bibcite-cli 0.5.2__tar.gz → 0.5.4__tar.gz

{bibcite_cli-0.5.2 → bibcite_cli-0.5.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: bibcite-cli
-Version: 0.5.2
+Version: 0.5.4
 Summary: Resolve papers (arXiv id / DOI / title) to canonical, normalized BibTeX for agents and humans
 Project-URL: Repository, https://github.com/leo1oel/bibcite
 License-Expression: MIT

{bibcite_cli-0.5.2 → bibcite_cli-0.5.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "bibcite-cli"
-version = "0.5.2"
+version = "0.5.4"
 description = "Resolve papers (arXiv id / DOI / title) to canonical, normalized BibTeX for agents and humans"
 readme = "Readme.md"
 license = "MIT"

{bibcite_cli-0.5.2 → bibcite_cli-0.5.4}/src/bibcite/__init__.py

@@ -1,3 +1,3 @@
 """bibcite: canonical BibTeX resolution for papers (arXiv id / DOI / title)."""
 
-__version__ = "0.5.2"
+__version__ = "0.5.4"

{bibcite_cli-0.5.2 → bibcite_cli-0.5.4}/src/bibcite/bibfile.py

@@ -20,16 +20,14 @@ from .normalize import norm_title
 # \cite{} commands valid.
 TIDY_ARGS = [
     "--modify",
-    # volume/number/pages/doi are kept (bibliographic substance the user
-    # asked to retain); the omit list drops only true noise.
-    "--omit=publisher,timestamp,biburl,bibsource,abstract,month,series,editor,note,date,address",
+    "--omit=pages,publisher,doi,timestamp,biburl,bibsource,abstract,month,series,volume,editor,note,date,number,address,issn,isbn",
     "--curly",
     "--blank-lines",
     "--trailing-commas",
     "--sort=-year",
     "--duplicates=citation",
     "--merge=first",
-    "--sort-fields=author,title,booktitle,journal,volume,number,pages,year,doi,url,pdf",
+    "--sort-fields=author,title,booktitle,journal,year,url,pdf",
     "--strip-enclosing-braces",
     "--tidy-comments",
 ]

{bibcite_cli-0.5.2 → bibcite_cli-0.5.4}/src/bibcite/sources.py

@@ -209,6 +209,28 @@ def _dblp_get(c: httpx.Client, url: str, params: dict | None = None) -> httpx.Re
     return _paced_get(c, url, "dblp", 0.8, params=params)
 
 
+def _dblp_sanitize(q: str) -> str:
+    """DBLP's search parser 500s deterministically on queries containing its
+    syntax characters (':' in subtitled papers, '?' in question titles).
+    They tokenize on punctuation anyway, so replacing with spaces loses
+    nothing."""
+    return re.sub(r"[^\w\s.-]", " ", q)
+
+
+def _dblp_search(c: httpx.Client, q: str, h: int = 100) -> list:
+    """One search request; a 500 (broad all-common-words query × large h
+    times out their backend) is retried once with a small result window
+    before giving up on this query variant."""
+    url = "https://dblp.org/search/publ/api"
+    q = _dblp_sanitize(q)
+    r = _dblp_get(c, url, params={"q": q, "format": "json", "h": h})
+    if r.status_code == 500 and h > 10:
+        _log("[dblp] 500 on broad query — retrying with h=10")
+        r = _dblp_get(c, url, params={"q": q, "format": "json", "h": 10})
+    r.raise_for_status()
+    return r.json().get("result", {}).get("hits", {}).get("hit", []) or []
+
+
 def try_dblp(title: str, author_hint: str = "") -> Match | None:
     """DBLP search. Generic titles ("X is all you need") drown in DBLP's
     ranking, so when we know the first author we query with their last name
@@ -219,15 +241,7 @@ def try_dblp(title: str, author_hint: str = "") -> Match | None:
     queries.append(title)
     with _client() as c:
         for q in queries:
-            r = _dblp_get(
-                c,
-                "https://dblp.org/search/publ/api",
-                params={"q": q, "format": "json", "h": 100},
-            )
-            r.raise_for_status()
-            hits = (
-                r.json().get("result", {}).get("hits", {}).get("hit", []) or []
-            )
+            hits = _dblp_search(c, q)
             # Earliest year first: prefer the original conference publication
             # over later journal extensions (same heuristic as PaperMemory).
             hits.sort(key=lambda h: int(h.get("info", {}).get("year", 9999)))
@@ -283,13 +297,7 @@ def try_dblp_fuzzy(title: str, author_hint: str, year: str = "") -> Match | None
         return None
     q = " ".join([author_hint] + tokens)
     with _client() as c:
-        r = _dblp_get(
-            c,
-            "https://dblp.org/search/publ/api",
-            params={"q": q, "format": "json", "h": 100},
-        )
-        r.raise_for_status()
-        hits = r.json().get("result", {}).get("hits", {}).get("hit", []) or []
+        hits = _dblp_search(c, q)
         hits.sort(key=lambda h: int(h.get("info", {}).get("year", 9999)))
         for hit in hits:
             info = hit.get("info", {})

{bibcite_cli-0.5.2 → bibcite_cli-0.5.4}/tests/test_round3.py

@@ -84,3 +84,11 @@ def test_scrub_leaves_clean_files_alone(tmp_path: Path):
     bib.write_text(original)
     _scrub_month_strings(bib)
     assert bib.read_text() == original  # untouched, not even rewritten
+
+
+def test_dblp_sanitize_strips_syntax_chars():
+    from bibcite.sources import _dblp_sanitize
+
+    q = _dblp_sanitize("LeJEPA: Provable? Self-Supervised (Learning)")
+    assert ":" not in q and "?" not in q and "(" not in q
+    assert "Self-Supervised" in q  # hyphens survive

{bibcite_cli-0.5.2 → bibcite_cli-0.5.4}/uv.lock

@@ -18,7 +18,7 @@ wheels = [
 
 [[package]]
 name = "bibcite-cli"
-version = "0.5.2"
+version = "0.5.4"
 source = { editable = "." }
 dependencies = [
     { name = "bibtexparser" },