pax_global_header00006660000000000000000000000064147277765540014542gustar00rootroot0000000000000052 comment=688c2afe4e6180e903763e20c596e651cb7e15da LanguageMachines-ucto-688c2af/000077500000000000000000000000001472777655400163305ustar00rootroot00000000000000LanguageMachines-ucto-688c2af/.dockerignore000066400000000000000000000001241472777655400210010ustar00rootroot00000000000000.git .cache .* _* *.cache *.pyc build *.egg-info gource* *.tar.gz *.pdf TODO *.lock LanguageMachines-ucto-688c2af/.github/000077500000000000000000000000001472777655400176705ustar00rootroot00000000000000LanguageMachines-ucto-688c2af/.github/workflows/000077500000000000000000000000001472777655400217255ustar00rootroot00000000000000LanguageMachines-ucto-688c2af/.github/workflows/badge.svg000066400000000000000000000061641472777655400235170ustar00rootroot00000000000000 LanguageMachines-ucto-688c2af/.github/workflows/cleanup.yml000066400000000000000000000007241472777655400241020ustar00rootroot00000000000000--- name: Delete old workflow runs on: schedule: - cron: '0 15 14 * *' # Run monthly, at 15:00 on the 14t day of month. (testing) jobs: del_runs: runs-on: ubuntu-latest permissions: actions: write steps: - name: Delete workflow runs uses: Mattraks/delete-workflow-runs@v2 with: token: ${{ github.token }} repository: ${{ github.repository }} retain_days: 30 keep_minimum_runs: 6 LanguageMachines-ucto-688c2af/.github/workflows/ucto.yml000066400000000000000000000053651472777655400234330ustar00rootroot00000000000000--- name: C/C++ CI on: push: branches: - master - develop paths: - 'src/**' - 'include/**' - '.github/**' - 'tests/**' - configure.ac - Makefile.am pull_request: branches: [master] jobs: notification: runs-on: ubuntu-latest name: Notify start to IRC gitlama steps: - name: IRC notification uses: LanguageMachines/ticcactions/irc-init@v1 - name: Cancel Previous Runs uses: styfle/cancel-workflow-action@0.12.1 with: access_token: ${{ github.token }} build: runs-on: ${{ matrix.os }} needs: notification strategy: matrix: os: [ubuntu-latest, macos-latest] compiler: [g++-12, clang++] steps: - uses: actions/checkout@v4.1.1 - uses: LanguageMachines/ticcactions/cpp-build-env@v1 - uses: LanguageMachines/ticcactions/cpp-dependencies@v1 - uses: LanguageMachines/ticcactions/irc-nick@v1 - uses: LanguageMachines/ticcactions/cpp-submodule-build@v1 with: branch: ${{ github.ref_name }} module: ticcutils - uses: LanguageMachines/ticcactions/cpp-submodule-build@v1 with: branch: ${{ github.ref_name }} module: libfolia - uses: LanguageMachines/ticcactions/cpp-submodule-build@v1 with: module: uctodata - uses: LanguageMachines/ticcactions/setup-cppcheck@v1 - name: Static Code-check if: ${{ env.action_status == '' }} run: cppcheck ${{ env.cpc_opts }} . - name: install libexttextcat uses: LanguageMachines/ticcactions/add-textcat@v1 - uses: LanguageMachines/ticcactions/cpp-safe-build@v1 - name: Notify IRC of build results uses: LanguageMachines/ticcactions/irc-status@v1 with: branch: ${{ github.ref_name }} nickname: ${{ env.nick }} status: ${{ env.action_status }} details: ${{ env.action_details }} continue-on-error: true - name: run uctotests if: ${{ env.action_status == '' }} env: EXPECT: 0 LD_LIBRARY_PATH: $LD_LIBRARY_PATH:/usr/local/lib run: | cd tests ./testaction.sh TEST_STAT=$(cat status.tmp) if [ $TEST_STAT != 0 ] then echo "action_status=uctotests" >> $GITHUB_ENV fi echo "action_details=$TEST_STAT errors" >> $GITHUB_ENV continue-on-error: true - name: Notify IRC of results uses: LanguageMachines/ticcactions/irc-status@v1 with: branch: ${{ github.ref_name }} nickname: ${{ env.nick }} step: testing status: ${{ env.action_status }} details: ${{ env.action_details }} LanguageMachines-ucto-688c2af/.gitignore000066400000000000000000000032641472777655400203250ustar00rootroot00000000000000INSTALL ChangeLog *.tar.gz Makefile Makefile.in aclocal.m4 autom4te.cache/ compile config.guess config.h config.h.in config.log config.status config.sub config/Makefile config/Makefile.in configure depcomp docs/Makefile docs/Makefile.in docs/build include/Makefile include/Makefile.in include/ucto/Makefile include/ucto/Makefile.in install-sh libtool ltmain.sh m4/Makefile m4/Makefile.in m4/libtool.m4 m4/ltoptions.m4 m4/ltsugar.m4 m4/ltversion.m4 m4/lt~obsolete.m4 m4/pkg.m4 m4/ax_lib_readline.m4 missing src/.deps/ src/.libs/ src/Makefile src/Makefile.in src/*.la src/*.lo src/*.o src/test-suite.log src/tst.out src/tst.sh.log src/tst.sh.trs src/ucto stamp-h1 test-driver tests/Makefile tests/Makefile.in tests/testoutput/ ucto-icu.pc ucto.pc ### macOS ### # General .DS_Store .AppleDouble .LSOverride # Thumbnails ._* ### Vim ### # Swap [._]*.s[a-v][a-z] [._]*.sw[a-p] [._]s[a-rt-v][a-z] [._]ss[a-gi-z] [._]sw[a-p] # Temporary .netrwhist *~ # Auto-generated tag files tags # Persistent undo [._]*.un~ #emacs \#*\# /.emacs.desktop /.emacs.desktop.lock *.elc auto-save-list tramp .\#* ### LaTeX ### ## Core latex/pdflatex auxiliary files: *.aux *.lof *.log *.lot *.fls *.out *.toc *.fmt *.fot *.cb *.cb2 .*.lb ## Bibliography auxiliary files (bibtex/biblatex/biber): *.bbl *.bcf *.blg *-blx.aux *-blx.bib *.run.xml ### Python ### __pycache__/ *.py[cod] *$py.class # Environments .env .venv env/ venv/ ENV/ env.bak/ venv.bak/ ### C++ ### # Prerequisites *.d # Compiled Object files *.slo *.lo *.o *.obj # Precompiled Headers *.gch *.pch # Compiled Dynamic libraries *.so *.dylib *.dll # Fortran module files *.mod *.smod # Compiled Static libraries *.lai *.la *.a *.lib # Executables *.exe *.app LanguageMachines-ucto-688c2af/AUTHORS000066400000000000000000000001041472777655400173730ustar00rootroot00000000000000Maarten van Gompel Ko van der Sloot Folgert Karsdorp Iris Hendrickx LanguageMachines-ucto-688c2af/COPYING000066400000000000000000001045131472777655400173670ustar00rootroot00000000000000 GNU GENERAL PUBLIC LICENSE Version 3, 29 June 2007 Copyright (C) 2007 Free Software Foundation, Inc. Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The GNU General Public License is a free, copyleft license for software and other kinds of works. The licenses for most software and other practical works are designed to take away your freedom to share and change the works. By contrast, the GNU General Public License is intended to guarantee your freedom to share and change all versions of a program--to make sure it remains free software for all its users. We, the Free Software Foundation, use the GNU General Public License for most of our software; it applies also to any other work released this way by its authors. You can apply it to your programs, too. When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for them if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs, and that you know you can do these things. To protect your rights, we need to prevent others from denying you these rights or asking you to surrender the rights. Therefore, you have certain responsibilities if you distribute copies of the software, or if you modify it: responsibilities to respect the freedom of others. For example, if you distribute copies of such a program, whether gratis or for a fee, you must pass on to the recipients the same freedoms that you received. You must make sure that they, too, receive or can get the source code. And you must show them these terms so they know their rights. Developers that use the GNU GPL protect your rights with two steps: (1) assert copyright on the software, and (2) offer you this License giving you legal permission to copy, distribute and/or modify it. For the developers' and authors' protection, the GPL clearly explains that there is no warranty for this free software. For both users' and authors' sake, the GPL requires that modified versions be marked as changed, so that their problems will not be attributed erroneously to authors of previous versions. Some devices are designed to deny users access to install or run modified versions of the software inside them, although the manufacturer can do so. This is fundamentally incompatible with the aim of protecting users' freedom to change the software. The systematic pattern of such abuse occurs in the area of products for individuals to use, which is precisely where it is most unacceptable. Therefore, we have designed this version of the GPL to prohibit the practice for those products. If such problems arise substantially in other domains, we stand ready to extend this provision to those domains in future versions of the GPL, as needed to protect the freedom of users. Finally, every program is threatened constantly by software patents. States should not allow patents to restrict development and use of software on general-purpose computers, but in those that do, we wish to avoid the special danger that patents applied to a free program could make it effectively proprietary. To prevent this, the GPL assures that patents cannot be used to render the program non-free. The precise terms and conditions for copying, distribution and modification follow. TERMS AND CONDITIONS 0. Definitions. "This License" refers to version 3 of the GNU General Public License. "Copyright" also means copyright-like laws that apply to other kinds of works, such as semiconductor masks. "The Program" refers to any copyrightable work licensed under this License. Each licensee is addressed as "you". "Licensees" and "recipients" may be individuals or organizations. To "modify" a work means to copy from or adapt all or part of the work in a fashion requiring copyright permission, other than the making of an exact copy. The resulting work is called a "modified version" of the earlier work or a work "based on" the earlier work. A "covered work" means either the unmodified Program or a work based on the Program. To "propagate" a work means to do anything with it that, without permission, would make you directly or secondarily liable for infringement under applicable copyright law, except executing it on a computer or modifying a private copy. Propagation includes copying, distribution (with or without modification), making available to the public, and in some countries other activities as well. To "convey" a work means any kind of propagation that enables other parties to make or receive copies. Mere interaction with a user through a computer network, with no transfer of a copy, is not conveying. An interactive user interface displays "Appropriate Legal Notices" to the extent that it includes a convenient and prominently visible feature that (1) displays an appropriate copyright notice, and (2) tells the user that there is no warranty for the work (except to the extent that warranties are provided), that licensees may convey the work under this License, and how to view a copy of this License. If the interface presents a list of user commands or options, such as a menu, a prominent item in the list meets this criterion. 1. Source Code. The "source code" for a work means the preferred form of the work for making modifications to it. "Object code" means any non-source form of a work. A "Standard Interface" means an interface that either is an official standard defined by a recognized standards body, or, in the case of interfaces specified for a particular programming language, one that is widely used among developers working in that language. The "System Libraries" of an executable work include anything, other than the work as a whole, that (a) is included in the normal form of packaging a Major Component, but which is not part of that Major Component, and (b) serves only to enable use of the work with that Major Component, or to implement a Standard Interface for which an implementation is available to the public in source code form. A "Major Component", in this context, means a major essential component (kernel, window system, and so on) of the specific operating system (if any) on which the executable work runs, or a compiler used to produce the work, or an object code interpreter used to run it. The "Corresponding Source" for a work in object code form means all the source code needed to generate, install, and (for an executable work) run the object code and to modify the work, including scripts to control those activities. However, it does not include the work's System Libraries, or general-purpose tools or generally available free programs which are used unmodified in performing those activities but which are not part of the work. For example, Corresponding Source includes interface definition files associated with source files for the work, and the source code for shared libraries and dynamically linked subprograms that the work is specifically designed to require, such as by intimate data communication or control flow between those subprograms and other parts of the work. The Corresponding Source need not include anything that users can regenerate automatically from other parts of the Corresponding Source. The Corresponding Source for a work in source code form is that same work. 2. Basic Permissions. All rights granted under this License are granted for the term of copyright on the Program, and are irrevocable provided the stated conditions are met. This License explicitly affirms your unlimited permission to run the unmodified Program. The output from running a covered work is covered by this License only if the output, given its content, constitutes a covered work. This License acknowledges your rights of fair use or other equivalent, as provided by copyright law. You may make, run and propagate covered works that you do not convey, without conditions so long as your license otherwise remains in force. You may convey covered works to others for the sole purpose of having them make modifications exclusively for you, or provide you with facilities for running those works, provided that you comply with the terms of this License in conveying all material for which you do not control copyright. Those thus making or running the covered works for you must do so exclusively on your behalf, under your direction and control, on terms that prohibit them from making any copies of your copyrighted material outside their relationship with you. Conveying under any other circumstances is permitted solely under the conditions stated below. Sublicensing is not allowed; section 10 makes it unnecessary. 3. Protecting Users' Legal Rights From Anti-Circumvention Law. No covered work shall be deemed part of an effective technological measure under any applicable law fulfilling obligations under article 11 of the WIPO copyright treaty adopted on 20 December 1996, or similar laws prohibiting or restricting circumvention of such measures. When you convey a covered work, you waive any legal power to forbid circumvention of technological measures to the extent such circumvention is effected by exercising rights under this License with respect to the covered work, and you disclaim any intention to limit operation or modification of the work as a means of enforcing, against the work's users, your or third parties' legal rights to forbid circumvention of technological measures. 4. Conveying Verbatim Copies. You may convey verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice; keep intact all notices stating that this License and any non-permissive terms added in accord with section 7 apply to the code; keep intact all notices of the absence of any warranty; and give all recipients a copy of this License along with the Program. You may charge any price or no price for each copy that you convey, and you may offer support or warranty protection for a fee. 5. Conveying Modified Source Versions. You may convey a work based on the Program, or the modifications to produce it from the Program, in the form of source code under the terms of section 4, provided that you also meet all of these conditions: a) The work must carry prominent notices stating that you modified it, and giving a relevant date. b) The work must carry prominent notices stating that it is released under this License and any conditions added under section 7. This requirement modifies the requirement in section 4 to "keep intact all notices". c) You must license the entire work, as a whole, under this License to anyone who comes into possession of a copy. This License will therefore apply, along with any applicable section 7 additional terms, to the whole of the work, and all its parts, regardless of how they are packaged. This License gives no permission to license the work in any other way, but it does not invalidate such permission if you have separately received it. d) If the work has interactive user interfaces, each must display Appropriate Legal Notices; however, if the Program has interactive interfaces that do not display Appropriate Legal Notices, your work need not make them do so. A compilation of a covered work with other separate and independent works, which are not by their nature extensions of the covered work, and which are not combined with it such as to form a larger program, in or on a volume of a storage or distribution medium, is called an "aggregate" if the compilation and its resulting copyright are not used to limit the access or legal rights of the compilation's users beyond what the individual works permit. Inclusion of a covered work in an aggregate does not cause this License to apply to the other parts of the aggregate. 6. Conveying Non-Source Forms. You may convey a covered work in object code form under the terms of sections 4 and 5, provided that you also convey the machine-readable Corresponding Source under the terms of this License, in one of these ways: a) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by the Corresponding Source fixed on a durable physical medium customarily used for software interchange. b) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by a written offer, valid for at least three years and valid for as long as you offer spare parts or customer support for that product model, to give anyone who possesses the object code either (1) a copy of the Corresponding Source for all the software in the product that is covered by this License, on a durable physical medium customarily used for software interchange, for a price no more than your reasonable cost of physically performing this conveying of source, or (2) access to copy the Corresponding Source from a network server at no charge. c) Convey individual copies of the object code with a copy of the written offer to provide the Corresponding Source. This alternative is allowed only occasionally and noncommercially, and only if you received the object code with such an offer, in accord with subsection 6b. d) Convey the object code by offering access from a designated place (gratis or for a charge), and offer equivalent access to the Corresponding Source in the same way through the same place at no further charge. You need not require recipients to copy the Corresponding Source along with the object code. If the place to copy the object code is a network server, the Corresponding Source may be on a different server (operated by you or a third party) that supports equivalent copying facilities, provided you maintain clear directions next to the object code saying where to find the Corresponding Source. Regardless of what server hosts the Corresponding Source, you remain obligated to ensure that it is available for as long as needed to satisfy these requirements. e) Convey the object code using peer-to-peer transmission, provided you inform other peers where the object code and Corresponding Source of the work are being offered to the general public at no charge under subsection 6d. A separable portion of the object code, whose source code is excluded from the Corresponding Source as a System Library, need not be included in conveying the object code work. A "User Product" is either (1) a "consumer product", which means any tangible personal property which is normally used for personal, family, or household purposes, or (2) anything designed or sold for incorporation into a dwelling. In determining whether a product is a consumer product, doubtful cases shall be resolved in favor of coverage. For a particular product received by a particular user, "normally used" refers to a typical or common use of that class of product, regardless of the status of the particular user or of the way in which the particular user actually uses, or expects or is expected to use, the product. A product is a consumer product regardless of whether the product has substantial commercial, industrial or non-consumer uses, unless such uses represent the only significant mode of use of the product. "Installation Information" for a User Product means any methods, procedures, authorization keys, or other information required to install and execute modified versions of a covered work in that User Product from a modified version of its Corresponding Source. The information must suffice to ensure that the continued functioning of the modified object code is in no case prevented or interfered with solely because modification has been made. If you convey an object code work under this section in, or with, or specifically for use in, a User Product, and the conveying occurs as part of a transaction in which the right of possession and use of the User Product is transferred to the recipient in perpetuity or for a fixed term (regardless of how the transaction is characterized), the Corresponding Source conveyed under this section must be accompanied by the Installation Information. But this requirement does not apply if neither you nor any third party retains the ability to install modified object code on the User Product (for example, the work has been installed in ROM). The requirement to provide Installation Information does not include a requirement to continue to provide support service, warranty, or updates for a work that has been modified or installed by the recipient, or for the User Product in which it has been modified or installed. Access to a network may be denied when the modification itself materially and adversely affects the operation of the network or violates the rules and protocols for communication across the network. Corresponding Source conveyed, and Installation Information provided, in accord with this section must be in a format that is publicly documented (and with an implementation available to the public in source code form), and must require no special password or key for unpacking, reading or copying. 7. Additional Terms. "Additional permissions" are terms that supplement the terms of this License by making exceptions from one or more of its conditions. Additional permissions that are applicable to the entire Program shall be treated as though they were included in this License, to the extent that they are valid under applicable law. If additional permissions apply only to part of the Program, that part may be used separately under those permissions, but the entire Program remains governed by this License without regard to the additional permissions. When you convey a copy of a covered work, you may at your option remove any additional permissions from that copy, or from any part of it. (Additional permissions may be written to require their own removal in certain cases when you modify the work.) You may place additional permissions on material, added by you to a covered work, for which you have or can give appropriate copyright permission. Notwithstanding any other provision of this License, for material you add to a covered work, you may (if authorized by the copyright holders of that material) supplement the terms of this License with terms: a) Disclaiming warranty or limiting liability differently from the terms of sections 15 and 16 of this License; or b) Requiring preservation of specified reasonable legal notices or author attributions in that material or in the Appropriate Legal Notices displayed by works containing it; or c) Prohibiting misrepresentation of the origin of that material, or requiring that modified versions of such material be marked in reasonable ways as different from the original version; or d) Limiting the use for publicity purposes of names of licensors or authors of the material; or e) Declining to grant rights under trademark law for use of some trade names, trademarks, or service marks; or f) Requiring indemnification of licensors and authors of that material by anyone who conveys the material (or modified versions of it) with contractual assumptions of liability to the recipient, for any liability that these contractual assumptions directly impose on those licensors and authors. All other non-permissive additional terms are considered "further restrictions" within the meaning of section 10. If the Program as you received it, or any part of it, contains a notice stating that it is governed by this License along with a term that is a further restriction, you may remove that term. If a license document contains a further restriction but permits relicensing or conveying under this License, you may add to a covered work material governed by the terms of that license document, provided that the further restriction does not survive such relicensing or conveying. If you add terms to a covered work in accord with this section, you must place, in the relevant source files, a statement of the additional terms that apply to those files, or a notice indicating where to find the applicable terms. Additional terms, permissive or non-permissive, may be stated in the form of a separately written license, or stated as exceptions; the above requirements apply either way. 8. Termination. You may not propagate or modify a covered work except as expressly provided under this License. Any attempt otherwise to propagate or modify it is void, and will automatically terminate your rights under this License (including any patent licenses granted under the third paragraph of section 11). However, if you cease all violation of this License, then your license from a particular copyright holder is reinstated (a) provisionally, unless and until the copyright holder explicitly and finally terminates your license, and (b) permanently, if the copyright holder fails to notify you of the violation by some reasonable means prior to 60 days after the cessation. Moreover, your license from a particular copyright holder is reinstated permanently if the copyright holder notifies you of the violation by some reasonable means, this is the first time you have received notice of violation of this License (for any work) from that copyright holder, and you cure the violation prior to 30 days after your receipt of the notice. Termination of your rights under this section does not terminate the licenses of parties who have received copies or rights from you under this License. If your rights have been terminated and not permanently reinstated, you do not qualify to receive new licenses for the same material under section 10. 9. Acceptance Not Required for Having Copies. You are not required to accept this License in order to receive or run a copy of the Program. Ancillary propagation of a covered work occurring solely as a consequence of using peer-to-peer transmission to receive a copy likewise does not require acceptance. However, nothing other than this License grants you permission to propagate or modify any covered work. These actions infringe copyright if you do not accept this License. Therefore, by modifying or propagating a covered work, you indicate your acceptance of this License to do so. 10. Automatic Licensing of Downstream Recipients. Each time you convey a covered work, the recipient automatically receives a license from the original licensors, to run, modify and propagate that work, subject to this License. You are not responsible for enforcing compliance by third parties with this License. An "entity transaction" is a transaction transferring control of an organization, or substantially all assets of one, or subdividing an organization, or merging organizations. If propagation of a covered work results from an entity transaction, each party to that transaction who receives a copy of the work also receives whatever licenses to the work the party's predecessor in interest had or could give under the previous paragraph, plus a right to possession of the Corresponding Source of the work from the predecessor in interest, if the predecessor has it or can get it with reasonable efforts. You may not impose any further restrictions on the exercise of the rights granted or affirmed under this License. For example, you may not impose a license fee, royalty, or other charge for exercise of rights granted under this License, and you may not initiate litigation (including a cross-claim or counterclaim in a lawsuit) alleging that any patent claim is infringed by making, using, selling, offering for sale, or importing the Program or any portion of it. 11. Patents. A "contributor" is a copyright holder who authorizes use under this License of the Program or a work on which the Program is based. The work thus licensed is called the contributor's "contributor version". A contributor's "essential patent claims" are all patent claims owned or controlled by the contributor, whether already acquired or hereafter acquired, that would be infringed by some manner, permitted by this License, of making, using, or selling its contributor version, but do not include claims that would be infringed only as a consequence of further modification of the contributor version. For purposes of this definition, "control" includes the right to grant patent sublicenses in a manner consistent with the requirements of this License. Each contributor grants you a non-exclusive, worldwide, royalty-free patent license under the contributor's essential patent claims, to make, use, sell, offer for sale, import and otherwise run, modify and propagate the contents of its contributor version. In the following three paragraphs, a "patent license" is any express agreement or commitment, however denominated, not to enforce a patent (such as an express permission to practice a patent or covenant not to sue for patent infringement). To "grant" such a patent license to a party means to make such an agreement or commitment not to enforce a patent against the party. If you convey a covered work, knowingly relying on a patent license, and the Corresponding Source of the work is not available for anyone to copy, free of charge and under the terms of this License, through a publicly available network server or other readily accessible means, then you must either (1) cause the Corresponding Source to be so available, or (2) arrange to deprive yourself of the benefit of the patent license for this particular work, or (3) arrange, in a manner consistent with the requirements of this License, to extend the patent license to downstream recipients. "Knowingly relying" means you have actual knowledge that, but for the patent license, your conveying the covered work in a country, or your recipient's use of the covered work in a country, would infringe one or more identifiable patents in that country that you have reason to believe are valid. If, pursuant to or in connection with a single transaction or arrangement, you convey, or propagate by procuring conveyance of, a covered work, and grant a patent license to some of the parties receiving the covered work authorizing them to use, propagate, modify or convey a specific copy of the covered work, then the patent license you grant is automatically extended to all recipients of the covered work and works based on it. A patent license is "discriminatory" if it does not include within the scope of its coverage, prohibits the exercise of, or is conditioned on the non-exercise of one or more of the rights that are specifically granted under this License. You may not convey a covered work if you are a party to an arrangement with a third party that is in the business of distributing software, under which you make payment to the third party based on the extent of your activity of conveying the work, and under which the third party grants, to any of the parties who would receive the covered work from you, a discriminatory patent license (a) in connection with copies of the covered work conveyed by you (or copies made from those copies), or (b) primarily for and in connection with specific products or compilations that contain the covered work, unless you entered into that arrangement, or that patent license was granted, prior to 28 March 2007. Nothing in this License shall be construed as excluding or limiting any implied license or other defenses to infringement that may otherwise be available to you under applicable patent law. 12. No Surrender of Others' Freedom. If conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot convey a covered work so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not convey it at all. For example, if you agree to terms that obligate you to collect a royalty for further conveying from those to whom you convey the Program, the only way you could satisfy both those terms and this License would be to refrain entirely from conveying the Program. 13. Use with the GNU Affero General Public License. Notwithstanding any other provision of this License, you have permission to link or combine any covered work with a work licensed under version 3 of the GNU Affero General Public License into a single combined work, and to convey the resulting work. The terms of this License will continue to apply to the part which is the covered work, but the special requirements of the GNU Affero General Public License, section 13, concerning interaction through a network will apply to the combination as such. 14. Revised Versions of this License. The Free Software Foundation may publish revised and/or new versions of the GNU General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Program specifies that a certain numbered version of the GNU General Public License "or any later version" applies to it, you have the option of following the terms and conditions either of that numbered version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of the GNU General Public License, you may choose any version ever published by the Free Software Foundation. If the Program specifies that a proxy can decide which future versions of the GNU General Public License can be used, that proxy's public statement of acceptance of a version permanently authorizes you to choose that version for the Program. Later license versions may give you additional or different permissions. However, no additional obligations are imposed on any author or copyright holder as a result of your choosing to follow a later version. 15. Disclaimer of Warranty. THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 16. Limitation of Liability. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. 17. Interpretation of Sections 15 and 16. If the disclaimer of warranty and limitation of liability provided above cannot be given local legal effect according to their terms, reviewing courts shall apply local law that most closely approximates an absolute waiver of all civil liability in connection with the Program, unless a warranty or assumption of liability accompanies a copy of the Program in return for a fee. END OF TERMS AND CONDITIONS How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively state the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program. If not, see . Also add information on how to contact you by electronic and paper mail. If the program does terminal interaction, make it output a short notice like this when it starts in an interactive mode: Copyright (C) This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details. The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, your program's commands might be different; for a GUI interface, you would use an "about box". You should also get your employer (if you work as a programmer) or school, if any, to sign a "copyright disclaimer" for the program, if necessary. For more information on this, and how to apply and follow the GNU GPL, see . The GNU General Public License does not permit incorporating your program into proprietary programs. If your program is a subroutine library, you may consider it more useful to permit linking proprietary applications with the library. If this is what you want to do, use the GNU Lesser General Public License instead of this License. But first, please read . LanguageMachines-ucto-688c2af/Dockerfile000066400000000000000000000027001472777655400203210ustar00rootroot00000000000000FROM alpine:latest #VERSION can be: # - stable: builds latest stable versions from source (default) # - distro: uses packages as provided by Alpine Linux (may be slightly out of date) # - devel: latest development version (git master/main branch) ARG VERSION="stable" LABEL org.opencontainers.image.authors="Maarten van Gompel " LABEL description="Ucto, rule-based tokenizer" RUN mkdir -p /data RUN mkdir -p /usr/src/ucto COPY . /usr/src/ucto RUN if [ "$VERSION" = "distro" ]; then \ rm -Rf /usr/src/ucto &&\ echo -e "----------------------------------------------------------\nNOTE: Installing latest release as provided by Alpine package manager.\nThis version may diverge from the one in the git master tree or even from the latest release on github!\nFor development, build with --build-arg VERSION=development.\n----------------------------------------------------------\n" &&\ apk update && apk add ucto; \ else \ PACKAGES="libbz2 icu-libs libxml2 libexttextcat libgomp libstdc++" &&\ BUILD_PACKAGES="build-base autoconf-archive autoconf automake libtool bzip2-dev icu-dev libxml2-dev libexttextcat-dev git" &&\ apk add $PACKAGES $BUILD_PACKAGES &&\ cd /usr/src/ && ./ucto/build-deps.sh &&\ cd ucto && sh ./bootstrap.sh && ./configure && make && make install &&\ apk del $BUILD_PACKAGES && rm -Rf /usr/src; \ fi WORKDIR /data VOLUME /data ENTRYPOINT [ "ucto" ] LanguageMachines-ucto-688c2af/MAINTAINERS000066400000000000000000000001551472777655400200260ustar00rootroot00000000000000Maarten van Gompel (KNAW Humanities Cluster) Ko van der Sloot LanguageMachines-ucto-688c2af/Makefile.am000066400000000000000000000006431472777655400203670ustar00rootroot00000000000000ACLOCAL_AMFLAGS = -I m4 --install SUBDIRS = src include m4 config docs tests EXTRA_DIST = bootstrap.sh AUTHORS TODO NEWS README.md ucto.pc.in ucto-icu.pc.in codemeta.json pkgconfigdir = $(libdir)/pkgconfig pkgconfig_DATA = ucto.pc ChangeLog: NEWS git pull; git2cl > ChangeLog docker: docker build -t ucto:latest . docker-dev: docker build -t ucto:dev --build-arg VERSION=development . deps: ./build-deps.sh LanguageMachines-ucto-688c2af/NEWS000066400000000000000000000466551472777655400170470ustar00rootroot000000000000000.35 2024-12-16 [Ko van der Sloot] * require latest ticcutils * updated GitHub CI 0.34 2024-09-12 [Maarten van Gompel] * fall back when local config dir can not be checked for whatever reason https://github.com/LanguageMachines/ucto/issues/97 * extract custom configuration directory if provided, and fall back to that for includes https://github.com/LanguageMachines/ucto/issues/96 * needs ticcutils >= 0.35 [Ko van der Sloot] * force use of c++17 * minor code updates * streamlined Github CI file * adapted some foliatests to recent libfolia versions * refactored tests: - all shell scripts have the .sh extension now - use folialint or foliadiff to check folia results 0.33 2024-04-26 [Ko van der Sloot] * added a batch mode: https://github.com/LanguageMachines/ucto/issues/94 * improved handling of NonSpacing markers. * adapted some tests, based on the newest uctodata package (notably French was not correct implemented) 0.32.1 2024-03-20 [Ko van der Sloot] * additional fix for https://github.com/LanguageMachines/ucto/issues/93 0.32 2024-03-19 [Ko van der Sloot] * fix for https://github.com/LanguageMachines/ucto/issues/95 * automagicly geneate an xml:id when not provided 0.31 2024-02-28 [Ko van der Sloot] * fixed handling of the rare cases of Unidentifiable Characters They were ignored, which lead to incompatible text elements in FoLiA * some small refactoring, rooting out CppCheck warnings 0.30 2023-10-21 [Ko van der Sloot] * using ticcutils >- 0.34. All Unicode id NFC normalized now * normalization performed for passthru too. All output should be in the same encoding (NFC) * fixed a problem when using the API form Frog * improving code quality * added (dangerous, and compiletime only) option to change the magic 'tokconfig-' value. [Maarten van Gompel] * README.md: README: added demo screencast 0.29 2023-04-22 [Ko van der Sloot] * fixes for https://github.com/proycon/python-ucto/issues/16 * added a new --copyclass option, (see comments in https://github.com/LanguageMachines/ucto/issues/68) * updated man page 0.28.1 2023-02-22 [Maarten van Gompel] * Software metadata update only, no functional changes 0.28 2023-02-21 [Ko van der Sloot] * Made sure that TextCat is not initialized when not needed * Sentences inside quotes got an inconsistent xml:id (Not invalid though) * Separated Debug en Log streams. * C++ Code quality improved 0.27 2023-01-23 [Ko van der Sloot] * removed dependency on libtar * fixed build when HAVE_TEXTCAT was not set. Improved guards agains missing textcat support [Maarten van Gompel] * guard against uninitialized/missing textcat (https://github.com/proycon/python-frog#22) * require latest libfolia, ticcutils and a more recent libxml2 0.26 2023-01-02 [Ko van der Sloot] * some code quality improvements * fix for https://github.com/LanguageMachines/ucto/issues/89 * updated configure.ac * updated GitHub action [Maarten van Gompel] * Added MAINTAINERS * updated codemeta.json * fix for https://github.com/fbkarsdorp/homebrew-lamachine/issues/17 0.25 2022-07-22 [Ko van der Sloot] * Added a test for https://github.com/LanguageMachines/ucto/issues/87 * Adapted to latest update in tokconfig-fra (uctodata 0.9) * Deal with unknown languages (as detected by ucto), using iso-639-3 'und' (https://github.com/LanguageMachines/ucto/issues/86) * don't tokenize unknown languages * configurable sentence splitter for "und" text * added tests * added code to set the separator (--seperators), so ucto can split on more than just spaces * migrated test wrapper to Python 3 (was still on 2.7) [Maarten van Gompel] * Set up a Dockerfile * Added build-deps.sh to automatically download, build and install dependencies * Updated software metadata (codemeta.json) to latest requirements as proposed in CLARIAH * deprecated options -f and -x, still works but no longer advertised and gives a deprecation notice (https://github.com/LanguageMachines/ucto/issues/88) * textcat.cfg is now searched for in user config dir as well as global config; also allow running without textcat if the config is missing entirely (same as if not compiled in) * added support for user-based configuration dirs ($XDG_CONFIG_HOME/ucto), takes precedence over global data dirs 0.24.1 2021-12-17 [Ko van der Sloot] * added UTF8 members to the API, to replace the variants that were converted to UnicodeString This should help fixing https://github.com/proycon/python-ucto/issues/11 0.24 2021-12-15 [Ko vd Sloot] * fix for https://github.com/LanguageMachines/ucto/issues/84 * added a solution for https://github.com/LanguageMachines/ucto/issues/53 (only partly) * added some UnicodeString members to the API * bumped library version to 6.0, because of API changes * code cleanup and refactoring 0.23 2021-07-12 [Ko vd Sloot] * added support for the new 'tag' feature in FoLiA, only for tag="token" * fixed a problem with '-T full' option not always adding text * use the new TextPolicy class from libfolia * fix for https://github.com/LanguageMachines/ucto/issues/81 * fix for https://github.com/LanguageMachines/ucto/issues/82 * added code to handle several Unicode joiners * replaced TravisCI by GutHub action * %include files may have an extension now * added tests for new features 0.22 2020-10-08 [Ko van der Sloot] * fix for https://github.com/LanguageMachines/ucto/issues/79 0.21.1 2020-04-15 [Ko van der Sloot] * fix for https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=941498 0.21 2020-04-15 [Ko van der Sloot] * Adapted to newest libfolia 2.4 * adapted some tests * added an --allow-word-corrections option * improved handling of odd FoLiA 0.20 2019-11-27 [Ko van der Sloot] Bug fix release. solving: * https://github.com/LanguageMachines/frog/issues/84 * https://github.com/LanguageMachines/frog/issues/83 * https://github.com/LanguageMachines/ucto/issues/76 * https://github.com/LanguageMachines/ucto/issues/74 0.19 2019-09-16 [Ko van der Sloot] Bug fix release. solving: * https://github.com/LanguageMachines/ucto/issues/72 * some problems with the newest libfolia. * better provenance records 0.18 2019-07-22 [Ko van der Sloot] Bug fix release. solving: https://github.com/LanguageMachines/ucto/issues/70 0.17 2019-06-19 [Ko van der Sloot] Bug-fix release: - solved problems when tokenizing (partly-)tokenized FoLiA (but this is a very complicated situation. Might need more work) - solved problems with --passthru on FoLiA - avoid empty lines in FoLiA output - use the new generate_id attribute for provenance/processors - added more tests KNOW PROBLEM: On TravisCI/MacOSX some tests fail for unclear reasons. 0.16 2019-05-29 Major release supporting FoLiA 2.0 * bug fixes for: - empty sentences in FoLiA introduced by NonBreakingSpace - provide provenance data 0.15 2019-05-15 [Ko van der Sloot] stabilizing release for pre FoLiA 2.0 * uses new folia::engine to process FoLiA * lots of refactoring and cleanup * some small bug fixes * added tests for corner cases in FoLiA * improved TextCat handling and debugging 0.14.1 2018-12-10 [Ko van der Sloot] Bug fix release * fixed textcat installation problems om Debian and OpenBSD (https://github.com/LanguageMachines/ucto/issues/59) * typo in the man page fixed 0.14 2018-11-29 [Ko van der Sloot] * updated usage() and removed -S option (never used) * make sure the right textclass is assigned to nodes in FoLiA * minor code fixes/refactorings * added more tests * updated man.1 page [Maarten van Gompel] * updated README.md [Iris Hendrickx] * Updated and extended the manual 0.13.2 2018-05-17 [Ko van der Sloot] Bug fix release: * uctodata is mandatory. So don't install default rules anymore 0.13.1 2018-05-17 [Ko van der Sloot] Bug fix release: * configure now finds out the location of the uctodata files. should make it work on Mac systems too 0.13 2018-05-16 [Ko van der Sloot] * improved configure/build/test * added a --split option * fixed -P option * removed -S option (never used, and only half implemented) * added a --add-tokens option, to add special tokens for the default language * generally use the icu:: namespace * added more tests * fixed uninitialized variable. * added code to use an alternative search-path for uctodata [Maarten van Gompel] * added codemeta.json 0.12 2018-02-19 [Ko van der Sloot] * now use the UniFilter Unicode Filter from ticcutils * now use the UnicodeNormalizer from ticcutils * improved configuration. Support vor Mac OSX added 0.11 2017-12-04 [Ko van der Sloot] Bug fix release: * problems with text inside Cell elements 0.10 2017-11-07 [Ko van der Sloot] New release due to outdated files in the previous release. 0.9.9 2017-11-06 [Ko van der Sloot] Minor fix: * bumped the .so version to 3.0.0 0.9.8 2017-10-23 [Ko van der Sloot] Bug-fix release * fixed utterance handling in FoLiA input. Don't try sentence detection! 0.9.7 2017-10-17 [Ko van der Sloot] * added textredundancy option, default is 'minimal' * small adaptations to work with FoLiA 1.5 specs - set textclass on words when outputclass != inputclass - DON'T filter special characters when inputclass == outputclass * -F (folia input) is automatically set for .xml files * more robust against texts with embedded tabs, etc. * more and better tests added * better logging and error messaging * improved language handling. TODO: Language detection in FoLiA * bug fixes: - correctly handle xml-comment inside a - better id generation when parent has no id - better reaction on overly long 'words' 0.9.6 2017-01-23 [Maarten van Gompel] * Moving data files from etc/ to share/, as they are more data files than configuration files that should be edited. * Requires uctodata >= 0.4. * Should solve debian packaging issues (#18) * Minor updates to the manual (#2) * Some refactoring/code cleanup, temper expectations regarding ucto's date-tagging abilities (#16, thanks also to @sanmai-NL) 0.9.5 2017-01-06 [Ko van der Sloot] Bug fix release: * updated tokconfig-generic, which is removed from the uctodata package * configure no longer insists on the presence of uctodata, it merely warns when missing 0.9.4 2017-01-05 [Ko van der Sloot] Major update * Language support - added support for multiple languages - auto detection of languages using textcat * some refactoring - no more call to exit() - Better logging and Warning messages - some folia output improvements * bug fixes - in passthru, - issue #11 0.9.3 2016-09-28 [Ko van der Sloot] Major update: - require ICU 5.2 - implemented recursive application of rules. (which may be dangerous) - modfied tests, because not all failures wre detected correctly - check the uctodata version. version > 0.2 is preferred. 0.9.1 2016-07-12 [Ko van der Sloot] Bug fix release: - fixed autoconfig issue 0.9.0 2016-07-11 [Ko van der Sloot] Major update - now use uctodata for language specific information ucto itself only supports a generic tokenizer - interactive use now uses readline library - accept long options --help and --verision - UTF16BE now works - better support for crooked Windows files in general - added a --normalize option to map tokens in a certain TokenClass to it's generic name 0.8.6 2016-04-25 [Ko van der Sloot] * Bug fix release: fixing Sentence boundaries after abbreviations 0.8.5 2016-04-25 [Ko van der Sloot] * Bug fix release: Better handling of regexps 0.8.4 2016-03-10 [Ko van der Sloot] * implemented on top of libfolia 1.0 0.8.1 2016-01-14 [Ko van der Sloot] * repository moved to GIT * added Travis support * more tests added * added META-RULES code * %include now supports full paths * updated some languages * fixed passthru mode * code cleanup 0.8.0 2015-01-29 [Ko van der Sloot] * next release [Maarten van Gompel] * added new tokenize(string,string) meta-function for the API * allatonce enabled by default for tokenize() to folia doc * fixing date rules and adding FRACNUMBER * added Russian * Adicionei regras para tokenização portuguesa. [Antal vd Bosch] * added RK to dutch abbrev. 0.7.0 2014-11-26 [Ko van der Sloot] * unofficial release * experimental PUNCTUATION filter * bug fixes [Maarten van Gompel] * reduced memory usage 0.6.0 2014-09-23 [Ko van der Sloot] * release 0.5.5 2014-06-xx * made getSentence() public * adapted to most recent libfolia (0.11 or above) * needs libticcutils 0.6 or above * uses TiCC::CommandLine * detect EMOTICON's * generally switched to UChar32 and Unicode codepoints. (avoid length() problems) * handle FoLiA Note like Caption * a lot of bug fixes concerning FoLiA output ( nodes, textclass values etc.) * again some changes around quotes * improved tokenisation in differeny languages * added swedisch 0.5.3 2013-04-04 [Folgert Karsdorp] * Fixed quote detection, added tests. still shaky and default disabled [Ko van der Sloot] * changed verbose output slightly * fixed id's in folia output * various folia fixes * honour BOM markers in input file * lots of configuration updates * some fixes in handling if RULES 0.5.2 2012-03-29 [Ko vd Sloot] * some small changes. Made it work with libfolia 0.9 0.5.1 2012-02-27 [Ko vd Sloot] * added 'escape' possibility for regexps that start with a [ * better debugging output * removed all (?i) stuff from regexps. This attempts to avoid an ICU bug * added -X en --id= options * adapted to libfolia 0.8 (/tests too!) * some cleanup and refactoring [Maarten van Gompel] * added better rules for apostrophs in ATTACHEDSUFFIX and TOKENS 0.5.0 2012-01-09 [Ko vd Sloot] * added a different and more powerpull SMILEY rule. Which happens also to work on older ICU versions 0.4.9 2011-12-21 [Ko vd sloot] * reworked and more folia integration 0.4.8 2011-11-02 [Ko vd sloot] * use libfolia to generate folia XML 0.4.7 - (not released yet, feel free to add more stuff) [ Maarten van Gompel ] * Fix: proper XML entities in FoLiA output * fixed bug77 (the NOSPACE bug) * Fix: Nested quote problem (2011-08-18) * Improved protection against unbalanced quotes/sentences (2011-08-18) [Ko van der Sloot] * fixed passthru encoding problem * fixed problem with CRLF separated lines (bug 78) * configdir vs. config file hassle moved more inside. simpler API now. * -Q option works reversed now. -Q Enables Quote detection. Quote detection apears to be very hard and fragile. 0.4.6 - 2011-05-17 [Ko van der Sloot] * changed the regexp for KNOWN-ABBREVIATIONS to case sensitive * fixed include file handling for non-standard locations * fixed a problem with NON-Unix files. ucto would crash on a line with just '\r' 0.4.5 - 2011-04-27 [ Maarten van Gompel] * Added sentenceperline support for PassThru mode , improved sentenceperline support for normal mode [ Ko vd Sloot ] * on failue, ucto didn't use the right exit code. 0 == SUCCESS (on most systems) * added functions to display version info. 0.4.4 - 2011-03-31 [ Maarten van Gompel] * fixed "fatal error: ucto: out of range :No sentence exists with the specified index" problem. (Bug 65) [ Ko van der Sloot ] * Fixed terrible bug. Unicode strings were output in the current locale. But we advertise UTF8 0.4.3 - 2011-03-19 [ Ko van der Sloot ] * src/ucto.cxx: fixed --passthru problem * tests/testpassthru.ok: test now works [ Joost van Baal ] * NEWS: record changes and releases 0.4.2 - 2011-03-17 [ Ko van der Sloot ] * include/ucto/tokenize.h, src/tokenize.cxx, src/unicode.cxx: passes -pedantic * configure.ac: some cleanup, bumped version * include/ucto/tokenize.h, src/tokenize.cxx, src/ucto.cxx: added (hidden) --passthru option * [r8842] tests/passthru.txt, tests/testall, tests/testpassthru, added a passthru test. has t0 be tested :) * include/ucto/tokenize.h, src/tokenize.cxx: make compiler more happy * docs/ucto.1: added description, smal update 0.4.1 - 2011-03-11 [ Ko van der Sloot ] * src/tokenize.cxx: fixed regexp and error messag * config/tokconfig-nl, src/tokenize.cxx: added the possiblity to ste the order of RULES in the config file * tests/bug0063.nl.tok.V, tests/bug0063.nl.txt: added a test for bug63 Not sure about the 'correct' solution * docs/ucto.1: updated man page [ Maarten van Gompel ] * src/tokenize.cxx: fixed passthruline (skip=t) bug, FoLiA XSL has to be local unfortunately * tests/bug0063.nl.tok.V: override * config/tokconfig-nl, src/tokenize.cxx, tests/bug0052.nl.tok.V, tests/normalisation.nl.tok.V, tests/test.nl.tok.V: fix bug0063 0.4.0 - 2011-03-04 [ Maarten van Gompel ] * logo.svg: added logo 0.3.7 - 2011-03-01 [ Ko van der Sloot ] * [r8636] tests/testoption1.ok, tests/testusage.ok: these tests give a different outcome now. * [r8318] src/tokenize.cxx: added experimental code to use the -n option ( output one sentence per line) also to process the input one sentence per line * [r8317] tests/bug0054.nl.tok.V, tests/bug0054.nl.txt: testcase for bug0054 [ Maarten van Gompel ] * [r8618] include/ucto/tokenize.h, src/tokenize.cxx, src/ucto.cxx: sentence per line input and output: two modes * [r8617] src/tokenize.cxx, tests/bug0048.nl.tok.V, tests/bug0054.nl.tok.V: Fixed bug 54 * [r8615] src/tokenize.cxx, tests/abbreviations.nl.tok.V, tests/nu.nl.tok.V, tests/test.nl.tok.V: fixes * [r8614] src/tokenize.cxx: FoLiA improvement 0.3.6 - 2011-02-12 [ Ko van der Sloot ] * tests/: more tests added * configure.ac, include/ucto/tokenize.h, src/tokenize.cxx, src/ucto.cxx, tests/testnormalisation: added possibility to set the inputEncoding breaks ucto user interface! 0.3.5 - 2011-02-10 [ Ko van der Sloot ] * src/ucto.cxx: fix memory leak * include/ucto/tokenize.h, include/ucto/unicode.h, src/Makefile.am, src/tokenize.cxx, src/ucto.cxx, src/unicode.cxx, include/ucto/tokenize.h, src/unicode.cxx: added copyright notice * include/ucto/tokenize.h, src/tokenize.cxx, src/ucto.cxx: -f option now works * config/tokconfig-nl, include/ucto/tokenize.h, src/tokenize.cxx, src/ucto.cxx: added support for ligature filtering and Unicode normalizing. a bit rough still * tests/: more tests added * ucto.pc.in: now uses ucto-icu.pc [ Maarten van Gompel ] * configure.ac: version bump 0.3.4 - 2011-01-27 [ Joost van Baal ] * Makefile.am, configure.ac, icu.pc.in, ucto-icu.pc.in: rename icu.pc to ucto-icu.pc: be sure we wont suffer from filename clashes in the future. Once Debian and other distos ship icu 4.6's usr/lib/pkgconfig/icu-io.pc (released 2010-12-02) we can get rid of our local copy. [ Ko van der Sloot ] * tests/: more tests added [ Maarten van Gompel ] * include/ucto/tokenize.h, src/tokenize.cxx: Updates in FoLiA support 0.3.3 - 2011-01-27 [ Joost van Baal ] * Various bugfixes 0.3.2 - 2011-01-27 [ Ko van der Sloot ] * Various bugfixes 0.3.1 - 2011-01-26 [ Ko van der Sloot ] * Various bugfixes 0.3.0 - 2011-01-26 [ Maarten van Gompel ] * tests/: Added lots of tests * configure.ac, include/ucto/tokenize.h, src/tokenize.cxx, src/ucto.cxx: major refactoring. Improved buffering, less unnecessary storing of token/sentence vectors in memory. Improved quote support. * include/ucto/tokenize.h, src/tokenize.cxx: Ucto now remembers if a token was spaced or not in the original. Enabling ucto to recontruct the original text exactly. * include/ucto/tokenize.h, src/tokenize.cxx: Added quote detection support * include/ucto/tokenize.h, src/tokenize.cxx, src/ucto.cxx: Added preliminary FoLiA XML output support in ucto * include/ucto/tokenize.h, src/tokenize.cxx, src/ucto.cxx: Big API overhaul [ Peter Berck ] * config/Makefile.am, config/tokconfig-sv Added Swedish tokconfig [ Ko van der Sloot ] * config/tokconfig-nl, src/tokenize.cxx: read QUOTES from config file * src/ucto.cxx: refuse to run when inputfile is bad * docs/ucto.1: added a simple 'man' page * src/ucto.cxx: added al -p switch to disable paragraph detection 0.0.1 - 2010-12-25 - First snapshot release unreleased - 09-12-2010 - started to create a separate package LanguageMachines-ucto-688c2af/README000066400000000000000000000000521472777655400172050ustar00rootroot00000000000000Please see README.md for more information LanguageMachines-ucto-688c2af/README.md000066400000000000000000000164001472777655400176100ustar00rootroot00000000000000[![GitHub build](https://github.com/LanguageMachines/ucto/actions/workflows/ucto.yml/badge.svg?branch=master)](https://github.com/LanguageMachines/ucto/actions/) [![Language Machines Badge](http://applejack.science.ru.nl/lamabadge.php/ucto)](http://applejack.science.ru.nl/languagemachines/) [![DOI](https://zenodo.org/badge/9028617.svg)](https://zenodo.org/badge/latestdoi/9028617) [![GitHub release](https://img.shields.io/github/release/LanguageMachines/ucto.svg)](https://GitHub.com/LanguageMachines/ucto/releases/) [![Project Status: Active – The project has reached a stable, usable state and is being actively developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active) # Ucto - A rule-based tokeniser KNAW Humanities Cluster Centre for Language and Speech technology, Radboud University Nijmegen Induction of Linguistic Knowledge Research Group, Tilburg University **Website**: https://languagemachines.github.io/ucto/ Ucto tokenizes text files: it separates words from punctuation, and splits sentences. This is one of the first tasks for almost any Natural Language Processing application. Ucto offers several other basic preprocessing steps such as changing case that you can all use to make your text suited for further processing such as indexing, part-of-speech tagging, or machine translation. Ucto comes with tokenisation rules for several languages (packaged separately) and can be easily extended to suit other languages. It has been incorporated for tokenizing Dutch text in Frog (https://languagemachines.github.io/frog), our Dutch morpho-syntactic processor. The software is intended to be used from the command-line by researchers in Natural Language Processing or related areas, as well as software developers. An [Ucto python binding](https://github.com/proycon/python-ucto) is also available separately. Features: - Comes with tokenization rules for English, Dutch, French, Italian, Turkish, Spanish, Portuguese and Swedish; easily extendible to other languages. Rules consists of regular expressions and lists. They are packaged separately as [uctodata](https://github.com/LanguageMachines/uctodata). - Recognizes units, currencies, abbreviations, and simple dates and times like dd-mm-yyyy - Recognizes paired quote spans, sentences, and paragraphs. - Produces UTF8 encoding and NFC output normalization, optionally accepting other input encodings as well. - Ligature normalization (can undo for isntance fi,fl as single codepoints). - Optional conversion to all lowercase or uppercase. - Supports [FoLiA XML](https://proycon.github.io/folia) Ucto was written by Maarten van Gompel and Ko van der Sloot. Work on Ucto was funded by NWO, the Netherlands Organisation for Scientific Research, under the Implicit Linguistics project, the CLARIN-NL program, and the CLARIAH project. This software is available under the GNU Public License v3 (see the file COPYING). ## Demo ![Ucto demo](https://raw.githubusercontent.com/CLARIAH/wp3-demos/master/ucto.gif) ## Installation To install Ucto, first consult whether your distribution's package manager has an up-to-date package: * Alpine Linux users can do `apk install ucto`. * Debian/Ubuntu users can do `apt install ucto` but this version will likely be significantly out of date! * Arch Linux users can install Frog via the [AUR](https://aur.archlinux.org/packages/ucto). * macOS users with [homebrew](https://brew.sh/) can do: `brew tap fbkarsdorp/homebrew-lamachine && brew install ucto` * An OCI container image is also available and can be used with Docker: `docker pull proycon/ucto`. Alternatively, you can build an OCI container image yourself using the provided `Dockerfile` in this repository. To compile and install manually from source: $ bash bootstrap.sh $ ./configure $ make $ sudo make install If you want to *automatically* download, compile and install the latest stable versions of the required dependencies, then run `./build-deps.sh` prior to the above. You can pass a target directory prefix as first argument and you may need to prepend `sudo` to ensure you can install there. The dependencies are: * [ticcutils](https://github.com/LanguageMachine/ticcutils) - A shared utility library * [libfolia](https://github.com/LanguageMachines/libfolia) - A library for the FoLiA format. * [uctodata](https://github.com/LanguageMachines/uctodata) - Data files for ucto, packaged separately If you already have these dependencies, e.g. through a package manager or manually installed, then you should skip this step. You will still need to take care to install the following 3rd party dependencies through your distribution's package manager, as they are not provided by our script: * ``icu`` - A C++ library for Unicode and Globalization support. On Debian/Ubuntu systems, install the package libicu-dev. * ``libxml2`` - An XML library. On Debian/Ubuntu systems install the package libxml2-dev. * ``libexttextcat`` - A language detection package. * A sane build environment with a C++ compiler (e.g. gcc 4.9 or above or clang), make, autotools, libtool, pkg-config ## Usage Tokenize an english text file to standard output, tokens will be space-seperated, sentences delimiter by ````: $ ucto -L eng yourfile.txt The -L flag specifies the language (as a three letter iso-639-3 code), provided a configuration file exists for that language. The configurations are provided separately, for various languages, in the [uctodata](https://github.com/LanguageMachines/uctodata) package. Note that older versions of ucto used different two-letter codes, so you may need to update the way you invoke ucto. To output to file instead of standard output, just add another positional argument with the desired output filename. If you want each sentence on a separate line (i.e. newline delimited rather than delimited by ````), then pass the ``-n`` flag. If each sentence is already on one line in the input and you want to leave it at that, pass the ``-m`` flag. Tokenize plaintext to [FoLiA XML](https://proycon.github.io/folia) using the ``-X`` flag, you can specify an ID for the FoLiA document using the ``--id=`` flag. $ ucto -L eng -X --id=hamlet hamlet.txt hamlet.folia.xml Note that in the FoLiA XML output, ucto encodes the class of the token (date, url, smiley, etc...) based on the rule that matched. For further documentation consult the [ucto documentation](https://ucto.readthedocs.io/en/latest/). ## Container Usage A pre-made container image can be obtained from Docker Hub as follows: ``docker pull proycon/ucto`` Alternatively, you can build a docker container as follows, make sure you are in the root of this repository: ``docker build -t proycon/ucto .`` This builds the latest stable release, if you want to use the latest development version from the git repository instead, do: ``docker build -t proycon/ucto --build-arg VERSION=development .`` Run the container interactively as follows, you can pass any additional arguments that ``ucto`` takes. ``docker run -t -i proycon/ucto`` Add the ``-v /path/to/your/data:/data`` parameter (before `-t`) if you want to mount your data volume into the container at `/data`. ## Webservice If you are looking to run Ucto as a webservice yourself, please see https://github.com/proycon/ucto_webservice . It is not included in this repository. LanguageMachines-ucto-688c2af/TODO000066400000000000000000000001241472777655400170150ustar00rootroot00000000000000We need unit tests We need to comile list of known problems for several langauages LanguageMachines-ucto-688c2af/bootstrap.sh000077500000000000000000000053361472777655400207130ustar00rootroot00000000000000#!/bin/bash # bootstrap - script to bootstrap the distribution rolling engine # usage: # $ sh ./bootstrap && ./configure && make dist[check] # # this yields a tarball which one can install doing # # $ tar zxf PACKAGENAME-*.tar.gz # $ cd PACKAGENAME-* # $ ./configure # $ make # # make install # requirements: # GNU autoconf, from e.g. ftp.gnu.org:/pub/gnu/autoconf/ # GNU automake, from e.g. http://ftp.gnu.org/gnu/automake/ automake=automake aclocal=aclocal # if you want to autogenerate a ChangeLog form svn: # # svn2cl, a python script, as used in the GNU Enterprise project. # By jcater (Jason Cater), contributions by reinhard (Reinhard Müller). # Get it from # http://www.gnuenterprise.org/cgi-bin/viewcvs.cgi/*checkout*/gnue/trunk/gnue-common/utils/svn2cl . # svn2cl is used in Makefile.am too. # # (Another svn2cl implementation, in perl, is at # http://www.contactor.se/~dast/svn/archive-2002-04/0910.shtml) # # see also toplevel Makefile.am # test -f ChangeLog || { # svn log --verbose > ChangeLog #} # inspired by hack as used in mcl (from http://micans.org/) # autoconf-archive Debian package, aclocal-archive RPM, obsolete/badly supported OS, installed in home dir acdirs="/usr/share/autoconf-archive/ /usr/share/aclocal/ /usr/local/share/aclocal/ $HOME/local/share/autoconf-archive/ /opt/homebrew/share/aclocal/" found=false for d in $acdirs do if test -f ${d}pkg.m4 then found=true break fi done if ! $found then cat <&2 echo " Building latest stable release of main dependencies from source.">&2 echo "------------------------------------------------------------------------">&2 else echo "------------------------------------------------------------------------">&2 echo " Building development versions of main dependencie from source.">&2 echo " (This is experimental and may contain bugs! DO NOT PUBLISH!)">&2 echo "-----------------------------------------------------------------------">&2 fi PWD="$(pwd)" BUILDDIR="$(mktemp -dt "build-deps.XXXXXX")" cd "$BUILDDIR" BUILD_SOURCES="LanguageMachines/ticcutils LanguageMachines/libfolia LanguageMachines/uctodata" for SUFFIX in $BUILD_SOURCES; do \ NAME="$(basename "$SUFFIX")" git clone "https://github.com/$SUFFIX" cd "$NAME" REF=$(git tag -l | grep -E "^v?[0-9]+(\.[0-9])*" | sort -t. -k 1.2,1n -k 2,2n -k 3,3n -k 4,4n | tail -n 1) if [ "$VERSION" = "stable" ] && [ -n "$REF" ]; then git -c advice.detachedHead=false checkout "$REF" fi sh ./bootstrap.sh && ./configure --prefix "$PREFIX" && make && make install cd .. done cd "$PWD" [ -n "$BUILDDIR" ] && rm -Rf "$BUILDDIR" LanguageMachines-ucto-688c2af/codemeta.json000066400000000000000000000472541472777655400210200ustar00rootroot00000000000000{ "@context": [ "https://doi.org/10.5063/schema/codemeta-2.0", "http://schema.org", "https://w3id.org/software-types", "https://w3id.org/software-iodata" ], "@type": "SoftwareSourceCode", "identifier": "ucto", "name": "ucto", "version": "0.35", "description": "Ucto tokenizes text files: it separates words from punctuation, and splits sentences. This is one of the first tasks for almost any Natural Language Processing application. Ucto offers several other basic preprocessing steps such as changing case that you can all use to make your text suited for further processing such as indexing, part-of-speech tagging, or machine translation.", "license": "https://spdx.org/licenses/GPL-3.0-only", "url": "https://languagemachines.github.io/ucto", "thumbnailUrl": "https://raw.githubusercontent.com/LanguageMachines/ucto/master/logo.svg", "producer": { "@id": "https://huc.knaw.nl", "@type": "Organization", "name": "KNAW Humanities Cluster", "url": "https://huc.knaw.nl", "parentOrganization": { "@id": "https://knaw.nl", "@type": "Organization", "name": "KNAW", "url": "https://knaw.nl", "location": { "@type": "Place", "name": "Amsterdam" } } }, "author": [ { "@id": "https://orcid.org/0000-0002-1046-0006", "@type": "Person", "givenName": "Maarten", "familyName": "van Gompel", "email": "proycon@anaproy.nl", "affiliation": { "@id": "https://huc.knaw.nl" } }, { "@type": "Person", "givenName": "Ko", "familyName": "van der Sloot", "email": "ko.vandersloot@let.ru.nl", "affiliation": { "@id": "https://www.ru.nl/clst", "@type": "Organization", "name": "Centre for Language and Speech Technology", "url": "https://www.ru.nl/clst", "parentOrganization": { "@id": "https://www.ru.nl/cls", "@type": "Organization", "name": "Centre for Language Studies", "url": "https://www.ru.nl/cls", "parentOrganization": { "@id": "https://www.ru.nl", "name": "Radboud University", "@type": "Organization", "url": "https://www.ru.nl", "location": { "@type": "Place", "name": "Nijmegen" } } } } } ], "programmingLanguage": { "@type": "ComputerLanguage", "identifier": "c++", "name": "C++" }, "operatingSystem": [ "Linux", "BSD", "macOS" ], "codeRepository": "https://github.com/LanguageMachines/ucto", "softwareRequirements": [ { "@type": "SoftwareApplication", "identifier": "icu", "name": "icu" }, { "@type": "SoftwareApplication", "identifier": "libxml2", "name": "libxml2" }, { "@type": "SoftwareApplication", "identifier": "ticcutils", "name": "ticcutils" }, { "@type": "SoftwareApplication", "identifier": "libfolia", "name": "libfolia" } ], "funding": [ { "@type": "Grant", "name": "CLARIN-NL (NWO grant 184.021.003)", "url": "https://www.clariah.nl", "funder": { "@type": "Organization", "name": "NWO", "url": "https://www.nwo.nl" } }, { "@type": "Grant", "name": "CLARIAH-CORE (NWO grant 184.033.101)", "url": "https://www.clariah.nl", "funder": { "@type": "Organization", "name": "NWO", "url": "https://www.nwo.nl" } }, { "@type": "Grant", "name": "CLARIAH-PLUS (NWO grant 184.034.023)", "funder": { "@type": "Organization", "name": "NWO", "url": "https://www.nwo.nl" } } ], "readme": "https://github.com/LanguageMachines/ucto/blob/master/README.md", "softwareHelp": [ { "@id": "https://ucto.readthedocs.io", "@type": "WebSite", "name": "Ucto documentation", "url": "https://ucto.readthedocs.io" } ], "issueTracker": "https://github.com/LanguageMachines/ucto/issues", "contIntegration": "https://github.com/LanguageMachines/ucto/actions/workflows/ucto.yml", "releaseNotes": "https://github.com/LanguageMachines/ucto/releases", "developmentStatus": [ "https://www.repostatus.org/#active", "https://w3id.org/research-technology-readiness-levels#Level9Proven" ], "keywords": [ "nlp", "natural language processing", "tokenization", "tokenizer" ], "dateCreated": "2011-03-27", "dateModified": "2023-02-22T12:17:06Z+0100", "applicationCategory": [ "https://vocabs.dariah.eu/tadirah/annotating", "https://vocabs.dariah.eu/tadirah/tagging", "https://w3id.org/nwo-research-fields#Linguistics", "https://w3id.org/nwo-research-fields#TextualAndContentAnalysis" ], "targetProduct": [ { "@type": "SoftwareLibrary", "executableName": "libucto", "name": "libucto", "runtimePlatform": [ "Linux", "BSD", "macOS" ], "description": "Ucto Library with API for C++" }, { "@type": "CommandLineApplication", "executableName": "ucto", "name": "ucto", "runtimePlatform": [ "Linux", "BSD", "macOS" ], "description": "Command-line interface to the tokenizer", "consumesData": [ { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/nld", "@type": "Language", "name": "Dutch", "identifier": "nld" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/eng", "@type": "Language", "name": "English", "identifier": "eng" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/ita", "@type": "Language", "name": "Italian", "identifier": "ita" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/fra", "@type": "Language", "name": "French", "identifier": "fra" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/spa", "@type": "Language", "name": "Spanish", "identifier": "spa" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/por", "@type": "Language", "name": "Portuguese", "identifier": "por" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/deu", "@type": "Language", "name": "German", "identifier": "deu" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/fry", "@type": "Language", "name": "Frisian", "identifier": "fry" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/swe", "@type": "Language", "name": "Swedish", "identifier": "swe" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/rus", "@type": "Language", "name": "Russian", "identifier": "rus" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/tur", "@type": "Language", "name": "Turkish", "identifier": "tur" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/nld" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/eng" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/ita" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/fra" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/spa" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/por" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/deu" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/fry" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/swe" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/rus" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/tur" } ] } ], "producesData": [ { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/nld" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/eng" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/ita" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/fra" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/spa" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/por" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/deu" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/fry" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/swe" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/rus" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "text/plain", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/tur" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/nld" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/eng" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/ita" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/fra" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia+xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/spa" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/por" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/deu" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/fry" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/swe" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/rus" } ] }, { "@type": "TextDigitalDocument", "encodingFormat": "application/folia.xml", "inLanguage": [ { "@id": "https://iso639-3.sil.org/code/tur" } ] } ] } ] } LanguageMachines-ucto-688c2af/config/000077500000000000000000000000001472777655400175755ustar00rootroot00000000000000LanguageMachines-ucto-688c2af/config/Makefile.am000066400000000000000000000005511472777655400216320ustar00rootroot00000000000000config_DATA = textcat_normal.cfg textcat_alt.cfg configdir = $(datadir)/$(PACKAGE) EXTRA_DIST = $(config_DATA) install-data-hook: rm -f $(DESTDIR)$(configdir)/textcat.cfg if OLD_LM cp -f $(DESTDIR)$(configdir)/textcat_alt.cfg $(DESTDIR)$(configdir)/textcat.cfg else cp -f $(DESTDIR)$(configdir)/textcat_normal.cfg $(DESTDIR)$(configdir)/textcat.cfg endif LanguageMachines-ucto-688c2af/config/textcat.cfg000066400000000000000000000013421472777655400217320ustar00rootroot00000000000000# # A config file for the language models we support for texcat # provided with Gertjan van Noords language guesser # (http://odur.let.rug.nl/~vannoord/TextCat/) # # Notes: # - we only support a small range of languages. # - Putting the most probable languages at the top of the list # improves performance, because this will raise the threshold for # likely candidates more quickly. # # /usr/share/libexttextcat/nl.lm nld /usr/share/libexttextcat/en.lm eng /usr/share/libexttextcat/de.lm deu /usr/share/libexttextcat/fr.lm fra /usr/share/libexttextcat/it.lm ita /usr/share/libexttextcat/es.lm spa /usr/share/libexttextcat/ru.lm rus /usr/share/libexttextcat/pt.lm por /usr/share/libexttextcat/sv.lm swe /usr/share/libexttextcat/tr.lm tur LanguageMachines-ucto-688c2af/config/textcat_alt.cfg.in000066400000000000000000000013031472777655400231740ustar00rootroot00000000000000# # A config file for the language models we support for texcat # provided with Gertjan van Noords language guesser # (http://odur.let.rug.nl/~vannoord/TextCat/) # # Notes: # - we only support a small range of languages. # - Putting the most probable languages at the top of the list # improves performance, because this will raise the threshold for # likely candidates more quickly. # # @MODULE_PREFIX@/dutch.lm nld @MODULE_PREFIX@/english.lm eng @MODULE_PREFIX@/german.lm deu @MODULE_PREFIX@/french.lm fra @MODULE_PREFIX@/italian.lm ita @MODULE_PREFIX@/spanish.lm spa @MODULE_PREFIX@/russian-iso8859_5.lm rus @MODULE_PREFIX@/portuguese.lm por @MODULE_PREFIX@/swedish.lm swe @MODULE_PREFIX@/turkish.lm tur LanguageMachines-ucto-688c2af/config/textcat_normal.cfg.in000066400000000000000000000012101472777655400237010ustar00rootroot00000000000000# # A config file for the language models we support for texcat # provided with Gertjan van Noords language guesser # (http://odur.let.rug.nl/~vannoord/TextCat/) # # Notes: # - we only support a small range of languages. # - Putting the most probable languages at the top of the list # improves performance, because this will raise the threshold for # likely candidates more quickly. # # @MODULE_PREFIX@/nl.lm nld @MODULE_PREFIX@/en.lm eng @MODULE_PREFIX@/de.lm deu @MODULE_PREFIX@/fr.lm fra @MODULE_PREFIX@/it.lm ita @MODULE_PREFIX@/es.lm spa @MODULE_PREFIX@/ru.lm rus @MODULE_PREFIX@/pt.lm por @MODULE_PREFIX@/sv.lm swe @MODULE_PREFIX@/tr.lm tur LanguageMachines-ucto-688c2af/configure.ac000066400000000000000000000064601472777655400206240ustar00rootroot00000000000000# -*- Autoconf -*- # Process this file with autoconf to produce a configure script. AC_PREREQ([2.69]) AC_INIT([ucto],[0.35],[lamasoftware@science.ru.nl]) #adapt version number in codemeta.json as well AM_INIT_AUTOMAKE([foreign]) AC_CONFIG_SRCDIR([configure.ac]) AC_CONFIG_MACRO_DIR([m4]) AC_CONFIG_HEADERS([config.h]) SYSCONFDIR=$sysconfdir AC_SUBST([SYSCONFDIR]) AX_REQUIRE_DEFINED([AX_CXX_COMPILE_STDCXX_17]) # Checks for programs. AC_PROG_CXX( [g++ c++] ) AX_CXX_COMPILE_STDCXX_17 # use libtool LT_INIT AC_PROG_LN_S # when running tests, use CXX AC_LANG([C++]) # Checks for libraries. # Checks for header files. AC_HEADER_STDBOOL # Checks for typedefs, structures, and compiler characteristics. AC_C_INLINE AC_TYPE_SIZE_T AC_TYPE_INT8_T AC_TYPE_INT32_T # Checks for library functions. AX_LIB_READLINE if test $prefix = "NONE"; then prefix="$ac_default_prefix" fi PKG_PROG_PKG_CONFIG if test "x$PKG_CONFIG_PATH" = x; then export PKG_CONFIG_PATH="$prefix/lib/pkgconfig" else export PKG_CONFIG_PATH="$prefix/lib/pkgconfig:$PKG_CONFIG_PATH" fi AC_OSX_PKG( [icu4c libtextcat] ) AC_MSG_NOTICE([pkg-config: PATH=$PKG_CONFIG_PATH]) PKG_CHECK_MODULES( [TEXTCAT], [libexttextcat], [TEXTCAT_FOUND=1 CXXFLAGS="$CXXFLAGS $TEXTCAT_CFLAGS" LIBS="$TEXTCAT_LIBS $LIBS"], [PKG_CHECK_MODULES( [TEXTCAT], [libtextcat], [TEXTCAT_FOUND=1 CXXFLAGS="$CXXFLAGS $TEXTCAT_CFLAGS" LIBS="$TEXTCAT_LIBS $LIBS"], [TEXTCAT_FOUND=0] )] ) if test $TEXTCAT_FOUND = 0; then # So, no pkg-config for textcat found. # Hopefully an old style version can be found??? AC_CHECK_OLD_TEXTCAT if test $TEXTCAT_FOUND = 1; then AC_DEFINE([HAVE_OLD_TEXTCAT], [1], [textcat needs C linkage]) fi fi if test $TEXTCAT_FOUND = 1; then AC_SEARCH_LM fi if test $TEXTCAT_FOUND = 0; then AC_MSG_ERROR( [no working libtextcat or libexttextcat found!] ) else AC_DEFINE([HAVE_TEXTCAT], [1], [textcat]) fi PKG_CHECK_MODULES([ICU], [icu-uc >= 50 icu-io] ) CXXFLAGS="$CXXFLAGS $ICU_CFLAGS" LIBS="$ICU_LIBS $LIBS" PKG_CHECK_MODULES([XML2], [libxml-2.0 >= 2.9.4] ) CXXFLAGS="$CXXFLAGS $XML2_CFLAGS" LIBS="$LIBS $XML2_LIBS" PKG_CHECK_MODULES([folia], [folia >= 2.19] ) CXXFLAGS="$folia_CFLAGS $CXXFLAGS" LIBS="$folia_LIBS $LIBS" PKG_CHECK_MODULES([ticcutils], [ticcutils >= 0.36] ) CXXFLAGS="$CXXFLAGS $ticcutils_CFLAGS" LIBS="$LIBS $ticcutils_LIBS" PKG_CHECK_MODULES( [uctodata], [uctodata], [PKG_CHECK_MODULES( [uctodata], [uctodata >= 0.9], [], [AC_MSG_NOTICE([ATTENTION: Your ucto datafiles are outdated You should consider installing a newer version of the uctodata package!])]) ], [AC_MSG_ERROR([ATTENTION: ucto datafiles are not installed!. Please install uctodata package.] )] ) UCTODATA_PRE=`pkg-config --variable=prefix uctodata` UCTODATA_DIR=$UCTODATA_PRE/share/ucto AC_DEFINE_UNQUOTED( [UCTODATA_DIR], ["$UCTODATA_DIR/"], [location of uctodata files]) UCTODATA_VER=`pkg-config --modversion uctodata` AC_DEFINE_UNQUOTED( [UCTODATA_VERSION], ["${UCTODATA_VER}"], [the uctodata version]) # Checks for library functions. AC_CONFIG_FILES([ Makefile ucto.pc m4/Makefile config/Makefile config/textcat_normal.cfg config/textcat_alt.cfg docs/Makefile src/Makefile tests/Makefile include/Makefile include/ucto/Makefile ]) AC_OUTPUT LanguageMachines-ucto-688c2af/docs/000077500000000000000000000000001472777655400172605ustar00rootroot00000000000000LanguageMachines-ucto-688c2af/docs/Makefile.am000066400000000000000000000000741472777655400213150ustar00rootroot00000000000000# $Id: $ # $URL: $ man1_MANS = ucto.1 EXTRA_DIST = ucto.1 LanguageMachines-ucto-688c2af/docs/Makefile.sphinx000066400000000000000000000011201472777655400222220ustar00rootroot00000000000000# Minimal makefile for Sphinx documentation # # You can set these variables from the command line. SPHINXOPTS = SPHINXBUILD = sphinx-build SOURCEDIR = source BUILDDIR = build # Put it first so that "make" without argument is like "make help". help: @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) .PHONY: help Makefile # Catch-all target: route all unknown targets to Sphinx using the new # "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). %: Makefile.sphinx @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) LanguageMachines-ucto-688c2af/docs/source/000077500000000000000000000000001472777655400205605ustar00rootroot00000000000000LanguageMachines-ucto-688c2af/docs/source/_static/000077500000000000000000000000001472777655400222065ustar00rootroot00000000000000LanguageMachines-ucto-688c2af/docs/source/_static/DUMMY000066400000000000000000000000001472777655400230120ustar00rootroot00000000000000LanguageMachines-ucto-688c2af/docs/source/_templates/000077500000000000000000000000001472777655400227155ustar00rootroot00000000000000LanguageMachines-ucto-688c2af/docs/source/_templates/DUMMY000066400000000000000000000000001472777655400235210ustar00rootroot00000000000000LanguageMachines-ucto-688c2af/docs/source/conf.py000066400000000000000000000124411472777655400220610ustar00rootroot00000000000000# -*- coding: utf-8 -*- # # Configuration file for the Sphinx documentation builder. # # This file does only contain a selection of the most common options. For a # full list see the documentation: # http://www.sphinx-doc.org/en/master/config # -- Path setup -------------------------------------------------------------- # If extensions (or modules to document with autodoc) are in another directory, # add these directories to sys.path here. If the directory is relative to the # documentation root, use os.path.abspath to make it absolute, like shown here. # # import os # import sys # sys.path.insert(0, os.path.abspath('.')) # -- Project information ----------------------------------------------------- project = 'ucto' copyright = '2018, Language Machines' author = 'Language Machines' # The short X.Y version version = '' # The full version, including alpha/beta/rc tags release = '' # -- General configuration --------------------------------------------------- # If your documentation needs a minimal Sphinx version, state it here. # # needs_sphinx = '1.0' # Add any Sphinx extension module names here, as strings. They can be # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom # ones. extensions = [ ] # Add any paths that contain templates here, relative to this directory. templates_path = ['_templates'] # The suffix(es) of source filenames. # You can specify multiple suffix as a list of string: # # source_suffix = ['.rst', '.md'] source_suffix = '.rst' # The master toctree document. master_doc = 'index' # The language for content autogenerated by Sphinx. Refer to documentation # for a list of supported languages. # # This is also used if you do content translation via gettext catalogs. # Usually you set "language" from the command line for these cases. language = None # List of patterns, relative to source directory, that match files and # directories to ignore when looking for source files. # This pattern also affects html_static_path and html_extra_path. exclude_patterns = [] # The name of the Pygments (syntax highlighting) style to use. pygments_style = None # -- Options for HTML output ------------------------------------------------- # The theme to use for HTML and HTML Help pages. See the documentation for # a list of builtin themes. # html_theme = 'sphinx_rtd_theme' # Theme options are theme-specific and customize the look and feel of a theme # further. For a list of options available for each theme, see the # documentation. # # html_theme_options = {} html_theme_options = { 'logo_only': False, 'display_version': True, 'prev_next_buttons_location': 'bottom', #'style_external_links': False, # Toc options 'collapse_navigation': True, 'sticky_navigation': True, 'navigation_depth': 4, 'includehidden': True, 'titles_only': False } # Add any paths that contain custom static files (such as style sheets) here, # relative to this directory. They are copied after the builtin static files, # so a file named "default.css" will overwrite the builtin "default.css". html_static_path = ['_static'] # Custom sidebar templates, must be a dictionary that maps document names # to template names. # # The default sidebars (for documents that don't match any pattern) are # defined by theme itself. Builtin themes are using these templates by # default: ``['localtoc.html', 'relations.html', 'sourcelink.html', # 'searchbox.html']``. # # html_sidebars = {} # -- Options for HTMLHelp output --------------------------------------------- # Output file base name for HTML help builder. htmlhelp_basename = 'uctodoc' # -- Options for LaTeX output ------------------------------------------------ latex_elements = { # The paper size ('letterpaper' or 'a4paper'). # # 'papersize': 'letterpaper', # The font size ('10pt', '11pt' or '12pt'). # # 'pointsize': '10pt', # Additional stuff for the LaTeX preamble. # # 'preamble': '', # Latex figure (float) alignment # # 'figure_align': 'htbp', } # Grouping the document tree into LaTeX files. List of tuples # (source start file, target name, title, # author, documentclass [howto, manual, or own class]). latex_documents = [ (master_doc, 'ucto.tex', 'ucto Documentation', 'Language Machines', 'manual'), ] # -- Options for manual page output ------------------------------------------ # One entry per manual page. List of tuples # (source start file, name, description, authors, manual section). man_pages = [ (master_doc, 'ucto', 'ucto Documentation', [author], 1) ] # -- Options for Texinfo output ---------------------------------------------- # Grouping the document tree into Texinfo files. List of tuples # (source start file, target name, title, author, # dir menu entry, description, category) texinfo_documents = [ (master_doc, 'ucto', 'ucto Documentation', author, 'ucto', 'One line description of project.', 'Miscellaneous'), ] # -- Options for Epub output ------------------------------------------------- # Bibliographic Dublin Core info. epub_title = project # The unique identifier of the text. This can be a ISBN number # or the project homepage. # # epub_identifier = '' # A unique identification for the text. # # epub_uid = '' # A list of files that should not be packed into the epub file. epub_exclude_files = ['search.html'] LanguageMachines-ucto-688c2af/docs/source/index.rst000066400000000000000000000767041472777655400224370ustar00rootroot00000000000000:Author: Maarten van Gompel :Author: Ko van der Sloot :Author: Iris Hendrickx :Author: Antal van den Bosch Centre for Language Studies Radboud University Nijmegen URL: https://languagemachines.github.io/ucto/ Introduction ============ Tokenisation is a process in which text is segmented into the various sentence and word tokens that constitute the text. Most notably, words are separated from any punctuation attached and sentence boundaries are detected. Tokenisation is a common and necessary pre-processing step for almost any Natural Language Processing task, and precedes further processing such as part-of-speech tagging, lemmatisation or syntactic parsing. Whilst tokenisation may at first seem a trivial problem, it does pose various challenges. For instance, the detection of sentence boundaries is complicated by the usage of periods in abbreviations and the use of capital letters in proper names. Furthermore, tokens may be contracted in constructions such as “I’m”, “you’re”, “father’s”. A tokeniser will generally split these. UCTO is an advanced rule-based tokeniser. The tokenisation rules used by UCTO are implemented as regular expressions and read from external configuration files, making UCTO flexible and extensible. Configuration files can be further customised for specific needs and for languages not yet supported. Tokenisation rules have first been developed for Dutch, but configurations for several other languages are also provided. UCTO features full unicode support. UCTO is not just a standalone program providing a command-line interface, but is also a C++ library that you can use in your own software. A separate Python binding is also available for use in Python software. This reference guide is structured as follows. In Chapter [license] you can find the terms of the license according to which you are allowed to use, copy, and modify UCTO. The subsequent chapter gives instructions on how to install the software on your computer. Next, Chapter [implementation] describes the underlying implementation of the software. Chapter [usage] explains the usage. License and citation ======================= UCTO is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 3 of the License, or any later version. In publication of research that makes use of the Software, a citation should be given of: *Maarten van Gompel, Ko van der Sloot, Iris Hendrickx and Antal van den Bosch. UCTO: Unicode Tokeniser. Reference Guide, Language and Speech Technology Technical Report Series 18-01, Radboud University, Nijmegen, October 30, 2018, Available from https://UCTO.readthedocs.io/.* For information about commercial licenses for the Software, contact lamasoftware@science.ru.nl, or send your request to: :: Prof. dr. Antal van den Bosch Radboud University P.O. Box 9103 – 6500 HD Nijmegen The Netherlands Email: a.vandenbosch@let.ru.nl Installation on Linux ====================== UCTO can be used as a commandline tool. The UCTO source files can be obtained from: https://github.com/LanguageMachines/ucto These sources need to be compiled for the software to run. However, on most recent Debian and Ubuntu systems, UCTO can be found in the respective software repositories and can be installed with a simple:: $ apt-get install ucto On Arch Linux, UCTO is available from the Arch User Repository. Such packages may be behind a bit, however, and not correspond to the latest version. To facilitate installation of the latest stable UCTO version in most situations, we recommend to use our LaMachine software distribution, which includes UCTO and all dependencies: http://proycon.github.io/LaMachine/ Compilation from source ---------------------------- If you, however, install from the source archive, the compilation and installation should also be relatively straightforward on most UNIX systems, and will be explained in the remainder of this section. To install UCTO, the following libraries need to be installed first: * ``libicu`` library, available at http://site.icu-project.org/ but present in the package manager of all major Linux distributions. * ``uctodata`` * ``libfolia``, available from ``http://proycon.github.com/folia``), which in turn depends on * `libticcutils`` (available from ``http://github.com/LanguageMachines/ticcutils``). After all these dependencies are installed, you can compile UCTO on your computer by running the following from the UCTO source directory: $ bash bootstrap.sh $ ./configure Note: It is possible to install UCTO in a different location than the global default using the ``–prefix=`` option, but this tends to make further operations (such as compiling higher-level packages like Frog [#f1]_ ) more complicated. Use the ``–with-UCTO=`` option in configure. After configure you can compile UCTO:: $ make and install:: $ make install If the process was completed successfully, you should now have an executable file named UCTO in the installation directory (``/usr/local/bin`` by default, we will assume this in the remainder of this section), and a dynamic library libUCTO.so in the library directory (``/usr/local/lib/``). The configuration files for the tokeniser can be found in ``/usr/local/share/UCTO/``. UCTO should now be ready for use. You can close and reopen your commandline terminal and issue the UCTO command to verify this. If not found, you may need to add the installation directory (``/usr/local/bin``) to your ``$PATH``. That’s all! The e-mail address for problems with the installation, bug reports, comments and questions is lamasoftware@science.ru.nl. Getting Started ================ UCTO is a regular-expression-based tokeniser offering a command-line interface. The tokeniser program uses a list of regular expressions (rules) and a specified ordering of these regular expresssions to process a text. Each of the rules has a name that signals its purpose like YEAR-NAME, SMILE, ABBREVIATION, etc. The tokeniser will first split on the spaces already present in the input, resulting in various *fragments*. Each fragment is then matched against the ordered set of regular expressions, until a match is found. If a match is found, the matching part is a token and is assigned the name of the matching regular expression. The matching part may be only a substring of the fragment, in which case there are one or two remaining parts on the left and/or right side of the match. These will be treated as any other fragments and all regular expressions are again tested in the specified order, from the start, and in exactly the same way. This process continues until all fragments have been processed. Every fragment in the text has been treated after this iterative process and has been labelled with at least one rule name. As a next step, UCTO performs sentence segmentation by looking at a specified list of end-of-sentence markers. Special treatment is given to the period (“.”), because of its common use in abbreviations. UCTO will attempt to use capitalisation (for scripts that distinguish case) and sentence length cues to determine whether a period is an actual end of sentence marker or not. Simple paragraph detection is available in UCTO: a double newline triggers a paragraph break. Quote detection is also available, but still experimental and by default disabled as it quickly fails on input that is not well prepared. If your input can be trusted on quotes being paired, you can try to enable it. Note that quotes spanning over paragraphs are not supported. UCTO has a generic configuration file called ``generic`` that is mostly language independent. We advise to use a language-specific configuration when possible. We offer configuration files for the following languages and the configuration file name should given after ``UCTO -L``: +------------+---------+ | language | -L flag | +============+=========+ | Dutch | nld | +------------+---------+ | German | deu | +------------+---------+ | English | eng | +------------+---------+ | French | fra | +------------+---------+ | Frysian | fry | +------------+---------+ | Italian | ita | +------------+---------+ | Portuguese | por | +------------+---------+ | Russian | rus | +------------+---------+ | Spanish | spa | +------------+---------+ | Swedish | swe | +------------+---------+ | Turkish | tur | +------------+---------+ For Dutch we have made specific configuration files for certain domains: * nld: the default configuration file for Dutch and most up to date and detailed configuration file for Dutch * nld-historical: a configuration file for historical text, which is more inclined to keep certain punctuation attached to words. Developed in the Nederlab project [#f3]_ * nld-twitter: configuration for Dutch tweets, here the typical URL, email, emoticon and smiley regular expressions are first in order of application * nld-sonarchat: similar to the nld-twitter configuration but has an additional rule ``NICKNAME`` to identify the nicknames of authors in a chatroom * nld-withplaceholder: a 'placeholder' regular expression is the first rule that is applied. The placeholder can be used to prevent certain strings that are marked between \% from being changed by the tokenizer. Usage ===== UCTO is a command-line tool. The following options are available: :: Usage: UCTO [[options]] [input-file] [[output-file]] Options: -c - Explicitly specify a configuration file -d - Set debug level (numerical value 1 or 2) -e - Set input encoding (default UTF8) -N - Set output normalization (default NFC [#f4]_ ) --filter=[YES|NO] - Disable filtering of special characters -f - OBSOLETE. use --filter=NO -h or --help - This list of options -L - Automatically selects a configuration file by language code. - Available Languages: deu,eng,fra,fry,generic,ita,nld,nld-historical,nld-sonarchat,nld-twitter,nld-withplaceholder,por,rus,spa,swe,tur, -l - Convert to all lowercase -u - Convert to all uppercase -n - One sentence per line (output) -m - One sentence per line (input) -v - Verbose mode -s - End-of-Sentence marker (default: ) --passthru - Don't tokenize, but perform input decoding and simple token role detection --normalize=,class2>,... - For class1, class2, etc. output the class tokens instead of the tokens itself. -T or --textredundancy=[full|minimal|none] - Set text redundancy level for text nodes in FoLiA output: 'full' - Add text to all levels:

etc. 'minimal' - Don't introduce text on higher levels, but retain what is already there. 'none' - Only introduce text on , AND remove all text from higher levels --filterpunct - Remove all punctuation from the output --uselanguages= - Only tokenize strings in these languages. Default = 'lang1' --detectlanguages= - Try to assign languages before using. Default = 'lang1' -P - Disable paragraph detection -Q - Enable quote detection (experimental) -V or --version - Show version information -x - Output FoLiA XML, use the specified Document ID (obsolete) -F - Input file is in FoLiA XML. All untokenised sentences will be tokenised -F is automatically set when inputfile has extension '.xml' -X - Output FoLiA XML, use the Document ID specified with --id= --id - Use the specified Document ID to label the FoLia doc -X is automatically set when inputfile has extension '.xml' --inputclass - Use the specified class to search text in the FoLia doc.(default is 'current') --outputclass - Use the specified class to output text in the FoLia doc. (default is 'current') --textclass - Use the specified class for both input and output of text in the FoLia doc. (default is 'current'). Implies --filter=NO. (-x and -F disable usage of most other options: -nPQVsS) Input/output --------------- UCTO has two input formats. It can take either be applied to an untokenised plain text in UTF-8 character encoding as input, or a FoLiA XML document with untokenised sentences. If the latter is the case, the ``-F`` flag should be added. UCTO will output by default to standard error output in a simplistic format which will simply show all of the tokens and places an ```` symbol where sentence boundaries are detected. If the input text already has sentence boundaries in them, the option ``-s `` followed by the end-sentence-marker string can be used to let UCTO preserve these end-of-sentence-markers. When UCTO is given two filenames as parameters, the first file will be considdered the input file and the tokenized result will be written to the second file name (and overwrite the content of the second file if it already existed). UCTO will write the output as FoLiA XML when the parameters ``-X --id=`` are used. Interactive mode ---------------- UCTO can also be used in an interactive mode by running the command without specifying an input file. In the interactive mode you type a text (standard input) and the output is given as standard output. This interactive mode is mostly useful when editing a configuration file to adapt the behaviour of UCTO on certain tokens. Multilingual text ------------------ In case a document consists of mixed multilingual texts, UCTO has an option to apply the automatic language detection tool TextCat [#f5]_ [#f6]_ that guesses the language of a piece of text. UCTO attempts to recognize the language of all fragments (pieces of text separated by a new line) in the text. UCTO is limited to fragments and cannot handle code switching within a sentence nor recognize the use of one word in one language in a sentence in another language. If you have multiple languages within the same document, you can run UCTO with the option ``--detectlanguages=``. The first language in the specified list will be used as the default language for the whole document. UCTO will first apply TextCat to guess the languages of every fragment in the document. The language-specific configuration will be used on those fragments categorized by TextCat as written in that language for each language that was specified in the list after the ``--detectlanguage`` parameter. For fragments that were labeled as another (unlisted) language, the first language in the list will be used. Note that the option ``--uselanguages`` is intended only for Folia XML documents in which the language information was already specified beforehand. Example Usage ---------------- Consider the following untokenised input text: *Mr. John Doe goes to the pet store. He sees a cute rabbit, falls in love, and buys it. They live happily ever after.*, and observe the output in the example below. We save the file to ``/tmp/input.txt`` and we run UCTO on it. The ``-L eng`` option sets the language to English and loads the English configuration for UCTO. Instead of ``-L``, which is nothing more than a convenient shortcut, we could also use ``-c`` and point to the full path of the configuration file. :: $ ucto -L eng /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser... Mr. John Doe goes to the pet store . He sees a cute rabbit , falls in love , and buys it . They live happily ever after . Alternatively, you can use the ``-n`` option to output each sentence on a separate line, instead of using the ```` symbol: :: $ ucto -L eng -n /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser... Mr. John Doe goes to the pet store . He sees a cute rabbit , falls in love , and buys it . They live happily ever after . To output to an output file instead of standard output, we would invoke UCTO as follows: :: $ ucto -L eng /tmp/input.txt /tmp/output.txt This simplest form of output does not show all of the information UCTO has on the tokens. For a more verbose view, add the ``-v`` option. Now each token is labelled with information about the type of token, and optional functional roles like *BEGINOFSENTENCE* or *NEWPARAGRAPH*. This information can be useful for further NLP processing, and is already used with the Frog NLP pipeline [#f1]_. :: $ ucto -L eng -v /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser... Mr. ABBREVIATION-KNOWN BEGINOFSENTENCE NEWPARAGRAPH John WORD Doe WORD goes WORD to WORD the WORD pet WORD store WORD NOSPACE . PUNCTUATION ENDOFSENTENCE He WORD BEGINOFSENTENCE sees WORD a WORD cute WORD rabbit WORD NOSPACE , PUNCTUATION falls WORD in WORD love WORD NOSPACE , PUNCTUATION and WORD buys WORD it WORD NOSPACE . PUNCTUATION ENDOFSENTENCE They WORD BEGINOFSENTENCE live WORD happily WORD ever WORD after WORD NOSPACE . PUNCTUATION ENDOFSENTENCE As you see, this outputs the token types (the matching regular expressions) and roles such as ``BEGINOFSENTENCE``, ``ENDOFSENTENCE``, ``NEWPARAGRAPH``, ``BEGINQUOTE``, ``ENDQUOTE``, ``NOSPACE``. We explain these token types and roles in more detail in the section on Implementation. For further processing of your file in a natural language processing pipeline, or when releasing a corpus, it is recommended to make use of the FoLiA XML format ###:raw-latex:`\cite{FOLIA}` [#f2]_. FoLiA is a format for linguistic annotation supporting a wide variety of annotation types. FoLiA XML output is enabled by specifying the ``-X`` flag. An ID for the FoLiA document can be specified using the ``--id=`` flag. :: $ ucto4 -L eng -v -X --id=example /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser... .. code-block:: xml

Mr. John Doe goes to the pet store . He sees a cute rabbit , falls in love , and buys it . They lived happily ever after .

UCTO can also take FoLiA XML documents with untokenised sentences as input, using the ``-F`` option. Limitations ----------- UCTO simply applies rules to split a text into tokens and sentences. UCTO does not have knowlegde of the meaning of the text and for that reason certain choices will lead to correct tokenisation in most cases but to errors in other cases. An example is the recognition of name initials that prevent a sentence split on names. However, in a example sentence like this, no sentence break will be detected as the 'A.' is seen as a name initial: * Dutch: *De eerste letter is een A. Dat weet je toch wel.* * Turkish: *Alfabenin ilk harfi A. Viceversa burada mıydı ?* Such problematic case cannot be solved by simple rules and would involve more complex solutions such as using word frequency information or using information about the complete text (names tend to re-occur within one text) to determine the likelihood of a word as sentence start. This type of solution goes beyond the current UCTO implementation. Implementation ======================= The regular expressions on which UCTO relies are read from external configuration files. These configuration files and abbreviation files are stored in the **UCTOdata** git repository at https://github.com/LanguageMachines/uctodata. A configuration file is passed to UCTO using the ``-c`` or ``-L`` flags. Several languages have a language-specific configuration file. There are also some separate additional configuration files that contain certain rules that are useful for multiple languages like files for end-of-sentence markers and social media related rules. Configuration files are included for several languages, but it has to be noted that at this time only the Dutch one has been stress-tested to a sufficient extent. UCTO includes the following separate additional configuration files: * standard-eos.eos - Standard end-of-sentence markers * exotic-eos.eos - End-of-sentence markers for more exotic languages. * smiley.rule - Rules for the detection of smileys/emoticons. * url.rule - Rules for the detection of URLs. * email.rule - Rules for the detection of e-mail addresses. Language-specific abbreviations are listed in a separate file that is referenced in the configuration file as ``%include ``. These abbreviation files are created rather ad-hoc, often using https://wiktionary.org as a source for finding language-specific abbreviations. UCTO uses the unicode character properties and labels specific characters with their unicode property *general category*. Unicode character *symbols* (like the trademark or copyright symbol) are labeled as token type SYMBOL, pictograms like `thumb up' are labeled as PICTOGRAM, emoji as EMOTICON, currency symbols such as the dollar sign are labeled as CURRENCY. UCTO starts with dividing a text into fragments based on the spaces already in the text. Next UCTO applies an ordered set of rules to each fragment. Each rule consists of a rule-name and a regular expression. The part of the fragment that matches with the regular expression, is labeled with the rule-name as its token type. For example `Mr.' matches the rule `ABBREVIATION-KNOWN' that checks the fragment against the list of known English abbreviations. If the rule only partially matches with the regular expression, the remaining part of the fragment will again be processed using the ordered set of rules until a match is found. The result of this iterative rule application to all fragments is that all fragments are labeled with their token type. UCTO uses these types to determine the functional roles of ENDOFSENTENCE and BEGINOFSENTENCE. Rules ------------------ The regular expressions that form the basis of UCTO are defined in *libicu* syntax. This syntax is thoroughly described in the libicu syntax user guide [#f7]_ (http://userguide.icu-project.org/strings/regexp). The configuration file consists of the following sections: - ``RULE-ORDER`` – Specifies which rules are included and in what order they are tried. This section takes a space separated list (on one line) of rule identifiers as defined in the ``RULES`` section. Rules not included here but only in ``RULES`` will be automatically added to the far end of the chain, which often renders them ineffective. - ``RULES`` – Contains the actual rules in format ``ID=regexp``, where ``ID`` is a label identifying the rule, and ``regexp`` is a regular expression in libicu syntax. The order is specified separately in 'RULE-ORDER', so the order of definition here does not matter. - ``META-RULES`` – Contains rules similar to the RULES section but these rules contain an additional placeholder in the rule. The first line of the META-RULES section defines how the placeholder can be recognized. The SPLITTER denotes the special character that will be used to signal the start and end of the placeholder. In most cases the SPLITTER is the \% percent sign. - ``ABBREVIATIONS`` – Contains a list of known abbreviations, one per line. These may occur with a trailing period in the text, the trailing period is not specified in the configuration. This list will be processed prior to any of the explicit rules. Tokens that match abbreviations from this section get assigned the label ``ABBREVIATION-KNOWN``. - ``SUFFIXES`` – Contains a list of known suffixes, one per line, that the tokeniser should consider separate tokens. This list will be processed prior to any of the explicit rules. Tokens that match any suffixes in this section receive the label ``SUFFIX``. - ``PREFIXES`` – Contains a list of known prefixes, one per line, that the tokeniser should consider separate tokens. This list will be processed prior to any of the explicit rules. Tokens that match any suffixes in this section receive the label ``PREFIX``. - ``TOKENS`` – Treat any of the tokens, one per line, in this list as integral units and do not split. This list will be processed prior to any of the explicit rules. Tokens that match any suffixes in this section receive the label ``WORD-TOKEN``. - ``ATTACHEDSUFFIXES`` – This section contains suffixes, one per line, that should *not* be separated from the word token to which they are attached. Words containing such suffixes will be marked ``WORD-WITHSUFFIX``. - ``ATTACHEDPREFIXES`` – This section contains prefixes, one per line, that should *not* be e separated from the word token to which they are attached. Words containing such prefixes will be marked ``WORD-WITHPREFIX``. - ``ORDINALS`` – Contains suffixes, one per line, used for ordinal numerals. Numbers followed by such a suffix will be marked as ``NUMBER-ORDINAL``. - ``UNITS`` – This category is reserved for units of measurements, one per line, but is currently disabled due to problems. - ``CURRENCY`` – This category is reserved for currency symbols, one per line. The libicu syntax and unicode character encoding already take care of recognizing currency symbols (\Sc) like for example $ for US dollars. However, the 3 character currency code strings (like USD, SGD) are not recognized by default. For Dutch we added such codes to the Dutch configuration file. - ``EOSMARKERS`` – Contains a list of end-of-sentence markers, one per line and in ``\uXXXX`` format, where ``XXXX`` is a hexadecimal number indicating a unicode code-point. The period is generally not included in this list as UCTO treats it specially considering its role in abbreviations. - ``QUOTES`` – Contains a list of quote-pairs in the format ``beginquotes \s endquotes \n``. Multiple begin quotes and end quotes are assumed to be ambiguous. - ``FILTER`` – Contains a list of transformations. In the format ``pattern \s replacement \n``. Each occurrence of ``pattern`` will be replaced. This is useful for deconstructing ligatures for example. Lines starting with a hash sign are treated as comments. Lines starting with ``%include`` will include the contents of another file. This may be useful if, for example, multiple configurations share many of the same rules, as is often the case. How to configure UCTO for a new language? ========================================== When creating your own configuration, it is recommended to start by copying an existing configuration and use it as an example. We refer to the libicu syntax user guide [#f7]_ for the creation of language specific rules. For debugging purposes, run UCTO in a debug mode using ``-d ``. The higher the number, the more debug output is produced, showing the exact pattern matching. Note that the configuration files and abbreviation files are stored in the **UCTOdata** git repository at https://github.com/LanguageMachines/uctodata. If you created a configuration file for a language or genre that might be useful for a wider audience, please contact us (lamasoftware@science.ru.nl) and we are happy to add your contribution to the main UCTOdata repository. Acknowledgments --------------- We thank Ümit Mersinli for his help with the Turkish configuration file. .. [#f1] https://languagemachines.github.io/Frog .. [#f2] See also: http://proycon.github.com/folia .. [#f3] Nederlab: http://www.nederlab.nl .. [#f4] NFC unicode normalisation: http://unicode.org/reports/tr15/ .. [#f5] TextCat http://odur.let.rug.nl/vannoord/TextCat/ .. [#f6] Cavnar, W. B. and J. M. Trenkle, 'N-Gram-Based Text Categorization'' In Proceedings of Third Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, NV, UNLV Publications/Reprographics, pp. 161-175, 11-13 April 1994. (Available at http://odur.let.rug.nl/vannoord/TextCat/textcat.pdf) .. [#f7] libicu syntax: http://www.icu-project.org/userguide/regexp LanguageMachines-ucto-688c2af/docs/todo000066400000000000000000000001111472777655400201410ustar00rootroot00000000000000Nuttige link over Quotes: http://www.cl.cam.ac.uk/~mgk25/ucs/quotes.html LanguageMachines-ucto-688c2af/docs/ucto.1000066400000000000000000000122561472777655400203220ustar00rootroot00000000000000.TH ucto 1 "2024 apr 11" .SH NAME ucto \- Unicode Tokenizer .SH SYNOPSIS ucto [[options]] [input\(hyfile] [[output\(hyfile]] .SH DESCRIPTION .B ucto tokenizes text files: it separates words from punctuation, splits sentences (and optionally paragraphs), and finds paired quotes. Ucto is preconfigured with tokenisation rules for several languages. Those rules are provided by .B uctodata .SH OPTIONS .BR \-c " configfile" .RS read settings from a 'configfile' .RE .BR \-B .RS run in batch mode. Process all inputfiles to an output directory specified with \-O. .RE .BR \-d " value" .RS set debug mode to 'value' .RE .BR \-e " value" .RS set input encoding. (default UTF8) .RE .BR \-I " value" .RS set the input directory to 'value'. (batch mode only) .RE .BR \-O " value" .RS set the ouput directory to 'value'. (Required for batch mode) .RE .BR \-N " value" .RS set UTF8 output normalization. (default NFC) .RE .BR \-\-filter =[YES|NO] .RS disable filtering of special characters, (default YES) These special characters can be specified in the [FILTER] block of the configuration file. .RE .BR \-L " language" .RS Automatically selects a configuration file by language code. The language code is generally a three-letter iso-639-3 code. For example, 'fra' will select the file tokconfig\(hyfra from the installation directory .RE .BR \-\-detectlanguages = .RS try to detect all the specified languages. The default language will be 'lang1'. (only useful for FoLiA output). All values must be iso-639-3 codes. You can also use the special language code `und`. This ensures there is NO default language, and any language that is NOT in the list will remain unanalyzed. .B Warning: To be able to handle utterances of mixed language, Ucto uses a simple sentence splitter based on the markers '.' '?' and '!'. This may occasionally lead to surprising results. .RE .BR \-l .RS Convert output text to all lowercase .RE .BR \-u .RS Convert all input text to all uppercase .RE .BR \-n .RS Emit one sentence per line on output .RE .BR \-m .RS Assume one sentence per line on input .RE .BR \-\-normalize =class1,class2,..,classn .RS map all occurrences of tokens with class1,...class to their generic names. e.g \-\-normalize=DATE will map all dates to the word {{DATE}}. Very useful to normalize tokens like URL's, DATE's, E\-mail addresses and so on. .RE .BR \-T\ value or .BR \-\-textredundancy =value .RS set text redundancy level for text nodes in FoLiA output: 'full' - add text to all levels:

etc. 'minimal' - don't introduce text on higher levels, but retain what is already there. 'none' - only introduce text on , AND remove all text from higher levels .RE .BR \-\-allow-word-correction .RS Allow ucto to tokenize inside FoLiA Word elements, creating FoLiA Corrections .RE .BR \-\-ignore-tag-hints .RS Skip all .B tag=token hints from the FoLiA input. These hints can be used to signal text markup like subscript and superscript .RE .BR \-\-add\-tokens ="file" .RS Add additional tokens to the [TOKENS] block of the default language. The file should contain one TOKEN per line. .RE .BR \-\-passthru .RS Don't tokenize, but perform input decoding and simple token role detection .RE .BR \-\-filterpunct .RS remove most of the punctuation from the output. (not from abreviations and embedded punctuation like John's) .RE .B \-P .RS Disable Paragraph Detection .RE .B \-Q .RS Enable Quote Detection. (this is experimental and may lead to unexpected results) .RE .B \-s .RS Set End\(hyof\(hysentence marker. (Default ) .RE .B \-V or .B \-\- version .RS Show version information .RE .B \-v .RS set Verbose mode .RE .B \-F .RS The input file(s) are assumed to be FoLiA XML. Text in the correct 'inputclass' will be tokenized. For files with an '.xml' extension, \-F is the default. In batch mode, this forces to only select files with the '.xml' extension from the input directory. .RE .BR \-\-inputclass ="cls" .RS When tokenizing a FoLiA XML document, search for text nodes of class 'cls'. The default is "current". .RE .BR \-\-outputclass ="cls" .RS When tokenizing a FoLiA XML document, output the tokenized text in text nodes with 'cls'. The default is "current". It is recommended to have different classes for input and output. .RE .BR \-\-textclass ="cls" (obsolete) .RS use 'cls' for input and output of text from FoLiA. Equivalent to both \-\-inputclass='cls' and \-\-outputclass='cls') This option is obsolete and NOT recommended. Please use the separate \-\-inputclass= and \-\-outputclass options. .RE .BR \-\-copyclass .RS when ucto is used on FoLiA with fully tokenized text in inputclass='inputclass', no text in textclass 'outputclass' is produced. (A warning will be given). To circumvent this. Add the .B \-\-copyclass option. Which assures that text will be emitted in that class .RE .B \-X .RS All output will be FoLiA XML. Document id's are autogenerated. Works in batch mode too. .RE .B \-\-id .RS Use the specified Document ID for the FoLiA XML. (not allowed in batch mode) When not provided, a document is is generated based on the nema of the input file. .RE .SH BUGS likely .SH AUTHORS Maarten van Gompel Ko van der Sloot e-mail: lamasoftware@science.ru.nl LanguageMachines-ucto-688c2af/docs/ucto_manual.bib000066400000000000000000000004251472777655400222460ustar00rootroot00000000000000@techreport{FOLIA, author = {Maarten van Gompel}, title = {{FoLiA}: {Format for Linguistic Annotation. Documentation.} {ILK Technical Report} 12-03. Available from {http://ilk.uvt.nl/downloads/pub/papers/ilk.1203.pdf}}, type = {{ILK Technical Report}}, year = 2012 } LanguageMachines-ucto-688c2af/docs/ucto_manual.pdf000066400000000000000000006017431472777655400222750ustar00rootroot00000000000000%PDF-1.5 % 3 0 obj << /Length 420 /Filter /FlateDecode >> stream xڅn0E .I )%Ab IpUcъZ[ 0п/Z$h8$枹3C:DnCs4i%Z3dHirVe\֑BPk^a7!`k)TW ZBd8~$0ժd`Tuэn8$>R!+Ja5atv]L_خ?)RrHkC)x>aXib Wk@>]  endstream endobj 11 0 obj << /Length 284 /Filter /FlateDecode >> stream xRN0+hl~ T8bHi@M8EMiZ@Jl 5w!4oBr5X\{h^aMGc>7w_^vL4gs^Mm(QseArmA/8M 4) endstream endobj 14 0 obj << /Length 1669 /Filter /FlateDecode >> stream xmWK6 Wxr@E,޿ީj*b\M|QtW};J+6cûRvbUd~Yuq6h:J ؀4LQ5H&Ȇ]dkTqbh[%* Chbr`  mF) *_yuVY*/T>ȫzp!8F3L |\JH!CwYV*yN]q-5-{CAv`6$:u/?ӈ/ųa&84!@ rċ@c(x_y 9~6HW='dn; ɳ7̱!3/\Nkq͌quMEA!X QT@e1A#h~ڝQ)30g'>ts=`Kۂ:Bwd .JfdZ.NuR{9"SI4KlTs^y7zh^\3 ; agŎ]g\k;$J!ǩ𮅚K23X9G ؠ ,>wTż8,/̓1P!oEI L*և7?43$ɝ:H< VLmD#31/3B4@t/~ЯP)٣s>q$y Mk Ƚ EeWNq$/h0{hm/l5Vt))vc'Bg=)O y Ӻt|3Lg> stream xڅW[o6~0D1-$PKi b݃"QVYt)[a{1s|ĝ\q"~3 0 $'x@x܏&q6$VT 7.t뤤}X)oTWFY8JyhT{G8S_IV4,#CcBw%~L LGiRѦYѴuصҚTԤr @:+StMv}? g!+[Rsfr\#i פŐ{4D!C1Tp"OkSbJJT4?.@#(}ºn Wk7gp 9}uΘ1;(A$(pw`k|=}q(lH_Ck:l9[beIcƮyWBR 2{IrqL2gG@6BA]xϘ]:vWט?铈X%t«` +X,Qr^r(}Â{'<nn}n ('(r \KnMi6)%$)B]`7 FEZ BϓВBPbe0UinpO;8¼@EKS=aCHaCseNW=F)@K~986slĎiVlԎ` j~_CT).Adrv,CFP0 ;H0 k)!0!ۂ@֮!J:v=[l`O"3RȐ=GS6wQZBng|d+9* @GCͺ4I=t;bUk{Xe60MB O`zdgu/%ٯ"ӖM#MoÆWX%7u؍3`CX"ܺd}}q}Blh$[^$Y3.~> stream xڝWK6 ϯȡ8-;l @Q:V`3_R'N{IHQgY<.߭?b(/r>[mgpl[P|!dP8,ͽ ,ٷ]Q!IjwtO?ϥ`nuhKF.gͅ\?By aK'aE҉8+wOγAgNd{ IW*!'})N6ʫ2۰=zɂY}1d۪֍U4c+o~GC$&<mBA!$q꒗ 6~߅j1NBp\`@^ fP)\-N,!ۨz+;sMynfW |"R^Py ~;r9}qDE)v/D>h4):˧1fhH! 'roN*;"Йޓ7<'#(r8'|!W>Q, +rx\FeF ^z\W]X,Пa?=(|[p;_WGMd$yGYϡ|a;j`0Oq&`$0Y$nYUK]ׄJJ^0߾$ tQ툦c!< r2U^ګ E ^MS">7|L:K91fbLPPHڡkPxSL娌kH- pIRȯD ^B$'ؑ]Eǒ.<󻩻>$ǏZ{( DBJ?S endstream endobj 27 0 obj << /Length 1467 /Filter /FlateDecode >> stream xڕWIFϯp$x$^%b!0Cݞ2x}<Ȑ^kʡwBfTF,"K0̼}x~z6"I,o^٦߿S-9T8yDMwȘ1'n+j$컆V"|h>7.EtrKB2% z "=pC׍3xy ]޵[q͚߼{Ս6mJd~5Wy10TeIauMc:)!~^\s=V{1%r'Xw]rŔI”z-?O.w3 st{SV_1uIg"ɻ3DY V-eGFB{ ʩzkGӈq̫9%L!aʑ Ob_kUM)SuAmX5}i){4qY9${wGrbYr[aDyIꍯyKD /X7]oH,*]WyAr0$), 澪V"L>x i$,u@}RB@ sb#~]17HV%(`"2&MPfd)XcK%_-f_ت!>H4#9h{QL9Źwx`Nn!ml BE a9.% "ͩjG^P6_Ө0y̕>tXqM9W 2dHɹ:.f͐W~A[D58t޸{gGr\|iΟ'3!5OlܷZ7zV!LO]m,*Г1GKټz\LfwkI ʑiMuÈ By U-ZfnȔb쌩ZכOx~U'6}]؋~ endstream endobj 34 0 obj << /Length 1625 /Filter /FlateDecode >> stream xڍXK6 zro;v{*=t{J"c;fsж{RNo۬tovWElRkXiE%pzZ;7z 8_8VD$f*x :L~-Gc^ݠ8֌5UvFbZ}SW-w&QL&:+/reg'8Q+Yz|f՗z;|Npю-j$2鞜vGYyy>i|/a] [8CdUDWԸ^q@]C{'?%AِmmH]qR6ѥ'$yF1t dt$i= ceSG_N["|Y7etSˎ`U̵ilK78K]˙]Ӕ {&ػzdgB=,o?MJ9_*Vv%T)*L"Nlo `:xvY  !rlg² _1viLڜCTvbL*fnK'uG!EG!<@)BP0/2XC,^,fqC6c[Cyu!jQ"f.8˨]p$捗ήtڛy2UQlg;pUYAjit0iZRlq̢/ ۹XYDs]`:,xgn_@{e\txO7֚_^0ڙ7n^kIq|CS9!@0^L\̎}#t%S&{4|wTvuV&ܢ'ES3 ֍^`XRlͣJzdݨ՜y!RpH2ɢiQ s#~LwR)7fhQ^nTPYX̰?p-ݷ:SbyE-a*UaT K"` b}G#:t߲-CsPreVa#pu6ACX(hɛV"_Ӽ@ FX̙~ +{`e}ņ gI5WSzAz"z7/Gu3^! "-׺;ZsI~Q5y4J$IxؠTߡJw?IHZ)jMp|hE6]IiD GqSÇAje endstream endobj 38 0 obj << /Length 2044 /Filter /FlateDecode >> stream xڝXvF+ 4Žf;#3b$"Yg~~n=24ylWuխ[Wͫ]eneKhj]o\ݬ0[I8}껫u8o֩q6ן>N 3țYWVa쥱9u\A]6N T|󆾉Ø"+d/5eS"ϻ5,M;x4sЋL(|5c.?-zC6"|;Wu~;hɜ}v0bvg5C]5j/y_D^YLعn*ہzzǰiݷ"n`\@Xvdj?gZzWB''>'hܒq:w.+p, 3''ԩg ~e/EsӇCJ7E@۔|] s[z'ÏvtӖ[1vP7݂Y$襭 f/sy/d-B(veUCVFF`F Hv##N^0w̛O5"'MiH-!ǣpgO ] pfz-g֮1ui}.gT.0 V @'0p뼓pؕ}-z0}8` 2,R'ˍXoiF5z*nM.>%ټ|$̓3, 8LdeÅC fSv%؋yHqa#c`| !/{L6N *"Hjzܲ50mm̫sne!)e|4S1 U.lY03ލ Ar#|>"le:C#,R/`tyJN[|g4b=&U?5䊺fxٕD/dgy}pċPPጜ٢g`4^N8ÕLm4/lC&[2CzBzan HOP#v6aEĞԄ% TT {bN7X5Mtsr ݣ hЭ6oiTk`x'Ҏ.UmQb9M,dIܰued%r2Qpϋud=Nֹ!G Fr;J&8H/ 5?rbÜ #ꊼͷq!D;uhHϞNAE! %.,|v|<Ղ^nB µiӀmpcCԝ~HO59$p"@3 /î  zY KFΑdiT\)vgE.Z$Zw R1mx/Oɒ3UDE:OEߺQ3K8~vQ]"?CR9 m׎G۲/JM4=rn?¨Tu]+"k.0q@^dgs:$ GTt[lTvbi.\<mUZN0?ݙ,f ;)x686ʗD vLI$dPI" KV裏sTvD;o޾ H?iqZO}N?lk5Z箑JyxVqŪMY'ՔZLgzBkzm#?cUZb+s8Jp*B׋,^{-9V@ߑi NOMRV_9 g5+)É`ѡ.LeP9IqyCqh??AIg>wQ$fDg_H8IFK 0-EϏ~Z;KBğa=}6յj endstream endobj 42 0 obj << /Length 1924 /Filter /FlateDecode >> stream xXKo6WQ t(8MlN k5YrUb^k(Z >x!)gofHoy_Yz} ÙIr{`dZ~w}\-O )#"R9~^~) \̿@~YElSS,I'7[%JKQE|+X\7Ob,40MW*73WJin(l[~}tajb*|ʢ6nDߤU)_)LHRQ ~.T ,Z̜1`~Pv)HPju~yYa gP$[ hS[Zi"&#vNǓ L\^c^V뚇2NoZ`cr>ⰳBc^Wt2sA{Ec%.蝁E zȀ]/pxTHZHp6aӰ=q7,n0S|0|`jUVqm!j@RYSU˹uEzmh^A&)ұ 'X.{^`XFCaPfIǶ=- ;dwm17JS[hck9GQQ|yht&!h9%)_lyszQ^.j{zM7tbKV4 olx||b Iŗ3M?p!GP+]/GI]xx;#hbm֙$$ L6]'0suŰKc04ekM(SjP28LX/oMr;HS,o={TjdL^nllL kx]XeI_M߿@_NVUiJ2^$I_Գ/qWS&5I'j1<%>%ޘWOQ vOR+[6sIH; 78ި izT8GM579HeֆlՉpJF]7NiH*)IifӔ?{B endstream endobj 45 0 obj << /Length 1335 /Filter /FlateDecode >> stream xڅWݓ6/g  oN7G1mm<Vpa'O)q-~yݼB\d$`1dWot\R1/Wl].ϖde,X}_b#u*VY"70|_lW!a +Ag8'f{gJFjꥌXuĨʶUsog=4weS@(iA`S%:mj:"Hj甅*y9Y%?_*͝-U@OD ;*)o-odD;w¢9C2fMT|Lg~(z.a I$q†#vC!dJ%-3u6P:n )t|mhf4bLlLVH`]PGΨR-sD0'j{੼E84neJ*Hlc$ @ 1z"`hOX6єs|͐h8mX76r hlC-a]8;<MvNPmP4h091/yh0 b1k GmUt2^U/}I?pr6=4HAHk\@h=,(&B(J(OԂ > stream xڥV]o0}߯O l !Xh0 B{pp;ufK~{Y;(ϗˣ0w,t3#?ɝe\Rk̼8Kdv| 4Kx"kjp`;v?NȰyGȞ+h2eKg!["J3A1.?x.gxQYk&뤱<Ĝ%'&Ρ"'~w'&~hi0u Ř[UIl](Hy'S6@gbkAg`QsV0"jZ'@6xCZZ;5 { @񽤫vORRKtM( +!bTm _4(iEZn͟pAPfK8W{^/N9𪙗EAxŔQPl)M UPfц4ЦLܦʼnúBba N_Zn!pn(Vh'=$0 ,NǮWV[{{ax͛qQN&.ohS5_ں[%TtgsbBFwԻ1gڬ۾w/?lbYy{iaYQz5QJo0R< >A˪8!DtX  Nd3Hr[s[eTPOhWɇY]7ZʻE|k V<8:T[82*̶> stream xڽWKs6 WEz+dƍg663Mˉ,H+GnrI/$`]7GNΣd!($\6 "E"j{K? S/K?KCeyo^/Y;9š(EZ%N@o+C^(y*I AK?[ou7ȟ_4N)k]["_po 2pٗ.4$xk쎄|߬_89VωRzMyqrARsfM.K&Vh%q7ԕ6&(ڭR8`%HxT lrSW,W[l]7/SZiG\A!Q"8$J ANu[S;HrӴ2,ke9`Fw"BR+^‚8fG(LFvېTm:|ZX7$9WִDS=_GG* k\ VVY\ץƘpCg_&Dl;OSn1«2qeGP9{k_XDrd>zЄB$-mO\yq}ҦX&bN-m: 8=: o :ȁEeoɨ+G S @X°aUs >pqws4cyH1s Yv{S׈c(hb6HdctrՅ\u oAAr'c&_&NA0Ȇ+ȕd1EW%"b K,*;eb4$ .X@Ie bQsb'jB J!EXD?\5-zjjBW5'Ii,Ԡ5\# TNG$T` UnP8P wK`CF;fry`^mߪ{ζ4 BVxlh\y<b1PD!DQCv[-nlk\7XpewiJ\*Яz[kKjy4<9Brt9B 8eθe>\>u u8 X$@|F~@w.()sOzu/& endstream endobj 54 0 obj << /Length 814 /Filter /FlateDecode >> stream xڥUM@T-ÇPuˠSA`M3=_wnSY)27*e\)qX&2|QofOS: fq8tychzCC:}gdigvEA7˂h6{{8aMw-W1Q0<(C,LY5XHLR_%ubDYA&?qN4KcN[? IF&),Wk>RKMG]S-wtҖg?L1IQSe4aiR L"4䫒;Ya0O =ZIjǓF x>h"T\Сm -PV%3Cuׄ'"mk 6JSKעz eÎM)]cX'TZ3[@&-Pw5w؞:S,Ц0Dqyuc%p P>"i*Y!i 5߲o dz 7:|G޿Cd$Z4|*2˿'pdJ‰9[x01ǎ-IA(aДòqe 9_+>k<6 4?GEGp<0hq.f<σ]["Ŕ@79bV%A;ϰL1Wm1ax4`H}g f.B^HV]^\lKЫmy^x& /Jq+D ]-rrr_ο(_ZI=S endstream endobj 58 0 obj << /Length 4008 /Filter /FlateDecode >> stream x]Ys~`V-G{'ݕJ^[nDI,SǿO4!'1R:O|r\k-7 XX].^GRD}s:6yq6'Ϲ/Hk8JORY=VICuwC=|yqNοx~ ǜ U}=={|IRM?NG xa: PJe#ʕ4U߬ZBͫOb݆(7OWPlņ 82YM a Iv0.̳"|y@LLu׿t~KWl Z,t"Y,\rYf"xd 7$`U-80W ݙIIrt>{OOwVx&cbYgkJ\-'k2^@&TڬT=T.~}o?(,xwwj-wʱŤ:^ۦ̂3J@1<~/DeߠtƽLWx BWM-Xu9OJEUOk0<8Ps9Yě7aJT*Ja`N\څMi:ӠqM*8|q}uvhtr>7IY1{h8$Uqm8WXäj4Ӯ~&P WUhRNJ=)gܸ~ʂ8NqCpadka䘒ya_&ČĄĊڻI!a~^3LbVLNIt#9>4XK\їCwnb!ioZz7;T} 2QLWu_)bDoͿk3{0S(LsOٌJs*JY$t., gsɒx[Ҵ2,ӊN> =ǃC |#%Dڡ h--IܶC8ɸӉQE\-f$$\ڶjG14(834P 4XUhRN]=)kF1ZLhGƇڙ;Qy vKT-I(ӼNँM|'ڥR0hi>CV EN(=ҔJס%b-6QɇAAoKKc.Ԇ{c4w: h @UX+ۃbi^4LYhP8zO *㮓tJ3[bH۶ӝn;=ʣfIw Rj?2?,`bc3PvlZh\=(f qgL*0"ҸϷ Yfϋ6lEa7Ŭ'c~;<-nx%ؤ~($iNh"ѡk<@z0So h UX+փV@p0?r`i~"F(=R闹=B˹u9!]SDlJ\8!!ұVð3c5W:{o1X,ǂ:x6MPV=$eXTNU8q!ױVc3c5ڦٴN6ջhi ~`ز]`V +δ'inUeq'%Xu8v;8 >UC3-S2=pc˼jBК7:xt ?^̈́eQthxm~x3</*Y'x8:.c&=<Ȱ1x-p3TV;acbf+isR ᧗~χ8/p mD>:HÔ;&s0 -P ~]UhR=)&s0^Fu 5dn7>O<~JC5da@waԩ(e#{.#>4 UX+܃jmn;rNZ_Ψ.p3T3V;c;PfjpFϏ`')Y:#^sN+4TL`Z3uCZ)oT ْ0y 7r )lSJ'wW뇧''_#O_-vw6f1kO7uj=E endstream endobj 63 0 obj << /Length 2892 /Filter /FlateDecode >> stream xoW}՘=SqM(胑זӠKR;䬗#͜!` KLV칗g)N|tӫ?\=\sw9+:ܼj~'_0bkkD7¶Oysi sң .=n9m9m\togx˴˷WO뫿O8i19ϿWoh_]~m}|3V@ PG}Oʓ1BbL b*2g3Pg>f9&lr*}Oe n}vֺp𠟜c\&!N3C&!٨DwRpup֙Qi3=^$h&;r޾_2-0į0'llTŒqyfDU  JZ&dFCш}oxfW}ixʱ7ǯzqyJӸyf`prtvfdyeI/=[/m Z U1qF%#.;P+ȄiC!VWv=&āJx1.؋J?dY /JV⓯ݓoQf$~ÌlTbST0+Ȅl+z|o/e Ûc͑J4G\^qs*CW g%FG0zW&>gԌe3WjFXjȄͨe~?_wYBm^d;rt {׾;\+7E޽}:K!TwI٨+Ja\W g-tz)LϔRӦ&Y޹217NCَ)^!&MWQ^+T 2DLy17ā͘J1.،J@dY 3:~]^_}Oݿw{Xs.;&KRw8F%m\^EU L8k9%uί 7 RA,nlTU)XL8+=c\LWxwތ10c\^Q*ȄΘQi>c6tl4l8Q ;U)XL8+aG*f턺u^ɕ_uu_7ٕ^)y|$^8}peٌftp䣖IyV5dYPE :  _~XrtY٨<+JaV g-~?QO/^8\/ߦcvz)inlT)U)L8k9dHn37гf،٨͈ TA&0#}'{W쉷(ꎹ KH8> stream x]ko_!'~mwfu~HeclbHCLN4sG`ZHQu=:CAW?ɟO=jqJX+WFXB[Zhw珿_ I֧Fgkn? sCa4V:&ڕNv99?rXV4[];iV6'ji^k_nwl]=Ԏ߽DI1Q}YNTX NӣtDq2&`= >OͯSy󮝱__KZM7ܪj'5jf ti7 ӗml{n6䠭Z Rnϭkn]q3Wm5 \6x2\Vlv&̌!&X5~Mr;}nZn?"K?ka(m֧6׻s9u埢uoT㽿A{6TR 4F_C aOZ%na$!1RE"Trzk /~ADx2DңQ.h#` RnlD7 4ᱦ6pH)9^qJ@Ъh18h1fC%W,F,KA@hc%Ĩ/iu!2 Jg.eکy;fde|lozOd*YlB\F.xPX "9Z>v`_Ea# C>zt'dC%Z!.,W a\I+b^-\ڊd(hO*BdfK}~9{10?eXSǽA;j6TR=Rp 4ᱦ.3Djv ـW.AM[5(`Нh@2 TELWba>Դ+U"~jЄǚr(Ŗ_||K2<8h[͆Jj\^bY VX&# Ϥ]G]gW,0 Cu?hz6lqhc%BZ^W=̧4d\ $il)hcMyc6TBqybIJT&gZ.mlpD9/c %8ɆJtN\^q`Y j@+D$2q#bapZP 1RPX 1JNK,~X.(s WǽAi6TOR 4ᱦc.1c]m|'҇ yY 3I9ztdC%z$.G,]W  oA0h)"%V,D$CA;xP RM4_߰$_pVkPӾW^Yu X)Іs;ӼyuKa(iG*à;%)(Qm}d(HOj: qˉaspkCX p:̆J1.XX~*ЄJP0KZןZLY"JR^`VpڨbE2Oj:+K,L\ u;!* qyŽe)(MxD萚X5 '`DT?-lňe)Mx+p!Az 2q戨p3ZP 9RPX#r 0/}f^޾k󶹽hW7WesunP)k~:/ZQ!lK\aVv>ٶĂ&~{y}'ϡ+ ZƤ endstream endobj 69 0 obj << /Length 376 /Filter /FlateDecode >> stream xU=o  F, 8[6QtE?TXN_0VTO{w\m wTq*R P°$a.@^ܪKu-( dzmJq5 %fIkO_R$RAC9;{m &``{$@AmN5 ꡕWzꮣUxuH0 1G4JwvH9|vX `0_掤:UKU?5Ѓz~QKSp=vb#3Vnao<> N-t=KK?2;ԇ_J<=cLo݅ZP̗%@o,3 w&-_N endstream endobj 84 0 obj << /Length1 1505 /Length2 9542 /Length3 0 /Length 10539 /Filter /FlateDecode >> stream xڍT-3@pww' !;-Xp $5#sޚ]{WRdp49:rqU89l\(Z`W;п(: A ijUJnvNn''C_DG@@.(ҎN^>Z,$A9 tٿhh:A^AIà hcdx] dewkl(-k_MGKW x5؁A.!n uw /_߇dwHv3hnht;X,v [96WOW"5^ Iݟ9G?Ҽ=d{}>B` ?ڰpsbv;e漚Pcx988 gܚ @:90|mAW矎F( + dv@OW3/z'U~?~^*??]YZIUW픒rXx9|<ׅy]?b,zN*o 0= Υ\?B70p?ϐ?*HO?_h\7)Pu|])G;)_gAv{,ށ]ͭ_v?zirrpum_WMo)`hǔq0z^+pO]_C,!((竪Av?Pn*3vT<v?kf\<՞: ?_dh.Ѧc]$jfE-ܤfƨKLS[VX0RW{ TOwSf.?[4]`t θrp'ȢE(*G`D)}cޅLFwFBlvPc9{9wFB |$[S$xvОyP6[L}1y~ `' g$q`UEğR73C(hz[=0s*ƽv1哳LpS<輗5^_9\ȭRac0,iE|3,|{wB C7 α":!$'.D z9VAyΒ{ wQ66Y2_Bpp'ʔ?f*$WŨrr]RG=fxQ{PХt8C4)^aHNF wӮ"AlXx%nQC3aLhZF<[׽Qb+M'hcr98B Ҳ**b;Lxjdhxq1m͐BhM3NeI0~{V brьO^A6ܖUww\R'VkMfrAje6±4v|gUV0q>LӈgQqY40J; j Mԣ> a쬷;p urʾR^b sl$P[j36mJ"km;onRҏ?"{hR2mMd6_F`RlpFclӱ0\Mo<,|2T?ykrS1kNۋπG䂁>,q0峛S;21NӇC U&vTWG8Cy/ojY/u:FNKK䄳=7y9Ԟ4Un+~Gԋ( L,Aw>Wv$ D[پvu~al %kĀRQ ]ft:Ej/<0R5;/׶bG3,(<\Sv~qO# vޔ}IsNtyy!s oMiV O*1|p90kF3z#vV_a>&g\,_ _tmn+wB"v0bCP:vZbG`J aPe;Ae; TAO44Z6+O>Shn3oc+ᩞ$b u}aX0ѿ"q{x~<`*qN ,v7sZrq#`(im1~ +[& g]uw& Qa \;X'h!އpv1QP^z k&= Xk%$]z8)c5bdQ/S]:1} 42?)~́^ybYZ{Qk)iYOGn?2ԢZh+މ^=g`g&X( l`T%k&7َ dA_\tn=@dD _H δ/fVnVFqJb\Ts^f/e"X[氼u*Qkۥ!|E!F Go|lQ+$謷913 `QjMu$ bzSOͭ ymPhn-LӐK`~1!3*mqc \:sk})Spa `i+[")CX]qvf ڼ,ڛ ,XCȈ.'Zlcr .b2Dni%q{r+ٱ̞Y2 ?nq[OhYN>U)+dn9CQrǷW48ih9!3%8aȡ lNa ?WCt=ŀTUpB]gj]W)C;x"xkRKQ//_Pm Ort4@sեo[&]S brSQia6y/$09|恰4ioaA0s aeM_Ӡ0A1$ī#%9YGIPi u0Hm :/aDbplO3-s:|Ffum7l<'IL.(i'&Cr d՗-}{w1:Δ)rU8T{(6O<=)~ˆ$ʜ1B%+RmUq"1@""C/>3r= 4SՇ>[qQ;+r82t*&|M^F݁'[iڴ°*hRR箶~Ȳ́ Cr'|׼/ձl{ytqu;r~'sB?b/2]m/u!2A\,H* \&NVE?S 8?oPÚE)6gW8b?naA#xe9((ؕSgɣqUy;>ACiM?輽xF<:|-36(46Dֿn$q`r&2K9s+@U j y þHp<[q;:A0THRu?;q8 6s*r-mh\Fʖ'YecUڦ^_/Qlʃyta ߲rlD̪t{s2T JX9+r3B)7R}_Tnf&ڼ$6uu% # MSYϱ9c1xq%b>pڤW_#Η8}e[e#0iGͧ35;* ǯ2 ]Faз{.-ܟx"dt {Ka pyZpDqu n MV\"}Sd6!CV2<>z(nUQ\uPq'|\ceG/&+䋁Mf$|Y]xdSOoF1? 5f {a\|GhY'v,ۄ>q1K[1ʶޯ٤ruabs7"r 5Ѿao#̲B["P.bwT@Q$4C[&:2D'%,eNasgHrL@K]m "yZ%xs*LS5hո, !'~i2kᵾʫ8{dvq:{iܾ؆HPIlfTHѧɔ0=U`$k 2iI,TA"ٞ8|PFSKp=Ijb*D4Y/OlV:)[DJ[I]=k9IhjLE9:]a5敐B.GHd wo"RI"HV>au輚k_f`ԬP; ɝ^jEŬ ;8jbbYFxU>K\EG shwUVi>WLoϞy]1jWƯGISJ%8K0o <碥d1ϡliΗ$U)igа0UsHAtYo ȸZ"[ב P9|t1&f0g_C]! :D7cro9> `8$ uݭcp]m .NWi '>`J '|rXA,B[(V2|+yW,hK3'~h^Ψ<E":%{e/ksP'CS ZjZWūAN*O/v7B_qދzo ],DrhbfT2̠Sd*#`[-|ƛ$wcI=_RrR; AK) >y)50 FhJ)9R\ +A+ >z[I Ulcp1Zni @ҼGH+-kY~)TPjp \Bb/z/*!DHz"ײ&WD$晜 b8~&֠bN !U0':뤽M˹%4}gd7r8]Jڸa\Y2Ԏ,)ycAZE#{)x6Z;{'TASFYv֑SVi9os|Ы$A[!]2q șaRȨ悃ƕ qܶke-CE- ٶ<G{mNQֹ! WGy1',Γ Q~ddp"iw-&̳c k9 唢7\GTw7mLjbT!IW2V@x IB޼7{d'T O.:J\N\NGNf.\/s?Y%{¶fh;t{<`xyK)L2=c걘=/R) hc% N7NW=t18c7"ִNwQQFaXh|sn᥂Q3"6τr*Gmv$!rM3َu%F gbmWwYu~=Lf- "&"SQ@<Ftдx*f'Ney^\TQS./BM֝#NܱlyyW ȝ4)Fv 0Z?U;v-)[517\ ^EcD; Yxo`ݙ$'0TU M>\{ܩ%HJ\[5&}ѫ+z v)9zU^wS=WIxHj>5A]TpN=%0hg ZY.״d=O1uadd㥖wZշUK`\4'-s[h7>>C=.|AC SHW@g>FOFM O 2?)6@)Ș&/%yDxdeoNzB\)֞Z_&96 ha)D)7ؤ)@}'}nqmcm*-%gIԞz'҈X} vpOg`+*|mWҁ<\QRژʅQ U:J 2"=PY0KL=G@5TfCI6}݊'@uŌAL|kx=?DER3rMb((E-sm\Y0ܔjJo`uTi1/< rƑfnjJezHR8q\|9.zfJ4I>DAKKAUtͻgG2'X\v>QC6ҷ%U&~(day+.`\%`;g5J`CIiN, ,O%$PQI=c~M"ۥJ#5~l SCSo=*Gޝi+ҼrB z˕rXvzL }]B鋆ɕU'_m6mkɕ9 |dt"&lj1jẇ~&xG:i ٬r,*:} ;4_uI Wesg阩^ȗhr;h$*C4<]8K7EFc_Ly'hjo{!6ϑ[-f]1M8:9K~8qmI>_p56n2 xe*zXEll 0/{ DED7ۥZkD`L+Tqϓ2e}GB\myWN8\\kDqRYVDO>bƒvc,#vb+r3ܛh_* f5_k,F+_Ʒ=aUza/W &ۢGϪZ 'u+ޝPUO3 P zgӔ?dntds6yL!Ot.-M5nR'0'0~$lG]n'UB `7ch=<骉/lk}yh\W f=KCO5xq=j/ $8(m2dX,wgMf_l˷vGa۹p(bNL2cUnj0AJ at27Xc=E!3R4ځ. n2#j)]$6y[6ԅ:b~i#YOy<<, 嫘H K F}BeŤ|YF@52vJSĜcʉy9 |C‹%o{) X>'1:֌zmI&Rn`5Tjٷ+C*qj֬%3%'9r3q!_l3zZҡ ian`%X:C)D/KÓO֟t򺵍MPpr Hw*H[w۠z0F7P7|,&\xЅm/5o> 8}kY?qv|D)Φ>R#uґ ʒ͊|cV}:Qf˯װwe hPfu*AL͆6 ӓwz;ӓm#Q402dTe endstream endobj 86 0 obj << /Length1 1918 /Length2 12206 /Length3 0 /Length 13392 /Filter /FlateDecode >> stream xڍT-wwעšx wbE)E;+n-Exod$sٞk6=,ueȨJsx9xP!vQu.ȿ"d@g,9P PrpDE<\\ tp! *@ vAqprXY>& f ۟){3]'ZZ`vuuڻp88[3< M  2@ h5Tz5/ x6A,P7( x>xW9)w ?@j؁U8\=]@(@s>?I;? g 9(.@w0 o#Tnnb 0[A?wx ?gv^bN iY5ֿ[)- asy\̓w" 9`{A]KY`oqsY<q?ϔ?Q*e$fg鯀h;Yn[ v)wA je!.O0Hja\hv(X`vY>?.Ϛ~^>Rjcx@gg*׳x>{b'9ܜpJa >$ Txso$T q8#~?Hog 8-AL/|n'i tpsW4!Ԡz |[?su=';os+ϛf:39=;] d 뙮ÿ >7A>M v+g:< ? [.-8X U#E;!6Kv\1xJ*yӥ2Ճak۶D;{v)ɂC rvm='_ [Vn%'7!L<_ e+c {he3tbs3i])YpO=.fq'XQ~-1ZCBGb@L;6#}Dŧ(N)<ȒdY WKݽ$Z6:9J4H k{:FwtGA[#ui}(C/$|X$alx cj8orRexH\{ |8mM(Koh V4XR7SZ֡EIJލ$:']EP!x:6FDbT.G+0p SWbB6!N,Hc$mykuQ|N!20]: T- z;X6u#B|L++{YΫ16uޭA(jB4UDuMx31IZg f+FTG꧟ۨ t;}S[Fzj2L3F'j{{9Zxq0$L]zKU՛кb,J67p̄(cԷkܜUܬKcgd'rzM[zzPwK&uXW(y+_zxj#Sa.ls$MXx(#eJ5XLW^KeQe p~S%"P4WPQw>aa7G5Cp?AC`E#p5phZ#.#K  /;^?#/?ͨ 4¸Gײ6㞳BCl!ؐ[A&#ж K3txS411A3ҏƬ0b]$ôRDF. "|$]Yު9ej㼖\mӅׇ 7A A}o3HlbmeD{5$lЬ"!ڵKAׁ黍Wj=1ENs ƳA"S 4;U1~*s|ۍʮqG/f(%xԖ¦߫ J*RRv;(p:ȬJG7$8$lLʇ`uīqp_(d㛆NνE#>w3 \\b@ܠxlMb2v\hK ,~1^!Ft#\.f-c4+IxĿ WΏGw/X#Gt[Ռm8gOܖBPqd27F&򆼑]qX*EAgv7Q4qΠ[5gUwH¼>dwv UM[0/`X7b(5$H" _p:O/ 1Pf櫱\`}oO14ΑYHyǧ.am"hUh:Y=\^X&7Lv"^cub򌱣%p)#sAˍ\'G'C 4; +_=ZLkAmXREC.0Rgg4sR)uqjGykq.E *K ϳg]d,+XĘ)p:gcKwQ'QBZ&g3_!mI -G(l 7#Jil(5ǚ~l g~}smTyy .vks!D;m7- yJ wޖehnJ\L(Znip\p$Z{hCS>B 3w*4?X,Y3au"&G$xq{=S~ Вu?ϣ"iІ Z8WiԯJ7鮜ź%9HcE3u. VqnK7mk* 4ĺx 8V{ŇNb)?b;2ҟ>cӻgo"3Ş,y $VW}rv%Ds*n\{BK] m3QJ8]cfDZǗ/ (כ_lO<2?xO ]skoMSdYk Hm: ^d+\n?G8iFƜ-歲<<Hi,{͒Od=~߸**rZ1;Xyќ4y"h^6~zڅw"/ vд%#kP( Z9=Jp&Kro]]͐그R2ě-k;dm( $5U̴8At:R-c., <3OzJ:# i&#yKzh݁vǨV sGa62hs4ߛԝxaғ?R1OC?WN Ɵ?7p<*](eˌjgx ߕ0_PAaa] 2Rtaw#tga_%V]v0[@[Qts -k89H,F!뼈`<RN} ,=Vih~~K!><}hT?ͫ<,1bkZSPC_9hy˕s7jxK|nYVFTcS=ac6Z~3GJoѦ]£v6lPJ3T|`4g阣EմTzۘd'}~O?HN<=?l/Ep΅N$/W޻eDVL^m&XWJak{]b?O^0U!yCMk>N.O`]sϼw/2{hD)sjAemݔD;ٶۨB,J4(u^T6K-$)S;J̸@lHM"P dǕmЧty A,!gBQTjXnڙӹЩYj& n7O \4h"h "-OU:iPLR`M҄yrl?]X%F?d;n aěo(͕x^Ee])}8;MVN;i|xk.5zxzqSx"b$>鲁a^Ukk hRvy)@ˇ+DXjdZ fWCOatLER^r/01Grr|4E߇+m9yl#+=EǤq|?|Vm#XFpqPM<{ma lNp&W!ja1+g5KҤUؑw5]at5P,pn#x_֐;>*Sn?&B9"g_|ݵ~17SkL+[Q˙(x4zY2"PG}:N7_ƶ~< ᶛdi < BJBˋǓΥ?~R'\@4  W#g+F3\Yѷ05~9RbY;ol.٢j4o;=tIY\7(ޭ(xakL'JD`<Ͱ4|EPfλ4b{sX|桸=4[]QbA+'!yC>Bam><3!6v cB*E| 1y%?lmtpFΟ\/N^[g tQ7h(nhx[#!UsԿ06rw~ٹyQOV{쎩Cl'&0ѕ/;WW /4c ;Z۫0гjb9^^ۿwx4hT]d{I>4r@t끰l\[-bO= xOxۡ~+Eprirb!+AәSؕWJC[JCP*ۛPy* <; BEQ*y([ΚevS™nQG)03gl5,Y/qw?v,? Pɀd>e"* Hlw1\'˼&gZj Ѿ:MI0עIOJQS!(C(N\/g)\'qkkvL +G4*_dܜ.FY mdE-?@ā!VDIAn)]2&s.'tYIm0@ EsMieŕmJ =m7& 16NZ /Bhe7 \ `1F[LE_Mӊ7xW}[U1Я1g: a4v6PBa'@z4 [7 Z:ad=Q=|G mT| H۸?20,J]g^&HH1 )쉙%J^Kt5@#$#Q< Fb]CF =w1 9h:EQ ͂?-$<E@q,JJ;8nMZ-8ykzeKZ9F{Cl~+ou)E_. |ۯv6`6, p]PZ jN[I#ZVRW4hVQE8$,d7isYJm/Ԟ[V^̓uLX7 ]RُT㊽O͙ NЋk.EX Ecua~_ŌԊ#i%[NRfO:E1n?! hАʋiMHIȀΦ'=lnHd|,^-S YB>YX[(b}|Kjv݋c,\ȼ~GF]mjmM7fYS@*l÷ eN&IHlgCo#(Z^S )nBfRn}{zS }NӮ)){ @|uMMyA2y0U_r(y(K<Ņ$uua߰#'O[2CB j p1rr,sYݹOmyTޘg"Q ١+[0#rD)eSٹ}YaPIBj8+Aq3אHu&կQ'ޜ蠂F*UZEZÊ\t-+A%m,3^sI$DEy/+ҭe8^#eK%4`Ph$#>U8WƉE~N80kZ'H"&%)$Qrs%wPr_ wqKXcGRti4HP9d i StS1oDʳrls)C!s䠧ʅa҉Y~f⛀%95V~<׋cZ>D\|1v B6-$P#PU{bL/(-6c_cF70Ɩ4i~6 +P/^:?y@^6ZqlYW\b Ƅ/ĵ#/T7j*dsI绌&K4bՔѓJm0 ʴL; laQ%TU:.4w 7/o8a4fۚDʙtVL%!¯2T` #ƌ :48II78P;v~oϔJ,4o:F/PYȩ~lKaF`8):4P{ښ /2EAi PV: 88!͊5:#3sW85>lNQ I#@`ͯ:Ix"d\NNuaաFX|y"qJ}\id,DC5Wp87-q)Շd2DZ׫~ 8%H`- {XMTN(.ovx[G]TMJQ _'&Ѻ:A˚IÏlt^sr}8f ֡f[oZط.ZE}w9(~A0ȴ-zp}# Wq* (ET n\:brw6j(C,܀+덬k͹>FSokKlP(6RELI@V(-.:LR%(5H<75,g[ۨW߬_J3 '@!_Z?w E2*Cfۖ@T_Zhb|8 CVlYf bkmlF>Kn^#h[]W̌iUuFmwRkv[Xn l-|Lfuɧݤb}]:71̈0^OܬjuNz3sÞ8afyApu[ lSןWphb18;iaVCVD RjMFm*BPX_': ^n8ـA_Wr[y.` E^ƮB]O[돷X9$!J?&eBxƎND9èK˿ Oa8-lz轙,{ _xLr y] KWŅPj RijۄIyüQx lyeM:{^Z.jK%~)6$?Yѱk-g|mQ Pe÷~ %-+QcPb~F6+`mjЀ %/o٬I/*8ziE|.c)Mygvdj@[A~1@>t[Ij| `. l.eS\Wm@Zf@5fe-!#݉ tP'-#jIIOB;4Ay(0M%SWҴ9,qdiObWjܦqQ9 qnF;/V >5FqZ|COpp O&$c~1mc~~%)HUp"_XLޠ'ʯG=,,C9!K=j6Տel%w}m#7rAف3-j쩾Z%}xs,G ܬr W6j F(N"+:pĥgjl;/2 ƒj,—ܗ/5 ?HgCf,epK7kY"/JrMYS'q29f8ڵɤH% DI?xΡH._ _Un=&;Z`澷vңo~htysu vO ɖVǫoa&E.d36\%a ]s_QcYߟ)oڭ6Լ =`fIx~ 8D`A;$Xx]'UԔp Z*ċ.FeG QMe's5a;@` gDDl]bfj}zw%,)|UM_AzȐ|ꢒRzbTtz,#wǓgqjOQFֺOQMQ.$Rz}D=UB90`:jcq׎J_zB 6D(!eLMhDMWwٽ%o2\ċULG%p=dٯջt!$g9V&5X$SH${ zCW|N;_7IԲZH |sW`#]`~bBm9\${TKul=G2L=yA%̚~o\XA`R> #*J?th%v5?OˋPXI^QÂ;$p>)dPct%o6׊̖Uxջ&nJX0:c\{1 #;#* QZ;9;.pI$5Mrv dBЈ{)Ht2^M- H&sn2}%' 浀_.xYF5%k;(i G:*Ib9aK;U|;׾f F]kkθ OX!{ߤ )x#I(~0o:"I9>CNt4i+?8~k4f?›$;o:q}oK]3-Ă,!ӫRؗNcq%̓uwi êq^ }5P{ci;V OIySNIx۽М@"~:ذv%ArQW=7@T.EͫG9؛v(J5|@.(ٖe M3ANϬBuk䯖5q du~.d% ?ny}45!]7ui"ILmpM!?h=(&=E6[+tyWm9c tɲ##F cf7ۜC K8Ay}m|Un=w8CE!رi% 2nW]"X E'M&m }+Qd8mU2 i9s .ڳ,!@d$\b aYpURDß0xqyu8Z* Oo ϐRʬv¬:Sn+Yjo ԇyz²B :o'N'^;2s Vx? yJ~t ky uWEU*w2<@rkȠ#&HQF Ѕ|Kző )Fhഽo°hoRbUJ]]{kF5?jbc1)* IEc@hūvMya#Gkί}Io?D (_+~#[APU6z.zB+3N'k,]*f۱LؼvO-%8 ;a14'9ف1d Q!@%aVVkҒ1CaĠFnӆY]^vmr͖|> stream xڍwT6҄RE:QCH* $$ IU*H* H)*J/_PϽ_VJޙyfϳΛwv05$Iuu5 $, 89XW~) #RPF XOuW XK@@!Ho -Tx큺@-$p*#Qhߏ@n(,))~W:P C!.sïP8 2NX,JJPS@x=X'! C{# n? 8Np AÀx+ C`)04:HS!~u~l,W?_(醂 GWza! C< pWuPMOg>  Ga1Ōe۬WFX ?8ﻷuA =>[pP& $ą%D0w $x7 +pgA!Q@0? @<`@,?`0`pnoh 0{$_G,htO)ߟTRBz}B $"?]Op@/]ߨ{C? O]L/R42;R{+!npW??ښ#]D[ORؤwY8)}EW&Ң^YC"i!ɮxEtOnAKіzeZ T }3]QZVsbUXTD.W<3c3NVaӾ8;J\SQhB͌oF-ZhzU2mq߷kJ YWkqq4R Ȟl-28A9VRW[)a=A^ދ@=aGI`&t0@H߽.m:(PnT-7E੡pD/]O+SeIaݤe}J'?~iW'F(.6FU1R"H& s殰#3N5vVssJ,=.obH\zя N*ܲn{Y6!l:;^򵖯U`A%HvMYZ!N1vy:<mA-@I߫ ĽiNF !OHѠG7& @7t}g ajS%'$yg*=ƺݱKh"P (.mВ̜ F.Q~1G!TN^Dz;|Ш9`2Vp0;X^fQͺJ,gPջ7MfoHۋ<7.tAw;3!͇~<wx`l޳[c'iyMlq 5'Bgt+o-_p|n^N>vj8cgآ -ִ&h^ce`>x/8/ :e4x;6xدfu$2Tp<LV9Yߺe1JIvsȂx`^i3e7 h jg'zH֞*E`׺6 p{# mud+pai@&EV [[eU`W盟^7Q&C,lQR }2G|PSMJ"1nl}@@sP!+(/s.{ɚCC{rO:&|;u]~ %nTR_[#{&fcZI?2`X@hE)!gœ'{1=^4h92oeùakz;4veP,1̜;+f:<&.,=XipՄ=XeVAS@Υfx3(H~!M5f<2>;¥ܒGكr ѽ+oFK$׹gzAЃAgz9q:qOzMR+3a,}3.IOOL"LV$2D}׊Xaʌk +JfJRoV $Ѽ1K(j 0(MHA}!PWHCCx.%*o׻zo^F҈,x7sLi31@B,q3iU44yg-e uix8[~<+Jt^^Mff4#[ΦV'@mWj ИNOPnHԅ ÁS3qzџᷙ?yjbCsW>r{Srר{W|۬3[eCb-c{w;fZ|`dNCA&G}sJ> nkZ TDwR^|a>R|btD+DF38=hIR0e;іIͷ/k/FyO$U R&:)+5Q l,qG؂UMI|; dSQQo3m_\Rwߩzg%SrܤT˪Euk{aS3drEyg{صʲj!\a#1,εk]j$An3& Oq5#B藷ʋ QݢT^:*o"v3$D}rZRNy4ȫȚ<y9X=GVIĶj񌟨޵@ܫXt9 (Gs BȸRJ{\9Cb +m a779^$w{R)?K˦ݓlnQ s6~h-}}u@] &8Xơ@|(&AhoKjt3-l1NWcj >Z@]*Շdaav[Qww:BOi753{ӈѯ,_?zsHXlF@/rx*t|DžiPb;2jJr*8UeYvKqс8GЯsHT+Nh Eȫp[g.Q-MN\k׃B ̶K Q7Ӑ :T+C,J\[_L&ҡ#L+!ȗvfD+~Jj{E]p ,s=pPjBEsP*UC6uwpf\c'~nfY?tp[_\Ni'Q&"HLE뷨9'Ku[K6>ka 񽭥e[/=ڢϨ brgYVEJ0RVB!]jt4gw vo7{dBgN]NW|IGCyo{JsRGZl4K>Fl2| J4r3Y|춄Okw0Ĭߟm~]JlAj$VDbRt)?Ww|ܔvYHIVcML>'4 rvXQn{3j9Ax0 ^iJ`cŋ2 gKVY3!wog9 }DQ美-{5N@겹eա*T^h`']mk,cag䕩 M&. Dq7oB}[百^͍lxzܩ"PIdJƺgforדm3^9ZtHQ?<ơ{52qK$I_a+|SzR*tseWʑibcz[=Hhh%ʏ*dgq#)tYeBVmz0l$P Q8uL5ԶwegUV33jv"іB&P­<)u"%C(R%Hv#xQ+,GWU ]]|;҆ш! z?kMn`ZIFJzgЫBi(s;K;e5#zmI21ښKX#"r*M֬; #w4k^Y m ,r's֞=Sw.yqj]cAti{ŖbFKo~ɲk)+n|NT'mY?*z!b Ƣc_- ] KbfR:;I&*2<)[Vߒ_~O(4#!ØcMSw; C^DPշvS !I<*퐄K?QrVn%R.C8LbqTFhWh5G[%(n@ta'iv)`u$F@clEUoW_?=$% !lOA bG((wy4m dv K5.ES1)]P+ކ2l^Y?Շ*5}Aw+y?L'Ku2R]:C VQqՌT~?/6dmɿ\DnwXGy];p RE*j!9;a2O+ͣD.`1aE/%T8x֘:ο0Y)T|L~@Rt|dۆl#/` aqFz\_K_g~uPԑ9n^|:6lU־Ș6{GǪ1mtNQ?!E g^ؗQ>L<{N_Ed&svXHI'jgҟѐ:G'2E0}1t;h#o ~峊ƻ5_+w: <* k?_.P60FPfkq+:v8&R;#X R*+ ]'Qו e\ouF<.lrN[D/6 XKaQ_]Ȓpq@@uUk#$Մ`XcKptzy錔 AIBζt36 |E[ϝ>v圱5GD-?\Tu Z$"qr,8jLŅK;J2prݷ\s~ a~Ѳ$:cNLJ juxL> ͋y->jŁync>yRXPHid{G %źQxz qKʽwǟ;V>|Fz`Ga\xmI6.rv kz7ٌ(I(^ endstream endobj 90 0 obj << /Length1 1416 /Length2 6052 /Length3 0 /Length 7019 /Filter /FlateDecode >> stream xڍWT[(HQz Mz^wH@:HGPC]&Hޤ#Rw{kV̞93}=C>;-DCJ@!01 O@B0PB@@(O03( IťB)2jha$1upDa %%y\ (hP̊`3BP()BJ xzz\p,/r@p52@3?10ۣubZT ̄CPW uQ fU`vJp $O1-p0߿,{(j ;wWcqsbvZ+rcfu1c@/E `]1珀z,1>y0st?AEEOA!w:/f 8( b:p u!οn)(*||w+? ( 1 5֮6: Ci>o? AQ`ߴ73у#WW &KP_10!#9ԯ!Qnw>!Q1ycc|A~ 0){8ńWwf0>AUWvG 0 _‡@ `18X:ԩ6G' NS!kBTïqSoN:n?|_z|cV]s`}1vs1F\$E&"D73"9;nC~wk&=*Vki.Тb|`j3Z=22Y'US8γlo-gA˻(r>e3yEijJTڹ,4}Jy M;4lNě47[V '¢!ٟY8Q^ʵAWa|>L~m« iTUv#& |Y.QּKLC&vJKU w%DK>^1GPjŊI\[RO V`,L6~aGc2Cٌ[!~z]1c)G7.:tBeI,-w9k]RpEDЄܶѸv(57gs'BB&l]yq$28CSo U2ɣ;eL6fB I65P >P^pj ⩈jKR#󒃸ŵE쳶Ė;SpY2{:R]vߊ IЙM*4@䩶He8qWe[ gF-kHp~xb ,^ZWRf~C'ReZz)NYL${GɖG{v)*xpdȨ33~$G;n1馇p sJo7!]6xF9qd0.N89'x,a¤GGuDY,   =/ylw:e Xh8TQnW3`ݹۥBxxJjoE#IwD]¥E Yh wFei_G0+2nҁ="UZ;ͨ>y-;|sSm,vn˜z-0k!7\xZ{Jd&/$\$}YLXܳsq[g͛,B[>1t/&RNOiH z&вMk|F c ?\oV}Xk4 =q>x츭aV2N9[ #k3 0w+[ԒB5Ud6E=KPyS+$A^;/jd|ς&}sjJsz#xnʎX oX6sU N:Oy E_ !?z|ŧm׉8]}Aơhdژ`r27'Bn\l/Dm#ʱՂlX]Ka VyeCw>χ{Xn["vkZ"j,mVm_2aYїmX 1Q)ʪQR1Z/E0YE??g~/T_oû5gziH\@4{}$% \,F+{s-Nڔ rzvjܯ$fT ]|͔@_-&!q{|G^"'<Pr fHsZ$?a3N ՠ="c"wZ@BZnuի2ܭ@Ip$hЋV=SDT@6QBWqN=OYB$: W+i*AWM~50_ap>hIjovT|\IAuot{\U^ϳjs9kk?pj}!K%%7H {=D1k*wkC¢< otT7~|WkDپBAQäLXm4\ޏOE +N.x>NmZvG K}Nܺhl =ox^3>*I%vv"BI! a ոo7*3SҼ6*G^8 u42Zf;>,sr#G/`F&i["ǭ U/pqkr vF m#tsngm RFXʨi 3 VV/p $dVjOM,I`³cDM{utp\q^N}>ͭ`l?9״jyxv4p5 @<')=t=xVHoj2T`ΠnFMlX!ao/U;M.[P/ʘO=2Eg^ TQ0b CD֑9eEѢ'J>V.Tֹٙqtj+iV'nYAzX'/:8WZob*4?d@ x.ks(4?Yϙ4b>{ Ĥ֨^*n 2q_Jfݮ<)t7+Mk B djw|i\XXK,BX5)1vTrБW4|p6LL9(2n*!XKo"߲ؖ w^͎Z[/D2Fd]}ыbczjt3T}^h)f%cO6EowK!/,So9\s:7Tl Vd`zC g cHsRNwt9ސB`[IWepB..&+2ŘorgR3]xVDX:3DPF+GYQUL 4+@m3BBPYBlx {I GY!YTY, ÆxʩQӛp oTI2V\UW-)DX dbUzúbw]=hxC  =ycdg7F,]G[Y ͺ>ᝅRou%2xO6'MƟlqTk+hʈw=v }}`~%ז{Erjܶ'}t<:kgO4jbPolayX WHy6xpBh}#ON;6aSb=$2j*ϟw]oy(ڣ̎cn|6f÷rRz=T[]'VrnǬ =[,~_KŒ[Ϭ3h/LLſf'pvhA$ze=a[ uƗr.fk3/;֊{:?&Qle*b/5&6ޓODF֦Śa|m_uG8JCttePX?,F8ٖ|[vVBp'6{cX_|JW/>N,gXDrS% ~Ɋguf/oНb>lW'7@6=eOl#^ m 7>|ߋ|]BKekBS(L5moDڕ$#19qZAҽY%bӐC%Vg3.B0ۮnt(œ|Ħ$?ިD8[f|kkQ6Sm J0):=&6ycZ9l5k'POܽB"r8=&|"RTf2q> ܅USj/<>{+SҦZܐjxi@xʩZI$^CSDs6J?W6s\ѯkg$,M3nXq|yȜ>^;ϲ>:[PhAU>Ϋvw8gS%Ks*~ؐ9 }FX]͒+ZܸP-qٖ@˾)LZ_@sE؀=Ρ;|V׬j}]Q% WqFo!?wr6w#RiY WeՆYr2ͽ:a L{hDzuYŋMV8 endstream endobj 92 0 obj << /Length1 2376 /Length2 20728 /Length3 0 /Length 22120 /Filter /FlateDecode >> stream xڌP\۶ ܵ!hpww஍;\Kpwwwn{ cj*r5FQsGS †DEn GD tqvt Iv97;+;?.| wks"@D%bmiGow=hڃ3ͬ V rcf`2wertcxX@w9ெJ&:cB[Y#Wsy``tdN@1`+@;9;8xY;X,e)&'``#lw&)QU jbrerE€Yt0w:\Oh݋uppv0 s7'f kg7L"?2K :fVWrdK `ngm  7Ͽ!̭@Sҟ`1 >|kO xX,}d/sG;?/2?W'& a`0qX2nbb2+`Z0MS?A߱S r}N3Q߄moARnvviMcZ7xkM,"jeA&Eu/֮R֞@sk?\-v8ZuGt2_[oN)`h׊qrL\\L FV.=b3#ptAD8̢A\f?,% ^7 Yb0Af?,A 8ή+񀳫A pv?]g5 pv?]38 lj 5/g?$5L\e ` g(kn<)&V _€calb/_̦ ,A0g`&] &?|}1^8ʝ8/?rKڹo>Y Oy!;_]+7j`e'ZdYE>1 )=Tv%fn..߷=x|=fH f6u5D{T{Zt>.n_37]nEHވ6G%?>%~kGZ,8$A$fT}q n얣uvAUu1 Y?X:_%\6ToJ|UhƠ[ßb8Gbqܡy>*IFC#.Nn.3SP&+AES8($l$QOP(9S%}=*sQh+[3;?w(}*9Z1iv;W1QQ- +ĵsCӑ1,B2R Bz췅lY"d-Uu7a=:‘LjS\_rfg/N#)Aec\БXi#bD#@`ŧ\|Ra#eŠzECf]APp%p"Ҝ9_'Jf.*hA!9B-ҷ-QU``+2@)+K/Bڛ@YCRƨFnfQ BccMM(w .X.ޗ+Oy+A ;~?y7#t qXtPe߭>«)Y~[>2;^ѝl۷g}hBMKExwM (t v;Y3:Lkǣt x}L"uŤ;HIViQiٔYf5VqɪPR==V0&mG ٨,?V{Gɍ19+V {o%Fq}HoPn]oDɦ@g\3:w9JjҝɁ'8\s%}񖌂ۅIB-6OCgr"]VM1A_,I:y*Gq<7 7UF/²V?K5",#xqlHޕ+8p]zP2TgK{ߗ $Ҏt>[)=6,*cPSYq`zG(OD+ *LXSa?<%o&3[guRHjҩ)0 *߼˲уLmIA .!""cF:9k"W-Ww^o\幵w&l2e֓<, M^vu_+ڼ'c1)䄪0KbZb~t 0kj# ygAg1q[p ;ۥb:U;`=a&5#1Usߩݸ> 3$9X%?$^$"UD, e6ULܧ 4qjrƱtYI?bV+:!Ujj/uG΢ìRfR޲f)_ 9zW3}JM Z1]'o9,O`¡ʊW3(YRc_ &y>ϑ?6q$_R`؋v7tu頻 !]͹cO28YVn> SJ9%m\S7 f oF#@JİW{ٶQwk6a8㫎ň~mH|r{|Kerx${=)D/5;GdD,wr((뛏K%7M"-U<9erq|ᵞWIu(Ů9e)fYS&~q*9 q˵\52Cj.Qe@ UOvl #HkMhUEgH>zdwU0Q̐䣘]gQN_bq5U(xJF'fVuJ ',0KޔXxF@bz÷ 9,e?ц W:V<?[ ai-d Κ='䜸8)0W2C OuhV(YrJ!(<&k@zx5ۆa:`Uøe PTё.'光%6)Ӂ LZߜ%DLBi칖'2P]7ijn:Jz%0bzW;øyYێ ulGoVPT0fmI(W,=vy9lJ§mf ?͔E;ҥ)4sdZ/~Ϸ-:ȁsT62]g2oqdFMu?ZP #Q.×҈[ q ῐQ{!\nRȈ&`~d٠H{\~xqAf՘ʝʸF.%`|9fVopթgN&AKV'ʶYͿ3vQ*yܼ(].S֯!Y9szg=j0TBvrd.sViAG$R]SpBn[|!a2Tܗz HMyo TR._}%a-t8zGb(#d1b$ŝ&p؞ f\mO}l ;͂x}QaSt}2k9fu+v9ǧZJH' !?'8}2K^+JǒAH3%ÙVi[~rv]Y3v M kL#[sRdQ cY666zsnojI&ڔM!z?o׻G]˄?}D"~k#4ۑ1vX{rd7.A*w:MKkb CԈ6A_GLt)gc]fƯ+¤)nS4lJQn#l׽'[^Y$io/OXEڒ)#L=SVոQ{VtHalVߑP,ʡЗGv#`` ޤ(Qrש`|z_cp$]C+Nk!sKsC?-U ZÃ.iwD)Hs$"dC'ee)mKSBnk[6tKސ! Tj~g?~(ͨRw/ws$i=dT_RiTGL=߷đ_٘bZj%3 }S~I⢹GiP !D, .ӱ ] oJA˺4JVIWRfnzGXȒށ2v:K@]Ֆ\P'EDU*R:4#i rR$Δ8urGX`w9{nj>R6qYZڭ3ߨԨ|Y?F} %3vQ]L 傰͒t ?uٰNeFTLWɹ1ȓB"^6M~HHDJ}P m[# ^Y6ڪEԾ&~[[Mѿ0Yoy~ԱkhZ5J[WqHfDRٯ](PN_\VȘ92m%*Sx<#VڞJxh4M#^̘Ҕ w/^5/]Q:QLIEO?s(1! .بT[C[n_1/r%~>&sDuIqǥfp%b 7S:CUIP^qԝc2Wv%CQC*y5f~*BX;3}֐amd{{Uf]M-S§@ u5j\v#؃!a5]gZe3chii_̈o2̷]hk "=-'/NEs_ae$Ϯ ]a8M20SU9m ՙt.gJeW9H'Raˈ6ts^:Ǩ_uLr԰SA(TWSz?w&)H7tk}/dc.&O}a( :^2-xk-nҧBG) 3 u#|ǩ.5?df-NƠ(}AsHd=&-p7O{q.y+yӫaMknۚ:[C 2$1]8/2%eᩱp_Y[ДF7Loڢ7y$D@6vK3%&{=\G"AeEq JoE#j,u0$pؐdS]&Ua/͎fR ֤`}[fN5#]44XEMX#: h^vTzJUEf.\k- sG~I)[QL[ǖ w:"LL715,MI# d(eAF6 o }Lޏv7tK)f oנUbG<OJAKGgVLP:xSϞ9fzi)ĄVI}%?,;DeJG,ޫ<ѯR^e\X2[+UDX{I3APq-'z$Y53-='V/ozc7ѺPpč7@g/ Qy,BTx(:FiG!*qԭcl%.-U5ͽL_ά O|Hq&*r*(:Z0RG#jf1c'ҽʽ/4H3(cWW7h|!XPݰ8New9#\nLN>sA6+3?/{e̜vgmmc]83^^hMXI^c$t ,r18/s +Lqâ~nu@f9THG,ܐWbU,Ffo gS`rgY;HơeJA?ӄ7 O$#&Ǝ~kK/8jr5蔭,3! C|$w($~ZB+ac 5B/$70oJO ls6 s!3v5YLo&ayZ-[~(+n!~s?ppiW[jiK݌ȵt"٩e)GTfǜO\~6]%e3~jư `ZنM]1uۂI-5+\S+&g7 +qqN('=R26QL%dh;"Ef5}8bEy[7 IFו&HNd#BSZZ=*-}H{;Y[(į.&G|FH7Kf5{&]_+. @aq>y(gceP[L\ЇYa. r;IEsLappTwI&T yhA:P•P{,7_>wX%+/QRNJZ/a8K>jƢf} 9lPLܖlew2Pe$AKugy|P+|ӾY?"\"}g_NA 4Q\ .e]B(E|A%cܮMD TgVƜ: jq;7p?6Z,_lz.>Pʛwmk J{ԪVbCScO4ZJ$} hWU&3記ia ]}_cN9[|^ᖗDZ6j!}|lfĕk, Ōv\{+>ׂ:Ji_&CMQ[c 7`΄ YCz`<9V`P!bH:p 0(Mˀ ZJO$jq6`fG IOx"U' V*gwzc!nD˳7`/iɺ d0 W+7}@҄` P}Z0wnv^ebwƼ=S]gw!\E(1$aR< NuAv/xh0!Ft)2='.d八Ϋ@-!)T8Wx}.޸:v?&@V\z-5 +J5[>S?Ήf6_/&71L~k9}32‡a(Ϥ1+ǒynF[\Btԋ#a7oDvƧ_9DGRP5XPG@)0~WC;|h^Z:8(_^Iޱ ţdҤ/_Kz2WCӑ[v2gnb yJoG6|ȡ(Rʼ~TM4D-Grӄ&UcӔ)ùauUNhIo͹jkkdE#1#EjwJ5s"?b 7ޕK:Pg@lbۮ:S_ e*WD(,R+nRYfFyd52JNUXZ[ʇ8[ ݗ 7Fzqg0cL+GpIoMְlUO'k6Kr Q^9-ip{3@"IO"h`%s+_-V^03Bh\k 9>U,@7u䶝~[F> ! =P(q$=%oʤd=^ l](/tdd{k)Hud 9-\xV8E5T?t Ie1yJ:Ҩ,_y]`a~Q"KFX Iq={`~C$4Z5Wk'aL$bYoo l%ic >XrίU !#/fϟiG. oJS߸S7WL[>d9o%$|CFev/[X8!H%:đP<ޙKtYS#IRxС!50D 5?5kFL ;s]J놯c[;5ܧ\x*,rE"Mn<#xH,^Fn'[ǰALvkY Mẟxa!hN#+RB6񋾎▥eB/\?05"ۮn{Xw$F9 +Ԋ0Tfsn}r Jb?"$}EKe;\WuY`8#Ž!) e.#X Q3hv'~ҫ9cp#?z $ȭ}πJӃ*FH&H+6̎*$#gQJ%C>^,)&C]jDan1xc󦕸,(&g׾Hoc'9^; ,LX%Us7Z0H [M0k5gDc86ٮʌ1ƉzfO#-L>Lܪ(@GY A:mu;4F-%uFdm;D&z1 "ʭo'ޛ^J4G6TAXHwXU*Ͽtf;yWi8d zخ;H*ICs)e]ǸdW c'ݧ>AOJ؂Es[Cښ.a:'[ց]*[a`]V8!ڿC9K/ ƀi_J=gzy¿7`)qS#xVh b6䬮8Vfa{\$gmbפc$>نbٝ;4͸>?WD*&<DEw)_0[K&tC[˪FgwqbG^?7*@)ű+%_MubC% 2]cla )34h6˧Pҙ mu/4Szn UFw>mb~ysNEmM-}!;)_MxHb1IQ) 7cI]v|MW;sJrb(woXU>S }^6Xa[m0 yf`9A$jLw GcE|6HZ} 5Pzx ;r'5.2?J甤.Fq\SKJ@Z&b5'z@Qm?kѳeDNi lu$0]hEEwc0uh˶ ~ӟ<ֿ=Ss^ fQRc{&X뤆t|*sR7S#|үV)G[uɐ猔[͹μ{Î2%⽱|F+-+Jltk|O%.q%,fǨv) !Qwsu< z׸Hgb ?^"s}!i0c1`p ,M]Avl>(|CrQPT| a RhGA.=͗"ncҨ.DyAǾPdeJƐcW!sʀ7}]}(LnL`D9JJ,GG?RPQqlG;_5 \/Fk%gA)ݽ)"A%qm<5 yW 2?`q3HC߄{[e'K>(ʥ IB2,m_݈HŁ%n ũN"¦խYĢ6 e&F1ƇاPBC ©]RC,ߐU+n!'^P7l=ǵ?i>92b@nJRTWp7zߴoy=Փo07p@ 9 MzC[^\[;\ZԾP ^ ߥ,1Nyڡ׊qjK Y'!L2Tv|4uvZ4qQf=z7F<*~A]g`D7k8dǺO|=R\­ի"-^|zт5Qg08c X]qTn, ˶`#'EnTP.P'vFkQe²}*^b (HA$Ǘ"euotYɣ=kl.b5jVk$cUJ=鎉| e~i[٫ZJ& a˵^/8e "B7v07Inu&,6m1חMu_Mix)N~BDv}yQ˟Mn%cM T1j ]K ?K,=pzVc2aXﯭMaeC12P:To!b=> ݤަKD2 .M5j Ki=$F7˫봱sĬG!Z?hU< /0z]z\|ylϥ3dv*,̭ \꜊|,~ILX#iǐ@e_cppwd>[ "tΤGjw Ah)M\ cˬA9G@ii} T -sNL_/~19dȆ?=AjGE&p/P7%|KwOo+<"b|e3pXmtEE+jJp9&~$ee6D7k6o^i0J x&,tp>b z(g)=9,XmNy^>wFmۈхCEf6i.o;IIVa"B’;v߉C C6-$U3w>\Z JHPA=I}PRqd'[o;-XN(ȑB,* HCuav_F%j[ 6}/ڻ@!8WfxAFgdCt + 'Dza/ؼ%Uv/8ԽlbSJԄ;40DOߝ'P!DWC)S_RAfn~c3fz:t'-[,$w۽Wd9>3_삠f@)@j}LGxpҬߕO| k^>8c)W;EʪDyp}0٭}\iUI7 gg%3_Y5 ZٽLS~ȺنN h\+5-\b$]6YSk0C?,>w#?(S{Sࣽ]jKLFMЍ1*3Y fLo{<@%sҕW|[~ !Ëx{p7ISNٴqF"s:ԴF+q)w mڿtB@3`ū"f*FyU l~i"n1|wJ|C0.4j)1V܇΁ű}l7&{!!Kjԧ'ɥo3;ډr=V iTt83WacOJu 5n214a{.GH(7.b?t#y^ =+PDG 4 ](%=A5Lv6C|uJZ,8u:n=-|%?'s4S fIxc$jm \Rw+;X'.&z#`gwtu$ s6qэ`SC$~j"r0KUp<(y6wMqJ1^:yI bp; ʶ%[Iz+A \Ӛ鯖Z)KSE`}BU7a^vݳ0c\,Nײx͗8s=?fol>Ggnm_mFNB72(G {;&!b8,%K܁FD$\Iio uieOGSYdD2i%7Ҿ *vfQtveSC ̕!?z$I΋jce#Eo3BOwir?߁h镍;D @~%LA˖^x"{ҡXa(oC? xO+vN9|B|swe.0nC.<Bb`foRo+n z;³!M ȣ C4 k k-q%|(ʼC'.n7-r^G,paQ\*1NǭGU=֗o !J;bVA r~Gc3i 'ڢ^TƩ"Ԕdۏ.?.Ogp;ʼnWAyMFX~/Vb"ޓzh }iY)o@o[jbYb'6j3F*OmL{J/lƴQ> 78*848: 8k@5 V˲,)>k첎{w?ŦWe:8_a{nDq*x*r+(+o+}*&;lFgƊ*A'aWQ T~ @74.98, ? aeP䰩~EXZ^c% `49CZNP?ӊIwW0`D06Qpmy_?s7huÞfTDV2etJQc6BjbDd3gq<򾃠3HIkl~ !"4Hem}"ac~|Uo>ٽ볞ĥ)z˩8#(cd3k=ܼ?\R- >u1ZUn:P(E6Uwgps\I \PR*m.5}d) 2XPYP4ϸƴ*2kƺ 7z;W}OKzi8fw΢+r/c\mQhsAgL & +2 #}坺Fs~鍮 6z%؛OO|(N,/HK@XLA{.kB{L0qRz3aa]߀ 3}wH$1Vr*%aLh Y`DG`a*r7G^{^,{zki#lk,956F0dI1ǞHґvKmRfgfRQ%ITk^.h7Rrzw0 qAMAUy\.P@ J9a=؍7:@[wVa<$X Ϳ[qIri6=pBKEͬ4r߂0H94DD눐,`)[{yH'ITC<[ѥKe)aG1EO J3mgKaՈ̡Mrldz+|ɋFư/ S3 H![bNz #%v^ĢE_j%a)waUρd 1U-NXFOB}afeةn|$j6TzuNԋ.}Ϗ..D ?m{Ln3G#vI"nށsc ^ِp cRћye$qcZM1ȪA4$X3C<@_k[eyWQ9q~߮bi3kE?'\).{Oy7͖̾|Ψd4,okWfaz8 P͍c#|-eu$ Pǩ#%3>c)PmEXCCcQTy9@Lχ?o endstream endobj 94 0 obj << /Length1 2644 /Length2 20284 /Length3 0 /Length 21786 /Filter /FlateDecode >> stream xڌT . HHwH CtHwJ !ݍt7Hw %4q}kݻX yyJ2EFa[#;[#  * ٘@V$JJU 'k?b$Ju-QD&f,lN^.^  /@ (Em,̝ i#Ƙ;@`al:l  * '3wrefvuue2qdu0eZ8A  WyCߕ1!QT-ؚ::1p)Y z`ab7?޿Yr6463[ ;Y&'7'!䗡-bsC;a%!s4vsrdrU"0.MDmml@`'G_,@Ɛ3=Y++`j61U$% D[frp@.vr36g^RRh898=T!L,F 3 01o @=Ͽt!eb vm|E5_pqhh oW)-o.aOmK r!X7/;gk4?jC k ;9[X8o!fDe[Ȭ- E[G_O# t2<9! 9ۚ0VN;HO)a3  0u@5QN/߈DY70F<f7b0KFf߈ ,#E7p \#7oA(F.*oAkF욿$7XF.FV ȋ鷜__ flk ٔNkMlZ[:aabORVȞ:KflmhGH/MCHT? /hGP 9~A4X~ :b`M2,sw;s @H@ȘZ!}RHOG怸!Ro2g!VCA޸;?.;!i{FY;;"3lζN #5{ 2FZ5~hY~S-Lʸ3?KB|H[S8qceKJh!5AA?Nyz dp]? "1ЮףՋNi{gn4<> *N(H9\/oI^a]ʞ|&G>b+ZgZɋ+i*O$iϒ5/x6YhD4^YihA3'i4˨u_U%^q; uߢ94Nw4yHϿWݚ-LOWI0<1#-AyP_v6j&` TY";Q!& &dcObjWVȆthMpޅFE|F S:Gl,Xٓh"=^'bV:8={K! ka:,znIJOԚ-^ }5x '\uk?jhAޢo&@l࿰e'q O:B &79z0>jl΍R\y;b0oH5g#i&"I83fņ'EzM1Wي I_(ⲷPjGdEQrӬf {L8A}\ w h[^\IR7۴Jt%I#bqWQWz\Pgʵ= 3ipڈk SٱI].6(ilN[2I ]JG:Ƨ¹GX$TϋIIᲔ&DJaM&|3 {(DyNbGz=`'ng'5Ț1+٢wKtÔg#Mkiȝ͎ja?z:'F=JLE,zTZO~{ўGuz Q!+U.!gMf;ϊ mb)נ$sB~{$AY_w^t+/ IwUPɨ*cw)>x}P혴xT^He T< \)[)4WᩁyZ(ll.0{st}4ZJE{/Ւq̀xRJ_]}{ |w̉0'-e)1c'_AYMZ%qd˛ںLJfeRnB7}zuܥ>'uҫ)+:UFOY_i+y@ty+c(pZOCӑ6SgLL˷(!=J!T-DIn;c-`+ђjS{ N0[;zfZ9͝b&xY ݩޥ'=A;n{$7Iim0|g_)҇^~^:y` *(>z0ҲIu;*` 3{g.ۣ?S6kl~ŭ2F[^?gWqӚM6QDFGԄ?_,t`)OJ յ cdƺ!PK85Vȓ$%5Tv% z0!PF!4,ޯsg7__k/aE`pS9(|CdT!B'zᫍIL:t`y%r7C(լ;m4Md MZ5;Jt<V}?pAM2$s;,JW؛W1v^쏱g6^H(79Lr˙~4>Oi{xoJHǛuceb',wh. ٯr%o( 6$W%q`O)#rĢ߽֨Zvi#ҧ{5Fa'6pHA?F,}I^="^.wdXԠK&0=ַ0M?~|(t2- aY]t=f^N5>"goU &z#8ZN C8دh-~}(Ufs1,E8vB0b9 #fb!Rܛ<+JWnލ L<.2}@lCg JCŒй.Ƹpet+0'>PHS,>i@ETHu$v-tiSY3>>w5$'å%+0?tWXpҩz&R*K"7{ j3|UH *_}n' ~x:w 4:`$;5ÒuޚAby͌[T9fm5%:m8x3*qql?Fc T.ZFE ت 95< *Ǿ JNM>3rdv+v&d1:vΖX?-+j[)"Lh j7:7XN= m 1y[^˾u /Ģ6C 9ʄC>@x6vIX.BFG?7S.F_vp#@#L kY;@;WAT #7\uWe8Z`#R3W=Qۍ5Rpx[6+C( } >nZ :cؒ[5>%͘7&C/GƒnQIZ?#A[=غ>gcֽQ(Qvk•TH9R2bm궷-nG_Q;aEuep py-Fk!P*&d1IzLeӋ5:ۨX0/el5UbآpD񲲀(q뚜ns3kP?4g(Ξۀmg|PJ!NʵiUmy\i`JQgҧ#sZO[[$Yu?qWmP"=Q.jvjS_#ٕW+SQՑA`TTU;-=̀Ł9\vMeJeu\v]Mx&Biumɏ uM+/6E$ѩN5Jq#49@imo3ӎiyXŽ;]ێ)}pa߫%PCu Eϥrhֺl(`r:t`;ιDse EZW?1ҕ}nm9DW (nbKT=l(PךR(8}i"6mBh n ՟lztCvb:-r>b8uB?H 1tdk`=]mC=:wAg| vt"¦UCv|a uCŦ ~}'jߢEڥ,Y v db5Oƒi0 @vd0RNj˜VI \ }^3rwMDU(ryg^8jXض/>Z&45wF~4YӴƉt&˒@nym*@ -,ܬY(/kq%Uuqssܓg7{^YN>(&;T5.^zM;S=5UW&AXߦ?EE1E}!ΟժHjkEjzw E7Lh{ǤCH ։~ӂ0! E?aW>Qu;_AQu􏚣1QDy#AJfUCpW7N G,qdv2m_fRMW Q,KגnUkgʆc{T"˺Ejsy_𸁌ug==Dk^ +3ү< C˰bNء"Ы]{1oD{cf)@b$hWU70Kޛe+4Y\ _e J-P &2Ɲ0+|MwW'LZbD$[=I p#HNe pD0ql #г*=%{W$a >])9p"P`ZF]V[+i( ~:u%  }Yf1=Aʙ[mo 0O= t7hVPnᙩs<=լlgy _0 QwMvei+[57iY"E!:U_`)aoClej4|g#mVveZ)@ZJC|Zɯ?mwĂ/湡'%2aG.%ZNsAZUxq>c δa7񋋣^lrfy Xn zBJJ.}tljj>G Bq?Z>[5rW$M&3 Z=N+Lŝ*:H1DnMiwBD}'x<>Ns­ÁgIF\/\ /Qox=M73d8evOA 02=60~Ihoe3o?̕/Ag"7^s+WtHSPC#Qt".^cH(RkT[1@厕P>cMM5}yS!mu!=N 2g 8NPtVfKw]5lYyk/U˖V)era31¦Ko 8E͹Qc/Xo=Ca'~ؓaШxhiƼnU-hAE^:zIgXMQb9eo*~0}e)~*.FE-dq X֌)3^ 9Y=@Ȟ`X"'jMZ@,ꛐU _g8qK]x"۴YrBܑDS 5?Tn)H<obPEO,Cy"q"WQ$g&rD)o ;0aIg 4&a<n033qY5s7jj;+X9`Q鱞aBِ/woh{6.&0oq3VMTr!F吿d9`m+y!N !o#~Q`'o}0w:VɯtNl[L$ţĿ?&@M䕞w ?lKJ KN2nu8Md,_6&<*wγg1x'ʣ K1U|ʅFˑabIfEQegY arI§mʔ!/O$YYAT#>1@E15Ø:sGf9[9{a+6sg>Kdv31;K9 ۣ_6 rQxIPjlY"$NU菿M8۪w4w/OӽKΦ$7CpI5 :Lѳ6 R /CMqX&kxX͡t8z0sUќ*z8N!9'@Y]K [*h\)]vH׵Q(4>SuwH|V{BUYWw| MzOgq2tkljY{^ f,/@{cʩ|YK_(%e؞g䫄aj[4~Kk l(e#vvNi5Oi| iwqj$udu$mQ[+XyF*P'4M SL)M?|c0f2;TŞkA'0&K5!WiJd{\XxE]U 99o¨z,r&xɼ_/4 \iUvviYr I :B%N9R{ C;{"lW/+X*E^(5!'X8 V>usֱFer]Altcq=җ u:E^aɚ$f!PE)=C}G{шE-ǗˇWm*J.v[nѳ`YҊځ9TKWz?5#YP:3{:Rʇi[DS/t&SU6$q^ res+$0 .l{`i@13O*i,XZ\DQ F[eܳjLҁRGqDW^wW`oQìyn:T>4 ͚nDO/?D]dxnI;}wwsSΖj4m:uά{Gћx~f^`L|F}0p"]ї@X'훁>Z+}/@zC!oUSTXJp|zQ猿ձw+@ɑOۓ*|#f,&U/8oV#€GkFXytHO&rxX#0̥+B=RG]~FwWZ$-H^v2Bsl r2LygWCyu')[oZo|Չ=[|ޜf,=DF_xBK0[}ov,7s 퉠 %e?܋V{jӻPWKEB8YD edNjSE=h :01km2x/ӫ qyys@ZC ~.qc ` O* g 6og2 o?Vݝ'X Ǟe!= #C݅Qș|HD$(BQe"R#_cgєUWYIhOL}?ä#;t}yGXU{6PBuR]ORVp\)EErwxBSqFe 13`l _1GcoTֹ͗4̟k FaV]rpޕGcmExebF^R}t^sϺrG/ e3U..%7[0 Ѵhk!Q{`氾ct%5n@t ۏRYcVV>Nۇq'Uj/.l-hS'@D̽IZީ"@9s aCJӚaN~j.% !0|Z;-%tX`b[Սذ^7FM-_ƈX)n\@65o_ҲYU#eUOP?DmM*,,!}.,M!!5`5"GmOOcvnzqLav4Ǽ|>y ":8Vx73֊K*<#_0 xɰm!Nq^6#pܒyB̊6ywKgP8~Jh hea8j&3XÊIc n~we!m Ǻk 9oMOѦ*Ieۼ9m:pm[Vc|+IaүSb1H*6Bx9 \? 9 q[HoNx4j"f1,ڹqmNF,Ў,!|.W^X˩ =)+CKwvW\,$#OC-[9I]6 q^KܰHj CG/H*\3H7 %c)Bч٨ə(׶~iʝM_u9g+5#.P>|m1P$ԭ<-z72hL! `u`w3-?*Yz!@'| eNJ>.l Ƙypّ`_}:09; C }TfqߣpWi.T"(ʫCBG9y'2O3w=o:Z''$u#FuE_Ry[3G(0%F{x.O`hކ{'r1.UR?;nFnE܈ePK fxΓHޢ"^Zh59D Q[v !r*ǮFO@=dN"æ%[Ƙ#-ʖR;S$t[{/L̋K f3[Yp|HbȒWHAS61L2#5R4st>Ohqy)Rm:t?#<\ σQT~Qƨ{ZU >`O̯XDXPY)SodlMߔ\m׾8q LYr]'D& 7Wv8_&Q~ɼ_7|MQGU,z:q PU2Aa0~ &Db <%DIzkB\orBJ_iNY85IWxW[}|cāHrdi+,Kw "Q(;nYH*/7T%&'3 =H~w @?`/g170 L8@0j uW7$䋸Tj뫻%M8CLY{Ok»X%K!p=2$BZRr0쳶WD}9|eb!Aq;:/HnYȊ$MjMUoQ0Ș#hY.CnpdPHp-M@z OkAYĒš]?h̍C߱fX55v=cvkj$o4Nghn]+%%tD3w0(葻ڇ' #YQ H-3~vSo%p0; @ aC2DHLWAÒNπc]PP0J,'ӄt' ) Pg-.' Sk 8Y (bBMZ=diV OTDR֣v4 ATa [rQ龧ʿ&_cB*w!- !o2J[5lݑSyfq}A/R[(Wo׭%G/'+.>mWќVP1Pa<i&3; 60yݣv#0伦0šdثbq o(aVc'(]hT||vX|#{cJm;ꛄ[;t%@w paZ>g=i\"$\b`HGI0F4y:'P::`XJߩfqpXj'T!5FSC |rp:mDȟG.=Q%z7Dm(~ZSnD(XzސBuظ y;&&5hKmHiiSBʏɢ!ݸ.Y{{ђe~$@AvÇxŘ ʹB-lS(lR{ap )~ެWEP (h??=ysc]2t#a̺Fi% !ch‘ %=6h*@qw3K;լR빲Ng?R!ݡkbOkAhA\`ѝ6ƁCh#rn͉˸bNzUELݴU-TOǫ,(1Dax{V->Ӂ0SM^PzLHY!` Kd{9!AB% &N5*XXk>(leqCdsxW;J2T)io$: ͼ];aoqdIu{ldyR!m"cp%:;DYLIx@X~zjn#<L{ ?x;@r .oY>HVp0u0Gm| ⫗bXWlj%ey+u3-A wCNcjY (ߢ60 O@7(j=3Bp^Z%A0J>iשt3)!*劂I#==4;O&ӦE.ޯtmB/uYbL.D.nuUGtVh]e}e"Nb9*yl8ֵۭ.= ZAn6RdS!Ҹ0X*'_!TN$~|>9_W}_uY?dE~xχΧUNc<%hlM}#Y`O8a~ q꟏zH)7.heb*+b>sUbIcNPĹ3L0k- U$TR,~Ii饾n;T.,#Бǖ+btЗH[ ,%TwˇXOGrZdr.`-g'["ӪQEXyoH93gF?hJ~}/{W"YP*iZ4C lds-Le%[aΖ=ċrS&V`e:m1MnS.J dłR/gy3Șx/`#_k-JT@i뮳[QU7sVAXQ`K_DM5+yDL`oR<>~pʓc}VĖ&ϙDiz7 L䱚 +IGS'o?|p =DyŽ*Ola'uϽsnǤ1@zM?D>ߎ_V?,w+._409ɺ1TB?; u|.oå2_@^?qζ|&5zwt?L^\=P`ĉU~<xzc_͋oN_p.]c.aDkMGQ3Uwamd42\Eh atjӬ0 e|+ lr*f_Ie* /'G)zyO%H: S(S* )yڕxYX96SNzu+H⸾Z(D=?_xe5)۟:|rN ֬8MZߧ2F-. -1*F%N)w!_"Q``ev"n'̣yT >FOs펇Z\NaL`( .1V|3)¸`^qC2e=VB.sgIed7s1rZZ7n'j y"Dž$pnEg^ѡ*hjw9,`JZ?(HDMzi٬srv~#⇬ ŸӖ~T5K-s$XBi$,:U4vYouks&5'ET,,b+ y{4$,C+| v.=ʉu`=M-Dlb0 uw #NgHVR9?h^(S #An &x&^g9Br-F<q;i(mCO%!~3<;vѯ<ܥ!!v$wj7 PVBG}^b}EAaIei>옲FXFX #b@BrYгJ5(0>huzC (_)Ae0~N%og/ RZ3QUሗDg#[O<.;ˎ u(#LL~J>qvJKud-Jk6# \9_7Ϥ6.Ȭ!f,![+L "W ?]3O1ܘ;]8 f q4t[,!\Uc^;ou|Ȫ ]0ւQyt ~ UȇП""lc2u?l gBi`@.m/ `bT4O{FJgF >h(lrYΎrYWWE΂)ȀhSQ[WKیdsq2k! u]yk~  SF,@W\GYˤ+~S%Q:-7m-DGݓVBk)I.u: д <$X]¸ޓRca_<[fnHC95G4 [n|OrXlj˦ipp݇(1Rְ'Ev`xY{ِ{*5 s% Җ~Qi\re6+q% ΍ v ^9%7(ƙs9tzVn4cD@0~u{"8K,vM|CJ~:G٦(e09d>M Q LZz @&R%ImMNh"\? +WVׄ`?B3R4GA%W2}pJ@ s>eBs8[I=(yK}hZwI $ %4\ߑwQa,}s/FzOD#ɨ4A}l*Dʈ?<~Po̵"j9z4fjXV>: N}!LI颙'c4'SSi?&zaEVDrQ,,vExOO^û6<,?+~TKXKFc:O b'q]]nJ qt18zɦZ[ǼK%(^G_AYяΤ6ZeIHyE%D˳Q(Y~THB*Ivd&MIѳT϶Hv(C !kЯ?7'Hwv @0,j̈́]fF<ΕN^5hAoX. L| endstream endobj 96 0 obj << /Length1 1601 /Length2 8787 /Length3 0 /Length 9831 /Filter /FlateDecode >> stream xڍPZ- !8qƂwwwkn\&www,!@x$̝*זugSRjYBAP++P ؀@NTZZM=o3*6 #@dl4s}SBn.k^  +,4s[PV q}>_? ~~^?13 P2s9` <@?J',7oAn gͺ>_  J Kz\͞@ bm1] KU_bˮ{*Ur{, Y\# P`l |'y-A4 `g@]SΨo.qA<v#~~ſ3?7/^->d rS>35E 7gwΟG/;_%uclK1\.S+ߚyd/Zm= &THUN\ܽƞwH%QaWzQ.sU޷)hU1򵜊_!jdq%ھIqu#S}_Khۂ͗lF;QjPi%l'ѶaZ5>B9P؁UoS"-ale d0%%FA+LU6xtϮKK43׊PIcB.UHBCDZE Bިt4\ǯ>rd+:nNF3.`%ȣPGO{?x;ԕgvfeqSƋ狿mM -LxJ[DrBZ/VLAz@|bWct3qeD0=R?wn_:SL2^?q8<4H촢[u2eC'P;C]`O@0/h5!2#+sߓwnyzfYs>Ub.X5%a%V.^|pR+^u5*NHmӲqر`~աty%e.i섩oG״C{f3h vaMWm!nx/=nu9ot76ڮ' 7Eysbr jgkA-Wp#`uFFwbI 31KyxT"Zh-#[1!~i~65GVpy3ER~mI|_f֓@.(tO[haA UXa%R(4"[Ę4QEܢBS\-O|#vTݷ-xoX 6` a;鿹S; {R Tdj>_1ESF.oß!r[%7nUUlЯL&q!uŬi!ZFq) .zsޥGz}9"DH.~jmyf3QT,^Yv(ᨋPfc jA}-Ӽ*݀G'xx{5Y/G# |ϑgz(oU9YKm4aÁqXzNTR|i 61GXK?~` F@*1;J"E!*4AkyQbb8N]ͳ~SI"-Q4\WqS8e5]<:Xc7䔟Fqg%X5oVj0NB5kD;>$3S~+;ޏ^2k-BZIw*ٞs9_H 6 i{Nˢq KxYɶ {.e^)0W>:*cVB"R)"Cw@_URMæZPaoהf& .Ƞ>ӕ^pRيi(4{OM8ti|&Y[ƖJNa>WA]Q~)mw:2ۉՎPݗB=r<%MZǜ;E71wqQaR>u2~2V_px\ER2BĠݺvhs(eoqS] -ھK!& y?1o0IrL3|SWm6Rp2oUzH릹c>\ZØE54b+AA'd.|px'i[Y0D+'b"BZopNV~yv"Λ#Fl(D ]$҉s:ZшQ`S~-}lRP#r`|%Q4ԮTGκl\!*f%A lH~UƘN"Wc:i5/Vwir-37q78*"4PܺNx'o_yh^U|4-VѻͽPatV0a`E\ͷoq& >Xy]sU{4zՒaDWCW:>ݩgB,⎞.0QGLеm1-u!Sv51X,,r80Do!BfWo0~gfnD=ؚI4U$1#ŮLVT!~±n4u4=|H~Ja{Q" ȯ;vZ`2t[YG v!TJdR]-Q b`_Y{ F=Г 7|(}(@~)YH2a7F_x'0<YVw.UUnp [lFRgU>2,^2 eYk%ߐ$鮡& ז@j}ro N/%}extL.w LI^K4(% aL5_;d!/i!5ՊMCj[[9'vc3I䏯#H|]7Ng&Q{Dr hZf%@Zb\OJp֐yU Ue|{W/XqBeXQ;dH!oysM ovlN\c7wH@,jQV1#p'9OU%QN߫s@ЮiUcRtƻjwpB䔦g'yVO*PIз̂Ӳ&\!3^"S (z1y~|Y w}9 ?s)Xye `6}SpkY.Db昺s=P(Vz "М-N{UW#D&Zv5B$:2jE\W֒B0 gSRnɬڱ9xZfL[IКUa=ǩ"5&!>Az&r,3czx,3@010@M'PC̡sV2 $=+֏5 *=̬>>_֪~NX^\\f4%"b CSZ5tjxܗv#2.ۜ|Ē׭oOm#K-q4X̜egE4tYD껫_jKڕaE %x:lS2#)t4Μ4S-REyI㸃f|5˛e4n$ɾIr;?S X;I;IG|r&PdV3TtҨ I?maR~Tk{$l֋]R(|f9F6;ldAYX@BxDu!DxSIzj1~[U<d~Zp#XIɻU'Q `1X4CQ艋DǘDuE; ph?:\?E5Bf,":nlgc;׽ژeILx0je~U2P4qo!/%/JJ/?1:羭dVc:\ l] BbHӇtg3(/ e̸7t4wev.Kd,Y#Dઐq*טSE4r,Oa1zbUԼQDL"N*jk8qhB-l@+dc[ Ҿ K5<CتOδRkQH)rMȎ6?Z\KGrK>9Wy@'IC#Xnx]D:e_\dI"!2JY|&*ws)&sQKLs"4 0~qer)@vԒ7"X 7a?CKŪ}SЎ5v]cTr&IgA?Ps|R6;uM;"ow$AU}߿x2ikQ)Cd:{Q@]x&Qįov@QN斢vRY`[wGrJf[Lx C) j'Dם, T@udftϊ87m(SeٳL)cvDt'a$VP n܇uK$&Q<{^Z2.Fz {-qY?-XNp0'5Ь~` ;V ҍ"\s~!\AxI!G#䕧,0$iJQ*Ssכ+]$|st 5tȃKefii~:5|`ʋօlSVjd6Xn+l,yk.jJC)=uciC iH>0!YMcWUO,X3|qz$C<5y/8{$~y$M|e=uQ):1v:͇^ Ag_ؤ['|0`dV fO>Փ c'2ff_liI,kebzva&{@͢ʟbDn9m*^(9Ed!W741rHڮw@ٽ%sB P$6(ML /p($˼}d@~}S$~UG.NNN e30GtHPm$en]WX-wIfiy1Ǖ\E=WåG^;*yae/ .tǭ{ann*[_NEV-u*V"_ 9P9ִ)8+rV289"9cLGOo@{ ]ݵ:aB̤SW"d F%_ùج3Z!+ܥ!3L[ 0~ۿ^W*gR -wƌӪB2Һ^oQ`2ǘ)V 5? PTJp|B[8qlDy)x9FI8ٔZ#.`fR?!ޫFw.ȱL{$=$TX'A=D>:C "gSx S_xMc=mk[i\uv:`Lҩ2?E:J'{sMy;]JoZtSJTz} FS0 +;95ɽLtJ%nMJ&t̘ܣCzIk=ob5Lg%_8ƾuH=m.cM2|SګZJR]aobnCU鴢;Hw0&CAvo ޚ0H[]Q"^rˮpEw$Fć} &1 JáviPZT UeTEJylxD凓b;@75:gH" xFƻ=ňw-je7ѕhݬfe4{js#6]7v9pSsC"ɰbF4ûw㊢Sm搷m{"51d-ZVlIBsG*ƨQR+K'fOxy2DY+nK%z16tS9'z0gN52ZnUGJy}܍\< |՚)B^9\yK%:p%)fHG5jڽ'}c*s29ХSTY6O{tDuFY}/Ǎ IlDZERܧN@wǹܔ2Q:,spë8Ij~) FQ܊ga"Lœ1OZTAF(4O eIy5y;5V&Zip j<ѐe azgعUYlMW@Ƌ3{Z2w9WR2Ck}?s/^54jV:3<)~|:a9mT|j~>26ύ nu1t5hXKM=zXRһ5tI/Op S>nR KNˇ㰱;]iWl9akL{Ԥxd- l3ьǧ EwDzjV:PᎂGٓ-ݡEQX7v#2^=m?& endstream endobj 98 0 obj << /Length1 1357 /Length2 5946 /Length3 0 /Length 6879 /Filter /FlateDecode >> stream xڍVT۲I HG~)JOBޫT)B PHQ MQK'"MJQ HE=w{kV|3g|^>oj!qA`8ID 46W )D$,ly#XAX?$pM,#ڴ`81 {P*UP@iD_ @R kb|Hw-(UTTX$a8x" X`H.)Dxp>J`p`` 'JH`C`v 1)0`caX@4x#1ij }#菃P)+;cP>0t0!U#)\N]9¼0xX s!:.訛0bu"}p~R~H_!^6UB!8?ЯXxcBc?k7$W >`+4rDA |D+e7e&naH7 ?w (pEq hF'E!DAȯϿWDnb.X@Hw440A^RZP4@\3) Wcn@O[WM_/ae!2Mp{Ni;c,oߨ/0;/Wj#Wc+>FԀ:ߗA!\M8[70!=($*#7 Gj_꒖`X,,D1q'D"~3K18b@l/ p`A)/#X,QVO<_F p~˛*y%J'M Tiϳfi=LEv&bRC͇AoWhx%-ՖB}CEzד_b0g "M[4[z.oH{T^U}dpQNJ$V0K)A8(lL!nVhȧ~\B\v|;,.5V 8>K Fe>8膏(\ F&_zM~~}Z m]/ZB7b2ұD 2#NN _KK' {0<ϭs1 {{2_e_w+| ߌ^U8 :#--pYږ2cU#ѸH8Wᢐpr,spp^-Q:Ly5p͖%'ՈNzRЪEq))飷Y[ȋhxu/%9߱{V޾gBO.֧VMyJ9uњiNH>~[ҥ y\iƈ< +PvQ)ݵVWrg6r+Q j-ZO mSuѦ= EaNB_kŌ5ಳp [. j-j2ٿry?g3畦1Y"s6|4~qjhiY!}SU,)+ׂڃkjӯGXf ="6O*{OVTbjL¸4LAیyy>HJʙs<;ߍDyfV5~`lsVUʫ)"Ž%M`kuu܏'t}ZGm6p5pQa5+ t4BmIw?57>pܘEa8㗺 vnYںM~:YW9OFU&5ZV(S7 ;~Ig,H!,B{=X@ 6_XPUmKog~|J2/:H{}{R \Ń(q^D:2wQ97K.VSU+(kMzVؙ<1  lP=!f!*7B6G qaQ<:Y] yO+QW9z\≀v%F]%f8& O:d 6M5=S'u E[!.òi6s>-p;bW.c<-rHrB*lsH:'n9ŗj>Űmܽp-$+!{ϷLsrvJ.j#ɽ]џ򹜑_.A[h*YH^ęう8vD# <+s-1{S%ޟt#PՔgWQO"Ǭ$hȘu=9U}Nc ;eMZ=d2[剦ܮ)j+(ȨfoG]nqJYތ$? )/(\c#/}H^VD_TnQϭgeW>h|gjƭILdfDHY3e Le-9SKs$ \UX ٫;>}O43uF})b t]aTnHpi/mC7)Ӟ `N;xubȃ]e^S׿2o={M5nC6ژyZ=Wo1WGF[1ϧ  c4M*be>ހFˢ\Fa#;A(T9e1^zmKeKrוu5#_ 0o=@qe,BvrPSʕe:Y(sMgeB \k>4su_f&Ukz9 ;Z\oipTlw^-]Y廦Z$-}l,q9+m̐x|Y(Q=˳sVzm2wAM2kMƈGm\M+ԫ/=Ż滺SRo-9 61^+ Fv0xz`t9 R]i^rf Vy\S G"-c&f:ƁG +2{R:N|6y:a5ɘUFC.Q.Hn`{{> -QMPTڪ7t0 >3Z4rƾF68JPSDxO_)Py7a)jN6v'"ldhz!ծ/l[:G&ԪlhFG>A*^M;ժ 7ZCHщk]1]z:҆4~z_w&n0!-(",adg#Llm' [qto_7/NNsUaj{[F>ʰ~,jn(WWX"&^ॠNadΓb\d\.4Itzy4p'-̉pus&k@) ^$}kK"/ NEBc}~ӗ^ӈ/|OOC>PîuԸ_CpT+F2 )Em9Qq(>Χ։'uHyg<'R q?K947-D.rZGf5f5#ǵzW ҂1Zbk-* ҮfnZURCyz.,vj Oj2+ӖZwWQ`g?Lf12Χ}Q5Ѵc%\&~tU-7cKKUA:_wզjuuxK 1V[/1"kMSɁO]1{CwJwa'%oM-kٜq+DQ}*EF_O{ǎ.F0 ^|R-hxv#Ua عyFbgCRn!!%VXpK}>n)-)``uGܟ{vaIc̐Kȑ.!cuQ%[2HytI) M *kO?mfRtV &:wFR2VGL6za˴48S]e'''MJnfzBesc.7)$]c@q+)/sBcE&B.>}jX@{KtV.v}${P7mTeK=>iOb0Ib21"1M;0bI<:7tg9%f.Ht[ lz+G3iv_Y = ݔq3EKe f]Z4}F6+5Gh7L VNr+*PZŸ4ҦC8u}}y4+3кx9.p9s>ǩ>۔2wN'(tw |cꂝI$eW5.0)<ۅ"mxҵ &6 N*Q i>+ù;8 X)|8j~I9)É>%w|TwﲿU ǖ! &jHЅ/`^wعbԇHxpWu@gw7U5շ\\"F +-8ku >;o3{|2~)h~?_G1dMj}gVVeiv0!<,/qNCLudSV6bb^d;fTrÐƌ䔀S=rS)A]Jat'@jY5v?YaY+S%cNҽ՞eW;Z?$,ZL<M3(2Ŕ[3ti5 [>3Jh2̝W\֫Q6ZRlA=G'[S. f"X+ʝ$@"_}$ gswVh7oUݶT`rZLBIi5b<1 BƳMCݴ%DT٬،4C|ޖsKuntd“مW#5,ݧ+o1D4pĔ:}i05j0ugMi8o50]n,gS z2޵?٬P?p XXϳ[&F\857Yw<)>gWBu4 gS,"8AV+BÊ);AŖ$|?ɽ+V%V~bCSE"^Ε/jQJ{ Թ>yXVUȭh;dtW?.$AKY?xɁŤVq^_~<7AV/=U"Jc3rB{7`B{p?CkGW7IsO gŋ {sM> `Sqf]sUE'ZxS o<`9jޏ1fޡPvySO\X4d{!"D]#MR6grh0A ɢvl( 8`Oe V}oJM}oDksKOQ2N1Wx]Rdg`\30@B@QMl/:oW1 endstream endobj 100 0 obj << /Length1 1357 /Length2 5943 /Length3 0 /Length 6878 /Filter /FlateDecode >> stream xڍTT]sI``[DR.iw޵];g}>y!REm 0!H&pEB۔@(6pP\JP $((/G8B pIȦwF@QSpr⼿.`hP` (n # *% rAx##`hU: $!0Z48\fƷb0meh%Y18Elbg⤣TYjTKr)bISɫхW[w8ռhAIo~K NG{{hD w=XfBn@{tj W^EʍV:ޡXSu"CSL@`^k*.U U&=_:Y GHr|NmGr-EKqM#ZV k Nl*.EYgj{M2d~E~aD >NAu-pAT &"b8.fSo/lx2yšq4AWHXb. TW}jb/6T8Shf>q.@|S݋z\‘լVqI+wʓ#GFPToG[Ls*6ҧd~Wi6{!t᭟.Mʂ5V$&ÛpiWƄ}y岄[,=y"cIp]!F.ڑzBPCV&7"7ke sM.@iX2:[HRg1"%<\S.5a„t`!P5[Qm5V'ټua*^eK[ǁ3j.;Ʌ(+,M1Tjz!نa齙5l`h:tqLC*⭱l1{'Ǒv16;[\Z8w.UkPJ9QjH4j僝SV߾cL/2H" t6&6VJ8ЩOo)&.2ta ? =Vj~>3J*ȩ2p7;ց\9rYrz:GOvU,'g# (T?{f{@Lgj%D y;j>.eHW88)+5 n& d&bŲ+~hJɀ+4"71 ^jg7 u5Y-cJ޼i}>= d5 ѫ@w= "ۍ2k}aa-/fj 6Fcc z4+"j/i|7֒B_pR+hG0dB[Ȑtm2 VbZjZRfwi%iǥ˘_zi5FGߵ iJI)9_*7Qw7!W~ٓ~BDyLM pd ͰvuyCk)zf#EZnF.Ne6]R9+]&(!_JIVv9u>T9qlKY˻XWd)K_3m=WsKރFW;u4̮SrV]'u,&8yFV{|yβ1?gL$HrM+8oƻ.Z:wI~- - ~ !Wvct5ǺV\=bB(c2xc=\JJ{!Q)J4{Ȱ:f,/ Z*.|f  huW*:Dpv>8?*ul"yV_ݞ& +>&mNc7:wL25&. W :TvͻaSSSw`}h/7p"J69cy ű939*ڈJu`xu,hrwwВ#pGmto{4;.R ihBfHPɁ-׻ls 2^jv)atgLǓHfܘ8@;RJZ^6rR`wX0IL2쾺=*_kת옕a1ݚ\`~t0\&8HikGG4Kz(c5IeSŎ(RUx P9nFW`. z4t$:3CՃ$?K1VD =u.n."iC  fS/qwQeTnx9RVv@l>jR#3~~d\eɥK6dËpu &]GUK[$|9 Q2FW[sd1Fb=)Mj stK5w{7j"n^x~c$ 8#5[ɺ ?hS3,>[[ b*v^ɇp3}03}?"ƾFZ[agY;".D͓-(Dז %56;  ]5!'lwY_ A!Y]y%2YA"<$n=YD3Qcf<䃶: ˄/mqT}~ϗaĎhtZ*2zN]^gCț1k'&>߬Vߨ~/-w\]/&0uX\-^>mޱQ"tm{i떥TϫQ\L܎L~rbP Wn`;N .Ny3?=^Y\- lQ(-3Tз,w7EJZ~ߖМkn;UL2h[[;>_άHگ#2 Ň5S=&'3uxe21jI`,9!H59;}rP`ŰWH*'G[5xc+i>ޛy>#bOpR\ ~K{jCܭ1q'H e zPv{*32SxXVu7q$#et#kxϧrxnsN}H;mz3zODwd1Ŭ&/ W3&' N.(NIT:bT[?xI<;uw²M{z 5W0?p[wLQ[ #WĿp@3I4slDp^`*Wy´w9e=IDlJt5kz= N)*R5 8}<i\'bDPo٣=XU$Q&`(FjSx<XcZ* P׈哇VwrB( 0O)mpXMRzJ.Qݪ1_ÄYtE Ŗz&c]z&?#ۄ0# btgmɇl6eǜ_Ƽُs6S(m ],GW&?0~gacok1k3W ^j)fV#c5]z1'?EQcs xmU'ׇ!7Tt.uݾJO`'gAyqzwRq_gGS`YLwv@*Y 7b5==&ge?tƵ& h]eVt@vWWgcpY"l0hٔ}f۰>L%!~* 5*n\J?{[r}}5%-QT6 {qiPQCR鋙NK඄U$kONv?Kfzb7?6cWД  PN.-)Hs3$aTEM7dGz+tEج'p#)<̐GC/rhp Y'vLJ"ˣ37wY"0ץnsIV^#`)J.`}|.2[a;WM{;BGP?XT5/*jPgI +?'_|3.v_Qh̾e^. Ni"7~&Uov-QBtMk8U[!BeWtrC:(鐘SsGomyJ5{3T:Q>]u>Ag>9NI쵷Qx_tח[ 0ݦh(t&x7!CHzR攕u]8@} 9Xu haҋy(,FQb;>q*.i]:}G:̢_pܭ$BߕzE|rc[gU̶=iTұe\  .|T#"fphh]Jɒ v{#+r&1-3"(i aN/J){g9enُnECjD~iժTP4?IO _^~%ј=&c0(DtaLM5^ x6G-i`x F&x "np5lgobjk郷 ] KJڨBOjuYj/'VjxC]#! aFǙr?6ы4n)?>)6Ө{99.Pu:ŨJ0gYx懍 *:siӹ9Acrΐ΢r3SJww?Ms:J;zeٵuz]njbxgX˿Vl7}*UfA $Eu*۞ [4hNOnL.\.VH6\6u1sа]y|= QT 8̊|ە9)g endstream endobj 102 0 obj << /Length1 1641 /Length2 9899 /Length3 0 /Length 10973 /Filter /FlateDecode >> stream xڍvP\.`p= 2[$w {'{^{fk}ji59%, rN0wNP \@ #/; _ iW&v":J/$ <@N"' PrA0}\6Ou `d9 H:B\`@n q|h vh;YB!>EYˋ j# nWOw5#ָ0:PN^`WܞB<`VWSu @7@\'w"(`3 ; M;9=Ń=PᯥrSf uvwr:wmYI;9:B`n'uX>?ks YCaVֿ۰pօA]< 2pLl6w?@\oK[t|!9AO=9;9ڀ@!O/ ?7' ߎD  j@a?!wzO<) sj+RRN?N~'?y@@CYO" r_KG, +?s9=)`#tc ?-Bo*)^_~ u\)PuzS!* ^Ew4Hl)'&Xi@-mvA4ܠ/'/ӌY?]"nOy,+ t=k a%O` l fpkҊRyd&ZBcOqUdiەRA{Ź&'"i^USgVNXa5eaOd;\7qЃ6$,g0!uG.NtZ')&k>vTEH՞mvD8bF窑lGϥz|9aekbKmd?2ifkSчMWvC /E1f}УRt.E|˥v',ߞR86 7F~}/\*S@o Bɤ$%]vۜnW_UVG}_ k(6JVt(AF1Y頌pBd ?cNneG/or. {Z({ =kO-h^a̹'V (Ȝ!ƶYv ºG>]1pulQxKy\9rT1uҡ+%|%Q oM清u!+c'ٛ%c@](6Bj_UTi3 %:~sߥ6HEL^Ys*QxgW^I{2}YRT|_#Z%U^S;vC.}! e/N? G5Gw? R^ĤHg.,.Fg~FE9(VB-Hj\h|]x k^C|˨e\=KGϫTOOXXx'`ZU m{ _aZWvp>\ɓA2Hno[ϱlf?FZ,#Z^Ɋ4bXXRPN.-h#w Dʩl;n))TLp!6EzySo4H)R+Ke6c}/8Lx̛ğ>j+lh! }qFBc 4Vc e<#U5NPTck JvX384l&<[[LBE<QqXr͓4ALٽoZ1g6]YA)(M%1'&4Jӄ"!ouwSl (QF [M-5۩OԩSALЄ(QG 82t|/Ⱦib)0x3*Nor'=}zl~1=F*+]S2zHyt lutZR\:bcg[PGsx(h-MARr0X}]h ˤNwC߉JhB,>gUeʿhJ)NAygOFE??Rfw^}PN.ק|ĨERX tmud RV) s5|l^9cw"M'& 6,5Or Kb}?rp =K+\O2 X 11h=,X :N@~|$Ҕa7 /uQ\1j^!W#)k#֐n>d|^SCkVݵb&ց-d{ W 6/W@B:LR -Y<ƼW*"-h>^%6Mϕ|!aAx*'ȧqTD۰?9#z(z[fţM%'Be0ɸ %Jgݭ&ܵG z,bfyͱ#;}Bf+ܭ+d jDgǮػGws?3S*TQOIhǹwQf(||[lgaͨ*Dvps0MS2 яXG1NT |J ׏ #;n:L\iIXwК0X 5^:ShM=)."uc#=$_MHJHLT/7WHSsMS?dcܑO4Kyqg1͢:A޺$EAq&RD1R f(D*eb,7> Pm -!*ƈ{C1"T `<ʼ41¿pLdB]X%S>TIv }ž,C gMBПID5 f>hz]!UJIjn!p3l:E/gAe, +ч`ڻv} ~q[0+v)W5I=c({.-^[&KBn "s%ug)6p4fvG]` fJ9(-hx} cIf~ҙ%++Myr>6Q8ϐCl6YCTe0yqAL$o()SYxȬt :|m`˪SXch}nBXl.Sy}RWd|^á0V tW\n[Q}OE --39P\,޵MAx)~ngr_i\/(γP Z˞ Cg#3Ev/Bo՛I; 2t+D"!a}MyzZS^S۸,$D->J-B%!, 6аc01- K%g^=TuӺ1ndxEi*`\qqR<+8$Mn$HYBC/G,JnOmF&L@_d0b j}X+_⺟gpzYgO5yh5] :~IHh`N Cn/JTd+X @0;N-@y5(Mθe܏::"746>Q.YlX:ȱJsP~FpZD89="i&f!fէ݃ƨr*,Q dP q0#m9<̖h䙢Vw]XHb["'?WYyqtÊabn4-꫑saR߼DXv*OCB睆}ZzJ~SxܤtCkDL5 g Ͽ]V dH2\- ~NxghA1oM<ԜXdy=!>V HY=AQq_kN4ڵi:ѡtMԉrvMoŲYT_\>nuJkm7D"0ii|"Y9"+*s D*1z pvRpn`88@?oI) K:܀FI T,w:D_"9`cq,HsE.rIsz+O=EIInGFb)ux 퐉 psGOlK? eYW0˄ >2NV6S^J5ʼnnjtJy(?`!UޔrX0Zm_鶤o֯NEg+ YU+0;^bƟXYp%Nobp%xx +I{8̤' E5ڌO͉(f+uwWOssd͊-SWNJNC֘rc\\w"4K nS?*LR 7LyRC:¹UyTl D1T/d/FDQJ=x跷tv$<tr d1査l?V=!@Lu:H%QE>Eyf[ؖt#>, v=>zөO _+:zf` yAW( ZPg)r8*_ț%@R79Wf"ƅX[r`7PC:WynleUek!.P +$(9 F,7Pmfvw1df_j:=F e.cw*CZy<뗮q:>rkpGTS|ͪJ2ꖈ!}|[K u|(p,VX]?[ZLzNBQP޼&(]cPbcpxe(C7)K*N3H`yZ)2q]_n@xpw f+*|~,,/UTбǀ6Ţi*%OQldNp 5nؗr+:OˊQQ;yr1.ojXѾ4R,y7!J@Ҫǟn%aI[:xMBڋY[f]Ú'j*pCf_a|$Q,/:+o -2=r_̜a†q%rqo;1c֪:AQmqhj:vU8gmq;!?f+Uw7WSvpK8ܗBV(r`TV{S3!;]ԋ6fESX/[ټR6̂O7KLewLyb.E㭨vz@h8II\u$U!2Myْ˩~Qa`ofnaz:jv`?vp1 m7N܌1T8کP1LcS?mE^ჰ qoʩ="0߈ X-%Ǻ&eD` 3dFP6%XPwzǠG卪H#=́!,1}锜筎G ~ĂΒd!+z\B a8v]F]BbWcȴ:$g_4&)>AfI6OUSv'Bk=Fn+ߋN@ՉQޜ F$CZZx{:7/ oǧcb5 J>.Ȳ]b3]Qh `Tm!f|l7rSȟ-(7<Jih︄A#jm?a0xcpNP~s!Jlh?ۊ'ҮL8;Sny0( ~6F=WqC9qA3t9q$ &93hT)0TZf~aa:4tݭ X:vI[[ӓg{86LJVy7cF8t?֕!ceC;5,rl"͒-!` g)~>2M.Vdk$Vn|?|r8O}iIJF?<[q.O [Zu4SS}A µ\8H$v{1 lάCCXFy HCc*Ov& pSs-u{ Ut|h:"܊|1= r_lOK+բs||B[/km(5s;do^I¸%{*Vc6 uψch)k+3޷!Dai#}n7DB' 9ʼn!Yp.]hCZ\R$!.&x(ܵK8CbQ2Y7 =u3{Sn\2Wݷ)iab"ph W6IP*@jqcXL)uv^]hxzƬW/xj.J+q~}!>Ʈ`R@Q "Olx)ז2x:!ym!puDRo[0 \q=>C4/HXʈ]MQ|IKη+MxvX_R6U,l,w`Py`"2]Fg@ /x8dQ3#6M|w~pc,[`7!ko7!݋{ %Z{ϝu}XFM4$ڗܹZ|ӯn)13-(y˧ZFBX^AQQVt>Lmqx ?>(0k&p󰺪,Weqe?"EeG0ؠ,ra noqILڇ{wcc7#V{ WC3lh Yul [9AhuEjyiX*3u[¬_^l'Ú8dz(CmLӬEu$i$lZ&ͪmr beA֫c9YQwٟHWY2%3VZކ:S8cYrA08)9vrg*_?/mҋ9 $+>pdnOgjAu%nx|k7ɺ,,lJډ߻=?bu@:][`.v.@3o_Ek}[4c 0/nf96Fi䀻 XPgQ^yL 4<;(@2ee8JR9 ,^߸;WEC^bFތcy@ؗ=rkmf/4`RڟJ͞LK @ԭCd@U0]UasuaSpFJ(͢KiMxԎ>O} c]',/|FPvJ{ ܌> stream xڍxP5ҤN@zM@{B@HҫH Hҫ)RER("}?}$gL MPu$-TL@@(& qqp89C"d 1*!!m8$IȀ$e@((7-Pœzm$"RAzx\\ј}~ @ҒJPoѮP̎0`F{ʈ =PHoy>A 0޾P'`_ qL]a?3 `8 E0)>'7;DK` E!!:Hre*CNC HO0"p8P0-#~p`G w`Po'%( N*H("՟* {_@!^9Nοp1C|Zq0ѿ1( ^?U0f O'34 żP@  8B]`WP?k{@@ǿbDM}"F2$$* @ @RR:`_}G .n/ e>?k#1ʅx-t8y;_UWwG>p8{10Ac\xT A`>B1nPB`-# aP'CG5p_~PC$ W c2;S ~MT\a0t3@DDcRCHo_ (F qG(_?8FC 7ƐłioCP$D6ʭ9QO+8q4 W]:Pp-H7rG[EH;]9Nr4qiYx-}o搕UgV#>Nӟ;Ӑ(8͑l.FVlJ`Oh%6GNJrcNL0Ӈ7Tɛ6o |i}("J`SwաRG}'־rl5~(fHY=U}"?m})Tj ݴ/`7Ĝlz's_qLCf#^۞,ޭ2Lof= 9$pn?N >iӦG*g1ZZl^/[:8tto+ia״-QU8ijB"&j8LVB1F~eS| g&oull屛~x&9^4ݲNkQ,yceO$~+,G6t>7i#z欚VPhHPb\<鍫jx1vu|P ~uW.Ou2ڈu[#<ۓyAb#Gt1<=Ǖ\" wDt y YYs{Y;[Imi t7P̡qmJcWD0t܏})rcΏ]2׽F{n/; ~gj'~)%4ϔc<%]Rg'K!mSH%캄|]:N r{ ,XdzZ^^o"AHHiwsR04}Z6-#sRXi⍴~qof@}rHK'kSv\@l˫}Xdȹw>tG< NO^e"p?EZ$uNނH) z1RdW6Dq>gB6P]ʳ Fޭ.k Uupg& U"A<5wc,M1_E޵/ދ W:|G:P=EzlA\uNhx_ӤU5i?jR%01Z\\чKz $Jq< dYZ;h매<ޖ /wv 0{>f11{rEe!8ҁ7~0SY yߝ:s-8=5`vsJV-L(\+V>\U=vC!稗UTh$rNX$ȯ&~;)k2)+VF':a t)k[k!_#t\VzH#$=k"5܃$pHyZmĨʸt(u - l< ׏%XN ډ&0F :W|GW`vsעecɀZ+Twvu2Hj#<=k5~6sDH"nQ8KG70[|ۖɓ!͠t78MV%)0ozY)eQ7Rgy;Oҽ %e>Bө[-=)ou'H}SU]YWʠ>z):z,"8+6wq=]/`<q`ATJ֤D,.JajE)TF#$}jh^d&$^45,Bw'` s0A]I Cxx}֎E*66md_*͆Un|Wf5?y(VM&GVP(f=Yg;swj){֞iO`-K zbLXPfMe֩+}5xHwy]U;%R5yk"T HcS^j}sgvl5x"~x/⍥y@:{< WJ-_zdB)NiI-9fU4wIvOy7@߇[^;$\1Z".L鮤eGwNnR*k /7y.e$EA1|wmr,uzwF BZ~~>n٧piOv>Jo[<_oȓbUzfJ8.TXR=? ayEh+ϱ$ſo{U9r# 8^ss$Yoܶ,)fqZX%\ aNmWFti;;흽CsgES\,ţbN=F Ӎ>:Wшxh;~lէ>#ks^"GeC');P|!^Ѧ5Lrbu+?핗e .|B_IWAFym&J# 7jͿy[Vn/eFrԌ# v |b5YX\z!̃ eUJsnz{24ݮ) (tنMV'n=){<yޮ[zzDm-Q$^þ cg*kuZL }RiQ=S熅W=nRfvnTg2&Fg֪*I<%911ʺK?JI;y*EIfրo7- ڑOE9$̄x't梀 cs3r{_QV"ڶ 5~+! {%-uu.Y$ZPyOTl{oZ"~a\|396;;1?~F֢Ta.Iq5^7:teT A}b*cpbiR!utR?y"_IɆF>Y&7)FlR˽ê[=S6PMFX`Zrp ;鄼/yySOrvBJZMmGF_e@ZxE7\IJP~rB-0XL313 xX5wp//llRA[@F3p׬yA.-jT~"m.v lx9 QȨ5͜nkv%M "R\ҝfgmP|4,:T\VWILGcyθYܣL&řԦh<zQ ^#yn f7h?L`Y04YmW֓C3dA8]u02@hAgZNPZJΕ _#jwc&9`Q=)9N#|W޹>GԖZvY\!b\l 7x_" fnjѾ2>NF>쩛M8kJ.HmJX63XK&S1^]W9rBx|>Ӱ˿l}H7Sj7$o>W( ͅ(q@+˝=8!?eԍ+ 5|@ٮyw=;e&g_px.=m!Q XjDU;a$n~1ΨNY6t Ha` e"_ ۸%LhO]}yF/ 5ӣCRQ kCFߗ2-tʏ^sYt?46z G0 Qk}nqq*yWnO2Ê>ᮠ8bLkM=!S@r"!wn( \L_ԹoJf-i7r8f+3NU0qjtcr+#PZ/SA\wok\Nȣ}|tOW~؛[~Yo8:`E^)ҵW؆߈ӗ@ŋSvя W\N6 6(=.άD]g[ (c. *6peŶgADs8pX>J #˒ȌPyR%zl|۾m){쏒Nn$Yj765ԑ$tDiqQg}o\k@`MC+bQFHgr{:z/-߃B̆2 i#/f˭26|~Yلo$euF2.N951y 9;T֯2$W6x: 59O&2MOBٷzjhѥ֨ ڎb{GyNUGi}M/cwп'p.o>"uG=K:;JJ4-L88:-٦2_yJe n endstream endobj 106 0 obj << /Length1 2106 /Length2 15127 /Length3 0 /Length 16404 /Filter /FlateDecode >> stream xڍTk 4  4!www43gfr]Vw]U}ȔDL ,̼1uV33#33+:Jr37q}wTpȺX,,\Vff8:8MAF=Jdi?ft.D 3{=-@ t Z~+WWG^&&F;FgKA:z t: P45F*o3N؂̀.!n@g{v<@hrKd`33;G{/%d (I3zLr4uqx7q7ٚ;t b rtuat#_2,ao.`gwuA>q3ܽ}6>A {s0wsdҰ9eN!,fffnV 4b+#_F|m@w O"9` #QwyǏ 'I\BTUM[QT ```08~lwbe-<~N)3@]+ߔ:"I7[iv؁l>n[ U *Anv*j "7ry͕AfVO߼_f *;z¼G13ټ?E\G_&o^ {3󿖍`l>Q4zkL!],'I/o `g뿈$ 6`3A .kAE<*&{զ쿈f`~abu L}ߋ#^w]Ox@Wlގ^?0La~/=-`o pò{}K_:9w5'7WH1 ˻u$'q|??p?G˜9w'6UzBB;~Չz0O#DiI?޲F/D?nana1͌Ynꀶ0ݥx:uwc=5f7Ĺ:q'0)n-n^v[l;OߍU4֩Hrk/ &C PZmF**2-1jxI]L V=jgNdP6DC*!w ~pW2,֌PJȉ6HaFiŗܓ,fP ƓvZU-Dʷ@Ve.rD'O3\P N ؔ//LBמIm2G%kk `~jBom]ӓ)ELNnCXsļPB#%&D:62l5R1>pZx%.VgP!{ؤZ6M2*x>/_|nr,AmONmWx.nI{x h"'\ +Ka|#/KpC{rFQLV]$N*?'o`,^ڥpFyi|R^X8xsЪZ$FVBc%4&~VUd**=d^)gwYrj :ШTjNϨ% .?kqX ?sS$aHQAZZ|3D1GBb]PX}E&s=2* v˘k ڳPZ$2~b|"x(7mRwM>;! ;lA!{Sqn `Aul_^toFsRDg~rZlY3UA9g m7vqE Mq ~_DqD}E{50҄ IPnHLFjfxu,K@QM։\DHnq|?X6PH8Tr(':zX2wI%w-]ֽB|AM2U"Re ;:rrå˿[Do\xEkYe$6^~)`P#B!V1:x"mQ QYVr D,a\3I=~j!Z}?(q_HsvcpDLz w]*3Dm3(-} Y;2AvzwFL UtC$]$? 6@<{-S[<@oUOͭ" {y)cZlg~up֑jqVmV4>GzÇ!Ne]3 -u&'^qn ,T<eAeF?EN9~'b샯R5hj7 ȖfaEz۸"q@-ށ٣D2)~tæ6 qTge\ԏaܠR K4 zFZJ@A^Q( !"O=\rxIqH2q460f3Se?qIcce(S$HKe ѵ#oQ)ܚı9g>Xgv~͇ænwf=6ܱwާTHBbSc?3yzE4n0dtjdN=0/-u8[4yWwV~)v.^7V8tڄY$*I-37v9N |ʢ:3a^"UrLC\?d~-cìJԓV?,Ymϻ}@oEry D&ݑqA22هb {^y!c$Q:"5 ?!4?2xY5Ό FLBŵފ:lݍ^КL$`bG1TzCB2*ܵWM0 F<{бooqr䚅I]+zNq֝g: V,a].nOWs2 A"y8fʂT1bYa!s[fBCBl0d|JK:0F/y[Y( Ձ*vE ^BVn'&X:X)k2M3ӽ /Gf\{`?Ng>wT"9SU{k'@%k'~aOpZ{/P2_G cpPr7QݲBi\{ N g9><߽9(ܑ~H #}t'e3#OӮjFlrV<9g%Q_LRhrK;/xHvuꋎW&!3@/OQ)>wmi㪆 ǔIJ*9ѱ|x<r$YBrZqJd=,KSȃ;h>>_:])7lm'k%-l)#?Օ JҜ) ,j`sRT:i}Q5U!-V씟4Jӵm@oP|f ]~ނa /j׮Wej֒KFS`;ޓ~5P葽 o>*A%}bH vȈX:W ܎:TńGk]E0W7yO tiy4Ѥ.xBI32 *6'HGmC_N_qĀ!q?'/4%wT ++KFGNp1,musex`QvO}Lm/QM#Rlc7,'qOThA\XbuSQ//Q0RY㳦vªq~Au‑(L5hxK7Dk$:>Gv+A4%bt[?jr5! ܠ35zidm9]y z:D!MT[qG;}.UK1S/M0;̭z+3@_^P:jhyX£FZ Y"Ŋ! }w#r{*h*WZ H`~Ƙm":b-k3c0RxUk\.S$ .G,Ya%Z8$*U$r˹.d[Jz*L:Kϼ.Iє$_PSTwpvnzVmڵ#lN7yEt>*i#HK=15ou={|LB)D \32O6Mc / \(WhI*)wc(K5|ݫ>Ws&1ި`֬& oJ;t0]Hߐ|`VEx4rN]۬K~#6bL8تÒõ*q7vW0dL2t^7UWk;1  CWC'!+򛻟Wuȑ|jzìeYMR[N&.=L_){ y%&uƅ 6ƪ^ѐZ^@ a(2q<>^*kP"fx#k/ꍥSjhqK$ NFy9Bdh05h&td|].ŷ)PsOk^aX [?j$H/LJp?qBOLݐDt}SA!&R9EaO Zwvz} ¥U]*UrRt{N_ݮ2N&N jI]E~q~`+%,"dP6APIQ7?Ԅ*<%kNz4bi,08G0n&GeehY&0Wsm&BvjrAl[ʝr U*>v4/fk\q19'(nɰ 5۵ˆ$̝ 5KҭT-,vui`n-?FZG[I+Pte)R|"' vdP@o`r%c MAEX죘ncVR!,?6q+#ځ'g;mR޸kb#^b%4vS}2{ԅyvT.rd>N8/]n| ̶;c>RXq;uSz+U+cr>RzYǚC)כd?9wx{OUϨ,7."_TAddV\Kd(5*mjȥ.SHGlӡ3/QJGP>7!HbRXӆ0CRNVe|,l 4s|SBok|Nj[/1S jC)y.Mv{2#JVì━ҫWkZ:j#M8ߡ?#躳}h&8y%8>k:Q"2nl#' +;5;Vުєd23n X>`WϴhJx^xD}@YrZz&CE(W\T&44,-](tAE6ɦ{..}v1]ơHMTdjWnM:g5 "P&ͣk'BZy{Ғº HJ^SB4 ͫsQ,"tvh:v2n]%rNṑp_0c %*t%ZOa1|,m]* 嶉߃DE,#~G W_7UrJxs2>8>*gIH.^2W*ء8JIѨ 1sN c{"nMɵj?Mq,?(gG6)}E:+]Y}1_ڄ'=bxW$sU:sҏ\s AH Z<'ˮVZ/h&PUe奲w%/]u7zȱhmU4VvK>~{xUn4kj-oL3"R qTu1|Hju @LlӓKIVjjm8!͈V8c^u7[ N&#48GZc{)~7IX|G&PgS{~s^=hǬ='?tjS9yR=JT5T'39o).VTLsw` q<rL9ݔäq:]/1a7t51=DVDh1Ϥޱ eu !mSFƃ~SVD|U@ví6H 类@o򰭘E}5{e720pN}<0ի]TSNZ!W+Қt,Iע(Z.7Komg5` YlV Q+cd}Bc/6+RO\/iE pvZ}p_kWO.~c;1_4 iHR0-KmP,\-4ϗ14,Ť&A~P9׾,hn ̬i1G,֦C"µ3^`~4BՑ[߶')[?{{sKHZ2 h=06Z?=z 69+_%#үKbs *wY32 cglw*{>}u+ؼޗLX8H"KaTr:1MRZ#hlK%nF(<)t#0=a#X^Z^u^K4wT9pGo xТ XY(Km[dj?30)s u-e*;\-a9csRL|G[]0LmvcSKF% mgʐtpIBwN d"s\$BducZcB'kxMJc@^hSP+߈Dڨz1y\.op3Yv'Iwq$֬X6J~r$4b=xr΋vL% b|0ĤJmozpxn'aQQ|x"L6GW*h#tv3)/Bcη-,P!Y&L= nOʸ] *M]x=+5DEJv '+1t#?mʶl%ak= [ sĖ<ݖf63Kmwvj}\T&rTiOl!Wm3U}7'"A_љ敍IMz,B;(vعLgU{xp(&TN&ܑ6ʃз %=NUPqiEr^֏CTFyH(ޜ̸Gneh\Gěľy2V0&mmm9x݀k6X,>OLn87gd A #C1NWrk/6Y1`c~ڜ}`x7S%6!R0TY)]iܑWm2X1 E1.Fц w*<@}Wr9nuqBuUz* П60ڭ,=^W\*>0d%eF Žjud,vPZ+en&7q$ $PP:4t :)(<lrkt%ʊ~E4(|n5#UyȤ.kBgyr]rӴԐccB'Z)FLiL+3V ǖD-=Fx;Ec'36+ID?lǘ\R֌6/#P(zVӔ{X yǁCInc쬭F("3R( >ȝ.:gwk>n9XIZV m"t?/ֆannY5+d|;}@EfYUTzudX;#r>bt.\vX" ^3%u"5v+ TI-|yq 69UICEN(%k<12d;GbstPmo$CrÇɴys ,m+<ՊZ۔Lj˨%oUB5qFA'fd9MZf[v>}&SU]VH@P %EIX.ą_XqۧfKoL9?Y|;`p񃨽?5qRZ_rWnѭuK;{Ih @-^OC,*ŵi. i*bT&|~N' yI%i;TRS]wUP䖋(!UQ^30g>젎po4,U 2=zRcٻ Dkf|h^RIz< f$!&36R"YC>='l&>8_ NT:vX~̬=S=x|hUDՕZQoT t6ѾX5f!ssɒ>7t ӃK \ަ&E76H(‡sԊՕL6 X ç =vo6i*DsͭבiN;4X$s &#W8e7.\'zuuѬ5+wK|G 0RpEn4Ƒ6tjQ&ɧ{e,lzF2hjj%x~%_fxWl{y`p gyXΞc'Ss@M/MG`*j=w'-6(I>jX8$4ݒ/dMeDjZQXO ŸNogmgLOUI0, .;^fDɧI=먰.fP4+dJAdf-OP<5)bzsPD&HzQu_!`%`[Mzu\S{{3W#c>c2ϱ-wOAj~<1R6< p</X|Nɲ Iv., %!'_Ћ&P/G˱?l| <I^(2 ]ڳбoOGSM d6w"pF{EA?M,rgYQҺ:~BюCpCC/rvI8Yő p %/L2!^Z\fu^%2GHkц),X=&X MKˡb/0[X= H.FO}Rj%M䏁CqC辞~G5 V+xZE$?P{E7M tobX6Wv5%/i \=ڂ+ܠߢug52 T7Lb$'RG0LIaV!PaK56^kt[ȟVq[QXKH,!ip/ˮũX v)T ƷaC(@O)"jEc}Y"9Xڷ>E`z@!ߩ` VYQ"*K$_8 ÛD:H\ߦ—!%WR KQX,N^ż{8 `6'Ű~EtѴtDĻM]!7pSK *Mv㗗zp@)9rlO*6X^rtMܸu:rjjkJ!fE)=Iް KM(/Trr@C;ʦsWfIAhk:2Dx|UNUj%SHZZ>keiUp&btd.onBo^RN5}Ξ{ڲ(fLK5'g-gl9x.8Z8U ]ԋ;LZN%"3u>'G S%I՘Icr< _y ><ᯓ?,h)lM9nlo#/}P/*s>)ϤбCesnu<( *CG6{;X|_vħ{]?K*{W.!U0A2yߒEՈ֑B`Q*qG6DQLJ*%e R^'w:ۜuSG.&( :ta|__{KL CH67$W9V,RJ-A %$SKUHlG :Y*^їGD@y=h7=] 6hf -ؗ1 o.'|nmR^B-3X>Jڛ ~ńFBUX^0_bOj5lb6uHINR ^vB|4/22- :+`4s }9)6{b7$t2Qfż.W;!ųpʉq8PgR6, 2:c^M:l|Qn> d2ˋX6~ko{VJ{ oe!J# Gu Sӽ!&0xMdt+ᒸmպE[)(k(cXLF\I}xXnS@Cbb_g cle'f_ض.g](7iY.qQ}#).TWGg`|I0 Ofo7T'oO0͂4/O{zᘶs85y oƿlt@BN;.ydcЫ`M3[c] -e{%UssB|lԨLH| H%3 ¿{ @O<@lH+҂gݖ ^T:" /i| ]*<[G=Hsqɰw&񅃉LNYjPJBREǢ}Y=-Ut"郝1mN$& ѦZTsZìŝF0HU-fp)񇫎v9'hh,usnA[ۓU(@_ #DG e \XbS+]E+`n EɐgO8[G\YT^ >LE2/\c(Xgabak-sU:zjp/ײNZhFq:/ɇ\]3i=Tm҅DV Iq t~ 7ZXZwn٩ㅳp`3`5pZfNl|؝h ƣڡx1>`&ĵ}˵!q-Қڕxw0Ti4֮)w!cH` bnkt!$}ʈBkMirfzEws:MmyTm'mjYUjG+6,Xm܂+ $9zP+[)c731↘st=Iv tKZ-Y=DCץ' J9-?J@A܅_ٛg>O caٛ`Ƭx˨ +C# +j#'k=Z_pw@MaǛͬgj7COݔ*l"8Zm# ۡ_;5kO1\![7 +Y?]֨º*`Ucbh_"}Mr>- Y5岉,G$dg zWF#3]P<<%ڣGbӶ{nIMjf,lƜ ]*mdQa[p AlcԴpz/ *?G5a 6vEI86"Hhq++OQ|{-|pÈL˿EJDpՉs>٪H|lYSkJ8|rZ򾼟ͺMp$h ؤnUE_/T!zX{h 2C~ؐi4RZ&FUhdWyPP9uc*`PϾMzvZxKL&v~}p2P Br2EN¾!b)Ju;n%)kZSeg/fbĮbZOTe-n{mS\f&tq}֡yFc3Fbjknƽ/dUuf2$.LtMN)_ٓʑ4V2>Cǟ =Cʒ_ny1Fd^jH'Y[Dmgo517BpYʏTiU@Y|W*..1_'18 <$$s>n< 8sHa[FOU4V# W6h&2ށs G6Ƙ =g>Œ^#KG~dc鹕>K|9"v:7ǭh@d6Lʛg>GX66-riK U4FYFT~ܴɩc>7 v(CNz 3SP =֨Y}VZCO.jh/7 endstream endobj 108 0 obj << /Length1 1604 /Length2 9489 /Length3 0 /Length 10545 /Filter /FlateDecode >> stream xڍP.+V ww)N!;EJq/ZR)VR^ڽ9w2YY~zg>J5MqK9Hc`eH*kiqٹX9ih0{п4: ($=٤'2jp r 8E@R@7%@qHB<`kS[08@P ـ*Z 0_)m`0'A66wwwV +j- pl  d =2@{4Vt /& O{)+ǿ;O0t;Z + :Z&] O@7 hD: #>M|.P̅l{FiYRrO Y<'/dv=#$/7Ʉ5agg  <@O3z;AVOc|Vto|o[ k#?AV{ ٟ`?'YB=C %N  |;wwjհ {=K[?27bax?v$joO:=f<ʐMp_.UY]+>킸"Ya6YكAj?岰{=\$zڝ(hd<  DgR'i-AD `cuBO Pߏf*dc`Yrجl6<6? )*Qi Ou yГ@ `<ՆTn8`O n:B W(si@ s ꐖ$,[c"4[ ,_7X(I A .Mi7M(_ԛo}L4&& kzHYl;!6+8c]z.moW*>+bю6 ,5Ϛ}I c!Ce=9PcB=mzk\ӥ%9$nѼwqavVՑ^ vJDЯ#Ծ5lzh[fNNX/edT {L.#Ln(*_~Tz Zmo,7HH݇;+#mwfPWywێ:M{l{hIb$a ƝWqU 4áu2/h/:l?p1HWrw'O/1ma@Pɜ]07XX%x’72;/^[3U4D"dRtI#U#x7 v r{ IG??ޝΪ!BŰ"PnpRKZ#M{aiƎG"# _?K14Xԥ2ރˠŭ2+D%@{= 'nv xYcWCLw[Y-L1FƯd}"joqrNJޕhO+9"B.Ó+]Xt刔gdjg"/89yL!x@ ?17J{yBf}G"Lz/3((dRs/L:Xr?j"z]mfp^R bhVnX,>8 ;D. xL*MO&fpIti7d71D_dJ0 *zGjrrj`5^c95!ԋ X=!duI~vO}zk,-vIiȬl#]Y );F HKOT"\TyР3?/׽9q %nl CK+VQ-{}ދw9f+s+brU,z2}틲9l7ϴihIC_* JG=zY6f=Ly#bs~La>PdaCg>l̜,w PM߻xi#{ ujN9voƒ Ï5wKP;jwH[Մ&Ƈa_bL\8b"Evlexq:HxDh3s_  sRym U}3 P@Q({Ηfeτ1A'~ 7ۦy2~~ &Oj7AȎ|*Rt'D_b v'@@VoseGԷpJ,{Y5~€{"|£[C]uۯpi c1kb pF" zW*9}{}@k7r)tm0x|nuj< Hf~ZwX]3;ayl$jdZ P̗u蝰HxXɚK߱ ݆A;Ј>J()yXZ[1ѶLR2P_%kw{\/zȧ}h?]RG׀ب=6S2FI+2"67ߋ(OYlɮU@̮H ,jiODvq7|GQ1$AПGsDo %jh+TQ:w=_|64fЙ3_|0>M)L&!N\1JM#͈^b9B fe=6p7ﳼ$;O#/r}zc9bk/paɻh&/C"5A^٠QP_Ъ Cʍ!-M(jHϡj۹k7hQh`Z3.-cKp78vTj &澦3[Gf ]=/E'0~~k.n3բ^N(D1^&\C)U89=G|A(\; G՛a^4މEʢab:ZZ\/gJ~H։%SY9e}Ӎ/Q#v:+sp|&\Wʯ6gy7Ad"mSX; *٤~EMt`^qNկ/n=pԋdS~2S+1Jz#yP![ή\F t*2gMZ2e!wbs0\l`|Wؐk7@mɉ7a)a$R_W\xo}UY ^60ɫ="A%أ%#,?^,)m'h5ٟSB|>gڝ=;%\ BDFH,it5Uyԛd*uDw1 Y=!g&?tv<㘾<'0ELa/Ӣ&~6u.慡¿BN* ^fKh2oZSZ_= ]>Wl\K+7()0}%{M#~}F_f-kS[W顶lmsMF?Tj81_̪35j.{AL* vnaS߉Zrp9:~>Eu w['GMfa U^!l զ~ |1[>Byb,#w\|9_)P\5p2y}n8o;}C^}TқQݹeáC09iEm+&Opo-O}.˜8l+_I4$`ۯGuCY1 un !b¥d-& s?1", EL&4J5a&OkvѢZ*rFrz MZ ѳ3n_Auhvn>CvgVtuI(dSF=&d'7;֬Tb~ELqL@Ÿ>J֟ %)yS94%cLS6Hהƭ팉0%K!go/^ȳ>&q[U8ME }]~Zo,`YF2Lw\C5\ !-}BZَYNZ]Ǡd='igiWR,aޞXH6(fo;Nj@IgN;gc|4ڜ^ݔ`okAtzPsZQ1uay *Tݱ#hPݢ#BK' =1ޙ8`\VbN,2wY;22p".M[D5oUf!n(ZؖrYq rIJRr'i OƿQnUvt*{)[pd54|vQcwpb{pr*YQ䁉8(uTATjϽҹ\CnˮMv/) $t $2"U?kcu|A Kd{:G3Q^S7@SxdAowOP8zYSqy7)[bLַY!M(Qh}xP N 2S߈!Mۻ}T;zg=mH{kФ G== MC\8,rn;c:j(S,>|!aՁ6JIwD}sS/"!0lWh\=kDGˣ G:q3E i+TDR:Bv|&aC({+&i._MRz'IF'W$6a‹jt]и}pU'=( 1~X%]]U ?}>',"X nXk'\$Z\C]|bV{EnNPaye+Kal"I1qfUS# ]i jZ@ {p +WP]SŝV "0vu)}0f|Ԯ& Mw[:(#ɶRBVjdըD=].-FabBFcJ|#MՊL3%U>zb燵s*'bgz%$T{`A3bSe/Hοu9/~hW$V~v7d u˩0cBR#(J_naz Of2mjn,~h1o  p'1jrI~@:x wD uO`i Ԑ؟n5AD*t JM5_U7T;N sW.U\UXھ8U~3FY8o*@9bVrY#Q%GfkHPsCuH#1~'հa}p{~H'N);MTw^;!(\xtr}zvG:RGERhEoG\Y-& m|uvEJ(+JUX cxPC,0] ![53е(|nf5z >T̟8?k";B.~p,-nC,@5o&}yU®9&K_X?!E=ܮ*gm _)s!U^.g }e,&Rנ | ]rg@Xh_ ,nҏ{|4lS}_$ok@g{c)E*/ lrkBlrq؃M0|[[4.Q&d5`y8Ƌ?aTg}v(ï#Ih%G^_Fri*tE_JI"M<#l!%`ֆ8z( u*(z=ùD'LeN-t/3Hk+aR(Ɂצ ;\5*Hv ™F-J&Q,н60Bd<,(Ns`&i!G Xwߋ4F8r+K7Tޚ\G8F׵ɹփ42oSq-8 b:lc1Wmxsh UWCs֜Ψ^G#^vi%LӜǫaXY)9k20!1"ҐwǪ /-53QH X:ӟ.'1}'Q-CdVWQt7{< nyBk?ϙuԿͱ1#-;~骠V0Df6#҈ o[V) p[XKi(>9?EƺJ C{́9ZR!3 ə5?k\=)̜sYQH98)AW&Jl4D{ꎉ*^b^Y, J|^/#_,U%̂3 aWta2GYl"[fipDyFXK=}&jxU,zH&&qz'_r`1!f  }3e+G %ϳ d3ܞd~ھ?{="\/0K5R i1\T@a L#|XuXX ->morꅟѺ^t3bwr,Tk 1zaXc\?O*ѽ((chGZD? H{;ԅ|K2W:n]6W] ]_uɏ{-.i6.' B]//A_.]4qRlx(ۑX"op3>Z1r>**Km/^5W!wn.Mn kˠ6qs b32~CjuHWwWǥjxL ?[Evz{Ҡx*̹"5;hx0p_fJR"/F0g9?Y6}mTȿxQKI0, JϞDcw}Rr>At ;.!ǶCkftc |ԥ'H1TW<{`H! yObF;l 19ɍɴKFgN2Z;0S箹)SB^5)aYQKrg })"Cu󷍭 pHV1pisHI6&P> stream xڍPX A\ AB@pn]{p@Nv]W[Tg"S`3w0J;\ؘYJlVVfVVv$**MkW;HTZ@gk@WLlȻ8ll<vVV:8$MܭJyJft6>>ƿb@gk3@ hhfbp0z'#?  0# t:K() ieB ̀  gh)T6`3ۿ d T]=]& ߆&v.`wk;S_MbjpblbmFamK8A.HIZ;}bpmA ! k2Yހ܀r؀EH/2K+t=ͬX~'rd- n@??EHllsk3W),Zl gϿ fz1Y%)_' bpqE/r d]a&7xnڗ17`b5b<Q_2vKO ܺw@ k {qnW+j1ݿvZY53;kP`bce?:rقoHw@f濗`l $v..x́ 1 vX88#>Rn.o߈"x,/",R"V 6 bȾ  ȿ 0\^ sQ񂹨 0\4^ sy\^ syA`.">KL\_`G&jlbf ?EXq+{U3c? 'oKb/e`gg%(ܿNn=7 xLnK;=XblmIiXy9ZAXe@0W? @p{^8s`{^fQT :_UL ~=0Kf`G pǜ^  O066p!C/5rSؙXabX\=P=$<^ ;n p$oߩs9{׋z͐mjn=v9Q#.w^W ő 5yꐽVh75w twݡBg[%&A :MaX*eL%Q"p~7I N'ڠ@ZSQO獇n*Mǵ;e"GҶ 2IM*u͑:Mzs ڔ:6Nj"-˕]79l>@7?rZDhŘzwM~& @M $:eyzOXٌ)yUNɗwH$ۣ&/8a*,[9_w&čtdZP+r};nOnѓK"Dc˲ʲ$HFә9PsaXFj*1p^=;A=(f]}-إװv )S[X&a:wmՔ-|ueױӊW[bfgVaSg!}<̆׼ExZp4Err<%Pbc11T#Mq:g>pպ }w /ZX>T.shtwHN6qZ3JoIlGd6z$&ޞM`'qʛvh#M=m]"+Sً0:*PZZߍgZdܐMٝJ\;zYh{tથo8s>z޾\ۭl%[WEJQy?юOHx?)0L/}PI (QfI4oc7܌}xWrl(9z~{o3јj&ۦ7X¹R Z6b+eڷvNl^W<zj2"8ԀxRd7 7KWZxJ- I"͠(?)-fUY㠺&d 4ޚ\:QI:rE.av8!i:\EFN7adYWB!$m8&# ^m \XTaM.#C00BT[f-yi¯DlAo3"mE+3TK!21, 5eu$,qgE 84=%}Kk.:A(^?*Rߺ(rBYK-N3LU,f2_1 d=&od"-fymB׆ ~V(f U2'آ$6S̫g`jhTv'%.4V(M: jks8[T;$5+n)~}A'y=-?%[_ VVCt}Aj_$2I0,!s,.5td=A9c;V_l7nѓ9+Ni.T."?]óx$VUVV~G.}\,etL"}(|^~G01dlorO&䜿Jnٸ~B?A"\)ښv3ԑ| ʢѱJķPK޻'7@pdp"ZR }:x|.=CvжwH )vy KD1̅GH|XD4K%ם89ڑSru؂$ߔd+w+5";;e(#vL7ZdNDAА2{uMl,I4hL'nVn}FnF~Cː5Nu}5|5e0T[oh7W'9ø'"̘dHUӛѫK<201hzƒ ·:SeL{A 7eF\~n^p:8y'r8Vnj9mE h"oh%2f'ŋ?y}\j{~'T1dŊuE\˻`KBPG['xqU{L(O)a|$Rޛ6f1\=3O׍S8.I˚Kj5'f7ȩE.;k5+.H(,?wC9eD ?mJY#SwdW1Zjb[΍цXAsV@|6iJm1/x齾pM#YHʸUۣ,鉸'=/#7MO$EuiN  uӧD>@[;S"g#zXfaB2L@m\a[\86q ZӼpѳPДzB)=[r(]oл.UNh; oT%i[=h}k5um^gJ*T Iʕ%\}Џhu続SgY1v&9Fݥ%UxARs#MķVjg۫q~(ج޲fch ΐޟFyH r {7\Pk|(C"I}+VeŅ#"tXĭaE0V_H$EX^"A6>uJ[iH}10yL S4x͗{g!YefR_Ί?c헿N2;zF:.+,QQ&%帾OqE,{Ry(C#ʈXeXMa0=2P~Ȣ8݅m)D |퉩aGIDViMʱ:T.MKVt<Q%K{eSBbfޡ~ rݥB+IKZ>B}bUc[Q ؇/<4FNz\NIB*'Z_W={Y3iRCw1n<,l06, /ACM/4`F<[?Yew"T:(<"oe$9!*+9ZJn>͓AD'ls3 mIS=*/jCYQG"?P6iK:oby2q.5wL)f~5~#!Ԯ6$7A;Qߔ]3ק7 Yܛ6X0:isHsjxjGxLV6 qMn_z nJChxyr. !imǩ$g@ԝRݟBGR.4THb=(;ͷC5Ѽz~e-Ue}8(YY}&k\7o2 -NTF 1Ӵ=)[ZX30 7IuM~BoslRd \feX|ZdAE͑ㆭeUDs7ٍńƹP%t֟QVU|+}OexTԶ$sL!Ku`)7?~d 848 坁QV[g2Q.K^f՛GzCsRtA7|KmBmi7#mTasehE3wTF2H Ͳ9Z.:я#xQ`GY[y7zҠ{V[l$INwE|dzձ(,+qH9Iл4;rQ }s잀1,dnպ7W^׸ڗX> .ygy z!b"Z"܎Gs}YIX(rt#9>1WY EJL ؀lV; Y%v̒\[ CI5a62 P}W" R,jAc i2Bz% '~j!wf vhdd *K;Ry]:,XTGRɋ`5tKG=Ɔiw/z3(ob+ta^ o:F fX.2Gg Pnx!=WIKvh*d kQi~RyRL KG9x1"/Y<aTBL`oLxT՝Q RGD=QC)4Oef2nĞسt۷O@OxMP.C;4D`hcyVt)~lZʅ4`oY_y{ƭuU[&ѺY;7m㳬u㎚q ,"E|l|j?hkal}ܦ YesAfPM~)Ns;aɛ5_uS=T,2IC_ܵ|zEG%J(knoiQ ]YIɮb .iOۑgM"#s𜷮mRY<1Ϟ>5y Yj4 C25~|WLFW- 1™>047NA)rKq{bH :$``5)Fq(GCā~YKP>nR< Ay67.<v rd@/}(K?sNq)~v׏N *qy km:!CUTH_TSh}Lw0z+E^l XiQ9PR~2u?my>qOyzL[)h)}2Q1U ^ki]4i/E)YFT?gWKW]djZMQW< -ΐ U.]OaեYmRUz-".Ʉ#mj]BUL /üsZh8Ԡ~ XN0:G ñE*& [6K-`>FuYU_YG)Eq_ W~ĭm&'uB0k(2c%Ǧ3W2uOwBꔆnYZʘ}܏rCSn4?y 0CoBٙ%>]YXFy d:n6d(\t>.LH>`QȨRp>ʹI:e7ޙbړ"~I֌7cD{hDTmE-r{C+ka VvkO?'k\IuݕxdKK[QCP%vP^yoVnmkh{0})![s 띭<dHx9q=%ؔ jӅ<wHn0@t)TVk[#n'g:v` px݈Z={Q)Ȉ%1gU;L":SdUFaukO#҈2Kg8$9DPDWTB>Ғbc#*4dRZҺݴL!A lA=ٗȩf3dV E6xM:>=}^ŴN5D MS`alITCp+;aqIAc1'8: ,&ZoKk?MA:=a醛\¥TbVն,SH#O}Flզz0 NMH\ /1oKmۏ]&Bq6$1A [l7T9C Ɣ]@+xSWkc$Beef^Hd1a<"l\7ed$cŲ^O\ރׯs};glyFu[h? qP?)WGp|(7^Yn]0c5uj|2&?z4ʜH9ڵҥfteyڃɜV0NWp۴07C«䴦r&ɱ{RDđ\QiE Q6JԞoha*ufVN\yZ~&C}5C)>^},>g 9#nWMPXPůeoЀ5!rF[nA?Tn$[=g4`SΡm% dRwb'm<;iF}'cm|#xYع9:2#:J스3L7ݫb)$,b/x,a92p?XsP?+l o?q !ocw%2Яq0͏?0NJ6Iw| 渊 ۼCI9l#O#*5uŅZ4Qz-zǟNoY_m9d5^o3(.ͳ駏҇b}R8"vH =z6F2hඃ,u&ܹ2,*,[KYCh3p4cl[UX9icЅ! !`_JG~y}V9qEVPxn -F!2UorRxެe#g>BO4%x| C6XeanJg'uv!0t:Bmߞ1<ea.l)Ъa8 !F;.KQ:#፸,c3E"Nt;h-O<4P %zpj&vb؄J:g u|iφA$e\RZa?`KeKefD5Fa=2b2:4'[%"=_GK:E~,FRsV?$@G@]Xݸ,`4u#1$ )thzW8Σ{Yix܎1w,6d"_beϧ n: ML/WEl .PzYH'tIox{QK Tv]TE8bN$wʍDˈm>MޓDu=1 M$Պ+ bh,I>4`lXwvAG%7)02EstnEcmNKOT?I(] g b3y s6FQ6:>%@o'ڌӓ]yҍVϮ&ꭚLCvx$g&>@T!UZ|_i:dߙ!"M&+I%7Fek*?Õ:ەz|p4@[KRCfh\vW\Źzb-Cq|ApGScED>2aDH98@>y6H3vރlf##3?ѩW#1UY`kۮm(iL, } 2g㦾g/=1O@j\S Cu|:2` `X&nR{/a_{5J! K7AA^ ƒ.u "+?H-훡Zd[} }%7=2T99&ݢ_Ul X@Ht{Ԕ> endobj 7 0 obj << /Type /ObjStm /N 81 /First 658 /Length 3139 /Filter /FlateDecode >> stream xnH]_яXD}_@08O;LflmdˑLf~yӴMY,fu]]MS &YtLĔ LjbR1a1 ٨ ͔bAȑr,xϔe[tg8WǴN1 H& ށu#Df?`J(왒"_ʢR2 u<ǔJ9mT^둳L%3LE%AD)#( I]HAT!=V@T3ʨK( 46&>2kb0gD9+#HF4~p %fX[`S!tt!10hi./"`=^K0\L tf}*D*+ wZʀ=Q֢UѱƑ a\-,Xfux"X (+QmID;GџW'gو/Wj4-׋l qKd{}0`+S0r,`:ȿB&{=p'M 0 |z1?9VHQcŎ R7*e[ָ Y7(SI;ڟ$!߃,&Cc1p}<@!1R?MJu_mR-/0Wԓ,Hw_A(h]qCG\ q{|̦'[gUvs'Ai 4' |9) ~|;$hSsr;ow~Oʩ4*"q3ʉث6Os҄οL l1_e +:_d_1`?ża/7^~z/ʃApmz1,U`Z v&lgrP+ QOMj.O's}X߳7zv-WS zN?DVN=!*a%E57/>zN8O a3rt:7JKj}Yp=d6@ߔ2oVϫspD'E? @PbjvJVԫ;b_fww}uZavqu{ѹpfZn+~uЦKԵGUAB9 MG/v(b3j)|*{޽|\QQF I||e{7o}[ x<k[iXo7Wϐ@S| j/˦O@ãTIocv[K {}V荝kY߽ܒSN믊=~|fǣJ l뺚lRd/yCsՏ7u ~t 0,Uwm:oy_0Ta]PY1)PS`E)QrYtWl`+ p{ӈ9x*>؛.+;񗓢`·|_>w`.KA g>ն6s'j̝yMQޗwXan֦as]nZ&{xF݉5qJ[,[;fb5v ᜛k3h侬pbͼj՘[1wkݪ;&5RK k3w,*Fri%mVK*kzBhqӺ{-PׂK\+?YHezd~?Y[O:uɉ5 4h]muD%M\tхbJt'ĝ [QP8; endstream endobj 115 0 obj << /Type /XRef /Index [0 116] /Size 116 /W [1 3 1] /Root 113 0 R /Info 114 0 R /ID [<1783C648102E4DD9278365AEAA5A2562> <1783C648102E4DD9278365AEAA5A2562>] /Length 311 /Filter /FlateDecode >> stream x%;/azJZRgǢ֙.ba,؍6DD}Ml>df m~TKb^!<+ ωM($)bU(EDԞ?,2"-D(%ɦr"2kQ!DWUٷDf!6DH HmẢ&HڇLlqfD)KtO1HWC0|n5B|Zތ'&ȗ8 $sVt^]j)a5+E. zx?-. endstream endobj startxref 197036 %%EOF LanguageMachines-ucto-688c2af/docs/ucto_manual.rst000066400000000000000000000531401472777655400223240ustar00rootroot00000000000000:Author: Maarten van Gompel :Author: Ko van der Sloot :Author: Antal van den Bosch Centre for Language Studies Radboud University Nijmegen URL: https://languagemachines.github.io/ucto/ .. role:: math(raw) :format: html latex .. .. role:: raw-latex(raw) :format: latex .. Introduction ============ Tokenisation is a process in which text is segmented into the various sentence and word tokens that constitute the text. Most notably, words are separated from any punctuation attached and sentence boundaries are detected. Tokenisation is a common and necessary pre-processing step for almost any Natural Language Processing task, and preceeds further processing such as Part-of-Speech tagging, lemmatisation or syntactic parsing. Whilst tokenisation may at first seem a trivial problem, it does pose various challenges. For instance, the detection of sentence boundaries is complicated by the usage of periods abbreviations and the usage of capital letters in proper names. Furthermore, tokens may be contracted in constructions such as “I’m”, “you’re”, “father’s”. A tokeniser will generally split those. Ucto is an advanced rule-based tokeniser. The tokenisation rules used by ucto are implemented as regular expressions and read from external configuration files, making ucto flexible and extensible. Configuration files can be further customised for specific needs and for languages not yet supported. Tokenisation rules have first been developed for Dutch, but configurations for English, German, French, Italian, and Swedish are also provided. Ucto features full unicode support. Ucto is not just a standalone program, but is also a C++ library that you can use in your own software. This reference guide is structured as follows. In Chapter [license] you can find the terms of the license according to which you are allowed to use, copy, and modify Ucto. The subsequent chapter gives instructions on how to install the software on your computer. Next, Chapter [implementation] descibres the underlying implementation of the software. Chapter [usage] explains the usage. GNU General Public License ========================== Ucto is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 3 of the License, or (at your option) any later version. Ucto is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with Ucto. If not, see :math:`<`\ http://www.gnu.org/licenses/\ :math:`>`. In publication of research that makes use of the Software, a citation should be given of: *“Maarten van Gompel, Ko van der Sloot, Antal van den Bosch (2012). Ucto: Unicode Tokeniser. Reference Guide. ILK Technical Report 12-05, Available from http://ilk.uvt.nl/downloads/pub/papers/ilk.1205.pdf”* For information about commercial licenses for the Software, contact lamasoftware@science.ru.nl, or send your request to: Prof. dr. Antal van den Bosch Radboud University Nijmegen P.O. Box 9103 – 6500 HD Nijmegen The Netherlands Email: a.vandenbosch@let.ru.nl Installation ============ The ucto source can be obtained from: https://github.com/LanguageMachines/ucto These sources need to be compiled for the software to run. However, on most recent Debian and Ubuntu systems, Ucto can be found in the respective software repositories and can be installed with a simple: $ apt-get install ucto On Arch Linux, ucto is available from the Arch User Repository. If you have a package for your distribution, you can skip the remainder of this section. To facilitate installation in other situations, we recommend to use our LaMachine software distribution, which includes ucto and all dependencies: http://proycon.github.io/LaMachine/ If you however install from the source archive, the compilation and installation should also be relatively straightforward on most UNIX systems, and will be explained in the remainder of this section. | Ucto depends on the ``libicu`` library. This library can be obtained from | http://site.icu-project.org/ but is also present in the package manager of all major Linux distributions. Ucto also depends on ``uctodata``, ``libfolia`` (available from ``http://proycon.github.com/folia``), which in turn depends on ``libticcutils`` (available from | ``http://github.com/LanguageMachines/ticcutils``). It will not compile without any of them. If all dependencies are satisfied, to compile ucto on your computer, run the following from the ucto source directory: $ bash bootstrap.sh $ ./configure Note: It is possible to install Ucto in a different location than the global default using the ``–prefix=

`` option, but this tends to make further operations (such as compiling higher-level packages like Frog [1]_) more complicated. Use the –with-ucto= option in configure. After configure you can compile Ucto: $ make and install: $ make install If the process was completed successfully, you should now have executable file named ucto in the installation directory (/usr/local/bin by default, we will assume this in the reminder of this section), and a dynamic library libucto.so in the library directory (/usr/local/lib/). The configuration files for the tokeniser can be found in /usr/local/etc/ucto/. Ucto should now be ready for use. Reopen your terminal and issue the ucto command to verify this. If not found, you may need to add the installation directory (/usr/local/bin to your $PATH. That’s all! The e-mail address for problems with the installation, bug reports, comments and questions is lamasoftware@science.ru.nl. Implementation ============== Ucto is a regular-expression-based tokeniser. Regular expressions are read from an external configuration file and processed in an order explicitly specified in this same configuration file. Each regular expression has a named label. These labels are propagated to the tokeniser output as tokens processed by a certain regular expression are assigned its identifier. The tokeniser will first split on the spaces already present in the input, resulting in various *fragments*. Each fragment is then matched against the ordered set of regular expressions, until a match is found. If a match is found, the matching part is a token and is assigned the label of the matching regular expression. The matching part may be a only a substring of the fragment, in which case there are one or two remaining parts on the left and/or right side of the match. These will be treated as any other fragments and all regular expressions are again tested in the specified order, from the start, and in exactly the same way. This process continues until all fragments are processed. If a regular expression contains subgroups (marked by parentheses), then not the whole match, but rather the subgroups themselves will become *separate* tokens. Parts within the whole match but not in subgroups are discarded, whilst parts completely outside the match are treated as usual. Ucto performs sentence segmentation by looking at a specified list of end-of-sentence markers. Whenever an end-of-sentence marker is found, a sentence ends. However, special treatment is given to the period (“.”), because of its common use in abbreviations. Ucto will attempt to use capitalisation (for scripts that distinguish case) and sentence length cues to determine whether a period is an actual end of sentence marker or not. Simple paragraph detection is available in Ucto: a double newline triggers a paragraph break. Quote detection is also available, but still experimental and by default disabled as it quickly fails on input that is not well prepared.If your input can be trusted on quotes being paired, you can try to enable it. Note that quotes spanning over paragraphs are not supported. Configuration ------------- The regular expressions on which ucto relies are read from external configuration files. A configuration file is passed to ucto using the ``-c`` or ``-L`` flags. Configuration files are included for several languages, but it has to be noted that at this time only the Dutch one has been stress-tested to sufficient extent. The configuration file consists of the following sections: - ``RULE-ORDER`` – Specifies which rules are included and in what order they are tried. This section takes a space separated list (on one line) of rule identifiers as defined in the ``RULES`` section. Rules not included here but only in ``RULES`` will be automatically added to the far end of the chain, which often renders them ineffective. - | ``RULES`` – Contains the actual rules in format ``ID=regexp``, where ``ID`` is a label identifying the rule, and ``regexp`` is a regular expression in libicu syntax. This syntax is thoroughly described on | ``http://userguide.icu-project.org/strings/regexp`` . The order is specified seperately in ``RULE-ORDER``, so the order of definition here does not matter. - ``ABBREVIATIONS`` – Contains a list of known abbreviations, one per line. These may occur with a trailing period in the text, the trailing period is not specified in the configuration. This list will be processed prior to any of the explicit rules. Libicu regular expression syntax is used again. Tokens that match abbreviations from this section get assigned the label ``ABBREVIATION-KNOWN``. - ``SUFFIXES`` – Contains a list of known suffixes, one per line, that the tokeniser should consider separate tokens. This list will be processed prior to any of the explicit rules. Libicu regular expression syntax is used again. Tokens that match any suffixes in this section receive the label ``SUFFIX``. - ``PREFIXES`` – Contains a list of known prefixes, one per line, that the tokeniser should consider separate tokens. This list will be processed prior to any of the explicit rules. Libicu regular expression syntax is used again. Tokens that match any suffixes in this section receive the label ``PREFIX``. - ``TOKENS`` – Treat any of the tokens, one per line, in this list as integral units and do not split it. This list will be processed prior to any of the explicit rules. Once more, libicu regular expression syntax is used. Tokens that match any suffixes in this section receive the label ``WORD-TOKEN``. - ``ATTACHEDSUFFIXES`` – This section contains suffixes, one per line, that should *not* be split. Words containing such suffixes will be marked ``WORD-WITHSUFFIX``. - ``ATTACHEDPREFIXES`` – This section contains prefixes, one per line, that should *not* be split. Words containing such prefixes will be marked ``WORD-WITHPREFIX``. - ``ORDINALS`` – Contains suffixes, one per line, used for ordinal numbers. Number followed by such a suffix will be marked as ``NUMBER-ORDINAL``. - ``UNITS`` – This category is reserved for units of measurements, one per line, but is currently disabled due to problems. - ``CURRENCY`` – This category is reserved for currency symbols, one per line, but is currently disabled due to problems. - ``EOSMARKERS`` – Contains a list of end-of-sentence markers, one per line and in ``\uXXXX`` format, where ``XXXX`` is a hexadecimal number indicating a unicode code-point. The period is generally not included in this list as ucto treats it specially considering its role in abbreviations. - ``QUOTES`` – Contains a list of quote-pairs in the format ``beginquotes \s endquotes \n``. Multiple begin quotes and endquotes are assumed to be ambiguous. - ``FILTER`` – Contains a list of transformations. In the format ``pattern \s replacement \n``. Each occurrence of ``pattern`` will be replaced. This is useful for deconstructing ligatures for example. Lines starting with a hash sign are treated as comments. Lines starting with ``%include `` will include the contents of another file. This may be useful if for example multiple configurations share many of the same rules, as is often the case. This directive is for the moment only supported within ``RULES``, ``FILTER``, ``QUOTES`` and ``EOSMARKERS``. You can see several sections specifying lists. These are implicit regular expressions as all are converted to regular expressions. They are checked prior to any of the explicit rules, in the following order of precedence: ``SUFFIXES, PREFIXES, ATTACHEDSUFFIXES, ATTACHEDPREFIXES, TOKENS, ABBREVIATIONS, ORDINALS``. When creating your own configuration, it is recommended to start by copying an existing configuration and use it as example. For debugging purposes, run ucto in a debug mode using ``-d``. The higher the level, the more debug output is produced, showing the exact pattern matching. Usage ===== Ucto is a command-line tool. The following options are available: :: Usage: ucto [[options]] [input-file] [[output-file]] Options: -c - Explicitly specify a configuration file -d - set debug level -e - set input encoding (default UTF8) -N - set output normalization (default NFC) -f - Disable filtering of special characters -L - Automatically selects a configuration file by language code -l - Convert to all lowercase -u - Convert to all uppercase -n - One sentence per line (output) -m - One sentence per line (input) -v - Verbose mode -s - End-of-Sentence marker (default: ) --passthru - Don't tokenize, but perform input decoding and simple token role detection -P - Disable paragraph detection -S - Disable sentence detection! -Q - Enable quote detection (experimental) -V - Show version information -F - Input file is in FoLiA XML. All untokenised sentences will be tokenised. -X - Output FoLiA XML, use the Document ID specified with --id= --id - use the specified Document ID to label the FoLia doc. (-x and -F disable usage of most other options: -nulPQVsS) Ucto has two input formats and three output formats. It can take either an untokenised plain text UTF-8 as input, or a FoLiA XML document with untokenised sentences. If the latter is the case, the ``-F`` flag should be added. Output by default is to standard error output in a simplistic format which will simply show all of the tokens and places a ```` symbol where sentence boundaries are detected. Consider the following untokenised input text: *Mr. John Doe goes to the pet store. He sees a cute rabbit, falls in love, and buys it. They lived happily ever after.*, and observe the output in the example below. We save the file to ``/tmp/input.txt`` and we run ucto on it. The ``-L eng`` option sets the language to English and loads the English configuration for ucto. Instead of ``-L``, which is nothing more than a convenient shortcut, we could also use ``-c`` and point to the full path of the configuration file. :: $ ucto -L eng /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser... Mr. John Doe goes to the pet store . He sees a cute rabbit , falls in love , and buys it . They lived happily ever after . Alternatively, you can use the ``-n`` option to output each sentence on a separate line, instead of using the ```` symbol: :: $ ucto -L eng -n /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser... Mr. John Doe goes to the pet store . He sees a cute rabbit , falls in love , and buys it . They lived happily ever after . To output to an output file instead of standard output, we would invoke ucto as follows: :: $ ucto -L eng /tmp/input.txt /tmp/output.txt This simplest form of output does not show all of the information ucto has on the tokens. For a more verbose view, add the ``-v`` option: :: $ ucto -L eng -v /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser... Mr. ABBREVIATION-KNOWN BEGINOFSENTENCE NEWPARAGRAPH John WORD Doe WORD goes WORD to WORD the WORD pet WORD store WORD NOSPACE . PUNCTUATION ENDOFSENTENCE He WORD BEGINOFSENTENCE sees WORD a WORD cute WORD rabbit WORD NOSPACE , PUNCTUATION falls WORD in WORD love WORD NOSPACE , PUNCTUATION and WORD buys WORD it WORD NOSPACE . PUNCTUATION ENDOFSENTENCE They WORD BEGINOFSENTENCE lived WORD happily WORD ever WORD after WORD NOSPACE . PUNCTUATION ENDOFSENTENCE As you see, this outputs the token types (the matching regular expressions) and roles such as ``BEGINOFSENTENCE``, ``ENDOFSENTENCE``, ``NEWPARAGRAPH``, ``BEGINQUOTE``, ``ENDQUOTE``, ``NOSPACE``. For further processing of your file in a natural language processing pipeline, or when releasing a corpus. It is recommended to make use of the FoLiA XML format :raw-latex:`\cite{FOLIA}` [2]_. FoLiA is a format for linguistic annotation supporting a wide variety of annotation types. FoLiA XML output is enabled by specifying the ``-X`` flag. An ID for the FoLiA document can be specified using the ``–id=`` flag. :: $ ucto -L eng -v -X --id=example /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser...

Mr. John Doe goes to the pet store . He sees a cute rabbit , falls in love , and buys it . They lived happily ever after .

Ucto can also take FoLiA XML documents with untokenised sentences as input, using the ``-F`` option. .. [1] http://ilk.uvt.nl/frog .. [2] See also: http://proycon.github.com/folia LanguageMachines-ucto-688c2af/docs/ucto_manual.tex000066400000000000000000000565501472777655400223240ustar00rootroot00000000000000\documentclass[a4paper,12pt]{report} \usepackage[english]{babel} %\usepackage{palatino} \usepackage{url} \usepackage{listings} \usepackage{xcolor} \lstset{ language=xml, % choose the language of the code basicstyle=\footnotesize\color{black}, keywordstyle=\color{black}\bfseries, % style for keywords commentstyle=\color{blue}, stringstyle=\color{magenta}, numbers=none, % where to put the line-numbers numberstyle=\tiny, % the size of the fonts that are used for the line-numbers backgroundcolor=\color{white}, showspaces=false, % show spaces adding particular underscores showstringspaces=false, % underline spaces within strings showtabs=false, % show tabs within strings adding particular underscores frame=single, % adds a frame around the code tabsize=2, % sets default tabsize to 2 spaces rulesepcolor=\color{gray}, rulecolor=\color{black}, captionpos=b, % sets the caption-position to bottom breaklines=true, % sets automatic line breaking breakatwhitespace=false, } \author{Maarten van Gompel \and Ko van der Sloot \and Antal van den Bosch \\ Centre for Language Studies \\ Radboud University Nijmegen \\ \\ URL: https://languagemachines.github.io/ucto/} \title{{\huge Ucto: Unicode Tokeniser} \\ \vspace*{0.5cm} {\bf version 0.9.6} \\ \vspace*{0.5cm}{\huge Reference Guide}\\ \vspace*{1cm}} %{\it LST Technical Report -- ILK 12-05}} %better paragraph indentation \parindent 0pt \parskip 9pt \begin{document} \pagenumbering{roman} \maketitle \tableofcontents \chapter*{Introduction} Tokenisation is a process in which text is segmented into the various sentence and word tokens that constitute the text. Most notably, words are separated from any punctuation attached and sentence boundaries are detected. Tokenisation is a common and necessary pre-processing step for almost any Natural Language Processing task, and preceeds further processing such as Part-of-Speech tagging, lemmatisation or syntactic parsing. Whilst tokenisation may at first seem a trivial problem, it does pose various challenges. For instance, the detection of sentence boundaries is complicated by the usage of periods abbreviations and the usage of capital letters in proper names. Furthermore, tokens may be contracted in constructions such as ``I'm'', ``you're'', ``father's''. A tokeniser will generally split those. Ucto is an advanced rule-based tokeniser. The tokenisation rules used by Ucto are implemented as regular expressions and read from external configuration files, making Ucto flexible and extensible. Configuration files can be further customised for specific needs and for languages not yet supported. Tokenisation rules have first been developed for Dutch, but configurations for several other language (for example English, German, French, Italian, and Swedish) are also provided, a full list of supported languages can be found in \ref{langlist}. Ucto features full unicode support. Ucto is not just a standalone program, but is also a C++ library that you can use in your own software. This reference guide is structured as follows. In Chapter~\ref{license} you can find the terms of the license according to which you are allowed to use, copy, and modify Ucto. The subsequent chapter gives instructions on how to install the software on your computer. Next, Chapter~\ref{implementation} describes the underlying implementation of the software. Chapter~\ref{usage} explains the usage. \chapter{GNU General Public License} \label{license} \pagenumbering{arabic} Ucto is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 3 of the License, or (at your option) any later version. Ucto is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with Ucto. If not, see $<$http://www.gnu.org/licenses/$>$. In publication of research that makes use of the Software, a citation should be given of: {\em ``Maarten van Gompel, Ko van der Sloot, Antal van den Bosch (2012). Ucto: Unicode Tokeniser. Reference Guide. ILK Technical Report 12-05, \\ Available from {\tt http://ilk.uvt.nl/downloads/pub/papers/ilk.1205.pdf}''} For information about commercial licenses for the Software, contact {\tt lamasoftware@science.ru.nl}, or send your request to: {\footnotesize Prof. dr.~Antal van den Bosch\\ Radboud University Nijmegen \\ P.O. Box 9103 -- 6500 HD Nijmegen \\ The Netherlands \\ Email: a.vandenbosch@let.ru.nl} \pagestyle{headings} \chapter{Installation} \vspace{-1cm} The ucto source can be obtained from: {\tt https://github.com/LanguageMachines/ucto} These sources need to be compiled for the software to run. However, on most recent Debian and Ubuntu systems, Ucto can be found in the respective software repositories and can be installed with a simple: {\tt \$ apt-get install ucto} On Arch Linux, ucto is available from the Arch User Repository. If you have a package for your distribution, you can skip the remainder of this section. To facilitate installation in other situations, we recommend to use our LaMachine software distribution, which includes ucto and all dependencies: {\tt http://proycon.github.io/LaMachine/} If you however install from the source archive, the compilation and installation should also be relatively straightforward on most UNIX systems, and will be explained in the remainder of this section. Ucto depends on the \texttt{libicu} library. This library can be obtained from \\ {\tt http://site.icu-project.org/} but is also present in the package manager of all major Linux distributions. Ucto also depends on \texttt{uctodata}, \texttt{libfolia} (available from \texttt{http://proycon.github.com/folia}), which in turn depends on \texttt{libticcutils} (available from \\ \texttt{http://github.com/LanguageMachines/ticcutils}). It will not compile without any of them. If all dependencies are satisfied, to compile ucto on your computer, run the following from the ucto source directory: {\tt \$ bash bootstrap.sh} {\tt \$ ./configure} Note: It is possible to install Ucto in a different location than the global default using the \texttt{--prefix=} option, but this tends to make further operations (such as compiling higher-level packages like Frog\footnote{\url{http://ilk.uvt.nl/frog}}) more complicated. Use the {\tt --with-ucto=} option in configure. After {\tt configure} you can compile Ucto: {\tt \$ make} and install: {\tt \$ make install } If the process was completed successfully, you should now have executable file named {\tt ucto} in the installation directory ({\tt /usr/local/bin} by default, we will assume this in the reminder of this section), and a dynamic library {\tt libucto.so} in the library directory ({\tt /usr/local/lib/}). The configuration files for the tokeniser can be found in {\tt /usr/local/etc/ucto/}. Ucto should now be ready for use. Reopen your terminal and issue the {\tt ucto} command to verify this. If not found, you may need to add the installation directory ({\tt /usr/local/bin} to your \$PATH. That's all! The e-mail address for problems with the installation, bug reports, comments and questions is {\tt lamasoftware@science.ru.nl}. %\chapter{Changes} %\label{changes} %\section{From version 3.1 to 3.2} %\begin{itemize} %\item Mbt is based on both Timbl and TimblServer. MBT used to depend % only on Timbl, but Timbl's server functionality was moved to a % separate package, TimblServer, that acts as a wrapper around % Timbl. Thus, TimblServer depends on Timbl. In the future, it is % likely that also a separate MbtServer package will be released. Mbt % itself will then based on Timbl, once again. %\item Some small bugs have been fixed. %\end{itemize} \chapter{Implementation} \label{implementation} Ucto is a regular-expression-based tokeniser. Regular expressions are read from an external configuration file and processed in an order explicitly specified in this same configuration file. Each regular expression has a named label. These labels are propagated to the tokeniser output as tokens processed by a certain regular expression are assigned its identifier. The tokeniser will first split on the spaces already present in the input, resulting in various \emph{fragments}. Each fragment is then matched against the ordered set of regular expressions, until a match is found. If a match is found, the matching part is a token and is assigned the label of the matching regular expression. The matching part may be a only a substring of the fragment, in which case there are one or two remaining parts on the left and/or right side of the match. These will be treated as any other fragments and all regular expressions are again tested in the specified order, from the start, and in exactly the same way. This process continues until all fragments are processed. If a regular expression contains subgroups (marked by parentheses), then not the whole match, but rather the subgroups themselves will become \emph{separate} tokens. Parts within the whole match but not in subgroups are discarded, whilst parts completely outside the match are treated as usual. Ucto performs sentence segmentation by looking at a specified list of end-of-sentence markers. Whenever an end-of-sentence marker is found, a sentence ends. However, special treatment is given to the period (``.''), because of its common use in abbreviations. Ucto will attempt to use capitalisation (for scripts that distinguish case) and sentence length cues to determine whether a period is an actual end of sentence marker or not. Simple paragraph detection is available in Ucto: a double newline triggers a paragraph break. Quote detection is also available, but still experimental and by default disabled as it quickly fails on input that is not well prepared.If your input can be trusted on quotes being paired, you can try to enable it. Note that quotes spanning over paragraphs are not supported. \section{Configuration} The regular expressions on which ucto relies are read from external configuration files. A configuration file is passed to ucto using the \texttt{-c} or \texttt{-L} flags. Configuration files are included for several languages, but it has to be noted that at this time only the Dutch one has been stress-tested to sufficient extent. The configuration file consists of the following sections: \begin{itemize} \item \texttt{RULE-ORDER} -- Specifies which rules are included and in what order they are tried. This section takes a space separated list (on one line) of rule identifiers as defined in the \texttt{RULES} section. Rules not included here but only in \texttt{RULES} will be automatically added to the far end of the chain, which often renders them ineffective. \item \texttt{RULES} -- Contains the actual rules in format \texttt{ID=regexp}, where \texttt{ID} is a label identifying the rule, and \texttt{regexp} is a regular expression in libicu syntax. This syntax is thoroughly described on \\ \texttt{http://userguide.icu-project.org/strings/regexp} . The order is specified seperately in \texttt{RULE-ORDER}, so the order of definition here does not matter. \item \texttt{ABBREVIATIONS} -- Contains a list of known abbreviations, one per line. These may occur with a trailing period in the text, the trailing period is not specified in the configuration. This list will be processed prior to any of the explicit rules. Libicu regular expression syntax is used again. Tokens that match abbreviations from this section get assigned the label \texttt{ABBREVIATION-KNOWN}. \item \texttt{SUFFIXES} -- Contains a list of known suffixes, one per line, that the tokeniser should consider separate tokens. This list will be processed prior to any of the explicit rules. Libicu regular expression syntax is used again. Tokens that match any suffixes in this section receive the label \texttt{SUFFIX}. \item \texttt{PREFIXES} -- Contains a list of known prefixes, one per line, that the tokeniser should consider separate tokens. This list will be processed prior to any of the explicit rules. Libicu regular expression syntax is used again. Tokens that match any suffixes in this section receive the label \texttt{PREFIX}. \item \texttt{TOKENS} -- Treat any of the tokens, one per line, in this list as integral units and do not split it. This list will be processed prior to any of the explicit rules. Once more, libicu regular expression syntax is used. Tokens that match any suffixes in this section receive the label \texttt{WORD-TOKEN}. \item \texttt{ATTACHEDSUFFIXES} -- This section contains suffixes, one per line, that should \emph{not} be split. Words containing such suffixes will be marked \texttt{WORD-WITHSUFFIX}. \item \texttt{ATTACHEDPREFIXES} -- This section contains prefixes, one per line, that should \emph{not} be split. Words containing such prefixes will be marked \texttt{WORD-WITHPREFIX}. \item \texttt{ORDINALS} -- Contains suffixes, one per line, used for ordinal numbers. Number followed by such a suffix will be marked as \texttt{NUMBER-ORDINAL}. \item \texttt{UNITS} -- This category is reserved for units of measurements, one per line, but is currently disabled due to problems. \item \texttt{CURRENCY} -- This category is reserved for currency symbols, one per line, but is currently disabled due to problems. \item \texttt{EOSMARKERS} -- Contains a list of end-of-sentence markers, one per line and in \texttt{{\textbackslash}uXXXX} format, where \texttt{XXXX} is a hexadecimal number indicating a unicode code-point. The period is generally not included in this list as ucto treats it specially considering its role in abbreviations. \item \texttt{QUOTES} -- Contains a list of quote-pairs in the format \texttt{beginquotes {\textbackslash}s endquotes {\textbackslash}n}. Multiple begin quotes and endquotes are assumed to be ambiguous. \item \texttt{FILTER} -- Contains a list of transformations. In the format \texttt{pattern {\textbackslash}s replacement {\textbackslash}n}. Each occurrence of \texttt{pattern} will be replaced. This is useful for deconstructing ligatures for example. \end{itemize} Lines starting with a hash sign are treated as comments. Lines starting with \texttt{\%include } will include the contents of another file. This may be useful if for example multiple configurations share many of the same rules, as is often the case. This directive is for the moment only supported within \texttt{RULES}, \texttt{FILTER}, \texttt{QUOTES} and \texttt{EOSMARKERS}. You can see several sections specifying lists. These are implicit regular expressions as all are converted to regular expressions. They are checked prior to any of the explicit rules, in the following order of precedence: \texttt{SUFFIXES, PREFIXES, ATTACHEDSUFFIXES, ATTACHEDPREFIXES, TOKENS, ABBREVIATIONS, ORDINALS}. When creating your own configuration, it is recommended to start by copying an existing configuration and use it as example. For debugging purposes, run ucto in a debug mode using \texttt{-d}. The higher the level, the more debug output is produced, showing the exact pattern matching. \chapter{Usage} \label{usage} Ucto is a command-line tool. The following options are available: \begin{verbatim} Usage: ucto [[options]] [input-file] [[output-file]] Options: -c - Explicitly specify a configuration file -d - set debug level -e - set input encoding (default UTF8) -N - set output normalization (default NFC) -f - Disable filtering of special characters -L - Automatically selects a configuration file by language code -l - Convert to all lowercase -u - Convert to all uppercase -n - One sentence per line (output) -m - One sentence per line (input) -v - Verbose mode -s - End-of-Sentence marker (default: ) --passthru - Don't tokenize, but perform input decoding and simple token role detection -P - Disable paragraph detection -S - Disable sentence detection! -Q - Enable quote detection (experimental) -V - Show version information -F - Input file is in FoLiA XML. All untokenised sentences will be tokenised. -X - Output FoLiA XML, use the Document ID specified with --id= --id - use the specified Document ID to label the FoLia doc. (-x and -F disable usage of most other options: -nulPQVsS) \end{verbatim} Ucto has two input formats and three output formats. It can take either an untokenised plain text UTF-8 as input, or a FoLiA XML document with untokenised sentences. If the latter is the case, the \texttt{-F} flag should be added. Output by default is to standard error output in a simplistic format which will simply show all of the tokens and places a \texttt{} symbol where sentence boundaries are detected. Consider the following untokenised input text: \emph{Mr. John Doe goes to the pet store. He sees a cute rabbit, falls in love, and buys it. They lived happily ever after.}, and observe the output in the example below. We save the file to \texttt{/tmp/input.txt} and we run ucto on it. The \texttt{-L eng} option sets the language to English and loads the English configuration for ucto. Instead of \texttt{-L}, which is nothing more than a convenient shortcut, we could also use \texttt{-c} and point to the full path of the configuration file. \begin{verbatim} $ ucto -L eng /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser... Mr. John Doe goes to the pet store . He sees a cute rabbit , falls in love , and buys it . They lived happily ever after . \end{verbatim} Alternatively, you can use the \texttt{-n} option to output each sentence on a separate line, instead of using the \texttt{} symbol: \begin{verbatim} $ ucto -L eng -n /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser... Mr. John Doe goes to the pet store . He sees a cute rabbit , falls in love , and buys it . They lived happily ever after . \end{verbatim} To output to an output file instead of standard output, we would invoke ucto as follows: \begin{verbatim} $ ucto -L eng /tmp/input.txt /tmp/output.txt \end{verbatim} This simplest form of output does not show all of the information ucto has on the tokens. For a more verbose view, add the \texttt{-v} option: \begin{verbatim} $ ucto -L eng -v /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser... Mr. ABBREVIATION-KNOWN BEGINOFSENTENCE NEWPARAGRAPH John WORD Doe WORD goes WORD to WORD the WORD pet WORD store WORD NOSPACE . PUNCTUATION ENDOFSENTENCE He WORD BEGINOFSENTENCE sees WORD a WORD cute WORD rabbit WORD NOSPACE , PUNCTUATION falls WORD in WORD love WORD NOSPACE , PUNCTUATION and WORD buys WORD it WORD NOSPACE . PUNCTUATION ENDOFSENTENCE They WORD BEGINOFSENTENCE lived WORD happily WORD ever WORD after WORD NOSPACE . PUNCTUATION ENDOFSENTENCE \end{verbatim} As you see, this outputs the token types (the matching regular expressions) and roles such as \texttt{BEGINOFSENTENCE}, \texttt{ENDOFSENTENCE}, \texttt{NEWPARAGRAPH}, \texttt{BEGINQUOTE}, \texttt{ENDQUOTE}, \texttt{NOSPACE}. For further processing of your file in a natural language processing pipeline, or when releasing a corpus. It is recommended to make use of the FoLiA XML format \cite{FOLIA} \footnote{See also: http://proycon.github.com/folia}. FoLiA is a format for linguistic annotation supporting a wide variety of annotation types. FoLiA XML output is enabled by specifying the \texttt{-X} flag. An ID for the FoLiA document can be specified using the \texttt{--id=} flag. \begin{lstlisting}[language=xml] $ ucto -L eng -v -X --id=example /tmp/input.txt configfile = tokconfig-eng inputfile = /tmp/input.txt outputfile = Initiating tokeniser...

Mr. John Doe goes to the pet store . He sees a cute rabbit , falls in love , and buys it . They lived happily ever after .

\end{lstlisting} Ucto can also take FoLiA XML documents with untokenised sentences as input, using the \texttt{-F} option. \bibliographystyle{plain} \bibliography{ucto_manual} \end{document} LanguageMachines-ucto-688c2af/dox.cfg000066400000000000000000003432241472777655400176130ustar00rootroot00000000000000# Doxyfile 1.9.1 # This file describes the settings to be used by the documentation system # doxygen (www.doxygen.org) for a project. # # All text after a double hash (##) is considered a comment and is placed in # front of the TAG it is preceding. # # All text after a single hash (#) is considered a comment and will be ignored. # The format is: # TAG = value [value, ...] # For lists, items can also be appended using: # TAG += value [value, ...] # Values that contain spaces should be placed between quotes (\" \"). #--------------------------------------------------------------------------- # Project related configuration options #--------------------------------------------------------------------------- # This tag specifies the encoding used for all characters in the configuration # file that follow. The default is UTF-8 which is also the encoding used for all # text before the first occurrence of this tag. Doxygen uses libiconv (or the # iconv built into libc) for the transcoding. See # https://www.gnu.org/software/libiconv/ for the list of possible encodings. # The default value is: UTF-8. DOXYFILE_ENCODING = UTF-8 # The PROJECT_NAME tag is a single word (or a sequence of words surrounded by # double-quotes, unless you are using Doxywizard) that should identify the # project for which the documentation is generated. This name is used in the # title of most generated pages and in a few other places. # The default value is: My Project. PROJECT_NAME = Ucto # The PROJECT_NUMBER tag can be used to enter a project or revision number. This # could be handy for archiving the generated documentation or if some version # control system is used. PROJECT_NUMBER = # Using the PROJECT_BRIEF tag one can provide an optional one line description # for a project that appears at the top of each page and should give viewer a # quick idea about the purpose of the project. Keep the description short. PROJECT_BRIEF = # With the PROJECT_LOGO tag one can specify a logo or an icon that is included # in the documentation. The maximum height of the logo should not exceed 55 # pixels and the maximum width should not exceed 200 pixels. Doxygen will copy # the logo to the output directory. PROJECT_LOGO = # The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path # into which the generated documentation will be written. If a relative path is # entered, it will be relative to the location where doxygen was started. If # left blank the current directory will be used. OUTPUT_DIRECTORY = # If the CREATE_SUBDIRS tag is set to YES then doxygen will create 4096 sub- # directories (in 2 levels) under the output directory of each output format and # will distribute the generated files over these directories. Enabling this # option can be useful when feeding doxygen a huge amount of source files, where # putting all generated files in the same directory would otherwise causes # performance problems for the file system. # The default value is: NO. CREATE_SUBDIRS = NO # If the ALLOW_UNICODE_NAMES tag is set to YES, doxygen will allow non-ASCII # characters to appear in the names of generated files. If set to NO, non-ASCII # characters will be escaped, for example _xE3_x81_x84 will be used for Unicode # U+3044. # The default value is: NO. ALLOW_UNICODE_NAMES = NO # The OUTPUT_LANGUAGE tag is used to specify the language in which all # documentation generated by doxygen is written. Doxygen will use this # information to generate all constant output in the proper language. # Possible values are: Afrikaans, Arabic, Armenian, Brazilian, Catalan, Chinese, # Chinese-Traditional, Croatian, Czech, Danish, Dutch, English (United States), # Esperanto, Farsi (Persian), Finnish, French, German, Greek, Hungarian, # Indonesian, Italian, Japanese, Japanese-en (Japanese with English messages), # Korean, Korean-en (Korean with English messages), Latvian, Lithuanian, # Macedonian, Norwegian, Persian (Farsi), Polish, Portuguese, Romanian, Russian, # Serbian, Serbian-Cyrillic, Slovak, Slovene, Spanish, Swedish, Turkish, # Ukrainian and Vietnamese. # The default value is: English. OUTPUT_LANGUAGE = English # The OUTPUT_TEXT_DIRECTION tag is used to specify the direction in which all # documentation generated by doxygen is written. Doxygen will use this # information to generate all generated output in the proper direction. # Possible values are: None, LTR, RTL and Context. # The default value is: None. OUTPUT_TEXT_DIRECTION = None # If the BRIEF_MEMBER_DESC tag is set to YES, doxygen will include brief member # descriptions after the members that are listed in the file and class # documentation (similar to Javadoc). Set to NO to disable this. # The default value is: YES. BRIEF_MEMBER_DESC = YES # If the REPEAT_BRIEF tag is set to YES, doxygen will prepend the brief # description of a member or function before the detailed description # # Note: If both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the # brief descriptions will be completely suppressed. # The default value is: YES. REPEAT_BRIEF = YES # This tag implements a quasi-intelligent brief description abbreviator that is # used to form the text in various listings. Each string in this list, if found # as the leading text of the brief description, will be stripped from the text # and the result, after processing the whole list, is used as the annotated # text. Otherwise, the brief description is used as-is. If left blank, the # following values are used ($name is automatically replaced with the name of # the entity):The $name class, The $name widget, The $name file, is, provides, # specifies, contains, represents, a, an and the. ABBREVIATE_BRIEF = "The $name class" \ "The $name widget" \ "The $name file" \ is \ provides \ specifies \ contains \ represents \ a \ an \ the # If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then # doxygen will generate a detailed section even if there is only a brief # description. # The default value is: NO. ALWAYS_DETAILED_SEC = NO # If the INLINE_INHERITED_MEMB tag is set to YES, doxygen will show all # inherited members of a class in the documentation of that class as if those # members were ordinary class members. Constructors, destructors and assignment # operators of the base classes will not be shown. # The default value is: NO. INLINE_INHERITED_MEMB = NO # If the FULL_PATH_NAMES tag is set to YES, doxygen will prepend the full path # before files name in the file list and in the header files. If set to NO the # shortest path that makes the file name unique will be used # The default value is: YES. FULL_PATH_NAMES = YES # The STRIP_FROM_PATH tag can be used to strip a user-defined part of the path. # Stripping is only done if one of the specified strings matches the left-hand # part of the path. The tag can be used to show relative paths in the file list. # If left blank the directory from which doxygen is run is used as the path to # strip. # # Note that you can specify absolute paths here, but also relative paths, which # will be relative from the directory where doxygen is started. # This tag requires that the tag FULL_PATH_NAMES is set to YES. STRIP_FROM_PATH = # The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of the # path mentioned in the documentation of a class, which tells the reader which # header file to include in order to use a class. If left blank only the name of # the header file containing the class definition is used. Otherwise one should # specify the list of include paths that are normally passed to the compiler # using the -I flag. STRIP_FROM_INC_PATH = # If the SHORT_NAMES tag is set to YES, doxygen will generate much shorter (but # less readable) file names. This can be useful is your file systems doesn't # support long names like on DOS, Mac, or CD-ROM. # The default value is: NO. SHORT_NAMES = NO # If the JAVADOC_AUTOBRIEF tag is set to YES then doxygen will interpret the # first line (until the first dot) of a Javadoc-style comment as the brief # description. If set to NO, the Javadoc-style will behave just like regular Qt- # style comments (thus requiring an explicit @brief command for a brief # description.) # The default value is: NO. JAVADOC_AUTOBRIEF = NO # If the JAVADOC_BANNER tag is set to YES then doxygen will interpret a line # such as # /*************** # as being the beginning of a Javadoc-style comment "banner". If set to NO, the # Javadoc-style will behave just like regular comments and it will not be # interpreted by doxygen. # The default value is: NO. JAVADOC_BANNER = NO # If the QT_AUTOBRIEF tag is set to YES then doxygen will interpret the first # line (until the first dot) of a Qt-style comment as the brief description. If # set to NO, the Qt-style will behave just like regular Qt-style comments (thus # requiring an explicit \brief command for a brief description.) # The default value is: NO. QT_AUTOBRIEF = NO # The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make doxygen treat a # multi-line C++ special comment block (i.e. a block of //! or /// comments) as # a brief description. This used to be the default behavior. The new default is # to treat a multi-line C++ comment block as a detailed description. Set this # tag to YES if you prefer the old behavior instead. # # Note that setting this tag to YES also means that rational rose comments are # not recognized any more. # The default value is: NO. MULTILINE_CPP_IS_BRIEF = NO # By default Python docstrings are displayed as preformatted text and doxygen's # special commands cannot be used. By setting PYTHON_DOCSTRING to NO the # doxygen's special commands can be used and the contents of the docstring # documentation blocks is shown as doxygen documentation. # The default value is: YES. PYTHON_DOCSTRING = YES # If the INHERIT_DOCS tag is set to YES then an undocumented member inherits the # documentation from any documented member that it re-implements. # The default value is: YES. INHERIT_DOCS = YES # If the SEPARATE_MEMBER_PAGES tag is set to YES then doxygen will produce a new # page for each member. If set to NO, the documentation of a member will be part # of the file/class/namespace that contains it. # The default value is: NO. SEPARATE_MEMBER_PAGES = NO # The TAB_SIZE tag can be used to set the number of spaces in a tab. Doxygen # uses this value to replace tabs by spaces in code fragments. # Minimum value: 1, maximum value: 16, default value: 4. TAB_SIZE = 4 # This tag can be used to specify a number of aliases that act as commands in # the documentation. An alias has the form: # name=value # For example adding # "sideeffect=@par Side Effects:\n" # will allow you to put the command \sideeffect (or @sideeffect) in the # documentation, which will result in a user-defined paragraph with heading # "Side Effects:". You can put \n's in the value part of an alias to insert # newlines (in the resulting output). You can put ^^ in the value part of an # alias to insert a newline as if a physical newline was in the original file. # When you need a literal { or } or , in the value part of an alias you have to # escape them by means of a backslash (\), this can lead to conflicts with the # commands \{ and \} for these it is advised to use the version @{ and @} or use # a double escape (\\{ and \\}) ALIASES = # Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C sources # only. Doxygen will then generate output that is more tailored for C. For # instance, some of the names that are used will be different. The list of all # members will be omitted, etc. # The default value is: NO. OPTIMIZE_OUTPUT_FOR_C = NO # Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java or # Python sources only. Doxygen will then generate output that is more tailored # for that language. For instance, namespaces will be presented as packages, # qualified scopes will look different, etc. # The default value is: NO. OPTIMIZE_OUTPUT_JAVA = NO # Set the OPTIMIZE_FOR_FORTRAN tag to YES if your project consists of Fortran # sources. Doxygen will then generate output that is tailored for Fortran. # The default value is: NO. OPTIMIZE_FOR_FORTRAN = NO # Set the OPTIMIZE_OUTPUT_VHDL tag to YES if your project consists of VHDL # sources. Doxygen will then generate output that is tailored for VHDL. # The default value is: NO. OPTIMIZE_OUTPUT_VHDL = NO # Set the OPTIMIZE_OUTPUT_SLICE tag to YES if your project consists of Slice # sources only. Doxygen will then generate output that is more tailored for that # language. For instance, namespaces will be presented as modules, types will be # separated into more groups, etc. # The default value is: NO. OPTIMIZE_OUTPUT_SLICE = NO # Doxygen selects the parser to use depending on the extension of the files it # parses. With this tag you can assign which parser to use for a given # extension. Doxygen has a built-in mapping, but you can override or extend it # using this tag. The format is ext=language, where ext is a file extension, and # language is one of the parsers supported by doxygen: IDL, Java, JavaScript, # Csharp (C#), C, C++, D, PHP, md (Markdown), Objective-C, Python, Slice, VHDL, # Fortran (fixed format Fortran: FortranFixed, free formatted Fortran: # FortranFree, unknown formatted Fortran: Fortran. In the later case the parser # tries to guess whether the code is fixed or free formatted code, this is the # default for Fortran type files). For instance to make doxygen treat .inc files # as Fortran files (default is PHP), and .f files as C (default is Fortran), # use: inc=Fortran f=C. # # Note: For files without extension you can use no_extension as a placeholder. # # Note that for custom extensions you also need to set FILE_PATTERNS otherwise # the files are not read by doxygen. When specifying no_extension you should add # * to the FILE_PATTERNS. # # Note see also the list of default file extension mappings. EXTENSION_MAPPING = # If the MARKDOWN_SUPPORT tag is enabled then doxygen pre-processes all comments # according to the Markdown format, which allows for more readable # documentation. See https://daringfireball.net/projects/markdown/ for details. # The output of markdown processing is further processed by doxygen, so you can # mix doxygen, HTML, and XML commands with Markdown formatting. Disable only in # case of backward compatibilities issues. # The default value is: YES. MARKDOWN_SUPPORT = YES # When the TOC_INCLUDE_HEADINGS tag is set to a non-zero value, all headings up # to that level are automatically included in the table of contents, even if # they do not have an id attribute. # Note: This feature currently applies only to Markdown headings. # Minimum value: 0, maximum value: 99, default value: 5. # This tag requires that the tag MARKDOWN_SUPPORT is set to YES. TOC_INCLUDE_HEADINGS = 0 # When enabled doxygen tries to link words that correspond to documented # classes, or namespaces to their corresponding documentation. Such a link can # be prevented in individual cases by putting a % sign in front of the word or # globally by setting AUTOLINK_SUPPORT to NO. # The default value is: YES. AUTOLINK_SUPPORT = YES # If you use STL classes (i.e. std::string, std::vector, etc.) but do not want # to include (a tag file for) the STL sources as input, then you should set this # tag to YES in order to let doxygen match functions declarations and # definitions whose arguments contain STL classes (e.g. func(std::string); # versus func(std::string) {}). This also make the inheritance and collaboration # diagrams that involve STL classes more complete and accurate. # The default value is: NO. BUILTIN_STL_SUPPORT = YES # If you use Microsoft's C++/CLI language, you should set this option to YES to # enable parsing support. # The default value is: NO. CPP_CLI_SUPPORT = NO # Set the SIP_SUPPORT tag to YES if your project consists of sip (see: # https://www.riverbankcomputing.com/software/sip/intro) sources only. Doxygen # will parse them like normal C++ but will assume all classes use public instead # of private inheritance when no explicit protection keyword is present. # The default value is: NO. SIP_SUPPORT = NO # For Microsoft's IDL there are propget and propput attributes to indicate # getter and setter methods for a property. Setting this option to YES will make # doxygen to replace the get and set methods by a property in the documentation. # This will only work if the methods are indeed getting or setting a simple # type. If this is not the case, or you want to show the methods anyway, you # should set this option to NO. # The default value is: YES. IDL_PROPERTY_SUPPORT = YES # If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC # tag is set to YES then doxygen will reuse the documentation of the first # member in the group (if any) for the other members of the group. By default # all members of a group must be documented explicitly. # The default value is: NO. DISTRIBUTE_GROUP_DOC = NO # If one adds a struct or class to a group and this option is enabled, then also # any nested class or struct is added to the same group. By default this option # is disabled and one has to add nested compounds explicitly via \ingroup. # The default value is: NO. GROUP_NESTED_COMPOUNDS = NO # Set the SUBGROUPING tag to YES to allow class member groups of the same type # (for instance a group of public functions) to be put as a subgroup of that # type (e.g. under the Public Functions section). Set it to NO to prevent # subgrouping. Alternatively, this can be done per class using the # \nosubgrouping command. # The default value is: YES. SUBGROUPING = YES # When the INLINE_GROUPED_CLASSES tag is set to YES, classes, structs and unions # are shown inside the group in which they are included (e.g. using \ingroup) # instead of on a separate page (for HTML and Man pages) or section (for LaTeX # and RTF). # # Note that this feature does not work in combination with # SEPARATE_MEMBER_PAGES. # The default value is: NO. INLINE_GROUPED_CLASSES = NO # When the INLINE_SIMPLE_STRUCTS tag is set to YES, structs, classes, and unions # with only public data fields or simple typedef fields will be shown inline in # the documentation of the scope in which they are defined (i.e. file, # namespace, or group documentation), provided this scope is documented. If set # to NO, structs, classes, and unions are shown on a separate page (for HTML and # Man pages) or section (for LaTeX and RTF). # The default value is: NO. INLINE_SIMPLE_STRUCTS = NO # When TYPEDEF_HIDES_STRUCT tag is enabled, a typedef of a struct, union, or # enum is documented as struct, union, or enum with the name of the typedef. So # typedef struct TypeS {} TypeT, will appear in the documentation as a struct # with name TypeT. When disabled the typedef will appear as a member of a file, # namespace, or class. And the struct will be named TypeS. This can typically be # useful for C code in case the coding convention dictates that all compound # types are typedef'ed and only the typedef is referenced, never the tag name. # The default value is: NO. TYPEDEF_HIDES_STRUCT = NO # The size of the symbol lookup cache can be set using LOOKUP_CACHE_SIZE. This # cache is used to resolve symbols given their name and scope. Since this can be # an expensive process and often the same symbol appears multiple times in the # code, doxygen keeps a cache of pre-resolved symbols. If the cache is too small # doxygen will become slower. If the cache is too large, memory is wasted. The # cache size is given by this formula: 2^(16+LOOKUP_CACHE_SIZE). The valid range # is 0..9, the default is 0, corresponding to a cache size of 2^16=65536 # symbols. At the end of a run doxygen will report the cache usage and suggest # the optimal cache size from a speed point of view. # Minimum value: 0, maximum value: 9, default value: 0. LOOKUP_CACHE_SIZE = 0 # The NUM_PROC_THREADS specifies the number threads doxygen is allowed to use # during processing. When set to 0 doxygen will based this on the number of # cores available in the system. You can set it explicitly to a value larger # than 0 to get more control over the balance between CPU load and processing # speed. At this moment only the input processing can be done using multiple # threads. Since this is still an experimental feature the default is set to 1, # which efficively disables parallel processing. Please report any issues you # encounter. Generating dot graphs in parallel is controlled by the # DOT_NUM_THREADS setting. # Minimum value: 0, maximum value: 32, default value: 1. NUM_PROC_THREADS = 1 #--------------------------------------------------------------------------- # Build related configuration options #--------------------------------------------------------------------------- # If the EXTRACT_ALL tag is set to YES, doxygen will assume all entities in # documentation are documented, even if no documentation was available. Private # class members and static file members will be hidden unless the # EXTRACT_PRIVATE respectively EXTRACT_STATIC tags are set to YES. # Note: This will also disable the warnings about undocumented members that are # normally produced when WARNINGS is set to YES. # The default value is: NO. EXTRACT_ALL = YES # If the EXTRACT_PRIVATE tag is set to YES, all private members of a class will # be included in the documentation. # The default value is: NO. EXTRACT_PRIVATE = NO # If the EXTRACT_PRIV_VIRTUAL tag is set to YES, documented private virtual # methods of a class will be included in the documentation. # The default value is: NO. EXTRACT_PRIV_VIRTUAL = NO # If the EXTRACT_PACKAGE tag is set to YES, all members with package or internal # scope will be included in the documentation. # The default value is: NO. EXTRACT_PACKAGE = NO # If the EXTRACT_STATIC tag is set to YES, all static members of a file will be # included in the documentation. # The default value is: NO. EXTRACT_STATIC = NO # If the EXTRACT_LOCAL_CLASSES tag is set to YES, classes (and structs) defined # locally in source files will be included in the documentation. If set to NO, # only classes defined in header files are included. Does not have any effect # for Java sources. # The default value is: YES. EXTRACT_LOCAL_CLASSES = YES # This flag is only useful for Objective-C code. If set to YES, local methods, # which are defined in the implementation section but not in the interface are # included in the documentation. If set to NO, only methods in the interface are # included. # The default value is: NO. EXTRACT_LOCAL_METHODS = NO # If this flag is set to YES, the members of anonymous namespaces will be # extracted and appear in the documentation as a namespace called # 'anonymous_namespace{file}', where file will be replaced with the base name of # the file that contains the anonymous namespace. By default anonymous namespace # are hidden. # The default value is: NO. EXTRACT_ANON_NSPACES = NO # If this flag is set to YES, the name of an unnamed parameter in a declaration # will be determined by the corresponding definition. By default unnamed # parameters remain unnamed in the output. # The default value is: YES. RESOLVE_UNNAMED_PARAMS = YES # If the HIDE_UNDOC_MEMBERS tag is set to YES, doxygen will hide all # undocumented members inside documented classes or files. If set to NO these # members will be included in the various overviews, but no documentation # section is generated. This option has no effect if EXTRACT_ALL is enabled. # The default value is: NO. HIDE_UNDOC_MEMBERS = NO # If the HIDE_UNDOC_CLASSES tag is set to YES, doxygen will hide all # undocumented classes that are normally visible in the class hierarchy. If set # to NO, these classes will be included in the various overviews. This option # has no effect if EXTRACT_ALL is enabled. # The default value is: NO. HIDE_UNDOC_CLASSES = NO # If the HIDE_FRIEND_COMPOUNDS tag is set to YES, doxygen will hide all friend # declarations. If set to NO, these declarations will be included in the # documentation. # The default value is: NO. HIDE_FRIEND_COMPOUNDS = NO # If the HIDE_IN_BODY_DOCS tag is set to YES, doxygen will hide any # documentation blocks found inside the body of a function. If set to NO, these # blocks will be appended to the function's detailed documentation block. # The default value is: NO. HIDE_IN_BODY_DOCS = NO # The INTERNAL_DOCS tag determines if documentation that is typed after a # \internal command is included. If the tag is set to NO then the documentation # will be excluded. Set it to YES to include the internal documentation. # The default value is: NO. INTERNAL_DOCS = NO # With the correct setting of option CASE_SENSE_NAMES doxygen will better be # able to match the capabilities of the underlying filesystem. In case the # filesystem is case sensitive (i.e. it supports files in the same directory # whose names only differ in casing), the option must be set to YES to properly # deal with such files in case they appear in the input. For filesystems that # are not case sensitive the option should be be set to NO to properly deal with # output files written for symbols that only differ in casing, such as for two # classes, one named CLASS and the other named Class, and to also support # references to files without having to specify the exact matching casing. On # Windows (including Cygwin) and MacOS, users should typically set this option # to NO, whereas on Linux or other Unix flavors it should typically be set to # YES. # The default value is: system dependent. CASE_SENSE_NAMES = YES # If the HIDE_SCOPE_NAMES tag is set to NO then doxygen will show members with # their full class and namespace scopes in the documentation. If set to YES, the # scope will be hidden. # The default value is: NO. HIDE_SCOPE_NAMES = NO # If the HIDE_COMPOUND_REFERENCE tag is set to NO (default) then doxygen will # append additional text to a page's title, such as Class Reference. If set to # YES the compound reference will be hidden. # The default value is: NO. HIDE_COMPOUND_REFERENCE= NO # If the SHOW_INCLUDE_FILES tag is set to YES then doxygen will put a list of # the files that are included by a file in the documentation of that file. # The default value is: YES. SHOW_INCLUDE_FILES = YES # If the SHOW_GROUPED_MEMB_INC tag is set to YES then Doxygen will add for each # grouped member an include statement to the documentation, telling the reader # which file to include in order to use the member. # The default value is: NO. SHOW_GROUPED_MEMB_INC = NO # If the FORCE_LOCAL_INCLUDES tag is set to YES then doxygen will list include # files with double quotes in the documentation rather than with sharp brackets. # The default value is: NO. FORCE_LOCAL_INCLUDES = NO # If the INLINE_INFO tag is set to YES then a tag [inline] is inserted in the # documentation for inline members. # The default value is: YES. INLINE_INFO = YES # If the SORT_MEMBER_DOCS tag is set to YES then doxygen will sort the # (detailed) documentation of file and class members alphabetically by member # name. If set to NO, the members will appear in declaration order. # The default value is: YES. SORT_MEMBER_DOCS = YES # If the SORT_BRIEF_DOCS tag is set to YES then doxygen will sort the brief # descriptions of file, namespace and class members alphabetically by member # name. If set to NO, the members will appear in declaration order. Note that # this will also influence the order of the classes in the class list. # The default value is: NO. SORT_BRIEF_DOCS = NO # If the SORT_MEMBERS_CTORS_1ST tag is set to YES then doxygen will sort the # (brief and detailed) documentation of class members so that constructors and # destructors are listed first. If set to NO the constructors will appear in the # respective orders defined by SORT_BRIEF_DOCS and SORT_MEMBER_DOCS. # Note: If SORT_BRIEF_DOCS is set to NO this option is ignored for sorting brief # member documentation. # Note: If SORT_MEMBER_DOCS is set to NO this option is ignored for sorting # detailed member documentation. # The default value is: NO. SORT_MEMBERS_CTORS_1ST = NO # If the SORT_GROUP_NAMES tag is set to YES then doxygen will sort the hierarchy # of group names into alphabetical order. If set to NO the group names will # appear in their defined order. # The default value is: NO. SORT_GROUP_NAMES = NO # If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be sorted by # fully-qualified names, including namespaces. If set to NO, the class list will # be sorted only by class name, not including the namespace part. # Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES. # Note: This option applies only to the class list, not to the alphabetical # list. # The default value is: NO. SORT_BY_SCOPE_NAME = NO # If the STRICT_PROTO_MATCHING option is enabled and doxygen fails to do proper # type resolution of all parameters of a function it will reject a match between # the prototype and the implementation of a member function even if there is # only one candidate or it is obvious which candidate to choose by doing a # simple string match. By disabling STRICT_PROTO_MATCHING doxygen will still # accept a match between prototype and implementation in such cases. # The default value is: NO. STRICT_PROTO_MATCHING = NO # The GENERATE_TODOLIST tag can be used to enable (YES) or disable (NO) the todo # list. This list is created by putting \todo commands in the documentation. # The default value is: YES. GENERATE_TODOLIST = YES # The GENERATE_TESTLIST tag can be used to enable (YES) or disable (NO) the test # list. This list is created by putting \test commands in the documentation. # The default value is: YES. GENERATE_TESTLIST = YES # The GENERATE_BUGLIST tag can be used to enable (YES) or disable (NO) the bug # list. This list is created by putting \bug commands in the documentation. # The default value is: YES. GENERATE_BUGLIST = YES # The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or disable (NO) # the deprecated list. This list is created by putting \deprecated commands in # the documentation. # The default value is: YES. GENERATE_DEPRECATEDLIST= YES # The ENABLED_SECTIONS tag can be used to enable conditional documentation # sections, marked by \if ... \endif and \cond # ... \endcond blocks. ENABLED_SECTIONS = # The MAX_INITIALIZER_LINES tag determines the maximum number of lines that the # initial value of a variable or macro / define can have for it to appear in the # documentation. If the initializer consists of more lines than specified here # it will be hidden. Use a value of 0 to hide initializers completely. The # appearance of the value of individual variables and macros / defines can be # controlled using \showinitializer or \hideinitializer command in the # documentation regardless of this setting. # Minimum value: 0, maximum value: 10000, default value: 30. MAX_INITIALIZER_LINES = 30 # Set the SHOW_USED_FILES tag to NO to disable the list of files generated at # the bottom of the documentation of classes and structs. If set to YES, the # list will mention the files that were used to generate the documentation. # The default value is: YES. SHOW_USED_FILES = YES # Set the SHOW_FILES tag to NO to disable the generation of the Files page. This # will remove the Files entry from the Quick Index and from the Folder Tree View # (if specified). # The default value is: YES. SHOW_FILES = YES # Set the SHOW_NAMESPACES tag to NO to disable the generation of the Namespaces # page. This will remove the Namespaces entry from the Quick Index and from the # Folder Tree View (if specified). # The default value is: YES. SHOW_NAMESPACES = YES # The FILE_VERSION_FILTER tag can be used to specify a program or script that # doxygen should invoke to get the current version for each file (typically from # the version control system). Doxygen will invoke the program by executing (via # popen()) the command command input-file, where command is the value of the # FILE_VERSION_FILTER tag, and input-file is the name of an input file provided # by doxygen. Whatever the program writes to standard output is used as the file # version. For an example see the documentation. FILE_VERSION_FILTER = # The LAYOUT_FILE tag can be used to specify a layout file which will be parsed # by doxygen. The layout file controls the global structure of the generated # output files in an output format independent way. To create the layout file # that represents doxygen's defaults, run doxygen with the -l option. You can # optionally specify a file name after the option, if omitted DoxygenLayout.xml # will be used as the name of the layout file. # # Note that if you run doxygen from a directory containing a file called # DoxygenLayout.xml, doxygen will parse it automatically even if the LAYOUT_FILE # tag is left empty. LAYOUT_FILE = # The CITE_BIB_FILES tag can be used to specify one or more bib files containing # the reference definitions. This must be a list of .bib files. The .bib # extension is automatically appended if omitted. This requires the bibtex tool # to be installed. See also https://en.wikipedia.org/wiki/BibTeX for more info. # For LaTeX the style of the bibliography can be controlled using # LATEX_BIB_STYLE. To use this feature you need bibtex and perl available in the # search path. See also \cite for info how to create references. CITE_BIB_FILES = #--------------------------------------------------------------------------- # Configuration options related to warning and progress messages #--------------------------------------------------------------------------- # The QUIET tag can be used to turn on/off the messages that are generated to # standard output by doxygen. If QUIET is set to YES this implies that the # messages are off. # The default value is: NO. QUIET = NO # The WARNINGS tag can be used to turn on/off the warning messages that are # generated to standard error (stderr) by doxygen. If WARNINGS is set to YES # this implies that the warnings are on. # # Tip: Turn warnings on while writing the documentation. # The default value is: YES. WARNINGS = YES # If the WARN_IF_UNDOCUMENTED tag is set to YES then doxygen will generate # warnings for undocumented members. If EXTRACT_ALL is set to YES then this flag # will automatically be disabled. # The default value is: YES. WARN_IF_UNDOCUMENTED = YES # If the WARN_IF_DOC_ERROR tag is set to YES, doxygen will generate warnings for # potential errors in the documentation, such as not documenting some parameters # in a documented function, or documenting parameters that don't exist or using # markup commands wrongly. # The default value is: YES. WARN_IF_DOC_ERROR = YES # This WARN_NO_PARAMDOC option can be enabled to get warnings for functions that # are documented, but have no documentation for their parameters or return # value. If set to NO, doxygen will only warn about wrong or incomplete # parameter documentation, but not about the absence of documentation. If # EXTRACT_ALL is set to YES then this flag will automatically be disabled. # The default value is: NO. WARN_NO_PARAMDOC = NO # If the WARN_AS_ERROR tag is set to YES then doxygen will immediately stop when # a warning is encountered. If the WARN_AS_ERROR tag is set to FAIL_ON_WARNINGS # then doxygen will continue running as if WARN_AS_ERROR tag is set to NO, but # at the end of the doxygen process doxygen will return with a non-zero status. # Possible values are: NO, YES and FAIL_ON_WARNINGS. # The default value is: NO. WARN_AS_ERROR = NO # The WARN_FORMAT tag determines the format of the warning messages that doxygen # can produce. The string should contain the $file, $line, and $text tags, which # will be replaced by the file and line number from which the warning originated # and the warning text. Optionally the format may contain $version, which will # be replaced by the version of the file (if it could be obtained via # FILE_VERSION_FILTER) # The default value is: $file:$line: $text. WARN_FORMAT = "$file:$line: $text" # The WARN_LOGFILE tag can be used to specify a file to which warning and error # messages should be written. If left blank the output is written to standard # error (stderr). WARN_LOGFILE = #--------------------------------------------------------------------------- # Configuration options related to the input files #--------------------------------------------------------------------------- # The INPUT tag is used to specify the files and/or directories that contain # documented source files. You may enter file names like myfile.cpp or # directories like /usr/src/myproject. Separate the files or directories with # spaces. See also FILE_PATTERNS and EXTENSION_MAPPING # Note: If this tag is empty the current directory is searched. INPUT = ./src \ ./include/ucto # This tag can be used to specify the character encoding of the source files # that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses # libiconv (or the iconv built into libc) for the transcoding. See the libiconv # documentation (see: # https://www.gnu.org/software/libiconv/) for the list of possible encodings. # The default value is: UTF-8. INPUT_ENCODING = UTF-8 # If the value of the INPUT tag contains directories, you can use the # FILE_PATTERNS tag to specify one or more wildcard patterns (like *.cpp and # *.h) to filter out the source-files in the directories. # # Note that for custom extensions or not directly supported extensions you also # need to set EXTENSION_MAPPING for the extension otherwise the files are not # read by doxygen. # # Note the list of default checked file patterns might differ from the list of # default file extension mappings. # # If left blank the following patterns are tested:*.c, *.cc, *.cxx, *.cpp, # *.c++, *.java, *.ii, *.ixx, *.ipp, *.i++, *.inl, *.idl, *.ddl, *.odl, *.h, # *.hh, *.hxx, *.hpp, *.h++, *.cs, *.d, *.php, *.php4, *.php5, *.phtml, *.inc, # *.m, *.markdown, *.md, *.mm, *.dox (to be provided as doxygen C comment), # *.py, *.pyw, *.f90, *.f95, *.f03, *.f08, *.f18, *.f, *.for, *.vhd, *.vhdl, # *.ucf, *.qsf and *.ice. FILE_PATTERNS = *.c \ *.cc \ *.cxx \ *.cpp \ *.c++ \ *.java \ *.ii \ *.ixx \ *.ipp \ *.i++ \ *.inl \ *.idl \ *.ddl \ *.odl \ *.h \ *.hh \ *.hxx \ *.hpp \ *.h++ \ *.cs \ *.d \ *.php \ *.php4 \ *.php5 \ *.phtml \ *.inc \ *.m \ *.markdown \ *.md \ *.mm \ *.dox \ *.py \ *.pyw \ *.f90 \ *.f95 \ *.f03 \ *.f08 \ *.f \ *.for \ *.tcl \ *.vhd \ *.vhdl \ *.ucf \ *.qsf # The RECURSIVE tag can be used to specify whether or not subdirectories should # be searched for input files as well. # The default value is: NO. RECURSIVE = YES # The EXCLUDE tag can be used to specify files and/or directories that should be # excluded from the INPUT source files. This way you can easily exclude a # subdirectory from a directory tree whose root is specified with the INPUT tag. # # Note that relative paths are relative to the directory from which doxygen is # run. EXCLUDE = # The EXCLUDE_SYMLINKS tag can be used to select whether or not files or # directories that are symbolic links (a Unix file system feature) are excluded # from the input. # The default value is: NO. EXCLUDE_SYMLINKS = NO # If the value of the INPUT tag contains directories, you can use the # EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude # certain files from those directories. # # Note that the wildcards are matched against the file with absolute path, so to # exclude all test directories for example use the pattern */test/* EXCLUDE_PATTERNS = # The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names # (namespaces, classes, functions, etc.) that should be excluded from the # output. The symbol name can be a fully qualified name, a word, or if the # wildcard * is used, a substring. Examples: ANamespace, AClass, # AClass::ANamespace, ANamespace::*Test # # Note that the wildcards are matched against the file with absolute path, so to # exclude all test directories use the pattern */test/* EXCLUDE_SYMBOLS = # The EXAMPLE_PATH tag can be used to specify one or more files or directories # that contain example code fragments that are included (see the \include # command). EXAMPLE_PATH = # If the value of the EXAMPLE_PATH tag contains directories, you can use the # EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and # *.h) to filter out the source-files in the directories. If left blank all # files are included. EXAMPLE_PATTERNS = * # If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be # searched for input files to be used with the \include or \dontinclude commands # irrespective of the value of the RECURSIVE tag. # The default value is: NO. EXAMPLE_RECURSIVE = NO # The IMAGE_PATH tag can be used to specify one or more files or directories # that contain images that are to be included in the documentation (see the # \image command). IMAGE_PATH = # The INPUT_FILTER tag can be used to specify a program that doxygen should # invoke to filter for each input file. Doxygen will invoke the filter program # by executing (via popen()) the command: # # # # where is the value of the INPUT_FILTER tag, and is the # name of an input file. Doxygen will then use the output that the filter # program writes to standard output. If FILTER_PATTERNS is specified, this tag # will be ignored. # # Note that the filter must not add or remove lines; it is applied before the # code is scanned, but not when the output code is generated. If lines are added # or removed, the anchors will not be placed correctly. # # Note that for custom extensions or not directly supported extensions you also # need to set EXTENSION_MAPPING for the extension otherwise the files are not # properly processed by doxygen. INPUT_FILTER = # The FILTER_PATTERNS tag can be used to specify filters on a per file pattern # basis. Doxygen will compare the file name with each pattern and apply the # filter if there is a match. The filters are a list of the form: pattern=filter # (like *.cpp=my_cpp_filter). See INPUT_FILTER for further information on how # filters are used. If the FILTER_PATTERNS tag is empty or if none of the # patterns match the file name, INPUT_FILTER is applied. # # Note that for custom extensions or not directly supported extensions you also # need to set EXTENSION_MAPPING for the extension otherwise the files are not # properly processed by doxygen. FILTER_PATTERNS = # If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using # INPUT_FILTER) will also be used to filter the input files that are used for # producing the source files to browse (i.e. when SOURCE_BROWSER is set to YES). # The default value is: NO. FILTER_SOURCE_FILES = NO # The FILTER_SOURCE_PATTERNS tag can be used to specify source filters per file # pattern. A pattern will override the setting for FILTER_PATTERN (if any) and # it is also possible to disable source filtering for a specific pattern using # *.ext= (so without naming a filter). # This tag requires that the tag FILTER_SOURCE_FILES is set to YES. FILTER_SOURCE_PATTERNS = # If the USE_MDFILE_AS_MAINPAGE tag refers to the name of a markdown file that # is part of the input, its contents will be placed on the main page # (index.html). This can be useful if you have a project on for instance GitHub # and want to reuse the introduction page also for the doxygen output. USE_MDFILE_AS_MAINPAGE = #--------------------------------------------------------------------------- # Configuration options related to source browsing #--------------------------------------------------------------------------- # If the SOURCE_BROWSER tag is set to YES then a list of source files will be # generated. Documented entities will be cross-referenced with these sources. # # Note: To get rid of all source code in the generated output, make sure that # also VERBATIM_HEADERS is set to NO. # The default value is: NO. SOURCE_BROWSER = NO # Setting the INLINE_SOURCES tag to YES will include the body of functions, # classes and enums directly into the documentation. # The default value is: NO. INLINE_SOURCES = NO # Setting the STRIP_CODE_COMMENTS tag to YES will instruct doxygen to hide any # special comment blocks from generated source code fragments. Normal C, C++ and # Fortran comments will always remain visible. # The default value is: YES. STRIP_CODE_COMMENTS = YES # If the REFERENCED_BY_RELATION tag is set to YES then for each documented # entity all documented functions referencing it will be listed. # The default value is: NO. REFERENCED_BY_RELATION = NO # If the REFERENCES_RELATION tag is set to YES then for each documented function # all documented entities called/used by that function will be listed. # The default value is: NO. REFERENCES_RELATION = NO # If the REFERENCES_LINK_SOURCE tag is set to YES and SOURCE_BROWSER tag is set # to YES then the hyperlinks from functions in REFERENCES_RELATION and # REFERENCED_BY_RELATION lists will link to the source code. Otherwise they will # link to the documentation. # The default value is: YES. REFERENCES_LINK_SOURCE = YES # If SOURCE_TOOLTIPS is enabled (the default) then hovering a hyperlink in the # source code will show a tooltip with additional information such as prototype, # brief description and links to the definition and documentation. Since this # will make the HTML file larger and loading of large files a bit slower, you # can opt to disable this feature. # The default value is: YES. # This tag requires that the tag SOURCE_BROWSER is set to YES. SOURCE_TOOLTIPS = YES # If the USE_HTAGS tag is set to YES then the references to source code will # point to the HTML generated by the htags(1) tool instead of doxygen built-in # source browser. The htags tool is part of GNU's global source tagging system # (see https://www.gnu.org/software/global/global.html). You will need version # 4.8.6 or higher. # # To use it do the following: # - Install the latest version of global # - Enable SOURCE_BROWSER and USE_HTAGS in the configuration file # - Make sure the INPUT points to the root of the source tree # - Run doxygen as normal # # Doxygen will invoke htags (and that will in turn invoke gtags), so these # tools must be available from the command line (i.e. in the search path). # # The result: instead of the source browser generated by doxygen, the links to # source code will now point to the output of htags. # The default value is: NO. # This tag requires that the tag SOURCE_BROWSER is set to YES. USE_HTAGS = NO # If the VERBATIM_HEADERS tag is set the YES then doxygen will generate a # verbatim copy of the header file for each class for which an include is # specified. Set to NO to disable this. # See also: Section \class. # The default value is: YES. VERBATIM_HEADERS = YES # If the CLANG_ASSISTED_PARSING tag is set to YES then doxygen will use the # clang parser (see: # http://clang.llvm.org/) for more accurate parsing at the cost of reduced # performance. This can be particularly helpful with template rich C++ code for # which doxygen's built-in parser lacks the necessary type information. # Note: The availability of this option depends on whether or not doxygen was # generated with the -Duse_libclang=ON option for CMake. # The default value is: NO. CLANG_ASSISTED_PARSING = NO # If clang assisted parsing is enabled and the CLANG_ADD_INC_PATHS tag is set to # YES then doxygen will add the directory of each input to the include path. # The default value is: YES. CLANG_ADD_INC_PATHS = YES # If clang assisted parsing is enabled you can provide the compiler with command # line options that you would normally use when invoking the compiler. Note that # the include paths will already be set by doxygen for the files and directories # specified with INPUT and INCLUDE_PATH. # This tag requires that the tag CLANG_ASSISTED_PARSING is set to YES. CLANG_OPTIONS = # If clang assisted parsing is enabled you can provide the clang parser with the # path to the directory containing a file called compile_commands.json. This # file is the compilation database (see: # http://clang.llvm.org/docs/HowToSetupToolingForLLVM.html) containing the # options used when the source files were built. This is equivalent to # specifying the -p option to a clang tool, such as clang-check. These options # will then be passed to the parser. Any options specified with CLANG_OPTIONS # will be added as well. # Note: The availability of this option depends on whether or not doxygen was # generated with the -Duse_libclang=ON option for CMake. CLANG_DATABASE_PATH = #--------------------------------------------------------------------------- # Configuration options related to the alphabetical class index #--------------------------------------------------------------------------- # If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index of all # compounds will be generated. Enable this if the project contains a lot of # classes, structs, unions or interfaces. # The default value is: YES. ALPHABETICAL_INDEX = YES # In case all classes in a project start with a common prefix, all classes will # be put under the same header in the alphabetical index. The IGNORE_PREFIX tag # can be used to specify a prefix (or a list of prefixes) that should be ignored # while generating the index headers. # This tag requires that the tag ALPHABETICAL_INDEX is set to YES. IGNORE_PREFIX = #--------------------------------------------------------------------------- # Configuration options related to the HTML output #--------------------------------------------------------------------------- # If the GENERATE_HTML tag is set to YES, doxygen will generate HTML output # The default value is: YES. GENERATE_HTML = YES # The HTML_OUTPUT tag is used to specify where the HTML docs will be put. If a # relative path is entered the value of OUTPUT_DIRECTORY will be put in front of # it. # The default directory is: html. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_OUTPUT = html # The HTML_FILE_EXTENSION tag can be used to specify the file extension for each # generated HTML page (for example: .htm, .php, .asp). # The default value is: .html. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_FILE_EXTENSION = .html # The HTML_HEADER tag can be used to specify a user-defined HTML header file for # each generated HTML page. If the tag is left blank doxygen will generate a # standard header. # # To get valid HTML the header file that includes any scripts and style sheets # that doxygen needs, which is dependent on the configuration options used (e.g. # the setting GENERATE_TREEVIEW). It is highly recommended to start with a # default header using # doxygen -w html new_header.html new_footer.html new_stylesheet.css # YourConfigFile # and then modify the file new_header.html. See also section "Doxygen usage" # for information on how to generate the default header that doxygen normally # uses. # Note: The header is subject to change so you typically have to regenerate the # default header when upgrading to a newer version of doxygen. For a description # of the possible markers and block names see the documentation. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_HEADER = # The HTML_FOOTER tag can be used to specify a user-defined HTML footer for each # generated HTML page. If the tag is left blank doxygen will generate a standard # footer. See HTML_HEADER for more information on how to generate a default # footer and what special commands can be used inside the footer. See also # section "Doxygen usage" for information on how to generate the default footer # that doxygen normally uses. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_FOOTER = # The HTML_STYLESHEET tag can be used to specify a user-defined cascading style # sheet that is used by each HTML page. It can be used to fine-tune the look of # the HTML output. If left blank doxygen will generate a default style sheet. # See also section "Doxygen usage" for information on how to generate the style # sheet that doxygen normally uses. # Note: It is recommended to use HTML_EXTRA_STYLESHEET instead of this tag, as # it is more robust and this tag (HTML_STYLESHEET) will in the future become # obsolete. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_STYLESHEET = # The HTML_EXTRA_STYLESHEET tag can be used to specify additional user-defined # cascading style sheets that are included after the standard style sheets # created by doxygen. Using this option one can overrule certain style aspects. # This is preferred over using HTML_STYLESHEET since it does not replace the # standard style sheet and is therefore more robust against future updates. # Doxygen will copy the style sheet files to the output directory. # Note: The order of the extra style sheet files is of importance (e.g. the last # style sheet in the list overrules the setting of the previous ones in the # list). For an example see the documentation. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_EXTRA_STYLESHEET = # The HTML_EXTRA_FILES tag can be used to specify one or more extra images or # other source files which should be copied to the HTML output directory. Note # that these files will be copied to the base HTML output directory. Use the # $relpath^ marker in the HTML_HEADER and/or HTML_FOOTER files to load these # files. In the HTML_STYLESHEET file, use the file name only. Also note that the # files will be copied as-is; there are no commands or markers available. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_EXTRA_FILES = # The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. Doxygen # will adjust the colors in the style sheet and background images according to # this color. Hue is specified as an angle on a colorwheel, see # https://en.wikipedia.org/wiki/Hue for more information. For instance the value # 0 represents red, 60 is yellow, 120 is green, 180 is cyan, 240 is blue, 300 # purple, and 360 is red again. # Minimum value: 0, maximum value: 359, default value: 220. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_COLORSTYLE_HUE = 220 # The HTML_COLORSTYLE_SAT tag controls the purity (or saturation) of the colors # in the HTML output. For a value of 0 the output will use grayscales only. A # value of 255 will produce the most vivid colors. # Minimum value: 0, maximum value: 255, default value: 100. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_COLORSTYLE_SAT = 100 # The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to the # luminance component of the colors in the HTML output. Values below 100 # gradually make the output lighter, whereas values above 100 make the output # darker. The value divided by 100 is the actual gamma applied, so 80 represents # a gamma of 0.8, The value 220 represents a gamma of 2.2, and 100 does not # change the gamma. # Minimum value: 40, maximum value: 240, default value: 80. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_COLORSTYLE_GAMMA = 80 # If the HTML_TIMESTAMP tag is set to YES then the footer of each generated HTML # page will contain the date and time when the page was generated. Setting this # to YES can help to show when doxygen was last run and thus if the # documentation is up to date. # The default value is: NO. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_TIMESTAMP = YES # If the HTML_DYNAMIC_MENUS tag is set to YES then the generated HTML # documentation will contain a main index with vertical navigation menus that # are dynamically created via JavaScript. If disabled, the navigation index will # consists of multiple levels of tabs that are statically embedded in every HTML # page. Disable this option to support browsers that do not have JavaScript, # like the Qt help browser. # The default value is: YES. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_DYNAMIC_MENUS = YES # If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML # documentation will contain sections that can be hidden and shown after the # page has loaded. # The default value is: NO. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_DYNAMIC_SECTIONS = NO # With HTML_INDEX_NUM_ENTRIES one can control the preferred number of entries # shown in the various tree structured indices initially; the user can expand # and collapse entries dynamically later on. Doxygen will expand the tree to # such a level that at most the specified number of entries are visible (unless # a fully collapsed tree already exceeds this amount). So setting the number of # entries 1 will produce a full collapsed tree by default. 0 is a special value # representing an infinite number of entries and will result in a full expanded # tree by default. # Minimum value: 0, maximum value: 9999, default value: 100. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_INDEX_NUM_ENTRIES = 100 # If the GENERATE_DOCSET tag is set to YES, additional index files will be # generated that can be used as input for Apple's Xcode 3 integrated development # environment (see: # https://developer.apple.com/xcode/), introduced with OSX 10.5 (Leopard). To # create a documentation set, doxygen will generate a Makefile in the HTML # output directory. Running make will produce the docset in that directory and # running make install will install the docset in # ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find it at # startup. See https://developer.apple.com/library/archive/featuredarticles/Doxy # genXcode/_index.html for more information. # The default value is: NO. # This tag requires that the tag GENERATE_HTML is set to YES. GENERATE_DOCSET = NO # This tag determines the name of the docset feed. A documentation feed provides # an umbrella under which multiple documentation sets from a single provider # (such as a company or product suite) can be grouped. # The default value is: Doxygen generated docs. # This tag requires that the tag GENERATE_DOCSET is set to YES. DOCSET_FEEDNAME = "Doxygen generated docs" # This tag specifies a string that should uniquely identify the documentation # set bundle. This should be a reverse domain-name style string, e.g. # com.mycompany.MyDocSet. Doxygen will append .docset to the name. # The default value is: org.doxygen.Project. # This tag requires that the tag GENERATE_DOCSET is set to YES. DOCSET_BUNDLE_ID = org.doxygen.Project # The DOCSET_PUBLISHER_ID tag specifies a string that should uniquely identify # the documentation publisher. This should be a reverse domain-name style # string, e.g. com.mycompany.MyDocSet.documentation. # The default value is: org.doxygen.Publisher. # This tag requires that the tag GENERATE_DOCSET is set to YES. DOCSET_PUBLISHER_ID = org.doxygen.Publisher # The DOCSET_PUBLISHER_NAME tag identifies the documentation publisher. # The default value is: Publisher. # This tag requires that the tag GENERATE_DOCSET is set to YES. DOCSET_PUBLISHER_NAME = Publisher # If the GENERATE_HTMLHELP tag is set to YES then doxygen generates three # additional HTML index files: index.hhp, index.hhc, and index.hhk. The # index.hhp is a project file that can be read by Microsoft's HTML Help Workshop # (see: # https://www.microsoft.com/en-us/download/details.aspx?id=21138) on Windows. # # The HTML Help Workshop contains a compiler that can convert all HTML output # generated by doxygen into a single compiled HTML file (.chm). Compiled HTML # files are now used as the Windows 98 help format, and will replace the old # Windows help format (.hlp) on all Windows platforms in the future. Compressed # HTML files also contain an index, a table of contents, and you can search for # words in the documentation. The HTML workshop also contains a viewer for # compressed HTML files. # The default value is: NO. # This tag requires that the tag GENERATE_HTML is set to YES. GENERATE_HTMLHELP = NO # The CHM_FILE tag can be used to specify the file name of the resulting .chm # file. You can add a path in front of the file if the result should not be # written to the html output directory. # This tag requires that the tag GENERATE_HTMLHELP is set to YES. CHM_FILE = # The HHC_LOCATION tag can be used to specify the location (absolute path # including file name) of the HTML help compiler (hhc.exe). If non-empty, # doxygen will try to run the HTML help compiler on the generated index.hhp. # The file has to be specified with full path. # This tag requires that the tag GENERATE_HTMLHELP is set to YES. HHC_LOCATION = # The GENERATE_CHI flag controls if a separate .chi index file is generated # (YES) or that it should be included in the main .chm file (NO). # The default value is: NO. # This tag requires that the tag GENERATE_HTMLHELP is set to YES. GENERATE_CHI = NO # The CHM_INDEX_ENCODING is used to encode HtmlHelp index (hhk), content (hhc) # and project file content. # This tag requires that the tag GENERATE_HTMLHELP is set to YES. CHM_INDEX_ENCODING = # The BINARY_TOC flag controls whether a binary table of contents is generated # (YES) or a normal table of contents (NO) in the .chm file. Furthermore it # enables the Previous and Next buttons. # The default value is: NO. # This tag requires that the tag GENERATE_HTMLHELP is set to YES. BINARY_TOC = NO # The TOC_EXPAND flag can be set to YES to add extra items for group members to # the table of contents of the HTML help documentation and to the tree view. # The default value is: NO. # This tag requires that the tag GENERATE_HTMLHELP is set to YES. TOC_EXPAND = NO # If the GENERATE_QHP tag is set to YES and both QHP_NAMESPACE and # QHP_VIRTUAL_FOLDER are set, an additional index file will be generated that # can be used as input for Qt's qhelpgenerator to generate a Qt Compressed Help # (.qch) of the generated HTML documentation. # The default value is: NO. # This tag requires that the tag GENERATE_HTML is set to YES. GENERATE_QHP = NO # If the QHG_LOCATION tag is specified, the QCH_FILE tag can be used to specify # the file name of the resulting .qch file. The path specified is relative to # the HTML output folder. # This tag requires that the tag GENERATE_QHP is set to YES. QCH_FILE = # The QHP_NAMESPACE tag specifies the namespace to use when generating Qt Help # Project output. For more information please see Qt Help Project / Namespace # (see: # https://doc.qt.io/archives/qt-4.8/qthelpproject.html#namespace). # The default value is: org.doxygen.Project. # This tag requires that the tag GENERATE_QHP is set to YES. QHP_NAMESPACE = org.doxygen.Project # The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating Qt # Help Project output. For more information please see Qt Help Project / Virtual # Folders (see: # https://doc.qt.io/archives/qt-4.8/qthelpproject.html#virtual-folders). # The default value is: doc. # This tag requires that the tag GENERATE_QHP is set to YES. QHP_VIRTUAL_FOLDER = doc # If the QHP_CUST_FILTER_NAME tag is set, it specifies the name of a custom # filter to add. For more information please see Qt Help Project / Custom # Filters (see: # https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-filters). # This tag requires that the tag GENERATE_QHP is set to YES. QHP_CUST_FILTER_NAME = # The QHP_CUST_FILTER_ATTRS tag specifies the list of the attributes of the # custom filter to add. For more information please see Qt Help Project / Custom # Filters (see: # https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-filters). # This tag requires that the tag GENERATE_QHP is set to YES. QHP_CUST_FILTER_ATTRS = # The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this # project's filter section matches. Qt Help Project / Filter Attributes (see: # https://doc.qt.io/archives/qt-4.8/qthelpproject.html#filter-attributes). # This tag requires that the tag GENERATE_QHP is set to YES. QHP_SECT_FILTER_ATTRS = # The QHG_LOCATION tag can be used to specify the location (absolute path # including file name) of Qt's qhelpgenerator. If non-empty doxygen will try to # run qhelpgenerator on the generated .qhp file. # This tag requires that the tag GENERATE_QHP is set to YES. QHG_LOCATION = # If the GENERATE_ECLIPSEHELP tag is set to YES, additional index files will be # generated, together with the HTML files, they form an Eclipse help plugin. To # install this plugin and make it available under the help contents menu in # Eclipse, the contents of the directory containing the HTML and XML files needs # to be copied into the plugins directory of eclipse. The name of the directory # within the plugins directory should be the same as the ECLIPSE_DOC_ID value. # After copying Eclipse needs to be restarted before the help appears. # The default value is: NO. # This tag requires that the tag GENERATE_HTML is set to YES. GENERATE_ECLIPSEHELP = NO # A unique identifier for the Eclipse help plugin. When installing the plugin # the directory name containing the HTML and XML files should also have this # name. Each documentation set should have its own identifier. # The default value is: org.doxygen.Project. # This tag requires that the tag GENERATE_ECLIPSEHELP is set to YES. ECLIPSE_DOC_ID = org.doxygen.Project # If you want full control over the layout of the generated HTML pages it might # be necessary to disable the index and replace it with your own. The # DISABLE_INDEX tag can be used to turn on/off the condensed index (tabs) at top # of each HTML page. A value of NO enables the index and the value YES disables # it. Since the tabs in the index contain the same information as the navigation # tree, you can set this option to YES if you also set GENERATE_TREEVIEW to YES. # The default value is: NO. # This tag requires that the tag GENERATE_HTML is set to YES. DISABLE_INDEX = NO # The GENERATE_TREEVIEW tag is used to specify whether a tree-like index # structure should be generated to display hierarchical information. If the tag # value is set to YES, a side panel will be generated containing a tree-like # index structure (just like the one that is generated for HTML Help). For this # to work a browser that supports JavaScript, DHTML, CSS and frames is required # (i.e. any modern browser). Windows users are probably better off using the # HTML help feature. Via custom style sheets (see HTML_EXTRA_STYLESHEET) one can # further fine-tune the look of the index. As an example, the default style # sheet generated by doxygen has an example that shows how to put an image at # the root of the tree instead of the PROJECT_NAME. Since the tree basically has # the same information as the tab index, you could consider setting # DISABLE_INDEX to YES when enabling this option. # The default value is: NO. # This tag requires that the tag GENERATE_HTML is set to YES. GENERATE_TREEVIEW = NO # The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that # doxygen will group on one line in the generated HTML documentation. # # Note that a value of 0 will completely suppress the enum values from appearing # in the overview section. # Minimum value: 0, maximum value: 20, default value: 4. # This tag requires that the tag GENERATE_HTML is set to YES. ENUM_VALUES_PER_LINE = 4 # If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be used # to set the initial width (in pixels) of the frame in which the tree is shown. # Minimum value: 0, maximum value: 1500, default value: 250. # This tag requires that the tag GENERATE_HTML is set to YES. TREEVIEW_WIDTH = 250 # If the EXT_LINKS_IN_WINDOW option is set to YES, doxygen will open links to # external symbols imported via tag files in a separate window. # The default value is: NO. # This tag requires that the tag GENERATE_HTML is set to YES. EXT_LINKS_IN_WINDOW = NO # If the HTML_FORMULA_FORMAT option is set to svg, doxygen will use the pdf2svg # tool (see https://github.com/dawbarton/pdf2svg) or inkscape (see # https://inkscape.org) to generate formulas as SVG images instead of PNGs for # the HTML output. These images will generally look nicer at scaled resolutions. # Possible values are: png (the default) and svg (looks nicer but requires the # pdf2svg or inkscape tool). # The default value is: png. # This tag requires that the tag GENERATE_HTML is set to YES. HTML_FORMULA_FORMAT = png # Use this tag to change the font size of LaTeX formulas included as images in # the HTML documentation. When you change the font size after a successful # doxygen run you need to manually remove any form_*.png images from the HTML # output directory to force them to be regenerated. # Minimum value: 8, maximum value: 50, default value: 10. # This tag requires that the tag GENERATE_HTML is set to YES. FORMULA_FONTSIZE = 10 # Use the FORMULA_TRANSPARENT tag to determine whether or not the images # generated for formulas are transparent PNGs. Transparent PNGs are not # supported properly for IE 6.0, but are supported on all modern browsers. # # Note that when changing this option you need to delete any form_*.png files in # the HTML output directory before the changes have effect. # The default value is: YES. # This tag requires that the tag GENERATE_HTML is set to YES. FORMULA_TRANSPARENT = YES # The FORMULA_MACROFILE can contain LaTeX \newcommand and \renewcommand commands # to create new LaTeX commands to be used in formulas as building blocks. See # the section "Including formulas" for details. FORMULA_MACROFILE = # Enable the USE_MATHJAX option to render LaTeX formulas using MathJax (see # https://www.mathjax.org) which uses client side JavaScript for the rendering # instead of using pre-rendered bitmaps. Use this if you do not have LaTeX # installed or if you want to formulas look prettier in the HTML output. When # enabled you may also need to install MathJax separately and configure the path # to it using the MATHJAX_RELPATH option. # The default value is: NO. # This tag requires that the tag GENERATE_HTML is set to YES. USE_MATHJAX = NO # When MathJax is enabled you can set the default output format to be used for # the MathJax output. See the MathJax site (see: # http://docs.mathjax.org/en/v2.7-latest/output.html) for more details. # Possible values are: HTML-CSS (which is slower, but has the best # compatibility), NativeMML (i.e. MathML) and SVG. # The default value is: HTML-CSS. # This tag requires that the tag USE_MATHJAX is set to YES. MATHJAX_FORMAT = HTML-CSS # When MathJax is enabled you need to specify the location relative to the HTML # output directory using the MATHJAX_RELPATH option. The destination directory # should contain the MathJax.js script. For instance, if the mathjax directory # is located at the same level as the HTML output directory, then # MATHJAX_RELPATH should be ../mathjax. The default value points to the MathJax # Content Delivery Network so you can quickly see the result without installing # MathJax. However, it is strongly recommended to install a local copy of # MathJax from https://www.mathjax.org before deployment. # The default value is: https://cdn.jsdelivr.net/npm/mathjax@2. # This tag requires that the tag USE_MATHJAX is set to YES. MATHJAX_RELPATH = http://cdn.mathjax.org/mathjax/latest # The MATHJAX_EXTENSIONS tag can be used to specify one or more MathJax # extension names that should be enabled during MathJax rendering. For example # MATHJAX_EXTENSIONS = TeX/AMSmath TeX/AMSsymbols # This tag requires that the tag USE_MATHJAX is set to YES. MATHJAX_EXTENSIONS = # The MATHJAX_CODEFILE tag can be used to specify a file with javascript pieces # of code that will be used on startup of the MathJax code. See the MathJax site # (see: # http://docs.mathjax.org/en/v2.7-latest/output.html) for more details. For an # example see the documentation. # This tag requires that the tag USE_MATHJAX is set to YES. MATHJAX_CODEFILE = # When the SEARCHENGINE tag is enabled doxygen will generate a search box for # the HTML output. The underlying search engine uses javascript and DHTML and # should work on any modern browser. Note that when using HTML help # (GENERATE_HTMLHELP), Qt help (GENERATE_QHP), or docsets (GENERATE_DOCSET) # there is already a search function so this one should typically be disabled. # For large projects the javascript based search engine can be slow, then # enabling SERVER_BASED_SEARCH may provide a better solution. It is possible to # search using the keyboard; to jump to the search box use + S # (what the is depends on the OS and browser, but it is typically # , /