Skip to content

Fix Unicode in string decoding #22

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
darthwalsh wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fix Unicode in string decoding #22

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7f414d8
Fix Unicode in string decoding
darthwalsh Jul 15, 2025
1a7f31b
Sniff the copyright string to determine correct encoding
darthwalsh Nov 25, 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
48 changes: 29 additions & 19 deletions src/puz.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,11 +18,8 @@ function strToBytes(str, end) {
end = '\0';
}
str += end;
var result = new Uint8Array(str.length);
for (var i = 0; i < str.length; i += 1) {
result[i] = str.charCodeAt(i);
}
return result;
const encoder = new TextEncoder('ISO-8859-1');
return encoder.encode(str);
}

function concat(byteArrays) {
Expand Down Expand Up @@ -280,7 +277,7 @@ function getExtension(bytes, code) {
return null; // could not find
}

function getRebus(bytes) {
function getRebus(bytes, encoding) {
var grbs = 'GRBS';
var rtbl = 'RTBL';

Expand All @@ -289,7 +286,7 @@ function getRebus(bytes) {
return; // no rebus
}
var solbytes = getExtension(bytes, rtbl);
var enc = new TextDecoder('ISO-8859-1');
var enc = new TextDecoder(encoding);
var solstring = enc.decode(new Uint8Array(solbytes));
if (!solstring) {
return;
Expand Down Expand Up @@ -356,7 +353,6 @@ function addRebusToGrid(grid, rebus) {

function PUZtoJSON(buffer) {
var grid = [];
var info = {};
var across = [];
var down = [];
var bytes = new Uint8Array(buffer);
Expand Down Expand Up @@ -398,20 +394,34 @@ function PUZtoJSON(buffer) {
}
}

var ibyte = 52 + ncol * nrow * 2;
var ibyte;
function readString() {
var result = "";
var b = bytes[ibyte++];
while (b !== 0) {
result += String.fromCharCode(b);
b = bytes[ibyte++];
const start = ibyte;
while (bytes[ibyte] !== 0) {
ibyte++;
}
return result;
ibyte++;

const slice = bytes.slice(start, ibyte - 1);
return new TextDecoder(encoding).decode(slice);
}

info.title = readString();
info.author = readString();
info.copyright = readString();
function readInfo() {
ibyte = 52 + ncol * nrow * 2;
var title = readString();
var author = readString();
var copyright = readString();
return { title, author, copyright };
}

// The PUZ spec reqiures ISO-8859-1 not UTF-8, but some files don't follow the spec.
// Sniff the copyright string for the © unicode which is only encoded correctly once.
var encoding = 'utf-8';
var info = readInfo();
if (!info.copyright.includes('©')) {
encoding = 'ISO-8859-1';
info = readInfo();
}

for (var _i2 = 1; _i2 <= n; _i2++) {
if (isAcross[_i2]) {
Expand All @@ -424,7 +434,7 @@ function PUZtoJSON(buffer) {

info.description = readString();

var rebus = getRebus(bytes);
var rebus = getRebus(bytes, encoding);
var circles = getCircles(bytes);
var shades = getShades(bytes);
if (rebus) {
Expand Down