Skip to content

Add page_indexes parameter to transform functions #325

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

Add page_indexes parameter to transform functions #325

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a20de28
support page index
HuSharp Jan 7, 2026
f9dd20c
address comments
HuSharp Jan 7, 2026
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
4 changes: 4 additions & 0 deletions pdf_craft/functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,7 @@ def transform_markdown(
max_ocr_tokens: int | None = None,
max_ocr_output_tokens: int | None = None,
on_ocr_event: Callable[[OCREvent], None] = lambda _: None,
page_indexes: range | None = None,
) -> OCRTokensMetering:

return Transform(
Expand All @@ -67,6 +68,7 @@ def transform_markdown(
max_ocr_tokens=max_ocr_tokens,
max_ocr_output_tokens=max_ocr_output_tokens,
on_ocr_event=on_ocr_event,
page_indexes=page_indexes,
)


Expand Down Expand Up @@ -95,6 +97,7 @@ def transform_epub(
max_ocr_tokens: int | None = None,
max_ocr_output_tokens: int | None = None,
on_ocr_event: Callable[[OCREvent], None] = lambda _: None,
page_indexes: range | None = None,
) -> OCRTokensMetering:

return Transform(
Expand Down Expand Up @@ -123,4 +126,5 @@ def transform_epub(
max_ocr_tokens=max_ocr_tokens,
max_ocr_output_tokens=max_ocr_output_tokens,
on_ocr_event=on_ocr_event,
page_indexes=page_indexes,
)
41 changes: 25 additions & 16 deletions pdf_craft/transform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,7 @@ def transform_markdown(
max_ocr_tokens: int | None = None,
max_ocr_output_tokens: int | None = None,
on_ocr_event: Callable[[OCREvent], None] = lambda _: None,
page_indexes: range | None = None,
) -> OCRTokensMetering: # pyright: ignore[reportReturnType]

if markdown_assets_path is None:
Expand All @@ -81,6 +82,7 @@ def transform_markdown(
max_tokens=max_ocr_tokens,
max_output_tokens=max_ocr_output_tokens,
on_ocr_event=on_ocr_event,
page_indexes=page_indexes,
)
render_markdown_file(
chapters_path=chapters_path,
Expand Down Expand Up @@ -124,6 +126,7 @@ def transform_epub(
max_ocr_tokens: int | None = None,
max_ocr_output_tokens: int | None = None,
on_ocr_event: Callable[[OCREvent], None] = lambda _: None,
page_indexes: range | None = None,
) -> OCRTokensMetering: # pyright: ignore[reportReturnType]
try:
with EnsureFolder(
Expand All @@ -146,6 +149,7 @@ def transform_epub(
max_tokens=max_ocr_tokens,
max_output_tokens=max_ocr_output_tokens,
on_ocr_event=on_ocr_event,
page_indexes=page_indexes,
)
book_meta = book_meta or self._extract_book_meta(pdf_path)

Expand Down Expand Up @@ -190,6 +194,7 @@ def _extract_from_pdf(
max_tokens: int | None,
max_output_tokens: int | None,
on_ocr_event: Callable[[OCREvent], None],
page_indexes: range | None = None,
):

asserts_path = analysing_path / "assets"
Expand All @@ -208,22 +213,26 @@ def _extract_from_pdf(
input_tokens=0,
output_tokens=0,
)
for event in self._ocr.recognize(
pdf_path=pdf_path,
asset_path=asserts_path,
ocr_path=pages_path,
ocr_size=ocr_size,
dpi=dpi,
max_page_image_file_size=max_page_image_file_size,
includes_footnotes=includes_footnotes,
ignore_pdf_errors=ignore_pdf_errors,
ignore_ocr_errors=ignore_ocr_errors,
plot_path=plot_path,
cover_path=cover_path,
aborted=aborted,
max_tokens=max_tokens,
max_output_tokens=max_output_tokens,
):
recognize_kwargs = {
"pdf_path": pdf_path,
"asset_path": asserts_path,
"ocr_path": pages_path,
"ocr_size": ocr_size,
"dpi": dpi,
"max_page_image_file_size": max_page_image_file_size,
"includes_footnotes": includes_footnotes,
"ignore_pdf_errors": ignore_pdf_errors,
"ignore_ocr_errors": ignore_ocr_errors,
"plot_path": plot_path,
"cover_path": cover_path,
"aborted": aborted,
"max_tokens": max_tokens,
"max_output_tokens": max_output_tokens,
}
if page_indexes is not None:
recognize_kwargs["page_indexes"] = page_indexes

for event in self._ocr.recognize(**recognize_kwargs):
on_ocr_event(event)
metering.input_tokens += event.input_tokens
metering.output_tokens += event.output_tokens
Expand Down