Mercurial Repositories > eric / file comparison
comparison: ThirdParty/Pygments/pygments/lexers/data.py
ThirdParty/Pygments/pygments/lexers/data.py
- changeset 4172
- 4f20dba37ab6
- child 4697
- c2e9bf425554
equal
deleted
inserted
replaced
| 4170:8bc578136279 | 4172:4f20dba37ab6 |
|---|---|
| 1 # -*- coding: utf-8 -*- | |
| 2 """ | |
| 3 pygments.lexers.data | |
| 4 ~~~~~~~~~~~~~~~~~~~~ | |
| 5 | |
| 6 Lexers for data file format. | |
| 7 | |
| 8 :copyright: Copyright 2006-2014 by the Pygments team, see AUTHORS. | |
| 9 :license: BSD, see LICENSE for details. | |
| 10 """ | |
| 11 | |
| 12 import re | |
| 13 | |
| 14 from pygments.lexer import RegexLexer, ExtendedRegexLexer, LexerContext, \ | |
| 15 include, bygroups, inherit | |
| 16 from pygments.token import Text, Comment, Keyword, Name, String, Number, \ | |
| 17 Punctuation, Literal | |
| 18 | |
| 19 __all__ = ['YamlLexer', 'JsonLexer', 'JsonLdLexer'] | |
| 20 | |
| 21 | |
| 22 class YamlLexerContext(LexerContext): | |
| 23 """Indentation context for the YAML lexer.""" | |
| 24 | |
| 25 def __init__(self, *args, **kwds): | |
| 26 super(YamlLexerContext, self).__init__(*args, **kwds) | |
| 27 self.indent_stack = [] | |
| 28 self.indent = -1 | |
| 29 self.next_indent = 0 | |
| 30 self.block_scalar_indent = None | |
| 31 | |
| 32 | |
| 33 class YamlLexer(ExtendedRegexLexer): | |
| 34 """ | |
| 35 Lexer for `YAML <http://yaml.org/>`_, a human-friendly data serialization | |
| 36 language. | |
| 37 | |
| 38 .. versionadded:: 0.11 | |
| 39 """ | |
| 40 | |
| 41 name = 'YAML' | |
| 42 aliases = ['yaml'] | |
| 43 filenames = ['*.yaml', '*.yml'] | |
| 44 mimetypes = ['text/x-yaml'] | |
| 45 | |
| 46 def something(token_class): | |
| 47 """Do not produce empty tokens.""" | |
| 48 def callback(lexer, match, context): | |
| 49 text = match.group() | |
| 50 if not text: | |
| 51 return | |
| 52 yield match.start(), token_class, text | |
| 53 context.pos = match.end() | |
| 54 return callback | |
| 55 | |
| 56 def reset_indent(token_class): | |
| 57 """Reset the indentation levels.""" | |
| 58 def callback(lexer, match, context): | |
| 59 text = match.group() | |
| 60 context.indent_stack = [] | |
| 61 context.indent = -1 | |
| 62 context.next_indent = 0 | |
| 63 context.block_scalar_indent = None | |
| 64 yield match.start(), token_class, text | |
| 65 context.pos = match.end() | |
| 66 return callback | |
| 67 | |
| 68 def save_indent(token_class, start=False): | |
| 69 """Save a possible indentation level.""" | |
| 70 def callback(lexer, match, context): | |
| 71 text = match.group() | |
| 72 extra = '' | |
| 73 if start: | |
| 74 context.next_indent = len(text) | |
| 75 if context.next_indent < context.indent: | |
| 76 while context.next_indent < context.indent: | |
| 77 context.indent = context.indent_stack.pop() | |
| 78 if context.next_indent > context.indent: | |
| 79 extra = text[context.indent:] | |
| 80 text = text[:context.indent] | |
| 81 else: | |
| 82 context.next_indent += len(text) | |
| 83 if text: | |
| 84 yield match.start(), token_class, text | |
| 85 if extra: | |
| 86 yield match.start()+len(text), token_class.Error, extra | |
| 87 context.pos = match.end() | |
| 88 return callback | |
| 89 | |
| 90 def set_indent(token_class, implicit=False): | |
| 91 """Set the previously saved indentation level.""" | |
| 92 def callback(lexer, match, context): | |
| 93 text = match.group() | |
| 94 if context.indent < context.next_indent: | |
| 95 context.indent_stack.append(context.indent) | |
| 96 context.indent = context.next_indent | |
| 97 if not implicit: | |
| 98 context.next_indent += len(text) | |
| 99 yield match.start(), token_class, text | |
| 100 context.pos = match.end() | |
| 101 return callback | |
| 102 | |
| 103 def set_block_scalar_indent(token_class): | |
| 104 """Set an explicit indentation level for a block scalar.""" | |
| 105 def callback(lexer, match, context): | |
| 106 text = match.group() | |
| 107 context.block_scalar_indent = None | |
| 108 if not text: | |
| 109 return | |
| 110 increment = match.group(1) | |
| 111 if increment: | |
| 112 current_indent = max(context.indent, 0) | |
| 113 increment = int(increment) | |
| 114 context.block_scalar_indent = current_indent + increment | |
| 115 if text: | |
| 116 yield match.start(), token_class, text | |
| 117 context.pos = match.end() | |
| 118 return callback | |
| 119 | |
| 120 def parse_block_scalar_empty_line(indent_token_class, content_token_class): | |
| 121 """Process an empty line in a block scalar.""" | |
| 122 def callback(lexer, match, context): | |
| 123 text = match.group() | |
| 124 if (context.block_scalar_indent is None or | |
| 125 len(text) <= context.block_scalar_indent): | |
| 126 if text: | |
| 127 yield match.start(), indent_token_class, text | |
| 128 else: | |
| 129 indentation = text[:context.block_scalar_indent] | |
| 130 content = text[context.block_scalar_indent:] | |
| 131 yield match.start(), indent_token_class, indentation | |
| 132 yield (match.start()+context.block_scalar_indent, | |
| 133 content_token_class, content) | |
| 134 context.pos = match.end() | |
| 135 return callback | |
| 136 | |
| 137 def parse_block_scalar_indent(token_class): | |
| 138 """Process indentation spaces in a block scalar.""" | |
| 139 def callback(lexer, match, context): | |
| 140 text = match.group() | |
| 141 if context.block_scalar_indent is None: | |
| 142 if len(text) <= max(context.indent, 0): | |
| 143 context.stack.pop() | |
| 144 context.stack.pop() | |
| 145 return | |
| 146 context.block_scalar_indent = len(text) | |
| 147 else: | |
| 148 if len(text) < context.block_scalar_indent: | |
| 149 context.stack.pop() | |
| 150 context.stack.pop() | |
| 151 return | |
| 152 if text: | |
| 153 yield match.start(), token_class, text | |
| 154 context.pos = match.end() | |
| 155 return callback | |
| 156 | |
| 157 def parse_plain_scalar_indent(token_class): | |
| 158 """Process indentation spaces in a plain scalar.""" | |
| 159 def callback(lexer, match, context): | |
| 160 text = match.group() | |
| 161 if len(text) <= context.indent: | |
| 162 context.stack.pop() | |
| 163 context.stack.pop() | |
| 164 return | |
| 165 if text: | |
| 166 yield match.start(), token_class, text | |
| 167 context.pos = match.end() | |
| 168 return callback | |
| 169 | |
| 170 tokens = { | |
| 171 # the root rules | |
| 172 'root': [ | |
| 173 # ignored whitespaces | |
| 174 (r'[ ]+(?=#|$)', Text), | |
| 175 # line breaks | |
| 176 (r'\n+', Text), | |
| 177 # a comment | |
| 178 (r'#[^\n]*', Comment.Single), | |
| 179 # the '%YAML' directive | |
| 180 (r'^%YAML(?=[ ]|$)', reset_indent(Name.Tag), 'yaml-directive'), | |
| 181 # the %TAG directive | |
| 182 (r'^%TAG(?=[ ]|$)', reset_indent(Name.Tag), 'tag-directive'), | |
| 183 # document start and document end indicators | |
| 184 (r'^(?:---|\.\.\.)(?=[ ]|$)', reset_indent(Name.Namespace), | |
| 185 'block-line'), | |
| 186 # indentation spaces | |
| 187 (r'[ ]*(?!\s|$)', save_indent(Text, start=True), | |
| 188 ('block-line', 'indentation')), | |
| 189 ], | |
| 190 | |
| 191 # trailing whitespaces after directives or a block scalar indicator | |
| 192 'ignored-line': [ | |
| 193 # ignored whitespaces | |
| 194 (r'[ ]+(?=#|$)', Text), | |
| 195 # a comment | |
| 196 (r'#[^\n]*', Comment.Single), | |
| 197 # line break | |
| 198 (r'\n', Text, '#pop:2'), | |
| 199 ], | |
| 200 | |
| 201 # the %YAML directive | |
| 202 'yaml-directive': [ | |
| 203 # the version number | |
| 204 (r'([ ]+)([0-9]+\.[0-9]+)', | |
| 205 bygroups(Text, Number), 'ignored-line'), | |
| 206 ], | |
| 207 | |
| 208 # the %YAG directive | |
| 209 'tag-directive': [ | |
| 210 # a tag handle and the corresponding prefix | |
| 211 (r'([ ]+)(!|![\w-]*!)' | |
| 212 r'([ ]+)(!|!?[\w;/?:@&=+$,.!~*\'()\[\]%-]+)', | |
| 213 bygroups(Text, Keyword.Type, Text, Keyword.Type), | |
| 214 'ignored-line'), | |
| 215 ], | |
| 216 | |
| 217 # block scalar indicators and indentation spaces | |
| 218 'indentation': [ | |
| 219 # trailing whitespaces are ignored | |
| 220 (r'[ ]*$', something(Text), '#pop:2'), | |
| 221 # whitespaces preceeding block collection indicators | |
| 222 (r'[ ]+(?=[?:-](?:[ ]|$))', save_indent(Text)), | |
| 223 # block collection indicators | |
| 224 (r'[?:-](?=[ ]|$)', set_indent(Punctuation.Indicator)), | |
| 225 # the beginning a block line | |
| 226 (r'[ ]*', save_indent(Text), '#pop'), | |
| 227 ], | |
| 228 | |
| 229 # an indented line in the block context | |
| 230 'block-line': [ | |
| 231 # the line end | |
| 232 (r'[ ]*(?=#|$)', something(Text), '#pop'), | |
| 233 # whitespaces separating tokens | |
| 234 (r'[ ]+', Text), | |
| 235 # tags, anchors and aliases, | |
| 236 include('descriptors'), | |
| 237 # block collections and scalars | |
| 238 include('block-nodes'), | |
| 239 # flow collections and quoted scalars | |
| 240 include('flow-nodes'), | |
| 241 # a plain scalar | |
| 242 (r'(?=[^\s?:,\[\]{}#&*!|>\'"%@`-]|[?:-]\S)', | |
| 243 something(Name.Variable), | |
| 244 'plain-scalar-in-block-context'), | |
| 245 ], | |
| 246 | |
| 247 # tags, anchors, aliases | |
| 248 'descriptors': [ | |
| 249 # a full-form tag | |
| 250 (r'!<[\w;/?:@&=+$,.!~*\'()\[\]%-]+>', Keyword.Type), | |
| 251 # a tag in the form '!', '!suffix' or '!handle!suffix' | |
| 252 (r'!(?:[\w-]+)?' | |
| 253 r'(?:![\w;/?:@&=+$,.!~*\'()\[\]%-]+)?', Keyword.Type), | |
| 254 # an anchor | |
| 255 (r'&[\w-]+', Name.Label), | |
| 256 # an alias | |
| 257 (r'\*[\w-]+', Name.Variable), | |
| 258 ], | |
| 259 | |
| 260 # block collections and scalars | |
| 261 'block-nodes': [ | |
| 262 # implicit key | |
| 263 (r':(?=[ ]|$)', set_indent(Punctuation.Indicator, implicit=True)), | |
| 264 # literal and folded scalars | |
| 265 (r'[|>]', Punctuation.Indicator, | |
| 266 ('block-scalar-content', 'block-scalar-header')), | |
| 267 ], | |
| 268 | |
| 269 # flow collections and quoted scalars | |
| 270 'flow-nodes': [ | |
| 271 # a flow sequence | |
| 272 (r'\[', Punctuation.Indicator, 'flow-sequence'), | |
| 273 # a flow mapping | |
| 274 (r'\{', Punctuation.Indicator, 'flow-mapping'), | |
| 275 # a single-quoted scalar | |
| 276 (r'\'', String, 'single-quoted-scalar'), | |
| 277 # a double-quoted scalar | |
| 278 (r'\"', String, 'double-quoted-scalar'), | |
| 279 ], | |
| 280 | |
| 281 # the content of a flow collection | |
| 282 'flow-collection': [ | |
| 283 # whitespaces | |
| 284 (r'[ ]+', Text), | |
| 285 # line breaks | |
| 286 (r'\n+', Text), | |
| 287 # a comment | |
| 288 (r'#[^\n]*', Comment.Single), | |
| 289 # simple indicators | |
| 290 (r'[?:,]', Punctuation.Indicator), | |
| 291 # tags, anchors and aliases | |
| 292 include('descriptors'), | |
| 293 # nested collections and quoted scalars | |
| 294 include('flow-nodes'), | |
| 295 # a plain scalar | |
| 296 (r'(?=[^\s?:,\[\]{}#&*!|>\'"%@`])', | |
| 297 something(Name.Variable), | |
| 298 'plain-scalar-in-flow-context'), | |
| 299 ], | |
| 300 | |
| 301 # a flow sequence indicated by '[' and ']' | |
| 302 'flow-sequence': [ | |
| 303 # include flow collection rules | |
| 304 include('flow-collection'), | |
| 305 # the closing indicator | |
| 306 (r'\]', Punctuation.Indicator, '#pop'), | |
| 307 ], | |
| 308 | |
| 309 # a flow mapping indicated by '{' and '}' | |
| 310 'flow-mapping': [ | |
| 311 # include flow collection rules | |
| 312 include('flow-collection'), | |
| 313 # the closing indicator | |
| 314 (r'\}', Punctuation.Indicator, '#pop'), | |
| 315 ], | |
| 316 | |
| 317 # block scalar lines | |
| 318 'block-scalar-content': [ | |
| 319 # line break | |
| 320 (r'\n', Text), | |
| 321 # empty line | |
| 322 (r'^[ ]+$', | |
| 323 parse_block_scalar_empty_line(Text, Name.Constant)), | |
| 324 # indentation spaces (we may leave the state here) | |
| 325 (r'^[ ]*', parse_block_scalar_indent(Text)), | |
| 326 # line content | |
| 327 (r'[\S\t ]+', Name.Constant), | |
| 328 ], | |
| 329 | |
| 330 # the content of a literal or folded scalar | |
| 331 'block-scalar-header': [ | |
| 332 # indentation indicator followed by chomping flag | |
| 333 (r'([1-9])?[+-]?(?=[ ]|$)', | |
| 334 set_block_scalar_indent(Punctuation.Indicator), | |
| 335 'ignored-line'), | |
| 336 # chomping flag followed by indentation indicator | |
| 337 (r'[+-]?([1-9])?(?=[ ]|$)', | |
| 338 set_block_scalar_indent(Punctuation.Indicator), | |
| 339 'ignored-line'), | |
| 340 ], | |
| 341 | |
| 342 # ignored and regular whitespaces in quoted scalars | |
| 343 'quoted-scalar-whitespaces': [ | |
| 344 # leading and trailing whitespaces are ignored | |
| 345 (r'^[ ]+', Text), | |
| 346 (r'[ ]+$', Text), | |
| 347 # line breaks are ignored | |
| 348 (r'\n+', Text), | |
| 349 # other whitespaces are a part of the value | |
| 350 (r'[ ]+', Name.Variable), | |
| 351 ], | |
| 352 | |
| 353 # single-quoted scalars | |
| 354 'single-quoted-scalar': [ | |
| 355 # include whitespace and line break rules | |
| 356 include('quoted-scalar-whitespaces'), | |
| 357 # escaping of the quote character | |
| 358 (r'\'\'', String.Escape), | |
| 359 # regular non-whitespace characters | |
| 360 (r'[^\s\']+', String), | |
| 361 # the closing quote | |
| 362 (r'\'', String, '#pop'), | |
| 363 ], | |
| 364 | |
| 365 # double-quoted scalars | |
| 366 'double-quoted-scalar': [ | |
| 367 # include whitespace and line break rules | |
| 368 include('quoted-scalar-whitespaces'), | |
| 369 # escaping of special characters | |
| 370 (r'\\[0abt\tn\nvfre "\\N_LP]', String), | |
| 371 # escape codes | |
| 372 (r'\\(?:x[0-9A-Fa-f]{2}|u[0-9A-Fa-f]{4}|U[0-9A-Fa-f]{8})', | |
| 373 String.Escape), | |
| 374 # regular non-whitespace characters | |
| 375 (r'[^\s"\\]+', String), | |
| 376 # the closing quote | |
| 377 (r'"', String, '#pop'), | |
| 378 ], | |
| 379 | |
| 380 # the beginning of a new line while scanning a plain scalar | |
| 381 'plain-scalar-in-block-context-new-line': [ | |
| 382 # empty lines | |
| 383 (r'^[ ]+$', Text), | |
| 384 # line breaks | |
| 385 (r'\n+', Text), | |
| 386 # document start and document end indicators | |
| 387 (r'^(?=---|\.\.\.)', something(Name.Namespace), '#pop:3'), | |
| 388 # indentation spaces (we may leave the block line state here) | |
| 389 (r'^[ ]*', parse_plain_scalar_indent(Text), '#pop'), | |
| 390 ], | |
| 391 | |
| 392 # a plain scalar in the block context | |
| 393 'plain-scalar-in-block-context': [ | |
| 394 # the scalar ends with the ':' indicator | |
| 395 (r'[ ]*(?=:[ ]|:$)', something(Text), '#pop'), | |
| 396 # the scalar ends with whitespaces followed by a comment | |
| 397 (r'[ ]+(?=#)', Text, '#pop'), | |
| 398 # trailing whitespaces are ignored | |
| 399 (r'[ ]+$', Text), | |
| 400 # line breaks are ignored | |
| 401 (r'\n+', Text, 'plain-scalar-in-block-context-new-line'), | |
| 402 # other whitespaces are a part of the value | |
| 403 (r'[ ]+', Literal.Scalar.Plain), | |
| 404 # regular non-whitespace characters | |
| 405 (r'(?::(?!\s)|[^\s:])+', Literal.Scalar.Plain), | |
| 406 ], | |
| 407 | |
| 408 # a plain scalar is the flow context | |
| 409 'plain-scalar-in-flow-context': [ | |
| 410 # the scalar ends with an indicator character | |
| 411 (r'[ ]*(?=[,:?\[\]{}])', something(Text), '#pop'), | |
| 412 # the scalar ends with a comment | |
| 413 (r'[ ]+(?=#)', Text, '#pop'), | |
| 414 # leading and trailing whitespaces are ignored | |
| 415 (r'^[ ]+', Text), | |
| 416 (r'[ ]+$', Text), | |
| 417 # line breaks are ignored | |
| 418 (r'\n+', Text), | |
| 419 # other whitespaces are a part of the value | |
| 420 (r'[ ]+', Name.Variable), | |
| 421 # regular non-whitespace characters | |
| 422 (r'[^\s,:?\[\]{}]+', Name.Variable), | |
| 423 ], | |
| 424 | |
| 425 } | |
| 426 | |
| 427 def get_tokens_unprocessed(self, text=None, context=None): | |
| 428 if context is None: | |
| 429 context = YamlLexerContext(text, 0) | |
| 430 return super(YamlLexer, self).get_tokens_unprocessed(text, context) | |
| 431 | |
| 432 | |
| 433 class JsonLexer(RegexLexer): | |
| 434 """ | |
| 435 For JSON data structures. | |
| 436 | |
| 437 .. versionadded:: 1.5 | |
| 438 """ | |
| 439 | |
| 440 name = 'JSON' | |
| 441 aliases = ['json'] | |
| 442 filenames = ['*.json'] | |
| 443 mimetypes = ['application/json'] | |
| 444 | |
| 445 flags = re.DOTALL | |
| 446 | |
| 447 # integer part of a number | |
| 448 int_part = r'-?(0|[1-9]\d*)' | |
| 449 | |
| 450 # fractional part of a number | |
| 451 frac_part = r'\.\d+' | |
| 452 | |
| 453 # exponential part of a number | |
| 454 exp_part = r'[eE](\+|-)?\d+' | |
| 455 | |
| 456 tokens = { | |
| 457 'whitespace': [ | |
| 458 (r'\s+', Text), | |
| 459 ], | |
| 460 | |
| 461 # represents a simple terminal value | |
| 462 'simplevalue': [ | |
| 463 (r'(true|false|null)\b', Keyword.Constant), | |
| 464 (('%(int_part)s(%(frac_part)s%(exp_part)s|' | |
| 465 '%(exp_part)s|%(frac_part)s)') % vars(), | |
| 466 Number.Float), | |
| 467 (int_part, Number.Integer), | |
| 468 (r'"(\\\\|\\"|[^"])*"', String.Double), | |
| 469 ], | |
| 470 | |
| 471 | |
| 472 # the right hand side of an object, after the attribute name | |
| 473 'objectattribute': [ | |
| 474 include('value'), | |
| 475 (r':', Punctuation), | |
| 476 # comma terminates the attribute but expects more | |
| 477 (r',', Punctuation, '#pop'), | |
| 478 # a closing bracket terminates the entire object, so pop twice | |
| 479 (r'\}', Punctuation, ('#pop', '#pop')), | |
| 480 ], | |
| 481 | |
| 482 # a json object - { attr, attr, ... } | |
| 483 'objectvalue': [ | |
| 484 include('whitespace'), | |
| 485 (r'"(\\\\|\\"|[^"])*"', Name.Tag, 'objectattribute'), | |
| 486 (r'\}', Punctuation, '#pop'), | |
| 487 ], | |
| 488 | |
| 489 # json array - [ value, value, ... } | |
| 490 'arrayvalue': [ | |
| 491 include('whitespace'), | |
| 492 include('value'), | |
| 493 (r',', Punctuation), | |
| 494 (r'\]', Punctuation, '#pop'), | |
| 495 ], | |
| 496 | |
| 497 # a json value - either a simple value or a complex value (object or array) | |
| 498 'value': [ | |
| 499 include('whitespace'), | |
| 500 include('simplevalue'), | |
| 501 (r'\{', Punctuation, 'objectvalue'), | |
| 502 (r'\[', Punctuation, 'arrayvalue'), | |
| 503 ], | |
| 504 | |
| 505 # the root of a json document whould be a value | |
| 506 'root': [ | |
| 507 include('value'), | |
| 508 ], | |
| 509 } | |
| 510 | |
| 511 class JsonLdLexer(JsonLexer): | |
| 512 """ | |
| 513 For `JSON-LD <http://json-ld.org/>`_ linked data. | |
| 514 | |
| 515 .. versionadded:: 2.0 | |
| 516 """ | |
| 517 | |
| 518 name = 'JSON-LD' | |
| 519 aliases = ['jsonld', 'json-ld'] | |
| 520 filenames = ['*.jsonld'] | |
| 521 mimetypes = ['application/ld+json'] | |
| 522 | |
| 523 tokens = { | |
| 524 'objectvalue': [ | |
| 525 (r'"@(context|id|value|language|type|container|list|set|' | |
| 526 r'reverse|index|base|vocab|graph)"', Name.Decorator, | |
| 527 'objectattribute'), | |
| 528 inherit, | |
| 529 ], | |
| 530 } |
