fast-sentence-segment 1.3.0__tar.gz → 1.4.1__tar.gz

{fast_sentence_segment-1.3.0 → fast_sentence_segment-1.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fast-sentence-segment
-Version: 1.3.0
+Version: 1.4.1
 Summary: Fast and Efficient Sentence Segmentation
 Home-page: https://github.com/craigtrim/fast-sentence-segment
 License: MIT
@@ -9,7 +9,7 @@ Author: Craig Trim
 Author-email: craigtrim@gmail.com
 Maintainer: Craig Trim
 Maintainer-email: craigtrim@gmail.com
-Requires-Python: >=3.9,<4.0
+Requires-Python: >=3.9,<3.13
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
@@ -33,8 +33,9 @@ Description-Content-Type: text/markdown
 
 [![PyPI version](https://img.shields.io/pypi/v/fast-sentence-segment.svg)](https://pypi.org/project/fast-sentence-segment/)
 [![Python versions](https://img.shields.io/pypi/pyversions/fast-sentence-segment.svg)](https://pypi.org/project/fast-sentence-segment/)
+[![CI](https://img.shields.io/github/actions/workflow/status/craigtrim/fast-sentence-segment/ci.yml?branch=master&label=CI)](https://github.com/craigtrim/fast-sentence-segment/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![spaCy](https://img.shields.io/badge/spaCy-3.8-blue.svg)](https://spacy.io/)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Downloads](https://static.pepy.tech/badge/fast-sentence-segment)](https://pepy.tech/project/fast-sentence-segment)
 [![Downloads/Month](https://static.pepy.tech/badge/fast-sentence-segment/month)](https://pepy.tech/project/fast-sentence-segment)
 

{fast_sentence_segment-1.3.0 → fast_sentence_segment-1.4.1}/README.md

@@ -2,8 +2,9 @@
 
 [![PyPI version](https://img.shields.io/pypi/v/fast-sentence-segment.svg)](https://pypi.org/project/fast-sentence-segment/)
 [![Python versions](https://img.shields.io/pypi/pyversions/fast-sentence-segment.svg)](https://pypi.org/project/fast-sentence-segment/)
+[![CI](https://img.shields.io/github/actions/workflow/status/craigtrim/fast-sentence-segment/ci.yml?branch=master&label=CI)](https://github.com/craigtrim/fast-sentence-segment/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![spaCy](https://img.shields.io/badge/spaCy-3.8-blue.svg)](https://spacy.io/)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Downloads](https://static.pepy.tech/badge/fast-sentence-segment)](https://pepy.tech/project/fast-sentence-segment)
 [![Downloads/Month](https://static.pepy.tech/badge/fast-sentence-segment/month)](https://pepy.tech/project/fast-sentence-segment)
 

{fast_sentence_segment-1.3.0 → fast_sentence_segment-1.4.1}/fast_sentence_segment/cli.py

@@ -62,6 +62,11 @@ def main():
         action="store_true",
         help="Number output lines",
     )
+    parser.add_argument(
+        "--unwrap",
+        action="store_true",
+        help="Unwrap hard-wrapped lines and dehyphenate split words",
+    )
     args = parser.parse_args()
 
     # Get input text
@@ -77,7 +82,7 @@ def main():
         sys.exit(1)
 
     # Segment and output
-    sentences = segment_text(text.strip(), flatten=True)
+    sentences = segment_text(text.strip(), flatten=True, unwrap=args.unwrap)
     for i, sentence in enumerate(sentences, 1):
         if args.numbered:
             print(f"{i}. {sentence}")

{fast_sentence_segment-1.3.0 → fast_sentence_segment-1.4.1}/fast_sentence_segment/dmo/__init__.py

