1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337
|
#!/usr/bin/env python3
# $Id: test_publisher.py 10077 2025-04-09 08:55:54Z milde $
# Author: Martin Blais <blais@furius.ca>
# Copyright: This module has been placed in the public domain.
"""
Test the `Publisher` facade and the ``publish_*`` convenience functions.
"""
import pickle
from pathlib import Path
import sys
import unittest
if __name__ == '__main__':
# prepend the "docutils root" to the Python library path
# so we import the local `docutils` package.
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
import docutils
import docutils.parsers.null
from docutils import core, nodes, parsers, readers, writers
from docutils.writers import html4css1, odf_odt, pseudoxml
# DATA_ROOT is ./test/data/ from the docutils root
DATA_ROOT = Path(__file__).parent / 'data'
test_document = """\
Test Document
=============
This is a test document with a broken reference: nonexistent_
"""
pseudoxml_output = """\
<document ids="test-document" names="test\\ document" source="<string>" title="Test Document">
<title>
Test Document
<paragraph>
This is a test document with a broken reference: \n\
<problematic ids="problematic-1" refid="system-message-1">
nonexistent_
<section classes="system-messages">
<title>
Docutils System Messages
<system_message backrefs="problematic-1" ids="system-message-1" level="3" line="4" source="<string>" type="ERROR">
<paragraph>
Unknown target name: "nonexistent".
"""
exposed_pseudoxml_output = """\
<document ids="test-document" internal:refnames="{'nonexistent': [<reference: <#text: 'nonexistent'>>]}" names="test\\ document" source="<string>" title="Test Document">
<title>
Test Document
<paragraph>
This is a test document with a broken reference: \n\
<problematic ids="problematic-1" refid="system-message-1">
nonexistent_
<section classes="system-messages">
<title>
Docutils System Messages
<system_message backrefs="problematic-1" ids="system-message-1" level="3" line="4" source="<string>" type="ERROR">
<paragraph>
Unknown target name: "nonexistent".
"""
class PublisherTests(unittest.TestCase):
def test__init__(self):
reader = readers.standalone.Reader()
parser = parsers.null.Parser()
writer = writers.null.Writer()
# arguments may be component instances ...
publisher = core.Publisher(reader, parser, writer)
self.assertEqual(publisher.reader, reader)
self.assertEqual(publisher.parser, parser)
self.assertEqual(publisher.writer, writer)
# ... or names
publisher = core.Publisher('standalone', parser, writer)
self.assertTrue(isinstance(publisher.reader,
readers.standalone.Reader))
self.assertEqual(publisher.parser, parser)
self.assertEqual(publisher.writer, writer)
publisher = core.Publisher(reader, 'rst', writer)
self.assertEqual(publisher.reader, reader)
self.assertTrue(isinstance(publisher.parser, parsers.rst.Parser))
self.assertEqual(publisher.writer, writer)
publisher = core.Publisher(reader, parser, 'latex')
self.assertEqual(publisher.reader, reader)
self.assertEqual(publisher.parser, parser)
self.assertTrue(isinstance(publisher.writer, writers.latex2e.Writer))
def test_set_reader(self):
publisher = core.Publisher(parser='null')
parser = parsers.null.Parser()
# "parser" argument can be an instance or name
publisher.set_reader('standalone', parser='rst')
self.assertTrue(isinstance(publisher.parser, parsers.rst.Parser))
# synchronize parser attributes of publisher and reader:
self.assertEqual(publisher.reader.parser, publisher.parser)
# the "parser_name" argument is deprecated;
with self.assertWarnsRegex(PendingDeprecationWarning,
'Argument "parser_name" will be removed'):
publisher.set_reader('standalone', parser=None, parser_name='rst')
self.assertTrue(isinstance(publisher.parser, parsers.rst.Parser))
self.assertEqual(publisher.reader.parser, publisher.parser)
# "parser" takes precedence
with self.assertWarns(PendingDeprecationWarning):
publisher.set_reader('standalone', parser, parser_name='rst')
self.assertEqual(publisher.parser, parser)
self.assertEqual(publisher.reader.parser, publisher.parser)
# if there is no other parser specified, use self.parser
publisher.set_reader('standalone')
self.assertTrue(isinstance(publisher.parser, parsers.null.Parser))
self.assertEqual(publisher.reader.parser, publisher.parser)
def test_set_components(self):
publisher = core.Publisher()
reader = readers.standalone.Reader()
parser = parsers.null.Parser()
writer = writers.null.Writer()
# set components from names
with self.assertWarnsRegex(PendingDeprecationWarning,
'set_components.* will be removed'):
publisher.set_components('pep', 'rst', 'odt')
self.assertTrue(isinstance(publisher.reader, readers.pep.Reader))
self.assertTrue(isinstance(publisher.parser, parsers.rst.Parser))
self.assertTrue(isinstance(publisher.writer, writers.odf_odt.Writer))
# but don't overwrite registered component instances
publisher = core.Publisher(reader, parser, writer)
with self.assertWarns(PendingDeprecationWarning):
publisher.set_components('standalone', 'xml', 'odt')
self.assertEqual(publisher.reader, reader)
self.assertEqual(publisher.parser, parser)
self.assertEqual(publisher.writer, writer)
def test_set_destination(self):
# Exit if `_destination` and `output` settings conflict.
publisher = core.Publisher()
publisher.get_settings(output_path='out_name', _destination='other')
with self.assertRaises(SystemExit):
publisher.set_destination()
# no conflict if both have same value:
publisher.settings._destination = 'out_name'
publisher.set_destination()
# no conflict if both are overridden:
publisher.set_destination(destination_path='winning_dest')
# "output_path" and legacy settings are set to `destination_path`:
self.assertEqual(publisher.settings.output_path, 'winning_dest')
self.assertEqual(publisher.settings.output, 'winning_dest')
self.assertEqual(publisher.settings._destination, 'winning_dest')
class ConvenienceFunctionTests(unittest.TestCase):
maxDiff = None
settings = {'_disable_config': True,
'datestamp': False}
def test_publish_cmdline(self):
# the "*_name" arguments will be removed
with self.assertWarns(PendingDeprecationWarning):
core.publish_cmdline(writer_name='null',
argv=[(DATA_ROOT/'include.rst').as_posix()],
settings_overrides={'traceback': True})
def test_input_error_handling(self):
# core.publish_cmdline(argv=['nonexisting/path'])
# exits with a short message, if `traceback` is False,
# pass IOErrors to calling application if `traceback` is True:
with self.assertRaises(IOError):
core.publish_cmdline(argv=['nonexisting/path'],
settings_overrides={'traceback': True})
def test_output_error_handling(self):
# pass IOErrors to calling application if `traceback` is True
with self.assertRaises(docutils.io.OutputError):
core.publish_cmdline(argv=[(DATA_ROOT/'include.rst').as_posix(),
'nonexisting/path'],
settings_overrides={'traceback': True})
def test_destination_output_conflict(self):
# Exit if positional argument and --output option conflict.
settings = {'output_path': 'out_name'}
with self.assertRaises(SystemExit):
core.publish_cmdline(argv=['-', 'dest_name'],
settings_overrides=settings)
def test_publish_string_input_encoding(self):
"""Test handling of encoded input."""
# Transparently decode `bytes` source (with "input_encoding" setting)
# default: utf-8
# Output is encoded according to "output_encoding" setting.
settings = self.settings | {'input_encoding': 'utf-16',
'output_encoding': 'unicode'}
source = 'test → me'
expected = ('<document source="<string>">\n'
' <paragraph>\n'
' test → me\n')
output = core.publish_string(source.encode('utf-16'),
settings_overrides=settings)
self.assertEqual(expected, output)
# encoding declaration in source (used if input_encoding is None)
# input encoding detection will be removed in Docutils 1.0
source = '.. encoding: latin1\n\nGrüße'
settings['input_encoding'] = None
with self.assertWarnsRegex(DeprecationWarning, 'auto-detection'):
output = core.publish_string(source.encode('latin1'),
settings_overrides=settings)
self.assertTrue(output.endswith('Grüße\n'))
def test_publish_string_output_encoding(self):
settings = self.settings | {'output_encoding': 'latin1'}
settings['output_encoding_error_handler'] = 'replace'
source = 'Grüß → dich'
expected = ('<document source="<string>">\n'
' <paragraph>\n'
' Grüß → dich\n')
# encode output, return `bytes`
output = bytes(core.publish_string(source,
settings_overrides=settings))
self.assertEqual(expected.encode('latin1', 'replace'), output)
def test_publish_string_output_encoding_odt(self):
"""The ODT writer generates a zip archive, not a `str`.
TODO: return `str` with document as "flat XML" (.fodt).
"""
settings = self.settings | {'output_encoding': 'unicode',
'warning_stream': ''}
with self.assertRaisesRegex(docutils.utils.SystemMessage,
'The ODT writer returns `bytes` '):
core.publish_string('test', writer=odf_odt.Writer(),
settings_overrides=settings)
def test_publish_string_deprecation_warning(self):
"""The "*_name" arguments are deprecated."""
source = 'test → me'
with self.assertWarns(PendingDeprecationWarning):
output = core.publish_string(source, writer_name='xml')
# ... but should still set the corresponding component:
self.assertTrue(output.decode('utf-8').startswith(
'<?xml version="1.0" encoding="utf-8"?>'))
class PublishDoctreeTestCase(unittest.TestCase, docutils.SettingsSpec):
settings_default_overrides = {
'_disable_config': True,
'warning_stream': docutils.io.NullOutput(),
'output_encoding': 'unicode'}
def test_publish_doctree(self):
# Test `publish_doctree` and `publish_from_doctree`.
# Produce the document tree.
with self.assertWarns(PendingDeprecationWarning):
doctree = core.publish_doctree(
source=test_document,
parser_name='restructuredtext', settings_spec=self,
settings_overrides={'expose_internals':
['refnames', 'do_not_expose'],
'report_level': 5})
self.assertTrue(isinstance(doctree, nodes.document))
# Confirm that transforms have been applied (in this case, the
# DocTitle transform):
self.assertTrue(isinstance(doctree[0], nodes.title))
self.assertTrue(isinstance(doctree[1], nodes.paragraph))
# Confirm that the Messages transform has not yet been applied:
self.assertEqual(2, len(doctree))
# The `do_not_expose` attribute may not show up in the
# pseudoxml output because the expose_internals transform may
# not be applied twice.
doctree.do_not_expose = 'test'
# Write out the document:
output = core.publish_from_doctree(
doctree,
writer=pseudoxml.Writer(),
settings_spec=self,
settings_overrides={'expose_internals':
['refnames', 'do_not_expose'],
'report_level': 1,
'output_encoding': 'unicode'})
self.assertEqual(exposed_pseudoxml_output, output)
# Test publishing parts using document as the source.
parts = core.publish_parts(
reader='doctree', source_class=docutils.io.DocTreeInput,
source=doctree, source_path='test', writer=html4css1.Writer(),
settings_spec=self)
self.assertTrue(isinstance(parts, dict))
def test_publish_pickle(self):
# Test publishing a document tree with pickling and unpickling.
# Produce the document tree.
doctree = core.publish_doctree(
source=test_document,
settings_spec=self)
self.assertTrue(isinstance(doctree, nodes.document))
# Pickle the document. Note: if this fails, some unpickleable
# reference has been added somewhere within the document tree.
# If so, you need to fix that.
#
# Note: Please do not remove this test, this is an important
# requirement, applications will be built on the assumption
# that we can pickle the document.
# Remove the reporter and the transformer before pickling.
doctree.reporter = None
doctree.transformer = None
doctree_pickled = pickle.dumps(doctree)
self.assertTrue(isinstance(doctree_pickled, bytes))
del doctree
# Unpickle the document.
doctree_zombie = pickle.loads(doctree_pickled)
self.assertTrue(isinstance(doctree_zombie, nodes.document))
# Write out the document:
with self.assertWarnsRegex(PendingDeprecationWarning,
'Argument "writer_name" will be removed '):
output = core.publish_from_doctree(doctree_zombie,
writer_name='pseudoxml',
settings_spec=self)
self.assertEqual(pseudoxml_output, output)
if __name__ == '__main__':
unittest.main()
|