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
361
362
363
364
365
366
367
368
369
370
371
372
|
#!/usr/bin/env python
# encoding: utf-8
"""Not really a lexer in the classical sense, but code to convert snippet
definitions into logical units called Tokens."""
import string
import re
from UltiSnips.compatibility import as_unicode
from UltiSnips.position import Position
from UltiSnips.text import unescape
class _TextIterator(object):
"""Helper class to make iterating over text easier."""
def __init__(self, text, offset):
self._text = as_unicode(text)
self._line = offset.line
self._col = offset.col
self._idx = 0
def __iter__(self):
"""Iterator interface."""
return self
def __next__(self):
"""Returns the next character."""
if self._idx >= len(self._text):
raise StopIteration
rv = self._text[self._idx]
if self._text[self._idx] in ("\n", "\r\n"):
self._line += 1
self._col = 0
else:
self._col += 1
self._idx += 1
return rv
next = __next__ # for python2
def peek(self, count=1):
"""Returns the next 'count' characters without advancing the stream."""
if count > 1: # This might return '' if nothing is found
return self._text[self._idx : self._idx + count]
try:
return self._text[self._idx]
except IndexError:
return None
@property
def pos(self):
"""Current position in the text."""
return Position(self._line, self._col)
def _parse_number(stream):
"""Expects the stream to contain a number next, returns the number without
consuming any more bytes."""
rv = ""
while stream.peek() and stream.peek() in string.digits:
rv += next(stream)
return int(rv)
def _parse_till_closing_brace(stream):
"""
Returns all chars till a non-escaped } is found. Other
non escaped { are taken into account and skipped over.
Will also consume the closing }, but not return it
"""
rv = ""
in_braces = 1
while True:
if EscapeCharToken.starts_here(stream, "{}"):
rv += next(stream) + next(stream)
else:
char = next(stream)
if char == "{":
in_braces += 1
elif char == "}":
in_braces -= 1
if in_braces == 0:
break
rv += char
return rv
def _parse_till_unescaped_char(stream, chars):
"""
Returns all chars till a non-escaped char is found.
Will also consume the closing char, but and return it as second
return value
"""
rv = ""
while True:
escaped = False
for char in chars:
if EscapeCharToken.starts_here(stream, char):
rv += next(stream) + next(stream)
escaped = True
if not escaped:
char = next(stream)
if char in chars:
break
rv += char
return rv, char
class Token(object):
"""Represents a Token as parsed from a snippet definition."""
def __init__(self, gen, indent):
self.initial_text = as_unicode("")
self.start = gen.pos
self._parse(gen, indent)
self.end = gen.pos
def _parse(self, stream, indent):
"""Parses the token from 'stream' with the current 'indent'."""
pass # Does nothing
class TabStopToken(Token):
"""${1:blub}"""
CHECK = re.compile(r"^\${\d+[:}]")
@classmethod
def starts_here(cls, stream):
"""Returns true if this token starts at the current position in
'stream'."""
return cls.CHECK.match(stream.peek(10)) is not None
def _parse(self, stream, indent):
next(stream) # $
next(stream) # {
self.number = _parse_number(stream)
if stream.peek() == ":":
next(stream)
self.initial_text = _parse_till_closing_brace(stream)
def __repr__(self):
return "TabStopToken(%r,%r,%r,%r)" % (
self.start,
self.end,
self.number,
self.initial_text,
)
class VisualToken(Token):
"""${VISUAL}"""
CHECK = re.compile(r"^\${VISUAL[:}/]")
@classmethod
def starts_here(cls, stream):
"""Returns true if this token starts at the current position in
'stream'."""
return cls.CHECK.match(stream.peek(10)) is not None
def _parse(self, stream, indent):
for _ in range(8): # ${VISUAL
next(stream)
if stream.peek() == ":":
next(stream)
self.alternative_text, char = _parse_till_unescaped_char(stream, "/}")
self.alternative_text = unescape(self.alternative_text)
if char == "/": # Transformation going on
try:
self.search = _parse_till_unescaped_char(stream, "/")[0]
self.replace = _parse_till_unescaped_char(stream, "/")[0]
self.options = _parse_till_closing_brace(stream)
except StopIteration:
raise RuntimeError(
"Invalid ${VISUAL} transformation! Forgot to escape a '/'?"
)
else:
self.search = None
self.replace = None
self.options = None
def __repr__(self):
return "VisualToken(%r,%r)" % (self.start, self.end)
class TransformationToken(Token):
"""${1/match/replace/options}"""
CHECK = re.compile(r"^\${\d+\/")
@classmethod
def starts_here(cls, stream):
"""Returns true if this token starts at the current position in
'stream'."""
return cls.CHECK.match(stream.peek(10)) is not None
def _parse(self, stream, indent):
next(stream) # $
next(stream) # {
self.number = _parse_number(stream)
next(stream) # /
self.search = _parse_till_unescaped_char(stream, "/")[0]
self.replace = _parse_till_unescaped_char(stream, "/")[0]
self.options = _parse_till_closing_brace(stream)
def __repr__(self):
return "TransformationToken(%r,%r,%r,%r,%r)" % (
self.start,
self.end,
self.number,
self.search,
self.replace,
)
class MirrorToken(Token):
"""$1."""
CHECK = re.compile(r"^\$\d+")
@classmethod
def starts_here(cls, stream):
"""Returns true if this token starts at the current position in
'stream'."""
return cls.CHECK.match(stream.peek(10)) is not None
def _parse(self, stream, indent):
next(stream) # $
self.number = _parse_number(stream)
def __repr__(self):
return "MirrorToken(%r,%r,%r)" % (self.start, self.end, self.number)
class EscapeCharToken(Token):
"""\\n."""
@classmethod
def starts_here(cls, stream, chars=r"{}\$`"):
"""Returns true if this token starts at the current position in
'stream'."""
cs = stream.peek(2)
if len(cs) == 2 and cs[0] == "\\" and cs[1] in chars:
return True
def _parse(self, stream, indent):
next(stream) # \
self.initial_text = next(stream)
def __repr__(self):
return "EscapeCharToken(%r,%r,%r)" % (self.start, self.end, self.initial_text)
class ShellCodeToken(Token):
"""`echo "hi"`"""
@classmethod
def starts_here(cls, stream):
"""Returns true if this token starts at the current position in
'stream'."""
return stream.peek(1) == "`"
def _parse(self, stream, indent):
next(stream) # `
self.code = _parse_till_unescaped_char(stream, "`")[0]
def __repr__(self):
return "ShellCodeToken(%r,%r,%r)" % (self.start, self.end, self.code)
class PythonCodeToken(Token):
"""`!p snip.rv = "Hi"`"""
CHECK = re.compile(r"^`!p\s")
@classmethod
def starts_here(cls, stream):
"""Returns true if this token starts at the current position in
'stream'."""
return cls.CHECK.match(stream.peek(4)) is not None
def _parse(self, stream, indent):
for _ in range(3):
next(stream) # `!p
if stream.peek() in "\t ":
next(stream)
code = _parse_till_unescaped_char(stream, "`")[0]
# Strip the indent if any
if len(indent):
lines = code.splitlines()
self.code = lines[0] + "\n"
self.code += "\n".join([l[len(indent) :] for l in lines[1:]])
else:
self.code = code
self.indent = indent
def __repr__(self):
return "PythonCodeToken(%r,%r,%r)" % (self.start, self.end, self.code)
class VimLCodeToken(Token):
"""`!v g:hi`"""
CHECK = re.compile(r"^`!v\s")
@classmethod
def starts_here(cls, stream):
"""Returns true if this token starts at the current position in
'stream'."""
return cls.CHECK.match(stream.peek(4)) is not None
def _parse(self, stream, indent):
for _ in range(4):
next(stream) # `!v
self.code = _parse_till_unescaped_char(stream, "`")[0]
def __repr__(self):
return "VimLCodeToken(%r,%r,%r)" % (self.start, self.end, self.code)
class EndOfTextToken(Token):
"""Appears at the end of the text."""
def __repr__(self):
return "EndOfText(%r)" % self.end
def tokenize(text, indent, offset, allowed_tokens):
"""Returns an iterator of tokens of 'text'['offset':] which is assumed to
have 'indent' as the whitespace of the begging of the lines. Only
'allowed_tokens' are considered to be valid tokens."""
stream = _TextIterator(text, offset)
try:
while True:
done_something = False
for token in allowed_tokens:
if token.starts_here(stream):
yield token(stream, indent)
done_something = True
break
if not done_something:
next(stream)
except StopIteration:
yield EndOfTextToken(stream, indent)
|
