Recognize BitComet padding file names

Dockerfile

@@ -11,8 +11,12 @@ CMD ["python", "-m", "unittest", "discover", "-s", "tests", "-v"]
 
 FROM python:3.11-slim
 ENV PYTHONDONTWRITEBYTECODE=1 PYTHONUNBUFFERED=1
-RUN groupadd --gid 1001 archive-control \
+RUN if ! getent group 1001 >/dev/null; then \
-    && useradd --uid 1001 --gid 1001 --no-create-home archive-control
+        groupadd --gid 1001 archive-control; \
+    fi \
+    && if ! getent passwd 1001 >/dev/null; then \
+        useradd --uid 1001 --gid 1001 --no-create-home archive-control; \
+    fi
 COPY --from=builder /wheels /wheels
 RUN pip install --no-cache-dir /wheels/*.whl && rm -rf /wheels
 USER 1001:1001

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "archive-clients"
-version = "0.1.16"
+version = "0.1.19"
 requires-python = ">=3.11"
 dependencies = ["protobuf==7.35.1", "websockets==16.0"]
 

src/archive_clients/bencode.py

@@ -168,7 +168,7 @@ def _v1_files(info: dict[bytes, Any]) -> list[MetaFile]:
         components = [name] + [_component(part) for part in raw_path]
         result.append(MetaFile(
             "/".join(components), _length(item.get(b"length")),
-            _padding(item),
+            _padding(item) or _bitcomet_padding_name(components[-1]),
         ))
     return result
 
@@ -223,3 +223,13 @@ def _length(value: Any) -> int:
 def _padding(value: dict[bytes, Any]) -> bool:
     attributes = value.get(b"attr", b"")
     return isinstance(attributes, bytes) and b"p" in attributes
+
+
+def _bitcomet_padding_name(component: str) -> bool:
+    """Recognize BitComet's legacy padding-file convention.
+
+    Such v1 torrents often omit the standard ``attr=p`` flag, but
+    qBittorrent/libtorrent still hides these synthetic entries from its file
+    API.  The exact reserved prefix is the interoperable marker.
+    """
+    return component.startswith("_____padding_file_")

src/archive_clients/resources.py

@@ -91,12 +91,21 @@ def normalize_resource(
     observed_at: datetime | None = None,
 ) -> NormalizedResource:
     metainfo = decode_metainfo(metainfo_bytes)
-    if len(raw_files) != len(metainfo.files):
+    # qBittorrent/libtorrent may omit torrent padding files from
+    # /torrents/files while keeping them in the exported metainfo.
+    visible_metainfo_files = tuple(
+        item for item in metainfo.files if not item.padding
+    )
+    if len(raw_files) == len(metainfo.files):
+        matched_metainfo_files = metainfo.files
+    elif len(raw_files) == len(visible_metainfo_files):
+        matched_metainfo_files = visible_metainfo_files
+    else:
         raise ResourceError("qBittorrent and metainfo file counts differ")
     files = []
     canonical = True
     for expected_index, (raw, meta_file) in enumerate(
-        zip(raw_files, metainfo.files, strict=True)
+        zip(raw_files, matched_metainfo_files, strict=True)
     ):
         index = _integer(raw.get("index"), "file index")
         if index != expected_index:

tests/test_resources.py

@@ -118,6 +118,47 @@ class ResourceTests(unittest.TestCase):
         self.assertEqual(root.available_file_count, 1)
         self.assertEqual(root.available_logical_bytes, 3)
 
+    def test_qbittorrent_hidden_padding_files_are_normalized(self):
+        info = {
+            b"files": [
+                {b"length": 3, b"path": [b"first.bin"]},
+                {
+                    b"length": 5,
+                    b"path": [b"_____padding_file_5"],
+                },
+                {b"length": 7, b"path": [b"last.bin"]},
+            ],
+            b"name": b"with-padding",
+            b"piece length": 16384,
+            b"pieces": b"x" * 20,
+        }
+        metainfo = encode({b"info": info})
+        torrent_hash = hashlib.sha1(encode(info)).hexdigest()
+        normalized = normalize_resource(
+            {
+                "hash": torrent_hash,
+                "name": "with-padding",
+                "state": "stalledUP",
+            },
+            [
+                {
+                    "index": 0, "name": "with-padding/first.bin",
+                    "size": 3, "completed": 3, "priority": 1,
+                },
+                {
+                    "index": 1, "name": "with-padding/last.bin",
+                    "size": 7, "completed": 7, "priority": 1,
+                },
+            ],
+            metainfo,
+        )
+        self.assertEqual(
+            [item.canonical_path for item in normalized.files],
+            ["with-padding/first.bin", "with-padding/last.bin"],
+        )
+        self.assertEqual(normalized.summary.total_file_count, 2)
+        self.assertEqual(normalized.summary.selected_complete_bytes, 10)
+
     def test_noncanonical_and_unsafe_paths_are_distinct(self):
         info = {
             b"length": 3,