Skip to content

fix(convert): decode JIS X 0212 0x2237 to a single character #69

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

Merged
polygonplanet merged 1 commit into from
Oct 2, 2026
Merged

fix(convert): decode JIS X 0212 0x2237 to a single character #69

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 6 additions & 2 deletions src/encoding-convert.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -511,7 +511,9 @@ function EUCJPToUTF8(data) {
if (utf8 === void 0) {
results[results.length] = config.FALLBACK_CHARACTER;
} else {
if (utf8 < 0xFFFF) {
if (utf8 < 0x80) {
results[results.length] = utf8;
} else if (utf8 < 0xFFFF) {
results[results.length] = utf8 >> 8 & 0xFF;
results[results.length] = utf8 & 0xFF;
} else {
Expand Down Expand Up @@ -609,7 +611,9 @@ function JISToUTF8(data) {
if (utf8 === void 0) {
results[results.length] = config.FALLBACK_CHARACTER;
} else {
if (utf8 < 0xFFFF) {
if (utf8 < 0x80) {
results[results.length] = utf8;
} else if (utf8 < 0xFFFF) {
results[results.length] = utf8 >> 8 & 0xFF;
results[results.length] = utf8 & 0xFF;
} else {
Expand Down
11 changes: 11 additions & 0 deletions tests/test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1249,6 +1249,17 @@ describe('encoding', function() {
assert.equal(decoded, '?');
});

it('JIS X 0212 code point mapped to ASCII', function() {
// JIS X 0212 0x2237 maps to U+007E, a single UTF-8 byte.
var eucjp = [0x8F, 0xA2, 0xB7];
var jis = [0x1B, 0x24, 0x28, 0x44, 0x22, 0x37, 0x1B, 0x28, 0x42];

assert.deepEqual(encoding.convert(eucjp, 'UTF8', 'EUCJP'), [0x7E]);
assert.deepEqual(encoding.convert(eucjp, 'UNICODE', 'EUCJP'), [0x7E]);
assert.deepEqual(encoding.convert(jis, 'UTF8', 'JIS'), [0x7E]);
assert.deepEqual(encoding.convert(jis, 'UNICODE', 'JIS'), [0x7E]);
});

it('SJIS invalid trail byte 0x7F', function() {
var invalidSjisCode = [0x81, 0x7F];
var validSjisCode = [0x81, 0x7E];
Expand Down
Loading