version 1.151, 2012/05/31 22:29:13 |
version 1.160, 2014/08/10 23:54:41 |
|
|
/* $Id$ */ |
/* $Id$ */ |
/* |
/* |
* Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv> |
* Copyright (c) 2011, 2012 Ingo Schwarze <schwarze@openbsd.org> |
* Copyright (c) 2011, 2012, 2013, 2014 Ingo Schwarze <schwarze@openbsd.org> |
* |
* |
* 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 |
|
|
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF |
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF |
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. |
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. |
*/ |
*/ |
#ifdef HAVE_CONFIG_H |
|
#include "config.h" |
#include "config.h" |
#endif |
|
|
|
#include <sys/types.h> |
#include <sys/types.h> |
|
|
|
|
#include <unistd.h> |
#include <unistd.h> |
|
|
#include "mandoc.h" |
#include "mandoc.h" |
|
#include "mandoc_aux.h" |
#include "libmandoc.h" |
#include "libmandoc.h" |
#include "out.h" |
#include "out.h" |
#include "html.h" |
#include "html.h" |
Line 109 static const char *const roffscales[SCALE_MAX] = { |
|
Line 108 static const char *const roffscales[SCALE_MAX] = { |
|
|
|
static void bufncat(struct html *, const char *, size_t); |
static void bufncat(struct html *, const char *, size_t); |
static void print_ctag(struct html *, enum htmltag); |
static void print_ctag(struct html *, enum htmltag); |
|
static int print_escape(char); |
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 mandoc_esc); |
static void print_metaf(struct html *, enum mandoc_esc); |
static void print_attr(struct html *, const char *, const char *); |
static void print_attr(struct html *, const char *, const char *); |
static void *ml_alloc(char *, enum htmltype); |
static void *ml_alloc(char *, enum htmltype); |
|
|
|
|
static void * |
static void * |
ml_alloc(char *outopts, enum htmltype type) |
ml_alloc(char *outopts, enum htmltype type) |
{ |
{ |
Line 135 ml_alloc(char *outopts, enum htmltype type) |
|
Line 136 ml_alloc(char *outopts, enum htmltype type) |
|
|
|
while (outopts && *outopts) |
while (outopts && *outopts) |
switch (getsubopt(&outopts, UNCONST(toks), &v)) { |
switch (getsubopt(&outopts, UNCONST(toks), &v)) { |
case (0): |
case 0: |
h->style = v; |
h->style = v; |
break; |
break; |
case (1): |
case 1: |
h->base_man = v; |
h->base_man = v; |
break; |
break; |
case (2): |
case 2: |
h->base_includes = v; |
h->base_includes = v; |
break; |
break; |
case (3): |
case 3: |
h->oflags |= HTML_FRAGMENT; |
h->oflags |= HTML_FRAGMENT; |
break; |
break; |
default: |
default: |
Line 161 html_alloc(char *outopts) |
|
Line 162 html_alloc(char *outopts) |
|
return(ml_alloc(outopts, HTML_HTML_4_01_STRICT)); |
return(ml_alloc(outopts, HTML_HTML_4_01_STRICT)); |
} |
} |
|
|
|
|
void * |
void * |
xhtml_alloc(char *outopts) |
xhtml_alloc(char *outopts) |
{ |
{ |
Line 169 xhtml_alloc(char *outopts) |
|
Line 169 xhtml_alloc(char *outopts) |
|
return(ml_alloc(outopts, HTML_XHTML_1_0_STRICT)); |
return(ml_alloc(outopts, HTML_XHTML_1_0_STRICT)); |
} |
} |
|
|
|
|
void |
void |
html_free(void *p) |
html_free(void *p) |
{ |
{ |
Line 179 html_free(void *p) |
|
Line 178 html_free(void *p) |
|
h = (struct html *)p; |
h = (struct html *)p; |
|
|
while ((tag = h->tags.head) != NULL) { |
while ((tag = h->tags.head) != NULL) { |
h->tags.head = tag->next; |
h->tags.head = tag->next; |
free(tag); |
free(tag); |
} |
} |
|
|
if (h->symtab) |
if (h->symtab) |
mchars_free(h->symtab); |
mchars_free(h->symtab); |
|
|
free(h); |
free(h); |
} |
} |
|
|
|
|
void |
void |
print_gen_head(struct html *h) |
print_gen_head(struct html *h) |
{ |
{ |
Line 226 print_metaf(struct html *h, enum mandoc_esc deco) |
|
