/usr/lib/ruby/vendor_ruby/rugments/lexer.rb is in ruby-rugments 1.0.0~beta8-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | require 'strscan'
require 'cgi'
require 'set'
module Rugments
# @abstract
# A lexer transforms text into a stream of `[token, chunk]` pairs.
class Lexer
include Token::Tokens
class << self
# Lexes `stream` with the given options. The lex is delegated to a
# new instance.
#
# @see #lex
def lex(stream, opts = {}, &b)
new(opts).lex(stream, &b)
end
def default_options(o = {})
@default_options ||= {}
@default_options.merge!(o)
@default_options
end
# Given a string, return the correct lexer class.
def find(name)
registry[name.to_s]
end
# Find a lexer, with fancy shiny features.
#
# * The string you pass can include CGI-style options
#
# Lexer.find_fancy('erb?parent=tex')
#
# * You can pass the special name 'guess' so we guess for you,
# and you can pass a second argument of the code to guess by
#
# Lexer.find_fancy('guess', "#!/bin/bash\necho Hello, world")
#
# This is used in the Redcarpet plugin as well as Rouge's own
# markdown lexer for highlighting internal code blocks.
#
def find_fancy(str, code = nil)
name, opts = str ? str.split('?', 2) : [nil, '']
# parse the options hash from a cgi-style string
opts = CGI.parse(opts || '').map do |k, vals|
[k.to_sym, vals.empty? ? true : vals[0]]
end
opts = Hash[opts]
lexer_class = case name
when 'guess', nil
guess(source: code, mimetype: opts[:mimetype])
when String
find(name)
end
lexer_class && lexer_class.new(opts)
end
# Specify or get this lexer's title. Meant to be human-readable.
def title(t=nil)
if t.nil?
t = tag.capitalize
end
@title ||= t
end
# Specify or get this lexer's description.
def desc(arg = :absent)
if arg == :absent
@desc
else
@desc = arg
end
end
# Specify or get the path name containing a small demo for
# this lexer (can be overriden by {demo}).
def demo_file(arg = :absent)
return @demo_file = Pathname.new(arg) unless arg == :absent
@demo_file = Pathname.new(__FILE__).dirname.join('demos', tag)
end
# Specify or get a small demo string for this lexer
def demo(arg = :absent)
return @demo = arg unless arg == :absent
@demo = File.read(demo_file, encoding: 'utf-8')
end
# @return a list of all lexers.
def all
registry.values.uniq
end
# Guess which lexer to use based on a hash of info.
#
# This accepts the same arguments as Lexer.guess, but will never throw
# an error. It will return a (possibly empty) list of potential lexers
# to use.
def guesses(info = {})
mimetype, filename, source = info.values_at(:mimetype, :filename, :source)
lexers = registry.values.uniq
total_size = lexers.size
lexers = filter_by_mimetype(lexers, mimetype) if mimetype
return lexers if lexers.size == 1
lexers = filter_by_filename(lexers, filename) if filename
return lexers if lexers.size == 1
if source
# If we're filtering against *all* lexers, we only use confident return
# values from analyze_text. But if we've filtered down already, we can trust
# the analysis more.
source_threshold = lexers.size < total_size ? 0 : 0.5
return [best_by_source(lexers, source, source_threshold)].compact
end
[]
end
class AmbiguousGuess < StandardError
attr_reader :alternatives
def initialize(alternatives)
@alternatives = alternatives
end
def message
"Ambiguous guess: can't decide between #{alternatives.map(&:tag).inspect}"
end
end
# Guess which lexer to use based on a hash of info.
#
# @option info :mimetype
# A mimetype to guess by
# @option info :filename
# A filename to guess by
# @option info :source
# The source itself, which, if guessing by mimetype or filename
# fails, will be searched for shebangs, <!DOCTYPE ...> tags, and
# other hints.
#
# @see Lexer.analyze_text
# @see Lexer.multi_guess
def guess(info = {})
lexers = guesses(info)
return Lexers::PlainText if lexers.empty?
return lexers[0] if lexers.size == 1
fail AmbiguousGuess.new(lexers)
end
def guess_by_mimetype(mt)
guess mimetype: mt
end
def guess_by_filename(fname)
guess filename: fname
end
def guess_by_source(source)
guess source: source
end
private
def filter_by_mimetype(lexers, mt)
filtered = lexers.select { |lexer| lexer.mimetypes.include? mt }
filtered.any? ? filtered : lexers
end
# returns a list of lexers that match the given filename with
# equal specificity (i.e. number of wildcards in the pattern).
# This helps disambiguate between, e.g. the Nginx lexer, which
# matches `nginx.conf`, and the Conf lexer, which matches `*.conf`.
# In this case, nginx will win because the pattern has no wildcards,
# while `*.conf` has one.
def filter_by_filename(lexers, fname)
fname = File.basename(fname)
out = []
best_seen = nil
lexers.each do |lexer|
score = lexer.filenames.map do |pattern|
if File.fnmatch?(pattern, fname, File::FNM_DOTMATCH)
# specificity is better the fewer wildcards there are
pattern.scan(/[*?\[]/).size
end
end.compact.min
next unless score
if best_seen.nil? || score < best_seen
best_seen = score
out = [lexer]
elsif score == best_seen
out << lexer
end
end
out.any? ? out : lexers
end
def best_by_source(lexers, source, threshold = 0)
source = case source
when String
source
when ->(s) { s.respond_to? :read }
source.read
else
fail 'invalid source'
end
assert_utf8!(source)
source = TextAnalyzer.new(source)
best_result = threshold
best_match = nil
lexers.each do |lexer|
result = lexer.analyze_text(source) || 0
return lexer if result == 1
if result > best_result
best_match = lexer
best_result = result
end
end
best_match
end
protected
# @private
def register(name, lexer)
registry[name.to_s] = lexer
end
public
# Used to specify or get the canonical name of this lexer class.
#
# @example
# class MyLexer < Lexer
# tag 'foo'
# end
#
# MyLexer.tag # => 'foo'
#
# Lexer.find('foo') # => MyLexer
def tag(t = nil)
return @tag if t.nil?
@tag = t.to_s
Lexer.register(@tag, self)
end
# Used to specify alternate names this lexer class may be found by.
#
# @example
# class Erb < Lexer
# tag 'erb'
# aliases 'eruby', 'rhtml'
# end
#
# Lexer.find('eruby') # => Erb
def aliases(*args)
args.map!(&:to_s)
args.each { |arg| Lexer.register(arg, self) }
(@aliases ||= []).concat(args)
end
# Specify a list of filename globs associated with this lexer.
#
# @example
# class Ruby < Lexer
# filenames '*.rb', '*.ruby', 'Gemfile', 'Rakefile'
# end
def filenames(*fnames)
(@filenames ||= []).concat(fnames)
end
# Specify a list of mimetypes associated with this lexer.
#
# @example
# class Html < Lexer
# mimetypes 'text/html', 'application/xhtml+xml'
# end
def mimetypes(*mts)
(@mimetypes ||= []).concat(mts)
end
# @private
def assert_utf8!(str)
return if %w(US-ASCII UTF-8 ASCII-8BIT).include? str.encoding.name
fail EncodingError.new(
"Bad encoding: #{str.encoding.names.join(',')}. " \
'Please convert your string to UTF-8.'
)
end
private
def registry
@registry ||= {}
end
end
# -*- instance methods -*- #
# Create a new lexer with the given options. Individual lexers may
# specify extra options. The only current globally accepted option
# is `:debug`.
#
# @option opts :debug
# Prints debug information to stdout. The particular info depends
# on the lexer in question. In regex lexers, this will log the
# state stack at the beginning of each step, along with each regex
# tried and each stream consumed. Try it, it's pretty useful.
def initialize(opts = {})
options(opts)
@debug = option(:debug)
end
# get and/or specify the options for this lexer.
def options(o = {})
(@options ||= {}).merge!(o)
self.class.default_options.merge(@options)
end
# get or specify one option for this lexer
def option(k, v = :absent)
if v == :absent
options[k]
else
options(k => v)
end
end
# @abstract
#
# Called after each lex is finished. The default implementation
# is a noop.
def reset!
end
# Given a string, yield [token, chunk] pairs. If no block is given,
# an enumerator is returned.
#
# @option opts :continue
# Continue the lex from the previous state (i.e. don't call #reset!)
def lex(string, opts = {}, &b)
return enum_for(:lex, string, opts) unless block_given?
Lexer.assert_utf8!(string)
reset! unless opts[:continue]
# consolidate consecutive tokens of the same type
last_token = nil
last_val = nil
stream_tokens(string) do |tok, val|
next if val.empty?
if tok == last_token
last_val << val
next
end
b.call(last_token, last_val) if last_token
last_token = tok
last_val = val
end
b.call(last_token, last_val) if last_token
end
# delegated to {Lexer.tag}
def tag
self.class.tag
end
# @abstract
#
# Yield `[token, chunk]` pairs, given a prepared input stream. This
# must be implemented.
#
# @param [StringScanner] stream
# the stream
def stream_tokens(_stream, &_b)
fail 'abstract'
end
# @abstract
#
# Return a number between 0 and 1 indicating the likelihood that
# the text given should be lexed with this lexer. The default
# implementation returns 0. Values under 0.5 will only be used
# to disambiguate filename or mimetype matches.
#
# @param [TextAnalyzer] text
# the text to be analyzed, with a couple of handy methods on it,
# like {TextAnalyzer#shebang?} and {TextAnalyzer#doctype?}
def self.analyze_text(_text)
0
end
end
module Lexers
def self.load_const(const_name, relpath)
return if const_defined?(const_name)
root = Pathname.new(__FILE__).dirname.join('lexers')
load root.join(relpath)
end
end
end
|