mirror of
https://github.com/sehugg/8bitworkshop.git
synced 2026-03-11 13:41:43 +00:00
6502 stream parser -> Lezer grammar parser
This commit is contained in:
Fred Sauer
16
Makefile
16
Makefile
@@ -1,8 +1,21 @@
|
||||
|
||||
TSC=./node_modules/typescript/bin/tsc --build
|
||||
LEZER=./node_modules/.bin/lezer-generator
|
||||
TMP=./tmp/dist
|
||||
|
||||
buildtsc:
|
||||
buildgrammars:
|
||||
mkdir -p gen/parser
|
||||
$(LEZER) src/parser/lang-6502.grammar -o gen/parser/lang-6502.grammar.js
|
||||
|
||||
watchgrammars:
|
||||
while true; do \
|
||||
if [ src/parser/lang-6502.grammar -nt gen/parser/lang-6502.grammar.js ]; then \
|
||||
make buildgrammars; \
|
||||
fi; \
|
||||
sleep 1; \
|
||||
done
|
||||
|
||||
buildtsc: buildgrammars
|
||||
npm run esbuild-clean
|
||||
$(TSC) tsconfig.json
|
||||
npm run esbuild
|
||||
@@ -30,6 +43,7 @@ tsweb:
|
||||
npm run esbuild-clean
|
||||
(ip addr || ifconfig) | grep inet
|
||||
$(TSC) -w --preserveWatchOutput &
|
||||
make watchgrammars &
|
||||
sleep 9999999 | npm run esbuild-worker -- --watch &
|
||||
sleep 9999999 | npm run esbuild-ui -- --watch &
|
||||
python3 scripts/serveit.py 2>> /dev/null #http.out
|
||||
|
||||
162
src/parser/lang-6502.grammar
Normal file
162
src/parser/lang-6502.grammar
Normal file
@@ -0,0 +1,162 @@
|
||||
@top Program { Line* }
|
||||
|
||||
@skip { space | Comment }
|
||||
|
||||
Line {
|
||||
Label? Statement? eol
|
||||
}
|
||||
|
||||
Statement {
|
||||
Instruction |
|
||||
Directive |
|
||||
MacroDef |
|
||||
MacEnd |
|
||||
ControlOp |
|
||||
ErrorOp
|
||||
}
|
||||
|
||||
Label { Identifier ":" | Identifier }
|
||||
|
||||
Instruction {
|
||||
Opcode Operand?
|
||||
}
|
||||
|
||||
Register {
|
||||
@specialize<Identifier, "X" | "Y" | "A" | "x" | "y" | "a">
|
||||
}
|
||||
|
||||
Directive {
|
||||
PseudoOp (Expression)*
|
||||
}
|
||||
|
||||
PseudoOp {
|
||||
@specialize<Identifier,
|
||||
"ORG" | "EQU" | "END" | "org" | "equ" | "end" |
|
||||
"ds" | "ds.b" | "ds.w" | "dc" | "dc.b" | "dc.w" | "seg" | "seg.u" |
|
||||
"subroutine" |
|
||||
"echo" | "repeat" | "repend" | "set" |
|
||||
"processor" |
|
||||
".WORD" | ".word" | ".BYTE" | ".byte" | ".END" | ".end"
|
||||
>
|
||||
}
|
||||
|
||||
Mac { @specialize<Identifier, "mac"> }
|
||||
MacEnd { @specialize<Identifier, "endm"> }
|
||||
|
||||
ControlOp { @specialize<Identifier, "if" | "else" | "endif"> }
|
||||
ErrorOp { @specialize<Identifier, "err"> }
|
||||
|
||||
MacroDef {
|
||||
Mac Identifier
|
||||
}
|
||||
|
||||
CurrentAddress {
|
||||
@specialize<Identifier, ".">
|
||||
}
|
||||
|
||||
Opcode {
|
||||
@specialize<Identifier,
|
||||
"ADC" | "AND" | "ASL" | "BCC" | "BCS" | "BEQ" | "BIT" | "BMI" |
|
||||
"BNE" | "BPL" | "BRK" | "BVC" | "BVS" | "CLC" | "CLD" | "CLI" |
|
||||
"CLV" | "CMP" | "CPX" | "CPY" | "DEC" | "DEX" | "DEY" | "EOR" |
|
||||
"INC" | "INX" | "INY" | "JMP" | "JSR" | "LDA" | "LDX" | "LDY" |
|
||||
"LSR" | "NOP" | "ORA" | "PHA" | "PHP" | "PLA" | "PLP" | "ROL" |
|
||||
"ROR" | "RTI" | "RTS" | "SBC" | "SEC" | "SED" | "SEI" | "STA" |
|
||||
"STX" | "STY" | "TAX" | "TAY" | "TSX" | "TXA" | "TXS" | "TYA" |
|
||||
"adc" | "and" | "asl" | "bcc" | "bcs" | "beq" | "bit" | "bmi" |
|
||||
"bne" | "bpl" | "brk" | "bvc" | "bvs" | "clc" | "cld" | "cli" |
|
||||
"clv" | "cmp" | "cpx" | "cpy" | "dec" | "dex" | "dey" | "eor" |
|
||||
"inc" | "inx" | "iny" | "jmp" | "jsr" | "lda" | "ldx" | "ldy" |
|
||||
"lsr" | "nop" | "ora" | "pha" | "php" | "pla" | "plp" | "rol" |
|
||||
"ror" | "rti" | "rts" | "sbc" | "sec" | "sed" | "sei" | "sta" |
|
||||
"stx" | "sty" | "tax" | "tay" | "tsx" | "txa" | "txs" | "tya"
|
||||
>
|
||||
}
|
||||
|
||||
Expression {
|
||||
Expression !logic LogicOp Expression |
|
||||
Expression !bit BitOp Expression |
|
||||
Expression !compare (CompareOp | BinaryLt | BinaryGt) Expression |
|
||||
Expression !term (ArithOp | Plus | Minus | Percent) Expression |
|
||||
UnaryExpression |
|
||||
Value |
|
||||
"(" Expression ")"
|
||||
}
|
||||
|
||||
UnaryExpression {
|
||||
(Plus | Minus | Not | Tilde | UnaryLt | UnaryGt) Expression
|
||||
}
|
||||
|
||||
BinaryLt { lt !bin }
|
||||
BinaryGt { gt !bin }
|
||||
UnaryLt { lt !un }
|
||||
UnaryGt { gt !un }
|
||||
|
||||
Value {
|
||||
Number |
|
||||
Identifier |
|
||||
CurrentAddress |
|
||||
String |
|
||||
Char
|
||||
}
|
||||
|
||||
Operand {
|
||||
"#" Expression |
|
||||
"(" Expression Comma Register ")" |
|
||||
Expression (Comma Register)? |
|
||||
Register
|
||||
}
|
||||
|
||||
@tokens {
|
||||
Identifier { $[a-zA-Z_.] $[a-zA-Z0-9_.]* }
|
||||
|
||||
Number {
|
||||
"$" $[0-9a-fA-F]+ |
|
||||
"%" $[01]+ |
|
||||
$[0-9]+
|
||||
}
|
||||
|
||||
String { '"' (!["\\\n] | "\\" _)* '"' }
|
||||
|
||||
Char { "'" ![\n] "'"? }
|
||||
|
||||
Comment { ";" ![\n]* }
|
||||
|
||||
space { $[ \t]+ }
|
||||
eol { $[\n\r]+ }
|
||||
|
||||
Comma { "," }
|
||||
"#"
|
||||
"(" ")"
|
||||
|
||||
ArithOp { "*" | "/" }
|
||||
Percent { "%" }
|
||||
Plus { "+" }
|
||||
Minus { "-" }
|
||||
|
||||
BitOp { "&" | "|" | "^" | "<<" | ">>" }
|
||||
Tilde { "~" }
|
||||
|
||||
LogicOp { "&&" | "||" }
|
||||
Not { "!" }
|
||||
|
||||
CompareOp { "==" | "!=" | "<=" | ">=" }
|
||||
lt { "<" }
|
||||
gt { ">" }
|
||||
|
||||
@precedence { String, Char, Number, Percent, Identifier }
|
||||
}
|
||||
|
||||
@precedence {
|
||||
un,
|
||||
term @left,
|
||||
compare @left,
|
||||
bit @left,
|
||||
logic @left,
|
||||
bin @left,
|
||||
PseudoOp,
|
||||
Opcode,
|
||||
Label
|
||||
}
|
||||
|
||||
@detectDelim
|
||||
@@ -1,96 +1,55 @@
|
||||
// CodeMirror 6 language support for 6502 assembly
|
||||
// Migrated from CodeMirror 5 mode
|
||||
// Original copyright (c) by Marijn Haverbeke and others
|
||||
// Distributed under an MIT license: https://codemirror.net/5/LICENSE
|
||||
import { LRLanguage, LanguageSupport, delimitedIndent, foldInside, foldNodeProp, indentNodeProp } from "@codemirror/language"
|
||||
import { styleTags, tags as t } from "@lezer/highlight"
|
||||
import { parser } from "../../gen/parser/lang-6502.grammar.js"
|
||||
|
||||
import { StreamLanguage, StreamParser } from "@codemirror/language";
|
||||
import { LanguageSupport } from "@codemirror/language";
|
||||
|
||||
// TODO: Migrate to CodeMirror 6 Lezer parser.
|
||||
const asm6502Parser: StreamParser<{ context: number }> = {
|
||||
startState() {
|
||||
return {
|
||||
context: 0
|
||||
};
|
||||
},
|
||||
|
||||
token(stream, state) {
|
||||
// Labels at start of line
|
||||
if (!stream.column()) {
|
||||
state.context = 0;
|
||||
if (stream.eatWhile(/[\w.]/))
|
||||
return 'labelName';
|
||||
export const Lezer6502: LRLanguage = LRLanguage.define({
|
||||
parser: parser.configure({
|
||||
props: [
|
||||
indentNodeProp.add({
|
||||
Application: delimitedIndent({ closing: ")", align: false })
|
||||
}),
|
||||
foldNodeProp.add({
|
||||
Application: foldInside
|
||||
}),
|
||||
styleTags({
|
||||
Identifier: t.variableName,
|
||||
CurrentAddress: t.self,
|
||||
PseudoOp: t.definition(t.variableName),
|
||||
Opcode: t.keyword,
|
||||
Label: t.labelName,
|
||||
String: t.string,
|
||||
Char: t.number,
|
||||
Number: t.number,
|
||||
Register: t.typeName,
|
||||
Comment: t.lineComment,
|
||||
ArithOp: t.arithmeticOperator,
|
||||
Plus: t.arithmeticOperator,
|
||||
Minus: t.arithmeticOperator,
|
||||
Percent: t.arithmeticOperator,
|
||||
BitOp: t.bitwiseOperator,
|
||||
Tilde: t.bitwiseOperator,
|
||||
LogicOp: t.logicOperator,
|
||||
Not: t.logicOperator,
|
||||
CompareOp: t.compareOperator,
|
||||
BinaryLt: t.compareOperator,
|
||||
BinaryGt: t.compareOperator,
|
||||
UnaryLt: t.arithmeticOperator,
|
||||
UnaryGt: t.arithmeticOperator,
|
||||
Mac: t.definitionKeyword,
|
||||
MacEnd: t.definitionKeyword,
|
||||
"MacroDef/Identifier": t.macroName,
|
||||
ControlOp: t.controlKeyword,
|
||||
ErrorOp: t.keyword,
|
||||
Comma: t.separator,
|
||||
"( )": t.paren
|
||||
})
|
||||
]
|
||||
}),
|
||||
languageData: {
|
||||
commentTokens: { line: ";" }
|
||||
}
|
||||
})
|
||||
|
||||
if (stream.eatSpace())
|
||||
return null;
|
||||
|
||||
var w;
|
||||
if (stream.eatWhile(/\w/)) {
|
||||
w = stream.current();
|
||||
var cur = w.toLowerCase();
|
||||
|
||||
// Check for directives
|
||||
var style = directives.get(cur);
|
||||
if (style)
|
||||
return style;
|
||||
|
||||
// Check for opcodes (3-letter mnemonics)
|
||||
if (opcodes.test(w)) {
|
||||
state.context = 4;
|
||||
return 'keyword';
|
||||
} else if (state.context == 4 && numbers.test(w)) {
|
||||
return 'number';
|
||||
} else if (stream.match(numbers)) {
|
||||
return 'number';
|
||||
} else {
|
||||
return null;
|
||||
}
|
||||
} else if (stream.eat(';')) {
|
||||
stream.skipToEnd();
|
||||
return 'comment';
|
||||
} else if (stream.eat('"')) {
|
||||
while (w = stream.next()) {
|
||||
if (w == '"')
|
||||
break;
|
||||
|
||||
if (w == '\\')
|
||||
stream.next();
|
||||
}
|
||||
return 'string';
|
||||
} else if (stream.eat('\'')) {
|
||||
if (stream.match(/\\?.'/) || stream.match(/\\?.'/))
|
||||
return 'number';
|
||||
} else if (stream.eat('$') || stream.eat('#')) {
|
||||
if (stream.eatWhile(/[^;]/i))
|
||||
return 'number';
|
||||
} else if (stream.eat('%')) {
|
||||
if (stream.eatWhile(/[01]/))
|
||||
return 'number';
|
||||
} else {
|
||||
stream.next();
|
||||
}
|
||||
return null;
|
||||
}
|
||||
};
|
||||
|
||||
// Directive keywords
|
||||
const directives_list = [
|
||||
'processor',
|
||||
'byte', 'word', 'long',
|
||||
'include', 'seg', 'dc', 'ds', 'dv', 'hex', 'err', 'org', 'rorg', 'echo', 'rend',
|
||||
'align', 'subroutine', 'equ', 'eqm', 'set', 'mac', 'endm', 'mexit', 'ifconst',
|
||||
'ifnconst', 'if', 'else', 'endif', 'eif', 'repeat', 'repend'
|
||||
];
|
||||
const directives = new Map<string, string>();
|
||||
directives_list.forEach(function (s) { directives.set(s, 'keyword'); });
|
||||
|
||||
const opcodes = /^[a-z][a-z][a-z]\b/i;
|
||||
const numbers = /^([\da-f]+h|[0-7]+o|[01]+b|\d+d?)\b/i;
|
||||
|
||||
/**
|
||||
* Language support for 6502 assembly language
|
||||
*/
|
||||
export function asm6502(): LanguageSupport {
|
||||
return new LanguageSupport(StreamLanguage.define(asm6502Parser));
|
||||
return new LanguageSupport(Lezer6502)
|
||||
}
|
||||
|
||||
40
test/parsers/testparser6502.js
Normal file
40
test/parsers/testparser6502.js
Normal file
@@ -0,0 +1,40 @@
|
||||
|
||||
const assert = require('assert');
|
||||
const { EditorState } = require("@codemirror/state");
|
||||
const { syntaxTree } = require("@codemirror/language");
|
||||
const { asm6502 } = require("../../gen/parser/lang-6502.js");
|
||||
|
||||
|
||||
describe('6502 Parser', function () {
|
||||
|
||||
it('Should parse basic instructions', function () {
|
||||
const code = `
|
||||
lda #$00
|
||||
sta $1234
|
||||
rts
|
||||
`;
|
||||
|
||||
// Create an editor state with the new parser
|
||||
const state = EditorState.create({
|
||||
doc: code,
|
||||
extensions: [asm6502()]
|
||||
});
|
||||
|
||||
// Check if the tree is available (basic check that parser didn't crash)
|
||||
// In a real environment we might traverse the tree to check specific nodes
|
||||
// but here we just want to ensure it instantiates and runs without throwing.
|
||||
assert.ok(syntaxTree(state), "Syntax tree should be generated");
|
||||
});
|
||||
|
||||
it('Should handle labels', function () {
|
||||
const code = `
|
||||
start:
|
||||
jmp start
|
||||
`;
|
||||
const state = EditorState.create({
|
||||
doc: code,
|
||||
extensions: [asm6502()]
|
||||
});
|
||||
assert.ok(syntaxTree(state), "Syntax tree should be generated");
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user