diff options
| -rw-r--r-- | ChangeLog | 9 | ||||
| -rw-r--r-- | doc/DoubleObj.3 | 67 | ||||
| -rw-r--r-- | doc/scan.n | 137 | ||||
| -rw-r--r-- | generic/tclScan.c | 3 | ||||
| -rw-r--r-- | tests/scan.test | 6 |
5 files changed, 120 insertions, 102 deletions
@@ -1,3 +1,12 @@ +2006-04-25 Don Porter <dgp@users.sourceforge.net> + + * doc/DoubleObj.3: More doc updates for TIP 237. + * doc/scan.n: + + * generic/tclScan.c: [scan $s %u] is documented to accept only + * tests/scan.test: decimal formatted integers. Fixed code to + match. + 2006-04-19 Kevin B. Kenny <kennykb@acm.org> * generic/tclStrToD.c: Added code to support the "middle endian" diff --git a/doc/DoubleObj.3 b/doc/DoubleObj.3 index 4af284d..ea62c07 100644 --- a/doc/DoubleObj.3 +++ b/doc/DoubleObj.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: DoubleObj.3,v 1.3 2004/09/06 09:44:56 dkf Exp $ +'\" RCS: @(#) $Id: DoubleObj.3,v 1.4 2006/04/25 17:15:25 dgp Exp $ '\" .so man.macros .TH Tcl_DoubleObj 3 8.0 Tcl "Tcl Library Procedures" @@ -25,55 +25,42 @@ int .SH ARGUMENTS .AS Tcl_Interp doubleValue in/out .AP double doubleValue in -A double-precision floating-point value used to initialize or set a double object. +A double-precision floating-point value used to initialize or set a Tcl object. .AP Tcl_Obj *objPtr in/out -For \fBTcl_SetDoubleObj\fR, this points to the object to be converted -to double type. +For \fBTcl_SetDoubleObj\fR, this points to the object in which to store a +double value. For \fBTcl_GetDoubleFromObj\fR, this refers to the object -from which to get a double value; -if \fIobjPtr\fR does not already point to a double object, -an attempt will be made to convert it to one. +from which to retrieve a double value. .AP Tcl_Interp *interp in/out -If an error occurs during conversion, -an error message is left in the interpreter's result object -unless \fIinterp\fR is NULL. +When non-NULL, an error message is left here when double value retrieval fails. .AP double *doublePtr out -Points to place to store the double value -obtained from \fIobjPtr\fR. +Points to place to store the double value obtained from \fIobjPtr\fR. .BE .SH DESCRIPTION .PP -These procedures are used to create, modify, and read -double Tcl objects from C code. -\fBTcl_NewDoubleObj\fR and \fBTcl_SetDoubleObj\fR -will create a new object of double type -or modify an existing object to have double type. -Both of these procedures set the object to have the -double-precision floating-point value given by \fIdoubleValue\fR; -\fBTcl_NewDoubleObj\fR returns a pointer to a newly created object -with reference count zero. -Both procedures set the object's type to be double -and assign the double value to the object's internal representation -\fIdoubleValue\fR member. -\fBTcl_SetDoubleObj\fR invalidates any old string representation -and, if the object is not already a double object, -frees any old internal representation. +These procedures are used to create, modify, and read Tcl objects that +hold double-precision floating-point values. .PP -\fBTcl_GetDoubleFromObj\fR attempts to return a double value -from the Tcl object \fIobjPtr\fR. -If the object is not already a double object, -it will attempt to convert it to one. -If an error occurs during conversion, it returns \fBTCL_ERROR\fR -and leaves an error message in the interpreter's result object -unless \fIinterp\fR is NULL. -Otherwise, it returns \fBTCL_OK\fR and stores the double value -in the address given by \fIdoublePtr\fR. -If the object is not already a double object, -the conversion will free any old internal representation. - +\fBTcl_NewDoubleObj\fR creates and returns a new Tcl object initialized to +the double value \fIdoubleValue\fR. The returned Tcl object is unshared. +.PP +\fBTcl_SetDoubleObj\fR sets the value of an existing Tcl object pointed to +by \fIobjPtr\fR to the double value \fIdoubleValue\fR. The \fIobjPtr\fR +argument must point to an unshared Tcl object. Any attempt to set the value +of a shared Tcl object violates Tcl's copy-on-write policy. Any existing +string representation or internal representation in the unshared Tcl object +will be freed as a consequence of setting the new value. +.PP +\fBTcl_GetDoubleFromObj\fR attempts to retreive a double value from the +Tcl object \fIobjPtr\fR. If the attempt succeeds, then \fBTCL_OK\fR is +returned, and the double value is written to the storage pointed to by +\fIdoublePtr\fR. If the attempt fails, then \fBTCL_ERROR\fR is returned, +and if \fIinterp\fR is non-NULL, an error message is left in \fIinterp\fR. +The \fBTcl_ObjType\fR of \fIobjPtr\fR may be changed to make subsequent +calls to \fBTcl_GetDoubleFromObj\fR more efficient. +'\" TODO: add discussion of treatment of NaN value .SH "SEE ALSO" Tcl_NewObj, Tcl_DecrRefCount, Tcl_IncrRefCount, Tcl_GetObjResult - .SH KEYWORDS double, double object, double type, internal representation, object, object type, string representation @@ -6,7 +6,7 @@ '\" 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 1.15 2005/10/05 03:58:35 hobbs Exp $ +'\" RCS: @(#) $Id: scan.n,v 1.16 2006/04/25 17:15:25 dgp Exp $ '\" .so man.macros .TH scan n 8.4 Tcl "Tcl Built-In Commands" @@ -20,14 +20,15 @@ scan \- Parse string using conversion specifiers in the style of sscanf .SH INTRODUCTION .PP -This command parses fields from an input string in the same fashion as the -ANSI C \fBsscanf\fR procedure and returns a count of the number of +This command parses substrings from an input string in a fashion similar +to the ANSI C \fBsscanf\fR procedure and returns a count of the number of conversions performed, or -1 if the end of the input string is reached before any conversions have been performed. \fIString\fR gives the input to be parsed and \fIformat\fR indicates how to parse it, using \fB%\fR conversion specifiers as in \fBsscanf\fR. Each \fIvarName\fR gives the -name of a variable; when a field is scanned from \fIstring\fR the result is -converted back into a string and assigned to the corresponding variable. +name of a variable; when a substring is scanned from \fIstring\fR that +matches a conversion specifier, the substring is assigned to the +corresponding variable. If no \fIvarName\fR variables are specified, then \fBscan\fR works in an inline manner, returning the data that would otherwise be stored in the variables as a list. In the inline case, an empty string is returned when @@ -44,16 +45,16 @@ must match the next character of \fIstring\fR. When a \fB%\fR is encountered in \fIformat\fR, it indicates the start of a conversion specifier. 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 XPG3 position specifier; a number -indicating a maximum field width; a field size modifier; and a +a XPG3 position specifier (or a \fB*\fR to indicate the converted +value is to be discarded instead of assigned to any variable); a number +indicating a maximum substring width; a size modifier; 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 \fIformat\fR, it first skips any white-space characters in \fIstring\fR (unless the -specifier is \fB[\fR or \fBc\fR). +conversion character 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. @@ -68,75 +69,75 @@ list must correspond to exactly one conversion specifier or an error is generated, or in the inline case, any position can be specified at most once and the empty positions will be filled in with empty strings. .PP +.VS 8.5 +The size modifier field is used only when scanning a substring into +one of Tcl's integer values. The size modifier field dictates the +integer range acceptable to be stored in a variable, or, for the inline +case, in a position in the result list. +The syntactically valid values for the size modifier are \fBh\fR, \fBL\fR, +\fBl\fR, and \fBll\fR. The \fBh\fR size modifier value is equivalent +to the absence of a size modifier in the the conversion specifier. +Either one indicates the integer range to be stored is limited to +the same range produced by the \fBint()\fR function of the \fBexpr\fR +command. The \fBL\fR size modifier is equivalent to the \fBl\fR size +modifer. Either one indicates the integer range to be stored is +limited to the same range produced by the \fBwide()\fR function of +the \fBexpr\fR command. The \fBll\fR size modifier indicates that +the integer range ro be stored is unlimited. +.VE 8.5 +.PP The following conversion characters are supported: .TP 10 \fBd\fR -The input field must be a decimal integer. -It is read