version 1.93, 2010/01/29 14:39:37 |
version 1.102, 2010/06/19 20:46:27 |
|
|
/* $Id$ */ |
/* $Id$ */ |
/* |
/* |
* Copyright (c) 2008, 2009 Kristaps Dzonsons <kristaps@kth.se> |
* Copyright (c) 2008, 2009 Kristaps Dzonsons <kristaps@bsd.lv> |
* |
* |
* Permission to use, copy, modify, and distribute this software for any |
* Permission to use, copy, modify, and distribute this software for any |
* purpose with or without fee is hereby granted, provided that the above |
* purpose with or without fee is hereby granted, provided that the above |
|
|
#include <string.h> |
#include <string.h> |
#include <unistd.h> |
#include <unistd.h> |
|
|
|
#include "mandoc.h" |
#include "out.h" |
#include "out.h" |
#include "chars.h" |
#include "chars.h" |
#include "html.h" |
#include "html.h" |
#include "main.h" |
#include "main.h" |
|
|
#define UNCONST(a) ((void *)(uintptr_t)(const void *)(a)) |
|
|
|
struct htmldata { |
struct htmldata { |
const char *name; |
const char *name; |
int flags; |
int flags; |
Line 54 static const struct htmldata htmltags[TAG_MAX] = { |
|
Line 53 static const struct htmldata htmltags[TAG_MAX] = { |
|
{"h1", 0}, /* TAG_H1 */ |
{"h1", 0}, /* TAG_H1 */ |
{"h2", 0}, /* TAG_H2 */ |
{"h2", 0}, /* TAG_H2 */ |
{"span", 0}, /* TAG_SPAN */ |
{"span", 0}, /* TAG_SPAN */ |
{"link", HTML_CLRLINE | HTML_NOSTACK}, /* TAG_LINK */ |
{"link", HTML_CLRLINE | HTML_NOSTACK | HTML_AUTOCLOSE}, /* TAG_LINK */ |
{"br", HTML_CLRLINE | HTML_NOSTACK | HTML_AUTOCLOSE}, /* TAG_BR */ |
{"br", HTML_CLRLINE | HTML_NOSTACK | HTML_AUTOCLOSE}, /* TAG_BR */ |
{"a", 0}, /* TAG_A */ |
{"a", 0}, /* TAG_A */ |
{"table", HTML_CLRLINE}, /* TAG_TABLE */ |
{"table", HTML_CLRLINE}, /* TAG_TABLE */ |
Line 96 static void print_doctype(struct html *); |
|
Line 95 static void print_doctype(struct html *); |
|
static void print_xmltype(struct html *); |
static void print_xmltype(struct html *); |
static int print_encode(struct html *, const char *, int); |
static int print_encode(struct html *, const char *, int); |
static void print_metaf(struct html *, enum roffdeco); |
static void print_metaf(struct html *, enum roffdeco); |
|
static void print_attr(struct html *, |
|
const char *, const char *); |
static void *ml_alloc(char *, enum htmltype); |
static void *ml_alloc(char *, enum htmltype); |
|
|
|
|
Line 294 print_encode(struct html *h, const char *p, int norecu |
|
Line 295 print_encode(struct html *h, const char *p, int norecu |
|
int len, nospace; |
int len, nospace; |
const char *seq; |
const char *seq; |
enum roffdeco deco; |
enum roffdeco deco; |
|
static const char rejs[6] = { '\\', '<', '>', '&', ASCII_HYPH, '\0' }; |
|
|
nospace = 0; |
nospace = 0; |
|
|
for (; *p; p++) { |
for (; *p; p++) { |
sz = strcspn(p, "\\<>&"); |
sz = strcspn(p, rejs); |
|
|
fwrite(p, 1, sz, stdout); |
fwrite(p, 1, sz, stdout); |
p += /* LINTED */ |
p += /* LINTED */ |
Line 313 print_encode(struct html *h, const char *p, int norecu |
|
Line 315 print_encode(struct html *h, const char *p, int norecu |
|
} else if ('&' == *p) { |
} else if ('&' == *p) { |
printf("&"); |
printf("&"); |
continue; |
continue; |
|
} else if (ASCII_HYPH == *p) { |
|
/* |
|
* Note: "soft hyphens" aren't graphically |
|
* displayed when not breaking the text; we want |
|
* them to be displayed. |
|
*/ |
|
/*printf("­");*/ |
|
putchar('-'); |
|
continue; |
} else if ('\0' == *p) |
} else if ('\0' == *p) |
break; |
break; |
|
|
Line 351 print_encode(struct html *h, const char *p, int norecu |
|
Line 362 print_encode(struct html *h, const char *p, int norecu |
|
} |
} |
|
|
|
|
|
static void |
|
print_attr(struct html *h, const char *key, const char *val) |
|
{ |
|
printf(" %s=\"", key); |
|
(void)print_encode(h, val, 1); |
|
putchar('\"'); |
|
} |
|
|
|
|
struct tag * |
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 sz, const struct htmlpair *p) |
Line 358 print_otag(struct html *h, enum htmltag tag, |
|
Line 378 print_otag(struct html *h, enum htmltag tag, |
|
int i; |
int i; |
struct tag *t; |
struct tag *t; |
|
|
|
/* Push this tags onto the stack of open scopes. */ |
|
|
if ( ! (HTML_NOSTACK & htmltags[tag].flags)) { |
if ( ! (HTML_NOSTACK & htmltags[tag].flags)) { |
t = malloc(sizeof(struct tag)); |
t = malloc(sizeof(struct tag)); |
if (NULL == t) { |
if (NULL == t) { |
Line 374 print_otag(struct html *h, enum htmltag tag, |
|
Line 396 print_otag(struct html *h, enum htmltag tag, |
|
if ( ! (HTML_CLRLINE & htmltags[tag].flags)) |
if ( ! (HTML_CLRLINE & htmltags[tag].flags)) |
putchar(' '); |
putchar(' '); |
|
|
|
/* Print out the tag name and attributes. */ |
|
|
printf("<%s", htmltags[tag].name); |
printf("<%s", htmltags[tag].name); |
for (i = 0; i < sz; i++) { |
for (i = 0; i < sz; i++) |
printf(" %s=\"", htmlattrs[p[i].key]); |
print_attr(h, htmlattrs[p[i].key], p[i].val); |
assert(p->val); |
|
(void)print_encode(h, p[i].val, 1); |
/* Add non-overridable attributes. */ |
putchar('\"'); |
|
|
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"); |
} |
} |
|
|
|
/* Accomodate for XML "well-formed" singleton escaping. */ |
|
|
if (HTML_AUTOCLOSE & htmltags[tag].flags) |
if (HTML_AUTOCLOSE & htmltags[tag].flags) |
switch (h->type) { |
switch (h->type) { |
case (HTML_XHTML_1_0_STRICT): |
case (HTML_XHTML_1_0_STRICT): |
Line 422 print_gen_decls(struct html *h) |
|
Line 452 print_gen_decls(struct html *h) |
|
static void |
static void |
print_xmltype(struct html *h) |
print_xmltype(struct html *h) |
{ |
{ |
const char *decl; |
|
|
|
switch (h->type) { |
if (HTML_XHTML_1_0_STRICT == h->type) |
case (HTML_XHTML_1_0_STRICT): |
printf("<?xml version=\"1.0\" encoding=\"UTF-8\"?>"); |
decl = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>"; |
|
break; |
|
default: |
|
decl = NULL; |
|
break; |
|
} |
|
|
|
if (NULL == decl) |
|
return; |
|
|
|
printf("%s\n", decl); |
|
} |
} |
|
|
|
|
Line 445 print_doctype(struct html *h) |
|
Line 463 print_doctype(struct html *h) |
|
{ |
{ |
const char *doctype; |
const char *doctype; |
const char *dtd; |
const char *dtd; |
|
const char *name; |
|
|
switch (h->type) { |
switch (h->type) { |
case (HTML_HTML_4_01_STRICT): |
case (HTML_HTML_4_01_STRICT): |
|
name = "HTML"; |
doctype = "-//W3C//DTD HTML 4.01//EN"; |
doctype = "-//W3C//DTD HTML 4.01//EN"; |
dtd = "http://www.w3.org/TR/html4/strict.dtd"; |
dtd = "http://www.w3.org/TR/html4/strict.dtd"; |
break; |
break; |
default: |
default: |
|
name = "html"; |
doctype = "-//W3C//DTD XHTML 1.0 Strict//EN"; |
doctype = "-//W3C//DTD XHTML 1.0 Strict//EN"; |
dtd = "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"; |
dtd = "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"; |
break; |
break; |
} |
} |
|
|
printf("<!DOCTYPE HTML PUBLIC \"%s\" \"%s\">\n", doctype, dtd); |
printf("<!DOCTYPE %s PUBLIC \"%s\" \"%s\">\n", |
|
name, doctype, dtd); |
} |
} |
|
|
|
|
Line 482 print_text(struct html *h, const char *p) |
|
Line 504 print_text(struct html *h, const char *p) |
|
case(')'): |
case(')'): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case(']'): |
case(']'): |
/* FALLTHROUGH */ |
|
case('}'): |
|
if ( ! (HTML_IGNDELIM & h->flags)) |
if ( ! (HTML_IGNDELIM & h->flags)) |
h->flags |= HTML_NOSPACE; |
h->flags |= HTML_NOSPACE; |
break; |
break; |
Line 498 print_text(struct html *h, const char *p) |
|
Line 518 print_text(struct html *h, const char *p) |
|
if ( ! print_encode(h, p, 0)) |
if ( ! print_encode(h, p, 0)) |
h->flags &= ~HTML_NOSPACE; |
h->flags &= ~HTML_NOSPACE; |
|
|
|
/* |
|
* Note that we don't process the pipe: the parser sees it as |
|
* punctuation, but we don't in terms of typography. |
|
*/ |
if (*p && 0 == *(p + 1)) |
if (*p && 0 == *(p + 1)) |
switch (*p) { |
switch (*p) { |
case('('): |
case('('): |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case('['): |
case('['): |
/* FALLTHROUGH */ |
|
case('{'): |
|
h->flags |= HTML_NOSPACE; |
h->flags |= HTML_NOSPACE; |
break; |
break; |
default: |
default: |