speckl/compiler/dist/parser.js
Scott Scoble 898e2e53ae fix(compiler): protect object literal identifiers from this. prefix in rewriteExpr
Object spread expressions like { ...t, pending: false } were getting
spurious this. prefix applied to keys (this.pending: false), causing
3 tsc errors (TS1005: ':' expected). Fix: extract object literals
containing spread before Step 3 identifier rewriting, then restore.

Results: TigerBeetle TS errors reduced to known record-type issues (eng#11).
All 41 tests passing.
2026-05-09 20:06:36 -07:00

656 lines
No EOL
24 KiB
JavaScript

import fs from 'fs';
/**
* Parse a .speck file and return the AST
*/
export function parseSpeckFile(filePath) {
const content = fs.readFileSync(filePath, 'utf-8');
return parseSpeckContent(content, filePath);
}
/**
* Parse SpeckDL content and return the AST
*/
export function parseSpeckContent(content, filePath) {
const specks = [];
const lines = content.split('\n');
let i = 0;
while (i < lines.length) {
const line = lines[i].trim();
// Skip empty lines and comments
if (!line || line.startsWith('//') || line.startsWith('/*')) {
i++;
continue;
}
// Handle import statements
if (line.startsWith('import ')) {
const importNode = parseImportStatement(line);
// Import is a special case - it's not part of a speck
// We'll handle it separately in a future update
i++;
continue;
}
// Handle speck definitions
if (line.startsWith('speck ')) {
const speck = parseSpeck(lines, i);
if (speck) {
specks.push(speck);
// Move index past the speck we just parsed
i++; // Increment by 1, the loop will continue from next line
}
else {
i++;
}
continue;
}
i++;
}
return { specks };
}
function parseSpeck(lines, startIndex) {
const headerMatch = lines[startIndex].match(/^speck\s+([\w-]+)\s*{/);
if (!headerMatch)
return null;
const name = headerMatch[1];
const members = [];
let i = startIndex + 1;
let braceCount = 1;
while (i < lines.length && braceCount > 0) {
const rawLine = lines[i];
const line = rawLine.trim();
if (!line || line.startsWith('//') || line.startsWith('/*')) {
i++;
continue;
}
// Count braces on this line first
const openCount = (rawLine.match(/{/g) || []).length;
const closeCount = (rawLine.match(/}/g) || []).length;
// Check for block-opening members
const blockStarters = ['state:', 'init:', 'action ', 'event ', 'provenance ', 'bom ', 'interface ',
'state {', 'init {'];
const isBlockStarter = blockStarters.some(s => line.startsWith(s));
if (isBlockStarter && openCount > 0) {
// Multi-line block: parse it and skip to its end
const member = parseMemberBlock(lines, i);
if (member) {
members.push(member);
}
// Skip past this block
const endIdx = findBlockEnd(lines, i + 1, braceCount + openCount);
i = endIdx + 1;
continue;
}
// Single-line: update brace count, then parse if still inside
braceCount += openCount - closeCount;
if (braceCount <= 0) {
i++;
break;
}
const member = parseMember(line);
if (member) {
members.push(member);
}
i++;
}
return { type: 'speck', name, members };
}
function findBlockEnd(lines, startIndex, startBraceCount) {
let braceCount = startBraceCount;
let i = startIndex;
while (i < lines.length) {
const line = lines[i];
for (const ch of line) {
if (ch === '{')
braceCount++;
if (ch === '}') {
braceCount--;
if (braceCount < startBraceCount) {
return i;
}
}
}
i++;
}
return i;
}
function parseMemberBlock(lines, startIndex) {
const firstLine = lines[startIndex].trim();
const startBraceCount = (firstLine.match(/{/g) || []).length;
if (firstLine.startsWith('state:')) {
return parseStateBlockMultiline(lines, startIndex, startBraceCount);
}
if (firstLine.startsWith('state {') || firstLine === 'state') {
return parseStateBlockMultiline(lines, startIndex, startBraceCount);
}
if (firstLine.startsWith('init:')) {
return parseInitBlockMultiline(lines, startIndex, startBraceCount);
}
if (firstLine.startsWith('init {') || firstLine === 'init') {
return parseInitBlockMultiline(lines, startIndex, startBraceCount);
}
if (firstLine.startsWith('action ')) {
return parseActionBlockMultiline(lines, startIndex, startBraceCount);
}
if (firstLine.startsWith('event ')) {
return parseEventBlockMultiline(lines, startIndex, startBraceCount);
}
if (firstLine.startsWith('interface ')) {
return parseInterfaceBlockMultiline(lines, startIndex, startBraceCount);
}
if (firstLine.startsWith('provenance ')) {
return { type: 'provenance', clauses: [] };
}
if (firstLine.startsWith('bom ')) {
return { type: 'bom' };
}
return null;
}
function parseMember(line) {
// input:
if (line.startsWith('input:')) {
const typeExpr = parseTypeExpr(line.substring(6).trim());
return { type: 'input', typeExpr };
}
// output:
if (line.startsWith('output:')) {
const typeExpr = parseTypeExpr(line.substring(7).trim());
return { type: 'output', typeExpr };
}
// constraint:
if (line.startsWith('constraint:')) {
return { type: 'constraint', expr: line.substring(11).trim() };
}
// verify:
if (line.startsWith('verify:')) {
return { type: 'verify', temporalExpr: line.substring(7).trim() };
}
// interface:
if (line.startsWith('interface ')) {
return parseInterface(line);
}
// event:
if (line.startsWith('event ')) {
return parseEvent(line);
}
// provenance {
if (line.startsWith('provenance ')) {
return { type: 'provenance', clauses: [] };
}
// review:
if (line.startsWith('review:')) {
const kind = line.substring(7).trim();
return { type: 'review', kind };
}
// derives from:
if (line.startsWith('derives from ')) {
return parseDerives(line);
}
// satisfies:
if (line.startsWith('satisfies ')) {
return parseSatisfies(line);
}
// author:
if (line.startsWith('author:')) {
return parseAuthor(line);
}
// source:
if (line.startsWith('source:')) {
return parseSource(line);
}
// state: or state {
if (line.startsWith('state:')) {
const varsStr = line.substring(6).trim();
// state: { ... } - single-line form
if (varsStr.startsWith('{') && varsStr.endsWith('}')) {
const inner = varsStr.slice(1, -1).trim();
return parseStateBlock(inner);
}
// state: { - multi-line opening (handled by parseStateMultiline)
return { type: 'state', variables: [] };
}
if (line.startsWith('state {') || line === 'state') {
// state { ... } inline or state { on its own line (handled by parseMemberBlock)
if (line.startsWith('state {')) {
const inner = line.substring(6).trim();
const content = inner.startsWith('{') ? inner.slice(1).trim() : inner;
if (content.endsWith('}')) {
return parseStateBlock(content.slice(0, -1).trim());
}
}
return { type: 'state', variables: [] };
}
// init: or init {
if (line.startsWith('init:')) {
const initStr = line.substring(5).trim();
if (initStr.startsWith('{') && initStr.endsWith('}')) {
const inner = initStr.slice(1, -1).trim();
return parseInitBlock(inner);
}
return { type: 'init', assignments: [] };
}
if (line.startsWith('init {') || line === 'init') {
// init { ... } inline
if (line.startsWith('init {')) {
const inner = line.substring(5).trim();
const content = inner.startsWith('{') ? inner.slice(1).trim() : inner;
if (content.endsWith('}')) {
return parseInitBlock(content.slice(0, -1).trim());
}
}
return { type: 'init', assignments: [] };
}
// action keyword
if (line.startsWith('action ')) {
return parseActionHeader(line);
}
// bom {
if (line.startsWith('bom ')) {
// Simplified - full BOM block parsing would need multi-line context
return {
type: 'bom',
};
}
return null;
}
function parseStateBlock(inner) {
const variables = [];
if (!inner.trim())
return { type: 'state', variables };
const varStrs = inner.split(/;|\n/).map(s => s.trim()).filter(Boolean);
for (const vStr of varStrs) {
const withDefault = vStr.match(/^(\w+)\s*:\s*(.+?)\s*:=\s*(.+)$/);
if (withDefault) {
variables.push({
name: withDefault[1],
typeExpr: parseTypeExpr(withDefault[2].trim()),
defaultInit: withDefault[3].trim(),
});
continue;
}
const withoutDefault = vStr.match(/^(\w+)\s*:\s*(.+)$/);
if (withoutDefault) {
variables.push({
name: withoutDefault[1],
typeExpr: parseTypeExpr(withoutDefault[2].trim()),
});
}
}
return { type: 'state', variables };
}
function parseInitBlock(inner) {
const assignments = [];
if (!inner.trim())
return { type: 'init', assignments };
const assignStrs = inner.split(/;|\n/).map(s => s.trim()).filter(Boolean);
for (const aStr of assignStrs) {
const match = aStr.match(/^(\w+)\s*:=\s*(.+)$/);
if (match) {
assignments.push({ name: match[1], expr: match[2].trim() });
}
}
