Mercurial > hg > index.cgi
changeset 56:f741bb544a04
Clean up labels in tokenization routine
| author | William Astle <lost@l-w.ca> |
|---|---|
| date | Thu, 22 Dec 2022 23:44:25 -0700 |
| parents | 1568fa902257 |
| children | 6a4c342ac12b |
| files | src/lwbasic.s |
| diffstat | 1 files changed, 66 insertions(+), 68 deletions(-) [+] |
line wrap: on
line diff
--- a/src/lwbasic.s Thu Dec 22 23:08:49 2022 -0700 +++ b/src/lwbasic.s Thu Dec 22 23:44:25 2022 -0700 @@ -1498,55 +1498,53 @@ ldy #tokebuff ; point to destination buffer pshs y ; set return value tokenize0 lda ,x+ ; get input character - bne tokenize1 ; brif not end of input -tokenize0a sta ,y+ ; blank out final byte in result -tokenize0b tfr y,d ; get end address to accumulator + bne tokenize3 ; brif not end of input +tokenize1 sta ,y+ ; blank out final byte in result +tokenize2 tfr y,d ; get end address to accumulator subd #tokebuff ; subtract out start; gives length of result puls x,pc ; set return pointer and return -tokenize1 tst tok_skipkw ; are we in the middle of a "not token"? - beq tokenize3a ; brif not +tokenize3 tst tok_skipkw ; are we in the middle of a "not token"? + beq tokenize6 ; brif not jsr setcifalpha ; is it alpha - bcs tokenize2 ; brif so - store it and continue + bcs tokenize4 ; brif so - store it and continue jsr setcifdigit ; is it numeric? - bcc tokenize3 ; brif not -tokenize2 sta ,y+ ; save output character + bcc tokenize5 ; brif not +tokenize4 sta ,y+ ; save output character bra tokenize0 ; check for another -tokenize3 clr tok_skipkw ; clear the "not token" flag -tokenize3a cmpa #'" ; is it a string? - bne tokenize5 ; brif not +tokenize5 clr tok_skipkw ; clear the "not token" flag +tokenize6 cmpa #'" ; is it a string? + bne tokenize8 ; brif not sta ,y+ ; save string delimiter -tokenize4 lda ,x+ ; get input character - beq tokenize0a ; brif end of input +tokenize7 lda ,x+ ; get input character + beq tokenize1 ; brif end of input sta ,y+ ; save it in output cmpa #'" ; end of string? - bne tokenize4 ; brif not + bne tokenize7 ; brif not bra tokenize0 ; brif -tokenize5 cmpa #': ; end of statement? - bne tokenize6 ; brif not +tokenize8 cmpa #': ; end of statement? + bne tokenize9 ; brif not clr tok_skipdt ; reset "in data" flag - bra tokenize2 ; stash it and continue -tokenize6 cmpa #0x20 ; is it a space? - beq tokenize2 ; brif so - stash it unmodified + bra tokenize4 ; stash it and continue +tokenize9 cmpa #0x20 ; is it a space? + beq tokenize4 ; brif so - stash it unmodified tst tok_skipdt ; are we "in data"? - bne tokenize2 ; brif so - don't tokenize it + bne tokenize4 ; brif so - don't tokenize it cmpa #'? ; PRINT shortcut? - bne tokenize6a ; brif not + bne tokenize10 ; brif not lda #tok_print ; load token for PRINT - bra tokenize2 ; move stash it and move on -tokenize6a cmpa #'' ; ' shortcut for remark? - bne tokenize9 ; brif not + bra tokenize4 ; move stash it and move on +tokenize10 cmpa #'' ; ' shortcut for remark? + bne tokenize12 ; brif not ldd #':*256+tok_apos ; put token for ' and an implied colon std ,y++ ; stash it -tokenize8 lda ,x+ ; fetch byte from input +tokenize11 lda ,x+ ; fetch byte from input sta ,y+ ; stash in output - bne tokenize8 ; brif not end of input - bra tokenize0b ; go finish up -tokenize9 jsr setcifdigit ; is it a digit? - bcs tokenize2 ; brif so - pass it through + bne tokenize11 ; brif not end of input + bra tokenize2 ; go finish up +tokenize12 jsr setcifdigit ; is it a digit? + bcs tokenize4 ; brif so - pass it through tsta ; is the high bit set? bmi tokenize0 ; ignore it if so - -; do longest match dictionary lookup here ldu #primarydict ; point to keyword table leax -1,x ; back up input to start of potential token clr tok_kwtype ; set secondary table flag to primary table @@ -1554,69 +1552,69 @@ clr tok_kwmatch+1 clr tok_kwmatchl ; set length matched pshs x ; save start of input token -tokenize10x clr tok_kwnum ; clear keyword number -tokenize10 ldb ,u ; are we at the end of the table? - bne tokenize11 ; brif not +tokenize13 clr tok_kwnum ; clear keyword number +tokenize14 ldb ,u ; are we at the end of the table? + bne tokenize16 ; brif not ldu #secondarydict ; point to secondary token dictionary com tok_kwtype ; flip to secondary token flag - bne tokenize10x ; brif we haven't already done the secondaries + bne tokenize13 ; brif we haven't already done the secondaries puls x ; get back input pointer ldb tok_kwmatchl ; get length of best match - beq tokenize10y ; brif we don't have a match + beq tokenize15 ; brif we don't have a match abx ; move input pointer past matched token ldd tok_kwmatch ; get matched token number tsta ; is it a primary? - beq tokenize17 ; brif so - bra tokenize16 ; go stash two byte token -tokenize10y com tok_skipkw ; set "not token flag" + beq tokenize24 ; brif so + bra tokenize23 ; go stash two byte token +tokenize15 com tok_skipkw ; set "not token flag" lda ,x+ ; get character - bra tokenize2 ; stash it and continue -tokenize11 ldx ,s ; get back start of input token + bra tokenize4 ; stash it and continue +tokenize16 ldx ,s ; get back start of input token clra ; initalize match length counter -tokenize12 inca ; bump length counter +tokenize17 inca ; bump length counter ldb ,x+ ; get input character cmpb #'z ; is it above lower case Z? - bhi tokenize13 ; brif so + bhi tokenize18 ; brif so cmpb #'a ; is it below lower case A? - blo tokenize13 ; brif so + blo tokenize18 ; brif so subb #0x20 ; convert to upper case -tokenize13 subb ,u+ ; does it match? - beq tokenize12 ; brif so - check another +tokenize18 subb ,u+ ; does it match? + beq tokenize17 ; brif so - check another cmpb #0x80 ; did it match with high bit set? - beq tokenize15 ; brif so - exact match + beq tokenize21 ; brif so - exact match leau -1,u ; back up to current test character -tokenize14 ldb ,u+ ; end of token? - bpl tokenize14 ; brif not -tokenize14a inc tok_kwnum ; bump token counter - bra tokenize10 ; go check another one -tokenize15 cmpa tok_kwmatchl ; is it a longer match? - bls tokenize14a ; brif not, ignore it +tokenize19 ldb ,u+ ; end of token? + bpl tokenize19 ; brif not +tokenize20 inc tok_kwnum ; bump token counter + bra tokenize14 ; go check another one +tokenize21 cmpa tok_kwmatchl ; is it a longer match? + bls tokenize20 ; brif not, ignore it sta tok_kwmatchl ; save new match length ldd tok_kwtype ; get the matched token count orb #0x80 ; set token flag std tok_kwmatch ; save matched token - bra tokenize14a ; keep looking through the tables -tokenize18 lda #': ; for putting implied colons in -tokenize16 std ,y++ ; put output into buffer + bra tokenize20 ; keep looking through the tables +tokenize22 lda #': ; for putting implied colons in +tokenize23 std ,y++ ; put output into buffer jmp tokenize0 ; go handle more input -tokenize17 cmpb #tok_else ; is it ELSE? - beq tokenize18 ; brif so - stash it with colon +tokenize24 cmpb #tok_else ; is it ELSE? + beq tokenize22 ; brif so - stash it with colon cmpb #tok_data ; is it DATA? - bne tokenize18a ; brif not + bne tokenize26 ; brif not stb tok_skipdt ; set "in data" flag -tokenize20 stb ,y+ ; stash token +tokenize25 stb ,y+ ; stash token jmp tokenize0 ; go handle more -tokenize18a cmpb #tok_rem ; is it REM? - beq tokenize19 ; brif so +tokenize26 cmpb #tok_rem ; is it REM? + beq tokenize28 ; brif so cmpb #tok_apos ; apostrophe REM? - bne tokenize20 ; brif not - stash token and continue + bne tokenize25 ; brif not - stash token and continue lda #': ; stash the implied colon sta ,y+ - bra tokenize19 -tokenize19a ldb ,x+ ; fetch next input character -tokenize19 stb ,y+ ; stash the character - bne tokenize19a ; brif not end of input - do another - jmp tokenize0b ; stash end of buffer and handle cleanup + bra tokenize28 +tokenize27 ldb ,x+ ; fetch next input character +tokenize28 stb ,y+ ; stash the character + bne tokenize27 ; brif not end of input - do another + jmp tokenize2 ; stash end of buffer and handle cleanup ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; ; Keyword dictionaries and jump tables. These are defined by several macros which ensure that each command or function ; entry has an associated jump table entry. These macros are: