#perl 正则匹配中文字符
#!/usr/bin/perl -w
use strict;
use warnings;
#my $a = "aligned 中国(中国中)中国心(中国心中)426327399914 frames";
my $a = 'session 0: <enter>(<enter>) 啊(啊)<exit>(<exit>) 你好(你好)请(请)讲(讲)<exit>(<exit>) (D:\hongmi\zhuxiaocheng\tbnr_phone_new_stream_onepass\bin\taobao\DVS+20121006151539406-44035.wav)';
$a =~s/D:\\hongmi\\zhuxiaocheng\\tbnr_phone_new_stream_onepass\\bin\\taobao\\/ /; $a =~s/\.wav/ /; $a =~s/session 0://g; $a =~s/\<enter\>\(\<enter\>\)//g; $a =~s/\<exit\>\(\<exit\>\)//g; print "$a\n"; my @chars = (split /\([\x80-\xFF]+?|[\x80-\xFF]+?\)/,$a); foreach my $char (@chars) { #$char =~s/D:\\hongmi\\zhuxiaocheng\\tbnr_phone_new_stream_onepass\\bin\\taobao\\//; #$char =~s/session 0://g; #$char =~s/\<enter\>\(\<enter\>\)//g; #$char =~s/\<exit\>\(\<exit\>\)//g; $char=~s/\s+//g; $char=~s/\(/ ( /g; $char=~s/\)/ ) /g; print $char; }