File: dump_format_style.py

package info (click to toggle)
llvm-toolchain-15 1%3A15.0.6-4
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,554,644 kB
  • sloc: cpp: 5,922,452; ansic: 1,012,136; asm: 674,362; python: 191,568; objc: 73,855; f90: 42,327; lisp: 31,913; pascal: 11,973; javascript: 10,144; sh: 9,421; perl: 7,447; ml: 5,527; awk: 3,523; makefile: 2,520; xml: 885; cs: 573; fortran: 567
file content (360 lines) | stat: -rwxr-xr-x 12,314 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
#!/usr/bin/env python3
# A tool to parse the FormatStyle struct from Format.h and update the
# documentation in ../ClangFormatStyleOptions.rst automatically.
# Run from the directory in which this file is located to update the docs.

import inspect
import os
import re
import sys
from io import TextIOWrapper
from typing import Set

CLANG_DIR = os.path.join(os.path.dirname(__file__), '../..')
FORMAT_STYLE_FILE = os.path.join(CLANG_DIR, 'include/clang/Format/Format.h')
INCLUDE_STYLE_FILE = os.path.join(CLANG_DIR, 'include/clang/Tooling/Inclusions/IncludeStyle.h')
DOC_FILE = os.path.join(CLANG_DIR, 'docs/ClangFormatStyleOptions.rst')

PLURALS_FILE = os.path.join(os.path.dirname(__file__), 'plurals.txt')

plurals: Set[str] = set()
with open(PLURALS_FILE, 'a+') as f:
  f.seek(0)
  plurals = set(f.read().splitlines())

def substitute(text, tag, contents):
  replacement = '\n.. START_%s\n\n%s\n\n.. END_%s\n' % (tag, contents, tag)
  pattern = r'\n\.\. START_%s\n.*\n\.\. END_%s\n' % (tag, tag)
  return re.sub(pattern, '%s', text, flags=re.S) % replacement

def register_plural(singular: str, plural: str):
  if plural not in plurals:
    if not hasattr(register_plural, "generated_new_plural"):
      print('Plural generation: you can use '
      f'`git checkout -- {os.path.relpath(PLURALS_FILE)}` '
      'to reemit warnings or `git add` to include new plurals\n')
    register_plural.generated_new_plural = True

    plurals.add(plural)
    with open(PLURALS_FILE, 'a') as f:
      f.write(plural + '\n')
    cf = inspect.currentframe()
    lineno = ''
    if cf and cf.f_back:
      lineno = ':' + str(cf.f_back.f_lineno)
    print(f'{__file__}{lineno} check if plural of {singular} is {plural}', file=sys.stderr)
  return plural

def pluralize(word: str):
  lword = word.lower()
  if len(lword) >= 2 and lword[-1] == 'y' and lword[-2] not in 'aeiou':
    return register_plural(word, word[:-1] + 'ies')
  elif lword.endswith(('s', 'sh', 'ch', 'x', 'z')):
    return register_plural(word, word[:-1] + 'es')
  elif lword.endswith('fe'):
    return register_plural(word, word[:-2] + 'ves')
  elif lword.endswith('f') and not lword.endswith('ff'):
    return register_plural(word, word[:-1] + 'ves')
  else:
    return register_plural(word, word + 's')


def to_yaml_type(typestr: str):
  if typestr == 'bool':
    return 'Boolean'
  elif typestr == 'int':
    return 'Integer'
  elif typestr == 'unsigned':
    return 'Unsigned'
  elif typestr == 'std::string':
    return 'String'

  subtype, napplied = re.subn(r'^std::vector<(.*)>$', r'\1', typestr)
  if napplied == 1:
    return 'List of ' + pluralize(to_yaml_type(subtype))

  return typestr

def doxygen2rst(text):
  text = re.sub(r'<tt>\s*(.*?)\s*<\/tt>', r'``\1``', text)
  text = re.sub(r'\\c ([^ ,;\.]+)', r'``\1``', text)
  text = re.sub(r'\\\w+ ', '', text)
  return text

def indent(text, columns, indent_first_line=True):
  indent_str = ' ' * columns
  s = re.sub(r'\n([^\n])', '\n' + indent_str + '\\1', text, flags=re.S)
  if not indent_first_line or s.startswith('\n'):
    return s
  return indent_str + s

class Option(object):
  def __init__(self, name, opt_type, comment, version):
    self.name = name
    self.type = opt_type
    self.comment = comment.strip()
    self.enum = None
    self.nested_struct = None
    self.version = version

  def __str__(self):
    if self.version:
      s = '**%s** (``%s``) :versionbadge:`clang-format %s`\n%s' % (self.name, to_yaml_type(self.type), self.version,
                                 doxygen2rst(indent(self.comment, 2)))
    else:
      s = '**%s** (``%s``)\n%s' % (self.name, to_yaml_type(self.type),
                                 doxygen2rst(indent(self.comment, 2)))
    if self.enum and self.enum.values:
      s += indent('\n\nPossible values:\n\n%s\n' % self.enum, 2)
    if self.nested_struct:
      s += indent('\n\nNested configuration flags:\n\n%s\n' %self.nested_struct,
                  2)
    return s

class NestedStruct(object):
  def __init__(self, name, comment):
    self.name = name
    self.comment = comment.strip()
    self.values = []

  def __str__(self):
    return self.comment + '\n' + '\n'.join(map(str, self.values))

class NestedField(object):
  def __init__(self, name, comment):
    self.name = name
    self.comment = comment.strip()

  def __str__(self):
    return '\n* ``%s`` %s' % (
        self.name,
        doxygen2rst(indent(self.comment, 2, indent_first_line=False)))

class Enum(object):
  def __init__(self, name, comment):
    self.name = name
    self.comment = comment.strip()
    self.values = []

  def __str__(self):
    return '\n'.join(map(str, self.values))

class NestedEnum(object):
  def __init__(self, name, enumtype, comment, values):
    self.name = name
    self.comment = comment
    self.values = values
    self.type = enumtype

  def __str__(self):
    s = '\n* ``%s %s``\n%s' % (to_yaml_type(self.type), self.name,
                                 doxygen2rst(indent(self.comment, 2)))
    s += indent('\nPossible values:\n\n', 2)
    s += indent('\n'.join(map(str, self.values)), 2)
    return s

class EnumValue(object):
  def __init__(self, name, comment, config):
    self.name = name
    self.comment = comment
    self.config = config

  def __str__(self):
    return '* ``%s`` (in configuration: ``%s``)\n%s' % (
        self.name,
        re.sub('.*_', '', self.config),
        doxygen2rst(indent(self.comment, 2)))


class OptionsReader:
  def __init__(self, header: TextIOWrapper):
    self.header = header
    self.in_code_block = False
    self.code_indent = 0
    self.lineno = 0
    self.last_err_lineno = -1

  def __file_path(self):
    return os.path.relpath(self.header.name)

  def __print_line(self, line: str):
    print(f'{self.lineno:>6} | {line}', file=sys.stderr)

  def __warning(self, msg: str, line: str):
    print(f'{self.__file_path()}:{self.lineno}: warning: {msg}:', file=sys.stderr)
    self.__print_line(line)

  def __clean_comment_line(self, line: str):
    match = re.match(r'^/// (?P<indent> +)?\\code(\{.(?P<lang>\w+)\})?$', line)
    if match:
      if self.in_code_block:
        self.__warning('`\\code` in another `\\code`', line)
      self.in_code_block = True
      indent_str = match.group('indent')
      if not indent_str:
        indent_str = ''
      self.code_indent = len(indent_str)
      lang = match.group('lang')
      if not lang:
        lang = 'c++'
      return f'\n{indent_str}.. code-block:: {lang}\n\n'

    endcode_match = re.match(r'^/// +\\endcode$', line)
    if endcode_match:
      if not self.in_code_block:
        self.__warning('no correct `\\code` found before this `\\endcode`', line)
      self.in_code_block = False
      return ''

    # check code block indentation
    if (self.in_code_block and not line == '///' and not
        line.startswith('///  ' + ' ' * self.code_indent)):
      if self.last_err_lineno == self.lineno - 1:
        self.__print_line(line)
      else:
        self.__warning('code block should be indented', line)
      self.last_err_lineno = self.lineno

    match = re.match(r'^/// \\warning$', line)
    if match:
      return '\n.. warning:: \n\n'

    endwarning_match = re.match(r'^/// +\\endwarning$', line)
    if endwarning_match:
      return ''
    return line[4:] + '\n'

  def read_options(self):
    class State:
      BeforeStruct, Finished, InStruct, InNestedStruct, InNestedFieldComment, \
        InFieldComment, InEnum, InEnumMemberComment = range(8)
    state = State.BeforeStruct