@@ -2,6 +2,7 @@ from .abbreviation_merger import AbbreviationMerger
 from .abbreviation_splitter import AbbreviationSplitter
 from .title_name_merger import TitleNameMerger
 from .bullet_point_cleaner import BulletPointCleaner
+from .dehyphenator import Dehyphenator
 from .ellipsis_normalizer import EllipsisNormalizer
 from .newlines_to_periods import NewlinesToPeriods
 from .post_process_sentences import PostProcessStructure

fast_sentence_segment-1.4.1/fast_sentence_segment/dmo/dehyphenator.py

@@ -0,0 +1,55 @@
+# -*- coding: UTF-8 -*-
+"""Dehyphenate words split across lines.
+
+Related GitHub Issue:
+    #8 - Add dehyphenation support for words split across lines
+    https://github.com/craigtrim/fast-sentence-segment/issues/8
+
+When processing ebooks and scanned documents, words are often hyphenated
+at line breaks for typesetting purposes. This module rejoins those words.
+"""
+
+import re
+
+from fast_sentence_segment.core import BaseObject
+
+# Pattern to match hyphenated word breaks at end of line:
+# - A single hyphen (not -- em-dash)
+# - Followed by newline and optional whitespace
+# - Followed by a lowercase letter (continuation of word)
+_HYPHEN_LINE_BREAK_PATTERN = re.compile(r'(?<!-)-\n\s*([a-z])')
+
+
+class Dehyphenator(BaseObject):
+    """Rejoin words that were hyphenated across line breaks."""
+
+    def __init__(self):
+        """Change Log
+
+        Created:
+            3-Feb-2026
+            craigtrim@gmail.com
+            *   add dehyphenation support for words split across lines
+                https://github.com/craigtrim/fast-sentence-segment/issues/8
+        """
+        BaseObject.__init__(self, __name__)
+
+    @staticmethod
+    def process(input_text: str) -> str:
+        """Rejoin words that were hyphenated across line breaks.
+
+        Detects the pattern of a word fragment ending with a hyphen
+        at the end of a line, followed by the word continuation
+        starting with a lowercase letter on the next line.
+
+        Examples:
+            "bot-\\ntle" -> "bottle"
+            "cham-\\n    bermaid" -> "chambermaid"
+
+        Args:
+            input_text: Text that may contain hyphenated line breaks.
+
+        Returns:
+            Text with hyphenated word breaks rejoined.
+        """
+        return _HYPHEN_LINE_BREAK_PATTERN.sub(r'\1', input_text)

fast_sentence_segment-1.4.1/fast_sentence_segment/dmo/unwrap_hard_wrapped_text.py

@@ -0,0 +1,75 @@
+# -*- coding: UTF-8 -*-
+"""Unwrap hard-wrapped text (e.g., Project Gutenberg e-texts).
+
+Joins lines within paragraphs into continuous strings while
+preserving paragraph boundaries (blank lines). Also dehyphenates
+words that were split across lines for typesetting.
+
+Related GitHub Issue:
+    #8 - Add dehyphenation support for words split across lines
+    https://github.com/craigtrim/fast-sentence-segment/issues/8
+"""
+
+import re
+
+# Pattern to match hyphenated word breaks at end of line:
+# - A single hyphen (not -- em-dash)
+# - Followed by newline and optional whitespace
+# - Followed by a lowercase letter (continuation of word)
+_HYPHEN_LINE_BREAK_PATTERN = re.compile(r'(?<!-)-\n\s*([a-z])')
+
+
+def _dehyphenate_block(block: str) -> str:
+    """Remove hyphens from words split across lines.
+
+    Detects the pattern of a word fragment ending with a hyphen
+    at the end of a line, followed by the word continuation
+    starting with a lowercase letter on the next line.
+
+    Examples:
+        "bot-\\ntle" -> "bottle"
+        "cham-\\n    bermaid" -> "chambermaid"
+
+    Args:
+        block: A paragraph block that may contain hyphenated line breaks.
+
+    Returns:
+        The block with hyphenated word breaks rejoined.
+    """
+    return _HYPHEN_LINE_BREAK_PATTERN.sub(r'\1', block)
+
+
+def unwrap_hard_wrapped_text(text: str) -> str:
+    """Unwrap hard-wrapped paragraphs into continuous lines.
+
+    Splits on blank lines to identify paragraphs, then joins
+    lines within each paragraph into a single string with
+    single spaces. Also dehyphenates words that were split
+    across lines for typesetting purposes.
+
+    Examples:
+        >>> unwrap_hard_wrapped_text("a bot-\\ntle of wine")
+        'a bottle of wine'
+        >>> unwrap_hard_wrapped_text("line one\\nline two")
+        'line one line two'
+
+    Args:
+        text: Raw text with hard-wrapped lines.
+
+    Returns:
+        Text with paragraphs unwrapped into continuous strings,
+        separated by double newlines, with hyphenated words rejoined.
+    """
+    blocks = re.split(r'\n\s*\n', text)
+    unwrapped = []
+
+    for block in blocks:
+        # First, dehyphenate words split across lines
+        block = _dehyphenate_block(block)
+        # Then join remaining lines with spaces
+        lines = block.splitlines()
+        joined = ' '.join(line.strip() for line in lines if line.strip())
+        if joined:
+            unwrapped.append(joined)
+
+    return '\n\n'.join(unwrapped)

{fast_sentence_segment-1.3.0 → fast_sentence_segment-1.4.1}/fast_sentence_segment/svc/perform_sentence_segmentation.py

@@ -18,6 +18,7 @@ from fast_sentence_segment.dmo import QuestionExclamationSplitter
 from fast_sentence_segment.dmo import SpacyDocSegmenter
 from fast_sentence_segment.dmo import PostProcessStructure
 from fast_sentence_segment.dmo import StripTrailingPeriodAfterQuote
+from fast_sentence_segment.dmo import Dehyphenator
 
 
 class PerformSentenceSegmentation(BaseObject):
@@ -46,6 +47,7 @@ class PerformSentenceSegmentation(BaseObject):
         if not self.__nlp:
             self.__nlp = spacy.load("en_core_web_sm")
 
+        self._dehyphenate = Dehyphenator.process
         self._newlines_to_periods = NewlinesToPeriods.process
         self._normalize_numbered_lists = NumberedListNormalizer().process
         self._normalize_ellipses = EllipsisNormalizer().process
@@ -96,6 +98,10 @@ class PerformSentenceSegmentation(BaseObject):
         # Normalize tabs to spaces
         input_text = input_text.replace('\t', ' ')
 
+        # Dehyphenate words split across lines (issue #8)
+        # Must happen before newlines are converted to periods
+        input_text = self._dehyphenate(input_text)
+
         input_text = self._normalize_numbered_lists(input_text)
         input_text = self._normalize_ellipses(input_text)
 

{fast_sentence_segment-1.3.0 → fast_sentence_segment-1.4.1}/pyproject.toml

@@ -11,7 +11,7 @@ description = "Fast and Efficient Sentence Segmentation"
 license = "MIT"
 name = "fast-sentence-segment"
 readme = "README.md"
-version = "1.3.0"
+version = "1.4.1"
 
 keywords = ["nlp", "text", "preprocess", "segment"]
 repository = "https://github.com/craigtrim/fast-sentence-segment"
@@ -37,7 +37,7 @@ classifiers = [
 "Bug Tracker" = "https://github.com/craigtrim/fast-sentence-segment/issues"
 
 [tool.poetry.dependencies]
-python = "^3.9"
+python = ">=3.9,<3.13"
 spacy = "^3.8.0"
 
 [tool.poetry.dev-dependencies]

fast_sentence_segment-1.4.1/setup.py

@@ -0,0 +1,39 @@
+# -*- coding: utf-8 -*-
+from setuptools import setup
+
+packages = \
+['fast_sentence_segment',
+ 'fast_sentence_segment.bp',
+ 'fast_sentence_segment.core',
+ 'fast_sentence_segment.dmo',
+ 'fast_sentence_segment.svc']
+
+package_data = \
+{'': ['*']}
+
+install_requires = \
+['spacy>=3.8.0,<4.0.0']
+
+entry_points = \
+{'console_scripts': ['segment = fast_sentence_segment.cli:main',
+                     'segment-file = fast_sentence_segment.cli:file_main']}
+
+setup_kwargs = {
+    'name': 'fast-sentence-segment',
+    'version': '1.4.1',
+    'description': 'Fast and Efficient Sentence Segmentation',
+    'long_description': '# Fast Sentence Segmentation\n\n[![PyPI version](https://img.shields.io/pypi/v/fast-sentence-segment.svg)](https://pypi.org/project/fast-sentence-segment/)\n[![Python versions](https://img.shields.io/pypi/pyversions/fast-sentence-segment.svg)](https://pypi.org/project/fast-sentence-segment/)\n[![CI](https://img.shields.io/github/actions/workflow/status/craigtrim/fast-sentence-segment/ci.yml?branch=master&label=CI)](https://github.com/craigtrim/fast-sentence-segment/actions/workflows/ci.yml)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)\n[![Downloads](https://static.pepy.tech/badge/fast-sentence-segment)](https://pepy.tech/project/fast-sentence-segment)\n[![Downloads/Month](https://static.pepy.tech/badge/fast-sentence-segment/month)](https://pepy.tech/project/fast-sentence-segment)\n\nFast and efficient sentence segmentation using spaCy with surgical post-processing fixes. Handles complex edge cases like abbreviations (Dr., Mr., etc.), ellipses, quoted text, and multi-paragraph documents.\n\n## Why This Library?\n\n1. **Keep it local**: LLM API calls cost money and send your data to third parties. Run sentence segmentation entirely on your machine.\n2. **spaCy perfected**: spaCy is a great local model, but it makes mistakes. This library fixes most of spaCy\'s shortcomings.\n\n## Features\n\n- **Paragraph-aware segmentation**: Returns sentences grouped by paragraph\n- **Abbreviation handling**: Correctly handles "Dr.", "Mr.", "etc.", "p.m.", "a.m." without false splits\n- **Ellipsis preservation**: Keeps `...` intact while detecting sentence boundaries\n- **Question/exclamation splitting**: Properly splits on `?` and `!` followed by capital letters\n- **Cached processing**: LRU cache for repeated text processing\n- **Flexible output**: Nested lists (by paragraph) or flattened list of sentences\n- **Bullet point & numbered list normalization**: Cleans common list formats\n- **CLI tool**: Command-line interface for quick segmentation\n\n## Installation\n\n```bash\npip install fast-sentence-segment\n```\n\nAfter installation, download the spaCy model:\n\n```bash\npython -m spacy download en_core_web_sm\n```\n\n## Quick Start\n\n```python\nfrom fast_sentence_segment import segment_text\n\ntext = "Do you like Dr. Who? I prefer Dr. Strange! Mr. T is also cool."\n\nresults = segment_text(text, flatten=True)\n```\n\n```json\n[\n  "Do you like Dr. Who?",\n  "I prefer Dr. Strange!",\n  "Mr. T is also cool."\n]\n```\n\nNotice how "Dr. Who?" stays together as a single sentence—the library correctly recognizes that a title followed by a single-word name ending in `?` or `!` is a name reference, not a sentence boundary.\n\n## Usage\n\n### Basic Segmentation\n\nThe `segment_text` function returns a list of lists, where each inner list represents a paragraph containing its sentences:\n\n```python\nfrom fast_sentence_segment import segment_text\n\ntext = """Gandalf spoke softly. "All we have to decide is what to do with the time given us."\n\nFrodo nodded. The weight of the Ring pressed against his chest."""\n\nresults = segment_text(text)\n```\n\n```json\n[\n  [\n    "Gandalf spoke softly.",\n    "\\"All we have to decide is what to do with the time given us.\\"."\n  ],\n  [\n    "Frodo nodded.",\n    "The weight of the Ring pressed against his chest."\n  ]\n]\n```\n\n### Flattened Output\n\nIf you don\'t need paragraph boundaries, use the `flatten` parameter:\n\n```python\ntext = "At 9 a.m. the hobbits set out. By 3 p.m. they reached Rivendell. Mr. Frodo was exhausted."\n\nresults = segment_text(text, flatten=True)\n```\n\n```json\n[\n  "At 9 a.m. the hobbits set out.",\n  "By 3 p.m. they reached Rivendell.",\n  "Mr. Frodo was exhausted."\n]\n```\n\n### Direct Segmenter Access\n\nFor more control, use the `Segmenter` class directly:\n\n```python\nfrom fast_sentence_segment import Segmenter\n\nsegmenter = Segmenter()\nresults = segmenter.input_text("Your text here.")\n```\n\n### Command Line Interface\n\n```bash\n# Inline text\nsegment "Gandalf paused... You shall not pass! The Balrog roared."\n\n# Pipe from stdin\necho "Have you seen Dr. Who? It\'s brilliant!" | segment\n\n# Numbered output\nsegment -n -f silmarillion.txt\n\n# File-to-file (one sentence per line)\nsegment-file --input-file book.txt --output-file sentences.txt\n\n# Unwrap hard-wrapped e-texts (Project Gutenberg, etc.)\nsegment-file --input-file book.txt --output-file sentences.txt --unwrap\n```\n\n## API Reference\n\n| Function | Parameters | Returns | Description |\n|----------|------------|---------|-------------|\n| `segment_text()` | `input_text: str`, `flatten: bool = False`, `unwrap: bool = False` | `list` | Main entry point for segmentation |\n| `Segmenter.input_text()` | `input_text: str` | `list[list[str]]` | Cached paragraph-aware segmentation |\n\n### CLI Commands\n\n| Command | Description |\n|---------|-------------|\n| `segment [text]` | Segment text from argument, `-f FILE`, or stdin. Use `-n` for numbered output. |\n| `segment-file --input-file IN --output-file OUT [--unwrap]` | Segment a file and write one sentence per line. Use `--unwrap` for hard-wrapped e-texts. |\n\n## Why Nested Lists?\n\nThe segmentation process preserves document structure by segmenting into both paragraphs and sentences. Each outer list represents a paragraph, and each inner list contains that paragraph\'s sentences. This is useful for:\n\n- Document structure analysis\n- Paragraph-level processing\n- Maintaining original text organization\n\nUse `flatten=True` when you only need sentences without paragraph context.\n\n## Requirements\n\n- Python 3.9+\n- spaCy 3.8+\n- en_core_web_sm spaCy model\n\n## How It Works\n\nThis library uses spaCy for initial sentence segmentation, then applies surgical post-processing fixes for cases where spaCy\'s default behavior is incorrect:\n\n1. **Pre-processing**: Normalize numbered lists, preserve ellipses with placeholders\n2. **spaCy segmentation**: Use spaCy\'s sentence boundary detection\n3. **Post-processing**: Split on abbreviation boundaries, handle `?`/`!` + capital patterns\n4. **Denormalization**: Restore placeholders to original text\n\n## License\n\nMIT License - see [LICENSE](LICENSE) for details.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n1. Fork the repository\n2. Create your feature branch (`git checkout -b feature/amazing-feature`)\n3. Run tests (`make test`)\n4. Commit your changes\n5. Push to the branch\n6. Open a Pull Request\n',
+    'author': 'Craig Trim',
+    'author_email': 'craigtrim@gmail.com',
+    'maintainer': 'Craig Trim',
+    'maintainer_email': 'craigtrim@gmail.com',
+    'url': 'https://github.com/craigtrim/fast-sentence-segment',
+    'packages': packages,
+    'package_data': package_data,
+    'install_requires': install_requires,
+    'entry_points': entry_points,
+    'python_requires': '>=3.9,<3.13',
+}
+
+
+setup(**setup_kwargs)

