ified in the class command, dbName gives '\" the option's name in the option database, and dbClass gives '\" the option's class in the option database. '\" '\" .UL arg1 arg2 '\" Print arg1 underlined, then print arg2 normally. '\" '\" RCS: @(#) $Id: man.macros,v 1.4 2000/08/25 06:18:32 ericm Exp $ '\" '\" # Set up traps and other miscellaneous stuff for Tcl/Tk man pages. .if t .wh -1.3i ^B .nr ^l \n(.l .ad b '\" # Start an argument description .de AP .ie !"\\$4"" .TP \\$4 .el \{\ . ie !"\\$2"" .TP \\n()Cu . el .TP 15 .\} .ta \\n()Au \\n()Bu .ie !"\\$3"" \{\ \&\\$1 \\fI\\$2\\fP (\\$3) .\".b .\} .el \{\ .br .ie !"\\$2"" \{\ \&\\$1 \\fI\\$2\\fP .\} .el \{\ \&\\fI\\$1\\fP .\} .\} .. '\" # define tabbing values for .AP .de AS .nr )A 10n .if !"\\$1"" .nr )A \\w'\\$1'u+3n .nr )B \\n()Au+15n .\" .if !"\\$2"" .nr )B \\w'\\$2'u+\\n()Au+3n .nr )C \\n()Bu+\\w'(in/out)'u+2n .. .AS Tcl_Interp Tcl_CreateInterp in/out '\" # BS - start boxed text '\" # ^y = starting y location '\" # ^b = 1 .de BS .br .mk ^y .nr ^b 1u .if n .nf .if n .ti 0 .if n \l'\\n(.lu\(ul' .if n .fi .. '\" # BE - end boxed text (draw box now) .de BE .nf .ti 0 .mk ^t .ie n \l'\\n(^lu\(ul' .el \{\ .\" Draw four-sided box normally, but don't draw top of .\" box if the box started on an earlier page. .ie !\\n(^b-1 \{\ \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul' .\} .el \}\ \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul' .\} .\} .fi .br .nr ^b 0 .. '\" # VS - start vertical sidebar '\" # ^Y = starting y location '\" # ^v = 1 (for troff; for nroff this doesn't matter) .de VS .if !"\\$2"" .br .mk ^Y .ie n 'mc \s12\(br\s0 .el .nr ^v 1u .. '\" # VE - end of vertical sidebar .de VE .ie n 'mc .el \{\ .ev 2 .nf .ti 0 .mk ^t \h'|\\n(^lu+3n'\L'|\\n(^Yu-1v\(bv'\v'\\n(^tu+1v-\\n(^Yu'\h'-|\\n(^lu+3n' .sp -1 .fi .ev .\} .nr ^v 0 .. '\" # Special macro to handle page bottom: finish off current '\" # box/sidebar if in box/sidebar mode, then invoked standard '\" # page bottom macro. .de ^B .ev 2 'ti 0 'nf .mk ^t .if \\n(^b \{\ .\" Draw three-sided box if this is the box's first page, .\" draw two sides but no top otherwise. .ie !\\n(^b-1 \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c .el \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c .\} .if \\n(^v \{\ .nr ^x \\n(^tu+1v-\\n(^Yu \kx\h'-\\nxu'\h'|\\n(^lu+3n'\ky\L'-\\n(^xu'\v'\\n(^xu'\h'|0u'\c .\} .bp 'fi .ev .if \\n(^b \{\ .mk ^y .nr ^b 2 .\} .if \\n(^v \{\ .mk ^Y .\} .. '\" # DS - begin display .de DS .RS .nf .sp .. '\" # DE - end display .de DE .fi .RE .sp .. '\" # SO - start of list of standard options .de SO .SH "STANDARD OPTIONS" .LP .nf .ta 5.5c 11c .ft B .. '\" # SE - end of list of standard options .de SE .fi .ft R .LP See the \\fBoptions\\fR manual entry for details on the standard options. .. '\" # OP - start of full description for a single option .de OP .LP .nf .ta 4c Command-Line Name: \\fB\\$1\\fR Database Name: \\fB\\$2\\fR Database Class: \\fB\\$3\\fR .fi .IP .. '\" # CS - begin code excerpt .de CS .RS .nf .ta .25i .5i .75i 1i .. '\" # CE - end code excerpt .de CE .fi .RE .. .de UL \\$1\l'|0\(ul'\\$2 .. .TH Tcl_OpenFileChannel 3 8.3 Tcl "Tcl Library Procedures" .BS '\" Note: do not modify the .SH NAME line immediately below! .SH NAME Tcl_OpenFileChannel, Tcl_OpenCommandChannel, Tcl_MakeFileChannel, Tcl_GetChannel, Tcl_GetChannelNames, Tcl_GetChannelNamesEx, Tcl_RegisterChannel, Tcl_UnregisterChannel, Tcl_DetachChannel, Tcl_IsStandardChannel, Tcl_Close, Tcl_ReadChars, Tcl_Read, Tcl_GetsObj, Tcl_Gets, Tcl_WriteObj, Tcl_WriteChars, Tcl_Write, Tcl_Flush, Tcl_Seek, Tcl_Tell, Tcl_GetChannelOption, Tcl_SetChannelOption, Tcl_Eof, Tcl_InputBlocked, Tcl_InputBuffered, Tcl_OutputBuffered, Tcl_Ungets, Tcl_ReadRaw, Tcl_WriteRaw \- buffered I/O facilities using channels .SH SYNOPSIS .nf \fB#include \fR .sp Tcl_Channel \fBTcl_OpenFileChannel\fR(\fIinterp, fileName, mode, permissions\fR) .sp Tcl_Channel \fBTcl_OpenCommandChannel\fR(\fIinterp, argc, argv, flags\fR) .sp Tcl_Channel \fBTcl_MakeFileChannel\fR(\fIhandle, readOrWrite\fR) .sp Tcl_Channel \fBTcl_GetChannel\fR(\fIinterp, channelName, modePtr\fR) .VS 8.3 .sp int \fBTcl_GetChannelNames\fR(\fIinterp\fR) .sp int \fBTcl_GetChannelNamesEx\fR(\fIinterp, pattern\fR) .VE .sp void \fBTcl_RegisterChannel\fR(\fIinterp, channel\fR) .sp int \fBTcl_UnregisterChannel\fR(\fIinterp, channel\fR) .sp int \fBTcl_DetachChannel\fR(\fIinterp, channel\fR) .sp int \fBTcl_IsStandardChannel\fR(\fIchannel\fR) .sp int \fBTcl_Close\fR(\fIinterp, channel\fR) .sp .VS 8.1 int \fBTcl_ReadChars\fR(\fIchannel, readObjPtr, charsToRead, appendFlag\fR) .sp int \fBTcl_Read\fR(\fIchannel, readBuf, bytesToRead\fR) .sp int \fBTcl_GetsObj\fR(\fIchannel, lineObjPtr\fR) .sp int \fBTcl_Gets\fR(\fIchannel, lineRead\fR) .sp int \fBTcl_Ungets\fR(\fIchannel, input, inputLen, addAtEnd\fR) .sp int \fBTcl_WriteObj\fR(\fIchannel, writeObjPtr\fR) .sp int \fBTcl_WriteChars\fR(\fIchannel, charBuf, bytesToWrite\fR) .sp int \fBTcl_Write\fR(\fIchannel, byteBuf, bytesToWrite\fR) .VE .VS 8.3.2 .sp int \fBTcl_ReadRaw\fR(\fIchannel, readBuf, bytesToRead\fR) .sp int \fBTcl_WriteRaw\fR(\fIchannel, byteBuf, bytesToWrite\fR) .VE .sp int \fBTcl_Eof\fR(\fIchannel\fR) .sp int \fBTcl_Flush\fR(\fIchannel\fR) .sp int \fBTcl_InputBlocked\fR(\fIchannel\fR) .sp int \fBTcl_InputBuffered\fR(\fIchannel\fR) .VS 8.4 .sp int \fBTcl_OutputBuffered\fR(\fIchannel\fR) .VE .sp .VS 8.4 Tcl_WideInt \fBTcl_Seek\fR(\fIchannel, offset, seekMode\fR) .sp Tcl_WideInt \fBTcl_Tell\fR(\fIchannel\fR) .VE 8.4 .sp int \fBTcl_GetChannelOption\fR(\fIinterp, channel, optionName, optionValue\fR) .sp int \fBTcl_SetChannelOption\fR(\fIinterp, channel, optionName, newValue\fR) .sp .SH ARGUMENTS .AS Tcl_ChannelType newClientProcPtr in .AP Tcl_Interp *interp in Used for error reporting and to look up a channel registered in it. .AP "CONST char" *fileName in The name of a local or network file. .AP "CONST char" *mode in Specifies how the file is to be accessed. May have any of the values allowed for the \fImode\fR argument to the Tcl \fBopen\fR command. .AP int permissions in POSIX-style permission flags such as 0644. If a new file is created, these permissions will be set on the created file. .AP int argc in The number of elements in \fIargv\fR. .AP "CONST char" **argv in Arguments for constructing a command pipeline. These values have the same meaning as the non-switch arguments to the Tcl \fBexec\fR command. .AP int flags in Specifies the disposition of the stdio handles in pipeline: OR-ed combination of \fBTCL_STDIN\fR, \fBTCL_STDOUT\fR, \fBTCL_STDERR\fR, and \fBTCL_ENFORCE_MODE\fR. If \fBTCL_STDIN\fR is set, stdin for the first child in the pipe is the pipe channel, otherwise it is the same as the standard input of the invoking process; likewise for \fBTCL_STDOUT\fR and \fBTCL_STDERR\fR. If \fBTCL_ENFORCE_MODE\fR is not set, then the pipe can redirect stdio handles to override the stdio handles for which \fBTCL_STDIN\fR, \fBTCL_STDOUT\fR and \fBTCL_STDERR\fR have been set. If it is set, then such redirections cause an error. .AP ClientData handle in Operating system specific handle for I/O to a file. For Unix this is a file descriptor, for Windows it is a HANDLE. .AP int readOrWrite in OR-ed combination of \fBTCL_READABLE\fR and \fBTCL_WRITABLE\fR to indicate what operations are valid on \fIhandle\fR. .AP "CONST char" *channelName in The name of the channel. .AP int *modePtr out Points at an integer variable that will receive an OR-ed combination of \fBTCL_READABLE\fR and \fBTCL_WRITABLE\fR denoting whether the channel is open for reading and writing. .VS 8.3 .AP "CONST char" *pattern in The pattern to match on, passed to Tcl_StringMatch, or NULL. .VE .AP Tcl_Channel channel in A Tcl channel for input or output. Must have been the return value from a procedure such as \fBTcl_OpenFileChannel\fR. .VS 8.1 br .AP Tcl_Obj *readObjPtr in/out A pointer to a Tcl Object in which to store the characters read from the channel. .AP int charsToRead in The number of characters to read from the channel. If the channel's encoding is \fBbinary\fR, this is equivalent to the number of bytes to read from the channel. .AP int appendFlag in If non-zero, data read from the channel will be appended to the object. Otherwise, the data will replace the existing contents of the object. .AP char *readBuf out A buffer in which to store the bytes read from the channel. .AP int bytesToRead in The number of bytes to read from the channel. The buffer \fIreadBuf\fR must be large enough to hold this many bytes. .AP Tcl_Obj *lineObjPtr in/out A pointer to a Tcl object in which to store the line read from the channel. The line read will be appended to the current value of the object. .AP Tcl_DString *lineRead in/out A pointer to a Tcl dynamic string in which to store the line read from the channel. Must have been initialized by the caller. The line read will be appended to any data already in the dynamic string. .VS 8.3 .AP "CONST char" *input in The input to add to a channel buffer. .AP int inputLen in Length of the input .AP int addAtEnd in Flag indicating whether the input should be added to the end or beginning of the channel buffer. .VE .AP Tcl_Obj *writeObjPtr in A pointer to a Tcl Object whose contents will be output to the channel. .AP "CONST char" *charBuf in A buffer containing the characters to output to the channel. .AP "CONST char" *byteBuf in A buffer containing the bytes to output to the channel. .AP int bytesToWrite in The number of bytes to consume from \fIcharBuf\fR or \fIbyteBuf\fR and output to the channel. .VE .AP Tcl_WideInt offset in How far to move the access point in the channel at which the next input or output operation will be applied, measured in bytes from the position given by \fIseekMode\fR. May be either positive or negative. .AP int seekMode in Relative to which point to seek; used with \fIoffset\fR to calculate the new access point for the channel. Legal values are \fBSEEK_SET\fR, \fBSEEK_CUR\fR, and \fBSEEK_END\fR. .AP "CONST char" *optionName in The name of an option applicable to this channel, such as \fB\-blocking\fR. May have any of the values accepted by tKcLcMcNcOcPcQcRcScTcUcVcWcXcYcZc[c\c]c^c_c`cacbche \fBfconfigure\fR command. .AP Tcl_DString *optionValue in Where to store the value of an option or a list of all options and their values. Must have been initialized by the caller. .AP "CONST char" *newValue in New value for the option given by \fIoptionName\fR. .BE .SH DESCRIPTION .PP The Tcl channel mechanism provides a device-independent and platform-independent mechanism for performing buffered input and output operations on a variety of file, socket, and device types. The channel mechanism is extensible to new channel types, by providing a low level channel driver for the new type; the channel driver interface is described in the manual entry for \fBTcl_CreateChannel\fR. The channel mechanism provides a buffering scheme modeled after Unix's standard I/O, and it also allows for nonblocking I/O on channels. .PP The procedures described in this manual entry comprise the C APIs of the generic layer of the channel architecture. For a description of the channel driver architecture and how to implement channel drivers for new types of channels, see the manual entry for \fBTcl_CreateChannel\fR. .SH TCL_OPENFILECHANNEL .PP \fBTcl_OpenFileChannel\fR opens a file specified by \fIfileName\fR and returns a channel handle that can be used to perform input and output on the file. This API is modeled after the \fBfopen\fR procedure of the Unix standard I/O library. The syntax and meaning of all arguments is similar to those given in the Tcl \fBopen\fR command when opening a file. If an error occurs while opening the channel, \fBTcl_OpenFileChannel\fR returns NULL and records a POSIX error code that can be retrieved with \fBTcl_GetErrno\fR. In addition, if \fIinterp\fR is non-NULL, \fBTcl_OpenFileChannel\fR leaves an error message in \fIinterp\fR's result after any error. As of Tcl 8.4, the object-based API \fBTcl_FSOpenFileChannel\fR should be used in preference to \fBTcl_OpenFileChannel\fR wherever possible. .PP .PP The newly created channel is not registered in the supplied interpreter; to register it, use \fBTcl_RegisterChannel\fR, described below. If one of the standard channels, \fBstdin, stdout\fR or \fBstderr\fR was previously closed, the act of creating the new channel also assigns it as a replacement for the standard channel. .SH TCL_OPENCOMMANDCHANNEL .PP \fBTcl_OpenCommandChannel\fR provides a C-level interface to the functions of the \fBexec\fR and \fBopen\fR commands. It creates a sequence of subprocesses specified by the \fIargv\fR and \fIargc\fR arguments and returns a channel that can be used to communicate with these subprocesses. The \fIflags\fR argument indicates what sort of communication will exist with the command pipeline. .PP If the \fBTCL_STDIN\fR flag is set then the standard input for the first subprocess will be tied to the channel: writing to the channel will provide input to the subprocess. If \fBTCL_STDIN\fR is not set, then standard input for the first subprocess will be the same as this application's standard input. If \fBTCL_STDOUT\fR is set then standard output from the last subprocess can be read from the channel; otherwise it goes to this application's standard output. If \fBTCL_STDERR\fR is set, standard error output for all subprocesses is returned to the channel and results in an error when the channel is closed; otherwise it goes to this application's standard error. If \fBTCL_ENFORCE_MODE\fR is not set, then \fIargc\fR and \fIargv\fR can redirect the stdio handles to override \fBTCL_STDIN\fR, \fBTCL_STDOUT\fR, and \fBTCL_STDERR\fR; if it is set, then it is an error for argc and argv to override stdio channels for which \fBTCL_STDIN\fR, \fBTCL_STDOUT\fR, and \fBTCL_STDERR\fR have been set. .PP If an error occurs while opening the channel, \fBTcl_OpenCommandChannel\fR returns NULL and records a POSIX error code that can be retrieved with \fBTcl_GetErrno\fR. In addition, \fBTcl_OpenCommandChannel\fR leaves an error message in the interpreter's result if \fIinterp\fR is not NULL. .PP The newly created channel is not registered in the supplied interpreter; to register it, use \fBTcl_RegisterChannel\fR, described below. If one of the standard channels, \fBstdin, stdout\fR or \fBstderr\fR was previously closed, the act of creating the new channel also assigns it as a replacement for the standard channel. .SH TCL_MAKEFILECHANNEL .PP \fBTcl_MakeFileChannel\fR makes a \fBTcl_Channel\fR from an existing, platform-specific, file handle. The newly created channel is not registered in the supplied interpreter; to register it, use \fBTcl_RegisterChannel\fR, described below. If one of the standard channels, \fBstdin, stdout\fR or \fBstderr\fR was previously closed, the act of creating the new channel also assigns it as a replacement for the standard channel. .SH TCL_GETCHANNEL .PP \fBTcl_GetChannel\fR returns a channel given the \fIchannelName\fR used to create it with \fBTcl_CreateChannel\fR and a pointer to a Tcl interpreter in \fIinterp\fR. If a channel by that name is not registered in that interpreter, the procedure returns NULL. If the \fImodePtr\fR argument is not NULL, it points at an integer variable that will receive an OR-ed combination of \fBTCL_READABLE\fR and \fBTCL_WRITABLE\fR describing whether the channel is open for reading and writing. .PP \fBTcl_GetChannelNames\fR and \fBTcl_GetChannelNamesEx\fR write the names of the registered channels to the interpreter's result as a list object. \fBTcl_GetChannelNamesEx\fR will filter these names according to the \fIpattern\fR. If \fIpattern\fR is NULL, then it will not do any filtering. The return value is \fBTCL_OK\fR if no errors occurred writing to the result, otherwise it is \fBTCL_ERROR\fR, and the error message is left in the interpreter's result. .SH TCL_REGISTERCHANNEL .PP \fBTcl_RegisterChannel\fR adds a channel to the set of channels accessible in \fIinterp\fR. After this call, Tcl programs executing in that interpreter can refer to the channel in input or output operations using the name given in the call to \fBTcl_CreateChannel\fR. After this call, the channel becomes the property of the interpreter, and the caller should not call \fBTcl_Close\fR for the channel; the channel will be closed automatically when it is unregistered from the interpreter. .PP Code executing outside of any Tcl interpreter can call \fBTcl_RegisterChannel\fR with \fIinterp\fR as NULL, to indicate that it wishes to hold a reference to this channel. Subsequently, the channel can be registered in a Tcl interpreter and it will only be closed when the matching number of calls to \fBTcl_UnregisterChannel\fR have been made. This allows code executing outside of any interpreter to safely hold a reference to a channel that is also registered in a Tcl interpreter. .PP This procedure interacts with the code managing the standard channels. If no standard channels were initialized before the first call to \fBTcl_RegisterChannel\fR they will get initialized by that call. See \fBTcl_StandardChannels\fR for a general treatise about standard channels and the behaviour of the Tcl library with regard to them. .SH TCL_UNREGISTERCHANNEL .PP \fBTcl_UnregisterChannel\fR removes a channel from the set of channels accessible in \fIinterp\fR. After this call, Tcl programs will no longer be able to use the channel's name to refer to the channel in that interpreter. If this operation removed the last registration of the channel in any interpreter, the channel is also closed and destroyed. .PP Code not associated with a Tcl interpreter can call \fBTcl_UnregisterChannel\fR with \fIinterp\fR as NULL, to indicate to Tcl that it no longer holds a reference to that channel. If this is the last reference to the channel, it will now be closed. \fBTcl_UnregisterChannel\fR is very similar to \fBTcl_DetachChannel\fR except that it will also close the channel if no further references to it exist. .SH TCL_DETACHCHANNEL .PP \fBTcl_DetachChannel\fR removes a channel from the set of channels accessible in \fIinterp\fR. After this call, Tcl programs will no longer be able to use the channel's name to refer to the channel in that interpreter. Beyond that, this command has no further effect. It cannot be used on the standard channels (stdout, stderr, stdin), and will return TCL_ERROR if passed one of those channels. .PP Code not associated with a Tcl interpreter can call \fBTcl_DetachChannel\fR with \fIinterp\fR as NULL, to indicate to Tcl that it no longer holds a reference to that channel. If this is the last reference to the channel, unlike \fBTcl_UnregisterChannel\fR, it will not be closed. .SH TCL_ISSTANDARDCHANNEL .PP \fBTcl_IsStandardChannel\fR tests whether a channel is one of the three standard channels, stdin, stdout or stderr. If so, it returns 1, otherwise 0. .PP No attempt is made to check whether the given channel or the standard channels are initialized or otherwise valid. .SH TCL_CLOSE .PP \fBTcl_Close\fR destroys the channel \fIchannel\fR, which must denote a currently open channel. The channel should not be registered in any interpreter when \fBTcl_Close\fR is called. Buffered output is flushed to the channel's output device prior to destroying the channel, and any buffered input is discarded. If this is a blocking channel, the call does not return until all buffered data is successfully sent to the channel's output device. If this is a nonblocking channel and there is buffered output that cannot be written without blocking, the call returns immediately; output is flushed in the background and the channel will be closed once all of the buffered data has been output. In this case errors during flushing are not reported. .PP If the channel was closed successfully, \fBTcl_Close\fR returns \fBTCL_OK\fR. If an error occurs, \fBTcl_Close\fR returns \fBTCL_ERROR\fR and records a POSIX error code that can be retrieved with \fBTcl_GetErrno\fR. If the channel is being closed synchronously and an error occurs during closing of the channel and \fIinterp\fR is not NULL, an error message is left in the interpreter's result. .PP Note: it is not safe to call \fBTcl_Close\fR on a channel that has been registered using \fBTcl_RegisterChannel\fR; see the documentation for \fBTcl_RegisterChannel\fR, above, for details. If the channel has ever been given as the \fBchan\fR argument in a call to \fBTcl_RegisterChannel\fR, you should instead use \fBTcl_UnregisterChannel\fR, which will internally call \fBTcl_Close\fR when all calls to \fBTcl_RegisterChannel\fR have been matched by corresponding calls to \fBTcl_UnregisterChannel\fR. .VS 8.1 br .SH "TCL_READCHARS AND TCL_READ" .PP \fBTcl_ReadChars\fR consumes bytes from \fIchannel\fR, converting the bytes to UTF-8 based on the channel's encoding and storing the produced data in \fIreadObjPtr\fR's string representation. The return value of \fBTcl_ReadChars\fR is the number of characters, up to \fIcharsToRead\fR, that were stored in \fIreadObjPtr\fR. If an error occurs while reading, the return value is \-1 and \fBTcl_ReadChars\fR records a POSIX error code that can be retrieved with \fBTcl_GetErrno\fR. .PP Setting \fIcharsToRead\fR to \fB-1\fR will cause the command to read all characters currently available (non-blocking) or everything until eof (blocking mode). .PP The return value may be smaller than the value to read, indicating that less data than requested was available. This is called a \fIshort read\fR. In blocking mode, this can only happen on an end-of-file. In nonblocking mode, a short read can also occur if there is not enough input currently available: \fBTcl_ReadChars\fR returns a short count rather than waiting for more data. .PP If the channel is in blocking mode, a return value of zero indicates an end-of-file condition. If the channel is in nonblocking mode, a return value of zero indicates either that no input is currently available or an end-of-file condition. Use \fBTcl_Eof\fR and \fBTcl_InputBlocked\fR to tell which of these conditions actually occurred. .PP \fBTcl_ReadChars\fR translates the various end-of-line representations into the canonical \fB\en\fR internal representation according to the current end-of-line recognition mode. End-of-line recognition and the various platform-specific modes are described in the manual entry for the Tcl \fBfconfigure\fR command. .PP As a performance optimization, when reading from a channel with the encoding \fBbinary\fR, the bytes are not converted to UTF-8 as they are read. Instead, they are stored in \fIreadObjPtr\fR's internal representation as a byte-array object. The string representation of this object will only be constructed if it is needed (e.g., because of a call to \fBTcl_GetStringFromObj\fR). In this way, byte-oriented data can be read from a channel, manipulated by calling \fBTcl_GetByteArrayFromObj\fR and related functions, and then written to a channel without the expense of ever converting to or from UTF-8. .PP \fBTcl_Read\fR is similar to \fBTcl_ReadChars\fR, except that it doesn't do encoding conversions, regardless of the channel's encoding. It is deprecated and exists for backwards compatibility with non-internationalized Tcl extensions. It consumes bytes from \fIchannel\fR and stores them in \fIreadBuf\fR, performing end-of-line translations on the way. The return value of \fBTcl_Read\fR is the number of bytes, up to \fIbytesToRead\fR, written in \fIreadBuf\fR. The buffer produced by \fBTcl_Read\fR is not null-terminated. Its contents are valid from the zeroth position up to and excluding the position indicated by the return value. .PP \fBTcl_ReadRaw\fR is the same as \fBTcl_Read\fR but does not compensate for stacking. While \fBTcl_Read\fR (and the other functions in the API) always get their data from the topmost channel in the stack the supplied channel is part of, \fBTcl_ReadRaw\fR does not. Thus this function is \fBonly\fR usable for transformational channel drivers, i.e. drivers used in the middle of a stack of channels, to move data from the channel below into the transformation. .SH "TCL_GETSOBJ AND TCL_GETS" .PP \fBTcl_GetsObj\fR consumes bytes from \fIchannel\fR, converting the bytes to UTF-8 based on the channel's encoding, until a full line of input has been seen. If the channel's encoding is \fBbinary\fR, each byte read from the channel is treated as an individual Unicode character. All of the characters of the line except for the terminating end-of-line character(s) are appended to \fIlineObjPtr\fR's string representation. The end-of-line character(s) are read and discarded. .PP If a line was successfully read, the return value is greater than or equal to zero and indicates the number of bytes stored in \fIlineObjPtr\fR. If an error occurs, \fBTcl_GetsObj\fR returns \-1 and records a POSIX error code that can be retrieved with \fBTcl_GetErrno\fR. \fBTcl_GetsObj\fR also returns \-1 if the end of the file is reached; the \fBTcl_Eof\fR procedure can be used to distinguish an error from an end-of-file condition. .PP If the channel is in nonblocking mode, the return value can also be \-1 if no data was available or the data that was available did not contain an end-of-line character. When \-1 is returned, the \fBTcl_InputBlocked\fR procedure may be invoked to determine if the channel is blocked because of input unavailability. .PP \fBTcl_Gets\fR is the same as \fBTcl_GetsObj\fR except the resulting characters are appended to the dynamic string given by \fIlineRead\fR rather than a Tcl object. .SH "TCL_UNGETS" .PP \fBTcl_Ungets\fR is used to add data to the input queue of a channel, at either the head or tail of the queue. The pointer \fIinput\fR points to the data that is to be added. The length of the input to add is given by \fIinputLen\fR. A non-zero value of \fIaddAtEnd\fR indicates that the data is to be added at the end of queue; otherwise it will be added at the head of the queue. If \fIchannel\fR has a "sticky" EOF set, no data will be added to the input queue. \fBTcl_Ungets\fR returns \fIinputLen\fR or -1 if an error occurs. .SH "TCL_WRITECHARS, TCL_WRITEOBJ, AND TCL_WRITE" .PP \fBTcl_WriteChars\fR accepts \fIbytesToWrite\fR bytes of character data at \fIcharBuf\fR. The UTF-8 characters in the buffer are converted to the channel's encoding and queued for output to \fIchannel\fR. If \fIbytesToWrite\fR is negative, \fBTcl_WriteChars\fR expects \fIcharBuf\fR to be null-terminated and it outputs everything up to the null. .PP Data queued for output may not appear on the output device immediately, due to internal buffering. If the data should appear immediately, call \fBTcl_Flush\fR after the call to \fBTcl_WriteChars\fR, or set the \fB\-buffering\fR option on the channel to \fBnone\fR. If you wish the data to appear as soon as a complete line is accepted for output, set the \fB\-buffering\fR option on the channel to \fBline\fR mode. .PP The return value of \fBTcl_WriteChars\fR is a count of how many bytes were accepted for output to the channel. This is either greater than zero to indicate success or \-1 to indicate that an error occurred. If an error occurs, \fBTcl_WriteChars\fR records a POSIX error code that may be retrieved with \fBTcl_GetErrno\fR. .PP Newline characters in the output data are translated to platform-specific end-of-line sequences according to the \fB\-translation\fR option for the channel. This is done even if the channel has no encoding. .PP \fBTcl_WriteObj\fR is similar to \fBTcl_WriteChars\fR except it accepts a Tcl object whose contents will be output to the channel. The UTF-8 characters in \fIwriteObjPtr\fR's string representation are converted to the channel's encoding and queued for output to \fIchannel\fR. As a performance optimization, when writing to a channel with the encoding \fBbinary\fR, UTF-8 characters are not converted as they are written. Instead, the bytes in \fIwriteObjPtr\fR's internal representation as a byte-array object are written to the channel. The byte-array representation of the object will be constructed if it is needed. In this way, byte-oriented data can be read from a channel, manipulated by calling \fBTcl_GetByteArrayFromObj\fR and related functions, and then written to a channel without the expense of ever converting to or from UTF-8. .PP \fBTcl_Write\fR is similar to \fBTcl_WriteChars\fR except that it doesn't do encoding conversions, regardless of the channel's encoding. It is deprecated and exists for backwards compatibility with non-internationalized Tcl extensions. It accepts \fIbytesToWrite\fR bytes of data at \fIbyteBuf\fR and queues them for output to \fIchannel\fR. If \fIbytesToWrite\fR is negative, \fBTcl_Write\fR expects \fIbyteBuf\fR to be null-terminated and it outputs everything up to the null. .PP \fBTcl_WriteRaw\fR is the same as \fBTcl_Write\fR but does not compensate for stacking. While \fBTcl_Write\fR (and the other functions in the API) always feed their input to the topmost channel in the stack the supplied channel is part of, \fBTcl_WriteRaw\fR does not. Thus this function is \fBonly\fR usable for transformational channel drivers, i.e. drivers used in the middle of a stack of channels, to move data from the transformation into the channel below it. .VE .SH TCL_FLUSH .PP \fBTcl_Flush\fR causes all of the buffered output data for \fIchannel\fR to be written to its underlying file or device as soon as possible. If the channel is in blocking mode, the call does not return until all the buffered data has been sent to the channel or some error occurred. The call returns immediately if the channel is nonblocking; it starts a background flush that will write the buffered data to the channel eventually, as fast as the channel is able to absorb it. .PP The return value is normally \fBTCL_OK\fR. If an error occurs, \fBTcl_Flush\fR returns \fBTCL_ERROR\fR and records a POSIX error code that can be retrieved with \fBTcl_GetErrno\fR. .SH TCL_SEEK .PP \fBTcl_Seek\fR moves the access point in \fIchannel\fR where subsequent data will be read or written. Buffered output is flushed to the channel and buffered input is discarded, prior to the seek operation. .PP \fBTcl_Seek\fR normally returns the new access point. If an error occurs, \fBTcl_Seek\fR returns \-1 and records a POSIX error code that can be retrieved with \fBTcl_GetErrno\fR. After an error, the access point may or may not have been moved. .SH TCL_TELL .PP \fBTcl_Tell\fR returns the current access point for a channel. The returned value is \-1 if the channel does not support seeking. .SH TCL_GETCHANNELOPTION .PP \fBTcl_GetChannelOption\fR retrieves, in \fIoptionValue\fR, the value of one of the options currently in effect for a channel, or a list of all options and their values. The \fIchannel\fR argument identifies the channel for which to query an option or retrieve all options and their values. If \fIoptionName\fR is not NULL, it is the name of the option to query; the option's value is copied to the Tcl dynamic string denoted by \fIoptionValue\fR. If \fIoptionName\fR is NULL, the function stores an alternating list of option names and their values in \fIoptionValue\fR, using a series of calls to \fBTcl_DStringAppendElement\fR. The various preexisting options and their possible values are described in the manual entry for the Tcl \fBfconfigure\fR command. Other options can be added by each channel type. These channel type specific options are described in the manual entry for the Tcl command that creates a channel of that type; for example, the additional options for TCP based channels are described in the manual entry for the Tcl \fBsocket\fR command. The procedure normally returns \fBTCL_OK\fR. If an error occurs, it returns \fBTCL_ERROR\fR and calls \fBTcl_SetErrno\fR to store an appropriate POSIX error code. .SH TCL_SETCHANNELOPTION .PP \fBTcl_SetChannelOption\fR sets a new value \fInewValue\fR for an option \fIoptionName\fR on \fIchannel\fR. The procedure normally returns \fBTCL_OK\fR. If an error occurs, it returns \fBTCL_ERROR\fR; in addition, if \fIinterp\fR is non-NULL, \fBTcl_SetChannelOption\fR leaves an error message in the interpreter's result. .SH TCL_EOF .PP \fBTcl_Eof\fR returns a nonzero value if \fIchannel\fR encountered an end of file during the last input operation. .SH TCL_INPUTBLOCKED .PP \fBTcl_InputBlocked\fR returns a nonzero value if \fIchannel\fR is in nonblocking mode and the last input operation returned less data than requested because there was insufficient data available. The call always returns zero if the channel is in blocking mode. .SH TCL_INPUTBUFFERED .PP \fBTcl_InputBuffered\fR returns the number of bytes of input currently buffered in the internal buffers for a channel. If the channel is not open for reading, this function always returns zero. .SH TCL_OUTPUTBUFFERED .VS 8.4 \fBTcl_OutputBuffered\fR returns the number of bytes of output currently buffered in the internal buffers for a channel. If the channel is not open for writing, this function always returns zero. .VE .SH "PLATFORM ISSUES" .PP The handles returned from \fBTcl_GetChannelHandle\fR depend on the platform and the channel type. On Unix platforms, the handle is always a Unix file descriptor as returned from the \fBopen\fR system call. On Windows platforms, the handle is a file \fBHANDLE\fR when the channel was created with \fBTcl_OpenFileChannel\fR, \fBTcl_OpenCommandChannel\fR, or \fBTcl_MakeFileChannel\fR. Other channel types may return a different type of handle on Windows platforms. On the Macintosh platform, the handle is a file reference number as returned from \fBHOpenDF\fR. .SH "SEE ALSO" DString(3), fconfigure(n), filename(n), fopen(3), Tcl_CreateChannel(3) .SH KEYWORDS access point, blocking, buffered I/O, channel, channel driver, end of file, flush, input, nonblocking, output, read, seek, write '\" '\" Copyright (c) 1997-1998 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: Encoding.3,v 1.11.2.1 2003/07/18 16:56:24 dgp Exp $ '\" '\" The definitions below are for supplemental macros used in Tcl/Tk '\" manual entries. '\" '\" .AP type name in/out ?indent? '\" Start paragraph describing an argument to a library procedure. '\" type is type of argument (int, etc.), in/out is either "in", "out", '\" or "in/out" to describe whether procedure reads or modifies arg, '\" and indent is equivalent to second arg of .IP (shouldn't ever be '\" needed; use .AS below instead) '\" '\" .AS ?type? ?name? '\" Give maximum sizes of arguments for setting tab stops. Type and '\" name are examples of largest possible arguments that will be passed '\" to .AP later. If args are omitted, default tab stops are used. '\" '\" .BS '\" Start box enclosure. From here until next .BE, everything will be '\" enclosed in one large box. '\" '\" .BE '\" End of box enclosure. '\" '\" .CS '\" Begin code excerpt. '\" '\" .CE '\" End code excerpt. '\" '\" .VS ?version? ?br? '\" Begin vertical sidebar, for use in marking newly-changed parts '\" of man pages. The first argument is ignored and used for recording '\" the version when the .VS was added, so that the sidebars can be '\" found and removed when they reach a certain age. If another argument '\" is present, then a line break is forced before starting the sidebar. '\" '\" .VE '\" End of vertical sidebar. '\" '\" .DS '\" Begin an indented unfilled display. '\" '\" .DE '\" End of indented unfilled display. '\" '\" .SO '\" Start of list of standard options for a Tk widget. The '\" options follow on successive lines, in four columns separated '\" by tabs. '\" '\" .SE '\" End of list of standard options for a Tk widget. '\" '\" .OP cmdName dbName dbClass '\" Start of description of a specific option. cmdName gives the '\" option's name as specified in the class command, dbName gives '\" the option's name in the option database, and dbClass gives '\" the option's class in the option database. '\" '\" .UL arg1 arg2 '\" Print arg1 underlined, then print arg2 normally. '\" '\" RCS: @(#) $Id: man.macros,v 1.4 2000/08/25 06:18:32 ericm Exp $ '\" '\" # Set up traps and other miscellaneous stuff for Tcl/Tk man pages. .if t .wh -1.3i ^B .nr ^l \n(.l .ad b '\" # Start an argument description .de AP .ie !"\\$4"" .TP \\$4 .el \{\ . ie !"\\$2"" .TP \\n()Cu . el .TP 15 .\} .ta \\n()Au \\n()Bu .ie !"\\$3"" \{\ \&\\$1 \\fI\\$2\\fP (\\$3) .\".b .\} .el \{\ .br .ie !"\\$2"" \{\ \&\\$1 \\fI\\$2\\fP .\} .el \{\ \&\\fI\\$1\\fP .\} .\} .. '\" # define tabbing values for .AP .de AS .nr )A 10n .if !"\\$1"" .nr )A \\w'\\$1'u+3n .nr )B \\n()Au+15n .\" .if !"\\$2"" .nr )B \\w'\\$2'u+\\n()Au+3n .nr )C \\n()Bu+\\w'(in/out)'u+2n .. .AS Tcl_Interp Tcl_CreateInterp in/out '\" # BS - start boxed text '\" # ^y = starting y location '\" # ^b = 1 .de BS .br .mk ^y .nr ^b 1u .if n .nf .if n .ti 0 .if n \l'\\n(.lu\(ul' .if n .fi .. '\" # BE - end boxed text (draw box now) .de BE .nf .ti 0 .mk ^t .ie n \l'\\n(^lu\(ul' .el \{\ .\" Draw four-sided box normally, but don't draw top of .\" box if the box started on an earlier page. .ie !\\n(^b-1 \{\ \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul' .\} .el \}\ \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\l'|0u-1.5n\(ul' .\} .\} .fi .br .nr ^b 0 .. '\" # VS - start vertical sidebar '\" # ^Y = starting y location '\" # ^v = 1 (for troff; for nroff this doesn't matter) .de VS .if !"\\$2"" .br .mk ^Y .ie n 'mc \s12\(br\s0 .el .nr ^v 1u .. '\" # VE - end of vertical sidebar .de VE .ie n 'mc .el \{\ .ev 2 .nf .ti 0 .mk ^t \h'|\\n(^lu+3n'\L'|\\n(^Yu-1v\(bv'\v'\\n(^tu+1v-\\n(^Yu'\h'-|\\n(^lu+3n' .sp -1 .fi .ev .\} .nr ^v 0 .. '\" # Special macro to handle page bottom: finish off current '\" # box/sidebar if in box/sidebar mode, then invoked standard '\" # page bottom macro. .de ^B .ev 2 'ti 0 'nf .mk ^t .if \\n(^b \{\ .\" Draw three-sided box if this is the box's first page, .\" draw two sides but no top otherwise. .ie !\\n(^b-1 \h'-1.5n'\L'|\\n(^yu-1v'\l'\\n(^lu+3n\(ul'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c .el \h'-1.5n'\L'|\\n(^yu-1v'\h'\\n(^lu+3n'\L'\\n(^tu+1v-\\n(^yu'\h'|0u'\c .\} .if \\n(^v \{\ .nr ^x \\n(^tu+1v-\\n(^Yu \kx\h'-\\nxu'\h'|\\n(^lu+3n'\ky\L'-\\n(^xu'\v'\\n(^xu'\h'|0u'\c .\} .bp 'fi .ev .if \\n(^b \{\ .mk ^y .nr ^b 2 .\} .if \\n(^v \{\ .mk ^Y .\} .. '\" # DS - begin display .de DS .RS .nf .sp .. '\" # DE - end display .de DE .fi .RE .sp .. '\" # SO - start of list of standard options .de SO .SH "STANDARD OPTIONS" .LP .nf .ta 5.5c 11c .ft B .. '\" # SE - end of list of standard options .de SE .fi .ft R .LP See the \\fBoptions\\fR manual entry for details on the standard options. .. '\" # OP - start of full description for a single option .de OP .LP .nf .ta 4c Command-Line Name: \\fB\\$1\\fR Database Name: \\fB\\$2\\fR Database Class: \\fB\\$3\\fR .fi .IP .. '\" # CS - begin code excerpt .de CS .RS .nf .ta .25i .5i .75i 1i .. '\" # CE - end code excerpt .de CE .fi .RE .. .de UL \\$1\l'|0\(ul'\\$2 .. .TH Tcl_GetEncoding 3 "8.1" Tcl "Tcl Library Procedures" .BS .SH NAME Tcl_GetEncoding, Tcl_FreeEncoding, Tcl_ExternalToUtfDString, Tcl_ExternalToUtf, Tcl_UtfToExternalDString, Tcl_UtfToExternal, Tcl_WinTCharToUtf, Tcl_WinUtfToTChar, Tcl_GetEncodingName, Tcl_SetSystemEncoding, Tcl_GetEncodingNames, Tcl_CreateEncoding, Tcl_GetDefaultEncodingDir, Tcl_SetDefaultEncodingDir \- procedures for creating and using encodings. .SH SYNOPSIS .nf \fB#include \fR .sp Tcl_Encoding \fBTcl_GetEncoding\fR(\fIinterp, name\fR) .sp void \fBTcl_FreeEncoding\fR(\fIencoding\fR) .sp char * \fBTcl_ExternalToUtfDString\fR(\fIencoding, src, srcLen, dstPtr\fR) .sp int \fBTcl_ExternalToUtf\fR(\fIinterp, encoding, src, srcLen, flags, statePtr, dst, dstLen, srcReadPtr, dstWrotePtr, dstCharsPtr\fR) .sp char * \fBTcl_UtfToExternalDString\fR(\fIencoding, src, srcLen, dstPtr\fR) .sp int \fBTcl_UtfToExternal\fR(\fIinterp, encoding, src, srcLen, flags, statePtr, dst, dstLen, srcReadPtr, dstWrotePtr, dstCharsPtr\fR) .sp char * \fBTcl_WinTCharToUtf\fR(\fItsrc, srcLen, dstPtr\fR) .sp TCHAR * \fBTcl_WinUtfToTChar\fR(\fIsrc, srcLen, dstPtr\fR) .sp CONST char * \fBTcl_GetEncodingName\fR(\fIencoding\fR) .sp int \fBTcl_SetSystemEncoding\fR(\fIinterp, name\fR) .sp void \fBTcl_GetEncodingNames\fR(\fIinterp\fR) .sp Tcl_Encoding \fBTcl_CreateEncoding\fR(\fItypePtr\fR) .sp CONST char * \fBTcl_GetDefaultEncodingDir\fR(\fIvoid\fR) .sp void \fBTcl_SetDefaultEncodingDir\fR(\fIpath\fR) .SH ARGUMENTS .AS Tcl_EncodingState *dstWrotePtr .AP Tcl_Interp *interp in Interpreter to use for error reporting, or NULL if no error reporting is desired. .AP "CONST char" *name in Name of encoding to load. .AP Tcl_Encoding encoding in The encoding to query, free, or use for converting text. If \fIencoding\fR is NULL, the current system encoding is used. .AP "CONST char" *src in For the \fBTcl_ExternalToUtf\fR functions, an array of bytes in the specified encoding that are to be converted to UTF-8. For the \fBTcl_UtfToExternal\fR and \fBTcl_WinUtfToTChar\fR functions, an array of UTF-8 characters to be converted to the specified encoding. .AP "CONST TCHAR" *tsrc in An array of Windows TCHAR characters to convert to UTF-8. .AP int srcLen in Length of \fIsrc\fR or \fItsrc\fR in bytes. If the length is negative, the encoding-specific length of the string is used. .AP Tcl_DString *dstPtr out Pointer to an uninitialized or free \fBTcl_DString\fR in which the converted result will be stored. .AP int flags in Various flag bits OR-ed together. TCL_ENCODING_START signifies that the source buffer is the first block in a (potentially multi-block) input stream, telling the conversion routine to reset to an initial state and perform any initialization that needs to occur before the first byte is converted. TCL_ENCODING_END signifies that the source buffer is the last block in a (potentially multi-block) input stream, telling the conversion routine to perform any finalization that needs to occur after the last byte is converted and then to reset to an initial state. TCL_ENCODING_STOPONERROR signifies that the conversion routine should return immediately upon reading a source character that doesn't exist in the target encoding; otherwise a default fallback character will automatically be substituted. .AP Tcl_EncodingState *statePtr in/out Used when converting a (generally long or indefinite length) byte stream in a piece by piece fashion. The conversion routine stores its current state in \fI*statePtr\fR after \fIsrc\fR (the buffer containing the current piece) has been converted; that state information must be passed back when converting the next piece of the stream so the conversion routine knows what state it was in when it left off at the end of the last piece. May be NULL, in which case the value specified for \fIflags\fR is ignored and the source buffer is assumed to contain the complete string to convert. .AP char *dst out Buffer in which the converted result will be stored. No more than \fIdstLen\fR bytes will be stored in \fIdst\fR. .AP int dstLen in The maximum length of the output buffer \fIdst\fR in bytes. .AP int *srcReadPtr out Filled with the number of bytes from \fIsrc\fR that were actually converted. This may be less than the original source length if there was a problem converting some source characters. May be NULL. .AP int *dstWrotePtr out Filled with the number of bytes that were actually stored in the output buffer as a result of the conversion. May be NULL. .AP int *dstCharsPtr out Filled with the number of characters that correspond to the number of bytes stored in the output buffer. May be NULL. .AP Tcl_EncodingType *typePtr in Structure that defines a new type of encoding. .AP "CONST char" *path in A path to the location of the encoding file. .BE .SH INTRODUCTION .PP These routines convert between Tcl's internal character representation, UTF-8, and character representations used by various operating systems or file systems, such as Unicode, ASCII, or Shift-JIS. When operating on strings, such as such as obtaining the names of files or displaying characters using international fonts, the strings must be translated into one or possibly multiple formats that the various system calls can use. For instance, on a Japanese Unix workstation, a user might obtain a filename represented in the EUC-JP file encoding and then translate the characters to the jisx0208 font encoding in order to display the filename in a Tk widget. The purpose of the encoding package is to help bridge the translation gap. UTF-8 provides an intermediate staging ground for all the various encodings. In the example above, text would be translated into UTF-8 from whatever file encoding the operating system is using. Then it would be translated from UTF-8 into whatever font encoding the display routines require. .PP Some basic encodings are compiled into Tcl. Others can be defined by the user or dynamically loaded from encoding files in a platform-independent manner. .SH DESCRIPTION .PP \fBTcl_GetEncoding\fR finds an encoding given its \fIname\fR. The name may refer to a builtin Tcl encoding, a user-defined encoding registered by calling \fBTcl_CreateEncoding\fR, or a dynamically-loadable encoding file. The return value is a token that represents the encoding and can be used in subsequent calls to procedures such as \fBTcl_GetEncodingName\fR, \fBTcl_FreeEncoding\fR, and \fBTcl_UtfToExternal\fR. If the name did not refer to any known or loadable encoding, NULL is returned and an error message is returned in \fIinterp\fR. .PP The encoding package maintains a database of all encodings currently in use. The first time \fIname\fR is seen, \fBTcl_GetEncoding\fR returns an encoding with a reference count of 1. If the same \fIname\fR is requested further times, then the reference count for that encoding is incremented without the overhead of allocating a new encoding and all its associated data structures. .PP When an \fIencoding\fR is no longer needed, \fBTcl_FreeEncoding\fR should be calpcqcrcsctcucvcwcxcyczc{c|c}c~ccccled to release it. When an \fIencoding\fR is no longer in use anywhere (i.e., it has been freed as many times as it has been gotten) \fBTcl_FreeEncoding\fR will release all storage the encoding was using and delete it from the database. .PP \fBTcl_ExternalToUtfDString\fR converts a source buffer \fIsrc\fR from the specified \fIencoding\fR into UTF-8. The converted bytes are stored in \fIdstPtr\fR, which is then null-terminated. The caller should eventually call \fBTcl_DStringFree\fR to free any information stored in \fIdstPtr\fR. When converting, if any of the characters in the source buffer cannot be represented in the target encoding, a default fallback character will be used. The return value is a pointer to the value stored in the DString. .PP \fBTcl_ExternalToUtf\fR converts a source buffer \fIsrc\fR from the specified \fIencoding\fR into UTF-8. Up to \fIsrcLen\fR bytes are converted from the source buffer and up to \fIdstLen\fR converted bytes are stored in \fIdst\fR. In all cases, \fI*srcReadPtr\fR is filled with the number of bytes that were successfully converted from \fIsrc\fR and \fI*dstWrotePtr\fR is filled with the corresponding number of bytes that were stored in \fIdst\fR. The return value is one of the following: .RS .IP \fBTCL_OK\fR 29 All bytes of \fIsrc\fR were converted. .IP \fBTCL_CONVERT_NOSPACE\fR 29 The destination buffer was not large enough for all of the converted data; as many characters as could fit were converted though. .IP \fBTCL_CONVERT_MULTIBYTE\fR 29 The last fews bytes in the source buffer were the beginning of a multibyte sequence, but more bytes were needed to complete this sequence. A subsequent call to the conversion routine should pass a buffer containing the unconverted bytes that remained in \fIsrc\fR plus some further bytes from the source stream to properly convert the formerly split-up multibyte sequence. .IP \fBTCL_CONVERT_SYNTAX\fR 29 The source buffer contained an invalid character sequence. This may occur if the input stream has been damaged or if the input encoding method was misidentified. .IP \fBTCL_CONVERT_UNKNOWN\fR 29 The source buffer contained a character that could not be represented in the target encoding and TCL_ENCODING_STOPONERROR was specified. .RE .LP \fBTcl_UtfToExternalDString\fR converts a source buffer \fIsrc\fR from UTF-8 into the specified \fIencoding\fR. The converted bytes are stored in \fIdstPtr\fR, which is then terminated with the appropriate encoding-specific null. The caller should eventually call \fBTcl_DStringFree\fR to free any information stored in \fIdstPtr\fR. When converting, if any of the characters in the source buffer cannot be represented in the target encoding, a default fallback character will be used. The return value is a pointer to the value stored in the DString. .PP \fBTcl_UtfToExternal\fR converts a source buffer \fIsrc\fR from UTF-8 into the specified \fIencoding\fR. Up to \fIsrcLen\fR bytes are converted from the source buffer and up to \fIdstLen\fR converted bytes are stored in \fIdst\fR. In all cases, \fI*srcReadPtr\fR is filled with the number of bytes that were successfully converted from \fIsrc\fR and \fI*dstWrotePtr\fR is filled with the corresponding number of bytes that were stored in \fIdst\fR. The return values are the same as the return values for \fBTcl_ExternalToUtf\fR. .PP \fBTcl_WinUtfToTChar\fR and \fBTcl_WinTCharToUtf\fR are Windows-only convenience functions for converting between UTF-8 and Windows strings. On Windows 95 (as with the Macintosh and Unix operating systems), all strings exchanged between Tcl and the operating system are "char" based. On Windows NT, some strings exchanged between Tcl and the operating system are "char" oriented while others are in Unicode. By convention, in Windows a TCHAR is a character in the ANSI code page on Windows 95 and a Unicode character on Windows NT. .PP If you planned to use the same "char" based interfaces on both Windows 95 and Windows NT, you could use \fBTcl_UtfToExternal\fR and \fBTcl_ExternalToUtf\fR (or their \fBTcl_DString\fR equivalents) with an encoding of NULL (the current system encoding). On the other hand, if you planned to use the Unicode interface when running on Windows NT and the "char" interfaces when running on Windows 95, you would have to perform the following type of test over and over in your program (as represented in pseudo-code): .CS if (running NT) { encoding <- Tcl_GetEncoding("unicode"); nativeBuffer <- Tcl_UtfToExternal(encoding, utfBuffer); Tcl_FreeEncoding(encoding); } else { nativeBuffer <- Tcl_UtfToExternal(NULL, utfBuffer); .CE \fBTcl_WinUtfToTChar\fR and \fBTcl_WinTCharToUtf\fR automatically handle this test and use the proper encoding based on the current operating system. \fBTcl_WinUtfToTChar\fR returns a pointer to a TCHAR string, and \fBTcl_WinTCharToUtf\fR expects a TCHAR string pointer as the \fIsrc\fR string. Otherwise, these functions behave identically to \fBTcl_UtfToExternalDString\fR and \fBTcl_ExternalToUtfDString\fR. .PP \fBTcl_GetEncodingName\fR is roughly the inverse of \fBTcl_GetEncoding\fR. Given an \fIencoding\fR, the return value is the \fIname\fR argument that was used to create the encoding. The string returned by \fBTcl_GetEncodingName\fR is only guaranteed to persist until the \fIencoding\fR is deleted. The caller must not modify this string. .PP \fBTcl_SetSystemEncoding\fR sets the default encoding that should be used whenever the user passes a NULL value for the \fIencoding\fR argument to any of the other encoding functions. If \fIname\fR is NULL, the system encoding is reset to the default system encoding, \fBbinary\fR. If the name did not refer to any known or loadable encoding, TCL_ERROR is returned and an error message is left in \fIinterp\fR. Otherwise, this procedure increments the reference count of the new system encoding, decrements the reference count of the old system encoding, and returns TCL_OK. .PP \fBTcl_GetEncodingNames\fR sets the \fIinterp\fR result to a list consisting of the names of all the encodings that are currently defined or can be dynamically loaded, searching the encoding path specified by \fBTcl_SetDefaultEncodingDir\fR. This procedure does not ensure that the dynamically-loadable encoding files contain valid data, but merely that they exist. .PP \fBTcl_CreateEncoding\fR defines a new encoding and registers the C procedures that are called back to convert between the encoding and UTF-8. Encodings created by \fBTcl_CreateEncoding\fR are thereafter visible in the database used by \fBTcl_GetEncoding\fR. Just as with the \fBTcl_GetEncoding\fR procedure, the return value is a token that represents