diff options
Diffstat (limited to 'doc')
| -rw-r--r-- | doc/AssocData.3 | 4 | ||||
| -rw-r--r-- | doc/Async.3 | 4 | ||||
| -rw-r--r-- | doc/Backslash.3 | 30 | ||||
| -rw-r--r-- | doc/CrtChannel.3 | 63 | ||||
| -rw-r--r-- | doc/CrtObjCmd.3 | 21 | ||||
| -rw-r--r-- | doc/Encoding.3 | 484 | ||||
| -rw-r--r-- | doc/Eval.3 | 187 | ||||
| -rw-r--r-- | doc/EvalObj.3 | 91 | ||||
| -rw-r--r-- | doc/Exit.3 | 46 | ||||
| -rwxr-xr-x | doc/GetCwd.3 | 54 | ||||
| -rw-r--r-- | doc/GetIndex.3 | 31 | ||||
| -rwxr-xr-x[-rw-r--r--] | doc/GetVersion.3 (renamed from doc/CrtVersion.3) | 8 | ||||
| -rw-r--r-- | doc/ObjSetVar.3 | 162 | ||||
| -rw-r--r-- | doc/Object.3 | 13 | ||||
| -rw-r--r-- | doc/OpenFileChnl.3 | 325 | ||||
| -rw-r--r-- | doc/ParseCmd.3 | 426 | ||||
| -rw-r--r-- | doc/RegExp.3 | 21 | ||||
| -rw-r--r-- | doc/SaveResult.3 | 65 | ||||
| -rw-r--r-- | doc/SetRecLmt.3 | 4 | ||||
| -rw-r--r-- | doc/SetVar.3 | 211 | ||||
| -rw-r--r-- | doc/StringObj.3 | 32 | ||||
| -rw-r--r-- | doc/Tcl.n | 68 | ||||
| -rw-r--r-- | doc/Thread.3 | 100 | ||||
| -rw-r--r-- | doc/ToUpper.3 | 90 | ||||
| -rw-r--r-- | doc/TraceVar.3 | 42 | ||||
| -rw-r--r-- | doc/Translate.3 | 8 | ||||
| -rw-r--r-- | doc/Utf.3 | 160 | ||||
| -rw-r--r-- | doc/binary.n | 22 | ||||
| -rw-r--r-- | doc/catch.n | 62 | ||||
| -rw-r--r-- | doc/dde.n | 124 | ||||
| -rw-r--r-- | doc/encoding.n | 79 | ||||
| -rw-r--r-- | doc/exec.n | 17 | ||||
| -rw-r--r-- | doc/fconfigure.n | 194 | ||||
| -rw-r--r-- | doc/format.n | 6 | ||||
| -rw-r--r-- | doc/glob.n | 19 | ||||
| -rw-r--r-- | doc/http.n | 6 | ||||
| -rw-r--r-- | doc/library.n | 24 | ||||
| -rw-r--r-- | doc/man.macros | 4 | ||||
| -rw-r--r-- | doc/msgcat.n | 207 | ||||
| -rw-r--r-- | doc/namespace.n | 54 | ||||
| -rw-r--r-- | doc/open.n | 6 | ||||
| -rw-r--r-- | doc/puts.n | 6 | ||||
| -rw-r--r-- | doc/read.n | 6 | ||||
| -rw-r--r-- | doc/regexp.n | 1083 | ||||
| -rw-r--r-- | doc/registry.n | 3 | ||||
| -rw-r--r-- | doc/resource.n | 4 | ||||
| -rw-r--r-- | doc/safe.n | 19 | ||||
| -rw-r--r-- | doc/scan.n | 68 | ||||
| -rw-r--r-- | doc/socket.n | 6 | ||||
| -rw-r--r-- | doc/string.n | 40 | ||||
| -rw-r--r-- | doc/tclvars.n | 17 |
51 files changed, 3882 insertions, 944 deletions
diff --git a/doc/AssocData.3 b/doc/AssocData.3 index 4ff36c8..9b68c43 100644 --- a/doc/AssocData.3 +++ b/doc/AssocData.3 @@ -5,7 +5,7 @@ '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" '\" -'\" RCS: @(#) $Id: AssocData.3,v 1.2 1998/09/14 18:39:46 stanton Exp $ +'\" RCS: @(#) $Id: AssocData.3,v 1.3 1999/04/16 00:46:30 stanton Exp $ .so man.macros .TH Tcl_SetAssocData 3 7.5 Tcl "Tcl Library Procedures" .BS @@ -84,6 +84,6 @@ specified key exists in the given interpreter \fBTcl_GetAssocData\fR returns \fBNULL\fR. .PP \fBTcl_DeleteAssocData\fR deletes an association with a specified key in -the given interpreter. It does not call the deletion procedure. +the given interpreter. Then it calls the deletion procedure. .SH KEYWORDS association, data, deletion procedure, interpreter, key diff --git a/doc/Async.3 b/doc/Async.3 index 1c245cb..5086557 100644 --- a/doc/Async.3 +++ b/doc/Async.3 @@ -5,13 +5,13 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: Async.3,v 1.2 1998/09/14 18:39:46 stanton Exp $ +'\" RCS: @(#) $Id: Async.3,v 1.3 1999/04/16 00:46:30 stanton Exp $ '\" .so man.macros .TH Tcl_AsyncCreate 3 7.0 Tcl "Tcl Library Procedures" .BS .SH NAME -Tcl_AsyncCreate, Tcl_AsyncMark, Tcl_AsyncInvoke, Tcl_AsyncDelete \- handle asynchronous events +Tcl_AsyncCreate, Tcl_AsyncMark, Tcl_AsyncInvoke, Tcl_AsyncDelete, Tcl_AsyncReady \- handle asynchronous events .SH SYNOPSIS .nf \fB#include <tcl.h>\fR diff --git a/doc/Backslash.3 b/doc/Backslash.3 index 382e8f2..95fc7e8 100644 --- a/doc/Backslash.3 +++ b/doc/Backslash.3 @@ -5,10 +5,10 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: Backslash.3,v 1.2 1998/09/14 18:39:46 stanton Exp $ +'\" RCS: @(#) $Id: Backslash.3,v 1.3 1999/04/16 00:46:30 stanton Exp $ '\" .so man.macros -.TH Tcl_Backslash 3 "" Tcl "Tcl Library Procedures" +.TH Tcl_Backslash 3 "8.1" Tcl "Tcl Library Procedures" .BS .SH NAME Tcl_Backslash \- parse a backslash sequence @@ -30,16 +30,24 @@ the backslash character. .SH DESCRIPTION .PP -This is a utility procedure used by several of the Tcl -commands. It parses a backslash sequence and returns -the single character corresponding to the sequence. -\fBTcl_Backslash\fR modifies \fI*countPtr\fR to contain the number -of characters in the backslash sequence. +.VS 8.1 +The use of \fBTcl_Backslash\fR is deprecated in favor of +\fBTcl_UtfBackslash\fR. .PP -See the Tcl manual entry for information on the valid -backslash sequences. -All of the sequences described in the Tcl -manual entry are supported by \fBTcl_Backslash\fR. +This is a utility procedure provided for backwards compatibilty with +non-internationalized Tcl extensions. It parses a backslash sequence and +returns the low byte of the Unicode character corresponding to the sequence. +.VE +\fBTcl_Backslash\fR modifies \fI*countPtr\fR to contain the number of +characters in the backslash sequence. +.PP +See the Tcl manual entry for information on the valid backslash sequences. +All of the sequences described in the Tcl manual entry are supported by +\fBTcl_Backslash\fR. +.VS 8.1 br +.SH "SEE ALSO" +Tcl(n), Tcl_UtfBackslash(3) +.VE .SH KEYWORDS backslash, parse diff --git a/doc/CrtChannel.3 b/doc/CrtChannel.3 index daef201..dc0f91b 100644 --- a/doc/CrtChannel.3 +++ b/doc/CrtChannel.3 @@ -4,13 +4,13 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: CrtChannel.3,v 1.2 1998/09/14 18:39:46 stanton Exp $ +'\" RCS: @(#) $Id: CrtChannel.3,v 1.3 1999/04/16 00:46:30 stanton Exp $ .so man.macros .TH Tcl_CreateChannel 3 8.0 Tcl "Tcl Library Procedures" .BS '\" Note: do not modify the .SH NAME line immediately below! .SH NAME -Tcl_CreateChannel, Tcl_GetChannelInstanceData, Tcl_GetChannelType, Tcl_GetChannelName, Tcl_GetChannelHandle, Tcl_GetChannelMode, Tcl_GetChannelBufferSize, Tcl_SetDefaultTranslation, Tcl_SetChannelBufferSize, Tcl_NotifyChannel, Tcl_BadChannelOption \- procedures for creating and manipulating channels +Tcl_CreateChannel, Tcl_GetChannelInstanceData, Tcl_GetChannelType, Tcl_GetChannelName, Tcl_GetChannelHandle, Tcl_GetChannelMode, Tcl_GetChannelBufferSize, Tcl_SetChannelBufferSize, Tcl_NotifyChannel, Tcl_BadChannelOption \- procedures for creating and manipulating channels .SH SYNOPSIS .nf \fB#include <tcl.h>\fR @@ -33,11 +33,6 @@ int .VE .sp int -\fBTcl_GetChannelFlags\fR(\fIchannel\fR) -.sp -\fBTcl_SetDefaultTranslation\fR(\fIchannel, transMode\fR) -.sp -int \fBTcl_GetChannelBufferSize\fR(\fIchannel\fR) .sp \fBTcl_SetChannelBufferSize\fR(\fIchannel, size\fR) @@ -170,13 +165,7 @@ for each driver to determine what type of handle is returned. and \fBTCL_WRITABLE\fR, indicating whether the channel is open for input and output. .PP -\fBTcl_SetDefaultTranslation\fR sets the default end of line translation -mode. This mode will be installed as the translation mode for the channel -if an attempt is made to output on the channel while it is still in -\fBTCL_TRANSLATE_AUTO\fR mode. For a description of end of line translation -modes, see the manual entry for \fBfconfigure\fR. -.PP -\fBTcl_GetChannelBufferSize\fR returns the size, in bytes, of buffers + \fBTcl_GetChannelBufferSize\fR returns the size, in bytes, of buffers allocated to store input or output in \fIchan\fR. If the value was not set by a previous call to \fBTcl_SetChannelBufferSize\fR, described below, then the default value of 4096 is returned. @@ -221,16 +210,19 @@ typedef struct Tcl_ChannelType { Tcl_DriverGetOptionProc *\fIgetOptionProc\fR; Tcl_DriverWatchProc *\fIwatchProc\fR; Tcl_DriverGetHandleProc *\fIgetHandleProc\fR; + Tcl_DriverClose2Proc *\fIclose2Proc\fR; } Tcl_ChannelType; .CE .VE .PP The driver must provide implementations for all functions except -\fIblockModeProc\fR, \fIseekProc\fR, \fIsetOptionProc\fR, and -\fIgetOptionProc\fR, which may be specified as NULL to indicate that the -channel does not support seeking. Other functions that can not be -implemented for this type of device should return \fBEINVAL\fR when invoked -to indicate that they are not implemented. +\fIblockModeProc\fR, \fIseekProc\fR, \fIsetOptionProc\fR, +.VS +\fIgetOptionProc\fR, and \fIclose2Proc\fR, which may be specified as +.VE +NULL. Other functions that can not be implemented for this type of +device should return \fBEINVAL\fR when invoked to indicate that they +are not implemented. .SH TYPENAME .PP @@ -264,7 +256,7 @@ For some device types, the blocking and nonblocking behavior can be implemented by the underlying operating system; for other device types, the behavior must be emulated in the channel driver. -.SH CLOSEPROC +.SH CLOSEPROC AND CLOSE2PROC .PP The \fIcloseProc\fR field contains the address of a function called by the generic layer to clean up driver-related information when the channel is @@ -286,6 +278,35 @@ calling the \fIcloseProc\fR. If the close operation is successful, the procedure should return zero; otherwise it should return a nonzero POSIX error code. In addition, if an error occurs and \fIinterp\fR is not NULL, the procedure should store an error message in \fIinterp->result\fR. +.PP +.VS +Alternatively, channels that support closing the read and write sides +independently may set \fIcloseProc\fR to \fBTCL_CLOSE2PROC\fR and set +\fIclose2Proc\fR to the address of a function that matches the +following prototype: +.PP +.CS +typedef int Tcl_DriverClose2Proc( + ClientData \fIinstanceData\fR, + Tcl_Interp *\fIinterp\fR, + int \fIflags\fR); +.CE +.PP +The \fIclose2Proc\fR will be called with \fIflags\fR set to an OR'ed +combination of \fBTCL_CLOSE_READ\fR or \fBTCL_CLOSE_WRITE\fR to +indicate that the driver should close the read and/or write side of +the channel. The channel driver may be invoked to perform +additional operations on the channel after \fIclose2Proc\fR is +called to close one or both sides of the channel. If \fIflags\fR is +\fB0\fR (zero), the driver should close the channel in the manner +described above for \fIcloseProc\fR. No further operations will be +invoked on this instance after \fIclose2Proc\fR is called with all +flags cleared. In all cases, the \fIclose2Proc\fR function should +return zero if the close operation was successful; otherwise it should +return a nonzero POSIX error code. In addition, if an error occurs and +\fIinterp\fR is not NULL, the procedure should store an error message +in \fIinterp->result\fR. +.VE .SH INPUTPROC .PP @@ -382,7 +403,7 @@ typedef int Tcl_DriverSeekProc( .PP The \fIinstanceData\fR argument is the same as the value given to \fBTcl_CreateChannel\fR when this channel was created. \fIOffset\fR and -\fIseekMode\fR have the same meaning as for the \fBTcl_SeekChannel\fR +\fIseekMode\fR have the same meaning as for the \fBTcl_Seek\fR procedure (described in the manual entry for \fBTcl_OpenFileChannel\fR). .PP The \fIerrorCodePtr\fR argument points to an integer variable provided by diff --git a/doc/CrtObjCmd.3 b/doc/CrtObjCmd.3 index 4390ef0..756b970 100644 --- a/doc/CrtObjCmd.3 +++ b/doc/CrtObjCmd.3 @@ -4,7 +4,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: CrtObjCmd.3,v 1.2 1998/09/14 18:39:47 stanton Exp $ +'\" RCS: @(#) $Id: CrtObjCmd.3,v 1.3 1999/04/16 00:46:30 stanton Exp $ '\" .so man.macros .TH Tcl_CreateObjCommand 3 8.0 Tcl "Tcl Library Procedures" @@ -62,8 +62,10 @@ such that whenever \fIname\fR is invoked as a Tcl command (e.g., via a call to \fBTcl_EvalObj\fR) the Tcl interpreter will call \fIproc\fR to process the command. .PP -\fBTcl_CreateObjCommand\fR will delete any command \fIname\fR -already associated with the interpreter. +\fBTcl_CreateObjCommand\fR deletes any existing command +\fIname\fR already associated with the interpreter +(however see below for an exception where the existing command +is not deleted). It returns a token that may be used to refer to the command in subsequent calls to \fBTcl_GetCommandName\fR. If \fIname\fR contains any \fB::\fR namespace qualifiers, @@ -101,7 +103,7 @@ cause memory to be lost and the runtime stack to be corrupted. The compilers to report any such attempted assignment as an error. However, it is acceptable to modify the internal representation of any individual object argument. For instance, the user may call -\fBTcl_GetIntFromObject\fR on \fIobjv\fR[\fB2\fR] to obtain the integer +\fBTcl_GetIntFromObj\fR on \fIobjv\fR[\fB2\fR] to obtain the integer representation of that object; that call may change the type of the object that \fIobjv\fR[\fB2\fR] points at, but will not change where \fIobjv\fR[\fB2\fR] points. @@ -128,6 +130,17 @@ not modify them. Call \fBTcl_SetObjResult\fR if you want to return something from the \fIobjv\fR array. .PP +Ordinarily, \fBTcl_CreateObjCommand\fR deletes any existing command +\fIname\fR already associated with the interpreter. +However, if the existing command was created by a previous call to +\fBTcl_CreateCommand\fR, +\fBTcl_CreateObjCommand\fR does not delete the command +but instead arranges for the Tcl interpreter to call the +\fBTcl_ObjCmdProc\fR \fIproc\fR in the future. +The old string-based \fBTcl_CmdProc\fR associated with the command +is retained and its address can be obtained by subsequent +\fBTcl_GetCommandInfo\fR calls. This is done for backwards compatibility. +.PP \fIDeleteProc\fR will be invoked when (if) \fIname\fR is deleted. This can occur through a call to \fBTcl_DeleteCommand\fR, \fBTcl_DeleteCommandFromToken\fR, or \fBTcl_DeleteInterp\fR, diff --git a/doc/Encoding.3 b/doc/Encoding.3 new file mode 100644 index 0000000..e9329dd --- /dev/null +++ b/doc/Encoding.3 @@ -0,0 +1,484 @@ +'\" +'\" 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 1.2 1999/04/16 00:46:31 stanton Exp $ +'\" +.so man.macros +.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_GetEncodingName, Tcl_SetSystemEncoding, Tcl_GetEncodingNames, Tcl_CreateEncoding, Tcl_GetDefaultEncodingDir, Tcl_SetDefaultEncodingDir \- procedures for creating and using encodings. + + + + +.SH SYNOPSIS +.nf +\fB#include <tcl.h>\fR +.sp +Tcl_Encoding +\fBTcl_GetEncoding\fR(\fIinterp, name\fR) +.sp +void +\fBTcl_FreeEncoding\fR(\fIencoding\fR) +.sp +void +\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 +void +\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_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 +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 functions, an array of UTF-8 characters to be +converted to the specified encoding. +.AP int srcLen in +Length of \fIsrc\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 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 called 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. +.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. +.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_GetEncodingName\fR is roughly the inverse of \fBTk_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 a character in the encoding maps to the +Unicode character 0000, it means that the character doesn't actually exist. +If all characters on a page would map to 0000, that page can be omitted. +.PP +Case [4] is the escape-sequence encoding file. The lines in an this type of +file are in the same format as this example taken from the \fBiso2022-jp\fR +encoding: +.CS +.ta 1.5i +# Encoding file: iso2022-jp, escape-driven +E +init {} +final {} +iso8859-1 \\x1b(B +jis0201 \\x1b(J +jis0208 \\x1b$@ +jis0208 \\x1b$B +jis0212 \\x1b$(D +gb2312 \\x1b$A +ksc5601 \\x1b$(C +.CE +.PP +In the file, the first column represents an option and the second column +is the associated value. \fBinit\fR is a string to emit or expect before +the first character is converted, while \fBfinal\fR is a string to emit +or expect after the last character. All other options are names of +table-based encodings; the associated value is the escape-sequence that +marks that encoding. Tcl syntax is used for the values; in the above +example, for instance, ``\fB{}\fR'' represents the empty string and +``\fB\\x1b\fR'' represents character 27. +.PP +When \fBTcl_GetEncoding\fR encounters an encoding \fIname\fR that has not +been loaded, it attempts to load an encoding file called \fIname\fB.enc\fR +from the \fBencoding\fR subdirectory of each directory specified in the +library path \fB$tcl_libPath\fR. If the encoding file exists, but is +malformed, an error message will be left in \fIinterp\fR. +.SH KEYWORDS +utf, encoding, convert + + + @@ -5,97 +5,173 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: Eval.3,v 1.3 1999/03/10 05:52:45 stanton Exp $ +'\" RCS: @(#) $Id: Eval.3,v 1.4 1999/04/16 00:46:31 stanton Exp $ '\" .so man.macros -.TH Tcl_Eval 3 7.0 Tcl "Tcl Library Procedures" +.TH Tcl_Eval 3 8.1 Tcl "Tcl Library Procedures" .BS .SH NAME -Tcl_Eval, Tcl_VarEval, Tcl_VarEvalVA, Tcl_EvalFile, Tcl_GlobalEval \- execute Tcl commands +Tcl_EvalObjEx, Tcl_EvalFile, Tcl_EvalObjv, Tcl_Eval, Tcl_EvalEx, Tcl_GlobalEval, Tcl_GlobalEvalObj, Tcl_VarEval, Tcl_VarEvalVA \- execute Tcl scripts .SH SYNOPSIS .nf \fB#include <tcl.h>\fR .sp +.VS int -\fBTcl_Eval\fR(\fIinterp, cmd\fR) +\fBTcl_EvalObjEx\fR(\fIinterp, objPtr, flags\fR) .sp int -\fBTcl_VarEval\fR(\fIinterp, string, string, ... \fB(char *) NULL\fR) +\fBTcl_EvalFile\fR(\fIinterp, fileName\fR) .sp int -\fBTcl_VarEvalVA\fR(\fIinterp, argList\fR) +\fBTcl_EvalObjv\fR(\fIinterp, objc, objv, flags\fR) .sp int -\fBTcl_EvalFile\fR(\fIinterp, fileName\fR) +\fBTcl_Eval\fR(\fIinterp, script\fR) +.sp +int +\fBTcl_EvalEx\fR(\fIinterp, script, numBytes, flags\fR) +.sp +int +\fBTcl_GlobalEval\fR(\fIinterp, script\fR) .sp int -\fBTcl_GlobalEval\fR(\fIinterp, cmd\fR) +\fBTcl_GlobalEvalObj\fR(\fIinterp, objPtr, flags\fR) +.sp +int +\fBTcl_VarEval\fR(\fIinterp, string, string, ... \fB(char *) NULL\fR) +.sp +int +\fBTcl_VarEvalVA\fR(\fIinterp, argList\fR) .SH ARGUMENTS .AS Tcl_Interp **termPtr; .AP Tcl_Interp *interp in -Interpreter in which to execute the command. -A string result will be stored in \fIinterp->result\fR. -.AP char *cmd in -Command (or sequence of commands) to execute. Must be in writable -memory (\fBTcl_Eval\fR makes temporary modifications to the command). +Interpreter in which to execute the script. The interpreter's result is +modified to hold the result or error message from the script. +.AP Tcl_Obj *objPtr in +A Tcl object containing the script to execute. +.AP int flags in +ORed combination of flag bits that specify additional options. +\fBTCL_EVAL_GLOBAL\fR and \fBTCL_EVAL_DIRECT\fR are currently supported. +.AP char *fileName in +Name of a file containing a Tcl script. +.AP int *objc in +The number of objects in the array pointed to by \fIobjPtr\fR; +this is also the number of words in the command. +.AP Tcl_Obj **objv in +Points to an array of pointers to objects; each object holds the +value of a single word in the command to execute. +.AP int numBytes in +The number of bytes in \fIscript\fR, not including any +null terminating character. If \-1, then all characters up to the +first null byte are used. +.AP char *script in +Points to first byte of script to execute. This script must be in +writable memory: temporary modifications are made to it during +parsing. .AP char *string in -String forming part of Tcl command. +String forming part of a Tcl script. .AP va_list argList in An argument list which must have been initialised using \fBTCL_VARARGS_START\fR, and cleared using \fBva_end\fR. -.AP char *fileName in -Name of file containing Tcl command string. .BE .SH DESCRIPTION .PP -All four of these procedures execute Tcl commands. -\fBTcl_Eval\fR is the core procedure and is used by all the others. -It executes the commands in the script held by \fIcmd\fR -until either an error occurs or it reaches the end of the script. +The procedures described here are invoked to execute Tcl scripts in +various forms. +\fBTcl_EvalObjEx\fR is the core procedure and is used by many of the others. +It executes the commands in the script stored in \fIobjPtr\fR +until either an error occurs or the end of the script is reached. +If this is the first time \fIobjPtr\fR has been executed, +its commands are compiled into bytecode instructions +which are then executed. The +bytecodes are saved in \fIobjPtr\fR so that the compilation step +can be skipped if the object is evaluated again in the future. +.PP +The return value from \fBTcl_EvalObjEx\fR (and all the other procedures +described here) is a Tcl completion code with +one of the values \fBTCL_OK\fR, \fBTCL_ERROR\fR, \fBTCL_RETURN\fR, +\fBTCL_BREAK\fR, or \fBTCL_CONTINUE\fR. +In addition, a result value or error message is left in \fIinterp\fR's +result; it can be retrieved using \fBTcl_GetObjResult\fR. +.PP +\fBTcl_EvalFile\fR reads the file given by \fIfileName\fR and evaluates +its contents as a Tcl script. It returns the same information as +\fBTcl_EvalObjEx\fR. +If the file couldn't be read then a Tcl error is returned to describe +why the file couldn't be read. +.PP +\fBTcl_EvalObjv\fR executes a single pre-parsed command instead of a +script. The \fIobjc\fR and \fIobjv\fR arguments contain the values +of the words for the Tcl command, one word in each object in +\fIobjv\fR. \fBTcl_EvalObjv\fR evaluates the command and returns +a completion code and result just like \fBTcl_EvalObjEx\fR. +.PP +\fBTcl_Eval\fR is similar to \fBTcl_EvalObjEx\fR except that +the script to be executed is supplied as a string instead of an +object and no compilation occurs. The string is parsed and executed +directly (using \fBTcl_EvalObjv\fR) instead of compiling it and +executing the bytecodes. In situations where it is known that the +script will never be executed again, \fBTcl_Eval\fR may be +faster than \fBTcl_EvalObjEx\fR. \fBTcl_Eval\fR returns a completion +code and result just like \fBTcl_EvalObjEx\fR. Note: for backward +compatibility with versions before Tcl 8.0, \fBTcl_Eval\fR +copies the object result in \fIinterp\fR to \fIinterp->result\fR +where it can be accessed directly. This makes \fBTcl_Eval\fR somewhat +slower than \fBTcl_EvalEx\fR, which doesn't do the copy. .PP -Note that \fBTcl_Eval\fR and \fBTcl_GlobalEval\fR -have been largely replaced by the -object-based procedures \fBTcl_EvalObj\fR and \fBTcl_GlobalEvalObj\fR. -Those object-based procedures evaluate a script held in a Tcl object -instead of a string. -The object argument can retain the bytecode instructions for the script -and so avoid reparsing the script each time it is executed. -\fBTcl_Eval\fR is implemented using \fBTcl_EvalObj\fR -but is slower because it must reparse the script each time -since there is no object to retain the bytecode instructions. +\fBTcl_EvalEx\fR is an extended version of \fBTcl_Eval\fR that takes +additional arguments \fInumBytes\fR and \fIflags\fR. For the +efficiency reason given above, \fBTcl_EvalEx\fR is generally preferred +over \fBTcl_Eval\fR. .PP -The return value from \fBTcl_Eval\fR is one of the Tcl return codes -\fBTCL_OK\fR, \fBTCL_ERROR\fR, \fBTCL_RETURN\fR, \fBTCL_BREAK\fR, or -\fBTCL_CONTINUE\fR, and \fIinterp->result\fR will point to -a string with additional information (a result value or error message). -If an error occurs during compilation, this return information -describes the error. -Otherwise, this return information corresponds to the last command -executed from \fIcmd\fR. +\fBTcl_GlobalEval\fR and \fBTcl_GlobalEvalObj\fR are older procedures +that are now deprecated. They are similar to \fBTcl_EvalEx\fR and +\fBTcl_EvalObjEx\fR except that the script is evaluated in the global +namespace and its variable context consists of global variables only +(it ignores any Tcl procedures that are active). These functions are +equivalent to using the \fBTCL_EVAL_GLOBAL\fR flag (see below). .PP \fBTcl_VarEval\fR takes any number of string arguments of any length, concatenates them into a single string, then calls \fBTcl_Eval\fR to execute that string as a Tcl command. It returns the result of the command and also modifies -\fIinterp->result\fR in the usual fashion for Tcl commands. +\fIinterp->result\fR in the same way as \fBTcl_Eval\fR. The last argument to \fBTcl_VarEval\fR must be NULL to indicate the end -of arguments. +of arguments. \fBTcl_VarEval\fR is now deprecated. .PP \fBTcl_VarEvalVA\fR is the same as \fBTcl_VarEval\fR except that -instead of taking a variable number of arguments it takes an argument list. -.PP -\fBTcl_EvalFile\fR reads the file given by \fIfileName\fR and evaluates -its contents as a Tcl command by calling \fBTcl_Eval\fR. It returns -a standard Tcl result that reflects the result of evaluating the file. -If the file couldn't be read then a Tcl error is returned to describe -why the file couldn't be read. +instead of taking a variable number of arguments it takes an argument +list. Like \fBTcl_VarEval\fR, \fBTcl_VarEvalVA\fR is deprecated. + +.SH "FLAG BITS" +Any ORed combination of the following values may be used for the +\fIflags\fR argument to procedures such as \fBTcl_EvalObjEx\fR: +.TP 23 +\fBTCL_EVAL_DIRECT\fR +This flag is only used by \fBTcl_EvalObjEx\fR; it is ignored by +other procedures. If this flag bit is set, the script is not +compiled to bytecodes; instead it is executed directly +as is done by \fBTcl_EvalEx\fR. The +\fBTCL_EVAL_DIRECT\fR flag is useful in situations where the +contents of an object are going to change immediately, so the +bytecodes won't be reused in a future execution. In this case, +it's faster to execute the script directly. +.TP 23 +\fBTCL_EVAL_GLOBAL\fR +If this flag is set, the script is processed at global level. This +means that it is evaluated in the global namespace and its variable +context consists of global variables only (it ignores any Tcl +procedures at are active). + +.SH "MISCELLANEOUS DETAILS" .PP During the processing of a Tcl command it is legal to make nested calls to evaluate other commands (this is how procedures and some control structures are implemented). If a code other than \fBTCL_OK\fR is returned -from a nested \fBTcl_Eval\fR invocation, +from a nested \fBTcl_EvalObjEx\fR invocation, then the caller should normally return immediately, passing that same return code back to its caller, and so on until the top-level application is reached. @@ -103,21 +179,18 @@ A few commands, like \fBfor\fR, will check for certain return codes, like \fBTCL_BREAK\fR and \fBTCL_CONTINUE\fR, and process them specially without returning. .PP -\fBTcl_Eval\fR keeps track of how many nested \fBTcl_Eval\fR +\fBTcl_EvalObjEx\fR keeps track of how many nested \fBTcl_EvalObjEx\fR invocations are in progress for \fIinterp\fR. If a code of \fBTCL_RETURN\fR, \fBTCL_BREAK\fR, or \fBTCL_CONTINUE\fR is -about to be returned from the topmost \fBTcl_Eval\fR +about to be returned from the topmost \fBTcl_EvalObjEx\fR invocation for \fIinterp\fR, it converts the return code to \fBTCL_ERROR\fR -and sets \fIinterp->result\fR -to point to an error message indicating that +and sets \fIinterp\fR's result to an error message indicating that the \fBreturn\fR, \fBbreak\fR, or \fBcontinue\fR command was invoked in an inappropriate place. This means that top-level applications should never see a return code -from \fBTcl_Eval\fR other then \fBTCL_OK\fR or \fBTCL_ERROR\fR. - -.SH "SEE ALSO" -Tcl_EvalObj, Tcl_GlobalEvalObj +from \fBTcl_EvalObjEx\fR other then \fBTCL_OK\fR or \fBTCL_ERROR\fR. +.VE .SH KEYWORDS -command, execute, file, global, object, object result, variable +execute, file, global, object, result, script diff --git a/doc/EvalObj.3 b/doc/EvalObj.3 deleted file mode 100644 index 9948196..0000000 --- a/doc/EvalObj.3 +++ /dev/null @@ -1,91 +0,0 @@ -'\" -'\" Copyright (c) 1996-1997 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: EvalObj.3,v 1.2 1998/09/14 18:39:48 stanton Exp $ -'\" -.so man.macros -.TH Tcl_EvalObj 3 8.0 Tcl "Tcl Library Procedures" -.BS -.SH NAME -Tcl_EvalObj, Tcl_GlobalEvalObj \- execute Tcl commands -.SH SYNOPSIS -.nf -\fB#include <tcl.h>\fR -.sp -int -\fBTcl_EvalObj\fR(\fIinterp, objPtr\fR) -.sp -int -\fBTcl_GlobalEvalObj\fR(\fIinterp, objPtr\fR) -.SH ARGUMENTS -.AS Tcl_Interp **termPtr; -.AP Tcl_Interp *interp in -Interpreter in which to execute the command. -The command's result will be stored in the interpreter's result object -and can be retrieved using \fBTcl_GetObjResult\fR. -.AP Tcl_Obj *objPtr in -A Tcl object containing a command string -(or sequence of commands in a string) to execute. -.BE - -.SH DESCRIPTION -.PP -These two procedures execute Tcl commands. -\fBTcl_EvalObj\fR is the core procedure -and is used by \fBTcl_GlobalEvalObj\fR. -It executes the commands in the script held by \fIobjPtr\fR -until either an error occurs or it reaches the end of the script. -If this is the first time \fIobjPtr\fR has been executed, -its commands are compiled into bytecode instructions -that are then executed if there are no compilation errors. -.PP -The return value from \fBTcl_EvalObj\fR is one of the Tcl return codes -\fBTCL_OK\fR, \fBTCL_ERROR\fR, \fBTCL_RETURN\fR, \fBTCL_BREAK\fR, or -\fBTCL_CONTINUE\fR, -and a result object containing additional information -(a result value or error message) -that can be retrieved using \fBTcl_GetObjResult\fR. -If an error occurs during compilation, this return information -describes the error. -Otherwise, this return information corresponds to the last command -executed from \fIobjPtr\fR. -.PP -\fBTcl_GlobalEvalObj\fR is similar to \fBTcl_EvalObj\fR except that it -processes the command at global level. -This means that the variable context for the command consists of -global variables only (it ignores any Tcl procedure that is active). -This produces an effect similar to the Tcl command ``\fBuplevel 0\fR''. -.PP -During the processing of a Tcl command it is legal to make nested -calls to evaluate other commands (this is how procedures and -some control structures are implemented). -If a code other than \fBTCL_OK\fR is returned -from a nested \fBTcl_EvalObj\fR invocation, -then the caller should normally return immediately, -passing that same return code back to its caller, -and so on until the top-level application is reached. -A few commands, like \fBfor\fR, will check for certain -return codes, like \fBTCL_BREAK\fR and \fBTCL_CONTINUE\fR, and process them -specially without returning. -.PP -\fBTcl_EvalObj\fR keeps track of how many nested \fBTcl_EvalObj\fR -invocations are in progress for \fIinterp\fR. -If a code of \fBTCL_RETURN\fR, \fBTCL_BREAK\fR, or \fBTCL_CONTINUE\fR is -about to be returned from the topmost \fBTcl_EvalObj\fR -invocation for \fIinterp\fR, -it converts the return code to \fBTCL_ERROR\fR -and sets the interpreter's result object -to point to an error message indicating that -the \fBreturn\fR, \fBbreak\fR, or \fBcontinue\fR command was -invoked in an inappropriate place. -This means that top-level applications should never see a return code -from \fBTcl_EvalObj\fR other then \fBTCL_OK\fR or \fBTCL_ERROR\fR. - -.SH "SEE ALSO" -Tcl_GetObjResult, Tcl_SetObjResult - -.SH KEYWORDS -command, execute, file, global, object, object result, variable @@ -4,13 +4,13 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: Exit.3,v 1.2 1998/09/14 18:39:48 stanton Exp $ +'\" RCS: @(#) $Id: Exit.3,v 1.3 1999/04/16 00:46:31 stanton Exp $ '\" .so man.macros -.TH Tcl_Exit 3 7.7 Tcl "Tcl Library Procedures" +.TH Tcl_Exit 3 8.1 Tcl "Tcl Library Procedures" .BS .SH NAME -Tcl_Exit, Tcl_Finalize, Tcl_CreateExitHandler, Tcl_DeleteExitHandler \- end the application (and invoke exit handlers) +Tcl_Exit, Tcl_Finalize, Tcl_FinalizeThread, Tcl_CreateExitHandler, Tcl_DeleteExitHandler, Tcl_CreateThreadExitHandler, Tcl_DeleteThreadExitHandler \- end the application or thread (and invoke exit handlers) .SH SYNOPSIS .nf \fB#include <tcl.h>\fR @@ -22,10 +22,19 @@ Tcl_Exit, Tcl_Finalize, Tcl_CreateExitHandler, Tcl_DeleteExitHandler \- end the \fBTcl_CreateExitHandler\fR(\fIproc, clientData\fR) .sp \fBTcl_DeleteExitHandler\fR(\fIproc, clientData\fR) +.sp +\fBTcl_ExitThread\fR(\fIstatus\fR) +.sp +\fBTcl_FinalizeThread\fR() +.sp +\fBTcl_CreateThreadExitHandler\fR(\fIproc, clientData\fR) +.sp +\fBTcl_DeleteThreadExitHandler\fR(\fIproc, clientData\fR) .SH ARGUMENTS .AS Tcl_ExitProc clientData .AP int status in -Provides information about why application exited. Exact meaning may +Provides information about why the application or thread exited. +Exact meaning may be platform-specific. 0 usually means a normal exit, any nonzero value usually means that an error occurred. .AP Tcl_ExitProc *proc in @@ -51,7 +60,6 @@ otherwise causes the application to terminate without calling \fBTcl_Exit\fR internally invokes the \fBexit\fR system call, thus it never returns control to its caller. .PP -.VS \fBTcl_Finalize\fR is similar to \fBTcl_Exit\fR except that it does not exit from the current process. It is useful for cleaning up when a process is finished using \fBTcl\fR but @@ -64,10 +72,20 @@ However, to ensure portability, your code should always invoke \fBTcl_Finalize\fR when \fBTcl\fR is being unloaded, to ensure that the code will work on all platforms. \fBTcl_Finalize\fR can be safely called more than once. +.PP +.VS +\fBTcl_ExitThread\fR is used to terminate the current thread and invoke +per-thread exit handlers. This finalization is done by +\fBTcl_FinalizeThread\fR, which you can call if you just want to clean +up per-thread state and invoke the thread exit handlers. +\fBTcl_Finalize\fR calls \fBTcl_FinalizeThread\fR for the current +thread automatically. .VE .PP \fBTcl_CreateExitHandler\fR arranges for \fIproc\fR to be invoked by \fBTcl_Finalize\fR and \fBTcl_Exit\fR. +\fBTcl_CreateThreadExitHandler\fR arranges for \fIproc\fR to be invoked +by \fBTcl_FinalizeThread\fR and \fBTcl_ExitThread\fR. This provides a hook for cleanup operations such as flushing buffers and freeing global memory. \fIProc\fR should match the type \fBTcl_ExitProc\fR: @@ -76,16 +94,18 @@ typedef void Tcl_ExitProc(ClientData \fIclientData\fR); .CE The \fIclientData\fR parameter to \fIproc\fR is a copy of the \fIclientData\fR argument given to -\fBTcl_CreateExitHandler\fR when the callback +\fBTcl_CreateExitHandler\fR or \fBTcl_CreateThreadExitHandler\fR when +the callback was created. Typically, \fIclientData\fR points to a data structure containing application-specific information about what to do in \fIproc\fR. .PP -\fBTcl_DeleteExitHandler\fR may be called to delete a +\fBTcl_DeleteExitHandler\fR and \fBTcl_DeleteThreadExitHandler\fR may be +called to delete a previously-created exit handler. It removes the handler indicated by \fIproc\fR and \fIclientData\fR so that no call to \fIproc\fR will be made. If no such handler exists then -\fBTcl_DeleteExitHandler\fR does nothing. +\fBTcl_DeleteExitHandler\fR or \fBTcl_DeleteThreadExitHandler\fR does nothing. .PP .VS .PP @@ -98,6 +118,14 @@ If extension \fBA\fR registers its exit handlers before loading extension \fBB\fR, this ensures that any exit handlers for \fBB\fR will be executed before the exit handlers for \fBA\fR. .VE +.VS +.PP +\fBTcl_Finalize\fR and \fBTcl_Exit\fR call \fBTcl_FinalizeThread\fR +and the thread exit handlers \fIafter\fR +the process-wide exit handlers. This is because thread finalization shuts +down the I/O channel system, so any attempt at I/O by the global exit +handlers will vanish into the bitbucket. +.VE .SH KEYWORDS -callback, cleanup, dynamic loading, end application, exit, unloading +callback, cleanup, dynamic loading, end application, exit, unloading, thread diff --git a/doc/GetCwd.3 b/doc/GetCwd.3 new file mode 100755 index 0000000..4c8d65d --- /dev/null +++ b/doc/GetCwd.3 @@ -0,0 +1,54 @@ +'\" +'\" Copyright (c) 1998-1999 Scriptics Corportation +'\" +'\" See the file "license.terms" for information on usage and redistribution +'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. +'\" +'\" RCS: @(#) $Id: GetCwd.3,v 1.2 1999/04/16 00:46:31 stanton Exp $ +'\" +.so man.macros +.TH Tcl_GetCwd 3 8.1 Tcl "Tcl Library Procedures" +.BS +.SH NAME +Tcl_GetCwd, Tcl_Chdir \- manipulate the current working directory +.SH SYNOPSIS +.nf +\fB#include <tcl.h>\fR +.sp +char * +\fBTcl_GetCwd\fR(\fIinterp\fR, \fIbufferPtr\fR) +.sp +int +\fBTcl_Chdir\fR(\fIpath\fR) +.SH ARGUMENTS +.AS Tcl_DString *bufferPtr +.AP Tcl_Interp *interp in +Interpreter in which to report an error, if any. +.AP Tcl_DString *bufferPtr in/out +This dynamic string is used to store the current working directory. +At the time of the call it should be uninitialized or free. The +caller must eventually call \fBTcl_DStringFree\fR to free up +anything stored here. +.AP char *path in +File path in UTF\-8 format. +.BE + +.SH DESCRIPTION +.PP +These procedures may be used to manipulate the current working +directory for the application. They provide C\-level access to +the same functionality as the Tcl \fBpwd\fR command. +.PP +\fBTcl_GetCwd\fR returns a pointer to a string specifying the current +directory, or NULL if the current directory could not be determined. +If NULL is returned, an error message is left in the interp's result. +Storage for the result string is allocated in bufferPtr; the caller +must call \fBTcl_DStringFree()\fR when the result is no longer needed. +The format of the path is UTF\-8. +.PP +\fBTcl_Chdir\fR changes the applications current working directory to +the value specified in \fIpath\fR. The format of the passed in string +must be UTF\-8. The function returns -1 on error or 0 on success. + +.SH KEYWORDS +pwd diff --git a/doc/GetIndex.3 b/doc/GetIndex.3 index 4cacdb2..342069a 100644 --- a/doc/GetIndex.3 +++ b/doc/GetIndex.3 @@ -4,10 +4,10 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: GetIndex.3,v 1.2 1998/09/14 18:39:48 stanton Exp $ +'\" RCS: @(#) $Id: GetIndex.3,v 1.3 1999/04/16 00:46:31 stanton Exp $ '\" .so man.macros -.TH Tcl_GetIndexFromObj 3 8.0 Tcl "Tcl Library Procedures" +.TH Tcl_GetIndexFromObj 3 8.1 Tcl "Tcl Library Procedures" .BS .SH NAME Tcl_GetIndexFromObj \- lookup string in table of keywords @@ -16,7 +16,14 @@ Tcl_GetIndexFromObj \- lookup string in table of keywords \fB#include <tcl.h>\fR .sp int -\fBTcl_GetIndexFromObj\fR(\fIinterp, objPtr, tablePtr, msg, flags, indexPtr\fR) +\fBTcl_GetIndexFromObj\fR(\fIinterp, objPtr, tablePtr, msg, flags, +indexPtr\fR) +.VS +.sp +int +\fBTcl_GetIndexFromObjStruct\fR(\fIinterp, objPtr, tablePtr, offset, +msg, flags, indexPtr\fR) +.VE .SH ARGUMENTS .AS Tcl_Interp **tablePtr .AP Tcl_Interp *interp in @@ -29,6 +36,11 @@ table entry. .AP char **tablePtr in An array of null-terminated strings. The end of the array is marked by a NULL string pointer. +.VS +.AP int offset in +The offset to add to tablePtr to get to the next string in the +list. The end of the array is marked by a NULL string pointer. +.VE .AP char *msg in Null-terminated string describing what is being looked up, such as \fBoption\fR. This string is included in error messages. @@ -68,7 +80,18 @@ is invoked again with the same \fIobjPtr\fR and \fItablePtr\fR arguments (e.g. during a reinvocation of a Tcl command), it returns the matching index immediately without having to redo the lookup operation. Note: \fBTcl_GetIndexFromObj\fR assumes that the entries -in \fItablePtr\fR are static: they must not change between invocations. +in \fItablePtr\fR are static: they must not change between +invocations. +.VS +.PP +\fBTcl_GetIndexFromObjStruct\fR works just like +\fBTcl_GetIndexFromObj\fR, except that instead of treating +\fItablePtr\fR as an array of string pointers, it treats it as the +first in a series of string ptrs that are spaced apart by \fIoffset\fR +bytes. This is particularly useful when processing things like +\fBTk_ConfigurationSpec\fR, whose string keys are in the same place in +each of several array elements. +.VE .SH "SEE ALSO" Tcl_WrongNumArgs diff --git a/doc/CrtVersion.3 b/doc/GetVersion.3 index 4333786..0b88dc5 100644..100755 --- a/doc/CrtVersion.3 +++ b/doc/GetVersion.3 @@ -4,7 +4,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: CrtVersion.3,v 1.2 1999/03/11 19:29:34 redman Exp $ +'\" RCS: @(#) $Id: GetVersion.3,v 1.2 1999/04/16 00:46:32 stanton Exp $ '\" .so man.macros .TH Tcl_GetVersion 3 7.5 Tcl "Tcl Library Procedures" @@ -15,7 +15,7 @@ Tcl_GetVersion \- get the version of the library at runtime .nf \fB#include <tcl.h>\fR .sp -\fBTcl_GetVersion\fR(\fmajor, minor, patchLevel, type\fR) +\fBTcl_GetVersion\fR(\fImajor, minor, patchLevel, type\fR) .SH ARGUMENTS .AP int *major out Major version number of the Tcl library. @@ -41,8 +41,8 @@ Use \fBTcl_GetVersion\fR to verify that fact, and possibly to change the behavior of your extension. .PP If may pass a NULL for any of the arguments. For instance if -you do not care about the \fIpatchLevel\fI of the library, pass -a NULL for the \fIpatchLevel\fI argument. +you do not care about the \fIpatchLevel\fR of the library, pass +a NULL for the \fIpatchLevel\fR argument. .SH KEYWORDS version, patchlevel, major, minor, alpha, beta, release diff --git a/doc/ObjSetVar.3 b/doc/ObjSetVar.3 deleted file mode 100644 index e34f9d3..0000000 --- a/doc/ObjSetVar.3 +++ /dev/null @@ -1,162 +0,0 @@ -'\" -'\" Copyright (c) 1996-1997 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: ObjSetVar.3,v 1.2 1998/09/14 18:39:49 stanton Exp $ -'\" -.so man.macros -.TH Tcl_ObjSetVar2 3 8.0 Tcl "Tcl Library Procedures" -.BS -.SH NAME -Tcl_ObjSetVar2, Tcl_ObjGetVar2 \- manipulate Tcl variables -.SH SYNOPSIS -.nf -\fB#include <tcl.h>\fR -.sp -Tcl_Obj * -\fBTcl_ObjSetVar2\fR(\fIinterp, part1Ptr, part2Ptr, newValuePtr, flags\fR) -.sp -Tcl_Obj * -\fBTcl_ObjGetVar2\fR(\fIinterp, part1Ptr, part2Ptr, flags\fR) -.SH ARGUMENTS -.AS Tcl_Interp *newValuePtr -.AP Tcl_Interp *interp in -Interpreter containing variable. -.AP Tcl_Obj *part1Ptr in -Points to a Tcl object containing the variable's name. -The name may include a series of \fB::\fR namespace qualifiers -to specify a variable in a particular namespace. -May refer to a scalar variable or an element of an array variable. -.AP Tcl_Obj *part2Ptr in -If non-NULL, points to an object containing the name of an element -within an array and \fIpart1Ptr\fR must refer to an array variable. -.AP Tcl_Obj *newValuePtr in -Points to a Tcl object containing the new value for the variable. -.AP int flags in -OR-ed combination of bits providing additional information for -operation. See below for valid values. -.BE - -.SH DESCRIPTION -.PP -These two procedures may be used to read and modify -Tcl variables from C code. -\fBTcl_ObjSetVar2\fR will create a new variable or modify an existing one. -It sets the specified variable to -the object referenced by \fInewValuePtr\fR -and returns a pointer to the object which is the variable's new value. -The returned object may not be the same one -referenced by \fInewValuePtr\fR; -this might happen because variable traces may modify the variable's value. -The reference count for the variable's old value is decremented -and the reference count for its new value is incremented. -If the new value for the variable -is not the same one referenced by \fInewValuePtr\fR -(perhaps as a result of a variable trace), -then \fInewValuePtr\fR's reference count is left unchanged. -The reference count for the returned object is not incremented -to reflect the returned reference. -If the caller needs to keep a reference to the object, -say in a data structure, -it must increment its reference count using \fBTcl_IncrRefCount\fR. -If an error occurs in setting the variable -(e.g. an array variable is referenced -without giving an index into the array), -then NULL is returned. -.PP -The variable name specified to \fBTcl_ObjSetVar2\fR consists of two parts. -\fIpart1Ptr\fR contains the name of a scalar or array variable. -If \fIpart2Ptr\fR is NULL, the variable must be a scalar. -If \fIpart2Ptr\fR is not NULL, -it contains the name of an element in the array named by \fIpart2Ptr\fR. -As a special case, if the flag TCL_PARSE_PART1 is specified, -\fIpart1Ptr\fR may contain both an array and an element name: -if the name contains an open parenthesis and ends with a -close parenthesis, then the value between the parentheses is -treated as an element name (which can have any string value) and -the characters before the first open -parenthesis are treated as the name of an array variable. -If the flag TCL_PARSE_PART1 is given, -\fIpart2Ptr\fR should be NULL since the array and element names -are taken from \fIpart2Ptr\fR. -.PP -The \fIflags\fR argument may be used to specify any of several -options to the procedures. -It consists of an OR-ed combination of any of the following -bits: -.TP -\fBTCL_GLOBAL_ONLY\fR -Under normal circumstances the procedures look up variables as follows: -If a procedure call is active in \fIinterp\fR, -a variable is looked up at the current level of procedure call. -Otherwise, a variable is looked up first in the current namespace, -then in the global namespace. -However, if this bit is set in \fIflags\fR then the variable -is looked up only in the global namespace -even if there is a procedure call active. -If both \fBTCL_GLOBAL_ONLY\fR and \fBTCL_NAMESPACE_ONLY\fR are given, -\fBTCL_GLOBAL_ONLY\fR is ignored. -.TP -\fBTCL_NAMESPACE_ONLY\fR -Under normal circumstances the procedures look up variables as follows: -If a procedure call is active in \fIinterp\fR, -a variable is looked up at the current level of procedure call. -Otherwise, a variable is looked up first in the current namespace, -then in the global namespace. -However, if this bit is set in \fIflags\fR then the variable -is looked up only in the current namespace -even if there is a procedure call active. -.TP -\fBTCL_LEAVE_ERR_MSG\fR -If an error is returned and this bit is set in \fIflags\fR, then -an error message will be left in the interpreter's result, -where it can be retrieved with \fBTcl_GetObjResult\fR -or \fBTcl_GetStringResult\fR. -If this flag bit isn't set then no error message is left -and the interpreter's result will not be modified. -.TP -\fBTCL_APPEND_VALUE\fR -If this bit is set then \fInewValuePtr\fR is appended to the current -value, instead of replacing it. -If the variable is currently undefined, then this bit is ignored. -.TP -\fBTCL_LIST_ELEMENT\fR -If this bit is set, then \fInewValuePtr\fR is converted to a valid -Tcl list element before setting (or appending to) the variable. -A separator space is appended before the new list element unless -the list element is going to be the first element in a list or -sublist (i.e. the variable's current value is empty, or contains -the single character ``{'', or ends in `` }''). -.TP -\fBTCL_PARSE_PART1\fR -If this bit is set, -then \fBTcl_ObjGetVar2\fR and \fBTcl_ObjSetVar2\fR -will parse \fIpart1Ptr\fR -to obtain both an array name and an element name. -If the name in \fIpart1Ptr\fR contains an open parenthesis -and ends with a close parenthesis, -the name is treated as the name of an element of an array; -otherwise, the name in \fIpart1Ptr\fR -is interpreted as the name of a scalar variable. -When this bit is set, -\fIpart2Ptr\fR is ignored. -.PP -\fBTcl_ObjGetVar2\fR returns the value of the specified variable. -Its arguments are treated the same way as those for \fBTcl_ObjSetVar2\fR. -It returns a pointer to the object which is the variable's value. -The reference count for the returned object is not incremented. -If the caller needs to keep a reference to the object, -say in a data structure, -it must increment the reference count using \fBTcl_IncrRefCount\fR. -If an error occurs in setting the variable -(e.g. an array variable is referenced -without giving an index into the array), -then NULL is returned. - -.SH "SEE ALSO" -Tcl_GetObjResult, Tcl_GetStringResult, Tcl_GetVar, Tcl_GetVar2, Tcl_SetVar, Tcl_SetVar2, Tcl_TraceVar, Tcl_UnsetVar, Tcl_UnsetVar2 - -.SH KEYWORDS -array, interpreter, object, scalar, set, unset, variable diff --git a/doc/Object.3 b/doc/Object.3 index da9c3cd..214695f 100644 --- a/doc/Object.3 +++ b/doc/Object.3 @@ -4,7 +4,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: Object.3,v 1.2 1998/09/14 18:39:49 stanton Exp $ +'\" RCS: @(#) $Id: Object.3,v 1.3 1999/04/16 00:46:32 stanton Exp $ '\" .so man.macros .TH Tcl_Obj 3 8.0 Tcl "Tcl Library Procedures" @@ -85,7 +85,7 @@ Because of this representation invalidation and regeneration, it is dangerous for extension writers to access \fBTcl_Obj\fR fields directly. It is better to access Tcl_Obj information using -procedures like \fBTcl_GetStringFromObj\fR. +procedures like \fBTcl_GetStringFromObj\fR and \fBTcl_GetString\fR. .PP Objects are allocated on the heap and are referenced using a pointer to their \fBTcl_Obj\fR structure. @@ -138,7 +138,7 @@ The byte array must always have a null after the last byte, at offset \fIlength\fR; this allows string representations that do not contain nulls to be treated as conventional null-terminated C strings. -C programs use \fBTcl_GetStringFromObj\fR to get +C programs use \fBTcl_GetStringFromObj\fR and \fBTcl_GetString\fR to get an object's string representation. If \fIbytes\fR is NULL, the string representation is invalid. @@ -177,7 +177,8 @@ An object typically starts out containing only a string representation: it is untyped and has a NULL \fItypePtr\fR. An object containing an empty string or a copy of a specified string is created using \fBTcl_NewObj\fR or \fBTcl_NewStringObj\fR respectively. -An object's string value is gotten with \fBTcl_GetStringFromObj\fR +An object's string value is gotten with +\fBTcl_GetStringFromObj\fR or \fBTcl_GetString\fR and changed with \fBTcl_SetStringObj\fR. If the object is later passed to a procedure like \fBTcl_GetIntFromObj\fR that requires a specific internal representation, @@ -187,7 +188,7 @@ An object's two representations are duals of each other: changes made to one are reflected in the other. For example, \fBTcl_ListObjReplace\fR will modify an object's internal representation and the next call to \fBTcl_GetStringFromObj\fR -will reflect that change. +or \fBTcl_GetString\fR will reflect that change. .PP Representations are recomputed lazily for efficiency. A change to one representation made by a procedure @@ -208,7 +209,7 @@ free any storage associated with the old string representation. Objects usually remain one type over their life, but occasionally an object must be converted from one type to another. For example, a C program might build up a string in an object -with repeated calls to \fBTcl_StringObjAppend\fR, +with repeated calls to \fBTcl_AppendToObj\fR, and then call \fBTcl_ListObjIndex\fR to extract a list element from the object. The same object holding the same string value diff --git a/doc/OpenFileChnl.3 b/doc/OpenFileChnl.3 index c0d121c..e9205e3 100644 --- a/doc/OpenFileChnl.3 +++ b/doc/OpenFileChnl.3 @@ -4,13 +4,13 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: OpenFileChnl.3,v 1.2 1998/09/14 18:39:49 stanton Exp $ +'\" RCS: @(#) $Id: OpenFileChnl.3,v 1.3 1999/04/16 00:46:32 stanton Exp $ .so man.macros -.TH Tcl_OpenFileChannel 3 8.0 Tcl "Tcl Library Procedures" +.TH Tcl_OpenFileChannel 3 8.1 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_RegisterChannel, Tcl_UnregisterChannel, Tcl_Close, Tcl_Read, Tcl_Gets, Tcl_Write, Tcl_Flush, Tcl_Seek, Tcl_Tell, Tcl_Eof, Tcl_InputBlocked, Tcl_InputBuffered, Tcl_GetChannelOption, Tcl_SetChannelOption \- buffered I/O facilities using channels +Tcl_OpenFileChannel, Tcl_OpenCommandChannel, Tcl_MakeFileChannel, Tcl_GetChannel, Tcl_RegisterChannel, Tcl_UnregisterChannel, 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, \- buffered I/O facilities using channels .SH SYNOPSIS .nf \fB#include <tcl.h>\fR @@ -22,7 +22,7 @@ Tcl_Channel .sp Tcl_Channel \fBTcl_OpenCommandChannel\fR(\fIinterp, argc, argv, flags\fR) -.VS +.VS 8.0 .sp Tcl_Channel \fBTcl_MakeFileChannel\fR(\fIhandle, readOrWrite\fR) @@ -40,17 +40,28 @@ int int \fBTcl_Close\fR(\fIinterp, channel\fR) .sp +.VS 8.1 int -\fBTcl_Read\fR(\fIchannel, buf, toRead\fR) +\fBTcl_ReadChars\fR(\fIchannel, readObjPtr, charsToRead, appendFlag\fR) .sp int -\fBTcl_Gets\fR(\fIchannel, lineRead\fR) +\fBTcl_Read\fR(\fIchannel, byteBuf, bytesToRead\fR) .sp int \fBTcl_GetsObj\fR(\fIchannel, lineObjPtr\fR) .sp int -\fBTcl_Write\fR(\fIchannel, buf, toWrite\fR) +\fBTcl_Gets\fR(\fIchannel, lineRead\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 .sp int \fBTcl_Flush\fR(\fIchannel\fR) @@ -83,37 +94,36 @@ Used for error reporting and to look up a channel registered in it. .AP char *fileName in The name of a local or network file. .AP 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. -For \fBTcl_OpenCommandChannel\fR, may be NULL. +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. For +\fBTcl_OpenCommandChannel\fR, may be NULL. .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. +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 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. +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. -.VS +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. +.VS 8.0 .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 char *channelName in +The name of the channel. .VE .AP int *modePtr out Points at an integer variable that will receive an OR-ed combination of @@ -122,26 +132,40 @@ open for reading and writing. .