/*
* Is a character the end of an ANSI escape sequence?
*/
int
is_ansi_end(LWCHAR ch)
{
if (!is_ascii_char(ch))
return (0);
return (strchr(end_ansi_chars, (char)ch) != NULL);
}
int
is_ansi_middle(LWCHAR ch)
{
if (!is_ascii_char(ch))
return (0);
if (is_ansi_end(ch))
return (0);
return (strchr(mid_ansi_chars, (char)ch) != NULL);
}
/*
* Return the printing width of a given character and attribute,
* if the character were added to the current position in the line buffer.
* Adding a character with a given attribute may cause an enter or exit
* attribute sequence to be inserted, so this must be taken into account.
*/
static int
pwidth(LWCHAR ch, int a, LWCHAR prev_ch)
{
int w;
if (ch == '\b')
/*
* Backspace moves backwards one or two positions.
* XXX - Incorrect if several '\b' in a row.
*/
return ((utf_mode && is_wide_char(prev_ch)) ? -2 : -1);
if (!utf_mode || is_ascii_char(ch)) {
if (control_char((char)ch)) {
/*
* Control characters do unpredictable things,
* so we don't even try to guess; say it doesn't move.
* This can only happen if the -r flag is in effect.
*/
return (0);
}
} else {
if (is_composing_char(ch) || is_combining_char(prev_ch, ch)) {
/*
* Composing and combining chars take up no space.
*
* Some terminals, upon failure to compose a
* composing character with the character(s) that
* precede(s) it will actually take up one column
* for the composing character; there isn't much
* we could do short of testing the (complex)
* composition process ourselves and printing
* a binary representation when it fails.
*/
return (0);
}
}
/*
* Other characters take one or two columns,
* plus the width of any attribute enter/exit sequence.
*/
w = 1;
if (is_wide_char(ch))
w++;
if (curr > 0 && !is_at_equiv(attr[curr-1], a))
w += attr_ewidth(attr[curr-1]);
if ((apply_at_specials(a) != AT_NORMAL) &&
(curr == 0 || !is_at_equiv(attr[curr-1], a)))
w += attr_swidth(a);
return (w);
}
void parser::skip_whitespaces(utf8str::iterator& it, utf8str::iterator& end_it)
{
while (it != end_it)
{
uint32_t ch = utf8::peek_next(it, end_it);
if (is_ascii_char(ch))
{
switch ((char)ch)
{
case (' '):
case ('\n'):
case ('\r'):
case ('\v'):
case ('\t'):
utf8::unchecked::next(it);
break;
default:
return;
}
}
}
}
bool parser::is_atom_char(uint32_t ch)
{
return is_ascii_char(ch) && (iswalnum((char) ch) || iswdigit((char) ch) || iswpunct((char)ch))
&& ch != ')' && ch != '(';
}
static int
do_append(LWCHAR ch, char *rep, off_t pos)
{
int a;
LWCHAR prev_ch;
a = AT_NORMAL;
if (ch == '\b') {
if (bs_mode == BS_CONTROL)
goto do_control_char;
/*
* A better test is needed here so we don't
* backspace over part of the printed
* representation of a binary character.
*/
if (curr <= lmargin ||
column <= lmargin ||
(attr[curr - 1] & (AT_ANSI|AT_BINARY))) {
STORE_PRCHAR('\b', pos);
} else if (bs_mode == BS_NORMAL) {
STORE_CHAR(ch, AT_NORMAL, NULL, pos);
} else if (bs_mode == BS_SPECIAL) {
overstrike = backc();
}
return (0);
}
if (overstrike > 0) {
/*
* Overstrike the character at the current position
* in the line buffer. This will cause either
* underline (if a "_" is overstruck),
* bold (if an identical character is overstruck),
* or just deletion of the character in the buffer.
*/
overstrike = utf_mode ? -1 : 0;
/* To be correct, this must be a base character. */
prev_ch = get_wchar(linebuf + curr);
a = attr[curr];
if (ch == prev_ch) {
/*
* Overstriking a char with itself means make it bold.
* But overstriking an underscore with itself is
* ambiguous. It could mean make it bold, or
* it could mean make it underlined.
* Use the previous overstrike to resolve it.
*/
if (ch == '_') {
if ((a & (AT_BOLD|AT_UNDERLINE)) != AT_NORMAL)
a |= (AT_BOLD|AT_UNDERLINE);
else if (last_overstrike != AT_NORMAL)
a |= last_overstrike;
else
a |= AT_BOLD;
} else {
a |= AT_BOLD;
}
} else if (ch == '_') {
a |= AT_UNDERLINE;
ch = prev_ch;
rep = linebuf + curr;
} else if (prev_ch == '_') {
a |= AT_UNDERLINE;
}
/* Else we replace prev_ch, but we keep its attributes. */
} else if (overstrike < 0) {
if (is_composing_char(ch) ||
is_combining_char(get_wchar(linebuf + curr), ch))
/* Continuation of the same overstrike. */
a = last_overstrike;
else
overstrike = 0;
}
if (ch == '\t') {
/*
* Expand a tab into spaces.
*/
switch (bs_mode) {
case BS_CONTROL:
goto do_control_char;
case BS_NORMAL:
case BS_SPECIAL:
STORE_TAB(a, pos);
break;
}
} else if ((!utf_mode || is_ascii_char(ch)) && control_char((char)ch)) {
do_control_char:
if (ctldisp == OPT_ON ||
(ctldisp == OPT_ONPLUS && IS_CSI_START(ch))) {
/*
* Output as a normal character.
*/
STORE_CHAR(ch, AT_NORMAL, rep, pos);
} else {
STORE_PRCHAR((char)ch, pos);
}
} else if (utf_mode && ctldisp != OPT_ON && is_ubin_char(ch)) {
char *s;
s = prutfchar(ch);
if (column + (int)strlen(s) - 1 +
pwidth(' ', binattr, 0) + attr_ewidth(binattr) > sc_width)
return (1);
for (; *s != 0; s++)
STORE_CHAR(*s, AT_BINARY, NULL, pos);
} else {
STORE_CHAR(ch, a, rep, pos);
}
return (0);
}