Mercurial > repos > shellac > guppy_basecaller

comparison env/lib/python3.7/site-packages/docutils/transforms/universal.py @ 5:9b1c78e6ba9c draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit 6c0a8142489327ece472c84e558c47da711a9142"
author shellac
date Mon, 01 Jun 2020 08:59:25 -0400
parents 79f47841a781
children
comparison
equal deleted inserted replaced
4:79f47841a781 5:9b1c78e6ba9c
1 # $Id: universal.py 8393 2019-09-18 10:13:00Z milde $
2 # -*- coding: utf-8 -*-
3 # Authors: David Goodger <goodger@python.org>; Ueli Schlaepfer; Günter Milde
4 # Maintainer: docutils-develop@lists.sourceforge.net
5 # Copyright: This module has been placed in the public domain.
6
7 """
8 Transforms needed by most or all documents:
9
10 - `Decorations`: Generate a document's header & footer.
11 - `Messages`: Placement of system messages stored in
12 `nodes.document.transform_messages`.
13 - `TestMessages`: Like `Messages`, used on test runs.
14 - `FinalReferences`: Resolve remaining references.
15 """
16
17 __docformat__ = 'reStructuredText'
18
19 import re
20 import sys
21 import time
22 from docutils import nodes, utils
23 from docutils.transforms import TransformError, Transform
24 from docutils.utils import smartquotes
25
26
27 if sys.version_info >= (3, 0):
28 unicode = str # noqa
29
30
31 class Decorations(Transform):
32
33 """
34 Populate a document's decoration element (header, footer).
35 """
36
37 default_priority = 820
38
39 def apply(self):
40 header_nodes = self.generate_header()
41 if header_nodes:
42 decoration = self.document.get_decoration()
43 header = decoration.get_header()
44 header.extend(header_nodes)
45 footer_nodes = self.generate_footer()
46 if footer_nodes:
47 decoration = self.document.get_decoration()
48 footer = decoration.get_footer()
49 footer.extend(footer_nodes)
50
51 def generate_header(self):
52 return None
53
54 def generate_footer(self):
55 # @@@ Text is hard-coded for now.
56 # Should be made dynamic (language-dependent).
57 # @@@ Use timestamp from the `SOURCE_DATE_EPOCH`_ environment variable
58 # for the datestamp?
59 # See https://sourceforge.net/p/docutils/patches/132/
60 # and https://reproducible-builds.org/specs/source-date-epoch/
61 settings = self.document.settings
62 if settings.generator or settings.datestamp or settings.source_link \
63 or settings.source_url:
64 text = []
65 if settings.source_link and settings._source \
66 or settings.source_url:
67 if settings.source_url:
68 source = settings.source_url
69 else:
70 source = utils.relative_path(settings._destination,
71 settings._source)
72 text.extend([
73 nodes.reference('', 'View document source',
74 refuri=source),
75 nodes.Text('.\n')])
76 if settings.datestamp:
77 datestamp = time.strftime(settings.datestamp, time.gmtime())
78 text.append(nodes.Text('Generated on: ' + datestamp + '.\n'))
79 if settings.generator:
80 text.extend([
81 nodes.Text('Generated by '),
82 nodes.reference('', 'Docutils', refuri=
83 'http://docutils.sourceforge.net/'),
84 nodes.Text(' from '),
85 nodes.reference('', 'reStructuredText', refuri='http://'
86 'docutils.sourceforge.net/rst.html'),
87 nodes.Text(' source.\n')])
88 return [nodes.paragraph('', '', *text)]
89 else:
90 return None
91
92
93 class ExposeInternals(Transform):
94
95 """
96 Expose internal attributes if ``expose_internals`` setting is set.
97 """
98
99 default_priority = 840
100
101 def not_Text(self, node):
102 return not isinstance(node, nodes.Text)
103
104 def apply(self):
105 if self.document.settings.expose_internals:
106 for node in self.document.traverse(self.not_Text):
107 for att in self.document.settings.expose_internals:
108 value = getattr(node, att, None)
109 if value is not None:
110 node['internal:' + att] = value
111
112
113 class Messages(Transform):
114
115 """
116 Place any system messages generated after parsing into a dedicated section
117 of the document.
118 """
119
120 default_priority = 860
121
122 def apply(self):
123 unfiltered = self.document.transform_messages
124 threshold = self.document.reporter.report_level
125 messages = []
126 for msg in unfiltered:
127 if msg['level'] >= threshold and not msg.parent:
128 messages.append(msg)
129 if messages:
130 section = nodes.section(classes=['system-messages'])
131 # @@@ get this from the language module?
132 section += nodes.title('', 'Docutils System Messages')
133 section += messages
134 self.document.transform_messages[:] = []
135 self.document += section
136
137
138 class FilterMessages(Transform):
139
140 """
141 Remove system messages below verbosity threshold.
142 """
143
144 default_priority = 870
145
146 def apply(self):
147 for node in tuple(self.document.traverse(nodes.system_message)):
148 if node['level'] < self.document.reporter.report_level:
149 node.parent.remove(node)
150
151
152 class TestMessages(Transform):
153
154 """
155 Append all post-parse system messages to the end of the document.
156
157 Used for testing purposes.
158 """
159
160 default_priority = 880
161
162 def apply(self):
163 for msg in self.document.transform_messages:
164 if not msg.parent:
165 self.document += msg
166
167
168 class StripComments(Transform):
169
170 """
171 Remove comment elements from the document tree (only if the
172 ``strip_comments`` setting is enabled).
