indic-itn 0.1.0__tar.gz

indic_itn-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 indic-itn contributors
+
+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.

indic_itn-0.1.0/PKG-INFO

@@ -0,0 +1,104 @@
+Metadata-Version: 2.4
+Name: indic-itn
+Version: 0.1.0
+Summary: Inverse Text Normalization (ITN) for Indic languages
+License: MIT
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Provides-Extra: dev
+Requires-Dist: black>=24.0.0; extra == "dev"
+Requires-Dist: mypy>=1.9.0; extra == "dev"
+Requires-Dist: pre-commit>=3.6.0; extra == "dev"
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: ruff>=0.3.0; extra == "dev"
+Dynamic: license-file
+
+# indic-itn
+
+Inverse Text Normalization (ITN) for Indic languages.
+
+## Installation
+
+To install the package in editable mode for development:
+
+```bash
+pip install -e .
+```
+
+To install dev dependencies as well:
+
+```bash
+pip install -e ".[dev]"
+```
+
+## Usage
+
+```python
+from indic_itn import HindiITN
+
+# Instantiate the ITN processor
+itn = HindiITN()
+
+# Normalize text (placeholder)
+# text = "कक्षा दो" -> "कक्षा 2"
+```
+
+## Development and Tooling
+
+This project uses modern tooling for maintaining code quality:
+
+### Code Formatting and Linting
+
+We use [Ruff](https://github.com/astral-sh/ruff) and [Black](https://github.com/psf/black) for formatting, linting, and imports sorting.
+
+```bash
+# Run Ruff lint check
+ruff check .
+
+# Run Ruff formatter check
+ruff format --check .
+
+# Run Black formatting check
+black --check .
+```
+
+### Type Checking
+
+We use [MyPy](https://github.com/python/mypy) for static type checking.
+
+```bash
+mypy src tests
+```
+
+### Running Tests
+
+We use [Pytest](https://github.com/pytest-dev/pytest) for unit testing along with `pytest-cov` for coverage.
+
+```bash
+pytest
+```
+
+### Pre-commit Hooks
+
+To set up pre-commit hooks:
+
+```bash
+pre-commit install
+```
+
+To run hooks on all files manually:
+
+```bash
+pre-commit run --all-files
+```

indic_itn-0.1.0/README.md

@@ -0,0 +1,78 @@
+# indic-itn
+
+Inverse Text Normalization (ITN) for Indic languages.
+
+## Installation
+
+To install the package in editable mode for development:
+
+```bash
+pip install -e .
+```
+
+To install dev dependencies as well:
+
+```bash
+pip install -e ".[dev]"
+```
+
+## Usage
+
+```python
+from indic_itn import HindiITN
+
+# Instantiate the ITN processor
+itn = HindiITN()
+
+# Normalize text (placeholder)
+# text = "कक्षा दो" -> "कक्षा 2"
+```
+
+## Development and Tooling
+
+This project uses modern tooling for maintaining code quality:
+
+### Code Formatting and Linting
+
+We use [Ruff](https://github.com/astral-sh/ruff) and [Black](https://github.com/psf/black) for formatting, linting, and imports sorting.
+
+```bash
+# Run Ruff lint check
+ruff check .
+
+# Run Ruff formatter check
+ruff format --check .
+
+# Run Black formatting check
+black --check .
+```
+
+### Type Checking
+
+We use [MyPy](https://github.com/python/mypy) for static type checking.
+
+```bash
+mypy src tests
+```
+
+### Running Tests
+
+We use [Pytest](https://github.com/pytest-dev/pytest) for unit testing along with `pytest-cov` for coverage.
+
+```bash
+pytest
+```
+
+### Pre-commit Hooks
+
+To set up pre-commit hooks:
+
+```bash
+pre-commit install
+```
+
+To run hooks on all files manually:
+
+```bash
+pre-commit run --all-files
+```

indic_itn-0.1.0/pyproject.toml

@@ -0,0 +1,82 @@
+[build-system]
+requires = ["setuptools>=61.0.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "indic-itn"
+version = "0.1.0"
+description = "Inverse Text Normalization (ITN) for Indic languages"
+readme = "README.md"
+requires-python = ">=3.11"
+license = { text = "MIT" }
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+dependencies = []
+
+[project.optional-dependencies]
+dev = [
+    "black>=24.0.0",
+    "mypy>=1.9.0",
+    "pre-commit>=3.6.0",
+    "pytest>=8.0.0",
+    "pytest-cov>=4.1.0",
+    "ruff>=0.3.0",
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.black]
+line-length = 88
+target-version = ["py311"]
+
+[tool.ruff]
+line-length = 88
+target-version = "py311"
+
+[tool.ruff.lint]
+select = [
+    "E",    # pycodestyle errors
+    "W",    # pycodestyle warnings
+    "F",    # pyflakes
+    "I",    # isort
+    "N",    # pep8-naming
+    "D",    # pydocstyle
+    "UP",   # pyupgrade
+    "RUF",  # Ruff-specific rules
+]
+ignore = [
+    "D100", # Missing docstring in public module
+    "D104", # Missing docstring in public package
+    "RUF001", # Ambiguous unicode characters (e.g. Devanagari zero '०' lookalike warning)
+]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.mypy]
+python_version = "3.11"
+strict = true
+warn_unreachable = true
+pretty = true
+show_error_codes = true
+
+[[tool.mypy.overrides]]
+module = "tests.*"
+disallow_untyped_defs = false
+disallow_incomplete_defs = false
+
+[tool.pytest.ini_options]
+minversion = "8.0"
+addopts = "-ra -q --cov=indic_itn --cov-report=term-missing"
+testpaths = ["tests"]
+python_files = ["test_*.py"]

indic_itn-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

indic_itn-0.1.0/src/indic_itn/__init__.py

@@ -0,0 +1,7 @@
+"""Inverse Text Normalization (ITN) for Indic languages."""
+
+from indic_itn.main import HindiITN
+from indic_itn.tokenizer import HindiTokenizer
+
+__version__ = "0.1.0"
+__all__ = ["HindiITN", "HindiTokenizer"]

indic_itn-0.1.0/src/indic_itn/base.py

@@ -0,0 +1,105 @@
+"""Core domain classes and base interfaces for the ITN pipeline."""
+
+from abc import ABC, abstractmethod
+from dataclasses import dataclass, field
+from typing import Any
+
+
+@dataclass(frozen=True)
+class Token:
+    """A single token within the input text.
+
+    Attributes:
+        text: The text content of the token.
+        start_idx: The starting character index (inclusive) in the source text.
+        end_idx: The ending character index (exclusive) in the source text.
+    """
+
+    text: str
+    start_idx: int
+    end_idx: int
+
+    @property
+    def value(self) -> str:
+        """Alias for text."""
+        return self.text
+
+    @property
+    def start_offset(self) -> int:
+        """Alias for start_idx."""
+        return self.start_idx
+
+    @property
+    def end_offset(self) -> int:
+        """Alias for end_idx."""
+        return self.end_idx
+
+
+@dataclass(frozen=True)
+class Entity:
+    """A detected entity that requires normalization.
+
+    Attributes:
+        text: The raw spoken text representing the entity.
+        entity_type: The type of entity (e.g., "number", "date", "currency").
+        start_idx: The starting character index (inclusive) in the source text.
+        end_idx: The ending character index (exclusive) in the source text.
+        metadata: Optional dictionary containing additional structured details
+            about the detected entity.
+    """
+
+    text: str
+    entity_type: str
+    start_idx: int
+    end_idx: int
+    metadata: dict[str, Any] = field(default_factory=dict, hash=False, compare=False)
+
+
+class BaseTokenizer(ABC):
+    """Abstract base class for all tokenizers in the ITN pipeline."""
+
+    @abstractmethod
+    def tokenize(self, text: str) -> list[Token]:
+        """Split input text into a list of Token objects.
+
+        Args:
+            text: The raw input text.
+
+        Returns:
+            A list of Token objects with their corresponding indices.
+        """
+        pass
+
+
+class BaseEntityDetector(ABC):
+    """Abstract base class for detecting normalizeable entities in tokenized text."""
+
+    @abstractmethod
+    def detect(self, tokens: list[Token]) -> list[Entity]:
+        """Detect entities from the list of tokens.
+
+        Args:
+            tokens: A list of input Token objects.
+
+        Returns:
+            A list of detected Entity objects.
+        """
+        pass
+
+
+class BaseRewriter(ABC):
+    """Abstract base class for rewriting the input text with normalized values."""
+
+    @abstractmethod
+    def rewrite(self, text: str, entity_rewrites: dict[Entity, str]) -> str:
+        """Replace raw entities in the input text with their normalized string values.
+
+        Args:
+            text: The original input text.
+            entity_rewrites: A dictionary mapping each detected Entity to its
+                normalized string representation.
+
+        Returns:
+            The final normalized text.
+        """
+        pass