MrSphay/odysseus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: document_actions title/content helpers crash on non-string input (#1621)

Browse Source
This commit is contained in:
Afonso Coutinho
2026-06-03 00:59:55 +01:00
committed by GitHub
parent 03ddc5d2c4
commit 2d94e38d23
2 changed files with 23 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/document_actions.py
View File

@@ -21,7 +21,8 @@ _JUNK_TITLES = {
def _norm_title(t: str) -> str:
"""Normalize a title for grouping: trim, collapse whitespace, lowercase."""
return re.sub(r"\s+", " ", (t or "").strip()).lower()
t = t if isinstance(t, str) else ""
return re.sub(r"\s+", " ", t.strip()).lower()
def _content_fingerprint(content: str) -> str:
@@ -32,7 +33,7 @@ def _content_fingerprint(content: str) -> str:
that N imports of the same file collapse to one fingerprint. Whitespace is
collapsed and the result lowercased.
"""
c = content or ""
c = content if isinstance(content, str) else ""
c = re.sub(r'upload_id="[^"]*"', "upload_id", c) # pdf_source re-imports
c = re.sub(r"\bid=ann-[A-Za-z0-9_-]+", "id=ann", c) # annotation ids
c = re.sub(r"\s+", " ", c).strip().lower()
@@ -41,7 +42,8 @@ def _content_fingerprint(content: str) -> str:
def _real_len(content: str) -> int:
"""Length of content with markdown noise stripped — a 'completeness' proxy."""
stripped = re.sub(r"^#{1,6}\s+", "", content or "", flags=re.MULTILINE)
content = content if isinstance(content, str) else ""
stripped = re.sub(r"^#{1,6}\s+", "", content, flags=re.MULTILINE)
stripped = re.sub(r"[*_`>\-=]+", "", stripped)
stripped = re.sub(r"\s+", " ", stripped).strip()
return len(stripped)