mirrors/CyberChef
1
0
Fork 0
mirror of https://github.com/gchq/CyberChef.git synced 2025-05-09 15:55:01 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

working on email parsing

Browse source
This commit is contained in:
Brian Whitney 2018-11-21 15:26:09 -05:00
parent 13b10a68a2
commit 39fd016717
1 changed files with 18 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

34
src/core/operations/ParseIMF.mjs
View file

@ -79,15 +79,15 @@ class ParseIMF extends Operation {
*/ */
run(input, args) { run(input, args) {
if (!input) { if (!input) {
return; return "";
} }
let headerBody = this.splitHeaderFromBody(input); let headerBody = splitHeaderFromBody(input);
let header = headerBody[0]; let header = headerBody[0];
let headerArray = this.parseHeader(header); let headerArray = parseHeader(header);
if (args[0]) { if (true) {
header = this.replaceDecodeWord(header); header = replaceDecodeWord(header);
} }
return JSON.stringify(headerArray); return header;
} }
/** /**
@ -96,8 +96,8 @@ class ParseIMF extends Operation {
* @param {string} input * @param {string} input
* @returns {string[]} * @returns {string[]}
*/ */
splitHeaderFromBody(input) { static splitHeaderFromBody(input) {
const emlRegex = /^([\x20-\x7e\n\r\t]+?)(?:\r?\n){2}([\x20-\x7e\t\n\r]*)/; const emlRegex = /^([\x20-\xff\n\r\t]+?)(?:\r?\n){2}([\x20-\xff\t\n\r]*)/;
let splitEmail = emlRegex.exec(input); let splitEmail = emlRegex.exec(input);
if (splitEmail) { if (splitEmail) {
//TODO: Array splice vs shift? //TODO: Array splice vs shift?
@ -113,11 +113,13 @@ class ParseIMF extends Operation {
* @param {string} input * @param {string} input
* @returns {string} * @returns {string}
*/ */
replaceDecodeWord(input) { static replaceDecodeWord(input) {
return input.replace(/=\?([^?]+)\?(Q|B)\?([^?]+)\?=/g, function (a, charEnc, contEnc, input) { return input.replace(/=\?([^?]+)\?(Q|B)\?([^?]+)\?=/g, function (a, charEnc, contEnc, input) {
//TODO fix Q encoding as it isn't identical to quoted-printable. ie _=" "
contEnc = (contEnc === "B") ? "base64" : "quoted-printable"; contEnc = (contEnc === "B") ? "base64" : "quoted-printable";
return this.decodeMimeData(input, charEnc, contEnc); if (contEnc === "quoted-printable") {
input = input.replace("_", " ");
}
return decodeMimeData(input, charEnc, contEnc);
}); });
} }
@ -129,7 +131,7 @@ class ParseIMF extends Operation {
* @param {string} input * @param {string} input
* @returns {object} * @returns {object}
*/ */
parseHeader(input) { static parseHeader(input) {
const sectionRegex = /([A-Z-]+):\s+([\x20-\x7e\r\n\t]+?)(?=$|\r?\n\S)/gi; const sectionRegex = /([A-Z-]+):\s+([\x20-\x7e\r\n\t]+?)(?=$|\r?\n\S)/gi;
let header = {}, section; let header = {}, section;
while ((section = sectionRegex.exec(input))) { while ((section = sectionRegex.exec(input))) {
@ -152,11 +154,11 @@ class ParseIMF extends Operation {
* @param {string} contEnc * @param {string} contEnc
* @returns {string} * @returns {string}
*/ */
decodeMimeData(input, charEnc, contEnc) { static decodeMimeData(input, charEnc, contEnc) {
//TODO: make exceptions for unknown charEnc and contEnc? //TODO: make exceptions for unknown charEnc and contEnc?
input = this.DECODER[contEnc](input); input = DECODER[contEnc](input);
if (charEnc) { if (charEnc) {
input = cptable.utils.decode(this.MIME_FORMAT[charEnc.toLowerCase()], input); input = cptable.utils.decode(MIME_FORMAT[charEnc.toLowerCase()], input);
} }
return input; return input;
} }
@ -169,7 +171,7 @@ class ParseIMF extends Operation {
* @param {integer} fieldNum * @param {integer} fieldNum
* @returns {string} * @returns {string}
*/ */
getHeaderItem(header, fieldItem, fieldNum = 0){ static getHeaderItem(header, fieldItem, fieldNum = 0){
if (fieldItem[1] in header && header[fieldItem[1]].length > fieldNum) { if (fieldItem[1] in header && header[fieldItem[1]].length > fieldNum) {
let field = header[fieldItem[1]][fieldNum], item; let field = header[fieldItem[1]][fieldNum], item;
if ((item = fieldItem[0].exec(field))) { if ((item = fieldItem[0].exec(field))) {