Ignore .virtualenv

add FORCE_SCRIPT_NAME to host paperless on a subpath url

.gitignore

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

.travis.yml

@@ -8,7 +8,9 @@ matrix:
           env: TOXENV=py34
         - python: 3.5
           env: TOXENV=py35
-        - python: 3.5
+        - python: 3.6
+          env: TOXENV=py36
+        - python: 3.6
           env: TOXENV=pep8
 
 install:

Dockerfile

@@ -35,12 +35,16 @@ RUN groupadd -g 1000 paperless \
     && useradd -u 1000 -g 1000 -d /usr/src/paperless paperless \
     && chown -Rh paperless:paperless /usr/src/paperless
 
+# Set export directory
+ENV PAPERLESS_EXPORT_DIR /export
+RUN mkdir -p $PAPERLESS_EXPORT_DIR
+
 # Setup entrypoint
 COPY scripts/docker-entrypoint.sh /sbin/docker-entrypoint.sh
 RUN chmod 755 /sbin/docker-entrypoint.sh
 
 # Mount volumes
-VOLUME ["/usr/src/paperless/data", "/usr/src/paperless/media", "/consume"]
+VOLUME ["/usr/src/paperless/data", "/usr/src/paperless/media", "/consume", "/export"]
 
 ENTRYPOINT ["/sbin/docker-entrypoint.sh"]
 CMD ["--help"]

README.rst

@@ -6,7 +6,7 @@ Paperless
 |Travis|
 |Dependencies|
 
-Scan, index, and archive all of your paper documents
+Index and archive all of your scanned paper documents
 
 I hate paper.  Environmental issues aside, it's a tech person's nightmare:
 
@@ -23,13 +23,17 @@ it... because paper.  I wrote this to make my life easier.
 How it Works
 ============
 
-1. Buy a document scanner like `this one`_.
+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`_
+   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
    scanner doesn't know how to automatically upload the file somewhere, you can
    always do that manually.  Paperless doesn't care how the documents get into
    its local consumption directory.
-3. Have the target server run the Paperless consumption script to OCR the PDF
+3. Have the target server run the Paperless consumption script to OCR the file
    and index it into a local database.
 4. Use the web frontend to sift through the database and find what you want.
 5. Download the PDF you need/want via the web interface and do whatever you
@@ -47,16 +51,15 @@ Stability
 =========
 
 Paperless is still under active development (just look at the git commit
-history) so don't expect it to be 100% stable.  I'm using it for my own
-documents, but I'm crazy like that.  If you use this and it breaks something,
-you get to keep all the shiny pieces.
+history) so don't expect it to be 100% stable.  You can backup the sqlite3
+database, media directory and your configuration file to be on the safe side.
 
 
 Requirements
 ============
 
-This is all really a quite simple, shiny, user-friendly wrapper around some very
-powerful tools.
+This is all really a quite simple, shiny, user-friendly wrapper around some
+very powerful tools.
 
 * `ImageMagick`_ converts the images between colour and greyscale.
 * `Tesseract`_ does the character recognition.
@@ -82,22 +85,22 @@ Similar Projects
 
 There's another project out there called `Mayan EDMS`_ that has a surprising
 amount of technical overlap with Paperless.  Also based on Django and using
-a consumer model with Tesseract and unpaper, Mayan EDMS is *much* more
-featureful and comes with a slick UI as well.  It may be that Paperless is
-better suited for low-resource environments (like a Rasberry Pi), but to be
-honest, this is just a guess as I haven't tested this myself.  One thing's
-for certain though, *Paperless* is a **much** better name.
+a consumer model with Tesseract and Unpaper, Mayan EDMS is *much* more
+featureful and comes with a slick UI as well, but still in Python 2. It may be
+that Paperless consumes fewer resources, but to be honest, this is just a guess
+as I haven't tested this myself.  One thing's for certain though, *Paperless*
+is a **much** better name.
 
 
 Important Note
 ==============
 
 Document scanners are typically used to scan sensitive documents.  Things like
-your social insurance number, tax records, invoices, etc.  While paperless
-encrypts the original PDFs via the consumption script, the OCR'd text is *not*
+your social insurance number, tax records, invoices, etc.  While Paperless
+encrypts the original files via the consumption script, the OCR'd text is *not*
 encrypted and is therefore stored in the clear (it needs to be searchable, so
 if someone has ideas on how to do that on encrypted data, I'm all ears).  This
-means that paperless should never be run on an untrusted host.  Instead, I
+means that Paperless should never be run on an untrusted host.  Instead, I
 recommend that if you do want to use it, run it locally on a server in your own
 home.
 
@@ -116,6 +119,7 @@ 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/
 .. _ImageMagick: http://imagemagick.org/
 .. _Tesseract: https://github.com/tesseract-ocr
 .. _Unpaper: https://www.flameeyes.eu/projects/unpaper
@@ -136,5 +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

docs/changelog.rst

@@ -1,6 +1,67 @@
 Changelog
 #########
 
+* 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`_.
+  * Modified the Dockerfile to prepare an export directory (`#212`_).  Thanks
+    to combined efforts from `Pit`_ and `Strubbl`_ in working out the kinks on
+    this one.
+  * Updated the import/export scripts to include support for thumbnails.  Big
+    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`_).
+    * 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`_)
+
+* 0.4.1
+  * Fix for `#206`_ wherein the pluggable parser didn't recognise files with
+    all-caps suffixes like ``.PDF``
+
+* 0.4.0
+  * Introducing reminders.  See `#199`_ for more information, but the short
+    explanation is that you can now attach simple notes & times to documents
+    which are made available via the API.  Currently, the default API
+    (basically just the Django admin) doesn't really make use of this, but
+    `Thomas Brueggemann`_ over at `Paperless Desktop`_ has said that he would
+    like to make use of this feature in his project.
+
+* 0.3.6
+  * Fix for `#200`_ (!!) where the API wasn't configured to allow updating the
+    correspondent or the tags for a document.
+  * The ``content`` field is now optional, to allow for the edge case of a
+    purely graphical document.
+  * You can no longer add documents via the admin.  This never worked in the
+    first place, so all I've done here is remove the link to the broken form.
+  * The consumer code has been heavily refactored to support a pluggable
+    interface.  Install a paperless consumer via pip and tell paperless about
+    it with an environment variable, and you're good to go.  Proper
+    documentation is on its way.
+
 * 0.3.5
   * A serious facelift for the documents listing page wherein we drop the
     tabular layout in favour of a tiled interface.
@@ -161,6 +222,15 @@ Changelog
 .. _Tim White: https://github.com/timwhite
 .. _Florian Harr: https://github.com/evils
 .. _Justin Snyman: https://github.com/stringlytyped
+.. _Thomas Brueggemann: https://github.com/thomasbrueggemann
+.. _Jake Gysland: https://github.com/jgysland
+.. _Strubbl: https://github.com/strubbl
+.. _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
 
 .. _#20: https://github.com/danielquinn/paperless/issues/20
 .. _#44: https://github.com/danielquinn/paperless/issues/44
@@ -187,3 +257,17 @@ Changelog
 .. _#171: https://github.com/danielquinn/paperless/issues/171
 .. _#172: https://github.com/danielquinn/paperless/issues/172
 .. _#179: https://github.com/danielquinn/paperless/pull/179
+.. _#199: https://github.com/danielquinn/paperless/issues/199
+.. _#200: https://github.com/danielquinn/paperless/issues/200
+.. _#206: https://github.com/danielquinn/paperless/issues/206
+.. _#212: https://github.com/danielquinn/paperless/pull/212
+.. _#220: https://github.com/danielquinn/paperless/pull/220
+.. _#224: https://github.com/danielquinn/paperless/pull/224
+.. _#226: https://github.com/danielquinn/paperless/pull/226
+.. _#227: https://github.com/danielquinn/paperless/pull/227
+.. _#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

docs/consumption.rst

@@ -121,18 +121,21 @@ So, with all that in mind, here's what you do to get it running:
 
 1. Setup a new email account somewhere, or if you're feeling daring, create a
    folder in an existing email box and note the path to that folder.
-2. In ``settings.py`` set all of the appropriate values in ``MAIL_CONSUMPTION``.
+2. In ``/etc/paperless.conf`` set all of the appropriate values in
+   ``PATHS AND FOLDERS`` and ``SECURITY``.
    If you decided to use a subfolder of an existing account, then make sure you
-   set ``INBOX`` accordingly here.  You also have to set the
-   ``UPLOAD_SHARED_SECRET`` to something you can remember 'cause you'll have to
-   include that in every email you send.
+   set ``PAPERLESS_CONSUME_MAIL_INBOX`` accordingly here.  You also have to set
+   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 every 10 minutes for something new and pull down
-   whatever it finds.
+   the configured email account at startup and from then on every 10 minutes
+   for something new and pulls down whatever it finds.
 4. Send yourself an email!  Note that the subject is treated as the file name,
    so if you set the subject to ``Correspondent - Title - tag,tag,tag``, you'll
    get what you expect.  Also, you must include the aforementioned secret
    string in every email so the fetcher knows that it's safe to import.
+   Note that Paperless only allows the email title to consist of safe characters
+   to be imported. These consist of alpha-numeric characters and ``-_ ,.'``.
 5. After a few minutes, the consumer will poll your mailbox, pull down the
    message, and place the attachment in the consumption directory with the
    appropriate name.  A few minutes later, the consumer will import it like any
@@ -144,46 +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/index.rst

@@ -3,7 +3,11 @@
 Paperless
 =========
 
-Scan, index, and archive all of your paper documents.  Say goodbye to paper.
+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 
+reading after the installation section.
 
 
 .. _index-why-this-exists:
@@ -15,10 +19,11 @@ 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 wanted to be able to feed
-documents right from the post box into the scanner and then shred them so I
-never have to worry about finding stuff again.  Perhaps you might find it useful
-too.
+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.
+
+
 
 
 Contents

docs/requirements.rst

@@ -4,7 +4,7 @@ Requirements
 ============
 
 You need a Linux machine or Unix-like setup (theoretically an Apple machine
-should work) that has the following software installed on it:
+should work) that has the following software installed:
 
 * `Python3`_ (with development libraries, pip and virtualenv)
 * `GNU Privacy Guard`_
@@ -21,14 +21,14 @@ should work) that has the following software installed on it:
 Notably, you should confirm how you access your Python3 installation.  Many
 Linux distributions will install Python3 in parallel to Python2, using the names
 ``python3`` and ``python`` respectively.  The same goes for ``pip3`` and
-``pip``.  Using Python2 will likely break things, so make sure that you're using
-the right version.
+``pip``.  Running Paperless with Python2 will likely break things, so make sure that 
+you're using the right version.
 
 For the purposes of simplicity, ``python`` and ``pip`` is used everywhere to
-refer to their Python 3 versions.
+refer to their Python3 versions.
 
 In addition to the above, there are a number of Python requirements, all of
-which are listed in a file called ``requirements.txt`` in the project root.
+which are listed in a file called ``requirements.txt`` in the project root directory.
 
