ファイルカテゴリの修正（ファイル分割）

import requests
import json

def amend_split_category(workspace_id, task_id, split_tasks, app_id, secret_code):
    """
    Amend category and page numbers for file split tasks

    Args:
        workspace_id: Workspace ID
        task_id: Parent task ID (file split task ID)
        split_tasks: Split task list, format:
            [
                {
                    "category": "Category name",
                    "pages": [0, 1]  # Page number array, starting from 0
                },
                ...
            ]
        app_id: Application ID
        secret_code: Secret code
    """
    url = "https://docflow.textin.ai/api/app-api/sip/platform/v2/file/amend_category"

    headers = {
        "x-ti-app-id": app_id,
        "x-ti-secret-code": secret_code,
        "Content-Type": "application/json"
    }

    payload = {
        "workspace_id": workspace_id,
        "task_id": task_id,
        "split_tasks": split_tasks
    }

    response = requests.post(url, headers=headers, json=payload)
    return response.json()

# Usage example
if __name__ == "__main__":
    WORKSPACE_ID = "1234567890"
    PARENT_TASK_ID = "1234567890"  # Parent task ID (task_type = 2)
    APP_ID = "<your-app-id>"
    SECRET_CODE = "<your-secret-code>"

    # Important: Must include all split child file information
    # Assuming the original file is split into 3 child files:
    # - Child file 1: Pages 1-2, category "Invoice"
    # - Child file 2: Pages 3-5, category "Contract"
    # - Child file 3: Pages 6-7, category "Receipt"
    #
    # If you only need to modify child file 1's category, you must also include information for child files 2 and 3
    split_tasks = [
        {
            "category": "Electronic Invoice (Regular)",  # Modified category
            "pages": [0, 1]  # Keep original page numbers
        },
        {
            "category": "Contract",  # Keep original category
            "pages": [2, 3, 4]  # Keep original page numbers
        },
        {
            "category": "Receipt",  # Keep original category
            "pages": [5, 6]  # Keep original page numbers (Note: original file pages 6-7 correspond to page numbers 5-6)
        }
    ]

    result = amend_split_category(WORKSPACE_ID, PARENT_TASK_ID, split_tasks, APP_ID, SECRET_CODE)
    print(json.dumps(result, indent=2, ensure_ascii=False))

import requests
import json

def get_split_task_info(workspace_id, file_id, app_id, secret_code):
    """
    Get file split task information, including parent task ID and child file information
    """
    url = "https://docflow.textin.ai/api/app-api/sip/platform/v2/file/fetch"

    headers = {
        "x-ti-app-id": app_id,
        "x-ti-secret-code": secret_code
    }

    params = {
        "workspace_id": workspace_id,
        "file_id": file_id
    }

    response = requests.get(url, headers=headers, params=params)
    data = response.json()

    files = data.get("result", {}).get("files", [])
    if files:
        file_data = files[0]
        task_id = file_data.get("task_id")
        task_type = file_data.get("task_type")
        child_files = file_data.get("child_files", [])

        # Extract child file information
        split_children = []
        for child in child_files:
            if child.get("task_type") == 0:  # Child files generated by file split
                split_children.append({
                    "task_id": child.get("task_id"),
                    "category": child.get("category"),
                    "pages": child.get("pages", {}).get("pages", []) if isinstance(child.get("pages"), dict) else child.get("pages", [])
                })

        return {
            "parent_task_id": task_id,
            "parent_task_type": task_type,
            "split_children": split_children
        }
    return None

# Usage example
WORKSPACE_ID = "1234567890"
FILE_ID = "202412190001"
APP_ID = "<your-app-id>"
SECRET_CODE = "<your-secret-code>"

task_info = get_split_task_info(WORKSPACE_ID, FILE_ID, APP_ID, SECRET_CODE)
if task_info:
    print("Parent task ID:", task_info["parent_task_id"])
    print("Parent task type:", task_info["parent_task_type"])
    print("Child file information:")
    for child in task_info["split_children"]:
        print(json.dumps(child, indent=2, ensure_ascii=False))