summaryrefslogtreecommitdiff
path: root/pygments/lexers/robotframework.py
blob: eab06efef07762703d3c4d1237a3f143267d4767 (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
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
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
# -*- coding: utf-8 -*-
"""
    pygments.lexers.robotframework
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

    Lexer for Robot Framework.

    :copyright: Copyright 2006-2015 by the Pygments team, see AUTHORS.
    :license: BSD, see LICENSE for details.
"""

#  Copyright 2012 Nokia Siemens Networks Oyj
#
#  Licensed under the Apache License, Version 2.0 (the "License");
#  you may not use this file except in compliance with the License.
#  You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
#  Unless required by applicable law or agreed to in writing, software
#  distributed under the License is distributed on an "AS IS" BASIS,
#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#  See the License for the specific language governing permissions and
#  limitations under the License.

import re

from pygments.lexer import Lexer
from pygments.token import Token
from pygments.util import text_type

__all__ = ['RobotFrameworkLexer']


HEADING = Token.Generic.Heading
SETTING = Token.Keyword.Namespace
IMPORT = Token.Name.Namespace
TC_KW_NAME = Token.Generic.Subheading
KEYWORD = Token.Name.Function
ARGUMENT = Token.String
VARIABLE = Token.Name.Variable
COMMENT = Token.Comment
SEPARATOR = Token.Punctuation
SYNTAX = Token.Punctuation
GHERKIN = Token.Generic.Emph
ERROR = Token.Error


def normalize(string, remove=''):
    string = string.lower()
    for char in remove + ' ':
        if char in string:
            string = string.replace(char, '')
    return string


class RobotFrameworkLexer(Lexer):
    """
    For `Robot Framework <http://robotframework.org>`_ test data.

    Supports both space and pipe separated plain text formats.

    .. versionadded:: 1.6
    """
    name = 'RobotFramework'
    aliases = ['robotframework']
    filenames = ['*.txt', '*.robot']
    mimetypes = ['text/x-robotframework']

    def __init__(self, **options):
        options['tabsize'] = 2
        options['encoding'] = 'UTF-8'
        Lexer.__init__(self, **options)

    def get_tokens_unprocessed(self, text):
        row_tokenizer = RowTokenizer()
        var_tokenizer = VariableTokenizer()
        index = 0
        for row in text.splitlines():
            for value, token in row_tokenizer.tokenize(row):
                for value, token in var_tokenizer.tokenize(value, token):
                    if value:
                        yield index, token, text_type(value)
                        index += len(value)


class VariableTokenizer(object):

    def tokenize(self, string, token):
        var = VariableSplitter(string, identifiers='$@%&')
        if var.start < 0 or token in (COMMENT, ERROR):
            yield string, token
            return
        for value, token in self._tokenize(var, string, token):
            if value:
                yield value, token

    def _tokenize(self, var, string, orig_token):
        before = string[:var.start]
        yield before, orig_token
        yield var.identifier + '{', SYNTAX
        for value, token in self.tokenize(var.base, VARIABLE):
            yield value, token
        yield '}', SYNTAX
        if var.index:
            yield '[', SYNTAX
            for value, token in self.tokenize(var.index, VARIABLE):
                yield value, token
            yield ']', SYNTAX
        for value, token in self.tokenize(string[var.end:], orig_token):
            yield value, token


class RowTokenizer(object):

    def __init__(self):
        self._table = UnknownTable()
        self._splitter = RowSplitter()
        testcases = TestCaseTable()
        settings = SettingTable(testcases.set_default_template)
        variables = VariableTable()
        keywords = KeywordTable()
        self._tables = {'settings': settings, 'setting': settings,
                        'metadata': settings,
                        'variables': variables, 'variable': variables,
                        'testcases': testcases, 'testcase': testcases,
                        'keywords': keywords, 'keyword': keywords,
                        'userkeywords': keywords, 'userkeyword': keywords}

    def tokenize(self, row):
        commented = False
        heading = False
        for index, value in enumerate(self._splitter.split(row)):
            # First value, and every second after that, is a separator.
            index, separator = divmod(index-1, 2)
            if value.startswith('#'):
                commented = True
            elif index == 0 and value.startswith('*'):
                self._table = self._start_table(value)
                heading = True
            for value, token in self._tokenize(value, index, commented,
                                               separator, heading):
                yield value, token
        self._table.end_row()

    def _start_table(self, header):
        name = normalize(header, remove='*')
        return self._tables.get(name, UnknownTable())

    def _tokenize(self, value, index, commented, separator, heading):
        if commented:
            yield value, COMMENT
        elif separator:
            yield value, SEPARATOR
        elif heading:
            yield value, HEADING
        else:
            for value, token in self._table.tokenize(value, index):
                yield value, token


class RowSplitter(object):
    _space_splitter = re.compile('( {2,})')
    _pipe_splitter = re.compile('((?:^| +)\|(?: +|$))')

    def split(self, row):
        splitter = (row.startswith('| ') and self._split_from_pipes
                    or self._split_from_spaces)
        for value in splitter(row):
            yield value
        yield '\n'

    def _split_from_spaces(self, row):
        yield ''  # Start with (pseudo)separator similarly as with pipes
        for value in self._space_splitter.split(row):
            yield value

    def _split_from_pipes(self, row):
        _, separator, rest = self._pipe_splitter.split(row, 1)
        yield separator
        while self._pipe_splitter.search(rest):
            cell, separator, rest = self._pipe_splitter.split(rest, 1)
            yield cell
            yield separator
        yield rest


class Tokenizer(object):
    _tokens = None

    def __init__(self):
        self._index = 0

    def tokenize(self, value):
        values_and_tokens = self._tokenize(value, self._index)
        self._index += 1
        if isinstance(values_and_tokens, type(Token)):
            values_and_tokens = [(value, values_and_tokens)]
        return values_and_tokens

    def _tokenize(self, value, index):
        index = min(index, len(self._tokens) - 1)
        return self._tokens[index]

    def _is_assign(self, value):
        if value.endswith('='):
            value = value[:-1].strip()
        var = VariableSplitter(value, identifiers='$@&')
        return var.start == 0 and var.end == len(value)


class Comment(Tokenizer):
    _tokens = (COMMENT,)


class Setting(Tokenizer):
    _tokens = (SETTING, ARGUMENT)
    _keyword_settings = ('suitesetup', 'suiteprecondition', 'suiteteardown',
                         'suitepostcondition', 'testsetup', 'testprecondition',
                         'testteardown', 'testpostcondition', 'testtemplate')
    _import_settings = ('library', 'resource', 'variables')
    _other_settings = ('documentation', 'metadata', 'forcetags', 'defaulttags',
                       'testtimeout')
    _custom_tokenizer = None

    def __init__(self, template_setter=None):
        Tokenizer.__init__(self)
        self._template_setter = template_setter

    def _tokenize(self, value, index):
        if index == 1 and self._template_setter:
            self._template_setter(value)
        if index == 0:
            normalized = normalize(value)
            if normalized in self._keyword_settings:
                self._custom_tokenizer = KeywordCall(support_assign=False)
            elif normalized in self._import_settings:
                self._custom_tokenizer = ImportSetting()
            elif normalized not in self._other_settings:
                return ERROR
        elif self._custom_tokenizer:
            return self._custom_tokenizer.tokenize(value)
        return Tokenizer._tokenize(self, value, index)


class ImportSetting(Tokenizer):
    _tokens = (IMPORT, ARGUMENT)


class TestCaseSetting(Setting):
    _keyword_settings = ('setup', 'precondition', 'teardown', 'postcondition',
                         'template')
    _import_settings = ()
    _other_settings = ('documentation', 'tags', 'timeout')

    def _tokenize(self, value, index):
        if index == 0:
            type = Setting._tokenize(self, value[1:-1], index)
            return [('[', SYNTAX), (value[1:-1], type), (']', SYNTAX)]
        return Setting._tokenize(self, value, index)


class KeywordSetting(TestCaseSetting):
    _keyword_settings = ('teardown',)
    _other_settings = ('documentation', 'arguments', 'return', 'timeout', 'tags')


class Variable(Tokenizer):
    _tokens = (SYNTAX, ARGUMENT)

    def _tokenize(self, value, index):
        if index == 0 and not self._is_assign(value):
            return ERROR
        return Tokenizer._tokenize(self, value, index)


class KeywordCall(Tokenizer):
    _tokens = (KEYWORD, ARGUMENT)

    def __init__(self, support_assign=True):
        Tokenizer.__init__(self)
        self._keyword_found = not support_assign
        self._assigns = 0

    def _tokenize(self, value, index):
        if not self._keyword_found and self._is_assign(value):
            self._assigns += 1
            return SYNTAX  # VariableTokenizer tokenizes this later.
        if self._keyword_found:
            return Tokenizer._tokenize(self, value, index - self._assigns)
        self._keyword_found = True
        return GherkinTokenizer().tokenize(value, KEYWORD)


class GherkinTokenizer(object):
    _gherkin_prefix = re.compile('^(Given|When|Then|And) ', re.IGNORECASE)

    def tokenize(self, value, token):
        match = self._gherkin_prefix.match(value)
        if not match:
            return [(value, token)]
        end = match.end()
        return [(value[:end], GHERKIN), (value[end:], token)]


class TemplatedKeywordCall(Tokenizer):
    _tokens = (ARGUMENT,)


class ForLoop(Tokenizer):

    def __init__(self):
        Tokenizer.__init__(self)
        self._in_arguments = False

    def _tokenize(self, value, index):
        token = self._in_arguments and ARGUMENT or SYNTAX
        if value.upper() in ('IN', 'IN RANGE'):
            self._in_arguments = True
        return token


class _Table(object):
    _tokenizer_class = None

    def __init__(self, prev_tokenizer=None):
        self._tokenizer = self._tokenizer_class()
        self._prev_tokenizer = prev_tokenizer
        self._prev_values_on_row = []

    def tokenize(self, value, index):
        if self._continues(value, index):
            self._tokenizer = self._prev_tokenizer
            yield value, SYNTAX
        else:
            for value_and_token in self._tokenize(value, index):
                yield value_and_token
        self._prev_values_on_row.append(value)

    def _continues(self, value, index):
        return value == '...' and all(self._is_empty(t)
                                      for t in self._prev_values_on_row)

    def _is_empty(self, value):
        return value in ('', '\\')

    def _tokenize(self, value, index):
        return self._tokenizer.tokenize(value)

    def end_row(self):
        self.__init__(prev_tokenizer=self._tokenizer)


class UnknownTable(_Table):
    _tokenizer_class = Comment

    def _continues(self, value, index):
        return False


class VariableTable(_Table):
    _tokenizer_class = Variable


class SettingTable(_Table):
    _tokenizer_class = Setting

    def __init__(self, template_setter, prev_tokenizer=None):
        _Table.__init__(self, prev_tokenizer)
        self._template_setter = template_setter

    def _tokenize(self, value, index):
        if index == 0 and normalize(value) == 'testtemplate':
            self._tokenizer = Setting(self._template_setter)
        return _Table._tokenize(self, value, index)

    def end_row(self):
        self.__init__(self._template_setter, prev_tokenizer=self._tokenizer)


class TestCaseTable(_Table):
    _setting_class = TestCaseSetting
    _test_template = None
    _default_template = None

    @property
    def _tokenizer_class(self):
        if self._test_template or (self._default_template and
                                   self._test_template is not False):
            return TemplatedKeywordCall
        return KeywordCall

    def _continues(self, value, index):
        return index > 0 and _Table._continues(self, value, index)

    def _tokenize(self, value, index):
        if index == 0:
            if value:
                self._test_template = None
            return GherkinTokenizer().tokenize(value, TC_KW_NAME)
        if index == 1 and self._is_setting(value):
            if self._is_template(value):
                self._test_template = False
                self._tokenizer = self._setting_class(self.set_test_template)
            else:
                self._tokenizer = self._setting_class()
        if index == 1 and self._is_for_loop(value):
            self._tokenizer = ForLoop()
        if index == 1 and self._is_empty(value):
            return [(value, SYNTAX)]
        return _Table._tokenize(self, value, index)

    def _is_setting(self, value):
        return value.startswith('[') and value.endswith(']')

    def _is_template(self, value):
        return normalize(value) == '[template]'

    def _is_for_loop(self, value):
        return value.startswith(':') and normalize(value, remove=':') == 'for'

    def set_test_template(self, template):
        self._test_template = self._is_template_set(template)

    def set_default_template(self, template):
        self._default_template = self._is_template_set(template)

    def _is_template_set(self, template):
        return normalize(template) not in ('', '\\', 'none', '${empty}')


class KeywordTable(TestCaseTable):
    _tokenizer_class = KeywordCall
    _setting_class = KeywordSetting

    def _is_template(self, value):
        return False


# Following code copied directly from Robot Framework 2.7.5.

class VariableSplitter:

    def __init__(self, string, identifiers):
        self.identifier = None
        self.base = None
        self.index = None
        self.start = -1
        self.end = -1
        self._identifiers = identifiers
        self._may_have_internal_variables = False
        try:
            self._split(string)
        except ValueError:
            pass
        else:
            self._finalize()

    def get_replaced_base(self, variables):
        if self._may_have_internal_variables:
            return variables.replace_string(self.base)
        return self.base

    def _finalize(self):
        self.identifier = self._variable_chars[0]
        self.base = ''.join(self._variable_chars[2:-1])
        self.end = self.start + len(self._variable_chars)
        if self._has_list_or_dict_variable_index():
            self.index = ''.join(self._list_and_dict_variable_index_chars[1:-1])
            self.end += len(self._list_and_dict_variable_index_chars)

    def _has_list_or_dict_variable_index(self):
        return self._list_and_dict_variable_index_chars\
        and self._list_and_dict_variable_index_chars[-1] == ']'

    def _split(self, string):
        start_index, max_index = self._find_variable(string)
        self.start = start_index
        self._open_curly = 1
        self._state = self._variable_state
        self._variable_chars = [string[start_index], '{']
        self._list_and_dict_variable_index_chars = []
        self._string = string
        start_index += 2
        for index, char in enumerate(string[start_index:]):
            index += start_index  # Giving start to enumerate only in Py 2.6+
            try:
                self._state(char, index)
            except StopIteration:
                return
            if index  == max_index and not self._scanning_list_variable_index():
                return

    def _scanning_list_variable_index(self):
        return self._state in [self._waiting_list_variable_index_state,
                               self._list_variable_index_state]

    def _find_variable(self, string):
        max_end_index = string.rfind('}')
        if max_end_index == -1:
            raise ValueError('No variable end found')
        if self._is_escaped(string, max_end_index):
            return self._find_variable(string[:max_end_index])
        start_index = self._find_start_index(string, 1, max_end_index)
        if start_index == -1:
            raise ValueError('No variable start found')
        return start_index, max_end_index

    def _find_start_index(self, string, start, end):
        index = string.find('{', start, end) - 1
        if index < 0:
            return -1
        if self._start_index_is_ok(string, index):
            return index
        return self._find_start_index(string, index+2, end)

    def _start_index_is_ok(self, string, index):
        return string[index] in self._identifiers\
        and not self._is_escaped(string, index)

    def _is_escaped(self, string, index):
        escaped = False
        while index > 0 and string[index-1] == '\\':
            index -= 1
            escaped = not escaped
        return escaped

    def _variable_state(self, char, index):
        self._variable_chars.append(char)
        if char == '}' and not self._is_escaped(self._string, index):
            self._open_curly -= 1
            if self._open_curly == 0:
                if not self._is_list_or_dict_variable():
                    raise StopIteration
                self._state = self._waiting_list_variable_index_state
        elif char in self._identifiers:
            self._state = self._internal_variable_start_state

    def _is_list_or_dict_variable(self):
        return self._variable_chars[0] in ('@','&')

    def _internal_variable_start_state(self, char, index):
        self._state = self._variable_state
        if char == '{':
            self._variable_chars.append(char)
            self._open_curly += 1
            self._may_have_internal_variables = True
        else:
            self._variable_state(char, index)

    def _waiting_list_variable_index_state(self, char, index):
        if char != '[':
            raise StopIteration
        self._list_and_dict_variable_index_chars.append(char)
        self._state = self._list_variable_index_state

    def _list_variable_index_state(self, char, index):
        self._list_and_dict_variable_index_chars.append(char)
        if char == ']':
            raise StopIteration