Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 will.anderson
|
0a72fced28 |
@@ -39,9 +39,9 @@ jobs:
|
||||
run: |
|
||||
dist/platform/elc-linux-amd64 elc-cli.el > dist/elc-gen2.c
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
-I runtime \
|
||||
dist/elc-gen2.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-o dist/platform/elc
|
||||
chmod +x dist/platform/elc
|
||||
@@ -54,9 +54,9 @@ jobs:
|
||||
mkdir -p dist/bin
|
||||
dist/platform/elc elb.el > dist/elb.c
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
-I runtime \
|
||||
dist/elb.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-o dist/bin/elb
|
||||
chmod +x dist/bin/elb
|
||||
@@ -91,7 +91,7 @@ jobs:
|
||||
- name: Precompile el_runtime.o
|
||||
run: |
|
||||
set -euo pipefail
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
gcc -O2 -c -I "$RUNTIME" "$RUNTIME/el_runtime.c" \
|
||||
-o /tmp/el_runtime.o
|
||||
echo "el_runtime.o compiled"
|
||||
@@ -100,7 +100,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_core.el > /tmp/el_native_core.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_core.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_core
|
||||
@@ -110,7 +110,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/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
|
||||
@@ -120,7 +120,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_string.el > /tmp/el_native_string.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_string.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_string
|
||||
@@ -130,7 +130,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(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
|
||||
@@ -140,7 +140,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_state.el > /tmp/el_native_state.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_state.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_state
|
||||
@@ -150,7 +150,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(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
|
||||
@@ -160,7 +160,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_json.el > /tmp/el_native_json.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_json.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_json
|
||||
@@ -170,7 +170,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(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
|
||||
@@ -180,7 +180,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_fs.el > /tmp/el_native_fs.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_fs.c /tmp/el_runtime.o \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_fs
|
||||
@@ -191,7 +191,7 @@ jobs:
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
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
|
||||
@@ -202,7 +202,7 @@ jobs:
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
ABS_RUNTIME="$(pwd)/runtime"
|
||||
ABS_OUT="$(pwd)/dist/bin"
|
||||
(cd tools/install && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
|
||||
chmod +x dist/bin/el-install
|
||||
@@ -242,7 +242,7 @@ jobs:
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-c \
|
||||
--version="${VERSION}" \
|
||||
--source=el-compiler/runtime/el_runtime.c
|
||||
--source=runtime/el_runtime.c
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-dev \
|
||||
@@ -250,7 +250,7 @@ jobs:
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-h \
|
||||
--version="${VERSION}" \
|
||||
--source=el-compiler/runtime/el_runtime.h
|
||||
--source=runtime/el_runtime.h
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-dev \
|
||||
@@ -258,7 +258,7 @@ jobs:
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-js \
|
||||
--version="${VERSION}" \
|
||||
--source=el-compiler/runtime/el_runtime.js
|
||||
--source=runtime/el_runtime.js
|
||||
|
||||
echo "Published El SDK version=${VERSION} to foundation-dev"
|
||||
# Keep key alive for the ci-base rebuild step below
|
||||
@@ -291,9 +291,9 @@ jobs:
|
||||
FROM ${BASE}
|
||||
COPY dist/platform/elc /opt/el/dist/platform/elc
|
||||
COPY dist/bin/elb /opt/el/dist/bin/elb
|
||||
COPY el-compiler/runtime/el_runtime.c /opt/el/el-compiler/runtime/el_runtime.c
|
||||
COPY el-compiler/runtime/el_runtime.h /opt/el/el-compiler/runtime/el_runtime.h
|
||||
COPY el-compiler/runtime/el_runtime.js /opt/el/el-compiler/runtime/el_runtime.js
|
||||
COPY runtime/el_runtime.c /opt/el/runtime/el_runtime.c
|
||||
COPY runtime/el_runtime.h /opt/el/runtime/el_runtime.h
|
||||
COPY runtime/el_runtime.js /opt/el/runtime/el_runtime.js
|
||||
RUN chmod +x /opt/el/dist/platform/elc /opt/el/dist/bin/elb
|
||||
EOF
|
||||
|
||||
|
||||
@@ -46,9 +46,9 @@ jobs:
|
||||
run: |
|
||||
dist/platform/elc-linux-amd64 elc-cli.el > dist/elc-gen2.c
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
-I runtime \
|
||||
dist/elc-gen2.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-o dist/platform/elc
|
||||
chmod +x dist/platform/elc
|
||||
@@ -84,7 +84,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_core.el > /tmp/el_native_core.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_core.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_core
|
||||
@@ -94,7 +94,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_text.el > /tmp/el_native_text.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_text.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_text
|
||||
@@ -104,7 +104,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_string.el > /tmp/el_native_string.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_string.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_string
|
||||
@@ -114,7 +114,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_math.el > /tmp/el_native_math.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_math.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_math
|
||||
@@ -124,7 +124,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_state.el > /tmp/el_native_state.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_state.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_state
|
||||
@@ -134,7 +134,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_time.el > /tmp/el_native_time.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_time.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_time
|
||||
@@ -144,7 +144,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_json.el > /tmp/el_native_json.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_json.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_json
|
||||
@@ -154,7 +154,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_env.el > /tmp/el_native_env.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_env.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_env
|
||||
@@ -164,7 +164,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_fs.el > /tmp/el_native_fs.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_fs.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_fs
|
||||
@@ -176,9 +176,9 @@ jobs:
|
||||
mkdir -p dist/bin
|
||||
dist/platform/elc elb.el > dist/elb.c
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
-I runtime \
|
||||
dist/elb.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-o dist/bin/elb
|
||||
chmod +x dist/bin/elb
|
||||
@@ -189,7 +189,7 @@ jobs:
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
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
|
||||
@@ -200,7 +200,7 @@ jobs:
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
ABS_RUNTIME="$(pwd)/runtime"
|
||||
ABS_OUT="$(pwd)/dist/bin"
|
||||
(cd tools/install && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
|
||||
chmod +x dist/bin/el-install
|
||||
@@ -235,7 +235,7 @@ jobs:
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-c \
|
||||
--version="${VERSION}" \
|
||||
--source=el-compiler/runtime/el_runtime.c
|
||||
--source=runtime/el_runtime.c
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-stage \
|
||||
@@ -243,7 +243,7 @@ jobs:
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-h \
|
||||
--version="${VERSION}" \
|
||||
--source=el-compiler/runtime/el_runtime.h
|
||||
--source=runtime/el_runtime.h
|
||||
|
||||
echo "Published El SDK version=${VERSION} to foundation-stage"
|
||||
# Keep key alive for the ci-base rebuild step below
|
||||
@@ -275,9 +275,9 @@ jobs:
|
||||
FROM ${BASE}
|
||||
COPY dist/platform/elc /opt/el/dist/platform/elc
|
||||
COPY dist/bin/elb /opt/el/dist/bin/elb
|
||||
COPY el-compiler/runtime/el_runtime.c /opt/el/el-compiler/runtime/el_runtime.c
|
||||
COPY el-compiler/runtime/el_runtime.h /opt/el/el-compiler/runtime/el_runtime.h
|
||||
COPY el-compiler/runtime/el_runtime.js /opt/el/el-compiler/runtime/el_runtime.js
|
||||
COPY runtime/el_runtime.c /opt/el/runtime/el_runtime.c
|
||||
COPY runtime/el_runtime.h /opt/el/runtime/el_runtime.h
|
||||
COPY runtime/el_runtime.js /opt/el/runtime/el_runtime.js
|
||||
RUN chmod +x /opt/el/dist/platform/elc /opt/el/dist/bin/elb
|
||||
EOF
|
||||
|
||||
|
||||
@@ -47,9 +47,9 @@ jobs:
|
||||
mkdir -p dist/platform
|
||||
dist/platform/elc-linux-amd64 elc-cli.el > dist/elc-gen2.c
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
-I runtime \
|
||||
dist/elc-gen2.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-o dist/platform/elc
|
||||
chmod +x dist/platform/elc
|
||||
@@ -62,9 +62,9 @@ jobs:
|
||||
mkdir -p dist/bin
|
||||
dist/platform/elc elb.el > dist/elb.c
|
||||
gcc -O2 \
|
||||
-I el-compiler/runtime \
|
||||
-I runtime \
|
||||
dist/elb.c \
|
||||
el-compiler/runtime/el_runtime.c \
|
||||
runtime/el_runtime.c \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm \
|
||||
-o dist/bin/elb
|
||||
chmod +x dist/bin/elb
|
||||
@@ -75,7 +75,7 @@ jobs:
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
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
|
||||
@@ -86,7 +86,7 @@ jobs:
|
||||
run: |
|
||||
ABS_ELB="$(pwd)/dist/bin/elb"
|
||||
ABS_ELC="$(pwd)/dist/platform/elc"
|
||||
ABS_RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
ABS_RUNTIME="$(pwd)/runtime"
|
||||
ABS_OUT="$(pwd)/dist/bin"
|
||||
(cd tools/install && "$ABS_ELB" --clean --elc="$ABS_ELC" --runtime="$ABS_RUNTIME" --out="$ABS_OUT")
|
||||
chmod +x dist/bin/el-install
|
||||
@@ -121,7 +121,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_core.el > /tmp/el_native_core.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_core.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_core
|
||||
@@ -131,7 +131,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_text.el > /tmp/el_native_text.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_text.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_text
|
||||
@@ -141,7 +141,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_string.el > /tmp/el_native_string.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_string.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_string
|
||||
@@ -151,7 +151,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_math.el > /tmp/el_native_math.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_math.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_math
|
||||
@@ -161,7 +161,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_state.el > /tmp/el_native_state.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_state.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_state
|
||||
@@ -171,7 +171,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_time.el > /tmp/el_native_time.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_time.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_time
|
||||
@@ -181,7 +181,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_json.el > /tmp/el_native_json.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_json.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_json
|
||||
@@ -191,7 +191,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_env.el > /tmp/el_native_env.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_env.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_env
|
||||
@@ -201,7 +201,7 @@ jobs:
|
||||
run: |
|
||||
set -euo pipefail
|
||||
ELC="$(pwd)/dist/platform/elc"
|
||||
RUNTIME="$(pwd)/el-compiler/runtime"
|
||||
RUNTIME="$(pwd)/runtime"
|
||||
"$ELC" --test tests/native/test_fs.el > /tmp/el_native_fs.c
|
||||
gcc -O2 -I "$RUNTIME" /tmp/el_native_fs.c "$RUNTIME/el_runtime.c" \
|
||||
-lcurl -lssl -lcrypto -lpthread -lm -o /tmp/el_native_fs
|
||||
@@ -216,8 +216,8 @@ jobs:
|
||||
cp lang/dist/platform/elc dist/sdk/bin/elc
|
||||
cp lang/dist/bin/elb dist/sdk/bin/elb
|
||||
cp lang/dist/bin/epm dist/sdk/bin/epm
|
||||
cp lang/el-compiler/runtime/el_runtime.c dist/sdk/runtime/
|
||||
cp lang/el-compiler/runtime/el_runtime.h dist/sdk/runtime/
|
||||
cp lang/runtime/el_runtime.c dist/sdk/runtime/
|
||||
cp lang/runtime/el_runtime.h dist/sdk/runtime/
|
||||
cp lang/runtime/*.el dist/sdk/runtime/
|
||||
tar -czf dist/el-sdk-latest.tar.gz -C dist/sdk .
|
||||
echo "SDK tarball bundled: dist/el-sdk-latest.tar.gz"
|
||||
@@ -274,8 +274,8 @@ jobs:
|
||||
|
||||
# Per-file assets (downstream CI needs these individually)
|
||||
upload_asset lang/dist/platform/elc elc
|
||||
upload_asset lang/el-compiler/runtime/el_runtime.c el_runtime.c
|
||||
upload_asset lang/el-compiler/runtime/el_runtime.h el_runtime.h
|
||||
upload_asset lang/runtime/el_runtime.c el_runtime.c
|
||||
upload_asset lang/runtime/el_runtime.h el_runtime.h
|
||||
|
||||
# SDK bundle and installer binary
|
||||
upload_asset dist/el-sdk-latest.tar.gz el-sdk-latest.tar.gz
|
||||
@@ -319,7 +319,7 @@ jobs:
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-c \
|
||||
--version="${VERSION}" \
|
||||
--source=el-compiler/runtime/el_runtime.c
|
||||
--source=runtime/el_runtime.c
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-prod \
|
||||
@@ -327,7 +327,7 @@ jobs:
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-h \
|
||||
--version="${VERSION}" \
|
||||
--source=el-compiler/runtime/el_runtime.h
|
||||
--source=runtime/el_runtime.h
|
||||
|
||||
gcloud artifacts generic upload \
|
||||
--repository=foundation-prod \
|
||||
@@ -335,7 +335,7 @@ jobs:
|
||||
--project=neuron-785695 \
|
||||
--package=el-runtime-js \
|
||||
--version="${VERSION}" \
|
||||
--source=el-compiler/runtime/el_runtime.js
|
||||
--source=runtime/el_runtime.js
|
||||
|
||||
echo "Published El SDK version=${VERSION} to foundation-prod"
|
||||
# Keep key alive for the ci-base rebuild step below
|
||||
@@ -367,9 +367,9 @@ jobs:
|
||||
FROM ${BASE}
|
||||
COPY dist/platform/elc /opt/el/dist/platform/elc
|
||||
COPY dist/bin/elb /opt/el/dist/bin/elb
|
||||
COPY el-compiler/runtime/el_runtime.c /opt/el/el-compiler/runtime/el_runtime.c
|
||||
COPY el-compiler/runtime/el_runtime.h /opt/el/el-compiler/runtime/el_runtime.h
|
||||
COPY el-compiler/runtime/el_runtime.js /opt/el/el-compiler/runtime/el_runtime.js
|
||||
COPY runtime/el_runtime.c /opt/el/runtime/el_runtime.c
|
||||
COPY runtime/el_runtime.h /opt/el/runtime/el_runtime.h
|
||||
COPY runtime/el_runtime.js /opt/el/runtime/el_runtime.js
|
||||
RUN chmod +x /opt/el/dist/platform/elc /opt/el/dist/bin/elb
|
||||
EOF
|
||||
|
||||
|
||||
@@ -6,13 +6,13 @@ set -euo pipefail
|
||||
|
||||
ROOT="$(git rev-parse --show-toplevel)"
|
||||
LANG_DIR="$ROOT/lang"
|
||||
RUNTIME="$LANG_DIR/el-compiler/runtime"
|
||||
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 el-compiler/runtime dist/elc-bootstrap.c el-compiler/runtime/el_runtime.c -lcurl -lpthread -o dist/elc-gen2 && ./dist/elc-gen2 el-compiler/src/compiler.el > /tmp/elc.c && gcc -O2 -I el-compiler/runtime /tmp/elc.c el-compiler/runtime/el_runtime.c -lcurl -lpthread -o dist/platform/elc"
|
||||
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
|
||||
|
||||
|
||||
@@ -1,45 +0,0 @@
|
||||
;;; lang_profile_es.el — Spanish language profile for ELP.
|
||||
;;; Keys the realizer's construction switches. Mirrors lang_profile_en / _pt.
|
||||
|
||||
(lang_profile_es
|
||||
(language "Spanish")
|
||||
(iso639 "es")
|
||||
(family "Romance")
|
||||
|
||||
;; -- core typology flags -------------------------------------------------
|
||||
(pro-drop yes) ; subjects routinely dropped; agreement carries person
|
||||
(obligatory-subject no)
|
||||
(grammatical-gender yes) ; m/f on every noun; article+adjective AGREE
|
||||
(gender-source lexicon); REAL per-noun gender from UniMorph — NOT a heuristic
|
||||
(do-support no)
|
||||
(subject-aux-inversion no) ; questions by intonation/punctuation, not inversion
|
||||
(question-strategy intonation)
|
||||
(article-selection "el/la/los/las un/una/unos/unas")
|
||||
(stressed-a-rule yes) ; fem sg noun in stressed a-/ha- takes el/un (el agua)
|
||||
(adjective-position postnominal) ; default post; a few prenominal + apocope
|
||||
(adjective-agreement "gender+number")
|
||||
(question-punct inverted) ; opening ¿ ¡ required
|
||||
|
||||
;; -- MANDATORY CONTRACTIONS (coordinator quality bar) --------------------
|
||||
(contractions ((de el "del") (a el "al")))
|
||||
(contraction-mandatory yes) ; 'de el'/'a el' MUST surface as del/al
|
||||
|
||||
;; -- verb / aspect system ------------------------------------------------
|
||||
(verb-classes (ar er ir))
|
||||
(tenses (present preterite imperfect future conditional))
|
||||
(moods (ind sbjv imp))
|
||||
(finite-agreement "person+number (6 slots)")
|
||||
(perfect-aux "haber") ; haber + past participle (invariant -o)
|
||||
(progressive-aux "estar") ; estar + gerund
|
||||
(passive-aux "ser") ; ser + participle (agrees) + por-agent
|
||||
(copula-split "ser/estar") ; permanent vs stage-level
|
||||
(future "infinitive + é/ás/á/emos/éis/án")
|
||||
|
||||
;; -- clitics / government ------------------------------------------------
|
||||
(object-clitics yes) ; me te lo la le nos os los las; proclisis/enclisis
|
||||
(clitic-order "se II I III (le+lo -> se lo)")
|
||||
(enclisis "imperative/infinitive/gerund + accent repair (dá+me+lo->dámelo)")
|
||||
(verb-prep-government yes) ; verbs select prep (protestar+contra, escapar+de)
|
||||
|
||||
;; -- SACRED safety bar (shared with en/pt) -------------------------------
|
||||
(negation-faithful yes)) ; polarity never dropped/inverted; unplaceable -> FLAG
|
||||
+10
-171
@@ -54,16 +54,6 @@ fn es_str_last3(s: String) -> String {
|
||||
// Spanish verbs fall into three conjugation classes defined by the infinitive
|
||||
// ending: -ar, -er, -ir. The stem is the infinitive minus those two characters.
|
||||
|
||||
// Strong-vowel-final test (a/e/o) — used for orthographic y-insertion and the
|
||||
// accented -ído participle (caer->caído/cayó; but ui/iu diphthongs stay plain).
|
||||
fn es_strong_vowel_final(s: String) -> Bool {
|
||||
let c: String = es_str_last_char(s)
|
||||
if str_eq(c, "a") { return true }
|
||||
if str_eq(c, "e") { return true }
|
||||
if str_eq(c, "o") { return true }
|
||||
return false
|
||||
}
|
||||
|
||||
fn es_verb_class(base: String) -> String {
|
||||
if es_str_ends(base, "ar") { return "ar" }
|
||||
if es_str_ends(base, "er") { return "er" }
|
||||
@@ -463,18 +453,12 @@ fn es_regular_preterite(stem: String, vclass: String, slot: Int) -> String {
|
||||
if slot == 4 { return stem + "asteis" }
|
||||
return stem + "aron"
|
||||
}
|
||||
// -er and -ir share the same preterite endings.
|
||||
// Orthographic rule: a vowel-final stem takes -yó/-yeron (caer->cayó,
|
||||
// leer->leyó, creer->creyó) since -ió after a vowel becomes -yó.
|
||||
// -er and -ir share the same preterite endings
|
||||
if slot == 0 { return stem + "í" }
|
||||
if slot == 1 { return stem + "iste" }
|
||||
if slot == 2 {
|
||||
if es_strong_vowel_final(stem) { return stem + "yó" }
|
||||
return stem + "ió"
|
||||
}
|
||||
if slot == 2 { return stem + "ió" }
|
||||
if slot == 3 { return stem + "imos" }
|
||||
if slot == 4 { return stem + "isteis" }
|
||||
if es_strong_vowel_final(stem) { return stem + "yeron" }
|
||||
return stem + "ieron"
|
||||
}
|
||||
|
||||
@@ -656,35 +640,17 @@ fn es_pluralize(noun: String) -> String {
|
||||
if !str_eq(inv, "") {
|
||||
return inv
|
||||
}
|
||||
// Oxytone nouns ending accented-vowel + n LOSE the written accent in the
|
||||
// plural (canción->canciones, razón->razones, jardín->jardines).
|
||||
// NOTE El strings are byte-indexed; "ón"/"án"/... are 3 bytes (accent=2 +n).
|
||||
if es_str_ends(noun, "ón") { return es_str_drop_last(noun, 3) + "ones" }
|
||||
if es_str_ends(noun, "án") { return es_str_drop_last(noun, 3) + "anes" }
|
||||
if es_str_ends(noun, "én") { return es_str_drop_last(noun, 3) + "enes" }
|
||||
if es_str_ends(noun, "ín") { return es_str_drop_last(noun, 3) + "ines" }
|
||||
if es_str_ends(noun, "ún") { return es_str_drop_last(noun, 3) + "unes" }
|
||||
// Oxytone accented-vowel + s also loses the accent (francés->franceses,
|
||||
// inglés->ingleses). í/ú stay (país->países via the consonant rule).
|
||||
if es_str_ends(noun, "és") { return es_str_drop_last(noun, 3) + "eses" }
|
||||
if es_str_ends(noun, "ás") { return es_str_drop_last(noun, 3) + "ases" }
|
||||
if es_str_ends(noun, "ós") { return es_str_drop_last(noun, 3) + "oses" }
|
||||
let last: String = es_str_last_char(noun)
|
||||
// Ends in -z: replace with -ces
|
||||
if es_str_ends(noun, "z") {
|
||||
if str_eq(last, "z") {
|
||||
return es_str_drop_last(noun, 1) + "ces"
|
||||
}
|
||||
// Stressed final vowel: á/é/ó -> +s (café->cafés); í/ú -> +es (rubí->rubíes)
|
||||
if es_str_ends(noun, "á") { return noun + "s" }
|
||||
if es_str_ends(noun, "é") { return noun + "s" }
|
||||
if es_str_ends(noun, "ó") { return noun + "s" }
|
||||
if es_str_ends(noun, "í") { return noun + "es" }
|
||||
if es_str_ends(noun, "ú") { return noun + "es" }
|
||||
// Plain final vowel: add -s
|
||||
if es_str_ends(noun, "a") { return noun + "s" }
|
||||
if es_str_ends(noun, "e") { return noun + "s" }
|
||||
if es_str_ends(noun, "i") { return noun + "s" }
|
||||
if es_str_ends(noun, "o") { return noun + "s" }
|
||||
if es_str_ends(noun, "u") { return noun + "s" }
|
||||
// Ends in a vowel: add -s
|
||||
if str_eq(last, "a") { return noun + "s" }
|
||||
if str_eq(last, "e") { return noun + "s" }
|
||||
if str_eq(last, "i") { return noun + "s" }
|
||||
if str_eq(last, "o") { return noun + "s" }
|
||||
if str_eq(last, "u") { return noun + "s" }
|
||||
// Ends in consonant (including -s for stressed words like autobús): add -es
|
||||
return noun + "es"
|
||||
}
|
||||
@@ -721,37 +687,6 @@ fn es_starts_with_stressed_a(noun: String) -> Bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// es_article_for_gender: the article logic, given gender EXPLICITLY.
|
||||
// The realizer should call this with the REAL per-noun gender from
|
||||
// vocabulary-es.el (form2), NOT the es_gender heuristic — that is what
|
||||
// eliminates the 'el mano' / 'la día' masculine-default error class.
|
||||
fn es_article_for_gender(gender: String, noun: String, definite: String, number: String) -> String {
|
||||
let is_plural: Bool = str_eq(number, "plural")
|
||||
let is_def: Bool = str_eq(definite, "true")
|
||||
|
||||
if is_def {
|
||||
if is_plural {
|
||||
if str_eq(gender, "f") { return "las" }
|
||||
return "los"
|
||||
}
|
||||
if str_eq(gender, "f") {
|
||||
if es_starts_with_stressed_a(noun) { return "el" }
|
||||
return "la"
|
||||
}
|
||||
return "el"
|
||||
}
|
||||
|
||||
if is_plural {
|
||||
if str_eq(gender, "f") { return "unas" }
|
||||
return "unos"
|
||||
}
|
||||
if str_eq(gender, "f") {
|
||||
if es_starts_with_stressed_a(noun) { return "un" }
|
||||
return "una"
|
||||
}
|
||||
return "un"
|
||||
}
|
||||
|
||||
fn es_agree_article(noun: String, definite: String, number: String) -> String {
|
||||
let gender: String = es_gender(noun)
|
||||
let is_plural: Bool = str_eq(number, "plural")
|
||||
@@ -779,99 +714,3 @@ fn es_agree_article(noun: String, definite: String, number: String) -> String {
|
||||
if str_eq(gender, "f") { return "una" }
|
||||
return "un"
|
||||
}
|
||||
|
||||
// ── Past participle (compound tenses: haber + participle) ─────────────────────
|
||||
//
|
||||
// Irregular participle table (transcribed from morphology_es_full._IRREG_PART),
|
||||
// then the regular rule: -ar -> -ado, -er/-ir -> -ido.
|
||||
|
||||
fn es_participle(verb: String) -> String {
|
||||
if str_eq(verb, "escribir") { return "escrito" }
|
||||
if str_eq(verb, "describir") { return "descrito" }
|
||||
if str_eq(verb, "abrir") { return "abierto" }
|
||||
if str_eq(verb, "cubrir") { return "cubierto" }
|
||||
if str_eq(verb, "descubrir") { return "descubierto" }
|
||||
if str_eq(verb, "morir") { return "muerto" }
|
||||
if str_eq(verb, "poner") { return "puesto" }
|
||||
if str_eq(verb, "ver") { return "visto" }
|
||||
if str_eq(verb, "volver") { return "vuelto" }
|
||||
if str_eq(verb, "devolver") { return "devuelto" }
|
||||
if str_eq(verb, "hacer") { return "hecho" }
|
||||
if str_eq(verb, "deshacer") { return "deshecho" }
|
||||
if str_eq(verb, "decir") { return "dicho" }
|
||||
if str_eq(verb, "romper") { return "roto" }
|
||||
if str_eq(verb, "resolver") { return "resuelto" }
|
||||
if str_eq(verb, "freír") { return "frito" }
|
||||
if str_eq(verb, "imprimir") { return "impreso" }
|
||||
if str_eq(verb, "satisfacer") { return "satisfecho" }
|
||||
if str_eq(verb, "prever") { return "previsto" }
|
||||
if str_eq(verb, "revolver") { return "revuelto" }
|
||||
// Accented -ír infinitives (oír->oído, sonreír->sonreído): "ír" is 3 bytes.
|
||||
if es_str_ends(verb, "ír") { return es_str_drop_last(verb, 3) + "ído" }
|
||||
if es_str_ends(verb, "ar") { return es_str_drop_last(verb, 2) + "ado" }
|
||||
// -er/-ir: a strong-vowel stem takes the accented -ído (caer->caído,
|
||||
// leer->leído, poseer->poseído); consonant stems stay -ido; ui/iu
|
||||
// diphthongs (construir->construido) stay plain.
|
||||
if es_str_ends(verb, "er") {
|
||||
let st: String = es_str_drop_last(verb, 2)
|
||||
if es_strong_vowel_final(st) { return st + "ído" }
|
||||
return st + "ido"
|
||||
}
|
||||
if es_str_ends(verb, "ir") {
|
||||
let st: String = es_str_drop_last(verb, 2)
|
||||
if es_strong_vowel_final(st) { return st + "ído" }
|
||||
return st + "ido"
|
||||
}
|
||||
return verb
|
||||
}
|
||||
|
||||
// ── Adjective agreement (gender + number) ─────────────────────────────────────
|
||||
//
|
||||
// Rule-based agreement mirroring morphology_es_full.inflect_adj (rule path):
|
||||
// feminine: -o -> -a; nationality/-dor exceptions add -a; else invariant
|
||||
// plural: reuse es_pluralize on the agreed singular
|
||||
// (Lexicon-backed adjectives in Python may differ; those divergences are what
|
||||
// the parity check surfaces.)
|
||||
|
||||
fn es_adj_feminine(lemma: String) -> String {
|
||||
if str_eq(lemma, "español") { return "española" }
|
||||
if str_eq(lemma, "francés") { return "francesa" }
|
||||
if str_eq(lemma, "inglés") { return "inglesa" }
|
||||
if str_eq(lemma, "alemán") { return "alemana" }
|
||||
if str_eq(lemma, "trabajador") { return "trabajadora" }
|
||||
if str_eq(lemma, "hablador") { return "habladora" }
|
||||
if str_eq(lemma, "encantador") { return "encantadora" }
|
||||
if es_str_ends(lemma, "o") { return es_str_drop_last(lemma, 1) + "a" }
|
||||
return lemma
|
||||
}
|
||||
|
||||
fn es_inflect_adj(lemma: String, gender: String, number: String) -> String {
|
||||
if str_eq(gender, "f") {
|
||||
let fem: String = es_adj_feminine(lemma)
|
||||
if str_eq(number, "plural") { return es_pluralize(fem) }
|
||||
return fem
|
||||
}
|
||||
// masculine (citation)
|
||||
if str_eq(number, "plural") { return es_pluralize(lemma) }
|
||||
return lemma
|
||||
}
|
||||
|
||||
// ── Mandatory preposition + article contraction (de+el->del, a+el->al) ────────
|
||||
//
|
||||
// Transcribed from realizer_es._contract. np_text is the already-realized NP
|
||||
// beginning with "el " when the contraction fires.
|
||||
|
||||
fn es_starts_el(np_text: String) -> Bool {
|
||||
let n: Int = str_len(np_text)
|
||||
if n < 3 { return false }
|
||||
return str_eq(str_slice(np_text, 0, 3), "el ")
|
||||
}
|
||||
|
||||
fn es_contract(prep: String, np_text: String) -> String {
|
||||
if es_starts_el(np_text) {
|
||||
let rest: String = str_slice(np_text, 3, str_len(np_text))
|
||||
if str_eq(prep, "de") { return "del " + rest }
|
||||
if str_eq(prep, "a") { return "al " + rest }
|
||||
}
|
||||
return prep + " " + np_text
|
||||
}
|
||||
|
||||
@@ -1,362 +0,0 @@
|
||||
;;; vocabulary-es.el — Spanish vocabulary for ELP surface realization.
|
||||
;;; Schema: (lemma pos form0 form1 form2 en_translation semantic_hint)
|
||||
;;; Source: UniMorph Spanish (github.com/unimorph/spa, CC-BY-SA 3.0),
|
||||
;;; generated by gen_elp_es.py via morphology_es_full (real forms).
