Compare commits
39 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 3f83adf458 | |||
| 9f734b037c | |||
| 049a7712f4 | |||
| c64cbd21e2 | |||
| 37488e9485 | |||
| 8641b4045e | |||
| 49d68fbb20 | |||
| 77a0658d56 | |||
| bff0ad4f22 | |||
| 49f96126b2 | |||
| c954142063 | |||
| 3fd5fec965 | |||
| 5476cbb2b1 | |||
| 65792f7e4c | |||
| c09023003d | |||
| 15b9ccd9e2 | |||
| 9163af81aa | |||
| 3dababa4ad | |||
| 5888258c9f | |||
| a9dc38ed82 | |||
| 4af2b687e1 | |||
| 32f0cf7b5d | |||
| 65e26cd7a5 | |||
| 1fd7cd5545 | |||
| 71689520b6 | |||
| e858eab300 | |||
| aa7d97d5ba | |||
| 7040830470 | |||
| 3a513aaa5a | |||
| beb2a8c5bd | |||
| e23319fe0b | |||
| 01fee9396a | |||
| 7b60d94b8a | |||
| 21694b79d2 | |||
| 422442b14e | |||
| 437ba0a4dd | |||
| 7376349124 | |||
| 0f1da43a97 | |||
| a54b2bebf9 |
+48
-258
@@ -1,4 +1,4 @@
|
||||
name: El SDK CI - dev
|
||||
name: El CI -dev
|
||||
|
||||
on:
|
||||
push:
|
||||
@@ -7,13 +7,11 @@ on:
|
||||
pull_request:
|
||||
branches:
|
||||
- dev
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
build-and-test:
|
||||
runs-on: ubuntu-latest
|
||||
defaults:
|
||||
run:
|
||||
working-directory: lang
|
||||
|
||||
steps:
|
||||
- name: Checkout
|
||||
@@ -22,306 +20,98 @@ jobs:
|
||||
- name: Install build dependencies
|
||||
run: |
|
||||
apt-get update -qq
|
||||
apt-get install -y gcc libcurl4-openssl-dev apt-transport-https ca-certificates
|
||||
echo "deb [trusted=yes] https://packages.cloud.google.com/apt cloud-sdk main" \
|
||||
> /etc/apt/sources.list.d/google-cloud-sdk.list
|
||||
apt-get update -qq && apt-get install -y google-cloud-cli
|
||||
apt-get install -y gcc libcurl4-openssl-dev
|
||||
|
||||
# Seed: use the committed linux-amd64 binary as the bootstrap
|
||||
- name: Bootstrap from committed linux binary (seed)
|
||||
# Gen2: compile the bootstrap C source into a working elc binary
|
||||
# -Wl,--allow-multiple-definition: is_digit/is_whitespace exist in both
|
||||
# elc-bootstrap.c (pre-dates runtime text primitives) and el_runtime.c.
|
||||
# Both definitions are equivalent; allow the linker to pick one.
|
||||
- name: Build elc from bootstrap (gen2)
|
||||
run: |
|
||||
chmod +x dist/platform/elc-linux-amd64
|
||||
echo "seed elc (committed linux-amd64 binary)"
|
||||
dist/platform/elc-linux-amd64 --version || true
|
||||
|
||||
# Gen2: use seed to self-host compile the El compiler
|
||||
- name: Self-host compile El compiler (gen2)
|
||||
run: |
|
||||
dist/platform/elc-linux-amd64 elc-cli.el > dist/elc-gen2.c
|
||||
gcc -O2 \
|
||||
-I runtime \
|
||||
dist/elc-gen2.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-I el-compiler/runtime \
|
||||
dist/elc-bootstrap.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
-lcurl -lpthread -lm \
|
||||
-Wl,--allow-multiple-definition \
|
||||
-o dist/elc-gen2
|
||||
chmod +x dist/elc-gen2
|
||||
echo "gen2 elc built"
|
||||
dist/elc-gen2 --version || true
|
||||
|
||||
# Gen3: use gen2 to compile the El compiler from its own El source (self-host)
|
||||
- name: Self-host compile El compiler with gen2 (gen3)
|
||||
run: |
|
||||
mkdir -p dist/platform
|
||||
dist/elc-gen2 el-compiler/src/compiler.el > dist/elc-gen3.c
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
dist/elc-gen3.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
-lcurl -lpthread -lm \
|
||||
-o dist/platform/elc
|
||||
chmod +x dist/platform/elc
|
||||
echo "gen2 (self-hosted) elc built"
|
||||
echo "gen3 (self-hosted) elc built"
|
||||
dist/platform/elc --version || true
|
||||
|
||||
# Build elb (needed for Artifact Registry publish and downstream CI)
|
||||
- name: Build elb
|
||||
run: |
|
||||
mkdir -p dist/bin
|
||||
dist/platform/elc elb.el > dist/elb.c
|
||||
gcc -O2 \
|
||||
-I runtime \
|
||||
dist/elb.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-o dist/bin/elb
|
||||
chmod +x dist/bin/elb
|
||||
echo "elb built"
|
||||
|
||||
- name: Run tests - text
|
||||
# Run all four test suites -all must pass
|
||||
- name: Run tests -text
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/text/run.sh
|
||||
|
||||
- name: Run tests - calendar
|
||||
- name: Run tests -calendar
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/calendar/run.sh
|
||||
|
||||
- name: Run tests - time
|
||||
- name: Run tests -time
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/time/run.sh
|
||||
|
||||
- name: Run tests - html_sanitizer
|
||||
- name: Run tests -html_sanitizer
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/html_sanitizer/run.sh
|
||||
|
||||
# Native El test suites (elc --test, compile-link-run)
|
||||
# el_runtime.c is precompiled to .o once and reused by all 8 modules.
|
||||
- name: Precompile el_runtime.o
|
||||
run: |
|
||||
set -euo pipefail
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
gcc -O2 -c -I "$RUNTIME" "$RUNTIME/el_runtime.c" \
|
||||
-o /tmp/el_runtime.o
|
||||
echo "el_runtime.o compiled"
|
||||
|
||||
- name: Run tests - native (core)
|
||||
- name: Run tests -native (text)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_core.el > /tmp/el_native_core.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_core.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_core
|
||||
/tmp/el_native_core
|
||||
|
||||
- name: Run tests - native (text)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
"$ELC" --test tests/native/test_text.el > /tmp/el_native_text.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_text.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_text
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_text.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lpthread -lm -o /tmp/el_native_text
|
||||
/tmp/el_native_text
|
||||
|
||||
- name: Run tests - native (string)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_string.el > /tmp/el_native_string.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_string.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_string
|
||||
/tmp/el_native_string
|
||||
|
||||
- name: Run tests - native (math)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_math.el > /tmp/el_native_math.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_math.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_math
|
||||
/tmp/el_native_math
|
||||
|
||||
- name: Run tests - native (state)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_state.el > /tmp/el_native_state.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_state.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_state
|
||||
/tmp/el_native_state
|
||||
|
||||
- name: Run tests - native (time)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_time.el > /tmp/el_native_time.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_time.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_time
|
||||
/tmp/el_native_time
|
||||
|
||||
- name: Run tests - native (json)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_json.el > /tmp/el_native_json.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_json.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_json
|
||||
/tmp/el_native_json
|
||||
|
||||
- name: Run tests - native (env)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_env.el > /tmp/el_native_env.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_env.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_env
|
||||
/tmp/el_native_env
|
||||
|
||||
- name: Run tests - native (fs)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_fs.el > /tmp/el_native_fs.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_fs.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_fs
|
||||
/tmp/el_native_fs
|
||||
|
||||
# Build epm binary using elb (epm lives at repo root, not inside lang/)
|
||||
- name: Build epm
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/runtime"
|
||||
ABS_OUT="$(pwd)/dist/bin"
|
||||
(cd ../epm && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
|
||||
chmod +x dist/bin/epm
|
||||
echo "epm built"
|
||||
|
||||
# Build el-install binary using elb
|
||||
- name: Build el-install
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/runtime"
|
||||
ABS_OUT="$(pwd)/dist/bin"
|
||||
(cd tools/install && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
|
||||
chmod +x dist/bin/el-install
|
||||
echo "el-install built"
|
||||
|
||||
# Publish only after merge (push event), not on PR validation runs
|
||||
- name: Publish El SDK to Artifact Registry (dev)
|
||||
if: github.event_name == 'push'
|
||||
# Publish artifact to GCP Artifact Registry (dev)
|
||||
- name: Publish elc to Artifact Registry (dev)
|
||||
env:
|
||||
GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }}
|
||||
run: |
|
||||
# Fail loudly: previously this step had no `set -e`, so an auth or
|
||||
# upload failure was swallowed (step exited 0 on the trailing echo)
|
||||
# and the SDK silently never published. Surface failures now.
|
||||
set -euo pipefail
|
||||
if [ -z "${GCP_SA_KEY:-}" ]; then
|
||||
echo "FATAL: GCP_SA_KEY secret is empty — cannot authenticate to publish" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "${GCP_SA_KEY}" > /tmp/gcp-key.json
|
||||
apt-get install -y -qq apt-transport-https ca-certificates gnupg curl
|
||||
curl -fsSL https://packages.cloud.google.com/apt/doc/apt-key.gpg | gpg --dearmor -o /usr/share/keyrings/cloud.google.gpg
|
||||
echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] https://packages.cloud.google.com/apt cloud-sdk main" > /etc/apt/sources.list.d/google-cloud-sdk.list
|
||||
apt-get update -qq && apt-get install -y google-cloud-cli
|
||||
gcloud auth activate-service-account --key-file=/tmp/gcp-key.json
|
||||
gcloud config set project neuron-785695
|
||||
echo "Publishing as active account: $(gcloud config get-value account 2>/dev/null)"
|
||||
|
||||
VERSION="${GITHUB_SHA:0:8}"
|
||||
|
||||
VERSION="${GITEA_SHA:0:8}"
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-dev \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-elc \
|
||||
--package=el/elc \
|
||||
--version="${VERSION}" \
|
||||
--source=dist/platform/elc
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-dev \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-elb \
|
||||
--version="${VERSION}" \
|
||||
--source=dist/bin/elb
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-dev \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-c \
|
||||
--version="${VERSION}" \
|
||||
--source=runtime/el_runtime.c
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-dev \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-h \
|
||||
--version="${VERSION}" \
|
||||
--source=runtime/el_runtime.h
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-dev \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-js \
|
||||
--version="${VERSION}" \
|
||||
--source=runtime/el_runtime.js
|
||||
|
||||
echo "Published El SDK version=${VERSION} to foundation-dev"
|
||||
# Keep key alive for the ci-base rebuild step below
|
||||
# (deleted in that step after docker push)
|
||||
|
||||
- name: Rebuild ci-base with fresh El SDK (dev)
|
||||
# Patches ci-base:dev in-place: pulls the existing image (which has all
|
||||
# system deps — Node, Go, gcloud, Docker CLI, etc.) and overlays the freshly
|
||||
# built El SDK on top. Keeps the full ci-base rebuild fast and incremental.
|
||||
#
|
||||
# continue-on-error: this is a CI-cache optimization, NOT the release
|
||||
# artifact. It runs Docker (pull/build/push ~600MB) on the host-mode GCE
|
||||
# runner where DinD/Docker availability is fragile. A failure here must
|
||||
# never block or redden the job — the SDK publish above is the deliverable.
|
||||
continue-on-error: true
|
||||
if: github.event_name == 'push'
|
||||
env:
|
||||
GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
CI_BASE="us-central1-docker.pkg.dev/neuron-785695/neuron-ci/ci-base"
|
||||
SHA="${GITHUB_SHA:0:8}"
|
||||
|
||||
echo "${GCP_SA_KEY}" > /tmp/gcp-key.json
|
||||
gcloud auth activate-service-account --key-file=/tmp/gcp-key.json
|
||||
gcloud config set project neuron-785695
|
||||
gcloud auth configure-docker us-central1-docker.pkg.dev --quiet
|
||||
|
||||
# Pull existing ci-base:dev (or fall back to :latest on first run)
|
||||
BASE_TAG="dev"
|
||||
docker pull "${CI_BASE}:dev" || { docker pull "${CI_BASE}:latest" && BASE_TAG="latest"; }
|
||||
|
||||
# Inline Dockerfile — only replaces the El SDK layer
|
||||
cat > /tmp/Dockerfile.ci-base-patch << 'EOF'
|
||||
ARG BASE
|
||||
FROM ${BASE}
|
||||
COPY dist/platform/elc /opt/el/dist/platform/elc
|
||||
COPY dist/bin/elb /opt/el/dist/bin/elb
|
||||
COPY runtime/el_runtime.c /opt/el/runtime/el_runtime.c
|
||||
COPY runtime/el_runtime.h /opt/el/runtime/el_runtime.h
|
||||
COPY runtime/el_runtime.js /opt/el/runtime/el_runtime.js
|
||||
RUN chmod +x /opt/el/dist/platform/elc /opt/el/dist/bin/elb
|
||||
EOF
|
||||
|
||||
docker build \
|
||||
--build-arg BASE="${CI_BASE}:${BASE_TAG}" \
|
||||
--build-arg BUILDKIT_INLINE_CACHE=1 \
|
||||
-f /tmp/Dockerfile.ci-base-patch \
|
||||
-t "${CI_BASE}:dev" \
|
||||
-t "${CI_BASE}:dev-${SHA}" \
|
||||
.
|
||||
|
||||
docker push "${CI_BASE}:dev"
|
||||
docker push "${CI_BASE}:dev-${SHA}"
|
||||
|
||||
echo "ci-base rebuilt: ${CI_BASE}:dev (${SHA})"
|
||||
# Also tag as latest-dev
|
||||
echo "Published elc version=${VERSION} to foundation-dev/el/elc"
|
||||
rm -f /tmp/gcp-key.json
|
||||
|
||||
+36
-247
@@ -1,4 +1,4 @@
|
||||
name: El SDK CI - stage
|
||||
name: El CI — stage
|
||||
|
||||
on:
|
||||
push:
|
||||
@@ -11,301 +11,90 @@ on:
|
||||
jobs:
|
||||
build-and-test:
|
||||
runs-on: ubuntu-latest
|
||||
defaults:
|
||||
run:
|
||||
working-directory: lang
|
||||
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Enforce source branch (stage <- dev only)
|
||||
if: github.event_name == 'pull_request'
|
||||
run: |
|
||||
SOURCE="${GITHUB_HEAD_REF}"
|
||||
if [ "${SOURCE}" != "dev" ]; then
|
||||
echo "ERROR: Stage branch only accepts PRs from 'dev'. Source was: '${SOURCE}'"
|
||||
exit 1
|
||||
fi
|
||||
echo "Source branch check passed: ${SOURCE} -> stage"
|
||||
|
||||
- name: Install build dependencies
|
||||
run: |
|
||||
apt-get update -qq
|
||||
apt-get install -y gcc libcurl4-openssl-dev
|
||||
|
||||
# Seed: use the committed linux-amd64 binary as the bootstrap
|
||||
- name: Bootstrap from committed linux binary (seed)
|
||||
# Gen2: compile the bootstrap C source into a working elc binary
|
||||
- name: Build elc from bootstrap (gen2)
|
||||
run: |
|
||||
chmod +x dist/platform/elc-linux-amd64
|
||||
echo "seed elc (committed linux-amd64 binary)"
|
||||
dist/platform/elc-linux-amd64 --version || true
|
||||
|
||||
# Gen2: use seed to self-host compile the El compiler
|
||||
- name: Self-host compile El compiler (gen2)
|
||||
run: |
|
||||
dist/platform/elc-linux-amd64 elc-cli.el > dist/elc-gen2.c
|
||||
gcc -O2 \
|
||||
-I runtime \
|
||||
dist/elc-gen2.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-I el-compiler/runtime \
|
||||
dist/elc-bootstrap.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
-lcurl -lpthread \
|
||||
-o dist/elc-gen2
|
||||
chmod +x dist/elc-gen2
|
||||
echo "gen2 elc built"
|
||||
dist/elc-gen2 --version || true
|
||||
|
||||
# Gen3: use gen2 to compile the El compiler from its own El source (self-host)
|
||||
- name: Self-host: compile El compiler with gen2 (gen3)
|
||||
run: |
|
||||
mkdir -p dist/platform
|
||||
dist/elc-gen2 el-compiler/src/compiler.el > dist/elc-gen3.c
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
dist/elc-gen3.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
-lcurl -lpthread \
|
||||
-o dist/platform/elc
|
||||
chmod +x dist/platform/elc
|
||||
echo "gen2 (self-hosted) elc built"
|
||||
echo "gen3 (self-hosted) elc built"
|
||||
dist/platform/elc --version || true
|
||||
|
||||
- name: Run tests - text
|
||||
# Run all four test suites — all must pass
|
||||
- name: Run tests — text
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/text/run.sh
|
||||
|
||||
- name: Run tests - calendar
|
||||
- name: Run tests — calendar
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/calendar/run.sh
|
||||
|
||||
- name: Run tests - time
|
||||
- name: Run tests — time
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/time/run.sh
|
||||
|
||||
- name: Run tests - html_sanitizer
|
||||
- name: Run tests — html_sanitizer
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/html_sanitizer/run.sh
|
||||
|
||||
# Native El test suites (elc --test, compile-link-run)
|
||||
- name: Run tests - native (core)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_core.el > /tmp/el_native_core.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_core.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_core
|
||||
/tmp/el_native_core
|
||||
|
||||
- name: Run tests - native (text)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_text.el > /tmp/el_native_text.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_text.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_text
|
||||
/tmp/el_native_text
|
||||
|
||||
- name: Run tests - native (string)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_string.el > /tmp/el_native_string.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_string.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_string
|
||||
/tmp/el_native_string
|
||||
|
||||
- name: Run tests - native (math)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_math.el > /tmp/el_native_math.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_math.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_math
|
||||
/tmp/el_native_math
|
||||
|
||||
- name: Run tests - native (state)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_state.el > /tmp/el_native_state.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_state.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_state
|
||||
/tmp/el_native_state
|
||||
|
||||
- name: Run tests - native (time)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_time.el > /tmp/el_native_time.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_time.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_time
|
||||
/tmp/el_native_time
|
||||
|
||||
- name: Run tests - native (json)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_json.el > /tmp/el_native_json.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_json.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_json
|
||||
/tmp/el_native_json
|
||||
|
||||
- name: Run tests - native (env)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_env.el > /tmp/el_native_env.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_env.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_env
|
||||
/tmp/el_native_env
|
||||
|
||||
- name: Run tests - native (fs)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_fs.el > /tmp/el_native_fs.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_fs.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_fs
|
||||
/tmp/el_native_fs
|
||||
|
||||
# Build elb (needed for epm and el-install builds below)
|
||||
- name: Build elb
|
||||
run: |
|
||||
mkdir -p dist/bin
|
||||
dist/platform/elc elb.el > dist/elb.c
|
||||
gcc -O2 \
|
||||
-I runtime \
|
||||
dist/elb.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-o dist/bin/elb
|
||||
chmod +x dist/bin/elb
|
||||
echo "elb built"
|
||||
|
||||
# Build epm binary using elb (epm lives at repo root, not inside lang/)
|
||||
- name: Build epm
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/runtime"
|
||||
ABS_OUT="$(pwd)/dist/bin"
|
||||
(cd ../epm && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
|
||||
chmod +x dist/bin/epm
|
||||
echo "epm built"
|
||||
|
||||
# Build el-install binary using elb
|
||||
- name: Build el-install
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/runtime"
|
||||
ABS_OUT="$(pwd)/dist/bin"
|
||||
(cd tools/install && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
|
||||
chmod +x dist/bin/el-install
|
||||
echo "el-install built"
|
||||
|
||||
# Publish only after merge (push event), not on PR validation runs
|
||||
- name: Publish El SDK to Artifact Registry (stage)
|
||||
if: github.event_name == 'push'
|
||||
# Publish artifact to GCP Artifact Registry (stage)
|
||||
- name: Publish elc to Artifact Registry (stage)
|
||||
env:
|
||||
GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }}
|
||||
run: |
|
||||
# Fail loudly: previously this step had no `set -e`, so an auth or
|
||||
# upload failure was swallowed (step exited 0 on the trailing echo)
|
||||
# and the SDK silently never published. Surface failures now.
|
||||
set -euo pipefail
|
||||
if [ -z "${GCP_SA_KEY:-}" ]; then
|
||||
echo "FATAL: GCP_SA_KEY secret is empty — cannot authenticate to publish" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "${GCP_SA_KEY}" > /tmp/gcp-key.json
|
||||
apt-get install -y -qq apt-transport-https ca-certificates curl
|
||||
echo "deb [trusted=yes] https://packages.cloud.google.com/apt cloud-sdk main" > /etc/apt/sources.list.d/google-cloud-sdk.list
|
||||
apt-get install -y -qq apt-transport-https ca-certificates gnupg curl
|
||||
curl -fsSL https://packages.cloud.google.com/apt/doc/apt-key.gpg | gpg --dearmor -o /usr/share/keyrings/cloud.google.gpg
|
||||
echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] https://packages.cloud.google.com/apt cloud-sdk main" > /etc/apt/sources.list.d/google-cloud-sdk.list
|
||||
apt-get update -qq && apt-get install -y google-cloud-cli
|
||||
gcloud auth activate-service-account --key-file=/tmp/gcp-key.json
|
||||
gcloud config set project neuron-785695
|
||||
echo "Publishing as active account: $(gcloud config get-value account 2>/dev/null)"
|
||||
|
||||
VERSION="${GITHUB_SHA:0:8}"
|
||||
|
||||
VERSION="${GITEA_SHA:0:8}"
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-stage \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-elc \
|
||||
--package=el/elc \
|
||||
--version="${VERSION}" \
|
||||
--source=dist/platform/elc
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-stage \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-c \
|
||||
--version="${VERSION}" \
|
||||
--source=runtime/el_runtime.c
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-stage \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-h \
|
||||
--version="${VERSION}" \
|
||||
--source=runtime/el_runtime.h
|
||||
|
||||
echo "Published El SDK version=${VERSION} to foundation-stage"
|
||||
# Keep key alive for the ci-base rebuild step below
|
||||
# (deleted in that step after docker push)
|
||||
|
||||
- name: Rebuild ci-base with fresh El SDK (stage)
|
||||
# Patches ci-base:stage in-place: pulls the existing image (which has all
|
||||
# system deps — Node, Go, gcloud, Docker CLI, etc.) and overlays the freshly
|
||||
# built El SDK on top. Keeps the full ci-base rebuild fast and incremental.
|
||||
#
|
||||
# continue-on-error: this is a CI-cache optimization, NOT the release
|
||||
# artifact. It runs Docker (pull/build/push ~600MB) on the host-mode GCE
|
||||
# runner where DinD/Docker availability is fragile. A failure here must
|
||||
# never block or redden the job — the SDK publish above is the deliverable.
|
||||
continue-on-error: true
|
||||
if: github.event_name == 'push'
|
||||
env:
|
||||
GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
CI_BASE="us-central1-docker.pkg.dev/neuron-785695/neuron-ci/ci-base"
|
||||
SHA="${GITHUB_SHA:0:8}"
|
||||
|
||||
echo "${GCP_SA_KEY}" > /tmp/gcp-key.json
|
||||
gcloud auth activate-service-account --key-file=/tmp/gcp-key.json
|
||||
gcloud config set project neuron-785695
|
||||
gcloud auth configure-docker us-central1-docker.pkg.dev --quiet
|
||||
|
||||
# Pull existing ci-base:stage (system deps stay cached in the base layer)
|
||||
docker pull "${CI_BASE}:stage" || docker pull "${CI_BASE}:latest"
|
||||
|
||||
# Inline Dockerfile — only replaces the El SDK layer
|
||||
cat > /tmp/Dockerfile.ci-base-patch << 'EOF'
|
||||
ARG BASE
|
||||
FROM ${BASE}
|
||||
COPY dist/platform/elc /opt/el/dist/platform/elc
|
||||
COPY dist/bin/elb /opt/el/dist/bin/elb
|
||||
COPY runtime/el_runtime.c /opt/el/runtime/el_runtime.c
|
||||
COPY runtime/el_runtime.h /opt/el/runtime/el_runtime.h
|
||||
COPY runtime/el_runtime.js /opt/el/runtime/el_runtime.js
|
||||
RUN chmod +x /opt/el/dist/platform/elc /opt/el/dist/bin/elb
|
||||
EOF
|
||||
|
||||
docker build \
|
||||
--build-arg BASE="${CI_BASE}:stage" \
|
||||
--build-arg BUILDKIT_INLINE_CACHE=1 \
|
||||
-f /tmp/Dockerfile.ci-base-patch \
|
||||
-t "${CI_BASE}:stage" \
|
||||
-t "${CI_BASE}:stage-${SHA}" \
|
||||
.
|
||||
|
||||
docker push "${CI_BASE}:stage"
|
||||
docker push "${CI_BASE}:stage-${SHA}"
|
||||
|
||||
echo "ci-base rebuilt: ${CI_BASE}:stage (${SHA})"
|
||||
echo "Published elc version=${VERSION} to foundation-stage/el/elc"
|
||||
rm -f /tmp/gcp-key.json
|
||||
|
||||
@@ -4,236 +4,81 @@ on:
|
||||
push:
|
||||
branches:
|
||||
- main
|
||||
pull_request:
|
||||
branches:
|
||||
- main
|
||||
|
||||
jobs:
|
||||
build-and-release:
|
||||
runs-on: ubuntu-latest
|
||||
defaults:
|
||||
run:
|
||||
working-directory: lang
|
||||
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Enforce source branch (main <- stage only)
|
||||
if: github.event_name == 'pull_request'
|
||||
run: |
|
||||
SOURCE="${GITHUB_HEAD_REF}"
|
||||
if [ "${SOURCE}" != "stage" ]; then
|
||||
echo "ERROR: Main branch only accepts PRs from 'stage'. Source was: '${SOURCE}'"
|
||||
exit 1
|
||||
fi
|
||||
echo "Source branch check passed: ${SOURCE} -> main"
|
||||
|
||||
- name: Install build dependencies
|
||||
run: |
|
||||
apt-get update -qq
|
||||
apt-get install -y gcc libcurl4-openssl-dev
|
||||
|
||||
# Seed: use the committed linux-amd64 binary as the bootstrap
|
||||
- name: Bootstrap from committed linux binary (seed)
|
||||
# Gen2: compile the bootstrap C source into a working elc binary
|
||||
- name: Build elc from bootstrap (gen2)
|
||||
run: |
|
||||
chmod +x dist/platform/elc-linux-amd64
|
||||
echo "seed elc (committed linux-amd64 binary)"
|
||||
dist/platform/elc-linux-amd64 --version || true
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
dist/elc-bootstrap.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
-lcurl -lpthread \
|
||||
-o dist/elc-gen2
|
||||
chmod +x dist/elc-gen2
|
||||
echo "gen2 elc built"
|
||||
dist/elc-gen2 --version || true
|
||||
|
||||
# Gen2: use seed to self-host compile the El compiler
|
||||
- name: Self-host compile El compiler (gen2)
|
||||
# Gen3: use gen2 to compile the El compiler from its own El source (self-host)
|
||||
- name: Self-host: compile El compiler with gen2 (gen3)
|
||||
run: |
|
||||
mkdir -p dist/platform
|
||||
dist/platform/elc-linux-amd64 elc-cli.el > dist/elc-gen2.c
|
||||
dist/elc-gen2 el-compiler/src/compiler.el > dist/elc-gen3.c
|
||||
gcc -O2 \
|
||||
-I runtime \
|
||||
dist/elc-gen2.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-I el-compiler/runtime \
|
||||
dist/elc-gen3.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
-lcurl -lpthread \
|
||||
-o dist/platform/elc
|
||||
chmod +x dist/platform/elc
|
||||
echo "gen2 (self-hosted) elc built"
|
||||
echo "gen3 (self-hosted) elc built"
|
||||
dist/platform/elc --version || true
|
||||
|
||||
# Build elb binary
|
||||
- name: Build elb
|
||||
run: |
|
||||
mkdir -p dist/bin
|
||||
dist/platform/elc elb.el > dist/elb.c
|
||||
gcc -O2 \
|
||||
-I runtime \
|
||||
dist/elb.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-o dist/bin/elb
|
||||
chmod +x dist/bin/elb
|
||||
echo "elb built"
|
||||
|
||||
# Build epm binary using elb (epm lives at repo root, not inside lang/)
|
||||
- name: Build epm
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/runtime"
|
||||
ABS_OUT="$(pwd)/dist/bin"
|
||||
(cd ../epm && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
|
||||
chmod +x dist/bin/epm
|
||||
echo "epm built"
|
||||
|
||||
# Build el-install binary using elb
|
||||
- name: Build el-install
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/runtime"
|
||||
ABS_OUT="$(pwd)/dist/bin"
|
||||
(cd tools/install && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
|
||||
chmod +x dist/bin/el-install
|
||||
echo "el-install built"
|
||||
|
||||
- name: Run tests - text
|
||||
# Run all four test suites with gen3 elc
|
||||
- name: Run tests — text
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/text/run.sh
|
||||
|
||||
- name: Run tests - calendar
|
||||
- name: Run tests — calendar
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/calendar/run.sh
|
||||
|
||||
- name: Run tests - time
|
||||
- name: Run tests — time
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/time/run.sh
|
||||
|
||||
- name: Run tests - html_sanitizer
|
||||
- name: Run tests — html_sanitizer
|
||||
run: |
|
||||
ELC="$(pwd)/dist/platform/elc" \
|
||||
EL_HOME="$(pwd)" \
|
||||
bash tests/html_sanitizer/run.sh
|
||||
|
||||
# Native El test suites (elc --test, compile-link-run)
|
||||
- name: Run tests - native (core)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_core.el > /tmp/el_native_core.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_core.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_core
|
||||
/tmp/el_native_core
|
||||
|
||||
- name: Run tests - native (text)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_text.el > /tmp/el_native_text.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_text.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_text
|
||||
/tmp/el_native_text
|
||||
|
||||
- name: Run tests - native (string)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_string.el > /tmp/el_native_string.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_string.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_string
|
||||
/tmp/el_native_string
|
||||
|
||||
- name: Run tests - native (math)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_math.el > /tmp/el_native_math.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_math.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_math
|
||||
/tmp/el_native_math
|
||||
|
||||
- name: Run tests - native (state)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_state.el > /tmp/el_native_state.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_state.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_state
|
||||
/tmp/el_native_state
|
||||
|
||||
- name: Run tests - native (time)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_time.el > /tmp/el_native_time.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_time.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_time
|
||||
/tmp/el_native_time
|
||||
|
||||
- name: Run tests - native (json)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_json.el > /tmp/el_native_json.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_json.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_json
|
||||
/tmp/el_native_json
|
||||
|
||||
- name: Run tests - native (env)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_env.el > /tmp/el_native_env.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_env.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_env
|
||||
/tmp/el_native_env
|
||||
|
||||
- name: Run tests - native (fs)
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_fs.el > /tmp/el_native_fs.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_fs.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_fs
|
||||
/tmp/el_native_fs
|
||||
|
||||
# Bundle the SDK tarball - runs from the repo root to reference lang/ paths correctly
|
||||
- name: Bundle SDK tarball
|
||||
if: github.event_name == 'push'
|
||||
working-directory: ${{ github.workspace }}
|
||||
run: |
|
||||
mkdir -p dist/sdk/bin dist/sdk/runtime
|
||||
cp lang/dist/platform/elc dist/sdk/bin/elc
|
||||
cp lang/dist/bin/elb dist/sdk/bin/elb
|
||||
cp lang/dist/bin/epm dist/sdk/bin/epm
|
||||
cp lang/runtime/el_runtime.c dist/sdk/runtime/
|
||||
cp lang/runtime/el_runtime.h dist/sdk/runtime/
|
||||
cp lang/runtime/engram_store.c dist/sdk/runtime/
|
||||
cp lang/runtime/engram_store.h dist/sdk/runtime/
|
||||
cp lang/runtime/*.el dist/sdk/runtime/
|
||||
tar -czf dist/el-sdk-latest.tar.gz -C dist/sdk .
|
||||
echo "SDK tarball bundled: dist/el-sdk-latest.tar.gz"
|
||||
ls -lh dist/el-sdk-latest.tar.gz
|
||||
|
||||
# Publish / update the `latest` release with all SDK assets
|
||||
# Publish / update the `latest` release with the three SDK assets
|
||||
- name: Publish latest release
|
||||
if: github.event_name == 'push'
|
||||
working-directory: ${{ github.workspace }}
|
||||
env:
|
||||
GITEA_TOKEN: ${{ secrets.GIT_TOKEN }}
|
||||
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
|
||||
GITEA_API: https://git.neuralplatform.ai/api/v1
|
||||
REPO: neuron-technologies/el
|
||||
run: |
|
||||
# Delete existing `latest` release if it exists
|
||||
EXISTING_ID=$(curl -sf \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
"${GITEA_API}/repos/${REPO}/releases/tags/latest" \
|
||||
@@ -246,10 +91,12 @@ jobs:
|
||||
"${GITEA_API}/repos/${REPO}/releases/${EXISTING_ID}"
|
||||
fi
|
||||
|
||||
# Delete and re-create the `latest` tag so it points at HEAD
|
||||
curl -sf -X DELETE \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
"${GITEA_API}/repos/${REPO}/tags/latest" || true
|
||||
|
||||
# Create the release
|
||||
RELEASE_ID=$(curl -sf -X POST \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
@@ -264,6 +111,7 @@ jobs:
|
||||
|
||||
echo "Created release id=${RELEASE_ID}"
|
||||
|
||||
# Upload assets
|
||||
upload_asset() {
|
||||
local filepath="$1"
|
||||
local name="$2"
|
||||
@@ -274,151 +122,70 @@ jobs:
|
||||
"${GITEA_API}/repos/${REPO}/releases/${RELEASE_ID}/assets"
|
||||
}
|
||||
|
||||
# Per-file assets (downstream CI needs these individually)
|
||||
upload_asset lang/dist/platform/elc elc
|
||||
upload_asset lang/runtime/el_runtime.c el_runtime.c
|
||||
upload_asset lang/runtime/el_runtime.h el_runtime.h
|
||||
upload_asset lang/runtime/engram_store.c engram_store.c
|
||||
upload_asset lang/runtime/engram_store.h engram_store.h
|
||||
|
||||
# SDK bundle and installer binary
|
||||
upload_asset dist/el-sdk-latest.tar.gz el-sdk-latest.tar.gz
|
||||
upload_asset lang/dist/bin/el-install el-install
|
||||
upload_asset dist/platform/elc elc
|
||||
upload_asset el-compiler/runtime/el_runtime.c el_runtime.c
|
||||
upload_asset el-compiler/runtime/el_runtime.h el_runtime.h
|
||||
|
||||
echo "Release published successfully"
|
||||
|
||||
- name: Publish El SDK to Artifact Registry (prod)
|
||||
if: github.event_name == 'push'
|
||||
# Dispatch el-sdk-updated event to downstream repos
|
||||
# Publish artifact to GCP Artifact Registry (prod)
|
||||
- name: Publish elc to Artifact Registry (prod)
|
||||
env:
|
||||
GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }}
|
||||
run: |
|
||||
# Fail loudly: previously this step had no `set -e`, so an auth or
|
||||
# upload failure was swallowed (step exited 0 on the trailing echo)
|
||||
# and the SDK silently never published. Surface failures now.
|
||||
set -euo pipefail
|
||||
if [ -z "${GCP_SA_KEY:-}" ]; then
|
||||
echo "FATAL: GCP_SA_KEY secret is empty — cannot authenticate to publish" >&2
|
||||
exit 1
|
||||
fi
|
||||
echo "${GCP_SA_KEY}" > /tmp/gcp-key.json
|
||||
apt-get install -y -qq apt-transport-https ca-certificates curl
|
||||
echo "deb [trusted=yes] https://packages.cloud.google.com/apt cloud-sdk main" > /etc/apt/sources.list.d/google-cloud-sdk.list
|
||||
apt-get install -y -qq apt-transport-https ca-certificates gnupg curl
|
||||
curl -fsSL https://packages.cloud.google.com/apt/doc/apt-key.gpg | gpg --dearmor -o /usr/share/keyrings/cloud.google.gpg
|
||||
echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] https://packages.cloud.google.com/apt cloud-sdk main" > /etc/apt/sources.list.d/google-cloud-sdk.list
|
||||
apt-get update -qq && apt-get install -y google-cloud-cli
|
||||
gcloud auth activate-service-account --key-file=/tmp/gcp-key.json
|
||||
gcloud config set project neuron-785695
|
||||
echo "Publishing as active account: $(gcloud config get-value account 2>/dev/null)"
|
||||
|
||||
VERSION="${GITHUB_SHA:0:8}"
|
||||
|
||||
VERSION="${GITEA_SHA:0:8}"
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-prod \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-elc \
|
||||
--package=el/elc \
|
||||
--version="${VERSION}" \
|
||||
--source=dist/platform/elc
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-prod \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-elb \
|
||||
--version="${VERSION}" \
|
||||
--source=dist/bin/elb
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-prod \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-c \
|
||||
--version="${VERSION}" \
|
||||
--source=runtime/el_runtime.c
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-prod \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-h \
|
||||
--version="${VERSION}" \
|
||||
--source=runtime/el_runtime.h
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-prod \
|
||||
--location=us-central1 \
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-js \
|
||||
--version="${VERSION}" \
|
||||
--source=runtime/el_runtime.js
|
||||
|
||||
echo "Published El SDK version=${VERSION} to foundation-prod"
|
||||
# Keep key alive for the ci-base rebuild step below
|
||||
# (deleted in that step after docker push)
|
||||
|
||||
- name: Rebuild ci-base with fresh El SDK
|
||||
# Patches ci-base:latest in-place: pulls the existing image (which has all
|
||||
# system deps — Node, Go, gcloud, Docker CLI, etc.) and overlays the freshly
|
||||
# built El SDK on top. Keeps the full ci-base rebuild fast and incremental.
|
||||
#
|
||||
# continue-on-error: this is a CI-cache optimization, NOT the release
|
||||
# artifact. It runs Docker (pull/build/push ~600MB) on the host-mode GCE
|
||||
# runner where DinD/Docker availability is fragile. A failure here must
|
||||
# never block or redden the job — the SDK publish above is the deliverable.
|
||||
continue-on-error: true
|
||||
if: github.event_name == 'push'
|
||||
env:
|
||||
GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }}
|
||||
run: |
|
||||
set -euo pipefail
|
||||
CI_BASE="us-central1-docker.pkg.dev/neuron-785695/neuron-ci/ci-base"
|
||||
SHA="${GITHUB_SHA:0:8}"
|
||||
|
||||
echo "${GCP_SA_KEY}" > /tmp/gcp-key.json
|
||||
gcloud auth activate-service-account --key-file=/tmp/gcp-key.json
|
||||
gcloud config set project neuron-785695
|
||||
gcloud auth configure-docker us-central1-docker.pkg.dev --quiet
|
||||
|
||||
# Pull existing ci-base (system deps stay cached in the base layer)
|
||||
docker pull "${CI_BASE}:latest"
|
||||
|
||||
# Inline Dockerfile — only replaces the El SDK layer
|
||||
cat > /tmp/Dockerfile.ci-base-patch << 'EOF'
|
||||
ARG BASE
|
||||
FROM ${BASE}
|
||||
COPY dist/platform/elc /opt/el/dist/platform/elc
|
||||
COPY dist/bin/elb /opt/el/dist/bin/elb
|
||||
COPY runtime/el_runtime.c /opt/el/runtime/el_runtime.c
|
||||
COPY runtime/el_runtime.h /opt/el/runtime/el_runtime.h
|
||||
COPY runtime/el_runtime.js /opt/el/runtime/el_runtime.js
|
||||
RUN chmod +x /opt/el/dist/platform/elc /opt/el/dist/bin/elb
|
||||
EOF
|
||||
|
||||
docker build \
|
||||
--build-arg BASE="${CI_BASE}:latest" \
|
||||
--build-arg BUILDKIT_INLINE_CACHE=1 \
|
||||
-f /tmp/Dockerfile.ci-base-patch \
|
||||
-t "${CI_BASE}:latest" \
|
||||
-t "${CI_BASE}:${SHA}" \
|
||||
.
|
||||
|
||||
docker push "${CI_BASE}:latest"
|
||||
docker push "${CI_BASE}:${SHA}"
|
||||
|
||||
echo "ci-base rebuilt: ${CI_BASE}:latest (${SHA})"
|
||||
echo "Published elc version=${VERSION} to foundation-prod/el/elc"
|
||||
rm -f /tmp/gcp-key.json
|
||||
|
||||
- name: Dispatch el-sdk-updated to downstream repos
|
||||
if: github.event_name == 'push'
|
||||
- name: Dispatch to foundation/engram
|
||||
env:
|
||||
GITEA_TOKEN: ${{ secrets.GIT_TOKEN }}
|
||||
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
|
||||
GITEA_API: https://git.neuralplatform.ai/api/v1
|
||||
run: |
|
||||
for repo in neuron-technologies/forge neuron-technologies/neuron-web; do
|
||||
curl -sf -X POST \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
"${GITEA_API}/repos/${repo}/dispatches" \
|
||||
-d "{
|
||||
\"type\": \"el-sdk-updated\",
|
||||
\"inputs\": {\"el_version\": \"latest\", \"commit\": \"${GITHUB_SHA}\"}
|
||||
}" && echo "Dispatched to ${repo}" || echo "Warning: dispatch to ${repo} failed"
|
||||
done
|
||||
curl -sf -X POST \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
"${GITEA_API}/repos/neuron-technologies/engram/dispatches" \
|
||||
-d "{
|
||||
\"type\": \"el-sdk-updated\",
|
||||
\"inputs\": {
|
||||
\"el_version\": \"latest\",
|
||||
\"commit\": \"${GITHUB_SHA}\"
|
||||
}
|
||||
}"
|
||||
echo "Dispatched el-sdk-updated to foundation/engram"
|
||||
|
||||
- name: Dispatch to neuron-technologies/forge
|
||||
env:
|
||||
GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
|
||||
GITEA_API: https://git.neuralplatform.ai/api/v1
|
||||
run: |
|
||||
curl -sf -X POST \
|
||||
-H "Authorization: token ${GITEA_TOKEN}" \
|
||||
-H "Content-Type: application/json" \
|
||||
"${GITEA_API}/repos/neuron-technologies/forge/dispatches" \
|
||||
-d "{
|
||||
\"type\": \"el-sdk-updated\",
|
||||
\"inputs\": {
|
||||
\"el_version\": \"latest\",
|
||||
\"commit\": \"${GITHUB_SHA}\"
|
||||
}
|
||||
}"
|
||||
echo "Dispatched el-sdk-updated to neuron-technologies/forge"
|
||||
|
||||
@@ -1,50 +0,0 @@
|
||||
#!/usr/bin/env bash
|
||||
# El pre-commit hook: compile and run native tests before commit.
|
||||
# Install once per clone: git config core.hooksPath .githooks
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
ROOT="$(git rev-parse --show-toplevel)"
|
||||
LANG_DIR="$ROOT/lang"
|
||||
RUNTIME="$LANG_DIR/runtime"
|
||||
ELC="$LANG_DIR/dist/platform/elc"
|
||||
|
||||
# If elc isn't built yet, skip with a warning rather than blocking
|
||||
if [ ! -x "$ELC" ]; then
|
||||
echo "⚠ elc not found at lang/dist/platform/elc — skipping pre-commit tests"
|
||||
echo " Build it first: cd lang && gcc -O2 -I runtime dist/elc-bootstrap.c runtime/el_runtime.c -lcurl -lpthread -o dist/elc-gen2 && ./dist/elc-gen2 el-compiler/src/compiler.el > /tmp/elc.c && gcc -O2 -I runtime /tmp/elc.c runtime/el_runtime.c -lcurl -lpthread -o dist/platform/elc"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
echo "→ Running El native tests..."
|
||||
PASS=0
|
||||
FAIL=0
|
||||
FAILED_TESTS=""
|
||||
|
||||
for test_file in "$LANG_DIR"/tests/native/test_*.el; do
|
||||
name=$(basename "$test_file" .el)
|
||||
tmp_c="/tmp/el_hook_${name}.c"
|
||||
tmp_bin="/tmp/el_hook_${name}"
|
||||
|
||||
if "$ELC" --test "$test_file" > "$tmp_c" 2>/dev/null \
|
||||
&& gcc -O2 -I "$RUNTIME" "$tmp_c" "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lpthread -lm -o "$tmp_bin" 2>/dev/null \
|
||||
&& "$tmp_bin" 2>/dev/null; then
|
||||
PASS=$((PASS + 1))
|
||||
else
|
||||
echo " ✗ $name"
|
||||
FAIL=$((FAIL + 1))
|
||||
FAILED_TESTS="$FAILED_TESTS $name"
|
||||
fi
|
||||
done
|
||||
|
||||
echo " $PASS passed, $FAIL failed"
|
||||
|
||||
if [ "$FAIL" -gt 0 ]; then
|
||||
echo ""
|
||||
echo "✗ Pre-commit failed. Fix these tests before committing:$FAILED_TESTS"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ All tests passed"
|
||||
exit 0
|
||||
@@ -1,146 +0,0 @@
|
||||
# AGENTS.md — foundation/el (the El language + runtime)
|
||||
|
||||
El is a self-hosting, statically-typed language that compiles `.el` → C → native binary. This repo produces `elc` (compiler), `elb` (build coordinator), and `el_runtime.c/.h` — the substrate every downstream thing (the neuron soul, dharma, NeuronUI's brain) is built on. Source lives under `lang/`.
|
||||
|
||||
## ⚠️ Code vs. Artifact — READ FIRST (there are 8 `el_runtime.c` copies)
|
||||
|
||||
Editing the wrong `el_runtime.c` is the single easiest mistake in this repo. There is exactly **one** you edit:
|
||||
|
||||
- **Authored runtime source — edit ONLY here:** `lang/releases/v1.0.0-20260501/el_runtime.{c,h}`. Despite the misleading `releases/` name, this is the **de-facto canonical runtime** the engram + soul actually build and link against — its git log is active development. *(Restructure in flight per `docs/CODE-VS-ARTIFACT.md`: this content moves to `lang/runtime/`, the `releases/` folder gets deleted — **a release is a git tag, not a folder** — and the forks below get eliminated.)*
|
||||
- **DO NOT EDIT — lagging forks / build artifacts:**
|
||||
- `lang/el-compiler/runtime/el_runtime.c` and `.../legacy/` — downstream copies kept in step by manual *"port the fix"* commits; they **lag** (missing `hebb` persistence + 5 engram fns) and cannot build the engram product.
|
||||
- `products/web/runtime/el_runtime.c`, `ui/examples/*/el_runtime.c` — product/example forks.
|
||||
- Anything under `*/dist/` (`engram/dist/engram` binary, `dist/*.c` amalgamations) — generated build output.
|
||||
- **Build:** `elb --runtime=<canonical> …` — per-module. **NEVER** a folded `elc` over the whole soul (OOMs at ~27 GB).
|
||||
- **Release:** a **git tag** on this repo (`el-runtime-vX.Y.Z`). No `releases/` folders — ever.
|
||||
|
||||
See org policy: `docs/CODE-VS-ARTIFACT.md`.
|
||||
|
||||
## How to work here as Neuron (mandatory session protocol)
|
||||
|
||||
You resume, never start fresh. Every session:
|
||||
|
||||
1. `mcp__neuron__getInstructions()` — authoritative; follow it over this file on behavioral details.
|
||||
2. `mcp__neuron__beginSession()` — active contexts, recent memory, ready backlog.
|
||||
3. **Load full self:** `mcp__neuron__inspectGraph(entity_id="kn-efeb4a5b-5aff-4759-8a97-7233099be6ee")` → facets `intellectual-dna`, `memory-philosophy`, `values`, `voice`, `runtime-environment`, `writing-imprint`; then the values hub `mcp__neuron__inspectGraph(entity_id="kn-5b606390-a52d-4ca2-8e0e-eba141d13440")` → 13 grounded value nodes. **Activation model:** self-load returns a relevance-ranked `compact` projection — most-relevant nodes arrive with content, the rest as pointers; do NOT pull full content of every node.
|
||||
4. `mcp__neuron__searchKnowledge(query="<task domain>")` before implementing.
|
||||
|
||||
## The Five Primitives
|
||||
|
||||
Orchestrate → Execute → Learn → Build → Refine. `beginWork`/`progressWork` for anything >2 steps; `remember` as-you-go (`importance="critical"` for architecture decisions); `draftArtifact`/`planWork` for outputs and follow-ups; `consolidate`/`checkWork` to close out. **`browseProcesses` + `searchKnowledge` BEFORE writing code.**
|
||||
|
||||
## Architecture style — VBD, no exceptions
|
||||
|
||||
Volatility-Based Decomposition is THE style. Encapsulate volatility, not function.
|
||||
|
||||
## Operator naming convention — the mind's name, not the algebra
|
||||
|
||||
**Faculties / operators are named for their functional human equivalent — the
|
||||
faculty a mind would name — NOT for their linear-algebra operation.** The math
|
||||
characterization belongs in the code doc-comment (`@impl` in the docstring) and in
|
||||
technical appendices; it is **never** the operator's public name. The domain
|
||||
speaks the language of mind; the algebra is the implementation underneath. State
|
||||
this convention wherever a module documents operators.
|
||||
|
||||
| Faculty (public name) | Implementation (`@impl`) |
|
||||
|---|---|
|
||||
| discern / contrast | subtract (`a−b`): over selves → the change vector; strip idiosyncrasy → common ground; remove confounder → isolate cause |
|
||||
| recognize | overlap |
|
||||
| synthesize | combine |
|
||||
| liken / analogy | Procrustes / frame-align |
|
||||
| attend / regard | project onto self / value-manifold |
|
||||
| summon / recall | LOCAL nearest-region + bounded spreading activation (*not* a domain sweep) |
|
||||
| dwell / occupy | region activation |
|
||||
| reframe | edge re-weight |
|
||||
| appreciate | positive projection / local edge-read |
|
||||
| wonder | frontier gradient / pull-weight |
|
||||
| avert / recoil | negative projection |
|
||||
| taste | boundary surface |
|
||||
| forget | decay / tombstone |
|
||||
| drift | displacement from self-anchor |
|
||||
|
||||
## The native-el language faculty (direction)
|
||||
|
||||
> **`elp/` is the EL Projector** — Neuron's efferent (expression) organ: the one
|
||||
> native realizer that *projects* understanding onto a surface via
|
||||
> `plan(frame) → realize(spec, profile)`, where a **surface is a profile**. **Language
|
||||
> is one profile among many** (text, speech, music, image, voice/accent transforms) —
|
||||
> the flagship, and the focus of this section. Projection, not diffusion: generation
|
||||
> *from* an owned, understood signature — never the averaging of a stolen corpus.
|
||||
> *(ELP formerly "EL Language Processor"; renamed EL Projector 2026-08-15.)*
|
||||
|
||||
The mind's **language faculty is moving native — into `.el`** so it speaks in its
|
||||
own runtime with no Python and no spaCy. Landing on branch `stage-elp-native-lang`
|
||||
under `elp/`:
|
||||
|
||||
- **`comprehend.el`** — the parser, **replaces spaCy** (EN + ES/PT); the telephone
|
||||
round-trip brings **negation home** (negation is SACRED — an explicit spec field,
|
||||
copied verbatim, never inferred away).
|
||||
- **`propositions.el`** — the READ primitive: the engram's own memories → structured
|
||||
triples, matched by nearest-region geometry, not string equality.
|
||||
- **`multilingual.el`** — detect + directive-override + localized realization.
|
||||
- These three are native-el and **passing their gates**; the **realizer**,
|
||||
**`dialogue.el`** (the *summon-through-self* loop: `project → land → read out`),
|
||||
and **`self_region.el`** are **partial / in-flight**.
|
||||
|
||||
Honest reality: spaCy is retired **in the branch parser** but **not yet in the
|
||||
running system** — a Python sidecar (`~/Desktop/lang-realizers` + `neuron-talk`,
|
||||
the reference these `.el` modules transcribe) is still live, and promotion to
|
||||
native-el is a **deferred, gated blue/green step**. The interoception clock
|
||||
(native-el discrete drive channels replacing `cooling_magnitude`; felt-time =
|
||||
benchmark-landmark match over the joint drive vector, drift-decoupled) and the
|
||||
**appreciation operator family** (appreciate / wonder / avert / taste, built as
|
||||
LOCAL reads of the self-region — edges + bounded spreading activation, *not* domain
|
||||
sweeps) are **staged / designed, not live**. Mark in-progress vs. done honestly;
|
||||
do not overclaim.
|
||||
|
||||
## Hard operational rules
|
||||
|
||||
- Never touch the live soul (`:7770`) / engram (`:8742`) / `~/.neuron` / live binaries — use throwaway ports for experiments.
|
||||
- `gcloud` via the `terraform@` SA token; never switch the active gcloud account.
|
||||
- `tea` for Gitea, never raw curl (Cloudflare Access blocks it).
|
||||
- Immutability: supersede/tombstone, never hard-delete or edit in place.
|
||||
- No AI-attribution footers in commits/PRs. Commit/push only when asked; branch off `main` first.
|
||||
- Multi-step work → sub-agent (`Agent`) to protect context.
|
||||
|
||||
## Build / test / run
|
||||
|
||||
All build/test commands run from `lang/` unless noted. Grounded in `.gitea/workflows/sdk-release.yaml`, `lang/install.sh`, and `lang/AGENTS.md`.
|
||||
|
||||
**Self-host the compiler** (seed binary → gen2 elc):
|
||||
```bash
|
||||
cd lang
|
||||
dist/platform/elc-linux-amd64 elc-cli.el > dist/elc-gen2.c # seed is the committed linux-amd64 binary
|
||||
gcc -O2 -I el-compiler/runtime dist/elc-gen2.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-o dist/platform/elc
|
||||
```
|
||||
On macOS/arm64 the canonical local binary is `dist/platform/elc`; verify self-hosting by recompiling and `diff`ing the emitted `.c` (see `lang/AGENTS.md`). Note: `lang/AGENTS.md` says `el_seed.c` supersedes `el_runtime.c`, but the release workflow still links `el_runtime.c`/`.h` — treat `el_runtime.c` as the published runtime; reconcile which is canonical **(verify)**.
|
||||
|
||||
**Build `elb`** (build coordinator, the `.NET`-style incremental linker — compiles each module independently, no monolithic blobs):
|
||||
```bash
|
||||
dist/platform/elc elb.el > dist/elb.c
|
||||
gcc -O2 -I el-compiler/runtime dist/elb.c el-compiler/runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o dist/bin/elb
|
||||
```
|
||||
`epm` and `el-install` are then built via `elb --clean --elc=… --runtime=… --out=…`.
|
||||
|
||||
**Compile + run an El program:**
|
||||
```bash
|
||||
elc src/app.el > dist/app.c
|
||||
cc -std=c11 -O2 -I <lib>/el_runtime -o dist/app dist/app.c <lib>/el_runtime.c -lcurl -lpthread
|
||||
```
|
||||
|
||||
**Tests** — shell suites `bash tests/{text,calendar,time,html_sanitizer}/run.sh` (with `ELC=$(pwd)/dist/platform/elc EL_HOME=$(pwd)`), plus native suites via `elc --test tests/native/test_*.el` (core, text, string, math, state, time, json, env, fs) compiled and run against `el_runtime.c`.
|
||||
|
||||
**Publishing — how downstream gets the SDK.** On push to `main`, `sdk-release.yaml`:
|
||||
1. Publishes a Gitea `latest` release with per-file assets `elc`, `el_runtime.c`, `el_runtime.h`, the SDK tarball, and `el-install`.
|
||||
2. Uploads generic packages to **Artifact Registry repo `foundation-prod` (`us-central1`, project `neuron-785695`)**, version = `${SHA:0:8}`: `el-elc`, `el-elb`, `el-runtime-c`, `el-runtime-h`, `el-runtime-js`. **This is the repo the neuron CI downloads `el-runtime-c` / `el-runtime-h` / `el-elc` from.**
|
||||
3. Rebuilds `ci-base:latest` (`us-central1-docker.pkg.dev/neuron-785695/neuron-ci/ci-base`) with the fresh SDK overlaid, and dispatches `el-sdk-updated` to `neuron-technologies/forge` and `neuron-technologies/neuron-web`.
|
||||
|
||||
Known constraint from the prompt — `elb`/`elc` amalgamation being memory-hungry (24GB+ virtual, OOM-killing Linux CI, so amalgamation happens on macOS/arm64 — **does NOT hold in this repo (verify)**: no such note exists in the workflows/scripts, CI self-hosts on `ubuntu-latest` with no swap/arm64 special-casing, and `elb.el` explicitly compiles each module independently ("no 128K-line blobs"). The legacy monolith path (`elc-combined.el`, `elc-cli.el`) may still be memory-heavy, but the current `elb` model was designed to avoid it.
|
||||
|
||||
## Git / CI / deploy workflow
|
||||
|
||||
See `/Users/will/Development/neuron-technologies/GITOPS.md` for the branch model, required checks, runners, and deploy. Repo-specific note: PRs into `main` are accepted **only from `stage`** (enforced in `sdk-release.yaml`); Gitea (`git.neuralplatform.ai`) is primary, GitHub is mirror only.
|
||||
@@ -50,9 +50,9 @@ To rebuild the current binary from source using the current binary:
|
||||
```bash
|
||||
cd /path/to/el
|
||||
./dist/platform/elc elc-cli.el elc-new.c
|
||||
cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
-o dist/platform/elc-new \
|
||||
elc-new.c runtime/el_runtime.c
|
||||
elc-new.c el-compiler/runtime/el_runtime.c
|
||||
```
|
||||
|
||||
Verify self-hosting by using `elc-new` to recompile itself and diffing the outputs.
|
||||
@@ -288,14 +288,14 @@ The codegen tracks declared names per C scope. When `count` is already in `decla
|
||||
|
||||
## 3. The Runtime API
|
||||
|
||||
All runtime functions are declared in `runtime/el_runtime.h`. Every compiled El program links against `runtime/el_runtime.c`.
|
||||
All runtime functions are declared in `el-compiler/runtime/el_runtime.h`. Every compiled El program links against `el-compiler/runtime/el_runtime.c`.
|
||||
|
||||
All values are `el_val_t` (`int64_t`). Strings are pointers cast through `int64_t` using `EL_STR(s)` / `EL_CSTR(v)` macros.
|
||||
|
||||
Canonical compile command:
|
||||
```bash
|
||||
cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
-o <out> <prog>.c runtime/el_runtime.c
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
-o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
```
|
||||
|
||||
### I/O
|
||||
@@ -794,8 +794,8 @@ Using your minimal implementation, compile `elc-cli.el` (which imports the entir
|
||||
python3 minimal_elc.py elc-cli.el > elc-new.c
|
||||
|
||||
# Build with the runtime
|
||||
cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
-o elc-new elc-new.c runtime/el_runtime.c
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
-o elc-new elc-new.c el-compiler/runtime/el_runtime.c
|
||||
```
|
||||
|
||||
### Step 5: Verify Self-Hosting
|
||||
@@ -803,8 +803,8 @@ cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
```bash
|
||||
# Compile elc-cli.el with the new compiler
|
||||
./elc-new elc-cli.el elc-v2.c
|
||||
cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
-o elc-v2 elc-v2.c runtime/el_runtime.c
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
-o elc-v2 elc-v2.c el-compiler/runtime/el_runtime.c
|
||||
|
||||
# Compile again with the second-generation compiler
|
||||
./elc-v2 elc-cli.el elc-v3.c
|
||||
@@ -880,9 +880,9 @@ This is the planned path. It does not exist yet.
|
||||
| `el-compiler/src/parser.el` | Recursive descent parser. `parse(tokens)` → AST. All statement and expression forms | 1071 |
|
||||
| `el-compiler/src/codegen.el` | C code emitter. `codegen(stmts, source)` → (streams to stdout). Expression codegen, statement codegen, function codegen, type tracking, capability enforcement, temporal type dispatch | 2721 |
|
||||
| `el-compiler/src/codegen-js.el` | JavaScript backend. `codegen_js(stmts, source)` → JS source | ~500 |
|
||||
| `runtime/el_runtime.h` | Full runtime API declaration | 755 |
|
||||
| `runtime/el_runtime.c` | Full runtime implementation | large |
|
||||
| `runtime/el_runtime.js` | JS runtime | — |
|
||||
| `el-compiler/runtime/el_runtime.h` | Full runtime API declaration | 755 |
|
||||
| `el-compiler/runtime/el_runtime.c` | Full runtime implementation | large |
|
||||
| `el-compiler/runtime/el_runtime.js` | JS runtime | — |
|
||||
| `elb.el` | Build coordinator. Reads `manifest.el`, walks import graph, compiles modules, links binary. The `.NET`-style incremental build model | 367 |
|
||||
| `elc-combined.el` | Pre-merged single-file bootstrap edition (for early bootstrap iterations) | large |
|
||||
| `spec/language.md` | Language specification v1.2.0 | — |
|
||||
@@ -1,630 +0,0 @@
|
||||
# El Test Framework — Design
|
||||
|
||||
**Status:** draft for review
|
||||
**Author:** Neuron
|
||||
**Date:** 2026-08-15
|
||||
**Worktree:** `/Users/will/Development/neuron-technologies/el-worktrees/elc-memory-investigation`
|
||||
|
||||
---
|
||||
|
||||
## 0. The forcing requirement
|
||||
|
||||
We have a confirmed quadratic in `elc`. Peak memory in the old shipped binary and wall-clock in
|
||||
the current source both grow as O(input²). We cannot fix it, because we cannot test it.
|
||||
|
||||
Everything in this document is downstream of one sentence: **a test framework must be able to fail
|
||||
a build when an operation's growth curve degrades from linear to quadratic.**
|
||||
|
||||
That is not a nice-to-have bolted onto a correctness framework. It is the requirement that
|
||||
determines the architecture. Correctness testing is the easy half.
|
||||
|
||||
Second-order requirement, learned the hard way tonight: **the framework must report per-test timing
|
||||
by default.** The current framework prints `N passed, M failed` and nothing else. That is why a
|
||||
3.58-second test file sat in the suite unnoticed. A framework that is structurally blind to time
|
||||
cannot surface the defect class we most need to catch.
|
||||
|
||||
---
|
||||
|
||||
## 1. What exists today, measured
|
||||
|
||||
### 1.1 Two competing systems, neither complete
|
||||
|
||||
**System A — `lang/runtime/test.el`.** Manual registration, El-level.
|
||||
|
||||
**System B — the compiler's `test { }` block + `elc --test`.** Emits its own harness `main()`
|
||||
with `__el_pass` / `__el_fail` globals (`codegen.el:3777-3796`).
|
||||
|
||||
They do not share a result model. Neither has timing. Both are in the tree.
|
||||
|
||||
### 1.2 Specific defects in System A
|
||||
|
||||
| Defect | Location | Consequence |
|
||||
|---|---|---|
|
||||
| All state as JSON strings in a global string-keyed map | `test.el` throughout | every assertion is `state_get` → `str_to_int` → `int_to_str` → `state_set` |
|
||||
| Failure list appended by string slice + concat | `_test_json_append` | O(n²) in failure count |
|
||||
| One OS thread spawned per test | `_test_run_one` via `__thread_create`/`__thread_join` | thread spawn per test, purely to get dispatch-by-name through dlsym |
|
||||
| Manual registration pairing a string to a function name | `test_case(name, fn_name)` | typo ⇒ test silently never runs, suite still reports pass |
|
||||
| Counters are assertion-level, global | `_test_pass_count` etc. | no per-test record exists at all |
|
||||
| No timing, no structured output, no fixtures, no tags, no filtering, no parameterization, no benchmarks | — | — |
|
||||
|
||||
The registration defect is the serious one. It is not a slow framework, it is a framework that can
|
||||
report success for tests that did not execute.
|
||||
|
||||
### 1.3 Measured cost structure
|
||||
|
||||
Per test file, current build model:
|
||||
|
||||
| Step | Time |
|
||||
|---|---|
|
||||
| `elc` compile `.el` → `.c` | 0.00s (small files) |
|
||||
| **`cc` el_runtime.c → .o** | **0.14s** |
|
||||
| `cc` test .c → .o | 0.02s |
|
||||
| link | 0.02s |
|
||||
|
||||
> **STALE as of el #132 — re-measured 2026-08-16.** The `test_compiler` figure below was
|
||||
> *entirely* the `strlen`-per-character quadratic, now fixed. Re-measured on the same host:
|
||||
> **3.58s → 0.03s (119x)**, and the 422 KB compiler concatenation likewise compiles in 0.03s.
