chore: import upstream snapshot with attribution

graphify/extractors/base.py

@@ -0,0 +1,66 @@
+# DO NOT import from graphify.extract here — direction is extract.py → extractors/ only.
+from __future__ import annotations
+
+from pathlib import Path
+
+from graphify.ids import make_id
+
+# Language built-in globals that AST may classify as call targets when used as
+# constructors or coercion functions (e.g. String(x), Number(x), Boolean(x)).
+# Without this filter they become god-nodes accumulating spurious edges from
+# every call site. Filter applied at same-file and cross-file resolution.
+# See issue #726.
+_LANGUAGE_BUILTIN_GLOBALS: frozenset[str] = frozenset({
+    # JavaScript / TypeScript ECMAScript built-ins
+    "String", "Number", "Boolean", "Object", "Array", "Symbol", "BigInt",
+    "Date", "RegExp", "Error", "TypeError", "RangeError", "SyntaxError",
+    "ReferenceError", "EvalError", "URIError",
+    "Promise", "Map", "Set", "WeakMap", "WeakSet", "JSON", "Math",
+    "Reflect", "Proxy", "Intl",
+    "parseInt", "parseFloat", "isNaN", "isFinite",
+    "encodeURIComponent", "decodeURIComponent", "encodeURI", "decodeURI",
+    # Browser / Node common globals
+    "URL", "URLSearchParams", "FormData", "Blob", "File",
+    "Headers", "Request", "Response", "AbortController", "AbortSignal",
+    "TextEncoder", "TextDecoder", "console",
+    # Python built-in callables
+    "str", "int", "float", "bool", "list", "dict", "set", "tuple", "bytes",
+    "len", "range", "enumerate", "zip", "map", "filter", "sum", "min", "max",
+    "print", "open", "isinstance", "type", "super", "sorted", "reversed",
+    "any", "all", "abs", "round", "next", "iter", "hash", "id", "repr",
+    "callable", "getattr", "setattr", "hasattr", "delattr", "vars", "dir",
+})
+
+
+def _make_id(*parts: str) -> str:
+    return make_id(*parts)
+
+
+def _file_stem(path: Path) -> str:
+    """Stem used as the node-ID prefix for a file and its symbols.
+
+    The full path (extension dropped) is preserved as path segments; ``make_id``
+    later collapses the separators to underscores. Using every segment — not just
+    the immediate parent dir (#1504) — means same-named files in different
+    directories get distinct IDs instead of colliding into one
+    last-writer-wins node:
+
+        docs/v1/api/README.md -> docs/v1/api/README -> docs_v1_api_readme
+        docs/v2/api/README.md -> docs/v2/api/README -> docs_v2_api_readme
+
+    Top-level files keep a bare stem (``setup.py`` -> ``setup``). When passed an
+    absolute path the whole path is encoded; the extract() id-remap post-pass
+    re-derives the canonical repo-relative form from ``source_file`` so the on-disk
+    location can't leak into the persisted IDs (#502).
+
+    Returns "" for a path with no name (``Path('.')`` — a source_file that equals
+    the scan root, so it has no per-file stem). Guarding here keeps
+    ``path.with_suffix("")`` from raising ``ValueError: '.' has an empty name`` and
+    protects every caller, not just ``_semantic_id_remap`` (#1618)."""
+    if not path.name:
+        return ""
+    return path.with_suffix("").as_posix()
+
+
+def _read_text(node, source: bytes) -> str:
+    return source[node.start_byte:node.end_byte].decode("utf-8", errors="replace")