lipimala 1.0.0__tar.gz

lipimala-1.0.0/.gitignore

@@ -0,0 +1,62 @@
+# Python bytecode
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Virtual environments
+.venv/
+venv/
+env/
+ENV/
+
+# Packaging / build
+build/
+dist/
+*.egg-info/
+.eggs/
+wheels/
+pip-wheel-metadata/
+
+# Test / coverage
+.pytest_cache/
+.coverage
+.coverage.*
+htmlcov/
+coverage.xml
+*.cover
+.hypothesis/
+
+# Ruff
+.ruff_cache/
+
+# Mypy / type checker caches
+.mypy_cache/
+.pyright/
+.pytype/
+
+# IDEs / Editors
+.idea/
+.vscode/
+
+# OS files
+.DS_Store
+Thumbs.db
+
+# Logs / temporary files
+*.log
+*.tmp
+*.temp
+*.bak
+*.swp
+*.swo
+
+# Local environment / secrets
+.env
+.env.*
+!.env.example
+
+# Generated verification outputs
+*_output.txt
+
+# Local scratch / grabbed content
+grabbed_stuffs/

lipimala-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Jayesh Mepani
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

lipimala-1.0.0/PKG-INFO

@@ -0,0 +1,207 @@
+Metadata-Version: 2.4
+Name: lipimala
+Version: 1.0.0
+Summary: Exact Round-Trip IAST/extended Indic transliteration for Devanagari, Gujarati, plain English and canonical reverse conversion.
+Project-URL: Homepage, https://github.com/jayeshmepani/indic-script-converter
+Project-URL: Source, https://github.com/jayeshmepani/indic-script-converter
+Project-URL: Issues, https://github.com/jayeshmepani/indic-script-converter/issues
+Author-email: Jayesh Mepani <jayeshmepani777@gmail.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: devanagari,exact round-trip,gujarati,iast,indic,sanskrit,transliteration,vedic
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.12
+Provides-Extra: dev
+Requires-Dist: build>=1.0.0; extra == 'dev'
+Requires-Dist: pytest>=8.3.0; extra == 'dev'
+Requires-Dist: ruff>=0.9.0; extra == 'dev'
+Requires-Dist: twine>=4.0.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# Exact Round-Trip Indic Transliteration — Python 3.12+ port
+
+This directory is a Python port of the supplied Dart implementation. It keeps the Dart package's default **`extendedIndic`** behavior and ports all public conversion directions:
+
+- Latin/IAST → Devanagari
+- Latin/IAST → Gujarati
+- Latin/IAST → plain English/Hunterian
+- Devanagari → canonical Latin/IAST
+- Gujarati → canonical Latin/IAST
+- metadata-backed exact source recovery
+- exact round-trip result envelopes and JSON serialization
+
+The runtime has no third-party dependency. Python's standard `unicodedata` module supplies NFC/NFD normalization and Unicode mark categories.
+
+## Install
+
+```bash
+cd python
+python3.12 -m venv .venv
+source .venv/bin/activate
+python -m pip install -e .
+```
+
+For tests:
+
+```bash
+python -m pip install -e '.[dev]'
+python -m pytest
+```
+
+## Basic conversions
+
+```python
+from lipimala import (
+    to_devanagari_from_iast,
+    to_gujarati_from_iast,
+    to_plain_english_from_iast,
+    to_canonical_iast_from_devanagari,
+    to_canonical_iast_from_gujarati,
+)
+
+assert to_devanagari_from_iast('Kṛṣṇa') == 'कृष्ण'
+assert to_gujarati_from_iast('Kṛṣṇa') == 'કૃષ્ણ'
+assert to_plain_english_from_iast('Kṛṣṇa') == 'Krishna'
+assert to_canonical_iast_from_devanagari('कृष्ण') == 'kṛṣṇa'
+assert to_canonical_iast_from_gujarati('કૃષ્ણ') == 'kṛṣṇa'
+```
+
+## Exact original-key recovery
+
+Visible Brahmic output is many-to-one. For example, aliases, case, and NFC/NFD forms can render identically. Exact recovery therefore uses the same checksummed invisible Unicode-tag trailer as the Dart implementation.
+
+```python
+from lipimala import (
+    IastToDevanagariOptions,
+    IastToGujaratiOptions,
+    to_devanagari_from_iast,
+    to_gujarati_from_iast,
+    to_exact_iast_from_devanagari,
+    to_exact_iast_from_gujarati,
+)
+
+source = 'Kṛṣṇa / Kr̥ṣṇa / ḫāna / ṣ́akti'
+
+devanagari = to_devanagari_from_iast(
+    source,
+    IastToDevanagariOptions(embed_exact_source_metadata=True),
+)
+gujarati = to_gujarati_from_iast(
+    source,
+    IastToGujaratiOptions(embed_exact_source_metadata=True),
+)
+
+assert to_exact_iast_from_devanagari(devanagari) == source
+assert to_exact_iast_from_gujarati(gujarati) == source
+```
+
+The metadata stores the exact UTF-16LE code-unit sequence and preserves:
+
+- case
+- precomposed versus decomposed spelling
+- combining-mark order
+- aliases
+- punctuation and whitespace
+- supplementary Unicode characters
+- unpaired UTF-16 surrogates through Python's `surrogatepass` handling
+
+The trailer is rejected if either the visible rendering or encoded source payload is modified.
+
+## Exact Round-Trip envelope
+
+```python
+import json
+
+from lipimala import (
+    TransliterationResult,
+    to_plain_english,
+)
+
+result = to_plain_english('Kṛṣṇa ā́tman ḷa')
+assert result.restore_original() == 'Kṛṣṇa ā́tman ḷa'
+
+encoded = json.dumps(result.to_json(), ensure_ascii=False)
+restored = TransliterationResult.from_json(json.loads(encoded))
+assert restored.restore_original() == result.original
+```
+
+## Devanagari ↔ Gujarati Direct Converter
+
+This package includes a direct converter between Devanagari and Gujarati.
+
+### Canonical visible conversion
+```python
+from lipimala.deva_gujr_converter import (
+    to_canonical_gujarati_from_devanagari,
+    to_canonical_devanagari_from_gujarati,
+)
+
+print(to_canonical_gujarati_from_devanagari('कृष्ण'))  # કૃષ્ણ
+print(to_canonical_devanagari_from_gujarati('કૃષ્ણ'))  # कृष्ण
+```
+
+### Exact exact round-trip round trip
+The visible Gujarati and Devanagari repertoires are not one-to-one. Therefore, exact round-trip recovery uses a checksummed Unicode-tag trailer.
+
+```python
+from lipimala.deva_gujr_converter import (
+    IndicScriptConversionOptions,
+    to_canonical_gujarati_from_devanagari,
+    to_exact_devanagari_from_gujarati,
+)
+
+source = 'ऄ ऎ ऍ ॲ ऒ ऑ ॵ ळ ऴ ग़ ॻ ड़ ॸ ॾ'
+
+tagged_gujarati = to_canonical_gujarati_from_devanagari(
+    source,
+    IndicScriptConversionOptions(embed_exact_source_metadata=True),
+)
+
+assert to_exact_devanagari_from_gujarati(tagged_gujarati) == source
+```
+
+The opposite Gujarati → Devanagari → exact Gujarati direction uses `to_exact_gujarati_from_devanagari`.
+
+### Smart exact-or-canonical APIs
+These recover a correctly typed exact source trailer if present, and otherwise fall back to canonical visible conversion:
+- `to_devanagari_from_gujarati(text, options)`
+- `to_gujarati_from_devanagari(text, options)`
+
+Strict exact APIs throw when typed metadata is absent or damaged:
+- `to_exact_devanagari_from_gujarati(text)`
+- `to_exact_gujarati_from_devanagari(text)`
+
+## Generate the verification outputs
+
+Run from this directory after installation:
+
+```bash
+python3 -m tools.latn_iast_transliteration_verification.latn_iast_to_deva_test > latn_iast_to_deva_output.txt
+python3 -m tools.latn_iast_transliteration_verification.latn_iast_to_gujr_test > latn_iast_to_gujr_output.txt
+python3 -m tools.latn_iast_transliteration_verification.latn_iast_transcription_test > latn_iast_transcription_output.txt
+python3 -m tools.latn_iast_transliteration_verification.deva_to_latn_iast_test > deva_to_latn_iast_output.txt
+python3 -m tools.latn_iast_transliteration_verification.gujr_to_latn_iast_test > gujr_to_latn_iast_output.txt
+python3 -m tools.latn_iast_transliteration_verification.deva_to_gujr_test > deva_to_gujr_output.txt
+python3 -m tools.latn_iast_transliteration_verification.gujr_to_deva_test > gujr_to_deva_output.txt
+```
+
+## Verification performed
+
+The automated parity suite compares the Python implementation against the five supplied Dart-generated output files:
+
+- 497 Latin → Devanagari cases
+- 497 Latin → Gujarati cases
+- 497 Latin → plain-English cases
+- 497 Devanagari → canonical IAST cases
+- 497 Gujarati → canonical IAST cases
+
+That is **2,485 exact result comparisons**, including the complete supplied Vedic corpus. Additional tests cover exact metadata recovery, normalization distinctions, combining-mark order, supplementary characters, JSON envelopes, and tamper rejection.
+
+## Important distinction
+
+`to_canonical_iast_from_devanagari()` and `to_canonical_iast_from_gujarati()` generate canonical reverse transliteration from visible text. They cannot infer the exact original alias or case. Use `embed_exact_source_metadata=True` plus `to_exact_iast_from_*()` when the exact original key must be recovered.

lipimala-1.0.0/README.md

@@ -0,0 +1,182 @@
+# Exact Round-Trip Indic Transliteration — Python 3.12+ port
+
+This directory is a Python port of the supplied Dart implementation. It keeps the Dart package's default **`extendedIndic`** behavior and ports all public conversion directions:
+
+- Latin/IAST → Devanagari
+- Latin/IAST → Gujarati
+- Latin/IAST → plain English/Hunterian
+- Devanagari → canonical Latin/IAST
+- Gujarati → canonical Latin/IAST
+- metadata-backed exact source recovery
+- exact round-trip result envelopes and JSON serialization
+
+The runtime has no third-party dependency. Python's standard `unicodedata` module supplies NFC/NFD normalization and Unicode mark categories.
+
+## Install
+
+```bash
+cd python
+python3.12 -m venv .venv
+source .venv/bin/activate
+python -m pip install -e .
+```
+
+For tests:
+
+```bash
+python -m pip install -e '.[dev]'
+python -m pytest
+```
+
+## Basic conversions
+
+```python
+from lipimala import (
+    to_devanagari_from_iast,
+    to_gujarati_from_iast,
+    to_plain_english_from_iast,
+    to_canonical_iast_from_devanagari,
+    to_canonical_iast_from_gujarati,
+)
+
+assert to_devanagari_from_iast('Kṛṣṇa') == 'कृष्ण'
+assert to_gujarati_from_iast('Kṛṣṇa') == 'કૃષ્ણ'
+assert to_plain_english_from_iast('Kṛṣṇa') == 'Krishna'
+assert to_canonical_iast_from_devanagari('कृष्ण') == 'kṛṣṇa'
+assert to_canonical_iast_from_gujarati('કૃષ્ણ') == 'kṛṣṇa'
+```
+
+## Exact original-key recovery
+
+Visible Brahmic output is many-to-one. For example, aliases, case, and NFC/NFD forms can render identically. Exact recovery therefore uses the same checksummed invisible Unicode-tag trailer as the Dart implementation.
+
+```python
+from lipimala import (
+    IastToDevanagariOptions,
+    IastToGujaratiOptions,
+    to_devanagari_from_iast,
+    to_gujarati_from_iast,
+    to_exact_iast_from_devanagari,
+    to_exact_iast_from_gujarati,
+)
+
+source = 'Kṛṣṇa / Kr̥ṣṇa / ḫāna / ṣ́akti'
+
+devanagari = to_devanagari_from_iast(
+    source,
+    IastToDevanagariOptions(embed_exact_source_metadata=True),
+)
+gujarati = to_gujarati_from_iast(
+    source,
+    IastToGujaratiOptions(embed_exact_source_metadata=True),
+)
+
+assert to_exact_iast_from_devanagari(devanagari) == source
+assert to_exact_iast_from_gujarati(gujarati) == source
+```
+
+The metadata stores the exact UTF-16LE code-unit sequence and preserves:
+
+- case
+- precomposed versus decomposed spelling
+- combining-mark order
+- aliases
+- punctuation and whitespace
+- supplementary Unicode characters
+- unpaired UTF-16 surrogates through Python's `surrogatepass` handling
+
+The trailer is rejected if either the visible rendering or encoded source payload is modified.
+
+## Exact Round-Trip envelope
+
+```python
+import json
+
+from lipimala import (
+    TransliterationResult,
+    to_plain_english,
+)
+
+result = to_plain_english('Kṛṣṇa ā́tman ḷa')
+assert result.restore_original() == 'Kṛṣṇa ā́tman ḷa'
+
+encoded = json.dumps(result.to_json(), ensure_ascii=False)
+restored = TransliterationResult.from_json(json.loads(encoded))
+assert restored.restore_original() == result.original
+```
+
+## Devanagari ↔ Gujarati Direct Converter
+
+This package includes a direct converter between Devanagari and Gujarati.
+
+### Canonical visible conversion
+```python
+from lipimala.deva_gujr_converter import (
+    to_canonical_gujarati_from_devanagari,
+    to_canonical_devanagari_from_gujarati,
+)
+
+print(to_canonical_gujarati_from_devanagari('कृष्ण'))  # કૃષ્ણ
+print(to_canonical_devanagari_from_gujarati('કૃષ્ણ'))  # कृष्ण
+```
+
+### Exact exact round-trip round trip
+The visible Gujarati and Devanagari repertoires are not one-to-one. Therefore, exact round-trip recovery uses a checksummed Unicode-tag trailer.
+
+```python
+from lipimala.deva_gujr_converter import (
+    IndicScriptConversionOptions,
+    to_canonical_gujarati_from_devanagari,
+    to_exact_devanagari_from_gujarati,
+)
+
+source = 'ऄ ऎ ऍ ॲ ऒ ऑ ॵ ळ ऴ ग़ ॻ ड़ ॸ ॾ'
+
+tagged_gujarati = to_canonical_gujarati_from_devanagari(
+    source,
+    IndicScriptConversionOptions(embed_exact_source_metadata=True),
+)
+
+assert to_exact_devanagari_from_gujarati(tagged_gujarati) == source
+```
+
+The opposite Gujarati → Devanagari → exact Gujarati direction uses `to_exact_gujarati_from_devanagari`.
+
+### Smart exact-or-canonical APIs
+These recover a correctly typed exact source trailer if present, and otherwise fall back to canonical visible conversion:
+- `to_devanagari_from_gujarati(text, options)`
+- `to_gujarati_from_devanagari(text, options)`
+
+Strict exact APIs throw when typed metadata is absent or damaged:
+- `to_exact_devanagari_from_gujarati(text)`
+- `to_exact_gujarati_from_devanagari(text)`
+
+## Generate the verification outputs
+
+Run from this directory after installation:
+
+```bash
+python3 -m tools.latn_iast_transliteration_verification.latn_iast_to_deva_test > latn_iast_to_deva_output.txt
+python3 -m tools.latn_iast_transliteration_verification.latn_iast_to_gujr_test > latn_iast_to_gujr_output.txt
+python3 -m tools.latn_iast_transliteration_verification.latn_iast_transcription_test > latn_iast_transcription_output.txt
+python3 -m tools.latn_iast_transliteration_verification.deva_to_latn_iast_test > deva_to_latn_iast_output.txt
+python3 -m tools.latn_iast_transliteration_verification.gujr_to_latn_iast_test > gujr_to_latn_iast_output.txt
+python3 -m tools.latn_iast_transliteration_verification.deva_to_gujr_test > deva_to_gujr_output.txt
+python3 -m tools.latn_iast_transliteration_verification.gujr_to_deva_test > gujr_to_deva_output.txt
+```
+
+## Verification performed
+
+The automated parity suite compares the Python implementation against the five supplied Dart-generated output files:
+
+- 497 Latin → Devanagari cases
+- 497 Latin → Gujarati cases
+- 497 Latin → plain-English cases
+- 497 Devanagari → canonical IAST cases
+- 497 Gujarati → canonical IAST cases
+
+That is **2,485 exact result comparisons**, including the complete supplied Vedic corpus. Additional tests cover exact metadata recovery, normalization distinctions, combining-mark order, supplementary characters, JSON envelopes, and tamper rejection.
+
+## Important distinction
+
+`to_canonical_iast_from_devanagari()` and `to_canonical_iast_from_gujarati()` generate canonical reverse transliteration from visible text. They cannot infer the exact original alias or case. Use `embed_exact_source_metadata=True` plus `to_exact_iast_from_*()` when the exact original key must be recovered.

lipimala-1.0.0/lipimala/__init__.py

@@ -0,0 +1 @@
+from .transliteration_result import *