will_scan_string 0.0.1

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+.bundle
+Gemfile.lock
+pkg/*

data/Gemfile

@@ -0,0 +1,4 @@
+source "http://rubygems.org"
+
+# Specify your gem's dependencies in will_scan_string.gemspec
+gemspec

data/README.md

@@ -0,0 +1,20 @@
+Will scan string
+================
+Multi-pass string replacement has always been fun. I don't know any good way to
+perform multiple replacements on strings, so I made this minor gem.
+
+Usage
+-----
+Just don't use this, but if you're curious: Check `spec/lib/will_scan_string`
+for examples and features.
+
+Notes
+-----
+This gem is buggy and nowhere friendly to use. It's designed for personal use
+and is very experimental. It uses various hacks to combine multiple regular
+expressions to a single big-ass regular expression and it therefore is quite
+common for 2 regular expressions conflicting each other.
+
+Known regexp conflicts and issues
+---------------------------------
+- The gem does not support named capture groups whatsoever.

data/Rakefile

@@ -0,0 +1 @@
+require 'bundler/gem_tasks'

data/lib/will_scan_string/regexp_traits.rb

@@ -0,0 +1,12 @@
+module WillScanString
+	module RegexpTraits
+		CAPTURE_GROUP_PATTERN = /(?<!\\)\((?:\?(?:<([a-z]+)\>|'([a-z]+)')|(?!\?))/i
+
+		def capture_groups
+			c = 0
+			r = []
+			source.scan(CAPTURE_GROUP_PATTERN) { r.push $+.present? ? $+.to_sym : c+=1 }
+			r
+		end
+	end
+end

data/lib/will_scan_string/string_scanner.rb

@@ -0,0 +1,51 @@
+module WillScanString
+	class StringScanner
+		def register_replacement( pattern, replacement )
+			@replacements = [] if @replacements.nil?
+			@replacements << [ pattern, replacement, @replacements.last.present? ? @replacements.last[2] + (@replacements.last[0].is_a?(Regexp) ? @replacements.last[0].capture_groups.length : 0) + 1 : 0 ]
+			@replacements_regexp = nil
+		end
+
+		def replace( string )
+			string.gsub(replacement_regexp) do
+				m, r = *get_match_and_replacement( $~ )
+				execute_replacement_with_match r, m
+			end
+		end
+
+		protected
+		def get_match_and_replacement( m )
+			m = m.to_a.tap{ |m| m.shift }
+			i = m.find_index{ |v| v.present? }
+			r = find_replacement_by_index(i)
+			cps = [0] + (r[0].is_a?(Regexp) ? r[0].capture_groups : [])
+			m = m[i, cps.length]
+			[m, r[1]]
+		end
+
+		def execute_replacement_with_match( r, m )
+			r.is_a?(Proc) ? r.call(*m) : r.to_s
+		end
+
+		def find_replacement_by_index( i )
+			@replacements.find{ |r| r[2] == i }
+		end
+
+		def replacement_regexp
+			@replacements_regexp ||= reconstruct_replacement_regexp
+		end
+
+		private
+		def reconstruct_replacement_regexp
+			additional_offset = 1
+			pattern = @replacements.map(&:first).map{ |pat|
+				cpsc = pat.is_a?(Regexp) ? pat.capture_groups.length : 0
+				pat = pat.is_a?(Regexp) ? pat.source : Regexp.escape(pat.to_s)
+				pat.gsub!(/(?<!\\\\)(?<=\\)(\d+)/){ $1.to_i + additional_offset }
+				additional_offset += 1 + cpsc
+				"(#{pat})"
+			}.join "|"
+			/(?:#{pattern})/
+		end
+	end
+end

data/lib/will_scan_string/version.rb

@@ -0,0 +1,3 @@
+module WillScanString
+  VERSION = "0.0.1"
+end

data/lib/will_scan_string.rb

@@ -0,0 +1,7 @@
+require "will_scan_string/version"
+require "will_scan_string/string_scanner"
+require "will_scan_string/regexp_traits"
+
+module WillScanString
+	Regexp.send( :include, RegexpTraits )
+end

data/spec/lib/will_scan_string/regexp_traits_spec.rb

@@ -0,0 +1,41 @@
+require 'spec_helper.rb'
+
+describe WillScanString::RegexpTraits do
+	it "should match regular capture groups" do
+		/(a)/.capture_groups.should eql [ 1 ]
+	end
+
+	it "should not match escaped capture groups" do
+		/\(\)/.capture_groups.should eql []
+	end
+
+	it "should match named capture groups with less-than & greater-than characters" do
+		/(?<a>a)/.capture_groups.should eql [ :a ]
+	end
+
+	it "should match named capture groups with single quotes" do
+		/(?'a'a)/.capture_groups.should eql [ :a ]
+	end
+
+	it "should match nested regular capture groups" do
+		/(a(b))/.capture_groups.should eql [ 1, 2 ]
+	end
+
+	it "should ignore non-capture groups" do
+		/(?:a)/.capture_groups.should eql []
+	end
+
+	it "should ignore look-aheads and look-behinds" do
+		/(?=)/.capture_groups.should eql []
+		/(?!)/.capture_groups.should eql []
+		/(?<=)/.capture_groups.should eql []
+		/(?<!)/.capture_groups.should eql []
+	end
+
+	it "should match the capture groups in my bbcode gem's regular expressions" do
+		/\[(\/?)([a-z0-9_-]*)(\s*=?(?:(?:\s*(?:(?:[a-z0-9_-]+)|(?<=\=))\s*[:=]\s*)?(?:"[^"\\]*(?:\\[\s\S][^"\\]*)*"|'[^'\\]*(?:\\[\s\S][^'\\]*)*'|[^\]\s,]+|(?<=,)(?=\s*,))\s*,?\s*)*)\]/i.capture_groups.should \
+			eql [ 1, 2, 3 ]
+		/(?:\s*(?:([a-z0-9_-]+)|^)\s*[:=]\s*)?("[^"\\]*(?:\\[\s\S][^"\\]*)*"|'[^'\\]*(?:\\[\s\S][^'\\]*)*'|[^\]\s,]+|(?<=,)(?=\s*,))\s*,?/i.capture_groups.should \
+			eql [ 1, 2 ]
+	end
+end

