utils/anoter_to_json.py

# import json

# def convert_to_spacy_format(json_data):
#     spacy_data = []
    
#     # Iterate over the annotations in the input JSON
#     for annotation in json_data['annotations']:
#         text = annotation[0]  # The text is the first element in each annotation
#         entities = annotation[1]['entities']  # The entities are in the second element under 'entities'
        
#         spacy_entities = []
#         for entity in entities:
#             start, end, label = entity
#             spacy_entities.append((start, end, label))
        
#         # Append the converted data in the desired format (like B.json)
#         spacy_data.append([text, {'entities': spacy_entities}])
    
#     return spacy_data

# # Load your JSON data from 'A.json'
# json_file_path = './JSON/Row_Json_Data.json'

# with open(json_file_path, 'r', encoding='utf-8') as file:
#     json_data = json.load(file)

# # Convert the JSON data to the desired format
# spacy_formatted_data = convert_to_spacy_format(json_data)

# # Save the converted data to 'B.json'
# output_file_path = './data/Json_Data.json'

# with open(output_file_path, 'w', encoding='utf-8') as outfile:
#     json.dump(spacy_formatted_data, outfile, ensure_ascii=False, indent=4)

# print(f'Successfully converted and saved the data to {output_file_path}')

import json
import os

def convert_to_spacy_format(json_data):
    spacy_data = []
    
    # Iterate over the annotations in the input JSON
    for annotation in json_data['annotations']:
        text = annotation[0]  # The text is the first element in each annotation
        entities = annotation[1]['entities']  # The entities are in the second element under 'entities'
        
        spacy_entities = []
        for entity in entities:
            start, end, label = entity
            spacy_entities.append((start, end, label))
        
        # Append the converted data in the desired format (like B.json)
        spacy_data.append([text, {'entities': spacy_entities}])
    
    return spacy_data

def process_uploaded_json(file_path):
    # Load your JSON data from the uploaded file
    with open(file_path, 'r', encoding='utf-8') as file:
        json_data = json.load(file)

    # Convert the JSON data to the desired format
    spacy_formatted_data = convert_to_spacy_format(json_data)

    # Define the path to the output file
    output_file_path = './data/Json_Data.json'

    # Check if the file already exists
    if os.path.exists(output_file_path):
        # If the file exists, load its content
        with open(output_file_path, 'r', encoding='utf-8') as outfile:
            existing_data = json.load(outfile)
    else:
        # If the file doesn't exist, start with an empty list
        existing_data = []

    # Append the new data to the existing data
    existing_data.extend(spacy_formatted_data)

    # Write the updated data back to the file
    with open(output_file_path, 'w', encoding='utf-8') as outfile:
        json.dump(existing_data, outfile, ensure_ascii=False, indent=4)

    print(f'Successfully appended the new data to {output_file_path}')