restructure: move el compiler content into lang/

This commit is contained in:
Will Anderson
2026-05-05 01:38:51 -05:00
parent ce68f91a38
commit 1ae68962cf
143 changed files with 0 additions and 0 deletions
+9
View File
@@ -0,0 +1,9 @@
package "el-compiler" {
version "0.1.0"
description "el self-hosting compiler — lexer, parser, codegen"
edition "2026"
}
build {
entry "src/compiler.el"
}
File diff suppressed because it is too large Load Diff
+764
View File
@@ -0,0 +1,764 @@
/*
* 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);
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);
#ifdef __cplusplus
}
#endif
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+248
View File
@@ -0,0 +1,248 @@
/*
* el_seed.h — El language seed runtime header
*
* Declares all OS-boundary primitives available to compiled El programs.
* All functions use the __ prefix convention. Signatures use el_val_t (= int64_t)
* as the universal value type.
*
* el_seed.c is the complete C boundary for the El runtime. The heavy runtime
* (el_runtime.c) has been retired — everything lives in el_seed.c plus the
* native El runtime (runtime/ *.el files).
*
* Link requirements:
* -lcurl — HTTP client (__http_do, __http_do_to_file)
* -lpthread — threading (__thread_create, __thread_join, __mutex_new, ...)
*
* Canonical compile (via elb):
* elb builds and links el_seed.c automatically.
*/
#pragma once
#include <stdint.h>
#include <stdlib.h>
/* ── Value model ─────────────────────────────────────────────────────────────
* All El values are el_val_t (int64_t). On 64-bit systems a pointer fits.
* String -> el_val_t (holds const char* via uintptr_t cast)
* Int -> el_val_t (stored directly)
* Bool -> el_val_t (0 = false, nonzero = true)
* Void -> void
*/
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 slot via bit-cast. */
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
/* ── String primitives ───────────────────────────────────────────────────── */
el_val_t __str_len(el_val_t s);
el_val_t __str_char_at(el_val_t s, el_val_t i); /* returns Int (byte value) */
el_val_t __str_alloc(el_val_t n); /* malloc(n+1), zero-init, return String */
el_val_t __str_set_char(el_val_t s, el_val_t i, el_val_t c); /* s[i]=c, return s */
el_val_t __str_cmp(el_val_t a, el_val_t b); /* strcmp result as Int */
el_val_t __str_ncmp(el_val_t a, el_val_t b, el_val_t n); /* strncmp */
el_val_t __str_concat_raw(el_val_t a, el_val_t b); /* malloc+strcpy concat */
el_val_t __str_slice_raw(el_val_t s, el_val_t start, el_val_t end); /* substring copy */
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); /* f is bit-cast double */
el_val_t __str_to_float(el_val_t s); /* strtod, bit-cast result */
/* ── I/O ─────────────────────────────────────────────────────────────────── */
void __println(el_val_t s);
void __print(el_val_t s);
el_val_t __readline(void);
/* ── 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_exists(el_val_t path);
el_val_t __fs_list_raw(el_val_t path); /* newline-separated filenames */
el_val_t __fs_mkdir(el_val_t path);
el_val_t __fs_write_bytes(el_val_t path, el_val_t bytes, el_val_t n);
/* ── HTTP client ─────────────────────────────────────────────────────────── */
/* Unified HTTP call. headers_json is a JSON object of header name->value pairs
* (e.g. {"Authorization":"Bearer ...","Content-Type":"application/json"}).
* Use "" or "{}" for no extra headers. timeout_ms <= 0 uses the default. */
el_val_t __http_do(el_val_t method, el_val_t url, el_val_t body,
el_val_t headers_json, el_val_t timeout_ms);
/* Stream response body directly to a file. Returns 1 on success, 0 on failure. */
el_val_t __http_do_to_file(el_val_t method, el_val_t url, el_val_t body,
el_val_t headers_json, el_val_t out_path);
/* ── HTTP server ─────────────────────────────────────────────────────────── */
/* Blocking HTTP server. handler_name is the El function name to dispatch to.
* v1 handler: (method, path, body) -> String
* v2 handler: (method, path, headers_map, body) -> String or envelope */
void __http_serve(el_val_t port, el_val_t handler_name);
void __http_serve_v2(el_val_t port, el_val_t handler_name);
/* Build a structured HTTP response envelope.
* headers_json: JSON object literal like {"Content-Type":"text/plain"} or "{}" */
el_val_t __http_response(el_val_t status, el_val_t headers_json, el_val_t body);
/* ── HTTP SSE — Server-Sent Events streaming ─────────────────────────────── */
/* Returns the raw file descriptor for the current HTTP connection.
* Valid only inside an http_serve_v2 handler before it returns.
* Returns -1 if called outside a handler context. */
el_val_t __http_conn_fd(void);
/* Sends SSE response headers on conn_id (the fd from __http_conn_fd),
* keeping the connection open for streaming. Returns 1 on success, 0 on
* write failure. Call once at the start of an SSE handler. */
el_val_t __http_sse_open(el_val_t conn_id);
/* Writes one SSE event frame: "data: <data>\n\n". data must not contain
* newlines. Returns 1 on success, 0 if the client disconnected. */
el_val_t __http_sse_send(el_val_t conn_id, el_val_t data);
/* Closes the SSE connection. The handler must return http_sse_sentinel()
* so the HTTP worker does not double-close the fd. */
el_val_t __http_sse_close(el_val_t conn_id);
/* ── Threading ───────────────────────────────────────────────────────────── */
/* Create a thread that calls the named El function with a String argument.
* fn_name is resolved via dlsym(RTLD_DEFAULT, fn_name). Returns a thread
* handle Int that can be passed to __thread_join. Returns -1 on failure. */
el_val_t __thread_create(el_val_t fn_name, el_val_t arg);
/* Wait for thread tid (returned by __thread_create) to finish.
* Returns the thread's return value as a String. */
el_val_t __thread_join(el_val_t tid);
/* Allocate a new mutex. Returns a handle Int (index into internal table). */
el_val_t __mutex_new(void);
void __mutex_lock(el_val_t m);
void __mutex_unlock(el_val_t m);
/* ── Subprocess ──────────────────────────────────────────────────────────── */
el_val_t __exec(el_val_t cmd); /* popen, capture all stdout, return String */
void __exec_bg(el_val_t cmd); /* fire and forget */
/* ── Environment and process ─────────────────────────────────────────────── */
el_val_t __env_get(el_val_t key); /* getenv, return "" if not set */
void __exit_program(el_val_t code);
el_val_t __args_json(void); /* CLI args as JSON array string */
/* ── Time ────────────────────────────────────────────────────────────────── */
el_val_t __time_now_ns(void); /* clock_gettime REALTIME, nanoseconds */
void __sleep_ms(el_val_t ms);
/* ── UUID ────────────────────────────────────────────────────────────────── */
el_val_t __uuid_v4(void);
/* ── Math ────────────────────────────────────────────────────────────────── */
el_val_t __sqrt_f(el_val_t f);
el_val_t __log_f(el_val_t f);
el_val_t __ln_f(el_val_t f);
el_val_t __sin_f(el_val_t f);
el_val_t __cos_f(el_val_t f);
el_val_t __pi_f(void);
/* ── JSON ────────────────────────────────────────────────────────────────── */
el_val_t __json_get(el_val_t json, el_val_t key);
el_val_t __json_get_raw(el_val_t json_str, 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_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_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_set(el_val_t json_str, el_val_t key, el_val_t value);
/* ── 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);
/* ── HTML/URL ────────────────────────────────────────────────────────────── */
el_val_t __html_sanitize(el_val_t input_html, el_val_t allowlist_json);
el_val_t __url_encode(el_val_t s);
el_val_t __url_decode(el_val_t s);
/* ── Engram ──────────────────────────────────────────────────────────────── */
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);
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);
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);
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);
el_val_t __engram_compile_layered_json(el_val_t intent, el_val_t depth);
/* ── Cryptographic hashing ────────────────────────────────────────────────── */
/* __sha256_hex — return the SHA-256 hex digest of a string.
* The returned string is 64 hex characters (lowercase). */
el_val_t __sha256_hex(el_val_t s);
/* ── args init (called from main) ────────────────────────────────────────── */
/* Store argc/argv for __args_json. Call once at the start of main(). */
void el_seed_init_args(int argc, char** argv);
#ifdef __cplusplus
}
#endif
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,761 @@
/*
* 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
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
+542
View File
@@ -0,0 +1,542 @@
// compiler.el el self-hosting compiler pipeline
//
// Wires lexer -> parser -> codegen into a single compile() function.
// This is the bootstrap entry point: compiled once by the Rust el-compiler,
// then self-hosted from that point forward.
//
// Two backends:
// - C (default) compile() -> emits C source linked against el_runtime.c
// - JS (--target=js) compile_js() -> emits JS source linked against el_runtime.js
//
// Compile the C output with:
// cc -o <prog> <prog>.c el_runtime.c
//
// Run the JS output with:
// node <prog>.js (after copying el_runtime.js next to it)
import "lexer.el"
import "parser.el"
import "codegen.el"
import "codegen-js.el"
// compile full pipeline (C target): source string -> C source string
fn compile(source: String) -> String {
let tokens: [Map<String, Any>] = lex(source)
let stmts: [Map<String, Any>] = parse(tokens)
// Token list is no longer needed after parsing release it to free memory
// before codegen allocates its own working data on large source files.
el_release(tokens)
codegen(stmts, source)
}
// compile_js full pipeline (JS target, module mode): source string -> JS source string
fn compile_js(source: String) -> String {
let tokens: [Map<String, Any>] = lex(source)
let stmts: [Map<String, Any>] = parse(tokens)
// Token list is no longer needed after parsing release it to free memory.
el_release(tokens)
codegen_js(stmts, source)
}
// compile_js_with_bundle JS target in bundle mode.
// Reads el_runtime.js from runtime_path and inlines it inside an IIFE.
fn compile_js_with_bundle(source: String, runtime_path: String) -> String {
let tokens: [Map<String, Any>] = lex(source)
let stmts: [Map<String, Any>] = parse(tokens)
el_release(tokens)
let runtime_content: String = fs_read(runtime_path)
if str_eq(runtime_content, "") {
println("el-compiler: warning: --bundle: could not read runtime at " + runtime_path)
println("el-compiler: warning: bundle output will be incomplete")
}
codegen_js_bundle(stmts, source, runtime_content)
}
// compile_dispatch pick a backend based on the requested target.
// tgt = "c" | "js"
// (The parameter is named `tgt` because `target` is a reserved keyword
// in El's lexer it would be tokenised as `Target`, breaking the
// parser's identifier resolution.)
fn compile_dispatch(tgt: String, source: String) -> String {
if str_eq(tgt, "js") { return compile_js(source) }
compile(source)
}
// compile_dispatch_bundle like compile_dispatch but bundle mode for JS.
fn compile_dispatch_bundle(tgt: String, source: String, runtime_path: String) -> String {
if str_eq(tgt, "js") { return compile_js_with_bundle(source, runtime_path) }
compile(source)
}
// Detect a `--target=<lang>` flag in argv and return the target.
// Returns "c" if none specified or unrecognized.
fn detect_target(argv: [String]) -> String {
let n: Int = native_list_len(argv)
let i = 0
while i < n {
let a: String = native_list_get(argv, i)
if str_starts_with(a, "--target=") {
let v: String = str_slice(a, 9, str_len(a))
return v
}
let i = i + 1
}
return "c"
}
// Strip flags from argv, leaving only positional arguments.
fn strip_flags(argv: [String]) -> [String] {
let out: [String] = native_list_empty()
let n: Int = native_list_len(argv)
let i = 0
while i < n {
let a: String = native_list_get(argv, i)
if !str_starts_with(a, "--") {
let out = native_list_append(out, a)
}
let i = i + 1
}
return out
}
// Detect --emit-header flag in argv.
fn detect_emit_header(argv: [String]) -> Bool {
let n: Int = native_list_len(argv)
let i = 0
while i < n {
let a: String = native_list_get(argv, i)
if str_eq(a, "--emit-header") { return true }
let i = i + 1
}
return false
}
// Detect --bundle flag in argv.
fn detect_bundle(argv: [String]) -> Bool {
let n: Int = native_list_len(argv)
let i = 0
while i < n {
let a: String = native_list_get(argv, i)
if str_eq(a, "--bundle") { return true }
let i = i + 1
}
return false
}
// Detect --minify flag in argv.
fn detect_minify(argv: [String]) -> Bool {
let n: Int = native_list_len(argv)
let i = 0
while i < n {
let a: String = native_list_get(argv, i)
if str_eq(a, "--minify") { return true }
let i = i + 1
}
return false
}
// Detect --obfuscate flag in argv.
fn detect_obfuscate(argv: [String]) -> Bool {
let n: Int = native_list_len(argv)
let i = 0
while i < n {
let a: String = native_list_get(argv, i)
if str_eq(a, "--obfuscate") { return true }
let i = i + 1
}
return false
}
// Build a unique temp file path: /tmp/elc-<pid>-<timestamp>.<suffix>
fn make_temp_path(suffix: String) -> String {
let pid: Int = getpid_now()
let ts: Int = time_now()
"/tmp/elc-" + native_int_to_str(pid) + "-" + native_int_to_str(ts) + "." + suffix
}
// Reserved globals that terser and javascript-obfuscator must not mangle.
// These are referenced from HTML onclick= attributes and other direct window usage.
fn js_reserved_names() -> String {
"neuronDemoToggle,neuronDemoSend,neuronDemoReset,signInWith,signInWithEmail,signUpWithEmail,sendMagicLink,signOut,resetPassword,sendResetEmail,updatePassword,showSignIn,showSignUp,hideReset,setSort,addFamilyMember,removeFamilyMember,copyForPlatform,entHeadcountChange,NEURON_CFG"
}
// Find a CLI tool by checking node_modules paths first, then falling back to npx.
// src_dir is the directory of the source file being compiled.