Line 224 print_metaf(struct html *h, enum mandoc_esc deco) |
|
enum htmlfont font; |
enum htmlfont font; |
|
|
switch (deco) { |
switch (deco) { |
case (ESCAPE_FONTPREV): |
case ESCAPE_FONTPREV: |
font = h->metal; |
font = h->metal; |
break; |
break; |
case (ESCAPE_FONTITALIC): |
case ESCAPE_FONTITALIC: |
font = HTMLFONT_ITALIC; |
font = HTMLFONT_ITALIC; |
break; |
break; |
case (ESCAPE_FONTBOLD): |
case ESCAPE_FONTBOLD: |
font = HTMLFONT_BOLD; |
font = HTMLFONT_BOLD; |
break; |
break; |
case (ESCAPE_FONT): |
case ESCAPE_FONTBI: |
|
font = HTMLFONT_BI; |
|
break; |
|
case ESCAPE_FONT: |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case (ESCAPE_FONTROMAN): |
case ESCAPE_FONTROMAN: |
font = HTMLFONT_NONE; |
font = HTMLFONT_NONE; |
break; |
break; |
default: |
default: |
Line 253 print_metaf(struct html *h, enum mandoc_esc deco) |
|
Line 254 print_metaf(struct html *h, enum mandoc_esc deco) |
|
h->metal = h->metac; |
h->metal = h->metac; |
h->metac = font; |
h->metac = font; |
|
|
if (HTMLFONT_NONE != font) |
switch (font) { |
h->metaf = HTMLFONT_BOLD == font ? |
case HTMLFONT_ITALIC: |
print_otag(h, TAG_B, 0, NULL) : |
h->metaf = print_otag(h, TAG_I, 0, NULL); |
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 |
int |
Line 289 html_strlen(const char *cp) |
|
Line 300 html_strlen(const char *cp) |
|
break; |
break; |
cp++; |
cp++; |
switch (mandoc_escape(&cp, NULL, NULL)) { |
switch (mandoc_escape(&cp, NULL, NULL)) { |
case (ESCAPE_ERROR): |
case ESCAPE_ERROR: |
return(sz); |
return(sz); |
case (ESCAPE_UNICODE): |
case ESCAPE_UNICODE: |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case (ESCAPE_NUMBERED): |
case ESCAPE_NUMBERED: |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case (ESCAPE_SPECIAL): |
case ESCAPE_SPECIAL: |
if (skip) |
if (skip) |
skip = 0; |
skip = 0; |
else |
else |
sz++; |
sz++; |
break; |
break; |
case (ESCAPE_SKIPCHAR): |
case ESCAPE_SKIPCHAR: |
skip = 1; |
skip = 1; |
break; |
break; |
default: |
default: |
Line 312 html_strlen(const char *cp) |
|
Line 323 html_strlen(const char *cp) |
|
} |
} |
|
|
static int |
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) |
print_encode(struct html *h, const char *p, int norecurse) |
{ |
{ |
size_t sz; |
size_t sz; |
int c, len, nospace; |
int c, len, nospace; |
const char *seq; |
const char *seq; |
enum mandoc_esc esc; |
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; |
nospace = 0; |
|
|
Line 337 print_encode(struct html *h, const char *p, int norecu |
|
Line 380 print_encode(struct html *h, const char *p, int norecu |
|
if ('\0' == *p) |
if ('\0' == *p) |
break; |
break; |
|
|
switch (*p++) { |
if (print_escape(*p++)) |
case ('<'): |
|
printf("<"); |
|
continue; |
continue; |
case ('>'): |
|
printf(">"); |
|
continue; |
|
case ('&'): |
|
printf("&"); |
|
continue; |
|
case (ASCII_HYPH): |
|
putchar('-'); |
|
continue; |
|
default: |
|
break; |
|
} |
|
|
|
esc = mandoc_escape(&p, &seq, &len); |
esc = mandoc_escape(&p, &seq, &len); |
if (ESCAPE_ERROR == esc) |
if (ESCAPE_ERROR == esc) |
break; |
break; |
|
|
switch (esc) { |
switch (esc) { |
case (ESCAPE_FONT): |
case ESCAPE_FONT: |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case (ESCAPE_FONTPREV): |
case ESCAPE_FONTPREV: |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case (ESCAPE_FONTBOLD): |
case ESCAPE_FONTBOLD: |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case (ESCAPE_FONTITALIC): |
case ESCAPE_FONTITALIC: |
/* FALLTHROUGH */ |
/* FALLTHROUGH */ |
case (ESCAPE_FONTROMAN): |
case ESCAPE_FONTBI: |
|
/* FALLTHROUGH */ |
|
case ESCAPE_FONTROMAN: |
if (0 == norecurse) |
if (0 == norecurse) |
print_metaf(h, esc); |
print_metaf(h, esc); |
continue; |
continue; |
case (ESCAPE_SKIPCHAR): |
case ESCAPE_SKIPCHAR: |
h->flags |= HTML_SKIPCHAR; |
h->flags |= HTML_SKIPCHAR; |
continue; |
continue; |
default: |
default: |
Line 384 print_encode(struct html *h, const char *p, int norecu |
|
Line 415 print_encode(struct html *h, const char *p, int norecu |
|
} |
} |
|
|
switch (esc) { |
switch (esc) { |
case (ESCAPE_UNICODE): |
case ESCAPE_UNICODE: |
/* Skip passed "u" header. */ |
/* Skip past "u" header. */ |
c = mchars_num2uc(seq + 1, len - 1); |
c = mchars_num2uc(seq + 1, len - 1); |
if ('\0' != c) |
if ('\0' != c) |
printf("&#x%x;", c); |
printf("&#x%x;", c); |
break; |
break; |
case (ESCAPE_NUMBERED): |
case ESCAPE_NUMBERED: |
c = mchars_num2char(seq, len); |
c = mchars_num2char(seq, len); |
if ('\0' != c) |
if ( ! ('\0' == c || print_escape(c))) |
putchar(c); |
putchar(c); |
break; |
break; |
case (ESCAPE_SPECIAL): |
case ESCAPE_SPECIAL: |
c = mchars_spec2cp(h->symtab, seq, len); |
c = mchars_spec2cp(h->symtab, seq, len); |
if (c > 0) |
if (c > 0) |
printf("&#%d;", c); |
printf("&#%d;", c); |
else if (-1 == c && 1 == len) |
else if (-1 == c && 1 == len && |
|
!print_escape(*seq)) |
putchar((int)*seq); |
putchar((int)*seq); |
break; |
break; |
case (ESCAPE_NOSPACE): |
case ESCAPE_NOSPACE: |
if ('\0' == *p) |
if ('\0' == *p) |
nospace = 1; |
nospace = 1; |
break; |
break; |
Line 414 print_encode(struct html *h, const char *p, int norecu |
|
Line 446 print_encode(struct html *h, const char *p, int norecu |
|
return(nospace); |
return(nospace); |
} |
} |
|
|
|
|
static void |
static void |
print_attr(struct html *h, const char *key, const char *val) |
print_attr(struct html *h, const char *key, const char *val) |
{ |
{ |
Line 423 print_attr(struct html *h, const char *key, const char |
|
Line 454 print_attr(struct html *h, const char *key, const char |
|
putchar('\"'); |
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) |
{ |
{ |
int i; |
int i; |
Line 475 print_otag(struct html *h, enum htmltag tag, |
|
Line 505 print_otag(struct html *h, enum htmltag tag, |
|
|
|
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: |
putchar('/'); |
putchar('/'); |
break; |
break; |
default: |
default: |
Line 492 print_otag(struct html *h, enum htmltag tag, |
|
Line 522 print_otag(struct html *h, enum htmltag tag, |
|
return(t); |
return(t); |
} |
} |
|
|
|
|
static void |
static void |
print_ctag(struct html *h, enum htmltag tag) |
print_ctag(struct html *h, enum htmltag tag) |
{ |
{ |
|
|
printf("</%s>", htmltags[tag].name); |
printf("</%s>", htmltags[tag].name); |
if (HTML_CLRLINE & htmltags[tag].flags) { |
if (HTML_CLRLINE & htmltags[tag].flags) { |
h->flags |= HTML_NOSPACE; |
h->flags |= HTML_NOSPACE; |
putchar('\n'); |
putchar('\n'); |
} |
} |
} |
} |
|
|
void |
void |
Line 512 print_gen_decls(struct html *h) |
|
Line 541 print_gen_decls(struct html *h) |
|
const char *name; |
const char *name; |
|
|
switch (h->type) { |
switch (h->type) { |
case (HTML_HTML_4_01_STRICT): |
case HTML_HTML_4_01_STRICT: |
name = "HTML"; |
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"; |
Line 525 print_gen_decls(struct html *h) |
|
Line 554 print_gen_decls(struct html *h) |
|
break; |
break; |
} |
} |
|
|
printf("<!DOCTYPE %s PUBLIC \"%s\" \"%s\">\n", |
printf("<!DOCTYPE %s PUBLIC \"%s\" \"%s\">\n", |
name, doctype, dtd); |
name, doctype, dtd); |
} |
} |
|
|
void |
void |
Line 544 print_text(struct html *h, const char *word) |
|
Line 573 print_text(struct html *h, const char *word) |
|
} |
} |
|
|
assert(NULL == h->metaf); |
assert(NULL == h->metaf); |
if (HTMLFONT_NONE != h->metac) |
switch (h->metac) { |
h->metaf = HTMLFONT_BOLD == h->metac ? |
case HTMLFONT_ITALIC: |
print_otag(h, TAG_B, 0, NULL) : |
h->metaf = print_otag(h, TAG_I, 0, NULL); |
