static inline void outc(cmark_renderer *renderer, cmark_escaping escape,
int32_t c, unsigned char nextc) {
bool needs_escaping = false;
char encoded[20];
needs_escaping =
escape != LITERAL &&
((escape == NORMAL &&
(c == '*' || c == '_' || c == '[' || c == ']' || c == '#' || c == '<' ||
c == '>' || c == '\\' || c == '`' || c == '!' ||
(c == '&' && isalpha(nextc)) || (c == '!' && nextc == '[') ||
(renderer->begin_line && (c == '-' || c == '+' || c == '=')) ||
((c == '.' || c == ')') &&
isdigit(renderer->buffer->ptr[renderer->buffer->size - 1])))) ||
(escape == URL && (c == '`' || c == '<' || c == '>' || isspace(c) ||
c == '\\' || c == ')' || c == '(')) ||
(escape == TITLE &&
(c == '`' || c == '<' || c == '>' || c == '"' || c == '\\')));
if (needs_escaping) {
if (isspace(c)) {
// use percent encoding for spaces
sprintf(encoded, "%%%2x", c);
cmark_strbuf_puts(renderer->buffer, encoded);
renderer->column += 3;
} else {
cmark_render_ascii(renderer, "\\");
cmark_render_code_point(renderer, c);
}
} else {
cmark_render_code_point(renderer, c);
}
}
// Functions to convert cmark_nodes to groff man strings.
static
void S_outc(cmark_renderer *renderer,
cmark_escaping escape,
int32_t c,
unsigned char nextc)
{
(void)(nextc);
if (escape == LITERAL) {
cmark_render_code_point(renderer, c);
return;
}
switch(c) {
case 46:
if (renderer->begin_line) {
cmark_render_ascii(renderer, "\\&.");
} else {
cmark_render_code_point(renderer, c);
}
break;
case 39:
if (renderer->begin_line) {
cmark_render_ascii(renderer, "\\&'");
} else {
cmark_render_code_point(renderer, c);
}
break;
case 45:
cmark_render_ascii(renderer, "\\-");
break;
case 92:
cmark_render_ascii(renderer, "\\e");
break;
case 8216: // left single quote
cmark_render_ascii(renderer, "\\[oq]");
break;
case 8217: // right single quote
cmark_render_ascii(renderer, "\\[cq]");
break;
case 8220: // left double quote
cmark_render_ascii(renderer, "\\[lq]");
break;
case 8221: // right double quote
cmark_render_ascii(renderer, "\\[rq]");
break;
case 8212: // em dash
cmark_render_ascii(renderer, "\\[em]");
break;
case 8211: // en dash
cmark_render_ascii(renderer, "\\[en]");
break;
default:
cmark_render_code_point(renderer, c);
}
}
static CMARK_INLINE void outc(cmark_renderer *renderer, cmark_escaping escape,
int32_t c, unsigned char nextc) {
bool needs_escaping = false;
bool follows_digit =
renderer->buffer->size > 0 &&
cmark_isdigit(renderer->buffer->ptr[renderer->buffer->size - 1]);
char encoded[ENCODED_SIZE];
needs_escaping =
c < 0x80 && escape != LITERAL &&
((escape == NORMAL &&
(c < 0x20 ||
c == '*' || c == '_' || c == '[' || c == ']' || c == '#' || c == '<' ||
c == '>' || c == '\\' || c == '`' || c == '!' ||
(c == '&' && cmark_isalpha(nextc)) || (c == '!' && nextc == '[') ||
(renderer->begin_content && (c == '-' || c == '+' || c == '=') &&
// begin_content doesn't get set to false til we've passed digits
// at the beginning of line, so...
!follows_digit) ||
(renderer->begin_content && (c == '.' || c == ')') && follows_digit &&
(nextc == 0 || cmark_isspace(nextc))))) ||
(escape == URL &&
(c == '`' || c == '<' || c == '>' || cmark_isspace(c) || c == '\\' ||
c == ')' || c == '(')) ||
(escape == TITLE &&
(c == '`' || c == '<' || c == '>' || c == '"' || c == '\\')));
if (needs_escaping) {
if (escape == URL && cmark_isspace(c)) {
// use percent encoding for spaces
snprintf(encoded, ENCODED_SIZE, "%%%2X", c);
cmark_strbuf_puts(renderer->buffer, encoded);
renderer->column += 3;
} else if (cmark_ispunct(c)) {
cmark_render_ascii(renderer, "\\");
cmark_render_code_point(renderer, c);
} else { // render as entity
snprintf(encoded, ENCODED_SIZE, "&#%d;", c);
cmark_strbuf_puts(renderer->buffer, encoded);
renderer->column += strlen(encoded);
}
} else {
cmark_render_code_point(renderer, c);
}
}
static void S_out(cmark_renderer *renderer, cmark_node *node,
const char *source, bool wrap,
cmark_escaping escape) {
int length = (int)strlen(source);
unsigned char nextc;
int32_t c;
int i = 0;
int last_nonspace;
int len;
cmark_chunk remainder = cmark_chunk_literal("");
int k = renderer->buffer->size - 1;
cmark_syntax_extension *ext = NULL;
cmark_node *n = node;
while (n && !ext) {
ext = n->extension;
if (!ext)
n = n->parent;
}
if (ext && !ext->commonmark_escape_func)
ext = NULL;
wrap = wrap && !renderer->no_linebreaks;
if (renderer->in_tight_list_item && renderer->need_cr > 1) {
renderer->need_cr = 1;
}
while (renderer->need_cr) {
if (k < 0 || renderer->buffer->ptr[k] == '\n') {
k -= 1;
} else {
cmark_strbuf_putc(renderer->buffer, '\n');
if (renderer->need_cr > 1) {
cmark_strbuf_put(renderer->buffer, renderer->prefix->ptr,
renderer->prefix->size);
}
}
renderer->column = 0;
renderer->begin_line = true;
renderer->begin_content = true;
renderer->need_cr -= 1;
}
while (i < length) {
if (renderer->begin_line) {
cmark_strbuf_put(renderer->buffer, renderer->prefix->ptr,
renderer->prefix->size);
// note: this assumes prefix is ascii:
renderer->column = renderer->prefix->size;
}
len = cmark_utf8proc_iterate((const uint8_t *)source + i, length - i, &c);
if (len == -1) { // error condition
return; // return without rendering rest of string
}
if (ext && ext->commonmark_escape_func(ext, node, c))
cmark_strbuf_putc(renderer->buffer, '\\');
nextc = source[i + len];
if (c == 32 && wrap) {
if (!renderer->begin_line) {
last_nonspace = renderer->buffer->size;
cmark_strbuf_putc(renderer->buffer, ' ');
renderer->column += 1;
renderer->begin_line = false;
renderer->begin_content = false;
// skip following spaces
while (source[i + 1] == ' ') {
i++;
}
// We don't allow breaks that make a digit the first character
// because this causes problems with commonmark output.
if (!cmark_isdigit(source[i + 1])) {
renderer->last_breakable = last_nonspace;
}
}
} else if (c == 10) {
cmark_strbuf_putc(renderer->buffer, '\n');
renderer->column = 0;
renderer->begin_line = true;
renderer->begin_content = true;
renderer->last_breakable = 0;
} else if (escape == LITERAL) {
cmark_render_code_point(renderer, c);
renderer->begin_line = false;
// we don't set 'begin_content' to false til we've
// finished parsing a digit. Reason: in commonmark
// we need to escape a potential list marker after
// a digit:
renderer->begin_content =
renderer->begin_content && cmark_isdigit((char)c) == 1;
} else {
(renderer->outc)(renderer, node, escape, c, nextc);
renderer->begin_line = false;
renderer->begin_content =
renderer->begin_content && cmark_isdigit((char)c) == 1;
}
// If adding the character went beyond width, look for an
// earlier place where the line could be broken:
if (renderer->width > 0 && renderer->column > renderer->width &&
!renderer->begin_line && renderer->last_breakable > 0) {
// copy from last_breakable to remainder
cmark_chunk_set_cstr(renderer->mem, &remainder,
(char *)renderer->buffer->ptr +
renderer->last_breakable + 1);
// truncate at last_breakable
cmark_strbuf_truncate(renderer->buffer, renderer->last_breakable);
// add newline, prefix, and remainder
cmark_strbuf_putc(renderer->buffer, '\n');
cmark_strbuf_put(renderer->buffer, renderer->prefix->ptr,
renderer->prefix->size);
cmark_strbuf_put(renderer->buffer, remainder.data, remainder.len);
renderer->column = renderer->prefix->size + remainder.len;
cmark_chunk_free(renderer->mem, &remainder);
renderer->last_breakable = 0;
renderer->begin_line = false;
renderer->begin_content = false;
}
i += len;
}
}
static CMARK_INLINE void outc(cmark_renderer *renderer, cmark_escaping escape,
int32_t c, unsigned char nextc) {
if (escape == LITERAL) {
cmark_render_code_point(renderer, c);
return;
}
switch (c) {
case 123: // '{'
case 125: // '}'
case 35: // '#'
case 37: // '%'
case 38: // '&'
cmark_render_ascii(renderer, "\\");
cmark_render_code_point(renderer, c);
break;
case 36: // '$'
case 95: // '_'
if (escape == NORMAL) {
cmark_render_ascii(renderer, "\\");
}
cmark_render_code_point(renderer, c);
break;
case 45: // '-'
if (nextc == 45) { // prevent ligature
cmark_render_ascii(renderer, "-{}");
} else {
cmark_render_ascii(renderer, "-");
}
break;
case 126: // '~'
if (escape == NORMAL) {
cmark_render_ascii(renderer, "\\textasciitilde{}");
} else {
cmark_render_code_point(renderer, c);
}
break;
case 94: // '^'
cmark_render_ascii(renderer, "\\^{}");
break;
case 92: // '\\'
if (escape == URL) {
// / acts as path sep even on windows:
cmark_render_ascii(renderer, "/");
} else {
cmark_render_ascii(renderer, "\\textbackslash{}");
}
break;
case 124: // '|'
cmark_render_ascii(renderer, "\\textbar{}");
break;
case 60: // '<'
cmark_render_ascii(renderer, "\\textless{}");
break;
case 62: // '>'
cmark_render_ascii(renderer, "\\textgreater{}");
break;
case 91: // '['
case 93: // ']'
cmark_render_ascii(renderer, "{");
cmark_render_code_point(renderer, c);
cmark_render_ascii(renderer, "}");
break;
case 34: // '"'
cmark_render_ascii(renderer, "\\textquotedbl{}");
// requires \usepackage[T1]{fontenc}
break;
case 39: // '\''
cmark_render_ascii(renderer, "\\textquotesingle{}");
// requires \usepackage{textcomp}
break;
case 160: // nbsp
cmark_render_ascii(renderer, "~");
break;
case 8230: // hellip
cmark_render_ascii(renderer, "\\ldots{}");
break;
case 8216: // lsquo
if (escape == NORMAL) {
cmark_render_ascii(renderer, "`");
} else {
cmark_render_code_point(renderer, c);
}
break;
case 8217: // rsquo
if (escape == NORMAL) {
cmark_render_ascii(renderer, "\'");
} else {
cmark_render_code_point(renderer, c);
}
break;
case 8220: // ldquo
if (escape == NORMAL) {
cmark_render_ascii(renderer, "``");
} else {
cmark_render_code_point(renderer, c);
}
break;
case 8221: // rdquo
if (escape == NORMAL) {
cmark_render_ascii(renderer, "''");
} else {
cmark_render_code_point(renderer, c);
}
break;
case 8212: // emdash
if (escape == NORMAL) {
cmark_render_ascii(renderer, "---");
} else {
cmark_render_code_point(renderer, c);
}
break;
case 8211: // endash
if (escape == NORMAL) {
cmark_render_ascii(renderer, "--");
} else {
cmark_render_code_point(renderer, c);
}
break;
default:
cmark_render_code_point(renderer, c);
}
}
static
void S_out(cmark_renderer *renderer,
const char *source,
bool wrap,
cmark_escaping escape)
{
int length = cmark_strbuf_safe_strlen(source);
unsigned char nextc;
int32_t c;
int i = 0;
int len;
cmark_chunk remainder = cmark_chunk_literal("");
int k = renderer->buffer->size - 1;
wrap = wrap && !renderer->no_wrap;
if (renderer->in_tight_list_item && renderer->need_cr > 1) {
renderer->need_cr = 1;
}
while (renderer->need_cr) {
if (k < 0 || renderer->buffer->ptr[k] == '\n') {
k -= 1;
} else {
cmark_strbuf_putc(renderer->buffer, '\n');
if (renderer->need_cr > 1) {
cmark_strbuf_put(renderer->buffer, renderer->prefix->ptr,
renderer->prefix->size);
}
}
renderer->column = 0;
renderer->begin_line = true;
renderer->need_cr -= 1;
}
while (i < length) {
if (renderer->begin_line) {
cmark_strbuf_put(renderer->buffer, renderer->prefix->ptr,
renderer->prefix->size);
// note: this assumes prefix is ascii:
renderer->column = renderer->prefix->size;
}
len = utf8proc_iterate((const uint8_t *)source + i, length - i, &c);
if (len == -1) { // error condition
return; // return without rendering rest of string
}
nextc = source[i + len];
if (c == 32 && wrap) {
if (!renderer->begin_line) {
cmark_strbuf_putc(renderer->buffer, ' ');
renderer->column += 1;
renderer->begin_line = false;
renderer->last_breakable = renderer->buffer->size -
1;
// skip following spaces
while (source[i + 1] == ' ') {
i++;
}
}
} else if (c == 10) {
cmark_strbuf_putc(renderer->buffer, '\n');
renderer->column = 0;
renderer->begin_line = true;
renderer->last_breakable = 0;
} else if (escape == LITERAL) {
cmark_render_code_point(renderer, c);
renderer->begin_line = false;
} else {
(renderer->outc)(renderer, escape, c, nextc);
renderer->begin_line = false;
}
// If adding the character went beyond width, look for an
// earlier place where the line could be broken:
if (renderer->width > 0 &&
renderer->column > renderer->width &&
!renderer->begin_line &&
renderer->last_breakable > 0) {
// copy from last_breakable to remainder
cmark_chunk_set_cstr(&remainder, (char *) renderer->buffer->ptr + renderer->last_breakable + 1);
// truncate at last_breakable
cmark_strbuf_truncate(renderer->buffer, renderer->last_breakable);
// add newline, prefix, and remainder
cmark_strbuf_putc(renderer->buffer, '\n');
cmark_strbuf_put(renderer->buffer, renderer->prefix->ptr,
renderer->prefix->size);
cmark_strbuf_put(renderer->buffer, remainder.data, remainder.len);
renderer->column = renderer->prefix->size + remainder.len;
cmark_chunk_free(&remainder);
renderer->last_breakable = 0;
renderer->begin_line = false;
}
i += len;
}
}