// Returns the command string to invoke the tool, or "" if not found.
fn find_node_tool(tool_name: String, src_dir: String) -> String {
// 1. Check ./node_modules/.bin/<tool> relative to source file
let cand1: String = src_dir + "/node_modules/.bin/" + tool_name
let check1: String = str_trim(exec_capture("test -x " + cand1 + " && echo yes 2>/dev/null"))
if str_eq(check1, "yes") { return cand1 }
// 2. Check ../node_modules/.bin/<tool> (monorepo layout)
let parent_dir: String = dirname_of(src_dir)
let cand2: String = parent_dir + "/node_modules/.bin/" + tool_name
let check2: String = str_trim(exec_capture("test -x " + cand2 + " && echo yes 2>/dev/null"))
if str_eq(check2, "yes") { return cand2 }
// 3. Fall back to npx if it is on PATH. npx will use the globally cached
// package or download on first use. Use --no to avoid auto-install if
// the package is not already cached; if that fails, try with --yes.
let npx_path: String = str_trim(exec_capture("which npx 2>/dev/null"))
if !str_eq(npx_path, "") { return "npx --yes " + tool_name }
return ""
}
// apply_minify run terser on js_path, write result to out_path.
// Returns true on success, false on failure.
fn apply_minify(js_path: String, out_path: String, src_dir: String) -> Bool {
let terser: String = find_node_tool("terser", src_dir)
if str_eq(terser, "") {
println("el-compiler: error: terser not found. Run 'npm install terser' in your project directory.")
return false
}
let names: String = js_reserved_names()
// Single-quote the mangle reserved list so the shell does not glob-expand
// the bracket expression. The compress options are safe without quoting.
let compress_opts: String = "passes=2,drop_console=false,drop_debugger=true"
let mangle_reserved: String = "'reserved=[" + names + "]'"
let cmd: String = terser + " " + js_path + " --compress " + compress_opts + " --mangle " + mangle_reserved + " --output " + out_path
let ret: Int = exec_command(cmd)
if ret == 0 { return true }
println("el-compiler: error: terser failed (exit " + native_int_to_str(ret) + ")")
return false
}
// apply_obfuscate run javascript-obfuscator on js_path, write result to out_path.
// Returns true on success, false on failure.
fn apply_obfuscate(js_path: String, out_path: String, src_dir: String) -> Bool {
let obfuscator: String = find_node_tool("javascript-obfuscator", src_dir)
if str_eq(obfuscator, "") {
println("el-compiler: error: javascript-obfuscator not found. Run 'npm install javascript-obfuscator' in your project directory.")
return false
}
let names: String = js_reserved_names()
let cmd: String = obfuscator + " " + js_path + " --output " + out_path + " --compact true --simplify true --string-array true --string-array-encoding base64 --string-array-threshold 0.75 --identifier-names-generator hexadecimal --rename-globals false --self-defending false --reserved-names " + names
let ret: Int = exec_command(cmd)
if ret == 0 { return true }
println("el-compiler: error: javascript-obfuscator failed (exit " + native_int_to_str(ret) + ")")
return false
}
// Resolve the runtime path for --bundle mode.
// Looks for el_runtime.js next to the source file first;
// if not found there, looks next to the elc binary itself.
// Returns "" if not found anywhere (caller emits a warning).
fn resolve_runtime_path(src_path: String) -> String {
let src_dir: String = dirname_of(src_path)
let candidate: String = src_dir + "/el_runtime.js"
let existing: String = fs_read(candidate)
if !str_eq(existing, "") {
return candidate
}
return ""
}
// Reconstruct an El type annotation string from a parsed type node.
fn type_node_to_el(t: Map<String, Any>) -> String {
let k: String = t["kind"]
if str_eq(k, "Simple") { return t["name"] }
if str_eq(k, "List") {
let inner: String = type_node_to_el(t["inner"])
return "[" + inner + "]"
}
if str_eq(k, "Map") {
let kt: String = type_node_to_el(t["key"])
let vt: String = type_node_to_el(t["val"])
return "Map<" + kt + ", " + vt + ">"
}
"Any"
}
// emit_header write a .elh file from parsed statements.
// Scans for FnDef nodes and emits 'extern fn' declarations.
fn emit_header(stmts: [Map<String, Any>], hdr_path: String) -> Void {
let n: Int = native_list_len(stmts)
let i = 0
let parts: [String] = native_list_empty()
let parts = native_list_append(parts, "// auto-generated by elc --emit-header — do not edit\n")
while i < n {
let stmt = native_list_get(stmts, i)
let kind: String = stmt["stmt"]
if str_eq(kind, "FnDef") {
let name: String = stmt["name"]
if !str_eq(name, "main") {
let params = stmt["params"]
let ret_type: String = stmt["ret_type"]
// build param list
let np: Int = native_list_len(params)
let pi = 0
let param_parts: [String] = native_list_empty()
while pi < np {
let param = native_list_get(params, pi)
let pname: String = param["name"]
let ptype: String = param["type"]
if str_eq(ptype, "") { let ptype = "Any" }
let param_parts = native_list_append(param_parts, pname + ": " + ptype)
let pi = pi + 1
}
let params_str: String = str_join(param_parts, ", ")
let ret_str: String = ret_type
if str_eq(ret_str, "") { let ret_str = "Any" }
let sig: String = "extern fn " + name + "(" + params_str + ") -> " + ret_str
let parts = native_list_append(parts, sig + "\n")
}
}
let i = i + 1
}
let content: String = str_join(parts, "")
let ok: Bool = fs_write(hdr_path, content)
}
// Import resolution
//
// elc supports two forms of import:
// import "path/to/file.el" quoted relative path
// from module import { Name } bare module name resolves to module.el
// in the entry source's directory
//
// Codegen treats Import statements as no-ops (declarations only), so to
// actually link bodies across files we textually concatenate every imported
// source ahead of the entry source before lex/parse. resolve_imports does a
// depth-first traversal with deduplication so any module that gets pulled in
// transitively is included exactly once.
fn dirname_of(path: String) -> String {
let n: Int = str_len(path)
let i: Int = n - 1
while i >= 0 {
let c: String = str_slice(path, i, i + 1)
if str_eq(c, "/") {
return str_slice(path, 0, i)
}
let i = i - 1
}
return "."
}
// Extract the resolved file path from a single trimmed source line. Returns
// "" if the line is not an import.
fn parse_import_line(trimmed: String, dir: String) -> String {
if str_starts_with(trimmed, "import \"") {
let after: String = str_slice(trimmed, 8, str_len(trimmed))
let q: Int = str_index_of(after, "\"")
if q > 0 {
let mod: String = str_slice(after, 0, q)
return dir + "/" + mod
}
}
if str_starts_with(trimmed, "from ") {
let after: String = str_slice(trimmed, 5, str_len(trimmed))
// module name is the first whitespace-delimited token
let sp: Int = str_index_of(after, " ")
if sp > 0 {
let mod_raw: String = str_slice(after, 0, sp)
let mod: String = str_trim(mod_raw)
if !str_eq(mod, "") {
return dir + "/" + mod + ".el"
}
}
}
return ""
}
// Recursively resolve imports starting from src_path. Returns the combined
// source text with every imported module's body inlined ahead of the entry
// source, deduplicated by absolute path. Uses state_set to track which paths
// have already been pulled in for this run.
//
// Accumulates chunks into lists and joins once at the end to avoid the O(n²)
// memory growth caused by repeated `prefix = prefix + chunk` concatenation.
fn resolve_imports(src_path: String) -> String {
let seen_key: String = "__elc_imp__:" + src_path
let already: String = state_get(seen_key)
if !str_eq(already, "") { return "" }
state_set(seen_key, "1")
let source: String = fs_read(src_path)
let dir: String = dirname_of(src_path)
let lines: [String] = str_split(source, "\n")
let n: Int = native_list_len(lines)
// Collect chunks into lists O(1) amortized per append.
// Join once at the end O(n) single pass.
let prefix_chunks: [String] = native_list_empty()
let body_chunks: [String] = native_list_empty()
let i: Int = 0
while i < n {
let line: String = native_list_get(lines, i)
let trimmed: String = str_trim(line)
let imp_path: String = parse_import_line(trimmed, dir)
if !str_eq(imp_path, "") {
// Use pre-compiled header if available (separate compilation).
// Only check .elh for imported files never for the entry file itself.
let imp_elh_path: String = str_slice(imp_path, 0, str_len(imp_path) - 3) + ".elh"
let imp_elh: String = fs_read(imp_elh_path)
if !str_eq(imp_elh, "") {
// Header exists: mark the .el as seen (so it won't be re-inlined
// if something else also imports it) and use the header text.
let seen_imp_key: String = "__elc_imp__:" + imp_path
state_set(seen_imp_key, "1")
let prefix_chunks = native_list_append(prefix_chunks, imp_elh)
} else {
let imp_body: String = resolve_imports(imp_path)
let prefix_chunks = native_list_append(prefix_chunks, imp_body)
}
} else {
let body_chunks = native_list_append(body_chunks, line + "\n")
}
let i = i + 1
}
return str_join(prefix_chunks, "") + str_join(body_chunks, "")
}
// run_with_postprocess codegen + minify + optional obfuscate pipeline.
//
// Called from main() when --minify or --obfuscate is active. Redirects stdout
// to a temp file during codegen so the output can be passed through the
// external tools (terser, javascript-obfuscator) before final emission.
//
// Pipeline: codegen -> terser -> (javascript-obfuscator) -> stdout or file
fn run_with_postprocess(tgt: String, source: String, src_path: String, do_bundle: Bool, do_obfuscate: Bool, argc: Int, positional: [String]) -> Void {
let src_dir: String = dirname_of(src_path)
let tmp_gen: String = make_temp_path("js")
let tmp_min: String = make_temp_path("min.js")
// Redirect stdout to tmp_gen so codegen println output is captured.
stdout_to_file(tmp_gen)
if do_bundle {
let runtime_path: String = resolve_runtime_path(src_path)
compile_dispatch_bundle(tgt, source, runtime_path)
} else {
compile_dispatch(tgt, source)
}
stdout_restore()
// Run terser: tmp_gen -> tmp_min
let ok_min: Bool = apply_minify(tmp_gen, tmp_min, src_dir)
if !ok_min {
exec_command("rm -f " + tmp_gen + " " + tmp_min)
exit(1)
}
// Determine final result path (either tmp_min or post-obfuscation file).
// Use state to pass the final path out of the optional obfuscation branch.
state_set("__elc_final_js", tmp_min)
if do_obfuscate {
let tmp_obf: String = make_temp_path("obf.js")
let ok_obf: Bool = apply_obfuscate(tmp_min, tmp_obf, src_dir)
if !ok_obf {
exec_command("rm -f " + tmp_gen + " " + tmp_min + " " + tmp_obf)
exit(1)
}
state_set("__elc_final_js", tmp_obf)
}
let final_path: String = state_get("__elc_final_js")
let final_js: String = fs_read(final_path)
// Clean up all temp files.
exec_command("rm -f " + tmp_gen + " " + tmp_min)
if do_obfuscate {
exec_command("rm -f " + final_path)
}
if argc >= 2 {
let out_path: String = native_list_get(positional, 1)
let ok: Bool = fs_write(out_path, final_js)
if ok {
return
} else {
println("el-compiler: failed to write output")
exit(1)
}
}
// No output file: print final JS to stdout.
print(final_js)
}
// main CLI entry point.
//
// elc <source.el> # emit C to stdout
// elc --target=js <source.el> # emit JS (module) to stdout
// elc --target=js --bundle <source.el> # emit self-contained JS (IIFE) to stdout
// elc --target=js --bundle --minify <source.el> # emit minified IIFE to stdout
// elc --target=js --bundle --obfuscate <source.el> # emit minified+obfuscated IIFE to stdout
// elc --target=c <source.el> <out.c> # write C to file
// elc --target=js <source.el> <out.js> # write JS to file
// elc --target=js --bundle <source.el> <out.js> # write bundled JS to file
// elc --target=js --bundle --minify <source.el> <out.min.js> # write minified JS to file
fn main() -> Void {
let argv: [String] = args()
// Use `tgt` not `target`: `target` is a reserved keyword in the lexer
// (Section 1.5 of the language spec). detect_target itself is fine
// because the function-name position has no token-class restriction.
let tgt: String = detect_target(argv)
let do_emit_header: Bool = detect_emit_header(argv)
let do_bundle: Bool = detect_bundle(argv)
let do_minify: Bool = detect_minify(argv)
let do_obfuscate: Bool = detect_obfuscate(argv)
// --obfuscate implies --minify: obfuscating unminified code is pointless.
if do_obfuscate {
let do_minify = true
}
let positional: [String] = strip_flags(argv)
let argc: Int = native_list_len(positional)
if argc < 1 {
println("el-compiler: usage: elc [--target=c|js] [--bundle] [--minify] [--obfuscate] [--emit-header] <source.el> [<output>]")
exit(1)
}
// --minify and --obfuscate require --target=js
if do_minify {
if !str_eq(tgt, "js") {
println("el-compiler: error: --minify and --obfuscate require --target=js")
exit(1)
}
}
let src_path: String = native_list_get(positional, 0)
// When --emit-header is requested, parse the source file directly
// (without inlining imports) and write out a .elh file alongside the .c.
if do_emit_header {
let raw_source: String = fs_read(src_path)
let hdr_tokens: [Map<String, Any>] = lex(raw_source)
let hdr_stmts: [Map<String, Any>] = parse(hdr_tokens)
el_release(hdr_tokens)
let hdr_path: String = str_slice(src_path, 0, str_len(src_path) - 3) + ".elh"
emit_header(hdr_stmts, hdr_path)
el_release(hdr_stmts)
}
let source: String = resolve_imports(src_path)
// When post-processing (--minify or --obfuscate) is requested, redirect
// stdout to a temp file so codegen output can be captured and piped through
// the external tools. After codegen, restore stdout before emitting the
// final result.
if do_minify {
run_with_postprocess(tgt, source, src_path, do_bundle, do_obfuscate, argc, positional)
exit(0)
}
// Standard path (no post-processing).
let out: String = ""
if do_bundle {
let runtime_path: String = resolve_runtime_path(src_path)
let out = compile_dispatch_bundle(tgt, source, runtime_path)
} else {
let out = compile_dispatch(tgt, source)
}
if argc >= 2 {
let out_path: String = native_list_get(positional, 1)
let ok: Bool = fs_write(out_path, out)
if ok {
exit(0)
} else {
println("el-compiler: failed to write output")
exit(1)
}
}
// No output path: codegen streamed to stdout already; out is "".
