Skip to content

Add support UTF8 emoji #4

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
kai3341 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Add support UTF8 emoji #4

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
47 changes: 5 additions & 42 deletions src/bson.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -547,60 +547,23 @@ export namespace BSON {
return hi * TWO_PWR_32 + ((lo >= 0) ? lo : TWO_PWR_32 + lo);
}

const utf8Encoder = new TextEncoder();
const utf8Decoder = new TextDecoder();

/**
* Convert a string (UTF-8 encoded) to a byte array
* @param {String} str UTF-8 encoded string
* @return {Uint8Array} Byte array
*/
function str2bin(str: string): Uint8Array {
str = str.replace(/\r\n/g, '\n');
let bin = [], p = 0;
for (let i = 0, len = str.length; i < len; i++) {
let c = str.charCodeAt(i);
if (c < 128) {
bin[p++] = c;
} else if (c < 2048) {
bin[p++] = (c >>> 6) | 192;
bin[p++] = (c & 63) | 128;
} else {
bin[p++] = (c >>> 12) | 224;
bin[p++] = ((c >>> 6) & 63) | 128;
bin[p++] = (c & 63) | 128;
}
}
return new Uint8Array(bin);
}
const str2bin = utf8Encoder.encode.bind(utf8Encoder);


/**
* Convert a byte array to an UTF-8 string
* @param {Uint8Array} bin UTF-8 text given as array of bytes
* @return {String} UTF-8 Text string
*/
function bin2str(bin: Uint8Array): string {
let str = '', len = bin.length, i = 0, c, c2, c3;

while (i < len) {
c = bin[i];
if (c < 128) {
str += String.fromCharCode(c);
i++;
}
else if ((c > 191) && (c < 224)) {
c2 = bin[i + 1];
str += String.fromCharCode(((c & 31) << 6) | (c2 & 63));
i += 2;
}
else {
c2 = bin[i + 1];
c3 = bin[i + 2];
str += String.fromCharCode(((c & 15) << 12) | ((c2 & 63) << 6) | (c3 & 63));
i += 3;
}
}
return str;
}
const bin2str = utf8Decoder.decode.bind(utf8Decoder);


/**
Expand All @@ -609,7 +572,7 @@ export namespace BSON {
* @return {Number} Stringlength in bytes (not in chars)
*/
function strlen(str: string): number {
return encodeURI(str).split(/%..|./).length - 1;
return utf8Encoder.encode(str).length;
}

} // namespace BSON
4 changes: 2 additions & 2 deletions test/spec/bson_test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,8 +136,8 @@ describe('BSON', () => {
});

it("checks UTF-8 string", function () {
let bson = BSON.serialize({ str: "\u00C4\u00D6\u00DC\u00DF" });
expect(bin2hex(bson)).to.deep.equal("17000000027374720009000000c384c396c39cc39f0000");
let bson = BSON.serialize({ str: "\u00C4\u00D6\u00DC\u00DF\ud83e\uddff" });
expect(bin2hex(bson)).to.deep.equal("1b00000002737472000d000000c384c396c39cc39ff09fa7bf0000");
});

it("checks boolean", function () {
Expand Down