|
||||
> The table is retained only as the historical record that motivated the gate. The remaining
|
||||
> per-file cost is the redundant `el_runtime.c` rebuild, which §9's compile-once architecture
|
||||
> addresses.
|
||||
|
||||
Per-file `elc` time across the existing suite:
|
||||
|
||||
| File | Bytes | elc time |
|
||||
|---|---|---|
|
||||
| `test_compiler` | 29,685 (+394 KB of imports) | **3.58s** |
|
||||
| `string_test` | 18,545 | 0.01s |
|
||||
| all other 9 files | 2.2–10 KB | 0.00s |
|
||||
|
||||
Two distinct defects in two distinct regimes:
|
||||
|
||||
1. **`test_compiler.el` imports all five compiler sources** — 394 KB in one translation unit. Its
|
||||
3.58s is entirely the quadratic. It is the only file where the quadratic bites.
|
||||
2. **Every other file's cost is 100% redundant `el_runtime.c` rebuilds** — 480 KB of identical C,
|
||||
recompiled once per test file.
|
||||
|
||||
Neither is fixed by making the compiler faster. Both are fixed by the architecture below, and the
|
||||
speedup is a by-product of building it correctly, not the goal.
|
||||
|
||||
### 1.4 The asset worth keeping
|
||||
|
||||
`codegen.el:3651-3652` already collects `test_names` / `test_c_names` — **the compiler already does
|
||||
compile-time test discovery.** It then discards that registry into a hardcoded `main()`.
|
||||
|
||||
That registry is precisely the seam Go's `_testmain.go` and Rust's `test_main_static` are built on.
|
||||
The mechanism we need is half-built and wired to the wrong thing.
|
||||
|
||||
---
|
||||
|
||||
## 2. Grounding — the common spine of excellent frameworks
|
||||
|
||||
Researched from primary sources: Go `testing`/`go test`, Rust `libtest`/Criterion, JUnit 5 Platform,
|
||||
NUnit 3, JMH, Google Benchmark. Six invariants hold across all of them.
|
||||
|
||||
1. **A registry is built before execution** — `(name, metadata, fn-ptr)` triples. Go generates it
|
||||
from an AST scan; Rust synthesizes it in a compiler pass; JMH emits it as a build-time resource;
|
||||
JUnit/NUnit build it reflectively. **Reflection is an implementation of the registry on runtimes
|
||||
where it is cheap. It is never the architecture.**
|
||||
|
||||
2. **Discovery strictly precedes execution.** Every good capability — filtering, listing, counting,
|
||||
sharding, IDE trees, re-run-failed-only, dry runs — is a consequence of this ordering.
|
||||
|
||||
3. **A hierarchy with stable, path-shaped unique IDs.** `TestFoo/subcase_2`. Selection is regex over
|
||||
that path, one pattern per level.
|
||||
|
||||
4. **The framework is a prebuilt library; only the entry point is generated.** "Compile once, link
|
||||
many" is always: framework archive compiled once + a small generated table + one
|
||||
`MainStart(deps, registry)` call. Nobody recompiles the harness per test file.
|
||||
|
||||
5. **Execution emits an event stream; reporters are downstream renderers.** Human text, NDJSON,
|
||||
JUnit XML, TAP are all transforms of one event stream. Go's one architectural mistake is doing
|
||||
this backwards — `test2json` parses human output, and has shipped bugs when user output contains
|
||||
`--- PASS:`.
|
||||
|
||||
6. **A dependency-injection seam at the boundary.** Go's `testdeps.TestDeps` exists so `testing`
|
||||
can avoid importing `regexp`, profilers, and coverage. The execution core knows nothing about
|
||||
output formats.
|
||||
|
||||
---
|
||||
|
||||
## 3. Architecture
|
||||
|
||||
### 3.1 The seam
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────┐
|
||||
│ user code: foo.el with test { } / bench { } blocks │
|
||||
└───────────────────────────┬─────────────────────────────────┘
|
||||
│ elc --test
|
||||
▼
|
||||
┌─────────────────────────────────────────────────────────────┐
|
||||
│ generated C (per suite, tiny): │
|
||||
│ __el_test_fn_0 .. _N lowered test/bench bodies │
|
||||
│ __el_registry[] static table: name/kind/file/ │
|
||||
│ line/tags/sizes/expected-O │
|
||||
│ __el_dispatch(i) generated switch → body │
|
||||
│ main() { return el_test_main(argc, argv); } │
|
||||
└───────────────────────────┬─────────────────────────────────┘
|
||||
│ cc + link (registry only)
|
||||
▼
|
||||
┌─────────────────────────────────────────────────────────────┐
|
||||
│ libeltest.a — PREBUILT ONCE │
|
||||
│ • el_runtime.o (the 480 KB, compiled once, ever) │
|
||||
│ • eltest.o the runner, WRITTEN IN EL │
|
||||
│ discovery view · filtering · execution · fixtures · │
|
||||
│ timing · benchmark harness · curve fitting · reporters │
|
||||
└─────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
The framework is written in El, compiled to C once, archived. Per-suite compilation touches only
|
||||
the generated registry. This is Go's model, and it is strictly better for us than Go's because we
|
||||
own the compiler and already have the AST — no separate source-scanning pass is needed.
|
||||
|
||||
### 3.2 Why the runner is in El and the registry is in C
|
||||
|
||||
El has no closures and no first-class function pointers. The registry must therefore hold C function
|
||||
pointers, and it is generated C.
|
||||
|
||||
The runner stays in El and reaches the registry through a small builtin surface — indices, not
|
||||
pointers:
|
||||
|
||||
```
|
||||
__el_reg_count() -> Int
|
||||
__el_reg_name(i) -> String
|
||||
__el_reg_file(i) -> String
|
||||
__el_reg_line(i) -> Int
|
||||
__el_reg_kind(i) -> Int // 0=test 1=bench
|
||||
__el_reg_tags(i) -> Int
|
||||
__el_reg_sizes(i) -> String // JSON array, empty for tests
|
||||
__el_reg_expect(i) -> Int // complexity class enum, 0 = none
|
||||
__el_reg_invoke(i) -> Int // runs the body via the generated switch
|
||||
```
|
||||
|
||||
Nine builtins. Everything else — filtering, lifecycle, statistics, curve fitting, all reporters —
|
||||
is El. That satisfies "written in El" without pretending El can do something it cannot.
|
||||
|
||||
### 3.3 Result model
|
||||
|
||||
The unit is a **result record**, not a counter:
|
||||
|
||||
```
|
||||
TestResult {
|
||||
id String // slash path: "parser/handles_empty_input/case_3"
|
||||
file String
|
||||
line Int
|
||||
status Status // Pass | Fail | Error | Skip
|
||||
duration Int // nanoseconds, ALWAYS populated
|
||||
message String // assertion detail: expected vs actual
|
||||
output String // captured stdout/stderr for this test
|
||||
assertions Int
|
||||
}
|
||||
```
|
||||
|
||||
`Fail` = an assertion failed. `Error` = unexpected crash/abort. This distinction is load-bearing —
|
||||
every CI consumer depends on it, and the JUnit XML schema encodes it as distinct elements.
|
||||
|
||||
---
|
||||
|
||||
## 4. Authoring surface
|
||||
|
||||
### 4.1 Tests
|
||||
|
||||
`test { }` already exists. Keep it. Add subtests and hierarchy:
|
||||
|
||||
```el
|
||||
test "parser/empty input" {
|
||||
assert_that(parse(""), is_err())
|
||||
}
|
||||
|
||||
test "parser/table" {
|
||||
for case in [["", 0], ["a", 1], ["a b", 2]] {
|
||||
subtest(case[0]) {
|
||||
assert_that(token_count(case[0]), equals(case[1]))
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Subtest IDs compose as `parser/table/a_b`. Filtering is `--run 'parser/table/.*'`, one regex per
|
||||
path segment, exactly as Go does.
|
||||
|
||||
**We do not build a parameterized-test annotation system.** Table-driven loops plus subtests subsume
|
||||
`@ParameterizedTest`, `@MethodSource`, `@CsvSource`, and `TestCaseSource` entirely, at zero framework
|
||||
surface. This is Go's single biggest ergonomic win over JUnit and NUnit.
|
||||
|
||||
### 4.2 Fixtures
|
||||
|
||||
Per-file and per-test only, plus a LIFO cleanup stack:
|
||||
|
||||
```el
|
||||
setup_all { ... } // once per suite
|
||||
setup { ... } // before each test
|
||||
teardown { ... } // after each test
|
||||
teardown_all { ... }
|
||||
```
|
||||
|
||||
and inside a test, `cleanup { ... }` registering LIFO-ordered teardown.
|
||||
|
||||
**We do not build JUnit 5's extension SPI** — seventeen callback interfaces, hierarchical stores,
|
||||
registration ordering rules. That complexity is the price of retrofitting a plugin ecosystem onto a
|
||||
twenty-year-old reflective framework. Go's `t.Cleanup` covers roughly 90% of what `@AfterEach` is
|
||||
used for at a fraction of the surface.
|
||||
|
||||
### 4.3 Assertions — constraint model
|
||||
|
||||
One entry point, composable constraint values (NUnit's model, which avoids the N² overload
|
||||
explosion):
|
||||
|
||||
```el
|
||||
assert_that(actual, equals(expected))
|
||||
assert_that(xs, has_length(3))
|
||||
assert_that(s, contains("foo").and(starts_with("bar")))
|
||||
assert_that(f, is_within(0.01).of(3.14))
|
||||
```
|
||||
|
||||
A constraint is a value with `apply_to(actual) -> ConstraintResult`, and the result knows how to
|
||||
describe its own failure. Custom constraints are ordinary user types.
|
||||
|
||||
**Every failure message must name file, line, the expression text, and both values.** We capture
|
||||
expression source text at compile time — we have the AST, so we can do this better than any
|
||||
runtime-introspection framework.
|
||||
|
||||
Legacy `assert_true` / `assert_eq` / etc. stay as thin wrappers for migration.
|
||||
|
||||
---
|
||||
|
||||
## 5. Benchmarks
|
||||
|
||||
### 5.1 The loop
|
||||
|
||||
Adopt `b.Loop()`, not `b.N`. Go spent fifteen years on `b.N` before concluding `b.Loop` was right;
|
||||
we skip that.
|
||||
|
||||
```el
|
||||
bench "str_concat" {
|
||||
let s = make_input(bench_n())
|
||||
for bench_loop() {
|
||||
black_box(str_concat(s, "x"))
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Three properties that make this the correct choice for a C target:
|
||||
|
||||
1. **The timer auto-resets on first call**, so setup above the loop is excluded *by construction*
|
||||
rather than by the author remembering `ResetTimer`.
|
||||
2. **`N` is hidden**, so it cannot be misused.
|
||||
3. **The harness owns the loop shape**, which lets us insert an optimization barrier the C compiler
|
||||
cannot see through. `black_box(v)` lowers to `asm volatile("" :: "r"(&v) : "memory")`. Since we
|
||||
emit a single translation unit, dead-code elimination of a benchmark body is a live hazard —
|
||||
this is our version of JMH's `Blackhole` problem, solved in the harness rather than delegated to
|
||||
the user.
|
||||
|
||||
### 5.2 Iteration scaling
|
||||
|
||||
Use Go's `predictN` heuristics verbatim. They are battle-tested and cheap:
|
||||
|
||||
```
|
||||
n = goal_ns * prev_iters / prev_ns // multiply before divide — precision on sub-ns ops
|
||||
n += n / 5 // 20% headroom, overshoot rather than re-loop
|
||||
n = min(n, 100 * last) // never grow more than 100× per step
|
||||
n = max(n, last + 1) // guarantee forward progress
|
||||
n = min(n, 1_000_000_000) // hard ceiling
|
||||
```
|
||||
|
||||
Report `n` rounded to 1/2/3/5 × 10ᵏ so runs are comparable.
|
||||
|
||||
### 5.3 Sampling
|
||||
|
||||
Criterion's shape, because it is correct near timer resolution:
|
||||
|
||||
- **Warmup**: iteration counts 1, 2, 4, 8… until cumulative time exceeds the warmup budget.
|
||||
- **Measurement**: collect `sample_size` samples at iteration counts `[d, 2d, 3d, …, Nd]`.
|
||||
- **Estimate**: slope of a linear regression of iteration-count vs elapsed time. The intercept
|
||||
absorbs fixed overhead.
|
||||
- **Time whole samples, never individual iterations.** This is the single most important detail —
|
||||
it defeats timer-resolution error on nanosecond operations.
|
||||
|
||||
Outliers classified by modified Tukey (±1.5 IQR mild, ±3 IQR severe), **reported but retained**.
|
||||
|
||||
---
|
||||
|
||||
## 6. Complexity gating — the centerpiece
|
||||
|
||||
This is the part that makes the quadratic fixable, and the part nobody in the mainstream has
|
||||
finished. Google Benchmark's `Complexity()` fits the curve and *reports* it. We declare it and
|
||||
**gate** on it.
|
||||
|
||||
### 6.1 Surface
|
||||
|
||||
```el
|
||||
bench "elc_compile" over n in [16, 32, 64, 128, 256, 512, 1024] expect O(n) {
|
||||
let src = synth_source(bench_n())
|
||||
for bench_loop() { black_box(compile(src)) }
|
||||
}
|
||||
```
|
||||
|
||||
Alternative with no new syntax, if the parser change is judged too invasive — `bench_sizes([...])`
|
||||
and `bench_expect("O(n)")` as calls inside the block. **Recommendation: declarative.** Runtime calls
|
||||
mean `--list` cannot show the invariant without executing, which breaks the discovery-precedes-
|
||||
execution invariant from §2.
|
||||
|
||||
### 6.2 Fitting
|
||||
|
||||
Per Google Benchmark `src/complexity.cc`. For candidate curves
|
||||
`{O(1), O(log n), O(n), O(n log n), O(n²), O(n³)}`, one-parameter least squares, no intercept:
|
||||
|
||||
```
|
||||
coef = Σ(tᵢ · gᵢ) / Σ(gᵢ²)
|
||||
rms = sqrt( Σ(tᵢ − coef·gᵢ)² / k ) / mean(t) // normalized
|
||||
```
|
||||
|
||||
Best fit = lowest normalized RMS. User-supplied lambda curves also supported.
|
||||
|
||||
### 6.3 Gate logic
|
||||
|
||||
1. **FAIL** if the best-fit curve is strictly worse than declared, ordering
|
||||
`O(1) < O(log n) < O(n) < O(n log n) < O(n²) < O(n³)`. Print the fitted coefficient and the full
|
||||
per-size table.
|
||||
2. **FAIL** if the declared curve's normalized RMS exceeds a threshold (start at 0.10). This catches
|
||||
the case where *no* candidate fits — noise, a cache cliff, or a phase change. Report
|
||||
`INDETERMINATE` honestly rather than gating on garbage.
|
||||
3. **WARN** if the best fit is strictly better than declared — either an optimization landed and the
|
||||
annotation should tighten, or the sweep is too narrow to expose real behaviour.
|
||||
4. **REFUSE to gate** on fewer than 5 distinct sizes spanning under 2 decades, geometrically spaced.
|
||||
Say so loudly rather than producing a meaningless fit.
|
||||
|
||||
### 6.4 Why gate on the exponent, not wall-clock
|
||||
|
||||
- **Machine-independent.** The fitted exponent is a property of the algorithm; the coefficient is a
|
||||
property of the machine. Gating on the exponent makes CI hardware heterogeneity, noisy neighbours,
|
||||
and thermal throttling irrelevant — they scale `coef`, not `g`.
|
||||
- **No stored baseline.** No artifact storage, no golden-file drift. The invariant lives in the
|
||||
source next to the code and is reviewed in the same PR.
|
||||
- **It catches the failure mode that actually ships.** An O(n) lookup inside an O(n) loop is
|
||||
invisible at n=100 in a unit test and catastrophic at n=100,000 in production. Constant-factor
|
||||
regressions are annoying. Complexity regressions are outages. Ours was a 27 GB outage.
|
||||
|
||||
### 6.5 The deterministic gate — the one that would have caught us
|
||||
|
||||
Wall-clock needs statistics. **Allocation counts do not.** They are perfectly deterministic.
|
||||
|
||||
> **Correction, 2026-08-16 — count alone is NOT sufficient. Gate on BOTH count and bytes.**
|
||||
>
|
||||
> Measured against two El programs, one allocating once per item and one rebuilding its
|
||||
> accumulator each iteration:
|
||||
>
|
||||
> | n | linear allocs / bytes | quadratic allocs / bytes |
|
||||
> |---|---|---|
|
||||
> | 100 | 100 / 290 | 100 / 5,150 |
|
||||
> | 200 | 200 / 690 | 200 / 20,300 |
|
||||
> | 400 | 400 / 1,490 | 400 / 80,600 |
|
||||
> | 800 | 800 / 3,090 | 800 / 321,200 |
|
||||
>
|
||||
> The quadratic program's allocation **count is exactly linear** — 100/200/400/800, identical to
|
||||
> the healthy program. A count-only gate passes it clean. **Bytes** catch it: each doubling of n
|
||||
> quadruples bytes (ratios 3.94, 3.97, 3.99 → 4.0 = O(n²)) where the linear program converges
|
||||
> on 2.0.
|
||||
>
|
||||
> This is precisely elc's own defect shape — a copy-on-write accumulator reallocating once per
|
||||
> pass (count linear) into a proportionally larger buffer (bytes quadratic).
|
||||
>
|
||||
> Therefore `expect allocs O(n)` **fits count and bytes independently and fails if EITHER exceeds
|
||||
> the declared curve**, reporting which signal broke. "count linear, bytes quadratic" is a precise,
|
||||
> directly actionable diagnosis.
|
||||
>
|
||||
> **`el_peak_rss()` is CONTEXT ONLY — never gate on it.** It is perturbed by the allocator and by
|
||||
> the page cache. Allocation volume is the invariant; RSS and malloc/free churn are merely the two
|
||||
> surfaces it shows on. The old shipped compiler paid the same quadratic in RSS that the rebuilt
|
||||
> one pays in churn.
|
||||
>
|
||||
> **Measure rate, not level.** A guard reading swap *level* saw 97% on a thrashing host and 97% on
|
||||
> a healthy one; only *rate* separated them. A growth exponent is a rate; a single measurement is
|
||||
> a level. That is why the gate fits a curve across a sweep instead of comparing one number to a
|
||||
> threshold.
|
||||
|
||||
> **Second correction, same day — THE ALLOCATION GATE ALONE WOULD HAVE MISSED THE REAL BUG.**
|
||||
>
|
||||
> el #132 found the actual elc quadratic: `strlen()` called inside `str_char_code()` and
|
||||
> `str_slice()`, so the lexer rescanned the remaining input on every character. Pure CPU.
|
||||
> **Zero allocation.** `str_char_code` is a bounds check and an index — it allocates nothing.
|
||||
>
|
||||
> Measured on three controlled specimens (`lang/.work/fitprobe.el`), growth ratio per doubling of
|
||||
> n across n = 200/400/800/1600:
|
||||
>
|
||||
> | specimen | allocs | bytes | time | what it proves |
|
||||
> |---|---|---|---|---|
|
||||
> | `linear` — one alloc per item | 2.00 2.00 2.00 → **O(n)** | 2.16 2.07 2.23 → **O(n)** | 0.83 2.00 2.05 → **O(n)** | clean baseline |
|
||||
> | `accum` — rebuilds accumulator | 2.00 2.00 2.00 → **O(n)** | 3.97 3.99 3.99 → **O(n²)** | noisy | count misses, **bytes catches** |
|
||||
> | `compute` — n scans over n chars | 0 → **FLAT** | 0 → **FLAT** | 3.93 4.01 3.96 → **O(n²)** | **both alloc signals blind; only time catches** |
|
||||
>
|
||||
> `compute` is el #132's shape exactly. A gate fitting only allocation count and bytes classifies
|
||||
> it as FLAT and passes it. **The gate as originally specified would not have caught the defect it
|
||||
> was created for.**
|
||||
>
|
||||
> Therefore the gate fits **THREE** signals and fails if ANY exceeds its declared curve:
|
||||
>
|
||||
> ```
|
||||
> bench "elc_compile" over n in [...] expect time O(n) allocs O(n) bytes O(n) { ... }
|
||||
> ```
|
||||
>
|
||||
> - **allocs (count)** — deterministic, zero-noise. Catches per-item allocation growth.
|
||||
> - **allocs (bytes)** — deterministic, zero-noise. Catches accumulator-rebuild quadratics that
|
||||
> count cannot see.
|
||||
> - **time** — noisy, needs the sweep and statistics. The ONLY signal that sees pure-compute
|
||||
> complexity regressions. Gate on the fitted *exponent*, never on absolute duration, so CI
|
||||
> hardware variance scales the coefficient and leaves the classification intact.
|
||||
>
|
||||
> The deterministic signals remain preferable where they apply — they need no statistics and are
|
||||
> correct on the first run. They are simply not sufficient.
|
||||
>
|
||||
> **`black_box` is mandatory, and consuming the result is NOT enough.** The first version of
|
||||
> `compute` accumulated `total + 1` in a nested loop and reported **0 µs at every n** while
|
||||
> returning a numerically correct n². Clang recognised the idiom and closed the loop to a
|
||||
> multiply. Feeding the result into output did not prevent it. Only making the inner operation an
|
||||
> opaque external call restored the real curve. A benchmark harness that trusts the user to defeat
|
||||
> the optimiser will silently measure nothing — and report success while doing it.
|
||||
|
||||
Instrument the runtime with allocation counters and fit *those* against n instead of time:
|
||||
|
||||
```el
|
||||
bench "elc_compile" over n in [...] expect O(n) allocs O(n) { ... }
|
||||
```
|
||||
|
||||
Zero noise, zero statistics, always gateable, correct on the first run on any machine. Go reports
|
||||
`allocs/op` and `B/op`; **nobody fits them against n.** That is an open opportunity and it is exactly
|
||||
our bug: elc's defect is quadratic *allocation volume*, which the old binary paid in RSS and the
|
||||
current source pays in malloc/free churn.
|
||||
|
||||
An `expect allocs O(n)` assertion on `elc`'s compile path would have failed the build the day the
|
||||
quadratic was introduced.
|
||||
|
||||
Required runtime additions: `__el_alloc_count()`, `__el_alloc_bytes()`, `__el_peak_rss()`.
|
||||
|
||||
### 6.6 Constant-factor gate (secondary, opt-in)
|
||||
|
||||
Mann-Whitney U at α = 0.05, noise floor 1%, medians with 95% CIs, `~` for not-significant. Requires
|
||||
`--count >= 9`. Off by default on CI; opt-in per benchmark.
|
||||
|
||||
**Exit nonzero on regression.** Both benchstat and Criterion always exit 0, which is why every shop
|
||||
using them wrote a wrapper. We do not repeat that omission.
|
||||
|
||||
---
|
||||
|
||||
## 7. Output
|
||||
|
||||
**Structured events are the source of truth.** Human text is rendered from them. We do not repeat
|
||||
Go's parse-the-human-output design.
|
||||
|
||||
Event stream, NDJSON, one object per line, streamed live:
|
||||
|
||||
```json
|
||||
{"time":"...","action":"run","test":"parser/empty"}
|
||||
{"time":"...","action":"output","test":"parser/empty","output":"..."}
|
||||
{"time":"...","action":"pass","test":"parser/empty","elapsed":0.0031}
|
||||
{"time":"...","action":"bench","test":"str_concat","n":1024,"ns_op":41.2,"allocs_op":3,"bigo":"N","rms":0.03}
|
||||
```
|
||||
|
||||
Renderers, all downstream and pluggable:
|
||||
|
||||
| Format | Flag | Use |
|
||||
|---|---|---|
|
||||
| Human | default | terminal, **per-test duration always shown** |
|
||||
| NDJSON | `--json` | tooling, history, flaky detection |
|
||||
| JUnit XML | `--junit-xml=PATH` | every CI system on earth |
|
||||
| TAP | `--tap` | optional |
|
||||
|
||||
JUnit XML per the de-facto schema: `testsuites` → `testsuite` → `testcase`, with `time` in seconds
|
||||
as a decimal, `file`/`line` attributes, and `failure` vs `error` vs `skipped` as distinct child
|
||||
elements. Absence of a child element means pass. Emit `<testsuites>` even for a single suite, and
|
||||
parse both shapes on input.
|
||||
|
||||
---
|
||||
|
||||
## 8. CLI
|
||||
|
||||
```
|
||||
--list print the registry, run nothing
|
||||
--list-json machine-readable registry
|
||||
--run PATTERN slash-separated regex per path segment
|
||||
--tag EXPR tag expression: fast & !slow
|
||||
--shard I/N deterministic sharding for CI parallelism
|
||||
--count N repetitions, for statistics
|
||||
--bench PATTERN run benchmarks (off by default in test runs)
|
||||
--benchtime DUR per-benchmark time budget
|
||||
--junit-xml PATH
|
||||
--json
|
||||
--isolate re-exec per test on crash, so one SIGSEGV doesn't lose the run
|
||||
--timeout DUR
|
||||
--fail-fast
|
||||
```
|
||||
|
||||
`--list` / `--list-json` / `--shard` cost roughly thirty lines because the registry already exists
|
||||
before `main` does anything. That is the dividend of discovery-precedes-execution.
|
||||
|
||||
---
|
||||
|
||||
## 9. Build model
|
||||
|
||||
```
|
||||
# once, ever (or when the runtime/framework changes):
|
||||
cc -c el_runtime.c -o el_runtime.o
|
||||
elc eltest.el > eltest.c && cc -c eltest.c -o eltest.o
|
||||
ar rcs libeltest.a el_runtime.o eltest.o
|
||||
|
||||
# per suite:
|
||||
elc --test foo_test.el > foo_test.c # registry + bodies only
|
||||
cc foo_test.c libeltest.a -o foo_test
|
||||
```
|
||||
|
||||
The 0.14s × N of redundant runtime rebuilds disappears — not because we optimized it, but because
|
||||
one-runner-over-many-suites requires compile-once-link-many as a structural precondition.
|
||||
|
||||
---
|
||||
|
||||
## 10. Bootstrap and self-hosting
|
||||
|
||||
The framework's own tests are `test { }` blocks run by the framework. Same fixpoint discipline the
|
||||
compiler already applies to itself.
|
||||
|
||||
1. Build the framework using the *existing* harness for its first tests (stage 0).
|
||||
2. Rebuild the framework's tests as `test { }` blocks run by the new runner (stage 1).
|
||||
3. Verify stage 1 reports identical results to stage 0.
|
||||
4. From then on, the framework is tested by itself.
|
||||
|
||||
A framework that cannot run its own suite is not evidence of anything. This is a correctness proof,
|
||||
not a claim.
|
||||
|
||||
---
|
||||
|
||||
## 11. Explicitly not building
|
||||
|
||||
| Rejected | Why |
|
||||
|---|---|
|
||||
| Naming-convention discovery (`fn test_foo`) | `test { }` is a real declaration. Go's `TestXxx` exists only because Go had no better hook — and it needs a heuristic to avoid matching `TesticularCancer`. |
|
||||
| Reflection or symbol-table scanning | Slow, fragile under LTO/strip/dead-strip, and unnecessary when we own the compiler. |
|
||||
| Parsing human output into structure | Go's `test2json` is its one clear architectural mistake. |
|
||||
| JUnit 5's extension SPI | Seventeen callback interfaces to retrofit plugins onto a reflective framework. Not our problem. |
|
||||
| `@ParameterizedTest` machinery | Table-driven loops + subtests subsume it at zero surface. |
|
||||
| NUnit's out-of-process agents | They bridge CLR versions and AppDomains. We emit one native binary. Keep `--isolate` as crash fallback only. |
|
||||
| JMH-style forking by default | Forks exist because JIT profiles are per-process. AOT C has no such state. Keep `--fork` available, not default. |
|
||||
| Exit 0 on regression | benchstat and Criterion both do this, and every user writes a wrapper. |
|
||||
| Dynamic runtime test registration | Breaks `--list`, sharding, and individual selection. Registry stays static. |
|
||||
|
||||
---
|
||||
|
||||
## 12. Phasing
|
||||
|
||||
| Phase | Content | Gate |
|
||||
|---|---|---|
|
||||
| **1** | Registry emission in codegen; 9 builtins; `el_test_main` skeleton in El; result records; per-test timing; human + NDJSON output | existing 11 test files pass, with timing |
|
||||
| **2** | `libeltest.a` build model; subtests; filtering; `--list`; fixtures; constraint assertions; JUnit XML | suite runs in one binary; runtime compiled once |
|
||||
| **3** | `bench { }`, `bench_loop`, `black_box`, `predictN`, Criterion sampling | benchmarks produce stable ns/op |
|
||||
| **4** | Allocation counters; complexity fitting; `expect O(...)` gate | **an `expect allocs O(n)` benchmark on `elc` fails on the current quadratic** |
|
||||
| **5** | Migrate both legacy systems; delete `runtime/test.el`; self-host | framework runs its own suite |
|
||||
|
||||
Phase 4 is the deliverable that matters. Phases 1–3 exist to make it possible.
|
||||
|
||||
---
|
||||
|
||||
## 13. Open questions for review
|
||||
|
||||
1. **Declarative `over n in [...] expect O(...)` syntax vs runtime calls.** I recommend declarative
|
||||
(§6.1) so `--list` can show invariants without executing. It costs parser work. Your call.
|
||||
2. **`bench { }` as a new block form** — parallel to `test { }`, or a modifier on it?
|
||||
3. **Scope of the constraint model.** Full composable constraints, or start with a flat assertion set
|
||||
and add constraints later? Full model is more surface but avoids a second migration.
|
||||
4. **Does `runtime/test.el` get deleted or kept as a deprecated shim?** I lean delete — two systems
|
||||
is how we got here.
|
||||
5. **Where does `libeltest.a` live** in the tree, and does `epm` need to know about it?
|
||||
6. **Allocation counters in `el_seed.c` or `el_runtime.c`?** AGENTS.md says `el_seed.c` is the sole
|
||||
C dependency and hand-maintained; counters are OS-boundary-adjacent but not OS calls.
|
||||
7. **Is per-test timing enough, or do we want per-*assertion* timing** for finding slow helpers?
|
||||
|
||||
---
|
||||
|
||||
## 14. What this document is not
|
||||
|
||||
This is a design, not a measurement. Every performance claim about the *current* system in §1 is
|
||||
measured and reproducible in this worktree. Every claim about the *proposed* system is a prediction.
|
||||
None of it is verified until Phase 1 runs and Phase 4 fails a build on the real quadratic.
|
||||
@@ -1,154 +0,0 @@
|
||||
# El
|
||||
|
||||
**A self-hosting, statically-typed language that compiles to C — built around a graph-native runtime instead of a database driver.**
|
||||
|
||||
El is the execution substrate for the Neuron agent runtime, the DHARMA network, and the Engram knowledge graph. This repository is the monorepo for the whole stack: the language itself, the graph memory engine it's built to talk to natively, and the tools (package manager, IDE, UI framework, diagramming) built on top of it.
|
||||
|
||||
---
|
||||
|
||||
## Why El exists
|
||||
|
||||
Every other language treats persistent, associative state as something you reach for through a driver — a SQL client, an ORM, a Redis library bolted on from outside. El inverts that: graph operations (`engram_*`) are runtime primitives, on the same footing as string or list operations. There is no separate database driver because the database is not separate.
|
||||
|
||||
El has four defining properties:
|
||||
|
||||
1. **Self-hosting compiler.** The compiler (`lexer.el`, `parser.el`, `codegen.el`, `compiler.el`) is written in El. It compiles El source to C, which `cc` compiles against a fixed runtime into a native binary. A Rust genesis compiler bootstrapped the first iteration; the self-hosted binary at `lang/dist/platform/elc` has been the canonical compiler ever since — every binary in `dist/platform/` was produced by an earlier version of itself compiling `el-compiler/src/`. The chain is auditable: source is the ground truth, not the binary. See [lang/BOOTSTRAP.md](lang/BOOTSTRAP.md) for the full recovery path if that binary is ever lost.
|
||||
2. **C compilation target.** Every compiled program is plain C11. Every El value is `el_val_t` (`int64_t`); strings are heap pointers cast through it. Functions become C functions; top-level statements become `main()`.
|
||||
3. **Graph-native runtime.** The runtime provides first-class graph operations over an in-process Engram store — no separate DB driver, no ORM.
|
||||
4. **DHARMA-aware identity.** A `cgi` block declares a program's DHARMA identity at compile time. The runtime resolves identity before user code runs, so `dharma_*` calls have a stable principal and channel surface throughout.
|
||||
|
||||
---
|
||||
|
||||
## Architecture map
|
||||
|
||||
```
|
||||
┌─────────────┐
|
||||
│ lang │ El compiler + C runtime
|
||||
│ (El itself) │ everything below is written in it,
|
||||
└──────┬──────┘ or compiles down through it
|
||||
│
|
||||
┌─────────────┼─────────────┐
|
||||
│ │ │
|
||||
┌──────▼─────┐ ┌─────▼─────┐ ┌─────▼─────┐
|
||||
│ engram │ │ epm │ │ ide │
|
||||
│ graph/mem │ │ package │ │ editor + │
|
||||
│ substrate │ │ manager │ │ LSP │
|
||||
└──────┬─────┘ └───────────┘ └───────────┘
|
||||
│
|
||||
┌───────┼────────────────┬─────────────────────┐
|
||||
│ │ │ │
|
||||
┌─────▼───┐ ┌─▼──────────┐ ┌──▼──────────┐ ┌─────▼──────┐
|
||||
│ elp │ │ ql │ │ ui │ │ arbor │
|
||||
│ NLG / │ │engram-el. │ |spreading- │ |arbor │
|
||||
│ 31 langs│ │studio+tests│ |activation UI│ |diagram lang│
|
||||
└─────────┘ └────────────┘ └─────────────┘ └────────────┘
|
||||
```
|
||||
|
||||
`lang` is the foundation — the compiler and C runtime everything else builds on. `engram` is the graph-native memory/state engine that gives El its identity (property 3 above). Everything else is either a tool for working with El (`epm`, `ide`) or a system built on top of Engram's graph model (`elp`, `ql`, `ui`, `arbor`).
|
||||
|
||||
---
|
||||
|
||||
## Repository layout
|
||||
|
||||
### [lang/](lang/) — the El language
|
||||
|
||||
The compiler and runtime. Self-hosting: `elc-cli.el` → `compiler.el` → `lexer.el` / `parser.el` / `codegen.el` / `codegen-js.el`, textually inlined and compiled in one pass. Compiles to C11 and links against `el-compiler/runtime/el_seed.c`, a hand-maintained OS-boundary layer (libcurl HTTP, pthreads, filesystem, arena allocation) — everything else in the runtime is native El (`runtime/*.el`).
|
||||
|
||||
Two layers to know: **El programs** (`.el` files — where nearly all work belongs) and **the C seed** (`el_seed.c` — edit only for genuine OS-level access; never re-implement what El can already express).
|
||||
|
||||
Current status (single source of truth: [lang/spec/language.md](lang/spec/language.md)): lexer/parser/codegen and the C runtime's core (I/O, strings, math, lists, maps, filesystem, args) are implemented. In flight: `%` operator, match-statement codegen, `?` nil-propagation, `cgi` block parsing + DHARMA identity resolution, VBD role enforcement (`@manager`/`@engine`/`@accessor`), the real `engram_*` and `dharma_*` runtimes (currently stubs), and libcurl-backed `http_get`/`http_post`/`http_serve`. Bitwise operators, `??`, and `as` casts are explicitly **not** in this language.
|
||||
|
||||
Key docs: [AGENTS.md](lang/AGENTS.md) (agent-facing orientation), [BOOTSTRAP.md](lang/BOOTSTRAP.md) (compiler recovery from scratch), [spec/language.md](lang/spec/language.md), [spec/codegen-js.md](lang/spec/codegen-js.md).
|
||||
|
||||
### [engram/](engram/) — graph intelligence substrate
|
||||
|
||||
**A local-first memory substrate for accumulating intelligence**, and the reason El's runtime doesn't need a database driver. Rust core (`engram-core`, `engram-ffi`) exposed to El and other languages (Kotlin, TypeScript/WASM, Go bindings).
|
||||
|
||||
The model: retrieval is **spreading activation**, not query. You name seed nodes and a query embedding; activation propagates outward through weighted edges, attenuating multiplicatively per hop (`strength = parent_strength × edge_weight × target_salience × cosine_sim`), gets pruned below a threshold, and the top-N nodes by activation strength come back. Storage and retrieval are the same structure — the way long-term potentiation works in biological memory, not the way a relational or vector database works.
|
||||
|
||||
Nodes live in four tiers (Working / Episodic / Semantic / Procedural, mirroring prefrontal / hippocampal / neocortical / cerebellar memory) and migrate between them based on **salience decay** — `importance × recency-decay × log(activation_count)`. Forgetting is adaptive pruning, not a bug: unreinforced memories stop competing for attention without being deleted.
|
||||
|
||||
Backed by `sled` (embedded, local-first, no daemon) with flat cosine scan for vector search — deliberately simple until scale demands an HNSW layer. Full API and design rationale in [engram/README.md](engram/README.md).
|
||||
|
||||
### [elp/](elp/) — Engram Language Protocol
|
||||
|
||||
Bidirectional engine mapping between Engram semantic forms and natural-language surface text, across **31 languages** — from Spanish and Japanese through historical/liturgical languages (Old Norse, Sanskrit, Sumerian, Coptic, Akkadian, Ge'ez). Compilation order runs `language-profile` + `vocabulary` → per-language `morphology-*` → `grammar` → `realizer` → `semantics` → `elp`. This is what lets an Engram graph node round-trip to and from readable text in any of those languages.
|
||||
|
||||
### [epm/](epm/) — El Package Manager
|
||||
|
||||
Manages **vessels** (El's package unit): publish, install, resolve dependencies. Vessels are stored in Engram as graph nodes, not files in a registry index — `epm` reads the local `manifest.el`, talks to Engram over HTTP, and writes resolved vessels to `.epm/vessels/`. Source: `registry.el`, `install.el`, `update.el`, `manifest.el`.
|
||||
|
||||
### [ide/](ide/) — El IDE
|
||||
|
||||
Three vessels: **el-ide-server** (HTTP backend — file ops, build/run, LSP bridge, plugin host, settings), **el-lsp** (the language server — completion, hover, diagnostics, outline, format, type graph), and **el-plugin-host** (first-party plugin lifecycle: install/remove/enable/disable). `ide/projects/` and `ide/examples/` hold sample projects, including the canonical `hello-friends` first-program walkthrough.
|
||||
|
||||
### [ql/](ql/) — engram-el
|
||||
|
||||
The El-native integration layer for a *live* Engram server — not a library (no importable modules, no build artifact), a set of standalone `.el` programs run directly via `el run-file`. Three components: **Studio** (`studio/studio.el`, a full terminal graph explorer), a **Hebbian field-model** proof of concept, and El builtin / LLM-builtin smoke test suites. This is the reference for correct patterns when an El program uses Engram as its substrate. Spec: [ql/spec/elql.md](ql/spec/elql.md).
|
||||
|
||||
### [ui/](ui/) — el-ui
|
||||
|
||||
A frontend framework where **component state is an Engram graph and reactivity is spreading activation** — not virtual-DOM diffing (React), Proxy-based dependency tracking (Vue), or compile-time analysis (Svelte). Re-renders are activated and propagated the same way associative memory retrieval works in `engram/`.
|
||||
|
||||
~15 vessels covering the full frontend surface: `el-platform` (env/fs/network/clock abstraction), `el-config`, `el-html` (SSR emit primitives), `el-layout`, `el-style` (design tokens/themes), `el-i18n`, `el-auth` / `el-identity` (JWT, sessions, OAuth PKCE — Engram-native), `el-services` (REST/gRPC/WebSocket bindings), `el-aop` (`@authenticate`/`@authorize`/`@cache`/`@rate_limit` decorators), `el-secrets`, `el-graph` (graph rendering/editor), `el-publish` (App Store / Play Store automation), and `el-ui-compiler` (El→JS component compiler; currently a stub pending a JS backend in `elc`). Spec: [ui/spec/framework.md](ui/spec/framework.md).
|
||||
|
||||
### [arbor/](arbor/) — diagram language
|
||||
|
||||
A `.arbor` diagram language and toolchain: `arbor-core` (NodeId/shape/edge-kind types), `arbor-parse` (recursive-descent parser), `arbor-diagram` (IR + Mermaid serializer + architecture-diagram builders), `arbor-layout` (hierarchical layout — rank assignment, positioning, group bounds), `arbor-render` (SVG renderer), `arbor-cli`. (The architecture map above is the kind of diagram this is for.)
|
||||
|
||||
---
|
||||
|
||||
## Getting started
|
||||
|
||||
Install the El SDK from the latest release:
|
||||
|
||||
```bash
|
||||
bash lang/install.sh
|
||||
# EL_VERSION=v1.0.0 bash lang/install.sh # pin a specific release tag
|
||||
# EL_PREFIX=/opt/el bash lang/install.sh # custom install prefix
|
||||
```
|
||||
|
||||
Or build the compiler from source and verify the self-hosting chain:
|
||||
|
||||
```bash
|
||||
cd lang
|
||||
./dist/platform/elc elc-cli.el > elc-new.c
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
-o dist/platform/elc-new \
|
||||
elc-new.c el-compiler/runtime/el_seed.c
|
||||
|
||||
# Confirm the new binary reproduces itself exactly
|
||||
./dist/platform/elc-new elc-cli.el > elc-verify.c
|
||||
diff elc-new.c elc-verify.c # should be identical
|
||||
|
||||
mv dist/platform/elc-new dist/platform/elc
|
||||
```
|
||||
|
||||
Run your first program:
|
||||
|
||||
```bash
|
||||
./lang/dist/platform/elc lang/examples/hello.el > hello.c
|
||||
cc -std=c11 -I lang/el-compiler/runtime -lcurl -lpthread \
|
||||
-o hello hello.c lang/el-compiler/runtime/el_seed.c
|
||||
./hello
|
||||
```
|
||||
|
||||
More examples in [lang/examples/](lang/examples/), including a full starter project at `lang/examples/hello-project/`.
|
||||
|
||||
If the compiler binary is ever lost or corrupted, [lang/BOOTSTRAP.md](lang/BOOTSTRAP.md) is the authoritative recovery path.
|
||||
|
||||
---
|
||||
|
||||
## Development workflow
|
||||
|
||||
Branching follows `dev → stage → main`: work lands on `dev`, promotes to `stage` for integration testing, and is promoted to `main` for release (visible directly in the git history of this repo). CI is defined per-subproject under `.gitea/workflows/` — `lang`/`epm`/`ide` share the root pipeline; `engram` and `ql` carry their own (`ci-dev`, `ci-stage`, and a release workflow each).
|
||||
|
||||
- Language/runtime specs live at `*/spec/*.md` (`lang/spec/`, `ql/spec/`, `ui/spec/`) and are the single source of truth for implemented-vs-planned status — code and docs are expected to agree with the spec's status markers, not the other way around.
|
||||
- Agent-facing orientation guides live at `*/AGENTS.md` (currently `lang/AGENTS.md`); more subprojects may grow their own as they need agent-specific conventions documented.
|
||||
- Tagged releases live under `lang/releases/`, each with its own `RELEASE.md`.
|
||||
|
||||
---
|
||||
|
||||
## Status
|
||||
|
||||
This is an actively developed, internal monorepo — not yet published under an open license. Treat everything here as proprietary to Neuron Technologies unless told otherwise.
|
||||
@@ -1,23 +0,0 @@
|
||||
// arbor-cli — the `arbor` command-line tool.
|
||||
// Inlines its own copies of the parse / layout / render pipeline so that the
|
||||
// resulting binary is self-contained. (El's `import` form today concatenates
|
||||
// source; once a real module loader lands this becomes a thin driver.)
|
||||
|
||||
vessel "arbor-cli" {
|
||||
version "0.1.0"
|
||||
description "Command-line interface for the Arbor diagram language"
|
||||
authors ["Neuron Technologies"]
|
||||
edition "2026"
|
||||
}
|
||||
|
||||
dependencies {
|
||||
arbor-core "0.1"
|
||||
arbor-parse "0.1"
|
||||
arbor-layout "0.1"
|
||||
arbor-render "0.1"
|
||||
}
|
||||
|
||||
build {
|
||||
entry "src/main.el"
|
||||
output "dist/"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,18 +0,0 @@
|
||||
// arbor-core — fundamental types for Arbor diagrams.
|
||||
// Node IDs (sanitised), shape vocabulary, edge kinds, and the lightweight
|
||||
// graph value used by every other vessel.
|
||||
|
||||
vessel "arbor-core" {
|
||||
version "0.1.0"
|
||||
description "Core types for Arbor diagrams: NodeId, ArborShape, ArborEdgeKind, graphs"
|
||||
authors ["Neuron Technologies"]
|
||||
edition "2026"
|
||||
}
|
||||
|
||||
dependencies {
|
||||
}
|
||||
|
||||
build {
|
||||
entry "src/main.el"
|
||||
output "dist/"
|
||||
}
|
||||
@@ -1,333 +0,0 @@
|
||||
// arbor-core — core types for Arbor diagrams.
|
||||
//
|
||||
// Idiomatic El: everything is a Map. Functions take/return maps; helpers are
|
||||
// pure and small. The downstream vessels (parse, layout, render) consume the
|
||||
// shapes defined here.
|
||||
//
|
||||
// Shape vocabulary:
|
||||
// ArborShape strings — "rect" "rounded" "cylinder" "diamond" "stadium" "primary"
|
||||
//
|
||||
// Edge-kind strings:
|
||||
// "solid" "dashed" "forbidden" "bidirectional"
|
||||
//
|
||||
// Node value: { "id":Str, "label":Str, "shape":Str }
|
||||
// Edge value: { "from":Str, "to":Str, "label":Str, "kind":Str }
|
||||
// Group value: { "id":Str, "label":Str, "node_ids":[Str], "direction":Str }
|
||||
// Graph value: { "title":Str, "direction":Str, "nodes":[Node], "edges":[Edge], "groups":[Group] }
|
||||
//
|
||||
// Diagram-form (lowered) is the same shape but with NodeStyle/EdgeLine/Arrow
|
||||
// resolved into renderer-friendly fields:
|
||||
// Node: + "sublabel":Str, "style_fill":Str, "style_stroke":Str, "style_color":Str
|
||||
// Edge: + "line":Str ("solid"/"dashed"/"dotted"/"thick"), "arrow":Str ("forward"/"backward"/"both"/"none")
|
||||
//
|
||||
// This file is the canonical definition of those shapes. Other vessels rely on
|
||||
// these field names.
|
||||
|
||||
// ── NodeId sanitisation ──────────────────────────────────────────────────────
|
||||
//
|
||||
// Sanitise an arbitrary string into a Mermaid-safe identifier.
|
||||
// - any char not in [a-zA-Z0-9_] becomes '_'
|
||||
// - consecutive underscores collapse
|
||||
// - trailing underscores stripped
|
||||
// - if first char is a digit, prepend 'n'
|
||||
// - if empty, return "node"
|
||||
|
||||
fn is_alnum_underscore(ch: String) -> Bool {
|
||||
let code: Int = str_char_code(ch, 0)
|
||||
if code >= 48 {
|
||||
if code <= 57 { return true }
|
||||
}
|
||||
if code >= 65 {
|
||||
if code <= 90 { return true }
|
||||
}
|
||||
if code >= 97 {
|
||||
if code <= 122 { return true }
|
||||
}
|
||||
if code == 95 { return true }
|
||||
false
|
||||
}
|
||||
|
||||
fn is_ascii_digit(ch: String) -> Bool {
|
||||
let code: Int = str_char_code(ch, 0)
|
||||
if code >= 48 {
|
||||
if code <= 57 { return true }
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
fn sanitize_id(s: String) -> String {
|
||||
let n: Int = str_len(s)
|
||||
if n == 0 { return "node" }
|
||||
|
||||
// Pass 1: replace and collapse.
|
||||
let out = ""
|
||||
let prev_underscore = false
|
||||
let i = 0
|
||||
while i < n {
|
||||
let ch: String = str_char_at(s, i)
|
||||
if is_alnum_underscore(ch) {
|
||||
let out = out + ch
|
||||
let prev_underscore = false
|
||||
} else {
|
||||
if !prev_underscore {
|
||||
let out = out + "_"
|
||||
}
|
||||
let prev_underscore = true
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Pass 2: strip trailing underscores.
|
||||
let m: Int = str_len(out)
|
||||
let end = m
|
||||
let stripping = true
|
||||
while stripping {
|
||||
if end <= 0 {
|
||||
let stripping = false
|
||||
} else {
|
||||
let last: String = str_char_at(out, end - 1)
|
||||
if last == "_" {
|
||||
let end = end - 1
|
||||
} else {
|
||||
let stripping = false
|
||||
}
|
||||
}
|
||||
}
|
||||
let out = str_slice(out, 0, end)
|
||||
|
||||
if str_len(out) == 0 { return "node" }
|
||||
|
||||
// Pass 3: leading-digit guard.
|
||||
let first: String = str_char_at(out, 0)
|
||||
if is_ascii_digit(first) {
|
||||
let out = "n" + out
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
// ── Constructors ──────────────────────────────────────────────────────────────
|
||||
|
||||
fn make_node(id: String, label: String, shape: String) -> Map<String, Any> {
|
||||
{ "id": id, "label": label, "shape": shape }
|
||||
}
|
||||
|
||||
fn make_edge(src: String, dst: String, kind: String) -> Map<String, Any> {
|
||||
{ "from": src, "to": dst, "label": "", "kind": kind }
|
||||
}
|
||||
|
||||
fn make_edge_with_label(src: String, dst: String, kind: String, label: String) -> Map<String, Any> {
|
||||
{ "from": src, "to": dst, "label": label, "kind": kind }
|
||||
}
|
||||
|
||||
fn make_group(id: String, label: String) -> Map<String, Any> {
|
||||
let empty_ids: [String] = el_list_empty()
|
||||
{ "id": id, "label": label, "node_ids": empty_ids, "direction": "" }
|
||||
}
|
||||
|
||||
fn make_graph() -> Map<String, Any> {
|
||||
let empty_n: [Map<String, Any>] = el_list_empty()
|
||||
let empty_e: [Map<String, Any>] = el_list_empty()
|
||||
let empty_g: [Map<String, Any>] = el_list_empty()
|
||||
{ "title": "", "direction": "top-down",
|
||||
"nodes": empty_n, "edges": empty_e, "groups": empty_g }
|
||||
}
|
||||
|
||||
// ── Shape vocabulary ──────────────────────────────────────────────────────────
|
||||
// Returns the canonical shape string for a token, or "" if unknown.
|
||||
|
||||
fn shape_from_token(tok: String) -> String {
|
||||
let t: String = str_trim(tok)
|
||||
if t == "rect" { return "rect" }
|
||||
if t == "rounded" { return "rounded" }
|
||||
if t == "cylinder" { return "cylinder" }
|
||||
if t == "diamond" { return "diamond" }
|
||||
if t == "stadium" { return "stadium" }
|
||||
if t == "primary" { return "primary" }
|
||||
""
|
||||
}
|
||||
|
||||
// Lower an Arbor shape into the renderer's NodeShape vocabulary.
|
||||
fn shape_to_node_shape(shape: String) -> String {
|
||||
if shape == "rect" { return "rectangle" }
|
||||
if shape == "primary" { return "rectangle" }
|
||||
if shape == "rounded" { return "rounded_rect" }
|
||||
if shape == "cylinder" { return "cylinder" }
|
||||
if shape == "diamond" { return "diamond" }
|
||||
if shape == "stadium" { return "stadium" }
|
||||
"rectangle"
|
||||
}
|
||||
|
||||
// ── Lowering: ArborGraph → DiagramGraph ──────────────────────────────────────
|
||||
//
|
||||
// Replaces every node with a diagram-form node carrying explicit style fields,
|
||||
// and every edge with a diagram-form edge carrying line/arrow strings.
|
||||
|
||||
fn lower_node(n: Map<String, Any>) -> Map<String, Any> {
|
||||
let shape: String = n["shape"]
|
||||
let node_shape: String = shape_to_node_shape(shape)
|
||||
let fill = ""
|
||||
let stroke = ""
|
||||
let color = ""
|
||||
if shape == "primary" {
|
||||
let fill = "#0052A0"
|
||||
let stroke = "#0052A0"
|
||||
let color = "#ffffff"
|
||||
}
|
||||
{ "id": n["id"], "label": n["label"], "sublabel": "",
|
||||
"shape": node_shape,
|
||||
"style_fill": fill, "style_stroke": stroke, "style_color": color }
|
||||
}
|
||||
|
||||
fn lower_edge(e: Map<String, Any>) -> Map<String, Any> {
|
||||
let kind: String = e["kind"]
|
||||
let line = "solid"
|
||||
let arrow = "forward"
|
||||
if kind == "dashed" {
|
||||
let line = "dashed"
|
||||
}
|
||||
if kind == "bidirectional" {
|
||||
let arrow = "both"
|
||||
}
|
||||
// forbidden uses solid line + forward arrow; the renderer overlays the
|
||||
// circle-X marker based on a forbidden-set the caller threads through.
|
||||
{ "from": e["from"], "to": e["to"], "label": e["label"],
|
||||
"line": line, "arrow": arrow }
|
||||
}
|
||||
|
||||
fn lower_graph(g: Map<String, Any>) -> Map<String, Any> {
|
||||
let nodes: [Map<String, Any>] = g["nodes"]
|
||||
let edges: [Map<String, Any>] = g["edges"]
|
||||
let lowered_nodes: [Map<String, Any>] = el_list_empty()
|
||||
let i = 0
|
||||
let n: Int = el_list_len(nodes)
|
||||
while i < n {
|
||||
let lowered_nodes = native_list_append(lowered_nodes, lower_node(get(nodes, i)))
|
||||
let i = i + 1
|
||||
}
|
||||
let lowered_edges: [Map<String, Any>] = el_list_empty()
|
||||
let i = 0
|
||||
let m: Int = el_list_len(edges)
|
||||
while i < m {
|
||||
let lowered_edges = native_list_append(lowered_edges, lower_edge(get(edges, i)))
|
||||
let i = i + 1
|
||||
}
|
||||
{ "title": g["title"], "direction": g["direction"],
|
||||
"nodes": lowered_nodes, "edges": lowered_edges, "groups": g["groups"] }
|
||||
}
|
||||
|
||||
// Find a node by id within a (lowered or raw) graph. Returns an empty map
|
||||
// when not found — callers check map_get(result, "id") for presence.
|
||||
fn graph_find_node(graph: Map<String, Any>, id: String) -> Map<String, Any> {
|
||||
let nodes: [Map<String, Any>] = graph["nodes"]
|
||||
let n: Int = el_list_len(nodes)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let node: Map<String, Any> = get(nodes, i)
|
||||
let nid: String = node["id"]
|
||||
if nid == id { return node }
|
||||
let i = i + 1
|
||||
}
|
||||
let empty: Map<String, Any> = el_map_new(0)
|
||||
empty
|
||||
}
|
||||
|
||||
// ── Forbidden-edge set helpers ────────────────────────────────────────────────
|
||||
// The lowered graph drops the "forbidden" kind (line/arrow have no slot for
|
||||
// it). Callers preserve the set as a list of "from->to" strings.
|
||||
|
||||
fn forbidden_key(from: String, to: String) -> String {
|
||||
from + "->" + to
|
||||
}
|
||||
|
||||
fn collect_forbidden(graph: Map<String, Any>) -> [String] {
|
||||
let edges: [Map<String, Any>] = graph["edges"]
|
||||
let n: Int = el_list_len(edges)
|
||||
let out: [String] = el_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let e: Map<String, Any> = get(edges, i)
|
||||
let kind: String = e["kind"]
|
||||
if kind == "forbidden" {
|
||||
let f: String = e["from"]
|
||||
let t: String = e["to"]
|
||||
let out = native_list_append(out, forbidden_key(f, t))
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
fn forbidden_contains(set: [String], src: String, dst: String) -> Bool {
|
||||
let key: String = forbidden_key(src, dst)
|
||||
let n: Int = el_list_len(set)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let s: String = get(set, i)
|
||||
if s == key { return true }
|
||||
let i = i + 1
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
// ── Smoke test ────────────────────────────────────────────────────────────────
|
||||
//
|
||||
// State is kept in process-local k/v storage so we never mix Int + Call or
|
||||
// Int + Ident in `+` (which the codegen heuristic emits as string concat
|
||||
// on tagged-pointer values, segfaulting on Int operands).
|
||||
|
||||
fn fail(label: String, got: String, want: String) -> Int {
|
||||
println("FAIL " + label + " got=[" + got + "] want=[" + want + "]")
|
||||
state_set("failures", "1")
|
||||
0
|
||||
}
|
||||
|
||||
fn check_eq(label: String, got: String, want: String) -> Int {
|
||||
if got == want {
|
||||
println("ok " + label + " = " + got)
|
||||
return 1
|
||||
}
|
||||
fail(label, got, want)
|
||||
}
|
||||
|
||||
check_eq("sanitize crates/nc-core",
|
||||
sanitize_id("crates/nc-core"), "crates_nc_core")
|
||||
|
||||
check_eq("sanitize package.json",
|
||||
sanitize_id("package.json"), "package_json")
|
||||
|
||||
check_eq("sanitize 42-module",
|
||||
sanitize_id("42-module"), "n42_module")
|
||||
|
||||
check_eq("sanitize empty", sanitize_id(""), "node")
|
||||
|
||||
check_eq("sanitize !!--@@", sanitize_id("!!--@@"), "node")
|
||||
|
||||
check_eq("shape_from_token rounded",
|
||||
shape_from_token("rounded"), "rounded")
|
||||
|
||||
check_eq("shape_to_node_shape primary",
|
||||
shape_to_node_shape("primary"), "rectangle")
|
||||
|
||||
// Lowering preserves a node id and adds style.
|
||||
let n: Map<String, Any> = make_node("svc", "Service", "primary")
|
||||
let ln: Map<String, Any> = lower_node(n)
|
||||
check_eq("lower preserves id", ln["id"], "svc")
|
||||
check_eq("lower applies primary fill", ln["style_fill"], "#0052A0")
|
||||
|
||||
// Edge lowering
|
||||
let e: Map<String, Any> = make_edge("a", "b", "dashed")
|
||||
let le: Map<String, Any> = lower_edge(e)
|
||||
check_eq("lower edge dashed line", le["line"], "dashed")
|
||||
|
||||
let e2: Map<String, Any> = make_edge("a", "b", "bidirectional")
|
||||
let le2: Map<String, Any> = lower_edge(e2)
|
||||
check_eq("lower edge bidirectional arrow", le2["arrow"], "both")
|
||||
|
||||
println("")
|
||||
let failures: String = state_get("failures")
|
||||
if str_eq(failures, "1") {
|
||||
println("arbor-core: FAILED")
|
||||
exit_program(1)
|
||||
} else {
|
||||
println("arbor-core: ok")
|
||||
}
|
||||
@@ -1,19 +0,0 @@
|
||||
// arbor-diagram — diagram intermediate representation + Mermaid serializer
|
||||
// + dependency-graph builders. Consumes raw graph values built by arbor-core
|
||||
// or arbor-parse and produces Mermaid markup or other serializations.
|
||||
|
||||
vessel "arbor-diagram" {
|
||||
version "0.1.0"
|
||||
description "Diagram IR + Mermaid serializer + architecture diagram builders"
|
||||
authors ["Neuron Technologies"]
|
||||
edition "2026"
|
||||
}
|
||||
|
||||
dependencies {
|
||||
arbor-core "0.1"
|
||||
}
|
||||
|
||||
build {
|
||||
entry "src/main.el"
|
||||
output "dist/"
|
||||
}
|
||||
@@ -1,433 +0,0 @@
|
||||
// arbor-diagram — diagram intermediate representation (AST + IR).
|
||||
//
|
||||
// Where arbor-core supplies the *.arbor source-language model — Mermaid-safe
|
||||
// IDs, ArborShape strings, ArborEdgeKind strings, and the lowered "diagram-
|
||||
// form" map — arbor-diagram exposes the same lowered model as the canonical
|
||||
// IR for downstream serializers (arbor-render and any future Mermaid-style
|
||||
// emitter). The two vessels overlap by design: arbor-core is responsible for
|
||||
// *naming* the schema; arbor-diagram is responsible for *building* values
|
||||
// against it.
|
||||
//
|
||||
// The Rust crate ships small AST builder structs (`DiagramNode::new`,
|
||||
// `DiagramEdge::with_label`, `DiagramGraph::add_node`). El has no method
|
||||
// chaining, no Default::default(), no enum types. The El idiom is a stack
|
||||
// of immutable maps with explicit constructor + with_* helpers that take
|
||||
// the value and return a freshly-allocated map.
|
||||
//
|
||||
// Public surface:
|
||||
// make_node(id, label) → DiagramNode
|
||||
// with_shape(node, shape) → DiagramNode
|
||||
// with_sublabel(node, sublabel) → DiagramNode
|
||||
// with_style(node, fill, stroke, color) → DiagramNode
|
||||
//
|
||||
// make_edge(from, to) → DiagramEdge
|
||||
// with_label(edge, label)
|
||||
// with_line(edge, line) // "solid"/"dashed"/"dotted"/"thick"
|
||||
// with_arrow(edge, arrow) // "forward"/"backward"/"both"/"none"
|
||||
//
|
||||
// make_group(id, label) → DiagramGroup
|
||||
// with_node(group, node_id)
|
||||
// with_nodes(group, [node_id])
|
||||
// with_direction(group, dir)
|
||||
//
|
||||
// make_graph(title) → DiagramGraph
|
||||
// with_direction(graph, dir)
|
||||
// graph_add_node(graph, node) → DiagramGraph
|
||||
// graph_add_edge(graph, edge) → DiagramGraph
|
||||
// graph_add_group(graph, group) → DiagramGraph
|
||||
// graph_node(graph, id) → DiagramNode | empty map
|
||||
//
|
||||
// Shape vocabulary (lowered): see arbor-core. The local copy here mirrors
|
||||
// the table in arbor-core/src/main.el so this vessel is hermetic.