}
+993
View File
@@ -0,0 +1,993 @@
// lexer.el - el self-hosting lexer
//
// Tokenises an el source string into a list of token maps.
// Each token is a Map<String, Any> with keys:
// "kind" -> String (e.g. "Int", "Ident", "Plus")
// "value" -> String (the raw text of the token)
//
// Entry point: fn lex(source: String) -> [Map<String, Any>]
//
// Uses native_string_chars to split the source into a chars list,
// then indexes it with native_list_get - avoids O(N-) string cloning.
// -- Character helpers ---------------------------------------------------------
fn lex_is_digit(ch: String) -> Bool {
if ch == "0" { return true }
if ch == "1" { return true }
if ch == "2" { return true }
if ch == "3" { return true }
if ch == "4" { return true }
if ch == "5" { return true }
if ch == "6" { return true }
if ch == "7" { return true }
if ch == "8" { return true }
if ch == "9" { return true }
false
}
fn lex_is_alpha(ch: String) -> Bool {
if ch == "a" { return true }
if ch == "b" { return true }
if ch == "c" { return true }
if ch == "d" { return true }
if ch == "e" { return true }
if ch == "f" { return true }
if ch == "g" { return true }
if ch == "h" { return true }
if ch == "i" { return true }
if ch == "j" { return true }
if ch == "k" { return true }
if ch == "l" { return true }
if ch == "m" { return true }
if ch == "n" { return true }
if ch == "o" { return true }
if ch == "p" { return true }
if ch == "q" { return true }
if ch == "r" { return true }
if ch == "s" { return true }
if ch == "t" { return true }
if ch == "u" { return true }
if ch == "v" { return true }
if ch == "w" { return true }
if ch == "x" { return true }
if ch == "y" { return true }
if ch == "z" { return true }
if ch == "A" { return true }
if ch == "B" { return true }
if ch == "C" { return true }
if ch == "D" { return true }
if ch == "E" { return true }
if ch == "F" { return true }
if ch == "G" { return true }
if ch == "H" { return true }
if ch == "I" { return true }
if ch == "J" { return true }
if ch == "K" { return true }
if ch == "L" { return true }
if ch == "M" { return true }
if ch == "N" { return true }
if ch == "O" { return true }
if ch == "P" { return true }
if ch == "Q" { return true }
if ch == "R" { return true }
if ch == "S" { return true }
if ch == "T" { return true }
if ch == "U" { return true }
if ch == "V" { return true }
if ch == "W" { return true }
if ch == "X" { return true }
if ch == "Y" { return true }
if ch == "Z" { return true }
false
}
fn is_alnum_or_underscore(ch: String) -> Bool {
if lex_is_digit(ch) { return true }
if lex_is_alpha(ch) { return true }
if ch == "_" { return true }
false
}
fn lex_is_whitespace(ch: String) -> Bool {
if ch == " " { return true }
if ch == "\t" { return true }
if ch == "\n" { return true }
if ch == "\r" { return true }
false
}
fn make_tok(kind: String, value: String) -> Map<String, Any> {
{ "kind": kind, "value": value }
}
// -- Keyword lookup ------------------------------------------------------------
fn keyword_kind(word: String) -> String {
if word == "let" { return "Let" }
if word == "fn" { return "Fn" }
if word == "type" { return "Type" }
if word == "enum" { return "Enum" }
if word == "match" { return "Match" }
if word == "return" { return "Return" }
if word == "if" { return "If" }
if word == "else" { return "Else" }
if word == "for" { return "For" }
if word == "in" { return "In" }
if word == "while" { return "While" }
if word == "import" { return "Import" }
if word == "from" { return "From" }
if word == "as" { return "As" }
if word == "with" { return "With" }
if word == "sealed" { return "Sealed" }
if word == "activate" { return "Activate" }
if word == "where" { return "Where" }
if word == "test" { return "Test" }
if word == "seed" { return "Seed" }
if word == "assert" { return "Assert" }
if word == "protocol" { return "Protocol" }
if word == "impl" { return "Impl" }
if word == "retry" { return "Retry" }
if word == "times" { return "Times" }
if word == "fallback" { return "Fallback" }
if word == "reason" { return "Reason" }
if word == "parallel" { return "Parallel" }
if word == "trace" { return "Trace" }
if word == "requires" { return "Requires" }
if word == "deploy" { return "Deploy" }
if word == "to" { return "To" }
if word == "via" { return "Via" }
if word == "target" { return "Target" }
if word == "true" { return "Bool" }
if word == "false" { return "Bool" }
if word == "cgi" { return "Cgi" }
if word == "service" { return "Service" }
if word == "manager" { return "Manager" }
if word == "engine" { return "Engine" }
if word == "accessor" { return "Accessor" }
if word == "vessel" { return "Vessel" }
if word == "extern" { return "Extern" }
if word == "break" { return "Break" }
if word == "continue" { return "Continue" }
""
}
// -- Scan helpers --------------------------------------------------------------
// All scan helpers receive the chars list and total length.
// scan_digits - advance i while chars[i] is a digit
// Returns { "text": ..., "pos": i }
fn scan_digits(chars: [String], start: Int, total: Int) -> Map<String, Any> {
let i = start
let parts: [String] = native_list_empty()
let running = true
while running {
if i >= total {
let running = false
} else {
let ch: String = native_list_get(chars, i)
if lex_is_digit(ch) {
let parts = native_list_append(parts, ch)
let i = i + 1
} else {
let running = false
}
}
}
{ "text": str_join(parts, ""), "pos": i }
}
// scan_ident - advance i while chars[i] is alphanumeric or underscore
fn scan_ident(chars: [String], start: Int, total: Int) -> Map<String, Any> {
let i = start
let parts: [String] = native_list_empty()
let running = true
while running {
if i >= total {
let running = false
} else {
let ch: String = native_list_get(chars, i)
if is_alnum_or_underscore(ch) {
let parts = native_list_append(parts, ch)
let i = i + 1
} else {
let running = false
}
}
}
{ "text": str_join(parts, ""), "pos": i }
}
// -- Code-bearing string detection + comment strip ----------------------------
// Inline JS/CSS literals embedded in El source (e.g. <script>-</script> blobs
// or stylesheet payloads inside string literals) carry their own line and
// block comments. Those comments leak into the served HTML and reveal build
// notes the visitor should never see. We strip them at the lexer so every
// downstream consumer (codegen-c, codegen-js, parser) gets the cleaned form.
