Check Book: Add checks for empty HTML/XML/CSS/image files in the book. Fixes #1329971 [Private bug](https://bugs.launchpad.net/calibre/+bug/1329971)

src/calibre/ebooks/oeb/polish/check/images.py

@@ -9,6 +9,7 @@ __copyright__ = '2013, Kovid Goyal <kovid at kovidgoyal.net>'
 from calibre import as_unicode
 from calibre.utils.magick import Image
 from calibre.ebooks.oeb.polish.check.base import BaseError, WARN
+from calibre.ebooks.oeb.polish.check.parsing import EmptyFile
 
 class InvalidImage(BaseError):
 
@@ -47,6 +48,8 @@ class CMYKImage(BaseError):
         return True
 
 def check_raster_images(name, mt, raw):
+    if not raw:
+        return [EmptyFile(name)]
     errors = []
     i = Image()
     try:

src/calibre/ebooks/oeb/polish/check/main.py

@@ -13,7 +13,8 @@ from calibre.ebooks.oeb.polish.utils import guess_type
 from calibre.ebooks.oeb.polish.cover import is_raster_image
 from calibre.ebooks.oeb.polish.check.base import run_checkers
 from calibre.ebooks.oeb.polish.check.parsing import (
-    check_filenames, check_xml_parsing, check_css_parsing, fix_style_tag, check_html_size, check_ids)
+    check_filenames, check_xml_parsing, check_css_parsing, fix_style_tag,
+    check_html_size, check_ids, EmptyFile)
 from calibre.ebooks.oeb.polish.check.images import check_raster_images
 from calibre.ebooks.oeb.polish.check.links import check_links, check_mimetypes, check_link_destinations
 from calibre.ebooks.oeb.polish.check.fonts import check_fonts
@@ -46,8 +47,14 @@ def run_checks(container):
 
     # cssutils is not thread safe
     for name, mt, raw in stylesheets:
+        if not raw:
+            errors.append(EmptyFile(name))
+            continue
         errors.extend(check_css_parsing(name, raw))
+
     for name, mt, raw in html_items:
+        if not raw:
+            continue
         root = container.parsed(name)
         for style in root.xpath('//*[local-name()="style"]'):
             if style.get('type', 'text/css') == 'text/css' and style.text:

src/calibre/ebooks/oeb/polish/check/parsing.py

@@ -25,6 +25,18 @@ ALL_ENTITIES = HTML_ENTITTIES | XML_ENTITIES
 replace_pat = re.compile('&(%s);' % '|'.join(re.escape(x) for x in sorted((HTML_ENTITTIES - XML_ENTITIES))))
 mismatch_pat = re.compile('tag mismatch:.+?line (\d+).+?line \d+')
 
+class EmptyFile(BaseError):
+
+    HELP = _('This file is empty, it contains nothing, you should probably remove it.')
+    INDIVIDUAL_FIX = _('Remove this file')
+
+    def __init__(self, name):
+        BaseError.__init__(self, _('The file %s is empty') % name, name)
+
+    def __call__(self, container):
+        container.remove_item(self.name)
+        return True
+
 class DecodeError(BaseError):
 
     is_parsing_error = True
@@ -197,6 +209,8 @@ def check_html_size(name, mt, raw):
 entity_pat = re.compile(br'&(#{0,1}[a-zA-Z0-9]{1,8});')
 
 def check_xml_parsing(name, mt, raw):
+    if not raw:
+        return [EmptyFile(name)]
     raw = raw.replace(b'\r\n', b'\n').replace(b'\r', b'\n')
     # Get rid of entities as named entities trip up the XML parser
     eproc = EntitityProcessor(mt)