diff -ru par-1.52.orig/buffer.c par-1.52-i18n.2/buffer.c --- par-1.52.orig/buffer.c 2001-03-09 00:51:11.000000000 +0100 +++ par-1.52-i18n.2/buffer.c 2006-08-03 16:27:06.000000000 +0200 @@ -1,9 +1,9 @@ -/*********************/ -/* buffer.c */ -/* for Par 1.52 */ -/* Copyright 2001 by */ -/* Adam M. Costello */ -/*********************/ +/***********************/ +/* buffer.c */ +/* for Par 1.52-i18n.2 */ +/* Copyright 2001 by */ +/* Adam M. Costello */ +/***********************/ /* This is ANSI C code (C89). */ @@ -18,6 +18,7 @@ #include #include +#include #undef NULL #define NULL ((void *) 0) @@ -60,7 +61,7 @@ blk = malloc(sizeof (block)); items = malloc(maxhere * itemsize); if (!buf || !blk || !items) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); goto nberror; } @@ -127,7 +128,7 @@ new = malloc(sizeof (block)); items = malloc(maxhere * itemsize); if (!new || !items) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); goto aierror; } blk->next = new; @@ -174,7 +175,7 @@ r = malloc(n * itemsize); if (!r) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); return NULL; } diff -ru par-1.52.orig/buffer.h par-1.52-i18n.2/buffer.h --- par-1.52.orig/buffer.h 2001-03-09 00:51:25.000000000 +0100 +++ par-1.52-i18n.2/buffer.h 2006-08-03 16:27:06.000000000 +0200 @@ -1,9 +1,9 @@ -/*********************/ -/* buffer.h */ -/* for Par 1.52 */ -/* Copyright 2001 by */ -/* Adam M. Costello */ -/*********************/ +/***********************/ +/* buffer.h */ +/* for Par 1.52-i18n.2 */ +/* Copyright 2001 by */ +/* Adam M. Costello */ +/***********************/ /* This is ANSI C code (C89). */ diff -ru par-1.52.orig/charset.c par-1.52-i18n.2/charset.c --- par-1.52.orig/charset.c 2001-04-02 23:51:48.000000000 +0200 +++ par-1.52-i18n.2/charset.c 2006-08-03 16:27:06.000000000 +0200 @@ -1,9 +1,11 @@ -/*********************/ -/* charset.c */ -/* for Par 1.52 */ -/* Copyright 2001 by */ -/* Adam M. Costello */ -/*********************/ +/***********************/ +/* charset.c */ +/* for Par 1.52-i18n.2 */ +/* Copyright 2001 by */ +/* Adam M. Costello */ +/* Modified by */ +/* Jérôme Pouiller */ +/***********************/ /* This is ANSI C code (C89). */ @@ -22,6 +24,8 @@ #include #include #include +#include +#include #undef NULL #define NULL ((void *) 0) @@ -39,8 +43,8 @@ typedef unsigned char csflag_t; struct charset { - char *inlist; /* Characters in inlist are in the set. */ - char *outlist; /* Characters in outlist are not in the set. */ + wchar_t *inlist; /* Characters in inlist are in the set. */ + wchar_t *outlist; /* Characters in outlist are not in the set. */ /* inlist and outlist must have no common characters. */ /* inlist and outlist may be NULL, which acts like "". */ csflag_t flags; /* Characters in neither list are in the set if they */ @@ -56,25 +60,25 @@ CS_NUL = 8; /* Includes the NUL character. */ -static int appearsin(char c, const char *str) +static int appearsin(wchar_t c, const wchar_t *str) /* Returns 0 if c is '\0' or str is NULL or c */ /* does not appear in *str. Otherwise returns 1. */ { - return c && str && strchr(str,c); + return c && str && wcschr(str,c); } -static int hexdigtoint(char c) +static int hexdigtoint(wchar_t c) /* Returns the value represented by the hexadecimal */ /* digit c, or -1 if c is not a hexadecimal digit. */ { - const char *p, * const hexdigits = "0123456789ABCDEFabcdef"; + const wchar_t *p, * const hexdigits = L"0123456789ABCDEFabcdef"; int n; if (!c) return -1; - p = strchr(hexdigits, *(unsigned char *)&c); + p = wcschr(hexdigits, c); if (!p) return -1; n = p - hexdigits; if (n >= 16) n -= 6; @@ -91,35 +95,46 @@ { charset *cset = NULL; buffer *cbuf = NULL; - const char *p, * const singleescapes = "_sbqQx"; + const wchar_t *p, * const singleescapes = L"_sbqQx"; int hex1, hex2; - char ch; - + wchar_t ch; + wchar_t *wstr; + + wstr = (wchar_t *) malloc((strlen(str) + 1) * sizeof(wchar_t)); + if (!wstr) { + wcscpy(errmsg,outofmem); + goto pcserror; + } + if ((size_t)(-1) == mbstowcs(wstr, str, strlen(str) + 1)) { + wcscpy(errmsg,mbserror); + goto pcserror; + } cset = malloc(sizeof (charset)); if (!cset) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); goto pcserror; } cset->inlist = cset->outlist = NULL; cset->flags = 0; - cbuf = newbuffer(sizeof (char), errmsg); + cbuf = newbuffer(sizeof (wchar_t), errmsg); if (*errmsg) goto pcserror; - for (p = str; *p; ++p) - if (*p == '_') { + for (p = wstr; *p; ++p) + if (*p == L'_') { ++p; if (appearsin(*p, singleescapes)) { - if (*p == '_') ch = '_' ; - else if (*p == 's') ch = ' ' ; - else if (*p == 'b') ch = '\\'; - else if (*p == 'q') ch = '\''; - else if (*p == 'Q') ch = '\"'; + if (*p == L'_') ch = L'_' ; + else if (*p == L's') ch = L' ' ; + else if (*p == L'b') ch = L'\\'; + else if (*p == L'q') ch = L'\''; + else if (*p == L'Q') ch = L'\"'; else /* *p == 'x' */ { + /* FIXME _x metacharacter should allow wide characters input.