//
// looks_like_code - heuristic gate so we only strip strings that actually
// embed JS or CSS. Plain prose, hex blobs, JSON, etc. pass through verbatim.
fn substr_at(chars: [String], start: Int, total: Int, needle: String) -> Bool {
let nchars: [String] = native_string_chars(needle)
let nlen: Int = native_list_len(nchars)
if start + nlen > total { return false }
let i = 0
let matched = true
while i < nlen {
let a: String = native_list_get(chars, start + i)
let b: String = native_list_get(nchars, i)
if a == b { let i = i + 1 } else { let matched = false; let i = nlen }
}
matched
}
fn str_has(s: String, needle: String) -> Bool {
let chars: [String] = native_string_chars(s)
let total: Int = native_list_len(chars)
let i = 0
let found = false
while i < total {
if substr_at(chars, i, total, needle) {
let found = true
let i = total
} else {
let i = i + 1
}
}
found
}
fn looks_like_code(s: String) -> Bool {
if str_has(s, "<script") { return true }
if str_has(s, "<style") { return true }
if str_has(s, "function") {
if str_has(s, ";") { return true }
}
false
}
// strip_code_comments - character-by-character walk. Tracks JS string state
// (single, double, backtick) and never strips inside one. Backslash escapes
// inside JS strings consume the next char verbatim. URLs like https:// are
// preserved by checking the previous char before treating // as a line
// comment opener: if the char immediately before '/' is ':', emit the '/'
// literally and advance one position.
fn strip_code_comments(s: String) -> String {
let chars: [String] = native_string_chars(s)
let total: Int = native_list_len(chars)
let out_parts: [String] = native_list_empty()
let i = 0
let in_squote = false
let in_dquote = false
let in_btick = false
let prev = ""
while i < total {
let ch: String = native_list_get(chars, i)
let in_js_string = false
if in_squote { let in_js_string = true }
if in_dquote { let in_js_string = true }
if in_btick { let in_js_string = true }
if in_js_string {
// Backslash escape: consume next char verbatim regardless of which.
if ch == "\\" {
let out_parts = native_list_append(out_parts, ch)
let next_i = i + 1
if next_i < total {
let nc: String = native_list_get(chars, next_i)
let out_parts = native_list_append(out_parts, nc)
let prev = nc
let i = next_i + 1
} else {
let prev = ch
let i = next_i
}
} else {
if in_squote {
if ch == "'" { let in_squote = false }
} else {
if in_dquote {
if ch == "\"" { let in_dquote = false }
} else {
if in_btick {
if ch == "`" { let in_btick = false }
}
}
}
let out_parts = native_list_append(out_parts, ch)
let prev = ch
let i = i + 1
}
} else {
// Not in a JS string. Check for comment openers.
let next_i = i + 1
let next_ch = ""
if next_i < total {
let next_ch: String = native_list_get(chars, next_i)
}
if ch == "/" {
if next_ch == "/" {
// URL guard: prev char ':' means this is "://", not a comment.
if prev == ":" {
let out_parts = native_list_append(out_parts, ch)
let prev = ch
let i = i + 1
} else {
// Skip until newline (newline itself is preserved so
// surrounding line counts/structure stay sane).
let i = i + 2
let scanning = true
while scanning {
if i >= total {
let scanning = false
} else {
let lc: String = native_list_get(chars, i)
if lc == "\n" {
let scanning = false
} else {
let i = i + 1
}
}
}
let prev = ""
}
} else {
if next_ch == "*" {
// Skip until matching "*/".
let i = i + 2
let scanning2 = true
while scanning2 {
if i >= total {
let scanning2 = false
} else {
let bc: String = native_list_get(chars, i)
if bc == "*" {
let after = i + 1
if after < total {
let nc2: String = native_list_get(chars, after)
if nc2 == "/" {
let i = after + 1
let scanning2 = false
} else {
let i = i + 1
}
} else {
let i = i + 1
}
} else {
let i = i + 1
}
}
}
let prev = ""
} else {
let out_parts = native_list_append(out_parts, ch)
let prev = ch
let i = i + 1
}
}
} else {
// Open a JS string?
if ch == "'" {
let in_squote = true
let out_parts = native_list_append(out_parts, ch)
let prev = ch
let i = i + 1
} else {
if ch == "\"" {
let in_dquote = true
let out_parts = native_list_append(out_parts, ch)
let prev = ch
let i = i + 1
} else {
if ch == "`" {
let in_btick = true
let out_parts = native_list_append(out_parts, ch)
let prev = ch
let i = i + 1
} else {
let out_parts = native_list_append(out_parts, ch)
let prev = ch
let i = i + 1
}
}
}
}
}
}
str_join(out_parts, "")
}
// scan_string - scan a quoted string literal, handling \" escapes.
// Starts AFTER the opening quote. Returns { "text": content, "pos": i_after_close }
fn scan_string(chars: [String], start: Int, total: Int) -> Map<String, Any> {
let i = start
let parts: [String] = native_list_empty()
let running = true
while running {
if i >= total {
let running = false
} else {
let ch: String = native_list_get(chars, i)
if ch == "\\" {
// escape: peek next char
let next_i = i + 1
if next_i < total {
let next_ch: String = native_list_get(chars, next_i)
if next_ch == "\"" {
let parts = native_list_append(parts, "\"")
let i = next_i + 1
} else {
if next_ch == "n" {
let parts = native_list_append(parts, "\n")
let i = next_i + 1
} else {
if next_ch == "t" {
let parts = native_list_append(parts, "\t")
let i = next_i + 1
} else {
if next_ch == "r" {
let parts = native_list_append(parts, "\r")
let i = next_i + 1
} else {
if next_ch == "\\" {
let parts = native_list_append(parts, "\\")
let i = next_i + 1
} else {
let parts = native_list_append(parts, next_ch)
let i = next_i + 1
}
}
}
}
}
} else {
let i = i + 1
}
} else {
if ch == "\"" {
let i = i + 1
let running = false
} else {
let parts = native_list_append(parts, ch)
let i = i + 1
}
}
}
}
{ "text": str_join(parts, ""), "pos": i }
}
// -- String interpolation ------------------------------------------------------
//
// scan_interp_brace - scan from `start` (the char after `${`) to the matching
// `}`, tracking brace depth so inner braces (e.g. fn calls, map literals) are
// handled correctly. Returns { "text": inner_source, "pos": i_after_close }.
fn scan_interp_brace(chars: [String], start: Int, total: Int) -> Map<String, Any> {
let i = start
let parts: [String] = native_list_empty()
let depth = 1
let running = true
while running {
if i >= total {
let running = false
} else {
let ch: String = native_list_get(chars, i)
if ch == "{" {
let depth = depth + 1
let parts = native_list_append(parts, ch)
let i = i + 1
} else {
if ch == "}" {
let depth = depth - 1
if depth <= 0 {
// Closing brace of the interpolation - stop, do not include it
let i = i + 1
let running = false
} else {
let parts = native_list_append(parts, ch)
let i = i + 1
}
} else {
let parts = native_list_append(parts, ch)
let i = i + 1
}
}
}
}
{ "text": str_join(parts, ""), "pos": i }
}
// interp_tokens_append_all - copy every token from src into dst, skipping the
// trailing Eof sentinel that lex() always appends. Returns the updated dst list.
fn interp_tokens_append_all(dst: [Map<String, Any>], src: [Map<String, Any>]) -> [Map<String, Any>] {
let src_len: Int = native_list_len(src)
let j = 0
let result = dst
while j < src_len {
let tok: Map<String, Any> = native_list_get(src, j)
let tk: String = tok["kind"]
if tk == "Eof" {
let j = src_len
} else {
let result = native_list_append(result, tok)
let j = j + 1
}
}
result
}
// scan_interp_string - scan a string literal that may contain ${expr}
// interpolations. Starts AFTER the opening `"`.
// Returns { "tokens": [token list to inject], "pos": i_after_close_quote }.
//
// For a plain string (no ${}) this emits a single Str token, identical to the
// old scan_string path. For an interpolated string it emits a flat sequence
// of tokens equivalent to the string-concat expression, for example:
//
// "hello ${name}!"
// => Str("hello ") Plus <tokens for name> Plus Str("!")
//
// Empty literal segments between adjacent ${ } blocks are omitted. The
// resulting token stream is consumed by the existing parse_binop / parse_primary
// path in the parser with zero parser changes required.
//
// Supported escape sequences: \" \n \t \r \\ \$ (literal dollar sign).
// Nested quotes inside ${} are not supported; use a variable instead.
fn scan_interp_string(chars: [String], start: Int, total: Int) -> Map<String, Any> {
let i = start
let out_tokens: [Map<String, Any>] = native_list_empty()
let cur_part: [String] = native_list_empty()
let has_interp = false
let need_plus = false
let running = true
while running {
if i >= total {
let running = false
} else {
let ch: String = native_list_get(chars, i)
if ch == "\\" {
// Escape sequence
let next_i = i + 1
if next_i < total {
let next_ch: String = native_list_get(chars, next_i)
if next_ch == "$" {
// \$ => literal '$' (escape for interpolation syntax)
let cur_part = native_list_append(cur_part, "$")
let i = next_i + 1
} else {
if next_ch == "\"" {
let cur_part = native_list_append(cur_part, "\"")
let i = next_i + 1
} else {
if next_ch == "n" {
let cur_part = native_list_append(cur_part, "\n")
let i = next_i + 1
} else {
if next_ch == "t" {
let cur_part = native_list_append(cur_part, "\t")
let i = next_i + 1
} else {
if next_ch == "r" {
let cur_part = native_list_append(cur_part, "\r")
let i = next_i + 1
} else {
if next_ch == "\\" {
let cur_part = native_list_append(cur_part, "\\")
let i = next_i + 1
} else {
let cur_part = native_list_append(cur_part, next_ch)
let i = next_i + 1
}
}
}
}
}
}
} else {
let i = i + 1
}
} else {
if ch == "\"" {
// Closing quote - stop scanning
let i = i + 1
let running = false
} else {
if ch == "$" {
// Check for ${ (start of interpolation)
let next_i = i + 1
let is_interp = false
if next_i < total {
let next_ch: String = native_list_get(chars, next_i)
if next_ch == "{" {
let is_interp = true
}
}
if is_interp {
// Flush the accumulated literal part (if non-empty)
let part_len: Int = native_list_len(cur_part)
if part_len > 0 {
let part_text = str_join(cur_part, "")
if need_plus {
let out_tokens = native_list_append(out_tokens, make_tok("Plus", "+"))
}
let clean_part = part_text
if looks_like_code(part_text) {
let clean_part = strip_code_comments(part_text)
}
let out_tokens = native_list_append(out_tokens, make_tok("Str", clean_part))
let need_plus = true
}
let cur_part = native_list_empty()
let has_interp = true
// Scan brace-balanced expression source
let brace_result = scan_interp_brace(chars, next_i + 1, total)
let expr_src: String = brace_result["text"]
let new_i: Int = brace_result["pos"]
let i = new_i
// Re-lex the expression and inline the tokens.
// Wrap in ( ) so that operators inside ${} (e.g.
// age + 1) are parsed as a grouped sub-expression
// rather than merging with the surrounding concat
// Plus tokens at the wrong precedence level.
let inner_toks: [Map<String, Any>] = lex(expr_src)
let inner_len: Int = native_list_len(inner_toks)
if need_plus {
let out_tokens = native_list_append(out_tokens, make_tok("Plus", "+"))
}
// Empty interpolation ${} => empty string segment
if inner_len <= 1 {
let out_tokens = native_list_append(out_tokens, make_tok("Str", ""))
} else {
let out_tokens = native_list_append(out_tokens, make_tok("LParen", "("))
let out_tokens = interp_tokens_append_all(out_tokens, inner_toks)
let out_tokens = native_list_append(out_tokens, make_tok("RParen", ")"))
}
let need_plus = true
} else {
// Plain '$' not followed by '{' - treat as literal
let cur_part = native_list_append(cur_part, "$")
let i = i + 1
}
} else {
let cur_part = native_list_append(cur_part, ch)
let i = i + 1
}
}
}
}
}
// Flush remaining literal segment and build final token list
let part_text = str_join(cur_part, "")
let part_len: Int = native_list_len(cur_part)
if has_interp {
// Interpolated string: only emit trailing segment if non-empty
if part_len > 0 {
let clean_part = part_text
if looks_like_code(part_text) {
let clean_part = strip_code_comments(part_text)
}
if need_plus {
let out_tokens = native_list_append(out_tokens, make_tok("Plus", "+"))
}
let out_tokens = native_list_append(out_tokens, make_tok("Str", clean_part))
}
} else {
// Plain string with no interpolation - same behaviour as old scan_string
let clean_text = part_text
if looks_like_code(part_text) {
let clean_text = strip_code_comments(part_text)
}
let out_tokens = native_list_append(out_tokens, make_tok("Str", clean_text))
}
{ "tokens": out_tokens, "pos": i }
}
// -- Main lexer ----------------------------------------------------------------
fn lex(source: String) -> [Map<String, Any>] {
let chars: [String] = native_string_chars(source)
let total: Int = native_list_len(chars)
let tokens: [Map<String, Any>] = native_list_empty()
let i: Int = 0
while i < total {
let ch: String = native_list_get(chars, i)
// Skip whitespace
if lex_is_whitespace(ch) {
let i = i + 1
} else {
// Line comments: //
if ch == "/" {
let next_i = i + 1
if next_i < total {
let next_ch: String = native_list_get(chars, next_i)
if next_ch == "/" {
// skip to end of line
let i = i + 2
let running2 = true
while running2 {
if i >= total {
let running2 = false
} else {
let lch: String = native_list_get(chars, i)
if lch == "\n" {
let running2 = false
} else {
let i = i + 1
}
}
}
} else {
let tokens = native_list_append(tokens, make_tok("Slash", "/"))
let i = i + 1
}
} else {
let tokens = native_list_append(tokens, make_tok("Slash", "/"))
let i = i + 1
}
} else {
// String literal (plain or interpolated with ${expr} syntax).
