fix(pixiv): match gallery-dl's exact on-disk filename to avoid re-download at cutover

The native downloader used the Windows-safe sanitize_segment, but gallery-dl on
Linux (path-restrict auto→'/', path-remove default control chars, path-strip
auto→'') replaces ONLY '/' and deletes control chars — the Windows-forbidden set
(<>:"|?*) and trailing dots/spaces stay RAW in on-disk titles. Any pixiv title
with those chars would therefore miss the tier-2 disk-skip and re-download the
whole work at cutover (seen-ledger starts empty). Replace sanitize_segment with
gdl_clean_filename, a byte-exact mirror of gallery-dl 1.32.5 build_filename
(verified against path.py). Directory + template already matched; this closes the
last parity gap.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM

backend/app/services/pixiv_downloader.py

@@ -34,6 +34,7 @@ from __future__ import annotations
 
 import json
 import logging
+import re
 import time
 from collections.abc import Callable
 from pathlib import Path
@@ -44,12 +45,32 @@ from .native_ingest_common import (
     BaseNativeDownloader,
     MediaOutcome,
     PostRecordOutcome,
-    sanitize_segment,
 )
 from .pixiv_client import PIXIV_APP_HEADERS, rating_label
 
 log = logging.getLogger(__name__)
 
+# Control chars (0x00–0x1f + 0x7f DEL) — gallery-dl's default `path-remove`.
+_GDL_PATH_REMOVE_RE = re.compile(r"[\x00-\x1f\x7f]")
+
+
+def gdl_clean_filename(name: str) -> str:
+    """Reproduce gallery-dl's on-disk filename EXACTLY as it wrote it on this
+    Linux host, so the tier-2 disk-skip recognizes pre-cutover files instead of
+    re-downloading them.
+
+    gallery-dl's PathFormat.build_filename is `clean_path(clean_segment(name))`.
+    On Linux (verified against gallery-dl 1.32.5 path.py) the defaults resolve to:
+      - path-restrict "auto" → "/"          → clean_segment replaces ONLY "/" → "_"
+      - path-remove   "\\x00-\\x1f\\x7f"       → clean_path DELETES control chars
+      - path-strip    "auto" → ""           → NO trailing dot/space stripping
+    Crucially it does NOT touch the Windows-forbidden set (<>:"|?*) — those stay
+    raw in titles on disk. A stricter sanitizer here would rename any such title,
+    miss the on-disk match, and re-pull the whole work. Order mirrors gallery-dl
+    (segment inner, path outer); for these disjoint char sets it's commutative.
+    """
+    return _GDL_PATH_REMOVE_RE.sub("", name.replace("/", "_"))
+
 # Enrichment keys copied verbatim from the app-API work dict into the post
 # record (they're already JSON scalars/objects). Everything lands in
 # Post.raw_metadata via the importer, so the archive keeps pixiv's stats and
@@ -150,9 +171,11 @@ class PixivDownloader(BaseNativeDownloader):
         if seen and not recapture:
             return MediaOutcome(media=media, status="skipped_seen", path=None, error=None)
 
-        # The client's filename already carries the {id}_{title50}_{NN} shape;
+        # The client's filename already carries the {id}_{title50}_{NN} shape
-        # only path-restrict sanitization happens here.
+        # (raw title, gallery-dl-template order); clean it to the byte-exact
-        media_path = flat_dir / sanitize_segment(media.filename)
+        # name gallery-dl wrote on disk so tier-2 disk-skip matches (else a
+        # re-download of the whole work). See gdl_clean_filename.
+        media_path = flat_dir / gdl_clean_filename(media.filename)
 
         if media_path.exists():  # tier-2: already on disk
             return MediaOutcome(

tests/test_pixiv_downloader.py

@@ -178,11 +178,15 @@ def test_download_post_honours_should_stop(tmp_path):
     assert outcomes == []
 
 
-def test_filename_is_sanitized(tmp_path):
+def test_filename_matches_gallery_dl_linux_restrict(tmp_path):
+    # gallery-dl on Linux replaces ONLY "/" and deletes control chars — the
+    # Windows-forbidden set (<>:"|?*) stays RAW in the on-disk name. Matching
+    # that byte-for-byte is what lets the tier-2 disk-skip recognize
+    # pre-cutover files; a stricter sanitizer would re-download them.
     post, _ = _post_and_media(222)
     weird = MediaItem(
         url="https://i.pximg.net/img-original/img/2026/06/18/12/30/00/222_p0.jpg",
-        filename='222_What? A "Title"/Slash_00.jpg',
+        filename='222_What? A "Title"/Slash\x0900.jpg',  # ? " stay, / → _, \t dropped
         kind="image",
         filehash=None,
         post_id="222",
@@ -191,7 +195,18 @@ def test_filename_is_sanitized(tmp_path):
     dl = _downloader(tmp_path)
     outcomes = dl.download_post(post, [weird], "artist-a")
     assert outcomes[0].status == "downloaded"
-    assert outcomes[0].path.name == "222_What_ A _Title__Slash_00.jpg"
+    assert outcomes[0].path.name == '222_What? A "Title"_Slash00.jpg'
+
+
+def test_gdl_clean_filename_parity():
+    from backend.app.services.pixiv_downloader import gdl_clean_filename
+    # Only "/" is replaced; the Windows-forbidden set is untouched.
+    assert gdl_clean_filename('a<>:"|?*b.png') == 'a<>:"|?*b.png'
+    assert gdl_clean_filename("a/b/c.png") == "a_b_c.png"
+    # Control chars (newline, tab, DEL) are deleted, not replaced.
+    assert gdl_clean_filename("a\nb\tc\x7fd.png") == "abcd.png"
+    # Trailing dots/spaces are NOT stripped on Linux.
+    assert gdl_clean_filename("title . .png") == "title . .png"
 
 
 def test_own_session_carries_app_referer(tmp_path):