russian 0.2.7 → 1.0.0

data/lib/russian/strptime.rb

@@ -0,0 +1,166 @@
+# frozen_string_literal: true
+
+require "date"
+require "time"
+
+module Russian
+  # Localized `strptime` helpers for Russian month and weekday names.
+  #
+  # The module normalizes Russian textual date/time tokens to the English
+  # tokens expected by Ruby's native parsers, then delegates to
+  # `Date.strptime`, `Time.strptime`, or `DateTime.strptime`.
+  #
+  #
+  # Локализованные хелперы `strptime` для русских названий месяцев и дней
+  # недели.
+  #
+  # Модуль нормализует русские текстовые токены даты и времени к английским
+  # токенам, которые ожидают стандартные parser'ы Ruby, а затем делегирует
+  # работу в `Date.strptime`, `Time.strptime` или `DateTime.strptime`.
+  module Strptime
+    module_function
+
+    # Parses a localized Russian date string with `Date.strptime`.
+    #
+    #
+    # Разбирает локализованную русскую строку даты через `Date.strptime`.
+    #
+    # @param string [String] Localized date string.
+    #   Локализованная строка даты.
+    # @param format [String] Optional `strptime` format string.
+    #   Строка формата `strptime`.
+    # @return [Date] Parsed date.
+    #   Разобранная дата.
+    def date_strptime(string, format = "%F")
+      Date.strptime(normalize_input(string, format), format, Date::ITALY)
+    end
+
+    # Parses a localized Russian date/time string with `Time.strptime`.
+    #
+    #
+    # Разбирает локализованную русскую строку даты и времени через
+    # `Time.strptime`.
+    #
+    # @param string [String] Localized date/time string.
+    #   Локализованная строка даты и времени.
+    # @param format [String] `strptime` format string.
+    #   Строка формата `strptime`.
+    # @param now [Time] Optional base time passed to `Time.strptime`.
+    #   Базовое значение времени, передаваемое в `Time.strptime`.
+    # @return [Time] Parsed time.
+    #   Разобранное время.
+    def time_strptime(string, format, now = Time.now)
+      Time.strptime(normalize_input(string, format), format, now)
+    end
+
+    # Parses a localized Russian date/time string with `DateTime.strptime`.
+    #
+    #
+    # Разбирает локализованную русскую строку даты и времени через
+    # `DateTime.strptime`.
+    #
+    # @param string [String] Localized date/time string.
+    #   Локализованная строка даты и времени.
+    # @param format [String] Optional `strptime` format string.
+    #   Строка формата `strptime`.
+    # @return [DateTime] Parsed datetime.
+    #   Разобранный `DateTime`.
+    def datetime_strptime(string, format = "%FT%T%z")
+      DateTime.strptime(normalize_input(string, format), format, Date::ITALY)
+    end
+
+    # @private
+    def normalize_input(string, format)
+      return string unless string.is_a?(String) && format.is_a?(String)
+
+      replacements = localized_replacements(format)
+      return string if replacements.empty?
+
+      token_regexp = Regexp.new(
+        "(?<!\\p{L})(?:#{replacements.keys.sort_by(&:length).reverse.map do |token|
+          Regexp.escape(token)
+        end.join("|")})(?!\\p{L})",
+        Regexp::IGNORECASE
+      )
+
+      string.gsub(token_regexp) { |token| replacements.fetch(token.downcase) }
+    end
+
+    # @private
+    def localized_replacements(format)
+      directives = directives_in(format)
+      replacements = {}
+
+      replacements.merge!(localized_tokens(month_names_key(format), Date::MONTHNAMES)) if directives.include?("B")
+
+      if directives.include?("b")
+        replacements.merge!(localized_tokens(abbr_month_names_key(format), Date::ABBR_MONTHNAMES))
+      end
+
+      replacements.merge!(localized_tokens(day_names_key(format), Date::DAYNAMES)) if directives.include?("A")
+
+      replacements.merge!(localized_tokens(abbr_day_names_key(format), Date::ABBR_DAYNAMES)) if directives.include?("a")
+
+      replacements
+    end
+
+    # @private
+    def localized_tokens(key, english_names)
+      localized_names = I18n.t(key, locale: Russian::LOCALE).compact
+      english_names = english_names.compact
+
+      localized_names.zip(english_names).each_with_object({}) do |(localized_name, english_name), replacements|
+        replacements[localized_name.downcase] = english_name
+      end
+    end
+
+    # @private
+    def directives_in(format)
+      directives = []
+      index = 0
+
+      while index < format.length
+        if format[index] != "%"
+          index += 1
+          next
+        end
+
+        if format[index + 1] == "%"
+          index += 2
+          next
+        end
+
+        index += 1
+        index += 1 while index < format.length && Russian::STRPTIME_DIRECTIVE_MODIFIERS.include?(format[index])
+        index += 1 while index < format.length && format[index].match?(/\d/)
+
+        index += 1 if index < format.length && %w[E O].include?(format[index])
+
+        directives << format[index] if index < format.length
+        index += 1
+      end
+
+      directives
+    end
+
+    # @private
+    def month_names_key(format)
+      Russian::LOCALIZE_MONTH_NAMES_MATCH.match?(format) ? :"date.common_month_names" : :"date.standalone_month_names"
+    end
+
+    # @private
+    def abbr_month_names_key(format)
+      Russian::LOCALIZE_ABBR_MONTH_NAMES_MATCH.match?(format) ? :"date.common_abbr_month_names" : :"date.standalone_abbr_month_names"
+    end
+
+    # @private
+    def day_names_key(format)
+      Russian::LOCALIZE_STANDALONE_DAY_NAMES_MATCH.match?(format) ? :"date.standalone_day_names" : :"date.common_day_names"
+    end
+
+    # @private
+    def abbr_day_names_key(format)
+      Russian::LOCALIZE_STANDALONE_ABBR_DAY_NAMES_MATCH.match?(format) ? :"date.common_abbr_day_names" : :"date.standalone_abbr_day_names"
+    end
+  end
+end

