Function cbm_extract_file_impl

internal/cbm/cbm.c:704–1051

}

static CBMFileResult *cbm_extract_file_impl(const char *source, int source_len,
                                            CBMLanguage language, const char *project,
                                            const char *rel_path, int64_t timeout_micros,
                                            const char **extra_defines,
                                            const char **include_paths) {
    // Allocate result on heap (arena inside for all string data)
    enum { SINGLE = 1 };
    CBMFileResult *result = (CBMFileResult *)calloc(SINGLE, sizeof(CBMFileResult));
    if (!result) {
        return NULL;
    }

    cbm_arena_init(&result->arena);
    CBMArena *a = &result->arena;

    /* Crash-quarantine hard guard (Stage 3c): a file the supervisor pinned as a
     * crasher must NEVER be parsed again. Return a clean empty result BEFORE the
     * marker write and fault injector so no pass (including sequential re-extract
     * passes that miss the result cache) can crash on it. The pipeline extract
     * loops separately record it as a phase="crash" skip. Checked before the
     * marker so quarantined files never overwrite it — the marker keeps pointing
     * at the real (non-quarantined) file being processed when a crash hits. */
    if (cbm_index_is_quarantined(rel_path)) {
        return result;
    }

    cbm_index_mark_start(rel_path);
    cbm_test_fault_inject(rel_path);

    // Get language spec
    const CBMLangSpec *spec = cbm_lang_spec(language);
    if (!spec) {
        result->has_error = true;
        result->error_msg = cbm_arena_strdup(a, "unsupported language");
        return result;
    }

    // Get tree-sitter language
    const TSLanguage *ts_lang = cbm_ts_language(language);
    if (!ts_lang) {
        result->has_error = true;
        result->error_msg = cbm_arena_strdup(a, "no tree-sitter grammar");
        return result;
    }

    // Get thread-local parser (reused across files on same thread)
    TSParser *parser = get_thread_parser(ts_lang, language);
    if (!parser) {
        result->has_error = true;
        result->error_msg = cbm_arena_strdup(a, "parser alloc failed");
        return result;
    }

    // Reset parser state from any previous parse (cancellation flags etc.)
    ts_parser_reset(parser);

    uint64_t t0 = now_ns();