Commit 5333e28106b8438f76b07b855c0c5fe4b3570947

Michael Schmidt 2021-10-19T19:34:41

Added regex coverage (#3138)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index c8de6ee..f8f4941 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -57,3 +57,16 @@ jobs:
           node-version: 14.x
       - run: npm ci
       - run: npm run lint:ci
+
+  coverage:
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Use Node.js 14.x
+        uses: actions/setup-node@v1
+        with:
+          node-version: 14.x
+      - run: npm ci
+      - run: npm run regex-coverage
diff --git a/package.json b/package.json
index 1961040..e15083f 100755
--- a/package.json
+++ b/package.json
@@ -14,6 +14,7 @@
 		"lint": "eslint . --cache",
 		"lint:fix": "npm run lint -- --fix",
 		"lint:ci": "eslint . --max-warnings 0",
+		"regex-coverage": "mocha tests/coverage.js",
 		"test:aliases": "mocha tests/aliases-test.js",
 		"test:core": "mocha tests/core/**/*.js",
 		"test:dependencies": "mocha tests/dependencies-test.js",
diff --git a/tests/coverage.js b/tests/coverage.js
new file mode 100644
index 0000000..cd71757
--- /dev/null
+++ b/tests/coverage.js
@@ -0,0 +1,260 @@
+'use strict';
+
+const TestDiscovery = require('./helper/test-discovery');
+const TestCase = require('./helper/test-case');
+const PrismLoader = require('./helper/prism-loader');
+const { BFS, BFSPathToPrismTokenPath } = require('./helper/util');
+const { assert } = require('chai');
+const components = require('../components.json');
+const ALL_LANGUAGES = [...Object.keys(components.languages).filter(k => k !== 'meta')];
+
+
+describe('Pattern test coverage', function () {
+	/**
+	 * @type {Map<string, PatternData>}
+	 * @typedef PatternData
+	 * @property {RegExp} pattern
+	 * @property {string} language
+	 * @property {Set<string>} from
+	 * @property {RegExpExecArray[]} matches
+	 */
+	const patterns = new Map();
+
+	/**
+	 * @param {string | string[]} languages
+	 * @returns {import("./helper/prism-loader").Prism}
+	 */
+	function createInstance(languages) {
+		const Prism = PrismLoader.createInstance(languages);
+
+		BFS(Prism.languages, (path, object) => {
+			const { key, value } = path[path.length - 1];
+			const tokenPath = BFSPathToPrismTokenPath(path);
+
+			if (Object.prototype.toString.call(value) == '[object RegExp]') {
+				const regex = makeGlobal(value);
+				object[key] = regex;
+
+				const patternKey = String(regex);
+				let data = patterns.get(patternKey);
+				if (!data) {
+					data = {
+						pattern: regex,
+						language: path[1].key,
+						from: new Set([tokenPath]),
+						matches: []
+					};
+					patterns.set(patternKey, data);
+				} else {
+					data.from.add(tokenPath);
+				}
+
+				regex.exec = string => {
+					let match = RegExp.prototype.exec.call(regex, string);
+					if (match) {
+						data.matches.push(match);
+					}
+					return match;
+				};
+			}
+		});
+
+		return Prism;
+	}
+
+	describe('Register all patterns', function () {
+		it('all', function () {
+			this.slow(10 * 1000);
+			// This will cause ALL regexes of Prism to be registered in the patterns map.
+			// (Languages that don't have any tests can't be caught otherwise.)
+			createInstance(ALL_LANGUAGES);
+		});
+	});
+
+	describe('Run all language tests', function () {
+		// define tests for all tests in all languages in the test suite
+		for (const [languageIdentifier, files] of TestDiscovery.loadAllTests()) {
+			it(languageIdentifier, function () {
+				this.timeout(10 * 1000);
+
+				for (const filePath of files) {
+					try {
+						TestCase.run({
+							languageIdentifier,
+							filePath,
+							updateMode: 'none',
+							createInstance
+						});
+					} catch (error) {
+						// we don't case about whether the test succeeds,
+						// we just want to gather usage data
+					}
+				}
+			});
+		}
+	});
+
+	describe('Coverage', function () {
+		for (const language of ALL_LANGUAGES) {
+			describe(language, function () {
+				it(`- should cover all patterns`, function () {
+					const untested = getAllOf(language).filter(d => d.matches.length === 0);
+					if (untested.length === 0) {
+						return;
+					}
+
+					const problems = untested.map(data => {
+						return formatProblem(data, [
+							'This pattern is completely untested. Add test files that match this pattern.'
+						]);
+					});
+
+					assert.fail([
+						`${problems.length} pattern(s) are untested:\n`
+						+ 'You can learn more about writing tests at https://prismjs.com/test-suite.html#writing-tests',
+						...problems
+					].join('\n\n'));
+				});
+
+				it(`- should exhaustively cover all keywords in keyword lists`, function () {
+					const problems = [];
+
+					for (const data of getAllOf(language)) {
+						if (data.matches.length === 0) {
+							// don't report the same pattern twice
+							continue;
+						}
+
+						const keywords = getKeywordList(data.pattern);
+						if (!keywords) {
+							continue;
+						}
+						const keywordCount = keywords.size;
+
+						data.matches.forEach(([m]) => {
+							if (data.pattern.ignoreCase) {
+								m = m.toUpperCase();
+							}
+							keywords.delete(m);
+						});
+
+						if (keywords.size > 0) {
+							problems.push(formatProblem(data, [
+								`Add test files to test all keywords. The following keywords (${keywords.size}/${keywordCount}) are untested:`,
+								...[...keywords].map(k => `    ${k}`)
+							]));
+						}
+					}
+
+					if (problems.length === 0) {
+						return;
+					}
+
+					assert.fail([
+						`${problems.length} keyword list(s) are not exhaustively tested:\n`
+						+ 'You can learn more about writing tests at https://prismjs.com/test-suite.html#writing-tests',
+						...problems
+					].join('\n\n'));
+				});
+			});
+		}
+	});
+
+	/**
+	 * @param {string} language
+	 * @returns {PatternData[]}
+	 */
+	function getAllOf(language) {
+		return [...patterns.values()].filter(d => d.language === language);
+	}
+
+	/**
+	 * @param {string} string
+	 * @param {number} maxLength
+	 * @returns {string}
+	 */
+	function short(string, maxLength) {
+		if (string.length > maxLength) {
+			return string.slice(0, maxLength - 1) + '…';
+		} else {
+			return string;
+		}
+	}
+
+	/**
+	 * If the given pattern string describes a keyword list, all keyword will be returned. Otherwise, `null` will be
+	 * returned.
+	 *
+	 * @param {RegExp} pattern
+	 * @returns {Set<string> | null}
+	 */
+	function getKeywordList(pattern) {
+		// Right now, only keyword lists of the form /\b(?:foo|bar)\b/ are supported.
+		// In the future, we might want to convert these regexes to NFAs and iterate all words to cover more complex
+		// keyword lists and even operator and punctuation lists.
+
+		let source = pattern.source.replace(/^\\b|\\b$/g, '');
+		if (source.startsWith('(?:') && source.endsWith(')')) {
+			source = source.slice('(?:'.length, source.length - ')'.length);
+		}
+
+		if (/^\w+(?:\|\w+)*$/.test(source)) {
+			if (pattern.ignoreCase) {
+				source = source.toUpperCase();
+			}
+			return new Set(source.split(/\|/g));
+		} else {
+			return null;
+		}
+	}
+
+	/**
+	 * @param {Iterable<string>} occurrences
+	 * @returns {{ origin: string; otherOccurrences: string[] }}
+	 */
+	function splitOccurrences(occurrences) {
+		const all = [...occurrences];
+		return {
+			origin: all[0],
+			otherOccurrences: all.slice(1),
+		};
+	}
+
+	/**
+	 * @param {PatternData} data
+	 * @param {string[]} messageLines
+	 * @returns {string}
+	 */
+	function formatProblem(data, messageLines) {
+		const { origin, otherOccurrences } = splitOccurrences(data.from);
+
+		const lines = [
+			`${origin}:`,
+			short(String(data.pattern), 100),
+			'',
+			...messageLines,
+		];
+
+		if (otherOccurrences.length) {
+			lines.push(
+				'',
+				'Other occurrences of this pattern:',
+				...otherOccurrences.map(o => `- ${o}`)
+			);
+		}
+
+		return lines.join('\n    ');
+	}
+});
+
+/**
+ * @param {RegExp} regex
+ * @returns {RegExp}
+ */
+function makeGlobal(regex) {
+	if (regex.global) {
+		return regex;
+	} else {
+		return RegExp(regex.source, regex.flags + 'g');
+	}
+}
diff --git a/tests/helper/test-case.js b/tests/helper/test-case.js
index 3454d77..d69e2c3 100644
--- a/tests/helper/test-case.js
+++ b/tests/helper/test-case.js
@@ -1,6 +1,7 @@
 'use strict';
 
 const fs = require('fs');
+const path = require('path');
 const { assert } = require('chai');
 const Prettier = require('prettier');
 const PrismLoader = require('./prism-loader');
@@ -12,6 +13,12 @@ const TokenStreamTransformer = require('./token-stream-transformer');
  */
 
 /**
+ * @param {string[]} languages
+ * @returns {Prism}
+ */
+const defaultCreateInstance = (languages) => PrismLoader.createInstance(languages);
+
+/**
  * Handles parsing and printing of a test case file.
  *
  * A test case file consists of at most three parts, separated by a line of at least 10 dashes.
@@ -298,6 +305,29 @@ module.exports = {
 	TestCaseFile,
 
 	/**
+	 * Runs the given test file and asserts the result.
+	 *
+	 * This function will determine what kind of test files the given file is and call the appropriate method to run the
+	 * test.
+	 *
+	 * @param {RunOptions} options
+	 * @returns {void}
+	 *
+	 * @typedef RunOptions
+	 * @property {string} languageIdentifier
+	 * @property {string} filePath
+	 * @property {"none" | "insert" | "update"} updateMode
+	 * @property {(languages: string[]) => Prism} [createInstance]
+	 */
+	run(options) {
+		if (path.extname(options.filePath) === '.test') {
+			this.runTestCase(options.languageIdentifier, options.filePath, options.updateMode, options.createInstance);
+		} else {
+			this.runTestsWithHooks(options.languageIdentifier, require(options.filePath), options.createInstance);
+		}
+	},
+
+	/**
 	 * Runs the given test case file and asserts the result
 	 *
 	 * The passed language identifier can either be a language like "css" or a composed language
@@ -312,13 +342,16 @@ module.exports = {
 	 * @param {string} languageIdentifier
 	 * @param {string} filePath
 	 * @param {"none" | "insert" | "update"} updateMode
+	 * @param {(languages: string[]) => Prism} [createInstance]
 	 */
-	runTestCase(languageIdentifier, filePath, updateMode) {
+	runTestCase(languageIdentifier, filePath, updateMode, createInstance = defaultCreateInstance) {
+		let runner;
 		if (/\.html\.test$/i.test(filePath)) {
-			this.runTestCaseWithRunner(languageIdentifier, filePath, updateMode, new HighlightHTMLRunner());
+			runner = new HighlightHTMLRunner();
 		} else {
-			this.runTestCaseWithRunner(languageIdentifier, filePath, updateMode, new TokenizeJSONRunner());
+			runner = new TokenizeJSONRunner();
 		}
+		this.runTestCaseWithRunner(languageIdentifier, filePath, updateMode, runner, createInstance);
 	},
 
 	/**
@@ -326,13 +359,14 @@ module.exports = {
 	 * @param {string} filePath
 	 * @param {"none" | "insert" | "update"} updateMode
 	 * @param {Runner<T>} runner
+	 * @param {(languages: string[]) => Prism} createInstance
 	 * @template T
 	 */
-	runTestCaseWithRunner(languageIdentifier, filePath, updateMode, runner) {
+	runTestCaseWithRunner(languageIdentifier, filePath, updateMode, runner, createInstance) {
 		const testCase = TestCaseFile.readFromFile(filePath);
 		const usedLanguages = this.parseLanguageNames(languageIdentifier);
 
-		const Prism = PrismLoader.createInstance(usedLanguages.languages);
+		const Prism = createInstance(usedLanguages.languages);
 
 		// the first language is the main language to highlight
 		const actualValue = runner.run(Prism, testCase.code, usedLanguages.mainLanguage);
diff --git a/tests/helper/test-discovery.js b/tests/helper/test-discovery.js
index 4d97873..3e374a3 100644
--- a/tests/helper/test-discovery.js
+++ b/tests/helper/test-discovery.js
@@ -3,41 +3,37 @@
 const fs = require('fs');
 const path = require('path');
 
+const LANGUAGES_DIR = path.join(__dirname, '..', 'languages');
+
 module.exports = {
 
 	/**
 	 * Loads the list of all available tests
 	 *
-	 * @param {string} rootDir
-	 * @returns {Object<string, string[]>}
+	 * @param {string} [rootDir]
+	 * @returns {Map<string, string[]>}
 	 */
 	loadAllTests(rootDir) {
-		/** @type {Object.<string, string[]>} */
-		const testSuite = {};
-
-		for (const language of this.getAllDirectories(rootDir)) {
-			testSuite[language] = this.getAllFiles(path.join(rootDir, language));
-		}
+		rootDir = rootDir || LANGUAGES_DIR;
 
-		return testSuite;
+		return new Map(this.getAllDirectories(rootDir).map(language => {
+			return [language, this.getAllFiles(path.join(rootDir, language))];
+		}));
 	},
 
 	/**
 	 * Loads the list of available tests that match the given languages
 	 *
-	 * @param {string} rootDir
 	 * @param {string|string[]} languages
-	 * @returns {Object<string, string[]>}
+	 * @param {string} [rootDir]
+	 * @returns {Map<string, string[]>}
 	 */
-	loadSomeTests(rootDir, languages) {
-		/** @type {Object.<string, string[]>} */
-		const testSuite = {};
-
-		for (const language of this.getSomeDirectories(rootDir, languages)) {
-			testSuite[language] = this.getAllFiles(path.join(rootDir, language));
-		}
+	loadSomeTests(languages, rootDir) {
+		rootDir = rootDir || LANGUAGES_DIR;
 
-		return testSuite;
+		return new Map(this.getSomeDirectories(rootDir, languages).map(language => {
+			return [language, this.getAllFiles(path.join(rootDir, language))];
+		}));
 	},
 
 
diff --git a/tests/helper/util.js b/tests/helper/util.js
index da3a18d..e4c7287 100644
--- a/tests/helper/util.js
+++ b/tests/helper/util.js
@@ -19,7 +19,7 @@ module.exports = {
 	 * Performs a breadth-first search on the given start element.
 	 *
 	 * @param {any} start
-	 * @param {(path: { key: string, value: any }[]) => void} callback
+	 * @param {(path: { key: string, value: any }[], obj: Record<string, any>) => void} callback
 	 */
 	BFS(start, callback) {
 		const visited = new Set();
@@ -28,8 +28,6 @@ module.exports = {
 			[{ key: null, value: start }]
 		];
 
-		callback(toVisit[0]);
-
 		while (toVisit.length > 0) {
 			/** @type {{ key: string, value: any }[][]} */
 			const newToVisit = [];
@@ -43,7 +41,7 @@ module.exports = {
 						const value = obj[key];
 
 						path.push({ key, value });
-						callback(path);
+						callback(path, obj);
 
 						if (Array.isArray(value) || Object.prototype.toString.call(value) == '[object Object]') {
 							newToVisit.push([...path]);
@@ -59,6 +57,30 @@ module.exports = {
 	},
 
 	/**
+	 * Given the `BFS` path given to `BFS` callbacks, this will return the Prism language token path of the current
+	 * value (e.g. `Prism.languages.xml.tag.pattern`).
+	 *
+	 * @param {readonly{ key: string, value: any }[]} path
+	 * @param {string} [root]
+	 * @returns {string}
+	 */
+	BFSPathToPrismTokenPath(path, root = 'Prism.languages') {
+		let tokenPath = root;
+		for (const { key } of path) {
+			if (!key) {
+				// do nothing
+			} else if (/^\d+$/.test(key)) {
+				tokenPath += `[${key}]`;
+			} else if (/^[a-z]\w*$/i.test(key)) {
+				tokenPath += `.${key}`;
+			} else {
+				tokenPath += `[${JSON.stringify(key)}]`;
+			}
+		}
+		return tokenPath;
+	},
+
+	/**
 	 * Returns the AST of a given pattern.
 	 *
 	 * @param {RegExp} regex
diff --git a/tests/pattern-tests.js b/tests/pattern-tests.js
index 2dc9ee4..91ce21e 100644
--- a/tests/pattern-tests.js
+++ b/tests/pattern-tests.js
@@ -5,7 +5,7 @@ const { assert } = require('chai');
 const PrismLoader = require('./helper/prism-loader');
 const TestDiscovery = require('./helper/test-discovery');
 const TestCase = require('./helper/test-case');
-const { BFS, parseRegex } = require('./helper/util');
+const { BFS, BFSPathToPrismTokenPath, parseRegex } = require('./helper/util');
 const { languages } = require('../components.json');
 const { visitRegExpAST } = require('regexpp');
 const { transform, combineTransformers, getIntersectionWordSets, JS, Words, NFA, Transformers } = require('refa');
@@ -19,8 +19,8 @@ const RAA = require('regexp-ast-analysis');
  * @type {Map<string, string[]>}
  */
 const testSnippets = new Map();
-const testSuite = TestDiscovery.loadAllTests(__dirname + '/languages');
-for (const languageIdentifier in testSuite) {
+const testSuite = TestDiscovery.loadAllTests();
+for (const [languageIdentifier, files] of testSuite) {
 	const lang = TestCase.parseLanguageNames(languageIdentifier).mainLanguage;
 	let snippets = testSnippets.get(lang);
 	if (snippets === undefined) {
@@ -28,7 +28,7 @@ for (const languageIdentifier in testSuite) {
 		testSnippets.set(lang, snippets);
 	}
 
