regex 1.1.0 → 1.1.1

data/.ruby

@@ -0,0 +1,43 @@
+---
+source:
+- meta
+authors:
+- name: Thomas Sawyer
+  email: transfire@gmail.com
+- name: Tyler Rick
+copyrights: []
+replacements: []
+alternatives: []
+requirements:
+- name: detroit
+  groups:
+  - build
+  development: true
+- name: qed
+  groups:
+  - test
+  development: true
+dependencies: []
+conflicts: []
+repositories:
+- uri: git://github.com/proutils/regex.git
+  scm: git
+  name: upstream
+resources:
+  Website: http://rubyworks.github.com/regex
+  User Guide: http://wiki.github.com/rubyworks/regex
+  Source Code: http://github.com/rubyworks/regex
+  Mailing List: http://groups.google.com/group/rubyworks-mailinglist
+extra: {}
+load_path:
+- lib
+revision: 0
+created: '2006-05-09'
+summary: Regex is a simple commmand-line Regular Expression tool.
+title: Regex
+version: 1.1.1
+name: regex
+description: ! 'Regex is a simple commmand-line Regular Expression tool
+
+  that makes it easy to search documents for content matches.'
+date: '2011-10-24'

data/.yardopts

@@ -0,0 +1,8 @@
+--title "RegEx"
+--readme README.rdoc
+--protected
+--private
+lib/**/*.rb
+-
+[A-Z]*.*
+

data/COPYING.rdoc

@@ -0,0 +1,31 @@
+= COPYRIGHT NOTICES
+
+== Regex
+
+Copyright:: (c) 2010 Thomas Sawyer, Rubyworks
+License:: BSD-2-Clause
+Website:: http://rubyworks.github.com/tapout
+
+    Copyright 2010 Thomas Sawyer. All rights reserved.
+
+    Redistribution and use in source and binary forms, with or without
+    modification, are permitted provided that the following conditions are met:
+
+       1. Redistributions of source code must retain the above copyright notice,
+          this list of conditions and the following disclaimer.
+
+       2. Redistributions in binary form must reproduce the above copyright
+          notice, this list of conditions and the following disclaimer in the
+          documentation and/or other materials provided with the distribution.
+
+    THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES,
+    INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+    AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
+    COPYRIGHT HOLDERS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+    INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
+    NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR  SERVICES; LOSS OF USE,
+    DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
+    OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+    NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+    EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+

data/{HISTORY → HISTORY.rdoc}

@@ -1,5 +1,17 @@
 = RELEASE HISTORY
 
+== 1.1.1 / 2011-10-24
+
+Maintenance release updates build configuration. This release
+also adds a man-page and fixes one bug with single search output.
+
+Changes:
+
+* Modernize build configuration.
+* Fix return value when no single match is found.
+* Add man-page for help.
+
+
 == 1.1.0 / 2010-10-12
 
 This release adds a detailed output option, and corrects

data/{README → README.rdoc}

@@ -18,8 +18,9 @@ well. Well that's what you get.
 
 == RESOURCES
 
-* Home: http://rubyworks.github.com/regex
-* Code: http://github.com/rubyworks/regex
+* {Home}[http://rubyworks.github.com/regex]
+* {Code}[http://github.com/rubyworks/regex]
+* {Mail}[http://groups.google.com/groups/rubyworks-mailinglist]
 
 
 == USAGE
@@ -81,14 +82,23 @@ Check out the <code>--help</code> and I am sure the rest will be smooth sailing.
 But it you want more information, then do us the good favor of jumping over
 to the wiki[http://wiki.github.com/rubyworks/regex].
 
+
+== OUTPUT
+
+Regex has three output modes. YAML, JSON and standard text. The standard
+text output is unique in that it utilizes special ASCII characters
+to separate matches and regex groups. ASCII 29, called the *record separator*,
+is used to separate repeat matches. ASCII 30, called the *group separator*, is
+is used to separate regular expression groups.
+
+
 == STATUS
 
-This is a very early release. So don't expect every feature under the sun just yet,
-or that every detail is going to work peachy. But hey, if something needs fixing
-or a feature needs adding, well then get in there and send me a patch. Open
-source software is built on *TEAM WORK*, baby.
+The project is maturing but still a touch wet behnd the years. So don't be too surprised if
+it doesn't have every feature under the sun just yet, or that every detail is going to work
+absolutely peachy. But hey, if something needs fixing or a feature needs adding, well then get
+in there and send me a patch. Open source software is built on *TEAM WORK*, right?
 