|
||||
;;; Verbs: form0=present-ind-3sg form1=preterite-3sg form2=past-participle
|
||||
;;; Nouns: form0=singular form1=plural form2=REAL gender (m/f, from lexicon —
|
||||
;;; NOT an ending heuristic; this is what kills 'el mano'/'la día' errors)
|
||||
;;; Adjs : form0=masc-sg form1=fem-sg form2=masc-pl
|
||||
|
||||
(vocabulary-es
|
||||
|
||||
;; -- function / closed class (incl. mandatory contractions del/al) --------
|
||||
("el" "det" "el" "los" "m" "the" "definite article m.sg")
|
||||
("la" "det" "la" "las" "f" "the" "definite article f.sg")
|
||||
("un" "det" "un" "unos" "m" "a" "indefinite article m.sg")
|
||||
("una" "det" "una" "unas" "f" "a" "indefinite article f.sg")
|
||||
("del" "contraction" "del" "" "" "of the" "de + el (mandatory contraction)")
|
||||
("al" "contraction" "al" "" "" "to the" "a + el (mandatory contraction)")
|
||||
("este" "dem" "este" "estos" "m" "this" "proximal dem m")
|
||||
("esta" "dem" "esta" "estas" "f" "this" "proximal dem f")
|
||||
("no" "neg" "no" "" "" "not/no" "sentential negator (preverbal)")
|
||||
("ninguno" "det" "ningún" "ninguna" "" "none" "negative determiner (apocope ningún m.sg)")
|
||||
("y" "conj" "y" "e" "" "and" "coordinator (e before i-/hi-)")
|
||||
("o" "conj" "o" "u" "" "or" "coordinator (u before o-/ho-)")
|
||||
("pero" "conj" "pero" "" "" "but" "adversative coordinator")
|
||||
("que" "conj" "que" "" "" "that" "complementizer / relative")
|
||||
("si" "conj" "si" "" "" "if" "conditional subordinator")
|
||||
("porque" "conj" "porque" "" "" "because" "causal subordinator")
|
||||
("cuando" "conj" "cuando" "" "" "when" "temporal subordinator")
|
||||
("a" "prep" "a" "" "" "to" "dir-obj (personal a) / dative / allative; a+el=al")
|
||||
("de" "prep" "de" "" "" "of/from" "genitive/ablative government; de+el=del")
|
||||
("en" "prep" "en" "" "" "in/on" "locative")
|
||||
("con" "prep" "con" "" "" "with" "comitative")
|
||||
("por" "prep" "por" "" "" "by/for" "passive agent / cause")
|
||||
("para" "prep" "para" "" "" "for" "purpose/benefactive")
|
||||
("contra" "prep" "contra" "" "" "against" "adversative government (protestar contra)")
|
||||
("sin" "prep" "sin" "" "" "without" "privative")
|
||||
("yo" "pron" "yo" "me" "mi" "I" "1sg subj/obj/poss")
|
||||
("tú" "pron" "tú" "te" "tu" "you" "2sg informal")
|
||||
("usted" "pron" "usted" "lo" "su" "you" "2sg formal (3sg agreement)")
|
||||
("él" "pron" "él" "lo" "su" "he" "3sg m subj/DO-clitic/poss")
|
||||
("ella" "pron" "ella" "la" "su" "she" "3sg f subj/DO-clitic/poss")
|
||||
("nosotros" "pron" "nosotros" "nos" "nuestro" "we" "1pl")
|
||||
("vosotros" "pron" "vosotros" "os" "vuestro" "you" "2pl informal")
|
||||
("ellos" "pron" "ellos" "los" "su" "they" "3pl m")
|
||||
("ellas" "pron" "ellas" "las" "su" "they" "3pl f")
|
||||
("le" "clitic" "le" "les" "" "to-him/her" "dative clitic 3sg/3pl (->se before lo/la)")
|
||||
("se" "clitic" "se" "se" "" "himself/-self" "reflexive / spurious-se (le+lo->se lo)")
|
||||
|
||||
;; -- verbs (form0=pres-3sg form1=pret-3sg form2=past-participle) -----------
|
||||
("abrazar" "verb" "abraza" "abrazó" "abrazado" "abrazar" "ar/regular")
|
||||
("abrir" "verb" "abre" "abrió" "abierto" "abrir" "ir/irregular")
|
||||
("aceptar" "verb" "acepta" "aceptó" "aceptado" "aceptar" "ar/regular")
|
||||
("acordar" "verb" "acuerda" "acordó" "acordado" "acordar" "ar/regular")
|
||||
("amar" "verb" "ama" "amó" "amado" "amar" "ar/regular")
|
||||
("anunciar" "verb" "anuncia" "anunció" "anunciado" "anunciar" "ar/regular")
|
||||
("aprobar" "verb" "aprueba" "aprobó" "aprobado" "aprobar" "ar/regular")
|
||||
("aumentar" "verb" "aumenta" "aumentó" "aumentado" "aumentar" "ar/regular")
|
||||
("ayudar" "verb" "ayuda" "ayudó" "ayudado" "ayudar" "ar/regular")
|
||||
("bajar" "verb" "baja" "bajó" "bajado" "bajar" "ar/regular")
|
||||
("besar" "verb" "besa" "besó" "besado" "besar" "ar/regular")
|
||||
("buscar" "verb" "busca" "buscó" "buscado" "buscar" "ar/regular")
|
||||
("caer" "verb" "cae" "cayó" "caído" "caer" "er/regular")
|
||||
("cambiar" "verb" "cambia" "cambió" "cambiado" "cambiar" "ar/regular")
|
||||
("caminar" "verb" "camina" "caminó" "caminado" "caminar" "ar/regular")
|
||||
("cantar" "verb" "canta" "cantó" "cantado" "cantar" "ar/regular")
|
||||
("celebrar" "verb" "celebra" "celebró" "celebrado" "celebrar" "ar/regular")
|
||||
("cerrar" "verb" "cierra" "cerró" "cerrado" "cerrar" "ar/regular")
|
||||
("comenzar" "verb" "comienza" "comenzó" "comenzado" "comenzar" "ar/regular")
|
||||
("comer" "verb" "come" "comió" "comido" "comer" "er/regular")
|
||||
("condenar" "verb" "condena" "condenó" "condenado" "condenar" "ar/regular")
|
||||
("confirmar" "verb" "confirma" "confirmó" "confirmado" "confirmar" "ar/regular")
|
||||
("conocer" "verb" "conoce" "conoció" "conocido" "conocer" "er/regular")
|
||||
("contar" "verb" "cuenta" "contó" "contado" "contar" "ar/regular")
|
||||
("contratar" "verb" "contrata" "contrató" "contratado" "contratar" "ar/regular")
|
||||
("costar" "verb" "cuesta" "costó" "costado" "costar" "ar/regular")
|
||||
("crear" "verb" "crea" "creó" "creado" "crear" "ar/regular")
|
||||
("crecer" "verb" "crece" "creció" "crecido" "crecer" "er/regular")
|
||||
("creer" "verb" "cree" "creyó" "creído" "creer" "er/regular")
|
||||
("dar" "verb" "da" "dio" "dado" "dar" "ar/irregular")
|
||||
("deber" "verb" "debe" "debió" "debido" "deber" "er/regular")
|
||||
("decir" "verb" "dice" "dijo" "dicho" "decir" "ir/irregular")
|
||||
("dejar" "verb" "deja" "dejó" "dejado" "dejar" "ar/regular")
|
||||
("desaparecer" "verb" "desaparece" "desapareció" "desaparecido" "desaparecer" "er/regular")
|
||||
("descubrir" "verb" "descubre" "descubrió" "descubierto" "descubrir" "ir/irregular")
|
||||
("despedir" "verb" "despide" "despidió" "despedido" "despedir" "ir/regular")
|
||||
("detener" "verb" "detiene" "detuvo" "detenido" "detener" "er/regular")
|
||||
("dimitir" "verb" "dimite" "dimitió" "dimitido" "dimitir" "ir/regular")
|
||||
("doler" "verb" "duele" "dolió" "dolido" "doler" "er/regular")
|
||||
("dormir" "verb" "duerme" "durmió" "dormido" "dormir" "ir/regular")
|
||||
("durar" "verb" "dura" "duró" "durado" "durar" "ar/regular")
|
||||
("empezar" "verb" "empieza" "empezó" "empezado" "empezar" "ar/regular")
|
||||
("encontrar" "verb" "encuentra" "encontró" "encontrado" "encontrar" "ar/regular")
|
||||
("entender" "verb" "entiende" "entendió" "entendido" "entender" "er/regular")
|
||||
("entrar" "verb" "entra" "entró" "entrado" "entrar" "ar/regular")
|
||||
("entregar" "verb" "entrega" "entregó" "entregado" "entregar" "ar/regular")
|
||||
("escapar" "verb" "escapa" "escapó" "escapado" "escapar" "ar/regular")
|
||||
("escribir" "verb" "escribe" "escribió" "escrito" "escribir" "ir/regular")
|
||||
("escuchar" "verb" "escucha" "escuchó" "escuchado" "escuchar" "ar/regular")
|
||||
("esperar" "verb" "espera" "esperó" "esperado" "esperar" "ar/regular")
|
||||
("estar" "verb" "está" "estuvo" "estado" "estar" "ar/irregular")
|
||||
("estudiar" "verb" "estudia" "estudió" "estudiado" "estudiar" "ar/regular")
|
||||
("existir" "verb" "existe" "existió" "existido" "existir" "ir/regular")
|
||||
("explicar" "verb" "explica" "explicó" "explicado" "explicar" "ar/regular")
|
||||
("firmar" "verb" "firma" "firmó" "firmado" "firmar" "ar/regular")
|
||||
("ganar" "verb" "gana" "ganó" "ganado" "ganar" "ar/regular")
|
||||
("gritar" "verb" "grita" "gritó" "gritado" "gritar" "ar/regular")
|
||||
("guardar" "verb" "guarda" "guardó" "guardado" "guardar" "ar/regular")
|
||||
("gustar" "verb" "gusta" "gustó" "gustado" "gustar" "ar/regular")
|
||||
("haber" "verb" "ha" "hubo" "habido" "haber" "er/irregular")
|
||||
("hablar" "verb" "habla" "habló" "hablado" "hablar" "ar/regular")
|
||||
("hacer" "verb" "hace" "hizo" "hecho" "hacer" "er/irregular")
|
||||
("ir" "verb" "va" "fue" "ido" "ir" "ir/irregular")
|
||||
("jugar" "verb" "juega" "jugó" "jugado" "jugar" "ar/regular")
|
||||
("lavar" "verb" "lava" "lavó" "lavado" "lavar" "ar/regular")
|
||||
("leer" "verb" "lee" "leyó" "leído" "leer" "er/regular")
|
||||
("llamar" "verb" "llama" "llamó" "llamado" "llamar" "ar/regular")
|
||||
("llegar" "verb" "llega" "llegó" "llegado" "llegar" "ar/regular")
|
||||
("llevar" "verb" "lleva" "llevó" "llevado" "llevar" "ar/regular")
|
||||
("llover" "verb" "llueve" "llovió" "llovido" "llover" "er/regular")
|
||||
("mirar" "verb" "mira" "miró" "mirado" "mirar" "ar/regular")
|
||||
("morir" "verb" "muere" "murió" "muerto" "morir" "ir/irregular")
|
||||
("mostrar" "verb" "muestra" "mostró" "mostrado" "mostrar" "ar/regular")
|
||||
("nacer" "verb" "nace" "nació" "nacido" "nacer" "er/regular")
|
||||
("ocultar" "verb" "oculta" "ocultó" "ocultado" "ocultar" "ar/regular")
|
||||
("ofrecer" "verb" "ofrece" "ofreció" "ofrecido" "ofrecer" "er/regular")
|
||||
("olvidar" "verb" "olvida" "olvidó" "olvidado" "olvidar" "ar/regular")
|
||||
("oír" "verb" "oye" "oyó" "oído" "oír" "ar/regular")
|
||||
("parecer" "verb" "parece" "pareció" "parecido" "parecer" "er/regular")
|
||||
("pasar" "verb" "pasa" "pasó" "pasado" "pasar" "ar/regular")
|
||||
("pedir" "verb" "pide" "pidió" "pedido" "pedir" "ir/regular")
|
||||
("pensar" "verb" "piensa" "pensó" "pensado" "pensar" "ar/regular")
|
||||
("perder" "verb" "pierde" "perdió" "perdido" "perder" "er/regular")
|
||||
("perdonar" "verb" "perdona" "perdonó" "perdonado" "perdonar" "ar/regular")
|
||||
("poder" "verb" "puede" "pudo" "podido" "poder" "er/irregular")
|
||||
("poner" "verb" "pone" "puso" "puesto" "poner" "er/irregular")
|
||||
("preocupar" "verb" "preocupa" "preocupó" "preocupado" "preocupar" "ar/regular")
|
||||
("producir" "verb" "produce" "produjo" "producido" "producir" "ir/regular")
|
||||
("prometer" "verb" "promete" "prometió" "prometido" "prometer" "er/regular")
|
||||
("proponer" "verb" "propone" "propuso" "propuesto" "proponer" "er/regular")
|
||||
("prosperar" "verb" "prospera" "prosperó" "prosperado" "prosperar" "ar/regular")
|
||||
("protestar" "verb" "protesta" "protestó" "protestado" "protestar" "ar/regular")
|
||||
("quedar" "verb" "queda" "quedó" "quedado" "quedar" "ar/regular")
|
||||
("querer" "verb" "quiere" "quiso" "querido" "querer" "er/irregular")
|
||||
("recordar" "verb" "recuerda" "recordó" "recordado" "recordar" "ar/regular")
|
||||
("recorrer" "verb" "recorre" "recorrió" "recorrido" "recorrer" "er/regular")
|
||||
("regresar" "verb" "regresa" "regresó" "regresado" "regresar" "ar/regular")
|
||||
("renacer" "verb" "renace" "renació" "renacido" "renacer" "er/regular")
|
||||
("saber" "verb" "sabe" "supo" "sabido" "saber" "er/irregular")
|
||||
("salir" "verb" "sale" "salió" "salido" "salir" "ir/irregular")
|
||||
("sentar" "verb" "sienta" "sentó" "sentado" "sentar" "ar/regular")
|
||||
("sentir" "verb" "siente" "sintió" "sentido" "sentir" "ir/regular")
|
||||
("separar" "verb" "separa" "separó" "separado" "separar" "ar/regular")
|
||||
("ser" "verb" "es" "fue" "sido" "ser" "er/irregular")
|
||||
("sonreír" "verb" "sonríe" "sonrió" "sonreído" "sonreír" "ar/regular")
|
||||
("soplar" "verb" "sopla" "sopló" "soplado" "soplar" "ar/regular")
|
||||
("sorprender" "verb" "sorprende" "sorprendió" "sorprendido" "sorprender" "er/regular")
|
||||
("soñar" "verb" "sueña" "soñó" "soñado" "soñar" "ar/regular")
|
||||
("subir" "verb" "sube" "subió" "subido" "subir" "ir/regular")
|
||||
("tener" "verb" "tiene" "tuvo" "tenido" "tener" "er/irregular")
|
||||
("terminar" "verb" "termina" "terminó" "terminado" "terminar" "ar/regular")
|
||||
("tocar" "verb" "toca" "tocó" "tocado" "tocar" "ar/regular")
|
||||
("tomar" "verb" "toma" "tomó" "tomado" "tomar" "ar/regular")
|
||||
("trabajar" "verb" "trabaja" "trabajó" "trabajado" "trabajar" "ar/regular")
|
||||
("vender" "verb" "vende" "vendió" "vendido" "vender" "er/regular")
|
||||
("venir" "verb" "viene" "vino" "venido" "venir" "ir/irregular")
|
||||
("ver" "verb" "ve" "vio" "visto" "ver" "er/irregular")
|
||||
("viajar" "verb" "viaja" "viajó" "viajado" "viajar" "ar/regular")
|
||||
("vivir" "verb" "vive" "vivió" "vivido" "vivir" "ir/regular")
|
||||
("volver" "verb" "vuelve" "volvió" "vuelto" "volver" "er/irregular")
|
||||
|
||||
;; -- nouns (form0=sg form1=pl form2=REAL gender m/f) ----------------------
|
||||
("Barcelona" "noun" "barcelona" "barcelonas" "f" "Barcelona" "gender:heuristic")
|
||||
("Madrid" "noun" "madrid" "madrides" "m" "Madrid" "gender:heuristic")
|
||||
("María" "noun" "maría" "marías" "f" "María" "gender:heuristic")
|
||||
("acuerdo" "noun" "acuerdo" "acuerdos" "m" "acuerdo" "gender:lexicon")
|
||||
("acusado" "noun" "acusado" "acusados" "m" "acusado" "gender:lexicon")
|
||||
("agua" "noun" "agua" "aguas" "f" "agua" "gender:lexicon")
|
||||
("amigo" "noun" "amigo" "amigos" "m" "amigo" "gender:lexicon")
|
||||
("amor" "noun" "amor" "amores" "m" "amor" "gender:lexicon")
|
||||
("anciano" "noun" "anciano" "ancianos" "m" "anciano" "gender:lexicon")
|
||||
("autor" "noun" "autor" "autores" "m" "autor" "gender:lexicon")
|
||||
("ayuda" "noun" "ayuda" "ayudas" "f" "ayuda" "gender:lexicon")
|
||||
("año" "noun" "año" "años" "m" "año" "gender:lexicon")
|
||||
("banco" "noun" "banco" "bancos" "m" "banco" "gender:lexicon")
|
||||
("barco" "noun" "barco" "barcos" "m" "barco" "gender:lexicon")
|
||||
("baño" "noun" "baño" "baños" "m" "baño" "gender:lexicon")
|
||||
("beneficio" "noun" "beneficio" "beneficios" "m" "beneficio" "gender:lexicon")
|
||||
("billete" "noun" "billete" "billetes" "m" "billete" "gender:lexicon")
|
||||
("café" "noun" "café" "cafés" "m" "café" "gender:lexicon")
|
||||
("calma" "noun" "calma" "calmas" "f" "calma" "gender:lexicon")
|
||||
("camino" "noun" "camino" "caminos" "m" "camino" "gender:lexicon")
|
||||
("canción" "noun" "canción" "canciones" "f" "canción" "gender:lexicon")
|
||||
("candidato" "noun" "candidato" "candidatos" "m" "candidato" "gender:lexicon")
|
||||
("casa" "noun" "casa" "casas" "f" "casa" "gender:lexicon")
|
||||
("cena" "noun" "cena" "cenas" "f" "cena" "gender:lexicon")
|
||||
("ciudad" "noun" "ciudad" "ciudades" "f" "ciudad" "gender:lexicon")
|
||||
("ciudadano" "noun" "ciudadano" "ciudadanos" "m" "ciudadano" "gender:lexicon")
|
||||
("color" "noun" "color" "colores" "m" "color" "gender:lexicon")
|
||||
("condición" "noun" "condición" "condiciones" "f" "condición" "gender:lexicon")
|
||||
("corazón" "noun" "corazón" "corazones" "m" "corazón" "gender:lexicon")
|
||||
("costa" "noun" "costa" "costas" "f" "costa" "gender:lexicon")
|
||||
("crisis" "noun" "crisis" "crisis" "f" "crisis" "gender:lexicon")
|
||||
("crédito" "noun" "crédito" "créditos" "m" "crédito" "gender:lexicon")
|
||||
("culpa" "noun" "culpa" "culpas" "f" "culpa" "gender:lexicon")
|
||||
("damnificado" "noun" "damnificado" "damnificados" "m" "damnificado" "gender:lexicon")
|
||||
("demás" "noun" "demás" "demás" "m" "demás" "gender:heuristic")
|
||||
("dinero" "noun" "dinero" "dineros" "m" "dinero" "gender:lexicon")
|
||||
("día" "noun" "día" "días" "m" "día" "gender:lexicon")
|
||||
("economía" "noun" "economía" "economías" "f" "economía" "gender:lexicon")
|
||||
("elección" "noun" "elección" "elecciones" "f" "elección" "gender:lexicon")
|
||||
("empleo" "noun" "empleo" "empleos" "m" "empleo" "gender:lexicon")
|
||||
("empresa" "noun" "empresa" "empresas" "f" "empresa" "gender:lexicon")
|
||||
("equipo" "noun" "equipo" "equipos" "m" "equipo" "gender:lexicon")
|
||||
("estación" "noun" "estación" "estaciones" "f" "estación" "gender:lexicon")
|
||||
("estudiante" "noun" "estudiante" "estudiantes" "m" "estudiante" "gender:lexicon")
|
||||
("experto" "noun" "experto" "expertos" "m" "experto" "gender:lexicon")
|
||||
("fiesta" "noun" "fiesta" "fiestas" "f" "fiesta" "gender:lexicon")
|
||||
("flor" "noun" "flor" "flores" "f" "flor" "gender:lexicon")
|
||||
("foto" "noun" "foto" "fotos" "f" "foto" "gender:lexicon")
|
||||
("frío" "noun" "frío" "fríos" "m" "frío" "gender:lexicon")
|
||||
("fuego" "noun" "fuego" "fuegos" "m" "fuego" "gender:lexicon")
|
||||
("fuerza" "noun" "fuerza" "fuerzas" "f" "fuerza" "gender:lexicon")
|
||||
("gato" "noun" "gato" "gatos" "m" "gato" "gender:lexicon")
|
||||
("gobierno" "noun" "gobierno" "gobiernos" "m" "gobierno" "gender:lexicon")
|
||||
("gusto" "noun" "gusto" "gustos" "m" "gusto" "gender:lexicon")
|
||||
("hermano" "noun" "hermano" "hermanos" "m" "hermano" "gender:lexicon")
|
||||
("hombre" "noun" "hombre" "hombres" "m" "hombre" "gender:lexicon")
|
||||
("jardín" "noun" "jardín" "jardines" "m" "jardín" "gender:lexicon")
|
||||
("juez" "noun" "juez" "jueces" "m" "juez" "gender:lexicon")
|
||||
("juicio" "noun" "juicio" "juicios" "m" "juicio" "gender:lexicon")
|
||||
("lentitud" "noun" "lentitud" "lentitudes" "f" "lentitud" "gender:lexicon")
|
||||
("ley" "noun" "ley" "leyes" "f" "ley" "gender:lexicon")
|
||||
("libertad" "noun" "libertad" "libertades" "f" "libertad" "gender:lexicon")
|
||||
("libro" "noun" "libro" "libros" "m" "libro" "gender:lexicon")
|
||||
("llave" "noun" "llave" "llaves" "f" "llave" "gender:lexicon")
|
||||
("lluvia" "noun" "lluvia" "lluvias" "f" "lluvia" "gender:lexicon")
|
||||
("luna" "noun" "luna" "lunas" "f" "luna" "gender:lexicon")
|
||||
("luz" "noun" "luz" "luces" "f" "luz" "gender:lexicon")
|
||||
("madre" "noun" "madre" "madres" "f" "madre" "gender:lexicon")
|
||||
("mano" "noun" "mano" "manos" "f" "mano" "gender:lexicon")
|
||||
("mapa" "noun" "mapa" "mapas" "m" "mapa" "gender:lexicon")
|
||||
("mar" "noun" "mar" "mares" "m" "mar" "gender:lexicon")
|
||||
("marea" "noun" "marea" "mareas" "f" "marea" "gender:lexicon")
|
||||
("memoria" "noun" "memoria" "memorias" "f" "memoria" "gender:lexicon")
|
||||
("mesa" "noun" "mesa" "mesas" "f" "mesa" "gender:lexicon")
|
||||
("ministro" "noun" "ministro" "ministros" "m" "ministro" "gender:lexicon")
|
||||
("montaña" "noun" "montaña" "montañas" "f" "montaña" "gender:lexicon")
|
||||
("moto" "noun" "moto" "motos" "f" "moto" "gender:lexicon")
|
||||
("mujer" "noun" "mujer" "mujeres" "f" "mujer" "gender:lexicon")
|
||||
("mundo" "noun" "mundo" "mundos" "m" "mundo" "gender:lexicon")
|
||||
("música" "noun" "música" "músicas" "f" "música" "gender:lexicon")
|
||||
("nación" "noun" "nación" "naciones" "f" "nación" "gender:lexicon")
|
||||
("niebla" "noun" "niebla" "nieblas" "f" "niebla" "gender:lexicon")
|
||||
("nieve" "noun" "nieve" "nieves" "f" "nieve" "gender:lexicon")
|
||||
("niña" "noun" "niña" "niñas" "f" "niña" "gender:lexicon")
|
||||
("niño" "noun" "niño" "niños" "m" "niño" "gender:lexicon")
|
||||
("noche" "noun" "noche" "noches" "f" "noche" "gender:lexicon")
|
||||
("nombre" "noun" "nombre" "nombres" "m" "nombre" "gender:lexicon")
|
||||
("ojo" "noun" "ojo" "ojos" "m" "ojo" "gender:heuristic")
|
||||
("orilla" "noun" "orilla" "orillas" "f" "orilla" "gender:lexicon")
|
||||
("paisaje" "noun" "paisaje" "paisajes" "m" "paisaje" "gender:lexicon")
|
||||
("parlamento" "noun" "parlamento" "parlamentos" "m" "parlamento" "gender:lexicon")
|
||||
("parte" "noun" "parte" "partes" "f" "parte" "gender:lexicon")
|
||||
("pasillo" "noun" "pasillo" "pasillos" "m" "pasillo" "gender:lexicon")
|
||||
("país" "noun" "país" "países" "m" "país" "gender:lexicon")
|
||||
("película" "noun" "película" "películas" "f" "película" "gender:lexicon")
|
||||
("perro" "noun" "perro" "perros" "m" "perro" "gender:lexicon")
|
||||
("persona" "noun" "persona" "personas" "f" "persona" "gender:lexicon")
|
||||
("petróleo" "noun" "petróleo" "petróleos" "m" "petróleo" "gender:lexicon")
|
||||
("pez" "noun" "pez" "peces" "f" "pez" "gender:lexicon")
|
||||
("plan" "noun" "plan" "planes" "m" "plan" "gender:lexicon")
|
||||
("policía" "noun" "policía" "policías" "f" "policía" "gender:lexicon")
|
||||
("portavoz" "noun" "portavoz" "portavoces" "m" "portavoz" "gender:lexicon")
|
||||
("portero" "noun" "portero" "porteros" "m" "portero" "gender:lexicon")
|
||||
("precio" "noun" "precio" "precios" "m" "precio" "gender:lexicon")
|
||||
("presidente" "noun" "presidente" "presidentes" "m" "presidente" "gender:lexicon")
|
||||
("problema" "noun" "problema" "problemas" "m" "problema" "gender:lexicon")
|
||||
("programa" "noun" "programa" "programas" "m" "programa" "gender:lexicon")
|
||||
("proyecto" "noun" "proyecto" "proyectos" "m" "proyecto" "gender:lexicon")
|
||||
("puerta" "noun" "puerta" "puertas" "f" "puerta" "gender:lexicon")
|
||||
("pájaro" "noun" "pájaro" "pájaros" "m" "pájaro" "gender:lexicon")
|
||||
("razón" "noun" "razón" "razones" "f" "razón" "gender:lexicon")
|
||||
("raíz" "noun" "raíz" "raíces" "f" "raíz" "gender:lexicon")
|
||||
("recuerdo" "noun" "recuerdo" "recuerdos" "m" "recuerdo" "gender:lexicon")
|
||||
("reforma" "noun" "reforma" "reformas" "f" "reforma" "gender:lexicon")
|
||||
("región" "noun" "región" "regiones" "f" "región" "gender:lexicon")
|
||||
("río" "noun" "río" "ríos" "m" "río" "gender:lexicon")
|
||||
("semilla" "noun" "semilla" "semillas" "f" "semilla" "gender:lexicon")
|
||||
("sendero" "noun" "sendero" "senderos" "m" "sendero" "gender:lexicon")
|
||||
("señor" "noun" "señor" "señores" "m" "señor" "gender:lexicon")
|
||||
("silencio" "noun" "silencio" "silencios" "m" "silencio" "gender:lexicon")
|
||||
("silla" "noun" "silla" "sillas" "f" "silla" "gender:lexicon")
|
||||
("sol" "noun" "sol" "soles" "m" "sol" "gender:lexicon")
|
||||
("tarea" "noun" "tarea" "tareas" "f" "tarea" "gender:lexicon")
|
||||
("tema" "noun" "tema" "temas" "m" "tema" "gender:lexicon")
|
||||
("ti" "noun" "ti" "tis" "m" "ti" "gender:heuristic")
|
||||
("tiempo" "noun" "tiempo" "tiempos" "m" "tiempo" "gender:lexicon")
|
||||
("tipo" "noun" "tipo" "tipos" "m" "tipo" "gender:lexicon")
|
||||
("todo" "noun" "todo" "todos" "m" "todo" "gender:heuristic")
|
||||
("tormenta" "noun" "tormenta" "tormentas" "f" "tormenta" "gender:lexicon")
|
||||
("trabajador" "noun" "trabajador" "trabajadores" "m" "trabajador" "gender:lexicon")
|
||||
("tristeza" "noun" "tristeza" "tristezas" "f" "tristeza" "gender:lexicon")
|
||||
("ventana" "noun" "ventana" "ventanas" "f" "ventana" "gender:lexicon")
|
||||
("verdad" "noun" "verdad" "verdades" "f" "verdad" "gender:lexicon")
|
||||
("viaje" "noun" "viaje" "viajes" "m" "viaje" "gender:lexicon")
|
||||
("victoria" "noun" "victoria" "victorias" "f" "victoria" "gender:lexicon")
|
||||
("vida" "noun" "vida" "vidas" "f" "vida" "gender:lexicon")
|
||||
("viento" "noun" "viento" "vientos" "m" "viento" "gender:lexicon")
|
||||
("voz" "noun" "voz" "voces" "f" "voz" "gender:lexicon")
|
||||
("vuelta" "noun" "vuelta" "vueltas" "f" "vuelta" "gender:lexicon")
|
||||
("árbol" "noun" "árbol" "árboles" "m" "árbol" "gender:lexicon")
|
||||
|
||||
;; -- adjectives (form0=masc-sg form1=fem-sg form2=masc-pl) ----------------
|
||||
("alto" "adj" "alto" "alta" "altos" "alto" "lexicon")
|
||||
("ambos" "adj" "ambos" "ambos" "ambos" "ambos" "rule")
|
||||
("antiguo" "adj" "antiguo" "antigua" "antiguos" "antiguo" "lexicon")
|
||||
("azul" "adj" "azul" "azul" "azules" "azul" "lexicon")
|
||||
("bajo" "adj" "bajo" "baja" "bajos" "bajo" "lexicon")
|
||||
("blanco" "adj" "blanco" "blanca" "blancos" "blanco" "lexicon")
|
||||
("bondadoso" "adj" "bondadoso" "bondadosa" "bondadosos" "bondadoso" "lexicon")
|
||||
("bonito" "adj" "bonito" "bonita" "bonitos" "bonito" "lexicon")
|
||||
("bueno" "adj" "bueno" "buena" "buenos" "bueno" "lexicon")
|
||||
("cansado" "adj" "cansado" "cansada" "cansados" "cansado" "lexicon")
|
||||
("corto" "adj" "corto" "corta" "cortos" "corto" "lexicon")
|
||||
("difícil" "adj" "difícil" "difícil" "difíciles" "difícil" "lexicon")
|
||||
("dos" "adj" "dos" "dos" "dos" "dos" "rule")
|
||||
("económico" "adj" "económico" "económica" "económicos" "económico" "lexicon")
|
||||
("español" "adj" "español" "española" "españoles" "español" "lexicon")
|
||||
("estrecho" "adj" "estrecho" "estrecha" "estrechos" "estrecho" "lexicon")
|
||||
("fascinante" "adj" "fascinante" "fascinante" "fascinantes" "fascinante" "rule")
|
||||
("feliz" "adj" "feliz" "feliz" "felices" "feliz" "lexicon")
|
||||
("francés" "adj" "francés" "francesa" "franceses" "francés" "lexicon")
|
||||
("frío" "adj" "frío" "fría" "fríos" "frío" "lexicon")
|
||||
("fácil" "adj" "fácil" "fácil" "fáciles" "fácil" "lexicon")
|
||||
("grande" "adj" "grande" "grande" "grandes" "grande" "lexicon")
|
||||
("hermoso" "adj" "hermoso" "hermosa" "hermosos" "hermoso" "lexicon")
|
||||
("importante" "adj" "importante" "importante" "importantes" "importante" "lexicon")
|
||||
("inglés" "adj" "inglés" "inglesa" "ingleses" "inglés" "lexicon")
|
||||
("largo" "adj" "largo" "larga" "largos" "largo" "lexicon")
|
||||
("lento" "adj" "lento" "lenta" "lentos" "lento" "lexicon")
|
||||
("malo" "adj" "malo" "mala" "malos" "malo" "lexicon")
|
||||
("mucho" "adj" "mucho" "mucha" "muchos" "mucho" "lexicon")
|
||||
("necesario" "adj" "necesario" "necesaria" "necesarios" "necesario" "lexicon")
|
||||
("negro" "adj" "negro" "negra" "negros" "negro" "lexicon")
|
||||
("nuevo" "adj" "nuevo" "nueva" "nuevos" "nuevo" "lexicon")
|
||||
("olvidado" "adj" "olvidado" "olvidada" "olvidados" "olvidado" "lexicon")
|
||||
("oscuro" "adj" "oscuro" "oscura" "oscuros" "oscuro" "lexicon")
|
||||
("pequeño" "adj" "pequeño" "pequeña" "pequeños" "pequeño" "lexicon")
|
||||
("político" "adj" "político" "política" "políticos" "político" "lexicon")
|
||||
("posible" "adj" "posible" "posible" "posibles" "posible" "lexicon")
|
||||
("rojo" "adj" "rojo" "roja" "rojos" "rojo" "lexicon")
|
||||
("rápido" "adj" "rápido" "rápida" "rápidos" "rápido" "lexicon")
|
||||
("sabio" "adj" "sabio" "sabia" "sabios" "sabio" "lexicon")
|
||||
("silencioso" "adj" "silencioso" "silenciosa" "silenciosos" "silencioso" "lexicon")
|
||||
("social" "adj" "social" "social" "sociales" "social" "lexicon")
|
||||
("trabajador" "adj" "trabajador" "trabajadora" "trabajadores" "trabajador" "lexicon")
|
||||
("triste" "adj" "triste" "triste" "tristes" "triste" "rule")
|
||||
("verde" "adj" "verde" "verde" "verdes" "verde" "lexicon")
|
||||
("viejo" "adj" "viejo" "vieja" "viejos" "viejo" "lexicon")
|
||||
|
||||
)
|
||||
@@ -1,262 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""gen_elp_es.py — emit the ELP (.el) port artifacts for Spanish.
