diff options
Diffstat (limited to 'doc/Utf.3')
| -rw-r--r-- | doc/Utf.3 | 160 |
1 files changed, 160 insertions, 0 deletions
diff --git a/doc/Utf.3 b/doc/Utf.3 new file mode 100644 index 0000000..f68a6cb --- /dev/null +++ b/doc/Utf.3 @@ -0,0 +1,160 @@ +'\" +'\" 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 1.2 1999/04/16 00:46:34 stanton Exp $ +'\" +.so man.macros +.TH Utf 3 "8.1" Tcl "Tcl Library Procedures" +.BS +.SH NAME +Tcl_UniChar, Tcl_UniCharToUtf, Tcl_UtfToUniChar, 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 <tcl.h>\fR +.sp +typedef ... Tcl_UniChar; +.sp +int +\fBTcl_UniCharToUtf\fR(\fIch, buf\fR) +.sp +int +\fBTcl_UtfToUniChar\fR(\fIsrc, chPtr\fR) +.sp +int +\fBTcl_UtfCharComplete\fR(\fIsrc, len\fR) +.sp +int +\fBTcl_NumUtfChars\fR(\fIsrc, len\fR) +.sp +char * +\fBTcl_UtfFindFirst\fR(\fIsrc, ch\fR) +.sp +char * +\fBTcl_UtfFindLast\fR(\fIsrc, ch\fR) +.sp +char * +\fBTcl_UtfNext\fR(\fIsrc\fR) +.sp +char * +\fBTcl_UtfPrev\fR(\fIsrc, start\fR) +.sp +Tcl_UniChar +\fBTcl_UniCharAtIndex\fR(\fIsrc, index\fR) +.sp +char * +\fBTcl_UtfAtIndex\fR(\fIsrc, index\fR) +.sp +int +\fBTcl_UtfBackslash\fR(\fIsrc, readPtr, dst\fR) +.SH ARGUMENTS +.AS "CONST char" *chPtr out +.AP char *buf out +Buffer in which the UTF-8 representation of the Tcl_UniChar is stored. At most +TCL_UTF_MAX 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 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 "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 TCL_UTF_MAX bytes are stored in the buffer. +.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 TCL_UTF_MAX 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_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 occurance 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 occurance 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. +.PP +Given \fIsrc\fR, a pointer to some location in a UTF-8 string, +\fBTcl_UtfPrev\fR returns a pointer to the previous UTF-8 character in the +string. 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. +.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. +.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 TCL_UTF_MAX 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 |