Skip to content

lib: map Latin1 labels to iso-8859-1 instead of Windows-1252 #58890

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

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
+89 −31
Open

lib: map Latin1 labels to iso-8859-1 instead of Windows-1252 #58890

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
50aa8bc
lib: map Latin1 labels to iso-8859-1 encoding
lytovka Jun 29, 2025
1bf1c92
test: fix label assertions in existing tests
lytovka Jun 29, 2025
8819222
test: decode 0x7F-0x9F bytes with windows-1252 encoding
lytovka Jun 29, 2025
2813ea4
test: revert removal of windows-1254 labels
lytovka Jun 29, 2025
eff9039
test: remove unnecessary console.log
lytovka Jun 29, 2025
7143420
test: remove unnecessary comments
lytovka Jun 29, 2025
43fbb04
test: fix linting errors
lytovka Jun 30, 2025
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
32 changes: 16 additions & 16 deletions lib/internal/encoding.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -206,23 +206,23 @@ const encodings = new SafeMap([
['cp1251', 'windows-1251'],
['windows-1251', 'windows-1251'],
['x-cp1251', 'windows-1251'],
['ansi_x3.4-1968', 'windows-1252'],
['ascii', 'windows-1252'],
['cp1252', 'windows-1252'],
['cp819', 'windows-1252'],
['csisolatin1', 'windows-1252'],
['ibm819', 'windows-1252'],
['iso-8859-1', 'windows-1252'],
['iso-ir-100', 'windows-1252'],
['iso8859-1', 'windows-1252'],
['iso88591', 'windows-1252'],
['iso_8859-1', 'windows-1252'],
['iso_8859-1:1987', 'windows-1252'],
['l1', 'windows-1252'],
['latin1', 'windows-1252'],
['us-ascii', 'windows-1252'],
['ansi_x3.4-1968', 'iso-8859-1'],
['ascii', 'iso-8859-1'],
['cp819', 'iso-8859-1'],
['csisolatin1', 'iso-8859-1'],
['ibm819', 'iso-8859-1'],
['iso-8859-1', 'iso-8859-1'],
['iso-ir-100', 'iso-8859-1'],
['iso8859-1', 'iso-8859-1'],
['iso88591', 'iso-8859-1'],
['iso_8859-1', 'iso-8859-1'],
['iso_8859-1:1987', 'iso-8859-1'],
['l1', 'iso-8859-1'],
['latin1', 'iso-8859-1'],
['us-ascii', 'iso-8859-1'],
['windows-1252', 'windows-1252'],
['x-cp1252', 'windows-1252'],
['cp1252', 'windows-1252'],
['cp1253', 'windows-1253'],
['windows-1253', 'windows-1253'],
['x-cp1253', 'windows-1253'],
Expand Down Expand Up @@ -421,7 +421,7 @@ function makeTextDecoderICU() {
this[kFatal] = Boolean(options?.fatal);
// Only support fast path for UTF-8.
this[kUTF8FastPath] = enc === 'utf-8';
this[kLatin1FastPath] = enc === 'windows-1252';
this[kLatin1FastPath] = enc === 'iso-8859-1';
this[kHandle] = undefined;

if (!this[kUTF8FastPath] && !this[kLatin1FastPath]) {
Expand Down
2 changes: 1 addition & 1 deletion test/fixtures/wpt/encoding/streams/decode-attributes.any.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
const labelToName = {
'unicode-1-1-utf-8': 'utf-8',
'iso-8859-2': 'iso-8859-2',
'ascii': 'windows-1252',
'ascii': 'iso-8859-1',
'utf-16': 'utf-16le'
};

Expand Down
30 changes: 16 additions & 14 deletions test/parallel/test-whatwg-encoding-custom-internals.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,21 @@ const { getEncodingFromLabel } = require('internal/encoding');
'cp866',
'csibm866',
],
'iso-8859-1': [
'ansi_x3.4-1968',
'ascii',
'cp819',
'csisolatin1',
'ibm819',
'iso-ir-100',
'iso8859-1',
'iso88591',
'iso_8859-1',
'iso_8859-1:1987',
'l1',
'latin1',
'us-ascii',
],
'iso-8859-2': [
'csisolatin2',
'iso-ir-101',
Expand Down Expand Up @@ -170,21 +185,7 @@ const { getEncodingFromLabel } = require('internal/encoding');
'x-cp1251',
],
'windows-1252': [
'ansi_x3.4-1968',
'ascii',
'cp1252',
'cp819',
'csisolatin1',
'ibm819',
'iso-8859-1',
'iso-ir-100',
'iso8859-1',
'iso88591',
'iso_8859-1',
'iso_8859-1:1987',
'l1',
'latin1',
'us-ascii',
'x-cp1252',
],
'windows-1253': [
Expand Down Expand Up @@ -281,6 +282,7 @@ const { getEncodingFromLabel } = require('internal/encoding');
Object.entries(mappings).forEach((i) => {
const enc = i[0];
const labels = i[1];
console.log("label: ",enc, "enc: ", getEncodingFromLabel(enc))
assert.strictEqual(getEncodingFromLabel(enc), enc);
labels.forEach((l) => assert.strictEqual(getEncodingFromLabel(l), enc));
});
Expand Down
63 changes: 63 additions & 0 deletions test/parallel/test-whatwg-encoding-custom-textdecoder-windows1252-decoding.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,63 @@
'use strict';

// From: https://github.com/w3c/web-platform-tests/blob/39a67e2fff/encoding/textdecoder-fatal.html
// With the twist that we specifically test for Node.js error codes

const common = require('../common');

if (!common.hasIntl)
common.skip('missing Intl');

const assert = require('assert');

{
// Windows-1252 mapping for bytes 0x7F-0x9F as [byte, unicode code point]
const win1252_0x7F_0x9F = [
[0x7F, 0x007F], // DELETE
[0x80, 0x20AC], // EURO SIGN
[0x81, 0x0081], // UNDEFINED
[0x82, 0x201A], // SINGLE LOW-9 QUOTATION MARK
[0x83, 0x0192], // LATIN SMALL LETTER F WITH HOOK
[0x84, 0x201E], // DOUBLE LOW-9 QUOTATION MARK
[0x85, 0x2026], // HORIZONTAL ELLIPSIS
[0x86, 0x2020], // DAGGER
[0x87, 0x2021], // DOUBLE DAGGER
[0x88, 0x02C6], // CIRCUMFLEX
[0x89, 0x2030], // PER MILLE SIGN
[0x8A, 0x0160], // LATIN CAPITAL LETTER S WITH CARON
[0x8B, 0x2039], // SINGLE LEFT-POINTING ANGLE QUOTATION MARK
[0x8C, 0x0152], // LATIN CAPITAL LIGATURE OE
[0x8D, 0x008D], // UNDEFINED
[0x8E, 0x017D], // LATIN CAPITAL LETTER Z WITH CARON
[0x8F, 0x008F], // UNDEFINED
[0x90, 0x0090], // UNDEFINED
[0x91, 0x2018], // LEFT SINGLE QUOTATION MARK
[0x92, 0x2019], // RIGHT SINGLE QUOTATION MARK
[0x93, 0x201C], // LEFT DOUBLE QUOTATION MARK
[0x94, 0x201D], // RIGHT DOUBLE QUOTATION MARK
[0x95, 0x2022], // BULLET
[0x96, 0x2013], // EN DASH
[0x97, 0x2014], // EM DASH
[0x98, 0x02DC], // SMALL TILDE
[0x99, 0x2122], // TRADE MARK SIGN
[0x9A, 0x0161], // LATIN SMALL LETTER S WITH CARON
[0x9B, 0x203A], // SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
[0x9C, 0x0153], // LATIN SMALL LIGATURE OE
[0x9D, 0x009D], // UNDEFINED
[0x9E, 0x017E], // LATIN SMALL LETTER Z WITH CARON
[0x9F, 0x0178] // LATIN CAPITAL LETTER Y WITH DIAERESIS
];

for (let i = 0; i < win1252_0x7F_0x9F.length; i++) {
const byte = win1252_0x7F_0x9F[i][0];
const expectedUnicodeCode = win1252_0x7F_0x9F[i][1];
const arr = new Uint8Array([byte]);
let decoded;
assert.doesNotThrow(() => {
decoded = new TextDecoder("windows-1252").decode(arr);
}, `Decoding byte ${byte} should not throw`);
assert.strictEqual(decoded.length, 1, `Decoded string for ${byte} should have length 1`);
const actualUnicodeCode = decoded.codePointAt(0);
assert.strictEqual(actualUnicodeCode, expectedUnicodeCode, `Decoded code point for ${byte} should be U+${expectedUnicodeCode.toString(16).toUpperCase()}`);
}
}