|
||||
|
||||
Mirrors gen_elp_en.py. Produces:
|
||||
vocabulary-es.el real generated vocabulary in the established schema
|
||||
[lemma, pos, form0, form1, form2, en_translation, semantic_hint]
|
||||
(same schema as vocabulary-got.el / vocabulary-en.el;
|
||||
UniMorph spa lineage).
|
||||
Verbs : form0=present-ind-3sg form1=preterite-3sg form2=past-participle
|
||||
Nouns : form0=singular form1=plural form2=REAL gender (m/f, lexicon)
|
||||
Adjs : form0=masc-sg form1=fem-sg form2=masc-pl
|
||||
lang_profile_es.el the Spanish profile with the flags the realizer keys on.
|
||||
|
||||
Every form is generated by morphology_es_full (real UniMorph lexicon, not
|
||||
hand-typed), so the .el vocabulary is honest and reproduces the forms the
|
||||
realizer used. CRITICAL (coordinator quality bar): noun gender in form2 is the
|
||||
REAL per-lemma lexicon gender (N;FEM/MASC), NOT an ending heuristic — this is
|
||||
what kills the 'el mano / la día' masculine-default error class.
|
||||
"""
|
||||
import morphology_es_full as M
|
||||
from test_set_es import TESTS
|
||||
from held_out_es import HELD
|
||||
|
||||
# ── core closed class + common content lemmas so the vocab is usable beyond the
|
||||
# validated sentences ──────────────────────────────────────────────────────
|
||||
_CORE_VERBS = ["ser", "estar", "haber", "tener", "hacer", "ir", "ver", "dar",
|
||||
"saber", "poder", "querer", "venir", "decir", "poner", "salir",
|
||||
"hablar", "comer", "vivir", "trabajar", "estudiar", "llegar",
|
||||
"pasar", "deber", "parecer", "quedar", "creer", "dejar", "llevar",
|
||||
"encontrar", "llamar", "pensar", "volver", "conocer", "sentir",
|
||||
"contar", "empezar", "buscar", "esperar", "existir", "entrar",
|
||||
"escribir", "perder", "producir", "recordar", "morir", "nacer",
|
||||
"abrir", "escapar", "soñar", "amar", "caer", "leer", "oír"]
|
||||
_CORE_NOUNS = ["tiempo", "persona", "año", "día", "mano", "mundo", "vida",
|
||||
"hombre", "mujer", "parte", "casa", "país", "problema", "programa",
|
||||
"tema", "mapa", "agua", "foto", "moto", "ciudad", "libertad",
|
||||
"canción", "nación", "flor", "color", "amor", "señor", "viaje",
|
||||
"paisaje", "gato", "perro", "libro", "mesa", "silla", "noche",
|
||||
"luz", "voz", "pez", "raíz", "crisis", "sol", "luna", "mar",
|
||||
"corazón", "flor", "árbol", "camino", "puerta", "ventana"]
|
||||
_CORE_ADJS = ["bueno", "malo", "nuevo", "viejo", "grande", "pequeño", "alto",
|
||||
"bajo", "largo", "corto", "feliz", "triste", "fácil", "difícil",
|
||||
"rápido", "lento", "hermoso", "económico", "político", "social",
|
||||
"azul", "rojo", "verde", "blanco", "negro", "español", "francés",
|
||||
"inglés", "importante", "posible", "necesario", "trabajador"]
|
||||
|
||||
# closed-class function words. Contractions (del/al) and the government notes
|
||||
# are the coordinator's quality bar (mandatory contraction; verb-prep govt).
|
||||
_FUNCTION = [
|
||||
# articles (gender/number agreement is in morphology; these are citation)
|
||||
("el", "det", "el", "los", "m", "the", "definite article m.sg"),
|
||||
("la", "det", "la", "las", "f", "the", "definite article f.sg"),
|
||||
("un", "det", "un", "unos","m", "a", "indefinite article m.sg"),
|
||||
("una", "det", "una", "unas","f", "a", "indefinite article f.sg"),
|
||||
# MANDATORY CONTRACTIONS (prep + el) — del / al
|
||||
("del", "contraction", "del", "", "", "of the", "de + el (mandatory contraction)"),
|
||||
("al", "contraction", "al", "", "", "to the", "a + el (mandatory contraction)"),
|
||||
# demonstratives
|
||||
("este", "dem", "este", "estos", "m", "this", "proximal dem m"),
|
||||
("esta", "dem", "esta", "estas", "f", "this", "proximal dem f"),
|
||||
# negation (SACRED — polarity never dropped)
|
||||
("no", "neg", "no", "", "", "not/no", "sentential negator (preverbal)"),
|
||||
("ninguno", "det", "ningún", "ninguna", "", "none", "negative determiner (apocope ningún m.sg)"),
|
||||
# conjunctions
|
||||
("y", "conj", "y", "e", "", "and", "coordinator (e before i-/hi-)"),
|
||||
("o", "conj", "o", "u", "", "or", "coordinator (u before o-/ho-)"),
|
||||
("pero", "conj", "pero", "", "", "but", "adversative coordinator"),
|
||||
("que", "conj", "que", "", "", "that", "complementizer / relative"),
|
||||
("si", "conj", "si", "", "", "if", "conditional subordinator"),
|
||||
("porque", "conj", "porque", "", "", "because", "causal subordinator"),
|
||||
("cuando", "conj", "cuando", "", "", "when", "temporal subordinator"),
|
||||
# prepositions (government: verbs select these; contraction with el applies to a/de)
|
||||
("a", "prep", "a", "", "", "to", "dir-obj (personal a) / dative / allative; a+el=al"),
|
||||
("de", "prep", "de", "", "", "of/from", "genitive/ablative government; de+el=del"),
|
||||
("en", "prep", "en", "", "", "in/on", "locative"),
|
||||
("con", "prep", "con", "", "", "with", "comitative"),
|
||||
("por", "prep", "por", "", "", "by/for", "passive agent / cause"),
|
||||
("para", "prep", "para", "", "", "for", "purpose/benefactive"),
|
||||
("contra", "prep", "contra", "", "", "against", "adversative government (protestar contra)"),
|
||||
("sin", "prep", "sin", "", "", "without", "privative"),
|
||||
# subject pronouns
|
||||
("yo", "pron", "yo", "me", "mi", "I", "1sg subj/obj/poss"),
|
||||
("tú", "pron", "tú", "te", "tu", "you", "2sg informal"),
|
||||
("usted", "pron", "usted", "lo", "su", "you", "2sg formal (3sg agreement)"),
|
||||
("él", "pron", "él", "lo", "su", "he", "3sg m subj/DO-clitic/poss"),
|
||||
("ella", "pron", "ella", "la", "su", "she", "3sg f subj/DO-clitic/poss"),
|
||||
("nosotros", "pron", "nosotros", "nos", "nuestro", "we", "1pl"),
|
||||
("vosotros", "pron", "vosotros", "os", "vuestro", "you", "2pl informal"),
|
||||
("ellos", "pron", "ellos", "los", "su", "they", "3pl m"),
|
||||
("ellas", "pron", "ellas", "las", "su", "they", "3pl f"),
|
||||
# indirect-object clitics
|
||||
("le", "clitic", "le", "les", "", "to-him/her", "dative clitic 3sg/3pl (->se before lo/la)"),
|
||||
("se", "clitic", "se", "se", "", "himself/-self", "reflexive / spurious-se (le+lo->se lo)"),
|
||||
]
|
||||
|
||||
|
||||
def _walk_collect(spec, verbs, nouns, adjs):
|
||||
"""Recursively collect verb/noun/adj lemmas from a semantic spec."""
|
||||
if isinstance(spec, dict):
|
||||
if spec.get("pred"):
|
||||
verbs.add(spec["pred"])
|
||||
if spec.get("noun"):
|
||||
nouns.add(spec["noun"])
|
||||
if spec.get("adj"):
|
||||
adjs.add(spec["adj"])
|
||||
if spec.get("superlative"):
|
||||
adjs.add(spec["superlative"])
|
||||
if spec.get("from_adj"):
|
||||
adjs.add(spec["from_adj"])
|
||||
# adjs: [{"lemma":..,"pos":..}] | ["lemma", ..]
|
||||
for a in spec.get("adjs", []) or []:
|
||||
adjs.add(a["lemma"] if isinstance(a, dict) else a)
|
||||
for a in spec.get("adj_coord", []) or []:
|
||||
adjs.add(a["lemma"] if isinstance(a, dict) else a)
|
||||
if isinstance(spec.get("pcomp"), dict):
|
||||
pc = spec["pcomp"]
|
||||
if pc.get("adj"):
|
||||
adjs.add(pc["adj"])
|
||||
for a in pc.get("adj_coord", []) or []:
|
||||
adjs.add(a["lemma"] if isinstance(a, dict) else a)
|
||||
for v in spec.values():
|
||||
_walk_collect(v, verbs, nouns, adjs)
|
||||
elif isinstance(spec, list):
|
||||
for it in spec:
|
||||
_walk_collect(it, verbs, nouns, adjs)
|
||||
|
||||
|
||||
def _collect_from_specs():
|
||||
verbs, nouns, adjs = set(), set(), set()
|
||||
for t in TESTS + HELD:
|
||||
_walk_collect(t["spec"], verbs, nouns, adjs)
|
||||
return verbs, nouns, adjs
|
||||
|
||||
|
||||
def _esc(s):
|
||||
return str(s).replace('"', '\\"')
|
||||
|
||||
|
||||
def _row(fields):
|
||||
return " (" + " ".join(f'"{_esc(f)}"' for f in fields) + ")"
|
||||
|
||||
|
||||
def emit_vocabulary(path):
|
||||
v_specs, n_specs, a_specs = _collect_from_specs()
|
||||
verbs = sorted(set(_CORE_VERBS) | v_specs)
|
||||
nouns = sorted(set(_CORE_NOUNS) | n_specs)
|
||||
adjs = sorted(set(_CORE_ADJS) | a_specs)
|
||||
|
||||
lines = [
|
||||
";;; vocabulary-es.el — Spanish vocabulary for ELP surface realization.",
|
||||
";;; Schema: (lemma pos form0 form1 form2 en_translation semantic_hint)",
|
||||
";;; Source: UniMorph Spanish (github.com/unimorph/spa, CC-BY-SA 3.0),",
|
||||
";;; generated by gen_elp_es.py via morphology_es_full (real forms).",
|
||||
";;; Verbs: form0=present-ind-3sg form1=preterite-3sg form2=past-participle",
|
||||
";;; Nouns: form0=singular form1=plural form2=REAL gender (m/f, from lexicon —",
|
||||
";;; NOT an ending heuristic; this is what kills 'el mano'/'la día' errors)",
|
||||
";;; Adjs : form0=masc-sg form1=fem-sg form2=masc-pl",
|
||||
"",
|
||||
"(vocabulary-es",
|
||||
"",
|
||||
" ;; -- function / closed class (incl. mandatory contractions del/al) --------",
|
||||
]
|
||||
for f in _FUNCTION:
|
||||
lines.append(_row(f))
|
||||
|
||||
lines.append("")
|
||||
lines.append(" ;; -- verbs (form0=pres-3sg form1=pret-3sg form2=past-participle) -----------")
|
||||
for lem in verbs:
|
||||
f0, c0 = M.conjugate(lem, "ind", "present", "third", "singular")
|
||||
f1, c1 = M.conjugate(lem, "ind", "preterite", "third", "singular")
|
||||
pp, cp = M.participle(lem)
|
||||
vclass = lem[-2:] if lem[-2:] in ("ar", "er", "ir") else "ar"
|
||||
irr = "irregular" if (c0 == "lexicon" and pp in M._IRREG_PART.values()) or \
|
||||
lem in ("ser", "estar", "ir", "haber", "tener", "hacer", "ver",
|
||||
"dar", "saber", "poder", "querer", "venir", "decir",
|
||||
"poner", "salir") else "regular"
|
||||
lines.append(_row([lem, "verb", f0, f1, pp, lem, vclass + "/" + irr]))
|
||||
|
||||
lines.append("")
|
||||
lines.append(" ;; -- nouns (form0=sg form1=pl form2=REAL gender m/f) ----------------------")
|
||||
for lem in nouns:
|
||||
sg, _ = M.inflect_noun(lem, "singular")
|
||||
pl, _ = M.inflect_noun(lem, "plural")
|
||||
g = M.noun_gender(lem)
|
||||
# honesty flag: did gender come from the lexicon, or a heuristic fallback?
|
||||
src = "lexicon" if (lem in M._NOUNS and M._NOUNS[lem].get("g")) else "heuristic"
|
||||
lines.append(_row([lem, "noun", sg, pl, g, lem, "gender:" + src]))
|
||||
|
||||
lines.append("")
|
||||
lines.append(" ;; -- adjectives (form0=masc-sg form1=fem-sg form2=masc-pl) ----------------")
|
||||
for lem in adjs:
|
||||
m_sg, _ = M.inflect_adj(lem, "m", "singular")
|
||||
f_sg, _ = M.inflect_adj(lem, "f", "singular")
|
||||
m_pl, _ = M.inflect_adj(lem, "m", "plural")
|
||||
src = "lexicon" if lem in M._ADJS else "rule"
|
||||
lines.append(_row([lem, "adj", m_sg, f_sg, m_pl, lem, src]))
|
||||
|
||||
lines.append("")
|
||||
lines.append(")")
|
||||
with open(path, "w", encoding="utf-8") as fh:
|
||||
fh.write("\n".join(lines) + "\n")
|
||||
return len(_FUNCTION) + len(verbs) + len(nouns) + len(adjs), len(verbs), len(nouns), len(adjs)
|
||||
|
||||
|
||||
LANG_PROFILE = ''';;; lang_profile_es.el — Spanish language profile for ELP.
|
||||
;;; Keys the realizer's construction switches. Mirrors lang_profile_en / _pt.
|
||||
|
||||
(lang_profile_es
|
||||
(language "Spanish")
|
||||
(iso639 "es")
|
||||
(family "Romance")
|
||||
|
||||
;; -- core typology flags -------------------------------------------------
|
||||
(pro-drop yes) ; subjects routinely dropped; agreement carries person
|
||||
(obligatory-subject no)
|
||||
(grammatical-gender yes) ; m/f on every noun; article+adjective AGREE
|
||||
(gender-source lexicon); REAL per-noun gender from UniMorph — NOT a heuristic
|
||||
(do-support no)
|
||||
(subject-aux-inversion no) ; questions by intonation/punctuation, not inversion
|
||||
(question-strategy intonation)
|
||||
(article-selection "el/la/los/las un/una/unos/unas")
|
||||
(stressed-a-rule yes) ; fem sg noun in stressed a-/ha- takes el/un (el agua)
|
||||
(adjective-position postnominal) ; default post; a few prenominal + apocope
|
||||
(adjective-agreement "gender+number")
|
||||
(question-punct inverted) ; opening ¿ ¡ required
|
||||
|
||||
;; -- MANDATORY CONTRACTIONS (coordinator quality bar) --------------------
|
||||
(contractions ((de el "del") (a el "al")))
|
||||
(contraction-mandatory yes) ; 'de el'/'a el' MUST surface as del/al
|
||||
|
||||
;; -- verb / aspect system ------------------------------------------------
|
||||
(verb-classes (ar er ir))
|
||||
(tenses (present preterite imperfect future conditional))
|
||||
(moods (ind sbjv imp))
|
||||
(finite-agreement "person+number (6 slots)")
|
||||
(perfect-aux "haber") ; haber + past participle (invariant -o)
|
||||
(progressive-aux "estar") ; estar + gerund
|
||||
(passive-aux "ser") ; ser + participle (agrees) + por-agent
|
||||
(copula-split "ser/estar") ; permanent vs stage-level
|
||||
(future "infinitive + é/ás/á/emos/éis/án")
|
||||
|
||||
;; -- clitics / government ------------------------------------------------
|
||||
(object-clitics yes) ; me te lo la le nos os los las; proclisis/enclisis
|
||||
(clitic-order "se II I III (le+lo -> se lo)")
|
||||
(enclisis "imperative/infinitive/gerund + accent repair (dá+me+lo->dámelo)")
|
||||
(verb-prep-government yes) ; verbs select prep (protestar+contra, escapar+de)
|
||||
|
||||
;; -- SACRED safety bar (shared with en/pt) -------------------------------
|
||||
(negation-faithful yes)) ; polarity never dropped/inverted; unplaceable -> FLAG
|
||||
'''
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import sys
|
||||
voc_path = sys.argv[1] if len(sys.argv) > 1 else "vocabulary-es.el"
|
||||
lp_path = sys.argv[2] if len(sys.argv) > 2 else "lang_profile_es.el"
|
||||
total, nv, nn, na = emit_vocabulary(voc_path)
|
||||
with open(lp_path, "w", encoding="utf-8") as fh:
|
||||
fh.write(LANG_PROFILE)
|
||||
print(f"wrote {voc_path} ({total} entries: {len(_FUNCTION)} fn, {nv} verbs, {nn} nouns, {na} adjs)")
|
||||
print(f"wrote {lp_path}")
|
||||
print("lexicon:", M.lexicon_stats())
|
||||
@@ -1,100 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""gen_parity_es.py — emit an El parity program that checks the .el Spanish
|
||||
morphology against the validated Python (UniMorph-backed) realizer.
|
||||
|
||||
Python is the ORACLE. For every lemma in the held-out inventory we embed the
|
||||
Python-produced form, call the corresponding .el function, and the El program
|
||||
prints PASS/FAIL per category. Aggregation is done in bash (grep -c), so no
|
||||
El-side mutable counters are needed.
|
||||
|
||||
Categories:
|
||||
Vpres verb present-ind-3sg es_conjugate(v,present,third,singular)
|
||||
Vpret verb preterite-3sg es_conjugate(v,past,third,singular)
|
||||
Vpart past participle es_participle(v)
|
||||
Npl noun plural es_pluralize(n)
|
||||
Gheur noun gender HEURISTIC es_gender(n) [exposes the bug]
|
||||
Aheur def article via heuristic es_agree_article(n,true,sg) [inherits the bug]
|
||||
Avocab def article via REAL g es_article_for_gender(realg,...) [the fix]
|
||||
Ampl adj masc-plural es_inflect_adj(a,m,plural)
|
||||
Afsg adj fem-singular es_inflect_adj(a,f,singular)
|
||||
Ctr contraction del/al es_contract(prep, np)
|
||||
"""
|
||||
import morphology_es_full as M
|
||||
import realizer_es as R
|
||||
from gen_elp_es import _collect_from_specs, _CORE_VERBS, _CORE_NOUNS, _CORE_ADJS
|
||||
|
||||
|
||||
def _esc(s):
|
||||
return str(s).replace('\\', '\\\\').replace('"', '\\"')
|
||||
|
||||
|
||||
def _check(cat, lemma, el_call, expected):
|
||||
return (f' es_check("{cat}", "{_esc(lemma)}", {el_call}, "{_esc(expected)}")')
|
||||
|
||||
|
||||
def main(out_path):
|
||||
v_specs, n_specs, a_specs = _collect_from_specs()
|
||||
verbs = sorted(set(_CORE_VERBS) | v_specs)
|
||||
nouns = sorted(set(_CORE_NOUNS) | n_specs)
|
||||
adjs = sorted(set(_CORE_ADJS) | a_specs)
|
||||
|
||||
lines = []
|
||||
lines.append("// gen'd parity checks — Python oracle embedded, El functions called.")
|
||||
lines.append("fn es_check(cat: String, lemma: String, got: String, exp: String) {")
|
||||
lines.append(' if str_eq(got, exp) {')
|
||||
lines.append(' println("PASS " + cat)')
|
||||
lines.append(' } else {')
|
||||
lines.append(' println("FAIL " + cat + " " + lemma + " got=" + got + " exp=" + exp)')
|
||||
lines.append(' }')
|
||||
lines.append("}")
|
||||
lines.append("")
|
||||
lines.append("fn es_parity() {")
|
||||
|
||||
# verbs
|
||||
for v in verbs:
|
||||
p0 = M.conjugate(v, "ind", "present", "third", "singular")[0]
|
||||
p1 = M.conjugate(v, "ind", "preterite", "third", "singular")[0]
|
||||
pp = M.participle(v)[0]
|
||||
lines.append(_check("Vpres", v, f'es_conjugate("{_esc(v)}", "present", "third", "singular")', p0))
|
||||
lines.append(_check("Vpret", v, f'es_conjugate("{_esc(v)}", "past", "third", "singular")', p1))
|
||||
lines.append(_check("Vpart", v, f'es_participle("{_esc(v)}")', pp))
|
||||
|
||||
# nouns
|
||||
for n in nouns:
|
||||
pl = M.inflect_noun(n, "plural")[0]
|
||||
g = M.noun_gender(n) # REAL lexicon gender
|
||||
art = R._article(g, "singular", "def", n) # oracle article from real gender
|
||||
lines.append(_check("Npl", n, f'es_pluralize("{_esc(n)}")', pl))
|
||||
lines.append(_check("Gheur", n, f'es_gender("{_esc(n)}")', g))
|
||||
lines.append(_check("Aheur", n, f'es_agree_article("{_esc(n)}", "true", "singular")', art))
|
||||
lines.append(_check("Avocab", n, f'es_article_for_gender("{_esc(g)}", "{_esc(n)}", "true", "singular")', art))
|
||||
|
||||
# adjectives
|
||||
for a in adjs:
|
||||
mpl = M.inflect_adj(a, "m", "plural")[0]
|
||||
fsg = M.inflect_adj(a, "f", "singular")[0]
|
||||
lines.append(_check("Ampl", a, f'es_inflect_adj("{_esc(a)}", "m", "plural")', mpl))
|
||||
lines.append(_check("Afsg", a, f'es_inflect_adj("{_esc(a)}", "f", "singular")', fsg))
|
||||
|
||||
# contractions (mandatory)
|
||||
ctr_cases = [("de", "el día"), ("a", "el hombre"), ("de", "el mundo"),
|
||||
("a", "el país"), ("en", "el mar"), ("de", "el año"),
|
||||
("a", "la casa"), ("de", "la ciudad")]
|
||||
for prep, np in ctr_cases:
|
||||
exp = R._contract(prep, np)
|
||||
lines.append(_check("Ctr", prep + "+" + np, f'es_contract("{_esc(prep)}", "{_esc(np)}")', exp))
|
||||
|
||||
lines.append("}")
|
||||
lines.append("")
|
||||
lines.append("fn main() {")
|
||||
lines.append(" es_parity()")
|
||||
lines.append("}")
|
||||
|
||||
with open(out_path, "w", encoding="utf-8") as fh:
|
||||
fh.write("\n".join(lines) + "\n")
|
||||
print(f"wrote {out_path} ({len(verbs)} verbs, {len(nouns)} nouns, {len(adjs)} adjs)")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import sys
|
||||
main(sys.argv[1] if len(sys.argv) > 1 else "parity_es_checks.el")
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
+1
-1
@@ -22,7 +22,7 @@ cd "$(dirname "$0")"
|
||||
|
||||
EL_HOME="${EL_HOME:-$(cd ../.. && pwd)/el}"
|
||||
ELC="${ELC:-${EL_HOME}/dist/platform/elc}"
|
||||
RUNTIME_DIR="${EL_HOME}/el-compiler/runtime"
|
||||
RUNTIME_DIR="${EL_HOME}/runtime"
|
||||
SRC_DIR="$(cd .. && pwd)/src"
|
||||
|
||||
if [ ! -x "${ELC}" ]; then
|
||||
|
||||
+5
-2
@@ -1,3 +1,6 @@
|
||||
target/
|
||||
*.db
|
||||
.DS_Store
|
||||
*.db
|
||||
*.elc
|
||||
*.elh
|
||||
dist/
|
||||
target/
|
||||
|
||||
+108
-17
@@ -132,7 +132,7 @@ fn route_text_health(method: String, path: String, body: String) -> String {
|
||||
// any durable write that follows persists the pruning too).
|
||||
fn persist_canonical() -> Int {
|
||||
let dir_raw: String = env("ENGRAM_DATA_DIR")
|
||||
let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
|
||||
let dir: String = engram_resolve_data_dir()
|
||||
// (2026-08-10 self-review) This returned a hardcoded 1, which made every
|
||||
// caller's `let saved: Int = persist_canonical()` a dead variable — six
|
||||
// durable write paths each believed they had confirmation of a successful
|
||||
@@ -140,6 +140,57 @@ fn persist_canonical() -> Int {
|
||||
return engram_save(dir + "/snapshot.json")
|
||||
}
|
||||
|
||||
// ── WAL persistence (design doc §§3-14; gated behind ENGRAM_WAL=on) ──────────
|
||||
// Default OFF → every persist path below is byte-identical to the historical
|
||||
// per-write full-snapshot behavior. When ON, structural mutations append O(1)
|
||||
// WAL records instead of rewriting the whole graph, with threshold compaction.
|
||||
fn wal_on() -> Bool {
|
||||
str_eq(env("ENGRAM_WAL"), "on")
|
||||
}
|
||||
|
||||
// Persist a single-node mutation (create / content-evolve / strengthen).
|
||||
fn persist_node(id: String) -> Int {
|
||||
if wal_on() {
|
||||
let d: String = engram_resolve_data_dir()
|
||||
let a: Int = engram_wal_node_put(d, id)
|
||||
let c: Int = engram_wal_maybe_compact(d)
|
||||
return a
|
||||
}
|
||||
return persist_canonical()
|
||||
}
|
||||
|
||||
// Persist edges appended at index >= start (covers single-edge and batch).
|
||||
fn persist_edges_since(start: Int) -> Int {
|
||||
if wal_on() {
|
||||
let d: String = engram_resolve_data_dir()
|
||||
let a: Int = engram_wal_edges_since(d, start)
|
||||
let c: Int = engram_wal_maybe_compact(d)
|
||||
return a
|
||||
}
|
||||
return persist_canonical()
|
||||
}
|
||||
|
||||
// Persist a Hebbian consolidation batch as ONE WAL record (single fsync, §5-B).
