fast-sentence-segment 1.4.1__tar.gz → 1.4.3__tar.gz

{fast_sentence_segment-1.4.1 → fast_sentence_segment-1.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: fast-sentence-segment
-Version: 1.4.1
+Version: 1.4.3
 Summary: Fast and Efficient Sentence Segmentation
 Home-page: https://github.com/craigtrim/fast-sentence-segment
 License: MIT
@@ -33,7 +33,7 @@ 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)
+[![Tests](https://img.shields.io/badge/tests-664-brightgreen)](https://github.com/craigtrim/fast-sentence-segment/tree/master/tests)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![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)

{fast_sentence_segment-1.4.1 → fast_sentence_segment-1.4.3}/README.md

@@ -2,7 +2,7 @@
 
 [![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)
+[![Tests](https://img.shields.io/badge/tests-664-brightgreen)](https://github.com/craigtrim/fast-sentence-segment/tree/master/tests)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![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)

{fast_sentence_segment-1.4.1 → fast_sentence_segment-1.4.3}/fast_sentence_segment/cli.py

@@ -2,9 +2,11 @@
 """CLI for fast-sentence-segment."""
 
 import argparse
+import itertools
 import logging
 import os
 import sys
+import threading
 import time
 
 from fast_sentence_segment import segment_text
@@ -21,6 +23,34 @@ YELLOW = "\033[33m"
 RESET = "\033[0m"
 
 
+class Spinner:
+    """Animated spinner for long-running operations."""
+
+    def __init__(self, message: str):
+        self.message = message
+        self.running = False
+        self.thread = None
+        self.frames = itertools.cycle(["⠋", "⠙", "⠹", "⠸", "⠼", "⠴", "⠦", "⠧", "⠇", "⠏"])
+
+    def _spin(self):
+        while self.running:
+            frame = next(self.frames)
+            print(f"\r  {YELLOW}{frame}{RESET} {self.message}", end="", flush=True)
+            time.sleep(0.08)
+
+    def __enter__(self):
+        self.running = True
+        self.thread = threading.Thread(target=self._spin)
+        self.thread.start()
+        return self
+
+    def __exit__(self, *args):
+        self.running = False
+        if self.thread:
+            self.thread.join()
+        print(f"\r  {' ' * (len(self.message) + 4)}\r", end="", flush=True)
+
+
 def _header(title: str):
     print(f"\n{BOLD}{CYAN}{title}{RESET}")
     print(f"{DIM}{'─' * 40}{RESET}")
@@ -113,35 +143,50 @@ def file_main():
     )
     args = parser.parse_args()
 
+    # Echo command immediately
     _header("segment-file")
+    print(f"  {DIM}Segmenting text file into sentences{RESET}")
+    print()
+
+    # Show configuration
     _param("Input", args.input_file)
     _param("Output", args.output_file)
     _param("Size", _file_size(args.input_file))
-    if args.unwrap:
-        _param("Unwrap", "enabled")
-
-    print(f"\n  {YELLOW}Segmenting...{RESET}", end="", flush=True)
+    _param("Unwrap", "enabled" if args.unwrap else "disabled")
+    _param("Normalize quotes", "disabled" if args.no_normalize_quotes else "enabled")
+    print()
 
+    # Step 1: Read file
+    print(f"  {YELLOW}→{RESET} Reading input file...")
     with open(args.input_file, "r", encoding="utf-8") as f:
         text = f.read()
+    print(f"  {GREEN}✓{RESET} Read {len(text):,} characters")
 
+    # Step 2: Segment text
+    print(f"  {YELLOW}→{RESET} Segmenting text...", end="", flush=True)
     start = time.perf_counter()
     normalize = not args.no_normalize_quotes
     sentences = segment_text(
         text.strip(), flatten=True, unwrap=args.unwrap, normalize=normalize,
     )
     elapsed = time.perf_counter() - start
+    print(f"\r  {GREEN}✓{RESET} Segmented into {len(sentences):,} sentences ({elapsed:.2f}s)")
 
+    # Step 3: Write output
+    total = len(sentences)
     with open(args.output_file, "w", encoding="utf-8") as f:
         if args.unwrap:
             f.write(format_grouped_sentences(sentences) + "\n")
+            print(f"  {GREEN}✓{RESET} Written {total:,} sentences to {args.output_file}")
         else:
-            for sentence in sentences:
+            for i, sentence in enumerate(sentences, 1):
                 f.write(sentence + "\n")
+                if i % 500 == 0 or i == total:
+                    pct = (i / total) * 100
+                    print(f"\r  {YELLOW}→{RESET} Writing... {pct:.0f}% ({i:,}/{total:,})", end="", flush=True)
+            print(f"\r  {GREEN}✓{RESET} Written {total:,} sentences to {args.output_file}       ")
 
-    print(f"\r  {' ' * 20}\r", end="")
-    _done(f"{len(sentences):,} sentences in {elapsed:.2f}s")
-    _done(f"Written to {args.output_file}")
+    print(f"\n  {GREEN}Done!{RESET}")
     print()
 
 

{fast_sentence_segment-1.4.1 → fast_sentence_segment-1.4.3}/fast_sentence_segment/svc/perform_sentence_segmentation.py

@@ -3,10 +3,46 @@
 """ Sentence Segmentation """
 
 
+import subprocess
+import sys
+
 import spacy
 
 from fast_sentence_segment.core import BaseObject
 
+
+def _load_spacy_model(model_name: str = "en_core_web_sm"):
+    """Load spaCy model, auto-downloading if not found."""
+    # ANSI color codes
+    bold = "\033[1m"
+    cyan = "\033[36m"
+    green = "\033[32m"
+    yellow = "\033[33m"
+    reset = "\033[0m"
+
+    try:
+        return spacy.load(model_name)
+    except OSError:
+        print(f"\n{bold}{cyan}fast-sentence-segment{reset}", file=sys.stderr)
+        print(f"{'─' * 40}", file=sys.stderr)
+        print(
+            f"  {yellow}⚠{reset}  spaCy model '{model_name}' not found.",
+            file=sys.stderr,
+        )
+        print(f"  {yellow}⏳{reset} Downloading model (one-time setup)...", file=sys.stderr)
+        print(file=sys.stderr)
+
+        subprocess.check_call(
+            [sys.executable, "-m", "spacy", "download", model_name],
+        )
+
+        print(file=sys.stderr)
+        print(f"  {green}✓{reset}  Model '{model_name}' installed successfully.", file=sys.stderr)
+        print(f"  {green}✓{reset}  You won't see this message again.", file=sys.stderr)
+        print(file=sys.stderr)
+
+        return spacy.load(model_name)
+
 from fast_sentence_segment.dmo import AbbreviationMerger
 from fast_sentence_segment.dmo import AbbreviationSplitter
 from fast_sentence_segment.dmo import TitleNameMerger
@@ -45,7 +81,7 @@ class PerformSentenceSegmentation(BaseObject):
         """
         BaseObject.__init__(self, __name__)
         if not self.__nlp:
-            self.__nlp = spacy.load("en_core_web_sm")
+            self.__nlp = _load_spacy_model("en_core_web_sm")
 
         self._dehyphenate = Dehyphenator.process
         self._newlines_to_periods = NewlinesToPeriods.process

{fast_sentence_segment-1.4.1 → fast_sentence_segment-1.4.3}/pyproject.toml

@@ -11,7 +11,7 @@ description = "Fast and Efficient Sentence Segmentation"
 license = "MIT"
 name = "fast-sentence-segment"
 readme = "README.md"
-version = "1.4.1"
+version = "1.4.3"
 
 keywords = ["nlp", "text", "preprocess", "segment"]
 repository = "https://github.com/craigtrim/fast-sentence-segment"

fast_sentence_segment-1.4.3/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': '1.4.3',
+    '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[![Tests](https://img.shields.io/badge/tests-664-brightgreen)](https://github.com/craigtrim/fast-sentence-segment/tree/master/tests)\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-1.4.1/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': '1.4.1',
-    '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)