Improve the code's documentation

libmat2/abstract.py

@@ -6,10 +6,16 @@ assert Set  # make pyflakes happy
 
 
 class AbstractParser(abc.ABC):
+    """ This is the base classe of every parser.
+    It might yeild `ValueError` on instanciation on invalid files.
+    """
     meta_list = set()  # type: Set[str]
     mimetypes = set()  # type: Set[str]
 
     def __init__(self, filename: str) -> None:
+        """
+        :raises ValueError: Raised upon an invalid file
+        """
         self.filename = filename
         fname, extension = os.path.splitext(filename)
         self.output_filename = fname + '.cleaned' + extension
@@ -23,5 +29,8 @@ class AbstractParser(abc.ABC):
         pass  # pragma: no cover
 
     def remove_all_lightweight(self) -> bool:
-        """ Remove _SOME_ metadata. """
+        """ This method removes _SOME_ metadata.
+        I might be useful to implement it for fileformats that do
+        not support non-destructive cleaning.
+        """
         return self.remove_all()

libmat2/harmless.py

@@ -4,7 +4,7 @@ from . import abstract
 
 
 class HarmlessParser(abstract.AbstractParser):
-    """ This is the parser for filetypes that do not contain metadata. """
+    """ This is the parser for filetypes that can not contain metadata. """
     mimetypes = {'text/plain', 'image/x-ms-bmp'}
 
     def get_meta(self) -> Dict[str, str]:

libmat2/images.py

@@ -19,6 +19,9 @@ from . import abstract
 assert Set
 
 class _ImageParser(abstract.AbstractParser):
+    """ Since we use `exiftool` to get metadata from
+    all images fileformat, `get_meta` is implemented in this class,
+    and all the image-handling ones are inheriting from it."""
     meta_whitelist = set()  # type: Set[str]
 
     @staticmethod
@@ -72,7 +75,7 @@ class PNGParser(_ImageParser):
 
 class GdkPixbufAbstractParser(_ImageParser):
     """ GdkPixbuf can handle a lot of surfaces, so we're rending images on it,
-        this has the side-effect of removing metadata completely.
+        this has the side-effect of completely removing metadata.
     """
     _type = ''
 

libmat2/office.py

@@ -33,6 +33,7 @@ def _parse_xml(full_path: str):
 
 
 class ArchiveBasedAbstractParser(abstract.AbstractParser):
+    """ Office files (.docx, .odt, …) are zipped files. """
     # Those are the files that have a format that _isn't_
     # supported by MAT2, but that we want to keep anyway.
     files_to_keep = set()  # type: Set[str]
@@ -58,14 +59,13 @@ class ArchiveBasedAbstractParser(abstract.AbstractParser):
     def _clean_zipinfo(zipinfo: zipfile.ZipInfo) -> zipfile.ZipInfo:
         zipinfo.create_system = 3  # Linux
         zipinfo.comment = b''
-        zipinfo.date_time = (1980, 1, 1, 0, 0, 0)
+        zipinfo.date_time = (1980, 1, 1, 0, 0, 0)  # this is as early as a zipfile can be
         return zipinfo
 
     @staticmethod
     def _get_zipinfo_meta(zipinfo: zipfile.ZipInfo) -> Dict[str, str]:
         metadata = {}
-        if zipinfo.create_system == 3:
+        if zipinfo.create_system == 3:  # this is Linux
-            #metadata['create_system'] = 'Linux'
             pass
         elif zipinfo.create_system == 2:
             metadata['create_system'] = 'Windows'
@@ -145,23 +145,27 @@ class MSOfficeParser(ArchiveBasedAbstractParser):
 
     @staticmethod
     def __remove_revisions(full_path: str) -> bool:
-        """ In this function, we're changing the XML
+        """ In this function, we're changing the XML document in several
-        document in two times, since we don't want
+        different times, since we don't want to change the tree we're currently
-        to change the tree we're iterating on."""
+        iterating on.
+        """
         try:
             tree, namespace = _parse_xml(full_path)
         except ET.ParseError:
             return False
 
-        # No revisions are present
+        # Revisions are either deletions (`w:del`) or
+        # insertions (`w:ins`)
         del_presence = tree.find('.//w:del', namespace)
         ins_presence = tree.find('.//w:ins', namespace)
         if del_presence is None and ins_presence is None:
-            return True
+            return True  # No revisions are present
 
         parent_map = {c:p for p in tree.iter() for c in p}
 
-        elements = list([element for element in tree.iterfind('.//w:del', namespace)])
+        elements = list()
+        for element in tree.iterfind('.//w:del', namespace):
+            elements.append(element)
         for element in elements:
             parent_map[element].remove(element)
 
@@ -172,7 +176,6 @@ class MSOfficeParser(ArchiveBasedAbstractParser):
                     for children in element.iterfind('./*'):
                         elements.append((element, position, children))
                     break
-
         for (element, position, children) in elements:
             parent_map[element].insert(position, children)
             parent_map[element].remove(element)
@@ -183,6 +186,7 @@ class MSOfficeParser(ArchiveBasedAbstractParser):
 
     def _specific_cleanup(self, full_path: str) -> bool:
         if full_path.endswith('/word/document.xml'):
+            # this file contains the revisions
             return self.__remove_revisions(full_path)
         return True
 

libmat2/parser_factory.py

@@ -13,10 +13,12 @@ T = TypeVar('T', bound='abstract.AbstractParser')
 def __load_all_parsers():
     """ Loads every parser in a dynamic way """
     current_dir = os.path.dirname(__file__)
-    for name in glob.glob(os.path.join(current_dir, '*.py')):
+    for fname in glob.glob(os.path.join(current_dir, '*.py')):
-        if name.endswith('abstract.py') or name.endswith('__init__.py'):
+        if fname.endswith('abstract.py'):
             continue
-        basename = os.path.basename(name)
+        elif fname.endswith('__init__.py'):
+            continue
+        basename = os.path.basename(fname)
         name, _ = os.path.splitext(basename)
         importlib.import_module('.' + name, package='libmat2')
 

libmat2/pdf.py

@@ -47,7 +47,7 @@ class PDFParser(abstract.AbstractParser):
         pages_count = document.get_n_pages()
 
         tmp_path = tempfile.mkstemp()[1]
-        pdf_surface = cairo.PDFSurface(tmp_path, 10, 10)
+        pdf_surface = cairo.PDFSurface(tmp_path, 10, 10)  # resized later anyway
         pdf_context = cairo.Context(pdf_surface)  # context draws on the surface
 
         for pagenum in range(pages_count):
@@ -101,7 +101,7 @@ class PDFParser(abstract.AbstractParser):
             pdf_surface.set_size(page_width*self.__scale, page_height*self.__scale)
             pdf_context.set_source_surface(img, 0, 0)
             pdf_context.paint()
-            pdf_context.show_page()
+            pdf_context.show_page()  # draw pdf_context on pdf_surface
 
         pdf_surface.finish()