data/spec/lib/will_scan_string/string_scanner_spec.rb

@@ -0,0 +1,32 @@
+require 'spec_helper.rb'
+
+describe WillScanString::StringScanner do
+	it "should perform a regular replacement" do
+		ss = WillScanString::StringScanner.new
+		ss.register_replacement ":)", "HAPPY"
+		ss.replace(":)").should eql "HAPPY"
+	end
+
+	it "should perform a regexp replacement with a capture group" do
+		ss = WillScanString::StringScanner.new
+		ss.register_replacement %r{<([a-z]+)>.*?</\1>}, ->(_, tagname){ "#{tagname}" }
+		ss.replace("<strong>hi!</strong>").should eql("strong")
+	end
+
+	it "should not replace replaced strings" do
+		ss = WillScanString::StringScanner.new
+		ss.register_replacement ":)", %{<img src="happy.png" alt=":)" title=":)">}
+		ss.register_replacement "<", "&lt;"
+		ss.register_replacement ">", "&gt;"
+		ss.register_replacement "\"", "&quot;"
+		ss.register_replacement "&", "&amp;"
+		ss.replace("& :)").should eql %{&amp; <img src="happy.png" alt=":)" title=":)">}
+	end
+
+	it "should be able to use multiple regular expressions to replace with" do
+		ss = WillScanString::StringScanner.new
+		ss.register_replacement /(a)(b)/, "AB"
+		ss.register_replacement /(c)(d)/, "CD"
+		ss.replace("abcd").should eql "ABCD"
+	end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,9 @@
+require 'rubygems'
+require 'bundler/setup'
+require 'active_support/all'
+
+require 'will_scan_string'
+
+RSpec.configure do |config|
+  # some (optional) config here
+end

data/will_scan_string.gemspec

@@ -0,0 +1,24 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "will_scan_string/version"
+
+Gem::Specification.new do |s|
+  s.name        = "will_scan_string"
+  s.version     = WillScanString::VERSION
+  s.authors     = ["Toby Hinloopen"]
+  s.email       = ["toby@kutcomputers.nl"]
+  s.homepage    = ""
+  s.summary     = %q{Gem for string replacements using multiple regular expressions in a single pass.}
+  s.description = %q{Gem for string replacements using multiple regular expressions in a single pass.}
+
+  s.rubyforge_project = "will_scan_string"
+
+	s.add_development_dependency "rspec", "~> 2.6"
+	s.add_dependency "activesupport", "~> 3.0.9"
+	s.add_dependency "i18n", "~> 0.5.0"
+
+  s.files         = `git ls-files`.split("\n")
+  s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  s.require_paths = ["lib"]
+end

metadata

@@ -0,0 +1,95 @@
+--- !ruby/object:Gem::Specification
+name: will_scan_string
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Toby Hinloopen
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2011-11-04 00:00:00.000000000Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &70303473805000 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.6'
+  type: :development
+  prerelease: false
+  version_requirements: *70303473805000
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: &70303473803740 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 3.0.9
+  type: :runtime
+  prerelease: false
+  version_requirements: *70303473803740
+- !ruby/object:Gem::Dependency
+  name: i18n
+  requirement: &70303473802140 !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.5.0
+  type: :runtime
+  prerelease: false
+  version_requirements: *70303473802140
+description: Gem for string replacements using multiple regular expressions in a single
+  pass.
+email:
+- toby@kutcomputers.nl
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- README.md
+- Rakefile
+- lib/will_scan_string.rb
+- lib/will_scan_string/regexp_traits.rb
+- lib/will_scan_string/string_scanner.rb
+- lib/will_scan_string/version.rb
+- spec/lib/will_scan_string/regexp_traits_spec.rb
+- spec/lib/will_scan_string/string_scanner_spec.rb
+- spec/spec_helper.rb
+- will_scan_string.gemspec
+homepage: ''
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: will_scan_string
+rubygems_version: 1.8.11
+signing_key: 
+specification_version: 3
+summary: Gem for string replacements using multiple regular expressions in a single
+  pass.
+test_files:
+- spec/lib/will_scan_string/regexp_traits_spec.rb
+- spec/lib/will_scan_string/string_scanner_spec.rb
+- spec/spec_helper.rb