This is a test.
33 | 34 |Link to Slashdot
41 | >>> 42 | 43 | h3. Notes: 44 | 45 | * Active development supports Python 3.8 or later. 46 | 47 | h3. Running Tests 48 | 49 | To run the test suite, use pytest. `pytest-cov` is required as well. 50 | 51 | When textile is installed locally: 52 | 53 | bc. pytest 54 | 55 | When textile is not installed locally: 56 | 57 | bc. PYTHONPATH=. pytest 58 | -------------------------------------------------------------------------------- /TODO.textile: -------------------------------------------------------------------------------- 1 | TODO 2 | 3 | * Improve documentation, both of the code and Textile syntax. 4 | ** Not all functions have docstrings or adequate docstrings. 5 | ** Because the Textile syntax implemented by PyTextile has deviated from the syntax implemented by other implementations of Textile, PyTextile-specific documentation needs to be produced for end-users. 6 | * Update to comply with Textile 2.5 7 | -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- 1 | [build-system] 2 | requires = ["setuptools", "setuptools-scm", "nh3"] 3 | build-backend = "setuptools.build_meta" 4 | 5 | [project] 6 | name = "textile" 7 | authors = [ 8 | { name = "Dennis Burke", email = "ikirudennis@gmail.com"} 9 | ] 10 | description = 'Textile processing for python.' 11 | classifiers = [ 12 | 'Development Status :: 5 - Production/Stable', 13 | 'Environment :: Web Environment', 14 | 'Intended Audience :: Developers', 15 | 'License :: OSI Approved :: BSD License', 16 | 'Operating System :: OS Independent', 17 | 'Programming Language :: Python', 18 | 'Programming Language :: Python :: 3', 19 | 'Programming Language :: Python :: 3 :: Only', 20 | 'Programming Language :: Python :: 3.8', 21 | 'Programming Language :: Python :: 3.9', 22 | 'Programming Language :: Python :: 3.10', 23 | 'Programming Language :: Python :: 3.11', 24 | 'Programming Language :: Python :: 3.12', 25 | 'Topic :: Software Development :: Libraries :: Python Modules', 26 | ] 27 | dynamic = ["version",] 28 | dependencies = [ 29 | 'nh3', 30 | 'regex>1.0; implementation_name != "pypy"', 31 | ] 32 | requires-python = '>=3.8' 33 | keywords = ['textile', 'text', 'html markup'] 34 | # Use the following command to generate a README.txt which is compatible with 35 | # pypi's readme rendering: 36 | # pytextile README.textile | sed -e 's/^\t//' > README.txt 37 | readme = {file = 'README.txt', content-type = 'text/markdown'} 38 | 39 | [project.optional-dependencies] 40 | develop = ['pytest', 'pytest-cov'] 41 | imagesize = ['Pillow>=3.0.0',] 42 | 43 | [project.urls] 44 | Homepage = "https://github.com/textile/python-textile" 45 | Repository = "https://github.com/textile/python-textile.git" 46 | Issues = "https://github.com/textile/python-textile/issues" 47 | 48 | [project.scripts] 49 | pytextile = "textile.__main__:main" 50 | 51 | [tool.setuptools.dynamic] 52 | version = {attr = "textile.__version__"} 53 | -------------------------------------------------------------------------------- /pytest.ini: -------------------------------------------------------------------------------- 1 | [pytest] 2 | testpaths = tests 3 | addopts = --cov=textile --cov-report=html --cov-append --cov-report=term-missing 4 | -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/textile/python-textile/a1c31e525dfdb1745ae8d09d5a08323ef579f414/tests/__init__.py -------------------------------------------------------------------------------- /tests/fixtures/README.txt: -------------------------------------------------------------------------------- 1 |
python-textile is a Python port of Textile, Dean Allen’s humane web text generator.
6 | 7 |pip install textile
Dependencies: 12 |
Optional dependencies include: 18 |
pip install 'textile[imagesize]'import textile
25 | >>> s = """
26 | ... _This_ is a *test.*
27 | ...
28 | ... * One
29 | ... * Two
30 | ... * Three
31 | ...
32 | ... Link to "Slashdot":http://slashdot.org/
33 | ... """
34 | >>> html = textile.textile(s)
35 | >>> print html
36 | <p><em>This</em> is a <strong>test.</strong></p>
37 |
38 | <ul>
39 | <li>One</li>
40 | <li>Two</li>
41 | <li>Three</li>
42 | </ul>
43 |
44 | <p>Link to <a href="http://slashdot.org/">Slashdot</a></p>
45 | >>>To run the test suite, use pytest. `pytest-cov` is required as well.
56 | 57 |When textile is installed locally:
58 | 59 |pytestWhen textile is not installed locally:
62 | 63 |PYTHONPATH=. pytesttext\nmoretext\n\nevenmoretext\n\nmoremoretexttest
' 54 | t = textile.Textile() 55 | result = t.parse(input) 56 | assert result == expect 57 | 58 | 59 | def test_blockcode_in_README(): 60 | with open('README.textile') as f: 61 | readme = ''.join(f.readlines()) 62 | result = textile.textile(readme) 63 | with open('tests/fixtures/README.txt') as f: 64 | expect = ''.join(f.readlines()) 65 | assert result == expect 66 | 67 | 68 | def test_blockcode_comment(): 69 | input = '###.. block comment\nanother line\n\np. New line' 70 | expect = '\tNew line
' 71 | t = textile.Textile() 72 | result = t.parse(input) 73 | assert result == expect 74 | 75 | 76 | def test_extended_pre_block_with_many_newlines(): 77 | """Extra newlines in an extended pre block should not get cut down to only 78 | two.""" 79 | text = '''pre.. word 80 | 81 | another 82 | 83 | word 84 | 85 | 86 | yet anothe word''' 87 | expect = '''word 88 | 89 | another 90 | 91 | word 92 | 93 | 94 | yet anothe word''' 95 | result = textile.textile(text) 96 | assert result == expect 97 | 98 | text = 'p. text text\n\n\nh1. Hello\n' 99 | expect = '\t
text text
\n\n\n\tgoogle.com google.com blackhole@sun.comet
' 8 | assert result == expect 9 | 10 | 11 | def test_github_issue_17(): 12 | result = textile.textile('!http://www.ox.ac.uk/favicon.ico!') 13 | expect = '\tThis is a link to a Wikipedia article about Textile.
' 21 | assert result == expect 22 | 23 | 24 | def test_github_issue_21(): 25 | text = ('''h1. xml example 26 | 27 | bc. ''' 28 | ''' 29 |\n<foo>\n bar\n</foo>Ty Segall’s
' 41 | assert result == expect 42 | 43 | 44 | def test_github_issue_26(): 45 | text = '' 46 | result = textile.textile(text) 47 | expect = '' 48 | assert result == expect 49 | 50 | 51 | def test_github_issue_27(): 52 | test = """* Folders with ":" in their names are displayed with a forward slash "/" instead. (Filed as "#4581709":/test/link, which was considered "normal behaviour" - quote: "Please note that Finder presents the 'Carbon filesystem' view, regardless of the underlying filesystem.")""" 53 | result = textile.textile(test) 54 | expect = """\t
62 | def parseWapProfile(self, url):
63 | result = fetch.fetchURL(url)
64 | soup = BeautifulStoneSoup(result['data'], convertEntities=BeautifulStoneSoup.HTML_ENTITIES)
65 | try:
66 | width, height = soup('prf:screensize')[0].contents[0].split('x')
67 | except:
68 | width = height = None
69 | return {"width": width, "height": height}
70 |
71 |
72 | Of course there's a lot more error handling to do (and useful data to glean off the "XML":XML), but being able to cut through all the usual parsing crap is immensely gratifying."""
73 | result = textile.textile(test)
74 | expect = ("""\tSo here I am porting my ancient newspipe front-end to Snakelets and Python, and I’ve just trimmed down over 20 lines of PHP down to essentially one line of BeautifulSoup retrieval:
75 | 76 |
77 | def parseWapProfile(self, url):
78 | result = fetch.fetchURL(url)
79 | soup = BeautifulStoneSoup(result['data'], convertEntities=BeautifulStoneSoup.HTML_ENTITIES)
80 | try:
81 | width, height = soup('prf:screensize')[0].contents[0].split('x')
82 | except:
83 | width = height = None
84 | return {"width": width, "height": height}
85 |
86 |
87 | \tOf course there’s a lot more error handling to do (and useful data to glean off the XML), but being able to cut through all the usual parsing crap is immensely gratifying.
""") 88 | assert result == expect 89 | 90 | 91 | def test_github_issue_30(): 92 | text = '"Tëxtíle (Tëxtíle)":http://lala.com' 93 | result = textile.textile(text) 94 | expect = '\t' 95 | assert result == expect 96 | 97 | text = '!http://lala.com/lol.gif(♡ imáges)!' 98 | result = textile.textile(text) 99 | expect = '\t
\t
Highlights
119 | 120 | \t
smart ‘quotes’ are not smart!' 150 | assert result == expect 151 | 152 | 153 | def test_github_issue_45(): 154 | """Incorrect transform unicode url""" 155 | text = '"test":https://myabstractwiki.ru/index.php/%D0%97%D0%B0%D0%B3%D0%BB%D0%B0%D0%B2%D0%BD%D0%B0%D1%8F_%D1%81%D1%82%D1%80%D0%B0%D0%BD%D0%B8%D1%86%D0%B0' 156 | result = textile.textile(text) 157 | expect = '\t' 158 | assert result == expect 159 | 160 | 161 | def test_github_issue_46(): 162 | """Key error on mal-formed numbered lists. CAUTION: both the input and the 163 | ouput are ugly.""" 164 | text = '# test\n### test\n## test' 165 | expect = ('\t
word 183 | 184 | another 185 | 186 | word 187 | 188 | yet anothe word''' 189 | assert result == expect 190 | 191 | 192 | def test_github_issue_49(): 193 | """Key error on russian hash-route link""" 194 | s = '"link":https://ru.vuejs.org/v2/guide/components.html#Входные-параметры' 195 | result = textile.textile(s) 196 | expect = '\t' 197 | assert result == expect 198 | 199 | 200 | def test_github_issue_50(): 201 | """Incorrect wrap code with Java generics in pre""" 202 | test = ('pre.. public class Tynopet
public class Tynopet<T extends Framework> {}\n\n'
206 | 'final List<List<String>> multipleList = new '
207 | 'ArrayList<>();')
208 | assert result == expect
209 |
210 |
211 | def test_github_issue_51():
212 | """Link build with $ sign without "http" prefix broken."""
213 | test = '"$":www.google.com.br'
214 | result = textile.textile(test)
215 | expect = '\t'
216 | assert result == expect
217 |
218 |
219 | def test_github_issue_52():
220 | """Table build without space after aligment raise a AttributeError."""
221 | test = '|=.First Header |=. Second Header |'
222 | result = textile.textile(test)
223 | expect = ('\t| =.First Header ' 224 | ' | \n\t\t\tSecond Header | ' 225 | '\n\t\t
this is the first line\n\nbut "quotes" in an ' 235 | 'extended pre block need to be handled properly.') 236 | assert result == expect 237 | 238 | # supplied input 239 | test = ('pre.. import org.slf4j.Logger;\nimport org.slf4j.LoggerFactory;' 240 | '\nimport ru.onyma.job.Context;\nimport ru.onyma.job.' 241 | 'RescheduleTask;\n\nimport java.util.concurrent.' 242 | 'ScheduledExecutorService;\nimport java.util.concurrent.TimeUnit;' 243 | '\n\n/**\n* @author ustits\n*/\npublic abstract class ' 244 | 'MainService
import org.slf4j.Logger;\nimport org.slf4j.LoggerFactory;'
260 | '\nimport ru.onyma.job.Context;\nimport ru.onyma.job.'
261 | 'RescheduleTask;\n\nimport java.util.concurrent.'
262 | 'ScheduledExecutorService;\nimport java.util.concurrent.'
263 | 'TimeUnit;\n\n/**\n* @author ustits\n*/\npublic abstract class '
264 | 'MainService<T> extends RescheduleTask implements '
265 | 'Context<T> {\n\nprivate static final Logger log = '
266 | 'LoggerFactory.getLogger(MainService.class);\nprivate final '
267 | 'ScheduledExecutorService scheduler;\n\nprivate boolean '
268 | 'isFirstRun = true;\nprivate T configs;\n\npublic MainService('
269 | 'final ScheduledExecutorService scheduler) {\nsuper(scheduler);'
270 | '\nthis.scheduler = scheduler;\n}\n\n@Override\npublic void '
271 | 'setConfig(final T configs) {\nthis.configs = configs;\nif ('
272 | 'isFirstRun) {\nscheduler.schedule(this, 0, TimeUnit.SECONDS);'
273 | '\nisFirstRun = false;\n}\n}\n\n@Override\npublic void stop() {'
274 | '\nsuper.stop();\nscheduler.shutdown();\ntry {\nscheduler.'
275 | 'awaitTermination(Long.MAX_VALUE, TimeUnit.DAYS);\n} catch '
276 | '(InterruptedException ie) {\nlog.warn("Unable to wait '
277 | 'for syncs termination", ie);\nThread.currentThread().'
