fix(review): address PR #16 code-review findings

#1 ingest: normalize the pinned caller id (_norm_cited_id) so a non-bare DOI caller cannot store a URL-form papers.id that defeats DQ-5 idempotency / the startswith(10.) recovery gates. #2 quality.section_label: collapse to a controlled bucket only for an EXACT canonical heading; descriptive titles ('Abstract Nonsense...') keep their real title instead of being mislabelled. #4 ra_grobid_backfill: release the read connection before the slow GROBID network loop, fresh connection for the write (no idle-in-transaction across the loop over the flaky tunnel).

#5/#10 tex: flatten_inputs strips unresolved input/include at the depth cap (no literal leak on cycles); _norm_texkey strips only a single leading ./ . #6/#7 arxiv.fetch_source: keep non-.tex members resolvable for input; pick primary on an UN-commented documentclass line. #13 is_arxiv_id: also exclude http:// and arXiv-DOI forms. Tests added/updated for each.

Left as deliberate decisions: #3 (pre-section text drop is pre-existing in extract_sections; abstract stored separately), #8 (script normalizer is intentionally self-contained, already documented), #9/#11/#12 (no current trigger / tightening the gzip heuristic would reject valid old LaTeX like documentstyle / title truncation is by design on a write-only column). ruff + mypy clean.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

codex/sources/arxiv.py

@@ -97,6 +97,16 @@ def fetch_metadata(arxiv_id: str) -> Paper | None:
     )
 
 
+def _has_documentclass(content: str) -> bool:
+    """True if *content* has an UN-commented ``\\documentclass`` line.
+
+    A plain ``"\\documentclass" in content`` substring test also matches a
+    commented-out ``%\\documentclass`` (common in arXiv preambles); requiring the
+    command to start its line avoids selecting the wrong primary file.
+    """
+    return any(line.lstrip().startswith("\\documentclass") for line in content.splitlines())
+
+
 def fetch_source(arxiv_id: str) -> str | None:
     """Download and extract the primary LaTeX source for an arXiv paper.
 
@@ -128,29 +138,38 @@ def fetch_source(arxiv_id: str) -> str | None:
     from codex.parsing.tex import flatten_inputs
 
     raw = response.content
+    # Image/font/binary members are never \input'd as text; skip them so the source
+    # map stays text-only (decode-with-replace would otherwise store garbled bytes).
+    skip_ext = (".png", ".jpg", ".jpeg", ".gif", ".bmp", ".pdf", ".eps", ".ps", ".ttf", ".otf")
     try:
         with tarfile.open(fileobj=io.BytesIO(raw), mode="r:gz") as tf:
             files: dict[str, str] = {}
             primary_name: str | None = None
             for member in tf.getmembers():
-                if not member.name.endswith(".tex"):
+                if not member.isfile() or member.name.lower().endswith(skip_ext):
                     continue
                 f = tf.extractfile(member)
                 if f is None:
                     continue
-                content = f.read().decode("utf-8", errors="replace")
-                files[member.name] = content
-                # Prefer the \documentclass file as the primary document.
-                if primary_name is None and "\\documentclass" in content:
+                # Keep ALL text members resolvable so \input of a non-.tex include
+                # (e.g. a .def or extension-less body file) is not silently dropped (R-C).
+                files[member.name] = f.read().decode("utf-8", errors="replace")
+                # Primary doc = a .tex with an UN-commented \documentclass.
+                if (
+                    primary_name is None
+                    and member.name.endswith(".tex")
+                    and _has_documentclass(files[member.name])
+                ):
                     primary_name = member.name
 
-            if not files:
+            tex_files = {k: v for k, v in files.items() if k.endswith(".tex")}
+            if not tex_files:
                 logger.debug("No .tex files found in arXiv source for %s", arxiv_id)
                 return None
 
             # No \documentclass anywhere → fall back to the largest .tex.
             if primary_name is None:
-                primary_name = max(files, key=lambda k: len(files[k]))
+                primary_name = max(tex_files, key=lambda k: len(tex_files[k]))
 
             # Inline \input/\include so multi-file projects yield the full body,
             # not just the primary file's skeleton of include directives (R-C).