Delete create_fitz_json.py

create_fitz_json.py

@@ -1,80 +0,0 @@
-import fitz  # PyMuPDF
-import json
-
-def extract_text_to_json_with_bbox(pdf_path):
-    # Open the PDF
-    doc = fitz.open(pdf_path)
-    pdf_name = pdf_path.split("/")[-1]  # Extract the PDF filename
-    result = {}
-
-    # Iterate through each page
-    for page_num in range(doc.page_count):
-        page = doc.load_page(page_num)
-        page_width = page.rect.width
-        page_height = page.rect.height
-
-        # Get text blocks
-        blocks = page.get_text("dict")["blocks"]
-        text_block_id = 0
-        element_id = 0
-        page_data = []
-
-        for block in blocks:
-            if block["type"] == 0:  # Text block
-                for line in block["lines"]:
-                    for span in line["spans"]:
-                        text = span["text"].strip()
-                        if text:  # Only process non-empty text
-                            bbox = span["bbox"]  # [x0, y0, x1, y1]
-                            font_size = span["size"]
-                            font_type = span["font"]
-
-                            # Create the JSON entry
-                            entry = {
-                                "text_block_id": text_block_id,
-                                "element_id": element_id,
-                                "text": text,
-                                "font_size": font_size,
-                                "font_type": font_type,
-                                "pdf_name": pdf_name,
-                                "bbox": list(bbox),
-                                "page_number": page_num + 1,
-                                "page_width": page_width,
-                                "page_height": page_height
-                            }
-                            page_data.append(entry)
-                            element_id += 1
-                text_block_id += 1
-
-        # Store page data in output dictionary
-        result[str(page_num + 1)] = page_data
-
-    # Close the PDF
-    doc.close()
-    return result
-
-def save_to_json(data, output_file):
-    with open(output_file, 'w', encoding='utf-8') as f:
-        json.dump(data, f, ensure_ascii=False, indent=4)
-
-
-
-
-if __name__ == "__main__":
-
-    # Example usage
-    # pdf_path = "/shared_disk/kushal/db_str_chunking/new_ws_structured_code/MILN/data_mike/Home Re 2021-1 Final Offering Circular.pdf"
-    pdf_path = "/shared_disk/kushal/db_str_chunking/new_ws_structured_code/MILN/data_fitz_test/3_column_layout_sample.pdf"
-    json_output = extract_text_to_json_with_bbox(pdf_path)
-
-    # Save to JSON file
-    with open("/shared_disk/kushal/db_str_chunking/new_ws_structured_code/MILN/output/3_column_output.json", "w") as f:
-        json.dump(json_output, f, indent=4)
-
-    # Print the JSON output
-    # print(json.dumps(json_output, indent=4))
-
-
-
-
-