From dcc48ad81b0dee365ae5c3694103b06615c32351 Mon Sep 17 00:00:00 2001 From: Peter Stephenson Date: Sun, 2 Oct 2005 19:13:44 +0000 Subject: minor tidy-ups --- ChangeLog | 4 +++ Src/Zle/complist.c | 3 +- Src/Zle/compmatch.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++++ Src/Zle/zle_main.c | 1 - 4 files changed, 90 insertions(+), 2 deletions(-) diff --git a/ChangeLog b/ChangeLog index d4190cfd8..4f537abe4 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,5 +1,9 @@ 2005-10-02 Peter Stephenson + * 21802: Src/Zle/complist.c, Src/Zle/compmatch.c, + Src/Zle/zle_main.c: attempt to prevent matches ending in + the middle of multibyte characters, also some minor tidy-ups. + * unposted, c.f. 21799: Doc/Zsh/func.yo: documentation for returns from TRAPNAL functions was wayward. diff --git a/Src/Zle/complist.c b/Src/Zle/complist.c index 0b6601cea..a9d57ae43 100644 --- a/Src/Zle/complist.c +++ b/Src/Zle/complist.c @@ -575,7 +575,8 @@ clnicezputs(Listcols colors, char *s, int ml) * ps is the shift state of the conversion to wide characters. */ char *ums, *uptr, *sptr, *wptr; - int ret, umleft, umlen, width; + int ret, umleft, umlen; + size_t width; mbstate_t ps; memset(&ps, 0, sizeof(ps)); diff --git a/Src/Zle/compmatch.c b/Src/Zle/compmatch.c index 7054feb6d..e4c5a438f 100644 --- a/Src/Zle/compmatch.c +++ b/Src/Zle/compmatch.c @@ -1584,6 +1584,11 @@ sub_match(Cmdata md, char *str, int len, int sfx) { int ret = 0, l, ind, add; char *p, *q; +#ifdef ZLE_UNICODE_SUPPORT + int fulllen = len; + char *fullstr = str; + mbstate_t ps; +#endif if (sfx) { str += len; @@ -1614,6 +1619,85 @@ sub_match(Cmdata md, char *str, int len, int sfx) || (l < md->len && q[-1] == Meta))) l--; } +#ifdef ZLE_UNICODE_SUPPORT + /* + * Make sure we don't end in the middle of a multibyte character. + * Don't need to do this if the match ended at the start + * of the original string. + * + * Let q be the match point we've found. + */ + q = sfx ? str - l : str + l; + if (q != fullstr) { + memset(&ps, 0, sizeof(ps)); + /* + * Otherwise read characters from the start of the original + * string until we reach or pass the match point. This + * is rather inefficient, but in general only reading + * the full string can keep track of where we are in + * a character. With a prefix we could be more efficient, + * but it's difficult with a suffix where the match point + * moves backwards. + */ + for (p = fullstr; p < fullstr + fulllen; ) { + wchar_t wc; + /* + * ret must, in fact, be set by the current logic, + * but gcc doesn't realise (at least some versions don't). + */ + int ret = -1, diff; + char *p2; + + /* + * Because the string is metafied, we need to + * assembled wide characters a byte at a time. + */ + for (p2 = p; p2 < fullstr + fulllen; p2++) { + char curchar = (*p2 == Meta) ? (*++p2 ^ 32) : *p2; + ret = mbrtowc(&wc, &curchar, 1, &ps); + /* + * Continue while character is incomplete. + */ + if (ret != -2) + break; + } + if (ret < 0) { + /* not a valid character, give up test */ + break; + } + /* increment p2 for last byte read */ + diff = ++p2 - q; + if (diff == 0) { + /* + * Prefix or suffix matches at end of multbyte character, + * so OK. + */ + break; + } else if (diff > 0) { + /* + * The prefix or suffix finishes in the middle + * of a character. Shorten it until it doesn't. + */ + if (sfx) { + /* + * We need to remove the trailing part of + * the character from the suffix. + */ + l -= diff; + } else { + /* + * We need to remove the initial part of + * the character from the prefix. + */ + l -= (q - p); + } + break; + } + /* Advance over full character */ + p += ret; + } + } +#endif if (l) { /* There was a common prefix, use it. */ md->len -= l; len -= l; diff --git a/Src/Zle/zle_main.c b/Src/Zle/zle_main.c index 683771701..591b2d585 100644 --- a/Src/Zle/zle_main.c +++ b/Src/Zle/zle_main.c @@ -758,7 +758,6 @@ getfullchar(int keytmout) mod_export ZLE_INT_T getrestchar(int inchar) { - /* char cnull = '\0'; */ char c = inchar; wchar_t outchar; int ret, timeout; -- cgit 1.4.1