Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add python style unicode support (\U0001F3B5) #3

Merged
merged 4 commits into from
Nov 20, 2017
Merged

Add python style unicode support (\U0001F3B5) #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0820a95
Add python style unicode support (`\U0001F3B5`)
tedivm Nov 18, 2017
8cf9152
fix comment
tedivm Nov 18, 2017
5a95b7e
make python test check for fixed character count instead of dynamic
tedivm Nov 18, 2017
368192e
Correct handling of backslashes on python unescaping
tedivm Nov 19, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 9 additions & 5 deletions src/index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,15 +6,17 @@ import 'string.fromcodepoint';
* u\{([0-9A-Fa-f]+)\} - first alternative; matches the variable-length hexadecimal escape sequence (\u{ABCD0})
* |
* u([0-9A-Fa-f]{4}) - second alternative; matches the 4-digit hexadecimal escape sequence (\uABCD)
* |
* |
* x([0-9A-Fa-f]{2}) - third alternative; matches the 2-digit hexadecimal escape sequence (\xA5)
* |
* |
* ([1-7][0-7]{0,2}|[0-7]{2,3}) - fourth alternative; matches the up-to-3-digit octal escape sequence (\5 or \512)
* |
* |
* (['"tbrnfv0\\]) - fifth alternative; matches the special escape characters (\t, \n and so on)
* |
* \U([0-9A-Fa-f]+) - sixth alternative; matches the 8-digit hexadecimal escape sequence used by python (\U0001F3B5)
* )
*/
const jsEscapeRegex = /\\(u\{([0-9A-Fa-f]+)\}|u([0-9A-Fa-f]{4})|x([0-9A-Fa-f]{2})|([1-7][0-7]{0,2}|[0-7]{2,3})|(['"tbrnfv0\\]))/g;
const jsEscapeRegex = /\\(u\{([0-9A-Fa-f]+)\}|u([0-9A-Fa-f]{4})|x([0-9A-Fa-f]{2})|([1-7][0-7]{0,2}|[0-7]{2,3})|(['"tbrnfv0\\]))|\\U([0-9A-Fa-f]{8})/g;

const usualEscapeSequences = {
'0': '\0',
Expand All @@ -33,7 +35,7 @@ const fromHex = (str) => String.fromCodePoint(parseInt(str, 16));
const fromOct = (str) => String.fromCodePoint(parseInt(str, 8));

export default (string) => {
return string.replace(jsEscapeRegex, (_, __, varHex, longHex, shortHex, octal, specialCharacter) => {
return string.replace(jsEscapeRegex, (_, __, varHex, longHex, shortHex, octal, specialCharacter, python) => {
if (varHex !== undefined) {
return fromHex(varHex);
} else if (longHex !== undefined) {
Expand All @@ -42,6 +44,8 @@ export default (string) => {
return fromHex(shortHex);
} else if (octal !== undefined) {
return fromOct(octal);
} else if (python !== undefined) {
return fromHex(python);
} else {
return usualEscapeSequences[specialCharacter];
}
Expand Down
5 changes: 5 additions & 0 deletions test/index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,3 +39,8 @@ test('avoids double unescape cascade', t => {
t.is(unescapeJs('---\\\\x41---'), '---\\x41---');
t.is(unescapeJs('---\\x5cx41---'), '---\\x41---');
});

test('python hex escape sequences', t => {
t.is(unescapeJs('---\\U000000A9---'), '---\u00A9---');
t.is(unescapeJs('---\\U0001F3B5---'), '---\uD83C\uDFB5---');
});