truty 0.1.1 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1f40bb7fec5fbcc791d421f3815710ffea30736b
-  data.tar.gz: a64fddfb5f0fec224737008005e4f3657b09c22a
+  metadata.gz: 4feee35354a4825efaf7b001e6e75d5da250d16d
+  data.tar.gz: b026eb59f352ba1eb611a19eac14d87b4b2d426f
 SHA512:
-  metadata.gz: 14476727de9625d8872b21ab3134d441b662da6a4c9010d7756ac17ade34d500125b840a9273fda4c2971067c1f6990e115d8af1222760c36a7e43f73a2ea5c8
-  data.tar.gz: bd59bad1b93812342cb70fba9435b2164cf10acbdaff7b6387c89a1a71606e4d67255770472d001e20bbdecc21e2767628867664dbf7f0847a07e5bef7c0c44a
+  metadata.gz: 362609e41ac202bcfb3f46be87e9b6caeb8f6c82b424086feca76222b54bfb9aa60690fd5c0a27909feb58a7f26fb3bd468a72608af6b31125ef4500f0200c49
+  data.tar.gz: 100ae5a99c6a5552a8c99aec4444e5dfdd820fba072066b0105675db41003fee0ced281181f82fe0459e71926384a45715f10769996c2c611c76ba1fe484faa1

data/bin/truty

@@ -3,7 +3,12 @@
 require "truty"
 
 def main
-  puts Truty.fix_czech_text(ARGF.read)
+  language = :general
+  if ARGV[0] == "-l" || ARGV[0] == "--language" then
+    language = ARGV[1]
+    ARGV.shift(2)
+  end
+  puts Truty.send :fix, ARGF.read, language
 end
 
 main

data/lib/truty.rb

@@ -3,6 +3,8 @@
 require 'uri'
 require 'text/hyphen'
 require 'truty/general'
+require 'truty/english'
+require 'truty/french'
 require 'truty/czech'
 
 # A Ruby library which is a simple string converter, which aims to fix all the typography imperfections of the plain text.
@@ -10,7 +12,7 @@ require 'truty/czech'
 module Truty
 
   extend General
-  extend Czech
+  extend English, French, Czech
 
 end
 

data/lib/truty/czech.rb

@@ -5,52 +5,33 @@ module Truty
   # @author Matěj Kašpar Jirásek
   module Czech
 
-    # Improves the typography of the large plain text with paragraphs. Adds non-breaking spaces, hyphenation, fixes dashes, etc. Fixes some typography fixes specific for the Czech languages, like one character prepositions, abbreviations and spaces between numbers.
-    #
-    # @param input [String] The text which will be converted.
-    # @return [String] Text with improved typography.
-    def fix_czech_text(input)
-      input.split("\n").collect { |p| fix_czech_paragraph(p) }.join("\n")
-    end
-
-    # Improves the Czech typography of single paragraph. If you supply more paragraphs you might lose some improvements like widows. For improving longer text see {#fix_czech_text}.
+    # Improves the Czech typography of single paragraph. If you supply more paragraphs you might lose some improvements like widows. For improving longer text see {General#fix}.
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with improved typography.
-    def fix_czech_paragraph(input)
-      output = input
-      output = ellipsis(output)
-      output = fix_multicharacters(output)
-      output = fix_punctuation_whitespace(output)
-      output = fix_brackets_whitespace(output)
-      output = add_soft_hyphens(output, "cs")
-      output = emdash_spaces(output)
-      output = endash_spaces(output)
-      output = fix_quotes(output, "\"", "„", "“")
-      output = fix_quotes(output, "'", "‚", "‘")
-      output = fix_multiplication_sign(output)
-      output = fix_space_between_numbers(output)
-      output = fix_units(output)
-      output = fix_trailing_spaces(output)
-      output = fix_widows(output)
-      output = fix_long_czech_numbers(output)
-      output = fix_czech_one_character_words(output)
-      output = fix_czech_abbreviations(output)
+    def czech(input)
+      input = soft_hyphens(input, "cs")
+      input = general(input)
+      input = czech_double_quotes(input)
+      input = czech_single_quotes(input)
+      input = czech_long_numbers(input)
+      input = czech_prepositions(input)
+      input = czech_abbreviations(input)
     end
 
     # Adds non-breaking space after Czech one character prepostion.
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with non-breaking spaces after prepositions.
-    def fix_czech_one_character_words(input)
-      input.gsub(/(\s+|^|\A)(([aikosuvz]\s+)+)/i) { |prep| $1 + $2.gsub(/\s+/, " ") }
+    def czech_prepositions(input)
+      input.gsub(/(\s+|^|\A)(([aikosuvz]\s+)+)/i) { $1 + $2.gsub(/\s+/, " ") }
     end
 
