11.13
This commit is contained in:
parent
59b7bed441
commit
6e7da080bc
@ -44,8 +44,8 @@ def parse_text_by_heading(text):
|
||||
skip_subheadings = False
|
||||
last_main_number = None
|
||||
temp_title = None # 临时存储以点号开头但不带数字的标题
|
||||
pattern_numbered = re.compile(r'^\s*([一二三四五六七八九十]{1,2})\s*、\s*')
|
||||
pattern_parentheses = re.compile(r'^\s*[((]\s*([一二三四五六七八九十]{1,2})\s*[))]\s*')
|
||||
pattern_numbered = re.compile(r'^\s*([一二三四五六七八九十]{1,2})\s*、\s*') #一、
|
||||
pattern_parentheses = re.compile(r'^\s*[((]\s*([一二三四五六七八九十]{1,2})\s*[))]\s*') #(一)
|
||||
initial_heading_pattern = None
|
||||
special_section_keywords = ['文件的组成', '文件的构成','文件包括:','文件包括:'] # 定义特殊章节关键词
|
||||
in_special_section = False # 标志是否在特殊章节中
|
||||
|
@ -36,12 +36,19 @@ def read_tables_from_docx(file_path):
|
||||
def preprocess_paragraphs(paragraphs):
|
||||
processed = [] # 初始化处理后的段落列表
|
||||
index = 0
|
||||
# 定义两个新的正则表达式模式
|
||||
pattern_numbered = re.compile(r'^\s*([一二三四五六七八九十]{1,2})\s*、\s*')
|
||||
pattern_parentheses = re.compile(r'^\s*[((]\s*([一二三四五六七八九十]{1,2})\s*[))]\s*')
|
||||
#排除遇到表格、填空的情况
|
||||
def has_long_spaces(text, max_space_count=5):
|
||||
return any(len(space) > max_space_count for space in re.findall(r'\s+', text))
|
||||
while index < len(paragraphs):
|
||||
current_text = paragraphs[index].text.strip() # 去除当前段落的前后空白
|
||||
|
||||
# 检查当前段落是否匹配任一排除模式
|
||||
if pattern_numbered.match(current_text) or pattern_parentheses.match(current_text):
|
||||
# 如果匹配,则跳过当前段落,不添加到processed列表中
|
||||
index += 1
|
||||
continue
|
||||
# 检查当前段落是否为空
|
||||
if current_text == '':
|
||||
# 确保有前一个和后一个段落
|
||||
|
@ -100,6 +100,7 @@ def handle_query(file_path, user_query, output_file, result_key, keywords):
|
||||
print(f"handle_query 在处理 {result_key} 时发生异常: {e}")
|
||||
return {result_key: ""}
|
||||
|
||||
#TODO:增加提取逻辑 else里面的内容
|
||||
def combine_find_invalid(file_path, output_folder, qualification):
|
||||
os.makedirs(output_folder, exist_ok=True)
|
||||
queries = [
|
||||
|
@ -136,7 +136,7 @@ def merge_pdfs(paths, output_filename):
|
||||
return output_path
|
||||
|
||||
|
||||
def find_forbidden(truncate_json_path, clause_path, qualification=""):
|
||||
def find_forbidden(qualification=""):
|
||||
try:
|
||||
if qualification:
|
||||
file_id = upload_file(qualification)
|
||||
|
Loading…
x
Reference in New Issue
Block a user