diff options
author | Gonçalo Silva <goncalossilva@gmail.com> | 2010-08-10 18:15:12 +0100 |
---|---|---|
committer | Gonçalo Silva <goncalossilva@gmail.com> | 2010-08-10 18:15:12 +0100 |
commit | 62658500049fbb7a5e7d75537dd6f6a374204207 (patch) | |
tree | 8892d8305ced43866068a6c1c66548e465e45b38 /activesupport/lib/active_support/multibyte/unicode.rb | |
parent | cd2bbed9846d84a1230a1b9e52843eedca17b28d (diff) | |
parent | e86cced311539932420f9cda49d736606d106c28 (diff) | |
download | rails-62658500049fbb7a5e7d75537dd6f6a374204207.tar.gz rails-62658500049fbb7a5e7d75537dd6f6a374204207.tar.bz2 rails-62658500049fbb7a5e7d75537dd6f6a374204207.zip |
Merge branch 'master' of http://github.com/rails/rails
Diffstat (limited to 'activesupport/lib/active_support/multibyte/unicode.rb')
-rw-r--r-- | activesupport/lib/active_support/multibyte/unicode.rb | 19 |
1 files changed, 9 insertions, 10 deletions
diff --git a/activesupport/lib/active_support/multibyte/unicode.rb b/activesupport/lib/active_support/multibyte/unicode.rb index 11c72d873b..1139783b65 100644 --- a/activesupport/lib/active_support/multibyte/unicode.rb +++ b/activesupport/lib/active_support/multibyte/unicode.rb @@ -64,7 +64,7 @@ module ActiveSupport # valid UTF-8. # # Example: - # Unicode.u_unpack('Café') #=> [67, 97, 102, 233] + # Unicode.u_unpack('Café') # => [67, 97, 102, 233] def u_unpack(string) begin string.unpack 'U*' @@ -85,8 +85,8 @@ module ActiveSupport # Unpack the string at grapheme boundaries. Returns a list of character lists. # # Example: - # Unicode.g_unpack('क्षि') #=> [[2325, 2381], [2359], [2367]] - # Unicode.g_unpack('Café') #=> [[67], [97], [102], [233]] + # Unicode.g_unpack('क्षि') # => [[2325, 2381], [2359], [2367]] + # Unicode.g_unpack('Café') # => [[67], [97], [102], [233]] def g_unpack(string) codepoints = u_unpack(string) unpacked = [] @@ -99,15 +99,15 @@ module ActiveSupport current = codepoints[pos] if ( # CR X LF - one = ( previous == database.boundary[:cr] and current == database.boundary[:lf] ) or + ( previous == database.boundary[:cr] and current == database.boundary[:lf] ) or # L X (L|V|LV|LVT) - two = ( database.boundary[:l] === previous and in_char_class?(current, [:l,:v,:lv,:lvt]) ) or + ( database.boundary[:l] === previous and in_char_class?(current, [:l,:v,:lv,:lvt]) ) or # (LV|V) X (V|T) - three = ( in_char_class?(previous, [:lv,:v]) and in_char_class?(current, [:v,:t]) ) or + ( in_char_class?(previous, [:lv,:v]) and in_char_class?(current, [:v,:t]) ) or # (LVT|T) X (T) - four = ( in_char_class?(previous, [:lvt,:t]) and database.boundary[:t] === current ) or + ( in_char_class?(previous, [:lvt,:t]) and database.boundary[:t] === current ) or # X Extend - five = (database.boundary[:extend] === current) + (database.boundary[:extend] === current) ) else unpacked << codepoints[marker..pos-1] @@ -120,7 +120,7 @@ module ActiveSupport # Reverse operation of g_unpack. # # Example: - # Unicode.g_pack(Unicode.g_unpack('क्षि')) #=> 'क्षि' + # Unicode.g_pack(Unicode.g_unpack('क्षि')) # => 'क्षि' def g_pack(unpacked) (unpacked.flatten).pack('U*') end @@ -238,7 +238,6 @@ module ActiveSupport bytes.each_index do |i| byte = bytes[i] - is_ascii = byte < 128 is_cont = byte > 127 && byte < 192 is_lead = byte > 191 && byte < 245 is_unused = byte > 240 |