|
|
|
@ -1,59 +1,12 @@
|
|
|
|
|
import re
|
|
|
|
|
import subprocess
|
|
|
|
|
import os
|
|
|
|
|
import uuid
|
|
|
|
|
|
|
|
|
|
# 可执行文件路径
|
|
|
|
|
mtef = r'D:\dsWork\dsProject\dsRag\mtef-go-3\mtef-go.exe'
|
|
|
|
|
# docx文件路径
|
|
|
|
|
docx_file = 'D:\dsWork\dsProject\dsRag\static\Txt\化学方程式_CHEMISTRY_1.docx'
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# 结合Pandoc和mtef-go的结果,合并成最终的输出文本
|
|
|
|
|
def get_docx_content_by_pandoc(f, formula_list):
|
|
|
|
|
# StringBuilder结果
|
|
|
|
|
sb = []
|
|
|
|
|
# output_file 设置为临时目录下的uuid.md
|
|
|
|
|
temp_markdown = os.path.join(os.environ['TEMP'], uuid.uuid4().hex + '.md')
|
|
|
|
|
# 调用pandoc将docx文件转换成markdown
|
|
|
|
|
subprocess.run(['pandoc', f, '-f', 'docx', '-t', 'markdown', '-o', temp_markdown])
|
|
|
|
|
# 读取然后修改内容,输出到新的文件
|
|
|
|
|
idx = 0
|
|
|
|
|
with open(temp_markdown, 'r', encoding='utf-8') as f:
|
|
|
|
|
for line in f:
|
|
|
|
|
if line.strip():
|
|
|
|
|
# 改进后的正则表达式,匹配更多格式的MathType公式
|
|
|
|
|
if re.search(r'!\[]\(media/image\d+\.\w+\)', line) or \
|
|
|
|
|
re.search(r'\.!\[]\(media/image\d+\.\w+\)\.', line):
|
|
|
|
|
sb.append(formula_list[idx])
|
|
|
|
|
idx = idx + 1
|
|
|
|
|
else:
|
|
|
|
|
sb.append(line.strip())
|
|
|
|
|
|
|
|
|
|
# 删除临时文件 output_file
|
|
|
|
|
os.remove(temp_markdown)
|
|
|
|
|
return sb
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
# 获取MathType对应的Latex公式
|
|
|
|
|
def getLatexList(docx_file):
|
|
|
|
|
res = []
|
|
|
|
|
output = os.path.join(os.environ['TEMP'], uuid.uuid4().hex + '.txt')
|
|
|
|
|
command = mtef + r" -w " + docx_file + " -o " + output
|
|
|
|
|
os.system(command)
|
|
|
|
|
with open(output, 'r', encoding='utf-8') as file:
|
|
|
|
|
for i, line in enumerate(file):
|
|
|
|
|
res.append(line.strip())
|
|
|
|
|
return res
|
|
|
|
|
|
|
|
|
|
from Util.DocxUtil import *
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
|
# 一、获取Latex公式列表
|
|
|
|
|
formula_list = getLatexList(docx_file)
|
|
|
|
|
# docx文件路径
|
|
|
|
|
docx_file = 'D:\dsWork\dsProject\dsRag\static\Txt\化学方程式_CHEMISTRY_1.docx'
|
|
|
|
|
|
|
|
|
|
# 二、整合最终的拼接完的文本
|
|
|
|
|
sb = get_docx_content_by_pandoc(docx_file, formula_list)
|
|
|
|
|
# 整合最终的拼接完的文本
|
|
|
|
|
sb = get_docx_content_by_pandoc(docx_file)
|
|
|
|
|
|
|
|
|
|
# 三、输出
|
|
|
|
|
# 输出
|
|
|
|
|
for x in sb:
|
|
|
|
|
print(x)
|
|
|
|
|