Skip to content

Adapt pymupf test suite to text extraction behaviour in MuPDF upcomin… #4704

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
julian-smith-artifex-com merged 1 commit into from
Sep 18, 2025
Merged

Adapt pymupf test suite to text extraction behaviour in MuPDF upcomin… #4704

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion tests/test_tables.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -184,7 +184,12 @@ def test_2979():
), f"{pymupdf.TOOLS.set_small_glyph_heights()=}"

wt = pymupdf.TOOLS.mupdf_warnings()
if pymupdf.mupdf_version_tuple >= (1, 26, 0):
if pymupdf.mupdf_version_tuple >= (1, 27, 0):
assert (
wt
== "bogus font ascent/descent values (3117 / -2463)\n... repeated 2 times...\nActualtext with no position. Text may be lost or mispositioned.\n... repeated 96 times..."
)
elif pymupdf.mupdf_version_tuple >= (1, 26, 0):
assert (
wt
== "bogus font ascent/descent values (3117 / -2463)\n... repeated 2 times..."
Expand Down
16 changes: 15 additions & 1 deletion tests/test_textextract.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -338,6 +338,11 @@ def test_3594():
for line in text.split('\n'):
print(f' {line!r}')
print('='*40)
wt = pymupdf.TOOLS.mupdf_warnings()
if pymupdf.mupdf_version_tuple < (1, 27):
assert not wt
else:
assert wt == 'Actualtext with no position. Text may be lost or mispositioned.\n... repeated 2 times...'


def test_3687():
Expand Down Expand Up @@ -885,6 +890,9 @@ def test_4546():

# This output is different from expected_1_23_5.
expected_mupdf_1_26_1 = b'JOB No.: Shipper (complete name and address) \xe5\x8f\x91\xe8\xb4\xa7\xe4\xba\xba(\xe5\x90\x8d\xe7\xa7\xb0\xe5\x8f\x8a\xe5\x9c\xb0\xe5\x9d\x80) Tel: Fax: \n \nS/O No. \xe6\x89\x98\xe8\xbf\x90\xe5\x8d\x95\xe5\x8f\xb7\xe7\xa0\x81 \nSINORICH TRANSPORT LIMITED \nSHIPPING ORDER \n\xe6\x89\x98\xe8\xbf\x90\xe5\x8d\x95 \n \xe5\xb8\x82\xe5\x9c\xba\xe9\x83\xa8: \n88570009 \n88577019 \n88'.decode()

# This output is different from either of the two expected strings.
expected_mupdf_1_27_0 = b'JOB No.: \n \nS/O No. \xe6\x89\x98\xe8\xbf\x90\xe5\x8d\x95\xe5\x8f\xb7\xe7\xa0\x81 \nSINORICH TRANSPORT LIMITED \nSHIPPING ORDER \n\xe6\x89\x98\xe8\xbf\x90\xe5\x8d\x95 \n \xe5\xb8\x82\xe5\x9c\xba\xe9\x83\xa8: \n88570009 \n88577019 \n88572702 \n \xe6\x93\x8d\xe4\xbd\x9c\xe9\x83\xa8: \n88570008 \n88570004 \n \xe6\x96\x87\xe4\xbb\xb6\xe9\x83\xa8: \n88570003\n \nNotify Party(complete name and address, '.decode()

print(f'expected_1_23_5\n{textwrap.indent(expected_1_23_5, " ")}')
print(f'expected_mupdf_1_26_1\n{textwrap.indent(expected_mupdf_1_26_1, " ")}')
Expand All @@ -894,10 +902,16 @@ def test_4546():
print(f'{text=}')
print(f'{text.encode()=}')

if pymupdf.mupdf_version_tuple >= (1, 26, 1):
wt = pymupdf.TOOLS.mupdf_warnings()
if pymupdf.mupdf_version_tuple >= (1, 27, 0):
assert text == expected_mupdf_1_27_0
assert wt == 'Actualtext with no position. Text may be lost or mispositioned.\n... repeated 120 times...'
elif pymupdf.mupdf_version_tuple >= (1, 26, 1):
assert text == expected_mupdf_1_26_1
assert not wt
else:
print(f'No expected output for {pymupdf.mupdf_version_tuple=}')
assert not wt


def test_4503():
Expand Down