    options = []
    enums = {}
    nested_structs = {}
    comment = ''
    enum = None
    nested_struct = None
    version = None

    for line in self.header:
      self.lineno += 1
      line = line.strip()
      if state == State.BeforeStruct:
        if line in ('struct FormatStyle {', 'struct IncludeStyle {'):
          state = State.InStruct
      elif state == State.InStruct:
        if line.startswith('///'):
          state = State.InFieldComment
          comment = self.__clean_comment_line(line)
        elif line == '};':
          state = State.Finished
          break
      elif state == State.InFieldComment:
        if line.startswith(r'/// \version'):
          match = re.match(r'/// \\version\s*(?P<version>[0-9.]+)*', line)
          if match:
            version = match.group('version')
        elif line.startswith('///'):
          comment += self.__clean_comment_line(line)
        elif line.startswith('enum'):
          state = State.InEnum
          name = re.sub(r'enum\s+(\w+)\s*(:((\s*\w+)+)\s*)?\{', '\\1', line)
          enum = Enum(name, comment)
        elif line.startswith('struct'):
          state = State.InNestedStruct
          name = re.sub(r'struct\s+(\w+)\s*\{', '\\1', line)
          nested_struct = NestedStruct(name, comment)
        elif line.endswith(';'):
          prefix = '// '
          if line.startswith(prefix):
            line = line[len(prefix):]
          state = State.InStruct
          field_type, field_name = re.match(r'([<>:\w(,\s)]+)\s+(\w+);',
                                            line).groups()

          if not version:
            self.__warning(f'missing version for {field_name}', line)
          option = Option(str(field_name), str(field_type), comment, version)
          options.append(option)
          version = None
        else:
          raise Exception('Invalid format, expected comment, field or enum\n' + line)
      elif state == State.InNestedStruct:
        if line.startswith('///'):
          state = State.InNestedFieldComment
          comment = self.__clean_comment_line(line)
        elif line == '};':
          state = State.InStruct
          nested_structs[nested_struct.name] = nested_struct
      elif state == State.InNestedFieldComment:
        if line.startswith('///'):
          comment += self.__clean_comment_line(line)
        else:
          state = State.InNestedStruct
          field_type, field_name = re.match(r'([<>:\w(,\s)]+)\s+(\w+);', line).groups()
          if field_type in enums:
            nested_struct.values.append(NestedEnum(field_name,
                                                   field_type,
                                                   comment,
                                                   enums[field_type].values))
          else:
            nested_struct.values.append(NestedField(field_type + " " + field_name, comment))

      elif state == State.InEnum:
        if line.startswith('///'):
          state = State.InEnumMemberComment
          comment = self.__clean_comment_line(line)
        elif line == '};':
          state = State.InStruct
          enums[enum.name] = enum
        else:
          # Enum member without documentation. Must be documented where the enum
          # is used.
          pass
      elif state == State.InEnumMemberComment:
        if line.startswith('///'):
          comment += self.__clean_comment_line(line)
        else:
          state = State.InEnum
          val = line.replace(',', '')
          pos = val.find(" // ")
          if pos != -1:
            config = val[pos + 4:]
            val = val[:pos]
          else:
            config = val
          enum.values.append(EnumValue(val, comment, config))
    if state != State.Finished:
      raise Exception('Not finished by the end of file')

    for option in options:
      if option.type not in ['bool', 'unsigned', 'int', 'std::string',
                             'std::vector<std::string>',
                             'std::vector<IncludeCategory>',
                             'std::vector<RawStringFormat>']:
        if option.type in enums:
          option.enum = enums[option.type]
        elif option.type in nested_structs:
          option.nested_struct = nested_structs[option.type]
        else:
          raise Exception('Unknown type: %s' % option.type)
    return options


with open(FORMAT_STYLE_FILE) as f:
  opts = OptionsReader(f).read_options()
with open(INCLUDE_STYLE_FILE) as f:
  opts += OptionsReader(f).read_options()

opts = sorted(opts, key=lambda x: x.name)
options_text = '\n\n'.join(map(str, opts))

with open(DOC_FILE) as f:
  contents = f.read()

contents = substitute(contents, 'FORMAT_STYLE_OPTIONS', options_text)

with open(DOC_FILE, 'wb') as output:
  output.write(contents.encode())