diff --git a/src/documents/admin.py b/src/documents/admin.py index d3bdd3ba4..42c3fc968 100644 --- a/src/documents/admin.py +++ b/src/documents/admin.py @@ -56,26 +56,35 @@ class DocumentAdmin(admin.ModelAdmin): def tags_(self, obj): r = "" for tag in obj.tags.all(): - r += '{}'.format( - tag.get_colour_display(), - "{}?tags__id__exact={}".format( - reverse("admin:documents_document_changelist"), - tag.pk - ), - tag.slug + 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 + ) + } ) return r tags_.allow_tags = True def document(self, obj): - return '' \ - '{} icon' \ - ''.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 admin.site.register(Sender) @@ -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}".format( + kind=kind, attributes=" ".join(attributes), inside=inside) + + return "<{} {}/>".format(kind, " ".join(attributes)) diff --git a/src/documents/consumer.py b/src/documents/consumer.py index d6818cf5d..6cf3b3d9d 100644 --- a/src/documents/consumer.py +++ b/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: " - - <tags>.<suffix>" "<sender> - <title>.<suffix>" "<title>.<suffix>" diff --git a/src/documents/forms.py b/src/documents/forms.py index d544917b4..404be1763 100644 --- a/src/documents/forms.py +++ b/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: diff --git a/src/documents/languages.py b/src/documents/languages.py index 2bfafe08a..5ea560654 100644 --- a/src/documents/languages.py +++ b/src/documents/languages.py @@ -185,10 +185,10 @@ 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" -} \ No newline at end of file +} diff --git a/src/documents/management/commands/document_retagger.py b/src/documents/management/commands/document_retagger.py index 09a3fb917..8f56e1eea 100644 --- a/src/documents/management/commands/document_retagger.py +++ b/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): diff --git a/src/documents/management/commands/loaddata_stdin.py b/src/documents/management/commands/loaddata_stdin.py index b6848f1eb..ca0b9ef7b 100644 --- a/src/documents/management/commands/loaddata_stdin.py +++ b/src/documents/management/commands/loaddata_stdin.py @@ -13,7 +13,7 @@ from django.core.management.commands.loaddata import Command as LoadDataCommand class Command(LoadDataCommand): def parse_name(self, fixture_name): - self.compression_formats['stdin'] = (lambda x,y: sys.stdin, None) + self.compression_formats['stdin'] = (lambda x, y: sys.stdin, None) if fixture_name == '-': return '-', 'json', 'stdin' diff --git a/src/documents/mixins.py b/src/documents/mixins.py index 881589fa3..4d4e9783f 100644 --- a/src/documents/mixins.py +++ b/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): diff --git a/src/documents/models.py b/src/documents/models.py index d4d95aa38..267bebffe 100644 --- a/src/documents/models.py +++ b/src/documents/models.py @@ -36,7 +36,7 @@ class Sender(SluggedModel): class Tag(SluggedModel): - + COLOURS = ( (1, "#a6cee3"), (2, "#1f78b4"), @@ -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 " diff --git a/src/documents/serialisers.py b/src/documents/serialisers.py index 209c778a1..f23a482c6 100644 --- a/src/documents/serialisers.py +++ b/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): diff --git a/src/documents/tests/test_consumer.py b/src/documents/tests/test_consumer.py index 7cee524c3..6db501e02 100644 --- a/src/documents/tests/test_consumer.py +++ b/src/documents/tests/test_consumer.py @@ -4,10 +4,10 @@ from ..consumer import Consumer class TestAttachment(TestCase): - + TAGS = ("tag1", "tag2", "tag3") CONSUMER = Consumer() - + def _test_guess_attributes_from_name(self, path, sender, title, tags): for suffix in ("pdf", "png", "jpg", "jpeg", "gif"): f = path.format(suffix) diff --git a/src/documents/tests/test_tags.py b/src/documents/tests/test_tags.py index f3518e012..e0ab43244 100644 --- a/src/documents/tests/test_tags.py +++ b/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")) - diff --git a/src/paperless/urls.py b/src/paperless/urls.py index d8a48995d..5803a6685 100644 --- a/src/paperless/urls.py +++ b/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: diff --git a/tox.ini b/tox.ini new file mode 100644 index 000000000..360385de8 --- /dev/null +++ b/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