/** * @license * Copyright Google Inc. All Rights Reserved. * * Use of this source code is governed by an MIT-style license that can be * found in the LICENSE file at https://angular.io/license */ import {getHtmlTagDefinition} from '../../src/ml_parser/html_tags'; import * as lex from '../../src/ml_parser/lexer'; import {ParseLocation, ParseSourceFile, ParseSourceSpan} from '../../src/parse_util'; { describe('HtmlLexer', () => { describe('line/column numbers', () => { it('should work without newlines', () => { expect(tokenizeAndHumanizeLineColumn('a')).toEqual([ [lex.TokenType.TAG_OPEN_START, '0:0'], [lex.TokenType.TAG_OPEN_END, '0:2'], [lex.TokenType.TEXT, '0:3'], [lex.TokenType.TAG_CLOSE, '0:4'], [lex.TokenType.EOF, '0:8'], ]); }); it('should work with one newline', () => { expect(tokenizeAndHumanizeLineColumn('\na')).toEqual([ [lex.TokenType.TAG_OPEN_START, '0:0'], [lex.TokenType.TAG_OPEN_END, '0:2'], [lex.TokenType.TEXT, '0:3'], [lex.TokenType.TAG_CLOSE, '1:1'], [lex.TokenType.EOF, '1:5'], ]); }); it('should work with multiple newlines', () => { expect(tokenizeAndHumanizeLineColumn('\na')).toEqual([ [lex.TokenType.TAG_OPEN_START, '0:0'], [lex.TokenType.TAG_OPEN_END, '1:0'], [lex.TokenType.TEXT, '1:1'], [lex.TokenType.TAG_CLOSE, '2:1'], [lex.TokenType.EOF, '2:5'], ]); }); it('should work with CR and LF', () => { expect(tokenizeAndHumanizeLineColumn('\r\na\r')).toEqual([ [lex.TokenType.TAG_OPEN_START, '0:0'], [lex.TokenType.TAG_OPEN_END, '1:0'], [lex.TokenType.TEXT, '1:1'], [lex.TokenType.TAG_CLOSE, '2:1'], [lex.TokenType.EOF, '2:5'], ]); }); }); describe('content ranges', () => { it('should only process the text within the range', () => { expect(tokenizeAndHumanizeSourceSpans( 'pre 1\npre 2\npre 3 `line 1\nline 2\nline 3` post 1\n post 2\n post 3', {range: {startPos: 19, startLine: 2, startCol: 7, endPos: 39}})) .toEqual([ [lex.TokenType.TEXT, 'line 1\nline 2\nline 3'], [lex.TokenType.EOF, ''], ]); }); it('should take into account preceding (non-processed) lines and columns', () => { expect(tokenizeAndHumanizeLineColumn( 'pre 1\npre 2\npre 3 `line 1\nline 2\nline 3` post 1\n post 2\n post 3', {range: {startPos: 19, startLine: 2, startCol: 7, endPos: 39}})) .toEqual([ [lex.TokenType.TEXT, '2:7'], [lex.TokenType.EOF, '4:6'], ]); }); }); describe('comments', () => { it('should parse comments', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.COMMENT_START], [lex.TokenType.RAW_TEXT, 't\ne\ns\nt'], [lex.TokenType.COMMENT_END], [lex.TokenType.EOF], ]); }); it('should store the locations', () => { expect(tokenizeAndHumanizeSourceSpans('')).toEqual([ [lex.TokenType.COMMENT_START, ''], [lex.TokenType.EOF, ''], ]); }); it('should report { expect(tokenizeAndHumanizeErrors(' { expect(tokenizeAndHumanizeErrors('')).toEqual([ [lex.TokenType.COMMENT_START, ''], [lex.TokenType.EOF, ''], ]); }); it('should accept comments finishing by too many dashes (odd number)', () => { expect(tokenizeAndHumanizeSourceSpans('')).toEqual([ [lex.TokenType.COMMENT_START, ''], [lex.TokenType.EOF, ''], ]); }); }); describe('doctype', () => { it('should parse doctypes', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.DOC_TYPE, 'doctype html'], [lex.TokenType.EOF], ]); }); it('should store the locations', () => { expect(tokenizeAndHumanizeSourceSpans('')).toEqual([ [lex.TokenType.DOC_TYPE, ''], [lex.TokenType.EOF, ''], ]); }); it('should report missing end doctype', () => { expect(tokenizeAndHumanizeErrors(' { it('should parse CDATA', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.CDATA_START], [lex.TokenType.RAW_TEXT, 't\ne\ns\nt'], [lex.TokenType.CDATA_END], [lex.TokenType.EOF], ]); }); it('should store the locations', () => { expect(tokenizeAndHumanizeSourceSpans('')).toEqual([ [lex.TokenType.CDATA_START, ''], [lex.TokenType.EOF, ''], ]); }); it('should report { expect(tokenizeAndHumanizeErrors(' { expect(tokenizeAndHumanizeErrors(' { it('should parse open tags without prefix', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'test'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse namespace prefix', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, 'ns1', 'test'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse void tags', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'test'], [lex.TokenType.TAG_OPEN_END_VOID], [lex.TokenType.EOF], ]); }); it('should allow whitespace after the tag name', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'test'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should store the locations', () => { expect(tokenizeAndHumanizeSourceSpans('')).toEqual([ [lex.TokenType.TAG_OPEN_START, ''], [lex.TokenType.EOF, ''], ]); }); }); describe('attributes', () => { it('should parse attributes without prefix', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse attributes with interpolation', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_VALUE, '{{v}}'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_NAME, '', 'b'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_VALUE, 's{{m}}e'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_NAME, '', 'c'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_VALUE, 's{{m//c}}e'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse attributes with prefix', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, 'ns1', 'a'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse attributes whose prefix is not valid', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', '(ns1:a)'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse attributes with single quote value', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_QUOTE, '\''], [lex.TokenType.ATTR_VALUE, 'b'], [lex.TokenType.ATTR_QUOTE, '\''], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse attributes with double quote value', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_VALUE, 'b'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse attributes with unquoted value', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_VALUE, 'b'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should allow whitespace', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_VALUE, 'b'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse attributes with entities in values', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_VALUE, 'AA'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should not decode entities without trailing ";"', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_VALUE, '&'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_NAME, '', 'b'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_VALUE, 'c&&d'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse attributes with "&" in values', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_VALUE, 'b && c &'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse values with CR and LF', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_QUOTE, '\''], [lex.TokenType.ATTR_VALUE, 't\ne\ns\nt'], [lex.TokenType.ATTR_QUOTE, '\''], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should store the locations', () => { expect(tokenizeAndHumanizeSourceSpans('')).toEqual([ [lex.TokenType.TAG_OPEN_START, ''], [lex.TokenType.EOF, ''], ]); }); it('should report missing closing single quote', () => { expect(tokenizeAndHumanizeErrors('')).toEqual([ [lex.TokenType.ATTR_VALUE, 'Unexpected character "EOF"', '0:8'], ]); }); it('should report missing closing double quote', () => { expect(tokenizeAndHumanizeErrors(' { it('should parse closing tags without prefix', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_CLOSE, '', 'test'], [lex.TokenType.EOF], ]); }); it('should parse closing tags with prefix', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_CLOSE, 'ns1', 'test'], [lex.TokenType.EOF], ]); }); it('should allow whitespace', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TAG_CLOSE, '', 'test'], [lex.TokenType.EOF], ]); }); it('should store the locations', () => { expect(tokenizeAndHumanizeSourceSpans('')).toEqual([ [lex.TokenType.TAG_CLOSE, ''], [lex.TokenType.EOF, ''], ]); }); it('should report missing name after { expect(tokenizeAndHumanizeErrors('', () => { expect(tokenizeAndHumanizeErrors(' { it('should parse named entities', () => { expect(tokenizeAndHumanizeParts('a&b')).toEqual([ [lex.TokenType.TEXT, 'a&b'], [lex.TokenType.EOF], ]); }); it('should parse hexadecimal entities', () => { expect(tokenizeAndHumanizeParts('AA')).toEqual([ [lex.TokenType.TEXT, 'AA'], [lex.TokenType.EOF], ]); }); it('should parse decimal entities', () => { expect(tokenizeAndHumanizeParts('A')).toEqual([ [lex.TokenType.TEXT, 'A'], [lex.TokenType.EOF], ]); }); it('should store the locations', () => { expect(tokenizeAndHumanizeSourceSpans('a&b')).toEqual([ [lex.TokenType.TEXT, 'a&b'], [lex.TokenType.EOF, ''], ]); }); it('should report malformed/unknown entities', () => { expect(tokenizeAndHumanizeErrors('&tbo;')).toEqual([[ lex.TokenType.TEXT, 'Unknown entity "tbo" - use the "&#;" or "&#x;" syntax', '0:0' ]]); expect(tokenizeAndHumanizeErrors('sdf;')).toEqual([ [lex.TokenType.TEXT, 'Unexpected character "s"', '0:3'] ]); expect(tokenizeAndHumanizeErrors(' sdf;')).toEqual([ [lex.TokenType.TEXT, 'Unexpected character "s"', '0:4'] ]); expect(tokenizeAndHumanizeErrors('઼')).toEqual([ [lex.TokenType.TEXT, 'Unexpected character "EOF"', '0:6'] ]); }); }); describe('regular text', () => { it('should parse text', () => { expect(tokenizeAndHumanizeParts('a')).toEqual([ [lex.TokenType.TEXT, 'a'], [lex.TokenType.EOF], ]); }); it('should parse interpolation', () => { expect(tokenizeAndHumanizeParts('{{ a }}b{{ c // comment }}')).toEqual([ [lex.TokenType.TEXT, '{{ a }}b{{ c // comment }}'], [lex.TokenType.EOF], ]); }); it('should parse interpolation with custom markers', () => { expect(tokenizeAndHumanizeParts('{% a %}', {interpolationConfig: {start: '{%', end: '%}'}})) .toEqual([ [lex.TokenType.TEXT, '{% a %}'], [lex.TokenType.EOF], ]); }); it('should handle CR & LF', () => { expect(tokenizeAndHumanizeParts('t\ne\rs\r\nt')).toEqual([ [lex.TokenType.TEXT, 't\ne\ns\nt'], [lex.TokenType.EOF], ]); }); it('should parse entities', () => { expect(tokenizeAndHumanizeParts('a&b')).toEqual([ [lex.TokenType.TEXT, 'a&b'], [lex.TokenType.EOF], ]); }); it('should parse text starting with "&"', () => { expect(tokenizeAndHumanizeParts('a && b &')).toEqual([ [lex.TokenType.TEXT, 'a && b &'], [lex.TokenType.EOF], ]); }); it('should store the locations', () => { expect(tokenizeAndHumanizeSourceSpans('a')).toEqual([ [lex.TokenType.TEXT, 'a'], [lex.TokenType.EOF, ''], ]); }); it('should allow "<" in text nodes', () => { expect(tokenizeAndHumanizeParts('{{ a < b ? c : d }}')).toEqual([ [lex.TokenType.TEXT, '{{ a < b ? c : d }}'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeSourceSpans('

a')).toEqual([ [lex.TokenType.TAG_OPEN_START, ''], [lex.TokenType.TEXT, 'a'], [lex.TokenType.EOF, ''], ]); expect(tokenizeAndHumanizeParts('< a>')).toEqual([ [lex.TokenType.TEXT, '< a>'], [lex.TokenType.EOF], ]); }); it('should parse valid start tag in interpolation', () => { expect(tokenizeAndHumanizeParts('{{ a d }}')).toEqual([ [lex.TokenType.TEXT, '{{ a '], [lex.TokenType.TAG_OPEN_START, '', 'b'], [lex.TokenType.ATTR_NAME, '', '&&'], [lex.TokenType.ATTR_NAME, '', 'c'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TEXT, ' d }}'], [lex.TokenType.EOF], ]); }); it('should parse start tags quotes in place of an attribute name as text', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TEXT, ''], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TEXT, ''], [lex.TokenType.EOF], ]); }); it('should parse start tags quotes in place of an attribute name (after a valid attribute) as text', () => { expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TEXT, ''], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('')).toEqual([ [lex.TokenType.TEXT, ''], [lex.TokenType.EOF], ]); }); it('should be able to escape {', () => { expect(tokenizeAndHumanizeParts('{{ "{" }}')).toEqual([ [lex.TokenType.TEXT, '{{ "{" }}'], [lex.TokenType.EOF], ]); }); it('should be