@quereus/quereus 0.2.1 → 0.4.0

package/src/parser/lexer.ts

@@ -19,6 +19,7 @@ export enum TokenType {
 	TABLE = 'TABLE',
 	INDEX = 'INDEX',
 	VIEW = 'VIEW',
+	ASSERTION = 'ASSERTION',
 	TEMP = 'TEMP',
 	TEMPORARY = 'TEMPORARY',
 	VIRTUAL = 'VIRTUAL',
@@ -47,6 +48,7 @@ export enum TokenType {
 	UNION = 'UNION',
 	INTERSECT = 'INTERSECT',
 	EXCEPT = 'EXCEPT',
+	DIFF = 'DIFF',
 	ALL = 'ALL',
 	PRIMARY = 'PRIMARY',
 	CONSTRAINT = 'CONSTRAINT',
@@ -111,6 +113,7 @@ export enum TokenType {
 	CAST = 'CAST',
 	OVER = 'OVER',
 	PARTITION = 'PARTITION',
+	LATERAL = 'LATERAL',
 	ROW = 'ROW',
 	ROWS = 'ROWS',
 	RANGE = 'RANGE',
@@ -119,6 +122,14 @@ export enum TokenType {
 	FOLLOWING = 'FOLLOWING',
 	CURRENT = 'CURRENT',
 
+	// Declarative schema
+	DECLARE = 'DECLARE',
+	SCHEMA = 'SCHEMA',
+	APPLY = 'APPLY',
+	EXPLAIN = 'EXPLAIN',
+	VERSION = 'VERSION',
+	SEED = 'SEED',
+
 	// Operators and punctuation
 	PLUS = 'PLUS',               // +
 	MINUS = 'MINUS',             // -
@@ -146,6 +157,8 @@ export enum TokenType {
 	COLON = 'COLON',             // : (for named parameters)
 	DOLLAR = 'DOLLAR',           // $ (for named parameters)
 	ARROW = 'ARROW',             // -> (JSON operator)
+	LBRACE = 'LBRACE',           // {
+	RBRACE = 'RBRACE',           // }
 
 	// Special
 	EOF = 'EOF',
@@ -156,6 +169,7 @@ export enum TokenType {
 export interface Token {
 	type: TokenType;
 	lexeme: string;
+	// eslint-disable-next-line @typescript-eslint/no-explicit-any
 	literal?: any;
 	startLine: number;
 	startColumn: number;
@@ -179,6 +193,7 @@ export const KEYWORDS: Record<string, TokenType> = {
 	'table': TokenType.TABLE,
 	'index': TokenType.INDEX,
 	'view': TokenType.VIEW,
+	'assertion': TokenType.ASSERTION,
 	'virtual': TokenType.VIRTUAL,
 	'using': TokenType.USING,
 	'null': TokenType.NULL,
@@ -202,6 +217,7 @@ export const KEYWORDS: Record<string, TokenType> = {
 	'limit': TokenType.LIMIT,
 	'offset': TokenType.OFFSET,
 	'union': TokenType.UNION,
+	'diff': TokenType.DIFF,
 	'all': TokenType.ALL,
 	'primary': TokenType.PRIMARY,
 	'constraint': TokenType.CONSTRAINT,
@@ -267,6 +283,7 @@ export const KEYWORDS: Record<string, TokenType> = {
 	'cast': TokenType.CAST,
 	'over': TokenType.OVER,
 	'partition': TokenType.PARTITION,
+	'lateral': TokenType.LATERAL,
 	'row': TokenType.ROW,
 	'rows': TokenType.ROWS,
 	'range': TokenType.RANGE,
@@ -276,6 +293,11 @@ export const KEYWORDS: Record<string, TokenType> = {
 	'current': TokenType.CURRENT,
 	'intersect': TokenType.INTERSECT,
 	'except': TokenType.EXCEPT,
+	'declare': TokenType.DECLARE,
+	// Note: schema, version, seed deliberately NOT reserved here - treated as contextual keywords
+	// to avoid breaking schema() function calls and column names like 'version', 'seed'
+	'apply': TokenType.APPLY,
+	'explain': TokenType.EXPLAIN,
 };
 
 /**
@@ -331,6 +353,8 @@ export class Lexer {
 			// Single-character tokens
 			case '(': this.addToken(TokenType.LPAREN); break;
 			case ')': this.addToken(TokenType.RPAREN); break;
+				case '{': this.addToken(TokenType.LBRACE); break;
+				case '}': this.addToken(TokenType.RBRACE); break;
 			case ',': this.addToken(TokenType.COMMA); break;
 			case '.': this.addToken(TokenType.DOT); break;
 			case ';': this.addToken(TokenType.SEMICOLON); break;
@@ -416,8 +440,7 @@ export class Lexer {
 				// Ignore whitespace
 				break;
 			case '\n':
-				this.line++;
-				this.column = 1;
+				// Newline handling already done in advance()
 				break;
 
 			// Default - handle identifiers and numbers
@@ -469,11 +492,6 @@ export class Lexer {
 		let escaping = false;
 
 		while ((!this.isAtEnd() && this.peek() !== quote) || escaping) {
-			if (this.peek() === '\n') {
-				this.line++;
-				this.column = 1;
-			}
-
 			if (escaping) {
 				// Handle escape sequences
 				const c = this.peek();
@@ -523,10 +541,6 @@ export class Lexer {
 		let value = '';
 
 		while (!this.isAtEnd() && this.peek() !== '`') {
-			if (this.peek() === '\n') {
-				this.line++;
-				this.column = 1;
-			}
 			value += this.advance();
 		}
 
@@ -545,10 +559,6 @@ export class Lexer {
 		let value = '';
 
 		while (!this.isAtEnd() && this.peek() !== ']') {
-			if (this.peek() === '\n') {
-				this.line++;
-				this.column = 1;
-			}
 			value += this.advance();
 		}
 
@@ -698,12 +708,7 @@ export class Lexer {
 				this.advance(); // Consume '/'
 				nesting--;
 			} else {
-				if (this.peek() === '\n') {
-					this.line++;
-					this.column = 1;
-				} else {
-					this.column++;
-				}
+				// Advance one character and let advance() maintain line/column
 				this.advance();
 			}
 		}
@@ -737,6 +742,7 @@ export class Lexer {
 		return c === ' ' || c === '\r' || c === '\n' || c === '\t';
 	}
 
+	// eslint-disable-next-line @typescript-eslint/no-explicit-any
 	private addToken(type: TokenType, literal?: any): void {
 		const lexeme = this.source.substring(this.start, this.current);
 		this.tokens.push({