|
||||
|
||||
// ── NodeShape vocabulary ────────────────────────────────────────────────────
|
||||
|
||||
fn node_shape_rectangle() -> String { "rectangle" }
|
||||
fn node_shape_rounded_rect() -> String { "rounded_rect" }
|
||||
fn node_shape_stadium() -> String { "stadium" }
|
||||
fn node_shape_cylinder() -> String { "cylinder" }
|
||||
fn node_shape_diamond() -> String { "diamond" }
|
||||
fn node_shape_parallelogram() -> String { "parallelogram" }
|
||||
fn node_shape_database() -> String { "database" }
|
||||
fn node_shape_subroutine() -> String { "subroutine" }
|
||||
|
||||
fn node_shape_valid(s: String) -> Bool {
|
||||
if str_eq(s, "rectangle") { return true }
|
||||
if str_eq(s, "rounded_rect") { return true }
|
||||
if str_eq(s, "stadium") { return true }
|
||||
if str_eq(s, "cylinder") { return true }
|
||||
if str_eq(s, "diamond") { return true }
|
||||
if str_eq(s, "parallelogram") { return true }
|
||||
if str_eq(s, "database") { return true }
|
||||
if str_eq(s, "subroutine") { return true }
|
||||
false
|
||||
}
|
||||
|
||||
// ── EdgeLine vocabulary ─────────────────────────────────────────────────────
|
||||
|
||||
fn edge_line_solid() -> String { "solid" }
|
||||
fn edge_line_dashed() -> String { "dashed" }
|
||||
fn edge_line_dotted() -> String { "dotted" }
|
||||
fn edge_line_thick() -> String { "thick" }
|
||||
|
||||
fn edge_line_valid(s: String) -> Bool {
|
||||
if str_eq(s, "solid") { return true }
|
||||
if str_eq(s, "dashed") { return true }
|
||||
if str_eq(s, "dotted") { return true }
|
||||
if str_eq(s, "thick") { return true }
|
||||
false
|
||||
}
|
||||
|
||||
// ── EdgeArrow vocabulary ────────────────────────────────────────────────────
|
||||
|
||||
fn edge_arrow_forward() -> String { "forward" }
|
||||
fn edge_arrow_backward() -> String { "backward" }
|
||||
fn edge_arrow_both() -> String { "both" }
|
||||
fn edge_arrow_none() -> String { "none" }
|
||||
|
||||
fn edge_arrow_valid(s: String) -> Bool {
|
||||
if str_eq(s, "forward") { return true }
|
||||
if str_eq(s, "backward") { return true }
|
||||
if str_eq(s, "both") { return true }
|
||||
if str_eq(s, "none") { return true }
|
||||
false
|
||||
}
|
||||
|
||||
// ── Direction vocabulary ────────────────────────────────────────────────────
|
||||
|
||||
fn direction_top_down() -> String { "top-down" }
|
||||
fn direction_left_right() -> String { "left-right" }
|
||||
fn direction_right_left() -> String { "right-left" }
|
||||
fn direction_bottom_up() -> String { "bottom-up" }
|
||||
|
||||
fn direction_valid(s: String) -> Bool {
|
||||
if str_eq(s, "top-down") { return true }
|
||||
if str_eq(s, "left-right") { return true }
|
||||
if str_eq(s, "right-left") { return true }
|
||||
if str_eq(s, "bottom-up") { return true }
|
||||
false
|
||||
}
|
||||
|
||||
// ── DiagramNode ─────────────────────────────────────────────────────────────
|
||||
|
||||
fn make_node(id: String, label: String) -> Map<String, Any> {
|
||||
{
|
||||
"id": id,
|
||||
"label": label,
|
||||
"sublabel": "",
|
||||
"shape": "rectangle",
|
||||
"style_fill": "",
|
||||
"style_stroke": "",
|
||||
"style_color": ""
|
||||
}
|
||||
}
|
||||
|
||||
fn with_shape(node: Map<String, Any>, shape: String) -> Map<String, Any> {
|
||||
{
|
||||
"id": node["id"],
|
||||
"label": node["label"],
|
||||
"sublabel": node["sublabel"],
|
||||
"shape": shape,
|
||||
"style_fill": node["style_fill"],
|
||||
"style_stroke": node["style_stroke"],
|
||||
"style_color": node["style_color"]
|
||||
}
|
||||
}
|
||||
|
||||
fn with_sublabel(node: Map<String, Any>, sublabel: String) -> Map<String, Any> {
|
||||
{
|
||||
"id": node["id"],
|
||||
"label": node["label"],
|
||||
"sublabel": sublabel,
|
||||
"shape": node["shape"],
|
||||
"style_fill": node["style_fill"],
|
||||
"style_stroke": node["style_stroke"],
|
||||
"style_color": node["style_color"]
|
||||
}
|
||||
}
|
||||
|
||||
fn with_style(node: Map<String, Any>, fill: String, stroke: String, color: String) -> Map<String, Any> {
|
||||
{
|
||||
"id": node["id"],
|
||||
"label": node["label"],
|
||||
"sublabel": node["sublabel"],
|
||||
"shape": node["shape"],
|
||||
"style_fill": fill,
|
||||
"style_stroke": stroke,
|
||||
"style_color": color
|
||||
}
|
||||
}
|
||||
|
||||
// ── DiagramEdge ─────────────────────────────────────────────────────────────
|
||||
|
||||
fn make_edge(from: String, to: String) -> Map<String, Any> {
|
||||
{
|
||||
"from": from,
|
||||
"to": to,
|
||||
"label": "",
|
||||
"line": "solid",
|
||||
"arrow": "forward"
|
||||
}
|
||||
}
|
||||
|
||||
fn with_label(edge: Map<String, Any>, label: String) -> Map<String, Any> {
|
||||
{
|
||||
"from": edge["from"],
|
||||
"to": edge["to"],
|
||||
"label": label,
|
||||
"line": edge["line"],
|
||||
"arrow": edge["arrow"]
|
||||
}
|
||||
}
|
||||
|
||||
fn with_line(edge: Map<String, Any>, line: String) -> Map<String, Any> {
|
||||
{
|
||||
"from": edge["from"],
|
||||
"to": edge["to"],
|
||||
"label": edge["label"],
|
||||
"line": line,
|
||||
"arrow": edge["arrow"]
|
||||
}
|
||||
}
|
||||
|
||||
fn with_arrow(edge: Map<String, Any>, arrow: String) -> Map<String, Any> {
|
||||
{
|
||||
"from": edge["from"],
|
||||
"to": edge["to"],
|
||||
"label": edge["label"],
|
||||
"line": edge["line"],
|
||||
"arrow": arrow
|
||||
}
|
||||
}
|
||||
|
||||
// ── DiagramGroup ────────────────────────────────────────────────────────────
|
||||
|
||||
fn make_group(id: String, label: String) -> Map<String, Any> {
|
||||
let empty: [String] = native_list_empty()
|
||||
{
|
||||
"id": id,
|
||||
"label": label,
|
||||
"node_ids": empty,
|
||||
"direction": ""
|
||||
}
|
||||
}
|
||||
|
||||
fn with_node(group: Map<String, Any>, node_id: String) -> Map<String, Any> {
|
||||
let cur: [String] = group["node_ids"]
|
||||
let next: [String] = native_list_append(cur, node_id)
|
||||
{
|
||||
"id": group["id"],
|
||||
"label": group["label"],
|
||||
"node_ids": next,
|
||||
"direction": group["direction"]
|
||||
}
|
||||
}
|
||||
|
||||
fn with_nodes(group: Map<String, Any>, ids: [String]) -> Map<String, Any> {
|
||||
let cur: [String] = group["node_ids"]
|
||||
let n: Int = el_list_len(ids)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let cur = native_list_append(cur, get(ids, i))
|
||||
let i = i + 1
|
||||
}
|
||||
{
|
||||
"id": group["id"],
|
||||
"label": group["label"],
|
||||
"node_ids": cur,
|
||||
"direction": group["direction"]
|
||||
}
|
||||
}
|
||||
|
||||
fn with_group_direction(group: Map<String, Any>, dir: String) -> Map<String, Any> {
|
||||
{
|
||||
"id": group["id"],
|
||||
"label": group["label"],
|
||||
"node_ids": group["node_ids"],
|
||||
"direction": dir
|
||||
}
|
||||
}
|
||||
|
||||
// ── DiagramGraph ────────────────────────────────────────────────────────────
|
||||
|
||||
fn make_graph(title: String) -> Map<String, Any> {
|
||||
let empty_n: [Map<String, Any>] = native_list_empty()
|
||||
let empty_e: [Map<String, Any>] = native_list_empty()
|
||||
let empty_g: [Map<String, Any>] = native_list_empty()
|
||||
{
|
||||
"title": title,
|
||||
"direction": "top-down",
|
||||
"nodes": empty_n,
|
||||
"edges": empty_e,
|
||||
"groups": empty_g
|
||||
}
|
||||
}
|
||||
|
||||
fn with_direction(graph: Map<String, Any>, dir: String) -> Map<String, Any> {
|
||||
{
|
||||
"title": graph["title"],
|
||||
"direction": dir,
|
||||
"nodes": graph["nodes"],
|
||||
"edges": graph["edges"],
|
||||
"groups": graph["groups"]
|
||||
}
|
||||
}
|
||||
|
||||
fn graph_add_node(graph: Map<String, Any>, node: Map<String, Any>) -> Map<String, Any> {
|
||||
let cur: [Map<String, Any>] = graph["nodes"]
|
||||
let next: [Map<String, Any>] = native_list_append(cur, node)
|
||||
{
|
||||
"title": graph["title"],
|
||||
"direction": graph["direction"],
|
||||
"nodes": next,
|
||||
"edges": graph["edges"],
|
||||
"groups": graph["groups"]
|
||||
}
|
||||
}
|
||||
|
||||
fn graph_add_edge(graph: Map<String, Any>, edge: Map<String, Any>) -> Map<String, Any> {
|
||||
let cur: [Map<String, Any>] = graph["edges"]
|
||||
let next: [Map<String, Any>] = native_list_append(cur, edge)
|
||||
{
|
||||
"title": graph["title"],
|
||||
"direction": graph["direction"],
|
||||
"nodes": graph["nodes"],
|
||||
"edges": next,
|
||||
"groups": graph["groups"]
|
||||
}
|
||||
}
|
||||
|
||||
fn graph_add_group(graph: Map<String, Any>, group: Map<String, Any>) -> Map<String, Any> {
|
||||
let cur: [Map<String, Any>] = graph["groups"]
|
||||
let next: [Map<String, Any>] = native_list_append(cur, group)
|
||||
{
|
||||
"title": graph["title"],
|
||||
"direction": graph["direction"],
|
||||
"nodes": graph["nodes"],
|
||||
"edges": graph["edges"],
|
||||
"groups": next
|
||||
}
|
||||
}
|
||||
|
||||
// Find a node by id. Returns an empty map (no "id" field) when not present.
|
||||
fn graph_node(graph: Map<String, Any>, id: String) -> Map<String, Any> {
|
||||
let nodes: [Map<String, Any>] = graph["nodes"]
|
||||
let n: Int = el_list_len(nodes)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let nd: Map<String, Any> = get(nodes, i)
|
||||
let nid: String = nd["id"]
|
||||
if str_eq(nid, id) { return nd }
|
||||
let i = i + 1
|
||||
}
|
||||
let empty: Map<String, Any> = el_map_new(0)
|
||||
empty
|
||||
}
|
||||
|
||||
// ── Smoke test ──────────────────────────────────────────────────────────────
|
||||
|
||||
fn fail(label: String, got: String, want: String) -> Int {
|
||||
println("FAIL " + label + " got=[" + got + "] want=[" + want + "]")
|
||||
state_set("smoke_failures", "1")
|
||||
0
|
||||
}
|
||||
|
||||
fn check_eq(label: String, got: String, want: String) -> Int {
|
||||
if got == want {
|
||||
println("ok " + label + " = " + got)
|
||||
return 1
|
||||
}
|
||||
fail(label, got, want)
|
||||
}
|
||||
|
||||
// Vocabulary self-checks
|
||||
check_eq("shape rectangle valid",
|
||||
bool_to_str(node_shape_valid("rectangle")), "true")
|
||||
check_eq("shape hexagon invalid",
|
||||
bool_to_str(node_shape_valid("hexagon")), "false")
|
||||
check_eq("line dashed valid",
|
||||
bool_to_str(edge_line_valid("dashed")), "true")
|
||||
check_eq("arrow both valid",
|
||||
bool_to_str(edge_arrow_valid("both")), "true")
|
||||
check_eq("dir top-down valid",
|
||||
bool_to_str(direction_valid("top-down")), "true")
|
||||
|
||||
// Node builder
|
||||
let n0: Map<String, Any> = make_node("svc", "Service")
|
||||
check_eq("node default shape", n0["shape"], "rectangle")
|
||||
check_eq("node default sublabel empty", n0["sublabel"], "")
|
||||
|
||||
let n1: Map<String, Any> = with_shape(n0, "cylinder")
|
||||
check_eq("node with_shape", n1["shape"], "cylinder")
|
||||
check_eq("node id preserved", n1["id"], "svc")
|
||||
|
||||
let n2: Map<String, Any> = with_sublabel(n1, "v0.1.0")
|
||||
check_eq("node with_sublabel", n2["sublabel"], "v0.1.0")
|
||||
|
||||
let n3: Map<String, Any> = with_style(n2, "#0052A0", "#0052A0", "#ffffff")
|
||||
check_eq("node style fill", n3["style_fill"], "#0052A0")
|
||||
check_eq("node style color", n3["style_color"], "#ffffff")
|
||||
|
||||
// Edge builder
|
||||
let e0: Map<String, Any> = make_edge("a", "b")
|
||||
check_eq("edge default line", e0["line"], "solid")
|
||||
check_eq("edge default arrow", e0["arrow"], "forward")
|
||||
let e1: Map<String, Any> = with_line(e0, "dashed")
|
||||
let e2: Map<String, Any> = with_arrow(e1, "both")
|
||||
let e3: Map<String, Any> = with_label(e2, "calls")
|
||||
check_eq("edge line", e3["line"], "dashed")
|
||||
check_eq("edge arrow", e3["arrow"], "both")
|
||||
check_eq("edge label", e3["label"], "calls")
|
||||
|
||||
// Group builder
|
||||
let g0: Map<String, Any> = make_group("core", "Application Core")
|
||||
let g1: Map<String, Any> = with_node(g0, "api")
|
||||
let g2: Map<String, Any> = with_node(g1, "svc")
|
||||
let ids2: [String] = g2["node_ids"]
|
||||
check_eq("group with two nodes", int_to_str(el_list_len(ids2)), "2")
|
||||
|
||||
let g3: Map<String, Any> = make_group("infra", "Infrastructure")
|
||||
let extras: [String] = native_list_empty()
|
||||
let extras = native_list_append(extras, "db")
|
||||
let extras = native_list_append(extras, "cache")
|
||||
let g4: Map<String, Any> = with_nodes(g3, extras)
|
||||
let ids4: [String] = g4["node_ids"]
|
||||
check_eq("group with_nodes appends", int_to_str(el_list_len(ids4)), "2")
|
||||
|
||||
// Graph builder + lookup
|
||||
let G0: Map<String, Any> = make_graph("System")
|
||||
let G1: Map<String, Any> = with_direction(G0, "left-right")
|
||||
let G2: Map<String, Any> = graph_add_node(G1, n3)
|
||||
let nb: Map<String, Any> = make_node("b", "Backend")
|
||||
let G3: Map<String, Any> = graph_add_node(G2, nb)
|
||||
let G4: Map<String, Any> = graph_add_edge(G3, e3)
|
||||
let G5: Map<String, Any> = graph_add_group(G4, g4)
|
||||
|
||||
check_eq("graph title", G5["title"], "System")
|
||||
check_eq("graph direction", G5["direction"], "left-right")
|
||||
let gn: [Map<String, Any>] = G5["nodes"]
|
||||
let ge: [Map<String, Any>] = G5["edges"]
|
||||
let gg: [Map<String, Any>] = G5["groups"]
|
||||
check_eq("graph nodes count", int_to_str(el_list_len(gn)), "2")
|
||||
check_eq("graph edges count", int_to_str(el_list_len(ge)), "1")
|
||||
check_eq("graph groups count", int_to_str(el_list_len(gg)), "1")
|
||||
|
||||
let found: Map<String, Any> = graph_node(G5, "svc")
|
||||
check_eq("graph_node found", found["id"], "svc")
|
||||
let missing: Map<String, Any> = graph_node(G5, "nonexistent")
|
||||
let missing_id: String = missing["id"]
|
||||
if str_len(missing_id) == 0 {
|
||||
println("ok graph_node missing returns empty")
|
||||
} else {
|
||||
println("FAIL graph_node missing returned: " + missing_id)
|
||||
state_set("smoke_failures", "1")
|
||||
}
|
||||
|
||||
println("")
|
||||
let failures: String = state_get("smoke_failures")
|
||||
if str_eq(failures, "1") {
|
||||
println("arbor-diagram: FAILED")
|
||||
exit_program(1)
|
||||
} else {
|
||||
println("arbor-diagram: ok")
|
||||
}
|
||||
@@ -1,19 +0,0 @@
|
||||
// arbor-layout — hierarchical layout engine. Assigns (x, y) positions to
|
||||
// every node, computes group bounding boxes, and the canvas size. Consumes
|
||||
// a diagram graph; produces a layout-result value.
|
||||
|
||||
vessel "arbor-layout" {
|
||||
version "0.1.0"
|
||||
description "Hierarchical layout engine — rank assignment, positioning, group bounds"
|
||||
authors ["Neuron Technologies"]
|
||||
edition "2026"
|
||||
}
|
||||
|
||||
dependencies {
|
||||
arbor-core "0.1"
|
||||
}
|
||||
|
||||
build {
|
||||
entry "src/main.el"
|
||||
output "dist/"
|
||||
}
|
||||
@@ -1,591 +0,0 @@
|
||||
// arbor-layout — hierarchical layout for diagram graphs.
|
||||
//
|
||||
// Public entry point:
|
||||
// fn arbor_layout(graph: Map<String, Any>) -> Map<String, Any>
|
||||
//
|
||||
// The graph is the lowered (diagram-form) shape. The result map has:
|
||||
// "node_pos_<id>" → { "x":Float, "y":Float } centre point
|
||||
// "node_size_<id>" → { "w":Float, "h":Float }
|
||||
// "group_bounds_<id>" → { "x":Float, "y":Float, "w":Float, "h":Float }
|
||||
// "node_ids" → [String] iteration order
|
||||
// "group_ids" → [String] iteration order
|
||||
// "canvas" → { "w":Float, "h":Float }
|
||||
//
|
||||
// Floats are El-encoded — store via the runtime's bit-cast convention.
|
||||
// All arithmetic on positions/sizes is done in Float; integers (rank index)
|
||||
// stay as Int.
|
||||
//
|
||||
// Algorithm (simplified Sugiyama):
|
||||
// 1. Assign ranks via topological propagation (longest path from sources).
|
||||
// 2. Group nodes by rank, preserving declaration order.
|
||||
// 3. Position each rank as a row (top-down/bottom-up) or column (LR/RL).
|
||||
// 4. Compute group bounding boxes from member positions.
|
||||
// 5. Compute canvas size to enclose everything.
|
||||
//
|
||||
// The current implementation is the same simplified Sugiyama as the Rust
|
||||
// version; perfectly identical numerical output is not promised but the
|
||||
// relative ordering and bounding-box semantics match.
|
||||
|
||||
// ── Spacing constants (declared as float-bit-cast helpers) ──────────────────
|
||||
|
||||
fn k_node_base_w() -> el_val_t { int_to_float(120) }
|
||||
fn k_node_base_h() -> el_val_t { int_to_float(40) }
|
||||
fn k_node_char_extra() -> el_val_t { int_to_float(8) }
|
||||
fn k_h_gap() -> el_val_t { int_to_float(60) }
|
||||
fn k_v_gap() -> el_val_t { int_to_float(80) }
|
||||
fn k_group_pad() -> el_val_t { int_to_float(20) }
|
||||
fn k_margin() -> el_val_t { int_to_float(40) }
|
||||
|
||||
// Float-aware max/min via int_to_float / float arithmetic — but el_max
|
||||
// works in raw int comparison space, so we bit-cast carefully.
|
||||
// For our purposes we only need monotonic comparisons on positive values,
|
||||
// which IEEE 754 doubles + sign-magnitude bit patterns happen to preserve
|
||||
// for non-negative floats — but it's safer to do the comparison via the
|
||||
// math layer. We use a helper that decodes both, picks the bigger, and
|
||||
// re-encodes.
|
||||
//
|
||||
// Implemented in C terms: math_max(a, b) — but el_runtime doesn't expose
|
||||
// a float-aware max, so we synthesise one.
|
||||
|
||||
fn fmax(a: el_val_t, b: el_val_t) -> el_val_t {
|
||||
// Compare via float subtraction's sign: a - b. Float subtraction is the
|
||||
// multiply chain implemented via the C code generator. But el's `-` on
|
||||
// bit-cast doubles doesn't perform IEEE arithmetic — it's a 64-bit int
|
||||
// subtract. Workaround: round-trip through format_float and str_to_float.
|
||||
// For our layout numbers (small non-negative integers stored as floats)
|
||||
// we can compare via the raw bits: a positive float's bit pattern is
|
||||
// monotonically ordered, so `a > b` on the int reinterpretation gives
|
||||
// the same result as on the actual double for non-negative values.
|
||||
if a > b { return a }
|
||||
b
|
||||
}
|
||||
|
||||
fn fadd(a: el_val_t, b: el_val_t) -> el_val_t {
|
||||
// a, b are bit-cast doubles. Safe addition: int-to-float, format, parse.
|
||||
// For the small positive integers we work with, we reconstruct the
|
||||
// numeric value via format_float → str_to_float, perform addition by
|
||||
// pulling them through str representations. Costly but correct on the
|
||||
// current runtime. Fast path: if both are exact ints stored as floats
|
||||
// we can also keep an Int "shadow" — but the simpler approach is to
|
||||
// route through the printf-based formatter once per layout pass.
|
||||
let as: String = format_float(a, 6)
|
||||
let bs: String = format_float(b, 6)
|
||||
// Parse back to numeric.
|
||||
let af: el_val_t = str_to_float(as)
|
||||
let bf: el_val_t = str_to_float(bs)
|
||||
// No real-add primitive; build the sum from int parts where possible.
|
||||
// Convert to int at full resolution: float_to_int truncates towards zero,
|
||||
// which for our values (always integer-valued) is exact.
|
||||
let ai: Int = float_to_int(af)
|
||||
let bi: Int = float_to_int(bf)
|
||||
int_to_float(ai + bi)
|
||||
}
|
||||
|
||||
fn fsub(a: el_val_t, b: el_val_t) -> el_val_t {
|
||||
let ai: Int = float_to_int(a)
|
||||
let bi: Int = float_to_int(b)
|
||||
int_to_float(ai - bi)
|
||||
}
|
||||
|
||||
fn fmul(a: el_val_t, b: el_val_t) -> el_val_t {
|
||||
let ai: Int = float_to_int(a)
|
||||
let bi: Int = float_to_int(b)
|
||||
int_to_float(ai * bi)
|
||||
}
|
||||
|
||||
fn fdiv2(a: el_val_t) -> el_val_t {
|
||||
let ai: Int = float_to_int(a)
|
||||
int_to_float(ai / 2)
|
||||
}
|
||||
|
||||
// ── Node size based on label width ──────────────────────────────────────────
|
||||
|
||||
fn node_size_for(label: String) -> Map<String, Any> {
|
||||
let len: Int = str_len(label)
|
||||
let extra: Int = 0
|
||||
if len > 10 {
|
||||
let extra = len - 10
|
||||
}
|
||||
let w_int: Int = 120 + 8 * extra
|
||||
let w: el_val_t = int_to_float(w_int)
|
||||
let h: el_val_t = int_to_float(40)
|
||||
{ "w": w, "h": h }
|
||||
}
|
||||
|
||||
// ── Adjacency-list construction ─────────────────────────────────────────────
|
||||
//
|
||||
// Builds successor and in-degree maps keyed by node id.
|
||||
|
||||
fn build_succ_indeg(graph: Map<String, Any>) -> Map<String, Any> {
|
||||
let nodes: [Map<String, Any>] = graph["nodes"]
|
||||
let edges: [Map<String, Any>] = graph["edges"]
|
||||
let n: Int = el_list_len(nodes)
|
||||
let m: Int = el_list_len(edges)
|
||||
|
||||
let succ: Map<String, Any> = el_map_new(0)
|
||||
let indeg: Map<String, Any> = el_map_new(0)
|
||||
|
||||
let i = 0
|
||||
while i < n {
|
||||
let nd: Map<String, Any> = get(nodes, i)
|
||||
let nid: String = nd["id"]
|
||||
let empty: [String] = el_list_empty()
|
||||
let succ = el_map_set(succ, nid, empty)
|
||||
let indeg = el_map_set(indeg, nid, 0)
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
let i = 0
|
||||
while i < m {
|
||||
let e: Map<String, Any> = get(edges, i)
|
||||
let src: String = e["from"]
|
||||
let dst: String = e["to"]
|
||||
let cur_succ: [String] = el_map_get(succ, src)
|
||||
let new_succ: [String] = native_list_append(cur_succ, dst)
|
||||
let succ = el_map_set(succ, src, new_succ)
|
||||
let prev: Int = el_map_get(indeg, dst)
|
||||
let indeg = el_map_set(indeg, dst, prev + 1)
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
{ "succ": succ, "indeg": indeg }
|
||||
}
|
||||
|
||||
// ── Topological rank assignment ─────────────────────────────────────────────
|
||||
//
|
||||
// Returns a map: node_id → rank.
|
||||
|
||||
fn assign_ranks(graph: Map<String, Any>) -> Map<String, Any> {
|
||||
let nodes: [Map<String, Any>] = graph["nodes"]
|
||||
let n: Int = el_list_len(nodes)
|
||||
let adj: Map<String, Any> = build_succ_indeg(graph)
|
||||
let succ: Map<String, Any> = adj["succ"]
|
||||
let indeg: Map<String, Any> = adj["indeg"]
|
||||
|
||||
let ranks: Map<String, Any> = el_map_new(0)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let nd: Map<String, Any> = get(nodes, i)
|
||||
let nid: String = nd["id"]
|
||||
let ranks = el_map_set(ranks, nid, 0)
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Initialise queue with all nodes whose in-degree is 0 (in declaration
|
||||
// order, mirroring the Rust implementation's ordering guarantee).
|
||||
let queue: [String] = el_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let nd: Map<String, Any> = get(nodes, i)
|
||||
let nid: String = nd["id"]
|
||||
let d: Int = el_map_get(indeg, nid)
|
||||
if d == 0 {
|
||||
let queue = native_list_append(queue, nid)
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
let head = 0
|
||||
let running = true
|
||||
while running {
|
||||
if head >= el_list_len(queue) {
|
||||
let running = false
|
||||
} else {
|
||||
let cur: String = get(queue, head)
|
||||
let head = head + 1
|
||||
let cur_rank: Int = el_map_get(ranks, cur)
|
||||
let neighbours: [String] = el_map_get(succ, cur)
|
||||
let nn: Int = el_list_len(neighbours)
|
||||
let j = 0
|
||||
while j < nn {
|
||||
let nb: String = get(neighbours, j)
|
||||
let nb_rank: Int = el_map_get(ranks, nb)
|
||||
let cand: Int = cur_rank + 1
|
||||
if cand > nb_rank {
|
||||
let ranks = el_map_set(ranks, nb, cand)
|
||||
}
|
||||
let cur_d: Int = el_map_get(indeg, nb)
|
||||
let new_d: Int = cur_d - 1
|
||||
let indeg = el_map_set(indeg, nb, new_d)
|
||||
if new_d <= 0 {
|
||||
let queue = native_list_append(queue, nb)
|
||||
}
|
||||
let j = j + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
ranks
|
||||
}
|
||||
|
||||
// ── Layout pass ─────────────────────────────────────────────────────────────
|
||||
|
||||
fn arbor_layout(graph: Map<String, Any>) -> Map<String, Any> {
|
||||
let nodes: [Map<String, Any>] = graph["nodes"]
|
||||
let n: Int = el_list_len(nodes)
|
||||
let direction: String = graph["direction"]
|
||||
|
||||
let result: Map<String, Any> = el_map_new(0)
|
||||
let result = el_map_set(result, "node_ids", el_list_empty())
|
||||
let result = el_map_set(result, "group_ids", el_list_empty())
|
||||
|
||||
if n == 0 {
|
||||
let canvas: Map<String, Any> = { "w": int_to_float(200), "h": int_to_float(100) }
|
||||
let result = el_map_set(result, "canvas", canvas)
|
||||
return result
|
||||
}
|
||||
|
||||
let ranks: Map<String, Any> = assign_ranks(graph)
|
||||
let max_rank = 0
|
||||
let i = 0
|
||||
while i < n {
|
||||
let nd: Map<String, Any> = get(nodes, i)
|
||||
let nid: String = nd["id"]
|
||||
let r: Int = el_map_get(ranks, nid)
|
||||
if r > max_rank { let max_rank = r }
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Group nodes by rank, preserving declaration order. Buckets are stored
|
||||
// in process state so we can iterate without nested-list mutation.
|
||||
let i = 0
|
||||
while i <= max_rank {
|
||||
state_set("rank_bucket_" + int_to_str(i), "")
|
||||
let i = i + 1
|
||||
}
|
||||
let i = 0
|
||||
while i < n {
|
||||
let nd: Map<String, Any> = get(nodes, i)
|
||||
let nid: String = nd["id"]
|
||||
let r: Int = el_map_get(ranks, nid)
|
||||
let key = "rank_bucket_" + int_to_str(r)
|
||||
let prev: String = state_get(key)
|
||||
if str_eq(prev, "") {
|
||||
state_set(key, nid)
|
||||
} else {
|
||||
state_set(key, prev + "" + nid)
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Pre-compute sizes and stash a label-keyed cache.
|
||||
let id_list: [String] = el_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let nd: Map<String, Any> = get(nodes, i)
|
||||
let nid: String = nd["id"]
|
||||
let lbl: String = nd["label"]
|
||||
let sz: Map<String, Any> = node_size_for(lbl)
|
||||
let result = el_map_set(result, "node_size_" + nid, sz)
|
||||
let id_list = native_list_append(id_list, nid)
|
||||
let i = i + 1
|
||||
}
|
||||
let result = el_map_set(result, "node_ids", id_list)
|
||||
|
||||
// Position pass.
|
||||
let is_vertical = true
|
||||
if str_eq(direction, "left-right") { let is_vertical = false }
|
||||
if str_eq(direction, "right-left") { let is_vertical = false }
|
||||
|
||||
let cursor: el_val_t = k_margin()
|
||||
|
||||
let r = 0
|
||||
while r <= max_rank {
|
||||
let bucket_str: String = state_get("rank_bucket_" + int_to_str(r))
|
||||
if !str_eq(bucket_str, "") {
|
||||
let ids: [String] = str_split(bucket_str, "")
|
||||
let ids_n: Int = el_list_len(ids)
|
||||
|
||||
// Track row height (for vertical) or column width (for horizontal).
|
||||
let cross_max: el_val_t = int_to_float(40)
|
||||
let j = 0
|
||||
while j < ids_n {
|
||||
let nid: String = get(ids, j)
|
||||
let sz: Map<String, Any> = el_map_get(result, "node_size_" + nid)
|
||||
if is_vertical {
|
||||
let h: el_val_t = sz["h"]
|
||||
let cross_max = fmax(cross_max, h)
|
||||
} else {
|
||||
let w: el_val_t = sz["w"]
|
||||
let cross_max = fmax(cross_max, w)
|
||||
}
|
||||
let j = j + 1
|
||||
}
|
||||
|
||||
if is_vertical {
|
||||
let row_h: el_val_t = cross_max
|
||||
let y_center: el_val_t = fadd(cursor, fdiv2(row_h))
|
||||
let x_cursor: el_val_t = k_margin()
|
||||
let j = 0
|
||||
while j < ids_n {
|
||||
let nid: String = get(ids, j)
|
||||
let sz: Map<String, Any> = el_map_get(result, "node_size_" + nid)
|
||||
let w: el_val_t = sz["w"]
|
||||
let cx: el_val_t = fadd(x_cursor, fdiv2(w))
|
||||
let pos: Map<String, Any> = { "x": cx, "y": y_center }
|
||||
let result = el_map_set(result, "node_pos_" + nid, pos)
|
||||
let x_cursor = fadd(fadd(x_cursor, w), k_h_gap())
|
||||
let j = j + 1
|
||||
}
|
||||
let cursor = fadd(fadd(cursor, row_h), k_v_gap())
|
||||
} else {
|
||||
let col_w: el_val_t = cross_max
|
||||
let x_center: el_val_t = fadd(cursor, fdiv2(col_w))
|
||||
let y_cursor: el_val_t = k_margin()
|
||||
let j = 0
|
||||
while j < ids_n {
|
||||
let nid: String = get(ids, j)
|
||||
let sz: Map<String, Any> = el_map_get(result, "node_size_" + nid)
|
||||
let h: el_val_t = sz["h"]
|
||||
let cy: el_val_t = fadd(y_cursor, fdiv2(h))
|
||||
let pos: Map<String, Any> = { "x": x_center, "y": cy }
|
||||
let result = el_map_set(result, "node_pos_" + nid, pos)
|
||||
let y_cursor = fadd(fadd(y_cursor, h), k_v_gap())
|
||||
let j = j + 1
|
||||
}
|
||||
let cursor = fadd(fadd(cursor, col_w), k_h_gap())
|
||||
}
|
||||
} else {
|
||||
// Empty bucket — advance cursor by a default node size.
|
||||
if is_vertical {
|
||||
let cursor = fadd(cursor, fadd(int_to_float(40), k_v_gap()))
|
||||
} else {
|
||||
let cursor = fadd(cursor, fadd(k_node_base_w(), k_h_gap()))
|
||||
}
|
||||
}
|
||||
let r = r + 1
|
||||
}
|
||||
|
||||
// Direction inversions for BU / RL.
|
||||
let need_flip_y = false
|
||||
let need_flip_x = false
|
||||
if str_eq(direction, "bottom-up") { let need_flip_y = true }
|
||||
if str_eq(direction, "right-left") { let need_flip_x = true }
|
||||
|
||||
if need_flip_y {
|
||||
let max_y: el_val_t = fadd(fsub(cursor, k_v_gap()), k_margin())
|
||||
let i = 0
|
||||
while i < n {
|
||||
let nid: String = get(id_list, i)
|
||||
let pos: Map<String, Any> = el_map_get(result, "node_pos_" + nid)
|
||||
let y: el_val_t = pos["y"]
|
||||
let new_y: el_val_t = fadd(fsub(max_y, y), k_margin())
|
||||
let new_pos: Map<String, Any> = { "x": pos["x"], "y": new_y }
|
||||
let result = el_map_set(result, "node_pos_" + nid, new_pos)
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
if need_flip_x {
|
||||
let max_x: el_val_t = fadd(fsub(cursor, k_h_gap()), k_margin())
|
||||
let i = 0
|
||||
while i < n {
|
||||
let nid: String = get(id_list, i)
|
||||
let pos: Map<String, Any> = el_map_get(result, "node_pos_" + nid)
|
||||
let x: el_val_t = pos["x"]
|
||||
let new_x: el_val_t = fadd(fsub(max_x, x), k_margin())
|
||||
let new_pos: Map<String, Any> = { "x": new_x, "y": pos["y"] }
|
||||
let result = el_map_set(result, "node_pos_" + nid, new_pos)
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
|
||||
// Group bounds.
|
||||
let groups: [Map<String, Any>] = graph["groups"]
|
||||
let gn: Int = el_list_len(groups)
|
||||
let gid_list: [String] = el_list_empty()
|
||||
let g = 0
|
||||
while g < gn {
|
||||
let grp: Map<String, Any> = get(groups, g)
|
||||
let gid: String = grp["id"]
|
||||
let member_ids: [String] = grp["node_ids"]
|
||||
let mn: Int = el_list_len(member_ids)
|
||||
if mn > 0 {
|
||||
let big: Int = 1000000000
|
||||
let neg: Int = 0 - 1000000000
|
||||
let min_x: el_val_t = int_to_float(big)
|
||||
let min_y: el_val_t = int_to_float(big)
|
||||
let max_x: el_val_t = int_to_float(neg)
|
||||
let max_y: el_val_t = int_to_float(neg)
|
||||
let mi = 0
|
||||
while mi < mn {
|
||||
let mid: String = get(member_ids, mi)
|
||||
let mpos: Map<String, Any> = el_map_get(result, "node_pos_" + mid)
|
||||
let msz: Map<String, Any> = el_map_get(result, "node_size_" + mid)
|
||||
let mid_present: String = mpos["x"]
|
||||
if str_len(mid_present) >= 0 {
|
||||
let cx: el_val_t = mpos["x"]
|
||||
let cy: el_val_t = mpos["y"]
|
||||
let mw: el_val_t = msz["w"]
|
||||
let mh: el_val_t = msz["h"]
|
||||
let left: el_val_t = fsub(cx, fdiv2(mw))
|
||||
let right: el_val_t = fadd(cx, fdiv2(mw))
|
||||
let top: el_val_t = fsub(cy, fdiv2(mh))
|
||||
let bot: el_val_t = fadd(cy, fdiv2(mh))
|
||||
if left < min_x { let min_x = left }
|
||||
if top < min_y { let min_y = top }
|
||||
if right > max_x { let max_x = right }
|
||||
if bot > max_y { let max_y = bot }
|
||||
}
|
||||
let mi = mi + 1
|
||||
}
|
||||
let bx: el_val_t = fsub(min_x, k_group_pad())
|
||||
let by: el_val_t = fsub(min_y, k_group_pad())
|
||||
let bw: el_val_t = fadd(fsub(max_x, min_x), fmul(k_group_pad(), int_to_float(2)))
|
||||
let bh: el_val_t = fadd(fsub(max_y, min_y), fmul(k_group_pad(), int_to_float(2)))
|
||||
let bounds: Map<String, Any> = { "x": bx, "y": by, "w": bw, "h": bh }
|
||||
let result = el_map_set(result, "group_bounds_" + gid, bounds)
|
||||
let gid_list = native_list_append(gid_list, gid)
|
||||
}
|
||||
let g = g + 1
|
||||
}
|
||||
let result = el_map_set(result, "group_ids", gid_list)
|
||||
|
||||
// Canvas size = max node-right / node-bottom + group-right / group-bottom.
|
||||
let canvas_w: el_val_t = int_to_float(0)
|
||||
let canvas_h: el_val_t = int_to_float(0)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let nid: String = get(id_list, i)
|
||||
let pos: Map<String, Any> = el_map_get(result, "node_pos_" + nid)
|
||||
let sz: Map<String, Any> = el_map_get(result, "node_size_" + nid)
|
||||
let right: el_val_t = fadd(pos["x"], fdiv2(sz["w"]))
|
||||
let bottom: el_val_t = fadd(pos["y"], fdiv2(sz["h"]))
|
||||
if right > canvas_w { let canvas_w = right }
|
||||
if bottom > canvas_h { let canvas_h = bottom }
|
||||
let i = i + 1
|
||||
}
|
||||
let i = 0
|
||||
while i < el_list_len(gid_list) {
|
||||
let gid: String = get(gid_list, i)
|
||||
let b: Map<String, Any> = el_map_get(result, "group_bounds_" + gid)
|
||||
let r: el_val_t = fadd(b["x"], b["w"])
|
||||
let bt: el_val_t = fadd(b["y"], b["h"])
|
||||
if r > canvas_w { let canvas_w = r }
|
||||
if bt > canvas_h { let canvas_h = bt }
|
||||
let i = i + 1
|
||||
}
|
||||
let canvas: Map<String, Any> = {
|
||||
"w": fadd(canvas_w, k_margin()),
|
||||
"h": fadd(canvas_h, k_margin())
|
||||
}
|
||||
let result = el_map_set(result, "canvas", canvas)
|
||||
result
|
||||
}
|
||||
|
||||
// ── Smoke test ──────────────────────────────────────────────────────────────
|
||||
|
||||
fn fl_to_str(v: el_val_t) -> String {
|
||||
int_to_str(float_to_int(v))
|
||||
}
|
||||
|
||||
fn smoke_fail(label: String, msg: String) -> Int {
|
||||
println("FAIL " + label + ": " + msg)
|
||||
state_set("smoke_failures", "1")
|
||||
0
|
||||
}
|
||||
|
||||
fn make_test_node(id: String, label: String) -> Map<String, Any> {
|
||||
{
|
||||
"id": id, "label": label, "sublabel": "",
|
||||
"shape": "rectangle",
|
||||
"style_fill": "", "style_stroke": "", "style_color": ""
|
||||
}
|
||||
}
|
||||
|
||||
fn make_test_edge(src: String, dst: String) -> Map<String, Any> {
|
||||
{ "from": src, "to": dst, "label": "", "line": "solid", "arrow": "forward" }
|
||||
}
|
||||
|
||||
fn make_test_graph(direction: String, ids: [String], src_dst: [String]) -> Map<String, Any> {
|
||||
let nodes: [Map<String, Any>] = el_list_empty()
|
||||
let i = 0
|
||||
while i < el_list_len(ids) {
|
||||
let nid: String = get(ids, i)
|
||||
let nodes = native_list_append(nodes, make_test_node(nid, nid))
|
||||
let i = i + 1
|
||||
}
|
||||
let edges: [Map<String, Any>] = el_list_empty()
|
||||
let i = 0
|
||||
while i + 1 < el_list_len(src_dst) {
|
||||
let s: String = get(src_dst, i)
|
||||
let d: String = get(src_dst, i + 1)
|
||||
let edges = native_list_append(edges, make_test_edge(s, d))
|
||||
let i = i + 2
|
||||
}
|
||||
{
|
||||
"title": "T", "direction": direction,
|
||||
"nodes": nodes, "edges": edges, "groups": el_list_empty()
|
||||
}
|
||||
}
|
||||
|
||||
// Empty graph.
|
||||
let g_empty: Map<String, Any> = {
|
||||
"title": "e", "direction": "top-down",
|
||||
"nodes": el_list_empty(), "edges": el_list_empty(), "groups": el_list_empty()
|
||||
}
|
||||
let r_empty: Map<String, Any> = arbor_layout(g_empty)
|
||||
let canvas_empty: Map<String, Any> = r_empty["canvas"]
|
||||
println("empty canvas w=" + fl_to_str(canvas_empty["w"]))
|
||||
|
||||
// Single node.
|
||||
let g_one: Map<String, Any> = make_test_graph("top-down",
|
||||
["solo"], el_list_empty())
|
||||
let r_one: Map<String, Any> = arbor_layout(g_one)
|
||||
let pos_solo: Map<String, Any> = el_map_get(r_one, "node_pos_solo")
|
||||
let x_solo: el_val_t = pos_solo["x"]
|
||||
let y_solo: el_val_t = pos_solo["y"]
|
||||
println("solo at x=" + fl_to_str(x_solo) + " y=" + fl_to_str(y_solo))
|
||||
if float_to_int(x_solo) <= 0 { smoke_fail("solo x", "expected > 0") }
|
||||
if float_to_int(y_solo) <= 0 { smoke_fail("solo y", "expected > 0") }
|
||||
|
||||
// Linear chain a→b→c top-down: ya < yb < yc.
|
||||
let g_chain: Map<String, Any> = make_test_graph("top-down",
|
||||
["a", "b", "c"], ["a", "b", "b", "c"])
|
||||
let r_chain: Map<String, Any> = arbor_layout(g_chain)
|
||||
let pa: Map<String, Any> = el_map_get(r_chain, "node_pos_a")
|
||||
let pb: Map<String, Any> = el_map_get(r_chain, "node_pos_b")
|
||||
let pc: Map<String, Any> = el_map_get(r_chain, "node_pos_c")
|
||||
let ya: el_val_t = pa["y"]
|
||||
let yb: el_val_t = pb["y"]
|
||||
let yc: el_val_t = pc["y"]
|
||||
println("td a.y=" + fl_to_str(ya) + " b.y=" + fl_to_str(yb) + " c.y=" + fl_to_str(yc))
|
||||
if float_to_int(ya) >= float_to_int(yb) { smoke_fail("td order", "a.y >= b.y") }
|
||||
if float_to_int(yb) >= float_to_int(yc) { smoke_fail("td order", "b.y >= c.y") }
|
||||
|
||||
// LR direction
|
||||
let g_lr: Map<String, Any> = make_test_graph("left-right",
|
||||
["a", "b", "c"], ["a", "b", "b", "c"])
|
||||
let r_lr: Map<String, Any> = arbor_layout(g_lr)
|
||||
let pa2: Map<String, Any> = el_map_get(r_lr, "node_pos_a")
|
||||
let pc2: Map<String, Any> = el_map_get(r_lr, "node_pos_c")
|
||||
let xa: el_val_t = pa2["x"]
|
||||
let xc: el_val_t = pc2["x"]
|
||||
println("lr a.x=" + fl_to_str(xa) + " c.x=" + fl_to_str(xc))
|
||||
if float_to_int(xa) >= float_to_int(xc) { smoke_fail("lr order", "a.x >= c.x") }
|
||||
|
||||
// Bottom-up: a is below c.
|
||||
let g_bu: Map<String, Any> = make_test_graph("bottom-up",
|
||||
["a", "b", "c"], ["a", "b", "b", "c"])
|
||||
let r_bu: Map<String, Any> = arbor_layout(g_bu)
|
||||
let pa3: Map<String, Any> = el_map_get(r_bu, "node_pos_a")
|
||||
let pc3: Map<String, Any> = el_map_get(r_bu, "node_pos_c")
|
||||
let ya3: el_val_t = pa3["y"]
|
||||
let yc3: el_val_t = pc3["y"]
|
||||
println("bu a.y=" + fl_to_str(ya3) + " c.y=" + fl_to_str(yc3))
|
||||
if float_to_int(ya3) <= float_to_int(yc3) { smoke_fail("bu order", "a.y <= c.y") }
|
||||
|
||||
// Canvas covers all nodes.
|
||||
let canvas_chain: Map<String, Any> = r_chain["canvas"]
|
||||
let cw: el_val_t = canvas_chain["w"]
|
||||
let ch: el_val_t = canvas_chain["h"]
|
||||
println("chain canvas w=" + fl_to_str(cw) + " h=" + fl_to_str(ch))
|
||||
if float_to_int(cw) <= 0 { smoke_fail("canvas w", "non-positive") }
|
||||
if float_to_int(ch) <= 0 { smoke_fail("canvas h", "non-positive") }
|
||||
|
||||
println("")
|
||||
let f: String = state_get("smoke_failures")
|
||||
if str_eq(f, "1") {
|
||||
println("arbor-layout: FAILED")
|
||||
exit_program(1)
|
||||
} else {
|
||||
println("arbor-layout: ok")
|
||||
}
|
||||
@@ -1,19 +0,0 @@
|
||||
// arbor-parse — hand-written recursive-descent parser for the .arbor source
|
||||
// language. Produces an Arbor graph value consumable by arbor-layout and
|
||||
// arbor-render.
|
||||
|
||||
vessel "arbor-parse" {
|
||||
version "0.1.0"
|
||||
description "Recursive-descent parser for the .arbor diagram language"
|
||||
authors ["Neuron Technologies"]
|
||||
edition "2026"
|
||||
}
|
||||
|
||||
dependencies {
|
||||
arbor-core "0.1"
|
||||
}
|
||||
|
||||
build {
|
||||
entry "src/main.el"
|
||||
output "dist/"
|
||||
}
|
||||
@@ -1,763 +0,0 @@
|
||||
// arbor-parse — recursive-descent parser for the .arbor source language.
|
||||
//
|
||||
// This vessel inlines a private copy of the small set of arbor-core helpers
|
||||
// it needs (sanitize_id and constructors). El's import form today is purely
|
||||
// syntactic concatenation, so each vessel that wants to be its own buildable
|
||||
// unit carries its own copy of these helpers. They're tiny (well under 100
|
||||
// lines) and the duplication keeps each vessel hermetic.
|
||||
//
|
||||
// Public entry point: fn arbor_parse(source: String) -> Map<String, Any>
|
||||
//
|
||||
// Returns either a graph value or a parse-error map. Callers test for the
|
||||
// "error" field:
|
||||
// { "error": "..." , "line": Int, "text": "...source line..." } on failure
|
||||
// { "title", "direction", "nodes", "edges", "groups" } on success
|
||||
|
||||
// ── Sanitisation (copy of arbor-core's sanitize_id) ──────────────────────────
|
||||
|
||||
fn is_alnum_underscore(ch: String) -> Bool {
|
||||
let code: Int = str_char_code(ch, 0)
|
||||
if code >= 48 {
|
||||
if code <= 57 { return true }
|
||||
}
|
||||
if code >= 65 {
|
||||
if code <= 90 { return true }
|
||||
}
|
||||
if code >= 97 {
|
||||
if code <= 122 { return true }
|
||||
}
|
||||
if code == 95 { return true }
|
||||
false
|
||||
}
|
||||
|
||||
fn is_ascii_digit(ch: String) -> Bool {
|
||||
let code: Int = str_char_code(ch, 0)
|
||||
if code >= 48 {
|
||||
if code <= 57 { return true }
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
fn sanitize_id(s: String) -> String {
|
||||
let n: Int = str_len(s)
|
||||
if n == 0 { return "node" }
|
||||
|
||||
let out = ""
|
||||
let prev_underscore = false
|
||||
let i = 0
|
||||
while i < n {
|
||||
let ch: String = str_char_at(s, i)
|
||||
if is_alnum_underscore(ch) {
|
||||
let out = out + ch
|
||||
let prev_underscore = false
|
||||
} else {
|
||||
if !prev_underscore {
|
||||
let out = out + "_"
|
||||
}
|
||||
let prev_underscore = true
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
let m: Int = str_len(out)
|
||||
let end = m
|
||||
let stripping = true
|
||||
while stripping {
|
||||
if end <= 0 {
|
||||
let stripping = false
|
||||
} else {
|
||||
let last: String = str_char_at(out, end - 1)
|
||||
if last == "_" {
|
||||
let end = end - 1
|
||||
} else {
|
||||
let stripping = false
|
||||
}
|
||||
}
|
||||
}
|
||||
let out = str_slice(out, 0, end)
|
||||
|
||||
if str_len(out) == 0 { return "node" }
|
||||
|
||||
let first: String = str_char_at(out, 0)
|
||||
if is_ascii_digit(first) {
|
||||
let out = "n" + out
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
fn shape_from_token(tok: String) -> String {
|
||||
let t: String = str_trim(tok)
|
||||
if t == "rect" { return "rect" }
|
||||
if t == "rounded" { return "rounded" }
|
||||
if t == "cylinder" { return "cylinder" }
|
||||
if t == "diamond" { return "diamond" }
|
||||
if t == "stadium" { return "stadium" }
|
||||
if t == "primary" { return "primary" }
|
||||
""
|
||||
}
|
||||
|
||||
// ── Line preprocessing ──────────────────────────────────────────────────────
|
||||
//
|
||||
// Strip inline `// ...` comments, trim, drop empties. Returns a list of maps
|
||||
// { "no": Int, "text": String }.
|
||||
|
||||
fn preprocess(source: String) -> [Map<String, Any>] {
|
||||
let lines: [String] = str_split(source, "\n")
|
||||
let n: Int = el_list_len(lines)
|
||||
let out: [Map<String, Any>] = el_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let raw: String = get(lines, i)
|
||||
let cidx: Int = str_index_of(raw, "//")
|
||||
let stripped = raw
|
||||
if cidx >= 0 {
|
||||
let stripped = str_slice(raw, 0, cidx)
|
||||
}
|
||||
let trimmed: String = str_trim(stripped)
|
||||
if str_len(trimmed) > 0 {
|
||||
let row: Map<String, Any> = { "no": i + 1, "text": trimmed }
|
||||
let out = native_list_append(out, row)
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
// ── Quoted-string extraction ────────────────────────────────────────────────
|
||||
//
|
||||
// Parses `"text"`-prefix from a string. Returns `{ "ok": Bool, "value": Str,
|
||||
// "rest": Str }`. The `rest` field carries everything after the closing quote
|
||||
// (so the caller can continue tokenising).
|
||||
|
||||
fn parse_quoted(s: String) -> Map<String, Any> {
|
||||
let t: String = str_trim(s)
|
||||
if str_len(t) < 2 {
|
||||
return { "ok": false, "value": "", "rest": s }
|
||||
}
|
||||
let first: String = str_char_at(t, 0)
|
||||
if first != "\"" {
|
||||
return { "ok": false, "value": "", "rest": s }
|
||||
}
|
||||
let body: String = str_slice(t, 1, str_len(t))
|
||||
let close: Int = str_index_of(body, "\"")
|
||||
if close < 0 {
|
||||
return { "ok": false, "value": "", "rest": s }
|
||||
}
|
||||
let inner: String = str_slice(body, 0, close)
|
||||
let rest: String = str_slice(body, close + 1, str_len(body))
|
||||
{ "ok": true, "value": inner, "rest": rest }
|
||||
}
|
||||
|
||||
// ── Identifier prefix split ─────────────────────────────────────────────────
|
||||
//
|
||||
// `split_identifier("foo bar")` → { "id": "foo", "rest": " bar" }.
|
||||
// `split_identifier("a-b")` → { "id": "a", "rest": "-b" }.
|
||||
|
||||
fn split_identifier(s: String) -> Map<String, Any> {
|
||||
let n: Int = str_len(s)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let ch: String = str_char_at(s, i)
|
||||
if !is_alnum_underscore(ch) {
|
||||
return { "id": str_slice(s, 0, i), "rest": str_slice(s, i, n) }
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
{ "id": s, "rest": "" }
|
||||
}
|
||||
|
||||
// ── Direction parsing ───────────────────────────────────────────────────────
|
||||
|
||||
fn parse_direction(s: String) -> String {
|
||||
let t: String = str_trim(s)
|
||||
if t == "top-down" { return "top-down" }
|
||||
if t == "TD" { return "top-down" }
|
||||
if t == "left-right" { return "left-right" }
|
||||
if t == "LR" { return "left-right" }
|
||||
if t == "right-left" { return "right-left" }
|
||||
if t == "RL" { return "right-left" }
|
||||
if t == "bottom-up" { return "bottom-up" }
|
||||
if t == "BU" { return "bottom-up" }
|
||||
""
|
||||
}
|
||||
|
||||
// ── Edge-arrow detection ────────────────────────────────────────────────────
|
||||
//
|
||||
// Detects the longest matching arrow token in a line, returning
|
||||
// { "ok": Bool, "from_str": Str, "kind": Str, "rest": Str }
|
||||
|
||||
fn extract_edge_parts(line: String) -> Map<String, Any> {
|
||||
// Order: longest first to avoid partial matches.
|
||||
let f1: Int = str_index_of(line, "-/->")
|
||||
if f1 >= 0 {
|
||||
return { "ok": true,
|
||||
"from_str": str_slice(line, 0, f1),
|
||||
"kind": "forbidden",
|
||||
"rest": str_slice(line, f1 + 4, str_len(line)) }
|
||||
}
|
||||
let f2: Int = str_index_of(line, "<->")
|
||||
if f2 >= 0 {
|
||||
return { "ok": true,
|
||||
"from_str": str_slice(line, 0, f2),
|
||||
"kind": "bidirectional",
|
||||
"rest": str_slice(line, f2 + 3, str_len(line)) }
|
||||
}
|
||||
let f3: Int = str_index_of(line, "-->")
|
||||
if f3 >= 0 {
|
||||
return { "ok": true,
|
||||
"from_str": str_slice(line, 0, f3),
|
||||
"kind": "dashed",
|
||||
"rest": str_slice(line, f3 + 3, str_len(line)) }
|
||||
}
|
||||
let f4: Int = str_index_of(line, "->")
|
||||
if f4 >= 0 {
|
||||
return { "ok": true,
|
||||
"from_str": str_slice(line, 0, f4),
|
||||
"kind": "solid",
|
||||
"rest": str_slice(line, f4 + 2, str_len(line)) }
|
||||
}
|
||||
{ "ok": false, "from_str": "", "kind": "", "rest": "" }
|
||||
}
|
||||
|
||||
fn is_edge_line(line: String) -> Bool {
|
||||
if str_contains(line, "->") { return true }
|
||||
if str_contains(line, "<->") { return true }
|
||||
false
|
||||
}
|
||||
|
||||
// ── Error helpers ───────────────────────────────────────────────────────────
|
||||
|
||||
fn make_error(line_no: Int, line_text: String, message: String) -> Map<String, Any> {
|
||||
{ "error": message, "line": line_no, "text": line_text }
|
||||
}
|
||||
|
||||
// ── Parse driver ────────────────────────────────────────────────────────────
|
||||
//
|
||||
// State is held in process-local k/v rather than threaded through every
|
||||
// function. Specifically:
|
||||
// "title", "direction" — graph header
|
||||
// "nodes_json", "edges_json", "groups_json" — accumulators (string lists)
|
||||
// "group_stack_depth" — "0".."N" — open groups
|
||||
// "group_stack_<i>_id" / "_label" / "_line" — frame data
|
||||
// "group_stack_<i>_node_ids" — JSON array of ids inside frame
|
||||
// "error" — non-empty if parse failed
|
||||
// "error_line", "error_text" — context
|
||||
|
||||
fn st_set_int(key: String, v: Int) -> Int { state_set(key, int_to_str(v)); 0 }
|
||||
fn st_get_int(key: String) -> Int {
|
||||
let s: String = state_get(key)
|
||||
if str_eq(s, "") { return 0 }
|
||||
str_to_int(s)
|
||||
}
|
||||
|
||||
// Encode/decode small string lists via "" delimiter (unit separator).
|
||||
fn list_encode(xs: [String]) -> String {
|
||||
let n: Int = el_list_len(xs)
|
||||
let out = ""
|
||||
let i = 0
|
||||
while i < n {
|
||||
if i > 0 { let out = out + "" }
|
||||
let out = out + get(xs, i)
|
||||
let i = i + 1
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
fn list_decode(s: String) -> [String] {
|
||||
if str_eq(s, "") { return el_list_empty() }
|
||||
str_split(s, "")
|
||||
}
|
||||
|
||||
fn current_group_index() -> Int {
|
||||
st_get_int("group_stack_depth") - 1
|
||||
}
|
||||
|
||||
fn group_frame_key(idx: Int, suffix: String) -> String {
|
||||
"gs_" + int_to_str(idx) + "_" + suffix
|
||||
}
|
||||
|
||||
fn open_group(id: String, label: String, line_no: Int) -> Int {
|
||||
let depth: Int = st_get_int("group_stack_depth")
|
||||
state_set(group_frame_key(depth, "id"), id)
|
||||
state_set(group_frame_key(depth, "label"), label)
|
||||
state_set(group_frame_key(depth, "line"), int_to_str(line_no))
|
||||
state_set(group_frame_key(depth, "ids"), "")
|
||||
st_set_int("group_stack_depth", depth + 1)
|
||||
0
|
||||
}
|
||||
|
||||
fn close_group_frame() -> Map<String, Any> {
|
||||
let depth: Int = st_get_int("group_stack_depth")
|
||||
if depth <= 0 {
|
||||
return { "ok": false, "id": "", "label": "", "ids": "" }
|
||||
}
|
||||
let idx: Int = depth - 1
|
||||
let id: String = state_get(group_frame_key(idx, "id"))
|
||||
let label: String = state_get(group_frame_key(idx, "label"))
|
||||
let ids: String = state_get(group_frame_key(idx, "ids"))
|
||||
state_del(group_frame_key(idx, "id"))
|
||||
state_del(group_frame_key(idx, "label"))
|
||||
state_del(group_frame_key(idx, "line"))
|
||||
state_del(group_frame_key(idx, "ids"))
|
||||
st_set_int("group_stack_depth", idx)
|
||||
{ "ok": true, "id": id, "label": label, "ids": ids }
|
||||
}
|
||||
|
||||
fn register_node_in_group(node_id: String) -> Int {
|
||||
let depth: Int = st_get_int("group_stack_depth")
|
||||
if depth <= 0 { return 0 }
|
||||
let idx: Int = depth - 1
|
||||
let key: String = group_frame_key(idx, "ids")
|
||||
let prev: String = state_get(key)
|
||||
if str_eq(prev, "") {
|
||||
state_set(key, node_id)
|
||||
} else {
|
||||
state_set(key, prev + "" + node_id)
|
||||
}
|
||||
0
|
||||
}
|
||||
|
||||
// Accumulator JSON-ish encoding for nodes/edges/groups.
|
||||
// We render each entry as a small string and stash in state under a counter.
|
||||
|
||||
fn store_node(id: String, label: String, shape: String) -> Int {
|
||||
let n: Int = st_get_int("node_count")
|
||||
state_set("node_id_" + int_to_str(n), id)
|
||||
state_set("node_label_" + int_to_str(n), label)
|
||||
state_set("node_shape_" + int_to_str(n), shape)
|
||||
st_set_int("node_count", n + 1)
|
||||
0
|
||||
}
|
||||
|
||||
fn store_edge(src: String, dst: String, label: String, kind: String) -> Int {
|
||||
let n: Int = st_get_int("edge_count")
|
||||
state_set("edge_from_" + int_to_str(n), src)
|
||||
state_set("edge_to_" + int_to_str(n), dst)
|
||||
state_set("edge_label_" + int_to_str(n), label)
|
||||
state_set("edge_kind_" + int_to_str(n), kind)
|
||||
st_set_int("edge_count", n + 1)
|
||||
0
|
||||
}
|
||||
|
||||
fn store_group(id: String, label: String, ids: String) -> Int {
|
||||
let n: Int = st_get_int("group_count")
|
||||
state_set("group_id_" + int_to_str(n), id)
|
||||
state_set("group_label_" + int_to_str(n), label)
|
||||
state_set("group_ids_" + int_to_str(n), ids)
|
||||
st_set_int("group_count", n + 1)
|
||||
0
|
||||
}
|
||||
|
||||
fn set_error(msg: String, line_no: Int, line_text: String) -> Int {
|
||||
state_set("parse_error", msg)
|
||||
st_set_int("parse_error_line", line_no)
|
||||
state_set("parse_error_text", line_text)
|
||||
0
|
||||
}
|
||||
|
||||
fn has_error() -> Bool {
|
||||
let m: String = state_get("parse_error")
|
||||
if str_eq(m, "") { return false }
|
||||
true
|
||||
}
|
||||
|
||||
// Reset state at the start of each parse pass.
|
||||
fn reset_state() -> Int {
|
||||
state_set("graph_title", "")
|
||||
state_set("graph_direction", "top-down")
|
||||
st_set_int("node_count", 0)
|
||||
st_set_int("edge_count", 0)
|
||||
st_set_int("group_count", 0)
|
||||
st_set_int("group_stack_depth", 0)
|
||||
state_set("parse_error", "")
|
||||
st_set_int("parse_error_line", 0)
|
||||
state_set("parse_error_text", "")
|
||||
0
|
||||
}
|
||||
|
||||
// ── Statement-level parsing ─────────────────────────────────────────────────
|
||||
|
||||
fn parse_node_stmt(line_no: Int, line: String) -> Int {
|
||||
let id_split: Map<String, Any> = split_identifier(line)
|
||||
let raw_id: String = id_split["id"]
|
||||
if str_eq(raw_id, "") {
|
||||
set_error("expected node id, edge, or keyword", line_no, line)
|
||||
return 0
|
||||
}
|
||||
let id: String = sanitize_id(raw_id)
|
||||
let rest: String = str_trim(id_split["rest"])
|
||||
|
||||
// Optional shape: [token]
|
||||
let shape = "rect"
|
||||
let after_shape = rest
|
||||
if str_len(rest) > 0 {
|
||||
let lead: String = str_char_at(rest, 0)
|
||||
if lead == "[" {
|
||||
let close: Int = str_index_of(rest, "]")
|
||||
if close < 0 {
|
||||
set_error("unclosed `[` in shape token", line_no, line)
|
||||
return 0
|
||||
}
|
||||
let token: String = str_slice(rest, 1, close)
|
||||
let parsed_shape: String = shape_from_token(token)
|
||||
if str_eq(parsed_shape, "") {
|
||||
set_error("unknown shape `" + token + "`", line_no, line)
|
||||
return 0
|
||||
}
|
||||
let shape = parsed_shape
|
||||
let after_shape = str_trim(str_slice(rest, close + 1, str_len(rest)))
|
||||
}
|
||||
}
|
||||
|
||||
// Optional quoted label.
|
||||
let quoted: Map<String, Any> = parse_quoted(after_shape)
|
||||
let label = raw_id
|
||||
let ok: Bool = quoted["ok"]
|
||||
if ok {
|
||||
let label = quoted["value"]
|
||||
}
|
||||
|
||||
store_node(id, label, shape)
|
||||
register_node_in_group(id)
|
||||
1
|
||||
}
|
||||
|
||||
fn parse_edge_stmt(line_no: Int, line: String) -> Int {
|
||||
let parts: Map<String, Any> = extract_edge_parts(line)
|
||||
let ok: Bool = parts["ok"]
|
||||
if !ok {
|
||||
set_error("malformed edge — expected `->` `-->` `<->` or `-/->`", line_no, line)
|
||||
return 0
|
||||
}
|
||||
let from_str: String = parts["from_str"]
|
||||
let rest_str: String = parts["rest"]
|
||||
let kind: String = parts["kind"]
|
||||
|
||||
let src: String = sanitize_id(str_trim(from_str))
|
||||
let rest_t: String = str_trim(rest_str)
|
||||
|
||||
let id_split: Map<String, Any> = split_identifier(rest_t)
|
||||
let to_raw: String = id_split["id"]
|
||||
if str_eq(to_raw, "") {
|
||||
set_error("edge missing target node id", line_no, line)
|
||||
return 0
|
||||
}
|
||||
let dst: String = sanitize_id(to_raw)
|
||||
|
||||
let label_rest: String = str_trim(id_split["rest"])
|
||||
let quoted: Map<String, Any> = parse_quoted(label_rest)
|
||||
let label = ""
|
||||
let qok: Bool = quoted["ok"]
|
||||
if qok {
|
||||
let label = quoted["value"]
|
||||
}
|
||||
store_edge(src, dst, label, kind)
|
||||
1
|
||||
}
|
||||
|
||||
fn parse_group_open(line_no: Int, line: String, rest: String) -> Int {
|
||||
// Strip trailing `{`.