able to escape {{', () => { expect(tokenizeAndHumanizeParts('{{ "{{" }}')).toEqual([ [lex.TokenType.TEXT, '{{ "{{" }}'], [lex.TokenType.EOF], ]); }); it('should treat expansion form as text when they are not parsed', () => { expect(tokenizeAndHumanizeParts( '{a, b, =4 {c}}', {tokenizeExpansionForms: false})) .toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'span'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TEXT, '{a, b, =4 {c}}'], [lex.TokenType.TAG_CLOSE, '', 'span'], [lex.TokenType.EOF], ]); }); }); describe('raw text', () => { it('should parse text', () => { expect(tokenizeAndHumanizeParts(``)).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'script'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.RAW_TEXT, 't\ne\ns\nt'], [lex.TokenType.TAG_CLOSE, '', 'script'], [lex.TokenType.EOF], ]); }); it('should not detect entities', () => { expect(tokenizeAndHumanizeParts(``)).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'script'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.RAW_TEXT, '&'], [lex.TokenType.TAG_CLOSE, '', 'script'], [lex.TokenType.EOF], ]); }); it('should ignore other opening tags', () => { expect(tokenizeAndHumanizeParts(``)).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'script'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.RAW_TEXT, 'a

'], [lex.TokenType.TAG_CLOSE, '', 'script'], [lex.TokenType.EOF], ]); }); it('should ignore other closing tags', () => { expect(tokenizeAndHumanizeParts(``)).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'script'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.RAW_TEXT, 'a'], [lex.TokenType.TAG_CLOSE, '', 'script'], [lex.TokenType.EOF], ]); }); it('should store the locations', () => { expect(tokenizeAndHumanizeSourceSpans(``)).toEqual([ [lex.TokenType.TAG_OPEN_START, ''], [lex.TokenType.RAW_TEXT, 'a'], [lex.TokenType.TAG_CLOSE, ''], [lex.TokenType.EOF, ''], ]); }); }); describe('escapable raw text', () => { it('should parse text', () => { expect(tokenizeAndHumanizeParts(`t\ne\rs\r\nt`)).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'title'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.ESCAPABLE_RAW_TEXT, 't\ne\ns\nt'], [lex.TokenType.TAG_CLOSE, '', 'title'], [lex.TokenType.EOF], ]); }); it('should detect entities', () => { expect(tokenizeAndHumanizeParts(`&`)).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'title'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.ESCAPABLE_RAW_TEXT, '&'], [lex.TokenType.TAG_CLOSE, '', 'title'], [lex.TokenType.EOF], ]); }); it('should ignore other opening tags', () => { expect(tokenizeAndHumanizeParts(`a<div>`)).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'title'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.ESCAPABLE_RAW_TEXT, 'a
'], [lex.TokenType.TAG_CLOSE, '', 'title'], [lex.TokenType.EOF], ]); }); it('should ignore other closing tags', () => { expect(tokenizeAndHumanizeParts(`a</test>`)).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'title'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.ESCAPABLE_RAW_TEXT, 'a'], [lex.TokenType.TAG_CLOSE, '', 'title'], [lex.TokenType.EOF], ]); }); it('should store the locations', () => { expect(tokenizeAndHumanizeSourceSpans(`a`)).toEqual([ [lex.TokenType.TAG_OPEN_START, ''], [lex.TokenType.ESCAPABLE_RAW_TEXT, 'a'], [lex.TokenType.TAG_CLOSE, ''], [lex.TokenType.EOF, ''], ]); }); }); describe('expansion forms', () => { it('should parse an expansion form', () => { expect( tokenizeAndHumanizeParts( '{one.two, three, =4 {four} =5 {five} foo {bar} }', {tokenizeExpansionForms: true})) .toEqual([ [lex.TokenType.EXPANSION_FORM_START], [lex.TokenType.RAW_TEXT, 'one.two'], [lex.TokenType.RAW_TEXT, 'three'], [lex.TokenType.EXPANSION_CASE_VALUE, '=4'], [lex.TokenType.EXPANSION_CASE_EXP_START], [lex.TokenType.TEXT, 'four'], [lex.TokenType.EXPANSION_CASE_EXP_END], [lex.TokenType.EXPANSION_CASE_VALUE, '=5'], [lex.TokenType.EXPANSION_CASE_EXP_START], [lex.TokenType.TEXT, 'five'], [lex.TokenType.EXPANSION_CASE_EXP_END], [lex.TokenType.EXPANSION_CASE_VALUE, 