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

Fix typo in code (#8327)

Browse Source 
### What problem does this PR solve?

Fix typo in code

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2025-06-18 09:41:09 +08:00
committed by GitHub
parent 09b7ac26ad
commit 4a2ff633e0
15 changed files with 45 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
deepdoc/parser/pdf_parser.py
View File

@ -180,13 +180,13 @@ class RAGFlowPdfParser:
return fea
@staticmethod
def sort_X_by_page(arr, threashold):
def sort_X_by_page(arr, threshold):
# sort using y1 first and then x1
arr = sorted(arr, key=lambda r: (r["page_number"], r["x0"], r["top"]))
for i in range(len(arr) - 1):
for j in range(i, -1, -1):
# restore the order using th
if abs(arr[j + 1]["x0"] - arr[j]["x0"]) < threashold \
if abs(arr[j + 1]["x0"] - arr[j]["x0"]) < threshold \
and arr[j + 1]["top"] < arr[j]["top"] \
and arr[j + 1]["page_number"] == arr[j]["page_number"]:
tmp = arr[j]
@ -264,13 +264,13 @@ class RAGFlowPdfParser:
for b in self.boxes:
if b.get("layout_type", "") != "table":
continue
ii = Recognizer.find_overlapped_with_threashold(b, rows, thr=0.3)
ii = Recognizer.find_overlapped_with_threshold(b, rows, thr=0.3)
if ii is not None:
b["R"] = ii
b["R_top"] = rows[ii]["top"]
b["R_bott"] = rows[ii]["bottom"]
ii = Recognizer.find_overlapped_with_threashold(
ii = Recognizer.find_overlapped_with_threshold(
b, headers, thr=0.3)
if ii is not None:
b["H_top"] = headers[ii]["top"]
@ -285,7 +285,7 @@ class RAGFlowPdfParser:
b["C_left"] = clmns[ii]["x0"]
b["C_right"] = clmns[ii]["x1"]
ii = Recognizer.find_overlapped_with_threashold(b, spans, thr=0.3)
ii = Recognizer.find_overlapped_with_threshold(b, spans, thr=0.3)
if ii is not None:
b["H_top"] = spans[ii]["top"]
b["H_bott"] = spans[ii]["bottom"]