1
0
Fork 0
mirror of https://github.com/rails/rails.git synced 2022-11-09 12:12:34 -05:00

Correctly handle offsets in Multibyte::Chars#index and #rindex.

The offset in codepoints was being passed directly to the wrapped string's index/rindex method. Now we translate the offset into bytes first.

[#3028 state:committed]

Signed-off-by: Jeremy Kemper <jeremy@bitsweat.net>
This commit is contained in:
Erik Ostrom 2009-08-09 22:14:59 -07:00 committed by Jeremy Kemper
parent 3e35ba2481
commit 7d16e94d82
2 changed files with 11 additions and 4 deletions

View file

@ -206,7 +206,8 @@ module ActiveSupport #:nodoc:
# 'Café périferôl'.mb_chars.index('ô') #=> 12
# 'Café périferôl'.mb_chars.index(/\w/u) #=> 0
def index(needle, offset=0)
index = @wrapped_string.index(needle, offset)
wrapped_offset = self.first(offset).wrapped_string.length
index = @wrapped_string.index(needle, wrapped_offset)
index ? (self.class.u_unpack(@wrapped_string.slice(0...index)).size) : nil
end
@ -215,11 +216,12 @@ module ActiveSupport #:nodoc:
# string. Returns +nil+ if _needle_ isn't found.
#
# Example:
# 'Café périferôl'.mb_chars.rindex('é') #=> 5
# 'Café périferôl'.mb_chars.rindex('é') #=> 6
# 'Café périferôl'.mb_chars.rindex(/\w/u) #=> 13
def rindex(needle, offset=nil)
offset ||= length
index = @wrapped_string.rindex(needle, offset)
wrapped_offset = self.first(offset).wrapped_string.length
index = @wrapped_string.rindex(needle, wrapped_offset)
index ? (self.class.u_unpack(@wrapped_string.slice(0...index)).size) : nil
end

View file

@ -230,14 +230,19 @@ class MultibyteCharsUTF8BehaviourTest < Test::Unit::TestCase
assert_nil @chars.index('u')
assert_equal 0, @chars.index('こに')
assert_equal 2, @chars.index('ち')
assert_equal 2, @chars.index('ち', -2)
assert_equal nil, @chars.index('ち', -1)
assert_equal 3, @chars.index('わ')
assert_equal 5, 'ééxééx'.mb_chars.index('x', 4)
end
def test_rindex_should_return_character_offset
assert_nil @chars.rindex('u')
assert_equal 1, @chars.rindex('に')
assert_equal 2, @chars.rindex('ち', -2)
assert_nil @chars.rindex('ち', -3)
assert_equal 6, 'Café périferôl'.mb_chars.rindex('é')
assert_equal 12, 'Café périferôl'.mb_chars.rindex(/\w/u)
assert_equal 13, 'Café périferôl'.mb_chars.rindex(/\w/u)
end
def test_indexed_insert_should_take_character_offsets