-/* $Id: html.c,v 1.29 2009/09/16 09:41:24 kristaps Exp $ */
+/* $Id: html.c,v 1.155 2014/03/23 11:25:26 schwarze Exp $ */
/*
- * Copyright (c) 2008, 2009 Kristaps Dzonsons <kristaps@kth.se>
+ * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
+ * Copyright (c) 2011, 2012, 2013, 2014 Ingo Schwarze <schwarze@openbsd.org>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* 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 <sys/types.h>
+
#include <assert.h>
-#include <err.h>
+#include <ctype.h>
+#include <stdarg.h>
#include <stdio.h>
+#include <stdint.h>
#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
-#include "mdoc.h"
-#include "man.h"
-
-#define DOCTYPE "-//W3C//DTD HTML 4.01//EN"
-#define DTD "http://www.w3.org/TR/html4/strict.dtd"
-
-enum htmltag {
- TAG_HTML,
- TAG_HEAD,
- TAG_BODY,
- TAG_META,
- TAG_TITLE,
- TAG_DIV,
- TAG_H1,
- TAG_H2,
- TAG_P,
- TAG_SPAN,
- TAG_LINK,
- TAG_MAX
-};
-
-enum htmlattr {
- ATTR_HTTPEQUIV,
- ATTR_CONTENT,
- ATTR_NAME,
- ATTR_REL,
- ATTR_HREF,
- ATTR_TYPE,
- ATTR_MEDIA,
- ATTR_CLASS,
- ATTR_MAX
-};
+#include "mandoc.h"
+#include "mandoc_aux.h"
+#include "libmandoc.h"
+#include "out.h"
+#include "html.h"
+#include "main.h"
struct htmldata {
- char *name;
+ const char *name;
int flags;
-#define HTML_BLOCK (1 << 0)
+#define HTML_CLRLINE (1 << 0)
+#define HTML_NOSTACK (1 << 1)
+#define HTML_AUTOCLOSE (1 << 2) /* Tag has auto-closure. */
};
static const struct htmldata htmltags[TAG_MAX] = {
- {"html", HTML_BLOCK}, /* TAG_HTML */
- {"head", HTML_BLOCK}, /* TAG_HEAD */
- {"body", HTML_BLOCK}, /* TAG_BODY */
- {"meta", HTML_BLOCK}, /* TAG_META */
- {"title", HTML_BLOCK}, /* TAG_TITLE */
- {"div", HTML_BLOCK}, /* TAG_DIV */
+ {"html", HTML_CLRLINE}, /* TAG_HTML */
+ {"head", HTML_CLRLINE}, /* TAG_HEAD */
+ {"body", HTML_CLRLINE}, /* TAG_BODY */
+ {"meta", HTML_CLRLINE | HTML_NOSTACK | HTML_AUTOCLOSE}, /* TAG_META */
+ {"title", HTML_CLRLINE}, /* TAG_TITLE */
+ {"div", HTML_CLRLINE}, /* TAG_DIV */
{"h1", 0}, /* TAG_H1 */
{"h2", 0}, /* TAG_H2 */
- {"p", HTML_BLOCK}, /* TAG_P */
{"span", 0}, /* TAG_SPAN */
- {"link", HTML_BLOCK}, /* TAG_LINK */
+ {"link", HTML_CLRLINE | HTML_NOSTACK | HTML_AUTOCLOSE}, /* TAG_LINK */
+ {"br", HTML_CLRLINE | HTML_NOSTACK | HTML_AUTOCLOSE}, /* TAG_BR */
+ {"a", 0}, /* TAG_A */
+ {"table", HTML_CLRLINE}, /* TAG_TABLE */
+ {"tbody", HTML_CLRLINE}, /* TAG_TBODY */
+ {"col", HTML_CLRLINE | HTML_NOSTACK | HTML_AUTOCLOSE}, /* TAG_COL */
+ {"tr", HTML_CLRLINE}, /* TAG_TR */
+ {"td", HTML_CLRLINE}, /* TAG_TD */
+ {"li", HTML_CLRLINE}, /* TAG_LI */
+ {"ul", HTML_CLRLINE}, /* TAG_UL */
+ {"ol", HTML_CLRLINE}, /* TAG_OL */
+ {"dl", HTML_CLRLINE}, /* TAG_DL */
+ {"dt", HTML_CLRLINE}, /* TAG_DT */
+ {"dd", HTML_CLRLINE}, /* TAG_DD */
+ {"blockquote", HTML_CLRLINE}, /* TAG_BLOCKQUOTE */
+ {"p", HTML_CLRLINE | HTML_NOSTACK | HTML_AUTOCLOSE}, /* TAG_P */
+ {"pre", HTML_CLRLINE }, /* TAG_PRE */
+ {"b", 0 }, /* TAG_B */
+ {"i", 0 }, /* TAG_I */
+ {"code", 0 }, /* TAG_CODE */
+ {"small", 0 }, /* TAG_SMALL */
};
-static const char *const htmlattrs[ATTR_MAX] = {
- "http-equiv",
- "content",
- "name",
- "rel",
- "href",
- "type",
- "media",
- "class"
+static const char *const htmlattrs[ATTR_MAX] = {
+ "http-equiv", /* ATTR_HTTPEQUIV */
+ "content", /* ATTR_CONTENT */
+ "name", /* ATTR_NAME */
+ "rel", /* ATTR_REL */
+ "href", /* ATTR_HREF */
+ "type", /* ATTR_TYPE */
+ "media", /* ATTR_MEDIA */
+ "class", /* ATTR_CLASS */
+ "style", /* ATTR_STYLE */
+ "width", /* ATTR_WIDTH */
+ "id", /* ATTR_ID */
+ "summary", /* ATTR_SUMMARY */
+ "align", /* ATTR_ALIGN */
+ "colspan", /* ATTR_COLSPAN */
};
-struct htmlpair {
- enum htmlattr key;
- char *val;
+static const char *const roffscales[SCALE_MAX] = {
+ "cm", /* SCALE_CM */
+ "in", /* SCALE_IN */
+ "pc", /* SCALE_PC */
+ "pt", /* SCALE_PT */
+ "em", /* SCALE_EM */
+ "em", /* SCALE_MM */
+ "ex", /* SCALE_EN */
+ "ex", /* SCALE_BU */
+ "em", /* SCALE_VS */
+ "ex", /* SCALE_FS */
};
-struct html {
- int flags;
-#define HTML_NOSPACE (1 << 0)
-};
+static void bufncat(struct html *, const char *, size_t);
+static void print_ctag(struct html *, enum htmltag);
+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);
-#define MDOC_ARGS const struct mdoc_meta *m, \
- const struct mdoc_node *n, \
- struct html *h
-#define MAN_ARGS const struct man_meta *m, \
- const struct man_node *n, \
- struct html *h
-struct htmlmdoc {
- int (*pre)(MDOC_ARGS);
- void (*post)(MDOC_ARGS);
-};
+static void *
+ml_alloc(char *outopts, enum htmltype type)
+{
+ struct html *h;
+ const char *toks[5];
+ char *v;
-static void print_gen_doctype(struct html *);
-static void print_gen_head(struct html *);
-static void print_mdoc(MDOC_ARGS);
-static void print_mdoc_head(MDOC_ARGS);
-static void print_mdoc_node(MDOC_ARGS);
-static void print_man(MAN_ARGS);
-static void print_man_head(MAN_ARGS);
-static void print_man_body(MAN_ARGS);
-static void print_otag(struct html *, enum htmltag,
- int, const struct htmlpair *);
-static void print_ctag(struct html *, enum htmltag);
-static void print_encode(const char *);
-static void print_text(struct html *, const char *);
-static int mdoc_root_pre(MDOC_ARGS);
-static void mdoc_root_post(MDOC_ARGS);
-
-static int mdoc_nd_pre(MDOC_ARGS);
-static int mdoc_nm_pre(MDOC_ARGS);
-static void mdoc_nm_post(MDOC_ARGS);
-static int mdoc_pp_pre(MDOC_ARGS);
-static int mdoc_sh_pre(MDOC_ARGS);
-static void mdoc_sh_post(MDOC_ARGS);
-static int mdoc_ss_pre(MDOC_ARGS);
-static void mdoc_ss_post(MDOC_ARGS);
-
-static const struct htmlmdoc mdocs[MDOC_MAX] = {
- {NULL, NULL}, /* Ap */
- {NULL, NULL}, /* Dd */
- {NULL, NULL}, /* Dt */
- {NULL, NULL}, /* Os */
- {mdoc_sh_pre, mdoc_sh_post }, /* Sh */
- {mdoc_ss_pre, mdoc_ss_post }, /* Ss */
- {mdoc_pp_pre, NULL}, /* Pp */
- {NULL, NULL}, /* D1 */
- {NULL, NULL}, /* Dl */
- {NULL, NULL}, /* Bd */
- {NULL, NULL}, /* Ed */
- {NULL, NULL}, /* Bl */
- {NULL, NULL}, /* El */
- {NULL, NULL}, /* It */
- {NULL, NULL}, /* Ad */
- {NULL, NULL}, /* An */
- {NULL, NULL}, /* Ar */
- {NULL, NULL}, /* Cd */
- {NULL, NULL}, /* Cm */
- {NULL, NULL}, /* Dv */
- {NULL, NULL}, /* Er */
- {NULL, NULL}, /* Ev */
- {NULL, NULL}, /* Ex */
- {NULL, NULL}, /* Fa */
- {NULL, NULL}, /* Fd */
- {NULL, NULL}, /* Fl */
- {NULL, NULL}, /* Fn */
- {NULL, NULL}, /* Ft */
- {NULL, NULL}, /* Ic */
- {NULL, NULL}, /* In */
- {NULL, NULL}, /* Li */
- {mdoc_nd_pre, NULL}, /* Nd */
- {mdoc_nm_pre, mdoc_nm_post}, /* Nm */
- {NULL, NULL}, /* Op */
- {NULL, NULL}, /* Ot */
- {NULL, NULL}, /* Pa */
- {NULL, NULL}, /* Rv */
- {NULL, NULL}, /* St */
- {NULL, NULL}, /* Va */
- {NULL, NULL}, /* Vt */
- {NULL, NULL}, /* Xr */
- {NULL, NULL}, /* %A */
- {NULL, NULL}, /* %B */
- {NULL, NULL}, /* %D */
- {NULL, NULL}, /* %I */
- {NULL, NULL}, /* %J */
- {NULL, NULL}, /* %N */
- {NULL, NULL}, /* %O */
- {NULL, NULL}, /* %P */
- {NULL, NULL}, /* %R */
- {NULL, NULL}, /* %T */
- {NULL, NULL}, /* %V */
- {NULL, NULL}, /* Ac */
- {NULL, NULL}, /* Ao */
- {NULL, NULL}, /* Aq */
- {NULL, NULL}, /* At */
- {NULL, NULL}, /* Bc */
- {NULL, NULL}, /* Bf */
- {NULL, NULL}, /* Bo */
- {NULL, NULL}, /* Bq */
- {NULL, NULL}, /* Bsx */
- {NULL, NULL}, /* Bx */
- {NULL, NULL}, /* Db */
- {NULL, NULL}, /* Dc */
- {NULL, NULL}, /* Do */
- {NULL, NULL}, /* Dq */
- {NULL, NULL}, /* Ec */
- {NULL, NULL}, /* Ef */
- {NULL, NULL}, /* Em */
- {NULL, NULL}, /* Eo */
- {NULL, NULL}, /* Fx */
- {NULL, NULL}, /* Ms */
- {NULL, NULL}, /* No */
- {NULL, NULL}, /* Ns */
- {NULL, NULL}, /* Nx */
- {NULL, NULL}, /* Ox */
- {NULL, NULL}, /* Pc */
- {NULL, NULL}, /* Pf */
- {NULL, NULL}, /* Po */
- {NULL, NULL}, /* Pq */
- {NULL, NULL}, /* Qc */
- {NULL, NULL}, /* Ql */
- {NULL, NULL}, /* Qo */
- {NULL, NULL}, /* Qq */
- {NULL, NULL}, /* Re */
- {NULL, NULL}, /* Rs */
- {NULL, NULL}, /* Sc */
- {NULL, NULL}, /* So */
- {NULL, NULL}, /* Sq */
- {NULL, NULL}, /* Sm */
- {NULL, NULL}, /* Sx */
- {NULL, NULL}, /* Sy */
- {NULL, NULL}, /* Tn */
- {NULL, NULL}, /* Ux */
- {NULL, NULL}, /* Xc */
- {NULL, NULL}, /* Xo */
- {NULL, NULL}, /* Fo */
- {NULL, NULL}, /* Fc */
- {NULL, NULL}, /* Oo */
- {NULL, NULL}, /* Oc */
- {NULL, NULL}, /* Bk */
- {NULL, NULL}, /* Ek */
- {NULL, NULL}, /* Bt */
- {NULL, NULL}, /* Hf */
- {NULL, NULL}, /* Fr */
- {NULL, NULL}, /* Ud */
- {NULL, NULL}, /* Lb */
- {NULL, NULL}, /* Lp */
- {NULL, NULL}, /* Lk */
- {NULL, NULL}, /* Mt */
- {NULL, NULL}, /* Brq */
- {NULL, NULL}, /* Bro */
- {NULL, NULL}, /* Brc */
- {NULL, NULL}, /* %C */
- {NULL, NULL}, /* Es */
- {NULL, NULL}, /* En */
- {NULL, NULL}, /* Dx */
- {NULL, NULL}, /* %Q */
- {NULL, NULL}, /* br */
- {NULL, NULL}, /* sp */
-};
+ toks[0] = "style";
+ toks[1] = "man";
+ toks[2] = "includes";
+ toks[3] = "fragment";
+ toks[4] = NULL;
+ h = mandoc_calloc(1, sizeof(struct html));
-int
-html_mdoc(void *arg, const struct mdoc *m)
-{
- struct html *h;
+ h->type = type;
+ h->tags.head = NULL;
+ h->symtab = mchars_alloc();
- h = (struct html *)arg;
+ while (outopts && *outopts)
+ switch (getsubopt(&outopts, UNCONST(toks), &v)) {
+ case (0):
+ h->style = v;
+ break;
+ case (1):
+ h->base_man = v;
+ break;
+ case (2):
+ h->base_includes = v;
+ break;
+ case (3):
+ h->oflags |= HTML_FRAGMENT;
+ break;
+ default:
+ break;
+ }
- print_gen_doctype(h);
- print_otag(h, TAG_HTML, 0, NULL);
- print_mdoc(mdoc_meta(m), mdoc_node(m), h);
- print_ctag(h, TAG_HTML);
- printf("\n");
- return(1);
+ return(h);
}
-
-int
-html_man(void *arg, const struct man *m)
+void *
+html_alloc(char *outopts)
{
- struct html *h;
-
- h = (struct html *)arg;
- print_gen_doctype(h);
- print_otag(h, TAG_HTML, 0, NULL);
- print_man(man_meta(m), man_node(m), h);
- print_ctag(h, TAG_HTML);
- printf("\n");
- return(1);
+ return(ml_alloc(outopts, HTML_HTML_4_01_STRICT));
}
void *
-html_alloc(void)
+xhtml_alloc(char *outopts)
{
- return(calloc(1, sizeof(struct html)));
+ return(ml_alloc(outopts, HTML_XHTML_1_0_STRICT));
}
void
html_free(void *p)
{
+ struct tag *tag;
+ struct html *h;
- free(p);
-}
-
+ h = (struct html *)p;
-static void
-print_mdoc(MDOC_ARGS)
-{
+ while ((tag = h->tags.head) != NULL) {
+ h->tags.head = tag->next;
+ free(tag);
+ }
+
+ if (h->symtab)
+ mchars_free(h->symtab);
- print_otag(h, TAG_HEAD, 0, NULL);
- print_mdoc_head(m, n, h);
- print_ctag(h, TAG_HEAD);
- print_otag(h, TAG_BODY, 0, NULL);
- print_mdoc_node(m, n, h);
- print_ctag(h, TAG_BODY);
+ free(h);
}
-static void
+void
print_gen_head(struct html *h)
{
- struct htmlpair meta0[2];
- struct htmlpair meta1[2];
- struct htmlpair link[4];
-
- meta0[0].key = ATTR_HTTPEQUIV;
- meta0[0].val = "Content-Type";
- meta0[1].key = ATTR_CONTENT;
- meta0[1].val = "text/html; charest-utf-8";
-
- meta1[0].key = ATTR_NAME;
- meta1[0].val = "resource-type";
- meta1[1].key = ATTR_CONTENT;
- meta1[1].val = "document";
-
- link[0].key = ATTR_REL;
- link[0].val = "stylesheet";
- link[1].key = ATTR_HREF;
- link[1].val = "style.css";
- link[2].key = ATTR_TYPE;
- link[2].val = "text/css";
- link[3].key = ATTR_MEDIA;
- link[3].val = "all";
-
- print_otag(h, TAG_META, 2, meta0);
- print_otag(h, TAG_META, 2, meta1);
- print_otag(h, TAG_LINK, 4, link);
+ struct htmlpair tag[4];
+
+ 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_NAME;
+ tag[0].val = "resource-type";
+ tag[1].key = ATTR_CONTENT;
+ tag[1].val = "document";
+ print_otag(h, TAG_META, 2, tag);
+
+ if (h->style) {
+ tag[0].key = ATTR_REL;
+ tag[0].val = "stylesheet";
+ tag[1].key = ATTR_HREF;
+ tag[1].val = h->style;
+ tag[2].key = ATTR_TYPE;
+ tag[2].val = "text/css";
+ tag[3].key = ATTR_MEDIA;
+ tag[3].val = "all";
+ print_otag(h, TAG_LINK, 4, tag);
+ }
}
-
static void
-print_mdoc_head(MDOC_ARGS)
+print_metaf(struct html *h, enum mandoc_esc deco)
{
+ enum htmlfont font;
- print_gen_head(h);
- print_otag(h, TAG_TITLE, 0, NULL);
- print_encode(m->title);
- print_ctag(h, TAG_TITLE);
+ switch (deco) {
+ case (ESCAPE_FONTPREV):
+ font = h->metal;
+ break;
+ case (ESCAPE_FONTITALIC):
+ font = HTMLFONT_ITALIC;
+ break;
+ case (ESCAPE_FONTBOLD):
+ font = HTMLFONT_BOLD;
+ break;
+ case (ESCAPE_FONTBI):
+ font = HTMLFONT_BI;
+ break;
+ case (ESCAPE_FONT):
+ /* FALLTHROUGH */
+ case (ESCAPE_FONTROMAN):
+ font = HTMLFONT_NONE;
+ break;
+ default:
+ abort();
+ /* NOTREACHED */
+ }
+
+ if (h->metaf) {
+ print_tagq(h, h->metaf);
+ h->metaf = NULL;
+ }
+
+ h->metal = h->metac;
+ h->metac = font;
+
+ 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
+html_strlen(const char *cp)
+{
+ size_t rsz;
+ int skip, sz;
+
+ /*
+ * Account for escaped sequences within string length
+ * calculations. This follows the logic in term_strlen() as we
+ * must calculate the width of produced strings.
+ * Assume that characters are always width of "1". This is
+ * hacky, but it gets the job done for approximation of widths.
+ */
+
+ sz = 0;
+ skip = 0;
+ while (1) {
+ rsz = strcspn(cp, "\\");
+ if (rsz) {
+ cp += rsz;
+ if (skip) {
+ skip = 0;
+ rsz--;
+ }
+ sz += rsz;
+ }
+ if ('\0' == *cp)
+ break;
+ cp++;
+ switch (mandoc_escape(&cp, NULL, NULL)) {
+ case (ESCAPE_ERROR):
+ return(sz);
+ case (ESCAPE_UNICODE):
+ /* FALLTHROUGH */
+ case (ESCAPE_NUMBERED):
+ /* FALLTHROUGH */
+ case (ESCAPE_SPECIAL):
+ if (skip)
+ skip = 0;
+ else
+ sz++;
+ break;
+ case (ESCAPE_SKIPCHAR):
+ skip = 1;
+ break;
+ default:
+ break;
+ }
+ }
+ return(sz);
+}
static int
-mdoc_root_pre(MDOC_ARGS)
+print_encode(struct html *h, const char *p, int norecurse)
{
- struct htmlpair div;
+ size_t sz;
+ int c, len, nospace;
+ const char *seq;
+ enum mandoc_esc esc;
+ static const char rejs[8] = { '\\', '<', '>', '&',
+ ASCII_NBRSP, ASCII_HYPH, ASCII_BREAK, '\0' };
+
+ nospace = 0;
+
+ while ('\0' != *p) {
+ if (HTML_SKIPCHAR & h->flags && '\\' != *p) {
+ h->flags &= ~HTML_SKIPCHAR;
+ p++;
+ continue;
+ }
- div.key = ATTR_CLASS;
- div.val = "body";
+ sz = strcspn(p, rejs);
- print_otag(h, TAG_DIV, 1, &div);
- return(1);
-}
+ fwrite(p, 1, sz, stdout);
+ p += (int)sz;
+ if ('\0' == *p)
+ break;
-static void
-mdoc_root_post(MDOC_ARGS)
-{
+ switch (*p++) {
+ case ('<'):
+ printf("<");
+ continue;
+ case ('>'):
+ printf(">");
+ continue;
+ case ('&'):
+ printf("&");
+ continue;
+ case (ASCII_NBRSP):
+ putchar('-');
+ continue;
+ case (ASCII_HYPH):
+ putchar('-');
+ /* FALLTHROUGH */
+ case (ASCII_BREAK):
+ continue;
+ default:
+ break;
+ }
- print_ctag(h, TAG_DIV);
-}
+ esc = mandoc_escape(&p, &seq, &len);
+ if (ESCAPE_ERROR == esc)
+ break;
+ switch (esc) {
+ case (ESCAPE_FONT):
+ /* FALLTHROUGH */
+ case (ESCAPE_FONTPREV):
+ /* FALLTHROUGH */
+ case (ESCAPE_FONTBOLD):
+ /* FALLTHROUGH */
+ case (ESCAPE_FONTITALIC):
+ /* FALLTHROUGH */
+ case (ESCAPE_FONTBI):
+ /* FALLTHROUGH */
+ case (ESCAPE_FONTROMAN):
+ if (0 == norecurse)
+ print_metaf(h, esc);
+ continue;
+ case (ESCAPE_SKIPCHAR):
+ h->flags |= HTML_SKIPCHAR;
+ continue;
+ default:
+ break;
+ }
-static int
-mdoc_ss_pre(MDOC_ARGS)
-{
+ if (h->flags & HTML_SKIPCHAR) {
+ h->flags &= ~HTML_SKIPCHAR;
+ continue;
+ }
+
+ switch (esc) {
+ case (ESCAPE_UNICODE):
+ /* Skip passed "u" header. */
+ c = mchars_num2uc(seq + 1, len - 1);
+ if ('\0' != c)
+ printf("&#x%x;", c);
+ break;
+ case (ESCAPE_NUMBERED):
+ c = mchars_num2char(seq, len);
+ if ('\0' != c)
+ putchar(c);
+ break;
+ case (ESCAPE_SPECIAL):
+ c = mchars_spec2cp(h->symtab, seq, len);
+ if (c > 0)
+ printf("&#%d;", c);
+ else if (-1 == c && 1 == len)
+ putchar((int)*seq);
+ break;
+ case (ESCAPE_NOSPACE):
+ if ('\0' == *p)
+ nospace = 1;
+ break;
+ default:
+ break;
+ }
+ }
- if (MDOC_BODY == n->type)
- print_otag(h, TAG_P, 0, NULL);
- if (MDOC_HEAD == n->type)
- print_otag(h, TAG_H2, 0, NULL);
- return(1);
+ return(nospace);
}
static void
-mdoc_ss_post(MDOC_ARGS)
+print_attr(struct html *h, const char *key, const char *val)
{
-
- if (MDOC_BODY == n->type)
- print_ctag(h, TAG_P);
- if (MDOC_HEAD == n->type)
- print_ctag(h, TAG_H2);
+ printf(" %s=\"", key);
+ (void)print_encode(h, val, 1);
+ putchar('\"');
}
-static int
-mdoc_pp_pre(MDOC_ARGS)
+struct tag *
+print_otag(struct html *h, enum htmltag tag,
+ int sz, const struct htmlpair *p)
{
+ int i;
+ struct tag *t;
- print_otag(h, TAG_P, 0, NULL);
- return(0);
-}
+ /* Push this tags onto the stack of open scopes. */
+ if ( ! (HTML_NOSTACK & htmltags[tag].flags)) {
+ t = mandoc_malloc(sizeof(struct tag));
+ t->tag = tag;
+ t->next = h->tags.head;
+ h->tags.head = t;
+ } else
+ t = NULL;
-static int
-mdoc_nd_pre(MDOC_ARGS)
-{
-
- if (MDOC_BODY == n->type)
- print_text(h, "--");
- return(1);
-}
+ if ( ! (HTML_NOSPACE & h->flags))
+ if ( ! (HTML_CLRLINE & htmltags[tag].flags)) {
+ /* Manage keeps! */
+ if ( ! (HTML_KEEP & h->flags)) {
+ if (HTML_PREKEEP & h->flags)
+ h->flags |= HTML_KEEP;
+ putchar(' ');
+ } else
+ printf(" ");
+ }
+ if ( ! (h->flags & HTML_NONOSPACE))
+ h->flags &= ~HTML_NOSPACE;
+ else
+ h->flags |= HTML_NOSPACE;
-static int
-mdoc_nm_pre(MDOC_ARGS)
-{
- struct htmlpair class;
+ /* Print out the tag name and attributes. */
- class.key = ATTR_CLASS;
- class.val = "name";
+ printf("<%s", htmltags[tag].name);
+ for (i = 0; i < sz; i++)
+ print_attr(h, htmlattrs[p[i].key], p[i].val);
- print_otag(h, TAG_SPAN, 1, &class);
- if (NULL == n->child)
- print_text(h, m->name);
+ /* Add non-overridable attributes. */
- return(1);
-}
+ 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. */
-static void
-mdoc_nm_post(MDOC_ARGS)
-{
+ if (HTML_AUTOCLOSE & htmltags[tag].flags)
+ switch (h->type) {
+ case (HTML_XHTML_1_0_STRICT):
+ putchar('/');
+ break;
+ default:
+ break;
+ }
- print_ctag(h, TAG_SPAN);
-}
+ putchar('>');
+ h->flags |= HTML_NOSPACE;
-static int
-mdoc_sh_pre(MDOC_ARGS)
-{
+ if ((HTML_AUTOCLOSE | HTML_CLRLINE) & htmltags[tag].flags)
+ putchar('\n');
- if (MDOC_BODY == n->type)
- print_otag(h, TAG_P, 0, NULL);
- if (MDOC_HEAD == n->type)
- print_otag(h, TAG_H1, 0, NULL);
- return(1);
+ return(t);
}
static void
-mdoc_sh_post(MDOC_ARGS)
+print_ctag(struct html *h, enum htmltag tag)
{
-
- if (MDOC_BODY == n->type)
- print_ctag(h, TAG_P);
- if (MDOC_HEAD == n->type)
- print_ctag(h, TAG_H1);
+
+ printf("</%s>", htmltags[tag].name);
+ if (HTML_CLRLINE & htmltags[tag].flags) {
+ h->flags |= HTML_NOSPACE;
+ putchar('\n');
+ }
}
-
-static void
-print_mdoc_node(MDOC_ARGS)
+void
+print_gen_decls(struct html *h)
{
- int child;
-
- child = 1;
-
- switch (n->type) {
- case (MDOC_ROOT):
- child = mdoc_root_pre(m, n, h);
- break;
- case (MDOC_TEXT):
- print_text(h, n->string);
+ 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:
- if (mdocs[n->tok].pre)
- child = (*mdocs[n->tok].pre)(m, n, h);
+ puts("<?xml version=\"1.0\" encoding=\"UTF-8\"?>");
+ name = "html";
+ doctype = "-//W3C//DTD XHTML 1.0 Strict//EN";
+ dtd = "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd";
break;
}
- if (child && n->child)
- print_mdoc_node(m, n->child, h);
+ printf("<!DOCTYPE %s PUBLIC \"%s\" \"%s\">\n",
+ name, doctype, dtd);
+}
- switch (n->type) {
- case (MDOC_ROOT):
- mdoc_root_post(m, n, h);
+void
+print_text(struct html *h, const char *word)
+{
+
+ if ( ! (HTML_NOSPACE & h->flags)) {
+ /* Manage keeps! */
+ if ( ! (HTML_KEEP & h->flags)) {
+ if (HTML_PREKEEP & h->flags)
+ h->flags |= HTML_KEEP;
+ putchar(' ');
+ } else
+ printf(" ");
+ }
+
+ assert(NULL == h->metaf);
+ switch (h->metac) {
+ case (HTMLFONT_ITALIC):
+ h->metaf = print_otag(h, TAG_I, 0, NULL);
break;
- case (MDOC_TEXT):
+ 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:
- if (mdocs[n->tok].post)
- (*mdocs[n->tok].post)(m, n, h);
break;
}
- if (n->next)
- print_mdoc_node(m, n->next, h);
-}
-
+ assert(word);
+ if ( ! print_encode(h, word, 0)) {
+ if ( ! (h->flags & HTML_NONOSPACE))
+ h->flags &= ~HTML_NOSPACE;
+ } else
+ h->flags |= HTML_NOSPACE;
-static void
-print_man(MAN_ARGS)
-{
+ if (h->metaf) {
+ print_tagq(h, h->metaf);
+ h->metaf = NULL;
+ }
- print_otag(h, TAG_HEAD, 0, NULL);
- print_man_head(m, n, h);
- print_ctag(h, TAG_HEAD);
- print_otag(h, TAG_BODY, 0, NULL);
- print_man_body(m, n, h);
- print_ctag(h, TAG_BODY);
+ h->flags &= ~HTML_IGNDELIM;
}
-static void
-print_man_head(MAN_ARGS)
+void
+print_tagq(struct html *h, const struct tag *until)
{
-
- print_gen_head(h);
- print_otag(h, TAG_TITLE, 0, NULL);
- print_encode(m->title);
- print_ctag(h, TAG_TITLE);
+ struct tag *tag;
+
+ while ((tag = h->tags.head) != NULL) {
+ /*
+ * Remember to close out and nullify the current
+ * meta-font and table, if applicable.
+ */
+ if (tag == h->metaf)
+ h->metaf = NULL;
+ if (tag == h->tblt)
+ h->tblt = NULL;
+ print_ctag(h, tag->tag);
+ h->tags.head = tag->next;
+ free(tag);
+ if (until && tag == until)
+ return;
+ }
}
-static void
-print_man_body(MAN_ARGS)
+void
+print_stagq(struct html *h, const struct tag *suntil)
{
+ struct tag *tag;
+
+ 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.
+ */
+ if (tag == h->metaf)
+ h->metaf = NULL;
+ if (tag == h->tblt)
+ h->tblt = NULL;
+ print_ctag(h, tag->tag);
+ h->tags.head = tag->next;
+ free(tag);
+ }
}
-
-static void
-print_encode(const char *p)
+void
+bufinit(struct html *h)
{
- printf("%s", p); /* XXX */
+ h->buf[0] = '\0';
+ h->buflen = 0;
}
-
-static void
-print_otag(struct html *h, enum htmltag tag,
- int sz, const struct htmlpair *p)
+void
+bufcat_style(struct html *h, const char *key, const char *val)
{
- int i;
- if ( ! (HTML_NOSPACE & h->flags))
- if ( ! (HTML_BLOCK & htmltags[tag].flags))
- printf(" ");
-
- printf("<%s", htmltags[tag].name);
- for (i = 0; i < sz; i++) {
- printf(" %s=\"", htmlattrs[p[i].key]);
- assert(p->val);
- print_encode(p[i].val);
- printf("\"");
- }
- printf(">");
+ bufcat(h, key);
+ bufcat(h, ":");
+ bufcat(h, val);
+ bufcat(h, ";");
+}
- h->flags |= HTML_NOSPACE;
+void
+bufcat(struct html *h, const char *p)
+{
+ h->buflen = strlcat(h->buf, p, BUFSIZ);
+ assert(h->buflen < BUFSIZ);
}
-
-/* ARGSUSED */
-static void
-print_ctag(struct html *h, enum htmltag tag)
+void
+bufcat_fmt(struct html *h, const char *fmt, ...)
{
-
- printf("</%s>", htmltags[tag].name);
- if (HTML_BLOCK & htmltags[tag].flags)
- h->flags |= HTML_NOSPACE;
-}
+ va_list ap;
+ va_start(ap, fmt);
+ (void)vsnprintf(h->buf + (int)h->buflen,
+ BUFSIZ - h->buflen - 1, fmt, ap);
+ va_end(ap);
+ h->buflen = strlen(h->buf);
+}
-/* ARGSUSED */
static void
-print_gen_doctype(struct html *h)
+bufncat(struct html *h, const char *p, size_t sz)
{
-
- printf("<!DOCTYPE HTML PUBLIC \"%s\" \"%s\">\n", DOCTYPE, DTD);
-}
+ assert(h->buflen + sz + 1 < BUFSIZ);
+ strncat(h->buf, p, sz);
+ h->buflen += sz;
+}
-static void
-print_text(struct html *h, const char *p)
+void
+buffmt_includes(struct html *h, const char *name)
{
+ const char *p, *pp;
- if (*p && 0 == *(p + 1))
- switch (*p) {
- case('.'):
- /* FALLTHROUGH */
- case(','):
- /* FALLTHROUGH */
- case(';'):
- /* FALLTHROUGH */
- case(':'):
- /* FALLTHROUGH */
- case('?'):
- /* FALLTHROUGH */
- case('!'):
- /* FALLTHROUGH */
- case(')'):
- /* FALLTHROUGH */
- case(']'):
- /* FALLTHROUGH */
- case('}'):
- h->flags |= HTML_NOSPACE;
+ pp = h->base_includes;
+
+ bufinit(h);
+ while (NULL != (p = strchr(pp, '%'))) {
+ bufncat(h, pp, (size_t)(p - pp));
+ switch (*(p + 1)) {
+ case('I'):
+ bufcat(h, name);
+ break;
default:
+ bufncat(h, p, 2);
break;
}
+ pp = p + 2;
+ }
+ if (pp)
+ bufcat(h, pp);
+}
- if ( ! (h->flags & HTML_NOSPACE))
- printf(" ");
- h->flags &= ~HTML_NOSPACE;
-
- if (p)
- print_encode(p);
+void
+buffmt_man(struct html *h,
+ const char *name, const char *sec)
+{
+ const char *p, *pp;
- if (*p && 0 == *(p + 1))
- switch (*p) {
- case('('):
- /* FALLTHROUGH */
- case('['):
- /* FALLTHROUGH */
- case('{'):
- h->flags |= HTML_NOSPACE;
+ pp = h->base_man;
+
+ bufinit(h);
+ while (NULL != (p = strchr(pp, '%'))) {
+ bufncat(h, pp, (size_t)(p - pp));
+ switch (*(p + 1)) {
+ case('S'):
+ bufcat(h, sec ? sec : "1");
+ break;
+ case('N'):
+ bufcat_fmt(h, "%s", name);
+ break;
default:
+ bufncat(h, p, 2);
break;
}
+ pp = p + 2;
+ }
+ if (pp)
+ bufcat(h, pp);
+}
+
+void
+bufcat_su(struct html *h, const char *p, const struct roffsu *su)
+{
+ double v;
+
+ v = su->scale;
+ if (SCALE_MM == su->unit && 0.0 == (v /= 100.0))
+ v = 1.0;
+
+ bufcat_fmt(h, "%s: %.2f%s;", p, v, roffscales[su->unit]);
+}
+
+void
+bufcat_id(struct html *h, const char *src)
+{
+
+ /* Cf. <http://www.w3.org/TR/html4/types.html#h-6.2>. */
+
+ while ('\0' != *src)
+ bufcat_fmt(h, "%.2x", *src++);
}
git.ckatri.com / mandoc.git / blobdiff