camertron-eprun 2.0.0 → 2.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 26933843a3512031c7c7d634c1fe12df78d39ee78639f673d1fb175b8df50c21
-  data.tar.gz: 8ef34886023216ee7b39aee4d93b9fe1374c855528af2e5885be4cc4d7dd8ade
+  metadata.gz: d717364f04a54e9a735a051300e3e95a45da9b77ee684492dba168e2e022b399
+  data.tar.gz: 12d9342da34767b7f0d327d52a7a9f25b6780ea6b826b783048cc90b497c7dfd
 SHA512:
-  metadata.gz: ce0baa5b5f798e53d8ab831f7e1865665a0aeaf673cf32cf1223dadeef983cd2cf99fc3be5415c2253370e6ae4da7a4546ba403ebb49df70a32b8e794d2aff54
-  data.tar.gz: 06a218b4865a111ebf9696f9bd08b52bdab15a8b1eda0ea0d2250a36ab14856400dd8e11032dbd5f8cacd896238a3f99f507365e0f058165d9bfb5106907e4ea
+  metadata.gz: ccbe83e39877f83318a43a58879e12d274bab3f6bfb4d47f74994958302a82a733d355d14a6b2bbe8759f8c1f19d8fbffde636ef5e37143e756d6819425ffa6c
+  data.tar.gz: 134d37aea675f15ff462d9422a9e48de8c8a8b8069ad8ac77960b0572e5822e9ff6864091b635c05e428acaf68c39d0c212a48c6323ff88ef18607cbb2446db7

data/CHANGELOG.md

@@ -1,3 +1,6 @@
+== 2.0.1
+* Fix bug in combining mark regex.
+
 == 2.0.0
 * Removed MRI 1.8 compatibility.
 * Big internal refactor, but same API.

data/Gemfile

@@ -10,4 +10,5 @@ end
 
 group :test do
   gem "test-unit"
+  gem "m"
 end

data/lib/eprun/v14_0_0/tables.rb

@@ -73,11 +73,9 @@ module Eprun
         "\u0F35" \
         "\u0F37" \
         "\u0F39" \
-        "\u0F71\u0F72" \
-        "\u0F74" \
+        "\u0F71-\u0F75" \
         "\u0F7A-\u0F7D" \
-        "\u0F80" \
-        "\u0F82-\u0F84" \
+        "\u0F80-\u0F84" \
         "\u0F86\u0F87" \
         "\u0FC6" \
         "\u102E" \

data/lib/eprun/v15_1_0/tables.rb

@@ -73,11 +73,9 @@ module Eprun
         "\u0F35" \
         "\u0F37" \
         "\u0F39" \
-        "\u0F71\u0F72" \
-        "\u0F74" \
+        "\u0F71-\u0F75" \
         "\u0F7A-\u0F7D" \
-        "\u0F80" \
-        "\u0F82-\u0F84" \
+        "\u0F80-\u0F84" \
         "\u0F86\u0F87" \
         "\u0FC6" \
         "\u102E" \

data/lib/eprun/v16_0_0/tables.rb

@@ -73,11 +73,9 @@ module Eprun
         "\u0F35" \
         "\u0F37" \
         "\u0F39" \
-        "\u0F71\u0F72" \
-        "\u0F74" \
+        "\u0F71-\u0F75" \
         "\u0F7A-\u0F7D" \
-        "\u0F80" \
-        "\u0F82-\u0F84" \
+        "\u0F80-\u0F84" \
         "\u0F86\u0F87" \
         "\u0FC6" \
         "\u102E" \

data/lib/eprun/v17_0_0/tables.rb

@@ -73,11 +73,9 @@ module Eprun
         "\u0F35" \
         "\u0F37" \
         "\u0F39" \
-        "\u0F71\u0F72" \
-        "\u0F74" \
+        "\u0F71-\u0F75" \
         "\u0F7A-\u0F7D" \
-        "\u0F80" \
-        "\u0F82-\u0F84" \
+        "\u0F80-\u0F84" \
         "\u0F86\u0F87" \
         "\u0FC6" \
         "\u102E" \

data/lib/eprun/v18_0_0/tables.rb

@@ -73,11 +73,9 @@ module Eprun
         "\u0F35" \
         "\u0F37" \
         "\u0F39" \
-        "\u0F71\u0F72" \
-        "\u0F74" \
+        "\u0F71-\u0F75" \
         "\u0F7A-\u0F7D" \
-        "\u0F80" \
-        "\u0F82-\u0F84" \
+        "\u0F80-\u0F84" \
         "\u0F86\u0F87" \
         "\u0FC6" \
         "\u102E" \

data/lib/eprun/version.rb

@@ -5,7 +5,7 @@
 # (see http://www.ruby-lang.org/en/LICENSE.txt)
 
 module Eprun
-  VERSION = "2.0.0"
+  VERSION = "2.0.1"
   UCD_VERSIONS = [
     "18.0.0",
     "17.0.0",

data/lib/eprun.rb

@@ -17,11 +17,11 @@ module Eprun
 
   class << self
     def current_version
-      Thread.current[:__eprun_current_version__]
+      Fiber[:__eprun_current_version__]
     end
 
     def current_version=(new_version)
-      Thread.current[:__eprun_current_version__] = Eprun::UcdVersion.get(new_version)
+      Fiber[:__eprun_current_version__] = Eprun::UcdVersion.get(new_version)
     end
 
     def normalize(*args)

data/test/test_normalize.rb

@@ -58,7 +58,11 @@ class TestNormalize < Test::Unit::TestCase
     end
   end
 
-  Eprun::UCD_VERSIONS.each do |ucd_version|
+  def self.ucd_versions
+    Array(ENV.fetch("UCD_VERSION", Eprun::UCD_VERSIONS))
+  end
+
+  ucd_versions.each do |ucd_version|
     Eprun.with_version(ucd_version) do
       # source; NFC; NFD; NFKC; NFKD
       #
@@ -147,7 +151,7 @@ class TestNormalize < Test::Unit::TestCase
     end
   end
 
-  Eprun::UCD_VERSIONS.each do |ucd_version|
+  ucd_versions.each do |ucd_version|
     Eprun.with_version(ucd_version) do
       generate_test_check_true :NFC, :nfc
       generate_test_check_true :NFD, :nfd
@@ -195,4 +199,24 @@ class TestNormalize < Test::Unit::TestCase
     assert_equal utf8('\u1100\u1161\u0323\u0300'), Eprun.normalize(utf8('\uAC00\u0300\u0323'), :nfd)
     assert_equal utf8('\u1100\u1161\u0323\u0300'), Eprun.normalize(utf8('\u1100\u1161\u0300\u0323'), :nfd)
   end
+
+  def test_combining_sequences_ordered_together
+    # The following example comes from the Unicode collation tests. In this example,
+    # the 0F81 decomposes into 0F71 0F80, which have combining classes of 129 and 130
+    # respectively. The 0591 that comes logically earlier in the codepoint sequence
+    # has a combining class of 220. Because Ruby's NFD normalization algorithm decomposes
+    # subsections of the string rather than the entire string at once, earlier
+    # implementations processed 0FB2 and 0591 in isolation, which generated a string
+    # with combining classes 0 220 129 130 0, which is not the correct canonical order;
+    # 0591 (combining class of 220) should be ordered after 0F80 (combining class of
+    # 130). This test ensures correct ordering is observed for such cases.
+    a = "\u0FB2\u0591\u0F81\u0061"
+    assert_equal("\u0FB2\u0F71\u0F80\u0591\u0061", Eprun.normalize(a, :nfd))
+
+    # This tests that the logic above holds when the sequence starts with a decomposition
+    # starter. 00C0 decomposes to 0041 0300 and 0F81 decomposes to 0F71 0F80, all of
+    # which have combining classes > 0 and must be ordered with 0591.
+    a = "\u00C0\u0591\u0F81"
+    assert_equal("\u0041\u0F71\u0F80\u0591\u0300", Eprun.normalize(a, :nfd))
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: camertron-eprun
 version: !ruby/object:Gem::Version
-  version: 2.0.0
+  version: 2.0.1
 platform: ruby
 authors:
 - Ayumu Nojima (野島 歩)
@@ -60,7 +60,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.3
+rubygems_version: 4.0.23
 specification_version: 4
 summary: Efficient pure Ruby Unicode normalization.
 test_files: []