Another localization

.gitignore

@@ -6,3 +6,4 @@
 /doc/
 /tags/
 Gemfile.lock
+.idea

lib/chronic.rb

@@ -7,6 +7,9 @@
 require 'chronic/parser'
 require 'chronic/date'
 require 'chronic/time'
+require 'chronic/locale'
+require 'chronic/locales/en'
+require 'chronic/locales/ru'
 
 require 'chronic/handler'
 require 'chronic/handlers'
@@ -74,10 +77,12 @@ class << self
     #
     # Returns The Time class Chronic uses internally.
     attr_accessor :time_class
+    attr_accessor :locale
   end
 
   self.debug = false
   self.time_class = ::Time
+  self.locale = :en
 
 
   # Parses a string containing a natural language date or time.
@@ -89,7 +94,8 @@ class << self
   # text - The String text to parse.
   # opts - An optional Hash of configuration options passed to Parser::new.
   def self.parse(text, options = {})
-    Parser.new(options).parse(text)
+    locale_class = Locale.by_name(options.delete(:locale) || locale)
+    Parser.new({locale: locale_class}.merge(options)).parse(text)
   end
 
   # Construct a new time object determining possible month overflows

lib/chronic/handlers.rb

@@ -452,7 +452,13 @@ def handle_s_r_p_a(tokens, options)
     end
 
     def handle_s_r_a_s_r_p_a(tokens, options)
-      anchor_span = get_anchor(tokens[4..tokens.size - 1], options)
+      anchor_tokens = tokens[4..tokens.size - 1]
+
+      anchor_span = if anchor_tokens.count > 1
+                      get_anchor(anchor_tokens, options)
+                    else
+                      Span.new(self.now, self.now + 1)
+                    end
 
       span = handle_srp(tokens[0..1]+tokens[4..6], anchor_span, options)
       handle_srp(tokens[2..3]+tokens[4..6], span, options)

lib/chronic/locale.rb

@@ -0,0 +1,26 @@
+require 'active_support/core_ext'
+
+module Chronic
+  class Locale
+
+    AVAILABLE = [:en, :ru]
+
+    def [](path)
+      path.to_s.split('.').reduce(self.class::LOCALE_HASH) do |value, element|
+        value[element.to_sym] || {}
+      end
+    end
+
+    class << self
+      def by_name(name)
+        raise "Unknown locale #{name}. Available: #{AVAILABLE}" unless AVAILABLE.include?(name)
+        klass = "Chronic::Locale::#{name.to_s.camelize}".constantize
+        klass.new
+      end
+
+      def default
+        by_name(:en)
+      end
+    end
+  end
+end