278 | 'interrupt();\n}\n}\n\nprotected final T getConfigs() {\n'
279 | 'return configs;\n}\n}')
280 | assert result == expect
281 |
282 |
283 | def test_github_issue_56():
284 | """Empty description lists throw error"""
285 | result = textile.textile("- :=\n-")
286 | expect = 'This is some TEXT inside a "Code BLOCK"
309 |
310 | {
311 | if (JSON) {
312 |
313 | return {"JSON":"value"}
314 | }
315 | }
316 |
317 | Back to 10-4 CAPS Some multiline Paragragh
320 | 321 |Here is some output!!! “Some” CAPS
''' 322 | t = textile.Textile() 323 | result = t.parse(test) 324 | assert result == expect 325 | 326 | 327 | def test_github_pull_62(): 328 | """Fix for paragraph multiline, only last paragraph is rendered 329 | correctly""" 330 | test = '''p.. First one 'is' 331 | 332 | ESCAPED "bad" 333 | 334 | p.. Second one 'is' 335 | 336 | 337 | 338 | ESCAPED "bad" 339 | 340 | p.. Third one 'is' 341 | 342 | ESCAPED "bad" 343 | 344 | p.. Last one 'is' 345 | 346 | ESCAPED "good" test''' 347 | 348 | expect = '''First one ‘is’
349 | 350 |ESCAPED “bad”
351 | 352 |Second one ‘is’
353 | 354 | 355 | 356 |ESCAPED “bad”
357 | 358 |Third one ‘is’
359 | 360 |ESCAPED “bad”
361 | 362 |Last one ‘is’
363 | 364 |ESCAPED “good” test
''' 365 | t = textile.Textile() 366 | result = t.parse(test) 367 | assert result == expect 368 | 369 | 370 | def test_github_pull_63(): 371 | """Forgot to set multiline_para to False""" 372 | test = '''p.. First one 'is' 373 | 374 | ESCAPED "bad" 375 | 376 | bc.. { 377 | First code BLOCK 378 | 379 | {"JSON":'value'} 380 | } 381 | 382 | p.. Second one 'is' 383 | 384 | 385 | 386 | ESCAPED "bad" 387 | 388 | p.. Third one 'is' 389 | 390 | ESCAPED "bad" 391 | 392 | bc.. { 393 | Last code BLOCK 394 | 395 | {"JSON":'value'} 396 | } 397 | 398 | p.. Last one 'is' 399 | 400 | ESCAPED "good" test''' 401 | 402 | expect = '''First one ‘is’
403 | 404 |ESCAPED “bad”
405 | 406 |{
407 | First code BLOCK
408 |
409 | {"JSON":'value'}
410 | }Second one ‘is’
413 | 414 | 415 | 416 |ESCAPED “bad”
417 | 418 |Third one ‘is’
419 | 420 |ESCAPED “bad”
421 | 422 |{
423 | Last code BLOCK
424 |
425 | {"JSON":'value'}
426 | }Last one ‘is’
429 | 430 |ESCAPED “good” test
''' 431 | t = textile.Textile() 432 | result = t.parse(test) 433 | assert result == expect 434 | -------------------------------------------------------------------------------- /tests/test_glyphs.py: -------------------------------------------------------------------------------- 1 | from textile import Textile 2 | 3 | 4 | def test_glyphs(): 5 | t = Textile() 6 | 7 | result = t.glyphs("apostrophe's") 8 | expect = 'apostrophe’s' 9 | assert result == expect 10 | 11 | result = t.glyphs("back in '88") 12 | expect = 'back in ’88' 13 | assert result == expect 14 | 15 | result = t.glyphs('foo ...') 16 | expect = 'foo …' 17 | assert result == expect 18 | 19 | result = t.glyphs('--') 20 | expect = '—' 21 | assert result == expect 22 | 23 | result = t.glyphs('FooBar[tm]') 24 | expect = 'FooBar™' 25 | assert result == expect 26 | 27 | result = t.glyphs("Cat's Cradle by Vonnegut
") 28 | expect = 'Cat’s Cradle by Vonnegut
' 29 | assert result == expect 30 | -------------------------------------------------------------------------------- /tests/test_image.py: -------------------------------------------------------------------------------- 1 | from textile import Textile 2 | 3 | 4 | def test_image(): 5 | t = Textile() 6 | result = t.image('!/imgs/myphoto.jpg!:http://jsamsa.com') 7 | expect = ('Test „quotes”.
' 11 | result = TextilePL().parse(test) 12 | assert expect == result 13 | 14 | # Base Textile is unchanged. 15 | expect = '\tTest “quotes”.
' 16 | result = textile.textile(test) 17 | assert expect == result 18 | -------------------------------------------------------------------------------- /tests/test_table.py: -------------------------------------------------------------------------------- 1 | from textile import Textile 2 | 3 | 4 | def test_table(): 5 | t = Textile() 6 | result = t.table('(rowclass). |one|two|three|\n|a|b|c|') 7 | expect = '\t| one | \n\t\t\ttwo | \n\t\t\tthree | \n\t\t
| a | \n\t\t\tb | \n\t\t\tc | \n\t\t
| one | \n\t\t\ttwo | \n\t\t\tthree | \n\t\t
| a | \n\t\t\tb | \n\t\t\tc | \n\t\t
| * test\n* test | \n\t\t\t1 | \n\t\t\t2 | \n\t\t
YACC1
', html) is not None 10 | 11 | 12 | def test_Footnote(): 13 | html = textile.textile('This is covered elsewhere[1].\n\nfn1. Down here, in fact.\n\nfn2. Here is another footnote.') 14 | assert re.search(r'^\tThis is covered elsewhere1.
\n\n\t1 Down here, in fact.
\n\n\t2 Here is another footnote.
$', html) is not None 15 | 16 | html = textile.textile('''See[1] for details -- or perhaps[100] at a push.\n\nfn1. Here are the details.\n\nfn100(footy#otherid). A totally unrelated footnote.''') 17 | assert re.search(r'^\tSee1 for details — or perhaps100 at a push.
\n\n\t1 Here are the details.
\n\n\t100 A totally unrelated footnote.
$', html) is not None 18 | 19 | html = textile.textile('''See[2] for details, and later, reference it again[2].\n\nfn2^(footy#otherid)[en]. Here are the details.''') 20 | assert re.search(r'^\tSee2 for details, and later, reference it again2.
\n\n\t2 Here are the details.
$', html) is not None 21 | 22 | html = textile.textile('''See[3!] for details.\n\nfn3. Here are the details.''') 23 | assert re.search(r'^\tSee3 for details.
\n\n\t3 Here are the details.
$', html) is not None 24 | 25 | html = textile.textile('''See[4!] for details.\n\nfn4^. Here are the details.''') 26 | assert re.search(r'^\tSee4 for details.
\n\n\t4 Here are the details.
$', html) is not None 27 | 28 | 29 | def test_issue_35(): 30 | result = textile.textile('"z"') 31 | expect = '\t“z”
' 32 | assert result == expect 33 | 34 | result = textile.textile('" z"') 35 | expect = '\t“ z”
' 36 | assert result == expect 37 | 38 | 39 | def test_restricted(): 40 | # Note that the HTML is escaped, thus rendering the " 42 | result = textile.textile_restricted(test) 43 | expect = "\tHere is some text.
\n<script>alert(‘hello world’)</script>
Here’s some <!— commented out —> text.
" 50 | 51 | assert result == expect 52 | 53 | test = "p[fr]. Partir, c'est toujours mourir un peu." 54 | result = textile.textile_restricted(test) 55 | expect = '\tPartir, c’est toujours mourir un peu.
' 56 | 57 | assert result == expect 58 | 59 | test = "p{color:blue}. is this blue?" 60 | result = textile.textile_restricted(test) 61 | expect = '\tis this blue?
' 62 | 63 | assert result == expect 64 | 65 | test = """\ 66 | table{border:1px solid black}. 67 | |={color:gray}. Your caption goes here 68 | |~. 69 | |{position:absolute}. A footer | foo | 70 | |-. 71 | |_{font-size:xxlarge}. header|_=. centered header| 72 | |~. bottom aligned|{background:red;width:200px}. asfd|""" 73 | result = textile.textile_restricted(test, lite=False) 74 | # styles from alignment hints like =. and ~. are ok 75 | expect = '''\ 76 | \t| A footer | 81 | \t\t\tfoo | 82 | \t\t
| header | 87 | \t\t\tcentered header | 88 | \t\t
|---|---|
| bottom aligned | 91 | \t\t\tasfd | 92 | \t\t
текст1
$', re.U).search(html) is not None 102 | 103 | 104 | def test_autolinking(): 105 | test = """some text "test":http://www.google.com http://www.google.com "$":http://www.google.com""" 106 | result = """\tsome text test http://www.google.com www.google.com
""" 107 | expect = textile.textile(test) 108 | 109 | assert result == expect 110 | 111 | 112 | def test_sanitize(): 113 | test = "a paragraph of benign text" 114 | result = "\ta paragraph of benign text
" 115 | expect = textile.Textile().parse(test, sanitize=True) 116 | assert result == expect 117 | 118 | test = """a paragraph of evil text
""" 119 | result = 'a paragraph of evil text
' 120 | expect = textile.Textile().parse(test, sanitize=True) 121 | assert result == expect 122 | 123 | test = """a paragraph of benign text
and more text
a paragraph of benign text
\nand more text
Scientists say the moon is slowly shrinking1.
\n\n\tTim Berners-Lee is one of the pioneer voices in favour of Net Neutrality1 and has expressed the view that ISPs should supply “connectivity with no strings attached”1 2
\n\n\tBerners-Lee admitted that the forward slashes \(“//”\) in a web address were actually unnecessary. He told the newspaper that he could easily have designed URLs not to have the forward slashes. “… it seemed like a good idea at the time,”3
\n\n\tScientists say1 the moon is quite small. But I, for one, don’t believe them. Others claim it to be made of cheese2. If this proves true I suspect we are in for troubled times3 as people argue over their “share” of the moon’s cheese. In the end, its limited size1 may prove problematic.
\n\n\tScientists say1 the moon is quite small. But I, for one, don’t believe them. Others claim it to be made of cheese2. If this proves true I suspect we are in for troubled times3 as people argue over their “share” of the moon’s cheese. In the end, its limited size1 may prove problematic.
\n\n\tScientists say the moon is slowly shrinking1.
\n\n\tSee2 for details, and later, reference it again2.
\n\n\t2 Here are the details.
$' 217 | assert re.compile(searchstring).search(html) is not None 218 | 219 | 220 | def test_footnote_without_reflink(): 221 | html = textile.textile('''See[3!] for details.\n\nfn3. Here are the details.''') 222 | searchstring = r'^\tSee3 for details.
\n\n\t3 Here are the details.
$' 223 | assert re.compile(searchstring).search(html) is not None 224 | 225 | 226 | def testSquareBrackets(): 227 | html = textile.textile("""1[^st^], 2[^nd^], 3[^rd^]. 2 log[~n~]\n\nA close[!http://textpattern.com/favicon.ico!]image.\nA tight["text":http://textpattern.com/]link.\nA ["footnoted link":http://textpattern.com/][182].""") 228 | searchstring = r'^\t1st, 2nd, 3rd. 2 logn
\n\n\tA closeimage.
\nA tighttextlink.
\nA footnoted link182.
We use CSS.
' 237 | expect = textile.textile(test, html_type="html5") 238 | assert result == expect 239 | 240 | 241 | def test_relURL(): 242 | t = textile.Textile() 243 | t.restricted = True 244 | assert t.relURL("gopher://gopher.com/") == '#' 245 | -------------------------------------------------------------------------------- /tests/test_textilefactory.py: -------------------------------------------------------------------------------- 1 | from textile import textilefactory 2 | import pytest 3 | 4 | 5 | def test_TextileFactory(): 6 | f = textilefactory.TextileFactory() 7 | result = f.process("some text here") 8 | expect = '\tsome text here
' 9 | assert result == expect 10 | 11 | f = textilefactory.TextileFactory(restricted=True) 12 | result = f.process("more text here") 13 | expect = '\tmore text here
' 14 | assert result == expect 15 | 16 | f = textilefactory.TextileFactory(noimage=True) 17 | result = f.process("this covers a partial branch.") 18 | expect = '\tthis covers a partial branch.
' 19 | assert result == expect 20 | 21 | # Certain parameter values are not permitted because they are illogical: 22 | 23 | with pytest.raises(ValueError) as ve: 24 | f = textilefactory.TextileFactory(lite=True) 25 | assert 'lite can only be enabled in restricted mode' in str(ve.value) 26 | 27 | with pytest.raises(ValueError) as ve: 28 | f = textilefactory.TextileFactory(html_type='invalid') 29 | assert "html_type must be 'xhtml' or 'html5'" in str(ve.value) 30 | -------------------------------------------------------------------------------- /tests/test_urls.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | from textile import Textile 3 | 4 | 5 | def test_urls(): 6 | t = Textile() 7 | assert t.relURL("http://www.google.com/") == 'http://www.google.com/' 8 | 9 | result = t.links('fooobar "Google":http://google.com/foobar/ and hello world "flickr":http://flickr.com/photos/jsamsa/ ') 10 | expect = 'fooobar {0}2:shelve and hello world {0}4:shelve '.format(t.uid) 11 | assert result == expect 12 | 13 | result = t.links('""Open the door, HAL!"":https://xkcd.com/375/') 14 | expect = '{0}6:shelve'.format(t.uid) 15 | assert result == expect 16 | 17 | result = t.links('"$":http://domain.tld/test_[brackets]') 18 | expect = '{0}8:shelve'.format(t.uid) 19 | assert result == expect 20 | 21 | result = t.links('"$":http://domain.tld/test_') 22 | expect = '{0}10:shelve'.format(t.uid) 23 | assert result == expect 24 | 25 | expect = '"":test' 26 | result = t.links(expect) 27 | assert result == expect 28 | 29 | expect = '"$":htt://domain.tld' 30 | result = t.links(expect) 31 | assert result == expect 32 | 33 | result = t.shelveURL('') 34 | expect = '' 35 | assert result == expect 36 | 37 | result = t.retrieveURLs('{0}2:url'.format(t.uid)) 38 | expect = '' 39 | assert result == expect 40 | 41 | result = t.encode_url('http://domain.tld/übermensch') 42 | expect = 'http://domain.tld/%C3%BCbermensch' 43 | assert result == expect 44 | 45 | result = t.parse('A link that starts with an h is "handled":/test/ incorrectly.') 46 | expect = '\tA link that starts with an h is handled incorrectly.
' 47 | assert result == expect 48 | 49 | result = t.parse('A link that starts with a space" raises":/test/ an exception.') 50 | expect = '\tA link that starts with a space” raises an exception.
' 51 | assert result == expect 52 | 53 | result = t.parse('A link that "contains a\nnewline":/test/ raises an exception.') 54 | expect = '\tA link that contains a\nnewline raises an exception.
' 55 | assert result == expect 56 | 57 | 58 | def test_rel_attribute(): 59 | t = Textile(rel='nofollow') 60 | result = t.parse('"$":http://domain.tld') 61 | expect = '\t' 62 | assert result == expect 63 | 64 | 65 | def test_quotes_in_link_text(): 66 | """quotes in link text are tricky.""" 67 | test = '""this is a quote in link text"":url' 68 | t = Textile() 69 | result = t.parse(test) 70 | expect = '\t“this is a quote in link text”
' 71 | assert result == expect 72 | -------------------------------------------------------------------------------- /tests/test_utils.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | from textile import utils 3 | 4 | 5 | def test_encode_html(): 6 | result = utils.encode_html('''this is a "test" of text that's safe to ''' 7 | 'put in an attribute.') 8 | expect = ('this is a "test" of text that's safe to put in ' 9 | 'an <html> attribute.') 10 | assert result == expect 11 | 12 | 13 | def test_has_raw_text(): 14 | assert utils.has_raw_text('foo bar biz baz
') is False 15 | assert utils.has_raw_text(' why yes, yes it does') is True 16 | 17 | 18 | def test_is_rel_url(): 19 | assert utils.is_rel_url("http://www.google.com/") is False 20 | assert utils.is_rel_url("/foo") is True 21 | 22 | 23 | def test_generate_tag(): 24 | result = utils.generate_tag('span', 'inner text', {'class': 'test'}) 25 | expect = 'inner text' 26 | assert result == expect 27 | 28 | text = 'Übermensch' 29 | attributes = {'href': 'http://de.wikipedia.org/wiki/%C3%C9bermensch'} 30 | expect = 'Übermensch' 31 | result = utils.generate_tag('a', text, attributes) 32 | assert result == expect 33 | 34 | 35 | def test_human_readable_url_edge_case(): 36 | assert utils.human_readable_url('google.com') == 'google.com' 37 | assert utils.human_readable_url('tel:1-800-555-1212') == '1-800-555-1212' 38 | -------------------------------------------------------------------------------- /tests/test_values.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | import textile 3 | import pytest 4 | 5 | xhtml_known_values = ( 6 | ('hello, world', '\thello, world
'), 7 | 8 | ('A single paragraph.\n\nFollowed by another.', 9 | '\tA single paragraph.
\n\n\tFollowed by another.
'), 10 | 11 | ('I am very serious.\n\n\nI am very serious.\n', 12 | '\t
I am very serious.
\n\n\nI am <b>very</b> serious.\n'), 13 | 14 | ('I spoke.\nAnd none replied.', '\t
I spoke.
\nAnd none replied.
“Observe!”
'), 17 | 18 | ('Observe -- very nice!', '\tObserve — very nice!
'), 19 | 20 | ('Observe - tiny and brief.', '\tObserve – tiny and brief.
'), 21 | 22 | ('Observe...', '\tObserve…
'), 23 | 24 | ('Observe ...', '\tObserve …
'), 25 | 26 | ('Observe: 2 x 2.', '\tObserve: 2 × 2.
'), 27 | 28 | ('one(TM), two(R), three(C).', '\tone™, two®, three©.
'), 29 | 30 | ('h1. Header 1', '\tAn old text
\n\n\t\n\t\t\n\n\tA block quotation.
\n\t
Any old text
'), 38 | 39 | ('I _believe_ every word.', '\tI believe every word.
'), 40 | 41 | ('And then? She *fell*!', '\tAnd then? She fell!
'), 42 | 43 | ('I __know__.\nI **really** __know__.', '\tI know.
\nI really know.
Cat’s Cradle by Vonnegut
'), 46 | 47 | ('Convert with @str(foo)@', '\tConvert with str(foo)
I’m sure not sure.
You are a pleasant child.
'), 52 | 53 | ('a ^2^ + b ^2^ = c ^2^', '\ta 2 + b 2 = c 2
'), 54 | 55 | ('log ~2~ x', '\tlog 2 x
'), 56 | 57 | ('I\'m %unaware% of most soft drinks.', '\tI’m unaware of most soft drinks.
'), 58 | 59 | ("I'm %{color:red}unaware%\nof most soft drinks.", '\tI’m unaware
\nof most soft drinks.
An example
'), 62 | 63 | ('p(#big-red). Red here', '\tRed here
'), 64 | 65 | ('p(example1#big-red2). Red here', '\tRed here
'), 66 | 67 | ('p{color:blue;margin:30px}. Spacey blue', '\tSpacey blue
'), 68 | 69 | ('p[fr]. rouge', '\trouge
'), 70 | 71 | ('I seriously *{color:red}blushed*\nwhen I _(big)sprouted_ that\ncorn stalk from my\n%[es]cabeza%.', 72 | '\tI seriously blushed
\nwhen I sprouted'
73 | ' that
\ncorn stalk from my
\ncabeza.
align left
'), 76 | 77 | ('p>. align right', '\talign right
'), 78 | 79 | ('p=. centered', '\tcentered
'), 80 | 81 | ('p<>. justified', '\tjustified
'), 82 | 83 | ('p(. left ident 1em', '\tleft ident 1em
'), 84 | 85 | ('p((. left ident 2em', '\tleft ident 2em
'), 86 | 87 | ('p))). right ident 3em', '\tright ident 3em
'), 88 | 89 | ('h2()>. Bingo.', '\t\n\na.gsub!( /\n',
94 | '\n\na.gsub!( /</, "" )\n\n'),
95 |
96 | ('The main text of the
\n'
100 | 'page goes here and will
\nstay to the left of the
\nsidebar.
I searched Google.
'), 115 | 116 | ('I searched "a search engine (Google)":http://google.com.', '\tI searched a search engine.
'), 117 | 118 | ('I am crazy about "Hobix":hobix\nand "it\'s":hobix "all":hobix I ever\n"link to":hobix!\n\n[hobix]http://hobix.com', 119 | '\tI am crazy about Hobix
\nand it’s '
120 | 'all I ever
\nlink to!
And others sat all round the small
\nmachine and paid it to sing to them.
We use CSS.
'), 133 | 134 | ('|one|two|three|\n|a|b|c|', 135 | '\t| one | \n\t\t\ttwo | \n\t\t\tthree | \n\t\t
| a | \n\t\t\tb | \n\t\t\tc | \n\t\t
| name | \n\t\t\tage | \n\t\t\tsex | \n\t\t
| joan | \n\t\t\t24 | \n\t\t\tf | \n\t\t
| archie | \n\t\t\t29 | \n\t\t\tm | \n\t\t
| bella | \n\t\t\t45 | \n\t\t\tf | \n\t\t
| name | \n\t\t\tage | \n\t\t\tsex | \n\t\t
|---|---|---|
| joan | \n\t\t\t24 | \n\t\t\tf | \n\t\t
| archie | \n\t\t\t29 | \n\t\t\tm | \n\t\t
| bella | \n\t\t\t45 | \n\t\t\tf | \n\t\t
Hello\n\nHello Again\n\n\t
normal text
'), 153 | 154 | ('this is in a pre tag', '
this is in a pre tag'), 155 | 156 | ('"test1":http://foo.com/bar--baz\n\n"test2":http://foo.com/bar---baz\n\n"test3":http://foo.com/bar-17-18-baz', 157 | '\t\n\n\t' 158 | '\n\n\t' 159 | ''), 160 | 161 | ('"foo ==(bar)==":#foobar', '\t'), 162 | 163 | ('!http://render.mathim.com/A%5EtAx%20%3D%20A%5Et%28Ax%29.!', 164 | '\t
array[4] = 8
Links (like this), are now mangled in 2.1.0, whereas 2.0 parsed them correctly.
'), 176 | 177 | ('@monospaced text@, followed by text', 178 | '\tmonospaced text, followed by text
some text
'), 181 | 182 | ('pre.. foo bar baz\nquux', 'foo bar baz\nquux'), 183 | 184 | ('line of text\n\n leading spaces', 185 | '\t
line of text
\n\n leading spaces'), 186 | 187 | ('"some text":http://www.example.com/?q=foo%20bar and more text', 188 | '\tsome text and more text
'), 189 | 190 | ('(??some text??)', '\t(some text)
'), 191 | 192 | ('(*bold text*)', '\t(bold text)
'), 193 | 194 | ('H[~2~]O', '\tH2O
'), 195 | 196 | ("p=. Où est l'école, l'église s'il vous plaît?", 197 | """\tOù est l’école, l’église s’il vous plaît?
"""), 198 | 199 | ("p=. *_The_* _*Prisoner*_", 200 | """\tThe Prisoner
"""), 201 | 202 | ("""p=. "An emphasised _word._" & "*A spanned phrase.*" """, 203 | """\t“An emphasised word.” & “A spanned phrase.”
"""), 204 | 205 | ("""p=. "*Here*'s a word!" """, 206 | """\t“Here’s a word!”
"""), 207 | 208 | ("""p=. "Please visit our "Textile Test Page":http://textile.sitemonks.com" """, 209 | """\t“Please visit our Textile Test Page”
"""), 210 | ("""| Foreign EXPÓŅÉNTIAL |""", 211 | """\t| Foreign EXPÓŅÉNTIAL | \n\t\t
Piękne ŹDŹBŁO
"""), 214 | 215 | ("""p=. Tell me, what is AJAX(Asynchronous Javascript and XML), please?""", 216 | """\tTell me, what is AJAX, please?
"""), 217 | ('p{font-size:0.8em}. *TxStyle* is a documentation project of Textile 2.4 for "Textpattern CMS":http://texpattern.com.', 218 | '\tTxStyle is a documentation project of Textile 2.4 for Textpattern CMS.
'), 219 | (""""Übermensch":http://de.wikipedia.org/wiki/Übermensch""", """\t"""), 220 | ("""Here is some text with a block.\n\n\n\n\n\nbc. """, 221 | """\tHere is some text with a block.
\n\n\n\n\n\n<!-- Here is a comment block in a code block. -->“Textile©” is a registered® ‘trademark’ of Textpattern™ — or TXP — at least it was – back in ’88 when 2×4 was ±5°C … QED!
\n\n\t2¼ 3½ 4¾
"""), 224 | ("""|=. Testing colgroup and col syntax\n|:\\5. 80\n|a|b|c|d|e|\n\n|=. Testing colgroup and col syntax|\n|:\\5. 80|\n|a|b|c|d|e|""", """\t| a | \n\t\t\tb | \n\t\t\tc | \n\t\t\td | \n\t\t\te | \n\t\t
| a | \n\t\t\tb | \n\t\t\tc | \n\t\t\td | \n\t\t\te | \n\t\t
| Title | \n\t\t\tStarring | \n\t\t\tDirector | \n\t\t\tWriter | \n\t\t\tNotes | \n\t\t
|---|---|---|---|---|
| This is the tfoot, centred | \n\t\t||||
| The Usual Suspects | \n\t\t\tBenicio Del Toro, Gabriel Byrne, Stephen Baldwin, Kevin Spacey | \n\t\t\tBryan Singer | \n\t\t\tChris McQaurrie | \n\t\t\tOne of the finest films ever made | \n\t\t
| Se7en | \n\t\t\tMorgan Freeman, Brad Pitt, Kevin Spacey | \n\t\t\tDavid Fincher | \n\t\t\tAndrew Kevin Walker | \n\t\t\tGreat psychological thriller | \n\t\t
| Primer | \n\t\t\tDavid Sullivan, Shane Carruth | \n\t\t\tShane Carruth | \n\t\t\tShane Carruth | \n\t\t\t Amazing insight into trust and human psychology \nrather than science fiction. Terrific! | \n\t\t
| District 9 | \n\t\t\tSharlto Copley, Jason Cope | \n\t\t\tNeill Blomkamp | \n\t\t\tNeill Blomkamp, Terri Tatchell | \n\t\t\t Social commentary layered on thick, \nbut boy is it done well | \n\t\t
| Arlington Road | \n\t\t\tTim Robbins, Jeff Bridges | \n\t\t\tMark Pellington | \n\t\t\tEhren Kruger | \n\t\t\tAwesome study in neighbourly relations | \n\t\t
| Phone Booth | \n\t\t\tColin Farrell, Kiefer Sutherland, Forest Whitaker | \n\t\t\tJoel Schumacher | \n\t\t\tLarry Cohen | \n\t\t\t Edge-of-the-seat stuff in this \nshort but brilliantly executed thriller | \n\t\t
Nourishing beverage for baby cows.
\nCold drink that goes great with cookies.
Here is a comment
\n\n\tHere is a comment
\n\n\tHere is a class that is a little extended and is
\nfollowed by a strong word!
; Content-type: text/javascript\n; Cache-Control: no-store, no-cache, must-revalidate, pre-check=0, post-check=0, max-age=0\n; Expires: Sat, 24 Jul 2003 05:00:00 GMT\n; Last-Modified: Wed, 1 Jan 2025 05:00:00 GMT\n; Pragma: no-cache123 test
\n\n\ttest 123
\n\n\t123 test
\n\n\ttest 123
"""), 233 | ("""#_(first#list) one\n# two\n# three\n\ntest\n\n#(ordered#list2).\n# one\n# two\n# three\n\ntest\n\n#_(class_4).\n# four\n# five\n# six\n\ntest\n\n#_ seven\n# eight\n# nine\n\ntest\n\n# one\n# two\n# three\n\ntest\n\n#22 22\n# 23\n# 24""", 234 | """\ttest
\n\n\ttest
\n\n\ttest
\n\n\ttest
\n\n\ttest
\n\n\ttest
\n\n\ttest
\n\n\t\t
| \n\t\t
\t
| \n\t\t
| \n\t\t
| table | \n\t\t\tmore | \n\t\t\tbadass | \n\t\t
|---|---|---|
| Horizontal span of 3 | \n\t\t||
| first | \n\t\t\tHAL | \n\t\t\t1 | \n\t\t
| some | \n\t\t\tstyled | \n\t\t\tcontent | \n\t\t
| spans 2 rows | \n\t\t\tthis is | \n\t\t\tquite a | \n\t\t
| deep test | \n\t\t\tdon’t you think? | \n\t\t|
| fifth | \n\t\t\tI’m a lumberjack | \n\t\t\t5 | \n\t\t
| sixth | \n\t\t\tbold italics | \n\t\t\t6 | \n\t\t
| strong | \n\t\t
| em | \n\t\t
| Inter-word | \n\t\t\tZIP-codes are 5- or 9-digit codes | \n\t\t
| attribute list | \n\t\t
|---|
| align left | \n\t\t
| align right | \n\t\t
| center | \n\t\t
| justify me | \n\t\t
| valign top | \n\t\t
| bottom | \n\t\t
Goodbye.
