eric/audita
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

Updated configuration to utilize segment ids provided in the input transcript

Browse Source
This commit is contained in:
Eric Rakestraw
2026-04-21 15:01:31 -05:00
parent 7e1a3f721a
commit ca01e46d77
13 changed files with 186 additions and 97 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
tests/test_validation.py
View File

@@ -8,12 +8,13 @@ def test_valid_transcript_parses():
segments = parse_transcript_json(
"""
[
{"speaker": "Eric", "start": 0.0, "end": 1.25, "text": "Then Lyra."}
{"id": 1, "speaker": "Eric", "start": 0.0, "end": 1.25, "text": "Then Lyra."}
]
"""
)
assert len(segments) == 1
assert segments[0].id == 1
assert segments[0].speaker == "Eric"
@@ -22,7 +23,7 @@ def test_transcript_rejects_extra_fields():
parse_transcript_json(
"""
[
{"speaker": "Eric", "start": 0.0, "end": 1.25, "text": "Hi", "extra": true}
{"id": 1, "speaker": "Eric", "start": 0.0, "end": 1.25, "text": "Hi", "extra": true}
]
"""
)
@@ -33,7 +34,64 @@ def test_transcript_rejects_bad_timestamps():
parse_transcript_json(
"""
[
{"speaker": "Eric", "start": 2.0, "end": 1.0, "text": "Hi"}
{"id": 1, "speaker": "Eric", "start": 2.0, "end": 1.0, "text": "Hi"}
]
"""
)
def test_transcript_rejects_missing_id():
with pytest.raises(AuditaValidationError):
parse_transcript_json(
"""
[
{"speaker": "Eric", "start": 0.0, "end": 1.0, "text": "Hi"}
]
"""
)
def test_transcript_rejects_duplicate_ids():
with pytest.raises(AuditaValidationError):
parse_transcript_json(
"""
[
{"id": 1, "speaker": "Eric", "start": 0.0, "end": 1.0, "text": "Hi"},
{"id": 1, "speaker": "Mike", "start": 1.0, "end": 2.0, "text": "There"}
]
"""
)
def test_transcript_rejects_nonsequential_ids():
with pytest.raises(AuditaValidationError):
parse_transcript_json(
"""
[
{"id": 1, "speaker": "Eric", "start": 0.0, "end": 1.0, "text": "Hi"},
{"id": 3, "speaker": "Mike", "start": 1.0, "end": 2.0, "text": "There"}
]
"""
)
def test_transcript_rejects_zero_or_negative_id():
with pytest.raises(AuditaValidationError):
parse_transcript_json(
"""
[
{"id": 0, "speaker": "Eric", "start": 0.0, "end": 1.0, "text": "Hi"}
]
"""
)
def test_transcript_rejects_noninteger_id():
with pytest.raises(AuditaValidationError):
parse_transcript_json(
"""
[
{"id": 1.5, "speaker": "Eric", "start": 0.0, "end": 1.0, "text": "Hi"}
]
"""
)
@@ -73,4 +131,3 @@ def test_glossary_rejects_extra_fields():
extra: "nope"
"""
)