lib/chronic/locales/en.rb

@@ -0,0 +1,131 @@
+class Chronic::Locale::En < Chronic::Locale
+
+  LOCALE_HASH = {
+      repeater:  {
+          scan_for_season_names: {
+              /^springs?$/          => :spring,
+              /^summers?$/          => :summer,
+              /^(autumn)|(fall)s?$/ => :autumn,
+              /^winters?$/          => :winter
+          },
+          scan_for_month_names:  {
+              /^jan[:\.]?(uary)?$/           => :january,
+              /^feb[:\.]?(ruary)?$/          => :february,
+              /^mar[:\.]?(ch)?$/             => :march,
+              /^apr[:\.]?(il)?$/             => :april,
+              /^may$/                        => :may,
+              /^jun[:\.]?e?$/                => :june,
+              /^jul[:\.]?y?$/                => :july,
+              /^aug[:\.]?(ust)?$/            => :august,
+              /^sep[:\.]?(t[:\.]?|tember)?$/ => :september,
+              /^oct[:\.]?(ober)?$/           => :october,
+              /^nov[:\.]?(ember)?$/          => :november,
+              /^dec[:\.]?(ember)?$/          => :december,
+          },
+          scan_for_day_names:    {
+              /^m[ou]n(day)?$/             => :monday,
+              /^t(ue|eu|oo|u)s?(day)?$/    => :tuesday,
+              /^we(d|dnes|nds|nns)(day)?$/ => :wednesday,
+              /^th(u|ur|urs|ers)(day)?$/   => :thursday,
+              /^fr[iy](day)?$/             => :friday,
+              /^sat(t?[ue]rday)?$/         => :saturday,
+              /^su[nm](day)?$/             => :sunday
+          },
+          scan_for_day_portions: {
+              /^ams?$/           => :am,
+              /^pms?$/           => :pm,
+              /^mornings?$/      => :morning,
+              /^afternoons?$/    => :afternoon,
+              /^evenings?$/      => :evening,
+              /^(night|nite)s?$/ => :night
+          },
+          scan_for_times:        /^\d{1,2}(:?\d{1,2})?([\.:]?\d{1,2}([\.:]\d{1,6})?)?$/,
+          scan_for_units:        {
+              /^years?$/               => :year,
+              /^seasons?$/             => :season,
+              /^months?$/              => :month,
+              /^fortnights?$/          => :fortnight,
+              /^weeks?$/               => :week,
+              /^weekends?$/            => :weekend,
+              /^(week|business)days?$/ => :weekday,
+              /^days?$/                => :day,
+              /^hrs?$/                 => :hour,
+              /^hours?$/               => :hour,
+              /^mins?$/                => :minute,
+              /^minutes?$/             => :minute,
+              /^secs?$/                => :second,
+              /^seconds?$/             => :second
+          }
+      },
+      grabber:   {
+          scan_for_all: {
+              /last/ => :last,
+              /this/ => :this,
+              /next/ => :next
+          }
+      },
+      pointer:   {
+          scan_for_all: {
+              /\bpast\b/          => :past,
+              /\b(?:future|in)\b/ => :future,
+          }
+      },
+      separator: {
+          comma:          /^,$/,
+          dot:            /^\.$/,
+          colon:          /^:$/,
+          space:          /^ $/,
+          slash:          /^\/$/,
+          dash:           /^-$/,
+          scan_for_quote: {
+              /^'$/ => :single_quote,
+              /^"$/ => :double_quote
+          },
+          at:             /^(at|@)$/,
+          in:             /^in$/,
+          on:             /^on$/,
+          and:            /^and$/,
+          t:              /^t$/,
+          w:              /^w$/
+      }
+  }
+
+  def pre_normalize(text)
+    text = text.to_s.downcase
+    text.gsub!(/\b(\d{2})\.(\d{2})\.(\d{4})\b/, '\3 / \2 / \1')
+    text.gsub!(/\b([ap])\.m\.?/, '\1m')
+    text.gsub!(/(\s+|:\d{2}|:\d{2}\.\d{3})\-(\d{2}:?\d{2})\b/, '\1tzminus\2')
+    text.gsub!(/\./, ':')
+    text.gsub!(/([ap]):m:?/, '\1m')
+    text.gsub!(/['"]/, '')
+    text.gsub!(/,/, ' ')
+    text.gsub!(/^second /, '2nd ')
+    text.gsub!(/\bsecond (of|day|month|hour|minute|second)\b/, '2nd \1')
+    text = Numerizer.numerize(text)
+    text.gsub!(/([\/\-\,\@])/) { ' ' + $1 + ' ' }
+    text.gsub!(/(?:^|\s)0(\d+:\d+\s*pm?\b)/, ' \1')
+    text.gsub!(/\btoday\b/, 'this day')
+    text.gsub!(/\btomm?orr?ow\b/, 'next day')
+    text.gsub!(/\byesterday\b/, 'last day')
+    text.gsub!(/\bnoon\b/, '12:00pm')
+    text.gsub!(/\bmidnight\b/, '24:00')
+    text.gsub!(/\bnow\b/, 'this second')
+    text.gsub!('quarter', '15')
+    text.gsub!('half', '30')
+    text.gsub!(/(\d{1,2}) (to|till|prior to|before)\b/, '\1 minutes past')
+    text.gsub!(/(\d{1,2}) (after|past)\b/, '\1 minutes future')
+    text.gsub!(/\b(?:ago|before(?: now)?)\b/, 'past')
+    text.gsub!(/\bthis (?:last|past)\b/, 'last')
+    text.gsub!(/\b(?:in|during) the (morning)\b/, '\1')
+    text.gsub!(/\b(?:in the|during the|at) (afternoon|evening|night)\b/, '\1')
+    text.gsub!(/\btonight\b/, 'this night')
+    text.gsub!(/\b\d+:?\d*[ap]\b/, '\0m')
+    text.gsub!(/\b(\d{2})(\d{2})(am|pm)\b/, '\1:\2\3')
+    text.gsub!(/(\d)([ap]m|oclock)\b/, '\1 \2')
+    text.gsub!(/\b(hence|after|from)\b/, 'future')
+    text.gsub!(/^\s?an? /i, '1 ')
+    text.gsub!(/\b(\d{4}):(\d{2}):(\d{2})\b/, '\1 / \2 / \3') # DTOriginal
+    text.gsub!(/\b0(\d+):(\d{2}):(\d{2}) ([ap]m)\b/, '\1:\2:\3 \4')
+    text
+  end
+end

lib/chronic/locales/ru.rb

@@ -0,0 +1,97 @@
+class Chronic::Locale::Ru < Chronic::Locale
+
+  LOCALE_HASH = {
+      repeater:  {
+          scan_for_season_names: {},
+          scan_for_month_names:  {
+              /^янв[:\.]?(ар)?(ь|я)?$/   => :january,
+              /^фев[:\.]?(рал)?(ь|я)?$/  => :february,
+              /^мар[:\.]?(т)?(а)?$/      => :march,
+              /^апр[:\.]?(ел)?(ь|я)?$/   => :april,
+              /^ма(й|я)$/                => :may,
+              /^июн[:\.]?(ь|я)?$/        => :june,
+              /^июл[:\.]?(ь|я)?$/        => :july,
+              /^авг[:\.]?(уст)?(а)?$/    => :august,
+              /^сен[:\.]?(тябр)?(ь|я)?$/ => :september,
+              /^окт[:\.]?(ябр)?(ь|я)?$/  => :october,
+              /^ноя[:\.]?(бр)?(ь|я)?$/   => :november,
+              /^дек[:\.]?(абр)?(ь|я)?$/  => :december,
+          },
+          scan_for_day_names:    {
+              /^понедельник$/ => :monday,
+              /^вторник$/     => :tuesday,
+              /^среда$/       => :wednesday,
+              /^четверг$/     => :thursday,
+              /^пятница$/     => :friday,
+              /^суббота$/     => :saturday,
+              /^воскресение$/ => :sunday
+          },
+          scan_for_day_portions: {
+              /^утра$/   => :am,
+              /^вечера$/ => :pm
+          },
+          scan_for_times:        /^\d{1,2}(:?\d{1,2})?([\.:]?\d{1,2}([\.:]\d{1,6})?)?$/,
+          scan_for_units:        {
+              /^лет?$/          => :year,
+              /^год(а)?$/       => :year,
+              /^г\.$/           => :year,
+              /^сезон(ов)?$/    => :season,
+              /^месяц(ев)?$/    => :month,
+              /^недел(я|ь)$/    => :week,
+              /^выходн(ой|ых)$/ => :weekend,
+              /^дн(я|ей)$/      => :day,
+              /^час(ов)?(а)?$/  => :hour,
+              /^мин(ут)?(а)?$/  => :minute,
+              /^сек(унд)?(а)?$/ => :second,
+          }
+      },
+      grabber:   {
+          scan_for_all: {
+              /прошлый/   => :last,
+              /этот/      => :this,
+              /следующий/ => :next
+          }
+      },
+      pointer:   {
+          scan_for_all: {
+              /\bназад\b/     => :past,
+              /\b(?:через)\b/ => :future,
+          }
+      },
+      separator: {
+          comma:          /^,$/,
+          dot:            /^\.$/,
+          colon:          /^:$/,
+          space:          /^ $/,
+          slash:          /^\/$/,
+          dash:           /^-$/,
+          scan_for_quote: {
+              /^'$/ => :single_quote,
+              /^"$/ => :double_quote
+          },
+          at:             /^в$/,
+          in:             /^в$/,
+          on:             /^в$/,
+          and:            /^и$/,
+          t:              /^t$/,
+          w:              /^w$/
+      }
+  }
+
+
+  def pre_normalize(text)
+    text = text.to_s.mb_chars.downcase
+    text.gsub!(/\b(\d{2})\.(\d{2})\.(\d{4})\b/, '\3 / \2 / \1')
+    text.gsub!(/(\s+|:\d{2}|:\d{2}\.\d{3})\-(\d{2}:?\d{2})\b/, '\1tzminus\2')
+    text.gsub!(/\./, ':')
+    text.gsub!(/['"]/, '')
+    text.gsub!(/,/, ' ')
+    text = Numerizer.numerize(text)
+    text.gsub!(/([\/\-\,\@])/) { ' ' + $1 + ' ' }
+    text.gsub!(/(?:^|\s)0(\d+:\d+\s*pm?\b)/, ' \1')
+    text.gsub!(/\b(\d{4}):(\d{2}):(\d{2})\b/, '\1 / \2 / \3') # DTOriginal
+    text.gsub!(/\b0(\d+):(\d{2}):(\d{2}) ([ap]m)\b/, '\1:\2:\3 \4')
+    text.gsub!(/\bсейчас\b/, 'эта секунда')
+    text
+  end
+end

