#define SIZEOF(a) (sizeof(a) / sizeof(a[0]))
-/* The Tcl syntax is defined in the Tcl.n manual page.
+/* The Tcl syntax is defined in the Tcl.n manual page, see
+ https://www.tcl-lang.org/man/tcl8.6/TclCmd/Tcl.htm .
Summary of Tcl syntax:
Like sh syntax, except that `...` is replaced with [...]. In detail:
- In a preprocessing pass, backslash-newline-anywhitespace is replaced
- The list of resulting words is split into commands by semicolon and
newline.
- '#' at the beginning of a command introduces a comment until end of line.
- The parser is implemented in tcl8.3.3/generic/tclParse.c. */
+ The parser is implemented in tcl8.6/generic/tclParse.c. */
/* ====================== Keyword set customization. ====================== */
/* An int that becomes a space when casted to 'unsigned char'. */
#define BS_NL (UCHAR_MAX + 1 + ' ')
-static int phase1_pushback[1];
+static int phase1_pushback[5];
static int phase1_pushback_length;
static int
/* Read an escape sequence. The value is an ISO-8859-1 character (in the
- range 0x00..0xff) or a Unicode character (in the range 0x0000..0xffff). */
+ range 0x00..0xff) or a Unicode character (in the range 0x0000..0x10FFFF). */
static int
do_getc_escaped ()
{
return '\v';
case 'x':
{
- int n = 0;
+ unsigned int n = 0;
unsigned int i;
- for (i = 0;; i++)
+ for (i = 0; i < 2; i++)
{
c = phase1_getc ();
if (c == EOF || !c_isxdigit ((unsigned char) c))
- break;
+ {
+ phase1_ungetc (c);
+ break;
+ }
if (c >= '0' && c <= '9')
n = (n << 4) + (c - '0');
else if (c >= 'a' && c <= 'f')
n = (n << 4) + (c - 'a' + 10);
}
- phase1_ungetc (c);
return (i > 0 ? (unsigned char) n : 'x');
}
case 'u':
{
- int n = 0;
+ unsigned int n = 0;
unsigned int i;
for (i = 0; i < 4; i++)
break;
}
+ if (c >= '0' && c <= '9')
+ n = (n << 4) + (c - '0');
+ else if (c >= 'A' && c <= 'F')
+ n = (n << 4) + (c - 'A' + 10);
+ else if (c >= 'a' && c <= 'f')
+ n = (n << 4) + (c - 'a' + 10);
+ }
+ return (i > 0 ? n : 'u');
+ }
+ case 'U':
+ {
+ unsigned int n = 0;
+ unsigned int i;
+
+ for (i = 0; i < 8; i++)
+ {
+ c = phase1_getc ();
+ if (c == EOF || !c_isxdigit ((unsigned char) c) || n >= 0x11000)
+ {
+ phase1_ungetc (c);
+ break;
+ }
+
if (c >= '0' && c <= '9')
n = (n << 4) + (c - '0');
else if (c >= 'A' && c <= 'F')
}
}
+/* Read an escape sequence for a low surrogate Unicode character.
+ The value is in the range 0xDC00..0xDFFF.
+ Return -1 when none was seen. */
+static int
+do_getc_escaped_low_surrogate ()
+{
+ int c;
+
+ c = phase1_getc ();
+ switch (c)
+ {
+ case 'u':
+ {
+ unsigned char buf[4];
+ unsigned int n = 0;
+ unsigned int i;
+
+ for (i = 0; i < 4; i++)
+ {
+ c = phase1_getc ();
+ if (c == EOF || !c_isxdigit ((unsigned char) c))
+ {
+ phase1_ungetc (c);
+ while (i > 0)
+ phase1_ungetc (buf[--i]);
+ phase1_ungetc ('u');
+ return -1;
+ }
+
+ if (c >= '0' && c <= '9')
+ n = (n << 4) + (c - '0');
+ else if (c >= 'A' && c <= 'F')
+ n = (n << 4) + (c - 'A' + 10);
+ else if (c >= 'a' && c <= 'f')
+ n = (n << 4) + (c - 'a' + 10);
+ }
+ if (n >= 0xdc00 && n <= 0xdfff)
+ return n;
+ else
+ {
+ while (i > 0)
+ phase1_ungetc (buf[--i]);
+ phase1_ungetc ('u');
+ return -1;
+ }
+ }
+ default:
+ phase1_ungetc (c);
+ return -1;
+ }
+}
+
enum terminator
{
}
else if (c == '\\')
{
- unsigned int uc;
- unsigned char utf8buf[6];
- int count;
- int i;
-
- uc = do_getc_escaped ();
- assert (uc < 0x10000);
- count = u8_uctomb (utf8buf, uc, 6);
- if (count < 0)
+ unsigned int uc = do_getc_escaped ();
+ assert (uc < 0x110000);
+ if (uc >= 0xd800 && uc <= 0xdfff)
{
+ if (uc < 0xdc00)
+ {
+ /* Saw a high surrogate Unicode character.
+ Is it followed by a low surrogate Unicode character? */
+ c = phase2_getc ();
+ if (c == '\\')
+ {
+ int uc2 = do_getc_escaped_low_surrogate ();
+ if (uc2 >= 0)
+ {
+ /* Saw a low surrogate Unicode character. */
+ assert (uc2 >= 0xdc00 && uc2 <= 0xdfff);
+ uc = 0x10000 + ((uc - 0xd800) << 10) + (uc2 - 0xdc00);
+ goto saw_unicode_escape;
+ }
+ }
+ phase2_ungetc (c);
+ }
error_with_progname = false;
error (0, 0, _("%s:%d: warning: invalid Unicode character"),
logical_file_name, line_number);
error_with_progname = true;
+ goto done_escape;
}
- else
- {
- assert (count > 0);
- if (wp->type == t_string)
- for (i = 0; i < count; i++)
- {
- grow_token (wp->token);
- wp->token->chars[wp->token->charcount++] = utf8buf[i];
- }
- }
+ saw_unicode_escape:
+ {
+ unsigned char utf8buf[6];
+ int count = u8_uctomb (utf8buf, uc, 6);
+ int i;
+ assert (count > 0);
+ if (wp->type == t_string)
+ for (i = 0; i < count; i++)
+ {
+ grow_token (wp->token);
+ wp->token->chars[wp->token->charcount++] = utf8buf[i];
+ }
+ }
+ done_escape: ;
}
else
{
puts [_ "\udc1c"]
EOF
+cat <<\EOF > xg-t-5c.tcl
+puts [_ "\uD83D\n"]
+EOF
+
+cat <<\EOF > xg-t-5d.tcl
+puts [_ "\uD83D\u"]
+EOF
+
+cat <<\EOF > xg-t-5e.tcl
+puts [_ "\uD83D\u9843"]
+EOF
+
+cat <<\EOF > xg-t-5f.tcl
+puts [_ "\uD83D\ud913"]
+EOF
+
+cat <<\EOF > xg-t-5g.tcl
+puts [_ "\udc1c\ud83d"]
+EOF
+
: ${XGETTEXT=xgettext}
LANGUAGE= LC_ALL=C ${XGETTEXT} --no-location -k_ -d xg-t-5.tmp xg-t-5a.tcl 2>xg-t-5.err
result=$?
cat xg-t-5.err
test $result = 0 || Exit 1
+: ${XGETTEXT=xgettext}
+LANGUAGE= LC_ALL=C ${XGETTEXT} --no-location -k_ -d xg-t-5.tmp xg-t-5c.tcl 2>xg-t-5.err
+result=$?
+cat xg-t-5.err
+test $result = 0 || Exit 1
+
+: ${XGETTEXT=xgettext}
+LANGUAGE= LC_ALL=C ${XGETTEXT} --no-location -k_ -d xg-t-5.tmp xg-t-5d.tcl 2>xg-t-5.err
+result=$?
+cat xg-t-5.err
+test $result = 0 || Exit 1
+
+: ${XGETTEXT=xgettext}
+LANGUAGE= LC_ALL=C ${XGETTEXT} --no-location -k_ -d xg-t-5.tmp xg-t-5e.tcl 2>xg-t-5.err
+result=$?
+cat xg-t-5.err
+test $result = 0 || Exit 1
+
+: ${XGETTEXT=xgettext}
+LANGUAGE= LC_ALL=C ${XGETTEXT} --no-location -k_ -d xg-t-5.tmp xg-t-5f.tcl 2>xg-t-5.err
+result=$?
+cat xg-t-5.err
+test $result = 0 || Exit 1
+
+: ${XGETTEXT=xgettext}
+LANGUAGE= LC_ALL=C ${XGETTEXT} --no-location -k_ -d xg-t-5.tmp xg-t-5g.tcl 2>xg-t-5.err
+result=$?
+cat xg-t-5.err
+test $result = 0 || Exit 1
+
exit 0
projects / thirdparty / gettext.git / commitdiff