the encoding and can be used in subsequent calls to other encoding functions. \fBTcl_CreateEncoding\fR returns an encoding with a reference count of 1. If an encoding with the specified \fIname\fR already exists, then its entry in the database is replaced with the new encoding; the token for the old encoding will remain valid and continue to behave as before, but users of the new token will now call the new encoding procedures. .PP The \fItypePtr\fR argument to \fBTcl_CreateEncoding\fR contains information about the name of the encoding and the procedures that will be called to convert between this encoding and UTF-8. It is defined as follows: .PP .CS typedef struct Tcl_EncodingType { CONST char *\fIencodingName\fR; Tcl_EncodingConvertProc *\fItoUtfProc\fR; Tcl_EncodingConvertProc *\fIfromUtfProc\fR; Tcl_EncodingFreeProc *\fIfreeProc\fR; ClientData \fIclientData\fR; int \fInullSize\fR; } Tcl_EncodingType; .CE .PP The \fIencodingName\fR provides a string name for the encoding, by which it can be referred in other procedures such as \fBTcl_GetEncoding\fR. The \fItoUtfProc\fR refers to a callback procedure to invoke to convert text from this encoding into UTF-8. The \fIfromUtfProc\fR refers to a callback procedure to invoke to convert text from UTF-8 into this encoding. The \fIfreeProc\fR refers to a callback procedure to invoke when this encoding is deleted. The \fIfreeProc\fR field may be NULL. The \fIclientData\fR contains an arbitrary one-word value passed to \fItoUtfProc\fR, \fIfromUtfProc\fR, and \fIfreeProc\fR whenever they are called. Typically, this is a pointer to a data structure containing encoding-specific information that can be used by the callback procedures. For instance, two very similar encodings such as \fBascii\fR and \fBmacRoman\fR may use the same callback procedure, but use different values of \fIclientData\fR to control its behavior. The \fInullSize\fR specifies the number of zero bytes that signify end-of-string in this encoding. It must be \fB1\fR (for single-byte or multi-byte encodings like ASCII or Shift-JIS) or \fB2\fR (for double-byte encodings like Unicode). Constant-sized encodings with 3 or more bytes per character (such as CNS11643) are not accepted. .PP The callback procedures \fItoUtfProc\fR and \fIfromUtfProc\fR should match the type \fBTcl_EncodingConvertProc\fR: .PP .CS typedef int Tcl_EncodingConvertProc( ClientData \fIclientData\fR, CONST char *\fIsrc\fR, int \fIsrcLen\fR, int \fIflags\fR, Tcl_Encoding *\fIstatePtr\fR, char *\fIdst\fR, int \fIdstLen\fR, int *\fIsrcReadPtr\fR, int *\fIdstWrotePtr\fR, int *\fIdstCharsPtr\fR); .CE .PP The \fItoUtfProc\fR and \fIfromUtfProc\fR procedures are called by the \fBTcl_ExternalToUtf\fR or \fBTcl_UtfToExternal\fR family of functions to perform the actual conversion. The \fIclientData\fR parameter to these procedures is the same as the \fIclientData\fR field specified to \fBTcl_CreateEncoding\fR when the encoding was created. The remaining arguments to the callback procedures are the same as the arguments, documented at the top, to \fBTcl_ExternalToUtf\fR or \fBTcl_UtfToExternal\fR, with the following exceptions. If the \fIsrcLen\fR argument to one of those high-level functions is negative, the value passed to the callback procedure will be the appropriate encoding-specific string length of \fIsrc\fR. If any of the \fIsrcReadPtr\fR, \fIdstWrotePtr\fR, or \fIdstCharsPtr\fR arguments to one of the high-level functions is NULL, the corresponding value passed to the callback procedure will be a non-NULL location. .PP The callback procedure \fIfreeProc\fR, if non-NULL, should match the type \fBTcl_EncodingFreeProc\fR: .CS typedef void Tcl_EncodingFreeProc( ClientData \fIclientData\fR); .CE .PP This \fIfreeProc\fR function is called when the encoding is deleted. The \fIclientData\fR parameter is the same as the \fIclientData\fR field specified to \fBTcl_CreateEncoding\fR when the encoding was created. .PP \fBTcl_GetDefaultEncodingDir\fR and \fBTcl_SetDefaultEncodingDir\fR access and set the directory to use when locating the default encoding files. If this value is not NULL, the \fBTclpInitLibraryPath\fR routine appends the path to the head of the search path, and uses this path as the first place to look into when trying to locate the encoding file. .SH "ENCODING FILES" Space would prohibit precompiling into Tcl every possible encoding algorithm, so many encodings are stored on disk as dynamically-loadable encoding files. This behavior also allows the user to create additional encoding files that can be loaded using the same mechanism. These encoding files contain information about the tables and/or escape sequences used to map between an external encoding and Unicode. The external encoding may consist of single-byte, multi-byte, or double-byte characters. .PP Each dynamically-loadable encoding is represented as a text file. The initial line of the file, beginning with a ``#'' symbol, is a comment that provides a human-readable description of the file. The next line identifies the type of encoding file. It can be one of the following letters: .IP "[1] \fBS\fR" A single-byte encoding, where one character is always one byte long in the encoding. An example is \fBiso8859-1\fR, used by many European languages. .IP "[2] \fBD\fR" A double-byte encoding, where one character is always two bytes long in the encoding. An example is \fBbig5\fR, used for Chinese text. .IP "[3] \fBM\fR" A multi-byte encoding, where one character may be either one or two bytes long. Certain bytes are a lead bytes, indicating that another byte must follow and that together the two bytes represent one character. Other bytes are not lead bytes and represent themselves. An example is \fBshiftjis\fR, used by many Japanese computers. .IP "[4] \fBE\fR" An escape-sequence encoding, specifying that certain sequences of bytes do not represent characters, but commands that describe how following bytes should be interpreted. .PP The rest of the lines in the file depend on the type. .PP Cases [1], [2], and [3] are collectively referred to as table-based encoding files. The lines in a table-based encoding file are in the same format as this example taken from the \fBshiftjis\fR encoding (this is not the complete file): .CS # Encoding file: shiftjis, multi-byte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he third line of the file is three numbers. The first number is the fallback character (in base 16) to use when converting from UTF-8 to this encoding. The second number is a \fB1\fR if this file represents the encoding for a symbol font, or \fB0\fR otherwise. The last number (in base 10) is how many pages of data follow. .PP Subsequent lines in the example above are pages that describe how to map from the encoding into 2-byte Unicode. The first line in a page identifies the page number. Following it are 256 double-byte numbers, arranged as 16 rows of 16 numbers. Given a character in the encoding, the high byte of that character is used to select which page, and the low byte of that character is used as an index to select one of the double-byte numbers in that page \- the value obtained being the corresponding Unicode character. By examination of the example above, one can see that the characters 0x7E and 0x8163 in \fBshiftjis\fR map to 203E and 2026 in Unicode, respectively. .PP Following the first page will be all the other pages, each in the same format as the first: one number identifying the page followed by 256 double-byte Unicode characters. If