'foo'], [lex.TokenType.EXPANSION_CASE_EXP_START], [lex.TokenType.TEXT, 'bar'], [lex.TokenType.EXPANSION_CASE_EXP_END], [lex.TokenType.EXPANSION_FORM_END], [lex.TokenType.EOF], ]); }); it('should parse an expansion form with text elements surrounding it', () => { expect(tokenizeAndHumanizeParts( 'before{one.two, three, =4 {four}}after', {tokenizeExpansionForms: true})) .toEqual([ [lex.TokenType.TEXT, 'before'], [lex.TokenType.EXPANSION_FORM_START], [lex.TokenType.RAW_TEXT, 'one.two'], [lex.TokenType.RAW_TEXT, 'three'], [lex.TokenType.EXPANSION_CASE_VALUE, '=4'], [lex.TokenType.EXPANSION_CASE_EXP_START], [lex.TokenType.TEXT, 'four'], [lex.TokenType.EXPANSION_CASE_EXP_END], [lex.TokenType.EXPANSION_FORM_END], [lex.TokenType.TEXT, 'after'], [lex.TokenType.EOF], ]); }); it('should parse an expansion form as a tag single child', () => { expect(tokenizeAndHumanizeParts( '
{a, b, =4 {c}}
', {tokenizeExpansionForms: true})) .toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'div'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TAG_OPEN_START, '', 'span'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EXPANSION_FORM_START], [lex.TokenType.RAW_TEXT, 'a'], [lex.TokenType.RAW_TEXT, 'b'], [lex.TokenType.EXPANSION_CASE_VALUE, '=4'], [lex.TokenType.EXPANSION_CASE_EXP_START], [lex.TokenType.TEXT, 'c'], [lex.TokenType.EXPANSION_CASE_EXP_END], [lex.TokenType.EXPANSION_FORM_END], [lex.TokenType.TAG_CLOSE, '', 'span'], [lex.TokenType.TAG_CLOSE, '', 'div'], [lex.TokenType.EOF], ]); }); it('should parse an expansion forms with elements in it', () => { expect(tokenizeAndHumanizeParts( '{one.two, three, =4 {four a}}', {tokenizeExpansionForms: true})) .toEqual([ [lex.TokenType.EXPANSION_FORM_START], [lex.TokenType.RAW_TEXT, 'one.two'], [lex.TokenType.RAW_TEXT, 'three'], [lex.TokenType.EXPANSION_CASE_VALUE, '=4'], [lex.TokenType.EXPANSION_CASE_EXP_START], [lex.TokenType.TEXT, 'four '], [lex.TokenType.TAG_OPEN_START, '', 'b'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TEXT, 'a'], [lex.TokenType.TAG_CLOSE, '', 'b'], [lex.TokenType.EXPANSION_CASE_EXP_END], [lex.TokenType.EXPANSION_FORM_END], [lex.TokenType.EOF], ]); }); it('should parse an expansion forms containing an interpolation', () => { expect(tokenizeAndHumanizeParts( '{one.two, three, =4 {four {{a}}}}', {tokenizeExpansionForms: true})) .toEqual([ [lex.TokenType.EXPANSION_FORM_START], [lex.TokenType.RAW_TEXT, 'one.two'], [lex.TokenType.RAW_TEXT, 'three'], [lex.TokenType.EXPANSION_CASE_VALUE, '=4'], [lex.TokenType.EXPANSION_CASE_EXP_START], [lex.TokenType.TEXT, 'four {{a}}'], [lex.TokenType.EXPANSION_CASE_EXP_END], [lex.TokenType.EXPANSION_FORM_END], [lex.TokenType.EOF], ]); }); it('should parse nested expansion forms', () => { expect(tokenizeAndHumanizeParts( `{one.two, three, =4 { {xx, yy, =x {one}} }}`, {tokenizeExpansionForms: true})) .toEqual([ [lex.TokenType.EXPANSION_FORM_START], [lex.TokenType.RAW_TEXT, 'one.two'], [lex.TokenType.RAW_TEXT, 'three'], [lex.TokenType.EXPANSION_CASE_VALUE, '=4'], [lex.TokenType.EXPANSION_CASE_EXP_START], [lex.TokenType.EXPANSION_FORM_START], [lex.TokenType.RAW_TEXT, 'xx'], [lex.TokenType.RAW_TEXT, 'yy'], [lex.TokenType.EXPANSION_CASE_VALUE, '=x'], [lex.TokenType.EXPANSION_CASE_EXP_START], [lex.TokenType.TEXT, 'one'], [lex.TokenType.EXPANSION_CASE_EXP_END], [lex.TokenType.EXPANSION_FORM_END], [lex.TokenType.TEXT, ' '], [lex.TokenType.EXPANSION_CASE_EXP_END], [lex.TokenType.EXPANSION_FORM_END], [lex.TokenType.EOF], ]); }); }); describe('errors', () => { it('should report unescaped "{" on error', () => { expect(tokenizeAndHumanizeErrors(`

before { after

`, {tokenizeExpansionForms: true})) .toEqual([[ lex.TokenType.RAW_TEXT, `Unexpected character "EOF" (Do you have an unescaped "{" in your template? Use "{{ '{' }}") to escape it.)`, '0:21', ]]); }); it('should include 2 lines of context in message', () => { const src = '111\n222\n333\nE\n444\n555\n666\n'; const file = new ParseSourceFile(src, 'file://'); const location = new ParseLocation(file, 12, 123, 456); const span = new ParseSourceSpan(location, location); const error = new lex.TokenError('**ERROR**', null !, span); expect(error.toString()) .toEqual(`**ERROR** ("\n222\n333\n[ERROR ->]E\n444\n555\n"): file://@123:456`); }); }); describe('unicode characters', () => { it('should support unicode characters', () => { expect(tokenizeAndHumanizeSourceSpans(`

İ

`)).toEqual([ [lex.TokenType.TAG_OPEN_START, ''], [lex.TokenType.TEXT, 'İ'], [lex.TokenType.TAG_CLOSE, '

'], [lex.TokenType.EOF, ''], ]); }); }); describe('(processing escaped strings)', () => { it('should unescape standard escape sequences', () => { expect(tokenizeAndHumanizeParts('\\\' \\\' \\\'', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\' \' \''], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('\\" \\" \\"', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\" \" \"'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('\\` \\` \\`', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\` \` \`'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('\\\\ \\\\ \\\\', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\\ \\ \\'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('\\n \\n \\n', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\n \n \n'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('\\r \\r \\r', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\n \n \n'], // post processing converts `\r` to `\n` [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('\\v \\v \\v', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\v \v \v'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('\\t \\t \\t', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\t \t \t'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('\\b \\b \\b', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\b \b \b'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('\\f \\f \\f', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\f \f \f'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts( '\\\' \\" \\` \\\\ \\n \\r \\v \\t \\b \\f', {escapedString: true})) .toEqual([ [lex.TokenType.TEXT, '\' \" \` \\ \n \n \v \t \b \f'], [lex.TokenType.EOF], ]); }); it('should unescape null sequences', () => { expect(tokenizeAndHumanizeParts('\\0', {escapedString: true})).toEqual([ [lex.TokenType.EOF], ]); // \09 is not an octal number so the \0 is taken as EOF expect(tokenizeAndHumanizeParts('\\09', {escapedString: true})).toEqual([ [lex.TokenType.EOF], ]); }); it('should unescape octal sequences', () => { // \19 is read as an octal `\1` followed by a normal char `9` // \1234 is read as an octal `\123` followed by a normal char `4` // \999 is not an octal number so its backslash just gets removed. expect(tokenizeAndHumanizeParts( '\\001 \\01 \\1 \\12 \\223 \\19 \\2234 \\999', {escapedString: true})) .toEqual([ [lex.TokenType.TEXT, '\x01 \x01 \x01 \x0A \x93 \x019 \x934 999'], [lex.TokenType.EOF], ]); }); it('should unescape hex sequences', () => { expect(tokenizeAndHumanizeParts('\\x12 \\x4F \\xDC', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\x12 \x4F \xDC'], [lex.TokenType.EOF], ]); }); it('should report an error on an invalid hex sequence', () => { expect(tokenizeAndHumanizeErrors('\\xGG', {escapedString: true})).toEqual([ [null, 'Invalid hexadecimal escape sequence', '0:2'] ]); expect(tokenizeAndHumanizeErrors('abc \\x xyz', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, 'Invalid hexadecimal escape sequence', '0:6'] ]); expect(tokenizeAndHumanizeErrors('abc\\x', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, 'Unexpected character "EOF"', '0:5'] ]); }); it('should unescape fixed length Unicode sequences', () => { expect(tokenizeAndHumanizeParts('\\u0123 \\uABCD', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, '\u0123 \uABCD'], [lex.TokenType.EOF], ]); }); it('should error on an invalid fixed length Unicode sequence', () => { expect(tokenizeAndHumanizeErrors('\\uGGGG', {escapedString: true})).toEqual([ [null, 'Invalid