text-summarizer-aweebtaku 1.0.1__tar.gz → 1.0.2__tar.gz

{text_summarizer_aweebtaku-1.0.1/text_summarizer_aweebtaku.egg-info → text_summarizer_aweebtaku-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: text-summarizer-aweebtaku
-Version: 1.0.1
+Version: 1.0.2
 Summary: A text summarization tool using GloVe embeddings and PageRank algorithm
 Home-page: https://github.com/AWeebTaku/Summarizer
 Author: Your Name
@@ -60,6 +60,8 @@ 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:
@@ -73,16 +75,7 @@ cd Summarizer
 pip install -e .
 ```
 
-### Download GloVe Embeddings
-
-The tool requires GloVe word embeddings. Download the 100d version:
-
-```bash
-wget http://nlp.stanford.edu/data/glove.6B.zip
-unzip glove.6B.zip
-```
-
-Place the `glove.6B.100d.txt` file in the project root or specify the path.
+**Note:** The GloVe word embeddings are included in the package, so no additional download is required.
 
 ## Usage
 

{text_summarizer_aweebtaku-1.0.1 → text_summarizer_aweebtaku-1.0.2}/README.md

@@ -24,6 +24,8 @@ 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:
@@ -37,16 +39,7 @@ cd Summarizer
 pip install -e .
 ```
 
-### Download GloVe Embeddings
-
-The tool requires GloVe word embeddings. Download the 100d version:
-
-```bash
-wget http://nlp.stanford.edu/data/glove.6B.zip
-unzip glove.6B.zip
-```
-
-Place the `glove.6B.100d.txt` file in the project root or specify the path.
+**Note:** The GloVe word embeddings are included in the package, so no additional download is required.
 
 ## Usage
 

{text_summarizer_aweebtaku-1.0.1 → text_summarizer_aweebtaku-1.0.2}/setup.py

@@ -8,7 +8,7 @@ with open("requirements.txt", "r", encoding="utf-8") as fh:
 
 setup(
     name="text-summarizer-aweebtaku",
-    version="1.0.1",
+    version="1.0.2",
     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={
-        "textsummarizer": ["data/*.csv"],
+        "text_summarizer": ["data/*.csv"],
     },
 )

{text_summarizer_aweebtaku-1.0.1 → text_summarizer_aweebtaku-1.0.2}/text_summarizer/summarizer.py

@@ -6,6 +6,10 @@ 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')
@@ -14,13 +18,58 @@ import networkx as nx
 class TextSummarizer:
     """A class for summarizing text documents using GloVe embeddings and PageRank."""
 
-    def __init__(self, glove_path='glove.6B.100d.txt/glove.6B.100d.txt', num_sentences=5):
+    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'))
         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'
+        
+        try:
+            # Download the zip file
+            print(f"Downloading GloVe from {zip_url}...")
+            urllib.request.urlretrieve(zip_url, zip_path)
+            
+            # 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!")
+            
+        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")
+            raise
+
     def _load_embeddings(self):
         """Load GloVe word embeddings from file."""
         try:

{text_summarizer_aweebtaku-1.0.1 → text_summarizer_aweebtaku-1.0.2/text_summarizer_aweebtaku.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: text-summarizer-aweebtaku
-Version: 1.0.1
+Version: 1.0.2
 Summary: A text summarization tool using GloVe embeddings and PageRank algorithm
 Home-page: https://github.com/AWeebTaku/Summarizer
 Author: Your Name
@@ -60,6 +60,8 @@ 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:
@@ -73,16 +75,7 @@ cd Summarizer
 pip install -e .
 ```
 
-### Download GloVe Embeddings
-
-The tool requires GloVe word embeddings. Download the 100d version:
-
-```bash
-wget http://nlp.stanford.edu/data/glove.6B.zip
-unzip glove.6B.zip
-```
-
-Place the `glove.6B.100d.txt` file in the project root or specify the path.
+**Note:** The GloVe word embeddings are included in the package, so no additional download is required.
 
 ## Usage