Create app.py

app.py

@@ -0,0 +1,47 @@
+import pdfplumber
+from transformers import LayoutLMv2Processor, LayoutLMv2ForTokenClassification
+import torch
+from difflib import unified_diff
+
+def extract_text_from_pdf(file_path):
+    """Extract text from a PDF using pdfplumber."""
+    text = ""
+    with pdfplumber.open(file_path) as pdf:
+        for page in pdf.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text + "\n"
+    return text
+
+def compare_texts(source_text, target_text):
+    """Compare two texts and highlight differences with source as truth."""
+    diff = unified_diff(
+        source_text.splitlines(),
+        target_text.splitlines(),
+        lineterm='',
+        fromfile='Source PDF',
+        tofile='Target PDF'
+    )
+    return '\n'.join(diff)
+
+def process_pdfs(pdf1, pdf2):
+    # Extract text from the uploaded PDFs
+    text1 = extract_text_from_pdf(pdf1)
+    text2 = extract_text_from_pdf(pdf2)
+
+    if not text1 or not text2:
+        return "One or both PDFs have no extractable text. Please check the files."
+
+    # Compare texts and find differences
+    differences = compare_texts(text1, text2)
+
+    return f"Differences found between the PDFs:\n\n{differences}"
+
+if __name__ == "__main__":
+    # Paths to your PDF files for testing
+    pdf1_path = "path/to/your/source.pdf"  # Replace with actual file path
+    pdf2_path = "path/to/your/target.pdf"  # Replace with actual file path
+
+    # Process and print differences
+    result = process_pdfs(pdf1_path, pdf2_path)
+    print(result)