# -*- coding:utf-8 -*-
'''
anslysis_doc.py

功能：解析doc文件中xml段落的個數
步驟：
'''

import os
import re
from docx import Document


def get_xml_count(path):
    '''
    :param path: doc文件的絕對路徑
    :return: 返回doc文件中XML段落的個數
    '''

    # print('doc檔案： %s' %path)
    doc = Document(path)
    count = 0
    flag = True
    
 
for paragraph in doc.paragraphs:
        # print(paragraph.text)
        if flag:
            regex = re.match(r'^<[A-Z]+>$', paragraph.text)   # 首次匹配到XML的標籤，eg:<ACL>
            if regex:
                value = regex.group(0)   # 獲取標籤內容
                flag = False
                count 
 
+= 1
        elif re.match(value, paragraph.text):        # 以首次獲取的標籤內容對剩下段落做正則匹配
            count += 1
    return count


if __name__ == '__main__':
    path_dir = 'D:\\workspace_py\\FILES'
    sum = 0
    for file in os.listdir(path_dir):
        path = path_dir + '/' + file
        count = get_xml_count(path)
        
 
print('%s檔案中，符合條件XML個數： %s' % (path, count))
        sum += count
    print('總的符合條件XML個數：%s' % sum)


# path = 'D:\\workspace_py\\FILES\\Comware ACL NETCONF XML API Action Reference.docx'
# count = get_xml_count(path)
# print(count)