menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

test: Add a basic redo OCR test

Browse Source
This commit is contained in:
James R. Barlow
2018-11-04 15:54:41 -08:00
parent 2125b5bfab
commit 2ac028c759
1 changed files with 12 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test_main.py
+12 -1
View File
@@ -190,11 +190,22 @@ def test_force_ocr(spoof_tesseract_cache, resources, outpdf):
def test_skip_ocr(spoof_tesseract_cache, resources, outpdf):
out = check_ocrmypdf(resources / 'graph_ocred.pdf', outpdf, '-s',
env=spoof_tesseract_cache)
env=spoof_tesseract_cache)
pdfinfo = PdfInfo(out)
assert pdfinfo[0].has_text
def test_redo_ocr(spoof_tesseract_cache, resources, outpdf):
in_ = resources / 'graph_ocred.pdf'
before = PdfInfo(in_, detailed_page_analysis=True)
out = check_ocrmypdf(in_, outpdf, '--redo-ocr',
env=spoof_tesseract_cache)
after = PdfInfo(out, detailed_page_analysis=True)
assert before[0].has_text and after[0].has_text
assert before[0].get_textareas() != after[0].get_textareas(), \
"Expected text to be different after re-OCR"
def test_argsfile(spoof_tesseract_noop, resources, outdir):
path_argsfile = outdir / 'test_argsfile.txt'
with open(str(path_argsfile), 'w') as argsfile: