Create app.py

app.py

@@ -0,0 +1,157 @@
+# Add this to your imports
+from streamlit_sortables import sort_items
+import uuid
+
+# Function to get a thumbnail, using your original function
+def get_pdf_thumbnail(uploaded_file, page_num):
+    """Generates a thumbnail image of a PDF page."""
+    uploaded_file.seek(0)
+    doc = fitz.open(stream=uploaded_file.read(), filetype="pdf")
+    page = doc.load_page(page_num)
+    pix = page.get_pixmap()
+    img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+    img.thumbnail((100, 140))
+    return img
+
+# Sidebar Navigation
+st.sidebar.title("Tool Selector")
+selection = st.sidebar.radio("Choose a tool:", ["PDF Combiner", "PDF Transcriber", "PDF Rotator", "PDF Document Separator"])
+
+# PDF Document Separator Tool
+if selection == "PDF Document Separator":
+    st.title("PDF Document Separator")
+    st.write("Upload a multi-document PDF and separate the documents out.")
+
+    uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
+
+    if uploaded_file:
+        # Initialize session state variables if not already defined
+        if "uploaded_pdf" not in st.session_state:
+            st.session_state.uploaded_pdf = None
+        if "target_pages" not in st.session_state:
+            st.session_state.target_pages = [] # List of dictionaries of "page_index", "rotation", "uuid", "image"
+        if "available_pages" not in st.session_state:
+            st.session_state.available_pages = []
+
+        st.session_state.uploaded_pdf = uploaded_file
+
+        if not st.session_state.available_pages:
+          uploaded_file.seek(0)
+          doc = fitz.open(stream=uploaded_file.read(), filetype="pdf")
+          for page_num in range(len(doc)):
+            image = get_pdf_thumbnail(uploaded_file, page_num)
+            st.session_state.available_pages.append({"page_index":page_num, "rotation":0, "uuid":str(uuid.uuid4()), "image":image})
+
+
+
+        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)
+
+        with right_col:
+            st.header("Target Document Builder")
+            st.write("Reorder the pages, change rotation, and create the final document.")
+
+            if st.session_state.target_pages:
+                # Use sort_items for the right-hand column to manage reordering
+                target_page_uuids = [page["uuid"] for page in st.session_state.target_pages]
+                reordered_page_uuids = sort_items(target_page_uuids)
+                reordered_target_pages = [next(page for page in st.session_state.target_pages if page['uuid'] == uuid) for uuid in reordered_page_uuids]
+                st.session_state.target_pages = reordered_target_pages
+
+                for page in st.session_state.target_pages:
+                    with st.expander(f"Page {page['page_index'] + 1} Options", expanded=True):
+                        col1, col2 = st.columns([1,1])
+                        with col1:
+                          st.image(page["image"], use_container_width=True)
+                        with col2:
+                          rotation = st.selectbox(f"Rotation", [0, 90, 180, 270], key=page["uuid"], index = [0,90,180,270].index(page['rotation']))
+                          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":
+    st.title("PDF Combiner with Preview & Reordering")
+    st.write("Upload individual PDF pages, visualize them, reorder, and merge into a single PDF.")
+
+    uploaded_files = st.file_uploader("Upload PDF pages", type="pdf", accept_multiple_files=True)
+
+    if uploaded_files:
+        # Generate thumbnails and filenames for each uploaded PDF
+        thumbnails = []
+        filenames = []
+
+        for file in uploaded_files:
+            thumbnails.append(get_pdf_thumbnail(file, 0))
+            filenames.append(file.name)
+
+        # Display thumbnails with filenames for reordering
+        st.write("**Drag and drop to reorder the PDFs:**")
+        reordered_filenames = sort_items(filenames)
+
+        # Map the filenames back to the corresponding files
+        reordered_files = [uploaded_files[filenames.index(name)] for name in reordered_filenames]
+
+        # Display the thumbnails in the new order
+        st.write("**Preview of selected order:**")
+        cols = st.columns(len(reordered_files))
+        for idx, file in enumerate(reordered_files):
+            with cols[idx]:
+                st.image(get_pdf_thumbnail(file, 0), caption=file.name, use_container_width=True)
+
+        # Merge PDFs in the specified order
+        if st.button("Merge PDFs"):
+            output_file = merge_pdfs(reordered_files)
+            st.success("PDF pages combined successfully!")
+            download_file(output_file, generate_unique_filename("combined_document", "", ".pdf"), "application/pdf")
+            os.remove(output_file)
+
+# PDF Transcriber Tool
+elif selection == "PDF Transcriber":
+    st.title("PDF Transcriber Tool")
+    st.write("Upload a scanned PDF to transcribe the text.")
+    if not client:
+        st.error("Google Cloud credentials are not set. Please configure the secret.")
+    uploaded_file = st.file_uploader("Upload a PDF", type=["pdf"])
+    if uploaded_file and st.button("Transcribe PDF"):
+        with st.spinner("Processing..."):
+            output_file = process_pdf(uploaded_file)
+            if output_file:
+                st.success("Text extraction complete!")
+                st.text_area("Extracted Text", open(output_file, encoding="utf-8").read(), height=400)
+                output_file_name = generate_unique_filename(uploaded_file.name, "(T)", ".txt")
+                with open(output_file, "rb") as f:
+                  st.download_button("Download Extracted Text", f, file_name=output_file_name, mime="text/plain")
+                os.remove(output_file)
+            else:
+                st.error("Could not process the PDF, please try again")
+
+# PDF Rotator Tool
+elif selection == "PDF Rotator":
+    st.title("PDF Rotator")
+    st.write("Upload a PDF and rotate all pages by a specified angle.")
+
+    pdf_file = st.file_uploader("Upload PDF", type=["pdf"])
+    rotation_angle = st.selectbox("Select rotation angle:", [90, 180, 270])
+
+    if pdf_file:
+      if 'rotated_doc' not in st.session_state:
+          st.session_state.rotated_doc = None
+      if st.button("Rotate PDF"):
+        with st.spinner("Rotating PDF..."):
+          st.session_state.rotated_doc = rotate_pdf(pdf_file, rotation_angle)
+          st.success("PDF rotated successfully!")
+      if st.session_state.rotated_doc:
+          display_pdf_preview(st.session_state.rotated_doc)
+          if st.button("Download Rotated PDF"):
+              with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as temp_pdf:
+                  st.session_state.rotated_doc.save(temp_pdf.name)
+                  download_file(temp_pdf.name, generate_unique_filename(pdf_file.name, "(R)", ".pdf"), "application/pdf")
+                  os.remove(temp_pdf.name)