regexp-examples 0.0.2 → 0.1.0

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    M2JjOGMxOWExYWQxMzdhMjdkN2Y4YjQzMDlhMmU3Mzc2MjA3NmRhZQ==
+    ZmEzZDkwZTIyMTM0MzM1MTQ3YThmY2NhNGJmNGQzZDZmYTdlOTgzZQ==
   data.tar.gz: !binary |-
-    NDkxOTNhYmMyZjU1YTgwMzQ5Njk5MWJmOGZjZGM1YWVhMzIxOGE3Mw==
+    ZTdlYjhjOTg2MTc1MWU5M2NjYTk1ODU2OGNiNWMxYTIxYzlhMjdlMg==
 SHA512:
   metadata.gz: !binary |-
-    MGVhODk0ZTI5YjU1MmIwMmVkNjdjNTZhZDIxNDU4N2MzYTA2MWM2MDJlYTBj
-    NDU1MGIxZmNhNGI0MTNkZjMyZjc1MDdlZGY1YThlYTg3NzUwZGNhNjcyZjg3
-    MjY3YWQ2Yjk2ODY0YjZmZTEyZjc2NWE0ZTY5ZWIwZmYxYWM4ZjQ=
+    NTUyY2Q2MzUwNjczMmYwOWQ1YTJkZTk5N2I2YWIzM2Q4NzUxODM0NDg4ZWQ3
+    ZDJiYTVkM2RhYzE1NTAzODdjMzY4ZDI4NTM3NjM0ZjJiZWQ1N2U4ZmVmMzIz
+    M2YyMDQ1MTAyZDg5NjAwOTY5Y2FlMDIyNzkwZjdhMDJiOTZhNDU=
   data.tar.gz: !binary |-
-    NjkwYWYwM2Q1MDM3ZjEzNjc0MDU0YTU1NWRmYWQyMTljYjJhZDEzZTU0N2Jj
-    ODU5YmNhNTJhY2NjMWRmODJkZGE2NmM1ZjQzY2UyODU2Y2JmZDc1MGE0NTVk
-    NTMzYWM4NGJiNTMxMWVmZTA0MGZkZjc1NjM3ZWMxNzM5MGRiZTE=
+    ZmQ1NWY5NjRiYzViNjdlNjNhODQ1ODkyZTZmMzk5MTIzZDgxZDFjNDIxODEz
+    ODY5ZDcxYzEwODAxYjhmNDE5MGM1ZDk5YzkxYjk5ZTUxYzRkYjY5ZTM2MWNk
+    NTNkZmRjYmMzN2ZkNjg4MDQ1MzdlNWNhZjYzOTJlODVkZjQwMTE=

data/README.md

@@ -29,15 +29,14 @@ or a huge number of possible matches, such as `/.\w/`, then only a subset of the
 * Boolean "Or" groups, e.g. `/a|b|c/`
 * Character sets (inluding ranges and negation!), e.g. `/[abc]/`, `/[A-Z0-9]/`, `/[^a-z]/`
 * Escaped characters, e.g. `/\n/`, `/\w/`, `/\D/` (and so on...)
-* Capture groups, and backreferences(!!), e.g. `/(this|that) \1/`
-* Arbitrarily complex combinations of all the above!
+* Capture groups, including named groups and backreferences(!!), e.g. `/(this|that) \1/` `/(?<name>foo) \k<name>/`
+* Non-capture groups, e.g. `/(?:foo)/`
+* '''Arbitrarily complex combinations of all the above!'''
 
 ## Not-Yet-Supported syntax
 
 I plan to add the following features to the gem (in order of most -> least likely), but have not yet got round to it:
 
-* Non-capture groups, e.g. `/(?:foo)/`
-* Named capture groups, e.g. `(?<name>bar)/`
 * Throw exceptions if illegal syntax (see below) is used
 * POSIX bracket expressions, e.g. `/[[:alnum:]]/`, `/[[:space:]]/`
 * Options, e.g. `/pattern/i`, `/foo.*bar/m`

data/lib/regexp-examples/backreferences.rb

@@ -23,8 +23,8 @@ module RegexpExamples
           [full_example]
         else
           full_example.map! do |partial_example|
-            partial_example.gsub(/__(\d+)__/) do |match|
-              find_backref_for(full_example, $1.to_i)
+            partial_example.gsub(/__(\w+)__/) do |match|
+              find_backref_for(full_example, $1)
             end
           end
         end

data/lib/regexp-examples/groups.rb

@@ -109,13 +109,13 @@ module RegexpExamples
   end
 
   class BackReferenceGroup
-    attr_reader :num
-    def initialize(num)
-      @num = num
+    attr_reader :id
+    def initialize(id)
+      @id = id
     end
 
