removed all string related builtin functions and moved them to separate routines in new 'string' library module

compiler/res/.editorconfig

@@ -7,16 +7,14 @@ indent_size = 4
 indent_style = space
 insert_final_newline = true
 max_line_length = 120
-tab_width = 4
+tab_width = 8
 trim_trailing_whitespace = true
 ij_smart_tabs = true
 
 [*.p8]
-tab_width = 4
 indent_size = 4
 indent_style = space
 
 [*.asm]
-tab_width = 8
 indent_size = 8
 indent_style = tab

compiler/res/prog8lib/diskio.p8

@@ -3,6 +3,7 @@
 ; Written by Irmen de Jong (irmen@razorvine.net) - license: GNU GPL 3.0
 
 %import textio
+%import string
 %import syslib
 
 diskio {
@@ -84,7 +85,7 @@ io_error:
                 name_ptrs++
                 @(name_ptrs) = msb(names_buffer)
                 name_ptrs++
-                names_buffer += strcopy(diskio.list_filename, names_buffer) + 1
+                names_buffer += string.copy(diskio.list_filename, names_buffer) + 1
                 files_found++
                 if names_buffer - buffer_start > 512-18
                     break
@@ -204,7 +205,7 @@ close_end:
         ;    note: only a single iteration loop can be active at a time!
         f_close()
 
-        c64.SETNAM(strlen(filenameptr), filenameptr)
+        c64.SETNAM(string.length(filenameptr), filenameptr)
         c64.SETLFS(11, drivenumber, 3)
         void c64.OPEN()          ; open 11,8,0,"filename"
         if_cc {
@@ -373,7 +374,7 @@ io_error:
 
 
     sub save(ubyte drivenumber, uword filenameptr, uword address, uword size) -> ubyte {
-        c64.SETNAM(strlen(filenameptr), filenameptr)
+        c64.SETNAM(string.length(filenameptr), filenameptr)
         c64.SETLFS(1, drivenumber, 0)
         uword end_address = address + size
 
@@ -403,7 +404,7 @@ io_error:
     }
 
     sub load(ubyte drivenumber, uword filenameptr, uword address_override) -> uword {
-        c64.SETNAM(strlen(filenameptr), filenameptr)
+        c64.SETNAM(string.length(filenameptr), filenameptr)
         ubyte secondary = 1
         uword end_of_load = 0
         if address_override
@@ -435,7 +436,7 @@ io_error:
 
     sub delete(ubyte drivenumber, uword filenameptr) {
         ; -- delete a file on the drive
-        ubyte flen = strlen(filenameptr)
+        ubyte flen = string.length(filenameptr)
         filename[0] = 's'
         filename[1] = ':'
         memcopy(filenameptr, &filename+2, flen+1)
@@ -448,8 +449,8 @@ io_error:
 
     sub rename(ubyte drivenumber, uword oldfileptr, uword newfileptr) {
         ; -- rename a file on the drive
-        ubyte flen_old = strlen(oldfileptr)
+        ubyte flen_old = string.length(oldfileptr)
-        ubyte flen_new = strlen(newfileptr)
+        ubyte flen_new = string.length(newfileptr)
         filename[0] = 'r'
         filename[1] = ':'
         memcopy(newfileptr, &filename+2, flen_new)

compiler/res/prog8lib/prog8_funcs.asm

@@ -1204,205 +1204,3 @@ func_memcopy255	.proc
 		ldx  P8ZP_SCRATCH_REG
 		rts
 		.pend
-
-
-func_leftstr	.proc
-		; leftstr(source, target, length)
-		lda  _arg_source
-		ldy  _arg_source+1
-		sta  P8ZP_SCRATCH_W1
-		sty  P8ZP_SCRATCH_W1+1
-		lda  _arg_target
-		ldy  _arg_target+1
-		sta  P8ZP_SCRATCH_W2
-		sty  P8ZP_SCRATCH_W2+1
-		ldy  _arg_length
-		lda  #0
-		sta  (P8ZP_SCRATCH_W2),y
-		cpy  #0
-		bne  _loop
-		rts
-_loop		dey
-		lda  (P8ZP_SCRATCH_W1),y
-		sta  (P8ZP_SCRATCH_W2),y
-		cpy  #0
-		bne  _loop
-+		rts
-
-_arg_source	.word  0
-_arg_target	.word  0
-_arg_length	.byte  0
-		.pend
-
-
-func_rightstr	.proc
-		; rightstr(source, target, length)
-		lda  _arg_source
-		ldy  _arg_source+1
-		jsr  func_strlen_into_A
-		sec
-		sbc  _arg_length
-		sta  P8ZP_SCRATCH_B1
-		lda  _arg_source
-		ldy  _arg_source+1
-		sta  P8ZP_SCRATCH_W1
-		sty  P8ZP_SCRATCH_W1+1
-		lda  _arg_target
-		ldy  _arg_target+1
-		sta  P8ZP_SCRATCH_W2
-		sty  P8ZP_SCRATCH_W2+1
-		ldy  #0
-		sty  P8ZP_SCRATCH_REG
--		ldy  P8ZP_SCRATCH_B1
-		lda  (P8ZP_SCRATCH_W1),y
-		inc  P8ZP_SCRATCH_B1
-		ldy  P8ZP_SCRATCH_REG
-		sta  (P8ZP_SCRATCH_W2),y
-		inc  P8ZP_SCRATCH_REG
-		cmp  #0
-		bne  -
-		rts
-
-_arg_source	.word  0
-_arg_target	.word  0
-_arg_length	.byte  0
-		.pend
-
-
-func_strlen_into_A		.proc
-	; -- put length of 0-terminated string in A/Y into A
-		sta  P8ZP_SCRATCH_W1
-		sty  P8ZP_SCRATCH_W1+1
-		ldy  #0
--		lda  (P8ZP_SCRATCH_W1),y
-		beq  +
-		iny
-		bne  -
-+		tya
-		rts
-		.pend
-
-func_strlen_stack	.proc
-		jsr  func_strlen_into_A
-		sta  P8ESTACK_LO,x
-		dex
-		rts
-		.pend
-
-
-func_substr	.proc
-		; substr(source, target, start, length)
-		lda  _arg_source
-		ldy  _arg_source+1
-		sta  P8ZP_SCRATCH_W1
-		sty  P8ZP_SCRATCH_W1+1
-		lda  _arg_target
-		ldy  _arg_target+1
-		sta  P8ZP_SCRATCH_W2
-		sty  P8ZP_SCRATCH_W2+1
-		ldy  _arg_length
-		lda  _arg_start
-		sta  P8ZP_SCRATCH_B1
-
-		; adjust src location
-		clc
-		lda  P8ZP_SCRATCH_W1
-		adc  P8ZP_SCRATCH_B1
-		sta  P8ZP_SCRATCH_W1
-		bcc  +
-		inc  P8ZP_SCRATCH_W1+1
-+		lda  #0
-		sta  (P8ZP_SCRATCH_W2),y
-		jmp  _startloop
--		lda  (P8ZP_SCRATCH_W1),y
-		sta  (P8ZP_SCRATCH_W2),y
-_startloop	dey
-		cpy  #$ff
-		bne  -
-		rts
-
-_arg_source	.word  0
-_arg_target	.word  0
-_arg_start	.byte  0
-_arg_length	.byte  0
-		.pend
-
-
-func_strcmp	.proc
-		; -- compare 2 strings -> A
-		lda  _arg_s2
-		ldy  _arg_s2+1
-		sta  P8ZP_SCRATCH_W2
-		sty  P8ZP_SCRATCH_W2+1
-		lda  _arg_s1
-		ldy  _arg_s1+1
-		jmp  strcmp_mem
-_arg_s1		.word  0
-_arg_s2		.word  0
-		.pend
-
-func_strcmp_stack	.proc
-		jsr	func_strcmp
-		sta  P8ESTACK_LO,x
-		dex
-		rts
-		.pend
-
-func_strcopy	.proc
-		lda  _arg_to
-		ldy  _arg_to+1
-		sta  P8ZP_SCRATCH_W1
-		sty  P8ZP_SCRATCH_W1+1
-		lda  _arg_from
-		ldy  _arg_from+1
-		jsr  strcpy
-		tya
-		rts
-_arg_from	.word  0
-_arg_to		.word  0
-		.pend
-
-func_strcopy_to_stack	.proc
-		jsr  func_strcopy
-		sta  P8ESTACK_LO,x
-		dex
-		rts
-		.pend
-
-
-func_strfind	.proc
-		lda  _arg_string
-		ldy  _arg_string+1
-		sta  P8ZP_SCRATCH_W1
-		sty  P8ZP_SCRATCH_W1+1
-		ldy  #0
--		lda  (P8ZP_SCRATCH_W1),y
-		beq  _notfound
-		cmp  _arg_char
-		beq  _found
-		iny
-		bne  -
-_notfound	lda  #0
-		ldy  #0
-		rts
-_found		sty  P8ZP_SCRATCH_B1
-		lda  P8ZP_SCRATCH_W1
-		clc
-		adc  P8ZP_SCRATCH_B1
-		sta  P8ZP_SCRATCH_W1
-		bcc  +
-		inc  P8ZP_SCRATCH_W1+1
-+		ldy  P8ZP_SCRATCH_W1+1
-		rts
-
-_arg_string	.word  0
-_arg_char	.byte  0
-		.pend
-
-func_strfind_stack	.proc
-		jsr  func_strfind
-		sta  P8ESTACK_LO,x
-		sty  P8ESTACK_HI,x
-		dex
-		rts
-		.pend

compiler/res/prog8lib/string.p8

@@ -5,5 +5,189 @@
 
 string {
 
+    asmsub length(uword string @AY) clobbers(A) -> ubyte @Y {
+        ; Returns the number of bytes in the string.
+        ; This value is determined during runtime and counts upto the first terminating 0 byte in the string,
+        ; regardless of the size of the string during compilation time. Don’t confuse this with len and sizeof!
+
+        %asm {{
+		sta  P8ZP_SCRATCH_W1
+		sty  P8ZP_SCRATCH_W1+1
+		ldy  #0
+-		lda  (P8ZP_SCRATCH_W1),y
+		beq  +
+		iny
+		bne  -
++		rts
+        }}
+    }
+
+    asmsub left(uword source @R0, ubyte length @A, uword target @R1) clobbers(A, Y) {
+        ; Copies the left side of the source string of the given length to target string.
+        ; It is assumed the target string buffer is large enough to contain the result.
+        ; Also, you have to make sure yourself that length is smaller or equal to the length of the source string.
+        ; Modifies in-place, doesn’t return a value (so can’t be used in an expression).
+        %asm {{
+                ; need to copy the the cx16 virtual registers to zeropage to be compatible with C64...
+		ldy  cx16.r0
+		sty  P8ZP_SCRATCH_W1
+		ldy  cx16.r0+1
+		sty  P8ZP_SCRATCH_W1+1
+		ldy  cx16.r1
+		sty  P8ZP_SCRATCH_W2
+		ldy  cx16.r1+1
+		sty  P8ZP_SCRATCH_W2+1
+		tay
+		lda  #0
+		sta  (P8ZP_SCRATCH_W2),y
+		cpy  #0
+		bne  _loop
+		rts
+_loop		dey
+		lda  (P8ZP_SCRATCH_W1),y
+		sta  (P8ZP_SCRATCH_W2),y
+		cpy  #0
+		bne  _loop
++		rts
+        }}
+;                asmgen.out("  jsr  prog8_lib.func_leftstr")
+    }
+
+    asmsub right(uword source @R0, ubyte length @A, uword target @R1) clobbers(A,Y) {
+        ; Copies the right side of the source string of the given length to target string.
+        ; It is assumed the target string buffer is large enough to contain the result.
+        ; Also, you have to make sure yourself that length is smaller or equal to the length of the source string.
+        ; Modifies in-place, doesn’t return a value (so can’t be used in an expression).
+        %asm {{
+                ; need to copy the the cx16 virtual registers to zeropage to be compatible with C64...
+                sta  P8ZP_SCRATCH_B1
+                lda  cx16.r0
+                ldy  cx16.r0+1
+                jsr  string.length
+                tya
+                sec
+                sbc  P8ZP_SCRATCH_B1
+                clc
+                adc  cx16.r0
+		sta  P8ZP_SCRATCH_W1
+		lda  cx16.r0+1
+		adc  #0
+		sta  P8ZP_SCRATCH_W1+1
+		ldy  cx16.r1
+		sty  P8ZP_SCRATCH_W2
+		ldy  cx16.r1+1
+		sty  P8ZP_SCRATCH_W2+1
+		ldy  P8ZP_SCRATCH_B1
+		lda  #0
+		sta  (P8ZP_SCRATCH_W2),y
+		cpy  #0
+		bne  _loop
+		rts
+_loop		dey
+		lda  (P8ZP_SCRATCH_W1),y
+		sta  (P8ZP_SCRATCH_W2),y
+		cpy  #0
+		bne  _loop
++		rts
+        }}
+    }
+
+    asmsub slice(uword source @R0, ubyte start @A, ubyte length @Y, uword target @R1) clobbers(A, Y) {
+        ; Copies a segment from the source string, starting at the given index,
+        ;  and of the given length to target string.
+        ; It is assumed the target string buffer is large enough to contain the result.
+        ; Also, you have to make sure yourself that start and length are within bounds of the strings.
+        ; Modifies in-place, doesn’t return a value (so can’t be used in an expression).
+        %asm {{
+                ; need to copy the the cx16 virtual registers to zeropage to be compatible with C64...
+		; substr(source, target, start, length)
+		sta  P8ZP_SCRATCH_B1
+		lda  cx16.r0
+		sta  P8ZP_SCRATCH_W1
+		lda  cx16.r0+1
+		sta  P8ZP_SCRATCH_W1+1
+		lda  cx16.r1
+		sta  P8ZP_SCRATCH_W2
+		lda  cx16.r1+1
+		sta  P8ZP_SCRATCH_W2+1
+
+		; adjust src location
+		clc
+		lda  P8ZP_SCRATCH_W1
+		adc  P8ZP_SCRATCH_B1
+		sta  P8ZP_SCRATCH_W1
+		bcc  +
+		inc  P8ZP_SCRATCH_W1+1
++		lda  #0
+		sta  (P8ZP_SCRATCH_W2),y
+		beq  _startloop
+-		lda  (P8ZP_SCRATCH_W1),y
+		sta  (P8ZP_SCRATCH_W2),y
+_startloop	dey
+		cpy  #$ff
+		bne  -
+		rts
+        }}
+    }
+
+    asmsub find(uword string @R0, ubyte character @A) -> uword @AY {
+        ; Locates the first position of the given character in the string,
+        ;  returns the string starting with this character or $0000 if the character is not found.
+        %asm {{
+                ; need to copy the the cx16 virtual registers to zeropage to be compatible with C64...
+                sta  P8ZP_SCRATCH_B1
+		lda  cx16.r0
+		ldy  cx16.r0+1
+		sta  P8ZP_SCRATCH_W1
+		sty  P8ZP_SCRATCH_W1+1
+		ldy  #0
+-		lda  (P8ZP_SCRATCH_W1),y
+		beq  _notfound
+		cmp  P8ZP_SCRATCH_B1
+		beq  _found
+		iny
+		bne  -
+_notfound	lda  #0
+		ldy  #0
+		rts
+_found		sty  P8ZP_SCRATCH_B1
+		ldy  P8ZP_SCRATCH_W1+1
+		lda  P8ZP_SCRATCH_W1
+		clc
+		adc  P8ZP_SCRATCH_B1
+		bcc  +
+		iny
++		rts
+
+        }}
+    }
+
+    asmsub copy(uword source @R0, uword target @AY) clobbers(A) -> ubyte @Y {
+        ; Copy a string to another, overwriting that one.
+        ; Returns the length of the string that was copied.
+        ; Often you don’t have to call this explicitly and can just write string1 = string2
+        ; but this function is useful if you’re dealing with addresses for instance.
+        %asm {{
+		sta  P8ZP_SCRATCH_W1
+		sty  P8ZP_SCRATCH_W1+1
+		lda  cx16.r0
+		ldy  cx16.r0+1
+		jmp  prog8_lib.strcpy
+        }}
+    }
+
+    asmsub compare(uword string1 @R0, uword string2 @AY) clobbers(Y) -> ubyte @A {
+        ; Compares two strings for sorting.
+        ; Returns -1 (255), 0 or 1 depeding on wether string1 sorts before, equal or after string2.
+        ; Note that you can also directly compare strings and string values with eachother using
+        ; comparison operators ==, < etcetera (it will use strcmp for you under water automatically).
+        %asm {{
+		sta  P8ZP_SCRATCH_W2
+		sty  P8ZP_SCRATCH_W2+1
+		lda  cx16.r0
+		ldy  cx16.r0+1
+		jmp  prog8_lib.strcmp_mem
+        }}
+    }
 
 }

compiler/src/prog8/compiler/target/c64/codegen/BuiltinFunctionsAsmGen.kt

@@ -79,21 +79,7 @@ internal class BuiltinFunctionsAsmGen(private val program: Program, private val
             "set_carry" -> asmgen.out("  sec")
             "clear_irqd" -> asmgen.out("  cli")
             "set_irqd" -> asmgen.out("  sei")
-            "strlen" -> funcStrlen(fcall, resultToStack)
-            "strfind" -> funcStrfind(fcall, func, resultToStack, sscope)
-            "strcmp" -> funcStrcmp(fcall, func, resultToStack, sscope)
-            "strcopy" -> {
-                translateArguments(fcall.args, func, sscope)
-                if(resultToStack)
-                    asmgen.out("  jsr  prog8_lib.func_strcopy_to_stack")
-                else
-                    asmgen.out("  jsr  prog8_lib.func_strcopy")
-            }
             "memcopy", "memset", "memsetw" -> funcMemSetCopy(fcall, func, sscope)
-            "substr", "leftstr", "rightstr" -> {
-                translateArguments(fcall.args, func, sscope)
-                asmgen.out("  jsr  prog8_lib.func_${func.name}")
-            }
             "exit" -> {
                 translateArguments(fcall.args, func, sscope)
                 asmgen.out("  jmp  prog8_lib.func_exit")
@@ -198,22 +184,6 @@ internal class BuiltinFunctionsAsmGen(private val program: Program, private val
         }
     }
 
-    private fun funcStrfind(fcall: IFunctionCall, func: FSignature, resultToStack: Boolean, scope: Subroutine?) {
-        translateArguments(fcall.args, func, scope)
-        if(resultToStack)
-            asmgen.out("  jsr  prog8_lib.func_strfind_stack")
-        else
-            asmgen.out("  jsr  prog8_lib.func_strfind")
-    }
-
-    private fun funcStrcmp(fcall: IFunctionCall, func: FSignature, resultToStack: Boolean, scope: Subroutine?) {
-        translateArguments(fcall.args, func, scope)
-        if(resultToStack)
-            asmgen.out("  jsr  prog8_lib.func_strcmp_stack")
-        else
-            asmgen.out("  jsr  prog8_lib.func_strcmp")
-    }
-
     private fun funcSqrt16(fcall: IFunctionCall, func: FSignature, resultToStack: Boolean, scope: Subroutine?) {
         translateArguments(fcall.args, func, scope)
         if(resultToStack)
@@ -588,27 +558,6 @@ internal class BuiltinFunctionsAsmGen(private val program: Program, private val
         }
     }
 
-    private fun funcStrlen(fcall: IFunctionCall, resultToStack: Boolean) {
-        if (fcall.args[0] is IdentifierReference) {
-            // use the address of the variable
-            val name = asmgen.asmVariableName(fcall.args[0] as IdentifierReference)
-            val type = fcall.args[0].inferType(program)
-            when {
-                type.istype(DataType.STR) -> asmgen.out("  lda  #<$name |  ldy  #>$name")
-                type.istype(DataType.UWORD) -> asmgen.out("  lda  $name |  ldy  $name+1")
-                else -> throw AssemblyError("strlen requires str or uword arg")
-            }
-        }
-        else {
-            // use the expression value as address of the string
-            asmgen.assignExpressionToRegister(fcall.args[0], RegisterOrPair.AY)
-        }
-        if (resultToStack)
-            asmgen.out("  jsr  prog8_lib.func_strlen_stack")
-        else
-            asmgen.out("  jsr  prog8_lib.func_strlen_into_A")
-    }
-
     private fun funcSwap(fcall: IFunctionCall) {
         val first = fcall.args[0]
         val second = fcall.args[1]

compiler/src/prog8/functions/BuiltinFunctions.kt

@@ -159,24 +159,7 @@ private val functionSignatures: List<FSignature> = listOf(
     FSignature("memsetw"     , false, listOf(
                             FParam("address", IterableDatatypes + DataType.UWORD),
                             FParam("numwords", setOf(DataType.UWORD)),
-                            FParam("wordvalue", setOf(DataType.UWORD, DataType.WORD))), null),
+                            FParam("wordvalue", setOf(DataType.UWORD, DataType.WORD))), null)
-    FSignature("strlen"      , true, listOf(FParam("string", StringlyDatatypes)), DataType.UBYTE, ::builtinStrlen),
-    FSignature("strcopy"     , false, listOf(FParam("from", StringlyDatatypes), FParam("to", StringlyDatatypes)), DataType.UBYTE),
-    FSignature("substr"      , false, listOf(
-            FParam("source", StringlyDatatypes),
-            FParam("target", StringlyDatatypes),
-            FParam("start", setOf(DataType.UBYTE)),
-            FParam("length", setOf(DataType.UBYTE))), null),
-    FSignature("leftstr"     , false, listOf(
-            FParam("source", StringlyDatatypes),
-            FParam("target", StringlyDatatypes),
-            FParam("length", setOf(DataType.UBYTE))), null),
-    FSignature("rightstr"    , false, listOf(
-            FParam("source", StringlyDatatypes),
-            FParam("target", StringlyDatatypes),
-            FParam("length", setOf(DataType.UBYTE))), null),
-    FSignature("strcmp"      , true, listOf(FParam("s1", StringlyDatatypes), FParam("s2", StringlyDatatypes)), DataType.BYTE, null),
-    FSignature("strfind"     , true, listOf(FParam("string", StringlyDatatypes), FParam("char", setOf(DataType.UBYTE))), DataType.STR, null)
 )
 
 val BuiltinFunctions = functionSignatures.associateBy { it.name }
@@ -355,23 +338,6 @@ private fun builtinSizeof(args: List<Expression>, position: Position, program: P
     }
 }
 
