email-bounce-parser 1.0.16 → 1.0.18

package/README.md

@@ -39,7 +39,7 @@ console.log(result);
 ### Parse a bounce email
 
 `read(body)` parses the bounce email and extracts available information (error code and type, server, original recipient, etc.):
-* `body` must be a string representing the bounce email body (as returned by [mailparser](https://github.com/nodemailer/mailparser), for example)
+* `body` must be a string representing the bounce email **text** body (not HTML body). You can use [mailparser](https://github.com/nodemailer/mailparser) for example.
 
 ```js
 const EmailBounceParse = require("email-bounce-parser");
@@ -53,7 +53,7 @@ console.log(result);
 //   email: {
 //     body: "This is the mail system at host mailer.acme.email [...] (in reply to RCPT TO command)",
 //     intro: "This is the mail system at host mailer.acme.email [...] The mail system",
-//     error: "<support@yipee.com>: host smtp.secureserver.net[92.240.81.0] said: [...] (in reply to RCPT TO command)"
+//     error: "<john@yipee.com>: host smtp.secureserver.net[92.240.81.0] said: [...] (in reply to RCPT TO command)"
 //   },
 //
 //   data: {
@@ -62,7 +62,7 @@ console.log(result);
 //         basic: "550",
 //         enhanced: "5.1.1"
 //       },
-//       label: "<support@yipee.com> Recipient not found.",
+//       label: "<john@yipee.com> Recipient not found.",
 //
 //       type: "action_not_taken",
 //
@@ -76,6 +76,8 @@ console.log(result);
 //       }
 //     },
 //
+//     recipient: "john@yipee.com",
+//
 //     server: {
 //       hostname: "smtp.secureserver.net",
 //       ip: "92.240.81.0",

package/lib/parser.js

@@ -65,8 +65,8 @@ var REGEXES = {
     /\(in reply to end of ([A-Z\s]+) command\)$/m, // "in reply to end of DATA command"
     /\(in reply to ([A-Z\s]+) command\)$/m, // "in reply to RCPT TO command"
     /timed out while sending ([A-Z\s]+)$/m, // "timed out while sending (RCPT TO)", "timed out while sending RCPT TO"
-    /error after ([A-Z\s]+)/m, // "LMTP error after RCPT TO"
-    /while sending end of ([a-z\s]+)/m // "while sending end of data"
+    /error after ([A-Z\s]+)/i, // "LMTP error after RCPT TO"
+    /while sending end of ([a-z\s]+)/i // "while sending end of data"
   ],
 
   email_server : [
@@ -82,21 +82,30 @@ var REGEXES = {
   ],
 
   error : [
-    /said\: (\d{3}(?:[\s\-]\d\.\d\.\d\d?)?) (.+) \(in reply to/,
-    /said\: (\d{3}(?:[\s\-]\d\.\d\.\d\d?)?)-(.+)/,
-    /(\d{3}\-\'\d\.\d\.\d\d?) (.+)/,
-    /LMTP error after .+?\:\<.+?\>\: (\d{3}(?:[\s\-]\d\.\d\.\d\d?)?) <.+?\>(.+)$/m,
-    /remote server returned \'(\d{3}(?:[\s\-]\d\.\d\.\d\d?)?) (.+)\'/i,
-    /The response from the remote server was:\s(\d{3}(?:[\s\-]\d\.\d\.\d\d?)?) (.+)/,
-    /refused to talk to me\: (\d{3}(?:[\s\-]\d\.\d\.\d\d?)?) (.+)/,
-    /(?:error|reason)\:\s*?(\d{3}(?:[\s\-]\d\.\d\.\d\d?)?) (.+)/i,
-    /(\d{3}[\s\-]\d\.\d\.\d\d?)/,
-    /(\d{3}\-\'\d\.\d\.\d\d?)/
+    /said\: (\d{3}(?:[\s\-]\d\.\d\.\d{1,3})?) (.+) \(in reply to/,
+    /said\: (\d{3}(?:[\s\-]\d\.\d\.\d{1,3})?)-(.+)/,
+    /(\d{3}\-\'\d\.\d\.\d{1,3}) (.+)/,
+    /LMTP error after .+?\:\<.+?\>\: (\d{3}(?:[\s\-]\d\.\d\.\d{1,3})?) <.+?\>(.+)$/m,
+    /remote server returned \'(\d{3}(?:[\s\-]\d\.\d\.\d{1,3})?) (.+)\'/i,
+    /The response from the remote server was:\s(\d{3}(?:[\s\-]\d\.\d\.\d{1,3})?) (.+)/,
+    /refused to talk to me\: (\d{3}(?:[\s\-]\d\.\d\.\d{1,3})?) (.+)/,
+    /(?:error|reason)\:\s*?(\d{3}(?:[\s\-]\d\.\d\.\d{1,3})?) (.+)/i,
+    /(\d{3}[\s\-]\d\.\d\.\d{1,3})/,
+    /(\d{3}\-\'\d\.\d\.\d{1,3})/
   ],
 
   error_lax : [
     /^(?:\<.+?\> \(expanded from \<.+?\>\)\:)(.+)/m, // "<john@acme.com> (expanded from <john@digiflex.com>):  Domain name not found"
-    /^(?:\<.+?\>\:)(.+)/m // "<john@acme.com>: Domain name not found"
+    /^(?:\<.+?\>\:)(.+)/m, // "<john@acme.com>: Domain name not found"
+  ],
+
+  error_label_cleanup_recipient : [
+    /^\<.+?\> \(expanded from \<.+?\>\)\:/m, // "<john@acme.com> (expanded from <john@digiflex.com>):  Domain name not found"
+    /^\<.+?\>\:/m, // "<john@acme.com>: Domain name not found"
+  ],
+
+  error_label_cleanup_command : [
+    /\(in reply to (?:end of)?[A-Z\s]+ command\)$/m // "in reply to DATA command" or "in reply to end of DATA command"
   ],
 
   recipient : [
@@ -104,7 +113,7 @@ var REGEXES = {
     /the following message to \<(.+?)\> was undeliverable/i,
     /to the following addresses:\s*(.+)/i,
     /^\<(.+?)\>:/m,
-    /^(.+?)\s?\n?\s*[\[|<]mailto\:(.+?)[\]|>]/mi, // "john@acme.com<mailto:john@acme.com>"
+    /^(.+?)\s?(?:\s\(.*?\))?\n?\s*[\[|<]mailto\:(.+?)[\]|>]/mi, // "john@acme.com<mailto:john@acme.com>" or "john@acme.com[mailto:john@acme.com]" or "john@acme.com (john@acme.com)<mailto:john@acme.com>"
     /^your message wasn't delivered to (.+?)\s/mi, // "Your message wasn't delivered to john@acme.com"
     /^your message to (.+?) couldn\'t/mi, // "Your message to john@acme.com couldn't"
     /\<(.+?)\> \(expanded from \<.+?\>\)\:/, // "<john@acme.com> (expanded from <john@digiflex.com>): "
@@ -126,7 +135,8 @@ var REGEXES = {
 
   enhanced_types_server_unknown : [
     /(does not accept mail)/i,
-    /(domain name not found)/i
+    /(domain (?:name\s+)?(?:\S+\s)?(?:not found|does not exist))/i, // "domain does not exist" or "domain name does not exist" or "domain acme.com does not exist" or "domain name acme.com does not exist"
+    /(no route to host)/i
   ],
 
   enhanced_types_server_timeout : [
@@ -138,8 +148,8 @@ var REGEXES = {
   ],
 
   error_code : [
-    /(\d{3})[\s\-](\d\.\d\.\d\d?)/,  // "550 5.4.1" or "550-5.4.1" or "550-5.4.11"
-    /(\d{3})\-\'(\d\.\d\.\d\d?)/, // "550-'5.4.1" or "550-'5.4.11"
+    /(\d{3})[\s\-](\d\.\d\.\d{1,3})/,  // "550 5.4.1" or "550-5.4.1" or "550-5.4.11" or "550-5.4.110"
+    /(\d{3})\-\'(\d\.\d\.\d{1,3})/, // "550-'5.4.1" or "550-'5.4.11" or "550-'5.4.110"
     /(\d{3})/ // "550"
   ]
 };
@@ -567,6 +577,13 @@ class Parser {
 
     _label = trimString(_label);
 
+    // Strip recipient (at the beginning) and command (at the end), in case \
+    //   they are still present
+    _label = loopRegexes(this.__regexes.error_label_cleanup_recipient, _label, "replace");
+    _label = loopRegexes(this.__regexes.error_label_cleanup_command, _label, "replace");
+
+    _label = trimString(_label);
+
     return _label;
   }
 

package/lib/utils.js

@@ -23,6 +23,8 @@ var loopRegexes = function(
   regexes, str, mode = "match", highestPosition = true
 ) {
   var _match;
+  var _minLength = mode === "split" ? 1 : 0;
+  var _maxLength = str.length;
 
   for (var _i = 0; _i < regexes.length; _i++) {
     var _regex = regexes[_i];
@@ -40,15 +42,12 @@ var loopRegexes = function(
       _match = _currentMatch;
 
       // A successfull replace must return a smaller string than the input
-      var _maxLength = str.length;
-
       if (_match.length < _maxLength) {
         break;
       }
     } else if (mode === "split" || mode === "match") {
-      // A successfull split must return an array with at least two items
-      var _minLength = mode === "split" ? 1 : 0;
 
+      // A successfull split must return an array with at least two items
       if ((_currentMatch || []).length > _minLength) {
         if (highestPosition === true) {
           // No previous match?
@@ -80,7 +79,7 @@ var loopRegexes = function(
     }
   }
 
-  return (_match || []);
+  return (mode === "replace") ? (_match || "") : (_match || []);
 }
 
 
@@ -91,7 +90,7 @@ var loopRegexes = function(
  * @return {string} The trimed string
  */
 var trimString = function(str) {
-  return ((str || "").trim() || null)
+  return ((str || "").trim() || "");
 }
 
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "email-bounce-parser",
-  "version": "1.0.16",
+  "version": "1.0.18",
   "description": "Parses bounce emails and extract errors",
   "author": "Eliott Vincent <eliott@crisp.chat>",
   "main": "lib/index.js",