Class: CssTidy::Parser
- Inherits:
-
Object
- Object
- CssTidy::Parser
- Defined in:
- lib/modules/css_parser.rb
Instance Attribute Summary collapse
-
#css ⇒ Object
these are used to poke values in for testing instance methods.
-
#index ⇒ Object
these are used to poke values in for testing instance methods.
-
#sheet ⇒ Object
these are used to poke values in for testing instance methods.
Instance Method Summary collapse
- #current_char ⇒ Object
-
#initialize ⇒ Parser
constructor
setup the class vars used by Tidy.
- #is_at_rule?(text) ⇒ Boolean
- #is_char_ctype?(ctype, char) ⇒ Boolean
- #is_char_escaped?(char) ⇒ Boolean
- #is_char_token?(char) ⇒ Boolean
- #is_comment? ⇒ Boolean
- #is_comment_end? ⇒ Boolean
- #is_css_whitespace?(char) ⇒ Boolean
- #is_ctype?(ctype, offset = 0) ⇒ Boolean
-
#is_current_char?(char, offset = 0) ⇒ Boolean
any sort of character - use for readability.
-
#is_escaped?(offset = 0) ⇒ Boolean
Checks if a character is escaped (and returns true if it is).
- #is_newline? ⇒ Boolean
- #is_property_valid?(property) ⇒ Boolean
-
#is_token?(offset = 0) ⇒ Boolean
These functions all test the character at the current index location.
- #parse(css) ⇒ Object
-
#property_is_next? ⇒ Boolean
Checks if the next word in a string from after current index is a CSS property.
Constructor Details
#initialize ⇒ Parser
setup the class vars used by Tidy
19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 |
# File 'lib/modules/css_parser.rb', line 19 def initialize # temporary array to hold data during development @stylesheet = CssTidy::StyleSheet.new # the raw, unprocessed css @raw_css = '' # the string that is being processed @css = '' # the current position in the string @index = 0 # the current parser context. i.e where we are in the CSS @context = [NONE, IN_SELECTOR] # the current line number @line_number = 1 end |
Instance Attribute Details
#css ⇒ Object
these are used to poke values in for testing instance methods
16 17 18 |
# File 'lib/modules/css_parser.rb', line 16 def css @css end |
#index ⇒ Object
these are used to poke values in for testing instance methods
16 17 18 |
# File 'lib/modules/css_parser.rb', line 16 def index @index end |
#sheet ⇒ Object
these are used to poke values in for testing instance methods
16 17 18 |
# File 'lib/modules/css_parser.rb', line 16 def sheet @sheet end |
Instance Method Details
#current_char ⇒ Object
323 324 325 |
# File 'lib/modules/css_parser.rb', line 323 def current_char @css[@index,1] end |
#is_at_rule?(text) ⇒ Boolean
435 436 437 |
# File 'lib/modules/css_parser.rb', line 435 def is_at_rule?(text) #if($this->selector{0} == '@' && isset($at_rules[substr($this->selector,1)]) && $at_rules[substr($this->selector,1)] == 'iv') end |
#is_char_ctype?(ctype, char) ⇒ Boolean
414 415 416 417 418 419 420 421 422 423 |
# File 'lib/modules/css_parser.rb', line 414 def is_char_ctype?(ctype, char) case ctype when :space char =~ / |\t|\f|\v|\n|\r/ when :xdigit # hexidecimal char =~ /[0-9a-f]/i when :alpha char =~ /[A-Za-z]/ end end |
#is_char_escaped?(char) ⇒ Boolean
373 374 375 376 377 378 379 380 381 |
# File 'lib/modules/css_parser.rb', line 373 def is_char_escaped?(char) # cannot backtrack before index '1' (would be -1, or the end of the string) if @index > 0 if char === '\\' return true end end false end |
#is_char_token?(char) ⇒ Boolean
364 365 366 |
# File 'lib/modules/css_parser.rb', line 364 def is_char_token?(char) TOKENS.include?(char) end |
#is_comment? ⇒ Boolean
384 385 386 387 388 389 390 391 392 |
# File 'lib/modules/css_parser.rb', line 384 def is_comment? # cannot look beyond the end of the string if @index < @css.length if @css[@index, 2] == '/*' return true end end false end |
#is_comment_end? ⇒ Boolean
394 395 396 397 398 399 400 401 402 |
# File 'lib/modules/css_parser.rb', line 394 def is_comment_end? # cannot look beyond the end of the string if @index < @css.length if @css[@index, 2] == '*/' return true end end false end |
#is_css_whitespace?(char) ⇒ Boolean
353 354 355 |
# File 'lib/modules/css_parser.rb', line 353 def is_css_whitespace?(char) WHITESPACE.include?(char) end |
#is_ctype?(ctype, offset = 0) ⇒ Boolean
408 409 410 411 412 |
# File 'lib/modules/css_parser.rb', line 408 def is_ctype?(ctype, offset=0) if @index < @css.length is_char_ctype?(ctype, @css[@index+offset,1]) end end |
#is_current_char?(char, offset = 0) ⇒ Boolean
any sort of character - use for readability
426 427 428 429 430 431 432 433 |
# File 'lib/modules/css_parser.rb', line 426 def is_current_char?(char,offset=0) case char.class.to_s when 'String' @css[@index+offset,1] == char when 'Array' char.include?(@css[@index+offset,1]) end end |
#is_escaped?(offset = 0) ⇒ Boolean