 If you're not working on a virtual environment (like Vagrant or Docker), you
 should probably be using a virtualenv, but that's your call.  The reasons why
@@ -67,7 +67,7 @@ dependencies is easy:
 
     $ pip install --user --requirement /path/to/paperless/requirements.txt
 
-This should download and install all of the requirements into
+This will download and install all of the requirements into
 ``${HOME}/.local``.  Remember that your distribution may be using ``pip3`` as
 mentioned above.
 
@@ -86,8 +86,8 @@ enter it, and install the requirements using the ``requirements.txt`` file:
     $ . /path/to/arbitrary/directory/bin/activate
     $ pip install  --requirement /path/to/paperless/requirements.txt
 
-Now you're ready to go.  Just remember to enter your virtualenv whenever you
-want to use Paperless.
+Now you're ready to go.  Just remember to enter (activate) your virtualenv 
+whenever you want to use Paperless.
 
 
 .. _requirements-documentation:
@@ -95,7 +95,7 @@ want to use Paperless.
 Documentation
 -------------
 
-As generation of the documentation is not required for use of Paperless,
+As generation of the documentation is not required for the use of Paperless,
 dependencies for this process are not included in ``requirements.txt``.  If
 you'd like to generate your own docs locally, you'll need to:
 

docs/setup.rst

@@ -4,7 +4,7 @@ Setup
 =====
 
 Paperless isn't a very complicated app, but there are a few components, so some
-basic documentation is in order.  If you go follow along in this document and
+basic documentation is in order.  If you follow along in this document and
 still have trouble, please open an `issue on GitHub`_ so I can fill in the
 gaps.
 
@@ -28,6 +28,7 @@ or just download the tarball and go that route:
 
 .. code:: bash
 
+    $ cd to the directory where you want to run Paperless
     $ wget https://github.com/danielquinn/paperless/archive/master.zip
     $ unzip master.zip
     $ cd paperless-master
@@ -43,7 +44,9 @@ route`_ is quick & easy, but means you're running a VM which comes with memory
 consumption etc. We also `support Docker`_, which you can use natively under
 Linux and in a VM with `Docker Machine`_ (this guide was written for native
 Docker usage under Linux, you might have to adapt it for Docker Machine.)
-Alternatively the standard, `bare metal`_ approach is a little more
+Not to forget the virtualenv, this is similar to `bare metal`_ with the
+exception that you have to activate the virtualenv first.
+Last but not least, the standard `bare metal`_ approach is a little more
 complicated, but worth it because it makes it easier should you want to
 contribute some code back.
 
@@ -59,9 +62,11 @@ Standard (Bare Metal)
 .....................
 
 1. Install the requirements as per the :ref:`requirements <requirements>` page.
-2. Change to the ``src`` directory in this repo.
-3. Copy ``paperless.conf.example`` to ``/etc/paperless.conf`` and open it in
-   your favourite editor.  Set the values for:
+2. Within the extract of master.zip go to the ``src`` directory.
+3. Copy ``paperless.conf.example`` to ``/etc/paperless.conf`` also the virtual
+   envrionment look there for it and open it in your favourite editor.
+   Because this file contains passwords it should only be readable by user root
+   and paperless !  Set the values for:
 
     * ``PAPERLESS_CONSUMPTION_DIR``: this is where your documents will be
       dumped to be consumed by Paperless.
@@ -70,18 +75,19 @@ Standard (Bare Metal)
     * ``PAPERLESS_OCR_THREADS``: this is the number of threads the OCR process
       will spawn to process document pages in parallel.
 
-4. Initialise the database with ``./manage.py migrate``.
+4. Initialise the SQLite database with ``./manage.py migrate``.
 5. Create a user for your Paperless instance with
    ``./manage.py createsuperuser``. Follow the prompts to create your user.
 6. Start the webserver with ``./manage.py runserver <IP>:<PORT>``.
-   If no specifc IP or port are given, the default is ``127.0.0.1:8000``.
-   You should now be able to visit your (empty) `Paperless webserver`_ at
-   ``127.0.0.1:8000`` (or whatever you chose).  You can login with the
-   user/pass you created in #5.
+   If no specifc IP or port are given, the default is ``127.0.0.1:8000``
+   also known as http://localhost:8000/.
+   You should now be able to visit your (empty) at `Paperless webserver`_ or
+   whatever you chose before.  You can login with the user/pass you created in
+   #5.
 7. In a separate window, change to the ``src`` directory in this repo again,
    but this time, you should start the consumer script with
    ``./manage.py document_consumer``.
-8. Scan something.  Put it in the ``CONSUMPTION_DIR``.
+8. Scan something or put a file into the  ``CONSUMPTION_DIR``.
 9. Wait a few minutes
 10. Visit the document list on your webserver, and it should be there, indexed
     and downloadable.
@@ -299,17 +305,21 @@ Standard (Bare Metal, Systemd)
 
 If you're running on a bare metal system that's using Systemd, you can use the
 service unit files in the ``scripts`` directory to set this up.  You'll need to
-create a user called ``paperless`` and setup Paperless to be in a place that
-this new user can read and write to. Be sure to edit the service scripts to point
-to the proper location of your paperless install, referencing the appropriate Python
-binary. For example: ``ExecStart=/path/to/python3 /path/to/paperless/src/manage.py document_consumer``.
-If you don't want to make a new user, you can change the ``Group`` and ``User`` variables
-accordingly.
+create a user called ``paperless`` (without login (if not already done so #5))
+and setup Paperless to be in a place that this new user can read and write to.
+Be sure to edit the service  scripts to point to the proper location of your
+paperless install, referencing the appropriate Python binary. For example:
+``ExecStart=/path/to/python3 /path/to/paperless/src/manage.py document_consumer``.
+If you don't want to make a new user, you can change the ``Group`` and ``User``
+variables accordingly.
 
-Then, you can just tell Systemd as ``root`` (or using ``sudo``) to enable the two ``.service`` files::
+Then, as ``root`` (or using ``sudo``) you can just copy the ``.service`` files
+to the Systemd directory and tell it to enable the two services::
 
-    # systemctl enable /path/to/paperless/scripts/paperless-consumer.service
-    # systemctl enable /path/to/paperless/scripts/paperless-webserver.service
+    # cp /path/to/paperless/scripts/paperless-consumer.service /etc/systemd/system/
+    # cp /path/to/paperless/scripts/paperless-webserver.service /etc/systemd/system/
+    # systemctl enable paperless-consumer
+    # systemctl enable paperless-webserver
     # systemctl start paperless-consumer
     # systemctl start paperless-webserver
 
@@ -344,7 +354,7 @@ after restarting your system:
   If you are using a network interface other than ``eth0``, you will have to
   change ``IFACE=eth0``. For example, if you are connected via WiFi, you will
   likely need to replace ``eth0`` above with ``wlan0``. To see all interfaces,
-  run ``ifconfig``.
+  run ``ifconfig -a``.
 
   Save the file.
 
@@ -384,7 +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
 ~~~~~~
@@ -562,3 +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

@@ -1,11 +1,34 @@
 # Sample paperless.conf
 # Copy this file to /etc/paperless.conf and modify it to suit your needs.
+# As this file contains passwords it should only be readable by the user
+# running paperless.
+
+
+###############################################################################
+####                         Paths & Folders                               ####
+###############################################################################
 
 # This where your documents should go to be consumed.  Make sure that it exists
 # and that the user running the paperless service can read/write its contents
 # before you start Paperless.
 PAPERLESS_CONSUMPTION_DIR=""
 
+
+# You can specify where you want the SQLite database to be stored instead of
+# the default location of /data/ within the install directory.
+#PAPERLESS_DBDIR=/path/to/database/file
+
+
+# Override the default MEDIA_ROOT here.  This is where all files are stored.
+# The default location is /media/documents/ within the install folder.
+#PAPERLESS_MEDIADIR=/path/to/media
+
+
+# Override the default STATIC_ROOT here.  This is where all static files
+# created using "collectstatic" manager command are stored.
+#PAPERLESS_STATICDIR=""
+
+
 # These values are required if you want paperless to check a particular email
 # box every 10 minutes and attempt to consume documents from there.  If you
 # don't define a HOST, mail checking will just be disabled.
@@ -14,6 +37,19 @@ PAPERLESS_CONSUME_MAIL_PORT=""
 PAPERLESS_CONSUME_MAIL_USER=""
 PAPERLESS_CONSUME_MAIL_PASS=""
 
+# Override the default IMAP inbox here. If not set Paperless defaults to
+# "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=""
+
+
+###############################################################################
+####                              Security                                 ####
+###############################################################################
+
 # You must have a passphrase in order for Paperless to work at all.  If you set
 # this to "", GNUGPG will "encrypt" your PDF by writing it out as a zero-byte
 # file.
@@ -28,75 +64,13 @@ PAPERLESS_CONSUME_MAIL_PASS=""
 # you've since changed it to a new one.
 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=""
 
-# After a document is consumed, Paperless can trigger an arbitrary script if
-# you like.  This script will be passed a number of arguments for you to work
-# with.  The default is blank, which means nothing will be executed.  For more
-# information, take a look at the docs: http://paperless.readthedocs.org/en/latest/consumption.html#hooking-into-the-consumption-process
-#PAPERLESS_POST_CONSUME_SCRIPT="/path/to/an/arbitrary/script.sh"
+# 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.
+#PAPERLESS_SECRET_KEY="change-me"
 
 
-#
-# The following values use sensible defaults for modern systems, but if you're
-# running Paperless on a low-resource machine (like a Raspberry Pi), modifying
-# some of these values may be necessary.
-#
-
-
-# By default, Paperless will attempt to use all available CPU cores to process
-# a document, but if you would like to limit that, you can set this value to
-# an integer:
-#PAPERLESS_OCR_THREADS=1
-
-# On smaller systems, or even in the case of Very Large Documents, the consumer
-# may explode, complaining about how it's "unable to extent pixel cache".  In
-# such cases, try setting this to a reasonably low value, like 32000000.  The
-# default is to use whatever is necessary to do everything without writing to
-# disk, and units are in megabytes.
-#
-# For more information on how to use this value, you should probably search
-# the web for "MAGICK_MEMORY_LIMIT".
-#PAPERLESS_CONVERT_MEMORY_LIMIT=0
-
-# By default the conversion density setting for documents is 300DPI, in some
-# cases it has proven useful to configure a lesser value.
-# This setting has a high impact on the physical size of tmp page files,
-# the speed of document conversion, and can affect the accuracy of OCR
-# results. Individual results can vary and this setting should be tested
-# thoroughly against the documents you are importing to see if it has any
-# impacts either negative or positive. Testing on limited document sets has
-# shown a setting of 200 can cut the size of tmp files by 1/3, and speed up
-# conversion by up to 4x with little impact to OCR accuracy.
-#PAPERLESS_CONVERT_DENSITY=300
-
-# Similar to the memory limit, if you've got a small system and your OS mounts
-# /tmp as tmpfs, you should set this to a path that's on a physical disk, like
-# /home/your_user/tmp or something.  ImageMagick will use this as scratch space
-# when crunching through very large documents.
-#
-# For more information on how to use this value, you should probably search
-# the web for "MAGICK_TMPDIR".
-#PAPERLESS_CONVERT_TMPDIR=/var/tmp/paperless
-
-# You can specify where you want the SQLite database to be stored instead of
-# the default location
-#PAPERLESS_DBDIR=/path/to/database/file
-
-# Override the default MEDIA_ROOT here.  This is where all files are stored.
-#PAPERLESS_MEDIADIR=/path/to/media
-
-# Override the default STATIC_ROOT here. This is where all static files created
-# using "collectstatic" manager command are stored.
-#PAPERLESS_STATICDIR=""
-
-# The number of seconds that Paperless will wait between checking
-# PAPERLESS_CONSUMPTION_DIR.  If you tend to write documents to this directory
-# very slowly, you may want to use a higher value than the default (10).
-# PAPERLESS_CONSUMER_LOOP_TIME=10
-
 # If you're planning on putting Paperless on the open internet, then you
 # really should set this value to the domain name you're using.  Failing to do
 # so leaves you open to HTTP host header attacks:
@@ -106,22 +80,94 @@ 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"
 
-# Override the default UTC time zone here
+# 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                              ####
+###############################################################################
+
+# After a document is consumed, Paperless can trigger an arbitrary script if
+# you like.  This script will be passed a number of arguments for you to work
+# with.  The default is blank, which means nothing will be executed.  For more
+# information, take a look at the docs:
+# http://paperless.readthedocs.org/en/latest/consumption.html#hooking-into-the-consumption-process
+#PAPERLESS_POST_CONSUME_SCRIPT="/path/to/an/arbitrary/script.sh"
+
+
+#
+# The following values use sensible defaults for modern systems, but if you're
+# running Paperless on a low-resource device (like a Raspberry Pi), modifying
+# some of these values may be necessary.
+#
+
+
+# By default, Paperless will attempt to use all available CPU cores to process
+# a document, but if you would like to limit that, you can set this value to
+# an integer:
+#PAPERLESS_OCR_THREADS=1
+
+
+# Customize the default language that tesseract will attempt to use when
+# parsing documents.  It should be a 3-letter language code consistent with ISO
+# 639: https://www.loc.gov/standards/iso639-2/php/code_list.php
+#PAPERLESS_OCR_LANGUAGE=eng
+
+
+# On smaller systems, or even in the case of Very Large Documents, the consumer
+# may explode, complaining about how it's "unable to extend pixel cache".  In
+# such cases, try setting this to a reasonably low value, like 32000000.  The
+# default is to use whatever is necessary to do everything without writing to
+# disk, and units are in megabytes.
+#
+# For more information on how to use this value, you should probably search
+# the web for "MAGICK_MEMORY_LIMIT".
+#PAPERLESS_CONVERT_MEMORY_LIMIT=0
+
+
+# Similar to the memory limit, if you've got a small system and your OS mounts
+# /tmp as tmpfs, you should set this to a path that's on a physical disk, like
+# /home/your_user/tmp or something.  ImageMagick will use this as scratch space
+# when crunching through very large documents.
+#
+# For more information on how to use this value, you should probably search
+# the web for "MAGICK_TMPDIR".
+#PAPERLESS_CONVERT_TMPDIR=/var/tmp/paperless
+
+
+# By default the conversion density setting for documents is 300DPI, in some
+# cases it has proven useful to configure a lesser value.
+# This setting has a high impact on the physical size of tmp page files,
+# the speed of document conversion, and can affect the accuracy of OCR
+# results. Individual results can vary and this setting should be tested
+# thoroughly against the documents you are importing to see if it has any
+# impacts either negative or positive.
+# Testing on limited document sets has shown a setting of 200 can cut the
+# size of tmp files by 1/3, and speed up conversion by up to 4x
+# with little impact to OCR accuracy.
+#PAPERLESS_CONVERT_DENSITY=300
+
+
+# The number of seconds that Paperless will wait between checking
+# PAPERLESS_CONSUMPTION_DIR.  If you tend to write documents to this directory
+# rarely, you may want to use a higher value than the default (10).
+#PAPERLESS_CONSUMER_LOOP_TIME=10
+
+
+###############################################################################
+####                            Interface                                  ####
+###############################################################################
+
+# 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
 
-# Customize number of list items to show per page
-#PAPERLESS_LIST_PER_PAGE=50
-
-# Customize the default language that tesseract will attempt to use when parsing
-# documents.  It should be a 3-letter language code consistent with ISO 639.
-#PAPERLESS_OCR_LANGUAGE=eng
 
 # The number of items on each page in the web UI.  This value must be a
 # positive integer, but if you don't define one in paperless.conf, a default of
 # 100 will be used.
 #PAPERLESS_LIST_PER_PAGE=100
-
-# 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.
-#PAPERLESS_SECRET_KEY="change-me"

requirements.txt

@@ -1,4 +1,4 @@
-Django==1.10.5
+Django>=1.10,<1.11
 Pillow>=3.1.1
 django-crispy-forms>=1.6.1
 django-extensions>=1.7.6
@@ -6,18 +6,21 @@ django-filter>=1.0
 django-flat-responsive>=1.2.0
 djangorestframework>=3.5.3
 filemagic>=1.6
+fuzzywuzzy[speedup]==0.15.0
 langdetect>=1.0.7
-pyocr>=0.4.6
+pyocr>=0.4.7
 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
+pytest-env
 pep8
 flake8
 tox

scripts/docker-entrypoint.sh

@@ -7,34 +7,37 @@ 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
 }
 
 set_permissions() {
-    # Set permissions for consumption directory
-    chgrp paperless "$PAPERLESS_CONSUMPTION_DIR" || {
-        echo "Changing group of consumption directory:"
-        echo "  $PAPERLESS_CONSUMPTION_DIR"
-        echo "failed."
-        echo ""
-        echo "Either try to set it on your host-mounted directory"
-        echo "directly, or make sure that the directory has \`o+x\`"
-        echo "permissions and the files in it at least \`o+r\`."
-    } >&2
-    chmod g+x "$PAPERLESS_CONSUMPTION_DIR" || {
-        echo "Changing group permissions of consumption directory:"
-        echo "  $PAPERLESS_CONSUMPTION_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 "permissions and the files in it at least \`o+r\`."
-    } >&2
-
+    # Set permissions for consumption and export directory
+    for dir in PAPERLESS_CONSUMPTION_DIR PAPERLESS_EXPORT_DIR; do
+      # Extract the name of the current directory from $dir for the error message
+      cur_dir_name=$(echo "$dir" | awk -F'_' '{ print tolower($2); }')
+      chgrp paperless "${!dir}" || {
+          echo "Changing group of ${cur_dir_name} directory:"
+          echo "  ${!dir}"
+          echo "failed."
+          echo ""
+          echo "Either try to set it on your host-mounted directory"
+          echo "directly, or make sure that the directory has \`o+x\`"
+          echo "permissions and the files in it at least \`o+r\`."
+      } >&2
+      chmod g+x "${!dir}" || {
+          echo "Changing group permissions of ${cur_dir_name} directory:"
+          echo "  ${!dir}"