-	for (const file of testSuite[languageIdentifier]) {
+	for (const file of files) {
 		snippets.push(TestCase.TestCaseFile.readFromFile(file).code);
 	}
 }
@@ -91,27 +91,6 @@ function testPatterns(Prism, mainLanguage) {
 	}
 
 	/**
-	 * @param {string} root
-	 * @param {Parameters<Parameters<typeof BFS>[1]>[0]} path
-	 * @returns {string}
-	 */
-	function BFSPathToString(root, path) {
-		let pathStr = root;
-		for (const { key } of path) {
-			if (!key) {
-				// do nothing
-			} else if (/^\d+$/.test(key)) {
-				pathStr += `[${key}]`;
-			} else if (/^[a-z]\w*$/i.test(key)) {
-				pathStr += `.${key}`;
-			} else {
-				pathStr += `[${JSON.stringify(key)}]`;
-			}
-		}
-		return pathStr;
-	}
-
-	/**
 	 * Invokes the given function on every pattern in `Prism.languages`.
 	 *
 	 * _Note:_ This will aggregate all errors thrown by the given callback and throw an aggregated error at the end
@@ -146,10 +125,9 @@ function testPatterns(Prism, mainLanguage) {
 
 			BFS(root, path => {
 				const { key, value } = path[path.length - 1];
+				const tokenPath = BFSPathToPrismTokenPath(path, rootStr);
 				visited.add(value);
 
-				const tokenPath = BFSPathToString(rootStr, path);
-
 				if (Object.prototype.toString.call(value) == '[object RegExp]') {
 					try {
 						let ast;
diff --git a/tests/run.js b/tests/run.js
index f030fbc..390d771 100644
--- a/tests/run.js
+++ b/tests/run.js
@@ -8,29 +8,23 @@ const { argv } = require('yargs');
 
 const testSuite =
 	(argv.language)
-		? TestDiscovery.loadSomeTests(__dirname + '/languages', argv.language)
+		? TestDiscovery.loadSomeTests(argv.language)
 		// load complete test suite
-		: TestDiscovery.loadAllTests(__dirname + '/languages');
+		: TestDiscovery.loadAllTests();
 
 const update = !!argv.update;
 
 // define tests for all tests in all languages in the test suite
-for (const language in testSuite) {
-	if (!testSuite.hasOwnProperty(language)) {
-		continue;
-	}
+for (const [languageIdentifier, files] of testSuite) {
+	describe("Testing language '" + languageIdentifier + "'", function () {
+		this.timeout(10000);
 
-	(function (language, testFiles) {
-		describe("Testing language '" + language + "'", function () {
-			this.timeout(10000);
+		for (const filePath of files) {
+			const fileName = path.basename(filePath, path.extname(filePath));
 
-			for (const filePath of testFiles) {
-				const fileName = path.basename(filePath, path.extname(filePath));
-
-				it("– should pass test case '" + fileName + "'", function () {
-					TestCase.runTestCase(language, filePath, update ? 'update' : 'insert');
-				});
-			}
-		});
-	}(language, testSuite[language]));
+			it("– should pass test case '" + fileName + "'", function () {
+				TestCase.runTestCase(languageIdentifier, filePath, update ? 'update' : 'insert');
+			});
+		}
+	});
 }