lib/chronic/parser.rb

@@ -91,43 +91,13 @@ def parse(text)
     #     #=> "136 days future this second"
     #
     # Returns a new String ready for Chronic to parse.
+
     def pre_normalize(text)
-      text = text.to_s.downcase
-      text.gsub!(/\b(\d{2})\.(\d{2})\.(\d{4})\b/, '\3 / \2 / \1')
-      text.gsub!(/\b([ap])\.m\.?/, '\1m')
-      text.gsub!(/(\s+|:\d{2}|:\d{2}\.\d{3})\-(\d{2}:?\d{2})\b/, '\1tzminus\2')
-      text.gsub!(/\./, ':')
-      text.gsub!(/([ap]):m:?/, '\1m')
-      text.gsub!(/['"]/, '')
-      text.gsub!(/,/, ' ')
-      text.gsub!(/^second /, '2nd ')
-      text.gsub!(/\bsecond (of|day|month|hour|minute|second)\b/, '2nd \1')
-      text = Numerizer.numerize(text)
-      text.gsub!(/([\/\-\,\@])/) { ' ' + $1 + ' ' }
-      text.gsub!(/(?:^|\s)0(\d+:\d+\s*pm?\b)/, ' \1')
-      text.gsub!(/\btoday\b/, 'this day')
-      text.gsub!(/\btomm?orr?ow\b/, 'next day')
-      text.gsub!(/\byesterday\b/, 'last day')
-      text.gsub!(/\bnoon\b/, '12:00pm')
-      text.gsub!(/\bmidnight\b/, '24:00')
-      text.gsub!(/\bnow\b/, 'this second')
-      text.gsub!('quarter', '15')
-      text.gsub!('half', '30')
-      text.gsub!(/(\d{1,2}) (to|till|prior to|before)\b/, '\1 minutes past')
-      text.gsub!(/(\d{1,2}) (after|past)\b/, '\1 minutes future')
-      text.gsub!(/\b(?:ago|before(?: now)?)\b/, 'past')
-      text.gsub!(/\bthis (?:last|past)\b/, 'last')
-      text.gsub!(/\b(?:in|during) the (morning)\b/, '\1')
-      text.gsub!(/\b(?:in the|during the|at) (afternoon|evening|night)\b/, '\1')
-      text.gsub!(/\btonight\b/, 'this night')
-      text.gsub!(/\b\d+:?\d*[ap]\b/,'\0m')
-      text.gsub!(/\b(\d{2})(\d{2})(am|pm)\b/, '\1:\2\3')
-      text.gsub!(/(\d)([ap]m|oclock)\b/, '\1 \2')
-      text.gsub!(/\b(hence|after|from)\b/, 'future')
-      text.gsub!(/^\s?an? /i, '1 ')
-      text.gsub!(/\b(\d{4}):(\d{2}):(\d{2})\b/, '\1 / \2 / \3') # DTOriginal
-      text.gsub!(/\b0(\d+):(\d{2}):(\d{2}) ([ap]m)\b/, '\1:\2:\3 \4')
-      text
+      locale.pre_normalize(text)
+    end
+
+    def locale
+      options[:locale] || Chronic::Locale.default
     end
 
     # Guess a specific time within the given span.

lib/chronic/tags/grabber.rb

@@ -10,24 +10,19 @@ class Grabber < Tag
     # Returns an Array of Token objects.
     def self.scan(tokens, options)
       tokens.each do |token|
-        token.tag scan_for_all(token)
+        token.tag scan_for_all(token, options)
       end
     end
 
     # token - The Token object to scan.
     #
     # Returns a new Grabber object.
-    def self.scan_for_all(token)
-      scan_for token, self,
-      {
-        /last/ => :last,
-        /this/ => :this,
-        /next/ => :next
-      }
+    def self.scan_for_all(token, options={})
+      scan_for token, self, options[:locale]['grabber.scan_for_all']
     end
 
     def to_s
       'grabber-' << @type.to_s
     end
   end
-end
+end