mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
lib/unicode_normalize.rb: Added documentation.
git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@48016 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
parent
982f0de141
commit
f83c0b0ae7
2 changed files with 53 additions and 0 deletions
|
@ -1,3 +1,7 @@
|
|||
Sun Oct 19 17:26:26 2014 Martin Duerst <duerst@it.aoyama.ac.jp>
|
||||
|
||||
* lib/unicode_normalize.rb: Added documentation.
|
||||
|
||||
Sun Oct 19 11:09:09 2014 Martin Duerst <duerst@it.aoyama.ac.jp>
|
||||
|
||||
* tool/unicode_norm_gen.rb, lib/unicode_normalize.rb:
|
||||
|
|
|
@ -4,15 +4,64 @@
|
|||
|
||||
require 'unicode_normalize/normalize.rb'
|
||||
|
||||
# additions to class String for Unicode normalization
|
||||
class String
|
||||
# === Unicode Normalization
|
||||
#
|
||||
# :call-seq:
|
||||
# str.unicode_normalize(form=:nfc)
|
||||
#
|
||||
# Returns a normalized form of +str+, using Unicode normalizations
|
||||
# NFC, NFD, NFKC, or NFKD. The normalization form used is determined
|
||||
# by +form+, which is any of the four values :nfc, :nfd, :nfkc, or :nfkd.
|
||||
# The default is :nfc.
|
||||
#
|
||||
# If the string is not in a Unicode Encoding, then an Exception is raised.
|
||||
# In this context, 'Unicode Encoding' means any of UTF-8, UTF-16BE/LE,
|
||||
# and UTF-32BE/LE. Currently, anything else than UTF-8 is implemented
|
||||
# by converting to UTF-8, which makes it slower than UTF-8.
|
||||
#
|
||||
# _Examples_
|
||||
#
|
||||
# "a\u0300".unicode_normalize #=> 'à' (same as "\u00E0")
|
||||
# "a\u0300".unicode_normalize(:nfc) #=> 'à' (same as "\u00E0")
|
||||
# "\u00E0".unicode_normalize(:nfd) #=> 'à' (same as "a\u0300")
|
||||
# "\xE0".force_encoding('ISO-8859-1').unicode_normalize(:nfd)
|
||||
# #=> Encoding::CompatibilityError raised
|
||||
#
|
||||
def unicode_normalize(form = :nfc)
|
||||
UnicodeNormalize.normalize(self, form)
|
||||
end
|
||||
|
||||
# :call-seq:
|
||||
# str.unicode_normalize(form=:nfc)
|
||||
#
|
||||
# Destructive version of String#unicode_normalize, doing Unicode
|
||||
# normalization in place.
|
||||
#
|
||||
def unicode_normalize!(form = :nfc)
|
||||
replace(self.normalize(form))
|
||||
end
|
||||
|
||||
# :call-seq:
|
||||
# str.unicode_normalized?(form=:nfc)
|
||||
#
|
||||
# Checks whether +str+ is in Unicode normalization form +form+,
|
||||
# which is any of the four values :nfc, :nfd, :nfkc, or :nfkd.
|
||||
# The default is :nfc.
|
||||
#
|
||||
# If the string is not in a Unicode Encoding, then an Exception is raised.
|
||||
# For details, see String#unicode_normalize.
|
||||
#
|
||||
# _Examples_
|
||||
#
|
||||
# "a\u0300".unicode_normalized? #=> false
|
||||
# "a\u0300".unicode_normalized?(:nfd) #=> true
|
||||
# "\u00E0".unicode_normalized? #=> true
|
||||
# "\u00E0".unicode_normalized?(:nfd) #=> false
|
||||
# "\xE0".force_encoding('ISO-8859-1').unicode_normalized?
|
||||
# #=> Encoding::CompatibilityError raised
|
||||
#
|
||||
def unicode_normalized?(form = :nfc)
|
||||
UnicodeNormalize.normalized?(self, form)
|
||||
end
|
||||
|
|
Loading…
Add table
Reference in a new issue