-Expect a potenial for rapid change here at the beginning.
 
 == COPYRIGHT
 
@@ -96,5 +106,5 @@ Copyright (c) 2010 Thomas Sawyer
 
 Regex is licensed under the terms of the Apache License, Version 2.0.
 
-See LICENSE file for details.
+See COPYING.rdoc file for details.
 

data/lib/regex.rb

@@ -1,19 +1,20 @@
 module Regex
-  DIRECTORY = File.dirname(__FILE__)
-
   # Access to PACAKGE metadata.
-  def self.package
-    @package ||= (
+  def self.metadata
+    @metadata ||= (
       require 'yaml'
-      YAML.load(File.new(DIRECTORY + '/regex/package.yml'))
+      YAML.load(File.new(File.dirname(__FILE__) + '/regex.yml'))
     )
   end
 
   # Need VRESION? You got it.
   def self.const_missing(name)
-    package[name.to_s.downcase] || super(name)
+    metadata[name.to_s.downcase] || super(name)
   end
 
+  # TODO: This is only here to support broken Ruby 1.8.x.
+  VERSION = metadata['version']
+
   # Shortcut to create a new Regex::Extractor instance.
   def self.new(*io)
     Extractor.new(*io)

data/lib/regex.yml

@@ -0,0 +1,43 @@
+---
+source:
+- meta
+authors:
+- name: Thomas Sawyer
+  email: transfire@gmail.com
+- name: Tyler Rick
+copyrights: []
+replacements: []
+alternatives: []
+requirements:
+- name: detroit
+  groups:
+  - build
+  development: true
+- name: qed
+  groups:
+  - test
+  development: true
+dependencies: []
+conflicts: []
+repositories:
+- uri: git://github.com/proutils/regex.git
+  scm: git
+  name: upstream
+resources:
+  Website: http://rubyworks.github.com/regex
+  User Guide: http://wiki.github.com/rubyworks/regex
+  Source Code: http://github.com/rubyworks/regex
+  Mailing List: http://groups.google.com/group/rubyworks-mailinglist
+extra: {}
+load_path:
+- lib
+revision: 0
+created: '2006-05-09'
+summary: Regex is a simple commmand-line Regular Expression tool.
+title: Regex
+version: 1.1.1
+name: regex
+description: ! 'Regex is a simple commmand-line Regular Expression tool
+
+  that makes it easy to search documents for content matches.'
+date: '2011-10-24'

data/lib/regex/extractor.rb

@@ -16,6 +16,9 @@ module Regex
     # the record deliminator. This is the default value.
     DELIMINATOR_RECORD = 30.chr + "\n"
 
+    # TODO: Separate by file ?
+    # DELIMINATOR_FILE = 28.chr +" \n"
+
     #
     def self.input_cache(input)
       @input_cache ||= {}
@@ -41,6 +44,9 @@ module Regex
     # Select built-in regular expression by name.
     attr_accessor :template
 
+    # Is a recusive serach?
+    attr_accessor :recursive
+
     # Index of expression return.
     attr_accessor :index
 
@@ -53,7 +59,7 @@ module Regex
     # Escape expression.
     attr_accessor :escape
 
-    # Repeat Match.
+    # Repeat Match (global).
     attr_accessor :repeat
 
     # Output format.
@@ -263,7 +269,7 @@ module Regex
 
     # Structure the matchdata for single match.
     def structure_single
-      structure_repeat.first
+      structure_repeat.first || []
     end
 
     # Structure the matchdata for repeat matches.
@@ -281,9 +287,14 @@ module Regex
     def scan
       list = []
       io.each do |input|
-        text = read(input)
-        text.scan(regex) do
-          list << Match.new(input, $~)
+        # TODO: limit to text files, how?
+        begin
+          text = read(input)
+          text.scan(regex) do
+            list << Match.new(input, $~)
+          end
+        rescue => err
+          warn(input.inspect + ' ' + err.to_s) if $VERBOSE
         end
       end
       list
@@ -333,6 +344,12 @@ module Regex
         opt.on('--search', '-s PATTERN', "search for regular expression") do |re|
           options[:pattern] = re
         end
+        opt.on('--recursive', '-R', 'search recursively though subdirectories') do
+          options[:recursive] = true
+        end
+        opt.on('--escape', '-e', 'make all patterns verbatim string matchers') do
+          options[:escape] = true
+        end
         opt.on('--index', '-n INT', "return a specific match index") do |int|
           options[:index] = int.to_i
         end
@@ -387,11 +404,17 @@ module Regex
         end
       end
 
-      files = argv
-
-      files.each do |file|
-        if !File.file?(file)
-          $stderr.puts "No such file -- '#{file}'."
+      files = []
+      argv.each do |file|
+        if File.directory?(file)
+          if options[:recursive]
+            rec_files = Dir[File.join(file, '**')].reject{ |d| File.directory?(d) }
+            files.concat(rec_files)
+          end
+        elsif File.file?(file)
+          files << file
+        else
+          $stderr.puts "Not a file -- '#{file}'."
           exit 1
         end
       end

data/lib/regex/replacer.rb

@@ -1,4 +1,5 @@
 require 'stringio'
+require 'optparse'
 
 module Regex
 
@@ -8,6 +9,9 @@ module Regex
     # Array of [search, replace] rules.
     attr_reader :rules
 
+    # Is this a recursive search?
+    attr_accessor :recursive
+
     # Make all patterns exact string matchers.
     attr_accessor :escape
 
@@ -23,6 +27,9 @@ module Regex
     # Make backups of files when they change.
     attr_accessor :backup
 
+    # Interactive replacement.
+    attr_accessor :interactive
+
     #
     def initialize(options={})
       @rules = []
@@ -40,12 +47,16 @@ module Regex
     def apply(*ios)
       ios.each do |io|
         original = (IO === io || StringIO === io ? io.read : io.to_s)
-        generate = original
+        generate = original.to_s
         rules.each do |(pattern, replacement)|
-          if pattern.global
-            generate = generate.gsub(pattern.to_re, replacement)
-          else
-            generate = generate.sub(pattern.to_re, replacement)
+          begin
+            if pattern.global
+              generate = generate.gsub(pattern.to_re, replacement)
+            else
+              generate = generate.sub(pattern.to_re, replacement)
+            end
+          rescue => err
+            warn(io.inspect + ' ' + err.to_s) if $VERBOSE
           end
         end
         if original != generate
@@ -54,6 +65,20 @@ module Regex
       end
     end
 
+    #
+    # TODO: interactive mode needs to handle \1 style substitutions.
+    def interactive_gsub(string, pattern, replacement)
+      copy = string.dup
+      string.scan(pattern) do |match|
+        print "#{match} ? (Y/n)"
+        case ask
+        when 'y', 'Y', ''
+          copy[$~.begin(0)..$~.end(0)] = replacement
+        else
+        end
+      end
+    end
+
     private
 
     # Parse pattern matcher.
@@ -92,7 +117,7 @@ module Regex
       replaces = []
       options = {}
       parser = OptionParser.new do |opt|
-        opt.on('--subtitute', '-s PATTERN', 'search portion of substitution') do |search|
+        opt.on('--search', '-s PATTERN', 'search portion of substitution') do |search|
           searches << search
         end
         opt.on('--template', '-t NAME', 'search for built-in regular expression') do |name|
@@ -101,7 +126,10 @@ module Regex
         opt.on('--replace', '-r STRING', 'replacement string of substitution') do |replace|
           replaces << replace
         end
-        opt.on('--escape', '-e', 'make all patterns exact string matchers') do
+        opt.on('--recursive', '-R', 'search recursively though subdirectories') do
+          options[:recursive] = true
+        end
+        opt.on('--escape', '-e', 'make all patterns verbatim string matchers') do
           options[:escape] = true
         end
         opt.on('--insensitive', '-i', 'make all patterns case-insensitive matchers') do
@@ -119,7 +147,10 @@ module Regex
         opt.on('-b', '--backup', 'backup any files that are changed') do
           options[:backup] = true
         end
-        opt.on_tail('--debug', 'run in debug mode') do
+        opt.on('-i', '--interactive', 'interactive mode') do
+          options[:interactive] = true
+        end
+         opt.on_tail('--debug', 'run in debug mode') do
           $DEBUG = true
         end
         opt.on_tail('--help', '-h', 'display this lovely help message') do
@@ -129,10 +160,19 @@ module Regex
       end
       parser.parse!(argv)
 
-      files = argv
-      files.each do |file|
+      files = []
+
+      argv.each{ |file|
         raise "file does not exist -- #{file}" unless File.exist?(file)
-      end
+        if File.directory?(file)
+          if options[:recursive] 
+            files.concat Dir[File.join(file, '**')].reject{ |d| File.directory?(d) }
+          end
+        else
+          files << file
+        end
+      }
+
       targets = files.empty? ? [ARGF] : files.map{ |f| File.new(f) }
 
       unless searches.size == replaces.size

data/lib/regex/templates.rb

@@ -3,8 +3,9 @@ module Regex
   # = Templates
   #
   # TODO: What about regular expressions with variable content?
-  # Should these be methods rather than constants? But then how
-  # would we handle named substituions?
+  # But then how would we handle named substituions?
+  #
+  # TODO: Should these be methods rather than constants?
   module Templates
 
     # Empty line.
@@ -13,6 +14,7 @@ module Regex
     # Blank line.
     BLANK = /^\s*$/
 
+    #
     NUMBER = /[-+]?[0-9]*\.?[0-9]+/
 
     # Markup language tag, e.g \<a>stuff</a>.
@@ -21,8 +23,8 @@ module Regex
     # IPv4 Address
     IPV4 = /\b(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.(25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\b/
 
-    # Username
-    USERNAME = /^[a-zA-Z0-9_]{3,16}$/
+    # Dni (spanish ID card)
+    DNI = /^\d{8}[A-Za-z]{1}$/
 
     # Email Address
     EMAIL = /([a-zA-Z0-9_\-\.]+)@((\[[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?)/i
@@ -51,6 +53,34 @@ module Regex
     # HTTP URL Address
     HTTP = /^(https?:\/\/)?([\da-z\.-]+)\.([a-z\.]{2,6})([\/\w \?=.-]*)*\/?$/
 
+    # Validates Credit Card numbers, contains 16 numbers in groups of 4 separated
+    # by `-`, space or nothing.
+    CREDITCARD = /^(\d{4}-){3}\d{4}$|^(\d{4}\s){3}\d{4}$|^\d{16}$/
+
+    # MasterCard credit card
+    MASTERCARD = /^5[1-5]\d{14}$/
+
+    # Visa credit card.
+    VISA = /^4\d{15}$/
+
+    # TODO: Better name?
+    UNIXWORD = /^[a-zA-Z0-9_]*$/
+
+    # Username, at lest 3 characters and no more than 16.
+    USERNAME = /^[a-zA-Z0-9_]{3,16}$/
+
+    # Twitter username
+    TWITTER_USERNMAE = /^([a-z0-9\_])+$/ix
+
+    # Github username
+    GITHUB_USERNAME = /^([a-z0-9\_\-])+$/ix
+
+    # Slideshare username
+    SLIDESHARE_USERNAME = /^([a-z0-9])+$/ix
+
+    # Del.icio.us username
+    DELICIOUS_USERNMAME = /^([a-z0-9\_\-])+$/ix
+
     # Ruby comment block.
     RUBYBLOCK = /^=begin\s*(.*?)\n(.*?)\n=end/m
 
@@ -58,7 +88,7 @@ module Regex
     # TODO: Not quite right.
     RUBYMETHOD_WITH_COMMENT = /(^\ *\#.*?)^\s*def\s*(.*?)$/m
 
-    #
+    # Ruby method definition.
     RUBYMETHOD = /^\ *def\s*(.*?)$/
 
     # By the legendary abigail. Fails to match if and only if it is matched against