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. -.AP char *buf in -An array of bytes in which to store channel input, or from which -to read channel output. -.AP int len in -The length of the input or output. -.AP int atEnd in -If nonzero, store the input at the end of the input queue, otherwise store -it at the head of the input queue. -.AP int toRead in -The number of bytes to read from the channel. -.AP Tcl_DString *lineRead in -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. -.AP Tcl_Obj *linePtrObj in +.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 int toWrite in -The number of bytes to read from \fIbuf\fR and output to the channel. +.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. +.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 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 int 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 @@ -169,7 +193,7 @@ 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 modelled after +channel mechanism provides a buffering scheme modeled after Unix's standard I/O, and it also allows for nonblocking I/O on channels. .PP @@ -182,7 +206,7 @@ channels, see the manual entry for \fBTcl_CreateChannel\fR. .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 modelled after the \fBfopen\fR procedure of +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. @@ -190,7 +214,7 @@ 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->result\fR after any error. +leaves an error message in \fIinterp\fR's result after any error. .PP The newly created channel is not registered in the supplied interpreter; to register it, use \fBTcl_RegisterChannel\fR, described below. @@ -310,93 +334,136 @@ left in \fIinterp->result\fR. .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. +\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. -.SH TCL_READ -.PP -\fBTcl_Read\fR consumes up to \fItoRead\fR bytes of data from -\fIchannel\fR and stores it at \fIbuf\fR. -The return value of \fBTcl_Read\fR is the number of characters written -at \fIbuf\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. -If an error occurs, the return value is -1 and \fBTcl_Read\fR records -a POSIX error code that can be retrieved with \fBTcl_GetErrno\fR. -.PP -The return value may be smaller than the value of \fItoRead\fR, indicating -that less data than requested was available, also 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_Read\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_Read\fR translates platform-specific 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. +.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 \fIobjPtr\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 +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 +\fIbuf\fR, performing end-of-line translations on the way. The return value +of \fBTcl_Read\fR is the number of bytes, up to \fItoRead\fR, written in +\fIbuf\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. -.SH TCL_GETS AND TCL_GETSOBJ -.PP -\fBTcl_Gets\fR reads a line of input from a channel and appends all of -the characters of the line except for the terminating end-of-line character(s) -to the dynamic string given by \fIdsPtr\fR. -The end-of-line character(s) are read and discarded. +.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 appended to the dynamic string given by +\fIdsPtr\fR rather than a Tcl object. + +.SH TCL_WRITECHARS, TCL_WRITEOBJ, AND TCL_WRITE .PP -If a line was successfully read, the return value is greater than or -equal to zero, and it indicates the number of characters stored -in the dynamic string. -If an error occurs, \fBTcl_Gets\fR returns -1 and records a POSIX error -code that can be retrieved with \fBTcl_GetErrno\fR. -\fBTcl_Gets\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_GetsObj\fR is the same as \fBTcl_Gets\fR except the resulting -characters are appended to a Tcl object \fBlineObjPtr\fR rather than a -dynamic string. -.SH TCL_WRITE -.PP -\fBTcl_Write\fR accepts \fItoWrite\fR bytes of data at \fIbuf\fR for output -on \fIchannel\fR. This data may not appear on the output device -immediately. If the data should appear immediately, call \fBTcl_Flush\fR -after the call to \fBTcl_Write\fR, or set the \fB-buffering\fR option on -the channel to \fBnone\fR. If you wish the data to appear as soon as an end -of line is accepted for output, set the \fB\-buffering\fR option on the -channel to \fBline\fR mode. -.PP -The \fItoWrite\fR argument specifies how many bytes of data are provided in -the \fIbuf\fR argument. If it is negative, \fBTcl_Write\fR expects the data +\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 -The return value of \fBTcl_Write\fR is a count of how many -characters were accepted for output to the channel. This is either equal to -\fItoWrite\fR or -1 to indicate that an error occurred. -If an error occurs, \fBTcl_Write\fR also records a POSIX error code -that may be retrieved with \fBTcl_GetErrno\fR. +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. +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. +.VE .SH TCL_FLUSH .PP @@ -419,14 +486,14 @@ 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 +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. +value is \-1 if the channel does not support seeking. .SH TCL_GETCHANNELOPTION .PP @@ -477,7 +544,7 @@ The call always returns zero if the channel is in blocking mode. buffered in the internal buffers for a channel. If the channel is not open for reading, this function always returns zero. -.VS +.VS 8.0 .SH "PLATFORM ISSUES" .PP The handles returned from \fBTcl_GetChannelHandle\fR depend on the diff --git a/doc/ParseCmd.3 b/doc/ParseCmd.3 new file mode 100644 index 0000000..2a180a6 --- /dev/null +++ b/doc/ParseCmd.3 @@ -0,0 +1,426 @@ +'\" +'\" 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: ParseCmd.3,v 1.2 1999/04/16 00:46:32 stanton Exp $ +'\" +.so man.macros +.TH Tcl_ParseCommand 3 8.1 Tcl "Tcl Library Procedures" +.BS +.SH NAME +Tcl_ParseCommand, Tcl_ParseExpr, Tcl_ParseBraces, Tcl_ParseQuotedString, Tcl_ParseVarName, Tcl_FreeParse, Tcl_EvalTokens \- parse Tcl scripts and expressions +.SH SYNOPSIS +.nf +\fB#include <tcl.h>\fR +.sp +int +\fBTcl_ParseCommand\fR(\fIinterp, string, numBytes, nested, parsePtr\fR) +.sp +int +\fBTcl_ParseExpr\fR(\fIinterp, string, numBytes, parsePtr\fR) +.sp +int +\fBTcl_ParseBraces\fR(\fIinterp, string, numBytes, parsePtr, append, termPtr\fR) +.sp +int +\fBTcl_ParseQuotedString\fR(\fIinterp, string, numBytes, parsePtr, append, termPtr\fR) +.sp +int +\fBTcl_ParseVarName\fR(\fIinterp, string, numBytes, parsePtr, append\fR) +.sp +\fBTcl_FreeParse\fR(\fIusedParsePtr\fR) +.sp +Tcl_Obj * +\fBTcl_EvalTokens\fR(\fIinterp, tokenPtr, numTokens\fR) +.SH ARGUMENTS +.AS Tcl_Interp *usedParsePtr +.AP Tcl_Interp *interp out +For procedures other than \fBTcl_FreeParse\fR and \fBTcl_EvalTokens\fR, +used only for error reporting; +if NULL, then no error messages are left after errors. +For \fBTcl_EvalTokens\fR, determines the context for evaluating the +script and also is used for error reporting; must not be NULL. +.AP char *string in +Pointer to first character in string to parse. +.AP int numBytes in +Number of bytes in \fIstring\fR, not including any terminating null +character. If less than 0 then the script consists of all characters +in \fIstring\fR up to the first null character. +.AP int nested in +Non-zero means that the script is part of a command substitution so an +unquoted close bracket should be treated as a command terminator. If zero, +close brackets have no special meaning. +.AP int append in +Non-zero means that \fI*parsePtr\fR already contains valid tokens; the new +tokens should be appended to those already present. Zero means that +\fI*parsePtr\fR is uninitialized; any information in it is ignored. +This argument is normally 0. +.AP Tcl_Parse *parsePtr out +Points to structure to fill in with information about the parsed +command, expression, variable name, etc. +Any previous information in this structure +is ignored, unless \fIappend\fR is non-zero in a call to +\fBTcl_ParseBraces\fR, \fBTcl_ParseQuotedString\fR, +or \fBTcl_ParseVarName\fR. +.AP char **termPtr out +If not NULL, points to a location where +\fBTcl_ParseBraces\fR and \fBTcl_ParseQuotedString\fR +will store a pointer to the character +just after the terminating close-brace or close-quote (respectively) +if the parse was successful. +.AP Tcl_Parse *usedParsePtr in +Points to structure that was filled in by a previous call to +\fBTcl_ParseCommand\fR, \fBTcl_ParseExpr\fR, \fBTcl_ParseVarName\fR, etc. +.BE + +.SH DESCRIPTION +.PP +These procedures parse Tcl commands or portions of Tcl commands such as +expressions or references to variables. +Each procedure takes a pointer to a script (or portion thereof) +and fills in the structure pointed to by \fIparsePtr\fR +with a collection of tokens describing the information that was parsed. +The procedures normally return \fBTCL_OK\fR. +However, if an error occurs then they return \fBTCL_ERROR\fR, +leave an error message in \fIinterp's\fR result +(if \fIinterp\fR is not NULL), +and leave nothing in \fIparsePtr\fR. +.PP +\fBTcl_ParseCommand\fR is a procedure that parses Tcl +scripts. Given a pointer to a script, it +parses the first command from the script. If the command was parsed +successfully, \fBTcl_ParseCommand\fR returns \fBTCL_OK\fR and fills in the +structure pointed to by \fIparsePtr\fR with information about the +structure of the command (see below for details). +If an error occurred in parsing the command then +\fBTCL_ERROR\fR is returned, an error message is left in \fIinterp\fR's +result, and no information is left at \fI*parsePtr\fR. +.PP +\fBTcl_ParseExpr\fR parses Tcl expressions. +Given a pointer to a script containing an expression, +\fBTcl_ParseCommand\fR parses the expression. +If the expression was parsed successfully, +\fBTcl_ParseExpr\fR returns \fBTCL_OK\fR and fills in the +structure pointed to by \fIparsePtr\fR with information about the +structure of the expression (see below for details). +If an error occurred in parsing the command then +\fBTCL_ERROR\fR is returned, an error message is left in \fIinterp\fR's +result, and no information is left at \fI*parsePtr\fR. +.PP +\fBTcl_ParseBraces\fR parses a string or command argument +enclosed in braces such as +\fB{hello}\fR or \fB{string \\t with \\t tabs}\fR +from the beginning of its argument \fIstring\fR. +The first character of \fIstring\fR must be \fB{\fR. +If the braced string was parsed successfully, +\fBTcl_ParseBraces\fR returns \fBTCL_OK\fR, +fills in the structure pointed to by \fIparsePtr\fR +with information about the structure of the string +(see below for details), +and stores a pointer to the character just after the terminating \fB}\fR +in the location given by \fI*termPtr\fR. +If an error occurrs while parsing the string +then \fBTCL_ERROR\fR is returned, +an error message is left in \fIinterp\fR's result, +and no information is left at \fI*parsePtr\fR or \fI*termPtr\fR. +.PP +\fBTcl_ParseQuotedString\fR parses a double-quoted string such as +\fB"sum is [expr $a+$b]"\fR +from the beginning of the argument \fIstring\fR. +The first character of \fIstring\fR must be \fB"\fR. +If the double-quoted string was parsed successfully, +\fBTcl_ParseQuotedString\fR returns \fBTCL_OK\fR, +fills in the structure pointed to by \fIparsePtr\fR +with information about the structure of the string +(see below for details), +and stores a pointer to the character just after the terminating \fB"\fR +in the location given by \fI*termPtr\fR. +If an error occurrs while parsing the string +then \fBTCL_ERROR\fR is returned, +an error message is left in \fIinterp\fR's result, +and no information is left at \fI*parsePtr\fR or \fI*termPtr\fR. +.PP +\fBTcl_ParseVarName\fR parses a Tcl variable reference such as +\fB$abc\fR or \fB$x([expr $index + 1])\fR from the beginning of its +\fIstring\fR argument. +The first character of \fIstring\fR must be \fB$\fR. +If a variable name was parsed successfully, \fBTcl_ParseVarName\fR +returns \fBTCL_OK\fR and fills in the structure pointed to by +\fIparsePtr\fR with information about the structure of the variable name +(see below for details). If an error +occurrs while parsing the command then \fBTCL_ERROR\fR is returned, an +error message is left in \fIinterp\fR's result (if \fIinterp\fR isn't +NULL), and no information is left at \fI*parsePtr\fR. +.PP +The information left at \fI*parsePtr\fR +by \fBTcl_ParseCommand\fR, \fBTcl_ParseExpr\fR, \fBTcl_ParseBraces\fR, +\fBTcl_ParseQuotedString\fR, and \fBTcl_ParseVarName\fR +may include dynamically allocated memory. +If these five parsing procedures return \fBTCL_OK\fR +then the caller must invoke \fBTcl_FreeParse\fR to release +the storage at \fI*parsePtr\fR. +These procedures ignore any existing information in +\fI*parsePtr\fR (unless \fIappend\fR is non-zero), +so if repeated calls are being made to any of them +then \fBTcl_FreeParse\fR must be invoked once after each call. +.PP +\fBTcl_EvalTokens\fR evaluates a sequence of parse tokens from a Tcl_Parse +structure. The tokens typically consist +of all the tokens in a word or all the tokens that make up the index for +a reference to an array variable. \fBTcl_EvalTokens\fR performs the +substitutions requested by the tokens, concatenates the +resulting values, and returns the result in a new Tcl_Obj. The +reference count of the object returned as result has been +incremented, so the caller must +invoke \fBTcl_DecrRefCount\fR when it is finished with the object. +If an error occurs while evaluating the tokens (such as a reference to +a non-existent variable) then the return value is NULL and an error +message is left in \fIinterp\fR's result. + +.SH TCL_PARSE STRUCTURE +.PP +\fBTcl_ParseCommand\fR, \fBTcl_ParseExpr\fR, \fBTcl_ParseBraces\fR, +\fBTcl_ParseQuotedString\fR, and \fBTcl_ParseVarName\fR +return parse information in two data structures, Tcl_Parse and Tcl_Token: +.CS +typedef struct Tcl_Parse { + char *\fIcommentStart\fR; + int \fIcommentSize\fR; + char *\fIcommandStart\fR; + int \fIcommandSize\fR; + int \fInumWords\fR; + Tcl_Token *\fItokenPtr\fR; + int \fInumTokens\fR; + ... +} Tcl_Parse; + +typedef struct Tcl_Token { + int \fItype\fR; + char *\fIstart\fR; + int \fIsize\fR; + int \fInumComponents\fR; +} Tcl_Token; +.CE +.PP +The first five fields of a Tcl_Parse structure +are filled in only by \fBTcl_ParseCommand\fR. +These fields are not used by the other parsing procedures. +.PP +\fBTcl_ParseCommand\fR fills in a Tcl_Parse structure +with information that describes one Tcl command and any comments that +precede the command. +If there are comments, +the \fIcommentStart\fR field points to the \fB#\fR character that begins +the first comment and \fIcommentSize\fR indicates the number of bytes +in all of the comments preceding the command, including the newline +character that terminates the last comment. +If the command is not preceded by any comments, \fIcommentSize\fR is 0. +\fBTcl_ParseCommand\fR also sets the \fIcommandStart\fR field +to point to the first character of the first +word in the command (skipping any comments and leading space) and +\fIcommandSize\fR gives the total number of bytes in the command, +including the character pointed to by \fIcommandStart\fR up to and +including the newline, close bracket, or semicolon character that +terminates the command. The \fInumWords\fR field gives the +total number of words in the command. +.PP +All parsing procedures set the remaining fields, +\fItokenPtr\fR and \fInumTokens\fR. +The \fItokenPtr\fR field points to the first in an array of Tcl_Token +structures that describe the components of the entity being parsed. +The \fInumTokens\fR field gives the total number of tokens +present in the array. +Each token contains four fields. +The \fItype\fR field selects one of several token types +that are described below. The \fIstart\fR field +points to the first character in the token and the \fIsize\fR field +gives the total number of characters in the token. Some token types, +such as \fBTCL_TOKEN_WORD\fR and \fBTCL_TOKEN_VARIABLE\fR, consist of +several component tokens, which immediately follow the parent token; +the \fInumComponents\fR field describes how many of these there are. +The \fItype\fR field has one of the following values: +.TP 20 +\fBTCL_TOKEN_WORD\fR +This token ordinarily describes one word of a command +but it may also describe a quoted or braced string in an expression. +The token describes a component of the script that is +the result of concatenating together a sequence of subcomponents, +each described by a separate subtoken. +The token starts with the first non-blank +character of the component (which may be a double-quote or open brace) +and includes all characters in the component up to but not including the +space, semicolon, close bracket, close quote, or close brace that +terminates the component. The \fInumComponents\fR field counts the total +number of sub-tokens that make up the word, including sub-tokens +of \fBTCL_TOKEN_VARIABLE\fR and \fBTCL_TOKEN_BS\fR tokens. +.TP +\fBTCL_TOKEN_SIMPLE_WORD\fR +This token has the same meaning as \fBTCL_TOKEN_WORD\fR, except that +the word is guaranteed to consist of a single \fBTCL_TOKEN_TEXT\fR +sub-token. The \fInumComponents\fR field is always 1. +.TP +\fBTCL_TOKEN_TEXT\fR +The token describes a range of literal text that is part of a word. +The \fInumComponents\fR field is always 0. +.TP +\fBTCL_TOKEN_BS\fR +The token describes a backslash sequence such as \fB\en\fR or \fB\e0xa3\fR. +The \fInumComponents\fR field is always 0. +.TP +\fBTCL_TOKEN_COMMAND\fR +The token describes a command whose result result must be substituted into +the word. The token includes the square brackets that surround the +command. The \fInumComponents\fR field is always 0 (the nested command +is not parsed; call \fBTcl_ParseCommand\fR recursively if you want to +see its tokens). +.TP +\fBTCL_TOKEN_VARIABLE\fR +The token describes a variable substitution, including the +\fB$\fR, variable name, and array index (if there is one) up through the +close parenthesis that terminates the index. This token is followed +by one or more additional tokens that describe the variable name and +array index. If \fInumComponents\fR is 1 then the variable is a +scalar and the next token is a \fBTCL_TOKEN_TEXT\fR token that gives the +variable name. If \fInumComponents\fR is greater than 1 then the +variable is an array: the first sub-token is a \fBTCL_TOKEN_TEXT\fR +token giving the array name and the remaining sub-tokens are +\fBTCL_TOKEN_TEXT\fR, \fBTCL_TOKEN_BS\fR, \fBTCL_TOKEN_COMMAND\fR, and +\fBTCL_TOKEN_VARIABLE\fR tokens that must be concatenated to produce the +array index. The \fInumComponents\fR field includes nested sub-tokens +that are part of \fBTCL_TOKEN_VARIABLE\fR tokens in the array index. +.TP +\fBTCL_TOKEN_SUB_EXPR\fR +The token describes one subexpression of an expression +(or an entire expression). +A subexpression may consist of a value +such as an integer literal, variable substitution, +or parenthesized subexpression; +it may also consist of an operator and its operands. +The token starts with the first non-blank character of the subexpression +up to but not including the space, brace, close-paren, or bracket +that terminates the subexpression. +This token is followed by one or more additional tokens +that describe the subexpression. +If the first sub-token after the \fBTCL_TOKEN_SUB_EXPR\fR token +is a \fBTCL_TOKEN_OPERATOR\fR token, +the subexpression consists of an operator and its token operands. +If the operator has no operands, the subexpression consists of +just the \fBTCL_TOKEN_OPERATOR\fR token. +Each operand is described by a \fBTCL_TOKEN_SUB_EXPR\fR token. +Otherwise, the subexpression is a value described by +one of the token types \fBTCL_TOKEN_WORD\fR, \fBTCL_TOKEN_TEXT\fR, +\fBTCL_TOKEN_BS\fR, \fBTCL_TOKEN_COMMAND\fR, +\fBTCL_TOKEN_VARIABLE\fR, and \fBTCL_TOKEN_SUB_EXPR\fR. +The \fInumComponents\fR field +counts the total number of sub-tokens that make up the subexpression; +this includes the sub-tokens for any nested \fBTCL_TOKEN_SUB_EXPR\fR tokens. +.TP +\fBTCL_TOKEN_OPERATOR\fR +The token describes one operator of an expression +such as \fB&&\fR or \fBhypot\fR. +An \fBTCL_TOKEN_OPERATOR\fR token is always preceeded by a +\fBTCL_TOKEN_SUB_EXPR\fR token +that describes the operator and its operands; +the \fBTCL_TOKEN_SUB_EXPR\fR token's \fInumComponents\fR field +can be used to determine the number of operands. +A binary operator such as \fB*\fR +is followed by two \fBTCL_TOKEN_SUB_EXPR\fR tokens +that describe its operands. +A unary operator like \fB-\fR +is followed by a single \fBTCL_TOKEN_SUB_EXPR\fR token +for its operand. +If the operator is a math function such as \fBlog10\fR, +the \fBTCL_TOKEN_OPERATOR\fR token will give its name and +the following \fBTCL_TOKEN_SUB_EXPR\fR tokens will describe +its operands; +if there are no operands (as with \fBrand\fR), +no \fBTCL_TOKEN_SUB_EXPR\fR tokens follow. +There is one trinary operator, \fB?\fR, +that appears in if-then-else subexpressions +such as \fIx\fB?\fIy\fB:\fIz\fR; +in this case, the \fB?\fR \fBTCL_TOKEN_OPERATOR\fR token +is followed by three \fBTCL_TOKEN_SUB_EXPR\fR tokens for the operands +\fIx\fR, \fIy\fR, and \fIz\fR. +The \fInumComponents\fR field for a \fBTCL_TOKEN_OPERATOR\fR token +is always 0. +.PP +After \fBTcl_ParseCommand\fR returns, the first token pointed to by +the \fItokenPtr\fR field of the +Tcl_Parse structure always has type \fBTCL_TOKEN_WORD\fR or +\fBTCL_TOKEN_SIMPLE_WORD\fR. It is followed by the sub-tokens +that must be concatenated to produce the value of that word. +The next token is the \fBTCL_TOKEN_WORD\fR or \fBTCL_TOKEN_SIMPLE_WORD\fR +token for the second word, followed by sub-tokens for that +word, and so on until all \fInumWords\fR have been accounted +for. +.PP +After \fBTcl_ParseExpr\fR returns, the first token pointed to by +the \fItokenPtr\fR field of the +Tcl_Parse structure always has type \fBTCL_TOKEN_SUB_EXPR\fR. +It is followed by the sub-tokens that must be evaluated +to produce the value of the expression. +Only the token information in the Tcl_Parse structure +is modified: the \fIcommentStart\fR, \fIcommentSize\fR, +\fIcommandStart\fR, and \fIcommandSize\fR fields are not modified +by \fBTcl_ParseExpr\fR. +.PP +After \fBTcl_ParseBraces\fR returns, +the array of tokens pointed to by the \fItokenPtr\fR field of the +Tcl_Parse structure will contain a single \fBTCL_TOKEN_TEXT\fR token +if the braced string does not contain any backslash-newlines. +If the string does contain backslash-newlines, +the array of tokens will contain one or more +\fBTCL_TOKEN_TEXT\fR or \fBTCL_TOKEN_BS\fR sub-tokens +that must be concatenated to produce the value of the string. +If the braced string was just \fB{}\fR +(that is, the string was empty), +the single \fBTCL_TOKEN_TEXT\fR token will have a \fIsize\fR field +containing zero; +this ensures that at least one token appears +to describe the braced string. +Only the token information in the Tcl_Parse structure +is modified: the \fIcommentStart\fR, \fIcommentSize\fR, +\fIcommandStart\fR, and \fIcommandSize\fR fields are not modified +by \fBTcl_ParseBraces\fR. +.PP +After \fBTcl_ParseQuotedString\fR returns, +the array of tokens pointed to by the \fItokenPtr\fR field of the +Tcl_Parse structure depends on the contents of the quoted string. +It will consist of one or more \fBTCL_TOKEN_TEXT\fR, \fBTCL_TOKEN_BS\fR, +\fBTCL_TOKEN_COMMAND\fR, and \fBTCL_TOKEN_VARIABLE\fR sub-tokens. +The array always contains at least one token; +for example, if the argument \fIstring\fR is empty, +the array returned consists of a single \fBTCL_TOKEN_TEXT\fR token +with a zero \fIsize\fR field. +Only the token information in the Tcl_Parse structure +is modified: the \fIcommentStart\fR, \fIcommentSize\fR, +\fIcommandStart\fR, and \fIcommandSize\fR fields are not modified. +.PP +After \fBTcl_ParseVarName\fR returns, the first token pointed to by +the \fItokenPtr\fR field of the +Tcl_Parse structure always has type \fBTCL_TOKEN_VARIABLE\fR. It +is followed by the sub-tokens that make up the variable name as +described above. The total length of the variable name is +contained in the \fIsize\fR field of the first token. +As in \fBTcl_ParseExpr\fR, +only the token information in the Tcl_Parse structure +is modified by \fBTcl_ParseVarName\fR: +the \fIcommentStart\fR, \fIcommentSize\fR, +\fIcommandStart\fR, and \fIcommandSize\fR fields are not modified. +.PP +All of the character pointers in the +Tcl_Parse and Tcl_Token structures refer +to characters in the \fIstring\fR argument passed to +\fBTcl_ParseCommand\fR, \fBTcl_ParseExpr\fR, \fBTcl_ParseBraces\fR, +\fBTcl_ParseQuotedString\fR, and \fBTcl_ParseVarName\fR. +.PP +There are additional fields in the Tcl_Parse structure after the +\fInumTokens\fR field, but these are for the private use of +\fBTcl_ParseCommand\fR, \fBTcl_ParseExpr\fR, \fBTcl_ParseBraces\fR, +\fBTcl_ParseQuotedString\fR, and \fBTcl_ParseVarName\fR; they should not be +referenced by code outside of these procedures. + +.SH KEYWORDS +backslash substitution, braces, command, expression, parse, token, variable substitution diff --git a/doc/RegExp.3 b/doc/RegExp.3 index 61778cd..1f1064d 100644 --- a/doc/RegExp.3 +++ b/doc/RegExp.3 @@ -1,21 +1,25 @@ '\" '\" Copyright (c) 1994 The Regents of the University of California. '\" Copyright (c) 1994-1996 Sun Microsystems, Inc. +'\" Copyright (c) 1998-1999 Scriptics Corportation '\" '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: RegExp.3,v 1.2 1998/09/14 18:39:50 stanton Exp $ +'\" RCS: @(#) $Id: RegExp.3,v 1.3 1999/04/16 00:46:32 stanton Exp $ '\" .so man.macros .TH Tcl_RegExpMatch 3 7.4 Tcl "Tcl Library Procedures" .BS .SH NAME -Tcl_RegExpMatch, Tcl_RegExpCompile, Tcl_RegExpExec, Tcl_RegExpRange \- Pattern matching with regular expressions +Tcl_GetRegExpFromObj, Tcl_RegExpMatch, Tcl_RegExpCompile, Tcl_RegExpExec, Tcl_RegExpRange \- Pattern matching with regular expressions .SH SYNOPSIS .nf \fB#include <tcl.h>\fR .sp +Tcl_RegExp +\fBTcl_GetRegExpFromObj\fR(\fIinterp\fR, \fIpatObj\fR, \fIflags\fR) +.sp int \fBTcl_RegExpMatch\fR(\fIinterp\fR, \fIstring\fR, \fIpattern\fR) .sp @@ -34,9 +38,13 @@ Tcl interpreter to use for error reporting. String to check for a match with a regular expression. .AP char *pattern in String in the form of a regular expression pattern. +.AP Tcl_Obj *patObj in +Refers to the object from which to get a compiled regular expression. +.AP int flags in +Various flags to control regular expression compile options. .AP Tcl_RegExp regexp in Compiled regular expression. Must have been returned previously -by \fBTcl_RegExpCompile\fR. +by \fBTcl_GetRegExpFromObj\fR. .AP char *start in If \fIstring\fR is just a portion of some other string, this argument identifies the beginning of the larger string. @@ -56,6 +64,13 @@ is stored here, or NULL if there is no such range. .SH DESCRIPTION .PP +\fBTcl_GetRegExpFromObj\fR attepts to return a compiled regular +expression from the Tcl obj \fIpatObj\fR. If the object does not +already contain a compiled regular expression it will attempt to +create one from the string in the Tcl obj and assign it to the +internal representation of the \fIpatObj\fR. The return value +of this function is of type \fBTcl_RegExp\fR. +.PP \fBTcl_RegExpMatch\fR determines whether its \fIpattern\fR argument matches \fIregexp\fR, where \fIregexp\fR is interpreted as a regular expression using the same rules as for the diff --git a/doc/SaveResult.3 b/doc/SaveResult.3 new file mode 100644 index 0000000..6a0a051 --- /dev/null +++ b/doc/SaveResult.3 @@ -0,0 +1,65 @@ +'\" +'\" Copyright (c) 1997 by 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: SaveResult.3,v 1.2 1999/04/16 00:46:33 stanton Exp $ +'\" +.so man.macros +.TH Tcl_SaveResult 3 8.1 Tcl "Tcl Library Procedures" +.BS +.SH NAME +Tcl_SaveResult, Tcl_RestoreResult, Tcl_DiscardResult \- save and restore an interpreter's result +.SH SYNOPSIS +.nf +\fB#include <tcl.h>\fR +.sp +\fBTcl_SaveResult(\fIinterp, statePtr\fB)\fR +.sp +\fBTcl_RestoreResult(\fIinterp, statePtr\fB)\fR +.sp +\fBTcl_DiscardResult(\fIstatePtr\fB)\fR +.SH ARGUMENTS +.AS Tcl_SavedResult statePtr +.AP Tcl_Interp *interp in +Interpreter for which state should be saved. +.AP Tcl_SavedResult *statePtr in +Pointer to location where interpreter result should be saved or restored. +.BE + +.SH DESCRIPTION +.PP +These routines allows a C procedure to take a snapshot of the current +interpreter result so that it can be restored after a call +to \fBTcl_Eval\fR or some other routine that modifies the interpreter +result. These routines are passed a pointer to a structure that is +used to store enough information to restore the interpreter result +state. This structure can be allocated on the stack of the calling +procedure. These routines do not save the state of any error +information in the interpreter (e.g. the \fBerrorCode\fR or +\fBerrorInfo\fR variables). +.PP +\fBTcl_SaveResult\fR moves the string and object results +of \fIinterp\fR into the location specified by \fIstatePtr\fR. +\fBTcl_SaveResult\fR clears the result for \fIinterp\fR and +leaves the result in its normal empty initialized state. +.PP +\fBTcl_RestoreResult\fR moves the string and object results from +\fIstatePtr\fR back into \fIinterp\fR. Any result or error that was +already in the interpreter will be cleared. The \fIstatePtr\fR is left +in an uninitialized state and cannot be used until another call to +\fBTcl_SaveResult\fR. +.PP +\fBTcl_DiscardResult\fR releases the saved interpreter state +stored at \fBstatePtr\fR. The state structure is left in an +uninitialized state and cannot be used until another call to +\fBTcl_SaveResult\fR. +.PP +Once \fBTcl_SaveResult\fR is called to save the interpreter +result, either \fBTcl_RestoreResult\fR or +\fBTcl_DiscardResult\fR must be called to properly clean up the +memory associated with the saved state. + +.SH KEYWORDS +result, state, interp diff --git a/doc/SetRecLmt.3 b/doc/SetRecLmt.3 index b41985b..599e46f 100644 --- a/doc/SetRecLmt.3 +++ b/doc/SetRecLmt.3 @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: SetRecLmt.3,v 1.2 1998/09/14 18:39:50 stanton Exp $ +'\" RCS: @(#) $Id: SetRecLmt.3,v 1.3 1999/04/16 00:46:33 stanton Exp $ '\" .so man.macros .TH Tcl_SetRecursionLimit 3 7.0 Tcl "Tcl Library Procedures" @@ -41,7 +41,7 @@ allowable nesting depth for an interpreter. The \fIdepth\fR argument specifies a new limit for \fIinterp\fR, and \fBTcl_SetRecursionLimit\fR returns the old limit. To read out the old limit without modifying it, invoke -\fBTcl_SetRecursionDepth\fR with \fIdepth\fR equal to 0. +\fBTcl_SetRecursionLimit\fR with \fIdepth\fR equal to 0. .PP The \fBTcl_SetRecursionLimit\fR only sets the size of the Tcl call stack: it cannot by itself prevent stack overflows on the diff --git a/doc/SetVar.3 b/doc/SetVar.3 index 70100f4..bb07005 100644 --- a/doc/SetVar.3 +++ b/doc/SetVar.3 @@ -5,93 +5,158 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: SetVar.3,v 1.2 1998/09/14 18:39:50 stanton Exp $ +'\" RCS: @(#) $Id: SetVar.3,v 1.3 1999/04/16 00:46:33 stanton Exp $ '\" .so man.macros -.TH Tcl_SetVar 3 7.4 Tcl "Tcl Library Procedures" +.TH Tcl_SetVar 3 8.1 Tcl "Tcl Library Procedures" .BS .SH NAME -Tcl_SetVar, Tcl_SetVar2, Tcl_GetVar, Tcl_GetVar2, Tcl_UnsetVar, Tcl_UnsetVar2 \- manipulate Tcl variables +Tcl_SetVar2Ex, Tcl_SetVar, Tcl_SetVar2, Tcl_ObjSetVar2, Tcl_GetVar2Ex, Tcl_GetVar, Tcl_GetVar2, Tcl_ObjGetVar2, Tcl_UnsetVar, Tcl_UnsetVar2 \- manipulate Tcl variables .SH SYNOPSIS .nf \fB#include <tcl.h>\fR .sp +.VS 8.1 +Tcl_Obj * +\fBTcl_SetVar2Ex\fR(\fIinterp, name1, name2, newValuePtr, flags\fR) +.VE +.sp char * \fBTcl_SetVar\fR(\fIinterp, varName, newValue, flags\fR) .sp char * \fBTcl_SetVar2\fR(\fIinterp, name1, name2, newValue, flags\fR) .sp +Tcl_Obj * +\fBTcl_ObjSetVar2\fR(\fIinterp, part1Ptr, part2Ptr, newValuePtr, flags\fR) +.sp +.VS 8.1 +Tcl_Obj * +\fBTcl_GetVar2Ex\fR(\fIinterp, name1, name2, flags\fR) +.VE +.sp char * \fBTcl_GetVar\fR(\fIinterp, varName, flags\fR) .sp char * \fBTcl_GetVar2\fR(\fIinterp, name1, name2, flags\fR) .sp +Tcl_Obj * +\fBTcl_ObjGetVar2\fR(\fIinterp, part1Ptr, part2Ptr, flags\fR) +.sp int \fBTcl_UnsetVar\fR(\fIinterp, varName, flags\fR) .sp int \fBTcl_UnsetVar2\fR(\fIinterp, name1, name2, flags\fR) .SH ARGUMENTS -.AS Tcl_Interp *newValue +.AS Tcl_Interp *newValuePtr .AP Tcl_Interp *interp in Interpreter containing variable. +.AP char *name1 in +Contains the name of an array variable (if \fIname2\fR is non-NULL) +or (if \fIname2\fR is NULL) either the name of a scalar variable +or a complete name including both variable name and index. +May include \fB::\fR namespace qualifiers +to specify a variable in a particular namespace. +.AP char *name2 in +If non-NULL, gives name of element within array; in this +case \fIname1\fR must refer to an array variable. +.AP Tcl_Obj *newValuePtr in +.VS 8.1 +Points to a Tcl object containing the new value for the variable. +.VE +.AP int flags in +OR-ed combination of bits providing additional information. See below +for valid values. .AP char *varName in Name of variable. -May include a series of \fB::\fR namespace qualifiers +May include \fB::\fR namespace qualifiers to specify a variable in a particular namespace. May refer to a scalar variable or an element of -an array variable. -If the name references an element of an array, then it +an array. +If the name references an element of an array, then the name must be in writable memory: Tcl will make temporary modifications to it while looking up the name. .AP char *newValue in -New value for variable. -.AP int flags in -OR-ed combination of bits providing additional information for -operation. See below for valid values. -.AP char *name1 in -Name of scalar variable, or name of array variable if \fIname2\fR -is non-NULL. -May include a series of \fB::\fR namespace qualifiers +New value for variable, specified as a NULL-terminated string. +A copy of this value is stored in the variable. +.AP Tcl_Obj *part1Ptr in +Points to a Tcl object containing the variable's name. +The name may include a series of \fB::\fR namespace qualifiers to specify a variable in a particular namespace. -.AP char *name2 in -If non-NULL, gives name of element within array and \fIname1\fR -must refer to an array variable. +May refer to a scalar variable or an element of an array variable. +.AP Tcl_Obj *part2Ptr in +If non-NULL, points to an object containing the name of an element +within an array and \fIpart1Ptr\fR must refer to an array variable. .BE .SH DESCRIPTION .PP -These procedures may be used to create, modify, read, and delete +These procedures are used to create, modify, read, and delete Tcl variables from C code. .PP -Note that \fBTcl_GetVar\fR and \fBTcl_SetVar\fR -have been largely replaced by the -object-based procedures \fBTcl_ObjGetVar2\fR and \fBTcl_ObjSetVar2\fR. -Those object-based procedures read, modify, and create -a variable whose name is held in a Tcl object instead of a string. -They also return a pointer to the object -which is the variable's value instead of returning a string. -Operations on objects can be faster since objects -hold an internal representation that can be manipulated more efficiently. -.PP -\fBTcl_SetVar\fR and \fBTcl_SetVar2\fR +.VS 8.1 +\fBTcl_SetVar2Ex\fR, \fBTcl_SetVar\fR, \fBTcl_SetVar2\fR, and +\fBTcl_ObjSetVar2\fR will create a new variable or modify an existing one. -Both of these procedures set the given variable to the value -given by \fInewValue\fR, and they return a pointer to a -copy of the variable's new value, which is stored in Tcl's +These procedures set the given variable to the value +given by \fInewValuePtr\fR or \fInewValue\fR and return a +pointer to the variable's new value, which is stored in Tcl's variable structure. -Tcl keeps a private copy of the variable's value, so the caller -may change \fInewValue\fR after these procedures return without -affecting the value of the variable. +\fBTcl_SetVar2Ex\fR and \fBTcl_ObjSetVar2\fR take the new value as a +Tcl_Obj and return +a pointer to a Tcl_Obj. \fBTcl_SetVar\fR and \fBTcl_SetVar2\fR +take the new value as a string and return a string; they are +usually less efficient than \fBTcl_ObjSetVar2\fR. Note that the +return value may be different than the \fInewValuePtr\fR or +.VE +\fInewValue\fR argument, due to modifications made by write traces. If an error occurs in setting the variable (e.g. an array -variable is referenced without giving an index into the array), -they return NULL. +variable is referenced without giving an index into the array) +NULL is returned and an error message is left in \fIinterp\fR's +result if the \fBTCL_LEAVE_ERR_MSG\fR \fIflag\fR bit is set. +.PP +.VS 8.1 +\fBTcl_GetVar2Ex\fR, \fBTcl_GetVar\fR, \fBTcl_GetVar2\fR, and +\fBTcl_ObjGetVar2\fR +return the current value of a variable. +The arguments to these procedures are treated in the same way +as the arguments to the procedures described above. +Under normal circumstances, the return value is a pointer +to the variable's value. For \fBTcl_GetVar2Ex\fR and +\fBTcl_ObjGetVar2\fR the value is +returned as a pointer to a Tcl_Obj. For \fBTcl_GetVar\fR and +\fBTcl_GetVar2\fR the value is returned as a string; this is +usually less efficient, so \fBTcl_GetVar2Ex\fR or \fBTcl_ObjGetVar2\fR +are preferred. +.VE +If an error occurs while reading the variable (e.g. the variable +doesn't exist or an array element is specified for a scalar +variable), then NULL is returned and an error message is left +in \fIinterp\fR's result if the \fBTCL_LEAVE_ERR_MSG\fR \fIflag\fR +bit is set. .PP -The name of the variable may be specified to -\fBTcl_SetVar\fR and \fBTcl_SetVar2\fR in either of two ways. -If \fBTcl_SetVar\fR is called, the variable name is given as +\fBTcl_UnsetVar\fR and \fBTcl_UnsetVar2\fR may be used to remove +a variable, so that future attempts to read the variable will return +an error. +The arguments to these procedures are treated in the same way +as the arguments to the procedures above. +If the variable is successfully removed then TCL_OK is returned. +If the variable cannot be removed because it doesn't exist then +TCL_ERROR is returned and an error message is left +in \fIinterp\fR's result if the \fBTCL_LEAVE_ERR_MSG\fR \fIflag\fR +bit is set. +If an array element is specified, the given element is removed +but the array remains. +If an array name is specified without an index, then the entire +array is removed. +.PP +The name of a variable may be specified to these procedures in +four ways: +.IP [1] +If \fBTcl_SetVar\fR, \fBTcl_GetVar\fR, or \fBTcl_UnsetVar\fR +is invoked, the variable name is given as a single string, \fIvarName\fR. If \fIvarName\fR contains an open parenthesis and ends with a close parenthesis, then the value between the parentheses is @@ -100,22 +165,31 @@ the characters before the first open parenthesis are treated as the name of an array variable. If \fIvarName\fR doesn't have parentheses as described above, then the entire string is treated as the name of a scalar variable. -If \fBTcl_SetVar2\fR is called, then the array name and index -have been separated by the caller into two separate strings, -\fIname1\fR and \fIname2\fR respectively; if \fIname2\fR is -zero it means that a scalar variable is being referenced. +.IP [2] +If the \fIname1\fR and \fIname2\fR arguments are provided and +\fIname2\fR is non-NULL, then an array element is specified and +the array name and index have +already been separated by the caller: \fIname1\fR contains the +name and \fIname2\fR contains the index. +.VS 8.1 +An error is generated +if \fIname1\fR contains an open parenthesis and ends with a +close parenthesis (array element) and \fIname2\fR is non-NULL. +.IP [3] +If \fIname2\fR is NULL, \fIname1\fR is treated just like +\fIvarName\fR in case [1] above (it can be either a scalar or an array +element variable name). +.VE .PP The \fIflags\fR argument may be used to specify any of several options to the procedures. It consists of an OR-ed combination of the following bits. -Note that the flag bit TCL_PARSE_PART1 is only meaningful -for the procedures Tcl_SetVar2 and Tcl_GetVar2. .TP \fBTCL_GLOBAL_ONLY\fR -Under normal circumstances the procedures look up variables as follows: +Under normal circumstances the procedures look up variables as follows. If a procedure call is active in \fIinterp\fR, -a variable is looked up at the current level of procedure call. -Otherwise, a variable is looked up first in the current namespace, +the variable is looked up at the current level of procedure call. +Otherwise, the variable is looked up first in the current namespace, then in the global namespace. However, if this bit is set in \fIflags\fR then the variable is looked up only in the global namespace @@ -124,14 +198,10 @@ If both \fBTCL_GLOBAL_ONLY\fR and \fBTCL_NAMESPACE_ONLY\fR are given, \fBTCL_GLOBAL_ONLY\fR is ignored. .TP \fBTCL_NAMESPACE_ONLY\fR -Under normal circumstances the procedures look up variables as follows: -If a procedure call is active in \fIinterp\fR, -a variable is looked up at the current level of procedure call. -Otherwise, a variable is looked up first in the current namespace, -then in the global namespace. -However, if this bit is set in \fIflags\fR then the variable -is looked up only in the current namespace -even if there is a procedure call active. +If this bit is set in \fIflags\fR then the variable +is looked up only in the current namespace; if a procedure is active +its variables are ignored, and the global namespace is also ignored unless +it is the current namespace. .TP \fBTCL_LEAVE_ERR_MSG\fR If an error is returned and this bit is set in \fIflags\fR, then @@ -142,9 +212,10 @@ If this flag bit isn't set then no error message is left and the interpreter's result will not be modified. .TP \fBTCL_APPEND_VALUE\fR -If this bit is set then \fInewValue\fR is appended to the current -value, instead of replacing it. -If the variable is currently undefined, then this bit is ignored. +If this bit is set then \fInewValuePtr\fR or \fInewValue\fR is +appended to the current value instead of replacing it. +If the variable is currently undefined, then the bit is ignored. +This bit is only used by the \fBTcl_Set*\fR procedures. .TP \fBTCL_LIST_ELEMENT\fR If this bit is set, then \fInewValue\fR is converted to a valid @@ -153,18 +224,6 @@ A separator space is appended before the new list element unless the list element is going to be the first element in a list or sublist (i.e. the variable's current value is empty, or contains the single character ``{'', or ends in `` }''). -.TP -\fBTCL_PARSE_PART1\fR -If this bit is set when calling \fITcl_SetVar2\fR and \fITcl_GetVar2\fR, -\fIname1\fR may contain both an array and an element name: -if the name contains an open parenthesis and ends with a -close parenthesis, then the value between the parentheses is -treated as an element name (which can have any string value) and -the characters before the first open -parenthesis are treated as the name of an array variable. -If the flag TCL_PARSE_PART1 is given, -\fIname2\fR should be NULL since the array and element names -are taken from \fIname1\fR. .PP \fBTcl_GetVar\fR and \fBTcl_GetVar2\fR return the current value of a variable. @@ -178,8 +237,6 @@ or \fBTcl_SetVar2\fR). and TCL_LEAVE_ERR_MSG, both of which have the same meaning as for \fBTcl_SetVar\fR. -In addition, \fBTcl_GetVar2\fR uses the bit TCL_PARSE_PART1, -which has the same meaning as for \fBTcl_SetVar2\fR. If an error occurs in reading the variable (e.g. the variable doesn't exist or an array element is specified for a scalar variable), then NULL is returned. @@ -198,7 +255,7 @@ If an array name is specified without an index, then the entire array is removed. .SH "SEE ALSO" -Tcl_GetObjResult, Tcl_GetStringResult, Tcl_ObjGetVar2, Tcl_ObjSetVar2, Tcl_TraceVar +Tcl_GetObjResult, Tcl_GetStringResult, Tcl_TraceVar .SH KEYWORDS -array, interpreter, object, scalar, set, unset, variable +array, get variable, interpreter, object, scalar, set, unset, variable diff --git a/doc/StringObj.3 b/doc/StringObj.3 index 94cd142..46fe959 100644 --- a/doc/StringObj.3 +++ b/doc/StringObj.3 @@ -4,13 +4,13 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: StringObj.3,v 1.3 1999/03/10 05:52:45 stanton Exp $ +'\" RCS: @(#) $Id: StringObj.3,v 1.4 1999/04/16 00:46:33 stanton Exp $ '\" .so man.macros -.TH Tcl_StringObj 3 8.0 Tcl "Tcl Library Procedures" +.TH Tcl_StringObj 3 8.1 Tcl "Tcl Library Procedures" .BS .SH NAME -Tcl_NewStringObj, Tcl_SetStringObj, Tcl_GetStringFromObj, Tcl_AppendToObj, Tcl_AppendStringsToObj, Tcl_AppendStringsToObjVA, Tcl_SetObjLength, TclConcatObj \- manipulate Tcl objects as strings +Tcl_NewStringObj, Tcl_SetStringObj, Tcl_GetStringFromObj, Tcl_GetString, Tcl_AppendToObj, Tcl_AppendStringsToObj, Tcl_AppendStringsToObjVA, Tcl_AppendObjToObj, Tcl_SetObjLength, Tcl_ConcatObj \- manipulate Tcl objects as strings .SH SYNOPSIS .nf \fB#include <tcl.h>\fR @@ -23,7 +23,14 @@ Tcl_Obj * char * \fBTcl_GetStringFromObj\fR(\fIobjPtr, lengthPtr\fR) .sp +char * +\fBTcl_GetString\fR(\fIobjPtr\fR) +.sp \fBTcl_AppendToObj\fR(\fIobjPtr, bytes, length\fR) +.VS +.sp +\fBTcl_AppendObjToObj\fR(\fIobjPtr, appendObjPtr\fR) +.VE .sp \fBTcl_AppendStringsToObj\fR(\fIobjPtr, string, string, ... \fB(char *) NULL\fR) .sp @@ -34,7 +41,7 @@ char * Tcl_Obj * \fBTcl_ConcatObj\fR(\fIobjc, objv\fR) .SH ARGUMENTS -.AS Tcl_Interp *lengthPtr out +.AS Tcl_Interp *appendObjPtr in/out .AP char *bytes in Points to the first byte of an array of bytes used to set or append to a string object. @@ -46,6 +53,10 @@ initializing, setting, or appending to a string object. If negative, all bytes up to the first null are used. .AP Tcl_Obj *objPtr in/out Points to an object to manipulate. +.VS +.AP Tcl_Obj *appendObjPtr in +The object to append to \fIobjPtr\fR in \fBTcl_AppendObjToObj\fR. +.VE .AP int *lengthPtr out If non-NULL, the location where \fBTcl_GetStringFromObj\fR will store the the length of an object's string representation. @@ -81,21 +92,30 @@ Both procedures set the object to hold a copy of the specified string. \fBTcl_SetStringObj\fR frees any old string representation as well as any old internal representation of the object. .PP -\fBTcl_GetStringFromObj\fR returns an object's string representation. +\fBTcl_GetStringFromObj\fR and \fBTcl_GetString\fR +return an object's string representation. This is given by the returned byte pointer -and length, which is stored in \fIlengthPtr\fR if it is non-NULL. +and (for \fBTcl_GetStringFromObj\fR) length, +which is stored in \fIlengthPtr\fR if it is non-NULL. If the object's string representation is invalid (its byte pointer is NULL), the string representation is regenerated from the object's internal representation. The storage referenced by the returned byte pointer is owned by the object manager and should not be modified by the caller. +The procedure \fBTcl_GetString\fR is used in the common case +where the caller does not need the length of the string representation. .PP \fBTcl_AppendToObj\fR appends the data given by \fIbytes\fR and \fIlength\fR to the object specified by \fIobjPtr\fR. It does this in a way that handles repeated calls relatively efficiently (it overallocates the string space to avoid repeated reallocations and copies of object's string value). +.VS +.PP +\fBTcl_AppendObjToObj\fR is similar to \fBTcl_AppendToObj\fR, but it +appends the string value of \fIappendObjPtr\fR to \fIobjPtr\fR. +.VE .PP \fBTcl_AppendStringsToObj\fR is similar to \fBTcl_AppendToObj\fR except that it can be passed more than one value to append and @@ -5,10 +5,10 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: Tcl.n,v 1.2 1998/09/14 18:39:50 stanton Exp $ -' +'\" RCS: @(#) $Id: Tcl.n,v 1.3 1999/04/16 00:46:33 stanton Exp $ +'\" .so man.macros -.TH Tcl n "" Tcl "Tcl Built-In Commands" +.TH Tcl n "8.1" Tcl "Tcl Built-In Commands" .BS .SH NAME Tcl \- Summary of Tcl language syntax. @@ -111,47 +111,61 @@ special processing. The following table lists the backslash sequences that are handled specially, along with the value that replaces each sequence. .RS -.TP 6 +.TP 7 \e\fBa\fR Audible alert (bell) (0x7). -.TP 6 +.TP 7 \e\fBb\fR Backspace (0x8). -.TP 6 +.TP 7 \e\fBf\fR Form feed (0xc). -.TP 6 +.TP 7 \e\fBn\fR Newline (0xa). -.TP 6 +.TP 7 \e\fBr\fR Carriage-return (0xd). -.TP 6 +.TP 7 \e\fBt\fR Tab (0x9). -.TP 6 +.TP 7 \e\fBv\fR Vertical tab (0xb). -.TP 6 +.TP 7 \e\fB<newline>\fIwhiteSpace\fR -A single space character replaces the backslash, newline, and all -spaces and tabs after the newline. -This backslash sequence is unique in that it is replaced in a separate -pre-pass before the command is actually parsed. -This means that it will be replaced even when it occurs between -braces, and the resulting space will be treated as a word separator -if it isn't in braces or quotes. -.TP 6 +. +A single space character replaces the backslash, newline, and all spaces +and tabs after the newline. This backslash sequence is unique in that it +is replaced in a separate pre-pass before the command is actually parsed. +This means that it will be replaced even when it occurs between braces, +and the resulting space will be treated as a word separator if it isn't +in braces or quotes. +.TP 7 \e\e Backslash (``\e''). -.TP 6 -\e\fIooo\fR -The digits \fIooo\fR (one, two, or three of them) give the octal value of -the character. -.TP 6 -\e\fBx\fIhh\fR -The hexadecimal digits \fIhh\fR give the hexadecimal value of -the character. Any number of digits may be present. +.VS 8.1 br +.TP 7 +\e\fIooo\fR +. +The digits \fIooo\fR (one, two, or three of them) give an eight-bit octal +value for the Unicode character that will be inserted. The upper bits of the +Unicode character will be 0. +.TP 7 +\e\fBx\fIhh\fR +. +The hexadecimal digits \fIhh\fR give an eight-bit hexadecimal value for the +Unicode character that will be inserted. Any number of hexadecimal digits +may be present; however, all but the last two are ignored (the result is +always a one-byte quantity). The upper bits of the Unicode character will +be 0. +.TP 7 +\e\fBu\fIhhhh\fR +. +The hexadecimal digits \fIhhhh\fR (one, two, three, or four of them) give a +sixteen-bit hexadecimal value for the Unicode character that will be +inserted. +.VE .LP Backslash substitution is not performed on words enclosed in braces, except for backslash-newline as described above. diff --git a/doc/Thread.3 b/doc/Thread.3 new file mode 100644 index 0000000..595fac3 --- /dev/null +++ b/doc/Thread.3 @@ -0,0 +1,100 @@ +'\" +'\" Copyright (c) 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: Thread.3,v 1.2 1999/04/16 00:46:33 stanton Exp $ +'\" +.so man.macros +.TH Tcl_ConditionNotify 3 "8.1" Tcl "Tcl Library Procedures" +.BS +.SH NAME +Tcl_ConditionNotify, Tcl_ConditionWait, Tcl_GetThreadData, Tcl_MutexLock, Tcl_MutexUnlock \- thread synchronization support. +.SH SYNOPSIS +.nf +\fB#include <tcl.h>\fR +.sp +void +\fBTcl_ConditionNotify\fR(\fIcondPtr\fR) +.sp +void +\fBTcl_ConditionWait\fR(\fIcondPtr, mutexPtr, timePtr\fR) +.sp +VOID * +\fBTcl_GetThreadData\fR(\fIkeyPtr, size\fR) +.sp +void +\fBTcl_MutexLock\fR(\fImutexPtr\fR) +.sp +void +\fBTcl_MutexUnlock\fR(\fImutexPtr\fR) +.SH ARGUMENTS +.AS Tcl_ThreadDataKey *keyPtr +.AP Tcl_Condition *condPtr in +A condition variable, which must be associated with a mutex lock. +.AP Tcl_Condition *mutexPtr in +A mutex lock. +.AP Tcl_Time *timePtr in +A time limit on the condition wait. NULL to wait forever. +Note that a polling value of 0 seconds doesn't make much sense. +.AP Tcl_ThreadDataKey *keyPtr in +This identifies a block of thread local storage. The key should be +static and process-wide, yet each thread will end up associating +a different block of storage with this key. +.AP int *size in +The size of the thread local storage block. This amount of data +is allocated and initialized to zero the first time each thread +calls \fBTcl_GetThreadData\fR. +.BE + +.SH DESCRIPTION +.PP +A mutex is a lock that is used to serialize all threads through a piece +of code by calling \fBTcl_MutexLock\fR and \fBTcl_MutexUnlock\fR. +If one thread holds a mutex, any other thread calling \fBTcl_MutexLock\fR will +block until \fBTcl_MutexUnlock\fR is called. +.VS +The result of locking a mutex twice from the same thread is undefined. +On some platforms it will result in a deadlock. +.VE +\fBTcl_MutexLock\fR and \fBTcl_MutexUnlock\fR +procedures are defined as empty macros if not compiling with threads enabled. +.PP +A condition variable is used as a signaling mechanism: +a thread can lock a mutex and then wait on a condition variable +with \fBTcl_ConditionWait\fR. This atomically releases the mutex lock +and blocks the waiting thread until another thread calls +\fBTcl_ConditionNotify\fR. The caller of \fBTcl_ConditionNotify\fR should +have the associated mutex held by previously calling \fBTcl_MutexLock\fR, +but this is not enforced. Notifying the +condition variable unblocks all threads waiting on the condition variable, +but they do not proceed until the mutex is released with \fBTcl_MutexUnlock\fR. +The implementation of \fBTcl_ConditionWait\fR automatically locks +the mutex before returning. +.PP +The caller of \fBTcl_ConditionWait\fR should be prepared for spurious +notifications by calling \fBTcl_ConditionWait\fR within a while loop +that tests some invariant. +.PP +The \fBTcl_GetThreadData\fR call returns a pointer to a block of +thread-private data. Its argument is a key that is shared by all threads +and a size for the block of storage. The storage is automatically +allocated and initialized to all zeros the first time each thread asks for it. +The storage is automatically deallocated by \fBTcl_FinalizeThread\fR +.SH INITIALIZATION +.PP +.PP +All of these synchronization objects are self initializing. +They are implemented as opaque pointers that should be NULL +upon first use. +The mutexes and condition variables are +cleaned up by process exit handlers. Thread local storage is +reclaimed during \fBTcl_FinalizeThread\fR. +.SH CREATING THREADS +The API to create threads is not finalized at this time. +There are private facilities to create threads that contain a new +Tcl interpreter, and to send scripts among threads. +Dive into tclThreadTest.c and tclThread.c for examples. +.SH KEYWORDS +thread, mutex, condition variable, thread local storage diff --git a/doc/ToUpper.3 b/doc/ToUpper.3 new file mode 100644 index 0000000..639dd61 --- /dev/null +++ b/doc/ToUpper.3 @@ -0,0 +1,90 @@ +'\" +'\" Copyright (c) 1997 by 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: ToUpper.3,v 1.2 1999/04/16 00:46:33 stanton Exp $ +'\" +.so man.macros +.TH Tcl_UtfToUpper 3 "8.1" Tcl "Tcl Library Procedures" +.BS +.SH NAME +Tcl_UniCharToUpper, Tcl_UniCharToLower, Tcl_UniCharToTitle, Tcl_UtfToUpper, Tcl_UtfToLower, Tcl_UtfToTitle \- routines for manipulating the case of Unicode characters and UTF-8 strings. +.SH SYNOPSIS +.nf +\fB#include <tcl.h>\fR +.sp +Tcl_UniChar +\fBTcl_UniCharToUpper\fR(\fIch\fR) +.sp +Tcl_UniChar +\fBTcl_UniCharToLower\fR(\fIch\fR) +.sp +Tcl_UniChar +\fBTcl_UniCharToTitle\fR(\fIch\fR) +.sp +int +\fBTcl_UtfToUpper\fR(\fIstr\fR) +.sp +int +\fBTcl_UtfToLower\fR(\fIstr\fR) +.sp +int +\fBTcl_UtfToTitle\fR(\fIstr\fR) +.SH ARGUMENTS +.AS char *str in/out +.AP int ch in +The Tcl_UniChar to be converted. +.AP char *str in/out +Pointer to UTF-8 string to be converted in place. +.BE + +.SH DESCRIPTION +.PP +The first three routines convert the case of individual Unicode characters: +.PP +If \fIch\fR represents a lower-case character, +\fBTcl_UniCharToUpper\fR returns the corresponding upper-case +character. If no upper-case character is defined, it returns the +character unchanged. +.PP +If \fIch\fR represents an upper-case character, +\fBTcl_UniCharToLower\fR returns the corresponding lower-case +character. If no lower-case character is defined, it returns the +character unchanged. +.PP +If \fIch\fR represents a lower-case character, +\fBTcl_UniCharToTitle\fR returns the corresponding title-case +character. If no title-case character is defined, it returns the +corresponding upper-case character. If no upper-case character is +defined, it returns the character unchanged. Title-case is defined +for a small number of characters that have a different appearance when +they are at the beginning of a capitalized word. +.PP +The next three routines convert the case of UTF-8 strings in place in +memory: +.PP +\fBTcl_UtfToUpper\fR changes every UTF-8 character in \fIstr\fR to +upper-case. Because changing the case of a character may change its +size, the byte offset of each character in the resulting string may +differ from its original location. \fBTcl_UtfToUpper\fR writes a null +byte at the end of the converted string. \fBTcl_UtfToUpper\fR returns +the new length of the string in bytes. This new length is guaranteed +to be no longer than the original string length. +.PP +\fBTcl_UtfToLower\fR is the same as \fBTcl_UtfToUpper\fR except it +turns each character in the string into its lower-case equivalent. +.PP +\fBTcl_UtfToTitle\fR is the same as \fBTcl_UtfToUpper\fR except it +turns the first character in the string into its title-case equivalent +and all following characters into their lower-case equivalents. + +.SH BUGS +.PP +At this time, the case conversions are only defined for the ISO8859-1 +characters. Unicode characters above 0x00ff are not modified by these +routines. + +.SH KEYWORDS +utf, unicode, toupper, tolower, totitle, case diff --git a/doc/TraceVar.3 b/doc/TraceVar.3 index ac4891d..57a3350 100644 --- a/doc/TraceVar.3 +++ b/doc/TraceVar.3 @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: TraceVar.3,v 1.2 1998/09/14 18:39:50 stanton Exp $ +'\" RCS: @(#) $Id: TraceVar.3,v 1.3 1999/04/16 00:46:33 stanton Exp $ '\" .so man.macros .TH Tcl_TraceVar 3 7.4 Tcl "Tcl Library Procedures" @@ -44,7 +44,7 @@ must be in writable memory: Tcl will make temporary modifications to it while looking up the name. .AP int flags in OR-ed combination of the values TCL_TRACE_READS, TCL_TRACE_WRITES, and -TCL_TRACE_UNSETS, TCL_PARSE_PART1, and TCL_GLOBAL_ONLY. +TCL_TRACE_UNSETS, TCL_TRACE_ARRAY, and TCL_GLOBAL_ONLY. Not all flags are used by all procedures. See below for more information. .AP Tcl_VarTraceProc *proc in @@ -96,6 +96,12 @@ A variable may be unset either explicitly by an \fBunset\fR command, or implicitly when a procedure returns (its local variables are automatically unset) or when the interpreter is deleted (all variables are automatically unset). +.TP +\fBTCL_TRACE_ARRAY\fR +Invoke \fIproc\fR whenever the array command is invoked. +This gives the trace procedure a chance to update the array before +array names or array get is called. Note that this is called +before an array set, but that will trigger write traces. .PP Whenever one of the specified operations occurs on the variable, \fIproc\fR will be invoked. @@ -120,7 +126,8 @@ in the normal two-part form (see the description of \fBTcl_TraceVar2\fR below for details). \fIFlags\fR is an OR-ed combination of bits providing several pieces of information. -One of the bits TCL_TRACE_READS, TCL_TRACE_WRITES, or TCL_TRACE_UNSETS +One of the bits TCL_TRACE_READS, TCL_TRACE_WRITES, TCL_TRACE_ARRAY, +or TCL_TRACE_UNSETS will be set in \fIflags\fR to indicate which operation is being performed on the variable. The bit TCL_GLOBAL_ONLY will be set whenever the variable being @@ -175,24 +182,26 @@ The procedures \fBTcl_TraceVar2\fR, \fBTcl_UntraceVar2\fR, and except that the name of the variable consists of two parts. \fIName1\fR gives the name of a scalar variable or array, and \fIname2\fR gives the name of an element within an array. -If \fIname2\fR is NULL it means that either the variable is -a scalar or the trace is to be set on the entire array rather -than an individual element (see WHOLE-ARRAY TRACES below for -more information). -As a special case, if the flag TCL_PARSE_PART1 is specified, +.VS 8.1 +When \fIname2\fR is NULL, \fIname1\fR may contain both an array and an element name: if the name contains an open parenthesis and ends with a close parenthesis, then the value between the parentheses is treated as an element name (which can have any string value) and the characters before the first open parenthesis are treated as the name of an array variable. -If the flag TCL_PARSE_PART1 is given, -\fIname2\fR should be NULL since the array and element names -are taken from \fIname1\fR. +If \fIname2\fR is NULL and \fIname1\fR does not refer +to an array element +.VE +it means that either the variable is +a scalar or the trace is to be set on the entire array rather +than an individual element (see WHOLE-ARRAY TRACES below for +more information). + .SH "ACCESSING VARIABLES DURING TRACES" .PP -During read and write traces, the +During read, write, and array traces, the trace procedure can read, write, or unset the traced variable using \fBTcl_GetVar2\fR, \fBTcl_SetVar2\fR, and other procedures. @@ -245,6 +254,12 @@ access. If it deletes the variable then the traced access will return an empty string. .PP +When array tracing has been specified, the trace procedure +will be invoked at the beginning of the array command implementation, +before any of the operations like get, set, or names have been invoked. +The trace procedure can modify the array elements with \fBTcl_SetVar\fR +and \fBTcl_SetVar2\fR. +.PP When unset tracing has been specified, the trace procedure will be invoked whenever the variable is destroyed. The traces will be called after the variable has been @@ -343,6 +358,9 @@ to clean up and free their own internal data structures. Tcl doesn't do any error checking to prevent trace procedures from misusing the interpreter during traces with TCL_INTERP_DESTROYED set. +.PP +Array traces are not yet integrated with the Tcl "info exists" command, +nor is there Tcl-level access to array traces. .SH KEYWORDS clientData, trace, variable diff --git a/doc/Translate.3 b/doc/Translate.3 index e57d7f3..5d0d598 100644 --- a/doc/Translate.3 +++ b/doc/Translate.3 @@ -1,14 +1,14 @@ '\" '\" Copyright (c) 1989-1993 The Regents of the University of California. -'\" Copyright (c) 1994-1996 Sun Microsystems, Inc. +'\" Copyright (c) 1994-1998 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: Translate.3,v 1.2 1998/09/14 18:39:51 stanton Exp $ +'\" RCS: @(#) $Id: Translate.3,v 1.3 1999/04/16 00:46:33 stanton Exp $ '\" .so man.macros -.TH Tcl_TranslateFileName 3 7.5 Tcl "Tcl Library Procedures" +.TH Tcl_TranslateFileName 3 8.1 Tcl "Tcl Library Procedures" .BS .SH NAME Tcl_TranslateFileName \- convert file name to native form and replace tilde with home directory @@ -26,7 +26,7 @@ Interpreter in which to report an error, if any. File name, which may start with a ``~''. .AP Tcl_DString *bufferPtr in/out If needed, this dynamic string is used to store the new file name. -At the time of the call it should be uninitialized or empty. The +At the time of the call it should be uninitialized or free. The caller must eventually call \fBTcl_DStringFree\fR to free up anything stored here. .BE 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 diff --git a/doc/binary.n b/doc/binary.n index 871182e..8b20259 100644 --- a/doc/binary.n +++ b/doc/binary.n @@ -4,7 +4,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: binary.n,v 1.2 1998/09/14 18:39:51 stanton Exp $ +'\" RCS: @(#) $Id: binary.n,v 1.3 1999/04/16 00:46:34 stanton Exp $ '\" .so man.macros .TH binary n 8.0 Tcl "Tcl Built-In Commands" @@ -119,7 +119,7 @@ remaining bits of the last byte will be zeros. For example, .CS \fBbinary format h3h* AB def\fR .CE -will return a string equivalent to \fB\\xba\\xed\\x0f\fR. +will return a string equivalent to \fB\\xba\\x00\\xed\\x0f\fR. .RE .IP \fBH\fR 5 This form is the same as \fBh\fR except that the digits are stored in @@ -128,7 +128,7 @@ high-to-low order within each byte. For example, .CS \fBbinary format H3H* ab DEF\fR .CE -will return a string equivalent to \fB\\xab\\xde\\xf0\fR. +will return a string equivalent to \fB\\xab\\x00\\xde\\xf0\fR. .RE .IP \fBc\fR 5 Stores one or more 8-bit integer values in the output string. If no @@ -142,10 +142,10 @@ error is generated. If the number of elements in the list is greater than \fIcount\fR, then the extra elements are ignored. For example, .RS .CS -\fBbinary format c3cc* {3 -3 128 1} 257 {2 5}\fR +\fBbinary format c3cc* {3 -3 128 1} 260 {2 5}\fR .CE will return a string equivalent to -\fB\\x03\\xfd\\x80\\x01\\x02\\x05\fR, whereas +\fB\\x03\\xfd\\x80\\x04\\x02\\x05\fR, whereas .CS \fBbinary format c {2 5}\fR .CE @@ -186,7 +186,7 @@ example, \fBbinary format i3 {3 -3 65536 1}\fR .CE will return a string equivalent to -\fB\\x03\\x00\\x00\\x00\\xfd\\xff\\xff\\xff\\x00\\x00\\x10\\x00\fR. +\fB\\x03\\x00\\x00\\x00\\xfd\\xff\\xff\\xff\\x00\\x00\\x01\\x00\fR .RE .IP \fBI\fR 5 This form is the same as \fBi\fR except that it stores one or more one @@ -197,7 +197,7 @@ For example, \fBbinary format I3 {3 -3 65536 1}\fR .CE will return a string equivalent to -\fB\\x00\\x00\\x00\\x03\\xff\\xff\\xff\\xfd\\x00\\x10\\x00\\x00\fR. +\fB\\x00\\x00\\x00\\x03\\xff\\xff\\xff\\xfd\\x00\\x01\\x00\\x00\fR .RE .IP \fBf\fR 5 This form is the same as \fBc\fR except that it stores one or more one @@ -318,7 +318,7 @@ This form is the same as \fBa\fR, except trailing blanks and nulls are stripped the scanned value before it is stored in the variable. For example, .RS .CS -\fBbinary scan "abc efghi \\000" a* var1\fR +\fBbinary scan "abc efghi \\000" A* var1\fR .CE will return \fB1\fR with \fBabc efghi\fR stored in \fBvar1\fR. .RE @@ -338,11 +338,11 @@ will return \fB2\fR with \fB11100\fR stored in \fBvar1\fR and \fB1110000110100000\fR stored in \fBvar2\fR. .RE .IP \fBB\fR 5 -This form is the same as \fBB\fR, except the bits are taken in +This form is the same as \fBb\fR, except the bits are taken in high-to-low order within each byte. For example, .RS .CS -\fBbinary scan \\x70\\x87\\x05 b5b* var1 var2\fR +\fBbinary scan \\x70\\x87\\x05 B5B* var1 var2\fR .CE will return \fB2\fR with \fB01110\fR stored in \fBvar1\fR and \fB1000011100000101\fR stored in \fBvar2\fR. @@ -365,7 +365,7 @@ will return \fB2\fR with \fB706\fR stored in \fBvar1\fR and .RE .IP \fBH\fR 5 This form is the same as \fBh\fR, except the digits are taken in -low-to-high order within each byte. For example, +high-to-low order within each byte. For example, .RS .CS \fBbinary scan \\x07\\x86\\x05 H3H* var1 var2\fR diff --git a/doc/catch.n b/doc/catch.n index 17b5c1d..23771f9 100644 --- a/doc/catch.n +++ b/doc/catch.n @@ -5,10 +5,10 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: catch.n,v 1.2 1998/09/14 18:39:51 stanton Exp $ +'\" RCS: @(#) $Id: catch.n,v 1.3 1999/04/16 00:46:34 stanton Exp $ '\" .so man.macros -.TH catch n "" Tcl "Tcl Built-In Commands" +.TH catch n "8.0" Tcl "Tcl Built-In Commands" .BS '\" Note: do not modify the .SH NAME line immediately below! .SH NAME @@ -19,22 +19,52 @@ catch \- Evaluate script and trap exceptional returns .SH DESCRIPTION .PP -The \fBcatch\fR command may be used to prevent errors from aborting -command interpretation. \fBCatch\fR calls the Tcl interpreter recursively -to execute \fIscript\fR, and always returns a TCL_OK code, regardless of -any errors that might occur while executing \fIscript\fR. The return -value from \fBcatch\fR is a decimal string giving the -code returned by the Tcl interpreter after executing \fIscript\fR. -This will be \fB0\fR (TCL_OK) if there were no errors in \fIscript\fR; -otherwise -it will have a non-zero value corresponding to one of the exceptional -return codes (see tcl.h for the definitions of code values). If the -\fIvarName\fR argument is given, then it gives the name of a variable; -\fBcatch\fR will set the variable to the string returned -from \fIscript\fR (either a result or an error message). +The \fBcatch\fR command may be used to prevent errors from aborting command +interpretation. \fBCatch\fR calls the Tcl interpreter recursively to +execute \fIscript\fR, and always returns without raising an error, +regardless of any errors that might occur while executing \fIscript\fR. +.PP +If \fIscript\fR raises an error, \fBcatch\fR will return a non-zero integer +value corresponding to one of the exceptional return codes (see tcl.h +for the definitions of code values). If the \fIvarName\fR argument is +given, then the variable it names is set to the error message from +interpreting \fIscript\fR. +.PP +If \fIscript\fR does not raise an error, \fBcatch\fR will return 0 +(TCL_OK) and set the variable to the value returned from \fIscript\fR. .PP Note that \fBcatch\fR catches all exceptions, including those -generated by \fBbreak\fR and \fBcontinue\fR as well as errors. +generated by \fBbreak\fR and \fBcontinue\fR as well as errors. The +only errors that are not caught are syntax errors found when the +script is compiled. This is because the catch command only catches +errors during runtime. When the catch statement is compiled, the +script is compiled as well and any syntax errors will generate a Tcl +error. + +.SH EXAMPLES + +The \fBcatch\fR command may be used in an \fBif\fR to branch based on +the success of a script. + +.DS +.CS +if { [catch {open $someFile w} fid] } { + puts stderr "Could not open $someFile for writing\\n$fid" + exit 1 +} +.CE +.DE +The \fBcatch\fR command will not catch compiled syntax errors. The +first time proc \fBfoo\fR is called, the body will be compiled and a +Tcl error will be generated. + +.DS +.CS +proc foo {} { + catch {expr {1 +- }} +} +.CE +.DE .SH KEYWORDS catch, error diff --git a/doc/dde.n b/doc/dde.n new file mode 100644 index 0000000..c9797a6 --- /dev/null +++ b/doc/dde.n @@ -0,0 +1,124 @@ +'\" +'\" 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: dde.n,v 1.2 1999/04/16 00:46:34 stanton Exp $ +'\" +.so man.macros +.TH dde n 8.1 Tcl "Tcl Built-In Commands" +.BS +'\" Note: do not modify the .SH NAME line immediately below! +.SH NAME +dde \- Execute a Dynamic Data Exchange command +.SH SYNOPSIS +.sp +\fBpackage require dde 1.0\fR +.sp +\fBdde \fIservername \fR?\fItopic\fR? +.sp +\fBdde ?\-async?\fR \fIcommand service topic \fR?\fIdata\fR? +.BE + +.SH DESCRIPTION +.PP +This command allows an application to send Dynamic Data Exchange (DDE) +command when running under Microsoft Windows. Dynamic Data Exchange is +a mechanism where applications can exchange raw data. Each DDE +transaction needs a \fIservice name\fR and a \fItopic\fR. Both the +\fIservice name\fR and \fItopic\fR are application defined; Tcl uses +the service name \fBTclEval\fR, while the topic name is the name of the +interpreter given by \fBdde servername\fR. Other applications have their +own \fIservice names\fR and \fItopics\fR. For instance, Microsoft Excel +has the service name \fBExcel\fR. +.PP +The only option to the \fBdde\fR command is: +.TP +\fB\-async\fR +Requests asynchronous invocation. This is valid only for the +\fBexecute\fR subcommand. Normally, the \fBdde execute\fR subcommand +waits until the command completes, returning appropriate error +messages. When the \fB\-async\fR option is used, the command returns +immediately, and no error information is available. +.SH "DDE COMMANDS" +.PP +The following commands are a subset of the full Dynamic Data Exchange +set of commands. +.TP +\fBdde servername \fR?\fItopic\fR? +\fBdde servername\fR registers the interpreter as a DDE server with +the service name TclEval and the topic name specified byt \fItopic\fR. +If no \fItopic\fR is given, \fBdde servername\fR returns the name +of the current topic or the empty string if it is not registered as a service. +.TP +\fBdde execute \fIservice topic data\fR +\fBdde execute\fR takes the \fIdata\fR and sends it to the server +indicated by \fIservice\fR with the topic indicated by +\fItopic\fR. Typically, \fIservice\fR is the name of an application, +and \fItopic\fR is a file to work on. The \fIdata\fR field is given +to the remote application. Typically, the application treats the +\fIdata\fR field as a script, and the script is run in the +application. The command returns an error if the script did not +run. If the \fB\-async\fR flag was used, the command +returns immediately with no error. +.TP +\fBdde request \fIservice topic item\fR +\fBdde request\fR is typically used to get the value of something; the +value of a cell in Microsoft Excel or the text of a selection in +Microsoft Word. \fIservice\fR is typically the name of an application, +\fItopic\fR is typically the name of the file, and \fIitem\fR is +application-specific. The command returns the value of \fIitem\fR as +defined in the application. +.TP +\fBdde services \fIservice topic\fR +\fBdde services\fR returns a list of service-topic pairs that +currently exist on the machine. If \fIservice\fR and \fItopic\fR are +both null strings ({}), then all service-topic pairs currently +available on the system are returned. If \fIservice\fR is null and +\fItopic\fR is not, then all services with the specified topic are +returned. If \fIservice\fR is not null and \fItopic\fR is, all topics +for a given service are returned. If both are not null, if that +service-topic pair currently exists, it is returned; otherwise, null +is returned. +.TP +\fBdde eval \fItopic cmd \fR?\fIarg arg ...\fR? +\fBdde eval\fR evaluates a command and its arguments using the +interpreter specified by \fItopic\fR. The DDE service must be the +"TclEval" service. This command can be used to replace send on Windows. +.SH "DDE AND TCL" +A Tcl interpreter always has a service name of "TclEval". Each +different interp of all running Tcl applications should a unique +name specified by \fBdde servername\fR. Each interp is available as a +DDE topic only if the \fBdde servername\fR command was used to set the +name of the topic for each interp. So a \fBdde services TclEval {}\fR +command will return a list of service-topic pairs, where each of the +currently running interps will be a topic. +.PP +When Tcl processes a \fBdde execute\fR command, the data for the +execute is run as a script in the interp named by the topic of the +\fBdde execute\fR command. +.PP +When Tcl processes a \fBdde request\fR command, it returns the value of +the variable given in the dde command in the context of the interp +named by the dde topic. Tcl reserves the variable "$TCLEVAL$EXECUTE$RESULT" +for internal use, and \fBdde request\fR commands for that variable +will give unpredictable results. +.PP +An external application which wishes to run a script in Tcl should have +that script store its result in a variable, run the \fBdde execute\fR +command, and the run \fBdde request\fR to get the value of the +variable. +.PP +When using DDE, be careful to ensure that the event queue is flushed +using either \fBupdate\fR or \fBvwait\fR. This happens by default +when using \fBwish\fR unless a blocking command is called (such as \fBexec\fR +without adding the \fB&\fR to place the process in the background). +If for any reason the event queue is not flushed, DDE commands may +hang until the event queue is flushed. This can create a deadlock +situation. +.SH KEYWORDS +application, dde, name, remote execution +.SH "SEE ALSO" +tk, winfo, send + diff --git a/doc/encoding.n b/doc/encoding.n new file mode 100644 index 0000000..fc6d4f7 --- /dev/null +++ b/doc/encoding.n @@ -0,0 +1,79 @@ +'\" +'\" Copyright (c) 1998 by Scriptics Corporation. +'\" +'\" See the file "license.terms" for information on usage and redistribution +'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. +'\" +'\" RCS: @(#) $Id: encoding.n,v 1.2 1999/04/16 00:46:34 stanton Exp $ +'\" +.so man.macros +.TH encoding n "8.1" Tcl "Tcl Built-In Commands" +.BS +.SH NAME +encoding \- Manipulate encodings +.SH SYNOPSIS +\fBencoding \fIoption\fR ?\fIarg arg ...\fR? +.BE + +.SH INTRODUCTION +.PP +Strings in Tcl are encoded using 16-bit Unicode characters. Different +operating system interfaces or applications may generate strings in +other encodings such as Shift-JIS. The \fBencoding\fR command helps +to bridge the gap between Unicode and these other formats. + +.SH DESCRIPTION +.PP +Performs one of several encoding related operations, depending on +\fIoption\fR. The legal \fIoption\fRs are: +.TP +\fBencoding convertfrom ?\fIencoding\fR? \fIdata\fR +Convert \fIdata\fR to Unicode from the specified \fIencoding\fR. The +characters in \fIdata\fR are treated as binary data where the lower +8-bits of each character is taken as a single byte. The resulting +sequence of bytes is treated as a string in the specified +\fIencoding\fR. If \fIencoding\fR is not specified, the current +system encoding is used. +.TP +\fBencoding convertto ?\fIencoding\fR? \fIstring\fR +Convert \fIstring\fR from Unicode to the specified \fIencoding\fR. +The result is a sequence of bytes that represents the converted +string. Each byte is stored in the lower 8-bits of a Unicode +character. If \fIencoding\fR is not specified, the current +system encoding is used. +.TP +\fBencoding names\fR +Returns a list containing the names of all of the encodings that are +currently available. +.TP +\fBencoding system\fR ?\fIencoding\fR? +Set the system encoding to \fIencoding\fR. If \fIencoding\fR is +omitted then the command returns the current system encoding. The +system encoding is used whenever Tcl passes strings to system calls. + +.SH EXAMPLE +.PP +It is common practice to write script files using a text editor that +produces output in the euc-jp encoding, which represents the ASCII +characters as singe bytes and Japanese characters as two bytes. This +makes it easy to embed literal strings that correspond to non-ASCII +characters by simply typing the strings in place in the script. +However, because the \fBsource\fR command always reads files using the +ISO8859-1 encoding, Tcl will treat each byte in the file as a separate +character that maps to the 00 page in Unicode. The +resulting Tcl strings will not contain the expected Japanese +characters. Instead, they will contain a sequence of Latin-1 +characters that correspond to the bytes of the original string. The +\fBencoding\fR command can be used to convert this string to the +expected Japanese Unicode characters. For example, +.CS + set s [encoding convertfrom euc-jp "\\xA4\\xCF"] +.CE +would return the Unicode string "\\u306F", which is the Hiragana +letter HA. + +.SH "SEE ALSO" +Tcl_GetEncoding + +.SH KEYWORDS +encoding @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: exec.n,v 1.2 1998/09/14 18:39:52 stanton Exp $ +'\" RCS: @(#) $Id: exec.n,v 1.3 1999/04/16 00:46:34 stanton Exp $ '\" .so man.macros .TH exec n 7.6 Tcl "Tcl Built-In Commands" @@ -202,10 +202,11 @@ instead of ``applbakery.default''). Two or more forward or backward slashes in a row in a path refer to a network path. For example, a simple concatenation of the root directory \fBc:/\fR with a subdirectory \fB/windows/system\fR will yield -\fBc://windows/system\fR (two slashes together), which refers to the -directory \fB/system\fR on the machine \fBwindows\fR (and the \fBc:/\fR is -ignored), and is not equivalent to \fBc:/windows/system\fR, which describes -a directory on the current computer. +\fBc://windows/system\fR (two slashes together), which refers to the mount +point called \fBsystem\fR on the machine called \fBwindows\fR (and the +\fBc:/\fR is ignored), and is not equivalent to \fBc:/windows/system\fR, +which describes a directory on the current computer. The \fBfile join\fR +command should be used to concatenate path components. .TP \fBWindows NT\fR . @@ -264,7 +265,7 @@ the caller must prepend ``\fBcommand.com /c\0\fR'' to the desired command. Once a 16-bit DOS application has read standard input from a console and then quit, all subsequently run 16-bit DOS applications will see the standard input as already closed. 