Function is_reference_node

internal/cbm/extract_usages.c:83–232

Is this an identifier-like node that represents a reference?

// Is this an identifier-like node that represents a reference?
static bool is_reference_node(TSNode node, CBMLanguage lang) {
    const char *kind = ts_node_type(node);

    /* Python's attribute node and its terminal identifier describe the same
     * source occurrence. For a direct callable-value argument, keep the leaf
     * as the raw carrier (so unresolved cases retain a useful short-name
     * USAGE) and stamp it with the full attribute span below. Receivers remain
     * independent value references. */
    if (lang == CBM_LANG_PYTHON && strcmp(kind, "attribute") == 0 &&
        !ts_node_is_null(python_direct_callable_attribute_site(node))) {
        return false;
    }

    /* A Rust scoped_identifier owns the complete path occurrence. Its nested
     * path/identifier children are grammar structure, not additional value
     * references; keeping them would let a short-name fallback bind a decoy. */
    if (lang == CBM_LANG_RUST &&
        (strcmp(kind, "identifier") == 0 || strcmp(kind, "scoped_identifier") == 0)) {
        TSNode parent = ts_node_parent(node);
        if (!ts_node_is_null(parent) && strcmp(ts_node_type(parent), "scoped_identifier") == 0) {
            return false;
        }
    }

    /* Some grammars expose the sigil/scope as a named wrapper around a generic
     * identifier. Keep exactly one occurrence: the wrapper carries the source
     * spelling that resolution needs (`$watched`, `a:watched`).
     *
     * The language gate MUST precede the parent fetch: ts_node_parent descends
     * from the root (O(depth)), and fetching it for every identifier in every
     * language made deep-nesting extraction quadratic across the board (the
     * stack_overflow deep tests went 0-1s -> 39-119s and blew the suite
     * budget on every non-M4 venue). */
    if ((lang == CBM_LANG_PUPPET || lang == CBM_LANG_VIMSCRIPT) &&
        strcmp(kind, "identifier") == 0) {
        TSNode parent = ts_node_parent(node);
        if (!ts_node_is_null(parent) &&
            ((lang == CBM_LANG_PUPPET && strcmp(ts_node_type(parent), "variable") == 0) ||
             (lang == CBM_LANG_VIMSCRIPT && strcmp(ts_node_type(parent), "argument") == 0))) {
            return false;
        }
    }

    // Common identifier types across languages
    if (strcmp(kind, "identifier") == 0 || strcmp(kind, "simple_identifier") == 0 ||
        strcmp(kind, "type_identifier") == 0) {
        return true;
    }

    // Language-specific reference types
    switch (lang) {
    case CBM_LANG_JAVASCRIPT:
    case CBM_LANG_TYPESCRIPT:
    case CBM_LANG_TSX:
    case CBM_LANG_QML:
    case CBM_LANG_CFSCRIPT:
        return strcmp(kind, "property_identifier") == 0 ||
               strcmp(kind, "private_property_identifier") == 0;