diff options
| -rw-r--r-- | ChangeLog | 6 | ||||
| -rw-r--r-- | Src/utils.c | 77 |
2 files changed, 37 insertions, 46 deletions
@@ -1,3 +1,9 @@ +2007-02-07 Peter Stephenson <pws@csr.com> + + * 23153: Src/utils.c: put back old ztrcmp(), with a comment: + as we're not doing strcoll() using full wide character conversion + is overkill. + 2007-02-06 Peter Stephenson <p.w.stephenson@ntlworld.com> * 23152: Src/builtin.c, Src/hashtable.c, Src/module.c, diff --git a/Src/utils.c b/Src/utils.c index eb466278d..166dad151 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -3693,61 +3693,46 @@ unmeta(const char *file_name) return fn; } -/* Unmetafy and compare two strings, comparing unsigned character values. - * "a\0" sorts after "a". */ +/* + * Unmetafy and compare two strings, comparing unsigned character values. + * "a\0" sorts after "a". + * + * Currently this is only used in hash table sorting, where the + * keys are names of hash nodes and where we don't use strcoll(); + * it's not clear if that's right but it does guarantee the ordering + * of shell structures on output. + * + * As we don't use strcoll(), it seems overkill to convert multibyte + * characters to wide characters for comparison every time. In the case + * of UTF-8, Unicode ordering is preserved when sorted raw, and for + * other character sets we rely on an extension of ASCII so the result, + * while it may not be correct, is at least rational. + */ /**/ int ztrcmp(char const *s1, char const *s2) { - convchar_t c1 = 0, c2; - -#ifdef MULTIBYTE_SUPPORT - if (isset(MULTIBYTE)) { - mb_metacharinit(); - while (*s1) { - int clen = mb_metacharlenconv(s1, &c1); - - if (strncmp(s1, s2, clen)) - break; - s1 += clen; - s2 += clen; - } - } else -#endif - while (*s1 && *s1 == *s2) { - s1++; - s2++; - } + int c1, c2; - if (!*s1) { - if (!*s2) - return 0; - return -1; - } - if (!*s2) - return 1; -#ifdef MULTIBYTE_SUPPORT - if (isset(MULTIBYTE)) { - /* TODO: shift state for s2 might be wrong? */ - mb_metacharinit(); - (void)mb_metacharlenconv(s2, &c2); - if (c1 == WEOF) - c1 = STOUC(*s1 == Meta ? s1[1] ^ 32 : *s1); - if (c2 == WEOF) - c2 = STOUC(*s2 == Meta ? s2[1] ^ 32 : *s2); - } - else -#endif - { - c1 = STOUC(*s1 == Meta ? s1[1] ^ 32 : *s1); - c2 = STOUC(*s2 == Meta ? s2[1] ^ 32 : *s2); + while(*s1 && *s1 == *s2) { + s1++; + s2++; } - if (c1 < c2) - return -1; - else if (c1 == c2) + if(!(c1 = *s1)) + c1 = -1; + else if(c1 == STOUC(Meta)) + c1 = *++s1 ^ 32; + if(!(c2 = *s2)) + c2 = -1; + else if(c2 == STOUC(Meta)) + c2 = *++s2 ^ 32; + + if(c1 == c2) return 0; + else if(c1 < c2) + return -1; else return 1; } |