     # Divides long numbers into parts of three digits using thin space.
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with spaces inside of long numbers.
-    def fix_long_czech_numbers(input)
+    def czech_long_numbers(input)
       input.gsub(/\d+/) { |n| n.reverse.scan(/(.{1,3})/).join(' ').reverse }
     end
 
@@ -58,10 +39,26 @@ module Truty
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with non-breaking spaces in and after abbreviations.
-    def fix_czech_abbreviations(input)
+    def czech_abbreviations(input)
       abbreviations = /(a. s.|abl. |absol. |adj. |adm. |adv. |aj.|ak. |ak. sl.|akt. |alch. |amer. |anat. |angl. |anglosas. |ap.|apod.|arab. |arch. |archit. |arg. |arm. gen. |astr. |astrol. |atd.|atp.|att. |b. k.|Bc. |BcA. |belg. |bibl. |biol. |bl. |boh. |bot. |br. |brig. gen. |brit. |bulh. |bás. |býv. |chcsl. |chem. |chil. |CSc. |csl. |círk. |dat. |dep. |des. |dial. |DiS.|dl. |doc. |dol. |dop. |dopr. |dosl. |dán. |dór. |děj. |dět. |ekon. |epic. |etnonym. |eufem. |ev. |event. |f. |fam. |fem. |fil. |film. |fin. |form. |fot. |fr. |fut. |fyz. |gen. |genmjr. |genplk. |genpor. |geogr. |geol. |geom. |germ. |gram. |hebr. |herald. |hist. |hl. |hod. |hor. |horn. |hovor. |hud. |hut. |ie. |imp. |impf. |ind. |indoevr. |inf. |Ing. |instr. |interj. |iron. |it. |ión. |j. č.|jap. |JUDr. |k. s.|kanad. |katalán. |klas. |kniž. |komp. |konj. |konkr. |kpt. |kr. |kuch. |kř. |lat. |les. |lid. |lit. |liturg. |log. |lok. |lék. |m. |mat. |meteor. |metr. |MgA. |Mgr. |mil. |mj. |mjr. |ml. |mld. |mn. č.|mod. |ms. |MUDr. |MVDr. |mysl. |n. |n. l.|např. |neklas. |nesklon. |než. |niz. |nom. |nor. |npor. |nprap. |nrtm. |nstržm. |náb. |nám. |námoř. |něm. |o. p. s.|o. s.|ob. |obch. |obyč. |odd. |odp. |ojed. |opt. |p. |p. n. l.|p. o.|P. S. |P. T. |part. |pas. |pejor. |pers. |pf. |PharmDr. |PhDr. |pl. |plk. |plpf. |po Kr.|pol. |pomn. |popř. |por. |pplk. |ppor. |pprap. |prap. |prep. |prof. |práv. |př. Kr.|př. n. l.|před n. l.|předl. |přivl. |r. |rak. |rcsl. |refl. |reg. |resp. |rkp. |RNDr. |roč. |RSDr. |rtm. |rtn. |rum. |rus. |s. |s. p.|s. r. o.|samohl. |Sb. |sg. |sl. |slang. |slov. |souhl. |spec. |spol. s r. o.|sport. |srov. |st. |stfr. |stol. |str. |stržm. |stsl. |střv. |subj. |subst. |superl. |sv. |svob. |sz. |t. r.|tech. |telev. |teol. |ThDr. |tis. |tj. |trans. |tur. |typogr. |tzn. |tzv. |táz. |v z.|v. o. s.|v. r.|v. v. i.|var. |vedl. |verb. |vl. jm. |voj. |vok. |vulg. |vztaž. |výtv. |vč. |vůb. |z. s.|zahr. |zast. |zejm. |zeměd. |zkr. |zn. |zvl. |zájm. |zř. |č. |č. j.|č. p. |čas. |čes. |čet. |čj. |čp. |čín. |čís. |ř. |řec. |říj. |škpt. |špan. |šprap. |št. prap. |švýc. )/i
       input.gsub(abbreviations) { |abbr| abbr.gsub(/ /, ' ') }
     end
 
