truty 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: e33c09b42c8ceb567b09cf0a0577bb01b20dba5c
+  data.tar.gz: 08f1808d7826aeef5738b05af2081799d0606cd5
+SHA512:
+  metadata.gz: cb6bd314915bfa2ca1d9d467b39fdc647f0528820d255c73808a1389eddd5687ae3d72deb423bd2c1b2ecc06451d8e483b2067f53fa4db1ec7be3eaf559657d9
+  data.tar.gz: f10562c3e8a6215d74cfdf0308a02cfd2b281b724c4eb11116daacf7a0f84a80a7244df7c861b82f58ebadc854267a4791e4f03ed86f23dcbe3e6f4048fad8c3

data/LICENSE

@@ -0,0 +1,22 @@
+The MIT License (MIT)
+
+Copyright (c) 2014 Matěj Kašpar Jirásek
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+

data/README.md

@@ -0,0 +1,4 @@
+
+# Truty
+
+This is a ruby gem in development which is a simple string converter, which aims to fix all the typography imperfections of the plain text.

data/bin/truty

@@ -0,0 +1,9 @@
+#!/usr/bin/env ruby -rubygems
+
+require "truty"
+
+def main
+  puts Truty.fix_czech_text(ARGF.read)
+end
+
+main

data/lib/truty.rb

@@ -0,0 +1,16 @@
+#!/usr/bin/ruby
+
+require 'uri'
+require 'text/hyphen'
+require 'truty/general'
+require 'truty/czech'
+
+# A Ruby library which is a simple string converter, which aims to fix all the typography imperfections of the plain text.
+# @author Matěj Kašpar Jirásek
+module Truty
+
+  extend General
+  extend Czech
+
+end
+

data/lib/truty/czech.rb

@@ -0,0 +1,67 @@
+
+module Truty
+
+  # Module with specific Czech typography fixes.
+  # @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}.
+    #
+    # @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_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)
+      output = fix_long_czech_numbers(output)
+      output = fix_czech_one_character_words(output)
+      output = fix_czech_abbreviations(output)
+    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+/, " ") }
+    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)
+      input.gsub(/\d+/) { |n| n.reverse.scan(/(.{1,3})/).join(' ').reverse }
+    end
+
+    # Adds non-breaking spaces in and after Czech abbreviations.
+    #
+    # @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)
+      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
+
+  end
+end

