orthotypo 0.5.1 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '05389ada5ba288061bd70f8e3170fb77b7d4d9df171b90e55d3c0c6edbf4d810'
-  data.tar.gz: edd5731b28644f5515133994a89185f2da4fc5cffb7c12273f2d1f48985571be
+  metadata.gz: fd24cbdb2c5adaa4f6ecf91acf144025549b7599aeb0f944e3f1987331448450
+  data.tar.gz: 6d9a7bb478c4cc0b76722128a1065fc99666f7d1f284cc82cb6f26acfe89bf70
 SHA512:
-  metadata.gz: 32280cc5abbc8b3d9a728db9943f815821c84c97384f59f6be2f0ba12789e2ef204a8c72ec579a2544cea505b9c2f3d46c51aef5db7006ac74e3e8d568813a85
-  data.tar.gz: b81b849cf147939f7ad2e6fb16ccbc3af8eed2016efa67a288fcc9fc2c7cbd3d9d2d4b78ad4d70588fd75dade26830e4443627024838404f01e4010cbb5f2989
+  metadata.gz: e51b243378c8d97df6fd3bfa7f59a7aeb7f516d3f54d82cce4eb0ae8d3c7b6a5893211c857c72f8c249a73e0333f3d187ddf4d6145a45ab6de5039633aeaf457
+  data.tar.gz: dc77c1043a6210122c48a8d5849d63df04247d3d957707469d9e3029ed0cf1a9bec745cd12115bb4563254abc6e227c74e13f02285fc0cada9a0d75ab0be2ad6

data/Gemfile.lock

@@ -1,8 +1,9 @@
 PATH
   remote: .
   specs:
-    orthotypo (0.5.1)
+    orthotypo (1.0.0)
       htmlentities
+      nokogiri
 
 GEM
   remote: https://rubygems.org/
@@ -14,6 +15,10 @@ GEM
     htmlentities (4.3.4)
     json (2.6.3)
     language_server-protocol (3.17.0.3)
+    nokogiri (1.15.4-arm64-darwin)
+      racc (~> 1.4)
+    nokogiri (1.15.4-x86_64-darwin)
+      racc (~> 1.4)
     parallel (1.23.0)
     parser (3.2.2.4)
       ast (~> 2.4.1)

data/README.md

@@ -28,10 +28,10 @@ Ajout d'espace fine insécable avant les signes doubles en français.
 ## Roadmap
 
 ### v1
-1. S'adapter aux locales (détecter I18n)
-2. Ne pas endommager l'HTML et les HTML entities ( )
+Ne pas endommager l'HTML et les HTML entities ( )
 
 ### v2
+S'adapter aux locales (détecter I18n)
 Permettre les configs
 
 ## Sources

data/lib/orthotypo/analyzer.rb

@@ -0,0 +1,18 @@
+module Orthotypo
+  class Analyzer
+
+    def self.url?(string)
+      (string =~ /\A#{URI::DEFAULT_PARSER.regexp[:ABS_URI]}\z/) && 
+      (string =~ /\A(http|https):\/\/[a-z0-9]+([\-\.]{1}[a-z0-9]+)*\.[a-z]{2,5}(:[0-9]{1,5})?(\/.*)?\z/ix) ? true : false
+    end
+  
+    def self.email?(string)
+      string =~ /\A#{URI::MailTo::EMAIL_REGEXP}\z/ ? true : false
+    end
+
+    def self.precious?(string)
+      email?(string) || url?(string)
+    end
+    
+  end
+end

data/lib/orthotypo/composer.rb

@@ -5,6 +5,7 @@ module Orthotypo
     SPACE = ' '.freeze
     NBSP = ' '.freeze
     NNBSP = ' '.freeze
+    PRECIOUS_TOKEN = 'orthotypopreciousthing'
 
     def initialize(string, html: nil)
       @string = string
@@ -18,6 +19,12 @@ module Orthotypo
       []
     end
 
+    def chars_with_space_before_after_digit
+      [
+        '%'
+      ]
+    end
+
     def chars_with_space_after
       [
         ',',
@@ -41,6 +48,22 @@ module Orthotypo
       []
     end
 
+    def chars_with_no_space_around_between_digits
+      [
+        '/',
+        ':'
+      ]
+    end
+
+    def chars_in_numbers
+      [
+        '.', 
+        ',',
+        '/',
+        ':'
+      ]
+    end
+
     def is_html?
       # TODO contains tags?
       @html || contains_html_entities?
@@ -52,17 +75,21 @@ module Orthotypo
 
     def prepare_ortho
       @ortho = string.dup
-      @ortho = html_entities.decode(@ortho) if contains_html_entities?
+      # @ortho = html_entities.decode(@ortho) if contains_html_entities?
+      @nokogiri = Nokogiri::HTML.fragment @ortho
     end
 
     def clean_ortho
-      @ortho = html_entities.encode(@ortho) if contains_html_entities?
+      @ortho = @nokogiri.to_s
+      # @ortho = html_entities.encode(@ortho) if contains_html_entities?
     end
 
     def parse
       prepare_ortho
+      preserve_precious_things
       # Chars
       parse_chars_with_space_before
+      parse_chars_with_space_before_after_digit
       parse_chars_with_space_after
       parse_chars_with_space_around
       parse_chars_with_no_space_around
@@ -70,17 +97,47 @@ module Orthotypo
       parse_pairs_with_space_around
       parse_pairs_with_no_space_around
       # Numbers
-      parse_numbers
+      parse_chars_in_numbers
       # 
       clean_ortho
+      restore_precious_things
+    end
+
+    def preserve_precious_things
+      @precious_things = []
+      @nokogiri.traverse do |node|
+        next unless node.text?
+        new_content = node.content.split(SPACE).map { |fragment|
+          if Analyzer::precious?(fragment)
+            token = "#{PRECIOUS_TOKEN}#{@precious_things.length}"
+            @precious_things << fragment
+            token
+          else
+            fragment
+          end
+        }.join(SPACE)
+        node.content = new_content
+      end
+    end
+
+    def restore_precious_things
+      @precious_things.each_with_index do |value, index|
+        @ortho.gsub! "#{PRECIOUS_TOKEN}#{index}", value
+      end
     end
 
     def parse_chars_with_space_before
       chars_with_space_before.each do |char|
         # Espace normal avant -> espace fine insécable avant
-        fix(SPACE + '%', NNBSP + '%')
+        fix(SPACE + char, NNBSP + char)
         # Pas d'espace avant -> espace fine insécable avant
-        fix(/([[:alnum:]])%/, "\\1" + NNBSP + '%')
+        fix(/([[:alpha:]])[#{char}]/, "\\1" + NNBSP + char)
+      end
+    end
+
+    def parse_chars_with_space_before_after_digit
+      chars_with_space_before_after_digit.each do |char|
+        fix(/([[:digit:]])[#{char}]/, "\\1" + NNBSP + char)
       end
     end
 
@@ -89,7 +146,7 @@ module Orthotypo
         # Espace avant -> pas d'espace avant 
         fix(SPACE + char, char)
         # Pas d'espace après -> espace après
-        fix(/[#{char}]([[:alnum:]])/, char + SPACE + "\\1")
+        fix(/[#{char}]([[:alpha:]])/, char + SPACE + "\\1")
       end
     end
 
@@ -98,7 +155,7 @@ module Orthotypo
         # Espace normal avant -> espace fine insécable avant
         fix(SPACE + char, NNBSP + char)
         # Pas d'espace avant -> espace fine insécable avant
-        fix(/([[:alnum:]])[#{char}]/, "\\1" + NNBSP + char)
+        fix(/([[:alpha:]])[#{char}]/, "\\1" + NNBSP + char)
       end
     end
 
@@ -134,8 +191,10 @@ module Orthotypo
       end
     end
 
-    def parse_numbers
-      ['.', ','].each do |char|
+    def parse_chars_in_numbers
+      chars_in_numbers.each do |char|
+        fix(/([[:digit:]])[[:space:]][#{char}]([[:digit:]])/, "\\1" + char + "\\2")
+        fix(/([[:digit:]])[[:space:]][#{char}][[:space:]]([[:digit:]])/, "\\1" + char + "\\2")
         fix(/([[:digit:]])[#{char}][[:space:]]([[:digit:]])/, "\\1" + char + "\\2")
       end
     end
@@ -145,7 +204,10 @@ module Orthotypo
     end
 
     def fix(bad, good)
-      @ortho.gsub! bad, good
+      @nokogiri.traverse do |node|
+        next unless node.text?
+        node.content = node.content.gsub(bad, good)
+      end
     end
   end
 end

data/lib/orthotypo/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Orthotypo
-  VERSION = "0.5.1"
+  VERSION = "1.0.0"
 end

data/lib/orthotypo.rb

@@ -1,6 +1,9 @@
 # frozen_string_literal: true
 
 require "htmlentities"
+require "nokogiri"
+require "uri"
+require_relative "orthotypo/analyzer"
 require_relative "orthotypo/composer"
 require_relative "orthotypo/composer/fr"
 require_relative "orthotypo/composer/fr_fr"

data/orthotypo.gemspec

@@ -21,6 +21,7 @@ Gem::Specification.new do |spec|
   spec.require_paths = "lib"
 
   spec.add_dependency "htmlentities"
+  spec.add_dependency "nokogiri"
 
   spec.add_development_dependency "rspec"
   spec.add_development_dependency "rspec-nc"

data/spec/analyzer_spec.rb

@@ -0,0 +1,8 @@
+require 'spec_helper'
+
+describe Orthotypo::Analyzer do
+  it 'find urls' do
+    expect(Orthotypo::Analyzer.url?("https://unsplash.com/@lusvardi?utm_source=osuny")).to be true
+    expect(Orthotypo::Analyzer.url?("mot:")).to be false
+  end
+end

