python/python-pypandoc
SHA256
14
0
Fork 0
forked from pool/python-pypandoc
Code Pull Requests Activity

Accepting request 1088924 from devel:languages:python

Browse Source 
- Updating to upstream version 1.11 (as previous 1.6.4 fails)
  * tests.py was also updated and needed another item excluded to
    possibly account for how pandoc is built.
- Converting to noarch (per rpmlint).
- Adding pandocfilters module to BuildRequires

OBS-URL: https://build.opensuse.org/request/show/1088924
OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/python-pypandoc?expand=0&rev=7
This commit is contained in:
Dominique Leuenberger
2023-05-25 21:52:23 +00:00
committed by Git OBS Bridge
parent 88a3e1f7aa 2895fe3c8f
commit 38f2df4f4f
5 changed files with 298 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
pypandoc-1.11.tar.gz Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fab24b0c4e437a3982820171ad7a3b0125cd05a02ec4578bef243bf239c6d633
size 69118

3
pypandoc-1.6.4.tar.gz
View File

@@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9184c512c5aef9fb8eeb6ea3f22446f067eb44ab924f7372475e49b6f283006b
size 36386

9
python-pypandoc.changes
View File

@@ -1,3 +1,12 @@
-------------------------------------------------------------------
Wed May 24 17:47:42 UTC 2023 - Scott Bradnick <scott.bradnick@suse.com>
- Updating to upstream version 1.11 (as previous 1.6.4 fails)
* tests.py was also updated and needed another item excluded to
possibly account for how pandoc is built.
- Converting to noarch (per rpmlint).
- Adding pandocfilters module to BuildRequires
-------------------------------------------------------------------
Sun Jul 17 01:20:53 UTC 2022 - John Vandenberg <jayvdb@gmail.com>

16
python-pypandoc.spec
View File

@@ -1,7 +1,7 @@
#
# spec file for package python-pypandoc
#
# Copyright (c) 2022 SUSE LLC
# Copyright (c) 2023 SUSE LLC
#
# All modifications and additions to the file contributed by third parties
# remain the property of their copyright owners, unless otherwise agreed
@@ -16,9 +16,9 @@
#
%{?!python_module:%define python_module() python-%{**} python3-%{**}}
%define base_name pypandoc
Name: python-pypandoc
Version: 1.6.4
Version: 1.11
Release: 0
Summary: Thin wrapper for pandoc
License: MIT
@@ -26,6 +26,7 @@ Group: Development/Languages/Python
URL: https://github.com/bebraw/pypandoc
Source: https://github.com/NicklasTegner/pypandoc/archive/refs/tags/v%{version}.tar.gz#/pypandoc-%{version}.tar.gz
Source1: https://raw.githubusercontent.com/NicklasTegner/pypandoc/master/tests.py
BuildRequires: %{python_module pandocfilters}
BuildRequires: %{python_module pip}
BuildRequires: %{python_module pytest}
BuildRequires: %{python_module setuptools}
@@ -40,6 +41,7 @@ Requires: python-pip
Requires: python-wheel
Suggests: ghc-citeproc
ExcludeArch: %{ix86}
BuildArch: noarch
%python_subpackages
%description
@@ -58,12 +60,14 @@ cp %{SOURCE1} tests.py
%python_expand %fdupes %{buildroot}%{$python_sitelib}
%check
# test_basic_conversion_from_http_url needs network
%pytest tests.py -k 'not test_basic_conversion_from_http_url'
# 'test_basic_conversion_from_http_url' needs network
# 'test_conversion_with_data_files' => https://github.com/JessicaTegner/pypandoc/issues/278
%pytest tests.py -k 'not test_basic_conversion_from_http_url and not test_conversion_with_data_files'
%files %{python_files}
%license LICENSE
%doc README.md
%{python_sitelib}/*
%{python_sitelib}/pypandoc
%{python_sitelib}/pypandoc-%{version}*-info
%changelog

285
tests.py
View File

@@ -3,18 +3,33 @@
import contextlib
import io
import logging
import os
import re
import shutil
import subprocess
import sys
import tempfile
import textwrap
import unittest
import warnings
from pathlib import Path
import pypandoc
from pypandoc.py3compat import path2url, string_types, unicode_type
@contextlib.contextmanager
def capture(command, *args, **kwargs):
err, sys.stderr = sys.stderr, io.StringIO()
try:
command(*args, **kwargs)
sys.stderr.seek(0)
yield sys.stderr.read()
finally:
sys.stderr = err
@contextlib.contextmanager
def closed_tempfile(suffix, text=None, dir_name=None):
file_name = None
@@ -142,8 +157,19 @@ class TestPypandoc(unittest.TestCase):
version = pypandoc.get_pandoc_version()
self.assertTrue(isinstance(version, pypandoc.string_types))
major = int(version.split(".")[0])
# according to http://pandoc.org/releases.html there were only two versions 0.x ...
self.assertTrue(major in [0, 1, 2])
self.assertTrue(major in [0, 1, 2, 3])
def test_ensure_pandoc_minimal_version(self):
assert "HOME" in os.environ, "No HOME set, this will error..."
assert pypandoc.ensure_pandoc_minimal_version(1) == True
assert pypandoc.ensure_pandoc_minimal_version(1,1) == True
assert pypandoc.ensure_pandoc_minimal_version(999,999) == False
def test_ensure_pandoc_maximal_version(self):
assert "HOME" in os.environ, "No HOME set, this will error..."
assert pypandoc.ensure_pandoc_maximal_version(999) == True
assert pypandoc.ensure_pandoc_maximal_version(999,999) == True
assert pypandoc.ensure_pandoc_maximal_version(1,1) == False
def test_converts_valid_format(self):
self.assertEqualExceptForNewlineEnd(pypandoc.convert_text("ok", format='md', to='rest'), 'ok')
@@ -168,6 +194,25 @@ class TestPypandoc(unittest.TestCase):
received = pypandoc.convert_file(file_name, 'rst')
self.assertEqualExceptForNewlineEnd(expected, received)
def test_basic_conversion_from_multiple_files(self):
with closed_tempfile('.md', text='some title') as file_name1:
with closed_tempfile('.md', text='some title') as file_name2:
expected = '<p>some title</p>\n<p>some title</p>'
received = pypandoc.convert_file([file_name1,file_name2], 'html')
self.assertEqualExceptForNewlineEnd(expected, received)
def test_basic_conversion_from_file_pattern(self):
received = pypandoc.convert_file("./*.md", 'html')
received = received.lower()
assert "making a release" in received
assert "pypandoc provides a thin wrapper" in received
def test_basic_conversion_from_file_pattern_with_input_list(self):
received = pypandoc.convert_file(["./*.md", "./*.md"], 'html')
received = received.lower()
assert "making a release" in received
assert "pypandoc provides a thin wrapper" in received
@unittest.skipIf(sys.platform.startswith("win"), "File based urls do not work on windows: "
"https://github.com/jgm/pandoc/issues/4613")
def test_basic_conversion_from_file_url(self):
@@ -186,7 +231,27 @@ class TestPypandoc(unittest.TestCase):
received = pypandoc.convert_file(url, 'html')
assert "GPL2 license" in received
def test_conversion_with_data_files(self):
# remove our test.docx file from our test_data dir if it already exosts
test_data_dir = os.path.join(os.path.dirname(__file__), 'test_data')
test_docx_file = os.path.join(test_data_dir, 'test.docx')
if os.path.exists(test_docx_file):
os.remove(test_docx_file)
result = pypandoc.convert_file(
os.path.join(test_data_dir, 'index.html'),
to='docx',
format='html',
outputfile=test_docx_file,
sandbox=True,
)
print(result)
def test_convert_with_custom_writer(self):
version = pypandoc.get_pandoc_version()
major = int(version.split(".")[0])
if major == 3:
# apparently --print-default-data-file fails on pandoc3x
return
lua_file_content = self.create_sample_lua()
with closed_tempfile('.md', text='# title\n') as file_name:
with closed_tempfile('.lua', text=lua_file_content, dir_name="foo-bar+baz") as lua_file_name:
@@ -262,6 +327,176 @@ class TestPypandoc(unittest.TestCase):
found = re.search(r'10.1038', written)
self.assertTrue(found is None)
def test_conversion_with_python_filter(self):
markdown_source = "**Here comes the content.**"
python_source = '''\
#!{0}
"""
Pandoc filter to convert all regular text to uppercase.
Code, link URLs, etc. are not affected.
"""
from pandocfilters import toJSONFilter, Str
def caps(key, value, format, meta):
if key == 'Str':
return Str(value.upper())
if __name__ == "__main__":
toJSONFilter(caps)
'''
python_source = textwrap.dedent(python_source)
python_source = python_source.format(sys.executable)
with closed_tempfile(".py", python_source) as tempfile:
os.chmod(tempfile, 0o755)
output = pypandoc.convert_text(
markdown_source, to='html', format='md', outputfile=None, filters=tempfile
).strip()
expected = '<p><strong>HERE COMES THE CONTENT.</strong></p>'
self.assertTrue(output == expected)
def test_conversion_with_lua_filter(self):
markdown_source = "**Here comes the content.**"
lua_source = """\
-- taken from: https://pandoc.org/lua-filters.html
function Strong(elem)
return pandoc.SmallCaps(elem.c)
end
"""
lua_source = textwrap.dedent(lua_source)
with closed_tempfile(".lua", lua_source) as tempfile:
output = pypandoc.convert_text(
markdown_source, to='html', format='md', outputfile=None, filters=tempfile
).strip()
expected = '<p><span class="smallcaps">Here comes the content.</span></p>'
self.assertTrue(output == expected)
def test_conversion_with_mixed_filters(self):
markdown_source = "-0-"
lua = """\
function Para(elem)
return pandoc.Para(elem.content .. {{"{0}-"}})
end
"""
lua = textwrap.dedent(lua)
python = """\
#!{0}
from pandocfilters import toJSONFilter, Para, Str
def func(key, value, format, meta):
if key == "Para":
return Para(value + [Str("{{0}}-")])
if __name__ == "__main__":
toJSONFilter(func)
"""
python = textwrap.dedent(python)
python = python.format(sys.executable)
with closed_tempfile(".lua", lua.format(1)) as temp1, closed_tempfile(".py", python.format(2)) as temp2:
os.chmod(temp2, 0o755)
with closed_tempfile(".lua", lua.format(3)) as temp3, closed_tempfile(".py", python.format(4)) as temp4:
os.chmod(temp4, 0o755)
output = pypandoc.convert_text(
markdown_source, to="html", format="md", outputfile=None, filters=[temp1, temp2, temp3, temp4]
).strip()
expected = "<p>-0-1-2-3-4-</p>"
self.assertEquals(output, expected)
output = pypandoc.convert_text(
markdown_source, to="html", format="md", outputfile=None, filters=[temp3, temp1, temp4, temp2]
).strip()
expected = "<p>-0-3-1-4-2-</p>"
self.assertEquals(output, expected)
def test_classify_pandoc_logging(self):
test = ("[WARNING] This is some message on\ntwo lines\n"
"[ERROR] This is a second message.")
expected_levels = [30, 40]
expected_msgs = ["This is some message on\ntwo lines",
"This is a second message."]
for i, (l, m) in enumerate(pypandoc._classify_pandoc_logging(test)):
self.assertEqual(expected_levels[i], l)
self.assertEqual(expected_msgs[i], m)
def test_classify_pandoc_logging_default(self):
test = ("This is some message on\ntwo lines\n"
"[ERROR] This is a second message.")
expected_levels = [30, 40]
expected_msgs = ["This is some message on\ntwo lines",
"This is a second message."]
for i, (l, m) in enumerate(pypandoc._classify_pandoc_logging(test)):
self.assertEqual(expected_levels[i], l)
self.assertEqual(expected_msgs[i], m)
def test_classify_pandoc_logging_invalid_level(self):
test = ("[WARN] This is some message on\ntwo lines\n"
"[ERR] This is a second message.\n"
"[ERROR] This is a third message.")
expected_levels = [30, 30, 40]
expected_msgs = ["This is some message on\ntwo lines",
"This is a second message.",
"This is a third message."]
for i, (l, m) in enumerate(pypandoc._classify_pandoc_logging(test)):
self.assertEqual(expected_levels[i], l)
self.assertEqual(expected_msgs[i], m)
def test_conversion_stderr(self):
# Clear logger handlers
logger = logging.getLogger("pypandoc")
logger.handlers = []
with closed_tempfile('.docx') as file_name:
text = ('![Mock](missing.png)\n'
'![Mock](missing.png)\n')
with capture(pypandoc.convert_text,
text,
to='docx',
format='md',
outputfile=file_name) as output:
output = re.sub(r'\r', '', output)
output = output.replace("'missing.png'",
"missing.png")
output = output.lower()
print(output)
assert "[warning] could not fetch resource missing.png" in output
def test_conversion_stderr_nullhandler(self):
# Replace any logging handlers with a null handler
logger = logging.getLogger("pypandoc")
logger.handlers = [logging.NullHandler()]
with closed_tempfile('.docx') as file_name:
text = ('![Mock](missing.png)\n'
'![Mock](missing.png)\n')
with capture(pypandoc.convert_text,
text,
to='docx',
format='md',
outputfile=file_name) as output:
self.assertFalse(output)
def test_conversion_error(self):
# pandoc dies on wrong commandline arguments
def f():
@@ -339,9 +574,9 @@ class TestPypandoc(unittest.TestCase):
# no extensions allowed
with closed_tempfile('.pdf') as file_name:
def f():
pypandoc.convert_text('# some title\n', to='pdf+somethign', format='md', outputfile=file_name)
pypandoc.convert_text('# some title\n', to='pdf+something', format='md', outputfile=file_name)
with self.assertRaisesRegex(RuntimeError, r"PDF output can't contain any extensions: pdf\+somethign"):
with self.assertRaisesRegex(RuntimeError, r"PDF output can't contain any extensions: pdf\+something"):
f()
def test_get_pandoc_path(self):
@@ -372,17 +607,49 @@ class TestPypandoc(unittest.TestCase):
received = pypandoc.convert_file(file_name, 'rst', format='md')
self.assertTrue("title" in received)
def test_depreaction_warnings(self):
# convert itself is deprecated...
with assert_produces_warning(DeprecationWarning):
pypandoc.convert('# some title\n', to='rst', format='md')
def create_sample_lua(self):
args = [pypandoc.get_pandoc_path(), '--print-default-data-file', 'sample.lua']
p = subprocess.Popen(args, stdout=subprocess.PIPE)
out, err = p.communicate()
return out.decode('utf-8')
def test_basic_conversion_from_file_pathlib(self):
with closed_tempfile('.md', text='# some title\n') as file_name:
expected = u'some title{0}=========={0}{0}'.format(os.linesep)
received_from_str_filename_input = pypandoc.convert_file(file_name, 'rst')
received_from_path_filename_input = pypandoc.convert_file(Path(file_name), 'rst')
self.assertEqualExceptForNewlineEnd(expected, received_from_str_filename_input)
self.assertEqualExceptForNewlineEnd(expected, received_from_path_filename_input)
def test_basic_conversion_from_multiple_files_pathlib(self):
with closed_tempfile('.md', text='some title') as file_name1:
with closed_tempfile('.md', text='some title') as file_name2:
expected = '<p>some title</p>\n<p>some title</p>'
received_from_str_filename_input = pypandoc.convert_file([file_name1, file_name2], 'html')
received_from_path_filename_input = pypandoc.convert_file([Path(file_name1), Path(file_name2)], 'html')
self.assertEqualExceptForNewlineEnd(expected, received_from_str_filename_input)
self.assertEqualExceptForNewlineEnd(expected, received_from_path_filename_input)
def test_basic_conversion_from_file_pattern_pathlib_glob(self):
received_from_str_filename_input = pypandoc.convert_file("./*.md", 'html').lower()
received_from_path_filename_input = pypandoc.convert_file(Path(".").glob("*.md"), 'html').lower()
assert received_from_str_filename_input == received_from_path_filename_input
def test_basic_conversion_from_file_pattern_with_input_list_pathlib_glob(self):
received_from_str_filename_input = pypandoc.convert_file(["./*.md", "./*.md"], 'html').lower()
received_from_path_filename_input = pypandoc.convert_file([*Path(".").glob("*.md"), *Path(".").glob("*.md")],
'html').lower()
assert received_from_str_filename_input == received_from_path_filename_input
def test_basic_conversion_to_pathlib_file(self):
with closed_tempfile('.rst', ) as file_name:
expected = u'some title{0}=========={0}{0}'.format(os.linesep)
received = pypandoc.convert_text('# some title\n', to='rst', format='md', outputfile=Path(file_name))
self.assertEqualExceptForNewlineEnd("", received)
with io.open(file_name) as f:
written = f.read()
self.assertEqualExceptForNewlineEnd(expected, written)
def assertEqualExceptForNewlineEnd(self, expected, received): # noqa
# output written to a file does not seem to have os.linesep
# handle everything here by replacing the os linesep by a simple \n