kotovalexarian-likes-github/ruby--ruby
1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00
Code Releases Activity

unicode_normalize: UNICODE_VERSION constant

Browse source 
* template/unicode_norm_gen.tmpl (UnicodeNormalize): embed the
  version of Unicode data files used to generate.

* test/test_unicode_normalize.rb (TestUnicodeNormalize): use the
  embedded version to load the test data.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@48357 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nobu 2014-11-10 06:56:41 +00:00
parent 8cba9dccf6
commit 79c0b7fcc8
2 changed files with 12 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

10
template/unicode_norm_gen.tmpl
View file

@ -7,7 +7,7 @@
# Constants for input and ouput directory # Constants for input and ouput directory
InputDataDir = ARGV[0] || 'enc/unicode/data' InputDataDir = ARGV[0] || 'enc/unicode/data'
OuputDataDir = ARGV[1] || 'lib/unicode_normalize' unicode_version = InputDataDir[/[\d.]+\z/]
# convenience methods # convenience methods
class Integer class Integer
@ -67,6 +67,12 @@ end
# read the file 'CompositionExclusions.txt' # read the file 'CompositionExclusions.txt'
composition_exclusions = vpath.open("#{InputDataDir}/CompositionExclusions.txt") {|f| composition_exclusions = vpath.open("#{InputDataDir}/CompositionExclusions.txt") {|f|
base = Regexp.quote(File.basename(f.path, '.*'))
ext = Regexp.quote(File.extname(f.path))
version = (line = f.gets)[/^# *#{base}-([\d.]+)#{ext}\s*$/, 1] or
abort "No file version in #{f.path}: #{line}"
(unicode_version ||= version) == version or
abort "Unicode version of directory (#{unicode_version}) and file (#{version}) mismatch"
f.grep(/^[A-Z0-9]{4,5}/) {|line| line.hex} f.grep(/^[A-Z0-9]{4,5}/) {|line| line.hex}
} }
@ -151,6 +157,8 @@ end
# automatically generated by template/unicode_norm_gen.tmpl # automatically generated by template/unicode_norm_gen.tmpl
module UnicodeNormalize module UnicodeNormalize
UNICODE_VERSION = "<%=unicode_version%>".freeze
accents = "" \ accents = "" \
"[<% accent_array.each_regexp_chars do |rx|%><%=rx%>" \ "[<% accent_array.each_regexp_chars do |rx|%><%=rx%>" \
"<% end%>]" \ "<% end%>]" \

4
test/test_unicode_normalize.rb
View file

@ -3,15 +3,17 @@
# Copyright Ayumu Nojima (野島 歩) and Martin J. Dürst (duerst@it.aoyama.ac.jp) # Copyright Ayumu Nojima (野島 歩) and Martin J. Dürst (duerst@it.aoyama.ac.jp)
require 'test/unit' require 'test/unit'
require 'unicode_normalize/normalize'
class TestUnicodeNormalize < Test::Unit::TestCase class TestUnicodeNormalize < Test::Unit::TestCase
UNICODE_VERSION = '7.0.0' UNICODE_VERSION = UnicodeNormalize::UNICODE_VERSION
NormTest = Struct.new :source, :NFC, :NFD, :NFKC, :NFKD, :line NormTest = Struct.new :source, :NFC, :NFD, :NFKC, :NFKD, :line
def read_tests def read_tests
IO.readlines(File.expand_path("../enc/unicode/data/#{UNICODE_VERSION}/NormalizationTest.txt", __dir__), encoding: 'utf-8') IO.readlines(File.expand_path("../enc/unicode/data/#{UNICODE_VERSION}/NormalizationTest.txt", __dir__), encoding: 'utf-8')
.tap { |lines| assert_include(lines[0], "NormalizationTest-#{UNICODE_VERSION}.txt")}
.collect.with_index { |linedata, linenumber| [linedata, linenumber]} .collect.with_index { |linedata, linenumber| [linedata, linenumber]}
.reject { |line| line[0] =~ /^[\#@]/ } .reject { |line| line[0] =~ /^[\#@]/ }
.collect do |line| .collect do |line|