improv: colorblind colors

v1.16

.github/workflows/docker.yml

@@ -0,0 +1,34 @@
+name: Docker
+
+on: ["push", "pull_request"]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v1
+      - name: Cache Docker layers
+        uses: actions/cache@v2
+        with:
+          path: /tmp/.buildx-cache
+          key: ${{ runner.os }}-buildx-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-buildx-
+      - name: Build
+        uses: docker/build-push-action@v2
+        with:
+          context: ./
+          file: ./Dockerfile
+          builder: ${{ steps.buildx.outputs.name }}
+          push: false
+          cache-from: type=local,src=/tmp/.buildx-cache
+          cache-to: type=local,dest=/tmp/.buildx-cache-new
+      - name: Move cache
+        run: |
+          rm -rf /tmp/.buildx-cache
+          mv /tmp/.buildx-cache-new /tmp/.buildx-cache
+      - name: Image digest
+        run: echo ${{ steps.docker_build.outputs.digest }}

.github/workflows/python.yml

@@ -0,0 +1,26 @@
+name: Python
+
+on: ["push", "pull_request"]
+
+jobs:
+  syntax:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.7, 3.8, 3.9]
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install flake8
+    - name: Lint with flake8
+      run: |
+        # stop the build if there are Python syntax errors or undefined names
+        flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
+        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
+        flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics

.gitignore

@@ -4,4 +4,5 @@ __pycache__
 .env
 error_*
 *.log
-logs/
+/logs/
+.vscode

Dockerfile

@@ -0,0 +1,17 @@
+FROM python:3.8.10
+
+# Create app directory
+WORKDIR /usr/src/app
+
+VOLUME ["/usr/src/app/logs"]
+
+COPY requirements.txt ./
+
+RUN pip install -r requirements.txt
+
+RUN mkdir -p logs && touch logs/guilds.log && ln -s logs/guilds.log guilds.log
+
+# Bundle app source
+COPY . .
+
+CMD [ "sh", "-c", "python src/main.py" ]

LICENSE

@@ -0,0 +1,674 @@
+                    GNU GENERAL PUBLIC LICENSE
+                       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <https://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 <https://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
+<https://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
+<https://www.gnu.org/licenses/why-not-lgpl.html>.

README.md

@@ -1,15 +1,82 @@
+![Python Version >= 3.7](https://img.shields.io/badge/python-%3E=3.7%20-blue)
 [![Scc Count Badge](https://sloc.xyz/github/klemek/discord-analyst/?category=code)](https://github.com/boyter/scc/#badges-beta)
 [![Language grade: Python](https://img.shields.io/lgtm/grade/python/g/Klemek/discord-analyst.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/Klemek/discord-analyst/context:python)
 [![Total alerts](https://img.shields.io/lgtm/alerts/g/Klemek/discord-analyst.svg?logo=lgtm&logoWidth=18)](https://lgtm.com/projects/g/Klemek/discord-analyst/alerts/)
+[![Discord Bots](https://top.gg/api/widget/status/643808410495615006.svg)](https://top.gg/bot/643808410495615006)
 
 # Discord Analyst
 
-When you need statistics about your discord server
+#### 📈 Gives you precisions you never asked for.
 
-* `%help (command)` - info about commands
-* `%info` - version and uptime
-* `%emotes` - gives you a full ranking of the server emotes by usage
-  *  Be more specific by adding some `@member` or `#channel` in arguments
+![preview](https://user-images.githubusercontent.com/12103162/111427226-1823ac80-86f6-11eb-9581-fada2db43143.png)
+
+## All commands
+```
+* %help (command) - info about commands
+* %info - version and uptime
+* %scan - full analysis
+* %freq - frequency analysis
+* %compo - composition analysis
+* %pres - presence analysis
+* %repeat - repeat last analysis (adding supplied arguments)
+* %mobile - fix @invalid-user for last command but mentions users
+* %gdpr - displays GDPR information
+* %find - find specific words or phrases (you can use quotes to add spaces in queries, backticks define regexes)
+  * arguments:
+    * top - rank users for these queries
+* %first - read first message (add text to filter like %find)
+  * arguments:
+    * image - pull an image instead of a message
+    * spoiler:allow/only - allow spoiler images
+* %rand - read a random message (add text to filter like %find)
+  * arguments:
+    * image - pull an image instead of a message
+    * spoiler:allow/only - allow spoiler images
+* %last - read last message (add text to filter like %find)
+  * arguments:
+    * image - pull an image instead of a message
+    * spoiler:allow/only - allow spoiler images
+* %emojis - rank emojis by their usage
+  * arguments:
+    * <n> - top <n> emojis, default is 20
+    * all - list all common emojis in addition to this guild's
+    * members - show top member for each emoji
+    * sort:usage/reaction - other sorting methods
+* %mentions - rank mentions by their usage
+  * arguments:
+    * <n> - top <n> mentions, default is 10
+    * all - show role/channel/everyone/here mentions
+* %mentioned - rank specific user mentions by their usage
+  * arguments:
+    * <n> - top <n> mentions, default is 10
+* %msg - rank users by their messages
+  * arguments:
+    * <n> - top <n> messages, default is 10
+* %chan - rank channels by their messages
+  * arguments:
+    * <n> - top <n> channels, default is 10
+* %react - rank users by their reactions
+  * arguments:
+    * <n> - top <n> messages, default is 10
+* %words - (BETA) rank words by their usage
+  * arguments:
+    * <n> - words containings <n> or more letters, default is 3
+    * <n2> - top <n2> words, default is 10
+* %cancel - cancel current analysis (not launched with fast)
+
+* Common arguments:
+    * @member/me: filter for one or more member
+    * #channel/here: filter for one or more channel
+    * <date1> - filter after <date1>
+    * <date2> - filter before <date2>
+    * all/everyone - include bots messages
+    * fast: only read cache
+    * fresh: does not read cache
+    * nsfw:allow/only - allow messages from nsfw channels
+    * mobile/mention: mentions users (fix @invalid-user bug)
+
+(Sample dates: 2020 / 2021-11 / 2021-06-28 / 2020-06-28T23:00 / today / week / 8days / 1y)
+```
 
 ## Running this bot
 
@@ -41,11 +108,79 @@ You will need:
 **4. Launch bot**
 
 ```
-python3 bot.py
+python3 src/main.py
 ```
 
+## Recommended permissions
+
+- [x] View Channels
+- [x] Read Message History
+- [x] Send Messages
+
+> On large servers, you should disable "Send Messages" and enable it on an read-only channel where only administrators can launch commands. The bot can't be triggered elsewhere if it can't answer.
+
+## Already hosted bot
+
+[![Discord Bots](https://top.gg/api/widget/643808410495615006.svg)](https://top.gg/bot/643808410495615006)
+
 ## Changelog
 
+* **v1.16**
+  * `%freq graph` graph hours frequency along the week
+  * uses discord new time format
+  * `%freq` now shows quietest day of week and hour of day
+  * improvments and bug fix
+* **v1.15**
+  * `nsfw:allow/only` filter nsfw channels
+  * `%find` can use regexes
+  * `%first`, `%rand` and `%last` can be filter with specific keywords
+  * `%first`, `%rand` and `%last` can pull images
+  * bug fix
+* **v1.14**
+  * `mobile/mention` arg to fix mobile bug
+  * `%repeat`, `%mobile` to repeat commands
+  * more scan: `%find`
+  * bug fix
+* **v1.13**
+  * improved scan `%words`
+  * remove old and unused logs at start and guild leaving
+  * GDPR disclaimer before scanning
+  * start and stop dates
+  * bug fix and improvements
+* **v1.12**
+  * more scans: `%words`
+  * concurrent `fast` analysis
+  * assume `fast` if last analysis is fresh
+  * better memory handling
+  * bug fix
+* **v1.11**
+  * more scans: `%first`, `%rand`, `%last`
+  * streak computing in `%pres`
+* **v1.10**
+  * multithreading for queries
+  * bug fix
+* **v1.9**:
+  * `all/everyone` to include bots in scans
+  * `fresh` to not use previously cached data
+  * bug fix
+* **v1.8**:
+  * more scans: `%msg`, `%chan`
+  * bug fix
+* **v1.7**:
+  * emojis percents
+  * emojis other sorting
+  * mentions/mentioned ranking
+  * `%cancel`
+* **v1.6**:
+  * more scans: `%scan`, `%freq`, `%compo`, `%pres`
+  * huge bug fix
+* **v1.5**:
+  * top <n> emojis
+  * bug fix
+* **v1.4**:
+  * integrate miniscord
+  * insane speed with bot-side logging
+  * bug fix
 * **v1.3**: revert to v1.1 and update requirements
 * **v1.2**: don't quit on occasional exception
 * **v1.1**:

bot.py

@@ -1,25 +0,0 @@
-from miniscord import Bot
-import logging
-
-import emotes
-
-logging.basicConfig(
-    format="[%(asctime)s][%(levelname)s][%(module)s] %(message)s", level=logging.INFO
-)
-
-emotes.load_emojis()
-
-bot = Bot(
-    "Discord Analyst",  # name
-    "1.4",  # version
-    alias="%",  # respond to '|command' messages
-)
-bot.log_calls = True
-bot.client.bot = bot  # TODO place in miniscord
-bot.register_command(
-    "emotes",  # command text (regex)
-    emotes.compute,  # command function
-    "emotes: Emotes analysis",  # short help
-    emotes.HELP,
-)
-bot.start()

emotes.py

@@ -1,397 +0,0 @@
-from typing import Dict, List, Tuple, Optional
-from datetime import datetime
-from collections import defaultdict
-import discord
-import re
-import json
-import logging
-
-# Custom libs
-from utils import debug, aggregate, no_duplicate
-from log_manager import GuildLogs, ChannelLogs, MessageLog
-
-# CONSTANTS
-
-CHUNK_SIZE = 1000
-
-# preload
-
-EXTRA_EMOJI = {
-    "thumbup": "1f44d",
-    "thumbdown": "1f44e",
-    "timer": "23f2-fe0f",
-    "cowboy": "1f920",
-    "clown": "1f921",
-    "newspaper2": "1f5de-fe0f",
-    "french_bread": "1f956",
-    "nerd": "1f913",
-    "zipper_mouth": "1f910",
-    "salad": "1f957",
-    "rolling_eyes": "1f644",
-    "basketball_player": "26f9-fe0f-200d-2642-fe0f",
-    "thinking": "1f914",
-    "e_mail": "2709-fe0f",
-    "slight_frown": "1f641",
-    "skull_crossbones": "2620-fe0f",
-    "hand_splayed": "1f590-fe0f",
-    "speaking_head": "1f5e3-fe0f",
-    "cross": "271d-fe0f",
-    "crayon": "1f58d-fe0f",
-    "head_bandage": "1f915",
-    "rofl": "1f923",
-    "flag_white": "1f3f3-fe0f",
-    "slight_smile": "1f642",
-    "fork_knife_plate": "1f37d-fe0f",
-    "robot": "1f916",
-    "hugging": "1f917",
-    "biohazard": "2623-fe0f",
-    "notepad_spiral": "1f5d2-fe0f",
-    "lifter": "1f3cb-fe0f-200d-2642-fe0f",
-    "race_car": "1f3ce-fe0f",
-    "left_facing_fist": "1f91b",
-    "right_facing_fist": "1f91c",
-    "tools": "1f6e0-fe0f",
-    "umbrella2": "2602-fe0f",
-    "upside_down": "2b07-fe0f",
-    "first_place": "1f947",
-    "dagger": "1f5e1-fe0f",
-    "fox": "1f98a",
-    "menorah": "1f54e",
-    "desktop": "1f5a5-fe0f",
-    "motorcycle": "1f3cd-fe0f",
-    "levitate": "1f574-fe0f",
-    "cheese": "1f9c0",
-    "fingers_crossed": "1f91e",
-    "frowning2": "1f626",
-    "microphone2": "1f399-fe0f",
-    "flag_black": "1f3f4",
-    "chair": "1FA91",
-}
-
-GLOBAL_EMOJIS = {}
-EMOJI_REGEX = re.compile("(<a?:\\w+:\\d+>|:\\w+:)")
-
-
-def load_emojis():
-    global GLOBAL_EMOJIS, INV_GLOBAL_EMOJIS, EMOJI_REGEX
-    emoji_list = []
-    with open("emoji.json", mode="r") as f:
-        emoji_list = json.loads(f.readline().strip())
-    for emoji in EXTRA_EMOJI:
-        emoji_list += [{"short_name": emoji, "unified": EXTRA_EMOJI[emoji]}]
-    unicode_list = []
-    for emoji in emoji_list:
-        shortcode = emoji["short_name"]
-        unified = emoji["unified"]
-        if unified is not None and shortcode is not None:
-            unicode_escaped = "".join([f"\\U{c:0>8}" for c in unified.split("-")])
-            unicode = bytes(unicode_escaped, "ascii").decode("unicode-escape")
-            shortcode = f":{shortcode.replace('-','_')}:"
-            GLOBAL_EMOJIS[unicode] = shortcode
-            unicode_list += [unicode_escaped]
-    EMOJI_REGEX = re.compile(f"(<a?:\\w+:\\d+>|:\\w+:|{'|'.join(unicode_list)})")
-    logging.info(f"loaded {len(GLOBAL_EMOJIS)} emojis")
-
-
-# MAIN
-
-HELP = (
-    "```\n"
-    + "%emotes : Rank emotes by their usage\n"
-    + "arguments:\n"
-    + "* @member : filter for one or more member\n"
-    + "* #channel : filter for one or more channel\n"
-    + "* reactions : add reaction analysis for members (long)\n"
-    + "* all : list all common emojis in addition to this guild's\n"
-    + "```"
-)
-
-
-async def compute(client: discord.client, message: discord.Message, *args: str):
-    """
-    Computes the %emotes command
-    """
-    guild = message.guild
-    logs = GuildLogs(guild)
-
-    # If "%emotes help" redirect to "%help emotes"
-    if "help" in args:
-        await client.bot.help(client, message, "help", "emotes")
-        return
-
-    # Create emotes dict from custom emojis of the guild
-    emotes = defaultdict(Emote)
-    for emoji in guild.emojis:
-        emotes[str(emoji)] = Emote(emoji)
-
-    # Get selected channels or all of them if no channel arguments
-    channels = no_duplicate(message.channel_mentions)
-    full = len(channels) == 0
-    if full:
-        channels = guild.text_channels
-
-    # Get selected members
-    members = no_duplicate(message.mentions)
-    raw_members = no_duplicate(message.raw_mentions)
-
-    # Start computing data
-    async with message.channel.typing():
-        progress = await message.channel.send("```Starting analysis...```")
-        total_msg, total_chan = await logs.load(progress, channels)
-        for id in logs.channels:
-            analyse_channel(
-                logs.channels[id], emotes, raw_members, all_emojis="all" in args
-            )
-        # Delete custom progress message
-        await progress.delete()
-        # Display results
-        await tell_results(
-            get_intro(emotes, full, channels, members, total_msg, total_chan),
-            emotes,
-            message.channel,
-            total_msg,
-            allow_unused=full and len(members) == 0,
-            show_life=False,
-        )
-
-
-# CLASSES
-
-
-class Emote:
-    """
-    Custom class to store emotes data
-    """
-
-    def __init__(self, emoji: Optional[discord.Emoji] = None):
-        self.emoji = emoji
-        self.usages = 0
-        self.reactions = 0
-        self.last_used = None
-
-    def update_use(self, date: datetime):
-        """
-        Update last use date if more recent
-        """
-        if self.last_used is None or date > self.last_used:
-            self.last_used = date
-
-    def used(self) -> bool:
-        return self.usages > 0 or self.reactions > 0
-
-    def score(self) -> float:
-        # Score is compose of usages + reactions
-        # When 2 emotes have the same score,
-        # the days since last use is stored in the digits
-        # (more recent first)
-        return self.usages + self.reactions + 1 / (100000 * (self.use_days() + 1))
-
-    def life_days(self) -> int:
-        return (datetime.today() - self.emoji.created_at).days
-
-    def use_days(self) -> int:
-        # If never used, use creation date instead
-        if self.last_used is None:
-            return self.life_days()
-        else:
-            return (datetime.today() - self.last_used).days
-
-
-# ANALYSIS
-
-
-def analyse_channel(
-    channel: ChannelLogs,
-    emotes: Dict[str, Emote],
-    raw_members: List[int],
-    *,
-    all_emojis: bool,
-):
-    for message in channel.messages:
-        # If author included in the selection (empty list is all)
-        if len(raw_members) == 0 or message.author in raw_members:
-            # Find all emotes un the current message in the form "<:emoji:123456789>"
-            # Filter for known emotes
-            found = EMOJI_REGEX.findall(message.content)
-            # For each emote, update its usage
-            for name in found:
-                if name not in emotes:
-                    if not all_emojis or name not in GLOBAL_EMOJIS:
-                        continue
-                    name = GLOBAL_EMOJIS[name]
-                emotes[name].usages += 1
-                emotes[name].update_use(message.created_at)
-            # For each reaction of this message, test if known emote and update when it's the case
-            for name in message.reactions:
-                raw_name = name
-                if name not in emotes:
-                    if not all_emojis or name not in GLOBAL_EMOJIS:
-                        continue
-                    name = GLOBAL_EMOJIS[name]
-                if len(raw_members) == 0:
-                    emotes[name].reactions += len(message.reactions[raw_name])
-                    emotes[name].update_use(message.created_at)
-                else:
-                    for member in raw_members:
-                        if member in message.reactions[raw_name]:
-                            emotes[name].reactions += 1
-                            emotes[name].update_use(message.created_at)
-
-
-# RESULTS
-
-
-async def tell_results(
-    intro: str,  # introduction sentence (from get_intro)
-    emotes: Dict[str, Emote],
-    channel: discord.TextChannel,
-    nmm: int,  # number of impacted messages
-    *,
-    allow_unused: bool,
-    show_life: bool,
-):
-    names = [name for name in emotes]
-    names.sort(key=lambda name: emotes[name].score(), reverse=True)
-    res = [intro]
-    res += [
-        f"{get_place(names.index(name))} {name} - "
-        f"{get_usage(emotes[name])}"
-        f"{get_reactions(emotes[name])}"
-        f"{get_life(emotes[name], show_life)}"
-        f"{get_last_used(emotes[name])}"
-        for name in names
-        if allow_unused or emotes[name].used()
-    ]
-    res += [get_total(emotes, nmm)]
-    response = ""
-    for r in res:
-        if len(response + "\n" + r) > 2000:
-            await channel.send(response)
-            response = ""
-        response += "\n" + r
-    if len(response) > 0:
-        await channel.send(response)
-
-
-def get_intro(
-    emotes: Dict[str, Emote],
-    full: bool,
-    channels: List[discord.TextChannel],
-    members: List[discord.Member],
-    nmm: int,  # number of messages impacted
-    nc: int,  # number of channels analysed
-) -> str:
-    """
-    Get the introduction sentence of the response
-    """
-    # Show all data (members, channels) when it's less than 5 units
-    if len(members) == 0:
-        # Full scan of the server
-        if full:
-            return f"{len(emotes)} emotes in this server ({nc} channels, {nmm:,} messages):"
-        elif len(channels) < 5:
-            return f"{aggregate([c.mention for c in channels])} emotes usage in {nmm:,} messages:"
-        else:
-            return f"These {len(channels)} channels emotes usage in {nmm:,} messages:"
-    elif len(members) < 5:
-        if full:
-            return f"{aggregate([m.mention for m in members])} emotes usage in {nmm:,} messages:"
-        elif len(channels) < 5:
-            return (
-                f"{aggregate([m.mention for m in members])} on {aggregate([c.mention for c in channels])} "
-                f"emotes usage in {nmm:,} messages:"
-            )
-        else:
-            return (
-                f"{aggregate([m.mention for m in members])} on these {len(channels)} channels "
-                f"emotes usage in {nmm:,} messages:"
-            )
-    else:
-        if full:
-            return f"These {len(members)} members emotes usage in {nmm:,} messages:"
-        elif len(channels) < 5:
-            return (
-                f"These {len(members)} members on {aggregate([c.mention for c in channels])} "
-                f"emotes usage in {nmm:,} messages:"
-            )
-        else:
-            return (
-                f"These {len(members)} members on these {len(channels)} channels "
-                f"emotes usage in {nmm:,} messages:"
-            )
-
-
-def get_place(i: int) -> str:
-    """
-    Get the correct rank displayed (1st to 3rd have an emoji)
-    """
-    if i == 0:
-        return ":first_place:"
-    if i == 1:
-        return ":second_place:"
-    if i == 2:
-        return ":third_place:"
-    return f"**#{i + 1}**"
-
-
-def get_usage(emote: Emote) -> str:
-    """
-    Get the correct usage displayed
-    """
-    if emote.usages == 0 and emote.reactions == 0:
-        return "never used "
-    elif emote.usages == 1:
-        return "1 time "
-    else:
-        return f"{emote.usages:,} times "
-
-
-def get_reactions(emote: Emote) -> str:
-    """
-    Get the correct reactions displayed
-    """
-    if emote.reactions == 0:
-        return ""
-    elif emote.reactions == 1:
-        return "and 1 reaction "
-    else:
-        return f"and {emote.reactions:,} reactions "
-
-
-def get_life(emote: Emote, show_life: bool) -> str:
-    """
-    Get the correct life span displayed
-    """
-    if not show_life or emote.default:
-        return ""
-    else:
-        return f"(in {emote.life_days()} days) "
-
-
-def get_last_used(emote: Emote) -> str:
-    """
-    Get the correct "last used" displayed
-    """
-    if emote.usages == 0 and emote.reactions == 0:
-        return ""
-    elif emote.use_days() == 0:
-        return "(last used today)"
-    elif emote.use_days() == 1:
-        return "(last used yesterday)"
-    else:
-        return f"(last used {emote.use_days()} days ago)"
-
-
-def get_total(emotes: Dict[str, Emote], nmm: int) -> str:
-    """
-    Get the total of all emotes used
-    """
-    nu = 0
-    nr = 0
-    for name in emotes:
-        nu += emotes[name].usages
-        nr += emotes[name].reactions
-    if nr > 0:
-        return f"Total: {nu:,} times ({nu / nmm:.4f} / message) and {nr:,} reactions"
-    else:
-        return f"Total: {nu:,} times ({nu / nmm:.4f} / message)"

log_manager.py

@@ -1,206 +0,0 @@
-from typing import Union, List, Tuple
-import os
-import discord
-import json
-import gzip
-from datetime import datetime
-import logging
-
-LOG_DIR = "logs"
-
-if not os.path.exists(LOG_DIR):
-    os.mkdir(LOG_DIR)
-
-
-CHUNK_SIZE = 1000
-
-
-class FakeMessage:
-    def __init__(self, id: int):
-        self.id = id
-
-
-class MessageLog:
-    def __init__(self, message: Union[discord.Message, dict]):
-        if isinstance(message, discord.Message):
-            self.id = message.id
-            self.created_at = message.created_at
-            self.edited_at = message.edited_at
-            self.author = message.author.id
-            self.pinned = message.pinned
-            self.mention_everyone = message.mention_everyone
-            self.tts = message.tts
-            self.reference = (
-                message.reference.id if message.reference is not None else None
-            )
-            self.content = message.content
-            self.mentions = message.raw_mentions
-            self.role_mentions = message.raw_role_mentions
-            self.channel_mentions = message.raw_channel_mentions
-            self.reactions = {}
-        elif isinstance(message, dict):
-            self.id = int(message["id"])
-            self.created_at = datetime.fromisoformat(message["created_at"])
-            self.edited_at = (
-                datetime.fromisoformat(message["edited_at"])
-                if message["edited_at"] is not None
-                else None
-            )
-            self.author = message["author"]
-            self.pinned = message["pinned"]
-            self.mention_everyone = message["mention_everyone"]
-            self.tts = message["tts"]
-            self.reference = message["reference"]
-            self.content = message["content"]
-            self.mentions = message["mentions"]
-            self.role_mentions = message["role_mentions"]
-            self.channel_mentions = message["channel_mentions"]
-            self.reactions = message["reactions"]
-
-    async def load(self, message: discord.Message):
-        for reaction in message.reactions:
-            self.reactions[str(reaction.emoji)] = []
-            async for user in reaction.users():
-                self.reactions[str(reaction.emoji)] += [user.id]
-
-    def dict(self) -> dict:
-        message = dict(self.__dict__)
-        message["created_at"] = self.created_at.isoformat()
-        message["edited_at"] = (
-            self.edited_at.isoformat() if self.edited_at is not None else None
-        )
-        return message
-
-
-class ChannelLogs:
-    def __init__(self, channel: Union[discord.TextChannel, dict]):
-        if isinstance(channel, discord.TextChannel):
-            self.id = channel.id
-            self.name = channel.name
-            self.last_message_id = None
-            self.messages = []
-        elif isinstance(channel, dict):
-            self.id = int(channel["id"])
-            self.name = channel["name"]
-            self.last_message_id = channel["last_message_id"]
-            self.messages = [MessageLog(message) for message in channel["messages"]]
-
-    async def load(self, channel: discord.TextChannel) -> Tuple[int, int]:
-        self.name = channel.name
-        self.channel = channel
-        try:
-            if self.last_message_id is not None:  # append
-                while self.last_message_id != channel.last_message_id:
-                    async for message in channel.history(
-                        limit=CHUNK_SIZE,
-                        after=FakeMessage(self.last_message_id),
-                        oldest_first=True,
-                    ):
-                        self.last_message_id = message.id
-                        if not message.author.bot:
-                            m = MessageLog(message)
-                            await m.load(message)
-                            self.messages.insert(0, m)
-                    yield len(self.messages), False
-            else:  # first load
-                last_message_id = None
-                done = 0
-                while done >= CHUNK_SIZE or last_message_id is None:
-                    done = 0
-                    async for message in channel.history(
-                        limit=CHUNK_SIZE,
-                        before=FakeMessage(last_message_id)
-                        if last_message_id is not None
-                        else None,
-                        oldest_first=False,
-                    ):
-                        done += 1
-                        last_message_id = message.id
-                        if not message.author.bot:
-                            m = MessageLog(message)
-                            await m.load(message)
-                            self.messages += [m]
-                    yield len(self.messages), False
-                self.last_message_id = channel.last_message_id
-        except discord.errors.HTTPException:
-            return  # When an exception occurs (like Forbidden)
-        yield len(self.messages), True
-
-    def dict(self) -> dict:
-        channel = dict(self.__dict__)
-        channel.pop("channel", None)
-        channel["messages"] = [message.dict() for message in self.messages]
-        return channel
-
-
-class GuildLogs:
-    def __init__(self, guild: discord.Guild):
-        self.guild = guild
-        self.log_file = os.path.join(LOG_DIR, f"{guild.id}.logz")
-        self.channels = {}
-
-    def dict(self) -> dict:
-        return {id: self.channels[id].dict() for id in self.channels}
-
-    async def load(
-        self, progress: discord.Message, target_channels: List[discord.TextChannel] = []
-    ):
-        await progress.edit(
-            content=f"```Reading history...\n(this might take a while)```"
-        )
-        # read logs
-        t0 = datetime.now()
-        if os.path.exists(self.log_file):
-            channels = {}
-            try:
-                with open(self.log_file, mode="rb") as f:
-                    channels = json.loads(gzip.decompress(f.read()))
-                self.channels = {int(id): ChannelLogs(channels[id]) for id in channels}
-                dt = (datetime.now() - t0).total_seconds()
-                logging.info(f"log {self.guild.id} > loaded in {dt} s")
-            except json.decoder.JSONDecodeError:
-                logging.error(f"log {self.guild.id} > invalid JSON")
-            except IOError:
-                logging.error(f"log {self.guild.id} > cannot read")
-        # load channels
-        t0 = datetime.now()
-        if len(target_channels) == 0:
-            target_channels = self.guild.text_channels
-        loading_new = 0
-        total_msg = 0
-        total_chan = 0
-        for channel in target_channels:
-            if channel.id not in self.channels:
-                loading_new += 1
-                self.channels[channel.id] = ChannelLogs(channel)
-            async for count, done in self.channels[channel.id].load(channel):
-                if count > 0:
-                    tmp_msg = total_msg + count
-                    warning_msg = "(this might take a while)"
-                    if len(target_channels) > 5 and loading_new > 5:
-                        warning_msg = (
-                            "(most channels are new, this might take a looong while)"
-                        )
-                    elif loading_new > 0:
-                        warning_msg = (
-                            "(some channels are new, this might take a long while)"
-                        )
-                    dt = (datetime.now() - t0).total_seconds()
-                    await progress.edit(
-                        content=f"```Reading history...\n{tmp_msg} messages in {total_chan + 1} channels ({round(tmp_msg/dt)}m/s)\n{warning_msg}```"
-                    )
-                    if done:
-                        total_chan += 1
-            total_msg += len(self.channels[channel.id].messages)
-        dt = (datetime.now() - t0).total_seconds()
-        await progress.edit(
-            content=f"```Analysing...\n{tmp_msg} messages in {total_chan} channels```"
-        )
-        logging.info(f"log {self.guild.id} > queried in {dt} s -> {total_msg / dt} m/s")
-        # write logs
-        t0 = datetime.now()
-        with open(self.log_file, mode="wb") as f:
-            f.write(gzip.compress(bytes(json.dumps(self.dict()), "utf-8")))
-        dt = (datetime.now() - t0).total_seconds()
-        logging.info(f"log {self.guild.id} > written in {dt} s")
-        return total_msg, total_chan

requirements.txt

@@ -1,3 +1,6 @@
-discord.py
-python-dotenv
+discord.py==1.7.0
+python-dotenv==0.15.0
+python-dateutil==2.8.1
 git+git://github.com/Klemek/miniscord.git
+numpy
+matplotlib

src/data_types/__init__.py

@@ -0,0 +1,6 @@
+from .emoji import Emoji, get_emoji_dict
+from .composition import Composition
+from .counter import Counter
+from .frequency import Frequency
+from .history import History
+from .presence import Presence

src/data_types/composition.py

@@ -0,0 +1,67 @@
+from typing import List
+from collections import defaultdict
+
+from utils import percent, top_key, plural, precise, val_sum
+
+
+class Composition:
+    def __init__(self):
+        self.total_characters = 0
+        self.plain_text = 0
+        self.emoji_msg = 0
+        self.emoji_only = 0
+        self.emojis = defaultdict(int)
+        self.edited = 0
+        self.everyone = 0
+        self.answers = 0
+        self.images = 0
+        self.tts = 0
+        self.mentions = 0
+        self.mention_msg = 0
+        self.links = 0
+        self.link_msg = 0
+        self.spoilers = 0
+
+    def to_string(self, msg_count: int) -> List[str]:
+        total_emojis = val_sum(self.emojis)
+        top_emoji = top_key(self.emojis)
+        ret = [
+            f"- **avg. characters / message**: {self.total_characters/msg_count:.2f}",
+            f"- **plain text messages**: {self.plain_text:,} ({percent(self.plain_text/msg_count)})"
+            if self.plain_text > 0
+            else "",
+            f"- **edited messages**: {self.edited:,} ({percent(self.edited/msg_count)})"
+            if self.edited > 0
+            else "",
+            f"- **@\u200beveryone**: {self.everyone:,} ({percent(self.everyone/msg_count)})"
+            if self.everyone > 0
+            else "",
+            f"- **mentions**: {self.mentions:,} (in {percent(self.mention_msg/msg_count)} of msg, avg. {precise(self.mentions/msg_count)}/msg)"
+            if self.mentions > 0
+            else "",
+            f"- **answers**: {self.answers:,} ({percent(self.answers/msg_count)})"
+            if self.answers > 0
+            else "",
+            f"- **emojis**: {total_emojis:,} (in {percent(self.emoji_msg/msg_count)} of msg, avg. {precise(total_emojis/msg_count)}/msg)"
+            if total_emojis > 0
+            else "",
+            f"- **most used emoji**: {top_emoji} ({plural(self.emojis[top_emoji], 'time')}, {percent(self.emojis[top_emoji]/total_emojis)})"
+            if total_emojis > 0
+            else "",
+            f"- **emoji-only messages**: {self.emoji_only:,} ({percent(self.emoji_only/msg_count)})"
+            if self.emoji_only > 0
+            else "",
+            f"- **images**: {self.images:,} ({percent(self.images/msg_count)})"
+            if self.images > 0
+            else "",
+            f"- **links**: {self.links:,} ({percent(self.link_msg/msg_count)})"
+            if self.links > 0
+            else "",
+            f"- **spoilers**: {self.spoilers:,} ({percent(self.spoilers/msg_count)})"
+            if self.spoilers > 0
+            else "",
+            f"- **tts messages**: {self.tts:,} ({percent(self.tts/msg_count)})"
+            if self.tts > 0
+            else "",
+        ]
+        return ret

src/data_types/counter.py

@@ -0,0 +1,73 @@
+from typing import Optional, Callable
+from datetime import datetime
+from collections import defaultdict
+
+# Custom libs
+
+from utils import plural, from_now, percent, val_sum, top_key
+
+
+class Counter:
+    def __init__(self):
+        self.usages = defaultdict(int)
+        self.last_used = None
+
+    def update_use(self, count: int, date: datetime, item: int = 0):
+        self.usages[item] += count
+        if count > 0 and (self.last_used is None or date > self.last_used):
+            self.last_used = date
+
+    def score(self) -> float:
+        # Score is compose of usages + reactions
+        # When 2 emojis have the same score,
+        # the days since last use is stored in the digits
+        # (more recent first)
+        if self.last_used is None:
+            return 0
+        return self.all_usages() + 1 / (
+            100000 * ((datetime.today() - self.last_used).days + 1)
+        )
+
+    def all_usages(self) -> int:
+        return val_sum(self.usages)
+
+    def to_string(
+        self,
+        i: int,
+        name: str,
+        *,
+        total_usage: int,
+        counted: str = "time",
+        transform: Optional[Callable[[int], str]] = None,
+        ranking: bool = True,
+        top: bool = True,
+    ) -> str:
+        # place
+        output = ""
+        if ranking:
+            if i == 0:
+                output += ":first_place: "
+            elif i == 1:
+                output += ":second_place: "
+            elif i == 2:
+                output += ":third_place: "
+            else:
+                output += f"**#{i + 1}** "
+        else:
+            output += f"- "
+        sum = val_sum(self.usages)
+        if sum > 0:
+            output += f"{name} - {plural(sum, counted)} ({percent(sum/total_usage)}, last {from_now(self.last_used)})"
+        else:
+            output += f"{name} - unused"
+        top_item = top_key(self.usages)
+        if sum > 0 and top and top_item != 0 and transform is not None:
+            if self.usages[top_item] == sum:
+                output += f" (all{transform(top_item)})"
+            else:
+                output += f" ({self.usages[top_item]:,}{transform(top_item)}, {percent(self.usages[top_item]/sum)})"
+        return output
+
+    @staticmethod
+    def total(d: dict) -> int:
+        return sum([val_sum(counter.usages) for counter in d.values()])

src/data_types/emoji.py

@@ -0,0 +1,106 @@
+from typing import List, Optional, Dict
+from datetime import datetime
+from collections import defaultdict
+import discord
+
+# Custom libs
+
+from utils import mention, plural, from_now, top_key, percent
+
+
+class Emoji:
+    """
+    Custom class to store emojis data
+    """
+
+    def __init__(self, emoji: Optional[discord.Emoji] = None):
+        self.emoji = emoji
+        self.usages = 0
+        self.reactions = 0
+        self.last_used = None
+        self.members = defaultdict(int)
+
+    def update_use(self, date: datetime, members_id: List[int]):
+        """
+        Update last use date if more recent and last member
+        """
+        if self.last_used is None or date > self.last_used:
+            self.last_used = date
+        for member_id in members_id:
+            self.members[member_id] += 1
+
+    def used(self) -> bool:
+        return self.usages > 0 or self.reactions > 0
+
+    def score(self, *, usage_weight: int = 1, react_weight: int = 1) -> float:
+        # Score is compose of usages + reactions
+        # When 2 emojis have the same score,
+        # the days since last use is stored in the digits
+        # (more recent first)
+        return (
+            self.usages * usage_weight
+            + self.reactions * react_weight
+            + 1 / (100000 * (self.use_days() + 1))
+        )
+
+    def life_days(self) -> int:
+        return (datetime.today() - self.emoji.created_at).days
+
+    def use_days(self) -> int:
+        # If never used, use creation date instead
+        if self.last_used is None:
+            return self.life_days()
+        else:
+            return (datetime.today() - self.last_used).days
+
+    def get_top_member(self) -> int:
+        return top_key(self.members)
+
+    def to_string(
+        self,
+        i: int,
+        name: str,
+        *,
+        total_usage: int,
+        total_react: int,
+        show_life: bool,
+        show_members: bool,
+    ) -> str:
+        # place
+        output = ""
+        if i == 0:
+            output += ":first_place:"
+        elif i == 1:
+            output += ":second_place:"
+        elif i == 2:
+            output += ":third_place:"
+        else:
+            output += f"**#{i + 1}**"
+        output += f" {name} - "
+        if not self.used():
+            output += "never used"
+        else:
+            if self.usages > 0:
+                output += f"{plural(self.usages, 'time')} ({percent(self.usages/total_usage)})"
+            if self.usages > 0 and self.reactions > 0:
+                output += " and "
+            if self.reactions >= 1:
+                output += f"{plural(self.reactions, 'reaction')} ({percent(self.reactions/total_react)})"
+            output += f" (last used {from_now(self.last_used)})"
+            if show_members:
+                top_member = self.get_top_member()
+                total = self.usages + self.reactions
+                if total == self.members[top_member]:
+                    output += f" (all by {mention(top_member)})"
+                else:
+                    output += f" ({self.members[top_member]} by {mention(top_member)}, {percent(self.members[top_member]/total)})"
+        if show_life and not self.default:
+            output += f" (in {plural(self.life_days(), 'day')})"
+        return output
+
+
+def get_emoji_dict(guild: discord.Guild) -> Dict[str, Emoji]:
+    emojis = defaultdict(Emoji)
+    for emoji in guild.emojis:
+        emojis[str(emoji)] = Emoji(emoji)
+    return emojis

src/data_types/frequency.py

@@ -0,0 +1,155 @@
+from typing import List
+from datetime import timedelta
+import calendar
+import matplotlib.pyplot as plt
+import numpy as np
+from io import BytesIO
+import discord
+import time
+
+from utils import (
+    from_now,
+    plural,
+    percent,
+    precise,
+    top_key,
+    mention,
+)
+
+CB_color_cycle = [
+    "#e41a1c",
+    "#984ea3",
+    "#377eb8",
+    "#4daf4a",
+    "#dede00",
+    "#ff7f00",
+    "#a65628",
+    "#f781bf",
+    "#999999",
+]
+
+
+class Frequency:
+    def __init__(self):
+        self.dates = []
+        self.longest_break = timedelta(seconds=0)
+        self.longest_break_start = None
+        self.hours = {i: {j: 0 for j in range(24)} for i in range(7)}
+        self.busiest_day = None
+        self.busiest_day_count = 0
+        self.busiest_hour = None
+        self.busiest_hour_count = 0
+        self.streaks = []
+        self.last_author = None
+        self.last_streak_start = None
+        self.last_streak_author = None
+        self.longest_streak = None
+        self.longest_streak_start = None
+        self.longest_streak_author = None
+
+    def to_graph(self) -> List[str]:
+        self.dates.sort()
+        delta = self.dates[-1] - self.dates[0]
+        if delta.days == 0:
+            delta = timedelta(days=1)
+        day = {j: sum(self.hours[i][j] for i in range(7)) for j in range(24)}
+        busiest_hour = top_key(day)
+        n_hours = delta.days
+        if self.dates[0].hour <= busiest_hour and self.dates[-1].hour >= busiest_hour:
+            n_hours += 1
+
+        plt.style.use("dark_background")
+
+        fig, ax = plt.subplots()
+
+        times = range(25)
+        ax.set_xticks(times)
+        ax.set_xticklabels([f"{t:0>2}h" if t % 2 == 0 else "" for t in times])
+
+        for i in range(7):
+            hours = [self.hours[i][hour] * 7 / n_hours for hour in range(24)] + [
+                self.hours[i][0] * 7 / n_hours
+            ]
+            ax.plot(
+                times,
+                hours,
+                label=calendar.day_name[i],
+                linestyle="--",
+                linewidth=0.8,
+                c=CB_color_cycle[i],
+            )
+
+        hours = [day[hour] / n_hours for hour in range(24)] + [day[0] / n_hours]
+        ax.plot(times, hours, c="r", label="average", linewidth=1.5)
+
+        fig.patch.set_facecolor("#36393F")
+        ax.patch.set_alpha(0)
+        ax.set_xlim([0, 24])
+        ax.set_ylim([0, None])
+        ax.set_ylabel("average messages")
+        ax.legend(framealpha=0)
+        ax.grid(True, alpha=0.1)
+
+        with BytesIO() as f:
+            plt.savefig(
+                f,
+                format="png",
+                facecolor=fig.get_facecolor(),
+                edgecolor="none",
+                bbox_inches="tight",
+                dpi=300,
+            )
+            f.seek(0)
+            return [discord.File(f, f"{time.time()}-plot.png")]
+
+    def to_string(
+        self,
+        *,
+        member_specific: bool,
+    ) -> List[str]:
+        self.dates.sort()
+        delta = self.dates[-1] - self.dates[0]
+        if delta.days == 0:
+            delta = timedelta(days=1)
+        total_msg = len(self.dates)
+
+        week = {i: sum(self.hours[i].values()) for i in range(7)}
+        day = {j: sum(self.hours[i][j] for i in range(7)) for j in range(24)}
+
+        busiest_weekday = top_key(week)
+        busiest_hour = top_key(day)
+        quietest_weekday = top_key(week, reverse=True)
+        quietest_hour = top_key(day, reverse=True)
+        n_weekdays = delta.days // 7
+        if (
+            self.dates[0].weekday() <= busiest_weekday
+            and self.dates[-1].weekday() >= busiest_weekday
+        ) or n_weekdays == 0:
+            n_weekdays += 1
+        n_hours = delta.days
+        if self.dates[0].hour <= busiest_hour and self.dates[-1].hour >= busiest_hour:
+            n_hours += 1
+        ret = [
+            f"- **earliest message**: {from_now(self.dates[0])}",
+            f"- **latest message**: {from_now(self.dates[-1])}",
+            f"- **messages/day**: {precise(total_msg/delta.days, precision=3)}",
+            f"- **busiest day of week**: {calendar.day_name[busiest_weekday]} (~{precise(week[busiest_weekday]/n_weekdays, precision=3)} msg, {percent(week[busiest_weekday]/total_msg)})",
+            f"- **quietest day of week**: {calendar.day_name[quietest_weekday]} (~{precise(week[quietest_weekday]/n_weekdays, precision=3)} msg, {percent(week[quietest_weekday]/total_msg)})"
+            if week[quietest_weekday] > 0
+            else "",
+            f"- **busiest day ever**: {from_now(self.busiest_day)} ({self.busiest_day_count} msg)"
+            if self.busiest_day is not None
+            else "",
+            f"- **messages/hour**: {precise(total_msg*3600/delta.total_seconds(), precision=3)}",
+            f"- **busiest hour of day**: {busiest_hour:0>2}:00 (~{precise(day[busiest_hour]/n_hours, precision=3)} msg, {percent(day[busiest_hour]/total_msg)})",
+            f"- **quietest hour of day**: {quietest_hour:0>2}:00 (~{precise(day[quietest_hour]/n_hours, precision=3)} msg, {percent(day[quietest_hour]/total_msg)})"
+            if day[quietest_hour] > 0
+            else "",
+            f"- **busiest hour ever**: {from_now(self.busiest_hour)} ({self.busiest_hour_count} msg)",
+            f"- **longest break**: {plural(round(self.longest_break.total_seconds()/3600), 'hour')} ({plural(self.longest_break.days,'day')}), started {from_now(self.longest_break_start)}",
+            f"- **avg. streak**: {precise(sum(self.streaks)/len(self.streaks), precision=3)} msg",
+            f"- **longest streak**: {self.longest_streak:,} msg, started {from_now(self.longest_streak_start)}"
+            if member_specific
+            else f"- **longest streak**: {mention(self.longest_streak_author)} ({self.longest_streak:,} msg, started {from_now(self.longest_streak_start)})",
+        ]
+        return ret

src/data_types/history.py

@@ -0,0 +1,112 @@
+from typing import List
+import random
+
+# Custom libs
+
+from utils import (
+    mention,
+    from_now,
+    message_link,
+    SPLIT_TOKEN,
+    FilterLevel,
+    should_allow_spoiler,
+    is_image_gif,
+)
+
+MAX_RANDOM_TRIES = 100
+
+
+class History:
+    def __init__(self):
+        self.messages = []
+
+    async def to_string_image(
+        self, *, type: str, spoiler: FilterLevel, gif_only: bool
+    ) -> List[str]:
+        if len(self.messages) == 0:
+            return ["There was no messages matching your filters"]
+        message = None
+        intro = None
+        real_message = None
+        if type == "first":
+            self.messages.sort(key=lambda m: m.created_at)
+            index = 0
+            while real_message is None and index < len(self.messages):
+                message = self.messages[index]
+                real_message = await message.fetch()
+                if real_message is not None and (
+                    not should_allow_spoiler(real_message, spoiler)
+                    or (gif_only and not is_image_gif(real_message))
+                ):
+                    real_message = None
+                index += 1
+            intro = f"First image out of {len(self.messages):,}"
+        elif type == "last":
+            self.messages.sort(key=lambda m: m.created_at, reverse=True)
+            index = 0
+            while real_message is None and index < len(self.messages):
+                message = self.messages[index]
+                real_message = await message.fetch()
+                if real_message is not None and (
+                    not should_allow_spoiler(real_message, spoiler)
+                    or (gif_only and not is_image_gif(real_message))
+                ):
+                    real_message = None
+                index += 1
+            intro = f"Last image out of {len(self.messages):,}"
+        elif type == "random":
+            intro = f"Random image out of {len(self.messages):,}"
+            tries = 0
+            while real_message is None and tries < MAX_RANDOM_TRIES:
+                message = random.choice(self.messages)
+                real_message = await message.fetch()
+                if real_message is not None and (
+                    not should_allow_spoiler(real_message, spoiler)
+                    or (gif_only and not is_image_gif(real_message))
+                ):
+                    real_message = None
+                tries += 1
+
+        if real_message is None:
+            return ["There was no messages matching your filters"]
+        image = "<Error>"
+        if len(real_message.attachments) > 0:
+            image = real_message.attachments[0].url
+        elif len(real_message.embeds) > 0:
+            image = real_message.embeds[0].url
+
+        return [
+            intro,
+            f"{from_now(message.created_at)}, {mention(message.author)} sent:",
+            f"<{message_link(message)}>",
+            SPLIT_TOKEN,
+            image,
+        ]
+
+    def to_string(self, *, type: str) -> List[str]:
+        if len(self.messages) == 0:
+            return ["There was no messages matching your filters"]
+        message = None
+        intro = None
+        if type == "first":
+            self.messages.sort(key=lambda m: m.created_at)
+            message = self.messages[0]
+            intro = f"First message out of {len(self.messages):,}"
+        elif type == "last":
+            self.messages.sort(key=lambda m: m.created_at, reverse=True)
+            message = self.messages[0]
+            intro = f"Last message out of {len(self.messages):,}"
+        elif type == "random":
+            message = random.choice(self.messages)
+            intro = f"Random message out of {len(self.messages):,}"
+
+        text = ["> " + line for line in message.content.splitlines()]
+        if message.attachment:
+            text += ["> <image>" if message.image else "> <attachment>"]
+
+        return [
+            intro,
+            f"{from_now(message.created_at)}, {mention(message.author)} said:",
+            *text,
+            f"<{message_link(message)}>",
+        ]

src/data_types/presence.py

@@ -0,0 +1,94 @@
+from typing import List, Optional
+from collections import defaultdict
+
+
+from utils import mention, channel_mention, plural, percent, top_key, val_sum
+
+
+class Presence:
+    def __init__(self):
+        self.messages = defaultdict(int)
+        self.reactions = defaultdict(int)
+        self.used_reaction = defaultdict(int)
+        self.channel_usage = defaultdict(int)
+        self.channel_total = defaultdict(int)
+        self.mentions = defaultdict(int)
+        self.mention_others = defaultdict(int)
+        self.mention_count = defaultdict(int)
+
+    def to_string(
+        self,
+        msg_count: int,
+        total_msg: int,
+        *,
+        chan_count: Optional[int],
+        show_top_channel: bool,
+        member_specific: bool,
+    ) -> List[str]:
+        if chan_count is None:
+            type = "server's"
+        elif chan_count == 1:
+            type = "channel's"
+        else:
+            type = "channels'"
+        top_member = top_key(self.messages)
+        top_channel = top_key(self.channel_usage)
+        channel_sum = val_sum(self.channel_usage)
+        found_in = top_key(
+            self.channel_usage,
+            key=lambda k: self.channel_usage[k] / self.channel_total[k],
+        )
+        top_mention = top_key(self.mentions)
+        mention_sum = val_sum(self.mentions)
+        top_mention_others = top_key(self.mention_others)
+        mention_others_sum = val_sum(self.mention_others)
+        top_member_mentioned = top_key(self.mention_count)
+        total_reaction_used = val_sum(self.reactions)
+        top_reaction = top_key(self.reactions)
+        top_reaction_member = top_key(self.used_reaction)
+
+        ret = [
+            f"- **messages**: {msg_count:,} ({percent(msg_count/total_msg)} of {type})"
+            if member_specific
+            else f"- **top messages**:  {mention(top_member)} ({self.messages[top_member]:,} msg, {percent(self.messages[top_member]/val_sum(self.messages))})",
+            f"- **most visited channel**: {channel_mention(top_channel)} ({self.channel_usage[top_channel]:,} msg, {percent(self.channel_usage[top_channel]/channel_sum)})"
+            if show_top_channel
+            else "",
+            f"- **most contributed channel**: {channel_mention(found_in)} ({self.channel_usage[found_in]:,} msg, {percent(self.channel_usage[found_in]/self.channel_total[found_in])} of {type})"
+            if show_top_channel and member_specific
+            else "",
+            f"- **was mentioned**: {plural(mention_sum, 'time')} ({percent(mention_sum/val_sum(self.mention_count))} of {type})"
+            if member_specific and len(self.mentions) > 0
+            else "",
+            f"- **mostly mentioned by**: {mention(top_mention)} ({plural(self.mentions[top_mention], 'time')}, {percent(self.mentions[top_mention]/mention_sum)})"
+            if member_specific and len(self.mentions) > 0
+            else "",
+            f"- **mentioned others**: {plural(mention_others_sum, 'time')} ({percent(mention_others_sum/val_sum(self.mention_count))} of {type})"
+            if len(self.mention_others) > 0 and member_specific
+            else "",
+            f"- **mostly mentioned**: {mention(top_mention_others)} ({plural(self.mention_others[top_mention_others], 'time')}, {percent(self.mention_others[top_mention_others]/mention_others_sum)})"
+            if len(self.mention_others) > 0 and member_specific
+            else "",
+            f"- **mentioned**: {plural(mention_others_sum, 'time')} ({mention(top_member_mentioned)}, {percent(self.mention_count[top_member_mentioned]/val_sum(self.mention_count))})"
+            if len(self.mention_others) > 0 and not member_specific
+            else "",
+            f"- **top mentions**: {mention(top_member_mentioned)} ({plural(self.mention_count[top_member_mentioned], 'time')}, {percent(self.mention_count[top_member_mentioned]/val_sum(self.mention_count))})"
+            if len(self.mention_others) > 0 and not member_specific
+            else "",
+            f"- **most mentioned**: {mention(top_mention_others)} ({plural(self.mention_others[top_mention_others], 'time')}, {percent(self.mention_others[top_mention_others]/mention_others_sum)})"
+            if len(self.mention_others) > 0 and not member_specific
+            else "",
+            f"- **reactions**: {plural(total_reaction_used, 'time')}"
+            if len(self.reactions) > 0 and not member_specific
+            else "",
+            f"- **reactions**: {plural(total_reaction_used, 'time')} ({percent(total_reaction_used/val_sum(self.used_reaction))} of {type})"
+            if len(self.reactions) > 0 and member_specific
+            else "",
+            f"- **top reactions**: {mention(top_reaction_member)} ({plural(self.used_reaction[top_reaction_member], 'time')}, {percent(self.used_reaction[top_reaction_member]/val_sum(self.used_reaction))})"
+            if len(self.reactions) > 0 and not member_specific
+            else "",
+            f"- **most used reaction**: {top_reaction} ({plural(self.reactions[top_reaction], 'time')}, {percent(self.reactions[top_reaction]/total_reaction_used)})"
+            if len(self.reactions) > 0
+            else "",
+        ]
+        return ret

src/logs/__init__.py

@@ -0,0 +1,3 @@
+from .message_log import MessageLog
+from .channel_logs import ChannelLogs
+from .guild_logs import GuildLogs, ALREADY_RUNNING, CANCELLED, NO_FILE

src/logs/channel_logs.py

@@ -0,0 +1,141 @@
+import logging
+from typing import Union, Tuple, Any
+import discord
+from datetime import datetime
+
+from . import MessageLog
+from utils import serialize, FakeMessage
+
+CHUNK_SIZE = 2000
+FORMAT = 3
+
+
+class ChannelLogs:
+    def __init__(self, channel: Union[discord.TextChannel, dict], guild: Any):
+        self.guild = guild
+        if isinstance(channel, discord.TextChannel):
+            self.id = channel.id
+            self.name = channel.name
+            self.last_message_id = None
+            self.first_message_id = None
+            self.format = FORMAT
+            self.messages = set()
+            self.start_date = None
+        elif isinstance(channel, dict):
+            self.format = channel["format"] if "format" in channel else None
+            if not self.is_format():
+                return
+            self.id = int(channel["id"])
+            self.name = channel["name"]
+            self.last_message_id = (
+                int(channel["last_message_id"])
+                if channel["last_message_id"] is not None
+                else None
+            )
+            self.first_message_id = (
+                int(channel["first_message_id"])
+                if "first_message_id" in channel
+                and channel["first_message_id"] is not None
+                else None
+            )
+            self.messages = {
+                MessageLog(message, self) for message in channel["messages"]
+            }
+            self.start_date = (
+                self.sorted_messages[0].created_at if len(self.messages) > 0 else None
+            )
+
+    def is_format(self):
+        return self.format == FORMAT
+
+    def preload(self, channel: discord.TextChannel):
+        self.name = channel.name
+        self.channel = channel
+
+    @property
+    def sorted_messages(self):
+        return sorted(self.messages)
+
+    @property
+    def nsfw(self):
+        self.channel.nsfw
+
+    async def load(
+        self, channel: discord.TextChannel, start_date: datetime, stop_date: datetime
+    ) -> Tuple[int, int]:
+        is_empty = self.last_message_id is None
+        try:
+            if is_empty:
+                sanity_check = len(await channel.history(limit=1).flatten())
+                if sanity_check != 1:
+                    yield len(self.messages), True
+                    return
+            # load backward
+            if is_empty or (
+                self.first_message_id is not None
+                and (
+                    start_date is None
+                    or (self.start_date is not None and self.start_date > start_date)
+                )
+            ):
+                first_message_date = None
+                tmp_message_id = 0
+                done = 0
+                while (
+                    first_message_date is None
+                    or (
+                        done >= CHUNK_SIZE
+                        and (start_date is None or first_message_date > start_date)
+                    )
+                ) and tmp_message_id != self.first_message_id:
+                    tmp_message_id = self.first_message_id
+                    done = 0
+                    async for message in channel.history(
+                        limit=CHUNK_SIZE,
+                        before=FakeMessage(self.first_message_id)
+                        if self.first_message_id is not None
+                        else None,
+                        oldest_first=False,
+                    ):
+                        done += 1
+                        self.first_message_id = message.id
+                        first_message_date = message.created_at
+                        m = MessageLog(message, self)
+                        await m.load(message)
+                        self.messages.add(m)
+                    yield len(self.messages), False
+                if done < CHUNK_SIZE:  # reached bottom
+                    self.first_message_id = None
+                self.last_message_id = channel.last_message_id
+            # load forward
+            last_message_date = self.sorted_messages[-1].created_at
+            if not is_empty and (stop_date is None or last_message_date < stop_date):
+                tmp_message_id = None
+                while (
+                    self.last_message_id != channel.last_message_id
+                    and (stop_date is None or last_message_date < stop_date)
+                ) and self.last_message_id != tmp_message_id:
+                    tmp_message_id = self.last_message_id
+                    async for message in channel.history(
+                        limit=CHUNK_SIZE,
+                        after=FakeMessage(self.first_message_id),
+                        oldest_first=True,
+                    ):
+                        last_message_date = message.created_at
+                        self.last_message_id = message.id
+                        m = MessageLog(message, self)
+                        await m.load(message)
+                        self.messages.add(m)
+                    yield len(self.messages), False
+        except discord.errors.HTTPException as e:
+            yield -1, True
+            return  # When an exception occurs (like Forbidden)
+        self.start_date = (
+            self.sorted_messages[0].created_at if len(self.messages) > 0 else None
+        )
+        yield len(self.messages), True
+
+    def dict(self) -> dict:
+        channel = serialize(self, not_serialized=["channel", "guild", "start_date"])
+        channel["messages"] = [message.dict() for message in self.messages]
+        return channel

src/logs/guild_logs.py

@@ -0,0 +1,391 @@
+from typing import List, Tuple
+import os
+import discord
+import json
+import gzip
+from datetime import datetime
+import time
+import logging
+import asyncio
+import threading
+
+
+from . import ChannelLogs
+from utils import code_message, delta, deltas
+
+
+LOG_DIR = "logs"
+LOG_EXT = ".logz"
+
+current_analysis = []
+current_analysis_lock = threading.Lock()
+
+
+ALREADY_RUNNING = -100
+CANCELLED = -200
+NO_FILE = -300
+
+# 5 minutes, assume 'fast' arg
+MIN_MODIFICATION_TIME = 5 * 60
+# ~1 year, remove log file
+MAX_MODIFICATION_TIME = 365 * 24 * 60 * 60
+
+
+class Worker:
+    def __init__(
+        self,
+        channel_log: ChannelLogs,
+        channel: discord.TextChannel,
+        start_date: datetime,
+        stop_date: datetime,
+    ):
+        self.channel_log = channel_log
+        self.channel = channel
+        self.start_msg = len(channel_log.messages)
+        self.total_msg = self.start_msg
+        self.queried_msg = 0
+        self.done = False
+        self.cancelled = False
+        self.loop = asyncio.get_event_loop()
+        self.start_date = start_date
+        self.stop_date = stop_date
+
+    def start(self):
+        asyncio.run_coroutine_threadsafe(self.process(), self.loop)
+
+    async def process(self):
+        async for count, done in self.channel_log.load(
+            self.channel, self.start_date, self.stop_date
+        ):
+            if count > 0:
+                self.queried_msg = count - self.start_msg
+                self.total_msg = count
+            self.done = done
+            if self.cancelled:
+                return
+
+
+class GuildLogs:
+    def __init__(self, guild: discord.Guild):
+        self.id = guild.id
+        self.guild = guild
+        self.log_file = os.path.join(LOG_DIR, f"{guild.id}{LOG_EXT}")
+        self.channels = {}
+        self.locked = False
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, type, value, tb):
+        del self.channels
+        del self.guild
+        if self.locked:
+            self.unlock()
+
+    def dict(self) -> dict:
+        return {id: self.channels[id].dict() for id in self.channels}
+
+    def check_cancelled(self) -> bool:
+        return self.locked and self.log_file not in current_analysis
+
+    def lock(self) -> bool:
+        current_analysis_lock.acquire()
+        if self.log_file in current_analysis:
+            current_analysis_lock.release()
+            return False
+        self.locked = True
+        current_analysis.append(self.log_file)
+        current_analysis_lock.release()
+        return True
+
+    def unlock(self):
+        if self.locked:
+            self.locked = False
+            current_analysis_lock.acquire()
+            if self.log_file in current_analysis:
+                current_analysis.remove(self.log_file)
+            current_analysis_lock.release()
+
+    async def load(
+        self,
+        progress: discord.Message,
+        target_channels: List[discord.TextChannel],
+        start_date: datetime,
+        stop_date: datetime,
+        *,
+        fast: bool,
+        fresh: bool,
+    ) -> Tuple[int, int]:
+        self.locked = False
+        if not fast and not self.lock():
+            return ALREADY_RUNNING, 0
+        t00 = datetime.now()
+        # read logs
+        if not os.path.exists(LOG_DIR):
+            os.mkdir(LOG_DIR)
+        last_time = None
+        if not os.path.exists(self.log_file):
+            return NO_FILE, 0
+        channels = {}
+        try:
+            last_time = os.path.getmtime(self.log_file)
+            gziped_data = None
+            await code_message(progress, "Reading saved history (1/4)...")
+            t0 = datetime.now()
+            with open(self.log_file, mode="rb") as f:
+                gziped_data = f.read()
+            logging.info(f"log {self.guild.id} > read in {delta(t0):,}ms")
+            if self.check_cancelled():
+                return CANCELLED, 0
+            await code_message(progress, "Reading saved history (2/4)...")
+            t0 = datetime.now()
+            json_data = gzip.decompress(gziped_data)
+            del gziped_data
+            logging.info(f"log {self.guild.id} > gzip decompress in {delta(t0):,}ms")
+            if self.check_cancelled():
+                return CANCELLED, 0
+            await code_message(progress, "Reading saved history (3/4)...")
+            t0 = datetime.now()
+            channels = json.loads(json_data)
+            del json_data
+            logging.info(f"log {self.guild.id} > json parse in {delta(t0):,}ms")
+            if self.check_cancelled():
+                return CANCELLED, 0
+            await code_message(progress, "Reading saved history (4/4)...")
+            t0 = datetime.now()
+            self.channels = {
+                int(id): ChannelLogs(channels[id], self) for id in channels
+            }
+            # remove invalid format
+            self.channels = {
+                id: self.channels[id]
+                for id in self.channels
+                if self.channels[id].is_format()
+            }
+            logging.info(f"log {self.guild.id} > loaded in {delta(t0):,}ms")
+        except json.decoder.JSONDecodeError:
+            logging.error(f"log {self.guild.id} > invalid JSON")
+        except IOError:
+            logging.error(f"log {self.guild.id} > cannot read")
+
+        if len(target_channels) == 0:
+            target_channels = (
+                self.channels.values() if fast else self.guild.text_channels
+            )
+        elif fast:
+            # select already loaded channels only
+            target_channels_tmp = [
+                channel for channel in target_channels if channel.id in self.channels
+            ]
+            if len(target_channels_tmp) == 0:
+                fast = False
+            else:
+                target_channels = target_channels_tmp
+
+        # assume fast if file is fresh
+        if (
+            not fast
+            and not fresh
+            and start_date is None
+            and stop_date is None
+            and last_time is not None
+            and (time.time() - last_time) < MIN_MODIFICATION_TIME
+        ):
+            invalid_target_channels = [
+                channel
+                for channel in target_channels
+                if channel.id not in self.channels
+                or self.channels[channel.id].first_message_id is not None
+            ]
+            if len(invalid_target_channels) == 0:
+                logging.info(f"log {self.guild.id} > assumed fast")
+                fast = True
+                if self.locked:
+                    self.unlock()
+
+        total_msg = 0
+        total_chan = 0
+        if fast:
+            target_channels_id = [channel.id for channel in target_channels]
+            total_msg = sum(
+                [
+                    len(channel.messages)
+                    for channel in self.channels.values()
+                    if channel.id in target_channels_id
+                ]
+            )
+            total_chan = len(target_channels)
+            for channel in target_channels:
+                self.channels[channel.id].preload(channel)
+        else:
+            if not self.locked and not self.lock():
+                return ALREADY_RUNNING, 0
+            # load channels
+            t0 = datetime.now()
+            loading_new = 0
+            queried_msg = 0
+            total_chan = 0
+            max_chan = len(target_channels)
+            if self.check_cancelled():
+                return CANCELLED, 0
+            workers = []
+            for channel in target_channels:
+                if channel.id not in self.channels or fresh:
+                    loading_new += 1
+                    self.channels[channel.id] = ChannelLogs(channel, self)
+                self.channels[channel.id].preload(channel)
+                workers += [
+                    Worker(self.channels[channel.id], channel, start_date, stop_date)
+                ]
+            warning_msg = "(this might take a while)"
+            if len(target_channels) > 5 and loading_new > 5:
+                warning_msg = "(most channels are new, this will take a long while)"
+            elif loading_new > 0:
+                warning_msg = "(some channels are new, this might take a long while)"
+            await code_message(
+                progress,
+                f"Reading new history...\n0 messages in 0/{max_chan:,} channels\n{warning_msg}",
+            )
+            for worker in workers:
+                worker.start()
+            done = False
+            while not done:
+                if self.check_cancelled():
+                    for worker in workers:
+                        worker.cancelled = True
+                    return CANCELLED, 0
+
+                await asyncio.sleep(0.5)
+
+                remaining = [
+                    worker.channel.name for worker in workers if not worker.done
+                ]
+                total_chan = max_chan - len(remaining)
+                queried_msg = sum([worker.queried_msg for worker in workers])
+                total_msg = sum([worker.total_msg for worker in workers])
+
+                if total_chan == max_chan:
+                    done = True
+
+                remaining_msg = ""
+
+                if len(remaining) <= 5:
+                    remaining_msg = "\nRemaining: " + ", ".join(remaining)
+
+                await code_message(
+                    progress,
+                    f"Reading new history...\n{total_msg:,} messages in {total_chan:,}/{max_chan:,} channels ({round(queried_msg/deltas(t0)):,}m/s)\n{warning_msg}{remaining_msg}",
+                )
+            logging.info(
+                f"log {self.guild.id} > queried {queried_msg} in {delta(t0):,}ms -> {queried_msg / deltas(t0):,.3f} m/s"
+            )
+            # write logs
+            real_total_msg = sum(
+                [len(channel.messages) for channel in self.channels.values()]
+            )
+            real_total_chan = len(self.channels)
+            if self.check_cancelled():
+                return CANCELLED, 0
+            await code_message(
+                progress,
+                f"Saving history (1/3)...\n{real_total_msg:,} messages in {real_total_chan:,} channels",
+            )
+            t0 = datetime.now()
+            json_data = bytes(json.dumps(self.dict()), "utf-8")
+            logging.info(
+                f"log {self.guild.id} > json dump in {delta(t0):,}ms -> {real_total_msg / deltas(t0):,.3f} m/s"
+            )
+            if self.check_cancelled():
+                return CANCELLED, 0
+            await code_message(
+                progress,
+                f"Saving history (2/3)...\n{real_total_msg:,} messages in {real_total_chan:,} channels",
+            )
+            t0 = datetime.now()
+            gziped_data = gzip.compress(json_data)
+            del json_data
+            logging.info(
+                f"log {self.guild.id} > gzip in {delta(t0):,}ms -> {real_total_msg / deltas(t0):,.3f} m/s"
+            )
+            if self.check_cancelled():
+                return CANCELLED, 0
+            await code_message(
+                progress,
+                f"Saving history (3/3)...\n{real_total_msg:,} messages in {real_total_chan:,} channels",
+            )
+            t0 = datetime.now()
+            with open(self.log_file, mode="wb") as f:
+                f.write(gziped_data)
+            del gziped_data
+            logging.info(
+                f"log {self.guild.id} > saved in {delta(t0):,}ms -> {real_total_msg / deltas(t0):,.3f} m/s"
+            )
+        if self.check_cancelled():
+            return CANCELLED, 0
+        await code_message(
+            progress,
+            f"Analysing...\n{total_msg:,} messages in {total_chan:,} channels",
+        )
+        logging.info(f"log {self.guild.id} > TOTAL TIME: {delta(t00):,}ms")
+        if self.locked:
+            current_analysis_lock.acquire()
+            current_analysis.remove(self.log_file)
+            current_analysis_lock.release()
+        return total_msg, total_chan
+
+    @staticmethod
+    async def cancel(client: discord.client, message: discord.Message, *args: str):
+        logs = GuildLogs(message.guild)
+        current_analysis_lock.acquire()
+        if logs.log_file in current_analysis:
+            current_analysis.remove(logs.log_file)
+            current_analysis_lock.release()
+        else:
+            current_analysis_lock.release()
+            await message.channel.send(
+                f"No cancellable analysis are currently running on this server",
+                reference=message,
+            )
+
+    @staticmethod
+    def init_log(guild: List[discord.Guild]):
+        if not os.path.exists(LOG_DIR):
+            os.mkdir(LOG_DIR)
+        filename = os.path.join(LOG_DIR, f"{guild.id}{LOG_EXT}")
+        if not os.path.exists(filename):
+            with open(filename, mode="wb") as f:
+                f.write(gzip.compress(bytes("{}", "utf-8")))
+            logging.info(f"log {guild.id} > created")
+        else:
+            logging.info(f"log {guild.id} > already exists")
+
+    @staticmethod
+    def remove_log(guild: List[discord.Guild]):
+        if not os.path.exists(LOG_DIR):
+            os.mkdir(LOG_DIR)
+        filename = os.path.join(LOG_DIR, f"{guild.id}{LOG_EXT}")
+        if os.path.exists(filename):
+            os.unlink(filename)
+            logging.info(f"log {guild.id} > removed")
+        else:
+            logging.info(f"log {guild.id} > does not exists")
+
+    @staticmethod
+    def check_logs(guilds: List[discord.Guild]):
+        logging.info(f"checking logs...")
+        if not os.path.exists(LOG_DIR):
+            os.mkdir(LOG_DIR)
+        guild_ids = [str(guild.id) for guild in guilds]
+        for item in os.listdir(LOG_DIR):
+            path = os.path.join(LOG_DIR, item)
+            name, ext = os.path.splitext(item)
+            if os.path.isfile(path) and ext == LOG_EXT:
+                if (
+                    name in guild_ids
+                    and (time.time() - os.path.getmtime(path)) > MAX_MODIFICATION_TIME
+                ):
+                    logging.info(f"> removing old log '{path}'")
+                    os.unlink(path)
+                elif name not in guild_ids:
+                    logging.info(f"> removing unused log '{path}'")
+                    os.unlink(path)

src/logs/message_log.py

@@ -0,0 +1,90 @@
+from typing import Optional, Union, Any
+import discord
+from datetime import datetime
+
+from utils import (
+    serialize,
+    has_image,
+)
+
+
+class MessageLog:
+    def __init__(self, message: Union[discord.Message, dict], channel: Any):
+        self.channel = channel
+        if isinstance(message, discord.Message):
+            self.id = message.id
+            self.created_at = message.created_at
+            self.edited_at = message.edited_at
+            self.author = message.author.id
+            self.pinned = message.pinned
+            self.mention_everyone = message.mention_everyone
+            self.tts = message.tts
+            self.bot = message.author.bot or message.author.system
+            self.content = message.content
+            self.mentions = message.raw_mentions
+            if message.reference is not None:
+                self.reference = message.reference.message_id
+                if message.reference.resolved is not None:
+                    try:
+                        self.mentions += [message.reference.resolved.author.id]
+                    except AttributeError:
+                        pass
+            else:
+                self.reference = None
+            self.role_mentions = message.raw_role_mentions
+            self.channel_mentions = message.raw_channel_mentions
+            self.image = False
+            self.attachment = len(message.attachments) > 0
+            self.embed = len(message.embeds) > 0
+            self.image = has_image(message)
+            self.reactions = {}
+        elif isinstance(message, dict):
+            self.id = int(message["id"])
+            self.created_at = datetime.fromisoformat(message["created_at"])
+            self.edited_at = (
+                datetime.fromisoformat(message["edited_at"])
+                if message["edited_at"] is not None
+                else None
+            )
+            self.author = int(message["author"])
+            self.pinned = message["pinned"]
+            self.mention_everyone = message["mention_everyone"]
+            self.tts = message["tts"]
+            self.reference = (
+                int(message["reference"]) if message["reference"] is not None else None
+            )
+            self.bot = message["bot"]
+            self.content = message["content"]
+            self.mentions = [int(m) for m in message["mentions"]]
+            self.role_mentions = [int(m) for m in message["role_mentions"]]
+            self.channel_mentions = [int(m) for m in message["channel_mentions"]]
+            self.image = message["image"]
+            self.embed = message["embed"]
+            self.attachment = message["attachment"]
+            self.reactions = message["reactions"]
+
+    def __eq__(self, other: object) -> bool:
+        return isinstance(other, self.__class__) and other.id == self.id
+
+    def __gt__(self, other: "MessageLog") -> bool:
+        return self.created_at > other.created_at
+
+    def __hash__(self) -> int:
+        return self.id
+
+    async def load(self, message: discord.Message):
+        for reaction in message.reactions:
+            self.reactions[str(reaction.emoji)] = []
+            async for user in reaction.users():
+                self.reactions[str(reaction.emoji)] += [user.id]
+
+    async def fetch(self) -> Optional[discord.Message]:
+        try:
+            return await self.channel.channel.fetch_message(self.id)
+        except (discord.NotFound, discord.Forbidden, discord.HTTPException):
+            return None
+
+    def dict(self) -> dict:
+        return serialize(
+            self, not_serialized=["channel"], dates=["created_at", "edited_at"]
+        )

src/main.py

@@ -0,0 +1,156 @@
+import sys
+from miniscord import Bot
+import logging
+
+if sys.version_info < (3, 7):
+    print("Please upgrade your Python version to 3.7.0 or higher")
+    sys.exit(1)
+
+from utils import emojis, gdpr, command_cache
+import scanners
+from logs import GuildLogs
+
+logging.basicConfig(
+    format="[%(asctime)s][%(levelname)s][%(module)s] %(message)s", level=logging.INFO
+)
+
+emojis.load_emojis()
+
+bot = Bot(
+    "Discord Analyst",
+    "1.16.1",
+    alias="%",
+)
+
+bot.log_calls = True
+
+
+async def on_ready():
+    GuildLogs.check_logs(bot.client.guilds)
+    return True
+
+
+async def on_guild_remove():
+    GuildLogs.check_logs(bot.client.guilds)
+    return True
+
+
+bot.register_event(on_ready)
+bot.register_event(on_guild_remove)
+
+bot.register_command(
+    "(cancel|stop)",
+    GuildLogs.cancel,
+    "cancel: stop current analysis (not launched with fast)",
+    "```\n%cancel: Stop current analysis (not launched with fast)\n```",
+)
+bot.register_command(
+    "gdpr",
+    gdpr.process,
+    "gdpr: displays GDPR information",
+    gdpr.HELP,
+)
+bot.register_command(
+    "words",
+    lambda *args: scanners.WordsScanner().compute(*args),
+    "words: (BETA) rank words by their usage",
+    scanners.WordsScanner.help(),
+)
+bot.register_command(
+    "repeat",
+    command_cache.repeat,
+    "repeat: repeat last analysis (adding supplied arguments)",
+    "```\n%repeat: repeat last analysis (adding supplied arguments)\n```",
+)
+bot.register_command(
+    "mobile",
+    lambda *args: command_cache.repeat(*args, add_args=["mobile"]),
+    "mobile: fix @invalid-user for last command but mentions users",
+    "```\n%mobile: fix @invalid-user for last command but mentions users\n```",
+)
+bot.register_command(
+    "find",
+    lambda *args: scanners.FindScanner().compute(*args),
+    "find: find specific words or phrases",
+    scanners.FindScanner.help(),
+)
+bot.register_command(
+    "last",
+    lambda *args: scanners.LastScanner().compute(*args),
+    "last: read last message",
+    scanners.LastScanner.help(),
+)
+bot.register_command(
+    "(rand(om)?|mood)",
+    lambda *args: scanners.RandomScanner().compute(*args),
+    "rand: read a random message",
+    scanners.RandomScanner.help(),
+)
+bot.register_command(
+    "first",
+    lambda *args: scanners.FirstScanner().compute(*args),
+    "first: read first message",
+    scanners.FirstScanner.help(),
+)
+bot.register_command(
+    "mentioned",
+    lambda *args: scanners.MentionedScanner().compute(*args),
+    "mentioned: rank specific user mentions by their usage",
+    scanners.MentionedScanner.help(),
+)
+bot.register_command(
+    "(mentions?)",
+    lambda *args: scanners.MentionsScanner().compute(*args),
+    "mentions: rank mentions by their usage",
+    scanners.MentionsScanner.help(),
+)
+bot.register_command(
+    "(emojis?|emotes?)",
+    lambda *args: scanners.EmojisScanner().compute(*args),
+    "emojis: rank emojis by their usage",
+    scanners.EmojisScanner.help(),
+)
+bot.register_command(
+    "(react(ions?)?)",
+    lambda *args: scanners.ReactionsScanner().compute(*args),
+    "react: rank users by their reactions",
+    scanners.ReactionsScanner.help(),
+)
+bot.register_command(
+    "(channels?|chan)",
+    lambda *args: scanners.ChannelsScanner().compute(*args),
+    "chan: rank channels by their messages",
+    scanners.ChannelsScanner.help(),
+)
+bot.register_command(
+    "(messages?|msg)",
+    lambda *args: scanners.MessagesScanner().compute(*args),
+    "msg: rank users by their messages",
+    scanners.MessagesScanner.help(),
+)
+bot.register_command(
+    "pres(ence)?",
+    lambda *args: scanners.PresenceScanner().compute(*args),
+    "pres: presence analysis",
+    scanners.PresenceScanner.help(),
+)
+bot.register_command(
+    "compo(sition)?",
+    lambda *args: scanners.CompositionScanner().compute(*args),
+    "compo: composition analysis",
+    scanners.CompositionScanner.help(),
+)
+bot.register_command(
+    "freq(ency)?",
+    lambda *args: scanners.FrequencyScanner().compute(*args),
+    "freq: frequency analysis",
+    scanners.FrequencyScanner.help(),
+)
+bot.register_command(
+    "(full|scan)",
+    lambda *args: scanners.FullScanner().compute(*args),
+    "scan: full analysis",
+    scanners.FullScanner.help(),
+)
+
+bot.start()

src/scanners/__init__.py

@@ -0,0 +1,17 @@
+from .scanner import Scanner
+
+from .channels_scanner import ChannelsScanner
+from .composition_scanner import CompositionScanner
+from .emojis_scanner import EmojisScanner
+from .find_scanner import FindScanner
+from .first_scanner import FirstScanner
+from .frequency_scanner import FrequencyScanner
+from .full_scanner import FullScanner
+from .last_scanner import LastScanner
+from .mentioned_scanner import MentionedScanner
+from .mentions_scanner import MentionsScanner
+from .messages_scanner import MessagesScanner
+from .presence_scanner import PresenceScanner
+from .random_scanner import RandomScanner
+from .reactions_scanner import ReactionsScanner
+from .words_scanner import WordsScanner

src/scanners/channels_scanner.py

@@ -0,0 +1,87 @@
+from typing import Dict, List
+from collections import defaultdict
+import discord
+
+
+# Custom libs
+
+from logs import ChannelLogs, MessageLog
+from .scanner import Scanner
+from data_types import Counter
+from utils import generate_help, mention, channel_mention
+
+
+class ChannelsScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "chan",
+            "Rank channels by their messages",
+            args=["<n> - top <n>, default is 10", "all/everyone - include bots"],
+            example="5 @user",
+        )
+
+    def __init__(self):
+        super().__init__(
+            has_digit_args=True,
+            valid_args=["all", "everyone"],
+            help=ChannelsScanner.help(),
+            intro_context="Channels",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.top = 10
+        for arg in args:
+            if arg.isdigit():
+                self.top = int(arg)
+        self.all_messages = "all" in args or "everyone" in args
+        # Create mentions dict
+        self.messages = defaultdict(Counter)
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return ChannelsScanner.analyse_message(
+            channel.id,
+            message,
+            self.messages,
+            self.raw_members,
+            all_messages=self.all_messages,
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        names = [name for name in self.messages]
+        names.sort(key=lambda name: self.messages[name].score(), reverse=True)
+        names = names[: self.top]
+        usage_count = Counter.total(self.messages)
+        res = [intro]
+        res += [
+            self.messages[name].to_string(
+                names.index(name),
+                channel_mention(name),
+                total_usage=usage_count,
+                counted="message",
+                transform=lambda id: f" by {mention(id)}",
+                top=len(self.members) != 1,
+            )
+            for name in names
+        ]
+        return res
+
+    @staticmethod
+    def analyse_message(
+        channel_id: int,
+        message: MessageLog,
+        messages: Dict[str, Counter],
+        raw_members: List[int],
+        *,
+        all_messages: bool,
+    ) -> bool:
+        impacted = False
+        if (
+            len(raw_members) == 0
+            and (not message.bot or all_messages)
+            or message.author in raw_members
+        ):
+            impacted = True
+            messages[channel_id].update_use(1, message.created_at, message.author)
+        return impacted

src/scanners/composition_scanner.py

@@ -0,0 +1,117 @@
+from typing import List
+import re
+import discord
+
+
+# Custom libs
+
+from .scanner import Scanner
+from data_types import Composition
+from logs import ChannelLogs, MessageLog
+from utils import emojis, generate_help
+
+
+class CompositionScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help("compo", "Show composition statistics")
+
+    def __init__(self):
+        super().__init__(
+            valid_args=["all", "everyone"],
+            help=CompositionScanner.help(),
+            intro_context="Composition",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.compo = Composition()
+        self.all_messages = "all" in args or "everyone" in args
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        ret = CompositionScanner.analyse_message(
+            message, self.compo, self.raw_members, all_messages=self.all_messages
+        )
+        return ret
+
+    def get_results(self, intro: str) -> List[str]:
+        res = [intro]
+        res += self.compo.to_string(self.msg_count)
+        return res
+
+    @staticmethod
+    def analyse_message(
+        message: MessageLog,
+        compo: Composition,
+        raw_members: List[int],
+        *,
+        all_messages: bool,
+    ) -> bool:
+        impacted = False
+        # If author is included in the selection (empty list is all)
+        if (
+            (not message.bot or all_messages)
+            and len(raw_members) == 0
+            or message.author in raw_members
+        ):
+            impacted = True
+            compo.total_characters += len(message.content)
+
+            emojis_found = emojis.regex.findall(message.content)
+            without_emoji = message.content
+            for name in emojis_found:
+                if name in emojis.unicode_list or re.match(
+                    r"(<a?:[\w\-\~]+:\d+>|:[\w\\-\~]+:)", name
+                ):
+                    compo.emojis[name] += 1
+                    i = without_emoji.index(name)
+                    without_emoji = without_emoji[:i] + without_emoji[i + len(name) :]
+            if len(message.content.strip()) > 0 and len(without_emoji.strip()) == 0:
+                compo.emoji_only += 1
+            if len(emojis_found) > 0:
+                compo.emoji_msg += 1
+
+            links_found = re.findall(r"https?:\/\/", message.content)
+            compo.links += len(links_found)
+            if len(links_found) > 0:
+                compo.link_msg += 1
+
+            mentions = (
+                len(message.mentions)
+                + len(message.role_mentions)
+                + len(message.channel_mentions)
+            )
+            if message.mention_everyone:
+                compo.everyone += 1
+                mentions += 1
+            if mentions > 0:
+                compo.mentions += mentions
+                compo.mention_msg += 1
+
+            spoilers_found = re.findall(r"\|\|[^|]+\|\|", message.content)
+            if len(spoilers_found) > 0:
+                compo.spoilers += 1
+
+            if message.edited_at is not None:
+                compo.edited += 1
+            if message.reference is not None:
+                compo.answers += 1
+            if message.image:
+                compo.images += 1
+            if message.tts:
+                compo.tts += 1
+
+            if (
+                len(emojis_found) == 0
+                and message.reference is None
+                and not message.image
+                and len(message.mentions) == 0
+                and len(message.role_mentions) == 0
+                and len(message.channel_mentions) == 0
+                and not message.tts
+                and not message.mention_everyone
+                and not message.embed
+                and not message.attachment
+            ):
+                compo.plain_text += 1
+        return impacted

src/scanners/emojis_scanner.py

@@ -0,0 +1,149 @@
+from typing import Dict, List
+import discord
+
+
+# Custom libs
+
+from logs import ChannelLogs, MessageLog
+from data_types import Emoji, get_emoji_dict
+from .scanner import Scanner
+from utils import emojis, generate_help, plural, precise
+
+
+class EmojisScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "emojis",
+            "Rank emojis by their usage",
+            args=[
+                "<n> - top <n> emojis, default is 20",
+                "all - list all common emojis in addition to this guild's",
+                "members - show top member for each emojis",
+                "sort:usage/reaction - other sorting methods",
+                "everyone - include bots",
+            ],
+            example="10 all #mychannel1 #mychannel2 @user",
+        )
+
+    def __init__(self):
+        super().__init__(
+            has_digit_args=True,
+            valid_args=["all", "members", "sort:usage", "sort:reaction", "everyone"],
+            help=EmojisScanner.help(),
+            intro_context="Emoji usage",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        guild = message.channel.guild
+        # get max emojis to view
+        self.top = 20
+        for arg in args:
+            if arg.isdigit():
+                self.top = int(arg)
+        # check other args
+        self.all_emojis = "all" in args
+        self.show_members = "members" in args and (
+            len(self.members) == 0 or len(self.members) > 1
+        )
+        # Create emojis dict from custom emojis of the guild
+        self.emojis = get_emoji_dict(guild)
+        self.sort = None
+        if "sort:usage" in args:
+            self.sort = "usage"
+        elif "sort:reaction" in args:
+            self.sort = "reaction"
+        self.all_messages = "everyone" in args
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return EmojisScanner.analyse_message(
+            message,
+            self.emojis,
+            self.raw_members,
+            all_emojis=self.all_emojis,
+            all_messages=self.all_messages,
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        names = [name for name in self.emojis]
+        names.sort(
+            key=lambda name: self.emojis[name].score(
+                usage_weight=(0 if self.sort == "reaction" else 1),
+                react_weight=(0 if self.sort == "usage" else 1),
+            ),
+            reverse=True,
+        )
+        names = names[: self.top]
+        # Get the total of all emojis used
+        usage_count = 0
+        reaction_count = 0
+        for name in self.emojis:
+            usage_count += self.emojis[name].usages
+            reaction_count += self.emojis[name].reactions
+        res = [intro]
+        allow_unused = self.full and len(self.members) == 0
+        if self.sort is not None:
+            res += [f"(Sorted by {self.sort})"]
+        res += [
+            self.emojis[name].to_string(
+                names.index(name),
+                name,
+                total_usage=usage_count,
+                total_react=reaction_count,
+                show_life=False,
+                show_members=self.show_members or len(self.raw_members) == 0,
+            )
+            for name in names
+            if allow_unused or self.emojis[name].used()
+        ]
+        res += [
+            f"Total: {plural(usage_count,'time')} ({precise(usage_count/self.msg_count)}/msg)"
+        ]
+        if reaction_count > 0:
+            res[-1] += f" and {plural(reaction_count, 'reaction')}"
+        return res
+
+    @staticmethod
+    def analyse_message(
+        message: MessageLog,
+        emojis_dict: Dict[str, Emoji],
+        raw_members: List[int],
+        *,
+        all_emojis: bool,
+        all_messages: bool,
+    ) -> bool:
+        impacted = False
+        # If author is included in the selection (empty list is all)
+        if (
+            (not message.bot or all_messages)
+            and len(raw_members) == 0
+            or message.author in raw_members
+        ):
+            impacted = True
+            # Find all emojis un the current message in the form "<:emoji:123456789>"
+            # Filter for known emojis
+            found = emojis.regex.findall(message.content)
+            # For each emoji, update its usage
+            for name in found:
+                if name not in emojis_dict:
+                    if not all_emojis or name not in emojis.unicode_list:
+                        continue
+                emojis_dict[name].usages += 1
+                emojis_dict[name].update_use(message.created_at, [message.author])
+        # For each reaction of this message, test if known emoji and update when it's the case
+        for name in message.reactions:
+            if name not in emojis_dict:
+                if not all_emojis or name not in emojis.unicode_list:
+                    continue
+            if len(raw_members) == 0:
+                emojis_dict[name].reactions += len(message.reactions[name])
+                emojis_dict[name].update_use(
+                    message.created_at, message.reactions[name]
+                )
+            else:
+                for member in raw_members:
+                    if member in message.reactions[name]:
+                        emojis_dict[name].reactions += 1
+                        emojis_dict[name].update_use(message.created_at, [member])
+        return impacted

src/scanners/find_scanner.py

@@ -0,0 +1,134 @@
+from typing import Dict, List, Optional, Tuple
+from collections import defaultdict
+import discord
+import re
+
+# Custom libs
+
+from logs import ChannelLogs, MessageLog
+from .scanner import Scanner
+from data_types import Counter
+from utils import (
+    generate_help,
+    plural,
+    precise,
+    mention,
+    escape_text,
+)
+
+
+class FindScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "find",
+            "Find specific words or phrases (you can use quotes to add spaces in queries, backticks define regexes)",
+            args=[
+                "top - rank users for these queries",
+                "all/everyone - include bots",
+            ],
+            example='#mychannel1 #mychannel2 @user "I love you" "you too"',
+        )
+
+    def __init__(self):
+        super().__init__(
+            all_args=True,
+            valid_args=["all", "everyone", "top"],
+            help=FindScanner.help(),
+            intro_context="Matches",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.matches = defaultdict(Counter)
+        self.all_messages = "all" in args or "everyone" in args
+        self.top = "top" in args or len(self.other_args) == 1
+        if len(self.other_args) == 0:
+            await message.channel.send(
+                "You need to add a query to find (you can use quotes to add spaces in queries, backticks define regexes)",
+                reference=message,
+            )
+            return False
+        self.queries = [
+            (query, query.strip("`") if re.match(r"^`.*`$", query) else None)
+            for query in self.other_args
+        ]
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return FindScanner.analyse_message(
+            message,
+            self.matches,
+            self.queries,
+            self.raw_members,
+            all_messages=self.all_messages,
+            top=self.top,
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        res = [intro]
+        matches = [match for match in self.matches]
+        matches.sort(key=lambda match: self.matches[match].score(), reverse=True)
+        usage_count = Counter.total(self.matches)
+        if self.top:
+            res += [
+                self.matches[match].to_string(
+                    matches.index(match),
+                    mention(match),
+                    total_usage=usage_count,
+                )
+                for match in matches
+            ]
+        else:
+            res += [
+                self.matches[match].to_string(
+                    matches.index(match),
+                    f'"{escape_text(match)}"'
+                    if len(match.strip("`")) == len(match)
+                    else match,
+                    total_usage=self.msg_count,
+                    ranking=False,
+                    transform=lambda id: f" by {mention(id)}",
+                    top=len(self.members) != 1,
+                )
+                for match in matches
+            ]
+        if self.top or len(matches) > 1:
+            res += [
+                f"Total: {plural(usage_count,'time')} ({precise(usage_count/self.msg_count)}/msg)"
+            ]
+        return res
+
+    special_cases = ["'s", "s"]
+
+    @staticmethod
+    def analyse_message(
+        message: MessageLog,
+        matches: Dict[str, Counter],
+        queries: List[Tuple[str, Optional[str]]],
+        raw_members: List[int],
+        *,
+        all_messages: bool,
+        top: bool,
+    ) -> bool:
+        impacted = False
+        # If author is included in the selection (empty list is all)
+        if (
+            (not message.bot or all_messages)
+            and len(raw_members) == 0
+            or message.author in raw_members
+        ):
+            impacted = True
+            content = message.content.lower()
+            for query in queries:
+                if query[1] is not None:
+                    count = len(re.findall(query[1], message.content))
+                else:
+                    count = content.count(query[0].lower())
+                if top:
+                    if count > 0:
+                        matches[message.author].update_use(count, message.created_at)
+                else:
+                    matches[query[0]].update_use(
+                        count, message.created_at, message.author
+                    )
+        return impacted

src/scanners/first_scanner.py

@@ -0,0 +1,30 @@
+from typing import List
+
+# Custom libs
+
+from .history_scanner import HistoryScanner
+from utils import generate_help
+
+
+class FirstScanner(HistoryScanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "first",
+            "Read first message  (add text to filter like %find)",
+            args=[
+                "image/gif - pull an image instead of a message",
+                "spoiler:allow/only - allow spoiler images",
+            ],
+        )
+
+    def __init__(self):
+        super().__init__(help=FirstScanner.help())
+
+    async def get_results(self, intro: str) -> List[str]:
+        if self.images_only:
+            return await self.history.to_string_image(
+                type="first", spoiler=self.spoiler, gif_only=self.gif_only
+            )
+        else:
+            return self.history.to_string(type="first")

src/scanners/frequency_scanner.py

@@ -0,0 +1,125 @@
+from typing import List
+from datetime import datetime
+import discord
+
+
+# Custom libs
+
+from .scanner import Scanner
+from data_types import Frequency
+from logs import ChannelLogs, MessageLog
+from utils import generate_help
+
+
+class FrequencyScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "freq",
+            "(BETA) Show frequency-related statistics",
+            args=[
+                "graph - plot hours of week",
+            ],
+        )
+
+    def __init__(self):
+        super().__init__(
+            valid_args=["all", "everyone", "graph"],
+            help=FrequencyScanner.help(),
+            intro_context="Frequency",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.freq = Frequency()
+        self.all_messages = "all" in args or "everyone" in args
+        self.member_specific = len(self.members) > 0
+        self.to_graph = "graph" in args
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return FrequencyScanner.analyse_message(
+            message, self.freq, self.raw_members, all_messages=self.all_messages
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        FrequencyScanner.compute_results(self.freq)
+        if self.to_graph:
+            res = self.freq.to_graph()
+        else:
+            res = [intro]
+            res += self.freq.to_string(
+                member_specific=self.member_specific,
+            )
+        return res
+
+    @staticmethod
+    def analyse_message(
+        message: MessageLog,
+        freq: Frequency,
+        raw_members: List[int],
+        *,
+        all_messages: bool,
+    ) -> bool:
+        impacted = False
+        # If author is included in the selection (empty list is all)
+        if (
+            (not message.bot or all_messages)
+            and len(raw_members) == 0
+            or message.author in raw_members
+        ):
+            impacted = True
+            freq.dates += [message.created_at]
+            if message.author == freq.last_author:
+                freq.streaks[-1] += 1
+            else:
+                if len(freq.streaks) > 0 and (
+                    freq.longest_streak is None
+                    or freq.streaks[-1] > freq.longest_streak
+                ):
+                    freq.longest_streak = freq.streaks[-1]
+                    freq.longest_streak_start = freq.last_streak_start
+                    freq.longest_streak_author = freq.last_streak_author
+                freq.streaks += [1]
+                freq.last_streak_start = message.created_at
+                freq.last_streak_author = message.author
+        freq.last_author = message.author
+        return impacted
+
+    @staticmethod
+    def compute_results(freq: Frequency):
+        freq.dates.sort()
+        latest = freq.dates[0]
+        current_day = 0
+        current_day_date = freq.dates[0]
+        current_day_count = 0
+        current_hour_buffer = []
+        for date in freq.dates:
+            # calculate longest break
+            delay = date - latest
+            if delay > freq.longest_break:
+                freq.longest_break = delay
+                freq.longest_break_start = latest
+            latest = date
+            # calculate busiest weekday / hours
+            freq.hours[date.weekday()][date.hour] += 1
+            # calculate busiest day ever
+            start_delta = date - freq.dates[0]
+            if start_delta.days > current_day:
+                if current_day_count > freq.busiest_day_count:
+                    freq.busiest_day_count = current_day_count
+                    freq.busiest_day = current_day_date
+                current_day = start_delta.days
+                current_day_date = date
+                current_day_count = 0
+            else:
+                current_day_count += 1
+            # calculate busiest hour ever
+            while (
+                len(current_hour_buffer) > 0
+                and (date - current_hour_buffer[0]).total_seconds() > 3600
+            ):
+                current_hour_buffer.pop(0)
+            current_hour_buffer += [date]
+            if len(current_hour_buffer) > freq.busiest_hour_count:
+                freq.busiest_hour = current_hour_buffer[0]
+                freq.busiest_hour_count = len(current_hour_buffer)