173 """
174
175 default_priority = 740
176
177 def apply(self):
178 if self.document.settings.strip_comments:
179 for node in tuple(self.document.traverse(nodes.comment)):
180 node.parent.remove(node)
181
182
183 class StripClassesAndElements(Transform):
184
185 """
186 Remove from the document tree all elements with classes in
187 `self.document.settings.strip_elements_with_classes` and all "classes"
188 attribute values in `self.document.settings.strip_classes`.
189 """
190
191 default_priority = 420
192
193 def apply(self):
194 if self.document.settings.strip_elements_with_classes:
195 self.strip_elements = set(
196 self.document.settings.strip_elements_with_classes)
197 # Iterate over a tuple as removing the current node
198 # corrupts the iterator returned by `traverse`:
199 for node in tuple(self.document.traverse(self.check_classes)):
200 node.parent.remove(node)
201
202 if not self.document.settings.strip_classes:
203 return
204 strip_classes = self.document.settings.strip_classes
205 for node in self.document.traverse(nodes.Element):
206 for class_value in strip_classes:
207 try:
208 node['classes'].remove(class_value)
209 except ValueError:
210 pass
211
212 def check_classes(self, node):
213 if not isinstance(node, nodes.Element):
214 return False
215 for class_value in node['classes'][:]:
216 if class_value in self.strip_elements:
217 return True
218 return False
219
220
221 class SmartQuotes(Transform):
222
223 """
224 Replace ASCII quotation marks with typographic form.
225
226 Also replace multiple dashes with em-dash/en-dash characters.
227 """
228
229 default_priority = 850
230
231 nodes_to_skip = (nodes.FixedTextElement, nodes.Special)
232 """Do not apply "smartquotes" to instances of these block-level nodes."""
233
234 literal_nodes = (nodes.FixedTextElement, nodes.Special,
235 nodes.image, nodes.literal, nodes.math,
236 nodes.raw, nodes.problematic)
237 """Do apply smartquotes to instances of these inline nodes."""
238
239 smartquotes_action = 'qDe'
240 """Setting to select smartquote transformations.
241
242 The default 'qDe' educates normal quote characters: (", '),
243 em- and en-dashes (---, --) and ellipses (...).
244 """
245
246 def __init__(self, document, startnode):
247 Transform.__init__(self, document, startnode=startnode)
248 self.unsupported_languages = set()
249
250 def get_tokens(self, txtnodes):
251 # A generator that yields ``(texttype, nodetext)`` tuples for a list
252 # of "Text" nodes (interface to ``smartquotes.educate_tokens()``).
253 for node in txtnodes:
254 if (isinstance(node.parent, self.literal_nodes)
255 or isinstance(node.parent.parent, self.literal_nodes)):
256 yield ('literal', unicode(node))
257 else:
258 # SmartQuotes uses backslash escapes instead of null-escapes
259 txt = re.sub('(?<=\x00)([-\\\'".`])', r'\\\1', unicode(node))
260 yield ('plain', txt)
261
262 def apply(self):
263 smart_quotes = self.document.settings.smart_quotes
264 if not smart_quotes:
265 return
266 try:
267 alternative = smart_quotes.startswith('alt')
268 except AttributeError:
269 alternative = False
270
271 document_language = self.document.settings.language_code
272 lc_smartquotes = self.document.settings.smartquotes_locales
273 if lc_smartquotes:
274 smartquotes.smartchars.quotes.update(dict(lc_smartquotes))
275
276 # "Educate" quotes in normal text. Handle each block of text
277 # (TextElement node) as a unit to keep context around inline nodes:
278 for node in self.document.traverse(nodes.TextElement):
279 # skip preformatted text blocks and special elements:
280 if isinstance(node, self.nodes_to_skip):
281 continue
282 # nested TextElements are not "block-level" elements:
283 if isinstance(node.parent, nodes.TextElement):
284 continue
285
286 # list of text nodes in the "text block":
287 txtnodes = [txtnode for txtnode in node.traverse(nodes.Text)
288 if not isinstance(txtnode.parent,
289 nodes.option_string)]
290
291 # language: use typographical quotes for language "lang"
292 lang = node.get_language_code(document_language)
293 # use alternative form if `smart-quotes` setting starts with "alt":
294 if alternative:
295 if '-x-altquot' in lang:
296 lang = lang.replace('-x-altquot', '')
297 else:
298 lang += '-x-altquot'
299 # drop unsupported subtags:
300 for tag in utils.normalize_language_tag(lang):
301 if tag in smartquotes.smartchars.quotes:
302 lang = tag
303 break
304 else: # language not supported: (keep ASCII quotes)
305 if lang not in self.unsupported_languages:
306 self.document.reporter.warning('No smart quotes '
307 'defined for language "%s".'%lang, base_node=node)
308 self.unsupported_languages.add(lang)
309 lang = ''
310
311 # Iterator educating quotes in plain text:
312 # (see "utils/smartquotes.py" for the attribute setting)
313 teacher = smartquotes.educate_tokens(self.get_tokens(txtnodes),
314 attr=self.smartquotes_action, language=lang)
315
316 for txtnode, newtext in zip(txtnodes, teacher):
317 txtnode.parent.replace(txtnode, nodes.Text(newtext,
318 rawsource=txtnode.rawsource))
319
320 self.unsupported_languages = set() # reset