diff options
Diffstat (limited to 'doc/StringObj.3')
| -rw-r--r-- | doc/StringObj.3 | 365 |
1 files changed, 294 insertions, 71 deletions
diff --git a/doc/StringObj.3 b/doc/StringObj.3 index 46fe959..d81f23d 100644 --- a/doc/StringObj.3 +++ b/doc/StringObj.3 @@ -4,13 +4,11 @@ '\" 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 1.4 1999/04/16 00:46:33 stanton Exp $ -'\" -.so man.macros .TH Tcl_StringObj 3 8.1 Tcl "Tcl Library Procedures" +.so man.macros .BS .SH NAME -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 +Tcl_NewStringObj, Tcl_NewUnicodeObj, Tcl_SetStringObj, Tcl_SetUnicodeObj, Tcl_GetStringFromObj, Tcl_GetString, Tcl_GetUnicodeFromObj, Tcl_GetUnicode, Tcl_GetUniChar, Tcl_GetCharLength, Tcl_GetRange, Tcl_AppendToObj, Tcl_AppendUnicodeToObj, Tcl_AppendObjToObj, Tcl_AppendStringsToObj, Tcl_AppendStringsToObjVA, Tcl_AppendLimitedToObj, Tcl_Format, Tcl_AppendFormatToObj, Tcl_ObjPrintf, Tcl_AppendPrintfToObj, Tcl_SetObjLength, Tcl_AttemptSetObjLength, Tcl_ConcatObj \- manipulate Tcl values as strings .SH SYNOPSIS .nf \fB#include <tcl.h>\fR @@ -18,104 +16,228 @@ Tcl_NewStringObj, Tcl_SetStringObj, Tcl_GetStringFromObj, Tcl_GetString, Tcl_App Tcl_Obj * \fBTcl_NewStringObj\fR(\fIbytes, length\fR) .sp +Tcl_Obj * +\fBTcl_NewUnicodeObj\fR(\fIunicode, numChars\fR) +.sp +void \fBTcl_SetStringObj\fR(\fIobjPtr, bytes, length\fR) .sp +void +\fBTcl_SetUnicodeObj\fR(\fIobjPtr, unicode, numChars\fR) +.sp char * \fBTcl_GetStringFromObj\fR(\fIobjPtr, lengthPtr\fR) .sp char * \fBTcl_GetString\fR(\fIobjPtr\fR) .sp +Tcl_UniChar * +\fBTcl_GetUnicodeFromObj\fR(\fIobjPtr, lengthPtr\fR) +.sp +Tcl_UniChar * +\fBTcl_GetUnicode\fR(\fIobjPtr\fR) +.sp +Tcl_UniChar +\fBTcl_GetUniChar\fR(\fIobjPtr, index\fR) +.sp +int +\fBTcl_GetCharLength\fR(\fIobjPtr\fR) +.sp +Tcl_Obj * +\fBTcl_GetRange\fR(\fIobjPtr, first, last\fR) +.sp +void \fBTcl_AppendToObj\fR(\fIobjPtr, bytes, length\fR) -.VS .sp +void +\fBTcl_AppendUnicodeToObj\fR(\fIobjPtr, unicode, numChars\fR) +.sp +void \fBTcl_AppendObjToObj\fR(\fIobjPtr, appendObjPtr\fR) -.VE .sp +void \fBTcl_AppendStringsToObj\fR(\fIobjPtr, string, string, ... \fB(char *) NULL\fR) .sp +void \fBTcl_AppendStringsToObjVA\fR(\fIobjPtr, argList\fR) .sp +void +\fBTcl_AppendLimitedToObj\fR(\fIobjPtr, bytes, length, limit, ellipsis\fR) +.sp +Tcl_Obj * +\fBTcl_Format\fR(\fIinterp, format, objc, objv\fR) +.sp +int +\fBTcl_AppendFormatToObj\fR(\fIinterp, objPtr, format, objc, objv\fR) +.sp +Tcl_Obj * +\fBTcl_ObjPrintf\fR(\fIformat, ...\fR) +.sp +void +\fBTcl_AppendPrintfToObj\fR(\fIobjPtr, format, ...\fR) +.sp +void \fBTcl_SetObjLength\fR(\fIobjPtr, newLength\fR) .sp +int +\fBTcl_AttemptSetObjLength\fR(\fIobjPtr, newLength\fR) +.sp Tcl_Obj * \fBTcl_ConcatObj\fR(\fIobjc, objv\fR) .SH ARGUMENTS -.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. -This byte array may contain embedded null bytes -unless \fIlength\fR is negative. +.AS "const Tcl_UniChar" *appendObjPtr in/out +.AP "const char" *bytes in +Points to the first byte of an array of UTF-8-encoded bytes +used to set or append to a string value. +This byte array may contain embedded null characters +unless \fInumChars\fR is negative. (Applications needing null bytes +should represent them as the two-byte sequence \fI\e700\e600\fR, use +\fBTcl_ExternalToUtf\fR to convert, or \fBTcl_NewByteArrayObj\fR if +the string is a collection of uninterpreted bytes.) .AP int length in The number of bytes to copy from \fIbytes\fR when -initializing, setting, or appending to a string object. +initializing, setting, or appending to a string value. If negative, all bytes up to the first null are used. +.AP "const Tcl_UniChar" *unicode in +Points to the first byte of an array of Unicode characters +used to set or append to a string value. +This byte array may contain embedded null characters +unless \fInumChars\fR is negative. +.AP int numChars in +The number of Unicode characters to copy from \fIunicode\fR when +initializing, setting, or appending to a string value. +If negative, all characters up to the first null character are used. +.AP int index in +The index of the Unicode character to return. +.AP int first in +The index of the first Unicode character in the Unicode range to be +returned as a new value. +.AP int last in +The index of the last Unicode character in the Unicode range to be +returned as a new value. .AP Tcl_Obj *objPtr in/out -Points to an object to manipulate. -.VS +Points to a value to manipulate. .AP Tcl_Obj *appendObjPtr in -The object to append to \fIobjPtr\fR in \fBTcl_AppendObjToObj\fR. -.VE +The value to append to \fIobjPtr\fR in \fBTcl_AppendObjToObj\fR. .AP int *lengthPtr out If non-NULL, the location where \fBTcl_GetStringFromObj\fR will store -the the length of an object's string representation. -.AP char *string in +the length of a value's string representation. +.AP "const char" *string in Null-terminated string value to append to \fIobjPtr\fR. .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 int newLength in -New length for the string value of \fIobjPtr\fR, not including the -final NULL character. +An argument list which must have been initialized using +\fBva_start\fR, and cleared using \fBva_end\fR. +.AP int limit in +Maximum number of bytes to be appended. +.AP "const char" *ellipsis in +Suffix to append when the limit leads to string truncation. +If NULL is passed then the suffix +.QW "..." +is used. +.AP "const char" *format in +Format control string including % conversion specifiers. .AP int objc in -The number of elements to concatenate. +The number of elements to format or concatenate. .AP Tcl_Obj *objv[] in -The array of objects to concatenate. +The array of values to format or concatenate. +.AP int newLength in +New length for the string value of \fIobjPtr\fR, not including the +final null character. .BE - .SH DESCRIPTION .PP -The procedures described in this manual entry allow Tcl objects to +The procedures described in this manual entry allow Tcl values to be manipulated as string values. They use the internal representation -of the object to store additional information to make the string +of the value to store additional information to make the string manipulations more efficient. In particular, they make a series of append operations efficient by allocating extra storage space for the -string so that it doesn't have to be copied for each append. -.PP -\fBTcl_NewStringObj\fR and \fBTcl_SetStringObj\fR create a new object -or modify an existing object to hold a copy of -the string given by \fIbytes\fR and \fIlength\fR. -\fBTcl_NewStringObj\fR returns a pointer to a newly created object -with reference count zero. -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 and \fBTcl_GetString\fR -return an object's string representation. -This is given by the returned byte pointer -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. +string so that it does not have to be copied for each append. +Also, indexing and length computations are optimized because the +Unicode string representation is calculated and cached as needed. +When using the \fBTcl_Append*\fR family of functions where the +interpreter's result is the value being appended to, it is important +to call Tcl_ResetResult first to ensure you are not unintentionally +appending to existing data in the result value. +.PP +\fBTcl_NewStringObj\fR and \fBTcl_SetStringObj\fR create a new value +or modify an existing value to hold a copy of the string given by +\fIbytes\fR and \fIlength\fR. \fBTcl_NewUnicodeObj\fR and +\fBTcl_SetUnicodeObj\fR create a new value or modify an existing +value to hold a copy of the Unicode string given by \fIunicode\fR and +\fInumChars\fR. \fBTcl_NewStringObj\fR and \fBTcl_NewUnicodeObj\fR +return a pointer to a newly created value with reference count zero. +All four procedures set the value to hold a copy of the specified +string. \fBTcl_SetStringObj\fR and \fBTcl_SetUnicodeObj\fR free any +old string representation as well as any old internal representation +of the value. +.PP +\fBTcl_GetStringFromObj\fR and \fBTcl_GetString\fR return a value's +string representation. This is given by the returned byte pointer and +(for \fBTcl_GetStringFromObj\fR) length, which is stored in +\fIlengthPtr\fR if it is non-NULL. If the value's UTF string +representation is invalid (its byte pointer is NULL), the string +representation is regenerated from the value's internal +representation. The storage referenced by the returned byte pointer +is owned by the value manager. It is passed back as a writable +pointer so that extension author creating their own \fBTcl_ObjType\fR +will be able to modify the string representation within the +\fBTcl_UpdateStringProc\fR of their \fBTcl_ObjType\fR. Except for that +limited purpose, the pointer returned by \fBTcl_GetStringFromObj\fR +or \fBTcl_GetString\fR should be treated as read-only. It is +recommended that this pointer be assigned to a (const char *) variable. +Even in the limited situations where writing to this pointer is +acceptable, one should take care to respect the copy-on-write +semantics required by \fBTcl_Obj\fR's, with appropriate calls +to \fBTcl_IsShared\fR and \fBTcl_DuplicateObj\fR prior to any +in-place modification of the string representation. The procedure \fBTcl_GetString\fR is used in the common case -where the caller does not need the length of the string representation. +where the caller does not need the length of the string +representation. +.PP +\fBTcl_GetUnicodeFromObj\fR and \fBTcl_GetUnicode\fR return a value's +value as a Unicode string. This is given by the returned pointer and +(for \fBTcl_GetUnicodeFromObj\fR) length, which is stored in +\fIlengthPtr\fR if it is non-NULL. The storage referenced by the returned +byte pointer is owned by the value manager and should not be modified by +the caller. The procedure \fBTcl_GetUnicode\fR is used in the common case +where the caller does not need the length of the unicode string +representation. +.PP +\fBTcl_GetUniChar\fR returns the \fIindex\fR'th character in the +value's Unicode representation. +.PP +\fBTcl_GetRange\fR returns a newly created value comprised of the +characters between \fIfirst\fR and \fIlast\fR (inclusive) in the +value's Unicode representation. If the value's Unicode +representation is invalid, the Unicode representation is regenerated +from the value's string representation. +.PP +\fBTcl_GetCharLength\fR returns the number of characters (as opposed +to bytes) in the string value. .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 +\fIlength\fR to the string representation of the value specified by +\fIobjPtr\fR. If the value has an invalid string representation, +then an attempt is made to convert \fIbytes\fR is to the Unicode +format. If the conversion is successful, then the converted form of +\fIbytes\fR is appended to the value's Unicode representation. +Otherwise, the value's Unicode representation is invalidated and +converted to the UTF format, and \fIbytes\fR is appended to the +value's new string representation. +.PP +\fBTcl_AppendUnicodeToObj\fR appends the Unicode string given by +\fIunicode\fR and \fInumChars\fR to the value specified by +\fIobjPtr\fR. If the value has an invalid Unicode representation, +then \fIunicode\fR is converted to the UTF format and appended to the +value's string representation. Appends are optimized to handle +repeated appends relatively efficiently (it over-allocates the string +or Unicode space to avoid repeated reallocations and copies of +value's string value). .PP \fBTcl_AppendObjToObj\fR is similar to \fBTcl_AppendToObj\fR, but it -appends the string value of \fIappendObjPtr\fR to \fIobjPtr\fR. -.VE +appends the string or Unicode value (whichever exists and is best +suited to be appended to \fIobjPtr\fR) of \fIappendObjPtr\fR to +\fIobjPtr\fR. .PP \fBTcl_AppendStringsToObj\fR is similar to \fBTcl_AppendToObj\fR except that it can be passed more than one value to append and @@ -128,34 +250,135 @@ must be a NULL pointer to indicate the end of the list. except that instead of taking a variable number of arguments it takes an argument list. .PP +\fBTcl_AppendLimitedToObj\fR is similar to \fBTcl_AppendToObj\fR +except that it imposes a limit on how many bytes are appended. +This can be handy when the string to be appended might be +very large, but the value being constructed should not be allowed to grow +without bound. A common usage is when constructing an error message, where the +end result should be kept short enough to be read. +Bytes from \fIbytes\fR are appended to \fIobjPtr\fR, but no more +than \fIlimit\fR bytes total are to be appended. If the limit prevents +all \fIlength\fR bytes that are available from being appended, then the +appending is done so that the last bytes appended are from the +string \fIellipsis\fR. This allows for an indication of the truncation +to be left in the string. +When \fIlength\fR is \fB-1\fR, all bytes up to the first zero byte are appended, +subject to the limit. When \fIellipsis\fR is NULL, the default +string \fB...\fR is used. When \fIellipsis\fR is non-NULL, it must point +to a zero-byte-terminated string in Tcl's internal UTF encoding. +The number of bytes appended can be less than the lesser +of \fIlength\fR and \fIlimit\fR when appending fewer +bytes is necessary to append only whole multi-byte characters. +.PP +\fBTcl_Format\fR is the C-level interface to the engine of the \fBformat\fR +command. The actual command procedure for \fBformat\fR is little more +than +.PP +.CS +\fBTcl_Format\fR(interp, \fBTcl_GetString\fR(objv[1]), objc-2, objv+2); +.CE +.PP +The \fIobjc\fR Tcl_Obj values in \fIobjv\fR are formatted into a string +according to the conversion specification in \fIformat\fR argument, following +the documentation for the \fBformat\fR command. The resulting formatted +string is converted to a new Tcl_Obj with refcount of zero and returned. +If some error happens during production of the formatted string, NULL is +returned, and an error message is recorded in \fIinterp\fR, if \fIinterp\fR +is non-NULL. +.PP +\fBTcl_AppendFormatToObj\fR is an appending alternative form +of \fBTcl_Format\fR with functionality equivalent to: +.PP +.CS +Tcl_Obj *newPtr = \fBTcl_Format\fR(interp, format, objc, objv); +if (newPtr == NULL) return TCL_ERROR; +\fBTcl_AppendObjToObj\fR(objPtr, newPtr); +return TCL_OK; +.CE +.PP +but with greater convenience and efficiency when the appending +functionality is needed. +.PP +\fBTcl_ObjPrintf\fR serves as a replacement for the common sequence +.PP +.CS +char buf[SOME_SUITABLE_LENGTH]; +sprintf(buf, format, ...); +\fBTcl_NewStringObj\fR(buf, -1); +.CE +.PP +but with greater convenience and no need to +determine \fBSOME_SUITABLE_LENGTH\fR. The formatting is done with the same +core formatting engine used by \fBTcl_Format\fR. This means the set of +supported conversion specifiers is that of the \fBformat\fR command and +not that of the \fBsprintf\fR routine where the two sets differ. When a +conversion specifier passed to \fBTcl_ObjPrintf\fR includes a precision, +the value is taken as a number of bytes, as \fBsprintf\fR does, and not +as a number of characters, as \fBformat\fR does. This is done on the +assumption that C code is more likely to know how many bytes it is +passing around than the number of encoded characters those bytes happen +to represent. The variable number of arguments passed in should be of +the types that would be suitable for passing to \fBsprintf\fR. Note in +this example usage, \fIx\fR is of type \fBint\fR. +.PP +.CS +int x = 5; +Tcl_Obj *objPtr = \fBTcl_ObjPrintf\fR("Value is %d", x); +.CE +.PP +If the value of \fIformat\fR contains internal inconsistencies or invalid +specifier formats, the formatted string result produced by +\fBTcl_ObjPrintf\fR will be an error message describing the error. +It is impossible however to provide runtime protection against +mismatches between the format and any subsequent arguments. +Compile-time protection may be provided by some compilers. +.PP +\fBTcl_AppendPrintfToObj\fR is an appending alternative form +of \fBTcl_ObjPrintf\fR with functionality equivalent to +.PP +.CS +\fBTcl_AppendObjToObj\fR(objPtr, \fBTcl_ObjPrintf\fR(format, ...)); +.CE +.PP +but with greater convenience and efficiency when the appending +functionality is needed. +.PP The \fBTcl_SetObjLength\fR procedure changes the length of the string value of its \fIobjPtr\fR argument. If the \fInewLength\fR -argument is greater than the space allocated for the object's +argument is greater than the space allocated for the value's string, then the string space is reallocated and the old value is copied to the new space; the bytes between the old length of the string and the new length may have arbitrary values. If the \fInewLength\fR argument is less than the current length -of the object's string, with \fIobjPtr->length\fR is reduced without +of the value's string, with \fIobjPtr->length\fR is reduced without reallocating the string space; the original allocated size for the -string is recorded in the object, so that the string length can be +string is recorded in the value, so that the string length can be enlarged in a subsequent call to \fBTcl_SetObjLength\fR without reallocating storage. In all cases \fBTcl_SetObjLength\fR leaves a null character at \fIobjPtr->bytes[newLength]\fR. .PP -The \fBTcl_ConcatObj\fR function returns a new string object whose +\fBTcl_AttemptSetObjLength\fR is identical in function to +\fBTcl_SetObjLength\fR except that if sufficient memory to satisfy the +request cannot be allocated, it does not cause the Tcl interpreter to +\fBpanic\fR. Thus, if \fInewLength\fR is greater than the space +allocated for the value's string, and there is not enough memory +available to satisfy the request, \fBTcl_AttemptSetObjLength\fR will take +no action and return 0 to indicate failure. If there is enough memory +to satisfy the request, \fBTcl_AttemptSetObjLength\fR behaves just like +\fBTcl_SetObjLength\fR and returns 1 to indicate success. +.PP +The \fBTcl_ConcatObj\fR function returns a new string value whose value is the space-separated concatenation of the string -representations of all of the objects in the \fIobjv\fR +representations of all of the values in the \fIobjv\fR array. \fBTcl_ConcatObj\fR eliminates leading and trailing white space as it copies the string representations of the \fIobjv\fR array to the result. If an element of the \fIobjv\fR array consists of nothing but -white space, then that object is ignored entirely. This white-space +white space, then that value is ignored entirely. This white-space removal was added to make the output of the \fBconcat\fR command cleaner-looking. \fBTcl_ConcatObj\fR returns a pointer to a -newly-created object whose ref count is zero. - +newly-created value whose ref count is zero. .SH "SEE ALSO" -Tcl_NewObj, Tcl_IncrRefCount, Tcl_DecrRefCount - +Tcl_NewObj(3), Tcl_IncrRefCount(3), Tcl_DecrRefCount(3), format(n), sprintf(3) .SH KEYWORDS -append, internal representation, object, object type, string object, -string type, string representation, concat, concatenate +append, internal representation, value, value type, string value, +string type, string representation, concat, concatenate, unicode |