+    # Converts single quotes to the typograhic ones.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with correct single quotes.
+    def czech_single_quotes(input)
+      quotes(input, "'", "‚", "‘")
+    end
+
+    # Converts double quotes to the typograhic ones.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with correct double quotes.
+    def czech_double_quotes(input)
+      quotes(input, "\"", "„", "”")
+    end
+
   end
 end

data/lib/truty/english.rb

@@ -0,0 +1,37 @@
+
+module Truty
+
+  # Module with specific English typography fixes.
+  # @author Matěj Kašpar Jirásek
+  module English
+
+    # Improves the English typography of single paragraph. If you supply more paragraphs you might lose some improvements like widows. For improving longer text see {General#fix}.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @param country [String] The country ("uk" or "us").
+    # @return [String] Paragraph with improved typography.
+    def english(input, country = "us")
+      input = soft_hyphens(input, "en_" + country)
+      input = general(input)
+      input = english_double_quotes(input)
+      input = english_single_quotes(input)
+    end
+
+    # Converts single quotes to the typograhic ones.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with correct single quotes.
+    def english_single_quotes(input)
+      quotes(input, "'", "‘", "’")
+    end
+
+    # Converts double quotes to the typograhic ones.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with correct double quotes.
+    def english_double_quotes(input)
+      quotes(input)
+    end
+
+  end
+end

data/lib/truty/french.rb

@@ -0,0 +1,36 @@
+
+module Truty
+
+  # Module with specific French typography fixes.
+  # @author Matěj Kašpar Jirásek
+  module French
+
+    # Improves the French typography of single paragraph. If you supply more paragraphs you might lose some improvements like widows. For improving longer text see {General#fix}.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with improved typography.
+    def french(input)
+      input = soft_hyphens(input, "fr")
+      input = general(input)
+      input = french_double_quotes(input)
+      input = french_single_quotes(input)
+    end
+
+    # Converts single quotes to the typograhic ones.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with correct single quotes.
+    def french_single_quotes(input)
+      quotes(input, "'", "‹ ", " ›")
+    end
+
+    # Converts double quotes to the typograhic ones.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with correct double quotes.
+    def french_double_quotes(input)
+      quotes(input, "\"", "« ", " »")
+    end
+
+  end
+end

data/lib/truty/general.rb

@@ -8,33 +8,31 @@ module Truty
     # Improves the typography of the large plain text with paragraphs. Adds non-breaking spaces, hyphenation, fixes dashes, etc.
     #
     # @param input [String] The text which will be converted.
-    # @param lang [String] Sets the language of hyphenation. (See {#add_soft_hyphens}.)
+    # @param lang [Symbol] Sets the language (english name like "czech", "german", etc.)
     # @return [String] Text with improved typography.
-    def fix(input, lang = "en_us")
-      input.split("\n").collect { |p| fix_paragraph(p, lang) }.join("\n")
+    def fix(input, lang = :general)
+      if not Truty.respond_to? lang then
+        lang = :general
+      end
+      input.split("\n").collect { |p| Truty.send lang, p }.join("\n")
     end
 
-    # Improves the typography of single paragraph. If you supply more paragraphs you might lose some improvements like widows. For improving longer text see {#fix}.
+    # Improves basic non-language specific issues in typography.
     #
     # @param input [String] The paragraph which will be converted.
-    # @param lang [String] Sets the language of hyphenation. (See {#add_soft_hyphens}.)
     # @return [String] Paragraph with improved typography.
-    def fix_paragraph(input, lang = "en_us")
-      output = input
-      output = ellipsis(output)
-      output = fix_multicharacters(output)
-      output = fix_punctuation_whitespace(output)
-      output = fix_brackets_whitespace(output)
-      output = add_soft_hyphens(output, lang)
-      output = emdash_spaces(output)
-      output = endash_spaces(output)
-      output = fix_double_quotes(output)
-      output = fix_single_quotes(output)
-      output = fix_multiplication_sign(output)
-      output = fix_space_between_numbers(output)
-      output = fix_units(output)
-      output = fix_trailing_spaces(output)
-      output = fix_widows(output)
+    def general(input)
+      input = ellipsis(input)
+      input = multicharacters(input)
+      input = punctuation_whitespace(input)
+      input = brackets_whitespace(input)
+      input = emdash(input)
+      input = endash(input)
+      input = multiplication_sign(input)
+      input = space_between_numbers(input)
+      input = units(input)
+      input = trailing_spaces(input)
+      input = widows(input)
     end
 
     # Converts three or more periods (dots, points) into ellipsis.
@@ -49,7 +47,7 @@ module Truty
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with corrected emdashes.
-    def emdash_spaces(input)
+    def emdash(input)
       input.gsub(/\s+(—|-{2,3})\s+/, " — ")
     end
 
@@ -57,7 +55,7 @@ module Truty
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with corrected endashes.
-    def endash_spaces(input)
+    def endash(input)
       input.gsub(/\s+(–|-)\s+/, " – ")
     end
 
