"

 COPYRIGHT (c) 1988 by Claus Gittinger

	      All Rights Reserved

 This software is furnished under a license and may be used

 only in accordance with the terms of that license and with the

 inclusion of the above copyright notice.   This software may not

 be provided or otherwise made available to, or used by, any

 other person.  No title to or ownership of the software is

 hereby transferred.

"

"{ Package: 'stx:libbasic' }"

"{ NameSpace: Smalltalk }"

CharacterArray variableByteSubclass:#String

	instanceVariableNames:''

	classVariableNames:'CRLF CR LF TAB'

	poolDictionaries:''

	category:'Collections-Text'

!

!String primitiveDefinitions!

%{

#include <stdio.h>

#define _STDIO_H_INCLUDED_

#include <stdlib.h>

#include <ctype.h>

#ifdef LINUX

# define __STRINGDEFS__

# include <linuxIntern.h>

#endif

#ifdef __osx__

# include <string.h>

# include <stdlib.h>

#endif

/*

 * old st/x creates strings with spaces in it;

 * new st/x will fill it with zeros (for st-80 compatibility)

 * the define below sets old behavior.

 */

#define INITIALIZE_WITH_SPACE

#ifdef FAST_MEMCHR

 char *memchr();

#endif

%}

! !

!String primitiveFunctions!

%{

static int

nextOnKeyboard(char1, char2)

{

    /* compare two characters if they are next to each other on a (US-) keyboard */

    static char *us_keys[] = { "1234567890-",

			    "*qwertyuiop",

			    "**asdfghjkl:",

			    "***zxcvbnm",

			    0 };

    static char *de_keys[] = { "1234567890-",

			    "*qwertzuiop",

			    "**asdfghjkl:",

			    "***yxcvbnm",

			    0 };

    char **keys = us_keys;

    char **line1, **line2;

    char *col1, *col2;

    int diff;

    for (line1 = keys; *line1 != 0; line1++) {

	for (col1 = *line1; *col1 != 0 && *col1 != char1; col1++)

	    continue;

    }

    if (*col1 == 0)

	return(0);

    for (line2 = keys; *line2 != 0; line2++) {

	for (col2 = *line2; *col2 != 0 && *col2 != char2; col2++)

	    continue;

    }

    if (*col2 == 0)

	return(0);

    diff = col1 - col2;

    if (diff > 1 || diff < -1)

	return(0);

    diff = line1 - line2;

    if (diff > 1 || diff < -1)

	return(0);

    return(1);

}

%}

! !

!String class methodsFor:'documentation'!

copyright

"

 COPYRIGHT (c) 1988 by Claus Gittinger

	      All Rights Reserved

 This software is furnished under a license and may be used

 only in accordance with the terms of that license and with the

 inclusion of the above copyright notice.   This software may not

 be provided or otherwise made available to, or used by, any

 other person.  No title to or ownership of the software is

 hereby transferred.

"

!

documentation

"

    Strings are ByteArrays storing Characters.

    Strings are kind of kludgy: to allow for easy handling by c-functions,

    there is always one 0-byte added at the end, which is not counted

    in the strings size, and is not accessable from the smalltalk level.

    This guarantees, that a smalltalk string can always be passed to a

    C- or a system api function without danger (of course, this does not

    prevent a nonsense contents ...)

    You cannot add any instvars to String, since the the run time system & compiler

    creates literal strings and knows that strings have no named instvars.

    If you really need strings with instVars, you have to create a subclass

    of String (the access functions defined here can handle this).

    A little warning though: not all smalltalk systems allow subclassing String,

    so your program may become unportable if you do so.

    Strings have an implicit (assumed) encoding of iso8859-1.

    For strings with other encodings, either keep the encoding separately,

    or use instances of encodedString.

    [author:]

	Claus Gittinger

    [see also:]

	Text StringCollection TwoByteString JISEncodedString

	Symbol

"

! !

!String class methodsFor:'instance creation'!

basicNew:anInteger

    "return a new empty string with anInteger characters.

     In contrast to other smalltalks, this returns a string filled

     with spaces (instead of a string filled with 0-bytes).

     This makes much more sense, in that a freshly created string

     can be directly used as separator or for formatting."