"""), 248 | ("""h2. A Definition list which covers the instance where a new definition list is created with a term without a definition\n\n- term :=\n- term2 := def""", """\t& test
'), 252 | ) 253 | 254 | # A few extra cases for HTML4 255 | html_known_values = ( 256 | ("pre.. The beginning\n\nbc.. This code\n\nis the last\n\nblock in the document\n", 257 | "The beginning\n\n
This code\n\nis the last\n\nblock in the documentThis code\n\nis not\n\nsurrounded by anythingParagraph 1\n\nParagraph 2\n\nParagraph 3post-code paragraph
"), 262 | ("bc.. Paragraph 1\n\nParagraph 2\n\nParagraph 3\n\npre.. post-code non-p block", 263 | "Paragraph 1\n\nParagraph 2\n\nParagraph 3post-code non-p block"), 264 | ('I spoke.\nAnd none replied.', '\t
I spoke.
\nAnd none replied.
I know.
\nI really know.
I’m unaware
\nof most soft drinks.
I seriously blushed
\nwhen I sprouted'
269 | ' that
\ncorn stalk from my
\ncabeza.
\n\na.gsub!( /\n',
271 | '\n\na.gsub!( /</, "" )\n\n'),
272 | ('The main text of the
\n'
276 | 'page goes here and will
\nstay to the left of the
\nsidebar.
I am crazy about Hobix
\nand it’s '
279 | 'all I ever
\nlink to!
And others sat all round the small
\nmachine and paid it to sing to them.
quux
'), 290 | ('"foo":http://google.com/one--two', '\t'), 291 | # issue 24 colspan 292 | ('|\\2. spans two cols |\n| col 1 | col 2 |', '\t| spans two cols | \n\t\t|
| col 1 | \n\t\t\tcol 2 | \n\t\t
Hello\n\nAgain\n\n\t
normal text
'), 297 | # url with parentheses 298 | ('"python":http://en.wikipedia.org/wiki/Python_(programming_language)', '\t'), 299 | # table with hyphen styles 300 | ('table(linkblog-thumbnail).\n|(linkblog-thumbnail-cell). apple|bear|', '\t| apple | \n\t\t\tbear | \n\t\t
| thing | \n\t\t\t\n\t\t\t | \n\t\t\t | otherthing | \n\t\t
test text
"), 308 | ("_*test text*_", "\ttest text
"), 309 | # quotes in code block 310 | ("'quoted string'", "\t'quoted string'
some preformatted textother text", "\t
some preformatted textother text"), 312 | # at sign and notextile in table 313 | ("|@
<A1> | \n\t\t\t<A2> <A3> | \n\t\t
| *B1* | \n\t\t\t*B2* *B3* | \n\t\t
\n\t\t'), 316 | ('Hello ["(Mum) & dad"]', '\tText…
\n\t
Hello [“(Mum) & dad”]
'), 317 | # Dimensions 318 | ( 319 | ('[1/2] x [1/4] and (1/2)" x [1/4]" and (1/2)\' x (1/4)\'\n\n' 320 | '(2 x 10) X (3 / 4) x (200 + 64)\n\n' 321 | '1 x 1 = 1\n\n' 322 | '1 x1 = 1\n\n' 323 | '1x 1 = 1\n\n' 324 | '1x1 = 1\n\n' 325 | '1 X 1 = 1\n\n' 326 | '1 X1 = 1\n\n' 327 | '1X 1 = 1\n\n' 328 | '1X1 = 1\n\n' 329 | 'What is 1 x 1?\n\n' 330 | 'What is 1x1?\n\n' 331 | 'What is 1 X 1?\n\n' 332 | 'What is 1X1?\n\n' 333 | '1 x 2 x 3 = 6\n\n' 334 | '1x2x3=6\n\n' 335 | '1x2 x 1x3 = 6\n\n' 336 | '2\' x 2\' = 4 sqft.\n\n' 337 | '2\'x 2\' = 4 sqft.\n\n' 338 | '2\' x2\' = 4 sqft.\n\n' 339 | '2\'x2\' = 4 sqft.\n\n' 340 | '2\' X 2\' = 4 sqft.\n\n' 341 | '2\'X 2\' = 4 sqft.\n\n' 342 | '2\' X2\' = 4 sqft.\n\n' 343 | '2\'X2\' = 4 sqft.\n\n' 344 | '2" x 2" = 4 sqin.\n\n' 345 | '2"x 2" = 4 sqin.\n\n' 346 | '2" x2" = 4 sqin.\n\n' 347 | '2"x2" = 4 sqin.\n\n' 348 | '2" X 2" = 4 sqin.\n\n' 349 | '2"X 2" = 4 sqin.\n\n' 350 | '2" X2" = 4 sqin.\n\n' 351 | '2"X2" = 4in[^2^].\n\n' 352 | 'What is 1.2 x 3.5?\n\n' 353 | 'What is .2 x .5?\n\n' 354 | 'What is 1.2x3.5?\n\n' 355 | 'What is .2x.5?\n\n' 356 | 'What is 1.2\' x3.5\'?\n\n' 357 | 'What is .2"x .5"?\n\n' 358 | '1 x $10.00 x -£ 1.23 x ¥20,000 x -¤120.00 x ฿1,000,000 x -€110,00\n\n'), 359 | 360 | ('\t½ × ¼ and ½” × ¼” and ½’ × ¼’
\n\n' 361 | '\t(2 × 10) × (3 / 4) × (200 + 64)
\n\n' 362 | '\t1 × 1 = 1
\n\n' 363 | '\t1 ×1 = 1
\n\n' 364 | '\t1× 1 = 1
\n\n' 365 | '\t1×1 = 1
\n\n' 366 | '\t1 × 1 = 1
\n\n' 367 | '\t1 ×1 = 1
\n\n' 368 | '\t1× 1 = 1
\n\n' 369 | '\t1×1 = 1
\n\n' 370 | '\tWhat is 1 × 1?
\n\n' 371 | '\tWhat is 1×1?
\n\n' 372 | '\tWhat is 1 × 1?
\n\n' 373 | '\tWhat is 1×1?
\n\n' 374 | '\t1 × 2 × 3 = 6
\n\n' 375 | '\t1×2×3=6
\n\n' 376 | '\t1×2 × 1×3 = 6
\n\n' 377 | '\t2’ × 2’ = 4 sqft.
\n\n' 378 | '\t2’× 2’ = 4 sqft.
\n\n' 379 | '\t2’ ×2’ = 4 sqft.
\n\n' 380 | '\t2’×2’ = 4 sqft.
\n\n' 381 | '\t2’ × 2’ = 4 sqft.
\n\n' 382 | '\t2’× 2’ = 4 sqft.
\n\n' 383 | '\t2’ ×2’ = 4 sqft.
\n\n' 384 | '\t2’×2’ = 4 sqft.
\n\n' 385 | '\t2” × 2” = 4 sqin.
\n\n' 386 | '\t2”× 2” = 4 sqin.
\n\n' 387 | '\t2” ×2” = 4 sqin.
\n\n' 388 | '\t2”×2” = 4 sqin.
\n\n' 389 | '\t2” × 2” = 4 sqin.
\n\n' 390 | '\t2”× 2” = 4 sqin.
\n\n' 391 | '\t2” ×2” = 4 sqin.
\n\n' 392 | '\t2”×2” = 4in2.
\n\n' 393 | '\tWhat is 1.2 × 3.5?
\n\n' 394 | '\tWhat is .2 × .5?
\n\n' 395 | '\tWhat is 1.2×3.5?
\n\n' 396 | '\tWhat is .2×.5?
\n\n' 397 | '\tWhat is 1.2’ ×3.5’?
\n\n' 398 | '\tWhat is .2”× .5”?
\n\n' 399 | '\t1 × $10.00 × -£ 1.23 × ¥20,000 × -¤120.00 × ฿1,000,000 × -€110,00
') 400 | ), 401 | # Empty note lists 402 | ('There should be nothing below.\n\nnotelist.', '\tThere should be nothing below.
\n\n\t'), 403 | # Empty things 404 | (('\'\'\n\n""\n\n%%\n\n^^\n\n&&\n\n**\n\n__\n\n--\n\n++\n\n~~\n\n{}\n\n' 405 | '[]\n\n()\n\n<>\n\n\\\\\n\n//\n\n??\n\n==\n\n@@\n\n##\n\n$$\n\n!!\n\n' 406 | '::\n\n;;\n\n..\n\n,,\n\n||\n\n` `\n\n\' \'\n\n" "\n\n% %\n\n^ ^\n\n' 407 | '& &\n\n* *\n\n_ _\n\n- -\n\n+ +\n\n~ ~\n\n{ }\n\n[ ]\n\n( )\n\n< >\n\n' 408 | '\\ \\\n\n/ /\n\n? ?\n\n= =\n\n@ @\n\n# #\n\n$ $\n\n! !\n\n: :\n\n; ;\n\n' 409 | '. .\n\n, ,'), 410 | ("\t‘’
\n\n\t“”
\n\n\t%%
\n\n\t^^
\n\n\t" 411 | "&&
\n\n\t**
\n\n\t__
\n\n\t—
\n\n\t++
\n\n\t" 412 | "~~
\n\n\t{}
\n\n\t[]
\n\n\t()
\n\n\t<>
\n\n\t\\\\
\n\n\t" 413 | "//
\n\n\t??
\n\n\t==
\n\n\t##
\n\n\t$$
\n\n\t" 414 | "!!
\n\n\t::
\n\n\t;;
\n\n\t..
\n\n\t,,
\n\n\t" 415 | "| \n\t\t |
` `
\n\n\t‘ ‘
\n\n\t" 416 | "“ “
\n\n\t% %
\n\n\t^ ^
\n\n\t& &
\n\n\t" 417 | "_ _
\n\n\t- -
\n\n\t+ +
\n\n\t~ ~
\n\n\t" 418 | "{ }
\n\n\t[ ]
\n\n\t( )
\n\n\t< >
\n\n\t\\ \\
\n\n\t" 419 | "/ /
\n\n\t? ?
\n\n\t= =
\n\n\t
$ $
\n\n\t! !
\n\n\t. .
\n\n\t, ,
")), 422 | # A lone standing comment must be preserved as is: 423 | # withouth wrapping it into a paragraph 424 | (('An ordinary block.\n\n' 425 | '\n'), 426 | '\tAn ordinary block.
\n\n'), 427 | # Headers must be "breakable", just like paragraphs. 428 | ('h1. Two line with *strong*\nheading\n', 429 | '\t“test”
\n\n" 435 | "\t“test”
\n\n" 436 | "\ttest
")), 437 | # Nested and mixed multi-level ordered and unordered lists 438 | (("* bullet\n" 439 | "*# number\n" 440 | "*# number\n" 441 | "*#* bullet\n" 442 | "*# number\n" 443 | "*# number with\n" 444 | "a break\n" 445 | "* bullet\n" 446 | "** okay"), 447 | ("\t
| \n"
474 | "\t\t
Here is a ‘spanned’ word.
'), 480 | # Using $-links with link aliases 481 | ("\"$\":test\n[test]https://textpattern.com/start\n", 482 | "\t"), 483 | ('Please check on "$":test for any updates.\n[test]https://de.wikipedia.org/wiki/Übermensch', 484 | '\tPlease check on de.wikipedia.org/wiki/Übermensch for any updates.
'), 485 | # Make sure smileys don't get recognised as a definition list. 486 | (":(\n\n:)\n\n:( \n:( \n:( \n:) \n\nPinocchio!\n:^)\n\nBaboon!\n:=)\n\nWink!\n;)\n\n:[ \n:]\n\n;(\nsomething\ndark side\n:) \n\n;(c)[de] Item", 487 | '\t:(
\n\n\t:)
\n\n\t:(
\n:(
\n:(
\n:)
Pinocchio!
\n:^)
Baboon!
\n:=)
Wink!
\n;)
:[
\n:]
;(
\nsomething
\ndark side
\n:)
text1 text2
 | \n\t\t\t | \n\t\t
| a | \n\t\t\tb | \n\t\t\tc | \n\t\t\td | \n\t\t\te | \n\t\t
| touch this! | \n\t\t\ttouch this! | \n\t\t
| a | \n\t\t\tb | \n\t\t\tc | \n\t\t\td | \n\t\t\te | \n\t\t
..
are added to line 441 | multiline_para = False 442 | 443 | tag = 'p' 444 | atts = cite = ext = '' 445 | 446 | out = [] 447 | 448 | for line in text: 449 | # the line is just whitespace, add it to the output, and move on 450 | if not line.strip(): 451 | if not eat_whitespace: 452 | out.append(line) 453 | continue 454 | 455 | eat_whitespace = False 456 | 457 | pattern = (r'^(?P\[)? # Optionally open with a square bracket eg. Look ["here":url]
810 | {0}linkStartMarker:" # marks start of the link
811 | (?P(?:.|\n)*?) # grab the content of the inner "..." part of the link, can be anything but
812 | # do not worry about matching class, id, lang or title yet
813 | ": # literal ": marks end of atts + text + title block
814 | (?P[^{1}]*) # url upto a stopchar
815 | """.format(self.uid, stopchars)
816 | text = re.compile(pattern, flags=re.X | re.U).sub(self.fLink, text)
817 | return text
818 |
819 | def fLink(self, m):
820 | in_ = m.group()
821 | pre, inner, url = m.groups()
822 | pre = pre or ''
823 |
824 | if inner == '':
825 | return '{0}"{1}":{2}'.format(pre, inner, url)
826 |
827 | m = re.search(r'''^
828 | (?P{0}) # $atts (if any)
829 | {1}* # any optional spaces
830 | (?P # $text is...
831 | (!.+!) # an image
832 | | # else...
833 | .+? # link text
834 | ) # end of $text
835 | (?:\((?P[^)]+?)\))? # $title (if any)
836 | $'''.format(cls_re_s, regex_snippets['space']), inner,
837 | flags=re.X | re.U)
838 |
839 | atts = (m and m.group('atts')) or ''
840 | text = (m and m.group('text')) or inner
841 | title = (m and m.group('title')) or ''
842 |
843 | pop, tight = '', ''
844 | counts = {'[': None, ']': url.count(']'), '(': None, ')': None}
845 |
846 | # Look for footnotes or other square-bracket delimited stuff at the end
847 | # of the url...
