Update tools/pdfquery

tools/pdfquery

@@ -1,37 +1,54 @@
-""" first install pypdf using pip install pypdf"""
+import os
 import pypdf
 
-def search_word_in_pdf(pdf_path, search_word):
+def search_word_in_folder(folder_path, search_word):
     """
-    Searches for a specific word in a PDF file and prints the pages where it's found.
+    Searches for a word across all PDF files in a given folder.
     """
-    # Open the PDF file
-    with open(pdf_path, 'rb') as file:
-        # Create a PDF reader object
-        reader = pypdf.PdfReader(file)
-        
-        # Track if the word was found at all
-        found_matches = False
-        
-        print(f"Searching for '{search_word}' in '{pdf_path}'...\n")
-        
-        # Loop through each page (0-indexed, so we add 1 for actual page number)
-        for page_num, page in enumerate(reader.pages, start=1):
-            # Extract text from the page
-            text = page.extract_text()
+    # Normalize the search word for case-insensitive matching
+    search_word_lower = search_word.lower()
+    
+    # Check if the folder exists
+    if not os.path.exists(folder_path):
+        print(f"❌ Error: The folder '{folder_path}' does not exist.")
+        return
+
+    print(f"Scanning folder '{folder_path}' for '{search_word}'...\n")
+    overall_matches = 0
+
+    # Loop through all files in the directory
+    for filename in os.listdir(folder_path):
+        # Only process files that end with .pdf
+        if filename.lower().endswith('.pdf'):
+            pdf_path = os.path.join(folder_path, filename)
             
-            # Perform case-insensitive search
-            if text and search_word.lower() in text.lower():
-                print(f"✅ Found on Page {page_num}")
-                found_matches = True
+            try:
+                with open(pdf_path, 'rb') as file:
+                    reader = pypdf.PdfReader(file)
+                    file_has_matches = False
+                    
+                    # Search page by page
+                    for page_num, page in enumerate(reader.pages, start=1):
+                        text = page.extract_text()
+                        
+                        if text and search_word_lower in text.lower():
+                            # Print the filename and page number where found
+                            print(f"✅ Found in [{filename}] on Page {page_num}")
+                            file_has_matches = True
+                            overall_matches += 1
+                            
+            except Exception as e:
+                print(f"⚠️ Could not read file {filename}: {e}")
                 
-        if not found_matches:
-            print("❌ Word not found in the document.")
+    if overall_matches == 0:
+        print("❌ Word not found in any PDF files inside this folder.")
+    else:
+        print(f"\nSearch complete. Total matches found: {overall_matches}")
 
 # Example Usage
 if __name__ == "__main__":
-    # Replace with your actual PDF file path and target word
-    pdf_file = "sample.pdf"
-    word_to_find = "invoice"
+    # Replace with the path to your folder
+    my_folder = "./my_pdf_documents" 
+    word_to_find = "contract"
     
-    search_word_in_pdf(pdf_file, word_to_find)
+    search_word_in_folder(my_folder, word_to_find)