2016-04-12 09:40:37 -07:00
|
|
|
import {
|
|
|
|
|
ddescribe,
|
|
|
|
|
describe,
|
|
|
|
|
it,
|
|
|
|
|
iit,
|
|
|
|
|
xit,
|
|
|
|
|
expect,
|
|
|
|
|
beforeEach,
|
|
|
|
|
afterEach
|
|
|
|
|
} from 'angular2/testing_internal';
|
2015-11-10 15:56:25 -08:00
|
|
|
import {BaseException} from 'angular2/src/facade/exceptions';
|
|
|
|
|
|
2016-04-12 09:40:37 -07:00
|
|
|
import {
|
|
|
|
|
tokenizeHtml,
|
|
|
|
|
HtmlToken,
|
|
|
|
|
HtmlTokenType,
|
|
|
|
|
HtmlTokenError
|
|
|
|
|
} from 'angular2/src/compiler/html_lexer';
|
2015-11-10 15:56:25 -08:00
|
|
|
import {ParseSourceSpan, ParseLocation, ParseSourceFile} from 'angular2/src/compiler/parse_util';
|
2015-10-07 09:34:21 -07:00
|
|
|
|
|
|
|
|
export function main() {
|
|
|
|
|
describe('HtmlLexer', () => {
|
|
|
|
|
describe('line/column numbers', () => {
|
|
|
|
|
it('should work without newlines', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeLineColumn('<t>a</t>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, '0:0'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END, '0:2'],
|
|
|
|
|
[HtmlTokenType.TEXT, '0:3'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, '0:4'],
|
|
|
|
|
[HtmlTokenType.EOF, '0:8']
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should work with one newline', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeLineColumn('<t>\na</t>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, '0:0'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END, '0:2'],
|
|
|
|
|
[HtmlTokenType.TEXT, '0:3'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, '1:1'],
|
|
|
|
|
[HtmlTokenType.EOF, '1:5']
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should work with multiple newlines', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeLineColumn('<t\n>\na</t>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, '0:0'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END, '1:0'],
|
|
|
|
|
[HtmlTokenType.TEXT, '1:1'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, '2:1'],
|
|
|
|
|
[HtmlTokenType.EOF, '2:5']
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
2015-12-04 23:12:31 -08:00
|
|
|
|
|
|
|
|
it('should work with CR and LF', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeLineColumn('<t\n>\r\na\r</t>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, '0:0'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END, '1:0'],
|
|
|
|
|
[HtmlTokenType.TEXT, '1:1'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, '2:1'],
|
|
|
|
|
[HtmlTokenType.EOF, '2:5']
|
|
|
|
|
]);
|
2015-12-04 23:12:31 -08:00
|
|
|
});
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('comments', () => {
|
|
|
|
|
it('should parse comments', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<!--t\ne\rs\r\nt-->'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.COMMENT_START],
|
|
|
|
|
[HtmlTokenType.RAW_TEXT, 't\ne\ns\nt'],
|
|
|
|
|
[HtmlTokenType.COMMENT_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
2015-12-04 23:12:31 -08:00
|
|
|
it('should store the locations',
|
2016-04-12 09:40:37 -07:00
|
|
|
() => {expect(tokenizeAndHumanizeSourceSpans('<!--t\ne\rs\r\nt-->'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.COMMENT_START, '<!--'],
|
|
|
|
|
[HtmlTokenType.RAW_TEXT, 't\ne\rs\r\nt'],
|
|
|
|
|
[HtmlTokenType.COMMENT_END, '-->'],
|
|
|
|
|
[HtmlTokenType.EOF, '']
|
|
|
|
|
])});
|
2015-10-07 09:34:21 -07:00
|
|
|
|
|
|
|
|
it('should report <!- without -', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeErrors('<!-a'))
|
|
|
|
|
.toEqual([[HtmlTokenType.COMMENT_START, 'Unexpected character "a"', '0:3']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should report missing end comment', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeErrors('<!--'))
|
|
|
|
|
.toEqual([[HtmlTokenType.RAW_TEXT, 'Unexpected character "EOF"', '0:4']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('doctype', () => {
|
|
|
|
|
it('should parse doctypes', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<!doctype html>'))
|
|
|
|
|
.toEqual([[HtmlTokenType.DOC_TYPE, 'doctype html'], [HtmlTokenType.EOF]]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should store the locations', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans('<!doctype html>'))
|
|
|
|
|
.toEqual([[HtmlTokenType.DOC_TYPE, '<!doctype html>'], [HtmlTokenType.EOF, '']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should report missing end doctype', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeErrors('<!'))