+          echo "failed."
+          echo ""
+          echo "Either try to set it on your host-mounted directory"
+          echo "directly, or make sure that the directory has \`o+x\`"
+          echo "permissions and the files in it at least \`o+r\`."
+      } >&2
+    done
     # Set permissions for application directory
     chown -Rh paperless:paperless /usr/src/paperless
 }
@@ -59,11 +62,11 @@ install_languages() {
     # Loop over languages to be installed
     for lang in "${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

@@ -62,15 +62,24 @@ class DocumentAdmin(CommonAdmin):
     list_filter = ("tags", "correspondent", MonthListFilter)
     ordering = ["-created", "correspondent"]
 
+    def has_add_permission(self, request):
+        return False
+
     def created_(self, obj):
         return obj.created.date().strftime("%Y-%m-%d")
+    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",
+            alt="Thumbnail of {}".format(obj.file_name),
             title=obj.file_name
         )
         return self._html_tag("a", png_img, href=obj.download_url)

src/documents/consumer.py

@@ -1,35 +1,21 @@
+import datetime
+import hashlib
+import logging
 import os
 import re
 import uuid
-import shutil
-import hashlib
-import logging
-import datetime
-import tempfile
-import itertools
-import subprocess
-from multiprocessing.pool import Pool
 
-import pyocr
-import langdetect
-from PIL import Image
 from django.conf import settings
 from django.utils import timezone
 from paperless.db import GnuPG
-from pyocr.tesseract import TesseractError
-from pyocr.libtesseract.tesseract_raw import \
-    TesseractError as OtherTesseractError
 
-from .models import Tag, Document, FileInfo
+from .models import Document, FileInfo, Tag
+from .parsers import ParseError
 from .signals import (
-    document_consumption_started,
-    document_consumption_finished
+    document_consumer_declaration,
+    document_consumption_finished,
+    document_consumption_started
 )
-from .languages import ISO639
-
-
-class OCRError(Exception):
-    pass
 
 
 class ConsumerError(Exception):
@@ -47,13 +33,7 @@ class Consumer(object):
     """
 
     SCRATCH = settings.SCRATCH_DIR
-    CONVERT = settings.CONVERT_BINARY
-    UNPAPER = settings.UNPAPER_BINARY
     CONSUME = settings.CONSUMPTION_DIR
-    THREADS = int(settings.OCR_THREADS) if settings.OCR_THREADS else None
-    DENSITY = settings.CONVERT_DENSITY if settings.CONVERT_DENSITY else 300
-
-    DEFAULT_OCR_LANGUAGE = settings.OCR_LANGUAGE
 
     def __init__(self):
 
@@ -78,6 +58,16 @@ class Consumer(object):
             raise ConsumerError(
                 "Consumption directory {} does not exist".format(self.CONSUME))
 
+        self.parsers = []
+        for response in document_consumer_declaration.send(self):
+            self.parsers.append(response[1])
+
+        if not self.parsers:
+            raise ConsumerError(
+                "No parsers could be found, not even the default.  "
+                "This is a problem."
+            )
+
     def log(self, level, message):
         getattr(self.logger, level)(message, extra={
             "group": self.logging_group
@@ -109,6 +99,13 @@ class Consumer(object):
                 self._ignore.append(doc)
                 continue
 
+            parser_class = self._get_parser_class(doc)
+            if not parser_class:
+                self.log(
+                    "error", "No parsers could be found for {}".format(doc))
+                self._ignore.append(doc)
+                continue
+
             self.logging_group = uuid.uuid4()
 
             self.log("info", "Consuming {}".format(doc))
@@ -119,25 +116,26 @@ class Consumer(object):
                 logging_group=self.logging_group
             )
 
-            tempdir = tempfile.mkdtemp(prefix="paperless", dir=self.SCRATCH)
-            imgs = self._get_greyscale(tempdir, doc)
-            thumbnail = self._get_thumbnail(tempdir, doc)
+            parsed_document = parser_class(doc)
+            thumbnail = parsed_document.get_thumbnail()
 
             try:
-
-                document = self._store(self._get_ocr(imgs), doc, thumbnail)
-
-            except OCRError as e:
+                document = self._store(
+                    parsed_document.get_text(),
+                    doc,
+                    thumbnail
+                )
+            except ParseError as e:
 
                 self._ignore.append(doc)
-                self.log("error", "OCR FAILURE for {}: {}".format(doc, e))
-                self._cleanup_tempdir(tempdir)
+                self.log("error", "PARSE FAILURE for {}: {}".format(doc, e))
+                parsed_document.cleanup()
 
                 continue
 
             else:
 
-                self._cleanup_tempdir(tempdir)
+                parsed_document.cleanup()
                 self._cleanup_doc(doc)
 
                 self.log(
@@ -151,142 +149,30 @@ class Consumer(object):
                     logging_group=self.logging_group
                 )
 
-    def _get_greyscale(self, tempdir, doc):
+    def _get_parser_class(self, doc):
         """
-        Greyscale images are easier for Tesseract to OCR
+        Determine the appropriate parser class based on the file
         """
 
-        self.log("info", "Generating greyscale image from {}".format(doc))
+        options = []
+        for parser in self.parsers:
+            result = parser(doc)
+            if result:
+                options.append(result)
 
-        # Convert PDF to multiple PNMs
-        pnm = os.path.join(tempdir, "convert-%04d.pnm")
-        run_convert(
-            self.CONVERT,
-            "-density", str(self.DENSITY),
-            "-depth", "8",
-            "-type", "grayscale",
-            doc, pnm,
-        )
-
-        # Get a list of converted images
-        pnms = []
-        for f in os.listdir(tempdir):
-            if f.endswith(".pnm"):
-                pnms.append(os.path.join(tempdir, f))
-
-        # Run unpaper in parallel on converted images
-        with Pool(processes=self.THREADS) as pool:
-            pool.map(run_unpaper, itertools.product([self.UNPAPER], pnms))
-
-        # Return list of converted images, processed with unpaper
-        pnms = []
-        for f in os.listdir(tempdir):
-            if f.endswith(".unpaper.pnm"):
-                pnms.append(os.path.join(tempdir, f))
-
-        return sorted(filter(lambda __: os.path.isfile(__), pnms))
-
-    def _get_thumbnail(self, tempdir, doc):
-        """
-        The thumbnail of a PDF is just a 500px wide image of the first page.
-        """
-
-        self.log("info", "Generating the thumbnail")
-
-        run_convert(
-            self.CONVERT,
-            "-scale", "500x5000",
-            "-alpha", "remove",
-            doc, os.path.join(tempdir, "convert-%04d.png")
-        )
-
-        return os.path.join(tempdir, "convert-0000.png")
-
-    def _guess_language(self, text):
-        try:
-            guess = langdetect.detect(text)
-            self.log("debug", "Language detected: {}".format(guess))
-            return guess
-        except Exception as e:
-            self.log("warning", "Language detection error: {}".format(e))
-
-    def _get_ocr(self, imgs):
-        """
-        Attempts to do the best job possible OCR'ing the document based on
-        simple language detection trial & error.
-        """
-
-        if not imgs:
-            raise OCRError("No images found")
-
-        self.log("info", "OCRing the document")
-
-        # Since the division gets rounded down by int, this calculation works
-        # for every edge-case, i.e. 1
-        middle = int(len(imgs) / 2)
-        raw_text = self._ocr([imgs[middle]], self.DEFAULT_OCR_LANGUAGE)
-
-        guessed_language = self._guess_language(raw_text)
-
-        if not guessed_language or guessed_language not in ISO639:
-            self.log("warning", "Language detection failed!")
-            if settings.FORGIVING_OCR:
-                self.log(
-                    "warning",
-                    "As FORGIVING_OCR is enabled, we're going to make the "
-                    "best with what we have."
-                )
-                raw_text = self._assemble_ocr_sections(imgs, middle, raw_text)
-                return raw_text
-            raise OCRError("Language detection failed")
-
-        if ISO639[guessed_language] == self.DEFAULT_OCR_LANGUAGE:
-            raw_text = self._assemble_ocr_sections(imgs, middle, raw_text)
-            return raw_text
-
-        try:
-            return self._ocr(imgs, ISO639[guessed_language])
-        except pyocr.pyocr.tesseract.TesseractError:
-            if settings.FORGIVING_OCR:
-                self.log(
-                    "warning",
-                    "OCR for {} failed, but we're going to stick with what "
-                    "we've got since FORGIVING_OCR is enabled.".format(
-                        guessed_language
-                    )
-                )
-                raw_text = self._assemble_ocr_sections(imgs, middle, raw_text)
-                return raw_text
-            raise OCRError(
-                "The guessed language is not available in this instance of "
-                "Tesseract."
+        self.log(
+            "info",
+            "Parsers available: {}".format(
+                ", ".join([str(o["parser"].__name__) for o in options])
             )
+        )
 
-    def _assemble_ocr_sections(self, imgs, middle, text):
-        """
-        Given a `middle` value and the text that middle page represents, we OCR
-        the remainder of the document and return the whole thing.
-        """
-        text = self._ocr(imgs[:middle], self.DEFAULT_OCR_LANGUAGE) + text
-        text += self._ocr(imgs[middle + 1:], self.DEFAULT_OCR_LANGUAGE)
-        return text
+        if not options:
+            return None
 
-    def _ocr(self, imgs, lang):
-        """
-        Performs a single OCR attempt.
-        """
-
-        if not imgs:
-            return ""
-
-        self.log("info", "Parsing for {}".format(lang))
-
-        with Pool(processes=self.THREADS) as pool:
-            r = pool.map(image_to_string, itertools.product(imgs, [lang]))
-            r = " ".join(r)
-
-        # Strip out excess white space to allow matching to go smoother
-        return strip_excess_whitespace(r)
+        # Return the parser with the highest weight.
+        return sorted(
+            options, key=lambda _: _["weight"], reverse=True)[0]["parser"]
 
     def _store(self, text, doc, thumbnail):
 
@@ -332,10 +218,6 @@ class Consumer(object):
 
         return document
 
-    def _cleanup_tempdir(self, d):
-        self.log("debug", "Deleting directory {}".format(d))
-        shutil.rmtree(d)
-
     def _cleanup_doc(self, doc):
         self.log("debug", "Deleting document {}".format(doc))
         os.unlink(doc)
@@ -361,41 +243,3 @@ class Consumer(object):
         with open(doc, "rb") as f:
             checksum = hashlib.md5(f.read()).hexdigest()
         return Document.objects.filter(checksum=checksum).exists()
-
-
-def strip_excess_whitespace(text):
-    collapsed_spaces = re.sub(r"([^\S\r\n]+)", " ", text)
-    no_leading_whitespace = re.sub(
-        "([\n\r]+)([^\S\n\r]+)", '\\1', collapsed_spaces)
-    no_trailing_whitespace = re.sub("([^\S\n\r]+)$", '', no_leading_whitespace)
-    return no_trailing_whitespace
-
-
-def image_to_string(args):
-    img, lang = args
-    ocr = pyocr.get_available_tools()[0]
-    with Image.open(os.path.join(Consumer.SCRATCH, img)) as f:
-        if ocr.can_detect_orientation():
-            try:
-                orientation = ocr.detect_orientation(f, lang=lang)
-                f = f.rotate(orientation["angle"], expand=1)
-            except (TesseractError, OtherTesseractError):
-                pass
-        return ocr.image_to_string(f, lang=lang)
-
-
-def run_unpaper(args):
-    unpaper, pnm = args
-    subprocess.Popen(
-        (unpaper, pnm, pnm.replace(".pnm", ".unpaper.pnm"))).wait()
-
-
-def run_convert(*args):
-
-    environment = os.environ.copy()
-    if settings.CONVERT_MEMORY_LIMIT:
-        environment["MAGICK_MEMORY_LIMIT"] = settings.CONVERT_MEMORY_LIMIT
-    if settings.CONVERT_TMPDIR:
-        environment["MAGICK_TMPDIR"] = settings.CONVERT_TMPDIR
-
-    subprocess.Popen(args, env=environment).wait()

src/documents/filters.py

@@ -8,7 +8,7 @@ class CorrespondentFilterSet(FilterSet):
     class Meta(object):
         model = Correspondent
         fields = {
-            'name': [
+            "name": [
                 "startswith", "endswith", "contains",
                 "istartswith", "iendswith", "icontains"
             ],
@@ -21,7 +21,7 @@ class TagFilterSet(FilterSet):
     class Meta(object):
         model = Tag
         fields = {
-            'name': [
+            "name": [
                 "startswith", "endswith", "contains",
                 "istartswith", "iendswith", "icontains"
             ],

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.clened_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
@@ -100,11 +86,11 @@ class UploadForm(forms.Form):
         form do that as well.  Think of it as a poor-man's queue server.
         """
 
-        correspondent = self.clened_data.get("correspondent")
+        correspondent = self.cleaned_data.get("correspondent")
         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)
 
@@ -219,7 +222,7 @@ class MailFetcher(Loggable):
         if not login[0] == "OK":
             raise MailFetcherError("Can't log into mail: {}".format(login[1]))
 
-        inbox = self._connection.select("INBOX")
+        inbox = self._connection.select(self._inbox)
         if not inbox[0] == "OK":
             raise MailFetcherError("Can't find the inbox: {}".format(inbox[1]))
 

src/documents/management/commands/document_consumer.py

@@ -28,6 +28,7 @@ class Command(BaseCommand):
 
         self.file_consumer = None
         self.mail_fetcher = None
+        self.first_iteration = True
 
         BaseCommand.__init__(self, *args, **kwargs)
 
@@ -66,6 +67,9 @@ class Command(BaseCommand):
         self.file_consumer.consume()
 
         # Occasionally fetch mail and store it to be consumed on the next loop
+        # We fetch email when we first start up so that it is not necessary to
+        # wait for 10 minutes after making changes to the config file.
         delta = self.mail_fetcher.last_checked + self.MAIL_DELTA
-        if delta < datetime.datetime.now():
+        if self.first_iteration or delta < datetime.datetime.now():
+            self.first_iteration = False
             self.mail_fetcher.pull()

src/documents/management/commands/document_exporter.py

@@ -10,6 +10,7 @@ from documents.models import Document, Correspondent, Tag
 from paperless.db import GnuPG
 
 from ...mixins import Renderable
+from documents.settings import EXPORTER_FILE_NAME, EXPORTER_THUMBNAIL_NAME
 
 
 class Command(Renderable, BaseCommand):
@@ -61,15 +62,24 @@ class Command(Renderable, BaseCommand):
 
             document = document_map[document_dict["pk"]]
 
-            target = os.path.join(self.target, document.file_name)
-            document_dict["__exported_file_name__"] = target
+            file_target = os.path.join(self.target, document.file_name)
 
-            print("Exporting: {}".format(target))
+            thumbnail_name = document.file_name + "-tumbnail.png"
+            thumbnail_target = os.path.join(self.target, thumbnail_name)
 
-            with open(target, "wb") as f:
+            document_dict[EXPORTER_FILE_NAME] = document.file_name
+            document_dict[EXPORTER_THUMBNAIL_NAME] = thumbnail_name
+
+            print("Exporting: {}".format(file_target))
+
+            t = int(time.mktime(document.created.timetuple()))
+            with open(file_target, "wb") as f:
                 f.write(GnuPG.decrypted(document.source_file))
-                t = int(time.mktime(document.created.timetuple()))
-                os.utime(target, times=(t, t))
+                os.utime(file_target, times=(t, t))
+
+            with open(thumbnail_target, "wb") as f:
+                f.write(GnuPG.decrypted(document.thumbnail_file))
+                os.utime(thumbnail_target, times=(t, t))
 
         manifest += json.loads(
             serializers.serialize("json", Correspondent.objects.all()))

src/documents/management/commands/document_importer.py

@@ -10,6 +10,8 @@ from paperless.db import GnuPG
 
 from ...mixins import Renderable
 
+from documents.settings import EXPORTER_FILE_NAME, EXPORTER_THUMBNAIL_NAME
+
 
 class Command(Renderable, BaseCommand):
 
@@ -70,13 +72,13 @@ class Command(Renderable, BaseCommand):
             if not record["model"] == "documents.document":
                 continue
 
-            if "__exported_file_name__" not in record:
+            if EXPORTER_FILE_NAME not in record:
                 raise CommandError(
                     'The manifest file contains a record which does not '
                     'refer to an actual document file.'
                 )
 
-            doc_file = record["__exported_file_name__"]
+            doc_file = record[EXPORTER_FILE_NAME]
             if not os.path.exists(os.path.join(self.source, doc_file)):
                 raise CommandError(
                     'The manifest file refers to "{}" which does not '
@@ -90,10 +92,21 @@ class Command(Renderable, BaseCommand):
             if not record["model"] == "documents.document":
                 continue
 
-            doc_file = record["__exported_file_name__"]
+            doc_file = record[EXPORTER_FILE_NAME]
+            thumb_file = record[EXPORTER_THUMBNAIL_NAME]
             document = Document.objects.get(pk=record["pk"])
-            with open(doc_file, "rb") as unencrypted:
+
+            document_path = os.path.join(self.source, doc_file)
+            thumbnail_path = os.path.join(self.source, thumb_file)
+
+            with open(document_path, "rb") as unencrypted:
                 with open(document.source_path, "wb") as encrypted:
                     print("Encrypting {} and saving it to {}".format(
                         doc_file, document.source_path))
                     encrypted.write(GnuPG.encrypted(unencrypted))
+
+            with open(thumbnail_path, "rb") as unencrypted:
+                with open(document.thumbnail_path, "wb") as encrypted:
+                    print("Encrypting {} and saving it to {}".format(
+                        thumb_file, document.thumbnail_path))
+                    encrypted.write(GnuPG.encrypted(unencrypted))

src/documents/managers.py

@@ -50,7 +50,7 @@ class GroupConcat(models.Aggregate):
 
     def _get_template(self, separator):
         if self.engine == self.ENGINE_MYSQL:
-            return "%(function)s(%(expressions)s, SEPARATOR '{}')".format(
+            return "%(function)s(%(expressions)s SEPARATOR '{}')".format(
                 separator)
         return "%(function)s(%(expressions)s, '{}')".format(separator)
 

src/documents/migrations/0001_initial.py

@@ -3,6 +3,7 @@
 from __future__ import unicode_literals
 
 from django.db import migrations, models
+from django.conf import settings
 
 
 class Migration(migrations.Migration):
@@ -19,7 +20,7 @@ class Migration(migrations.Migration):
                 ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
                 ('sender', models.CharField(blank=True, db_index=True, max_length=128)),
                 ('title', models.CharField(blank=True, db_index=True, max_length=128)),
-                ('content', models.TextField(db_index=True)),
+                ('content', models.TextField(db_index=("mysql" not in settings.DATABASES["default"]["ENGINE"]))),
                 ('created', models.DateTimeField(auto_now_add=True)),
                 ('modified', models.DateTimeField(auto_now=True)),
             ],

src/documents/migrations/0003_sender.py

@@ -47,7 +47,11 @@ class Migration(migrations.Migration):
             ],
         ),
         migrations.RunPython(move_sender_strings_to_sender_model),
-        migrations.AlterField(
+        migrations.RemoveField(
+            model_name='document',
+            name='sender',
+        ),
+        migrations.AddField(
             model_name='document',
             name='sender',
             field=models.ForeignKey(blank=True, on_delete=django.db.models.deletion.CASCADE, to='documents.Sender'),

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/0016_auto_20170325_1558.py

@@ -0,0 +1,20 @@
+# -*- coding: utf-8 -*-
+# Generated by Django 1.10.5 on 2017-03-25 15:58
+from __future__ import unicode_literals
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('documents', '0015_add_insensitive_to_match'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='document',
+            name='content',
+            field=models.TextField(blank=True, db_index=True, help_text='The raw, text-only data of the document.  This field is primarily used for searching.'),
+        ),
+    ]

src/documents/migrations/0017_auto_20170512_0507.py

@@ -0,0 +1,25 @@
+# -*- coding: utf-8 -*-
+# Generated by Django 1.10.5 on 2017-05-12 05:07
+from __future__ import unicode_literals
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('documents', '0016_auto_20170325_1558'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='correspondent',
+            name='matching_algorithm',
+            field=models.PositiveIntegerField(choices=[(1, 'Any'), (2, 'All'), (3, 'Literal'), (4, 'Regular Expression'), (5, 'Fuzzy Match')], default=1, 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 "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 is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containg imperfections that foil accurate OCR.'),
+        ),
+        migrations.AlterField(
+            model_name='tag',
+            name='matching_algorithm',
+            field=models.PositiveIntegerField(choices=[(1, 'Any'), (2, 'All'), (3, 'Literal'), (4, 'Regular Expression'), (5, 'Fuzzy Match')], default=1, 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 "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 is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containg imperfections that foil accurate OCR.'),
+        ),
+    ]

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/mixins.py

@@ -1,8 +1,3 @@
-from django.contrib.auth.mixins import AccessMixin
-from django.contrib.auth import authenticate, login
-import base64
-
-
 class Renderable(object):
     """
     A handy mixin to make it easier/cleaner to print output based on a
@@ -12,46 +7,3 @@ class Renderable(object):
     def _render(self, text, verbosity):
         if self.verbosity >= verbosity:
             print(text)
-
-
-class SessionOrBasicAuthMixin(AccessMixin):
-    """
-    Session or Basic Authentication mixin for Django.
-    It determines if the requester is already logged in or if they have
-    provided proper http-authorization and returning the view if all goes
-    well, otherwise responding with a 401.
-
-    Base for mixin found here: https://djangosnippets.org/snippets/3073/
-    """
-
-    def dispatch(self, request, *args, **kwargs):
-
-        # check if user is authenticated via the session
-        if request.user.is_authenticated:
-
-            # Already logged in, just return the view.
-            return super(SessionOrBasicAuthMixin, self).dispatch(
-                request, *args, **kwargs
-            )
-
-        # apparently not authenticated via session, maybe via HTTP Basic?
-        if 'HTTP_AUTHORIZATION' in request.META:
-            auth = request.META['HTTP_AUTHORIZATION'].split()
-            if len(auth) == 2:
-                # NOTE: Support for only basic authentication
-                if auth[0].lower() == "basic":
-                    authString = base64.b64decode(auth[1]).decode('utf-8')
-                    uname, passwd = authString.split(':')
-                    user = authenticate(username=uname, password=passwd)
-                    if user is not None:
-                        if user.is_active:
-                            login(request, user)
-                            request.user = user
-                            return super(
-                                SessionOrBasicAuthMixin, self
-                            ).dispatch(
-                                request, *args, **kwargs
-                            )
-
-        # nope, really not authenticated
-        return self.handle_no_permission()

src/documents/models.py

@@ -5,6 +5,7 @@ import re
 import uuid
 
 from collections import OrderedDict
+from fuzzywuzzy import fuzz
 
 from django.conf import settings
 from django.core.urlresolvers import reverse
@@ -21,11 +22,13 @@ class MatchingModel(models.Model):
     MATCH_ALL = 2
     MATCH_LITERAL = 3
     MATCH_REGEX = 4
+    MATCH_FUZZY = 5
     MATCHING_ALGORITHMS = (
         (MATCH_ANY, "Any"),
         (MATCH_ALL, "All"),
         (MATCH_LITERAL, "Literal"),
         (MATCH_REGEX, "Regular Expression"),
+        (MATCH_FUZZY, "Fuzzy Match"),
     )
 
     name = models.CharField(max_length=128, unique=True)
@@ -42,8 +45,11 @@ class MatchingModel(models.Model):
             "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 "
-            "is, you probably don't want this option."
+            "uses a regex to match the PDF.  (If you don't know what a regex "
+            "is, you probably don't want this option.)  Finally, a \"fuzzy "
+            "match\" looks for words or phrases that are mostly—but not "
+            "exactly—the same, which can be useful for matching against "
+            "documents containg imperfections that foil accurate OCR."
         )
     )
 
@@ -104,6 +110,15 @@ class MatchingModel(models.Model):
             return bool(re.search(
                 re.compile(self.match, **search_kwargs), text))
 
+        if self.matching_algorithm == self.MATCH_FUZZY:
+            match = re.sub(r'[^\w\s]', '', self.match)
+            text = re.sub(r'[^\w\s]', '', text)
+            if self.is_insensitive:
+                match = match.lower()
+                text = text.lower()
+
+            return True if fuzz.partial_ratio(match, text) >= 90 else False
+
         raise NotImplementedError("Unsupported matching algorithm")
 
     def save(self, *args, **kwargs):
@@ -157,14 +172,28 @@ 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)
-    content = models.TextField(db_index=True)
+
+    content = models.TextField(
+        db_index=True,
+        blank=True,
+        help_text="The raw, text-only data of the document.  This field is "
+                  "primarily used for searching."
+    )
+
     file_type = models.CharField(
         max_length=4,
         editable=False,
         choices=tuple([(t, t.upper()) for t in TYPES])
     )
+
     tags = models.ManyToManyField(
         Tag, related_name="documents", blank=True)
 
@@ -292,45 +321,45 @@ 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
         ))
     ])
@@ -373,6 +402,8 @@ class FileInfo(object):
         r = extension.lower()
         if r == "jpeg":
             return "jpg"
+        if r == "tif":
+            return "tiff"
         return r
 
     @classmethod

src/documents/parsers.py

@@ -0,0 +1,45 @@
+import logging
+import shutil
+import tempfile
+
+from django.conf import settings
+
+
+class ParseError(Exception):
+    pass
+
+
+class DocumentParser(object):
+    """
+    Subclass this to make your own parser.  Have a look at
+    `paperless_tesseract.parsers` for inspiration.
+    """
+
+    SCRATCH = settings.SCRATCH_DIR
+
+    def __init__(self, path):
+        self.document_path = path
+        self.tempdir = tempfile.mkdtemp(prefix="paperless", dir=self.SCRATCH)
+        self.logger = logging.getLogger(__name__)
+        self.logging_group = None
+
+    def get_thumbnail(self):
+        """
+        Returns the path to a file we can use as a thumbnail for this document.
+        """
+        raise NotImplementedError()
+
+    def get_text(self):
+        """
+        Returns the text from the document and only the text.
+        """
+        raise NotImplementedError()
+
+    def log(self, level, message):
+        getattr(self.logger, level)(message, extra={
+            "group": self.logging_group
+        })
+
+    def cleanup(self):
+        self.log("debug", "Deleting directory {}".format(self.tempdir))
+        shutil.rmtree(self.tempdir)

src/documents/serialisers.py

@@ -18,12 +18,21 @@ class TagSerializer(serializers.HyperlinkedModelSerializer):
             "id", "slug", "name", "colour", "match", "matching_algorithm")
 
 
+class CorrespondentField(serializers.HyperlinkedRelatedField):
+    def get_queryset(self):
+        return Correspondent.objects.all()
+
+
+class TagsField(serializers.HyperlinkedRelatedField):
+    def get_queryset(self):
+        return Tag.objects.all()
+
+
 class DocumentSerializer(serializers.ModelSerializer):
 
-    correspondent = serializers.HyperlinkedRelatedField(
-        read_only=True, view_name="drf:correspondent-detail", allow_null=True)
-    tags = serializers.HyperlinkedRelatedField(
-        read_only=True, view_name="drf:tag-detail", many=True)
+    correspondent = CorrespondentField(
+        view_name="drf:correspondent-detail", allow_null=True)
+    tags = TagsField(view_name="drf:tag-detail", many=True)
 
     class Meta(object):
         model = Document

src/documents/settings.py

@@ -0,0 +1,4 @@
+# Defines the names of file/thumbnail for the manifest
+# for exporting/importing commands
+EXPORTER_FILE_NAME = "__exported_file_name__"
+EXPORTER_THUMBNAIL_NAME = "__exported_thumbnail_name__"

src/documents/signals/__init__.py

@@ -2,3 +2,4 @@ from django.dispatch import Signal
 
 document_consumption_started = Signal(providing_args=["filename"])
 document_consumption_finished = Signal(providing_args=["document"])
+document_consumer_declaration = Signal(providing_args=[])

src/documents/signals/handlers.py

@@ -1,6 +1,5 @@
 import logging
 import os
-
 from subprocess import Popen
 
 from django.conf import settings

src/documents/static/paperless.css

@@ -10,3 +10,14 @@ td a.tag {
   margin: 1px;
   display: inline-block;
 }
+
+#result_list th.column-note {
+  text-align: right;
+}
+#result_list td.field-note {
+  text-align: right;
+}
+#result_list td textarea {
+  width: 90%;
+  height: 5em;
+}

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

@@ -158,7 +158,7 @@
 
 
 <script>
-  // We nee to re-build the select-all functionality as the old logic pointed
+  // We need to re-build the select-all functionality as the old logic pointed
   // to a table and we're using divs now.
   django.jQuery("#action-toggle").on("change", function(){
     django.jQuery(".grid .box .result .checkbox input")

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

@@ -1,22 +1,66 @@
-import os
-from unittest import mock, skipIf
-
-import pyocr
 from django.test import TestCase
-from pyocr.libtesseract.tesseract_raw import \
-    TesseractError as OtherTesseractError
+from unittest import mock
 
+from ..consumer import Consumer
 from ..models import FileInfo
-from ..consumer import image_to_string, strip_excess_whitespace
+
+
+class TestConsumer(TestCase):
+
+    class DummyParser(object):
+        pass
+
+    def test__get_parser_class_1_parser(self):
+        self.assertEqual(
+            self._get_consumer()._get_parser_class("doc.pdf"),
+            self.DummyParser
+        )
+
+    @mock.patch("documents.consumer.Consumer.CONSUME")
+    @mock.patch("documents.consumer.os.makedirs")
+    @mock.patch("documents.consumer.os.path.exists", return_value=True)
+    @mock.patch("documents.consumer.document_consumer_declaration.send")
+    def test__get_parser_class_n_parsers(self, m, *args):
+
+        class DummyParser1(object):
+            pass
+
+        class DummyParser2(object):
+            pass
+
+        m.return_value = (
+            (None, lambda _: {"weight": 0, "parser": DummyParser1}),
+            (None, lambda _: {"weight": 1, "parser": DummyParser2}),
+        )
+
+        self.assertEqual(Consumer()._get_parser_class("doc.pdf"), DummyParser2)
+
+    @mock.patch("documents.consumer.Consumer.CONSUME")
+    @mock.patch("documents.consumer.os.makedirs")
+    @mock.patch("documents.consumer.os.path.exists", return_value=True)
+    @mock.patch("documents.consumer.document_consumer_declaration.send")
+    def test__get_parser_class_0_parsers(self, m, *args):
+        m.return_value = ((None, lambda _: None),)
+        self.assertIsNone(Consumer()._get_parser_class("doc.pdf"))
+
+    @mock.patch("documents.consumer.Consumer.CONSUME")
+    @mock.patch("documents.consumer.os.makedirs")
+    @mock.patch("documents.consumer.os.path.exists", return_value=True)
+    @mock.patch("documents.consumer.document_consumer_declaration.send")
+    def _get_consumer(self, m, *args):
+        m.return_value = (
+            (None, lambda _: {"weight": 0, "parser": self.DummyParser}),
+        )
+        return Consumer()
 
 
 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):
@@ -36,6 +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)
 
@@ -308,71 +354,3 @@ class TestFieldPermutations(TestCase):
                         }
                         self._test_guessed_attributes(
                             template.format(**spec), **spec)
-
-
-class FakeTesseract(object):
-
-    @staticmethod
-    def can_detect_orientation():
-        return True
-
-    @staticmethod
-    def detect_orientation(file_handle, lang):
-        raise OtherTesseractError("arbitrary status", "message")
-
-    @staticmethod
-    def image_to_string(file_handle, lang):
-        return "This is test text"
-
-
-class FakePyOcr(object):
-
-    @staticmethod
-    def get_available_tools():
-        return [FakeTesseract]
-
-
-class TestOCR(TestCase):
-
-    text_cases = [
-        ("simple     string", "simple string"),
-        (
-            "simple    newline\n   testing string",
-            "simple newline\ntesting string"
-        ),
-        (
-            "utf-8   строка с пробелами в конце  ",
-            "utf-8 строка с пробелами в конце"
-        )
-    ]
-
-    SAMPLE_FILES = os.path.join(os.path.dirname(__file__), "samples")
-    TESSERACT_INSTALLED = bool(pyocr.get_available_tools())
-
-    def test_strip_excess_whitespace(self):
-        for source, result in self.text_cases:
-            actual_result = strip_excess_whitespace(source)
-            self.assertEqual(
-                result,
-                actual_result,
-                "strip_exceess_whitespace({}) != '{}', but '{}'".format(
-                    source,
-                    result,
-                    actual_result
-                )
-            )
-
-    @skipIf(not TESSERACT_INSTALLED, "Tesseract not installed. Skipping")
-    @mock.patch("documents.consumer.Consumer.SCRATCH", SAMPLE_FILES)
-    @mock.patch("documents.consumer.pyocr", FakePyOcr)
-    def test_image_to_string_with_text_free_page(self):
-        """
-        This test is sort of silly, since it's really just reproducing an odd
-        exception thrown by pyocr when it encounters a page with no text.
-        Actually running this test against an installation of Tesseract results
-        in a segmentation fault rooted somewhere deep inside pyocr where I
-        don't care to dig.  Regardless, if you run the consumer normally,
-        text-free pages are now handled correctly so long as we work around
-        this weird exception.
-        """
-        image_to_string(["no-text.png", "en"])

src/documents/tests/test_importer.py

@@ -3,6 +3,8 @@ from django.test import TestCase
 
 from ..management.commands.document_importer import Command
 
+from documents.settings import EXPORTER_FILE_NAME
+
 
 class TestImporter(TestCase):
 
@@ -27,7 +29,7 @@ class TestImporter(TestCase):
 
         cmd.manifest = [{
             "model": "documents.document",
-            "__exported_file_name__": "noexist.pdf"
+            EXPORTER_FILE_NAME: "noexist.pdf"
         }]
         # self.assertRaises(CommandError, cmd._check_manifest)
         with self.assertRaises(CommandError) as cm:

src/documents/tests/test_matchables.py

@@ -149,6 +149,22 @@ class TestMatching(TestCase):
             )
         )
 
+    def test_match_fuzzy(self):
+
+        self._test_matching(
+            "Springfield, Miss.",
+            "MATCH_FUZZY",
+            (
+                "1220 Main Street, Springf eld, Miss.",
+                "1220 Main Street, Spring field, Miss.",
+                "1220 Main Street, Springfeld, Miss.",
+                "1220 Main Street Springfield Miss",
+            ),
+            (
+                "1220 Main Street, Springfield, Mich.",
+            )
+        )
+
 
 class TestApplications(TestCase):
     """

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

@@ -1,16 +1,16 @@
-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 rest_framework.filters import SearchFilter, OrderingFilter
 from paperless.db import GnuPG
+from paperless.mixins import SessionOrBasicAuthMixin
+from paperless.views import StandardPagination
+from rest_framework.filters import OrderingFilter, SearchFilter
 from rest_framework.mixins import (
     DestroyModelMixin,
     ListModelMixin,
     RetrieveModelMixin,
     UpdateModelMixin
 )
-from rest_framework.pagination import PageNumberPagination
 from rest_framework.permissions import IsAuthenticated
 from rest_framework.viewsets import (
     GenericViewSet,
@@ -27,7 +27,6 @@ from .serialisers import (
     LogSerializer,
     TagSerializer
 )
-from .mixins import SessionOrBasicAuthMixin
 
 
 class IndexView(TemplateView):
@@ -81,21 +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")
-
-
-class StandardPagination(PageNumberPagination):
-    page_size = 25
-    page_size_query_param = "page-size"
-    max_page_size = 100000
+        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/mixins.py

@@ -0,0 +1,46 @@
+from django.contrib.auth.mixins import AccessMixin
+from django.contrib.auth import authenticate, login
+import base64
+
+
+class SessionOrBasicAuthMixin(AccessMixin):
+    """
+    Session or Basic Authentication mixin for Django.
+    It determines if the requester is already logged in or if they have
+    provided proper http-authorization and returning the view if all goes
+    well, otherwise responding with a 401.
+
+    Base for mixin found here: https://djangosnippets.org/snippets/3073/
+    """
+
+    def dispatch(self, request, *args, **kwargs):
+
+        # check if user is authenticated via the session
+        if request.user.is_authenticated:
+
+            # Already logged in, just return the view.
+            return super(SessionOrBasicAuthMixin, self).dispatch(
+                request, *args, **kwargs
+            )
+
+        # apparently not authenticated via session, maybe via HTTP Basic?
+        if 'HTTP_AUTHORIZATION' in request.META:
+            auth = request.META['HTTP_AUTHORIZATION'].split()
+            if len(auth) == 2:
+                # NOTE: Support for only basic authentication
+                if auth[0].lower() == "basic":
+                    authString = base64.b64decode(auth[1]).decode('utf-8')
+                    uname, passwd = authString.split(':')
+                    user = authenticate(username=uname, password=passwd)
+                    if user is not None:
+                        if user.is_active:
+                            login(request, user)
+                            request.user = user
+                            return super(
+                                SessionOrBasicAuthMixin, self
+                            ).dispatch(
+                                request, *args, **kwargs
+                            )
+
+        # nope, really not authenticated
+        return self.handle_no_permission()

src/paperless/settings.py

@@ -4,10 +4,10 @@ Django settings for paperless project.
 Generated by 'django-admin startproject' using Django 1.9.
 
 For more information on this file, see
-https://docs.djangoproject.com/en/1.9/topics/settings/
+https://docs.djangoproject.com/en/1.10/topics/settings/
 
 For the full list of settings and their values, see
-https://docs.djangoproject.com/en/1.9/ref/settings/
+https://docs.djangoproject.com/en/1.10/ref/settings/
 """
 
 import os
@@ -25,7 +25,7 @@ BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 
 
 # Quick-start development settings - unsuitable for production
-# See https://docs.djangoproject.com/en/1.9/howto/deployment/checklist/
+# See https://docs.djangoproject.com/en/1.10/howto/deployment/checklist/
 
 # 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
@@ -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 = [
@@ -61,15 +62,21 @@ INSTALLED_APPS = [
     "django_extensions",
 
     "documents.apps.DocumentsConfig",
+    "reminders.apps.RemindersConfig",
+    "paperless_tesseract.apps.PaperlessTesseractConfig",
 
     "flat_responsive",
     "django.contrib.admin",
 
     "rest_framework",
     "crispy_forms",
+    "django_filters"
 
 ]
 
+if os.getenv("PAPERLESS_INSTALLED_APPS"):
+    INSTALLED_APPS += os.getenv("PAPERLESS_INSTALLED_APPS").split(",")
+
 MIDDLEWARE_CLASSES = [
     'django.middleware.security.SecurityMiddleware',
     'django.contrib.sessions.middleware.SessionMiddleware',
@@ -103,7 +110,7 @@ WSGI_APPLICATION = 'paperless.wsgi.application'
 
 
 # Database
-# https://docs.djangoproject.com/en/1.9/ref/settings/#databases
+# https://docs.djangoproject.com/en/1.10/ref/settings/#databases
 
 DATABASES = {
     "default": {
@@ -128,7 +135,7 @@ if os.getenv("PAPERLESS_DBUSER") and os.getenv("PAPERLESS_DBPASS"):
 
 
 # Password validation
-# https://docs.djangoproject.com/en/1.9/ref/settings/#auth-password-validators
+# https://docs.djangoproject.com/en/1.10/ref/settings/#auth-password-validators
 
 AUTH_PASSWORD_VALIDATORS = [
     {
@@ -147,7 +154,7 @@ AUTH_PASSWORD_VALIDATORS = [
 
 
 # Internationalization
-# https://docs.djangoproject.com/en/1.9/topics/i18n/
+# https://docs.djangoproject.com/en/1.10/topics/i18n/
 
 LANGUAGE_CODE = 'en-us'
 
@@ -161,7 +168,7 @@ USE_TZ = True
 
 
 # Static files (CSS, JavaScript, Images)
-# https://docs.djangoproject.com/en/1.9/howto/static-files/
+# https://docs.djangoproject.com/en/1.10/howto/static-files/
 
 STATIC_ROOT = os.getenv(
     "PAPERLESS_STATICDIR", os.path.join(BASE_DIR, "..", "static"))
@@ -231,18 +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"),
-    "USE_SSL": os.getenv("PAPERLESS_CONSUME_MAIL_USE_SSL", "y").lower() == "y",  # If True, use SSL/TLS to connect
-    "INBOX": "INBOX"  # The name of the inbox on the server
-}
-
 # 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
@@ -252,11 +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

@@ -1,35 +1,22 @@
-"""paperless URL Configuration
-
-The `urlpatterns` list routes URLs to views. For more information please see:
-    https://docs.djangoproject.com/en/1.9/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.contrib import admin
+from django.views.decorators.csrf import csrf_exempt
 
 from rest_framework.routers import DefaultRouter
 
 from documents.views import (
-    IndexView, FetchView, PushView,
+    FetchView, PushView,
     CorrespondentViewSet, TagViewSet, DocumentViewSet, LogViewSet
 )
+from reminders.views import ReminderViewSet
 
 router = DefaultRouter()
-router.register(r'correspondents', CorrespondentViewSet)
-router.register(r'tags', TagViewSet)
-router.register(r'documents', DocumentViewSet)
-router.register(r'logs', LogViewSet)
+router.register(r"correspondents", CorrespondentViewSet)
+router.register(r"documents", DocumentViewSet)
+router.register(r"logs", LogViewSet)
+router.register(r"reminders", ReminderViewSet)
+router.register(r"tags", TagViewSet)
 
 urlpatterns = [
 
@@ -40,9 +27,6 @@ urlpatterns = [
     ),
     url(r"^api/", include(router.urls, namespace="drf")),
 
-    # Normal pages (coming soon)
-    # url(r"^$", IndexView.as_view(), name="index"),
-
     # File downloads
     url(
         r"^fetch/(?P<kind>doc|thumb)/(?P<pk>\d+)$",
@@ -50,11 +34,18 @@ 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
 
 ] + 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>.
+admin.site.site_title = 'Paperless'
+# Text at the top of the admin index page.
+admin.site.index_title = 'Paperless administration'

src/paperless/version.py

@@ -1 +1 @@
-__version__ = (0, 3, 5)
+__version__ = (0, 6, 1)

src/paperless/views.py

@@ -0,0 +1,7 @@
+from rest_framework.pagination import PageNumberPagination
+
+
+class StandardPagination(PageNumberPagination):
+    page_size = 25
+    page_size_query_param = "page-size"
+    max_page_size = 100000

src/paperless/wsgi.py

@@ -4,7 +4,7 @@ WSGI config for paperless project.
 It exposes the WSGI callable as a module-level variable named ``application``.
 
 For more information on this file, see
-https://docs.djangoproject.com/en/1.9/howto/deployment/wsgi/
+https://docs.djangoproject.com/en/1.10/howto/deployment/wsgi/
 """
 
 import os

src/paperless_tesseract/apps.py

@@ -0,0 +1,16 @@
+from django.apps import AppConfig
+
+
+class PaperlessTesseractConfig(AppConfig):
+
+    name = "paperless_tesseract"
+
+    def ready(self):
+
+        from documents.signals import document_consumer_declaration
+
+        from .signals import ConsumerDeclaration
+
+        document_consumer_declaration.connect(ConsumerDeclaration.handle)
+
+        AppConfig.ready(self)

src/paperless_tesseract/parsers.py

@@ -0,0 +1,214 @@
+import itertools
+import os
+import re
+import subprocess
+from multiprocessing.pool import Pool
+
+import langdetect
+import pyocr
+from django.conf import settings
+from documents.parsers import DocumentParser, ParseError
+from PIL import Image
+from pyocr.libtesseract.tesseract_raw import \
+    TesseractError as OtherTesseractError
+from pyocr.tesseract import TesseractError
+
+from .languages import ISO639
+
+
+class OCRError(Exception):
+    pass
+
+
+class RasterisedDocumentParser(DocumentParser):
+    """
+    This parser uses Tesseract to try and get some text out of a rasterised
+    image, whether it's a PDF, or other graphical format (JPEG, TIFF, etc.)
+    """
+
+    CONVERT = settings.CONVERT_BINARY
+    DENSITY = settings.CONVERT_DENSITY if settings.CONVERT_DENSITY else 300
+    THREADS = int(settings.OCR_THREADS) if settings.OCR_THREADS else None
+    UNPAPER = settings.UNPAPER_BINARY
+    DEFAULT_OCR_LANGUAGE = settings.OCR_LANGUAGE
+
+    def get_thumbnail(self):
+        """
+        The thumbnail of a PDF is just a 500px wide image of the first page.
+        """
+
+        run_convert(
+            self.CONVERT,
+            "-scale", "500x5000",
+            "-alpha", "remove",
+            self.document_path, os.path.join(self.tempdir, "convert-%04d.png")
+        )
+
+        return os.path.join(self.tempdir, "convert-0000.png")
+
+    def get_text(self):
+
+        images = self._get_greyscale()
+
+        try:
+
+            return self._get_ocr(images)
+        except OCRError as e:
+            raise ParseError(e)
+
+    def _get_greyscale(self):
+        """
+        Greyscale images are easier for Tesseract to OCR
+        """
+
+        # Convert PDF to multiple PNMs
+        pnm = os.path.join(self.tempdir, "convert-%04d.pnm")
+        run_convert(
+            self.CONVERT,
+            "-density", str(self.DENSITY),
+            "-depth", "8",
+            "-type", "grayscale",
+            self.document_path, pnm,
+        )
+
+        # Get a list of converted images
+        pnms = []
+        for f in os.listdir(self.tempdir):
+            if f.endswith(".pnm"):
+                pnms.append(os.path.join(self.tempdir, f))
+
+        # Run unpaper in parallel on converted images
+        with Pool(processes=self.THREADS) as pool:
+            pool.map(run_unpaper, itertools.product([self.UNPAPER], pnms))
+
+        # Return list of converted images, processed with unpaper
+        pnms = []
+        for f in os.listdir(self.tempdir):
+            if f.endswith(".unpaper.pnm"):
+                pnms.append(os.path.join(self.tempdir, f))
+
+        return sorted(filter(lambda __: os.path.isfile(__), pnms))
+
+    def _guess_language(self, text):
+        try:
+            guess = langdetect.detect(text)
+            self.log("debug", "Language detected: {}".format(guess))
+            return guess
+        except Exception as e:
+            self.log("warning", "Language detection error: {}".format(e))
+
+    def _get_ocr(self, imgs):
+        """
+        Attempts to do the best job possible OCR'ing the document based on
+        simple language detection trial & error.
+        """
+
+        if not imgs:
+            raise OCRError("No images found")
+
+        self.log("info", "OCRing the document")
+
+        # Since the division gets rounded down by int, this calculation works
+        # for every edge-case, i.e. 1
+        middle = int(len(imgs) / 2)
+        raw_text = self._ocr([imgs[middle]], self.DEFAULT_OCR_LANGUAGE)
+
+        guessed_language = self._guess_language(raw_text)
+
+        if not guessed_language or guessed_language not in ISO639:
+            self.log("warning", "Language detection failed!")
+            if settings.FORGIVING_OCR:
+                self.log(
+                    "warning",
+                    "As FORGIVING_OCR is enabled, we're going to make the "
+                    "best with what we have."
+                )
+                raw_text = self._assemble_ocr_sections(imgs, middle, raw_text)
+                return raw_text
+            raise OCRError("Language detection failed")
+
+        if ISO639[guessed_language] == self.DEFAULT_OCR_LANGUAGE:
+            raw_text = self._assemble_ocr_sections(imgs, middle, raw_text)
+            return raw_text
+
+        try:
+            return self._ocr(imgs, ISO639[guessed_language])
+        except pyocr.pyocr.tesseract.TesseractError:
+            if settings.FORGIVING_OCR:
+                self.log(
+                    "warning",
+                    "OCR for {} failed, but we're going to stick with what "
+                    "we've got since FORGIVING_OCR is enabled.".format(
+                        guessed_language
+                    )
+                )
+                raw_text = self._assemble_ocr_sections(imgs, middle, raw_text)
+                return raw_text
+            raise OCRError(
+                "The guessed language is not available in this instance of "
+                "Tesseract."
+            )
+
+    def _ocr(self, imgs, lang):
+        """
+        Performs a single OCR attempt.
+        """
+
+        if not imgs:
+            return ""
+
+        self.log("info", "Parsing for {}".format(lang))
+
+        with Pool(processes=self.THREADS) as pool:
+            r = pool.map(image_to_string, itertools.product(imgs, [lang]))
+            r = " ".join(r)
+
+        # Strip out excess white space to allow matching to go smoother
+        return strip_excess_whitespace(r)
+
+    def _assemble_ocr_sections(self, imgs, middle, text):
+        """
+        Given a `middle` value and the text that middle page represents, we OCR
+        the remainder of the document and return the whole thing.
+        """
+        text = self._ocr(imgs[:middle], self.DEFAULT_OCR_LANGUAGE) + text
+        text += self._ocr(imgs[middle + 1:], self.DEFAULT_OCR_LANGUAGE)
+        return text
+
+
+def run_convert(*args):
+
+    environment = os.environ.copy()
+    if settings.CONVERT_MEMORY_LIMIT:
+        environment["MAGICK_MEMORY_LIMIT"] = settings.CONVERT_MEMORY_LIMIT
+    if settings.CONVERT_TMPDIR:
+        environment["MAGICK_TMPDIR"] = settings.CONVERT_TMPDIR
+
+    subprocess.Popen(args, env=environment).wait()
+
+
+def run_unpaper(args):
+    unpaper, pnm = args
+    subprocess.Popen(
+        (unpaper, pnm, pnm.replace(".pnm", ".unpaper.pnm"))).wait()
+
+
+def strip_excess_whitespace(text):
+    collapsed_spaces = re.sub(r"([^\S\r\n]+)", " ", text)
+    no_leading_whitespace = re.sub(
+        "([\n\r]+)([^\S\n\r]+)", '\\1', collapsed_spaces)
+    no_trailing_whitespace = re.sub("([^\S\n\r]+)$", '', no_leading_whitespace)
+    return no_trailing_whitespace
+
+
+def image_to_string(args):
+    img, lang = args
+    ocr = pyocr.get_available_tools()[0]
+    with Image.open(os.path.join(RasterisedDocumentParser.SCRATCH, img)) as f:
+        if ocr.can_detect_orientation():
+            try:
+                orientation = ocr.detect_orientation(f, lang=lang)
+                f = f.rotate(orientation["angle"], expand=1)
+            except (TesseractError, OtherTesseractError):
+                pass
+        return ocr.image_to_string(f, lang=lang)

src/paperless_tesseract/signals.py

@@ -0,0 +1,23 @@
+import re
+
+from .parsers import RasterisedDocumentParser
+
+
+class ConsumerDeclaration(object):
+
+    MATCHING_FILES = re.compile("^.*\.(pdf|jpg|gif|png|tiff?|pnm|bmp)$")
+
+    @classmethod
+    def handle(cls, sender, **kwargs):
+        return cls.test
+
+    @classmethod
+    def test(cls, doc):
+
+        if cls.MATCHING_FILES.match(doc.lower()):
+            return {
+                "parser": RasterisedDocumentParser,
+                "weight": 0
+            }
+
+        return None

src/paperless_tesseract/tests/test_ocr.py

@@ -0,0 +1,80 @@
+import os
+from unittest import mock, skipIf
+
+import pyocr
+from django.test import TestCase
+from pyocr.libtesseract.tesseract_raw import \
+    TesseractError as OtherTesseractError
+
+from ..parsers import image_to_string, strip_excess_whitespace
+
+
+class FakeTesseract(object):
+
+    @staticmethod
+    def can_detect_orientation():
+        return True
+
+    @staticmethod
+    def detect_orientation(file_handle, lang):
+        raise OtherTesseractError("arbitrary status", "message")
+
+    @staticmethod
+    def image_to_string(file_handle, lang):
+        return "This is test text"
+
+
+class FakePyOcr(object):
+
+    @staticmethod
+    def get_available_tools():
+        return [FakeTesseract]
+
+
+class TestOCR(TestCase):
+
+    text_cases = [
+        ("simple     string", "simple string"),
+        (
+            "simple    newline\n   testing string",
+            "simple newline\ntesting string"
+        ),
+        (
+            "utf-8   строка с пробелами в конце  ",
+            "utf-8 строка с пробелами в конце"
+        )
+    ]
+
+    SAMPLE_FILES = os.path.join(os.path.dirname(__file__), "samples")
+    TESSERACT_INSTALLED = bool(pyocr.get_available_tools())
+
+    def test_strip_excess_whitespace(self):
+        for source, result in self.text_cases:
+            actual_result = strip_excess_whitespace(source)
+            self.assertEqual(
+                result,
+                actual_result,
+                "strip_exceess_whitespace({}) != '{}', but '{}'".format(
+                    source,
+                    result,
+                    actual_result
+                )
+            )
+
+    @skipIf(not TESSERACT_INSTALLED, "Tesseract not installed. Skipping")
+    @mock.patch(
+        "paperless_tesseract.parsers.RasterisedDocumentParser.SCRATCH",
+        SAMPLE_FILES
+    )
+    @mock.patch("paperless_tesseract.parsers.pyocr", FakePyOcr)
+    def test_image_to_string_with_text_free_page(self):
+        """
+        This test is sort of silly, since it's really just reproducing an odd
+        exception thrown by pyocr when it encounters a page with no text.
+        Actually running this test against an installation of Tesseract results
+        in a segmentation fault rooted somewhere deep inside pyocr where I
+        don't care to dig.  Regardless, if you run the consumer normally,
+        text-free pages are now handled correctly so long as we work around
+        this weird exception.
+        """
+        image_to_string(["no-text.png", "en"])

src/paperless_tesseract/tests/test_signals.py

@@ -0,0 +1,36 @@
+from django.test import TestCase
+
+from ..signals import ConsumerDeclaration
+
+
+class SignalsTestCase(TestCase):
+
+    def test_test_handles_various_file_names_true(self):
+
+        prefixes = (
+            "doc", "My Document", "Μυ Γρεεκ Δοψθμεντ", "Doc -with - tags",
+            "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",
+        )
+
+        for prefix in prefixes:
+            for suffix in suffixes:
+                name = "{}.{}".format(prefix, suffix)
+                self.assertTrue(ConsumerDeclaration.test(name))
+
+    def test_test_handles_various_file_names_false(self):
+
+        prefixes = ("doc",)
+        suffixes = ("txt", "markdown", "",)
+
+        for prefix in prefixes:
+            for suffix in suffixes:
+                name = "{}.{}".format(prefix, suffix)
+                self.assertFalse(ConsumerDeclaration.test(name))
+
+        self.assertFalse(ConsumerDeclaration.test(""))
+        self.assertFalse(ConsumerDeclaration.test("doc"))

src/pytest.ini

@@ -1,3 +1,7 @@
 [pytest]
 DJANGO_SETTINGS_MODULE=paperless.settings
-
+env =
+  PAPERLESS_CONSUME=/tmp
+  PAPERLESS_PASSPHRASE=THISISNOTASECRET
+  PAPERLESS_SECRET=paperless
+  PAPERLESS_EMAIL_SECRET=paperless

src/reminders/admin.py

@@ -0,0 +1,20 @@
+from django.conf import settings
+from django.contrib import admin
+
+from .models import Reminder
+
+
+class ReminderAdmin(admin.ModelAdmin):
+
+    class Media:
+        css = {
+            "all": ("paperless.css",)
+        }
+
+    list_per_page = settings.PAPERLESS_LIST_PER_PAGE
+    list_display = ("date", "document", "note")
+    list_filter = ("date",)
+    list_editable = ("note",)
+
+
+admin.site.register(Reminder, ReminderAdmin)

src/reminders/apps.py

@@ -0,0 +1,5 @@
+from django.apps import AppConfig
+
+
+class RemindersConfig(AppConfig):
+    name = "reminders"

src/reminders/filters.py

@@ -0,0 +1,14 @@
+from django_filters.rest_framework import CharFilter, FilterSet
+
+from .models import Reminder
+
+
+class ReminderFilterSet(FilterSet):
+
+    class Meta(object):
+        model = Reminder
+        fields = {
+            "document": ["exact"],
+            "date": ["gt", "lt", "gte", "lte", "exact"],
+            "note": ["istartswith", "iendswith", "icontains"]
+        }

src/reminders/migrations/0001_initial.py

@@ -0,0 +1,27 @@
+# -*- coding: utf-8 -*-
+# Generated by Django 1.10.5 on 2017-03-25 15:58
+from __future__ import unicode_literals
+
+from django.db import migrations, models
+import django.db.models.deletion
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+        ('documents', '0016_auto_20170325_1558'),
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='Reminder',
+            fields=[
+                ('id', models.AutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('date', models.DateTimeField()),
+                ('note', models.TextField(blank=True)),
+                ('document', models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, to='documents.Document')),
+            ],
+        ),
+    ]

src/reminders/models.py

@@ -0,0 +1,8 @@
+from django.db import models
+
+
+class Reminder(models.Model):
+
+    document = models.ForeignKey("documents.Document")
+    date = models.DateTimeField()
+    note = models.TextField(blank=True)

src/reminders/serialisers.py

@@ -0,0 +1,14 @@
+from documents.models import Document
+from rest_framework import serializers
+
+from .models import Reminder
+
+
+class ReminderSerializer(serializers.HyperlinkedModelSerializer):
+
+    document = serializers.HyperlinkedRelatedField(
+        view_name="drf:document-detail", queryset=Document.objects)
+
+    class Meta(object):
+        model = Reminder
+        fields = ("id", "document", "date", "note")

src/reminders/tests.py

@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.

src/reminders/views.py

@@ -0,0 +1,22 @@
+from django_filters.rest_framework import DjangoFilterBackend
+from rest_framework.filters import OrderingFilter
+from rest_framework.permissions import IsAuthenticated
+from rest_framework.viewsets import (
+    ModelViewSet,
+)
+
+from .filters import ReminderFilterSet
+from .models import Reminder
+from .serialisers import ReminderSerializer
+from paperless.views import StandardPagination
+
+
+class ReminderViewSet(ModelViewSet):
+    model = Reminder
+    queryset = Reminder.objects
+    serializer_class = ReminderSerializer
+    pagination_class = StandardPagination
+    permission_classes = (IsAuthenticated,)
+    filter_backends = (DjangoFilterBackend, OrderingFilter)
+    filter_class = ReminderFilterSet
+    ordering_fields = ("date", "document")

src/tox.ini

@@ -5,15 +5,11 @@
 
 [tox]
 skipsdist = True
-envlist = py34, py35, pep8
+envlist = py34, py35, py36, pep8
 
 [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