From f3f8537cfa05414ad14494e809d9ebfeef86ebbc Mon Sep 17 00:00:00 2001 From: Peter Stephenson Date: Tue, 7 Mar 2017 10:43:58 +0000 Subject: 40760: Always tokenize unquoted - to Dash. This fixes use of pattern match character ranges in unusual contexts. Attempt to detect a tokenized - in cases where we don't care. --- Src/utils.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'Src/utils.c') diff --git a/Src/utils.c b/Src/utils.c index 7f3ddad40..9669944f6 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -2376,7 +2376,7 @@ zstrtol_underscore(const char *s, char **t, int base, int underscore) while (inblank(*s)) s++; - if ((neg = (*s == '-'))) + if ((neg = IS_DASH(*s))) s++; else if (*s == '+') s++; @@ -6118,7 +6118,9 @@ quotedzputs(char const *s, FILE *stream) } else *ptr++ = '\''; while(*s) { - if (*s == Meta) + if (*s == Dash) + c = '-'; + else if (*s == Meta) c = *++s ^ 32; else c = *s; @@ -6155,7 +6157,9 @@ quotedzputs(char const *s, FILE *stream) } else { /* use Bourne-style quoting, avoiding empty quoted strings */ while (*s) { - if (*s == Meta) + if (*s == Dash) + c = '-'; + else if (*s == Meta) c = *++s ^ 32; else c = *s; -- cgit v1.2.3 From 071017965f469c88b10467205f30ea3e609e56dc Mon Sep 17 00:00:00 2001 From: "Barton E. Schaefer" Date: Wed, 8 Mar 2017 21:26:55 -0800 Subject: 40763: count wide characters and Cmatcher pointers more sanely in cfp_matcher_pats(), and count characters in pattern_match() the same way to stay in sync Might not fix wide-char matching in completion matcher-lists but should avoid wild pointer crash --- ChangeLog | 8 ++++++++ Src/Zle/compmatch.c | 57 +++++------------------------------------------------ Src/Zle/computil.c | 19 ++++++++++++------ Src/utils.c | 42 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 68 insertions(+), 58 deletions(-) (limited to 'Src/utils.c') diff --git a/ChangeLog b/ChangeLog index 4219b1510..65ef5cc90 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,11 @@ +2017-03-08 Barton E. Schaefer + + * 40763: Src/Zle/compmatch.c, Src/Zle/computil.c, Src/utils.c: + count wide characters and Cmatcher pointers more sanely in + cfp_matcher_pats(), and count characters in pattern_match() + the same way to stay in sync; might not fix wide-char matching + in completion matcher-lists but should avoid wild pointer crash + 2017-03-08 Daniel Shahaf * 40745 + 40753: Src/init.c, Src/params.c: Fix 'unset diff --git a/Src/Zle/compmatch.c b/Src/Zle/compmatch.c index aedf463fc..1cdbb8a48 100644 --- a/Src/Zle/compmatch.c +++ b/Src/Zle/compmatch.c @@ -1548,27 +1548,11 @@ pattern_match(Cpattern p, char *s, Cpattern wp, char *ws) { convchar_t c, wc; convchar_t ind, wind; - int len = 0, wlen, mt, wmt; -#ifdef MULTIBYTE_SUPPORT - mbstate_t lstate, wstate; - - memset(&lstate, 0, sizeof(lstate)); - memset(&wstate, 0, sizeof(wstate)); -#endif + int len = 0, wlen = 0, mt, wmt; while (p && wp && *s && *ws) { /* First test the word character */ -#ifdef MULTIBYTE_SUPPORT - wlen = mb_metacharlenconv_r(ws, &wc, &wstate); -#else - if (*ws == Meta) { - wc = STOUC(ws[1]) ^ 32; - wlen = 2; - } else { - wc = STOUC(*ws); - wlen = 1; - } -#endif + wc = unmeta_one(ws, &wlen); wind = pattern_match1(wp, wc, &wmt); if (!wind) return 0; @@ -1576,18 +1560,7 @@ pattern_match(Cpattern p, char *s, Cpattern wp, char *ws) /* * Now the line character. */ -#ifdef MULTIBYTE_SUPPORT - len = mb_metacharlenconv_r(s, &c, &lstate); -#else - /* We have the character itself. */ - if (*s == Meta) { - c = STOUC(s[1]) ^ 32; - len = 2; - } else { - c = STOUC(*s); - len = 1; - } -#endif + c = unmeta_one(s, &len); /* * If either is "?", they match each other; no further tests. * Apply this even if the character wasn't convertable; @@ -1627,17 +1600,7 @@ pattern_match(Cpattern p, char *s, Cpattern wp, char *ws) } while (p && *s) { -#ifdef MULTIBYTE_SUPPORT - len = mb_metacharlenconv_r(s, &c, &lstate); -#else - if (*s == Meta) { - c = STOUC(s[1]) ^ 32; - len = 2; - } else { - c = STOUC(*s); - len = 1; - } -#endif + c = unmeta_one(s, &len); if (!pattern_match1(p, c, &mt)) return 0; p = p->next; @@ -1645,17 +1608,7 @@ pattern_match(Cpattern p, char *s, Cpattern wp, char *ws) } while (wp && *ws) { -#ifdef MULTIBYTE_SUPPORT - wlen = mb_metacharlenconv_r(ws, &wc, &wstate); -#else - if (*ws == Meta) { - wc = STOUC(ws[1]) ^ 32; - wlen = 2; - } else { - wc = STOUC(*ws); - wlen = 1; - } -#endif + wc = unmeta_one(ws, &wlen); if (!pattern_match1(wp, wc, &wmt)) return 0; wp = wp->next; diff --git a/Src/Zle/computil.c b/Src/Zle/computil.c index 325da6ddb..e704f9ffa 100644 --- a/Src/Zle/computil.c +++ b/Src/Zle/computil.c @@ -4465,17 +4465,24 @@ cfp_matcher_pats(char *matcher, char *add) if (m && m != pcm_err) { char *tmp; int al = strlen(add), zl = ztrlen(add), tl, cl; - VARARR(Cmatcher, ms, zl); + VARARR(Cmatcher, ms, zl); /* One Cmatcher per character */ Cmatcher *mp; Cpattern stopp; int stopl = 0; + /* zl >= (number of wide characters) is guaranteed */ memset(ms, 0, zl * sizeof(Cmatcher)); for (; m && *add; m = m->next) { stopp = NULL; if (!(m->flags & (CMF_LEFT|CMF_RIGHT))) { if (m->llen == 1 && m->wlen == 1) { + /* + * In this loop and similar loops below we step + * through tmp one (possibly wide) character at a + * time. pattern_match() compares only the first + * character using unmeta_one() so keep in step. + */ for (tmp = add, tl = al, mp = ms; tl; ) { if (pattern_match(m->line, tmp, NULL, NULL)) { if (*mp) { @@ -4485,10 +4492,10 @@ cfp_matcher_pats(char *matcher, char *add) } else *mp = m; } - cl = (*tmp == Meta) ? 2 : 1; + (void) unmeta_one(tmp, &cl); tl -= cl; tmp += cl; - mp += cl; + mp++; } } else { stopp = m->line; @@ -4505,10 +4512,10 @@ cfp_matcher_pats(char *matcher, char *add) } else *mp = m; } - cl = (*tmp == Meta) ? 2 : 1; + (void) unmeta_one(tmp, &cl); tl -= cl; tmp += cl; - mp += cl; + mp++; } } else if (m->llen) { stopp = m->line; @@ -4531,7 +4538,7 @@ cfp_matcher_pats(char *matcher, char *add) al = tmp - add; break; } - cl = (*tmp == Meta) ? 2 : 1; + (void) unmeta_one(tmp, &cl); tl -= cl; tmp += cl; } diff --git a/Src/utils.c b/Src/utils.c index 9669944f6..b3fa3d24c 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -4787,6 +4787,48 @@ unmeta(const char *file_name) return fn; } +/* + * Unmetafy just one character and store the number of bytes it occupied. + */ +/**/ +mod_export convchar_t +unmeta_one(const char *in, int *sz) +{ + convchar_t wc; + int newsz; +#ifdef MULTIBYTE_SUPPORT + int ulen; + mbstate_t wstate; +#endif + + if (!sz) + sz = &newsz; + *sz = 0; + + if (!in || !*in) + return 0; + +#ifdef MULTIBYTE_SUPPORT + memset(&wstate, 0, sizeof(wstate)); + ulen = mb_metacharlenconv_r(in, &wc, &wstate); + while (ulen-- > 0) { + if (in[*sz] == Meta) + *sz += 2; + else + *sz += 1; + } +#else + if (in[0] == Meta) { + *sz = 2; + wc = STOUC(in[1] ^ 32); + } else { + *sz = 1; + wc = STOUC(in[0]); + } +#endif + return wc; +} + /* * Unmetafy and compare two strings, comparing unsigned character values. * "a\0" sorts after "a". -- cgit v1.2.3 From a11b241d4a5ec7ee1009905372cf32fb4538fbb3 Mon Sep 17 00:00:00 2001 From: Orlov Sergey Date: Tue, 4 Apr 2017 22:43:47 +0300 Subject: 40935: User names need metafying. On some systems they can contain 8-bit characters and on all systems this is logically correct anyway. --- ChangeLog | 5 +++++ Src/utils.c | 6 +++--- 2 files changed, 8 insertions(+), 3 deletions(-) (limited to 'Src/utils.c') diff --git a/ChangeLog b/ChangeLog index b232c16af..828b7064f 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,8 @@ +2017-04-10 Peter Stephenson + + * Orlov Sergey: 40935: Src/utils.c: User names need metafying as + they can contain multibyte characters on some systems. + 2017-04-07 Bart Schaefer * 40940: Src/cond.c: untokenize names of condition features diff --git a/Src/utils.c b/Src/utils.c index b3fa3d24c..9701ea78a 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -1230,13 +1230,13 @@ adduserdir(char *s, char *t, int flags, int always) * named directory, since these are sometimes used for * special purposes. */ - nd->dir = ztrdup(t); + nd->dir = metafy(t, -1, META_DUP); } else - nd->dir = ztrduppfx(t, eptr - t); + nd->dir = metafy(t, eptr - t, META_DUP); /* The variables PWD and OLDPWD are not to be displayed as ~PWD etc. */ if (!strcmp(s, "PWD") || !strcmp(s, "OLDPWD")) nd->node.flags |= ND_NOABBREV; - nameddirtab->addnode(nameddirtab, ztrdup(s), nd); + nameddirtab->addnode(nameddirtab, metafy(s, -1, META_DUP), nd); } /* Get a named directory: this function can cause a directory name * -- cgit v1.2.3 From 3c78f14d5cfe98cb567cced9cfe283cb890155ef Mon Sep 17 00:00:00 2001 From: Jun-ichi Takimoto Date: Sun, 23 Apr 2017 23:58:44 +0900 Subject: 40994: unmeta_one() need not count Meta --- ChangeLog | 4 ++++ Src/utils.c | 9 +-------- 2 files changed, 5 insertions(+), 8 deletions(-) (limited to 'Src/utils.c') diff --git a/ChangeLog b/ChangeLog index 6566d23e8..00aebbb83 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,7 @@ +2017-04-23 Jun-ichi Takimoto + + * 40994: Src/utils.c: unmeta_one() need not count Meta + 2017-04-21 Peter Stephenson * 40990: Src/params.c: When starting in sh emulation, don't diff --git a/Src/utils.c b/Src/utils.c index 9701ea78a..ea4b34bab 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -4797,7 +4797,6 @@ unmeta_one(const char *in, int *sz) convchar_t wc; int newsz; #ifdef MULTIBYTE_SUPPORT - int ulen; mbstate_t wstate; #endif @@ -4810,13 +4809,7 @@ unmeta_one(const char *in, int *sz) #ifdef MULTIBYTE_SUPPORT memset(&wstate, 0, sizeof(wstate)); - ulen = mb_metacharlenconv_r(in, &wc, &wstate); - while (ulen-- > 0) { - if (in[*sz] == Meta) - *sz += 2; - else - *sz += 1; - } + *sz = mb_metacharlenconv_r(in, &wc, &wstate); #else if (in[0] == Meta) { *sz = 2; -- cgit v1.2.3 From c7a9cf465dd620ef48d586026944d9bd7a0d5d6d Mon Sep 17 00:00:00 2001 From: Peter Stephenson Date: Tue, 9 May 2017 17:49:18 +0100 Subject: 40181: Fix buffer overrun in xsymlinks. There was no check for copying to the internal xbuf2 for a preliminary test. --- ChangeLog | 3 +++ Src/utils.c | 14 +++++++++++--- Test/D02glob.ztst | 8 ++++++++ 3 files changed, 22 insertions(+), 3 deletions(-) (limited to 'Src/utils.c') diff --git a/ChangeLog b/ChangeLog index 82d4a7086..ee6e918db 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,5 +1,8 @@ 2017-05-09 Peter Stephenson + * 41081: Src/utils.c, Test/D02glob.ztst: Symlink expansion + didn't test all buffer length calculations. + * 41078: Src/prompt.c, Test/D01prompt.ztst: Empty psvar could cause bad reference in prompt expansion. diff --git a/Src/utils.c b/Src/utils.c index ea4b34bab..5eb936bed 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -886,7 +886,7 @@ xsymlinks(char *s, int full) char **pp, **opp; char xbuf2[PATH_MAX*3+1], xbuf3[PATH_MAX*2+1]; int t0, ret = 0; - zulong xbuflen = strlen(xbuf); + zulong xbuflen = strlen(xbuf), pplen; opp = pp = slashsplit(s); for (; xbuflen < sizeof(xbuf) && *pp && ret >= 0; pp++) { @@ -907,10 +907,18 @@ xsymlinks(char *s, int full) xbuflen--; continue; } - sprintf(xbuf2, "%s/%s", xbuf, *pp); + /* Includes null byte. */ + pplen = strlen(*pp) + 1; + if (xbuflen + pplen + 1 > sizeof(xbuf2)) { + *xbuf = 0; + ret = -1; + break; + } + memcpy(xbuf2, xbuf, xbuflen); + xbuf2[xbuflen] = '/'; + memcpy(xbuf2 + xbuflen + 1, *pp, pplen); t0 = readlink(unmeta(xbuf2), xbuf3, PATH_MAX); if (t0 == -1) { - zulong pplen = strlen(*pp) + 1; if ((xbuflen += pplen) < sizeof(xbuf)) { strcat(xbuf, "/"); strcat(xbuf, *pp); diff --git a/Test/D02glob.ztst b/Test/D02glob.ztst index 413381f92..0ff696807 100644 --- a/Test/D02glob.ztst +++ b/Test/D02glob.ztst @@ -687,6 +687,14 @@ 0:modifier ':P' resolves symlinks before '..' components *>*glob.tmp/hello/world + # This is a bit brittle as it depends on PATH_MAX. + # We could use sysconf.. + bad_pwd="/${(l:16000:: :):-}" + print ${bad_pwd:P} +0:modifier ':P' with path too long +?(eval):2: path expansion failed, using root directory +>/ + foo=a value="ac" print ${value//[${foo}b-z]/x} -- cgit v1.2.3 From 171e7fa4c1d9cbf0d8ff35ee795e1599913aa329 Mon Sep 17 00:00:00 2001 From: Jun-ichi Takimoto Date: Fri, 12 May 2017 12:10:13 +0900 Subject: 41090: Replace iswprint() if unicode9 is enabled. If wcwidth() or iswprint() is broken, force enable unicode9. --- ChangeLog | 7 ++ Src/Zle/zle_refresh.c | 8 +- Src/compat.c | 322 +------------------------------------------------- Src/pattern.c | 2 +- Src/utils.c | 4 +- Src/wcwidth9.h | 6 +- Src/zsh.h | 12 +- Src/ztype.h | 6 +- configure.ac | 40 ++++--- 9 files changed, 56 insertions(+), 351 deletions(-) (limited to 'Src/utils.c') diff --git a/ChangeLog b/ChangeLog index 670fc9d89..e608b167f 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,10 @@ +2017-05-12 Jun-ichi Takimoto + + * 41090: Src/Zle/zle_refresh.c, Src/compat.c, Src/pattern.c, + Src/utils.c, Src/wcwidth9.h, Src/zsh.h, Src/ztype.h, + configure.ac: Replace iswprint() if unicode9 support is enabled. + Enable unicode9 if wcwidth() and/or iswprint() is broken. + 2017-05-11 Peter Stephenson * 41096: Src/string.c: Fix dupstring_wlen() for unmetafied diff --git a/Src/Zle/zle_refresh.c b/Src/Zle/zle_refresh.c index 83917396a..d0dd1ef06 100644 --- a/Src/Zle/zle_refresh.c +++ b/Src/Zle/zle_refresh.c @@ -1278,7 +1278,7 @@ zrefresh(void) #ifdef __STDC_ISO_10646__ !ZSH_INVALID_WCHAR_TEST(*t) && #endif - iswprint(*t) && (width = WCWIDTH(*t)) > 0) { + WC_ISPRINT(*t) && (width = WCWIDTH(*t)) > 0) { int ichars; if (width > rpms.sen - rpms.s) { int started = 0; @@ -1460,7 +1460,7 @@ zrefresh(void) u = outputline; for (; u < outputline + outll; u++) { #ifdef MULTIBYTE_SUPPORT - if (iswprint(*u)) { + if (WC_ISPRINT(*u)) { int width = WCWIDTH(*u); /* Handle wide characters as above */ if (width > rpms.sen - rpms.s) { @@ -2468,7 +2468,7 @@ singlerefresh(ZLE_STRING_T tmpline, int tmpll, int tmpcs) if (tmpline[t0] == ZWC('\t')) vsiz = (vsiz | 7) + 2; #ifdef MULTIBYTE_SUPPORT - else if (iswprint(tmpline[t0]) && ((width = WCWIDTH(tmpline[t0])) > 0)) { + else if (WC_ISPRINT(tmpline[t0]) && ((width = WCWIDTH(tmpline[t0])) > 0)) { vsiz += width; if (isset(COMBININGCHARS) && IS_BASECHAR(tmpline[t0])) { while (t0 < tmpll-1 && IS_COMBINING(tmpline[t0+1])) @@ -2556,7 +2556,7 @@ singlerefresh(ZLE_STRING_T tmpline, int tmpll, int tmpcs) vp->atr = all_atr_on | all_atr_off; vp++; #ifdef MULTIBYTE_SUPPORT - } else if (iswprint(tmpline[t0]) && + } else if (WC_ISPRINT(tmpline[t0]) && (width = WCWIDTH(tmpline[t0])) > 0) { int ichars; if (isset(COMBININGCHARS) && IS_BASECHAR(tmpline[t0])) { diff --git a/Src/compat.c b/Src/compat.c index a2956946f..a130d9264 100644 --- a/Src/compat.c +++ b/Src/compat.c @@ -672,7 +672,7 @@ strtoul(nptr, endptr, base) /**/ int -mk_wcwidth(wchar_t ucs) +u9_wcwidth(wchar_t ucs) { int w = wcwidth9(ucs); if (w < -1) @@ -680,327 +680,17 @@ mk_wcwidth(wchar_t ucs) return w; } -/**/ -#elif defined(BROKEN_WCWIDTH) && (defined(__STDC_ISO_10646__) || defined(__APPLE__)) - -/* - * This is an implementation of wcwidth() and wcswidth() (defined in - * IEEE Std 1002.1-2001) for Unicode. - * - * http://www.opengroup.org/onlinepubs/007904975/functions/wcwidth.html - * http://www.opengroup.org/onlinepubs/007904975/functions/wcswidth.html - * - * In fixed-width output devices, Latin characters all occupy a single - * "cell" position of equal width, whereas ideographic CJK characters - * occupy two such cells. Interoperability between terminal-line - * applications and (teletype-style) character terminals using the - * UTF-8 encoding requires agreement on which character should advance - * the cursor by how many cell positions. No established formal - * standards exist at present on which Unicode character shall occupy - * how many cell positions on character terminals. These routines are - * a first attempt of defining such behavior based on simple rules - * applied to data provided by the Unicode Consortium. - * - * For some graphical characters, the Unicode standard explicitly - * defines a character-cell width via the definition of the East Asian - * FullWidth (F), Wide (W), Half-width (H), and Narrow (Na) classes. - * In all these cases, there is no ambiguity about which width a - * terminal shall use. For characters in the East Asian Ambiguous (A) - * class, the width choice depends purely on a preference of backward - * compatibility with either historic CJK or Western practice. - * Choosing single-width for these characters is easy to justify as - * the appropriate long-term solution, as the CJK practice of - * displaying these characters as double-width comes from historic - * implementation simplicity (8-bit encoded characters were displayed - * single-width and 16-bit ones double-width, even for Greek, - * Cyrillic, etc.) and not any typographic considerations. - * - * Much less clear is the choice of width for the Not East Asian - * (Neutral) class. Existing practice does not dictate a width for any - * of these characters. It would nevertheless make sense - * typographically to allocate two character cells to characters such - * as for instance EM SPACE or VOLUME INTEGRAL, which cannot be - * represented adequately with a single-width glyph. The following - * routines at present merely assign a single-cell width to all - * neutral characters, in the interest of simplicity. This is not - * entirely satisfactory and should be reconsidered before - * establishing a formal standard in this area. At the moment, the - * decision which Not East Asian (Neutral) characters should be - * represented by double-width glyphs cannot yet be answered by - * applying a simple rule from the Unicode database content. Setting - * up a proper standard for the behavior of UTF-8 character terminals - * will require a careful analysis not only of each Unicode character, - * but also of each presentation form, something the author of these - * routines has avoided to do so far. - * - * http://www.unicode.org/unicode/reports/tr11/ - * - * Markus Kuhn -- 2007-05-26 (Unicode 5.0) - * - * Permission to use, copy, modify, and distribute this software - * for any purpose and without fee is hereby granted. The author - * disclaims all warranties with regard to this software. - * - * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c - */ - -struct interval { - int first; - int last; -}; - -/* auxiliary function for binary search in interval table */ -static int bisearch(wchar_t ucs, const struct interval *table, int max) { - int min = 0; - int mid; - - if (ucs < table[0].first || ucs > table[max].last) - return 0; - while (max >= min) { - mid = (min + max) / 2; - if (ucs > table[mid].last) - min = mid + 1; - else if (ucs < table[mid].first) - max = mid - 1; - else - return 1; - } - - return 0; -} - - -/* The following two functions define the column width of an ISO 10646 - * character as follows: - * - * - The null character (U+0000) has a column width of 0. - * - * - Other C0/C1 control characters and DEL will lead to a return - * value of -1. - * - * - Non-spacing and enclosing combining characters (general - * category code Mn or Me in the Unicode database) have a - * column width of 0. - * - * - SOFT HYPHEN (U+00AD) has a column width of 1. - * - * - Other format characters (general category code Cf in the Unicode - * database) and ZERO WIDTH SPACE (U+200B) have a column width of 0. - * - * - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF) - * have a column width of 0. - * - * - Spacing characters in the East Asian Wide (W) or East Asian - * Full-width (F) category as defined in Unicode Technical - * Report #11 have a column width of 2. - * - * - All remaining characters (including all printable - * ISO 8859-1 and WGL4 characters, Unicode control characters, - * etc.) have a column width of 1. - * - * This implementation assumes that wchar_t characters are encoded - * in ISO 10646. - */ - /**/ int -mk_wcwidth(wchar_t ucs) -{ - /* sorted list of non-overlapping intervals of non-spacing characters */ - /* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */ - static const struct interval combining[] = { - { 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 }, - { 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, - { 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 }, - { 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 }, - { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, - { 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A }, - { 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 }, - { 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D }, - { 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 }, - { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD }, - { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C }, - { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D }, - { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC }, - { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD }, - { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C }, - { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D }, - { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 }, - { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 }, - { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC }, - { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD }, - { 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D }, - { 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 }, - { 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E }, - { 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC }, - { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 }, - { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E }, - { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 }, - { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 }, - { 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 }, - { 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F }, - { 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 }, - { 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD }, - { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD }, - { 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 }, - { 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B }, - { 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 }, - { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 }, - { 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF }, - { 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 }, - { 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F }, - { 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B }, - { 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F }, - { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB }, - { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F }, - { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 }, - { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD }, - { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F }, - { 0xE0100, 0xE01EF } - }; - - /* test for 8-bit control characters */ - if (ucs == 0) - return 0; - if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0)) - return -1; - - /* binary search in table of non-spacing characters */ - if (bisearch(ucs, combining, - sizeof(combining) / sizeof(struct interval) - 1)) - return 0; - - /* if we arrive here, ucs is not a combining or C0/C1 control character */ - - return 1 + - (ucs >= 0x1100 && - (ucs <= 0x115f || /* Hangul Jamo init. consonants */ - ucs == 0x2329 || ucs == 0x232a || - (ucs >= 0x2e80 && ucs <= 0xa4cf && - ucs != 0x303f) || /* CJK ... Yi */ - (ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */ - (ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */ - (ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */ - (ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */ - (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */ - (ucs >= 0xffe0 && ucs <= 0xffe6) || - (ucs >= 0x20000 && ucs <= 0x2fffd) || - (ucs >= 0x30000 && ucs <= 0x3fffd))); -} - - -/* - * The following functions are part of the original wcwidth.c: - * we don't use them but I've kept them in case - pws. - */ -#if 0 -int mk_wcswidth(const wchar_t *pwcs, size_t n) -{ - int w, width = 0; - - for (;*pwcs && n-- > 0; pwcs++) - if ((w = mk_wcwidth(*pwcs)) < 0) - return -1; - else - width += w; - - return width; -} - - -/* - * The following functions are the same as mk_wcwidth() and - * mk_wcswidth(), except that spacing characters in the East Asian - * Ambiguous (A) category as defined in Unicode Technical Report #11 - * have a column width of 2. This variant might be useful for users of - * CJK legacy encodings who want to migrate to UCS without changing - * the traditional terminal character-width behaviour. It is not - * otherwise recommended for general use. - */ -int mk_wcwidth_cjk(wchar_t ucs) +u9_iswprint(wint_t ucs) { - /* sorted list of non-overlapping intervals of East Asian Ambiguous - * characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */ - static const struct interval ambiguous[] = { - { 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 }, - { 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 }, - { 0x00B6, 0x00BA }, { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 }, - { 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 }, - { 0x00E6, 0x00E6 }, { 0x00E8, 0x00EA }, { 0x00EC, 0x00ED }, - { 0x00F0, 0x00F0 }, { 0x00F2, 0x00F3 }, { 0x00F7, 0x00FA }, - { 0x00FC, 0x00FC }, { 0x00FE, 0x00FE }, { 0x0101, 0x0101 }, - { 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011B, 0x011B }, - { 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 }, - { 0x0138, 0x0138 }, { 0x013F, 0x0142 }, { 0x0144, 0x0144 }, - { 0x0148, 0x014B }, { 0x014D, 0x014D }, { 0x0152, 0x0153 }, - { 0x0166, 0x0167 }, { 0x016B, 0x016B }, { 0x01CE, 0x01CE }, - { 0x01D0, 0x01D0 }, { 0x01D2, 0x01D2 }, { 0x01D4, 0x01D4 }, - { 0x01D6, 0x01D6 }, { 0x01D8, 0x01D8 }, { 0x01DA, 0x01DA }, - { 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 }, - { 0x02C4, 0x02C4 }, { 0x02C7, 0x02C7 }, { 0x02C9, 0x02CB }, - { 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, { 0x02D8, 0x02DB }, - { 0x02DD, 0x02DD }, { 0x02DF, 0x02DF }, { 0x0391, 0x03A1 }, - { 0x03A3, 0x03A9 }, { 0x03B1, 0x03C1 }, { 0x03C3, 0x03C9 }, - { 0x0401, 0x0401 }, { 0x0410, 0x044F }, { 0x0451, 0x0451 }, - { 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 }, - { 0x201C, 0x201D }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 }, - { 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 }, - { 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 }, - { 0x207F, 0x207F }, { 0x2081, 0x2084 }, { 0x20AC, 0x20AC }, - { 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 }, - { 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 }, - { 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 }, - { 0x215B, 0x215E }, { 0x2160, 0x216B }, { 0x2170, 0x2179 }, - { 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, { 0x21D2, 0x21D2 }, - { 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, { 0x2200, 0x2200 }, - { 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B }, - { 0x220F, 0x220F }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 }, - { 0x221A, 0x221A }, { 0x221D, 0x2220 }, { 0x2223, 0x2223 }, - { 0x2225, 0x2225 }, { 0x2227, 0x222C }, { 0x222E, 0x222E }, - { 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 }, - { 0x224C, 0x224C }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 }, - { 0x2264, 0x2267 }, { 0x226A, 0x226B }, { 0x226E, 0x226F }, - { 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 }, - { 0x2299, 0x2299 }, { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF }, - { 0x2312, 0x2312 }, { 0x2460, 0x24E9 }, { 0x24EB, 0x254B }, - { 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 }, - { 0x25A0, 0x25A1 }, { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 }, - { 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, { 0x25C0, 0x25C1 }, - { 0x25C6, 0x25C8 }, { 0x25CB, 0x25CB }, { 0x25CE, 0x25D1 }, - { 0x25E2, 0x25E5 }, { 0x25EF, 0x25EF }, { 0x2605, 0x2606 }, - { 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 }, - { 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 }, - { 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 }, - { 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F }, - { 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xE000, 0xF8FF }, - { 0xFFFD, 0xFFFD }, { 0xF0000, 0xFFFFD }, { 0x100000, 0x10FFFD } - }; - - /* binary search in table of non-spacing characters */ - if (bisearch(ucs, ambiguous, - sizeof(ambiguous) / sizeof(struct interval) - 1)) - return 2; - - return mk_wcwidth(ucs); + if (ucs == 0) + return 0; + return wcwidth9(ucs) != -1; } - -int mk_wcswidth_cjk(const wchar_t *pwcs, size_t n) -{ - int w, width = 0; - - for (;*pwcs && n-- > 0; pwcs++) - if ((w = mk_wcwidth_cjk(*pwcs)) < 0) - return -1; - else - width += w; - - return width; -} -#endif /* 0 */ - /**/ -#endif /* BROKEN_WCWIDTH && (__STDC_ISO_10646__ || __APPLE__) */ +#endif /* ENABLE_UNICODE9 */ /**/ #if defined(__APPLE__) && defined(BROKEN_ISPRINT) diff --git a/Src/pattern.c b/Src/pattern.c index 75db01634..fc7c73739 100644 --- a/Src/pattern.c +++ b/Src/pattern.c @@ -3625,7 +3625,7 @@ mb_patmatchrange(char *range, wchar_t ch, int zmb_ind, wint_t *indptr, int *mtp) return 1; break; case PP_PRINT: - if (iswprint(ch)) + if (WC_ISPRINT(ch)) return 1; break; case PP_PUNCT: diff --git a/Src/utils.c b/Src/utils.c index 5eb936bed..acb891d82 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -629,7 +629,7 @@ wcs_nicechar_sel(wchar_t c, size_t *widthp, char **swidep, int quotable) } s = buf; - if (!iswprint(c) && (c < 0x80 || !isset(PRINTEIGHTBIT))) { + if (!WC_ISPRINT(c) && (c < 0x80 || !isset(PRINTEIGHTBIT))) { if (c == 0x7f) { if (quotable) { *s++ = '\\'; @@ -734,7 +734,7 @@ wcs_nicechar(wchar_t c, size_t *widthp, char **swidep) /**/ mod_export int is_wcs_nicechar(wchar_t c) { - if (!iswprint(c) && (c < 0x80 || !isset(PRINTEIGHTBIT))) { + if (!WC_ISPRINT(c) && (c < 0x80 || !isset(PRINTEIGHTBIT))) { if (c == 0x7f || c == L'\n' || c == L'\t' || c < 0x20) return 1; if (c >= 0x80) { diff --git a/Src/wcwidth9.h b/Src/wcwidth9.h index 07e6bae1c..448f548e9 100644 --- a/Src/wcwidth9.h +++ b/Src/wcwidth9.h @@ -22,6 +22,7 @@ static const struct wcwidth9_interval wcwidth9_nonprint[] = { {0x070f, 0x070f}, {0x180b, 0x180e}, {0x200b, 0x200f}, + {0x2028, 0x2029}, {0x202a, 0x202e}, {0x206a, 0x206f}, {0xd800, 0xdfff}, @@ -1283,6 +1284,9 @@ static inline bool wcwidth9_intable(const struct wcwidth9_interval *table, size_ } static inline int wcwidth9(int c) { + if (c == 0) { + return 0; + } if (c < 0|| c > 0x10ffff) { return -1; } @@ -1292,7 +1296,7 @@ static inline int wcwidth9(int c) { } if (wcwidth9_intable(wcwidth9_combining, WCWIDTH9_ARRAY_SIZE(wcwidth9_combining), c)) { - return -1; + return 0; } if (wcwidth9_intable(wcwidth9_not_assigned, WCWIDTH9_ARRAY_SIZE(wcwidth9_not_assigned), c)) { diff --git a/Src/zsh.h b/Src/zsh.h index 10931512d..22f73f806 100644 --- a/Src/zsh.h +++ b/Src/zsh.h @@ -3158,9 +3158,7 @@ typedef wint_t convchar_t; * works on MacOS which doesn't define that. */ #ifdef ENABLE_UNICODE9 -#define WCWIDTH(wc) mk_wcwidth(wc) -#elif defined(BROKEN_WCWIDTH) && (defined(__STDC_ISO_10646__) || defined(__APPLE__)) -#define WCWIDTH(wc) mk_wcwidth(wc) +#define WCWIDTH(wc) u9_wcwidth(wc) #else #define WCWIDTH(wc) wcwidth(wc) #endif @@ -3205,15 +3203,7 @@ typedef wint_t convchar_t; * sense throughout the shell. I am not aware of a way of * detecting the Unicode trait in standard libraries. */ -#ifdef BROKEN_WCWIDTH -/* - * We can't be quite sure the wcwidth we've provided is entirely - * in agreement with the system's, so be extra safe. - */ -#define IS_COMBINING(wc) (wc != 0 && WCWIDTH(wc) == 0 && !iswcntrl(wc)) -#else #define IS_COMBINING(wc) (wc != 0 && WCWIDTH(wc) == 0) -#endif /* * Test for the base of a combining character. * diff --git a/Src/ztype.h b/Src/ztype.h index 76589b152..ae7236774 100644 --- a/Src/ztype.h +++ b/Src/ztype.h @@ -72,7 +72,11 @@ #ifdef MULTIBYTE_SUPPORT #define WC_ZISTYPE(X,Y) wcsitype((X),(Y)) -#define WC_ISPRINT(X) iswprint(X) +# ifdef ENABLE_UNICODE9 +# define WC_ISPRINT(X) u9_iswprint(X) +# else +# define WC_ISPRINT(X) iswprint(X) +# endif #else #define WC_ZISTYPE(X,Y) zistype((X),(Y)) #define WC_ISPRINT(X) isprint(X) diff --git a/configure.ac b/configure.ac index 911cc4547..88da89e3e 100644 --- a/configure.ac +++ b/configure.ac @@ -2589,16 +2589,21 @@ AC_HELP_STRING([--enable-unicode9], [compile with unicode9 character widths]), AC_DEFINE(ENABLE_UNICODE9) fi]) -AH_TEMPLATE([BROKEN_WCWIDTH], -[Define to 1 if the wcwidth() function is present but broken.]) AH_TEMPLATE([BROKEN_ISPRINT], [Define to 1 if the isprint() function is broken under UTF-8 locale.]) + if test x$zsh_cv_c_unicode_support = xyes; then AC_DEFINE(MULTIBYTE_SUPPORT) - dnl Test for a wcwidth() implementation that gives the wrong width for - dnl zero-width combining characters. - dnl For the test we use a combining acute accent (\u0301). + dnl Test if wcwidth() and/or iswprint() is broken for + dnl zero-width combining characters, or + dnl some characters in the Latin Extended-B. + dnl If either of the functions is broken, both functions will be replaced + dnl by the ones from wcwidth9.h by defining ENABLE_UNICODE9. We will do + dnl this only if __STDC_ISO_10646__ is defined (or if building on macOS, + dnl where __STDC_ISO_10646__ is not defined but wchar_t is UCS). + dnl For the test we use a combining acute accent (\u0301) or + dnl a LATIN SMALL LETTER L WITH CURL (\u0234). dnl We input it as UTF-8 since that is the standard we can rely dnl upon most: we can't rely on a wchar_t being stored as a dnl Unicode code point on all systems. @@ -2607,9 +2612,8 @@ if test x$zsh_cv_c_unicode_support = xyes; then dnl - the programme compiled, linked and ran dnl - we successfully set a UTF-8 locale dnl - the locale we set plausibly converted the UTF-8 string - dnl for a zero-width combining character (the only way to be - dnl 100% sure would be to output it and ask if it looked right) - dnl - the converted wide character gave a non-zero width. + dnl into the correct wide character + dnl - but wcwidth() or iswprint() is broken for the converted wide character. dnl locale -a is a fallback; on most systems we should find en_US.UTF-8. [locale_prog='char *my_locales[] = { "en_US.UTF-8", "en_GB.UTF-8", "en.UTF-8", ' @@ -2621,32 +2625,38 @@ if test x$zsh_cv_c_unicode_support = xyes; then #include #include #include + #include int main() { char **localep; char comb_acute_mb[] = { (char)0xcc, (char)0x81 }; + char u_0234[] = { (char)0xc8, (char)0xb4 }; wchar_t wc; + #if !defined(__STDC_ISO_10646__) && !defined(__APPLE__) + return 1; + #endif for (localep = my_locales; *localep; localep++) - if (setlocale(LC_ALL, *localep) && - mbtowc(&wc, comb_acute_mb, 2) == 2) + if (setlocale(LC_ALL, *localep)) break; if (!*localep) return 1; - if (wcwidth(wc) == 0) - return 1; - return 0; + if (mbtowc(&wc, comb_acute_mb, 2) == 2 && (wcwidth(wc) != 0 || !iswprint(wc))) + return 0; + if (mbtowc(&wc, u_0234, 2) == 2 && (wcwidth(wc) != 1 || !iswprint(wc))) + return 0; + return 1; } "] - AC_CACHE_CHECK(if the wcwidth() function is broken, + AC_CACHE_CHECK(if the wcwidth() and/or iswprint() functions are broken, zsh_cv_c_broken_wcwidth, [AC_TRY_RUN([$locale_prog], zsh_cv_c_broken_wcwidth=yes, zsh_cv_c_broken_wcwidth=no, zsh_cv_c_broken_wcwidth=no)]) if test x$zsh_cv_c_broken_wcwidth = xyes; then - AC_DEFINE(BROKEN_WCWIDTH) + AC_DEFINE(ENABLE_UNICODE9) fi dnl Check if isprint() behaves correctly under UTF-8 locale. -- cgit v1.2.3 From e8edd42f7ff0fefbf74db7fbab2d242852b6bce6 Mon Sep 17 00:00:00 2001 From: Peter Stephenson Date: Sun, 2 Jul 2017 20:29:00 +0100 Subject: 22760: fix partial string length reports with NO_MULTIBYTE --- ChangeLog | 5 +++++ Src/utils.c | 2 +- Test/D04parameter.ztst | 20 ++++++++++++++++++++ 3 files changed, 26 insertions(+), 1 deletion(-) (limited to 'Src/utils.c') diff --git a/ChangeLog b/ChangeLog index 7ed5ba565..c843d8856 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,8 @@ +2017-07-02 Peter Stephenson + + * 22760: Src/utils.c, Test/D04parameter.ztst: NO_MULTIBYTE + partial string lengths were reported as full string lengths. + 2017-06-27 Peter Stephenson * 41368: Src/Zle/compctl.c: missing unqueue_signals(). diff --git a/Src/utils.c b/Src/utils.c index acb891d82..1b80e8cb0 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -5417,7 +5417,7 @@ mb_metastrlenend(char *ptr, int width, char *eptr) int num, num_in_char, complete; if (!isset(MULTIBYTE)) - return ztrlen(ptr); + return eptr ? (int)(eptr - ptr) : ztrlen(ptr); laststart = ptr; ret = MB_INVALID; diff --git a/Test/D04parameter.ztst b/Test/D04parameter.ztst index d5798b5b9..3c93990f1 100644 --- a/Test/D04parameter.ztst +++ b/Test/D04parameter.ztst @@ -783,16 +783,36 @@ 0:${(R)...} >is the , + # Although there's no reliance on multibyte here, the + # code exercised is different, so test both paths in the following group. + # If the shell isn't multibyte capable the tests are the same; + # that's not a problem. # This (1) doesn't work with // or / # (2) perhaps ought to be 18, to be consistent with normal zsh # substring indexing and with backreferences. print ${(BES)string##white} + (unsetopt multibyte; print ${(BES)string##white}) 0:${(BE...)...} +>14 19 >14 19 print ${(NS)string##white} + (unsetopt multibyte; print ${(NS)string##white}) 0:${(N)...} >5 +>5 + + fn() { + emulate -L zsh + local a=abcdef + print ${(SNBE)a#abcd} + unsetopt multibyte + print ${(SNBE)a#abcd} + } + fn +0:${(BEN)...} again, with match +>1 5 4 +>1 5 4 string='abcdefghijklmnopqrstuvwxyz' print ${${string%[aeiou]*}/(#m)?(#e)/${(U)MATCH}} -- cgit v1.2.3 From a51cd62b4567e5c18b4a2b7c98bb3087013afdc3 Mon Sep 17 00:00:00 2001 From: Martijn Dekker Date: Thu, 3 Aug 2017 19:57:04 +0200 Subject: 41484: Make ${(q+)...} quote backsleshes. --- ChangeLog | 5 +++++ Src/utils.c | 6 +++++- 2 files changed, 10 insertions(+), 1 deletion(-) (limited to 'Src/utils.c') diff --git a/ChangeLog b/ChangeLog index 01e3f6a22..0336c8787 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,8 @@ +2017-08-03 Peter Stephenson + + * Martijn: 41484: Src/utils.c: ${(q+)...} didn't properly + quote backslashes. + 2017-08-02 Daniel Shahaf * 41479: Completion/Unix/Command/_xz: Complete compressed, diff --git a/Src/utils.c b/Src/utils.c index 1b80e8cb0..5055d69fe 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -5119,7 +5119,7 @@ niceztrlen(char const *s) * If flags contains NICEFLAG_HEAP, use the heap for *outstrp, else * zalloc. * If flags contsins NICEFLAG_QUOTE, the output is going to be within - * $'...', so quote "'" with a backslash. + * $'...', so quote "'" and "\" with a backslash. */ /**/ @@ -5175,6 +5175,10 @@ mb_niceformat(const char *s, FILE *stream, char **outstrp, int flags) fmt = "\\'"; newl = 2; } + else if (c == L'\\' && (flags & NICEFLAG_QUOTE)) { + fmt = "\\\\"; + newl = 2; + } else fmt = wcs_nicechar_sel(c, &newl, NULL, flags & NICEFLAG_QUOTE); break; -- cgit v1.2.3 From 2eacbef91913fe967335812900d43cf2edfa54d9 Mon Sep 17 00:00:00 2001 From: Peter Stephenson Date: Mon, 7 Aug 2017 18:47:43 +0100 Subject: 41499 (with one further tweak): POSIX_STRINGS behaviour. Ignore a terminating delimiter when splitting as separators despite being called separators are terminators. --- ChangeLog | 6 ++++++ Doc/Zsh/options.yo | 30 +++++++++++++++++++++--------- Src/utils.c | 20 ++++++++++++++++++-- Test/E01options.ztst | 41 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 86 insertions(+), 11 deletions(-) (limited to 'Src/utils.c') diff --git a/ChangeLog b/ChangeLog index c224c675f..f885721ff 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +2017-08-07 Peter Stephenson + + * 41499 (with one further tweak): Src/utils.c, + Doc/Zsh/options.yo, Test/E01options.ztst: With POSIX_STRINGS + ignore terminating separator when splitting. + 2017-08-07 Peter Stephenson * Anthony: 41500: Doc/Zsh/mod_zutil.yo: document '-' to end diff --git a/Doc/Zsh/options.yo b/Doc/Zsh/options.yo index 70092d681..36bd939ad 100644 --- a/Doc/Zsh/options.yo +++ b/Doc/Zsh/options.yo @@ -2193,16 +2193,16 @@ cindex(discarding embedded nulls in $'...') cindex(embedded nulls, in $'...') cindex(nulls, embedded in $'...') item(tt(POSIX_STRINGS) )( -This option affects processing of quoted strings. Currently it only -affects the behaviour of null characters, i.e. character 0 in the -portable character set corresponding to US ASCII. +This option affects processing of quoted strings, and also +splitting of strngs. -When this option is not set, null characters embedded within strings -of the form tt($')var(...)tt(') are treated as ordinary characters. The -entire string is maintained within the shell and output to files where -necessary, although owing to restrictions of the library interface -the string is truncated at the null character in file names, environment -variables, or in arguments to external programs. +When this option is not set, null characters (character 0 in the +portable character set coresponding to US ASCII) that are embedded +within strings of the form tt($')var(...)tt(') are treated as ordinary +characters. The entire string is maintained within the shell and output +to files where necessary, although owing to restrictions of the library +interface the string is truncated at the null character in file names, +environment variables, or in arguments to external programs. When this option is set, the tt($')var(...)tt(') expression is truncated at the null character. Note that remaining parts of the same string @@ -2211,6 +2211,18 @@ beyond the termination of the quotes are not truncated. For example, the command line argument tt(a$'b\0c'd) is treated with the option off as the characters tt(a), tt(b), null, tt(c), tt(d), and with the option on as the characters tt(a), tt(b), tt(d). + +Furthermore, when the option is set, a trailing separator followed by an +empty strings does not cause extra fields to be produced when the string +is split. For example, + +example(var="foo bar " +print -l "${=var}") + +outputs a blank line at the end if tt(POSIXSTRINGS) is not set, but +no blank line if the option is set. Note that empty elements would in +any case be removed if quotation marks were not used. If the separator +is not white space, only the final separator is ignored in this fashion. ) pindex(POSIX_TRAPS) pindex(NO_POSIX_TRAPS) diff --git a/Src/utils.c b/Src/utils.c index 5055d69fe..d30a7b47e 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -3500,12 +3500,12 @@ skipwsep(char **s) mod_export char ** spacesplit(char *s, int allownull, int heap, int quote) { - char *t, **ret, **ptr; + char *t, **ret, **ptr, **eptr; int l = sizeof(*ret) * (wordcount(s, NULL, -!allownull) + 1); char *(*dup)(const char *) = (heap ? dupstring : ztrdup); /* ### TODO: s/calloc/alloc/ */ - ptr = ret = (char **) (heap ? hcalloc(l) : zshcalloc(l)); + eptr = ptr = ret = (char **) (heap ? hcalloc(l) : zshcalloc(l)); if (quote) { /* @@ -3537,6 +3537,7 @@ spacesplit(char *s, int allownull, int heap, int quote) if (s > t || allownull) { *ptr = (char *) (heap ? zhalloc((s - t) + 1) : zalloc((s - t) + 1)); + eptr = ptr; ztrncpy(*ptr++, t, s - t); } else *ptr++ = dup(nulstring); @@ -3545,6 +3546,21 @@ spacesplit(char *s, int allownull, int heap, int quote) } if (!allownull && t != s) *ptr++ = dup(""); + if (isset(POSIXSTRINGS) && ptr > eptr + 1) { + /* + * Trailing separators do not generate extra fields in POSIX. + * Note this is only the final separator --- if the + * immediately preceding field was null it is still counted. + * So just back up one. + */ + --ptr; + if (!heap) { + char **ret2 = realloc(ret, sizeof(*ret) * (ptr+1-ret)); + ptr -= ret-ret2; + free(ret); + ret = ret2; + } + } *ptr = NULL; return ret; } diff --git a/Test/E01options.ztst b/Test/E01options.ztst index f01d83567..b394e7cf4 100644 --- a/Test/E01options.ztst +++ b/Test/E01options.ztst @@ -1339,3 +1339,44 @@ ?(anon):4: `break' active at end of function scope ?(anon):4: `break' active at end of function scope ?(anon):4: `break' active at end of function scope + + for opt in POSIX_STRINGS NO_POSIX_STRINGS; do + var="foo bar " + (setopt $opt; print -l X "${=var}" Y) + var="foo2::bar2:" + (setopt $opt; IFS=:; print -l X "${=var}" Y) + var="foo3:bar3::" + (setopt $opt; IFS=:; print -l X "${=var}" Y) + done +0:POSIX_STRINGS effect on final delimiters +>X +>foo +>bar +>Y +>X +>foo2 +> +>bar2 +>Y +>X +>foo3 +>bar3 +> +>Y +>X +>foo +>bar +> +>Y +>X +>foo2 +> +>bar2 +> +>Y +>X +>foo3 +>bar3 +> +> +>Y -- cgit v1.2.3 From a9b579a9d3921c4d843be7a52faeb8a3f3f6c35e Mon Sep 17 00:00:00 2001 From: Peter Stephenson Date: Tue, 8 Aug 2017 19:04:49 +0100 Subject: Revert "41499 (with one further tweak): POSIX_STRINGS behaviour." This reverts commit 2eacbef91913fe967335812900d43cf2edfa54d9. Conflicts: ChangeLog --- ChangeLog | 5 +++++ Doc/Zsh/options.yo | 30 +++++++++--------------------- Src/utils.c | 20 ++------------------ Test/E01options.ztst | 41 ----------------------------------------- 4 files changed, 16 insertions(+), 80 deletions(-) (limited to 'Src/utils.c') diff --git a/ChangeLog b/ChangeLog index 34087fb8f..43e6b4ceb 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,8 @@ +2017-08-08 Peter Stephenson + + * unposted: back off 41499 as it has side effects which, while + perfectly logical, are not what POSIX expects. + 2017-08-08 Peter Stephenson * 41510: Doc/Zsh/params.yo: update doc for $ZSH_PATCHLEVEL. diff --git a/Doc/Zsh/options.yo b/Doc/Zsh/options.yo index 36bd939ad..70092d681 100644 --- a/Doc/Zsh/options.yo +++ b/Doc/Zsh/options.yo @@ -2193,16 +2193,16 @@ cindex(discarding embedded nulls in $'...') cindex(embedded nulls, in $'...') cindex(nulls, embedded in $'...') item(tt(POSIX_STRINGS) )( -This option affects processing of quoted strings, and also -splitting of strngs. +This option affects processing of quoted strings. Currently it only +affects the behaviour of null characters, i.e. character 0 in the +portable character set corresponding to US ASCII. -When this option is not set, null characters (character 0 in the -portable character set coresponding to US ASCII) that are embedded -within strings of the form tt($')var(...)tt(') are treated as ordinary -characters. The entire string is maintained within the shell and output -to files where necessary, although owing to restrictions of the library -interface the string is truncated at the null character in file names, -environment variables, or in arguments to external programs. +When this option is not set, null characters embedded within strings +of the form tt($')var(...)tt(') are treated as ordinary characters. The +entire string is maintained within the shell and output to files where +necessary, although owing to restrictions of the library interface +the string is truncated at the null character in file names, environment +variables, or in arguments to external programs. When this option is set, the tt($')var(...)tt(') expression is truncated at the null character. Note that remaining parts of the same string @@ -2211,18 +2211,6 @@ beyond the termination of the quotes are not truncated. For example, the command line argument tt(a$'b\0c'd) is treated with the option off as the characters tt(a), tt(b), null, tt(c), tt(d), and with the option on as the characters tt(a), tt(b), tt(d). - -Furthermore, when the option is set, a trailing separator followed by an -empty strings does not cause extra fields to be produced when the string -is split. For example, - -example(var="foo bar " -print -l "${=var}") - -outputs a blank line at the end if tt(POSIXSTRINGS) is not set, but -no blank line if the option is set. Note that empty elements would in -any case be removed if quotation marks were not used. If the separator -is not white space, only the final separator is ignored in this fashion. ) pindex(POSIX_TRAPS) pindex(NO_POSIX_TRAPS) diff --git a/Src/utils.c b/Src/utils.c index d30a7b47e..5055d69fe 100644 --- a/Src/utils.c +++ b/Src/utils.c @@ -3500,12 +3500,12 @@ skipwsep(char **s) mod_export char ** spacesplit(char *s, int allownull, int heap, int quote) { - char *t, **ret, **ptr, **eptr; + char *t, **ret, **ptr; int l = sizeof(*ret) * (wordcount(s, NULL, -!allownull) + 1); char *(*dup)(const char *) = (heap ? dupstring : ztrdup); /* ### TODO: s/calloc/alloc/ */ - eptr = ptr = ret = (char **) (heap ? hcalloc(l) : zshcalloc(l)); + ptr = ret = (char **) (heap ? hcalloc(l) : zshcalloc(l)); if (quote) { /* @@ -3537,7 +3537,6 @@ spacesplit(char *s, int allownull, int heap, int quote) if (s > t || allownull) { *ptr = (char *) (heap ? zhalloc((s - t) + 1) : zalloc((s - t) + 1)); - eptr = ptr; ztrncpy(*ptr++, t, s - t); } else *ptr++ = dup(nulstring); @@ -3546,21 +3545,6 @@ spacesplit(char *s, int allownull, int heap, int quote) } if (!allownull && t != s) *ptr++ = dup(""); - if (isset(POSIXSTRINGS) && ptr > eptr + 1) { - /* - * Trailing separators do not generate extra fields in POSIX. - * Note this is only the final separator --- if the - * immediately preceding field was null it is still counted. - * So just back up one. - */ - --ptr; - if (!heap) { - char **ret2 = realloc(ret, sizeof(*ret) * (ptr+1-ret)); - ptr -= ret-ret2; - free(ret); - ret = ret2; - } - } *ptr = NULL; return ret; } diff --git a/Test/E01options.ztst b/Test/E01options.ztst index b394e7cf4..f01d83567 100644 --- a/Test/E01options.ztst +++ b/Test/E01options.ztst @@ -1339,44 +1339,3 @@ ?(anon):4: `break' active at end of function scope ?(anon):4: `break' active at end of function scope ?(anon):4: `break' active at end of function scope - - for opt in POSIX_STRINGS NO_POSIX_STRINGS; do - var="foo bar " - (setopt $opt; print -l X "${=var}" Y) - var="foo2::bar2:" - (setopt $opt; IFS=:; print -l X "${=var}" Y) - var="foo3:bar3::" - (setopt $opt; IFS=:; print -l X "${=var}" Y) - done -0:POSIX_STRINGS effect on final delimiters ->X ->foo ->bar ->Y ->X ->foo2 -> ->bar2 ->Y ->X ->foo3 ->bar3 -> ->Y ->X ->foo ->bar -> ->Y ->X ->foo2 -> ->bar2 -> ->Y ->X ->foo3 ->bar3 -> -> ->Y -- cgit v1.2.3