Getting only mains parts of mail + headers

SpamScope · Feb 3, 2019 · fdb0f86 · fdb0f86
1 parent f7a41cc
commit fdb0f86
Show file tree

Hide file tree

Showing 3 changed files with 7 additions and 3 deletions.
diff --git a/requirements-dev.txt b/requirements-dev.txt
@@ -4,7 +4,7 @@ astropy==1.3.3
 backports.functools-lru-cache>=1.3
 chainmap
 lxml
-mail-parser>=3.4.1
+mail-parser>=3.9.0
 patool
 pyparsing
 python-magic

diff --git a/requirements.txt b/requirements.txt
@@ -3,7 +3,7 @@ astropy==1.3.3
 backports.functools-lru-cache>=1.3
 chainmap
 lxml
-mail-parser>=3.4.1
+mail-parser>=3.9.0
 patool
 pyparsing
 python-magic

diff --git a/src/bolts/tokenizer.py b/src/bolts/tokenizer.py
@@ -101,7 +101,11 @@ def _make_mail(self, tup):
         mail_type = tup.values[5]
         rand = '_' + ''.join(random.choice('0123456789') for i in range(10))
         self.parser = self.mailparser[mail_type](raw_mail)
-        mail = self.parser.mail
+
+        # get only the mains headers because this number can explode
+        # Elastic can't manage all possible headers
+        mail = self.parser.mail_partial
+        mail["headers"] = self.parser.headers_json
 
         # Data mail sources
         mail["mail_server"] = tup.values[1]