*/ hex1 = hexdigtoint(p[1]); hex2 = hexdigtoint(p[2]); if (hex1 < 0 || hex2 < 0) goto pcsbadstr; - *(unsigned char *)&ch = 16 * hex1 + hex2; + ch = 16 * hex1 + hex2; p += 2; } if (!ch) @@ -130,14 +145,14 @@ } } else { - if (*p == 'A') cset->flags |= CS_UCASE; - else if (*p == 'a') cset->flags |= CS_LCASE; - else if (*p == '0') cset->flags |= CS_DIGIT; + if (*p == L'A') cset->flags |= CS_UCASE; + else if (*p == L'a') cset->flags |= CS_LCASE; + else if (*p == L'0') cset->flags |= CS_DIGIT; else goto pcsbadstr; } } else { - additem(cbuf,p,errmsg); + additem(cbuf, p,errmsg); if (*errmsg) goto pcserror; } ch = '\0'; @@ -149,11 +164,12 @@ pcscleanup: if (cbuf) freebuffer(cbuf); + if (wstr) free(wstr); return cset; pcsbadstr: - sprintf(errmsg, "Bad charset syntax: %.*s\n", errmsg_size - 22, str); + swprintf(errmsg, errmsg_size, L"Bad charset syntax: %.*s\n", errmsg_size - 22, str); pcserror: @@ -171,14 +187,14 @@ } -int csmember(char c, const charset *cset) +int csmember(wchar_t c, const charset *cset) { return appearsin(c, cset->inlist) || ( !appearsin(c, cset->outlist) && - ( (cset->flags & CS_LCASE && islower(*(unsigned char *)&c)) || - (cset->flags & CS_UCASE && isupper(*(unsigned char *)&c)) || - (cset->flags & CS_DIGIT && isdigit(*(unsigned char *)&c)) || + ( (cset->flags & CS_LCASE && iswlower(*(wint_t *)&c)) || + (cset->flags & CS_UCASE && iswupper(*(wint_t *)&c)) || + (cset->flags & CS_DIGIT && iswdigit(*(wint_t *)&c)) || (cset->flags & CS_NUL && !c ) ) ); } @@ -191,16 +207,16 @@ { charset *csu; buffer *inbuf = NULL, *outbuf = NULL; - char *lists[4], **list, *p, nullchar = '\0'; + wchar_t *lists[4], **list, *p, nullchar = L'\0'; csu = malloc(sizeof (charset)); if (!csu) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); goto csuderror; } - inbuf = newbuffer(sizeof (char), errmsg); + inbuf = newbuffer(sizeof (wchar_t), errmsg); if (*errmsg) goto csuderror; - outbuf = newbuffer(sizeof (char), errmsg); + outbuf = newbuffer(sizeof (wchar_t), errmsg); if (*errmsg) goto csuderror; csu->inlist = csu->outlist = NULL; csu->flags = u ? cset1->flags | cset2->flags diff -ru par-1.52.orig/charset.h par-1.52-i18n.2/charset.h --- par-1.52.orig/charset.h 2001-03-09 01:50:35.000000000 +0100 +++ par-1.52-i18n.2/charset.h 2006-08-03 16:27:06.000000000 +0200 @@ -1,9 +1,11 @@ -/*********************/ -/* charset.h */ -/* for Par 1.52 */ -/* Copyright 2001 by */ -/* Adam M. Costello */ -/*********************/ +/***********************/ +/* charset.h */ +/* for Par 1.52-i18n.2 */ +/* Copyright 2001 by */ +/* Adam M. Costello */ +/* Modified by */ +/* Jérôme Pouiller */ +/***********************/ /* This is ANSI C code (C89). */ @@ -11,7 +13,7 @@ /* Note: Those functions declared here which do not use errmsg */ /* always succeed, provided that they are passed valid arguments. */ - +#include #include "errmsg.h" @@ -30,7 +32,7 @@ /* *cset. cset may not be used after this call. */ -int csmember(char c, const charset *cset); +int csmember(wchar_t c, const charset *cset); /* csmember(c,cset) returns 1 if c is a member of *cset, 0 otherwise. */ diff -ru par-1.52.orig/errmsg.c par-1.52-i18n.2/errmsg.c --- par-1.52.orig/errmsg.c 2001-03-09 01:50:46.000000000 +0100 +++ par-1.52-i18n.2/errmsg.c 2006-08-03 16:27:06.000000000 +0200 @@ -1,9 +1,11 @@ -/*********************/ -/* errmsg.c */ -/* for Par 1.52 */ -/* Copyright 2001 by */ -/* Adam M. Costello */ -/*********************/ +/***********************/ +/* errmsg.c */ +/* for Par 1.52-i18n.2 */ +/* Copyright 2001 by */ +/* Adam M. Costello */ +/* Modified by */ +/* Jérôme Pouiller */ +/***********************/ /* This is ANSI C code (C89). */ @@ -11,8 +13,11 @@ #include "errmsg.h" /* Makes sure we're consistent with the declarations. */ -const char * const outofmem = - "Out of memory.\n"; +const wchar_t * const outofmem = + L"Out of memory.\n"; -const char * const impossibility = - "Impossibility #%d has occurred. Please report it.\n"; +const wchar_t * const mbserror = + L"Error in input multibyte string.\n"; + +const wchar_t * const impossibility = + L"Impossibility #%d has occurred. Please report it.\n"; diff -ru par-1.52.orig/errmsg.h par-1.52-i18n.2/errmsg.h --- par-1.52.orig/errmsg.h 2001-03-09 01:50:56.000000000 +0100 +++ par-1.52-i18n.2/errmsg.h 2006-08-03 16:27:06.000000000 +0200 @@ -1,9 +1,11 @@ -/*********************/ -/* errmsg.h */ -/* for Par 1.52 */ -/* Copyright 2001 by */ -/* Adam M. Costello */ -/*********************/ +/***********************/ +/* errmsg.h */ +/* for Par 1.52-i18n.2 */ +/* Copyright 2001 by */ +/* Adam M. Costello */ +/* Modified by */ +/* Jérôme Pouiller */ +/***********************/ /* This is ANSI C code (C89). */ @@ -11,7 +13,7 @@ #ifndef ERRMSG_H #define ERRMSG_H - +#include #define errmsg_size 163 /* This is the maximum number of characters that will */ @@ -20,7 +22,7 @@ /* versions of this header file. */ -typedef char errmsg_t[errmsg_size]; +typedef wchar_t errmsg_t[errmsg_size]; /* Any function which takes the argument errmsg_t errmsg must, before */ /* returning, either set errmsg[0] to '\0' (indicating success), or */ @@ -28,10 +30,13 @@ /* being careful not to overrun the space. */ -extern const char * const outofmem; +extern const wchar_t * const outofmem; /* "Out of memory.\n" */ -extern const char * const impossibility; +extern const wchar_t * const mbserror; + /* "Error in input multibyte string.\n" */ + +extern const wchar_t * const impossibility; /* "Impossibility #%d has occurred. Please report it.\n" */ diff -ru par-1.52.orig/par.1 par-1.52-i18n.2/par.1 --- par-1.52.orig/par.1 2001-04-29 23:16:22.000000000 +0200 +++ par-1.52-i18n.2/par.1 2006-06-27 18:00:53.000000000 +0200 @@ -1,6 +1,6 @@ .\"********************* .\"* par.1 * -.\"* for Par 1.52 * +.\"* for Par 1.52 i18n * .\"* Copyright 2001 by * .\"* Adam M. Costello * .\"********************* @@ -220,7 +220,7 @@ advance the divider over any immediately following spaces. The comprelen of .I S -is the number of characters preceeding the divider. +is the number of characters preceding the divider. .IP comsuflen Given a non-empty sequence .I S @@ -249,7 +249,7 @@ .I body is 1, place the divider just before the first non-space non-body character, then back up -the divider over one immediately preceeding +the divider over one immediately preceding space if there is one. The comsuflen of .I S is the number of characters following the divider. @@ -853,7 +853,7 @@ .IR Tab ) spaces, where .I n -is the number of characters preceeding the +is the number of characters preceding the tab character on the line (evaluated after earlier tab characters have been expanded). .LP @@ -917,7 +917,7 @@ in the .SM OPTIONS section). The first word includes any -spaces that preceed it on the same line. +spaces that preced it on the same line. .LP Let .I L @@ -1135,7 +1135,7 @@ .B par will return .BR \s-1EXIT_FAILURE\s0 . -If the error is local to a single paragraph, the preceeding +If the error is local to a single paragraph, the preceding paragraphs will have been output before the error was detected. Line numbers in error messages are local to the IP in which the error occurred. All diff -ru par-1.52.orig/par.c par-1.52-i18n.2/par.c --- par-1.52.orig/par.c 2001-04-02 06:25:57.000000000 +0200 +++ par-1.52-i18n.2/par.c 2006-08-03 16:27:06.000000000 +0200 @@ -1,9 +1,11 @@ -/*********************/ -/* par.c */ -/* for Par 1.52 */ -/* Copyright 2001 by */ -/* Adam M. Costello */ -/*********************/ +/***********************/ +/* par.c */ +/* for Par 1.52-i18n.2 */ +/* Copyright 2001 by */ +/* Adam M. Costello */ +/* Modified by */ +/* Jérôme Pouiller */ +/***********************/ /* This is ANSI C code (C89). */ @@ -17,6 +19,7 @@ #include #include #include +#include #undef NULL #define NULL ((void *) 0) @@ -126,7 +129,7 @@ /* line, or the fallback prelen and suflen */ /* of the IP containing a non-bodiless line. */ lflag_t flags; /* Boolean properties (see below). */ - char rc; /* The repeated character of a bodiless line. */ + wchar_t rc; /* The repeated character of a bodiless line. */ } lineprop; /* Flags for marking boolean properties: */ @@ -203,7 +206,7 @@ int n; *errmsg = '\0'; - + if (*arg == '-') ++arg; if (!strcmp(arg, "help")) { @@ -277,12 +280,12 @@ badarg: - sprintf(errmsg, "Bad argument: %.*s\n", errmsg_size - 16, savearg); + swprintf(errmsg, errmsg_size,L"Bad argument: %.*s\n", errmsg_size - 16, savearg); *phelp = 1; } -static char **readlines( +static wchar_t **readlines( lineprop **pprops, const charset *protectchars, const charset *quotechars, int Tab, int invis, int quote, errmsg_t errmsg ) @@ -303,8 +306,10 @@ { buffer *cbuf = NULL, *lbuf = NULL, *lpbuf = NULL; int c, empty, blank, firstline, qsonly, oldqsonly = 0, vlnlen, i; - char ch, *ln = NULL, nullchar = '\0', *nullline = NULL, *qpend, - *oldln = NULL, *oldqpend = NULL, *p, *op, *vln = NULL, **lines = NULL; + char ch, *ln = NULL, *qpend, *oldln = NULL, + *oldqpend = NULL, *p, *op; + wchar_t nullchar = L'\0'; + wchar_t *nullline = NULL, *vln = NULL, **lines = NULL; lineprop vprop = { 0, 0, 0, '\0' }, iprop = { 0, 0, 0, '\0' }; /* oldqsonly, oldln, and oldquend don't really need to be initialized. */ @@ -318,7 +323,7 @@ cbuf = newbuffer(sizeof (char), errmsg); if (*errmsg) goto rlcleanup; - lbuf = newbuffer(sizeof (char *), errmsg); + lbuf = newbuffer(sizeof (wchar_t *), errmsg); if (*errmsg) goto rlcleanup; lpbuf = newbuffer(sizeof (lineprop), errmsg); if (*errmsg) goto rlcleanup; @@ -339,7 +344,7 @@ if (quote) { for (qpend = ln; *qpend && csmember(*qpend, quotechars); ++qpend); for (p = qpend; *p == ' ' || csmember(*p, quotechars); ++p); - qsonly = *p == '\0'; + qsonly = (*p == '\0'); while (qpend > ln && qpend[-1] == ' ') --qpend; if (!firstline) { for (p = ln, op = oldln; @@ -358,13 +363,13 @@ } else { vlnlen = p - ln; - vln = malloc((vlnlen + 1) * sizeof (char)); + vln = malloc((vlnlen + 1) * sizeof (wchar_t)); if (!vln) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); goto rlcleanup; } - strncpy(vln,ln,vlnlen); - vln[vlnlen] = '\0'; + mbstowcs(vln,ln,vlnlen + 1); + vln[vlnlen] = L'\0'; additem(lbuf, &vln, errmsg); if (*errmsg) goto rlcleanup; additem(lpbuf, invis ? &iprop : &vprop, errmsg); @@ -373,13 +378,27 @@ } } } + if (oldln != NULL) { + free(oldln); + oldln = NULL; + } oldln = ln; oldqpend = qpend; oldqsonly = qsonly; } - additem(lbuf, &ln, errmsg); + vln = malloc((strlen(ln) + 1) * sizeof (wchar_t)); + if (!vln) { + wcscpy(errmsg, outofmem); + goto rlcleanup; + } + mbstowcs(vln,ln,strlen(ln) + 1); + if (oldln == NULL) { + free(ln); + ln = NULL; + } + additem(lbuf, &vln, errmsg); if (*errmsg) goto rlcleanup; - ln = NULL; + vln = NULL; additem(lpbuf, &vprop, errmsg); if (*errmsg) goto rlcleanup; clearbuffer(cbuf); @@ -403,21 +422,32 @@ } continue; } - if (isspace(c)) ch = ' '; - else blank = 0; + if (isspace(c)) + ch = ' '; + else + blank = 0; additem(cbuf, &ch, errmsg); - if (*errmsg) goto rlcleanup; + if (*errmsg) + goto rlcleanup; } } - + if (!blank) { additem(cbuf, &nullchar, errmsg); if (*errmsg) goto rlcleanup; ln = copyitems(cbuf,errmsg); if (*errmsg) goto rlcleanup; - additem(lbuf, &ln, errmsg); - if (*errmsg) goto rlcleanup; + vln = malloc((strlen(ln) + 1) * sizeof (wchar_t)); + if (!vln) { + wcscpy(errmsg, outofmem); + goto rlcleanup; + } + mbstowcs(vln,ln,strlen(ln) + 1); + free(ln); ln = NULL; + additem(lbuf, &vln, errmsg); + if (*errmsg) goto rlcleanup; + vln = NULL; additem(lpbuf, &vprop, errmsg); if (*errmsg) goto rlcleanup; } @@ -449,7 +479,7 @@ static void compresuflen( - const char * const *lines, const char * const *endline, + const wchar_t * const *lines, const wchar_t * const *endline, const charset *bodychars, int body, int pre, int suf, int *ppre, int *psuf ) /* lines is an array of strings, up to but not including endline. */ @@ -457,9 +487,9 @@ /* lines in lines. Assumes that they have already been determined */ /* to be at least pre and suf. endline must not equal lines. */ { - const char *start, *end, *knownstart, * const *line, *p1, *p2, *knownend, + const wchar_t *start, *end, *knownstart, * const *line, *p1, *p2, *knownend, *knownstart2; - + start = *lines; end = knownstart = start + pre; if (body) @@ -474,7 +504,7 @@ } if (body) for (p1 = end; p1 > knownstart; ) - if (*--p1 != ' ') { + if (*--p1 != L' ') { if (csmember(*p1, bodychars)) end = p1; else @@ -501,18 +531,18 @@ } if (body) { for (p1 = start; - start < knownend && (*start == ' ' || csmember(*start, bodychars)); + start < knownend && (*start == L' ' || csmember(*start, bodychars)); ++start); - if (start > p1 && start[-1] == ' ') --start; + if (start > p1 && start[-1] == L' ') --start; } else - while (end - start >= 2 && *start == ' ' && start[1] == ' ') ++start; + while (end - start >= 2 && *start == L' ' && start[1] == L' ') ++start; *psuf = end - start; } static void delimit( - const char * const *lines, const char * const *endline, + const wchar_t * const *lines, const wchar_t * const *endline, const charset *bodychars, int repeat, int body, int div, int pre, int suf, lineprop *props ) @@ -523,8 +553,8 @@ /* and comsuflen of the lines in lines have already been */ /* determined to be at least pre and suf, respectively. */ { - const char * const *line, *end, *p, * const *nextline; - char rc; + const wchar_t * const *line, *end, *p, * const *nextline; + wchar_t rc; lineprop *prop, *nextprop; int anybodiless = 0, status; @@ -545,8 +575,8 @@ for (end = *line; *end; ++end); end -= suf; p = *line + pre; - rc = p < end ? *p : ' '; - if (rc != ' ' && (!repeat || end - p < repeat)) + rc = p < end ? *p : L' '; + if (rc != L' ' && (!repeat || end - p < repeat)) prop->flags &= ~L_BODILESS; else while (p < end) { @@ -589,9 +619,9 @@ } line = lines, prop = props; - status = ((*lines)[pre] == ' '); + status = ((*lines)[pre] == L' '); do { - if (((*line)[pre] == ' ') == status) + if (((*line)[pre] == L' ') == status) prop->flags |= L_FIRST; ++line, ++prop; } while (line < endline); @@ -599,14 +629,14 @@ static void marksuperf( - const char * const * lines, const char * const * endline, lineprop *props + const wchar_t * const * lines, const wchar_t * const * endline, lineprop *props ) /* lines points to the first line of a segment, and endline to one */ /* line beyond the last line in the segment. Sets L_SUPERF bits in */ /* the flags fields of the props array whenever the corresponding */ /* line is superfluous. L_BODILESS bits must already be set. */ { - const char * const *line, *p; + const wchar_t * const *line, *p; lineprop *prop, *mprop, dummy; int inbody, num, mnum; @@ -619,7 +649,7 @@ for (line = lines, prop = props; line < endline; ++line, ++prop) if (isvacant(prop)) { for (num = 0, p = *line; *p; ++p) - if (*p != ' ') ++num; + if (*p != L' ') ++num; if (inbody || num < mnum) mnum = num, mprop = prop; inbody = 0; @@ -631,7 +661,7 @@ static void setaffixes( - const char * const *inlines, const char * const *endline, + const wchar_t * const *inlines, const wchar_t * const *endline, const lineprop *props, const charset *bodychars, const charset *quotechars, int hang, int body, int quote, int *pafp, int *pfs, int *pprefix, int *psuffix @@ -644,7 +674,7 @@ /* default value as specified in "par.doc". */ { int numin, pre, suf; - const char *p; + const wchar_t *p; numin = endline - inlines; @@ -666,11 +696,11 @@ } -static void freelines(char **lines) +static void freelines(wchar_t **lines) /* Frees the elements of lines, and lines itself. */ /* lines is a NULL-terminated array of strings. */ { - char **line; + wchar_t **line; for (line = lines; *line; ++line) free(*line); @@ -678,18 +708,21 @@ free(lines); } - int main(int argc, const char * const *argv) { int help = 0, version = 0, hang = 0, prefix = -1, repeat = 0, suffix = -1, Tab = 1, width = 72, body = 0, cap = 0, div = 0, Err = 0, expel = 0, fit = 0, guess = 0, invis = 0, just = 0, last = 0, quote = 0, Report = 0, touch = -1; - int prefixbak, suffixbak, c, sawnonblank, oweblank, n, i, afp, fs; + int prefixbak, suffixbak, sawnonblank, oweblank, n, i, afp, fs; charset *bodychars = NULL, *protectchars = NULL, *quotechars = NULL; - char *parinit = NULL, *arg, **inlines = NULL, **endline, **firstline, *end, - **nextline, **outlines = NULL, **line, ch; - const char *env, * const whitechars = " \f\n\r\t\v"; + char ch; + wint_t c; + char *arg, *parinit = NULL; + wchar_t *end, **nextline, **inlines = NULL, **endline, **firstline, + **outlines = NULL, **line; + const char *env; + const char * const whitechars = " \f\n\r\t\v"; errmsg_t errmsg = { '\0' }; lineprop *props = NULL, *firstprop, *nextprop; FILE *errout; @@ -728,7 +761,7 @@ if (env) { parinit = malloc((strlen(env) + 1) * sizeof (char)); if (!parinit) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); goto parcleanup; } strcpy(parinit,env); @@ -756,16 +789,15 @@ } if (Tab == 0) { - strcpy(errmsg, " must not be 0.\n"); + wcscpy(errmsg, L" must not be 0.\n"); goto parcleanup; } if (touch < 0) touch = fit || last; prefixbak = prefix; suffixbak = suffix; - -/* Main loop: */ - + + /* Main loop: */ for (sawnonblank = oweblank = 0; ; ) { for (;;) { c = getchar(); @@ -778,7 +810,7 @@ if (csmember(ch, protectchars)) { sawnonblank = 1; if (oweblank) { - puts(""); + fputwc('\n', stdout); oweblank = 0; } while (ch != '\n') { @@ -797,8 +829,7 @@ inlines = readlines(&props, protectchars, quotechars, Tab, invis, quote, errmsg); if (*errmsg) goto parcleanup; - - for (endline = inlines; *endline; ++endline); + for (endline = inlines; *endline; ++endline) ; if (endline == inlines) { free(inlines); inlines = NULL; @@ -807,19 +838,20 @@ sawnonblank = 1; if (oweblank) { - puts(""); + fputwc('\n', stdout); oweblank = 0; } - delimit((const char * const *) inlines, - (const char * const *) endline, + delimit((const wchar_t * const *) inlines, + (const wchar_t * const *) endline, bodychars, repeat, body, div, 0, 0, props); if (expel) - marksuperf((const char * const *) inlines, - (const char * const *) endline, props); + marksuperf((const wchar_t * const *) inlines, + (const wchar_t * const *) endline, props); firstline = inlines, firstprop = props; + do { if (isbodiless(firstprop)) { if (!isinvis(firstprop) && !(expel && issuperf(firstprop))) { @@ -827,18 +859,18 @@ if (!repeat || (firstprop->rc == ' ' && !firstprop->s)) { while (end > *firstline && end[-1] == ' ') --end; *end = '\0'; - puts(*firstline); + fwprintf(stdout, L"%ls\n", *firstline); } else { n = width - firstprop->p - firstprop->s; if (n < 0) { - sprintf(errmsg,impossibility,5); + swprintf(errmsg,errmsg_size,impossibility,5); goto parcleanup; } - printf("%.*s", firstprop->p, *firstline); + fwprintf(stdout, L"%.*ls", firstprop->p, *firstline); for (i = n; i; --i) - putchar(*(unsigned char *)&firstprop->rc); - puts(end - firstprop->s); + fputwc(firstprop->rc, stdout); + fwprintf(stdout, L"%ls\n", end - firstprop->s); } } ++firstline, ++firstprop; @@ -848,28 +880,26 @@ for (nextline = firstline + 1, nextprop = firstprop + 1; nextline < endline && !isbodiless(nextprop) && !isfirst(nextprop); ++nextline, ++nextprop); - + prefix = prefixbak, suffix = suffixbak; - setaffixes((const char * const *) firstline, - (const char * const *) nextline, firstprop, bodychars, + setaffixes((const wchar_t * const *) firstline, + (const wchar_t * const *) nextline, firstprop, bodychars, quotechars, hang, body, quote, &afp, &fs, &prefix, &suffix); if (width <= prefix + suffix) { - sprintf(errmsg, - " (%d) <= (%d) + (%d)\n", + swprintf(errmsg,errmsg_size, + L" (%d) <= (%d) + (%d)\n", width, prefix, suffix); goto parcleanup; } outlines = - reformat((const char * const *) firstline, - (const char * const *) nextline, + reformat((const wchar_t * const *) firstline, + (const wchar_t * const *) nextline, afp, fs, hang, prefix, suffix, width, cap, fit, guess, just, last, Report, touch, errmsg); if (*errmsg) goto parcleanup; - for (line = outlines; *line; ++line) - puts(*line); - + fwprintf(stdout, L"%ls\n", *line); freelines(outlines); outlines = NULL; @@ -894,8 +924,12 @@ if (outlines) freelines(outlines); errout = Err ? stderr : stdout; - if (*errmsg) fprintf(errout, "par error:\n%.*s", errmsg_size, errmsg); - if (version) fputs("par 1.52\n",errout); + if (*errmsg) fwprintf(errout, L"par error:\n%.*ls", errmsg_size, errmsg); +#ifdef NOWIDTH + if (version) fputws(L"par 1.52-i18n.2 (without wcwidth() support)\n",errout); +#else + if (version) fputws(L"par 1.52-i18n.2\n",errout); +#endif if (help) fputs(usagemsg,errout); return *errmsg ? EXIT_FAILURE : EXIT_SUCCESS; diff -ru par-1.52.orig/par.doc par-1.52-i18n.2/par.doc --- par-1.52.orig/par.doc 2001-04-29 23:17:28.000000000 +0200 +++ par-1.52-i18n.2/par.doc 2006-06-27 18:00:53.000000000 +0200 @@ -1,6 +1,6 @@ ********************* * par.doc * - * for Par 1.52 * + * for Par 1.52 i18n * * Copyright 2001 by * * Adam M. Costello * ********************* diff -ru par-1.52.orig/reformat.c par-1.52-i18n.2/reformat.c --- par-1.52.orig/reformat.c 2001-03-22 05:17:15.000000000 +0100 +++ par-1.52-i18n.2/reformat.c 2006-08-03 16:27:06.000000000 +0200 @@ -1,9 +1,11 @@ -/*********************/ -/* reformat.c */ -/* for Par 1.52 */ -/* Copyright 2001 by */ -/* Adam M. Costello */ -/*********************/ +/***********************/ +/* reformat.c */ +/* for Par 1.52-i18n.2 */ +/* Copyright 2001 by */ +/* Adam M. Costello */ +/* Modified by */ +/* Jérôme Pouiller */ +/***********************/ /* This is ANSI C code (C89). */ @@ -16,6 +18,7 @@ #include #include #include +#include #undef NULL #define NULL ((void *) 0) @@ -33,14 +36,15 @@ typedef unsigned char wflag_t; typedef struct word { - const char *chrs; /* Pointer to the characters in the word */ + const wchar_t *chrs; /* Pointer to the characters in the word */ /* (NOT terminated by '\0'). */ struct word *prev, /* Pointer to previous word. */ *next, /* Pointer to next word. */ /* Supposing this word were the first... */ *nextline; /* Pointer to first word in next line. */ int score, /* Value of the objective function. */ - length; /* Length of this word. */ + length, /* Length (in widechar) of this word. */ + width; /* Visual width of this word. */ wflag_t flags; /* Notable properties of this word. */ } word; @@ -57,17 +61,36 @@ #define iscurious(w) (((w)->flags & 2) != 0) #define iscapital(w) (((w)->flags & 4) != 0) +static int getWidth(const wchar_t *beg, const wchar_t *end) +/* Compute (visual) width of a word. This function is aware */ +/* about double-width characters used in oriental langages. */ +{ + int ret, tmp; + + for (ret = 0; beg != end; beg++) { +#ifdef NOWIDTH + tmp = 1; +#else + tmp = wcwidth(*beg); +#endif + if (tmp < 0) + tmp = 0; + ret += tmp; + } + + return ret; +} static int checkcapital(word *w) /* Returns 1 if *w is capitalized according to the definition */ /* in par.doc (assuming is 0), or 0 if not. */ { - const char *p, *end; + const wchar_t *p, *end; for (p = w->chrs, end = p + w->length; - p < end && !isalnum(*(unsigned char *)p); + p < end && !iswalnum(*p); ++p); - return p < end && !islower(*(unsigned char *)p); + return p < end && !iswlower(*p); } @@ -75,19 +98,19 @@ /* Returns 1 if *w is curious according to */ /* the definition in par.doc, or 0 if not. */ { - const char *start, *p; - char ch; + const wchar_t *start, *p; + wchar_t ch; for (start = w->chrs, p = start + w->length; p > start; --p) { ch = p[-1]; - if (isalnum(*(unsigned char *)&ch)) return 0; - if (ch == '.' || ch == '?' || ch == '!' || ch == ':') break; + if (iswalnum(*(wchar_t *)&ch)) return 0; + if (ch == L'.' || ch == L'?' || ch == L'!' || ch == L':') break; } if (p <= start + 1) return 0; --p; - do if (isalnum(*(unsigned char *)--p)) return 1; + do if (iswalnum(*(wint_t *)--p)) return 1; while (p > start); return 0; @@ -95,31 +118,32 @@ static int simplebreaks(word *head, word *tail, int L, int last) - -/* Chooses line breaks in a list of words which maximize the length of the */ -/* shortest line. L is the maximum line length. The last line counts as a */ -/* line only if last is non-zero. _head must point to a dummy word, and tail */ -/* must point to the last word, whose next field must be NULL. Returns the */ -/* length of the shortest line on success, -1 if there is a word of length */ -/* greater than L, or L if there are no lines. */ +/* Chooses line breaks in a list of words which maximize */ +/* the length of the shortest line. L is the maximum line */ +/* length. The last line counts as a line only if last is */ +/* non-zero. _head must point to a dummy word, and tail */ +/* must point to the last word, whose next field must be */ +/* NULL. Returns the length of the shortest line on */ +/* success, -1 if there is a word of length greater than L, */ +/* or L if there are no lines. */ { word *w1, *w2; int linelen, score; if (!head->next) return L; - for (w1 = tail, linelen = w1->length; + for (w1 = tail, linelen = w1->width; w1 != head && linelen <= L; - linelen += isshifted(w1), w1 = w1->prev, linelen += 1 + w1->length) { + linelen += isshifted(w1), w1 = w1->prev, linelen += 1 + w1->width) { w1->score = last ? linelen : L; w1->nextline = NULL; } for ( ; w1 != head; w1 = w1->prev) { w1->score = -1; - for (linelen = w1->length, w2 = w1->next; + for (linelen = w1->width, w2 = w1->next; linelen <= L; - linelen += 1 + isshifted(w2) + w2->length, w2 = w2->next) { + linelen += 1 + isshifted(w2) + w2->width, w2 = w2->next) { score = w2->score; if (linelen < score) score = linelen; if (score >= w1->score) { @@ -168,7 +192,7 @@ shortest = simplebreaks(head,tail,target,last); if (shortest < 0) { - sprintf(errmsg,impossibility,1); + swprintf(errmsg,errmsg_size,impossibility,1); return; } @@ -178,9 +202,9 @@ w1 = tail; do { w1->score = -1; - for (linelen = w1->length, w2 = w1->next; + for (linelen = w1->width, w2 = w1->next; linelen <= target; - linelen += 1 + isshifted(w2) + w2->length, w2 = w2->next) { + linelen += 1 + isshifted(w2) + w2->width, w2 = w2->next) { extra = target - linelen; minlen = shortest; if (w2) @@ -202,7 +226,7 @@ } while (w1 != head); if (head->next->score < 0) - sprintf(errmsg,impossibility,2); + swprintf(errmsg,errmsg_size,impossibility,2); } @@ -225,9 +249,9 @@ w1 = tail; do { w1->score = L; - for (numgaps = 0, extra = L - w1->length, w2 = w1->next; + for (numgaps = 0, extra = L - w1->width, w2 = w1->next; extra >= 0; - ++numgaps, extra -= 1 + isshifted(w2) + w2->length, w2 = w2->next) { + ++numgaps, extra -= 1 + isshifted(w2) + w2->width, w2 = w2->next) { gap = numgaps ? (extra + numgaps - 1) / numgaps : L; if (w2) score = w2->score; @@ -247,7 +271,7 @@ maxgap = head->next->score; if (maxgap >= L) { - strcpy(errmsg, "Cannot justify.\n"); + wcscpy(errmsg, L"Cannot justify.\n"); return; } @@ -257,9 +281,9 @@ w1 = tail; do { w1->score = -1; - for (numgaps = 0, extra = L - w1->length, w2 = w1->next; + for (numgaps = 0, extra = L - w1->width, w2 = w1->next; extra >= 0; - ++numgaps, extra -= 1 + isshifted(w2) + w2->length, w2 = w2->next) { + ++numgaps, extra -= 1 + isshifted(w2) + w2->width, w2 = w2->next) { gap = numgaps ? (extra + numgaps - 1) / numgaps : L; if (w2) score = w2->score; @@ -288,40 +312,39 @@ } while (w1 != head); if (head->next->score < 0) - sprintf(errmsg,impossibility,3); + swprintf(errmsg,errmsg_size,impossibility,3); } -char **reformat( - const char * const *inlines, const char * const *endline, int afp, int fs, +wchar_t **reformat( + const wchar_t * const *inlines, const wchar_t * const *endline, int afp, int fs, int hang, int prefix, int suffix, int width, int cap, int fit, int guess, int just, int last, int Report, int touch, errmsg_t errmsg ) { int numin, affix, L, onfirstword = 1, linelen, numout, numgaps, extra, phase; - const char * const *line, **suffixes = NULL, **suf, *end, *p1, *p2; - char *q1, *q2, **outlines = NULL; + const wchar_t * const *line, **suffixes = NULL, **suf, *end, *p1, *p2; + wchar_t *q1, *q2, **outlines = NULL; word dummy, *head, *tail, *w1, *w2; buffer *pbuf = NULL; /* Initialization: */ - *errmsg = '\0'; dummy.next = dummy.prev = NULL; dummy.flags = 0; head = tail = &dummy; numin = endline - inlines; if (numin <= 0) { - sprintf(errmsg,impossibility,4); + swprintf(errmsg,errmsg_size,impossibility,4); goto rfcleanup; } numgaps = extra = 0; /* unnecessary, but quiets compiler warnings */ /* Allocate space for pointers to the suffixes: */ - suffixes = malloc(numin * sizeof (const char *)); + suffixes = malloc(numin * sizeof (const wchar_t *)); if (!suffixes) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); goto rfcleanup; } @@ -334,7 +357,7 @@ do { for (end = *line; *end; ++end); if (end - *line < affix) { - sprintf(errmsg, + swprintf(errmsg,errmsg_size, "Line %d shorter than + = %d + %d = %d\n", line - inlines + 1, prefix, suffix, affix); goto rfcleanup; @@ -343,17 +366,17 @@ *suf = end; p1 = *line + prefix; for (;;) { - while (p1 < end && *p1 == ' ') ++p1; + while (p1 < end && *p1 == L' ') ++p1; if (p1 == end) break; p2 = p1; if (onfirstword) { p1 = *line + prefix; onfirstword = 0; } - while (p2 < end && *p2 != ' ') ++p2; + while (p2 < end && *p2 != L' ') ++p2; w1 = malloc(sizeof (word)); if (!w1) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); goto rfcleanup; } w1->next = NULL; @@ -361,6 +384,7 @@ tail = tail->next = w1; w1->chrs = p1; w1->length = p2 - p1; + w1->width = getWidth(p1, p2); w1->flags = 0; p1 = p2; } @@ -397,20 +421,20 @@ if (Report) for (w2 = head->next; w2; w2 = w2->next) { - if (w2->length > L) { - linelen = w2->length; + if (w2->width > L) { + linelen = w2->width; if (linelen > errmsg_size - 17) linelen = errmsg_size - 17; - sprintf(errmsg, "Word too long: %.*s\n", linelen, w2->chrs); + swprintf(errmsg,errmsg_size, L"Word too long: %.*ls\n", linelen, w2->chrs); goto rfcleanup; } } else for (w2 = head->next; w2; w2 = w2->next) - while (w2->length > L) { + while (w2->width > L) { w1 = malloc(sizeof (word)); if (!w1) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); goto rfcleanup; } w1->next = w2; @@ -420,7 +444,9 @@ w1->chrs = w2->chrs; w2->chrs += L; w1->length = L; + w1->width = getWidth(w1->chrs, w1->chrs + L); w2->length -= L; + w2->width -= w1->width; w1->flags = 0; if (iscapital(w2)) { w1->flags |= W_CAPITAL; @@ -444,9 +470,9 @@ L = 0; w1 = head->next; while (w1) { - for (linelen = w1->length, w2 = w1->next; + for (linelen = w1->width, w2 = w1->next; w2 != w1->nextline; - linelen += 1 + isshifted(w2) + w2->length, w2 = w2->next); + linelen += 1 + isshifted(w2) + w2->width, w2 = w2->next); if (linelen > L) L = linelen; w1 = w2; } @@ -454,67 +480,67 @@ /* Construct the lines: */ - pbuf = newbuffer(sizeof (char *), errmsg); + pbuf = newbuffer(sizeof (wchar_t *), errmsg); if (*errmsg) goto rfcleanup; numout = 0; w1 = head->next; while (numout < hang || w1) { if (w1) - for (w2 = w1->next, numgaps = 0, extra = L - w1->length; + for (w2 = w1->next, numgaps = 0, extra = L - w1->width; w2 != w1->nextline; - ++numgaps, extra -= 1 + isshifted(w2) + w2->length, w2 = w2->next); + ++numgaps, extra -= 1 + isshifted(w2) + w2->width, w2 = w2->next); linelen = suffix || (just && (w2 || last)) ? L + affix : w1 ? prefix + L - extra : prefix; - q1 = malloc((linelen + 1) * sizeof (char)); + q1 = malloc((linelen + 1) * sizeof (wchar_t)); if (!q1) { - strcpy(errmsg,outofmem); + wcscpy(errmsg,outofmem); goto rfcleanup; } additem(pbuf, &q1, errmsg); if (*errmsg) goto rfcleanup; ++numout; q2 = q1 + prefix; - if (numout <= numin) memcpy(q1, inlines[numout - 1], prefix); - else if (numin > hang ) memcpy(q1, endline[-1], prefix); + if (numout <= numin) memcpy(q1, inlines[numout - 1], prefix * sizeof(wchar_t)); + else if (numin > hang ) memcpy(q1, endline[-1], prefix * sizeof(wchar_t)); else { if (afp > prefix) afp = prefix; - memcpy(q1, endline[-1], afp); + memcpy(q1, endline[-1], afp * sizeof(wchar_t)); q1 += afp; - while (q1 < q2) *q1++ = ' '; + while (q1 < q2) *q1++ = L' '; } q1 = q2; if (w1) { phase = numgaps / 2; for (w2 = w1; ; ) { - memcpy(q1, w2->chrs, w2->length); + memcpy(q1, w2->chrs, w2->length * sizeof(wchar_t)); q1 += w2->length; w2 = w2->next; if (w2 == w1->nextline) break; - *q1++ = ' '; + *q1++ = L' '; if (just && (w1->nextline || last)) { phase += extra; while (phase >= numgaps) { - *q1++ = ' '; + *q1++ = L' '; phase -= numgaps; } } - if (isshifted(w2)) *q1++ = ' '; + if (isshifted(w2)) *q1++ = L' '; } } q2 += linelen - affix; - while (q1 < q2) *q1++ = ' '; + while (q1 < q2) *q1++ = L' '; q2 = q1 + suffix; - if (numout <= numin) memcpy(q1, suffixes[numout - 1], suffix); - else if (numin > hang ) memcpy(q1, suffixes[numin - 1], suffix); + if (numout <= numin) memcpy(q1, suffixes[numout - 1], suffix * sizeof(wchar_t)); + else if (numin > hang ) memcpy(q1, suffixes[numin - 1], suffix * sizeof(wchar_t)); else { if (fs > suffix) fs = suffix; - memcpy(q1, suffixes[numin - 1], fs); + memcpy(q1, suffixes[numin - 1], fs * sizeof(wchar_t)); q1 += fs; - while(q1 < q2) *q1++ = ' '; + while(q1 < q2) *q1++ = L' '; } - *q2 = '\0'; + *q2 = L'\0'; if (w1) w1 = w1->nextline; } @@ -543,5 +569,6 @@ freebuffer(pbuf); } + return outlines; } diff -ru par-1.52.orig/reformat.h par-1.52-i18n.2/reformat.h --- par-1.52.orig/reformat.h 2001-03-09 01:53:43.000000000 +0100 +++ par-1.52-i18n.2/reformat.h 2006-08-03 16:27:06.000000000 +0200 @@ -1,18 +1,20 @@ -/*********************/ -/* reformat.h */ -/* for Par 1.52 */ -/* Copyright 2001 by */ -/* Adam M. Costello */ -/*********************/ +/***********************/ +/* reformat.h */ +/* for Par 1.52-i18n.2 */ +/* Copyright 2001 by */ +/* Adam M. Costello */ +/* Modified by */ +/* Jérôme Pouiller */ +/***********************/ /* This is ANSI C code (C89). */ #include "errmsg.h" +#include - -char **reformat( - const char * const *inlines, const char * const *endline, int afp, int fs, +wchar_t **reformat( + const wchar_t * const *inlines, const wchar_t * const *endline, int afp, int fs, int hang, int prefix, int suffix, int width, int cap, int fit, int guess, int just, int last, int Report, int touch, errmsg_t errmsg ); diff -ru par-1.52.orig/releasenotes par-1.52-i18n.2/releasenotes --- par-1.52.orig/releasenotes 2001-04-29 23:12:05.000000000 +0200 +++ par-1.52-i18n.2/releasenotes 2006-08-03 16:28:31.000000000 +0200 @@ -1,13 +1,22 @@ - ********************* - * releasenotes * - * for Par 1.52 * - * Copyright 2001 by * - * Adam M. Costello * - ********************* + *********************** + * releasenotes * + * for Par 1.52-i18n.1 * + * Copyright 2001 by * + * Adam M. Costello * + * Modified by * + * Jérôme Pouiller * + *********************** Each entry below describes changes since the previous version. +Par 1.52-i18n.2 released 2006-Aug-03 + Fix bug debian #310495. + +Par 1.52-i18n.1 released 2006-Jun-22 + Changed char in wchar_t. Allow support of multibytes characters. + Added support for double-width characters. + Par 1.52 released 2001-Apr-29 Fixed a portability problem regarding unsigned char versus char. (This was a potential problem only on platforms where char is a