Tests are green for opendocument format

4 files changed, 16 insertions, 15 deletions

diff --git a/lib/archive.py b/lib/archive.py
index 8a8f7f4..f22af39 100644
--- a/lib/archive.py
+++ b/lib/archive.py
@@ -69,10 +69,13 @@ class ZipStripper(GenericArchiveStripper):
                         return False
                 except:
                     #best solution I have found
-                    logging.error('%s is not supported' % item.filename)
-                    _, ext = os.path.splitext(name)
+                    logging.info('%s\'s fileformat is not supported, or is a \
+harmless format' % item.filename)
+                    base, ext = os.path.splitext(name)
+                    bname = os.path.basename(item.filename)
                     if ext not in parser.NOMETA:
-                        return False
+                        if bname != 'mimetype':
+                            return False
                 mat.secure_remove(name)
         zipin.close()
         return True
diff --git a/lib/mat.py b/lib/mat.py
index 5dcdbc2..ccf653f 100644
--- a/lib/mat.py
+++ b/lib/mat.py
@@ -18,8 +18,8 @@ import audio
 import office
 import archive
 
-__version__ = "0.1"
-__author__ = "jvoisin"
+__version__ = '0.1'
+__author__ = 'jvoisin'
 
 LOGGING_LEVEL = logging.DEBUG
 
@@ -53,7 +53,7 @@ def is_secure(filename):
     '''
 
     if not(os.path.isfile(filename)): #check if the file exist
-        logging.error("Error: %s is not a valid file" % filename)
+        logging.error('Error: %s is not a valid file' % filename)
         return False
 
 def create_class_file(name, backup, add2archive):
@@ -64,7 +64,7 @@ def create_class_file(name, backup, add2archive):
     if is_secure(name):
         return
 
-    filename = ""
+    filename = ''
     realname = name
     try:
         filename = hachoir_core.cmd_line.unicodeFilename(name)
@@ -72,7 +72,7 @@ def create_class_file(name, backup, add2archive):
         filename = name
     parser = hachoir_parser.createParser(filename)
     if not parser:
-        logging.error("Unable to parse %s" % filename)
+        logging.info('Unable to parse %s' % filename)
         return
 
     editor = hachoir_editor.createEditor(parser)
@@ -85,7 +85,7 @@ def create_class_file(name, backup, add2archive):
         stripper_class = strippers[editor.input.__class__]
     except KeyError:
         #Place for another lib than hachoir
-        logging.error("Don't have stripper for format %s" % editor.description)
+        logging.info('Don\'t have stripper for format %s' % editor.description)
         return
 
     if editor.input.__class__ == hachoir_parser.misc.PDFDocument:#pdf
@@ -95,8 +95,7 @@ def create_class_file(name, backup, add2archive):
         #zip based format
         mime = mimetypes.guess_type(filename)[0]
         try:#Ugly workaround, cleaning open document delete mime (wtf?)
-            if mime.startswith(#Open document format
-            'application/vnd.oasis.opendocument'):
+            if mime.startswith('application/vnd.oasis.opendocument'):
                 return office.OpenDocumentStripper(realname, filename, parser,
                     editor, backup, add2archive)
             else:#normal zip
diff --git a/lib/office.py b/lib/office.py
index b7fa555..27677d2 100644
--- a/lib/office.py
+++ b/lib/office.py
@@ -34,7 +34,6 @@ class OpenDocumentStripper(archive.GenericArchiveStripper):
                 metadata[key] = node.text
         except KeyError:#no meta.xml file found
             logging.debug('%s has no opendocument metadata' % self.filename)
-            metadata[self.filename] = ''
         return metadata
 
 
@@ -76,7 +75,7 @@ class OpenDocumentStripper(archive.GenericArchiveStripper):
                     except:
                         logging.info('%s\' fileformat is not supported' %  item)
                         if self.add2archive:
-                            zipout.write(item, name)
+                            zipout.write(name, item)
                     mat.secure_remove(name)
         zipout.comment = ''
         logging.info('%s treated' % self.filename)
diff --git a/lib/parser.py b/lib/parser.py
index 04d7625..aa7e7f1 100644
--- a/lib/parser.py
+++ b/lib/parser.py
@@ -13,7 +13,7 @@ import mimetypes
 
 import mat
 
-NOMETA = ('.txt', '.bmp', '.py', '.xml')
+NOMETA = ('.txt', '.bmp', '.py', '.xml', '.rdf')
 
 class Generic_parser(object):
     def __init__(self, realname, filename, parser, editor, backup, add2archive):
@@ -21,7 +21,7 @@ class Generic_parser(object):
         self.output = basename + '.cleaned' + ext
         self.filename = filename #path + filename
         self.realname = realname #path + filename
-        self.shortname = os.path.basename(filename) #only filename
+        self.basename = os.path.basename(filename) #only filename
         self.mime = mimetypes.guess_type(filename)[0] #mimetype
         self.parser = parser
         self.editor = editor