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
|
# Copyright (C) 2013 Google Inc.
#
# This file is part of YouCompleteMe.
#
# YouCompleteMe is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# YouCompleteMe is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with YouCompleteMe. If not, see <http://www.gnu.org/licenses/>.
from __future__ import unicode_literals
from __future__ import print_function
from __future__ import division
from __future__ import absolute_import
from future import standard_library
standard_library.install_aliases()
from builtins import * # noqa
from future.utils import itervalues
import re
import vim
from ycm import vimsupport
SYNTAX_GROUP_REGEX = re.compile(
r"""^
(?P<group_name>\w+)
\s+
xxx
\s+
(?P<content>.+?)
$""",
re.VERBOSE )
KEYWORD_REGEX = re.compile( r'^[\w,]+$' )
SYNTAX_ARGUMENT_REGEX = re.compile(
r"^\w+=.*$" )
SYNTAX_ARGUMENTS = set([
'cchar',
'conceal',
'contained',
'containedin',
'nextgroup',
'skipempty',
'skipnl',
'skipwhite',
'transparent',
'concealends',
'contains',
'display',
'extend',
'fold',
'oneline',
'keepend',
'excludenl',
])
# We want to parse lines starting with these args
ALLOWED_SYNTAX_ARGUMENTS = set([
'contained',
])
# These are the parent groups from which we want to extract keywords
ROOT_GROUPS = set([
'Statement',
'Boolean',
'Include',
'Type',
'Identifier',
])
class SyntaxGroup( object ):
def __init__( self, name, lines = None ):
self.name = name
self.lines = lines if lines else []
self.children = []
def SyntaxKeywordsForCurrentBuffer():
vim.command( 'redir => b:ycm_syntax' )
vim.command( 'silent! syntax list' )
vim.command( 'redir END' )
syntax_output = vimsupport.VimExpressionToPythonType( 'b:ycm_syntax' )
return _KeywordsFromSyntaxListOutput( syntax_output )
def _KeywordsFromSyntaxListOutput( syntax_output ):
group_name_to_group = _SyntaxGroupsFromOutput( syntax_output )
_ConnectGroupChildren( group_name_to_group )
groups_with_keywords = []
for root_group in ROOT_GROUPS:
groups_with_keywords.extend(
_GetAllDescendentats( group_name_to_group[ root_group ] ) )
keywords = []
for group in groups_with_keywords:
keywords.extend( _ExtractKeywordsFromGroup( group ) )
return set( keywords )
def _SyntaxGroupsFromOutput( syntax_output ):
group_name_to_group = _CreateInitialGroupMap()
lines = syntax_output.split( '\n' )
looking_for_group = True
current_group = None
for line in lines:
if not line:
continue
match = SYNTAX_GROUP_REGEX.search( line )
if match:
if looking_for_group:
looking_for_group = False
else:
group_name_to_group[ current_group.name ] = current_group
current_group = SyntaxGroup( match.group( 'group_name' ),
[ match.group( 'content').strip() ] )
else:
if looking_for_group:
continue
if line[ 0 ] == ' ' or line[ 0 ] == '\t':
current_group.lines.append( line.strip() )
if current_group:
group_name_to_group[ current_group.name ] = current_group
return group_name_to_group
def _CreateInitialGroupMap():
def AddToGroupMap( name, parent ):
new_group = SyntaxGroup( name )
group_name_to_group[ name ] = new_group
parent.children.append( new_group )
statement_group = SyntaxGroup( 'Statement' )
type_group = SyntaxGroup( 'Type' )
identifier_group = SyntaxGroup( 'Identifier' )
# See `:h group-name` for details on how the initial group hierarchy is built
group_name_to_group = {
'Statement': statement_group,
'Type': type_group,
'Boolean': SyntaxGroup( 'Boolean' ),
'Include': SyntaxGroup( 'Include' ),
'Identifier': identifier_group,
}
AddToGroupMap( 'Conditional', statement_group )
AddToGroupMap( 'Repeat' , statement_group )
AddToGroupMap( 'Label' , statement_group )
AddToGroupMap( 'Operator' , statement_group )
AddToGroupMap( 'Keyword' , statement_group )
AddToGroupMap( 'Exception' , statement_group )
AddToGroupMap( 'StorageClass', type_group )
AddToGroupMap( 'Structure' , type_group )
AddToGroupMap( 'Typedef' , type_group )
AddToGroupMap( 'Function', identifier_group )
return group_name_to_group
def _ConnectGroupChildren( group_name_to_group ):
def GetParentNames( group ):
links_to = 'links to '
parent_names = []
for line in group.lines:
if line.startswith( links_to ):
parent_names.append( line[ len( links_to ): ] )
return parent_names
for group in itervalues( group_name_to_group ):
parent_names = GetParentNames( group )
for parent_name in parent_names:
try:
parent_group = group_name_to_group[ parent_name ]
except KeyError:
continue
parent_group.children.append( group )
def _GetAllDescendentats( root_group ):
descendants = []
for child in root_group.children:
descendants.append( child )
descendants.extend( _GetAllDescendentats( child ) )
return descendants
def _ExtractKeywordsFromGroup( group ):
keywords = []
for line in group.lines:
if line.startswith( 'links to ' ):
continue
words = line.split()
if not words or ( words[ 0 ] in SYNTAX_ARGUMENTS and
words[ 0 ] not in ALLOWED_SYNTAX_ARGUMENTS ):
continue
for word in words:
if ( word not in SYNTAX_ARGUMENTS and
not SYNTAX_ARGUMENT_REGEX.match( word ) and
KEYWORD_REGEX.match( word ) ):
if word.endswith( ',' ):
word = word[ :-1 ]
keywords.append( word )
return keywords
|