Index: Makefile =================================================================== --- Makefile (revision 6) +++ Makefile (working copy) @@ -26,6 +26,21 @@ # # CFLAGS += -DOSNAME="\"OpenBSD 5.5\"" +ifeq ($(findstring Windows,$(OS)),Windows) + CFLAGS += -DOSNAME="\"MINGW\"" + CFLAGS += -DHAVE_LIMITS_H + CFLAGS += -DHAVE_SQLITE3_ERRSTR + DBLIB += -lmman + LDFLAGS += -s + $(info Windows specified OS = $(OS)) + $(info CFLAGS = $(CFLAGS)) +else + # OpenBSD has the ohash functions in libutil. + # Comment the following line if your system doesn't. + # + DBLIB += -lutil +endif + # IFF your system supports multi-byte functions (setlocale(), wcwidth(), # putwchar()) AND has __STDC_ISO_10646__ (that is, wchar_t is simply a # UCS-4 value) should you define USE_WCHAR. If you define it and your @@ -75,10 +90,6 @@ #CFLAGS += -I/usr/local/include #DBLIB += -L/usr/local/lib -# OpenBSD has the ohash functions in libutil. -# Comment the following line if your system doesn't. -# -DBLIB += -lutil SBINDIR = $(PREFIX)/sbin @@ -188,6 +199,8 @@ term_ps.c \ tree.c \ vol.c \ + wcwidth.c \ + vasprintf.c \ $(TESTSRCS) DISTFILES = INSTALL \ @@ -279,7 +292,8 @@ mandoc.o \ mandoc_aux.o \ msec.o \ - read.o + read.o \ + vasprintf.o COMPAT_OBJS = compat_fgetln.o \ compat_getsubopt.o \ @@ -305,7 +319,8 @@ term.o \ term_ascii.o \ term_ps.o \ - tbl_term.o + tbl_term.o \ + wcwidth.o MANDOC_OBJS = $(MANDOC_HTML_OBJS) \ $(MANDOC_MAN_OBJS) \ Index: mandoc_aux.c =================================================================== --- mandoc_aux.c (revision 6) +++ mandoc_aux.c (working copy) @@ -26,6 +26,8 @@ #include #include +int vasprintf (char **, const char *, va_list); + #include "mandoc.h" #include "mandoc_aux.h" Index: term_ascii.c =================================================================== --- term_ascii.c (revision 6) +++ term_ascii.c (working copy) @@ -30,6 +30,8 @@ #include #ifdef USE_WCHAR # include +# define wcwidth(a) mk_wcwidth(a) + int mk_wcwidth(wchar_t ucs); #endif #include "mandoc.h" Index: vasprintf.c =================================================================== --- vasprintf.c (revision 0) +++ vasprintf.c (working copy) @@ -0,0 +1,641 @@ +/* + * Copyright (c) Ian F. Darwin 1986-1995. + * Software written by Ian F. Darwin and others; + * maintained 1995-present by Christos Zoulas and others. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice immediately at the beginning of the file, without modification, + * this list of conditions, and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE FOR + * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ +/*########################################################################### + # # + # vasprintf # + # # + # Copyright (c) 2002-2005 David TAILLANDIER # + # # + ###########################################################################*/ + +/* + +This software is distributed under the "modified BSD licence". + +This software is also released with GNU license (GPL) in another file (same +source-code, only license differ). + + + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + +Redistributions of source code must retain the above copyright notice, this +list of conditions and the following disclaimer. Redistributions in binary +form must reproduce the above copyright notice, this list of conditions and +the following disclaimer in the documentation and/or other materials +provided with the distribution. The name of the author may not be used to +endorse or promote products derived from this software without specific +prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED +WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO +EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, +PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; +OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, +WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR +OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF +ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +==================== + +Hacked from xnprintf version of 26th February 2005 to provide only +vasprintf by Reuben Thomas . + +==================== + + +'printf' function family use the following format string: + +%[flag][width][.prec][modifier]type + +%% is the escape sequence to print a '%' +% followed by an unknown format will print the characters without +trying to do any interpretation + +flag: none + - # (blank) +width: n 0n * +prec: none .0 .n .* +modifier: F N L h l ll ('F' and 'N' are ms-dos/16-bit specific) +type: d i o u x X f e g E G c s p n + + +The function needs to allocate memory to store the full text before to +actually writting it. i.e if you want to fnprintf() 1000 characters, the +functions will allocate 1000 bytes. +This behaviour can be modified: you have to customise the code to flush the +internal buffer (writing to screen or file) when it reach a given size. Then +the buffer can have a shorter length. But what? If you really need to write +HUGE string, don't use printf! +During the process, some other memory is allocated (1024 bytes minimum) +to handle the output of partial sprintf() calls. If you have only 10000 bytes +free in memory, you *may* not be able to nprintf() a 8000 bytes-long text. + +note: if a buffer overflow occurs, exit() is called. This situation should +never appear ... but if you want to be *really* sure, you have to modify the +code to handle those situations (only one place to modify). +A buffer overflow can only occur if your sprintf() do strange things or when +you use strange formats. + +*/ +#ifdef HAVE_CONFIG_H +#include "config.h" +#endif + +#include +#include +#include +#include +#include +#include +#ifdef HAVE_LIMITS_H +#include +#endif + +#define ALLOC_CHUNK 2048 +#define ALLOC_SECURITY_MARGIN 1024 /* big value because some platforms have very big 'G' exponent */ +#if ALLOC_CHUNK < ALLOC_SECURITY_MARGIN +# error !!! ALLOC_CHUNK < ALLOC_SECURITY_MARGIN !!! +#endif +/* note: to have some interest, ALLOC_CHUNK should be much greater than ALLOC_SECURITY_MARGIN */ + +/* + * To save a lot of push/pop, every variable are stored into this + * structure, which is passed among nearly every sub-functions. + */ +typedef struct { + const char * src_string; /* current position into intput string */ + char * buffer_base; /* output buffer */ + char * dest_string; /* current position into output string */ + size_t buffer_len; /* length of output buffer */ + size_t real_len; /* real current length of output text */ + size_t pseudo_len; /* total length of output text if it were not limited in size */ + size_t maxlen; + va_list vargs; /* pointer to current position into vargs */ + char * sprintf_string; + FILE * fprintf_file; +} xprintf_struct; + +/* + * Realloc buffer if needed + * Return value: 0 = ok + * EOF = not enought memory + */ +static int realloc_buff(xprintf_struct *s, size_t len) +{ + char * ptr; + + if (len + ALLOC_SECURITY_MARGIN + s->real_len > s->buffer_len) { + len += s->real_len + ALLOC_CHUNK; + ptr = (char *)realloc((void *)(s->buffer_base), len); + if (ptr == NULL) { + s->buffer_base = NULL; + return EOF; + } + + s->dest_string = ptr + (size_t)(s->dest_string - s->buffer_base); + s->buffer_base = ptr; + s->buffer_len = len; + + (s->buffer_base)[s->buffer_len - 1] = 1; /* overflow marker */ + } + + return 0; +} + +/* + * Prints 'usual' characters up to next '%' + * or up to end of text + */ +static int usual_char(xprintf_struct * s) +{ + size_t len; + + len = strcspn(s->src_string, "%"); /* reachs the next '%' or end of input string */ + /* note: 'len' is never 0 because the presence of '%' */ + /* or end-of-line is checked in the calling function */ + + if (realloc_buff(s,len) == EOF) + return EOF; + + memcpy(s->dest_string, s->src_string, len); + s->src_string += len; + s->dest_string += len; + s->real_len += len; + s->pseudo_len += len; + + return 0; +} + +/* + * Return value: 0 = ok + * EOF = error + */ +static int print_it(xprintf_struct *s, size_t approx_len, + const char *format_string, ...) +{ + va_list varg; + int vsprintf_len; + size_t len; + + if (realloc_buff(s,approx_len) == EOF) + return EOF; + + va_start(varg, format_string); + vsprintf_len = vsprintf(s->dest_string, format_string, varg); + va_end(varg); + + /* Check for overflow */ + assert((s->buffer_base)[s->buffer_len - 1] == 1); + + if (vsprintf_len == EOF) /* must be done *after* overflow-check */ + return EOF; + + s->pseudo_len += vsprintf_len; + len = strlen(s->dest_string); + s->real_len += len; + s->dest_string += len; + + return 0; +} + +/* + * Prints a string (%s) + * We need special handling because: + * a: the length of the string is unknown + * b: when .prec is used, we must not access any extra byte of the + * string (of course, if the original sprintf() does... what the + * hell, not my problem) + * + * Return value: 0 = ok + * EOF = error + */ +static int type_s(xprintf_struct *s, int width, int prec, + const char *format_string, const char *arg_string) +{ + size_t string_len; + + if (arg_string == NULL) + return print_it(s, (size_t)6, "(null)", 0); + + /* hand-made strlen() whitch stops when 'prec' is reached. */ + /* if 'prec' is -1 then it is never reached. */ + string_len = 0; + while (arg_string[string_len] != 0 && (size_t)prec != string_len) + string_len++; + + if (width != -1 && string_len < (size_t)width) + string_len = (size_t)width; + + return print_it(s, string_len, format_string, arg_string); +} + +/* + * Read a serie of digits. Stop when non-digit is found. + * Return value: the value read (between 0 and 32767). + * Note: no checks are made against overflow. If the string contain a big + * number, then the return value won't be what we want (but, in this case, + * the programmer don't know whatr he wants, then no problem). + */ +static int getint(const char **string) +{ + int i = 0; + + while (isdigit((unsigned char)**string) != 0) { + i = i * 10 + (**string - '0'); + (*string)++; + } + + if (i < 0 || i > 32767) + i = 32767; /* if we have i==-10 this is not because the number is */ + /* negative; this is because the number is big */ + return i; +} + +/* + * Read a part of the format string. A part is 'usual characters' (ie "blabla") + * or '%%' escape sequence (to print a single '%') or any combination of + * format specifier (ie "%i" or "%10.2d"). + * After the current part is managed, the function returns to caller with + * everything ready to manage the following part. + * The caller must ensure than the string is not empty, i.e. the first byte + * is not zero. + * + * Return value: 0 = ok + * EOF = error + */ +static int dispatch(xprintf_struct *s) +{ + const char *initial_ptr; + char format_string[24]; /* max length may be something like "% +-#032768.32768Ld" */ + char *format_ptr; + int flag_plus, flag_minus, flag_space, flag_sharp, flag_zero; + int width, prec, modifier, approx_width; + char type; + /* most of those variables are here to rewrite the format string */ + +#define SRCTXT (s->src_string) +#define DESTTXT (s->dest_string) + + /* incoherent format string. Characters after the '%' will be printed with the next call */ +#define INCOHERENT() do {SRCTXT=initial_ptr; return 0;} while (0) /* do/while to avoid */ +#define INCOHERENT_TEST() do {if(*SRCTXT==0) INCOHERENT();} while (0) /* a null statement */ + + /* 'normal' text */ + if (*SRCTXT != '%') + return usual_char(s); + + /* we then have a '%' */ + SRCTXT++; + /* don't check for end-of-string ; this is done later */ + + /* '%%' escape sequence */ + if (*SRCTXT == '%') { + if (realloc_buff(s, (size_t)1) == EOF) /* because we can have "%%%%%%%%..." */ + return EOF; + *DESTTXT = '%'; + DESTTXT++; + SRCTXT++; + (s->real_len)++; + (s->pseudo_len)++; + return 0; + } + + /* '%' managing */ + initial_ptr = SRCTXT; /* save current pointer in case of incorrect */ + /* 'decoding'. Points just after the '%' so the '%' */ + /* won't be printed in any case, as required. */ + + /* flag */ + flag_plus = flag_minus = flag_space = flag_sharp = flag_zero = 0; + + for (;; SRCTXT++) { + if (*SRCTXT == ' ') + flag_space = 1; + else if (*SRCTXT == '+') + flag_plus = 1; + else if (*SRCTXT == '-') + flag_minus = 1; + else if (*SRCTXT == '#') + flag_sharp = 1; + else if (*SRCTXT == '0') + flag_zero = 1; + else + break; + } + + INCOHERENT_TEST(); /* here is the first test for end of string */ + + /* width */ + if (*SRCTXT == '*') { /* width given by next argument */ + SRCTXT++; + width = va_arg(s->vargs, int); + if ((size_t)width > 0x3fffU) /* 'size_t' to check against negative values too */ + width = 0x3fff; + } else if (isdigit((unsigned char)*SRCTXT)) /* width given as ASCII number */ + width = getint(&SRCTXT); + else + width = -1; /* no width specified */ + + INCOHERENT_TEST(); + + /* .prec */ + if (*SRCTXT == '.') { + SRCTXT++; + if (*SRCTXT == '*') { /* .prec given by next argument */ + SRCTXT++; + prec = va_arg(s->vargs, int); + if ((size_t)prec >= 0x3fffU) /* 'size_t' to check against negative values too */ + prec = 0x3fff; + } else { /* .prec given as ASCII number */ + if (isdigit((unsigned char)*SRCTXT) == 0) + INCOHERENT(); + prec = getint(&SRCTXT); + } + INCOHERENT_TEST(); + } else + prec = -1; /* no .prec specified */ + + /* modifier */ + if (*SRCTXT == 'L' || *SRCTXT == 'h' || *SRCTXT == 'l') { + modifier = *SRCTXT; + SRCTXT++; + if (modifier=='l' && *SRCTXT=='l') { + SRCTXT++; + modifier = 'L'; /* 'll' == 'L' long long == long double */ + } /* only for compatibility ; not portable */ + INCOHERENT_TEST(); + } else + modifier = -1; /* no modifier specified */ + + /* type */ + type = *SRCTXT; + if (strchr("diouxXfegEGcspn",type) == NULL) + INCOHERENT(); /* unknown type */ + SRCTXT++; + + /* rewrite format-string */ + format_string[0] = '%'; + format_ptr = &(format_string[1]); + + if (flag_plus) { + *format_ptr = '+'; + format_ptr++; + } + if (flag_minus) { + *format_ptr = '-'; + format_ptr++; + } + if (flag_space) { + *format_ptr = ' '; + format_ptr++; + } + if (flag_sharp) { + *format_ptr = '#'; + format_ptr++; + } + if (flag_zero) { + *format_ptr = '0'; + format_ptr++; + } /* '0' *must* be the last one */ + + if (width != -1) { + sprintf(format_ptr, "%i", width); + format_ptr += strlen(format_ptr); + } + + if (prec != -1) { + *format_ptr = '.'; + format_ptr++; + sprintf(format_ptr, "%i", prec); + format_ptr += strlen(format_ptr); + } + + if (modifier != -1) { + if (modifier == 'L' && strchr("diouxX",type) != NULL) { + *format_ptr = 'l'; + format_ptr++; + *format_ptr = 'l'; + format_ptr++; + } else { + *format_ptr = modifier; + format_ptr++; + } + } + + *format_ptr = type; + format_ptr++; + *format_ptr = 0; + + /* vague approximation of minimal length if width or prec are specified */ + approx_width = width + prec; + if (approx_width < 0) /* because width == -1 and/or prec == -1 */ + approx_width = 0; + + switch (type) { + /* int */ + case 'd': + case 'i': + case 'o': + case 'u': + case 'x': + case 'X': + switch (modifier) { + case -1 : + return print_it(s, (size_t)approx_width, format_string, va_arg(s->vargs, int)); + case 'L': + return print_it(s, (size_t)approx_width, format_string, va_arg(s->vargs, long long int)); + case 'l': + return print_it(s, (size_t)approx_width, format_string, va_arg(s->vargs, long int)); + case 'h': + return print_it(s, (size_t)approx_width, format_string, va_arg(s->vargs, int)); + /* 'int' instead of 'short int' because default promotion is 'int' */ + default: + INCOHERENT(); + } + + /* char */ + case 'c': + if (modifier != -1) + INCOHERENT(); + return print_it(s, (size_t)approx_width, format_string, va_arg(s->vargs, int)); + /* 'int' instead of 'char' because default promotion is 'int' */ + + /* math */ + case 'e': + case 'f': + case 'g': + case 'E': + case 'G': + switch (modifier) { + case -1 : /* because of default promotion, no modifier means 'l' */ + case 'l': + return print_it(s, (size_t)approx_width, format_string, va_arg(s->vargs, double)); + case 'L': + return print_it(s, (size_t)approx_width, format_string, va_arg(s->vargs, long double)); + default: + INCOHERENT(); + } + + /* string */ + case 's': + return type_s(s, width, prec, format_string, va_arg(s->vargs, const char*)); + + /* pointer */ + case 'p': + if (modifier == -1) + return print_it(s, (size_t)approx_width, format_string, va_arg(s->vargs, void *)); + INCOHERENT(); + + /* store */ + case 'n': + if (modifier == -1) { + int * p; + p = va_arg(s->vargs, int *); + if (p != NULL) { + *p = s->pseudo_len; + return 0; + } + return EOF; + } + INCOHERENT(); + + } /* switch */ + + INCOHERENT(); /* unknown type */ + +#undef INCOHERENT +#undef INCOHERENT_TEST +#undef SRCTXT +#undef DESTTXT +} + +/* + * Return value: number of *virtually* written characters + * EOF = error + */ +static int core(xprintf_struct *s) +{ + size_t len, save_len; + char *dummy_base; + + /* basic checks */ + if ((int)(s->maxlen) <= 0) /* 'int' to check against some conversion */ + return EOF; /* error for example if value is (int)-10 */ + s->maxlen--; /* because initial maxlen counts final 0 */ + /* note: now 'maxlen' _can_ be zero */ + + if (s->src_string == NULL) + s->src_string = "(null)"; + + /* struct init and memory allocation */ + s->buffer_base = NULL; + s->buffer_len = 0; + s->real_len = 0; + s->pseudo_len = 0; + if (realloc_buff(s, (size_t)0) == EOF) + return EOF; + s->dest_string = s->buffer_base; + + /* process source string */ + for (;;) { + /* up to end of source string */ + if (*(s->src_string) == 0) { + *(s->dest_string) = 0; /* final 0 */ + len = s->real_len + 1; + break; + } + + if (dispatch(s) == EOF) + goto free_EOF; + + /* up to end of dest string */ + if (s->real_len >= s->maxlen) { + (s->buffer_base)[s->maxlen] = 0; /* final 0 */ + len = s->maxlen + 1; + break; + } + } + + /* for (v)asnprintf */ + dummy_base = s->buffer_base; + save_len = 0; /* just to avoid a compiler warning */ + + dummy_base = s->buffer_base + s->real_len; + save_len = s->real_len; + + /* process the remaining of source string to compute 'pseudo_len'. We + * overwrite again and again, starting at 'dummy_base' because we don't + * need the text, only char count. */ + while(*(s->src_string) != 0) { /* up to end of source string */ + s->real_len = 0; + s->dest_string = dummy_base; + if (dispatch(s) == EOF) + goto free_EOF; + } + + s->buffer_base = (char *)realloc((void *)(s->buffer_base), save_len + 1); + if (s->buffer_base == NULL) + return EOF; /* should rarely happen because we shrink the buffer */ + return s->pseudo_len; + + free_EOF: + if (s->buffer_base != NULL) + free(s->buffer_base); + return EOF; +} + +int vasprintf(char **ptr, const char *format_string, va_list vargs) +{ + xprintf_struct s; + int retval; + + s.src_string = format_string; +#ifdef va_copy + va_copy (s.vargs, vargs); +#else +#ifdef __va_copy + __va_copy (s.vargs, vargs); +#else + memcpy (&s.vargs, vargs, sizeof (va_list)); +#endif /* __va_copy */ +#endif /* va_copy */ + s.maxlen = (size_t)INT_MAX; + + retval = core(&s); + va_end(s.vargs); + if (retval == EOF) { + *ptr = NULL; + return EOF; + } + + *ptr = s.buffer_base; + return retval; +} Index: wcwidth.c =================================================================== --- wcwidth.c (revision 0) +++ wcwidth.c (working copy) @@ -0,0 +1,309 @@ +/* + * 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 + */ + +#include + +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))); +} + + +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) +{ + /* 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); +} + + +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; +}