@@ -69,7 +67,7 @@ module Truty
     # @param right [Integer] Number of characters on the beginning of the words which cannnot be hyphenated.
     # @param char [Integer] The character which will be added to hyphenation places.
     # @return [String] Paragraph with added hyphenation characters.
-    def add_soft_hyphens(input, lang = "en_us", left = 2, right = 2, char = "­")
+    def soft_hyphens(input, lang = "en_us", left = 2, right = 2, char = "­")
       l = Text::Hyphen.new(:language => lang, :left => left, :right => right)
       words = input.split(/[ ]+/m)
       result = []
@@ -89,32 +87,16 @@ module Truty
     # @param start_quotes [String] The character used for starting quotes.
     # @param end_quotes [String] The character used for ending quotes.
     # @return [String] Paragraph with correct double quotes.
-    def fix_quotes(input, type = '"', start_quotes = "“", end_quotes = "”")
+    def quotes(input, type = '"', start_quotes = "“", end_quotes = "”")
       regexp = Regexp.new(type + '[^' + type + ']*' + type)
       input.gsub(regexp) { |s| start_quotes + s[1..-2].strip + end_quotes }
     end
 
-    # Converts single quotes to the typograhic ones.
-    #
-    # @param input [String] The paragraph which will be converted.
-    # @return [String] Paragraph with correct single quotes.
-    def fix_single_quotes(input)
-      fix_quotes(input, "'", "‘", "’")
-    end
-
-    # Converts double quotes to the typograhic ones.
-    #
-    # @param input [String] The paragraph which will be converted.
-    # @return [String] Paragraph with correct double quotes.
-    def fix_double_quotes(input)
-      fix_quotes(input, '"', "“", "”")
-    end
-
     # Adds multiplication sign between numbers instead of X.
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with correct multiplication signs.
-    def fix_multiplication_sign(input)
+    def multiplication_sign(input)
       output = input.gsub(/(\d+)\s{0,1}[Xx]\s{0,1}(\d+)/, '\1 × \2')
       output = output.gsub(/(\d+)[Xx]/, '\1×')
     end
@@ -123,7 +105,7 @@ module Truty
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with correct spaces between numbers.
-    def fix_space_between_numbers(input)
+    def space_between_numbers(input)
       input.gsub(/(\d)\s+(\d)/, '\1 \2')
     end
 
@@ -131,7 +113,7 @@ module Truty
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with correct spaces around brackets.
-    def fix_brackets_whitespace(input)
+    def brackets_whitespace(input)
       output = input.gsub(/([\(\[\{])\s*/, '\1')
       output = output.gsub(/\s*([\]\)\}])/, '\1')
       output = output.gsub(/\s+([\(\[\{])\s*/, ' \1')
@@ -142,7 +124,7 @@ module Truty
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with converted characters.
-    def fix_multicharacters(input)
+    def multicharacters(input)
       output = input.gsub(/\([Cc]\)/, "©")
       output = output.gsub(/\([Pp]\)/, "℗")
       output = output.gsub(/\([Rr]\)/, "®")
@@ -159,7 +141,7 @@ module Truty
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with correct spaces around punctuation.
-    def fix_punctuation_whitespace(input)
+    def punctuation_whitespace(input)
       input.gsub(/\s*([\!\?\.,;:…]+)\s*/, '\1 ')
     end
 
@@ -167,7 +149,7 @@ module Truty
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with correct spaces between number and unit.
-    def fix_units(input)
+    def units(input)
       output = input.gsub(/(\d+)\s+(%|‰|‱|℃|℉|°|€|Kč|(Y|Z|E|P|T|G|M|k|h|da|d|m|µ|n|p|f|a|z|y)?(m(²|³)?|g|s|h|A|K|cd|mol|Ω|℃|℉))/, '\1 \2')
       output.gsub(/(\*|§|#|†)\s+(\d+)/, '\1 \2')
     end
@@ -176,7 +158,7 @@ module Truty
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph with removed widows.
-    def fix_widows(input)
+    def widows(input)
       input.gsub(/(\s)(\S+(\$|\z))/, ' \2')
     end
 
@@ -184,7 +166,7 @@ module Truty
     #
     # @param input [String] The paragraph which will be converted.
     # @return [String] Paragraph without trailing spaces.
-    def fix_trailing_spaces(input)
+    def trailing_spaces(input)
       input.gsub(/\s*($|\z)/, '')
     end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: truty
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.2.0
 platform: ruby
 authors:
 - Matěj Kašpar Jirásek
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-01-04 00:00:00.000000000 Z
+date: 2015-01-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: text-hyphen
@@ -66,9 +66,10 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.8'
-description: A string converter which aims to correct the typography.
+description: A string converter aiming to correct the typography of plain text.
 email: matej.jirasek@me.com
-executables: []
+executables:
+- truty
 extensions: []
 extra_rdoc_files: []
 files:
@@ -77,6 +78,8 @@ files:
 - bin/truty
 - lib/truty.rb
 - lib/truty/czech.rb
+- lib/truty/english.rb
+- lib/truty/french.rb
 - lib/truty/general.rb
 homepage: https://github.com/mkj-is/Truty
 licenses: