Fix: resolve regex library warnings (#7782)

### What problem does this PR solve?
This small PR resolves the regex library warnings showing in Python3.11:
```python
DeprecationWarning: 'count' is passed as positional argument
```

### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>

deepdoc/parser/resume/entities/corporations.py

@@ -53,14 +53,14 @@ def corpNorm(nm, add_region=True):
     nm = re.sub(r"&", "&", nm)
     nm = re.sub(r"[\(\)（）\+'\"\t \*\\【】-]+", " ", nm)
     nm = re.sub(
-        r"([—-]+.*| +co\..*|corp\..*| +inc\..*| +ltd.*)", "", nm, 10000, re.IGNORECASE
+        r"([—-]+.*| +co\..*|corp\..*| +inc\..*| +ltd.*)", "", nm, count=10000, flags=re.IGNORECASE
     )
     nm = re.sub(
         r"(计算机|技术|(技术|科技|网络)*有限公司|公司|有限|研发中心|中国|总部)$",
         "",
         nm,
-        10000,
-        re.IGNORECASE,
+        count=10000,
+        flags=re.IGNORECASE,
     )
     if not nm or (len(nm) < 5 and not regions.isName(nm[0:2])):
         return nm

deepdoc/parser/resume/step_two.py

@@ -51,7 +51,7 @@ PY = Pinyin()
 
 
 def rmHtmlTag(line):
-    return re.sub(r"<[a-z0-9.\"=';,:\+_/ -]+>", " ", line, 100000, re.IGNORECASE)
+    return re.sub(r"<[a-z0-9.\"=';,:\+_/ -]+>", " ", line, count=100000, flags=re.IGNORECASE)
 
 
 def highest_degree(dg):
@@ -507,7 +507,7 @@ def parse(cv):
                      (r".*国有.*", "国企"),
                      (r"[ （）\(\)人/·0-9-]+", ""),
                      (r".*(元|规模|于|=|北京|上海|至今|中国|工资|州|shanghai|强|餐饮|融资|职).*", "")]:
-            cv["corporation_type"] = re.sub(p, r, cv["corporation_type"], 1000, re.IGNORECASE)
+            cv["corporation_type"] = re.sub(p, r, cv["corporation_type"], count=1000, flags=re.IGNORECASE)
         if len(cv["corporation_type"]) < 2:
             del cv["corporation_type"]
 

rag/nlp/__init__.py

@@ -343,7 +343,7 @@ def remove_contents_table(sections, eng=False):
                                               type("")) else sections[i][0]).strip()
 
         if not re.match(r"(contents|目录|目次|table of contents|致谢|acknowledge)$",
-                        re.sub(r"( | |\u3000)+", "", get(i).split("@@")[0], re.IGNORECASE)):
+                        re.sub(r"( | |\u3000)+", "", get(i).split("@@")[0], flags=re.IGNORECASE)):
             i += 1
             continue
         sections.pop(i)