Update app.py

app.py

@@ -1,8 +1,83 @@
-# Add this to your imports
+import os
+import streamlit as st # Moved this to the top
+from PyPDF2 import PdfMerger
+from google.cloud import vision
+from google.oauth2 import service_account
+import fitz
+from PIL import Image
+from io import BytesIO
+import tempfile
+import json
 from streamlit_sortables import sort_items
+import subprocess
+from tqdm import tqdm
+from datetime import datetime
 import uuid
 
-# Function to get a thumbnail, using your original function
+#os.environ["PATH"] += os.pathsep + "/usr/bin" + os.pathsep + "/usr/local/bin" #Removed redundant path setting
+print(f"Current PATH: {os.environ['PATH']}")
+
+
+# Check if /usr/bin/pdfinfo exists
+if os.path.exists("/usr/bin/pdfinfo"):
+    print("pdfinfo exists at /usr/bin/pdfinfo")
+    # Check the file permissions
+    permissions = os.stat("/usr/bin/pdfinfo").st_mode
+    print(f"File permissions: {oct(permissions)}")
+else:
+    print("pdfinfo does not exist at /usr/bin/pdfinfo")
+
+
+# Load Google Cloud Vision credentials from secret
+credentials_json = os.getenv("GOOGLE_CREDENTIALS_JSON")
+if credentials_json:
+    credentials_dict = json.loads(credentials_json)
+    credentials = service_account.Credentials.from_service_account_info(credentials_dict)
+    client = vision.ImageAnnotatorClient(credentials=credentials)
+else:
+    client = None
+
+# Function to extract text using Google Cloud Vision
+def extract_text_with_google_vision(image_bytes):
+    """Extracts text using Google Cloud Vision."""
+    image = vision.Image(content=image_bytes)
+    response = client.document_text_detection(image=image)
+    if response.error.message:
+        raise Exception(f"Google Cloud Vision API Error: {response.error.message}")
+    return response.full_text_annotation.text if response.full_text_annotation else ""
+
+# Function to process PDF for transcription
+def process_pdf(file):
+    """Converts PDF pages to images and extracts text."""
+    text = ""
+    with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as temp_pdf:
+        temp_pdf.write(file.read())
+        temp_pdf_path = temp_pdf.name
+
+    try:
+        doc = fitz.open(temp_pdf_path)
+        for i in tqdm(range(len(doc)), desc="Processing pages"):
+            page = doc.load_page(i)
+            pix = page.get_pixmap()
+            image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+            image_bytes = BytesIO()
+            image.save(image_bytes, format="PNG")
+            image_bytes.seek(0)
+            try:
+                page_text = extract_text_with_google_vision(image_bytes.getvalue())
+                text += f"--- Page {i + 1} ---\n{page_text}\n\n"
+            except Exception as e:
+                st.error(f"Error on page {i + 1}: {e}")
+    finally:
+        os.remove(temp_pdf_path)
+
+    with tempfile.NamedTemporaryFile(suffix=".txt", delete=False) as temp_txt:
+      temp_txt.write(text.encode("utf-8"))
+      temp_txt_path = temp_txt.name
+    return temp_txt_path
+
+
+# Function to generate thumbnail from PDF
 def get_pdf_thumbnail(uploaded_file, page_num):
     """Generates a thumbnail image of a PDF page."""
     uploaded_file.seek(0)
@@ -13,6 +88,53 @@ def get_pdf_thumbnail(uploaded_file, page_num):
     img.thumbnail((100, 140))
     return img
 
+# Function to merge PDFs
+def merge_pdfs(reordered_files):
+    """Merges multiple PDFs into one."""
+    merger = PdfMerger()
+    for file in reordered_files:
+        file.seek(0)
+        merger.append(file)
+    output_filename = "combined_document.pdf"
+    with open(output_filename, "wb") as output_file:
+        merger.write(output_file)
+    return output_filename
+
+def download_file(output_file, file_name, mime_type):
+    with open(output_file, "rb") as f:
+        st.download_button(
+            label="Download File",
+            data=f,
+            file_name=file_name,
+            mime=mime_type,
+        )
+
+def generate_unique_filename(original_filename, suffix, file_type):
+    """Generates a unique filename based on date, time, and original filename."""
+    now = datetime.now()
+    timestamp = now.strftime("%Y%m%d_%H%M%S")
+    name, ext = os.path.splitext(original_filename)
+    return f"{name}_{timestamp}{suffix}{file_type}"
+
+def rotate_pdf(pdf_file, rotation_angle):
+    """Rotates all pages of a PDF by a specified angle."""
+    with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as temp_pdf:
+        temp_pdf.write(pdf_file.read())
+        temp_pdf_path = temp_pdf.name
+
+    doc = fitz.open(temp_pdf_path)
+    for page in doc:
+        page.set_rotation(rotation_angle)
+    os.remove(temp_pdf_path)
+    return doc
+
+def display_pdf_preview(doc, page_num=0):
+    """Displays a preview of a PDF page."""
+    page = doc.load_page(page_num)
+    pix = page.get_pixmap()
+    img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+    st.image(img, use_container_width=True)
+
 # Sidebar Navigation
 st.sidebar.title("Tool Selector")
 selection = st.sidebar.radio("Choose a tool:", ["PDF Combiner", "PDF Transcriber", "PDF Rotator", "PDF Document Separator"])
@@ -43,15 +165,24 @@ if selection == "PDF Document Separator":
             st.session_state.available_pages.append({"page_index":page_num, "rotation":0, "uuid":str(uuid.uuid4()), "image":image})
 
 
+        def move_page_to_target(page_uuid):
+          """Moves a page from available_pages to target_pages."""
+          page_to_move = next((page for page in st.session_state.available_pages if page["uuid"] == page_uuid), None)
+          if page_to_move:
+            st.session_state.target_pages.append(page_to_move)
+            st.session_state.available_pages = [page for page in st.session_state.available_pages if page["uuid"] != page_uuid]
 
         left_col, right_col = st.columns(2)
 
-
         with left_col:
             st.header("Document Overview")
             st.write("Drag pages to the right to start creating the new document.")
             for page in st.session_state.available_pages:
-                st.image(page["image"], caption=f"Page {page['page_index'] + 1}", use_container_width=True)
+              # Add a button for each page to move to the right column
+              if st.button(f"Add Page {page['page_index'] + 1} to Document", key=f"button_{page['uuid']}"):
+                  move_page_to_target(page["uuid"])
+              st.image(page["image"], caption=f"Page {page['page_index'] + 1}", use_container_width=True)
+
 
         with right_col:
             st.header("Target Document Builder")
@@ -74,7 +205,6 @@ if selection == "PDF Document Separator":
                           if rotation != page['rotation']:
                             page['rotation'] = rotation
 
-
 # The rest of your original app.py code should go here
 # PDF Combiner with Preview and Reordering
 elif selection == "PDF Combiner":