in and the value is stored in the variable as a decimal string. -If the \fBl\fR or \fBL\fR field size modifier is given, the scanned -value will have an internal representation that is at least 64-bits in -size. +The input substring must be a decimal integer. +It is read in and the integer value is stored in the variable, +truncated as required by the size modifier value. .TP 10 \fBo\fR -The input field must be an octal integer. It is read in and the -value is stored in the variable as a decimal string. -If the \fBl\fR or \fBL\fR field size modifier is given, the scanned -value will have an internal representation that is at least 64-bits in -size. -If the value exceeds MAX_INT (017777777777 on platforms using 32-bit -integers when the \fBl\fR and \fBL\fR modifiers are not given), it -will be truncated to a signed integer. Hence, 037777777777 will -appear as -1 on a 32-bit machine by default. +The input substring must be an octal integer. It is read in and the +integer value is stored in the variable, +truncated as required by the size modifier value. .TP 10 \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. -If the \fBl\fR or \fBL\fR field size modifier is given, the scanned -value will have an internal representation that is at least 64-bits in -size. -If the value exceeds MAX_INT (0x7FFFFFFF on platforms using 32-bit -integers when the \fBl\fR and \fBL\fR modifiers are not given), it -will be truncated to a signed integer. Hence, 0xFFFFFFFF will appear -as -1 on a 32-bit machine. +The input substring must be a hexadecimal integer. +It is read in and the integer value is stored in the variable, +truncated as required by the size modifier value. .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. -If the \fBl\fR or \fBL\fR field size modifier is given, the scanned -value will have an internal representation that is at least 64-bits in -size. +The input substring must be a decimal integer. +The integer value is truncated as required by the size modifier +value, and the corresponding unsigned value for that truncated +range is computed and stored in the variable as a decimal string. +The conversion makes no sense without refernce to a truncation range, +so the size modifer \fBll\fR is not permitted in combination +with conversion character \fBu\fR. .TP 10 \fBi\fR -The input field must be an integer. The base (i.e. decimal, octal, or +The input substring 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. -If the \fBl\fR or \fBL\fR field size modifier is given, the scanned -value will have an internal representation that is at least 64-bits in -size. +\fBexpr\fR. The integer value is stored in the variable, +truncated as required by the size modifier value. .TP 10 \fBc\fR -A single character is read in and its binary value is stored in -the variable as a decimal string. +A single character is read in and its Unicode value is stored in +the variable as an integer value. Initial white space is not skipped in this case, so the input -field may be a white-space character. -This conversion is different from the ANSI standard in that the -input field always consists of a single character and no field -width may be specified. +substring may be a white-space character. .TP 10 \fBs\fR -The input field consists of all the characters up to the next +The input substring consists of all the characters up to the next white-space character; the characters are copied to the variable. .TP 10 \fBe\fR or \fBf\fR or \fBg\fR -The input field must be a floating-point number consisting +The input substring must be a floating-point number consisting of an optional sign, a string of decimal digits possibly containing a decimal point, and an optional exponent consisting of an \fBe\fR or \fBE\fR followed by an optional sign and a string of decimal digits. -It is read in and stored in the variable as a floating-point string. +It is read in and stored in the variable as a floating-point value. .TP 10 \fB[\fIchars\fB]\fR -The input field consists of one or more characters in \fIchars\fR. +The input substring consists of one or more characters in \fIchars\fR. 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 @@ -148,7 +149,7 @@ 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 \fB[^\fIchars\fB]\fR -The input field consists of one or more characters not in \fIchars\fR. +The input substring consists of one or more characters not in \fIchars\fR. 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 @@ -158,7 +159,7 @@ 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. +it is treated as part of \fIchars\fR rather than indicating a ranvaluege. .TP 10 \fBn\fR No input is consumed from the input string. Instead, the total number @@ -168,8 +169,8 @@ The number of characters read from the input for a conversion is the largest number that makes sense for that particular conversion (e.g. as many decimal digits as possible for \fB%d\fR, as many octal digits as possible for \fB%o\fR, and so on). -The input field for a given conversion terminates either when a -white-space character is encountered or when the maximum field +The input substring for a given conversion terminates either when a +white-space character is encountered or when the maximum substring width has been reached, whichever comes first. If a \fB*\fR is present in the conversion specifier then no variable is assigned and the next scan argument is not consumed. @@ -178,22 +179,23 @@ then no variable is assigned and the next scan argument is not consumed. 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: .IP [1] -\fB%p\fR conversion specifier is not currently supported. +\fB%p\fR conversion specifier is not supported. .IP [2] For \fB%c\fR conversions a single character value is converted to a decimal string, which is then assigned to the corresponding \fIvarName\fR; -no field width may be specified for this conversion. +no substring width may be specified for this conversion. .IP [3] The \fBh\fR modifier is always ignored and the \fBl\fR and \fBL\fR modifiers are ignored when converting real values (i.e. type -\fBdouble\fR is used for the internal representation). +\fBdouble\fR is used for the internal representation). The \fBll\fR +modifier has no \fBsscanf\fR counterpart. .IP [4] If the end of the input string is reached before any conversions have been performed and no variables are given, an empty string is returned. .SH EXAMPLES Parse a simple color specification of the form \fI#RRGGBB\fR using -hexadecimal conversions with field sizes: +hexadecimal conversions with substring sizes: .CS set string "#08D03F" \fBscan\fR $string "#%2x%2x%2x" r g b @@ -240,6 +242,21 @@ if { } puts "X=$x, Y=$y" .CE +.PP +.VS 8.5 +An interactive session demonstrating the truncation of integer +values determined by size modifiers: +.CS +% set tcl_platform(wordSize) +4 +% scan 20000000000000000000 %d +2147483647 +% scan 20000000000000000000 %ld +9223372036854775807 +% scan 20000000000000000000 %lld +20000000000000000000 +.CE +.VE 8.5 .SH "SEE ALSO" format(n), sscanf(3) diff --git a/generic/tclScan.c b/generic/tclScan.c index 91909c8..8696240 100644 --- a/generic/tclScan.c +++ b/generic/tclScan.c @@ -8,7 +8,7 @@ * See the file "license.terms" for information on usage and redistribution of * this file, and for a DISCLAIMER OF ALL WARRANTIES. * - * RCS: @(#) $Id: tclScan.c,v 1.23 2005/12/19 19:03:17 dgp Exp $ + * RCS: @(#) $Id: tclScan.c,v 1.24 2006/04/25 17:15:25 dgp Exp $ */ #include "tclInt.h" @@ -751,6 +751,7 @@ Tcl_ScanObjCmd( break; case 'u': op = 'i'; + parseFlag |= TCL_PARSE_DECIMAL_ONLY; flags |= SCAN_UNSIGNED; break; diff --git a/tests/scan.test b/tests/scan.test index e9ffad6..2a07f4b 100644 --- a/tests/scan.test +++ b/tests/scan.test @@ -11,7 +11,7 @@ # See the file "license.terms" for information on usage and redistribution # of this file, and for a DISCLAIMER OF ALL WARRANTIES. # -# RCS: @(#) $Id: scan.test,v 1.20 2006/03/21 11:12:29 dkf Exp $ +# RCS: @(#) $Id: scan.test,v 1.21 2006/04/25 17:15:25 dgp Exp $ if {[lsearch [namespace children] ::tcltest] == -1} { package require tcltest 2 @@ -429,6 +429,10 @@ test scan-5.13 {integer scanning and overflow} { scan {300000000 3000000000 30000000000} {%ld %ld %ld} } {300000000 3000000000 30000000000} +test scan-5.14 {integer scanning} { + scan 0xff %u +} 0 + test scan-6.1 {floating-point scanning} { set a {}; set b {}; set c {}; set d {} list [scan "2.1 -3.0e8 .99962 a" "%f%g%e%f" a b c d] $a $b $c $d |