32-bit applications do not have this -problem and will run correctly even after a 16-bit DOS application thinks +problem and will run correctly, even after a 16-bit DOS application thinks that standard input is closed. There is no known workaround for this bug at this time. .sp @@ -282,8 +283,8 @@ other end of the pipe must be closed before the 16-bit DOS application begins executing. All standard output or error from a 16-bit DOS application to a pipe is collected into temporary files; the application must terminate before the temporary files are redirected to the next stage -of the pipeline. This is due to a workaround for a Windows 95 bug in the -implementation of pipes, and is how the Windows 95 command line interpreter +of the pipeline. This is due to a workaround for a Windows 95 bug in the +implementation of pipes, and is how the standard Windows 95 DOS shell handles pipes itself. .sp Certain applications, such as \fBcommand.com\fR, should not be executed diff --git a/doc/fconfigure.n b/doc/fconfigure.n index 720b206..e2479e8a 100644 --- a/doc/fconfigure.n +++ b/doc/fconfigure.n @@ -4,10 +4,10 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: fconfigure.n,v 1.2 1998/09/14 18:39:52 stanton Exp $ +'\" RCS: @(#) $Id: fconfigure.n,v 1.3 1999/04/16 00:46:34 stanton Exp $ '\" .so man.macros -.TH fconfigure n 7.5 Tcl "Tcl Built-In Commands" +.TH fconfigure n 8.1 Tcl "Tcl Built-In Commands" .BS '\" Note: do not modify the .SH NAME line immediately below! .SH NAME @@ -51,122 +51,143 @@ using the Tcl event loop (e.g. by calling \fBTcl_DoOneEvent\fR or invoking the \fBvwait\fR command). .TP \fB\-buffering\fR \fInewValue\fR +. If \fInewValue\fR is \fBfull\fR then the I/O system will buffer output until its internal buffer is full or until the \fBflush\fR command is invoked. If \fInewValue\fR is \fBline\fR, then the I/O system will automatically flush output for the channel whenever a newline character is output. If \fInewValue\fR is \fBnone\fR, the I/O system will flush -automatically after every output operation. -The default is for \fB\-buffering\fR to be set to \fBfull\fR except for -channels that connect to terminal-like devices; for these channels the -initial setting is \fBline\fR. +automatically after every output operation. The default is for +\fB\-buffering\fR to be set to \fBfull\fR except for channels that +connect to terminal-like devices; for these channels the initial setting +is \fBline\fR. .TP \fB\-buffersize\fR \fInewSize\fR +. \fINewvalue\fR must be an integer; its value is used to set the size of buffers, in bytes, subsequently allocated for this channel to store input or output. \fINewvalue\fR must be between ten and one million, allowing buffers of ten to one million bytes in size. +.VS 8.1 br +.TP +\fB\-encoding\fR \fIname\fR +. +This option is used to specify the encoding of the channel, so that the data +can be converted to and from Unicode for use in Tcl. For instance, in +order for Tcl to read characters from a Japanese file in \fBshiftjis\fR +and properly process and display the contents, the encoding would be set +to \fBshiftjis\fR. Thereafter, when reading from the channel, the bytes in +the Japanese file would be converted to Unicode as they are read. +Writing is also supported \- as Tcl strings are written to the channel they +will automatically be converted to the specified encoding on output. +.RS +.PP +If a file contains pure binary data (for instance, a JPEG image), the +encoding for the channel should be configured to be \fBbinary\fR. Tcl +will then assign no interpretation to the data in the file and simply read or +write raw bytes. The Tcl \fBbinary\fR command can be used to manipulate this +byte-oriented data. +.PP +The default encoding for newly opened channels is the same platform- and +locale-dependent system encoding used for interfacing with the operating +system. +.RE +.VE .TP \fB\-eofchar\fR \fIchar\fR .TP \fB\-eofchar\fR \fB{\fIinChar outChar\fB}\fR -This option supports DOS file systems that use Control-z (\ex1a) as -an end of file marker. -If \fIchar\fR is not an empty string, then this character signals -end of file when it is encountered during input. -For output, the end of file character is output when -the channel is closed. -If \fIchar\fR is the empty string, then there is no special -end of file character marker. -For read-write channels, a two-element list specifies -the end of file marker for input and output, respectively. -As a convenience, when setting the end-of-file character -for a read-write channel -you can specify a single value that will apply to both reading and writing. -When querying the end-of-file character of a read-write channel, -a two-element list will always be returned. -The default value for \fB\-eofchar\fR is the empty string in all -cases except for files under Windows. In that case the \fB\-eofchar\fR -is Control-z (\ex1a) for reading and the empty string for writing. +. +This option supports DOS file systems that use Control-z (\ex1a) as an +end of file marker. If \fIchar\fR is not an empty string, then this +character signals end-of-file when it is encountered during input. For +output, the end-of-file character is output when the channel is closed. +If \fIchar\fR is the empty string, then there is no special end of file +character marker. For read-write channels, a two-element list specifies +the end of file marker for input and output, respectively. As a +convenience, when setting the end-of-file character for a read-write +channel you can specify a single value that will apply to both reading +and writing. When querying the end-of-file character of a read-write +channel, a two-element list will always be returned. The default value +for \fB\-eofchar\fR is the empty string in all cases except for files +under Windows. In that case the \fB\-eofchar\fR is Control-z (\ex1a) for +reading and the empty string for writing. .TP \fB\-translation\fR \fImode\fR .TP -\fB\-translation\fR \fB{\fIinMode outMode\fB}\fR -In Tcl scripts the end of a line is always represented using a -single newline character (\en). -However, in actual files and devices the end of a line may be -represented differently on different platforms, or even for -different devices on the same platform. For example, under UNIX -newlines are used in files, whereas carriage-return-linefeed -sequences are normally used in network connections. -On input (i.e., with \fBgets\fP and \fBread\fP) -the Tcl I/O system automatically translates the external end-of-line -representation into newline characters. -Upon output (i.e., with \fBputs\fP), -the I/O system translates newlines to the external -end-of-line representation. -The default translation mode, \fBauto\fP, handles all the common -cases automatically, but the \fB\-translation\fR option provides -explicit control over the end of line translations. +\fB\-translation\fR \fB{\fIinMode outMode\fB}\fR +. +In Tcl scripts the end of a line is always represented using a single +newline character (\en). However, in actual files and devices the end of +a line may be represented differently on different platforms, or even for +different devices on the same platform. For example, under UNIX newlines +are used in files, whereas carriage-return-linefeed sequences are +normally used in network connections. On input (i.e., with \fBgets\fP +and \fBread\fP) the Tcl I/O system automatically translates the external +end-of-line representation into newline characters. Upon output (i.e., +with \fBputs\fP), the I/O system translates newlines to the external +end-of-line representation. The default translation mode, \fBauto\fP, +handles all the common cases automatically, but the \fB\-translation\fR +option provides explicit control over the end of line translations. .RS .PP The value associated with \fB\-translation\fR is a single item for -read-only and write-only channels. -The value is a two-element list for read-write channels; -the read translation mode is the first element of the list, -and the write translation mode is the second element. -As a convenience, when setting the translation mode for a read-write channel -you can specify a single value that will apply to both reading and writing. -When querying the translation mode of a read-write channel, -a two-element list will always be returned. -The following values are currently supported: +read-only and write-only channels. The value is a two-element list for +read-write channels; the read translation mode is the first element of +the list, and the write translation mode is the second element. As a +convenience, when setting the translation mode for a read-write channel +you can specify a single value that will apply to both reading and +writing. When querying the translation mode of a read-write channel, a +two-element list will always be returned. The following values are +currently supported: .TP \fBauto\fR -As the input translation mode, \fBauto\fR treats any of newline (\fBlf\fP), -carriage return (\fBcr\fP), or carriage return followed by a newline (\fBcrlf\fP) -as the end of line representation. The end of line representation can -even change from line-to-line, and all cases are translated to a newline. -As the output translation mode, \fBauto\fR chooses a platform specific -representation; for sockets on all platforms Tcl -chooses \fBcrlf\fR, for all Unix flavors, it chooses \fBlf\fR, for the +. +As the input translation mode, \fBauto\fR treats any of newline +(\fBlf\fP), carriage return (\fBcr\fP), or carriage return followed by a +newline (\fBcrlf\fP) as the end of line representation. The end of line +representation can even change from line-to-line, and all cases are +translated to a newline. As the output translation mode, \fBauto\fR +chooses a platform specific representation; for sockets on all platforms +Tcl chooses \fBcrlf\fR, for all Unix flavors, it chooses \fBlf\fR, for the Macintosh platform it chooses \fBcr\fR and for the various flavors of -Windows it chooses \fBcrlf\fR. -The default setting for \fB\-translation\fR is \fBauto\fR for both -input and output. +Windows it chooses \fBcrlf\fR. The default setting for +\fB\-translation\fR is \fBauto\fR for both input and output. +.VS 8.1 br .TP -\fBbinary\fR +\fBbinary\fR +. No end-of-line translations are performed. This is nearly identical to \fBlf\fP mode, except that in addition \fBbinary\fP mode also sets the -end of file character to the empty string, which disables it. -See the description of -\fB\-eofchar\fP for more information. +end-of-file character to the empty string (which disables it) and sets the +encoding to \fBbinary\fR (which disables encoding filtering). See the +description of \fB\-eofchar\fR and \fB\-encoding\fR for more information. +.VE .TP \fBcr\fR -The end of a line in the underlying file or device is represented -by a single carriage return character. -As the input translation mode, \fBcr\fP mode converts carriage returns -to newline characters. -As the output translation mode, \fBcr\fP mode -translates newline characters to carriage returns. -This mode is typically used on Macintosh platforms. +. +The end of a line in the underlying file or device is represented by a +single carriage return character. As the input translation mode, +\fBcr\fP mode converts carriage returns to newline characters. As the +output translation mode, \fBcr\fP mode translates newline characters to +carriage returns. This mode is typically used on Macintosh platforms. .TP \fBcrlf\fR -The end of a line in the underlying file or device is represented -by a carriage return character followed by a linefeed character. -As the input translation mode, \fBcrlf\fP mode converts -carriage-return-linefeed sequences -to newline characters. -As the output translation mode, \fBcrlf\fP mode -translates newline characters to -carriage-return-linefeed sequences. -This mode is typically used on Windows platforms and for network -connections. +. +The end of a line in the underlying file or device is represented by a +carriage return character followed by a linefeed character. As the input +translation mode, \fBcrlf\fP mode converts carriage-return-linefeed +sequences to newline characters. As the output translation mode, +\fBcrlf\fP mode translates newline characters to carriage-return-linefeed +sequences. This mode is typically used on Windows platforms and for +network connections. .TP \fBlf\fR -The end of a line in the underlying file or device is represented -by a single newline (linefeed) character. -In this mode no translations occur during either input or output. -This mode is typically used on UNIX platforms. +. +The end of a line in the underlying file or device is represented by a +single newline (linefeed) character. In this mode no translations occur +during either input or output. This mode is typically used on UNIX +platforms. .RE .PP @@ -175,4 +196,5 @@ close(n), flush(n), gets(n), puts(n), read(n), socket(n) .SH KEYWORDS blocking, buffering, carriage return, end of line, flushing, linemode, -newline, nonblocking, platform, translation +newline, nonblocking, platform, translation, encoding, filter, byte array, +binary diff --git a/doc/format.n b/doc/format.n index 8161ee6..9f737e0 100644 --- a/doc/format.n +++ b/doc/format.n @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: format.n,v 1.2 1998/09/14 18:39:52 stanton Exp $ +'\" RCS: @(#) $Id: format.n,v 1.3 1999/04/16 00:46:34 stanton Exp $ '\" .so man.macros .TH format n "" Tcl "Tcl Built-In Commands" @@ -154,9 +154,11 @@ Convert integer to unsigned octal string. \fBx\fR or \fBX\fR Convert integer to unsigned hexadecimal string, using digits ``0123456789abcdef'' for \fBx\fR and ``0123456789ABCDEF'' for \fBX\fR). +.VS .TP 10 \fBc\fR -Convert integer to the 8-bit character it represents. +Convert integer to the Unicode character it represents. +.VE .TP 10 \fBs\fR No conversion; just insert string. @@ -5,10 +5,10 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: glob.n,v 1.2 1998/09/14 18:39:52 stanton Exp $ +'\" RCS: @(#) $Id: glob.n,v 1.3 1999/04/16 00:46:35 stanton Exp $ '\" .so man.macros -.TH glob n 7.5 Tcl "Tcl Built-In Commands" +.TH glob n 8.1 Tcl "Tcl Built-In Commands" .BS '\" Note: do not modify the .SH NAME line immediately below! .SH NAME @@ -76,9 +76,18 @@ contains a ?, *, or [] construct. Unlike other Tcl commands that will accept both network and native style names (see the \fBfilename\fR manual entry for details on how native and network names are specified), the \fBglob\fR command only -accepts native names. Also, for Windows UNC names, the servername and -sharename components of the path may not contain ?, *, or [] -constructs. +accepts native names. +.VS 8.1 +.TP +\fBWindows\fR +. +For Windows UNC names, the servername and sharename components of the path +may not contain ?, *, or [] constructs. On Windows NT, if \fIpattern\fR is +of the form ``\fB~\fIusername\fB@\fIdomain\fR'' it refers to the home +directory of the user whose account information resides on the specified NT +domain server. Otherwise, user account information is obtained from +the local computer. +.VE .SH KEYWORDS exist, file, glob, pattern @@ -4,7 +4,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: http.n,v 1.2 1998/09/14 18:39:53 stanton Exp $ +'\" RCS: @(#) $Id: http.n,v 1.3 1999/04/16 00:46:35 stanton Exp $ '\" .so man.macros .TH "Http" n 8.0 Tcl "Tcl Built-In Commands" @@ -250,7 +250,9 @@ Use this construct to create an easy-to-use array variable: .CS upvar #0 $token state .CE -The following elements of the array are supported: +Once the data associated with the url is no longer needed, the state +array should be unset to free up storage. The following elements of +the array are supported: .RS .TP \fBbody\fR diff --git a/doc/library.n b/doc/library.n index a760c04..eb20351 100644 --- a/doc/library.n +++ b/doc/library.n @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: library.n,v 1.5 1998/10/30 23:02:02 welch Exp $ +'\" RCS: @(#) $Id: library.n,v 1.6 1999/04/16 00:46:35 stanton Exp $ .so man.macros .TH library n "8.0" Tcl "Tcl Built-In Commands" .BS @@ -60,16 +60,18 @@ the auto-load mechanism defined below. The following procedures are provided in the Tcl library: .TP \fBauto_execok \fIcmd\fR -Determines whether there is an executable file by the name \fIcmd\fR. -This command examines the directories in the current search path -(given by the PATH environment variable) to see if there is an -executable file named \fIcmd\fR in any of those directories. -If so, it returns 1; if not it returns 0. \fBAuto_exec\fR -remembers information about previous searches in an array -named \fBauto_execs\fR; this avoids the path search in -future calls for the same \fIcmd\fR. The command \fBauto_reset\fR -may be used to force \fBauto_execok\fR to forget its cached -information. +Determines whether there is an executable file or shell builtin +by the name \fIcmd\fR. If so, it returns a list of arguments to be +passed to \fBexec\fR to execute the executable file or shell builtin +named by \fIcmd\fR. If not, it returns an empty string. This command +examines the directories in the current search path (given by the PATH +environment variable) in its search for an executable file named +\fIcmd\fR. On Windows platforms, the search is expanded with the same +directories and file extensions as used by \fBexec\fR. \fBAuto_exec\fR +remembers information about previous searches in an array named +\fBauto_execs\fR; this avoids the path search in future calls for the +same \fIcmd\fR. The command \fBauto_reset\fR may be used to force +\fBauto_execok\fR to forget its cached information. .TP \fBauto_load \fIcmd\fR This command attempts to load the definition for a Tcl command named diff --git a/doc/man.macros b/doc/man.macros index 86525bd..bdf69ff 100644 --- a/doc/man.macros +++ b/doc/man.macros @@ -59,7 +59,7 @@ '\" .UL arg1 arg2 '\" Print arg1 underlined, then print arg2 normally. '\" -'\" RCS: @(#) $Id: man.macros,v 1.2 1998/09/14 18:39:54 stanton Exp $ +'\" RCS: @(#) $Id: man.macros,v 1.3 1999/04/16 00:46:35 stanton Exp $ '\" '\" # Set up traps and other miscellaneous stuff for Tcl/Tk man pages. .if t .wh -1.3i ^B @@ -72,8 +72,8 @@ . ie !"\\$2"" .TP \\n()Cu . el .TP 15 .\} -.ie !"\\$3"" \{\ .ta \\n()Au \\n()Bu +.ie !"\\$3"" \{\ \&\\$1 \\fI\\$2\\fP (\\$3) .\".b .\} diff --git a/doc/msgcat.n b/doc/msgcat.n new file mode 100644 index 0000000..e04d2a6 --- /dev/null +++ b/doc/msgcat.n @@ -0,0 +1,207 @@ +'\" +'\" Copyright (c) 1998 Mark Harrison. +'\" +'\" See the file "license.terms" for information on usage and redistribution +'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. +'\" +'\" SCCS: @(#) msgcat.n +'\" +.so man.macros +.TH "msgcat" n 8.1 Tcl "Tcl Built-In Commands" +.BS +'\" Note: do not modify the .SH NAME line immediately below! +.SH NAME +msgcat \- Tcl message catalog +.SH SYNOPSIS +\fB::msgcat::mc src-string\fR +.sp +\fB::msgcat::mclocale \fR?\fInewLocale\fR? +.sp +\fB::msgcat::mcpreferences\fR +.sp +\fB::msgcat::mcload \fIdirname\fR +.sp +\fB::msgcat::mcset \fIlocale src-string \fR?\fItranslate-string\fR? +.sp +\fB::msgcat::mcunknown \fIlocale src-string\fR +.BE + +.SH DESCRIPTION +.PP +The \fBmsgcat\fR package provides a set of functions +that can be used to manage multi-lingual user interfaces. +Text strings are defined in a ``message catalog'' which +is independent from the application, and +which can be edited or localized without modifying +the application source code. New languages +or locales are provided by adding a new file to +the message catalog. +.PP +Use of the message catalog is optional by any application +or package, but is encouraged if the application or package +wishes to be enabled for multi-lingual applications. + +.SH COMMANDS +.TP +\fB::msgcat::mc src-string\fR +Returns a translation of \fIsrc-string\fR according to the +user's current locale. If no translation string +exists, \fB::msgcat::mcunknown\fR is called and the string +returned from \fB::msgcat::mcunknown\fR is returned. +.PP +\fB::msgcat::mc\fR is the main function used to localize an +application. Instead of using an English string directly, an +applicaton can pass the English string through \fB::msgcat::mc\fR and +use the result. If an application is written for a single language in +this fashion, then it is easy to add support for additional languages +later simply by defining new message catalog entries. +.TP +\fB::msgcat::mclocale \fR?\fInewLocale\fR? +This function sets the locale to \fInewLocale\fR. If \fInewLocale\fR +is omitted, the current locale is returned, otherwise the new locale +is returned. The initial locale defaults to the locale specified in +the user's environment. See \fBLOCALE AND SUBLOCALE SPECIFICATION\fR +below for a description of the locale string format. +.TP +\fB::msgcat::mcpreferences\fR +Returns an ordered list of the locales preferred by +the user, based on the user's language specification. +The list is ordered from most specific to least +preference. If the user has specified LANG=en_US_funky, +this procedure would return {en_US_funky en_US en}. +.TP +\fB::msgcat::mcload \fIdirname\fR +Searches the specified directory for files that match +the language specifications returned by \fB::msgcat::mcpreferences\fR. +Each file located is sourced. The file extension is ``.msg''. +The number of message files which matched the specification +and were loaded is returned. +.TP +\fB::msgcat::mcset \fIlocale src-string \fR?\fItranslate-string\fR? +Sets the translation for \fIsrc-string\fR to \fItranslate-string\fR +in the specified \fIlocale\fR. If \fItranslate-string\fR is not +specified, \fIsrc-string\fR is used for both. The function +return \fItranslate-string\fR. +.TP +\fB::msgcat::mcunknown \fIlocale src-string\fR +This routine is called by \fB::msgcat::mc\fR in the case when +a translation for \fIsrc-string\fR is not defined in the +current locale. The default action is to return +\fIsrc-string\fR. This procedure can be redefined by the +application, for example to log error messages for each unknown +string. The \fB::msgcat::mcunknown\fB procedure is invoked at the +same stack context as the call to \fB::msgcat::mc\fR. The return vaue +of \fB::msgcat::mcunknown\fB is used as the return vaue for the call +to \fB::msgcat::mc\fR. + +.SH "LOCALE AND SUBLOCALE SPECIFICATION" +.PP +The locale is specified by a locale string. +The locale string consists of +a language code, an optional country code, and an optional +system-specific code, each separated by ``_''. The country and language +codes are specified in standards ISO-639 and ISO-3166. +For example, the locale ``en'' specifies English and + ``en_US'' specifes U.S. English. +.PP +The locale defaults to the value in \fBenv(LANG)\fR at the time the +\fBmsgcat\fR package is loaded. If \fBenv(LANG)\fR is not defined, then the +locale defaults to ``C''. +.PP +When a locale is specified by the user, a ``best match'' search is +performed during string translation. For example, if a user specifies +en_UK_Funky, the locales ``en_UK_Funky'', ``en_UK'', and ``en'' are +searched in order until a matching translation string is found. If no +translation string is available, then \fB::msgcat::unknown\fR is +called. + +.SH "NAMESPACES AND MESSAGE CATALOGS" +.PP +Strings stored in the message catalog are stored relative +to the namespace from which they were added. This allows +multiple packages to use the same strings without fear +of collisions with other packages. It also allows the +source string to be shorter and less prone to typographical +error. +.PP +For example, executing the code +.CS +mcset en hello "hello from ::" +namespace eval foo {mcset en hello "hello from ::foo"} +puts [mc hello] +namespace eval foo {puts [mc hello]} +.CE +will print +.CS +hello from :: +hello from ::foo +.CE + +.SH "LOCATION AND FORMAT OF MESSAGE FILES" +.PP +Message files can be located in any directory, subject +to the following conditions: +.IP [1] +All message files for a package are in the same directory. +.IP [2] +The message file name is a locale specifier followed +by ``.msg''. For example: +.CS +es.msg -- spanish +en_UK.msg -- UK English +.CE +.IP [3] +The file contains a series of calls to mcset, setting the +necessary translation strings for the language. For example: +.CS +::msgcat::mcset es "Free Beer!" "Cerveza Gracias!" +.CE + +.SH "RECOMMENDED MESSAGE SETUP FOR PACKAGES" +.PP +If a package is installed into a subdirectory of the +\fBtcl_pkgPath\fR and loaded via \fBpackage require\fR, the +following procedure is recommended. +.IP [1] +During package installation, create a subdirectory +\fBmsgs\fR under your package directory. +.IP [2] +Copy your *.msg files into that directory. +.IP [3] + Add the following command to your package +initialization script: +.CS +# load language files, stored in msgs subdirectory +::msgcat::mcload [file join [file dirname [info script]] msgs] +.CE + +.SH "POSTITIONAL CODES FOR FORMAT AND SCAN COMMANDS" +.PP +It is possible that a message string used as an argument +to \fBformat\fR might have positionally dependent parameters that +might need to be repositioned. For example, it might be +syntactically desirable to rearrange the sentence structure +while translating. +.CS +format "We produced %d units in location %s" $num $city +format "In location %s we produced %d units" $city $num +.CE +.PP +This can be handled by using the positional +parameters: +.CS +format "We produced %1\\\\$d units in location %2\\\\$s" $num $city +format "In location %2\\\\$s we produced %1\\\\$d units" $num $city +.CE +.PP +Similarly, positional parameters can be used with \fBscan\fR to +extract values from internationalized strings. + +.SH "SEE ALSO" +format(n), scan(n), namespace(n), package(n) + +.SH CREDITS +.PP +The message catalog code was developed by Mark Harrison. +.SH KEYWORDS +internationalization, i18n, localization, l10n, message, text, translation diff --git a/doc/namespace.n b/doc/namespace.n index a8b6b16..eeb45f5 100644 --- a/doc/namespace.n +++ b/doc/namespace.n @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: namespace.n,v 1.2 1998/09/14 18:39:54 stanton Exp $ +'\" RCS: @(#) $Id: namespace.n,v 1.3 1999/04/16 00:46:35 stanton Exp $ '\" .so man.macros .TH namespace n 8.0 Tcl "Tcl Built-In Commands" @@ -245,21 +245,21 @@ The \fBnamespace eval\fR command lets you create new namespaces. For example, .CS \fBnamespace eval Counter { - namespace export Bump + namespace export bump variable num 0 - proc Bump {} { + proc bump {} { variable num incr num } }\fR .CE creates a new namespace containing the variable \fBnum\fR and -the procedure \fBBump\fR. +the procedure \fBbump\fR. The commands and variables in this namespace are separate from other commands and variables in the same program. -If there is a command named \fBBump\fR in the global namespace, -for example, it will be different from the command \fBBump\fR +If there is a command named \fBbump\fR in the global namespace, +for example, it will be different from the command \fBbump\fR in the \fBCounter\fR namespace. .PP Namespace variables resemble global variables in Tcl. @@ -276,7 +276,7 @@ as the namespace definition shown above: .CS \fBnamespace eval Counter { variable num 0 - proc Bump {} { + proc bump {} { variable num return [incr num] } @@ -322,7 +322,7 @@ Names must be qualified by the namespace that contains them. From the global namespace, we might access the \fBCounter\fR procedures like this: .CS -\fBCounter::Bump 5 +\fBCounter::bump 5 Counter::Reset\fR .CE We could access the current count like this: @@ -332,10 +332,10 @@ We could access the current count like this: When one namespace contains another, you may need more than one qualifier to reach its elements. If we had a namespace \fBFoo\fR that contained the namespace \fBCounter\fR, -you could invoke its \fBBump\fR procedure +you could invoke its \fBbump\fR procedure from the global namespace like this: .CS -\fBFoo::Counter::Bump 3\fR +\fBFoo::Counter::bump 3\fR .CE .PP You can also use qualified names when you create and rename commands. @@ -517,36 +517,36 @@ the command is automatically removed from all namespaces that import it. You can export commands from a namespace like this: .CS \fBnamespace eval Counter { - namespace export Bump Reset - variable num 0 - variable max 100 + namespace export bump reset + variable Num 0 + variable Max 100 - proc Bump {{by 1}} { - variable num - incr num $by - check - return $num + proc bump {{by 1}} { + variable Num + incr Num $by + Check + return $Num } - proc Reset {} { - variable num - set num 0 + proc reset {} { + variable Num + set Num 0 } - proc check {} { - variable num - variable max - if {$num > $max} { + proc Check {} { + variable Num + variable Max + if {$Num > $Max} { error "too high!" } } }\fR .CE -The procedures \fBBump\fR and \fBReset\fR are exported, +The procedures \fBbump\fR and \fBreset\fR are exported, so they are included when you import from the \fBCounter\fR namespace, like this: .CS \fBnamespace import Counter::*\fR .CE -However, the \fBcheck\fR procedure is not exported, +However, the \fBCheck\fR procedure is not exported, so it is ignored by the import operation. .PP The \fBnamespace import\fR command only imports commands @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: open.n,v 1.3 1999/04/15 22:38:46 stanton Exp $ +'\" RCS: @(#) $Id: open.n,v 1.4 1999/04/16 00:46:35 stanton Exp $ '\" .so man.macros .TH open n 7.6 Tcl "Tcl Built-In Commands" @@ -217,9 +217,7 @@ no interactions between command pipelines and the console. .TP \fBMacintosh\fR . -Access to the serial port is not accomplished through magic cookies passed -to the \fIopen\fR command on the Macintosh. Instead, you can use Sean Wood's -(yoda@drexel.edu) \fIDevice\fR extension for the same purpose. +Opening a serial port is not currently implemented under Macintosh. .sp Opening a command pipeline is not supported under Macintosh, since applications do not support the concept of standard input or output. @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: puts.n,v 1.2 1998/09/14 18:39:54 stanton Exp $ +'\" RCS: @(#) $Id: puts.n,v 1.3 1999/04/16 00:46:35 stanton Exp $ '\" .so man.macros .TH puts n 7.5 Tcl "Tcl Built-In Commands" @@ -34,8 +34,8 @@ value of the \fB\-translation\fR option for the channel (for example, on PCs newlines are normally replaced with carriage-return-linefeed sequences; on Macintoshes newlines are normally replaced with carriage-returns). -See the \fBfconfigure\fR manual entry for a discussion of end-of-line -translations. +See the \fBfconfigure\fR manual entry for a discussion on ways in +which \fBfconfigure\fR will alter output. .PP Tcl buffers output internally, so characters written with \fBputs\fR may not appear immediately on the output file or device; Tcl will @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: read.n,v 1.2 1998/09/14 18:39:54 stanton Exp $ +'\" RCS: @(#) $Id: read.n,v 1.3 1999/04/16 00:46:35 stanton Exp $ '\" .so man.macros .TH read n 7.5 Tcl "Tcl Built-In Commands" @@ -40,8 +40,8 @@ before reaching the end of the file. \fBRead\fR translates end-of-line sequences in the input into newline characters according to the \fB\-translation\fR option for the channel. -See the manual entry for \fBfconfigure\fR for details on the -\fB\-translation\fR option. +See the \fBfconfigure\fR manual entry for a discussion on ways in +which \fBfconfigure\fR will alter input. .SH "SEE ALSO" eof(n), fblocked(n), fconfigure(n) diff --git a/doc/regexp.n b/doc/regexp.n index ed61c8d..0d08dcf 100644 --- a/doc/regexp.n +++ b/doc/regexp.n @@ -1,18 +1,18 @@ '\" -'\" Copyright (c) 1993 The Regents of the University of California. -'\" Copyright (c) 1994-1996 Sun Microsystems, Inc. +'\" Copyright (c) 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: regexp.n,v 1.2 1998/09/14 18:39:54 stanton Exp $ +'\" RCS: @(#) $Id: regexp.n,v 1.3 1999/04/16 00:46:35 stanton Exp $ '\" .so man.macros -.TH regexp n "" Tcl "Tcl Built-In Commands" +.TH regexp n 8.1 Tcl "Tcl Built-In Commands" .BS '\" Note: do not modify the .SH NAME line immediately below! .SH NAME regexp \- Match a regular expression against a string + .SH SYNOPSIS \fBregexp \fR?\fIswitches\fR? \fIexp string \fR?\fImatchVar\fR? ?\fIsubMatchVar subMatchVar ...\fR? .BE @@ -31,27 +31,61 @@ the characters in \fIstring\fR that matched the leftmost parenthesized subexpression within \fIexp\fR, the next \fIsubMatchVar\fR will contain the characters that matched the next parenthesized subexpression to the right in \fIexp\fR, and so on. -.LP +.PP If the initial arguments to \fBregexp\fR start with \fB\-\fR then they are treated as switches. The following switches are currently supported: -.TP 10 +.TP 15 \fB\-nocase\fR Causes upper-case characters in \fIstring\fR to be treated as lower case during the matching process. -.TP 10 +.TP 15 \fB\-indices\fR Changes what is stored in the \fIsubMatchVar\fRs. -Instead of storing the matching characters from \fBstring\fR, +Instead of storing the matching characters from \fIstring\fR, each variable will contain a list of two decimal strings giving the indices in \fIstring\fR of the first and last characters in the matching range of characters. -.TP 10 +.VS 8.1 +.TP 15 +\fB\-expanded\fR +Enables use of the expanded regular expression syntax where +whitespace and comments are ignored. This is the same as specifying +the \fB(?x)\fR embedded option (see METASYNTAX, below). +.TP 15 +\fB\-line\fR +Enables newline-sensitive matching. By default, newline is a +completely ordinary character with no special meaning. With this +flag, `[^' bracket expressions and `.' never match newline, `^' +matches an empty string after any newline in addition to its normal +function, and `$' matches an empty string before any newline in +addition to its normal function. This flag is equivalent to +specifying both \fB\-linestop\fR and \fB\-lineanchor\fR, or the +\fB(?n)\fR embedded option (see METASYNTAX, below). +.TP 15 +\fB\-linestop\fR +Changes the behavior of `[^' bracket expressions and `.' so that they +stop at newlines. This is the same as specifying the \fB(?p)\fR +embedded option (see METASYNTAX, below). +.TP 15 +\fB\-lineanchor\fR +Changes the behavior of `^' and `$' (the ``anchors'') so they match the +beginning and end of a line respectively. This is the same as +specifying the \fB(?w)\fR embedded option (see METASYNTAX, below). +.TP 15 +\fB\-about\fR +Instead of attempting to match the regular expression, returns a list +containing information about the regular expression. The first +element of the list is a subexpression count. The second element is a +list of property names that describe various attributes of the regular +expression. This switch is primarily intended for debugging purposes. +.VE 8.1 +.TP 15 \fB\-\|\-\fR Marks the end of switches. The argument following this one will be treated as \fIexp\fR even if it starts with a \fB\-\fR. -.LP +.PP If there are more \fIsubMatchVar\fR's than parenthesized subexpressions within \fIexp\fR, or if a particular subexpression in \fIexp\fR doesn't match the string (e.g. because it was in a @@ -59,87 +93,956 @@ portion of the expression that wasn't matched), then the corresponding \fIsubMatchVar\fR will be set to ``\fB\-1 \-1\fR'' if \fB\-indices\fR has been specified or to an empty string otherwise. -.SH "REGULAR EXPRESSIONS" -.PP -Regular expressions are implemented using Henry Spencer's package -(thanks, Henry!), -and much of the description of regular expressions below is copied verbatim -from his manual entry. -.PP -A regular expression is zero or more \fIbranches\fR, separated by ``|''. -It matches anything that matches one of the branches. -.PP -A branch is zero or more \fIpieces\fR, concatenated. -It matches a match for the first, followed by a match for the second, etc. -.PP -A piece is an \fIatom\fR possibly followed by ``*'', ``+'', or ``?''. -An atom followed by ``*'' matches a sequence of 0 or more matches of the atom. -An atom followed by ``+'' matches a sequence of 1 or more matches of the atom. -An atom followed by ``?'' matches a match of the atom, or the null string. -.PP -An atom is a regular expression in parentheses (matching a match for the -regular expression), a \fIrange\fR (see below), ``.'' -(matching any single character), ``^'' (matching the null string at the -beginning of the input string), ``$'' (matching the null string at the -end of the input string), a ``\e'' followed by a single character (matching -that character), or a single character with no other significance -(matching that character). -.PP -A \fIrange\fR is a sequence of characters enclosed in ``[]''. -It normally matches any single character from the sequence. -If the sequence begins with ``^'', -it matches any single character \fInot\fR from the rest of the sequence. -If two characters in the sequence are separated by ``\-'', this is shorthand -for the full list of ASCII characters between them -(e.g. ``[0-9]'' matches any decimal digit). -To include a literal ``]'' in the sequence, make it the first character -(following a possible ``^''). -To include a literal ``\-'', make it the first or last character. +.SH "DIFFERENT FLAVORS OF REs" +.VS 8.1 +Regular expressions (``RE''s), as defined by POSIX, come in two +flavors: \fIextended\fR REs (``EREs'') and \fIbasic\fR REs (``BREs''). +EREs are roughly those of the traditional \fIegrep\fR, while BREs are +roughly those of the traditional \fIed\fR . This implementation adds +a third flavor, \fIadvanced\fR REs (``AREs''), basically EREs with +some significant extensions. +.PP +This manual page primarily describes AREs. BREs mostly exist for +backward compatibility in some old programs; they will be discussed at +the end. POSIX EREs are almost an exact subset of AREs. Features of +AREs that are not present in EREs will be indicated. -.SH "CHOOSING AMONG ALTERNATIVE MATCHES" -.PP -In general there may be more than one way to match a regular expression -to an input string. For example, consider the command -.CS -\fBregexp (a*)b* aabaaabb x y\fR -.CE -Considering only the rules given so far, \fBx\fR and \fBy\fR could -end up with the values \fBaabb\fR and \fBaa\fR, \fBaaab\fR and \fBaaa\fR, -\fBab\fR and \fBa\fR, or any of several other combinations. -To resolve this potential ambiguity \fBregexp\fR chooses among -alternatives using the rule ``first then longest''. -In other words, it considers the possible matches in order working -from left to right across the input string and the pattern, and it -attempts to match longer pieces of the input string before shorter -ones. More specifically, the following rules apply in decreasing -order of priority: -.IP [1] -If a regular expression could match two different parts of an input string -then it will match the one that begins earliest. -.IP [2] -If a regular expression contains \fB|\fR operators then the leftmost -matching sub-expression is chosen. -.IP [3] -In \fB*\fR, \fB+\fR, and \fB?\fR constructs, longer matches are chosen -in preference to shorter ones. -.IP [4] -In sequences of expression components the components are considered -from left to right. -.LP -In the example from above, \fB(a*)b*\fR matches \fBaab\fR: the \fB(a*)\fR -portion of the pattern is matched first and it consumes the leading -\fBaa\fR; then the \fBb*\fR portion of the pattern consumes the -next \fBb\fR. Or, consider the following example: -.CS -\fBregexp (ab|a)(b*)c abc x y z\fR -.CE -After this command \fBx\fR will be \fBabc\fR, \fBy\fR will be -\fBab\fR, and \fBz\fR will be an empty string. -Rule 4 specifies that \fB(ab|a)\fR gets first shot at the input -string and Rule 2 specifies that the \fBab\fR sub-expression -is checked before the \fBa\fR sub-expression. -Thus the \fBb\fR has already been claimed before the \fB(b*)\fR -component is checked and \fB(b*)\fR must match an empty string. +.SH "REGULAR EXPRESSION SYNTAX" +.PP +Tcl regular expressions are implemented using the package written by +Henry Spencer, based on the 1003.2 spec and some (not quite all) of +the Perl5 extensions (thanks, Henry!). Much of the description of +regular expressions below is copied verbatim from his manual entry. +.PP +An ARE is one or more \fIbranches\fR, +separated by `\fB|\fR', +matching anything that matches any of the branches. +.PP +A branch is zero or more \fIconstraints\fR or \fIquantified atoms\fR, +concatenated. +It matches a match for the first, followed by a match for the second, etc; +an empty branch matches the empty string. +.PP +A quantified atom is an \fIatom\fR possibly followed +by a single \fIquantifier\fR. +Without a quantifier, it matches a match for the atom. +The quantifiers, +and what a so-quantified atom matches, are: +.RS 2 +.TP 6 +\fB*\fR +a sequence of 0 or more matches of the atom +.TP +\fB+\fR +a sequence of 1 or more matches of the atom +.TP +\fB?\fR +a sequence of 0 or 1 matches of the atom +.TP +\fB{\fIm\fB}\fR +a sequence of exactly \fIm\fR matches of the atom +.TP +\fB{\fIm\fB,}\fR +a sequence of \fIm\fR or more matches of the atom +.TP +\fB{\fIm\fB,\fIn\fB}\fR +a sequence of \fIm\fR through \fIn\fR (inclusive) matches of the atom; +\fIm\fR may not exceed \fIn\fR +.TP +\fB*? +? ?? {\fIm\fB}? {\fIm\fB,}? {\fIm\fB,\fIn\fB}?\fR +\fInon-greedy\fR quantifiers, +which match the same possibilities, +but prefer the smallest number rather than the largest number +of matches (see MATCHING) +.RE +.PP +The forms using +\fB{\fR and \fB}\fR +are known as \fIbound\fRs. +The numbers +\fIm\fR and \fIn\fR are unsigned decimal integers +with permissible values from 0 to 255 inclusive. +.PP +An atom is one of: +.RS 2 +.TP 6 +\fB(\fIre\fB)\fR +(where \fIre\fR is any regular expression) +matches a match for +\fIre\fR, with the match noted for possible reporting +.TP +\fB(?:\fIre\fB)\fR +as previous, +but does no reporting +(a ``non-capturing'' set of parentheses) +.TP +\fB()\fR +matches an empty string, +noted for possible reporting +.TP +\fB(?:)\fR +matches an empty string, +without reporting +.TP +\fB[\fIchars\fB]\fR +a \fIbracket expression\fR, +matching any one of the \fIchars\fR (see BRACKET EXPRESSIONS for more detail) +.TP + \fB.\fR +matches any single character +.TP +\fB\e\fIk\fR +(where \fIk\fR is a non-alphanumeric character) +matches that character taken as an ordinary character, +e.g. \e\e matches a backslash character +.TP +\fB\e\fIc\fR +where \fIc\fR is alphanumeric +(possibly followed by other characters), +an \fIescape\fR (AREs only), +see ESCAPES below +.TP +\fB{\fR +when followed by a character other than a digit, +matches the character +`\fB{\fR'; +when followed by a digit, it is the beginning of a +\fIbound\fR (see above) +.TP +\fIx\fR +where \fIx\fR is +a single character with no other significance, matches that character. +.RE +.PP +A \fIconstraint\fR matches an empty string when specific conditions +are met. +A constraint may not be followed by a quantifier. +The simple constraints are as follows; some more constraints are +described later, under ESCAPES. +.RS 2 +.TP 8 +\fB^\fR +matches at the beginning of a line +.TP +\fB$\fR +matches at the end of a line +.TP +\fB(?=\fIre\fB)\fR +\fIpositive lookahead\fR (AREs only), matches at any point +where a substring matching \fIre\fR begins +.TP +\fB(?!\fIre\fB)\fR +\fInegative lookahead\fR (AREs only), matches at any point +where no substring matching \fIre\fR begins +.RE +.PP +The lookahead constraints may not contain back references (see later), +and all parentheses within them are considered non-capturing. +.PP +An RE may not end with +`\fB\e\fR'. + +.SH "BRACKET EXPRESSIONS" +A \fIbracket expression\fR is a list of characters enclosed in +`\fB[\|]\fR'. +It normally matches any single character from the list (but see below). +If the list begins with +`\fB^\fR', +it matches any single character +(but see below) \fInot\fR from the rest of the list. +.PP +If two characters in the list are separated by +`\fB\-\fR', +this is shorthand +for the full \fIrange\fR of characters between those two (inclusive) in the +collating sequence, +e.g. +\fB[0\-9]\fR +in ASCII matches any decimal digit. +Two ranges may not share an +endpoint, so e.g. +\fBa\-c\-e\fR +is illegal. +Ranges are very collating-sequence-dependent, +and portable programs should avoid relying on them. +.PP +To include a literal +\fB]\fR +or +\fB\-\fR +in the list, +the simplest method is to +enclose it in +\fB[.\fR +and +\fB.]\fR +to make it a collating element (see below). +Alternatively, +make it the first character +(following a possible +`\fB^\fR'), +or (AREs only) precede it with +`\fB\e\fR'. +Alternatively, for +`\fB\-\fR', +make it the last character, +or the second endpoint of a range. +To use a literal +\fB\-\fR +as the first endpoint of a range, +make it a collating element +or (AREs only) precede it with +`\fB\e\fR'. +With the exception of these, some combinations using +\fB[\fR +(see next +paragraphs), and escapes, +all other special characters lose their +special significance within a bracket expression. +.PP +Within a bracket expression, a collating element (a character, +a multi-character sequence that collates as if it were a single character, +or a collating-sequence name for either) +enclosed in +\fB[.\fR +and +\fB.]\fR +stands for the +sequence of characters of that collating element. +The sequence is a single element of the bracket expression's list. +A bracket expression in a locale which has +multi-character collating elements +can thus match more than one character. +Most insidiously, if +\fB^\fR +is used, +this can happen even if no multi-character collating +elements appear in the bracket expression! +If the collating sequence includes a +\fBch\fR +multi-character collating element, +then the RE +\fB[[.ch.]]*c\fR +matches the first five characters +of +`\fBchchcc\fR', +and the RE +\fB[^c]b\fR +matches all of +`\fBchb\fR'. +.PP +Within a bracket expression, a collating element enclosed in +\fB[=\fR +and +\fB=]\fR +is an equivalence class, standing for the sequences of characters +of all collating elements equivalent to that one, including itself. +(If there are no other equivalent collating elements, +the treatment is as if the enclosing delimiters were +`\fB[.\fR'\& +and +`\fB.]\fR'.) +For example, if +\fBo\fR +and +\fB\o'o^'\fR +are the members of an equivalence class, +then +`\fB[[=o=]]\fR', +`\fB[[=\o'o^'=]]\fR', +and +`\fB[o\o'o^']\fR'\& +are all synonymous. +An equivalence class may not be an endpoint +of a range. +.PP +Within a bracket expression, the name of a \fIcharacter class\fR enclosed +in +\fB[:\fR +and +\fB:]\fR +stands for the list of all characters +(not all collating elements!) +belonging to that +class. +Standard character class names are: +.PP +.RS +.ne 5 +.nf +.ta 3c 6c 9c +\fBalnum digit punct +alpha graph space +blank lower upper +cntrl print xdigit\fR +.fi +.RE +.PP +These stand for the character classes defined in +\fIctype\fR(3). +A locale may provide others. +A character class may not be used as an endpoint of a range. +.PP +There are two special cases of bracket expressions: +the bracket expressions +\fB[[:<:]]\fR +and +\fB[[:>:]]\fR +are constraints, matching empty strings at +the beginning and end of a word respectively. +'\" note, discussion of escapes below references this definition of word +A word is defined as a sequence of +word characters +which is neither preceded nor followed by +word characters. +A word character is an +\fIalnum\fR +character (as defined by +\fIctype\fR(3)) +or an underscore +(\fB_\fR). +These special bracket expressions are deprecated; +users of AREs should use constraint escapes instead (see below). +.SH ESCAPES +Escapes (AREs only), which begin with a +\fB\e\fR +followed by an alphanumeric character, +come in several varieties: +character entry, class shorthands, constraint escapes, and back references. +A +\fB\e\fR +followed by an alphanumeric character but not constituting +a valid escape is illegal in AREs. +In EREs, there are no escapes: +outside a bracket expression, +a +\fB\e\fR +followed by an alphanumeric character merely stands for that +character as an ordinary character, +and inside a bracket expression, +\fB\e\fR +is an ordinary character. +(The latter is the one actual incompatibility between EREs and AREs.) +.PP +Character-entry escapes (AREs only) exist to make it easier to specify +non-printing and otherwise inconvenient characters in REs: +.RS 2 +.TP 5 +\fB\ea\fR +alert, aka bell, character, as in C +.TP +\fB\eb\fR +backspace, as in C +.TP +\fB\eB\fR +synonym for +\fB\e\fR +to help reduce backslash doubling in some +applications where there are multiple levels of backslash processing +.TP +\fB\ec\fIX\fR +(where X is any character) the character whose +low-order 5 bits are the same as those of +\fIX\fR, +and whose other bits are all zero +.TP +\fB\ee\fR +the character whose collating-sequence name +is +`\fBESC\fR', +or failing that, the character with octal value 033 +.TP +\fB\ef\fR +formfeed, as in C +.TP +\fB\en\fR +newline, as in C +.TP +\fB\er\fR +carriage return, as in C +.TP +\fB\et\fR +horizontal tab, as in C +.TP +\fB\eu\fIwxyz\fR +(where +\fIwxyz\fR +is exactly four hexadecimal digits) +the Unicode character +\fBU+\fIwxyz\fR +in the local byte ordering +.TP +\fB\eU\fIstuvwxyz\fR +(where +\fIstuvwxyz\fR +is exactly eight hexadecimal digits) +reserved for a somewhat-hypothetical Unicode extension to 32 bits +.TP +\fB\ev\fR +vertical tab, as in C +are all available. +.TP +\fB\ex\fIhhh\fR +(where +\fIhhh\fR +is any sequence of hexadecimal digits) +the character whose hexadecimal value is +\fB0x\fIhhh\fR +(a single character no matter how many hexadecimal digits are used). +.TP +\fB\e0\fR +the character whose value is +\fB0\fR +.TP +\fB\e\fIxy\fR +(where +\fIxy\fR +is exactly two octal digits, +and is not a +\fIback reference\fR (see below)) +the character whose octal value is +\fB0\fIxy\fR +.TP +\fB\e\fIxyz\fR +(where +\fIxyz\fR +is exactly three octal digits, +and is not a +back reference (see below)) +the character whose octal value is +\fB0\fIxyz\fR +.RE +.PP +Hexadecimal digits are +`\fB0\fR'-`\fB9\fR', +`\fBa\fR'-`\fBf\fR', +and +`\fBA\fR'-`\fBF\fR'. +Octal digits are +`\fB0\fR'-`\fB7\fR'. +.PP +The character-entry escapes are always taken as ordinary characters. +For example, +\fB\e135\fR +is +\fB]\fR +in ASCII, +but +\fB\e135\fR +does not terminate a bracket expression. +Beware, however, that some applications (e.g., C compilers) interpret +such sequences themselves before the regular-expression package +gets to see them, which may require doubling (quadrupling, etc.) the +`\fB\e\fR'. +.PP +Class-shorthand escapes (AREs only) provide shorthands for certain commonly-used +character classes: +.RS 2 +.TP 10 +\fB\ed\fR +\fB[[:digit:]]\fR +.TP +\fB\es\fR +\fB[[:space:]]\fR +.TP +\fB\ew\fR +\fB[[:alnum:]_]\fR +(note underscore) +.TP +\fB\eD\fR +\fB[^[:digit:]]\fR +.TP +\fB\eS\fR +\fB[^[:space:]]\fR +.TP +\fB\eW\fR +\fB[^[:alnum:]_]\fR +(note underscore) +.RE +.PP +Within bracket expressions, +`\fB\ed\fR', +`\fB\es\fR', +and +`\fB\ew\fR'\& +lose their outer brackets, +and +`\fB\eD\fR', +`\fB\eS\fR', +and +`\fB\eW\fR'\& +are illegal. +.PP +A constraint escape (AREs only) is a constraint, +matching the empty string if specific conditions are met, +written as an escape: +.RS 2 +.TP 6 +\fB\eA\fR +matches only at the beginning of the string +(see MATCHING, below, for how this differs from +`\fB^\fR') +.TP +\fB\em\fR +matches only at the beginning of a word +.TP +\fB\eM\fR +matches only at the end of a word +.TP +\fB\ey\fR +matches only at the beginning or end of a word +.TP +\fB\eY\fR +matches only at a point which is not the beginning or end of a word +.TP +\fB\eZ\fR +matches only at the end of the string +(see MATCHING, below, for how this differs from +`\fB$\fR') +.TP +\fB\e\fIm\fR +(where +\fIm\fR +is a nonzero digit) a \fIback reference\fR, see below +.TP +\fB\e\fImnn\fR +(where +\fIm\fR +is a nonzero digit, and +\fInn\fR +is some more digits, +and the decimal value +\fImnn\fR +is not greater than the number of closing capturing parentheses seen so far) +a \fIback reference\fR, see below +.RE +.PP +A word is defined as in the specification of +\fB[[:<:]]\fR +and +\fB[[:>:]]\fR +above. +Constraint escapes are illegal within bracket expressions. +.PP +A back reference (AREs only) matches the same string matched by the parenthesized +subexpression specified by the number, +so that (e.g.) +\fB([bc])\e1\fR +matches +\fBbb\fR +or +\fBcc\fR +but not +`\fBbc\fR'. +The subexpression must entirely precede the back reference in the RE. +Subexpressions are numbered in the order of their leading parentheses. +Non-capturing parentheses do not define subexpressions. +.PP +There is an inherent historical ambiguity between octal character-entry +escapes and back references, which is resolved by heuristics, +as hinted at above. +A leading zero always indicates an octal escape. +A single non-zero digit, not followed by another digit, +is always taken as a back reference. +A multi-digit sequence not starting with a zero is taken as a back +reference if it comes after a suitable subexpression +(i.e. the number is in the legal range for a back reference), +and otherwise is taken as octal. +.SH "METASYNTAX" +In addition to the main syntax described above, there are some special +forms and miscellaneous syntactic facilities available. +.PP +Normally the flavor of RE being used is specified by +application-dependent means. +However, this can be overridden by a \fIdirector\fR. +If an RE of any flavor begins with +`\fB***:\fR', +the rest of the RE is an ARE. +If an RE of any flavor begins with +`\fB***=\fR', +the rest of the RE is taken to be a literal string, +with all characters considered ordinary characters. +.PP +An ARE may begin with \fIembedded options\fR: +a sequence +\fB(?\fIxyz\fB)\fR +(where +\fIxyz\fR +is one or more alphabetic characters) +specifies options affecting the rest of the RE. +These supplement, and can override, +any options specified by the application. +The available option letters are: +.RS 2 +.TP 3 +\fBb\fR +rest of RE is a BRE +.TP 3 +\fBc\fR +case-sensitive matching (usual default) +.TP 3 +\fBe\fR +rest of RE is an ERE +.TP 3 +\fBi\fR +case-insensitive matching (see MATCHING, below) +.TP 3 +\fBm\fR +historical synonym for +\fBn\fR +.TP 3 +\fBn\fR +newline-sensitive matching (see MATCHING, below) +.TP 3 +\fBp\fR +partial newline-sensitive matching (see MATCHING, below) +.TP 3 +\fBq\fR +rest of RE is a literal (``quoted'') string, all ordinary characters +.TP 3 +\fBs\fR +non-newline-sensitive matching (usual default) +.TP 3 +\fBt\fR +tight syntax (usual default; see below) +.TP 3 +\fBw\fR +inverse partial newline-sensitive (``weird'') matching (see MATCHING, below) +.TP 3 +\fBx\fR +expanded syntax (see below) +.RE +.PP +Embedded options take effect at the +\fB)\fR +terminating the sequence. +They are available only at the start of an ARE, +and may not be used later within it. +.PP +In addition to the usual (\fItight\fR) RE syntax, in which all characters are +significant, there is an \fIexpanded\fR syntax, +available in all flavors of RE +with the \fB-expanded\fR switch, or in AREs with the embedded x option. +In the expanded syntax, +white-space characters are ignored +and all characters between a +\fB#\fR +and the following newline (or the end of the RE) are ignored, +permitting paragraphing and commenting a complex RE. +There are three exceptions to that basic rule: +.RS 2 +.PP +a white-space character or `\fB#\fR' preceded by `\fB\e\fR' is retained +.PP +white space or `\fB#\fR' within a bracket expression is retained +.PP +white space and comments are illegal within multi-character symbols +like the ARE `\fB(?:\fR' or the BRE `\fB\e(\fR' +.RE +.PP +Expanded-syntax +white-space characters are blank, tab, newline, etc. (any character +defined as \fIspace\fR by +\fIctype\fR(3)). +Exactly how a multi-line expanded-syntax RE +can be entered interactively by a user, +if at all, is application-specific; +expanded syntax is primarily a scripting facility. +.PP +Finally, in an ARE, +outside bracket expressions, the sequence +`\fB(?#\fIttt\fB)\fR' +(where +\fIttt\fR +is any text not containing a +`\fB)\fR') +is a comment, +completely ignored. +Again, this is not allowed between the characters of +multi-character symbols like +`\fB(?:\fR'. +Such comments are more a historical artifact than a useful facility, +and their use is deprecated; +use the expanded syntax instead. +.PP +\fINone\fR of these metasyntax extensions is available if the application +(or an initial +\fB***=\fR +director) +has specified that the user's input be treated as a literal string +rather than as an RE. +.SH MATCHING +In the event that an RE could match more than one substring of a given +string, +the RE matches the one starting earliest in the string. +If the RE could match more than one substring starting at that point, +its choice is determined by its \fIpreference\fR: +either the longest substring, or the shortest. +.PP +Most atoms, and all constraints, have no preference. +A parenthesized RE has the same preference (possibly none) as the RE. +A quantified atom with quantifier +\fB{\fIm\fB}\fR +or +\fB{\fIm\fB}?\fR +has the same preference (possibly none) as the atom itself. +A quantified atom with other normal quantifiers (including +\fB{\fIm\fB,\fIn\fB}\fR +with +\fIm\fR +equal to +\fIn\fR) +prefers longest match. +A quantified atom with other non-greedy quantifiers (including +\fB{\fIm\fB,\fIn\fB}?\fR +with +\fIm\fR +equal to +\fIn\fR) +prefers shortest match. +A branch has the same preference as the first quantified atom in it +which has a preference. +An RE consisting of two or more branches connected by the +\fB|\fR +operator prefers longest match. +.PP +Subject to the constraints imposed by the rules for matching the whole RE, +subexpressions also match the longest or shortest possible substrings, +based on their preferences, +with subexpressions starting earlier in the RE taking priority over +ones starting later. +Note that outer subexpressions thus take priority over +their component subexpressions. +.PP +Note that the quantifiers +\fB{1,1}\fR +and +\fB{1,1}?\fR +can be used to force longest and shortest preference, respectively, +on a subexpression or a whole RE. +.PP +Match lengths are measured in characters, not collating elements. +An empty string is considered longer than no match at all. +For example, +\fBbb*\fR +matches the three middle characters of +`\fBabbbc\fR', +\fB(week|wee)(night|knights)\fR +matches all ten characters of +`\fBweeknights\fR', +when +\fB(.*).*\fR +is matched against +\fBabc\fR +the parenthesized subexpression +matches all three characters, and +when +\fB(a*)*\fR +is matched against +\fBbc\fR +both the whole RE and the parenthesized +subexpression match an empty string. +.PP +If case-independent matching is specified, +the effect is much as if all case distinctions had vanished from the +alphabet. +When an alphabetic that exists in multiple cases appears as an +ordinary character outside a bracket expression, it is effectively +transformed into a bracket expression containing both cases, +so that +\fBx\fR +becomes +`\fB[xX]\fR'. +When it appears inside a bracket expression, all case counterparts +of it are added to the bracket expression, so that +\fB[x]\fR +becomes +\fB[xX]\fR +and +\fB[^x]\fR +becomes +`\fB[^xX]\fR'. +.PP +If newline-sensitive matching is specified, +\fB.\fR +and bracket expressions using +\fB^\fR +will never match the newline character +(so that matches will never cross newlines unless the RE +explicitly arranges it) +and +\fB^\fR +and +\fB$\fR +will match the empty string after and before a newline +respectively, in addition to matching at beginning and end of string +respectively. +ARE +\fB\eA\fR +and +\fB\eZ\fR +continue to match beginning or end of string \fIonly\fR. +.PP +If partial newline-sensitive matching is specified, +this affects +\fB.\fR +and bracket expressions +as with newline-sensitive matching, but not +\fB^\fR +and +`\fB$\fR'. +.PP +If inverse partial newline-sensitive matching is specified, +this affects +\fB^\fR +and +\fB$\fR +as with +newline-sensitive matching, +but not +\fB.\fR +and bracket expressions. +This isn't very useful but is provided for symmetry. +.SH "LIMITS AND COMPATIBILITY" +No particular limit is imposed on the length of REs. +Programs intended to be highly portable should not employ REs longer +than 256 bytes, +as a POSIX-compliant implementation can refuse to accept such REs. +.PP +The only feature of AREs that is actually incompatible with +POSIX EREs is that +\fB\e\fR +does not lose its special +significance inside bracket expressions. +All other ARE features use syntax which is illegal or has +undefined or unspecified effects in POSIX EREs; +the +\fB***\fR +syntax of directors likewise is outside the POSIX +syntax for both BREs and EREs. +.PP +Many of the ARE extensions are borrowed from Perl, but some have +been changed to clean them up, and a few Perl extensions are not present. +Incompatibilities of note include +`\fB\eb\fR', +`\fB\eB\fR', +the lack of special treatment for a trailing newline, +the addition of complemented bracket expressions to the things +affected by newline-sensitive matching, +the restrictions on parentheses and back references in lookahead constraints, +and the longest/shortest-match (rather than first-match) matching semantics. +.PP +The matching rules for REs containing both normal and non-greedy quantifiers +have changed since early beta-test versions of this package. +(The new rules are much simpler and cleaner, +but don't work as hard at guessing the user's real intentions.) +.PP +Henry Spencer's original 1986 \fIregexp\fR package, +still in widespread use (e.g., in pre-8.1 releases of Tcl), +implemented an early version of today's EREs. +There are four incompatibilities between \fIregexp\fR's near-EREs +(`RREs' for short) and AREs. +In roughly increasing order of significance: +.PP +.RS +In AREs, +\fB\e\fR +followed by an alphanumeric character is either an +escape or an error, +while in RREs, it was just another way of writing the +alphanumeric. +This should not be a problem because there was no reason to write +such a sequence in RREs. +.PP +\fB{\fR +followed by a digit in an ARE is the beginning of a bound, +while in RREs, +\fB{\fR +was always an ordinary character. +Such sequences should be rare, +and will often result in an error because following characters +will not look like a valid bound. +.PP +In AREs, +\fB\e\fR +remains a special character within +`\fB[\|]\fR', +so a literal +\fB\e\fR +within +\fB[\|]\fR +must be written +`\fB\e\e\fR'. +\fB\e\e\fR +also gives a literal +\fB\e\fR +within +\fB[\|]\fR +in RREs, +but only truly paranoid programmers routinely doubled the backslash. +.PP +AREs report the longest/shortest match for the RE, +rather than the first found in a specified search order. +This may affect some RREs which were written in the expectation that +the first match would be reported. +(The careful crafting of RREs to optimize the search order for fast +matching is obsolete (AREs examine all possible matches +in parallel, and their performance is largely insensitive to their +complexity) but cases where the search order was exploited to deliberately +find a match which was \fInot\fR the longest/shortest will need rewriting.) +.RE + +.SH "BASIC REGULAR EXPRESSIONS" +BREs differ from EREs in several respects. +`\fB|\fR', +`\fB+\fR', +and +\fB?\fR +are ordinary characters and there is no equivalent +for their functionality. +The delimiters for bounds are +\fB\e{\fR +and +`\fB\e}\fR', +with +\fB{\fR +and +\fB}\fR +by themselves ordinary characters. +The parentheses for nested subexpressions are +\fB\e(\fR +and +`\fB\e)\fR', +with +\fB(\fR +and +\fB)\fR +by themselves ordinary characters. +\fB^\fR +is an ordinary character except at the beginning of the +RE or the beginning of a parenthesized subexpression, +\fB$\fR +is an ordinary character except at the end of the +RE or the end of a parenthesized subexpression, +and +\fB*\fR +is an ordinary character if it appears at the beginning of the +RE or the beginning of a parenthesized subexpression +(after a possible leading +`\fB^\fR'). +Finally, +single-digit back references are available, +and +\fB\e<\fR +and +\fB\e>\fR +are synonyms for +\fB[[:<:]]\fR +and +\fB[[:>:]]\fR +respectively; +no other escapes are available. +.VE 8.1 .SH KEYWORDS match, regular expression, string diff --git a/doc/registry.n b/doc/registry.n index 4b7dbf3..f0e199f 100644 --- a/doc/registry.n +++ b/doc/registry.n @@ -4,7 +4,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: registry.n,v 1.3 1999/02/02 22:25:21 stanton Exp $ +'\" RCS: @(#) $Id: registry.n,v 1.4 1999/04/16 00:46:35 stanton Exp $ '\" .so man.macros .TH registry n 8.0 Tcl "Tcl Built-In Commands" @@ -112,7 +112,6 @@ registry command: . The registry value contains arbitrary binary data. The data is represented exactly in Tcl, including any embedded nulls. -Tcl .TP \fBnone\fR . diff --git a/doc/resource.n b/doc/resource.n index 9858abc..428591b 100644 --- a/doc/resource.n +++ b/doc/resource.n @@ -3,7 +3,7 @@ '\" '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. -'\" RCS: @(#) $Id: resource.n,v 1.3 1998/12/29 22:55:12 surles Exp $ +'\" RCS: @(#) $Id: resource.n,v 1.4 1999/04/16 00:46:36 stanton Exp $ '\" .so man.macros .TH resource n 8.0 Tcl "Tcl Built-In Commands" @@ -55,7 +55,7 @@ If the \fB-file\fR option is specified then the resource will be deleted from the file pointed to by \fIresourceRef\fR. Otherwise the first resource with the given \fIresourceName\fR and or \fIresourceId\fR which is found on the resource file path will be -deleted. To inspect the file path, use the \fIresource files\fB command. +deleted. To inspect the file path, use the \fIresource files\fR command. .RE .TP \fBresource files ?\fIresourceRef\fR? @@ -4,16 +4,15 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: safe.n,v 1.2 1998/09/14 18:39:55 stanton Exp $ +'\" RCS: @(#) $Id: safe.n,v 1.3 1999/04/16 00:46:36 stanton Exp $ '\" .so man.macros .TH "Safe Tcl" n 8.0 Tcl "Tcl Built-In Commands" .BS '\" Note: do not modify the .SH NAME line immediately below! .SH NAME -Safe Base \- A mechanism for creating and manipulating safe interpreters. +Safe\ Base \- A mechanism for creating and manipulating safe interpreters. .SH SYNOPSIS -.PP \fB::safe::interpCreate\fR ?\fIslave\fR? ?\fIoptions...\fR? .sp \fB::safe::interpInit\fR \fIslave\fR ?\fIoptions...\fR? @@ -50,7 +49,7 @@ hosting application to any party. .PP The Safe Base allows a master interpreter to create safe, restricted interpreters that contain a set of predefined aliases for the \fBsource\fR, -\fBload\fR, \fBfile\fR and \fBexit\fR commands and +\fBload\fR, \fBfile\fR, \fBencoding\fR, and \fBexit\fR commands and are able to use the auto-loading and package mechanisms. .PP No knowledge of the file system structure is leaked to the @@ -246,6 +245,12 @@ the \fBfile\fR command; it allows only \fBdirname\fR, \fBjoin\fR, subcommands. For more details on what these subcommands do see the manual page for the \fBfile\fR command. .TP +\fBencoding\fR ?\fIsubCmd args...\fR? +The \fBenconding\fR alias provides access to a safe subset of the +subcommands of the \fBencoding\fR command; it disallows setting of +the system encoding, but allows all other subcommands including +\fBsystem\fR to check the current encoding. +.TP \fBexit\fR The calling interpreter is deleted and its computation is stopped, but the Tcl process in which this interpreter exists is not terminated. @@ -262,9 +267,9 @@ is to prevent. .PP The commands available in a safe interpreter, in addition to the safe set as defined in \fBinterp\fR manual page, are mediated aliases -for \fBsource\fR, \fBload\fR, \fBexit\fR, and a safe subset of \fBfile\fR. -The safe interpreter can also auto-load code and it can request that -packages be loaded. +for \fBsource\fR, \fBload\fR, \fBexit\fR, and safe subsets of +\fBfile\fR and \fBencoding\fR. The safe interpreter can also auto-load +code and it can request that packages be loaded. .PP Because some of these commands access the local file system, there is a potential for information leakage about its directory structure. @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: scan.n,v 1.2 1998/09/14 18:39:55 stanton Exp $ +'\" RCS: @(#) $Id: scan.n,v 1.3 1999/04/16 00:46:36 stanton Exp $ '\" .so man.macros .TH scan n "" Tcl "Tcl Built-In Commands" @@ -31,25 +31,41 @@ and assigned to the corresponding variable. .SH "DETAILS ON SCANNING" .PP -\fBScan\fR operates by scanning \fIstring\fR and \fIformatString\fR together. -If the next character in \fIformatString\fR is a blank or tab then it +\fBScan\fR operates by scanning \fIstring\fR and \fIformat\fR together. +If the next character in \fIformat\fR is a blank or tab then it matches any number of white space characters in \fIstring\fR (including zero). Otherwise, if it isn't a \fB%\fR character then it must match the next character of \fIstring\fR. -When a \fB%\fR is encountered in \fIformatString\fR, it indicates +When a \fB%\fR is encountered in \fIformat\fR, it indicates the start of a conversion specifier. -A conversion specifier contains three fields after the \fB%\fR: +A conversion specifier contains up to four fields after the \fB%\fR: a \fB*\fR, which indicates that the converted value is to be discarded -instead of assigned to a variable; a number indicating a maximum field -width; and a conversion character. +.VS 8.1 +instead of assigned to a variable; a XPG3 position specifier; a number +.VE 8.1 +indicating a maximum field width; and a conversion character. All of these fields are optional except for the conversion character. +The fields that are present must appear in the order given above. .PP -When \fBscan\fR finds a conversion specifier in \fIformatString\fR, it -first skips any white-space characters in \fIstring\fR. +When \fBscan\fR finds a conversion specifier in \fIformat\fR, it +first skips any white-space characters in \fIstring\fR (unless the +specifier is \fB[\fR or \fBc\fR). Then it converts the next input characters according to the conversion specifier and stores the result in the variable given by the next argument to \fBscan\fR. +.VS 8.1 +.PP +If the \fB%\fR is followed by a decimal number and a \fB$\fR, as in +``\fB%2$d\fR'', then the variable to use is not taken from the next +sequential argument. Instead, it is taken from the argument indicated +by the number, where 1 corresponds to the first \fIvarName\fR. If +there are any positional specifiers in \fIformat\fR then all of the +specifiers must be positional. Every \fIvarName\fR on the argument +list must correspond to exactly one conversion specifier or an error +is generated. +.VE 8.1 +.PP The following conversion characters are supported: .TP 10 \fBd\fR @@ -63,6 +79,17 @@ value is stored in the variable as a decimal string. \fBx\fR The input field must be a hexadecimal integer. It is read in and the value is stored in the variable as a decimal string. +.VS 8.1 +.TP 10 +\fBu\fR +The input field must be a decimal integer. The value is stored in the +variable as an unsigned decimal integer string. +.TP 10 +\fBi\fR +The input field must be an integer. The base (i.e. decimal, octal, or +hexadecimal) is determined in the same fashion as described in +\fBexpr\fR. The value is stored in the variable as a decimal string. +.VE 8.1 .TP 10 \fBc\fR A single character is read in and its binary value is stored in @@ -92,6 +119,13 @@ The matching string is stored in the variable. If the first character between the brackets is a \fB]\fR then it is treated as part of \fIchars\fR rather than the closing bracket for the set. +.VS 8.1 +If \fIchars\fR +contains a sequence of the form \fIa\fB\-\fIb\fR then any +character between \fIa\fR and \fIb\fR (inclusive) will match. +If the first or last character between the brackets is a \fB\-\fR, then +it is treated as part of \fIchars\fR rather than indicating a range. +.VE 8.1 .TP 10 \fB[^\fIchars\fB]\fR The input field consists of any number of characters not in @@ -100,6 +134,18 @@ The matching string is stored in the variable. If the character immediately following the \fB^\fR is a \fB]\fR then it is treated as part of the set rather than the closing bracket for the set. +.VS 8.1 +If \fIchars\fR +contains a sequence of the form \fIa\fB\-\fIb\fR then any +character between \fIa\fR and \fIb\fR (inclusive) will be excluded +from the set. +If the first or last character between the brackets is a \fB\-\fR, then +it is treated as part of \fIchars\fR rather than indicating a range. +.TP 10 +\fBn\fR +No input is consumed from the input string. Instead, the total number +of chacters scanned from the input string so far is stored in the variable. +.VE 8.1 .LP The number of characters read from the input for a conversion is the largest number that makes sense for that particular conversion (e.g. @@ -115,9 +161,11 @@ then no variable is assigned and the next scan argument is not consumed. .PP The behavior of the \fBscan\fR command is the same as the behavior of the ANSI C \fBsscanf\fR procedure except for the following differences: +.VS 8.1 .IP [1] -\fB%p\fR and \fB%n\fR conversion specifiers are not currently +\fB%p\fR conversion specifier is not currently supported. +.VE 8.1 .IP [2] For \fB%c\fR conversions a single character value is converted to a decimal string, which is then assigned to the diff --git a/doc/socket.n b/doc/socket.n index ebb7383..d73883f 100644 --- a/doc/socket.n +++ b/doc/socket.n @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: socket.n,v 1.3 1999/02/03 00:51:19 stanton Exp $ +'\" RCS: @(#) $Id: socket.n,v 1.4 1999/04/16 00:46:36 stanton Exp $ .so man.macros .TH socket n 8.0 Tcl "Tcl Built-In Commands" .BS @@ -104,14 +104,14 @@ will be accepted. .SH CONFIGURATION OPTIONS The \fBfconfigure\fR command can be used to query several readonly configuration options for socket channels: -.VS +.VS 8.0.5 .TP \fB\-error\fR This option gets the current error status of the given socket. This is useful when you need to determine if an asynchronous connect operation succeeded. If there was an error, the error message is returned. If there was no error, an empty string is returned. -.VE +.VE 8.0.5 .TP \fB\-sockname\fR This option returns a list of three elements, the address, the host name diff --git a/doc/string.n b/doc/string.n index 44ef20c..42d6e0b 100644 --- a/doc/string.n +++ b/doc/string.n @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: string.n,v 1.2 1998/09/14 18:39:55 stanton Exp $ +'\" RCS: @(#) $Id: string.n,v 1.3 1999/04/16 00:46:36 stanton Exp $ '\" .so man.macros .TH string n 7.6 Tcl "Tcl Built-In Commands" @@ -85,14 +85,22 @@ If \fIfirst\fR is less than zero then it is treated as if it were zero, and if \fIlast\fR is greater than or equal to the length of the string then it is treated as if it were \fBend\fR. If \fIfirst\fR is greater than \fIlast\fR then an empty string is returned. +.VS .TP \fBstring tolower \fIstring\fR -Returns a value equal to \fIstring\fR except that all upper case -letters have been converted to lower case. +Returns a value equal to \fIstring\fR except that all upper (or title) +case letters have been converted to lower case. .TP -\fBstring toupper \fIstring\fR -Returns a value equal to \fIstring\fR except that all lower case -letters have been converted to upper case. +\fBstring totitle \fIstring\fR +Returns a value equal to \fIstring\fR except that the first character +in \fIstring\fR is converted to its Unicode title case variant (or upper +case if there is no title case variant) and the rest of the string is +converted to lower case. +.TP +\fBstring toupper \fIstring\fR +Returns a value equal to \fIstring\fR except that all lower (or title) +case letters have been converted to upper case. +.VE .TP \fBstring trim \fIstring\fR ?\fIchars\fR? Returns a value equal to \fIstring\fR except that any leading @@ -114,18 +122,22 @@ trailing characters from the set given by \fIchars\fR are removed. If \fIchars\fR is not specified then white space is removed (spaces, tabs, newlines, and carriage returns). +.VS .TP \fBstring wordend \fIstring index\fR -Returns the index of the character just after the last one in the -word containing character \fIindex\fR of \fIstring\fR. -A word is considered to be any contiguous range of alphanumeric -or underscore characters, or any single character other than these. +Returns the index of the character just after the last one in the word +containing character \fIindex\fR of \fIstring\fR. A word is +considered to be any contiguous range of alphanumeric (Unicode letters +or decimal digits) or underscore (Unicode connector punctuation) +characters, or any single character other than these. .TP \fBstring wordstart \fIstring index\fR -Returns the index of the first character in the -word containing character \fIindex\fR of \fIstring\fR. -A word is considered to be any contiguous range of alphanumeric -or underscore characters, or any single character other than these. +Returns the index of the first character in the word containing +character \fIindex\fR of \fIstring\fR. A word is considered to be any +contiguous range of alphanumeric (Unicode letters or decimal digits) +or underscore (Unicode connector punctuation) characters, or any +single character other than these. +.VE .SH KEYWORDS case conversion, compare, index, match, pattern, string, word diff --git a/doc/tclvars.n b/doc/tclvars.n index 8536327..2e68519 100644 --- a/doc/tclvars.n +++ b/doc/tclvars.n @@ -5,7 +5,7 @@ '\" See the file "license.terms" for information on usage and redistribution '\" of this file, and for a DISCLAIMER OF ALL WARRANTIES. '\" -'\" RCS: @(#) $Id: tclvars.n,v 1.2 1998/09/14 18:39:55 stanton Exp $ +'\" RCS: @(#) $Id: tclvars.n,v 1.3 1999/04/16 00:46:36 stanton Exp $ '\" .so man.macros .TH tclvars n 8.0 Tcl "Tcl Built-In Commands" @@ -259,16 +259,27 @@ is the value returned by \fBuname -m\fR. .TP \fBos\fR The name of the operating system running on this machine, -such as \fBWin32s\fR, \fBWindows NT\fR, \fBMacOS\fR, or \fBSunOS\fR. +such as \fBWindows 95\fR, \fBWindows NT\fR, \fBMacOS\fR, or \fBSunOS\fR. On UNIX machines, this is the value returned by \fBuname -s\fR. +On Windows 95 and Windows 98, the value returned will be \fBWindows +95\fR to provide better backwards compatibility to Windows 95; to +distinguish between the two, check the \fBosVersion\fR. .TP \fBosVersion\fR The version number for the operating system running on this machine. -On UNIX machines, this is the value returned by \fBuname -r\fR. +On UNIX machines, this is the value returned by \fBuname -r\fR. On +Windows 95, the version will be 4.0; on Windows 98, the version will +be 4.10. .TP \fBplatform\fR Either \fBwindows\fR, \fBmacintosh\fR, or \fBunix\fR. This identifies the general operating environment of the machine. +.TP +\fBuser\fR +Either \fBwindows\fR, \fBmacintosh\fR, or \fBunix\fR. This identifies the +current user based on the login information available on the platform. +This comes from the USER or LOGNAME environment variable on Unix, +and the value from GetUserName on Windows and Macintosh. .RE .TP \fBtcl_precision\fR |