scriptoria 0.5.1__tar.gz → 0.5.2__tar.gz

{scriptoria-0.5.1 → scriptoria-0.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scriptoria
-Version: 0.5.1
+Version: 0.5.2
 Summary: Deterministic scriptorium-keeper (the `scrip` CLI): staleness, provenance integrity, and fact queries for an agent-compiled knowledge base
 Project-URL: Homepage, https://github.com/coredipper/scriptorium
 Project-URL: Changelog, https://github.com/coredipper/scriptorium/blob/main/CHANGELOG.md

{scriptoria-0.5.1 → scriptoria-0.5.2}/pyproject.toml

@@ -2,7 +2,7 @@
 # Distribution name on PyPI is `scriptoria` (scrip/scriptorium were taken); the
 # CLI command and the import package both remain `scrip`.
 name = "scriptoria"
-version = "0.5.1"
+version = "0.5.2"
 description = "Deterministic scriptorium-keeper (the `scrip` CLI): staleness, provenance integrity, and fact queries for an agent-compiled knowledge base"
 readme = "README.md"
 requires-python = ">=3.10"

{scriptoria-0.5.1 → scriptoria-0.5.2}/src/scrip/__init__.py

@@ -13,7 +13,7 @@ from __future__ import annotations
 
 from pathlib import Path
 
-__version__ = "0.5.1"
+__version__ = "0.5.2"
 
 # --- canonical vault layout ------------------------------------------------
 # ``root`` is the repo/instance root: the directory containing ``vault/``.

{scriptoria-0.5.1 → scriptoria-0.5.2}/src/scrip/frontmatter.py

@@ -39,13 +39,54 @@ def parse(text: str) -> tuple[dict, str]:
     raise DataError("unterminated frontmatter (missing closing '---')")
 
 
+def _read_frontmatter(f) -> tuple[bool, dict]:
+    first_line = f.readline()
+    if not first_line or first_line.strip() != FENCE:
+        return False, {}
+
+    fm_lines = []
+    for line in f:
+        if line.strip() == FENCE:
+            break
+        fm_lines.append(line)
+    else:
+        raise DataError("unterminated frontmatter (missing closing '---')")
+
+    try:
+        meta = yaml.safe_load("".join(fm_lines))
+    except yaml.YAMLError as e:
+        raise DataError(f"invalid YAML frontmatter: {e}") from e
+    if meta is None:
+        meta = {}
+    if not isinstance(meta, dict):
+        raise DataError("frontmatter must be a YAML mapping")
+    return True, meta
+
+
 def load(path: str | Path) -> tuple[dict, str]:
     p = Path(path)
     try:
-        text = p.read_text(encoding="utf-8")
+        with open(p, encoding="utf-8") as f:
+            found, meta = _read_frontmatter(f)
+            if not found:
+                f.seek(0)
+                return {}, f.read()
+            body = f.read()
+            return meta, body
+    except OSError as e:
+        raise DataError(f"cannot read {p}: {e}") from e
+
+
+def load_meta(path: str | Path) -> dict:
+    """Read just the frontmatter from a file without loading the body.
+    Significantly faster for metadata-only operations like scanning the vault."""
+    p = Path(path)
+    try:
+        with open(p, encoding="utf-8") as f:
+            _, meta = _read_frontmatter(f)
+            return meta
     except OSError as e:
         raise DataError(f"cannot read {p}: {e}") from e
-    return parse(text)
 
 
 def dump(meta: dict, body: str) -> str:
@@ -69,9 +110,7 @@ def as_str(meta: dict, key: str, where: str = "frontmatter") -> str | None:
     if value is None:
         return None
     if not isinstance(value, str):
-        raise DataError(
-            f"{where}: '{key}' must be a string, got {type(value).__name__}"
-        )
+        raise DataError(f"{where}: '{key}' must be a string, got {type(value).__name__}")
     return value
 
 

{scriptoria-0.5.1 → scriptoria-0.5.2}/src/scrip/graph.py

@@ -77,7 +77,7 @@ def scan_derived(root: Path) -> dict:
     wd = wiki_dir(root)
     if wd.is_dir():
         for path in sorted(wd.rglob("*.md")):
-            meta, _ = frontmatter.load(path)
+            meta = frontmatter.load_meta(path)
             if not meta or "derived-from" not in meta:
                 continue  # index.md, log.md, hand notes: not tracked artifacts
             where = str(path.relative_to(root))
@@ -195,11 +195,7 @@ def compute_status(
         else:
             ok.append({"id": did, "path": d["path"]})
 