src/scanners/full_scanner.py

@@ -0,0 +1,71 @@
+from typing import List
+import discord
+
+
+# Custom libs
+
+from .scanner import Scanner
+from .composition_scanner import CompositionScanner
+from .frequency_scanner import FrequencyScanner
+from .presence_scanner import PresenceScanner
+from data_types import Frequency, Composition, Presence
+from logs import ChannelLogs, MessageLog
+from utils import generate_help
+
+
+class FullScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help("scan", "Show full statistics")
+
+    def __init__(self):
+        super().__init__(
+            valid_args=["all", "everyone"],
+            help=FullScanner.help(),
+            intro_context="Full analysis",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.freq = Frequency()
+        self.compo = Composition()
+        self.pres = Presence()
+        self.member_specific = len(self.members) > 0
+        self.all_messages = "all" in args or "everyone" in args
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        FrequencyScanner.analyse_message(
+            message, self.freq, self.raw_members, all_messages=self.all_messages
+        )
+        CompositionScanner.analyse_message(
+            message, self.compo, self.raw_members, all_messages=self.all_messages
+        )
+        PresenceScanner.analyse_message(
+            channel,
+            message,
+            self.pres,
+            self.raw_members,
+            all_messages=self.all_messages,
+        )
+        return (
+            (not message.bot or self.all_messages)
+            and len(self.raw_members) == 0
+            or message.author in self.raw_members
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        FrequencyScanner.compute_results(self.freq)
+        res = [intro]
+        res += ["__Frequency__:"]
+        res += self.freq.to_string(member_specific=self.member_specific)
+        res += ["__Composition__:"]
+        res += self.compo.to_string(self.msg_count)
+        res += ["__Presence__:"]
+        res += self.pres.to_string(
+            self.msg_count,
+            self.total_msg,
+            show_top_channel=len(self.channels) > 1,
+            member_specific=self.member_specific,
+            chan_count=len(self.channels) if not self.full else None,
+        )
+        return res

src/scanners/history_scanner.py

@@ -0,0 +1,103 @@
+from abc import ABC, abstractmethod
+from typing import List, Tuple, Optional
+import discord
+import re
+
+# Custom libs
+
+from .scanner import Scanner
+from data_types import History
+from logs import ChannelLogs, MessageLog
+from utils import FilterLevel
+
+
+class HistoryScanner(Scanner, ABC):
+    def __init__(self, *, help: str):
+        super().__init__(
+            has_digit_args=True,
+            valid_args=[
+                "all",
+                "everyone",
+                "spoiler",
+                "spoiler:allow",
+                "spoiler:only",
+                "image",
+                "img",
+                "gif",
+            ],
+            help=help,
+            intro_context="",
+            all_args=True,
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.history = History()
+        self.all_messages = "all" in args or "everyone" in args
+        self.images_only = "image" in args or "img" in args or "gif" in args
+        self.gif_only = "gif" in args
+        if "spoiler" in args or "spoiler:allow" in args:
+            self.spoiler = FilterLevel.ALLOW
+        elif "spoiler:only" in args:
+            self.spoiler = FilterLevel.ONLY
+        else:
+            self.spoiler = FilterLevel.NONE
+        if not self.images_only:
+            self.queries = [
+                (
+                    query.lower(),
+                    query.strip("`") if re.match(r"^`.*`$", query) else None,
+                )
+                for query in self.other_args
+            ]
+        else:
+            self.queries = []
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return HistoryScanner.analyse_message(
+            channel,
+            message,
+            self.history,
+            self.raw_members,
+            all_messages=self.all_messages,
+            queries=self.queries,
+            images_only=self.images_only,
+        )
+
+    @abstractmethod
+    def get_results(self, intro: str):
+        pass
+
+    @staticmethod
+    def analyse_message(
+        channel: ChannelLogs,
+        message: MessageLog,
+        history: History,
+        raw_members: List[int],
+        *,
+        all_messages: bool,
+        queries: List[Tuple[str, Optional[str]]],
+        images_only: bool,
+    ) -> bool:
+        impacted = False
+        # If author is included in the selection (empty list is all)
+        if (
+            (
+                (not message.bot or all_messages)
+                and len(raw_members) == 0
+                or message.author in raw_members
+            )
+            and (message.content or message.attachment)
+            and (not images_only or message.image)
+        ):
+            if not images_only:
+                content = message.content.lower()
+                for query in queries:
+                    if query[1] is not None:
+                        if not re.match(query[1], message.content):
+                            return False
+                    elif not query[0] in content:
+                        return False
+            impacted = True
+            history.messages += [message]
+        return impacted

src/scanners/last_scanner.py

@@ -0,0 +1,30 @@
+from typing import List
+
+# Custom libs
+
+from .history_scanner import HistoryScanner
+from utils import generate_help
+
+
+class LastScanner(HistoryScanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "last",
+            "Read last message (add text to filter like %find)",
+            args=[
+                "image/gif - pull an image instead of a message",
+                "spoiler:allow/only - allow spoiler images",
+            ],
+        )
+
+    def __init__(self):
+        super().__init__(help=LastScanner.help())
+
+    async def get_results(self, intro: str) -> List[str]:
+        if self.images_only:
+            return await self.history.to_string_image(
+                type="last", spoiler=self.spoiler, gif_only=self.gif_only
+            )
+        else:
+            return self.history.to_string(type="last")

src/scanners/mentioned_scanner.py

@@ -0,0 +1,92 @@
+from typing import Dict, List
+from collections import defaultdict
+import discord
+
+
+# Custom libs
+
+from logs import ChannelLogs, MessageLog
+from .scanner import Scanner
+from data_types import Counter
+from utils import generate_help, plural, precise, mention, alt_mention
+
+
+class MentionedScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "mentioned",
+            "Rank specific user's mentions by their usage",
+            args=["<n> - top <n>, default is 10", "all/everyone - include bots"],
+            example="5 @user",
+            replace_args=[" @member/me - (required) one or more member"],
+        )
+
+    def __init__(self):
+        super().__init__(
+            has_digit_args=True,
+            valid_args=["all"],
+            help=MentionedScanner.help(),
+            intro_context="Mentioned by members",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.top = 10
+        for arg in args:
+            if arg.isdigit():
+                self.top = int(arg)
+        if len(self.members) == 0:
+            await message.channel.send(
+                "You need to mention at least one member or use `me`", reference=message
+            )
+            return False
+        self.all_mentions = "all" in args or "everyone" in args
+        # Create mentions dict
+        self.mentions = defaultdict(Counter)
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return MentionedScanner.analyse_message(
+            message, self.mentions, self.raw_members, all_mentions=self.all_mentions
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        names = [name for name in self.mentions]
+        names.sort(key=lambda name: self.mentions[name].score(), reverse=True)
+        names = names[: self.top]
+        usage_count = Counter.total(self.mentions)
+        res = [intro]
+        res += [
+            self.mentions[name].to_string(
+                names.index(name),
+                name,
+                total_usage=usage_count,
+                transform=lambda id: f" for {mention(id)}",
+                top=len(self.members) != 1,
+            )
+            for name in names
+        ]
+        res += [
+            f"Total: {plural(usage_count,'time')} ({precise(usage_count/self.msg_count)}/msg)"
+        ]
+        return res
+
+    @staticmethod
+    def analyse_message(
+        message: MessageLog,
+        mentions: Dict[str, Counter],
+        raw_members: List[int],
+        *,
+        all_mentions: bool,
+    ) -> bool:
+        impacted = True
+        if not message.bot or all_mentions:
+            for member_id in message.mentions:
+                if member_id in raw_members:
+                    count = message.content.count(
+                        mention(member_id)
+                    ) + message.content.count(alt_mention(member_id))
+                    mentions[mention(message.author)].update_use(
+                        count, message.created_at, member_id
+                    )
+        return impacted

src/scanners/mentions_scanner.py

@@ -0,0 +1,132 @@
+from typing import Dict, List
+from collections import defaultdict
+import discord
+
+
+# Custom libs
+
+from logs import ChannelLogs, MessageLog
+from .scanner import Scanner
+from data_types import Counter
+from utils import (
+    generate_help,
+    plural,
+    precise,
+    mention,
+    alt_mention,
+    role_mention,
+    channel_mention,
+)
+
+
+class MentionsScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "mentions",
+            "Rank mentions by their usage",
+            args=[
+                "<n> - top <n>, default is 10",
+                "all - show role/channel/everyone/here mentions",
+                "everyone - include bots mentions",
+            ],
+            example="10 #mychannel1 #mychannel2 @user",
+        )
+
+    def __init__(self):
+        super().__init__(
+            has_digit_args=True,
+            valid_args=["all", "everyone"],
+            help=MentionsScanner.help(),
+            intro_context="Mention usage",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.top = 10
+        for arg in args:
+            if arg.isdigit():
+                self.top = int(arg)
+        # check other args
+        self.all_mentions = "all" in args
+        # Create mentions dict
+        self.mentions = defaultdict(Counter)
+        self.all_messages = "everyone" in args
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return MentionsScanner.analyse_message(
+            message,
+            self.mentions,
+            self.raw_members,
+            all_mentions=self.all_mentions,
+            all_messages=self.all_messages,
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        names = [name for name in self.mentions]
+        names.sort(key=lambda name: self.mentions[name].score(), reverse=True)
+        names = names[: self.top]
+        usage_count = Counter.total(self.mentions)
+        res = [intro]
+        res += [
+            self.mentions[name].to_string(
+                names.index(name),
+                name,
+                total_usage=usage_count,
+                transform=lambda id: f" by {mention(id)}",
+                top=len(self.members) != 1,
+            )
+            for name in names
+        ]
+        res += [
+            f"Total: {plural(usage_count,'time')} ({precise(usage_count/self.msg_count)}/msg)"
+        ]
+        return res
+
+    @staticmethod
+    def analyse_message(
+        message: MessageLog,
+        mentions: Dict[str, Counter],
+        raw_members: List[int],
+        *,
+        all_mentions: bool,
+        all_messages: bool,
+    ) -> bool:
+        impacted = False
+        # If author is included in the selection (empty list is all)
+        if (
+            (not message.bot or all_messages)
+            and len(raw_members) == 0
+            or message.author in raw_members
+        ):
+            impacted = True
+            for member_id in message.mentions:
+                name = mention(member_id)
+                count = message.content.count(name) + message.content.count(
+                    alt_mention(member_id)
+                )
+                mentions[name].update_use(count, message.created_at, message.author)
+            if all_mentions:
+                for role_id in message.role_mentions:
+                    name = role_mention(role_id)
+                    mentions[name].update_use(
+                        message.content.count(name), message.created_at, message.author
+                    )
+                for channel_id in message.channel_mentions:
+                    name = channel_mention(channel_id)
+                    mentions[name].update_use(
+                        message.content.count(name), message.created_at, message.author
+                    )
+                if "@everyone" in message.content:
+                    mentions["@\u200beveryone"].update_use(
+                        message.content.count("@everyone"),
+                        message.created_at,
+                        message.author,
+                    )
+                if "@here" in message.content:
+                    mentions["@\u200bhere"].update_use(
+                        message.content.count("@here"),
+                        message.created_at,
+                        message.author,
+                    )
+        return impacted

src/scanners/messages_scanner.py

@@ -0,0 +1,87 @@
+from typing import Dict, List
+from collections import defaultdict
+import discord
+
+
+# Custom libs
+
+from logs import ChannelLogs, MessageLog
+from .scanner import Scanner
+from data_types import Counter
+from utils import generate_help, mention, channel_mention
+
+
+class MessagesScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "msg",
+            "Rank users by their messages",
+            args=["<n> - top <n>, default is 10", "all/everyone - include bots"],
+            example="10 #channel",
+        )
+
+    def __init__(self):
+        super().__init__(
+            has_digit_args=True,
+            valid_args=["all", "everyone"],
+            help=MessagesScanner.help(),
+            intro_context="Messages",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.top = 10
+        for arg in args:
+            if arg.isdigit():
+                self.top = int(arg)
+        self.all_messages = "all" in args or "everyone" in args
+        # Create mentions dict
+        self.messages = defaultdict(Counter)
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return MessagesScanner.analyse_message(
+            channel.id,
+            message,
+            self.messages,
+            self.raw_members,
+            all_messages=self.all_messages,
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        names = [name for name in self.messages]
+        names.sort(key=lambda name: self.messages[name].score(), reverse=True)
+        names = names[: self.top]
+        usage_count = Counter.total(self.messages)
+        res = [intro]
+        res += [
+            self.messages[name].to_string(
+                names.index(name),
+                mention(name),
+                total_usage=usage_count,
+                counted="message",
+                transform=lambda id: f" in {channel_mention(id)}",
+                top=self.channels != 1,
+            )
+            for name in names
+        ]
+        return res
+
+    @staticmethod
+    def analyse_message(
+        channel_id: int,
+        message: MessageLog,
+        messages: Dict[str, Counter],
+        raw_members: List[int],
+        *,
+        all_messages: bool,
+    ) -> bool:
+        impacted = False
+        if (
+            len(raw_members) == 0
+            and (not message.bot or all_messages)
+            or message.author in raw_members
+        ):
+            impacted = True
+            messages[message.author].update_use(1, message.created_at, channel_id)
+        return impacted

src/scanners/presence_scanner.py

@@ -0,0 +1,88 @@
+from typing import List
+import discord
+
+
+# Custom libs
+
+from .scanner import Scanner
+from data_types import Presence
+from logs import ChannelLogs, MessageLog
+from utils import generate_help
+
+
+class PresenceScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help("pres", "Show presence statistics")
+
+    def __init__(self):
+        super().__init__(
+            valid_args=["all", "everyone"],
+            help=PresenceScanner.help(),
+            intro_context="Presence",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.pres = Presence()
+        self.member_specific = len(self.members) > 0
+        self.all_messages = "all" in args or "everyone" in args
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return PresenceScanner.analyse_message(
+            channel,
+            message,
+            self.pres,
+            self.raw_members,
+            all_messages=self.all_messages,
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        res = [intro]
+        res += self.pres.to_string(
+            self.msg_count,
+            self.total_msg,
+            chan_count=len(self.channels) if not self.full else None,
+            show_top_channel=(len(self.channels) > 1),
+            member_specific=self.member_specific,
+        )
+        return res
+
+    @staticmethod
+    def analyse_message(
+        channel: ChannelLogs,
+        message: MessageLog,
+        pres: Presence,
+        raw_members: List[int],
+        *,
+        all_messages: bool,
+    ) -> bool:
+        impacted = False
+        # If author is included in the selection (empty list is all)
+        if (
+            (not message.bot or all_messages)
+            and len(raw_members) == 0
+            or message.author in raw_members
+        ):
+            impacted = True
+            pres.channel_usage[channel.id] += 1
+            for mention in message.mentions:
+                pres.mention_others[mention] += 1
+            pres.messages[message.author] += 1
+        pres.channel_total[channel.id] += 1
+        pres.mention_count[message.author] += len(message.mentions)
+        if len(raw_members) > 0:
+            for mention in message.mentions:
+                if mention in raw_members:
+                    pres.mentions[message.author] += 1
+            for reaction in message.reactions:
+                for member_id in message.reactions[reaction]:
+                    pres.used_reaction[member_id] += 1
+                    if member_id in raw_members:
+                        pres.reactions[reaction] += 1
+        else:
+            for reaction in message.reactions:
+                pres.reactions[reaction] += len(message.reactions[reaction])
+                for member_id in message.reactions[reaction]:
+                    pres.used_reaction[member_id] += 1
+        return impacted

src/scanners/random_scanner.py

@@ -0,0 +1,30 @@
+from typing import List
+
+# Custom libs
+
+from .history_scanner import HistoryScanner
+from utils import generate_help
+
+
+class RandomScanner(HistoryScanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "rand",
+            "Read a random message (add text to filter like %find)",
+            args=[
+                "image/gif - pull an image instead of a message",
+                "spoiler:allow/only - allow spoiler images",
+            ],
+        )
+
+    def __init__(self):
+        super().__init__(help=RandomScanner.help())
+
+    async def get_results(self, intro: str) -> List[str]:
+        if self.images_only:
+            return await self.history.to_string_image(
+                type="random", spoiler=self.spoiler, gif_only=self.gif_only
+            )
+        else:
+            return self.history.to_string(type="random")

src/scanners/reactions_scanner.py

@@ -0,0 +1,79 @@
+from typing import Dict, List
+from collections import defaultdict
+import discord
+
+
+# Custom libs
+
+from logs import ChannelLogs, MessageLog
+from .scanner import Scanner
+from data_types import Counter
+from utils import generate_help, mention, channel_mention
+
+
+class ReactionsScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "react",
+            "Rank users by their reactions",
+            args=["<n> - top <n>, default is 10"],
+            example="10 #channel",
+        )
+
+    def __init__(self):
+        super().__init__(
+            has_digit_args=True,
+            help=ReactionsScanner.help(),
+            intro_context="Reactions",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.top = 10
+        for arg in args:
+            if arg.isdigit():
+                self.top = int(arg)
+        # Create mentions dict
+        self.messages = defaultdict(Counter)
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return ReactionsScanner.analyse_message(
+            channel.id,
+            message,
+            self.messages,
+            self.raw_members,
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        names = [name for name in self.messages]
+        names.sort(key=lambda name: self.messages[name].score(), reverse=True)
+        names = names[: self.top]
+        usage_count = Counter.total(self.messages)
+        res = [intro]
+        res += [
+            self.messages[name].to_string(
+                names.index(name),
+                mention(name),
+                total_usage=usage_count,
+                counted="reaction",
+                transform=lambda id: f" in {channel_mention(id)}",
+                top=self.channels != 1,
+            )
+            for name in names
+        ]
+        return res
+
+    @staticmethod
+    def analyse_message(
+        channel_id: int,
+        message: MessageLog,
+        messages: Dict[str, Counter],
+        raw_members: List[int],
+    ) -> bool:
+        impacted = True
+        for reaction in message.reactions:
+            for member_id in message.reactions[reaction]:
+                if len(raw_members) == 0 or member_id in raw_members:
+                    messages[member_id].update_use(1, message.created_at, channel_id)
+        return impacted

