Skip to content

Commit 9b4fc4f

Browse files
ExplodingCabbageExplodingCabbage
committed
word.js -> word.ts
1 parent 4bd69ee commit 9b4fc4f

File tree

3 files changed

+98
-88
lines changed

3 files changed

+98
-88
lines changed

‎package.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -44,7 +44,7 @@
4444
"scripts": {
4545
"clean": "rm -rf lib/ dist/ coverage/ .nyc_output/",
4646
"lint": "yarn eslint 'src/**/*.js' 'test/**/*.js'",
47-
"build": "yarn tsc src/**/*.ts --module es2015 --moduleResolution bundler && yarn run-babel && yarn run-rollup && yarn run-uglify",
47+
"build": "yarn tsc src/**/*.ts --module es2015 --moduleResolution bundler --target es2022 && yarn run-babel && yarn run-rollup && yarn run-uglify",
4848
"test": "nyc yarn _test",
4949
"_test": "yarn build && cross-env NODE_ENV=test yarn run-mocha",
5050
"run-babel": "babel --out-dir lib --source-maps=inline src",

‎src/diff/base.ts

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -23,6 +23,9 @@ export interface DiffOptions<ValueT> {
2323
// diffJson only:
2424
undefinedReplacement?: any,
2525
stringifyReplacer?: (k: string, v: any) => any,
26+
27+
// diffWords only:
28+
intlSegmenter?: Intl.Segmenter,
2629
}
2730

2831
/**

‎src/diff/word.js renamed to ‎src/diff/word.ts

Lines changed: 94 additions & 87 deletions
Original file line numberDiff line numberDiff line change
@@ -1,4 +1,4 @@
1-
import Diff from './base';
1+
import Diff, { DiffOptions } from './base';
22
import { longestCommonPrefix, longestCommonSuffix, replacePrefix, replaceSuffix, removePrefix, removeSuffix, maximumOverlap, leadingWs, trailingWs } from '../util/string';
33

44
// Based on https://en.wikipedia.org/wiki/Latin_script_in_Unicode
@@ -48,94 +48,98 @@ const extendedWordChars = 'a-zA-Z0-9_\\u{C0}-\\u{FF}\\u{D8}-\\u{F6}\\u{F8}-\\u{2
4848
// tokens.
4949
const tokenizeIncludingWhitespace = new RegExp(`[${extendedWordChars}]+|\\s+|[^${extendedWordChars}]`, 'ug');
5050

51-
export const wordDiff = new Diff();
52-
wordDiff.equals = function(left, right, options) {
53-
if (options.ignoreCase) {
54-
left = left.toLowerCase();
55-
right = right.toLowerCase();
56-
}
57-
58-
return left.trim() === right.trim();
59-
};
6051

61-
wordDiff.tokenize = function(value, options = {}) {
62-
let parts;
63-
if (options.intlSegmenter) {
64-
if (options.intlSegmenter.resolvedOptions().granularity != 'word') {
65-
throw new Error('The segmenter passed must have a granularity of "word"');
52+
class WordDiff extends Diff<string, string> {
53+
protected equals(left: string, right: string, options: DiffOptions<string>) {
54+
if (options.ignoreCase) {
55+
left = left.toLowerCase();
56+
right = right.toLowerCase();
6657
}
67-
parts = Array.from(options.intlSegmenter.segment(value), segment => segment.segment);
68-
} else {
69-
parts = value.match(tokenizeIncludingWhitespace) || [];
58+
59+
return left.trim() === right.trim();
7060
}
71-
const tokens = [];
72-
let prevPart = null;
73-
parts.forEach(part => {
74-
if ((/\s/).test(part)) {
75-
if (prevPart == null) {
76-
tokens.push(part);
77-
} else {
78-
tokens.push(tokens.pop() + part);
79-
}
80-
} else if ((/\s/).test(prevPart)) {
81-
if (tokens[tokens.length - 1] == prevPart) {
82-
tokens.push(tokens.pop() + part);
83-
} else {
84-
tokens.push(prevPart + part);
61+
62+
protected tokenize(value: string, options: DiffOptions<string> = {}) {
63+
let parts;
64+
if (options.intlSegmenter) {
65+
if (options.intlSegmenter.resolvedOptions().granularity != 'word') {
66+
throw new Error('The segmenter passed must have a granularity of "word"');
8567
}
68+
parts = Array.from(options.intlSegmenter.segment(value), segment => segment.segment);
8669
} else {
87-
tokens.push(part);
70+
parts = value.match(tokenizeIncludingWhitespace) || [];
8871
}
72+
const tokens: string[] = [];
73+
let prevPart = null;
74+
parts.forEach(part => {
75+
if ((/\s/).test(part)) {
76+
if (prevPart == null) {
77+
tokens.push(part);
78+
} else {
79+
tokens.push(tokens.pop() + part);
80+
}
81+
} else if (prevPart != null && (/\s/).test(prevPart)) {
82+
if (tokens[tokens.length - 1] == prevPart) {
83+
tokens.push(tokens.pop() + part);
84+
} else {
85+
tokens.push(prevPart + part);
86+
}
87+
} else {
88+
tokens.push(part);
89+
}
8990

