Skip to content
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

Jump to bottom

[Fix] reduce memory consumption and close pdf stream after usage #164

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[Fix] reduce memory consumption and close pdf stream after usage #164

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7c869db
fix: flush cashe to reduce memory consumption
jakobnrmnn Dec 11, 2022
80f2651
fix: use as context manager so that pdf stream is closed afterwards
jakobnrmnn Dec 11, 2022
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
46 changes: 26 additions & 20 deletions src/layoutparser/io/pdf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,8 @@ def extract_words_for_page(
block_type="rectangle",
)

page.flush_cashe()

return page_tokens


Expand Down Expand Up @@ -181,26 +183,30 @@ def load_pdf(
plumber_pdf_object = pdfplumber.open(filename)

all_page_layout = []
for page_id in range(len(plumber_pdf_object.pages)):
cur_page = plumber_pdf_object.pages[page_id]

page_tokens = extract_words_for_page(
cur_page,
x_tolerance=x_tolerance,
y_tolerance=y_tolerance,
keep_blank_chars=keep_blank_chars,
use_text_flow=use_text_flow,
horizontal_ltr=horizontal_ltr,
vertical_ttb=vertical_ttb,
extra_attrs=extra_attrs,
)

# Adding metadata for the current page
page_tokens.page_data["width"] = float(cur_page.width)
page_tokens.page_data["height"] = float(cur_page.height)
page_tokens.page_data["index"] = page_id

all_page_layout.append(page_tokens)

with plumber_pdf_object:
for page_id in range(len(plumber_pdf_object.pages)):
cur_page = plumber_pdf_object.pages[page_id]

page_tokens = extract_words_for_page(
cur_page,
x_tolerance=x_tolerance,
y_tolerance=y_tolerance,
keep_blank_chars=keep_blank_chars,
use_text_flow=use_text_flow,
horizontal_ltr=horizontal_ltr,
vertical_ttb=vertical_ttb,
extra_attrs=extra_attrs,
)

# Adding metadata for the current page
page_tokens.page_data["width"] = float(cur_page.width)
page_tokens.page_data["height"] = float(cur_page.height)
page_tokens.page_data["index"] = page_id

all_page_layout.append(page_tokens)

plumber_pdf_object.flush_cashe()

if not load_images:
return all_page_layout
Expand Down