return { type: 'init', assignments };
}
function parseActionHeader(line) {
const match = line.match(/^action\s+(\w+)\s*(?:\(([^)]*)\))?\s*\{/);
if (!match)
return null;
const name = match[1];
const paramsStr = match[2] || '';
const params = [];
if (paramsStr.trim()) {
const paramPairs = paramsStr.split(',').map(s => s.trim()).filter(Boolean);
for (const p of paramPairs) {
const pMatch = p.match(/^(\w+)\s*:\s*(.+)$/);
if (pMatch) {
params.push({ name: pMatch[1], type: parseTypeExpr(pMatch[2].trim()) });
}
}
}
return { type: 'action', name, params, statements: [] };
}
function parseImportStatement(line) {
const match = line.match(/^import\s+(['"])(.+?)\1(?:\s+as\s+(\w+))?(?:\s+version\s+(['"])(.+?)\4)?(?:\s+hash\s+(['"])(.+?)\6)?/);
if (!match) {
throw new Error(`Failed to parse import statement: ${line}`);
}
const [, , path, , alias, , version, , hash] = match;
return {
type: 'import',
path,
alias,
version: version || undefined,
hash: hash || undefined,
};
}
function parseTypeExpr(expr) {
expr = expr.trim();
// Primitive types
const primitives = ['Nat', 'Int', 'Real', 'Bool', 'String', 'Bytes'];
if (primitives.includes(expr)) {
return { type: 'primitive', name: expr };
}
// List<T>
if (expr.startsWith('List<') && expr.endsWith('>')) {
const inner = expr.substring(5, expr.length - 1).trim();
return { type: 'list', elementType: parseTypeExpr(inner) };
}
// Set<T>
if (expr.startsWith('Set<') && expr.endsWith('>')) {
const inner = expr.substring(4, expr.length - 1).trim();
return { type: 'set', elementType: parseTypeExpr(inner) };
}
// Map<K, V>
if (expr.startsWith('Map<') && expr.endsWith('>')) {
const inner = expr.substring(4, expr.length - 1);
// Find the first-level comma (not inside nested generics)
let depth = 0;
let commaIdx = -1;
for (let i = 0; i < inner.length; i++) {
if (inner[i] === '<')
depth++;
else if (inner[i] === '>')
depth--;
else if (inner[i] === ',' && depth === 0) {
commaIdx = i;
break;
}
}
if (commaIdx !== -1) {
const keyStr = inner.substring(0, commaIdx).trim();
const valStr = inner.substring(commaIdx + 1).trim();
return { type: 'map', keyType: parseTypeExpr(keyStr), valueType: parseTypeExpr(valStr) };
}
// Fallback: treat as ident if malformed
return { type: 'ident', name: expr };
}
// List(T) — parenthetical syntax (SpeckDL canonical form)
if (expr.startsWith('List(') && expr.endsWith(')')) {
const inner = expr.substring(5, expr.length - 1).trim();
return { type: 'list', elementType: parseTypeExpr(inner) };
}
// Set(T) — parenthetical syntax (SpeckDL canonical form)
if (expr.startsWith('Set(') && expr.endsWith(')')) {
const inner = expr.substring(4, expr.length - 1).trim();
return { type: 'set', elementType: parseTypeExpr(inner) };
}
// Map(K, V) — parenthetical syntax (SpeckDL canonical form)
if (expr.startsWith('Map(') && expr.endsWith(')')) {
const inner = expr.substring(4, expr.length - 1);
let depth = 0;
let commaIdx = -1;
for (let i = 0; i < inner.length; i++) {
if (inner[i] === '(' || inner[i] === '<')
depth++;
else if (inner[i] === ')' || inner[i] === '>')
depth--;
else if (inner[i] === ',' && depth === 0) {
commaIdx = i;
break;
}
}
if (commaIdx !== -1) {
const keyStr = inner.substring(0, commaIdx).trim();
const valStr = inner.substring(commaIdx + 1).trim();
return { type: 'map', keyType: parseTypeExpr(keyStr), valueType: parseTypeExpr(valStr) };
}
// Fallback: treat as ident if malformed
return { type: 'ident', name: expr };
}
// List type: [T]
if (expr.startsWith('[') && expr.endsWith(']')) {
const elementType = parseTypeExpr(expr.substring(1, expr.length - 1));
return { type: 'list', elementType };
}
// Record type: { ... }
if (expr.startsWith('{') && expr.endsWith('}')) {
const content = expr.substring(1, expr.length - 1).trim();
const fields = [];
if (content) {
// Split by comma and parse each field
const fieldStrs = content.split(',').map(s => s.trim());
for (const fieldStr of fieldStrs) {
const fieldMatch = fieldStr.match(/^(\w+)\s*:\s*(.+)$/);
if (fieldMatch) {
const [, name, typeStr] = fieldMatch;
fields.push({ name, type: parseTypeExpr(typeStr.trim()) });
}
}
}
return { type: 'record', fields };
}
// Identifier (for interface references, etc.)
