pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-08 20:42:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
### 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)
This commit is contained in:
Zhichang Yu
2024-11-28 13:00:38 +08:00
committed by GitHub
parent 9f57534843
commit bc701d7b4c
19 changed files with 51 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
deepdoc/parser/pdf_parser.py
View File

@ -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