scriptconv 0.0.2a2__tar.gz → 0.0.3a2__tar.gz

{scriptconv-0.0.2a2 → scriptconv-0.0.3a2}/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: scriptconv
-Version: 0.0.2a2
-Summary: Shared script-conversion core — ISO-15924 detection, IPA↔ARPA/X-SAMPA/Lexique, Buckwalter, Hangul→jamo
+Version: 0.0.3a2
+Summary: Zero-dependency script & phoneme-notation core — ISO-15924 detection & metadata, IPA↔ARPABET/X-SAMPA/Lexique/Kirshenbaum/Cotovía/RFE, Buckwalter↔Arabic, Hangul→jamo, kana
 License: Apache-2.0
 Project-URL: Homepage, https://github.com/TigreGotico/scriptconv
 Project-URL: Issues, https://github.com/TigreGotico/scriptconv/issues
-Keywords: ipa,arpabet,x-sampa,lexique,buckwalter,hangul,script,iso15924,tts,g2p,phoneme
+Keywords: ipa,arpabet,x-sampa,kirshenbaum,cotovia,rfe,lexique,buckwalter,hangul,jamo,kana,transliteration,notation,phoneme,phonetic-alphabet,script,iso15924,unicode,tts,g2p
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -20,9 +20,12 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Provides-Extra: ja
+Requires-Dist: pykakasi<3,>=2.3; extra == "ja"
 Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
 Requires-Dist: pytest-timeout; extra == "test"
+Requires-Dist: pykakasi<3,>=2.3; extra == "test"
 Dynamic: license-file
 
 # scriptconv
@@ -31,12 +34,21 @@ Dynamic: license-file
 [![Build Tests](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml/badge.svg?branch=dev)](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml)
 [![PyPI version](https://img.shields.io/pypi/v/scriptconv.svg)](https://pypi.org/project/scriptconv/)
 
-**scriptconv** is a zero-dependency Python library for written-script operations:
-ISO-15924 script identification and metadata, character-range detection, language-to-script
-mapping, phoneme-notation transcoding (IPA ↔ ARPABET / X-SAMPA / Lexique / Kirshenbaum / Cotovía / RFE,
-Buckwalter ↔ Arabic script), and orthographic decomposition of Hangul syllable blocks into
-jamo letters. Every conversion is a pure data table or arithmetic operation; no linguistic
-rules, no external files, no runtime dependencies beyond the Python standard library.
+**scriptconv** is a zero-dependency Python library for written-script and
+phoneme-notation operations:
+
+- **Script identification & metadata** — ISO-15924 detection, character-range
+  lookup, typological `script_type`, base direction, mixed-script segmentation
+  (`script_runs`), and language ↔ script mapping.
+- **Phoneme-notation transcoding** — IPA ↔ ARPABET, X-SAMPA, Lexique,
+  Kirshenbaum, Cotovía and RFE, routed through IPA, with queryable per-notation
+  fidelity metadata (`NOTATION_INFO`) and a `looks_like_ipa` detector.
+- **Script transliteration & decomposition** — Buckwalter ↔ Arabic script,
+  Hangul → jamo (compatibility or conjoining), Hiragana ↔ Katakana.
+
+Every conversion is a pure data table or arithmetic operation — **no
+phonemization**, no linguistic rules, no external files, and no runtime
+dependencies beyond the Python standard library.
 
 Transcoding is reversible where the target inventory permits — see
 [Fidelity guarantees](#fidelity-guarantees) for the exact per-notation guarantees.

{scriptconv-0.0.2a2 → scriptconv-0.0.3a2}/README.md

@@ -4,12 +4,21 @@
 [![Build Tests](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml/badge.svg?branch=dev)](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml)
 [![PyPI version](https://img.shields.io/pypi/v/scriptconv.svg)](https://pypi.org/project/scriptconv/)
 
-**scriptconv** is a zero-dependency Python library for written-script operations:
-ISO-15924 script identification and metadata, character-range detection, language-to-script
-mapping, phoneme-notation transcoding (IPA ↔ ARPABET / X-SAMPA / Lexique / Kirshenbaum / Cotovía / RFE,
-Buckwalter ↔ Arabic script), and orthographic decomposition of Hangul syllable blocks into
-jamo letters. Every conversion is a pure data table or arithmetic operation; no linguistic
-rules, no external files, no runtime dependencies beyond the Python standard library.
+**scriptconv** is a zero-dependency Python library for written-script and
+phoneme-notation operations:
+
+- **Script identification & metadata** — ISO-15924 detection, character-range
+  lookup, typological `script_type`, base direction, mixed-script segmentation
+  (`script_runs`), and language ↔ script mapping.
+- **Phoneme-notation transcoding** — IPA ↔ ARPABET, X-SAMPA, Lexique,
+  Kirshenbaum, Cotovía and RFE, routed through IPA, with queryable per-notation
+  fidelity metadata (`NOTATION_INFO`) and a `looks_like_ipa` detector.
+- **Script transliteration & decomposition** — Buckwalter ↔ Arabic script,
+  Hangul → jamo (compatibility or conjoining), Hiragana ↔ Katakana.
+
+Every conversion is a pure data table or arithmetic operation — **no
+phonemization**, no linguistic rules, no external files, and no runtime
+dependencies beyond the Python standard library.
 
