From 121b582f46be3b3079587b0be07811710a6c82df Mon Sep 17 00:00:00 2001
From: Tarik Moussa <tarikmoussa@MacBookAir.fritz.box>
Date: Thu, 18 Jun 2026 04:18:18 +0200
Subject: [PATCH] fix(arxiv): handle legacy single-file gzipped source (no tar
 wrapper)

Old arXiv submissions (e.g. legacy math/* papers) are served as a bare gzipped .tex rather than a .tar.gz, which tarfile.open rejected with 'invalid header'. Fall back to gunzipping the body directly when the tar parse fails, so R-C covers those papers too (recovers math/0001176 + math/0306167). Adds a regression test.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 codex/sources/arxiv.py      | 16 ++++++++++++----
 tests/sources/test_arxiv.py | 24 ++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/codex/sources/arxiv.py b/codex/sources/arxiv.py
index dd61961..7c1a803 100644
--- a/codex/sources/arxiv.py
+++ b/codex/sources/arxiv.py
@@ -8,6 +8,7 @@ Provides:
 
 from __future__ import annotations
 
+import gzip
 import io
 import logging
 import tarfile
@@ -157,12 +158,19 @@ def fetch_source(arxiv_id: str) -> str | None:
             # Inline \input/\include so multi-file projects yield the full body,
             # not just the primary file's skeleton of include directives (R-C).
             return flatten_inputs(files[primary_name], files)
-    except tarfile.TarError as exc:
-        logger.warning("Failed to open tar archive for %s: %s", arxiv_id, exc)
+    except tarfile.TarError:
+        # Old arXiv submissions are served as a single bare gzipped .tex with no
+        # tar wrapper (e.g. legacy math/* papers) — gunzip the body directly.
+        try:
+            single = gzip.decompress(raw).decode("utf-8", errors="replace")
+        except (OSError, EOFError) as exc:
+            logger.warning("Failed to read arXiv source for %s: %s", arxiv_id, exc)
+            return None
+        if "\\" in single[:5000]:  # looks like LaTeX (has backslash commands)
+            return single
+        logger.debug("arXiv source for %s is not LaTeX", arxiv_id)
         return None
 
-    return None  # unreachable but satisfies type checker
-
 
 def fetch_pdf_url(arxiv_id: str) -> str:
     """Return the canonical PDF URL for an arXiv paper.
diff --git a/tests/sources/test_arxiv.py b/tests/sources/test_arxiv.py
index f62ff82..db376c1 100644
--- a/tests/sources/test_arxiv.py
+++ b/tests/sources/test_arxiv.py
@@ -86,6 +86,30 @@ def test_fetch_source_flattens_multifile(monkeypatch: pytest.MonkeyPatch) -> Non
     assert "\\input" not in result and "\\include" not in result
 
 
+def test_fetch_source_bare_gzip_single_file(monkeypatch: pytest.MonkeyPatch) -> None:
+    """Legacy arXiv submissions are served as a single bare gzipped .tex (no tar
+    wrapper); fetch_source must gunzip the body directly rather than fail."""
+    import gzip
+
+    latex = b"\\documentstyle[a4]{article}\n\\section{Intro}\nOld single-file paper body."
+    gz_bytes = gzip.compress(latex)
+
+    def mock_get(
+        url: str,
+        *,
+        timeout: int = 60,
+        follow_redirects: bool = True,
+    ) -> httpx.Response:
+        return httpx.Response(200, content=gz_bytes)
+
+    monkeypatch.setattr(httpx, "get", mock_get)
+
+    result = arxiv.fetch_source("math/0001176")
+
+    assert result is not None
+    assert "Old single-file paper body." in result
+
+
 # ---------------------------------------------------------------------------
 # fetch_source — 404 → None
 # ---------------------------------------------------------------------------