848 | #
849 | # eg. "text":url][otherstuff... will have "[otherstuff" popped back
850 | # out.
851 | #
852 | # "text":url?q[]=x][123] will have "[123]" popped off the back, the
853 | # remaining closing square brackets will later be tested for balance
854 | if (counts[']']):
855 | m = re.search(r'(?P<url>^.*\])(?P<tight>\[.*?)$', url, flags=re.U)
856 | if m:
857 | url, tight = m.groups()
858 |
859 | # Split off any trailing text that isn't part of an array assignment.
860 | # eg. "text":...?q[]=value1&q[]=value2 ... is ok
861 | # "text":...?q[]=value1]following ... would have "following" popped
862 | # back out and the remaining square bracket will later be tested for
863 | # balance
864 | if (counts[']']):
865 | m = re.search(r'(?P<url>^.*\])(?!=)(?P<end>.*?)$', url, flags=re.U)
866 | url = m.group('url')
867 | tight = '{0}{1}'.format(m.group('end'), tight)
868 |
869 | # Now we have the array of all the multi-byte chars in the url we will
870 | # parse the uri backwards and pop off any chars that don't belong
871 | # there (like . or , or unmatched brackets of various kinds).
872 | first = True
873 | popped = True
874 |
875 | counts[']'] = url.count(']')
876 | url_chars = list(url)
877 |
878 | def _endchar(c, pop, popped, url_chars, counts, pre):
879 | """Textile URL shouldn't end in these characters, we pop them off
880 | the end and push them out the back of the url again."""
881 | pop = '{0}{1}'.format(c, pop)
882 | url_chars.pop()
883 | popped = True
884 | return pop, popped, url_chars, counts, pre
885 |
886 | def _rightanglebracket(c, pop, popped, url_chars, counts, pre):
887 | url_chars.pop()
888 | urlLeft = ''.join(url_chars)
889 |
890 | m = re.search(r'(?P<url_chars>.*)(?P<tag><\/[a-z]+)$', urlLeft)
891 | url_chars = m.group('url_chars')
892 | pop = '{0}{1}{2}'.format(m.group('tag'), c, pop)
893 | popped = True
894 | return pop, popped, url_chars, counts, pre
895 |
896 | def _closingsquarebracket(c, pop, popped, url_chars, counts, pre):
897 | """If we find a closing square bracket we are going to see if it is
898 | balanced. If it is balanced with matching opening bracket then it
899 | is part of the URL else we spit it back out of the URL."""
900 | # If counts['['] is None, count the occurrences of '['
901 | counts['['] = counts['['] or url.count('[')
902 |
903 | if counts['['] == counts[']']:
904 | # It is balanced, so keep it
905 | url_chars.append(c)
906 | else:
907 | # In the case of un-matched closing square brackets we just eat
908 | # it
909 | popped = True
910 | url_chars.pop()
911 | counts[']'] = counts[']'] - 1
912 | if first: # pragma: no branch
913 | pre = ''
914 | return pop, popped, url_chars, counts, pre
915 |
916 | def _closingparenthesis(c, pop, popped, url_chars, counts, pre):
917 | if counts[')'] is None: # pragma: no branch
918 | counts['('] = url.count('(')
919 | counts[')'] = url.count(')')
920 |
921 | if counts['('] != counts[')']:
922 | # Unbalanced so spit it out the back end
923 | popped = True
924 | pop = '{0}{1}'.format(url_chars.pop(), pop)
925 | counts[')'] = counts[')'] - 1
926 | return pop, popped, url_chars, counts, pre
927 |
928 | def _casesdefault(c, pop, popped, url_chars, counts, pre):
929 | return pop, popped, url_chars, counts, pre
930 |
931 | cases = {
932 | '!': _endchar,
933 | '?': _endchar,
934 | ':': _endchar,
935 | ';': _endchar,
936 | '.': _endchar,
937 | ',': _endchar,
938 | '>': _rightanglebracket,
939 | ']': _closingsquarebracket,
940 | ')': _closingparenthesis,
941 | }
942 | for c in url_chars[-1::-1]: # pragma: no branch
943 | popped = False
944 | pop, popped, url_chars, counts, pre = cases.get(
945 | c, _casesdefault)(c, pop, popped, url_chars, counts, pre)
946 | first = False
947 | if popped is False:
948 | break
949 |
950 | url = ''.join(url_chars)
951 | uri_parts = urlsplit(url)
952 |
953 | scheme_in_list = uri_parts.scheme in self.url_schemes
954 | valid_scheme = (uri_parts.scheme and scheme_in_list)
955 | if not is_valid_url(url) and not valid_scheme:
956 | return in_.replace('{0}linkStartMarker:'.format(self.uid), '')
957 |
958 | if text == '$':
959 | if valid_scheme:
960 | text = human_readable_url(url)
961 | else:
962 | ref_url = self.urlrefs.get(url)
963 | if ref_url is not None:
964 | text = human_readable_url(ref_url)
965 | else:
966 | text = url
967 |
968 | text = text.strip()
969 | title = encode_html(title)
970 |
971 | if not self.noimage: # pragma: no branch
972 | text = self.image(text)
973 | text = self.span(text)
974 | text = self.glyphs(text)
975 | url = self.shelveURL(self.encode_url(urlunsplit(uri_parts)))
976 | attributes = parse_attributes(atts, restricted=self.restricted)
977 | attributes['href'] = url
978 | if title:
979 | # if the title contains unicode data, it is annoying to get Python
980 | # 2.6 and all the latter versions working properly. But shelving
981 | # the title is a quick and dirty solution.
982 | attributes['title'] = self.shelve(title)
983 | if self.rel:
984 | attributes['rel'] = self.rel
985 | a_text = generate_tag('a', text, attributes)
986 | a_shelf_id = self.shelve(a_text)
987 |
988 | out = '{0}{1}{2}{3}'.format(pre, a_shelf_id, pop, tight)
989 |
990 | return out
991 |
992 | def encode_url(self, url):
993 | """
994 | Converts a (unicode) URL to an ASCII URL, with the domain part
995 | IDNA-encoded and the path part %-encoded (as per RFC 3986).
996 |
997 | Fixed version of the following code fragment from Stack Overflow:
998 | http://stackoverflow.com/a/804380/72656
999 | """
1000 | # parse it
1001 | parsed = urlsplit(url)
1002 |
1003 | if parsed.netloc:
1004 | # divide the netloc further
1005 | netloc_pattern = re.compile(r"""
1006 | (?:(?P<user>[^:@]+)(?::(?P<password>[^:@]+))?@)?
1007 | (?P<host>[^:]+)
1008 | (?::(?P<port>[0-9]+))?
1009 | """, re.X | re.U)
1010 | netloc_parsed = netloc_pattern.match(parsed.netloc).groupdict()
1011 | else:
1012 | netloc_parsed = {'user': '', 'password': '', 'host': '', 'port': ''}
1013 |
1014 | # encode each component
1015 | scheme = parsed.scheme
1016 | user = netloc_parsed['user'] and quote(netloc_parsed['user'])
1017 | password = (
1018 | netloc_parsed['password'] and quote(netloc_parsed['password'])
1019 | )
1020 | host = netloc_parsed['host']
1021 | port = netloc_parsed['port'] and netloc_parsed['port']
1022 | # the below splits the path portion of the url by slashes, translates
1023 | # percent-encoded characters back into strings, then re-percent-encodes
1024 | # what's necessary. Sounds screwy, but the url could include encoded
1025 | # slashes, and this is a way to clean that up. It branches for PY2/3
1026 | # because the quote and unquote functions expects different input
1027 | # types: unicode strings for PY2 and str for PY3.
1028 | path_parts = (quote(unquote(pce), b'') for pce in
1029 | parsed.path.split('/'))
1030 | path = '/'.join(path_parts)
1031 |
1032 | # put it back together
1033 | netloc = ''
1034 | if user:
1035 | netloc = '{0}{1}'.format(netloc, user)
1036 | if password:
1037 | netloc = '{0}:{1}'.format(netloc, password)
1038 | netloc = '{0}@'.format(netloc)
1039 | netloc = '{0}{1}'.format(netloc, host)
1040 | if port:
1041 | netloc = '{0}:{1}'.format(netloc, port)
1042 | return urlunsplit((scheme, netloc, path, parsed.query, parsed.fragment))
1043 |
1044 | def span(self, text):
1045 | qtags = (r'\*\*', r'\*', r'\?\?', r'\-', r'__',
1046 | r'_', r'%', r'\+', r'~', r'\^')
1047 | pnct = r""".,"'?!;:‹›«»„“”‚‘’"""
1048 | self.span_depth = self.span_depth + 1
1049 |
1050 | if self.span_depth <= self.max_span_depth:
1051 | for tag in qtags:
1052 | pattern = re.compile(r"""
1053 | (?P<pre>^|(?<=[\s>{pnct}\(])|[{{[])
1054 | (?P<tag>{tag})(?!{tag})
1055 | (?P<atts>{cls})
1056 | (?!{tag})
1057 | (?::(?P<cite>\S+[^{tag}]{space}))?
1058 | (?P<content>[^{space}{tag}]+|\S.*?[^\s{tag}\n])
1059 | (?P<end>[{pnct}]*)
1060 | {tag}
1061 | (?P<tail>$|[\[\]}}<]|(?=[{pnct}]{{1,2}}[^0-9]|\s|\)))
1062 | """.format(
1063 | **{'tag': tag, 'cls': cls_re_s, 'pnct': pnct, 'space':
1064 | regex_snippets['space']}
1065 | ), flags=re.X | re.U)
1066 | text = pattern.sub(self.fSpan, text)
1067 | self.span_depth = self.span_depth - 1
1068 | return text
1069 |
1070 | def getSpecialOptions(self, pre, tail):
1071 | for before, after in self.spanWrappers:
1072 | if pre == before and tail == after:
1073 | pre = tail = ''
1074 | break
1075 | return (pre, tail)
1076 |
1077 | def fSpan(self, match):
1078 | pre, tag, atts, cite, content, end, tail = match.groups()
1079 | pre, tail = self.getSpecialOptions(pre, tail)
1080 |
1081 | qtags = {
1082 | '*': 'strong', # noqa: E241
1083 | '**': 'b', # noqa: E241
1084 | '??': 'cite', # noqa: E241
1085 | '_': 'em', # noqa: E241
1086 | '__': 'i', # noqa: E241
1087 | '-': 'del', # noqa: E241
1088 | '%': 'span', # noqa: E241
1089 | '+': 'ins', # noqa: E241
1090 | '~': 'sub', # noqa: E241
1091 | '^': 'sup' # noqa: E241
1092 | }
1093 |
1094 | tag = qtags[tag]
1095 | atts = pba(atts, restricted=self.restricted)
1096 | if cite:
1097 | atts = '{0} cite="{1}"'.format(atts, cite.rstrip())
1098 |
1099 | content = self.span(content)
1100 | opentag = '<{0}{1}>'.format(tag, atts)
1101 | closetag = '</{0}>'.format(tag)
1102 | tags = self.storeTags(opentag, closetag)
1103 | return pre + tags['open'] + content + end + tags['close'] + tail
1104 |
1105 | def storeTags(self, opentag, closetag=''):
1106 | tags = {}
1107 | self.refIndex += 1
1108 | self.refCache[self.refIndex] = opentag
1109 | tags['open'] = self.uid + str(self.refIndex) + ':ospan '
1110 |
1111 | self.refIndex += 1
1112 | self.refCache[self.refIndex] = closetag
1113 | tags['close'] = ' ' + self.uid + str(self.refIndex) + ':cspan'
1114 | return tags
1115 |
1116 | def retrieveTags(self, text):
1117 | text = (re.compile('{0}(?P<token>[0-9]+):ospan '.format(self.uid), re.U)
1118 | .sub(self.fRetrieveTags, text))
1119 | text = (re.compile(' {0}(?P<token>[0-9]+):cspan'.format(self.uid), re.U)
1120 | .sub(self.fRetrieveTags, text))
1121 | return text
1122 |
1123 | def fRetrieveTags(self, match):
1124 | return self.refCache[int(match.group('token'))]
1125 |
1126 | def image(self, text):
1127 | pattern = re.compile(r"""
1128 | (?:[\[{{])? # pre
1129 | \! # opening !
1130 | (\<|\=|\>)? # optional alignment atts
1131 | ({0}) # optional style,class atts
1132 | (?:\.\s)? # optional dot-space
1133 | ([^\s(!]+) # presume this is the src
1134 | \s? # optional space
1135 | (?:\(([^\)]+)\))? # optional title
1136 | \! # closing
1137 | (?::(\S+)(?<![\]).,]))? # optional href sans final punct
1138 | (?:[\]}}]|(?=[.,\s)|]|$)) # lookahead: space or end of string
1139 | """.format(cls_re_s), re.U | re.X)
1140 | return pattern.sub(self.fImage, text)
1141 |
1142 | def fImage(self, match):
1143 | # (None, '', '/imgs/myphoto.jpg', None, None)
1144 | align, attributes, url, title, href = match.groups()
1145 | atts = OrderedDict()
1146 | size = None
1147 |
1148 | alignments = {'<': 'left', '=': 'center', '>': 'right'}
1149 |
1150 | if not title:
1151 | title = ''
1152 |
1153 | if not is_rel_url(url) and self.get_sizes:
1154 | size = getimagesize(url)
1155 |
1156 | if href:
1157 | href = self.shelveURL(href)
1158 |
1159 | url = self.shelveURL(url)
1160 |
1161 | if align:
1162 | atts.update(align=alignments[align])
1163 | atts.update(alt=title)
1164 | if size:
1165 | atts.update(height="{0}".format(size[1]))
1166 | atts.update(src=url)
1167 | if attributes:
1168 | atts.update(parse_attributes(attributes, restricted=self.restricted))
1169 | if title:
1170 | atts.update(title=title)
1171 | if size:
1172 | atts.update(width="{0}".format(size[0]))
1173 | img = generate_tag('img', ' /', atts)
1174 | if href:
1175 | a_atts = OrderedDict(href=href)
1176 | if self.rel:
1177 | a_atts.update(rel=self.rel)
1178 | img = generate_tag('a', img, a_atts)
1179 | return img
1180 |
1181 | def code(self, text):
1182 | text = self.doSpecial(text, '<code>', '</code>', self.fCode)
1183 | text = self.doSpecial(text, '@', '@', self.fCode)
1184 | text = self.doSpecial(text, '<pre>', '</pre>', self.fPre)
1185 | return text
1186 |
1187 | def fCode(self, match):
1188 | before, text, after = match.groups()
1189 | after = after or ''
1190 | before, after = self.getSpecialOptions(before, after)
1191 | # text needs to be escaped
1192 | text = encode_html(text, quotes=False)
1193 | return ''.join([before, self.shelve('<code>{0}</code>'.format(text)), after])
1194 |
1195 | def fPre(self, match):
1196 | before, text, after = match.groups()
1197 | if after is None:
1198 | after = ''
1199 | before, after = self.getSpecialOptions(before, after)
1200 | # text needs to be escaped
1201 | text = encode_html(text)
1202 | return ''.join([before, '<pre>', self.shelve(text), '</pre>', after])
1203 |
1204 | def doSpecial(self, text, start, end, method):
1205 | pattern = re.compile(r'(^|\s|[\[({{>|]){0}(.*?){1}($|[\])}}])?'.format(
1206 | re.escape(start), re.escape(end)), re.M | re.S)
1207 | return pattern.sub(method, text)
1208 |
1209 | def noTextile(self, text):
1210 | text = self.doSpecial(text, '<notextile>', '</notextile>',
1211 | self.fTextile)
1212 | return self.doSpecial(text, '==', '==', self.fTextile)
1213 |
1214 | def fTextile(self, match):
1215 | before, notextile, after = match.groups()
1216 | if after is None: # pragma: no branch
1217 | after = ''
1218 | before, after = self.getSpecialOptions(before, after)
1219 | return ''.join([before, self.shelve(notextile), after])
1220 |
1221 | def getHTMLComments(self, text):
1222 | """Search the string for HTML comments, e.g. <!-- comment text -->. We
1223 | send the text that matches this to fParseHTMLComments."""
1224 | return self.doSpecial(text, '<!--', '-->', self.fParseHTMLComments)
1225 |
1226 | def fParseHTMLComments(self, match):
1227 | """If self.restricted is True, clean the matched contents of the HTML
1228 | comment. Otherwise, return the comments unchanged.
1229 | The original php had an if statement in here regarding restricted mode.
1230 | nose reported that this line wasn't covered. It's correct. In
1231 | restricted mode, the html comment tags have already been converted to
1232 | <!*#8212; and —> so they don't match in getHTMLComments,
1233 | and never arrive here.
1234 | """
1235 | before, commenttext, after = match.groups()
1236 | commenttext = self.shelve(commenttext)
1237 | return '{0}<!--{1}-->'.format(before, commenttext)
1238 |
1239 | def redcloth_list(self, text):
1240 | """Parse the text for definition lists and send them to be
1241 | formatted."""
1242 | pattern = re.compile(r"^([-]+{0}[ .].*:=.*)$(?![^-])".format(cls_re_s),
1243 | re.M | re.U | re.S)
1244 | return pattern.sub(self.fRCList, text)
1245 |
1246 | def fRCList(self, match):
1247 | """Format a definition list."""
1248 | out = []
1249 | text = re.split(r'\n(?=[-])', match.group(), flags=re.M)
1250 | for line in text:
1251 | # parse the attributes and content
1252 | m = re.match(r'^[-]+({0})[ .](.*)$'.format(cls_re_s), line,
1253 | flags=re.M | re.S)
1254 | if not m:
1255 | continue
1256 |
1257 | atts, content = m.groups()
1258 | # cleanup
1259 | content = content.strip()
1260 | atts = pba(atts, restricted=self.restricted)
1261 |
1262 | # split the content into the term and definition
1263 | xm = re.match(
1264 | r'^(.*?){0}*:=(.*?){0}*(=:|:=)?{0}*$'
1265 | .format(regex_snippets['space']),
1266 | content,
1267 | re.S)
1268 | term, definition, _ = xm.groups()
1269 | # cleanup
1270 | term = term.strip()
1271 | definition = definition.strip(' ')
1272 |
1273 | # if this is the first time through, out as a bool is False
1274 | if not out:
1275 | if definition == '':
1276 | dltag = "<dl{0}>".format(atts)
1277 | else:
1278 | dltag = "<dl>"
1279 | out.append(dltag)
1280 |
1281 | if term != '':
1282 | is_newline_started_def = definition.startswith('\n')
1283 | definition = (
1284 | definition
1285 | .strip()
1286 | .replace('\n', '<br />'))
1287 |
1288 | if is_newline_started_def:
1289 | definition = '<p>{0}</p>'.format(definition)
1290 | term = term.replace('\n', '<br />')
1291 |
1292 | term = self.graf(term)
1293 | definition = self.graf(definition)
1294 |
1295 | out.append('\t<dt{0}>{1}</dt>'.format(atts, term))
1296 | if definition:
1297 | out.append('\t<dd>{0}</dd>'.format(definition))
1298 |
1299 | out.append('</dl>')
1300 | out = '\n'.join(out)
1301 | return out
1302 |
1303 | def placeNoteLists(self, text):
1304 | """Parse the text for endnotes."""
1305 | if self.notes:
1306 | o = OrderedDict()
1307 | for label, info in self.notes.items():
1308 | if 'seq' in info:
1309 | i = info['seq']
1310 | info['seq'] = label
1311 | o[i] = info
1312 | else:
1313 | self.unreferencedNotes[label] = info
1314 |
1315 | if o: # pragma: no branch
1316 | # sort o by key
1317 | o = OrderedDict(sorted(o.items(), key=lambda t: t[0]))
1318 | self.notes = o
1319 | text_re = re.compile(r'<p>notelist({0})(?:\:([\w|{1}]))?([\^!]?)(\+?)'
1320 | r'\.?[\s]*</p>'.format(cls_re_s, syms_re_s), re.U)
1321 | text = text_re.sub(self.fNoteLists, text)
1322 | return text
1323 |
1324 | def fNoteLists(self, match):
1325 | """Given the text that matches as a note, format it into HTML."""
1326 | att, start_char, g_links, extras = match.groups()
1327 | start_char = start_char or 'a'
1328 | index = '{0}{1}{2}'.format(g_links, extras, start_char)
1329 | result = ''
1330 |
1331 | if index not in self.notelist_cache: # pragma: no branch
1332 | o = []
1333 | if self.notes: # pragma: no branch
1334 | for seq, info in self.notes.items():
1335 | links = self.makeBackrefLink(info, g_links, start_char)
1336 | atts = ''
1337 | if 'def' in info:
1338 | infoid = info['id']
1339 | atts = info['def']['atts']
1340 | content = info['def']['content']
1341 | li = ('\t\t<li{0}>{1}<span id="note{2}"> '
1342 | '</span>{3}</li>').format(atts, links, infoid,
1343 | content)
1344 | else:
1345 | li = ('\t\t<li{0}>{1} Undefined Note [#{2}].</li>'
1346 | ).format(atts, links, info['seq'])
1347 | o.append(li)
1348 | if '+' == extras and self.unreferencedNotes:
1349 | for seq, info in self.unreferencedNotes.items():
1350 | atts = info['def']['atts']
1351 | content = info['def']['content']
1352 | li = '\t\t<li{0}>{1}</li>'.format(atts, content)
1353 | o.append(li)
1354 | self.notelist_cache[index] = "\n".join(o)
1355 | result = self.notelist_cache[index]
1356 | if result:
1357 | list_atts = pba(att, restricted=self.restricted)
1358 | result = '<ol{0}>\n{1}\n\t</ol>'.format(list_atts, result)
1359 | return result
1360 |
1361 | def makeBackrefLink(self, info, g_links, i):
1362 | """Given the pieces of a back reference link, create an <a> tag."""
1363 | link = ''
1364 | if 'def' in info:
1365 | link = info['def']['link']
1366 | backlink_type = link or g_links
1367 | i_ = encode_high(i)
1368 | allow_inc = i not in syms_re_s
1369 | i_ = int(i_)
1370 |
1371 | if backlink_type == "!":
1372 | return ''
1373 | elif backlink_type == '^':
1374 | return """<sup><a href="#noteref{0}">{1}</a></sup>""".format(
1375 | info['refids'][0], i)
1376 | else:
1377 | result = []
1378 | for refid in info['refids']:
1379 | i_entity = decode_high(i_)
1380 | sup = """<sup><a href="#noteref{0}">{1}</a></sup>""".format(
1381 | refid, i_entity)
1382 | if allow_inc:
1383 | i_ = i_ + 1
1384 | result.append(sup)
1385 | result = ' '.join(result)
1386 | return result
1387 |
1388 | def fParseNoteDefs(self, m):
1389 | """Parse the note definitions and format them as HTML"""
1390 | label = m.group('label')
1391 | link = m.group('link')
1392 | att = m.group('att')
1393 | content = m.group('content')
1394 |
1395 | # Assign an id if the note reference parse hasn't found the label yet.
1396 | if label not in self.notes:
1397 | self.notes[label] = {'id': '{0}{1}'.format(
1398 | self.linkPrefix, self._increment_link_index())}
1399 |
1400 | # Ignores subsequent defs using the same label
1401 | if 'def' not in self.notes[label]: # pragma: no branch
1402 | self.notes[label]['def'] = {
1403 | 'atts': pba(att, restricted=self.restricted), 'content':
1404 | self.graf(content), 'link': link}
1405 | return ''
1406 |
1407 | def noteRef(self, text):
1408 | """Search the text looking for note references."""
1409 | text_re = re.compile(r"""
1410 | \[ # start
1411 | ({0}) # !atts
1412 | \#
1413 | ([^\]!]+) # !label
1414 | ([!]?) # !nolink
1415 | \]""".format(cls_re_s), re.X)
1416 | text = text_re.sub(self.fParseNoteRefs, text)
1417 | return text
1418 |
1419 | def fParseNoteRefs(self, match):
1420 | """Parse and format the matched text into note references.
1421 | By the time this function is called, all the defs will have been
1422 | processed into the notes array. So now we can resolve the link numbers
1423 | in the order we process the refs..."""
1424 | atts, label, nolink = match.groups()
1425 | atts = pba(atts, restricted=self.restricted)
1426 | nolink = nolink == '!'
1427 |
1428 | # Assign a sequence number to this reference if there isn't one already
1429 | if label in self.notes:
1430 | num = self.notes[label]['seq']
1431 | else:
1432 | self.notes[label] = {
1433 | 'seq': self.note_index, 'refids': [], 'id': ''
1434 | }
1435 | num = self.note_index
1436 | self.note_index = self.note_index + 1
1437 |
1438 | # Make our anchor point and stash it for possible use in backlinks when
1439 | # the note list is generated later...
1440 | refid = '{0}{1}'.format(self.linkPrefix, self._increment_link_index())
1441 | self.notes[label]['refids'].append(refid)
1442 |
1443 | # If we are referencing a note that hasn't had the definition parsed
1444 | # yet, then assign it an ID...
1445 | if not self.notes[label]['id']:
1446 | self.notes[label]['id'] = '{0}{1}'.format(
1447 | self.linkPrefix, self._increment_link_index())
1448 | labelid = self.notes[label]['id']
1449 |
1450 | # Build the link (if any)...
1451 | result = '<span id="noteref{0}">{1}</span>'.format(refid, num)
1452 | if not nolink:
1453 | result = '<a href="#note{0}">{1}</a>'.format(labelid, result)
1454 |
1455 | # Build the reference...
1456 | result = '<sup{0}>{1}</sup>'.format(atts, result)
1457 | return result
1458 |
1459 | def shelveURL(self, text):
1460 | if text == '':
1461 | return ''
1462 | self.refIndex = self.refIndex + 1
1463 | self.refCache[self.refIndex] = text
1464 | output = '{0}{1}{2}'.format(self.uid, self.refIndex, ':url')
1465 | return output
1466 |
1467 | def retrieveURLs(self, text):
1468 | return re.sub(r'{0}(?P<token>[0-9]+):url'.format(self.uid), self.retrieveURL, text)
1469 |
1470 | def retrieveURL(self, match):
1471 | url = self.refCache.get(int(match.group('token')), '')
1472 | if url == '':
1473 | return url
1474 |
1475 | if url in self.urlrefs:
1476 | url = self.urlrefs[url]
1477 |
1478 | return url
1479 |
1480 | def _increment_link_index(self):
1481 | """The self.linkIndex property needs to be incremented in various
1482 | places. Don't Repeat Yourself."""
1483 | self.linkIndex = self.linkIndex + 1
1484 | return self.linkIndex
1485 |
1486 |
1487 | def textile(text, html_type='xhtml'):
1488 | """
1489 | Apply Textile to a block of text.
1490 |
1491 | This function takes the following additional parameters:
1492 |
1493 | html_type - 'xhtml' or 'html5' style tags (default: 'xhtml')
1494 |
1495 | """
1496 | return Textile(html_type=html_type).parse(text)
1497 |
1498 |
1499 | def textile_restricted(text, lite=True, noimage=True, html_type='xhtml'):
1500 | """
1501 | Apply Textile to a block of text, with restrictions designed for weblog
1502 | comments and other untrusted input. Raw HTML is escaped, style attributes
1503 | are disabled, and rel='nofollow' is added to external links.
1504 |
1505 | This function takes the following additional parameters:
1506 |
1507 | html_type - 'xhtml' or 'html5' style tags (default: 'xhtml')
1508 | lite - restrict block tags to p, bq, and bc, disable tables (default: True)
1509 | noimage - disable image tags (default: True)
1510 |
1511 | """
1512 | return Textile(restricted=True, lite=lite, noimage=noimage,
1513 | html_type=html_type, rel='nofollow').parse(text)
1514 |
--------------------------------------------------------------------------------
/textile/objects/__init__.py:
--------------------------------------------------------------------------------
1 | from .block import Block
2 | from .table import Table
3 |
4 | __all__ = ['Block', 'Table']
5 |
--------------------------------------------------------------------------------
/textile/objects/block.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | from collections import OrderedDict
3 | try:
4 | import regex as re
5 | except ImportError:
6 | import re
7 |
8 | from textile.regex_strings import cls_re_s, regex_snippets
9 | from textile.utils import encode_html, generate_tag, parse_attributes
10 |
11 |
12 | class Block(object):
13 | def __init__(self, textile, tag, atts, ext, cite, content):
14 | self.textile = textile
15 | self.tag = tag
16 | self.atts = atts
17 | self.ext = ext
18 | self.cite = cite
19 | self.content = content
20 |
21 | self.attributes = parse_attributes(atts, restricted=self.textile.restricted)
22 | self.outer_tag = ''
23 | self.inner_tag = ''
24 | self.outer_atts = OrderedDict()
25 | self.inner_atts = OrderedDict()
26 | self.eat = False
27 | self.process()
28 |
29 | def process(self):
30 | if self.tag == 'p':
31 | # is this an anonymous block with a note definition?