Checks if a character is escaped (and returns true if it is)
369 370 371 |
# File 'lib/modules/css_parser.rb', line 369 def is_escaped?(offset=0) is_char_escaped?(@css[@index+offset-1,1]) end |
#is_newline? ⇒ Boolean
404 405 406 |
# File 'lib/modules/css_parser.rb', line 404 def is_newline? @css[@index,1] =~ /\n|\r/ end |
#is_property_valid?(property) ⇒ Boolean
349 350 351 |
# File 'lib/modules/css_parser.rb', line 349 def is_property_valid?(property) PROPERTIES.has_key?(property) end |
#is_token?(offset = 0) ⇒ Boolean
These functions all test the character at the current index location
360 361 362 |
# File 'lib/modules/css_parser.rb', line 360 def is_token?(offset=0) is_char_token?(@css[@index+offset,1]) end |
#parse(css) ⇒ Object
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 |
# File 'lib/modules/css_parser.rb', line 40 def parse(css) css_length = css.length @css = css.clone # vars used in processing of sheets current_at_block = '' invalid_at = false invalid_at_name = '' current_selector = '' current_property = '' current_ruleset = CssTidy::RuleSet.new current_value = '' sub_value = '' sub_value_array = [] current_string = '' string_char = '' str_in_str = false current_comment = '' while @index < css_length if is_newline? @line_number += 1 end case @context.last when IN_AT_BLOCK if is_token? # current_at_block empty? allows comment inside of selectors to pass if is_comment? && current_at_block.strip.empty? @context << IN_COMMENT @index += 1 # move past '*' elsif is_current_char? '{' @context << IN_SELECTOR elsif is_current_char? ',' current_at_block = current_at_block.strip + ',' elsif is_current_char? ['(',')',':','/','*','!','\\'] # catch media queries and escapes current_at_block << current_char end # of is_comment else # not token if(! ( (is_char_ctype?(:space, current_at_block[-1,1]) || is_char_token?(current_at_block[-1,1]) && current_at_block[-1,1] == ',') && is_ctype?(:space) )) current_at_block << current_char end end when IN_SELECTOR if is_token? # current_selector empty? allows comment inside of selectors to pass if is_comment? && current_selector.strip.empty? @context << IN_COMMENT @index += 1 elsif is_current_char?('@') && current_selector.strip.empty? # Check for at-rule invalid_at = true AT_RULES.each do |name, type| size_of_property = name.length # look ahead for the name property_to_find = (@css[@index+1,size_of_property]).strip.downcase if name == property_to_find if type == IN_AT_BLOCK current_at_block = '@' + name else current_selector = '@' + name end @context << type @index += size_of_property invalid_at = false end end if invalid_at current_selector = '@' invalid_at_name = '' puts "invalid At rule" # for($j = $i+1; $j < $size; ++$j) # { # if(!ctype_alpha($string{$j})) # { # break; # } # $invalid_at_name .= $string{$j}; # } # $this->log('Invalid @-rule: '.$invalid_at_name.' (removed)','Warning'); end elsif is_current_char?('"') || is_current_char?("'") @context << IN_STRING current_string = current_char string_char = current_char elsif invalid_at && is_current_char?(';') invalid_at = false @context << IN_SELECTOR elsif is_current_char?('{') @context << IN_PROPERTY elsif is_current_char?('}') current_at_block = '' @stylesheet.end_at_block current_selector = '' # when there is a new selector we save the last set @stylesheet << current_ruleset unless current_ruleset.empty? # and start a new one current_ruleset = CssTidy::RuleSet.new elsif is_current_char?([',','\\']) current_selector = current_selector.strip + current_char #remove unnecessary universal selector, FS#147 #elseif ! (is_current_char?('*') && @in_array($string{$i+1}, array('.', '#', '[', ':')))) else current_selector << current_char end else # not is_token last_position = current_selector.length - 1 if( last_position == -1 || ! ( (is_char_ctype?(:space, current_selector[last_position,1]) || is_char_token?(current_selector[last_position,1]) && current_selector[last_position,1] == ',') && is_ctype?(:space) )) current_selector << current_char end end when IN_PROPERTY if is_token? if (is_current_char?(':') || is_current_char?('=')) && ! current_property.empty? @context << IN_VALUE elsif is_comment? && current_property.empty? @context << IN_COMMENT @index += 1 # move past '*' elsif is_current_char?('}') @context << IN_SELECTOR invalid_at = false current_property = '' current_selector = '' # when there is a new selector we save the last set @stylesheet << current_ruleset unless current_ruleset.empty? # and start a new one current_ruleset = CssTidy::RuleSet.new elsif is_current_char?(';') current_property = '' elsif is_current_char?