@antoneeo/course-creator 0.1.0-beta.1 → 0.1.0-beta.10

package/skills/course-creator/scripts/knowledge.py

@@ -125,6 +125,21 @@ def kb_unquote(value):
     return v
 
 
+def frontmatter_date(meta):
+    """A note's or a sidecar's `date:` as `YYYY-MM-DD`, or None (F-073).
+    Quotes stripped, a datetime suffix tolerated, an impossible date refused --
+    the one parser behind orient's recency probe and any chronology reader."""
+    m = re.match(r"(\d{4}-\d{2}-\d{2})", kb_unquote((meta or {}).get("date")))
+    if not m:
+        return None
+    try:
+        import datetime as _dt
+        _dt.date.fromisoformat(m.group(1))
+    except ValueError:
+        return None
+    return m.group(1)
+
+
 def kb_parse_scope(text):
     """'-' | 'from X' | 'until X' | 'from X until Y' | 'if <cond>' ->
     ('always',) | ('window', from, until) | ('if', cond). Raises on junk."""
@@ -336,6 +351,17 @@ def kb_check_claims(root):
         if rel not in fm_cache:
             fm_cache[rel] = _note_frontmatter(root, rel)
         return fm_cache[rel]
+    # F-069: the same per-run memo for the source paths themselves -- each
+    # distinct path is resolved and stat'ed once, and each cited extraction
+    # read once (loc_cache, owned here, dropped when this call returns).
+    src_cache = {}
+    loc_cache = {}
+
+    def _resolved(path_s):
+        if path_s not in src_cache:
+            t = sdlc_core.confine_under(root, path_s)
+            src_cache[path_s] = (t, t is not None and t.is_file())
+        return src_cache[path_s]
     per_file_rows = []
     for p in sorted(topics.glob("*.md")):
         rel = "topics/" + p.name
@@ -357,16 +383,16 @@ def kb_check_claims(root):
                     errors.append("%s: source %r has no locator" % (where, src))
                     continue
                 path_s, loc = src.rsplit("#", 1)
-                target = sdlc_core.confine_under(root, path_s)
+                target, is_file = _resolved(path_s)
                 if target is None:
                     errors.append("%s: source %r escapes the docs root" % (where, src))
                     continue
-                if not target.is_file():
+                if not is_file:
                     errors.append("%s: source %r does not resolve — a claim whose "
                                   "origin cannot be reopened is model knowledge"
                                   % (where, src))
                     continue
-                kb_check_locator(target, loc, where, errors)
+                kb_check_locator(target, loc, where, errors, loc_cache)
             # --- provenance ---
             prov = row["prov"]
             # Resolved ONCE, for every provenance: the non-GIVEN classes read it
@@ -556,8 +582,14 @@ def kb_check_claims(root):
     return errors, warnings, notes
 
