summaryrefslogtreecommitdiff
path: root/docutils/docutils/transforms/peps.py
blob: edaba25579ba8cbb42069019e377623da0913b53 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
# Author: David Goodger
# Contact: goodger@users.sourceforge.net
# Revision: $Revision$
# Date: $Date$
# Copyright: This module has been placed in the public domain.

"""
Transforms for PEP processing.

- `Headers`: Used to transform a PEP's initial RFC-2822 header.  It remains a
  field list, but some entries get processed.
- `Contents`: Auto-inserts a table of contents.
- `PEPZero`: Special processing for PEP 0.
"""

__docformat__ = 'reStructuredText'

import sys
import os
import re
import time
from docutils import nodes, utils, languages
from docutils import ApplicationError, DataError
from docutils.transforms import Transform, TransformError
from docutils.transforms import parts, references, misc


class Headers(Transform):

    """
    Process fields in a PEP's initial RFC-2822 header.
    """

    default_priority = 360

    pep_url = 'pep-%04d.html'
    pep_cvs_url = ('http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/python/'
                   'python/nondist/peps/pep-%04d.txt')
    rcs_keyword_substitutions = (
          (re.compile(r'\$' r'RCSfile: (.+),v \$$', re.IGNORECASE), r'\1'),
          (re.compile(r'\$[a-zA-Z]+: (.+) \$$'), r'\1'),)

    def apply(self):
        if not len(self.document):
            # @@@ replace these DataErrors with proper system messages
            raise DataError('Document tree is empty.')
        header = self.document[0]
        if not isinstance(header, nodes.field_list) or \
              'rfc2822' not in header['classes']:
            raise DataError('Document does not begin with an RFC-2822 '
                            'header; it is not a PEP.')
        pep = None
        for field in header:
            if field[0].astext().lower() == 'pep': # should be the first field
                value = field[1].astext()
                try:
                    pep = int(value)
                    cvs_url = self.pep_cvs_url % pep
                except ValueError:
                    pep = value
                    cvs_url = None
                    msg = self.document.reporter.warning(
                        '"PEP" header must contain an integer; "%s" is an '
                        'invalid value.' % pep, base_node=field)
                    msgid = self.document.set_id(msg)
                    prb = nodes.problematic(value, value or '(none)',
                                            refid=msgid)
                    prbid = self.document.set_id(prb)
                    msg.add_backref(prbid)
                    if len(field[1]):
                        field[1][0][:] = [prb]
                    else:
                        field[1] += nodes.paragraph('', '', prb)
                break
        if pep is None:
            raise DataError('Document does not contain an RFC-2822 "PEP" '
                            'header.')
        if pep == 0:
            # Special processing for PEP 0.
            pending = nodes.pending(PEPZero)
            self.document.insert(1, pending)
            self.document.note_pending(pending)
        if len(header) < 2 or header[1][0].astext().lower() != 'title':
            raise DataError('No title!')
        for field in header:
            name = field[0].astext().lower()
            body = field[1]
            if len(body) > 1:
                raise DataError('PEP header field body contains multiple '
                                'elements:\n%s' % field.pformat(level=1))
            elif len(body) == 1:
                if not isinstance(body[0], nodes.paragraph):
                    raise DataError('PEP header field body may only contain '
                                    'a single paragraph:\n%s'
                                    % field.pformat(level=1))
            elif name == 'last-modified':
                date = time.strftime(
                      '%d-%b-%Y',
                      time.localtime(os.stat(self.document['source'])[8]))
                if cvs_url:
                    body += nodes.paragraph(
                        '', '', nodes.reference('', date, refuri=cvs_url))
            else:
                # empty
                continue
            para = body[0]
            if name == 'author':
                for node in para:
                    if isinstance(node, nodes.reference):
                        node.replace_self(mask_email(node))
            elif name == 'discussions-to':
                for node in para:
                    if isinstance(node, nodes.reference):
                        node.replace_self(mask_email(node, pep))
            elif name in ('replaces', 'replaced-by', 'requires'):
                newbody = []
                space = nodes.Text(' ')
                for refpep in re.split(',?\s+', body.astext()):
                    pepno = int(refpep)
                    newbody.append(nodes.reference(
                        refpep, refpep,
                        refuri=(self.document.settings.pep_base_url
                                + self.pep_url % pepno)))
                    newbody.append(space)
                para[:] = newbody[:-1] # drop trailing space
            elif name == 'last-modified':
                utils.clean_rcs_keywords(para, self.rcs_keyword_substitutions)
                if cvs_url:
                    date = para.astext()
                    para[:] = [nodes.reference('', date, refuri=cvs_url)]
            elif name == 'content-type':
                pep_type = para.astext()
                uri = self.document.settings.pep_base_url + self.pep_url % 12
                para[:] = [nodes.reference('', pep_type, refuri=uri)]
            elif name == 'version' and len(body):
                utils.clean_rcs_keywords(para, self.rcs_keyword_substitutions)


class Contents(Transform):

