From 64b667be5d6b36d17839482593ccf2207af14ac9 Mon Sep 17 00:00:00 2001
From: jvoisin
Date: Mon, 29 Aug 2016 22:12:40 +0200
Subject: Python3, now with less features

I want to release a new version ASAP, so lets ditch some features for
now.
---
 libmat/office.py | 89 +-------------------------------------------------------
 1 file changed, 1 insertion(+), 88 deletions(-)

(limited to 'libmat/office.py')

diff --git a/libmat/office.py b/libmat/office.py
index b23ec84..b4a05a7 100644
--- a/libmat/office.py
+++ b/libmat/office.py
@@ -18,94 +18,7 @@ except ImportError:
     logging.info('office.py loaded without PDF support')
 
 from libmat import parser
-from libmat import archive
-
-
-class OpenDocumentStripper(archive.TerminalZipStripper):
-    """ An open document file is a zip, with xml file into.
-        The one that interest us is meta.xml
-    """
-
-    def get_meta(self):
-        """ Return a dict with all the meta of the file by
-            trying to read the meta.xml file.
-        """
-        metadata = super(OpenDocumentStripper, self).get_meta()
-        zipin = zipfile.ZipFile(self.filename, 'r')
-        try:
-            content = zipin.read('meta.xml')
-            dom1 = minidom.parseString(content)
-            elements = dom1.getElementsByTagName('office:meta')
-            for i in elements[0].childNodes:
-                if i.tagName != 'meta:document-statistic':
-                    nodename = ''.join(i.nodeName.split(':')[1:])
-                    metadata[nodename] = ''.join([j.data for j in i.childNodes])
-        except KeyError:  # no meta.xml file found
-            logging.debug('%s has no opendocument metadata', self.filename)
-        zipin.close()
-        return metadata
-
-    def remove_all(self):
-        """ Removes metadata
-        """
-        return super(OpenDocumentStripper, self).remove_all(ending_blacklist=['meta.xml'])
-
-    def is_clean(self):
-        """ Check if the file is clean from harmful metadatas
-        """
-        clean_super = super(OpenDocumentStripper, self).is_clean()
-        if clean_super is False:
-            return False
-
-        zipin = zipfile.ZipFile(self.filename, 'r')
-        try:
-            zipin.getinfo('meta.xml')
-        except KeyError:  # no meta.xml in the file
-            return True
-        zipin.close()
-        return False
-
-
-class OpenXmlStripper(archive.TerminalZipStripper):
-    """ Represent an office openxml document, which is like
-        an opendocument format, with some tricky stuff added.
-        It contains mostly xml, but can have media blobs, crap, ...
-        (I don't like this format.)
-    """
-
-    def remove_all(self):
-        """ Remove harmful metadata, by deleting everything that doesn't end with '.rels' in the
-        'docProps' folder. """
-        return super(OpenXmlStripper, self).remove_all(
-            beginning_blacklist=['docProps/'], whitelist=['.rels'])
-
-    def is_clean(self):
-        """ Check if the file is clean from harmful metadatas.
-            This implementation is faster than something like
-            "return this.get_meta() == {}".
-        """
-        clean_super = super(OpenXmlStripper, self).is_clean()
-        if clean_super is False:
-            return False
-
-        zipin = zipfile.ZipFile(self.filename)
-        for item in zipin.namelist():
-            if item.startswith('docProps/'):
-                return False
-        zipin.close()
-        return True
-
-    def get_meta(self):
-        """ Return a dict with all the meta of the file
-        """
-        metadata = super(OpenXmlStripper, self).get_meta()
-
-        zipin = zipfile.ZipFile(self.filename)
-        for item in zipin.namelist():
-            if item.startswith('docProps/'):
-                metadata[item] = 'harmful content'
-        zipin.close()
-        return metadata
+#from libmat import archive
 
 
 class PdfStripper(parser.GenericParser):
-- 
cgit v1.3