(['*','\\']) # allow star hack and \ hack for properties current_property << current_char end elsif ! is_ctype?(:space) current_property << current_char end when IN_VALUE property_next = is_newline? && property_is_next? || @index == css_length-1 if is_token? || property_next if is_comment? @context << IN_COMMENT @index += 1 elsif is_current_char?('"') || is_current_char?("'") || is_current_char?('(') current_string = current_char string_char = is_current_char?('(') ? ')' : current_char @context << IN_STRING elsif is_current_char?([',','\\']) sub_value = sub_value.strip + current_char elsif is_current_char?(';') || property_next if current_selector[0,1] == '@' && AT_RULES.has_key?(current_selector[1..-1]) && AT_RULES[current_selector[1..-1]] == IN_VALUE sub_value_array << sub_value.strip @context << IN_SELECTOR case current_selector when '@charset' unless (@stylesheet.charset = sub_value_array[0]) puts "extra charset" end when '@namespace' #$this->namespace = implode(' ',$this->sub_value_arr); when '@import' @stylesheet << CssTidy::Import.new(sub_value_array.join(' ')) end sub_value_array = [] sub_value = '' current_selector = '' else @context << IN_PROPERTY end elsif ! is_current_char?('}') sub_value << current_char end if (is_current_char?('}') || is_current_char?(';') || property_next) && ! current_selector.empty? unless current_at_block.empty? @stylesheet << CssTidy::MediaSet.new(current_at_block.strip) current_at_block = '' end if ! sub_value.strip.empty? sub_value_array << sub_value.strip sub_value = '' end current_value = sub_value_array.join(' ') valid = is_property_valid?(current_property) if (! invalid_at || valid) current_ruleset.add_rule({:selector => current_selector.strip, :declarations => "#{current_property}:#{current_value}" }) end current_property = '' sub_value_array = [] current_value = '' end if is_current_char?('}') @context << IN_SELECTOR invalid_at = false current_selector = '' # when there is a new selector we save the last set @stylesheet << current_ruleset unless current_ruleset.empty? # and start a new one current_ruleset = CssTidy::RuleSet.new end elsif ! property_next sub_value << current_char if is_ctype?(:space) if ! sub_value.strip.empty? sub_value_array << sub_value.strip sub_value = '' end end end when IN_STRING if string_char === ')' && (is_current_char?('"') || is_current_char?("'")) && ! str_in_str && ! is_escaped? str_in_str = true elsif string_char === ')' && (is_current_char?('"') || is_current_char?("'")) && str_in_str && ! is_escaped? str_in_str = false end temp_add = current_char # // ...and no not-escaped backslash at the previous position if is_newline? && !is_current_char?('\\',-1) && ! is_escaped?(-1) temp_add = "\\A " #$this->log('Fixed incorrect newline in string','Warning'); end if !(string_char === ')' && is_css_whitespace?(current_char) && !str_in_str) current_string << temp_add end if is_current_char?(string_char) && !is_escaped? && !str_in_str @context.pop if is_css_whitespace?(current_string) && current_property != 'content' if (!quoted_string) if (string_char === '"' || string_char === '\'') # Temporarily disable this optimization to avoid problems with @charset rule, quote properties, and some attribute selectors... # Attribute selectors fixed, added quotes to @chartset, no problems with properties detected. Enabled #current_string = current_string.slice($this->cur_string, 1, -1); elsif (current_string > 3) && (current_string[1,1] === '"' || current_string[1,1] === '\'') #current_string = current_string + substr($this->cur_string, 2, -2) . substr($this->cur_string, -1); end else quoted_string = false end end if @context[-1] === IN_VALUE # from in value? sub_value << current_string elsif @context[-1] === IN_SELECTOR current_selector << current_string; end end when IN_COMMENT if is_comment_end? @context.pop # go back to previous context @index += 1 # skip the '/' @stylesheet << CssTidy::Comment.new(current_comment) current_comment = '' else current_comment << current_char end end @index += 1 end @stylesheet end |
#property_is_next? ⇒ Boolean
Checks if the next word in a string from after current index is a CSS property
328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 |
# File 'lib/modules/css_parser.rb', line 328 def property_is_next? pos = @css.index(':', @index+1) if ! pos return false end # get the length until just before the ':' size_of_property = pos - @index - 1 # extract the name of the property property_to_find = (@css[@index+1,size_of_property]).strip.downcase if PROPERTIES.has_key?(property_to_find) #$this->log('Added semicolon to the end of declaration','Warning'); return true else return false end end |