initial parser

.gitignore

@@ -0,0 +1,175 @@
+# Based on https://raw.githubusercontent.com/github/gitignore/main/Node.gitignore
+
+# Logs
+
+logs
+_.log
+npm-debug.log_
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Caches 
+
+.cache
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+
+report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
+
+# Runtime data
+
+pids
+_.pid
+_.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+
+lib-cov
+
+# Coverage directory used by tools like istanbul
+
+coverage
+*.lcov
+
+# nyc test coverage
+
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+
+bower_components
+
+# node-waf configuration
+
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+
+build/Release
+
+# Dependency directories
+
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+
+web_modules/
+
+# TypeScript cache
+
+*.tsbuildinfo
+
+# Optional npm cache directory
+
+.npm
+
+# Optional eslint cache
+
+.eslintcache
+
+# Optional stylelint cache
+
+.stylelintcache
+
+# Microbundle cache
+
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+
+.node_repl_history
+
+# Output of 'npm pack'
+
+*.tgz
+
+# Yarn Integrity file
+
+.yarn-integrity
+
+# dotenv environment variable files
+
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+
+.parcel-cache
+
+# Next.js build output
+
+.next
+out
+
+# Nuxt.js build / generate output
+
+.nuxt
+dist
+
+# Gatsby files
+
+# Comment in the public line in if your project uses Gatsby and not Next.js
+
+# https://nextjs.org/blog/next-9-1#public-directory-support
+
+# public
+
+# vuepress build output
+
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+
+.temp
+
+# Docusaurus cache and generated files
+
+.docusaurus
+
+# Serverless directories
+
+.serverless/
+
+# FuseBox cache
+
+.fusebox/
+
+# DynamoDB Local files
+
+.dynamodb/
+
+# TernJS port file
+
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+
+.vscode-test
+
+# yarn v2
+
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*
+
+# IntelliJ based IDEs
+.idea
+
+# Finder (MacOS) folder config
+.DS_Store

.prettierrc

@@ -0,0 +1,18 @@
+{
+  "arrowParens": "avoid",
+  "bracketSpacing": true,
+  "htmlWhitespaceSensitivity": "css",
+  "insertPragma": false,
+  "jsxBracketSameLine": false,
+  "jsxSingleQuote": true,
+  "printWidth": 80,
+  "proseWrap": "always",
+  "quoteProps": "as-needed",
+  "requirePragma": false,
+  "semi": true,
+  "singleQuote": true,
+  "tabWidth": 2,
+  "trailingComma": "all",
+  "useTabs": false,
+  "plugins": ["prettier-plugin-pegjs"]
+}

README.md

@@ -0,0 +1,2 @@
+An interpreter for the CPS intermediate representation as
+suggested in "Compiling with Continuations" by Appel.

package.json

@@ -0,0 +1,18 @@
+{
+  "name": "cps-interpreter",
+  "module": "index.ts",
+  "type": "module",
+  "devDependencies": {
+    "@types/bun": "latest"
+  },
+  "peerDependencies": {
+    "typescript": "^5.0.0"
+  },
+  "dependencies": {
+    "minimist": "^1.2.8",
+    "peggy": "^4.0.0",
+    "prettier": "^3.2.5",
+    "prettier-plugin-pegjs": "^2.0.2",
+    "ts-pegjs": "^4.2.1"
+  }
+}

src/args.ts

@@ -0,0 +1,11 @@
+const argv = require('minimist')(process.argv.slice(2));
+
+export type Args = {
+  devMode: boolean;
+  repl: boolean;
+};
+
+export const args: Args = {
+  repl: argv.repl ?? false,
+  devMode: argv.dev ?? false,
+};

src/index.ts

@@ -0,0 +1,63 @@
+import { args, type Args } from '@/args';
+import { join } from 'path';
+import { watch } from 'fs/promises';
+import { generateParser, GRAMMAR_FILE, GENERATED_PARSER } from '@/parser';
+import {
+  ConsoleTracingLogger,
+  type LogLevel,
+  type TracingLogger,
+} from '@/utils';
+import { evaluate } from '@/interpreter';
+
+const LOG_LEVELS: LogLevel[] = ['info', 'warn', 'error'];
+
+const devMode = async (logger: TracingLogger) => {
+  logger.info('Watching for changes in parser...');
+
+  const watcher = watch(import.meta.dir, { recursive: true });
+  for await (const event of watcher) {
+    if (event.filename?.endsWith(GRAMMAR_FILE)) {
+      const grammarFile = join(import.meta.dir, event.filename);
+      const outputFile = join(
+        import.meta.dir,
+        event.filename.replace(GRAMMAR_FILE, GENERATED_PARSER),
+      );
+      logger.info(
+        `Generating parser at Location=(${grammarFile}) to Source=(${outputFile})...`,
+      );
+      generateParser(grammarFile, outputFile);
+    }
+  }
+};
+
+const doRepl = async (prompt = '~> ') => {
+  process.stdout.write(prompt);
+
+  for await (const line of console) {
+    const result = await evaluate(line);
+    console.log(result);
+    break;
+  }
+
+  await doRepl(prompt);
+};
+
+export const main = async (args: Args) => {
+  if (args.devMode) {
+    LOG_LEVELS.push('debug');
+  }
+
+  const logger = new ConsoleTracingLogger('main', LOG_LEVELS);
+
+  if (args.devMode) {
+    logger.info('Starting in dev mode...');
+    await devMode(logger);
+  }
+
+  if (args.repl) {
+    logger.info('Starting REPL...');
+    logger.info('Welcome to the CPS interpreter!');
+  }
+};
+
+main(args);

src/interpreter/index.ts

@@ -0,0 +1 @@
+export const evaluate = async (ast: Program) => {};

src/parser/generate.ts

@@ -0,0 +1,17 @@
+import peggy from 'peggy';
+const tspegjs: any = require('ts-pegjs');
+
+export const GRAMMAR_FILE = 'grammar.pegjs';
+export const GENERATED_PARSER = 'parser.ts';
+
+export const generateParser = async (file: string, output: string) => {
+  const grammar = await Bun.file(file).text();
+
+  const parserSrc = peggy.generate(grammar, {
+    format: 'commonjs',
+    plugins: [tspegjs],
+    output: 'source',
+  });
+
+  await Bun.write(output, parserSrc);
+};