data/lib/russian/transliteration.rb

@@ -1,72 +1,106 @@
-# -*- encoding: utf-8 -*- 
+# frozen_string_literal: true
 
 module Russian
-  # Russian transliteration 
+  # Russian transliteration tables and helpers.
   #
-  # Транслитерация для букв русского алфавита
+  # Transliteration is heavily based on the
+  # [rutils](https://github.com/julik/rutils) gem by
+  # Julian "julik" Tarkhanov and contributors, then cleaned up and
+  # adapted for this gem.
+  #
+  #
+  # Таблицы и хелперы для русской транслитерации.
+  #
+  # Транслитерация во многом основана на gem
+  # [rutils](https://github.com/julik/rutils) Юлика Тарханова и
+  # соавторов, а затем упрощена и адаптирована для этого gem'а.
+  #
+  # @example
+  #   Russian::Transliteration.transliterate("Юлия")
+  #   # => "Yuliya"
+  #
+  #   Russian::Transliteration.transliterate("Н.П. Шерстяков")
+  #   # => "N.P. Sherstyakov"
   module Transliteration
-    extend self
-
-    # Transliteration heavily based on rutils gem by Julian "julik" Tarkhanov and Co.
-    # <http://rutils.rubyforge.org/>
-    # Cleaned up and optimized.
+    module_function
 
+    # @private
     LOWER_SINGLE = {
-      "і"=>"i","ґ"=>"g","ё"=>"yo","№"=>"#","є"=>"e",
-      "ї"=>"yi","а"=>"a","б"=>"b",
-      "в"=>"v","г"=>"g","д"=>"d","е"=>"e","ж"=>"zh",
-      "з"=>"z","и"=>"i","й"=>"y","к"=>"k","л"=>"l",
-      "м"=>"m","н"=>"n","о"=>"o","п"=>"p","р"=>"r",
-      "с"=>"s","т"=>"t","у"=>"u","ф"=>"f","х"=>"h",
-      "ц"=>"ts","ч"=>"ch","ш"=>"sh","щ"=>"sch","ъ"=>"'",
-      "ы"=>"y","ь"=>"","э"=>"e","ю"=>"yu","я"=>"ya",
-    }
+      "і" => "i", "ґ" => "g", "ё" => "yo", "№" => "#", "є" => "e",
+      "ї" => "yi", "а" => "a", "б" => "b",
+      "в" => "v", "г" => "g", "д" => "d", "е" => "e", "ж" => "zh",
+      "з" => "z", "и" => "i", "й" => "y", "к" => "k", "л" => "l",
+      "м" => "m", "н" => "n", "о" => "o", "п" => "p", "р" => "r",
+      "с" => "s", "т" => "t", "у" => "u", "ф" => "f", "х" => "h",
+      "ц" => "ts", "ч" => "ch", "ш" => "sh", "щ" => "sch", "ъ" => "'",
+      "ы" => "y", "ь" => "", "э" => "e", "ю" => "yu", "я" => "ya"
+    }.freeze
+    # @private
     LOWER_MULTI = {
-      "ье"=>"ie",
-      "ьё"=>"ie",
-    }
+      "ье" => "ie",
+      "ьё" => "ie"
+    }.freeze
 
+    # @private
     UPPER_SINGLE = {
-      "Ґ"=>"G","Ё"=>"YO","Є"=>"E","Ї"=>"YI","І"=>"I",
-      "А"=>"A","Б"=>"B","В"=>"V","Г"=>"G",
-      "Д"=>"D","Е"=>"E","Ж"=>"ZH","З"=>"Z","И"=>"I",
-      "Й"=>"Y","К"=>"K","Л"=>"L","М"=>"M","Н"=>"N",
-      "О"=>"O","П"=>"P","Р"=>"R","С"=>"S","Т"=>"T",
-      "У"=>"U","Ф"=>"F","Х"=>"H","Ц"=>"TS","Ч"=>"CH",
-      "Ш"=>"SH","Щ"=>"SCH","Ъ"=>"'","Ы"=>"Y","Ь"=>"",
-      "Э"=>"E","Ю"=>"YU","Я"=>"YA",
-    }
+      "Ґ" => "G", "Ё" => "YO", "Є" => "E", "Ї" => "YI", "І" => "I",
+      "А" => "A", "Б" => "B", "В" => "V", "Г" => "G",
+      "Д" => "D", "Е" => "E", "Ж" => "ZH", "З" => "Z", "И" => "I",
+      "Й" => "Y", "К" => "K", "Л" => "L", "М" => "M", "Н" => "N",
+      "О" => "O", "П" => "P", "Р" => "R", "С" => "S", "Т" => "T",
+      "У" => "U", "Ф" => "F", "Х" => "H", "Ц" => "TS", "Ч" => "CH",
+      "Ш" => "SH", "Щ" => "SCH", "Ъ" => "'", "Ы" => "Y", "Ь" => "",
+      "Э" => "E", "Ю" => "YU", "Я" => "YA"
+    }.freeze
+    # @private
     UPPER_MULTI = {
-      "ЬЕ"=>"IE",
-      "ЬЁ"=>"IE",
-    }
+      "ЬЕ" => "IE",
+      "ЬЁ" => "IE"
+    }.freeze
 
-    LOWER = (LOWER_SINGLE.merge(LOWER_MULTI)).freeze
-    UPPER = (UPPER_SINGLE.merge(UPPER_MULTI)).freeze
-    MULTI_KEYS = (LOWER_MULTI.merge(UPPER_MULTI)).keys.sort_by {|s| s.length}.reverse.freeze
+    # @private
+    LOWER = LOWER_SINGLE.merge(LOWER_MULTI).freeze
+    # @private
+    UPPER = UPPER_SINGLE.merge(UPPER_MULTI).freeze
+    # @private
+    TITLE = UPPER.transform_values(&:capitalize).freeze
+    # @private
+    MULTI_KEYS = LOWER_MULTI.merge(UPPER_MULTI).keys.sort_by(&:length).reverse.freeze
+    # @private
+    TOKEN_RE = /#{Regexp.union(MULTI_KEYS).source}|./m
 
-    # Transliterate a string with russian characters
+    # Transliterates a string containing Cyrillic characters.
+    #
+    # The method preserves non-Cyrillic characters and follows the historical
+    # casing rules of the gem.
+    #
+    #
+    # Транслитерирует строку, содержащую кириллические символы.
+    #
+    # Метод сохраняет некириллические символы и следует историческим правилам
+    # gem'а для регистра.
+    #
+    # @param str [String] String to transliterate.
+    #   Строка для транслитерации.
+    # @return [String] Transliteration result.
+    #   Результат транслитерации.
     #
-    # Возвращает строку, в которой все буквы русского алфавита заменены на похожую по звучанию латиницу
+    # @example
+    #   Russian::Transliteration.transliterate("Привет, мир!")
+    #   # => "Privet, mir!"
     def transliterate(str)
-      chars = str.scan(%r{#{MULTI_KEYS.join '|'}|\w|.})
+      tokens = str.scan(TOKEN_RE)
 
-      result = ""
+      tokens.each_with_index.map do |token, index|
+        lower = LOWER[token]
+        next lower if lower
 
-      chars.each_with_index do |char, index|
-        if UPPER.has_key?(char) && LOWER.has_key?(chars[index+1])
-          # combined case
-          result << UPPER[char].downcase.capitalize
-        elsif UPPER.has_key?(char)
-          result << UPPER[char]
-        elsif LOWER.has_key?(char)
-          result << LOWER[char]
-        else
-          result << char
-        end
-      end
+        upper = UPPER[token]
+        next TITLE[token] if upper && LOWER[tokens[index + 1]]
+        next upper if upper
 
-      result
+        token
+      end.join
     end
   end
-end
+end

data/lib/russian/version.rb

@@ -0,0 +1,31 @@
+# frozen_string_literal: true
+
+module Russian
+  # Gem version constants.
+  #
+  # The version is split into major, minor, and tiny components, plus a string
+  # representation.
+  #
+  #
+  # Константы версии gem'а.
+  #
+  # Версия разбита на major, minor и tiny-компоненты, а также на строковое
+  # представление.
+  #
+  # @example
+  #   Russian::VERSION::STRING
+  #   # => "1.0.0"
+  module VERSION
+    MAJOR = 1
+    MINOR = 0
+    TINY = 0
+
+    # Full version string.
+    #
+    # Полная строка версии.
+    #
+    # @return [String] Full version string.
+    #   Полная строка версии.
+    STRING = [MAJOR, MINOR, TINY].join(".")
+  end
+end