 
-def kb_check_locator(target, loc, where, errors):
-    """A locator must address an existing span of the stored bytes."""
+def kb_check_locator(target, loc, where, errors, cache=None):
+    """A locator must address an existing span of the stored bytes.
+
+    `cache` is an optional dict the CALLER owns for one run (F-069): keyed by
+    the path actually read, it holds only what the checks compare against --
+    page lengths, a line count, or False for a missing extraction -- never the
+    text. Findings are still appended per call, so per row. Without it, every
+    call reads the file, as before."""
     m = LOC_PAGE_RE.match(loc)
     if m:
         page, a, b = int(m.group(1)), int(m.group(2)), int(m.group(3))
@@ -566,17 +598,24 @@ def kb_check_locator(target, loc, where, errors):
             return
         # offsets address the stored extraction (<stem>.txt beside the original)
         ext = target if target.suffix == ".txt" else target.with_suffix(".txt")
-        if not ext.is_file():
+        key = ("p", ext)
+        if cache is None or key not in cache:
+            lengths = ([len(pg) for pg in sdlc_core.read_text(ext).split("\f")]
+                       if ext.is_file() else False)
+            if cache is not None:
+                cache[key] = lengths
+        else:
+            lengths = cache[key]
+        if lengths is False:
             errors.append("%s: no stored extraction %s for locator %r — offsets "
                           "must address kept bytes" % (where, ext.name, loc))
             return
-        pages = sdlc_core.read_text(ext).split("\f")
-        if page < 1 or page > len(pages):
+        if page < 1 or page > len(lengths):
             errors.append("%s: locator %r addresses page %d of %d" %
-                          (where, loc, page, len(pages)))
-        elif b > len(pages[page - 1]):
+                          (where, loc, page, len(lengths)))
+        elif b > lengths[page - 1]:
             errors.append("%s: locator %r spans past the end of page %d "
-                          "(%d chars)" % (where, loc, page, len(pages[page - 1])))
+                          "(%d chars)" % (where, loc, page, lengths[page - 1]))
         return
     m = LOC_LINE_RE.match(loc)
     if m:
@@ -584,7 +623,13 @@ def kb_check_locator(target, loc, where, errors):
         if a > b or a < 1:
             errors.append("%s: locator %r has an invalid line range" % (where, loc))
             return
-        n = sdlc_core.read_text(target).count("\n") + 1
+        key = ("L", target)
+        if cache is None or key not in cache:
+            n = sdlc_core.read_text(target).count("\n") + 1
+            if cache is not None:
+                cache[key] = n
+        else:
+            n = cache[key]
         if b > n:
             errors.append("%s: locator %r spans past line %d" % (where, loc, n))
         return
@@ -1085,12 +1130,18 @@ KB_GENERATED_RE = re.compile(r"GENERATED by \S+ index - do not edit by hand")
 KB_HEX12_RE = re.compile(r"^[0-9a-f]{12}$")
 
 
-def _kb_hex_bounded(text, cid):
-    """True when cid appears NOT embedded in a longer hex run: a git hash
-    sharing a substring must never count as a citation (either side, either
-    case). cid is pre-validated 12-hex, so it is regex-safe by construction."""
-    return re.search(r"(?<![0-9a-fA-F])%s(?![0-9a-fA-F])" % cid,
-                     text) is not None
+# A citation of a claim id is a run of exactly its 12 lowercase hex characters
+# NOT embedded in a longer hex run: a git hash sharing a substring must never
+# count as a citation (either side, either case). Two such bounded runs cannot
+# overlap, so findall returns every one of them.
+KB_HEX_TOKEN_RE = re.compile(r"(?<![0-9a-fA-F])[0-9a-f]{12}(?![0-9a-fA-F])")
+
+
+def _kb_hex_tokens(text):
+    """The ids a text cites, extracted in one pass (F-069). Callers test
+    membership instead of scanning the text once per id: that per-(document,
+    id) scan made the time cycle grow with superseded ids x living documents."""
+    return frozenset(KB_HEX_TOKEN_RE.findall(text))
 
 
 def _kb_df_entries(value):
@@ -1172,19 +1223,23 @@ def kb_time_cycle(docs):
         if (meta.get("status") or "").strip() == "SUPERSEDED":
             continue
         living.append((rel, text))
-    for rel, text in living:
-        for old in sorted(superseded):
-            if _kb_hex_bounded(text, old):
-                succs = superseded[old]
-                missing = tuple(x for x in succs
-                                if not _kb_hex_bounded(text, x))
-                if missing:
-                    cited.append((rel, old, missing, succs))
+    # One token pass per living document, and none at all on a KB with no
+    # supersession and no validity window (the orient line runs this at every
+    # session start).
+    tokens = ({rel: _kb_hex_tokens(text) for rel, text in living}
+              if superseded or windows else {})
+    for rel, _text in living:
+        cites = tokens[rel] if tokens else frozenset()
+        for old in cites.intersection(superseded):
+            succs = superseded[old]
+            missing = tuple(x for x in succs if x not in cites)
+            if missing:
+                cited.append((rel, old, missing, succs))
     today = _dt.date.today().isoformat()
     for topic_rel, rid, until in sorted(windows):
         if until <= today:
-            by = tuple(rel for rel, text in living
-                       if rel != topic_rel and _kb_hex_bounded(text, rid))
+            by = tuple(rel for rel, _text in living
+                       if rel != topic_rel and rid in tokens[rel])
             expired.append((topic_rel, rid, until, by))
     rev = {}
     node_meta = {}
@@ -1491,16 +1546,17 @@ def memory_records(docs):
                     paths.append(p)
     records = []
     for p in sorted(set(paths), key=lambda p: p.relative_to(docs).as_posix()):
-        raw = p.read_bytes()
-        text = raw.decode("utf-8", errors="replace")
+        text = p.read_bytes().decode("utf-8", errors="replace")
         meta = sdlc_core.load_frontmatter(text.splitlines())
         title = next((line[2:].strip() for line in text.splitlines()
                       if line.startswith("# ")), p.stem)
+        # LF-normalized like the guides' source_hash: an autocrlf checkout must
+        # regenerate the same catalog as an LF one.
         records.append((p.relative_to(docs).as_posix(),
                         kb_unquote(meta.get("domain")) or default,
                         ", ".join(_as_list(meta.get("topics", ""))),
                         kb_unquote(meta.get("description")) or title,
-                        hashlib.sha256(raw).hexdigest()))
+                        sdlc_core.sha256_file(p)))
     return records
 
 
@@ -1662,17 +1718,18 @@ def kb_cmd_validate(root, docs, strict=False, hybrid=False):
 
 def kb_cmd_check(root, docs, strict=False, hybrid=False):
     # The spine's check owns its banners and summary line: reuse it whole, so a
-    # tree with no kb surface gets byte-identical output. The kb checks run
-    # after, and only when the surface exists.
-    rc = sdlc_core.cmd_check(root, strict=strict, hybrid=hybrid)
-    rc = max(rc, _kb_extra_validate(docs), memory_validate(docs))
+    # tree with no kb surface gets byte-identical output. The kb checks ride its
+    # hooks -- index freshness in the validate stage, graph/corpus as sections
+    # only when the surface exists -- so the summary is printed after all of them.
+    sections = ()
     if (docs / "topics").is_dir() or (docs / "corpus").is_dir():
         cycle = kb_time_cycle(docs)
-        print("===== graph =====")
-        rc = max(rc, kb_cmd_graph(docs, cycle))
-        print("===== corpus =====")
-        rc = max(rc, kb_cmd_corpus(docs, cycle))
-    return rc
+        sections = (("graph", lambda: kb_cmd_graph(docs, cycle)),
+                    ("corpus", lambda: kb_cmd_corpus(docs, cycle)))
+    return sdlc_core.cmd_check(
+        root, strict=strict, hybrid=hybrid,
+        extra_validate=lambda: max(_kb_extra_validate(docs), memory_validate(docs)),
+        extra_sections=sections)
 
 
 def kb_cmd_stale(root, docs, hybrid=False):
@@ -1903,14 +1960,13 @@ def kb_cmd_orient(argv):
                     # it -- the file was already fully read, so the cap bought
                     # only failure. load_frontmatter is the authoritative
                     # reader (fence-bounded, so a column-0 date: in the body
-                    # still cannot misdate the note); kb_unquote covers quoted
-                    # dates; the prefix match tolerates a datetime suffix.
+                    # still cannot misdate the note); frontmatter_date covers
+                    # quoted dates and tolerates a datetime suffix.
                     meta = sdlc_core.load_frontmatter(
                         sdlc_core.read_text(p).splitlines()) or {}
-                    m = re.match(r"(\d{4}-\d{2}-\d{2})",
-                                 kb_unquote(meta.get("date")))
-                    if m:
-                        stamp = _dt.date.fromisoformat(m.group(1))
+                    day = frontmatter_date(meta)
+                    if day:
+                        stamp = _dt.date.fromisoformat(day)
                 except Exception:
                     pass
                 if stamp is None: