Bump to v1.0.0!

Add multi-word match

.gitignore

@@ -68,6 +68,7 @@ db.sqlite3
 .idea
 
 # Other stuff that doesn't belong
+.virtualenv
 virtualenv
 .vagrant
 docker-compose.yml

README.rst

@@ -26,7 +26,8 @@ How it Works
 Paperless does not control your scanner, it only helps you deal with what your
 scanner produces
 
-1. Buy a document scanner like `this one`_ (used by me) or `this other one`_
+1. Buy a document scanner that can write to a place on your network.  If you
+   need some inspiration, have a look at the `scanner recommendations`_ page.
    recommended by another user.
 2. Set it up to "scan to FTP" or something similar. It should be able to push
    scanned images to a server without you having to do anything.  If your
@@ -118,8 +119,7 @@ The thing is, I'm doing ok for money, so I would instead ask you to donate to
 the `United Nations High Commissioner for Refugees`_.  They're doing important
 work and they need the money a lot more than I do.
 
-.. _this one: http://www.brother.ca/en-CA/Scanners/11/ProductDetail/ADS1500W?ProductDetail=productdetail
-.. _this other one: http://www.fujitsu.com/us/products/computing/peripheral/scanners/scansnap/ix500/
+.. _scanner recommendations: https://paperless.readthedocs.io/en/latest/scanners.html
 .. _ImageMagick: http://imagemagick.org/
 .. _Tesseract: https://github.com/tesseract-ocr
 .. _Unpaper: https://www.flameeyes.eu/projects/unpaper
@@ -140,5 +140,5 @@ work and they need the money a lot more than I do.
    :target: https://gitter.im/danielquinn/paperless?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge
 .. |Travis| image:: https://travis-ci.org/danielquinn/paperless.svg?branch=master
    :target: https://travis-ci.org/danielquinn/paperless
-.. |Dependencies| image:: https://www.versioneye.com/user/projects/57b33b81d9f1b00016faa500/badge.svg?style=flat-square
+.. |Dependencies| image:: https://www.versioneye.com/user/projects/57b33b81d9f1b00016faa500/badge.svg
    :target: https://www.versioneye.com/user/projects/57b33b81d9f1b00016faa500

Vagrantfile

@@ -12,4 +12,9 @@ Vagrant.configure(VAGRANT_API_VERSION) do |config|
 
   # Networking details
   config.vm.network "private_network", ip: "172.28.128.4"
+
+  config.vm.provider "virtualbox" do |vb|
+    # Customize the amount of memory on the VM:
+    vb.memory = "1024"
+  end
 end

docker-compose.yml.example

@@ -17,7 +17,7 @@ services:
         # value with nothing.
         environment:
             - PAPERLESS_OCR_LANGUAGES=
-        command: ["runserver", "0.0.0.0:8000"]
+        command: ["runserver", "--insecure", "0.0.0.0:8000"]
 
     consumer:
         image: pitkley/paperless
@@ -26,7 +26,7 @@ services:
             - media:/usr/src/paperless/media
             # You have to adapt the local path you want the consumption
             # directory to mount to by modifying the part before the ':'.
-            - /path/to/arbitrary/place:/consume
+            - ./consume:/consume
             # Likewise, you can add a local path to mount a directory for
             # exporting. This is not strictly needed for paperless to
             # function, only if you're exporting your files: uncomment

docs/changelog.rst

@@ -1,6 +1,49 @@
 Changelog
 #########
 
+* 1.0.0
+  * Upgrade to Django 1.11.  **You'll need to run
+    ``pip install -r requirements.txt`` to after the usual ``git pull`` to
+    properly update**.
+  * Replace the templatetag-based hack we had for document listing in favour of
+    a slightly less ugly solution in the form of another template tag with less
+    copypasta.
+  * Support for multi-word-matches for auto-tagging thanks to an excellent
+    patch from `ishirav`_ `#277`_.
+  * Fixed a CSS bug reported by `Stefan Hagen`_ that caused an overlapping of
+    the text and checkboxes under some resolutions `#272`_.
+  * Patched the Docker config to force the serving of static files.  Credit for
+    this one goes to `dev-rke`_ via `#248`_.
+  * Fix file permissions during Docker start up thanks to `Pit`_ on `#268`_.
+  * Date fields in the admin are now expressed as HTML5 date fields thanks to
+    `Lukas Winkler`_'s issue `#278`_
+
+* 0.8.0
+  * Paperless can now run in a subdirectory on a host (``/paperless``), rather
+    than always running in the root (``/``) thanks to `maphy-psd`_'s work on
+    `#255`_.
+
+* 0.7.0
+  * **Potentially breaking change**: As per `#235`_, Paperless will no longer
+    automatically delete documents attached to correspondents when those
+    correspondents are themselves deleted.  This was Django's default
+    behaviour, but didn't make much sense in Paperless' case.  Thanks to
+    `Thomas Brueggemann`_ and `David Martin`_ for their input on this one.
+  * Fix for `#232`_ wherein Paperless wasn't recognising ``.tif`` files
+    properly.  Thanks to `ayounggun`_ for reporting this one and to
+    `Kusti Skytén`_ for posting the correct solution in the Github issue.
+
+* 0.6.0
+  * Abandon the shared-secret trick we were using for the POST API in favour
+    of BasicAuth or Django session.
+  * Fix the POST API so it actually works.  `#236`_
+  * **Breaking change**: We've dropped the use of ``PAPERLESS_SHARED_SECRET``
+    as it was being used both for the API (now replaced with a normal auth)
+    and form email polling.  Now that we're only using it for email, this
+    variable has been renamed to ``PAPERLESS_EMAIL_SECRET``.  The old value
+    will still work for a while, but you should change your config if you've
+    been using the email polling feature.  Thanks to `Joshua Gilman`_ for all
+    the help with this feature.
 * 0.5.0
   * Support for fuzzy matching in the auto-tagger & auto-correspondent systems
     thanks to `Jake Gysland`_'s patch `#220`_.
@@ -11,7 +54,8 @@ Changelog
     thanks to `CkuT`_ for finding this shortcoming and doing the work to get
     it fixed in `#224`_.
   * All of the following changes are thanks to `David Martin`_:
-    * Bumped the dependency on pyocr to 0.4.7 so new users can make use of Tesseract 4 if they so prefer (`#226`_).
+    * Bumped the dependency on pyocr to 0.4.7 so new users can make use of
+    Tesseract 4 if they so prefer (`#226`_).
     * Fixed a number of issues with the automated mail handler (`#227`_, `#228`_)
     * Amended the documentation for better handling of systemd service files (`#229`_)
     * Amended the Django Admin configuration to have nice headers (`#230`_)
@@ -206,6 +250,14 @@ Changelog
 .. _CkuT: https://github.com/CkuT
 .. _David Martin: https://github.com/ddddavidmartin
 .. _Paperless Desktop: https://github.com/thomasbrueggemann/paperless-desktop
+.. _Joshua Gilman: https://github.com/jmgilman
+.. _ayounggun: https://github.com/ayounggun
+.. _Kusti Skytén: https://github.com/kskyten
+.. _maphy-psd: https://github.com/maphy-psd
+.. _ishirav: https://github.com/ishirav
+.. _Stefan Hagen: https://github.com/xkpd3
+.. _dev-rke: https://github.com/dev-rke
+.. _Lukas Winkler: https://github.com/Findus23
 
 .. _#20: https://github.com/danielquinn/paperless/issues/20
 .. _#44: https://github.com/danielquinn/paperless/issues/44
@@ -243,4 +295,12 @@ Changelog
 .. _#228: https://github.com/danielquinn/paperless/pull/228
 .. _#229: https://github.com/danielquinn/paperless/pull/229
 .. _#230: https://github.com/danielquinn/paperless/pull/230
-
+.. _#232: https://github.com/danielquinn/paperless/issues/232
+.. _#235: https://github.com/danielquinn/paperless/issues/235
+.. _#236: https://github.com/danielquinn/paperless/issues/236
+.. _#255: https://github.com/danielquinn/paperless/pull/255
+.. _#268: https://github.com/danielquinn/paperless/pull/268
+.. _#277: https://github.com/danielquinn/paperless/pull/277
+.. _#272: https://github.com/danielquinn/paperless/issues/272
+.. _#248: https://github.com/danielquinn/paperless/issues/248
+.. _#278: https://github.com/danielquinn/paperless/issues/248

docs/consumption.rst

@@ -125,7 +125,7 @@ So, with all that in mind, here's what you do to get it running:
    ``PATHS AND FOLDERS`` and ``SECURITY``.
    If you decided to use a subfolder of an existing account, then make sure you
    set ``PAPERLESS_CONSUME_MAIL_INBOX`` accordingly here.  You also have to set
-   the ``PAPERLESS_SHARED_SECRET`` to something you can remember 'cause you'll
+   the ``PAPERLESS_EMAIL_SECRET`` to something you can remember 'cause you'll
    have to include that in every email you send.
 3. Restart the :ref:`consumer <utilities-consumer>`.  The consumer will check
    the configured email account at startup and from then on every 10 minutes
@@ -147,46 +147,83 @@ So, with all that in mind, here's what you do to get it running:
 HTTP POST
 =========
 
-You can also submit a document via HTTP POST.  It doesn't do tags yet, and the
-URL schema isn't concrete, but it's a start.
-
-To push your document to Paperless, send an HTTP POST to the server with the
-following name/value pairs:
+You can also submit a document via HTTP POST, so long as you do so after
+authenticating.  To push your document to Paperless, send an HTTP POST to the
+server with the following name/value pairs:
 
 * ``correspondent``: The name of the document's correspondent.  Note that there
   are restrictions on what characters you can use here.  Specifically,
-  alphanumeric characters, `-`, `,`, `.`, and `'` are ok, everything else it
+  alphanumeric characters, `-`, `,`, `.`, and `'` are ok, everything else is
   out.  You also can't use the sequence ` - ` (space, dash, space).
 * ``title``: The title of the document.  The rules for characters is the same
   here as the correspondent.
-* ``signature``: For security reasons, we have the correspondent send a
-  signature using a "shared secret" method to make sure that random strangers
-  don't start uploading stuff to your server.  The means of generating this
-  signature is defined below.
+* ``document``: The file you're uploading
 
 Specify ``enctype="multipart/form-data"``, and then POST your file with::
 
     Content-Disposition: form-data; name="document"; filename="whatever.pdf"
 
+An example of this in HTML is a typical form:
 
-.. _consumption-http-signature:
+.. code:: html
 
-Generating the Signature
-------------------------
+    <form method="post" enctype="multipart/form-data">
+        <input type="text" name="correspondent" value="My Correspondent" />
+        <input type="text" name="title" value="My Title" />
+        <input type="file" name="document" />
+        <input type="submit" name="go" value="Do the thing" />
+    </form>
 
-Generating a signature based a shared secret is pretty simple: define a secret,
-and store it on the server and the client.  Then use that secret, along with
-the text you want to verify to generate a string that you can use for
-verification.
-
-In the case of Paperless, you configure the server with the secret by setting
-``UPLOAD_SHARED_SECRET``.  Then on your client, you generate your signature by
-concatenating the correspondent, title, and the secret, and then using sha256
-to generate a hexdigest.
-
-If you're using Python, this is what that looks like:
+But a potentially more useful way to do this would be in Python.  Here we use
+the requests library to handle basic authentication and to send the POST data
+to the URL.
 
 .. code:: python
 
+    import os
+
     from hashlib import sha256
-    signature = sha256(correspondent + title + secret).hexdigest()
+
+    import requests
+    from requests.auth import HTTPBasicAuth
+
+    # You authenticate via BasicAuth or with a session id.
+    # We use BasicAuth here
+    username = "my-username"
+    password = "my-super-secret-password"
+
+    # Where you have Paperless installed and listening
+    url = "http://localhost:8000/push"
+
+    # Document metadata
+    correspondent = "Test Correspondent"
+    title = "Test Title"
+
+    # The local file you want to push
+    path = "/path/to/some/directory/my-document.pdf"
+
+
+    with open(path, "rb") as f:
+
+        response = requests.post(
+            url=url,
+            data={"title": title,  "correspondent": correspondent},
+            files={"document": (os.path.basename(path), f, "application/pdf")},
+            auth=HTTPBasicAuth(username, password),
+            allow_redirects=False
+        )
+
+        if response.status_code == 202:
+
+            # Everything worked out ok
+            print("Upload successful")
+
+        else:
+
+            # If you don't get a 202, it's probably because your credentials
+            # are wrong or something.  This will give you a rough idea of what
+            # happened.
+
+            print("We got HTTP status code: {}".format(response.status_code))
+            for k, v in response.headers.items():
+                print("{}: {}".format(k, v))

docs/guesswork.rst

@@ -80,6 +80,12 @@ text and matching algorithm.  From the help info there:
     uses a regex to match the PDF.  If you don't know what a regex is, you
     probably don't want this option.
 
+When using the "any" or "all" matching algorithms, you can search for terms that
+consist of multiple words by enclosing them in double quotes. For example, defining
+a match text of ``"Bank of America" BofA`` using the "any" algorithm, will match
+documents that contain either "Bank of America" or "BofA", but will not match
+documents containing "Bank of South America".
+
 Then just save your tag/correspondent and run another document through the
 consumer.  Once complete, you should see the newly-created document,
 automatically tagged with the appropriate data.

docs/index.rst

@@ -3,10 +3,10 @@
 Paperless
 =========
 
-Paperless is a simple Django application running in two parts: 
-a :ref:`consumer <utilities-consumer>` (the thing that does the indexing) and 
+Paperless is a simple Django application running in two parts:
+a :ref:`consumer <utilities-consumer>` (the thing that does the indexing) and
 the :ref:`webserver <utilities-webserver>` (the part that lets you search & download
-already-indexed documents). If you want to learn more about its functions keep on 
+already-indexed documents). If you want to learn more about its functions keep on
 reading after the installation section.
 
 
@@ -19,8 +19,8 @@ Paper is a nightmare.  Environmental issues aside, there's no excuse for it in
 the 21st century.  It takes up space, collects dust, doesn't support any form of
 a search feature, indexing is tedious, it's heavy and prone to damage & loss.
 
-I wrote this to make "going paperless" easier.  I do not have to worry about 
-finding stuff again. I feed documents right from the post box into the scanner and 
+I wrote this to make "going paperless" easier.  I do not have to worry about
+finding stuff again. I feed documents right from the post box into the scanner and
 then shred them.  Perhaps you might find it useful too.
 
 
@@ -40,4 +40,5 @@ Contents
    guesswork
    migrating
    troubleshooting
+   scanners
    changelog

docs/scanners.rst

@@ -0,0 +1,29 @@
+.. _scanners:
+
+Scanner Recommendations
+=======================
+
+As Paperless operates by watching a folder for new files, doesn't care what
+scanner you use, but sometimes finding a scanner that will write to an FTP,
+NFS, or SMB server can be difficult.  This page is here to help you find one
+that works right for you based on recommentations from other Paperless users.
+
++---------+----------------+-----+-----+-----+----------------+
+| Brand   | Model          | Supports        | Recommended By |
++---------+----------------+-----+-----+-----+----------------+
+|         |                | FTP | NFS | SMB |                |
++=========+================+=====+=====+=====+================+
+| Brother | `ADS-1500W`_   | yes | no  | yes | `danielquinn`_ |
++---------+----------------+-----+-----+-----+----------------+
+| Brother | `MFC-J6930DW`_ | yes |     |     | `ayounggun`_   |
++---------+----------------+-----+-----+-----+----------------+
+| Fujitsu | `ix500`_       | yes |     | yes | `eonist`_      |
++---------+----------------+-----+-----+-----+----------------+
+
+.. _ADS-1500W: https://www.brother.ca/en/p/ads1500w
+.. _MFC-J6930DW: https://www.brother.ca/en/p/MFCJ6930DW
+.. _ix500: http://www.fujitsu.com/us/products/computing/peripheral/scanners/scansnap/ix500/
+
+.. _danielquinn: https://github.com/danielquinn
+.. _ayounggun: https://github.com/ayounggun
+.. _eonist: https://github.com/eonist

docs/setup.rst

@@ -394,7 +394,10 @@ Using a Real Webserver
 The default is to use Django's development server, as that's easy and does the
 job well enough on a home network.  However, if you want to do things right,
 it's probably a good idea to use a webserver capable of handling more than one
-thread.
+thread. You will also have to let the webserver serve the static files (CSS,
+JavaScript) from the directory configured in ``PAPERLESS_STATICDIR``. For that,
+you need to run ``./manage.py collectstatic`` in the ``src`` directory.  The
+default static files directory is ``../static``.
 
 Apache
 ~~~~~~
@@ -572,3 +575,28 @@ If you're using Docker, you can set a restart-policy_ in the
 Docker daemon.
 
 .. _restart-policy: https://docs.docker.com/engine/reference/commandline/run/#restart-policies-restart
+
+
+.. _setup-subdirectory
+
+Hosting Paperless in a Subdirectory
+-----------------------------------
+
+Paperless was designed to run off the root of the hosting domain,
+(ie: ``https://example.com/``) but with a few changes, you can configure
+it to run in a subdirectory on your server
+(ie: ``https://example.com/paperless/``).
+
+Thanks to the efforts of `maphy-psd`_ on `Github`_, running Paperless in a
+subdirectory is now as easy as setting a config variable.  Simply set
+``PAPERLESS_FORCE_SCRIPT_NAME`` in your environment or
+``/etc/paperless.conf`` to the path you want Paperless hosted at, configure
+Nginx/Apache for your needs and you're done.  So, if you want Paperless to live
+at ``https://example.com/arbitrary/path/to/paperless`` then you just set
+``PAPERLESS_FORCE_SCRIPT_NAME`` to ``/arbitrary/path/to/paperless``.  Note the
+leading ``/`` there.
+
+As to how to configure Nginx or Apache for this, that's on you :-)
+
+.. _maphy-psd: https://github.com/maphy-psd
+.. _Github: https://github.com/danielquinn/paperless/pull/255

paperless.conf.example

@@ -5,7 +5,7 @@
 
 
 ###############################################################################
-####                       Paths  and folders                              ####
+####                         Paths & Folders                               ####
 ###############################################################################
 
 # This where your documents should go to be consumed.  Make sure that it exists
@@ -39,7 +39,11 @@ PAPERLESS_CONSUME_MAIL_PASS=""
 
 # Override the default IMAP inbox here. If not set Paperless defaults to
 # "INBOX".
-#PAPERLESS_CONSUME_MAIL_INBOX=""
+#PAPERLESS_CONSUME_MAIL_INBOX="INBOX"
+
+# Any email sent to the target account that does not contain this text will be
+# ignored.
+PAPERLESS_EMAIL_SECRET=""
 
 
 ###############################################################################
@@ -61,11 +65,6 @@ PAPERLESS_CONSUME_MAIL_PASS=""
 PAPERLESS_PASSPHRASE="secret"
 
 
-# If you intend to consume documents either via HTTP POST or by email, you must
-# have a shared secret here.
-PAPERLESS_SHARED_SECRET=""
-
-
 # The secret key has a default that should be fine so long as you're hosting
 # Paperless on a closed network.  However, if you're putting this anywhere
 # public, you should change the key to something unique and verbose.
@@ -81,6 +80,11 @@ PAPERLESS_SHARED_SECRET=""
 # as is "example.com,www.example.com", but NOT " example.com" or "example.com,"
 #PAPERLESS_ALLOWED_HOSTS="example.com,www.example.com"
 
+# To host paperless under a subpath url like example.com/paperless you set
+# this value to /paperless. No trailing slash!
+#
+# https://docs.djangoproject.com/en/1.11/ref/settings/#force-script-name
+#PAPERLESS_FORCE_SCRIPT_NAME=""
 
 ###############################################################################
 ####                          Software Tweaks                              ####
@@ -157,7 +161,9 @@ PAPERLESS_SHARED_SECRET=""
 ####                            Interface                                  ####
 ###############################################################################
 
-# Override the default UTC time zone here
+# Override the default UTC time zone here.
+# See https://docs.djangoproject.com/en/1.10/ref/settings/#std:setting-TIME_ZONE
+# for details on how to set it.
 #PAPERLESS_TIME_ZONE=UTC
 
 

requirements.txt

@@ -1,4 +1,4 @@
-Django==1.10.5
+Django>=1.11,<2.0
 Pillow>=3.1.1
 django-crispy-forms>=1.6.1
 django-extensions>=1.7.6
@@ -13,12 +13,14 @@ python-dateutil>=2.6.0
 python-dotenv>=0.6.2
 python-gnupg>=0.3.9
 pytz>=2016.10
-gunicorn==19.6.0
+gunicorn==19.7.1
 
 # For the tests
+factory-boy
 pytest
 pytest-django
 pytest-sugar
-pep8
+pytest-env
+pycodestyle
 flake8
 tox

scripts/docker-entrypoint.sh

@@ -7,9 +7,9 @@ map_uidgid() {
     USERMAP_ORIG_UID=$(id -g paperless)
     USERMAP_GID=${USERMAP_GID:-${USERMAP_UID:-$USERMAP_ORIG_GID}}
     USERMAP_UID=${USERMAP_UID:-$USERMAP_ORIG_UID}
-    if [[ ${USERMAP_UID} != ${USERMAP_ORIG_UID} || ${USERMAP_GID} != ${USERMAP_ORIG_GID} ]]; then
+    if [[ ${USERMAP_UID} != "${USERMAP_ORIG_UID}" || ${USERMAP_GID} != "${USERMAP_ORIG_GID}" ]]; then
         echo "Mapping UID and GID for paperless:paperless to $USERMAP_UID:$USERMAP_GID"
-        groupmod -g ${USERMAP_GID} paperless
+        groupmod -g "${USERMAP_GID}" paperless
         sed -i -e "s|:${USERMAP_ORIG_UID}:${USERMAP_GID}:|:${USERMAP_UID}:${USERMAP_GID}:|" /etc/passwd
     fi
 }
@@ -25,16 +25,16 @@ set_permissions() {
           echo "failed."
           echo ""
           echo "Either try to set it on your host-mounted directory"
-          echo "directly, or make sure that the directory has \`o+x\`"
+          echo "directly, or make sure that the directory has \`g+wx\`"
           echo "permissions and the files in it at least \`o+r\`."
       } >&2
-      chmod g+x "${!dir}" || {
+      chmod g+wx "${!dir}" || {
           echo "Changing group permissions of ${cur_dir_name} directory:"
           echo "  ${!dir}"
           echo "failed."
           echo ""
           echo "Either try to set it on your host-mounted directory"
-          echo "directly, or make sure that the directory has \`o+x\`"
+          echo "directly, or make sure that the directory has \`g+wx\`"
           echo "permissions and the files in it at least \`o+r\`."
       } >&2
     done
@@ -62,11 +62,11 @@ install_languages() {
     # Loop over languages to be installed
     for lang in "${langs[@]}"; do
         pkg="tesseract-ocr-$lang"
-        if dpkg -s "$pkg" 2>&1 > /dev/null; then
+        if dpkg -s "$pkg" > /dev/null 2>&1; then
             continue
         fi
 
-        if ! apt-cache show "$pkg" 2>&1 > /dev/null; then
+        if ! apt-cache show "$pkg" > /dev/null 2>&1; then
             continue
         fi
 

src/documents/admin.py

@@ -70,9 +70,14 @@ class DocumentAdmin(CommonAdmin):
     created_.short_description = "Created"
 
     def thumbnail(self, obj):
+        if settings.FORCE_SCRIPT_NAME:
+            src_link = "{}/fetch/thumb/{}".format(
+                settings.FORCE_SCRIPT_NAME, obj.id)
+        else:
+            src_link = "/fetch/thumb/{}".format(obj.id)
         png_img = self._html_tag(
             "img",
-            src="/fetch/thumb/{}".format(obj.id),
+            src=src_link,
             width=180,
             alt="Thumbnail of {}".format(obj.file_name),
             title=obj.file_name

src/documents/forms.py

@@ -2,7 +2,6 @@ import magic
 import os
 
 from datetime import datetime
-from hashlib import sha256
 from time import mktime
 
 from django import forms
@@ -14,7 +13,6 @@ from .consumer import Consumer
 
 class UploadForm(forms.Form):
 
-    SECRET = settings.SHARED_SECRET
     TYPE_LOOKUP = {
         "application/pdf": Document.TYPE_PDF,
         "image/png": Document.TYPE_PNG,
@@ -32,10 +30,9 @@ class UploadForm(forms.Form):
         required=False
     )
     document = forms.FileField()
-    signature = forms.CharField(max_length=256)
 
     def __init__(self, *args, **kwargs):
-        forms.Form.__init__(*args, **kwargs)
+        forms.Form.__init__(self, *args, **kwargs)
         self._file_type = None
 
     def clean_correspondent(self):
@@ -82,17 +79,6 @@ class UploadForm(forms.Form):
 
         return document
 
-    def clean(self):
-
-        corresp = self.cleaned_data.get("correspondent")
-        title = self.cleaned_data.get("title")
-        signature = self.cleaned_data.get("signature")
-
-        if sha256(corresp + title + self.SECRET).hexdigest() == signature:
-            return self.cleaned_data
-
-        raise forms.ValidationError("The signature provided did not validate")
-
     def save(self):
         """
         Since the consumer already does a lot of work, it's easier just to save
@@ -104,7 +90,7 @@ class UploadForm(forms.Form):
         title = self.cleaned_data.get("title")
         document = self.cleaned_data.get("document")
 
-        t = int(mktime(datetime.now()))
+        t = int(mktime(datetime.now().timetuple()))
         file_name = os.path.join(
             Consumer.CONSUME,
             "{} - {}.{}".format(correspondent, title, self._file_type)

src/documents/mail.py

@@ -43,7 +43,10 @@ class Message(Loggable):
     and n attachments, and that we don't care about the message body.
     """
 
-    SECRET = settings.SHARED_SECRET
+    SECRET = os.getenv(
+        "PAPERLESS_EMAIL_SECRET",
+        os.getenv("PAPERLESS_SHARED_SECRET")  # TODO: Remove after 2017/09
+    )
 
     def __init__(self, data, group=None):
         """
@@ -153,11 +156,11 @@ class MailFetcher(Loggable):
         Loggable.__init__(self)
 
         self._connection = None
-        self._host = settings.MAIL_CONSUMPTION["HOST"]
-        self._port = settings.MAIL_CONSUMPTION["PORT"]
-        self._username = settings.MAIL_CONSUMPTION["USERNAME"]
-        self._password = settings.MAIL_CONSUMPTION["PASSWORD"]
-        self._inbox = settings.MAIL_CONSUMPTION["INBOX"]
+        self._host = os.getenv("PAPERLESS_CONSUME_MAIL_HOST")
+        self._port = os.getenv("PAPERLESS_CONSUME_MAIL_PORT")
+        self._username = os.getenv("PAPERLESS_CONSUME_MAIL_USER")
+        self._password = os.getenv("PAPERLESS_CONSUME_MAIL_PASS")
+        self._inbox = os.getenv("PAPERLESS_CONSUME_MAIL_INBOX", "INBOX")
 
         self._enabled = bool(self._host)
 

src/documents/migrations/0012_auto_20160305_0040.py

@@ -38,6 +38,9 @@ class GnuPG(object):
 
 def move_documents_and_create_thumbnails(apps, schema_editor):
 
+    os.makedirs(os.path.join(settings.MEDIA_ROOT, "documents", "originals"), exist_ok=True)
+    os.makedirs(os.path.join(settings.MEDIA_ROOT, "documents", "thumbnails"), exist_ok=True)
+
     documents = os.listdir(os.path.join(settings.MEDIA_ROOT, "documents"))
 
     if set(documents) == {"originals", "thumbnails"}:

src/documents/migrations/0018_auto_20170715_1712.py

@@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+# Generated by Django 1.10.5 on 2017-07-15 17:12
+from __future__ import unicode_literals
+
+from django.db import migrations, models
+import django.db.models.deletion
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('documents', '0017_auto_20170512_0507'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='document',
+            name='correspondent',
+            field=models.ForeignKey(blank=True, null=True, on_delete=django.db.models.deletion.SET_NULL, related_name='documents', to='documents.Correspondent'),
+        ),
+    ]

src/documents/models.py

@@ -1,3 +1,5 @@
+# coding=utf-8
+
 import dateutil.parser
 import logging
 import os
@@ -89,7 +91,7 @@ class MatchingModel(models.Model):
             search_kwargs = {"flags": re.IGNORECASE}
 
         if self.matching_algorithm == self.MATCH_ALL:
-            for word in self.match.split(" "):
+            for word in self._split_match():
                 search_result = re.search(
                     r"\b{}\b".format(word), text, **search_kwargs)
                 if not search_result:
@@ -97,7 +99,7 @@ class MatchingModel(models.Model):
             return True
 
         if self.matching_algorithm == self.MATCH_ANY:
-            for word in self.match.split(" "):
+            for word in self._split_match():
                 if re.search(r"\b{}\b".format(word), text, **search_kwargs):
                     return True
             return False
@@ -121,6 +123,21 @@ class MatchingModel(models.Model):
 
         raise NotImplementedError("Unsupported matching algorithm")
 
+    def _split_match(self):
+        """
+        Splits the match to individual keywords, getting rid of unnecessary
+        spaces and grouping quoted words together.
+
+        Example:
+          '  some random  words "with   quotes  " and   spaces'
+            ==>
+          ["some", "random", "words", "with\s+quotes", "and", "spaces"]
+        """
+        findterms = re.compile(r'"([^"]+)"|(\S+)').findall
+        normspace = re.compile(r"\s+").sub
+        return [normspace(r"\s+", (t[0] or t[1]).strip())
+                for t in findterms(self.match)]
+
     def save(self, *args, **kwargs):
 
         self.match = self.match.lower()
@@ -172,7 +189,12 @@ class Document(models.Model):
     TYPES = (TYPE_PDF, TYPE_PNG, TYPE_JPG, TYPE_GIF, TYPE_TIF,)
 
     correspondent = models.ForeignKey(
-        Correspondent, blank=True, null=True, related_name="documents")
+        Correspondent,
+        blank=True,
+        null=True,
+        related_name="documents",
+        on_delete=models.SET_NULL
+    )
 
     title = models.CharField(max_length=128, blank=True, db_index=True)
 
@@ -316,45 +338,45 @@ class FileInfo(object):
             r"(?P<correspondent>.*) - "
             r"(?P<title>.*) - "
             r"(?P<tags>[a-z0-9\-,]*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
+            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
             flags=re.IGNORECASE
         )),
         ("created-title-tags", re.compile(
             r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
             r"(?P<title>.*) - "
             r"(?P<tags>[a-z0-9\-,]*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
+            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
             flags=re.IGNORECASE
         )),
         ("created-correspondent-title", re.compile(
             r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
             r"(?P<correspondent>.*) - "
             r"(?P<title>.*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
+            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
             flags=re.IGNORECASE
         )),
         ("created-title", re.compile(
             r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
             r"(?P<title>.*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
+            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
             flags=re.IGNORECASE
         )),
         ("correspondent-title-tags", re.compile(
             r"(?P<correspondent>.*) - "
             r"(?P<title>.*) - "
             r"(?P<tags>[a-z0-9\-,]*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
+            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
             flags=re.IGNORECASE
         )),
         ("correspondent-title", re.compile(
             r"(?P<correspondent>.*) - "
             r"(?P<title>.*)?"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
+            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
             flags=re.IGNORECASE
         )),
         ("title", re.compile(
             r"(?P<title>.*)"
-            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
+            r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
             flags=re.IGNORECASE
         ))
     ])
@@ -397,6 +419,8 @@ class FileInfo(object):
         r = extension.lower()
         if r == "jpeg":
             return "jpg"
+        if r == "tif":
+            return "tiff"
         return r
 
     @classmethod

src/documents/templates/admin/change_list_results.html

@@ -1,6 +0,0 @@
-{% load hacks %}
-
-{# See documents.templatetags.hacks.change_list_results for an explanation #}
-
-{% change_list_results %}
-

src/documents/templates/admin/documents/document/change_form.html

@@ -0,0 +1,13 @@
+{% extends 'admin/change_form.html' %}
+
+
+{% block footer %}
+
+	{{ block.super }}
+
+	{# Hack to force Django to make the created date a date input rather than `text` (the default) #}
+	<script>
+		django.jQuery(".field-created input").first().attr("type", "date")
+	</script>
+
+{% endblock footer %}

src/documents/templates/admin/documents/document/change_list.html

@@ -0,0 +1,12 @@
+{% extends 'admin/change_list.html' %}
+
+
+{% load admin_actions from admin_list%}
+{% load result_list from hacks %}
+
+
+{% block result_list %}
+	{% if action_form and actions_on_top and cl.show_admin_actions %}{% admin_actions %}{% endif %}
+	{% result_list cl %}
+	{% if action_form and actions_on_bottom and cl.show_admin_actions %}{% admin_actions %}{% endif %}
+{% endblock %}

src/documents/templates/admin/documents/document/change_list_results.html

@@ -29,18 +29,13 @@
   .result .header {
     padding: 5px;
     background-color: #79AEC8;
-    height: 6em;
-  }
-  .result .header .checkbox {
-    margin-right: 5px;
   }
   .result .header .checkbox{
     width: 5%;
     float: left;
   }
   .result .header .info {
-    width: 90%;
-    float: left;
+    margin-left: 10%;
   }
   .result .header a,
   .result a.tag {

src/documents/templates/documents/index.html

@@ -6,5 +6,6 @@
     <meta charset="utf-8">
   </head>
   <body>
+		{# One day someone (maybe even myself) is going to write a proper web front-end for Paperless, and this is where it'll start. #}
   </body>
 </html>

src/documents/templatetags/hacks.py

@@ -1,41 +1,28 @@
-import os
-
-from django.contrib import admin
+from django.contrib.admin.templatetags.admin_list import (
+    result_headers,
+    result_hidden_fields,
+    results
+)
 from django.template import Library
-from django.template.loader import get_template
-
-from ..models import Document
 
 
 register = Library()
 
 
-@register.simple_tag(takes_context=True)
-def change_list_results(context):
+@register.inclusion_tag("admin/documents/document/change_list_results.html")
+def result_list(cl):
     """
-    Django has a lot of places where you can override defaults, but
-    unfortunately, `change_list_results.html` is not one of them.  In fact,
-    it's a downright pain in the ass to override this file on a per-model basis
-    and this is the cleanest way I could come up with.
-
-    Basically all we've done here is defined `change_list_results.html` in an
-    `admin` directory which globally overrides that file for *every* model.
-    That template however simply loads this templatetag which determines
-    whether we're currently looking at a `Document` listing or something else
-    and loads the appropriate file in each case.
-
-    Better work arounds for this are welcome as I hate this myself, but at the
-    moment, it's all I could come up with.
+    Copy/pasted from django.contrib.admin.templatetags.admin_list just so I can
+    modify the value passed to `.inclusion_tag()` in the decorator here.  There
+    must be a cleaner way... right?
     """
-
-    path = os.path.join(
-        os.path.dirname(admin.__file__),
-        "templates",
-        "admin",
-        "change_list_results.html"
-    )
-
-    if context["cl"].model == Document:
-        path = "admin/documents/document/change_list_results.html"
-
-    return get_template(path).render(context)
+    headers = list(result_headers(cl))
+    num_sorted_fields = 0
+    for h in headers:
+        if h['sortable'] and h['sorted']:
+            num_sorted_fields += 1
+    return {'cl': cl,
+            'result_hidden_fields': list(result_hidden_fields(cl)),
+            'result_headers': headers,
+            'num_sorted_fields': num_sorted_fields,
+            'results': list(results(cl))}

src/documents/tests/factories.py

@@ -0,0 +1,17 @@
+import factory
+
+from ..models import Document, Correspondent
+
+
+class CorrespondentFactory(factory.DjangoModelFactory):
+
+    class Meta:
+        model = Correspondent
+
+    name = factory.Faker("name")
+
+
+class DocumentFactory(factory.DjangoModelFactory):
+
+    class Meta:
+        model = Document

src/documents/tests/test_consumer.py

@@ -58,9 +58,9 @@ class TestAttributes(TestCase):
 
     TAGS = ("tag1", "tag2", "tag3")
     EXTENSIONS = (
-        "pdf", "png", "jpg", "jpeg", "gif",
-        "PDF", "PNG", "JPG", "JPEG", "GIF",
-        "PdF", "PnG", "JpG", "JPeG", "GiF",
+        "pdf", "png", "jpg", "jpeg", "gif", "tiff", "tif",
+        "PDF", "PNG", "JPG", "JPEG", "GIF", "TIFF", "TIF",
+        "PdF", "PnG", "JpG", "JPeG", "GiF", "TiFf", "TiF",
     )
 
     def _test_guess_attributes_from_name(self, path, sender, title, tags):
@@ -80,6 +80,8 @@ class TestAttributes(TestCase):
             self.assertEqual(tuple([t.slug for t in file_info.tags]), tags, f)
             if extension.lower() == "jpeg":
                 self.assertEqual(file_info.extension, "jpg", f)
+            elif extension.lower() == "tif":
+                self.assertEqual(file_info.extension, "tiff", f)
             else:
                 self.assertEqual(file_info.extension, extension.lower(), f)
 

src/documents/tests/test_matchables.py

@@ -1,6 +1,6 @@
 from random import randint
 
-from django.test import TestCase
+from django.test import TestCase, override_settings
 
 from ..models import Correspondent, Document, Tag
 from ..signals import document_consumption_finished
@@ -16,9 +16,15 @@ class TestMatching(TestCase):
                 matching_algorithm=getattr(klass, algorithm)
             )
             for string in true:
-                self.assertTrue(instance.matches(string))
+                self.assertTrue(
+                    instance.matches(string),
+                    '"%s" should match "%s" but it does not' % (text, string)
+                )
             for string in false:
-                self.assertFalse(instance.matches(string))
+                self.assertFalse(
+                    instance.matches(string),
+                    '"%s" should not match "%s" but it does' % (text, string)
+                )
 
     def test_match_all(self):
 
@@ -54,6 +60,21 @@ class TestMatching(TestCase):
             )
         )
 
+        self._test_matching(
+            'brown fox "lazy dogs"',
+            "MATCH_ALL",
+            (
+                "the quick brown fox jumped over the lazy dogs",
+                "the quick brown fox jumped over the lazy  dogs",
+            ),
+            (
+                "the quick fox jumped over the lazy dogs",
+                "the quick brown wolf jumped over the lazy dogs",
+                "the quick brown fox jumped over the fat dogs",
+                "the quick brown fox jumped over the lazy... dogs",
+            )
+        )
+
     def test_match_any(self):
 
         self._test_matching(
@@ -89,6 +110,18 @@ class TestMatching(TestCase):
             )
         )
 
+        self._test_matching(
+            '"brown fox" " lazy  dogs "',
+            "MATCH_ANY",
+            (
+                "the quick brown fox",
+                "jumped over the lazy  dogs.",
+            ),
+            (
+                "the lazy fox jumped over the brown dogs",
+            )
+        )
+
     def test_match_literal(self):
 
         self._test_matching(
@@ -166,7 +199,8 @@ class TestMatching(TestCase):
         )
 
 
-class TestApplications(TestCase):
+@override_settings(POST_CONSUME_SCRIPT=None)
+class TestDocumentConsumptionFinishedSignal(TestCase):
     """
     We make use of document_consumption_finished, so we should test that it's
     doing what we expect wrt to tag & correspondent matching.

src/documents/tests/test_models.py

@@ -0,0 +1,31 @@
+from django.test import TestCase
+
+from ..models import Document, Correspondent
+from .factories import DocumentFactory, CorrespondentFactory
+
+
+class CorrespondentTestCase(TestCase):
+
+    def test___str__(self):
+        for s in ("test", "οχι", "test with fun_charÅc'\"terß"):
+            correspondent = CorrespondentFactory.create(name=s)
+            self.assertEqual(str(correspondent), s)
+
+
+class DocumentTestCase(TestCase):
+
+    def test_correspondent_deletion_does_not_cascade(self):
+
+        self.assertEqual(Correspondent.objects.all().count(), 0)
+        correspondent = CorrespondentFactory.create()
+        self.assertEqual(Correspondent.objects.all().count(), 1)
+
+        self.assertEqual(Document.objects.all().count(), 0)
+        DocumentFactory.create(correspondent=correspondent)
+        self.assertEqual(Document.objects.all().count(), 1)
+        self.assertIsNotNone(Document.objects.all().first().correspondent)
+
+        correspondent.delete()
+        self.assertEqual(Correspondent.objects.all().count(), 0)
+        self.assertEqual(Document.objects.all().count(), 1)
+        self.assertIsNone(Document.objects.all().first().correspondent)

src/documents/views.py

@@ -1,5 +1,4 @@
-from django.http import HttpResponse
-from django.views.decorators.csrf import csrf_exempt
+from django.http import HttpResponse, HttpResponseBadRequest
 from django.views.generic import DetailView, FormView, TemplateView
 from django_filters.rest_framework import DjangoFilterBackend
 from paperless.db import GnuPG
@@ -81,15 +80,12 @@ class PushView(SessionOrBasicAuthMixin, FormView):
 
     form_class = UploadForm
 
-    @classmethod
-    def as_view(cls, **kwargs):
-        return csrf_exempt(FormView.as_view(**kwargs))
-
     def form_valid(self, form):
-        return HttpResponse("1")
+        form.save()
+        return HttpResponse("1", status=202)
 
     def form_invalid(self, form):
-        return HttpResponse("0")
+        return HttpResponseBadRequest(str(form.errors))
 
 
 class CorrespondentViewSet(ModelViewSet):

src/paperless/checks.py

@@ -84,3 +84,20 @@ def binaries_check(app_configs, **kwargs):
             check_messages.append(Warning(error.format(binary), hint))
 
     return check_messages
+
+
+@register()
+def config_check(app_configs, **kwargs):
+    warning = (
+        "It looks like you have PAPERLESS_SHARED_SECRET defined.  Note that "
+        "in the \npast, this variable was used for both API authentication "
+        "and as the mail \nkeyword.  As the API no no longer uses it, this "
+        "variable has been renamed to \nPAPERLESS_EMAIL_SECRET, so if you're "
+        "using the mail feature, you'd best update \nyour variable name.\n\n"
+        "The old variable will stop working in a few months."
+    )
+
+    if os.getenv("PAPERLESS_SHARED_SECRET"):
+        return [Warning(warning)]
+
+    return []

src/paperless/settings.py

@@ -47,7 +47,8 @@ _allowed_hosts = os.getenv("PAPERLESS_ALLOWED_HOSTS")
 if _allowed_hosts:
     ALLOWED_HOSTS = _allowed_hosts.split(",")
 
-
+FORCE_SCRIPT_NAME = os.getenv("PAPERLESS_FORCE_SCRIPT_NAME")
+    
 # Application definition
 
 INSTALLED_APPS = [
@@ -69,6 +70,7 @@ INSTALLED_APPS = [
 
     "rest_framework",
     "crispy_forms",
+    "django_filters"
 
 ]
 
@@ -236,20 +238,6 @@ CONSUMPTION_DIR = os.getenv("PAPERLESS_CONSUMPTION_DIR")
 # slowly, you may want to use a higher value than the default.
 CONSUMER_LOOP_TIME = int(os.getenv("PAPERLESS_CONSUMER_LOOP_TIME", 10))
 
-# If you want to use IMAP mail consumption, populate this with useful values.
-# If you leave HOST set to None, we assume you're not going to use this
-# feature.
-MAIL_CONSUMPTION = {
-    "HOST": os.getenv("PAPERLESS_CONSUME_MAIL_HOST"),
-    "PORT": os.getenv("PAPERLESS_CONSUME_MAIL_PORT"),
-    "USERNAME": os.getenv("PAPERLESS_CONSUME_MAIL_USER"),
-    "PASSWORD": os.getenv("PAPERLESS_CONSUME_MAIL_PASS"),
-    # If True, use SSL/TLS to connect
-    "USE_SSL": os.getenv("PAPERLESS_CONSUME_MAIL_USE_SSL", "y").lower() == "y",
-    # The name of the inbox on the server
-    "INBOX": os.getenv("PAPERLESS_CONSUME_MAIL_INBOX", "INBOX")
-}
-
 # This is used to encrypt the original documents and decrypt them later when
 # you want to download them.  Set it and change the permissions on this file to
 # 0600, or set it to `None` and you'll be prompted for the passphrase at
@@ -259,11 +247,6 @@ MAIL_CONSUMPTION = {
 # files.
 PASSPHRASE = os.getenv("PAPERLESS_PASSPHRASE")
 
-# If you intend to use the "API" to push files into the consumer, you'll need
-# to provide a shared secret here.  Leaving this as the default will disable
-# the API.
-SHARED_SECRET = os.getenv("PAPERLESS_SHARED_SECRET", "")
-
 # Trigger a script after every successful document consumption?
 PRE_CONSUME_SCRIPT = os.getenv("PAPERLESS_PRE_CONSUME_SCRIPT")
 POST_CONSUME_SCRIPT = os.getenv("PAPERLESS_POST_CONSUME_SCRIPT")

src/paperless/urls.py

@@ -1,28 +1,17 @@
-"""paperless URL Configuration
-
-The `urlpatterns` list routes URLs to views. For more information please see:
-    https://docs.djangoproject.com/en/1.10/topics/http/urls/
-Examples:
-Function views
-    1. Add an import:  from my_app import views
-    2. Add a URL to urlpatterns:  url(r'^$', views.home, name='home')
-Class-based views
-    1. Add an import:  from other_app.views import Home
-    2. Add a URL to urlpatterns:  url(r'^$', Home.as_view(), name='home')
-Including another URLconf
-    1. Add an import:  from blog import urls as blog_urls
-    2. Import the include() function: from django.conf.urls import url, include
-    3. Add a URL to urlpatterns:  url(r'^blog/', include(blog_urls))
-"""
 from django.conf import settings
-from django.conf.urls import url, static, include
+from django.conf.urls import include, static, url
 from django.contrib import admin
-
+from django.views.decorators.csrf import csrf_exempt
+from django.views.generic import RedirectView
 from rest_framework.routers import DefaultRouter
 
 from documents.views import (
-    IndexView, FetchView, PushView,
-    CorrespondentViewSet, TagViewSet, DocumentViewSet, LogViewSet
+    CorrespondentViewSet,
+    DocumentViewSet,
+    FetchView,
+    LogViewSet,
+    PushView,
+    TagViewSet
 )
 from reminders.views import ReminderViewSet
 
@@ -42,9 +31,6 @@ urlpatterns = [
     ),
     url(r"^api/", include(router.urls, namespace="drf")),
 
-    # Normal pages (coming soon)
-    # url(r"^$", IndexView.as_view(), name="index"),
-
     # File downloads
     url(
         r"^fetch/(?P<kind>doc|thumb)/(?P<pk>\d+)$",
@@ -52,15 +38,17 @@ urlpatterns = [
         name="fetch"
     ),
 
+    # File uploads
+    url(r"^push$", csrf_exempt(PushView.as_view()), name="push"),
+
     # The Django admin
     url(r"admin/", admin.site.urls),
-    url(r"", admin.site.urls),  # This is going away
+
+    # Catch all redirect back to /admin
+    url(r"", RedirectView.as_view(permanent=True, url="/admin/")),
 
 ] + static.static(settings.MEDIA_URL, document_root=settings.MEDIA_ROOT)
 
-if settings.SHARED_SECRET:
-    urlpatterns.insert(0, url(r"^push$", PushView.as_view(), name="push"))
-
 # Text in each page's <h1> (and above login form).
 admin.site.site_header = 'Paperless'
 # Text at the end of each page's <title>.

src/paperless/version.py

@@ -1 +1 @@
-__version__ = (0, 5, 0)
+__version__ = (1, 0, 0)

src/paperless_tesseract/signals.py

@@ -5,7 +5,7 @@ from .parsers import RasterisedDocumentParser
 
 class ConsumerDeclaration(object):
 
-    MATCHING_FILES = re.compile("^.*\.(pdf|jpg|gif|png|tiff?|pnm|bmp)$")
+    MATCHING_FILES = re.compile("^.*\.(pdf|jpe?g|gif|png|tiff?|pnm|bmp)$")
 
     @classmethod
     def handle(cls, sender, **kwargs):

src/paperless_tesseract/tests/test_signals.py

@@ -12,9 +12,9 @@ class SignalsTestCase(TestCase):
             "A document with a . in it", "Doc with -- in it"
         )
         suffixes = (
-            "pdf", "jpg", "gif", "png", "tiff", "tif", "pnm", "bmp",
-            "PDF", "JPG", "GIF", "PNG", "TIFF", "TIF", "PNM", "BMP",
-            "pDf", "jPg", "gIf", "pNg", "tIff", "tIf", "pNm", "bMp",
+            "pdf", "jpg", "jpeg", "gif", "png", "tiff", "tif", "pnm", "bmp",
+            "PDF", "JPG", "JPEG", "GIF", "PNG", "TIFF", "TIF", "PNM", "BMP",
+            "pDf", "jPg", "jpEg", "gIf", "pNg", "tIff", "tIf", "pNm", "bMp",
         )
 
         for prefix in prefixes:

src/pytest.ini

@@ -1,3 +1,8 @@
 [pytest]
 DJANGO_SETTINGS_MODULE=paperless.settings
-
+addopts = --pythonwarnings=all
+env =
+  PAPERLESS_CONSUME=/tmp
+  PAPERLESS_PASSPHRASE=THISISNOTASECRET
+  PAPERLESS_SECRET=paperless
+  PAPERLESS_EMAIL_SECRET=paperless

src/tox.ini

@@ -5,19 +5,18 @@
 
 [tox]
 skipsdist = True
-envlist = py34, py35, py36, pep8
+envlist = py34, py35, py36, pycodestyle
 
 [testenv]
-commands = {envpython} manage.py test
+commands = pytest
 deps = -r{toxinidir}/../requirements.txt
-setenv =
-    PAPERLESS_CONSUME=/tmp
-    PAPERLESS_PASSPHRASE=THISISNOTASECRET
-    PAPERLESS_SECRET=paperless
 
-[testenv:pep8]
-commands=pep8
-deps=pep8
+[testenv:pycodestyle]
+commands=pycodestyle
+deps=pycodestyle
 
-[pep8]
-exclude=.tox,migrations,paperless/settings.py
+[pycodestyle]
+exclude=
+  .tox,
+  migrations,
+  paperless/settings.py