-private fun builtinStrlen(args: List<Expression>, position: Position, program: Program): NumericLiteralValue {
-    if (args.size != 1)
-        throw SyntaxError("strlen requires one argument", position)
-    val argument=args[0]
-    if(argument is StringLiteralValue)
-        return NumericLiteralValue.optimalInteger(argument.value.length, argument.position)
-    val vardecl = (argument as? IdentifierReference)?.targetVarDecl(program.namespace)
-    if(vardecl!=null) {
-        if(vardecl.datatype!=DataType.STR && vardecl.datatype!=DataType.UWORD)
-            throw SyntaxError("strlen must have string argument", position)
-        if(vardecl.autogeneratedDontRemove && vardecl.value!=null) {
-            return NumericLiteralValue.optimalInteger((vardecl.value as StringLiteralValue).value.length, argument.position)
-        }
-    }
-    throw NotConstArgumentException()
-}
-
 private fun builtinLen(args: List<Expression>, position: Position, program: Program): NumericLiteralValue {
     // note: in some cases the length is > 255 and then we have to return a UWORD type instead of a UBYTE.
     if(args.size!=1)

docs/source/libraries.rst

@@ -65,6 +65,49 @@ Provides several routines that deal with disk drive I/O, such as:
 - delete and rename files on the disk
 
 
+string
+------
+Provides string manipulation routines.
+
+length(str) -> ubyte length
+    Number of bytes in the string. This value is determined during runtime and counts upto
+    the first terminating 0 byte in the string, regardless of the size of the string during compilation time.
+    Don't confuse this with ``len`` and ``sizeof``
+
+left(source, length, target)
+    Copies the left side of the source string of the given length to target string.
+    It is assumed the target string buffer is large enough to contain the result.
+    Also, you have to make sure yourself that length is smaller or equal to the length of the source string.
+    Modifies in-place, doesn't return a value (so can't be used in an expression).
+
+right(source, length, target)
+    Copies the right side of the source string of the given length to target string.
+    It is assumed the target string buffer is large enough to contain the result.
+    Also, you have to make sure yourself that length is smaller or equal to the length of the source string.
+    Modifies in-place, doesn't return a value (so can't be used in an expression).
+
+slice(source, start, length, target)
+    Copies a segment from the source string, starting at the given index,
+    and of the given length to target string.
+    It is assumed the target string buffer is large enough to contain the result.
+    Also, you have to make sure yourself that start and length are within bounds of the strings.
+    Modifies in-place, doesn't return a value (so can't be used in an expression).
+
+find(string, char) -> uword address
+    Locates the first position of the given character in the string, returns the string starting
+    with this character or $0000 if the character is not found.
+
+compare(string1, string2) -> ubyte result
+    Returns -1, 0 or 1 depeding on wether string1 sorts before, equal or after string2.
+    Note that you can also directly compare strings and string values with eachother
+    using ``==``, ``<`` etcetera (it will use string.compare for you under water automatically).
+
+copy(from, to) -> ubyte length
+    Copy a string to another, overwriting that one. Returns the length of the string that was copied.
+    Often you don't have to call this explicitly and can just write ``string1 = string2``
+    but this function is useful if you're dealing with addresses for instance.
+
+
 floats
 ------
 Provides definitions for the ROM/kernel subroutines and utility routines dealing with floating

docs/source/programming.rst

@@ -799,44 +799,6 @@ memsetw(address, numwords, wordvalue)
     Efficiently set a part of memory to the given (u)word value.
     But the most efficient will always be to write a specialized fill routine in assembly yourself!
 
-leftstr(source, target, length)
-    Copies the left side of the source string of the given length to target string.
-    It is assumed the target string buffer is large enough to contain the result.
-    Also, you have to make sure yourself that length is smaller or equal to the length of the source string.
-    Modifies in-place, doesn't return a value (so can't be used in an expression).
-
-rightstr(source, target, length)
-    Copies the right side of the source string of the given length to target string.
-    It is assumed the target string buffer is large enough to contain the result.
-    Also, you have to make sure yourself that length is smaller or equal to the length of the source string.
-    Modifies in-place, doesn't return a value (so can't be used in an expression).
-
-strlen(str)
-    Number of bytes in the string. This value is determined during runtime and counts upto
-    the first terminating 0 byte in the string, regardless of the size of the string during compilation time.
-    Don't confuse this with ``len`` and ``sizeof``
-
-strcmp(string1, string2)
-    Returns -1, 0 or 1 depeding on wether string1 sorts before, equal or after string2.
-    Note that you can also directly compare strings and string values with eachother
-    using ``==``, ``<`` etcetera (it will use strcmp for you under water automatically).
-
-substr(source, target, start, length)
-    Copies a segment from the source string, starting at the given index,
-    and of the given length to target string.
-    It is assumed the target string buffer is large enough to contain the result.
-    Also, you have to make sure yourself that start and length are within bounds of the strings.
-    Modifies in-place, doesn't return a value (so can't be used in an expression).
-
-strcopy(from, to)
-    Copy a string to another, overwriting that one. Returns the length of the string that was copied.
-    Often you don't have to call this explicitly and can just write ``string1 = string2``
-    but this function is useful if you're dealing with addresses for instance.
-
-strfind(string, char)
-    Locates the first position of the given character in the string, returns the string starting
-    with this character or $0000 if the character is not found.
-
 
 Miscellaneous
 ^^^^^^^^^^^^^

docs/source/todo.rst

@@ -3,8 +3,10 @@ TODO
 ====
 
 - move all str* builtin functions to a strings library module, mem* to the sys module. update docs.
+- move target() builtin to sys.target constant
 - use (zp) addressing mode on 65c02 specific code rather than ldy#0 / lda (zp),y
 - optimize pointer access code @(pointer)? use a subroutine? macro?  65c02 vs 6502?
+- allow byte return type with single register for asmsubs, for instance string.compare
 - can we get rid of the --longOptionName command line options and only keep the short versions? https://github.com/Kotlin/kotlinx-cli/issues/50
 - optimizer: detect variables that are written but never read - mark those as unused too and remove them, such as uword unused = memory("unused222", 20) - also remove the memory slab allocation
 - hoist all variable declarations up to the subroutine scope *before* even the constant folding takes place (to avoid undefined symbol errors when referring to a variable from another nested scope in the subroutine)

examples/.editorconfig

@@ -7,16 +7,14 @@ indent_size = 4
 indent_style = space
 insert_final_newline = true
 max_line_length = 120
-tab_width = 4
+tab_width = 8
 trim_trailing_whitespace = true
 ij_smart_tabs = true
 
 [*.p8]
-tab_width = 4
 indent_size = 4
 indent_style = space
 
 [*.asm]
-tab_width = 8
 indent_size = 8
 indent_style = tab

examples/arithmetic/aggregates.p8

@@ -1,5 +1,6 @@
 %import floats
 %import textio
+%import string
 %zeropage basicsafe
 
 main {
@@ -22,10 +23,10 @@ main {
         if length!=5 txt.print("error len1\n")
         length = len(uwarr)
         if length!=5 txt.print("error len2\n")
-        length=strlen(name)
+        length=string.length(name)
         if length!=5 txt.print("error strlen1\n")
         name[3] = 0
-        length=strlen(name)
+        length=string.length(name)
         if length!=3 txt.print("error strlen2\n")
 
         ; MAX

examples/arithmetic/bitshift.p8

@@ -477,6 +477,7 @@ main {
 
 
 
+    ; @TODO fix type errors
 
     sub shiftrsw0() -> word {
         word q = -12345

examples/arithmetic/builtins.p8

@@ -1,5 +1,6 @@
 %import textio
 %import floats
+%import string
 %import syslib
 %import test_stack
 %zeropage basicsafe
@@ -8,7 +9,6 @@ main {
 
     sub start() {
         rotations()
-        strings()
         integers()
         floatingpoint()
 
@@ -256,82 +256,6 @@ main {
 
     }
 
-    sub strings() {
-        const uword ADDR = $8400
-        const uword ADDR2 = $8000
-
-        memset(ADDR2, 40*25, '*')
-        memset(ADDR2, 40, '1')
-        memset(ADDR2+24*40, 39, '2')
-        memsetw(ADDR2, 40*25/2, $3132)
-        memsetw(ADDR2, 20, $4142)
-        memsetw(ADDR2+24*40, 19, $4241)
-        memcopy(ADDR2, ADDR, 200)
-
-        str result = "?" *10
-        str s1 = "irmen"
-        str s2 = "hello"
-        str dots = "....."
-
-        ubyte ub
-        byte bb
-        ubyte zero=0
-
-        bb = strcmp(s1, s2)
-        txt.print_b(bb)
-        txt.chrout('\n')
-        bb = strcmp(s2, s1)
-        txt.print_b(bb)
-        txt.chrout('\n')
-        txt.print_ub(s1==s2)
-        txt.chrout('\n')
-        txt.print_ub(s1<s2)
-        txt.chrout('\n')
-        txt.print_ub(s1>s2)
-        txt.chrout('\n')
-        bb = zero+strcmp(s1,s2)*1+zero
-        txt.print_b(bb)
-        txt.chrout('\n')
-        bb = zero+strcmp(s2,s1)*1+zero
-        txt.print_b(bb)
-        txt.chrout('\n')
-
-        ub = strlen(s1)
-        txt.print_ub(ub)
-        txt.chrout('\n')
-        ub = zero+strlen(s1)*1+zero
-        txt.print_ub(ub)
-        txt.chrout('\n')
-
-        leftstr(s1, result, 3)
-        txt.print(result)
-        txt.chrout('\n')
-        leftstr(s1, result, len(s1))
-        txt.print(result)
-        txt.chrout('\n')
-        txt.chrout('\n')
-
-        result = "x"*8
-        rightstr(s2, result, 3)
-        txt.print(result)
-        txt.chrout('\n')
-        rightstr(s2, result, len(s1))
-        txt.print(result)
-        txt.chrout('\n')
-
-        result = "y"*10
-        substr(s2, result, 1, 3)
-        txt.print(result)
-        txt.chrout('\n')
-
-        void strcopy(s2, s1)
-        txt.print_ub(99+strcopy(s2,s1))
-        txt.chrout('\n')
-
-        test_stack.test()
-
-    }
-
     sub integers() {
         ubyte[]  ubarr = [1,2,3,4,5,0,4,3,2,1, 255, 255, 255]
         byte[]  barr = [1,2,3,4,5,-4,0,-3,2,1, -128, -128, -127]

examples/compilerperformance/perf.p8

@@ -6,6 +6,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %import perf2
 %import perf3
@@ -954,7 +955,7 @@ util {
     }
 
     sub print_right(ubyte width, uword string) {
-        repeat width - strlen(string) {
+        repeat width - string.length(string) {
             txt.chrout(' ')
         }
         txt.print(string)

examples/compilerperformance/perf10.p8

@@ -1,6 +1,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %option no_sysinit
 %zeropage basicsafe
@@ -944,7 +945,7 @@ util10 {
     }
 
     sub print_right(ubyte width, uword string) {
-        repeat width - strlen(string) {
+        repeat width - string.length(string) {
             txt.chrout(' ')
         }
         txt.print(string)

examples/compilerperformance/perf2.p8

@@ -1,6 +1,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %option no_sysinit
 %zeropage basicsafe
@@ -944,7 +945,7 @@ util2 {
     }
 
     sub print_right(ubyte width, uword string) {
-        repeat width - strlen(string) {
+        repeat width - string.length(string) {
             txt.chrout(' ')
         }
         txt.print(string)

examples/compilerperformance/perf3.p8

@@ -1,6 +1,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %option no_sysinit
 %zeropage basicsafe
@@ -944,7 +945,7 @@ util3 {
     }
 
     sub print_right(ubyte width, uword string) {
-        repeat width - strlen(string) {
+        repeat width - string.length(string) {
             txt.chrout(' ')
         }
         txt.print(string)

examples/compilerperformance/perf4.p8

@@ -1,6 +1,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %option no_sysinit
 %zeropage basicsafe
@@ -944,7 +945,7 @@ util4 {
     }
 
     sub print_right(ubyte width, uword string) {
-        repeat width - strlen(string) {
+        repeat width - string.length(string) {
             txt.chrout(' ')
         }
         txt.print(string)

examples/compilerperformance/perf5.p8

@@ -1,6 +1,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %option no_sysinit
 %zeropage basicsafe
@@ -944,7 +945,7 @@ util5 {
     }
 
     sub print_right(ubyte width, uword string) {
-        repeat width - strlen(string) {
+        repeat width - string.length(string) {
             txt.chrout(' ')
         }
         txt.print(string)

examples/compilerperformance/perf6.p8

@@ -1,6 +1,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %option no_sysinit
 %zeropage basicsafe
@@ -944,7 +945,7 @@ util6 {
     }
 
     sub print_right(ubyte width, uword string) {
-        repeat width - strlen(string) {
+        repeat width - string.length(string) {
             txt.chrout(' ')
         }
         txt.print(string)

examples/compilerperformance/perf7.p8

@@ -1,6 +1,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %option no_sysinit
 %zeropage basicsafe
@@ -944,7 +945,7 @@ util7 {
     }
 
     sub print_right(ubyte width, uword string) {
-        repeat width - strlen(string) {
+        repeat width - string.length(string) {
             txt.chrout(' ')
         }
         txt.print(string)

examples/compilerperformance/perf8.p8

@@ -1,6 +1,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %option no_sysinit
 %zeropage basicsafe
@@ -944,7 +945,7 @@ util8 {
     }
 
     sub print_right(ubyte width, uword string) {
-        repeat width - strlen(string) {
+        repeat width - string.length(string) {
             txt.chrout(' ')
         }
         txt.print(string)

examples/compilerperformance/perf9.p8

@@ -1,6 +1,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %option no_sysinit
 %zeropage basicsafe
@@ -944,7 +945,7 @@ util9 {
     }
 
     sub print_right(ubyte width, uword string) {
-        repeat width - strlen(string) {
+        repeat width - string.length(string) {
             txt.chrout(' ')
         }
         txt.print(string)

examples/cx16/assembler/assem.p8

@@ -1,6 +1,7 @@
 %target cx16
 %import test_stack
 %import textio
+%import string
 %zeropage basicsafe
 %option no_sysinit
 
@@ -61,7 +62,7 @@ textparse {
         }
 
         uword value = conv.any2uword(word_addrs[2])
-        if strcmp("*", word_addrs[0])==0 {
+        if word_addrs[0] == "*" {       ; TODO does this string compare work?
             program_counter = value
         } else {
             set_symbol(word_addrs[0], value)
@@ -96,7 +97,7 @@ textparse {
         }
 
         if label_ptr {
-            uword lastlabelchar = label_ptr + strlen(label_ptr)-1
+            uword lastlabelchar = label_ptr + string.length(label_ptr)-1
             if @(lastlabelchar) == ':'
                 @(lastlabelchar) = 0
             if instructions.match(label_ptr) {
@@ -346,7 +347,7 @@ textparse {
         }
         if changed {
             @(dest)=0
-            void strcopy(input_line2, src)
+            string.copy(input_line2, src)
         }
     }
 }

examples/cx16/imageviewer/imageviewer.p8

@@ -2,6 +2,7 @@
 %import gfx2
 %import textio
 %import diskio
+%import string
 %import koala_module
 %import iff_module
 %import pcx_module
@@ -14,7 +15,7 @@ main {
     sub start() {
         ; trick to check if we're running on sdcard or host system shared folder
         txt.print("\nimage viewer for commander x16\nformats supported: .iff, .pcx, .bmp, .koa (c64 koala)\n\n")
-        if strlen(diskio.status(8)) {
+        if string.length(diskio.status(8)) {
             txt.print("enter image file name or just enter for all on disk: ")
             ubyte i = txt.input_chars(diskio.filename)
             gfx2.screen_mode(1)    ; 320*240, 256c
@@ -54,7 +55,7 @@ main {
         ;txt.print(filenameptr)
         ;txt.chrout('\n')
         uword extension = filenameptr + rfind(filenameptr, '.')
-        if strcmp(extension, ".iff")==0 {
+        if extension == ".iff" {        ; TODO does this compare work?
             ;txt.print("loading ")
             ;txt.print("iff\n")
             if iff_module.show_image(filenameptr) {
@@ -70,7 +71,7 @@ main {
                 load_error(filenameptr)
             }
         }
-        else if strcmp(extension, ".pcx")==0 {
+        else if extension == ".pcx" {       ; TODO works?
             ;txt.print("loading ")
             ;txt.print("pcx\n")
             if pcx_module.show_image(filenameptr) {
@@ -79,7 +80,7 @@ main {
                 load_error(filenameptr)
             }
         }
-        else if strcmp(extension, ".koa")==0 {
+        else if extension == ".koa" {    ; TODO works?
             ;txt.print("loading ")
             ;txt.print("koala\n")
             if koala_module.show_image(filenameptr) {
@@ -88,7 +89,7 @@ main {
                 load_error(filenameptr)
             }
         }
-        else if strcmp(extension, ".bmp")==0 {
+        else if extension == ".bmp"  {   ; TODO works?
             ;txt.print("loading ")
             ;txt.print("bmp\n")
             if bmp_module.show_image(filenameptr) {
@@ -97,7 +98,7 @@ main {
                 load_error(filenameptr)
             }
         }
-;        else if strcmp(extension, ".ci")==0 {
+;        else if extension == ".ci" {
 ;;            txt.print("loading ")
 ;;            txt.print("ci\n")
 ;            if ci_module.show_image(filenameptr) {
@@ -117,12 +118,12 @@ main {
 
     sub extension_equals(uword stringptr, uword extensionptr) -> ubyte {
         ubyte ix = rfind(stringptr, '.')
-        return ix<255 and strcmp(stringptr+ix, extensionptr)==0
+        return ix<255 and string.compare(stringptr+ix, extensionptr)==0
     }
 
     sub rfind(uword stringptr, ubyte char) -> ubyte {
         ubyte i
-        for i in strlen(stringptr)-1 downto 0 {
+        for i in string.length(stringptr)-1 downto 0 {
             if @(stringptr+i)==char
                 return i
         }

examples/test.p8

@@ -1,11 +1,99 @@
 %import test_stack
 %import textio
+%import string
 %zeropage basicsafe
 %option no_sysinit
 
 main {
 
+    ; TODO: error when a parameter has the same name as an existing module/block/subroutine:  sub print_right(ubyte width, uword string) {
+
+
     sub start() {
+        str s1 = "irmen"
+        str s2 = "what"
+        str s3 = "irmen2"
+
+        s3[5] = 0
+
+        txt.print("length:\n")
+        txt.print_ub(len(s1))
+        txt.chrout('\n')
+        txt.print_ub(string.length(s1))
+
+        txt.print("\n\ncopy:\n")
+        txt.print(s3)
+        txt.chrout('\n')
+        s3 = s2
+        txt.print(s3)
+        txt.chrout('\n')
+        txt.print_ub(string.copy("new", s3))
+        txt.print(s3)
+
+        txt.print("\n\ncompare:\n")
+        txt.chrout('\n')
+        txt.print_ub(string.compare(s1, s2))
+        txt.chrout('\n')
+        txt.print_ub(string.compare(s2, s1))
+        txt.chrout('\n')
+        txt.print_ub(string.compare(s1, s3))
+        txt.chrout('\n')
+        txt.chrout('\n')
+        txt.print_ub(s1==s2)
+        txt.chrout('\n')
+        txt.print_ub(s1<s2)
+        txt.chrout('\n')
+        txt.print_ub(s1>s2)
+        txt.chrout('\n')
+
+        txt.print("\n\nleft:")
+        string.left(s2,2,s3)
+        txt.print(s3)
+        txt.chrout('\n')
+        txt.print("\n\nright:\n")
+        txt.print(s2)
+        txt.chrout('\n')
+        string.right(s2,2,s3)
+        txt.print(s3)
+        txt.chrout('\n')
+
+        txt.print("\n\nfind:\n")
+        txt.print(s1)
+        txt.chrout('\n')
+        uword found = string.find(s1, 'e')
+        txt.print_uwhex(found, 1)
+        if found
+            txt.print(found)
+        txt.chrout('\n')
+        found = string.find(s1, 'i')
+        txt.print_uwhex(found, 1)
+        if found
+            txt.print(found)
+        txt.chrout('\n')
+        found = string.find(s1, 'x')
+        txt.print_uwhex(found, 1)
+        if found
+            txt.print(found)
+        txt.chrout('\n')
+
+        txt.print("\n\nslice:\n")
+        string.slice(s1, 0, 5, s2)
+        txt.print(s2)
+        txt.chrout('\n')
+        string.slice(s1, 1, 4, s2)
+        txt.print(s2)
+        txt.chrout('\n')
+        string.slice(s1, 2, 2, s2)
+        txt.print(s2)
+        txt.chrout('\n')
+        string.slice(s1, 3, 2, s2)
+        txt.print(s2)
+        txt.chrout('\n')
+
+        test_stack.test()
+    }
+
+    sub start2 () {
         str[] binstrings = [
             "",
             "%",
@@ -151,16 +239,16 @@ main {
         }
 
 
-;        found = strfind("irmen de jong", ' ')
+;        found = string.find("irmen de jong", ' ')
 ;        txt.print_uwhex(found, 1)
 ;        txt.chrout('\n')
-;        found = strfind(" irmen-de-jong", ' ')
+;        found = string.find(" irmen-de-jong", ' ')
 ;        txt.print_uwhex(found, 1)
 ;        txt.chrout('\n')
-;        found = strfind("irmen-de-jong ", ' ')
+;        found = string.find("irmen-de-jong ", ' ')
 ;        txt.print_uwhex(found, 1)
 ;        txt.chrout('\n')
-;        found = strfind("irmen-de-jong", ' ')
+;        found = string.find("irmen-de-jong", ' ')
 ;        txt.print_uwhex(found, 1)
 ;        txt.chrout('\n')
 

examples/textelite.p8

@@ -1,6 +1,7 @@
 %import textio
 %import conv
 %import diskio
+%import string
 %import test_stack
 %option no_sysinit
 %zeropage basicsafe
@@ -943,11 +944,11 @@ util {
         return false
     }
 
-    sub print_right(ubyte width, uword string) {
+    sub print_right(ubyte width, uword s) {
-        repeat width - strlen(string) {
+        repeat width - string.length(s) {
             txt.chrout(' ')
         }
-        txt.print(string)
+        txt.print(s)
     }
 
     asmsub print_10s(uword value @AY) clobbers(A, X, Y) {