    """
    Insert an empty table of contents topic and a transform placeholder into
    the document after the RFC 2822 header.
    """

    default_priority = 380

    def apply(self):
        language = languages.get_language(self.document.settings.language_code)
        name = language.labels['contents']
        title = nodes.title('', name)
        topic = nodes.topic('', title, classes=['contents'])
        name = nodes.fully_normalize_name(name)
        if not self.document.has_name(name):
            topic['names'].append(name)
        self.document.note_implicit_target(topic)
        pending = nodes.pending(parts.Contents)
        topic += pending
        self.document.insert(1, topic)
        self.document.note_pending(pending)


class TargetNotes(Transform):

    """
    Locate the "References" section, insert a placeholder for an external
    target footnote insertion transform at the end, and schedule the
    transform to run immediately.
    """

    default_priority = 520

    def apply(self):
        doc = self.document
        i = len(doc) - 1
        refsect = copyright = None
        while i >= 0 and isinstance(doc[i], nodes.section):
            title_words = doc[i][0].astext().lower().split()
            if 'references' in title_words:
                refsect = doc[i]
                break
            elif 'copyright' in title_words:
                copyright = i
            i -= 1
        if not refsect:
            refsect = nodes.section()
            refsect += nodes.title('', 'References')
            doc.set_id(refsect)
            if copyright:
                # Put the new "References" section before "Copyright":
                doc.insert(copyright, refsect)
            else:
                # Put the new "References" section at end of doc:
                doc.append(refsect)
        pending = nodes.pending(references.TargetNotes)
        refsect.append(pending)
        self.document.note_pending(pending, 0)
        pending = nodes.pending(misc.CallBack,
                                details={'callback': self.cleanup_callback})
        refsect.append(pending)
        self.document.note_pending(pending, 1)

    def cleanup_callback(self, pending):
        """
        Remove an empty "References" section.

        Called after the `references.TargetNotes` transform is complete.
        """
        if len(pending.parent) == 2:    # <title> and <pending>
            pending.parent.parent.remove(pending.parent)


class PEPZero(Transform):

    """
    Special processing for PEP 0.
    """

    default_priority =760

    def apply(self):
        visitor = PEPZeroSpecial(self.document)
        self.document.walk(visitor)
        self.startnode.parent.remove(self.startnode)


class PEPZeroSpecial(nodes.SparseNodeVisitor):

    """
    Perform the special processing needed by PEP 0:

    - Mask email addresses.

    - Link PEP numbers in the second column of 4-column tables to the PEPs
      themselves.
    """

    pep_url = Headers.pep_url

    def unknown_visit(self, node):
        pass

    def visit_reference(self, node):
        node.replace_self(mask_email(node))

    def visit_field_list(self, node):
        if 'rfc2822' in node['classes']:
            raise nodes.SkipNode

    def visit_tgroup(self, node):
        self.pep_table = node['cols'] == 4
        self.entry = 0

    def visit_colspec(self, node):
        self.entry += 1
        if self.pep_table and self.entry == 2:
            node['classes'].append('num')

    def visit_row(self, node):
        self.entry = 0

    def visit_entry(self, node):
        self.entry += 1
        if self.pep_table and self.entry == 2 and len(node) == 1:
            node['classes'].append('num')
            p = node[0]
            if isinstance(p, nodes.paragraph) and len(p) == 1:
                text = p.astext()
                try:
                    pep = int(text)
                    ref = (self.document.settings.pep_base_url
                           + self.pep_url % pep)
                    p[0] = nodes.reference(text, text, refuri=ref)
                except ValueError:
                    pass


non_masked_addresses = ('peps@python.org',
                        'python-list@python.org',
                        'python-dev@python.org')

def mask_email(ref, pepno=None):
    """
    Mask the email address in `ref` and return a replacement node.

    `ref` is returned unchanged if it contains no email address.

    For email addresses such as "user@host", mask the address as "user at
    host" (text) to thwart simple email address harvesters (except for those
    listed in `non_masked_addresses`).  If a PEP number (`pepno`) is given,
    return a reference including a default email subject.
    """
    if ref.hasattr('refuri') and ref['refuri'].startswith('mailto:'):
        if ref['refuri'][8:] in non_masked_addresses:
            replacement = ref[0]
        else:
            replacement_text = ref.astext().replace('@', '&#32;&#97;t&#32;')
            replacement = nodes.raw('', replacement_text, format='html')
        if pepno is None:
            return replacement
        else:
            ref['refuri'] += '?subject=PEP%%20%s' % pepno
            ref[:] = [replacement]
            return ref
    else:
        return ref