- init

src/engine/__tests__/lexer.spec.ts

@@ -0,0 +1,66 @@
+import { describe, it, expect } from 'vitest';
+import { tokenize } from '../lexer';
+
+const types = (s: string) => tokenize(s).map((t) => t.type);
+const values = (s: string) => tokenize(s).map((t) => t.value);
+
+describe('lexer', () => {
+  it('tokenizes numbers incl. decimals and exponents', () => {
+    expect(values('1 2.5 .5 1e3 1.2E-3')).toEqual([
+      '1',
+      '2.5',
+      '.5',
+      '1e3',
+      '1.2E-3',
+      '',
+    ]);
+    expect(types('42')).toEqual(['NUMBER', 'EOF']);
+  });
+
+  it('tokenizes operators and punctuation', () => {
+    expect(types('+-*/^():;!')).toEqual([
+      'PLUS',
+      'MINUS',
+      'STAR',
+      'SLASH',
+      'CARET',
+      'LPAREN',
+      'RPAREN',
+      'COLON',
+      'SEMICOLON',
+      'BANG',
+      'EOF',
+    ]);
+  });
+
+  it('reads bare words as IDENT (cell refs, functions, sheet names alike)', () => {
+    expect(types('SUM(A1:B2)')).toEqual([
+      'IDENT',
+      'LPAREN',
+      'IDENT',
+      'COLON',
+      'IDENT',
+      'RPAREN',
+      'EOF',
+    ]);
+  });
+
+  it('reads single-quoted sheet names with spaces', () => {
+    const t = tokenize("'Kosten Q3'!B2");
+    expect(t[0]).toMatchObject({ type: 'QUOTED', value: 'Kosten Q3' });
+    expect(t[1].type).toBe('BANG');
+    expect(t[2]).toMatchObject({ type: 'IDENT', value: 'B2' });
+  });
+
+  it('handles escaped double-quoted strings', () => {
+    expect(tokenize('"a\\"b"')[0]).toMatchObject({ type: 'STRING', value: 'a"b' });
+  });
+
+  it('skips whitespace', () => {
+    expect(types('  A1\t+\n B2 ')).toEqual(['IDENT', 'PLUS', 'IDENT', 'EOF']);
+  });
+
+  it('throws on an unexpected character', () => {
+    expect(() => tokenize('A1 & B2')).toThrow();
+  });
+});