isodoc-i18n 1.2.1 → 1.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7552e0a62364e47c4f8ea7b2810e1ba5d11e39d2a3711792c826412b1aef661f
-  data.tar.gz: 29d4eef4f2a07bcf6ad1de7ddc229cf7ff9b0ffa8e55c81652d2174165cf2214
+  metadata.gz: 490a22f13264a470afa34644c450651239bb43409aa8e579bae72229d165fe38
+  data.tar.gz: 9be5c331d23f732e37e2588ff3269e867231f56b6b074417258f5e01fa55aeba
 SHA512:
-  metadata.gz: 220fddc821f5f00d4f1eecca1f7583b0236254bb0a5141c50d7583f4c725be2b4aca949ffc4f89ed390c01850f2912d86b9562959773efabf1a3df4838e8ec60
-  data.tar.gz: 59373ef3a3688bf4f382da1e2a5df55b3b7ae1615385bc04504faf9421e9c5e66333ed1859243f0e8a86d4f42724692ab1cd9b8f9f0bd62d4c4e70cceb7e93cd
+  metadata.gz: 024f04dedc8bdef757f52d1ae35b69af155d786bb5e1075b6be8c11e2a2039b0bf9ee4e39a0bbca260e3edee85aafb70360240286a38ce12cb41fef88db70e02
+  data.tar.gz: 6952b1cf007e02b5e7fcb9ca3507cda68e22e27facee436fafc41daaa65b6b5eed3b5e0b9fbbde57d8c10361ab55dcc870a25b92a0f624597b02bb3a912c7586

data/isodoc-i18n.gemspec

@@ -37,5 +37,6 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "simplecov", "~> 0.15"
   spec.add_development_dependency "timecop", "~> 0.9"
   spec.add_development_dependency "webmock"
+  spec.add_development_dependency "xml-c14n"
   # spec.metadata["rubygems_mfa_required"] = "true"
 end

data/lib/isodoc/i18n/version.rb

@@ -1,5 +1,5 @@
 module IsoDoc
   class I18n
-    VERSION = "1.2.1".freeze
+    VERSION = "1.2.2".freeze
   end
 end

data/lib/isodoc/l10n.rb

@@ -5,9 +5,8 @@ module IsoDoc
     end
 
     # function localising spaces and punctuation.
-    # Not clear if period needs to be localised for zh
     def l10n(text, lang = @lang, script = @script, locale = @locale)
-      lang == "zh" and text = l10n_zh(text, script)
+      %w(zh ja ko).include?(lang) and text = l10n_zh(text, script)
       lang == "fr" && text = l10n_fr(text, locale || "FR")
       bidiwrap(text, lang, script)
     end
@@ -30,11 +29,11 @@ module IsoDoc
          .default_script(@lang))]
     end
 
+    # CJK
     def l10n_zh(text, script = "Hans")
       xml = Nokogiri::XML::DocumentFragment.parse(text)
       xml.traverse do |n|
-        next unless n.text?
-
+        n.text? or next
         n.replace(l10_zh1(cleanup_entities(n.text, is_xml: false), script))
       end
       xml.to_xml(encoding: "UTF-8").gsub(/<b>/, "").gsub("</b>", "")
@@ -56,19 +55,32 @@ module IsoDoc
 
     # note: we can't differentiate comma from enumeration comma 、
     def l10_zh1(text, _script)
-      l10n_zh_remove_space(l10n_zh_punct(text))
+      l10n_zh_dash(l10n_zh_remove_space(l10n_zh_punct(text)))
     end
 
+    # CJK punct if (^|CJK).($|CJK)
     def l10n_zh_punct(text)
-      [":：", ",，", ".．", ")）", "]］", ":：", ";；", "?？", "!！", "–～"].each do |m|
-        text = text.gsub(/#{Regexp.quote m[0]}/, m[1])
-      end
-      ["(（", "[［"].each do |m|
-        text = text.gsub(/#{Regexp.quote m[0]}/, m[1])
+      [":：", ",，", ".．", ")）", "]］", ";；", "?？", "!！", "(（", "[［"].each do |m|
+        text = text.gsub(/(?<=#{ZH_CHAR}|^) # CJK character, or start of string
+    (\s*)                  # Latin spaces optional
+    #{Regexp.quote(m[0])}  # Latin punctuation we want to convert to CJK
+    (?=   \s*              # followed (lookahead) by ignorable Latin spaces
+      [:,.()\[\];?!-]*     # Latin punctuation which we will also convert to CJK
+      (#{ZH_CHAR}|$)       # CJK character, or end of string
+    ) /x, "\\1#{m[1]}")
       end
       text
     end
 
+    def l10n_zh_dash(text)
+      text.gsub(/(?<=#{ZH_CHAR}|^) # CJK character, or start of string
+                (\d*)              # optional digits
+                –                  # en-dash
+                (\d*)              # optional digits
+                (#{ZH_CHAR}|$)     # CJK character, or end of string
+                /xo, "\\1～\\2\\3")
+    end
+
     def l10n_zh_remove_space(text)
       text.gsub(/(?<=#{ZH_CHAR}) (?=#{ZH_CHAR})/o, "")
         .gsub(/(?<=\d) (?=#{ZH_CHAR})/o, "")
@@ -102,7 +114,8 @@ module IsoDoc
 
     def interleave_space_cjk?(text)
       text.size == 2 or return
-      ["\u2014\u2014", "\u2025\u2025", "\u2026\u2026", "\u22ef\u22ef"].include?(text) ||
+      ["\u2014\u2014", "\u2025\u2025", "\u2026\u2026",
+       "\u22ef\u22ef"].include?(text) ||
         /\d\d|\p{Latin}\p{Latin}|[[:space:]]/.match?(text) ||
         /^[\u2018\u201c(\u3014\[{\u3008\u300a\u300c\u300e\u3010\u2985\u3018\u3016\u00ab\u301d]/.match?(text) ||
         /[\u2019\u201d)\u3015\]}\u3009\u300b\u300d\u300f\u3011\u2986\u3019\u3017\u00bb\u301f]$/.match?(text) ||

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: isodoc-i18n
 version: !ruby/object:Gem::Version
-  version: 1.2.1
+  version: 1.2.2
 platform: ruby
 authors:
 - Ribose Inc.
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2024-02-19 00:00:00.000000000 Z
+date: 2024-10-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: htmlentities
@@ -206,6 +206,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: xml-c14n
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: 'Internationalisation for Metanorma rendering
 
   '
@@ -249,7 +263,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.26
+rubygems_version: 3.3.27
 signing_key: 
 specification_version: 4
 summary: isodoc-i18n