Update app.py

app.py

@@ -91,7 +91,7 @@ def download_gitlab_repo():
         print("Upload complete")
 
 
-def extract_single_zip_file(directory):
+#def extract_single_zip_file(directory):
     zip_files = [file for file in os.listdir(directory) if file.endswith('.zip')]
 
     if not zip_files:
@@ -117,40 +117,49 @@ def process_directory(directory):
     all_texts = []
     file_references = []
 
-    directory_path = extract_single_zip_file(directory)
-    has_files = any(os.path.isfile(os.path.join(directory_path, file)) for file in os.listdir(directory_path))
-    os.listdir(directory_path))
-    if not has_files:
-        print(f"No files found in the directory: {directory_path}")
-        return all_texts, 
-    for root, _, files in os.walk(directory_path):
-        for file in files:
-            print(f"Any files??: {file}")
-            file_path = os.path.join(root, file)
-            file_ext = os.path.splitext(file_path)[1]
-
-            if os.path.getsize(file_path) == 0:
-                print(f"Skipping an empty file: {file_path}")
-                continue
-
-            with open(file_path, 'rb') as f:
-                if file_ext in ['.rst', '.md', '.txt', '.html', '.json', '.yaml', '.py']:
-                    text = f.read().decode('utf-8')
-                    print(f"Extracted text from {file_path}:\n{text[:200]}...\n")
-                elif file_ext == '.pdf':
-                    reader = PdfReader(f)
-                    text = ""
-                    for page in reader.pages:
-                        text += page.extract_text()
-                elif file_ext in ['.svg']:
-                    text = f"SVG file content from {file_path}"
-                elif file_ext in ['.png', '.ico']:
-                    text = f"Image metadata from {file_path}"
-                else:
-                    continue
-
-                all_texts.append(text)
-                file_references.append(file_path)
+    zip_files = [file for file in os.listdir(directory) if file.endswith('.zip')]
+
+    if not zip_files:
+        print("No zip file found in the directory.")
+        return all_texts, file_references
+
+    if len(zip_files) > 1:
+        print("More than one zip file found.")
+        return all_texts, file_references
+    else:
+        zip_file_path = os.path.join(directory, zip_files[0])
+        
+        # Create a temporary directory for the zip file
+        with tempfile.TemporaryDirectory() as tmpdirname:
+            # Unzip the file into the temporary directory
+            with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:
+                zip_ref.extractall(tmpdirname)
+            print(f"Extracted {zip_file_path} to {tmpdirname}")
+
+            # Process the files in the temporary directory
+            for root, _, files in os.walk(tmpdirname):
+                for file in files:
+                    print(f"Any files??: {file}")
+                    file_path = os.path.join(root, file)
+                    file_ext = os.path.splitext(file_path)[1]
+
+                    if os.path.getsize(file_path) == 0:
+                        print(f"Skipping an empty file: {file_path}")
+                        continue
+
+                    with open(file_path, 'rb') as f:
+                        if file_ext in ['.rst', '.md', '.txt', '.html', '.json', '.yaml', '.py']:
+                            text = f.read().decode('utf-8')
+                            print(f"Extracted text from {file_path}:\n{text[:200]}...\n")
+                        elif file_ext in ['.svg']:
+                            text = f"SVG file content from {file_path}"
+                        elif file_ext in ['.png', '.ico']:
+                            text = f"Image metadata from {file_path}"
+                        else:
+                            continue
+
+                        all_texts.append(text)
+                        file_references.append(file_path)
                 
     print(f"All extracted texts:\n{all_texts}")
     return all_texts, file_references