32 | notedef_re = re.compile(r"""
33 | ^note\# # start of note def marker
34 | (?P<label>[^%<*!@\#^([{{ {space}.]+) # label
35 | (?P<link>[*!^]?) # link
36 | (?P<att>{cls}) # att
37 | \.? # optional period.
38 | [{space}]+ # whitespace ends def marker
39 | (?P<content>.*)$ # content""".format(
40 | space=regex_snippets['space'], cls=cls_re_s),
41 | flags=re.X | re.U)
42 | notedef = notedef_re.sub(self.textile.fParseNoteDefs, self.content)
43 |
44 | # It will be empty if the regex matched and ate it.
45 | if '' == notedef:
46 | self.content = notedef
47 | self.eat = True
48 |
49 | fns = re.search(r'fn(?P<fnid>{0}+)'.format(regex_snippets['digit']),
50 | self.tag, flags=re.U)
51 | if fns:
52 | self.tag = 'p'
53 | fnid = self.textile.fn.get(fns.group('fnid'), None)
54 | if fnid is None:
55 | fnid = '{0}{1}'.format(self.textile.linkPrefix,
56 | self.textile._increment_link_index())
57 |
58 | # If there is an author-specified ID goes on the wrapper & the
59 | # auto-id gets pushed to the <sup>
60 | supp_id = OrderedDict()
61 |
62 | # if class has not been previously specified, set it to "footnote"
63 | if 'class' not in self.attributes:
64 | self.attributes.update({'class': 'footnote'})
65 |
66 | # if there's no specified id, use the generated one.
67 | if 'id' not in self.attributes:
68 | self.attributes.update({'id': 'fn{0}'.format(fnid)})
69 | else:
70 | supp_id = parse_attributes('(#fn{0})'.format(fnid), restricted=self.textile.restricted)
71 |
72 | if '^' not in self.atts:
73 | sup = generate_tag('sup', fns.group('fnid'), supp_id)
74 | else:
75 | fnrev = generate_tag('a', fns.group('fnid'), {'href':
76 | '#fnrev{0}'.format(fnid)})
77 | sup = generate_tag('sup', fnrev, supp_id)
78 |
79 | self.content = '{0} {1}'.format(sup, self.content)
80 |
81 | if self.tag == 'bq':
82 | if self.cite:
83 | self.cite = self.textile.shelveURL(self.cite)
84 | cite_att = OrderedDict(cite=self.cite)
85 | self.cite = ' cite="{0}"'.format(self.cite)
86 | else:
87 | self.cite = ''
88 | cite_att = OrderedDict()
89 | cite_att.update(self.attributes)
90 | self.outer_tag = 'blockquote'
91 | self.outer_atts = cite_att
92 | self.inner_tag = 'p'
93 | self.inner_atts = self.attributes
94 | self.eat = False
95 |
96 | elif self.tag == 'bc' or self.tag == 'pre':
97 | i_tag = ''
98 | if self.tag == 'bc':
99 | i_tag = 'code'
100 | content = encode_html(self.content)
101 | self.content = self.textile.shelve(content)
102 | self.outer_tag = 'pre'
103 | self.outer_atts = self.attributes
104 | self.inner_tag = i_tag
105 | self.inner_atts = self.attributes
106 | self.eat = False
107 |
108 | elif self.tag == 'notextile':
109 | self.content = self.textile.shelve(self.content)
110 |
111 | elif self.tag == '###':
112 | self.eat = True
113 |
114 | else:
115 | self.outer_tag = self.tag
116 | self.outer_atts = self.attributes
117 |
118 | if not self.eat:
119 | self.content = self.textile.graf(self.content)
120 | else:
121 | self.content = ''
122 |
--------------------------------------------------------------------------------
/textile/objects/table.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | from xml.etree import ElementTree
3 |
4 | from textile.regex_strings import (align_re_s, cls_re_s, regex_snippets,
5 | table_span_re_s, valign_re_s, pnct_re_s)
6 | from textile.utils import generate_tag, parse_attributes
7 |
8 | try:
9 | import regex as re
10 | except ImportError:
11 | import re
12 |
13 |
14 | class Table(object):
15 | caption_re = re.compile(
16 | (r'^\|\=(?P<capts>{s}{a}{c})\. '
17 | r'(?P<cap>[^\n]*)(?P<row>.*)'
18 | .format(**{'s': table_span_re_s, 'a': align_re_s, 'c': cls_re_s})),
19 | re.S)
20 | colgroup_re = re.compile(
21 | r'^\|:(?P<cols>{s}{a}{c}\. .*)'
22 | .format(**{'s': table_span_re_s, 'a': align_re_s, 'c': cls_re_s}),
23 | re.M)
24 | heading_re = re.compile(
25 | r'^_(?={0}|{1})'.format(regex_snippets['space'], pnct_re_s))
26 |
27 | def __init__(self, textile, tatts, rows, summary):
28 | self.textile = textile
29 | self.attributes = parse_attributes(tatts, 'table', restricted=self.textile.restricted)
30 | if summary:
31 | self.attributes.update(summary=summary.strip())
32 | self.input = rows
33 | self.caption = ''
34 | self.colgroup = ''
35 | self.content = []
36 |
37 | def process(self):
38 | rgrp = None
39 | groups = []
40 | split = (
41 | re.compile(r'\|{0}*?$'.format(regex_snippets['space']), re.M)
42 | .split(self.input))
43 | for i, row in enumerate([x for x in split if x]):
44 | row = row.lstrip()
45 |
46 | # Caption -- only occurs on row 1, otherwise treat '|=. foo |...'
47 | # as a normal center-aligned cell.
48 | cmtch = self.caption_re.match(row)
49 | if i == 0 and cmtch:
50 | caption = Caption(restricted=self.textile.restricted, **cmtch.groupdict())
51 | self.caption = '\n{0}'.format(caption.caption)
52 | row = cmtch.group('row').lstrip()
53 | if row == '':
54 | continue
55 |
56 | # Colgroup -- A colgroup row will not necessarily end with a |.
57 | # Hence it may include the next row of actual table data.
58 | if row[:2] == '|:':
59 | if '\n' in row:
60 | colgroup_data, row = row[2:].split('\n')
61 | else:
62 | colgroup_data, row = row[2:], ''
63 | colgroup_atts, cols = colgroup_data, None
64 | if '|' in colgroup_data:
65 | colgroup_atts, cols = colgroup_data.split('|', 1)
66 | colgrp = Colgroup(cols, colgroup_atts, restricted=self.textile.restricted)
67 | self.colgroup = colgrp.process()
68 | if row == '':
69 | continue
70 |
71 | # search the row for a table group - thead, tfoot, or tbody
72 | grpmatchpattern = (r"(:?^\|(?P<part>{v})(?P<rgrpatts>{s}{a}{c})"
73 | r"\.\s*$\n)?^(?P<row>.*)").format(
74 | **{'v': valign_re_s, 's': table_span_re_s,
75 | 'a': align_re_s, 'c': cls_re_s})
76 | grpmatch_re = re.compile(grpmatchpattern, re.S | re.M)
77 | grpmatch = grpmatch_re.match(row.lstrip())
78 |
79 | grptypes = {'^': Thead, '~': Tfoot, '-': Tbody}
80 | if grpmatch.group('part'):
81 | # we're about to start a new group, so process the current one
82 | # and add it to the output
83 | if rgrp:
84 | groups.append('\n\t{0}'.format(rgrp.process()))
85 | rgrp = grptypes[grpmatch.group('part')](grpmatch.group(
86 | 'rgrpatts'), restricted=self.textile.restricted)
87 | row = grpmatch.group('row')
88 |
89 | rmtch = re.search(r'^(?P<ratts>{0}{1}\. )(?P<row>.*)'.format(
90 | align_re_s, cls_re_s), row.lstrip())
91 | if rmtch:
92 | row_atts = parse_attributes(rmtch.group('ratts'), 'tr', restricted=self.textile.restricted)
93 | row = rmtch.group('row')
94 | else:
95 | row_atts = {}
96 |
97 | # create a row to hold the cells.
98 | r = Row(row_atts, row)
99 | for cellctr, cell in enumerate(row.split('|')[1:]):
100 | ctag = 'td'
101 | if self.heading_re.match(cell):
102 | ctag = 'th'
103 |
104 | cmtch = re.search(r'^(?P<catts>_?{0}{1}{2}\. )'
105 | '(?P<cell>.*)'.format(
106 | table_span_re_s, align_re_s, cls_re_s),
107 | cell, flags=re.S)
108 | if cmtch:
109 | catts = cmtch.group('catts')
110 | cell_atts = parse_attributes(catts, 'td', restricted=self.textile.restricted)
111 | cell = cmtch.group('cell')
112 | else:
113 | cell_atts = {}
114 |
115 | if not self.textile.lite:
116 | a_pattern = r'(?P<space>{0}*)(?P<cell>.*)'.format(
117 | regex_snippets['space'])
118 | a = re.search(a_pattern, cell, flags=re.S)
119 | cell = self.textile.redcloth_list(a.group('cell'))
120 | cell = self.textile.textileLists(cell)
121 | cell = '{0}{1}'.format(a.group('space'), cell)
122 |
123 | # create a cell
124 | c = Cell(ctag, cell, cell_atts)
125 | cline_tag = '\n\t\t\t{0}'.format(c.process())
126 | # add the cell to the row
127 | r.cells.append(self.textile.doTagBr(ctag, cline_tag))
128 |
129 | # if we're in a group, add it to the group's rows, else add it
130 | # directly to the content
131 | if rgrp:
132 | rgrp.rows.append(r.process())
133 | else:
134 | self.content.append(r.process())
135 |
136 | # if there's still an rgrp, process it and add it to the output
137 | if rgrp:
138 | groups.append('\n\t{0}'.format(rgrp.process()))
139 |
140 | content = '{0}{1}{2}{3}\n\t'.format(
141 | self.caption, self.colgroup, ''.join(groups), ''.join(self.content))
142 | tbl = generate_tag('table', content, self.attributes)
143 | return '\t{0}\n\n'.format(tbl)
144 |
145 |
146 | class Caption(object):
147 | def __init__(self, capts, cap, row, restricted):
148 | self.attributes = parse_attributes(capts, restricted=restricted)
149 | self.caption = self.process(cap)
150 |
151 | def process(self, cap):
152 | tag = generate_tag('caption', cap.strip(), self.attributes)
153 | return '\t{0}'.format(tag)
154 |
155 |
156 | class Colgroup(object):
157 | def __init__(self, cols, atts, restricted):
158 | self.row = ''
159 | self.attributes = atts
160 | self.cols = cols
161 | self.restricted = restricted
162 |
163 | def process(self):
164 | enc = 'unicode'
165 |
166 | group_atts = parse_attributes(self.attributes, 'col', restricted=self.restricted)
167 | colgroup = ElementTree.Element('colgroup', attrib=group_atts)
168 | colgroup.text = '\n\t'
169 | if self.cols is not None:
170 | match_cols = self.cols.replace('.', '').split('|')
171 | # colgroup is the first item in match_cols, the remaining items are
172 | # cols.
173 | for idx, col in enumerate(match_cols):
174 | col_atts = parse_attributes(col.strip(), 'col', restricted=self.restricted)
175 | ElementTree.SubElement(colgroup, 'col', col_atts)
176 | colgrp = ElementTree.tostring(colgroup, encoding=enc)
177 | # cleanup the extra xml declaration if it exists, (python versions
178 | # differ) and then format the resulting string accordingly: newline and
179 | # tab between cols and a newline at the end
180 | xml_declaration = "<?xml version='1.0' encoding='UTF-8'?>\n"
181 | colgrp = colgrp.replace(xml_declaration, '')
182 | colgrp = colgrp.replace('><', '>\n\t<')
183 | return f"\n\t{colgrp}"
184 |
185 |
186 | class Row(object):
187 | def __init__(self, attributes, row):
188 | self.tag = 'tr'
189 | self.attributes = attributes
190 | self.cells = []
191 |
192 | def process(self):
193 | output = []
194 | for c in self.cells:
195 | output.append(c)
196 | cell_data = '{0}\n\t\t'.format(''.join(output))
197 | tag = generate_tag('tr', cell_data, self.attributes)
198 | return '\n\t\t{0}'.format(tag)
199 |
200 |
201 | class Cell(object):
202 | def __init__(self, tag, content, attributes):
203 | self.tag = tag
204 | self.content = content
205 | self.attributes = attributes
206 |
207 | def process(self):
208 | return generate_tag(self.tag, self.content, self.attributes)
209 |
210 |
211 | class _TableSection(object):
212 | def __init__(self, tag, attributes, restricted):
213 | self.tag = tag
214 | self.attributes = parse_attributes(attributes, restricted=restricted)
215 | self.rows = []
216 |
217 | def process(self):
218 | return generate_tag(self.tag, '{0}\n\t'.format(''.join(self.rows)), self.attributes)
219 |
220 |
221 | class Thead(_TableSection):
222 | def __init__(self, attributes, restricted):
223 | super(Thead, self).__init__('thead', attributes, restricted)
224 |
225 |
226 | class Tbody(_TableSection):
227 | def __init__(self, attributes, restricted):
228 | super(Tbody, self).__init__('tbody', attributes, restricted)
229 |
230 |
231 | class Tfoot(_TableSection):
232 | def __init__(self, attributes, restricted):
233 | super(Tfoot, self).__init__('tfoot', attributes, restricted)
234 |
--------------------------------------------------------------------------------
/textile/regex_strings.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | try:
3 | # Use regex module for matching uppercase characters if installed,
4 | # otherwise fall back to finding all the uppercase chars in a loop.
