Update progress info and start welcome info (#3768)

### 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

View File

@ -59,11 +59,12 @@ class Pdf(PdfParser):
def __call__(self, filename, binary=None, from_page=0,
to_page=100000, zoomin=3, callback=None):
callback(msg="OCR is running...")
from timeit import default_timer as timer
start = timer()
callback(msg="OCR started")
self.__images__(filename if not binary else binary,
zoomin, from_page, to_page, callback)
callback(0.8, "Page {}~{}: OCR finished".format(
from_page, min(to_page, self.total_page)))
callback(msg="Page {}~{}: OCR finished ({:.2f}s)".format(from_page, min(to_page, self.total_page), timer() - start))
assert len(self.boxes) == len(self.page_images), "{} vs. {}".format(
len(self.boxes), len(self.page_images))
res = []