diff options
Diffstat (limited to 'doc/Utf.3')
-rw-r--r-- | doc/Utf.3 | 64 |
1 files changed, 30 insertions, 34 deletions
@@ -4,10 +4,8 @@ '\" 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 1.20 2004/10/07 16:05:15 dkf Exp $ -'\" -.so man.macros .TH Utf 3 "8.1" Tcl "Tcl Library Procedures" +.so man.macros .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 @@ -15,48 +13,43 @@ Tcl_UniChar, Tcl_UniCharCaseMatch, Tcl_UniCharNcasecmp, Tcl_UniCharToUtf, Tcl_Ut .nf \fB#include <tcl.h>\fR .sp -typedef ... Tcl_UniChar; +typedef ... \fBTcl_UniChar\fR; .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) +\fBTcl_UniCharToUtfDString\fR(\fIuniStr, uniLength, dsPtr\fR) .sp Tcl_UniChar * -\fBTcl_UtfToUniCharDString\fR(\fIsrc, len, dstPtr\fR) -.VE 8.4 +\fBTcl_UtfToUniCharDString\fR(\fIsrc, length, dsPtr\fR) .sp int \fBTcl_UniCharLen\fR(\fIuniStr\fR) .sp int -\fBTcl_UniCharNcmp\fR(\fIuniStr, uniStr, num\fR) -.VS 8.4 +\fBTcl_UniCharNcmp\fR(\fIucs, uct, numChars\fR) .sp int -\fBTcl_UniCharNcasecmp\fR(\fIuniStr, uniStr, num\fR) +\fBTcl_UniCharNcasecmp\fR(\fIucs, uct, numChars\fR) .sp int \fBTcl_UniCharCaseMatch\fR(\fIuniStr, uniPattern, nocase\fR) -.VE 8.4 .sp int -\fBTcl_UtfNcmp\fR(\fIsrc, src, num\fR) +\fBTcl_UtfNcmp\fR(\fIcs, ct, numChars\fR) .sp int -\fBTcl_UtfNcasecmp\fR(\fIsrc, src, num\fR) +\fBTcl_UtfNcasecmp\fR(\fIcs, ct, numChars\fR) .sp int -\fBTcl_UtfCharComplete\fR(\fIsrc, len\fR) +\fBTcl_UtfCharComplete\fR(\fIsrc, length\fR) .sp int -\fBTcl_NumUtfChars\fR(\fIsrc, len\fR) -.VS 8.4 +\fBTcl_NumUtfChars\fR(\fIsrc, length\fR) .sp const char * \fBTcl_UtfFindFirst\fR(\fIsrc, ch\fR) @@ -69,15 +62,12 @@ const char * .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) @@ -92,19 +82,27 @@ The Tcl_UniChar to be converted or examined. 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 char" *cs in +Pointer to a UTF-8 string. +.AP "const char" *ct in +Pointer to a UTF-8 string. .AP "const Tcl_UniChar" *uniStr in A null-terminated Unicode string. +.AP "const Tcl_UniChar" *ucs in +A null-terminated Unicode string. +.AP "const Tcl_UniChar" *uct in +A null-terminated Unicode string. .AP "const Tcl_UniChar" *uniPattern in A null-terminated Unicode string. -.AP int len in +.AP int length 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 +.AP int uniLength in The length of the Unicode string in characters. Must be greater than or equal to 0. -.AP "Tcl_DString" *dstPtr in/out +.AP "Tcl_DString" *dsPtr in/out A pointer to a previously initialized \fBTcl_DString\fR. -.AP "unsigned long" num in +.AP "unsigned long" numChars in The number of characters to compare. .AP "const char" *start in Pointer to the beginning of a UTF-8 string. @@ -117,10 +115,8 @@ including the backslash character. Buffer in which the bytes represented by the backslash sequence are stored. At most \fBTCL_UTF_MAX\fR bytes are stored in the buffer. .AP int nocase in -.VS 8.4 Specifies whether the match should be done case-sensitive (0) or case-insensitive (1). -.VE 8.4 .BE .SH DESCRIPTION @@ -150,14 +146,16 @@ byte of \fIsrc\fR in \fI*chPtr\fR as a Tcl_UniChar between 0x0000 and .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. +You must specify \fIuniLength\fR, 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 the argument \fIlength\fR, you may either specify the length of +the given UTF-8 string in bytes or +.QW \-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 @@ -171,23 +169,21 @@ the number of Unicode characters (not bytes) in that string. \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 +to compare. Both strings are assumed to be at least \fInumChars\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 +to compare. (Both strings are assumed to be at least \fInumChars\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 @@ -200,7 +196,7 @@ 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 +of \fIlength\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 @@ -208,7 +204,7 @@ 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 +\fIsrc\fR. The length of the source string is \fIlength\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 |