     def result
-      ["__#{@num}__"]
+      ["__#{@id}__"]
     end
   end
 

data/lib/regexp-examples/parser.rb

@@ -45,8 +45,12 @@ module RegexpExamples
     def parse_after_backslash_group
       @current_position += 1
       case
-      when regexp_string[@current_position..-1] =~ /^(\d+)/
-        group = parse_backreference_group($&)
+      when rest_of_string =~ /\A(\d+)/
+        @current_position += ($1.length - 1) # In case of 10+ backrefs!
+        group = parse_backreference_group($1)
+      when rest_of_string =~ /\Ak<([^>]+)>/ # Named capture group
+        @current_position += ($1.length + 2)
+        group = parse_backreference_group($1)
       when BackslashCharMap.keys.include?(regexp_string[@current_position])
         group = CharGroup.new(
           BackslashCharMap[regexp_string[@current_position]])
@@ -79,11 +83,25 @@ module RegexpExamples
     def parse_multi_group
       @current_position += 1
       @num_groups += 1
-      this_group_num = @num_groups
+      group_id = nil # init
+      rest_of_string.match(/\A(\?)?(:|!|=|<(!|=|[^!=][^>]*))?/) do |match|
+        case
+        when match[1].nil? # e.g. /(normal)/
+          group_id = @num_groups.to_s
+        when match[2] == ':' # e.g. /(?:nocapture)/
+          @current_position += 2
+          group_id = nil
+        when %w(! =).include?(match[2]) # e.g. /(?=lookahead)/, /(?!neglookahead)/
+          # TODO: Raise exception
+        when %w(! =).include?(match[3]) # e.g. /(?<=lookbehind)/, /(?<!neglookbehind)/
+          # TODO: Raise exception
+        else # e.g. /(?<name>namedgroup)/
+          @current_position += (match[3].length + 3)
+          group_id = match[3]
+        end
+      end
       groups = parse
-      # TODO: Non-capture groups, i.e. /...(?:foo).../
-      # TODO: Named capture groups, i.e. /...(?<name>foo).../
-      MultiGroup.new(groups, this_group_num)
+      MultiGroup.new(groups, group_id)
     end
 
     def parse_multi_end_group
@@ -127,7 +145,7 @@ module RegexpExamples
     end
 
     def parse_backreference_group(match)
-      BackReferenceGroup.new(match.to_i)
+      BackReferenceGroup.new(match)
     end
 
     def parse_star_repeater(group)
@@ -146,7 +164,7 @@ module RegexpExamples
     end
 
     def parse_range_repeater(group)
-      match = regexp_string[@current_position..-1].match(/^\{(\d+)(,)?(\d+)?\}/)
+      match = rest_of_string.match(/\A\{(\d+)(,)?(\d+)?\}/)
       @current_position += match[0].size
       min = match[1].to_i if match[1]
       has_comma = !match[2].nil?
@@ -157,6 +175,10 @@ module RegexpExamples
     def parse_one_time_repeater(group)
       OneTimeRepeater.new(group)
     end
+
+    def rest_of_string
+      regexp_string[@current_position..-1]
+    end
   end
 end
 

data/lib/regexp-examples/regexp_extensions.rb

@@ -1,16 +1,16 @@
 class Regexp
-module Examples
-  def examples
-    partial_examples =
-      RegexpExamples::Parser.new(source)
-        .parse
-        .map {|repeater| repeater.result}
-    full_examples = RegexpExamples::permutations_of_strings(partial_examples.dup, no_join: true)
-    full_examples_with_backrefs = \
-      RegexpExamples::BackReferenceReplacer.new.substitute_backreferences(full_examples)
-    full_examples_with_backrefs.map(&:join)
+  module Examples
+    def examples
+      partial_examples =
+        RegexpExamples::Parser.new(source)
+      .parse
+      .map {|repeater| repeater.result}
+      full_examples = RegexpExamples::permutations_of_strings(partial_examples.dup, no_join: true)
+      full_examples_with_backrefs = \
+        RegexpExamples::BackReferenceReplacer.new.substitute_backreferences(full_examples)
+      full_examples_with_backrefs.map(&:join)
+    end
   end
-end
   include Examples
 end
 

data/lib/regexp-examples/version.rb

@@ -1,3 +1,3 @@
 module RegexpExamples
-  VERSION = '0.0.2'
+  VERSION = '0.1.0'
 end

data/spec/regexp-examples_spec.rb

@@ -52,6 +52,21 @@ describe Regexp, "#examples" do
       )
     end
 
+    context "for complex multi groups" do
+      examples_exist_and_match(
+        /(normal)/,
+        /(?:nocapture)/,
+        /(?<name>namedgroup)/,
+        /(?<name>namedgroup) \k<name>/
+      )
+      # TODO: These are not yet implemented
+      # (expect to raise exception)
+#        /(?=lookahead)/,
+#        /(?!neglookahead)/,
+#        /(?<=lookbehind)/,
+#        /(?<!neglookbehind)/,
+    end
+
     context "for escaped characters" do
       examples_exist_and_match(
         /\w/,

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: regexp-examples
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.1.0
 platform: ruby
 authors:
 - Tom Lord