115 lines
3.9 KiB
Python
115 lines
3.9 KiB
Python
import json
|
|
|
|
from audita.core.config import AuditaConfig
|
|
from audita.core.io import write_report
|
|
from audita.core.schemas import parse_glossary_yaml, parse_source_transcript_json
|
|
from audita.modules import default_module_specs
|
|
from audita.pipeline import process_transcript, process_transcript_result
|
|
|
|
|
|
def _glossary():
|
|
return parse_glossary_yaml(
|
|
"""
|
|
glossary:
|
|
- name: "Jesters"
|
|
category: faction
|
|
summary: "A faction."
|
|
"""
|
|
)
|
|
|
|
|
|
def _transcript():
|
|
return parse_source_transcript_json(
|
|
"""
|
|
[
|
|
{"speaker": "Eric", "start": 0.0, "end": 1.0, "text": "Hello."},
|
|
{"speaker": "Eric", "start": 1.5, "end": 2.0, "text": "Again."},
|
|
{"speaker": "Mike", "start": 10.0, "end": 11.0, "text": "Done."}
|
|
]
|
|
"""
|
|
)
|
|
|
|
|
|
def test_process_transcript_runs_noop_framework(tmp_path):
|
|
revised = process_transcript(
|
|
_transcript(),
|
|
_glossary(),
|
|
AuditaConfig.from_sources(env={}, overrides=None),
|
|
)
|
|
|
|
assert [segment.id for segment in revised] == [1, 2]
|
|
assert revised[0].text == "Hello. Again."
|
|
assert revised[1].text == "Done."
|
|
|
|
|
|
def test_process_transcript_result_writes_report_and_preserves_skips_per_policy(tmp_path):
|
|
config = AuditaConfig.from_sources(
|
|
env={},
|
|
overrides=None,
|
|
)
|
|
config = AuditaConfig(
|
|
api_key=config.api_key,
|
|
model=config.model,
|
|
base_url=config.base_url,
|
|
max_retries=config.max_retries,
|
|
max_section_tokens=config.max_section_tokens,
|
|
normalize_max_segment_gap=config.normalize_max_segment_gap,
|
|
normalize_ellipsis_gap=config.normalize_ellipsis_gap,
|
|
normalize_max_segment_duration=config.normalize_max_segment_duration,
|
|
normalize_max_segment_tokens=config.normalize_max_segment_tokens,
|
|
work_dir=tmp_path / "work",
|
|
work_dir_retention="always",
|
|
)
|
|
|
|
result = process_transcript_result(_transcript(), _glossary(), config)
|
|
|
|
assert result.work_dir_retained is True
|
|
assert result.report.pipeline == [
|
|
"glossary_primary",
|
|
"homophones",
|
|
"glossary_secondary",
|
|
"spoken_word",
|
|
"grammar",
|
|
]
|
|
assert result.report.totals["applied_change_count"] == 0
|
|
assert (result.run_dir / "report.json").exists()
|
|
assert (result.run_dir / "normalization" / "summary.json").exists()
|
|
assert [validator["name"] for validator in result.report.modules[0].to_dict()["validators"]] == [
|
|
"protected_glossary_guard",
|
|
"spoken_form_plausibility_review",
|
|
"meaning_reversal_review",
|
|
]
|
|
|
|
|
|
def test_external_report_can_be_written(tmp_path):
|
|
config = AuditaConfig.from_sources(env={})
|
|
result = process_transcript_result(_transcript(), _glossary(), config)
|
|
report_path = tmp_path / "report.json"
|
|
write_report(report_path, result.report)
|
|
|
|
payload = json.loads(report_path.read_text(encoding="utf-8"))
|
|
assert payload["pipeline"][0] == "glossary_primary"
|
|
assert payload["totals"]["applied_change_count"] == 0
|
|
|
|
|
|
def test_default_module_specs_expose_final_validator_order():
|
|
specs = default_module_specs()
|
|
|
|
assert [validator.name for validator in specs[0].module.validators()] == [
|
|
"protected_glossary_guard",
|
|
"spoken_form_plausibility_review",
|
|
"meaning_reversal_review",
|
|
]
|
|
assert [validator.name for validator in specs[1].module.validators()] == [
|
|
"protected_glossary_guard",
|
|
"spoken_form_plausibility_review",
|
|
"meaning_reversal_review",
|
|
]
|
|
assert [validator.name for validator in specs[2].module.validators()] == [
|
|
"protected_glossary_guard",
|
|
"spoken_form_plausibility_review",
|
|
"meaning_reversal_review",
|
|
]
|
|
assert [validator.name for validator in specs[3].module.validators()] == ["protected_glossary_guard"]
|
|
assert [validator.name for validator in specs[4].module.validators()] == ["protected_glossary_guard"]
|