5 | import regex as re # noqa: F401
6 | upper_re_s = r'\p{Lu}'
7 | regex_snippets = {
8 | 'acr': r'\p{Lu}\p{Nd}',
9 | 'abr': r'\p{Lu}',
10 | 'nab': r'\p{Ll}',
11 | 'wrd': r'(?:\p{L}|\p{M}|\p{N}|\p{Pc})',
12 | 'cur': r'\p{Sc}',
13 | 'digit': r'\p{N}',
14 | 'space': r'(?:\p{Zs}|\v)',
15 | 'char': r'(?:[^\p{Zs}\v])',
16 | }
17 | except ImportError:
18 | from sys import maxunicode
19 | upper_re_s = "".join(
20 | [chr(c) for c in range(maxunicode) if chr(c).isupper()]
21 | )
22 | regex_snippets = {
23 | 'acr': r'{0}0-9'.format(upper_re_s),
24 | 'abr': r'{0}'.format(upper_re_s),
25 | 'nab': r'a-z',
26 | 'wrd': r'\w',
27 | # All codepoints identified as currency symbols
28 | # by the [mrab-regex library](https://pypi.org/project/regex/)
29 | # and the UNICODE standard.
30 | 'cur': r'$¢-¥֏؋৲৳৻૱௹฿៛\u20a0-\u20cf\ua838﷼﹩＄￠￡￥￦',
31 | 'digit': r'\d',
32 | 'space': r'(?:\s|\v)',
33 | 'char': r'\S',
34 | }
35 |
36 | halign_re_s = r'(?:\<(?!>)|(?<!<)\>|\<\>|\=|[()]+(?! ))'
37 | valign_re_s = r'[\-^~]'
38 | class_re_s = r'(?:\([^)\n]+\))' # Don't allow classes/ids,
39 | language_re_s = r'(?:\[[^\]\n]+\])' # languages,
40 | style_re_s = r'(?:\{[^}\n]+\})' # or styles to span across newlines
41 | colspan_re_s = r'(?:\\\d+)'
42 | rowspan_re_s = r'(?:\/\d+)'
43 | align_re_s = r'(?:{0}|{1})*'.format(halign_re_s, valign_re_s)
44 | table_span_re_s = r'(?:{0}|{1})*'.format(colspan_re_s, rowspan_re_s)
45 | # regex string to match class, style and language attributes
46 | cls_re_s = (r'(?:'
47 | r'{c}(?:{l}(?:{s})?|{s}(?:{l})?)?|'
48 | r'{l}(?:{c}(?:{s})?|{s}(?:{c})?)?|'
49 | r'{s}(?:{c}(?:{l})?|{l}(?:{c})?)?'
50 | r')?'
51 | ).format(c=class_re_s, s=style_re_s, l=language_re_s)
52 | pnct_re_s = r'[-!"#$%&()*+,/:;<=>?@\'\[\\\]\.^_`{|}~]'
53 | syms_re_s = '¤§µ¶†‡•∗∴◊♠♣♥♦'
54 |
--------------------------------------------------------------------------------
/textile/textilefactory.py:
--------------------------------------------------------------------------------
1 | from .core import Textile
2 |
3 |
4 | class TextileFactory(object):
5 | """ Use TextileFactory to create a Textile object which can be re-used to
6 | process multiple strings with the same settings."""
7 |
8 | def __init__(self, restricted=False, lite=False, sanitize=False,
9 | noimage=None, get_sizes=False, html_type='xhtml'):
10 |
11 | self.class_parms = {}
12 | self.method_parms = {}
13 |
14 | if lite and not restricted:
15 | raise ValueError("lite can only be enabled in restricted mode")
16 |
17 | if restricted:
18 | self.class_parms['restricted'] = True
19 | self.class_parms['lite'] = lite
20 | self.method_parms['rel'] = 'nofollow'
21 |
22 | if noimage is None:
23 | noimage = bool(restricted)
24 |
25 | self.class_parms['noimage'] = noimage
26 | self.method_parms['sanitize'] = sanitize
27 | self.class_parms['get_sizes'] = get_sizes
28 |
29 | if html_type not in ['xhtml', 'html5']:
30 | raise ValueError("html_type must be 'xhtml' or 'html5'")
31 | else:
32 | self.class_parms['html_type'] = html_type
33 |
34 | def process(self, text):
35 | return Textile(**self.class_parms).parse(text, **self.method_parms)
36 |
--------------------------------------------------------------------------------
/textile/utils.py:
--------------------------------------------------------------------------------
1 | try:
2 | import regex as re
3 | except ImportError:
4 | import re
5 |
6 | from urllib.parse import urlparse
7 | import html
8 |
9 | from collections import OrderedDict
10 |
11 | from xml.etree import ElementTree
12 |
13 | from textile.regex_strings import valign_re_s, halign_re_s
14 |
15 | # Regular expressions for stripping chunks of HTML,
16 | # leaving only content not wrapped in a tag or a comment
17 | RAW_TEXT_REVEALERS = (
18 | # The php version has orders the below list of tags differently. The
19 | # important thing to note here is that the pre must occur before the p or
20 | # else the regex module doesn't properly match pre-s. It only matches the
21 | # p in pre.
22 | re.compile(r'<(pre|p|blockquote|div|form|table|ul|ol|dl|h[1-6])[^>]*?>.*</\1>',
23 | re.S),
24 | re.compile(r'<(hr|br)[^>]*?/>'),
25 | re.compile(r'<!--.*?-->'),
26 | )
27 |
28 |
29 | def decode_high(text):
30 | """Decode encoded HTML entities."""
31 | text = '&#{0};'.format(text)
32 | return html.unescape(text)
33 |
34 |
35 | def encode_high(text):
36 | """Encode the text so that it is an appropriate HTML entity."""
37 | return ord(text)
38 |
39 |
40 | def encode_html(text, quotes=True):
41 | """Return text that's safe for an HTML attribute."""
42 | a = (
43 | ('&', '&'),
44 | ('<', '<'),
45 | ('>', '>'))
46 |
47 | if quotes:
48 | a = a + (("'", '''),
49 | ('"', '"'))
50 |
51 | for k, v in a:
52 | text = text.replace(k, v)
53 | return text
54 |
55 |
56 | def generate_tag(tag, content, attributes=None):
57 | """Generate a complete html tag using the ElementTree module. tag and
58 | content are strings, the attributes argument is a dictionary. As
59 | a convenience, if the content is ' /', a self-closing tag is generated."""
60 | enc = 'unicode'
61 | if not tag:
62 | return content
63 | element = ElementTree.Element(tag, attrib=attributes)
64 | # Sort attributes for Python 3.8+, as suggested in
65 | # https://docs.python.org/3/library/xml.etree.elementtree.html
66 | if len(element.attrib) > 1:
67 | # adjust attribute order, e.g. by sorting
68 | attribs = sorted(element.attrib.items())
69 | element.attrib.clear()
70 | element.attrib.update(attribs)
71 | # FIXME: Kind of an ugly hack. There *must* be a cleaner way. I tried
72 | # adding text by assigning it to element_tag.text. That results in
73 | # non-ascii text being html-entity encoded. Not bad, but not entirely
74 | # matching php-textile either.
75 | element_tag = ElementTree.tostringlist(element, encoding=enc,
76 | method='html')
77 | element_tag.insert(len(element_tag) - 1, content)
78 | element_text = ''.join(element_tag)
79 | return element_text
80 |
81 |
82 | def getimagesize(url):
83 | """
84 | Attempts to determine an image's width and height, and returns a tuple,
85 | (width, height), in pixels or an empty string in case of failure.
86 | Requires that PIL is installed.
87 |
88 | """
89 |
90 | try:
91 | from PIL import ImageFile
92 | except ImportError:
93 | return ''
94 |
95 | from urllib.request import urlopen
96 |
97 | try:
98 | p = ImageFile.Parser()
99 | f = urlopen(url)
100 | while True:
101 | s = f.read(1024)
102 | if not s:
103 | break
104 | p.feed(s)
105 | if p.image:
106 | return p.image.size
107 | except (IOError, ValueError):
108 | return ''
109 |
110 |
111 | def has_raw_text(text):
112 | """checks whether the text has text not already enclosed by a block tag"""
113 | r = text.strip()
114 | for pattern in RAW_TEXT_REVEALERS:
115 | r = pattern.sub('', r).strip()
116 | return r != ''
117 |
118 |
119 | def human_readable_url(url):
120 | if "://" in url:
121 | url = url.split("://")[1]
122 | elif ":" in url:
123 | url = url.split(":")[1]
124 | return url
125 |
126 |
127 | def is_rel_url(url):
128 | """Identify relative urls."""
129 | (scheme, netloc) = urlparse(url)[0:2]
130 | return not scheme and not netloc
131 |
132 |
133 | def is_valid_url(url):
134 | parsed = urlparse(url)
135 | if parsed.scheme == '':
136 | return True
137 | return False
138 |
139 |
140 | def list_type(list_string):
141 | listtypes = {
142 | list_string.endswith('*'): 'u',
143 | list_string.endswith('#'): 'o',
144 | (not list_string.endswith('*') and not list_string.endswith('#')):
145 | 'd'
146 | }
147 | return listtypes.get(True, False)
148 |
149 |
150 | def normalize_newlines(string):
151 | out = re.sub(r'\r\n?', '\n', string)
152 | out = re.compile(r'^[ \t]*\n', flags=re.M).sub('\n', out)
153 | out = out.strip('\n')
154 | return out
155 |
156 |
157 | def parse_attributes(block_attributes, element=None, include_id=True, restricted=False):
158 | vAlign = {'^': 'top', '-': 'middle', '~': 'bottom'}
159 | hAlign = {'<': 'left', '=': 'center', '>': 'right', '<>': 'justify'}
160 | style = []
161 | aclass = ''
162 | lang = ''
163 | colspan = ''
164 | rowspan = ''
165 | block_id = ''
166 | span = ''
167 | width = ''
168 | result = OrderedDict()
169 |
170 | if not block_attributes:
171 | return result
172 |
173 | matched = block_attributes
174 | if element == 'td':
175 | m = re.search(r'\\(\d+)', matched)
176 | if m:
177 | colspan = m.group(1)
178 |
179 | m = re.search(r'/(\d+)', matched)
180 | if m:
181 | rowspan = m.group(1)
182 |
183 | if element == 'td' or element == 'tr':
184 | m = re.search(r'(^{0})'.format(valign_re_s), matched)
185 | if m:
186 | style.append("vertical-align:{0}".format(vAlign[m.group(1)]))
187 |
188 | if not restricted:
189 | m = re.search(r'\{([^}]*)\}', matched)
190 | if m:
191 | style.extend(m.group(1).rstrip(';').split(';'))
192 | matched = matched.replace(m.group(0), '')
193 |
194 | m = re.search(r'\[([^\]]+)\]', matched, re.U)
195 | if m:
196 | lang = m.group(1)
197 | matched = matched.replace(m.group(0), '')
198 |
199 | m = re.search(r'\(([^()]+)\)', matched, re.U)
200 | if m:
201 | matched = matched.replace(m.group(0), '')
202 | # Only allow a restricted subset of the CSS standard characters for classes/ids.
203 | # No encoding markers allowed.
204 | id_class_match = re.compile(r"^([-a-zA-Z 0-9_\/\[\]\.\:\#]+)$", re.U).match(m.group(1))
205 | if id_class_match:
206 | class_regex = re.compile(r"^([-a-zA-Z 0-9_\.\/\[\]]*)$")
207 | id_class = id_class_match.group(1)
208 | # If a textile class block attribute was found with a '#' in it
209 | # split it into the css class and css id...
210 | hashpos = id_class.find('#')
211 | if hashpos >= 0:
212 | id_match = re.match(r"^#([-a-zA-Z0-9_\.\:]*)$", id_class[hashpos:])
213 | if id_match:
214 | block_id = id_match.group(1)
215 |
216 | cls_match = class_regex.match(id_class[:hashpos])
217 | else:
218 | cls_match = class_regex.match(id_class)
219 |
220 | if cls_match:
221 | aclass = cls_match.group(1)
222 |
223 | m = re.search(r'([(]+)', matched)
224 | if m:
225 | style.append("padding-left:{0}em".format(len(m.group(1))))
226 | matched = matched.replace(m.group(0), '')
227 |
228 | m = re.search(r'([)]+)', matched)
229 | if m:
230 | style.append("padding-right:{0}em".format(len(m.group(1))))
231 | matched = matched.replace(m.group(0), '')
232 |
233 | m = re.search(r'({0})'.format(halign_re_s), matched)
234 | if m:
235 | style.append("text-align:{0}".format(hAlign[m.group(1)]))
236 |
237 | if element == 'col':
238 | pattern = r'(?:\\(\d+)\.?)?\s*(\d+)?'
239 | csp = re.match(pattern, matched)
240 | span, width = csp.groups()
241 |
242 | if colspan:
243 | result['colspan'] = colspan
244 |
245 | if style:
246 | # Previous splits that created style may have introduced extra
247 | # whitespace into the list elements. Clean it up.
248 | style = [x.strip() for x in style]
249 | result['style'] = '{0};'.format("; ".join(style))
250 | if aclass:
251 | result['class'] = aclass
252 | if block_id and include_id:
253 | result['id'] = block_id
254 | if lang:
255 | result['lang'] = lang
256 | if rowspan:
257 | result['rowspan'] = rowspan
258 | if span:
259 | result['span'] = span
260 | if width:
261 | result['width'] = width
262 | return result
263 |
264 |
265 | def pba(block_attributes, element=None, include_id=True, restricted=False):
266 | """Parse block attributes."""
267 | attrs = parse_attributes(block_attributes, element, include_id, restricted)
268 | if not attrs:
269 | return ''
270 | result = ' '.join(['{0}="{1}"'.format(k, v) for k, v in attrs.items()])
271 | return ' {0}'.format(result)
272 |
--------------------------------------------------------------------------------
/textile/version.py:
--------------------------------------------------------------------------------
1 | VERSION = '4.0.3'
2 |
--------------------------------------------------------------------------------