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

@ -27,7 +27,9 @@ 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,
@ -35,21 +37,24 @@ class Pdf(PdfParser):
to_page,
callback
)
callback(msg="OCR finished.")
callback(msg="OCR finished ({:.2f}s)".format(timer() - start))
from timeit import default_timer as timer
start = timer()
self._layouts_rec(zoomin)
callback(0.63, "Layout analysis finished")
callback(0.63, "Layout analysis ({:.2f}s)".format(timer() - start))
logging.debug(f"layouts cost: {timer() - start}s")
start = timer()
self._table_transformer_job(zoomin)
callback(0.68, "Table analysis finished")
callback(0.68, "Table analysis ({:.2f}s)".format(timer() - start))
start = timer()
self._text_merge()
tbls = self._extract_table_figure(True, zoomin, True, True)
column_width = np.median([b["x1"] - b["x0"] for b in self.boxes])
self._concat_downward()
self._filter_forpages()
callback(0.75, "Text merging finished.")
callback(0.75, "Text merged ({:.2f}s)".format(timer() - start))
# clean mess
if column_width < self.page_images[0].size[0] / zoomin / 2: