pep8

src/documents/admin.py

@@ -56,25 +56,34 @@ class DocumentAdmin(admin.ModelAdmin):
     def tags_(self, obj):
         r = ""
         for tag in obj.tags.all():
-            r += '<a class="tag" style="background-color: {};" href="{}">{}</a>'.format(
-                tag.get_colour_display(),
-                "{}?tags__id__exact={}".format(
+            colour = tag.get_colour_display()
+            r += html_tag(
+                "a",
+                tag.slug,
+                **{
+                    "class": "tag",
+                    "style": "background-color: {};".format(colour),
+                    "href": "{}?tags__id__exact={}".format(
                         reverse("admin:documents_document_changelist"),
                         tag.pk
-                ),
-                tag.slug
+                    )
+                }
             )
         return r
     tags_.allow_tags = True
 
     def document(self, obj):
-        return '<a href="{}">' \
-                 '<img src="{}" width="22" height="22" alt="{} icon" title="{}">' \
-               '</a>'.format(
-                    obj.download_url,
-                    static("documents/img/{}.png".format(obj.file_type)),
-                    obj.file_type,
-                    obj.file_name
+        return html_tag(
+            "a",
+            html_tag(
+                "img",
+                src=static("documents/img/{}.png".format(obj.file_type)),
+                width=22,
+                height=22,
+                alt=obj.file_type,
+                title=obj.file_name
+            ),
+            href=obj.download_url
         )
     document.allow_tags = True
 
@@ -85,3 +94,16 @@ admin.site.register(Document, DocumentAdmin)
 # Unless we implement multi-user, these default registrations don't make sense.
 admin.site.unregister(Group)
 admin.site.unregister(User)
+
+
+def html_tag(kind, inside=None, **kwargs):
+
+    attributes = []
+    for lft, rgt in kwargs.items():
+        attributes.append('{}="{}"'.format(lft, rgt))
+
+    if inside is not None:
+        return "<{kind} {attributes}>{inside}</{kind}>".format(
+            kind=kind, attributes=" ".join(attributes), inside=inside)
+
+    return "<{} {}/>".format(kind, " ".join(attributes))

src/documents/consumer.py

@@ -127,7 +127,8 @@ class Consumer(object):
                 self._store(text, doc)
             except OCRError:
                 self._ignore.append(doc)
-                Log.error("OCR FAILURE: {}".format(doc), Log.COMPONENT_CONSUMER)
+                Log.error(
+                    "OCR FAILURE: {}".format(doc), Log.COMPONENT_CONSUMER)
                 self._cleanup_tempdir(tempdir)
                 continue
             else:
@@ -190,8 +191,8 @@ class Consumer(object):
             Log.warning("Language detection failed!", Log.COMPONENT_CONSUMER)
             if settings.FORGIVING_OCR:
                 Log.warning(
-                    "As FORGIVING_OCR is enabled, we're going to make the best "
-                    "with what we have.",
+                    "As FORGIVING_OCR is enabled, we're going to make the "
+                    "best with what we have.",
                     Log.COMPONENT_CONSUMER
                 )
                 raw_text = self._assemble_ocr_sections(pngs, middle, raw_text)
@@ -246,8 +247,8 @@ class Consumer(object):
 
     def _guess_attributes_from_name(self, parseable):
         """
-        We use a crude naming convention to make handling the sender, title, and
-        tags easier:
+        We use a crude naming convention to make handling the sender, title,
+        and tags easier:
           "<sender> - <title> - <tags>.<suffix>"
           "<sender> - <title>.<suffix>"
           "<title>.<suffix>"

src/documents/forms.py

@@ -26,15 +26,17 @@ class UploadForm(forms.Form):
     sender = forms.CharField(
         max_length=Sender._meta.get_field("name").max_length, required=False)
     title = forms.CharField(
-        max_length=Document._meta.get_field("title").max_length, required=False)
+        max_length=Document._meta.get_field("title").max_length,
+        required=False
+    )
     document = forms.FileField()
     signature = forms.CharField(max_length=256)
 
     def clean_sender(self):
         """
         I suppose it might look cleaner to use .get_or_create() here, but that
-        would also allow someone to fill up the db with bogus senders before all
-        validation was met.
+        would also allow someone to fill up the db with bogus senders before
+        all validation was met.
         """
         sender = self.cleaned_data.get("sender")
         if not sender:

src/documents/languages.py

@@ -185,8 +185,8 @@ ISO639 = {
     "yo": "yor",
     "za": "zha",
 
-    # Tessdata contains two values for Chinese, "chi_sim" and "chi_tra".  I have
-    # no idea which one is better, so I just picked the bigger file.
+    # Tessdata contains two values for Chinese, "chi_sim" and "chi_tra".  I
+    # have no idea which one is better, so I just picked the bigger file.
     "zh": "chi_tra",
 
     "zu": "zul"

src/documents/management/commands/document_retagger.py

@@ -10,8 +10,8 @@ class Command(Renderable, BaseCommand):
     help = """
         Using the current set of tagging rules, apply said rules to all
         documents in the database, effectively allowing you to back-tag all
-        previously indexed documents with tags created (or modified) after their
-        initial import.
+        previously indexed documents with tags created (or modified) after
+        their initial import.
     """.replace("    ", "")
 
     def __init__(self, *args, **kwargs):

src/documents/mixins.py

@@ -1,7 +1,7 @@
 class Renderable(object):
     """
-    A handy mixin to make it easier/cleaner to print output based on a verbosity
-    value.
+    A handy mixin to make it easier/cleaner to print output based on a
+    verbosity value.
     """
 
     def _render(self, text, verbosity):

src/documents/models.py

@@ -71,9 +71,9 @@ class Tag(SluggedModel):
         default=MATCH_ANY,
         help_text=(
             "Which algorithm you want to use when matching text to the OCR'd "
-            "PDF.  Here, \"any\" looks for any occurrence of any word provided "
-            "in the PDF, while \"all\" requires that every word provided "
-            "appear in the PDF, albeit not in the order provided.  A "
+            "PDF.  Here, \"any\" looks for any occurrence of any word "
+            "provided in the PDF, while \"all\" requires that every word "
+            "provided appear in the PDF, albeit not in the order provided.  A "
             "\"literal\" match means that the text you enter must appear in "
             "the PDF exactly as you've entered it, and \"regular expression\" "
             "uses a regex to match the PDF.  If you don't know what a regex "

src/documents/serialisers.py

@@ -14,7 +14,8 @@ class TagSerializer(serializers.ModelSerializer):
 
     class Meta(object):
         model = Tag
-        fields = ("id", "slug", "name", "colour", "match", "matching_algorithm")
+        fields = (
+            "id", "slug", "name", "colour", "match", "matching_algorithm")
 
 
 class DocumentSerializer(serializers.ModelSerializer):

src/documents/tests/test_tags.py

@@ -117,4 +117,3 @@ class TestTagMatching(TestCase):
         self.assertFalse(t.matches("I have alpha, charlie, and gamma in me"))
         self.assertFalse(t.matches("I have alphas, charlie, and gamma in me"))
         self.assertFalse(t.matches("I have alphas in me"))
-

src/paperless/urls.py

@@ -29,10 +29,20 @@ router.register(r'tags', TagViewSet)
 router.register(r'documents', DocumentViewSet)
 
 urlpatterns = [
-    url(r"^api/auth/", include('rest_framework.urls', namespace='rest_framework')),
+
+    # API
+    url(
+        r"^api/auth/",
+        include('rest_framework.urls', namespace='rest_framework')
+    ),
     url(r"^api/", include(router.urls)),
+
+    # File downloads
     url(r"^fetch/(?P<pk>\d+)$", PdfView.as_view(), name="fetch"),
+
+    # The Django admin
     url(r"", admin.site.urls),
+
 ] + static.static(settings.MEDIA_URL, document_root=settings.MEDIA_ROOT)
 
 if settings.UPLOAD_SHARED_SECRET:

tox.ini

@@ -0,0 +1,14 @@
+# Tox (http://tox.testrun.org/) is a tool for running tests
+# in multiple virtualenvs. This configuration file will run the
+# test suite on all supported python versions. To use it, "pip install tox"
+# and then run "tox" from this directory.
+
+#[tox]
+#envlist = py34, py35
+
+#[testenv]
+#commands = {envpython} src/manage.py test
+#deps =
+
+[pep8]
+exclude=migrations,src/paperless/settings.py