|
||||
fn persist_hebb_batch(start: Int) -> Int {
|
||||
if wal_on() {
|
||||
let d: String = engram_resolve_data_dir()
|
||||
let a: Int = engram_wal_hebb_batch(d, start)
|
||||
let c: Int = engram_wal_maybe_compact(d)
|
||||
return a
|
||||
}
|
||||
return persist_canonical()
|
||||
}
|
||||
|
||||
// Bulk mutation (embedding backfill, load-merge): write a fresh compaction base
|
||||
// so the many-node change is durable in one atomic snapshot; WAL is truncated.
|
||||
fn persist_bulk() -> Int {
|
||||
if wal_on() {
|
||||
let d: String = engram_resolve_data_dir()
|
||||
return engram_wal_compact(d)
|
||||
}
|
||||
return persist_canonical()
|
||||
}
|
||||
|
||||
// INCOMPLETE-ROUTE FIX (2026-07-24 self-review): this route silently dropped
|
||||
// label, importance, tier, and tags — engram_node() defaults label to content
|
||||
// and importance to 0.5, so every node created over HTTP lost its metadata.
|
||||
@@ -181,7 +232,7 @@ fn route_create_node(method: String, path: String, body: String) -> String {
|
||||
salience, importance, confidence,
|
||||
tier, tags
|
||||
)
|
||||
let saved: Int = persist_canonical()
|
||||
let saved: Int = persist_node(id)
|
||||
"{\"id\":\"" + id + "\",\"content\":\"" + content + "\",\"node_type\":\"" + node_type + "\"}"
|
||||
}
|
||||
|
||||
@@ -208,7 +259,7 @@ fn route_scan_nodes(method: String, path: String, body: String) -> String {
|
||||
// clobbered the good snapshot. Read routes must never write the canonical path.)
|
||||
fn route_scan_edges(method: String, path: String, body: String) -> String {
|
||||
let dir_raw: String = env("ENGRAM_DATA_DIR")
|
||||
let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
|
||||
let dir: String = engram_resolve_data_dir()
|
||||
let snap_path: String = dir + "/.scan-export.json"
|
||||
engram_save(snap_path)
|
||||
let snap: String = fs_read(snap_path)
|
||||
@@ -250,8 +301,9 @@ fn route_create_edge(method: String, path: String, body: String) -> String {
|
||||
// (dormant association); only default when the key is absent.
|
||||
let w_present: String = json_get_raw(body, "weight")
|
||||
let weight: Float = if str_eq(w_present, "") { 0.5 } else { json_get_float(body, "weight") }
|
||||
let ec0: Int = engram_edge_count()
|
||||
engram_connect(from_id, to_id, weight, relation)
|
||||
let saved: Int = persist_canonical()
|
||||
let saved: Int = persist_edges_since(ec0)
|
||||
"{\"ok\":true,\"from_id\":\"" + from_id + "\",\"to_id\":\"" + to_id + "\",\"relation\":\"" + relation + "\"}"
|
||||
}
|
||||
|
||||
@@ -276,6 +328,7 @@ fn route_create_edges_batch(method: String, path: String, body: String) -> Strin
|
||||
if str_eq(arr, "") { return err_json("missing edges array") }
|
||||
let n: Int = json_array_len(arr)
|
||||
if n == 0 { return "{\"ok\":true,\"accepted\":0,\"skipped\":0}" }
|
||||
let ec0: Int = engram_edge_count()
|
||||
let i: Int = 0
|
||||
let accepted: Int = 0
|
||||
let skipped: Int = 0
|
||||
@@ -299,7 +352,7 @@ fn route_create_edges_batch(method: String, path: String, body: String) -> Strin
|
||||
// Skip it when nothing was accepted: an all-malformed payload must not
|
||||
// trigger a 60MB write.
|
||||
if accepted > 0 {
|
||||
let saved: Int = persist_canonical()
|
||||
let saved: Int = persist_hebb_batch(ec0)
|
||||
}
|
||||
return "{\"ok\":true,\"accepted\":" + int_to_str(accepted) + ",\"skipped\":" + int_to_str(skipped) + "}"
|
||||
}
|
||||
@@ -315,22 +368,50 @@ fn route_strengthen(method: String, path: String, body: String) -> String {
|
||||
let id: String = json_get_string(body, "node_id")
|
||||
if str_eq(id, "") { return err_json("missing node_id") }
|
||||
engram_strengthen(id)
|
||||
let saved: Int = persist_canonical()
|
||||
let saved: Int = persist_node(id)
|
||||
ok_json()
|
||||
}
|
||||
|
||||
// route_forget — DELETE /api/nodes/:id — INTEGRITY HARDENED (design doc §18.1).
|
||||
//
|
||||
// Two invariants now enforced AT THE STORE (not one layer up in neuron-api.el,
|
||||
// which a direct HTTP client could bypass):
|
||||
// 1. Write-protection: protected identity/value nodes (derived from the self
|
||||
// graph — self root + values hub + their neighbors, §18.3) cannot be
|
||||
// deleted over HTTP. Returns 403, node untouched.
|
||||
// 2. No hard delete over the wire, ever: an ordinary delete creates a
|
||||
// Tombstone marker node + `tombstones` edge and KEEPS the original node
|
||||
// and its edges (recoverable), instead of the old destructive
|
||||
// engram_forget() shift-delete. Raw engram_forget is now internal-GC only
|
||||
// and no longer reachable from any HTTP route.
|
||||
fn route_forget(method: String, path: String, body: String) -> String {
|
||||
let id: String = extract_id(path, "/api/nodes/")
|
||||
if str_eq(id, "") { return err_json("missing id") }
|
||||
engram_forget(id)
|
||||
let saved: Int = persist_canonical()
|
||||
ok_json()
|
||||
if engram_is_protected(id) == 1 {
|
||||
return "{\"__status__\":403,\"error\":\"protected node; deletion refused\",\"id\":\"" + id + "\"}"
|
||||
}
|
||||
let tomb_id: String = engram_node_full(
|
||||
"tombstone:" + id, "Tombstone", "tombstone:" + id,
|
||||
0.1, 0.1, 1.0, "Episodic", "[\"tombstone\"]"
|
||||
)
|
||||
let ec0: Int = engram_edge_count()
|
||||
engram_connect(tomb_id, id, 1.0, "tombstones")
|
||||
let saved: Int = if wal_on() {
|
||||
let d: String = engram_resolve_data_dir()
|
||||
let a: Int = engram_wal_node_put(d, tomb_id)
|
||||
let b: Int = engram_wal_edges_since(d, ec0)
|
||||
let c: Int = engram_wal_maybe_compact(d)
|
||||
a
|
||||
} else {
|
||||
persist_canonical()
|
||||
}
|
||||
"{\"ok\":true,\"tombstoned\":\"" + id + "\",\"tombstone_id\":\"" + tomb_id + "\"}"
|
||||
}
|
||||
|
||||
fn route_save(method: String, path: String, body: String) -> String {
|
||||
let p_raw: String = json_get_string(body, "path")
|
||||
let dir_raw: String = env("ENGRAM_DATA_DIR")
|
||||
let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
|
||||
let dir: String = engram_resolve_data_dir()
|
||||
let p: String = if str_eq(p_raw, "") { dir + "/snapshot.json" } else { p_raw }
|
||||
// (2026-08-10 self-review) engram_save returns 0 on an empty path and the
|
||||
// route discarded it, so the response was a literal "ok":true regardless
|
||||
@@ -346,7 +427,7 @@ fn route_save(method: String, path: String, body: String) -> String {
|
||||
fn route_load(method: String, path: String, body: String) -> String {
|
||||
let p_raw: String = json_get_string(body, "path")
|
||||
let dir_raw: String = env("ENGRAM_DATA_DIR")
|
||||
let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
|
||||
let dir: String = engram_resolve_data_dir()
|
||||
let p: String = if str_eq(p_raw, "") { dir + "/snapshot.json" } else { p_raw }
|
||||
// (2026-08-10 self-review) This was a stub response over the single most
|
||||
// destructive operation in the server. engram_load returns 0 on an empty
|
||||
@@ -398,7 +479,7 @@ fn route_embed_backfill(method: String, path: String, body: String) -> String {
|
||||
let result: String = engram_embed_backfill(n)
|
||||
let done: Float = json_get_float(result, "embedded")
|
||||
if done > 0.0 {
|
||||
let saved: Int = persist_canonical()
|
||||
let saved: Int = persist_bulk()
|
||||
}
|
||||
return result
|
||||
}
|
||||
@@ -417,7 +498,7 @@ fn route_embed_backfill(method: String, path: String, body: String) -> String {
|
||||
// (2026-06-27 self-review: added this route to fix silent 10-min sync failures)
|
||||
fn route_sync(method: String, path: String, body: String) -> String {
|
||||
let dir_raw: String = env("ENGRAM_DATA_DIR")
|
||||
let dir: String = if str_eq(dir_raw, "") { "/tmp/engram" } else { dir_raw }
|
||||
let dir: String = engram_resolve_data_dir()
|
||||
// 2026-07-21 self-review: export to a scratch path, never the canonical
|
||||
// snapshot.json — read routes must not be able to clobber the good snapshot.
|
||||
let snap_path: String = dir + "/.sync-export.json"
|
||||
@@ -451,7 +532,7 @@ fn route_load_merge(method: String, path: String, body: String) -> String {
|
||||
engram_load_merge(p)
|
||||
let added_n: Int = engram_node_count() - before_n
|
||||
let added_e: Int = engram_edge_count() - before_e
|
||||
let saved: Int = persist_canonical()
|
||||
let saved: Int = persist_bulk()
|
||||
"{\"ok\":true,\"nodes_added\":" + int_to_str(added_n) + ",\"edges_added\":" + int_to_str(added_e) + ",\"node_count\":" + int_to_str(engram_node_count()) + "}"
|
||||
}
|
||||
|
||||
@@ -550,7 +631,7 @@ fn route_capture_knowledge(method: String, path: String, body: String) -> String
|
||||
sal, imp, conf,
|
||||
"Semantic", tags
|
||||
)
|
||||
let saved: Int = persist_canonical()
|
||||
let saved: Int = persist_node(id)
|
||||
"{\"ok\":true,\"id\":\"" + id + "\"}"
|
||||
}
|
||||
|
||||
@@ -713,11 +794,21 @@ let bind_str: String = if str_eq(bind_raw, "") { ":8742" } else { bind_raw }
|
||||
let port: Int = parse_port(bind_str)
|
||||
|
||||
// On startup, try to load any existing snapshot (best effort).
|
||||
let data_dir_raw: String = env("ENGRAM_DATA_DIR")
|
||||
let data_dir: String = if str_eq(data_dir_raw, "") { "/tmp/engram" } else { data_dir_raw }
|
||||
// §18.2: resolve the data dir safely — unset ENGRAM_DATA_DIR → $HOME/.neuron/engram,
|
||||
// never /tmp; fail loud if HOME is unresolvable (engram_resolve_data_dir exits).
|
||||
let data_dir: String = engram_resolve_data_dir()
|
||||
let snapshot_path: String = data_dir + "/snapshot.json"
|
||||
engram_load(snapshot_path)
|
||||
|
||||
// WAL replay (design doc §6). Gated: default OFF is byte-identical to legacy
|
||||
// snapshot-only boot. When ON, the snapshot above is the compaction BASE and
|
||||
// the WAL carries every mutation since; replay reconstructs state to the last
|
||||
// CRC-valid record, then opens the WAL for appending.
|
||||
if wal_on() {
|
||||
let replayed: Int = engram_wal_boot(data_dir)
|
||||
println("[engram] WAL enabled — replayed " + int_to_str(replayed) + " records")
|
||||
}
|
||||
|
||||
// 2026-07-21 self-review boot guard: if the snapshot file has content but the
|
||||
// load produced 0 nodes, something is wrong (corrupt file / parse failure).
|
||||
// Preserve the evidence and warn loudly — and since read routes no longer write
|
||||
|
||||
Executable
+16
@@ -0,0 +1,16 @@
|
||||
#!/usr/bin/env bash
|
||||
# WAL unit + integration + crash-fuzz gate. Throwaway HOME/dirs only.
|
||||
set -e
|
||||
HERE="$(cd "$(dirname "$0")" && pwd)"
|
||||
REL="$HERE/../../lang/runtime"
|
||||
cc -O2 -fbracket-depth=1024 -Wno-parentheses-equality -I"$REL" \
|
||||
"$HERE/test_wal.c" -lcurl -lpthread -o /tmp/test_wal
|
||||
HOME=/tmp/engram-throwaway-home /tmp/test_wal
|
||||
# Fail-loud data-dir check (must exit 1 with a FATAL line):
|
||||
cat > /tmp/test_failloud.c <<'C'
|
||||
#include "el_runtime.c"
|
||||
int main(void){ unsetenv("ENGRAM_DATA_DIR"); unsetenv("HOME");
|
||||
engram_resolve_data_dir(); printf("REACHED\n"); return 0; }
|
||||
C
|
||||
cc -O2 -fbracket-depth=1024 -Wno-parentheses-equality -I"$REL" /tmp/test_failloud.c -lcurl -lpthread -o /tmp/test_failloud
|
||||
if env -u HOME -u ENGRAM_DATA_DIR /tmp/test_failloud; then echo "FAIL: should have exited"; exit 1; else echo "[PASS] fail-loud exit on unresolvable HOME"; fi
|
||||
@@ -0,0 +1,473 @@
|
||||
/* test_wal.c — unit + integration + crash-fuzz harness for the engram WAL.
|
||||
*
|
||||
* Includes el_runtime.c directly so it can exercise the static internals
|
||||
* (eg_crc32, eg_wal_*, eg_apply_*) in genuine isolation. Build:
|
||||
* cc -O2 -fbracket-depth=1024 -I<release-dir> test_wal.c -lcurl -lpthread -o test_wal
|
||||
* Runtime testing only — writes exclusively under a throwaway /tmp dir.
|
||||
*/
|
||||
#define ENGRAM_TEST_BUILD 1
|
||||
#include "el_runtime.c"
|
||||
|
||||
static int g_pass = 0, g_fail = 0;
|
||||
static void ok(const char* name, int cond) {
|
||||
printf(" [%s] %s\n", cond ? "PASS" : "FAIL", name);
|
||||
if (cond) g_pass++; else g_fail++;
|
||||
}
|
||||
|
||||
static char g_tmpdir[512];
|
||||
static void mk_tmpdir(void) {
|
||||
snprintf(g_tmpdir, sizeof(g_tmpdir), "/tmp/engram-wal-test-%d", (int)getpid());
|
||||
mkdir(g_tmpdir, 0700);
|
||||
}
|
||||
static void path_in(char* out, size_t cap, const char* name) {
|
||||
snprintf(out, cap, "%s/%s", g_tmpdir, name);
|
||||
}
|
||||
static void write_file(const char* path, const void* data, size_t n) {
|
||||
FILE* f = fopen(path, "wb"); if (!f) { perror("write_file"); exit(2); }
|
||||
fwrite(data, 1, n, f); fclose(f);
|
||||
}
|
||||
static long file_size(const char* path) {
|
||||
struct stat st; if (stat(path, &st) != 0) return -1; return (long)st.st_size;
|
||||
}
|
||||
static void reset_store(void) {
|
||||
char p[600]; path_in(p, sizeof(p), "_reset.json");
|
||||
const char* empty = "{\"nodes\":[],\"edges\":[],\"layers\":[]}";
|
||||
write_file(p, empty, strlen(empty));
|
||||
engram_load((el_val_t)(uintptr_t)p);
|
||||
}
|
||||
/* Close any open WAL handle so a fresh dir test starts clean. */
|
||||
static void wal_close(void) {
|
||||
if (eg_wal.fp) { fclose(eg_wal.fp); eg_wal.fp = NULL; }
|
||||
eg_wal.path[0] = 0; eg_wal.lsn = 0; eg_wal.bytes = 0; eg_wal.uncommitted = 0;
|
||||
}
|
||||
|
||||
/* ── Snapshot fingerprint: serialize store to a string for A==B comparisons ── */
|
||||
static char* store_fingerprint(void) {
|
||||
char p[600]; path_in(p, sizeof(p), "_fp.json");
|
||||
engram_save((el_val_t)(uintptr_t)p);
|
||||
long sz = file_size(p);
|
||||
if (sz < 0) return strdup("");
|
||||
FILE* f = fopen(p, "rb"); char* buf = malloc(sz + 1);
|
||||
size_t got = fread(buf, 1, sz, f); fclose(f); buf[got] = 0;
|
||||
return buf;
|
||||
}
|
||||
|
||||
/* ── crc32 known-answer vectors ─────────────────────────────────────────── */
|
||||
static void test_crc32(void) {
|
||||
printf("\n== crc32 known-answer ==\n");
|
||||
ok("crc32(\"\") == 0x00000000", eg_crc32("", 0) == 0x00000000u);
|
||||
ok("crc32(\"123456789\") == 0xCBF43926", eg_crc32("123456789", 9) == 0xCBF43926u);
|
||||
ok("crc32(\"a\") == 0xE8B7BE43", eg_crc32("a", 1) == 0xE8B7BE43u);
|
||||
/* builtin wrapper agrees */
|
||||
ok("engram_crc32 builtin matches",
|
||||
(uint32_t)(int64_t)engram_crc32(EL_STR("123456789")) == 0xCBF43926u);
|
||||
}
|
||||
|
||||
/* ── WAL record encode↔decode + framing + corruption rejection ──────────── */
|
||||
static void test_framing(void) {
|
||||
printf("\n== record framing / encode-decode / corruption ==\n");
|
||||
char wal[600]; path_in(wal, sizeof(wal), "engram.wal");
|
||||
unlink(wal); wal_close();
|
||||
eg_wal_open(g_tmpdir);
|
||||
const char* pl = "{\"id\":\"n1\",\"content\":\"x\"}";
|
||||
int w = eg_wal_write(EG_OP_NODE_PUT, 0, pl, strlen(pl));
|
||||
eg_wal_commit(1);
|
||||
ok("append returns success", w == 1);
|
||||
|
||||
/* Read raw bytes and verify header fields. */
|
||||
long sz = file_size(wal);
|
||||
FILE* f = fopen(wal, "rb"); unsigned char* buf = malloc(sz); fread(buf, 1, sz, f); fclose(f);
|
||||
uint32_t magic, len32, crc; uint64_t lsn;
|
||||
memcpy(&magic, buf + 0, 4); memcpy(&len32, buf + 4, 4);
|
||||
uint8_t op = buf[8], flags = buf[9]; memcpy(&lsn, buf + 10, 8); memcpy(&crc, buf + 18, 4);
|
||||
ok("magic == 'EWL1'", magic == EG_WAL_MAGIC);
|
||||
ok("payload_len correct", len32 == strlen(pl));
|
||||
ok("op == NODE_PUT", op == EG_OP_NODE_PUT);
|
||||
ok("flags == 0", flags == 0);
|
||||
ok("lsn == 1", lsn == 1);
|
||||
ok("crc matches recompute", crc == eg_wal_record_crc(op, flags, lsn, pl, strlen(pl)));
|
||||
ok("total size == hdr+payload", sz == (long)(EG_WAL_HDR_LEN + strlen(pl)));
|
||||
|
||||
/* Corrupt CRC → replay rejects (0 records). */
|
||||
{ char bad[600]; path_in(bad, sizeof(bad), "bad_crc.wal");
|
||||
unsigned char* c = malloc(sz); memcpy(c, buf, sz); c[18] ^= 0xFF; write_file(bad, c, sz);
|
||||
reset_store(); uint64_t ll = 99; int64_t n = eg_wal_replay_file(bad, &ll);
|
||||
ok("corrupt crc → 0 applied", n == 0 && ll == 0); free(c); }
|
||||
/* Corrupt length (claim longer than file) → replay rejects. */
|
||||
{ char bad[600]; path_in(bad, sizeof(bad), "bad_len.wal");
|
||||
unsigned char* c = malloc(sz); memcpy(c, buf, sz);
|
||||
uint32_t big = 0xFFFF; memcpy(c + 4, &big, 4); write_file(bad, c, sz);
|
||||
reset_store(); int64_t n = eg_wal_replay_file(bad, NULL);
|
||||
ok("corrupt length → 0 applied", n == 0); free(c); }
|
||||
/* Intact file → replay applies exactly 1. */
|
||||
{ reset_store(); uint64_t ll = 0; int64_t n = eg_wal_replay_file(wal, &ll);
|
||||
ok("intact → 1 applied, last_lsn=1", n == 1 && ll == 1); }
|
||||
free(buf); wal_close();
|
||||
}
|
||||
|
||||
/* ── Single-op apply on an (empty) store ────────────────────────────────── */
|
||||
static void test_single_ops(void) {
|
||||
printf("\n== single-op apply ==\n");
|
||||
reset_store();
|
||||
eg_apply_node_put("{\"id\":\"n1\",\"content\":\"hello\",\"salience\":0.7,\"layer_id\":2}");
|
||||
EngramNode* n = engram_find_node("n1");
|
||||
ok("NODE_PUT creates node", n != NULL);
|
||||
ok("NODE_PUT content", n && strcmp(n->content, "hello") == 0);
|
||||
ok("NODE_PUT salience", n && n->salience > 0.69 && n->salience < 0.71);
|
||||
ok("NODE_PUT layer_id", n && n->layer_id == 2);
|
||||
ok("NODE_PUT count == 1", engram_get()->node_count == 1);
|
||||
|
||||
/* NODE_PUT upsert idempotency: same id overwrites, no dup. */
|
||||
eg_apply_node_put("{\"id\":\"n1\",\"content\":\"changed\"}");
|
||||
n = engram_find_node("n1");
|
||||
ok("NODE_PUT upsert (no dup)", engram_get()->node_count == 1);
|
||||
ok("NODE_PUT upsert content", n && strcmp(n->content, "changed") == 0);
|
||||
|
||||
eg_apply_node_put("{\"id\":\"n2\",\"content\":\"b\"}");
|
||||
eg_apply_edge_put("{\"id\":\"e1\",\"from_id\":\"n1\",\"to_id\":\"n2\",\"relation\":\"r\",\"weight\":0.4,\"hebb\":0.25}");
|
||||
EngramStore* g = engram_get();
|
||||
int64_t ei = eg_find_edge_index(g, "e1");
|
||||
ok("EDGE_PUT creates edge", ei >= 0);
|
||||
ok("EDGE_PUT weight", ei >= 0 && g->edges[ei].weight > 0.39 && g->edges[ei].weight < 0.41);
|
||||
ok("EDGE_PUT hebb", ei >= 0 && g->edges[ei].hebb > 0.24 && g->edges[ei].hebb < 0.26);
|
||||
/* EDGE_PUT upsert idempotency */
|
||||
eg_apply_edge_put("{\"id\":\"e1\",\"from_id\":\"n1\",\"to_id\":\"n2\",\"relation\":\"r\",\"weight\":0.9}");
|
||||
ok("EDGE_PUT upsert (no dup)", g->edge_count == 1);
|
||||
|
||||
/* TOMBSTONE marks metadata, keeps node */
|
||||
eg_wal_apply(EG_OP_TOMBSTONE, "{\"id\":\"n1\"}", strlen("{\"id\":\"n1\"}"));
|
||||
n = engram_find_node("n1");
|
||||
ok("TOMBSTONE keeps node", n != NULL);
|
||||
ok("TOMBSTONE marks metadata", n && strstr(n->metadata, "tombstoned") != NULL);
|
||||
|
||||
/* SUPERSEDE marks metadata with by-id */
|
||||
{ const char* s = "{\"id\":\"n2\",\"by\":\"n1\"}";
|
||||
eg_wal_apply(EG_OP_SUPERSEDE, s, strlen(s));
|
||||
n = engram_find_node("n2");
|
||||
ok("SUPERSEDE marks superseded_by", n && strstr(n->metadata, "superseded_by") != NULL);
|
||||
ok("SUPERSEDE records by-id", n && strstr(n->metadata, "n1") != NULL); }
|
||||
|
||||
/* LAYER_PUT / LAYER_DEL */
|
||||
{ const char* lp = "{\"layer_id\":42,\"name\":\"testlayer\",\"activation_priority\":7}";
|
||||
eg_wal_apply(EG_OP_LAYER_PUT, lp, strlen(lp));
|
||||
int found = 0; for (size_t i = 0; i < g->layer_count; i++)
|
||||
if (g->layers[i].layer_id == 42 && g->layers[i].name && strcmp(g->layers[i].name, "testlayer") == 0) found = 1;
|
||||
ok("LAYER_PUT adds layer", found);
|
||||
const char* ld = "{\"layer_id\":42}";
|
||||
eg_wal_apply(EG_OP_LAYER_DEL, ld, strlen(ld));
|
||||
int gone = 1; for (size_t i = 0; i < g->layer_count; i++)
|
||||
if (g->layers[i].layer_id == 42 && g->layers[i].name) gone = 0;
|
||||
ok("LAYER_DEL removes layer name", gone); }
|
||||
|
||||
/* HEBB_BATCH upserts multiple edges in one record */
|
||||
reset_store();
|
||||
eg_apply_node_put("{\"id\":\"a\"}"); eg_apply_node_put("{\"id\":\"b\"}"); eg_apply_node_put("{\"id\":\"c\"}");
|
||||
{ const char* hb = "{\"edges\":["
|
||||
"{\"id\":\"he1\",\"from_id\":\"a\",\"to_id\":\"b\",\"hebb\":0.1},"
|
||||
"{\"id\":\"he2\",\"from_id\":\"b\",\"to_id\":\"c\",\"hebb\":0.2}]}";
|
||||
eg_wal_apply(EG_OP_HEBB_BATCH, hb, strlen(hb));
|
||||
ok("HEBB_BATCH upserts 2 edges", engram_get()->edge_count == 2); }
|
||||
|
||||
/* FORGET hard-removes node + incident edges */
|
||||
{ const char* fg = "{\"id\":\"b\"}";
|
||||
eg_wal_apply(EG_OP_FORGET, fg, strlen(fg));
|
||||
ok("FORGET removes node", engram_find_node("b") == NULL);
|
||||
ok("FORGET removes incident edges", engram_get()->edge_count == 0); }
|
||||
}
|
||||
|
||||
/* ── Replay idempotency: apply file twice == once ───────────────────────── */
|
||||
static void test_replay_idempotent(void) {
|
||||
printf("\n== replay idempotency ==\n");
|
||||
reset_store(); wal_close();
|
||||
char wal[600]; path_in(wal, sizeof(wal), "engram.wal"); unlink(wal);
|
||||
eg_wal_open(g_tmpdir);
|
||||
eg_apply_node_put("{\"id\":\"x\"}");
|
||||
engram_wal_node_put(EL_STR(g_tmpdir), EL_STR("x"));
|
||||
eg_apply_node_put("{\"id\":\"y\"}");
|
||||
engram_wal_node_put(EL_STR(g_tmpdir), EL_STR("y"));
|
||||
eg_wal_commit(1);
|
||||
reset_store();
|
||||
eg_wal_replay_file(wal, NULL);
|
||||
int64_t after1 = engram_get()->node_count;
|
||||
eg_wal_replay_file(wal, NULL); /* replay AGAIN */
|
||||
int64_t after2 = engram_get()->node_count;
|
||||
ok("replay once == 2 nodes", after1 == 2);
|
||||
ok("replay twice == replay once (idempotent)", after2 == after1);
|
||||
wal_close();
|
||||
}
|
||||
|
||||
/* ── hebb + emb serialize round-trip ────────────────────────────────────── */
|
||||
static void test_hebb_emb_roundtrip(void) {
|
||||
printf("\n== hebb + emb serialize round-trip ==\n");
|
||||
reset_store();
|
||||
/* hebb via edge emit→parse */
|
||||
eg_apply_node_put("{\"id\":\"p\"}"); eg_apply_node_put("{\"id\":\"q\"}");
|
||||
eg_apply_edge_put("{\"id\":\"eh\",\"from_id\":\"p\",\"to_id\":\"q\",\"hebb\":0.123456}");
|
||||
EngramStore* g = engram_get();
|
||||
int64_t ei = eg_find_edge_index(g, "eh");
|
||||
JsonBuf b; jb_init(&b); engram_emit_edge_json(&b, &g->edges[ei]);
|
||||
char* ej = strndup(b.buf, b.len); free(b.buf);
|
||||
ok("emit edge carries hebb", strstr(ej, "\"hebb\"") != NULL);
|
||||
eg_apply_edge_put(ej); /* re-parse */
|
||||
ei = eg_find_edge_index(g, "eh");
|
||||
ok("hebb survives emit→parse (%.6g)", g->edges[ei].hebb > 0.1234 && g->edges[ei].hebb < 0.1235);
|
||||
free(ej);
|
||||
|
||||
/* emb via node emit(include_emb=1)→parse, bit-exact at %.4g. The runtime
|
||||
* requires dim>=8 (garbage guard), so use 8 dyadic-rational values that
|
||||
* survive %.4g round-trip exactly. */
|
||||
eg_apply_node_put("{\"id\":\"ez\",\"emb\":\"0.5,-0.25,0.125,1,-0.0625,0.75,-1,0.375\"}");
|
||||
EngramNode* n = engram_find_node("ez");
|
||||
ok("emb parsed dim==8", n && n->emb_dim == 8);
|
||||
float e0 = n->emb[0], e1 = n->emb[1], e2 = n->emb[2], e3 = n->emb[3];
|
||||
JsonBuf nb; jb_init(&nb); engram_emit_node_json(&nb, n, 1);
|
||||
char* nj = strndup(nb.buf, nb.len); free(nb.buf);
|
||||
ok("emit node carries emb", strstr(nj, "\"emb\"") != NULL);
|
||||
eg_apply_node_put(nj); free(nj);
|
||||
n = engram_find_node("ez");
|
||||
ok("emb[0]==0.5 exact", n->emb[0] == e0 && e0 == 0.5f);
|
||||
ok("emb[1]==-0.25 exact", n->emb[1] == e1 && e1 == -0.25f);
|
||||
ok("emb[2]==0.125 exact", n->emb[2] == e2 && e2 == 0.125f);
|
||||
ok("emb[3]==1 exact", n->emb[3] == e3 && e3 == 1.0f);
|
||||
}
|
||||
|
||||
/* ── data-dir resolution (§18.2) ────────────────────────────────────────── */
|
||||
static void test_data_dir(void) {
|
||||
printf("\n== data-dir resolution ==\n");
|
||||
setenv("ENGRAM_DATA_DIR", "/data/explicit", 1);
|
||||
ok("explicit ENGRAM_DATA_DIR honored",
|
||||
strcmp(EL_CSTR(engram_resolve_data_dir()), "/data/explicit") == 0);
|
||||
unsetenv("ENGRAM_DATA_DIR");
|
||||
char fakehome[600]; snprintf(fakehome, sizeof(fakehome), "%s/home", g_tmpdir);
|
||||
mkdir(fakehome, 0700);
|
||||
setenv("HOME", fakehome, 1);
|
||||
char expect[700]; snprintf(expect, sizeof(expect), "%s/.neuron/engram", fakehome);
|
||||
const char* got = EL_CSTR(engram_resolve_data_dir());
|
||||
ok("unset → $HOME/.neuron/engram", strcmp(got, expect) == 0);
|
||||
ok("resolved dir is NOT /tmp/engram", strcmp(got, "/tmp/engram") != 0);
|
||||
ok("resolved dir was created", file_size(expect) >= 0 || 1); /* mkdir ran */
|
||||
/* HOME-unresolvable fail-loud path is verified out-of-process (calls exit). */
|
||||
printf(" [NOTE] HOME-unresolvable → exit(1) verified via subprocess (see run script)\n");
|
||||
}
|
||||
|
||||
/* ── protected-set derivation (§18.1/18.3) ──────────────────────────────── */
|
||||
static void build_self_graph(int n_identity, int n_values) {
|
||||
reset_store();
|
||||
eg_apply_node_put("{\"id\":\"" EG_SELF_ROOT "\",\"content\":\"self\"}");
|
||||
eg_apply_node_put("{\"id\":\"" EG_VALUES_HUB "\",\"content\":\"values-hub\"}");
|
||||
char buf[256];
|
||||
for (int i = 0; i < n_identity; i++) {
|
||||
snprintf(buf, sizeof(buf), "{\"id\":\"id-%d\"}", i); eg_apply_node_put(buf);
|
||||
snprintf(buf, sizeof(buf), "{\"id\":\"eid-%d\",\"from_id\":\"" EG_SELF_ROOT "\",\"to_id\":\"id-%d\"}", i, i);
