1
0
Fork 0
mirror of https://github.com/rails/rails.git synced 2022-11-09 12:12:34 -05:00
rails--rails/activesupport/test/multibyte_grapheme_break_conformance_test.rb
2017-07-15 19:29:45 +09:00

62 lines
2 KiB
Ruby
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# frozen_string_literal: true
require "abstract_unit"
require "multibyte_test_helpers"
require "fileutils"
require "open-uri"
require "tmpdir"
class MultibyteGraphemeBreakConformanceTest < ActiveSupport::TestCase
include MultibyteTestHelpers
UNIDATA_FILE = "/auxiliary/GraphemeBreakTest.txt"
RUN_P = begin
Downloader.download(UNIDATA_URL + UNIDATA_FILE, CACHE_DIR + UNIDATA_FILE)
rescue
end
def setup
skip "Unable to download test data" unless RUN_P
end
def test_breaks
each_line_of_break_tests do |*cols|
*clusters, comment = *cols
packed = ActiveSupport::Multibyte::Unicode.pack_graphemes(clusters)
assert_equal clusters, ActiveSupport::Multibyte::Unicode.unpack_graphemes(packed), comment
end
end
private
def each_line_of_break_tests(&block)
lines = 0
max_test_lines = 0 # Don't limit below 21, because that's the header of the testfile
File.open(File.join(CACHE_DIR, UNIDATA_FILE), "r") do | f |
until f.eof? || (max_test_lines > 21 && lines > max_test_lines)
lines += 1
line = f.gets.chomp!
next if line.empty? || line.start_with?("#")
cols, comment = line.split("#")
# Cluster breaks are represented by ÷
clusters = cols.split("÷").map { |e| e.strip }.reject { |e| e.empty? }
clusters = clusters.map do |cluster|
# Codepoints within each cluster are separated by ×
codepoints = cluster.split("×").map { |e| e.strip }.reject { |e| e.empty? }
# codepoints are in hex in the test suite, pack wants them as integers
codepoints.map { |codepoint| codepoint.to_i(16) }
end
# The tests contain a solitary U+D800 <Non Private Use High
# Surrogate, First> character, which Ruby does not allow to stand
# alone in a UTF-8 string. So we'll just skip it.
next if clusters.flatten.include?(0xd800)
clusters << comment.strip
yield(*clusters)
end
end
end
end