text-summarizer-aweebtaku 1.2.6__tar.gz → 1.2.7__tar.gz

{text_summarizer_aweebtaku-1.2.6 → text_summarizer_aweebtaku-1.2.7}/LICENSE

@@ -1,21 +1,21 @@
-MIT License
-
-Copyright (c) 2026 Aditya Chaurasiya
-
-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
+MIT License
+
+Copyright (c) 2026 Aditya Chaurasiya
+
+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.

{text_summarizer_aweebtaku-1.2.6 → text_summarizer_aweebtaku-1.2.7}/MANIFEST.in

@@ -1,7 +1,7 @@
-include README.md
-include LICENSE
-include requirements.txt
-include create_shortcuts.bat
-recursive-include text_summarizer/data *.csv
-global-exclude *.pyc
+include README.md
+include LICENSE
+include requirements.txt
+include create_shortcuts.bat
+recursive-include text_summarizer/data *.csv
+global-exclude *.pyc
 global-exclude __pycache__

{text_summarizer_aweebtaku-1.2.6/text_summarizer_aweebtaku.egg-info → text_summarizer_aweebtaku-1.2.7}/PKG-INFO

@@ -1,206 +1,217 @@
-Metadata-Version: 2.1
-Name: text-summarizer-aweebtaku
-Version: 1.2.6
-Summary: A text summarization tool using GloVe embeddings and PageRank algorithm
-Home-page: https://github.com/AWeebTaku/Summarizer
-Author: Aditya Chaurasiya
-Author-email: adityachaurasiya57527@gmail.com
-License: MIT
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.8
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Requires-Python: >=3.8
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: pandas>=1.3.0
-Requires-Dist: numpy>=1.21.0
-Requires-Dist: nltk>=3.6
-Requires-Dist: scikit-learn>=1.0
-Requires-Dist: networkx>=2.6
-Requires-Dist: requests>=2.25.0
-
-# Text Summarizer
-
-A Python-based text summarization tool that uses GloVe word embeddings and PageRank algorithm to generate extractive summaries of documents.
-
-## Features
-
-- **Extractive Summarization**: Uses sentence similarity and PageRank to identify the most important sentences
-- **GloVe Embeddings**: Leverages pre-trained GloVe word vectors for semantic similarity calculation
-- **Multiple Input Methods**: Support for single documents, CSV files, or interactive creation
-- **GUI Interface**: User-friendly Tkinter-based graphical interface
-- **Command Line Interface**: Scriptable command-line tool for automation
-- **Batch Processing**: Process multiple documents at once
-
-## Installation
-
-### Prerequisites
-
-- Python 3.8 or higher
-- Required packages (automatically installed): pandas, numpy, nltk, scikit-learn, networkx
-
-### Install from PyPI
-
-```bash
-pip install text-summarizer-aweebtaku
-```
-
-### Install from Source
-
-1. Clone the repository:
-```bash
-git clone https://github.com/AWeebTaku/Summarizer.git
-cd Summarizer
-```
-
-2. Install the package:
-```bash
-pip install -e .
-```
-
-### Upgrade Package
-
-To upgrade to the latest version with new features:
-```bash
-pip install --upgrade text-summarizer-aweebtaku
-```
-
-### Create Desktop Shortcuts (Windows)
-
-After installation, create desktop shortcuts for easy access:
-
-**Option 1: Automatic (Recommended)**
-```bash
-text-summarizer-shortcuts
-```
-This will create desktop shortcuts for both GUI and CLI versions.
-
-**Option 2: Manual**
-Run the included batch file:
-```cmd
-create_shortcuts.bat
-```
-
-### Download GloVe Embeddings
-
-**No manual download required!** The package will automatically download GloVe embeddings (100d, ~400MB) on first use and cache them in your home directory (`~/.text_summarizer/`).
-
-If you prefer to use your own GloVe file, you can specify the path:
-```python
-summarizer = TextSummarizer(glove_path='path/to/your/glove.6B.100d.txt')
-```
-
-## Usage
-
-### Console Scripts
-
-After installation, you can use these commands from anywhere:
-
-```bash
-# Upgrade to the latest version
-pip install --upgrade text-summarizer-aweebtaku
-
-# Launch the graphical user interface
-text-summarizer-gui
-
-# Use the command line interface
-text-summarizer-aweebtaku --help
-
-# Create desktop shortcuts (Windows only)
-text-summarizer-shortcuts
-```
-
-### Command Line Interface
-
-```bash
-# Summarize a CSV file
-text-summarizer-aweebtaku --csv-file data/tennis.csv --article-id 1
-
-# Interactive mode
-text-summarizer-aweebtaku
-```
-
-### Graphical User Interface
-
-```bash
-# Launch GUI (easiest way)
-text-summarizer-aweebtaku --gui
-
-# Or use the dedicated GUI command
-text-summarizer-gui
-```
-
-### Python API
-
-```python
-from text_summarizer import TextSummarizer
-
-# Initialize summarizer (automatic GloVe download)
-summarizer = TextSummarizer(num_sentences=3)
-
-# Simple text summarization
-text = "Your long text here..."
-summary = summarizer.summarize_text(text)
-print(summary)
-
-# Advanced usage with DataFrame
-import pandas as pd
-df = pd.DataFrame([{'article_id': 1, 'article_text': text}])
-scored_sentences = summarizer.run_summarization(df)
-article_text, summary = summarizer.summarize_article(scored_sentences, 1, df)
-```
-
-## Data Format
-
-Input data should be in CSV format with columns:
-- `article_id`: Unique identifier for each document
-- `article_text`: The full text of the document
-
-Example:
-```csv
-article_id,article_text
-1,"This is the first article. It contains multiple sentences..."
-2,"This is the second article. It also has several sentences..."
-```
-
-## Algorithm
-
-The summarization process follows these steps:
-
-1. **Sentence Tokenization**: Split documents into individual sentences
-2. **Text Cleaning**: Remove punctuation, convert to lowercase, remove stopwords
-3. **Sentence Vectorization**: Convert sentences to vectors using GloVe embeddings
-4. **Similarity Calculation**: Compute cosine similarity between all sentence pairs
-5. **PageRank Scoring**: Apply PageRank algorithm to identify important sentences
-6. **Summary Extraction**: Select top-ranked sentences in original order
-
-## Configuration
-
-- `glove_path`: Path to GloVe embeddings file (default: 'glove.6B.100d.txt/glove.6B.100d.txt')
-- `num_sentences`: Number of sentences in summary (default: 5)
-
-## License
-
-This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
-
-## Contributing
-
-Contributions are welcome! Please feel free to submit a Pull Request.
-
-## Citation
-
-If you use this tool in your research, please cite:
-
-```
-@software{text_summarizer,
-  title = {Text Summarizer},
-  author = {Aditya Chaurasiya},
-  url = {https://github.com/AWeebTaku/Summarizer},
-  year = {2026}
-}
-```
+Metadata-Version: 2.4
+Name: text-summarizer-aweebtaku
+Version: 1.2.7
+Summary: A text summarization tool using GloVe embeddings and PageRank algorithm
+Home-page: https://github.com/AWeebTaku/Summarizer
+Author: Aditya Chaurasiya
+Author-email: adityachaurasiya57527@gmail.com
+License: MIT
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas>=1.3.0
+Requires-Dist: numpy>=1.21.0
+Requires-Dist: nltk>=3.6
+Requires-Dist: scikit-learn>=1.0
+Requires-Dist: networkx>=2.6
+Requires-Dist: requests>=2.25.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# Text Summarizer
+
+A Python-based text summarization tool that uses GloVe word embeddings and PageRank algorithm to generate extractive summaries of documents.
+
+## Features
+
+- **Extractive Summarization**: Uses sentence similarity and PageRank to identify the most important sentences
+- **GloVe Embeddings**: Leverages pre-trained GloVe word vectors for semantic similarity calculation
+- **Multiple Input Methods**: Support for single documents, CSV files, or interactive creation
+- **GUI Interface**: User-friendly Tkinter-based graphical interface
+- **Command Line Interface**: Scriptable command-line tool for automation
+- **Batch Processing**: Process multiple documents at once
+
+## Installation
+
+### Prerequisites
+
+- Python 3.8 or higher
+- Required packages (automatically installed): pandas, numpy, nltk, scikit-learn, networkx
+
+### Install from PyPI
+
+```bash
+pip install text-summarizer-aweebtaku
+```
+
+### Install from Source
+
+1. Clone the repository:
+```bash
+git clone https://github.com/AWeebTaku/Summarizer.git
+cd Summarizer
+```
+
+2. Install the package:
+```bash
+pip install -e .
+```
+
+### Upgrade Package
+
+To upgrade to the latest version with new features:
+```bash
+pip install --upgrade text-summarizer-aweebtaku
+```
+
+### Create Desktop Shortcuts (Windows)
+
+After installation, create desktop shortcuts for easy access:
+
+**Option 1: Automatic (Recommended)**
+```bash
+text-summarizer-shortcuts
+```
+This will create desktop shortcuts for both GUI and CLI versions.
+
+**Option 2: Manual**
+Run the included batch file:
+```cmd
+create_shortcuts.bat
+```
+
+### Download GloVe Embeddings
+
+**No manual download required!** The package will automatically download GloVe embeddings (100d, ~400MB) on first use and cache them in your home directory (`~/.text_summarizer/`).
+
+If you prefer to use your own GloVe file, you can specify the path:
+```python
+summarizer = TextSummarizer(glove_path='path/to/your/glove.6B.100d.txt')
+```
+
+## Usage
+
+### Console Scripts
+
+After installation, you can use these commands from anywhere:
+
+```bash
+# Upgrade to the latest version
+pip install --upgrade text-summarizer-aweebtaku
+
+# Launch the graphical user interface
+text-summarizer-gui
+
+# Use the command line interface
+text-summarizer-aweebtaku --help
+
+# Create desktop shortcuts (Windows only)
+text-summarizer-shortcuts
+```
+
+### Command Line Interface
+
+```bash
+# Summarize a CSV file
+text-summarizer-aweebtaku --csv-file data/tennis.csv --article-id 1
+
+# Interactive mode
+text-summarizer-aweebtaku
+```
+
+### Graphical User Interface
+
+```bash
+# Launch GUI (easiest way)
+text-summarizer-aweebtaku --gui
+
+# Or use the dedicated GUI command
+text-summarizer-gui
+```
+
+### Python API
+
+```python
+from text_summarizer import TextSummarizer
+
+# Initialize summarizer (automatic GloVe download)
+summarizer = TextSummarizer(num_sentences=3)
+
+# Simple text summarization
+text = "Your long text here..."
+summary = summarizer.summarize_text(text)
+print(summary)
+
+# Advanced usage with DataFrame
+import pandas as pd
+df = pd.DataFrame([{'article_id': 1, 'article_text': text}])
+scored_sentences = summarizer.run_summarization(df)
+article_text, summary = summarizer.summarize_article(scored_sentences, 1, df)
+```
+
+## Data Format
+
+Input data should be in CSV format with columns:
+- `article_id`: Unique identifier for each document
+- `article_text`: The full text of the document
+
+Example:
+```csv
+article_id,article_text
+1,"This is the first article. It contains multiple sentences..."
+2,"This is the second article. It also has several sentences..."
+```
+
+## Algorithm
+
+The summarization process follows these steps:
+
+1. **Sentence Tokenization**: Split documents into individual sentences
+2. **Text Cleaning**: Remove punctuation, convert to lowercase, remove stopwords
+3. **Sentence Vectorization**: Convert sentences to vectors using GloVe embeddings
+4. **Similarity Calculation**: Compute cosine similarity between all sentence pairs
+5. **PageRank Scoring**: Apply PageRank algorithm to identify important sentences
+6. **Summary Extraction**: Select top-ranked sentences in original order
+
+## Configuration
+
+- `glove_path`: Path to GloVe embeddings file (default: 'glove.6B.100d.txt/glove.6B.100d.txt')
+- `num_sentences`: Number of sentences in summary (default: 5)
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request.
+
+## Citation
+
+If you use this tool in your research, please cite:
+
+```
+@software{text_summarizer,
+  title = {Text Summarizer},
+  author = {Aditya Chaurasiya},
+  url = {https://github.com/AWeebTaku/Summarizer},
+  year = {2026}
+}
+```