=================================================================== RCS file: /cvs/mandoc/html.c,v retrieving revision 1.151 retrieving revision 1.166 diff -u -p -r1.151 -r1.166 --- mandoc/html.c 2012/05/31 22:29:13 1.151 +++ mandoc/html.c 2014/09/27 09:03:24 1.166 @@ -1,7 +1,7 @@ -/* $Id: html.c,v 1.151 2012/05/31 22:29:13 schwarze Exp $ */ +/* $Id: html.c,v 1.166 2014/09/27 09:03:24 kristaps Exp $ */ /* * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons - * Copyright (c) 2011, 2012 Ingo Schwarze + * Copyright (c) 2011, 2012, 2013, 2014 Ingo Schwarze * * Permission to use, copy, modify, and distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -15,9 +15,7 @@ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#ifdef HAVE_CONFIG_H #include "config.h" -#endif #include @@ -31,6 +29,7 @@ #include #include "mandoc.h" +#include "mandoc_aux.h" #include "libmandoc.h" #include "out.h" #include "html.h" @@ -75,11 +74,10 @@ static const struct htmldata htmltags[TAG_MAX] = { {"i", 0 }, /* TAG_I */ {"code", 0 }, /* TAG_CODE */ {"small", 0 }, /* TAG_SMALL */ + {"style", HTML_CLRLINE}, /* TAG_STYLE */ }; static const char *const htmlattrs[ATTR_MAX] = { - "http-equiv", /* ATTR_HTTPEQUIV */ - "content", /* ATTR_CONTENT */ "name", /* ATTR_NAME */ "rel", /* ATTR_REL */ "href", /* ATTR_HREF */ @@ -92,6 +90,7 @@ static const char *const htmlattrs[ATTR_MAX] = { "summary", /* ATTR_SUMMARY */ "align", /* ATTR_ALIGN */ "colspan", /* ATTR_COLSPAN */ + "charset", /* ATTR_CHARSET */ }; static const char *const roffscales[SCALE_MAX] = { @@ -109,11 +108,13 @@ static const char *const roffscales[SCALE_MAX] = { static void bufncat(struct html *, const char *, size_t); static void print_ctag(struct html *, enum htmltag); +static int print_escape(char); static int print_encode(struct html *, const char *, int); static void print_metaf(struct html *, enum mandoc_esc); static void print_attr(struct html *, const char *, const char *); static void *ml_alloc(char *, enum htmltype); + static void * ml_alloc(char *outopts, enum htmltype type) { @@ -135,16 +136,16 @@ ml_alloc(char *outopts, enum htmltype type) while (outopts && *outopts) switch (getsubopt(&outopts, UNCONST(toks), &v)) { - case (0): + case 0: h->style = v; break; - case (1): + case 1: h->base_man = v; break; - case (2): + case 2: h->base_includes = v; break; - case (3): + case 3: h->oflags |= HTML_FRAGMENT; break; default: @@ -161,7 +162,6 @@ html_alloc(char *outopts) return(ml_alloc(outopts, HTML_HTML_4_01_STRICT)); } - void * xhtml_alloc(char *outopts) { @@ -169,7 +169,6 @@ xhtml_alloc(char *outopts) return(ml_alloc(outopts, HTML_XHTML_1_0_STRICT)); } - void html_free(void *p) { @@ -179,33 +178,29 @@ html_free(void *p) h = (struct html *)p; while ((tag = h->tags.head) != NULL) { - h->tags.head = tag->next; + h->tags.head = tag->next; free(tag); } - + if (h->symtab) mchars_free(h->symtab); free(h); } - void print_gen_head(struct html *h) { struct htmlpair tag[4]; + struct tag *t; - tag[0].key = ATTR_HTTPEQUIV; - tag[0].val = "Content-Type"; - tag[1].key = ATTR_CONTENT; - tag[1].val = "text/html; charset=utf-8"; - print_otag(h, TAG_META, 2, tag); + tag[0].key = ATTR_CHARSET; + tag[0].val = "utf-8"; + print_otag(h, TAG_META, 1, tag); - tag[0].key = ATTR_NAME; - tag[0].val = "resource-type"; - tag[1].key = ATTR_CONTENT; - tag[1].val = "document"; - print_otag(h, TAG_META, 2, tag); + t = print_otag(h, TAG_STYLE, 0, NULL); + print_text(h, "table.head, table.foot { width: 100%; }\n"); + print_tagq(h, t); if (h->style) { tag[0].key = ATTR_REL; @@ -226,18 +221,21 @@ print_metaf(struct html *h, enum mandoc_esc deco) enum htmlfont font; switch (deco) { - case (ESCAPE_FONTPREV): + case ESCAPE_FONTPREV: font = h->metal; break; - case (ESCAPE_FONTITALIC): + case ESCAPE_FONTITALIC: font = HTMLFONT_ITALIC; break; - case (ESCAPE_FONTBOLD): + case ESCAPE_FONTBOLD: font = HTMLFONT_BOLD; break; - case (ESCAPE_FONT): + case ESCAPE_FONTBI: + font = HTMLFONT_BI; + break; + case ESCAPE_FONT: /* FALLTHROUGH */ - case (ESCAPE_FONTROMAN): + case ESCAPE_FONTROMAN: font = HTMLFONT_NONE; break; default: @@ -253,10 +251,20 @@ print_metaf(struct html *h, enum mandoc_esc deco) h->metal = h->metac; h->metac = font; - if (HTMLFONT_NONE != font) - h->metaf = HTMLFONT_BOLD == font ? - print_otag(h, TAG_B, 0, NULL) : - print_otag(h, TAG_I, 0, NULL); + switch (font) { + case HTMLFONT_ITALIC: + h->metaf = print_otag(h, TAG_I, 0, NULL); + break; + case HTMLFONT_BOLD: + h->metaf = print_otag(h, TAG_B, 0, NULL); + break; + case HTMLFONT_BI: + h->metaf = print_otag(h, TAG_B, 0, NULL); + print_otag(h, TAG_I, 0, NULL); + break; + default: + break; + } } int @@ -289,19 +297,19 @@ html_strlen(const char *cp) break; cp++; switch (mandoc_escape(&cp, NULL, NULL)) { - case (ESCAPE_ERROR): + case ESCAPE_ERROR: return(sz); - case (ESCAPE_UNICODE): + case ESCAPE_UNICODE: /* FALLTHROUGH */ - case (ESCAPE_NUMBERED): + case ESCAPE_NUMBERED: /* FALLTHROUGH */ - case (ESCAPE_SPECIAL): + case ESCAPE_SPECIAL: if (skip) skip = 0; else sz++; break; - case (ESCAPE_SKIPCHAR): + case ESCAPE_SKIPCHAR: skip = 1; break; default: @@ -312,13 +320,45 @@ html_strlen(const char *cp) } static int +print_escape(char c) +{ + + switch (c) { + case '<': + printf("<"); + break; + case '>': + printf(">"); + break; + case '&': + printf("&"); + break; + case '"': + printf("""); + break; + case ASCII_NBRSP: + putchar('-'); + break; + case ASCII_HYPH: + putchar('-'); + /* FALLTHROUGH */ + case ASCII_BREAK: + break; + default: + return(0); + } + return(1); +} + +static int print_encode(struct html *h, const char *p, int norecurse) { size_t sz; int c, len, nospace; const char *seq; enum mandoc_esc esc; - static const char rejs[6] = { '\\', '<', '>', '&', ASCII_HYPH, '\0' }; + static const char rejs[9] = { '\\', '<', '>', '&', '"', + ASCII_NBRSP, ASCII_HYPH, ASCII_BREAK, '\0' }; nospace = 0; @@ -337,41 +377,29 @@ print_encode(struct html *h, const char *p, int norecu if ('\0' == *p) break; - switch (*p++) { - case ('<'): - printf("<"); + if (print_escape(*p++)) continue; - case ('>'): - printf(">"); - continue; - case ('&'): - printf("&"); - continue; - case (ASCII_HYPH): - putchar('-'); - continue; - default: - break; - } esc = mandoc_escape(&p, &seq, &len); if (ESCAPE_ERROR == esc) break; switch (esc) { - case (ESCAPE_FONT): + case ESCAPE_FONT: /* FALLTHROUGH */ - case (ESCAPE_FONTPREV): + case ESCAPE_FONTPREV: /* FALLTHROUGH */ - case (ESCAPE_FONTBOLD): + case ESCAPE_FONTBOLD: /* FALLTHROUGH */ - case (ESCAPE_FONTITALIC): + case ESCAPE_FONTITALIC: /* FALLTHROUGH */ - case (ESCAPE_FONTROMAN): + case ESCAPE_FONTBI: + /* FALLTHROUGH */ + case ESCAPE_FONTROMAN: if (0 == norecurse) print_metaf(h, esc); continue; - case (ESCAPE_SKIPCHAR): + case ESCAPE_SKIPCHAR: h->flags |= HTML_SKIPCHAR; continue; default: @@ -384,25 +412,26 @@ print_encode(struct html *h, const char *p, int norecu } switch (esc) { - case (ESCAPE_UNICODE): - /* Skip passed "u" header. */ + case ESCAPE_UNICODE: + /* Skip past "u" header. */ c = mchars_num2uc(seq + 1, len - 1); if ('\0' != c) printf("&#x%x;", c); break; - case (ESCAPE_NUMBERED): + case ESCAPE_NUMBERED: c = mchars_num2char(seq, len); - if ('\0' != c) + if ( ! ('\0' == c || print_escape(c))) putchar(c); break; - case (ESCAPE_SPECIAL): + case ESCAPE_SPECIAL: c = mchars_spec2cp(h->symtab, seq, len); if (c > 0) printf("&#%d;", c); - else if (-1 == c && 1 == len) + else if (-1 == c && 1 == len && + !print_escape(*seq)) putchar((int)*seq); break; - case (ESCAPE_NOSPACE): + case ESCAPE_NOSPACE: if ('\0' == *p) nospace = 1; break; @@ -414,7 +443,6 @@ print_encode(struct html *h, const char *p, int norecu return(nospace); } - static void print_attr(struct html *h, const char *key, const char *val) { @@ -423,9 +451,8 @@ print_attr(struct html *h, const char *key, const char putchar('\"'); } - struct tag * -print_otag(struct html *h, enum htmltag tag, +print_otag(struct html *h, enum htmltag tag, int sz, const struct htmlpair *p) { int i; @@ -463,19 +490,11 @@ print_otag(struct html *h, enum htmltag tag, for (i = 0; i < sz; i++) print_attr(h, htmlattrs[p[i].key], p[i].val); - /* Add non-overridable attributes. */ - - if (TAG_HTML == tag && HTML_XHTML_1_0_STRICT == h->type) { - print_attr(h, "xmlns", "http://www.w3.org/1999/xhtml"); - print_attr(h, "xml:lang", "en"); - print_attr(h, "lang", "en"); - } - /* Accommodate for XML "well-formed" singleton escaping. */ if (HTML_AUTOCLOSE & htmltags[tag].flags) switch (h->type) { - case (HTML_XHTML_1_0_STRICT): + case HTML_XHTML_1_0_STRICT: putchar('/'); break; default: @@ -492,41 +511,22 @@ print_otag(struct html *h, enum htmltag tag, return(t); } - static void print_ctag(struct html *h, enum htmltag tag) { - + printf("", htmltags[tag].name); if (HTML_CLRLINE & htmltags[tag].flags) { h->flags |= HTML_NOSPACE; putchar('\n'); - } + } } void print_gen_decls(struct html *h) { - const char *doctype; - const char *dtd; - const char *name; - switch (h->type) { - case (HTML_HTML_4_01_STRICT): - name = "HTML"; - doctype = "-//W3C//DTD HTML 4.01//EN"; - dtd = "http://www.w3.org/TR/html4/strict.dtd"; - break; - default: - puts(""); - name = "html"; - doctype = "-//W3C//DTD XHTML 1.0 Strict//EN"; - dtd = "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"; - break; - } - - printf("\n", - name, doctype, dtd); + puts(""); } void @@ -544,10 +544,20 @@ print_text(struct html *h, const char *word) } assert(NULL == h->metaf); - if (HTMLFONT_NONE != h->metac) - h->metaf = HTMLFONT_BOLD == h->metac ? - print_otag(h, TAG_B, 0, NULL) : - print_otag(h, TAG_I, 0, NULL); + switch (h->metac) { + case HTMLFONT_ITALIC: + h->metaf = print_otag(h, TAG_I, 0, NULL); + break; + case HTMLFONT_BOLD: + h->metaf = print_otag(h, TAG_B, 0, NULL); + break; + case HTMLFONT_BI: + h->metaf = print_otag(h, TAG_B, 0, NULL); + print_otag(h, TAG_I, 0, NULL); + break; + default: + break; + } assert(word); if ( ! print_encode(h, word, 0)) { @@ -564,14 +574,13 @@ print_text(struct html *h, const char *word) h->flags &= ~HTML_IGNDELIM; } - void print_tagq(struct html *h, const struct tag *until) { struct tag *tag; while ((tag = h->tags.head) != NULL) { - /* + /* * Remember to close out and nullify the current * meta-font and table, if applicable. */ @@ -587,7 +596,6 @@ print_tagq(struct html *h, const struct tag *until) } } - void print_stagq(struct html *h, const struct tag *suntil) { @@ -596,7 +604,7 @@ print_stagq(struct html *h, const struct tag *suntil) while ((tag = h->tags.head) != NULL) { if (suntil && tag == suntil) return; - /* + /* * Remember to close out and nullify the current * meta-font and table, if applicable. */ @@ -632,6 +640,12 @@ void bufcat(struct html *h, const char *p) { + /* + * XXX This is broken and not easy to fix. + * When using the -Oincludes option, buffmt_includes() + * may pass in strings overrunning BUFSIZ, causing a crash. + */ + h->buflen = strlcat(h->buf, p, BUFSIZ); assert(h->buflen < BUFSIZ); } @@ -642,8 +656,8 @@ bufcat_fmt(struct html *h, const char *fmt, ...) va_list ap; va_start(ap, fmt); - (void)vsnprintf(h->buf + (int)h->buflen, - BUFSIZ - h->buflen - 1, fmt, ap); + (void)vsnprintf(h->buf + (int)h->buflen, + BUFSIZ - h->buflen - 1, fmt, ap); va_end(ap); h->buflen = strlen(h->buf); } @@ -663,12 +677,12 @@ buffmt_includes(struct html *h, const char *name) const char *p, *pp; pp = h->base_includes; - + bufinit(h); while (NULL != (p = strchr(pp, '%'))) { bufncat(h, pp, (size_t)(p - pp)); switch (*(p + 1)) { - case('I'): + case'I': bufcat(h, name); break; default: @@ -682,22 +696,21 @@ buffmt_includes(struct html *h, const char *name) } void -buffmt_man(struct html *h, - const char *name, const char *sec) +buffmt_man(struct html *h, const char *name, const char *sec) { const char *p, *pp; pp = h->base_man; - + bufinit(h); while (NULL != (p = strchr(pp, '%'))) { bufncat(h, pp, (size_t)(p - pp)); switch (*(p + 1)) { - case('S'): + case 'S': bufcat(h, sec ? sec : "1"); break; - case('N'): - bufcat_fmt(h, name); + case 'N': + bufcat_fmt(h, "%s", name); break; default: bufncat(h, p, 2); @@ -717,6 +730,8 @@ bufcat_su(struct html *h, const char *p, const struct v = su->scale; if (SCALE_MM == su->unit && 0.0 == (v /= 100.0)) v = 1.0; + else if (SCALE_BU == su->unit) + v /= 24.0; bufcat_fmt(h, "%s: %.2f%s;", p, v, roffscales[su->unit]); }