feat: 避免段落空格影响检测结果

2023-08-24 20:06:54 +08:00 · 2023-08-24 20:06:54 +08:00 · 0ee978ba4e
parent 1ddb4e83dd
commit 0ee978ba4e
1 changed files with 1 additions and 0 deletions
--- a/retriever/tools/keyword_find.py
+++ b/retriever/tools/keyword_find.py
@ -29,6 +29,7 @@ def docx_find(file_path: str, keyword_list: list) -> dict:
    paragraph_keyword = []

    for para in doc_text.split('\n'):
+        para = re.sub(r'\s+', '', para)  # 删除段落中空格
        this_para_keyword = [keyword for keyword in keyword_list if keyword in para]  # 查找该段落中的敏感词

        if this_para_keyword: