mirror of
https://github.com/ocrmypdf/OCRmyPDF.git
synced 2026-05-05 21:27:37 -04:00
52 lines
1.4 KiB
Python
52 lines
1.4 KiB
Python
#!/usr/bin/env python3
|
|
# © 2017 James R. Barlow: github.com/jbarlow83
|
|
|
|
from subprocess import Popen, PIPE, check_output, check_call, DEVNULL
|
|
import os
|
|
import shutil
|
|
import pytest
|
|
from ocrmypdf.pdfinfo import PdfInfo, Colorspace, Encoding
|
|
import PyPDF2 as pypdf
|
|
from ocrmypdf.exceptions import ExitCode
|
|
from ocrmypdf import leptonica
|
|
from ocrmypdf.pdfa import file_claims_pdfa
|
|
from ocrmypdf.exec import ghostscript
|
|
import logging
|
|
from math import isclose
|
|
|
|
|
|
check_ocrmypdf = pytest.helpers.check_ocrmypdf
|
|
run_ocrmypdf = pytest.helpers.run_ocrmypdf
|
|
spoof = pytest.helpers.spoof
|
|
|
|
@pytest.fixture
|
|
def spoof_tesseract_noop():
|
|
return spoof(tesseract='tesseract_noop.py')
|
|
|
|
|
|
@pytest.fixture
|
|
def spoof_tesseract_cache():
|
|
if pytest.helpers.running_in_docker():
|
|
return os.environ.copy()
|
|
return spoof(tesseract="tesseract_cache.py")
|
|
|
|
|
|
@pytest.fixture
|
|
def poster(resources):
|
|
return resources / 'poster.pdf'
|
|
|
|
|
|
def test_userunit_ghostscript_fails(poster, no_outpdf):
|
|
p, out, err = run_ocrmypdf(poster, no_outpdf, '--output-type=pdfa')
|
|
assert p.returncode == ExitCode.input_file
|
|
|
|
|
|
def test_userunit_qpdf_passes(spoof_tesseract_cache, poster, outpdf):
|
|
before = PdfInfo(poster)
|
|
check_ocrmypdf(poster, outpdf, '--output-type=pdf',
|
|
env=spoof_tesseract_cache)
|
|
|
|
after = PdfInfo(outpdf)
|
|
assert isclose(before[0].width_inches, after[0].width_inches)
|
|
|