stringex 1.3.1 → 1.3.2

data/lib/stringex/string_extensions.rb

@@ -0,0 +1,198 @@
+# encoding: UTF-8
+
+module Stringex
+  # These methods are all added on String class.
+  module StringExtensions
+    def self.included(base) # :nodoc:
+      base.extend(ClassMethods)
+    end
+
+    # Returns the string converted (via Textile/RedCloth) to HTML format
+    # or self [with a friendly warning] if Redcloth is not available.
+    #
+    # Using <tt>:lite</tt> argument will cause RedCloth to not wrap the HTML in a container
+    # P element, which is useful behavior for generating header element text, etc.
+    # This is roughly equivalent to ActionView's <tt>textilize_without_paragraph</tt>
+    # except that it makes RedCloth do all the work instead of just gsubbing the return
+    # from RedCloth.
+    def to_html(lite_mode = false)
+      if defined?(RedCloth)
+        if lite_mode
+          RedCloth.new(self, [:lite_mode]).to_html
+        else
+          if self =~ /<pre>/
+            RedCloth.new(self).to_html.tr("\t", "")
+          else
+            RedCloth.new(self).to_html.tr("\t", "").gsub(/\n\n/, "")
+          end
+        end
+      else
+        warn "String#to_html was called without RedCloth being successfully required"
+        self
+      end
+    end
+
+    # Create a URI-friendly representation of the string. This is used internally by
+    # acts_as_url[link:classes/Stringex/ActsAsUrl/ClassMethods.html#M000012]
+    # but can be called manually in order to generate an URI-friendly version of any string.
+    def to_url(options = {})
+      remove_formatting(options).downcase.replace_whitespace("-").collapse("-")
+    end
+
+    # Performs multiple text manipulations. Essentially a shortcut for typing them all. View source
+    # below to see which methods are run.
+    def remove_formatting(options = {})
+      strip_html_tags.convert_smart_punctuation.convert_accented_entities.convert_misc_entities.convert_misc_characters(options).to_ascii.collapse
+    end
+
+    # Removes HTML tags from text. This code is simplified from Tobias Luettke's regular expression
+    # in Typo[http://typosphere.org].
+    def strip_html_tags(leave_whitespace = false)
+      name = /[\w:_-]+/
+      value = /([A-Za-z0-9]+|('[^']*?'|"[^"]*?"))/
+      attr = /(#{name}(\s*=\s*#{value})?)/
+      rx = /<[!\/?\[]?(#{name}|--)(\s+(#{attr}(\s+#{attr})*))?\s*([!\/?\]]+|--)?>/
+      (leave_whitespace) ?  gsub(rx, "").strip : gsub(rx, "").gsub(/\s+/, " ").strip
+    end
+
+    # Converts HTML entities into the respective non-accented letters. Examples:
+    #
+    #   "&aacute;".convert_accented_entities # => "a"
+    #   "&ccedil;".convert_accented_entities # => "c"
+    #   "&egrave;".convert_accented_entities # => "e"
+    #   "&icirc;".convert_accented_entities # => "i"
+    #   "&oslash;".convert_accented_entities # => "o"
+    #   "&uuml;".convert_accented_entities # => "u"
+    #
+    # Note: This does not do any conversion of Unicode/ASCII accented-characters. For that
+    # functionality please use <tt>to_ascii</tt>.
+    def convert_accented_entities
+      gsub(/&([A-Za-z])(grave|acute|circ|tilde|uml|ring|cedil|slash);/, '\1')
+    end
+
+    # Converts HTML entities (taken from common Textile/RedCloth formattings) into plain text formats.
+    #
+    # Note: This isn't an attempt at complete conversion of HTML entities, just those most likely
+    # to be generated by Textile.
+    def convert_misc_entities
+      dummy = dup
+      {
+        "#822[01]" => "\"",
+        "#821[67]" => "'",
+        "#8230" => "...",
+        "#8211" => "-",
+        "#8212" => "--",
+        "#215" => "x",
+        "gt" => ">",
+        "lt" => "<",
+        "(#8482|trade)" => "(tm)",
+        "(#174|reg)" => "(r)",
+        "(#169|copy)" => "(c)",
+        "(#38|amp)" => "and",
+        "nbsp" => " ",
+        "(#162|cent)" => " cent",
+        "(#163|pound)" => " pound",
+        "(#188|frac14)" => "one fourth",
+        "(#189|frac12)" => "half",
+        "(#190|frac34)" => "three fourths",
+        "(#176|deg)" => " degrees"
+      }.each do |textiled, normal|
+        dummy.gsub!(/&#{textiled};/, normal)
+      end
+      dummy.gsub(/&[^;]+;/, "")
+    end
+
+    # Converts MS Word 'smart punctuation' to ASCII
+    #
+    def convert_smart_punctuation
+      dummy = dup
+      {
+
+        "(“|”|\302\223|\302\224|\303\222|\303\223)" => '"',
+        "(‘|’|\302\221|\302\222|\303\225)" => "'",
+        "…" => "...",
+      }.each do |smart, normal|
+        dummy.gsub!(/#{smart}/, normal)
+      end
+      dummy
+    end
+
+    # Converts various common plaintext characters to a more URI-friendly representation.
+    # Examples:
+    #
+    #   "foo & bar".convert_misc_characters # => "foo and bar"
+    #   "Chanel #9".convert_misc_characters # => "Chanel number nine"
+    #   "user@host".convert_misc_characters # => "user at host"
+    #   "google.com".convert_misc_characters # => "google dot com"
+    #   "$10".convert_misc_characters # => "10 dollars"
+    #   "*69".convert_misc_characters # => "star 69"
+    #   "100%".convert_misc_characters # => "100 percent"
+    #   "windows/mac/linux".convert_misc_characters # => "windows slash mac slash linux"
+    #
+    # Note: Because this method will convert any & symbols to the string "and",
+    # you should run any methods which convert HTML entities (convert_html_entities and convert_misc_entities)
+    # before running this method.
+    def convert_misc_characters(options = {})
+      dummy = dup.gsub(/\.{3,}/, " dot dot dot ") # Catch ellipses before single dot rule!
+      # Special rules for money
+      {
+        /(\s|^)\$(\d+)\.(\d+)(\s|$)/ => '\2 dollars \3 cents',
+        /(\s|^)£(\d+)\.(\d+)(\s|$)/u => '\2 pounds \3 pence',
+      }.each do |found, replaced|
+        replaced = " #{replaced} " unless replaced =~ /\\1/
+        dummy.gsub!(found, replaced)
+      end
+      # Back to normal rules
+      misc_characters = 
+      {
+        /\s*&\s*/ => "and",
+        /\s*#/ => "number",
+        /\s*@\s*/ => "at",
+        /(\S|^)\.(\S)/ => '\1 dot \2',
+        /(\s|^)\$(\d*)(\s|$)/ => '\2 dollars',
+        /(\s|^)£(\d*)(\s|$)/u => '\2 pounds',
+        /(\s|^)¥(\d*)(\s|$)/u => '\2 yen',
+        /\s*\*\s*/ => "star",
+        /\s*%\s*/ => "percent",
+        /(\s*=\s*)/ => " equals ",
+        /\s*\+\s*/ => "plus"
+      }
+      misc_characters[/\s*(\\|\/)\s*/] = 'slash' unless options[:allow_slash]
+      misc_characters.each do |found, replaced|
+        replaced = " #{replaced} " unless replaced =~ /\\1/
+        dummy.gsub!(found, replaced)
+      end
+      dummy = dummy.gsub(/(^|\w)'(\w|$)/, '\1\2').gsub(/[\.,:;()\[\]\?!\^'"_]/, " ")
+    end
+
+    # Replace runs of whitespace in string. Defaults to a single space but any replacement
+    # string may be specified as an argument. Examples:
+    #
+    #   "Foo       bar".replace_whitespace # => "Foo bar"
+    #   "Foo       bar".replace_whitespace("-") # => "Foo-bar"
+    def replace_whitespace(replace = " ")
+      gsub(/\s+/, replace)
+    end
+
+    # Removes specified character from the beginning and/or end of the string and then performs
+    # <tt>String#squeeze(character)</tt>, condensing runs of the character within the string.
+    #
+    # Note: This method has been superceded by ActiveSupport's squish method.
+    def collapse(character = " ")
+      sub(/^#{character}*/, "").sub(/#{character}*$/, "").squeeze(character)
+    end
+
+    module ClassMethods
+      # Returns string of random characters with a length matching the specified limit. Excludes 0
+      # to avoid confusion between 0 and O.
+      def random(limit)
+        strong_alphanumerics = %w{
+          a b c d e f g h i j k l m n o p q r s t u v w x y z
+          A B C D E F G H I J K L M N O P Q R S T U V W X Y Z
+          1 2 3 4 5 6 7 8 9
+        }
+        Array.new(limit, "").collect{strong_alphanumerics[rand(61)]}.join
+      end
+    end
+  end
+end

data/lib/stringex/unidecoder.rb

@@ -0,0 +1,159 @@
+# encoding: UTF-8
+require "yaml"
+
+module Stringex
+  module Unidecoder
+    # Contains Unicode codepoints, loading as needed from YAML files
+    CODEPOINTS = Hash.new{|h, k|
+      h[k] = YAML.load_file(File.join(File.expand_path(File.dirname(__FILE__)), "unidecoder_data", "#{k}.yml"))
+    } unless defined?(CODEPOINTS)
+    LOCAL_CODEPOINTS = Hash.new unless defined?(LOCAL_CODEPOINTS)
+
+    class << self
+      # Returns string with its UTF-8 characters transliterated to ASCII ones
+      #
+      # You're probably better off just using the added String#to_ascii
+      def decode(string)
+        string.gsub(/[^\x00-\x7f]/u) do |codepoint|
+          if localized = local_codepoint(codepoint)
+            localized
+          else
+            begin
+              unpacked = codepoint.unpack("U")[0]
+              CODEPOINTS[code_group(unpacked)][grouped_point(unpacked)]
+            rescue
+              # Hopefully this won't come up much
+              # TODO: Make this note something to the user that is reportable to me perhaps
+              "?"
+            end
+          end
+        end
+      end
+
+      # Returns character for the given Unicode codepoint
+      def encode(codepoint)
+        ["0x#{codepoint}".to_i(16)].pack("U")
+      end
+
+      # Returns string indicating which file (and line) contains the
+      # transliteration value for the character
+      def in_yaml_file(character)
+        unpacked = character.unpack("U")[0]
+        "#{code_group(unpacked)}.yml (line #{grouped_point(unpacked) + 2})"
+      end
+
+      # Adds localized transliterations to Unidecoder
+      def localize_from(hash_or_path_to_file)
+        hash = if hash_or_path_to_file.is_a?(Hash)
+          hash_or_path_to_file
+        else
+          YAML.load_file(hash_or_path_to_file)
+        end
+        verify_local_codepoints hash
+      end
+
+      # Returns locale for localized transliterations
+      def locale
+        if @locale
+          @locale
+        elsif defined?(I18n)
+          I18n.locale
+        else
+          default_locale
+        end
+      end
+
+      # Sets locale for localized transliterations
+      def locale=(new_locale)
+        @locale = new_locale
+      end
+
+      # Returns default locale for localized transliterations. NOTE: Will set @locale as well.
+      def default_locale
+        @default_locale ||= "en"
+        @locale = @default_locale
+      end
+
+      # Sets the default locale for localized transliterations. NOTE: Will set @locale as well.
+      def default_locale=(new_locale)
+        @default_locale = new_locale
+        # Seems logical that @locale should be the new default
+        @locale = new_locale
+      end
+
+      # Returns the localized transliteration for a codepoint
+      def local_codepoint(codepoint)
+        locale_hash = LOCAL_CODEPOINTS[locale] || LOCAL_CODEPOINTS[locale.is_a?(Symbol) ? locale.to_s : locale.to_sym]
+        locale_hash && locale_hash[codepoint]
+      end
+
+      # Runs a block with a temporary locale setting, returning the locale to the original state when complete
+      def with_locale(new_locale, &block)
+        new_locale = default_locale if new_locale == :default
+        original_locale = locale
+        self.locale = new_locale
+        block.call
+        self.locale = original_locale
+      end
+
+      # Runs a block with default locale
+      def with_default_locale(&block)
+        with_locale default_locale, &block
+      end
+
+    private
+      # Returns the Unicode codepoint grouping for the given character
+      def code_group(unpacked_character)
+        "x%02x" % (unpacked_character >> 8)
+      end
+
+      # Returns the index of the given character in the YAML file for its codepoint group
+      def grouped_point(unpacked_character)
+        unpacked_character & 255
+      end
+
+      # Checks LOCAL_CODEPOINTS's Hash is in the format we expect before assigning it and raises
+      # instructive exception if not
+      def verify_local_codepoints(hash)
+        pass_check = hash.is_a?(Hash) && hash.all?{|key, value|
+          # Fuck a duck, eh?
+          [Symbol, String].include?(key.class) && value.is_a?(Hash) &&
+            value.keys.all?{|k| k.is_a?(String)} && value.values.all?{|v| v.is_a?(String)}
+        }
+        if pass_check
+          hash.each do |k, v|
+            LOCAL_CODEPOINTS[k] = v
+          end
+        else
+          raise ArgumentError, "LOCAL_CODEPOINTS is not correctly defined. Please see the README for more information on how to correctly format this data."
+        end
+      end
+    end
+  end
+
+  # Provide a simpler interface for localization implementations
+  class << self
+    %w{
+      localize_from
+      locale locale=
+      default_locale default_locale=
+      local_codepoint
+      with_locale with_default_locale
+    }.each do |name|
+      define_method name do |*args, &block|
+        Unidecoder.send name, *args, &block
+      end
+    end
+  end
+end
+
+module Stringex
+  module StringExtensions
+    # Returns string with its UTF-8 characters transliterated to ASCII ones. Example:
+    #
+    #   "⠋⠗⠁⠝⠉⠑".to_ascii #=> "braille"
+    def to_ascii
+      Stringex::Unidecoder.decode(self)
+    end
+  end
+end

data/lib/stringex/unidecoder_data/x00.yml

@@ -0,0 +1,257 @@
+---
+- "\x00"
+- "\x01"
+- "\x02"
+- "\x03"
+- "\x04"
+- "\x05"
+- "\x06"
+- "\a"
+- "\x08"
+- '  '
+- "\n"
+- "\v"
+- "\f"
+- "\r"
+- "\x0e"
+- "\x0f"
+- "\x10"
+- "\x11"
+- "\x12"
+- "\x13"
+- "\x14"
+- "\x15"
+- "\x16"
+- "\x17"
+- "\x18"
+- "\x19"
+- "\x1a"
+- "\e"
+- "\x1c"
+- "\x1d"
+- "\x1e"
+- "\x1f"
+- ' '
+- '!'
+- '"'
+- '#'
+- $
+- '%'
+- '&'
+- "'"
+- (
+- )
+- '*'
+- +
+- ','
+- '-'
+- .
+- /
+- 0
+- 1
+- 2
+- 3
+- 4
+- 5
+- 6
+- 7
+- 8
+- 9
+- ':'
+- ;
+- <
+- '='
+- '>'
+- '?'
+- '@'
+- A
+- B
+- C
+- D
+- E
+- F
+- G
+- H
+- I
+- J
+- K
+- L
+- M
+- N
+- O
+- P
+- Q
+- R
+- S
+- T
+- U
+- V
+- W
+- X
+- Y
+- Z
+- ']'
+- \
+- ']'
+- '^'
+- _
+- '`'
+- a
+- b
+- c
+- d
+- e
+- f
+- g
+- h
+- i
+- j
+- k
+- l
+- m
+- n
+- o
+- p
+- q
+- r
+- s
+- t
+- u
+- v
+- w
+- x
+- y
+- z
+- '{'
+- '|'
+- '}'
+- '~'
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- "'"
+- "'"
+- '"'
+- '"'
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ''
+- ' '
+- ''
+- C/
+- PS
+- $?
+- Y=
+- '|'
+- SS
+- '"'
+- (c)
+- a
+- '<<'
+- '!'
+- ''
+- (r)
+- '-'
+- deg
+- +-
+- 2
+- 3
+- "'"
+- u
+- P
+- '*'
+- ','
+- 1
+- o
+- '>>'
+- 1/4
+- 1/2
+- 3/4
+- ''
+- A
+- A
+- A
+- A
+- A
+- A
+- AE
+- C
+- E
+- E
+- E
+- E
+- I
+- I
+- I
+- I
+- D
+- N
+- O
+- O
+- O
+- O
+- O
+- x
+- O
+- U
+- U
+- U
+- U
+- Y
+- Th
+- ss
+- a
+- a
+- a
+- a
+- a
+- a
+- ae
+- c
+- e
+- e
+- e
+- e
+- i
+- i
+- i
+- i
+- d
+- n
+- o
+- o
+- o
+- o
+- o
+- /
+- o
+- u
+- u
+- u
+- u
+- y
+- th
+- y