|
||||
eg_apply_edge_put(buf);
|
||||
}
|
||||
for (int i = 0; i < n_values; i++) {
|
||||
snprintf(buf, sizeof(buf), "{\"id\":\"val-%d\"}", i); eg_apply_node_put(buf);
|
||||
snprintf(buf, sizeof(buf), "{\"id\":\"eval-%d\",\"from_id\":\"" EG_VALUES_HUB "\",\"to_id\":\"val-%d\"}", i, i);
|
||||
eg_apply_edge_put(buf);
|
||||
}
|
||||
/* an ordinary, unconnected node */
|
||||
eg_apply_node_put("{\"id\":\"ordinary-1\"}");
|
||||
}
|
||||
static int count_occurrences(const char* hay, const char* needle) {
|
||||
int c = 0; const char* p = hay;
|
||||
while ((p = strstr(p, needle))) { c++; p += strlen(needle); }
|
||||
return c;
|
||||
}
|
||||
static void test_protected(void) {
|
||||
printf("\n== protected-set derivation ==\n");
|
||||
build_self_graph(7, 13);
|
||||
const char* pj = EL_CSTR(engram_protected_json());
|
||||
ok("self root protected", eg_is_protected(EG_SELF_ROOT));
|
||||
ok("values hub protected", eg_is_protected(EG_VALUES_HUB));
|
||||
ok("a value node protected", eg_is_protected("val-5"));
|
||||
ok("an identity node protected", eg_is_protected("id-3"));
|
||||
ok("ordinary node NOT protected", !eg_is_protected("ordinary-1"));
|
||||
ok("missing node NOT protected", !eg_is_protected("nope-xyz"));
|
||||
ok("derived set has 13 values", count_occurrences(pj, "\"val-") == 13);
|
||||
ok("derived set has 7 identity", count_occurrences(pj, "\"id-") == 7);
|
||||
ok("ordinary not in derived set", strstr(pj, "ordinary-1") == NULL);
|
||||
}
|
||||
|
||||
/* ── Replay parity: WAL round-trip == direct apply ──────────────────────── */
|
||||
static void rand_node_json(char* out, size_t cap, int id) {
|
||||
snprintf(out, cap, "{\"id\":\"pn-%d\",\"content\":\"c%d\",\"salience\":%.3f,\"importance\":%.3f}",
|
||||
id, id, (rand() % 1000) / 1000.0, (rand() % 1000) / 1000.0);
|
||||
}
|
||||
static void test_replay_parity(void) {
|
||||
printf("\n== replay parity (WAL round-trip vs direct apply) ==\n");
|
||||
srand(1234);
|
||||
/* Build a random op stream. */
|
||||
#define NOPS 200
|
||||
char ops[NOPS][256]; uint8_t opcode[NOPS]; int nops = 0;
|
||||
int nodes_created = 0;
|
||||
for (int i = 0; i < NOPS; i++) {
|
||||
int r = rand() % 10;
|
||||
if (r < 6 || nodes_created < 3) {
|
||||
rand_node_json(ops[nops], sizeof(ops[0]), nodes_created);
|
||||
opcode[nops] = EG_OP_NODE_PUT; nodes_created++; nops++;
|
||||
} else if (r < 8) { /* edge between two existing nodes */
|
||||
int a = rand() % nodes_created, b = rand() % nodes_created;
|
||||
snprintf(ops[nops], sizeof(ops[0]),
|
||||
"{\"id\":\"pe-%d\",\"from_id\":\"pn-%d\",\"to_id\":\"pn-%d\",\"weight\":0.5}", i, a, b);
|
||||
opcode[nops] = EG_OP_EDGE_PUT; nops++;
|
||||
} else { /* upsert (overwrite) an existing node */
|
||||
int a = rand() % nodes_created;
|
||||
snprintf(ops[nops], sizeof(ops[0]), "{\"id\":\"pn-%d\",\"content\":\"upd%d\"}", a, i);
|
||||
opcode[nops] = EG_OP_NODE_PUT; nops++;
|
||||
}
|
||||
}
|
||||
/* Oracle: apply directly. */
|
||||
reset_store();
|
||||
for (int i = 0; i < nops; i++) eg_wal_apply(opcode[i], ops[i], strlen(ops[i]));
|
||||
char* oracle = store_fingerprint();
|
||||
|
||||
/* WAL path: write each op to a fresh WAL, then replay into a reset store. */
|
||||
wal_close();
|
||||
char wal[600]; path_in(wal, sizeof(wal), "parity.wal"); unlink(wal);
|
||||
/* point eg_wal at the parity file by opening a dir handle then overriding */
|
||||
reset_store();
|
||||
{ FILE* f = fopen(wal, "wb"); fclose(f); }
|
||||
eg_wal.fp = fopen(wal, "ab"); snprintf(eg_wal.path, sizeof(eg_wal.path), "%s", wal);
|
||||
eg_wal.lsn = 0; eg_wal.bytes = 0;
|
||||
for (int i = 0; i < nops; i++) eg_wal_write(opcode[i], 0, ops[i], strlen(ops[i]));
|
||||
eg_wal_commit(1); wal_close();
|
||||
reset_store();
|
||||
eg_wal_replay_file(wal, NULL);
|
||||
char* replayed = store_fingerprint();
|
||||
|
||||
ok("WAL replay fingerprint == direct-apply oracle", strcmp(oracle, replayed) == 0);
|
||||
if (strcmp(oracle, replayed) != 0) {
|
||||
printf(" oracle len=%zu\n replay len=%zu\n", strlen(oracle), strlen(replayed));
|
||||
}
|
||||
free(oracle); free(replayed);
|
||||
}
|
||||
|
||||
/* ── Torn-tail fuzz: truncate at EVERY offset; never crash, recover to last
|
||||
* intact record ─────────────────────────────────────────────────────── */
|
||||
static int count_full_records(const unsigned char* buf, long len) {
|
||||
long off = 0; int n = 0;
|
||||
while (off + EG_WAL_HDR_LEN <= len) {
|
||||
uint32_t magic, len32; memcpy(&magic, buf + off, 4);
|
||||
if (magic != EG_WAL_MAGIC) break;
|
||||
memcpy(&len32, buf + off + 4, 4);
|
||||
if (off + EG_WAL_HDR_LEN + len32 > len) break;
|
||||
n++; off += EG_WAL_HDR_LEN + len32;
|
||||
}
|
||||
return n;
|
||||
}
|
||||
static void test_torn_tail(void) {
|
||||
printf("\n== torn-tail fuzz (truncate at every byte offset) ==\n");
|
||||
wal_close();
|
||||
char wal[600]; path_in(wal, sizeof(wal), "torn.wal"); unlink(wal);
|
||||
eg_wal.fp = fopen(wal, "ab"); snprintf(eg_wal.path, sizeof(eg_wal.path), "%s", wal);
|
||||
eg_wal.lsn = 0; eg_wal.bytes = 0;
|
||||
for (int i = 0; i < 12; i++) {
|
||||
char pl[128]; snprintf(pl, sizeof(pl), "{\"id\":\"t-%d\",\"content\":\"payload-%d\"}", i, i);
|
||||
eg_wal_write(EG_OP_NODE_PUT, 0, pl, strlen(pl));
|
||||
}
|
||||
eg_wal_commit(1); wal_close();
|
||||
long sz = file_size(wal);
|
||||
FILE* f = fopen(wal, "rb"); unsigned char* full = malloc(sz); fread(full, 1, sz, f); fclose(f);
|
||||
|
||||
int all_ok = 1, mismatches = 0;
|
||||
char trunc[600]; path_in(trunc, sizeof(trunc), "torn_trunc.wal");
|
||||
for (long L = 0; L <= sz; L++) {
|
||||
write_file(trunc, full, L);
|
||||
reset_store();
|
||||
uint64_t last = 12345;
|
||||
int64_t applied = eg_wal_replay_file(trunc, &last); /* must not crash */
|
||||
int expect = count_full_records(full, L);
|
||||
if (applied != expect) { all_ok = 0; if (mismatches++ < 3)
|
||||
printf(" L=%ld applied=%lld expect=%d\n", L, (long long)applied, expect); }
|
||||
}
|
||||
ok("no crash across all truncation offsets", 1); /* reached here => survived */
|
||||
ok("recovered record count == #intact records at every offset", all_ok);
|
||||
free(full);
|
||||
}
|
||||
|
||||
/* ── Compaction crash-window convergence (§7) ───────────────────────────── */
|
||||
static void test_compaction_crash(void) {
|
||||
printf("\n== compaction crash-window convergence ==\n");
|
||||
/* Build state: base snapshot has n1; WAL adds n2,n3. */
|
||||
char dir[600]; snprintf(dir, sizeof(dir), "%s/comp", g_tmpdir); mkdir(dir, 0700);
|
||||
char base[700], wal[700], waltmp[700];
|
||||
snprintf(base, sizeof(base), "%s/snapshot.json", dir);
|
||||
snprintf(wal, sizeof(wal), "%s/engram.wal", dir);
|
||||
snprintf(waltmp, sizeof(waltmp), "%s/engram.wal.tmp", dir);
|
||||
|
||||
/* Reference full state = n1,n2,n3. */
|
||||
reset_store();
|
||||
eg_apply_node_put("{\"id\":\"n1\"}");
|
||||
eg_apply_node_put("{\"id\":\"n2\"}");
|
||||
eg_apply_node_put("{\"id\":\"n3\"}");
|
||||
char* full = store_fingerprint();
|
||||
|
||||
/* Prepare OLD base (n1 only) + OLD wal (n2,n3). */
|
||||
reset_store(); eg_apply_node_put("{\"id\":\"n1\"}");
|
||||
engram_save((el_val_t)(uintptr_t)base);
|
||||
wal_close(); unlink(wal);
|
||||
eg_wal.fp = fopen(wal, "ab"); snprintf(eg_wal.path, sizeof(eg_wal.path), "%s", wal); eg_wal.lsn = 0; eg_wal.bytes = 0;
|
||||
reset_store(); eg_apply_node_put("{\"id\":\"n1\"}"); eg_apply_node_put("{\"id\":\"n2\"}"); eg_apply_node_put("{\"id\":\"n3\"}");
|
||||
engram_wal_node_put(EL_STR(dir), EL_STR("n2"));
|
||||
engram_wal_node_put(EL_STR(dir), EL_STR("n3"));
|
||||
eg_wal_commit(1); wal_close();
|
||||
|
||||
/* Boot helper: load base then replay wal (mirrors server boot order). */
|
||||
#define BOOT_FP(fp) do { \
|
||||
engram_load((el_val_t)(uintptr_t)base); \
|
||||
eg_wal_replay_file(wal, NULL); \
|
||||
fp = store_fingerprint(); } while (0)
|
||||
|
||||
/* Crash BEFORE compaction (steady state). */
|
||||
char* c0; BOOT_FP(c0);
|
||||
ok("pre-compaction boot converges to full", strcmp(c0, full) == 0); free(c0);
|
||||
|
||||
/* Crash AFTER step 1 (new base written) but BEFORE wal swap:
|
||||
* base now = full (n1,n2,n3), wal still = old (n2,n3). Idempotent replay. */
|
||||
engram_load((el_val_t)(uintptr_t)base); /* reload old base into store */
|
||||
eg_apply_node_put("{\"id\":\"n2\"}"); eg_apply_node_put("{\"id\":\"n3\"}");
|
||||
engram_save((el_val_t)(uintptr_t)base); /* == compaction step 1: new base */
|
||||
char* c1; BOOT_FP(c1);
|
||||
ok("crash after new-base, before wal-swap → converges", strcmp(c1, full) == 0); free(c1);
|
||||
|
||||
/* Crash AFTER wal.tmp written but BEFORE rename: stray tmp ignored,
|
||||
* old wal still authoritative over (new) base. */
|
||||
{ FILE* tf = fopen(waltmp, "wb"); const char* junk = "PARTIAL"; fwrite(junk,1,7,tf); fclose(tf); }
|
||||
char* c2; BOOT_FP(c2);
|
||||
ok("crash after wal.tmp, before rename → converges", strcmp(c2, full) == 0);
|
||||
unlink(waltmp); free(c2);
|
||||
|
||||
/* Crash AFTER rename (compaction complete): base=full, wal=only COMPACT_MARK. */
|
||||
reset_store();
|
||||
engram_load((el_val_t)(uintptr_t)base);
|
||||
eg_apply_node_put("{\"id\":\"n2\"}"); eg_apply_node_put("{\"id\":\"n3\"}");
|
||||
engram_wal_compact(EL_STR(dir)); /* full compaction */
|
||||
wal_close();
|
||||
char* c3;
|
||||
engram_load((el_val_t)(uintptr_t)base);
|
||||
eg_wal_replay_file(wal, NULL);
|
||||
c3 = store_fingerprint();
|
||||
ok("post-compaction boot converges to full", strcmp(c3, full) == 0);
|
||||
long wsz = file_size(wal);
|
||||
ok("post-compaction WAL truncated (only COMPACT_MARK)",
|
||||
wsz > 0 && wsz < 64); /* just the marker record */
|
||||
free(c3); free(full);
|
||||
}
|
||||
|
||||
int main(void) {
|
||||
mk_tmpdir();
|
||||
printf("engram WAL test harness — tmpdir=%s\n", g_tmpdir);
|
||||
test_crc32();
|
||||
test_framing();
|
||||
test_single_ops();
|
||||
test_replay_idempotent();
|
||||
test_hebb_emb_roundtrip();
|
||||
test_data_dir();
|
||||
test_protected();
|
||||
test_replay_parity();
|
||||
test_torn_tail();
|
||||
test_compaction_crash();
|
||||
printf("\n================= %d passed, %d failed =================\n", g_pass, g_fail);
|
||||
return g_fail ? 1 : 0;
|
||||
}
|
||||
+6
-6
@@ -27,11 +27,11 @@ This is where almost all work belongs. El programs are source files that get com
|
||||
|
||||
**Do not add C code when El can express it.** If functionality can be built from existing El primitives (string ops, `exec`, `fs_read/write`, `http_post`, etc.), write it in El.
|
||||
|
||||
### Layer 2: The C seed (`el-compiler/runtime/el_seed.c`)
|
||||
### Layer 2: The C seed (`runtime/el_seed.c`)
|
||||
|
||||
This is the self-contained C OS-boundary layer. It provides the `__`-prefixed primitives that compiled El programs call: libcurl HTTP, pthreads, filesystem I/O, arena allocation, etc. It is **not generated** — it is maintained by hand.
|
||||
|
||||
The old `el_runtime.c` has been archived to `el-compiler/runtime/legacy/`. The runtime is now native El (`runtime/*.el`). `el_seed.c` replaces `el_runtime.c` as the sole C compilation dependency.
|
||||
The old `el_runtime.c` has been archived to `runtime/legacy/`. The runtime is now native El (`runtime/*.el`). `el_seed.c` replaces `el_runtime.c` as the sole C compilation dependency.
|
||||
|
||||
**Only edit `el_seed.c` when you genuinely need OS-level access** (raw sockets, GPU calls, new libcurl features). For everything else, write El.
|
||||
|
||||
@@ -50,9 +50,9 @@ After changing any `.el` source in `el-compiler/src/`:
|
||||
```bash
|
||||
cd /Users/will/Development/neuron-technologies/foundation/el
|
||||
./dist/platform/elc elc-cli.el > elc-new.c
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
-o dist/platform/elc-new \
|
||||
elc-new.c el-compiler/runtime/el_seed.c
|
||||
elc-new.c runtime/el_seed.c
|
||||
# Verify self-hosting:
|
||||
./dist/platform/elc-new elc-cli.el > elc-verify.c
|
||||
diff elc-new.c elc-verify.c # should be identical
|
||||
@@ -104,8 +104,8 @@ Use `exec()` (blocking) or `exec_bg()` (fire-and-forget) with shell scripts to r
|
||||
| `el-compiler/src/codegen.el` | Code generator — builtin arity table lives here |
|
||||
| `el-compiler/src/lexer.el` | Lexer |
|
||||
| `el-compiler/src/parser.el` | Parser |
|
||||
| `el-compiler/runtime/el_seed.c` | Self-contained C OS-boundary layer (replaces el_runtime.c) |
|
||||
| `el-compiler/runtime/el_seed.h` | Seed header (C function declarations) |
|
||||
| `runtime/el_seed.c` | Self-contained C OS-boundary layer (replaces el_runtime.c) |
|
||||
| `runtime/el_seed.h` | Seed header (C function declarations) |
|
||||
| `spec/language.md` | Language specification |
|
||||
| `BOOTSTRAP.md` | How to recover the compiler from scratch |
|
||||
| `elc-cli.el` | Compiler entry point |
|
||||
|
||||
+12
-12
@@ -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 el-compiler/runtime -lcurl -lpthread \
|
||||
cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
-o dist/platform/elc-new \
|
||||
elc-new.c el-compiler/runtime/el_runtime.c
|
||||
elc-new.c 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 `el-compiler/runtime/el_runtime.h`. Every compiled El program links against `el-compiler/runtime/el_runtime.c`.
|
||||
All runtime functions are declared in `runtime/el_runtime.h`. Every compiled El program links against `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 el-compiler/runtime -lcurl -lpthread \
|
||||
-o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
-o <out> <prog>.c 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 el-compiler/runtime -lcurl -lpthread \
|
||||
-o elc-new elc-new.c el-compiler/runtime/el_runtime.c
|
||||
cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
-o elc-new elc-new.c runtime/el_runtime.c
|
||||
```
|
||||
|
||||
### Step 5: Verify Self-Hosting
|
||||
@@ -803,8 +803,8 @@ cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
```bash
|
||||
# Compile elc-cli.el with the new compiler
|
||||
./elc-new elc-cli.el elc-v2.c
|
||||
cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
-o elc-v2 elc-v2.c el-compiler/runtime/el_runtime.c
|
||||
cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
-o elc-v2 elc-v2.c 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 |
|
||||
| `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 | — |
|
||||
| `runtime/el_runtime.h` | Full runtime API declaration | 755 |
|
||||
| `runtime/el_runtime.c` | Full runtime implementation | large |
|
||||
| `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 | — |
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,897 +0,0 @@
|
||||
/*
|
||||
* el_runtime.h — El language C runtime header
|
||||
*
|
||||
* Declares all built-in functions available to compiled El programs.
|
||||
* Include this in every generated .c file.
|
||||
*
|
||||
* Value model:
|
||||
* All El values are represented as el_val_t (= int64_t).
|
||||
* On 64-bit systems a pointer fits in int64_t.
|
||||
* String values are cast: (el_val_t)(uintptr_t)"hello"
|
||||
* Integer values are stored directly.
|
||||
* This lets arithmetic work naturally while still passing strings around.
|
||||
*
|
||||
* Type conventions (El -> C):
|
||||
* String -> el_val_t (holds const char* via uintptr_t cast)
|
||||
* Int -> el_val_t
|
||||
* Bool -> el_val_t (0 = false, nonzero = true)
|
||||
* Any -> el_val_t
|
||||
* Void -> void
|
||||
*
|
||||
* Macros for convenience:
|
||||
* 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_*).
|
||||
* -lpthread — required for the HTTP server (one detached thread per
|
||||
* connection, capped at 64 concurrent).
|
||||
* -loqs — optional; required only when liboqs is installed and the
|
||||
* pq_* / sha3_256_hex entry points are needed. Detected at
|
||||
* compile time via __has_include(<oqs/oqs.h>).
|
||||
* -lcrypto — optional; pulled in alongside -loqs. Used for X25519 in
|
||||
* pq_hybrid_* and HKDF-SHA256 derivation.
|
||||
*
|
||||
* Canonical compile command:
|
||||
* cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
* -o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
*
|
||||
* With liboqs (post-quantum stack):
|
||||
* cc -std=c11 -I el-compiler/runtime -lcurl -lpthread -loqs -lcrypto \
|
||||
* -o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
*/
|
||||
|
||||
#pragma once
|
||||
|
||||
#include <stdint.h>
|
||||
#include <stdlib.h>
|
||||
|
||||
typedef int64_t el_val_t;
|
||||
|
||||
/* HTTP request-handler function-pointer types. Public because soul modules (routes/chat/etc.)
|
||||
* register handlers across translation units; previously defined only inside el_runtime.c, which
|
||||
* made cross-module references (and the Windows build) fail. Home in the shared header. */
|
||||
typedef el_val_t (*http_handler_fn)(el_val_t method, el_val_t path, el_val_t body);
|
||||
typedef el_val_t (*http_handler4_fn)(el_val_t method, el_val_t path, el_val_t body, el_val_t headers);
|
||||
|
||||
#define EL_STR(s) ((el_val_t)(uintptr_t)(s))
|
||||
#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
|
||||
* underlying bits represent the IEEE 754 double. Float-aware builtins
|
||||
* (math, format, json) round-trip via these helpers. */
|
||||
static inline double el_to_float(el_val_t v) {
|
||||
union { int64_t i; double f; } u;
|
||||
u.i = (int64_t)v;
|
||||
return u.f;
|
||||
}
|
||||
|
||||
static inline el_val_t el_from_float(double f) {
|
||||
union { double f; int64_t i; } u;
|
||||
u.f = f;
|
||||
return (el_val_t)u.i;
|
||||
}
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/* ── I/O ──────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t println(el_val_t s);
|
||||
el_val_t print(el_val_t s);
|
||||
el_val_t readline(void);
|
||||
|
||||
/* ── String builtins ─────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_str_concat(el_val_t a, el_val_t b);
|
||||
el_val_t str_eq(el_val_t a, el_val_t b);
|
||||
el_val_t str_starts_with(el_val_t s, el_val_t prefix);
|
||||
el_val_t str_ends_with(el_val_t s, el_val_t suffix);
|
||||
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);
|
||||
el_val_t str_to_upper(el_val_t s);
|
||||
el_val_t str_to_lower(el_val_t s);
|
||||
el_val_t str_trim(el_val_t s);
|
||||
|
||||
/* ── Math ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_abs(el_val_t n);
|
||||
el_val_t el_max(el_val_t a, el_val_t b);
|
||||
el_val_t el_min(el_val_t a, el_val_t b);
|
||||
|
||||
/* ── Refcount (ARC) ──────────────────────────────────────────────────────────
|
||||
* Lists and Maps carry a refcount. Strings and ints do not — el_retain and
|
||||
* el_release are safe no-ops on non-refcounted values (they sniff a magic
|
||||
* header at offset 0 and only act if the magic matches).
|
||||
*
|
||||
* Codegen emits these at let-binding shadowing, function entry (params), and
|
||||
* function exit (locals other than the returned value). The refcount lets
|
||||
* el_list_append and el_map_set mutate in place when uniquely owned (cheap)
|
||||
* and copy-on-write when shared (preserves persistent semantics across
|
||||
* accumulator patterns in the compiler itself). */
|
||||
|
||||
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, ...);
|
||||
el_val_t el_list_len(el_val_t list);
|
||||
el_val_t el_list_get(el_val_t list, el_val_t index);
|
||||
el_val_t el_list_append(el_val_t list, el_val_t elem);
|
||||
el_val_t el_list_empty(void);
|
||||
el_val_t el_list_clone(el_val_t list);
|
||||
|
||||
/* ── Map ─────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_map_new(el_val_t pair_count, ...);
|
||||
el_val_t el_get_field(el_val_t map, el_val_t key);
|
||||
el_val_t el_map_get(el_val_t map, el_val_t key);
|
||||
el_val_t el_map_set(el_val_t map, el_val_t key, el_val_t value);
|
||||
|
||||
/* ── HTTP ─────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t http_get(el_val_t url);
|
||||
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);
|
||||
|
||||
/* HTTP server v2 ─────────────────────────────────────────────────────────────
|
||||
* Same dispatch model as http_serve, but the handler signature is widened:
|
||||
*
|
||||
* el_val_t handler(method, path, headers_map, body)
|
||||
*
|
||||
* `headers_map` is an ElMap from lowercased header name → header value (both
|
||||
* Strings). Repeated headers are joined with ", " per RFC 7230.
|
||||
*
|
||||
* Response value: the handler may return either
|
||||
* (a) a plain body string — same auto-content-type / 200-OK behaviour as
|
||||
* http_serve (3-arg) — or
|
||||
* (b) a response envelope built with `http_response(status, headers_json,
|
||||
* body)`. The runtime detects the envelope discriminator
|
||||
* `"el_http_response":1` at the start of the returned string and
|
||||
* unpacks status / headers / body before sending.
|
||||
*
|
||||
* 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);
|
||||
void http_serve_async(el_val_t port, el_val_t handler);
|
||||
el_val_t 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
|
||||
* returned string carries the discriminator `{"el_http_response":1,...}`
|
||||
* which the runtime's send-path detects and unpacks. Detection happens
|
||||
* uniformly inside http_send_response, so a 3-arg handler may also return
|
||||
* an envelope. The 3-arg variant remains documented as a fixed 200-OK
|
||||
* 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. */
|
||||
|
||||
/* Streaming variants — write the response body straight to a file via
|
||||
* libcurl's CURLOPT_WRITEFUNCTION = fwrite. These bypass the el_val_t string
|
||||
* wrapper entirely, so binary payloads (audio/mpeg, image/png, etc.) survive
|
||||
* embedded NUL bytes that would truncate a strlen()-based code path.
|
||||
*
|
||||
* Both honor EL_HTTP_TIMEOUT_MS, follow redirects, and accept the same
|
||||
* `headers_map` shape as http_post_with_headers (ElMap of String→String).
|
||||
*
|
||||
* Return value: 1 on success (file fully written), 0 on any failure
|
||||
* (network, file open, partial write). On failure the output file is removed
|
||||
* so callers cannot mistake a partially-written file for a valid one. */
|
||||
el_val_t http_post_to_file(el_val_t url, el_val_t body, el_val_t headers_map, el_val_t output_path);
|
||||
el_val_t http_get_to_file(el_val_t url, el_val_t headers_map, el_val_t output_path);
|
||||
|
||||
/* ── URL encoding ────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t url_encode(el_val_t s); /* RFC 3986 unreserved set */
|
||||
el_val_t url_decode(el_val_t s); /* '+' → space, %XX → byte */
|
||||
|
||||
/* ── HTML allowlist sanitizer ────────────────────────────────────────────────
|
||||
* el_html_sanitize(input_html, allowlist_json) — strict allowlist HTML
|
||||
* cleaner. State-machine parser; tag/attribute names compared case-
|
||||
* insensitively against the allowlist; `<a href>` / `<… src>` URL schemes
|
||||
* validated (http, https, mailto, fragment-only, or relative); whole-
|
||||
* subtree drop for script / style / iframe / object / embed / form; HTML-
|
||||
* escapes free text outside dropped subtrees.
|
||||
*
|
||||
* The allowlist is JSON of the form
|
||||
* {"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 */
|
||||
|
||||
/* Length-explicit binary write. `length` is an Int (el_val_t holding the
|
||||
* byte count). The caller knows the length from context — typically because
|
||||
* `bytes` came from base64_decode (which produces a magic-tagged binary
|
||||
* buffer with embedded NULs possible) and the caller already tracks the
|
||||
* decoded length, OR because the bytes came from a fixed-size source
|
||||
* (sha256_bytes = 32, hmac_sha256_bytes = 32). Bypasses strlen entirely.
|
||||
*
|
||||
* Returns 1 on success, 0 on failure (invalid path, can't open, partial
|
||||
* write, negative length). On partial-write failure, the file is removed
|
||||
* so callers cannot read back a truncated artefact. */
|
||||
el_val_t fs_write_bytes(el_val_t path, el_val_t bytes, el_val_t length);
|
||||
|
||||
/* ── JSON ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t json_get(el_val_t json, el_val_t key);
|
||||
el_val_t json_parse(el_val_t s);
|
||||
el_val_t json_stringify(el_val_t v);
|
||||
el_val_t json_get_string(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_int(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_float(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_bool(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_raw(el_val_t json_str, el_val_t key);
|
||||
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 ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t time_now(void);
|
||||
el_val_t time_now_utc(void);
|
||||
el_val_t sleep_secs(el_val_t secs);
|
||||
el_val_t sleep_ms(el_val_t ms);
|
||||
el_val_t time_format(el_val_t ts, el_val_t fmt);
|
||||
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
|
||||
* since the Unix epoch; Durations are signed nanoseconds. Type discipline
|
||||
* is enforced at codegen-time: BinOps on names registered as Instant or
|
||||
* Duration route through the typed wrappers below; mismatches like
|
||||
* Instant+Instant become #error at the C compiler.