-    uncompiled = [
-        {"id": rid, "path": r["path"]}
-        for rid, r in raw.items()
-        if rid not in referenced
-    ]
+    uncompiled = [{"id": rid, "path": r["path"]} for rid, r in raw.items() if rid not in referenced]
 
     if rebuild:
         manifest_mod.save(root, manifest_mod.build(raw, derived))
@@ -271,11 +267,7 @@ def print_status(result: dict) -> None:
     if stale:
         print(f"STALE ({len(stale)})")
         for s in stale:
-            tag = (
-                f"  [changed: {', '.join(s['changed_sources'])}]"
-                if s["changed_sources"]
-                else ""
-            )
+            tag = f"  [changed: {', '.join(s['changed_sources'])}]" if s["changed_sources"] else ""
             print(f"  ✗ {s['id']} — {s['reason']}{tag}")
     if unc:
         print(f"UNCOMPILED ({len(unc)})")

{scriptoria-0.5.1 → scriptoria-0.5.2}/src/scrip/similar.py

@@ -115,7 +115,7 @@ def compute_similar(
         if d.get("type") != want_type or cid in skip:
             continue  # other-kind pages and the facts.set row are dropped here
         c_sources = _source_set(d["derived_from"])
-        meta, _ = frontmatter.load(root / d["path"])
+        meta = frontmatter.load_meta(root / d["path"])
         c_title = (meta.get("title") if meta else "") or ""
         c_tags = _page_tags(c_sources, source_tags)
 
@@ -163,7 +163,7 @@ def print_similar(result: dict) -> None:
         s = c["scores"]
         print(f'  {s["combined"]:.3f}  {c["id"]}  "{c["title"]}"')
         print(
-            f'         sources {s["sources"]:.2f}  tags {s["tags"]:.2f}  title {s["title"]:.2f}'
-            f'   shared sources: {len(c["shared"]["sources"])}, tags: {len(c["shared"]["tags"])}'
+            f"         sources {s['sources']:.2f}  tags {s['tags']:.2f}  title {s['title']:.2f}"
+            f"   shared sources: {len(c['shared']['sources'])}, tags: {len(c['shared']['tags'])}"
         )
     print(f"({len(cands)} candidate(s))")

{scriptoria-0.5.1 → scriptoria-0.5.2}/tests/test_frontmatter.py

@@ -44,6 +44,36 @@ def test_load_missing_file_raises(tmp_path):
         frontmatter.load(tmp_path / "nope.md")
 
 
+def test_load_no_frontmatter_returns_whole_text(tmp_path):
+    path = tmp_path / "plain.md"
+    path.write_text("just a body\n", encoding="utf-8")
+
+    meta, body = frontmatter.load(path)
+
+    assert meta == {}
+    assert body == "just a body\n"
+
+
+def test_load_empty_frontmatter_strips_fences(tmp_path):
+    path = tmp_path / "empty.md"
+    path.write_text("---\n---\nbody\n", encoding="utf-8")
+
+    meta, body = frontmatter.load(path)
+
+    assert meta == {}
+    assert body == "body\n"
+
+
+def test_load_comment_only_frontmatter_strips_fences(tmp_path):
+    path = tmp_path / "comment.md"
+    path.write_text("---\n# intentionally empty\n---\nbody\n", encoding="utf-8")
+
+    meta, body = frontmatter.load(path)
+
+    assert meta == {}
+    assert body == "body\n"
+
+
 def test_dump_roundtrips_and_preserves_insertion_order():
     meta = {"id": "concept/x", "type": "wiki.concept", "derived-from": ["raw/a"]}
     text = frontmatter.dump(meta, "Body.\n")

{scriptoria-0.5.1 → scriptoria-0.5.2}/uv.lock

@@ -1141,7 +1141,7 @@ wheels = [
 
 [[package]]
 name = "scriptoria"
-version = "0.5.1"
+version = "0.5.2"
 source = { editable = "." }
 dependencies = [
     { name = "duckdb" },