Simplification of the __init__() method

5 files changed, 33 insertions, 30 deletions

diff --git a/lib/archive.py b/lib/archive.py
index 1aaf74b..f9e4dba 100644
--- a/lib/archive.py
+++ b/lib/archive.py
@@ -14,10 +14,9 @@ class GenericArchiveStripper(parser.GenericParser):
     '''
         Represent a generic archive
     '''
-    def __init__(self, realname, filename, parser, editor, backup,
-        add2archive):
-        super(GenericArchiveStripper, self).__init__(realname,
-            filename, parser, editor, backup, add2archive)
+    def __init__(self, filename, parser, mime, backup, add2archive):
+        super(GenericArchiveStripper, self).__init__(filename, parser, mime,
+        backup, add2archive)
         self.compression = ''
         self.add2archive = add2archive
         self.tempdir = tempfile.mkdtemp()
@@ -254,10 +253,9 @@ class GzipStripper(TarStripper):
     '''
         Represent a tar.gz archive
     '''
-    def __init__(self, realname, filename, parser, editor, backup,
-        add2archive):
-        super(GzipStripper, self).__init__(realname,
-            filename, parser, editor, backup, add2archive)
+    def __init__(self, filename, parser, mime, backup, add2archive):
+        super(GzipStripper, self).__init__(filename, parser, mime, backup,
+            add2archive)
         self.compression = ':gz'
 
 
@@ -265,8 +263,7 @@ class Bzip2Stripper(TarStripper):
     '''
         Represents a tar.bz2 archive
     '''
-    def __init__(self, realname, filename, parser, editor, backup,
-        add2archive):
-        super(Bzip2Stripper, self).__init__(realname,
-            filename, parser, editor, backup, add2archive)
+    def __init__(self, filename, parser, mime, backup, add2archive):
+        super(Bzip2Stripper, self).__init__(filename, parser, mime, backup,
+            add2archive)
         self.compression = ':bz2'
diff --git a/lib/audio.py b/lib/audio.py
index d77efd9..d146fad 100644
--- a/lib/audio.py
+++ b/lib/audio.py
@@ -10,3 +10,6 @@ class MpegAudioStripper(parser.GenericParser):
             return True
         else:
             return False
+
+class FlacStripper(parser.GenericParser):
+    pass
diff --git a/lib/mat.py b/lib/mat.py
index ea4fefd..3d1687f 100644
--- a/lib/mat.py
+++ b/lib/mat.py
@@ -11,7 +11,6 @@ import mimetypes
 
 import hachoir_core.cmd_line
 import hachoir_parser
-import hachoir_editor
 
 import images
 import audio
@@ -39,7 +38,7 @@ STRIPPERS = {
 
 try:
     import mutagen
-    STRIPPERS[hachoir_parser.audio.FlacParser] = audio.FlacStripper
+    STRIPPERS['audio/x-flac'] = audio.FlacStripper
 except ImportError:
     print('unable to import python-mutagen : limited audio format support')
 
@@ -85,7 +84,6 @@ def create_class_file(name, backup, add2archive):
         logging.info('Unable to parse %s' % filename)
         return
 
-    editor = hachoir_editor.createEditor(parser)
     mime = parser.mime_type
 
     if mime.startswith('application/vnd.oasis.opendocument'):
@@ -94,8 +92,7 @@ def create_class_file(name, backup, add2archive):
     try:
         stripper_class = STRIPPERS[mime]
     except KeyError:
-        logging.info('Don\'t have stripper for format %s' % editor.description)
+        logging.info('Don\'t have stripper for %s\' format' % filename)
         return
 
-    return stripper_class(realname, filename, parser, editor, backup,
-        add2archive)
+    return stripper_class(filename, parser, mime, backup, add2archive)
diff --git a/lib/office.py b/lib/office.py
index 5fa475d..00fce3c 100644
--- a/lib/office.py
+++ b/lib/office.py
@@ -89,8 +89,8 @@ class OpenDocumentStripper(archive.GenericArchiveStripper):
             return False
         except KeyError:  # no meta.xml in the file
                 zipin.close()
-                czf = archive.ZipStripper(self.realname, self.filename,
-                    self.parser, self.editor, self.backup, self.add2archive)
+                czf = archive.ZipStripper(self.filename, self.parser,
+                    'application/zip', self.backup, self.add2archive)
                 if czf.is_clean():
                     return True
                 else:
@@ -102,14 +102,14 @@ class PdfStripper(parser.GenericParser):
     '''
         Represent a pdf file, with the help of pdfrw
     '''
-    def __init__(self, filename, realname, backup):
+    def __init__(self, filename, parser, mime, backup, add2archive):
         name, ext = os.path.splitext(filename)
         self.output = name + '.cleaned' + ext
         self.filename = filename
         self.backup = backup
         self.realname = realname
         self.shortname = os.path.basename(filename)
-        self.mime = mimetypes.guess_type(filename)[0]
+        self.mime = mime
         self.tempdir = tempfile.mkdtemp()
         self.trailer = pdfrw.PdfReader(self.filename)
         self.writer = pdfrw.PdfWriter()
diff --git a/lib/parser.py b/lib/parser.py
index ae647fe..385dd78 100644
--- a/lib/parser.py
+++ b/lib/parser.py
@@ -3,6 +3,7 @@
 '''
 
 import hachoir_core
+import hachoir_editor
 
 import os
 import mimetypes
@@ -13,17 +14,22 @@ NOMETA = ('.bmp', 'html', '.py', '.rdf', '.txt', '.xml')
 
 
 class GenericParser(object):
-    def __init__(self, realname, filename, parser, editor, backup,
-        add2archive):
+    def __init__(self, filename, parser, mime, backup, add2archive):
+        self.filename = ''
+        self.parser = parser
+        self.mime = mime
+        self.backup = backup
+        self.editor = hachoir_editor.createEditor(parser)
+        self.realname = filename
+        try:
+            self.filename = hachoir_core.cmd_line.unicodeFilename(filename)
+        except TypeError:  # get rid of "decoding Unicode is not supported"
+            self.filename = filename
         basename, ext = os.path.splitext(filename)
         self.output = basename + '.cleaned' + ext
-        self.filename = filename  # path + filename
-        self.realname = realname  # path + filename
         self.basename = os.path.basename(filename)  # only filename
-        self.mime = mimetypes.guess_type(filename)[0]  # mimetype
-        self.parser = parser
-        self.editor = editor
-        self.backup = backup
+
+
 
     def is_clean(self):
         '''