Add support for sidecar output to io.BytesIO

Closes #1252
This commit is contained in:
James R. Barlow
2024-04-07 01:38:55 -07:00
parent 0674829d8f
commit 7a8cc21e31
2 changed files with 19 additions and 1 deletions
+13
View File
@@ -29,6 +29,18 @@ def test_stream_api(resources: Path):
assert b'%PDF' in out.read(1024)
def test_sidecar_stringio(resources: Path, outdir: Path, outpdf: Path):
s = BytesIO()
ocrmypdf.ocr(
resources / 'ccitt.pdf',
outpdf,
plugins=['tests/plugins/tesseract_cache.py'],
sidecar=s
)
s.seek(0)
assert b'the' in s.getvalue()
def test_hocr_api_multipage(resources: Path, outdir: Path, outpdf: Path):
ocrmypdf.api._pdf_to_hocr(
resources / 'multipage.pdf',
@@ -62,3 +74,4 @@ def test_hocr_to_pdf_api(resources: Path, outdir: Path, outpdf: Path):
text = extract_text(outpdf)
assert 'hocr' in text and 'the' not in text