Metadata-Version: 2.4
Name: rara-subject-indexer
Version: 3.0.0
Summary: Automatically detect subject indices.
License:                     GNU AFFERO GENERAL PUBLIC LICENSE
                               Version 3, 19 November 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 Affero General Public License is a free, copyleft license for
        software and other kinds of works, specifically designed to ensure
        cooperation with the community in the case of network server software.
        
          The licenses for most software and other practical works are designed
        to take away your freedom to share and change the works.  By contrast,
        our General Public Licenses are 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.
        
          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.
        
          Developers that use our General Public Licenses protect your rights
        with two steps: (1) assert copyright on the software, and (2) offer
        you this License which gives you legal permission to copy, distribute
        and/or modify the software.
        
          A secondary benefit of defending all users' freedom is that
        improvements made in alternate versions of the program, if they
        receive widespread use, become available for other developers to
        incorporate.  Many developers of free software are heartened and
        encouraged by the resulting cooperation.  However, in the case of
        software used on network servers, this result may fail to come about.
        The GNU General Public License permits making a modified version and
        letting the public access it on a server without ever releasing its
        source code to the public.
        
          The GNU Affero General Public License is designed specifically to
        ensure that, in such cases, the modified source code becomes available
        to the community.  It requires the operator of a network server to
        provide the source code of the modified version running there to the
        users of that server.  Therefore, public use of a modified version, on
        a publicly accessible server, gives the public access to the source
        code of the modified version.
        
          An older license, called the Affero General Public License and
        published by Affero, was designed to accomplish similar goals.  This is
        a different license, not a version of the Affero GPL, but Affero has
        released a new version of the Affero GPL which permits relicensing under
        this license.
        
          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 Affero 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. Remote Network Interaction; Use with the GNU General Public License.
        
          Notwithstanding any other provision of this License, if you modify the
        Program, your modified version must prominently offer all users
        interacting with it remotely through a computer network (if your version
        supports such interaction) an opportunity to receive the Corresponding
        Source of your version by providing access to the Corresponding Source
        from a network server at no charge, through some standard or customary
        means of facilitating copying of software.  This Corresponding Source
        shall include the Corresponding Source for any work covered by version 3
        of the GNU General Public License that is incorporated pursuant to the
        following paragraph.
        
          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 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 work with which it is combined will remain governed by version
        3 of the GNU General Public License.
        
          14. Revised Versions of this License.
        
          The Free Software Foundation may publish revised and/or new versions of
        the GNU Affero 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 Affero 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 Affero 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 Affero 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) 2024  rsirel
        
            This program is free software: you can redistribute it and/or modify
            it under the terms of the GNU Affero 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 Affero General Public License for more details.
        
            You should have received a copy of the GNU Affero 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 your software can interact with users remotely through a computer
        network, you should also make sure that it provides a way for users to
        get its source.  For example, if your program is a web application, its
        interface could display a "Source" link that leads users to an archive
        of the code.  There are many ways you could offer source, and different
        solutions will be better for different programs; see section 13 for the
        specific requirements.
        
          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 AGPL, see
        <https://www.gnu.org/licenses/>.
        
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Intended Audience :: Science/Research
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: omikuji>=0.5.1
Requires-Dist: scikit-learn>=1.6.0
Requires-Dist: scipy>=1.13.0
Requires-Dist: estnltk==1.7.3
Requires-Dist: langdetect>=1.0.9
Requires-Dist: tqdm>=4.67
Requires-Dist: gensim>=4.3.3
Requires-Dist: nltk>=3.9.1
Requires-Dist: rakun2>=0.29
Requires-Dist: symspellpy>=6.7.8
Requires-Dist: numpy>=1.26.4
Requires-Dist: gdown>=5.2.0
Requires-Dist: gliner==0.2.*
Requires-Dist: jellyfish==1.1.*
Requires-Dist: regex==2024.11.*
Requires-Dist: stanza==1.10.*
Requires-Dist: urllib3==2.3.*
Provides-Extra: testing
Requires-Dist: pytest>=8.0; extra == "testing"
Requires-Dist: pytest-order; extra == "testing"
Dynamic: license-file

# RaRa Subject Indexer

![Py3.10](https://img.shields.io/badge/python-3.10-green.svg)
![Py3.11](https://img.shields.io/badge/python-3.11-green.svg)
![Py3.12](https://img.shields.io/badge/python-3.12-green.svg)

**`rara-subject-indexer`** is a  Python library for predicting subject indices (keywords) for textual inputs.

---

## ✨ Features  

- Predict subject indices of following types: **personal names**, **organizations**, **titles of work**, **locations**, **events**, **topics**, **UDC Summary**, **UDC National Bibliography**, **times**, **genres/form**, **EMS categories**.
- Supports subject indexing texts in **Estonian** and **English**.
- Use [Omikuji](https://github.com/tomtung/omikuji) for supervised subject indexing.
- Use [RaKUn](https://github.com/SkBlaz/rakun2) for unsupervised subject indexing.
- Use [StanzaNER](https://stanfordnlp.github.io/stanza/ner.html) and/or [GLiNER](https://github.com/urchade/GLiNER) for NER-based subject indexing.
- Train new Omikuji models.

---

## ⚡ Quick Start  

Get started with `rara-subject-indexer` in just a few steps:

1. **Install the Package**  
   Ensure you're using Python 3.10 or above, then run:  
   ```bash
   pip install rara-subject-indexer
   ```

2. **Import and Use**  
   Example usage for finding subject indices with default configuration:

   ```python
   from rara_subject_indexer.rara_indexer import RaraSubjectIndexer
   from pprint import pprint

   # If this is your first usage, download relevant models:
   # NB! This has to be done only once!
   RaraSubjectIndexer.download_resources()
   
   # Initialize the instance with default configuration
   rara_indexer = RaraSubjectIndexer()
   
   # Just a dummy text, use a longer one to get some meaningful results
   text = "Kui Arno isaga koolimajja jõudis, olid tunnid juba alanud."

   subject_indices = rara_indexer.apply_indexers(text=text)
   pprint(subject_indices)
   ```

---

---

## ⚙️ Installation Guide

Follow the steps below to install the `rara-subject-indexer` package, either via `pip` or locally.

---

### Installation via `pip`

<details><summary>Click to expand</summary>

1. **Set Up Your Python Environment**  
   Create or activate a Python environment using Python **3.10** or above.

2. **Install the Package**  
   Run the following command:  
   ```bash
   pip install rara-subject-indexer
   ```
</details>

---

### Local Installation

Follow these steps to install the `rara-subject-indexer` package locally:  

<details><summary>Click to expand</summary>


1. **Clone the Repository**  
   Clone the repository and navigate into it:  
   ```bash
   git clone <repository-url>
   cd <repository-directory>
   ```

2. **Set Up Python Environment**  
   Create or activate a Python environment using Python 3.10 or above. E.g:
   ```bash
   conda create -n py310 python==3.10
   conda activate py310
   ```

3. **Install Build Package**  
   Install the `build` package to enable local builds:  
   ```bash
   pip install build
   ```

4. **Build the Package**  
   Run the following command inside the repository:  
   ```bash
   python -m build
   ```

5. **Install the Package**  
   Install the built package locally:  
   ```bash
   pip install .
   ```

</details>

---

## 📝 Testing

<details><summary>Click to expand</summary>

1. **Clone the Repository**  
   Clone the repository and navigate into it:  
   ```bash
   git clone <repository-url>
   cd <repository-directory>
   ```

2. **Set Up Python Environment**  
   Create or activate a Python environment using Python 3.10 or above.

3. **Install Build Package**  
   Install the `build` package:  
   ```bash
   pip install build
   ```

4. **Build the Package**  
   Build the package inside the repository:  
   ```bash
   python -m build
   ```

5. **Install with Testing Dependencies**  
   Install the package along with its testing dependencies:  
   ```bash
   pip install .[testing]
   ```

6. **Run Tests**  
   Run the test suite from the repository root:  
   ```bash
   python -m pytest -v tests
   ```
---

</details>

## 📚 Documentation

<details><summary>Click to expand</summary>


### 🔍 RaraSubjectIndexer Class

#### Overview

`RaraSubjectIndexer` wraps all logic of different models and keyword types.

#### Parameters


| Name           | Type                 | Optional | Default                 | Description                                                                                                               |
|----------------|----------------------|----------|-------------------------|---------------------------------------------------------------------------------------------------------------------------|
| methods        | Dict[str, List[str]] | True     | DEFAULT_METHOD_MAP      | Methods to use per each keyword type. See ALLOWED_METHODS for a list of supported methods of each keyword type.           |
| keyword_types  | List[str]            | True     | DEFAULT_KEYWORD_TYPES   | Keyword (subject index) types to predict. See ALLOWED_KEYWORD_TYPES for a list of supported methods of each keyword type. |
| topic_config   | dict                 | True     | DEFAULT_TOPIC_CONFIG    | Configuration for topic subject indexing models. |
| time_config    | dict                 | True     | DEFAULT_TIME_CONFIG     | Configuration for time subject indexing models. |
| genre_config   | dict                 | True     | DEFAULT_GENRE_CONFIG    | Configuration for genre/form subject indexing models. |
| category_config| dict                 | True     | DEFAULT_CATEGORY_CONFIG | Configuration for EMS category prediction models. |
| udc_config     | dict                 | True     | DEFAULT_UDC_CONFIG      | Configuration for UDC (National Bibliography) prediction models.|
| udc2_config    | dict                 | True     | DEFAULT_UDC2_CONFIG     | Configuration for UDC Summary models.|
| ner_config     | dict                 | True     | DEFAULT_NER_CONFIG      | Configuration for NER-based subject indexing models.|
| omikuji_data_dir | string             | True     | OMIKUJI_DATA_DIR        | Path to directory storing Omikuji models. |
| ner_data_dir     | string             | True     | NER_DATA_DIR            | Path to directory storing NER models.     |


##### Allowed keyword types

| Enum object          | String value                     | 
|----------------------|----------------------------------|
| KeywordType.TOPIC    | "Teemamärksõnad"                 | 
| KeywordType.EVENT    | "Ajutine kollektiiv või sündmus" |
| KeywordType.LOC      | "Kohamärksõnad"                  |
| KeywordType.TIME     | "Ajamärksõnad"                   |
| KeywordType.GENRE    | "Vormimärksõnad"                 |
| KeywordType.PER      | "Isikunimi"                      |
| KeywordType.ORG      | "Kollektiivi nimi"               |
| KeywordType.TITLE    | "Teose pealkiri"                 |
| KeywordType.UDK      | "UDK Rahvusbibliograafia"        |
| KeywordType.UDK2     | "UDC Summary"                    |
| KeywordType.CATEGORY | "Valdkonnamärksõnad"             |

##### Allowed methods

| Keyword type (Enum object)| Keyword type (string value)      | Allowed methods                    |
|---------------------------|----------------------------------|------------------------------------|
| KeywordType.TOPIC         | "Teemamärksõnad"                 | "omikuji", "rakun"                 |
| KeywordType.EVENT         | "Ajutine kollektiiv või sündmus" | "gliner"                           |
| KeywordType.LOC           | "Kohamärksõnad"                  | "gliner", "stanza", "ner_ensemble" |
| KeywordType.TIME          | "Ajamärksõnad"                   | "omikuji"                          |
| KeywordType.GENRE         | "Vormimärksõnad"                 | "omikuji"                          |
| KeywordType.PER           | "Isikunimi"                      | "gliner", "stanza", "ner_ensemble" |
| KeywordType.ORG           | "Kollektiivi nimi"               | "gliner", "stanza", "ner_enseble"  |
| KeywordType.TITLE         | "Teose pealkiri"                 | "gliner"                           |
| KeywordType.UDK           | "UDK Rahvusbibliograafia"        | "omikuji"                          |
| KeywordType.UDK2          | "UDC Summary"                    | "omikuji"                          |
| KeywordType.CATEGORY      | "Valdkonnamärksõnad"             | "omikuji"                          |


##### Default configurations
<details><summary>Default configurations</summary>


DEFAULT_KEYWORD_TYPES:

```json 
[
    "Teemamärksõnad",
    "Kohamärksõnad",
    "Isikunimi",
    "Kollektiivi nimi",
    "Kohamärksõnad",
    "Ajamärksõnad",
    "Teose pealkiri",
    "UDK Rahvusbibliograafia",
    "UDC Summary",
    "Vormimärksõnad",
    "Valdkonnamärksõnad",
    "Ajutine kollektiiv või sündmus"
]
```

DEFAULT_METHOD_MAP:

```json
 {
    "Teemamärksõnad": ["omikuji", "rakun"],
    "Kohamärksõnad": ["ner_ensemble"],
    "Isikunimi": ["ner_ensemble"], 
    "Kollektiivi nimi": ["ner_ensemble"],
    "Kohamärksõnad": ["ner_ensemble"],
    "Ajamärksõnad": ["omikuji"],
    "Teose pealkiri": ["gliner"],
    "UDK Rahvusbibliograafia": ["omikuji"],
    "UDC Summary": ["omikuji"],
    "Vormimärksõnad": ["omikuji"],
    "Valdkonnamärksõnad": ["omikuji"],
    "NER": ["ner"],
    "Ajutine kollektiiv või sündmus": ["gliner"]     
}
```
DEFAULT_TOPIC_CONFIG:

```json
 {
    "omikuji": {
        "et": "./rara_subject_indexer/data/omikuji_models/teemamarksonad_est"
        "en": "./rara_subject_indexer/data/omikuji_models/teemamarksonad_eng"
    }
    "rakun": {
        "stopwords": {
            "et": <list of stopwords loaded from "rara_subject_indexer/resources/stopwords/et_stopwords_lemmas.txt">,
            "en": <list of stopwords loaded from "rara_subject_indexer/resources/stopwords/et_stopwords.txt">,
        },
        "n_raw_keywords": 30
    }
}
```


DEFAULT_TIME_CONFIG:

```json
 {
    "omikuji": {
        "et": "./rara_subject_indexer/data/omikuji_models/ajamarksonad_est"
        "en": "./rara_subject_indexer/data/omikuji_models/ajamarksonad_eng"
    }
    "rakun": {}
}
```

DEFAULT_GENRE_CONFIG:

```json
 {
    "omikuji": {
        "et": "./rara_subject_indexer/data/omikuji_models/vormimarksonad_est"
        "en": "./rara_subject_indexer/data/omikuji_models/vormimarksonad_eng"
    }
    "rakun": {}
}
```

DEFAULT_CATEGORY_CONFIG:

```json
 {
    "omikuji": {
        "et": "./rara_subject_indexer/data/omikuji_models/valdkonnamarksonad_est"
        "en": "./rara_subject_indexer/data/omikuji_models/valdkonnamarksonad_eng"
    }
    "rakun": {}
}
```

DEFAULT_UDC_CONFIG:

```json
 {
    "omikuji": {
        "et": "./rara_subject_indexer/data/omikuji_models/udk_rahvbibl_est"
        "en": "./rara_subject_indexer/data/omikuji_models/udk_rahvbibl_eng"
    }
    "rakun": {}
}
```

DEFAULT_UDC2_CONFIG:

```json
 {
    "omikuji": {
        "et": "./rara_subject_indexer/data/omikuji_models/udk_general_depth_11_est"
        "en": "./rara_subject_indexer/data/omikuji_models/udk_general_depth_11_eng"
    }
    "rakun": {}
}
```

DEFAULT_NER_CONFIG:

```json
 {
    "ner": {
        "stanza_config": {
            "resource_dir": "./rara_subject_indexer/data/ner_resources/",
            "download_resources": False,
            "supported_languages": ["et", "en"],
            "custom_ner_model_langs": ["et"],
            "refresh_data": False,
            "custom_ner_models": {
                "et": "https://packages.texta.ee/texta-resources/ner_models/_estonian_nertagger.pt"
            },
            "unknown_lang_token": "unk"   
        },
        "gliner_config": {
            "labels": ["Person", "Organization", "Location", "Title of a work", "Date", "Event"], 
            "model_name": "urchade/gliner_multi-v2.1",
            "multi_label": False,
            "resource_dir": "./rara_subject_indexer/data/ner_resources/",
            "threshold": 0.5,
            "device": "cpu"
        },
        "ner_method_map": {
            "PER": "ner_ensemble",
            "ORG": "ner_ensemble",
            "LOC": "ner_ensemble",
            "TITLE": "gliner",
            "EVENT": "gliner"
        }
    }
}
```
OMIKUJI_DATA_DIR = `"./rara_subject_indexer/data/omikuji_models/"`

NER_DATA_DIR = `"./rara_subject_indexer/data/ner_resources/"`

</details>

#### Key Functions

##### `apply_indexers`

`apply_indexers` takes plaintext as an input and outputs predicted subject indices for all keyword types and methods defined during initiating the class instance.

###### Parameters

| Name           | Type                 | Optional | Default                 | Description                                    |
|----------------|----------------------|----------|-------------------------|---------------------------------------------------------------------------------------------------------------------------|
| text        | str | False    | -     | Text for which to find the subject indices. |
| lang             | str | False    | ""    | Language code indicating the language of the text. If not specified, the language of the text is detected automatically. |
| threshold_config  | dict | False    | DEFAULT_THRESHOLD_CONFIG     | Can be used to overwrite default threshold settings for each keyword type separately. |
| min_score        | float | False    | None    | If not None, defaults to min threshold score for all keyword types that are NOT specifically set via `threshold_config`. Has to be a float between 0 and 1. |
| max_count        | int | False    | None     | If not None, defaults to max keyword count for all keyword types that are NOT specifically set via `threshold_config`.|
| flat       |bool | False    | True     | If enabled, keywords are returned in a flat list of dicts; otherwise with more nested structure. |
| rakun_config       | dict | False    | DEFAULT_RAKUN_CONFIG   | Configuration parameters for Rakun. |
| omikuji_config        | dict | False    | DEFAULT_OMIKUJI_CONFIG    | Configuration parameters for Omikuji. |
| ner_config       | dict | False    | DEFAULT_NER_CONFIG     | Configuration parameters for NER-based indexers. |


Allowed options along with default configurations for `rakun_config`, `omikuji_config`, `ner_config` can be seen below.

**Rakun config**

|Name | Type | Optional | Default | Description |
|-----|------|----------|---------|-------------|
|use_phraser| bool | True | False | If enabled, two-word keyphrases can be extracted from the text. Otherwise, only single words will be returned as keywords / subject indices. NB! Using phraser is currently **supported only for Estonian**. |
| postags_to_ignore | List[str] | True | ["V", "A", "D", "Z", "H", "P", "U", "N", "O"] | List of part-of-speech tags to ignore while detecting keywords / subject_indices. List of possible POS-tags can be found from her:  https://www.sketchengine.eu/estonian-filosoft-part-of-speech-tagset. NB! Ignoring POS-tags is currently **supported only for Estonian**. |

DEFAULT_RAKUN_CONFIG:

```json
{
    "use_phraser": False, 
    "postags_to_ignore": ["V", "A", "D", "Z", "H", "P", "U", "N", "O"]
}
```

**Omikuji config**

|Name | Type | Optional | Default | Description |
|-----|------|----------|---------|-------------|
|lemmatize | bool | True | False | Is enabled, text is lemmatized/stemmed (depending on the language) in `OmikujiModel` class. Default value is False as text in this workflow is actually lemmatized before passing it to the `OmikujiModel` class.|

DEFAULT_OMIKUJI_CONFIG:

```json
{
    "lemmatize": False
}
```

**NER config**

|Name | Type | Optional | Default | Description |
|-----|------|----------|---------|-------------|
|lemmatize | bool | True | False | Is enabled, text is lemmatized/stemmed (depending on the language) in `NERIndexer` class. Default and recommended value is False as lemmatizing/stemming might lead to incorrect NER entities, especially for titles, events and organizations.|
|min_count | int | True | 3 | The minimum number of times an entity has to appear in the text to be considered as a potential subject index (before applying additional score-based filtering). |
|ensemble_strategy | string | True| "intersection" | The strategy used, is selected NER method = "ner_ensemble". Allowed options are: ["intersection", "union"]. "intersection" outputs the intersection of Stanza and GLiNER method outputs; "union" outputs the union of Stanza and GLiNER method outputs. "interection" is recommended for more precise results, while "union" is recommended for higher recall |


DEFAULT_NER_CONFIG:

```json
{
    "lemmatize": False, 
    "min_count": 3, 
    "ensemble_strategy": "intersection"
}     
```
**threshold_config**

Specifying a threshold_config will overwrite default configurations of all keyword and method types occuring in the configuration. 

DEFAULT_THREHOLD_CONFIG:

```json
{
    KeywordType.TOPIC: {
        ModelArch.OMIKUJI: {"max_count": 5, "min_score": 0.1},
        ModelArch.RAKUN: {"max_count": 5, "min_score": 0.01}
    },
    KeywordType.TIME: {
        ModelArch.OMIKUJI: {"max_count": 3, "min_score": 0.2}
    },
    KeywordType.GENRE: {
        ModelArch.OMIKUJI: {"max_count": 3, "min_score": 0.2}
    },
    KeywordType.UDK: {
        ModelArch.OMIKUJI: {"max_count": 1, "min_score": 0.3}
    },
    KeywordType.UDK2: {
        ModelArch.OMIKUJI: {"max_count": 1, "min_score": 0.3}
    },
    KeywordType.PER: {
        ModelArch.NER: {"max_count": 5, "min_score": 0.3}
    },
    KeywordType.ORG: {
        ModelArch.NER: {"max_count": 5, "min_score": 0.3}
    },
    KeywordType.TITLE: {
        ModelArch.NER: {"max_count": 5, "min_score": 0.3}
    },
    KeywordType.LOC: {
        ModelArch.NER: {"max_count": 5, "min_score": 0.3}
    },
    KeywordType.CATEGORY: {
        ModelArch.OMIKUJI: {"max_count": 3, "min_score": 0.2}
    },
    KeywordType.EVENT: {
        ModelArch.NER: {"max_count": 5, "min_score": 0.1}
    }
}
```

---
 

### Training Supervised and Unsupervised Models

If necessary, you can train the supervised and unsupervised models from scratch using the provided pipelines. 
The training process involves reading text and label files, preprocessing the text, and training the models 
using the extracted features.

#### Training an Omikuji Model for Supervised Keyword Extraction

A sample code snippet to train and predict using the Omikuji model is provided below:

```python
from rara_subject_indexer.supervised.omikuji.omikuji_model import OmikujiModel

model = OmikujiModel()

model.train(
    text_file="texts.txt",         # File with one document per line
    label_file="labels.txt",       # File with semicolon-separated labels for each document
    language="et",                 # Language of the text, in ISO 639-1 format
    entity_type="Teemamärksõnad",  # Entity type for the keywords
    lemmatization_required=True,   # (Optional) Whether to lemmatize the text - only set False if text_file is already lemmatized
    max_features=20000,            # (Optional) Maximum number of features for TF-IDF extraction
    keep_train_file=False,         # (Optional) Whether to retain intermediate training files
    eval_split=0.1                 # (Optional) Proportion of the dataset used for evaluation
)

predictions = model.predict(
    text="Kui Arno isaga koolimajja jõudis",  # Text to classify
    top_k=3  # Number of top predictions to return
)  # Output: [('koolimajad', 0.262), ('isad', 0.134), ('õpilased', 0.062)]
```

##### 📂 Data Format

The files provided to the train function should be in the following format:
- A **text file** (`.txt`) where each line is a document.
    ```
    Document one content.
    Document two content.
    ```
- A **label file** (`.txt`) where each line contains semicolon-separated labels corresponding to the text file.
    ```
    label1;label2
    label3;label4
    ```



---

#### Training Phraser for Unsupervised Keyword Extraction


A sample code snippet to train and predict using the Phraser model is provided below:

```python
from rara_subject_indexer.utils.phraser_model import PhraserModel

model = PhraserModel()

model.train(
    train_data_path=".../train.txt",  # File with one document per line, text should be lemmatised.
    lang_code="et",                   # Language of the text, in ISO 639-1 format
    min_count=5,                      # (Optional) Minimum word frequency for phrase formation.
    threshold=10.0                    # (Optional) Score threshold for forming phrases.
)

predictions = model.predict(
    text="'vabariik aastapäev sööma kiluvõileib'",  # Lemmatised text for phrase detection
)  # Output: ['vabariik_aastapäev', 'sööma', kiluvõileib']
```

##### 📂 Data Format

The file provided to the PhraserModel train function should be in the following format:

- A **text file** (`.txt`) where each line is a document.
    ```
    Document one content.
    Document two content.
    ```

</details>

## 🔍 Usage Examples

<details><summary>Click to expand</summary>
    
### Test  texts

<details><summary>TEXT_ET</summary>

```
Los Angeleses jagatakse 97. korda Ameerika filmiakadeemia auhindu ehk Oscareid. Parima täispika animatsiooni kategoorias pälvis Oscari Läti režissööri Gints Zilbalodise film "Vooluga kaasa". Õhtu suurim võitja oli aga Sean Bakeri "Anora", mis läks koju viie auhinnaga, nende hulgas ka aasta filmi preemia.

Läti võitis filmiga "Vooluga kaasa" oma esimese Oscari. Režissöör Gints Zilbalodis ütles, et ta on väga liigutatud sellest, kui hästi nende film on vastu võetud. "Ma loodan, et see avab ka teistele sõltumatutele filmitegijatele uksi," ütles ta ja lisas, et see on esimene kord, kui Läti film on olnud nomineeritud Oscarile. "See tähendab meie jaoks väga palju, loodame varsti siin tagasi olla." "Vooluga kaasa" võidu peale ütles õhtujuht Conan O'Brien, et "pall on nüüd teie väljakupoolel, Eesti".

Auhinnagala algas pühendusega Los Angelesele, kus möllasid tänavu jaanuaris rasked metsatulekahjud, mis puudustasid ka paljusid filmitegijaid. Sellele järgnes Ariana Grande laulunumber, kus ta kandis ette filmist "Võlur Oz" tuntuks saanud loo "Over the Rainbow". Näitleja ja muusik Cynthia Erivo, kes astus koos Grandega üles filmis "Wicked", esitas pärast teda Diana Rossi loo "Home", mis kõlas esmakordselt 1975. aastal Broadway muusikalis "The Wiz".

Teine suurem muusikanumber toimus keset galat, kui tehti austusavaldus James Bondile. Tantsunumbriga astus laval üles näitleja Margaret Qualley, muusikutest astusid üles Blackpinki liige Lisa, kes esitas loo "Live and Let Die"; Doja Cat, kes kandis ette pala "Diamonds are Forever" ning Raye, kelle esituses kõlas "Skyfall".

Oma avakõnes ütles õhtujuht Conan O'Brien, et Los Angelese inimesed on viimasel ajal palju läbi elanud ja sellised auhinnagalad võivad tunduda seejuures tühised. "Me tunnustame siin küll palju näitlejaid, aga samas pöörame tähelepanu ka inimestele, kes tegutsevad kaamera taga ning kes on pühendanud oma elu sellele, et filmidega tegeleda, kuigi paljud neist ei ole tuntud ega rikkad," sõnas ta.


Funk: Eesti anima on kaootiliselt mitmekülgne, Oscarid vajavad lihtsamaid lugusid
Gala lõpuosas ütles O'Brien, et on rõõm näha, et "Anora" on võitnud juba kaks auhinda. "Ameeriklastel on ilmselt hea näha, et keegi astub lõpuks võimsa venelase vastu."

Näitleja Kieran Culkin pälvis rolli eest filmis "Tõeline valu" oma esimese Oscari. "Mul ei ole mingit aimu, kuidas ma jõudsin siia, sest ma olen näidelnud terve oma elu," ütles ta ja lisas, et Jesse Eisenberg on geenius. "Ma ei ole seda kunagi varem sulle öelnud ja ei ütle enam kunagi uuesti."

Oma esimese Oscari pälvis tänavu ka Zoe Saldana rolli eest filmis "Emilia Perez". Tänukõnes rõhutas ta, et 1961. aastal kolis ta vanaema Ameerikasse ning ta on uhkusega immigrantide perekonnast pärit. "Ma olen ka esimene dominikaani juurtega ameeriklane, kes on võitnud Oscari, aga ma olen kindel, et mitte viimane."

22 aastat tagasi filmiga "Pianist" oma esimese Oscari võitnud Adrien Brody pälvis tänavu oma teise auhinna. "Näitlemine on väga habras elukutse, mis tundub väga glamuurne ja mingitel hetkedel kindlasti on, kuid aastate jooksul olen mõistnud, et kõik, mida sa oled oma karjääri jooksul saavutanud, võib kaduda," ütles ta ja lisas, et see auhind näitab talle, et tal on võimalus alustada uuesti. "See annab mulle võimaluse ka järgmised 20 aastat oma elust näidata, et olen suuri ja tähenduslikke rolle väärt."

Rolli eest filmis "Anora" pälvis näitleja Mikey Madison. "Ma kasvasin üles Los Angeleses, aga Hollywood tundus minust alati nii kaugel, seega võimalus seista siin ruumis on täiesti uskumatu," kinnitas ta ja lisas, et see on unistuse täitumine.


Galerii: Ameerika filmiakadeemia auhindade punane vaip
Parim film
"Anora", režissöör Sean Baker
"Brutalist" ("The Brutalist"), režissöör Brady Corbet
"Täiesti tundmatu" ("A Complete Unknown"), režissöör James Mangold
"Konklaav" ("Conclave"), režissöör Edward Berger
"Düün: teine osa" ("Dune: Part Two"), režissöör Denis Villeneuve
"Emilia Perez", režissöör Jacques Audiard
"Olen veel siin" ("I'm Still Here"), režissöör Walter Salles
"Nickel Boys", režissöör RaMell Ross
"Protseduur" ("The Subtance"), režissöör Coralie Fargeat
"Wicked", režissöör Jon M. Chu

Parim naispeaosa
Cynthia Erivo rolli eest filmis "Wicked"
Karla Sofia Garcon rolli eest filmis "Emilia Perez"
Mikey Madison rolli eest filmis "Anora"
Demi Moore rolli eest filmis "Protseduur"
Fernanda Torres rolli eest filmist "Olen veel siin"

Parim lavastaja
Sean Baker filmiga "Anora"
Brady Corbet filmiga "Brutalist"
James Mangold filmiga "Täiesti tundmatu"
Jacques Audiard filmiga "Emilia Perez"
Coralie Fargeat filmiga "Protseduur"

Parim meespeaosa
Adrien Brody rolli eest filmis "Brutalist"
Timothee Chalamet rolli eest filmist "Täiesti tundmatu"
Colman Domingo rolli eest filmis "Sing Sing"
Ralph Fiennes rolli eest filmis "Konklaav"
Sebastian Stan rolli eest filmist "Mantlipärija: Trumpi lugu"

Parim originaalmuusika
"Brutalist"
"Konklaav"
"Emilia Perez"
"Wicked"
"Pöörane robot" ("The Wild Robot")

Parim rahvusvaheline film
"Olen veel siin", Brasiilia
"Tüdruk nõelaga" ("The Girl With the Needle"), Taani
"Emilia Perez", Prantsusmaa
"The Seed of the Sacred Fig", Saksamaa
"Flow", Läti

Parim operaatoritöö
"Brutalist"
"Düün: teine osa"
"Emilia Perez"
"Maria"
"Nosferatu"


Briti filmiauhindade jagamisel võidutsesid "Konklaav" ja "Brutalist"
Parim lühimängufilm
"A Lien"
"Anuja"
"I'm Not A Robot"
"The Last Ranger"
"The Man Who Could Not Remain Silent"

Parimad eriefektid
"Alien: Romulus"
"Better Man"
"Düün: teine osa"
"Ahvide planeedi kuningriik" ("Kingdom of the Planet of the Apes")
"Wicked"

Parim heli
"Täiesti tundmatu"
"Düün: teine osa"
"Emilia Perez"
"Wicked"
"Pöörane robot"

Parim dokumentaalfilm
"Black Box Diaries"
"Pole muud maad" ("No Other Land")
"Portselanist sõda" ("Porcelain War")
"Soundtrack to a Coup d'etat"
"Sugarcane"

Parim lühidokumentaal
"Death by Numbers"
"I Am Ready, Warden"
"Incident"
"Instruments of a Beating Heart"
"Only Girl in the Orchestra"

Parim originaallugu
"El Mal" filmist "Emilia Perez"
"The Journey" filmist "Six Triple Eight"
"Like a Bird" filmist "Sing Sing"
"Mi Camino" filmist "Emilia Perez"
"Never Too Late" filmist "Elton John: Never Too Late"

Parim kunstnikutöö
"Brutalist"
"Konklaav"
"Düün: teine osa"
"Nosferatu"
"Wicked"

Parim naiskõrvalosa
Monica Barbaro rolli eest filmis "Täiesti tundmatu"
Ariana Grande rolli eest filmis "Wicked"
Felicity Jones rolli eest filmis "Brutalist"
Isabella Rossellini rolli eest filmis "Konklaav"
Zoe Saldana rolli eest filmis "Emilia Perez"

Parim montaaž
"Anora"
"Brutalist"
"Konklaav"
"Emilia Perez"
"Wicked"

Parim grimm
"A Different Man"
"Emilia Perez"
"Nosferatu"
"Protseduur"
"Wicked"

Parim kohandatud stsenaarium
"Täiesti tundmatu"
"Konklaav"
"Emilia Perez"
"Nickel Boys"
"Sing Sing"

Parim originaalstsenaarium
"Anora"
"Brutalist"
"Tõeline valu"
"5. september" ("September 5")
"Protseduur"

Parim kostüümidisain
"Täiesti tundmatu"
"Konklaav"
"Gladiaator II"
"Nosferatu"
"Wicked"

Parim lühianimatsioon
"Beautiful Man"
"In The Shadow of the Cypress"
"Magic Candies"
"Wander to Wonder"
"Yuck!"

Parim täispikk animatsioon
"Vooluga kaasa"
"Pahupidi 2"
"Memoir of a Snail"
"Wallace and Gromit: Vengence Most Fowl"
"Pöörane robot"

Parim meeskõrvalosa
Yuri Borissov rolli eest filmis "Anora"
Kieran Culkin rolli eest filmis "Tõeline valu" ("A Real Pain")
Edward Norton rolli eest filmis "Täiesti tundmatu"
Guy Pierce rolli eest filmis "Brutalist"
Jeremy Strong rolli eest filmis "Mantlipärija: Trumpi lugu" ("The Apprentice")    
```
</details>

<details><summary>TEXT_EN</summary>

```
Easter marks the start of spring, the triumph of life and renewal and is a time of festivities and tradition in Estonia.

Easter is known by many names in Estonia, including lihavõtted (a direct reference to the return of meat on menus after Lent), munadepüha (egg holiday) and kiigepüha (swing holiday, pointing to the tradition of taking to traditional wooden village swings on Easter Sunday).

In the old folk calendar, the spring holiday started on the next Sunday after the first full moon following the spring equinox, falling between March 23 and April 26. The holiday week was important for household chores, such as spring cleaning after a long winter. According to tradition, the weather during this week could be used to predict conditions for the entire summer. If it rained, a wet summer would follow, and if there was fog, a hot summer could be expected.

Maundy Thursday was considered a semi-holiday, during which people prepared for Good Friday. Lighter meals were eaten, such as soup. The types of soup varied by region, but one thing was certain: everyone rested on Good Friday. It was very rare for anyone to even leave the house on that day.

Easter Sunday, much like today, was a festive occasion. On this day, people traditionally exchanged eggs or gave them as gifts. Young people would gather by the village swing and girls would give decorated Easter eggs to the boys as thanks for building the swing, where they would then spend the afternoon together. People gathered in their homes or at the local tavern and exchanged eggs as gifts. Eggs were also used in food, most commonly as egg butter or egg spread.


Singers in Sõrve national dress on a traditional village swing. Source: Margus Muld/ERR
Pussy willows brought indoors were and are an inseparable part of the holiday. Those who hadn't gotten them earlier would place them in a vase by the time egg dyeing began. When liverworts started to bloom, people would also bring in moss and the first spring flowers. In the 20th century, it became customary to sprout grass on a plate or in a bowl for Easter, creating a bed on which to place decorated eggs. Nests made of twigs and moss were also crafted to hold the colorful eggs. Additionally, budding branches of various kinds were placed indoors and used to decorate rooms.

Easter customs and springtime traditions varied across different regions of Estonia. Some of these old Easter traditions are celebrated each year at the Estonian Open Air Museum in Tallinn. Visitors can also travel to Setomaa in southern Estonia to gain a deeper understanding of the local customs there.

These days, Easter Sunday is usually celebrated by having a long lunch, dyeing and swapping eggs and a traditional Easter hunt. Eggs are usually colored using natural dies, such as those from onion peels or beets. The multicolored eggs are a mandatory part of any Easter spread and the natural colorings mean they're perfectly edible.

While rooms can be decorated with artificial eggs, real eggs are needed for the traditional egg tapping competition, which crowns a new champion each year. The rules are simple — tap the tip of your egg against your opponent's, and whoever's shell remains unbroken wins! Some families keep the fun going all year round — it's just that enjoyable. If natural dyes are used, the extra layer of the one with the cracked egg having to eat it is sometimes added to the competition, making ultimate victory dependent not only on the best tapping tactic but also one's capacity for boiled eggs.

Many Easter customs still practiced today originate from old folk traditions. One such game, popular especially in Setomaa, is egg rolling, which shares the same goal as egg tapping: to crack the opponent's eggshell. Players roll their eggs down a sand mound, aiming to hit other eggs. The difficulty of the slope is entirely up to the player. The winner is the one whose egg stays intact.

Traditional Easter food covers everything to do with eggs, but also curd and cottage cheese dishes, including salads, desserts and pastries utilizing these ingredients. Prime examples include deviled eggs and egg salad, Of meats, veal, hare and rabbit are revered during this period, while it's no good turning your nose up at fish, pork, chicken or lamb either.

Porridge and all manner of baked goodness, including homemade white bread, pastries and cakes, are also held in high esteem around the holiday. However, among Easter desserts, paskha is widely considered a favorite.    
```
</details>

<details><summary>TEXT_RU</summary>

```
Министр иностранных дел Ирана Аббас Аракчи выразил надежду
что Россия примет участие в переговорах по ядерной программе Ирана.

До сих пор переговоры проходили в двустороннем формате между Ираном и США. Следующий раунд состоится завтра в Риме, передает "Актуальная камера".

По словам главы иранского МИДа, переговоры до сих пор были конструктивными и стороны могут прийти к согласию по ядерной программе.   
```
</details>

### Apply with default configuration

#### Estonian input text

```python
from rara_subject_indexer.rara_indexer import RaraSubjectIndexer
from pprint import pprint

# If this is your first usage, download relevant models:
# NB! This has to be done only once!
RaraSubjectIndexer.download_resources()

# Initialize the instance with default configuration
rara_indexer = RaraSubjectIndexer()

subject_indices = rara_indexer.apply_indexers(text=TEXT_ET)
pprint(subject_indices)
```

<details><summary>Output</summary>
    
```json

{"durations": [{"duration": 0.0283,
                "keyword_type": "Teemamärksõnad",
                "model_arch": "omikuji"},
               {"duration": 1.22906,
                "keyword_type": "Teemamärksõnad",
                "model_arch": "rakun"},
               {"duration": 0.00891,
                "keyword_type": "Ajamärksõnad",
                "model_arch": "omikuji"},
               {"duration": 0.01025,
                "keyword_type": "Vormimärksõnad",
                "model_arch": "omikuji"},
               {"duration": 5.44328,
                "keyword_type": "NER",
                "model_arch": "ner"},
               {"duration": 0.01392,
                "keyword_type": "UDK Rahvusbibliograafia",
                "model_arch": "omikuji"},
               {"duration": 0.0177,
                "keyword_type": "UDC Summary",
                "model_arch": "omikuji"},
               {"duration": 0.00761,
                "keyword_type": "Valdkonnamärksõnad",
                "model_arch": "omikuji"}],
 "keywords": [{"entity_type": "Teemamärksõnad",
               "keyword": "filmid (teosed)",
               "model_arch": "omikuji",
               "score": 0.979},
              {"entity_type": "Teemamärksõnad",
               "keyword": "mängufilmid",
               "model_arch": "omikuji",
               "score": 0.573},
              {"entity_type": "Teemamärksõnad",
               "keyword": "filmiauhinnad",
               "model_arch": "omikuji",
               "score": 0.164},
              {"entity_type": "Teemamärksõnad",
               "keyword": "film",
               "model_arch": "rakun",
               "score": 0.32},
              {"entity_type": "Teemamärksõnad",
               "keyword": "ameeriklane",
               "model_arch": "rakun",
               "score": 0.039},
              {"entity_type": "Teemamärksõnad",
               "keyword": "metsatulekahju",
               "model_arch": "rakun",
               "score": 0.025},
              {"entity_type": "Teemamärksõnad",
               "keyword": "kostüümidisain",
               "model_arch": "rakun",
               "score": 0.025},
              {"entity_type": "Teemamärksõnad",
               "keyword": "austusavaldus",
               "model_arch": "rakun",
               "score": 0.023},
              {"entity_type": "Vormimärksõnad",
               "keyword": "filmiarvustused",
               "model_arch": "omikuji",
               "score": 0.905},
              {"count": 3,
               "entity_type": "Isikunimi",
               "keyword": "Sean Baker",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 5,
               "entity_type": "Teose pealkiri",
               "keyword": "Wicked",
               "method": "gliner",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 5,
               "entity_type": "Teose pealkiri",
               "keyword": "Brutalist",
               "method": "gliner",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 4,
               "entity_type": "Teose pealkiri",
               "keyword": "Anora",
               "method": "gliner",
               "model_arch": "ner",
               "score": 0.8},
              {"count": 3,
               "entity_type": "Teose pealkiri",
               "keyword": "Nosferatu",
               "method": "gliner",
               "model_arch": "ner",
               "score": 0.6},
              {"count": 3,
               "entity_type": "Teose pealkiri",
               "keyword": "Vooluga kaasa",
               "method": "gliner",
               "model_arch": "ner",
               "score": 0.6},
              {"entity_type": "UDK Rahvusbibliograafia",
               "keyword": "791",
               "model_arch": "omikuji",
               "score": 1.0},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "FOTOGRAAFIA. FILM. KINO",
               "model_arch": "omikuji",
               "score": 1.0},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "KOHANIMED",
               "model_arch": "omikuji",
               "score": 0.944},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "AJAKIRJANDUS. KOMMUNIKATSIOON. MEEDIA. REKLAAM",
               "model_arch": "omikuji",
               "score": 0.449}]}
```

</details>

#### English input text

```python
from rara_subject_indexer.rara_indexer import RaraSubjectIndexer
from pprint import pprint

# If this is your first usage, download relevant models:
# NB! This has to be done only once!
# RaraSubjectIndexer.download_resources()

# Initialize the instance with default configuration
rara_indexer = RaraSubjectIndexer()

subject_indices = rara_indexer.apply_indexers(text=TEXT_EN)
pprint(subject_indices)
```

<details><summary>Output</summary>
    
```json
{"durations": [{"duration": 0.06654,
                "keyword_type": "Teemamärksõnad",
                "model_arch": "omikuji"},
               {"duration": 0.02818,
                "keyword_type": "Teemamärksõnad",
                "model_arch": "rakun"},
               {"duration": 0.01287,
                "keyword_type": "Ajamärksõnad",
                "model_arch": "omikuji"},
               {"duration": 0.01382,
                "keyword_type": "Vormimärksõnad",
                "model_arch": "omikuji"},
               {"duration": 2.80652,
                "keyword_type": "NER",
                "model_arch": "ner"},
               {"duration": 0.01278,
                "keyword_type": "UDK Rahvusbibliograafia",
                "model_arch": "omikuji"},
               {"duration": 0.01117,
                "keyword_type": "UDC Summary",
                "model_arch": "omikuji"},
               {"duration": 0.00898,
                "keyword_type": "Valdkonnamärksõnad",
                "model_arch": "omikuji"}],
 "keywords": [{"entity_type": "Teemamärksõnad",
               "keyword": "ülestõusmispühad",
               "model_arch": "omikuji",
               "score": 1.0},
              {"entity_type": "Teemamärksõnad",
               "keyword": "kombed",
               "model_arch": "omikuji",
               "score": 0.296},
              {"entity_type": "Teemamärksõnad",
               "keyword": "kirikukalendrid",
               "model_arch": "omikuji",
               "score": 0.218},
              {"entity_type": "Teemamärksõnad",
               "keyword": "munad",
               "model_arch": "omikuji",
               "score": 0.207},
              {"entity_type": "Teemamärksõnad",
               "keyword": "kirikupühad",
               "model_arch": "omikuji",
               "score": 0.163},
              {"entity_type": "Teemamärksõnad",
               "keyword": "easter",
               "model_arch": "rakun",
               "score": 0.118},
              {"entity_type": "Teemamärksõnad",
               "keyword": "egg",
               "model_arch": "rakun",
               "score": 0.095},
              {"entity_type": "Teemamärksõnad",
               "keyword": "holiday",
               "model_arch": "rakun",
               "score": 0.071},
              {"entity_type": "Teemamärksõnad",
               "keyword": "also",
               "model_arch": "rakun",
               "score": 0.042},
              {"entity_type": "Teemamärksõnad",
               "keyword": "swing",
               "model_arch": "rakun",
               "score": 0.038},
              {"count": 4,
               "entity_type": "Kohamärksõnad",
               "keyword": "Estonia",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 14,
               "entity_type": "Ajutine kollektiiv või sündmus",
               "keyword": "Easter Sunday",
               "method": "gliner",
               "model_arch": "ner",
               "score": 1.0},
              {"entity_type": "UDK Rahvusbibliograafia",
               "keyword": "39",
               "model_arch": "omikuji",
               "score": 0.76},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "ETNOLOOGIA. KULTUURIANTROPOLOOGIA",
               "model_arch": "omikuji",
               "score": 1.0},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "RELIGIOON. TEOLOOGIA. ESOTEERIKA",
               "model_arch": "omikuji",
               "score": 0.99},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "KODUMAJANDUS. TOITLUSTUS. TOIDUAINETETÖÖSTUS. OLME",
               "model_arch": "omikuji",
               "score": 0.911}]}
```

</details>

#### Russian input text

```python
from rara_subject_indexer.rara_indexer import RaraSubjectIndexer
from pprint import pprint

# If this is your first usage, download relevant models:
# NB! This has to be done only once!
# RaraSubjectIndexer.download_resources()

# Initialize the instance with default configuration
rara_indexer = RaraSubjectIndexer()

subject_indices = rara_indexer.apply_indexers(text=TEXT_RU)
pprint(subject_indices)
```

<details><summary>Output</summary>
    
`InvalidLanguageException: The text appears to be in language 'ru', which is not supported. Supported languages are: ['et', 'en'].`

</details>

### Modify thresholds


```python
from rara_subject_indexer.rara_indexer import RaraSubjectIndexer
from pprint import pprint

# If this is your first usage, download relevant models:
# NB! This has to be done only once!
RaraSubjectIndexer.download_resources()

# Initialize the instance with default configuration
rara_indexer = RaraSubjectIndexer()

# Change ensemble strategy for NER-based methods

ner_config = {"ensemble_strategy": "union"}

# Change min_score threshold for 
# keyword_type="Teemamärksõnad", method = "rakun"
threshold_config = {
    "Teemamärksõnad": {
        "rakun": {"min_score": 0.02}
    }
}

# max_count and min_score will overwrite
# thresholds for all keyword types in the default
# configuration, which are not specified
# with threshold_config

subject_indices = rara_indexer.apply_indexers(
    text=TEXT_ET,
    threshold_config=threshold_config,
    max_count=10,
    min_score=0.1,
    ner_config=ner_config
)
pprint(subject_indices)
```

<details><summary>Output</summary>
    
```json
{"durations": [{"duration": 0.03303,
                "keyword_type": "Teemamärksõnad",
                "model_arch": "omikuji"},
               {"duration": 1.79884,
                "keyword_type": "Teemamärksõnad",
                "model_arch": "rakun"},
               {"duration": 0.00897,
                "keyword_type": "Ajamärksõnad",
                "model_arch": "omikuji"},
               {"duration": 0.01052,
                "keyword_type": "Vormimärksõnad",
                "model_arch": "omikuji"},
               {"duration": 0.00057,
                "keyword_type": "NER",
                "model_arch": "ner"},
               {"duration": 0.0082,
                "keyword_type": "UDK Rahvusbibliograafia",
                "model_arch": "omikuji"},
               {"duration": 0.01001,
                "keyword_type": "UDC Summary",
                "model_arch": "omikuji"},
               {"duration": 0.00709,
                "keyword_type": "Valdkonnamärksõnad",
                "model_arch": "omikuji"}],
 "keywords": [{"entity_type": "Teemamärksõnad",
               "keyword": "filmid (teosed)",
               "model_arch": "omikuji",
               "score": 0.979},
              {"entity_type": "Teemamärksõnad",
               "keyword": "mängufilmid",
               "model_arch": "omikuji",
               "score": 0.573},
              {"entity_type": "Teemamärksõnad",
               "keyword": "filmiauhinnad",
               "model_arch": "omikuji",
               "score": 0.164},
              {"entity_type": "Teemamärksõnad",
               "keyword": "film",
               "model_arch": "rakun",
               "score": 0.32},
              {"entity_type": "Teemamärksõnad",
               "keyword": "ameeriklane",
               "model_arch": "rakun",
               "score": 0.039},
              {"entity_type": "Teemamärksõnad",
               "keyword": "metsatulekahju",
               "model_arch": "rakun",
               "score": 0.025},
              {"entity_type": "Teemamärksõnad",
               "keyword": "kostüümidisain",
               "model_arch": "rakun",
               "score": 0.025},
              {"entity_type": "Teemamärksõnad",
               "keyword": "austusavaldus",
               "model_arch": "rakun",
               "score": 0.023},
              {"entity_type": "Vormimärksõnad",
               "keyword": "filmiarvustused",
               "model_arch": "omikuji",
               "score": 0.905},
              {"entity_type": "Vormimärksõnad",
               "keyword": "e-raamatud",
               "model_arch": "omikuji",
               "score": 0.104},
              {"count": 12,
               "entity_type": "Isikunimi",
               "keyword": "Emilia Perez",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 3,
               "entity_type": "Isikunimi",
               "keyword": "Sean Baker",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 0.25},
              {"count": 3,
               "entity_type": "Isikunimi",
               "keyword": "Conan O'Brien",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 0.25},
              {"count": 3,
               "entity_type": "Kollektiivi nimi",
               "keyword": "Läti",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 3,
               "entity_type": "Kollektiivi nimi",
               "keyword": "Anora",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 4,
               "entity_type": "Kohamärksõnad",
               "keyword": "Los Angeleses",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 4,
               "entity_type": "Kohamärksõnad",
               "keyword": "Los",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 3,
               "entity_type": "Kohamärksõnad",
               "keyword": "Läti",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 0.75},
              {"count": 3,
               "entity_type": "Kohamärksõnad",
               "keyword": "Angeleses",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 0.75},
              {"count": 3,
               "entity_type": "Kohamärksõnad",
               "keyword": "Ameerika",
               "method": "ner_ensemble",
               "model_arch": "ner",
               "score": 0.75},
              {"count": 5,
               "entity_type": "Teose pealkiri",
               "keyword": "Wicked",
               "method": "gliner",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 5,
               "entity_type": "Teose pealkiri",
               "keyword": "Brutalist",
               "method": "gliner",
               "model_arch": "ner",
               "score": 1.0},
              {"count": 4,
               "entity_type": "Teose pealkiri",
               "keyword": "Anora",
               "method": "gliner",
               "model_arch": "ner",
               "score": 0.8},
              {"count": 3,
               "entity_type": "Teose pealkiri",
               "keyword": "Nosferatu",
               "method": "gliner",
               "model_arch": "ner",
               "score": 0.6},
              {"count": 3,
               "entity_type": "Teose pealkiri",
               "keyword": "Vooluga kaasa",
               "method": "gliner",
               "model_arch": "ner",
               "score": 0.6},
              {"entity_type": "UDK Rahvusbibliograafia",
               "keyword": "791",
               "model_arch": "omikuji",
               "score": 1.0},
              {"entity_type": "UDC Summary",
               "keyword": "821.111",
               "model_arch": "omikuji",
               "score": 0.156},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "FOTOGRAAFIA. FILM. KINO",
               "model_arch": "omikuji",
               "score": 1.0},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "KOHANIMED",
               "model_arch": "omikuji",
               "score": 0.944},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "AJAKIRJANDUS. KOMMUNIKATSIOON. MEEDIA. REKLAAM",
               "model_arch": "omikuji",
               "score": 0.449},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "TÖÖTINGIMUSED. TÖÖHÕIVE. AMETID",
               "model_arch": "omikuji",
               "score": 0.324},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "INFORMAATIKA. INFOTEHNOLOOGIA. AUTOMAATIKA",
               "model_arch": "omikuji",
               "score": 0.181},
              {"entity_type": "Valdkonnamärksõnad",
               "keyword": "TEATER. TANTS",
               "model_arch": "omikuji",
               "score": 0.154}]}    
```
</details>
    

</details>
