text-summarizer-aweebtaku 1.0.2__tar.gz → 1.1.0__tar.gz

{text_summarizer_aweebtaku-1.0.2/text_summarizer_aweebtaku.egg-info → text_summarizer_aweebtaku-1.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: text-summarizer-aweebtaku
-Version: 1.0.2
+Version: 1.1.0
 Summary: A text summarization tool using GloVe embeddings and PageRank algorithm
 Home-page: https://github.com/AWeebTaku/Summarizer
 Author: Your Name
@@ -22,6 +22,7 @@ Requires-Dist: numpy
 Requires-Dist: nltk
 Requires-Dist: scikit-learn
 Requires-Dist: networkx
+Requires-Dist: requests
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -60,8 +61,6 @@ A Python-based text summarization tool that uses GloVe word embeddings and PageR
 pip install text-summarizer-aweebtaku
 ```
 
-**Note:** This package includes the GloVe word embeddings file (~400MB), so the installation may take some time.
-
 ### Install from Source
 
 1. Clone the repository:
@@ -75,7 +74,14 @@ cd Summarizer
 pip install -e .
 ```
 
-**Note:** The GloVe word embeddings are included in the package, so no additional download is required.
+### 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
 

{text_summarizer_aweebtaku-1.0.2 → text_summarizer_aweebtaku-1.1.0}/README.md

@@ -24,8 +24,6 @@ A Python-based text summarization tool that uses GloVe word embeddings and PageR
 pip install text-summarizer-aweebtaku
 ```
 
-**Note:** This package includes the GloVe word embeddings file (~400MB), so the installation may take some time.
-
 ### Install from Source
 
 1. Clone the repository:
@@ -39,7 +37,14 @@ cd Summarizer
 pip install -e .
 ```
 
-**Note:** The GloVe word embeddings are included in the package, so no additional download is required.
+### 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
 

{text_summarizer_aweebtaku-1.0.2 → text_summarizer_aweebtaku-1.1.0}/requirements.txt

@@ -2,4 +2,5 @@ pandas
 numpy
 nltk
 scikit-learn
-networkx
+networkx
+requests

{text_summarizer_aweebtaku-1.0.2 → text_summarizer_aweebtaku-1.1.0}/setup.py

@@ -8,7 +8,7 @@ with open("requirements.txt", "r", encoding="utf-8") as fh:
 
 setup(
     name="text-summarizer-aweebtaku",
-    version="1.0.2",
+    version="1.1.0",
     author="Your Name",
     author_email="your.email@example.com",
     description="A text summarization tool using GloVe embeddings and PageRank algorithm",
@@ -37,6 +37,6 @@ setup(
     },
     include_package_data=True,
     package_data={
-        "text_summarizer": ["data/*.csv"],
+        "textsummarizer": ["data/*.csv"],
     },
 )

{text_summarizer_aweebtaku-1.0.2 → text_summarizer_aweebtaku-1.1.0}/text_summarizer/summarizer.py

@@ -2,14 +2,13 @@ import pandas as pd
 import numpy as np
 import nltk
 import os
+import requests
+import zipfile
+from pathlib import Path
 from nltk.tokenize import sent_tokenize
 from nltk.corpus import stopwords
 from sklearn.metrics.pairwise import cosine_similarity
 import networkx as nx
-import pkg_resources
-import urllib.request
-import zipfile
-import shutil
 
 # Download necessary NLTK data
 # nltk.download('punkt_tab')
@@ -19,68 +18,88 @@ class TextSummarizer:
     """A class for summarizing text documents using GloVe embeddings and PageRank."""
 
     def __init__(self, glove_path=None, num_sentences=5):
-        if glove_path is None:
-            # Try to find GloVe file in package data first
-            try:
-                glove_path = pkg_resources.resource_filename('text_summarizer', 'glove.6B.100d.txt/glove.6B.100d.txt')
-            except (FileNotFoundError, ModuleNotFoundError):
-                # Fallback to default path
-                glove_path = 'glove.6B.100d.txt/glove.6B.100d.txt'
-        
-        # Download GloVe if it doesn't exist
-        if not os.path.exists(glove_path):
-            print("GloVe embeddings not found. Downloading...")
-            self._download_glove()
-        
-        self.glove_path = glove_path
         self.num_sentences = num_sentences
         self.word_embeddings = {}
         self.stop_words = set(stopwords.words('english'))
+
+        # Set default GloVe path
+        if glove_path is None:
+            glove_path = self._get_default_glove_path()
+
+        self.glove_path = glove_path
         self._load_embeddings()
 
-    def _download_glove(self):
-        """Download and extract GloVe embeddings."""
-        glove_dir = 'glove.6B.100d.txt'
-        glove_file = os.path.join(glove_dir, 'glove.6B.100d.txt')
-        zip_url = 'http://nlp.stanford.edu/data/glove.6B.zip'
-        zip_path = 'glove.6B.zip'
-        
+    def _get_default_glove_path(self):
+        """Get the default path for GloVe embeddings."""
+        # Use user's home directory for data
+        home_dir = Path.home()
+        glove_dir = home_dir / '.text_summarizer'
+        glove_dir.mkdir(exist_ok=True)
+        return glove_dir / 'glove.6B.100d.txt'
+
+    def _download_glove_embeddings(self):
+        """Download GloVe embeddings if not present."""
+        print("GloVe embeddings not found. Downloading from Stanford NLP...")
+
+        # Create directory if it doesn't exist
+        glove_file = Path(self.glove_path)
+        glove_file.parent.mkdir(exist_ok=True)
+
+        # Download the zip file
+        url = "https://nlp.stanford.edu/data/glove.6B.zip"
+        zip_path = glove_file.parent / "glove.6B.zip"
+
         try:
-            # Download the zip file
-            print(f"Downloading GloVe from {zip_url}...")
-            urllib.request.urlretrieve(zip_url, zip_path)
-            
+            print("Downloading GloVe embeddings (862 MB)...")
+            response = requests.get(url, stream=True)
+            response.raise_for_status()
+
+            total_size = int(response.headers.get('content-length', 0))
+            downloaded_size = 0
+
+            with open(zip_path, 'wb') as f:
+                for chunk in response.iter_content(chunk_size=8192):
+                    if chunk:
+                        f.write(chunk)
+                        downloaded_size += len(chunk)
+                        if total_size > 0:
+                            progress = (downloaded_size / total_size) * 100
+                            print(".1f", end='', flush=True)
+
+            print("\nDownload complete. Extracting...")
+
             # Extract the specific file we need
-            print("Extracting GloVe embeddings...")
             with zipfile.ZipFile(zip_path, 'r') as zip_ref:
-                # Create directory if it doesn't exist
-                os.makedirs(glove_dir, exist_ok=True)
-                # Extract only the 100d file
-                zip_ref.extract('glove.6B.100d.txt', '.')
-                # Move to the expected directory
-                if os.path.exists('glove.6B.100d.txt'):
-                    shutil.move('glove.6B.100d.txt', glove_file)
-            
-            # Clean up
-            os.remove(zip_path)
-            print("GloVe embeddings downloaded successfully!")
-            
+                zip_ref.extract('glove.6B.100d.txt', glove_file.parent)
+
+            # Clean up zip file
+            zip_path.unlink()
+
+            print(f"GloVe embeddings extracted to {self.glove_path}")
+
         except Exception as e:
             print(f"Failed to download GloVe embeddings: {e}")
-            print("Please download manually from: http://nlp.stanford.edu/data/glove.6B.zip")
+            print("Please download manually from: https://nlp.stanford.edu/data/glove.6B.zip")
             raise
 
     def _load_embeddings(self):
         """Load GloVe word embeddings from file."""
+        if not os.path.exists(self.glove_path):
+            self._download_glove_embeddings()
+
         try:
+            print(f"Loading GloVe embeddings from {self.glove_path}...")
             with open(self.glove_path, 'r', encoding='utf-8') as f:
                 for line in f:
                     values = line.split()
                     word = values[0]
                     coefs = np.asarray(values[1:], dtype='float32')
                     self.word_embeddings[word] = coefs
+            print(f"Loaded {len(self.word_embeddings)} word embeddings.")
         except FileNotFoundError:
             raise FileNotFoundError(f"GloVe file not found at {self.glove_path}")
+        except Exception as e:
+            raise Exception(f"Error loading GloVe embeddings: {e}")
 
     def load_data(self):
         """Load data interactively."""

{text_summarizer_aweebtaku-1.0.2 → text_summarizer_aweebtaku-1.1.0/text_summarizer_aweebtaku.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: text-summarizer-aweebtaku
-Version: 1.0.2
+Version: 1.1.0
 Summary: A text summarization tool using GloVe embeddings and PageRank algorithm
 Home-page: https://github.com/AWeebTaku/Summarizer
 Author: Your Name
@@ -22,6 +22,7 @@ Requires-Dist: numpy
 Requires-Dist: nltk
 Requires-Dist: scikit-learn
 Requires-Dist: networkx
+Requires-Dist: requests
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -60,8 +61,6 @@ A Python-based text summarization tool that uses GloVe word embeddings and PageR
 pip install text-summarizer-aweebtaku
 ```
 
-**Note:** This package includes the GloVe word embeddings file (~400MB), so the installation may take some time.
-
 ### Install from Source
 
 1. Clone the repository:
@@ -75,7 +74,14 @@ cd Summarizer
 pip install -e .
 ```
 
-**Note:** The GloVe word embeddings are included in the package, so no additional download is required.
+### 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
 

{text_summarizer_aweebtaku-1.0.2 → text_summarizer_aweebtaku-1.1.0}/text_summarizer_aweebtaku.egg-info/requires.txt

@@ -3,3 +3,4 @@ numpy
 nltk
 scikit-learn
 networkx
+requests