WIP Phase 4 ingestion: platform guides, exclusion gate, gitea/vault/graph harvest, payload provenance

corpus/globs.py

@@ -0,0 +1,89 @@
+"""Path globs, with the one extension the guides need: `**/` matches nothing.
+
+`fnmatch` is close but wrong for this job in two ways: it lets `*` cross a `/`,
+and it has no `**`. Platform guides are read by a human and written as ordinary
+gitignore-style globs (`**/node_modules/**`, `200 projects/**`), so this module
+implements exactly that little language and nothing else.
+
+Matching is always against a normalised, repository-relative POSIX path.
+"""
+
+from __future__ import annotations
+
+import re
+
+_CACHE: dict = {}
+
+
+def normalise(path: str) -> str:
+    """Repository-relative, POSIX separators, no leading `./` or `/`."""
+    path = str(path).replace("\\", "/").strip()
+    while path.startswith("./"):
+        path = path[2:]
+    return path.lstrip("/")
+
+
+def compile_glob(pattern: str):
+    """Compile one glob to a regular expression. Cached."""
+    cached = _CACHE.get(pattern)
+    if cached is not None:
+        return cached
+
+    pattern = normalise(pattern)
+    out = ["^"]
+    index = 0
+    while index < len(pattern):
+        char = pattern[index]
+        if char == "*":
+            if pattern[index : index + 2] == "**":
+                index += 2
+                if pattern[index : index + 1] == "/":
+                    # `**/` — any number of whole directories, including none.
+                    out.append("(?:[^/]+/)*")
+                    index += 1
+                else:
+                    out.append(".*")
+                continue
+            out.append("[^/]*")
+        elif char == "?":
+            out.append("[^/]")
+        elif char == "[":
+            close = pattern.find("]", index + 1)
+            if close == -1:
+                out.append(re.escape(char))
+            else:
+                body = pattern[index + 1 : close]
+                if body.startswith("!"):
+                    body = "^" + body[1:]
+                out.append("[" + body + "]")
+                index = close
+        else:
+            out.append(re.escape(char))
+        index += 1
+    out.append("$")
+    compiled = re.compile("".join(out))
+    _CACHE[pattern] = compiled
+    return compiled
+
+
+def matches(path: str, pattern: str) -> bool:
+    return bool(compile_glob(pattern).match(normalise(path)))
+
+
+def matches_any(path: str, patterns) -> bool:
+    return any(matches(path, pattern) for pattern in (patterns or ()))
+
+
+def under_any(path: str, patterns) -> bool:
+    """True when `path` is a pattern's directory itself or inside it.
+
+    `200 projects/**` should also exclude the bare directory entry `200 projects`
+    that a tree listing returns, not only the files underneath it.
+    """
+    path = normalise(path)
+    for pattern in patterns or ():
+        if matches(path, pattern):
+            return True
+        if pattern.endswith("/**") and path == normalise(pattern[:-3]):
+            return True
+    return False