regexp-examples 0.5.1 → 0.5.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: ff205ed61ad0ca0c2dc2383afd17930110763b44
-  data.tar.gz: a13f23a7d56b9b7d7e4323380d705276793e6e4f
+  metadata.gz: 0d34e8d62dc70d3b7b1ba17930f94a3799e9f669
+  data.tar.gz: 62b828f1e6207cf7198ad96a2b61ab5f08dea5d2
 SHA512:
-  metadata.gz: 068c7dbd13945c0487b91c61e9cae304323775adc82cd4e80092ab32505eb46f31aaf98736f5a353eb1ad06a471864f9432ce3d203097f2dcfc6e696dba07e12
-  data.tar.gz: c2014a4055874af1edbdc3fbee60e58b3f182ba37278f5f0738f4699256a0669b84e8b7d731494c5493e04fb249c3135cb31e5a716e687cd677fd3f9fa1a8da9
+  metadata.gz: 3e41e5d5a41dfaa44c67c3e99f28b0b37675774b3509f22d417f7bc2e9c664cccb9b480c8218a72ba63ce9876d2c7d09cbfc0bf8ab2c04d773f0e9e8d3818657
+  data.tar.gz: 82393a8ad2d76ebd853845a9f1de46cf1aa2175d56e0883004dc770fb9eaf5253dc23750a9eafb4cb36a8a751f5794071bd42fda0d8a2f4f68989486f31dccdc

data/README.md

@@ -38,6 +38,7 @@ For more detail on this, see [configuration options](#configuration-options).
   * ...And backreferences(!!!), e.g. `/(this|that) \1/` `/(?<name>foo) \k<name>/`
   * Groups work fine, even if nested or optional e.g. `/(even(this(works?))) \1 \2 \3/`, `/what about (this)? \1/`
   * Non-capture groups, e.g. `/(?:foo)/`
+  * Comment groups, e.g. `/foo(?#comment)bar/`
 * Control characters, e.g. `/\ca/`, `/\cZ/`, `/\C-9/`
 * Escape sequences, e.g. `/\x42/`, `/\x5word/`, `/#{"\x80".force_encoding("ASCII-8BIT")}/`
 * Unicode characters, e.g. `/\u0123/`, `/\uabcd/`, `/\u{789}/`
@@ -45,8 +46,9 @@ For more detail on this, see [configuration options](#configuration-options).
 
 * Regexp options can also be used:
   * Case insensitive examples: `/cool/i.examples #=> ["cool", "cooL", "coOl", "coOL", ...]`
-  * Multiline examples: `/./m.examples(max_group_results: 999) #=> ["a", "b", "c", ..., "\n"]`
+  * Multiline examples: `/./m.examples #=> ["\n", "a", "b", "c", "d"]`
   * Extended form examples: `/line1 #comment \n line2/x.examples #=> ["line1line2"]`
+  * Options toggling supported: `/before(?imx-imx)after/`, `/before(?imx-imx:subexpr)after/`
 
 ## Bugs and Not-Yet-Supported syntax
 
@@ -54,10 +56,7 @@ For more detail on this, see [configuration options](#configuration-options).
   * `/[[abc]]/.examples`  (which _should_ return `["a", "b", "c"]`)
   * `/[[a-d]&&[c-f]]/.examples` (which _should_ return: `["c", "d"]`)
 
-* Extended groups are not yet supported, such as:
-  * Including comments inside the pattern, i.e. `/(?#...)/`
-  * Conditional capture groups, such as `/(group1) (?(1)yes|no)`
-  * Options toggling, i.e. `/(?imx)/`, `/(?-imx)/`, `/(?imx: re)/` and `/(?-imx: re)/`
+* Conditional capture groups, such as `/(group1) (?(1)yes|no)`
 
 * The patterns: `/\10/` ... `/\77/` should match the octal representation of their character code, if there is no nth grouped subexpression. For example, `/\10/.examples` should return `["\x08"]`. Funnily enough, I did not think of this when writing my regexp parser.
 

data/lib/regexp-examples/groups.rb

@@ -126,7 +126,7 @@ module RegexpExamples
 
     def result
       chars = CharSets::Any
-      chars |= ["\n"] if multiline
+      chars = (["\n"] | chars) if multiline
       chars.map do |result|
         GroupResult.new(result)
       end
@@ -134,12 +134,10 @@ module RegexpExamples
   end
 
   class MultiGroup
-    prepend GroupWithIgnoreCase
     attr_reader :group_id
-    def initialize(groups, group_id, ignorecase)
+    def initialize(groups, group_id)
       @groups = groups
       @group_id = group_id
-      @ignorecase = ignorecase
     end
 
     # Generates the result of each contained group

data/lib/regexp-examples/parser.rb

@@ -146,13 +146,44 @@ module RegexpExamples
       @current_position += 1
       @num_groups += 1
       group_id = nil # init
-      rest_of_string.match(/\A(\?)?(:|!|=|<(!|=|[^!=][^>]*))?/) do |match|
+      previous_ignorecase = @ignorecase
+      previous_multiline = @multiline
+      previous_extended = @extended
+      rest_of_string.match(
+        /
+          \A
+          (\?)?               # Is it a "special" group, i.e. starts with a "?"?
+            (
+              :               # Non capture group
+              |!              # Neglookahead
+              |=              # Lookahead
+              |\#             # Comment group
+              |<              # Lookbehind or named capture
+              (
+                !             # Neglookbehind
+                |=            # Lookbehind
+                |[^>]+        # Named capture
+              )
+              |[mix]*-?[mix]* # Option toggle
+          )?
+        /x
+      ) 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 match[2] == '#' # e.g. /(?#comment)/
+          comment_group = rest_of_string.match(/.*?[^\\](?:\\{2})*\)/)[0]
+          @current_position += comment_group.length
+        when match[2] =~ /\A(?=[mix-]+)([mix]*)-?([mix]*)/ # e.g. /(?i-mx)/
+          regexp_options_toggle($1, $2)
+          @current_position += $&.length + 1
+          if next_char == ':' # e.g. /(?i:subexpr)/
+            @current_position += 1
+          else
+            return parse_single_char_group('')
+          end
         when %w(! =).include?(match[2]) # e.g. /(?=lookahead)/, /(?!neglookahead)/
           raise IllegalSyntaxError, "Lookaheads are not regular; cannot generate examples"
         when %w(! =).include?(match[3]) # e.g. /(?<=lookbehind)/, /(?<!neglookbehind)/
@@ -163,7 +194,19 @@ module RegexpExamples
         end
       end
       groups = parse
-      MultiGroup.new(groups, group_id, @ignorecase)
+      @ignorecase = previous_ignorecase
+      @multiline = previous_multiline
+      @extended = previous_extended
+      MultiGroup.new(groups, group_id)
+    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")
     end
 
     def parse_multi_end_group

data/lib/regexp-examples/version.rb

@@ -1,3 +1,3 @@
 module RegexpExamples
-  VERSION = '0.5.1'
+  VERSION = '0.5.2'
 end

data/spec/regexp-examples_spec.rb

@@ -231,6 +231,13 @@ RSpec.describe Regexp, "#examples" do
       )
     end
 
+    context "comment group" do
+      examples_exist_and_match(
+        /a(?#comment)b/,
+        /a(?#ugly backslashy\ comment\\\))b/
+      )
+    end
+
     context "exact examples match" do
       # More rigorous tests to assert that ALL examples are being listed
       context "default config options" do
@@ -284,6 +291,19 @@ RSpec.describe Regexp, "#examples" do
           ).to eq %w(line1line2)
         end
       end
+
+      context "options toggling" do
+        context "rest of string" do
+          it { expect(/a(?i)b(?-i)c/.examples).to eq %w{abc aBc}}
+          it { expect(/a(?x)   b(?-x) c/.examples).to eq %w{ab\ c}}
+          it { expect(/(?m)./.examples(max_group_results: 999)).to include "\n" }
+        end
+        context "subexpression" do
+          it { expect(/a(?i:b)c/.examples).to eq %w{abc aBc}}
+          it { expect(/a(?i:b(?-i:c))/.examples).to eq %w{abc aBc}}
+          it { expect(/a(?-i:b)c/i.examples).to eq %w{abc abC Abc AbC}}
+        end
+      end
     end
 
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: regexp-examples
 version: !ruby/object:Gem::Version
-  version: 0.5.1
+  version: 0.5.2
 platform: ruby
 authors:
 - Tom Lord