fix: treat .cjs (explicit CommonJS) as a code extension

.cjs was half-registered: the language maps in build.py and
extract.py already routed it to the JS grammar, but it was missing
from CODE_EXTENSIONS, the extractor _DISPATCH, _LANG_FAMILY, and the
JS resolution/cache suffix sets — so .cjs sources (Electron
main/preload scripts, CommonJS escape hatches in "type": "module"
packages) were silently skipped during a build: classified as
non-code and never handed to the JS extractor.

Add .cjs alongside .mjs in the six lists that gate/route JS files
(detect.py, extract.py _DISPATCH, analyze.py _LANG_FAMILY,
extractors/models.py cache-bypass, extractors/resolution.py resolve
exts, cli.py _HOOK_SOURCE_EXTS), with regression locks mirroring the
.mts/.cts fix (#1607).

Real-world impact: an Electron app whose ~2000-line main.cjs backend
was invisible went from 201 to 294 nodes and 256 to 441 edges on
rebuild.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

graphify/analyze.py

@@ -23,7 +23,7 @@ _BUILTIN_NOISE_LABELS = frozenset({
 # Language families — extensions sharing a runtime can legitimately call each other
 _LANG_FAMILY: dict[str, str] = {
     **{e: "python" for e in (".py", ".pyw")},
-    **{e: "js" for e in (".js", ".jsx", ".mjs", ".ejs", ".ts", ".tsx", ".mts", ".cts", ".vue", ".svelte")},
+    **{e: "js" for e in (".js", ".jsx", ".mjs", ".cjs", ".ejs", ".ts", ".tsx", ".mts", ".cts", ".vue", ".svelte")},
     **{e: "go" for e in (".go",)},
     **{e: "rust" for e in (".rs",)},
     **{e: "jvm" for e in (".java", ".kt", ".kts", ".scala")},

graphify/cli.py

@@ -38,7 +38,7 @@ _READ_NUDGE = json.dumps({
     }
 }, ensure_ascii=False, separators=(",", ":")) + "\n"
 _HOOK_SOURCE_EXTS = (
-    '.py', '.js', '.ts', '.tsx', '.jsx', '.astro', '.vue', '.svelte', '.go',
+    '.py', '.js', '.cjs', '.ts', '.tsx', '.jsx', '.astro', '.vue', '.svelte', '.go',
     '.rs', '.java', '.rb', '.c', '.h', '.cpp', '.hpp', '.cc', '.cs', '.kt',
     '.swift', '.php', '.scala', '.lua', '.sh', '.md', '.rst', '.txt', '.mdx',
 )

graphify/detect.py

@@ -27,7 +27,7 @@ class FileType(str, Enum):
 
 _MANIFEST_PATH = str(out_path("manifest.json"))
 
-CODE_EXTENSIONS = {'.py', '.ts', '.tsx', '.mts', '.cts', '.js', '.jsx', '.mjs', '.ejs', '.ets', '.go', '.rs', '.java', '.groovy', '.gradle', '.cpp', '.cc', '.cxx', '.c', '.h', '.hpp', '.cu', '.cuh', '.metal', '.rb', '.rake', '.swift', '.kt', '.kts', '.cs', '.scala', '.php', '.lua', '.luau', '.toc', '.zig', '.ps1', '.psm1', '.psd1', '.ex', '.exs', '.m', '.mm', '.jl', '.vue', '.svelte', '.astro', '.dart', '.v', '.sv', '.svh', '.sql', '.r', '.f', '.F', '.f90', '.F90', '.f95', '.F95', '.f03', '.F03', '.f08', '.F08', '.pas', '.pp', '.dpr', '.dpk', '.lpr', '.inc', '.dfm', '.lfm', '.lpk', '.sh', '.bash', '.json', '.tf', '.tfvars', '.hcl', '.dm', '.dme', '.dmi', '.dmm', '.dmf', '.sln', '.slnx', '.csproj', '.fsproj', '.vbproj', '.xaml', '.razor', '.cshtml', '.cls', '.trigger'}
+CODE_EXTENSIONS = {'.py', '.ts', '.tsx', '.mts', '.cts', '.js', '.jsx', '.mjs', '.cjs', '.ejs', '.ets', '.go', '.rs', '.java', '.groovy', '.gradle', '.cpp', '.cc', '.cxx', '.c', '.h', '.hpp', '.cu', '.cuh', '.metal', '.rb', '.rake', '.swift', '.kt', '.kts', '.cs', '.scala', '.php', '.lua', '.luau', '.toc', '.zig', '.ps1', '.psm1', '.psd1', '.ex', '.exs', '.m', '.mm', '.jl', '.vue', '.svelte', '.astro', '.dart', '.v', '.sv', '.svh', '.sql', '.r', '.f', '.F', '.f90', '.F90', '.f95', '.F95', '.f03', '.F03', '.f08', '.F08', '.pas', '.pp', '.dpr', '.dpk', '.lpr', '.inc', '.dfm', '.lfm', '.lpk', '.sh', '.bash', '.json', '.tf', '.tfvars', '.hcl', '.dm', '.dme', '.dmi', '.dmm', '.dmf', '.sln', '.slnx', '.csproj', '.fsproj', '.vbproj', '.xaml', '.razor', '.cshtml', '.cls', '.trigger'}
 DOC_EXTENSIONS = {'.md', '.mdx', '.qmd', '.skill', '.txt', '.rst', '.html', '.yaml', '.yml'}
 PAPER_EXTENSIONS = {'.pdf'}
 IMAGE_EXTENSIONS = {'.png', '.jpg', '.jpeg', '.gif', '.webp', '.svg'}