|
||||
*
|
||||
* Postfix literals — `30.seconds`, `1.hour`, `500.millis`, `30.nanos` — are
|
||||
* recognised by the parser as DurationLit AST nodes and lowered to literal
|
||||
* int64 nanoseconds at codegen time. The runtime never sees the units. */
|
||||
|
||||
el_val_t el_now_instant(void);
|
||||
el_val_t now(void);
|
||||
el_val_t unix_seconds(el_val_t n);
|
||||
el_val_t unix_millis(el_val_t n);
|
||||
el_val_t instant_from_iso8601(el_val_t s);
|
||||
|
||||
el_val_t el_duration_from_nanos(el_val_t ns);
|
||||
el_val_t duration_seconds(el_val_t n);
|
||||
el_val_t duration_millis(el_val_t n);
|
||||
el_val_t duration_nanos(el_val_t n);
|
||||
|
||||
el_val_t el_instant_add_dur(el_val_t inst, el_val_t dur);
|
||||
el_val_t el_instant_sub_dur(el_val_t inst, el_val_t dur);
|
||||
el_val_t el_instant_diff(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_add(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_sub(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_scale(el_val_t dur, el_val_t scalar);
|
||||
el_val_t el_duration_div(el_val_t dur, el_val_t scalar);
|
||||
|
||||
el_val_t el_instant_lt(el_val_t a, el_val_t b);
|
||||
el_val_t el_instant_le(el_val_t a, el_val_t b);
|
||||
el_val_t el_instant_gt(el_val_t a, el_val_t b);
|
||||
el_val_t el_instant_ge(el_val_t a, el_val_t b);
|
||||
el_val_t el_instant_eq(el_val_t a, el_val_t b);
|
||||
el_val_t el_instant_ne(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_lt(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_le(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_gt(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_ge(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_eq(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_ne(el_val_t a, el_val_t b);
|
||||
|
||||
el_val_t instant_to_unix_seconds(el_val_t i);
|
||||
el_val_t instant_to_unix_millis(el_val_t i);
|
||||
el_val_t instant_to_iso8601(el_val_t i);
|
||||
el_val_t duration_to_seconds(el_val_t d);
|
||||
el_val_t duration_to_millis(el_val_t d);
|
||||
el_val_t duration_to_nanos(el_val_t d);
|
||||
|
||||
el_val_t el_sleep_duration(el_val_t dur);
|
||||
el_val_t unix_timestamp(void);
|
||||
|
||||
el_val_t ttl_cache_set(el_val_t key, el_val_t value);
|
||||
el_val_t ttl_cache_get(el_val_t key, el_val_t max_age);
|
||||
el_val_t ttl_cache_age(el_val_t key);
|
||||
|
||||
/* ── Calendar + CalendarTime + Rhythm + LocalDate/Time/DateTime ─────────────
|
||||
* Phase 1.5 of the time system. Calendar is pluggable: EarthCalendar (IANA
|
||||
* zones, Gregorian, DST) is the user-facing default; MarsCalendar,
|
||||
* CycleCalendar(period), NoCycleCalendar, RelativeCalendar handle non-Earth
|
||||
* domains.
|
||||
*
|
||||
* A Calendar interprets an Instant under a particular cycle convention and
|
||||
* produces a CalendarTime. CalendarTime carries the underlying Instant and
|
||||
* a back-pointer to its Calendar; arithmetic and formatting consult the
|
||||
* Calendar to convert ns since epoch into year/month/day/hour/minute/second
|
||||
* (or sol/phase, or cycle/phase, depending on kind).
|
||||
*
|
||||
* Storage convention: Calendar / CalendarTime / Rhythm / LocalDate /
|
||||
* LocalDateTime are heap-allocated structs whose pointers are cast into
|
||||
* el_val_t. A 24-bit magic header at offset 0 lets the runtime identify
|
||||
* the kind safely. LocalTime is small enough to live in the int64 slot
|
||||
* directly (nanos since midnight, signed). */
|
||||
|
||||
/* Zone — opaque IANA zone or fixed offset, used by EarthCalendar.
|
||||
* `zone_id` is either an IANA name ("America/New_York", "UTC") or a fixed
|
||||
* offset string ("+05:30", "-08:00"). The runtime resolves it via tzset()
|
||||
* on first use of the owning EarthCalendar. */
|
||||
el_val_t zone(el_val_t id);
|
||||
el_val_t zone_utc(void);
|
||||
el_val_t zone_local(void);
|
||||
el_val_t zone_offset(el_val_t hours, el_val_t minutes);
|
||||
|
||||
/* Calendar constructors. Each returns an el_val_t pointer to a heap-
|
||||
* allocated, magic-tagged Calendar struct. Calendars are interned by
|
||||
* (kind, zone_id, period_ns, epoch_ns) so identical constructors return
|
||||
* the same pointer — equality is reference equality. */
|
||||
el_val_t earth_calendar(el_val_t z);
|
||||
el_val_t earth_calendar_default(void);
|
||||
el_val_t mars_calendar(void);
|
||||
el_val_t cycle_calendar(el_val_t period_dur);
|
||||
el_val_t no_cycle_calendar(void);
|
||||
el_val_t relative_calendar(el_val_t epoch_inst);
|
||||
|
||||
/* CalendarTime constructors and methods. Returns a heap-allocated struct
|
||||
* whose pointer fits in el_val_t. */
|
||||
el_val_t now_in(el_val_t cal);
|
||||
el_val_t in_calendar(el_val_t inst, el_val_t cal);
|
||||
el_val_t cal_format(el_val_t ct, el_val_t pattern);
|
||||
el_val_t cal_to_instant(el_val_t ct);
|
||||
el_val_t cal_cycle_phase(el_val_t ct);
|
||||
el_val_t cal_in(el_val_t ct, el_val_t cal);
|
||||
|
||||
/* LocalDate / LocalTime / LocalDateTime — calendar-agnostic value types.
|
||||
* LocalTime carries nanoseconds since midnight as a signed int64 directly
|
||||
* in the el_val_t slot (no allocation). LocalDate / LocalDateTime are
|
||||
* heap-allocated structs with magic headers. */
|
||||
el_val_t local_date(el_val_t y, el_val_t m, el_val_t d);
|
||||
el_val_t local_time(el_val_t h, el_val_t m, el_val_t s, el_val_t ns);
|
||||
el_val_t local_datetime(el_val_t date, el_val_t time);
|
||||
el_val_t zoned(el_val_t date, el_val_t time, el_val_t cal);
|
||||
|
||||
el_val_t local_date_year(el_val_t ld);
|
||||
el_val_t local_date_month(el_val_t ld);
|
||||
el_val_t local_date_day(el_val_t ld);
|
||||
el_val_t local_time_hour(el_val_t lt);
|
||||
el_val_t local_time_minute(el_val_t lt);
|
||||
el_val_t local_time_second(el_val_t lt);
|
||||
el_val_t local_time_nanos(el_val_t lt);
|
||||
|
||||
el_val_t el_local_date_add_dur(el_val_t ld, el_val_t dur);
|
||||
el_val_t el_local_time_add_dur(el_val_t lt, el_val_t dur);
|
||||
el_val_t el_local_date_lt(el_val_t a, el_val_t b);
|
||||
el_val_t el_local_date_eq(el_val_t a, el_val_t b);
|
||||
|
||||
/* Rhythm — pluggable recurrence AST. Returns a heap-allocated struct
|
||||
* pointer in el_val_t; rhythms are immutable so callers may share them. */
|
||||
el_val_t rhythm_cycle_start(void);
|
||||
el_val_t rhythm_cycle_phase(el_val_t phase);
|
||||
el_val_t rhythm_duration(el_val_t d);
|
||||
el_val_t rhythm_session_start(void);
|
||||
el_val_t rhythm_event(el_val_t name);
|
||||
el_val_t rhythm_and(el_val_t a, el_val_t b);
|
||||
el_val_t rhythm_or(el_val_t a, el_val_t b);
|
||||
el_val_t rhythm_weekday(el_val_t day);
|
||||
el_val_t rhythm_weekly_at(el_val_t day, el_val_t hour, el_val_t minute);
|
||||
el_val_t rhythm_next_after(el_val_t r, el_val_t after, el_val_t cal);
|
||||
el_val_t rhythm_matches(el_val_t r, el_val_t ct);
|
||||
|
||||
/* ── UUID ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t uuid_new(void);
|
||||
el_val_t uuid_v4(void);
|
||||
|
||||
/* ── Environment ─────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t env(el_val_t key);
|
||||
|
||||
/* ── In-process state K/V ────────────────────────────────────────────────── */
|
||||
|
||||
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 ────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t float_to_str(el_val_t f);
|
||||
el_val_t int_to_float(el_val_t n);
|
||||
el_val_t float_to_int(el_val_t f);
|
||||
el_val_t format_float(el_val_t f, el_val_t decimals);
|
||||
el_val_t decimal_round(el_val_t f, el_val_t decimals);
|
||||
el_val_t str_to_float(el_val_t s);
|
||||
|
||||
/* ── Math (Float-aware) ──────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t math_sqrt(el_val_t f);
|
||||
el_val_t math_log(el_val_t f);
|
||||
el_val_t math_ln(el_val_t f);
|
||||
el_val_t math_sin(el_val_t f);
|
||||
el_val_t math_cos(el_val_t f);
|
||||
el_val_t math_pi(void);
|
||||
|
||||
/* ── String additions ────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t str_index_of(el_val_t s, el_val_t sub);
|
||||
el_val_t str_split(el_val_t s, el_val_t sep);
|
||||
el_val_t str_char_at(el_val_t s, el_val_t i);
|
||||
el_val_t str_char_code(el_val_t s, el_val_t i);
|
||||
el_val_t str_pad_left(el_val_t s, el_val_t width, el_val_t pad);
|
||||
el_val_t str_pad_right(el_val_t s, el_val_t width, el_val_t pad);
|
||||
el_val_t str_format(el_val_t fmt, el_val_t data);
|
||||
el_val_t str_lower(el_val_t s);
|
||||
el_val_t str_upper(el_val_t s);
|
||||
|
||||
/* ── Text-processing primitives (Phase 1: byte/codepoint, ASCII char classes)
|
||||
* Phase 2 (filed): Unicode-grapheme awareness, NFC/NFD normalization, regex.
|
||||
* is_* predicates: empty input returns false; multi-char requires ALL bytes
|
||||
* to match. ASCII ranges only in Phase 1. */
|
||||
|
||||
/* Counting */
|
||||
el_val_t str_count(el_val_t s, el_val_t sub); /* non-overlapping */
|
||||
el_val_t str_count_chars(el_val_t s); /* codepoint count */
|
||||
el_val_t str_count_bytes(el_val_t s); /* alias of str_len */
|
||||
el_val_t str_count_lines(el_val_t s);
|
||||
el_val_t str_count_words(el_val_t s);
|
||||
el_val_t str_count_letters(el_val_t s); /* ASCII [A-Za-z] */
|
||||
el_val_t str_count_digits(el_val_t s); /* ASCII [0-9] */
|
||||
|
||||
/* Find / position */
|
||||
el_val_t str_index_of_all(el_val_t s, el_val_t sub); /* [Int] of byte offsets */
|
||||
el_val_t str_last_index_of(el_val_t s, el_val_t sub);
|
||||
el_val_t str_find_chars(el_val_t s, el_val_t any_of); /* first idx of any ch */
|
||||
|
||||
/* Transform */
|
||||
el_val_t str_repeat(el_val_t s, el_val_t n);
|
||||
el_val_t str_reverse(el_val_t s); /* by codepoint */
|
||||
el_val_t str_strip_prefix(el_val_t s, el_val_t prefix);
|
||||
el_val_t str_strip_suffix(el_val_t s, el_val_t suffix);
|
||||
el_val_t str_strip_chars(el_val_t s, el_val_t chars);
|
||||
el_val_t str_lstrip(el_val_t s);
|
||||
el_val_t str_rstrip(el_val_t s);
|
||||
|
||||
/* Char classification (Bool) */
|
||||
el_val_t is_letter(el_val_t s);
|
||||
el_val_t is_digit(el_val_t s);
|
||||
el_val_t is_alphanumeric(el_val_t s);
|
||||
el_val_t is_whitespace(el_val_t s);
|
||||
el_val_t is_punctuation(el_val_t s);
|
||||
el_val_t is_uppercase(el_val_t s);
|
||||
el_val_t is_lowercase(el_val_t s);
|
||||
|
||||
/* Split / join */
|
||||
el_val_t str_split_lines(el_val_t s);
|
||||
el_val_t str_split_chars(el_val_t s); /* alias of native_string_chars */
|
||||
el_val_t str_split_n(el_val_t s, el_val_t sep, el_val_t n);
|
||||
el_val_t str_join(el_val_t list, el_val_t sep); /* alias of list_join */
|
||||
|
||||
/* ── List additions ──────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t list_push(el_val_t list, el_val_t elem);
|
||||
el_val_t list_push_front(el_val_t list, el_val_t elem);
|
||||
el_val_t list_join(el_val_t list, el_val_t sep);
|
||||
el_val_t list_range(el_val_t start, el_val_t end);
|
||||
|
||||
/* ── Bool helpers ────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t bool_to_str(el_val_t b);
|
||||
|
||||
/* ── Numeric parsing ─────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t parse_int(el_val_t s, el_val_t default_val);
|
||||
|
||||
/* ── Process ─────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t 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. */
|
||||
|
||||
void el_cgi_init(el_val_t name, el_val_t dharma_id, el_val_t principal,
|
||||
el_val_t network, el_val_t engram);
|
||||
|
||||
/* ── DHARMA network builtins ─────────────────────────────────────────────────
|
||||
* Available to CGI programs (declared with a `cgi {}` block).
|
||||
*
|
||||
* Peers are addressed by `dharma_id` of the form
|
||||
* "<registry-id>@<transport-url>" e.g. "ntn-genesis@http://localhost:7770"
|
||||
* If the @<url> portion is omitted, transport defaults to
|
||||
* "http://localhost:7770" (the local CGI daemon assumption).
|
||||
*
|
||||
* Wire protocol (all peers expose):
|
||||
* POST <url>/dharma/recv { channel, from, content } → response body
|
||||
* POST <url>/dharma/event { type, payload, source, timestamp }
|
||||
* POST <url>/api/activate { query } → list of nodes
|
||||
*
|
||||
* Hosting application's responsibility: an El program with a `cgi {}` block
|
||||
* runs http_serve() with its own request handler; that handler should route
|
||||
* "/dharma/event" requests by calling el_runtime_dharma_event_arrive() so
|
||||
* incoming events feed dharma_field() queues. The runtime itself does not
|
||||
* intercept any /dharma path. */
|
||||
|
||||
el_val_t dharma_connect(el_val_t cgi_id);
|
||||
el_val_t dharma_send(el_val_t channel, el_val_t content);
|
||||
el_val_t dharma_activate(el_val_t query);
|
||||
void dharma_emit(el_val_t event_type, el_val_t payload);
|
||||
el_val_t dharma_field(el_val_t event_type);
|
||||
void dharma_strengthen(el_val_t cgi_id, el_val_t weight);
|
||||
el_val_t dharma_relationship(el_val_t cgi_id);
|
||||
el_val_t dharma_peers(void);
|
||||
|
||||
/* Public C API: called by an El program's HTTP handler when a /dharma/event
|
||||
* request arrives. Pushes onto the per-event-type queue and signals any
|
||||
* pending dharma_field() blockers. All three arguments must be NUL-terminated
|
||||
* C strings (or NULL — then treated as empty). */
|
||||
void el_runtime_dharma_event_arrive(const char* event_type,
|
||||
const char* payload,
|
||||
const char* source);
|
||||
|
||||
/* ── Engram local graph primitives ───────────────────────────────────────────
|
||||
* Operate on the CGI's local Engram knowledge graph.
|
||||
* `engram_activate` queries the local graph only; `dharma_activate` is
|
||||
* network-wide across all connected CGI graphs. */
|
||||
|
||||
el_val_t engram_node(el_val_t content, el_val_t node_type, el_val_t salience);
|
||||
el_val_t engram_node_full(el_val_t content, el_val_t node_type, el_val_t label,
|
||||
el_val_t salience, el_val_t importance, el_val_t confidence,
|
||||
el_val_t tier, el_val_t tags);
|
||||
/* Layered consciousness — see el_runtime.c for the layered architecture
|
||||
* design notes (search "Layered consciousness architecture"). The five
|
||||
* canonical layers (safety / core-identity / domain-knowledge / imprint /
|
||||
* suit) are seeded automatically; engram_add_layer extends the registry
|
||||
* with imprint or suit overlays at runtime. Nodes default to layer 1
|
||||
* (core-identity) when created via engram_node / engram_node_full. */
|
||||
el_val_t engram_node_layered(el_val_t content, el_val_t node_type, el_val_t label,
|
||||
el_val_t salience, el_val_t certainty, el_val_t confidence,
|
||||
el_val_t status, el_val_t tags, el_val_t layer_id);
|
||||
el_val_t engram_add_layer(el_val_t name, el_val_t priority, el_val_t suppressible,
|
||||
el_val_t transparent, el_val_t injectable);
|
||||
el_val_t engram_remove_layer(el_val_t layer_id);
|
||||
el_val_t engram_list_layers(void);
|
||||
el_val_t engram_get_node(el_val_t id);
|
||||
void engram_strengthen(el_val_t node_id);
|
||||
void engram_forget(el_val_t node_id);
|
||||
el_val_t engram_node_count(void);
|
||||
el_val_t engram_search(el_val_t query, el_val_t limit);
|
||||
el_val_t engram_scan_nodes(el_val_t limit, el_val_t offset);
|
||||
void engram_connect(el_val_t from_id, el_val_t to_id, el_val_t weight, el_val_t relation);
|
||||
el_val_t engram_edge_between(el_val_t from_id, el_val_t to_id);
|
||||
el_val_t engram_neighbors(el_val_t node_id);
|
||||
el_val_t engram_neighbors_filtered(el_val_t node_id, el_val_t max_depth, el_val_t direction);
|
||||
el_val_t engram_edge_count(void);
|
||||
/* Three-pass activation: background fan-out → working-memory promotion →
|
||||
* Layer 0 override. See "Three-pass activation" in el_runtime.c. */
|
||||
el_val_t engram_activate(el_val_t query, el_val_t depth);
|
||||
el_val_t engram_save(el_val_t path);
|
||||
el_val_t engram_load(el_val_t path);
|
||||
|
||||
/* JSON-string accessors — return pre-serialized JSON so HTTP handlers
|
||||
* can pass results straight through without round-tripping ElList/ElMap
|
||||
* through json_stringify. */
|
||||
el_val_t engram_get_node_json(el_val_t id);
|
||||
el_val_t engram_get_node_by_label(el_val_t label);
|
||||
el_val_t engram_search_json(el_val_t query, el_val_t limit);
|
||||
el_val_t engram_scan_nodes_json(el_val_t limit, el_val_t offset);
|
||||
el_val_t engram_scan_nodes_by_type_json(el_val_t node_type, el_val_t limit, el_val_t offset);
|
||||
el_val_t engram_neighbors_json(el_val_t node_id, el_val_t max_depth, el_val_t direction);
|
||||
el_val_t engram_activate_json(el_val_t query, el_val_t depth);
|
||||
el_val_t engram_stats_json(void);
|
||||
el_val_t engram_list_layers_json(void);
|
||||
/* engram_compile_layered_json — produce a prompt-ready text block split
|
||||
* into "[LAYER 0 — STRUCTURAL]" (non-suppressible layers, sacred fire)
|
||||
* and "[ENGRAM CONTEXT]" (standard suppressible layers). Returns "" if
|
||||
* no nodes promoted to working memory. */
|
||||
el_val_t engram_compile_layered_json(el_val_t intent, el_val_t depth);
|
||||
|
||||
/* ── Working memory ──────────────────────────────────────────────────────────*/
|
||||
el_val_t engram_wm_count(void);
|
||||
el_val_t engram_wm_avg_weight(void);
|
||||
el_val_t engram_wm_top_json(el_val_t n);
|
||||
el_val_t engram_load_merge(el_val_t path);
|
||||
|
||||
/* ── LLM (Anthropic API client) ─────────────────────────────────────────────
|
||||
* All functions call https://api.anthropic.com/v1/messages with the API key
|
||||
* from env ANTHROPIC_API_KEY. Default model when empty: claude-sonnet-4-5. */
|
||||
|
||||
el_val_t llm_call(el_val_t model, el_val_t prompt);
|
||||
el_val_t llm_call_system(el_val_t model, el_val_t system_prompt, el_val_t user_prompt);
|
||||
el_val_t llm_call_agentic(el_val_t model, el_val_t system, el_val_t user, el_val_t tools);
|
||||
el_val_t llm_vision(el_val_t model, el_val_t system, el_val_t prompt, el_val_t image_url_or_b64);
|
||||
el_val_t llm_models(void);
|
||||
|
||||
/* Register a tool handler by name. The handler is looked up via dlsym
|
||||
* (mirroring http_set_handler), so any El `fn <name>(input)` compiles to
|
||||
* a global C symbol that this function can locate at runtime.
|
||||
* Handler signature: `el_val_t handler(el_val_t input_json)` — receives
|
||||
* the tool input as a JSON-string el_val_t and returns a JSON-string
|
||||
* el_val_t result. Used by llm_call_agentic. */
|
||||
void llm_register_tool(el_val_t name, el_val_t handler_fn_name);
|
||||
|
||||
/* ── args() ─────────────────────────────────────────────────────────────────
|
||||
* Provides access to command-line arguments passed to the program.
|
||||
* Populated by el_runtime_init_args() before main() runs. */
|
||||
|
||||
el_val_t args(void);
|
||||
void el_runtime_init_args(int argc, char** argv);
|
||||
|
||||
/* ── Crypto primitives ─────────────────────────────────────────────────────
|
||||
* SHA-256, HMAC-SHA-256, and base64 (standard + URL-safe).
|
||||
* Self-contained — no OpenSSL/libcrypto dependency. The implementations are
|
||||
* adapted from public-domain reference code (Brad Conte / RFC 4648).
|
||||
*
|
||||
* Bytes-returning variants (sha256_bytes, hmac_sha256_bytes) return a string
|
||||
* value whose contents are raw binary; callers usually feed these into
|
||||
* base64_encode. Note that el_val_t strings are NUL-terminated by convention,
|
||||
* so the binary payload may contain embedded NULs — pass it directly into
|
||||
* base64_encode (which uses an explicit length) rather than treating it as
|
||||
* a printable C string.
|
||||
*
|
||||
* The "base64" variants emit/accept RFC 4648 standard alphabet with padding.
|
||||
* The "base64url" variants use URL-safe alphabet (`-`/`_`) with no padding,
|
||||
* as used in JWTs. */
|
||||
|
||||
el_val_t sha256_hex(el_val_t input);
|
||||
el_val_t sha256_bytes(el_val_t input);
|
||||
el_val_t hmac_sha256_hex(el_val_t key, el_val_t message);
|
||||
el_val_t hmac_sha256_bytes(el_val_t key, el_val_t message);
|
||||
el_val_t base64_encode(el_val_t input);
|
||||
el_val_t base64_decode(el_val_t input);
|
||||
el_val_t base64url_encode(el_val_t input);
|
||||
el_val_t base64url_decode(el_val_t input);
|
||||
|
||||
/* Length-aware variants (internal — exposed for the rare caller that already
|
||||
* has a known-length binary buffer and doesn't want to round-trip through
|
||||
* a NUL-terminated el_val_t string). Sha256_bytes and hmac_sha256_bytes feed
|
||||
* these implicitly. */
|
||||
el_val_t el_sha256_bytes_n(const unsigned char* data, size_t len);
|
||||
el_val_t el_base64_encode_n(const unsigned char* data, size_t len, int url_safe);
|
||||
|
||||
/* ── Post-quantum primitives (liboqs-backed) ────────────────────────────────
|
||||
* All inputs/outputs hex-encoded. Algorithm choices:
|
||||
* Signature: CRYSTALS-Dilithium-3 (NIST level 3, balanced)
|
||||
* KEM: CRYSTALS-Kyber-768 (NIST level 3)
|
||||
* Hash: SHA3-256 (Keccak) (PQ-aware protocols favour SHA3 over SHA2)
|
||||
*
|
||||
* If liboqs is not linked (detected via __has_include(<oqs/oqs.h>) at compile
|
||||
* time), the pq_* entry points return a JSON-shaped error string so callers
|
||||
* fail loudly rather than silently fall back to classical schemes:
|
||||
* {"error":"liboqs not linked, post-quantum primitives unavailable"}
|
||||
*
|
||||
* The hybrid handshake pairs X25519 with Kyber-768 per NIST PQ guidance and
|
||||
* CNSA 2.0. Combined shared secret is HKDF-SHA256(x25519_ss || kyber_ss).
|
||||
* Even if Kyber falls, X25519 holds; if X25519 falls under quantum attack,
|
||||
* Kyber holds. SHA3-256 also remains usable independent of liboqs (the
|
||||
* Keccak permutation is PQ-OK as a primitive). */
|
||||
|
||||
el_val_t pq_keygen_signature(void);
|
||||
el_val_t pq_sign(el_val_t secret_key_hex, el_val_t message);
|
||||
el_val_t pq_verify(el_val_t public_key_hex, el_val_t message, el_val_t signature_hex);
|
||||
|
||||
el_val_t pq_kem_keygen(void);
|
||||
el_val_t pq_kem_encaps(el_val_t public_key_hex);
|
||||
el_val_t pq_kem_decaps(el_val_t secret_key_hex, el_val_t ciphertext_hex);
|
||||
|
||||
el_val_t pq_hybrid_keygen(void);
|
||||
el_val_t pq_hybrid_handshake(el_val_t remote_pub_combined);
|
||||
|
||||
el_val_t sha3_256_hex(el_val_t input);
|
||||
|
||||
/* ── AEAD: AES-256-GCM (libcrypto-backed) ───────────────────────────────────
|
||||
* Symmetric authenticated encryption used to wrap envelopes after a KEM
|
||||
* handshake. Caller MUST supply a 32-byte key (64 hex chars) — typically the
|
||||
* Kyber-768 / hybrid shared_secret, optionally normalized via SHA3-256.
|
||||
*
|
||||
* aead_encrypt returns a JSON map {"nonce":"...","ciphertext":"..."} where
|
||||
* ciphertext is the AES-256-GCM output with the 16-byte auth tag appended.
|
||||
* Nonce is a fresh 12-byte CSPRNG draw — callers never pick the nonce, which
|
||||
* structurally rules out the GCM nonce-reuse footgun.
|
||||
*
|
||||
* aead_decrypt returns the plaintext String, or "" on any failure (including
|
||||
* auth-tag mismatch). Callers MUST check for "" before trusting the result. */
|
||||
el_val_t aead_encrypt(el_val_t key_hex, el_val_t plaintext);
|
||||
el_val_t aead_decrypt(el_val_t key_hex, el_val_t nonce_hex, el_val_t ciphertext_hex);
|
||||
|
||||
/* ── Native VM builtin aliases (for compiled El source) ─────────────────────
|
||||
* These match the El VM's native_* builtins so that El source compiled
|
||||
* to C can call the same names without modification. */
|
||||
|
||||
el_val_t native_list_get(el_val_t list, el_val_t index);
|
||||
el_val_t native_list_len(el_val_t list);
|
||||
el_val_t native_list_append(el_val_t list, el_val_t elem);
|
||||
el_val_t native_list_empty(void);
|
||||
el_val_t native_list_clone(el_val_t list);
|
||||
el_val_t native_string_chars(el_val_t s);
|
||||
el_val_t native_int_to_str(el_val_t n);
|
||||
|
||||
/* ── Method-call shorthand aliases ──────────────────────────────────────────
|
||||
* The El method-call convention `obj.method(args)` compiles to
|
||||
* `method(obj, args)`. These aliases expose the runtime functions under
|
||||
* the short names that result from method calls in El source.
|
||||
*
|
||||
* Example: `myList.append(x)` → `append(myList, x)` (calls this alias)
|
||||
* `myList.len()` → `len(myList)` (calls this alias) */
|
||||
|
||||
el_val_t append(el_val_t list, el_val_t elem); /* el_list_append */
|
||||
el_val_t len(el_val_t list); /* el_list_len */
|
||||
el_val_t get(el_val_t list, el_val_t index); /* el_list_get */
|
||||
el_val_t map_get(el_val_t map, el_val_t key); /* el_map_get */
|
||||
el_val_t map_set(el_val_t map, el_val_t key, el_val_t value); /* el_map_set */
|
||||
|
||||
/* ── OTLP/HTTP Observability ─────────────────────────────────────────────── */
|
||||
/* See bottom of el_runtime.c for the implementation.
|
||||
* Configured by env vars OTLP_ENDPOINT, OTEL_SERVICE_NAME, OTEL_SERVICE_VERSION.
|
||||
* No-op when OTLP_ENDPOINT is unset. Drop-on-failure semantics. */
|
||||
/* ── Subprocess execution ────────────────────────────────────────────────── */
|
||||
el_val_t exec_command(el_val_t cmd); /* run shell command, return exit code */
|
||||
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
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,761 +0,0 @@
|
||||
/*
|
||||
* el_runtime.h — El language C runtime header
|
||||
*
|
||||
* Declares all built-in functions available to compiled El programs.
|
||||
* Include this in every generated .c file.
|
||||
*
|
||||
* Value model:
|
||||
* All El values are represented as el_val_t (= int64_t).
|
||||
* On 64-bit systems a pointer fits in int64_t.
|
||||
* String values are cast: (el_val_t)(uintptr_t)"hello"
|
||||
* Integer values are stored directly.
|
||||
* This lets arithmetic work naturally while still passing strings around.
|
||||
*
|
||||
* Type conventions (El -> C):
|
||||
* String -> el_val_t (holds const char* via uintptr_t cast)
|
||||
* Int -> el_val_t
|
||||
* Bool -> el_val_t (0 = false, nonzero = true)
|
||||
* Any -> el_val_t
|
||||
* Void -> void
|
||||
*
|
||||
* Macros for convenience:
|
||||
* 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
|
||||
*
|
||||
* Link requirements:
|
||||
* -lcurl — required for the HTTP client (http_get, http_post, llm_*).
|
||||
* -lpthread — required for the HTTP server (one detached thread per
|
||||
* connection, capped at 64 concurrent).
