Parse email utf8 8bit

parse_emails/handle_eml.py

@@ -358,6 +358,8 @@ def decode_content(mime):
       Decode content
     """
     charset = mime.get_content_charset()
+    if (charset == 'utf-8' and mime.get('content-transfer-encoding', '') == '8bit'):
+        return mime.get_payload()
     payload = mime.get_payload(decode=True)
     try:
         if payload:

parse_emails/tests/parse_emails_test.py

@@ -887,3 +887,20 @@ def test_multipart_defective():
     results = email_parser.parse()
     assert results.get('Text')
     assert results.get('HTML')
+
+
+def test_handle_eml_utf8_8bit():
+    """
+    Given:
+     - chinese eml file encoded in utf-8, 8bit
+
+    When:
+     - parsing the file.
+
+    Then:
+     - make sure the chinese characters were decoded successfully.
+    """
+    email_parser = EmailParser(file_path='parse_emails/tests/test_data/chinese_email_test.eml')
+    results = email_parser.parse()
+    expected_response = '这是一个示例邮件，用于演示指定的条件。\r\n它使用了 UTF-8 编码，可以支持多种语言的字符，包括中文。\r\n祝好，\r\n发件人'
+    assert results['Text'] == expected_response

parse_emails/tests/test_data/chinese_email_test.eml

@@ -0,0 +1,16 @@
+To: [email protected]
+From: "[email protected]" <[email protected]>
+Subject: 示例邮件
+Message-ID: <[email protected]>
+Date: Wed, 23 Jan 2019 18:55:56 +0100
+User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:60.0) Gecko/20100101
+ Thunderbird/60.4.0
+MIME-Version: 1.0
+Content-Type: text/plain; charset=utf-8; format=flowed
+Content-Transfer-Encoding: 8bit
+Content-Language: en-US
+
+这是一个示例邮件，用于演示指定的条件。
+它使用了 UTF-8 编码，可以支持多种语言的字符，包括中文。
+祝好，
+发件人

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "parse-emails"
-version = "0.1.26"
+version = "0.1.27"
 description = "Parses an email message file and extracts the data from it."
 authors = ["Demisto"]
 license = "MIT"