parser.rb in regexp-examples-1.1.3

- old
+ new

@@ -13,11 +13,11 @@
 
     def parse
       repeaters = []
       until end_of_regexp
         group = parse_group(repeaters)
-        return [OneTimeRepeater.new(group)] if group.is_a? OrGroup
+        return [group] if group.is_a? OrGroup
         @current_position += 1
         repeaters << parse_repeater(group)
       end
       repeaters
     end
@@ -118,11 +118,11 @@
       when rest_of_string =~ /\A(c|C-)(.)/ # Control character
         @current_position += Regexp.last_match(1).length
         group = parse_single_char_group(parse_control_character(Regexp.last_match(2)))
       when rest_of_string =~ /\Ax(\h{1,2})/ # Escape sequence
         @current_position += Regexp.last_match(1).length
-        group = parse_single_char_group(parse_escape_sequence(Regexp.last_match(1)))
+        group = parse_single_char_group(parse_unicode_sequence(Regexp.last_match(1)))
       when rest_of_string =~ /\Au(\h{4}|\{\h{1,4}\})/ # Unicode sequence
         @current_position += Regexp.last_match(1).length
         sequence = Regexp.last_match(1).match(/\h{1,4}/)[0] # Strip off "{" and "}"
         group = parse_single_char_group(parse_unicode_sequence(sequence))
       when rest_of_string =~ /\A(p)\{(\^?)([^}]+)\}/i # Named properties
@@ -146,21 +146,22 @@
           ["\r\n", "\n", "\v", "\f", "\r"],
           @ignorecase
         ) # Using "\r\n" as one character is little bit hacky...
       when next_char == 'g' # Subexpression call
         fail IllegalSyntaxError,
-          'Subexpression calls (\\g) cannot be supported, as they are not regular'
+             'Subexpression calls (\\g) cannot be supported, as they are not regular'
       when next_char =~ /[bB]/ # Anchors
         raise_anchors_exception!
       when next_char =~ /[AG]/ # Start of string
         if @current_position == 1
           group = PlaceHolderGroup.new
         else
           raise_anchors_exception!
         end
       when next_char =~ /[zZ]/ # End of string
         if @current_position == (regexp_string.length - 1)
+          # TODO: /\Z/ should be treated as /\n?/
           group = PlaceHolderGroup.new
         else
           raise_anchors_exception!
         end
       else
@@ -210,14 +211,14 @@
             else
               return PlaceHolderGroup.new
             end
           when %w(! =).include?(match[2]) # e.g. /(?=lookahead)/, /(?!neglookahead)/
             fail IllegalSyntaxError,
-              'Lookaheads are not regular; cannot generate examples'
+                 'Lookaheads are not regular; cannot generate examples'
           when %w(! =).include?(match[3]) # e.g. /(?<=lookbehind)/, /(?<!neglookbehind)/
             fail IllegalSyntaxError,
-              'Lookbehinds are not regular; cannot generate examples'
+                 'Lookbehinds are not regular; cannot generate examples'
           else # e.g. /(?<name>namedgroup)/
             @current_position += (match[3].length + 3)
             group_id = match[3]
           end
         end
@@ -235,18 +236,20 @@
       @extended = previous_extended
       group
     end
 
     def regexp_options_toggle(on, off)
-      @ignorecase = true if on.include? 'i'
-      @ignorecase = false if off.include? 'i'
-      @multiline = true if on.include? 'm'
-      @multiline = false if off.include? 'm'
-      @extended = true if on.include? 'x'
-      @extended = false if off.include? 'x'
+      regexp_option_toggle(on, off, '@ignorecase', 'i')
+      regexp_option_toggle(on, off, '@multiline', 'm')
+      regexp_option_toggle(on, off, '@extended', 'x')
     end
 
+    def regexp_option_toggle(on, off, var, char)
+      instance_variable_set(var, true) if on.include? char
+      instance_variable_set(var, false) if off.include? char
+    end
+
     def parse_char_group
       @current_position += 1 # Skip past opening "["
       chargroup_parser = ChargroupParser.new(rest_of_string)
       parsed_chars = chargroup_parser.result
       @current_position += (chargroup_parser.length - 1) # Step back to closing "]"
@@ -274,16 +277,12 @@
     def parse_control_character(char)
       (char.ord % 32).chr # Black magic!
       # eval "?\\C-#{char.chr}" # Doesn't work for e.g. char = "?"
     end
 
-    def parse_escape_sequence(match)
-      eval "?\\x#{match}"
-    end
-
     def parse_unicode_sequence(match)
-      eval "?\\u{#{match}}"
+      [match.to_i(16)].pack('U')
     end
 
     def parse_star_repeater(group)
       @current_position += 1
       parse_reluctant_or_possessive_repeater
@@ -329,10 +328,10 @@
       repeater
     end
 
     def raise_anchors_exception!
       fail IllegalSyntaxError,
-        "Anchors ('#{next_char}') cannot be supported, as they are not regular"
+           "Anchors ('#{next_char}') cannot be supported, as they are not regular"
     end
 
     def parse_one_time_repeater(group)
       OneTimeRepeater.new(group)
     end