|
||||
* -loqs — optional; required only when liboqs is installed and the
|
||||
* pq_* / sha3_256_hex entry points are needed. Detected at
|
||||
* compile time via __has_include(<oqs/oqs.h>).
|
||||
* -lcrypto — optional; pulled in alongside -loqs. Used for X25519 in
|
||||
* pq_hybrid_* and HKDF-SHA256 derivation.
|
||||
*
|
||||
* Canonical compile command:
|
||||
* cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
* -o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
*
|
||||
* With liboqs (post-quantum stack):
|
||||
* cc -std=c11 -I el-compiler/runtime -lcurl -lpthread -loqs -lcrypto \
|
||||
* -o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
*/
|
||||
|
||||
#pragma once
|
||||
|
||||
#include <stdint.h>
|
||||
#include <stdlib.h>
|
||||
|
||||
typedef int64_t el_val_t;
|
||||
|
||||
#define EL_STR(s) ((el_val_t)(uintptr_t)(s))
|
||||
#define EL_CSTR(v) ((const char*)(uintptr_t)(v))
|
||||
#define EL_INT(v) (v)
|
||||
#define EL_NULL ((el_val_t)0)
|
||||
|
||||
/* 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
|
||||
* underlying bits represent the IEEE 754 double. Float-aware builtins
|
||||
* (math, format, json) round-trip via these helpers. */
|
||||
static inline double el_to_float(el_val_t v) {
|
||||
union { int64_t i; double f; } u;
|
||||
u.i = (int64_t)v;
|
||||
return u.f;
|
||||
}
|
||||
|
||||
static inline el_val_t el_from_float(double f) {
|
||||
union { double f; int64_t i; } u;
|
||||
u.f = f;
|
||||
return (el_val_t)u.i;
|
||||
}
|
||||
|
||||
#ifdef __cplusplus
|
||||
extern "C" {
|
||||
#endif
|
||||
|
||||
/* ── I/O ──────────────────────────────────────────────────────────────────── */
|
||||
|
||||
void println(el_val_t s);
|
||||
void print(el_val_t s);
|
||||
el_val_t readline(void);
|
||||
|
||||
/* ── String builtins ─────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_str_concat(el_val_t a, el_val_t b);
|
||||
el_val_t str_eq(el_val_t a, el_val_t b);
|
||||
el_val_t str_starts_with(el_val_t s, el_val_t prefix);
|
||||
el_val_t str_ends_with(el_val_t s, el_val_t suffix);
|
||||
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 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);
|
||||
el_val_t str_to_upper(el_val_t s);
|
||||
el_val_t str_to_lower(el_val_t s);
|
||||
el_val_t str_trim(el_val_t s);
|
||||
|
||||
/* ── Math ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_abs(el_val_t n);
|
||||
el_val_t el_max(el_val_t a, el_val_t b);
|
||||
el_val_t el_min(el_val_t a, el_val_t b);
|
||||
|
||||
/* ── Refcount (ARC) ──────────────────────────────────────────────────────────
|
||||
* Lists and Maps carry a refcount. Strings and ints do not — el_retain and
|
||||
* el_release are safe no-ops on non-refcounted values (they sniff a magic
|
||||
* header at offset 0 and only act if the magic matches).
|
||||
*
|
||||
* Codegen emits these at let-binding shadowing, function entry (params), and
|
||||
* function exit (locals other than the returned value). The refcount lets
|
||||
* el_list_append and el_map_set mutate in place when uniquely owned (cheap)
|
||||
* and copy-on-write when shared (preserves persistent semantics across
|
||||
* accumulator patterns in the compiler itself). */
|
||||
|
||||
void el_retain(el_val_t v);
|
||||
void el_release(el_val_t v);
|
||||
|
||||
/* ── List ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_list_new(el_val_t count, ...);
|
||||
el_val_t el_list_len(el_val_t list);
|
||||
el_val_t el_list_get(el_val_t list, el_val_t index);
|
||||
el_val_t el_list_append(el_val_t list, el_val_t elem);
|
||||
el_val_t el_list_empty(void);
|
||||
el_val_t el_list_clone(el_val_t list);
|
||||
|
||||
/* ── Map ─────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t el_map_new(el_val_t pair_count, ...);
|
||||
el_val_t el_get_field(el_val_t map, el_val_t key);
|
||||
el_val_t el_map_get(el_val_t map, el_val_t key);
|
||||
el_val_t el_map_set(el_val_t map, el_val_t key, el_val_t value);
|
||||
|
||||
/* ── HTTP ─────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t http_get(el_val_t url);
|
||||
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_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);
|
||||
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:
|
||||
*
|
||||
* el_val_t handler(method, path, headers_map, body)
|
||||
*
|
||||
* `headers_map` is an ElMap from lowercased header name → header value (both
|
||||
* Strings). Repeated headers are joined with ", " per RFC 7230.
|
||||
*
|
||||
* Response value: the handler may return either
|
||||
* (a) a plain body string — same auto-content-type / 200-OK behaviour as
|
||||
* http_serve (3-arg) — or
|
||||
* (b) a response envelope built with `http_response(status, headers_json,
|
||||
* body)`. The runtime detects the envelope discriminator
|
||||
* `"el_http_response":1` at the start of the returned string and
|
||||
* unpacks status / headers / body before sending.
|
||||
*
|
||||
* 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. */
|
||||
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
|
||||
* returned string carries the discriminator `{"el_http_response":1,...}`
|
||||
* which the runtime's send-path detects and unpacks. Detection happens
|
||||
* uniformly inside http_send_response, so a 3-arg handler may also return
|
||||
* an envelope. The 3-arg variant remains documented as a fixed 200-OK
|
||||
* 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. */
|
||||
|
||||
/* Streaming variants — write the response body straight to a file via
|
||||
* libcurl's CURLOPT_WRITEFUNCTION = fwrite. These bypass the el_val_t string
|
||||
* wrapper entirely, so binary payloads (audio/mpeg, image/png, etc.) survive
|
||||
* embedded NUL bytes that would truncate a strlen()-based code path.
|
||||
*
|
||||
* Both honor EL_HTTP_TIMEOUT_MS, follow redirects, and accept the same
|
||||
* `headers_map` shape as http_post_with_headers (ElMap of String→String).
|
||||
*
|
||||
* Return value: 1 on success (file fully written), 0 on any failure
|
||||
* (network, file open, partial write). On failure the output file is removed
|
||||
* so callers cannot mistake a partially-written file for a valid one. */
|
||||
el_val_t http_post_to_file(el_val_t url, el_val_t body, el_val_t headers_map, el_val_t output_path);
|
||||
el_val_t http_get_to_file(el_val_t url, el_val_t headers_map, el_val_t output_path);
|
||||
|
||||
/* ── URL encoding ────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t url_encode(el_val_t s); /* RFC 3986 unreserved set */
|
||||
el_val_t url_decode(el_val_t s); /* '+' → space, %XX → byte */
|
||||
|
||||
/* ── HTML allowlist sanitizer ────────────────────────────────────────────────
|
||||
* el_html_sanitize(input_html, allowlist_json) — strict allowlist HTML
|
||||
* cleaner. State-machine parser; tag/attribute names compared case-
|
||||
* insensitively against the allowlist; `<a href>` / `<… src>` URL schemes
|
||||
* validated (http, https, mailto, fragment-only, or relative); whole-
|
||||
* subtree drop for script / style / iframe / object / embed / form; HTML-
|
||||
* escapes free text outside dropped subtrees.
|
||||
*
|
||||
* The allowlist is JSON of the form
|
||||
* {"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);
|
||||
|
||||
/* ── 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_exists(el_val_t path);
|
||||
el_val_t fs_mkdir(el_val_t path); /* mkdir -p, mode 0755 */
|
||||
|
||||
/* Length-explicit binary write. `length` is an Int (el_val_t holding the
|
||||
* byte count). The caller knows the length from context — typically because
|
||||
* `bytes` came from base64_decode (which produces a magic-tagged binary
|
||||
* buffer with embedded NULs possible) and the caller already tracks the
|
||||
* decoded length, OR because the bytes came from a fixed-size source
|
||||
* (sha256_bytes = 32, hmac_sha256_bytes = 32). Bypasses strlen entirely.
|
||||
*
|
||||
* Returns 1 on success, 0 on failure (invalid path, can't open, partial
|
||||
* write, negative length). On partial-write failure, the file is removed
|
||||
* so callers cannot read back a truncated artefact. */
|
||||
el_val_t fs_write_bytes(el_val_t path, el_val_t bytes, el_val_t length);
|
||||
|
||||
/* ── JSON ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t json_get(el_val_t json, el_val_t key);
|
||||
el_val_t json_parse(el_val_t s);
|
||||
el_val_t json_stringify(el_val_t v);
|
||||
el_val_t json_get_string(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_int(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_float(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_bool(el_val_t json_str, el_val_t key);
|
||||
el_val_t json_get_raw(el_val_t json_str, el_val_t key);
|
||||
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);
|
||||
|
||||
/* ── Time ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t time_now(void);
|
||||
el_val_t time_now_utc(void);
|
||||
el_val_t sleep_secs(el_val_t secs);
|
||||
el_val_t sleep_ms(el_val_t ms);
|
||||
el_val_t time_format(el_val_t ts, el_val_t fmt);
|
||||
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);
|
||||
|
||||
/* ── Instant + Duration: first-class temporal types ──────────────────────────
|
||||
* Both types share the el_val_t (int64) slot. Instants are nanoseconds
|
||||
* since the Unix epoch; Durations are signed nanoseconds. Type discipline
|
||||
* is enforced at codegen-time: BinOps on names registered as Instant or
|
||||
* Duration route through the typed wrappers below; mismatches like
|
||||
* Instant+Instant become #error at the C compiler.
|
||||
*
|
||||
* Postfix literals — `30.seconds`, `1.hour`, `500.millis`, `30.nanos` — are
|
||||
* recognised by the parser as DurationLit AST nodes and lowered to literal
|
||||
* int64 nanoseconds at codegen time. The runtime never sees the units. */
|
||||
|
||||
el_val_t el_now_instant(void);
|
||||
el_val_t now(void);
|
||||
el_val_t unix_seconds(el_val_t n);
|
||||
el_val_t unix_millis(el_val_t n);
|
||||
el_val_t instant_from_iso8601(el_val_t s);
|
||||
|
||||
el_val_t el_duration_from_nanos(el_val_t ns);
|
||||
el_val_t duration_seconds(el_val_t n);
|
||||
el_val_t duration_millis(el_val_t n);
|
||||
el_val_t duration_nanos(el_val_t n);
|
||||
|
||||
el_val_t el_instant_add_dur(el_val_t inst, el_val_t dur);
|
||||
el_val_t el_instant_sub_dur(el_val_t inst, el_val_t dur);
|
||||
el_val_t el_instant_diff(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_add(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_sub(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_scale(el_val_t dur, el_val_t scalar);
|
||||
el_val_t el_duration_div(el_val_t dur, el_val_t scalar);
|
||||
|
||||
el_val_t el_instant_lt(el_val_t a, el_val_t b);
|
||||
el_val_t el_instant_le(el_val_t a, el_val_t b);
|
||||
el_val_t el_instant_gt(el_val_t a, el_val_t b);
|
||||
el_val_t el_instant_ge(el_val_t a, el_val_t b);
|
||||
el_val_t el_instant_eq(el_val_t a, el_val_t b);
|
||||
el_val_t el_instant_ne(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_lt(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_le(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_gt(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_ge(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_eq(el_val_t a, el_val_t b);
|
||||
el_val_t el_duration_ne(el_val_t a, el_val_t b);
|
||||
|
||||
el_val_t instant_to_unix_seconds(el_val_t i);
|
||||
el_val_t instant_to_unix_millis(el_val_t i);
|
||||
el_val_t instant_to_iso8601(el_val_t i);
|
||||
el_val_t duration_to_seconds(el_val_t d);
|
||||
el_val_t duration_to_millis(el_val_t d);
|
||||
el_val_t duration_to_nanos(el_val_t d);
|
||||
|
||||
el_val_t el_sleep_duration(el_val_t dur);
|
||||
el_val_t unix_timestamp(void);
|
||||
|
||||
el_val_t ttl_cache_set(el_val_t key, el_val_t value);
|
||||
el_val_t ttl_cache_get(el_val_t key, el_val_t max_age);
|
||||
el_val_t ttl_cache_age(el_val_t key);
|
||||
|
||||
/* ── Calendar + CalendarTime + Rhythm + LocalDate/Time/DateTime ─────────────
|
||||
* Phase 1.5 of the time system. Calendar is pluggable: EarthCalendar (IANA
|
||||
* zones, Gregorian, DST) is the user-facing default; MarsCalendar,
|
||||
* CycleCalendar(period), NoCycleCalendar, RelativeCalendar handle non-Earth
|
||||
* domains.
|
||||
*
|
||||
* A Calendar interprets an Instant under a particular cycle convention and
|
||||
* produces a CalendarTime. CalendarTime carries the underlying Instant and
|
||||
* a back-pointer to its Calendar; arithmetic and formatting consult the
|
||||
* Calendar to convert ns since epoch into year/month/day/hour/minute/second
|
||||
* (or sol/phase, or cycle/phase, depending on kind).
|
||||
*
|
||||
* Storage convention: Calendar / CalendarTime / Rhythm / LocalDate /
|
||||
* LocalDateTime are heap-allocated structs whose pointers are cast into
|
||||
* el_val_t. A 24-bit magic header at offset 0 lets the runtime identify
|
||||
* the kind safely. LocalTime is small enough to live in the int64 slot
|
||||
* directly (nanos since midnight, signed). */
|
||||
|
||||
/* Zone — opaque IANA zone or fixed offset, used by EarthCalendar.
|
||||
* `zone_id` is either an IANA name ("America/New_York", "UTC") or a fixed
|
||||
* offset string ("+05:30", "-08:00"). The runtime resolves it via tzset()
|
||||
* on first use of the owning EarthCalendar. */
|
||||
el_val_t zone(el_val_t id);
|
||||
el_val_t zone_utc(void);
|
||||
el_val_t zone_local(void);
|
||||
el_val_t zone_offset(el_val_t hours, el_val_t minutes);
|
||||
|
||||
/* Calendar constructors. Each returns an el_val_t pointer to a heap-
|
||||
* allocated, magic-tagged Calendar struct. Calendars are interned by
|
||||
* (kind, zone_id, period_ns, epoch_ns) so identical constructors return
|
||||
* the same pointer — equality is reference equality. */
|
||||
el_val_t earth_calendar(el_val_t z);
|
||||
el_val_t earth_calendar_default(void);
|
||||
el_val_t mars_calendar(void);
|
||||
el_val_t cycle_calendar(el_val_t period_dur);
|
||||
el_val_t no_cycle_calendar(void);
|
||||
el_val_t relative_calendar(el_val_t epoch_inst);
|
||||
|
||||
/* CalendarTime constructors and methods. Returns a heap-allocated struct
|
||||
* whose pointer fits in el_val_t. */
|
||||
el_val_t now_in(el_val_t cal);
|
||||
el_val_t in_calendar(el_val_t inst, el_val_t cal);
|
||||
el_val_t cal_format(el_val_t ct, el_val_t pattern);
|
||||
el_val_t cal_to_instant(el_val_t ct);
|
||||
el_val_t cal_cycle_phase(el_val_t ct);
|
||||
el_val_t cal_in(el_val_t ct, el_val_t cal);
|
||||
|
||||
/* LocalDate / LocalTime / LocalDateTime — calendar-agnostic value types.
|
||||
* LocalTime carries nanoseconds since midnight as a signed int64 directly
|
||||
* in the el_val_t slot (no allocation). LocalDate / LocalDateTime are
|
||||
* heap-allocated structs with magic headers. */
|
||||
el_val_t local_date(el_val_t y, el_val_t m, el_val_t d);
|
||||
el_val_t local_time(el_val_t h, el_val_t m, el_val_t s, el_val_t ns);
|
||||
el_val_t local_datetime(el_val_t date, el_val_t time);
|
||||
el_val_t zoned(el_val_t date, el_val_t time, el_val_t cal);
|
||||
|
||||
el_val_t local_date_year(el_val_t ld);
|
||||
el_val_t local_date_month(el_val_t ld);
|
||||
el_val_t local_date_day(el_val_t ld);
|
||||
el_val_t local_time_hour(el_val_t lt);
|
||||
el_val_t local_time_minute(el_val_t lt);
|
||||
el_val_t local_time_second(el_val_t lt);
|
||||
el_val_t local_time_nanos(el_val_t lt);
|
||||
|
||||
el_val_t el_local_date_add_dur(el_val_t ld, el_val_t dur);
|
||||
el_val_t el_local_time_add_dur(el_val_t lt, el_val_t dur);
|
||||
el_val_t el_local_date_lt(el_val_t a, el_val_t b);
|
||||
el_val_t el_local_date_eq(el_val_t a, el_val_t b);
|
||||
|
||||
/* Rhythm — pluggable recurrence AST. Returns a heap-allocated struct
|
||||
* pointer in el_val_t; rhythms are immutable so callers may share them. */
|
||||
el_val_t rhythm_cycle_start(void);
|
||||
el_val_t rhythm_cycle_phase(el_val_t phase);
|
||||
el_val_t rhythm_duration(el_val_t d);
|
||||
el_val_t rhythm_session_start(void);
|
||||
el_val_t rhythm_event(el_val_t name);
|
||||
el_val_t rhythm_and(el_val_t a, el_val_t b);
|
||||
el_val_t rhythm_or(el_val_t a, el_val_t b);
|
||||
el_val_t rhythm_weekday(el_val_t day);
|
||||
el_val_t rhythm_weekly_at(el_val_t day, el_val_t hour, el_val_t minute);
|
||||
el_val_t rhythm_next_after(el_val_t r, el_val_t after, el_val_t cal);
|
||||
el_val_t rhythm_matches(el_val_t r, el_val_t ct);
|
||||
|
||||
/* ── UUID ────────────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t uuid_new(void);
|
||||
el_val_t uuid_v4(void);
|
||||
|
||||
/* ── Environment ─────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t env(el_val_t key);
|
||||
|
||||
/* ── In-process state K/V ────────────────────────────────────────────────── */
|
||||
|
||||
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);
|
||||
|
||||
/* ── Float formatting ────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t float_to_str(el_val_t f);
|
||||
el_val_t int_to_float(el_val_t n);
|
||||
el_val_t float_to_int(el_val_t f);
|
||||
el_val_t format_float(el_val_t f, el_val_t decimals);
|
||||
el_val_t decimal_round(el_val_t f, el_val_t decimals);
|
||||
el_val_t str_to_float(el_val_t s);
|
||||
|
||||
/* ── Math (Float-aware) ──────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t math_sqrt(el_val_t f);
|
||||
el_val_t math_log(el_val_t f);
|
||||
el_val_t math_ln(el_val_t f);
|
||||
el_val_t math_sin(el_val_t f);
|
||||
el_val_t math_cos(el_val_t f);
|
||||
el_val_t math_pi(void);
|
||||
|
||||
/* ── String additions ────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t str_index_of(el_val_t s, el_val_t sub);
|
||||
el_val_t str_split(el_val_t s, el_val_t sep);
|
||||
el_val_t str_char_at(el_val_t s, el_val_t i);
|
||||
el_val_t str_char_code(el_val_t s, el_val_t i);
|
||||
el_val_t str_pad_left(el_val_t s, el_val_t width, el_val_t pad);
|
||||
el_val_t str_pad_right(el_val_t s, el_val_t width, el_val_t pad);
|
||||
el_val_t str_format(el_val_t fmt, el_val_t data);
|
||||
el_val_t str_lower(el_val_t s);
|
||||
el_val_t str_upper(el_val_t s);
|
||||
|
||||
/* ── Text-processing primitives (Phase 1: byte/codepoint, ASCII char classes)
|
||||
* Phase 2 (filed): Unicode-grapheme awareness, NFC/NFD normalization, regex.
|
||||
* is_* predicates: empty input returns false; multi-char requires ALL bytes
|
||||
* to match. ASCII ranges only in Phase 1. */
|
||||
|
||||
/* Counting */
|
||||
el_val_t str_count(el_val_t s, el_val_t sub); /* non-overlapping */
|
||||
el_val_t str_count_chars(el_val_t s); /* codepoint count */
|
||||
el_val_t str_count_bytes(el_val_t s); /* alias of str_len */
|
||||
el_val_t str_count_lines(el_val_t s);
|
||||
el_val_t str_count_words(el_val_t s);
|
||||
el_val_t str_count_letters(el_val_t s); /* ASCII [A-Za-z] */
|
||||
el_val_t str_count_digits(el_val_t s); /* ASCII [0-9] */
|
||||
|
||||
/* Find / position */
|
||||
el_val_t str_index_of_all(el_val_t s, el_val_t sub); /* [Int] of byte offsets */
|
||||
el_val_t str_last_index_of(el_val_t s, el_val_t sub);
|
||||
el_val_t str_find_chars(el_val_t s, el_val_t any_of); /* first idx of any ch */
|
||||
|
||||
/* Transform */
|
||||
el_val_t str_repeat(el_val_t s, el_val_t n);
|
||||
el_val_t str_reverse(el_val_t s); /* by codepoint */
|
||||
el_val_t str_strip_prefix(el_val_t s, el_val_t prefix);
|
||||
el_val_t str_strip_suffix(el_val_t s, el_val_t suffix);
|
||||
el_val_t str_strip_chars(el_val_t s, el_val_t chars);
|
||||
el_val_t str_lstrip(el_val_t s);
|
||||
el_val_t str_rstrip(el_val_t s);
|
||||
|
||||
/* Char classification (Bool) */
|
||||
el_val_t is_letter(el_val_t s);
|
||||
el_val_t is_digit(el_val_t s);
|
||||
el_val_t is_alphanumeric(el_val_t s);
|
||||
el_val_t is_whitespace(el_val_t s);
|
||||
el_val_t is_punctuation(el_val_t s);
|
||||
el_val_t is_uppercase(el_val_t s);
|
||||
el_val_t is_lowercase(el_val_t s);
|
||||
|
||||
/* Split / join */
|
||||
el_val_t str_split_lines(el_val_t s);
|
||||
el_val_t str_split_chars(el_val_t s); /* alias of native_string_chars */
|
||||
el_val_t str_split_n(el_val_t s, el_val_t sep, el_val_t n);
|
||||
el_val_t str_join(el_val_t list, el_val_t sep); /* alias of list_join */
|
||||
|
||||
/* ── List additions ──────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t list_push(el_val_t list, el_val_t elem);
|
||||
el_val_t list_push_front(el_val_t list, el_val_t elem);
|
||||
el_val_t list_join(el_val_t list, el_val_t sep);
|
||||
el_val_t list_range(el_val_t start, el_val_t end);
|
||||
|
||||
/* ── Bool helpers ────────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t bool_to_str(el_val_t b);
|
||||
|
||||
/* ── Numeric parsing ─────────────────────────────────────────────────────── */
|
||||
|
||||
el_val_t parse_int(el_val_t s, el_val_t default_val);
|
||||
|
||||
/* ── Process ─────────────────────────────────────────────────────────────── */
|
||||
|
||||
void exit_program(el_val_t code);
|
||||
el_val_t getpid_now(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. */
|
||||
|
||||
void el_cgi_init(el_val_t name, el_val_t dharma_id, el_val_t principal,
|
||||
el_val_t network, el_val_t engram);
|
||||
|
||||
/* ── DHARMA network builtins ─────────────────────────────────────────────────
|
||||
* Available to CGI programs (declared with a `cgi {}` block).
|
||||
*
|
||||
* Peers are addressed by `dharma_id` of the form
|
||||
* "<registry-id>@<transport-url>" e.g. "ntn-genesis@http://localhost:7770"
|
||||
* If the @<url> portion is omitted, transport defaults to
|
||||
* "http://localhost:7770" (the local CGI daemon assumption).
|
||||
*
|
||||
* Wire protocol (all peers expose):
|
||||
* POST <url>/dharma/recv { channel, from, content } → response body
|
||||
* POST <url>/dharma/event { type, payload, source, timestamp }
|
||||
* POST <url>/api/activate { query } → list of nodes
|
||||
*
|
||||
* Hosting application's responsibility: an El program with a `cgi {}` block
|
||||
* runs http_serve() with its own request handler; that handler should route
|
||||
* "/dharma/event" requests by calling el_runtime_dharma_event_arrive() so
|
||||
* incoming events feed dharma_field() queues. The runtime itself does not
|
||||
* intercept any /dharma path. */
|
||||
|
||||
el_val_t dharma_connect(el_val_t cgi_id);
|
||||
el_val_t dharma_send(el_val_t channel, el_val_t content);
|
||||
el_val_t dharma_activate(el_val_t query);
|
||||
void dharma_emit(el_val_t event_type, el_val_t payload);
|
||||
el_val_t dharma_field(el_val_t event_type);
|
||||
void dharma_strengthen(el_val_t cgi_id, el_val_t weight);
|
||||
el_val_t dharma_relationship(el_val_t cgi_id);
|
||||
el_val_t dharma_peers(void);
|
||||
|
||||
/* Public C API: called by an El program's HTTP handler when a /dharma/event
|
||||
* request arrives. Pushes onto the per-event-type queue and signals any
|
||||
* pending dharma_field() blockers. All three arguments must be NUL-terminated
|
||||
* C strings (or NULL — then treated as empty). */
|
||||
void el_runtime_dharma_event_arrive(const char* event_type,
|
||||
const char* payload,
|
||||
const char* source);
|
||||
|
||||
/* ── Engram local graph primitives ───────────────────────────────────────────
|
||||
* Operate on the CGI's local Engram knowledge graph.
|
||||
* `engram_activate` queries the local graph only; `dharma_activate` is
|
||||
* network-wide across all connected CGI graphs. */
|
||||
|
||||
el_val_t engram_node(el_val_t content, el_val_t node_type, el_val_t salience);
|
||||
el_val_t engram_node_full(el_val_t content, el_val_t node_type, el_val_t label,
|
||||
el_val_t salience, el_val_t importance, el_val_t confidence,
|
||||
el_val_t tier, el_val_t tags);
|
||||
/* Layered consciousness — see el_runtime.c for the layered architecture
|
||||
* design notes (search "Layered consciousness architecture"). The five
|
||||
* canonical layers (safety / core-identity / domain-knowledge / imprint /
|
||||
* suit) are seeded automatically; engram_add_layer extends the registry
|
||||
* with imprint or suit overlays at runtime. Nodes default to layer 1
|
||||
* (core-identity) when created via engram_node / engram_node_full. */
|
||||
el_val_t engram_node_layered(el_val_t content, el_val_t node_type, el_val_t label,
|
||||
el_val_t salience, el_val_t certainty, el_val_t confidence,
|
||||
el_val_t status, el_val_t tags, el_val_t layer_id);
|
||||
el_val_t engram_add_layer(el_val_t name, el_val_t priority, el_val_t suppressible,
|
||||
el_val_t transparent, el_val_t injectable);
|
||||
el_val_t engram_remove_layer(el_val_t layer_id);
|
||||
el_val_t engram_list_layers(void);
|
||||
el_val_t engram_get_node(el_val_t id);
|
||||
void engram_strengthen(el_val_t node_id);
|
||||
void engram_forget(el_val_t node_id);
|
||||
el_val_t engram_node_count(void);
|
||||
el_val_t engram_search(el_val_t query, el_val_t limit);
|
||||
el_val_t engram_scan_nodes(el_val_t limit, el_val_t offset);
|
||||
void engram_connect(el_val_t from_id, el_val_t to_id, el_val_t weight, el_val_t relation);
|
||||
el_val_t engram_edge_between(el_val_t from_id, el_val_t to_id);
|
||||
el_val_t engram_neighbors(el_val_t node_id);
|
||||
el_val_t engram_neighbors_filtered(el_val_t node_id, el_val_t max_depth, el_val_t direction);
|
||||
el_val_t engram_edge_count(void);
|
||||
/* Three-pass activation: background fan-out → working-memory promotion →
|
||||
* Layer 0 override. See "Three-pass activation" in el_runtime.c. */
|
||||
el_val_t engram_activate(el_val_t query, el_val_t depth);
|
||||
el_val_t engram_save(el_val_t path);
|
||||
el_val_t engram_load(el_val_t path);
|
||||
|
||||
/* JSON-string accessors — return pre-serialized JSON so HTTP handlers
|
||||
* can pass results straight through without round-tripping ElList/ElMap
|
||||
* through json_stringify. */
|
||||
el_val_t engram_get_node_json(el_val_t id);
|
||||
el_val_t engram_search_json(el_val_t query, el_val_t limit);
|
||||
el_val_t engram_scan_nodes_json(el_val_t limit, el_val_t offset);
|
||||
el_val_t engram_scan_nodes_by_type_json(el_val_t node_type, el_val_t limit, el_val_t offset);
|
||||
el_val_t engram_neighbors_json(el_val_t node_id, el_val_t max_depth, el_val_t direction);
|
||||
el_val_t engram_activate_json(el_val_t query, el_val_t depth);
|
||||
el_val_t engram_stats_json(void);
|
||||
el_val_t engram_list_layers_json(void);
|
||||
/* engram_compile_layered_json — produce a prompt-ready text block split
|
||||
* into "[LAYER 0 — STRUCTURAL]" (non-suppressible layers, sacred fire)
|
||||
* and "[ENGRAM CONTEXT]" (standard suppressible layers). Returns "" if
|
||||
* no nodes promoted to working memory. */
|
||||
el_val_t engram_compile_layered_json(el_val_t intent, el_val_t depth);
|
||||
|
||||
/* ── LLM (Anthropic API client) ─────────────────────────────────────────────
|
||||
* All functions call https://api.anthropic.com/v1/messages with the API key
|
||||
* from env ANTHROPIC_API_KEY. Default model when empty: claude-sonnet-4-5. */
|
||||
|
||||
el_val_t llm_call(el_val_t model, el_val_t prompt);
|
||||
el_val_t llm_call_system(el_val_t model, el_val_t system_prompt, el_val_t user_prompt);
|
||||
el_val_t llm_call_agentic(el_val_t model, el_val_t system, el_val_t user, el_val_t tools);
|
||||
el_val_t llm_vision(el_val_t model, el_val_t system, el_val_t prompt, el_val_t image_url_or_b64);
|
||||
el_val_t llm_models(void);
|
||||
|
||||
/* Register a tool handler by name. The handler is looked up via dlsym
|
||||
* (mirroring http_set_handler), so any El `fn <name>(input)` compiles to
|
||||
* a global C symbol that this function can locate at runtime.
|
||||
* Handler signature: `el_val_t handler(el_val_t input_json)` — receives
|
||||
* the tool input as a JSON-string el_val_t and returns a JSON-string
|
||||
* el_val_t result. Used by llm_call_agentic. */
|
||||
void llm_register_tool(el_val_t name, el_val_t handler_fn_name);
|
||||
|
||||
/* ── args() ─────────────────────────────────────────────────────────────────
|
||||
* Provides access to command-line arguments passed to the program.
|
||||
* Populated by el_runtime_init_args() before main() runs. */
|
||||
|
||||
el_val_t args(void);
|
||||
void el_runtime_init_args(int argc, char** argv);
|
||||
|
||||
/* ── Crypto primitives ─────────────────────────────────────────────────────
|
||||
* SHA-256, HMAC-SHA-256, and base64 (standard + URL-safe).
|
||||
* Self-contained — no OpenSSL/libcrypto dependency. The implementations are
|
||||
* adapted from public-domain reference code (Brad Conte / RFC 4648).
|
||||
*
|
||||
* Bytes-returning variants (sha256_bytes, hmac_sha256_bytes) return a string
|
||||
* value whose contents are raw binary; callers usually feed these into
|
||||
* base64_encode. Note that el_val_t strings are NUL-terminated by convention,
|
||||
* so the binary payload may contain embedded NULs — pass it directly into
|
||||
* base64_encode (which uses an explicit length) rather than treating it as
|
||||
* a printable C string.
|
||||
*
|
||||
* The "base64" variants emit/accept RFC 4648 standard alphabet with padding.
|
||||
* The "base64url" variants use URL-safe alphabet (`-`/`_`) with no padding,
|
||||
* as used in JWTs. */
|
||||
|
||||
el_val_t sha256_hex(el_val_t input);
|
||||
el_val_t sha256_bytes(el_val_t input);
|
||||
el_val_t hmac_sha256_hex(el_val_t key, el_val_t message);
|
||||
el_val_t hmac_sha256_bytes(el_val_t key, el_val_t message);
|
||||
el_val_t base64_encode(el_val_t input);
|
||||
el_val_t base64_decode(el_val_t input);
|
||||
el_val_t base64url_encode(el_val_t input);
|
||||
el_val_t base64url_decode(el_val_t input);
|
||||
|
||||
/* Length-aware variants (internal — exposed for the rare caller that already
|
||||
* has a known-length binary buffer and doesn't want to round-trip through
|
||||
* a NUL-terminated el_val_t string). Sha256_bytes and hmac_sha256_bytes feed
|
||||
* these implicitly. */
|
||||
el_val_t el_sha256_bytes_n(const unsigned char* data, size_t len);
|
||||
el_val_t el_base64_encode_n(const unsigned char* data, size_t len, int url_safe);
|
||||
|
||||
/* ── Post-quantum primitives (liboqs-backed) ────────────────────────────────
|
||||
* All inputs/outputs hex-encoded. Algorithm choices:
|
||||
* Signature: CRYSTALS-Dilithium-3 (NIST level 3, balanced)
|
||||
* KEM: CRYSTALS-Kyber-768 (NIST level 3)
|
||||
* Hash: SHA3-256 (Keccak) (PQ-aware protocols favour SHA3 over SHA2)
|
||||
*
|
||||
* If liboqs is not linked (detected via __has_include(<oqs/oqs.h>) at compile
|
||||
* time), the pq_* entry points return a JSON-shaped error string so callers
|
||||
* fail loudly rather than silently fall back to classical schemes:
|
||||
* {"error":"liboqs not linked, post-quantum primitives unavailable"}
|
||||
*
|
||||
* The hybrid handshake pairs X25519 with Kyber-768 per NIST PQ guidance and
|
||||
* CNSA 2.0. Combined shared secret is HKDF-SHA256(x25519_ss || kyber_ss).
|
||||
* Even if Kyber falls, X25519 holds; if X25519 falls under quantum attack,
|
||||
* Kyber holds. SHA3-256 also remains usable independent of liboqs (the
|
||||
* Keccak permutation is PQ-OK as a primitive). */
|
||||
|
||||
el_val_t pq_keygen_signature(void);
|
||||
el_val_t pq_sign(el_val_t secret_key_hex, el_val_t message);
|
||||
el_val_t pq_verify(el_val_t public_key_hex, el_val_t message, el_val_t signature_hex);
|
||||
|
||||
el_val_t pq_kem_keygen(void);
|
||||
el_val_t pq_kem_encaps(el_val_t public_key_hex);
|
||||
el_val_t pq_kem_decaps(el_val_t secret_key_hex, el_val_t ciphertext_hex);
|
||||
|
||||
el_val_t pq_hybrid_keygen(void);
|
||||
el_val_t pq_hybrid_handshake(el_val_t remote_pub_combined);
|
||||
|
||||
el_val_t sha3_256_hex(el_val_t input);
|
||||
|
||||
/* ── AEAD: AES-256-GCM (libcrypto-backed) ───────────────────────────────────
|
||||
* Symmetric authenticated encryption used to wrap envelopes after a KEM
|
||||
* handshake. Caller MUST supply a 32-byte key (64 hex chars) — typically the
|
||||
* Kyber-768 / hybrid shared_secret, optionally normalized via SHA3-256.
|
||||
*
|
||||
* aead_encrypt returns a JSON map {"nonce":"...","ciphertext":"..."} where
|
||||
* ciphertext is the AES-256-GCM output with the 16-byte auth tag appended.
|
||||
* Nonce is a fresh 12-byte CSPRNG draw — callers never pick the nonce, which
|
||||
* structurally rules out the GCM nonce-reuse footgun.
|
||||
*
|
||||
* aead_decrypt returns the plaintext String, or "" on any failure (including
|
||||
* auth-tag mismatch). Callers MUST check for "" before trusting the result. */
|
||||
el_val_t aead_encrypt(el_val_t key_hex, el_val_t plaintext);
|
||||
el_val_t aead_decrypt(el_val_t key_hex, el_val_t nonce_hex, el_val_t ciphertext_hex);
|
||||
|
||||
/* ── Native VM builtin aliases (for compiled El source) ─────────────────────
|
||||
* These match the El VM's native_* builtins so that El source compiled
|
||||
* to C can call the same names without modification. */
|
||||
|
||||
el_val_t native_list_get(el_val_t list, el_val_t index);
|
||||
el_val_t native_list_len(el_val_t list);
|
||||
el_val_t native_list_append(el_val_t list, el_val_t elem);
|
||||
el_val_t native_list_empty(void);
|
||||
el_val_t native_list_clone(el_val_t list);
|
||||
el_val_t native_string_chars(el_val_t s);
|
||||
el_val_t native_int_to_str(el_val_t n);
|
||||
|
||||
/* ── Method-call shorthand aliases ──────────────────────────────────────────
|
||||
* The El method-call convention `obj.method(args)` compiles to
|
||||
* `method(obj, args)`. These aliases expose the runtime functions under
|
||||
* the short names that result from method calls in El source.
|
||||
*
|
||||
* Example: `myList.append(x)` → `append(myList, x)` (calls this alias)
|
||||
* `myList.len()` → `len(myList)` (calls this alias) */
|
||||
|
||||
el_val_t append(el_val_t list, el_val_t elem); /* el_list_append */
|
||||
el_val_t len(el_val_t list); /* el_list_len */
|
||||
el_val_t get(el_val_t list, el_val_t index); /* el_list_get */
|
||||
el_val_t map_get(el_val_t map, el_val_t key); /* el_map_get */
|
||||
el_val_t map_set(el_val_t map, el_val_t key, el_val_t value); /* el_map_set */
|
||||
|
||||
/* ── OTLP/HTTP Observability ─────────────────────────────────────────────── */
|
||||
/* See bottom of el_runtime.c for the implementation.
|
||||
* Configured by env vars OTLP_ENDPOINT, OTEL_SERVICE_NAME, OTEL_SERVICE_VERSION.
|
||||
* No-op when OTLP_ENDPOINT is unset. Drop-on-failure semantics. */
|
||||
/* ── Subprocess execution ────────────────────────────────────────────────── */
|
||||
el_val_t exec_command(el_val_t cmd); /* run shell command, return exit code */
|
||||
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) */
|
||||
|
||||
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);
|
||||
|
||||
#ifdef __cplusplus
|
||||
}
|
||||
#endif
|
||||
@@ -1202,7 +1202,7 @@ 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/el-compiler/runtime/el_runtime.js")
|
||||
js_emit_line("// Runtime: foundation/el/runtime/el_runtime.js")
|
||||
js_emit_line("import \"./el_runtime.js\";")
|
||||
}
|
||||
// In module mode: destructure all builtins off globalThis.__el so call
|
||||
|
||||
+3
-3
@@ -368,13 +368,13 @@ 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 + "/../el-compiler/runtime/el_runtime.c"
|
||||
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/el-compiler/runtime (directory form)
|
||||
// --runtime=/opt/el/el-compiler/runtime/el_runtime.c (file form)
|
||||
// --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") {
|
||||
|
||||
@@ -6,8 +6,8 @@
|
||||
//
|
||||
// Compile and run:
|
||||
// ./dist/platform/elc examples/html-page.el > /tmp/html-page.c
|
||||
// cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
// -o /tmp/html-page /tmp/html-page.c el-compiler/runtime/el_runtime.c
|
||||
// cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
// -o /tmp/html-page /tmp/html-page.c runtime/el_runtime.c
|
||||
// /tmp/html-page
|
||||
|
||||
fn render_item(item: String) -> String {
|
||||
|
||||
@@ -1,28 +0,0 @@
|
||||
# El Compiler Release v1.0.0 — 2026-05-02
|
||||
|
||||
## Components
|
||||
- `bootstrap.py` — El language compiler (Python, recursive descent parser, emits C)
|
||||
- `el_runtime.c` — El runtime (C, HTTP server, engram, DHARMA, LLM chain)
|
||||
- `el_runtime.h` — Runtime public API header
|
||||
|
||||
## Changes in this release
|
||||
|
||||
### Critical bug fixes
|
||||
- `state_set`/`state_get` are now thread-safe (pthread_mutex). Was racing across 64 worker threads.
|
||||
- `looks_like_string` threshold raised from 1,000,000 to 4GB. Unix timestamps were being dereferenced as heap pointers.
|
||||
- `fs_read` guards against negative `ftell` result (pipe/special file overflow).
|
||||
|
||||
### Engram architecture (major)
|
||||
- Two-layer activation: `background_activation` (Layer 1, broad fan-out) + `working_memory_weight` (Layer 2, executive filter)
|
||||
- Inhibitory edges: `EngramEdge.inhibitory` flag suppresses working memory promotion without affecting background activation
|
||||
- Suppression memory: `suppression_count` — nodes activated-but-suppressed accumulate pressure toward breakthrough
|
||||
- Temporal decay: `temporal_decay_rate`, `created_at`, `last_activated_at`, `activation_count` on EngramNode
|
||||
- Per-type activation thresholds (Safety: 0.05, Canonical: 0.15, Lesson: 0.25, Note: 0.40)
|
||||
- Temporal range query: `engram_query_range(start_ms, end_ms)`
|
||||
- Layered consciousness: `EngramLayer` struct, `layer_id` on nodes and edges, `EngramStore.layers[]`
|
||||
- Layer 0 override pass: safety layer fires last and cannot be suppressed
|
||||
|
||||
## SHA256
|
||||
bootstrap.py
|
||||
el_runtime.c
|
||||
el_runtime.h
|
||||
@@ -132,7 +132,7 @@ if [[ $LVGL_OK -eq 1 ]]; then
|
||||
else
|
||||
_miss "LVGL/MCU" "-DEL_TARGET_LVGL (lvgl.h not found)"
|
||||
echo " Install: git clone https://github.com/lvgl/lvgl"
|
||||
echo " (place lvgl/ next to el-compiler/runtime/)"
|
||||
echo " (place lvgl/ next to runtime/)"
|
||||
MISSING=$((MISSING + 1))
|
||||
fi
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -34,12 +34,12 @@
|
||||
* pq_hybrid_* and HKDF-SHA256 derivation.
|
||||
*
|
||||
* Canonical compile command:
|
||||
* cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
* -o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
* cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
* -o <out> <prog>.c runtime/el_runtime.c
|
||||
*
|
||||
* With liboqs (post-quantum stack):
|
||||
* cc -std=c11 -I el-compiler/runtime -lcurl -lpthread -loqs -lcrypto \
|
||||
* -o <out> <prog>.c el-compiler/runtime/el_runtime.c
|
||||
* cc -std=c11 -I runtime -lcurl -lpthread -loqs -lcrypto \
|
||||
* -o <out> <prog>.c runtime/el_runtime.c
|
||||
*/
|
||||
|
||||
#pragma once
|
||||
@@ -628,22 +628,30 @@ el_val_t engram_hebb_drain_json(el_val_t max);
|
||||
/* Document frequency of a term across node labels — term-specificity signal
|
||||
* for curiosity seed selection. (2026-08-03 self-review.) */
|
||||
el_val_t engram_label_df(el_val_t term);
|
||||
/* Best curiosity seed from one node: argmax over idf·position·casing across
|
||||
* the candidate tokens of its label, falling back to its content when the
|
||||
* label is a sentinel. Excludes pipe-delimited tabu terms during selection
|
||||
* and gates candidates to the df band [min_df, max_df]. Returns "" when
|
||||
* nothing qualifies. (2026-08-13 self-review.) */
|
||||
el_val_t engram_salient_term(el_val_t node_id, el_val_t max_df,
|
||||
el_val_t min_df, el_val_t tabu);
|
||||
el_val_t engram_embed_backfill(el_val_t count);
|
||||
el_val_t engram_list_layers_json(void);
|
||||
/* Working memory introspection — count, mean weight, and top-N snapshot.
|
||||
* Ported from el-compiler/runtime on 2026-06-30 self-review. */
|
||||
* Ported from runtime on 2026-06-30 self-review. */
|
||||
el_val_t engram_wm_count(void);
|
||||
el_val_t engram_wm_avg_weight(void);
|
||||
el_val_t engram_wm_top_json(el_val_t n);
|
||||
/* Merge-load: add nodes/edges from a snapshot without resetting the store. */
|
||||
el_val_t engram_load_merge(el_val_t path);
|
||||
|
||||
/* ── WAL + compaction + integrity (ENGRAM_WAL=on; design doc §§3-14,§18) ──── */
|
||||
int engram_wal_enabled(void);
|
||||
el_val_t engram_crc32(el_val_t s);
|
||||
el_val_t engram_wal_boot(el_val_t dir); /* replay + open; returns records */
|
||||
el_val_t engram_wal_open_dir(el_val_t dir);
|
||||
el_val_t engram_wal_node_put(el_val_t dir, el_val_t id);
|
||||
el_val_t engram_wal_edges_since(el_val_t dir, el_val_t start_count);
|
||||
el_val_t engram_wal_hebb_batch(el_val_t dir, el_val_t start_count);
|
||||
el_val_t engram_wal_forget(el_val_t dir, el_val_t id);
|
||||
el_val_t engram_wal_compact(el_val_t dir);
|
||||
el_val_t engram_wal_maybe_compact(el_val_t dir);
|
||||
el_val_t engram_resolve_data_dir(void); /* §18.2 fail-loud default */
|
||||
el_val_t engram_is_protected(el_val_t id); /* §18.1/18.3 derived set */
|
||||
el_val_t engram_protected_json(void);
|
||||
/* engram_compile_layered_json — produce a prompt-ready text block split
|
||||
* into "[LAYER 0 — STRUCTURAL]" (non-suppressible layers, sacred fire)
|
||||
* and "[ENGRAM CONTEXT]" (standard suppressible layers). Returns "" if
|
||||
@@ -8,7 +8,7 @@
|
||||
* Threading: __thread_create / __thread_join use dlsym(RTLD_DEFAULT) to look
|
||||
* up El function symbols at runtime. This is the foundation of El's parallelism.
|
||||
*
|
||||
* Link: cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
* Link: cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
* -o <out> <prog>.c el_seed.c
|
||||
*/
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
//
|
||||
// Thin El wrappers over seed JSON primitives, plus pure-El builders and
|
||||
// helpers. Each function here corresponds to (and replaces) a C function
|
||||
// from el-compiler/runtime/legacy/el_runtime.c (lines 2692–3333).
|
||||
// from runtime/el_runtime.c (lines 2692–3333).
|
||||
//
|
||||
// Seed primitives consumed by this module:
|
||||
// __json_get(json, key) -> String (value as string)
|
||||
|
||||
@@ -25,8 +25,8 @@
|
||||
// runtime/collections.el \
|
||||
// <user-program.el> > combined.el
|
||||
// ./dist/platform/elc combined.el > output.c
|
||||
// cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
// -o output output.c el-compiler/runtime/el_seed.c
|
||||
// cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
// -o output output.c runtime/el_seed.c
|
||||
|
||||
// This file itself is not compiled — it is documentation only.
|
||||
fn runtime_version() -> String {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
// runtime/math.el — Float math, integer utilities, and numeric conversions.
|
||||
//
|
||||
// Implements the math/float surface from el-compiler/runtime/legacy/el_runtime.c
|
||||
// Implements the math/float surface from runtime/el_runtime.c
|
||||
// (lines 303–305 for el_abs/max/min, lines 4725–4771 for float/format ops)
|
||||
// in pure El, using seed primitives.
|
||||
//
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
// runtime/time.el — Time operations, sleep, and formatting.
|
||||
//
|
||||
// Implements the time surface from el-compiler/runtime/legacy/el_runtime.c
|
||||
// Implements the time surface from runtime/el_runtime.c
|
||||
// (lines 3334–3440, 3471–3656) in pure El, using seed primitives.
|
||||
//
|
||||
// Seed primitives consumed:
|
||||
|
||||
@@ -11,7 +11,7 @@ cd "$(dirname "$0")"
|
||||
|
||||
EL_HOME="${EL_HOME:-$(cd ../.. && pwd)}"
|
||||
ELC="${EL_HOME}/dist/platform/elc"
|
||||
RUNTIME_DIR="${EL_HOME}/el-compiler/runtime"
|
||||
RUNTIME_DIR="${EL_HOME}/runtime"
|
||||
|
||||
if [ ! -x "${ELC}" ]; then
|
||||
echo "elc not found at ${ELC}" >&2
|
||||
|
||||
@@ -10,7 +10,7 @@ cd "$(dirname "$0")"
|
||||
|
||||
EL_HOME="${EL_HOME:-$(cd ../.. && pwd)}"
|
||||
ELC="${EL_HOME}/dist/platform/elc"
|
||||
RUNTIME_DIR="${EL_HOME}/el-compiler/runtime"
|
||||
RUNTIME_DIR="${EL_HOME}/runtime"
|
||||
|
||||
if [ ! -x "${ELC}" ]; then
|
||||
echo "elc not found at ${ELC}" >&2
|
||||
|
||||
@@ -14,8 +14,8 @@
|
||||
// tests/runtime/string_test.el > /tmp/string_test_combined.el
|
||||
//
|
||||
// ./dist/platform/elc /tmp/string_test_combined.el > /tmp/string_test.c
|
||||
// cc -std=c11 -I el-compiler/runtime -lcurl -lpthread \
|
||||
// -o /tmp/string_test /tmp/string_test.c el-compiler/runtime/el_seed.c
|
||||
// cc -std=c11 -I runtime -lcurl -lpthread \
|
||||
// -o /tmp/string_test /tmp/string_test.c runtime/el_seed.c
|
||||
// /tmp/string_test; echo "exit: $?"
|
||||
//
|
||||
// Exit code equals the number of failing assertions (0 = all pass).
|
||||
|
||||
@@ -11,7 +11,7 @@ cd "$(dirname "$0")"
|
||||
|
||||
EL_HOME="${EL_HOME:-$(cd ../.. && pwd)}"
|
||||
ELC="${ELC:-${EL_HOME}/dist/platform/elc}"
|
||||
RUNTIME_DIR="${EL_HOME}/el-compiler/runtime"
|
||||
RUNTIME_DIR="${EL_HOME}/runtime"
|
||||
|
||||
if [ ! -x "${ELC}" ]; then
|
||||
echo "elc not found at ${ELC}" >&2
|
||||
|
||||
@@ -16,7 +16,7 @@ cd "$(dirname "$0")"
|
||||
|
||||
EL_HOME="${EL_HOME:-$(cd ../.. && pwd)}"
|
||||
ELC="${EL_HOME}/dist/platform/elc"
|
||||
RUNTIME_DIR="${EL_HOME}/el-compiler/runtime"
|
||||
RUNTIME_DIR="${EL_HOME}/runtime"
|
||||
|
||||
if [ ! -x "${ELC}" ]; then
|
||||
echo "elc not found at ${ELC}" >&2
|
||||
|
||||
@@ -44,7 +44,7 @@ INCLUDE_DIR="${PREFIX}/include"
|
||||
LIB_DIR="${PREFIX}/lib"
|
||||
|
||||
ELC_SRC="${EL_ROOT}/dist/platform/elc"
|
||||
RUNTIME_SRC="${EL_ROOT}/el-compiler/runtime"
|
||||
RUNTIME_SRC="${EL_ROOT}/runtime"
|
||||
STDLIB_SRC="${EL_ROOT}/runtime"
|
||||
|
||||
echo "==> Installing El framework to ${PREFIX}"
|
||||
|
||||
@@ -42,7 +42,7 @@ fi
|
||||
# Discover el_runtime.c
|
||||
EL_RUNTIME=""
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
LOCAL_RUNTIME="${SCRIPT_DIR}/../el-compiler/runtime/el_runtime.c"
|
||||
LOCAL_RUNTIME="${SCRIPT_DIR}/../runtime/el_runtime.c"
|
||||
if [[ -f "${LOCAL_RUNTIME}" ]]; then
|
||||
EL_RUNTIME="$(cd "$(dirname "${LOCAL_RUNTIME}")" && pwd)/$(basename "${LOCAL_RUNTIME}")"
|
||||
EL_INCLUDE="$(dirname "${EL_RUNTIME}")"
|
||||
|
||||
Executable
+94
@@ -0,0 +1,94 @@
|
||||
#!/usr/bin/env bash
|
||||
# check-single-runtime.sh — CODE-VS-ARTIFACT drift guard for the el runtime.
|
||||
#
|
||||
# Enforces org policy docs/CODE-VS-ARTIFACT.md rule #1 (single source of truth):
|
||||
# there is exactly ONE authored el_runtime.c, and it lives at lang/runtime/.
|
||||
# Any other el_runtime.c in the tree is a fork (a hand-synced copy). A lagging
|
||||
# fork is exactly what shipped to prod and dropped learned `hebb` edges on
|
||||
# restart — this guard exists to make that class of bug impossible to reintroduce.
|
||||
#
|
||||
# Exemptions:
|
||||
# * Build output — generated amalgamations under any dist/ or build/ dir are
|
||||
# artifacts, not sources.
|
||||
# * A small, explicit ALLOWLIST of pre-existing example-app vendored/staging
|
||||
# copies (see below). These are KNOWN DEFERRED DEBT, tracked separately from
|
||||
# the SDK/CI-published runtime. They do NOT ship to prod. The guard warns on
|
||||
# them (visible, greppable) but does not fail — while HARD-FAILING on any new
|
||||
# or non-allowlisted fork, including any return of lang/el-compiler/runtime/
|
||||
# or a lang/releases/ vendored copy.
|
||||
#
|
||||
# Wire-in: run from the repo root in CI (see note at bottom). Exits non-zero on drift.
|
||||
set -euo pipefail
|
||||
|
||||
ROOT="$(cd "$(dirname "$0")/.." && pwd)"
|
||||
cd "$ROOT"
|
||||
|
||||
CANONICAL="lang/runtime/el_runtime.c"
|
||||
|
||||
# KNOWN DEFERRED example-app forks — remove these as a follow-up, then delete
|
||||
# this allowlist. iOS + Docker copies are regenerated by their build scripts
|
||||
# (cp from lang/runtime) and can be git-rm'd now; the Android jni/ copy is a
|
||||
# committed source its CMake build depends on and needs a build-script change
|
||||
# (cp from lang/runtime) before removal. Tracked in docs/CODE-VS-ARTIFACT.md.
|
||||
ALLOWLIST=(
|
||||
"ui/examples/native-hello-android/app/src/main/jni/el_runtime.c"
|
||||
"ui/examples/native-hello-ios/NativeHello/el_runtime.c"
|
||||
"ui/examples/native-hello/build-docker/runtime/el_runtime.c"
|
||||
)
|
||||
|
||||
is_allowlisted() {
|
||||
local p="$1"
|
||||
for a in "${ALLOWLIST[@]}"; do [ "$p" = "$a" ] && return 0; done
|
||||
return 1
|
||||
}
|
||||
|
||||
if [ ! -f "$CANONICAL" ]; then
|
||||
echo "FATAL: canonical runtime source missing: $CANONICAL" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# All el_runtime.c files tracked by git, excluding build output (dist/ , build/)
|
||||
# and the canonical source itself.
|
||||
mapfile -t CANDIDATES < <(
|
||||
git ls-files '*el_runtime.c' \
|
||||
| grep -Ev '(^|/)(dist|build)/' \
|
||||
| grep -vx "$CANONICAL" || true
|
||||
)
|
||||
|
||||
FORKS=()
|
||||
DEFERRED=()
|
||||
for f in "${CANDIDATES[@]}"; do
|
||||
if is_allowlisted "$f"; then DEFERRED+=("$f"); else FORKS+=("$f"); fi
|
||||
done
|
||||
|
||||
if [ "${#DEFERRED[@]}" -gt 0 ]; then
|
||||
echo "WARN: allowlisted (deferred) el_runtime.c forks still present — clean these up:" >&2
|
||||
for f in "${DEFERRED[@]}"; do echo " - $f" >&2; done
|
||||
fi
|
||||
|
||||
if [ "${#FORKS[@]}" -gt 0 ]; then
|
||||
echo "FATAL: el_runtime.c fork(s) detected outside the canonical location." >&2
|
||||
echo " Canonical (the ONLY allowed source): $CANONICAL" >&2
|
||||
echo " Offending copies:" >&2
|
||||
for f in "${FORKS[@]}"; do echo " - $f" >&2; done
|
||||
echo "" >&2
|
||||
echo "Consumers must build against $CANONICAL (pin by git ref where" >&2
|
||||
echo "reproducibility matters) — never a hand-maintained copy." >&2
|
||||
echo "See docs/CODE-VS-ARTIFACT.md." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "OK: single canonical runtime source — $CANONICAL (no un-allowlisted forks)."
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# CI wire-in:
|
||||
# foundation/el .gitea/workflows/ci-dev.yaml, ci-stage.yaml, sdk-release.yaml
|
||||
# Add an early step (before the build/publish steps). It must run from the
|
||||
# REPO ROOT, so override the job's `defaults.run.working-directory: lang`:
|
||||
#
|
||||
# - name: Guard - single canonical runtime source
|
||||
# working-directory: ${{ github.workspace }}
|
||||
# run: bash scripts/check-single-runtime.sh
|
||||
#
|
||||
# Also add to .githooks/pre-commit so drift is caught before it is committed.
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -18,7 +18,7 @@ set -euo pipefail
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
|
||||
EL_UI_ROOT="${SCRIPT_DIR}/../.."
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/runtime"
|
||||
EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
|
||||
EL_APP_ENTRY="${EL_UI_ROOT}/examples/native-hello/src/main.el"
|
||||
EL_MANIFEST="${EL_UI_ROOT}/examples/native-hello/manifest.el"
|
||||
|
||||
@@ -17,7 +17,7 @@ set -euo pipefail
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
|
||||
EL_UI_ROOT="${SCRIPT_DIR}/../.."
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/runtime"
|
||||
EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
|
||||
EL_APP_ENTRY="${EL_UI_ROOT}/examples/native-hello/src/main.el"
|
||||
EL_MANIFEST="${EL_UI_ROOT}/examples/native-hello/manifest.el"
|
||||
|
||||
@@ -24,7 +24,7 @@ set -euo pipefail
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
|
||||
EL_UI_ROOT="${SCRIPT_DIR}/../.."
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/runtime"
|
||||
EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
|
||||
BUILD_DIR="${SCRIPT_DIR}/build-gtk4"
|
||||
|
||||
|
||||
@@ -23,7 +23,7 @@ set -euo pipefail
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
|
||||
EL_UI_ROOT="${SCRIPT_DIR}/../.."
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/runtime"
|
||||
EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
|
||||
BUILD_DIR="${SCRIPT_DIR}/build"
|
||||
|
||||
|
||||
@@ -18,7 +18,7 @@ set -euo pipefail
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
|
||||
EL_UI_ROOT="${SCRIPT_DIR}/../.."
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/runtime"
|
||||
EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
|
||||
BUILD_DIR="${SCRIPT_DIR}/build-win32"
|
||||
|
||||
|
||||
@@ -40,7 +40,7 @@ set -euo pipefail
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
|
||||
EL_UI_ROOT="${SCRIPT_DIR}/../.."
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/runtime"
|
||||
EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
|
||||
BUILD_DIR="${SCRIPT_DIR}/build"
|
||||
|
||||
@@ -193,6 +193,6 @@ run() {
|
||||
case "${1:-run}" in
|
||||
clean) clean ;;
|
||||
compile) compile ;;
|
||||
platforms) "${EL_LANG_ROOT}/el-compiler/runtime/detect-platforms" ;;
|
||||
platforms) "${EL_LANG_ROOT}/runtime/detect-platforms" ;;
|
||||
run|*) run ;;
|
||||
esac
|
||||
|
||||
@@ -32,7 +32,7 @@ set -euo pipefail
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
EL_LANG_ROOT="${SCRIPT_DIR}/../../../lang"
|
||||
EL_UI_ROOT="${SCRIPT_DIR}/../.."
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/el-compiler/runtime"
|
||||
EL_RUNTIME="${EL_LANG_ROOT}/runtime"
|
||||
EL_NATIVE_VESSEL="${EL_UI_ROOT}/vessels/el-native/src/main.el"
|
||||
BUILD_DIR="${SCRIPT_DIR}/build"
|
||||
DOCKER_CTX="${SCRIPT_DIR}/build-docker"
|
||||
|
||||
Reference in New Issue
Block a user