Function cbm_extract_file_ex

internal/cbm/cbm.c:1129–1599

}

CBMFileResult *cbm_extract_file_ex(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, const CBMMacroTable *macro_table,
                                   const CBMReturnTypeTable *return_type_table) {
    // 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);
#ifdef CBM_ENABLE_TEST_SEAMS
    cbm_test_fault_inject(rel_path);
#endif

    // 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");
        cbm_index_mark_done(rel_path);
        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");
        cbm_index_mark_done(rel_path);
        return result;
    }

    // Skip pathologically nested Perl before tree-sitter's recursive GLR stack
    // merge overflows a small stack during the parse (see
    // cbm_source_nesting_exceeds). Scoped to Perl: its ambiguous call grammar is
    // the only one that drives that recursion to the nesting depth.
    if (language == CBM_LANG_PERL &&
        cbm_source_nesting_exceeds(source, source_len, CBM_PERL_MAX_PARSE_NESTING)) {
        result->has_error = true;
        result->error_msg = cbm_arena_strdup(a, "perl source nesting too deep; skipped");
        return result;