From 5f0c882aaaa98d05f85230cb2ee867f18e409392 Mon Sep 17 00:00:00 2001
From: Vitali Lovich <vlovich@cloudflare.com>
Date: Mon, 31 Jan 2022 20:01:24 -0800
Subject: [PATCH 1/3] Fix incorrect handling of latin1 without iconv
Wrong regexp was used so if iconv is not present then the tests fail.
---
lib/rfc2047.js | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/lib/rfc2047.js b/lib/rfc2047.js
index 7ca5cc9..cdb6f38 100644
--- a/lib/rfc2047.js
+++ b/lib/rfc2047.js
@@ -1,7 +1,7 @@
/* global unescape */
const isUtf8RegExp = /^utf-?8$/i;
-const isLatin1RegExp = /^(?:iso-8859-1|latin1)$/i;
+const isLatin1RegExp = /^(?:iso-8859-1|latin1|us-ascii)$/i;
const iconvLite = require('iconv-lite');
const rfc2047 = (module.exports = {});
@@ -98,7 +98,7 @@ function decodeEncodedWord(encodedText, encoding, charset) {
) {
return decoded;
}
- } else if (/^(?:us-)?ascii$/i.test(charset)) {
+ } else if (isLatin1RegExp.test(charset)) {
return buffer.toString('ascii');
} else if (iconvLite.encodingExists(charset)) {
decoded = iconvLite.decode(buffer, charset);
From c372d0bdf527b73a7a090db10f8d129040e63f7a Mon Sep 17 00:00:00 2001
From: Vitali Lovich <vlovich@cloudflare.com>
Date: Mon, 31 Jan 2022 17:40:10 -0800
Subject: [PATCH 2/3] Make iconv and iconv-lite support optional
Don't try to require iconv on browser environments in the first place.
Not sure how to make iconv-lite properly configurable at runtime though.
---
lib/rfc2047.js | 21 ++++++++----
package.json | 5 ++-
test/rfc2047.js | 91 +++++++++++++++++++++++++++++++++++--------------
3 files changed, 84 insertions(+), 33 deletions(-)
diff --git a/lib/rfc2047.js b/lib/rfc2047.js
index cdb6f38..d6a153e 100644
--- a/lib/rfc2047.js
+++ b/lib/rfc2047.js
@@ -2,9 +2,21 @@
const isUtf8RegExp = /^utf-?8$/i;
const isLatin1RegExp = /^(?:iso-8859-1|latin1|us-ascii)$/i;
-const iconvLite = require('iconv-lite');
const rfc2047 = (module.exports = {});
+let iconv;
+let iconvLite;
+
+try {
+ iconv = require('iconv');
+} catch (e) {}
+
+if (!iconv) {
+ try {
+ iconvLite = require('iconv-lite');
+ } catch (e) {}
+}
+
function stringify(obj) {
if (typeof obj === 'string') {
return obj;
@@ -15,11 +27,6 @@ function stringify(obj) {
}
}
-let iconv;
-try {
- iconv = require('' + 'iconv'); // Prevent browserify from detecting iconv and failing
-} catch (e) {}
-
const replacementCharacterBuffer = Buffer.from('�');
function decodeBuffer(encodedText, encoding) {
@@ -100,7 +107,7 @@ function decodeEncodedWord(encodedText, encoding, charset) {
}
} else if (isLatin1RegExp.test(charset)) {
return buffer.toString('ascii');
- } else if (iconvLite.encodingExists(charset)) {
+ } else if (iconvLite && iconvLite.encodingExists(charset)) {
decoded = iconvLite.decode(buffer, charset);
if (
!/\ufffd/.test(decoded) ||
diff --git a/package.json b/package.json
index 6bb8faf..530aaa7 100644
--- a/package.json
+++ b/package.json
@@ -42,7 +42,6 @@
"eslint-plugin-node": "^11.1.0",
"eslint-plugin-promise": "^4.2.1",
"eslint-plugin-standard": "^4.0.1",
- "iconv": "^3.0.0",
"mocha": "2.1.0",
"nyc": "^15.1.0",
"prettier": "~2.4.1",
@@ -50,8 +49,12 @@
"unexpected": "10.20.0"
},
"dependencies": {
+ "iconv": "^3.0.0",
"iconv-lite": "0.4.5"
},
+ "browser": {
+ "iconv": false
+ },
"nyc": {
"include": [
"lib/**"
diff --git a/test/rfc2047.js b/test/rfc2047.js
index 59558a0..b3d5442 100644
--- a/test/rfc2047.js
+++ b/test/rfc2047.js
@@ -1,14 +1,47 @@
const unexpected = require('unexpected');
const proxyquire = require('proxyquire');
+const IconvType = {
+ Unavailable: 0,
+ LiteOnly: 1,
+ Available: 2,
+};
+
+function description(iconvType) {
+ switch (iconvType) {
+ case IconvType.Unavailable:
+ return 'iconv unavailable';
+ case IconvType.LiteOnly:
+ return 'iconv-lite available';
+ case IconvType.Available:
+ return 'iconv available';
+ }
+}
+
describe('rfc2047', () => {
- for (const iconvAvailable of [false, true]) {
- describe(`with iconv ${iconvAvailable ? '' : 'un'}available`, () => {
- const rfc2047 = iconvAvailable
- ? require('../lib/rfc2047')
- : proxyquire('../lib/rfc2047', {
- iconv: null,
- });
+ for (const iconvType of [
+ IconvType.Unavailable,
+ IconvType.LiteOnly,
+ IconvType.Available,
+ ]) {
+ describe(`with ${description(iconvType)}`, () => {
+ const requireStubs = {};
+
+ switch (iconvType) {
+ case IconvType.Unavailable:
+ requireStubs['iconv'] = null;
+ requireStubs['iconv-lite'] = null;
+ break;
+ case IconvType.LiteOnly:
+ requireStubs['iconv'] = null;
+ break;
+ }
+
+ const iconvAvailable = iconvType === IconvType.Available;
+ const iconvLiteAvailable =
+ iconvAvailable || iconvType === IconvType.LiteOnly;
+
+ const rfc2047 = proxyquire('../lib/rfc2047', requireStubs);
const expect = unexpected
.clone()
@@ -212,11 +245,13 @@ describe('rfc2047', () => {
'to decode to',
'Patrik Fältström <paf@nada.kth.se>'
);
- expect(
- 'Nathaniel Borenstein <nsb@thumper.bellcore.com> (=?iso-8859-8?b?7eXs+SDv4SDp7Oj08A==?=)',
- 'to decode to',
- 'Nathaniel Borenstein <nsb@thumper.bellcore.com> (םולש ןב ילטפנ)'
- );
+ if (iconvLiteAvailable) {
+ expect(
+ 'Nathaniel Borenstein <nsb@thumper.bellcore.com> (=?iso-8859-8?b?7eXs+SDv4SDp7Oj08A==?=)',
+ 'to decode to',
+ 'Nathaniel Borenstein <nsb@thumper.bellcore.com> (םולש ןב ילטפנ)'
+ );
+ }
expect('(=?ISO-8859-1?Q?a?=)', 'to decode to', '(a)');
expect('(=?ISO-8859-1?Q?a?= b)', 'to decode to', '(a b)');
expect(
@@ -230,11 +265,13 @@ describe('rfc2047', () => {
'(ab)'
);
expect('(=?ISO-8859-1?Q?a_b?=)', 'to decode to', '(a b)');
- expect(
- '(=?ISO-8859-1?Q?a?= =?ISO-8859-2?Q?_b?=)',
- 'to decode to',
- '(a b)'
- );
+ if (iconvLiteAvailable) {
+ expect(
+ '(=?ISO-8859-1?Q?a?= =?ISO-8859-2?Q?_b?=)',
+ 'to decode to',
+ '(a b)'
+ );
+ }
});
it('should handle subject found in mail with X-Mailer: MailChimp Mailer', () => {
@@ -327,17 +364,21 @@ describe('rfc2047', () => {
expect(
'=?ISO-8859-1?B?SWYgeW91IGNhbiByZWFkIHRoaXMgeW8=?==?ISO-8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?==?US-ASCII?Q?.._cool!?=',
'to decode to',
- 'If you can read this you understand the example... cool!'
+ iconvLiteAvailable
+ ? 'If you can read this you understand the example... cool!'
+ : 'If you can read this yo=?ISO-8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?=.. cool!'
);
});
- it('should handle a file name found in a Korean mail', () => {
- expect(
- '=?ks_c_5601-1987?B?MTMwMTE3X8HWwvfA5V+1tcDlX7jetLq+8y5wZGY=?=',
- 'to decode to',
- '130117_주차장_도장_메뉴얼.pdf'
- );
- });
+ if (iconvLiteAvailable) {
+ it('should handle a file name found in a Korean mail', () => {
+ expect(
+ '=?ks_c_5601-1987?B?MTMwMTE3X8HWwvfA5V+1tcDlX7jetLq+8y5wZGY=?=',
+ 'to decode to',
+ '130117_주차장_도장_메뉴얼.pdf'
+ );
+ });
+ }
it('should handle bogus encoded words (spotted in the wild)', () => {
expect(
From 941ae92911ee7649f0ec8d74ba25052261eb7cfb Mon Sep 17 00:00:00 2001
From: Vitali Lovich <vlovich@cloudflare.com>
Date: Tue, 1 Feb 2022 13:14:53 -0800
Subject: [PATCH 3/3] Make the package compatible with browser targets natively
Remove the need for a polyfill by providing an implementation that uses
web APIs.
---
lib/browser-buffer-ops.js | 42 +++
lib/node-buffer-ops.js | 21 ++
lib/rfc2047.js | 21 +-
package.json | 3 +-
test/rfc2047.js | 664 +++++++++++++++++++-------------------
5 files changed, 410 insertions(+), 341 deletions(-)
create mode 100644 lib/browser-buffer-ops.js
create mode 100644 lib/node-buffer-ops.js
diff --git a/lib/browser-buffer-ops.js b/lib/browser-buffer-ops.js
new file mode 100644
index 0000000..a1e09d9
--- /dev/null
+++ b/lib/browser-buffer-ops.js
@@ -0,0 +1,42 @@
+const replacementCharacterBuffer = new Uint8Array([0xef, 0xbf, 0xbd]);
+
+const base64js = require('base64-js');
+
+module.exports = {
+ fromBase64: (b64str) => {
+ try {
+ return base64js.toByteArray(b64str);
+ } catch (e) {
+ return new Uint8Array();
+ }
+ },
+
+ toUtf8: TextEncoder.prototype.encode.bind(new TextEncoder()),
+ fromUtf8: TextDecoder.prototype.decode.bind(new TextDecoder()),
+ fromAscii: TextDecoder.prototype.decode.bind(new TextDecoder('ascii')),
+
+ allocByteBuffer: (length) => {
+ return new Uint8Array(length);
+ },
+
+ includesReplacementCharacter: (haystack) => {
+ const needle = replacementCharacterBuffer;
+ if (haystack.length < needle.length) {
+ return false;
+ }
+ let fromIndex = 0;
+ while (fromIndex !== haystack.length - 3) {
+ const foundFirst = haystack[fromIndex] === needle[0];
+ const foundSecond = haystack[fromIndex + 1] === needle[1];
+ const foundThird = haystack[fromIndex + 2] === needle[2];
+
+ if (foundFirst && foundSecond && foundThird) {
+ return true;
+ } else {
+ fromIndex += 1;
+ }
+ }
+
+ return false;
+ },
+};
diff --git a/lib/node-buffer-ops.js b/lib/node-buffer-ops.js
new file mode 100644
index 0000000..9953da2
--- /dev/null
+++ b/lib/node-buffer-ops.js
@@ -0,0 +1,21 @@
+const replacementCharacterBuffer = new Uint8Array([0xef, 0xbf, 0xbd]);
+
+module.exports = {
+ fromBase64: (b64str) => {
+ return Buffer.from(b64str, 'base64');
+ },
+
+ toUtf8: (str) => {
+ return Buffer.from(str, 'utf-8');
+ },
+ fromUtf8: String,
+ fromAscii: (buffer) => {
+ return buffer.toString('ascii');
+ },
+
+ allocByteBuffer: Buffer.alloc,
+
+ includesReplacementCharacter: (haystack) => {
+ return haystack.includes(replacementCharacterBuffer);
+ },
+};
diff --git a/lib/rfc2047.js b/lib/rfc2047.js
index d6a153e..d20e198 100644
--- a/lib/rfc2047.js
+++ b/lib/rfc2047.js
@@ -2,6 +2,7 @@
const isUtf8RegExp = /^utf-?8$/i;
const isLatin1RegExp = /^(?:iso-8859-1|latin1|us-ascii)$/i;
+const bufferOps = require('./node-buffer-ops');
const rfc2047 = (module.exports = {});
let iconv;
@@ -22,13 +23,13 @@ function stringify(obj) {
return obj;
} else if (obj === null || typeof obj === 'undefined') {
return '';
+ } else if (obj instanceof Uint8Array) {
+ return bufferOps.fromUtf8(obj);
} else {
return String(obj);
}
}
-const replacementCharacterBuffer = Buffer.from('�');
-
function decodeBuffer(encodedText, encoding) {
if (encoding === 'q') {
encodedText = encodedText.replace(/_/g, ' ');
@@ -42,7 +43,7 @@ function decodeBuffer(encodedText, encoding) {
numValidlyEncodedBytes += 1;
}
}
- const buffer = Buffer.alloc(
+ const buffer = bufferOps.allocByteBuffer(
encodedText.length - numValidlyEncodedBytes * 2
);
let j = 0;
@@ -62,7 +63,7 @@ function decodeBuffer(encodedText, encoding) {
}
return buffer;
} else {
- return Buffer.from(encodedText, 'base64');
+ return bufferOps.fromBase64(encodedText);
}
}
@@ -95,23 +96,23 @@ function decodeEncodedWord(encodedText, encoding, charset) {
converter = new iconv.Iconv('iso-8859-1', 'utf-8//TRANSLIT');
}
try {
- return converter.convert(buffer).toString('utf-8');
+ return bufferOps.fromUtf8(converter.convert(buffer));
} catch (e2) {}
} else if (isUtf8RegExp.test(charset)) {
- const decoded = buffer.toString('utf-8');
+ const decoded = bufferOps.fromUtf8(buffer);
if (
!/\ufffd/.test(decoded) ||
- buffer.includes(replacementCharacterBuffer)
+ bufferOps.includesReplacementCharacter(buffer)
) {
return decoded;
}
} else if (isLatin1RegExp.test(charset)) {
- return buffer.toString('ascii');
+ return bufferOps.fromAscii(buffer);
} else if (iconvLite && iconvLite.encodingExists(charset)) {
decoded = iconvLite.decode(buffer, charset);
if (
!/\ufffd/.test(decoded) ||
- buffer.includes(replacementCharacterBuffer)
+ bufferOps.includesReplacementCharacter(buffer)
) {
return decoded;
}
@@ -264,7 +265,7 @@ rfc2047.encode = (text) => {
const charset = 'utf-8';
// Around 25% faster than encodeURIComponent(token.replace(/ /g, "_")).replace(/%/g, "="):
const encodedWordBody = bufferToQuotedPrintableString(
- Buffer.from(token, 'utf-8')
+ bufferOps.toUtf8(token)
);
if (previousTokenWasEncodedWord) {
result += ' ';
diff --git a/package.json b/package.json
index 530aaa7..fddea37 100644
--- a/package.json
+++ b/package.json
@@ -53,7 +53,8 @@
"iconv-lite": "0.4.5"
},
"browser": {
- "iconv": false
+ "iconv": false,
+ "lib/node-buffer-ops.js": "lib/browser-buffer-ops.js"
},
"nyc": {
"include": [
diff --git a/test/rfc2047.js b/test/rfc2047.js
index b3d5442..54cecf2 100644
--- a/test/rfc2047.js
+++ b/test/rfc2047.js
@@ -1,5 +1,5 @@
const unexpected = require('unexpected');
-const proxyquire = require('proxyquire');
+const proxyquire = require('proxyquire').noPreserveCache();
const IconvType = {
Unavailable: 0,
@@ -18,386 +18,390 @@ function description(iconvType) {
}
}
-describe('rfc2047', () => {
- for (const iconvType of [
- IconvType.Unavailable,
- IconvType.LiteOnly,
- IconvType.Available,
- ]) {
- describe(`with ${description(iconvType)}`, () => {
- const requireStubs = {};
-
- switch (iconvType) {
- case IconvType.Unavailable:
- requireStubs['iconv'] = null;
- requireStubs['iconv-lite'] = null;
- break;
- case IconvType.LiteOnly:
- requireStubs['iconv'] = null;
- break;
- }
-
- const iconvAvailable = iconvType === IconvType.Available;
- const iconvLiteAvailable =
- iconvAvailable || iconvType === IconvType.LiteOnly;
-
- const rfc2047 = proxyquire('../lib/rfc2047', requireStubs);
-
- const expect = unexpected
- .clone()
- .addAssertion('to encode to', (expect, subject, value) => {
- expect(rfc2047.encode(subject), 'to equal', value);
- })
- .addAssertion('to decode to', (expect, subject, value) => {
- expect(rfc2047.decode(subject), 'to equal', value);
- })
- .addAssertion(
- 'to encode back and forth to',
- (expect, subject, value) => {
- expect(subject, 'to encode to', value);
- expect(value, 'to decode to', subject);
- }
- );
+for (const environment of ['node', 'browser']) {
+ describe(`${environment} rfc2047`, () => {
+ const iconvTypes = [IconvType.Unavailable, IconvType.LiteOnly];
+ if (environment === 'node') {
+ iconvTypes.push(IconvType.Available);
+ }
+ for (const iconvType of iconvTypes) {
+ describe(`with ${description(iconvType)}`, () => {
+ const requireStubs = {
+ '../lib/node-buffer-ops': require(`../lib/${environment}-buffer-ops`),
+ };
+
+ switch (iconvType) {
+ case IconvType.Unavailable:
+ requireStubs.iconv = null;
+ requireStubs['iconv-lite'] = null;
+ break;
+ case IconvType.LiteOnly:
+ requireStubs.iconv = null;
+ break;
+ }
- describe('#encode() and #decode()', () => {
- it('should handle the empty string', () => {
- expect('', 'to encode back and forth to', '');
- });
+ const iconvAvailable = iconvType === IconvType.Available;
+ const iconvLiteAvailable =
+ iconvAvailable || iconvType === IconvType.LiteOnly;
+
+ const rfc2047 = proxyquire('../lib/rfc2047', requireStubs);
+
+ const expect = unexpected
+ .clone()
+ .addAssertion('to encode to', (expect, subject, value) => {
+ expect(rfc2047.encode(subject), 'to equal', value);
+ })
+ .addAssertion('to decode to', (expect, subject, value) => {
+ expect(rfc2047.decode(subject), 'to equal', value);
+ })
+ .addAssertion(
+ 'to encode back and forth to',
+ (expect, subject, value) => {
+ expect(subject, 'to encode to', value);
+ expect(value, 'to decode to', subject);
+ }
+ );
- it('should handle a string only containing a space', () => {
- expect(' ', 'to encode back and forth to', ' ');
- });
+ describe('#encode() and #decode()', () => {
+ it('should handle the empty string', () => {
+ expect('', 'to encode back and forth to', '');
+ });
- it('should not encode an equals sign', () => {
- expect('=', 'to encode back and forth to', '=');
- });
+ it('should handle a string only containing a space', () => {
+ expect(' ', 'to encode back and forth to', ' ');
+ });
- it('should handle a string that does not need to be encoded', () => {
- expect(
- 'Andreas Lind <andreas@one.com>',
- 'to encode back and forth to',
- 'Andreas Lind <andreas@one.com>'
- );
- });
+ it('should not encode an equals sign', () => {
+ expect('=', 'to encode back and forth to', '=');
+ });
- it('should handle a multi-word string where the middle word has to be encoded', () => {
- expect(
- 'Andreas Lindø <andreas@one.com>',
- 'to encode back and forth to',
- 'Andreas =?utf-8?Q?Lind=C3=B8?= <andreas@one.com>'
- );
- });
+ it('should handle a string that does not need to be encoded', () => {
+ expect(
+ 'Andreas Lind <andreas@one.com>',
+ 'to encode back and forth to',
+ 'Andreas Lind <andreas@one.com>'
+ );
+ });
- it('should use an UTF-8 encoded word when a character is not in iso-8859-1', () => {
- expect(
- 'Mr. Smiley face aka ☺ <smiley@face.dk>',
- 'to encode back and forth to',
- 'Mr. Smiley face aka =?utf-8?Q?=E2=98=BA?= <smiley@face.dk>'
- );
- });
+ it('should handle a multi-word string where the middle word has to be encoded', () => {
+ expect(
+ 'Andreas Lindø <andreas@one.com>',
+ 'to encode back and forth to',
+ 'Andreas =?utf-8?Q?Lind=C3=B8?= <andreas@one.com>'
+ );
+ });
- it('should handle two neighbouring words that have to be encoded', () => {
- expect(
- '¡Hola, señor!',
- 'to encode back and forth to',
- '=?utf-8?Q?=C2=A1Hola=2C?= =?utf-8?Q?_se=C3=B1or!?='
- );
- expect(
- 'På lördag',
- 'to encode back and forth to',
- '=?utf-8?Q?P=C3=A5?= =?utf-8?Q?_l=C3=B6rdag?='
- );
- });
+ it('should use an UTF-8 encoded word when a character is not in iso-8859-1', () => {
+ expect(
+ 'Mr. Smiley face aka ☺ <smiley@face.dk>',
+ 'to encode back and forth to',
+ 'Mr. Smiley face aka =?utf-8?Q?=E2=98=BA?= <smiley@face.dk>'
+ );
+ });
- it('should not rely on the space between neighbouring encoded words to be preserved', () => {
- expect(
- '☺ ☺',
- 'to encode back and forth to',
- '=?utf-8?Q?=E2=98=BA?= =?utf-8?Q?_=E2=98=BA?='
- );
- });
+ it('should handle two neighbouring words that have to be encoded', () => {
+ expect(
+ '¡Hola, señor!',
+ 'to encode back and forth to',
+ '=?utf-8?Q?=C2=A1Hola=2C?= =?utf-8?Q?_se=C3=B1or!?='
+ );
+ expect(
+ 'På lördag',
+ 'to encode back and forth to',
+ '=?utf-8?Q?P=C3=A5?= =?utf-8?Q?_l=C3=B6rdag?='
+ );
+ });
- it('should handle some dreamed up edge cases', () => {
- expect(
- 'lördag',
- 'to encode back and forth to',
- '=?utf-8?Q?l=C3=B6rdag?='
- );
- });
+ it('should not rely on the space between neighbouring encoded words to be preserved', () => {
+ expect(
+ '☺ ☺',
+ 'to encode back and forth to',
+ '=?utf-8?Q?=E2=98=BA?= =?utf-8?Q?_=E2=98=BA?='
+ );
+ });
- it('should handle a multi-word string where the middle word has to be left unencoded', () => {
- expect(
- 'Så er fødselen i gang',
- 'to encode back and forth to',
- '=?utf-8?Q?S=C3=A5?= er =?utf-8?Q?f=C3=B8dselen?= i gang'
- );
- });
+ it('should handle some dreamed up edge cases', () => {
+ expect(
+ 'lördag',
+ 'to encode back and forth to',
+ '=?utf-8?Q?l=C3=B6rdag?='
+ );
+ });
- it('should place leading quotes correctly', () => {
- expect(
- '"ÅÄÖ" <sss@example.com>',
- 'to encode back and forth to',
- '"=?utf-8?Q?=C3=85=C3=84=C3=96?=" <sss@example.com>'
- );
- });
+ it('should handle a multi-word string where the middle word has to be left unencoded', () => {
+ expect(
+ 'Så er fødselen i gang',
+ 'to encode back and forth to',
+ '=?utf-8?Q?S=C3=A5?= er =?utf-8?Q?f=C3=B8dselen?= i gang'
+ );
+ });
- it('should place trailing quotes correctly', () => {
- expect(
- '"TEST ÅÄÖ" <sss@example.com>',
- 'to encode back and forth to',
- '"TEST =?utf-8?Q?=C3=85=C3=84=C3=96?=" <sss@example.com>'
- );
- });
+ it('should place leading quotes correctly', () => {
+ expect(
+ '"ÅÄÖ" <sss@example.com>',
+ 'to encode back and forth to',
+ '"=?utf-8?Q?=C3=85=C3=84=C3=96?=" <sss@example.com>'
+ );
+ });
- // Regression test for #2:
- it('should handle an emoji test case', () => {
- expect(
- '{"tags":"","fullName":"😬"}',
- 'to encode back and forth to',
- '=?utf-8?Q?{=22tags=22=3A?=""=?utf-8?Q?=2C=22fullNa?= =?utf-8?Q?me=22=3A=22=F0=9F=98=AC=22?=}'
- );
- });
+ it('should place trailing quotes correctly', () => {
+ expect(
+ '"TEST ÅÄÖ" <sss@example.com>',
+ 'to encode back and forth to',
+ '"TEST =?utf-8?Q?=C3=85=C3=84=C3=96?=" <sss@example.com>'
+ );
+ });
- it('should handle the replacement character', () => {
- expect(
- 'test_�.docx',
- 'to encode back and forth to',
- '=?utf-8?Q?test=5F=EF=BF=BD=2Ed?=ocx'
- );
- });
- });
+ // Regression test for #2:
+ it('should handle an emoji test case', () => {
+ expect(
+ '{"tags":"","fullName":"😬"}',
+ 'to encode back and forth to',
+ '=?utf-8?Q?{=22tags=22=3A?=""=?utf-8?Q?=2C=22fullNa?= =?utf-8?Q?me=22=3A=22=F0=9F=98=AC=22?=}'
+ );
+ });
- describe('#encode()', () => {
- it('should handle non-string values correctly', () => {
- expect(-1, 'to encode to', '-1');
- expect(Infinity, 'to encode to', 'Infinity');
- expect(false, 'to encode to', 'false');
- expect(true, 'to encode to', 'true');
- expect(/bla/, 'to encode to', '/bla/');
- expect(undefined, 'to encode to', '');
- expect(null, 'to encode to', '');
+ it('should handle the replacement character', () => {
+ expect(
+ 'test_�.docx',
+ 'to encode back and forth to',
+ '=?utf-8?Q?test=5F=EF=BF=BD=2Ed?=ocx'
+ );
+ });
});
- it('should handle a tab character at the beginning of a word', () => {
- expect('\tfoo', 'to encode to', ' foo');
- });
+ describe('#encode()', () => {
+ it('should handle non-string values correctly', () => {
+ expect(-1, 'to encode to', '-1');
+ expect(Infinity, 'to encode to', 'Infinity');
+ expect(false, 'to encode to', 'false');
+ expect(true, 'to encode to', 'true');
+ expect(/bla/, 'to encode to', '/bla/');
+ expect(undefined, 'to encode to', '');
+ expect(null, 'to encode to', '');
+ });
- it('should handle control chars', () => {
- expect(
- '\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f',
- 'to encode to',
- '=?utf-8?Q?=00=01=02=03=04=05=06=07?= =?utf-8?Q?=08?= =?utf-8?Q?_=0E=0F=10=11=12=13=14=15?= =?utf-8?Q?=16=17=18=19=1A=1B=1C=1D?= =?utf-8?Q?=1E=1F?='
- );
- });
+ it('should handle a tab character at the beginning of a word', () => {
+ expect('\tfoo', 'to encode to', ' foo');
+ });
- it('should handle a tab character at the end of a word', () => {
- expect('foo\t', 'to encode to', 'foo ');
- });
+ it('should handle control chars', () => {
+ expect(
+ '\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f',
+ 'to encode to',
+ '=?utf-8?Q?=00=01=02=03=04=05=06=07?= =?utf-8?Q?=08?= =?utf-8?Q?_=0E=0F=10=11=12=13=14=15?= =?utf-8?Q?=16=17=18=19=1A=1B=1C=1D?= =?utf-8?Q?=1E=1F?='
+ );
+ });
- it('should handle a tab character with spaces around it', () => {
- expect('bar \t foo', 'to encode to', 'bar foo');
- });
+ it('should handle a tab character at the end of a word', () => {
+ expect('foo\t', 'to encode to', 'foo ');
+ });
- it('should not split a backslash from the doublequote it is escaping', () => {
- expect('"Öland\\""', 'to encode to', '"=?utf-8?Q?=C3=96land?=\\""');
- });
- });
+ it('should handle a tab character with spaces around it', () => {
+ expect('bar \t foo', 'to encode to', 'bar foo');
+ });
- describe('#decode()', () => {
- it('should handle non-string values correctly', () => {
- expect(-1, 'to decode to', '-1');
- expect(Infinity, 'to decode to', 'Infinity');
- expect(false, 'to decode to', 'false');
- expect(true, 'to decode to', 'true');
- expect(/bla/, 'to decode to', '/bla/');
- expect(undefined, 'to decode to', '');
- expect(null, 'to decode to', '');
+ it('should not split a backslash from the doublequote it is escaping', () => {
+ expect('"Öland\\""', 'to encode to', '"=?utf-8?Q?=C3=96land?=\\""');
+ });
});
- it('should decode encoded word with invalid quoted-printable, decodeURIComponent case', () => {
- expect('=?UTF-8?Q?=xxfoo?=', 'to decode to', '=xxfoo');
- });
+ describe('#decode()', () => {
+ it('should handle non-string values correctly', () => {
+ expect(-1, 'to decode to', '-1');
+ expect(Infinity, 'to decode to', 'Infinity');
+ expect(false, 'to decode to', 'false');
+ expect(true, 'to decode to', 'true');
+ expect(/bla/, 'to decode to', '/bla/');
+ expect(undefined, 'to decode to', '');
+ expect(null, 'to decode to', '');
+ });
- it('should decode encoded word with invalid quoted-printable, unescape case', () => {
- expect('=?iso-8859-1?Q?=xxfoo?=', 'to decode to', '=xxfoo');
- });
+ it('should decode encoded word with invalid quoted-printable, decodeURIComponent case', () => {
+ expect('=?UTF-8?Q?=xxfoo?=', 'to decode to', '=xxfoo');
+ });
- it('should decode encoded word with invalid base64', () => {
- expect('=?iso-8859-1?B?\u0000``?=', 'to decode to', '');
- });
+ it('should decode encoded word with invalid quoted-printable, unescape case', () => {
+ expect('=?iso-8859-1?Q?=xxfoo?=', 'to decode to', '=xxfoo');
+ });
- it('should decode separated encoded words', () => {
- expect(
- '=?utf-8?Q?One.com=E2=80?= =?utf-8?Q?=99s_=E2=80=9CDon=E2=80=99t_screw_it_up=E2=80=9D_?= =?utf-8?Q?code?=',
- 'to decode to',
- 'One.com’s “Don’t screw it up” code'
- );
- });
+ it('should decode encoded word with invalid base64', () => {
+ expect('=?iso-8859-1?B?\u0000``?=', 'to decode to', '');
+ });
- it('should handle the test cases listed in RFC 2047', () => {
- expect(
- '=?ISO-8859-1?Q?Olle_J=E4rnefors?= <ojarnef@admin.kth.se>',
- 'to decode to',
- 'Olle Järnefors <ojarnef@admin.kth.se>'
- );
- expect(
- '=?ISO-8859-1?Q?Patrik_F=E4ltstr=F6m?= <paf@nada.kth.se>',
- 'to decode to',
- 'Patrik Fältström <paf@nada.kth.se>'
- );
- if (iconvLiteAvailable) {
+ it('should decode separated encoded words', () => {
expect(
- 'Nathaniel Borenstein <nsb@thumper.bellcore.com> (=?iso-8859-8?b?7eXs+SDv4SDp7Oj08A==?=)',
+ '=?utf-8?Q?One.com=E2=80?= =?utf-8?Q?=99s_=E2=80=9CDon=E2=80=99t_screw_it_up=E2=80=9D_?= =?utf-8?Q?code?=',
'to decode to',
- 'Nathaniel Borenstein <nsb@thumper.bellcore.com> (םולש ןב ילטפנ)'
+ 'One.com’s “Don’t screw it up” code'
);
- }
- expect('(=?ISO-8859-1?Q?a?=)', 'to decode to', '(a)');
- expect('(=?ISO-8859-1?Q?a?= b)', 'to decode to', '(a b)');
- expect(
- '(=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=)',
- 'to decode to',
- '(ab)'
- );
- expect(
- '(=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=)',
- 'to decode to',
- '(ab)'
- );
- expect('(=?ISO-8859-1?Q?a_b?=)', 'to decode to', '(a b)');
- if (iconvLiteAvailable) {
+ });
+
+ it('should handle the test cases listed in RFC 2047', () => {
expect(
- '(=?ISO-8859-1?Q?a?= =?ISO-8859-2?Q?_b?=)',
+ '=?ISO-8859-1?Q?Olle_J=E4rnefors?= <ojarnef@admin.kth.se>',
'to decode to',
- '(a b)'
+ 'Olle Järnefors <ojarnef@admin.kth.se>'
);
- }
- });
-
- it('should handle subject found in mail with X-Mailer: MailChimp Mailer', () => {
- expect(
- '=?utf-8?Q?Spar=2020=20%=20p=C3=A5=20de=20bedste=20businessb=C3=B8ger=20fra=20Gyldendal=21?=',
- 'to decode to',
- 'Spar 20 % på de bedste businessbøger fra Gyldendal!'
- );
- expect(
- '=?iso-8859-1?Q?Spar 20 %...?=',
- 'to decode to',
- 'Spar 20 %...'
- );
- });
+ expect(
+ '=?ISO-8859-1?Q?Patrik_F=E4ltstr=F6m?= <paf@nada.kth.se>',
+ 'to decode to',
+ 'Patrik Fältström <paf@nada.kth.se>'
+ );
+ if (iconvLiteAvailable) {
+ expect(
+ 'Nathaniel Borenstein <nsb@thumper.bellcore.com> (=?iso-8859-8?b?7eXs+SDv4SDp7Oj08A==?=)',
+ 'to decode to',
+ 'Nathaniel Borenstein <nsb@thumper.bellcore.com> (םולש ןב ילטפנ)'
+ );
+ }
+ expect('(=?ISO-8859-1?Q?a?=)', 'to decode to', '(a)');
+ expect('(=?ISO-8859-1?Q?a?= b)', 'to decode to', '(a b)');
+ expect(
+ '(=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=)',
+ 'to decode to',
+ '(ab)'
+ );
+ expect(
+ '(=?ISO-8859-1?Q?a?= =?ISO-8859-1?Q?b?=)',
+ 'to decode to',
+ '(ab)'
+ );
+ expect('(=?ISO-8859-1?Q?a_b?=)', 'to decode to', '(a b)');
+ if (iconvLiteAvailable) {
+ expect(
+ '(=?ISO-8859-1?Q?a?= =?ISO-8859-2?Q?_b?=)',
+ 'to decode to',
+ '(a b)'
+ );
+ }
+ });
- it('should handle multiple base64 encoded words issued by Thunderbird', () => {
- expect(
- '=?UTF-8?B?Rm9vw6YsIEZvbyDDpiwgw6bDuMOmw7jDpsO4w6bDuMOmw7jDpsO4LCA=?==?UTF-8?B?4pi6IE1y4pi6IOKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYug==?= =?UTF-8?B?4pi64pi64pi64pi64pi64pi64pi6?=',
- 'to decode to',
- 'Fooæ, Foo æ, æøæøæøæøæøæø, ☺ Mr☺ ☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺'
- );
- });
+ it('should handle subject found in mail with X-Mailer: MailChimp Mailer', () => {
+ expect(
+ '=?utf-8?Q?Spar=2020=20%=20p=C3=A5=20de=20bedste=20businessb=C3=B8ger=20fra=20Gyldendal=21?=',
+ 'to decode to',
+ 'Spar 20 % på de bedste businessbøger fra Gyldendal!'
+ );
+ expect(
+ '=?iso-8859-1?Q?Spar 20 %...?=',
+ 'to decode to',
+ 'Spar 20 %...'
+ );
+ });
- it('should handle two back-to-back UTF-8 encoded words from the subject in a raygun mail', () => {
- expect(
- '=?utf-8?B?d2VibWFpbCBwcm9kdWN0aW9uIC0gbmV3IGVycm9yIC0gR2XD?==?utf-8?B?p2Vyc2l6IGRlxJ9pxZ9rZW4u?=',
- 'to decode to',
- 'webmail production - new error - Geçersiz değişken.'
- );
- });
+ it('should handle multiple base64 encoded words issued by Thunderbird', () => {
+ expect(
+ '=?UTF-8?B?Rm9vw6YsIEZvbyDDpiwgw6bDuMOmw7jDpsO4w6bDuMOmw7jDpsO4LCA=?==?UTF-8?B?4pi6IE1y4pi6IOKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYuuKYug==?= =?UTF-8?B?4pi64pi64pi64pi64pi64pi64pi6?=',
+ 'to decode to',
+ 'Fooæ, Foo æ, æøæøæøæøæøæø, ☺ Mr☺ ☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺☺'
+ );
+ });
- it('should keep encoded words with partial sequences separate if there is text between them', () => {
- expect(
- '=?utf-8?B?d2VibWFpbCBwcm9kdWN0aW9uIC0gbmV3IGVycm9yIC0gR2XD?=foo=?utf-8?B?p2Vyc2l6IGRlxJ9pxZ9rZW4u?=',
- 'to decode to',
- '=?utf-8?B?d2VibWFpbCBwcm9kdWN0aW9uIC0gbmV3IGVycm9yIC0gR2XD?=foo=?utf-8?B?p2Vyc2l6IGRlxJ9pxZ9rZW4u?='
- );
- });
+ it('should handle two back-to-back UTF-8 encoded words from the subject in a raygun mail', () => {
+ expect(
+ '=?utf-8?B?d2VibWFpbCBwcm9kdWN0aW9uIC0gbmV3IGVycm9yIC0gR2XD?==?utf-8?B?p2Vyc2l6IGRlxJ9pxZ9rZW4u?=',
+ 'to decode to',
+ 'webmail production - new error - Geçersiz değişken.'
+ );
+ });
- it('should decode a UTF-8 smiley (illegally) split up into 2 encoded words', () => {
- expect('=?utf-8?Q?=E2=98?= =?utf-8?Q?=BA?=', 'to decode to', '☺');
- });
+ it('should keep encoded words with partial sequences separate if there is text between them', () => {
+ expect(
+ '=?utf-8?B?d2VibWFpbCBwcm9kdWN0aW9uIC0gbmV3IGVycm9yIC0gR2XD?=foo=?utf-8?B?p2Vyc2l6IGRlxJ9pxZ9rZW4u?=',
+ 'to decode to',
+ '=?utf-8?B?d2VibWFpbCBwcm9kdWN0aW9uIC0gbmV3IGVycm9yIC0gR2XD?=foo=?utf-8?B?p2Vyc2l6IGRlxJ9pxZ9rZW4u?='
+ );
+ });
- it('should decode a UTF-8 smiley (illegally) split up into 3 encoded words', () => {
- expect(
- '=?utf-8?Q?=E2?= =?utf-8?Q?=98?= =?utf-8?Q?=BA?=',
- 'to decode to',
- '☺'
- );
- });
+ it('should decode a UTF-8 smiley (illegally) split up into 2 encoded words', () => {
+ expect('=?utf-8?Q?=E2=98?= =?utf-8?Q?=BA?=', 'to decode to', '☺');
+ });
- it('should give up decoding a UTF-8 smiley (illegally) split up into 3 encoded words if there is regular text between the encoded words', () => {
- expect(
- '=?utf-8?Q?=E2?= =?utf-8?Q?=98?=a=?utf-8?Q?=BA?==?utf-8?Q?=BA?=a',
- 'to decode to',
- '=?utf-8?Q?=E2?==?utf-8?Q?=98?=a=?utf-8?Q?=BA?==?utf-8?Q?=BA?=a'
- );
- });
+ it('should decode a UTF-8 smiley (illegally) split up into 3 encoded words', () => {
+ expect(
+ '=?utf-8?Q?=E2?= =?utf-8?Q?=98?= =?utf-8?Q?=BA?=',
+ 'to decode to',
+ '☺'
+ );
+ });
- it('should decode an encoded word following a undecodable sequence of encoded words', () => {
- expect(
- '=?utf-8?Q?=E2?= =?utf-8?Q?=98?= =?iso-8859-1?Q?=A1?=Hola, se=?iso-8859-1?Q?=F1?=or!',
- 'to decode to',
- '=?utf-8?Q?=E2?==?utf-8?Q?=98?=¡Hola, señor!'
- );
- });
+ it('should give up decoding a UTF-8 smiley (illegally) split up into 3 encoded words if there is regular text between the encoded words', () => {
+ expect(
+ '=?utf-8?Q?=E2?= =?utf-8?Q?=98?=a=?utf-8?Q?=BA?==?utf-8?Q?=BA?=a',
+ 'to decode to',
+ '=?utf-8?Q?=E2?==?utf-8?Q?=98?=a=?utf-8?Q?=BA?==?utf-8?Q?=BA?=a'
+ );
+ });
- it('should handle test cases from the MIME tools package', () => {
- // From http://search.cpan.org/~dskoll/MIME-tools-5.502/lib/MIME/Words.pm:
- expect(
- '=?ISO-8859-1?Q?Keld_J=F8rn_Simonsen?= <keld@dkuug.dk>',
- 'to decode to',
- 'Keld Jørn Simonsen <keld@dkuug.dk>'
- );
- expect(
- '=?US-ASCII?Q?Keith_Moore?= <moore@cs.utk.edu>',
- 'to decode to',
- 'Keith Moore <moore@cs.utk.edu>'
- );
- expect(
- '=?ISO-8859-1?Q?Andr=E9_?= Pirard <PIRARD@vm1.ulg.ac.be>',
- 'to decode to',
- 'André Pirard <PIRARD@vm1.ulg.ac.be>'
- );
- expect(
- '=?iso-8859-1?Q?J=F8rgen_Nellemose?=',
- 'to decode to',
- 'Jørgen Nellemose'
- );
- expect(
- '=?ISO-8859-1?B?SWYgeW91IGNhbiByZWFkIHRoaXMgeW8=?==?ISO-8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?==?US-ASCII?Q?.._cool!?=',
- 'to decode to',
- iconvLiteAvailable
- ? 'If you can read this you understand the example... cool!'
- : 'If you can read this yo=?ISO-8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?=.. cool!'
- );
- });
+ it('should decode an encoded word following a undecodable sequence of encoded words', () => {
+ expect(
+ '=?utf-8?Q?=E2?= =?utf-8?Q?=98?= =?iso-8859-1?Q?=A1?=Hola, se=?iso-8859-1?Q?=F1?=or!',
+ 'to decode to',
+ '=?utf-8?Q?=E2?==?utf-8?Q?=98?=¡Hola, señor!'
+ );
+ });
- if (iconvLiteAvailable) {
- it('should handle a file name found in a Korean mail', () => {
+ it('should handle test cases from the MIME tools package', () => {
+ // From http://search.cpan.org/~dskoll/MIME-tools-5.502/lib/MIME/Words.pm:
expect(
- '=?ks_c_5601-1987?B?MTMwMTE3X8HWwvfA5V+1tcDlX7jetLq+8y5wZGY=?=',
+ '=?ISO-8859-1?Q?Keld_J=F8rn_Simonsen?= <keld@dkuug.dk>',
'to decode to',
- '130117_주차장_도장_메뉴얼.pdf'
+ 'Keld Jørn Simonsen <keld@dkuug.dk>'
+ );
+ expect(
+ '=?US-ASCII?Q?Keith_Moore?= <moore@cs.utk.edu>',
+ 'to decode to',
+ 'Keith Moore <moore@cs.utk.edu>'
+ );
+ expect(
+ '=?ISO-8859-1?Q?Andr=E9_?= Pirard <PIRARD@vm1.ulg.ac.be>',
+ 'to decode to',
+ 'André Pirard <PIRARD@vm1.ulg.ac.be>'
+ );
+ expect(
+ '=?iso-8859-1?Q?J=F8rgen_Nellemose?=',
+ 'to decode to',
+ 'Jørgen Nellemose'
+ );
+ expect(
+ '=?ISO-8859-1?B?SWYgeW91IGNhbiByZWFkIHRoaXMgeW8=?==?ISO-8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?==?US-ASCII?Q?.._cool!?=',
+ 'to decode to',
+ iconvLiteAvailable
+ ? 'If you can read this you understand the example... cool!'
+ : 'If you can read this yo=?ISO-8859-2?B?dSB1bmRlcnN0YW5kIHRoZSBleGFtcGxlLg==?=.. cool!'
);
});
- }
- it('should handle bogus encoded words (spotted in the wild)', () => {
- expect(
- '=?utf-8?Q??= <andreas@one.com>',
- 'to decode to',
- ' <andreas@one.com>'
- );
- });
+ if (iconvLiteAvailable) {
+ it('should handle a file name found in a Korean mail', () => {
+ expect(
+ '=?ks_c_5601-1987?B?MTMwMTE3X8HWwvfA5V+1tcDlX7jetLq+8y5wZGY=?=',
+ 'to decode to',
+ '130117_주차장_도장_메뉴얼.pdf'
+ );
+ });
+ }
- if (iconvAvailable) {
- it('should decode a character set not in iconv-lite', () => {
+ it('should handle bogus encoded words (spotted in the wild)', () => {
expect(
- '=?iso-2022-jp?B?GyRCRnxLXDhsJE4lNSVWJTglJyUvJUghXRsoQnRlc3Q=?=',
+ '=?utf-8?Q??= <andreas@one.com>',
'to decode to',
- '日本語のサブジェクト−test'
+ ' <andreas@one.com>'
);
});
- }
+
+ if (iconvAvailable) {
+ it('should decode a character set not in iconv-lite', () => {
+ expect(
+ '=?iso-2022-jp?B?GyRCRnxLXDhsJE4lNSVWJTglJyUvJUghXRsoQnRlc3Q=?=',
+ 'to decode to',
+ '日本語のサブジェクト−test'
+ );
+ });
+ }
+ });
});
- });
- }
-});
+ }
+ });
+}