hexadecimal escape sequence', '0:2'] ]); }); it('should unescape variable length Unicode sequences', () => { expect(tokenizeAndHumanizeParts( '\\u{01} \\u{ABC} \\u{1234} \\u{123AB}', {escapedString: true})) .toEqual([ [lex.TokenType.TEXT, '\u{01} \u{ABC} \u{1234} \u{123AB}'], [lex.TokenType.EOF], ]); }); it('should error on an invalid variable length Unicode sequence', () => { expect(tokenizeAndHumanizeErrors('\\u{GG}', {escapedString: true})).toEqual([ [null, 'Invalid hexadecimal escape sequence', '0:3'] ]); }); it('should unescape line continuations', () => { expect(tokenizeAndHumanizeParts('abc\\\ndef', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, 'abcdef'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeParts('\\\nx\\\ny\\\n', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, 'xy'], [lex.TokenType.EOF], ]); }); it('should remove backslash from "non-escape" sequences', () => { expect(tokenizeAndHumanizeParts('\a \g \~', {escapedString: true})).toEqual([ [lex.TokenType.TEXT, 'a g ~'], [lex.TokenType.EOF], ]); }); it('should unescape sequences in plain text', () => { expect(tokenizeAndHumanizeParts('abc\ndef\\nghi\\tjkl\\`\\\'\\"mno', {escapedString: true})) .toEqual([ [lex.TokenType.TEXT, 'abc\ndef\nghi\tjkl`\'"mno'], [lex.TokenType.EOF], ]); }); it('should unescape sequences in raw text', () => { expect(tokenizeAndHumanizeParts( '', {escapedString: true})) .toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'script'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.RAW_TEXT, 'abc\ndef\nghi\tjkl`\'"mno'], [lex.TokenType.TAG_CLOSE, '', 'script'], [lex.TokenType.EOF], ]); }); it('should unescape sequences in escapable raw text', () => { expect(tokenizeAndHumanizeParts( 'abc\ndef\\nghi\\tjkl\\`\\\'\\"mno', {escapedString: true})) .toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'title'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.ESCAPABLE_RAW_TEXT, 'abc\ndef\nghi\tjkl`\'"mno'], [lex.TokenType.TAG_CLOSE, '', 'title'], [lex.TokenType.EOF], ]); }); it('should parse over escape sequences in tag definitions', () => { expect(tokenizeAndHumanizeParts('', {escapedString: true})) .toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_VALUE, 'b'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_NAME, '', 'c'], [lex.TokenType.ATTR_QUOTE, '\''], [lex.TokenType.ATTR_VALUE, 'd'], [lex.TokenType.ATTR_QUOTE, '\''], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.EOF], ]); }); it('should parse over escaped new line in tag definitions', () => { const text = ''; expect(tokenizeAndHumanizeParts(text, {escapedString: true})).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TAG_CLOSE, '', 't'], [lex.TokenType.EOF], ]); }); it('should parse over escaped characters in tag definitions', () => { const text = ''; expect(tokenizeAndHumanizeParts(text, {escapedString: true})).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TAG_CLOSE, '', 't'], [lex.TokenType.EOF], ]); }); it('should unescape characters in tag names', () => { const text = ''; expect(tokenizeAndHumanizeParts(text, {escapedString: true})).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 'td'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TAG_CLOSE, '', 'td'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeSourceSpans(text, {escapedString: true})).toEqual([ [lex.TokenType.TAG_OPEN_START, ''], [lex.TokenType.TAG_CLOSE, ''], [lex.TokenType.EOF, ''], ]); }); it('should unescape characters in attributes', () => { const text = ''; expect(tokenizeAndHumanizeParts(text, {escapedString: true})).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'd'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.ATTR_VALUE, 'e'], [lex.TokenType.ATTR_QUOTE, '"'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TAG_CLOSE, '', 't'], [lex.TokenType.EOF], ]); }); it('should parse over escaped new line in attribute values', () => { const text = ''; expect(tokenizeAndHumanizeParts(text, {escapedString: true})).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.ATTR_NAME, '', 'a'], [lex.TokenType.ATTR_VALUE, 'b'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TAG_CLOSE, '', 't'], [lex.TokenType.EOF], ]); }); it('should tokenize the correct span when there are escape sequences', () => { const text = 'selector: "app-root",\ntemplate: "line 1\\n\\"line 2\\"\\nline 3",\ninputs: []'; const range = { startPos: 33, startLine: 1, startCol: 10, endPos: 59, }; expect(tokenizeAndHumanizeParts(text, {range, escapedString: true})).toEqual([ [lex.TokenType.TEXT, 'line 1\n"line 2"\nline 3'], [lex.TokenType.EOF], ]); expect(tokenizeAndHumanizeSourceSpans(text, {range, escapedString: true})).toEqual([ [lex.TokenType.TEXT, 'line 1\\n\\"line 2\\"\\nline 3'], [lex.TokenType.EOF, ''], ]); }); it('should account for escape sequences when computing source spans ', () => { const text = 'line 1\n' + // <- unescaped line break 'line 2\\n' + // <- escaped line break 'line 3\\\n' + // <- line continuation ''; expect(tokenizeAndHumanizeParts(text, {escapedString: true})).toEqual([ [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TEXT, 'line 1'], [lex.TokenType.TAG_CLOSE, '', 't'], [lex.TokenType.TEXT, '\n'], [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TEXT, 'line 2'], [lex.TokenType.TAG_CLOSE, '', 't'], [lex.TokenType.TEXT, '\n'], [lex.TokenType.TAG_OPEN_START, '', 't'], [lex.TokenType.TAG_OPEN_END], [lex.TokenType.TEXT, 'line 3'], // <- line continuation does not appear in token [lex.TokenType.TAG_CLOSE, '', 't'], [lex.TokenType.EOF] ]); expect(tokenizeAndHumanizeLineColumn(text, {escapedString: true})).toEqual([ [lex.TokenType.TAG_OPEN_START, '0:0'], [lex.TokenType.TAG_OPEN_END, '0:2'], [lex.TokenType.TEXT, '0:3'], [lex.TokenType.TAG_CLOSE, '0:9'], [lex.TokenType.TEXT, '0:13'], // <- real newline increments the row [lex.TokenType.TAG_OPEN_START, '1:0'], [lex.TokenType.TAG_OPEN_END, '1:2'], [lex.TokenType.TEXT, '1:3'], [lex.TokenType.TAG_CLOSE, '1:9'], [lex.TokenType.TEXT, '1:13'], // <- escaped newline does not increment the row [lex.TokenType.TAG_OPEN_START, '1:15'], [lex.TokenType.TAG_OPEN_END, '1:17'], [lex.TokenType.TEXT, '1:18'], // <- the line continuation increments the row [lex.TokenType.TAG_CLOSE, '2:0'], [lex.TokenType.EOF, '2:4'], ]); expect(tokenizeAndHumanizeSourceSpans(text, {escapedString: true})).toEqual([ [lex.TokenType.TAG_OPEN_START, ''], [lex.TokenType.TEXT, 'line 1'], [lex.TokenType.TAG_CLOSE, ''], [lex.TokenType.TEXT, '\n'], [lex.TokenType.TAG_OPEN_START, ''], [lex.TokenType.TEXT, 'line 2'], [lex.TokenType.TAG_CLOSE, ''], [lex.TokenType.TEXT, '\\n'], [lex.TokenType.TAG_OPEN_START, ''], [lex.TokenType.TEXT, 'line 3\\\n'], [lex.TokenType.TAG_CLOSE, ''], [lex.TokenType.EOF, ''] ]); }); }); }); } function tokenizeWithoutErrors(input: string, options?: lex.TokenizeOptions): lex.Token[] { const tokenizeResult = lex.tokenize(input, 'someUrl', getHtmlTagDefinition, options); if (tokenizeResult.errors.length > 0) { const errorString = tokenizeResult.errors.join('\n'); throw new Error(`Unexpected parse errors:\n${errorString}`); } return tokenizeResult.tokens; } function tokenizeAndHumanizeParts(input: string, options?: lex.TokenizeOptions): any[] { return tokenizeWithoutErrors(input, options).map(token => [token.type].concat(token.parts)); } function tokenizeAndHumanizeSourceSpans(input: string, options?: lex.TokenizeOptions): any[] { return tokenizeWithoutErrors(input, options) .map(token => [token.type, token.sourceSpan.toString()]); } function humanizeLineColumn(location: ParseLocation): string { return `${location.line}:${location.col}`; } function tokenizeAndHumanizeLineColumn(input: string, options?: lex.TokenizeOptions): any[] { return tokenizeWithoutErrors(input, options) .map(token => [token.type, humanizeLineColumn(token.sourceSpan.start)]); } function tokenizeAndHumanizeErrors(input: string, options?: lex.TokenizeOptions): any[] { return lex.tokenize(input, 'someUrl', getHtmlTagDefinition, options) .errors.map(e => [e.tokenType, e.msg, humanizeLineColumn(e.span.start)]); }