src/parser/grammar.pegjs

@@ -0,0 +1,364 @@
+Program
+  = exprs:(ContinuationExpression / _)* {
+      return exprs.filter(x => !Array.isArray(x));
+    }
+
+ContinuationExpression
+  = RecordExpression
+  / SelectExpression
+  / OffsetExpression
+  / ApplicationExpression
+  / FixExpression
+  / SwitchExpression
+  / PrimitiveOperationExpression
+
+SelectExpression
+  = SELECT
+    _?
+    LPAREN
+    _?
+    select:Integer
+    _?
+    COMMA
+    _?
+    val:Value
+    _?
+    COMMA
+    _?
+    bind:Identifier
+    _?
+    continuation:ContinuationExpression
+    _?
+    RPAREN { return { select, val, bind, continuation }; }
+
+OffsetExpression
+  = OFFSET
+    _?
+    LPAREN
+    _?
+    offset:Integer
+    _?
+    COMMA
+    _?
+    val:Value
+    _?
+    COMMA
+    _?
+    bind:Identifier
+    _?
+    continuation:ContinuationExpression
+    _?
+    RPAREN { return { offset, val, bind, continuation }; }
+
+IdentifierList
+  = LBRACKET
+    _?
+    identifiers:(ident:Identifier _? COMMA _?)*
+    _?
+    lastIdent:Identifier?
+    _?
+    RBRACKET {
+      return identifiers.length || lastIdent
+        ? [...identifiers.map(x => x.ident), lastIdent]
+        : [];
+    }
+
+ValueList
+  = LBRACKET
+    _?
+    values:(value:Value _? COMMA _?)*
+    _?
+    lastValue:Value?
+    _?
+    RBRACKET {
+      return values.length || lastValue
+        ? [...values.map(x => x.value), lastValue]
+        : [];
+    }
+
+SwitchExpression
+  = SWITCH
+    _?
+    LPAREN
+    _?
+    switchIndex:Value
+    _?
+    COMMA
+    _?
+    continuations:ContinuationList
+    _?
+    RPAREN { return { switchIndex, continuations }; }
+
+ApplicationExpression
+  = APP _? LPAREN _? fn:Value _? COMMA _? args:ValueList _? RPAREN {
+      return { fn, args };
+    }
+
+FixBinding
+  = LPAREN
+    _?
+    fn:Identifier
+    _?
+    COMMA
+    _?
+    args:IdentifierList
+    _?
+    COMMA
+    _?
+    continuation:ContinuationExpression
+    _?
+    RPAREN
+
+FixBindingList
+  = LBRACKET
+    _
+    bindings:(binding:FixBinding _? COMMA _?)*
+    _?
+    lastBinding:FixBinding?
+    _?
+    RBRACKET {
+      return bindings.length || lastBinding
+        ? [...bindings.map(x => x.binding), lastBinding]
+        : [];
+    }
+
+FixExpression
+  = FIX
+    _?
+    LPAREN
+    _?
+    fixBindings:FixBindingList
+    _?
+    COMMA
+    _?
+    continuation:ContinuationExpression
+    _?
+    RPAREN { return { fixBindings, continuation }; }
+
+ContinuationList
+  = LBRACKET
+    _?
+    continuations:(continuation:ContinuationExpression _? COMMA _?)*
+    _?
+    lastContinuation:ContinuationExpression?
+    _?
+    RBRACKET {
+      return lastContinuation || continuations.length
+        ? [...continuations.map(x => x.continuation), lastContinuation]
+        : [];
+    }
+
+PrimitiveOperationExpression
+  = PRIMOP
+    _?
+    LPAREN
+    _?
+    opr:PrimitiveOperation
+    _?
+    COMMA
+    _?
+    operands:ValueList
+    _?
+    COMMA
+    _?
+    resultBindings:IdentifierList
+    _?
+    COMMA
+    _?
+    continuations:ContinuationList
+    _?
+    RPAREN { return { opr, operands, resultBindings, continuations }; }
+
+RecordExpressionTuple
+  = LPAREN
+    _?
+    variable:VarStatement
+    _?
+    COMMA
+    _?
+    offset:OffsetStatement
+    _?
+    RPAREN { return { variable, offset }; }
+
+RecordExpressionTupleList
+  = LBRACKET
+    _?
+    records:(record:RecordExpressionTuple _? COMMA _?)*
+    _?
+    lastRecord:RecordExpressionTuple?
+    _?
+    RBRACKET {
+      return records.length || lastRecord
+        ? [...records.map(x => x.record), lastRecord]
+        : [];
+    }
+
+RecordExpression
+  = RECORD
+    _?
+    LPAREN
+    _?
+    records:RecordExpressionTupleList
+    _?
+    COMMA
+    _?
+    address:Literal
+    _?
+    COMMA
+    _?
+    body:ContinuationExpression
+    _?
+    RPAREN {
+      return {
+        records,
+        address,
+        body,
+      };
+    }
+
+Value
+  = VarStatement
+  / LabelStatement
+  / IntStatement
+  / RealStatement
+  / StringStatement
+
+VarStatement = VAR _ ident:Identifier { return ident; }
+
+LabelStatement = LABEL _ ident:Identifier { return ident; }
+
+IntStatement = INT _ int:Integer { return int; }
+
+RealStatement = REAL _ real:Real { return real; }
+
+StringStatement = STRING _ string:QuotedString { return string; }
+
+AccessStatement
+  = OffsetStatement
+  / SelectStatement
+
+OffsetStatement = OFFP _ offset:Integer { return offset; }
+
+SelectStatement = SELP _ offset:Integer { return offset; }
+
+Identifier
+  = name:([A-Za-z] (LETTER / DIGIT / SAFE_SYMBOL)*) {
+      return { name: name[0] + name[1].join('') };
+    }
+
+PrimitiveOperation
+  = ArithmeticOperation
+  / ComparisonOperation
+  / BitOperation
+  / StoreOperation
+
+StoreOperation
+  = STORE
+  / UPDATE
+  / MAKEREF
+  / MAKEREFUNBOXED
+  / UNBOXED_UPDATE
+  / BOXED
+  / SUBSCRIPT
+
+ArithmeticOperation
+  = "+"
+  / "-"
+  / "/"
+  / "*"
+  / "**"
+
+BitOperation
+  = ">>"
+  / "<<"
+  / "~"
+  / "^"
+
+ComparisonOperation
+  = "=="
+  / "<="
+  / ">="
+  / "!="
+  / "!"
+  / ">"
+  / "<"
+
+Integer = digits:[0-9]+ !"." { return parseInt(digits.join(''), 10); }
+
+QuotedString
+  = "'" content:[^']* "'" { return content.join(''); }
+  / "\"" content:[^"]* "\"" { return content.join(''); }
+
+Real
+  = value:("-"? [0-9]+ "." [0-9]+) {
+      return parseFloat(
+        value.map(x => (Array.isArray(x) ? x.join('') : x)).join(''),
+      );
+    }
+
+Literal
+  = Real
+  / QuotedString
+  / Integer
+
+OFFSET = "OFFSET"
+
+OFFP = "OFFp"
+
+SELP = "SELp"
+
+VAR = "VAR"
+
+INT = "INT"
+
+REAL = "REAL"
+
+STRING = "STRING"
+
+APP = "APP"
+
+RECORD = "RECORD"
+
+SELECT = "SELECT"
+
+FIX = "FIX"
+
+SWITCH = "SWITCH"
+
+PRIMOP = "PRIMOP"
+
+LABEL = "LABEL"
+
+STORE = "store"
+
+UPDATE = "update"
+
+MAKEREF = "makeref"
+
+MAKEREFUNBOXED = "makerefunboxed"
+
+UNBOXED_UPDATE = "unboxedupdate"
+
+SUBSCRIPT = "subscript"
+
+BOXED = "boxed"
+
+LETTER = [A-Za-z]
+
+SAFE_SYMBOL = "_"
+
+DIGIT = [0-9]
+
+LBRACKET = "["
+
+RBRACKET = "]"
+
+COMMA = ","
+
+EQUALS = "="
+
+LPAREN = "("
+
+RPAREN = ")"
+
+_ = (" " / "\n" / "\t" / "\r\n")+

src/parser/index.ts

@@ -0,0 +1,6 @@
+export * from './generate';
+export * from './parser';
+import * as peggy from './parser';
+
+export const peggyParse = (source: string): peggy.FunctionDefinition[] =>
+  peggy.parse(source);

src/utils/exception.ts

@@ -0,0 +1 @@
+export class NotImplementedException extends Error {}

src/utils/index.ts

@@ -0,0 +1,2 @@
+export * from './logger';
+export * from './exception';

src/utils/logger.ts

@@ -0,0 +1,51 @@
+export interface TracingLogger {
+  info(log: string): void;
+  warn(log: string): void;
+  error(log: string): void;
+  debug(log: string): void;
+
+  createChild(prefix: string): TracingLogger;
+}
+
+export type LogLevel = 'debug' | 'info' | 'warn' | 'error';
+
+export class ConsoleTracingLogger implements TracingLogger {
+  protected prefix: string;
+  private levels: LogLevel[];
+
+  constructor(prefix: string, levels: LogLevel[] = ['warn', 'error']) {
+    this.prefix = prefix;
+    this.levels = levels;
+  }
+
+  private makePrefix(level: LogLevel): string {
+    return `[${new Date().toISOString()}] ${level} (${this.prefix}) > `;
+  }
+
+  public info(log: string) {
+    if (this.levels.includes('info'))
+      console.log(this.makePrefix('info') + log);
+  }
+
+  public warn(log: string) {
+    if (this.levels.includes('warn'))
+      console.warn(this.makePrefix('warn') + log);
+  }
+
+  public error(log: string) {
+    if (this.levels.includes('error'))
+      console.error(this.makePrefix('error') + log);
+  }
+
+  public debug(log: string) {
+    if (this.levels.includes('debug'))
+      console.debug(this.makePrefix('debug') + log);
+  }
+
+  public createChild(prefix: string, levels?: LogLevel[]) {
+    return new ConsoleTracingLogger(
+      `${this.prefix} -> ${prefix}`,
+      levels ?? this.levels,
+    );
+  }
+}

tsconfig.json

@@ -0,0 +1,27 @@
+{
+  "compilerOptions": {
+    "lib": ["ESNext"],
+    "target": "ESNext",
+    "module": "ESNext",
+    "moduleDetection": "force",
+    "jsx": "react-jsx",
+    "allowJs": true,
+
+    /* Bundler mode */
+    "moduleResolution": "bundler",
+    "allowImportingTsExtensions": true,
+    "verbatimModuleSyntax": true,
+    "noEmit": true,
+
+    /* Linting */
+    "skipLibCheck": true,
+    "strict": true,
+    "noFallthroughCasesInSwitch": true,
+    "forceConsistentCasingInFileNames": true,
+
+    "paths": {
+      "@/*": ["./src/*"],
+      "@t/*": ["./test/*"]
+    }
+  }
+}