fix(asr): use content_dir for subtitle output instead of video_path
PR Test / lint (pull_request) Successful in 2s

- Add content_dir field to ASRInput schema
- Pass content_dir from pipeline when creating ASRInput
- Modify _try_official_subtitle to use content_dir for output
- Modify _run_whisper_basic to use content_dir for output
- Add validation for empty video_path in Whisper fallback

Root cause: DownloadProcessor sets content_file="" for video types,
causing Path("").parent to resolve to current directory instead of
content directory. Subtitle files were written to wrong location.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-03-15 22:58:02 +08:00
parent b6ff7c81aa
commit 8ad64a4d1b
4 changed files with 48 additions and 22 deletions
+28 -14
View File
@@ -31,7 +31,8 @@ class TestASRInputSchema:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path="/path/to/video.mp4"
video_path="/path/to/video.mp4",
content_dir="/path/to/content"
)
# 验证继承
@@ -46,7 +47,8 @@ class TestASRInputSchema:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path="/path/to/video.mp4"
video_path="/path/to/video.mp4",
content_dir="/path/to/content"
)
assert hasattr(input_data, "video_path")
@@ -59,7 +61,8 @@ class TestASRInputSchema:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path="/path/to/video.mp4"
video_path="/path/to/video.mp4",
content_dir="/path/to/content"
)
assert input_data.content_type == "video"
@@ -222,7 +225,8 @@ class TestOfficialSubtitle:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
result = await processor._try_official_subtitle(input_data)
@@ -256,7 +260,8 @@ class TestOfficialSubtitle:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
result = await processor._try_official_subtitle(input_data)
@@ -283,7 +288,8 @@ class TestOfficialSubtitle:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
await processor.process(input_data)
@@ -325,7 +331,8 @@ class TestWhisperBasic:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
result = await processor._run_whisper_basic(input_data)
@@ -368,7 +375,8 @@ class TestWhisperBasic:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
await processor._run_whisper_basic(input_data)
@@ -392,7 +400,8 @@ class TestWhisperBasic:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
with pytest.raises(RuntimeError):
@@ -435,7 +444,8 @@ class TestDiarization:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
result = await processor._run_whisper(input_data)
@@ -470,7 +480,8 @@ class TestDiarization:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
result = await processor._run_whisper(input_data)
@@ -550,7 +561,8 @@ class TestStateRecording:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
await processor.process(input_data)
@@ -581,7 +593,8 @@ class TestStateRecording:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
with pytest.raises(Exception, match="Whisper error"):
@@ -611,7 +624,8 @@ class TestStateRecording:
input_data = ASRInput(
content_id="BV1xx",
platform="bilibili",
video_path=str(video_path)
video_path=str(video_path),
content_dir=str(tmp_path)
)
# 应该不抛异常