// scan_interp_string handles both cases: plain strings emit a
// single Str token; interpolated strings emit a flat token
// sequence (Str Plus expr-tokens Plus Str ...) that the parser
// naturally assembles into a BinOp concat tree.
if ch == "\"" {
let interp_result = scan_interp_string(chars, i + 1, total)
let interp_toks: [Map<String, Any>] = interp_result["tokens"]
let new_pos: Int = interp_result["pos"]
let tokens = interp_tokens_append_all(tokens, interp_toks)
let i = new_pos
} else {
// Number literal
if lex_is_digit(ch) {
let result = scan_digits(chars, i, total)
let num_text: String = result["text"]
let new_pos: Int = result["pos"]
// check for float (dot followed by digit)
if new_pos < total {
let dot_ch: String = native_list_get(chars, new_pos)
if dot_ch == "." {
let after_dot = new_pos + 1
if after_dot < total {
let after_dot_ch: String = native_list_get(chars, after_dot)
if lex_is_digit(after_dot_ch) {
let frac_result = scan_digits(chars, after_dot, total)
let frac_text: String = frac_result["text"]
let frac_pos: Int = frac_result["pos"]
let tokens = native_list_append(tokens, make_tok("Float", num_text + "." + frac_text))
let i = frac_pos
} else {
let tokens = native_list_append(tokens, make_tok("Int", num_text))
let i = new_pos
}
} else {
let tokens = native_list_append(tokens, make_tok("Int", num_text))
let i = new_pos
}
} else {
let tokens = native_list_append(tokens, make_tok("Int", num_text))
let i = new_pos
}
} else {
let tokens = native_list_append(tokens, make_tok("Int", num_text))
let i = new_pos
}
} else {
// Identifier or keyword
if lex_is_alpha(ch) || ch == "_" {
let result = scan_ident(chars, i, total)
let word: String = result["text"]
let new_pos: Int = result["pos"]
let kw = keyword_kind(word)
if kw == "" {
let tokens = native_list_append(tokens, make_tok("Ident", word))
} else {
let tokens = native_list_append(tokens, make_tok(kw, word))
}
let i = new_pos
} else {
// Multi-char and single-char operators/delimiters
let peek_i = i + 1
let peek_ch = ""
if peek_i < total {
let peek_ch: String = native_list_get(chars, peek_i)
}
if ch == "=" {
if peek_ch == "=" {
let tokens = native_list_append(tokens, make_tok("EqEq", "=="))
let i = i + 2
} else {
if peek_ch == ">" {
let tokens = native_list_append(tokens, make_tok("FatArrow", "=>"))
let i = i + 2
} else {
let tokens = native_list_append(tokens, make_tok("Eq", "="))
let i = i + 1
}
}
} else {
if ch == "!" {
if peek_ch == "=" {
let tokens = native_list_append(tokens, make_tok("NotEq", "!="))
let i = i + 2
} else {
let tokens = native_list_append(tokens, make_tok("Not", "!"))
let i = i + 1
}
} else {
if ch == "<" {
if peek_ch == "=" {
let tokens = native_list_append(tokens, make_tok("LtEq", "<="))
let i = i + 2
} else {
let tokens = native_list_append(tokens, make_tok("Lt", "<"))
let i = i + 1
}
} else {
if ch == ">" {
if peek_ch == "=" {
let tokens = native_list_append(tokens, make_tok("GtEq", ">="))
let i = i + 2
} else {
let tokens = native_list_append(tokens, make_tok("Gt", ">"))
let i = i + 1
}
} else {
if ch == "&" {
if peek_ch == "&" {
let tokens = native_list_append(tokens, make_tok("And", "&&"))
let i = i + 2
} else {
let i = i + 1
}
} else {
if ch == "|" {
if peek_ch == "|" {
let tokens = native_list_append(tokens, make_tok("Or", "||"))
let i = i + 2
} else {
if peek_ch == ">" {
let tokens = native_list_append(tokens, make_tok("PipeOp", "|>"))
let i = i + 2
} else {
let tokens = native_list_append(tokens, make_tok("Pipe", "|"))
let i = i + 1
}
}
} else {
if ch == "-" {
if peek_ch == ">" {
let tokens = native_list_append(tokens, make_tok("Arrow", "->"))
let i = i + 2
} else {
let tokens = native_list_append(tokens, make_tok("Minus", "-"))
let i = i + 1
}
} else {
if ch == ":" {
if peek_ch == ":" {
let tokens = native_list_append(tokens, make_tok("ColonColon", "::"))
let i = i + 2
} else {
let tokens = native_list_append(tokens, make_tok("Colon", ":"))
let i = i + 1
}
} else {
if ch == "+" {
let tokens = native_list_append(tokens, make_tok("Plus", "+"))
let i = i + 1
} else {
if ch == "*" {
let tokens = native_list_append(tokens, make_tok("Star", "*"))
let i = i + 1
} else {
if ch == "%" {
let tokens = native_list_append(tokens, make_tok("Percent", "%"))
let i = i + 1
} else {
if ch == "(" {
let tokens = native_list_append(tokens, make_tok("LParen", "("))
let i = i + 1
} else {
if ch == ")" {
let tokens = native_list_append(tokens, make_tok("RParen", ")"))
let i = i + 1
} else {
if ch == "{" {
let tokens = native_list_append(tokens, make_tok("LBrace", "{"))
let i = i + 1
} else {
if ch == "}" {
let tokens = native_list_append(tokens, make_tok("RBrace", "}"))
let i = i + 1
} else {
if ch == "[" {
let tokens = native_list_append(tokens, make_tok("LBracket", "["))
let i = i + 1
} else {
if ch == "]" {
let tokens = native_list_append(tokens, make_tok("RBracket", "]"))
let i = i + 1
} else {
if ch == "," {
let tokens = native_list_append(tokens, make_tok("Comma", ","))
let i = i + 1
} else {
if ch == "." {
// Check for ..= (inclusive range) before .. (exclusive range) before single .
let peek2_i = i + 2
let peek2_ch = ""
if peek2_i < total {
let peek2_ch: String = native_list_get(chars, peek2_i)
}
if peek_ch == "." {
if peek2_ch == "=" {
let tokens = native_list_append(tokens, make_tok("DotDotEq", "..="))
let i = i + 3
} else {
let tokens = native_list_append(tokens, make_tok("DotDot", ".."))
let i = i + 2
}
} else {
let tokens = native_list_append(tokens, make_tok("Dot", "."))
let i = i + 1
}
} else {
if ch == ";" {
let tokens = native_list_append(tokens, make_tok("Semicolon", ";"))
let i = i + 1
} else {
if ch == "@" {
let tokens = native_list_append(tokens, make_tok("At", "@"))
let i = i + 1
} else {
if ch == "?" {
let tokens = native_list_append(tokens, make_tok("QuestionMark", "?"))
let i = i + 1
} else {
// unknown char - skip
let i = i + 1
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
}
let tokens = native_list_append(tokens, make_tok("Eof", ""))
tokens
}
File diff suppressed because it is too large Load Diff