Preliminary support of producted pdf quality choice

6 files changed, 32 insertions, 30 deletions

diff --git a/MAT/archive.py b/MAT/archive.py
index f78a2a7..69c8f1b 100644
--- a/MAT/archive.py
+++ b/MAT/archive.py
@@ -17,11 +17,10 @@ class GenericArchiveStripper(parser.GenericParser):
     '''
         Represent a generic archive
     '''
-    def __init__(self, filename, parser, mime, backup, add2archive):
-        super(GenericArchiveStripper, self).__init__(filename, parser, mime,
-        backup, add2archive)
+    def __init__(self, filename, parser, mime, backup, **kwargs):
+        super(GenericArchiveStripper, self).__init__(filename, parser, mime, backup, **kwargs)
         self.compression = ''
-        self.add2archive = add2archive
+        self.add2archive = kwargs['add2archive']
         self.tempdir = tempfile.mkdtemp()
 
     def __del__(self):
@@ -81,7 +80,7 @@ class ZipStripper(GenericArchiveStripper):
             if os.path.isfile(name):
                 try:
                     cfile = mat.create_class_file(name, False,
-                        self.add2archive)
+                        add2archive=self.add2archive)
                     if not cfile.is_clean():
                         return False
                 except:
@@ -129,7 +128,7 @@ harmless format' % item.filename)
             if os.path.isfile(name):
                 try:
                     cfile = mat.create_class_file(name, False,
-                        self.add2archive)
+                        add2archive=self.add2archive)
                     cfile.remove_all()
                     logging.debug('Processing %s from %s' % (item.filename,
                         self.filename))
@@ -173,7 +172,7 @@ class TarStripper(GenericArchiveStripper):
                 #no backup file
                 try:
                     cfile = mat.create_class_file(name, False,
-                    self.add2archive)
+                            add2archive=self.add2archive)
                     cfile.remove_all()
                     tarout.add(name, item.name, filter=self._remove)
                 except:
@@ -218,7 +217,7 @@ class TarStripper(GenericArchiveStripper):
             if item.type == '0':  # is item a regular file ?
                 try:
                     class_file = mat.create_class_file(name,
-                        False, self.add2archive)  # no backup file
+                        False, add2archive=self.add2archive)  # no backup file
                     if not class_file.is_clean():
                         tarin.close()
                         return False
@@ -256,9 +255,8 @@ class GzipStripper(TarStripper):
     '''
         Represent a tar.gz archive
     '''
-    def __init__(self, filename, parser, mime, backup, add2archive):
-        super(GzipStripper, self).__init__(filename, parser, mime, backup,
-            add2archive)
+    def __init__(self, filename, parser, mime, backup, **kwargs):
+        super(GzipStripper, self).__init__(filename, parser, mime, backup, **kwargs)
         self.compression = ':gz'
 
 
@@ -266,7 +264,6 @@ class Bzip2Stripper(TarStripper):
     '''
         Represents a tar.bz2 archive
     '''
-    def __init__(self, filename, parser, mime, backup, add2archive):
-        super(Bzip2Stripper, self).__init__(filename, parser, mime, backup,
-            add2archive)
+    def __init__(self, filename, parser, mime, backup, **kwargs):
+        super(Bzip2Stripper, self).__init__(filename, parser, mime, backup, **kwargs)
         self.compression = ':bz2'
diff --git a/MAT/exiftool.py b/MAT/exiftool.py
index 758a094..eeefcb8 100644
--- a/MAT/exiftool.py
+++ b/MAT/exiftool.py
@@ -11,9 +11,8 @@ class ExiftoolStripper(parser.GenericParser):
         A generic stripper class using exiftool as backend
     '''
 
-    def __init__(self, filename, parser, mime, backup, add2archive):
-        super(ExiftoolStripper, self).__init__(filename, parser, mime,
-        backup, add2archive)
+    def __init__(self, filename, parser, mime, backup, **kwargs):
+        super(ExiftoolStripper, self).__init__(filename, parser, mime, backup, **kwargs)
         self.allowed = ['ExifTool Version Number', 'File Name', 'Directory',
                 'File Size', 'File Modification Date/Time', 'File Permissions',
                 'File Type', 'MIME Type', 'Image Width', 'Image Height',
diff --git a/MAT/mat.py b/MAT/mat.py
index 4c12333..84f26f2 100644
--- a/MAT/mat.py
+++ b/MAT/mat.py
@@ -102,7 +102,7 @@ def secure_remove(filename):
             logging.error('Unable to remove %s' % filename)
 
 
-def create_class_file(name, backup, add2archive):
+def create_class_file(name, backup, **kwargs):
     '''
         return a $FILETYPEStripper() class,
         corresponding to the filetype of the given file
@@ -149,4 +149,7 @@ def create_class_file(name, backup, add2archive):
         logging.info('Don\'t have stripper for %s format' % mime)
         return None
 
-    return stripper_class(filename, parser, mime, backup, add2archive)
+    if mime.endswith('pdf') and mime.startswith('application/'):
+        return stripper_class(filename, parser, mime, backup, **kwargs)
+
+    return stripper_class(filename, parser, mime, backup, **kwargs)
diff --git a/MAT/misc.py b/MAT/misc.py
index d084861..1ffc327 100644
--- a/MAT/misc.py
+++ b/MAT/misc.py
@@ -12,9 +12,8 @@ class TorrentStripper(parser.GenericParser):
         Represent a torrent file with the help
         of the bencode lib from Petru Paler
     '''
-    def __init__(self, filename, parser, mime, backup, add2archive):
-        super(TorrentStripper, self).__init__(filename, parser, mime,
-            backup, add2archive)
+    def __init__(self, filename, parser, mime, backup, **kwargs):
+        super(TorrentStripper, self).__init__(filename, parser, mime, backup)
         self.fields = ['comment', 'creation date', 'created by']
 
     def is_clean(self):
diff --git a/MAT/office.py b/MAT/office.py
index d14125b..190a6d4 100644
--- a/MAT/office.py
+++ b/MAT/office.py
@@ -107,8 +107,9 @@ class OpenDocumentStripper(archive.GenericArchiveStripper):
         try:
             zipin.getinfo('meta.xml')
         except KeyError:  # no meta.xml in the file
+            kwargs =  {'backup':self.backup, 'add2archive':self.add2archive}
             czf = archive.ZipStripper(self.filename, self.parser,
-                'application/zip', self.backup, self.add2archive)
+                'application/zip', **kwargs)
             if czf.is_clean():
                 zipin.close()
                 return True
@@ -120,11 +121,11 @@ class PdfStripper(parser.GenericParser):
     '''
         Represent a PDF file
     '''
-    def __init__(self, filename, parser, mime, backup, add2archive):
-        super(PdfStripper, self).__init__(filename, parser, mime, backup,
-            add2archive)
+    def __init__(self, filename, parser, mime, backup, **kwargs):
+        super(PdfStripper, self).__init__(filename, parser, mime, backup, **kwargs)
         uri = 'file://' + os.path.abspath(self.filename)
         self.password = None
+        self.quality = kwargs['low_pdf_quality']
         self.document = poppler.document_new_from_file(uri, self.password)
         self.meta_list = frozenset(['title', 'author', 'subject', 'keywords', 'creator',
             'producer', 'metadata'])
@@ -161,7 +162,10 @@ class PdfStripper(parser.GenericParser):
         for pagenum in xrange(self.document.get_n_pages()):
             page = self.document.get_page(pagenum)
             context.translate(0, 0)
-            page.render_for_printing(context)  # render the page on context
+            if self.quality:
+                page.render(context)  # render the page on context
+            else:
+                page.render_for_printing(context)  # render the page on context
             context.show_page()  # draw context on surface
         surface.finish()
 
@@ -175,7 +179,6 @@ class PdfStripper(parser.GenericParser):
             writer.trailer = trailer
             writer.write(self.output)
             self.do_backup()
-            return True
         except:
             print('Unable to remove all metadata from %s, please install\
 pdfrw' % self.output)
@@ -248,8 +251,9 @@ class OpenXmlStripper(archive.GenericArchiveStripper):
             if item.startswith('docProps/'):
                 return False
         zipin.close()
+        kwargs =  {'backup':self.backup, 'add2archive':self.add2archive}
         czf = archive.ZipStripper(self.filename, self.parser,
-                'application/zip', self.backup, self.add2archive)
+                'application/zip', **kwargs)
         return czf.is_clean()
 
     def get_meta(self):
diff --git a/MAT/parser.py b/MAT/parser.py
index 4427b01..6be2b03 100644
--- a/MAT/parser.py
+++ b/MAT/parser.py
@@ -23,7 +23,7 @@ class GenericParser(object):
     '''
         Parent class of all parsers
     '''
-    def __init__(self, filename, parser, mime, backup, add2archive):
+    def __init__(self, filename, parser, mime, backup, **kwargs):
         self.filename = ''
         self.parser = parser
         self.mime = mime