|
|
|
|
|
.toEqual([[HtmlTokenType.DOC_TYPE, 'Unexpected character "EOF"', '0:2']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2015-12-21 11:32:58 -08:00
|
|
|
describe('CDATA', () => {
|
|
|
|
|
it('should parse CDATA', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<![CDATA[t\ne\rs\r\nt]]>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.CDATA_START],
|
|
|
|
|
[HtmlTokenType.RAW_TEXT, 't\ne\ns\nt'],
|
|
|
|
|
[HtmlTokenType.CDATA_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should store the locations', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans('<![CDATA[t\ne\rs\r\nt]]>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.CDATA_START, '<![CDATA['],
|
|
|
|
|
[HtmlTokenType.RAW_TEXT, 't\ne\rs\r\nt'],
|
|
|
|
|
[HtmlTokenType.CDATA_END, ']]>'],
|
|
|
|
|
[HtmlTokenType.EOF, '']
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
2015-12-21 11:32:58 -08:00
|
|
|
it('should report <![ without CDATA[', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeErrors('<![a'))
|
|
|
|
|
.toEqual([[HtmlTokenType.CDATA_START, 'Unexpected character "a"', '0:3']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should report missing end cdata', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeErrors('<![CDATA['))
|
|
|
|
|
.toEqual([[HtmlTokenType.RAW_TEXT, 'Unexpected character "EOF"', '0:9']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('open tags', () => {
|
|
|
|
|
it('should parse open tags without prefix', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<test>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'test'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse namespace prefix', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<ns1:test>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, 'ns1', 'test'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse void tags', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<test/>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'test'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END_VOID],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
2015-12-06 13:12:41 -08:00
|
|
|
it('should allow whitespace after the tag name', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<test >'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'test'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should store the locations', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans('<test>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, '<test'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END, '>'],
|
|
|
|
|
[HtmlTokenType.EOF, '']
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('attributes', () => {
|
|
|
|
|
it('should parse attributes without prefix', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<t a>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'a'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse attributes with prefix', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<t ns1:a>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, 'ns1', 'a'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse attributes whose prefix is not valid', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<t (ns1:a)>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, '(ns1:a)'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse attributes with single quote value', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts("<t a='b'>"))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'a'],
|
|
|
|
|
[HtmlTokenType.ATTR_VALUE, 'b'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse attributes with double quote value', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<t a="b">'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'a'],
|
|
|
|
|
[HtmlTokenType.ATTR_VALUE, 'b'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse attributes with unquoted value', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<t a=b>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'a'],
|
|
|
|
|
[HtmlTokenType.ATTR_VALUE, 'b'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should allow whitespace', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<t a = b >'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'a'],
|
|
|
|
|
[HtmlTokenType.ATTR_VALUE, 'b'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse attributes with entities in values', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<t a="AA">'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'a'],
|
|
|
|
|
[HtmlTokenType.ATTR_VALUE, 'AA'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-11-10 15:56:25 -08:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should not decode entities without trailing ";"', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<t a="&" b="c&&d">'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'a'],
|
|
|
|
|
[HtmlTokenType.ATTR_VALUE, '&'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'b'],
|
|
|
|
|
[HtmlTokenType.ATTR_VALUE, 'c&&d'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-11-10 15:56:25 -08:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse attributes with "&" in values', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('<t a="b && c &">'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'a'],
|
|
|
|
|
[HtmlTokenType.ATTR_VALUE, 'b && c &'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
2015-12-04 23:12:31 -08:00
|
|
|
it('should parse values with CR and LF', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts("<t a='t\ne\rs\r\nt'>"))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 't'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'a'],
|
|
|
|
|
[HtmlTokenType.ATTR_VALUE, 't\ne\ns\nt'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-12-04 23:12:31 -08:00
|
|
|
});
|
|
|
|
|
|
2015-10-07 09:34:21 -07:00
|
|
|
it('should store the locations', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans('<t a=b>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, '<t'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, 'a'],
|
|
|
|
|
[HtmlTokenType.ATTR_VALUE, 'b'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END, '>'],
|
|
|
|
|
[HtmlTokenType.EOF, '']
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('closing tags', () => {
|
|
|
|
|
it('should parse closing tags without prefix', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('</test>'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TAG_CLOSE, null, 'test'], [HtmlTokenType.EOF]]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse closing tags with prefix', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('</ns1:test>'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TAG_CLOSE, 'ns1', 'test'], [HtmlTokenType.EOF]]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should allow whitespace', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('</ test >'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TAG_CLOSE, null, 'test'], [HtmlTokenType.EOF]]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should store the locations', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans('</test>'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TAG_CLOSE, '</test>'], [HtmlTokenType.EOF, '']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should report missing name after </', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeErrors('</'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TAG_CLOSE, 'Unexpected character "EOF"', '0:2']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should report missing >', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeErrors('</test'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TAG_CLOSE, 'Unexpected character "EOF"', '0:6']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('entities', () => {
|
|
|
|
|
it('should parse named entities', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('a&b'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'a&b'], [HtmlTokenType.EOF]]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse hexadecimal entities', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('AA'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'AA'], [HtmlTokenType.EOF]]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should parse decimal entities', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('A'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'A'], [HtmlTokenType.EOF]]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should store the locations', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans('a&b'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'a&b'], [HtmlTokenType.EOF, '']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
2015-11-10 15:56:25 -08:00
|
|
|
it('should report malformed/unknown entities', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeErrors('&tbo;'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[
|
|
|
|
|
HtmlTokenType.TEXT,
|
|
|
|
|
'Unknown entity "tbo" - use the "&#<decimal>;" or "&#x<hex>;" syntax',
|
|
|
|
|
'0:0'
|
|
|
|
|
]
|
|
|
|
|
]);
|
|
|
|
|
expect(tokenizeAndHumanizeErrors('&#asdf;'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'Unexpected character "s"', '0:3']]);
|
|
|
|
|
expect(tokenizeAndHumanizeErrors('
sdf;'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'Unexpected character "s"', '0:4']]);
|
|
|
|
|
|
|
|
|
|
expect(tokenizeAndHumanizeErrors('઼'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'Unexpected character "EOF"', '0:6']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('regular text', () => {
|
|
|
|
|
it('should parse text', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('a'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'a'], [HtmlTokenType.EOF]]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
2015-12-04 23:12:31 -08:00
|
|
|
it('should handle CR & LF', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('t\ne\rs\r\nt'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 't\ne\ns\nt'], [HtmlTokenType.EOF]]);
|
2015-12-04 23:12:31 -08:00
|
|
|
});
|
|
|
|
|
|
2015-10-07 09:34:21 -07:00
|
|
|
it('should parse entities', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('a&b'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'a&b'], [HtmlTokenType.EOF]]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
2015-11-10 15:56:25 -08:00
|
|
|
it('should parse text starting with "&"', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('a && b &'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'a && b &'], [HtmlTokenType.EOF]]);
|
2015-11-10 15:56:25 -08:00
|
|
|
});
|
|
|
|
|
|
2015-10-07 09:34:21 -07:00
|
|
|
it('should store the locations', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans('a'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, 'a'], [HtmlTokenType.EOF, '']]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
2015-12-06 13:11:00 -08:00
|
|
|
|
|
|
|
|
it('should allow "<" in text nodes', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('{{ a < b ? c : d }}'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, '{{ a < b ? c : d }}'], [HtmlTokenType.EOF]]);
|
2015-12-06 13:11:00 -08:00
|
|
|
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans('<p>a<b</p>'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, '<p'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END, '>'],
|
|
|
|
|
[HtmlTokenType.TEXT, 'a<b'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, '</p>'],
|
|
|
|
|
[HtmlTokenType.EOF, ''],
|
|
|
|
|
]);
|
2015-12-06 13:12:41 -08:00
|
|
|
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('< a>'))
|
|
|
|
|
.toEqual([[HtmlTokenType.TEXT, '< a>'], [HtmlTokenType.EOF]]);
|
2015-12-06 13:11:00 -08:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
// TODO(vicb): make the lexer aware of Angular expressions
|
|
|
|
|
// see https://github.com/angular/angular/issues/5679
|
|
|
|
|
it('should parse valid start tag in interpolation', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts('{{ a <b && c > d }}'))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TEXT, '{{ a '],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'b'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, '&&'],
|
|
|
|
|
[HtmlTokenType.ATTR_NAME, null, 'c'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.TEXT, ' d }}'],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-12-06 13:11:00 -08:00
|
|
|
});
|
|
|
|
|
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('raw text', () => {
|
|
|
|
|
it('should parse text', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts(`<script>t\ne\rs\r\nt</script>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'script'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.RAW_TEXT, 't\ne\ns\nt'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, null, 'script'],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should not detect entities', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts(`<script>&</SCRIPT>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'script'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.RAW_TEXT, '&'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, null, 'script'],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should ignore other opening tags', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts(`<script>a<div></script>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'script'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.RAW_TEXT, 'a<div>'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, null, 'script'],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should ignore other closing tags', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts(`<script>a</test></script>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'script'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.RAW_TEXT, 'a</test>'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, null, 'script'],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should store the locations', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans(`<script>a</script>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, '<script'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END, '>'],
|
|
|
|
|
[HtmlTokenType.RAW_TEXT, 'a'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, '</script>'],
|
|
|
|
|
[HtmlTokenType.EOF, '']
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
describe('escapable raw text', () => {
|
|
|
|
|
it('should parse text', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts(`<title>t\ne\rs\r\nt</title>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'title'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.ESCAPABLE_RAW_TEXT, 't\ne\ns\nt'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, null, 'title'],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should detect entities', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts(`<title>&</title>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'title'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.ESCAPABLE_RAW_TEXT, '&'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, null, 'title'],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should ignore other opening tags', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts(`<title>a<div></title>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'title'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.ESCAPABLE_RAW_TEXT, 'a<div>'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, null, 'title'],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should ignore other closing tags', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeParts(`<title>a</test></title>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, null, 'title'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END],
|
|
|
|
|
[HtmlTokenType.ESCAPABLE_RAW_TEXT, 'a</test>'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, null, 'title'],
|
|
|
|
|
[HtmlTokenType.EOF]
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it('should store the locations', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans(`<title>a</title>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, '<title'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END, '>'],
|
|
|
|
|
[HtmlTokenType.ESCAPABLE_RAW_TEXT, 'a'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, '</title>'],
|
|
|
|
|
[HtmlTokenType.EOF, '']
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
|
|
|
|
|
});
|
|
|
|
|
|
2015-11-10 15:56:25 -08:00
|
|
|
describe('errors', () => {
|
|
|
|
|
it('should include 2 lines of context in message', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
let src = "111\n222\n333\nE\n444\n555\n666\n";
|
2015-11-10 15:56:25 -08:00
|
|
|
let file = new ParseSourceFile(src, 'file://');
|
|
|
|
|
let location = new ParseLocation(file, 12, 123, 456);
|
2016-02-16 16:46:51 -08:00
|
|
|
let span = new ParseSourceSpan(location, location);
|
|
|
|
|
let error = new HtmlTokenError('**ERROR**', null, span);
|
2015-11-10 15:56:25 -08:00
|
|
|
expect(error.toString())
|
|
|
|
|
.toEqual(`**ERROR** ("\n222\n333\n[ERROR ->]E\n444\n555\n"): file://@123:456`);
|
|
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2015-12-21 11:32:58 -08:00
|
|
|
describe('unicode characters', () => {
|
|
|
|
|
it('should support unicode characters', () => {
|
2016-04-12 09:40:37 -07:00
|
|
|
expect(tokenizeAndHumanizeSourceSpans(`<p>İ</p>`))
|
|
|
|
|
.toEqual([
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_START, '<p'],
|
|
|
|
|
[HtmlTokenType.TAG_OPEN_END, '>'],
|
|
|
|
|
[HtmlTokenType.TEXT, 'İ'],
|
|
|
|
|
[HtmlTokenType.TAG_CLOSE, '</p>'],
|
|
|
|
|
[HtmlTokenType.EOF, '']
|
|
|
|
|
]);
|
2015-12-21 11:32:58 -08:00
|
|
|
});
|
|
|
|
|
});
|
|
|
|
|
|
2015-10-07 09:34:21 -07:00
|
|
|
});
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function tokenizeWithoutErrors(input: string): HtmlToken[] {
|
|
|
|
|
var tokenizeResult = tokenizeHtml(input, 'someUrl');
|
|
|
|
|
if (tokenizeResult.errors.length > 0) {
|
|
|
|
|
var errorString = tokenizeResult.errors.join('\n');
|
|
|
|
|
throw new BaseException(`Unexpected parse errors:\n${errorString}`);
|
|
|
|
|
}
|
|
|
|
|
return tokenizeResult.tokens;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function tokenizeAndHumanizeParts(input: string): any[] {
|
|
|
|
|
return tokenizeWithoutErrors(input).map(token => [<any>token.type].concat(token.parts));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function tokenizeAndHumanizeSourceSpans(input: string): any[] {
|
|
|
|
|
return tokenizeWithoutErrors(input).map(token => [<any>token.type, token.sourceSpan.toString()]);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function humanizeLineColumn(location: ParseLocation): string {
|
|
|
|
|
return `${location.line}:${location.col}`;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function tokenizeAndHumanizeLineColumn(input: string): any[] {
|
2016-04-12 09:40:37 -07:00
|
|
|
return tokenizeWithoutErrors(input)
|
|
|
|
|
.map(token => [<any>token.type, humanizeLineColumn(token.sourceSpan.start)]);
|
2015-10-07 09:34:21 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function tokenizeAndHumanizeErrors(input: string): any[] {
|
|
|
|
|
return tokenizeHtml(input, 'someUrl')
|
2016-04-12 09:40:37 -07:00
|
|
|
.errors.map(tokenError => [
|
|
|
|
|
<any>tokenError.tokenType,
|
|
|
|
|
tokenError.msg,
|
|
|
|
|
humanizeLineColumn(tokenError.span.start)
|
|
|
|
|
]);
|
2015-10-07 09:34:21 -07:00
|
|
|
}
|
