\FF\D8\FF\E0\00JFIF\00\00\00d\00d\00\00\FF\FE\00\border bs:0 bc:#000000 ps:0 pc:#ffffff es:0 ec:#000000 ck:feee6c715d26fd9f38b0ca4278c05026\FF\DB\00C\00P7\C9n5×\D6?\BDê\9Ds\EBp\9F[`8m\B7)o\B5\E8\E6I\99\FE3]]A2\BA\8Cw\D6E\93\\DEv\C8\009\F2\F1NI?uc\\F5\EA\96k\xN<~buv\EA\C8\D7 \8B\84\CEcxI\BBg\AE\9E=\D6+n\EC\80\C8A\8C\AE\EB\CF\D5\DA\E9"2\A4\B9j5\EB\F3W\B63\96\B30Yu\DA\FC8\ED\DF\E7Ms\FB\F1\8E\B3\FA\EA\E8\E6(\883zs\F2_\8DFk\8Bh \00\8C\DCw\D3R\B5+6X\BA\B2\C4j\AB0\B4\FCMw\C2I\8E\9B\E3\A9~9u\FA\D3l\80\C8%p\EE\FDn2€ \00 $\FEj\C4e\A9\DB\~\95\A7\A5\80EK\BB\8DDsP\00@@AD'k\CF\E8\DB\D2(\80\9AK\D3\85\D6lb\F2\BA\8C*\80\00)\95 59\A3R:\F3\CE"\B6\80\88\00\00i1u4ê\E9\F2á\A6\A2\FACM\93WMb*\E0*\00\00\00\00\00(\A8\80\00\00\80\00\00\00\00\00\00\00\00\00\FF\D9 C/// # coding: utf-8 # frozen_string_literal: false # Copyright Ayumu Nojima (野島 æ­©) and Martin J. Dürst (duerst@it.aoyama.ac.jp) # 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, as well as GB18030, UCS_2BE, and UCS_4BE. 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) #=> 'aÌ€' (same as "a\u0300") # "\xE0".force_encoding('ISO-8859-1').unicode_normalize(:nfd) # #=> Encoding::CompatibilityError raised # def unicode_normalize(form = :nfc) require 'unicode_normalize/normalize.rb' unless defined? UnicodeNormalize ## The following line can be uncommented to avoid repeated checking for ## UnicodeNormalize. However, tests didn't show any noticeable speedup