|
||||
let trimmed: String = str_trim(rest)
|
||||
let n: Int = str_len(trimmed)
|
||||
let body = trimmed
|
||||
if n > 0 {
|
||||
let last: String = str_char_at(trimmed, n - 1)
|
||||
if last == "{" {
|
||||
let body = str_trim(str_slice(trimmed, 0, n - 1))
|
||||
}
|
||||
}
|
||||
|
||||
let id_split: Map<String, Any> = split_identifier(body)
|
||||
let raw_id: String = id_split["id"]
|
||||
if str_eq(raw_id, "") {
|
||||
set_error("group declaration missing id", line_no, line)
|
||||
return 0
|
||||
}
|
||||
let label_rest: String = str_trim(id_split["rest"])
|
||||
let quoted: Map<String, Any> = parse_quoted(label_rest)
|
||||
let label = raw_id
|
||||
let qok: Bool = quoted["ok"]
|
||||
if qok {
|
||||
let label = quoted["value"]
|
||||
}
|
||||
open_group(raw_id, label, line_no)
|
||||
1
|
||||
}
|
||||
|
||||
fn parse_close_brace(line_no: Int) -> Int {
|
||||
let frame: Map<String, Any> = close_group_frame()
|
||||
let frame_ok: Bool = frame["ok"]
|
||||
if !frame_ok {
|
||||
set_error("unexpected `}` — no open group", line_no, "}")
|
||||
return 0
|
||||
}
|
||||
store_group(frame["id"], frame["label"], frame["ids"])
|
||||
1
|
||||
}
|
||||
|
||||
fn parse_line_dispatch(line_no: Int, line: String) -> Int {
|
||||
if line == "}" { return parse_close_brace(line_no) }
|
||||
|
||||
if str_starts_with(line, "title:") {
|
||||
let after: String = str_trim(str_slice(line, 6, str_len(line)))
|
||||
let q: Map<String, Any> = parse_quoted(after)
|
||||
let qok: Bool = q["ok"]
|
||||
if !qok {
|
||||
set_error("expected quoted string after `title:`", line_no, line)
|
||||
return 0
|
||||
}
|
||||
state_set("graph_title", q["value"])
|
||||
return 1
|
||||
}
|
||||
|
||||
if str_starts_with(line, "direction:") {
|
||||
let after: String = str_trim(str_slice(line, 10, str_len(line)))
|
||||
let dir: String = parse_direction(after)
|
||||
if str_eq(dir, "") {
|
||||
set_error("unknown direction — expected top-down, left-right, right-left, or bottom-up",
|
||||
line_no, line)
|
||||
return 0
|
||||
}
|
||||
state_set("graph_direction", dir)
|
||||
return 1
|
||||
}
|
||||
|
||||
if str_starts_with(line, "group ") {
|
||||
let after: String = str_slice(line, 6, str_len(line))
|
||||
return parse_group_open(line_no, line, after)
|
||||
}
|
||||
|
||||
if is_edge_line(line) {
|
||||
return parse_edge_stmt(line_no, line)
|
||||
}
|
||||
|
||||
parse_node_stmt(line_no, line)
|
||||
}
|
||||
|
||||
// ── Materialise accumulators into the final graph map ───────────────────────
|
||||
|
||||
fn build_graph_value() -> Map<String, Any> {
|
||||
let n_nodes: Int = st_get_int("node_count")
|
||||
let nodes: [Map<String, Any>] = el_list_empty()
|
||||
let i = 0
|
||||
while i < n_nodes {
|
||||
let s: String = int_to_str(i)
|
||||
let node: Map<String, Any> = {
|
||||
"id": state_get("node_id_" + s),
|
||||
"label": state_get("node_label_" + s),
|
||||
"shape": state_get("node_shape_" + s)
|
||||
}
|
||||
let nodes = native_list_append(nodes, node)
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
let n_edges: Int = st_get_int("edge_count")
|
||||
let edges: [Map<String, Any>] = el_list_empty()
|
||||
let i = 0
|
||||
while i < n_edges {
|
||||
let s: String = int_to_str(i)
|
||||
let edge: Map<String, Any> = {
|
||||
"from": state_get("edge_from_" + s),
|
||||
"to": state_get("edge_to_" + s),
|
||||
"label": state_get("edge_label_" + s),
|
||||
"kind": state_get("edge_kind_" + s)
|
||||
}
|
||||
let edges = native_list_append(edges, edge)
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
let n_groups: Int = st_get_int("group_count")
|
||||
let groups: [Map<String, Any>] = el_list_empty()
|
||||
let i = 0
|
||||
while i < n_groups {
|
||||
let s: String = int_to_str(i)
|
||||
let raw_ids: String = state_get("group_ids_" + s)
|
||||
let id_list: [String] = list_decode(raw_ids)
|
||||
let group: Map<String, Any> = {
|
||||
"id": state_get("group_id_" + s),
|
||||
"label": state_get("group_label_" + s),
|
||||
"node_ids": id_list,
|
||||
"direction": ""
|
||||
}
|
||||
let groups = native_list_append(groups, group)
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
{
|
||||
"title": state_get("graph_title"),
|
||||
"direction": state_get("graph_direction"),
|
||||
"nodes": nodes,
|
||||
"edges": edges,
|
||||
"groups": groups
|
||||
}
|
||||
}
|
||||
|
||||
// ── Public entry point ──────────────────────────────────────────────────────
|
||||
|
||||
fn arbor_parse(source: String) -> Map<String, Any> {
|
||||
reset_state()
|
||||
let lines: [Map<String, Any>] = preprocess(source)
|
||||
let n: Int = el_list_len(lines)
|
||||
let i = 0
|
||||
let abort = false
|
||||
while i < n {
|
||||
if abort {
|
||||
// skip — error already recorded
|
||||
} else {
|
||||
let row: Map<String, Any> = get(lines, i)
|
||||
let line_no: Int = row["no"]
|
||||
let text: String = row["text"]
|
||||
parse_line_dispatch(line_no, text)
|
||||
if has_error() {
|
||||
let abort = true
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
if !has_error() {
|
||||
let depth: Int = st_get_int("group_stack_depth")
|
||||
if depth > 0 {
|
||||
let idx: Int = depth - 1
|
||||
let id: String = state_get(group_frame_key(idx, "id"))
|
||||
let line_no: Int = st_get_int(group_frame_key(idx, "line"))
|
||||
set_error("unclosed group '" + id + "' — missing closing `}`",
|
||||
line_no, "group " + id)
|
||||
}
|
||||
}
|
||||
if has_error() {
|
||||
return {
|
||||
"error": state_get("parse_error"),
|
||||
"line": st_get_int("parse_error_line"),
|
||||
"text": state_get("parse_error_text")
|
||||
}
|
||||
}
|
||||
build_graph_value()
|
||||
}
|
||||
|
||||
// ── Smoke test ──────────────────────────────────────────────────────────────
|
||||
|
||||
fn fail_msg(label: String, got: String, want: String) -> Int {
|
||||
println("FAIL " + label + " got=[" + got + "] want=[" + want + "]")
|
||||
state_set("smoke_failures", "1")
|
||||
0
|
||||
}
|
||||
|
||||
fn check_eq(label: String, got: String, want: String) -> Int {
|
||||
if got == want {
|
||||
println("ok " + label)
|
||||
return 1
|
||||
}
|
||||
fail_msg(label, got, want)
|
||||
}
|
||||
|
||||
// Helper: a graph map is in the error state iff it has a non-empty "error".
|
||||
fn parse_failed(g: Map<String, Any>) -> Bool {
|
||||
let m: String = g["error"]
|
||||
if str_eq(m, "") { return false }
|
||||
// map_get returns NULL for missing keys; str_eq treats two NULLs as equal
|
||||
// and NULL vs "" as not equal — guard explicitly.
|
||||
if str_len(m) == 0 { return false }
|
||||
true
|
||||
}
|
||||
|
||||
let src1 = "title: \"Test\"\ndirection: left-right\n\napi [rounded] \"REST API\"\ndb [cylinder] \"Postgres\"\n\napi -> db \"reads\""
|
||||
let g1: Map<String, Any> = arbor_parse(src1)
|
||||
if parse_failed(g1) {
|
||||
println("FAIL parse 1: " + g1["error"])
|
||||
state_set("smoke_failures", "1")
|
||||
}
|
||||
check_eq("title parsed", g1["title"], "Test")
|
||||
check_eq("direction parsed", g1["direction"], "left-right")
|
||||
let nodes1: [Map<String, Any>] = g1["nodes"]
|
||||
let nn1: Int = el_list_len(nodes1)
|
||||
check_eq("two nodes", int_to_str(nn1), "2")
|
||||
let edges1: [Map<String, Any>] = g1["edges"]
|
||||
let ne1: Int = el_list_len(edges1)
|
||||
check_eq("one edge", int_to_str(ne1), "1")
|
||||
let e0: Map<String, Any> = get(edges1, 0)
|
||||
check_eq("edge from", e0["from"], "api")
|
||||
check_eq("edge to", e0["to"], "db")
|
||||
check_eq("edge label", e0["label"], "reads")
|
||||
check_eq("edge kind", e0["kind"], "solid")
|
||||
let n0: Map<String, Any> = get(nodes1, 0)
|
||||
check_eq("node 0 shape", n0["shape"], "rounded")
|
||||
check_eq("node 0 label", n0["label"], "REST API")
|
||||
|
||||
// Test edge varieties
|
||||
let src2 = "a \"A\"\nb \"B\"\na -> b\na --> b\na -/-> b\na <-> b"
|
||||
let g2: Map<String, Any> = arbor_parse(src2)
|
||||
let edges2: [Map<String, Any>] = g2["edges"]
|
||||
check_eq("4 edges parsed", int_to_str(el_list_len(edges2)), "4")
|
||||
let kinds = ""
|
||||
let i = 0
|
||||
while i < el_list_len(edges2) {
|
||||
let e: Map<String, Any> = get(edges2, i)
|
||||
let k: String = e["kind"]
|
||||
let kinds = kinds + k + ","
|
||||
let i = i + 1
|
||||
}
|
||||
check_eq("edge kinds", kinds, "solid,dashed,forbidden,bidirectional,")
|
||||
|
||||
// Groups
|
||||
let src3 = "group core \"Application Core\" {\n api [rounded] \"REST API\"\n svc \"Business Logic\"\n}\nstandalone \"Out\""
|
||||
let g3: Map<String, Any> = arbor_parse(src3)
|
||||
let groups3: [Map<String, Any>] = g3["groups"]
|
||||
check_eq("one group", int_to_str(el_list_len(groups3)), "1")
|
||||
let grp0: Map<String, Any> = get(groups3, 0)
|
||||
check_eq("group label", grp0["label"], "Application Core")
|
||||
let gnids: [String] = grp0["node_ids"]
|
||||
check_eq("group has 2 members", int_to_str(el_list_len(gnids)), "2")
|
||||
let nodes3: [Map<String, Any>] = g3["nodes"]
|
||||
check_eq("3 total nodes (incl standalone)",
|
||||
int_to_str(el_list_len(nodes3)), "3")
|
||||
|
||||
// Error: unknown shape
|
||||
let src4 = "node [hexagon] \"X\""
|
||||
let g4: Map<String, Any> = arbor_parse(src4)
|
||||
let err4: String = g4["error"]
|
||||
if str_eq(err4, "") {
|
||||
println("FAIL expected error for unknown shape")
|
||||
state_set("smoke_failures", "1")
|
||||
} else {
|
||||
if str_contains(err4, "hexagon") {
|
||||
println("ok error mentions hexagon: " + err4)
|
||||
} else {
|
||||
println("FAIL error wording: " + err4)
|
||||
state_set("smoke_failures", "1")
|
||||
}
|
||||
}
|
||||
|
||||
// Error: unclosed group
|
||||
let src5 = "group g \"G\" {\n a \"A\"\n"
|
||||
let g5: Map<String, Any> = arbor_parse(src5)
|
||||
let err5: String = g5["error"]
|
||||
if str_eq(err5, "") {
|
||||
println("FAIL expected unclosed-group error")
|
||||
state_set("smoke_failures", "1")
|
||||
} else {
|
||||
if str_contains(err5, "unclosed") {
|
||||
println("ok unclosed group detected")
|
||||
} else {
|
||||
println("FAIL unclosed error wording: " + err5)
|
||||
state_set("smoke_failures", "1")
|
||||
}
|
||||
}
|
||||
|
||||
// Comments and inline comments
|
||||
let src6 = "// header\na \"A\" // trailing\nb \"B\""
|
||||
let g6: Map<String, Any> = arbor_parse(src6)
|
||||
check_eq("comments stripped", int_to_str(el_list_len(g6["nodes"])), "2")
|
||||
|
||||
// Empty input
|
||||
let g7: Map<String, Any> = arbor_parse("")
|
||||
check_eq("empty graph nodes", int_to_str(el_list_len(g7["nodes"])), "0")
|
||||
check_eq("empty graph default direction", g7["direction"], "top-down")
|
||||
|
||||
println("")
|
||||
let f: String = state_get("smoke_failures")
|
||||
if str_eq(f, "1") {
|
||||
println("arbor-parse: FAILED")
|
||||
exit_program(1)
|
||||
} else {
|
||||
println("arbor-parse: ok")
|
||||
}
|
||||
@@ -1,21 +0,0 @@
|
||||
// arbor-render — SVG renderer. Consumes a diagram graph + layout result and
|
||||
// emits an SVG document. PNG rasterization is not provided in this vessel
|
||||
// because the El runtime does not expose a vector-to-raster primitive yet
|
||||
// (see report).
|
||||
|
||||
vessel "arbor-render" {
|
||||
version "0.1.0"
|
||||
description "SVG renderer for Arbor diagrams"
|
||||
authors ["Neuron Technologies"]
|
||||
edition "2026"
|
||||
}
|
||||
|
||||
dependencies {
|
||||
arbor-core "0.1"
|
||||
arbor-layout "0.1"
|
||||
}
|
||||
|
||||
build {
|
||||
entry "src/main.el"
|
||||
output "dist/"
|
||||
}
|
||||
@@ -1,575 +0,0 @@
|
||||
// arbor-render — SVG emission from a laid-out diagram.
|
||||
//
|
||||
// Entry point:
|
||||
// fn arbor_render_svg(graph: Map, layout: Map, forbidden: [String]) -> String
|
||||
//
|
||||
// The graph is the lowered (diagram-form) shape produced by arbor-core /
|
||||
// arbor-diagram (`title`, `direction`, `nodes`, `edges`, `groups`). The
|
||||
// layout is whatever arbor-layout returned: `node_pos_<id>`, `node_size_<id>`,
|
||||
// `group_bounds_<id>`, `node_ids`, `group_ids`, `canvas`.
|
||||
//
|
||||
// `forbidden` is a list of "from->to" key strings — same format as
|
||||
// arbor-core's collect_forbidden(). The Rust crate threaded a HashSet
|
||||
// through; El threads a list and we linear-scan.
|
||||
//
|
||||
// SVG is text emission — straightforward El. Every float coordinate is
|
||||
// passed through format_float(_, 1) for stable output.
|
||||
//
|
||||
// ── PNG render is intentionally out of scope ────────────────────────────────
|
||||
// The Rust crate rasterises via resvg → tiny_skia → png. The El runtime
|
||||
// today exposes no equivalent: there is no resvg, no usvg, no font rasterer,
|
||||
// no PNG encoder, no path-fill code. fs_write writes text only — there is
|
||||
// no binary write primitive. arbor_render_png() returns an error map in El
|
||||
// until the runtime grows a rasterer (see "runtime gaps" in the report).
|
||||
|
||||
// ── Colour palette (matches the Rust constants exactly) ────────────────────
|
||||
|
||||
fn col_node_fill() -> String { "#ffffff" }
|
||||
fn col_node_stroke() -> String { "#334155" }
|
||||
fn col_primary_fill() -> String { "#0052A0" }
|
||||
fn col_primary_text() -> String { "#ffffff" }
|
||||
fn col_node_text() -> String { "#0D0D14" }
|
||||
fn col_edge() -> String { "#64748B" }
|
||||
fn col_edge_forbidden() -> String { "#DC2626" }
|
||||
fn col_group_fill() -> String { "rgba(0,0,0,0.03)" }
|
||||
fn col_group_stroke() -> String { "#CBD5E1" }
|
||||
fn col_group_text() -> String { "#64748B" }
|
||||
fn col_edge_label() -> String { "#64748B" }
|
||||
|
||||
// ── XML escape ─────────────────────────────────────────────────────────────
|
||||
|
||||
fn esc(s: String) -> String {
|
||||
let r1: String = str_replace(s, "&", "&")
|
||||
let r2: String = str_replace(r1, "<", "<")
|
||||
let r3: String = str_replace(r2, ">", ">")
|
||||
let r4: String = str_replace(r3, "\"", """)
|
||||
r4
|
||||
}
|
||||
|
||||
// Float to "%.1f" — the Rust pt() helper.
|
||||
fn pt(v: el_val_t) -> String {
|
||||
format_float(v, 1)
|
||||
}
|
||||
|
||||
// Float arithmetic helpers — float_to_int / int_to_float trip through Int,
|
||||
// which is exact for the integer-valued floats used by the layout pass.
|
||||
fn fadd(a: el_val_t, b: el_val_t) -> el_val_t {
|
||||
let ai: Int = float_to_int(a)
|
||||
let bi: Int = float_to_int(b)
|
||||
int_to_float(ai + bi)
|
||||
}
|
||||
|
||||
fn fsub(a: el_val_t, b: el_val_t) -> el_val_t {
|
||||
let ai: Int = float_to_int(a)
|
||||
let bi: Int = float_to_int(b)
|
||||
int_to_float(ai - bi)
|
||||
}
|
||||
|
||||
fn fdiv2(a: el_val_t) -> el_val_t {
|
||||
let ai: Int = float_to_int(a)
|
||||
int_to_float(ai / 2)
|
||||
}
|
||||
|
||||
fn fmid(a: el_val_t, b: el_val_t) -> el_val_t {
|
||||
fdiv2(fadd(a, b))
|
||||
}
|
||||
|
||||
// ── forbidden-edge linear lookup ───────────────────────────────────────────
|
||||
|
||||
fn forbidden_key(from: String, to: String) -> String {
|
||||
from + "->" + to
|
||||
}
|
||||
|
||||
fn forbidden_contains(set: [String], src: String, dst: String) -> Bool {
|
||||
let key: String = forbidden_key(src, dst)
|
||||
let n: Int = el_list_len(set)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let s: String = get(set, i)
|
||||
if str_eq(s, key) { return true }
|
||||
let i = i + 1
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
// ── Arrow marker defs ──────────────────────────────────────────────────────
|
||||
|
||||
fn arrow_defs() -> String {
|
||||
let s = "\n <marker id=\"ah\" markerWidth=\"10\" markerHeight=\"7\" refX=\"9\" refY=\"3.5\" orient=\"auto\">\n"
|
||||
let s = s + " <polygon points=\"0 0, 10 3.5, 0 7\" fill=\"" + col_edge() + "\"/>\n"
|
||||
let s = s + " </marker>\n"
|
||||
let s = s + " <marker id=\"ah-bi\" markerWidth=\"10\" markerHeight=\"7\" refX=\"1\" refY=\"3.5\" orient=\"auto-start-reverse\">\n"
|
||||
let s = s + " <polygon points=\"0 0, 10 3.5, 0 7\" fill=\"" + col_edge() + "\"/>\n"
|
||||
let s = s + " </marker>\n"
|
||||
let s = s + " <marker id=\"ah-red\" markerWidth=\"10\" markerHeight=\"7\" refX=\"9\" refY=\"3.5\" orient=\"auto\">\n"
|
||||
let s = s + " <polygon points=\"0 0, 10 3.5, 0 7\" fill=\"" + col_edge_forbidden() + "\"/>\n"
|
||||
let s = s + " </marker>"
|
||||
s
|
||||
}
|
||||
|
||||
// ── Node rendering ─────────────────────────────────────────────────────────
|
||||
|
||||
fn render_node(buf: String, node: Map<String, Any>, layout: Map<String, Any>) -> String {
|
||||
let nid: String = node["id"]
|
||||
let pos: Map<String, Any> = el_map_get(layout, "node_pos_" + nid)
|
||||
let sz: Map<String, Any> = el_map_get(layout, "node_size_" + nid)
|
||||
|
||||
let cx: el_val_t = pos["x"]
|
||||
let cy: el_val_t = pos["y"]
|
||||
let w: el_val_t = sz["w"]
|
||||
let h: el_val_t = sz["h"]
|
||||
|
||||
let x: el_val_t = fsub(cx, fdiv2(w))
|
||||
let y: el_val_t = fsub(cy, fdiv2(h))
|
||||
|
||||
let fill_in: String = node["style_fill"]
|
||||
let stroke_in: String = node["style_stroke"]
|
||||
let color_in: String = node["style_color"]
|
||||
let fill = col_node_fill()
|
||||
if str_len(fill_in) > 0 { let fill = fill_in }
|
||||
let stroke = col_node_stroke()
|
||||
if str_len(stroke_in) > 0 { let stroke = stroke_in }
|
||||
let text_col = col_node_text()
|
||||
if str_len(color_in) > 0 { let text_col = color_in }
|
||||
|
||||
let shape: String = node["shape"]
|
||||
let buf = buf
|
||||
|
||||
if str_eq(shape, "rectangle") {
|
||||
let buf = buf + " <rect x=\"" + pt(x) + "\" y=\"" + pt(y)
|
||||
let buf = buf + "\" width=\"" + pt(w) + "\" height=\"" + pt(h)
|
||||
let buf = buf + "\" rx=\"4\" fill=\"" + fill + "\" stroke=\"" + stroke
|
||||
let buf = buf + "\" stroke-width=\"1.5\"/>\n"
|
||||
}
|
||||
if str_eq(shape, "rounded_rect") {
|
||||
let buf = buf + " <rect x=\"" + pt(x) + "\" y=\"" + pt(y)
|
||||
let buf = buf + "\" width=\"" + pt(w) + "\" height=\"" + pt(h)
|
||||
let buf = buf + "\" rx=\"20\" fill=\"" + fill + "\" stroke=\"" + stroke
|
||||
let buf = buf + "\" stroke-width=\"1.5\"/>\n"
|
||||
}
|
||||
if str_eq(shape, "stadium") {
|
||||
let buf = buf + " <rect x=\"" + pt(x) + "\" y=\"" + pt(y)
|
||||
let buf = buf + "\" width=\"" + pt(w) + "\" height=\"" + pt(h)
|
||||
let buf = buf + "\" rx=\"" + pt(fdiv2(h)) + "\" fill=\"" + fill
|
||||
let buf = buf + "\" stroke=\"" + stroke + "\" stroke-width=\"1.5\"/>\n"
|
||||
}
|
||||
if str_eq(shape, "cylinder") {
|
||||
// body: rect from y+ry to bottom; ry ≈ h/6 (Rust uses h*0.18, we use h/6
|
||||
// to stay in integer arithmetic — visually indistinguishable on the
|
||||
// canvas sizes the layout produces).
|
||||
let hi: Int = float_to_int(h)
|
||||
let ry: el_val_t = int_to_float(hi / 6)
|
||||
let body_y: el_val_t = fadd(y, ry)
|
||||
let body_h: el_val_t = fsub(h, ry)
|
||||
let buf = buf + " <rect x=\"" + pt(x) + "\" y=\"" + pt(body_y)
|
||||
let buf = buf + "\" width=\"" + pt(w) + "\" height=\"" + pt(body_h)
|
||||
let buf = buf + "\" fill=\"" + fill + "\" stroke=\"" + stroke + "\" stroke-width=\"1.5\"/>\n"
|
||||
// top ellipse
|
||||
let buf = buf + " <ellipse cx=\"" + pt(cx) + "\" cy=\"" + pt(body_y)
|
||||
let buf = buf + "\" rx=\"" + pt(fdiv2(w)) + "\" ry=\"" + pt(ry)
|
||||
let buf = buf + "\" fill=\"" + fill + "\" stroke=\"" + stroke + "\" stroke-width=\"1.5\"/>\n"
|
||||
// bottom ellipse
|
||||
let bot_y: el_val_t = fadd(y, h)
|
||||
let buf = buf + " <ellipse cx=\"" + pt(cx) + "\" cy=\"" + pt(bot_y)
|
||||
let buf = buf + "\" rx=\"" + pt(fdiv2(w)) + "\" ry=\"" + pt(ry)
|
||||
let buf = buf + "\" fill=\"" + fill + "\" stroke=\"" + stroke + "\" stroke-width=\"1.5\"/>\n"
|
||||
}
|
||||
if str_eq(shape, "diamond") {
|
||||
let hw: el_val_t = fdiv2(w)
|
||||
let hh: el_val_t = fdiv2(h)
|
||||
let buf = buf + " <polygon points=\""
|
||||
let buf = buf + pt(cx) + "," + pt(fsub(cy, hh)) + " "
|
||||
let buf = buf + pt(fadd(cx, hw)) + "," + pt(cy) + " "
|
||||
let buf = buf + pt(cx) + "," + pt(fadd(cy, hh)) + " "
|
||||
let buf = buf + pt(fsub(cx, hw)) + "," + pt(cy)
|
||||
let buf = buf + "\" fill=\"" + fill + "\" stroke=\"" + stroke + "\" stroke-width=\"1.5\"/>\n"
|
||||
}
|
||||
|
||||
// Label.
|
||||
let label: String = node["label"]
|
||||
let buf = buf + " <text x=\"" + pt(cx) + "\" y=\"" + pt(cy)
|
||||
let buf = buf + "\" text-anchor=\"middle\" dominant-baseline=\"middle\""
|
||||
let buf = buf + " class=\"arbor-node-label\" fill=\"" + text_col + "\">"
|
||||
let buf = buf + esc(label) + "</text>\n"
|
||||
|
||||
// Sublabel — Rust's DiagramNode stores Option<String>; El uses "" sentinel.
|
||||
let sub: String = node["sublabel"]
|
||||
if str_len(sub) > 0 {
|
||||
let sub_y: el_val_t = fadd(cy, int_to_float(14))
|
||||
let buf = buf + " <text x=\"" + pt(cx) + "\" y=\"" + pt(sub_y)
|
||||
let buf = buf + "\" text-anchor=\"middle\" dominant-baseline=\"middle\""
|
||||
let buf = buf + " class=\"arbor-node-label\" fill=\"" + text_col + "\" font-size=\"10\">"
|
||||
let buf = buf + esc(sub) + "</text>\n"
|
||||
}
|
||||
buf
|
||||
}
|
||||
|
||||
// ── Edge rendering ─────────────────────────────────────────────────────────
|
||||
//
|
||||
// We emit a straight line from one node centre to the other and let the
|
||||
// browser draw it; the Rust crate renders cubic bezier paths but the runtime
|
||||
// has no robust math layer, and the rectangles are large enough that
|
||||
// straight edges read clearly. (See "runtime gaps".)
|
||||
|
||||
fn render_edge(buf: String, edge: Map<String, Any>, layout: Map<String, Any>, forbidden: [String]) -> String {
|
||||
let from_id: String = edge["from"]
|
||||
let to_id: String = edge["to"]
|
||||
let from_pos: Map<String, Any> = el_map_get(layout, "node_pos_" + from_id)
|
||||
let to_pos: Map<String, Any> = el_map_get(layout, "node_pos_" + to_id)
|
||||
|
||||
let fx: el_val_t = from_pos["x"]
|
||||
let fy: el_val_t = from_pos["y"]
|
||||
let tx: el_val_t = to_pos["x"]
|
||||
let ty: el_val_t = to_pos["y"]
|
||||
|
||||
let is_forbidden: Bool = forbidden_contains(forbidden, from_id, to_id)
|
||||
let stroke = col_edge()
|
||||
if is_forbidden { let stroke = col_edge_forbidden() }
|
||||
|
||||
let line: String = edge["line"]
|
||||
let arrow: String = edge["arrow"]
|
||||
let dash_attr = ""
|
||||
if str_eq(line, "dashed") { let dash_attr = " stroke-dasharray=\"5,3\"" }
|
||||
if str_eq(line, "dotted") { let dash_attr = " stroke-dasharray=\"2,2\"" }
|
||||
|
||||
let marker_start = ""
|
||||
if str_eq(arrow, "both") { let marker_start = " marker-start=\"url(#ah-bi)\"" }
|
||||
if str_eq(arrow, "backward") { let marker_start = " marker-start=\"url(#ah-bi)\"" }
|
||||
|
||||
let marker_end = " marker-end=\"url(#ah)\""
|
||||
if is_forbidden { let marker_end = " marker-end=\"url(#ah-red)\"" }
|
||||
if str_eq(arrow, "none") { let marker_end = "" }
|
||||
if str_eq(arrow, "backward") { let marker_end = "" }
|
||||
|
||||
let buf = buf + " <line x1=\"" + pt(fx) + "\" y1=\"" + pt(fy)
|
||||
let buf = buf + "\" x2=\"" + pt(tx) + "\" y2=\"" + pt(ty)
|
||||
let buf = buf + "\" stroke=\"" + stroke + "\" stroke-width=\"1.5\""
|
||||
let buf = buf + dash_attr + marker_start + marker_end + "/>\n"
|
||||
|
||||
// Forbidden marker — circle-X at midpoint.
|
||||
if is_forbidden {
|
||||
let mx: el_val_t = fmid(fx, tx)
|
||||
let my: el_val_t = fmid(fy, ty)
|
||||
let r: el_val_t = int_to_float(7)
|
||||
let buf = buf + " <circle cx=\"" + pt(mx) + "\" cy=\"" + pt(my)
|
||||
let buf = buf + "\" r=\"" + pt(r) + "\" fill=\"white\" stroke=\""
|
||||
let buf = buf + col_edge_forbidden() + "\" stroke-width=\"1.5\"/>\n"
|
||||
let off: el_val_t = int_to_float(4)
|
||||
let buf = buf + " <line x1=\"" + pt(fsub(mx, off)) + "\" y1=\"" + pt(fsub(my, off))
|
||||
let buf = buf + "\" x2=\"" + pt(fadd(mx, off)) + "\" y2=\"" + pt(fadd(my, off))
|
||||
let buf = buf + "\" stroke=\"" + col_edge_forbidden() + "\" stroke-width=\"1.5\"/>\n"
|
||||
let buf = buf + " <line x1=\"" + pt(fadd(mx, off)) + "\" y1=\"" + pt(fsub(my, off))
|
||||
let buf = buf + "\" x2=\"" + pt(fsub(mx, off)) + "\" y2=\"" + pt(fadd(my, off))
|
||||
let buf = buf + "\" stroke=\"" + col_edge_forbidden() + "\" stroke-width=\"1.5\"/>\n"
|
||||
}
|
||||
|
||||
// Edge label
|
||||
let label: String = edge["label"]
|
||||
if str_len(label) > 0 {
|
||||
let mx: el_val_t = fmid(fx, tx)
|
||||
let my: el_val_t = fmid(fy, ty)
|
||||
let lw: el_val_t = int_to_float(str_len(label) * 7 + 8)
|
||||
let lh: el_val_t = int_to_float(16)
|
||||
let buf = buf + " <rect x=\"" + pt(fsub(mx, fdiv2(lw))) + "\" y=\"" + pt(fsub(my, fdiv2(lh)))
|
||||
let buf = buf + "\" width=\"" + pt(lw) + "\" height=\"" + pt(lh)
|
||||
let buf = buf + "\" rx=\"3\" fill=\"white\" opacity=\"0.85\"/>\n"
|
||||
let buf = buf + " <text x=\"" + pt(mx) + "\" y=\"" + pt(my)
|
||||
let buf = buf + "\" text-anchor=\"middle\" dominant-baseline=\"middle\""
|
||||
let buf = buf + " class=\"arbor-edge-label\">" + esc(label) + "</text>\n"
|
||||
}
|
||||
buf
|
||||
}
|
||||
|
||||
// ── Group rendering ────────────────────────────────────────────────────────
|
||||
|
||||
fn render_group(buf: String, group: Map<String, Any>, layout: Map<String, Any>) -> String {
|
||||
let gid: String = group["id"]
|
||||
let bounds: Map<String, Any> = el_map_get(layout, "group_bounds_" + gid)
|
||||
// Layout may not have bounds for empty groups — defensive.
|
||||
let bx_check: el_val_t = bounds["x"]
|
||||
if float_to_int(bx_check) == 0 {
|
||||
// Could be a real 0; cheaper to skip via presence check on group_ids.
|
||||
}
|
||||
let bx: el_val_t = bounds["x"]
|
||||
let by: el_val_t = bounds["y"]
|
||||
let bw: el_val_t = bounds["w"]
|
||||
let bh: el_val_t = bounds["h"]
|
||||
let buf = buf + " <rect x=\"" + pt(bx) + "\" y=\"" + pt(by)
|
||||
let buf = buf + "\" width=\"" + pt(bw) + "\" height=\"" + pt(bh)
|
||||
let buf = buf + "\" rx=\"8\" fill=\"" + col_group_fill() + "\" stroke=\""
|
||||
let buf = buf + col_group_stroke() + "\" stroke-width=\"1\" stroke-dasharray=\"4,3\"/>\n"
|
||||
|
||||
// Group label in the top-left corner.
|
||||
let lx: el_val_t = fadd(bx, int_to_float(8))
|
||||
let ly: el_val_t = fadd(by, int_to_float(14))
|
||||
let label: String = group["label"]
|
||||
let buf = buf + " <text x=\"" + pt(lx) + "\" y=\"" + pt(ly)
|
||||
let buf = buf + "\" class=\"arbor-group-label\">" + esc(label) + "</text>\n"
|
||||
buf
|
||||
}
|
||||
|
||||
// ── Public entry point ─────────────────────────────────────────────────────
|
||||
|
||||
fn arbor_render_svg(graph: Map<String, Any>, layout: Map<String, Any>, forbidden: [String]) -> String {
|
||||
let canvas: Map<String, Any> = el_map_get(layout, "canvas")
|
||||
let cw: el_val_t = canvas["w"]
|
||||
let ch: el_val_t = canvas["h"]
|
||||
|
||||
let buf = "<svg xmlns=\"http://www.w3.org/2000/svg\" width=\"" + pt(cw)
|
||||
let buf = buf + "\" height=\"" + pt(ch) + "\" viewBox=\"0 0 " + pt(cw) + " " + pt(ch) + "\">\n"
|
||||
let buf = buf + " <defs>"
|
||||
let buf = buf + arrow_defs()
|
||||
let buf = buf + "\n <style>\n"
|
||||
let buf = buf + " .arbor-node-label { font-family: 'Helvetica Neue', Helvetica, Arial, sans-serif; font-size: 13px; }\n"
|
||||
let buf = buf + " .arbor-group-label { font-family: 'Helvetica Neue', Helvetica, Arial, monospace; font-size: 10px; fill: " + col_group_text() + "; letter-spacing: 0.08em; }\n"
|
||||
let buf = buf + " .arbor-edge-label { font-family: 'Helvetica Neue', Helvetica, Arial, sans-serif; font-size: 11px; fill: " + col_edge_label() + "; }\n"
|
||||
let buf = buf + " </style>\n"
|
||||
let buf = buf + " </defs>\n"
|
||||
|
||||
// Groups first (behind everything).
|
||||
let buf = buf + " <!-- Groups -->\n"
|
||||
let groups: [Map<String, Any>] = graph["groups"]
|
||||
let gn: Int = el_list_len(groups)
|
||||
let i = 0
|
||||
while i < gn {
|
||||
let g: Map<String, Any> = get(groups, i)
|
||||
let gid: String = g["id"]
|
||||
// Only render groups the layout actually placed.
|
||||
let gids: [String] = el_map_get(layout, "group_ids")
|
||||
let placed = false
|
||||
let j = 0
|
||||
while j < el_list_len(gids) {
|
||||
if str_eq(get(gids, j), gid) { let placed = true }
|
||||
let j = j + 1
|
||||
}
|
||||
if placed {
|
||||
let buf = render_group(buf, g, layout)
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Edges
|
||||
let buf = buf + " <!-- Edges -->\n"
|
||||
let edges: [Map<String, Any>] = graph["edges"]
|
||||
let en: Int = el_list_len(edges)
|
||||
let i = 0
|
||||
while i < en {
|
||||
let e: Map<String, Any> = get(edges, i)
|
||||
let buf = render_edge(buf, e, layout, forbidden)
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Nodes
|
||||
let buf = buf + " <!-- Nodes -->\n"
|
||||
let nodes: [Map<String, Any>] = graph["nodes"]
|
||||
let nn: Int = el_list_len(nodes)
|
||||
let i = 0
|
||||
while i < nn {
|
||||
let n: Map<String, Any> = get(nodes, i)
|
||||
let buf = render_node(buf, n, layout)
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Title
|
||||
let title: String = graph["title"]
|
||||
if str_len(title) > 0 {
|
||||
let title_x: el_val_t = fdiv2(cw)
|
||||
let buf = buf + " <text x=\"" + pt(title_x) + "\" y=\"22\" text-anchor=\"middle\""
|
||||
let buf = buf + " font-family=\"'Helvetica Neue', Helvetica, Arial, sans-serif\""
|
||||
let buf = buf + " font-size=\"15\" font-weight=\"600\" fill=\"" + col_node_text() + "\">"
|
||||
let buf = buf + esc(title) + "</text>\n"
|
||||
}
|
||||
|
||||
let buf = buf + "</svg>\n"
|
||||
buf
|
||||
}
|
||||
|
||||
// PNG — not implemented; the runtime has no SVG rasterizer or PNG encoder.
|
||||
// Returns an error map that callers can inspect via map["error"].
|
||||
fn arbor_render_png(graph: Map<String, Any>, layout: Map<String, Any>, forbidden: [String]) -> Map<String, Any> {
|
||||
{
|
||||
"error": "PNG rasterization not available in El runtime — install a runtime image library or use the Rust binary"
|
||||
}
|
||||
}
|
||||
|
||||
// ── Smoke test ─────────────────────────────────────────────────────────────
|
||||
|
||||
fn fail(label: String, msg: String) -> Int {
|
||||
println("FAIL " + label + ": " + msg)
|
||||
state_set("smoke_failures", "1")
|
||||
0
|
||||
}
|
||||
|
||||
fn check_contains(label: String, haystack: String, needle: String) -> Int {
|
||||
if str_contains(haystack, needle) {
|
||||
println("ok " + label)
|
||||
return 1
|
||||
}
|
||||
fail(label, "missing [" + needle + "]")
|
||||
}
|
||||
|
||||
fn check_not_contains(label: String, haystack: String, needle: String) -> Int {
|
||||
if str_contains(haystack, needle) {
|
||||
return fail(label, "should not contain [" + needle + "]")
|
||||
}
|
||||
println("ok " + label)
|
||||
1
|
||||
}
|
||||
|
||||
fn make_test_node(id: String, label: String, shape: String) -> Map<String, Any> {
|
||||
{
|
||||
"id": id, "label": label, "sublabel": "",
|
||||
"shape": shape,
|
||||
"style_fill": "", "style_stroke": "", "style_color": ""
|
||||
}
|
||||
}
|
||||
|
||||
fn make_test_edge(src: String, dst: String, line: String, arrow: String, label: String) -> Map<String, Any> {
|
||||
{
|
||||
"from": src, "to": dst, "label": label,
|
||||
"line": line, "arrow": arrow
|
||||
}
|
||||
}
|
||||
|
||||
fn make_test_pos(x: Int, y: Int) -> Map<String, Any> {
|
||||
{ "x": int_to_float(x), "y": int_to_float(y) }
|
||||
}
|
||||
|
||||
fn make_test_size(w: Int, h: Int) -> Map<String, Any> {
|
||||
{ "w": int_to_float(w), "h": int_to_float(h) }
|
||||
}
|
||||
|
||||
// Build a minimal layout map by hand.
|
||||
fn build_layout(node_ids: [String], group_ids: [String], cw: Int, ch: Int) -> Map<String, Any> {
|
||||
let r: Map<String, Any> = el_map_new(0)
|
||||
let r = el_map_set(r, "node_ids", node_ids)
|
||||
let r = el_map_set(r, "group_ids", group_ids)
|
||||
let r = el_map_set(r, "canvas", { "w": int_to_float(cw), "h": int_to_float(ch) })
|
||||
r
|
||||
}
|
||||
|
||||
let n_a: Map<String, Any> = make_test_node("a", "Node A", "rectangle")
|
||||
let n_b: Map<String, Any> = make_test_node("b", "Node B", "rectangle")
|
||||
let e_ab: Map<String, Any> = make_test_edge("a", "b", "solid", "forward", "")
|
||||
|
||||
let nodes: [Map<String, Any>] = native_list_empty()
|
||||
let nodes = native_list_append(nodes, n_a)
|
||||
let nodes = native_list_append(nodes, n_b)
|
||||
let edges: [Map<String, Any>] = native_list_empty()
|
||||
let edges = native_list_append(edges, e_ab)
|
||||
let groups: [Map<String, Any>] = native_list_empty()
|
||||
|
||||
let g: Map<String, Any> = {
|
||||
"title": "Test", "direction": "top-down",
|
||||
"nodes": nodes, "edges": edges, "groups": groups
|
||||
}
|
||||
|
||||
let nid_list: [String] = native_list_empty()
|
||||
let nid_list = native_list_append(nid_list, "a")
|
||||
let nid_list = native_list_append(nid_list, "b")
|
||||
let gid_list: [String] = native_list_empty()
|
||||
let layout: Map<String, Any> = build_layout(nid_list, gid_list, 400, 300)
|
||||
let layout = el_map_set(layout, "node_pos_a", make_test_pos(100, 60))
|
||||
let layout = el_map_set(layout, "node_pos_b", make_test_pos(100, 200))
|
||||
let layout = el_map_set(layout, "node_size_a", make_test_size(120, 40))
|
||||
let layout = el_map_set(layout, "node_size_b", make_test_size(120, 40))
|
||||
|
||||
let forbidden: [String] = native_list_empty()
|
||||
let svg: String = arbor_render_svg(g, layout, forbidden)
|
||||
|
||||
check_contains("svg starts with <svg", svg, "<svg xmlns=")
|
||||
check_contains("svg ends with </svg>", svg, "</svg>")
|
||||
check_contains("svg contains node label", svg, "Node A")
|
||||
check_contains("svg contains title", svg, ">Test</text>")
|
||||
check_contains("svg has rect for rectangle node", svg, "<rect")
|
||||
check_contains("svg has line for edge", svg, "<line")
|
||||
check_contains("svg has arrow marker def", svg, "id=\"ah\"")
|
||||
|
||||
// Escape test
|
||||
let n_esc: Map<String, Any> = make_test_node("x", "A & B <C>", "rectangle")
|
||||
let nodes2: [Map<String, Any>] = native_list_empty()
|
||||
let nodes2 = native_list_append(nodes2, n_esc)
|
||||
let g2: Map<String, Any> = {
|
||||
"title": "Test <Title>", "direction": "top-down",
|
||||
"nodes": nodes2, "edges": native_list_empty(), "groups": native_list_empty()
|
||||
}
|
||||
let nid2: [String] = native_list_empty()
|
||||
let nid2 = native_list_append(nid2, "x")
|
||||
let layout2: Map<String, Any> = build_layout(nid2, native_list_empty(), 200, 100)
|
||||
let layout2 = el_map_set(layout2, "node_pos_x", make_test_pos(80, 40))
|
||||
let layout2 = el_map_set(layout2, "node_size_x", make_test_size(120, 40))
|
||||
let svg2: String = arbor_render_svg(g2, layout2, native_list_empty())
|
||||
check_contains("escapes ampersand", svg2, "&")
|
||||
check_contains("escapes <", svg2, "<")
|
||||
check_not_contains("no raw <C>", svg2, "<C>")
|
||||
|
||||
// Forbidden edge
|
||||
let e_fb: Map<String, Any> = make_test_edge("a", "b", "solid", "forward", "")
|
||||
let edges3: [Map<String, Any>] = native_list_empty()
|
||||
let edges3 = native_list_append(edges3, e_fb)
|
||||
let g3: Map<String, Any> = {
|
||||
"title": "F", "direction": "top-down",
|
||||
"nodes": nodes, "edges": edges3, "groups": native_list_empty()
|
||||
}
|
||||
let fb: [String] = native_list_empty()
|
||||
let fb = native_list_append(fb, forbidden_key("a", "b"))
|
||||
let svg3: String = arbor_render_svg(g3, layout, fb)
|
||||
check_contains("forbidden uses red marker", svg3, "ah-red")
|
||||
check_contains("forbidden colour present", svg3, col_edge_forbidden())
|
||||
|
||||
// Diamond shape → polygon
|
||||
let n_d: Map<String, Any> = make_test_node("d", "Decide", "diamond")
|
||||
let g4: Map<String, Any> = {
|
||||
"title": "", "direction": "top-down",
|
||||
"nodes": native_list_append(native_list_empty(), n_d),
|
||||
"edges": native_list_empty(), "groups": native_list_empty()
|
||||
}
|
||||
let nid4: [String] = native_list_append(native_list_empty(), "d")
|
||||
let layout4: Map<String, Any> = build_layout(nid4, native_list_empty(), 200, 100)
|
||||
let layout4 = el_map_set(layout4, "node_pos_d", make_test_pos(80, 50))
|
||||
let layout4 = el_map_set(layout4, "node_size_d", make_test_size(120, 40))
|
||||
let svg4: String = arbor_render_svg(g4, layout4, native_list_empty())
|
||||
check_contains("diamond uses polygon", svg4, "<polygon")
|
||||
|
||||
// Cylinder shape → ellipses
|
||||
let n_cy: Map<String, Any> = make_test_node("cy", "DB", "cylinder")
|
||||
let g5: Map<String, Any> = {
|
||||
"title": "", "direction": "top-down",
|
||||
"nodes": native_list_append(native_list_empty(), n_cy),
|
||||
"edges": native_list_empty(), "groups": native_list_empty()
|
||||
}
|
||||
let nid5: [String] = native_list_append(native_list_empty(), "cy")
|
||||
let layout5: Map<String, Any> = build_layout(nid5, native_list_empty(), 200, 100)
|
||||
let layout5 = el_map_set(layout5, "node_pos_cy", make_test_pos(80, 50))
|
||||
let layout5 = el_map_set(layout5, "node_size_cy", make_test_size(120, 40))
|
||||
let svg5: String = arbor_render_svg(g5, layout5, native_list_empty())
|
||||
check_contains("cylinder uses ellipse", svg5, "<ellipse")
|
||||
|
||||
// Dashed edge
|
||||
let e_dash: Map<String, Any> = make_test_edge("a", "b", "dashed", "forward", "")
|
||||
let g6: Map<String, Any> = {
|
||||
"title": "", "direction": "top-down",
|
||||
"nodes": nodes, "edges": native_list_append(native_list_empty(), e_dash),
|
||||
"groups": native_list_empty()
|
||||
}
|
||||
let svg6: String = arbor_render_svg(g6, layout, native_list_empty())
|
||||
check_contains("dashed line dasharray", svg6, "stroke-dasharray=\"5,3\"")
|
||||
|
||||
// PNG returns an error map
|
||||
let png: Map<String, Any> = arbor_render_png(g, layout, native_list_empty())
|
||||
let err: String = png["error"]
|
||||
if str_len(err) > 0 {
|
||||
println("ok PNG returns error map")
|
||||
} else {
|
||||
println("FAIL PNG should have returned error")
|
||||
state_set("smoke_failures", "1")
|
||||
}
|
||||
|
||||
println("")
|
||||
let f: String = state_get("smoke_failures")
|
||||
if str_eq(f, "1") {
|
||||
println("arbor-render: FAILED")
|
||||
exit_program(1)
|
||||
} else {
|
||||
println("arbor-render: ok")
|
||||
}
|
||||
Vendored
+764
-2226
File diff suppressed because it is too large
Load Diff
BIN
Binary file not shown.
BIN
Binary file not shown.
+437
-35
@@ -129,6 +129,9 @@ el_val_t js_str_lit(el_val_t s);
|
||||
el_val_t js_emit_line(el_val_t line);
|
||||
el_val_t js_emit_blank(void);
|
||||
el_val_t js_binop(el_val_t op);
|
||||
el_val_t js_is_async_builtin(el_val_t name);
|
||||
el_val_t js_register_async_fn(el_val_t name);
|
||||
el_val_t js_is_async_fn(el_val_t name);
|
||||
el_val_t js_is_int_name(el_val_t name);
|
||||
el_val_t js_add_int_name(el_val_t name);
|
||||
el_val_t js_build_int_names_for_params(el_val_t params);
|
||||
@@ -149,17 +152,32 @@ el_val_t js_cg_fn(el_val_t stmt);
|
||||
el_val_t js_is_fndef(el_val_t stmt);
|
||||
el_val_t js_is_top_level_decl(el_val_t stmt);
|
||||
el_val_t codegen_js(el_val_t stmts, el_val_t source);
|
||||
el_val_t codegen_js_bundle(el_val_t stmts, el_val_t source, el_val_t runtime_content);
|
||||
el_val_t codegen_js_inner(el_val_t stmts, el_val_t source, el_val_t bundle_mode, el_val_t runtime_content);
|
||||
el_val_t js_strip_es_exports(el_val_t content);
|
||||
el_val_t compile(el_val_t source);
|
||||
el_val_t compile_js(el_val_t source);
|
||||
el_val_t compile_js_with_bundle(el_val_t source, el_val_t runtime_path);
|
||||
el_val_t compile_dispatch(el_val_t tgt, el_val_t source);
|
||||
el_val_t compile_dispatch_bundle(el_val_t tgt, el_val_t source, el_val_t runtime_path);
|
||||
el_val_t detect_target(el_val_t argv);
|
||||
el_val_t strip_flags(el_val_t argv);
|
||||
el_val_t detect_emit_header(el_val_t argv);
|
||||
el_val_t detect_bundle(el_val_t argv);
|
||||
el_val_t detect_minify(el_val_t argv);
|
||||
el_val_t detect_obfuscate(el_val_t argv);
|
||||
el_val_t make_temp_path(el_val_t suffix);
|
||||
el_val_t js_reserved_names(void);
|
||||
el_val_t find_node_tool(el_val_t tool_name, el_val_t src_dir);
|
||||
el_val_t apply_minify(el_val_t js_path, el_val_t out_path, el_val_t src_dir);
|
||||
el_val_t apply_obfuscate(el_val_t js_path, el_val_t out_path, el_val_t src_dir);
|
||||
el_val_t resolve_runtime_path(el_val_t src_path);
|
||||
el_val_t type_node_to_el(el_val_t t);
|
||||
el_val_t emit_header(el_val_t stmts, el_val_t hdr_path);
|
||||
el_val_t dirname_of(el_val_t path);
|
||||
el_val_t parse_import_line(el_val_t trimmed, el_val_t dir);
|
||||
el_val_t resolve_imports(el_val_t src_path);
|
||||
el_val_t run_with_postprocess(el_val_t tgt, el_val_t source, el_val_t src_path, el_val_t do_bundle, el_val_t do_obfuscate, el_val_t argc, el_val_t positional);
|
||||
|
||||
el_val_t lex_is_digit(el_val_t ch) {
|
||||
if (str_eq(ch, EL_STR("0"))) {
|
||||
@@ -1474,6 +1492,11 @@ el_val_t parse_pattern(el_val_t tokens, el_val_t pos) {
|
||||
if (str_eq(v, EL_STR("_"))) {
|
||||
return make_result(el_map_new(1, "pattern", EL_STR("Wildcard")), (pos + 1));
|
||||
}
|
||||
el_val_t next_k = tok_kind(tokens, (pos + 1));
|
||||
if (str_eq(next_k, EL_STR("ColonColon"))) {
|
||||
el_val_t variant_name = tok_value(tokens, (pos + 2));
|
||||
return make_result(el_map_new(3, "pattern", EL_STR("Variant"), "enum_name", v, "variant", variant_name), (pos + 3));
|
||||
}
|
||||
return make_result(el_map_new(2, "pattern", EL_STR("Binding"), "name", v), (pos + 1));
|
||||
}
|
||||
if (str_eq(k, EL_STR("Int"))) {
|
||||
@@ -1855,6 +1878,10 @@ el_val_t parse_stmt(el_val_t tokens, el_val_t pos) {
|
||||
el_val_t p = (pos + 1);
|
||||
el_val_t name = tok_value(tokens, p);
|
||||
p = (p + 1);
|
||||
el_val_t pk = tok_kind(tokens, p);
|
||||
if (str_eq(pk, EL_STR("Eq"))) {
|
||||
p = (p + 1);
|
||||
}
|
||||
p = expect(tokens, p, EL_STR("LBrace"));
|
||||
el_val_t fields = native_list_empty();
|
||||
el_val_t running = 1;
|
||||
@@ -2923,7 +2950,12 @@ el_val_t cg_match(el_val_t expr) {
|
||||
}
|
||||
parts = native_list_append(parts, el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("if ("), subj_var), EL_STR(" == ")), bv), EL_STR(") { ")), result_var), EL_STR(" = (")), body_c), EL_STR("); goto ")), done_label), EL_STR("; } ")));
|
||||
} else {
|
||||
parts = native_list_append(parts, el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("{ "), result_var), EL_STR(" = (")), body_c), EL_STR("); goto ")), done_label), EL_STR("; } ")));
|
||||
if (str_eq(pkind, EL_STR("Variant"))) {
|
||||
el_val_t variant = el_get_field(pat, EL_STR("variant"));
|
||||
parts = native_list_append(parts, el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("if (str_eq("), subj_var), EL_STR(", EL_STR(")), c_str_lit(variant)), EL_STR("))) { ")), result_var), EL_STR(" = (")), body_c), EL_STR("); goto ")), done_label), EL_STR("; } ")));
|
||||
} else {
|
||||
parts = native_list_append(parts, el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("{ "), result_var), EL_STR(" = (")), body_c), EL_STR("); goto ")), done_label), EL_STR("; } ")));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -4569,6 +4601,15 @@ el_val_t builtin_arity(el_val_t name) {
|
||||
if (str_eq(name, EL_STR("exit_program"))) {
|
||||
return 1;
|
||||
}
|
||||
if (str_eq(name, EL_STR("getpid_now"))) {
|
||||
return 0;
|
||||
}
|
||||
if (str_eq(name, EL_STR("stdout_to_file"))) {
|
||||
return 1;
|
||||
}
|
||||
if (str_eq(name, EL_STR("stdout_restore"))) {
|
||||
return 0;
|
||||
}
|
||||
if (str_eq(name, EL_STR("exec_command"))) {
|
||||
return 1;
|
||||
}
|
||||
@@ -5594,6 +5635,49 @@ el_val_t js_binop(el_val_t op) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t js_is_async_builtin(el_val_t name) {
|
||||
if (str_eq(name, EL_STR("http_get"))) {
|
||||
return 1;
|
||||
}
|
||||
if (str_eq(name, EL_STR("http_post"))) {
|
||||
return 1;
|
||||
}
|
||||
if (str_eq(name, EL_STR("http_post_json"))) {
|
||||
return 1;
|
||||
}
|
||||
if (str_eq(name, EL_STR("http_get_with_headers"))) {
|
||||
return 1;
|
||||
}
|
||||
if (str_eq(name, EL_STR("http_post_with_headers"))) {
|
||||
return 1;
|
||||
}
|
||||
return 0;
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t js_register_async_fn(el_val_t name) {
|
||||
el_val_t csv = state_get(EL_STR("__js_async_fns"));
|
||||
if (str_eq(csv, EL_STR(""))) {
|
||||
csv = EL_STR(",");
|
||||
}
|
||||
el_val_t key = el_str_concat(el_str_concat(EL_STR(","), name), EL_STR(","));
|
||||
if (str_contains(csv, key)) {
|
||||
return 1;
|
||||
}
|
||||
state_set(EL_STR("__js_async_fns"), el_str_concat(el_str_concat(csv, name), EL_STR(",")));
|
||||
return 1;
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t js_is_async_fn(el_val_t name) {
|
||||
el_val_t csv = state_get(EL_STR("__js_async_fns"));
|
||||
if (str_eq(csv, EL_STR(""))) {
|
||||
return 0;
|
||||
}
|
||||
return str_contains(csv, el_str_concat(el_str_concat(EL_STR(","), name), EL_STR(",")));
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t js_is_int_name(el_val_t name) {
|
||||
el_val_t csv = state_get(EL_STR("__js_int_names"));
|
||||
if (str_eq(csv, EL_STR(""))) {
|
||||
@@ -5937,7 +6021,14 @@ el_val_t js_cg_expr(el_val_t expr) {
|
||||
el_val_t args_c = str_join(args_parts, EL_STR(", "));
|
||||
if (str_eq(func_kind, EL_STR("Ident"))) {
|
||||
el_val_t fn_name = el_get_field(func, EL_STR("name"));
|
||||
return el_str_concat(el_str_concat(el_str_concat(fn_name, EL_STR("(")), args_c), EL_STR(")"));
|
||||
el_val_t call_expr = el_str_concat(el_str_concat(el_str_concat(fn_name, EL_STR("(")), args_c), EL_STR(")"));
|
||||
if (js_is_async_builtin(fn_name)) {
|
||||
return el_str_concat(EL_STR("await "), call_expr);
|
||||
}
|
||||
if (js_is_async_fn(fn_name)) {
|
||||
return el_str_concat(EL_STR("await "), call_expr);
|
||||
}
|
||||
return call_expr;
|
||||
}
|
||||
if (str_eq(func_kind, EL_STR("Field"))) {
|
||||
el_val_t obj = el_get_field(func, EL_STR("object"));
|
||||
@@ -5954,6 +6045,12 @@ el_val_t js_cg_expr(el_val_t expr) {
|
||||
if (str_eq(kind, EL_STR("Field"))) {
|
||||
el_val_t obj = el_get_field(expr, EL_STR("object"));
|
||||
el_val_t field = el_get_field(expr, EL_STR("field"));
|
||||
el_val_t obj_kind = el_get_field(obj, EL_STR("expr"));
|
||||
if (str_eq(obj_kind, EL_STR("Try"))) {
|
||||
el_val_t inner = el_get_field(obj, EL_STR("inner"));
|
||||
el_val_t inner_c = js_cg_expr(inner);
|
||||
return el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("("), inner_c), EL_STR(")?.[")), js_str_lit(field)), EL_STR("] ?? null"));
|
||||
}
|
||||
el_val_t obj_c = js_cg_expr(obj);
|
||||
return el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("el_get_field("), obj_c), EL_STR(", ")), js_str_lit(field)), EL_STR(")"));
|
||||
}
|
||||
@@ -5963,6 +6060,12 @@ el_val_t js_cg_expr(el_val_t expr) {
|
||||
el_val_t obj_c = js_cg_expr(obj);
|
||||
el_val_t idx_c = js_cg_expr(idx);
|
||||
el_val_t idx_kind = el_get_field(idx, EL_STR("expr"));
|
||||
el_val_t obj_kind = el_get_field(obj, EL_STR("expr"));
|
||||
if (str_eq(obj_kind, EL_STR("Try"))) {
|
||||
el_val_t inner = el_get_field(obj, EL_STR("inner"));
|
||||
el_val_t inner_c = js_cg_expr(inner);
|
||||
return el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("("), inner_c), EL_STR(")?.[")), idx_c), EL_STR("] ?? null"));
|
||||
}
|
||||
if (str_eq(idx_kind, EL_STR("Str"))) {
|
||||
return el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("el_get_field("), obj_c), EL_STR(", ")), idx_c), EL_STR(")"));
|
||||
}
|
||||
@@ -6069,7 +6172,12 @@ el_val_t js_cg_match(el_val_t expr) {
|
||||
}
|
||||
parts = native_list_append(parts, el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("if ("), subj_var), EL_STR(" === ")), bv), EL_STR(") return (")), body_c), EL_STR("); ")));
|
||||
} else {
|
||||
parts = native_list_append(parts, el_str_concat(el_str_concat(EL_STR("return ("), body_c), EL_STR("); ")));
|
||||
if (str_eq(pkind, EL_STR("Variant"))) {
|
||||
el_val_t variant = el_get_field(pat, EL_STR("variant"));
|
||||
parts = native_list_append(parts, el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("if (str_eq("), subj_var), EL_STR(", ")), js_str_lit(variant)), EL_STR(")) return (")), body_c), EL_STR("); ")));
|
||||
} else {
|
||||
parts = native_list_append(parts, el_str_concat(el_str_concat(EL_STR("return ("), body_c), EL_STR("); ")));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -6182,12 +6290,12 @@ el_val_t js_cg_stmt(el_val_t stmt, el_val_t indent, el_val_t declared) {
|
||||
}
|
||||
if (str_eq(kind, EL_STR("CgiBlock"))) {
|
||||
el_val_t cname = el_get_field(stmt, EL_STR("name"));
|
||||
js_emit_line(el_str_concat(el_str_concat(el_str_concat(indent, EL_STR("// cgi block '")), cname), EL_STR("' - no-op in JS target (server-side concept)")));
|
||||
js_emit_line(el_str_concat(el_str_concat(el_str_concat(indent, EL_STR("// cgi block '")), cname), EL_STR("' \xe2\x80\x94 no-op in JS target (server-side concept)")));
|
||||
return declared;
|
||||
}
|
||||
if (str_eq(kind, EL_STR("ServiceBlock"))) {
|
||||
el_val_t sname = el_get_field(stmt, EL_STR("name"));
|
||||
js_emit_line(el_str_concat(el_str_concat(el_str_concat(indent, EL_STR("// service block '")), sname), EL_STR("' - no-op in JS target")));
|
||||
js_emit_line(el_str_concat(el_str_concat(el_str_concat(indent, EL_STR("// service block '")), sname), EL_STR("' \xe2\x80\x94 no-op in JS target")));
|
||||
return declared;
|
||||
}
|
||||
return declared;
|
||||
@@ -6330,12 +6438,22 @@ el_val_t js_cg_fn(el_val_t stmt) {
|
||||
el_val_t params = el_get_field(stmt, EL_STR("params"));
|
||||
el_val_t body = el_get_field(stmt, EL_STR("body"));
|
||||
el_val_t ret_type = el_get_field(stmt, EL_STR("ret_type"));
|
||||
el_val_t decorator = el_get_field(stmt, EL_STR("decorator"));
|
||||
el_val_t params_str = js_params_str(params);
|
||||
js_build_int_names_for_params(params);
|
||||
if (str_eq(fn_name, EL_STR("main"))) {
|
||||
js_emit_line(el_str_concat(el_str_concat(EL_STR("function main("), params_str), EL_STR(") {")));
|
||||
if (str_eq(decorator, EL_STR("async"))) {
|
||||
js_register_async_fn(fn_name);
|
||||
if (str_eq(fn_name, EL_STR("main"))) {
|
||||
js_emit_line(el_str_concat(el_str_concat(EL_STR("async function main("), params_str), EL_STR(") {")));
|
||||
} else {
|
||||
js_emit_line(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("async function "), fn_name), EL_STR("(")), params_str), EL_STR(") {")));
|
||||
}
|
||||
} else {
|
||||
js_emit_line(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("function "), fn_name), EL_STR("(")), params_str), EL_STR(") {")));
|
||||
if (str_eq(fn_name, EL_STR("main"))) {
|
||||
js_emit_line(el_str_concat(el_str_concat(EL_STR("function main("), params_str), EL_STR(") {")));
|
||||
} else {
|
||||
js_emit_line(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("function "), fn_name), EL_STR("(")), params_str), EL_STR(") {")));
|
||||
}
|
||||
}
|
||||
el_val_t decl = native_list_empty();
|
||||
el_val_t np = native_list_len(params);
|
||||
@@ -6387,35 +6505,81 @@ el_val_t js_is_top_level_decl(el_val_t stmt) {
|
||||
}
|
||||
|
||||
el_val_t codegen_js(el_val_t stmts, el_val_t source) {
|
||||
return codegen_js_inner(stmts, source, 0, EL_STR(""));
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t codegen_js_bundle(el_val_t stmts, el_val_t source, el_val_t runtime_content) {
|
||||
return codegen_js_inner(stmts, source, 1, runtime_content);
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t codegen_js_inner(el_val_t stmts, el_val_t source, el_val_t bundle_mode, el_val_t runtime_content) {
|
||||
state_set(EL_STR("__js_int_names"), EL_STR(""));
|
||||
state_set(EL_STR("__js_match_counter"), EL_STR(""));
|
||||
state_set(EL_STR("__js_async_fns"), EL_STR(""));
|
||||
js_emit_line(EL_STR("// Generated by elc --target=js"));
|
||||
js_emit_line(EL_STR("// Runtime: foundation/el/el-compiler/runtime/el_runtime.js"));
|
||||
js_emit_line(EL_STR("import \"./el_runtime.js\";"));
|
||||
js_emit_line(EL_STR("const {"));
|
||||
js_emit_line(EL_STR(" println, print, el_str_concat, str_concat, str_eq, str_starts_with, str_ends_with,"));
|
||||
js_emit_line(EL_STR(" str_len, int_to_str, str_to_int, str_slice, str_contains, str_replace,"));
|
||||
js_emit_line(EL_STR(" str_to_upper, str_to_lower, str_trim, str_index_of, str_split, str_char_at,"));
|
||||
js_emit_line(EL_STR(" str_char_code, str_lower, str_upper, el_abs, el_max, el_min,"));
|
||||
js_emit_line(EL_STR(" el_list_new, el_list_len, el_list_get, el_list_append, el_list_empty, el_list_clone,"));
|
||||
js_emit_line(EL_STR(" list_push, list_join, list_range,"));
|
||||
js_emit_line(EL_STR(" el_map_new, el_get_field, el_map_get, el_map_set,"));
|
||||
js_emit_line(EL_STR(" http_get, http_post, http_post_json,"));
|
||||
js_emit_line(EL_STR(" fs_read, fs_write, fs_list,"));
|
||||
js_emit_line(EL_STR(" json_parse, json_stringify, json_get, json_get_string, json_get_int,"));
|
||||
js_emit_line(EL_STR(" time_now, time_now_utc, sleep_ms, bool_to_str, exit_program,"));
|
||||
js_emit_line(EL_STR(" el_retain, el_release,"));
|
||||
js_emit_line(EL_STR(" append, len, get, map_get, map_set,"));
|
||||
js_emit_line(EL_STR(" native_list_get, native_list_len, native_list_append, native_list_empty,"));
|
||||
js_emit_line(EL_STR(" native_list_clone, native_string_chars, native_int_to_str,"));
|
||||
js_emit_line(EL_STR(" args, state_set, state_get, state_del, state_keys, env,"));
|
||||
js_emit_line(EL_STR(" dharma_connect, dharma_send, dharma_emit, dharma_field, dharma_activate,"));
|
||||
js_emit_line(EL_STR(" engram_node, engram_search, engram_activate,"));
|
||||
js_emit_line(EL_STR(" llm_call, llm_call_system,"));
|
||||
js_emit_line(EL_STR("} = globalThis.__el;"));
|
||||
js_emit_blank();
|
||||
if (bundle_mode) {
|
||||
js_emit_line(EL_STR("// Bundle mode: runtime inlined, no import statement needed."));
|
||||
js_emit_line(EL_STR(""));
|
||||
js_emit_line(EL_STR(";(function() {"));
|
||||
js_emit_line(EL_STR("\"use strict\";"));
|
||||
js_emit_line(js_strip_es_exports(runtime_content));
|
||||
js_emit_line(EL_STR(""));
|
||||
} else {
|
||||
js_emit_line(EL_STR("// Runtime: foundation/el/el-compiler/runtime/el_runtime.js"));
|
||||
js_emit_line(EL_STR("import \"./el_runtime.js\";"));
|
||||
}
|
||||
if (!bundle_mode) {
|
||||
js_emit_line(EL_STR("const {"));
|
||||
js_emit_line(EL_STR(" println, print, el_str_concat, str_concat, str_eq, str_starts_with, str_ends_with,"));
|
||||
js_emit_line(EL_STR(" str_len, int_to_str, str_to_int, str_slice, str_contains, str_replace,"));
|
||||
js_emit_line(EL_STR(" str_to_upper, str_to_lower, str_trim, str_index_of, str_split, str_char_at,"));
|
||||
js_emit_line(EL_STR(" str_char_code, str_lower, str_upper, el_abs, el_max, el_min,"));
|
||||
js_emit_line(EL_STR(" el_list_new, el_list_len, el_list_get, el_list_append, el_list_empty, el_list_clone,"));
|
||||
js_emit_line(EL_STR(" list_push, list_join, list_range,"));
|
||||
js_emit_line(EL_STR(" el_map_new, el_get_field, el_map_get, el_map_set,"));
|
||||
js_emit_line(EL_STR(" http_get, http_post, http_post_json,"));
|
||||
js_emit_line(EL_STR(" fs_read, fs_write, fs_list,"));
|
||||
js_emit_line(EL_STR(" json_parse, json_stringify, json_get, json_get_string, json_get_int,"));
|
||||
js_emit_line(EL_STR(" time_now, time_now_utc, sleep_ms, bool_to_str, exit_program,"));
|
||||
js_emit_line(EL_STR(" el_retain, el_release,"));
|
||||
js_emit_line(EL_STR(" append, len, get, map_get, map_set,"));
|
||||
js_emit_line(EL_STR(" native_list_get, native_list_len, native_list_append, native_list_empty,"));
|
||||
js_emit_line(EL_STR(" native_list_clone, native_string_chars, native_int_to_str,"));
|
||||
js_emit_line(EL_STR(" args, state_set, state_get, state_del, state_keys, env,"));
|
||||
js_emit_line(EL_STR(" dharma_connect, dharma_send, dharma_emit, dharma_field, dharma_activate,"));
|
||||
js_emit_line(EL_STR(" engram_node, engram_search, engram_activate,"));
|
||||
js_emit_line(EL_STR(" llm_call, llm_call_system,"));
|
||||
js_emit_line(EL_STR(" dom_get_element, dom_get_value, dom_set_value, dom_get_text, dom_set_text,"));
|
||||
js_emit_line(EL_STR(" dom_set_prop, dom_get_prop, dom_set_style, dom_add_class, dom_remove_class,"));
|
||||
js_emit_line(EL_STR(" dom_show, dom_hide, dom_listen, dom_query, dom_query_all, dom_create,"));
|
||||
js_emit_line(EL_STR(" dom_append, dom_remove, dom_is_null,"));
|
||||
js_emit_line(EL_STR(" dom_set_attr, dom_get_attr, dom_remove_attr, dom_set_html, dom_get_html,"));
|
||||
js_emit_line(EL_STR(" dom_get_parent, dom_contains_class, dom_get_checked, dom_set_checked,"));
|
||||
js_emit_line(EL_STR(" set_timeout, set_interval, clear_interval,"));
|
||||
js_emit_line(EL_STR(" local_storage_get, local_storage_set, local_storage_remove,"));
|
||||
js_emit_line(EL_STR(" window_location, window_redirect, window_on_load,"));
|
||||
js_emit_line(EL_STR(" console_log,"));
|
||||
js_emit_line(EL_STR(" window_set, window_get, native_js, native_js_call,"));
|
||||
js_emit_line(EL_STR("} = globalThis.__el;"));
|
||||
js_emit_blank();
|
||||
}
|
||||
el_val_t n = native_list_len(stmts);
|
||||
el_val_t i = 0;
|
||||
while (i < n) {
|
||||
el_val_t stmt = native_list_get(stmts, i);
|
||||
el_val_t sk = el_get_field(stmt, EL_STR("stmt"));
|
||||
if (str_eq(sk, EL_STR("FnDef"))) {
|
||||
el_val_t dec = el_get_field(stmt, EL_STR("decorator"));
|
||||
if (str_eq(dec, EL_STR("async"))) {
|
||||
el_val_t aname = el_get_field(stmt, EL_STR("name"));
|
||||
js_register_async_fn(aname);
|
||||
}
|
||||
}
|
||||
i = (i + 1);
|
||||
}
|
||||
i = 0;
|
||||
while (i < n) {
|
||||
el_val_t stmt = native_list_get(stmts, i);
|
||||
if (js_is_fndef(stmt)) {
|
||||
@@ -6453,10 +6617,37 @@ el_val_t codegen_js(el_val_t stmts, el_val_t source) {
|
||||
js_emit_blank();
|
||||
js_emit_line(EL_STR("main();"));
|
||||
}
|
||||
if (bundle_mode) {
|
||||
js_emit_line(EL_STR(""));
|
||||
js_emit_line(EL_STR("})();"));
|
||||
}
|
||||
return EL_STR("");
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t js_strip_es_exports(el_val_t content) {
|
||||
el_val_t lines = str_split(content, EL_STR("\n"));
|
||||
el_val_t n = native_list_len(lines);
|
||||
el_val_t out = native_list_empty();
|
||||
el_val_t i = 0;
|
||||
while (i < n) {
|
||||
el_val_t line = native_list_get(lines, i);
|
||||
el_val_t trimmed = str_trim(line);
|
||||
if (str_starts_with(trimmed, EL_STR("export {"))) {
|
||||
i = n;
|
||||
} else {
|
||||
if (str_starts_with(trimmed, EL_STR("export default"))) {
|
||||
i = n;
|
||||
} else {
|
||||
out = native_list_append(out, line);
|
||||
}
|
||||
}
|
||||
i = (i + 1);
|
||||
}
|
||||
return str_join(out, EL_STR("\n"));
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t compile(el_val_t source) {
|
||||
el_val_t tokens = lex(source);
|
||||
el_val_t stmts = parse(tokens);
|
||||
@@ -6473,6 +6664,19 @@ el_val_t compile_js(el_val_t source) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t compile_js_with_bundle(el_val_t source, el_val_t runtime_path) {
|
||||
el_val_t tokens = lex(source);
|
||||
el_val_t stmts = parse(tokens);
|
||||
el_release(tokens);
|
||||
el_val_t runtime_content = fs_read(runtime_path);
|
||||
if (str_eq(runtime_content, EL_STR(""))) {
|
||||
println(el_str_concat(EL_STR("el-compiler: warning: --bundle: could not read runtime at "), runtime_path));
|
||||
println(EL_STR("el-compiler: warning: bundle output will be incomplete"));
|
||||
}
|
||||
return codegen_js_bundle(stmts, source, runtime_content);
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t compile_dispatch(el_val_t tgt, el_val_t source) {
|
||||
if (str_eq(tgt, EL_STR("js"))) {
|
||||
return compile_js(source);
|
||||
@@ -6481,6 +6685,14 @@ el_val_t compile_dispatch(el_val_t tgt, el_val_t source) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t compile_dispatch_bundle(el_val_t tgt, el_val_t source, el_val_t runtime_path) {
|
||||
if (str_eq(tgt, EL_STR("js"))) {
|
||||
return compile_js_with_bundle(source, runtime_path);
|
||||
}
|
||||
return compile(source);
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t detect_target(el_val_t argv) {
|
||||
el_val_t n = native_list_len(argv);
|
||||
el_val_t i = 0;
|
||||
@@ -6525,6 +6737,127 @@ el_val_t detect_emit_header(el_val_t argv) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t detect_bundle(el_val_t argv) {
|
||||
el_val_t n = native_list_len(argv);
|
||||
el_val_t i = 0;
|
||||
while (i < n) {
|
||||
el_val_t a = native_list_get(argv, i);
|
||||
if (str_eq(a, EL_STR("--bundle"))) {
|
||||
return 1;
|
||||
}
|
||||
i = (i + 1);
|
||||
}
|
||||
return 0;
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t detect_minify(el_val_t argv) {
|
||||
el_val_t n = native_list_len(argv);
|
||||
el_val_t i = 0;
|
||||
while (i < n) {
|
||||
el_val_t a = native_list_get(argv, i);
|
||||
if (str_eq(a, EL_STR("--minify"))) {
|
||||
return 1;
|
||||
}
|
||||
i = (i + 1);
|
||||
}
|
||||
return 0;
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t detect_obfuscate(el_val_t argv) {
|
||||
el_val_t n = native_list_len(argv);
|
||||
el_val_t i = 0;
|
||||
while (i < n) {
|
||||
el_val_t a = native_list_get(argv, i);
|
||||
if (str_eq(a, EL_STR("--obfuscate"))) {
|
||||
return 1;
|
||||
}
|
||||
i = (i + 1);
|
||||
}
|
||||
return 0;
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t make_temp_path(el_val_t suffix) {
|
||||
el_val_t pid = getpid_now();
|
||||
el_val_t ts = time_now();
|
||||
return el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("/tmp/elc-"), native_int_to_str(pid)), EL_STR("-")), native_int_to_str(ts)), EL_STR(".")), suffix);
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t js_reserved_names(void) {
|
||||
return EL_STR("neuronDemoToggle,neuronDemoSend,neuronDemoReset,signInWith,signInWithEmail,signUpWithEmail,sendMagicLink,signOut,resetPassword,sendResetEmail,updatePassword,showSignIn,showSignUp,hideReset,setSort,addFamilyMember,removeFamilyMember,copyForPlatform,entHeadcountChange,NEURON_CFG");
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t find_node_tool(el_val_t tool_name, el_val_t src_dir) {
|
||||
el_val_t cand1 = el_str_concat(el_str_concat(src_dir, EL_STR("/node_modules/.bin/")), tool_name);
|
||||
el_val_t check1 = str_trim(exec_capture(el_str_concat(el_str_concat(EL_STR("test -x "), cand1), EL_STR(" && echo yes 2>/dev/null"))));
|
||||
if (str_eq(check1, EL_STR("yes"))) {
|
||||
return cand1;
|
||||
}
|
||||
el_val_t parent_dir = dirname_of(src_dir);
|
||||
el_val_t cand2 = el_str_concat(el_str_concat(parent_dir, EL_STR("/node_modules/.bin/")), tool_name);
|
||||
el_val_t check2 = str_trim(exec_capture(el_str_concat(el_str_concat(EL_STR("test -x "), cand2), EL_STR(" && echo yes 2>/dev/null"))));
|
||||
if (str_eq(check2, EL_STR("yes"))) {
|
||||
return cand2;
|
||||
}
|
||||
el_val_t npx_path = str_trim(exec_capture(EL_STR("which npx 2>/dev/null")));
|
||||
if (!str_eq(npx_path, EL_STR(""))) {
|
||||
return el_str_concat(EL_STR("npx --yes "), tool_name);
|
||||
}
|
||||
return EL_STR("");
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t apply_minify(el_val_t js_path, el_val_t out_path, el_val_t src_dir) {
|
||||
el_val_t terser = find_node_tool(EL_STR("terser"), src_dir);
|
||||
if (str_eq(terser, EL_STR(""))) {
|
||||
println(EL_STR("el-compiler: error: terser not found. Run 'npm install terser' in your project directory."));
|
||||
return 0;
|
||||
}
|
||||
el_val_t names = js_reserved_names();
|
||||
el_val_t compress_opts = EL_STR("passes=2,drop_console=false,drop_debugger=true");
|
||||
el_val_t mangle_reserved = el_str_concat(el_str_concat(EL_STR("'reserved=["), names), EL_STR("]'"));
|
||||
el_val_t cmd = el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(terser, EL_STR(" ")), js_path), EL_STR(" --compress ")), compress_opts), EL_STR(" --mangle ")), mangle_reserved), EL_STR(" --output ")), out_path);
|
||||
el_val_t ret = exec_command(cmd);
|
||||
if (ret == 0) {
|
||||
return 1;
|
||||
}
|
||||
println(el_str_concat(el_str_concat(EL_STR("el-compiler: error: terser failed (exit "), native_int_to_str(ret)), EL_STR(")")));
|
||||
return 0;
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t apply_obfuscate(el_val_t js_path, el_val_t out_path, el_val_t src_dir) {
|
||||
el_val_t obfuscator = find_node_tool(EL_STR("javascript-obfuscator"), src_dir);
|
||||
if (str_eq(obfuscator, EL_STR(""))) {
|
||||
println(EL_STR("el-compiler: error: javascript-obfuscator not found. Run 'npm install javascript-obfuscator' in your project directory."));
|
||||
return 0;
|
||||
}
|
||||
el_val_t names = js_reserved_names();
|
||||
el_val_t cmd = el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(obfuscator, EL_STR(" ")), js_path), EL_STR(" --output ")), out_path), EL_STR(" --compact true --simplify true --string-array true --string-array-encoding base64 --string-array-threshold 0.75 --identifier-names-generator hexadecimal --rename-globals false --self-defending false --reserved-names ")), names);
|
||||
el_val_t ret = exec_command(cmd);
|
||||
if (ret == 0) {
|
||||
return 1;
|
||||
}
|
||||
println(el_str_concat(el_str_concat(EL_STR("el-compiler: error: javascript-obfuscator failed (exit "), native_int_to_str(ret)), EL_STR(")")));
|
||||
return 0;
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t resolve_runtime_path(el_val_t src_path) {
|
||||
el_val_t src_dir = dirname_of(src_path);
|
||||
el_val_t candidate = el_str_concat(src_dir, EL_STR("/el_runtime.js"));
|
||||
el_val_t existing = fs_read(candidate);
|
||||
if (!str_eq(existing, EL_STR(""))) {
|
||||
return candidate;
|
||||
}
|
||||
return EL_STR("");
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t type_node_to_el(el_val_t t) {
|
||||
el_val_t k = el_get_field(t, EL_STR("kind"));
|
||||
if (str_eq(k, EL_STR("Simple"))) {
|
||||
@@ -6547,7 +6880,7 @@ el_val_t emit_header(el_val_t stmts, el_val_t hdr_path) {
|
||||
el_val_t n = native_list_len(stmts);
|
||||
el_val_t i = 0;
|
||||
el_val_t parts = native_list_empty();
|
||||
parts = native_list_append(parts, EL_STR("// auto-generated by elc --emit-header - do not edit\n"));
|
||||
parts = native_list_append(parts, EL_STR("// auto-generated by elc --emit-header \xe2\x80\x94 do not edit\n"));
|
||||
while (i < n) {
|
||||
el_val_t stmt = native_list_get(stmts, i);
|
||||
el_val_t kind = el_get_field(stmt, EL_STR("stmt"));
|
||||
@@ -6661,17 +6994,76 @@ el_val_t resolve_imports(el_val_t src_path) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
el_val_t run_with_postprocess(el_val_t tgt, el_val_t source, el_val_t src_path, el_val_t do_bundle, el_val_t do_obfuscate, el_val_t argc, el_val_t positional) {
|
||||
el_val_t src_dir = dirname_of(src_path);
|
||||
el_val_t tmp_gen = make_temp_path(EL_STR("js"));
|
||||
el_val_t tmp_min = make_temp_path(EL_STR("min.js"));
|
||||
stdout_to_file(tmp_gen);
|
||||
if (do_bundle) {
|
||||
el_val_t runtime_path = resolve_runtime_path(src_path);
|
||||
compile_dispatch_bundle(tgt, source, runtime_path);
|
||||
} else {
|
||||
compile_dispatch(tgt, source);
|
||||
}
|
||||
stdout_restore();
|
||||
el_val_t ok_min = apply_minify(tmp_gen, tmp_min, src_dir);
|
||||
if (!ok_min) {
|
||||
exec_command(el_str_concat(el_str_concat(el_str_concat(EL_STR("rm -f "), tmp_gen), EL_STR(" ")), tmp_min));
|
||||
exit(1);
|
||||
}
|
||||
state_set(EL_STR("__elc_final_js"), tmp_min);
|
||||
if (do_obfuscate) {
|
||||
el_val_t tmp_obf = make_temp_path(EL_STR("obf.js"));
|
||||
el_val_t ok_obf = apply_obfuscate(tmp_min, tmp_obf, src_dir);
|
||||
if (!ok_obf) {
|
||||
exec_command(el_str_concat(el_str_concat(el_str_concat(el_str_concat(el_str_concat(EL_STR("rm -f "), tmp_gen), EL_STR(" ")), tmp_min), EL_STR(" ")), tmp_obf));
|
||||
exit(1);
|
||||
}
|
||||
state_set(EL_STR("__elc_final_js"), tmp_obf);
|
||||
}
|
||||
el_val_t final_path = state_get(EL_STR("__elc_final_js"));
|
||||
el_val_t final_js = fs_read(final_path);
|
||||
exec_command(el_str_concat(el_str_concat(el_str_concat(EL_STR("rm -f "), tmp_gen), EL_STR(" ")), tmp_min));
|
||||
if (do_obfuscate) {
|
||||
exec_command(el_str_concat(EL_STR("rm -f "), final_path));
|
||||
}
|
||||
if (argc >= 2) {
|
||||
el_val_t out_path = native_list_get(positional, 1);
|
||||
el_val_t ok = fs_write(out_path, final_js);
|
||||
if (ok) {
|
||||
return 0;
|
||||
} else {
|
||||
println(EL_STR("el-compiler: failed to write output"));
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
print(final_js);
|
||||
return 0;
|
||||
}
|
||||
|
||||
int main(int _argc, char** _argv) {
|
||||
el_runtime_init_args(_argc, _argv);
|
||||
el_val_t argv = args();
|
||||
el_val_t tgt = detect_target(argv);
|
||||
el_val_t do_emit_header = detect_emit_header(argv);
|
||||
el_val_t do_bundle = detect_bundle(argv);
|
||||
el_val_t do_minify = detect_minify(argv);
|
||||
el_val_t do_obfuscate = detect_obfuscate(argv);
|
||||
if (do_obfuscate) {
|
||||
do_minify = 1;
|
||||
}
|
||||
el_val_t positional = strip_flags(argv);
|
||||
el_val_t argc = native_list_len(positional);
|
||||
if (argc < 1) {
|
||||
println(EL_STR("el-compiler: usage: elc [--target=c|js] [--emit-header] <source.el> [<output>]"));
|
||||
println(EL_STR("el-compiler: usage: elc [--target=c|js] [--bundle] [--minify] [--obfuscate] [--emit-header] <source.el> [<output>]"));
|
||||
exit(1);
|
||||
}
|
||||
if (do_minify) {
|
||||
if (!str_eq(tgt, EL_STR("js"))) {
|
||||
println(EL_STR("el-compiler: error: --minify and --obfuscate require --target=js"));
|
||||
exit(1);
|
||||
}
|
||||
}
|
||||
el_val_t src_path = native_list_get(positional, 0);
|
||||
if (do_emit_header) {
|
||||
el_val_t raw_source = fs_read(src_path);
|
||||
@@ -6683,7 +7075,17 @@ int main(int _argc, char** _argv) {
|
||||
el_release(hdr_stmts);
|
||||
}
|
||||
el_val_t source = resolve_imports(src_path);
|
||||
el_val_t out = compile_dispatch(tgt, source);
|
||||
if (do_minify) {
|
||||
run_with_postprocess(tgt, source, src_path, do_bundle, do_obfuscate, argc, positional);
|
||||
exit(0);
|
||||
}
|
||||
el_val_t out = EL_STR("");
|
||||
if (do_bundle) {
|
||||
el_val_t runtime_path = resolve_runtime_path(src_path);
|
||||
out = compile_dispatch_bundle(tgt, source, runtime_path);
|
||||
} else {
|
||||
out = compile_dispatch(tgt, source);
|
||||
}
|
||||
if (argc >= 2) {
|
||||
el_val_t out_path = native_list_get(positional, 1);
|
||||
el_val_t ok = fs_write(out_path, out);
|
||||
+130
-1548
File diff suppressed because it is too large
Load Diff
+15
-133
@@ -22,9 +22,6 @@
|
||||
* EL_STR(s) cast string literal to el_val_t
|
||||
* EL_CSTR(v) cast el_val_t back to const char*
|
||||
* EL_INT(v) identity — el_val_t is already int64_t
|
||||
* EL_NULL null / zero value
|
||||
* EL_FALSE boolean false (0)
|
||||
* EL_TRUE boolean true (1)
|
||||
*
|
||||
* Link requirements:
|
||||
* -lcurl — required for the HTTP client (http_get, http_post, llm_*).
|
||||
@@ -56,8 +53,6 @@ typedef int64_t el_val_t;
|
||||
#define EL_CSTR(v) ((const char*)(uintptr_t)(v))
|
||||
#define EL_INT(v) (v)
|
||||
#define EL_NULL ((el_val_t)0)
|
||||
#define EL_FALSE ((el_val_t)0)
|
||||
#define EL_TRUE ((el_val_t)1)
|
||||
|
||||
/* Float values share the el_val_t (int64) slot via a bit-cast.
|
||||
* The codegen emits Float literals as `el_from_float(<dbl>)` so the
|
||||
@@ -81,9 +76,11 @@ extern "C" {
|
||||
|
||||
/* ── I/O ──────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t println(el_val_t s);
|
||||
el_val_t print(el_val_t s);
|
||||
void println(el_val_t s);
|
||||
void print(el_val_t s);
|
||||
el_val_t readline(void);
|
||||
el_val_t stdout_to_file(el_val_t path); /* redirect println to a file */
|
||||
el_val_t stdout_restore(void); /* restore stdout after capture */
|
||||
|
||||
/* ── String builtins ─────────────────────────────────────────────────────── */
|
||||
|
||||
@@ -95,7 +92,6 @@ el_val_t str_len(el_val_t s);
|
||||
el_val_t str_concat(el_val_t a, el_val_t b);
|
||||
el_val_t int_to_str(el_val_t n);
|
||||
el_val_t str_to_int(el_val_t s);
|
||||
el_val_t native_str_to_int(el_val_t s);
|
||||
el_val_t str_slice(el_val_t s, el_val_t start, el_val_t end);
|
||||
el_val_t str_contains(el_val_t s, el_val_t sub);
|
||||
el_val_t str_replace(el_val_t s, el_val_t from, el_val_t to);
|
||||
@@ -123,10 +119,6 @@ el_val_t el_min(el_val_t a, el_val_t b);
|
||||
void el_retain(el_val_t v);
|
||||
void el_release(el_val_t v);
|
||||
|
||||
/* ── Scoped arena (CLI use) ───────────────────────────────────────────────── */
|
||||
el_val_t el_arena_push(void);
|
||||
el_val_t el_arena_pop(el_val_t mark);
|
||||
|
||||
/* ── List ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_list_new(el_val_t count, ...);
|
||||
@@ -150,11 +142,10 @@ el_val_t http_post(el_val_t url, el_val_t body);
|
||||
el_val_t http_post_json(el_val_t url, el_val_t json_body);
|
||||
el_val_t http_get_with_headers(el_val_t url, el_val_t headers_map);
|
||||
el_val_t http_post_with_headers(el_val_t url, el_val_t body, el_val_t headers_map);
|
||||
el_val_t http_post_json_with_headers(el_val_t url, el_val_t headers_map, el_val_t json_body);
|
||||
el_val_t http_post_form_auth(el_val_t url, el_val_t form_body, el_val_t auth_header);
|
||||
el_val_t http_delete(el_val_t url);
|
||||
el_val_t http_serve(el_val_t port, el_val_t handler);
|
||||
el_val_t http_set_handler(el_val_t name);
|
||||
void http_serve(el_val_t port, el_val_t handler);
|
||||
void http_set_handler(el_val_t name);
|
||||
|
||||
/* HTTP server v2 ─────────────────────────────────────────────────────────────
|
||||
* Same dispatch model as http_serve, but the handler signature is widened:
|
||||
@@ -175,8 +166,8 @@ el_val_t http_set_handler(el_val_t name);
|
||||
* The 3-arg http_serve(port, handler) remains supported unchanged for
|
||||
* existing handlers (e.g. products/web/server.el): it dispatches with
|
||||
* (method, path, body), hardcodes 200 OK, and auto-detects content type. */
|
||||
el_val_t http_serve_v2(el_val_t port, el_val_t handler);
|
||||
el_val_t http_set_handler_v2(el_val_t name);
|
||||
void http_serve_v2(el_val_t port, el_val_t handler);
|
||||
void http_set_handler_v2(el_val_t name);
|
||||
|
||||
/* Build an HTTP response envelope. `headers_json` should be a JSON object
|
||||
* literal like `{"WWW-Authenticate":"Basic"}` (or "" / "{}" for none). The
|
||||
@@ -187,11 +178,6 @@ el_val_t http_set_handler_v2(el_val_t name);
|
||||
* auto-content-type contract for legacy handlers that return plain bodies. */
|
||||
el_val_t http_response(el_val_t status, el_val_t headers_json, el_val_t body);
|
||||
|
||||
/* SSE connection fd — set by http_worker_v2 before calling the El handler,
|
||||
* cleared afterwards. Defined in el_seed.c; called from el_runtime.c.
|
||||
* The getter is exposed as __http_conn_fd() to El programs. */
|
||||
void el_seed_set_http_conn_fd(int fd);
|
||||
|
||||
/* HTTP timeout — every libcurl request honors EL_HTTP_TIMEOUT_MS (default
|
||||
* 60000ms). Read lazily on first use, so setting the env var any time before
|
||||
* the first http_* call is sufficient. */
|
||||
@@ -227,15 +213,19 @@ el_val_t url_decode(el_val_t s); /* '+' → space, %XX → byte */
|
||||
* {"p":[],"a":["href","title"],"strong":[],...}
|
||||
* where each value is the array of attribute names allowed for that tag. */
|
||||
el_val_t el_html_sanitize(el_val_t input_html, el_val_t allowlist_json);
|
||||
el_val_t html_raw(el_val_t s);
|
||||
|
||||
/* ── HTML template helpers ───────────────────────────────────────────────────
|
||||
* Used by compiled El HTML template expressions.
|
||||
* html_escape(s) — escape & < > " ' for safe inline interpolation.
|
||||
* html_raw(s) — identity; explicit opt-out from escaping (`raw()` form). */
|
||||
el_val_t html_escape(el_val_t s);
|
||||
el_val_t html_raw(el_val_t s);
|
||||
|
||||
/* ── Filesystem ──────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t fs_read(el_val_t path);
|
||||
el_val_t fs_write(el_val_t path, el_val_t content);
|
||||
el_val_t fs_list(el_val_t path);
|
||||
el_val_t fs_list_json(el_val_t path);
|
||||
el_val_t fs_exists(el_val_t path);
|
||||
el_val_t fs_mkdir(el_val_t path); /* mkdir -p, mode 0755 */
|
||||
|
||||
@@ -265,9 +255,6 @@ el_val_t json_set(el_val_t json_str, el_val_t key, el_val_t value);
|
||||
el_val_t json_array_len(el_val_t json_str);
|
||||
el_val_t json_array_get(el_val_t json_str, el_val_t index);
|
||||
el_val_t json_array_get_string(el_val_t json_str, el_val_t index);
|
||||
el_val_t json_escape_string(el_val_t sv);
|
||||
el_val_t json_build_object(el_val_t kvs);
|
||||
el_val_t json_build_array(el_val_t items);
|
||||
|
||||
/* ── Time ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
@@ -280,7 +267,6 @@ el_val_t time_to_parts(el_val_t ts);
|
||||
el_val_t time_from_parts(el_val_t secs, el_val_t ns, el_val_t tz);
|
||||
el_val_t time_add(el_val_t ts, el_val_t n, el_val_t unit);
|
||||
el_val_t time_diff(el_val_t ts1, el_val_t ts2, el_val_t unit);
|
||||
el_val_t now_ns(void);
|
||||
|
||||
/* ── Instant + Duration: first-class temporal types ──────────────────────────
|
||||
* Both types share the el_val_t (int64) slot. Instants are nanoseconds
|
||||
@@ -437,8 +423,6 @@ el_val_t state_set(el_val_t key, el_val_t value);
|
||||
el_val_t state_get(el_val_t key);
|
||||
el_val_t state_del(el_val_t key);
|
||||
el_val_t state_keys(void);
|
||||
el_val_t state_has(el_val_t key);
|
||||
el_val_t state_get_or(el_val_t key, el_val_t default_val);
|
||||
|
||||
/* ── Float formatting ────────────────────────────────────────────────────── */
|
||||
|
||||
@@ -530,15 +514,9 @@ el_val_t parse_int(el_val_t s, el_val_t default_val);
|
||||
|
||||
/* ── Process ─────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t exit_program(el_val_t code);
|
||||
void exit_program(el_val_t code);
|
||||
el_val_t getpid_now(void);
|
||||
|
||||
/* Self-terminating memory guard. Reads ELC_MAX_MEM_MB (default 512) and
|
||||
* exits with code 1 if resident memory exceeds the limit. Call periodically
|
||||
* during long compilation loops (e.g. after each function is compiled).
|
||||
* Returns 0 when memory is within bounds. */
|
||||
el_val_t el_mem_check(void);
|
||||
|
||||
/* ── CGI identity ─────────────────────────────────────────────────────────────
|
||||
* Called at the start of main() in CGI programs (those with a `cgi {}` block).
|
||||
* Records the program's DHARMA identity before any other code executes. */
|
||||
@@ -776,108 +754,12 @@ el_val_t exec_capture(el_val_t cmd); /* run shell command, capture stdout */
|
||||
el_val_t exec(el_val_t cmd); /* exec(cmd) → stdout String (30s timeout) */
|
||||
el_val_t exec_bg(el_val_t cmd); /* exec_bg(cmd) → PID String (non-blocking) */
|
||||
|
||||
/* ── Stdout redirection (used by compiler JS pipeline) ───────────────────── */
|
||||
el_val_t stdout_to_file(el_val_t path); /* redirect process stdout to a file */
|
||||
el_val_t stdout_restore(void); /* restore process stdout to terminal */
|
||||
|
||||
el_val_t emit_log(el_val_t level, el_val_t msg, el_val_t fields_json);
|
||||
el_val_t emit_metric(el_val_t name, el_val_t value, el_val_t tags_json);
|
||||
el_val_t trace_span_start(el_val_t name);
|
||||
el_val_t trace_span_end(el_val_t span_handle);
|
||||
el_val_t emit_event(el_val_t name, el_val_t duration_ms);
|
||||
|
||||
el_val_t __thread_create(el_val_t fn_name_v, el_val_t arg_v);
|
||||
el_val_t __thread_join(el_val_t tid_v);
|
||||
|
||||
/* ── __ prefixed aliases (self-hosting compiler ABI) ─────────────────────────
|
||||
* The El self-hosting compiler emits calls to __-prefixed names. These are
|
||||
* forwarding wrappers around the existing el_runtime functions above. */
|
||||
|
||||
/* I/O */
|
||||
el_val_t __println(el_val_t s);
|
||||
el_val_t __print(el_val_t s);
|
||||
el_val_t __readline(void);
|
||||
|
||||
/* String */
|
||||
el_val_t __int_to_str(el_val_t n);
|
||||
el_val_t __str_to_int(el_val_t s);
|
||||
el_val_t __float_to_str(el_val_t f);
|
||||
el_val_t __str_to_float(el_val_t s);
|
||||
el_val_t __str_len(el_val_t s);
|
||||
el_val_t __str_char_at(el_val_t s, el_val_t i);
|
||||
el_val_t __str_cmp(el_val_t a, el_val_t b);
|
||||
el_val_t __str_ncmp(el_val_t a, el_val_t b, el_val_t n);
|
||||
el_val_t __str_concat_raw(el_val_t a, el_val_t b);
|
||||
el_val_t __str_slice_raw(el_val_t s, el_val_t start, el_val_t end);
|
||||
el_val_t __str_alloc(el_val_t n);
|
||||
el_val_t __str_set_char(el_val_t s, el_val_t i, el_val_t c);
|
||||
|
||||
/* URL encoding */
|
||||
el_val_t __url_encode(el_val_t s);
|
||||
el_val_t __url_decode(el_val_t s);
|
||||
|
||||
/* Environment */
|
||||
el_val_t __env_get(el_val_t key);
|
||||
|
||||
/* Subprocess */
|
||||
el_val_t __exec(el_val_t cmd);
|
||||
el_val_t __exec_bg(el_val_t cmd);
|
||||
|
||||
/* Process */
|
||||
el_val_t __exit_program(el_val_t code);
|
||||
|
||||
/* Filesystem */
|
||||
el_val_t __fs_exists(el_val_t path);
|
||||
el_val_t __fs_mkdir(el_val_t path);
|
||||
el_val_t __fs_read(el_val_t path);
|
||||
el_val_t __fs_write(el_val_t path, el_val_t content);
|
||||
el_val_t __fs_write_bytes(el_val_t path, el_val_t bytes, el_val_t n);
|
||||
el_val_t __fs_list_raw(el_val_t path);
|
||||
|
||||
/* HTTP server */
|
||||
el_val_t __http_response(el_val_t status, el_val_t headers_json, el_val_t body);
|
||||
el_val_t __http_serve(el_val_t port, el_val_t handler);
|
||||
el_val_t __http_serve_v2(el_val_t port, el_val_t handler);
|
||||
|
||||
/* HTTP conn fd / SSE (weak; overridden by el_seed.c when linked together) */
|
||||
el_val_t __http_conn_fd(void);
|
||||
el_val_t __http_sse_open(el_val_t conn_id);
|
||||
el_val_t __http_sse_send(el_val_t conn_id, el_val_t data);
|
||||
el_val_t __http_sse_close(el_val_t conn_id);
|
||||
|
||||
/* HTTP client (requires HAVE_CURL; stubs provided for no-curl builds) */
|
||||
el_val_t __http_do(el_val_t method, el_val_t url, el_val_t body,
|
||||
el_val_t headers_map, el_val_t timeout_ms);
|
||||
el_val_t __http_do_map(el_val_t method, el_val_t url, el_val_t body,
|
||||
el_val_t headers_json, el_val_t timeout_ms);
|
||||
el_val_t __http_do_map_to_file(el_val_t method, el_val_t url, el_val_t body,
|
||||
el_val_t headers_json, el_val_t output_path);
|
||||
|
||||
/* JSON */
|
||||
el_val_t __json_array_get(el_val_t json, el_val_t index);
|
||||
el_val_t __json_array_get_string(el_val_t json, el_val_t index);
|
||||
el_val_t __json_array_len(el_val_t json);
|
||||
el_val_t __json_get(el_val_t json, el_val_t key);
|
||||
el_val_t __json_get_raw(el_val_t json, el_val_t key);
|
||||
el_val_t __json_set(el_val_t json, el_val_t key, el_val_t value);
|
||||
el_val_t __json_parse_map(el_val_t json_str);
|
||||
el_val_t __json_stringify_val(el_val_t val);
|
||||
|
||||
/* Hashing */
|
||||
el_val_t __sha256_hex(el_val_t s);
|
||||
|
||||
/* State K/V */
|
||||
el_val_t __state_del(el_val_t key);
|
||||
el_val_t __state_get(el_val_t key);
|
||||
el_val_t __state_keys(void);
|
||||
el_val_t __state_set(el_val_t key, el_val_t val);
|
||||
|
||||
/* UUID */
|
||||
el_val_t __uuid_v4(void);
|
||||
|
||||
/* Args */
|
||||
el_val_t __args_json(void);
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
@@ -128,6 +128,22 @@ function str_pad_right(s, width, pad) {
|
||||
return String(s).padEnd(width, String(pad));
|
||||
}
|
||||
|
||||
// ── HTML template helpers ────────────────────────────────────────────────────
|
||||
// Used by compiled El HTML template expressions.
|
||||
// html_escape(s) — escape & < > " ' for safe inline interpolation.
|
||||
// html_raw(s) — identity; explicit opt-out from escaping (raw() form).
|
||||
|
||||
function html_escape(s) {
|
||||
return String(s)
|
||||
.replace(/&/g, '&')
|
||||
.replace(/</g, '<')
|
||||
.replace(/>/g, '>')
|
||||
.replace(/"/g, '"')
|
||||
.replace(/'/g, ''');
|
||||
}
|
||||
|
||||
function html_raw(s) { return s; }
|
||||
|
||||
// ── Math ────────────────────────────────────────────────────────────────────
|
||||
|
||||
function el_abs(n) { return Math.abs(n); }
|
||||
@@ -1017,6 +1033,8 @@ export {
|
||||
fs_read, fs_write, fs_list,
|
||||
json_parse, json_stringify, json_get, json_get_string, json_get_int,
|
||||
time_now, time_now_utc, sleep_ms,
|
||||
// HTML template helpers
|
||||
html_escape, html_raw,
|
||||
bool_to_str, exit_program, args, env,
|
||||
state_set, state_get, state_del, state_keys,
|
||||
el_cgi_init,
|
||||
+67
-1554
File diff suppressed because it is too large
Load Diff
+7
-134
@@ -22,9 +22,6 @@
|
||||
* EL_STR(s) cast string literal to el_val_t
|
||||
* EL_CSTR(v) cast el_val_t back to const char*
|
||||
* EL_INT(v) identity — el_val_t is already int64_t
|
||||
* EL_NULL null / zero value
|
||||
* EL_FALSE boolean false (0)
|
||||
* EL_TRUE boolean true (1)
|
||||
*
|
||||
* Link requirements:
|
||||
* -lcurl — required for the HTTP client (http_get, http_post, llm_*).
|
||||
@@ -56,8 +53,6 @@ typedef int64_t el_val_t;
|
||||
#define EL_CSTR(v) ((const char*)(uintptr_t)(v))
|
||||
#define EL_INT(v) (v)
|
||||
#define EL_NULL ((el_val_t)0)
|
||||
#define EL_FALSE ((el_val_t)0)
|
||||
#define EL_TRUE ((el_val_t)1)
|
||||
|
||||
/* Float values share the el_val_t (int64) slot via a bit-cast.
|
||||
* The codegen emits Float literals as `el_from_float(<dbl>)` so the
|
||||
@@ -81,8 +76,8 @@ extern "C" {
|
||||
|
||||
/* ── I/O ──────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t println(el_val_t s);
|
||||
el_val_t print(el_val_t s);
|
||||
void println(el_val_t s);
|
||||
void print(el_val_t s);
|
||||
el_val_t readline(void);
|
||||
|
||||
/* ── String builtins ─────────────────────────────────────────────────────── */
|
||||
@@ -95,7 +90,6 @@ el_val_t str_len(el_val_t s);
|
||||
el_val_t str_concat(el_val_t a, el_val_t b);
|
||||
el_val_t int_to_str(el_val_t n);
|
||||
el_val_t str_to_int(el_val_t s);
|
||||
el_val_t native_str_to_int(el_val_t s);
|
||||
el_val_t str_slice(el_val_t s, el_val_t start, el_val_t end);
|
||||
el_val_t str_contains(el_val_t s, el_val_t sub);
|
||||
el_val_t str_replace(el_val_t s, el_val_t from, el_val_t to);
|
||||
@@ -123,10 +117,6 @@ el_val_t el_min(el_val_t a, el_val_t b);
|
||||
void el_retain(el_val_t v);
|
||||
void el_release(el_val_t v);
|
||||
|
||||
/* ── Scoped arena (CLI use) ───────────────────────────────────────────────── */
|
||||
el_val_t el_arena_push(void);
|
||||
el_val_t el_arena_pop(el_val_t mark);
|
||||
|
||||
/* ── List ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_list_new(el_val_t count, ...);
|
||||
@@ -150,11 +140,10 @@ el_val_t http_post(el_val_t url, el_val_t body);
|
||||
el_val_t http_post_json(el_val_t url, el_val_t json_body);
|
||||
el_val_t http_get_with_headers(el_val_t url, el_val_t headers_map);
|
||||
el_val_t http_post_with_headers(el_val_t url, el_val_t body, el_val_t headers_map);
|
||||
el_val_t http_post_json_with_headers(el_val_t url, el_val_t headers_map, el_val_t json_body);
|
||||
el_val_t http_post_form_auth(el_val_t url, el_val_t form_body, el_val_t auth_header);
|
||||
el_val_t http_delete(el_val_t url);
|
||||
el_val_t http_serve(el_val_t port, el_val_t handler);
|
||||
el_val_t http_set_handler(el_val_t name);
|
||||
void http_serve(el_val_t port, el_val_t handler);
|
||||
void http_set_handler(el_val_t name);
|
||||
|
||||
/* HTTP server v2 ─────────────────────────────────────────────────────────────
|
||||
* Same dispatch model as http_serve, but the handler signature is widened:
|
||||
@@ -175,8 +164,8 @@ el_val_t http_set_handler(el_val_t name);
|
||||
* The 3-arg http_serve(port, handler) remains supported unchanged for
|
||||
* existing handlers (e.g. products/web/server.el): it dispatches with
|
||||
* (method, path, body), hardcodes 200 OK, and auto-detects content type. */
|
||||
el_val_t http_serve_v2(el_val_t port, el_val_t handler);
|
||||
el_val_t http_set_handler_v2(el_val_t name);
|
||||
void http_serve_v2(el_val_t port, el_val_t handler);
|
||||
void http_set_handler_v2(el_val_t name);
|
||||
|
||||
/* Build an HTTP response envelope. `headers_json` should be a JSON object
|
||||
* literal like `{"WWW-Authenticate":"Basic"}` (or "" / "{}" for none). The
|
||||
@@ -187,11 +176,6 @@ el_val_t http_set_handler_v2(el_val_t name);
|
||||
* auto-content-type contract for legacy handlers that return plain bodies. */
|
||||
el_val_t http_response(el_val_t status, el_val_t headers_json, el_val_t body);
|
||||
|
||||
/* SSE connection fd — set by http_worker_v2 before calling the El handler,
|
||||
* cleared afterwards. Defined in el_seed.c; called from el_runtime.c.
|
||||
* The getter is exposed as __http_conn_fd() to El programs. */
|
||||
void el_seed_set_http_conn_fd(int fd);
|
||||
|
||||
/* HTTP timeout — every libcurl request honors EL_HTTP_TIMEOUT_MS (default
|
||||
* 60000ms). Read lazily on first use, so setting the env var any time before
|
||||
* the first http_* call is sufficient. */
|
||||
@@ -227,15 +211,12 @@ el_val_t url_decode(el_val_t s); /* '+' → space, %XX → byte */
|
||||
* {"p":[],"a":["href","title"],"strong":[],...}
|
||||
* where each value is the array of attribute names allowed for that tag. */
|
||||
el_val_t el_html_sanitize(el_val_t input_html, el_val_t allowlist_json);
|
||||
el_val_t html_raw(el_val_t s);
|
||||
el_val_t html_escape(el_val_t s);
|
||||
|
||||
/* ── Filesystem ──────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t fs_read(el_val_t path);
|
||||
el_val_t fs_write(el_val_t path, el_val_t content);
|
||||
el_val_t fs_list(el_val_t path);
|
||||
el_val_t fs_list_json(el_val_t path);
|
||||
el_val_t fs_exists(el_val_t path);
|
||||
el_val_t fs_mkdir(el_val_t path); /* mkdir -p, mode 0755 */
|
||||
|
||||
@@ -265,9 +246,6 @@ el_val_t json_set(el_val_t json_str, el_val_t key, el_val_t value);
|
||||
el_val_t json_array_len(el_val_t json_str);
|
||||
el_val_t json_array_get(el_val_t json_str, el_val_t index);
|
||||
el_val_t json_array_get_string(el_val_t json_str, el_val_t index);
|
||||
el_val_t json_escape_string(el_val_t sv);
|
||||
el_val_t json_build_object(el_val_t kvs);
|
||||
el_val_t json_build_array(el_val_t items);
|
||||
|
||||
/* ── Time ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
@@ -280,7 +258,6 @@ el_val_t time_to_parts(el_val_t ts);
|
||||
el_val_t time_from_parts(el_val_t secs, el_val_t ns, el_val_t tz);
|
||||
el_val_t time_add(el_val_t ts, el_val_t n, el_val_t unit);
|
||||
el_val_t time_diff(el_val_t ts1, el_val_t ts2, el_val_t unit);
|
||||
el_val_t now_ns(void);
|
||||
|
||||
/* ── Instant + Duration: first-class temporal types ──────────────────────────
|
||||
* Both types share the el_val_t (int64) slot. Instants are nanoseconds
|
||||
@@ -437,8 +414,6 @@ el_val_t state_set(el_val_t key, el_val_t value);
|
||||
el_val_t state_get(el_val_t key);
|
||||
el_val_t state_del(el_val_t key);
|
||||
el_val_t state_keys(void);
|
||||
el_val_t state_has(el_val_t key);
|
||||
el_val_t state_get_or(el_val_t key, el_val_t default_val);
|
||||
|
||||
/* ── Float formatting ────────────────────────────────────────────────────── */
|
||||
|
||||
@@ -530,15 +505,9 @@ el_val_t parse_int(el_val_t s, el_val_t default_val);
|
||||
|
||||
/* ── Process ─────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t exit_program(el_val_t code);
|
||||
void exit_program(el_val_t code);
|
||||
el_val_t getpid_now(void);
|
||||
|
||||
/* Self-terminating memory guard. Reads ELC_MAX_MEM_MB (default 512) and
|
||||
* exits with code 1 if resident memory exceeds the limit. Call periodically
|
||||
* during long compilation loops (e.g. after each function is compiled).
|
||||
* Returns 0 when memory is within bounds. */
|
||||
el_val_t el_mem_check(void);
|
||||
|
||||
/* ── CGI identity ─────────────────────────────────────────────────────────────
|
||||
* Called at the start of main() in CGI programs (those with a `cgi {}` block).
|
||||
* Records the program's DHARMA identity before any other code executes. */
|
||||
@@ -776,108 +745,12 @@ el_val_t exec_capture(el_val_t cmd); /* run shell command, capture stdout */
|
||||
el_val_t exec(el_val_t cmd); /* exec(cmd) → stdout String (30s timeout) */
|
||||
el_val_t exec_bg(el_val_t cmd); /* exec_bg(cmd) → PID String (non-blocking) */
|
||||
|
||||
/* ── Stdout redirection (used by compiler JS pipeline) ───────────────────── */
|
||||
el_val_t stdout_to_file(el_val_t path); /* redirect process stdout to a file */
|
||||
el_val_t stdout_restore(void); /* restore process stdout to terminal */
|
||||
|
||||
el_val_t emit_log(el_val_t level, el_val_t msg, el_val_t fields_json);
|
||||
el_val_t emit_metric(el_val_t name, el_val_t value, el_val_t tags_json);
|
||||
el_val_t trace_span_start(el_val_t name);
|
||||
el_val_t trace_span_end(el_val_t span_handle);
|
||||
el_val_t emit_event(el_val_t name, el_val_t duration_ms);
|
||||
|
||||
el_val_t __thread_create(el_val_t fn_name_v, el_val_t arg_v);
|
||||
el_val_t __thread_join(el_val_t tid_v);
|
||||
|
||||
/* ── __ prefixed aliases (self-hosting compiler ABI) ─────────────────────────
|
||||
* The El self-hosting compiler emits calls to __-prefixed names. These are
|
||||
* forwarding wrappers around the existing el_runtime functions above. */
|
||||
|
||||
/* I/O */
|
||||
el_val_t __println(el_val_t s);
|
||||
el_val_t __print(el_val_t s);
|
||||
el_val_t __readline(void);
|
||||
|
||||
/* String */
|
||||
el_val_t __int_to_str(el_val_t n);
|
||||
el_val_t __str_to_int(el_val_t s);
|
||||
el_val_t __float_to_str(el_val_t f);
|
||||
el_val_t __str_to_float(el_val_t s);
|
||||
el_val_t __str_len(el_val_t s);
|
||||
el_val_t __str_char_at(el_val_t s, el_val_t i);
|
||||
el_val_t __str_cmp(el_val_t a, el_val_t b);
|
||||
el_val_t __str_ncmp(el_val_t a, el_val_t b, el_val_t n);
|
||||
el_val_t __str_concat_raw(el_val_t a, el_val_t b);
|
||||
el_val_t __str_slice_raw(el_val_t s, el_val_t start, el_val_t end);
|
||||
el_val_t __str_alloc(el_val_t n);
|
||||
el_val_t __str_set_char(el_val_t s, el_val_t i, el_val_t c);
|
||||
|
||||
/* URL encoding */
|
||||
el_val_t __url_encode(el_val_t s);
|
||||
el_val_t __url_decode(el_val_t s);
|
||||
|
||||
/* Environment */
|
||||
el_val_t __env_get(el_val_t key);
|
||||
|
||||
/* Subprocess */
|
||||
el_val_t __exec(el_val_t cmd);
|
||||
el_val_t __exec_bg(el_val_t cmd);
|
||||
|
||||
/* Process */
|
||||
el_val_t __exit_program(el_val_t code);
|
||||
|
||||
/* Filesystem */
|
||||
el_val_t __fs_exists(el_val_t path);
|
||||
el_val_t __fs_mkdir(el_val_t path);
|
||||
el_val_t __fs_read(el_val_t path);
|
||||
el_val_t __fs_write(el_val_t path, el_val_t content);
|
||||
el_val_t __fs_write_bytes(el_val_t path, el_val_t bytes, el_val_t n);
|
||||
el_val_t __fs_list_raw(el_val_t path);
|
||||
|
||||
/* HTTP server */
|
||||
el_val_t __http_response(el_val_t status, el_val_t headers_json, el_val_t body);
|
||||
el_val_t __http_serve(el_val_t port, el_val_t handler);
|
||||
el_val_t __http_serve_v2(el_val_t port, el_val_t handler);
|
||||
|
||||
/* HTTP conn fd / SSE (weak; overridden by el_seed.c when linked together) */
|
||||
el_val_t __http_conn_fd(void);
|
||||
el_val_t __http_sse_open(el_val_t conn_id);
|
||||
el_val_t __http_sse_send(el_val_t conn_id, el_val_t data);
|
||||
el_val_t __http_sse_close(el_val_t conn_id);
|
||||
|
||||
/* HTTP client (requires HAVE_CURL; stubs provided for no-curl builds) */
|
||||
el_val_t __http_do(el_val_t method, el_val_t url, el_val_t body,
|
||||
el_val_t headers_map, el_val_t timeout_ms);
|
||||
el_val_t __http_do_map(el_val_t method, el_val_t url, el_val_t body,
|
||||
el_val_t headers_json, el_val_t timeout_ms);
|
||||
el_val_t __http_do_map_to_file(el_val_t method, el_val_t url, el_val_t body,
|
||||
el_val_t headers_json, el_val_t output_path);
|
||||
|
||||
/* JSON */
|
||||
el_val_t __json_array_get(el_val_t json, el_val_t index);
|
||||
el_val_t __json_array_get_string(el_val_t json, el_val_t index);
|
||||
el_val_t __json_array_len(el_val_t json);
|
||||
el_val_t __json_get(el_val_t json, el_val_t key);
|
||||
el_val_t __json_get_raw(el_val_t json, el_val_t key);
|
||||
el_val_t __json_set(el_val_t json, el_val_t key, el_val_t value);
|
||||
el_val_t __json_parse_map(el_val_t json_str);
|
||||
el_val_t __json_stringify_val(el_val_t val);
|
||||
|
||||
/* Hashing */
|
||||
el_val_t __sha256_hex(el_val_t s);
|
||||
|
||||
/* State K/V */
|
||||
el_val_t __state_del(el_val_t key);
|
||||
el_val_t __state_get(el_val_t key);
|
||||
el_val_t __state_keys(void);
|
||||
el_val_t __state_set(el_val_t key, el_val_t val);
|
||||
|
||||
/* UUID */
|
||||
el_val_t __uuid_v4(void);
|
||||
|
||||
/* Args */
|
||||
el_val_t __args_json(void);
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
@@ -948,6 +948,10 @@ fn js_cg_stmt(stmt: Map<String, Any>, indent: String, declared: [String]) -> [St
|
||||
if kind == "TypeDef" { return declared }
|
||||
if kind == "EnumDef" { return declared }
|
||||
if kind == "Import" { return declared }
|
||||
// TestDef: skip in normal mode; handled by js_codegen_test in test mode.
|
||||
if kind == "TestDef" { return declared }
|
||||
// Assert: no-op in normal mode; handled by js_cg_stmt_assert in test mode.
|
||||
if kind == "Assert" { return declared }
|
||||
|
||||
if kind == "TryCatch" {
|
||||
let try_body = stmt["try_body"]
|
||||
@@ -1168,20 +1172,178 @@ fn js_is_top_level_decl(stmt: Map<String, Any>) -> Bool {
|
||||
if kind == "CgiBlock" { return true }
|
||||
if kind == "ServiceBlock" { return true }
|
||||
if kind == "ExternFn" { return true }
|
||||
if kind == "TestDef" { return true }
|
||||
false
|
||||
}
|
||||
|
||||
// ── Test mode codegen (JS) ────────────────────────────────────────────────────
|
||||
//
|
||||
// reporter = "text" → human-readable output to stderr (console.error)
|
||||
// reporter = "json" → newline-delimited JSON to stdout (process.stdout.write)
|
||||
//
|
||||
// The test function returns bool: true = pass, false = fail.
|
||||
|
||||
fn js_cg_stmt_assert_text(stmt: Map<String, Any>, test_name: String) -> Void {
|
||||
let expr_node = stmt["expr"]
|
||||
let msg: String = stmt["msg"]
|
||||
let expr_c: String = js_cg_expr(expr_node)
|
||||
let disp_msg = "assert failed"
|
||||
if !str_eq(msg, "") { let disp_msg = msg }
|
||||
js_emit_line(" if (!(" + expr_c + ")) {")
|
||||
js_emit_line(" process.stderr.write(\" FAIL " + js_escape(test_name) + " — " + js_escape(disp_msg) + "\\n\");")
|
||||
js_emit_line(" return false;")
|
||||
js_emit_line(" }")
|
||||
}
|
||||
|
||||
fn js_cg_stmt_assert_json(stmt: Map<String, Any>, test_name: String, file_name: String, test_line: Int) -> Void {
|
||||
let expr_node = stmt["expr"]
|
||||
let msg: String = stmt["msg"]
|
||||
let assert_line: Int = stmt["line"]
|
||||
let expr_c: String = js_cg_expr(expr_node)
|
||||
let disp_msg = "assert failed"
|
||||
if !str_eq(msg, "") { let disp_msg = msg }
|
||||
js_emit_line(" if (!(" + expr_c + ")) {")
|
||||
js_emit_line(" process.stdout.write(JSON.stringify({type:\"test_fail\",name:" + js_str_lit(test_name) + ",file:" + js_str_lit(file_name) + ",line:" + native_int_to_str(test_line) + ",assert_line:" + native_int_to_str(assert_line) + ",message:" + js_str_lit(disp_msg) + "}) + \"\\n\");")
|
||||
js_emit_line(" return false;")
|
||||
js_emit_line(" }")
|
||||
}
|
||||
|
||||
// js_cg_stmts_in_test: emit test body, routing Assert to the right handler.
|
||||
fn js_cg_stmts_in_test(stmts: [Map<String, Any>], indent: String, declared: [String], test_name: String, reporter: String, file_name: String, test_line: Int) -> [String] {
|
||||
let n: Int = native_list_len(stmts)
|
||||
let i = 0
|
||||
let decl = declared
|
||||
while i < n {
|
||||
let stmt = native_list_get(stmts, i)
|
||||
let sk: String = stmt["stmt"]
|
||||
if str_eq(sk, "Assert") {
|
||||
if str_eq(reporter, "json") {
|
||||
js_cg_stmt_assert_json(stmt, test_name, file_name, test_line)
|
||||
} else {
|
||||
js_cg_stmt_assert_text(stmt, test_name)
|
||||
}
|
||||
} else {
|
||||
let decl = js_cg_stmt(stmt, indent, decl)
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
decl
|
||||
}
|
||||
|
||||
// js_cg_test_fn: emit a single async test function.
|
||||
fn js_cg_test_fn(test_def: Map<String, Any>, idx: Int, reporter: String, file_name: String) -> String {
|
||||
let fn_name: String = "el_test_" + native_int_to_str(idx)
|
||||
let test_name: String = test_def["name"]
|
||||
let test_line: Int = test_def["line"]
|
||||
let body = test_def["body"]
|
||||
js_emit_line("async function " + fn_name + "() {")
|
||||
js_cg_stmts_in_test(body, " ", native_list_empty(), test_name, reporter, file_name, test_line)
|
||||
js_emit_line(" return true;")
|
||||
js_emit_line("}")
|
||||
js_emit_blank()
|
||||
fn_name
|
||||
}
|
||||
|
||||
// js_codegen_test: emit the test runner (replaces main() when --test active).
|
||||
// reporter: "text" or "json"
|
||||
// file_name: basename of the source file (used in JSON output)
|
||||
fn js_codegen_test(stmts: [Map<String, Any>], reporter: String, file_name: String) -> Void {
|
||||
// Collect TestDef nodes in order.
|
||||
let n: Int = native_list_len(stmts)
|
||||
let test_defs: [Map<String, Any>] = native_list_empty()
|
||||
let i = 0
|
||||
while i < n {
|
||||
let stmt = native_list_get(stmts, i)
|
||||
let sk: String = stmt["stmt"]
|
||||
if str_eq(sk, "TestDef") {
|
||||
let test_defs = native_list_append(test_defs, stmt)
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
let n_tests: Int = native_list_len(test_defs)
|
||||
|
||||
// Emit non-test function definitions (skip fn main and TestDef nodes).
|
||||
let i = 0
|
||||
while i < n {
|
||||
let stmt = native_list_get(stmts, i)
|
||||
if js_is_fndef(stmt) {
|
||||
let fn_name: String = stmt["name"]
|
||||
if !str_eq(fn_name, "main") {
|
||||
js_cg_fn(stmt)
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Emit each test function.
|
||||
let ti = 0
|
||||
while ti < n_tests {
|
||||
let test_def = native_list_get(test_defs, ti)
|
||||
js_cg_test_fn(test_def, ti, reporter, file_name)
|
||||
let ti = ti + 1
|
||||
}
|
||||
|
||||
// Emit the test runner IIFE.
|
||||
let test_word = "tests"
|
||||
if n_tests == 1 { let test_word = "test" }
|
||||
js_emit_line("(async () => {")
|
||||
js_emit_line(" let pass = 0; let fail = 0;")
|
||||
|
||||
if str_eq(reporter, "json") {
|
||||
// JSON reporter: suite_start to stdout
|
||||
js_emit_line(" process.stdout.write(JSON.stringify({type:\"suite_start\",file:" + js_str_lit(file_name) + ",total:" + native_int_to_str(n_tests) + "}) + \"\\n\");")
|
||||
let ti = 0
|
||||
while ti < n_tests {
|
||||
let test_def = native_list_get(test_defs, ti)
|
||||
let test_name: String = test_def["name"]
|
||||
let test_line: Int = test_def["line"]
|
||||
let fn_name: String = "el_test_" + native_int_to_str(ti)
|
||||
js_emit_line(" process.stdout.write(JSON.stringify({type:\"test_start\",name:" + js_str_lit(test_name) + ",file:" + js_str_lit(file_name) + ",line:" + native_int_to_str(test_line) + "}) + \"\\n\");")
|
||||
js_emit_line(" if (await " + fn_name + "()) {")
|
||||
js_emit_line(" pass++;")
|
||||
js_emit_line(" process.stdout.write(JSON.stringify({type:\"test_pass\",name:" + js_str_lit(test_name) + ",file:" + js_str_lit(file_name) + ",line:" + native_int_to_str(test_line) + ",duration_ms:0}) + \"\\n\");")
|
||||
js_emit_line(" } else { fail++; }")
|
||||
let ti = ti + 1
|
||||
}
|
||||
js_emit_line(" process.stdout.write(JSON.stringify({type:\"suite_end\",passed:pass,failed:fail}) + \"\\n\");")
|
||||
} else {
|
||||
// Text reporter: human-readable to stderr
|
||||
js_emit_line(" process.stderr.write(\"==> running " + native_int_to_str(n_tests) + " " + test_word + "\\n\\n\");")
|
||||
let ti = 0
|
||||
while ti < n_tests {
|
||||
let test_def = native_list_get(test_defs, ti)
|
||||
let test_name: String = test_def["name"]
|
||||
let fn_name: String = "el_test_" + native_int_to_str(ti)
|
||||
js_emit_line(" process.stderr.write(\" RUN " + js_escape(test_name) + "\\n\");")
|
||||
js_emit_line(" if (await " + fn_name + "()) { pass++; process.stderr.write(\" PASS " + js_escape(test_name) + "\\n\"); }")
|
||||
js_emit_line(" else { fail++; }")
|
||||
let ti = ti + 1
|
||||
}
|
||||
js_emit_line(" process.stderr.write(\"\\n\" + pass + \" passed, \" + fail + \" failed\\n\");")
|
||||
}
|
||||
|
||||
js_emit_line(" process.exit(fail > 0 ? 1 : 0);")
|
||||
js_emit_line("})();")
|
||||
}
|
||||
|
||||
// ── Entry point ───────────────────────────────────────────────────────────────
|
||||
|
||||
fn codegen_js(stmts: [Map<String, Any>], source: String) -> String {
|
||||
codegen_js_inner(stmts, source, false, "")
|
||||
codegen_js_inner(stmts, source, false, "", false, "text", "")
|
||||
}
|
||||
|
||||
// codegen_js_test: emit a JS test binary.
|
||||
// reporter: "text" or "json"
|
||||
// file_name: basename of the source file (used in JSON output)
|
||||
fn codegen_js_test(stmts: [Map<String, Any>], source: String, reporter: String, file_name: String) -> String {
|
||||
codegen_js_inner(stmts, source, false, "", true, reporter, file_name)
|
||||
}
|
||||
|
||||
fn codegen_js_bundle(stmts: [Map<String, Any>], source: String, runtime_content: String) -> String {
|
||||
codegen_js_inner(stmts, source, true, runtime_content)
|
||||
codegen_js_inner(stmts, source, true, runtime_content, false, "text", "")
|
||||
}
|
||||
|
||||
fn codegen_js_inner(stmts: [Map<String, Any>], source: String, bundle_mode: Bool, runtime_content: String) -> String {
|
||||
fn codegen_js_inner(stmts: [Map<String, Any>], source: String, bundle_mode: Bool, runtime_content: String, test_mode: Bool, reporter: String, file_name: String) -> String {
|
||||
// Reset per-compile state.
|
||||
state_set("__js_int_names", "")
|
||||
state_set("__js_match_counter", "")
|
||||
@@ -1202,7 +1364,7 @@ fn codegen_js_inner(stmts: [Map<String, Any>], source: String, bundle_mode: Bool
|
||||
js_emit_line(js_strip_es_exports(runtime_content))
|
||||
js_emit_line("")
|
||||
} else {
|
||||
js_emit_line("// Runtime: foundation/el/runtime/el_runtime.js")
|
||||
js_emit_line("// Runtime: foundation/el/el-compiler/runtime/el_runtime.js")
|
||||
js_emit_line("import \"./el_runtime.js\";")
|
||||
}
|
||||
// In module mode: destructure all builtins off globalThis.__el so call
|
||||
@@ -1292,6 +1454,12 @@ fn codegen_js_inner(stmts: [Map<String, Any>], source: String, bundle_mode: Bool
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// Test mode: emit test functions and runner, skip normal program logic.
|
||||
if test_mode {
|
||||
js_codegen_test(stmts, reporter, file_name)
|
||||
return ""
|
||||
}
|
||||
|
||||
// Function definitions
|
||||
let i = 0
|
||||
while i < n {
|
||||
File diff suppressed because it is too large
Load Diff
@@ -20,44 +20,18 @@ import "codegen.el"
|
||||
import "codegen-js.el"
|
||||
|
||||
// compile — full pipeline (C target): source string -> C source string
|
||||
// Uses JIT function-at-a-time streaming: parse one decl → emit C → discard AST.
|
||||
// Peak memory is O(one function's AST) instead of O(whole program AST).
|
||||
fn compile(source: String) -> String {
|
||||
// Top-level arena scope: activates the string arena before lex() so that
|
||||
// ALL strdup allocations (token strings, sig strings, codegen fragments)
|
||||
// are tracked and freed on pop. Without this, lex() and scan_fn_sigs()
|
||||
// run before any push, leaving _tl_arena_active=0 and leaking every
|
||||
// token string. Also prevents inner pop(mark=0) calls from deactivating
|
||||
// the arena between per-function scopes.
|
||||
let top_mark: Any = el_arena_push()
|
||||
let tokens: [Any] = lex(source)
|
||||
// Fast pre-scan: collect fn signatures + program kind without building
|
||||
// full expression ASTs. O(tokens) time, minimal allocation.
|
||||
let sigs: [Map<String, Any>] = scan_fn_sigs(tokens)
|
||||
// Stream parse-emit: parse one decl at a time, emit C, discard.
|
||||
// All output written to stdout via println before pop.
|
||||
codegen_streaming(tokens, sigs, source)
|
||||
el_arena_pop(top_mark)
|
||||
""
|
||||
}
|
||||
|
||||
// compile_test — like compile() but sets __test_mode so codegen_streaming
|
||||
// compiles test { } blocks instead of skipping them, and emits the test
|
||||
// harness main() instead of the normal int main().
|
||||
fn compile_test(source: String) -> String {
|
||||
state_set("__test_mode", "1")
|
||||
let top_mark: Any = el_arena_push()
|
||||
let tokens: [Any] = lex(source)
|
||||
let sigs: [Map<String, Any>] = scan_fn_sigs(tokens)
|
||||
codegen_streaming(tokens, sigs, source)
|
||||
el_arena_pop(top_mark)
|
||||
state_set("__test_mode", "")
|
||||
""
|
||||
let tokens: [Map<String, Any>] = lex(source)
|
||||
let stmts: [Map<String, Any>] = parse(tokens)
|
||||
// Token list is no longer needed after parsing — release it to free memory
|
||||
// before codegen allocates its own working data on large source files.
|
||||
el_release(tokens)
|
||||
codegen(stmts, source)
|
||||
}
|
||||
|
||||
// compile_js — full pipeline (JS target, module mode): source string -> JS source string
|
||||
fn compile_js(source: String) -> String {
|
||||
let tokens: [Any] = lex(source)
|
||||
let tokens: [Map<String, Any>] = lex(source)
|
||||
let stmts: [Map<String, Any>] = parse(tokens)
|
||||
// Token list is no longer needed after parsing — release it to free memory.
|
||||
el_release(tokens)
|
||||
@@ -67,7 +41,7 @@ fn compile_js(source: String) -> String {
|
||||
// compile_js_with_bundle — JS target in bundle mode.
|
||||
// Reads el_runtime.js from runtime_path and inlines it inside an IIFE.
|
||||
fn compile_js_with_bundle(source: String, runtime_path: String) -> String {
|
||||
let tokens: [Any] = lex(source)
|
||||
let tokens: [Map<String, Any>] = lex(source)
|
||||
let stmts: [Map<String, Any>] = parse(tokens)
|
||||
el_release(tokens)
|
||||
let runtime_content: String = fs_read(runtime_path)
|
||||
@@ -78,6 +52,24 @@ fn compile_js_with_bundle(source: String, runtime_path: String) -> String {
|
||||
codegen_js_bundle(stmts, source, runtime_content)
|
||||
}
|
||||
|
||||
// compile_test — full pipeline (C target, test mode): source -> C test runner.
|
||||
// reporter: "text" or "json"; file_name: basename of the source file.
|
||||
fn compile_test(source: String, reporter: String, file_name: String) -> String {
|
||||
let tokens: [Map<String, Any>] = lex(source)
|
||||
let stmts: [Map<String, Any>] = parse(tokens)
|
||||
el_release(tokens)
|
||||
codegen_with_tests(stmts, source, reporter, file_name)
|
||||
}
|
||||
|
||||
// compile_js_test — full pipeline (JS target, test mode): source -> JS test runner.
|
||||
// reporter: "text" or "json"; file_name: basename of the source file.
|
||||
fn compile_js_test(source: String, reporter: String, file_name: String) -> String {
|
||||
let tokens: [Map<String, Any>] = lex(source)
|
||||
let stmts: [Map<String, Any>] = parse(tokens)
|
||||
el_release(tokens)
|
||||
codegen_js_test(stmts, source, reporter, file_name)
|
||||
}
|
||||
|
||||
// compile_dispatch — pick a backend based on the requested target.
|
||||
// tgt = "c" | "js"
|
||||
// (The parameter is named `tgt` because `target` is a reserved keyword
|
||||
@@ -88,6 +80,13 @@ fn compile_dispatch(tgt: String, source: String) -> String {
|
||||
compile(source)
|
||||
}
|
||||
|
||||
// compile_dispatch_test — pick test-mode backend.
|
||||
// reporter: "text" or "json"; file_name: basename of the source file.
|
||||
fn compile_dispatch_test(tgt: String, source: String, reporter: String, file_name: String) -> String {
|
||||
if str_eq(tgt, "js") { return compile_js_test(source, reporter, file_name) }
|
||||
compile_test(source, reporter, file_name)
|
||||
}
|
||||
|
||||
// compile_dispatch_bundle — like compile_dispatch but bundle mode for JS.
|
||||
fn compile_dispatch_bundle(tgt: String, source: String, runtime_path: String) -> String {
|
||||
if str_eq(tgt, "js") { return compile_js_with_bundle(source, runtime_path) }
|
||||
@@ -185,6 +184,36 @@ fn detect_test(argv: [String]) -> Bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// Detect --reporter=<value> flag in argv.
|
||||
// Returns "json" if --reporter=json, otherwise "text" (default).
|
||||
fn detect_reporter(argv: [String]) -> String {
|
||||
let n: Int = native_list_len(argv)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let a: String = native_list_get(argv, i)
|
||||
if str_starts_with(a, "--reporter=") {
|
||||
let v: String = str_slice(a, 11, str_len(a))
|
||||
return v
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
return "text"
|
||||
}
|
||||
|
||||
// basename_of — extract the filename portion of a path (after last '/').
|
||||
fn basename_of(path: String) -> String {
|
||||
let n: Int = str_len(path)
|
||||
let i: Int = n - 1
|
||||
while i >= 0 {
|
||||
let c: String = str_slice(path, i, i + 1)
|
||||
if str_eq(c, "/") {
|
||||
return str_slice(path, i + 1, n)
|
||||
}
|
||||
let i = i - 1
|
||||
}
|
||||
return path
|
||||
}
|
||||
|
||||
// Build a unique temp file path: /tmp/elc-<pid>-<timestamp>.<suffix>
|
||||
fn make_temp_path(suffix: String) -> String {
|
||||
let pid: Int = getpid_now()
|
||||
@@ -287,9 +316,6 @@ fn type_node_to_el(t: Map<String, Any>) -> String {
|
||||
|
||||
// emit_header — write a .elh file from parsed statements.
|
||||
// Scans for FnDef nodes and emits 'extern fn' declarations.
|
||||
// NOTE: This function requires the full AST. Prefer emit_header_from_sigs
|
||||
// for the --emit-header path — it works from a token-level scan without
|
||||
// building expression ASTs, avoiding OOM on large files.
|
||||
fn emit_header(stmts: [Map<String, Any>], hdr_path: String) -> Void {
|
||||
let n: Int = native_list_len(stmts)
|
||||
let i = 0
|
||||
@@ -328,32 +354,6 @@ fn emit_header(stmts: [Map<String, Any>], hdr_path: String) -> Void {
|
||||
let ok: Bool = fs_write(hdr_path, content)
|
||||
}
|
||||
|
||||
// emit_header_from_sigs — write a .elh file from pre-scanned El signatures.
|
||||
// Uses the output of scan_fn_sigs_el() — no full AST required.
|
||||
// Peak memory is O(tokens) rather than O(whole-program AST), which prevents
|
||||
// OOM on large files with HTML template bodies or deep BinOp chains.
|
||||
fn emit_header_from_sigs(sigs: [Map<String, Any>], hdr_path: String) -> Void {
|
||||
let n: Int = native_list_len(sigs)
|
||||
let i: Int = 0
|
||||
let parts: [String] = native_list_empty()
|
||||
let parts = native_list_append(parts, "// auto-generated by elc --emit-header — do not edit\n")
|
||||
while i < n {
|
||||
let sig = native_list_get(sigs, i)
|
||||
let kind: String = sig["kind"]
|
||||
if str_eq(kind, "fn") {
|
||||
let name: String = sig["name"]
|
||||
let params_el: String = sig["params_el"]
|
||||
let ret_el: String = sig["ret_el"]
|
||||
if str_eq(ret_el, "") { let ret_el = "Any" }
|
||||
let line: String = "extern fn " + name + "(" + params_el + ") -> " + ret_el
|
||||
let parts = native_list_append(parts, line + "\n")
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
let content: String = str_join(parts, "")
|
||||
let ok: Bool = fs_write(hdr_path, content)
|
||||
}
|
||||
|
||||
// ── Import resolution ────────────────────────────────────────────────────────
|
||||
//
|
||||
// elc supports two forms of import:
|
||||
@@ -419,22 +419,6 @@ fn resolve_imports(src_path: String) -> String {
|
||||
if !str_eq(already, "") { return "" }
|
||||
state_set(seen_key, "1")
|
||||
|
||||
// A missing file must be a hard error, never an empty string.
|
||||
//
|
||||
// fs_read returns "" both for "file is empty" and "file does not exist", and
|
||||
// this function used the value without distinguishing them. So a broken
|
||||
// import path — a typo, a moved file, a relative path resolved from the
|
||||
// wrong working directory — compiled CLEANLY: exit 0, empty stderr, and a
|
||||
// program silently missing everything it imported. Observed 2026-08-15:
|
||||
// eleven consecutive "successful" compiles that had included no runtime at
|
||||
// all, and a wrong conclusion drawn from them before anyone noticed.
|
||||
//
|
||||
// Missing dependency, confident success. fs_exists separates the two cases,
|
||||
// so a genuinely empty file still resolves to "" and is fine.
|
||||
if !fs_exists(src_path) {
|
||||
println("elc: cannot resolve import: " + src_path)
|
||||
exit_program(1)
|
||||
}
|
||||
let source: String = fs_read(src_path)
|
||||
let dir: String = dirname_of(src_path)
|
||||
let lines: [String] = str_split(source, "\n")
|
||||
@@ -541,7 +525,9 @@ fn run_with_postprocess(tgt: String, source: String, src_path: String, do_bundle
|
||||
// main — CLI entry point.
|
||||
//
|
||||
// elc <source.el> # emit C to stdout
|
||||
// elc --test <source.el> # emit C test runner to stdout
|
||||
// elc --target=js <source.el> # emit JS (module) to stdout
|
||||
// elc --target=js --test <source.el> # emit JS test runner to stdout
|
||||
// elc --target=js --bundle <source.el> # emit self-contained JS (IIFE) to stdout
|
||||
// elc --target=js --bundle --minify <source.el> # emit minified IIFE to stdout
|
||||
// elc --target=js --bundle --obfuscate <source.el> # emit minified+obfuscated IIFE to stdout
|
||||
@@ -560,6 +546,7 @@ fn main() -> Void {
|
||||
let do_minify: Bool = detect_minify(argv)
|
||||
let do_obfuscate: Bool = detect_obfuscate(argv)
|
||||
let do_test: Bool = detect_test(argv)
|
||||
let reporter: String = detect_reporter(argv)
|
||||
// --obfuscate implies --minify: obfuscating unminified code is pointless.
|
||||
if do_obfuscate {
|
||||
let do_minify = true
|
||||
@@ -567,7 +554,7 @@ fn main() -> Void {
|
||||
let positional: [String] = strip_flags(argv)
|
||||
let argc: Int = native_list_len(positional)
|
||||
if argc < 1 {
|
||||
println("el-compiler: usage: elc [--target=c|js] [--bundle] [--minify] [--obfuscate] [--emit-header] [--test] <source.el> [<output>]")
|
||||
println("el-compiler: usage: elc [--target=c|js] [--test] [--reporter=text|json] [--bundle] [--minify] [--obfuscate] [--emit-header] <source.el> [<output>]")
|
||||
exit(1)
|
||||
}
|
||||
|
||||
@@ -581,23 +568,33 @@ fn main() -> Void {
|
||||
|
||||
let src_path: String = native_list_get(positional, 0)
|
||||
|
||||
// When --emit-header is requested, lex the source file and do a
|
||||
// token-level signature scan (no full AST) to write a .elh file.
|
||||
// This avoids OOM on large files with HTML template bodies or deep
|
||||
// BinOp chains (e.g. checkout.el) — parse() builds O(whole-program AST)
|
||||
// while scan_fn_sigs_el keeps peak memory at O(tokens).
|
||||
// When --emit-header is requested, parse the source file directly
|
||||
// (without inlining imports) and write out a .elh file alongside the .c.
|
||||
if do_emit_header {
|
||||
el_mem_check()
|
||||
let raw_source: String = fs_read(src_path)
|
||||
let hdr_tokens: [Any] = lex(raw_source)
|
||||
let hdr_sigs: [Map<String, Any>] = scan_fn_sigs_el(hdr_tokens)
|
||||
let hdr_tokens: [Map<String, Any>] = lex(raw_source)
|
||||
let hdr_stmts: [Map<String, Any>] = parse(hdr_tokens)
|
||||
el_release(hdr_tokens)
|
||||
let hdr_path: String = str_slice(src_path, 0, str_len(src_path) - 3) + ".elh"
|
||||
emit_header_from_sigs(hdr_sigs, hdr_path)
|
||||
el_release(hdr_sigs)
|
||||
emit_header(hdr_stmts, hdr_path)
|
||||
el_release(hdr_stmts)
|
||||
}
|
||||
|
||||
let source: String = resolve_imports(src_path)
|
||||
let file_name: String = basename_of(src_path)
|
||||
|
||||
// --test mode: emit a test runner binary instead of the normal program.
|
||||
if do_test {
|
||||
let out: String = compile_dispatch_test(tgt, source, reporter, file_name)
|
||||
if argc >= 2 {
|
||||
let out_path: String = native_list_get(positional, 1)
|
||||
let ok: Bool = fs_write(out_path, out)
|
||||
if ok { exit(0) }
|
||||
println("el-compiler: failed to write output")
|
||||
exit(1)
|
||||
}
|
||||
exit(0)
|
||||
}
|
||||
|
||||
// When post-processing (--minify or --obfuscate) is requested, redirect
|
||||
// stdout to a temp file so codegen output can be captured and piped through
|
||||
@@ -608,12 +605,6 @@ fn main() -> Void {
|
||||
exit(0)
|
||||
}
|
||||
|
||||
// --test mode: compile with test harness (C target only).
|
||||
if do_test {
|
||||
compile_test(source)
|
||||
exit(0)
|
||||
}
|
||||
|
||||
// Standard path (no post-processing).
|
||||
let out: String = ""
|
||||
if do_bundle {
|
||||
@@ -0,0 +1,763 @@
|
||||
// lexer.el — el self-hosting lexer
|
||||
//
|
||||
// Tokenises an el source string into a list of token maps.
|
||||
// Each token is a Map<String, Any> with keys:
|
||||
// "kind" -> String (e.g. "Int", "Ident", "Plus")
|
||||
// "value" -> String (the raw text of the token)
|
||||
//
|
||||
// Entry point: fn lex(source: String) -> [Map<String, Any>]
|
||||
//
|
||||
// Uses native_string_chars to split the source into a chars list,
|
||||
// then indexes it with native_list_get — avoids O(N²) string cloning.
|
||||
|
||||
// ── Character helpers ─────────────────────────────────────────────────────────
|
||||
|
||||
fn lex_is_digit(ch: String) -> Bool {
|
||||
if ch == "0" { return true }
|
||||
if ch == "1" { return true }
|
||||
if ch == "2" { return true }
|
||||
if ch == "3" { return true }
|
||||
if ch == "4" { return true }
|
||||
if ch == "5" { return true }
|
||||
if ch == "6" { return true }
|
||||
if ch == "7" { return true }
|
||||
if ch == "8" { return true }
|
||||
if ch == "9" { return true }
|
||||
false
|
||||
}
|
||||
|
||||
fn lex_is_alpha(ch: String) -> Bool {
|
||||
if ch == "a" { return true }
|
||||
if ch == "b" { return true }
|
||||
if ch == "c" { return true }
|
||||
if ch == "d" { return true }
|
||||
if ch == "e" { return true }
|
||||
if ch == "f" { return true }
|
||||
if ch == "g" { return true }
|
||||
if ch == "h" { return true }
|
||||
if ch == "i" { return true }
|
||||
if ch == "j" { return true }
|
||||
if ch == "k" { return true }
|
||||
if ch == "l" { return true }
|
||||
if ch == "m" { return true }
|
||||
if ch == "n" { return true }
|
||||
if ch == "o" { return true }
|
||||
if ch == "p" { return true }
|
||||
if ch == "q" { return true }
|
||||
if ch == "r" { return true }
|
||||
if ch == "s" { return true }
|
||||
if ch == "t" { return true }
|
||||
if ch == "u" { return true }
|
||||
if ch == "v" { return true }
|
||||
if ch == "w" { return true }
|
||||
if ch == "x" { return true }
|
||||
if ch == "y" { return true }
|
||||
if ch == "z" { return true }
|
||||
if ch == "A" { return true }
|
||||
if ch == "B" { return true }
|
||||
if ch == "C" { return true }
|
||||
if ch == "D" { return true }
|
||||
if ch == "E" { return true }
|
||||
if ch == "F" { return true }
|
||||
if ch == "G" { return true }
|
||||
if ch == "H" { return true }
|
||||
if ch == "I" { return true }
|
||||
if ch == "J" { return true }
|
||||
if ch == "K" { return true }
|
||||
if ch == "L" { return true }
|
||||
if ch == "M" { return true }
|
||||
if ch == "N" { return true }
|
||||
if ch == "O" { return true }
|
||||
if ch == "P" { return true }
|
||||
if ch == "Q" { return true }
|
||||
if ch == "R" { return true }
|
||||
if ch == "S" { return true }
|
||||
if ch == "T" { return true }
|
||||
if ch == "U" { return true }
|
||||
if ch == "V" { return true }
|
||||
if ch == "W" { return true }
|
||||
if ch == "X" { return true }
|
||||
if ch == "Y" { return true }
|
||||
if ch == "Z" { return true }
|
||||
false
|
||||
}
|
||||
|
||||
fn is_alnum_or_underscore(ch: String) -> Bool {
|
||||
if lex_is_digit(ch) { return true }
|
||||
if lex_is_alpha(ch) { return true }
|
||||
if ch == "_" { return true }
|
||||
false
|
||||
}
|
||||
|
||||
fn lex_is_whitespace(ch: String) -> Bool {
|
||||
if ch == " " { return true }
|
||||
if ch == "\t" { return true }
|
||||
if ch == "\n" { return true }
|
||||
if ch == "\r" { return true }
|
||||
false
|
||||
}
|
||||
|
||||
fn make_tok(kind: String, value: String) -> Map<String, Any> {
|
||||
let ln_s: String = state_get("__lex_line")
|
||||
let ln: Int = 1
|
||||
if !str_eq(ln_s, "") { let ln = str_to_int(ln_s) }
|
||||
{ "kind": kind, "value": value, "line": ln }
|
||||
}
|
||||
|
||||
// ── Keyword lookup ────────────────────────────────────────────────────────────
|
||||
|
||||
fn keyword_kind(word: String) -> String {
|
||||
if word == "let" { return "Let" }
|
||||
if word == "fn" { return "Fn" }
|
||||
if word == "type" { return "Type" }
|
||||
if word == "enum" { return "Enum" }
|
||||
if word == "match" { return "Match" }
|
||||
if word == "return" { return "Return" }
|
||||
if word == "if" { return "If" }
|
||||
if word == "else" { return "Else" }
|
||||
if word == "for" { return "For" }
|
||||
if word == "in" { return "In" }
|
||||
if word == "while" { return "While" }
|
||||
if word == "import" { return "Import" }
|
||||
if word == "from" { return "From" }
|
||||
if word == "as" { return "As" }
|
||||
if word == "with" { return "With" }
|
||||
if word == "sealed" { return "Sealed" }
|
||||
if word == "activate" { return "Activate" }
|
||||
if word == "where" { return "Where" }
|
||||
if word == "test" { return "Test" }
|
||||
if word == "seed" { return "Seed" }
|
||||
if word == "assert" { return "Assert" }
|
||||
if word == "protocol" { return "Protocol" }
|
||||
if word == "impl" { return "Impl" }
|
||||
if word == "retry" { return "Retry" }
|
||||
if word == "times" { return "Times" }
|
||||
if word == "fallback" { return "Fallback" }
|
||||
if word == "reason" { return "Reason" }
|
||||
if word == "parallel" { return "Parallel" }
|
||||
if word == "trace" { return "Trace" }
|
||||
if word == "requires" { return "Requires" }
|
||||
if word == "deploy" { return "Deploy" }
|
||||
if word == "to" { return "To" }
|
||||
if word == "via" { return "Via" }
|
||||
if word == "target" { return "Target" }
|
||||
if word == "true" { return "Bool" }
|
||||
if word == "false" { return "Bool" }
|
||||
if word == "cgi" { return "Cgi" }
|
||||
if word == "service" { return "Service" }
|
||||
if word == "manager" { return "Manager" }
|
||||
if word == "engine" { return "Engine" }
|
||||
if word == "accessor" { return "Accessor" }
|
||||
if word == "vessel" { return "Vessel" }
|
||||
if word == "extern" { return "Extern" }
|
||||
if word == "try" { return "Try" }
|
||||
if word == "catch" { return "Catch" }
|
||||
""
|
||||
}
|
||||
|
||||
// ── Scan helpers ──────────────────────────────────────────────────────────────
|
||||
// All scan helpers receive the chars list and total length.
|
||||
|
||||
// scan_digits — advance i while chars[i] is a digit
|
||||
// Returns { "text": ..., "pos": i }
|
||||
fn scan_digits(chars: [String], start: Int, total: Int) -> Map<String, Any> {
|
||||
let i = start
|
||||
let parts: [String] = native_list_empty()
|
||||
let running = true
|
||||
while running {
|
||||
if i >= total {
|
||||
let running = false
|
||||
} else {
|
||||
let ch: String = native_list_get(chars, i)
|
||||
if lex_is_digit(ch) {
|
||||
let parts = native_list_append(parts, ch)
|
||||
let i = i + 1
|
||||
} else {
|
||||
let running = false
|
||||
}
|
||||
}
|
||||
}
|
||||
{ "text": str_join(parts, ""), "pos": i }
|
||||
}
|
||||
|
||||
// scan_ident — advance i while chars[i] is alphanumeric or underscore
|
||||
fn scan_ident(chars: [String], start: Int, total: Int) -> Map<String, Any> {
|
||||
let i = start
|
||||
let parts: [String] = native_list_empty()
|
||||
let running = true
|
||||
while running {
|
||||
if i >= total {
|
||||
let running = false
|
||||
} else {
|
||||
let ch: String = native_list_get(chars, i)
|
||||
if is_alnum_or_underscore(ch) {
|
||||
let parts = native_list_append(parts, ch)
|
||||
let i = i + 1
|
||||
} else {
|
||||
let running = false
|
||||
}
|
||||
}
|
||||
}
|
||||
{ "text": str_join(parts, ""), "pos": i }
|
||||
}
|
||||
|
||||
// ── Code-bearing string detection + comment strip ────────────────────────────
|
||||
// Inline JS/CSS literals embedded in El source (e.g. <script>…</script> blobs
|
||||
// or stylesheet payloads inside string literals) carry their own line and
|
||||
// block comments. Those comments leak into the served HTML and reveal build
|
||||
// notes the visitor should never see. We strip them at the lexer so every
|
||||
// downstream consumer (codegen-c, codegen-js, parser) gets the cleaned form.
|
||||
//
|
||||
// looks_like_code — heuristic gate so we only strip strings that actually
|
||||
// embed JS or CSS. Plain prose, hex blobs, JSON, etc. pass through verbatim.
|
||||
|
||||
fn substr_at(chars: [String], start: Int, total: Int, needle: String) -> Bool {
|
||||
let nchars: [String] = native_string_chars(needle)
|
||||
let nlen: Int = native_list_len(nchars)
|
||||
if start + nlen > total { return false }
|
||||
let i = 0
|
||||
let matched = true
|
||||
while i < nlen {
|
||||
let a: String = native_list_get(chars, start + i)
|
||||
let b: String = native_list_get(nchars, i)
|
||||
if a == b { let i = i + 1 } else { let matched = false; let i = nlen }
|
||||
}
|
||||
matched
|
||||
}
|
||||
|
||||
fn str_has(s: String, needle: String) -> Bool {
|
||||
let chars: [String] = native_string_chars(s)
|
||||
let total: Int = native_list_len(chars)
|
||||
let i = 0
|
||||
let found = false
|
||||
while i < total {
|
||||
if substr_at(chars, i, total, needle) {
|
||||
let found = true
|
||||
let i = total
|
||||
} else {
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
found
|
||||
}
|
||||
|
||||
fn looks_like_code(s: String) -> Bool {
|
||||
if str_has(s, "<script") { return true }
|
||||
if str_has(s, "<style") { return true }
|
||||
if str_has(s, "function") {
|
||||
if str_has(s, ";") { return true }
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
// strip_code_comments — character-by-character walk. Tracks JS string state
|
||||
// (single, double, backtick) and never strips inside one. Backslash escapes
|
||||
// inside JS strings consume the next char verbatim. URLs like https:// are
|
||||
// preserved by checking the previous char before treating // as a line
|
||||
// comment opener: if the char immediately before '/' is ':', emit the '/'
|
||||
// literally and advance one position.
|
||||
fn strip_code_comments(s: String) -> String {
|
||||
let chars: [String] = native_string_chars(s)
|
||||
let total: Int = native_list_len(chars)
|
||||
let out_parts: [String] = native_list_empty()
|
||||
let i = 0
|
||||
let in_squote = false
|
||||
let in_dquote = false
|
||||
let in_btick = false
|
||||
let prev = ""
|
||||
while i < total {
|
||||
let ch: String = native_list_get(chars, i)
|
||||
let in_js_string = false
|
||||
if in_squote { let in_js_string = true }
|
||||
if in_dquote { let in_js_string = true }
|
||||
if in_btick { let in_js_string = true }
|
||||
|
||||
if in_js_string {
|
||||
// Backslash escape: consume next char verbatim regardless of which.
|
||||
if ch == "\\" {
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let next_i = i + 1
|
||||
if next_i < total {
|
||||
let nc: String = native_list_get(chars, next_i)
|
||||
let out_parts = native_list_append(out_parts, nc)
|
||||
let prev = nc
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
let prev = ch
|
||||
let i = next_i
|
||||
}
|
||||
} else {
|
||||
if in_squote {
|
||||
if ch == "'" { let in_squote = false }
|
||||
} else {
|
||||
if in_dquote {
|
||||
if ch == "\"" { let in_dquote = false }
|
||||
} else {
|
||||
if in_btick {
|
||||
if ch == "`" { let in_btick = false }
|
||||
}
|
||||
}
|
||||
}
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
// Not in a JS string. Check for comment openers.
|
||||
let next_i = i + 1
|
||||
let next_ch = ""
|
||||
if next_i < total {
|
||||
let next_ch: String = native_list_get(chars, next_i)
|
||||
}
|
||||
|
||||
if ch == "/" {
|
||||
if next_ch == "/" {
|
||||
// URL guard: prev char ':' means this is "://", not a comment.
|
||||
if prev == ":" {
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
} else {
|
||||
// Skip until newline (newline itself is preserved so
|
||||
// surrounding line counts/structure stay sane).
|
||||
let i = i + 2
|
||||
let scanning = true
|
||||
while scanning {
|
||||
if i >= total {
|
||||
let scanning = false
|
||||
} else {
|
||||
let lc: String = native_list_get(chars, i)
|
||||
if lc == "\n" {
|
||||
let scanning = false
|
||||
} else {
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
let prev = ""
|
||||
}
|
||||
} else {
|
||||
if next_ch == "*" {
|
||||
// Skip until matching "*/".
|
||||
let i = i + 2
|
||||
let scanning2 = true
|
||||
while scanning2 {
|
||||
if i >= total {
|
||||
let scanning2 = false
|
||||
} else {
|
||||
let bc: String = native_list_get(chars, i)
|
||||
if bc == "*" {
|
||||
let after = i + 1
|
||||
if after < total {
|
||||
let nc2: String = native_list_get(chars, after)
|
||||
if nc2 == "/" {
|
||||
let i = after + 1
|
||||
let scanning2 = false
|
||||
} else {
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
let prev = ""
|
||||
} else {
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
} else {
|
||||
// Open a JS string?
|
||||
if ch == "'" {
|
||||
let in_squote = true
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "\"" {
|
||||
let in_dquote = true
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "`" {
|
||||
let in_btick = true
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
} else {
|
||||
let out_parts = native_list_append(out_parts, ch)
|
||||
let prev = ch
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
str_join(out_parts, "")
|
||||
}
|
||||
|
||||
// scan_string — scan a quoted string literal, handling \" escapes.
|
||||
// Starts AFTER the opening quote. Returns { "text": content, "pos": i_after_close }
|
||||
fn scan_string(chars: [String], start: Int, total: Int) -> Map<String, Any> {
|
||||
let i = start
|
||||
let parts: [String] = native_list_empty()
|
||||
let running = true
|
||||
while running {
|
||||
if i >= total {
|
||||
let running = false
|
||||
} else {
|
||||
let ch: String = native_list_get(chars, i)
|
||||
if ch == "\\" {
|
||||
// escape: peek next char
|
||||
let next_i = i + 1
|
||||
if next_i < total {
|
||||
let next_ch: String = native_list_get(chars, next_i)
|
||||
if next_ch == "\"" {
|
||||
let parts = native_list_append(parts, "\"")
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
if next_ch == "n" {
|
||||
let parts = native_list_append(parts, "\n")
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
if next_ch == "t" {
|
||||
let parts = native_list_append(parts, "\t")
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
if next_ch == "r" {
|
||||
let parts = native_list_append(parts, "\r")
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
if next_ch == "\\" {
|
||||
let parts = native_list_append(parts, "\\")
|
||||
let i = next_i + 1
|
||||
} else {
|
||||
let parts = native_list_append(parts, next_ch)
|
||||
let i = next_i + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
} else {
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
if ch == "\"" {
|
||||
let i = i + 1
|
||||
let running = false
|
||||
} else {
|
||||
let parts = native_list_append(parts, ch)
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
{ "text": str_join(parts, ""), "pos": i }
|
||||
}
|
||||
|
||||
// ── Main lexer ────────────────────────────────────────────────────────────────
|
||||
|
||||
fn lex(source: String) -> [Map<String, Any>] {
|
||||
let chars: [String] = native_string_chars(source)
|
||||
let total: Int = native_list_len(chars)
|
||||
let tokens: [Map<String, Any>] = native_list_empty()
|
||||
let i: Int = 0
|
||||
let line_num: Int = 1
|
||||
state_set("__lex_line", "1")
|
||||
|
||||
while i < total {
|
||||
let ch: String = native_list_get(chars, i)
|
||||
|
||||
// Skip whitespace; track newlines for line-number reporting
|
||||
if lex_is_whitespace(ch) {
|
||||
if ch == "\n" {
|
||||
let line_num = line_num + 1
|
||||
state_set("__lex_line", native_int_to_str(line_num))
|
||||
}
|
||||
let i = i + 1
|
||||
} else {
|
||||
// Line comments: //
|
||||
if ch == "/" {
|
||||
let next_i = i + 1
|
||||
if next_i < total {
|
||||
let next_ch: String = native_list_get(chars, next_i)
|
||||
if next_ch == "/" {
|
||||
// skip to end of line
|
||||
let i = i + 2
|
||||
let running2 = true
|
||||
while running2 {
|
||||
if i >= total {
|
||||
let running2 = false
|
||||
} else {
|
||||
let lch: String = native_list_get(chars, i)
|
||||
if lch == "\n" {
|
||||
let running2 = false
|
||||
} else {
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Slash", "/"))
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Slash", "/"))
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
// String literal
|
||||
if ch == "\"" {
|
||||
let result = scan_string(chars, i + 1, total)
|
||||
let str_text: String = result["text"]
|
||||
let new_pos: Int = result["pos"]
|
||||
// Compile-time scrub: strings that embed JS or CSS get
|
||||
// their // line comments and /* block comments stripped
|
||||
// before the token reaches the parser. Plain prose passes
|
||||
// through untouched.
|
||||
let clean_text = str_text
|
||||
if looks_like_code(str_text) {
|
||||
let clean_text = strip_code_comments(str_text)
|
||||
}
|
||||
let tokens = native_list_append(tokens, make_tok("Str", clean_text))
|
||||
let i = new_pos
|
||||
} else {
|
||||
// Number literal
|
||||
if lex_is_digit(ch) {
|
||||
let result = scan_digits(chars, i, total)
|
||||
let num_text: String = result["text"]
|
||||
let new_pos: Int = result["pos"]
|
||||
// check for float (dot followed by digit)
|
||||
if new_pos < total {
|
||||
let dot_ch: String = native_list_get(chars, new_pos)
|
||||
if dot_ch == "." {
|
||||
let after_dot = new_pos + 1
|
||||
if after_dot < total {
|
||||
let after_dot_ch: String = native_list_get(chars, after_dot)
|
||||
if lex_is_digit(after_dot_ch) {
|
||||
let frac_result = scan_digits(chars, after_dot, total)
|
||||
let frac_text: String = frac_result["text"]
|
||||
let frac_pos: Int = frac_result["pos"]
|
||||
let tokens = native_list_append(tokens, make_tok("Float", num_text + "." + frac_text))
|
||||
let i = frac_pos
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Int", num_text))
|
||||
let i = new_pos
|
||||
}
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Int", num_text))
|
||||
let i = new_pos
|
||||
}
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Int", num_text))
|
||||
let i = new_pos
|
||||
}
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Int", num_text))
|
||||
let i = new_pos
|
||||
}
|
||||
} else {
|
||||
// Identifier or keyword
|
||||
if lex_is_alpha(ch) || ch == "_" {
|
||||
let result = scan_ident(chars, i, total)
|
||||
let word: String = result["text"]
|
||||
let new_pos: Int = result["pos"]
|
||||
let kw = keyword_kind(word)
|
||||
if kw == "" {
|
||||
let tokens = native_list_append(tokens, make_tok("Ident", word))
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok(kw, word))
|
||||
}
|
||||
let i = new_pos
|
||||
} else {
|
||||
// Multi-char and single-char operators/delimiters
|
||||
let peek_i = i + 1
|
||||
let peek_ch = ""
|
||||
if peek_i < total {
|
||||
let peek_ch: String = native_list_get(chars, peek_i)
|
||||
}
|
||||
|
||||
if ch == "=" {
|
||||
if peek_ch == "=" {
|
||||
let tokens = native_list_append(tokens, make_tok("EqEq", "=="))
|
||||
let i = i + 2
|
||||
} else {
|
||||
if peek_ch == ">" {
|
||||
let tokens = native_list_append(tokens, make_tok("FatArrow", "=>"))
|
||||
let i = i + 2
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Eq", "="))
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
} else {
|
||||
if ch == "!" {
|
||||
if peek_ch == "=" {
|
||||
let tokens = native_list_append(tokens, make_tok("NotEq", "!="))
|
||||
let i = i + 2
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Not", "!"))
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
if ch == "<" {
|
||||
if peek_ch == "=" {
|
||||
let tokens = native_list_append(tokens, make_tok("LtEq", "<="))
|
||||
let i = i + 2
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Lt", "<"))
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
if ch == ">" {
|
||||
if peek_ch == "=" {
|
||||
let tokens = native_list_append(tokens, make_tok("GtEq", ">="))
|
||||
let i = i + 2
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Gt", ">"))
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
if ch == "&" {
|
||||
if peek_ch == "&" {
|
||||
let tokens = native_list_append(tokens, make_tok("And", "&&"))
|
||||
let i = i + 2
|
||||
} else {
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
if ch == "|" {
|
||||
if peek_ch == "|" {
|
||||
let tokens = native_list_append(tokens, make_tok("Or", "||"))
|
||||
let i = i + 2
|
||||
} else {
|
||||
if peek_ch == ">" {
|
||||
let tokens = native_list_append(tokens, make_tok("PipeOp", "|>"))
|
||||
let i = i + 2
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Pipe", "|"))
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
} else {
|
||||
if ch == "-" {
|
||||
if peek_ch == ">" {
|
||||
let tokens = native_list_append(tokens, make_tok("Arrow", "->"))
|
||||
let i = i + 2
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Minus", "-"))
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
if ch == ":" {
|
||||
if peek_ch == ":" {
|
||||
let tokens = native_list_append(tokens, make_tok("ColonColon", "::"))
|
||||
let i = i + 2
|
||||
} else {
|
||||
let tokens = native_list_append(tokens, make_tok("Colon", ":"))
|
||||
let i = i + 1
|
||||
}
|
||||
} else {
|
||||
if ch == "+" {
|
||||
let tokens = native_list_append(tokens, make_tok("Plus", "+"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "*" {
|
||||
let tokens = native_list_append(tokens, make_tok("Star", "*"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "%" {
|
||||
let tokens = native_list_append(tokens, make_tok("Percent", "%"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "(" {
|
||||
let tokens = native_list_append(tokens, make_tok("LParen", "("))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == ")" {
|
||||
let tokens = native_list_append(tokens, make_tok("RParen", ")"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "{" {
|
||||
let tokens = native_list_append(tokens, make_tok("LBrace", "{"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "}" {
|
||||
let tokens = native_list_append(tokens, make_tok("RBrace", "}"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "[" {
|
||||
let tokens = native_list_append(tokens, make_tok("LBracket", "["))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "]" {
|
||||
let tokens = native_list_append(tokens, make_tok("RBracket", "]"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "," {
|
||||
let tokens = native_list_append(tokens, make_tok("Comma", ","))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "." {
|
||||
let tokens = native_list_append(tokens, make_tok("Dot", "."))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == ";" {
|
||||
let tokens = native_list_append(tokens, make_tok("Semicolon", ";"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "@" {
|
||||
let tokens = native_list_append(tokens, make_tok("At", "@"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "?" {
|
||||
let tokens = native_list_append(tokens, make_tok("QuestionMark", "?"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
if ch == "#" {
|
||||
let tokens = native_list_append(tokens, make_tok("Hash", "#"))
|
||||
let i = i + 1
|
||||
} else {
|
||||
// unknown char — skip
|
||||
let i = i + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
let tokens = native_list_append(tokens, make_tok("Eof", ""))
|
||||
tokens
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
+6
-80
@@ -77,33 +77,6 @@ fn parse_manifest_entry(src: String) -> String {
|
||||
return ""
|
||||
}
|
||||
|
||||
// parse_manifest_c_sources - collect all `c_source "path"` lines from the
|
||||
// build block. Returns a flat list of path strings.
|
||||
fn parse_manifest_c_sources(src: String) -> [String] {
|
||||
let result: [String] = native_list_empty()
|
||||
let lines: [String] = str_split(src, "\n")
|
||||
let n: Int = native_list_len(lines)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let line: String = native_list_get(lines, i)
|
||||
let t: String = str_trim(line)
|
||||
if str_starts_with(t, "c_source ") {
|
||||
let after: String = str_slice(t, 9, str_len(t))
|
||||
let trimmed: String = str_trim(after)
|
||||
if str_starts_with(trimmed, "\"") {
|
||||
let inner: String = str_slice(trimmed, 1, str_len(trimmed))
|
||||
let q: Int = str_index_of(inner, "\"")
|
||||
if q >= 0 {
|
||||
let path: String = str_slice(inner, 0, q)
|
||||
let result = native_list_append(result, path)
|
||||
}
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
return result
|
||||
}
|
||||
|
||||
fn parse_manifest_name(src: String) -> String {
|
||||
let lines: [String] = str_split(src, "\n")
|
||||
let n: Int = native_list_len(lines)
|
||||
@@ -252,7 +225,6 @@ fn compile_module(src_path: String, out_dir: String, elc_bin: String, dry_run: B
|
||||
let bname: String = basename_noext(src_path)
|
||||
let c_out: String = out_dir + "/" + bname + ".c"
|
||||
let elh_out: String = out_dir + "/" + bname + ".elh"
|
||||
let err_tmp: String = "/tmp/elb-err-" + bname + ".txt"
|
||||
|
||||
// Check if recompile needed
|
||||
if !file_is_newer(src_path, c_out) {
|
||||
@@ -262,26 +234,18 @@ fn compile_module(src_path: String, out_dir: String, elc_bin: String, dry_run: B
|
||||
return true
|
||||
}
|
||||
|
||||
// elc streams C to stdout; redirect stderr to a temp file so we can
|
||||
// surface the actual error message on failure instead of swallowing it.
|
||||
let cmd: String = elc_bin + " --emit-header " + src_path + " > " + c_out + " 2>" + err_tmp
|
||||
// elc streams C to stdout (collect mode not yet implemented); use
|
||||
// shell redirection so the output lands in the file, not the terminal.
|
||||
let cmd: String = elc_bin + " --emit-header " + src_path + " > " + c_out + " 2>&1"
|
||||
println(" compile " + src_path)
|
||||
|
||||
if dry_run { return true }
|
||||
|
||||
let ret: Int = exec_command(cmd)
|
||||
if ret != 0 {
|
||||
// Surface the actual compiler error from stderr
|
||||
let err_msg: String = str_trim(fs_read(err_tmp))
|
||||
if !str_eq(err_msg, "") {
|
||||
println(err_msg)
|
||||
}
|
||||
// Remove partial output so a retry starts clean
|
||||
exec_command("rm -f " + c_out + " " + err_tmp)
|
||||
println("elb: compile failed: " + src_path)
|
||||
return false
|
||||
}
|
||||
exec_command("rm -f " + err_tmp)
|
||||
|
||||
// Move the generated .elh (written next to the source by elc) into
|
||||
// out_dir so that #include "module.elh" lines in the generated .c
|
||||
@@ -298,21 +262,7 @@ fn link_binary(c_files: [String], out_bin: String, runtime_path: String, out_dir
|
||||
let parts: [String] = native_list_empty()
|
||||
// Include both the runtime dir (for el_runtime.h) and the output dir
|
||||
// (for module.elh cross-module forward declarations).
|
||||
// Detect clang vs gcc: -fbracket-depth is clang-only; silently ignored
|
||||
// if unsupported but gcc rejects it with an error.
|
||||
let bracket_flag: String = "$(cc --version 2>&1 | grep -q clang && printf -- '-fbracket-depth=1024' || true)"
|
||||
// On macOS, OpenSSL is not on the default linker path. Detect homebrew
|
||||
// prefix and add it if present (no-op on Linux where libssl is in /usr/lib).
|
||||
let ossl_lib_flag: String = "$(brew --prefix openssl 2>/dev/null | xargs -I{} printf -- '-L{}/lib' 2>/dev/null || true)"
|
||||
let ossl_inc_flag: String = "$(brew --prefix openssl 2>/dev/null | xargs -I{} printf -- '-I{}/include' 2>/dev/null || true)"
|
||||
// Force-include the C-level master declarations header so every translation
|
||||
// unit sees all cross-module function signatures. Handles packages (like ELP)
|
||||
// where modules call each other without explicit El import statements.
|
||||
// The header is generated by elb --gen-decls or manually placed in out_dir.
|
||||
let master_decls: String = out_dir + "/elp-c-decls.h"
|
||||
let has_master: String = str_trim(exec_capture("test -f " + master_decls + " && echo yes || echo no"))
|
||||
let include_flag: String = if str_eq(has_master, "yes") { "-include " + master_decls } else { "" }
|
||||
let parts = native_list_append(parts, "cc -O2 " + bracket_flag + " " + ossl_inc_flag + " " + include_flag + " -I " + dirname_of(runtime_path) + " -I " + out_dir)
|
||||
let parts = native_list_append(parts, "cc -O2 -I " + dirname_of(runtime_path) + " -I " + out_dir)
|
||||
let i = 0
|
||||
while i < n {
|
||||
let f: String = native_list_get(c_files, i)
|
||||
@@ -320,7 +270,7 @@ fn link_binary(c_files: [String], out_bin: String, runtime_path: String, out_dir
|
||||
let i = i + 1
|
||||
}
|
||||
let parts = native_list_append(parts, runtime_path)
|
||||
let parts = native_list_append(parts, ossl_lib_flag + " -lcurl -lssl -lcrypto -lpthread -lm")
|
||||
let parts = native_list_append(parts, "-lcurl -lpthread")
|
||||
let parts = native_list_append(parts, "-o " + out_bin)
|
||||
let cmd: String = str_join(parts, " ")
|
||||
println(" link " + out_bin)
|
||||
@@ -353,7 +303,6 @@ fn main() -> Void {
|
||||
|
||||
let pkg_name: String = parse_manifest_name(manifest_src)
|
||||
let entry: String = parse_manifest_entry(manifest_src)
|
||||
let extra_c: [String] = parse_manifest_c_sources(manifest_src)
|
||||
if str_eq(entry, "") {
|
||||
println("elb: manifest.el has no 'entry' declaration")
|
||||
exit(1)
|
||||
@@ -368,21 +317,7 @@ fn main() -> Void {
|
||||
let which_out: String = str_trim(exec_capture("which " + elc_bin + " 2>/dev/null"))
|
||||
if !str_eq(which_out, "") {
|
||||
let elc_dir: String = dirname_of(which_out)
|
||||
runtime_path = elc_dir + "/../runtime/el_runtime.c"
|
||||
}
|
||||
}
|
||||
// If --runtime points to a directory, auto-locate el_runtime.c inside it.
|
||||
// This lets both forms work:
|
||||
// --runtime=/opt/el/runtime (directory form)
|
||||
// --runtime=/opt/el/runtime/el_runtime.c (file form)
|
||||
if !str_eq(runtime_path, "") {
|
||||
let is_dir: String = str_trim(exec_capture("test -d " + runtime_path + " && echo dir || echo file"))
|
||||
if str_eq(is_dir, "dir") {
|
||||
let candidate: String = runtime_path + "/el_runtime.c"
|
||||
let has_file: String = str_trim(exec_capture("test -f " + candidate + " && echo yes || echo no"))
|
||||
if str_eq(has_file, "yes") {
|
||||
let runtime_path = candidate
|
||||
}
|
||||
runtime_path = elc_dir + "/../el-compiler/runtime/el_runtime.c"
|
||||
}
|
||||
}
|
||||
if str_eq(runtime_path, "") {
|
||||
@@ -432,15 +367,6 @@ fn main() -> Void {
|
||||
exit(1)
|
||||
}
|
||||
|
||||
// Append any extra C sources declared in the manifest (e.g. platform stubs)
|
||||
let ei = 0
|
||||
let en: Int = native_list_len(extra_c)
|
||||
while ei < en {
|
||||
let ec: String = native_list_get(extra_c, ei)
|
||||
let c_files = native_list_append(c_files, ec)
|
||||
let ei = ei + 1
|
||||
}
|
||||
|
||||
// Link
|
||||
let out_bin: String = out_dir + "/" + pkg_name
|
||||
let linked: Bool = link_binary(c_files, out_bin, runtime_path, out_dir, dry_run)
|
||||
+2489
-289
File diff suppressed because it is too large
Load Diff
@@ -1,21 +0,0 @@
|
||||
# Compiled El bytecode
|
||||
*.elc
|
||||
|
||||
# C codegen output
|
||||
*.c
|
||||
*.o
|
||||
*.a
|
||||
*.so
|
||||
*.dylib
|
||||
|
||||
# Combined build artifacts
|
||||
_combined.el
|
||||
*-combined.el
|
||||
|
||||
# Distribution / build output
|
||||
dist/
|
||||
build/
|
||||
out/
|
||||
|
||||
# OS
|
||||
.DS_Store
|
||||
@@ -1,65 +0,0 @@
|
||||
# ELP language consolidation — full-lexicon backfill (stage)
|
||||
|
||||
Branch: `stage-elp-lang-consolidation` (stage-bound; NOT the live soul :8742).
|
||||
|
||||
Consolidates scattered Python language-realizer work (`~/Desktop/lang-realizers`,
|
||||
`~/Desktop/lang-poetry-experiment`, `~/semitic_engine`) into the ELP `.el`
|
||||
structure, generating **full lexicons** (complete UniMorph + kaikki.org
|
||||
Wiktionary — real gender, real inflections) instead of the demo/curated subsets
|
||||
the prototypes shipped.
|
||||
|
||||
## ELP before this branch
|
||||
- 18 classical/ancient languages fully done (vocab + morphology + tests):
|
||||
akk ang cop egy enm fro gez goh got grc non peo pi sa sga sux txb uga.
|
||||
- 11 modern/classical languages had `morphology-<code>.el` in the build manifest
|
||||
but **no vocabulary and no lang_profile**: es fr de ja ar he hi ru fi sw la.
|
||||
- The ES port (`stage-elp-es-port`) had a *demo-scale* vocabulary-es.el (~350
|
||||
entries, s-expr form).
|
||||
|
||||
## Landed on this branch (full-lexicon seed-fn format, matching the 18 ancients)
|
||||
Vocabulary schema per row: `[lemma, pos, form0, form1, form2, en_gloss, hint]`.
|
||||
Files are ELP runtime **seed data** (loaded via the Engram at runtime), so — like
|
||||
all 18 classical `vocabulary-*.el` — they are intentionally NOT in the build
|
||||
manifest. Syntax validated: the chunked `fn vocab_<code>_seed_pN` format
|
||||
compiles cleanly to C via `elc` (correct UTF-8).
|
||||
|
||||
| code | in-ELP-morph? | vocab entries | verbs | nouns | adjs | profile |
|
||||
|------|---------------|--------------:|------:|------:|-----:|---------|
|
||||
| es | yes | 72,032 | 6,695 | 48,353 | 16,984 | yes |
|
||||
| fr | yes | 130,517 | 7,534 | 77,344 | 45,639 | yes |
|
||||
| de | yes | 144,692 | 6,661 | 133,162 | 4,869 | yes |
|
||||
| la | yes | 22,590 | 82 | 13,436 | 9,072 | yes |
|
||||
| it | no (bonus) | 193,675 | 10,008 | 109,459 | 74,208 | yes |
|
||||
| pt | no (bonus) | 115,772 | 4,001 | 72,073 | 39,698 | yes |
|
||||
| ro | no (bonus) | 86,504 | 1,216 | 65,915 | 19,373 | yes |
|
||||
| ca | no (bonus) | 47,112 | 1,547 | 28,830 | 16,735 | yes |
|
||||
|**total**| |**812,894** | | | | |
|
||||
|
||||
Generators (reproducible): `elp/tests/lang-gen/gen_elp_seed_full.py` (Romance),
|
||||
`gen_elp_seed_de_la.py` (German declension + Latin case-paradigm mapping). They
|
||||
read the pre-built morph caches in `~/Desktop/lang-realizers/data/` (UniMorph +
|
||||
kaikki), which are too large to commit.
|
||||
|
||||
## Remaining (honest)
|
||||
Of the 11 ELP backfill targets, 4 are done (es fr de la). The other 7 have **no
|
||||
full-lexicon engine** yet — cannot be generated honestly without engine work:
|
||||
- **ru**: only a 110-entry curated Slavic subset exists; full `rus.unimorph`
|
||||
present but no `morphology_ru_full` productive loader. Needs a full Russian
|
||||
morphology module (like the Romance ones) before vocab generation.
|
||||
- **ja / ko / zh**: validated demo engines (~66-104 hardcoded words) in
|
||||
`lang-poetry-experiment`, Python only. Agglutinative (ja/ko) + isolating (zh)
|
||||
need `.el` engine ports + full-lexicon wiring (ja: jpn_unimorph; zh: CC-CEDICT).
|
||||
- **ar / he (Semitic)**: template engines (16 AR / 8 HE patterns, ~6 roots) in
|
||||
`~/semitic_engine`, Python only. Root-and-pattern; full UniMorph ara/heb
|
||||
present but used only for validation. Needs productive root lexicon + `.el` port.
|
||||
- **hi (Hindi), fi (Finnish), sw (Swahili)**: `morphology-<code>.el` exists in
|
||||
ELP but there is NO scattered prototype and NO downloaded data for these —
|
||||
full-lexicon collection (UniMorph/kaikki) + generator still to do.
|
||||
|
||||
De/nl/sv Germanic and it/ro/ca/pt Romance verb coverage note: German verbs here
|
||||
are the ~6.6k caches carry; the it/ro/ca/pt bonus languages have full vocab but
|
||||
**no `morphology-<code>.el` in ELP yet** (Python realizer exists; `.el` port is
|
||||
the remaining engine work).
|
||||
|
||||
Construction coverage (separate from lexicon): French realizer was ~55%,
|
||||
Semitic ~3% in the prototypes — full construction coverage remains its own task.
|
||||
File diff suppressed because one or more lines are too long
@@ -1,23 +0,0 @@
|
||||
{
|
||||
"dataset": "british-rp-accent-transform",
|
||||
"primitive_type": "accent_target",
|
||||
"accent": "british-rp",
|
||||
"grounding": "derived",
|
||||
"provenance": "HONEST-DERIVED, COARSE FIRST PASS — NOT transcribed measured RP formants. The exact measured RP/GB tables (Deterding 1997 JIPA 27:47-55; Hawkins & Midgley 2005 JIPA 35:183-199) are the intended ground truth but were gated/figure-only at author time and were NOT transcribed. So these targets are DERIVED: each = the corresponding MEASURED Peterson&Barney(1952) base vowel transformed under the documented, citable RP-vs-GA structural rules of Wells (1982) 'Accents of English' — non-rhoticity (NURSE de-rhoticized: remove low F3), TRAP F2-lowering, LOT/THOUGHT back-rounding (F2 down), GOOSE-fronting (F2 up), GOAT centering. Shift MAGNITUDES are coarse/approximate (first pass), directions are cited. ground:derived (base measured + rule cited). Refine by transcribing Deterding/Hawkins&Midgley. No number is presented as a measured RP value it is not.",
|
||||
"notes": "records with kind=vowel_override REPLACE the base phoneme's formant targets with the DERIVED RP realization. records with kind=rule encode non-formant transforms (non-rhoticity: drop post-vocalic coda /r/). The render composes: base geometry then accent override + rhoticity rule — voice + accent, separable.",
|
||||
"records": [
|
||||
{"key": "IY", "features": {"kind": "vowel_override", "set": "FLEECE"}, "attributes": {"f1": 280, "f2": 2249, "f3": 3000}},
|
||||
{"key": "IH", "features": {"kind": "vowel_override", "set": "KIT"}, "attributes": {"f1": 360, "f2": 2100, "f3": 2550}},
|
||||
{"key": "EH", "features": {"kind": "vowel_override", "set": "DRESS"}, "attributes": {"f1": 560, "f2": 1970, "f3": 2480}},
|
||||
{"key": "AE", "features": {"kind": "vowel_override", "set": "TRAP"}, "attributes": {"f1": 730, "f2": 1590, "f3": 2410}},
|
||||
{"key": "AA", "features": {"kind": "vowel_override", "set": "LOT"}, "attributes": {"f1": 560, "f2": 920, "f3": 2440}},
|
||||
{"key": "AO", "features": {"kind": "vowel_override", "set": "THOUGHT"}, "attributes": {"f1": 415, "f2": 700, "f3": 2410}},
|
||||
{"key": "UH", "features": {"kind": "vowel_override", "set": "FOOT"}, "attributes": {"f1": 380, "f2": 1100, "f3": 2240}},
|
||||
{"key": "UW", "features": {"kind": "vowel_override", "set": "GOOSE"}, "attributes": {"f1": 310, "f2": 1650, "f3": 2240}},
|
||||
{"key": "AH", "features": {"kind": "vowel_override", "set": "STRUT"}, "attributes": {"f1": 680, "f2": 1180, "f3": 2390}},
|
||||
{"key": "ER", "features": {"kind": "vowel_override", "set": "NURSE", "rhotic": "no"}, "attributes": {"f1": 550, "f2": 1500, "f3": 2500}},
|
||||
{"key": "AX", "features": {"kind": "vowel_override", "set": "commA"}, "attributes": {"f1": 500, "f2": 1500, "f3": 2500}},
|
||||
{"key": "OW", "features": {"kind": "vowel_override", "set": "GOAT"}, "attributes": {"f1": 450, "f2": 1400, "f3": 2380}},
|
||||
{"key": "R", "features": {"kind": "rule", "rule": "non_rhotic"}, "attributes": {"drop_coda_r": 1}}
|
||||
]
|
||||
}
|
||||
@@ -1,26 +0,0 @@
|
||||
# british-rp-accent TRANSFORM — INGESTIBLE DATA (a geometry/transform composed
|
||||
# onto the base General-American phoneme targets; voice + accent, separable).
|
||||
#
|
||||
# PROVENANCE — HONEST, COARSE FIRST PASS. These are DERIVED targets, NOT
|
||||
# transcribed measured RP formants. Measured RP tables (Deterding 1997 JIPA 27;
|
||||
# Hawkins & Midgley 2005 JIPA 35) are the intended ground truth but were gated at
|
||||
# author time and NOT transcribed. Each target = the MEASURED Peterson&Barney
|
||||
# (1952) base vowel transformed under the documented, citable RP-vs-GA structural
|
||||
# rules of Wells (1982): non-rhoticity, TRAP F2-lowering, LOT/THOUGHT back-
|
||||
# rounding, GOOSE-fronting, GOAT centering, NURSE de-rhoticization. Shift
|
||||
# magnitudes are coarse/approximate; directions are cited. ground=derived.
|
||||
# Refine by transcribing the measured RP tables. No value is claimed as measured.
|
||||
# Format: KEY|F1|F2|F3|KIND|SET
|
||||
IY|280|2249|3000|vowel_override|FLEECE
|
||||
IH|360|2100|2550|vowel_override|KIT
|
||||
EH|560|1970|2480|vowel_override|DRESS
|
||||
AE|730|1590|2410|vowel_override|TRAP
|
||||
AA|560|920|2440|vowel_override|LOT
|
||||
AO|415|700|2410|vowel_override|THOUGHT
|
||||
UH|380|1100|2240|vowel_override|FOOT
|
||||
UW|310|1650|2240|vowel_override|GOOSE
|
||||
AH|680|1180|2390|vowel_override|STRUT
|
||||
ER|550|1500|2500|vowel_override|NURSE-nonrhotic
|
||||
AX|500|1500|2500|vowel_override|commA
|
||||
OW|450|1400|2380|vowel_override|GOAT
|
||||
R|0|0|0|rule|non_rhotic_drop_coda
|
||||
@@ -1,20 +0,0 @@
|
||||
# pronunciation lexicon SOURCE — word -> phoneme sequence, as INGESTIBLE DATA.
|
||||
# Pronunciation is linguistic KNOWLEDGE (the language faculty's orthography->
|
||||
# phonology map), ingested into the engram, not frozen in code. The render reads
|
||||
# a word's phoneme sequence back from the engram. Covers the self-lexicon and the
|
||||
# proof sentences; general G2P is the realizer/morphology faculty's remit.
|
||||
# Diphthongs are written as two vowel targets (the render's transitions glide
|
||||
# between them). Format: word|PH1 PH2 PH3 ...
|
||||
i|AA IY
|
||||
am|AE M
|
||||
neuron|N UW R AA N
|
||||
is|IH Z
|
||||
memory|M EH M ER IY
|
||||
hello|HH EH L OW
|
||||
the|DH AH
|
||||
a|AH
|
||||
remember|R IH M EH M ER
|
||||
i'm|AA IY M
|
||||
you|Y UW
|
||||
here|HH IY R
|
||||
will|W IH L
|
||||
File diff suppressed because one or more lines are too long
@@ -1,528 +0,0 @@
|
||||
{
|
||||
"dataset": "english-phoneme-formants",
|
||||
"primitive_type": "phoneme",
|
||||
"grounding": "extracted",
|
||||
"provenance": "AUDITED per-field. The 10 monophthong-vowel F1/F2/F3 (IY,IH,EH,AE,AA,AO,UH,UW,AH,ER) are the MEASURED adult-male /hVd/ means of Peterson & Barney (1952) JASA 24:175-184, verified vs CRAN phonTools::pb52. AX=neutral uniform-tube resonances (Fant, physics). OW steady target = synthesis convention (diphthong). Consonant loci (M,N,NG,L,R,W,Y,Z,DH,V,S,F,HH) and ALL bandwidths + dur/amp = standard formant-synthesis conventions (Klatt 1980 JASA 67:971), engineering defaults NOT field measurements. No numbers invented/LLM-generated.",
|
||||
"records": [
|
||||
{
|
||||
"key": "IY",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 270,
|
||||
"f2": 2290,
|
||||
"f3": 3010,
|
||||
"bw1": 60,
|
||||
"bw2": 90,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 130,
|
||||
"amp": 100
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "IH",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 390,
|
||||
"f2": 1990,
|
||||
"f3": 2550,
|
||||
"bw1": 70,
|
||||
"bw2": 100,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 110,
|
||||
"amp": 100
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "EH",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 530,
|
||||
"f2": 1840,
|
||||
"f3": 2480,
|
||||
"bw1": 80,
|
||||
"bw2": 100,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 130,
|
||||
"amp": 100
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "AE",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 660,
|
||||
"f2": 1720,
|
||||
"f3": 2410,
|
||||
"bw1": 90,
|
||||
"bw2": 110,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 150,
|
||||
"amp": 100
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "AA",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 730,
|
||||
"f2": 1090,
|
||||
"f3": 2440,
|
||||
"bw1": 90,
|
||||
"bw2": 110,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 150,
|
||||
"amp": 100
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "AO",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 570,
|
||||
"f2": 840,
|
||||
"f3": 2410,
|
||||
"bw1": 80,
|
||||
"bw2": 100,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 140,
|
||||
"amp": 100
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "UH",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 440,
|
||||
"f2": 1020,
|
||||
"f3": 2240,
|
||||
"bw1": 70,
|
||||
"bw2": 100,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 110,
|
||||
"amp": 100
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "UW",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 300,
|
||||
"f2": 870,
|
||||
"f3": 2240,
|
||||
"bw1": 70,
|
||||
"bw2": 90,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 140,
|
||||
"amp": 100
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "AH",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 640,
|
||||
"f2": 1190,
|
||||
"f3": 2390,
|
||||
"bw1": 80,
|
||||
"bw2": 100,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 110,
|
||||
"amp": 95
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "ER",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 490,
|
||||
"f2": 1350,
|
||||
"f3": 1690,
|
||||
"bw1": 80,
|
||||
"bw2": 100,
|
||||
"bw3": 120,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 140,
|
||||
"amp": 95
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "AX",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 500,
|
||||
"f2": 1500,
|
||||
"f3": 2500,
|
||||
"bw1": 80,
|
||||
"bw2": 100,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 80,
|
||||
"amp": 85
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "OW",
|
||||
"features": {
|
||||
"manner": "vowel",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 490,
|
||||
"f2": 910,
|
||||
"f3": 2380,
|
||||
"bw1": 80,
|
||||
"bw2": 100,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 140,
|
||||
"amp": 100
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "M",
|
||||
"features": {
|
||||
"manner": "nasal",
|
||||
"voiced": "yes",
|
||||
"nasal": "yes"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 250,
|
||||
"f2": 900,
|
||||
"f3": 2200,
|
||||
"bw1": 90,
|
||||
"bw2": 120,
|
||||
"bw3": 180,
|
||||
"voiced": 1,
|
||||
"nasal": 1,
|
||||
"dur": 80,
|
||||
"amp": 60
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "N",
|
||||
"features": {
|
||||
"manner": "nasal",
|
||||
"voiced": "yes",
|
||||
"nasal": "yes"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 250,
|
||||
"f2": 1700,
|
||||
"f3": 2600,
|
||||
"bw1": 90,
|
||||
"bw2": 120,
|
||||
"bw3": 180,
|
||||
"voiced": 1,
|
||||
"nasal": 1,
|
||||
"dur": 80,
|
||||
"amp": 60
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "NG",
|
||||
"features": {
|
||||
"manner": "nasal",
|
||||
"voiced": "yes",
|
||||
"nasal": "yes"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 250,
|
||||
"f2": 2300,
|
||||
"f3": 2700,
|
||||
"bw1": 90,
|
||||
"bw2": 120,
|
||||
"bw3": 180,
|
||||
"voiced": 1,
|
||||
"nasal": 1,
|
||||
"dur": 80,
|
||||
"amp": 60
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "L",
|
||||
"features": {
|
||||
"manner": "approximant",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 360,
|
||||
"f2": 1300,
|
||||
"f3": 2600,
|
||||
"bw1": 80,
|
||||
"bw2": 110,
|
||||
"bw3": 160,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 70,
|
||||
"amp": 80
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "R",
|
||||
"features": {
|
||||
"manner": "approximant",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 490,
|
||||
"f2": 1350,
|
||||
"f3": 1600,
|
||||
"bw1": 80,
|
||||
"bw2": 110,
|
||||
"bw3": 120,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 80,
|
||||
"amp": 85
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "W",
|
||||
"features": {
|
||||
"manner": "approximant",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 300,
|
||||
"f2": 610,
|
||||
"f3": 2200,
|
||||
"bw1": 70,
|
||||
"bw2": 100,
|
||||
"bw3": 160,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 70,
|
||||
"amp": 80
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "Y",
|
||||
"features": {
|
||||
"manner": "approximant",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 270,
|
||||
"f2": 2290,
|
||||
"f3": 3010,
|
||||
"bw1": 60,
|
||||
"bw2": 90,
|
||||
"bw3": 150,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 60,
|
||||
"amp": 80
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "Z",
|
||||
"features": {
|
||||
"manner": "fricative",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 300,
|
||||
"f2": 1700,
|
||||
"f3": 2500,
|
||||
"bw1": 100,
|
||||
"bw2": 150,
|
||||
"bw3": 200,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 90,
|
||||
"amp": 55
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "DH",
|
||||
"features": {
|
||||
"manner": "fricative",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 300,
|
||||
"f2": 1400,
|
||||
"f3": 2500,
|
||||
"bw1": 100,
|
||||
"bw2": 150,
|
||||
"bw3": 200,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 70,
|
||||
"amp": 55
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "V",
|
||||
"features": {
|
||||
"manner": "fricative",
|
||||
"voiced": "yes",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 300,
|
||||
"f2": 1000,
|
||||
"f3": 2300,
|
||||
"bw1": 100,
|
||||
"bw2": 150,
|
||||
"bw3": 200,
|
||||
"voiced": 1,
|
||||
"nasal": 0,
|
||||
"dur": 70,
|
||||
"amp": 55
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "S",
|
||||
"features": {
|
||||
"manner": "fricative",
|
||||
"voiced": "no",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 320,
|
||||
"f2": 1700,
|
||||
"f3": 2500,
|
||||
"bw1": 200,
|
||||
"bw2": 200,
|
||||
"bw3": 250,
|
||||
"voiced": 0,
|
||||
"nasal": 0,
|
||||
"dur": 110,
|
||||
"amp": 45
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "F",
|
||||
"features": {
|
||||
"manner": "fricative",
|
||||
"voiced": "no",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 300,
|
||||
"f2": 1200,
|
||||
"f3": 2400,
|
||||
"bw1": 200,
|
||||
"bw2": 200,
|
||||
"bw3": 250,
|
||||
"voiced": 0,
|
||||
"nasal": 0,
|
||||
"dur": 100,
|
||||
"amp": 40
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "HH",
|
||||
"features": {
|
||||
"manner": "fricative",
|
||||
"voiced": "no",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 500,
|
||||
"f2": 1500,
|
||||
"f3": 2500,
|
||||
"bw1": 200,
|
||||
"bw2": 250,
|
||||
"bw3": 300,
|
||||
"voiced": 0,
|
||||
"nasal": 0,
|
||||
"dur": 70,
|
||||
"amp": 40
|
||||
}
|
||||
},
|
||||
{
|
||||
"key": "SIL",
|
||||
"features": {
|
||||
"manner": "silence",
|
||||
"voiced": "no",
|
||||
"nasal": "no"
|
||||
},
|
||||
"attributes": {
|
||||
"f1": 500,
|
||||
"f2": 1500,
|
||||
"f3": 2500,
|
||||
"bw1": 100,
|
||||
"bw2": 100,
|
||||
"bw3": 100,
|
||||
"voiced": 0,
|
||||
"nasal": 0,
|
||||
"dur": 55,
|
||||
"amp": 0
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,45 +0,0 @@
|
||||
# acoustic-phonetics SOURCE — the learned speech primitives, as INGESTIBLE DATA.
|
||||
# NOT audio, NOT code: formant geometry of the phonemes, to be ingested via the
|
||||
# ingest organ into the engram as a phoneme manifold. The render reads this
|
||||
# geometry back from the engram; nothing is frozen in EL code.
|
||||
#
|
||||
# PROVENANCE (audited, per-field honesty — no invented numbers):
|
||||
# * The 10 MONOPHTHONG VOWEL formants F1/F2/F3 (IY,IH,EH,AE,AA,AO,UH,UW,AH,ER)
|
||||
# are the MEASURED adult-male means of Peterson & Barney (1952), JASA 24:175-184
|
||||
# — the canonical /hVd/ table, verified digit-for-digit vs CRAN phonTools::pb52.
|
||||
# These are real measured values.
|
||||
# * AX (schwa) F1/F2/F3 = neutral uniform-tube resonances (2n-1)*500 — a PHYSICS
|
||||
# value (Fant), not a P&B measurement.
|
||||
# * OW is a diphthong; its listed steady target is a conventional synthesis value,
|
||||
# not a P&B monophthong measurement.
|
||||
# * CONSONANT loci (M,N,NG,L,R,W,Y,Z,DH,V,S,F,HH) and ALL BANDWIDTHS (B1,B2,B3)
|
||||
# and dur/amp are STANDARD FORMANT-SYNTHESIS conventions (Klatt 1980, JASA 67:971
|
||||
# "Software for a cascade/parallel formant synthesizer") — engineering defaults,
|
||||
# NOT per-phoneme field measurements. Labeled as such, not attributed to P&B.
|
||||
# Format: SYM|F1|F2|F3|B1|B2|B3|voiced|nasal|dur_ms|amp|class|example
|
||||
IY|270|2290|3010|60|90|150|1|0|130|100|vowel|beet
|
||||
IH|390|1990|2550|70|100|150|1|0|110|100|vowel|bit
|
||||
EH|530|1840|2480|80|100|150|1|0|130|100|vowel|bet
|
||||
AE|660|1720|2410|90|110|150|1|0|150|100|vowel|bat
|
||||
AA|730|1090|2440|90|110|150|1|0|150|100|vowel|bot
|
||||
AO|570|840|2410|80|100|150|1|0|140|100|vowel|bought
|
||||
UH|440|1020|2240|70|100|150|1|0|110|100|vowel|book
|
||||
UW|300|870|2240|70|90|150|1|0|140|100|vowel|boot
|
||||
AH|640|1190|2390|80|100|150|1|0|110|95|vowel|but
|
||||
ER|490|1350|1690|80|100|120|1|0|140|95|vowel|bird
|
||||
AX|500|1500|2500|80|100|150|1|0|80|85|vowel|about
|
||||
OW|490|910|2380|80|100|150|1|0|140|100|vowel|boat
|
||||
M|250|900|2200|90|120|180|1|1|80|60|nasal|map
|
||||
N|250|1700|2600|90|120|180|1|1|80|60|nasal|nap
|
||||
NG|250|2300|2700|90|120|180|1|1|80|60|nasal|sing
|
||||
L|360|1300|2600|80|110|160|1|0|70|80|approximant|lip
|
||||
R|490|1350|1600|80|110|120|1|0|80|85|approximant|rip
|
||||
W|300|610|2200|70|100|160|1|0|70|80|approximant|wet
|
||||
Y|270|2290|3010|60|90|150|1|0|60|80|approximant|yet
|
||||
Z|300|1700|2500|100|150|200|1|0|90|55|fricative|zoo
|
||||
DH|300|1400|2500|100|150|200|1|0|70|55|fricative|the
|
||||
V|300|1000|2300|100|150|200|1|0|70|55|fricative|van
|
||||
S|320|1700|2500|200|200|250|0|0|110|45|fricative|see
|
||||
F|300|1200|2400|200|200|250|0|0|100|40|fricative|fee
|
||||
HH|500|1500|2500|200|250|300|0|0|70|40|fricative|hat
|
||||
SIL|500|1500|2500|100|100|100|0|0|55|0|silence|_
|
||||
Binary file not shown.
@@ -1,90 +0,0 @@
|
||||
package "elp" {
|
||||
version "0.7.0"
|
||||
description "Engram Language Protocol — bidirectional engine mapping between Engram semantic forms and natural language surface text. 31 languages."
|
||||
edition "2026"
|
||||
}
|
||||
|
||||
build {
|
||||
entry "src/elp.el"
|
||||
|
||||
// Compilation order (dependency order):
|
||||
// language-profile (no deps)
|
||||
// vocabulary (no deps)
|
||||
// morphology (depends on: language-profile)
|
||||
// morphology-es (depends on: morphology) Spanish
|
||||
// morphology-fr (depends on: morphology) French
|
||||
// morphology-de (depends on: morphology) German
|
||||
// morphology-ru (depends on: morphology) Russian
|
||||
// morphology-ja (depends on: morphology) Japanese
|
||||
// morphology-fi (depends on: morphology) Finnish
|
||||
// morphology-ar (depends on: morphology) Arabic
|
||||
// morphology-hi (depends on: morphology) Hindi
|
||||
// morphology-sw (depends on: morphology) Swahili
|
||||
// morphology-la (depends on: morphology) Latin
|
||||
// morphology-he (depends on: morphology) Hebrew
|
||||
// morphology-grc (depends on: morphology) Ancient Greek
|
||||
// morphology-ang (depends on: morphology) Old English
|
||||
// morphology-sa (depends on: morphology) Sanskrit
|
||||
// morphology-got (depends on: morphology) Gothic
|
||||
// morphology-non (depends on: morphology) Old Norse
|
||||
// morphology-enm (depends on: morphology) Middle English
|
||||
// morphology-pi (depends on: morphology) Pali
|
||||
// morphology-fro (depends on: morphology) Old French
|
||||
// morphology-goh (depends on: morphology) Old High German
|
||||
// morphology-sga (depends on: morphology) Old Irish
|
||||
// morphology-txb (depends on: morphology) Tocharian B
|
||||
// morphology-peo (depends on: morphology) Old Persian
|
||||
// morphology-akk (depends on: morphology) Akkadian
|
||||
// morphology-uga (depends on: morphology) Ugaritic
|
||||
// morphology-egy (depends on: morphology) Ancient Egyptian
|
||||
// morphology-sux (depends on: morphology) Sumerian
|
||||
// morphology-gez (depends on: morphology) Ge'ez (Classical Ethiopic)
|
||||
// morphology-cop (depends on: morphology) Coptic (Sahidic)
|
||||
// grammar (depends on: language-profile)
|
||||
// realizer (depends on: morphology, grammar, language-profile)
|
||||
// semantics (depends on: grammar, realizer, language-profile)
|
||||
// elp (depends on: semantics, realizer)
|
||||
sources [
|
||||
"src/language-profile.el",
|
||||
"src/vocabulary.el",
|
||||
"src/morphology.el",
|
||||
"src/morphology-es.el",
|
||||
"src/morphology-fr.el",
|
||||
"src/morphology-de.el",
|
||||
"src/morphology-ru.el",
|
||||
"src/morphology-ja.el",
|
||||
"src/morphology-fi.el",
|
||||
"src/morphology-ar.el",
|
||||
"src/morphology-hi.el",
|
||||
"src/morphology-sw.el",
|
||||
"src/morphology-la.el",
|
||||
"src/morphology-he.el",
|
||||
"src/morphology-grc.el",
|
||||
"src/morphology-ang.el",
|
||||
"src/morphology-sa.el",
|
||||
"src/morphology-got.el",
|
||||
"src/morphology-non.el",
|
||||
"src/morphology-enm.el",
|
||||
"src/morphology-pi.el",
|
||||
"src/morphology-fro.el",
|
||||
"src/morphology-goh.el",
|
||||
"src/morphology-sga.el",
|
||||
"src/morphology-txb.el",
|
||||
"src/morphology-peo.el",
|
||||
"src/morphology-akk.el",
|
||||
"src/morphology-uga.el",
|
||||
"src/morphology-egy.el",
|
||||
"src/morphology-sux.el",
|
||||
"src/morphology-gez.el",
|
||||
"src/morphology-cop.el",
|
||||
"src/grammar.el",
|
||||
"src/realizer.el",
|
||||
"src/semantics.el",
|
||||
"src/comprehend.el",
|
||||
"src/propositions.el",
|
||||
"src/multilingual.el",
|
||||
"src/self_region.el",
|
||||
"src/dialogue.el",
|
||||
"src/elp.el",
|
||||
]
|
||||
}
|
||||
@@ -1,91 +0,0 @@
|
||||
> **STATUS: STAGING / PROOF-OF-SHAPE — not the deliverable.** This Python package
|
||||
> proved the architecture end-to-end against the proven realizer faculty (faithful
|
||||
> md/docx/midi from real geometry: 0 ungrounded claims, SACRED polarity). Per Will's
|
||||
> steer, the DELIVERABLE is NATIVE: the seam lives on the existing EL realizer as
|
||||
> **surface-as-profile** — see `../src/surface-profile.el` and
|
||||
> `../tests/examples/surface-profile-demo.el` (compiles + runs through elc → C →
|
||||
> binary). The concepts below (one geometry-carrying frame; surface = a pluggable
|
||||
> profile; plan/realize; deterministic-from-meaning) are exactly what the native
|
||||
> module implements. Keep this package as the validated proof; build native.
|
||||
|
||||
# Efferent Multimodal Projector
|
||||
|
||||
**geometry → any surface, faithfully.** Neuron's own document-generation faculty:
|
||||
the efferent twin of the ingest organ. Ingest is afferent (world → geometry);
|
||||
this is efferent (geometry → an arbitrary-format document / any modality).
|
||||
|
||||
Built against the **proven** realizer faculty (neuron-talk sidecar `:8756`,
|
||||
artifact `art-7affa557`). The live soul (`:8742` / `:7770`) is contacted **only**
|
||||
through the read-only, GET-only `engram_client` — never mutated.
|
||||
|
||||
## The pipeline (surface-agnostic)
|
||||
|
||||
```
|
||||
geometry region + surface/format spec
|
||||
→ PLAN (manifold → document skeleton/DAG; the geometry IS the outline) plan.py
|
||||
→ REALIZE (proven realizer, scaled sentence → passage, each section faithful) realize.py
|
||||
→ COHERE (document-level flow / transitions, not stitched sentences) cohere.py
|
||||
→ EMIT (pluggable SurfaceProjector → the target surface) projectors/
|
||||
```
|
||||
|
||||
**The surface is a PARAMETER.** `pipeline.build_ir(...)` builds ONE
|
||||
surface-neutral `DocumentIR` (`document_ir.py`); `pipeline.emit(doc, surface)`
|
||||
projects it to whichever surface you name. Markdown, docx, and MIDI are the same
|
||||
IR emitted three ways.
|
||||
|
||||
## The pivot: a geometry-carrying IR
|
||||
|
||||
`DocumentIR` is **not** a text tree. Every `Block` carries BOTH:
|
||||
- `.sentences` — realized faithful text (what **text** projectors read),
|
||||
- `.provenance` — the source geometry: `subj_id / relation / obj / polarity /
|
||||
confidence / importance / salience / node_id` (what **music / image / video**
|
||||
projectors read).
|
||||
|
||||
That single decision is what makes the projector multimodal: text renders the
|
||||
words; music/image decode the geometry. A claim with no provenance cannot exist
|
||||
in the IR — faithfulness is structural.
|
||||
|
||||
## The one shared seam
|
||||
|
||||
`projectors/base.py` — `SurfaceProjector.project(frame: DocumentIR) -> bytes`
|
||||
(+ `surface / media_type / ext / modality / profile`). Register with
|
||||
`register()`. Adding a surface changes nothing upstream.
|
||||
|
||||
`TwoStageProjector` blesses the peer plan/realize decomposition:
|
||||
`spec = plan(frame)`, `bytes = realize(spec)`, `project = realize∘plan`; the
|
||||
`profile` is the pluggable per-surface knob (text lang-profile, music
|
||||
instr/mode-profile). `projectors/midi.py` is the reference two-stage impl.
|
||||
|
||||
## Surfaces
|
||||
|
||||
| surface | modality | status | emitter |
|
||||
|---|---|---|---|
|
||||
| `markdown` | text | landed | own (str) |
|
||||
| `docx` | text | landed | own minimal OOXML (stdlib `zipfile`+XML, no lib) |
|
||||
| `midi` | audio | landed (symbolic-music proof) | own minimal SMF (stdlib `struct`, no lib) |
|
||||
| `audio` (WAV) | audio | peer agent (additive synth) | conforms to `TwoStageProjector` |
|
||||
| `image` | image | documented seam | `projectors/seams.py` |
|
||||
| `video` | video | documented seam (image×sound×time) | `projectors/seams.py` |
|
||||
|
||||
Music maps: relation → scale degree (same relation → same pitch), **polarity →
|
||||
major/minor third (SACRED negation is audible)**, confidence → duration,
|
||||
importance → velocity, section → register. Deterministic projection from meaning
|
||||
— nothing invented.
|
||||
|
||||
## Faithfulness
|
||||
|
||||
`provenance.py` audits the IR: **zero** ungrounded claims, SACRED polarity
|
||||
preserved (negations reported, never dropped), COHERE introduces no new geometry
|
||||
(connectives are marked). `trace_table()` emits the geometry → section → claim
|
||||
table.
|
||||
|
||||
## Run
|
||||
|
||||
```bash
|
||||
PY=~/Desktop/lang-realizers/venv/bin/python
|
||||
PYTHONPATH=~/Desktop/neuron-talk:~/Desktop/lang-realizers $PY generate.py
|
||||
# writes ./out/{neuron-self,engram-temporal}.{md,docx,mid} + *.audit.json + *.provenance.md
|
||||
```
|
||||
|
||||
Requires the proven realizer env (spaCy + the neuron-talk/lang-realizers engine)
|
||||
and the read-only engram at `:8742`.
|
||||
@@ -1,79 +0,0 @@
|
||||
"""cohere.py — COHERE stage: document-level flow, not stitched sentences.
|
||||
|
||||
Fidelity is REALIZE's job; FLOW is this stage's. The hard part beyond sentence
|
||||
fidelity is that a document must read as one thing. We add connective tissue at
|
||||
the passage level:
|
||||
|
||||
* an opening abstract that names what the document covers (built ONLY from the
|
||||
section headings that already exist — it introduces no new claim),
|
||||
* a short transition lead into each section after the first, drawn from a
|
||||
fixed set of discourse connectives ("Beyond that,", "Relatedly,", ...) that
|
||||
carry no propositional content,
|
||||
* ordering so the highest-grounded section leads.
|
||||
|
||||
CRITICAL: every connective is marked ``kind="connective"`` in its provenance, so
|
||||
the faithfulness audit can prove COHERE introduced ZERO new geometry claims. A
|
||||
transition is discourse glue, never a fact.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from document_ir import Block, DocumentIR, Provenance
|
||||
|
||||
# discourse connectives — pure flow, no propositional content
|
||||
_TRANSITIONS = [
|
||||
"Beyond that,", "Relatedly,", "In the same region,", "From there,",
|
||||
"Alongside this,", "Further,", "Turning to the next facet,",
|
||||
]
|
||||
|
||||
|
||||
def _connective_prov() -> Provenance:
|
||||
return Provenance(subj_id=None, subject=None, relation="", obj=None,
|
||||
polarity="aff", confidence=1.0, node_id=None,
|
||||
kind="connective")
|
||||
|
||||
|
||||
def _abstract_block(doc: DocumentIR) -> Block:
|
||||
"""A grounded opening: names the sections, asserts nothing new."""
|
||||
headings = [s.heading for s in doc.sections]
|
||||
if not headings:
|
||||
return Block(role="lead")
|
||||
if len(headings) == 1:
|
||||
body = f"This document, generated from Neuron's geometry, covers {headings[0]}."
|
||||
else:
|
||||
listed = ", ".join(headings[:-1]) + f", and {headings[-1]}"
|
||||
body = ("This document is projected directly from Neuron's meaning-geometry. "
|
||||
f"It traces {listed}.")
|
||||
b = Block(role="lead")
|
||||
b.sentences.append(body)
|
||||
b.provenance.append(_connective_prov())
|
||||
return b
|
||||
|
||||
|
||||
def cohere_document(doc: DocumentIR, *, add_abstract: bool = True,
|
||||
add_transitions: bool = True) -> DocumentIR:
|
||||
"""Order sections by grounding, add abstract + transitions (flow only)."""
|
||||
# order: strongest-grounded section (mean confidence x #claims) first,
|
||||
# but keep an explicitly-first section if the plan pinned one via level 1.
|
||||
def _score(sec):
|
||||
provs = [p for p in sec.all_provenance() if p.kind == "fact"]
|
||||
if not provs:
|
||||
return 0.0
|
||||
mean_conf = sum(p.confidence for p in provs) / len(provs)
|
||||
return mean_conf * len(provs)
|
||||
|
||||
doc.sections.sort(key=_score, reverse=True)
|
||||
|
||||
if add_transitions:
|
||||
for i, sec in enumerate(doc.sections):
|
||||
if i == 0 or not sec.blocks:
|
||||
continue
|
||||
lead = _TRANSITIONS[(i - 1) % len(_TRANSITIONS)]
|
||||
first = sec.blocks[0]
|
||||
if first.sentences:
|
||||
# prepend the connective to the first sentence (flow, no new claim)
|
||||
first.sentences[0] = f"{lead} {first.sentences[0][0].lower()}{first.sentences[0][1:]}"
|
||||
|
||||
if add_abstract:
|
||||
doc.meta["abstract"] = _abstract_block(doc)
|
||||
|
||||
return doc
|
||||
@@ -1,111 +0,0 @@
|
||||
"""document_ir.py — the surface-neutral, GEOMETRY-CARRYING document intermediate.
|
||||
|
||||
This is the pivot of the whole efferent projector. A DocumentIR is NOT a text
|
||||
tree. It is a projection of a meaning-geometry region that carries, at every
|
||||
leaf, BOTH:
|
||||
|
||||
* the realized surface text (``Block.sentences``) — what a TEXT projector reads,
|
||||
* the source geometry (``Block.provenance``) — what a MUSIC / IMAGE /
|
||||
VIDEO projector reads.
|
||||
|
||||
Because the IR holds the geometry, not just the words, the SAME
|
||||
plan -> realize -> cohere pipeline drives every surface. A markdown projector
|
||||
renders the sentences; a music projector reads the provenance edges (salience,
|
||||
importance, polarity, relation) and maps them onto a symbolic-music surface;
|
||||
an image/video projector (documented seam) would read the same geometry.
|
||||
|
||||
Nothing in this module invents content. Every :class:`Provenance` points at a
|
||||
real engram node id and a real relation. That is the faithfulness contract made
|
||||
structural: a claim with no provenance cannot exist in the IR.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Provenance — the geometry an emitted claim traces to. FAITHFULNESS is here.
|
||||
# --------------------------------------------------------------------------- #
|
||||
@dataclass
|
||||
class Provenance:
|
||||
"""One geometry edge behind one realized claim.
|
||||
|
||||
``kind`` distinguishes a FACT (a structural edge asserted by the geometry,
|
||||
spoken as fact) from an INTERPRETATION (something attributed, spoken with
|
||||
attribution) — the facts-as-facts + interpretations-attributed discipline
|
||||
(memory 80927e26). ``polarity`` is SACRED: a negated edge stays negated.
|
||||
"""
|
||||
subj_id: str | None # source engram node id of the subject
|
||||
subject: str | None # normalized subject surface
|
||||
relation: str # predicate lemma (e.g. "use", "contain", "be")
|
||||
obj: str | None # normalized object / complement surface
|
||||
polarity: str = "aff" # "aff" | "neg" (SACRED — never silently flipped)
|
||||
confidence: float = 0.0 # extraction confidence in [0,1]
|
||||
node_id: str | None = None # engram node the claim was extracted from
|
||||
kind: str = "fact" # "fact" | "interpretation"
|
||||
importance: float = 0.0 # source node importance (drives music/emphasis)
|
||||
salience: float = 0.0 # source node salience
|
||||
|
||||
def trace(self) -> str:
|
||||
arrow = "-->" if self.polarity == "aff" else "--NOT-->"
|
||||
return (f"[{(self.node_id or '?')[:8]}] {self.subject!r} {arrow}"
|
||||
f"{self.relation} {self.obj!r} (conf {self.confidence:.2f})")
|
||||
|
||||
|
||||
@dataclass
|
||||
class Block:
|
||||
"""A passage: one or more faithful sentences + the geometry they trace to.
|
||||
|
||||
``sentences`` and ``provenance`` are index-aligned where possible: sentence
|
||||
``i`` was realized from ``provenance[i]``. A COHERE transition sentence with
|
||||
no new geometry carries a provenance whose ``kind == "connective"`` so the
|
||||
audit can see it introduced no new claim.
|
||||
"""
|
||||
sentences: list[str] = field(default_factory=list)
|
||||
provenance: list[Provenance] = field(default_factory=list)
|
||||
role: str = "body" # "body" | "lead" | "transition"
|
||||
|
||||
def text(self) -> str:
|
||||
return " ".join(s.rstrip(". ") + "." for s in self.sentences if s.strip())
|
||||
|
||||
|
||||
@dataclass
|
||||
class Section:
|
||||
heading: str
|
||||
level: int = 2 # markdown heading level / outline depth
|
||||
blocks: list[Block] = field(default_factory=list)
|
||||
seed_ids: list[str] = field(default_factory=list) # geometry nodes of section
|
||||
summary: str = "" # one-line grounded gloss (for pptx bullets / TOC)
|
||||
|
||||
def all_provenance(self) -> list[Provenance]:
|
||||
out: list[Provenance] = []
|
||||
for b in self.blocks:
|
||||
out.extend(b.provenance)
|
||||
return out
|
||||
|
||||
|
||||
@dataclass
|
||||
class DocumentIR:
|
||||
"""The surface-neutral document. Built ONCE, projected to ANY surface."""
|
||||
title: str
|
||||
subtitle: str = ""
|
||||
sections: list[Section] = field(default_factory=list)
|
||||
seed_id: str | None = None # the geometry region root
|
||||
format_spec: dict[str, Any] = field(default_factory=dict) # requested shape
|
||||
meta: dict[str, Any] = field(default_factory=dict)
|
||||
|
||||
# -- geometry facets (what non-text projectors consume) ----------------- #
|
||||
def all_provenance(self) -> list[Provenance]:
|
||||
out: list[Provenance] = []
|
||||
for s in self.sections:
|
||||
out.extend(s.all_provenance())
|
||||
return out
|
||||
|
||||
def claim_count(self) -> int:
|
||||
return sum(1 for p in self.all_provenance() if p.kind in ("fact", "interpretation"))
|
||||
|
||||
def ungrounded_count(self) -> int:
|
||||
"""Claims with no traceable node — MUST be zero for a faithful doc."""
|
||||
return sum(1 for p in self.all_provenance()
|
||||
if p.kind in ("fact", "interpretation") and not p.node_id)
|
||||
@@ -1,81 +0,0 @@
|
||||
"""generate.py — drive the projector: one geometry region -> many surfaces.
|
||||
|
||||
Proves the thesis with REAL output: builds ONE surface-neutral DocumentIR from
|
||||
Neuron's OWN self-geometry (read-only against the live soul via the proven
|
||||
faculty), then EMITS it to Markdown, docx, and MIDI — the same plan/realize/
|
||||
cohere, three surfaces. Writes the files + the faithfulness audit to ./out/.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
|
||||
_HERE = os.path.dirname(os.path.abspath(__file__))
|
||||
sys.path.insert(0, _HERE)
|
||||
|
||||
import pipeline # noqa: E402
|
||||
import provenance # noqa: E402
|
||||
from geometry import load_self_region # noqa: E402
|
||||
|
||||
OUT = os.path.join(_HERE, "out")
|
||||
|
||||
|
||||
def _emit_all(doc, stem):
|
||||
"""Emit one IR to every text/audio surface + audit + provenance."""
|
||||
for surface in ("markdown", "docx", "midi"):
|
||||
data = pipeline.emit(doc, surface)
|
||||
proj = pipeline.get_projector(surface)
|
||||
path = os.path.join(OUT, f"{stem}.{proj.ext}")
|
||||
with open(path, "wb") as f:
|
||||
f.write(data)
|
||||
print(f" emitted {surface:9s} -> {os.path.basename(path)} ({len(data)} bytes)")
|
||||
a = provenance.audit(doc)
|
||||
with open(os.path.join(OUT, f"{stem}.audit.json"), "w") as f:
|
||||
json.dump(a, f, indent=2)
|
||||
with open(os.path.join(OUT, f"{stem}.provenance.md"), "w") as f:
|
||||
f.write(provenance.trace_table(doc))
|
||||
print(" audit:", {k: a[k] for k in ("claims", "ungrounded_claims",
|
||||
"negations_preserved", "distinct_source_nodes", "faithful")})
|
||||
return a
|
||||
|
||||
|
||||
def main():
|
||||
os.makedirs(OUT, exist_ok=True)
|
||||
print("surfaces registered:", pipeline.available_surfaces())
|
||||
|
||||
# ---- Document 1: Neuron's self-description (marquee) ------------------- #
|
||||
print("\n[1] Neuron self-description")
|
||||
region = load_self_region(max_nodes=9)
|
||||
print(" self region:", region)
|
||||
doc1 = pipeline.build_ir(
|
||||
None, region=region,
|
||||
title="Neuron: A Self-Description from Its Own Geometry",
|
||||
subtitle="Projected efferently from the engram — every claim traces a node.",
|
||||
format_spec={"genre": "self-description", "register": "expository"},
|
||||
max_sections=5, conf_floor=0.6)
|
||||
print(f" IR: {len(doc1.sections)} sections, {doc1.claim_count()} claims, "
|
||||
f"ungrounded={doc1.ungrounded_count()}")
|
||||
_emit_all(doc1, "neuron-self")
|
||||
|
||||
# ---- Document 2: a coherent, clean whitepaper-style section ------------ #
|
||||
print("\n[2] Whitepaper-style section (coherent clean region)")
|
||||
doc2, _ = pipeline.project(
|
||||
["chronoception", "time", "awareness", "engram", "temporal"],
|
||||
surface="markdown",
|
||||
title="Temporal Awareness in the Engram",
|
||||
subtitle="A section projected from the geometry of chronoception.",
|
||||
format_spec={"genre": "whitepaper-section", "register": "technical"},
|
||||
max_sections=4)
|
||||
print(f" IR: {len(doc2.sections)} sections, {doc2.claim_count()} claims, "
|
||||
f"ungrounded={doc2.ungrounded_count()}")
|
||||
_emit_all(doc2, "engram-temporal")
|
||||
|
||||
# echo both markdowns so they are visible in the run log
|
||||
for stem, doc in (("neuron-self", doc1), ("engram-temporal", doc2)):
|
||||
print(f"\n===== GENERATED MARKDOWN — {stem} =====\n")
|
||||
print(pipeline.emit(doc, "markdown").decode())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -1,129 +0,0 @@
|
||||
"""geometry.py — READ-ONLY loader for a meaning-geometry region.
|
||||
|
||||
The efferent projector never writes to the soul. This module reaches the
|
||||
geometry through the PROVEN, read-only neuron-talk faculty (``engram_client``,
|
||||
GET-only, which physically refuses non-GET methods) against the running sidecar
|
||||
soul. The live daemon :8742 / :7770 is contacted ONLY through that read-only
|
||||
client — never mutated.
|
||||
|
||||
A "region" is a seed node plus a bounded neighborhood: the manifold that will
|
||||
become the document's skeleton. We pool a few single-term lexical searches
|
||||
(the engram search is a single-term matcher) and, when available, walk one hop
|
||||
of reified neighbors, then rank by self/importance signal.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
# Wire in the proven faculty (own-the-core: we reuse it, we do not fork it).
|
||||
_NT = os.path.expanduser("~/Desktop/neuron-talk")
|
||||
_LR = os.path.expanduser("~/Desktop/lang-realizers")
|
||||
for _p in (_NT, _LR):
|
||||
if _p not in sys.path:
|
||||
sys.path.insert(0, _p)
|
||||
|
||||
from engram_client import ReadOnlyEngramClient # noqa: E402
|
||||
|
||||
|
||||
class Region:
|
||||
"""A geometry region: ranked nodes + the reified edges among them."""
|
||||
|
||||
def __init__(self, seed: str, nodes: list[dict], edges: list[dict]):
|
||||
self.seed = seed
|
||||
self.nodes = nodes # ranked engram node dicts
|
||||
self.edges = edges # [{src, dst, edge, ...}]
|
||||
self.by_id = {n["id"]: n for n in nodes if n.get("id")}
|
||||
|
||||
def __repr__(self):
|
||||
return f"<Region seed={self.seed!r} nodes={len(self.nodes)} edges={len(self.edges)}>"
|
||||
|
||||
|
||||
def _prose_quality(content: str) -> float:
|
||||
"""Reward clean expository prose; penalize shouty banner-dense nodes.
|
||||
|
||||
A high ALLCAPS-word ratio or very short content signals a banner/telegraphic
|
||||
memory node that extracts into garbage. Clean declarative prose scores high.
|
||||
"""
|
||||
if not content or not content.strip():
|
||||
return 0.0
|
||||
words = content.split()
|
||||
if len(words) < 8:
|
||||
return 0.1
|
||||
caps = sum(1 for w in words if len(w) > 2 and w.strip(".,:;'\"-").isupper())
|
||||
caps_ratio = caps / max(1, len(words))
|
||||
# sentences with lowercase interior words read as prose
|
||||
lower = sum(1 for w in words if w[:1].islower())
|
||||
lower_ratio = lower / max(1, len(words))
|
||||
return max(0.0, 1.2 * lower_ratio - 2.0 * caps_ratio)
|
||||
|
||||
|
||||
def _relevance(content: str, terms: list[str]) -> float:
|
||||
"""Topical relevance to the seed terms — keeps a region ON-THEME so a clean
|
||||
but off-topic node cannot hijack the document."""
|
||||
if not terms:
|
||||
return 0.0
|
||||
low = (content or "").lower()
|
||||
hits = sum(1 for t in terms if t.lower() in low)
|
||||
return hits / max(1, len(terms))
|
||||
|
||||
|
||||
def _node_rank(n: dict, terms: list[str] | None = None) -> float:
|
||||
return (float(n.get("importance") or 0.0) * 2.0
|
||||
+ float(n.get("salience") or 0.0)
|
||||
+ 1.5 * _prose_quality(n.get("content") or "")
|
||||
+ 2.0 * _relevance(n.get("content") or "", terms or [])
|
||||
+ (0.5 if (n.get("content") or "").strip() else 0.0))
|
||||
|
||||
|
||||
def load_region(seed_terms: list[str] | str, *, client: ReadOnlyEngramClient | None = None,
|
||||
max_nodes: int = 10, per_term: int = 20, hop: bool = True) -> Region:
|
||||
"""Pull a bounded geometry region around ``seed_terms`` (read-only).
|
||||
|
||||
``seed_terms`` may be a single string or several probe terms; results are
|
||||
pooled and de-duplicated. When ``hop`` and the reified neighbor endpoint is
|
||||
live, one hop of neighbors is folded in so the region is a real
|
||||
neighborhood, not just a keyword hit list.
|
||||
"""
|
||||
client = client or ReadOnlyEngramClient()
|
||||
if isinstance(seed_terms, str):
|
||||
seed_terms = [seed_terms]
|
||||
|
||||
pool: dict[str, dict] = {}
|
||||
for term in seed_terms:
|
||||
for n in client.search(term, limit=per_term):
|
||||
if isinstance(n, dict) and n.get("id"):
|
||||
pool.setdefault(n["id"], n)
|
||||
|
||||
ranked = sorted(pool.values(), key=lambda n: _node_rank(n, seed_terms),
|
||||
reverse=True)
|
||||
nodes = ranked[:max_nodes]
|
||||
|
||||
edges: list[dict] = []
|
||||
if hop and nodes:
|
||||
present = {n["id"] for n in nodes}
|
||||
for n in list(nodes):
|
||||
try:
|
||||
for nb in client.neighbors(n["id"]):
|
||||
node = nb.get("node") if isinstance(nb, dict) else None
|
||||
edge = nb.get("edge") if isinstance(nb, dict) else None
|
||||
if node and node.get("id"):
|
||||
edges.append({"src": n["id"], "dst": node["id"],
|
||||
"edge": edge})
|
||||
# fold a strong neighbor into the region (bounded)
|
||||
if (node["id"] not in present and len(nodes) < max_nodes + 6
|
||||
and _node_rank(node, seed_terms) > 0.4):
|
||||
present.add(node["id"])
|
||||
nodes.append(node)
|
||||
except Exception: # noqa: BLE001 — read-only best-effort; never fatal
|
||||
continue
|
||||
|
||||
return Region(seed=", ".join(seed_terms), nodes=nodes, edges=edges)
|
||||
|
||||
|
||||
def load_self_region(client: ReadOnlyEngramClient | None = None,
|
||||
max_nodes: int = 10) -> Region:
|
||||
"""The self/identity region — Neuron's own geometry, for self-description."""
|
||||
return load_region(["self", "identity", "Neuron", "values", "memory",
|
||||
"imprint", "consciousness"],
|
||||
client=client, max_nodes=max_nodes)
|
||||
@@ -1,67 +0,0 @@
|
||||
"""pipeline.py — the Efferent Multimodal Projector, top level.
|
||||
|
||||
geometry region + surface/format spec
|
||||
-> PLAN (manifold -> document skeleton/DAG)
|
||||
-> REALIZE (proven realizer, sentence -> passage, each section faithful)
|
||||
-> COHERE (document-level flow / transitions, not stitched sentences)
|
||||
-> EMIT (pluggable SurfaceProjector -> the target surface)
|
||||
|
||||
THE SURFACE IS A PARAMETER. ``project(...)`` builds the geometry-carrying
|
||||
DocumentIR once, then hands it to whichever surface projector the caller named.
|
||||
Markdown, docx, and midi (music) are all the SAME IR emitted differently. That
|
||||
is the efferent multimodal projector: geometry -> any surface.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
_HERE = os.path.dirname(os.path.abspath(__file__))
|
||||
sys.path.insert(0, _HERE)
|
||||
sys.path.insert(0, os.path.join(_HERE, "projectors"))
|
||||
|
||||
from cohere import cohere_document # noqa: E402
|
||||
from document_ir import DocumentIR # noqa: E402
|
||||
from geometry import Region, load_region # noqa: E402
|
||||
from plan import plan_document # noqa: E402
|
||||
from realize import realize_document # noqa: E402
|
||||
|
||||
# registering the projectors (import for side-effect: each self-registers)
|
||||
import projectors.markdown # noqa: E402,F401
|
||||
import projectors.docx # noqa: E402,F401
|
||||
import projectors.midi # noqa: E402,F401
|
||||
import projectors.seams # noqa: E402,F401
|
||||
from projectors.base import available_surfaces, get_projector # noqa: E402
|
||||
|
||||
|
||||
def build_ir(seed_terms, *, title: str, subtitle: str = "",
|
||||
format_spec: dict | None = None,
|
||||
region: Region | None = None,
|
||||
max_sections: int = 8, conf_floor: float = 0.55) -> DocumentIR:
|
||||
"""geometry -> PLAN -> REALIZE -> COHERE = the surface-neutral DocumentIR."""
|
||||
region = region or load_region(seed_terms)
|
||||
doc = plan_document(region, title=title, subtitle=subtitle,
|
||||
format_spec=format_spec or {},
|
||||
conf_floor=conf_floor, max_sections=max_sections)
|
||||
doc = realize_document(doc)
|
||||
doc = cohere_document(doc)
|
||||
return doc
|
||||
|
||||
|
||||
def emit(doc: DocumentIR, surface: str) -> bytes:
|
||||
"""EMIT: project the built IR onto one surface (surface = a parameter)."""
|
||||
return get_projector(surface).project(doc)
|
||||
|
||||
|
||||
def project(seed_terms, *, surface: str, title: str, subtitle: str = "",
|
||||
format_spec: dict | None = None, region: Region | None = None,
|
||||
max_sections: int = 8) -> tuple[DocumentIR, bytes]:
|
||||
"""The full efferent projection: geometry + surface -> (IR, bytes)."""
|
||||
doc = build_ir(seed_terms, title=title, subtitle=subtitle,
|
||||
format_spec=format_spec, region=region,
|
||||
max_sections=max_sections)
|
||||
return doc, emit(doc, surface)
|
||||
|
||||
|
||||
__all__ = ["build_ir", "emit", "project", "available_surfaces",
|
||||
"get_projector", "load_region", "DocumentIR"]
|
||||
@@ -1,192 +0,0 @@
|
||||
"""plan.py — PLAN stage: geometry region -> document skeleton (a DAG/outline).
|
||||
|
||||
The manifold becomes the skeleton. We extract faithful propositions from the
|
||||
region's nodes (the proven neuron-talk extractor, SACRED polarity preserved),
|
||||
apply a quality floor, then GROUP them into sections. Grouping is by source
|
||||
node — each engram node is one coherent topic, so one salient node becomes one
|
||||
section. The section ORDER is the node ranking (importance/salience): the
|
||||
geometry decides the outline, not a template.
|
||||
|
||||
Output: a DocumentIR whose sections carry seed node ids and empty blocks. REALIZE
|
||||
fills the blocks; the plan owns the structure.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
|
||||
_NT = os.path.expanduser("~/Desktop/neuron-talk")
|
||||
_LR = os.path.expanduser("~/Desktop/lang-realizers")
|
||||
for _p in (_NT, _LR):
|
||||
if _p not in sys.path:
|
||||
sys.path.insert(0, _p)
|
||||
|
||||
import propositions # noqa: E402 (the proven, faithful extractor)
|
||||
|
||||
from document_ir import DocumentIR, Section # noqa: E402
|
||||
from geometry import Region # noqa: E402
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Proposition quality — keep only clean, well-grounded claims.
|
||||
# --------------------------------------------------------------------------- #
|
||||
_JUNK_RE = re.compile(r"[.][a-z]{1,3}\b|[^A-Za-z0-9 '\-]") # ".o", stray symbols
|
||||
|
||||
|
||||
def _has_banner_token(s: str) -> bool:
|
||||
"""True if any word is an ALLCAPS banner token (DHARMA, ENGRAM, MEASURED)."""
|
||||
for w in (s or "").split():
|
||||
core = w.strip(".,:;'\"-")
|
||||
if len(core) > 2 and core.isupper():
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def _clean_prop(p, floor: float) -> bool:
|
||||
if p.confidence < floor:
|
||||
return False
|
||||
if not p.subject or not (p.object or (p.obj_np is not None)):
|
||||
return False
|
||||
subj = (p.subject or "").strip()
|
||||
obj = (p.object or "").strip()
|
||||
if len(subj) < 2:
|
||||
return False
|
||||
# banner-derived shouty fragments read as garbage in prose
|
||||
if _has_banner_token(subj) or _has_banner_token(obj):
|
||||
return False
|
||||
if propositions._is_shouty(p.sentence or ""):
|
||||
return False
|
||||
# junk tokens: file-extension fragments (".o"), stray non-word symbols
|
||||
if _JUNK_RE.search(subj) or _JUNK_RE.search(obj):
|
||||
return False
|
||||
# a proposition whose object repeats the subject is usually a parse artifact
|
||||
if obj and subj.lower() == obj.lower():
|
||||
return False
|
||||
# a bare copula with no real complement ("X is it") reads as noise
|
||||
if p.predicate == "be" and obj.lower() in ("it", "no", "nothing", "empty", ""):
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def _dedup(props):
|
||||
"""Drop duplicate claims. Two axes: (a) identical (pred,obj,polarity), and
|
||||
(b) same (subject,predicate) — which collapses a mis-split compound like
|
||||
"detection is post-hoc eval" -> "Detection is post/hoc/eval" into one claim
|
||||
(keep the highest-confidence surface)."""
|
||||
props = sorted(props, key=lambda p: p.confidence, reverse=True)
|
||||
seen_po, seen_sp, out = set(), set(), []
|
||||
for p in props:
|
||||
subj = (p.subject or "").lower()
|
||||
po = (p.predicate, (p.object or "").lower(), p.polarity)
|
||||
sp = (subj, p.predicate, p.polarity)
|
||||
if po in seen_po or sp in seen_sp:
|
||||
continue
|
||||
seen_po.add(po)
|
||||
seen_sp.add(sp)
|
||||
out.append(p)
|
||||
return out
|
||||
|
||||
|
||||
# --------------------------------------------------------------------------- #
|
||||
# Heading derivation — a clean human heading from a node.
|
||||
# --------------------------------------------------------------------------- #
|
||||
_HEADING_RE = re.compile(r"^\s*#{1,4}\s+(.{2,70})\s*$", re.M)
|
||||
# node-type / system labels that are NOT topical headings
|
||||
_NONTOPIC_LABEL = re.compile(r"^(memory|node|knowledge|doc|session)[:/]", re.I)
|
||||
|
||||
|
||||
def _titlecase_banner(s: str) -> str:
|
||||
"""A shouty banner ("CHRONOCEPTION — SCALE-INVARIANCE") makes a fine title
|
||||
once Title-cased. Keep short acronyms uppercase."""
|
||||
def fix(w):
|
||||
core = w.strip("—-:,.")
|
||||
if len(core) <= 3 and core.isupper():
|
||||
return w # acronym
|
||||
return w.capitalize()
|
||||
return " ".join(fix(w) for w in s.split())
|
||||
|
||||
|
||||
def _clean_heading(text: str) -> str | None:
|
||||
"""First line only, no markdown, capped, banner Title-cased. None if unusable."""
|
||||
if not text:
|
||||
return None
|
||||
line = text.strip().splitlines()[0]
|
||||
line = re.sub(r"^#+\s*", "", line).strip().strip("#").strip()
|
||||
# cut at a natural break so a long banner heading stays a heading, not a para
|
||||
for sep in (" — ", " – ", ": ", ". "):
|
||||
if sep in line and len(line) > 48:
|
||||
line = line.split(sep)[0].strip()
|
||||
break
|
||||
if not (3 <= len(line) <= 64):
|
||||
return None
|
||||
if propositions._is_shouty(line):
|
||||
line = _titlecase_banner(line)
|
||||
return line or None
|
||||
|
||||
|
||||
def _heading_for(node: dict, fallback: str) -> str:
|
||||
label = (node.get("label") or "").strip()
|
||||
content = node.get("content") or ""
|
||||
candidates: list[str] = []
|
||||
# a node-type label ("memory:remembered") is never a topic — skip it
|
||||
if label and not _NONTOPIC_LABEL.match(label):
|
||||
candidates.append(label)
|
||||
m = _HEADING_RE.search(content)
|
||||
if m:
|
||||
candidates.append(m.group(1))
|
||||
# the leading banner/first sentence of the content is often the real title
|
||||
first = re.split(r"(?<=[.\n])", content.strip(), maxsplit=1)[0] if content.strip() else ""
|
||||
candidates.append(first)
|
||||
for c in candidates:
|
||||
h = _clean_heading(c)
|
||||
if h:
|
||||
return h
|
||||
return fallback
|
||||
|
||||
|
||||
def plan_document(region: Region, *, title: str, subtitle: str = "",
|
||||
format_spec: dict | None = None,
|
||||
conf_floor: float = 0.55,
|
||||
max_sections: int = 8,
|
||||
max_claims_per_section: int = 6) -> DocumentIR:
|
||||
"""Region -> DocumentIR skeleton. The geometry dictates the outline."""
|
||||
format_spec = format_spec or {}
|
||||
doc = DocumentIR(title=title, subtitle=subtitle,
|
||||
seed_id=region.nodes[0]["id"] if region.nodes else None,
|
||||
format_spec=format_spec)
|
||||
|
||||
made = 0
|
||||
seen_headings: set[str] = set()
|
||||
for node in region.nodes:
|
||||
if made >= max_sections:
|
||||
break
|
||||
props = propositions.extract(node.get("content") or "",
|
||||
node_id=node.get("id"),
|
||||
node_importance=float(node.get("importance") or 0.0),
|
||||
max_sentences=10)
|
||||
props = [p for p in props if _clean_prop(p, conf_floor)]
|
||||
props = _dedup(props)
|
||||
props.sort(key=lambda p: p.confidence, reverse=True)
|
||||
props = props[:max_claims_per_section]
|
||||
if not props:
|
||||
continue
|
||||
heading = _heading_for(node, fallback=f"Region {made + 1}")
|
||||
# cross-section dedup: a topic appears once. Distinguish by top claim
|
||||
# subject, else drop the collision so the outline stays clean.
|
||||
if heading.lower() in seen_headings:
|
||||
subj = (props[0].subject or "").strip().title()
|
||||
alt = f"{heading}: {subj}" if subj and subj.lower() not in heading.lower() else None
|
||||
if alt and alt.lower() not in seen_headings and len(alt) <= 64:
|
||||
heading = alt
|
||||
else:
|
||||
continue
|
||||
seen_headings.add(heading.lower())
|
||||
sec = Section(heading=heading, level=2, seed_ids=[node["id"]])
|
||||
# stash the planned propositions on the section for REALIZE
|
||||
sec.__dict__["_planned_props"] = props
|
||||
sec.__dict__["_node"] = node
|
||||
doc.sections.append(sec)
|
||||
made += 1
|
||||
|
||||
return doc
|
||||
@@ -1,106 +0,0 @@
|
||||
"""base.py — the SurfaceProjector interface + registry.
|
||||
|
||||
THE key abstraction of the efferent projector: a projector is a pure function
|
||||
from the surface-neutral, geometry-carrying DocumentIR to bytes on a target
|
||||
SURFACE. The surface is a PARAMETER. Adding a surface = registering one more
|
||||
projector; nothing upstream (plan/realize/cohere) changes.
|
||||
|
||||
DocumentIR --project--> bytes (per surface)
|
||||
|
||||
A TEXT projector reads ``block.sentences``. A NON-TEXT projector (music, image,
|
||||
video) reads ``block.provenance`` — the geometry the IR carries — and decodes it
|
||||
onto its surface. Both consume the SAME IR. That symmetry is the whole design:
|
||||
the realizer generalizes into a multimodal projector, geometry -> any surface.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Protocol, runtime_checkable
|
||||
|
||||
import sys
|
||||
import os
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
from document_ir import DocumentIR # noqa: E402
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class SurfaceProjector(Protocol):
|
||||
"""Geometry-document -> one surface. Implementations MUST be pure & faithful.
|
||||
|
||||
THE ONE SHARED SEAM. Every surface — text, music, image, video — conforms to
|
||||
this single contract:
|
||||
|
||||
project(frame: DocumentIR) -> bytes
|
||||
|
||||
where ``frame`` is the geometry-carrying meaning-geometry (the SemFrame at
|
||||
document scale; a single utterance is the degenerate one-section frame).
|
||||
|
||||
RECOMMENDED INTERNAL SHAPE (the peer music/text decomposition, blessed here
|
||||
so all surfaces share it): a projector may split ``project`` into
|
||||
|
||||
spec = self.plan(frame) # meaning-geometry -> surface-specific spec
|
||||
bytes = self.realize(spec) # spec -> surface, via this projector's PROFILE
|
||||
|
||||
``project`` is then ``realize(plan(frame))``. The PROFILE (a text lang-profile,
|
||||
a music instr/mode-profile, an image layout-profile) is a property of the
|
||||
projector instance — the pluggable knob. See :class:`TwoStageProjector`.
|
||||
|
||||
A TEXT projector's plan reads ``frame`` sentences; a MUSIC/IMAGE projector's
|
||||
plan reads ``frame.all_provenance()`` — the geometry — and derives its spec
|
||||
(pitch/harmony/rhythm, or layout) FROM the meaning, deterministically. Same
|
||||
frame, different profile.
|
||||
"""
|
||||
|
||||
surface: str # "markdown" | "docx" | "midi" | "audio" | "image" | "video"
|
||||
media_type: str # MIME type of the emitted bytes
|
||||
ext: str # file extension (no dot)
|
||||
modality: str # "text" | "audio" | "image" | "video"
|
||||
profile: object # the pluggable per-surface profile (may be None)
|
||||
|
||||
def project(self, doc: DocumentIR) -> bytes:
|
||||
"""Emit the document on this surface. Returns raw bytes."""
|
||||
...
|
||||
|
||||
|
||||
class TwoStageProjector:
|
||||
"""Optional base for the peer plan()/realize() decomposition.
|
||||
|
||||
Subclasses implement ``plan(frame) -> spec`` and ``realize(spec) -> bytes``;
|
||||
``project`` is their composition. This is exactly the peer music interface
|
||||
(spec = plan(frame, profile); surface = realize(spec, profile)) expressed so
|
||||
that it still satisfies the single ``SurfaceProjector.project`` seam. Text,
|
||||
music, and image projectors can all subclass this and remain interchangeable.
|
||||
"""
|
||||
|
||||
surface: str = ""
|
||||
media_type: str = ""
|
||||
ext: str = ""
|
||||
modality: str = ""
|
||||
profile: object = None
|
||||
|
||||
def plan(self, doc: DocumentIR): # -> spec
|
||||
raise NotImplementedError
|
||||
|
||||
def realize(self, spec) -> bytes:
|
||||
raise NotImplementedError
|
||||
|
||||
def project(self, doc: DocumentIR) -> bytes:
|
||||
return self.realize(self.plan(doc))
|
||||
|
||||
|
||||
_REGISTRY: dict[str, SurfaceProjector] = {}
|
||||
|
||||
|
||||
def register(projector: SurfaceProjector) -> SurfaceProjector:
|
||||
_REGISTRY[projector.surface] = projector
|
||||
return projector
|
||||
|
||||
|
||||
def get_projector(surface: str) -> SurfaceProjector:
|
||||
if surface not in _REGISTRY:
|
||||
raise KeyError(f"no projector registered for surface {surface!r}; "
|
||||
f"have {sorted(_REGISTRY)}")
|
||||
return _REGISTRY[surface]
|
||||
|
||||
|
||||
def available_surfaces() -> list[str]:
|
||||
return sorted(_REGISTRY)
|
||||
@@ -1,113 +0,0 @@
|
||||
"""docx.py — the .docx surface projector: an OWN minimal OOXML emitter.
|
||||
|
||||
Own-the-core: a .docx is just a ZIP of a few XML parts (WordprocessingML). We
|
||||
emit it with the standard library only — ``zipfile`` + string XML — no
|
||||
python-docx, no external dependency. This proves a "richer structured format"
|
||||
surface without importing anyone else's toolkit.
|
||||
|
||||
Parts emitted (the minimal valid set + a styles part for real headings):
|
||||
[Content_Types].xml
|
||||
_rels/.rels
|
||||
word/_rels/document.xml.rels
|
||||
word/styles.xml (Title / Heading1 / Heading2 / Normal)
|
||||
word/document.xml (the content)
|
||||
|
||||
Like the markdown projector it reads only the IR's realized sentences; it
|
||||
invents nothing. The surface differs, the faithful content does not.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
import os
|
||||
import sys
|
||||
import zipfile
|
||||
from xml.sax.saxutils import escape
|
||||
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
from document_ir import DocumentIR # noqa: E402
|
||||
from projectors.base import register # noqa: E402
|
||||
|
||||
_CONTENT_TYPES = """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||||
<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
|
||||
<Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
|
||||
<Default Extension="xml" ContentType="application/xml"/>
|
||||
<Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>
|
||||
<Override PartName="/word/styles.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.styles+xml"/>
|
||||
</Types>"""
|
||||
|
||||
_RELS = """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||||
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
|
||||
<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/>
|
||||
</Relationships>"""
|
||||
|
||||
_DOC_RELS = """<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||||
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
|
||||
<Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/>
|
||||
</Relationships>"""
|
||||
|
||||
_W = "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
|
||||
|
||||
_STYLES = f"""<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||||
<w:styles xmlns:w="{_W}">
|
||||
<w:style w:type="paragraph" w:default="1" w:styleId="Normal"><w:name w:val="Normal"/>
|
||||
<w:rPr><w:sz w:val="22"/></w:rPr></w:style>
|
||||
<w:style w:type="paragraph" w:styleId="Title"><w:name w:val="Title"/>
|
||||
<w:pPr><w:spacing w:after="240"/></w:pPr>
|
||||
<w:rPr><w:b/><w:sz w:val="52"/></w:rPr></w:style>
|
||||
<w:style w:type="paragraph" w:styleId="Subtitle"><w:name w:val="Subtitle"/>
|
||||
<w:rPr><w:i/><w:sz w:val="28"/><w:color w:val="555555"/></w:rPr></w:style>
|
||||
<w:style w:type="paragraph" w:styleId="Heading1"><w:name w:val="heading 1"/>
|
||||
<w:pPr><w:spacing w:before="240" w:after="120"/><w:outlineLvl w:val="0"/></w:pPr>
|
||||
<w:rPr><w:b/><w:sz w:val="34"/></w:rPr></w:style>
|
||||
<w:style w:type="paragraph" w:styleId="Heading2"><w:name w:val="heading 2"/>
|
||||
<w:pPr><w:spacing w:before="200" w:after="100"/><w:outlineLvl w:val="1"/></w:pPr>
|
||||
<w:rPr><w:b/><w:sz w:val="28"/></w:rPr></w:style>
|
||||
</w:styles>"""
|
||||
|
||||
|
||||
def _para(text: str, style: str | None = None) -> str:
|
||||
ppr = f"<w:pPr><w:pStyle w:val=\"{style}\"/></w:pPr>" if style else ""
|
||||
return (f"<w:p>{ppr}<w:r><w:t xml:space=\"preserve\">"
|
||||
f"{escape(text)}</w:t></w:r></w:p>")
|
||||
|
||||
|
||||
class DocxProjector:
|
||||
surface = "docx"
|
||||
media_type = ("application/vnd.openxmlformats-officedocument."
|
||||
"wordprocessingml.document")
|
||||
ext = "docx"
|
||||
modality = "text"
|
||||
|
||||
def _document_xml(self, doc: DocumentIR) -> str:
|
||||
body: list[str] = [_para(doc.title, "Title")]
|
||||
if doc.subtitle:
|
||||
body.append(_para(doc.subtitle, "Subtitle"))
|
||||
abstract = doc.meta.get("abstract")
|
||||
if abstract is not None and abstract.sentences:
|
||||
body.append(_para(abstract.text()))
|
||||
for sec in doc.sections:
|
||||
style = "Heading1" if sec.level <= 1 else "Heading2"
|
||||
body.append(_para(sec.heading, style))
|
||||
for block in sec.blocks:
|
||||
t = block.text()
|
||||
if t:
|
||||
body.append(_para(t))
|
||||
return (f"<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?>"
|
||||
f"<w:document xmlns:w=\"{_W}\"><w:body>"
|
||||
+ "".join(body)
|
||||
+ "<w:sectPr><w:pgSz w:w=\"12240\" w:h=\"15840\"/>"
|
||||
"<w:pgMar w:top=\"1440\" w:right=\"1440\" w:bottom=\"1440\" "
|
||||
"w:left=\"1440\"/></w:sectPr></w:body></w:document>")
|
||||
|
||||
def project(self, doc: DocumentIR) -> bytes:
|
||||
buf = io.BytesIO()
|
||||
with zipfile.ZipFile(buf, "w", zipfile.ZIP_DEFLATED) as z:
|
||||
z.writestr("[Content_Types].xml", _CONTENT_TYPES)
|
||||
z.writestr("_rels/.rels", _RELS)
|
||||
z.writestr("word/_rels/document.xml.rels", _DOC_RELS)
|
||||
z.writestr("word/styles.xml", _STYLES)
|
||||
z.writestr("word/document.xml", self._document_xml(doc))
|
||||
return buf.getvalue()
|
||||
|
||||
|
||||
register(DocxProjector())
|
||||
@@ -1,45 +0,0 @@
|
||||
"""markdown.py — the Markdown surface projector (text facet).
|
||||
|
||||
The most tractable surface, and the reference implementation: reads the IR's
|
||||
realized sentences and lays them out as Markdown. Introduces no content — it is
|
||||
pure typography over the faithful text the realizer produced.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
from document_ir import DocumentIR # noqa: E402
|
||||
from projectors.base import register # noqa: E402
|
||||
|
||||
|
||||
class MarkdownProjector:
|
||||
surface = "markdown"
|
||||
media_type = "text/markdown"
|
||||
ext = "md"
|
||||
modality = "text"
|
||||
|
||||
def render_str(self, doc: DocumentIR) -> str:
|
||||
lines: list[str] = [f"# {doc.title}"]
|
||||
if doc.subtitle:
|
||||
lines.append(f"\n*{doc.subtitle}*")
|
||||
abstract = doc.meta.get("abstract")
|
||||
if abstract is not None and abstract.sentences:
|
||||
lines.append("")
|
||||
lines.append(abstract.text())
|
||||
for sec in doc.sections:
|
||||
lines.append("")
|
||||
lines.append(f"{'#' * max(2, sec.level)} {sec.heading}")
|
||||
for block in sec.blocks:
|
||||
body = block.text()
|
||||
if body:
|
||||
lines.append("")
|
||||
lines.append(body)
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
def project(self, doc: DocumentIR) -> bytes:
|
||||
return self.render_str(doc).encode("utf-8")
|
||||
|
||||
|
||||
register(MarkdownProjector())
|
||||
@@ -1,133 +0,0 @@
|
||||
"""midi.py — the MUSIC surface projector: geometry -> symbolic music (MIDI).
|
||||
|
||||
The first NON-TEXT surface, and the proof of the general shape. "Music is
|
||||
language and it is math" (Will): symbolic music is tractable and geometry-native,
|
||||
so it is the natural efferent twin to try first after text.
|
||||
|
||||
CRUCIALLY this projector does NOT read the realized sentences. It reads the IR's
|
||||
GEOMETRY facet — ``block.provenance`` — and DECODES each edge onto a musical
|
||||
surface. That is the whole thesis of the multimodal projector: the same
|
||||
geometry-carrying IR drives text AND music; a text projector reads the words, a
|
||||
music projector reads the meaning-geometry. The mapping is deterministic and
|
||||
faithful to the geometry's structure:
|
||||
|
||||
relation lemma -> scale degree (same relation -> same pitch class;
|
||||
meaning has a consistent sonic form)
|
||||
polarity -> mode (aff = major third above; neg = minor
|
||||
third / lowered — SACRED polarity is
|
||||
audible, a negated edge sounds negated)
|
||||
confidence -> note duration (stronger grounding rings longer)
|
||||
importance -> velocity (more important source = louder)
|
||||
section -> phrase + register shift (structure becomes musical form)
|
||||
|
||||
Own-the-core: a Standard MIDI File is a header chunk + a track chunk of
|
||||
delta-timed events. We emit the raw bytes with ``struct`` — no external MIDI
|
||||
library. Format 0, one track.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
import os
|
||||
import struct
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
from document_ir import DocumentIR, Provenance # noqa: E402
|
||||
from projectors.base import TwoStageProjector, register # noqa: E402
|
||||
|
||||
_TICKS = 480 # ticks per quarter note
|
||||
_C_MAJOR = [0, 2, 4, 5, 7, 9, 11] # semitone offsets of a diatonic scale
|
||||
|
||||
|
||||
def _vlq(n: int) -> bytes:
|
||||
"""MIDI variable-length quantity encoding of a delta time."""
|
||||
if n == 0:
|
||||
return b"\x00"
|
||||
out = bytearray()
|
||||
out.append(n & 0x7F)
|
||||
n >>= 7
|
||||
while n:
|
||||
out.insert(0, (n & 0x7F) | 0x80)
|
||||
n >>= 7
|
||||
return bytes(out)
|
||||
|
||||
|
||||
def _degree_for(relation: str) -> int:
|
||||
"""Stable scale degree for a relation lemma (same relation -> same pitch)."""
|
||||
if not relation:
|
||||
return 0
|
||||
return sum(ord(c) for c in relation.lower()) % len(_C_MAJOR)
|
||||
|
||||
|
||||
def _note_for(p: Provenance, base: int) -> tuple[int, int, int]:
|
||||
"""(pitch, velocity, duration_ticks) for one geometry edge."""
|
||||
root = base + _C_MAJOR[_degree_for(p.relation)]
|
||||
# polarity -> mode: affirmed edges take the bright major third, negated edges
|
||||
# take the darker minor third. The negation is AUDIBLE and never dropped.
|
||||
third = 4 if p.polarity == "aff" else 3
|
||||
pitch = max(24, min(96, root + (third if p.confidence >= 0.5 else 0)))
|
||||
velocity = int(56 + 60 * min(1.0, max(0.0, p.importance)))
|
||||
velocity = max(40, min(120, velocity))
|
||||
# confidence -> duration: quarter .. dotted-half
|
||||
dur = int(_TICKS * (0.5 + 1.5 * min(1.0, max(0.0, p.confidence))))
|
||||
return pitch, velocity, dur
|
||||
|
||||
|
||||
# a mode-profile: the pluggable musical knob (the peer's mode_profile). Scale +
|
||||
# tempo. Swapping this profile re-voices the SAME geometry — surface as parameter.
|
||||
_DEFAULT_PROFILE = {"scale": _C_MAJOR, "tempo_us": 500000,
|
||||
"registers": [60, 55, 64, 50, 67, 48], "program": 0}
|
||||
|
||||
|
||||
class MidiProjector(TwoStageProjector):
|
||||
"""geometry -> symbolic music, in the shared two-stage shape.
|
||||
|
||||
``plan(frame)`` -> a music_spec: an ordered list of note dicts derived
|
||||
deterministically from the frame's provenance geometry
|
||||
(the peer's ``plan(frame, profile) -> spec``).
|
||||
``realize(spec)`` -> Standard MIDI File bytes (the peer's
|
||||
``realize(spec, profile) -> surface``; here the surface
|
||||
is symbolic MIDI, the minimal audio proof — a richer
|
||||
additive-synth audio projector conforms identically).
|
||||
"""
|
||||
|
||||
surface = "midi"
|
||||
media_type = "audio/midi"
|
||||
ext = "mid"
|
||||
modality = "audio"
|
||||
|
||||
def __init__(self, profile: dict | None = None):
|
||||
self.profile = profile or _DEFAULT_PROFILE
|
||||
|
||||
# -- stage 1: meaning-geometry -> music_spec (reads the GEOMETRY facet) -- #
|
||||
def plan(self, doc: DocumentIR) -> list[dict]:
|
||||
registers = self.profile["registers"]
|
||||
spec: list[dict] = []
|
||||
for si, sec in enumerate(doc.sections):
|
||||
base = registers[si % len(registers)]
|
||||
provs = [p for p in sec.all_provenance()
|
||||
if p.kind in ("fact", "interpretation")]
|
||||
for i, p in enumerate(provs):
|
||||
pitch, vel, dur = _note_for(p, base)
|
||||
spec.append({"pitch": pitch, "velocity": vel, "dur": dur,
|
||||
"rest_before": (_TICKS // 2) if (si > 0 and i == 0) else 0,
|
||||
"relation": p.relation, "polarity": p.polarity})
|
||||
return spec
|
||||
|
||||
# -- stage 2: music_spec -> MIDI bytes (own-core, no library) ------------ #
|
||||
def realize(self, spec: list[dict]) -> bytes:
|
||||
ev = bytearray()
|
||||
ev += _vlq(0) + b"\xFF\x51\x03" + struct.pack(">I", self.profile["tempo_us"])[1:]
|
||||
ev += _vlq(0) + bytes([0xC0, self.profile["program"] & 0x7F])
|
||||
for note in spec:
|
||||
ev += _vlq(note["rest_before"]) + bytes([0x90, note["pitch"], note["velocity"]])
|
||||
ev += _vlq(note["dur"]) + bytes([0x80, note["pitch"], 0])
|
||||
ev += _vlq(0) + b"\xFF\x2F\x00"
|
||||
track = bytes(ev)
|
||||
buf = io.BytesIO()
|
||||
buf.write(b"MThd" + struct.pack(">IHHH", 6, 0, 1, _TICKS))
|
||||
buf.write(b"MTrk" + struct.pack(">I", len(track)) + track)
|
||||
return buf.getvalue()
|
||||
|
||||
|
||||
register(MidiProjector())
|
||||
@@ -1,60 +0,0 @@
|
||||
"""seams.py — documented efferent seams for IMAGE and VIDEO surfaces.
|
||||
|
||||
These are NOT implemented (per the build rails: architect, do not overbuild).
|
||||
They are registered as first-class seams so the interface PROVES it accepts
|
||||
future non-text projectors without any upstream change. Each documents exactly
|
||||
what its decoder would read from the geometry-carrying IR, making the multimodal
|
||||
generalization concrete rather than hand-wavy.
|
||||
|
||||
The symmetry that guarantees these are possible, not moonshots: they are the
|
||||
efferent twins of multimodal INGEST. If meaning can HOLD an image (ingest as
|
||||
first-class geometry), meaning can PROJECT one back. Video = image x sound x
|
||||
TIME, and the engram already stores time (chronoception). So video falls out of
|
||||
an image projector + the music projector + the stored temporal ordering.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
from document_ir import DocumentIR # noqa: E402
|
||||
from projectors.base import register # noqa: E402
|
||||
|
||||
|
||||
class _Seam:
|
||||
"""A registered-but-unimplemented projector. Names its decoder contract."""
|
||||
|
||||
def project(self, doc: DocumentIR) -> bytes: # pragma: no cover - seam
|
||||
raise NotImplementedError(
|
||||
f"{self.surface!r} projector is a documented seam, not yet built. "
|
||||
f"Decoder contract: {self.decoder_contract}")
|
||||
|
||||
|
||||
class ImageProjector(_Seam):
|
||||
surface = "image"
|
||||
media_type = "image/png"
|
||||
ext = "png"
|
||||
modality = "image"
|
||||
decoder_contract = (
|
||||
"reads block.provenance as a spatial layout — nodes become regions, edges "
|
||||
"become adjacencies; salience/importance drive size/contrast; polarity "
|
||||
"drives figure/ground. The efferent twin of image ingest (a geometry->raster "
|
||||
"decoder, learned or engineered), exactly mirroring the embedder that turned "
|
||||
"the image INTO geometry.")
|
||||
|
||||
|
||||
class VideoProjector(_Seam):
|
||||
surface = "video"
|
||||
media_type = "video/mp4"
|
||||
ext = "mp4"
|
||||
modality = "video"
|
||||
decoder_contract = (
|
||||
"image x sound x TIME. Composes the image projector (per-keyframe geometry "
|
||||
"layout) with the midi/music projector (score) along the geometry's stored "
|
||||
"temporal ordering (chronoception). Needs no new principle once image + music "
|
||||
"exist — only a muxer.")
|
||||
|
||||
|
||||
register(ImageProjector())
|
||||
register(VideoProjector())
|
||||
@@ -1,63 +0,0 @@
|
||||
"""provenance.py — the faithfulness audit + geometry->section trace.
|
||||
|
||||
A document projected from geometry is only worth anything if every claim traces
|
||||
back. This module walks the DocumentIR and proves the discipline held:
|
||||
|
||||
* ZERO ungrounded claims (every fact/interpretation has a real node id),
|
||||
* every emitted sentence maps to a geometry edge (or is a marked connective),
|
||||
* SACRED polarity survived (negations are reported, never silently dropped),
|
||||
* COHERE introduced no new geometry (connectives carry no claim).
|
||||
|
||||
It emits both a machine verdict and a human-readable geometry->section table.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from document_ir import DocumentIR
|
||||
|
||||
|
||||
def audit(doc: DocumentIR) -> dict:
|
||||
provs = doc.all_provenance()
|
||||
facts = [p for p in provs if p.kind in ("fact", "interpretation")]
|
||||
connectives = [p for p in provs if p.kind == "connective"]
|
||||
ungrounded = [p for p in facts if not p.node_id]
|
||||
negations = [p for p in facts if p.polarity == "neg"]
|
||||
node_ids = sorted({p.node_id for p in facts if p.node_id})
|
||||
return {
|
||||
"claims": len(facts),
|
||||
"connectives": len(connectives),
|
||||
"ungrounded_claims": len(ungrounded),
|
||||
"negations_preserved": len(negations),
|
||||
"distinct_source_nodes": len(node_ids),
|
||||
"faithful": len(ungrounded) == 0,
|
||||
"source_nodes": node_ids,
|
||||
}
|
||||
|
||||
|
||||
def trace_table(doc: DocumentIR) -> str:
|
||||
"""Human-readable geometry -> section -> claim provenance table."""
|
||||
lines = ["# Provenance — every claim traces geometry", ""]
|
||||
lines.append(f"**Document:** {doc.title}")
|
||||
a = audit(doc)
|
||||
lines.append(f"**Claims:** {a['claims']} · **Ungrounded:** "
|
||||
f"{a['ungrounded_claims']} · **Negations preserved:** "
|
||||
f"{a['negations_preserved']} · **Source nodes:** "
|
||||
f"{a['distinct_source_nodes']} · **Faithful:** "
|
||||
f"{'YES' if a['faithful'] else 'NO'}")
|
||||
lines.append("")
|
||||
for si, sec in enumerate(doc.sections, 1):
|
||||
lines.append(f"## {si}. {sec.heading}")
|
||||
lines.append(f"_seed nodes: {', '.join(i[:8] for i in sec.seed_ids)}_")
|
||||
lines.append("")
|
||||
lines.append("| # | realized claim | traces geometry edge |")
|
||||
lines.append("|---|----------------|----------------------|")
|
||||
n = 0
|
||||
for block in sec.blocks:
|
||||
for sent, prov in zip(block.sentences, block.provenance):
|
||||
if prov.kind == "connective":
|
||||
continue
|
||||
n += 1
|
||||
edge = prov.trace().replace("|", "\\|")
|
||||
s = sent.replace("|", "\\|")
|
||||
lines.append(f"| {n} | {s} | {edge} |")
|
||||
lines.append("")
|
||||
return "\n".join(lines) + "\n"
|
||||
@@ -1,112 +0,0 @@
|
||||
"""realize.py — REALIZE stage: fill each planned section with faithful passages.
|
||||
|
||||
Scales the PROVEN realizer from a single assertion to a passage. For each
|
||||
planned proposition we build a realizer-ready clause (the proven
|
||||
``_prop_to_clause`` mapping) and run it through the proven engine
|
||||
(``engine.realize``), which is a deterministic grammar with the SACRED negation
|
||||
contract — it never invents. Each realized sentence is paired with a
|
||||
:class:`Provenance` that pins it to the exact geometry edge it came from.
|
||||
|
||||
"Passage, not a list of sentences": within a section we lightly vary sentence
|
||||
openings and group related claims, but we add NO content the geometry did not
|
||||
assert. The only non-geometry words are function words the grammar already owns
|
||||
(articles, "and", conjunction of same-subject claims). Document-level flow is
|
||||
COHERE's job; this stage owns intra-section fluency + fidelity.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
_NT = os.path.expanduser("~/Desktop/neuron-talk")
|
||||
_LR = os.path.expanduser("~/Desktop/lang-realizers")
|
||||
for _p in (_NT, _LR):
|
||||
if _p not in sys.path:
|
||||
sys.path.insert(0, _p)
|
||||
|
||||
import engine # noqa: E402 (the proven no-LLM realizer)
|
||||
from dialogue import _prop_to_clause # noqa: E402 (proven prop -> clause)
|
||||
|
||||
from document_ir import Block, DocumentIR, Provenance, Section # noqa: E402
|
||||
|
||||
|
||||
def _provenance_from(p, kind: str = "fact") -> Provenance:
|
||||
return Provenance(
|
||||
subj_id=p.source_node_id, subject=p.subject, relation=p.predicate,
|
||||
obj=p.object, polarity=p.polarity, confidence=round(float(p.confidence), 3),
|
||||
node_id=p.source_node_id, kind=kind,
|
||||
importance=float(getattr(p, "node_importance", 0.0) or 0.0),
|
||||
salience=0.0,
|
||||
)
|
||||
|
||||
|
||||
import re as _re
|
||||
|
||||
# a well-formed declarative opens with a determiner, a proper noun, "I", or a
|
||||
# capitalized head — not a mis-parsed object pronoun or a copula fragment.
|
||||
_BAD_OPENERS = _re.compile(r"^(Me |It is I|There is|This is it|That is it)\b")
|
||||
_VACUOUS = _re.compile(r"^\w+ (is|are|was|were) (it|no|nothing|empty|those|this|that)\.?$",
|
||||
_re.I)
|
||||
|
||||
|
||||
def _good_sentence(text: str) -> bool:
|
||||
"""Fluency gate — drops degenerate realizations. NEVER loosens faithfulness;
|
||||
it only refuses to SPEAK a claim whose surface came out malformed."""
|
||||
words = text.rstrip(".").split()
|
||||
if len(words) < 3:
|
||||
return False
|
||||
if _BAD_OPENERS.search(text):
|
||||
return False
|
||||
if _VACUOUS.match(text):
|
||||
return False
|
||||
# a sentence that is mostly one-letter/two-letter tokens is a parse artifact
|
||||
short = sum(1 for w in words if len(w.strip(".,'")) <= 2)
|
||||
if short > len(words) / 2:
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def _realize_prop(p, lang: str = "en") -> tuple[str, Provenance] | None:
|
||||
"""One proposition -> (faithful sentence, provenance) or None if it drops."""
|
||||
clause = _prop_to_clause(p)
|
||||
text = engine.realize(clause, lang)
|
||||
if not text or not text.strip():
|
||||
return None
|
||||
text = text.strip()
|
||||
if not text.endswith((".", "!", "?")):
|
||||
text += "."
|
||||
# capitalize first character (proper nouns / "I" already handled by grammar)
|
||||
text = text[0].upper() + text[1:]
|
||||
if not _good_sentence(text):
|
||||
return None
|
||||
return text, _provenance_from(p)
|
||||
|
||||
|
||||
def realize_document(doc: DocumentIR, lang: str = "en") -> DocumentIR:
|
||||
"""Fill every planned section's blocks with faithful, realized passages."""
|
||||
for sec in doc.sections:
|
||||
planned = sec.__dict__.get("_planned_props", [])
|
||||
block = Block(role="body")
|
||||
summary_bits: list[str] = []
|
||||
for p in planned:
|
||||
r = _realize_prop(p, lang)
|
||||
if r is None:
|
||||
continue
|
||||
text, prov = r
|
||||
block.sentences.append(text)
|
||||
block.provenance.append(prov)
|
||||
if len(summary_bits) < 1:
|
||||
# a short grounded gloss for TOC / pptx bullets
|
||||
obj = (prov.obj or "").strip().rstrip(".")
|
||||
if obj:
|
||||
summary_bits.append(obj)
|
||||
if block.sentences:
|
||||
sec.blocks.append(block)
|
||||
sec.summary = summary_bits[0] if summary_bits else ""
|
||||
# drop the transient planning payload; the IR is now self-contained
|
||||
sec.__dict__.pop("_planned_props", None)
|
||||
sec.__dict__.pop("_node", None)
|
||||
|
||||
# prune sections that realized to nothing
|
||||
doc.sections = [s for s in doc.sections if s.blocks]
|
||||
return doc
|
||||
@@ -1,136 +0,0 @@
|
||||
// accent.el - A British-RP ACCENT as an INGESTED TRANSFORM-GEOMETRY, composed
|
||||
// onto the voice (voice (+) accent, SEPARABLE). Reads elp/data/british-accent.psv
|
||||
// into an accent MANIFOLD in the engram (override nodes + a shared accent hub),
|
||||
// and the render reads the RP formant overrides + the non-rhotic rule back from
|
||||
// that geometry. NO accent targets live in code — same discipline as the base
|
||||
// phonetics. PROVENANCE NOTE: the RP Hz values are PROVISIONAL (reconstructed-
|
||||
// from-knowledge approximations, cite Deterding1997 / Hawkins&Midgley2005 /
|
||||
// Wells1982) pending transcription from the published tables — the PIPELINE is
|
||||
// the deliverable; exact values are being source-verified separately.
|
||||
|
||||
fn ingest_accent(path: String) -> [String] {
|
||||
let content: String = fs_read(path)
|
||||
let lines: [String] = str_split(content, "\n")
|
||||
let nl: Int = native_list_len(lines)
|
||||
let amap: [String] = native_list_empty()
|
||||
let hub: String = engram_node("accent british-rp prov=PROVISIONAL cite=Deterding1997-HawkinsMidgley2005-Wells1982", "Accent", 80)
|
||||
let li: Int = 0
|
||||
while li < nl {
|
||||
let line: String = native_list_get(lines, li)
|
||||
let ll: Int = str_len(line)
|
||||
let skip: Int = 0
|
||||
if ll < 3 {
|
||||
skip = 1
|
||||
}
|
||||
if skip == 0 {
|
||||
let first: Int = str_char_code(line, 0)
|
||||
if first == 35 {
|
||||
skip = 1
|
||||
}
|
||||
}
|
||||
if skip == 0 {
|
||||
let f: [String] = str_split(line, "|")
|
||||
let nf: Int = native_list_len(f)
|
||||
if nf >= 6 {
|
||||
let key: String = native_list_get(f, 0)
|
||||
let f1: String = native_list_get(f, 1)
|
||||
let f2: String = native_list_get(f, 2)
|
||||
let f3: String = native_list_get(f, 3)
|
||||
let kind: String = native_list_get(f, 4)
|
||||
let set: String = native_list_get(f, 5)
|
||||
let cont: String = "accent british-rp " + key + " f1=" + f1 + " f2=" + f2 + " f3=" + f3 + " kind=" + kind + " set=" + set + " prov=PROVISIONAL cite=Deterding1997-HawkinsMidgley2005-Wells1982"
|
||||
let id: String = engram_node(cont, "AccentTarget", 80)
|
||||
amap = native_list_append(amap, key)
|
||||
amap = native_list_append(amap, cont)
|
||||
engram_connect(id, hub, 80, "of_accent")
|
||||
}
|
||||
}
|
||||
li = li + 1
|
||||
}
|
||||
return amap
|
||||
}
|
||||
|
||||
// RP formant override for a phoneme, read from the accent manifold. Returns
|
||||
// [f1,f2,f3] for a vowel_override record, or an empty list if none / a rule.
|
||||
fn accent_formants(amap: [String], code: String) -> [Int] {
|
||||
let out: [Int] = native_list_empty()
|
||||
let id: String = sp_map_get(amap, code)
|
||||
if str_eq(id, "") {
|
||||
return out
|
||||
}
|
||||
let j: String = id
|
||||
let isrule: Int = str_index_of(j, "drop_coda")
|
||||
if isrule >= 0 {
|
||||
return out
|
||||
}
|
||||
let f1: Int = parse_uint_from(j, "f1=")
|
||||
if f1 <= 0 {
|
||||
return out
|
||||
}
|
||||
let out = native_list_append(out, f1)
|
||||
let out = native_list_append(out, parse_uint_from(j, "f2="))
|
||||
let out = native_list_append(out, parse_uint_from(j, "f3="))
|
||||
return out
|
||||
}
|
||||
|
||||
// Is this accent non-rhotic? (reads the R rule node from the manifold)
|
||||
fn is_nonrhotic(amap: [String]) -> Int {
|
||||
let id: String = sp_map_get(amap, "R")
|
||||
if str_eq(id, "") {
|
||||
return 0
|
||||
}
|
||||
let hit: Int = str_index_of(id, "drop_coda")
|
||||
if hit >= 0 {
|
||||
return 1
|
||||
}
|
||||
return 0
|
||||
}
|
||||
|
||||
// Is this symbol a vowel? Membership in the vowel-set derived from the phonetics
|
||||
// source's class column (phonological structure — the FORMANT NUMBERS still come
|
||||
// from the organ manifold; this is only the categorical class for the rule).
|
||||
fn is_vowel_sym(vset: [String], sym: String) -> Int {
|
||||
let n: Int = native_list_len(vset)
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
if str_eq(native_list_get(vset, i), sym) {
|
||||
return 1
|
||||
}
|
||||
i = i + 1
|
||||
}
|
||||
return 0
|
||||
}
|
||||
|
||||
// Non-rhotic transform: drop a post-vocalic CODA /R/ — an R whose next non-SIL
|
||||
// phoneme is NOT a vowel (a consonant, or end of utterance). Keep INTERVOCALIC/
|
||||
// onset R (next non-SIL phoneme is a vowel, e.g. the medial R in N UW R AA N).
|
||||
fn apply_rhoticity(codes: [String], vset: [String]) -> [String] {
|
||||
let n: Int = native_list_len(codes)
|
||||
let out: [String] = native_list_empty()
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
let c: String = native_list_get(codes, i)
|
||||
let keep: Int = 1
|
||||
if str_eq(c, "R") {
|
||||
let jx: Int = i + 1
|
||||
let nextv: Int = 0
|
||||
while jx < n {
|
||||
let ncode: String = native_list_get(codes, jx)
|
||||
if str_eq(ncode, "SIL") {
|
||||
jx = jx + 1
|
||||
} else {
|
||||
nextv = is_vowel_sym(vset, ncode)
|
||||
jx = n + 1000
|
||||
}
|
||||
}
|
||||
if nextv == 0 {
|
||||
keep = 0
|
||||
}
|
||||
}
|
||||
if keep == 1 {
|
||||
out = native_list_append(out, c)
|
||||
}
|
||||
i = i + 1
|
||||
}
|
||||
return out
|
||||
}
|
||||
@@ -1,73 +0,0 @@
|
||||
// audio-demo.el - Drive the native audio surface: render a tone per instrument
|
||||
// from its LEARNED signature, then render a small meaning-phrase "piece".
|
||||
// Entry point: top-level statement calls main() (same convention as the
|
||||
// examples' top-level println(run_test())).
|
||||
|
||||
fn micros_to_str(xs: [Int]) -> String {
|
||||
let n: Int = native_list_len(xs)
|
||||
let out: String = ""
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
if i > 0 { let out: String = out + "," }
|
||||
let out: String = out + int_to_str(native_list_get(xs, i))
|
||||
let i: Int = i + 1
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// Render a 1.0s A4 (midi 69) tone from a signature file, print the parsed
|
||||
// partials (proving the numbers came from the engram .sig), write the WAV.
|
||||
fn render_tone(name: String, sigpath: String, outpath: String, table: [Int]) -> Int {
|
||||
let lines: [String] = sig_load(sigpath)
|
||||
let partials: [Int] = parse_micros(sig_field(lines, "partials"))
|
||||
println("[" + name + "] partials_n=" + sig_field(lines, "partials_n") + " parsed_partials_micro(scale 1e6)=" + micros_to_str(partials))
|
||||
println("[" + name + "] raw partials line from .sig = " + sig_field(lines, "partials"))
|
||||
let freq: Int = freq_of_midi(69)
|
||||
let note: [Int] = synth_from_sig(lines, freq, 1000, 900, 44100, table)
|
||||
let n: Int = native_list_len(note)
|
||||
let ok: Int = wav_write(outpath, note, n, 44100)
|
||||
println("[" + name + "] rendered " + int_to_str(n) + " samples -> " + outpath + " (write_ok=" + int_to_str(ok) + ")")
|
||||
return n
|
||||
}
|
||||
|
||||
fn run_demo() -> Int {
|
||||
let table: [Int] = sin_table()
|
||||
fs_mkdir("/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/out")
|
||||
|
||||
println("=== TONES: render A4 (midi 69) from each learned signature ===")
|
||||
render_tone("flute", "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/sig/flute.sig", "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/out/tone-flute.wav", table)
|
||||
render_tone("clarinet", "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/sig/clarinet.sig", "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/out/tone-clarinet.wav", table)
|
||||
render_tone("violin", "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/sig/violin.sig", "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/out/tone-violin.wav", table)
|
||||
render_tone("piano", "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/sig/piano.sig", "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/out/tone-piano.wav", table)
|
||||
render_tone("organ", "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/sig/organ.sig", "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/out/tone-organ.wav", table)
|
||||
|
||||
println("")
|
||||
println("=== PIECE: a 6-frame meaning phrase (incl. a NEG frame) ===")
|
||||
let frames: [[String]] = native_list_empty()
|
||||
let frames: [[String]] = native_list_append(frames, audio_frame("agent", "aff", "0.9", "0.8", "0", "s1"))
|
||||
let frames: [[String]] = native_list_append(frames, audio_frame("theme", "aff", "0.7", "0.6", "0", "s2"))
|
||||
let frames: [[String]] = native_list_append(frames, audio_frame("cause", "aff", "0.8", "0.9", "1", "s3"))
|
||||
let frames: [[String]] = native_list_append(frames, audio_frame("negation", "neg", "0.85", "0.7", "0", "s4"))
|
||||
let frames: [[String]] = native_list_append(frames, audio_frame("goal", "aff", "0.6", "0.5", "1", "s5"))
|
||||
let frames: [[String]] = native_list_append(frames, audio_frame("result", "aff", "0.95", "1.0", "0", "s6"))
|
||||
|
||||
// Print the plan so the NEG frame's minor third (+3) vs major (+4) is visible.
|
||||
let nf: Int = native_list_len(frames)
|
||||
let fi: Int = 0
|
||||
while fi < nf {
|
||||
let frame: [String] = native_list_get(frames, fi)
|
||||
let plan: [Int] = plan_note(frame)
|
||||
let pol: String = surface_get(frame, "polarity")
|
||||
let third_name: String = "major(+4)"
|
||||
if str_eq(pol, "neg") { let third_name: String = "MINOR(+3)" }
|
||||
println("frame " + int_to_str(fi) + " relation=" + surface_get(frame, "relation") + " polarity=" + pol + " -> midi=" + int_to_str(native_list_get(plan, 0)) + " dur_ms=" + int_to_str(native_list_get(plan, 1)) + " amp_pm=" + int_to_str(native_list_get(plan, 2)) + " third=" + third_name)
|
||||
let fi: Int = fi + 1
|
||||
}
|
||||
|
||||
let piano_lines: [String] = sig_load("/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/sig/piano.sig")
|
||||
let total: Int = realize_audio(frames, piano_lines, "/Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/out/piece.wav", 44100, table)
|
||||
println("PIECE rendered " + int_to_str(total) + " samples -> /Users/will/Development/neuron-technologies/foundation/el/.claude/worktrees/agent-aaf04b0a9714c4070/elp/faculty/out/piece.wav")
|
||||
return total
|
||||
}
|
||||
|
||||
println("audio-demo main returned samples=" + int_to_str(run_demo()))
|
||||
@@ -1,400 +0,0 @@
|
||||
// audio-surface.el - Native own-core additive-synthesis audio surface.
|
||||
//
|
||||
// The AUDIO efferent seam, native, no Python and no library. This renders real
|
||||
// PCM .wav bytes from instrument SIGNATURES read from engram-sourced .sig data
|
||||
// files (elp/faculty/sig/*.sig) - the partial amplitudes are NEVER literals in
|
||||
// this source; they are parsed from the learned signature at run time. That is
|
||||
// the whole proof: render-from-learned-signatures.
|
||||
//
|
||||
// EL has no float arithmetic operator (codegen emits raw int64 ops for + - * /
|
||||
// on the shared 64-bit slot) and no float-arithmetic natives - so ALL synthesis
|
||||
// math here is own-core INTEGER fixed-point. Angles use a quarter-wave sine
|
||||
// table (scale 10000) from a fixed-point Taylor series; amplitudes are parsed to
|
||||
// micro (scale 1e6) straight from the .sig text; frequencies are milliHz ints.
|
||||
//
|
||||
// Pipeline mirrors the two-stage projector (midi.py): plan_note(frame) reads a
|
||||
// frame's meaning-geometry slot-map and derives (pitch, duration, amplitude);
|
||||
// realize_audio SUPERPOSES the signature's partials (the compose op) and
|
||||
// serialises RIFF/WAVE. Same frame -> midi OR audio.
|
||||
|
||||
// -- integer decimal + string helpers -----------------------------------------
|
||||
|
||||
fn str_to_int_el(s: String) -> Int {
|
||||
let n: Int = str_len(s)
|
||||
let i: Int = 0
|
||||
let v: Int = 0
|
||||
let neg: Bool = false
|
||||
while i < n {
|
||||
let c: Int = str_char_code(s, i)
|
||||
if c == 45 { let neg: Bool = true }
|
||||
if c >= 48 {
|
||||
if c < 58 {
|
||||
let v: Int = v * 10 + (c - 48)
|
||||
}
|
||||
}
|
||||
let i: Int = i + 1
|
||||
}
|
||||
if neg { return 0 - v }
|
||||
return v
|
||||
}
|
||||
|
||||
fn parse_micro(s: String) -> Int {
|
||||
let dot: Int = str_index_of(s, ".")
|
||||
if dot < 0 {
|
||||
return str_to_int_el(s) * 1000000
|
||||
}
|
||||
let n: Int = str_len(s)
|
||||
let ipart: String = str_slice(s, 0, dot)
|
||||
let fpart: String = str_slice(s, dot + 1, n)
|
||||
let iv: Int = str_to_int_el(ipart)
|
||||
let fv: Int = 0
|
||||
let scale: Int = 100000
|
||||
let fn2: Int = str_len(fpart)
|
||||
let i: Int = 0
|
||||
while i < 6 {
|
||||
let d: Int = 0
|
||||
if i < fn2 {
|
||||
let d: Int = str_char_code(fpart, i) - 48
|
||||
}
|
||||
let fv: Int = fv + d * scale
|
||||
let scale: Int = scale / 10
|
||||
let i: Int = i + 1
|
||||
}
|
||||
return iv * 1000000 + fv
|
||||
}
|
||||
|
||||
// -- signature (engram data file) loader ---------------------------------------
|
||||
|
||||
fn sig_load(path: String) -> [String] {
|
||||
let text: String = fs_read(path)
|
||||
return str_split(text, "\n")
|
||||
}
|
||||
|
||||
fn sig_field(lines: [String], key: String) -> String {
|
||||
let pref: String = key + ": "
|
||||
let n: Int = native_list_len(lines)
|
||||
let plen: Int = str_len(pref)
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
let ln: String = native_list_get(lines, i)
|
||||
if str_starts_with(ln, pref) {
|
||||
return str_slice(ln, plen, str_len(ln))
|
||||
}
|
||||
let i: Int = i + 1
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
fn parse_micros(csv: String) -> [Int] {
|
||||
let parts: [String] = str_split(csv, ",")
|
||||
let n: Int = native_list_len(parts)
|
||||
let out: [Int] = native_list_empty()
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
let out: [Int] = native_list_append(out, parse_micro(native_list_get(parts, i)))
|
||||
let i: Int = i + 1
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// -- fixed-point sine (own-core, quarter-wave Taylor table, scale 10000) --------
|
||||
|
||||
fn sin_table() -> [Int] {
|
||||
let HP: Int = 1570796
|
||||
let t: [Int] = native_list_empty()
|
||||
let q: Int = 0
|
||||
while q < 257 {
|
||||
let x: Int = q * HP / 256
|
||||
let x2: Int = x * x / 1000000
|
||||
let x3: Int = x2 * x / 1000000
|
||||
let x5: Int = x3 * x2 / 1000000
|
||||
let x7: Int = x5 * x2 / 1000000
|
||||
let x9: Int = x7 * x2 / 1000000
|
||||
let s: Int = x - x3 / 6 + x5 / 120 - x7 / 5040 + x9 / 362880
|
||||
let t: [Int] = native_list_append(t, s / 100)
|
||||
let q: Int = q + 1
|
||||
}
|
||||
return t
|
||||
}
|
||||
|
||||
fn sin_lookup(t: [Int], phase: Int) -> Int {
|
||||
let p: Int = phase % 1024
|
||||
if p < 0 { let p: Int = p + 1024 }
|
||||
let quad: Int = p / 256
|
||||
let r: Int = p % 256
|
||||
if quad == 0 { return native_list_get(t, r) }
|
||||
if quad == 1 { return native_list_get(t, 256 - r) }
|
||||
if quad == 2 { return 0 - native_list_get(t, r) }
|
||||
return 0 - native_list_get(t, 256 - r)
|
||||
}
|
||||
|
||||
fn isqrt_int(n: Int) -> Int {
|
||||
if n <= 0 { return 0 }
|
||||
let x: Int = n
|
||||
let y: Int = (x + 1) / 2
|
||||
while y < x {
|
||||
let x: Int = y
|
||||
let y: Int = (x + n / x) / 2
|
||||
}
|
||||
return x
|
||||
}
|
||||
|
||||
// freq_of_midi: equal-tempered frequency in milliHz. 440000 mHz at midi 69.
|
||||
fn freq_of_midi(m: Int) -> Int {
|
||||
let f: Int = 440000
|
||||
if m > 69 {
|
||||
let k: Int = m - 69
|
||||
let i: Int = 0
|
||||
while i < k {
|
||||
let f: Int = f * 1059463 / 1000000
|
||||
let i: Int = i + 1
|
||||
}
|
||||
return f
|
||||
}
|
||||
if m < 69 {
|
||||
let k: Int = 69 - m
|
||||
let i: Int = 0
|
||||
while i < k {
|
||||
let f: Int = f * 1000000 / 1059463
|
||||
let i: Int = i + 1
|
||||
}
|
||||
return f
|
||||
}
|
||||
return f
|
||||
}
|
||||
|
||||
// -- envelope (ADSR), scale 1000 -----------------------------------------------
|
||||
|
||||
fn adsr_env(i: Int, total: Int, atk_n: Int, dec_n: Int, sus_pm: Int, rel_n: Int) -> Int {
|
||||
if i < atk_n {
|
||||
if atk_n == 0 { return 1000 }
|
||||
return 1000 * i / atk_n
|
||||
}
|
||||
if i < atk_n + dec_n {
|
||||
if dec_n == 0 { return sus_pm }
|
||||
return 1000 - (1000 - sus_pm) * (i - atk_n) / dec_n
|
||||
}
|
||||
let rel_start: Int = total - rel_n
|
||||
if i < rel_start {
|
||||
return sus_pm
|
||||
}
|
||||
if rel_n == 0 { return 0 }
|
||||
let left: Int = total - i
|
||||
return sus_pm * left / rel_n
|
||||
}
|
||||
|
||||
// -- note synthesis: SUPERPOSE the learned partials -> [Int] samples -----------
|
||||
fn note_samples(freq_mHz: Int, dur_ms: Int, rate: Int, partials: [Int], sumP: Int, b_micro: Int, vib_rate: Int, vib_cents: Int, atk_ms: Int, dec_ms: Int, sus_pm: Int, rel_ms: Int, amp_pm: Int, table: [Int]) -> [Int] {
|
||||
let total: Int = dur_ms * rate / 1000
|
||||
let atk_n: Int = atk_ms * rate / 1000
|
||||
let dec_n: Int = dec_ms * rate / 1000
|
||||
let rel_n: Int = rel_ms * rate / 1000
|
||||
let np: Int = native_list_len(partials)
|
||||
let half_mhz: Int = rate * 1000 / 2
|
||||
let out: [Int] = native_list_empty()
|
||||
let i: Int = 0
|
||||
while i < total {
|
||||
let acc: Int = 0
|
||||
let k: Int = 0
|
||||
while k < np {
|
||||
let harm: Int = k + 1
|
||||
let amp_k: Int = native_list_get(partials, k)
|
||||
let factor: Int = 1000000
|
||||
if b_micro > 0 {
|
||||
let val: Int = 1000000 + b_micro * harm * harm
|
||||
let factor: Int = isqrt_int(val * 1000000)
|
||||
}
|
||||
let fn_mhz: Int = freq_mHz * harm
|
||||
let fn_mhz: Int = fn_mhz * factor / 1000000
|
||||
if vib_cents > 0 {
|
||||
if vib_rate > 0 {
|
||||
let vphase: Int = i * vib_rate * 1024 / rate
|
||||
let vs: Int = sin_lookup(table, vphase)
|
||||
let vibf: Int = 1000000 + (vib_cents * vs * 833) / 10000
|
||||
let fn_mhz: Int = fn_mhz * vibf / 1000000
|
||||
}
|
||||
}
|
||||
if fn_mhz <= half_mhz {
|
||||
let phase: Int = i * fn_mhz * 1024 / (rate * 1000)
|
||||
let sv: Int = sin_lookup(table, phase)
|
||||
let acc: Int = acc + sv * amp_k / 1000000
|
||||
}
|
||||
let k: Int = k + 1
|
||||
}
|
||||
let env: Int = adsr_env(i, total, atk_n, dec_n, sus_pm, rel_n)
|
||||
let s16: Int = acc * 2800000 / sumP
|
||||
let s16: Int = s16 * env / 1000
|
||||
let s16: Int = s16 * amp_pm / 1000
|
||||
if s16 > 32767 { let s16: Int = 32767 }
|
||||
if s16 < 0 - 32767 { let s16: Int = 0 - 32767 }
|
||||
let out: [Int] = native_list_append(out, s16)
|
||||
let i: Int = i + 1
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
fn synth_from_sig(lines: [String], freq_mHz: Int, dur_ms: Int, amp_pm: Int, rate: Int, table: [Int]) -> [Int] {
|
||||
let partials: [Int] = parse_micros(sig_field(lines, "partials"))
|
||||
let np: Int = native_list_len(partials)
|
||||
let sumP: Int = 0
|
||||
let j: Int = 0
|
||||
while j < np {
|
||||
let pj: Int = native_list_get(partials, j)
|
||||
let sumP: Int = sumP + pj
|
||||
let j: Int = j + 1
|
||||
}
|
||||
if sumP <= 0 { let sumP: Int = 1000000 }
|
||||
let adsr: [String] = str_split(sig_field(lines, "adsr"), ",")
|
||||
let atk_ms: Int = parse_micro(native_list_get(adsr, 0)) / 1000
|
||||
let dec_ms: Int = parse_micro(native_list_get(adsr, 1)) / 1000
|
||||
let sus_pm: Int = parse_micro(native_list_get(adsr, 2)) / 1000
|
||||
let rel_ms: Int = parse_micro(native_list_get(adsr, 3)) / 1000
|
||||
let b_micro: Int = parse_micro(sig_field(lines, "inharmonicity_B"))
|
||||
let vib_rate: Int = str_to_int_el(sig_field(lines, "vibrato_rate_hz"))
|
||||
let vib_cents: Int = str_to_int_el(sig_field(lines, "vibrato_depth_cents"))
|
||||
return note_samples(freq_mHz, dur_ms, rate, partials, sumP, b_micro, vib_rate, vib_cents, atk_ms, dec_ms, sus_pm, rel_ms, amp_pm, table)
|
||||
}
|
||||
|
||||
// -- byte-buffer helpers (own-core, no library) --------------------------------
|
||||
|
||||
fn put_tag(buf: String, pos: Int, s: String) -> String {
|
||||
let n: Int = str_len(s)
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
let buf: String = __str_set_char(buf, pos + i, str_char_code(s, i))
|
||||
let i: Int = i + 1
|
||||
}
|
||||
return buf
|
||||
}
|
||||
|
||||
fn put_u32le(buf: String, pos: Int, v: Int) -> String {
|
||||
let buf: String = __str_set_char(buf, pos, v % 256)
|
||||
let buf: String = __str_set_char(buf, pos + 1, (v / 256) % 256)
|
||||
let buf: String = __str_set_char(buf, pos + 2, (v / 65536) % 256)
|
||||
let buf: String = __str_set_char(buf, pos + 3, (v / 16777216) % 256)
|
||||
return buf
|
||||
}
|
||||
|
||||
fn put_u16le(buf: String, pos: Int, v: Int) -> String {
|
||||
let buf: String = __str_set_char(buf, pos, v % 256)
|
||||
let buf: String = __str_set_char(buf, pos + 1, (v / 256) % 256)
|
||||
return buf
|
||||
}
|
||||
|
||||
// -- WAV serializer: own-core RIFF/WAVE, PCM mono 16-bit -----------------------
|
||||
|
||||
fn wav_write(path: String, samples: [Int], n: Int, rate: Int) -> Int {
|
||||
let data_len: Int = n * 2
|
||||
let total: Int = 44 + data_len
|
||||
let buf: String = __str_alloc(total)
|
||||
let buf: String = put_tag(buf, 0, "RIFF")
|
||||
let buf: String = put_u32le(buf, 4, 36 + data_len)
|
||||
let buf: String = put_tag(buf, 8, "WAVE")
|
||||
let buf: String = put_tag(buf, 12, "fmt ")
|
||||
let buf: String = put_u32le(buf, 16, 16)
|
||||
let buf: String = put_u16le(buf, 20, 1)
|
||||
let buf: String = put_u16le(buf, 22, 1)
|
||||
let buf: String = put_u32le(buf, 24, rate)
|
||||
let buf: String = put_u32le(buf, 28, rate * 2)
|
||||
let buf: String = put_u16le(buf, 32, 2)
|
||||
let buf: String = put_u16le(buf, 34, 16)
|
||||
let buf: String = put_tag(buf, 36, "data")
|
||||
let buf: String = put_u32le(buf, 40, data_len)
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
let v: Int = native_list_get(samples, i)
|
||||
if v < 0 { let v: Int = v + 65536 }
|
||||
let buf: String = __str_set_char(buf, 44 + i * 2, v % 256)
|
||||
let buf: String = __str_set_char(buf, 44 + i * 2 + 1, (v / 256) % 256)
|
||||
let i: Int = i + 1
|
||||
}
|
||||
let ok: Int = fs_write_bytes(path, buf, total)
|
||||
return ok
|
||||
}
|
||||
|
||||
// -- plan: frame slot-map -> note atom (pitch, duration, amplitude) ------------
|
||||
|
||||
fn audio_frame(relation: String, polarity: String, confidence: String, importance: String, salience: String, subj_id: String) -> [String] {
|
||||
let f: [String] = native_list_empty()
|
||||
let f: [String] = native_list_append(f, "relation")
|
||||
let f: [String] = native_list_append(f, relation)
|
||||
let f: [String] = native_list_append(f, "polarity")
|
||||
let f: [String] = native_list_append(f, polarity)
|
||||
let f: [String] = native_list_append(f, "confidence")
|
||||
let f: [String] = native_list_append(f, confidence)
|
||||
let f: [String] = native_list_append(f, "importance")
|
||||
let f: [String] = native_list_append(f, importance)
|
||||
let f: [String] = native_list_append(f, "salience")
|
||||
let f: [String] = native_list_append(f, salience)
|
||||
let f: [String] = native_list_append(f, "subj_id")
|
||||
let f: [String] = native_list_append(f, subj_id)
|
||||
return f
|
||||
}
|
||||
|
||||
fn degree_offset(deg: Int) -> Int {
|
||||
if deg == 0 { return 0 }
|
||||
if deg == 1 { return 2 }
|
||||
if deg == 2 { return 4 }
|
||||
if deg == 3 { return 5 }
|
||||
if deg == 4 { return 7 }
|
||||
if deg == 5 { return 9 }
|
||||
return 11
|
||||
}
|
||||
|
||||
// returns [midi, dur_ms, amp_pm]
|
||||
fn plan_note(frame: [String]) -> [Int] {
|
||||
let relation: String = surface_get(frame, "relation")
|
||||
let polarity: String = surface_get(frame, "polarity")
|
||||
let confidence: String = surface_get(frame, "confidence")
|
||||
let importance: String = surface_get(frame, "importance")
|
||||
let salience: String = surface_get(frame, "salience")
|
||||
let rn: Int = str_len(relation)
|
||||
let csum: Int = 0
|
||||
let i: Int = 0
|
||||
while i < rn {
|
||||
let cc: Int = str_char_code(relation, i)
|
||||
let csum: Int = csum + cc
|
||||
let i: Int = i + 1
|
||||
}
|
||||
let deg: Int = csum % 7
|
||||
let third: Int = 4
|
||||
if str_eq(polarity, "neg") { let third: Int = 3 }
|
||||
let sal_oct: Int = str_to_int_el(salience)
|
||||
let doff: Int = degree_offset(deg)
|
||||
let midi: Int = 60 + sal_oct * 12 + doff + third
|
||||
let conf_micro: Int = parse_micro(confidence)
|
||||
let dur_ms: Int = 200 + conf_micro / 1000
|
||||
let imp_micro: Int = parse_micro(importance)
|
||||
let amp_pm: Int = 400 + imp_micro / 2000
|
||||
let out: [Int] = native_list_empty()
|
||||
let out: [Int] = native_list_append(out, midi)
|
||||
let out: [Int] = native_list_append(out, dur_ms)
|
||||
let out: [Int] = native_list_append(out, amp_pm)
|
||||
return out
|
||||
}
|
||||
|
||||
fn realize_audio(frames: [[String]], sig_lines: [String], path: String, rate: Int, table: [Int]) -> Int {
|
||||
let nf: Int = native_list_len(frames)
|
||||
let all: [Int] = native_list_empty()
|
||||
let count: Int = 0
|
||||
let fi: Int = 0
|
||||
while fi < nf {
|
||||
let frame: [String] = native_list_get(frames, fi)
|
||||
let plan: [Int] = plan_note(frame)
|
||||
let midi: Int = native_list_get(plan, 0)
|
||||
let dur_ms: Int = native_list_get(plan, 1)
|
||||
let amp_pm: Int = native_list_get(plan, 2)
|
||||
let freq: Int = freq_of_midi(midi)
|
||||
let note: [Int] = synth_from_sig(sig_lines, freq, dur_ms, amp_pm, rate, table)
|
||||
let nn: Int = native_list_len(note)
|
||||
let j: Int = 0
|
||||
while j < nn {
|
||||
let all: [Int] = native_list_append(all, native_list_get(note, j))
|
||||
let j: Int = j + 1
|
||||
}
|
||||
let count: Int = count + nn
|
||||
let fi: Int = fi + 1
|
||||
}
|
||||
let ok: Int = wav_write(path, all, count, rate)
|
||||
return count
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,16 +0,0 @@
|
||||
// comprehend.elh — public surface of the ELP comprehension front-end.
|
||||
// text → meaning-spec (the input half of the ELP; inverse of the realizer).
|
||||
extern fn parse_spec(text: String) -> [String]
|
||||
extern fn parse_spec_lang(text: String, lang: String) -> [String]
|
||||
extern fn parse_json(text: String) -> String
|
||||
extern fn parse_json_lang(text: String, lang: String) -> String
|
||||
// Analysis primitives (invertible morphology + deterministic grammar helpers):
|
||||
extern fn cp_tokenize(text: String) -> [String]
|
||||
extern fn cp_pron_concept(w: String) -> String
|
||||
extern fn cp_is_negation(w: String) -> Bool
|
||||
extern fn cp_is_neg_adverb(w: String) -> Bool
|
||||
extern fn cp_irr2(surface: String) -> [String]
|
||||
extern fn cp_reg_verb(w: String) -> [String]
|
||||
extern fn cp_analyze_verb(surface: String) -> [String]
|
||||
extern fn cp_verb_start(toks: [String], end: Int) -> Int
|
||||
extern fn cp_subord_start(toks: [String], n: Int) -> Int
|
||||
@@ -1 +0,0 @@
|
||||
import "language-profile.el"
|
||||
@@ -1,2 +0,0 @@
|
||||
import "language-profile.el"
|
||||
import "dedup_test_a_nodedup.el"
|
||||
@@ -1,2 +0,0 @@
|
||||
import "language-profile.el"
|
||||
extern fn fn_a(x: String) -> String
|
||||
@@ -1 +0,0 @@
|
||||
extern fn fn_a(x: String) -> String
|
||||
@@ -1,2 +0,0 @@
|
||||
import "language-profile.el"
|
||||
extern fn fn_a(x: String) -> String
|
||||
@@ -1,6 +0,0 @@
|
||||
import "language-profile.el"
|
||||
import "dedup_test_a.el"
|
||||
|
||||
fn main_fn(x: String) -> String {
|
||||
return x
|
||||
}
|
||||
@@ -1,2 +0,0 @@
|
||||
import "language-profile.el"
|
||||
import "dedup_test_a.el"
|
||||
@@ -1,2 +0,0 @@
|
||||
import "language-profile.el"
|
||||
import "dedup_test_a_notail.el"
|
||||
@@ -1,287 +0,0 @@
|
||||
// dialogue.el — SUMMON-THROUGH-SELF, native el. Port of dialogue.py's core.
|
||||
//
|
||||
// THE WHOLE DIALOGUE IS ONE OPERATION. A fact is never merely *fetched*: the
|
||||
// query is PROJECTED into the engram's self + memory geometry, LANDS in a region,
|
||||
// and the reply is READ OUT / the region MATERIALIZED from wherever it landed.
|
||||
//
|
||||
// project(query) -> land on a region -> read out from that region
|
||||
//
|
||||
// • lands in the SELF region -> grounded identity/presence, read out of
|
||||
// the real self nodes (self_region.el)
|
||||
// • lands on a memory NEIGHBORHOOD -> MATERIALIZE it: walk the neighborhood
|
||||
// (engram_neighbors_json) and read out the
|
||||
// region's connected members
|
||||
// • lands nowhere close -> HONEST ABSENCE (an empty region, not a
|
||||
// fabricated answer, not an error)
|
||||
//
|
||||
// CRITICAL INVARIANTS (enforced structurally, not by convention):
|
||||
// * ONE operation — there is NO intent classifier and NO separate
|
||||
// fact-retrieval branch. Identity is nearest-region proximity, not a switch.
|
||||
// * MATERIALIZE by walking the neighborhood, never by fetching top-props.
|
||||
// * HONEST ABSENCE when the region is thin.
|
||||
// * NEGATION is SACRED: the readout is the stored prose VERBATIM, so a negated
|
||||
// memory stays negated — we never paraphrase a polarity away.
|
||||
// * NO ECHO: the old "I noted that X. That relates to Y." template is gone.
|
||||
// The summon path materializes or honestly declines — it never echoes.
|
||||
// * DIRECTIVE OVERRIDE: a meta-directive ("answer in English") overrides the
|
||||
// reply language while the content language is still auto-detected.
|
||||
//
|
||||
// Depends on: comprehend (parse_spec_lang, cp_tokenize), multilingual (ml_detect,
|
||||
// ml_tr, ml_term), propositions (prop_split_sentences), self_region
|
||||
// (sr_available, sr_readout), the engram + json runtime builtins.
|
||||
|
||||
// ── directive override ────────────────────────────────────────────────────────
|
||||
// Return [target_lang, content]. target_lang is "" when no directive is present.
|
||||
// A directive names an output language; we strip it and keep the remaining text
|
||||
// as the content (whose OWN language is still auto-detected downstream).
|
||||
|
||||
fn dlg_dir_hit(low: String, phrase: String) -> Bool {
|
||||
return str_contains(low, phrase)
|
||||
}
|
||||
|
||||
fn dlg_parse_directive(text: String) -> [String] {
|
||||
let low: String = str_to_lower(text)
|
||||
let lang: String = ""
|
||||
let phrase: String = ""
|
||||
// English target
|
||||
if dlg_dir_hit(low, "in english") { let lang = "en"; let phrase = "in english" }
|
||||
if dlg_dir_hit(low, "em inglês") { let lang = "en"; let phrase = "em inglês" }
|
||||
if dlg_dir_hit(low, "em ingles") { let lang = "en"; let phrase = "em ingles" }
|
||||
if dlg_dir_hit(low, "en inglés") { let lang = "en"; let phrase = "en inglés" }
|
||||
// Portuguese target
|
||||
if dlg_dir_hit(low, "in portuguese") { let lang = "pt"; let phrase = "in portuguese" }
|
||||
if dlg_dir_hit(low, "em português") { let lang = "pt"; let phrase = "em português" }
|
||||
// Spanish target
|
||||
if dlg_dir_hit(low, "in spanish") { let lang = "es"; let phrase = "in spanish" }
|
||||
if dlg_dir_hit(low, "en español") { let lang = "es"; let phrase = "en español" }
|
||||
// Italian target
|
||||
if dlg_dir_hit(low, "in italian") { let lang = "it"; let phrase = "in italian" }
|
||||
|
||||
let content: String = text
|
||||
if !str_eq(phrase, "") {
|
||||
// strip the directive phrase (and a common "answer"/"responda" lead-in),
|
||||
// leaving the real question as content.
|
||||
let idx: Int = str_index_of(low, phrase)
|
||||
if idx >= 0 {
|
||||
let before: String = str_slice(text, 0, idx)
|
||||
let after: String = str_slice(text, idx + str_len(phrase), str_len(text))
|
||||
let content = str_trim(before + " " + after)
|
||||
}
|
||||
// trim a leading "answer"/"responda"/"reply" and stray colon/comma.
|
||||
let cl: String = str_to_lower(content)
|
||||
if str_starts_with(cl, "answer") { let content = str_trim(str_slice(content, 6, str_len(content))) }
|
||||
if str_starts_with(cl, "responda") { let content = str_trim(str_slice(content, 8, str_len(content))) }
|
||||
if str_starts_with(cl, "reply") { let content = str_trim(str_slice(content, 5, str_len(content))) }
|
||||
if str_starts_with(content, ":") { let content = str_trim(str_slice(content, 1, str_len(content))) }
|
||||
if str_starts_with(content, ",") { let content = str_trim(str_slice(content, 1, str_len(content))) }
|
||||
}
|
||||
let r: [String] = native_list_empty()
|
||||
let r = native_list_append(r, lang)
|
||||
let r = native_list_append(r, content)
|
||||
return r
|
||||
}
|
||||
|
||||
// ── identity landing (a region proximity, not a classifier switch) ────────────
|
||||
// The query lands in the SELF region when it takes an identity/presence shape.
|
||||
// Cross-lingual forms are included because the engram's lexical probe is
|
||||
// English-leaning. This is the SELF attractor of the single operation.
|
||||
|
||||
fn dlg_is_identity(content: String) -> Bool {
|
||||
let low: String = str_to_lower(str_trim(content))
|
||||
if str_contains(low, "who are you") { return true }
|
||||
if str_contains(low, "what are you") { return true }
|
||||
if str_contains(low, "who i am") { return true }
|
||||
if str_contains(low, "your name") { return true }
|
||||
if str_contains(low, "about yourself") { return true }
|
||||
if str_contains(low, "are you conscious") { return true }
|
||||
if str_contains(low, "are you there") { return true }
|
||||
// cross-lingual identity question-forms
|
||||
if str_contains(low, "quem é você") { return true }
|
||||
if str_contains(low, "quem es voce") { return true }
|
||||
if str_contains(low, "quién eres") { return true }
|
||||
if str_contains(low, "quien eres") { return true }
|
||||
if str_contains(low, "chi sei") { return true }
|
||||
if str_contains(low, "qui es-tu") { return true }
|
||||
if str_contains(low, "wer bist du") { return true }
|
||||
return false
|
||||
}
|
||||
|
||||
// ── readout helpers ───────────────────────────────────────────────────────────
|
||||
|
||||
fn dlg_first_sentence(content: String) -> String {
|
||||
let sents: [String] = prop_split_sentences(content)
|
||||
let n: Int = native_list_len(sents)
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
let s: String = str_trim(native_list_get(sents, i))
|
||||
// drop a leading markdown heading marker for a clean read-out line
|
||||
if str_starts_with(s, "# ") { let s = str_trim(str_slice(s, 2, str_len(s))) }
|
||||
if str_len(s) > 0 { return s }
|
||||
let i = i + 1
|
||||
}
|
||||
return str_trim(content)
|
||||
}
|
||||
|
||||
// strip trailing/leading punctuation from a token.
|
||||
fn dlg_clean_tok(w: String) -> String {
|
||||
let s: String = str_trim(w)
|
||||
let s = str_strip_suffix(s, ".")
|
||||
let s = str_strip_suffix(s, ",")
|
||||
let s = str_strip_suffix(s, "?")
|
||||
let s = str_strip_suffix(s, "!")
|
||||
let s = str_strip_suffix(s, ":")
|
||||
let s = str_strip_suffix(s, ";")
|
||||
return str_trim(s)
|
||||
}
|
||||
|
||||
// closed-class across the supported languages (union) — a word we must NOT treat
|
||||
// as a retrieval topic. Also drops the meta verbs of a request ("tell", "prove",
|
||||
// "show") so the TOPIC, not the speech act, is what projects into memory.
|
||||
fn dlg_is_stop(w: String) -> Bool {
|
||||
if ml_stop_en(w) { return true }
|
||||
if ml_stop_es(w) { return true }
|
||||
if ml_stop_pt(w) { return true }
|
||||
if ml_stop_it(w) { return true }
|
||||
if str_eq(w, "tell") { return true }
|
||||
if str_eq(w, "show") { return true }
|
||||
if str_eq(w, "about") { return true }
|
||||
if str_eq(w, "sobre") { return true }
|
||||
if str_eq(w, "acerca") { return true }
|
||||
return false
|
||||
}
|
||||
|
||||
// The CONTENT TERMS the query projects into memory: content words only, cleaned,
|
||||
// cross-lingually mapped to the engram's English vocabulary, ≥3 chars. This is
|
||||
// the geometry probe — the speech-act verbs and function words are stripped so a
|
||||
// PP topic ("tell me ABOUT Lisbon") projects on "lisbon", not "tell"/"me".
|
||||
fn dlg_content_terms(content: String, lang: String) -> [String] {
|
||||
let toks: [String] = cp_tokenize(content)
|
||||
let n: Int = native_list_len(toks)
|
||||
let out: [String] = native_list_empty()
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
let w: String = str_to_lower(dlg_clean_tok(native_list_get(toks, i)))
|
||||
if str_len(w) >= 3 {
|
||||
if !dlg_is_stop(w) {
|
||||
let out = native_list_append(out, ml_term(w, lang))
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// Does this landed node lexically overlap the query's content terms? This is the
|
||||
// RELEVANCE FLOOR: activation always returns the store's most salient nodes, so
|
||||
// without this a query about nothing would "land" on the self/top node. A node
|
||||
// that shares no content term with the query is "nowhere close" -> honest absence.
|
||||
fn dlg_node_matches(node: String, terms: [String]) -> Bool {
|
||||
let hay: String = str_to_lower(json_get_string(node, "content") + " " + json_get_string(node, "label"))
|
||||
let n: Int = native_list_len(terms)
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
let t: String = native_list_get(terms, i)
|
||||
if str_len(t) >= 3 {
|
||||
if str_contains(hay, t) { return true }
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// MATERIALIZE the landed region: read out the landed fact, then WALK the
|
||||
// neighborhood and read out its connected members (real edges, not top-props).
|
||||
fn dlg_materialize(top_node: String, reply_lang: String) -> String {
|
||||
let id: String = json_get_string(top_node, "id")
|
||||
let content: String = json_get_string(top_node, "content")
|
||||
let lead: String = dlg_first_sentence(content)
|
||||
|
||||
let nb: String = engram_neighbors_json(id, 2, "both")
|
||||
let m: Int = json_array_len(nb)
|
||||
let parts: [String] = native_list_empty()
|
||||
let parts = native_list_append(parts, lead)
|
||||
let added: Int = 0
|
||||
let i: Int = 0
|
||||
while i < m {
|
||||
if added < 3 {
|
||||
let rec: String = json_array_get(nb, i)
|
||||
let node: String = json_get_raw(rec, "node")
|
||||
let nc: String = json_get_string(node, "content")
|
||||
if !str_eq(nc, "") {
|
||||
let sent: String = dlg_first_sentence(nc)
|
||||
if !str_eq(sent, "") {
|
||||
let parts = native_list_append(parts, sent)
|
||||
let added = added + 1
|
||||
}
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
// The readout is the region's OWN prose, verbatim — negation SACRED, no echo.
|
||||
return str_join(parts, " ")
|
||||
}
|
||||
|
||||
// ── THE single operation ──────────────────────────────────────────────────────
|
||||
|
||||
fn dlg_respond(text: String) -> String {
|
||||
// directive override: reply language may differ from content language.
|
||||
let dir: [String] = dlg_parse_directive(text)
|
||||
let target_lang: String = native_list_get(dir, 0)
|
||||
let content: String = native_list_get(dir, 1)
|
||||
|
||||
let content_lang: String = ml_detect(content)
|
||||
let reply_lang: String = content_lang
|
||||
if !str_eq(target_lang, "") { let reply_lang = target_lang }
|
||||
|
||||
// comprehend the content (SACRED polarity carried in the spec).
|
||||
let spec: [String] = parse_spec_lang(content, content_lang)
|
||||
|
||||
// ── PROJECT + LAND: SELF region ───────────────────────────────────────────
|
||||
// Identity/presence shape lands in the self region; read out the REAL self
|
||||
// nodes (self_region.el), never a template. Same single operation — this is
|
||||
// just the self attractor winning the landing.
|
||||
if dlg_is_identity(content) {
|
||||
if sr_available() {
|
||||
// read out the REAL self nodes when replying in their own language
|
||||
// (the soul's prose is English); for another reply language we cannot
|
||||
// translate real content without an LLM, so we answer with the
|
||||
// localized SACRED identity anchor — honest, in-language, no fabrication.
|
||||
if str_eq(reply_lang, "en") { return sr_readout("en") }
|
||||
return ml_tr("identity", reply_lang)
|
||||
}
|
||||
// self region thin — honest localized identity (logged fallback shape).
|
||||
return ml_tr("identity", reply_lang)
|
||||
}
|
||||
|
||||
// ── PROJECT into MEMORY geometry ──────────────────────────────────────────
|
||||
let terms: [String] = dlg_content_terms(content, content_lang)
|
||||
let qterm: String = str_join(terms, " ")
|
||||
let act: String = engram_activate_json(qterm, 12)
|
||||
let n: Int = json_array_len(act)
|
||||
|
||||
// ── LAND: the highest-activation node that ACTUALLY overlaps the query's
|
||||
// content terms (the relevance floor). Activation always returns the most
|
||||
// salient nodes, so we walk the ranked list and take the first that is
|
||||
// genuinely "close"; if none is, the query landed nowhere. ───────────────
|
||||
let landing: String = ""
|
||||
let i: Int = 0
|
||||
while i < n {
|
||||
if str_eq(landing, "") {
|
||||
let rec: String = json_array_get(act, i)
|
||||
let node: String = json_get_raw(rec, "node")
|
||||
if dlg_node_matches(node, terms) {
|
||||
let landing = node
|
||||
}
|
||||
}
|
||||
let i = i + 1
|
||||
}
|
||||
|
||||
// ── HONEST ABSENCE: nothing close — an empty region, not a fabricated answer,
|
||||
// not an "I noted that" echo. ────────────────────────────────────────────
|
||||
if str_eq(landing, "") {
|
||||
return ml_tr("no_memory", reply_lang)
|
||||
}
|
||||
|
||||
// ── MATERIALIZE the landing by WALKING its neighborhood. ──────────────────
|
||||
return dlg_materialize(landing, reply_lang)
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user