fix: extension set drift in analyze.py and watch.py; remove dead build_graph

graphify/analyze.py

@@ -1,6 +1,7 @@
 """Graph analysis: god nodes (most connected), surprising connections (cross-community), suggested questions."""
 from __future__ import annotations
 import networkx as nx
+from .detect import CODE_EXTENSIONS, DOC_EXTENSIONS, PAPER_EXTENSIONS, IMAGE_EXTENSIONS
 
 
 def _node_community_map(communities: dict[int, list[str]]) -> dict[str, int]:
@@ -109,19 +110,13 @@ def _is_concept_node(G: nx.Graph, node_id: str) -> bool:
     return False
 
 
-_CODE_EXTENSIONS = {"py", "ts", "tsx", "js", "go", "rs", "java", "rb", "cpp", "c", "h", "cs", "kt", "scala", "php"}
-_DOC_EXTENSIONS = {"md", "txt", "rst"}
-_PAPER_EXTENSIONS = {"pdf"}
-_IMAGE_EXTENSIONS = {"png", "jpg", "jpeg", "webp", "gif", "svg"}
-
-
 def _file_category(path: str) -> str:
-    ext = path.rsplit(".", 1)[-1].lower() if "." in path else ""
-    if ext in _CODE_EXTENSIONS:
+    ext = ("." + path.rsplit(".", 1)[-1].lower()) if "." in path else ""
+    if ext in CODE_EXTENSIONS:
         return "code"
-    if ext in _PAPER_EXTENSIONS:
+    if ext in PAPER_EXTENSIONS:
         return "paper"
-    if ext in _IMAGE_EXTENSIONS:
+    if ext in IMAGE_EXTENSIONS:
         return "image"
     return "doc"
 

graphify/cluster.py

@@ -52,23 +52,6 @@ def _partition(G: nx.Graph) -> dict[str, int]:
     return {node: cid for cid, nodes in enumerate(communities) for node in nodes}
 
 
-def build_graph(nodes: list[dict], edges: list[dict]) -> nx.Graph:
-    """Build a NetworkX graph from graphify node/edge dicts.
-
-    Preserves original edge direction as _src/_tgt attributes so that
-    display functions can show relationships in the correct direction,
-    even though the graph is undirected for structural analysis.
-    """
-    G = nx.Graph()
-    for n in nodes:
-        G.add_node(n["id"], **{k: v for k, v in n.items() if k != "id"})
-    for e in edges:
-        attrs = {k: v for k, v in e.items() if k not in ("source", "target")}
-        attrs["_src"] = e["source"]
-        attrs["_tgt"] = e["target"]
-        G.add_edge(e["source"], e["target"], **attrs)
-    return G
-
 _MAX_COMMUNITY_FRACTION = 0.25   # communities larger than 25% of graph get split
 _MIN_SPLIT_SIZE = 10             # only split if community has at least this many nodes
 

graphify/watch.py

@@ -3,19 +3,10 @@
 import json
 import time
 from pathlib import Path
+from .detect import CODE_EXTENSIONS, DOC_EXTENSIONS, PAPER_EXTENSIONS, IMAGE_EXTENSIONS
 
-
-_WATCHED_EXTENSIONS = {
-    ".py", ".ts", ".js", ".go", ".rs", ".java", ".cpp", ".c", ".rb", ".swift", ".kt",
-    ".cs", ".scala", ".php", ".cc", ".cxx", ".hpp", ".h", ".kts",
-    ".md", ".txt", ".rst", ".pdf",
-    ".png", ".jpg", ".jpeg", ".webp", ".gif", ".svg",
-}
-
-_CODE_EXTENSIONS = {
-    ".py", ".ts", ".js", ".go", ".rs", ".java", ".cpp", ".c", ".rb", ".swift", ".kt",
-    ".cs", ".scala", ".php", ".cc", ".cxx", ".hpp", ".h", ".kts",
-}
+_WATCHED_EXTENSIONS = CODE_EXTENSIONS | DOC_EXTENSIONS | PAPER_EXTENSIONS | IMAGE_EXTENSIONS
+_CODE_EXTENSIONS = CODE_EXTENSIONS
 
 
 def _rebuild_code(watch_path: Path, *, follow_symlinks: bool = False) -> bool:

tests/test_analyze.py

@@ -137,6 +137,15 @@ def test_file_category():
     assert _file_category("flash.pdf") == "paper"
     assert _file_category("diagram.png") == "image"
     assert _file_category("notes.md") == "doc"
+    # Languages that were previously misclassified as "doc"
+    assert _file_category("main.swift") == "code"
+    assert _file_category("lib.lua") == "code"
+    assert _file_category("build.zig") == "code"
+    assert _file_category("script.ps1") == "code"
+    assert _file_category("app.ex") == "code"
+    assert _file_category("view.jsx") == "code"
+    assert _file_category("solver.jl") == "code"
+    assert _file_category("bridge.m") == "code"
 
 
 def test_is_concept_node_empty_source():