Edit chunk shall update instead of insert it (#3709)

### What problem does this PR solve?

Edit chunk shall update instead of insert it. Close #3679 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

deepdoc/parser/docx_parser.py

@@ -47,7 +47,7 @@ class RAGFlowDocxParser:
             for p, n in patt:
                 if re.search(p, b):
                     return n
-            tks = [t for t in rag_tokenizer.tokenize(b).split(" ") if len(t) > 1]
+            tks = [t for t in rag_tokenizer.tokenize(b).split() if len(t) > 1]
             if len(tks) > 3:
                 if len(tks) < 12:
                     return "Tx"

deepdoc/parser/pdf_parser.py

@@ -108,13 +108,13 @@ class RAGFlowPdfParser:
         h = max(self.__height(up), self.__height(down))
         y_dis = self._y_dis(up, down)
         LEN = 6
-        tks_down = rag_tokenizer.tokenize(down["text"][:LEN]).split(" ")
-        tks_up = rag_tokenizer.tokenize(up["text"][-LEN:]).split(" ")
+        tks_down = rag_tokenizer.tokenize(down["text"][:LEN]).split()
+        tks_up = rag_tokenizer.tokenize(up["text"][-LEN:]).split()
         tks_all = up["text"][-LEN:].strip() \
                   + (" " if re.match(r"[a-zA-Z0-9]+",
                                      up["text"][-1] + down["text"][0]) else "") \
                   + down["text"][:LEN].strip()
-        tks_all = rag_tokenizer.tokenize(tks_all).split(" ")
+        tks_all = rag_tokenizer.tokenize(tks_all).split()
         fea = [
             up.get("R", -1) == down.get("R", -1),
             y_dis / h,
@@ -565,13 +565,13 @@ class RAGFlowPdfParser:
             if i >= len(self.boxes):
                 break
             prefix = self.boxes[i]["text"].strip()[:3] if not eng else " ".join(
-                self.boxes[i]["text"].strip().split(" ")[:2])
+                self.boxes[i]["text"].strip().split()[:2])
             while not prefix:
                 self.boxes.pop(i)
                 if i >= len(self.boxes):
                     break
                 prefix = self.boxes[i]["text"].strip()[:3] if not eng else " ".join(
-                    self.boxes[i]["text"].strip().split(" ")[:2])
+                    self.boxes[i]["text"].strip().split()[:2])
             self.boxes.pop(i)
             if i >= len(self.boxes) or not prefix:
                 break

deepdoc/parser/resume/entities/corporations.py

@@ -47,7 +47,7 @@ def corpNorm(nm, add_region=True):
     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)
     if not nm or (len(nm)<5 and not regions.isName(nm[0:2])):return nm
 
-    tks = rag_tokenizer.tokenize(nm).split(" ")
+    tks = rag_tokenizer.tokenize(nm).split()
     reg = [t for i,t in enumerate(tks) if regions.isName(t) and (t != "中国" or i > 0)]
     nm = ""
     for t in tks:

deepdoc/parser/resume/entities/schools.py

@@ -44,7 +44,7 @@ loadRank(os.path.join(current_file_path, "res/school.rank.csv"))
 
 def split(txt):
     tks = []
-    for t in re.sub(r"[ \t]+", " ",txt).split(" "):
+    for t in re.sub(r"[ \t]+", " ",txt).split():
         if tks and re.match(r".*[a-zA-Z]$", tks[-1]) and \
            re.match(r"[a-zA-Z]", t) and tks:
             tks[-1] = tks[-1] + " " + t

deepdoc/parser/resume/step_one.py

@@ -80,7 +80,7 @@ def refactor(df):
     def loadjson(line):
         try:
             return json.loads(line)
-        except Exception as e:
+        except Exception:
             pass
         return {}
 
@@ -183,4 +183,4 @@ def refactor(df):
                 "\r",
                 "\\n"))
     # print(df.values.tolist())
-    return dict(zip([n.split(" ")[0] for n in FIELDS], df.values.tolist()[0]))
+    return dict(zip([n.split()[0] for n in FIELDS], df.values.tolist()[0]))

deepdoc/parser/resume/step_two.py

@@ -100,7 +100,7 @@ def forEdu(cv):
         if n.get("school_name") and isinstance(n["school_name"], str):
             sch.append(re.sub(r"(211|985|重点大学|[,&;；-])", "", n["school_name"]))
             e["sch_nm_kwd"] = sch[-1]
-        fea.append(rag_tokenizer.fine_grained_tokenize(rag_tokenizer.tokenize(n.get("school_name", ""))).split(" ")[-1])
+        fea.append(rag_tokenizer.fine_grained_tokenize(rag_tokenizer.tokenize(n.get("school_name", ""))).split()[-1])
 
         if n.get("discipline_name") and isinstance(n["discipline_name"], str):
             maj.append(n["discipline_name"])
@@ -485,7 +485,7 @@ def parse(cv):
         nm = re.sub(r"[\n——\-\(（\+].*", "", cv["name"].strip())
         nm = re.sub(r"[ \t　]+", " ", nm)
         if re.match(r"[a-zA-Z ]+$", nm):
-            if len(nm.split(" ")) > 1:
+            if len(nm.split()) > 1:
                 cv["name"] = nm
             else:
                 nm = ""
@@ -503,7 +503,7 @@ def parse(cv):
         for py in PY.get_pinyins(nm[:20], ''):
             for i in range(2, len(py) + 1): cv["name_py_pref_tks"] += " " + py[:i]
         for py in PY.get_pinyins(nm[:20], ' '):
-            py = py.split(" ")
+            py = py.split()
             for i in range(1, len(py) + 1): cv["name_py_pref0_tks"] += " " + "".join(py[:i])
 
         cv["name_kwd"] = name