Bug fix pdf parse index out of range (#440)

### What problem does this PR solve?

fix a bug comes when parse some pdf file #436 

### Type of change

- [☑️ ] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
加帆 2024-04-19 08:44:51 +08:00 committed by GitHub
parent 1dada69daa
commit 39f1feaccb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -830,10 +830,13 @@ class HuParser:
pn = [bx["page_number"]]
top = bx["top"] - self.page_cum_height[pn[0] - 1]
bott = bx["bottom"] - self.page_cum_height[pn[0] - 1]
if pn[-1] - 1 >= len(self.page_images): return ""
page_images_cnt = len(self.page_images)
if pn[-1] - 1 >= page_images_cnt: return ""
while bott * ZM > self.page_images[pn[-1] - 1].size[1]:
bott -= self.page_images[pn[-1] - 1].size[1] / ZM
pn.append(pn[-1] + 1)
if pn[-1] - 1 >= page_images_cnt:
return ""
return "@@{}\t{:.1f}\t{:.1f}\t{:.1f}\t{:.1f}##" \
.format("-".join([str(p) for p in pn]),