data/spec/composer/fr_spec.rb

@@ -5,7 +5,8 @@ describe Orthotypo::Composer::Fr do
   it 'adds spaces before double punctuation marks' do
     expect("mot: suite".ortho).to(eq("mot : suite"))
     expect("é: suite".ortho).to(eq("é : suite"))
-    expect("1: suite".ortho).to(eq("1 : suite"))
+    # Pas automatisable, parce que 11:20
+    # expect("1: suite".ortho).to(eq("1 : suite"))
     expect("mot; suite".ortho).to(eq("mot ; suite"))
     expect("mot!".ortho).to(eq("mot !"))
     expect("mot !".ortho).to(eq("mot !"))
@@ -44,6 +45,14 @@ describe Orthotypo::Composer::Fr do
     expect("10 %".ortho).to(eq("10 %"))
   end
 
+  it 'fixes dates/time' do
+    expect("10/01/2023 16:00".ortho).to(eq("10/01/2023 16:00"))
+    expect("10/01/2023 16:00:00".ortho).to(eq("10/01/2023 16:00:00"))
+    expect("10 / 01 / 2023 16:00".ortho).to(eq("10/01/2023 16:00"))
+    expect("10 / 01 / 2023 16 : 00".ortho).to(eq("10/01/2023 16:00"))
+    expect("10 octobre 2023 16:00".ortho).to(eq("10 octobre 2023 16:00"))
+  end
+
   # https://www.scribbr.fr/elements-linguistiques/les-espaces/
   it 'tests de Justine Debret' do
     expect("Elle a vu son cousin,sa tante et son oncle.Ils allaient tous très bien.".ortho).to(eq("Elle a vu son cousin, sa tante et son oncle. Ils allaient tous très bien."))
@@ -53,6 +62,7 @@ describe Orthotypo::Composer::Fr do
     expect("Il a dit : «J’arrive ce matin ( ou plus tard ) à Paris [ rue de la République ] pour son anniversaire.»".ortho).to(eq("Il a dit : « J’arrive ce matin (ou plus tard) à Paris [rue de la République] pour son anniversaire. »"))
     # Le test suivant n'est pas automatisable, parce qu'on ne peut distinguer un Paris-Brest (le gâteau) d'un Paris - Brest (le trajet)
     # expect("Nous l’avons rencontré à Saint - Martin.".ortho).to(eq("Nous l’avons rencontré à Saint-Martin."))
+    expect("Il roule pendant 31, 5 km.".ortho).to(eq("Il roule pendant 31,5 km."))
     # Le test suivant est-il automatisable ?
     # expect("Il roule pendant 31, 5km.".ortho).to(eq("Il roule pendant 31,5 km."))
     # Pas automatisable, rien ne permet de distinguer s'il s'agit d'un rang ou d'un nombre

data/spec/orthotypo_spec.rb

@@ -8,4 +8,14 @@ describe Orthotypo do
   it 'leaves html tags untouched' do
     expect("<b>bold</b>".ortho).to eq "<b>bold</b>"
   end
+
+  it 'leaves URLs untouched' do
+    expect("https://unsplash.com/@lusvardi?utm_source=osuny".ortho).to eq "https://unsplash.com/@lusvardi?utm_source=osuny"
+    expect("<a href=\"https://unsplash.com/@lusvardi?utm_source=osuny\">https://unsplash.com/@lusvardi?utm_source=osuny</a>".ortho).to eq "<a href=\"https://unsplash.com/@lusvardi?utm_source=osuny\">https://unsplash.com/@lusvardi?utm_source=osuny</a>"
+  end
+
+  it 'leaves URLs untouched' do
+    expect("prenom.nom@example.com".ortho).to eq "prenom.nom@example.com"
+    expect("<a href=\"mailto:prenom.nom@example.com\">prenom.nom@example.com</a>".ortho).to eq "<a href=\"mailto:prenom.nom@example.com\">prenom.nom@example.com</a>"
+  end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: orthotypo
 version: !ruby/object:Gem::Version
-  version: 0.5.1
+  version: 1.0.0
 platform: ruby
 authors:
 - Arnaud Levy
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-10-16 00:00:00.000000000 Z
+date: 2023-10-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities
@@ -24,6 +24,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -87,6 +101,7 @@ files:
 - bin/console
 - bin/setup
 - lib/orthotypo.rb
+- lib/orthotypo/analyzer.rb
 - lib/orthotypo/composer.rb
 - lib/orthotypo/composer/en.rb
 - lib/orthotypo/composer/en_gb.rb
@@ -98,6 +113,7 @@ files:
 - lib/orthotypo/version.rb
 - orthotypo.gemspec
 - sig/orthotypo.rbs
+- spec/analyzer_spec.rb
 - spec/composer/en_spec.rb
 - spec/composer/fr_spec.rb
 - spec/localizer_spec.rb