Merge pull request #521 from inkhey/feature/somes_fixes

tracim/tracim/lib/email_fetcher.py

         #  if no from address for example) and catch it here
         while mails:
             mail = mails.pop()
+            body =  mail.get_body(
+                use_html_parsing=self.use_html_parsing,
+                use_txt_parsing=self.use_txt_parsing,
+            )
+            from_address = mail.get_from_address()
+
+            # don't create element for 'empty' mail
+            if not body:
+                logger.warning(
+                    self,
+                    'Mail from {} has not valable content'.format(
+                        from_address
+                    ),
+                )
+                continue
+
             msg = {'token': self.token,
-                   'user_mail': mail.get_from_address(),
+                   'user_mail': from_address,
                    'content_id': mail.get_key(),
                    'payload': {
-                       'content': mail.get_body(
-                           use_html_parsing=self.use_html_parsing,
-                           use_txt_parsing=self.use_txt_parsing),
+                       'content': body,
                    }}
             try:
                 logger.debug(

tracim/tracim/lib/email_processing/models.py

         if len(self._list) > 0:
             txt = BeautifulSoup(value.text, 'html.parser').get_text()
             txt = txt.replace('\n', '').strip()
-            if not txt:
+            img = BeautifulSoup(value.text, 'html.parser').find('img')
+            if not txt and not img:
                 value.part_type = self._list[-1].part_type
         BodyMailParts._check_value(value)
         BodyMailParts._append(self, value)

tracim/tracim/lib/email_processing/sanitizer.py

+import typing
 from bs4 import BeautifulSoup, Tag
-
+from tracim.lib.email_processing.sanitizer_config.attrs_whitelist import ATTRS_WHITELIST  # nopep8
+from tracim.lib.email_processing.sanitizer_config.class_blacklist import CLASS_BLACKLIST  # nopep8
+from tracim.lib.email_processing.sanitizer_config.id_blacklist import ID_BLACKLIST  # nopep8
+from tracim.lib.email_processing.sanitizer_config.tag_blacklist import TAG_BLACKLIST  # nopep8
+from tracim.lib.email_processing.sanitizer_config.tag_whitelist import TAG_WHITELIST  # nopep8
 
 class HtmlSanitizerConfig(object):
-    # some Default_html_tags type
-    HTML_Heading_tag = ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']
-    HTML_Text_parts_tag = ['p',
-                           'br', 'hr',
-                           'pre', 'code', 'samp',  # preformatted content
-                           'q', 'blockquote',  # quotes
-                           ]
-    HTML_Text_format_tag = ['b', 'i', 'u', 'small', 'sub', 'sup', ]
-    HTML_Text_semantic_tag = ['strong', 'em',
-                              'mark', 'cite', 'dfn',
-                              'del', 'ins', ]
-    HTML_Table_tag = ['table',
-                      'thead', 'tfoot', 'tbody',
-                      'tr', 'td', 'caption', ]
-
-    HTML_List_tag = ['ul', 'li', 'ol',  # simple list
-                     'dl', 'dt', 'dd', ]  # definition list
-
-    # Rules
-    Tag_whitelist = HTML_Heading_tag \
-                    + HTML_Text_parts_tag \
-                    + HTML_Text_format_tag \
-                    + HTML_Text_semantic_tag \
-                    + HTML_Table_tag \
-                    + HTML_List_tag
-
-    Tag_blacklist = ['script', 'style']
-
-    # TODO - G.M - 2017-12-01 - Think about removing class/id Blacklist
-    # These elements are no longer required.
-    Class_blacklist = []
-    Id_blacklist = []
-
-    Attrs_whitelist = ['href']
-
+    # whitelist : keep tag and content
+    Tag_whitelist = TAG_WHITELIST
+    Attrs_whitelist = ATTRS_WHITELIST
+    # blacklist : remove content
+    Tag_blacklist = TAG_BLACKLIST
+    Class_blacklist = CLASS_BLACKLIST
+    Id_blacklist = ID_BLACKLIST
 
 class HtmlSanitizer(object):
     """
     """
 
     @classmethod
-    def sanitize(cls, html_body: str) -> str:
+    def sanitize(cls, html_body: str) -> typing.Optional[str]:
         soup = BeautifulSoup(html_body, 'html.parser')
         for tag in soup.findAll():
             if cls._tag_to_extract(tag):
                         del tag.attrs[attr]
             else:
                 tag.unwrap()
-        return str(soup)
+
+        if cls._is_content_empty(soup):
+            return None
+        else:
+            return str(soup)
+
+    @classmethod
+    def _is_content_empty(cls, soup):
+        img = soup.find('img')
+        txt = soup.get_text().replace('\n', '').strip()
+        return (not img and not txt)
 
     @classmethod
     def _tag_to_extract(cls, tag: Tag) -> bool:

tracim/tracim/lib/email_processing/sanitizer_config/attrs_whitelist.py

+ATTRS_WHITELIST = ['href']

tracim/tracim/lib/email_processing/sanitizer_config/class_blacklist.py

+CLASS_BLACKLIST =  []

tracim/tracim/lib/email_processing/sanitizer_config/id_blacklist.py

+ID_BLACKLIST = []

tracim/tracim/lib/email_processing/sanitizer_config/tag_blacklist.py

+TAG_BLACKLIST = ['script', 'style']

tracim/tracim/lib/email_processing/sanitizer_config/tag_whitelist.py

+TAG_WHITELIST = [
+    'b', 'blockquote', 'br',
+    'caption', 'cite', 'code',
+    'dd', 'del', 'dfn', 'dl', 'dt',
+    'em',
+    'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr',
+    'i', 'img', 'ins',
+    'li',
+    'mark',
+    'ol',
+    'p', 'pre',
+    'q',
+    'samp', 'small', 'strong', 'sub', 'sup',
+    'table', 'tbody', 'td', 'tfoot', 'thead', 'tr',
+    'u', 'ul'
+]