fast_sentence_segment-1.3.0/fast_sentence_segment/dmo/unwrap_hard_wrapped_text.py

@@ -1,34 +0,0 @@
-# -*- coding: UTF-8 -*-
-"""Unwrap hard-wrapped text (e.g., Project Gutenberg e-texts).
-
-Joins lines within paragraphs into continuous strings while
-preserving paragraph boundaries (blank lines).
-"""
-
-import re
-
-
-def unwrap_hard_wrapped_text(text: str) -> str:
-    """Unwrap hard-wrapped paragraphs into continuous lines.
-
-    Splits on blank lines to identify paragraphs, then joins
-    lines within each paragraph into a single string with
-    single spaces.
-
-    Args:
-        text: Raw text with hard-wrapped lines.
-
-    Returns:
-        Text with paragraphs unwrapped into continuous strings,
-        separated by double newlines.
-    """
-    blocks = re.split(r'\n\s*\n', text)
-    unwrapped = []
-
-    for block in blocks:
-        lines = block.splitlines()
-        joined = ' '.join(line.strip() for line in lines if line.strip())
-        if joined:
-            unwrapped.append(joined)
-
-    return '\n\n'.join(unwrapped)

fast_sentence_segment-1.3.0/setup.py

@@ -1,39 +0,0 @@
-# -*- coding: utf-8 -*-
-from setuptools import setup
-
-packages = \
-['fast_sentence_segment',
- 'fast_sentence_segment.bp',
- 'fast_sentence_segment.core',
- 'fast_sentence_segment.dmo',
- 'fast_sentence_segment.svc']
-
-package_data = \
-{'': ['*']}
-
-install_requires = \
-['spacy>=3.8.0,<4.0.0']
-
-entry_points = \
-{'console_scripts': ['segment = fast_sentence_segment.cli:main',
-                     'segment-file = fast_sentence_segment.cli:file_main']}
-
-setup_kwargs = {
-    'name': 'fast-sentence-segment',
-    'version': '1.3.0',
-    'description': 'Fast and Efficient Sentence Segmentation',
-    'long_description': '# Fast Sentence Segmentation\n\n[![PyPI version](https://img.shields.io/pypi/v/fast-sentence-segment.svg)](https://pypi.org/project/fast-sentence-segment/)\n[![Python versions](https://img.shields.io/pypi/pyversions/fast-sentence-segment.svg)](https://pypi.org/project/fast-sentence-segment/)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![spaCy](https://img.shields.io/badge/spaCy-3.8-blue.svg)](https://spacy.io/)\n[![Downloads](https://static.pepy.tech/badge/fast-sentence-segment)](https://pepy.tech/project/fast-sentence-segment)\n[![Downloads/Month](https://static.pepy.tech/badge/fast-sentence-segment/month)](https://pepy.tech/project/fast-sentence-segment)\n\nFast and efficient sentence segmentation using spaCy with surgical post-processing fixes. Handles complex edge cases like abbreviations (Dr., Mr., etc.), ellipses, quoted text, and multi-paragraph documents.\n\n## Why This Library?\n\n1. **Keep it local**: LLM API calls cost money and send your data to third parties. Run sentence segmentation entirely on your machine.\n2. **spaCy perfected**: spaCy is a great local model, but it makes mistakes. This library fixes most of spaCy\'s shortcomings.\n\n## Features\n\n- **Paragraph-aware segmentation**: Returns sentences grouped by paragraph\n- **Abbreviation handling**: Correctly handles "Dr.", "Mr.", "etc.", "p.m.", "a.m." without false splits\n- **Ellipsis preservation**: Keeps `...` intact while detecting sentence boundaries\n- **Question/exclamation splitting**: Properly splits on `?` and `!` followed by capital letters\n- **Cached processing**: LRU cache for repeated text processing\n- **Flexible output**: Nested lists (by paragraph) or flattened list of sentences\n- **Bullet point & numbered list normalization**: Cleans common list formats\n- **CLI tool**: Command-line interface for quick segmentation\n\n## Installation\n\n```bash\npip install fast-sentence-segment\n```\n\nAfter installation, download the spaCy model:\n\n```bash\npython -m spacy download en_core_web_sm\n```\n\n## Quick Start\n\n```python\nfrom fast_sentence_segment import segment_text\n\ntext = "Do you like Dr. Who? I prefer Dr. Strange! Mr. T is also cool."\n\nresults = segment_text(text, flatten=True)\n```\n\n```json\n[\n  "Do you like Dr. Who?",\n  "I prefer Dr. Strange!",\n  "Mr. T is also cool."\n]\n```\n\nNotice how "Dr. Who?" stays together as a single sentence—the library correctly recognizes that a title followed by a single-word name ending in `?` or `!` is a name reference, not a sentence boundary.\n\n## Usage\n\n### Basic Segmentation\n\nThe `segment_text` function returns a list of lists, where each inner list represents a paragraph containing its sentences:\n\n```python\nfrom fast_sentence_segment import segment_text\n\ntext = """Gandalf spoke softly. "All we have to decide is what to do with the time given us."\n\nFrodo nodded. The weight of the Ring pressed against his chest."""\n\nresults = segment_text(text)\n```\n\n```json\n[\n  [\n    "Gandalf spoke softly.",\n    "\\"All we have to decide is what to do with the time given us.\\"."\n  ],\n  [\n    "Frodo nodded.",\n    "The weight of the Ring pressed against his chest."\n  ]\n]\n```\n\n### Flattened Output\n\nIf you don\'t need paragraph boundaries, use the `flatten` parameter:\n\n```python\ntext = "At 9 a.m. the hobbits set out. By 3 p.m. they reached Rivendell. Mr. Frodo was exhausted."\n\nresults = segment_text(text, flatten=True)\n```\n\n```json\n[\n  "At 9 a.m. the hobbits set out.",\n  "By 3 p.m. they reached Rivendell.",\n  "Mr. Frodo was exhausted."\n]\n```\n\n### Direct Segmenter Access\n\nFor more control, use the `Segmenter` class directly:\n\n```python\nfrom fast_sentence_segment import Segmenter\n\nsegmenter = Segmenter()\nresults = segmenter.input_text("Your text here.")\n```\n\n### Command Line Interface\n\n```bash\n# Inline text\nsegment "Gandalf paused... You shall not pass! The Balrog roared."\n\n# Pipe from stdin\necho "Have you seen Dr. Who? It\'s brilliant!" | segment\n\n# Numbered output\nsegment -n -f silmarillion.txt\n\n# File-to-file (one sentence per line)\nsegment-file --input-file book.txt --output-file sentences.txt\n\n# Unwrap hard-wrapped e-texts (Project Gutenberg, etc.)\nsegment-file --input-file book.txt --output-file sentences.txt --unwrap\n```\n\n## API Reference\n\n| Function | Parameters | Returns | Description |\n|----------|------------|---------|-------------|\n| `segment_text()` | `input_text: str`, `flatten: bool = False`, `unwrap: bool = False` | `list` | Main entry point for segmentation |\n| `Segmenter.input_text()` | `input_text: str` | `list[list[str]]` | Cached paragraph-aware segmentation |\n\n### CLI Commands\n\n| Command | Description |\n|---------|-------------|\n| `segment [text]` | Segment text from argument, `-f FILE`, or stdin. Use `-n` for numbered output. |\n| `segment-file --input-file IN --output-file OUT [--unwrap]` | Segment a file and write one sentence per line. Use `--unwrap` for hard-wrapped e-texts. |\n\n## Why Nested Lists?\n\nThe segmentation process preserves document structure by segmenting into both paragraphs and sentences. Each outer list represents a paragraph, and each inner list contains that paragraph\'s sentences. This is useful for:\n\n- Document structure analysis\n- Paragraph-level processing\n- Maintaining original text organization\n\nUse `flatten=True` when you only need sentences without paragraph context.\n\n## Requirements\n\n- Python 3.9+\n- spaCy 3.8+\n- en_core_web_sm spaCy model\n\n## How It Works\n\nThis library uses spaCy for initial sentence segmentation, then applies surgical post-processing fixes for cases where spaCy\'s default behavior is incorrect:\n\n1. **Pre-processing**: Normalize numbered lists, preserve ellipses with placeholders\n2. **spaCy segmentation**: Use spaCy\'s sentence boundary detection\n3. **Post-processing**: Split on abbreviation boundaries, handle `?`/`!` + capital patterns\n4. **Denormalization**: Restore placeholders to original text\n\n## License\n\nMIT License - see [LICENSE](LICENSE) for details.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n1. Fork the repository\n2. Create your feature branch (`git checkout -b feature/amazing-feature`)\n3. Run tests (`make test`)\n4. Commit your changes\n5. Push to the branch\n6. Open a Pull Request\n',
-    'author': 'Craig Trim',
-    'author_email': 'craigtrim@gmail.com',
-    'maintainer': 'Craig Trim',
-    'maintainer_email': 'craigtrim@gmail.com',
-    'url': 'https://github.com/craigtrim/fast-sentence-segment',
-    'packages': packages,
-    'package_data': package_data,
-    'install_requires': install_requires,
-    'entry_points': entry_points,
-    'python_requires': '>=3.9,<4.0',
-}
-
-
-setup(**setup_kwargs)