%{  /* NOCONTEXT */

    OBJ newString;

    REGISTER int len;

    REGISTER unsigned char *cp;

    REGISTER OBJ *op;

    int nInstVars, instsize;

    if (__isSmallInteger(anInteger)) {

	len = __intVal(anInteger);

	if (len >= 0) {

	    instsize = OHDR_SIZE + len + 1;

	    if (self == String) {

		if (__CanDoQuickNew(instsize)) {        /* OBJECT ALLOCATION */

		    /*

		     * the most common case

		     */

		    __qCheckedNew(newString, instsize);

		    __InstPtr(newString)->o_class = self; /* no need for PROTECT - there was no GC */

		    __qSTORE(newString, self);

		    cp = __stringVal(newString);

#if defined(memset4) && !defined(NON_ASCII)

		    {

			/*

			 * no sizeof(int) here please -

			 * - memset4 (if defined) fills 4-bytes on ALL machines

			 */

			int l4 = len >> 2;

			if (len & 3) l4++;

			memset4(cp, 0x20202020, l4);

			cp[len] = '\0';

		    }

#else

# ifdef FAST_MEMSET

		    memset(cp, ' ', len);

		    cp[len] = '\0';

# else

		    while (len >= 8) {

#  ifndef NON_ASCII       /* i.e. EBCDIC  */

#   ifdef INT64

			((INT64 *)cp)[0] = 0x2020202020202020L;

#   else

			((int *)cp)[0] = 0x20202020;

			((int *)cp)[1] = 0x20202020;

#   endif

#  else

			cp[0] = cp[1] = cp[2] = cp[3] = ' ';

			cp[4] = cp[5] = cp[6] = cp[7] = ' ';

#  endif

			cp += 8;

			len -= 8;

		    }

		    while (len--)

			*cp++ = ' ';

		    *cp = '\0';

# endif /* not FAST_MEMSET */

#endif /* not memset4 */

		    RETURN (newString);

		}

		nInstVars = 0;

	    } else {

		nInstVars = __intVal(__ClassInstPtr(self)->c_ninstvars);

		instsize += __OBJS2BYTES__(nInstVars);

	    }

	    __PROTECT_CONTEXT__;

	    __qNew(newString, instsize);        /* OBJECT ALLOCATION */

	    __UNPROTECT_CONTEXT__;

	    if (newString == nil) goto fail;

	    __InstPtr(newString)->o_class = self;

	    __qSTORE(newString, self);

	    cp = __stringVal(newString);

	    if (nInstVars) {

		cp += __OBJS2BYTES__(nInstVars);

		/*

		 * nil-out instvars

		 */

#if defined(memset4)

		memset4(__InstPtr(newString)->i_instvars, nil, nInstVars);

#else

# if defined(FAST_MEMSET) && ! defined(NEGATIVE_ADDRESSES)

		/*

		 * knowing that nil is 0

		 */

		memset(__InstPtr(newString)->i_instvars, 0, __OBJS2BYTES__(nInstVars));

# else

		op = __InstPtr(newString)->i_instvars;

		do {

		    *op++ = nil;

		} while (--nInstVars);

# endif

#endif

	    }

	    /*

	     * fill with spaces

	     */

#ifdef FAST_MEMSET

	    memset(cp, ' ', len);

	    *(cp + len) = '\0';

#else

	    while (len >= 8) {

# ifndef NON_ASCII       /* i.e. EBCDIC ;-) */

#  ifdef INT64

		((INT64 *)cp)[0] = 0x2020202020202020L;

#  else

		((int *)cp)[0] = 0x20202020;

		((int *)cp)[1] = 0x20202020;

#  endif

# else

		cp[0] = cp[1] = cp[2] = cp[3] = ' ';

		cp[4] = cp[5] = cp[6] = cp[7] = ' ';

# endif

		cp += 8;

		len -= 8;

	    }

	    while (len--)

		*cp++ = ' ';

	    *cp = '\0';

#endif

	    RETURN (newString);

	}

    }

fail: ;;

%}.

    "

     invalid argument, or out-of-memory:

     use error handling in superclass

    "

    (anInteger < 0) ifTrue:[

	"

	 the argument is negative,

	"

	self error:'bad (negative) argument to new:'.

	^ nil

    ].

    ^ (super basicNew:anInteger+1) atAllPut:(Character space)

!

new:n

    "return a new empty string with anInteger characters.

     In contrast to other smalltalks, this returns a string filled

     with spaces (instead of a string filled with 0-bytes).

     This makes much more sense, in that a freshly created string

     can be directly used as separator or for formatting."

    ^ self basicNew:n

!

readFrom:aStreamOrString onError:exceptionBlock

    "read & return the next String from the (character-)stream aStream;

     skipping all whitespace first; return the value of exceptionBlock,

     if no string can be read. The sequence of characters as read from the

     stream must be one as stored via storeOn: or storeString."

    "

     this method is not to be inherited

     (i.e. not ok for subclasses; Symbol, for example)

    "

    self ~~ String ifTrue:[

	^ super readFrom:aStreamOrString onError:exceptionBlock

    ].

    ^ self readSmalltalkStringFrom:aStreamOrString onError:exceptionBlock

    "

     String readFrom:('''hello world''' readStream)

     String readFrom:('''hello '''' world''' readStream)

     String readFrom:('1 ''hello'' ' readStream)

     String readFrom:('1 ''hello'' ' readStream) onError:['foobar']

    "

    "Modified: / 05-07-2006 / 16:41:29 / cg"

    "Modified: / 07-08-2006 / 15:03:09 / fm"

!

uninitializedNew:anInteger

    "return a new string with anInteger characters but undefined contents.

     Use this, if the string is filled anyway with new data, for example, if

     used as a stream buffer."

%{  /* NOCONTEXT */

    OBJ newString;

    REGISTER int len;

    REGISTER unsigned char *cp;

    REGISTER OBJ *op;

    int nInstVars, instsize;

    if (__isSmallInteger(anInteger)) {

	len = __intVal(anInteger);

	if (len >= 0) {

	    instsize = OHDR_SIZE + len + 1;

	    if (self == String) {

		if (__CanDoQuickNew(instsize)) {        /* OBJECT ALLOCATION */

		    /*

		     * the most common case

		     */

		    __qCheckedNew(newString, instsize);

		    __InstPtr(newString)->o_class = self; /* no need for PROTECT - there was no GC */

		    __qSTORE(newString, self);

		    cp = __stringVal(newString);

		    cp[len] = '\0';

		    RETURN (newString);

		}

		nInstVars = 0;

	    } else {

		nInstVars = __intVal(__ClassInstPtr(self)->c_ninstvars);

		instsize += __OBJS2BYTES__(nInstVars);

	    }

	    __PROTECT_CONTEXT__;

	    __qNew(newString, instsize);        /* OBJECT ALLOCATION */

	    __UNPROTECT_CONTEXT__;

	    if (newString == nil) goto fail;

	    __InstPtr(newString)->o_class = self;

	    __qSTORE(newString, self);

	    if (nInstVars) {

		/*

		 * nil-out instvars

		 */

#if defined(memset4)

		memset4(__InstPtr(newString)->i_instvars, nil, nInstVars);

#else

# if defined(FAST_MEMSET) && ! defined(NEGATIVE_ADDRESSES)

		/*

		 * knowing that nil is 0

		 */

		memset(__InstPtr(newString)->i_instvars, 0, __OBJS2BYTES__(nInstVars));

# else

		op = __InstPtr(newString)->i_instvars;

		do {

		    *op++ = nil;

		} while (--nInstVars);

# endif

#endif

		cp = __stringVal(newString) + __OBJS2BYTES__(nInstVars);

	    } else {

		cp = __stringVal(newString);

	    }

	    *(cp + len) = '\0';

	    RETURN (newString);

	}

    }

fail: ;;

%}.

    "

     invalid argument, or out-of-memory:

     use error handling in superclass

    "

    (anInteger < 0) ifTrue:[

	"

	 the argument is negative,

	"

	self error:'bad (negative) argument to new:'.

	^ nil

    ].

    ^ self basicNew:anInteger

    "

     String uninitializedNew:100

    "

! !

!String class methodsFor:'Compatibility-Dolphin'!

lineDelimiter

    "Dolphin compatibility: answer CR LF"

    ^ self crlf

! !

!String class methodsFor:'Compatibility-Squeak'!

cr

    "return a string consisting of the cr-Character"

    CR isNil ifTrue:[

	CR := String with:Character return

    ].

    ^ CR

    "Modified: / 13.11.1999 / 13:53:36 / cg"

!

crlf

    "return a string consisting of the cr-lf Characters"

    CRLF isNil ifTrue:[

	CRLF := String

		    with:Character return

		    with:Character linefeed

    ].

    ^ CRLF

!

lf

    "return a string consisting of the lf Character"

    LF isNil ifTrue:[

	LF := String with:Character linefeed

    ].

    ^ LF

!

stringHash:aString initialHash:speciesHash

    "for squeak compatibility only; this is NOT the same hash as my instances use"

    | stringSize hash low |

    stringSize := aString size.

    hash := speciesHash bitAnd: 16rFFFFFFF.

    1 to: stringSize do: [:pos |