From 410e9e3eb891db0846b09b04b5f8c4aafc4cbd7d Mon Sep 17 00:00:00 2001 From: John-David Dalton Date: Thu, 11 Aug 2016 23:00:11 -0700 Subject: [PATCH] Update `_.deburr` tests. --- lodash.js | 8 ++++---- test/test.js | 51 ++++++++++++++++++++++++++++++++++++++------------- 2 files changed, 42 insertions(+), 17 deletions(-) diff --git a/lodash.js b/lodash.js index 93c9edd02..3801e5c5f 100644 --- a/lodash.js +++ b/lodash.js @@ -182,7 +182,7 @@ /** Used to detect unsigned integer values. */ var reIsUint = /^(?:0|[1-9]\d*)$/; - /** Used to match Latin-1 Supplement and Latin Extended-A blocks (excluding mathematical operators). */ + /** Used to match Latin Unicode letters (excluding mathematical operators). */ var reLatin = /[\xc0-\xd6\xd8-\xf6\xf8-\xff\u0100-\u017f]/g; /** Used to ensure capturing order of template delimiters. */ @@ -306,7 +306,7 @@ cloneableTags[errorTag] = cloneableTags[funcTag] = cloneableTags[weakMapTag] = false; - /** Used to map Latin Unicode blocks to basic Latin letters. */ + /** Used to map Latin Unicode letters to basic Latin letters. */ var deburredLetters = { // Latin-1 Supplement block. '\xc0': 'A', '\xc1': 'A', '\xc2': 'A', '\xc3': 'A', '\xc4': 'A', '\xc5': 'A', @@ -315,8 +315,8 @@ '\xd0': 'D', '\xf0': 'd', '\xc8': 'E', '\xc9': 'E', '\xca': 'E', '\xcb': 'E', '\xe8': 'e', '\xe9': 'e', '\xea': 'e', '\xeb': 'e', - '\xcC': 'I', '\xcd': 'I', '\xce': 'I', '\xcf': 'I', - '\xeC': 'i', '\xed': 'i', '\xee': 'i', '\xef': 'i', + '\xcc': 'I', '\xcd': 'I', '\xce': 'I', '\xcf': 'I', + '\xec': 'i', '\xed': 'i', '\xee': 'i', '\xef': 'i', '\xd1': 'N', '\xf1': 'n', '\xd2': 'O', '\xd3': 'O', '\xd4': 'O', '\xd5': 'O', '\xd6': 'O', '\xd8': 'O', '\xf2': 'o', '\xf3': 'o', '\xf4': 'o', '\xf5': 'o', '\xf6': 'o', '\xf8': 'o', diff --git a/test/test.js b/test/test.js index 38ba90fcc..decd47a02 100644 --- a/test/test.js +++ b/test/test.js @@ -104,12 +104,24 @@ stubObject = function() { return {}; }, stubString = function() { return ''; }; - /** List of latin-1 supplementary letters to basic latin letters. */ + + + /** List of Latin Unicode letters. */ var burredLetters = [ - '\xc0', '\xc1', '\xc2', '\xc3', '\xc4', '\xc5', '\xc6', '\xc7', '\xc8', '\xc9', '\xca', '\xcb', '\xcc', '\xcd', '\xce', - '\xcf', '\xd0', '\xd1', '\xd2', '\xd3', '\xd4', '\xd5', '\xd6', '\xd8', '\xd9', '\xda', '\xdb', '\xdc', '\xdd', '\xde', - '\xdf', '\xe0', '\xe1', '\xe2', '\xe3', '\xe4', '\xe5', '\xe6', '\xe7', '\xe8', '\xe9', '\xea', '\xeb', '\xec', '\xed', '\xee', - '\xef', '\xf0', '\xf1', '\xf2', '\xf3', '\xf4', '\xf5', '\xf6', '\xf8', '\xf9', '\xfa', '\xfb', '\xfc', '\xfd', '\xfe', '\xff' + // Latin-1 Supplement letters. + '\xc0', '\xc1', '\xc2', '\xc3', '\xc4', '\xc5', '\xc6', '\xc7', '\xc8', '\xc9', '\xca', '\xcb', '\xcc', '\xcd', '\xce', '\xcf', + '\xd0', '\xd1', '\xd2', '\xd3', '\xd4', '\xd5', '\xd6', '\xd8', '\xd9', '\xda', '\xdb', '\xdc', '\xdd', '\xde', '\xdf', + '\xe0', '\xe1', '\xe2', '\xe3', '\xe4', '\xe5', '\xe6', '\xe7', '\xe8', '\xe9', '\xea', '\xeb', '\xec', '\xed', '\xee', '\xef', + '\xf0', '\xf1', '\xf2', '\xf3', '\xf4', '\xf5', '\xf6', '\xf8', '\xf9', '\xfa', '\xfb', '\xfc', '\xfd', '\xfe', '\xff', + // Latin Extended-A letters. + '\u0100', '\u0101', '\u0102', '\u0103', '\u0104', '\u0105', '\u0106', '\u0107', '\u0108', '\u0109', '\u010a', '\u010b', '\u010c', '\u010d', '\u010e', '\u010f', + '\u0110', '\u0111', '\u0112', '\u0113', '\u0114', '\u0115', '\u0116', '\u0117', '\u0118', '\u0119', '\u011a', '\u011b', '\u011c', '\u011d', '\u011e', '\u011f', + '\u0120', '\u0121', '\u0122', '\u0123', '\u0124', '\u0125', '\u0126', '\u0127', '\u0128', '\u0129', '\u012a', '\u012b', '\u012c', '\u012d', '\u012e', '\u012f', + '\u0130', '\u0131', '\u0132', '\u0133', '\u0134', '\u0135', '\u0136', '\u0137', '\u0138', '\u0139', '\u013a', '\u013b', '\u013c', '\u013d', '\u013e', '\u013f', + '\u0140', '\u0141', '\u0142', '\u0143', '\u0144', '\u0145', '\u0146', '\u0147', '\u0148', '\u0149', '\u014a', '\u014b', '\u014c', '\u014d', '\u014e', '\u014f', + '\u0150', '\u0151', '\u0152', '\u0153', '\u0154', '\u0155', '\u0156', '\u0157', '\u0158', '\u0159', '\u015a', '\u015b', '\u015c', '\u015d', '\u015e', '\u015f', + '\u0160', '\u0161', '\u0162', '\u0163', '\u0164', '\u0165', '\u0166', '\u0167', '\u0168', '\u0169', '\u016a', '\u016b', '\u016c', '\u016d', '\u016e', '\u016f', + '\u0170', '\u0171', '\u0172', '\u0173', '\u0174', '\u0175', '\u0176', '\u0177', '\u0178', '\u0179', '\u017a', '\u017b', '\u017c', '\u017d', '\u017e', '\u017f' ]; /** List of combining diacritical marks. */ @@ -124,12 +136,25 @@ '\ufe20', '\ufe21', '\ufe22', '\ufe23' ]; - /** List of `burredLetters` translated to basic latin letters. */ + /** List of converted Latin Unicode letters. */ var deburredLetters = [ + // Converted Latin-1 Supplement letters. 'A', 'A', 'A', 'A', 'A', 'A', 'Ae', 'C', 'E', 'E', 'E', 'E', 'I', 'I', 'I', 'I', 'D', 'N', 'O', 'O', 'O', 'O', 'O', 'O', 'U', 'U', 'U', 'U', 'Y', 'Th', 'ss', 'a', 'a', 'a', 'a', 'a', 'a', 'ae', 'c', 'e', 'e', 'e', 'e', 'i', 'i', 'i', - 'i', 'd', 'n', 'o', 'o', 'o', 'o', 'o', 'o', 'u', 'u', 'u', 'u', 'y', 'th', 'y' + 'i', 'd', 'n', 'o', 'o', 'o', 'o', 'o', 'o', 'u', 'u', 'u', 'u', 'y', 'th', 'y', + // Converted Latin Extended-A letters. + 'A', 'a', 'A', 'a', 'A', 'a', 'C', 'c', 'C', 'c', 'C', 'c', 'C', 'c', + 'D', 'd', 'D', 'd', 'E', 'e', 'E', 'e', 'E', 'e', 'E', 'e', 'E', 'e', + 'G', 'g', 'G', 'g', 'G', 'g', 'G', 'g', 'H', 'h', 'H', 'h', + 'I', 'i', 'I', 'i', 'I', 'i', 'I', 'i', 'I', 'i', 'IJ', 'ij', 'J', 'j', + 'K', 'k', 'k', 'L', 'l', 'L', 'l', 'L', 'l', 'L', 'l', 'L', 'l', + 'N', 'n', 'N', 'n', 'N', 'n', "'n", 'N', 'n', + 'O', 'o', 'O', 'o', 'O', 'o', 'Oe', 'oe', + 'R', 'r', 'R', 'r', 'R', 'r', 'S', 's', 'S', 's', 'S', 's', 'S', 's', + 'T', 't', 'T', 't', 'T', 't', + 'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', 'U', 'u', + 'W', 'w', 'Y', 'y', 'Y', 'Z', 'z', 'Z', 'z', 'Z', 'z', 'ss' ]; /** Used to provide falsey values to methods. */ @@ -2234,9 +2259,9 @@ assert.expect(1); var actual = lodashStable.map(burredLetters, function(burred, index) { - var letter = deburredLetters[index]; + var letter = deburredLetters[index].replace(/['\u2019]/g, ''); if (caseName == 'start') { - letter = lodashStable.capitalize(letter); + letter = letter == 'IJ' ? letter : lodashStable.capitalize(letter); } else if (caseName == 'upper') { letter = letter.toUpperCase(); } else { @@ -2273,7 +2298,7 @@ }); }); - QUnit.test('`_.' + methodName + '` should remove latin-1 mathematical operators', function(assert) { + QUnit.test('`_.' + methodName + '` should remove Latin mathematical operators', function(assert) { assert.expect(1); var actual = lodashStable.map(['\xd7', '\xf7'], func); @@ -4448,14 +4473,14 @@ QUnit.module('lodash.deburr'); (function() { - QUnit.test('should convert latin-1 supplementary letters to basic latin', function(assert) { + QUnit.test('should convert Latin-1 Supplement letters to basic Latin', function(assert) { assert.expect(1); var actual = lodashStable.map(burredLetters, _.deburr); assert.deepEqual(actual, deburredLetters); }); - QUnit.test('should not deburr latin-1 mathematical operators', function(assert) { + QUnit.test('should not deburr Latin mathematical operators', function(assert) { assert.expect(1); var operators = ['\xd7', '\xf7'], @@ -24985,7 +25010,7 @@ QUnit.module('lodash.words'); (function() { - QUnit.test('should treat latin-1 supplementary letters as words', function(assert) { + QUnit.test('should match words containing Latin-1 Supplement letters', function(assert) { assert.expect(1); var expected = lodashStable.map(burredLetters, function(letter) {