TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-03-23 07:55:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Initial version.

Browse Source 
Features:

- Upload PDF files let them analyze

- Manage meta data and items

- See processing in webapp
This commit is contained in:
Eike Kettner 2019-07-23 00:53:30 +02:00
parent 6154e6a387
commit 831cd8b655
341 changed files with 23634 additions and 484 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
.gitignore vendored
View File

@ -1,3 +1,5 @@
target/
dev.conf
elm-stuff
elm-stuff
result
_site/

674
LICENSE.txt Normal file
View File

@ -0,0 +1,674 @@
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
<http://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<http://www.gnu.org/philosophy/why-not-lgpl.html>.

10
README.md
View File

@ -1 +1,11 @@
<img align="right" src="./artwork/logo-only.svg" height="150px" style="padding-left: 20px"/>
# Docspell
Docspell is a personal document organizer. You'll need a scanner to
convert your papers into PDF files. Docspell can then assist in
organizing the resulting mess :wink:.
See the [microsite](https://eikek.github.io/docspell/) for more
information.

BIN
artwork/icon.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 5.8 KiB

217
build.sbt
View File

@ -1,39 +1,43 @@
import com.github.eikek.sbt.openapi._
import scala.sys.process._
import com.typesafe.sbt.SbtGit.GitKeys._
import docspell.build._
val sharedSettings = Seq(
organization := "com.github.eikek",
scalaVersion := "2.13.0",
scalaVersion := "2.13.1",
scalacOptions ++= Seq(
"-deprecation",
"-encoding", "UTF-8",
"-language:higherKinds",
"-language:postfixOps",
"-feature",
"-Xfatal-warnings", // fail when there are warnings
"-Werror", // fail when there are warnings
"-unchecked",
"-Xlint",
"-Xlint:_",
"-Ywarn-dead-code",
"-Ywarn-numeric-widen",
"-Ywarn-value-discard"
),
scalacOptions in (Compile, console) := Seq()
scalacOptions in (Compile, console) :=
(scalacOptions.value.filter(o => !o.contains("Xlint")) ++ Seq("-Xlint:_,-unused")),
scalacOptions in (Test, console) :=
(scalacOptions.value.filter(o => !o.contains("Xlint")) ++ Seq("-Xlint:_,-unused"))
)
val testSettings = Seq(
testFrameworks += new TestFramework("minitest.runner.Framework"),
libraryDependencies ++= Dependencies.miniTest
libraryDependencies ++= Dependencies.miniTest ++ Dependencies.logging.map(_ % Test)
)
val elmSettings = Seq(
Compile/resourceGenerators += (Def.task {
Compile/resourceGenerators += Def.task {
compileElm(streams.value.log
, (Compile/baseDirectory).value
, (Compile/resourceManaged).value
, name.value
, version.value)
}).taskValue,
}.taskValue,
watchSources += Watched.WatchSource(
(Compile/sourceDirectory).value/"elm"
, FileFilter.globFilter("*.elm")
@ -42,14 +46,14 @@ val elmSettings = Seq(
)
val webjarSettings = Seq(
Compile/resourceGenerators += (Def.task {
Compile/resourceGenerators += Def.task {
copyWebjarResources(Seq((sourceDirectory in Compile).value/"webjar")
, (Compile/resourceManaged).value
, name.value
, version.value
, streams.value.log
)
}).taskValue,
}.taskValue,
watchSources += Watched.WatchSource(
(Compile / sourceDirectory).value/"webjar"
, FileFilter.globFilter("*.js") || FileFilter.globFilter("*.css")
@ -57,7 +61,7 @@ val webjarSettings = Seq(
)
)
val debianSettings = Seq(
def debianSettings(cfgFile: String) = Seq(
maintainer := "Eike Kettner <eike.kettner@posteo.de>",
packageSummary := description.value,
packageDescription := description.value,
@ -66,9 +70,9 @@ val debianSettings = Seq(
if (!conf.exists) {
sys.error(s"File $conf not found")
}
conf -> "conf/docspell.conf"
conf -> s"conf/$cfgFile.conf"
},
bashScriptExtraDefines += """addJava "-Dconfig.file=${app_home}/../conf/docspell.conf""""
bashScriptExtraDefines += s"""addJava "-Dconfig.file=$${app_home}/../conf/$cfgFile.conf""""
)
val buildInfoSettings = Seq(
@ -77,7 +81,47 @@ val buildInfoSettings = Seq(
buildInfoOptions += BuildInfoOption.BuildTime
)
val openapiScalaSettings = Seq(
openapiScalaConfig := ScalaConfig().withJson(ScalaJson.circeSemiauto).
addMapping(CustomMapping.forType({
case TypeDef("LocalDateTime", _) =>
TypeDef("Timestamp", Imports("docspell.common.Timestamp"))
})).
addMapping(CustomMapping.forFormatType({
case "ident" => field =>
field.copy(typeDef = TypeDef("Ident", Imports("docspell.common.Ident")))
case "collectivestate" => field =>
field.copy(typeDef = TypeDef("CollectiveState", Imports("docspell.common.CollectiveState")))
case "userstate" => field =>
field.copy(typeDef = TypeDef("UserState", Imports("docspell.common.UserState")))
case "password" => field =>
field.copy(typeDef = TypeDef("Password", Imports("docspell.common.Password")))
case "contactkind" => field =>
field.copy(typeDef = TypeDef("ContactKind", Imports("docspell.common.ContactKind")))
case "direction" => field =>
field.copy(typeDef = TypeDef("Direction", Imports("docspell.common.Direction")))
case "priority" => field =>
field.copy(typeDef = TypeDef("Priority", Imports("docspell.common.Priority")))
case "jobstate" => field =>
field.copy(typeDef = TypeDef("JobState", Imports("docspell.common.JobState")))
case "loglevel" => field =>
field.copy(typeDef = TypeDef("LogLevel", Imports("docspell.common.LogLevel")))
case "mimetype" => field =>
field.copy(typeDef = TypeDef("MimeType", Imports("docspell.common.MimeType")))
case "itemstate" => field =>
field.copy(typeDef = TypeDef("ItemState", Imports("docspell.common.ItemState")))
case "nertag" => field =>
field.copy(typeDef = TypeDef("NerTag", Imports("docspell.common.NerTag")))
case "language" => field =>
field.copy(typeDef = TypeDef("Language", Imports("docspell.common.Language")))
}))
)
val reStartSettings = Seq(
javaOptions in reStart ++= Seq(s"-Dconfig.file=${(LocalRootProject/baseDirectory).value/"dev.conf"}")
)
// --- Modules
val common = project.in(file("modules/common")).
settings(sharedSettings).
@ -85,7 +129,10 @@ val common = project.in(file("modules/common")).
settings(
name := "docspell-common",
libraryDependencies ++=
Dependencies.fs2
Dependencies.fs2 ++
Dependencies.circe ++
Dependencies.loggingApi ++
Dependencies.pureconfig.map(_ % "optional")
)
val store = project.in(file("modules/store")).
@ -96,16 +143,31 @@ val store = project.in(file("modules/store")).
libraryDependencies ++=
Dependencies.doobie ++
Dependencies.bitpeace ++
Dependencies.tika ++
Dependencies.fs2 ++
Dependencies.databases ++
Dependencies.flyway ++
Dependencies.loggingApi
)
).dependsOn(common)
val text = project.in(file("modules/text")).
enablePlugins(NerModelsPlugin).
settings(sharedSettings).
settings(testSettings).
settings(NerModelsPlugin.nerClassifierSettings).
settings(
name := "docspell-text",
libraryDependencies ++=
Dependencies.fs2 ++
Dependencies.tika ++
Dependencies.stanfordNlpCore
).dependsOn(common)
val restapi = project.in(file("modules/restapi")).
enablePlugins(OpenApiSchema).
settings(sharedSettings).
settings(testSettings).
settings(openapiScalaSettings).
settings(
name := "docspell-restapi",
libraryDependencies ++=
@ -113,22 +175,21 @@ val restapi = project.in(file("modules/restapi")).
openapiTargetLanguage := Language.Scala,
openapiPackage := Pkg("docspell.restapi.model"),
openapiSpec := (Compile/resourceDirectory).value/"docspell-openapi.yml",
openapiScalaConfig := ScalaConfig().withJson(ScalaJson.circeSemiauto)
)
).dependsOn(common)
val joexapi = project.in(file("modules/joexapi")).
enablePlugins(OpenApiSchema).
settings(sharedSettings).
settings(testSettings).
settings(openapiScalaSettings).
settings(
name := "docspell-joexapi",
libraryDependencies ++=
Dependencies.circe,
openapiTargetLanguage := Language.Scala,
openapiPackage := Pkg("docspell.joexapi.model"),
openapiSpec := (Compile/resourceDirectory).value/"joex-openapi.yml",
openapiScalaConfig := ScalaConfig().withJson(ScalaJson.circeSemiauto)
)
openapiSpec := (Compile/resourceDirectory).value/"joex-openapi.yml"
).dependsOn(common)
val joex = project.in(file("modules/joex")).
enablePlugins(BuildInfoPlugin
@ -137,7 +198,7 @@ val joex = project.in(file("modules/joex")).
, SystemdPlugin).
settings(sharedSettings).
settings(testSettings).
settings(debianSettings).
settings(debianSettings("docspell-joex")).
settings(buildInfoSettings).
settings(
name := "docspell-joex",
@ -147,11 +208,12 @@ val joex = project.in(file("modules/joex")).
Dependencies.circe ++
Dependencies.pureconfig ++
Dependencies.loggingApi ++
Dependencies.logging,
Dependencies.logging.map(_ % Runtime),
addCompilerPlugin(Dependencies.kindProjectorPlugin),
addCompilerPlugin(Dependencies.betterMonadicFor),
buildInfoPackage := "docspell.joex"
).dependsOn(store, joexapi, restapi)
buildInfoPackage := "docspell.joex",
reStart/javaOptions ++= Seq(s"-Dconfig.file=${(LocalRootProject/baseDirectory).value/"dev.conf"}")
).dependsOn(store, text, joexapi, restapi)
val backend = project.in(file("modules/backend")).
settings(sharedSettings).
@ -160,7 +222,9 @@ val backend = project.in(file("modules/backend")).
name := "docspell-backend",
libraryDependencies ++=
Dependencies.loggingApi ++
Dependencies.fs2
Dependencies.fs2 ++
Dependencies.bcrypt ++
Dependencies.http4sClient
).dependsOn(store)
val webapp = project.in(file("modules/webapp")).
@ -183,7 +247,7 @@ val restserver = project.in(file("modules/restserver")).
, SystemdPlugin).
settings(sharedSettings).
settings(testSettings).
settings(debianSettings).
settings(debianSettings("docspell-server")).
settings(buildInfoSettings).
settings(
name := "docspell-restserver",
@ -194,39 +258,122 @@ val restserver = project.in(file("modules/restserver")).
Dependencies.yamusca ++
Dependencies.webjars ++
Dependencies.loggingApi ++
Dependencies.logging,
Dependencies.logging.map(_ % Runtime),
addCompilerPlugin(Dependencies.kindProjectorPlugin),
addCompilerPlugin(Dependencies.betterMonadicFor),
buildInfoPackage := "docspell.restserver",
Compile/sourceGenerators += (Def.task {
Compile/sourceGenerators += Def.task {
createWebjarSource(Dependencies.webjars, (Compile/sourceManaged).value)
}).taskValue,
Compile/unmanagedResourceDirectories ++= Seq((Compile/resourceDirectory).value.getParentFile/"templates")
}.taskValue,
Compile/resourceGenerators += Def.task {
copyWebjarResources(Seq((restapi/Compile/resourceDirectory).value/"docspell-openapi.yml")
, (Compile/resourceManaged).value
, name.value
, version.value
, streams.value.log)
}.taskValue,
Compile/unmanagedResourceDirectories ++= Seq((Compile/resourceDirectory).value.getParentFile/"templates"),
reStart/javaOptions ++= Seq(s"-Dconfig.file=${(LocalRootProject/baseDirectory).value/"dev.conf"}")
).dependsOn(restapi, joexapi, backend, webapp)
val microsite = project.in(file("modules/microsite")).
enablePlugins(MicrositesPlugin).
settings(sharedSettings).
settings(
name := "docspell-microsite",
publishArtifact := false,
scalacOptions -= "-Yno-imports",
scalacOptions ~= { _ filterNot (_ startsWith "-Ywarn") },
scalacOptions ~= { _ filterNot (_ startsWith "-Xlint") },
scalaVersion := "2.12.9",
skip in publish := true,
micrositeFooterText := Some(
"""
|<p>&copy; 2019 <a href="https://github.com/eikek/docspell">Docspell, v{{site.version}}</a></p>
|""".stripMargin
),
micrositeName := "Docspell",
micrositeDescription := "Docspell – A Document Organizer",
micrositeBaseUrl := "/docspell",
micrositeAuthor := "eikek",
micrositeGithubOwner := "eikek",
micrositeGithubRepo := "docspell",
micrositeGitterChannel := false,
micrositeFavicons := Seq(microsites.MicrositeFavicon("favicon.png", "96x96")),
micrositeShareOnSocial := false,
micrositeHighlightLanguages ++= Seq("json", "javascript"),
micrositePalette := Map(
"brand-primary" -> "#5d000a", // link color
"brand-secondary" -> "#172651", //sidebar background
"brand-tertiary" -> "#495680", //main brand background
"gray-dark" -> "#050913", //header font color
"gray" -> "#131f43", //font color
"gray-light" -> "#E3E2E3",
"gray-lighter" -> "#f8fbff", //body background
"white-color" -> "#FFFFFF"),
fork in tut := true,
scalacOptions in Tut ~= (_.filterNot(Set("-Ywarn-unused-import", "-Ywarn-dead-code", "-Werror"))),
resourceGenerators in Tut += Def.task {
val conf1 = (resourceDirectory in (restserver, Compile)).value / "reference.conf"
val conf2 = (resourceDirectory in (joex, Compile)).value / "reference.conf"
val out1 = resourceManaged.value/"main"/"jekyll"/"_includes"/"server.conf"
val out2 = resourceManaged.value/"main"/"jekyll"/"_includes"/"joex.conf"
streams.value.log.info(s"Copying reference.conf: $conf1 -> $out1, $conf2 -> $out2")
IO.write(out1, "{% raw %}\n")
IO.append(out1, IO.readBytes(conf1))
IO.write(out1, "\n{% endraw %}", append = true)
IO.write(out2, "{% raw %}\n")
IO.append(out2, IO.readBytes(conf2))
IO.write(out2, "\n{% endraw %}", append = true)
val oa1 = (resourceDirectory in (restapi, Compile)).value/"docspell-openapi.yml"
val oaout = resourceManaged.value/"main"/"jekyll"/"openapi"/"docspell-openapi.yml"
IO.copy(Seq(oa1 -> oaout))
Seq(out1, out2, oaout)
}.taskValue,
resourceGenerators in Tut += Def.task {
val staticDoc = (restapi/Compile/openapiStaticDoc).value
val target = resourceManaged.value/"main"/"jekyll"/"openapi"/"docspell-openapi.html"
IO.copy(Seq(staticDoc -> target))
Seq(target)
}.taskValue,
micrositeCompilingDocsTool := WithTut //WithMdoc
// mdocIn := sourceDirectory.value / "main" / "tut"
)
val root = project.in(file(".")).
settings(sharedSettings).
settings(
name := "docspell-root"
).
aggregate(common, store, joexapi, joex, backend, webapp, restapi, restserver)
aggregate(common
, text
, store
, joexapi
, joex
, backend
, webapp
, restapi
, restserver
, microsite)
// --- helpers
def copyWebjarResources(src: Seq[File], base: File, artifact: String, version: String, logger: Logger): Seq[File] = {
val targetDir = base/"META-INF"/"resources"/"webjars"/artifact/version
logger.info(s"Copy webjar resources from ${src.size} files/directories.")
src.flatMap { dir =>
if (dir.isDirectory) {
val files = (dir ** "*").filter(_.isFile).get pair Path.relativeTo(dir)
files.map { case (f, name) =>
val target = targetDir/name
logger.info(s"Copy $f -> $target")
IO.createDirectories(Seq(target.getParentFile))
IO.copy(Seq(f -> target))
target
}
} else {
val target = targetDir/dir.name
logger.info(s"Copy $dir -> $target")
IO.createDirectories(Seq(target.getParentFile))
IO.copy(Seq(dir -> target))
Seq(target)
@ -255,3 +402,9 @@ def createWebjarSource(wj: Seq[ModuleID], out: File): Seq[File] = {
IO.write(target, content)
Seq(target)
}
addCommandAlias("make", ";root/openapiCodegen ;root/test:compile")
addCommandAlias("make-zip", ";restserver/universal:packageBin ;joex/universal:packageBin")
addCommandAlias("make-deb", ";restserver/debian:packageBin ;joex/debian:packageBin")
addCommandAlias("make-pkg", ";make-zip ;make-deb")

110
doc/dev.md
View File

@ -1,110 +0,0 @@
# Development Documentation
## initial thoughts
* First there is a web app, where user can login, look at their
documents etc
* User can do queries and edit document meta data
* User can manage upload endpoints
Upload endpoints allow to receive "items". There are the following
different options:
1. Upload a single item by uploading one file.
2. Upload a single item by uploading a zip file.
3. Upload multiple items by uploading a zip file (one entry = one
item)
Files are received and stored in the database, always. Only if a size
constraint is not fulfilled the response is an error. Files are marked
as `RECEIVED`. Idea is that most files are valid, so are saved
anyways.
Then a job for a new item is inserted into the processing queue and
processing begins eventually.
External processes access the queue on the same database and take jobs
for processing.
Processing:
1. check mimetype and error if not supported
- want to use the servers mimetype instead of advertised one from
the client
2. extract text and other meta data
3. do some analysis
4. tag item/set meta data
5. encrypt files + text, if configured
If an error occurs, it can be inspected in the "queue screen". The web
app shows notifications in this case. User can download the file and
remove it. Otherwise, files will be deleted after some period. Errors
are also counted per source, so one can decide whether to block a
source.
Once processing is done, the item is put in the INBOX.
## Modules
### processor
### backend
### store
### backend server
### webapp
## Flow
1. webapp: calls rest route
2. server:
1. convert json -> data
2. choose backend operation
3. backend: execute logic
1. store: load or save from/to db
4. server:
1. convert data -> json
backend:
- need better name
- contains all logic encoded as operations
- operation: A -> Either[E, B]
- middleware translates userId -> required data
- e.g. userId -> public key
- operations can fail
- common error class is used
- can be converted to json easily
New Items:
1. upload endpoint
2. server:
1. convert json->data
3. store: add job to queue
4. processor:
1. eventually takes the job
2. execute job
3. notify about result
Processors
- multiple processors possible
- multiple backend servers possible
- separate processes
- register on database
- unique id
- url
- servers and processors
- once a job is added to the queue notify all processors
- take all registered urls from db
- call them, skip failing ones
- processors wake up and take next job based on their config
- first free processor gets a new job
- once done, notify registered backend server

1
doc/install.md
View File

@ -1 +0,0 @@
# Installation and Setup

69
doc/user.md
View File

@ -1,69 +0,0 @@
# User Documentation
## Concepts
## UI Screens
The web application is the provided user interface. THere are the following screens
### Login
### Change Password
### Document Overview
- search menu on the left, 25%
- listing in the middle, 25%
- choose to list all documents
- or grouped by date, corresp. etc
- right: document preview + details, 50%
### Document Edit
- search menu + listing is replaced by edit screen, 50%
- document preview 50%
### Manage Additional Data
CRUD for
- Organisation
- Person
- Equipment
- Sources, which are the possible upload endpoints.
### Collective Settings
- keystore
- collective data
- manage users
### User Settings
- preferences (language, ...)
- smtp servers
### Super Settings
- admin only
- enable/disable registration
- settings for the app and collectives
- e.g. can block collectives or users
- CRUD for all entities
### Collective Processing Queue
- user can inspect current processing
- see errors and progress
- see jobs in queue
- cancel jobs
- see some stats about executors, so one can make an educated guess as
to when the next job is executed
### Admin Processing Queue
- see which external processing workers are registered
- cancel/pause jobs
- some stats

14
elm.json
View File

@ -7,18 +7,26 @@
"elm-version": "0.19.0",
"dependencies": {
"direct": {
"CurrySoftware/elm-datepicker": "3.1.0",
"NoRedInk/elm-json-decode-pipeline": "1.0.0",
"NoRedInk/elm-simple-fuzzy": "1.0.3",
"elm/browser": "1.0.1",
"elm/core": "1.0.2",
"elm/file": "1.0.5",
"elm/html": "1.0.0",
"elm/http": "2.0.0",
"elm/json": "1.1.3",
"elm/url": "1.0.0"
"elm/time": "1.0.0",
"elm/url": "1.0.0",
"elm-explorations/markdown": "1.0.0",
"justinmimbs/date": "3.1.2",
"ryannhg/date-format": "2.3.0",
"truqu/elm-base64": "2.0.4"
},
"indirect": {
"elm/bytes": "1.0.8",
"elm/file": "1.0.5",
"elm/time": "1.0.0",
"elm/parser": "1.1.0",
"elm/regex": "1.0.0",
"elm/virtual-dom": "1.0.2"
}
},

66
modules/backend/src/main/scala/docspell/backend/BackendApp.scala Normal file
View File

@ -0,0 +1,66 @@
package docspell.backend
import cats.effect.{Blocker, ConcurrentEffect, ContextShift, Resource}
import docspell.backend.auth.Login
import docspell.backend.ops._
import docspell.backend.signup.OSignup
import docspell.store.Store
import docspell.store.ops.ONode
import docspell.store.queue.JobQueue
import scala.concurrent.ExecutionContext
trait BackendApp[F[_]] {
def login: Login[F]
def signup: OSignup[F]
def collective: OCollective[F]
def source: OSource[F]
def tag: OTag[F]
def equipment: OEquipment[F]
def organization: OOrganization[F]
def upload: OUpload[F]
def node: ONode[F]
def job: OJob[F]
def item: OItem[F]
}
object BackendApp {
def create[F[_]: ConcurrentEffect](cfg: Config, store: Store[F], httpClientEc: ExecutionContext): Resource[F, BackendApp[F]] =
for {
queue <- JobQueue(store)
loginImpl <- Login[F](store)
signupImpl <- OSignup[F](store)
collImpl <- OCollective[F](store)
sourceImpl <- OSource[F](store)
tagImpl <- OTag[F](store)
equipImpl <- OEquipment[F](store)
orgImpl <- OOrganization(store)
uploadImpl <- OUpload(store, queue, cfg, httpClientEc)
nodeImpl <- ONode(store)
jobImpl <- OJob(store, httpClientEc)
itemImpl <- OItem(store)
} yield new BackendApp[F] {
val login: Login[F] = loginImpl
val signup: OSignup[F] = signupImpl
val collective: OCollective[F] = collImpl
val source = sourceImpl
val tag = tagImpl
val equipment = equipImpl
val organization = orgImpl
val upload = uploadImpl
val node = nodeImpl
val job = jobImpl
val item = itemImpl
}
def apply[F[_]: ConcurrentEffect: ContextShift](cfg: Config
, connectEC: ExecutionContext
, httpClientEc: ExecutionContext
, blocker: Blocker): Resource[F, BackendApp[F]] =
for {
store <- Store.create(cfg.jdbc, connectEC, blocker)
backend <- create(cfg, store, httpClientEc)
} yield backend
}

10
modules/backend/src/main/scala/docspell/backend/Common.scala Normal file
View File

@ -0,0 +1,10 @@
package docspell.backend
import cats.effect._
import org.mindrot.jbcrypt.BCrypt
object Common {
def genSaltString[F[_]: Sync]: F[String] =
Sync[F].delay(BCrypt.gensalt())
}

16
modules/backend/src/main/scala/docspell/backend/Config.scala Normal file
View File

@ -0,0 +1,16 @@
package docspell.backend
import docspell.backend.signup.{Config => SignupConfig}
import docspell.common.MimeType
import docspell.store.JdbcConfig
case class Config( jdbc: JdbcConfig
, signup: SignupConfig
, files: Config.Files) {
}
object Config {
case class Files(chunkSize: Int, validMimeTypes: Seq[MimeType])
}

13
modules/backend/src/main/scala/docspell/backend/PasswordCrypt.scala Normal file
View File

@ -0,0 +1,13 @@
package docspell.backend
import docspell.common.Password
import org.mindrot.jbcrypt.BCrypt
object PasswordCrypt {
def crypt(pass: Password): Password =
Password(BCrypt.hashpw(pass.pass, BCrypt.gensalt()))
def check(plain: Password, hashed: Password): Boolean =
BCrypt.checkpw(plain.pass, hashed.pass)
}

81
modules/backend/src/main/scala/docspell/backend/auth/AuthToken.scala Normal file
View File

@ -0,0 +1,81 @@
package docspell.backend.auth
import cats.effect._
import cats.implicits._
import java.time.Instant
import javax.crypto.Mac
import javax.crypto.spec.SecretKeySpec
import scodec.bits.ByteVector
import docspell.backend.Common
import AuthToken._
import docspell.common._
case class AuthToken(millis: Long, account: AccountId, salt: String, sig: String) {
def asString = s"$millis-${b64enc(account.asString)}-$salt-$sig"
def sigValid(key: ByteVector): Boolean = {
val newSig = AuthToken.sign(this, key)
AuthToken.constTimeEq(sig, newSig)
}
def sigInvalid(key: ByteVector): Boolean =
!sigValid(key)
def notExpired(validity: Duration): Boolean =
!isExpired(validity)
def isExpired(validity: Duration): Boolean = {
val ends = Instant.ofEpochMilli(millis).plusMillis(validity.millis)
Instant.now.isAfter(ends)
}
def validate(key: ByteVector, validity: Duration): Boolean =
sigValid(key) && notExpired(validity)
}
object AuthToken {
private val utf8 = java.nio.charset.StandardCharsets.UTF_8
def fromString(s: String): Either[String, AuthToken] =
s.split("\\-", 4) match {
case Array(ms, as, salt, sig) =>
for {
millis <- asInt(ms).toRight("Cannot read authenticator data")
acc <- b64dec(as).toRight("Cannot read authenticator data")
accId <- AccountId.parse(acc)
} yield AuthToken(millis, accId, salt, sig)
case _ =>
Left("Invalid authenticator")
}
def user[F[_]: Sync](accountId: AccountId, key: ByteVector): F[AuthToken] = {
for {
salt <- Common.genSaltString[F]
millis = Instant.now.toEpochMilli
cd = AuthToken(millis, accountId, salt, "")
sig = sign(cd, key)
} yield cd.copy(sig = sig)
}
private def sign(cd: AuthToken, key: ByteVector): String = {
val raw = cd.millis.toString + cd.account.asString + cd.salt
val mac = Mac.getInstance("HmacSHA1")
mac.init(new SecretKeySpec(key.toArray, "HmacSHA1"))
ByteVector.view(mac.doFinal(raw.getBytes(utf8))).toBase64
}
private def b64enc(s: String): String =
ByteVector.view(s.getBytes(utf8)).toBase64
private def b64dec(s: String): Option[String] =
ByteVector.fromValidBase64(s).decodeUtf8.toOption
private def asInt(s: String): Option[Long] =
Either.catchNonFatal(s.toLong).toOption
private def constTimeEq(s1: String, s2: String): Boolean =
s1.zip(s2).foldLeft(true)({ case (r, (c1, c2)) => r & c1 == c2 }) & s1.length == s2.length
}

89
modules/backend/src/main/scala/docspell/backend/auth/Login.scala Normal file
View File

@ -0,0 +1,89 @@
package docspell.backend.auth
import cats.effect._
import cats.implicits._
import Login._
import docspell.common._
import docspell.store.Store
import docspell.store.queries.QLogin
import docspell.store.records.RUser
import org.mindrot.jbcrypt.BCrypt
import scodec.bits.ByteVector
import org.log4s._
trait Login[F[_]] {
def loginSession(config: Config)(sessionKey: String): F[Result]
def loginUserPass(config: Config)(up: UserPass): F[Result]
}
object Login {
private[this] val logger = getLogger
case class Config(serverSecret: ByteVector, sessionValid: Duration)
case class UserPass(user: String, pass: String) {
def hidePass: UserPass =
if (pass.isEmpty) copy(pass = "<none>")
else copy(pass = "***")
}
sealed trait Result {
def toEither: Either[String, AuthToken]
}
object Result {
case class Ok(session: AuthToken) extends Result {
val toEither = Right(session)
}
case object InvalidAuth extends Result {
val toEither = Left("Authentication failed.")
}
case object InvalidTime extends Result {
val toEither = Left("Authentication failed.")
}
def ok(session: AuthToken): Result = Ok(session)
def invalidAuth: Result = InvalidAuth
def invalidTime: Result = InvalidTime
}
def apply[F[_]: Effect](store: Store[F]): Resource[F, Login[F]] = Resource.pure(new Login[F] {
def loginSession(config: Config)(sessionKey: String): F[Result] =
AuthToken.fromString(sessionKey) match {
case Right(at) =>
if (at.sigInvalid(config.serverSecret)) Result.invalidAuth.pure[F]
else if (at.isExpired(config.sessionValid)) Result.invalidTime.pure[F]
else Result.ok(at).pure[F]
case Left(err) =>
Result.invalidAuth.pure[F]
}
def loginUserPass(config: Config)(up: UserPass): F[Result] = {
AccountId.parse(up.user) match {
case Right(acc) =>
val okResult=
store.transact(RUser.updateLogin(acc)) *>
AuthToken.user(acc, config.serverSecret).map(Result.ok)
for {
data <- store.transact(QLogin.findUser(acc))
_ <- Sync[F].delay(logger.trace(s"Account lookup: $data"))
res <- if (data.exists(check(up.pass))) okResult
else Result.invalidAuth.pure[F]
} yield res
case Left(err) =>
Result.invalidAuth.pure[F]
}
}
private def check(given: String)(data: QLogin.Data): Boolean = {
val collOk = data.collectiveState == CollectiveState.Active ||
data.collectiveState == CollectiveState.ReadOnly
val userOk = data.userState == UserState.Active
val passOk = BCrypt.checkpw(given, data.password.pass)
collOk && userOk && passOk
}
})
}

111
modules/backend/src/main/scala/docspell/backend/ops/OCollective.scala Normal file
View File

@ -0,0 +1,111 @@
package docspell.backend.ops
import cats.implicits._
import cats.effect.{Effect, Resource}
import docspell.common._
import docspell.store.{AddResult, Store}
import docspell.store.records.{RCollective, RUser}
import OCollective._
import docspell.backend.PasswordCrypt
import docspell.store.queries.QCollective
trait OCollective[F[_]] {
def find(name: Ident): F[Option[RCollective]]
def updateLanguage(collective: Ident, lang: Language): F[AddResult]
def listUser(collective: Ident): F[Vector[RUser]]
def add(s: RUser): F[AddResult]
def update(s: RUser): F[AddResult]
def deleteUser(login: Ident, collective: Ident): F[AddResult]
def insights(collective: Ident): F[InsightData]
def changePassword(accountId: AccountId, current: Password, newPass: Password): F[PassChangeResult]
}
object OCollective {
type InsightData = QCollective.InsightData
val insightData = QCollective.InsightData
sealed trait PassChangeResult
object PassChangeResult {
case object UserNotFound extends PassChangeResult
case object PasswordMismatch extends PassChangeResult
case object UpdateFailed extends PassChangeResult
case object Success extends PassChangeResult
def userNotFound: PassChangeResult = UserNotFound
def passwordMismatch: PassChangeResult = PasswordMismatch
def success: PassChangeResult = Success
def updateFailed: PassChangeResult = UpdateFailed
}
case class RegisterData(collName: Ident, login: Ident, password: Password, invite: Option[Ident])
sealed trait RegisterResult {
def toEither: Either[Throwable, Unit]
}
object RegisterResult {
case object Success extends RegisterResult {
val toEither = Right(())
}
case class CollectiveExists(id: Ident) extends RegisterResult {
val toEither = Left(new Exception())
}
case class Error(ex: Throwable) extends RegisterResult {
val toEither = Left(ex)
}
}
def apply[F[_]:Effect](store: Store[F]): Resource[F, OCollective[F]] =
Resource.pure(new OCollective[F] {
def find(name: Ident): F[Option[RCollective]] =
store.transact(RCollective.findById(name))
def updateLanguage(collective: Ident, lang: Language): F[AddResult] =
store.transact(RCollective.updateLanguage(collective, lang)).
attempt.map(AddResult.fromUpdate)
def listUser(collective: Ident): F[Vector[RUser]] = {
store.transact(RUser.findAll(collective, _.login))
}
def add(s: RUser): F[AddResult] =
store.add(RUser.insert(s.copy(password = PasswordCrypt.crypt(s.password))), RUser.exists(s.login))
def update(s: RUser): F[AddResult] =
store.add(RUser.update(s), RUser.exists(s.login))
def deleteUser(login: Ident, collective: Ident): F[AddResult] =
store.transact(RUser.delete(login, collective)).
attempt.map(AddResult.fromUpdate)
def insights(collective: Ident): F[InsightData] =
store.transact(QCollective.getInsights(collective))
def changePassword(accountId: AccountId, current: Password, newPass: Password): F[PassChangeResult] = {
val q = for {
optUser <- RUser.findByAccount(accountId)
check = optUser.map(_.password).map(p => PasswordCrypt.check(current, p))
n <- check.filter(identity).traverse(_ => RUser.updatePassword(accountId, PasswordCrypt.crypt(newPass)))
res = check match {
case Some(true) =>
if (n.getOrElse(0) > 0) PassChangeResult.success else PassChangeResult.updateFailed
case Some(false) =>
PassChangeResult.passwordMismatch
case None =>
PassChangeResult.userNotFound
}
} yield res
store.transact(q)
}
})
}

54
modules/backend/src/main/scala/docspell/backend/ops/OEquipment.scala Normal file
View File

@ -0,0 +1,54 @@
package docspell.backend.ops
import cats.implicits._
import cats.effect.{Effect, Resource}
import docspell.common.{AccountId, Ident}
import docspell.store.{AddResult, Store}
import docspell.store.records.{REquipment, RItem}
trait OEquipment[F[_]] {
def findAll(account: AccountId): F[Vector[REquipment]]
def add(s: REquipment): F[AddResult]
def update(s: REquipment): F[AddResult]
def delete(id: Ident, collective: Ident): F[AddResult]
}
object OEquipment {
def apply[F[_]: Effect](store: Store[F]): Resource[F, OEquipment[F]] =
Resource.pure(new OEquipment[F] {
def findAll(account: AccountId): F[Vector[REquipment]] =
store.transact(REquipment.findAll(account.collective, _.name))
def add(e: REquipment): F[AddResult] = {
def insert = REquipment.insert(e)
def exists = REquipment.existsByName(e.cid, e.name)
val msg = s"An equipment '${e.name}' already exists"
store.add(insert, exists).map(_.fold(identity, _.withMsg(msg), identity))
}
def update(e: REquipment): F[AddResult] = {
def insert = REquipment.update(e)
def exists = REquipment.existsByName(e.cid, e.name)
val msg = s"An equipment '${e.name}' already exists"
store.add(insert, exists).map(_.fold(identity, _.withMsg(msg), identity))
}
def delete(id: Ident, collective: Ident): F[AddResult] = {
val io = for {
n0 <- RItem.removeConcEquip(collective, id)
n1 <- REquipment.delete(id, collective)
} yield n0 + n1
store.transact(io).
attempt.
map(AddResult.fromUpdate)
}
})
}

159
modules/backend/src/main/scala/docspell/backend/ops/OItem.scala Normal file
View File

@ -0,0 +1,159 @@
package docspell.backend.ops
import fs2.Stream
import cats.implicits._
import cats.effect.{Effect, Resource}
import doobie._
import doobie.implicits._
import docspell.store.{AddResult, Store}
import docspell.store.queries.{QAttachment, QItem}
import OItem.{AttachmentData, ItemData, ListItem, Query}
import bitpeace.{FileMeta, RangeDef}
import docspell.common.{Direction, Ident, ItemState, MetaProposalList, Timestamp}
import docspell.store.records.{RAttachment, RAttachmentMeta, RItem, RTagItem}
trait OItem[F[_]] {
def findItem(id: Ident, collective: Ident): F[Option[ItemData]]
def findItems(q: Query, maxResults: Int): F[Vector[ListItem]]
def findAttachment(id: Ident, collective: Ident): F[Option[AttachmentData[F]]]
def setTags(item: Ident, tagIds: List[Ident], collective: Ident): F[AddResult]
def setDirection(item: Ident, direction: Direction, collective: Ident): F[AddResult]
def setCorrOrg(item: Ident, org: Option[Ident], collective: Ident): F[AddResult]
def setCorrPerson(item: Ident, person: Option[Ident], collective: Ident): F[AddResult]
def setConcPerson(item: Ident, person: Option[Ident], collective: Ident): F[AddResult]
def setConcEquip(item: Ident, equip: Option[Ident], collective: Ident): F[AddResult]
def setNotes(item: Ident, notes: Option[String], collective: Ident): F[AddResult]
def setName(item: Ident, notes: String, collective: Ident): F[AddResult]
def setState(item: Ident, state: ItemState, collective: Ident): F[AddResult]
def setItemDate(item: Ident, date: Option[Timestamp], collective: Ident): F[AddResult]
def setItemDueDate(item: Ident, date: Option[Timestamp], collective: Ident): F[AddResult]
def getProposals(item: Ident, collective: Ident): F[MetaProposalList]
def delete(itemId: Ident, collective: Ident): F[Int]
def findAttachmentMeta(id: Ident, collective: Ident): F[Option[RAttachmentMeta]]
}
object OItem {
type Query = QItem.Query
val Query = QItem.Query
type ListItem = QItem.ListItem
val ListItem = QItem.ListItem
type ItemData = QItem.ItemData
val ItemData = QItem.ItemData
case class AttachmentData[F[_]](ra: RAttachment, meta: FileMeta, data: Stream[F, Byte])
def apply[F[_]: Effect](store: Store[F]): Resource[F, OItem[F]] =
Resource.pure(new OItem[F] {
def findItem(id: Ident, collective: Ident): F[Option[ItemData]] =
store.transact(QItem.findItem(id)).
map(opt => opt.flatMap(_.filterCollective(collective)))
def findItems(q: Query, maxResults: Int): F[Vector[ListItem]] = {
store.transact(QItem.findItems(q).take(maxResults.toLong)).compile.toVector
}
def findAttachment(id: Ident, collective: Ident): F[Option[AttachmentData[F]]] = {
store.transact(RAttachment.findByIdAndCollective(id, collective)).
flatMap({
case Some(ra) =>
store.bitpeace.get(ra.fileId.id).unNoneTerminate.compile.last.
map(_.map(m => AttachmentData[F](ra, m, store.bitpeace.fetchData2(RangeDef.all)(Stream.emit(m)))))
case None =>
(None: Option[AttachmentData[F]]).pure[F]
})
}
def setTags(item: Ident, tagIds: List[Ident], collective: Ident): F[AddResult] = {
val db = for {
cid <- RItem.getCollective(item)
nd <- if (cid.contains(collective)) RTagItem.deleteItemTags(item) else 0.pure[ConnectionIO]
ni <- if (tagIds.nonEmpty && cid.contains(collective)) RTagItem.insertItemTags(item, tagIds) else 0.pure[ConnectionIO]
} yield nd + ni
store.transact(db).
attempt.
map(AddResult.fromUpdate)
}
def setDirection(item: Ident, direction: Direction, collective: Ident): F[AddResult] =
store.transact(RItem.updateDirection(item, collective, direction)).
attempt.
map(AddResult.fromUpdate)
def setCorrOrg(item: Ident, org: Option[Ident], collective: Ident): F[AddResult] =
store.transact(RItem.updateCorrOrg(item, collective, org)).
attempt.
map(AddResult.fromUpdate)
def setCorrPerson(item: Ident, person: Option[Ident], collective: Ident): F[AddResult] =
store.transact(RItem.updateCorrPerson(item, collective, person)).
attempt.
map(AddResult.fromUpdate)
def setConcPerson(item: Ident, person: Option[Ident], collective: Ident): F[AddResult] =
store.transact(RItem.updateConcPerson(item, collective, person)).
attempt.
map(AddResult.fromUpdate)
def setConcEquip(item: Ident, equip: Option[Ident], collective: Ident): F[AddResult] =
store.transact(RItem.updateConcEquip(item, collective, equip)).
attempt.
map(AddResult.fromUpdate)
def setNotes(item: Ident, notes: Option[String], collective: Ident): F[AddResult] =
store.transact(RItem.updateNotes(item, collective, notes)).
attempt.
map(AddResult.fromUpdate)
def setName(item: Ident, name: String, collective: Ident): F[AddResult] =
store.transact(RItem.updateName(item, collective, name)).
attempt.
map(AddResult.fromUpdate)
def setState(item: Ident, state: ItemState, collective: Ident): F[AddResult] =
store.transact(RItem.updateStateForCollective(item, state, collective)).
attempt.
map(AddResult.fromUpdate)
def setItemDate(item: Ident, date: Option[Timestamp], collective: Ident): F[AddResult] =
store.transact(RItem.updateDate(item, collective, date)).
attempt.
map(AddResult.fromUpdate)
def setItemDueDate(item: Ident, date: Option[Timestamp], collective: Ident): F[AddResult] =
store.transact(RItem.updateDueDate(item, collective, date)).
attempt.
map(AddResult.fromUpdate)
def delete(itemId: Ident, collective: Ident): F[Int] =
QItem.delete(store)(itemId, collective)
def getProposals(item: Ident, collective: Ident): F[MetaProposalList] =
store.transact(QAttachment.getMetaProposals(item, collective))
def findAttachmentMeta(id: Ident, collective: Ident): F[Option[RAttachmentMeta]] =
store.transact(QAttachment.getAttachmentMeta(id, collective))
})
}

84
modules/backend/src/main/scala/docspell/backend/ops/OJob.scala Normal file
View File

@ -0,0 +1,84 @@
package docspell.backend.ops
import cats.implicits._
import cats.effect.{ConcurrentEffect, Resource}
import docspell.backend.ops.OJob.{CollectiveQueueState, JobCancelResult}
import docspell.common.{Ident, JobState}
import docspell.store.Store
import docspell.store.queries.QJob
import docspell.store.records.{RJob, RJobLog}
import scala.concurrent.ExecutionContext
trait OJob[F[_]] {
def queueState(collective: Ident, maxResults: Int): F[CollectiveQueueState]
def cancelJob(id: Ident, collective: Ident): F[JobCancelResult]
}
object OJob {
sealed trait JobCancelResult
object JobCancelResult {
case object Removed extends JobCancelResult
case object CancelRequested extends JobCancelResult
case object JobNotFound extends JobCancelResult
}
case class JobDetail(job: RJob, logs: Vector[RJobLog])
case class CollectiveQueueState(jobs: Vector[JobDetail]) {
def queued: Vector[JobDetail] =
jobs.filter(r => JobState.queued.contains(r.job.state))
def done: Vector[JobDetail] =
jobs.filter(r => JobState.done.contains(r.job.state))
def running: Vector[JobDetail] =
jobs.filter(_.job.state == JobState.Running)
}
def apply[F[_]: ConcurrentEffect](store: Store[F], clientEC: ExecutionContext): Resource[F, OJob[F]] =
Resource.pure(new OJob[F] {
def queueState(collective: Ident, maxResults: Int): F[CollectiveQueueState] = {
store.transact(QJob.queueStateSnapshot(collective).take(maxResults.toLong)).
map(t => JobDetail(t._1, t._2)).
compile.toVector.
map(CollectiveQueueState)
}
def cancelJob(id: Ident, collective: Ident): F[JobCancelResult] = {
def mustCancel(job: Option[RJob]): Option[(RJob, Ident)] =
for {
worker <- job.flatMap(_.worker)
job <- job.filter(j => j.state == JobState.Scheduled || j.state == JobState.Running)
} yield (job, worker)
def canDelete(j: RJob): Boolean =
mustCancel(j.some).isEmpty
val tryDelete = for {
job <- RJob.findByIdAndGroup(id, collective)
jobm = job.filter(canDelete)
del <- jobm.traverse(j => RJob.delete(j.id))
} yield del match {
case Some(n) => Right(JobCancelResult.Removed: JobCancelResult)
case None => Left(mustCancel(job))
}
def tryCancel(job: RJob, worker: Ident): F[JobCancelResult] =
OJoex.cancelJob(job.id, worker, store, clientEC).
map(flag => if (flag) JobCancelResult.CancelRequested else JobCancelResult.JobNotFound)
for {
tryDel <- store.transact(tryDelete)
result <- tryDel match {
case Right(r) => r.pure[F]
case Left(Some((job, worker))) =>
tryCancel(job, worker)
case Left(None) =>
(JobCancelResult.JobNotFound: OJob.JobCancelResult).pure[F]
}
} yield result
}
})
}

54
modules/backend/src/main/scala/docspell/backend/ops/OJoex.scala Normal file
View File

@ -0,0 +1,54 @@
package docspell.backend.ops
import cats.implicits._
import cats.effect.ConcurrentEffect
import docspell.common.{Ident, NodeType}
import docspell.store.Store
import docspell.store.records.RNode
import org.http4s.client.blaze.BlazeClientBuilder
import org.http4s.Method._
import org.http4s.{Request, Uri}
import scala.concurrent.ExecutionContext
import org.log4s._
object OJoex {
private [this] val logger = getLogger
def notifyAll[F[_]: ConcurrentEffect](store: Store[F], clientExecutionContext: ExecutionContext): F[Unit] = {
for {
nodes <- store.transact(RNode.findAll(NodeType.Joex))
_ <- nodes.toList.traverse(notifyJoex[F](clientExecutionContext))
} yield ()
}
def cancelJob[F[_]: ConcurrentEffect](jobId: Ident, worker: Ident, store: Store[F], clientEc: ExecutionContext): F[Boolean] =
for {
node <- store.transact(RNode.findById(worker))
cancel <- node.traverse(joexCancel(clientEc)(_, jobId))
} yield cancel.getOrElse(false)
private def joexCancel[F[_]: ConcurrentEffect](ec: ExecutionContext)(node: RNode, job: Ident): F[Boolean] = {
val notifyUrl = node.url/"api"/"v1"/"job"/job.id/"cancel"
BlazeClientBuilder[F](ec).resource.use { client =>
val req = Request[F](POST, Uri.unsafeFromString(notifyUrl.asString))
client.expect[String](req).map(_ => true)
}
}
private def notifyJoex[F[_]: ConcurrentEffect](ec: ExecutionContext)(node: RNode): F[Unit] = {
val notifyUrl = node.url/"api"/"v1"/"notify"
val execute = BlazeClientBuilder[F](ec).resource.use { client =>
val req = Request[F](POST, Uri.unsafeFromString(notifyUrl.asString))
client.expect[String](req).map(_ => ())
}
execute.attempt.map {
case Right(_) =>
()
case Left(_) =>
logger.warn(s"Notifying Joex instance '${node.id.id}/${node.url.asString}' failed.")
()
}
}
}

81
modules/backend/src/main/scala/docspell/backend/ops/OOrganization.scala Normal file
View File

@ -0,0 +1,81 @@
package docspell.backend.ops
import cats.implicits._
import cats.effect.{Effect, Resource}
import docspell.common._
import docspell.store._
import docspell.store.records._
import OOrganization._
import docspell.store.queries.QOrganization
trait OOrganization[F[_]] {
def findAllOrg(account: AccountId): F[Vector[OrgAndContacts]]
def findAllOrgRefs(account: AccountId): F[Vector[IdRef]]
def addOrg(s: OrgAndContacts): F[AddResult]
def updateOrg(s: OrgAndContacts): F[AddResult]
def findAllPerson(account: AccountId): F[Vector[PersonAndContacts]]
def findAllPersonRefs(account: AccountId): F[Vector[IdRef]]
def addPerson(s: PersonAndContacts): F[AddResult]
def updatePerson(s: PersonAndContacts): F[AddResult]
def deleteOrg(orgId: Ident, collective: Ident): F[AddResult]
def deletePerson(personId: Ident, collective: Ident): F[AddResult]
}
object OOrganization {
case class OrgAndContacts(org: ROrganization, contacts: Seq[RContact])
case class PersonAndContacts(person: RPerson, contacts: Seq[RContact])
def apply[F[_] : Effect](store: Store[F]): Resource[F, OOrganization[F]] =
Resource.pure(new OOrganization[F] {
def findAllOrg(account: AccountId): F[Vector[OrgAndContacts]] =
store.transact(QOrganization.findOrgAndContact(account.collective, _.name)).
map({ case (org, cont) => OrgAndContacts(org, cont) }).
compile.toVector
def findAllOrgRefs(account: AccountId): F[Vector[IdRef]] =
store.transact(ROrganization.findAllRef(account.collective, _.name))
def addOrg(s: OrgAndContacts): F[AddResult] =
QOrganization.addOrg(s.org, s.contacts, s.org.cid)(store)
def updateOrg(s: OrgAndContacts): F[AddResult] =
QOrganization.updateOrg(s.org, s.contacts, s.org.cid)(store)
def findAllPerson(account: AccountId): F[Vector[PersonAndContacts]] =
store.transact(QOrganization.findPersonAndContact(account.collective, _.name)).
map({ case (person, cont) => PersonAndContacts(person, cont) }).
compile.toVector
def findAllPersonRefs(account: AccountId): F[Vector[IdRef]] =
store.transact(RPerson.findAllRef(account.collective, _.name))
def addPerson(s: PersonAndContacts): F[AddResult] =
QOrganization.addPerson(s.person, s.contacts, s.person.cid)(store)
def updatePerson(s: PersonAndContacts): F[AddResult] =
QOrganization.updatePerson(s.person, s.contacts, s.person.cid)(store)
def deleteOrg(orgId: Ident, collective: Ident): F[AddResult] =
store.transact(QOrganization.deleteOrg(orgId, collective)).
attempt.
map(AddResult.fromUpdate)
def deletePerson(personId: Ident, collective: Ident): F[AddResult] =
store.transact(QOrganization.deletePerson(personId, collective)).
attempt.
map(AddResult.fromUpdate)
})
}

48
modules/backend/src/main/scala/docspell/backend/ops/OSource.scala Normal file
View File

@ -0,0 +1,48 @@
package docspell.backend.ops
import cats.implicits._
import cats.effect.{Effect, Resource}
import docspell.common.{AccountId, Ident}
import docspell.store.{AddResult, Store}
import docspell.store.records.RSource
trait OSource[F[_]] {
def findAll(account: AccountId): F[Vector[RSource]]
def add(s: RSource): F[AddResult]
def update(s: RSource): F[AddResult]
def delete(id: Ident, collective: Ident): F[AddResult]
}
object OSource {
def apply[F[_]: Effect](store: Store[F]): Resource[F, OSource[F]] =
Resource.pure(new OSource[F] {
def findAll(account: AccountId): F[Vector[RSource]] =
store.transact(RSource.findAll(account.collective, _.abbrev))
def add(s: RSource): F[AddResult] = {
def insert = RSource.insert(s)
def exists = RSource.existsByAbbrev(s.cid, s.abbrev)
val msg = s"A source with abbrev '${s.abbrev}' already exists"
store.add(insert, exists).map(_.fold(identity, _.withMsg(msg), identity))
}
def update(s: RSource): F[AddResult] = {
def insert = RSource.updateNoCounter(s)
def exists = RSource.existsByAbbrev(s.cid, s.abbrev)
val msg = s"A source with abbrev '${s.abbrev}' already exists"
store.add(insert, exists).map(_.fold(identity, _.withMsg(msg), identity))
}
def delete(id: Ident, collective: Ident): F[AddResult] =
store.transact(RSource.delete(id, collective)).
attempt.
map(AddResult.fromUpdate)
})
}

56
modules/backend/src/main/scala/docspell/backend/ops/OTag.scala Normal file
View File

@ -0,0 +1,56 @@
package docspell.backend.ops
import cats.implicits._
import cats.effect.{Effect, Resource}
import docspell.common.{AccountId, Ident}
import docspell.store.{AddResult, Store}
import docspell.store.records.{RTag, RTagItem}
trait OTag[F[_]] {
def findAll(account: AccountId): F[Vector[RTag]]
def add(s: RTag): F[AddResult]
def update(s: RTag): F[AddResult]
def delete(id: Ident, collective: Ident): F[AddResult]
}
object OTag {
def apply[F[_]: Effect](store: Store[F]): Resource[F, OTag[F]] =
Resource.pure(new OTag[F] {
def findAll(account: AccountId): F[Vector[RTag]] =
store.transact(RTag.findAll(account.collective, _.name))
def add(t: RTag): F[AddResult] = {
def insert = RTag.insert(t)
def exists = RTag.existsByName(t)
val msg = s"A tag '${t.name}' already exists"
store.add(insert, exists).map(_.fold(identity, _.withMsg(msg), identity))
}
def update(t: RTag): F[AddResult] = {
def insert = RTag.update(t)
def exists = RTag.existsByName(t)
val msg = s"A tag '${t.name}' already exists"
store.add(insert, exists).map(_.fold(identity, _.withMsg(msg), identity))
}
def delete(id: Ident, collective: Ident): F[AddResult] = {
val io = for {
optTag <- RTag.findByIdAndCollective(id, collective)
n0 <- optTag.traverse(t => RTagItem.deleteTag(t.tagId))
n1 <- optTag.traverse(t => RTag.delete(t.tagId, collective))
} yield n0.getOrElse(0) + n1.getOrElse(0)
store.transact(io).
attempt.
map(AddResult.fromUpdate)
}
})
}

103
modules/backend/src/main/scala/docspell/backend/ops/OUpload.scala Normal file
View File

@ -0,0 +1,103 @@
package docspell.backend.ops
import bitpeace.MimetypeHint
import cats.implicits._
import cats.effect.{ConcurrentEffect, Effect, Resource}
import docspell.backend.Config
import fs2.Stream
import docspell.common._
import docspell.common.syntax.all._
import docspell.store.Store
import docspell.store.queue.JobQueue
import docspell.store.records.{RCollective, RJob, RSource}
import org.log4s._
import scala.concurrent.ExecutionContext
trait OUpload[F[_]] {
def submit(data: OUpload.UploadData[F], account: AccountId): F[OUpload.UploadResult]
def submit(data: OUpload.UploadData[F], sourceId: Ident): F[OUpload.UploadResult]
}
object OUpload {
private [this] val logger = getLogger
case class File[F[_]](name: Option[String], advertisedMime: Option[MimeType], data: Stream[F, Byte])
case class UploadMeta( direction: Option[Direction]
, sourceAbbrev: String
, validFileTypes: Seq[MimeType])
case class UploadData[F[_]]( multiple: Boolean
, meta: UploadMeta
, files: Vector[File[F]], priority: Priority, tracker: Option[Ident])
sealed trait UploadResult
object UploadResult {
case object Success extends UploadResult
case object NoFiles extends UploadResult
case object NoSource extends UploadResult
}
def apply[F[_]: ConcurrentEffect](store: Store[F], queue: JobQueue[F], cfg: Config, httpClientEC: ExecutionContext): Resource[F, OUpload[F]] =
Resource.pure(new OUpload[F] {
def submit(data: OUpload.UploadData[F], account: AccountId): F[OUpload.UploadResult] = {
for {
files <- data.files.traverse(saveFile).map(_.flatten)
pred <- checkFileList(files)
lang <- store.transact(RCollective.findLanguage(account.collective))
meta = ProcessItemArgs.ProcessMeta(account.collective, lang.getOrElse(Language.German), data.meta.direction, data.meta.sourceAbbrev, data.meta.validFileTypes)
args = if (data.multiple) files.map(f => ProcessItemArgs(meta, List(f))) else Vector(ProcessItemArgs(meta, files.toList))
job <- pred.traverse(_ => makeJobs(args, account, data.priority, data.tracker))
_ <- logger.fdebug(s"Storing jobs: $job")
res <- job.traverse(submitJobs)
_ <- store.transact(RSource.incrementCounter(data.meta.sourceAbbrev, account.collective))
} yield res.fold(identity, identity)
}
def submit(data: OUpload.UploadData[F], sourceId: Ident): F[OUpload.UploadResult] =
for {
sOpt <- store.transact(RSource.find(sourceId)).map(_.toRight(UploadResult.NoSource))
abbrev = sOpt.map(_.abbrev).toOption.getOrElse(data.meta.sourceAbbrev)
updata = data.copy(meta = data.meta.copy(sourceAbbrev = abbrev))
accId = sOpt.map(source => AccountId(source.cid, source.sid))
result <- accId.traverse(acc => submit(updata, acc))
} yield result.fold(identity, identity)
private def submitJobs(jobs: Vector[RJob]): F[OUpload.UploadResult] = {
for {
_ <- logger.fdebug(s"Storing jobs: $jobs")
_ <- queue.insertAll(jobs)
_ <- OJoex.notifyAll(store, httpClientEC)
} yield UploadResult.Success
}
private def saveFile(file: File[F]): F[Option[ProcessItemArgs.File]] = {
logger.finfo(s"Receiving file $file") *>
store.bitpeace.saveNew(file.data, cfg.files.chunkSize, MimetypeHint(file.name, None), None).
compile.lastOrError.map(fm => Ident.unsafe(fm.id)).attempt.
map(_.fold(ex => {
logger.warn(ex)(s"Could not store file for processing!")
None
}, id => Some(ProcessItemArgs.File(file.name, id))))
}
private def checkFileList(files: Seq[ProcessItemArgs.File]): F[Either[UploadResult, Unit]] =
Effect[F].pure(if (files.isEmpty) Left(UploadResult.NoFiles) else Right(()))
private def makeJobs(args: Vector[ProcessItemArgs], account: AccountId, prio: Priority, tracker: Option[Ident]): F[Vector[RJob]] = {
def create(id: Ident, now: Timestamp, arg: ProcessItemArgs): RJob =
RJob.newJob(id, ProcessItemArgs.taskName, account.collective, arg, arg.makeSubject, now, account.user, prio, tracker)
for {
id <- Ident.randomId[F]
now <- Timestamp.current[F]
jobs = args.map(a => create(id, now, a))
} yield jobs
}
})
}

41
modules/backend/src/main/scala/docspell/backend/signup/Config.scala Normal file
View File

@ -0,0 +1,41 @@
package docspell.backend.signup
import docspell.common.{Duration, Password}
import io.circe._
case class Config(mode: Config.Mode, newInvitePassword: Password, inviteTime: Duration)
object Config {
sealed trait Mode { self: Product =>
final def name: String =
productPrefix.toLowerCase
}
object Mode {
case object Open extends Mode
case object Invite extends Mode
case object Closed extends Mode
def fromString(str: String): Either[String, Mode] =
str.toLowerCase match {
case "open" => Right(Open)
case "invite" => Right(Invite)
case "closed" => Right(Closed)
case _ => Left(s"Invalid signup mode: $str")
}
def unsafe(str: String): Mode =
fromString(str).fold(sys.error, identity)
implicit val jsonEncoder: Encoder[Mode] =
Encoder.encodeString.contramap(_.name)
implicit val jsonDecoder: Decoder[Mode] =
Decoder.decodeString.emap(fromString)
}
def open: Mode = Mode.Open
def invite: Mode = Mode.Invite
def closed: Mode = Mode.Closed
}

19
modules/backend/src/main/scala/docspell/backend/signup/NewInviteResult.scala Normal file
View File

@ -0,0 +1,19 @@
package docspell.backend.signup
import docspell.common.Ident
sealed trait NewInviteResult { self: Product =>
final def name: String =
productPrefix.toLowerCase
}
object NewInviteResult {
case class Success(id: Ident) extends NewInviteResult
case object InvitationDisabled extends NewInviteResult
case object PasswordMismatch extends NewInviteResult
def passwordMismatch: NewInviteResult = PasswordMismatch
def invitationClosed: NewInviteResult = InvitationDisabled
def success(id: Ident): NewInviteResult = Success(id)
}

83
modules/backend/src/main/scala/docspell/backend/signup/OSignup.scala Normal file
View File

@ -0,0 +1,83 @@
package docspell.backend.signup
import cats.implicits._
import cats.effect.{Effect, Resource}
import docspell.backend.PasswordCrypt
import docspell.backend.ops.OCollective.RegisterData
import docspell.common._
import docspell.store.{AddResult, Store}
import docspell.store.records.{RCollective, RInvitation, RUser}
import doobie.free.connection.ConnectionIO
trait OSignup[F[_]] {
def register(cfg: Config)(data: RegisterData): F[SignupResult]
def newInvite(cfg: Config)(password: Password): F[NewInviteResult]
}
object OSignup {
def apply[F[_]:Effect](store: Store[F]): Resource[F, OSignup[F]] =
Resource.pure(new OSignup[F] {
def newInvite(cfg: Config)(password: Password): F[NewInviteResult] = {
if (cfg.mode == Config.Mode.Invite) {
if (cfg.newInvitePassword.isEmpty || cfg.newInvitePassword != password) NewInviteResult.passwordMismatch.pure[F]
else store.transact(RInvitation.insertNew).map(ri => NewInviteResult.success(ri.id))
} else {
Effect[F].pure(NewInviteResult.invitationClosed)
}
}
def register(cfg: Config)(data: RegisterData): F[SignupResult] = {
cfg.mode match {
case Config.Mode.Open =>
addUser(data).map(SignupResult.fromAddResult)
case Config.Mode.Closed =>
SignupResult.signupClosed.pure[F]
case Config.Mode.Invite =>
data.invite match {
case Some(inv) =>
for {
now <- Timestamp.current[F]
min = now.minus(cfg.inviteTime)
ok <- store.transact(RInvitation.useInvite(inv, min))
res <- if (ok) addUser(data).map(SignupResult.fromAddResult)
else SignupResult.invalidInvitationKey.pure[F]
} yield res
case None =>
SignupResult.invalidInvitationKey.pure[F]
}
}
}
private def addUser(data: RegisterData): F[AddResult] = {
def toRecords: F[(RCollective, RUser)] =
for {
id2 <- Ident.randomId[F]
now <- Timestamp.current[F]
c = RCollective(data.collName, CollectiveState.Active, Language.German, now)
u = RUser(id2, data.login, data.collName, PasswordCrypt.crypt(data.password), UserState.Active, None, 0, None, now)
} yield (c, u)
def insert(coll: RCollective, user: RUser): ConnectionIO[Int] = {
for {
n1 <- RCollective.insert(coll)
n2 <- RUser.insert(user)
} yield n1 + n2
}
def collectiveExists: ConnectionIO[Boolean] =
RCollective.existsById(data.collName)
val msg = s"The collective '${data.collName}' already exists."
for {
cu <- toRecords
save <- store.add(insert(cu._1, cu._2), collectiveExists)
} yield save.fold(identity, _.withMsg(msg), identity)
}
})
}

28
modules/backend/src/main/scala/docspell/backend/signup/SignupResult.scala Normal file
View File

@ -0,0 +1,28 @@
package docspell.backend.signup
import docspell.store.AddResult
sealed trait SignupResult {
}
object SignupResult {
case object CollectiveExists extends SignupResult
case object InvalidInvitationKey extends SignupResult
case object SignupClosed extends SignupResult
case class Failure(ex: Throwable) extends SignupResult
case object Success extends SignupResult
def collectiveExists: SignupResult = CollectiveExists
def invalidInvitationKey: SignupResult = InvalidInvitationKey
def signupClosed: SignupResult = SignupClosed
def failure(ex: Throwable): SignupResult = Failure(ex)
def success: SignupResult = Success
def fromAddResult(ar: AddResult): SignupResult = ar match {
case AddResult.Success => Success
case AddResult.Failure(ex) => Failure(ex)
case AddResult.EntityExists(_) => CollectiveExists
}
}

35
modules/common/src/main/scala/docspell/common/AccountId.scala Normal file
View File

@ -0,0 +1,35 @@
package docspell.common
case class AccountId(collective: Ident, user: Ident) {
def asString =
s"${collective.id}/${user.id}"
}
object AccountId {
private[this] val sepearatorChars: String = "/\\:"
def parse(str: String): Either[String, AccountId] = {
val input = str.replaceAll("\\s+", "").trim
val invalid: Either[String, AccountId] =
Left(s"Cannot parse account id: $str")
def parse0(sep: Char): Either[String, AccountId] =
input.indexOf(sep.toInt) match {
case n if n > 0 && input.length > 2 =>
val coll = input.substring(0, n)
val user = input.substring(n + 1)
Ident.fromString(coll).
flatMap(collId => Ident.fromString(user).
map(userId => AccountId(collId, userId)))
case _ =>
invalid
}
val separated = sepearatorChars.foldRight(invalid) { (c, v) =>
v.orElse(parse0(c))
}
separated.orElse(Ident.fromString(str).map(id => AccountId(id, id)))
}
}

34
modules/common/src/main/scala/docspell/common/Banner.scala Normal file
View File

@ -0,0 +1,34 @@
package docspell.common
case class Banner( component: String
, version: String
, gitHash: Option[String]
, jdbcUrl: LenientUri
, configFile: Option[String]
, appId: Ident
, baseUrl: LenientUri) {
private val banner =
"""______ _ _
|| _ \ | | |
|| | | |___ ___ ___ _ __ ___| | |
|| | | / _ \ / __/ __| '_ \ / _ \ | |
|| |/ / (_) | (__\__ \ |_) | __/ | |
||___/ \___/ \___|___/ .__/ \___|_|_|
| | |
|""".stripMargin +
s""" |_| v$version (#${gitHash.map(_.take(8)).getOrElse("")})"""
def render(prefix: String): String = {
val text = banner.split('\n').toList ++ List(
s"<< $component >>"
, s"Id: ${appId.id}"
, s"Base-Url: ${baseUrl.asString}"
, s"Database: ${jdbcUrl.asString}"
, s"Config: ${configFile.getOrElse("")}"
, ""
)
text.map(line => s"$prefix $line").mkString("\n")
}
}

16
modules/common/src/main/scala/docspell/common/BaseJsonCodecs.scala Normal file
View File

@ -0,0 +1,16 @@
package docspell.common
import java.time.Instant
import io.circe._
object BaseJsonCodecs {
implicit val encodeInstantEpoch: Encoder[Instant] =
Encoder.encodeJavaLong.contramap(_.toEpochMilli)
implicit val decodeInstantEpoch: Decoder[Instant] =
Decoder.decodeLong.map(Instant.ofEpochMilli)
}

52
modules/common/src/main/scala/docspell/common/CollectiveState.scala Normal file
View File