graphify/extract.py

@@ -3838,6 +3838,7 @@ _DISPATCH: dict[str, Any] = {
     ".js": extract_js,
     ".jsx": extract_js,
     ".mjs": extract_js,
+    ".cjs": extract_js,
     ".ts": extract_js,
     ".tsx": extract_js,
     ".mts": extract_js,

graphify/extractors/models.py

@@ -8,7 +8,7 @@ from dataclasses import dataclass, field
 
 _WORKSPACE_PACKAGE_CACHE: dict[str, dict[str, Path]] = {}
 
-_JS_CACHE_BYPASS_SUFFIXES = {".js", ".jsx", ".mjs", ".ts", ".tsx", ".mts", ".cts", ".vue", ".svelte"}
+_JS_CACHE_BYPASS_SUFFIXES = {".js", ".jsx", ".mjs", ".cjs", ".ts", ".tsx", ".mts", ".cts", ".vue", ".svelte"}
 
 @dataclass
 class LanguageConfig:

graphify/extractors/resolution.py

@@ -21,7 +21,7 @@ _TSCONFIG_ALIAS_CACHE: dict[str, dict[str, list[str]]] = {}
 
 _WORKSPACE_MANIFEST_NAMES = ("pnpm-workspace.yaml", "package.json")
 
-_JS_RESOLVE_EXTS = (".ts", ".tsx", ".mts", ".cts", ".svelte", ".js", ".jsx", ".mjs")
+_JS_RESOLVE_EXTS = (".ts", ".tsx", ".mts", ".cts", ".svelte", ".js", ".jsx", ".mjs", ".cjs")
 
 _JS_INDEX_FILES = ("index.ts", "index.tsx", "index.svelte", "index.js", "index.jsx", "index.mjs")
 

tests/test_cjs_module_extension.py

@@ -0,0 +1,90 @@
+"""CommonJS module extension (`.cjs`) is treated as code.
+
+`.cjs` is the explicit-CommonJS counterpart of `.mjs` (used pervasively in
+Electron main/preload scripts and in `"type": "module"` packages that need a
+CommonJS escape hatch). The language maps in `build.py` and `extract.py`
+already routed `.cjs` to the JS grammar, but the extension was missing from
+`CODE_EXTENSIONS`, the extractor `_DISPATCH`, `_LANG_FAMILY`, and the JS
+resolution/cache sets — so `.cjs` sources were silently skipped during a build
+(detected as non-code and never handed to the JS extractor). These are
+regression locks for the extension sets plus an end-to-end extraction proving
+`.cjs` parses identically to `.js`.
+
+Same shape of gap (and fix) as `.mts`/`.cts` in
+tests/test_typescript_module_extensions.py.
+"""
+from __future__ import annotations
+
+from pathlib import Path
+
+
+def _labels(r):
+    return [n["label"] for n in r["nodes"]]
+
+
+def test_cjs_registered_as_code():
+    from graphify.detect import CODE_EXTENSIONS
+    assert ".cjs" in CODE_EXTENSIONS
+
+
+def test_cjs_in_extractor_dispatch():
+    from graphify.extract import _DISPATCH, extract_js
+    assert _DISPATCH.get(".cjs") is extract_js
+
+
+def test_cjs_in_js_language_family():
+    from graphify.analyze import _LANG_FAMILY
+    assert _LANG_FAMILY.get(".cjs") == "js"
+
+
+def test_cjs_in_js_resolution_sets():
+    from graphify.extract import _JS_CACHE_BYPASS_SUFFIXES, _JS_RESOLVE_EXTS
+    assert ".cjs" in _JS_RESOLVE_EXTS
+    assert ".cjs" in _JS_CACHE_BYPASS_SUFFIXES
+
+
+def test_cjs_in_hook_source_exts():
+    from graphify.cli import _HOOK_SOURCE_EXTS
+    assert ".cjs" in _HOOK_SOURCE_EXTS
+
+
+# A representative CommonJS source: require() imports, a class, a function, and
+# module.exports — the shape of an Electron main-process script.
+_CJS_SOURCE = (
+    "const path = require('path');\n"
+    "const { app, BrowserWindow } = require('electron');\n"
+    "class WindowManager {\n"
+    "  open() { return new BrowserWindow(); }\n"
+    "}\n"
+    "function createWindow() {\n"
+    "  const manager = new WindowManager();\n"
+    "  return manager.open();\n"
+    "}\n"
+    "module.exports = { createWindow };\n"
+)
+
+
+def _extract(tmp_path: Path, ext: str):
+    from graphify.extract import extract_js
+    f = tmp_path / f"main{ext}"
+    f.write_text(_CJS_SOURCE, encoding="utf-8")
+    return extract_js(f)
+
+
+def test_cjs_extracts_like_js(tmp_path):
+    # `.cjs` must parse identically to the same source saved as `.js` — same
+    # node set (require() imports, class, function) modulo the file-node label.
+    cjs = _extract(tmp_path, ".cjs")
+    js = _extract(tmp_path, ".js")
+    assert "error" not in cjs
+    cjs_labels = set(_labels(cjs))
+    js_labels = set(_labels(js))
+    assert any("WindowManager" in label for label in cjs_labels), (
+        ".cjs class declaration missing — file was not parsed as JS"
+    )
+    assert any("createWindow" in label for label in cjs_labels), (
+        ".cjs function declaration missing — file was not parsed as JS"
+    )
+    assert {label for label in cjs_labels if not label.endswith(".cjs")} == {
+        label for label in js_labels if not label.endswith(".js")
+    }