return { type: 'ident', name: expr };
}
function parseInterface(line) {
// interface Name {
const match = line.match(/^interface\s+(\w+)\s*{/);
if (!match) {
throw new Error(`Failed to parse interface: ${line}`);
}
const name = match[1];
// This is a simplified parser - in a real implementation, we'd need to handle multi-line interfaces
return {
type: 'interface',
name,
methods: [],
};
}
function parseEvent(line) {
// event Name {
const match = line.match(/^event\s+(\w+)\s*{/);
if (!match) {
throw new Error(`Failed to parse event: ${line}`);
}
const name = match[1];
return {
type: 'event',
name,
fields: [],
};
}
function parseProvenanceBlock(lines, line) {
// This is a simplified parser - in a real implementation, we'd parse the full block
return {
type: 'provenance',
clauses: [],
};
}
function parseDerives(line) {
// derives from Name via "rationale"
const match = line.match(/^derives\s+from\s+(\w+(?:-\w+)*)(?:\s+via\s+(['"])(.+?)\2)?/);
if (!match) {
console.warn(`Failed to parse derives statement: ${line}`);
return { type: 'derives', from: 'unknown' };
}
const [, from, , via] = match;
return {
type: 'derives',
from,
via: via || undefined,
};
}
function parseSatisfies(line) {
// satisfies Name [clause "X.Y.Z"]
// e.g., satisfies RESILIENCE-REQ-01 clause "3.1.2"
// e.g., satisfies RESILIENCE-REQ-02
const match = line.match(/^satisfies\s+([\w-]+(?:-[\w]+)*)(?:\s+clause\s+(['"])(.+?)\2)?/);
if (!match) {
console.warn(`Failed to parse satisfies statement: ${line}`);
return { type: 'satisfies', requirement: 'unknown' };
}
const [, requirement, , clause] = match;
return {
type: 'satisfies',
requirement,
clause: clause || undefined,
};
}
function parseAuthor(line) {
// author: "Name" <"email">
// e.g., author: "Scott Scoble" <"scott@scoble.me">
const match = line.match(/^author:\s+(['"])(.+?)\1(?:\s+<(['"])(.+?)\3>)?/);
if (!match) {
// Try without angle brackets or with different format
console.warn(`Failed to parse author statement: ${line}`);
return { type: 'author', name: 'unknown' };
}
const [, , name, , email] = match;
return {
type: 'author',
name,
email: email || undefined,
};
}
function parseSource(line) {
// source: kind ref "identifier"
// e.g., source: architecture_review ref "AR-2024-0215"
const match = line.match(/^source:\s+(\w+)(?:\s+ref\s+(['"])(.+?)\2)?/);
if (!match) {
console.warn(`Failed to parse source statement: ${line}`);
return { type: 'source', kind: 'document' };
}
const [, kind, , ref] = match;
const validKinds = [
'conversation', 'meeting', 'document', 'regulation',
'architecture_review', 'threat_model', 'compliance_audit'
];
if (!validKinds.includes(kind)) {
console.warn(`Invalid source kind: ${kind}, defaulting to document`);
return { type: 'source', kind: 'document', ref: ref || undefined };
}
return {
type: 'source',
kind: kind,
ref: ref || undefined,
};
}
function parseStateBlockMultiline(lines, startIndex, startBraceCount) {
const endIndex = findBlockEnd(lines, startIndex + 1, startBraceCount);
const innerLines = lines.slice(startIndex + 1, endIndex).map(l => l.trim()).filter(l => l && !l.startsWith('//') && !l.startsWith('/*'));
const inner = innerLines.join('; ');
return parseStateBlock(inner);
}
function parseInitBlockMultiline(lines, startIndex, startBraceCount) {
const endIndex = findBlockEnd(lines, startIndex + 1, startBraceCount);
const innerLines = lines.slice(startIndex + 1, endIndex).map(l => l.trim()).filter(l => l && !l.startsWith('//') && !l.startsWith('/*'));
const inner = innerLines.join('; ');
return parseInitBlock(inner);
}
function parseActionBlockMultiline(lines, startIndex, startBraceCount) {
const firstLine = lines[startIndex].trim();
const header = parseActionHeader(firstLine);
if (!header)
return null;
const endIndex = findBlockEnd(lines, startIndex + 1, startBraceCount);
const bodyLines = lines.slice(startIndex + 1, endIndex).map(l => l.trim()).filter(l => l && !l.startsWith('//') && !l.startsWith('/*'));
const statements = [];
for (let i = 0; i < bodyLines.length; i++) {
const stmt = bodyLines[i];
// precondition: expr
if (stmt.startsWith('precondition:')) {
let expr = stmt.substring(13).trim();
// support 'or' continuation lines
while (i + 1 < bodyLines.length && bodyLines[i + 1].startsWith('or ')) {
i++;
expr += ' || ' + bodyLines[i].substring(3).trim();
}
statements.push({ type: 'precondition', expr });
continue;
}
// postcondition: expr
if (stmt.startsWith('postcondition:')) {
let expr = stmt.substring(14).trim();
// support 'or' continuation lines
while (i + 1 < bodyLines.length && bodyLines[i + 1].startsWith('or ')) {
i++;
expr += ' || ' + bodyLines[i].substring(3).trim();
}
statements.push({ type: 'postcondition', expr });
continue;
}
// require expr
if (stmt.startsWith('require ')) {
statements.push({ type: 'require', expr: stmt.substring(8).trim() });
continue;
}
// return expr
if (stmt.startsWith('return ')) {
statements.push({ type: 'return', expr: stmt.substring(7).trim() });
continue;
}
// emit Event { fields }
const emitMatch = stmt.match(/^emit\s+(\w+)\s*\{\s*(.*)\s*\}$/);
if (emitMatch) {
const eventName = emitMatch[1];
const fieldsStr = emitMatch[2];
const fields = [];
if (fieldsStr) {
const fieldPairs = fieldsStr.split(',').map(s => s.trim()).filter(Boolean);
for (const fp of fieldPairs) {
const colonIdx = fp.indexOf(':');
if (colonIdx > 0) {
fields.push({
name: fp.substring(0, colonIdx).trim(),
value: fp.substring(colonIdx + 1).trim(),
});
}
}
}
statements.push({ type: 'emit', event: eventName, fields });
continue;
}
// let name := expr
const letMatch = stmt.match(/^let\s+(\w+)\s*:=\s*(.+)$/);
if (letMatch) {
statements.push({ type: 'let', name: letMatch[1], expr: letMatch[2].trim() });
continue;
}
// assignment: target := expr
const assignMatch = stmt.match(/^(\w+(?:\[.*?\])?)\s*:=\s*(.+)$/);
if (assignMatch) {
statements.push({ type: 'assign', target: assignMatch[1], expr: assignMatch[2].trim() });
}
}
return { ...header, statements };
}
function parseEventBlockMultiline(lines, startIndex, startBraceCount) {
const firstLine = lines[startIndex].trim();
const header = parseEvent(firstLine);
const endIndex = findBlockEnd(lines, startIndex + 1, startBraceCount);
const innerLines = lines.slice(startIndex + 1, endIndex).map(l => l.trim()).filter(l => l && !l.startsWith('//') && !l.startsWith('/*'));
const fields = [];
for (const line of innerLines) {
const match = line.match(/^(\w+)\s*:\s*(.+?),?$/);
if (match) {
fields.push({ name: match[1], type: parseTypeExpr(match[2].replace(/,$/, '').trim()) });
}
}
return { ...header, fields };
}
function parseInterfaceBlockMultiline(lines, startIndex, startBraceCount) {
const firstLine = lines[startIndex].trim();
const header = parseInterface(firstLine);
const endIndex = findBlockEnd(lines, startIndex + 1, startBraceCount);
const innerLines = lines.slice(startIndex + 1, endIndex).map(l => l.trim()).filter(l => l && !l.startsWith('//') && !l.startsWith('/*'));
const methods = [];
for (const line of innerLines) {
// name(params) -> returnType
const match = line.match(/^(\w+)\s*\(([^)]*)\)\s*-\u003e\s*(.+?),?$/);
if (match) {
const name = match[1];
const paramsStr = match[2];
const returnTypeStr = match[3].replace(/,$/, '').trim();
const params = [];
if (paramsStr.trim()) {
const paramPairs = paramsStr.split(',').map(s => s.trim()).filter(Boolean);
for (const p of paramPairs) {
const pMatch = p.match(/^(\w+)\s*:\s*(.+)$/);
if (pMatch) {
params.push({ name: pMatch[1], type: parseTypeExpr(pMatch[2].trim()) });
}
}
}
methods.push({ name, params, returnType: parseTypeExpr(returnTypeStr) });
}
}
return { ...header, methods };
}
//# sourceMappingURL=parser.js.map