 Transcoding is reversible where the target inventory permits — see
 [Fidelity guarantees](#fidelity-guarantees) for the exact per-notation guarantees.

{scriptconv-0.0.2a2 → scriptconv-0.0.3a2}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "scriptconv"
 dynamic = ["version", "dependencies"]
-description = "Shared script-conversion core — ISO-15924 detection, IPA↔ARPA/X-SAMPA/Lexique, Buckwalter, Hangul→jamo"
+description = "Zero-dependency script & phoneme-notation core — ISO-15924 detection & metadata, IPA↔ARPABET/X-SAMPA/Lexique/Kirshenbaum/Cotovía/RFE, Buckwalter↔Arabic, Hangul→jamo, kana"
 readme = "README.md"
 license = {text = "Apache-2.0"}
 requires-python = ">=3.10"
@@ -22,14 +22,19 @@ classifiers = [
     "License :: OSI Approved :: Apache Software License",
     "Operating System :: OS Independent",
 ]
-keywords = ["ipa", "arpabet", "x-sampa", "lexique", "buckwalter", "hangul", "script", "iso15924", "tts", "g2p", "phoneme"]
+keywords = [
+    "ipa", "arpabet", "x-sampa", "kirshenbaum", "cotovia", "rfe", "lexique",
+    "buckwalter", "hangul", "jamo", "kana", "transliteration", "notation",
+    "phoneme", "phonetic-alphabet", "script", "iso15924", "unicode", "tts", "g2p",
+]
 
 [tool.setuptools.dynamic]
 version = {attr = "scriptconv.version.VERSION_STR"}
 dependencies = {file = ["requirements.txt"]}
 
 [project.optional-dependencies]
-test = ["pytest", "pytest-timeout"]
+ja = ["pykakasi>=2.3,<3"]
+test = ["pytest", "pytest-timeout", "pykakasi>=2.3,<3"]
 
 [project.urls]
 Homepage = "https://github.com/TigreGotico/scriptconv"

{scriptconv-0.0.2a2 → scriptconv-0.0.3a2}/scriptconv/__init__.py

@@ -17,8 +17,12 @@ notation:
 translit:
     Script-level decomposition and transliteration (Hangul → jamo,
     Hiragana ↔ Katakana).
+readings:
+    Dictionary-backed respelling (Japanese kanji → kana).  Needs the
+    optional ``pykakasi`` dependency (``pip install scriptconv[ja]``).
 
-Zero runtime dependencies (stdlib only).
+Zero required runtime dependencies (stdlib only); the readings module
+needs the optional ``ja`` extra.
 """
 
 from scriptconv.scripts import (
@@ -61,6 +65,10 @@ from scriptconv.translit import (
     hira_to_kana,
     kana_to_hira,
 )
+from scriptconv.readings import (
+    to_hiragana,
+    to_katakana,
+)
 
 __all__ = [
     # scripts
@@ -100,4 +108,7 @@ __all__ = [
     "decompose_hangul",
     "hira_to_kana",
     "kana_to_hira",
+    # readings (dictionary-backed, needs scriptconv[ja])
+    "to_hiragana",
+    "to_katakana",
 ]

scriptconv-0.0.3a2/scriptconv/readings.py

@@ -0,0 +1,71 @@
+"""Dictionary-backed script respelling (Japanese kanji → kana).
+
+Unlike the table-driven modules (:mod:`scriptconv.translit`,
+:mod:`scriptconv.notation`), converting kanji to kana is not a codepoint
+mapping: a kanji's kana spelling is a *lexical* property resolved against a
+reading dictionary, and genuinely ambiguous readings are decided by the
+dictionary's segmentation.  This is still orthography — the output is how the
+word is written in kana, exactly as an IME or furigana would render it — not
+phonemization; no sound rules are applied.
+
+Because it needs a reading dictionary, this module requires the optional
+``pykakasi`` dependency (``pip install scriptconv[ja]``).  Importing the
+module is always safe; the dependency is resolved on first conversion and a
+missing dictionary raises :class:`ImportError` rather than silently returning
+unconverted text.
+"""
+from __future__ import annotations
+
+__all__ = ["to_hiragana", "to_katakana"]
+
+_kakasi = None
+
+_HIRA = range(0x3040, 0x30A0)
+_KANA = range(0x30A0, 0x3100)
+
+
+def _converter():
+    global _kakasi
+    if _kakasi is None:
+        try:
+            import pykakasi
+        except ImportError:
+            raise ImportError(
+                "kanji→kana conversion needs the reading dictionary from "
+                "pykakasi — install with `pip install scriptconv[ja]`"
+            ) from None
+        _kakasi = pykakasi.kakasi()
+    return _kakasi
+
+
+def to_hiragana(text: str, keep_katakana: bool = False) -> str:
+    """Respell Japanese text in hiragana.
+
+    Kanji are resolved to their dictionary reading; existing kana and any
+    non-Japanese characters pass through.  With ``keep_katakana=True``,
+    katakana tokens keep their original script (useful when katakana marks
+    loanwords deliberately) instead of being folded into hiragana.
+    """
+    out = []
+    for token in _converter().convert(text):
+        orig = token["orig"]
+        if keep_katakana and orig and all(ord(c) in _KANA or not _is_japanese(c)
+                                          for c in orig):
+            out.append(orig)
+        else:
+            out.append(token["hira"])
+    return "".join(out)
+
+
+def to_katakana(text: str) -> str:
+    """Respell Japanese text in katakana.
+
+    Kanji are resolved to their dictionary reading; existing kana are
+    transposed to katakana and any non-Japanese characters pass through.
+    """
+    return "".join(token["kana"] for token in _converter().convert(text))
+
+
+def _is_japanese(ch: str) -> bool:
+    cp = ord(ch)
+    return cp in _HIRA or cp in _KANA or 0x4E00 <= cp <= 0x9FFF

{scriptconv-0.0.2a2 → scriptconv-0.0.3a2}/scriptconv/version.py

@@ -1,7 +1,7 @@
 # START_VERSION_BLOCK
 VERSION_MAJOR = 0
 VERSION_MINOR = 0
-VERSION_BUILD = 2
+VERSION_BUILD = 3
 VERSION_ALPHA = 2
 # END_VERSION_BLOCK
 

{scriptconv-0.0.2a2 → scriptconv-0.0.3a2}/scriptconv.egg-info/PKG-INFO

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: scriptconv
-Version: 0.0.2a2
-Summary: Shared script-conversion core — ISO-15924 detection, IPA↔ARPA/X-SAMPA/Lexique, Buckwalter, Hangul→jamo
+Version: 0.0.3a2
+Summary: Zero-dependency script & phoneme-notation core — ISO-15924 detection & metadata, IPA↔ARPABET/X-SAMPA/Lexique/Kirshenbaum/Cotovía/RFE, Buckwalter↔Arabic, Hangul→jamo, kana
 License: Apache-2.0
 Project-URL: Homepage, https://github.com/TigreGotico/scriptconv
 Project-URL: Issues, https://github.com/TigreGotico/scriptconv/issues
-Keywords: ipa,arpabet,x-sampa,lexique,buckwalter,hangul,script,iso15924,tts,g2p,phoneme
+Keywords: ipa,arpabet,x-sampa,kirshenbaum,cotovia,rfe,lexique,buckwalter,hangul,jamo,kana,transliteration,notation,phoneme,phonetic-alphabet,script,iso15924,unicode,tts,g2p
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -20,9 +20,12 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Provides-Extra: ja
+Requires-Dist: pykakasi<3,>=2.3; extra == "ja"
 Provides-Extra: test
 Requires-Dist: pytest; extra == "test"
 Requires-Dist: pytest-timeout; extra == "test"
+Requires-Dist: pykakasi<3,>=2.3; extra == "test"
 Dynamic: license-file
 
 # scriptconv
@@ -31,12 +34,21 @@ Dynamic: license-file
 [![Build Tests](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml/badge.svg?branch=dev)](https://github.com/TigreGotico/scriptconv/actions/workflows/build-tests.yml)
 [![PyPI version](https://img.shields.io/pypi/v/scriptconv.svg)](https://pypi.org/project/scriptconv/)
 
-**scriptconv** is a zero-dependency Python library for written-script operations:
-ISO-15924 script identification and metadata, character-range detection, language-to-script
-mapping, phoneme-notation transcoding (IPA ↔ ARPABET / X-SAMPA / Lexique / Kirshenbaum / Cotovía / RFE,
-Buckwalter ↔ Arabic script), and orthographic decomposition of Hangul syllable blocks into
-jamo letters. Every conversion is a pure data table or arithmetic operation; no linguistic
-rules, no external files, no runtime dependencies beyond the Python standard library.
+**scriptconv** is a zero-dependency Python library for written-script and
+phoneme-notation operations:
+
+- **Script identification & metadata** — ISO-15924 detection, character-range
+  lookup, typological `script_type`, base direction, mixed-script segmentation
+  (`script_runs`), and language ↔ script mapping.
+- **Phoneme-notation transcoding** — IPA ↔ ARPABET, X-SAMPA, Lexique,
+  Kirshenbaum, Cotovía and RFE, routed through IPA, with queryable per-notation
+  fidelity metadata (`NOTATION_INFO`) and a `looks_like_ipa` detector.
+- **Script transliteration & decomposition** — Buckwalter ↔ Arabic script,
+  Hangul → jamo (compatibility or conjoining), Hiragana ↔ Katakana.
+
+Every conversion is a pure data table or arithmetic operation — **no
+phonemization**, no linguistic rules, no external files, and no runtime
+dependencies beyond the Python standard library.
 
 Transcoding is reversible where the target inventory permits — see
 [Fidelity guarantees](#fidelity-guarantees) for the exact per-notation guarantees.

{scriptconv-0.0.2a2 → scriptconv-0.0.3a2}/scriptconv.egg-info/SOURCES.txt

@@ -6,6 +6,7 @@ scriptconv/__init__.py
 scriptconv/__main__.py
 scriptconv/notation.py
 scriptconv/py.typed
+scriptconv/readings.py
 scriptconv/scripts.py
 scriptconv/translit.py
 scriptconv/version.py
@@ -17,5 +18,6 @@ scriptconv.egg-info/top_level.txt
 tests/test_cli.py
 tests/test_examples.py
 tests/test_notation.py
+tests/test_readings.py
 tests/test_scripts.py
 tests/test_translit.py

scriptconv-0.0.3a2/scriptconv.egg-info/requires.txt

@@ -0,0 +1,8 @@
+
+[ja]
+pykakasi<3,>=2.3
+
+[test]
+pytest
+pytest-timeout
+pykakasi<3,>=2.3

scriptconv-0.0.3a2/tests/test_readings.py

@@ -0,0 +1,73 @@
+import sys
+import unittest
+from unittest import mock
+
+from scriptconv import to_hiragana, to_katakana
+from scriptconv import readings
+
+
+class TestToHiragana(unittest.TestCase):
+    def test_kanji_resolved_to_reading(self):
+        self.assertEqual(to_hiragana("日本語"), "にほんご")
+
+    def test_katakana_folded_by_default(self):
+        self.assertEqual(to_hiragana("コーヒー"), "こーひー")
+
+    def test_keep_katakana_flag_preserves_loanwords(self):
+        self.assertEqual(to_hiragana("コーヒー", keep_katakana=True), "コーヒー")
+
+    def test_keep_katakana_still_converts_kanji(self):
+        out = to_hiragana("私はコーヒーが好き", keep_katakana=True)
+        self.assertIn("コーヒー", out)
+        self.assertNotIn("私", out)
+        self.assertNotIn("好", out)
+
+    def test_hiragana_passes_through(self):
+        self.assertEqual(to_hiragana("こんにちは"), "こんにちは")
+
+    def test_non_japanese_passes_through(self):
+        self.assertEqual(to_hiragana("OVOS 123!"), "OVOS 123!")
+
+    def test_mixed_script_sentence(self):
+        out = to_hiragana("東京タワーは333mです")
+        self.assertIn("とうきょう", out)
+        self.assertIn("333m", out)
+
+    def test_empty_string(self):
+        self.assertEqual(to_hiragana(""), "")
+
+
+class TestToKatakana(unittest.TestCase):
+    def test_kanji_resolved_to_reading(self):
+        self.assertEqual(to_katakana("日本語"), "ニホンゴ")
+
+    def test_hiragana_transposed(self):
+        self.assertEqual(to_katakana("こんにちは"), "コンニチハ")
+
+    def test_katakana_passes_through(self):
+        self.assertEqual(to_katakana("コーヒー"), "コーヒー")
+
+    def test_non_japanese_passes_through(self):
+        self.assertEqual(to_katakana("OVOS 123!"), "OVOS 123!")
+
+    def test_empty_string(self):
+        self.assertEqual(to_katakana(""), "")
+
+
+class TestDependencyBoundary(unittest.TestCase):
+    def test_missing_pykakasi_raises_with_install_hint(self):
+        with mock.patch.object(readings, "_kakasi", None), \
+                mock.patch.dict(sys.modules, {"pykakasi": None}):
+            with self.assertRaises(ImportError) as ctx:
+                to_hiragana("日本語")
+            self.assertIn("scriptconv[ja]", str(ctx.exception))
+
+    def test_converter_instance_is_cached(self):
+        to_hiragana("日本語")
+        first = readings._kakasi
+        to_katakana("日本語")
+        self.assertIs(readings._kakasi, first)
+
+
+if __name__ == "__main__":
+    unittest.main()

scriptconv-0.0.2a2/scriptconv.egg-info/requires.txt

@@ -1,4 +0,0 @@
-
-[test]
-pytest
-pytest-timeout