data/lib/truty/general.rb

@@ -0,0 +1,184 @@
+
+module Truty
+
+  # Module with general typography fixes for all the languages. The fixes in here should not be language specific.
+  # @author Matěj Kašpar Jirásek
+  module General
+
+    # 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}.)
+    # @return [String] Text with improved typography.
+    def fix(input, lang = "en_us")
+      input.split("\n").collect { |p| fix_paragraph(p, lang) }.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}.
+    #
+    # @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)
+    end
+
+    # Converts three or more periods (dots, points) into ellipsis.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with ellipses.
+    def ellipsis(input)
+      input.gsub(/\.{3,}/, "…")
+    end
+
+    # Adds thin spaces to emdash from both sides. Also converts two or three hyphens to emdash.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with corrected emdashes.
+    def emdash_spaces(input)
+      input.gsub(/\s+(—|-{2,3})\s+/, " — ")
+    end
+
+    # Adds non-breaking space before endash.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with corrected endashes.
+    def endash_spaces(input)
+      input.gsub(/\s+(–|-)\s+/, " – ")
+    end
+
+    # Adds soft hyphens to the input.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @param lang [String] Sets the language of hyphenation. One of the languages a {http://www.rubydoc.info/gems/text-hyphen/ text-hyphen gem} can use.
+    # @param left [Integer] Number of characters on the beginning of the words which cannnot be hyphenated.
+    # @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 = "­")
+      l = Text::Hyphen.new(:language => lang, :left => left, :right => right)
+      words = input.split(/[ ]+/m)
+      result = []
+      words.each_with_index do |w, n|
+        if !(w.length < 6 || n == words.size - 1 || w =~ URI::regexp || w =~ /\A[\w+\-.]+@[a-z\d\-]+(\.[a-z]+)*\.[a-z]+\z/i)
+          w = l.visualise(w, char)
+        end
+        result << w
+      end
+      result.join(" ")
+    end
+
+    # Converts simple double quotes to the typograhic ones.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @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_double_quotes(input, start_quotes = "“", end_quotes = "”")
+      input.gsub(/"[^"]*"/) { |s| start_quotes + s[1..-2].strip + end_quotes }
+    end
+
+    # Converts simple single quotes to the typograhic ones.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @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 single quotes.
+    def fix_single_quotes(input, start_quotes = "‘", end_quotes = "’")
+      input.gsub(/'[^']*'/) { |s| start_quotes + s[1..-2].strip + end_quotes }
+    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)
+      output = input.gsub(/(\d+)\s{0,1}[Xx]\s{0,1}(\d+)/, '\1 × \2')
+      output = output.gsub(/(\d+)[Xx]/, '\1×')
+    end
+
+    # Adds thin non-breaking space between numbers.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with correct spaces between numbers.
+    def fix_space_between_numbers(input)
+      input.gsub(/(\d)\s+(\d)/, '\1 \2')
+    end
+
+    # Fixes spaces around various brackets.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with correct spaces around brackets.
+    def fix_brackets_whitespace(input)
+      output = input.gsub(/([\(\[\{])\s*/, '\1')
+      output = output.gsub(/\s*([\]\)\}])/, '\1')
+      output = output.gsub(/\s+([\(\[\{])\s*/, ' \1')
+      output = output.gsub(/\s*([\]\)\}])\s+/, '\1 ')
+    end
+
+    # Tries to substitute more characters which should be one, like "©", "™", etc.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with converted characters.
+    def fix_multicharacters(input)
+      output = input.gsub(/\([Cc]\)/, "©")
+      output = output.gsub(/\([Pp]\)/, "℗")
+      output = output.gsub(/\([Rr]\)/, "®")
+      output = output.gsub(/\((SM|sm|Sm)\)/, "℠")
+      output = output.gsub(/\((TM|tm|Tm)\)/, "™")
+      output = output.gsub(/\+-/, "±")
+      output = output.gsub(/-\+/, "∓")
+      output = output.gsub(/No.?\s*(\d+)/i, '№\1')
+      output = output.gsub(/°C/, '℃')
+      output = output.gsub(/°F/, '℉')
+    end
+
+    # Fixes spaces around punctuation.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with correct spaces around punctuation.
+    def fix_punctuation_whitespace(input)
+      input.gsub(/\s*([\!\?\.,;:…]+)\s*/, '\1 ')
+    end
+
+    # Fixes non-breaking spaces betwwen number and unit.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with correct spaces between number and unit.
+    def fix_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
+
+    # Adds non-breaking space before the last word in the paragraph.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph with removed widows.
+    def fix_widows(input)
+      input.gsub(/(\s)(\S+(\$|\z))/, ' \2')
+    end
+
+    # Removes whitespace after the end of the paragraph.
+    #
+    # @param input [String] The paragraph which will be converted.
+    # @return [String] Paragraph without trailing spaces.
+    def fix_trailing_spaces(input)
+      input.gsub(/\s*($|\z)/, '')
+    end
+
+  end
+end

metadata

@@ -0,0 +1,93 @@
+--- !ruby/object:Gem::Specification
+name: truty
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Matěj Kašpar Jirásek
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-01-04 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: text-hyphen
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+- !ruby/object:Gem::Dependency
+  name: simplecov
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.9'
+- !ruby/object:Gem::Dependency
+  name: yard
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.8'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.8'
+description: A string converter which aims to correct the typography.
+email: matej.jirasek@me.com
+executables:
+- truty
+extensions: []
+extra_rdoc_files: []
+files:
+- LICENSE
+- README.md
+- bin/truty
+- lib/truty.rb
+- lib/truty/czech.rb
+- lib/truty/general.rb
+homepage: https://github.com/mkj-is/Truty
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.3
+signing_key: 
+specification_version: 4
+summary: True typography converter
+test_files: []
+has_rdoc: