106 lines
3.5 KiB
Python
106 lines
3.5 KiB
Python
import pytest
|
|
|
|
from audita.core.config import (
|
|
AuditaConfig,
|
|
ConfigOverrides,
|
|
DEFAULT_GLOSSARY_CONFIDENCE_THRESHOLD,
|
|
DEFAULT_GRAMMAR_CONFIDENCE_THRESHOLD,
|
|
DEFAULT_HOMOPHONES_CONFIDENCE_THRESHOLD,
|
|
DEFAULT_NORMALIZE_MAX_SEGMENT_GAP,
|
|
DEFAULT_SPOKEN_WORD_CONFIDENCE_THRESHOLD,
|
|
DEFAULT_WORK_DIR_RETENTION,
|
|
)
|
|
from audita.core.errors import AuditaConfigError
|
|
from audita.modules import DEFAULT_MODULE_KEYS
|
|
|
|
|
|
def test_default_config_allows_missing_api_key():
|
|
config = AuditaConfig.from_sources(env={})
|
|
|
|
assert config.api_key is None
|
|
assert config.module_keys == DEFAULT_MODULE_KEYS
|
|
assert config.glossary_confidence_threshold == DEFAULT_GLOSSARY_CONFIDENCE_THRESHOLD
|
|
assert config.grammar_confidence_threshold == DEFAULT_GRAMMAR_CONFIDENCE_THRESHOLD
|
|
assert config.homophones_confidence_threshold == DEFAULT_HOMOPHONES_CONFIDENCE_THRESHOLD
|
|
assert config.spoken_word_confidence_threshold == DEFAULT_SPOKEN_WORD_CONFIDENCE_THRESHOLD
|
|
assert config.normalize_max_segment_gap == DEFAULT_NORMALIZE_MAX_SEGMENT_GAP
|
|
assert config.work_dir_retention == DEFAULT_WORK_DIR_RETENTION
|
|
|
|
|
|
def test_cli_overrides_take_precedence():
|
|
config = AuditaConfig.from_sources(
|
|
env={"AUDITA_MAX_SECTION_TOKENS": "1000"},
|
|
overrides=ConfigOverrides(max_section_tokens=2000),
|
|
)
|
|
|
|
assert config.max_section_tokens == 2000
|
|
|
|
|
|
def test_module_key_overrides_take_precedence():
|
|
config = AuditaConfig.from_sources(
|
|
env={"AUDITA_MODULES": "grammar"},
|
|
overrides=ConfigOverrides(module_keys="homophones,grammar"),
|
|
)
|
|
|
|
assert config.module_keys == ("homophones", "grammar")
|
|
|
|
|
|
def test_module_key_env_is_parsed_and_trimmed():
|
|
config = AuditaConfig.from_sources(env={"AUDITA_MODULES": " glossary , grammar "})
|
|
|
|
assert config.module_keys == ("glossary", "grammar")
|
|
|
|
|
|
def test_invalid_work_dir_retention_is_rejected():
|
|
with pytest.raises(AuditaConfigError):
|
|
AuditaConfig.from_sources(env={"AUDITA_WORK_DIR_RETENTION": "sometimes"})
|
|
|
|
|
|
def test_threshold_overrides_take_precedence():
|
|
config = AuditaConfig.from_sources(
|
|
env={
|
|
"AUDITA_GLOSSARY_CONFIDENCE_THRESHOLD": "0.6",
|
|
"AUDITA_GRAMMAR_CONFIDENCE_THRESHOLD": "0.65",
|
|
"AUDITA_HOMOPHONES_CONFIDENCE_THRESHOLD": "0.7",
|
|
"AUDITA_SPOKEN_WORD_CONFIDENCE_THRESHOLD": "0.75",
|
|
},
|
|
overrides=ConfigOverrides(
|
|
glossary_confidence_threshold=0.85,
|
|
grammar_confidence_threshold=0.88,
|
|
homophones_confidence_threshold=0.9,
|
|
spoken_word_confidence_threshold=0.95,
|
|
),
|
|
)
|
|
|
|
assert config.glossary_confidence_threshold == 0.85
|
|
assert config.grammar_confidence_threshold == 0.88
|
|
assert config.homophones_confidence_threshold == 0.9
|
|
assert config.spoken_word_confidence_threshold == 0.95
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"value",
|
|
[
|
|
"",
|
|
"grammar,,homophones",
|
|
"bogus",
|
|
],
|
|
)
|
|
def test_invalid_module_sequences_are_rejected(value):
|
|
with pytest.raises(AuditaConfigError, match="AUDITA_MODULES"):
|
|
AuditaConfig.from_sources(env={"AUDITA_MODULES": value})
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"env_name",
|
|
[
|
|
"AUDITA_GLOSSARY_CONFIDENCE_THRESHOLD",
|
|
"AUDITA_GRAMMAR_CONFIDENCE_THRESHOLD",
|
|
"AUDITA_HOMOPHONES_CONFIDENCE_THRESHOLD",
|
|
"AUDITA_SPOKEN_WORD_CONFIDENCE_THRESHOLD",
|
|
],
|
|
)
|
|
def test_invalid_thresholds_are_rejected(env_name):
|
|
with pytest.raises(AuditaConfigError):
|
|
AuditaConfig.from_sources(env={env_name: "1.5"})
|