Skip to content

perf: pdfminer to fitz in convert#630 #685

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
thinklab wants to merge 7 commits into
base: main
Choose a base branch
from
Open

perf: pdfminer to fitz in convert#630 #685

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
120800c
Update pdf_converter.py
Jun 8, 2023
09327be
Update poetry.lock
Jun 8, 2023
b6bc3cf
Update pyproject.toml
Jun 8, 2023
52815fd
skip typing erros
Jun 8, 2023
9a38365
remove unused package, switch to new badgerdoc converter, add test
Jun 8, 2023
2b3e77a
fix end of file
Jun 8, 2023
c792c09
fix tests
Jun 9, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 52 additions & 1 deletion convert/convert/converters/pdf/pdf_converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
from pathlib import Path
from typing import List, Optional, Tuple, Union
from typing import List, Optional

import fitz
from pdfminer.high_level import extract_pages
from pdfminer.layout import (
LTAnno,
Expand Down Expand Up @@ -101,3 +102,53 @@ def _create_neighbor_bbox(self, current_bbox: Bbox) -> Bbox:
new_x0, new_y0 = x1, y0
new_x1, new_y1 = (x1 - x0) + x1, y1
return new_x0, new_y0, new_x1, new_y1


class PlainPDFToBadgerdocTokensConverterPytz:
Copy link
Collaborator

@serereg serereg Jun 14, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As I understand it is needed to replase PlainPDFToBadgerdocTokensConverter class by this one

def __init__(self) -> None:
self.offset = 0
self.page_size: Optional[PageSize] = None

def _convert_span(self, span): # type: ignore
Copy link
Collaborator

@serereg serereg Jun 14, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It is necessary to remove all type ignores. In order to simplify the process of determining types, you can add a breakpoint here and in debug mode, find out the type of this variable.

tokens = []
for char in span.get("chars"):
token = BadgerdocToken(
bbox=char.get("bbox"),
text=char.get("c"),
offset=Offset(begin=self.offset, end=self.offset + 1),
)
tokens.append(token)
self.offset += 1
return tokens

def _convert_line(self, line): # type: ignore
tokens = []
for span in line.get("spans"):
tokens.extend(self._convert_span(span)) # type: ignore
return tokens

def _convert_element(self, element): # type: ignore
tokens = []
for line in element.get("lines"):
tokens.extend(self._convert_line(line)) # type: ignore
return tokens

def _convert_page(self, page): # type: ignore
tokens = []
text = page.get_textpage().extractDICT()
self.page_size = PageSize(
width=text.get("width"), height=text.get("height")
)
for block in page.get_textpage().extractRAWDICT().get("blocks"):
tokens.extend(self._convert_element(block)) # type: ignore
return tokens

def convert(self, plain_pdf: Path) -> List[Page]:
pages = []
with fitz.Document(plain_pdf) as doc:
for i, page in enumerate(doc.pages(), start=1):
objs = self._convert_page(page) # type: ignore
if not self.page_size:
continue
pages.append(Page(page_num=i, objs=objs, size=self.page_size))
return pages
4 changes: 2 additions & 2 deletions convert/convert/converters/pdf/pdf_to_badgerdoc_converter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@

from convert.converters.base_format.badgerdoc import Badgerdoc
from convert.converters.pdf.pdf_converter import (
PlainPDFToBadgerdocTokensConverter,
PlainPDFToBadgerdocTokensConverterPytz,
)
from convert.models.common import S3Path

Expand Down Expand Up @@ -35,7 +35,7 @@ def download_pdf_from_s3(self, s3_input_pdf: S3Path) -> None:
s3_input_pdf.bucket, s3_input_pdf.path, input_file
)
self.badgerdoc_format.tokens_pages = (
PlainPDFToBadgerdocTokensConverter().convert(input_file)
PlainPDFToBadgerdocTokensConverterPytz().convert(input_file)
)

def upload_badgerdoc_to_s3(self, s3_output_tokens: S3Path) -> None:
Expand Down
Loading