90-
prevPart = part;
91-
});
92-
return tokens;
93-
};
94-
95-
wordDiff.join = function(tokens) {
96-
// Tokens being joined here will always have appeared consecutively in the
97-
// same text, so we can simply strip off the leading whitespace from all the
98-
// tokens except the first (and except any whitespace-only tokens - but such
99-
// a token will always be the first and only token anyway) and then join them
100-
// and the whitespace around words and punctuation will end up correct.
101-
return tokens.map((token, i) => {
102-
if (i == 0) {
103-
return token;
104-
} else {
105-
return token.replace((/^\s+/), '');
106-
}
107-
}).join('');
108-
};
91+
prevPart = part;
92+
});
93+
return tokens;
94+
}
10995

110-
wordDiff.postProcess = function(changes, options) {
111-
if (!changes || options.oneChangePerToken) {
112-
return changes;
96+
protected join(tokens) {
97+
// Tokens being joined here will always have appeared consecutively in the
98+
// same text, so we can simply strip off the leading whitespace from all the
99+
// tokens except the first (and except any whitespace-only tokens - but such
100+
// a token will always be the first and only token anyway) and then join them
101+
// and the whitespace around words and punctuation will end up correct.
102+
return tokens.map((token, i) => {
103+
if (i == 0) {
104+
return token;
105+
} else {
106+
return token.replace((/^\s+/), '');
107+
}
108+
}).join('');
113109
}
114110

115-
let lastKeep = null;
116-
// Change objects representing any insertion or deletion since the last
117-
// "keep" change object. There can be at most one of each.
118-
let insertion = null;
119-
let deletion = null;
120-
changes.forEach(change => {
121-
if (change.added) {
122-
insertion = change;
123-
} else if (change.removed) {
124-
deletion = change;
125-
} else {
126-
if (insertion || deletion) { // May be false at start of text
127-
dedupeWhitespaceInChangeObjects(lastKeep, deletion, insertion, change);
111+
protected postProcess(changes, options) {
112+
if (!changes || options.oneChangePerToken) {
113+
return changes;
114+
}
115+
116+
let lastKeep = null;
117+
// Change objects representing any insertion or deletion since the last
118+
// "keep" change object. There can be at most one of each.
119+
let insertion = null;
120+
let deletion = null;
121+
changes.forEach(change => {
122+
if (change.added) {
123+
insertion = change;
124+
} else if (change.removed) {
125+
deletion = change;
126+
} else {
127+
if (insertion || deletion) { // May be false at start of text
128+
dedupeWhitespaceInChangeObjects(lastKeep, deletion, insertion, change);
129+
}
130+
lastKeep = change;
131+
insertion = null;
132+
deletion = null;
128133
}
129-
lastKeep = change;
130-
insertion = null;
131-
deletion = null;
134+
});
135+
if (insertion || deletion) {
136+
dedupeWhitespaceInChangeObjects(lastKeep, deletion, insertion, null);
132137
}
133-
});
134-
if (insertion || deletion) {
135-
dedupeWhitespaceInChangeObjects(lastKeep, deletion, insertion, null);
138+
return changes;
136139
}
137-
return changes;
138-
};
140+
}
141+
142+
export const wordDiff = new WordDiff();
139143

140144
export function diffWords(oldStr, newStr, options) {
141145
// This option has never been documented and never will be (it's clearer to
@@ -273,16 +277,19 @@ function dedupeWhitespaceInChangeObjects(startKeep, deletion, insertion, endKeep
273277
}
274278

275279

276-
export const wordWithSpaceDiff = new Diff();
277-
wordWithSpaceDiff.tokenize = function(value) {
278-
// Slightly different to the tokenizeIncludingWhitespace regex used above in
279-
// that this one treats each individual newline as a distinct tokens, rather
280-
// than merging them into other surrounding whitespace. This was requested
281-
// in https://github.com/kpdecker/jsdiff/issues/180 &
282-
// https://github.com/kpdecker/jsdiff/issues/211
283-
const regex = new RegExp(`(\\r?\\n)|[${extendedWordChars}]+|[^\\S\\n\\r]+|[^${extendedWordChars}]`, 'ug');
284-
return value.match(regex) || [];
285-
};
280+
class WordsWithSpaceDiff extends Diff<string, string> {
281+
protected tokenize(value: string) {
282+
// Slightly different to the tokenizeIncludingWhitespace regex used above in
283+
// that this one treats each individual newline as a distinct tokens, rather
284+
// than merging them into other surrounding whitespace. This was requested
285+
// in https://github.com/kpdecker/jsdiff/issues/180 &
286+
// https://github.com/kpdecker/jsdiff/issues/211
287+
const regex = new RegExp(`(\\r?\\n)|[${extendedWordChars}]+|[^\\S\\n\\r]+|[^${extendedWordChars}]`, 'ug');
288+
return value.match(regex) || [];
289+
}
290+
}
291+
292+
export const wordsWithSpaceDiff = new WordsWithSpaceDiff();
286293
export function diffWordsWithSpace(oldStr, newStr, options) {
287-
return wordWithSpaceDiff.diff(oldStr, newStr, options);
294+
return wordsWithSpaceDiff.diff(oldStr, newStr, options);
288295
}

0 commit comments

Comments
 (0)