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); |
assert(word); |
if ( ! print_encode(h, word, 0)) { |
if ( ! print_encode(h, word, 0)) { |
Line 564 print_text(struct html *h, const char *word) |
|
Line 603 print_text(struct html *h, const char *word) |
|
h->flags &= ~HTML_IGNDELIM; |
h->flags &= ~HTML_IGNDELIM; |
} |
} |
|
|
|
|
void |
void |
print_tagq(struct html *h, const struct tag *until) |
print_tagq(struct html *h, const struct tag *until) |
{ |
{ |
struct tag *tag; |
struct tag *tag; |
|
|
while ((tag = h->tags.head) != NULL) { |
while ((tag = h->tags.head) != NULL) { |
/* |
/* |
* Remember to close out and nullify the current |
* Remember to close out and nullify the current |
* meta-font and table, if applicable. |
* meta-font and table, if applicable. |
*/ |
*/ |
Line 587 print_tagq(struct html *h, const struct tag *until) |
|
Line 625 print_tagq(struct html *h, const struct tag *until) |
|
} |
} |
} |
} |
|
|
|
|
void |
void |
print_stagq(struct html *h, const struct tag *suntil) |
print_stagq(struct html *h, const struct tag *suntil) |
{ |
{ |
Line 596 print_stagq(struct html *h, const struct tag *suntil) |
|
Line 633 print_stagq(struct html *h, const struct tag *suntil) |
|
while ((tag = h->tags.head) != NULL) { |
while ((tag = h->tags.head) != NULL) { |
if (suntil && tag == suntil) |
if (suntil && tag == suntil) |
return; |
return; |
/* |
/* |
* Remember to close out and nullify the current |
* Remember to close out and nullify the current |
* meta-font and table, if applicable. |
* meta-font and table, if applicable. |
*/ |
*/ |
|
|
bufcat(struct html *h, const char *p) |
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); |
h->buflen = strlcat(h->buf, p, BUFSIZ); |
assert(h->buflen < BUFSIZ); |
assert(h->buflen < BUFSIZ); |
} |
} |
Line 642 bufcat_fmt(struct html *h, const char *fmt, ...) |
|
Line 685 bufcat_fmt(struct html *h, const char *fmt, ...) |
|
va_list ap; |
va_list ap; |
|
|
va_start(ap, fmt); |
va_start(ap, fmt); |
(void)vsnprintf(h->buf + (int)h->buflen, |
(void)vsnprintf(h->buf + (int)h->buflen, |
BUFSIZ - h->buflen - 1, fmt, ap); |
BUFSIZ - h->buflen - 1, fmt, ap); |
va_end(ap); |
va_end(ap); |
h->buflen = strlen(h->buf); |
h->buflen = strlen(h->buf); |
} |
} |
Line 663 buffmt_includes(struct html *h, const char *name) |
|
Line 706 buffmt_includes(struct html *h, const char *name) |
|
const char *p, *pp; |
const char *p, *pp; |
|
|
pp = h->base_includes; |
pp = h->base_includes; |
|
|
bufinit(h); |
bufinit(h); |
while (NULL != (p = strchr(pp, '%'))) { |
while (NULL != (p = strchr(pp, '%'))) { |
bufncat(h, pp, (size_t)(p - pp)); |
bufncat(h, pp, (size_t)(p - pp)); |
switch (*(p + 1)) { |
switch (*(p + 1)) { |
case('I'): |
case'I': |
bufcat(h, name); |
bufcat(h, name); |
break; |
break; |
default: |
default: |
Line 682 buffmt_includes(struct html *h, const char *name) |
|
Line 725 buffmt_includes(struct html *h, const char *name) |
|
} |
} |
|
|
void |
void |
buffmt_man(struct html *h, |
buffmt_man(struct html *h, const char *name, const char *sec) |
const char *name, const char *sec) |
|
{ |
{ |
const char *p, *pp; |
const char *p, *pp; |
|
|
pp = h->base_man; |
pp = h->base_man; |
|
|
bufinit(h); |
bufinit(h); |
while (NULL != (p = strchr(pp, '%'))) { |
while (NULL != (p = strchr(pp, '%'))) { |
bufncat(h, pp, (size_t)(p - pp)); |
bufncat(h, pp, (size_t)(p - pp)); |
switch (*(p + 1)) { |
switch (*(p + 1)) { |
case('S'): |
case 'S': |
bufcat(h, sec ? sec : "1"); |
bufcat(h, sec ? sec : "1"); |
break; |
break; |
case('N'): |
case 'N': |
bufcat_fmt(h, name); |
bufcat_fmt(h, "%s", name); |
break; |
break; |
default: |
default: |
bufncat(h, p, 2); |
bufncat(h, p, 2); |