'\" '\" Copyright (c) 1997 Sun Microsystems, Inc. '\" '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" '\" RCS: @(#) $Id: Utf.3,v 1.19 2004/10/07 15:15:48 dkf Exp $ '\" .so man.macros .TH Utf 3 "8.1" Tcl "Tcl Library Procedures" .BS .SH NAME Tcl_UniChar, Tcl_UniCharCaseMatch, Tcl_UniCharNcasecmp, Tcl_UniCharToUtf, Tcl_UtfToUniChar, Tcl_UniCharToUtfDString, Tcl_UtfToUniCharDString, Tcl_UniCharLen, Tcl_UniCharNcmp, Tcl_UtfCharComplete, Tcl_NumUtfChars, Tcl_UtfFindFirst, Tcl_UtfFindLast, Tcl_UtfNext, Tcl_UtfPrev, Tcl_UniCharAtIndex, Tcl_UtfAtIndex, Tcl_UtfBackslash \- routines for manipulating UTF-8 strings .SH SYNOPSIS .nf \fB#include \fR .sp typedef ... Tcl_UniChar; .sp int \fBTcl_UniCharToUtf\fR(\fIch, buf\fR) .sp int \fBTcl_UtfToUniChar\fR(\fIsrc, chPtr\fR) .VS 8.4 .sp char * \fBTcl_UniCharToUtfDString\fR(\fIuniStr, numChars, dstPtr\fR) .sp Tcl_UniChar * \fBTcl_UtfToUniCharDString\fR(\fIsrc, len, dstPtr\fR) .VE 8.4 .sp int \fBTcl_UniCharLen\fR(\fIuniStr\fR) .sp int \fBTcl_UniCharNcmp\fR(\fIuniStr, uniStr, num\fR) .VS 8.4 .sp int \fBTcl_UniCharNcasecmp\fR(\fIuniStr, uniStr, num\fR) .sp int \fBTcl_UniCharCaseMatch\fR(\fIuniStr, uniPattern, nocase\fR) .VE 8.4 .sp int \fBTcl_UtfNcmp\fR(\fIsrc, src, num\fR) .sp int \fBTcl_UtfNcasecmp\fR(\fIsrc, src, num\fR) .sp int \fBTcl_UtfCharComplete\fR(\fIsrc, len\fR) .sp int \fBTcl_NumUtfChars\fR(\fIsrc, len\fR) .VS 8.4 .sp const char * \fBTcl_UtfFindFirst\fR(\fIsrc, ch\fR) .sp const char * \fBTcl_UtfFindLast\fR(\fIsrc, ch\fR) .sp const char * \fBTcl_UtfNext\fR(\fIsrc\fR) .sp const char * \fBTcl_UtfPrev\fR(\fIsrc, start\fR) .VE 8.4 .sp Tcl_UniChar \fBTcl_UniCharAtIndex\fR(\fIsrc, index\fR) .VS 8.4 .sp const char * \fBTcl_UtfAtIndex\fR(\fIsrc, index\fR) .VE 8.4 .sp int \fBTcl_UtfBackslash\fR(\fIsrc, readPtr, dst\fR) .SH ARGUMENTS .AS "const Tcl_UniChar" *uniPattern in/out .AP char *buf out Buffer in which the UTF-8 representation of the Tcl_UniChar is stored. At most \fBTCL_UTF_MAX\fR bytes are stored in the buffer. .AP int ch in The Tcl_UniChar to be converted or examined. .AP Tcl_UniChar *chPtr out Filled with the Tcl_UniChar represented by the head of the UTF-8 string. .AP "const char" *src in Pointer to a UTF-8 string. .AP "const Tcl_UniChar" *uniStr in A null-terminated Unicode string. .AP "const Tcl_UniChar" *uniPattern in A null-terminated Unicode string. .AP int len in The length of the UTF-8 string in bytes (not UTF-8 characters). If negative, all bytes up to the first null byte are used. .AP int numChars in The length of the Unicode string in characters. Must be greater than or equal to 0. .AP "Tcl_DString" *dstPtr in/out A pointer to a previously initialized \fBTcl_DString\fR. .AP "unsigned long" num in The number of characters to compare. .AP "const char" *start in Pointer to the beginning of a UTF-8 string. .AP int index in The index of a character (not byte) in the UTF-8 string. .AP int *readPtr out If non-NULL, filled with the number of bytes in the backslash sequence, including the backslash character. .AP char *dst out Buffer in which the bytes represented by the backslash sequence are stored. At most \fBTCL_UTF_MAX\fR bytes are stored in the buffer. .VS 8.4 .AP int nocase in Specifies whether the match should be done case-sensitive (0) or case-insensitive (1). .VE 8.4 .BE .SH DESCRIPTION .PP These routines convert between UTF-8 strings and Tcl_UniChars. A Tcl_UniChar is a Unicode character represented as an unsigned, fixed-size quantity. A UTF-8 character is a Unicode character represented as a varying-length sequence of up to \fBTCL_UTF_MAX\fR bytes. A multibyte UTF-8 sequence consists of a lead byte followed by some number of trail bytes. .PP \fBTCL_UTF_MAX\fR is the maximum number of bytes that it takes to represent one Unicode character in the UTF-8 representation. .PP \fBTcl_UniCharToUtf\fR stores the Tcl_UniChar \fIch\fR as a UTF-8 string in starting at \fIbuf\fR. The return value is the number of bytes stored in \fIbuf\fR. .PP \fBTcl_UtfToUniChar\fR reads one UTF-8 character starting at \fIsrc\fR and stores it as a Tcl_UniChar in \fI*chPtr\fR. The return value is the number of bytes read from \fIsrc\fR. The caller must ensure that the source buffer is long enough such that this routine does not run off the end and dereference non-existent or random memory; if the source buffer is known to be null-terminated, this will not happen. If the input is not in proper UTF-8 format, \fBTcl_UtfToUniChar\fR will store the first byte of \fIsrc\fR in \fI*chPtr\fR as a Tcl_UniChar between 0x0000 and 0x00ff and return 1. .PP \fBTcl_UniCharToUtfDString\fR converts the given Unicode string to UTF-8, storing the result in a previously initialized \fBTcl_DString\fR. You must specify the length of the given Unicode string. The return value is a pointer to the UTF-8 representation of the Unicode string. Storage for the return value is appended to the end of the \fBTcl_DString\fR. .PP \fBTcl_UtfToUniCharDString\fR converts the given UTF-8 string to Unicode, storing the result in the previously initialized \fBTcl_DString\fR. You may either specify the length of the given UTF-8 string or "-1", in which case \fBTcl_UtfToUniCharDString\fR uses \fBstrlen\fR to calculate the length. The return value is a pointer to the Unicode representation of the UTF-8 string. Storage for the return value is appended to the end of the \fBTcl_DString\fR. The Unicode string is terminated with a Unicode null character. .PP \fBTcl_UniCharLen\fR corresponds to \fBstrlen\fR for Unicode characters. It accepts a null-terminated Unicode string and returns the number of Unicode characters (not bytes) in that string. .PP \fBTcl_UniCharNcmp\fR and \fBTcl_UniCharNcasecmp\fR correspond to \fBstrncmp\fR and \fBstrncasecmp\fR, respectively, for Unicode characters. They accept two null-terminated Unicode strings and the number of characters to compare. Both strings are assumed to be at least \fIlen\fR characters long. \fBTcl_UniCharNcmp\fR compares the two strings character-by-character according to the Unicode character ordering. It returns an integer greater than, equal to, or less than 0 if the first string is greater than, equal to, or less than the second string respectively. \fBTcl_UniCharNcasecmp\fR is the Unicode case insensitive version. .PP .VS 8.4 \fBTcl_UniCharCaseMatch\fR is the Unicode equivalent to \fBTcl_StringCaseMatch\fR. It accepts a null-terminated Unicode string, a Unicode pattern, and a boolean value specifying whether the match should be case sensitive and returns whether the string matches the pattern. .VE 8.4 .PP \fBTcl_UtfNcmp\fR corresponds to \fBstrncmp\fR for UTF-8 strings. It accepts two null-terminated UTF-8 strings and the number of characters to compare. (Both strings are assumed to be at least \fIlen\fR characters long.) \fBTcl_UtfNcmp\fR compares the two strings character-by-character according to the Unicode character ordering. It returns an integer greater than, equal to, or less than 0 if the first string is greater than, equal to, or less than the second