mirror of
https://github.com/ocrmypdf/OCRmyPDF.git
synced 2026-02-07 21:03:59 -05:00
636623ab49
strip_invisible_text resets the text render mode on each `BT` (begin text) command. However the text state is not actually reset for each text element, only for each page. The pdf reference says: > The text state operators can appear outside text objects, and the values they set > are retained across text objects in a single content stream. Like other graphics > state parameters, these parameters are initialized to their default values at the > beginning of each page. > > -- https://opensource.adobe.com/dc-acrobat-sdk-docs/pdfstandards/pdfreference1.7old.pdf#page=397 With the current implementation, a text object is only deleted if it contains a `3 Tr` command (setting the text rendering mode to invalid). However the rendering mode may be set once and then not changed for multiple text objects or set outside of a text object. In that case only the first text object (which contains the `3 Tr`-command) is removed. This not only leaves the other text objects in the pdf, but also makes them visible, since the text object that contained the `3 Tr`-command is removed. This PR updates `strip_invisible_text` to not reset the rendering mode for each object and to keep track of the rendering mode when the graphic state is pushed/popped.
112 lines
3.8 KiB
Python
112 lines
3.8 KiB
Python
# SPDX-FileCopyrightText: 2022 James R. Barlow
|
|
# SPDX-License-Identifier: MPL-2.0
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import patch
|
|
|
|
import pikepdf
|
|
|
|
import ocrmypdf
|
|
|
|
|
|
def test_no_glyphless_graft(resources, outdir):
|
|
with (
|
|
pikepdf.open(resources / 'francais.pdf') as pdf,
|
|
pikepdf.open(resources / 'aspect.pdf') as pdf_aspect,
|
|
pikepdf.open(resources / 'cmyk.pdf') as pdf_cmyk,
|
|
):
|
|
pdf.pages.extend(pdf_aspect.pages)
|
|
pdf.pages.extend(pdf_cmyk.pages)
|
|
pdf.save(outdir / 'test.pdf')
|
|
|
|
with patch('ocrmypdf._graft.MAX_REPLACE_PAGES', 2):
|
|
ocrmypdf.ocr(
|
|
outdir / 'test.pdf',
|
|
outdir / 'out.pdf',
|
|
deskew=True,
|
|
tesseract_timeout=0,
|
|
force_ocr=True,
|
|
)
|
|
# This test needs asserts
|
|
|
|
|
|
def test_links(resources, outpdf):
|
|
ocrmypdf.ocr(
|
|
resources / 'link.pdf', outpdf, redo_ocr=True, oversample=200, output_type='pdf'
|
|
)
|
|
with pikepdf.open(outpdf) as pdf:
|
|
p1 = pdf.pages[0]
|
|
p2 = pdf.pages[1]
|
|
assert p1.Annots[0].A.D[0].objgen == p2.objgen
|
|
assert p2.Annots[0].A.D[0].objgen == p1.objgen
|
|
|
|
|
|
def test_strip_invisble_text():
|
|
pdf = pikepdf.Pdf.new()
|
|
print(pikepdf.parse_content_stream(pikepdf.Stream(pdf, b'3 Tr')))
|
|
page = pdf.add_blank_page()
|
|
visible_text = [
|
|
pikepdf.ContentStreamInstruction((), pikepdf.Operator('BT')),
|
|
pikepdf.ContentStreamInstruction(
|
|
(pikepdf.Name('/F0'), 12), pikepdf.Operator('Tf')
|
|
),
|
|
pikepdf.ContentStreamInstruction((288, 720), pikepdf.Operator('Td')),
|
|
pikepdf.ContentStreamInstruction(
|
|
(pikepdf.String('visible'),), pikepdf.Operator('Tj')
|
|
),
|
|
pikepdf.ContentStreamInstruction((), pikepdf.Operator('ET')),
|
|
]
|
|
invisible_text = [
|
|
pikepdf.ContentStreamInstruction((), pikepdf.Operator('BT')),
|
|
pikepdf.ContentStreamInstruction(
|
|
(pikepdf.Name('/F0'), 12), pikepdf.Operator('Tf')
|
|
),
|
|
pikepdf.ContentStreamInstruction((288, 720), pikepdf.Operator('Td')),
|
|
pikepdf.ContentStreamInstruction(
|
|
(pikepdf.String('invisible'),), pikepdf.Operator('Tj')
|
|
),
|
|
pikepdf.ContentStreamInstruction((), pikepdf.Operator('ET')),
|
|
]
|
|
invisible_text_setting_tr = [
|
|
pikepdf.ContentStreamInstruction((), pikepdf.Operator('BT')),
|
|
pikepdf.ContentStreamInstruction([3], pikepdf.Operator('Tr')),
|
|
pikepdf.ContentStreamInstruction(
|
|
(pikepdf.Name('/F0'), 12), pikepdf.Operator('Tf')
|
|
),
|
|
pikepdf.ContentStreamInstruction((288, 720), pikepdf.Operator('Td')),
|
|
pikepdf.ContentStreamInstruction(
|
|
(pikepdf.String('invisible'),), pikepdf.Operator('Tj')
|
|
),
|
|
pikepdf.ContentStreamInstruction((), pikepdf.Operator('ET')),
|
|
]
|
|
stream = [
|
|
pikepdf.ContentStreamInstruction([], pikepdf.Operator('q')),
|
|
pikepdf.ContentStreamInstruction([3], pikepdf.Operator('Tr')),
|
|
*invisible_text,
|
|
pikepdf.ContentStreamInstruction([], pikepdf.Operator('Q')),
|
|
*visible_text,
|
|
*invisible_text_setting_tr,
|
|
*invisible_text,
|
|
]
|
|
content_stream = pikepdf.unparse_content_stream(stream)
|
|
page.Contents = pikepdf.Stream(pdf, content_stream)
|
|
|
|
def count(string, page):
|
|
return len(
|
|
[
|
|
True
|
|
for operands, operator in pikepdf.parse_content_stream(page)
|
|
if operator == pikepdf.Operator('Tj')
|
|
and operands[0] == pikepdf.String(string)
|
|
]
|
|
)
|
|
|
|
nr_visible_pre = count('visible', page)
|
|
ocrmypdf._graft.strip_invisible_text(pdf, page)
|
|
nr_visible_post = count('visible', page)
|
|
assert (
|
|
nr_visible_pre == nr_visible_post
|
|
), 'Number of visible text elements did not change'
|
|
assert count('invisible', page) == 0, 'No invisible elems left'
|