Tcl Source Code

.IP \fBlower\fR 12
Any Unicode lower case alphabet character.
.IP \fBprint\fR 12
Any Unicode printing character, including space.
.IP \fBpunct\fR 12
Any Unicode punctuation character.
.IP \fBspace\fR 12
Any Unicode space character.
Any Unicode whitespace character, zero width space (U+200b),
word joiner (U+2060) and zero width no-break space (U+feff) (=BOM).
.IP \fBtrue\fR 12
Any of the forms allowed to \fBTcl_GetBoolean\fR where the value is
true.
.IP \fBupper\fR 12
Any upper case alphabet character in the Unicode character set.
.IP \fBwideinteger\fR 12
Any of the valid forms for a wide integer in Tcl, with optional

the string to stop at (inclusive).  \fIfirst\fR and \fIlast\fR may be
specified using the forms described in \fBSTRING INDICES\fR.
.TP
\fBstring trim \fIstring\fR ?\fIchars\fR?
.
Returns a value equal to \fIstring\fR except that any leading or
trailing characters present in the string given by \fIchars\fR are removed.  If
\fIchars\fR is not specified then white space is removed (spaces,
tabs, newlines, and carriage returns).
\fIchars\fR is not specified then white space is removed (any character
for which \fBstring is space\fR returns 1, and "\0").
.TP
\fBstring trimleft \fIstring\fR ?\fIchars\fR?
.
Returns a value equal to \fIstring\fR except that any leading
characters present in the string given by \fIchars\fR are removed.  If
\fIchars\fR is not specified then white space is removed (spaces,
tabs, newlines, and carriage returns).
\fIchars\fR is not specified then white space is removed (any character
for which \fBstring is space\fR returns 1, and "\0").
.TP
\fBstring trimright \fIstring\fR ?\fIchars\fR?
.
Returns a value equal to \fIstring\fR except that any trailing
characters present in the string given by \fIchars\fR are removed.  If
\fIchars\fR is not specified then white space is removed (spaces,
tabs, newlines, and carriage returns).
\fIchars\fR is not specified then white space is removed (any character
for which \fBstring is space\fR returns 1, and "\0").
.TP
\fBstring wordend \fIstring charIndex\fR
.
Returns the index of the character just after the last one in the word
containing character \fIcharIndex\fR of \fIstring\fR.  \fIcharIndex\fR
may be specified using the forms in \fBSTRING INDICES\fR.  A word is
considered to be any contiguous range of alphanumeric (Unicode letters

#define NUM_PUNCT_CHAR (sizeof(punctCharTable)/sizeof(chr))

/*
 * Unicode: white space characters.
 */

static const crange spaceRangeTable[] = {
    {0x9, 0xd}, {0x2000, 0x200a}
    {0x9, 0xd}, {0x2000, 0x200b}
};

#define NUM_SPACE_RANGE (sizeof(spaceRangeTable)/sizeof(crange))

static const chr spaceCharTable[] = {
    0x20, 0xa0, 0x1680, 0x180e, 0x2028, 0x2029, 0x202f, 0x205f, 0x3000
    0x20, 0x85, 0xa0, 0x1680, 0x180e, 0x2028, 0x2029, 0x202f, 0x205f,
    0x2060, 0x3000, 0xfeff
};

#define NUM_SPACE_CHAR (sizeof(spaceCharTable)/sizeof(chr))

/*
 * Unicode: lowercase characters.
 */

static int		TryPostHandler(ClientData data[], Tcl_Interp *interp,
			    int result);
static int		UniCharIsAscii(int character);
static int		UniCharIsHexDigit(int character);

/*
 * Default set of characters to trim in [string trim] and friends. This is a
 * UTF-8 literal string containing space, tab, newline, carriage return,
 * UTF-8 literal string containing all Unicode space characters [TIP #413]
 * ethiopic wordspace (U+1361), ogham space mark (U+1680), and ideographic
 * space (U+3000). [TIP #318]
 */

#define DEFAULT_TRIM_SET " \t\n\r\xe1\x8d\xa1\xe1\x9a\x80\xe3\x80\x80"
#define DEFAULT_TRIM_SET \
	"\x09\x0a\x0b\x0c\x0d " /* ASCII */\
	"\xc0\x80" /*     nul (U+0000) */\
	"\xc2\x85" /*     next line (U+0085) */\
	"\xc2\xa0" /*     non-breaking space (U+00a0) */\
	"\xe1\x9a\x80" /* ogham space mark (U+1680) */ \
	"\xe1\xa0\x8e" /* mongolian vowel separator (U+180e) */\
	"\xe2\x80\x80" /* en quad (U+2000) */\
	"\xe2\x80\x81" /* em quad (U+2001) */\
	"\xe2\x80\x82" /* en space (U+2002) */\
	"\xe2\x80\x83" /* em space (U+2003) */\
	"\xe2\x80\x84" /* three-per-em space (U+2004) */\
	"\xe2\x80\x85" /* four-per-em space (U+2005) */\
	"\xe2\x80\x86" /* six-per-em space (U+2006) */\
	"\xe2\x80\x87" /* figure space (U+2007) */\
	"\xe2\x80\x88" /* punctuation space (U+2008) */\
	"\xe2\x80\x89" /* thin space (U+2009) */\
	"\xe2\x80\x8a" /* hair space (U+200a) */\
	"\xe2\x80\x8b" /* zero width space (U+200b) */\
	"\xe2\x80\xa8" /* line separator (U+2028) */\
	"\xe2\x80\xa9" /* paragraph separator (U+2029) */\
	"\xe2\x80\xaf" /* narrow no-break space (U+202f) */\
	"\xe2\x81\x9f" /* medium mathematical space (U+205f) */\
	"\xe2\x81\xa0" /* word joiner (U+2060) */\
	"\xe3\x80\x80" /* ideographic space (U+3000) */\
	"\xef\xbb\xbf" /* zero width no-break space (U+feff) */

/*
 *----------------------------------------------------------------------
 *
 * Tcl_PwdObjCmd --
 *
 *	This procedure is invoked to process the "pwd" Tcl command. See the

    /*
     * If the character is within the first 127 characters, just use the
     * standard C function, otherwise consult the Unicode table.
     */

    if (((Tcl_UniChar) ch) < ((Tcl_UniChar) 0x80)) {
	return isspace(UCHAR(ch)); /* INTL: ISO space */
    } else if ((Tcl_UniChar) ch == 0x0085 || (Tcl_UniChar) ch == 0x200b
	    || (Tcl_UniChar) ch == 0x2060 || (Tcl_UniChar) ch == 0xfeff) {
	return 1;
    } else {
	return ((SPACE_BITS >> GetCategory(ch)) & 1);
    }
}

/*
 *----------------------------------------------------------------------

test string-18.10 {string trim} {
    string trim ABC DEF
} {ABC}
test string-18.11 {string trim, unicode} {
    string trim "\xe7\xe8 AB\xe7C \xe8\xe7" \xe7\xe8
} " AB\xe7C "
test string-18.12 {string trim, unicode default} {
    string trim ABC\u1361\u1680\u3000
} ABC
    string trim \ufeff\x00\u0085\u00a0\u1680\u180eABC\u1361\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200a\u200b\u2028\u2029\u202f\u205f\u3000
} ABC\u1361

test string-19.1 {string trimleft} {
    list [catch {string trimleft} msg] $msg
} {1 {wrong # args: should be "string trimleft string ?chars?"}}
test string-19.2 {string trimleft} {
    string trimleft "    XYZ      "
} {XYZ      }
test string-19.3 {string trimleft, unicode default} {
    string trimleft \u1361\u1680\u3000ABC
} ABC
    string trimleft \ufeff\u0085\u00a0\x00\u1680\u180e\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200a\u200b\u2028\u2029\u202f\u205f\u3000\u1361ABC
} \u1361ABC

test string-20.1 {string trimright errors} {
    list [catch {string trimright} msg] $msg
} {1 {wrong # args: should be "string trimright string ?chars?"}}
test string-20.2 {string trimright errors} {
    list [catch {string trimg a} msg] $msg
} {1 {unknown or ambiguous subcommand "trimg": must be bytelength, compare, equal, first, index, is, last, length, map, match, range, repeat, replace, reverse, tolower, totitle, toupper, trim, trimleft, trimright, wordend, or wordstart}}
test string-20.3 {string trimright} {
    string trimright "    XYZ      "
} {    XYZ}
test string-20.4 {string trimright} {
    string trimright "   "
} {}
test string-20.5 {string trimright} {
    string trimright ""
} {}
test string-20.6 {string trimright, unicode default} {
    string trimright ABC\u1361\u1680\u3000
} ABC
    string trimright ABC\u1361\u0085\x00\u00a0\u1680\u180e\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007\u2008\u2009\u200a\u200b\u2028\u2029\u202f\u205f\u3000
} ABC\u1361

test string-21.1 {string wordend} {
    list [catch {string wordend a} msg] $msg
} {1 {wrong # args: should be "string wordend string index"}}
test string-21.2 {string wordend} {
    list [catch {string wordend a b c} msg] $msg
} {1 {wrong # args: should be "string wordend string index"}}