ruby-changes:2736
From: ko1@a...
Date: 14 Dec 2007 17:37:56 +0900
Subject: [ruby-changes:2736] matz - Ruby:r14227 (trunk): * string.c (rb_str_cmp): encoding aware comparison.
matz 2007-12-14 17:37:39 +0900 (Fri, 14 Dec 2007) New Revision: 14227 Modified files: trunk/ChangeLog trunk/string.c Log: * string.c (rb_str_cmp): encoding aware comparison. * string.c (rb_str_casecmp): ditto. http://svn.ruby-lang.org/cgi-bin/viewvc.cgi/trunk/string.c?r1=14227&r2=14226 http://svn.ruby-lang.org/cgi-bin/viewvc.cgi/trunk/ChangeLog?r1=14227&r2=14226 Index: ChangeLog =================================================================== --- ChangeLog (revision 14226) +++ ChangeLog (revision 14227) @@ -1,3 +1,9 @@ +Fri Dec 14 16:06:18 2007 Yukihiro Matsumoto <matz@r...> + + * string.c (rb_str_cmp): encoding aware comparison. + + * string.c (rb_str_casecmp): ditto. + Fri Dec 14 13:47:54 2007 Nobuyoshi Nakada <nobu@r...> * common.mk (ruby.imp): fix for circular dependency. a patch from Index: string.c =================================================================== --- string.c (revision 14226) +++ string.c (revision 14227) @@ -118,7 +118,7 @@ while (p < e) { int c = (unsigned char)*p; - if (!isascii(c)) { + if (!rb_enc_isascii(c, enc)) { cr = ENC_CODERANGE_8BIT; break; } @@ -1276,12 +1276,18 @@ { long len; int retval; + rb_encoding *enc; - rb_enc_check(str1, str2); /* xxxx error-less encoding check? */ + enc = rb_enc_compatible(str1, str2); len = lesser(RSTRING_LEN(str1), RSTRING_LEN(str2)); retval = memcmp(RSTRING_PTR(str1), RSTRING_PTR(str2), len); if (retval == 0) { - if (RSTRING_LEN(str1) == RSTRING_LEN(str2)) return 0; + if (RSTRING_LEN(str1) == RSTRING_LEN(str2)) { + if (!enc) { + return rb_enc_get_index(str1) - rb_enc_get_index(str2); + } + return 0; + } if (RSTRING_LEN(str1) > RSTRING_LEN(str2)) return 1; return -1; } @@ -1404,19 +1410,35 @@ static VALUE rb_str_casecmp(VALUE str1, VALUE str2) { - long len; + long i, len; int retval; + rb_encoding *enc; + char *p1, *p1end, *p2, *p2end; StringValue(str2); - len = lesser(RSTRING_LEN(str1), RSTRING_LEN(str2)); - retval = rb_memcicmp(RSTRING_PTR(str1), RSTRING_PTR(str2), len); - if (retval == 0) { - if (RSTRING_LEN(str1) == RSTRING_LEN(str2)) return INT2FIX(0); - if (RSTRING_LEN(str1) > RSTRING_LEN(str2)) return INT2FIX(1); - return INT2FIX(-1); + enc = rb_enc_compatible(str1, str2); + if (!enc) { + return rb_str_cmp(str1, str2); } - if (retval == 0) return INT2FIX(0); - if (retval > 0) return INT2FIX(1); + + p1 = RSTRING_PTR(str1); p1end = RSTRING_END(p1); + p2 = RSTRING_PTR(str2); p2end = RSTRING_END(str2); + while (p1 < p1end && p2 < p2end) { + int c1 = rb_enc_codepoint(p1, p1end, enc); + int c2 = rb_enc_codepoint(p2, p2end, enc); + + if (c1 != c2) { + c1 = rb_enc_toupper(c1, enc); + c2 = rb_enc_toupper(c2, enc); + if (c1 > c2) return INT2FIX(1); + if (c1 < c2) return INT2FIX(-1); + } + len = rb_enc_codelen(c1, enc); + p1 += len; + p2 += len; + } + if (RSTRING_LEN(str1) == RSTRING_LEN(str2)) return INT2FIX(0); + if (RSTRING_LEN(str1) > RSTRING_LEN(str2)) return INT2FIX(1); return INT2FIX(-1); } @@ -1834,7 +1856,7 @@ while ((s = rb_enc_prev_char(sbeg, s, enc)) != 0) { cc = rb_enc_codepoint(s, e, enc); if (rb_enc_isalnum(cc, enc)) { - if (isascii(cc)) { + if (rb_enc_isascii(cc, enc)) { if ((c = succ_char(s)) == 0) break; } else { -- ML: ruby-changes@q... Info: http://www.atdot.net/~ko1/quickml