@ -0,0 +1,52 @@
package docspell.common
import io.circe.{Decoder, Encoder}
sealed trait CollectiveState
object CollectiveState {
val all = List(Active, ReadOnly, Closed, Blocked)
/** A normal active collective */
case object Active extends CollectiveState
/** A collective may be readonly in cases it is implicitly closed
* (e.g. no payment). Users can still see there data and
* download, but have no write access. */
case object ReadOnly extends CollectiveState
/** A collective that has been explicitely closed. */
case object Closed extends CollectiveState
/** A collective blocked by a super user, usually some emergency
* action. */
case object Blocked extends CollectiveState
def fromString(s: String): Either[String, CollectiveState] =
s.toLowerCase match {
case "active" => Right(Active)
case "readonly" => Right(ReadOnly)
case "closed" => Right(Closed)
case "blocked" => Right(Blocked)
case _ => Left(s"Unknown state: $s")
}
def unsafe(str: String): CollectiveState =
fromString(str).fold(sys.error, identity)
def asString(state: CollectiveState): String = state match {
case Active => "active"
case Blocked => "blocked"
case Closed => "closed"
case ReadOnly => "readonly"
}
implicit val collectiveStateEncoder: Encoder[CollectiveState] =
Encoder.encodeString.contramap(CollectiveState.asString)
implicit val collectiveStateDecoder: Decoder[CollectiveState] =
Decoder.decodeString.emap(CollectiveState.fromString)
}

44
modules/common/src/main/scala/docspell/common/ContactKind.scala Normal file
View File

@ -0,0 +1,44 @@
package docspell.common
import io.circe.{Decoder, Encoder}
sealed trait ContactKind { self: Product =>
def asString: String = self.productPrefix
}
object ContactKind {
val all = List()
case object Phone extends ContactKind
case object Mobile extends ContactKind
case object Fax extends ContactKind
case object Email extends ContactKind
case object Docspell extends ContactKind
case object Website extends ContactKind
def fromString(s: String): Either[String, ContactKind] =
s.toLowerCase match {
case "phone" => Right(Phone)
case "mobile" => Right(Mobile)
case "fax" => Right(Fax)
case "email" => Right(Email)
case "docspell" => Right(Docspell)
case "website" => Right(Website)
case _ => Left(s"Not a state value: $s")
}
def unsafe(str: String): ContactKind =
fromString(str).fold(sys.error, identity)
def asString(s: ContactKind): String =
s.asString.toLowerCase
implicit val contactKindEncoder: Encoder[ContactKind] =
Encoder.encodeString.contramap(_.asString)
implicit val contactKindDecoder: Decoder[ContactKind] =
Decoder.decodeString.emap(ContactKind.fromString)
}

42
modules/common/src/main/scala/docspell/common/Direction.scala Normal file
View File

@ -0,0 +1,42 @@
package docspell.common
import io.circe.{Decoder, Encoder}
sealed trait Direction {
self: Product =>
def name: String =
productPrefix.toLowerCase
}
object Direction {
case object Incoming extends Direction
case object Outgoing extends Direction
def incoming: Direction = Incoming
def outgoing: Direction = Outgoing
def parse(str: String): Either[String, Direction] =
str.toLowerCase match {
case "incoming" => Right(Incoming)
case "outgoing" => Right(Outgoing)
case _ => Left(s"No direction: $str")
}
def unsafe(str: String): Direction =
parse(str).fold(sys.error, identity)
def isIncoming(dir: Direction): Boolean =
dir == Direction.Incoming
def isOutgoing(dir: Direction): Boolean =
dir == Direction.Outgoing
implicit val directionEncoder: Encoder[Direction] =
Encoder.encodeString.contramap(_.name)
implicit val directionDecoder: Decoder[Direction] =
Decoder.decodeString.emap(Direction.parse)
}

54
modules/common/src/main/scala/docspell/common/Duration.scala Normal file
View File

@ -0,0 +1,54 @@
package docspell.common
import cats.implicits._
import scala.concurrent.duration.{FiniteDuration, Duration => SDur}
import java.time.{Duration => JDur}
import java.util.concurrent.TimeUnit
import cats.effect.Sync
case class Duration(nanos: Long) {
def millis: Long = nanos / 1000000
def seconds: Long = millis / 1000
def toScala: FiniteDuration =
FiniteDuration(nanos, TimeUnit.NANOSECONDS)
def toJava: JDur =
JDur.ofNanos(nanos)
def formatExact: String =
s"$millis ms"
}
object Duration {
def apply(d: SDur): Duration =
Duration(d.toNanos)
def apply(d: JDur): Duration =
Duration(d.toNanos)
def seconds(n: Long): Duration =
apply(JDur.ofSeconds(n))
def millis(n: Long): Duration =
apply(JDur.ofMillis(n))
def minutes(n: Long): Duration =
apply(JDur.ofMinutes(n))
def hours(n: Long): Duration =
apply(JDur.ofHours(n))
def nanos(n: Long): Duration =
Duration(n)
def stopTime[F[_]: Sync]: F[F[Duration]] =
for {
now <- Timestamp.current[F]
end = Timestamp.current[F]
} yield end.map(e => Duration.millis(e.toMillis - now.toMillis))
}

16
modules/common/src/main/scala/docspell/common/IdRef.scala Normal file
View File

@ -0,0 +1,16 @@
package docspell.common
import io.circe._
import io.circe.generic.semiauto._
case class IdRef(id: Ident, name: String) {
}
object IdRef {
implicit val jsonEncoder: Encoder[IdRef] =
deriveEncoder[IdRef]
implicit val jsonDecoder: Decoder[IdRef] =
deriveDecoder[IdRef]
}

57
modules/common/src/main/scala/docspell/common/Ident.scala Normal file
View File

@ -0,0 +1,57 @@
package docspell.common
import java.security.SecureRandom
import java.util.UUID
import cats.effect.Sync
import io.circe.{Decoder, Encoder}
import scodec.bits.ByteVector
case class Ident(id: String) {
}
object Ident {
val chars: Set[Char] = (('A' to 'Z') ++ ('a' to 'z') ++ ('0' to '9') ++ "-_").toSet
def randomUUID[F[_]: Sync]: F[Ident] =
Sync[F].delay(unsafe(UUID.randomUUID.toString))
def randomId[F[_]: Sync]: F[Ident] = Sync[F].delay {
val random = new SecureRandom()
val buffer = new Array[Byte](32)
random.nextBytes(buffer)
unsafe(ByteVector.view(buffer).toBase58.grouped(11).mkString("-"))
}
def apply(str: String): Either[String, Ident] =
fromString(str)
def fromString(s: String): Either[String, Ident] =
if (s.forall(chars.contains)) Right(new Ident(s))
else Left(s"Invalid identifier: $s. Allowed chars: ${chars.mkString}")
def fromBytes(bytes: ByteVector): Ident =
unsafe(bytes.toBase58)
def fromByteArray(bytes: Array[Byte]): Ident =
fromBytes(ByteVector.view(bytes))
def unsafe(s: String): Ident =
fromString(s) match {
case Right(id) => id
case Left(err) => sys.error(err)
}
def unapply(arg: String): Option[Ident] =
fromString(arg).toOption
implicit val encodeIdent: Encoder[Ident] =
Encoder.encodeString.contramap(_.id)
implicit val decodeIdent: Decoder[Ident] =
Decoder.decodeString.emap(Ident.fromString)
}

35
modules/common/src/main/scala/docspell/common/ItemState.scala Normal file
View File

@ -0,0 +1,35 @@
package docspell.common
import io.circe.{Decoder, Encoder}
sealed trait ItemState { self: Product =>
final def name: String =
productPrefix.toLowerCase
}
object ItemState {
case object Premature extends ItemState
case object Processing extends ItemState
case object Created extends ItemState
case object Confirmed extends ItemState
def fromString(str: String): Either[String, ItemState] =
str.toLowerCase match {
case "premature" => Right(Premature)
case "processing" => Right(Processing)
case "created" => Right(Created)
case "confirmed" => Right(Confirmed)
case _ => Left(s"Invalid item state: $str")
}
def unsafe(str: String): ItemState =
fromString(str).fold(sys.error, identity)
implicit val jsonDecoder: Decoder[ItemState] =
Decoder.decodeString.emap(fromString)
implicit val jsonEncoder: Encoder[ItemState] =
Encoder.encodeString.contramap(_.name)
}

70
modules/common/src/main/scala/docspell/common/JobState.scala Normal file
View File

@ -0,0 +1,70 @@
package docspell.common
import io.circe.{Decoder, Encoder}
sealed trait JobState { self: Product =>
def name: String =
productPrefix.toLowerCase
}
object JobState {
/** Waiting for being executed. */
case object Waiting extends JobState {
}
/** A scheduler has picked up this job and will pass it to the next
* free slot. */
case object Scheduled extends JobState {
}
/** Is currently executing */
case object Running extends JobState {
}
/** Finished with failure and is being retried. */
case object Stuck extends JobState {
}
/** Finished finally with a failure */
case object Failed extends JobState {
}
/** Finished by cancellation. */
case object Cancelled extends JobState {
}
/** Finished with success */
case object Success extends JobState {
}
val all: Set[JobState] = Set(Waiting, Scheduled, Running, Stuck, Failed, Cancelled, Success)
val queued: Set[JobState] = Set(Waiting, Scheduled, Stuck)
val done: Set[JobState] = Set(Failed, Cancelled, Success)
def parse(str: String): Either[String, JobState] =
str.toLowerCase match {
case "waiting" => Right(Waiting)
case "scheduled" => Right(Scheduled)
case "running" => Right(Running)
case "stuck" => Right(Stuck)
case "failed" => Right(Failed)
case "cancelled" => Right(Cancelled)
case "success" => Right(Success)
case _ => Left(s"Not a job state: $str")
}
def unsafe(str: String): JobState =
parse(str).fold(sys.error, identity)
def asString(state: JobState): String =
state.name
implicit val jobStateEncoder: Encoder[JobState] =
Encoder.encodeString.contramap(_.name)
implicit val jobStateDecoder: Decoder[JobState] =
Decoder.decodeString.emap(JobState.parse)
}

46
modules/common/src/main/scala/docspell/common/Language.scala Normal file
View File

@ -0,0 +1,46 @@
package docspell.common
import io.circe.{Decoder, Encoder}
sealed trait Language { self: Product =>
final def name: String =
productPrefix.toLowerCase
def iso2: String
def iso3: String
private[common] def allNames =
Set(name, iso3, iso2)
}
object Language {
case object German extends Language {
val iso2 = "de"
val iso3 = "deu"
}
case object English extends Language {
val iso2 = "en"
val iso3 = "eng"
}
val all: List[Language] = List(German, English)
def fromString(str: String): Either[String, Language] = {
val lang = str.toLowerCase
all.find(_.allNames.contains(lang)).
toRight(s"Unsupported or invalid language: $str")
}
def unsafe(str: String): Language =
fromString(str).fold(sys.error, identity)
implicit val jsonDecoder: Decoder[Language] =
Decoder.decodeString.emap(fromString)
implicit val jsonEncoder: Encoder[Language] =
Encoder.encodeString.contramap(_.iso3)
}

186
modules/common/src/main/scala/docspell/common/LenientUri.scala Normal file
View File

@ -0,0 +1,186 @@
package docspell.common
import java.net.URL
import fs2.Stream
import cats.implicits._
import cats.data.NonEmptyList
import cats.effect.{Blocker, ContextShift, Sync}
import docspell.common.LenientUri.Path
import io.circe.{Decoder, Encoder}
/** A URI.
*
* It is not compliant to rfc3986, but covers most use cases in a convenient way.
*/
case class LenientUri(scheme: NonEmptyList[String]
, authority: Option[String]
, path: LenientUri.Path
, query: Option[String]
, fragment: Option[String]) {
def /(segment: String): LenientUri =
copy(path = path / segment)
def ++ (np: Path): LenientUri =
copy(path = np.segments.foldLeft(path)(_ / _))
def ++ (np: String): LenientUri = {
val rel = LenientUri.stripLeading(np, '/')
++(LenientUri.unsafe(s"a:$rel").path)
}
def toJavaUrl: Either[String, URL] =
Either.catchNonFatal(new URL(asString)).left.map(_.getMessage)
def readURL[F[_]: Sync : ContextShift](chunkSize: Int, blocker: Blocker): Stream[F, Byte] =
Stream.emit(Either.catchNonFatal(new URL(asString))).
covary[F].
rethrow.
flatMap(url => fs2.io.readInputStream(Sync[F].delay(url.openStream()), chunkSize, blocker, true))
def asString: String = {
val schemePart = scheme.toList.mkString(":")
val authPart = authority.map(a => s"//$a").getOrElse("")
val pathPart = path.asString
val queryPart = query.map(q => s"?$q").getOrElse("")
val fragPart = fragment.map(f => s"#$f").getOrElse("")
s"$schemePart:$authPart$pathPart$queryPart$fragPart"
}
}
object LenientUri {
sealed trait Path {
def segments: List[String]
def isRoot: Boolean
def isEmpty: Boolean
def /(segment: String): Path
def asString: String
}
case object RootPath extends Path {
val segments = Nil
val isRoot = true
val isEmpty = false
def /(seg: String): Path =
NonEmptyPath(NonEmptyList.of(seg))
def asString = "/"
}
case object EmptyPath extends Path {
val segments = Nil
val isRoot = false
val isEmpty = true
def /(seg: String): Path =
NonEmptyPath(NonEmptyList.of(seg))
def asString = ""
}
case class NonEmptyPath(segs: NonEmptyList[String]) extends Path {
def segments = segs.toList
val isEmpty = false
val isRoot = false
def /(seg: String): Path =
copy(segs = segs.append(seg))
def asString = segs.head match {
case "." => segments.map(percentEncode).mkString("/")
case ".." => segments.map(percentEncode).mkString("/")
case _ => "/" + segments.map(percentEncode).mkString("/")
}
}
def unsafe(str: String): LenientUri =
parse(str).fold(sys.error, identity)
def fromJava(u: URL): LenientUri =
unsafe(u.toExternalForm)
def parse(str: String): Either[String, LenientUri] = {
def makePath(str: String): Path = str.trim match {
case "/" => RootPath
case "" => EmptyPath
case _ => NonEmptyList.fromList(stripLeading(str, '/').split('/').toList.map(percentDecode)) match {
case Some(nl) => NonEmptyPath(nl)
case None => sys.error(s"Invalid url: $str")
}
}
def makeNonEmpty(str: String): Option[String] =
Option(str).filter(_.nonEmpty)
def makeScheme(s: String): Option[NonEmptyList[String]] =
NonEmptyList.fromList(s.split(':').toList.filter(_.nonEmpty).map(_.toLowerCase))
def splitPathQF(pqf: String): (Path, Option[String], Option[String]) =
pqf.indexOf('?') match {
case -1 =>
pqf.indexOf('#') match {
case -1 =>
(makePath(pqf), None, None)
case n =>
(makePath(pqf.substring(0, n)), None, makeNonEmpty(pqf.substring(n + 1)))
}
case n =>
pqf.indexOf('#', n) match {
case -1 =>
(makePath(pqf.substring(0, n)), makeNonEmpty(pqf.substring(n+1)), None)
case k =>
(makePath(pqf.substring(0, n)), makeNonEmpty(pqf.substring(n+1, k)), makeNonEmpty(pqf.substring(k+1)))
}
}
str.split("//", 2) match {
case Array(p0, p1) =>
// scheme:scheme:authority/path
val scheme = makeScheme(p0)
val (auth, pathQF) = p1.indexOf('/') match {
case -1 => (Some(p1), "")
case n => (Some(p1.substring(0, n)), p1.substring(n))
}
val (path, query, frag) = splitPathQF(pathQF)
scheme match {
case None =>
Left(s"No scheme found: $str")
case Some(nl) =>
Right(LenientUri(nl, auth, path, query, frag))
}
case Array(p0) =>
// scheme:scheme:path
p0.lastIndexOf(':') match {
case -1 =>
Left(s"No scheme found: $str")
case n =>
val scheme = makeScheme(p0.substring(0, n))
val (path, query, frag) = splitPathQF(p0.substring(n + 1))
scheme match {
case None =>
Left(s"No scheme found: $str")
case Some(nl) =>
Right(LenientUri(nl, None, path, query, frag))
}
}
}
}
private[this] val delims: Set[Char] = ":/?#[]@".toSet
private def percentEncode(s: String): String =
s.flatMap(c => if (delims.contains(c)) s"%${c.toInt.toHexString}" else c.toString)
private def percentDecode(s: String): String =
if (!s.contains("%")) s
else s.foldLeft(("", "")) { case ((acc, res), c) =>
if (acc.length == 2) ("", res :+ Integer.parseInt(acc.drop(1) :+ c, 16).toChar)
else if (acc.startsWith("%")) (acc :+ c, res)
else if (c == '%') ("%", res)
else (acc, res :+ c)
}._2
private def stripLeading(s: String, c: Char): String =
if (s.length > 0 && s.charAt(0) == c) s.substring(1)
else s
implicit val encodeLenientUri: Encoder[LenientUri] =
Encoder.encodeString.contramap(_.asString)
implicit val decodeLenientUri: Decoder[LenientUri] =
Decoder.decodeString.emap(LenientUri.parse)
}

44
modules/common/src/main/scala/docspell/common/LogLevel.scala Normal file
View File

@ -0,0 +1,44 @@
package docspell.common
import io.circe.{Decoder, Encoder}
sealed trait LogLevel { self: Product =>
def toInt: Int
final def name: String =
productPrefix.toLowerCase
}
object LogLevel {
case object Debug extends LogLevel { val toInt = 0 }
case object Info extends LogLevel { val toInt = 1 }
case object Warn extends LogLevel { val toInt = 2 }
case object Error extends LogLevel { val toInt = 3 }
def fromInt(n: Int): LogLevel =
n match {
case 0 => Debug
case 1 => Info
case 2 => Warn
case 3 => Error
case _ => Debug
}
def fromString(str: String): Either[String, LogLevel] =
str.toLowerCase match {
case "debug" => Right(Debug)
case "info" => Right(Info)
case "warn" => Right(Warn)
case "warning" => Right(Warn)
case "error" => Right(Error)
case _ => Left(s"Invalid log-level: $str")
}
def unsafeString(str: String): LogLevel =
fromString(str).fold(sys.error, identity)
implicit val jsonDecoder: Decoder[LogLevel] =
Decoder.decodeString.emap(fromString)
implicit val jsonEncoder: Encoder[LogLevel] =
Encoder.encodeString.contramap(_.name)
}

44
modules/common/src/main/scala/docspell/common/MetaProposal.scala Normal file
View File

@ -0,0 +1,44 @@
package docspell.common
import cats.data.NonEmptyList
import docspell.common.MetaProposal.Candidate
import io.circe._
import io.circe.generic.semiauto._
case class MetaProposal(proposalType: MetaProposalType, values: NonEmptyList[Candidate]) {
def addIdRef(refs: Seq[Candidate]): MetaProposal =
copy(values = MetaProposal.flatten(values ++ refs.toList))
def isSingleValue: Boolean =
values.tail.isEmpty
def isMultiValue: Boolean =
!isSingleValue
def size: Int =
values.size
}
object MetaProposal {
case class Candidate(ref: IdRef, origin: Set[NerLabel])
object Candidate {
implicit val jsonEncoder: Encoder[Candidate] =
deriveEncoder[Candidate]
implicit val jsonDecoder: Decoder[Candidate] =
deriveDecoder[Candidate]
}
def flatten(s: NonEmptyList[Candidate]): NonEmptyList[Candidate] = {
def append(list: List[Candidate]): Candidate =
list.reduce((l0, l1) => l0.copy(origin = l0.origin ++ l1.origin))
val grouped = s.toList.groupBy(_.ref.id)
NonEmptyList.fromListUnsafe(grouped.values.toList.map(append))
}
implicit val jsonDecoder: Decoder[MetaProposal] =
deriveDecoder[MetaProposal]
implicit val jsonEncoder: Encoder[MetaProposal] =
deriveEncoder[MetaProposal]
}

82
modules/common/src/main/scala/docspell/common/MetaProposalList.scala Normal file
View File

@ -0,0 +1,82 @@
package docspell.common
import cats.data.NonEmptyList
import cats.kernel.Monoid
import docspell.common.MetaProposal.Candidate
import io.circe._
import io.circe.generic.semiauto._
case class MetaProposalList private (proposals: List[MetaProposal]) {
def isEmpty: Boolean = proposals.isEmpty
def nonEmpty: Boolean = proposals.nonEmpty
def hasResults(mt: MetaProposalType, mts: MetaProposalType*): Boolean = {
(mts :+ mt).map(mtp => proposals.exists(_.proposalType == mtp)).
reduce(_ && _)
}
def hasResultsAll: Boolean =
proposals.map(_.proposalType).toSet == MetaProposalType.all.toSet
def getTypes: Set[MetaProposalType] =
proposals.foldLeft(Set.empty[MetaProposalType])(_ + _.proposalType)
def fillEmptyFrom(ml: MetaProposalList): MetaProposalList = {
val list = ml.proposals.foldLeft(proposals){ (mine, mp) =>
if (hasResults(mp.proposalType)) mine
else mp :: mine
}
new MetaProposalList(list)
}
def find(mpt: MetaProposalType): Option[MetaProposal] =
proposals.find(_.proposalType == mpt)
}
object MetaProposalList {
val empty = MetaProposalList(Nil)
def apply(lmp: List[MetaProposal]): MetaProposalList =
flatten(lmp.map(m => new MetaProposalList(List(m))))
def of(mps: MetaProposal*): MetaProposalList =
flatten(mps.toList.map(mp => MetaProposalList(List(mp))))
def from(mt: MetaProposalType, label: NerLabel)(refs: Seq[IdRef]): MetaProposalList =
fromSeq1(mt, refs.map(ref => Candidate(ref, Set(label))))
def fromSeq1(mt: MetaProposalType, refs: Seq[Candidate]): MetaProposalList =
NonEmptyList.fromList(refs.toList).
map(nl => MetaProposalList.of(MetaProposal(mt, nl))).
getOrElse(empty)
def fromMap(m: Map[MetaProposalType, MetaProposal]): MetaProposalList = {
new MetaProposalList(m.toList.map({ case (k, v) => v.copy(proposalType = k) }))
}
def flatten(ml: Seq[MetaProposalList]): MetaProposalList = {
val init: Map[MetaProposalType, MetaProposal] = Map.empty
def updateMap(map: Map[MetaProposalType, MetaProposal], mp: MetaProposal): Map[MetaProposalType, MetaProposal] =
map.get(mp.proposalType) match {
case Some(mp0) => map.updated(mp.proposalType, mp0.addIdRef(mp.values.toList))
case None => map.updated(mp.proposalType, mp)
}
val merged = ml.foldLeft(init) { (map, el) =>
el.proposals.foldLeft(map)(updateMap)
}
fromMap(merged)
}
implicit val jsonEncoder: Encoder[MetaProposalList] =
deriveEncoder[MetaProposalList]
implicit val jsonDecoder: Decoder[MetaProposalList] =
deriveDecoder[MetaProposalList]
implicit val metaProposalListMonoid: Monoid[MetaProposalList] =
Monoid.instance(empty, (m0, m1) => flatten(Seq(m0, m1)))
}

41
modules/common/src/main/scala/docspell/common/MetaProposalType.scala Normal file
View File

@ -0,0 +1,41 @@
package docspell.common
import io.circe._
sealed trait MetaProposalType { self: Product =>
final def name: String =
productPrefix.toLowerCase
}
object MetaProposalType {
case object CorrOrg extends MetaProposalType
case object CorrPerson extends MetaProposalType
case object ConcPerson extends MetaProposalType
case object ConcEquip extends MetaProposalType
case object DocDate extends MetaProposalType
case object DueDate extends MetaProposalType
val all: List[MetaProposalType] =
List(CorrOrg, CorrPerson, ConcPerson, ConcEquip)
def fromString(str: String): Either[String, MetaProposalType] =
str.toLowerCase match {
case "corrorg" => Right(CorrOrg)
case "corrperson" => Right(CorrPerson)
case "concperson" => Right(ConcPerson)
case "concequip" => Right(ConcEquip)
case "docdate" => Right(DocDate)
case "duedate" => Right(DueDate)
case _ => Left(s"Invalid item-proposal-type: $str")
}
def unsafe(str: String): MetaProposalType =
fromString(str).fold(sys.error, identity)
implicit val jsonDecoder: Decoder[MetaProposalType] =
Decoder.decodeString.emap(fromString)
implicit val jsonEncoder: Encoder[MetaProposalType] =
Encoder.encodeString.contramap(_.name)
}

62
modules/common/src/main/scala/docspell/common/MimeType.scala Normal file
View File

@ -0,0 +1,62 @@
package docspell.common
import docspell.common.syntax.all._
import io.circe.{Decoder, Encoder}
/** A MIME Type impl with just enough features for the use here.
*/
case class MimeType(primary: String, sub: String) {
def asString: String =
s"$primary/$sub"
def matches(other: MimeType): Boolean =
primary == other.primary &&
(sub == other.sub || sub == "*" )
}
object MimeType {
def application(sub: String): MimeType =
MimeType("application", partFromString(sub).throwLeft)
def text(sub: String): MimeType =
MimeType("text", partFromString(sub).throwLeft)
def image(sub: String): MimeType =
MimeType("image", partFromString(sub).throwLeft)
private[this] val validChars: Set[Char] = (('A' to 'Z') ++ ('a' to 'z') ++ ('0' to '9') ++ "*-").toSet
def parse(str: String): Either[String, MimeType] = {
str.indexOf('/') match {
case -1 => Left(s"Invalid MIME type: $str")
case n =>
for {
prim <- partFromString(str.substring(0, n))
sub <- partFromString(str.substring(n + 1))
} yield MimeType(prim.toLowerCase, sub.toLowerCase)
}
}
def unsafe(str: String): MimeType =
parse(str).throwLeft
private def partFromString(s: String): Either[String, String] =
if (s.forall(validChars.contains)) Right(s)
else Left(s"Invalid identifier: $s. Allowed chars: ${validChars.mkString}")
val octetStream = application("octet-stream")
val pdf = application("pdf")
val png = image("png")
val jpeg = image("jpeg")
val tiff = image("tiff")
val html = text("html")
val plain = text("plain")
implicit val jsonEncoder: Encoder[MimeType] =
Encoder.encodeString.contramap(_.asString)
implicit val jsonDecoder: Decoder[MimeType] =
Decoder.decodeString.emap(parse)
}

7
modules/common/src/main/scala/docspell/common/NerDateLabel.scala Normal file
View File

@ -0,0 +1,7 @@
package docspell.common
import java.time.LocalDate
case class NerDateLabel(date: LocalDate, label: NerLabel) {
}

13
modules/common/src/main/scala/docspell/common/NerLabel.scala Normal file
View File

@ -0,0 +1,13 @@
package docspell.common
import io.circe.generic.semiauto._
import io.circe.{Decoder, Encoder}
case class NerLabel(label: String, tag: NerTag, startPosition: Int, endPosition: Int) {
}
object NerLabel {
implicit val jsonEncoder: Encoder[NerLabel] = deriveEncoder[NerLabel]
implicit val jsonDecoder: Decoder[NerLabel] = deriveDecoder[NerLabel]
}

43
modules/common/src/main/scala/docspell/common/NerTag.scala Normal file
View File

@ -0,0 +1,43 @@
package docspell.common
import io.circe.{Decoder, Encoder}
sealed trait NerTag { self: Product =>
final def name: String =
productPrefix.toLowerCase
}
object NerTag {
case object Organization extends NerTag
case object Person extends NerTag
case object Location extends NerTag
case object Misc extends NerTag
case object Email extends NerTag
case object Website extends NerTag
case object Date extends NerTag
val all: List[NerTag] = List(Organization, Person, Location)
def fromString(str: String): Either[String, NerTag] =
str.toLowerCase match {
case "organization" => Right(Organization)
case "person" => Right(Person)
case "location" => Right(Location)
case "misc" => Right(Misc)
case "email" => Right(Email)
case "website" => Right(Website)
case "date" => Right(Date)
case _ => Left(s"Invalid ner tag: $str")
}
def unsafe(str: String): NerTag =
fromString(str).fold(sys.error, identity)
implicit val jsonDecoder: Decoder[NerTag] =
Decoder.decodeString.emap(fromString)
implicit val jsonEncoder: Encoder[NerTag] =
Encoder.encodeString.contramap(_.name)
}

25
modules/common/src/main/scala/docspell/common/NodeType.scala Normal file
View File

@ -0,0 +1,25 @@
package docspell.common
sealed trait NodeType { self: Product =>
final def name: String =
self.productPrefix.toLowerCase
}
object NodeType {
case object Restserver extends NodeType
case object Joex extends NodeType
def fromString(str: String): Either[String, NodeType] =
str.toLowerCase match {
case "restserver" => Right(Restserver)
case "joex" => Right(Joex)
case _ => Left(s"Invalid node type: $str")
}
def unsafe(str: String): NodeType =
fromString(str).fold(sys.error, identity)
}

27
modules/common/src/main/scala/docspell/common/Password.scala Normal file
View File

@ -0,0 +1,27 @@
package docspell.common
import io.circe.{Decoder, Encoder}
final class Password(val pass: String) extends AnyVal {
def isEmpty: Boolean= pass.isEmpty
override def toString: String =
if (pass.isEmpty) "<empty>" else "***"
}
object Password {
val empty = Password("")
def apply(pass: String): Password =
new Password(pass)
implicit val passwordEncoder: Encoder[Password] =
Encoder.encodeString.contramap(_.pass)
implicit val passwordDecoder: Decoder[Password] =
Decoder.decodeString.map(Password(_))
}

48
modules/common/src/main/scala/docspell/common/Priority.scala Normal file
View File

@ -0,0 +1,48 @@
package docspell.common
import cats.implicits._
import cats.Order
import io.circe.{Decoder, Encoder}
sealed trait Priority { self: Product =>
final def name: String =
productPrefix.toLowerCase
}
object Priority {
case object High extends Priority
case object Low extends Priority
def fromString(str: String): Either[String, Priority] =
str.toLowerCase match {
case "high" => Right(High)
case "low" => Right(Low)
case _ => Left(s"Invalid priority: $str")
}
def unsafe(str: String): Priority =
fromString(str).fold(sys.error, identity)
def fromInt(n: Int): Priority =
if (n <= toInt(Low)) Low
else High
def toInt(p: Priority): Int =
p match {
case Low => 0
case High => 10
}
implicit val priorityOrder: Order[Priority] =
Order.by[Priority, Int](toInt)
implicit val jsonEncoder: Encoder[Priority] =
Encoder.encodeString.contramap(_.name)
implicit val jsonDecoder: Decoder[Priority] =
Decoder.decodeString.emap(fromString)
}

47
modules/common/src/main/scala/docspell/common/ProcessItemArgs.scala Normal file
View File

@ -0,0 +1,47 @@
package docspell.common
import io.circe._, io.circe.generic.semiauto._
import docspell.common.syntax.all._
import ProcessItemArgs._
case class ProcessItemArgs(meta: ProcessMeta, files: List[File]) {
def makeSubject: String = {
files.flatMap(_.name) match {
case Nil => s"${meta.sourceAbbrev}: No files"
case n :: Nil => n
case n1 :: n2 :: Nil => s"$n1, $n2"
case more => s"${files.size} files from ${meta.sourceAbbrev}"
}
}
}
object ProcessItemArgs {
val taskName = Ident.unsafe("process-item")
case class ProcessMeta( collective: Ident
, language: Language
, direction: Option[Direction]
, sourceAbbrev: String
, validFileTypes: Seq[MimeType])
object ProcessMeta {
implicit val jsonEncoder: Encoder[ProcessMeta] = deriveEncoder[ProcessMeta]
implicit val jsonDecoder: Decoder[ProcessMeta] = deriveDecoder[ProcessMeta]
}
case class File(name: Option[String], fileMetaId: Ident)
object File {
implicit val jsonEncoder: Encoder[File] = deriveEncoder[File]
implicit val jsonDecoder: Decoder[File] = deriveDecoder[File]
}
implicit val jsonEncoder: Encoder[ProcessItemArgs] = deriveEncoder[ProcessItemArgs]
implicit val jsonDecoder: Decoder[ProcessItemArgs] = deriveDecoder[ProcessItemArgs]
def parse(str: String): Either[Throwable, ProcessItemArgs] =
str.parseJsonAs[ProcessItemArgs]
}

20
modules/common/src/main/scala/docspell/common/ThreadFactories.scala Normal file
View File

@ -0,0 +1,20 @@
package docspell.common
import java.util.concurrent.atomic.AtomicLong
import java.util.concurrent.{Executors, ThreadFactory}
object ThreadFactories {
def ofName(prefix: String): ThreadFactory =
new ThreadFactory {
val counter = new AtomicLong(0)
override def newThread(r: Runnable): Thread = {
val t = Executors.defaultThreadFactory().newThread(r)
t.setName(s"$prefix-${counter.getAndIncrement()}")
t
}
}
}

41
modules/common/src/main/scala/docspell/common/Timestamp.scala Normal file
View File

@ -0,0 +1,41 @@
package docspell.common
import java.time.{Instant, LocalDate, ZoneId}
import cats.effect.Sync
import io.circe.{Decoder, Encoder}
case class Timestamp(value: Instant) {
def toMillis: Long = value.toEpochMilli
def toSeconds: Long = value.toEpochMilli / 1000L
def minus(d: Duration): Timestamp =
Timestamp(value.minusNanos(d.nanos))
def minusHours(n: Long): Timestamp =
Timestamp(value.minusSeconds(n * 60 * 60))
def toDate: LocalDate =
value.atZone(ZoneId.of("UTC")).toLocalDate
def asString: String = value.toString
}
object Timestamp {
val Epoch = Timestamp(Instant.EPOCH)
def current[F[_]: Sync]: F[Timestamp] =
Sync[F].delay(Timestamp(Instant.now))
implicit val encodeTimestamp: Encoder[Timestamp] =
BaseJsonCodecs.encodeInstantEpoch.contramap(_.value)
implicit val decodeTimestamp: Decoder[Timestamp] =
BaseJsonCodecs.decodeInstantEpoch.map(Timestamp(_))
}

37
modules/common/src/main/scala/docspell/common/UserState.scala Normal file
View File

@ -0,0 +1,37 @@
package docspell.common
import io.circe.{Decoder, Encoder}
sealed trait UserState
object UserState {
val all = List(Active, Disabled)
/** An active or enabled user. */
case object Active extends UserState
/** The user is blocked by an admin. */
case object Disabled extends UserState
def fromString(s: String): Either[String, UserState] =
s.toLowerCase match {
case "active" => Right(Active)
case "disabled" => Right(Disabled)
case _ => Left(s"Not a state value: $s")
}
def unsafe(str: String): UserState =
fromString(str).fold(sys.error, identity)
def asString(s: UserState): String = s match {
case Active => "active"
case Disabled => "disabled"
}
implicit val userStateEncoder: Encoder[UserState] =
Encoder.encodeString.contramap(UserState.asString)
implicit val userStateDecoder: Decoder[UserState] =
Decoder.decodeString.emap(UserState.fromString)
}

35
modules/common/src/main/scala/docspell/common/pureconfig/Implicits.scala Normal file
View File

@ -0,0 +1,35 @@
package docspell.common.pureconfig
import docspell.common._
import _root_.pureconfig._
import _root_.pureconfig.error.{CannotConvert, FailureReason}
import scodec.bits.ByteVector
import scala.reflect.ClassTag
object Implicits {
implicit val lenientUriReader: ConfigReader[LenientUri] =
ConfigReader[String].emap(reason(LenientUri.parse))
implicit val durationReader: ConfigReader[Duration] =
ConfigReader[scala.concurrent.duration.Duration].map(sd => Duration(sd))
implicit val passwordReader: ConfigReader[Password] =
ConfigReader[String].map(Password(_))
implicit val mimeTypeReader: ConfigReader[MimeType] =
ConfigReader[String].emap(reason(MimeType.parse))
implicit val identReader: ConfigReader[Ident] =
ConfigReader[String].emap(reason(Ident.fromString))
implicit val byteVectorReader: ConfigReader[ByteVector] =
ConfigReader[String].emap(reason(str => {
if (str.startsWith("hex:")) ByteVector.fromHex(str.drop(4)).toRight("Invalid hex value.")
else if (str.startsWith("b64:")) ByteVector.fromBase64(str.drop(4)).toRight("Invalid Base64 string.")
else ByteVector.fromHex(str).toRight("Invalid hex value.")
}))
def reason[A: ClassTag](f: String => Either[String, A]): String => Either[FailureReason, A] =
in => f(in).left.map(str => CannotConvert(in, implicitly[ClassTag[A]].runtimeClass.toString, str))
}

21
modules/common/src/main/scala/docspell/common/syntax/EitherSyntax.scala Normal file
View File

@ -0,0 +1,21 @@
package docspell.common.syntax
trait EitherSyntax {
implicit final class LeftStringEitherOps[A](e: Either[String, A]) {
def throwLeft: A = e match {
case Right(a) => a
case Left(err) => sys.error(err)
}
}
implicit final class ThrowableLeftEitherOps[A](e: Either[Throwable, A]) {
def throwLeft: A = e match {
case Right(a) => a
case Left(err) => throw err
}
}
}
object EitherSyntax extends EitherSyntax

35
modules/common/src/main/scala/docspell/common/syntax/LoggerSyntax.scala Normal file
View File

@ -0,0 +1,35 @@
package docspell.common.syntax
import cats.effect.Sync
import fs2.Stream
import org.log4s.Logger
trait LoggerSyntax {
implicit final class LoggerOps(logger: Logger) {
def ftrace[F[_]: Sync](msg: => String): F[Unit] =
Sync[F].delay(logger.trace(msg))
def fdebug[F[_]: Sync](msg: => String): F[Unit] =
Sync[F].delay(logger.debug(msg))
def sdebug[F[_]: Sync](msg: => String): Stream[F, Nothing] =
Stream.eval(fdebug(msg)).drain
def finfo[F[_]: Sync](msg: => String): F[Unit] =
Sync[F].delay(logger.info(msg))
def sinfo[F[_]: Sync](msg: => String): Stream[F, Nothing] =
Stream.eval(finfo(msg)).drain
def fwarn[F[_]: Sync](msg: => String): F[Unit] =
Sync[F].delay(logger.warn(msg))
def ferror[F[_]: Sync](msg: => String): F[Unit] =
Sync[F].delay(logger.error(msg))
def ferror[F[_]: Sync](ex: Throwable)(msg: => String): F[Unit] =
Sync[F].delay(logger.error(ex)(msg))
}
}

24
modules/common/src/main/scala/docspell/common/syntax/StreamSyntax.scala Normal file
View File

@ -0,0 +1,24 @@
package docspell.common.syntax
import cats.effect.Sync
import fs2.Stream
import cats.implicits._
import io.circe._
import io.circe.parser._
trait StreamSyntax {
implicit class StringStreamOps[F[_]](s: Stream[F, String]) {
def parseJsonAs[A](implicit d: Decoder[A], F: Sync[F]): F[Either[Throwable, A]] =
s.fold("")(_ + _).
compile.last.
map(optStr => for {
str <- optStr.map(_.trim).toRight(new Exception("Empty string cannot be parsed into a value"))
json <- parse(str).leftMap(_.underlying)
value <- json.as[A]
} yield value)
}
}

21
modules/common/src/main/scala/docspell/common/syntax/StringSyntax.scala Normal file
View File

@ -0,0 +1,21 @@
package docspell.common.syntax
import cats.implicits._
import io.circe.Decoder
import io.circe.parser._
trait StringSyntax {
implicit class EvenMoreStringOps(s: String) {
def asNonBlank: Option[String] =
Option(s).filter(_.trim.nonEmpty)
def parseJsonAs[A](implicit d: Decoder[A]): Either[Throwable, A] =
for {
json <- parse(s).leftMap(_.underlying)
value <- json.as[A]
} yield value
}
}

10
modules/common/src/main/scala/docspell/common/syntax/package.scala Normal file
View File

@ -0,0 +1,10 @@
package docspell.common
package object syntax {
object all extends EitherSyntax
with StreamSyntax
with StringSyntax
with LoggerSyntax
}

14
modules/joex/src/main/resources/logback.xml Normal file
View File

@ -0,0 +1,14 @@
<configuration>
<appender name="STDOUT" class="ch.qos.logback.core.ConsoleAppender">
<withJansi>true</withJansi>
<encoder>
<pattern>[%thread] %highlight(%-5level) %cyan(%logger{15}) - %msg %n</pattern>
</encoder>
</appender>
<logger name="docspell" level="debug" />
<root level="INFO">
<appender-ref ref="STDOUT" />
</root>
</configuration>

128
modules/joex/src/main/resources/reference.conf
View File

@ -1,3 +1,131 @@
docspell.joex {
# This is the id of this node. If you run more than one server, you
# have to make sure to provide unique ids per node.
app-id = "joex1"
# This is the base URL this application is deployed to. This is used
# to register this joex instance such that docspell rest servers can
# reach them
base-url = "http://localhost:7878"
# Where the REST server binds to.
#
# JOEX provides a very simple REST interface to inspect its state.
bind {
address = "localhost"
port = 7878
}
# The database connection.
#
# By default a H2 file-based database is configured. You can provide
# a postgresql or mariadb connection here. When using H2 use the
# PostgreSQL compatibility mode and AUTO_SERVER feature.
#
# It must be the same connection as the rest server is using.
jdbc {
url = "jdbc:h2://"${java.io.tmpdir}"/docspell-demo.db;MODE=PostgreSQL;DATABASE_TO_LOWER=TRUE;AUTO_SERVER=TRUE"
user = "sa"
password = ""
}
# Configuration for the job scheduler.
scheduler {
# Each scheduler needs a unique name. This defaults to the node
# name, which must be unique, too.
name = ${docspell.joex.app-id}
# Number of processing allowed in parallel.
pool-size = 2
# A counting scheme determines the ratio of how high- and low-prio
# jobs are run. For example: 4,1 means run 4 high prio jobs, then
# 1 low prio and then start over.
counting-scheme = "4,1"
# How often a failed job should be retried until it enters failed
# state. If a job fails, it becomes "stuck" and will be retried
# after a delay.
retries = 5
# The delay until the next try is performed for a failed job. This
# delay is increased exponentially with the number of retries.
retry-delay = "1 minute"
# The queue size of log statements from a job.
log-buffer-size = 500
# If no job is left in the queue, the scheduler will wait until a
# notify is requested (using the REST interface). To also retry
# stuck jobs, it will notify itself periodically.
wakeup-period = "30 minutes"
}
# Configuration of text extraction
#
# Extracting text currently only work for image and pdf files. It
# will first runs ghostscript to create a gray image from a
# pdf. Then unpaper is run to optimize the image for the upcoming
# ocr, which will be done by tesseract. All these programs must be
# available in your PATH or the absolute path can be specified
# below.
extraction {
allowed-content-types = [ "application/pdf", "image/jpeg", "image/png" ]
# Defines what pages to process. If a PDF with 600 pages is
# submitted, it is probably not necessary to scan through all of
# them. This would take a long time and occupy resources for no
# value. The first few pages should suffice. The default is first
# 10 pages.
#
# If you want all pages being processed, set this number to -1.
#
# Note: if you change the ghostscript command below, be aware that
# this setting (if not -1) will add another parameter to the
# beginning of the command.
page-range {
begin = 10
}
# The ghostscript command.
ghostscript {
command {
program = "gs"
args = [ "-dNOPAUSE"
, "-dBATCH"
, "-dSAFER"
, "-sDEVICE=tiffscaled8"
, "-sOutputFile={{outfile}}"
, "{{infile}}"
]
timeout = "5 minutes"
}
working-dir = ${java.io.tmpdir}"/docspell-extraction"
}
# The unpaper command.
unpaper {
command {
program = "unpaper"
args = [ "{{infile}}", "{{outfile}}" ]
timeout = "5 minutes"
}
}
# The tesseract command.
tesseract {
command {
program = "tesseract"
args = ["{{file}}"
, "stdout"
, "-l"
, "{{lang}}"
]
timeout = "5 minutes"
}
}
}
}

15
modules/joex/src/main/scala/docspell/joex/Config.scala
View File

@ -1,18 +1,21 @@
package docspell.joex
import docspell.common.{Ident, LenientUri}
import docspell.joex.scheduler.SchedulerConfig
import docspell.store.JdbcConfig
import docspell.text.ocr.{Config => OcrConfig}
case class Config(id: String
case class Config(appId: Ident
, baseUrl: LenientUri
, bind: Config.Bind
, jdbc: JdbcConfig
, scheduler: SchedulerConfig
, extraction: OcrConfig
)
object Config {
val default: Config =
Config("testid", Config.Bind("localhost", 7878), JdbcConfig("", "", ""))
val postgres = JdbcConfig(LenientUri.unsafe("jdbc:postgresql://localhost:5432/docspelldev"), "dev", "dev")
val h2 = JdbcConfig(LenientUri.unsafe("jdbc:h2:./target/docspelldev.db;MODE=PostgreSQL;DATABASE_TO_LOWER=TRUE"), "sa", "")
case class Bind(address: String, port: Int)
}

20
modules/joex/src/main/scala/docspell/joex/ConfigFile.scala Normal file
View File

@ -0,0 +1,20 @@
package docspell.joex
import docspell.common.pureconfig.Implicits._
import _root_.pureconfig._
import _root_.pureconfig.generic.auto._
import docspell.joex.scheduler.CountingScheme
object ConfigFile {
import Implicits._
def loadConfig: Config =
ConfigSource.default.at("docspell.joex").loadOrThrow[Config]
object Implicits {
implicit val countingSchemeReader: ConfigReader[CountingScheme] =
ConfigReader[String].emap(reason(CountingScheme.readString))
}
}

17
modules/joex/src/main/scala/docspell/joex/JoexApp.scala
View File

@ -1,6 +1,23 @@
package docspell.joex
import docspell.common.Ident
import docspell.joex.scheduler.Scheduler
import docspell.store.records.RJobLog
trait JoexApp[F[_]] {
def init: F[Unit]
def scheduler: Scheduler[F]
def findLogs(jobId: Ident): F[Vector[RJobLog]]
/** Shuts down the job executor.
*
* It will immediately stop taking new jobs, waiting for currently
* running jobs to complete normally (i.e. running jobs are not
* canceled). After this completed, the webserver stops and the
* main loop will exit.
*/
def initShutdown: F[Unit]
}

50
modules/joex/src/main/scala/docspell/joex/JoexAppImpl.scala
View File

@ -1,16 +1,56 @@
package docspell.joex
import cats.implicits._
import cats.effect._
import docspell.common.{Ident, NodeType, ProcessItemArgs}
import docspell.joex.process.ItemHandler
import docspell.joex.scheduler.{JobTask, Scheduler, SchedulerBuilder}
import docspell.store.Store
import docspell.store.ops.ONode
import docspell.store.records.RJobLog
import fs2.concurrent.SignallingRef
final class JoexAppImpl[F[_]: Sync](cfg: Config) extends JoexApp[F] {
import scala.concurrent.ExecutionContext
def init: F[Unit] =
Sync[F].pure(())
final class JoexAppImpl[F[_]: ConcurrentEffect : ContextShift: Timer]( cfg: Config
, nodeOps: ONode[F]
, store: Store[F]
, termSignal: SignallingRef[F, Boolean]
, val scheduler: Scheduler[F]) extends JoexApp[F] {
def init: F[Unit] = {
val run = scheduler.start.compile.drain
for {
_ <- ConcurrentEffect[F].start(run)
_ <- scheduler.periodicAwake
_ <- nodeOps.register(cfg.appId, NodeType.Joex, cfg.baseUrl)
} yield ()
}
def findLogs(jobId: Ident): F[Vector[RJobLog]] =
store.transact(RJobLog.findLogs(jobId))
def shutdown: F[Unit] =
nodeOps.unregister(cfg.appId)
def initShutdown: F[Unit] =
scheduler.shutdown(false) *> termSignal.set(true)
}
object JoexAppImpl {
def create[F[_]: Sync](cfg: Config): Resource[F, JoexApp[F]] =
Resource.liftF(Sync[F].pure(new JoexAppImpl(cfg)))
def create[F[_]: ConcurrentEffect : ContextShift: Timer](cfg: Config
, termSignal: SignallingRef[F, Boolean]
, connectEC: ExecutionContext
, blocker: Blocker): Resource[F, JoexApp[F]] =
for {
store <- Store.create(cfg.jdbc, connectEC, blocker)
nodeOps <- ONode(store)
sch <- SchedulerBuilder(cfg.scheduler, blocker, store).
withTask(JobTask.json(ProcessItemArgs.taskName, ItemHandler[F](cfg.extraction), ItemHandler.onCancel[F])).
resource
app = new JoexAppImpl(cfg, nodeOps, store, termSignal, sch)
appR <- Resource.make(app.init.map(_ => app))(_.shutdown)
} yield appR
}

33
modules/joex/src/main/scala/docspell/joex/JoexServer.scala
View File

@ -1,37 +1,48 @@
package docspell.joex
import cats.effect._
import cats.effect.concurrent.Ref
import docspell.joex.routes._
import org.http4s.server.blaze.BlazeServerBuilder
import org.http4s.implicits._
import fs2.Stream
import fs2.concurrent.SignallingRef
import org.http4s.HttpApp
import org.http4s.server.middleware.Logger
import org.http4s.server.Router
import scala.concurrent.ExecutionContext
object JoexServer {
def stream[F[_]: ConcurrentEffect](cfg: Config)
private case class App[F[_]](httpApp: HttpApp[F], termSig: SignallingRef[F, Boolean], exitRef: Ref[F, ExitCode])
def stream[F[_]: ConcurrentEffect : ContextShift](cfg: Config, connectEC: ExecutionContext, blocker: Blocker)
(implicit T: Timer[F]): Stream[F, Nothing] = {
val app = for {
joexApp <- JoexAppImpl.create[F](cfg)
_ <- Resource.liftF(joexApp.init)
signal <- Resource.liftF(SignallingRef[F, Boolean](false))
exitCode <- Resource.liftF(Ref[F].of(ExitCode.Success))
joexApp <- JoexAppImpl.create[F](cfg, signal, connectEC, blocker)
httpApp = Router(
"/api/info" -> InfoRoutes(cfg)
"/api/info" -> InfoRoutes(cfg),
"/api/v1" -> JoexRoutes(cfg, joexApp)
).orNotFound
// With Middlewares in place
finalHttpApp = Logger.httpApp(false, false)(httpApp)
} yield finalHttpApp
} yield App(finalHttpApp, signal, exitCode)
Stream.resource(app).flatMap(httpApp =>
BlazeServerBuilder[F]
.bindHttp(cfg.bind.port, cfg.bind.address)
.withHttpApp(httpApp)
.serve
Stream.resource(app).flatMap(app =>
BlazeServerBuilder[F].
bindHttp(cfg.bind.port, cfg.bind.address).
withHttpApp(app.httpApp).
withoutBanner.
serveWhile(app.termSig, app.exitRef)
)
}.drain

22
modules/joex/src/main/scala/docspell/joex/Main.scala
View File

@ -1,16 +1,23 @@
package docspell.joex
import cats.effect.{ExitCode, IO, IOApp}
import cats.effect.{Blocker, ExitCode, IO, IOApp}
import cats.implicits._
import scala.concurrent.ExecutionContext
import java.util.concurrent.Executors
import java.nio.file.{Files, Paths}
import docspell.common.{Banner, ThreadFactories}
import org.log4s._
object Main extends IOApp {
private[this] val logger = getLogger
val blockingEc: ExecutionContext = ExecutionContext.fromExecutor(Executors.newCachedThreadPool)
val blockingEc: ExecutionContext = ExecutionContext.fromExecutor(
Executors.newCachedThreadPool(ThreadFactories.ofName("docspell-joex-blocking")))
val blocker = Blocker.liftExecutionContext(blockingEc)
val connectEC: ExecutionContext = ExecutionContext.fromExecutorService(
Executors.newFixedThreadPool(5, ThreadFactories.ofName("docspell-joex-dbconnect")))
def run(args: List[String]) = {
args match {
@ -32,7 +39,14 @@ object Main extends IOApp {
}
}
val cfg = Config.default
JoexServer.stream[IO](cfg).compile.drain.as(ExitCode.Success)
val cfg = ConfigFile.loadConfig
val banner = Banner("JOEX"
, BuildInfo.version
, BuildInfo.gitHeadCommit
, cfg.jdbc.url
, Option(System.getProperty("config.file"))
, cfg.appId, cfg.baseUrl)
logger.info(s"\n${banner.render("***>")}")
JoexServer.stream[IO](cfg, connectEC, blocker).compile.drain.as(ExitCode.Success)
}
}

73
modules/joex/src/main/scala/docspell/joex/process/CreateItem.scala Normal file
View File

@ -0,0 +1,73 @@
package docspell.joex.process
import cats.implicits._
import cats.effect.Sync
import fs2.Stream
import docspell.common._
import docspell.joex.scheduler.{Context, Task}
import docspell.store.queries.QItem
import docspell.store.records.{RAttachment, RItem}
/**
* Task that creates the item.
*/
object CreateItem {
def apply[F[_]: Sync]: Task[F, ProcessItemArgs, ItemData] =
findExisting[F].flatMap {
case Some(ri) => Task.pure(ri)
case None => createNew[F]
}
def createNew[F[_]: Sync]: Task[F, ProcessItemArgs, ItemData] =
Task { ctx =>
val validFiles = ctx.args.meta.validFileTypes.map(_.asString).toSet
def fileMetas(itemId: Ident, now: Timestamp) = Stream.emits(ctx.args.files).
flatMap(f => ctx.store.bitpeace.get(f.fileMetaId.id).map(fm => (f, fm))).
collect({ case (f, Some(fm)) if validFiles.contains(fm.mimetype.baseType) => (f, fm) }).
zipWithIndex.
evalMap({ case ((f, fm), index) =>
Ident.randomId[F].map(id => RAttachment(id, itemId, f.fileMetaId, index.toInt, now, f.name))
}).
compile.toVector
val item = RItem.newItem[F](ctx.args.meta.collective
, ctx.args.makeSubject
, ctx.args.meta.sourceAbbrev
, ctx.args.meta.direction.getOrElse(Direction.Incoming)
, ItemState.Premature)
for {
_ <- ctx.logger.info(s"Creating new item with ${ctx.args.files.size} attachment(s)")
time <- Duration.stopTime[F]
it <- item
n <- ctx.store.transact(RItem.insert(it))
_ <- if (n != 1) storeItemError[F](ctx) else ().pure[F]
fm <- fileMetas(it.id, it.created)
k <- fm.traverse(a => ctx.store.transact(RAttachment.insert(a)))
_ <- logDifferences(ctx, fm, k.sum)
dur <- time
_ <- ctx.logger.info(s"Creating item finished in ${dur.formatExact}")
} yield ItemData(it, fm, Vector.empty, Vector.empty)
}
def findExisting[F[_]: Sync]: Task[F, ProcessItemArgs, Option[ItemData]] =
Task { ctx =>
for {
cand <- ctx.store.transact(QItem.findByFileIds(ctx.args.files.map(_.fileMetaId)))
_ <- if (cand.nonEmpty) ctx.logger.warn("Found existing item with these files.") else ().pure[F]
ht <- cand.drop(1).traverse(ri => QItem.delete(ctx.store)(ri.id, ri.cid))
_ <- if (ht.sum > 0) ctx.logger.warn(s"Removed ${ht.sum} items with same attachments") else ().pure[F]
rms <- cand.headOption.traverse(ri => ctx.store.transact(RAttachment.findByItemAndCollective(ri.id, ri.cid)))
} yield cand.headOption.map(ri => ItemData(ri, rms.getOrElse(Vector.empty), Vector.empty, Vector.empty))
}
private def logDifferences[F[_]: Sync](ctx: Context[F, ProcessItemArgs], saved: Vector[RAttachment], saveCount: Int): F[Unit] =
ctx.logger.info("TODO log diffs")
private def storeItemError[F[_]: Sync](ctx: Context[F, ProcessItemArgs]): F[Unit] = {
val msg = "Inserting item failed. DB returned 0 update count!"
ctx.logger.error(msg) *> Sync[F].raiseError(new Exception(msg))
}
}

181
modules/joex/src/main/scala/docspell/joex/process/FindProposal.scala Normal file
View File

@ -0,0 +1,181 @@
package docspell.joex.process
import java.time.ZoneId
import cats.{Applicative, FlatMap}
import cats.implicits._
import cats.effect.Sync
import docspell.common.MetaProposal.Candidate
import docspell.common._
import docspell.joex.scheduler.{Context, Task}
import docspell.store.records.{RAttachmentMeta, REquipment, ROrganization, RPerson}
import docspell.text.contact.Domain
/** Super simple approach to find corresponding meta data to an item
* by looking up values from NER in the users address book.
*
*/
object FindProposal {
def apply[F[_]: Sync](data: ItemData): Task[F, ProcessItemArgs, ItemData] =
Task { ctx =>
val rmas = data.metas.map(rm =>
rm.copy(nerlabels = removeDuplicates(rm.nerlabels)))
ctx.logger.info("Starting find-proposal") *>
rmas.traverse(rm => processAttachment(rm, data.findDates(rm), ctx).map(ml => rm.copy(proposals = ml))).
flatMap(rmv => rmv.traverse(rm =>
ctx.logger.debug(s"Storing attachment proposals: ${rm.proposals}") *>
ctx.store.transact(RAttachmentMeta.updateProposals(rm.id, rm.proposals))).
map(_ => data.copy(metas = rmv)))
}
def processAttachment[F[_]: Sync]( rm: RAttachmentMeta
, rd: Vector[NerDateLabel]
, ctx: Context[F, ProcessItemArgs]): F[MetaProposalList] = {
val finder = Finder.searchExact(ctx).next(Finder.searchFuzzy(ctx))
List(finder.find(rm.nerlabels), makeDateProposal(rd)).
traverse(identity).map(MetaProposalList.flatten)
}
def makeDateProposal[F[_]: Sync](dates: Vector[NerDateLabel]): F[MetaProposalList] = {
Timestamp.current[F].map { now =>
val latestFirst = dates.sortWith(_.date isAfter _.date)
val nowDate = now.value.atZone(ZoneId.of("GMT")).toLocalDate
val (after, before) = latestFirst.span(ndl => ndl.date.isAfter(nowDate))
val dueDates = MetaProposalList.fromSeq1(MetaProposalType.DueDate,
after.map(ndl => Candidate(IdRef(Ident.unsafe(ndl.date.toString), ndl.date.toString), Set(ndl.label))))
val itemDates = MetaProposalList.fromSeq1(MetaProposalType.DocDate,
before.map(ndl => Candidate(IdRef(Ident.unsafe(ndl.date.toString), ndl.date.toString), Set(ndl.label))))
MetaProposalList.flatten(Seq(dueDates, itemDates))
}
}
def removeDuplicates(labels: List[NerLabel]): List[NerLabel] =
labels.foldLeft((Set.empty[String], List.empty[NerLabel])) { case ((seen, result), el) =>
if (seen.contains(el.tag.name+el.label.toLowerCase)) (seen, result)
else (seen + (el.tag.name + el.label.toLowerCase), el :: result)
}._2.sortBy(_.startPosition)
trait Finder[F[_]] { self =>
def find(labels: Seq[NerLabel]): F[MetaProposalList]
def contraMap(f: Seq[NerLabel] => Seq[NerLabel]): Finder[F] =
labels => self.find(f(labels))
def filterLabels(f: NerLabel => Boolean): Finder[F] =
contraMap(_.filter(f))
def flatMap(f: MetaProposalList => Finder[F])(implicit F: FlatMap[F]): Finder[F] =
labels => self.find(labels).flatMap(ml => f(ml).find(labels))
def map(f: MetaProposalList => MetaProposalList)(implicit F: Applicative[F]): Finder[F] =
labels => self.find(labels).map(f)
def next(f: Finder[F])(implicit F: FlatMap[F], F3: Applicative[F]): Finder[F] =
flatMap({ ml0 =>
if (ml0.hasResultsAll) Finder.unit[F](ml0)
else f.map(ml1 => ml0.fillEmptyFrom(ml1))
})
def nextWhenEmpty(f: Finder[F], mt0: MetaProposalType, mts: MetaProposalType*)
(implicit F: FlatMap[F], F2: Applicative[F]): Finder[F] =
flatMap(res0 => {
if (res0.hasResults(mt0, mts: _*)) Finder.unit[F](res0)
else f.map(res1 => res0.fillEmptyFrom(res1))
})
}
object Finder {
def none[F[_]: Applicative]: Finder[F] =
_ => MetaProposalList.empty.pure[F]
def unit[F[_]: Applicative](value: MetaProposalList): Finder[F] =
_ => value.pure[F]
def searchExact[F[_]: Sync](ctx: Context[F, ProcessItemArgs]): Finder[F] =
labels => labels.toList.traverse(nl => search(nl, true, ctx)).map(MetaProposalList.flatten)
def searchFuzzy[F[_]: Sync](ctx: Context[F, ProcessItemArgs]): Finder[F] =
labels => labels.toList.traverse(nl => search(nl, false, ctx)).map(MetaProposalList.flatten)
}
private def search[F[_]: Sync](nt: NerLabel, exact: Boolean, ctx: Context[F, ProcessItemArgs]): F[MetaProposalList] = {
val value =
if (exact) normalizeSearchValue(nt.label)
else s"%${normalizeSearchValue(nt.label)}%"
val minLength =
if (exact) 2 else 5
if (value.length < minLength) {
ctx.logger.debug(s"Skipping too small value '$value' (original '${nt.label}').").map(_ => MetaProposalList.empty)
} else nt.tag match {
case NerTag.Organization =>
ctx.logger.debug(s"Looking for organizations: $value") *>
ctx.store.transact(ROrganization.findLike(ctx.args.meta.collective, value)).
map(MetaProposalList.from(MetaProposalType.CorrOrg, nt))
case NerTag.Person =>
val s1 = ctx.store.transact(RPerson.findLike(ctx.args.meta.collective, value, true)).
map(MetaProposalList.from(MetaProposalType.ConcPerson, nt))
val s2 = ctx.store.transact(RPerson.findLike(ctx.args.meta.collective, value, false)).
map(MetaProposalList.from(MetaProposalType.CorrPerson, nt))
ctx.logger.debug(s"Looking for persons: $value") *> (for {
ml0 <- s1
ml1 <- s2
} yield ml0 |+| ml1)
case NerTag.Location =>
ctx.logger.debug(s"NerTag 'Location' is currently not used. Ignoring value '$value'.").
map(_ => MetaProposalList.empty)
case NerTag.Misc =>
ctx.logger.debug(s"Looking for equipments: $value") *>
ctx.store.transact(REquipment.findLike(ctx.args.meta.collective, value)).
map(MetaProposalList.from(MetaProposalType.ConcEquip, nt))
case NerTag.Email =>
searchContact(nt, ContactKind.Email, value, ctx)
case NerTag.Website =>
if (!exact) {
val searchString = Domain.domainFromUri(nt.label.toLowerCase).
toOption.
map(_.toPrimaryDomain.asString).
map(s => s"%$s%").
getOrElse(value)
searchContact(nt, ContactKind.Website, searchString, ctx)
} else {
searchContact(nt, ContactKind.Website, value, ctx)
}
case NerTag.Date =>
// There is no database search required for this tag
MetaProposalList.empty.pure[F]
}
}
private def searchContact[F[_]: Sync]( nt: NerLabel
, kind: ContactKind
, value: String
, ctx: Context[F, ProcessItemArgs]): F[MetaProposalList] = {
val orgs = ctx.store.transact(ROrganization.findLike(ctx.args.meta.collective, kind, value)).
map(MetaProposalList.from(MetaProposalType.CorrOrg, nt))
val corrP = ctx.store.transact(RPerson.findLike(ctx.args.meta.collective, kind, value, false)).
map(MetaProposalList.from(MetaProposalType.CorrPerson, nt))
val concP = ctx.store.transact(RPerson.findLike(ctx.args.meta.collective, kind, value, true)).
map(MetaProposalList.from(MetaProposalType.CorrPerson, nt))
ctx.logger.debug(s"Looking with $kind: $value") *>
List(orgs, corrP, concP).traverse(identity).map(MetaProposalList.flatten)
}
// The backslash *must* be stripped from search strings.
private [this] val invalidSearch =
"…_[]^<>=&ſ/{}*?@#$|~`+%\"';\\".toSet
private def normalizeSearchValue(str: String): String =
str.toLowerCase.filter(c => !invalidSearch.contains(c))
}

27
modules/joex/src/main/scala/docspell/joex/process/ItemData.scala Normal file
View File

@ -0,0 +1,27 @@
package docspell.joex.process
import docspell.common.{Ident, NerDateLabel, NerLabel}
import docspell.joex.process.ItemData.AttachmentDates
import docspell.store.records.{RAttachment, RAttachmentMeta, RItem}
case class ItemData( item: RItem
, attachments: Vector[RAttachment]
, metas: Vector[RAttachmentMeta]
, dateLabels: Vector[AttachmentDates]) {
def findMeta(attachId: Ident): Option[RAttachmentMeta] =
metas.find(_.id == attachId)
def findDates(rm: RAttachmentMeta): Vector[NerDateLabel] =
dateLabels.find(m => m.rm.id == rm.id).map(_.dates).getOrElse(Vector.empty)
}
object ItemData {
case class AttachmentDates(rm: RAttachmentMeta, dates: Vector[NerDateLabel]) {
def toNerLabel: Vector[NerLabel] =
dates.map(dl => dl.label.copy(label = dl.date.toString))
}
}

62
modules/joex/src/main/scala/docspell/joex/process/ItemHandler.scala Normal file
View File

@ -0,0 +1,62 @@
package docspell.joex.process
import cats.implicits._
import cats.effect.{ContextShift, Sync}
import docspell.common.{ItemState, ProcessItemArgs}
import docspell.joex.scheduler.{Context, Task}
import docspell.store.queries.QItem
import docspell.store.records.{RItem, RJob}
import docspell.text.ocr.{Config => OcrConfig}
object ItemHandler {
def onCancel[F[_]: Sync: ContextShift]: Task[F, ProcessItemArgs, Unit] =
logWarn("Now cancelling. Deleting potentially created data.").
flatMap(_ => deleteByFileIds)
def apply[F[_]: Sync: ContextShift](cfg: OcrConfig): Task[F, ProcessItemArgs, Unit] =
CreateItem[F].
flatMap(itemStateTask(ItemState.Processing)).
flatMap(safeProcess[F](cfg)).
map(_ => ())
def itemStateTask[F[_]: Sync, A](state: ItemState)(data: ItemData): Task[F, A, ItemData] =
Task { ctx =>
ctx.store.transact(RItem.updateState(data.item.id, state)).map(_ => data)
}
def isLastRetry[F[_]: Sync, A](ctx: Context[F, A]): F[Boolean] =
for {
current <- ctx.store.transact(RJob.getRetries(ctx.jobId))
last = ctx.config.retries == current.getOrElse(0)
} yield last
def safeProcess[F[_]: Sync: ContextShift](cfg: OcrConfig)(data: ItemData): Task[F, ProcessItemArgs, ItemData] =
Task(isLastRetry[F, ProcessItemArgs] _).flatMap {
case true =>
ProcessItem[F](cfg)(data).
attempt.flatMap({
case Right(d) =>
Task.pure(d)
case Left(ex) =>
logWarn[F]("Processing failed on last retry. Creating item but without proposals.").
flatMap(_ => itemStateTask(ItemState.Created)(data)).
andThen(_ => Sync[F].raiseError(ex))
})
case false =>
ProcessItem[F](cfg)(data).
flatMap(itemStateTask(ItemState.Created))
}
def deleteByFileIds[F[_]: Sync: ContextShift]: Task[F, ProcessItemArgs, Unit] =
Task { ctx =>
for {
items <- ctx.store.transact(QItem.findByFileIds(ctx.args.files.map(_.fileMetaId)))
_ <- ctx.logger.info(s"Deleting items ${items.map(_.id.id)}")
_ <- items.traverse(i => QItem.delete(ctx.store)(i.id, ctx.args.meta.collective))
} yield ()
}
private def logWarn[F[_]](msg: => String): Task[F, ProcessItemArgs, Unit] =
Task(_.logger.warn(msg))
}

71
modules/joex/src/main/scala/docspell/joex/process/LinkProposal.scala Normal file
View File

@ -0,0 +1,71 @@
package docspell.joex.process
import cats.implicits._
import cats.effect.Sync
import docspell.common._
import docspell.joex.scheduler.{Context, Task}
import docspell.store.records.RItem
object LinkProposal {
def apply[F[_]: Sync](data: ItemData): Task[F, ProcessItemArgs, ItemData] =
Task { ctx =>
val proposals = MetaProposalList.flatten(data.metas.map(_.proposals))
ctx.logger.info(s"Starting linking proposals") *>
MetaProposalType.all.
traverse(applyValue(data, proposals, ctx)).
map(result => ctx.logger.info(s"Results from proposal processing: $result")).
map(_ => data)
}
def applyValue[F[_]: Sync](data: ItemData, proposalList: MetaProposalList, ctx: Context[F, ProcessItemArgs])(mpt: MetaProposalType): F[Result] = {
proposalList.find(mpt) match {
case None =>
Result.noneFound(mpt).pure[F]
case Some(a) if a.isSingleValue =>
ctx.logger.info(s"Found one candidate for ${a.proposalType}") *>
setItemMeta(data.item.id, ctx, a.proposalType, a.values.head.ref.id).
map(_ => Result.single(mpt))
case Some(a) =>
ctx.logger.info(s"Found many (${a.size}, ${a.values.map(_.ref.id.id)}) candidates for ${a.proposalType}. Setting first.") *>
setItemMeta(data.item.id, ctx, a.proposalType, a.values.head.ref.id).
map(_ => Result.multiple(mpt))
}
}
def setItemMeta[F[_]: Sync](itemId: Ident, ctx: Context[F, ProcessItemArgs], mpt: MetaProposalType, value: Ident): F[Int] =
mpt match {
case MetaProposalType.CorrOrg =>
ctx.logger.debug(s"Updating item organization with: ${value.id}") *>
ctx.store.transact(RItem.updateCorrOrg(itemId, ctx.args.meta.collective, Some(value)))
case MetaProposalType.ConcPerson =>
ctx.logger.debug(s"Updating item concerning person with: $value") *>
ctx.store.transact(RItem.updateConcPerson(itemId, ctx.args.meta.collective, Some(value)))
case MetaProposalType.CorrPerson =>
ctx.logger.debug(s"Updating item correspondent person with: $value") *>
ctx.store.transact(RItem.updateCorrPerson(itemId, ctx.args.meta.collective, Some(value)))
case MetaProposalType.ConcEquip =>
ctx.logger.debug(s"Updating item concerning equipment with: $value") *>
ctx.store.transact(RItem.updateConcEquip(itemId, ctx.args.meta.collective, Some(value)))
case MetaProposalType.DocDate =>
ctx.logger.debug(s"Not linking document date suggestion ${value.id}").map(_ => 0)
case MetaProposalType.DueDate =>
ctx.logger.debug(s"Not linking document date suggestion ${value.id}").map(_ => 0)
}
sealed trait Result {
def proposalType: MetaProposalType
}
object Result {
case class NoneFound(proposalType: MetaProposalType) extends Result
case class SingleResult(proposalType: MetaProposalType) extends Result
case class MultipleResult(proposalType: MetaProposalType) extends Result
def noneFound(proposalType: MetaProposalType): Result = NoneFound(proposalType)
def single(proposalType: MetaProposalType): Result = SingleResult(proposalType)
def multiple(proposalType: MetaProposalType): Result = MultipleResult(proposalType)
}
}

19
modules/joex/src/main/scala/docspell/joex/process/ProcessItem.scala Normal file
View File

@ -0,0 +1,19 @@
package docspell.joex.process
import cats.effect.{ContextShift, Sync}
import docspell.common.ProcessItemArgs
import docspell.joex.scheduler.Task
import docspell.text.ocr.{Config => OcrConfig}
object ProcessItem {
def apply[F[_]: Sync: ContextShift](cfg: OcrConfig)(item: ItemData): Task[F, ProcessItemArgs, ItemData] =
TextExtraction(cfg, item).
flatMap(Task.setProgress(25)).
flatMap(TextAnalysis[F]).
flatMap(Task.setProgress(50)).
flatMap(FindProposal[F]).
flatMap(Task.setProgress(75)).
flatMap(LinkProposal[F]).
flatMap(Task.setProgress(99))
}

39
modules/joex/src/main/scala/docspell/joex/process/TestTasks.scala Normal file
View File

@ -0,0 +1,39 @@
package docspell.joex.process
import cats.implicits._
import cats.effect.Sync
import docspell.common.ProcessItemArgs
import docspell.common.syntax.all._
import docspell.joex.scheduler.Task
import org.log4s._
object TestTasks {
private [this] val logger = getLogger
def success[F[_]]: Task[F, ProcessItemArgs, Unit] =
Task { ctx =>
ctx.logger.info(s"Running task now: ${ctx.args}")
}
def failing[F[_]: Sync]: Task[F, ProcessItemArgs, Unit] =
Task { ctx =>
ctx.logger.info(s"Failing the task run :(").map(_ =>
sys.error("Oh, cannot extract gold from this document")
)
}
def longRunning[F[_]: Sync]: Task[F, ProcessItemArgs, Unit] =
Task { ctx =>
logger.fwarn(s"${Thread.currentThread()} From executing long running task") >>
ctx.logger.info(s"${Thread.currentThread()} Running task now: ${ctx.args}") >>
sleep(2400) >>
ctx.logger.debug("doing things") >>
sleep(2400) >>
ctx.logger.debug("doing more things") >>
sleep(2400) >>
ctx.logger.info("doing more things")
}
private def sleep[F[_]:Sync](ms: Long): F[Unit] =
Sync[F].delay(Thread.sleep(ms))
}

49
modules/joex/src/main/scala/docspell/joex/process/TextAnalysis.scala Normal file
View File

@ -0,0 +1,49 @@
package docspell.joex.process
import cats.implicits._
import cats.effect.Sync
import docspell.common.{Duration, Language, NerLabel, ProcessItemArgs}
import docspell.joex.process.ItemData.AttachmentDates
import docspell.joex.scheduler.Task
import docspell.store.records.RAttachmentMeta
import docspell.text.contact.Contact
import docspell.text.date.DateFind
import docspell.text.nlp.StanfordNerClassifier
object TextAnalysis {
def apply[F[_]: Sync](item: ItemData): Task[F, ProcessItemArgs, ItemData] =
Task { ctx =>
for {
_ <- ctx.logger.info("Starting text analysis")
s <- Duration.stopTime[F]
t <- item.metas.toList.traverse(annotateAttachment[F](ctx.args.meta.language))
_ <- ctx.logger.debug(s"Storing tags: ${t.map(_._1.copy(content = None))}")
_ <- t.traverse(m => ctx.store.transact(RAttachmentMeta.updateLabels(m._1.id, m._1.nerlabels)))
e <- s
_ <- ctx.logger.info(s"Text-Analysis finished in ${e.formatExact}")
v = t.toVector
} yield item.copy(metas = v.map(_._1), dateLabels = v.map(_._2))
}
def annotateAttachment[F[_]: Sync](lang: Language)(rm: RAttachmentMeta): F[(RAttachmentMeta, AttachmentDates)] =
for {
list0 <- stanfordNer[F](lang, rm)
list1 <- contactNer[F](rm)
dates <- dateNer[F](rm, lang)
} yield (rm.copy(nerlabels = (list0 ++ list1 ++ dates.toNerLabel).toList), dates)
def stanfordNer[F[_]: Sync](lang: Language, rm: RAttachmentMeta): F[Vector[NerLabel]] = Sync[F].delay {
rm.content.map(StanfordNerClassifier.nerAnnotate(lang)).getOrElse(Vector.empty)
}
def contactNer[F[_]: Sync](rm: RAttachmentMeta): F[Vector[NerLabel]] = Sync[F].delay {
rm.content.map(Contact.annotate).getOrElse(Vector.empty)
}
def dateNer[F[_]: Sync](rm: RAttachmentMeta, lang: Language): F[AttachmentDates] = Sync[F].delay {
AttachmentDates(rm, rm.content.map(txt => DateFind.findDates(txt, lang).toVector).getOrElse(Vector.empty))
}
}

45
modules/joex/src/main/scala/docspell/joex/process/TextExtraction.scala Normal file
View File

@ -0,0 +1,45 @@
package docspell.joex.process
import bitpeace.RangeDef
import cats.implicits._
import cats.effect.{Blocker, ContextShift, Sync}
import docspell.common.{Duration, Language, ProcessItemArgs}
import docspell.joex.scheduler.{Context, Task}
import docspell.store.Store
import docspell.store.records.{RAttachment, RAttachmentMeta}
import docspell.text.ocr.{TextExtract, Config => OcrConfig}
object TextExtraction {
def apply[F[_]: Sync : ContextShift](cfg: OcrConfig, item: ItemData): Task[F, ProcessItemArgs, ItemData] =
Task { ctx =>
for {
_ <- ctx.logger.info("Starting text extraction")
start <- Duration.stopTime[F]
txt <- item.attachments.traverse(extractTextToMeta(ctx, cfg, ctx.args.meta.language))
_ <- ctx.logger.debug("Storing extracted texts")
_ <- txt.toList.traverse(rm => ctx.store.transact(RAttachmentMeta.upsert(rm)))
dur <- start
_ <- ctx.logger.info(s"Text extraction finished in ${dur.formatExact}")
} yield item.copy(metas = txt)
}
def extractTextToMeta[F[_]: Sync : ContextShift](ctx: Context[F, _], cfg: OcrConfig, lang: Language)(ra: RAttachment): F[RAttachmentMeta] =
for {
_ <- ctx.logger.debug(s"Extracting text for attachment ${ra.name}")
dst <- Duration.stopTime[F]
txt <- extractText(cfg, lang, ctx.store, ctx.blocker)(ra)
meta = RAttachmentMeta.empty(ra.id).copy(content = txt.map(_.trim).filter(_.nonEmpty))
est <- dst
_ <- ctx.logger.debug(s"Extracting text for attachment ${ra.name} finished in ${est.formatExact}")
} yield meta
def extractText[F[_]: Sync : ContextShift](ocrConfig: OcrConfig, lang: Language, store: Store[F], blocker: Blocker)(ra: RAttachment): F[Option[String]] = {
val data = store.bitpeace.get(ra.fileId.id).
unNoneTerminate.
through(store.bitpeace.fetchData2(RangeDef.all))
TextExtract.extract(data, blocker, lang.iso3, ocrConfig).
compile.last
}
}

10
modules/joex/src/main/scala/docspell/joex/InfoRoutes.scala → modules/joex/src/main/scala/docspell/joex/routes/InfoRoutes.scala
View File

@ -1,14 +1,12 @@
package docspell.joex
package docspell.joex.routes
import cats.effect._
import org.http4s._
import cats.effect.Sync
import docspell.joex.{BuildInfo, Config}
import docspell.joexapi.model.VersionInfo
import org.http4s.HttpRoutes
import org.http4s.dsl.Http4sDsl
import org.http4s.circe.CirceEntityEncoder._
import docspell.joexapi.model._
import docspell.joex.BuildInfo
object InfoRoutes {
def apply[F[_]: Sync](cfg: Config): HttpRoutes[F] = {

59
modules/joex/src/main/scala/docspell/joex/routes/JoexRoutes.scala Normal file
View File

@ -0,0 +1,59 @@
package docspell.joex.routes
import cats.implicits._
import cats.effect._
import docspell.common.{Duration, Ident, Timestamp}
import docspell.joex.{Config, JoexApp}
import docspell.joexapi.model._
import docspell.store.records.{RJob, RJobLog}
import org.http4s.HttpRoutes
import org.http4s.dsl.Http4sDsl
import org.http4s.circe.CirceEntityEncoder._
object JoexRoutes {
def apply[F[_]: ConcurrentEffect: Timer](cfg: Config, app: JoexApp[F]): HttpRoutes[F] = {
val dsl = new Http4sDsl[F]{}
import dsl._
HttpRoutes.of[F] {
case POST -> Root / "notify" =>
for {
_ <- app.scheduler.notifyChange
resp <- Ok(BasicResult(true, "Scheduler notified."))
} yield resp
case GET -> Root / "running" =>
for {
jobs <- app.scheduler.getRunning
jj = jobs.map(mkJob)
resp <- Ok(JobList(jj.toList))
} yield resp
case POST -> Root / "shutdownAndExit" =>
for {
_ <- ConcurrentEffect[F].start(Timer[F].sleep(Duration.seconds(1).toScala) *> app.initShutdown)
resp <- Ok(BasicResult(true, "Shutdown initiated."))
} yield resp
case GET -> Root / "job" / Ident(id) =>
for {
optJob <- app.scheduler.getRunning.map(_.find(_.id == id))
optLog <- optJob.traverse(j => app.findLogs(j.id))
jAndL = for { job <- optJob; log <- optLog } yield mkJobLog(job, log)
resp <- jAndL.map(Ok(_)).getOrElse(NotFound(BasicResult(false, "Not found")))
} yield resp
case POST -> Root / "job" / Ident(id) / "cancel" =>
for {
flag <- app.scheduler.requestCancel(id)
resp <- Ok(BasicResult(flag, if (flag) "Cancel request submitted" else "Job not found"))
} yield resp
}
}
def mkJob(j: RJob): Job =
Job(j.id, j.subject, j.submitted, j.priority, j.retries, j.progress, j.started.getOrElse(Timestamp.Epoch))
def mkJobLog(j: RJob, jl: Vector[RJobLog]): JobAndLog =
JobAndLog(mkJob(j), jl.map(r => JobLogEvent(r.created, r.level, r.message)).toList)
}

69
modules/joex/src/main/scala/docspell/joex/scheduler/Context.scala Normal file
View File

@ -0,0 +1,69 @@
package docspell.joex.scheduler
import cats.Functor
import cats.effect.{Blocker, Concurrent}
import cats.implicits._
import docspell.common.Ident
import docspell.store.Store
import docspell.store.records.RJob
import docspell.common.syntax.all._
import org.log4s.{Logger => _, _}
trait Context[F[_], A] { self =>
def jobId: Ident
def args: A
def config: SchedulerConfig
def logger: Logger[F]
def setProgress(percent: Int): F[Unit]
def store: Store[F]
def blocker: Blocker
def map[C](f: A => C)(implicit F: Functor[F]): Context[F, C] =
new Context.ContextImpl[F, C](f(args), logger, store, blocker, config, jobId)
}
object Context {
private [this] val log = getLogger
def create[F[_]: Functor, A]( job: RJob
, arg: A
, config: SchedulerConfig
, log: Logger[F]
, store: Store[F]
, blocker: Blocker): Context[F, A] =
new ContextImpl(arg, log, store, blocker, config, job.id)
def apply[F[_]: Concurrent, A]( job: RJob
, arg: A
, config: SchedulerConfig
, logSink: LogSink[F]
, blocker: Blocker
, store: Store[F]): F[Context[F, A]] =
for {
_ <- log.ftrace("Creating logger for task run")
logger <- Logger(job.id, job.info, config.logBufferSize, logSink)
_ <- log.ftrace("Logger created, instantiating context")
ctx = create[F, A](job, arg, config, logger, store, blocker)
} yield ctx
private final class ContextImpl[F[_]: Functor, A]( val args: A
, val logger: Logger[F]
, val store: Store[F]
, val blocker: Blocker
, val config: SchedulerConfig
, val jobId: Ident)
extends Context[F,A] {
def setProgress(percent: Int): F[Unit] = {
val pval = math.min(100, math.max(0, percent))
store.transact(RJob.setProgress(jobId, pval)).map(_ => ())
}
}
}

40
modules/joex/src/main/scala/docspell/joex/scheduler/CountingScheme.scala Normal file
View File

@ -0,0 +1,40 @@
package docspell.joex.scheduler
import cats.implicits._
import docspell.common.Priority
/** A counting scheme to indicate a ratio between scheduling high and
* low priority jobs.
*
* For example high=4, low=1 means: ”schedule 4 high priority jobs
* and then 1 low priority job“.
*/
case class CountingScheme(high: Int, low: Int, counter: Int = 0) {
def nextPriority: (CountingScheme, Priority) = {
if (counter <= 0) (increment, Priority.High)
else {
val rest = counter % (high + low)
if (rest < high) (increment, Priority.High)
else (increment, Priority.Low)
}
}
def increment: CountingScheme =
copy(counter = counter + 1)
}
object CountingScheme {
def writeString(cs: CountingScheme): String =
s"${cs.high},${cs.low}"
def readString(str: String): Either[String, CountingScheme] =
str.split(',') match {
case Array(h, l) =>
Either.catchNonFatal(CountingScheme(h.toInt, l.toInt)).
left.map(_.getMessage)
case _ =>
Left(s"Invalid counting scheme: $str")
}
}

33
modules/joex/src/main/scala/docspell/joex/scheduler/JobTask.scala Normal file
View File

@ -0,0 +1,33 @@
package docspell.joex.scheduler
import cats.implicits._
import cats.effect.Sync
import docspell.common.Ident
import docspell.common.syntax.all._
import io.circe.Decoder
/**
* Binds a Task to a name. This is required to lookup the code based
* on the taskName in the RJob data and to execute it given the
* arguments that have to be read from a string.
*
* Since the scheduler only has a string for the task argument, this
* only works for Task impls that accept a string. There is a
* convenience constructor that uses circe to decode json into some
* type A.
*/
case class JobTask[F[_]](name: Ident, task: Task[F, String, Unit], onCancel: Task[F, String, Unit])
object JobTask {
def json[F[_]: Sync, A](name: Ident, task: Task[F, A, Unit], onCancel: Task[F, A, Unit])
(implicit D: Decoder[A]): JobTask[F] = {
val convert: String => F[A] =
str => str.parseJsonAs[A] match {
case Right(a) => a.pure[F]
case Left(ex) => Sync[F].raiseError(new Exception(s"Cannot parse task arguments: $str", ex))
}
JobTask(name, task.contramap(convert), onCancel.contramap(convert))
}
}

26
modules/joex/src/main/scala/docspell/joex/scheduler/JobTaskRegistry.scala Normal file
View File

@ -0,0 +1,26 @@
package docspell.joex.scheduler
import docspell.common.Ident
/**
* This is a mapping from some identifier to a task. This is used by
* the scheduler to lookup an implementation using the taskName field
* of the RJob database record.
*/
final class JobTaskRegistry[F[_]](tasks: Map[Ident, JobTask[F]]) {
def withTask(task: JobTask[F]): JobTaskRegistry[F] =
JobTaskRegistry(tasks.updated(task.name, task))
def find(taskName: Ident): Option[JobTask[F]] =
tasks.get(taskName)
}
object JobTaskRegistry {
def apply[F[_]](map: Map[Ident, JobTask[F]]): JobTaskRegistry[F] =
new JobTaskRegistry[F](map)
def empty[F[_]]: JobTaskRegistry[F] = apply(Map.empty)
}

25
modules/joex/src/main/scala/docspell/joex/scheduler/LogEvent.scala Normal file
View File

@ -0,0 +1,25 @@
package docspell.joex.scheduler
import cats.implicits._
import docspell.common._
import cats.effect.Sync
case class LogEvent( jobId: Ident
, jobInfo: String
, time: Timestamp
, level: LogLevel
, msg: String
, ex: Option[Throwable] = None) {
def logLine: String =
s">>> ${time.asString} $level $jobInfo: $msg"
}
object LogEvent {
def create[F[_]: Sync](jobId: Ident, jobInfo: String, level: LogLevel, msg: String): F[LogEvent] =
Timestamp.current[F].map(now => LogEvent(jobId, jobInfo, now, level, msg))
}

59
modules/joex/src/main/scala/docspell/joex/scheduler/LogSink.scala Normal file
View File

@ -0,0 +1,59 @@
package docspell.joex.scheduler
import cats.implicits._
import cats.effect.{Concurrent, Sync}
import fs2.{Pipe, Stream}
import org.log4s.{LogLevel => _, _}
import docspell.common._
import docspell.common.syntax.all._
import docspell.store.Store
import docspell.store.records.RJobLog
trait LogSink[F[_]] {
def receive: Pipe[F, LogEvent, Unit]
}
object LogSink {
private[this] val logger = getLogger
def apply[F[_]](sink: Pipe[F, LogEvent, Unit]): LogSink[F] =
new LogSink[F] {
val receive = sink
}
def logInternal[F[_]: Sync](e: LogEvent): F[Unit] =
e.level match {
case LogLevel.Info =>
logger.finfo(e.logLine)
case LogLevel.Debug =>
logger.fdebug(e.logLine)
case LogLevel.Warn =>
logger.fwarn(e.logLine)
case LogLevel.Error =>
e.ex match {
case Some(exc) =>
logger.ferror(exc)(e.logLine)
case None =>
logger.ferror(e.logLine)
}
}
def printer[F[_]: Sync]: LogSink[F] =
LogSink(_.evalMap(e => logInternal(e)))
def db[F[_]: Sync](store: Store[F]): LogSink[F] =
LogSink(_.evalMap(ev => for {
id <- Ident.randomId[F]
joblog = RJobLog(id, ev.jobId, ev.level, ev.time, ev.msg + ev.ex.map(th => ": "+ th.getMessage).getOrElse(""))
_ <- logInternal(ev)
_ <- store.transact(RJobLog.insert(joblog))
} yield ()))
def dbAndLog[F[_]: Concurrent](store: Store[F]): LogSink[F] = {
val s: Stream[F, Pipe[F, LogEvent, Unit]] =
Stream.emits(Seq(printer[F].receive, db[F](store).receive))
LogSink(Pipe.join(s))
}
}

49
modules/joex/src/main/scala/docspell/joex/scheduler/Logger.scala Normal file
View File

@ -0,0 +1,49 @@
package docspell.joex.scheduler
import cats.implicits._
import cats.effect.{Concurrent, Sync}
import docspell.common._
import fs2.concurrent.Queue
trait Logger[F[_]] {
def trace(msg: => String): F[Unit]
def debug(msg: => String): F[Unit]
def info(msg: => String): F[Unit]
def warn(msg: => String): F[Unit]
def error(ex: Throwable)(msg: => String): F[Unit]
def error(msg: => String): F[Unit]
}
object Logger {
def create[F[_]: Sync](jobId: Ident, jobInfo: String, q: Queue[F, LogEvent]): Logger[F] =
new Logger[F] {
def trace(msg: => String): F[Unit] =
LogEvent.create[F](jobId, jobInfo, LogLevel.Debug, msg).flatMap(q.enqueue1)
def debug(msg: => String): F[Unit] =
LogEvent.create[F](jobId, jobInfo, LogLevel.Debug, msg).flatMap(q.enqueue1)
def info(msg: => String): F[Unit] =
LogEvent.create[F](jobId, jobInfo, LogLevel.Info, msg).flatMap(q.enqueue1)
def warn(msg: => String): F[Unit] =
LogEvent.create[F](jobId, jobInfo, LogLevel.Warn, msg).flatMap(q.enqueue1)
def error(ex: Throwable)(msg: => String): F[Unit] =
LogEvent.create[F](jobId, jobInfo, LogLevel.Error, msg).map(le => le.copy(ex = Some(ex))).flatMap(q.enqueue1)
def error(msg: => String): F[Unit] =
LogEvent.create[F](jobId, jobInfo, LogLevel.Error, msg).flatMap(q.enqueue1)
}
def apply[F[_]: Concurrent](jobId: Ident, jobInfo: String, bufferSize: Int, sink: LogSink[F]): F[Logger[F]] =
for {
q <- Queue.circularBuffer[F, LogEvent](bufferSize)
log = create(jobId, jobInfo, q)
fib <- Concurrent[F].start(q.dequeue.through(sink.receive).compile.drain)
} yield log
}

33
modules/joex/src/main/scala/docspell/joex/scheduler/Scheduler.scala Normal file
View File

@ -0,0 +1,33 @@
package docspell.joex.scheduler
import cats.effect.{Fiber, Timer}
import fs2.Stream
import docspell.common.Ident
import docspell.store.records.RJob
trait Scheduler[F[_]] {
def config: SchedulerConfig
def getRunning: F[Vector[RJob]]
def requestCancel(jobId: Ident): F[Boolean]
def notifyChange: F[Unit]
def start: Stream[F, Nothing]
/** Requests to shutdown the scheduler.
*
* The scheduler will not take any new jobs from the queue. If
* there are still running jobs, it waits for them to complete.
* when the cancelAll flag is set to true, it cancels all running
* jobs.
*
* The returned F[Unit] can be evaluated to wait for all that to
* complete.
*/
def shutdown(cancelAll: Boolean): F[Unit]
def periodicAwake(implicit T: Timer[F]): F[Fiber[F, Unit]]
}

66
modules/joex/src/main/scala/docspell/joex/scheduler/SchedulerBuilder.scala Normal file
View File

@ -0,0 +1,66 @@
package docspell.joex.scheduler
import cats.implicits._
import cats.effect.concurrent.Semaphore
import cats.effect.{Blocker, ConcurrentEffect, ContextShift, Resource}
import docspell.store.Store
import docspell.store.queue.JobQueue
import fs2.concurrent.SignallingRef
case class SchedulerBuilder[F[_]: ConcurrentEffect : ContextShift](
config: SchedulerConfig
, tasks: JobTaskRegistry[F]
, store: Store[F]
, blocker: Blocker
, queue: Resource[F, JobQueue[F]]
, logSink: LogSink[F]) {
def withConfig(cfg: SchedulerConfig): SchedulerBuilder[F] =
copy(config = cfg)
def withTaskRegistry(reg: JobTaskRegistry[F]): SchedulerBuilder[F] =
copy(tasks = reg)
def withTask[A](task: JobTask[F]): SchedulerBuilder[F] =
withTaskRegistry(tasks.withTask(task))
def withQueue(queue: Resource[F, JobQueue[F]]): SchedulerBuilder[F] =
SchedulerBuilder[F](config, tasks, store, blocker, queue, logSink)
def withBlocker(blocker: Blocker): SchedulerBuilder[F] =
copy(blocker = blocker)
def withLogSink(sink: LogSink[F]): SchedulerBuilder[F] =
copy(logSink = sink)
def serve: Resource[F, Scheduler[F]] =
resource.evalMap(sch => ConcurrentEffect[F].start(sch.start.compile.drain).map(_ => sch))
def resource: Resource[F, Scheduler[F]] = {
val scheduler = for {
jq <- queue
waiter <- Resource.liftF(SignallingRef(true))
state <- Resource.liftF(SignallingRef(SchedulerImpl.emptyState[F]))
perms <- Resource.liftF(Semaphore(config.poolSize.toLong))
} yield new SchedulerImpl[F](config, blocker, jq, tasks, store, logSink, state, waiter, perms)
scheduler.evalTap(_.init).
map(s => s: Scheduler[F])
}
}
object SchedulerBuilder {
def apply[F[_]: ConcurrentEffect : ContextShift]( config: SchedulerConfig
, blocker: Blocker
, store: Store[F]): SchedulerBuilder[F] =
new SchedulerBuilder[F](config
, JobTaskRegistry.empty[F]
, store
, blocker
, JobQueue(store)
, LogSink.db[F](store))
}

25
modules/joex/src/main/scala/docspell/joex/scheduler/SchedulerConfig.scala Normal file
View File

@ -0,0 +1,25 @@
package docspell.joex.scheduler
import docspell.common._
case class SchedulerConfig( name: Ident
, poolSize: Int
, countingScheme: CountingScheme
, retries: Int
, retryDelay: Duration
, logBufferSize: Int
, wakeupPeriod: Duration
)
object SchedulerConfig {
val default = SchedulerConfig(
name = Ident.unsafe("default-scheduler")
, poolSize = 2 // math.max(2, Runtime.getRuntime.availableProcessors / 2)
, countingScheme = CountingScheme(2, 1)
, retries = 5
, retryDelay = Duration.seconds(30)
, logBufferSize = 500
, wakeupPeriod = Duration.minutes(10)
)
}

227
modules/joex/src/main/scala/docspell/joex/scheduler/SchedulerImpl.scala Normal file
View File

@ -0,0 +1,227 @@
package docspell.joex.scheduler
import fs2.Stream
import cats.implicits._
import cats.effect.concurrent.Semaphore
import docspell.common._
import docspell.common.syntax.all._
import docspell.store.queue.JobQueue
import docspell.store.records.RJob
import fs2.concurrent.SignallingRef
import cats.effect._
import org.log4s._
import SchedulerImpl._
import docspell.store.Store
import docspell.store.queries.QJob
final class SchedulerImpl[F[_]: ConcurrentEffect : ContextShift](val config: SchedulerConfig
, blocker: Blocker
, queue: JobQueue[F]
, tasks: JobTaskRegistry[F]
, store: Store[F]
, logSink: LogSink[F]
, state: SignallingRef[F, State[F]]
, waiter: SignallingRef[F, Boolean]
, permits: Semaphore[F]) extends Scheduler[F] {
private [this] val logger = getLogger
/**
* On startup, get all jobs in state running from this scheduler
* and put them into waiting state, so they get picked up again.
*/
def init: F[Unit] =
QJob.runningToWaiting(config.name, store)
def periodicAwake(implicit T: Timer[F]): F[Fiber[F, Unit]] =
ConcurrentEffect[F].start(Stream.awakeEvery[F](config.wakeupPeriod.toScala).
evalMap(_ => logger.fdebug("Periodic awake reached") *> notifyChange).compile.drain)
def getRunning: F[Vector[RJob]] =
state.get.flatMap(s => QJob.findAll(s.getRunning, store))
def requestCancel(jobId: Ident): F[Boolean] =
state.get.flatMap(_.cancelRequest(jobId) match {
case Some(ct) => ct.map(_ => true)
case None => logger.fwarn(s"Job ${jobId.id} not found, cannot cancel.").map(_ => false)
})
def notifyChange: F[Unit] =
waiter.update(b => !b)
def shutdown(cancelAll: Boolean): F[Unit] = {
val doCancel =
state.get.
flatMap(_.cancelTokens.values.toList.traverse(identity)).
map(_ => ())
val runShutdown =
state.modify(_.requestShutdown) *> (if (cancelAll) doCancel else ().pure[F])
val wait = Stream.eval(runShutdown).
evalMap(_ => logger.finfo("Scheduler is shutting down now.")).
flatMap(_ => Stream.eval(state.get) ++ Stream.suspend(state.discrete.takeWhile(_.getRunning.nonEmpty))).
flatMap(state => {
if (state.getRunning.isEmpty) Stream.eval(logger.finfo("No jobs running."))
else Stream.eval(logger.finfo(s"Waiting for ${state.getRunning.size} jobs to finish.")) ++
Stream.emit(state)
})
(wait.drain ++ Stream.emit(())).compile.lastOrError
}
def start: Stream[F, Nothing] =
logger.sinfo("Starting scheduler") ++
mainLoop
def mainLoop: Stream[F, Nothing] = {
val body: F[Boolean] =
for {
_ <- permits.available.flatMap(a => logger.fdebug(s"Try to acquire permit ($a free)"))
_ <- permits.acquire
_ <- logger.fdebug("New permit acquired")
down <- state.get.map(_.shutdownRequest)
rjob <- if (down) logger.finfo("") *> permits.release *> (None: Option[RJob]).pure[F]
else queue.nextJob(group => state.modify(_.nextPrio(group, config.countingScheme)), config.name, config.retryDelay)
_ <- logger.fdebug(s"Next job found: ${rjob.map(_.info)}")
_ <- rjob.map(execute).getOrElse(permits.release)
} yield rjob.isDefined
Stream.eval(state.get.map(_.shutdownRequest)).
evalTap(if (_) logger.finfo[F]("Stopping main loop due to shutdown request.") else ().pure[F]).
flatMap(if (_) Stream.empty else Stream.eval(body)).
flatMap({
case true =>
mainLoop
case false =>
logger.sdebug(s"Waiting for notify") ++
waiter.discrete.take(2).drain ++
logger.sdebug(s"Notify signal, going into main loop") ++
mainLoop
})
}
def execute(job: RJob): F[Unit] = {
val task = for {
jobtask <- tasks.find(job.task).toRight(s"This executor cannot run tasks with name: ${job.task}")
} yield jobtask
task match {
case Left(err) =>
logger.ferror(s"Unable to start a task for job ${job.info}: $err")
case Right(t) =>
for {
_ <- logger.fdebug(s"Creating context for job ${job.info} to run $t")
ctx <- Context[F, String](job, job.args, config, logSink, blocker, store)
jot = wrapTask(job, t.task, ctx)
tok <- forkRun(job, jot.run(ctx), t.onCancel.run(ctx), ctx)
_ <- state.modify(_.addRunning(job, tok))
} yield ()
}
}
def onFinish(job: RJob, finalState: JobState): F[Unit] =
for {
_ <- logger.fdebug(s"Job ${job.info} done $finalState. Releasing resources.")
_ <- permits.release *> permits.available.flatMap(a => logger.fdebug(s"Permit released ($a free)"))
_ <- state.modify(_.removeRunning(job))
_ <- QJob.setFinalState(job.id, finalState, store)
} yield ()
def onStart(job: RJob): F[Unit] =
QJob.setRunning(job.id, config.name, store) //also increments retries if current state=stuck
def wrapTask(job: RJob, task: Task[F, String, Unit], ctx: Context[F, String]): Task[F, String, Unit] = {
task.mapF(fa => onStart(job) *> logger.fdebug("Starting task now") *> blocker.blockOn(fa)).
mapF(_.attempt.flatMap({
case Right(()) =>
logger.info(s"Job execution successful: ${job.info}")
ctx.logger.info("Job execution successful") *>
(JobState.Success: JobState).pure[F]
case Left(ex) =>
state.get.map(_.wasCancelled(job)).flatMap {
case true =>
logger.error(ex)(s"Job ${job.info} execution failed (cancel = true)")
ctx.logger.error(ex)("Job execution failed (cancel = true)") *>
(JobState.Cancelled: JobState).pure[F]
case false =>
QJob.exceedsRetries(job.id, config.retries, store).flatMap {
case true =>
logger.error(ex)(s"Job ${job.info} execution failed. Retries exceeded.")
ctx.logger.error(ex)(s"Job ${job.info} execution failed. Retries exceeded.").
map(_ => JobState.Failed: JobState)
case false =>
logger.error(ex)(s"Job ${job.info} execution failed. Retrying later.")
ctx.logger.error(ex)(s"Job ${job.info} execution failed. Retrying later.").
map(_ => JobState.Stuck: JobState)
}
}
})).
mapF(_.attempt.flatMap {
case Right(jstate) =>
onFinish(job, jstate)
case Left(ex) =>
logger.error(ex)(s"Error happened during post-processing of ${job.info}!")
// we don't know the real outcome here…
// since tasks should be idempotent, set it to stuck. if above has failed, this might fail anyways
onFinish(job, JobState.Stuck)
})
}
def forkRun(job: RJob, code: F[Unit], onCancel: F[Unit], ctx: Context[F, String]): F[F[Unit]] = {
val bfa = blocker.blockOn(code)
logger.fdebug(s"Forking job ${job.info}") *>
ConcurrentEffect[F].start(bfa).
map(fiber =>
logger.fdebug(s"Cancelling job ${job.info}") *>
fiber.cancel *>
onCancel.attempt.map({
case Right(_) => ()
case Left(ex) =>
logger.error(ex)(s"Task's cancelling code failed. Job ${job.info}.")
()
}) *>
state.modify(_.markCancelled(job)) *>
onFinish(job, JobState.Cancelled) *>
ctx.logger.warn("Job has been cancelled.") *>
logger.fdebug(s"Job ${job.info} has been cancelled."))
}
}
object SchedulerImpl {
def emptyState[F[_]]: State[F] =
State(Map.empty, Set.empty, Map.empty, false)
case class State[F[_]]( counters: Map[Ident, CountingScheme]
, cancelled: Set[Ident]
, cancelTokens: Map[Ident, CancelToken[F]]
, shutdownRequest: Boolean) {
def nextPrio(group: Ident, initial: CountingScheme): (State[F], Priority) = {
val (cs, prio) = counters.getOrElse(group, initial).nextPriority
(copy(counters = counters.updated(group, cs)), prio)
}
def addRunning(job: RJob, token: CancelToken[F]): (State[F], Unit) =
(State(counters, cancelled, cancelTokens.updated(job.id, token), shutdownRequest), ())
def removeRunning(job: RJob): (State[F], Unit) =
(copy(cancelled = cancelled - job.id, cancelTokens = cancelTokens.removed(job.id)), ())
def markCancelled(job: RJob): (State[F], Unit) =
(copy(cancelled = cancelled + job.id), ())
def wasCancelled(job: RJob): Boolean =
cancelled.contains(job.id)
def cancelRequest(id: Ident): Option[F[Unit]] =
cancelTokens.get(id)
def getRunning: Seq[Ident] =
cancelTokens.keys.toSeq
def requestShutdown: (State[F], Unit) =
(copy(shutdownRequest = true), ())
}
}

55
modules/joex/src/main/scala/docspell/joex/scheduler/Task.scala Normal file
View File

@ -0,0 +1,55 @@
package docspell.joex.scheduler
import cats.implicits._
import cats.{Applicative, ApplicativeError, FlatMap, Functor}
import cats.data.Kleisli
import cats.effect.Sync
/**
* The code that is executed by the scheduler
*/
trait Task[F[_], A, B] {
def run(ctx: Context[F, A]): F[B]
def map[C](f: B => C)(implicit F: Functor[F]): Task[F, A, C] =
Task(Task.toKleisli(this).map(f))
def flatMap[C](f: B => Task[F, A, C])(implicit F: FlatMap[F]): Task[F, A, C] =
Task(Task.toKleisli(this).flatMap(a => Task.toKleisli(f(a))))
def andThen[C](f: B => F[C])(implicit F: FlatMap[F]): Task[F, A, C] =
Task(Task.toKleisli(this).andThen(f))
def mapF[C](f: F[B] => F[C]): Task[F, A, C] =
Task(Task.toKleisli(this).mapF(f))
def attempt(implicit F: ApplicativeError[F,Throwable]): Task[F, A, Either[Throwable, B]] =
mapF(_.attempt)
def contramap[C](f: C => F[A])(implicit F: FlatMap[F]): Task[F, C, B] = {
ctxc: Context[F, C] => f(ctxc.args).flatMap(a => run(ctxc.map(_ => a)))
}
}
object Task {
def pure[F[_]: Applicative, A, B](b: B): Task[F, A, B] =
Task(_ => b.pure[F])
def of[F[_], A, B](b: F[B]): Task[F, A, B] =
Task(_ => b)
def apply[F[_], A, B](f: Context[F, A] => F[B]): Task[F, A, B] =
(ctx: Context[F, A]) => f(ctx)
def apply[F[_], A, B](k: Kleisli[F, Context[F, A], B]): Task[F, A, B] =
c => k.run(c)
def toKleisli[F[_], A, B](t: Task[F, A, B]): Kleisli[F, Context[F, A], B] =
Kleisli(t.run)
def setProgress[F[_]: Sync, A, B](n: Int)(data: B): Task[F, A, B] =
Task(_.setProgress(n).map(_ => data))
}

15
modules/joex/src/test/scala/docspell/joex/scheduler/CountingSchemeSpec.scala Normal file
View File

@ -0,0 +1,15 @@
package docspell.joex.scheduler
import docspell.common.Priority
import minitest.SimpleTestSuite
object CountingSchemeSpec extends SimpleTestSuite {
test("counting") {
val cs = CountingScheme(2,1)
val list = List.iterate(cs.nextPriority, 6)(_._1.nextPriority).map(_._2)
val expect = List(Priority.High, Priority.High, Priority.Low)
assertEquals(list, expect ++ expect)
}
}

164
modules/joexapi/src/main/resources/joex-openapi.yml
View File

@ -9,9 +9,162 @@ servers:
description: Current host
paths:
/api/info:
get:
tag: [ Api Info ]
summary: Get basic information about this software.
description: |
Returns the version and project name and other properties of the build.
responses:
200:
content:
application/json:
schema:
$ref: "#/components/schemas/VersionInfo"
/api/v1/notify:
post:
tag: [ Job Executor ]
summary: Notify the job executor.
description: |
Notifies the job executor to wake up and look for jobs in th queue.
responses:
200:
description: Ok
content:
application/json:
schema:
$ref: "#/components/schemas/BasicResult"
/api/v1/running:
get:
tag: [ Job Executor ]
summary: Get a list of currently executing jobs.
description: |
Returns all jobs this executor is currently executing.
responses:
200:
description: Ok
content:
application/json:
schema:
$ref: "#/components/schemas/JobList"
/api/v1/shutdownAndExit:
post:
tag: [ Job Executor ]
summary: Stops this component and exits.
description: |
Gracefully stops the scheduler and also stops the process.
responses:
200:
description: Ok
content:
application/json:
schema:
$ref: "#/components/schemas/BasicResult"
/api/v1/job/{id}:
get:
tag: [ Current Jobs ]
summary: Get a job by its id.
description: |
Returns details about a job given the id.
responses:
200:
description: Ok
content:
application/json:
schema:
$ref: "#/components/schemas/JobAndLogs"
/api/v1/job/{id}/cancel:
post:
tag: [ Current Jobs ]
summary: Request to cancel a running job.
description: |
Requests to cancel the running job. This will try to cancel
the execution but it is not guaranteed that it can immediately
abort. The job is then removed from the queue.
responses:
200:
description: Ok
content:
application/json:
schema:
$ref: "#/components/schemas/BasicResult"
components:
schemas:
JobAndLog:
description: |
Some more details about the job.
required:
- job
- logs
properties:
job:
$ref: "#/components/schemas/Job"
logs:
type: array
items:
$ref: "#/components/schemas/JobLogEvent"
JobLogEvent:
description: |
A log output line.
required:
- time
- level
- message
properties:
time:
description: DateTime
type: integer
format: date-time
level:
type: string
format: loglevel
message:
type: string
JobList:
description: |
A list of jobs.
required:
- items
properties:
items:
type: array
items:
$ref: "#/components/schemas/Job"
Job:
description: |
Data about a running job.
required:
- id
- name
- submitted
- priority
- retries
- progress
- started
properties:
id:
type: string
format: ident
name:
type: string
submitted:
description: DateTime
type: integer
format: date-time
priority:
type: integer
format: priority
retries:
type: integer
format: int32
progress:
type: integer
format: int32
started:
description: DateTime
type: integer
format: date-time
VersionInfo:
description: |
Information about the software.
@ -33,3 +186,14 @@ components:
type: string
gitVersion:
type: string
BasicResult:
description: |
Some basic result of an operation.
required:
- success
- message
properties:
success:
type: boolean
message:
type: string

18
modules/microsite/src/main/resources/microsite/css/docspell.css Normal file
View File

@ -0,0 +1,18 @@
.jumbotron {
background: url(../img/back-master-small.jpg);
background-repeat: no-repeat;
background-size: 100% 800px;
}
.content-wrapper h1, .h1 {
border-bottom: 1px solid #d8dfe5;
padding-bottom: 0.8rem;
}
body {
font-size: 1.75em;
}
h4 {
text-decoration: underline;
}

48
modules/microsite/src/main/resources/microsite/data/menu.yml Normal file
View File

@ -0,0 +1,48 @@
options:
- title: Home
url: index.html
- title: Getit
url: getit.html
- title: Documentation
url: doc.html
nested_options:
- title: Installation
url: doc/install.html
- title: Configuring
url: doc/configure.html
- title: Adding Meta Data
url: doc/metadata.html
- title: Uploads
url: doc/uploading.html
- title: Processing Queue
url: doc/processing.html
- title: Find and Review
url: doc/curate.html
- title: Joex
url: doc/joex.html
- title: Development
url: dev.html
nested_options:
- tite: ADRs
url: dev/adr.html
- title: Api
url: api.html
nested_options:
- title: REST Api Doc
url: openapi/docspell-openapi.html
- title: REST OpenApi Spec
url: openapi/docspell-openapi.yml

BIN
modules/microsite/src/main/resources/microsite/img/back-master-small.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 339 KiB

BIN
modules/microsite/src/main/resources/microsite/img/docspell-curate-1.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 62 KiB

BIN
modules/microsite/src/main/resources/microsite/img/docspell-curate-2.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 88 KiB

Some files were not shown because too many files have changed in this diff Show More