mirror of
https://github.com/ocrmypdf/OCRmyPDF.git
synced 2026-07-30 23:17:52 -04:00
089f46690a
Replaces os.path/open()/os.stat()/os.chmod() calls with their Path method equivalents across src, tests, misc, and bin, wrapping str variables in Path(...) where they must stay str for other uses (e.g. subprocess argv, CLI-arg formatting). helpers.safe_symlink() now decodes StrOrBytesPath to a str Path via os.fsdecode() upfront, same pattern already used elsewhere for the str|bytes union.
58 lines
1.4 KiB
Python
58 lines
1.4 KiB
Python
# SPDX-FileCopyrightText: 2025 James R. Barlow
|
|
# SPDX-License-Identifier: MPL-2.0
|
|
|
|
"""Compare text in PDFs."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from pathlib import Path
|
|
from subprocess import run
|
|
from tempfile import NamedTemporaryFile
|
|
from typing import Annotated
|
|
|
|
import cyclopts
|
|
|
|
app = cyclopts.App()
|
|
|
|
|
|
@app.default
|
|
def main(
|
|
pdf1: Annotated[Path, cyclopts.Parameter()],
|
|
pdf2: Annotated[Path, cyclopts.Parameter()],
|
|
*,
|
|
engine: Annotated[str, cyclopts.Parameter()] = 'pdftotext',
|
|
):
|
|
"""Compare text in PDFs."""
|
|
with pdf1.open('rb') as f1, pdf2.open('rb') as f2:
|
|
text1 = run(
|
|
['pdftotext', '-layout', '-', '-'],
|
|
stdin=f1,
|
|
capture_output=True,
|
|
check=True,
|
|
)
|
|
text2 = run(
|
|
['pdftotext', '-layout', '-', '-'],
|
|
stdin=f2,
|
|
capture_output=True,
|
|
check=True,
|
|
)
|
|
|
|
with NamedTemporaryFile() as t1, NamedTemporaryFile() as t2:
|
|
t1.write(text1.stdout)
|
|
t1.flush()
|
|
t2.write(text2.stdout)
|
|
t2.flush()
|
|
diff = run(
|
|
['diff', '--color=always', '--side-by-side', t1.name, t2.name],
|
|
capture_output=True,
|
|
)
|
|
run(['less', '-R'], input=diff.stdout, check=True)
|
|
if text1.stdout.strip() != text2.stdout.strip():
|
|
return 1
|
|
|
|
return 0
|
|
|
|
|
|
if __name__ == '__main__':
|
|
app()
|