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

Update progress info and start welcome info (#3768)

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

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### Type of change

- [x] Refactoring

---------

Signed-off-by: jinhai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2024-11-30 18:48:06 +08:00
committed by GitHub
parent d00297a763
commit e079656473
11 changed files with 107 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
rag/app/manual.py
View File

@ -36,7 +36,7 @@ class Pdf(PdfParser):
to_page=100000, zoomin=3, callback=None):
from timeit import default_timer as timer
start = timer()
callback(msg="OCR is running...")
callback(msg="OCR started")
self.__images__(
filename if not binary else binary,
zoomin,
@ -44,22 +44,27 @@ class Pdf(PdfParser):
to_page,
callback
)
callback(msg="OCR finished.")
callback(msg="OCR finished ({:.2f}s)".format(timer() - start))
# for bb in self.boxes:
# for b in bb:
# print(b)
logging.debug("OCR: {}".format(timer() - start))
start = timer()
self._layouts_rec(zoomin)
callback(0.65, "Layout analysis finished.")
callback(0.65, "Layout analysis ({:.2f}s)".format(timer() - start))
logging.debug("layouts: {}".format(timer() - start))
start = timer()
self._table_transformer_job(zoomin)
callback(0.67, "Table analysis finished.")
callback(0.67, "Table analysis ({:.2f}s)".format(timer() - start))
start = timer()
self._text_merge()
tbls = self._extract_table_figure(True, zoomin, True, True)
self._concat_downward()
self._filter_forpages()
callback(0.68, "Text merging finished")
callback(0.68, "Text merged ({:.2f}s)".format(timer() - start))
# clean mess
for b in self.boxes: