From: Paul Eggert Date: Tue, 22 Jan 2002 07:43:55 +0000 (+0000) Subject: From textutils 2.1 X-Git-Url: https://git.dogcows.com/gitweb?a=commitdiff_plain;h=ba32aa1147aaa40f7c88095e101df63903a06b06;p=chaz%2Ftar From textutils 2.1 --- diff --git a/lib/quotearg.c b/lib/quotearg.c index 6e923a8..9d43956 100644 --- a/lib/quotearg.c +++ b/lib/quotearg.c @@ -1,5 +1,5 @@ /* quotearg.c - quote arguments for output - Copyright (C) 1998, 1999 Free Software Foundation, Inc. + Copyright (C) 1998, 1999, 2000, 2001, 2002 Free Software Foundation, Inc. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -21,21 +21,22 @@ # include #endif +#if HAVE_STDDEF_H +# include /* For the definition of size_t on windows w/MSVC. */ +#endif #include #include #include #include -#if defined (STDC_HEADERS) || (!defined (isascii) && !defined (HAVE_ISASCII)) -# define ISASCII(c) 1 -#else -# define ISASCII(c) isascii (c) -#endif -#ifdef isgraph -# define ISGRAPH(c) (ISASCII (c) && isgraph (c)) + +#if ENABLE_NLS +# include +# define _(text) gettext (text) #else -# define ISGRAPH(c) (ISASCII (c) && isprint (c) && !isspace (c)) +# define _(text) text #endif +#define N_(text) text #if HAVE_LIMITS_H # include @@ -43,9 +44,21 @@ #ifndef CHAR_BIT # define CHAR_BIT 8 #endif +#ifndef SIZE_MAX +# define SIZE_MAX ((size_t) -1) +#endif #ifndef UCHAR_MAX # define UCHAR_MAX ((unsigned char) -1) #endif +#ifndef UINT_MAX +# define UINT_MAX ((unsigned int) -1) +#endif + +#if HAVE_C_BACKSLASH_A +# define ALERT_CHAR '\a' +#else +# define ALERT_CHAR '\7' +#endif #if HAVE_STDLIB_H # include @@ -55,17 +68,55 @@ # include #endif +#if HAVE_WCHAR_H + +/* BSD/OS 4.1 wchar.h requires FILE and struct tm to be declared. */ +# include +# include + +# include +#endif + +#if !HAVE_MBRTOWC +/* Disable multibyte processing entirely. Since MB_CUR_MAX is 1, the + other macros are defined only for documentation and to satisfy C + syntax. */ +# undef MB_CUR_MAX +# define MB_CUR_MAX 1 +# define mbrtowc(pwc, s, n, ps) ((*(pwc) = *(s)) != 0) +# define mbsinit(ps) 1 +# define iswprint(wc) ISPRINT ((unsigned char) (wc)) +#endif + +#ifndef iswprint +# if HAVE_WCTYPE_H +# include +# endif +# if !defined iswprint && !HAVE_ISWPRINT +# define iswprint(wc) 1 +# endif +#endif + #define INT_BITS (sizeof (int) * CHAR_BIT) +#if defined (STDC_HEADERS) || (!defined (isascii) && !defined (HAVE_ISASCII)) +# define IN_CTYPE_DOMAIN(c) 1 +#else +# define IN_CTYPE_DOMAIN(c) isascii(c) +#endif + +/* Undefine to protect against the definition in wctype.h of solaris2.6. */ +#undef ISPRINT +#define ISPRINT(c) (IN_CTYPE_DOMAIN (c) && isprint (c)) + struct quoting_options { /* Basic quoting style. */ enum quoting_style style; - /* Quote the chararacters indicated by this bit vector even if the + /* Quote the characters indicated by this bit vector even if the quoting style would not normally require them to be quoted. */ - int quote_these_too[((UCHAR_MAX + 1) / INT_BITS - + ((UCHAR_MAX + 1) % INT_BITS != 0))]; + int quote_these_too[(UCHAR_MAX / INT_BITS) + 1]; }; /* Names of quoting styles. */ @@ -76,17 +127,21 @@ char const *const quoting_style_args[] = "shell-always", "c", "escape", + "locale", + "clocale", 0 }; -/* Correspondances to quoting style names. */ +/* Correspondences to quoting style names. */ enum quoting_style const quoting_style_vals[] = { literal_quoting_style, shell_quoting_style, shell_always_quoting_style, c_quoting_style, - escape_quoting_style + escape_quoting_style, + locale_quoting_style, + clocale_quoting_style }; /* The default quoting options. */ @@ -135,204 +190,409 @@ set_char_quoting (struct quoting_options *o, char c, int i) return r; } +/* MSGID approximates a quotation mark. Return its translation if it + has one; otherwise, return either it or "\"", depending on S. */ +static char const * +gettext_quote (char const *msgid, enum quoting_style s) +{ + char const *translation = _(msgid); + if (translation == msgid && s == clocale_quoting_style) + translation = "\""; + return translation; +} + /* Place into buffer BUFFER (of size BUFFERSIZE) a quoted version of - argument ARG (of size ARGSIZE), using O to control quoting. - If O is null, use the default. + argument ARG (of size ARGSIZE), using QUOTING_STYLE and the + non-quoting-style part of O to control quoting. Terminate the output with a null character, and return the written size of the output, not counting the terminating null. If BUFFERSIZE is too small to store the output string, return the value that would have been returned had BUFFERSIZE been large enough. - If ARGSIZE is -1, use the string length of the argument for ARGSIZE. */ -size_t -quotearg_buffer (char *buffer, size_t buffersize, - char const *arg, size_t argsize, - struct quoting_options const *o) + If ARGSIZE is -1, use the string length of the argument for ARGSIZE. + + This function acts like quotearg_buffer (BUFFER, BUFFERSIZE, ARG, + ARGSIZE, O), except it uses QUOTING_STYLE instead of the quoting + style specified by O, and O may not be null. */ + +static size_t +quotearg_buffer_restyled (char *buffer, size_t buffersize, + char const *arg, size_t argsize, + enum quoting_style quoting_style, + struct quoting_options const *o) { - unsigned char c; size_t i; - size_t len; - int quote_mark; - struct quoting_options const *p = o ? o : &default_quoting_options; - enum quoting_style quoting_style = p->style; + size_t len = 0; + char const *quote_string = 0; + size_t quote_string_len = 0; + int backslash_escapes = 0; + int unibyte_locale = MB_CUR_MAX == 1; + #define STORE(c) \ do \ { \ if (len < buffersize) \ buffer[len] = (c); \ - len++; \ + len++; \ } \ while (0) switch (quoting_style) { - case shell_quoting_style: - if (! (argsize == (size_t) -1 ? arg[0] == '\0' : argsize == 0)) - { - switch (arg[0]) - { - case '#': case '~': - break; + case c_quoting_style: + STORE ('"'); + backslash_escapes = 1; + quote_string = "\""; + quote_string_len = 1; + break; - default: - len = 0; - for (i = 0; ; i++) - { - if (argsize == (size_t) -1 ? arg[i] == '\0' : i == argsize) - goto done; - - c = arg[i]; - - switch (c) - { - case '\t': case '\n': case ' ': - case '!': /* special in csh */ - case '"': case '$': case '&': case '\'': - case '(': case ')': case '*': case ';': - case '<': case '>': case '?': case '[': case '\\': - case '^': /* special in old /bin/sh, e.g. SunOS 4.1.4 */ - case '`': case '|': - goto needs_quoting; - } - - if (p->quote_these_too[c / INT_BITS] & (1 << (c % INT_BITS))) - goto needs_quoting; - - STORE (c); - } - - needs_quoting:; - break; - } - } - /* Fall through. */ + case escape_quoting_style: + backslash_escapes = 1; + break; - case shell_always_quoting_style: - quote_mark = '\''; + case locale_quoting_style: + case clocale_quoting_style: + { + /* Get translations for open and closing quotation marks. + + The message catalog should translate "`" to a left + quotation mark suitable for the locale, and similarly for + "'". If the catalog has no translation, + locale_quoting_style quotes `like this', and + clocale_quoting_style quotes "like this". + + For example, an American English Unicode locale should + translate "`" to U+201C (LEFT DOUBLE QUOTATION MARK), and + should translate "'" to U+201D (RIGHT DOUBLE QUOTATION + MARK). A British English Unicode locale should instead + translate these to U+2018 (LEFT SINGLE QUOTATION MARK) and + U+2019 (RIGHT SINGLE QUOTATION MARK), respectively. */ + + char const *left = gettext_quote (N_("`"), quoting_style); + char const *right = gettext_quote (N_("'"), quoting_style); + for (quote_string = left; *quote_string; quote_string++) + STORE (*quote_string); + backslash_escapes = 1; + quote_string = right; + quote_string_len = strlen (quote_string); + } break; - case c_quoting_style: - quote_mark = '"'; + case shell_always_quoting_style: + STORE ('\''); + quote_string = "'"; + quote_string_len = 1; break; default: - quote_mark = 0; break; } - len = 0; - - if (quote_mark) - STORE (quote_mark); - for (i = 0; ! (argsize == (size_t) -1 ? arg[i] == '\0' : i == argsize); i++) { - c = arg[i]; + unsigned char c; + unsigned char esc; + + if (backslash_escapes + && quote_string_len + && i + quote_string_len <= argsize + && memcmp (arg + i, quote_string, quote_string_len) == 0) + STORE ('\\'); - switch (quoting_style) + c = arg[i]; + switch (c) { - case literal_quoting_style: + case '\0': + if (backslash_escapes) + { + STORE ('\\'); + STORE ('0'); + STORE ('0'); + c = '0'; + } break; - case shell_quoting_style: - case shell_always_quoting_style: - if (c == '\'') + case '?': + switch (quoting_style) { - STORE ('\''); - STORE ('\\'); - STORE ('\''); + case shell_quoting_style: + goto use_shell_always_quoting_style; + + case c_quoting_style: + if (i + 2 < argsize && arg[i + 1] == '?') + switch (arg[i + 2]) + { + case '!': case '\'': + case '(': case ')': case '-': case '/': + case '<': case '=': case '>': + /* Escape the second '?' in what would otherwise be + a trigraph. */ + i += 2; + c = arg[i + 2]; + STORE ('?'); + STORE ('\\'); + STORE ('?'); + break; + } + break; + + default: + break; } break; - case c_quoting_style: - case escape_quoting_style: - switch (c) + case ALERT_CHAR: esc = 'a'; goto c_escape; + case '\b': esc = 'b'; goto c_escape; + case '\f': esc = 'f'; goto c_escape; + case '\n': esc = 'n'; goto c_and_shell_escape; + case '\r': esc = 'r'; goto c_and_shell_escape; + case '\t': esc = 't'; goto c_and_shell_escape; + case '\v': esc = 'v'; goto c_escape; + case '\\': esc = c; goto c_and_shell_escape; + + c_and_shell_escape: + if (quoting_style == shell_quoting_style) + goto use_shell_always_quoting_style; + c_escape: + if (backslash_escapes) { - case '?': /* Do not generate trigraphs. */ - case '\\': goto store_escape; - /* Not all C compilers know what \a means. */ - case 7 : c = 'a'; goto store_escape; - case '\b': c = 'b'; goto store_escape; - case '\f': c = 'f'; goto store_escape; - case '\n': c = 'n'; goto store_escape; - case '\r': c = 'r'; goto store_escape; - case '\t': c = 't'; goto store_escape; - case '\v': c = 'v'; goto store_escape; - - case '"': - if (quoting_style == c_quoting_style) - goto store_escape; + c = esc; + goto store_escape; + } + break; + + case '#': case '~': + if (i != 0) + break; + /* Fall through. */ + case ' ': + case '!': /* special in bash */ + case '"': case '$': case '&': + case '(': case ')': case '*': case ';': + case '<': case '>': case '[': + case '^': /* special in old /bin/sh, e.g. SunOS 4.1.4 */ + case '`': case '|': + /* A shell special character. In theory, '$' and '`' could + be the first bytes of multibyte characters, which means + we should check them with mbrtowc, but in practice this + doesn't happen so it's not worth worrying about. */ + if (quoting_style == shell_quoting_style) + goto use_shell_always_quoting_style; + break; + + case '\'': + switch (quoting_style) + { + case shell_quoting_style: + goto use_shell_always_quoting_style; + + case shell_always_quoting_style: + STORE ('\''); + STORE ('\\'); + STORE ('\''); break; default: - if (!ISGRAPH (c)) - { - STORE ('\\'); - STORE ('0' + (c >> 6)); - STORE ('0' + ((c >> 3) & 7)); - c = '0' + (c & 7); - goto store_c; - } break; } + break; - if (! (p->quote_these_too[c / INT_BITS] & (1 << (c % INT_BITS)))) - goto store_c; + case '%': case '+': case ',': case '-': case '.': case '/': + case '0': case '1': case '2': case '3': case '4': case '5': + case '6': case '7': case '8': case '9': case ':': case '=': + case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': + case 'G': case 'H': case 'I': case 'J': case 'K': case 'L': + case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R': + case 'S': case 'T': case 'U': case 'V': case 'W': case 'X': + case 'Y': case 'Z': case ']': case '_': case 'a': case 'b': + case 'c': case 'd': case 'e': case 'f': case 'g': case 'h': + case 'i': case 'j': case 'k': case 'l': case 'm': case 'n': + case 'o': case 'p': case 'q': case 'r': case 's': case 't': + case 'u': case 'v': case 'w': case 'x': case 'y': case 'z': + case '{': case '}': + /* These characters don't cause problems, no matter what the + quoting style is. They cannot start multibyte sequences. */ + break; - store_escape: - STORE ('\\'); + default: + /* If we have a multibyte sequence, copy it until we reach + its end, find an error, or come back to the initial shift + state. For C-like styles, if the sequence has + unprintable characters, escape the whole sequence, since + we can't easily escape single characters within it. */ + { + /* Length of multibyte sequence found so far. */ + size_t m; + + int printable; + + if (unibyte_locale) + { + m = 1; + printable = ISPRINT (c); + } + else + { + mbstate_t mbstate; + memset (&mbstate, 0, sizeof mbstate); + + m = 0; + printable = 1; + if (argsize == (size_t) -1) + argsize = strlen (arg); + + do + { + wchar_t w; + size_t bytes = mbrtowc (&w, &arg[i + m], + argsize - (i + m), &mbstate); + if (bytes == 0) + break; + else if (bytes == (size_t) -1) + { + printable = 0; + break; + } + else if (bytes == (size_t) -2) + { + printable = 0; + while (i + m < argsize && arg[i + m]) + m++; + break; + } + else + { + if (! iswprint (w)) + printable = 0; + m += bytes; + } + } + while (! mbsinit (&mbstate)); + } + + if (1 < m || (backslash_escapes && ! printable)) + { + /* Output a multibyte sequence, or an escaped + unprintable unibyte character. */ + size_t ilim = i + m; + + for (;;) + { + if (backslash_escapes && ! printable) + { + STORE ('\\'); + STORE ('0' + (c >> 6)); + STORE ('0' + ((c >> 3) & 7)); + c = '0' + (c & 7); + } + if (ilim <= i + 1) + break; + STORE (c); + c = arg[++i]; + } + + goto store_c; + } + } } + if (! (backslash_escapes + && o->quote_these_too[c / INT_BITS] & (1 << (c % INT_BITS)))) + goto store_c; + + store_escape: + STORE ('\\'); + store_c: STORE (c); } - if (quote_mark) - STORE (quote_mark); + if (quote_string) + for (; *quote_string; quote_string++) + STORE (*quote_string); - done: if (len < buffersize) buffer[len] = '\0'; return len; + + use_shell_always_quoting_style: + return quotearg_buffer_restyled (buffer, buffersize, arg, argsize, + shell_always_quoting_style, o); } -/* Use storage slot N to return a quoted version of the string ARG. +/* Place into buffer BUFFER (of size BUFFERSIZE) a quoted version of + argument ARG (of size ARGSIZE), using O to control quoting. + If O is null, use the default. + Terminate the output with a null character, and return the written + size of the output, not counting the terminating null. + If BUFFERSIZE is too small to store the output string, return the + value that would have been returned had BUFFERSIZE been large enough. + If ARGSIZE is -1, use the string length of the argument for ARGSIZE. */ +size_t +quotearg_buffer (char *buffer, size_t buffersize, + char const *arg, size_t argsize, + struct quoting_options const *o) +{ + struct quoting_options const *p = o ? o : &default_quoting_options; + return quotearg_buffer_restyled (buffer, buffersize, arg, argsize, + p->style, p); +} + +/* Use storage slot N to return a quoted version of argument ARG. + ARG is of size ARGSIZE, but if that is -1, ARG is a null-terminated string. OPTIONS specifies the quoting options. The returned value points to static storage that can be reused by the next call to this function with the same value of N. - N must be nonnegative. N is deliberately declared with type `int' + N must be nonnegative. N is deliberately declared with type "int" to allow for future extensions (using negative values). */ static char * -quotearg_n_options (int n, char const *arg, +quotearg_n_options (int n, char const *arg, size_t argsize, struct quoting_options const *options) { - static unsigned int nslots; - static struct slotvec + /* Preallocate a slot 0 buffer, so that the caller can always quote + one small component of a "memory exhausted" message in slot 0. */ + static char slot0[256]; + static unsigned int nslots = 1; + unsigned int n0 = n; + struct slotvec { size_t size; char *val; - } *slotvec; + }; + static struct slotvec slotvec0 = {sizeof slot0, slot0}; + static struct slotvec *slotvec = &slotvec0; + + if (n < 0) + abort (); - if (nslots <= n) + if (nslots <= n0) { - int n1 = n + 1; - size_t s = n1 * sizeof (struct slotvec); - if (! (0 < n1 && n1 == s / sizeof (struct slotvec))) - abort (); + unsigned int n1 = n0 + 1; + size_t s = n1 * sizeof *slotvec; + + if (SIZE_MAX / UINT_MAX <= sizeof *slotvec + && n1 != s / sizeof *slotvec) + xalloc_die (); + + if (slotvec == &slotvec0) + { + slotvec = (struct slotvec *) xmalloc (sizeof *slotvec); + *slotvec = slotvec0; + } slotvec = (struct slotvec *) xrealloc (slotvec, s); - memset (slotvec + nslots, 0, (n1 - nslots) * sizeof (struct slotvec)); - nslots = n; + memset (slotvec + nslots, 0, (n1 - nslots) * sizeof *slotvec); + nslots = n1; } { size_t size = slotvec[n].size; char *val = slotvec[n].val; - size_t qsize = quotearg_buffer (val, size, arg, (size_t) -1, options); + size_t qsize = quotearg_buffer (val, size, arg, argsize, options); if (size <= qsize) { slotvec[n].size = size = qsize + 1; - slotvec[n].val = val = xrealloc (val, size); - quotearg_buffer (val, size, arg, (size_t) -1, options); + slotvec[n].val = val = xrealloc (val == slot0 ? 0 : val, size); + quotearg_buffer (val, size, arg, argsize, options); } return val; @@ -340,9 +600,9 @@ quotearg_n_options (int n, char const *arg, } char * -quotearg_n (unsigned int n, char const *arg) +quotearg_n (int n, char const *arg) { - return quotearg_n_options (n, arg, &default_quoting_options); + return quotearg_n_options (n, arg, (size_t) -1, &default_quoting_options); } char * @@ -351,13 +611,44 @@ quotearg (char const *arg) return quotearg_n (0, arg); } +/* Return quoting options for STYLE, with no extra quoting. */ +static struct quoting_options +quoting_options_from_style (enum quoting_style style) +{ + struct quoting_options o; + o.style = style; + memset (o.quote_these_too, 0, sizeof o.quote_these_too); + return o; +} + +char * +quotearg_n_style (int n, enum quoting_style s, char const *arg) +{ + struct quoting_options const o = quoting_options_from_style (s); + return quotearg_n_options (n, arg, (size_t) -1, &o); +} + +char * +quotearg_n_style_mem (int n, enum quoting_style s, + char const *arg, size_t argsize) +{ + struct quoting_options const o = quoting_options_from_style (s); + return quotearg_n_options (n, arg, argsize, &o); +} + +char * +quotearg_style (enum quoting_style s, char const *arg) +{ + return quotearg_n_style (0, s, arg); +} + char * quotearg_char (char const *arg, char ch) { struct quoting_options options; options = default_quoting_options; set_char_quoting (&options, ch, 1); - return quotearg_n_options (0, arg, &options); + return quotearg_n_options (0, arg, (size_t) -1, &options); } char *