documentExtractionag051/ExtractDocument

1"""2pp_utils.py3===========4 5Utility functions for post-processing operations.6"""7 8import json9from .geometry_utils import TextRect10 11 12def open_json(file_name):13    """14    Open and load a JSON file.15    16    Args:17        file_name (str): Path to JSON file18    19    Returns:20        dict: Parsed JSON data21    """22    with open(file_name, "r", encoding="utf-8-sig") as f:23        content = f.read()24        25        # Handle potential duplicated content (legacy issue)26        repeat_index = content.find('{"pages":', content.find('{"pages":') + 1)27        if repeat_index != -1:28            content = content[:repeat_index]29        30        try:31            data = json.loads(content)32        except json.JSONDecodeError as e:33            print(f"Error decoding JSON: {e}")34            data = None35    36    return data37 38 39def create_text_rects(elements):40    """41    Create a list of TextRect objects from JSON elements.42    43    Args:44        elements (list): List of JSON elements containing geometry and other attributes.45    46    Returns:47        list: List of TextRect objects.48    """49    return [50        TextRect(51            x1=elem['geometry']['x1'],52            y1=elem['geometry']['y1'],53            x2=elem['geometry']['x2'],54            y2=elem['geometry']['y2'],55            confidence=elem.get('confidence', 0.0),56            block_type=elem.get('blockType', 'LINE'),57            text=elem.get('text', ''),58            page_num=elem.get('pageNum', 1)59        )60        for elem in elements61    ]62