string respectively. .PP \fBTcl_UtfNcasecmp\fR corresponds to \fBstrncasecmp\fR for UTF-8 strings. It is similar to \fBTcl_UtfNcmp\fR except comparisons ignore differences in case when comparing upper, lower or title case characters. .PP \fBTcl_UtfCharComplete\fR returns 1 if the source UTF-8 string \fIsrc\fR of length \fIlen\fR bytes is long enough to be decoded by \fBTcl_UtfToUniChar\fR, or 0 otherwise. This function does not guarantee that the UTF-8 string is properly formed. This routine is used by procedures that are operating on a byte at a time and need to know if a full Tcl_UniChar has been seen. .PP \fBTcl_NumUtfChars\fR corresponds to \fBstrlen\fR for UTF-8 strings. It returns the number of Tcl_UniChars that are represented by the UTF-8 string \fIsrc\fR. The length of the source string is \fIlen\fR bytes. If the length is negative, all bytes up to the first null byte are used. .PP \fBTcl_UtfFindFirst\fR corresponds to \fBstrchr\fR for UTF-8 strings. It returns a pointer to the first occurrence of the Tcl_UniChar \fIch\fR in the null-terminated UTF-8 string \fIsrc\fR. The null terminator is considered part of the UTF-8 string. .PP \fBTcl_UtfFindLast\fR corresponds to \fBstrrchr\fR for UTF-8 strings. It returns a pointer to the last occurrence of the Tcl_UniChar \fIch\fR in the null-terminated UTF-8 string \fIsrc\fR. The null terminator is considered part of the UTF-8 string. .PP Given \fIsrc\fR, a pointer to some location in a UTF-8 string, \fBTcl_UtfNext\fR returns a pointer to the next UTF-8 character in the string. The caller must not ask for the next character after the last character in the string if the string is not terminated by a null character. .PP Given \fIsrc\fR, a pointer to some location in a UTF-8 string (or to a null byte immediately following such a string), \fBTcl_UtfPrev\fR returns a pointer to the closest preceding byte that starts a UTF-8 character. This function will not back up to a position before \fIstart\fR, the start of the UTF-8 string. If \fIsrc\fR was already at \fIstart\fR, the return value will be \fIstart\fR. .PP \fBTcl_UniCharAtIndex\fR corresponds to a C string array dereference or the Pascal Ord() function. It returns the Tcl_UniChar represented at the specified character (not byte) \fIindex\fR in the UTF-8 string \fIsrc\fR. The source string must contain at least \fIindex\fR characters. Behavior is undefined if a negative \fIindex\fR is given. .PP \fBTcl_UtfAtIndex\fR returns a pointer to the specified character (not byte) \fIindex\fR in the UTF-8 string \fIsrc\fR. The source string must contain at least \fIindex\fR characters. This is equivalent to calling \fBTcl_UtfNext\fR \fIindex\fR times. If a negative \fIindex\fR is given, the return pointer points to the first character in the source string. .PP \fBTcl_UtfBackslash\fR is a utility procedure used by several of the Tcl commands. It parses a backslash sequence and stores the properly formed UTF-8 character represented by the backslash sequence in the output buffer \fIdst\fR. At most \fBTCL_UTF_MAX\fR bytes are stored in the buffer. \fBTcl_UtfBackslash\fR modifies \fI*readPtr\fR to contain the number of bytes in the backslash sequence, including the backslash character. The return value is the number of bytes stored in the output buffer. .PP See the \fBTcl\fR manual entry for information on the valid backslash sequences. All of the sequences described in the Tcl manual entry are supported by \fBTcl_UtfBackslash\fR. .SH KEYWORDS utf, unicode, backslash