summaryrefslogtreecommitdiffstats
path: root/Documentation/sphinx/automarkup.py
blob: acc6d55718bd88f9d09ec008ef0208faea0b3320 (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
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
# SPDX-License-Identifier: GPL-2.0
# Copyright 2019 Jonathan Corbet <corbet@lwn.net>
#
# Apply kernel-specific tweaks after the initial document processing
# has been done.
#
from docutils import nodes
import sphinx
from sphinx import addnodes
if sphinx.version_info[0] < 2 or \
   sphinx.version_info[0] == 2 and sphinx.version_info[1] < 1:
    from sphinx.environment import NoUri
else:
    from sphinx.errors import NoUri
import re
from itertools import chain

#
# Python 2 lacks re.ASCII...
#
try:
    ascii_p3 = re.ASCII
except AttributeError:
    ascii_p3 = 0

#
# Regex nastiness.  Of course.
# Try to identify "function()" that's not already marked up some
# other way.  Sphinx doesn't like a lot of stuff right after a
# :c:func: block (i.e. ":c:func:`mmap()`s" flakes out), so the last
# bit tries to restrict matches to things that won't create trouble.
#
RE_function = re.compile(r'\b(([a-zA-Z_]\w+)\(\))', flags=ascii_p3)

#
# Sphinx 2 uses the same :c:type role for struct, union, enum and typedef
#
RE_generic_type = re.compile(r'\b(struct|union|enum|typedef)\s+([a-zA-Z_]\w+)',
                             flags=ascii_p3)

#
# Sphinx 3 uses a different C role for each one of struct, union, enum and
# typedef
#
RE_struct = re.compile(r'\b(struct)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
RE_union = re.compile(r'\b(union)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
RE_enum = re.compile(r'\b(enum)\s+([a-zA-Z_]\w+)', flags=ascii_p3)
RE_typedef = re.compile(r'\b(typedef)\s+([a-zA-Z_]\w+)', flags=ascii_p3)

#
# Detects a reference to a documentation page of the form Documentation/... with
# an optional extension
#
RE_doc = re.compile(r'(\bDocumentation/)?((\.\./)*[\w\-/]+)\.(rst|txt)')

RE_namespace = re.compile(r'^\s*..\s*c:namespace::\s*(\S+)\s*$')

#
# Reserved C words that we should skip when cross-referencing
#
Skipnames = [ 'for', 'if', 'register', 'sizeof', 'struct', 'unsigned' ]


#
# Many places in the docs refer to common system calls.  It is
# pointless to try to cross-reference them and, as has been known
# to happen, somebody defining a function by these names can lead
# to the creation of incorrect and confusing cross references.  So
# just don't even try with these names.
#
Skipfuncs = [ 'open', 'close', 'read', 'write', 'fcntl', 'mmap',
              'select', 'poll', 'fork', 'execve', 'clone', 'ioctl',
              'socket' ]

c_namespace = ''

#
# Detect references to commits.
#
RE_git = re.compile(r'commit\s+(?P<rev>[0-9a-f]{12,40})(?:\s+\(".*?"\))?',
    flags=re.IGNORECASE | re.DOTALL)

def markup_refs(docname, app, node):
    t = node.astext()
    done = 0
    repl = [ ]
    #
    # Associate each regex with the function that will markup its matches
    #
    markup_func_sphinx2 = {RE_doc: markup_doc_ref,
                           RE_function: markup_c_ref,
                           RE_generic_type: markup_c_ref}

    markup_func_sphinx3 = {RE_doc: markup_doc_ref,
                           RE_function: markup_func_ref_sphinx3,
                           RE_struct: markup_c_ref,
                           RE_union: markup_c_ref,
                           RE_enum: markup_c_ref,
                           RE_typedef: markup_c_ref,
                           RE_git: markup_git}

    if sphinx.version_info[0] >= 3:
        markup_func = markup_func_sphinx3
    else:
        markup_func = markup_func_sphinx2

    match_iterators = [regex.finditer(t) for regex in markup_func]
    #
    # Sort all references by the starting position in text
    #
    sorted_matches = sorted(chain(*match_iterators), key=lambda m: m.start())
    for m in sorted_matches:
        #
        # Include any text prior to match as a normal text node.
        #
        if m.start() > done:
            repl.append(nodes.Text(t[done:m.start()]))

        #
        # Call the function associated with the regex that matched this text and
        # append its return to the text
        #
        repl.append(markup_func[m.re](docname, app, m))

        done = m.end()
    if done < len(t):
        repl.append(nodes.Text(t[done:]))
    return repl

#
# Keep track of cross-reference lookups that failed so we don't have to
# do them again.
#
failed_lookups = { }
def failure_seen(target):
    return (target) in failed_lookups
def note_failure(target):
    failed_lookups[target] = True

#
# In sphinx3 we can cross-reference to C macro and function, each one with its
# own C role, but both match the same regex, so we try both.
#
def markup_func_ref_sphinx3(docname, app, match):
    cdom = app.env.domains['c']
    #
    # Go through the dance of getting an xref out of the C domain
    #
    base_target = match.group(2)
    target_text = nodes.Text(match.group(0))
    xref = None
    possible_targets = [base_target]
    # Check if this document has a namespace, and if so, try
    # cross-referencing inside it first.
    if c_namespace:
        possible_targets.insert(0, c_namespace + "." + base_target)

    if base_target not in Skipnames:
        for target in possible_targets:
            if (target not in Skipfuncs) and not failure_seen(target):
                lit_text = nodes.literal(classes=['xref', 'c', 'c-func'])
                lit_text += target_text
                pxref = addnodes.pending_xref('', refdomain = 'c',
                                              reftype = 'function',
                                              reftarget = target,
                                              modname = None,
                                              classname = None)
                #
                # XXX The Latex builder will throw NoUri exceptions here,
                # work around that by ignoring them.
                #
                try:
                    xref = cdom.resolve_xref(app.env, docname, app.builder,
                                             'function', target, pxref,
                                             lit_text)
                except NoUri:
                    xref = None

                if xref:
                    return xref
                note_failure(target)

    return target_text

def markup_c_ref(docname, app, match):
    class_str = {# Sphinx 2 only
                 RE_function: 'c-func',
                 RE_generic_type: 'c-type',
                 # Sphinx 3+ only
                 RE_struct: 'c-struct',
                 RE_union: 'c-union',
                 RE_enum: 'c-enum',
                 RE_typedef: 'c-type',
                 }
    reftype_str = {# Sphinx 2 only
                   RE_function: 'function',
                   RE_generic_type: 'type',
                   # Sphinx 3+ only
                   RE_struct: 'struct',
                   RE_union: 'union',
                   RE_enum: 'enum',
                   RE_typedef: 'type',
                   }

    cdom = app.env.domains['c']
    #
    # Go through the dance of getting an xref out of the C domain
    #
    base_target = match.group(2)
    target_text = nodes.Text(match.group(0))
    xref = None
    possible_targets = [base_target]
    # Check if this document has a namespace, and if so, try
    # cross-referencing inside it first.
    if c_namespace:
        possible_targets.insert(0, c_namespace + "." + base_target)

    if base_target not in Skipnames:
        for target in possible_targets:
            if not (match.re == RE_function and target in Skipfuncs):
                lit_text = nodes.literal(classes=['xref', 'c', class_str[match.re]])
                lit_text += target_text
                pxref = addnodes.pending_xref('', refdomain = 'c',
                                              reftype = reftype_str[match.re],
                                              reftarget = target, modname = None,
                                              classname = None)
                #
                # XXX The Latex builder will throw NoUri exceptions here,
                # work around that by ignoring them.
                #
                try:
                    xref = cdom.resolve_xref(app.env, docname, app.builder,
                                             reftype_str[match.re], target, pxref,
                                             lit_text)
                except NoUri:
                    xref = None

                if xref:
                    return xref

    return target_text

#
# Try to replace a documentation reference of the form Documentation/... with a
# cross reference to that page
#
def markup_doc_ref(docname, app, match):
    stddom = app.env.domains['std']
    #
    # Go through the dance of getting an xref out of the std domain
    #
    absolute = match.group(1)
    target = match.group(2)
    if absolute:
       target = "/" + target
    xref = None
    pxref = addnodes.pending_xref('', refdomain = 'std', reftype = 'doc',
                                  reftarget = target, modname = None,
                                  classname = None, refexplicit = False)
    #
    # XXX The Latex builder will throw NoUri exceptions here,
    # work around that by ignoring them.
    #
    try:
        xref = stddom.resolve_xref(app.env, docname, app.builder, 'doc',
                                   target, pxref, None)
    except NoUri:
        xref = None
    #
    # Return the xref if we got it; otherwise just return the plain text.
    #
    if xref:
        return xref
    else:
        return nodes.Text(match.group(0))

def get_c_namespace(app, docname):
    source = app.env.doc2path(docname)
    with open(source) as f:
        for l in f:
            match = RE_namespace.search(l)
            if match:
                return match.group(1)
    return ''

def markup_git(docname, app, match):
    # While we could probably assume that we are running in a git
    # repository, we can't know for sure, so let's just mechanically
    # turn them into git.kernel.org links without checking their
    # validity. (Maybe we can do something in the future to warn about
    # these references if this is explicitly requested.)
    text = match.group(0)
    rev = match.group('rev')
    return nodes.reference('', nodes.Text(text),
        refuri=f'https://git.kernel.org/torvalds/c/{rev}')

def auto_markup(app, doctree, name):
    global c_namespace
    c_namespace = get_c_namespace(app, name)
    def text_but_not_a_reference(node):
        # The nodes.literal test catches ``literal text``, its purpose is to
        # avoid adding cross-references to functions that have been explicitly
        # marked with cc:func:.
        if not isinstance(node, nodes.Text) or isinstance(node.parent, nodes.literal):
            return False

        child_of_reference = False
        parent = node.parent
        while parent:
            if isinstance(parent, nodes.Referential):
                child_of_reference = True
                break
            parent = parent.parent
        return not child_of_reference

    #
    # This loop could eventually be improved on.  Someday maybe we
    # want a proper tree traversal with a lot of awareness of which
    # kinds of nodes to prune.  But this works well for now.
    #
    for para in doctree.traverse(nodes.paragraph):
        for node in para.traverse(condition=text_but_not_a_reference):
            node.parent.replace(node, markup_refs(name, app, node))

def setup(app):
    app.connect('doctree-resolved', auto_markup)
    return {
        'parallel_read_safe': True,
        'parallel_write_safe': True,
        }