src/scanners/scanner.py

@@ -0,0 +1,347 @@
+from abc import ABC, abstractmethod
+from typing import List
+from datetime import datetime
+import logging
+import re
+import discord
+import inspect
+
+
+from utils import (
+    no_duplicate,
+    get_intro,
+    delta,
+    gdpr,
+    ISO8601_REGEX,
+    RELATIVE_REGEX,
+    parse_time,
+    command_cache,
+    FilterLevel,
+    SPLIT_TOKEN,
+)
+from logs import (
+    GuildLogs,
+    ChannelLogs,
+    MessageLog,
+    ALREADY_RUNNING,
+    CANCELLED,
+    NO_FILE,
+)
+
+
+class Scanner(ABC):
+    VALID_ARGS = [
+        "me",
+        "here",
+        "fast",
+        "fresh",
+        "mobile",
+        "mention",
+        "nsfw",
+        "nsfw:allow",
+        "nsfw:only",
+    ]
+
+    def __init__(
+        self,
+        *,
+        has_digit_args: bool = False,
+        valid_args: List[str] = [],
+        help: str,
+        intro_context: str,
+        all_args: bool = False,
+    ):
+        self.has_digit_args = has_digit_args
+        self.valid_args = valid_args
+        self.all_args = all_args
+        self.help = help
+        self.intro_context = intro_context
+
+        self.other_args = []
+
+        self.members = []
+        self.raw_members = []
+        self.full = False
+        self.channels = []
+
+        self.msg_count = 0
+        self.chan_count = 0
+
+    async def compute(
+        self,
+        client: discord.client,
+        message: discord.Message,
+        *args: str,
+        other_mentions: List[str] = [],
+    ):
+        args = list(args)
+        guild = message.guild
+        progress = None
+        try:
+            with GuildLogs(guild) as logs:
+                # If "%cmd help" redirect to "%help cmd"
+                if len(args) > 1 and args[1] == "help":
+                    await client.bot.help(client, message, "help", args[0])
+                    return
+
+                # check args validity
+                str_channel_mentions = [
+                    str(channel.id) for channel in message.channel_mentions
+                ]
+                str_mentions = [str(member.id) for member in message.mentions]
+                dates = []
+                for i, arg in enumerate(args[1:]):
+                    skip_check = False
+                    if self.all_args and (
+                        f"'{arg}'" in message.content or f'"{arg}"' in message.content
+                    ):
+                        self.other_args += [arg]
+                    elif re.match(r"^<@!?\d+>$", arg):
+                        arg = arg[3:-1] if "!" in arg else arg[2:-1]
+                    elif re.match(r"^<#!?\d+>$", arg):
+                        arg = arg[3:-1] if "!" in arg else arg[2:-1]
+                    elif re.match(ISO8601_REGEX, arg) or re.match(RELATIVE_REGEX, arg):
+                        dates += [parse_time(arg)]
+                        skip_check = True
+                        if len(dates) > 2:
+                            await message.channel.send(
+                                f"Too many date arguments: `{arg}`", reference=message
+                            )
+                            return
+                    if (
+                        arg not in self.valid_args + Scanner.VALID_ARGS
+                        and (not arg.isdigit() or not self.has_digit_args)
+                        and arg not in str_channel_mentions
+                        and arg not in str_mentions
+                        and arg not in other_mentions
+                        and not skip_check
+                        and len(arg) > 0
+                    ):
+                        if self.all_args:
+                            self.other_args += [arg]
+                        else:
+                            await message.channel.send(
+                                f"Unrecognized argument: `{arg}`", reference=message
+                            )
+                            return
+
+                for arg in self.other_args:
+                    args.remove(arg)
+
+                self.start_date = None if len(dates) < 1 else min(dates)
+                self.stop_date = None if len(dates) < 2 else max(dates)
+
+                if self.start_date is not None and self.start_date > datetime.now():
+                    await message.channel.send(
+                        f"Start date is after today", reference=message
+                    )
+                    return
+
+                # Get selected channels or all of them if no channel arguments
+                self.channels = no_duplicate(message.channel_mentions)
+
+                # transform the "here" arg
+                if "here" in args:
+                    self.channels += [message.channel]
+
+                self.full = len(self.channels) == 0
+                if self.full:
+                    self.channels = guild.text_channels
+
+                # Get selected members
+                self.members = no_duplicate(message.mentions)
+                self.raw_members = no_duplicate(message.raw_mentions)
+
+                # transform the "me" arg
+                if "me" in args:
+                    self.members += [message.author]
+                    self.raw_members += [message.author.id]
+
+                self.mention_users = "mention" in args or "mobile" in args
+
+                # nsfw filter
+                if "nsfw" in args or "nsfw:allow" in args:
+                    self.nsfw = FilterLevel.ALLOW
+                elif "nsfw:only" in args:
+                    self.nsfw = FilterLevel.ONLY
+                else:
+                    self.nsfw = FilterLevel.NONE
+
+                # fix nsfw filter if channel specified
+                if not self.full and any(channel.nsfw for channel in self.channels):
+                    self.nsfw = FilterLevel.ALLOW
+                elif all(channel.nsfw for channel in self.channels):
+                    self.nsfw = FilterLevel.ONLY
+
+                # filter nsfw channels
+                if self.nsfw == FilterLevel.NONE:
+                    self.channels = list(
+                        filter(lambda channel: not channel.nsfw, self.channels)
+                    )
+                elif self.nsfw == FilterLevel.ONLY:
+                    self.channels = list(
+                        filter(lambda channel: channel.nsfw, self.channels)
+                    )
+
+                if not await self.init(message, *args):
+                    return
+
+                # Start computing data
+                async with message.channel.typing():
+                    progress = await message.channel.send(
+                        "```Starting analysis...```",
+                        reference=message,
+                        allowed_mentions=discord.AllowedMentions.none(),
+                    )
+                    total_msg, total_chan = await logs.load(
+                        progress,
+                        self.channels,
+                        self.start_date,
+                        self.stop_date,
+                        fast="fast" in args,
+                        fresh="fresh" in args,
+                    )
+                    if total_msg == CANCELLED:
+                        await message.channel.send(
+                            "Operation cancelled by user",
+                            reference=message,
+                        )
+                    elif total_msg == ALREADY_RUNNING:
+                        await message.channel.send(
+                            "An analysis is already running on this server, please be patient.",
+                            reference=message,
+                        )
+                    elif total_msg == NO_FILE:
+                        await message.channel.send(gdpr.TEXT)
+                    else:
+                        if self.start_date is not None and len(logs.channels) > 0:
+                            self.start_date = max(
+                                self.start_date,
+                                min(
+                                    [
+                                        logs.channels[channel.id].start_date
+                                        for channel in self.channels
+                                        if channel.id in logs.channels
+                                        and logs.channels[channel.id].start_date
+                                        is not None
+                                    ]
+                                ),
+                            )
+                            if self.stop_date is None:
+                                self.stop_date = datetime.utcnow()
+
+                        self.msg_count = 0
+                        self.total_msg = 0
+                        self.chan_count = 0
+                        t0 = datetime.now()
+                        for channel in self.channels:
+                            if channel.id in logs.channels:
+                                channel_logs = logs.channels[channel.id]
+                                count = sum(
+                                    [
+                                        self.compute_message(channel_logs, message_log)
+                                        for message_log in channel_logs.messages
+                                        if (
+                                            self.start_date is None
+                                            or message_log.created_at >= self.start_date
+                                        )
+                                        and (
+                                            self.stop_date is None
+                                            or message_log.created_at <= self.stop_date
+                                        )
+                                    ]
+                                )
+                                self.total_msg += len(channel_logs.messages)
+                                self.msg_count += count
+                                self.chan_count += 1 if count > 0 else 0
+                        logging.info(f"scan {guild.id} > scanned in {delta(t0):,}ms")
+                        if self.msg_count == 0:
+                            await message.channel.send(
+                                "There are no messages found matching the filters",
+                                reference=message,
+                            )
+                        else:
+                            await progress.edit(content="```Computing results...```")
+                            # Display results
+                            t0 = datetime.now()
+                            intro = get_intro(
+                                self.intro_context,
+                                self.full,
+                                self.channels,
+                                self.members,
+                                self.msg_count,
+                                self.chan_count,
+                                self.start_date,
+                                self.stop_date,
+                            )
+                            if inspect.iscoroutinefunction(self.get_results):
+                                results = await self.get_results(intro)
+                            else:
+                                results = self.get_results(intro)
+                            logging.info(
+                                f"scan {guild.id} > results in {delta(t0):,}ms"
+                            )
+                            response = ""
+                            first = True
+                            allowed_mentions = (
+                                discord.AllowedMentions.all()
+                                if self.mention_users
+                                else discord.AllowedMentions.none()
+                            )
+                            file = None
+                            for r in results:
+                                if r:
+                                    if isinstance(r, discord.File):
+                                        file = r
+                                    elif isinstance(r, int) and r == SPLIT_TOKEN:
+                                        await message.channel.send(
+                                            response,
+                                            reference=message if first else None,
+                                            allowed_mentions=allowed_mentions,
+                                            file=file,
+                                        )
+                                        first = False
+                                        file = None
+                                        response = ""
+                                    elif isinstance(r, str):
+                                        if len(response + "\n" + r) > 2000:
+                                            await message.channel.send(
+                                                response,
+                                                reference=message if first else None,
+                                                allowed_mentions=allowed_mentions,
+                                                file=file,
+                                            )
+                                            first = False
+                                            file = None
+                                            response = ""
+                                        response += "\n" + r
+                            if len(response) > 0 or file is not None:
+                                await message.channel.send(
+                                    response,
+                                    reference=message if first else None,
+                                    allowed_mentions=allowed_mentions,
+                                    file=file,
+                                )
+                            command_cache.cache(self, message, args)
+                # Delete custom progress message
+                await progress.delete()
+        except Exception as error:
+            logging.exception(error)
+            await message.channel.send(
+                "An unexpected error happened while computing your command, we're sorry for the inconvenience.",
+                reference=message,
+            )
+            if progress is not None:
+                await progress.delete()
+
+    @abstractmethod
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        pass
+
+    @abstractmethod
+    def compute_message(self, channel: ChannelLogs, message: MessageLog) -> bool:
+        pass
+
+    @abstractmethod
+    def get_results(self, intro: str) -> List[str]:
+        pass

src/scanners/words_scanner.py

@@ -0,0 +1,122 @@
+from typing import Dict, List
+from collections import defaultdict
+import discord
+import re
+
+# Custom libs
+
+from logs import ChannelLogs, MessageLog
+from .scanner import Scanner
+from data_types import Counter
+from utils import generate_help, plural, precise, mention
+
+
+class WordsScanner(Scanner):
+    @staticmethod
+    def help() -> str:
+        return generate_help(
+            "words",
+            "(BETA) Rank words by their usage",
+            args=[
+                "<n> - words containings <n> or more letters, default is 3",
+                "<n2> - top <n2> words, default is 10",
+                "all/everyone - include bots",
+            ],
+            example="5 10 #mychannel1 #mychannel2 @user",
+        )
+
+    def __init__(self):
+        super().__init__(
+            has_digit_args=True,
+            valid_args=["all", "everyone"],
+            help=WordsScanner.help(),
+            intro_context="Words ({}+ letters)",
+        )
+
+    async def init(self, message: discord.Message, *args: str) -> bool:
+        self.letters = None
+        self.top = None
+        for arg in args:
+            if arg.isdigit():
+                if self.letters is None:
+                    self.letters = int(arg)
+                elif self.top is None:
+                    self.top = int(arg)
+        if self.letters is None:
+            self.letters = 3
+        if self.top is None:
+            self.top = 10
+        self.words = defaultdict(Counter)
+        self.all_messages = "all" in args or "everyone" in args
+        return True
+
+    def compute_message(self, channel: ChannelLogs, message: MessageLog):
+        return WordsScanner.analyse_message(
+            message,
+            self.words,
+            self.raw_members,
+            all_messages=self.all_messages,
+            letters_threshold=self.letters,
+        )
+
+    def get_results(self, intro: str) -> List[str]:
+        words = [word for word in self.words]
+        words.sort(key=lambda word: self.words[word].score(), reverse=True)
+        words = words[: self.top]
+        usage_count = Counter.total(self.words)
+        res = [intro.format(self.letters)]
+        res += [
+            self.words[word].to_string(
+                words.index(word),
+                f"`{word}`",
+                total_usage=usage_count,
+                transform=lambda id: f" by {mention(id)}",
+                top=len(self.members) != 1,
+            )
+            for word in words
+        ]
+        res += [
+            f"Total: {plural(usage_count,'time')} ({precise(usage_count/self.msg_count)}/msg)"
+        ]
+        return res
+
+    special_cases = ["'s", "s"]
+
+    @staticmethod
+    def analyse_message(
+        message: MessageLog,
+        words: Dict[str, Counter],
+        raw_members: List[int],
+        *,
+        all_messages: bool,
+        letters_threshold: int,
+    ) -> bool:
+        impacted = False
+        # If author is included in the selection (empty list is all)
+        if (
+            (not message.bot or all_messages)
+            and len(raw_members) == 0
+            or message.author in raw_members
+        ):
+            impacted = True
+            content = message.content
+            content = re.sub(r"```.+```", "", content, flags=re.DOTALL)
+            content = re.sub(r"`.+`", "", content, flags=re.DOTALL)
+            content = re.sub(r"\w+:\/\/[^ ]+", "", content)
+            for word in re.split("[^\w\-':]", content):
+                m = re.match(
+                    r"(?!^:\w+:$)^[^\w]*((?![\d_])\w[\w\-']*(?![\d_])\w)[^\w]*$", word
+                )
+                if m:
+                    word = m[1].lower()
+                    if len(word) >= letters_threshold:
+                        for case in WordsScanner.special_cases:
+                            if word.endswith(case) and word[: -len(case)] in words:
+                                word = word[: -len(case)]
+                                break
+                            if word + case in words:
+                                words[word] = words[word + case]
+                                del words[word + case]
+                                break
+                        words[word].update_use(1, message.created_at, message.author)
+        return impacted

src/utils/__init__.py

@@ -0,0 +1 @@
+from .utils import *

src/utils/command_cache.py

@@ -0,0 +1,45 @@
+from typing import List
+import logging
+import discord
+
+from scanners import Scanner
+
+command_cache = {}
+
+
+def cache(scanner: Scanner, message: discord.Message, args: List[str]):
+    id = message.channel.id
+    command_cache[id] = (
+        type(scanner),
+        list(args),
+        [str(channel.id) for channel in message.channel_mentions]
+        + [str(member.id) for member in message.mentions],
+    )
+
+
+async def repeat(
+    client: discord.client,
+    message: discord.Message,
+    *args: str,
+    add_args: List[str] = [],
+):
+    if len(args) > 1 and args[1] == "help":
+        await client.bot.help(client, message, "help", args[0])
+        return
+    id = message.channel.id
+    if id not in command_cache:
+        await message.channel.send(
+            "No command to repeat on this channel (type %help for more info)",
+            reference=message,
+        )
+        return
+    (
+        scannerType,
+        original_args,
+        original_mentions,
+    ) = command_cache[id]
+    args = original_args + add_args + list(args[1:]) + ["fast"]
+    logging.info(f"repeating {args}")
+    await scannerType().compute(
+        client, message, *args, other_mentions=original_mentions
+    )

src/utils/emojis.py

@@ -0,0 +1,88 @@
+import re
+import json
+import logging
+
+from . import get_resource_path
+
+EXTRA_EMOJI = {
+    "thumbup": "1f44d",
+    "thumbdown": "1f44e",
+    "timer": "23f2-fe0f",
+    "cowboy": "1f920",
+    "clown": "1f921",
+    "newspaper2": "1f5de-fe0f",
+    "french_bread": "1f956",
+    "nerd": "1f913",
+    "zipper_mouth": "1f910",
+    "salad": "1f957",
+    "rolling_eyes": "1f644",
+    "basketball_player": "26f9-fe0f-200d-2642-fe0f",
+    "thinking": "1f914",
+    "e_mail": "2709-fe0f",
+    "slight_frown": "1f641",
+    "skull_crossbones": "2620-fe0f",
+    "hand_splayed": "1f590-fe0f",
+    "speaking_head": "1f5e3-fe0f",
+    "cross": "271d-fe0f",
+    "crayon": "1f58d-fe0f",
+    "head_bandage": "1f915",
+    "rofl": "1f923",
+    "flag_white": "1f3f3-fe0f",
+    "slight_smile": "1f642",
+    "fork_knife_plate": "1f37d-fe0f",
+    "robot": "1f916",
+    "hugging": "1f917",
+    "biohazard": "2623-fe0f",
+    "notepad_spiral": "1f5d2-fe0f",
+    "lifter": "1f3cb-fe0f-200d-2642-fe0f",
+    "race_car": "1f3ce-fe0f",
+    "left_facing_fist": "1f91b",
+    "right_facing_fist": "1f91c",
+    "tools": "1f6e0-fe0f",
+    "umbrella2": "2602-fe0f",
+    "upside_down": "2b07-fe0f",
+    "first_place": "1f947",
+    "dagger": "1f5e1-fe0f",
+    "fox": "1f98a",
+    "menorah": "1f54e",
+    "desktop": "1f5a5-fe0f",
+    "motorcycle": "1f3cd-fe0f",
+    "levitate": "1f574-fe0f",
+    "cheese": "1f9c0",
+    "fingers_crossed": "1f91e",
+    "frowning2": "1f626",
+    "microphone2": "1f399-fe0f",
+    "flag_black": "1f3f4",
+    "chair": "1FA91",
+    "champagne_glass": "1F942",
+    "raised_hand": "270B",
+    "knife": "1F52A",
+    "postal_horn": "1F4EF",
+    "punch": "1F44A",
+}
+
+global_list = {}
+unicode_list = []
+regex = re.compile("(<a?:[\\w\\-\\~]+:\\d+>|:[\\w\\-\\~]+:)")
+
+
+def load_emojis():
+    global global_list, unicode_list, regex
+    emoji_list = []
+    with open(get_resource_path("emoji.json"), mode="r") as f:
+        emoji_list = json.loads(f.readline().strip())
+    for emoji in EXTRA_EMOJI:
+        emoji_list += [{"short_name": emoji, "unified": EXTRA_EMOJI[emoji]}]
+    unicode_list_escaped = []
+    for emoji in emoji_list:
+        shortname = emoji["short_name"]
+        unified = emoji["unified"]
+        if unified is not None and shortname is not None:
+            unicode_escaped = "".join([f"\\U{c:0>8}" for c in unified.split("-")])
+            unicode = bytes(unicode_escaped, "ascii").decode("unicode-escape")
+            shortcode = shortname.replace("-", "_")
+            global_list[unicode] = f":{shortcode}:"
+            unicode_list += [unicode]
+            unicode_list_escaped += [unicode_escaped]
+    regex = re.compile(f"(<a?:\\w+:\\d+>|:\\w+:|{'|'.join(unicode_list_escaped)})")
+    logging.info(f"loaded {len(unicode_list)} emojis")

src/utils/gdpr.py

@@ -0,0 +1,65 @@
+import discord
+
+from logs import GuildLogs
+
+
+HELP = """```
+%gdpr: Displays GDPR information
+arguments:
+* agree - agree to GDPR
+* revoke - remove this server's data
+```"""
+
+TEXT = """
+__**About Analyst-bot's data usage**__
+**TL;DR**
+Analyst-bot collects text message information. It does not share collected data with any third-party and data is retained 18 months or until the bot is leaving the guild/server.
+**Data collection**
+Analyst-bot collects a Discord guild/server's history when asked to.
+This includes:
+- Visible text channel names
+- Visible text messages: date and time of creation and edition,  author,  content,  reactions and other available metadata (pinned, tts, etc.)
+This does __not__ includes:
+- Voice channels and not visible channels
+- Not visible text messages
+- Visible text messages' embedded content, images and other attachments
+**Data processing**
+Any data collected is only processed in order to produce a one-time report sent to the user immediately. No temporary data are retained.
+**Data storage and retain policy**
+Analyst-bot stores the collected data in files that are accessible by the software and its administrator only.
+Any collected data are retained maximum 18 months until deletion or when the bot is leaving a guild/server.
+**Data sharing**
+Analyst-bot does not share the data collected with any third-party.
+**Right to retract**
+If you want to have your data removed, you can use the `%gdpr revoke` command or remove this bot from your guild/server.
+**Terms agreement**
+By agreeing to these terms, you ensure having the legal age if you are in a country that does have one and you also ensure having the consent of every member involved.
+
+*If you want more information, please contact the creator of this bot: <https://github.com/Klemek/discord-analyst>.*
+
+Type `%gdpr agree` to agree to these terms, `%gdpr revoke` to remove this guild/server's collected data or `%gdpr` to see this message again.
+"""
+
+AGREE_TEXT = "Thanks for agreeing for these terms, you can now run analysis on this guild/server."
+
+REVOKE_TEXT = "This guild/server's data has been deleted. To run new analysis you must agree to the terms again."
+
+
+async def process(client: discord.client, message: discord.Message, *args: str):
+    args = list(args)
+    if len(args) == 1:
+        await message.channel.send(TEXT)
+    elif args[1] == "help":
+        await client.bot.help(client, message, "help", args[0])
+    elif len(args) > 2:
+        await message.channel.send(f"Too many arguments", reference=message)
+    elif args[1] in ["agree", "accept"]:
+        GuildLogs.init_log(message.channel.guild)
+        await message.channel.send(AGREE_TEXT, reference=message)
+    elif args[1] in ["revoke", "cancel", "remove", "delete"]:
+        GuildLogs.remove_log(message.channel.guild)
+        await message.channel.send(REVOKE_TEXT, reference=message)
+    else:
+        await message.channel.send(
+            f"Unrecognized argument: `{args[1]}`", reference=message
+        )

src/utils/utils.py

@@ -0,0 +1,383 @@
+from enum import IntEnum
+from typing import Callable, List, Dict, Union, Optional, Any
+import os
+import logging
+import discord
+import math
+from datetime import datetime, timedelta
+import re
+import time
+import dateutil.parser
+from dateutil.relativedelta import relativedelta
+
+# OTHER
+
+COMMON_HELP_ARGS = [
+    "@member/me - filter for one or more member",
+    "#channel/here - filter for one or more channel",
+    "<date1> - filter after <date1>",
+    "<date2> - filter before <date2>",
+    "fast - only read cache",
+    "fresh - does not read cache (long)",
+    "nsfw:allow/only - allow messages from nsfw channels",
+    "mobile/mention - mentions users (fix @invalid-user bug)",
+]
+
+
+def generate_help(
+    cmd: str,
+    info: str,
+    *,
+    args=["all/everyone - include bots"],
+    example="#mychannel1 @user",
+    replace_args=[],
+):
+    arg_list = "* " + "\n* ".join(
+        args + replace_args + COMMON_HELP_ARGS[len(replace_args) :]
+    )
+    return f"""```
+%{cmd}: {info}
+arguments:
+{arg_list}
+(Sample dates: 2020 / 2021-11 / 2021-06-28 / 2020-06-28T23:00 / today / week / 8days / 1y)
+Example: %{cmd} {example}
+```"""
+
+
+def delta(t0: datetime):
+    return round((datetime.now() - t0).total_seconds() * 1000)
+
+
+def deltas(t0: datetime):
+    return (datetime.now() - t0).total_seconds()
+
+
+class FilterLevel(IntEnum):
+    NONE = 0
+    ALLOW = 1
+    ONLY = 2
+
+
+SPLIT_TOKEN = 1152317803
+
+
+# FILE
+
+IMAGE_FORMAT = [".png", ".jpg", ".jpeg", ".bmp"]
+EMBED_IMAGES = ["image"]
+
+GIF_FORMAT = [".gif", ".gifv"]
+EMBED_GIF = ["gifv"]
+
+
+def is_extension(filepath: str, ext_list: List[str]) -> bool:
+    filename, file_extension = os.path.splitext(filepath.lower())
+    return file_extension in ext_list
+
+
+def get_resource_path(filename: str) -> str:
+    return os.path.realpath(
+        os.path.join(os.path.dirname(__file__), "..", "resources", filename)
+    )
+
+
+# DISCORD API
+
+
+def debug(message: discord.Message, txt: str):
+    logging.info(f"{message.guild} > #{message.channel}: {txt}")
+
+
+async def code_message(message: discord.Message, content: str):
+    await message.edit(content=f"```\n{content}\n```")
+
+
+def mention(member_id: int) -> str:
+    return f"<@{member_id}>"
+
+
+def alt_mention(member_id: int) -> str:
+    return f"<@!{member_id}>"
+
+
+def role_mention(role_id: int) -> str:
+    return f"<@&{role_id}>"
+
+
+def channel_mention(channel_id: int) -> str:
+    return f"<#{channel_id}>"
+
+
+def message_link(message: discord.Message) -> str:
+    return f"https://discord.com/channels/{message.channel.guild.id}/{message.channel.id}/{message.id}"
+
+
+def escape_text(text: str) -> str:
+    return discord.utils.escape_markdown(discord.utils.escape_mentions(text))
+
+
+class FakeMessage:
+    def __init__(self, id: int):
+        self.id = id
+
+
+def has_image(message: discord.Message) -> bool:
+    for attachment in message.attachments:
+        if is_extension(attachment.filename, GIF_FORMAT + IMAGE_FORMAT):
+            return True
+    for embed in message.embeds:
+        if embed.type in (EMBED_IMAGES + EMBED_GIF):
+            return True
+    return False
+
+
+def is_image_spoiler(message: discord.Message) -> bool:
+    if len(message.attachments) > 0:
+        return message.attachments[0].is_spoiler()
+    elif len(message.embeds) > 0:
+        return re.match(r"\|\|[^|]*http[^|]\|\|", message.content.lower()) is not None
+    else:
+        return False
+
+
+def is_image_gif(message: discord.Message) -> bool:
+    if len(message.attachments) > 0:
+        return is_extension(message.attachments[0].filename, GIF_FORMAT)
+    elif len(message.embeds) > 0:
+        return message.embeds[0].type in EMBED_GIF
+    else:
+        return False
+
+
+def should_allow_spoiler(message: discord.Message, spoiler: FilterLevel) -> bool:
+    is_spoiler = is_image_spoiler(message)
+    return (
+        not is_spoiler
+        and spoiler <= FilterLevel.ONLY
+        or is_spoiler
+        and spoiler >= FilterLevel.ALLOW
+    )
+
+
+# LISTS
+
+
+def no_duplicate(seq: list) -> list:
+    """
+    Remove any duplicates on a list
+
+    :param seq: original list
+    :type seq: list
+    :return: same list with no duplicates
+    :rtype: list
+    """
+    return list(dict.fromkeys(seq))
+
+
+# DICTS
+
+
+def top_key(
+    d: Dict[Union[str, int], int], key: Optional[Callable] = None, reverse: bool = False
+) -> Union[str, int]:
+    if len(d) == 0:
+        return None
+    if key is None:
+        key = lambda k: d[k]
+    return sorted(d, key=key, reverse=reverse)[-1]
+
+
+def val_sum(d: Dict[Any, int]) -> int:
+    if len(d) == 0:
+        return 0
+    return sum(d.values())
+
+
+def serialize(
+    obj: Any, *, not_serialized: List[str] = [], dates: List[str] = []
+) -> Dict:
+    output = dict(obj.__dict__)
+    for key in not_serialized:
+        output.pop(key, None)
+    for key in dates:
+        if output[key]:
+            try:
+                output[key] = getattr(obj, key).isoformat()
+            except AttributeError:
+                pass
+    return output
+
+
+# MESSAGE FORMATTING
+
+
+def aggregate(names: List[str]) -> str:
+    """
+    Aggregate names with , and &
+
+    Example : "a, b, c & d"
+    """
+    if len(names) == 0:
+        return ""
+    elif len(names) == 1:
+        return names[0]
+    else:
+        return ", ".join(names[:-1]) + " & " + names[-1]
+
+
+def plural(count: int, word: str) -> str:
+    return f"{count:,} {word}{'s' if count != 1 else ''}"
+
+
+def percent(p: float) -> str:
+    return f"{precise(100*p)}%"
+
+
+def precise(p: float, *, precision: int = 2) -> str:
+    if p == 0:
+        return "0"
+    precision = abs(min(0, math.ceil(math.log10(p)) - precision))
+    s = "{:." + str(precision) + "f}"
+    return s.format(p)
+
+
+# DATE FORMATTING
+
+ISO8601_REGEX = r"^([\+-]?\d{4}(?!\d{2}\b))((-?)((0[1-9]|1[0-2])(\3([12]\d|0[1-9]|3[01]))?|W([0-4]\d|5[0-2])(-?[1-7])?|(00[1-9]|0[1-9]\d|[12]\d{2}|3([0-5]\d|6[1-6])))([T\s]((([01]\d|2[0-3])((:?)[0-5]\d)?|24\:?00)([\.,]\d+(?!:))?)?(\17[0-5]\d([\.,]\d+)?)?([zZ]|([\+-])([01]\d|2[0-3]):?([0-5]\d)?)?)?)?$"
+ISO8601_FULL = "0000-01-01T00:00:00"
+
+
+def parse_iso_datetime(str_date: str) -> datetime:
+    if re.match(
+        "^\d{4}(-\d{2}(-\d{2}(T\d{2}(:\d{2}(:\d{2}(:\d{2})?)?)?)?)?)?$", str_date
+    ):
+        str_date = str_date + "0000-01-01T00:00:00"[len(str_date) :]
+    return dateutil.parser.parse(str_date)
+
+
+RELATIVE_REGEX = r"(yesterday|today|\d*hours?|\d+h(ours?)?|\d*days?|\d+d(ays?)?|\d*weeks?|\d+w(eeks?)?|\d*months?|\d+m(onths?)?|\d*years?|\d+y(ears?)?)"
+
+
+def parse_relative_time(src: str) -> datetime:
+    today = datetime.utcnow().date()
+    today = datetime(today.year, today.month, today.day)
+    if src == "today":
+        return today
+    elif src == "yesterday":
+        return today - relativedelta(days=1)
+    else:
+        m = re.match("(\d*)(\w+)", src)
+        delta = None
+        value = int(m[1]) if m[1] else 1
+        unit = m[2][0]
+        if unit == "h":
+            delta = relativedelta(hours=value)
+        elif unit == "d":
+            delta = relativedelta(days=value)
+        elif unit == "w":
+            delta = relativedelta(weeks=value)
+        elif unit == "m":
+            delta = relativedelta(months=value)
+        elif unit == "y":
+            delta = relativedelta(years=value)
+        return datetime.utcnow() - delta
+
+
+def parse_time(src: str) -> datetime:
+    if re.match(RELATIVE_REGEX, src):
+        return parse_relative_time(src)
+    else:
+        return parse_iso_datetime(src)
+
+
+def str_date(date: datetime) -> str:
+    return f"<t:{int(time.mktime(date.timetuple()))}:D>"
+
+
+def str_datetime(date: datetime) -> str:
+    return f"<t:{int(time.mktime(date.timetuple()))}:f>"
+
+
+def str_delta(delay: timedelta) -> str:
+    seconds = delay.seconds
+    minutes = seconds // 60
+    hours = minutes // 60
+    if delay.days < 1:
+        if hours < 1:
+            if minutes == 0:
+                return "no time"
+            elif minutes == 1:
+                return "a minute"
+            else:
+                return f"{minutes} minutes"
+        elif hours == 1:
+            return "an hour"
+        else:
+            return f"{hours} hours"
+    elif delay.days == 1:
+        return "one day"
+    else:
+        return f"{delay.days:,} days"
+
+
+def from_now(src: Optional[datetime]) -> str:
+    if src is None:
+        return "never"
+    return f"<t:{int(time.mktime(src.timetuple()))}:R>"
+
+
+# APP SPECIFIC
+
+
+def get_intro(
+    subject: str,
+    full: bool,
+    channels: List[discord.TextChannel],
+    members: List[discord.Member],
+    nmm: int,  # number of messages impacted
+    nc: int,  # number of impacted channels
+    start_datetime: datetime,
+    stop_datetime: datetime,
+) -> str:
+    """
+    Get the introduction sentence of the response
+    """
+    time_text = ""
+    if start_datetime is not None:
+        stop_datetime = datetime.now() if stop_datetime is None else stop_datetime
+        time_text = f" (in {str_delta(stop_datetime - start_datetime)})"
+    # Show all data (members, channels) when it's less than 5 units
+    if len(members) == 0:
+        # Full scan of the server
+        if full:
+            return f"{subject} in this server ({nc} channels, {nmm:,} messages){time_text}:"
+        elif len(channels) < 5:
+            return f"{aggregate([c.mention for c in channels])} {subject.lower()} in {nmm:,} messages{time_text}:"
+        else:
+            return f"These {len(channels)} channels {subject.lower()} in {nmm:,} messages{time_text}:"
+    elif len(members) < 5:
+        if full:
+            return f"{aggregate([m.mention for m in members])} {subject.lower()} in {nmm:,} messages{time_text}:"
+        elif len(channels) < 5:
+            return (
+                f"{aggregate([m.mention for m in members])} on {aggregate([c.mention for c in channels])} "
+                f"{subject.lower()} in {nmm:,} messages{time_text}:"
+            )
+        else:
+            return (
+                f"{aggregate([m.mention for m in members])} on these {len(channels)} channels "
+                f"{subject.lower()} in {nmm:,} messages{time_text}:"
+            )
+    else:
+        if full:
+            return f"These {len(members)} members {subject.lower()} in {nmm:,} messages{time_text}:"
+        elif len(channels) < 5:
+            return (
+                f"These {len(members)} members on {aggregate([c.mention for c in channels])} "
+                f"{subject.lower()} in {nmm:,} messages{time_text}:"
+            )
+        else:
+            return (
+                f"These {len(members)} members on these {len(channels)} channels "
+                f"{subject.lower()} in {nmm:,} messages{time_text}:"
+            )

test-requirements.txt

@@ -0,0 +1,3 @@
+pytest~=6.2.3
+pytest-cov
+coveralls

tests/integration/scanners/test_first_scanner.py

@@ -0,0 +1,90 @@
+from unittest import TestCase
+from unittest.mock import MagicMock
+from src.scanners import FirstScanner
+from datetime import datetime, timedelta
+
+from tests.utils import AsyncTestCase, fake_message
+
+
+class TestFirstScanner(AsyncTestCase):
+    def test_help(self):
+        self.assertGreater(len(FirstScanner.help()), 0)
+        self.assertIn("%first", FirstScanner.help())
+
+    def test_empty_no_messages(self):
+        scanner = FirstScanner()
+
+        command_msg = MagicMock()
+        self._await(scanner.init(command_msg, []))
+
+        results = self._await(scanner.get_results(""))
+        self.assertListEqual(["There was no messages matching your filters"], results)
+
+    def test_empty_filtered(self):
+        scanner = FirstScanner()
+        scanner.raw_members = [1]
+
+        self._await(scanner.init(fake_message(), []))
+
+        messages = [fake_message(author=2), fake_message(author=3)]
+
+        for msg in messages:
+            scanner.compute_message(msg.channel, msg)
+
+        results = self._await(scanner.get_results(""))
+        self.assertListEqual(["There was no messages matching your filters"], results)
+
+    def test_normal(self):
+        scanner = FirstScanner()
+
+        self._await(scanner.init(fake_message(), []))
+
+        messages = [
+            fake_message(id=1, created_at=timedelta(days=-2)),
+            fake_message(id=2, created_at=timedelta(days=-3)),
+            fake_message(id=3, created_at=timedelta(days=-1)),
+        ]
+
+        for msg in messages:
+            scanner.compute_message(msg.channel, msg)
+
+        results = self._await(scanner.get_results(""))
+
+        expected = messages[1]
+        self.assertListEqual(
+            [
+                "First message out of 3",
+                f"{expected.created_at.strftime('%H:%M, %d %b. %Y')} (2 days ago) <@1> said:",
+                f"> {expected.content}",
+                "<https://discord.com/channels/1/1/2>",
+            ],
+            results,
+        )
+
+    def test_filtered(self):
+        scanner = FirstScanner()
+        scanner.raw_members = [1]
+
+        self._await(scanner.init(fake_message(), []))
+
+        messages = [
+            fake_message(id=1, author=1, created_at=timedelta(days=-2)),
+            fake_message(id=2, author=2, created_at=timedelta(days=-3)),
+            fake_message(id=3, author=1, created_at=timedelta(days=-1)),
+        ]
+
+        for msg in messages:
+            scanner.compute_message(msg.channel, msg)
+
+        results = self._await(scanner.get_results(""))
+
+        expected = messages[0]
+        self.assertListEqual(
+            [
+                "First message out of 2",
+                f"{expected.created_at.strftime('%H:%M, %d %b. %Y')} (yesterday) <@1> said:",
+                f"> {expected.content}",
+                "<https://discord.com/channels/1/1/1>",
+            ],
+            results,
+        )

tests/utils.py

@@ -0,0 +1,99 @@
+from typing import List, Optional, Dict, Union
+from unittest import TestCase
+import asyncio
+from datetime import datetime, timedelta
+from unittest.mock import MagicMock
+import random
+import string
+
+
+class AsyncTestCase(TestCase):
+    def setUp(self):
+        self.loop = asyncio.new_event_loop()
+        asyncio.set_event_loop(None)
+
+    def tearDown(self):
+        self.loop.close()
+
+    def _await(self, fn):
+        return self.loop.run_until_complete(fn)
+
+
+RANDOM_TEXT_CHARS = string.ascii_letters + string.digits + string.punctuation
+
+
+def random_text(min_len: int = 3, max_len: int = 45):
+    return "".join(
+        random.choice(RANDOM_TEXT_CHARS)
+        for _ in range(random.randrange(min_len, max_len))
+    )
+
+
+def fake_guild(id: int = 1):
+    return MagicMock(id=id)
+
+
+def fake_channel(id: int = 1, name: str = "fake-channel"):
+    return MagicMock(id=id, name=name, guild=fake_guild())
+
+
+def fake_message(
+    id: int = 1,
+    channel_id: int = 1,
+    channel_name: str = "fake-channel",
+    created_at: Optional[Union[datetime, timedelta]] = None,
+    edited_at: Optional[datetime] = None,
+    author: int = 1,
+    pinned: bool = False,
+    mention_everyone: bool = False,
+    tts: bool = False,
+    bot: bool = False,
+    content: Optional[str] = None,
+    mentions: Optional[List[int]] = None,
+    reference: Optional[int] = None,
+    role_mentions: Optional[List[int]] = None,
+    channel_mentions: Optional[List[int]] = None,
+    image: bool = False,
+    attachment: bool = False,
+    embed: bool = False,
+    reactions: Optional[Dict[str, List[int]]] = None,
+):
+    if created_at is None:
+        created_at = datetime.now() + timedelta(hours=random.randrange(-30 * 24, 0))
+    elif isinstance(created_at, timedelta):
+        created_at = datetime.now() + created_at
+    if isinstance(edited_at, timedelta):
+        edited_at = datetime.now() + edited_at
+    if content is None:
+        content = random_text()
+    if mentions is None:
+        mentions = []
+    if role_mentions is None:
+        role_mentions = []
+    if channel_mentions is None:
+        channel_mentions = []
+    if reactions is None:
+        reactions = {}
+    return MagicMock(
+        id=id,
+        channel=fake_channel(channel_id, channel_name),
+        created_at=created_at,
+        edited_at=edited_at,
+        author=author,
+        pinned=pinned,
+        mention_everyone=mention_everyone,
+        tts=tts,
+        bot=bot,
+        content=content,
+        mentions=mentions,
+        raw_mentions=mentions,
+        reference=reference,
+        role_mentions=role_mentions,
+        raw_role_mentions=role_mentions,
+        channel_mentions=channel_mentions,
+        raw_channel_mentions=channel_mentions,
+        image=image,
+        attachment=attachment,
+        embed=embed,
+        reactions=reactions,
+    )

utils.py

@@ -1,41 +0,0 @@
-from typing import List
-import logging
-import discord
-
-# DISCORD API
-
-
-def debug(message: discord.Message, txt: str):
-    logging.info(f"{message.guild} > #{message.channel}: {txt}")
-
-
-# LISTS
-
-
-def no_duplicate(seq: list) -> list:
-    """
-    Remove any duplicates on a list
-
-    :param seq: original list
-    :type seq: list
-    :return: same list with no duplicates
-    :rtype: list
-    """
-    return list(dict.fromkeys(seq))
-
-
-# MESSAGE FORMATTING
-
-
-def aggregate(names: List[str]) -> str:
-    """
-    Aggregate names with , and &
-
-    Example : "a, b, c & d"
-    """
-    if len(names) == 0:
-        return ""
-    elif len(names) == 1:
-        return names[0]
-    else:
-        return ", ".join(names[:-1]) + " & " + names[-1]