Dymas/abogen
1
0
Fork 0
mirror of https://github.com/denizsafak/abogen.git synced 2026-09-20 11:40:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

refactor: Language Enum with ISO codes

Browse Source 
- Language enum: en-US, en-GB, es, fr, hi, it, ja, pt-BR, zh
- Engine-specific mappings (kokoro → single-letter) live in pipeline_factory and synthesize
- spacy_utils uses Language enum keys for model mapping
- split_pattern uses Language enum properties (is_cjk)
- Updated all tests to use ISO codes
This commit is contained in:
Artem Akymenko
2026-07-22 10:54:39 +00:00
parent 4aef73ff85
commit 0805e9fdae
11 changed files with 206 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_split_pattern.py
+20 -20
View File
@@ -12,49 +12,49 @@ from abogen.domain.split_pattern import get_split_pattern
class TestEnglish:
def test_english_sentence(self):
assert get_split_pattern("a", "Sentence") == "\n"
assert get_split_pattern("en-US", "Sentence") == "\n"
def test_english_sentence_comma(self):
assert get_split_pattern("a", "Sentence + Comma") == "\n"
assert get_split_pattern("en-US", "Sentence + Comma") == "\n"
def test_english_line(self):
assert get_split_pattern("a", "Line") == "\n"
assert get_split_pattern("en-US", "Line") == "\n"
def test_english_disabled(self):
assert get_split_pattern("a", "Disabled") == "\n"
assert get_split_pattern("en-US", "Disabled") == "\n"
def test_english_b(self):
assert get_split_pattern("b", "Sentence") == "\n"
def test_english_gb(self):
assert get_split_pattern("en-GB", "Sentence") == "\n"
# --- CJK languages ---
class TestCJK:
def test_chinese_disabled(self):
pattern = get_split_pattern("z", "Disabled")
pattern = get_split_pattern("zh", "Disabled")
assert pattern != "\n"
assert r"\n+" in pattern
def test_chinese_line(self):
pattern = get_split_pattern("z", "Line")
pattern = get_split_pattern("zh", "Line")
assert pattern != "\n"
assert r"\n+" in pattern
def test_chinese_sentence(self):
pattern = get_split_pattern("z", "Sentence")
pattern = get_split_pattern("zh", "Sentence")
assert r"\n+" in pattern
def test_chinese_sentence_comma(self):
pattern = get_split_pattern("z", "Sentence + Comma")
pattern = get_split_pattern("zh", "Sentence + Comma")
assert r"\n+" in pattern
def test_japanese_disabled(self):
pattern = get_split_pattern("j", "Disabled")
pattern = get_split_pattern("ja", "Disabled")
assert pattern != "\n"
assert r"\n+" in pattern
def test_japanese_sentence(self):
pattern = get_split_pattern("j", "Sentence")
pattern = get_split_pattern("ja", "Sentence")
assert r"\n+" in pattern
@@ -62,18 +62,18 @@ class TestCJK:
class TestOtherLanguages:
def test_spanish_sentence(self):
pattern = get_split_pattern("e", "Sentence")
pattern = get_split_pattern("es", "Sentence")
assert r"\n+" in pattern
def test_spanish_line(self):
assert get_split_pattern("e", "Line") == "\n"
assert get_split_pattern("es", "Line") == "\n"
def test_spanish_disabled(self):
# canonical: \n+ for non-CJK Disabled
assert get_split_pattern("e", "Disabled") == r"\n+"
assert get_split_pattern("es", "Disabled") == r"\n+"
def test_french_sentence_comma(self):
pattern = get_split_pattern("f", "Sentence + Comma")
pattern = get_split_pattern("fr", "Sentence + Comma")
assert r"\n+" in pattern
def test_unknown_lang(self):
@@ -85,17 +85,17 @@ class TestOtherLanguages:
class TestPatternStructure:
def test_sentence_has_lookbehind(self):
pattern = get_split_pattern("e", "Sentence")
pattern = get_split_pattern("es", "Sentence")
assert r"(?<=" in pattern
def test_sentence_comma_has_comma_chars(self):
pattern = get_split_pattern("e", "Sentence + Comma")
pattern = get_split_pattern("es", "Sentence + Comma")
assert "," in pattern
def test_cjk_spacing_uses_star(self):
pattern = get_split_pattern("z", "Sentence")
pattern = get_split_pattern("zh", "Sentence")
assert r"\s*" in pattern
def test_non_cjk_spacing_uses_plus(self):
pattern = get_split_pattern("e", "Sentence")
pattern = get_split_pattern("es", "Sentence")
assert r"\s+" in pattern