summaryrefslogtreecommitdiff
path: root/indexing
diff options
context:
space:
mode:
authorNorbert Preining <norbert@preining.info>2022-04-06 03:01:01 +0000
committerNorbert Preining <norbert@preining.info>2022-04-06 03:01:01 +0000
commit333540a9182285f9d72d7d39be3fa730c135d664 (patch)
treebdffc5aea11535dc73e81752b4a77eed105989ff /indexing
parenta4e931576165d0a4a143915f4725399272e06fee (diff)
CTAN sync 202204060301
Diffstat (limited to 'indexing')
-rw-r--r--indexing/hsindex/HsIndex.cabal58
-rw-r--r--indexing/hsindex/LICENSE674
-rw-r--r--indexing/hsindex/README150
-rw-r--r--indexing/hsindex/README.md7
-rw-r--r--indexing/hsindex/src/HsIndex/CharLists/English.hs34
-rw-r--r--indexing/hsindex/src/HsIndex/CharLists/French.hs108
-rw-r--r--indexing/hsindex/src/HsIndex/CharLists/German.hs76
-rw-r--r--indexing/hsindex/src/HsIndex/CharLists/Russian.hs73
-rw-r--r--indexing/hsindex/src/HsIndex/CharLists/SubsIEC.hs128
-rw-r--r--indexing/hsindex/src/HsIndex/CharLists/Symbols.hs30
-rw-r--r--indexing/hsindex/src/HsIndex/Files.hs156
-rw-r--r--indexing/hsindex/src/HsIndex/Functions.hs206
-rw-r--r--indexing/hsindex/src/HsIndex/Parser.hs542
-rw-r--r--indexing/hsindex/src/HsIndex/Show.hs324
-rw-r--r--indexing/hsindex/src/HsIndex/Sorting.hs246
-rw-r--r--indexing/hsindex/src/HsIndex/Types.hs205
-rw-r--r--indexing/hsindex/src/hsindex.hs395
17 files changed, 3412 insertions, 0 deletions
diff --git a/indexing/hsindex/HsIndex.cabal b/indexing/hsindex/HsIndex.cabal
new file mode 100644
index 0000000000..afe8e5c183
--- /dev/null
+++ b/indexing/hsindex/HsIndex.cabal
@@ -0,0 +1,58 @@
+-- Initial classement-multi.cabal generated by cabal init. For further
+-- documentation, see http://haskell.org/cabal/users-guide/
+-- cabal install --global
+name: HsIndex
+-- PVP summary: +-+------- breaking API changes
+-- | | +----- non-breaking API additions
+-- | | |
+version: 0.12.0
+synopsis: A program to generate indexes for LaTeX
+-- description:
+homepage: www.jeanjoux.fr
+license: GPL-3
+license-file: LICENSE
+author: Jean-Luc JOULIN
+maintainer: Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- copyright:
+-- category:
+build-type: Simple
+cabal-version: >=1.8
+
+
+library
+ hs-source-dirs: src
+ exposed-modules:
+ HsIndex.Types
+ , HsIndex.Sorting
+ , HsIndex.Show
+ , HsIndex.Parser
+ , HsIndex.Functions
+ , HsIndex.Files
+ , HsIndex.CharLists.English
+ , HsIndex.CharLists.French
+ , HsIndex.CharLists.German
+ , HsIndex.CharLists.Russian
+ , HsIndex.CharLists.Symbols
+ , HsIndex.CharLists.Substitutions
+
+ build-depends: base > 4.5
+ , parsec > 3.1
+ , directory
+ , transformers
+ , text
+
+
+executable hsindex
+ hs-source-dirs: src
+ main-Is: hsindex.hs
+ other-modules:
+ build-depends: base > 4.5
+ , parsec > 3.1
+ , cmdargs > 0.9
+ , directory
+ , transformers
+ , text
+
+
+
+
diff --git a/indexing/hsindex/LICENSE b/indexing/hsindex/LICENSE
new file mode 100644
index 0000000000..6fdf4aa7f2
--- /dev/null
+++ b/indexing/hsindex/LICENSE
@@ -0,0 +1,674 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+ The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works. By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users. We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors. You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+ To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights. Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received. You must make sure that they, too, receive
+or can get the source code. And you must show them these terms so they
+know their rights.
+
+ Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+ For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software. For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+ Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so. This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software. The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable. Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products. If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+ Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary. To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ TERMS AND CONDITIONS
+
+ 0. Definitions.
+
+ "This License" refers to version 3 of the GNU General Public License.
+
+ "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+ "The Program" refers to any copyrightable work licensed under this
+License. Each licensee is addressed as "you". "Licensees" and
+"recipients" may be individuals or organizations.
+
+ To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy. The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+ A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+ To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy. Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+ To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies. Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+ An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License. If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+ 1. Source Code.
+
+ The "source code" for a work means the preferred form of the work
+for making modifications to it. "Object code" means any non-source
+form of a work.
+
+ A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+ The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form. A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+ The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities. However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work. For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+ The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+ The Corresponding Source for a work in source code form is that
+same work.
+
+ 2. Basic Permissions.
+
+ All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met. This License explicitly affirms your unlimited
+permission to run the unmodified Program. The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work. This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+ You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force. You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright. Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+ Conveying under any other circumstances is permitted solely under
+the conditions stated below. Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+ 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+ No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+ When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+ 4. Conveying Verbatim Copies.
+
+ You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+ You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+ 5. Conveying Modified Source Versions.
+
+ You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+ a) The work must carry prominent notices stating that you modified
+ it, and giving a relevant date.
+
+ b) The work must carry prominent notices stating that it is
+ released under this License and any conditions added under section
+ 7. This requirement modifies the requirement in section 4 to
+ "keep intact all notices".
+
+ c) You must license the entire work, as a whole, under this
+ License to anyone who comes into possession of a copy. This
+ License will therefore apply, along with any applicable section 7
+ additional terms, to the whole of the work, and all its parts,
+ regardless of how they are packaged. This License gives no
+ permission to license the work in any other way, but it does not
+ invalidate such permission if you have separately received it.
+
+ d) If the work has interactive user interfaces, each must display
+ Appropriate Legal Notices; however, if the Program has interactive
+ interfaces that do not display Appropriate Legal Notices, your
+ work need not make them do so.
+
+ A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit. Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+ 6. Conveying Non-Source Forms.
+
+ You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+ a) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by the
+ Corresponding Source fixed on a durable physical medium
+ customarily used for software interchange.
+
+ b) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by a
+ written offer, valid for at least three years and valid for as
+ long as you offer spare parts or customer support for that product
+ model, to give anyone who possesses the object code either (1) a
+ copy of the Corresponding Source for all the software in the
+ product that is covered by this License, on a durable physical
+ medium customarily used for software interchange, for a price no
+ more than your reasonable cost of physically performing this
+ conveying of source, or (2) access to copy the
+ Corresponding Source from a network server at no charge.
+
+ c) Convey individual copies of the object code with a copy of the
+ written offer to provide the Corresponding Source. This
+ alternative is allowed only occasionally and noncommercially, and
+ only if you received the object code with such an offer, in accord
+ with subsection 6b.
+
+ d) Convey the object code by offering access from a designated
+ place (gratis or for a charge), and offer equivalent access to the
+ Corresponding Source in the same way through the same place at no
+ further charge. You need not require recipients to copy the
+ Corresponding Source along with the object code. If the place to
+ copy the object code is a network server, the Corresponding Source
+ may be on a different server (operated by you or a third party)
+ that supports equivalent copying facilities, provided you maintain
+ clear directions next to the object code saying where to find the
+ Corresponding Source. Regardless of what server hosts the
+ Corresponding Source, you remain obligated to ensure that it is
+ available for as long as needed to satisfy these requirements.
+
+ e) Convey the object code using peer-to-peer transmission, provided
+ you inform other peers where the object code and Corresponding
+ Source of the work are being offered to the general public at no
+ charge under subsection 6d.
+
+ A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+ A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling. In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage. For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product. A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+ "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source. The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+ If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information. But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+ The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed. Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+ Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+ 7. Additional Terms.
+
+ "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law. If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+ When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it. (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.) You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+ Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+ a) Disclaiming warranty or limiting liability differently from the
+ terms of sections 15 and 16 of this License; or
+
+ b) Requiring preservation of specified reasonable legal notices or
+ author attributions in that material or in the Appropriate Legal
+ Notices displayed by works containing it; or
+
+ c) Prohibiting misrepresentation of the origin of that material, or
+ requiring that modified versions of such material be marked in
+ reasonable ways as different from the original version; or
+
+ d) Limiting the use for publicity purposes of names of licensors or
+ authors of the material; or
+
+ e) Declining to grant rights under trademark law for use of some
+ trade names, trademarks, or service marks; or
+
+ f) Requiring indemnification of licensors and authors of that
+ material by anyone who conveys the material (or modified versions of
+ it) with contractual assumptions of liability to the recipient, for
+ any liability that these contractual assumptions directly impose on
+ those licensors and authors.
+
+ All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10. If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term. If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+ If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+ Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+ 8. Termination.
+
+ You may not propagate or modify a covered work except as expressly
+provided under this License. Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+ However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+ Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+ Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License. If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+ 9. Acceptance Not Required for Having Copies.
+
+ You are not required to accept this License in order to receive or
+run a copy of the Program. Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance. However,
+nothing other than this License grants you permission to propagate or
+modify any covered work. These actions infringe copyright if you do
+not accept this License. Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+ 10. Automatic Licensing of Downstream Recipients.
+
+ Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License. You are not responsible
+for enforcing compliance by third parties with this License.
+
+ An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations. If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+ You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License. For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+ 11. Patents.
+
+ A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based. The
+work thus licensed is called the contributor's "contributor version".
+
+ A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version. For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+ Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+ In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement). To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+ If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients. "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+ If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+ A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License. You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+ Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+ 12. No Surrender of Others' Freedom.
+
+ If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all. For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+ 13. Use with the GNU Affero General Public License.
+
+ Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work. The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+ 14. Revised Versions of this License.
+
+ The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+ Each version is given a distinguishing version number. If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation. If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+ If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+ Later license versions may give you additional or different
+permissions. However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+ 15. Disclaimer of Warranty.
+
+ THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+ 16. Limitation of Liability.
+
+ IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+ 17. Interpretation of Sections 15 and 16.
+
+ If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ HsIndex
+ Copyright (C) 2019-2020 Jean-Luc JOULIN
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+ If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+ HsIndex Copyright (C) 2019-2020 Jean-Luc JOULIN
+ This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+ You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<http://www.gnu.org/licenses/>.
+
+ The GNU General Public License does not permit incorporating your program
+into proprietary programs. If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library. If this is what you want to do, use the GNU Lesser General
+Public License instead of this License. But first, please read
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.
diff --git a/indexing/hsindex/README b/indexing/hsindex/README
new file mode 100644
index 0000000000..d18cf480ab
--- /dev/null
+++ b/indexing/hsindex/README
@@ -0,0 +1,150 @@
+ _ _ _____ _____ __ __
+ | | | | |_ _| | __ \ \ \ / /
+ | |__| |___ | | _ __ | | | | ___ \ V /
+ | __ / __| | | | '_ \| | | |/ _ \ > <
+ | | | \__ \_| |_| | | | |__| | __// . \
+ |_| |_|___/_____|_| |_|_____/ \___/_/ \_\
+
+ Copyright (c) 2018-2020 Jean-Luc JOULIN <jeanjoux@orange.fr>
+
+
+HsIndeX is a general purpose index generator for LaTeX and XeTeX. This release contains the binary of version 0.11.1 and this README file
+
+
+
+USAGE
+=====
+The usage of HsIndex is the same as "makeindex", it must be used after the first compilation of you LaTeX documents with "imakeidx" package and before the second pass.
+
+Basic usage
+-----------
+
+A english index can be generated with :
+
+>>> hsindex english -i input.idx -o output.ind
+
+A French index can be generated with :
+
+>>> hsindex french -i input.idx -o output.ind
+
+
+Advanced usage
+--------------
+
+A custom style can be provided with:
+
+>>> hsindex english --style="myindexstyle.sty" --input=input.idx --output=output.ind
+
+A custom language definition can be used with:
+
+
+>>> hsindex custom --def="mylanguage.def" --style="myindexstyle.sty" --input=input.idx --output=output.ind
+
+Successives pages numbers can be converted into ranges with the option --range. 3 or more succesives pages numbers will be converted into a range using a specific delimiter.
+
+>>> hsindex english --range --style="myindexstyle.sty" --input=input.idx --output=output.ind
+
+Style file
+==========
+
+A style file is composed with several tags containing the LaTeX commands to be executed at specific locations of the index. The tags are almost the same than the "makeindex" program with a few exceptions.
+
+This is the standard style implemented in the hsindex program.
+
+
+Tags setting the beginning and the end of the index.
+
+>>> preamble "\begin{theindex}\\n"
+>>> postamble "\\n\\n\end{theindex}\\n"
+
+
+Tags setting the first layer letters heading (First letter) The "headings_flag" is a bit different from "makeindex" in the where it can be set to :
+ 0 or None : No heading showed
+ 1 or UpperCase : First letter in upper case.
+-1 or LowerCase : First letter in lower case.
+
+>>> headings_flag UpperCase
+>>> heading_prefix "{\vspace{1.5cm}\huge{\textbf{"
+>>> heading_suffix "}}\hfill}\\nopagebreak\\n"
+
+
+
+Tags setting the second layer letters heading (Two first letters) These tags don't exist with "makeindex":
+
+>>> headings_flag1 None
+>>> heading_prefix1 ""
+>>> heading_suffix1 ""
+
+
+Tags to set the title of the Symbol and Number sections:
+
+>>> symhead_positive "Symbols"
+>>> numhead_positive "Numbers"
+
+Tags to set the skip between two group of items of the same layer.
+The "group_skip1" don't exist in "makeindex":
+>>> group_skip "\\n \indexspace\\n" -- "\\n\\n \indexspace\\n"
+>>> group_skip1 ""
+
+
+The following tags are used to define the LaTeX commands to declare items, subitems and subsubitems:
+>>> item_0 "\\n \item "
+>>> item_1 "\\n \subitem "
+>>> item_2 "\\n \subsubitem "
+>>> item_01 "\\n \subitem "
+>>> item_12 "\\n \subsubitem "
+
+The following tags are used to define the delimiters betwen items and pages numbers:
+>>> delim_0 ", " -- \hfill
+>>> delim_1 ", "
+>>> delim_2 ", "
+>>> delim_n ", "
+
+
+
+Language file
+=============
+
+The language file allow the user to define a new language and its custom letters order and substitutions.
+
+
+The LETTERS section allow the user to give the list of characters considered as letters and their sorting order. This section is mandatory.
+
+>>> LETTERS
+>>> abcdefghijklmnopqrstuvwxyz
+
+
+The NUMBERS section allow the user to give the list of characters considered as numbers and their sorting order. This section is optional.
+
+>>> NUMBERS
+>>> 0123456789
+
+The SYMBOLS section allow the user to give the list of characters considered as symbols and their sorting order. This section is optional.
+
+>>> SYMBOLS
+>>> ~*@&
+
+The SUBSTITUTIONS section define the characters substitutions to perform. These substitutions are taken into consideration to sort and classify the items. The substituions bellow means that th "œ" character will be replaced by "oe", the accentuated "ê" and "é" will be treated as an "e" and the "_" and "-" will be treated as a space " ".
+
+>>> SUBSTITUTIONS
+>>> œ->oe
+>>> ê->e
+>>> é->e
+>>> _->
+>>> -->
+
+
+Feedback and improvement
+========================
+
+If you whish to improve this program and add languages or features, this project is available on gitlab :
+
+https://gitlab.com/JeanJouX/hsindex
+
+I hope this program will be usefull for you !
+
+
+
+
+
+
diff --git a/indexing/hsindex/README.md b/indexing/hsindex/README.md
new file mode 100644
index 0000000000..1452a0157d
--- /dev/null
+++ b/indexing/hsindex/README.md
@@ -0,0 +1,7 @@
+# HsIndex
+
+**HsIndex** is an index generator for **LaTeX**, **XeLaTeX** written with **Haskell**.
+
+It parse **imakeidx** *.idx files and generate *.ind LaTeX index files.
+
+This an alternative to **xindy**. \ No newline at end of file
diff --git a/indexing/hsindex/src/HsIndex/CharLists/English.hs b/indexing/hsindex/src/HsIndex/CharLists/English.hs
new file mode 100644
index 0000000000..27adf8186e
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/CharLists/English.hs
@@ -0,0 +1,34 @@
+-- |
+-- Module : HsIndex.CharLists.English
+-- Copyright : Jean-Luc JOULIN 2018-2019
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The letters, numbers and symbol definition for the english language.
+
+
+module HsIndex.CharLists.English where
+
+import HsIndex.Types
+import HsIndex.Functions
+import HsIndex.CharLists.Symbols
+import HsIndex.CharLists.French
+
+
+
+ordEnglish = lstLatinLetter
+
+ordEnglishUpperLower = upperLower lstLatinLetter
+
+
+-- |
+langDefEnglish :: LangDef
+langDefEnglish = LangDef
+ { lstLetters = lstSpace ++ ordEnglishUpperLower
+ , lstNumbers = lstDigit
+ , lstSymbols = Nothing
+ , lstSubs = subsFrenchUpperLower++subsSymb
+ , lstSecOrder = [Symbols, Numbers, Letters]
+ }
+
diff --git a/indexing/hsindex/src/HsIndex/CharLists/French.hs b/indexing/hsindex/src/HsIndex/CharLists/French.hs
new file mode 100644
index 0000000000..a2b54e0a54
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/CharLists/French.hs
@@ -0,0 +1,108 @@
+-- |
+-- Module : HsIndex.CharLists.French
+-- Copyright : Jean-Luc JOULIN 2018-2019
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The letters, numbers and symbol definition for the french language.
+
+
+module HsIndex.CharLists.French where
+
+import HsIndex.Functions
+import HsIndex.CharLists.Symbols
+import HsIndex.Types
+
+lstSubsLatin = take 1
+
+
+ordFrench = lstLatinLetter
+
+ordFrenchUpperLower = upperLower lstLatinLetter
+
+
+
+
+lstLatinLetter =
+ [ 'a'
+ , 'b'
+ , 'c'
+ , 'd'
+ , 'e'
+ , 'f'
+ , 'g'
+ , 'h'
+ , 'i'
+ , 'j'
+ , 'k'
+ , 'l'
+ , 'm'
+ , 'n'
+ , 'o'
+ , 'p'
+ , 'q'
+ , 'r'
+ , 's'
+ , 't'
+ , 'u'
+ , 'v'
+ , 'w'
+ , 'x'
+ , 'y'
+ , 'z'
+ ]
+
+
+subsFrenchUpperLower = replaUpperLower subsFrench
+
+
+
+
+subsFrench =
+ [ ('à', "a")
+ , ('â', "a")
+ , ('å', "a")
+ , ('ä', "a")
+
+ , ('ç', "c")
+
+ , ('é', "e")
+ , ('è', "e")
+ , ('ê', "e")
+ , ('ë', "e")
+
+ , ('î', "i")
+ , ('ï', "i")
+
+ , ('ô', "o")
+ , ('ö', "o")
+
+ , ('ù', "u")
+ , ('û', "u")
+ , ('ü', "u")
+
+
+ , ('æ', "ae")
+ , ('œ', "oe")
+ ]
+
+
+subsSymb =
+ [ ('-', " ")
+ , ('_', " ")
+ , ('\\', " ")
+ ]
+
+
+
+langDefFrench = LangDef
+ { lstLetters = lstSpace ++ ordFrenchUpperLower -- ++ (map substituted subsFrenchUpperLower)
+ , lstNumbers = lstDigit
+ , lstSymbols = Nothing
+ , lstSubs = subsFrenchUpperLower++subsSymb
+ , lstSecOrder = [Symbols, Numbers, Letters]
+ }
+
+
+
diff --git a/indexing/hsindex/src/HsIndex/CharLists/German.hs b/indexing/hsindex/src/HsIndex/CharLists/German.hs
new file mode 100644
index 0000000000..cb7df65686
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/CharLists/German.hs
@@ -0,0 +1,76 @@
+-- |
+-- Module : HsIndex.CharLists.German
+-- Copyright : Jean-Luc JOULIN 2018-2019
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The letters, numbers and symbol definition for the german language.
+
+
+module HsIndex.CharLists.German where
+
+
+import HsIndex.Functions
+import HsIndex.Types
+import HsIndex.CharLists.Symbols
+import HsIndex.CharLists.French ( lstLatinLetter )
+
+
+
+ordGerman = lstLatinLetter
+
+ordGermanLowerUpper = lowerUpper lstLatinLetter
+
+lstGermanLetter =
+ [ 'a'
+ , 'b'
+ , 'c'
+ , 'd'
+ , 'e'
+ , 'f'
+ , 'g'
+ , 'h'
+ , 'i'
+ , 'j'
+ , 'k'
+ , 'l'
+ , 'm'
+ , 'n'
+ , 'o'
+ , 'p'
+ , 'q'
+ , 'r'
+ , 's'
+ , 'ß'
+ , 't'
+ , 'u'
+ , 'v'
+ , 'w'
+ , 'x'
+ , 'y'
+ , 'z'
+ ]
+
+
+charSubsGerman =
+ [ ('æ', "ae")
+ , ('ä', "a")
+ , ('ö', "o")
+ , ('ß', "ss")
+ , ('ü', "u")
+ ]
+
+
+
+
+langDefGerman = LangDef
+ { lstLetters = lstSpace ++ ordGermanLowerUpper -- ++ map substituted charSubsGerman
+ , lstNumbers = lstDigit
+ , lstSymbols = Nothing
+ , lstSubs = charSubsGerman
+ , lstSecOrder = [Symbols, Letters, Numbers]
+ }
+
+
+
diff --git a/indexing/hsindex/src/HsIndex/CharLists/Russian.hs b/indexing/hsindex/src/HsIndex/CharLists/Russian.hs
new file mode 100644
index 0000000000..1e9c3c96dc
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/CharLists/Russian.hs
@@ -0,0 +1,73 @@
+-- |
+-- Module : HsIndex.CharLists.Russian
+-- Copyright : Jean-Luc JOULIN 2018-2019
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The letters, numbers and symbol definition for the russian language.
+
+
+module HsIndex.CharLists.Russian where
+
+import HsIndex.Functions
+import HsIndex.Types
+import HsIndex.CharLists.Symbols
+
+ordRussian = lstCyrillic
+
+ordRussianUpperLower = upperLower lstCyrillic
+
+-- | List of cyrillic characters.
+lstCyrillic =
+ [ 'а'
+ , 'б'
+ , 'в'
+ , 'г'
+ , 'д'
+ , 'е'
+ , 'ё'
+ , 'ж'
+ , 'з'
+ , 'и'
+ , 'й'
+ , 'к'
+ , 'л'
+ , 'м'
+ , 'н'
+ , 'о'
+ , 'п'
+ , 'р'
+ , 'с'
+ , 'т'
+ , 'у'
+ , 'ф'
+ , 'х'
+ , 'ц'
+ , 'ч'
+ , 'ш'
+ , 'щ'
+ , 'ъ'
+ , 'ы'
+ , 'ь'
+ , 'э'
+ , 'ю'
+ , 'я'
+ ]
+
+
+
+
+
+lettersRussian = lstCyrillic
+
+langDefRussian = LangDef
+ { lstLetters = lstSpace ++ ordRussianUpperLower
+ , lstNumbers = lstDigit
+ , lstSymbols = Nothing
+ , lstSubs = []
+ , lstSecOrder = [Symbols, Numbers, Letters]
+ }
+
+
+
diff --git a/indexing/hsindex/src/HsIndex/CharLists/SubsIEC.hs b/indexing/hsindex/src/HsIndex/CharLists/SubsIEC.hs
new file mode 100644
index 0000000000..33813a6ce8
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/CharLists/SubsIEC.hs
@@ -0,0 +1,128 @@
+-- |
+-- Module : HsIndex.CharLists.SubsIEC
+-- Copyright : Jean-Luc JOULIN 2018-2019
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The list of imakeidx IEC substitution hard-coded for all languages.
+
+
+module HsIndex.CharLists.SubsIEC where
+
+
+-- | List of characters substitutions for parsing the 'imakeindex' output file.
+lstLaTeXSubs =
+ [ ("'e" , 'é')
+ , ("`e" , 'è')
+ , ("^e" , 'ê')
+ , ("\"e" , 'ë')
+ , ("`a" , 'à')
+ , ("^a" , 'â')
+ , ("\"a" , 'ä')
+ , ("\"\\i" , 'ï')
+ , ("^\\i " , 'î')
+ , ("^u" , 'û')
+ , ("\"u" , 'ü')
+ , ("^o" , 'ô')
+ , ("\"o" , 'ö')
+ , ("'E" , 'É')
+ , ("`E" , 'È')
+ , ("^E" , 'Ê')
+ , ("\"E" , 'Ë')
+ , ("`A" , 'À')
+ , ("^A" , 'Â')
+ , ("\"A" , 'Ä')
+ , ("\"\\I" , 'Ï')
+ , ("^\\I " , 'Î')
+ , ("^U" , 'Û')
+ , ("\"U" , 'Ü')
+ , ("^O" , 'Ô')
+ , ("\"O" , 'Ö')
+ , ("r a" , 'å')
+ , ("ae" , 'æ')
+ , ("oe" , 'œ')
+ , ("c c" , 'ç')
+ , ("ss" , 'ß')
+ , ("r A" , 'Å')
+ , ("AE" , 'Æ')
+ , ("OE" , 'Œ')
+ , ("cyra" , 'а')
+ , ("cyrb" , 'б')
+ , ("cyrv" , 'в')
+ , ("cyrg" , 'г')
+ , ("cyrd" , 'д')
+ , ("cyre" , 'е')
+ , ("cyryo" , 'ё')
+ , ("cyrzh" , 'ж')
+ , ("cyrz" , 'з')
+ , ("cyri" , 'и')
+ , ("cyrishrt", 'й')
+ , ("cyrk" , 'к')
+ , ("cyrl" , 'л')
+ , ("cyrm" , 'м')
+ , ("cyrn" , 'н')
+ , ("cyro" , 'о')
+ , ("cyrp" , 'п')
+ , ("cyrr" , 'р')
+ , ("cyrs" , 'с')
+ , ("cyrt" , 'т')
+ , ("cyru" , 'у')
+ , ("cyrf" , 'ф')
+ , ("cyrh" , 'х')
+ , ("cyrc" , 'ц')
+ , ("cyrch" , 'ч')
+ , ("cyrsh" , 'ш')
+ , ("cyrshch" , 'щ')
+ , ("cyrhrdsn", 'ъ')
+ , ("cyrery" , 'ы')
+ , ("cyrsftsn", 'ь')
+ , ("cyrerev" , 'э')
+ , ("cyryu" , 'ю')
+ , ("cyrya" , 'я')
+ , ("CYRA" , 'А')
+ , ("CYRB" , 'Б')
+ , ("CYRV" , 'В')
+ , ("CYRG" , 'Г')
+ , ("CYRD" , 'Д')
+ , ("CYRE" , 'Е')
+ , ("CYRYO" , 'Ё')
+ , ("CYRZH" , 'Ж')
+ , ("CYRZ" , 'З')
+ , ("CYRI" , 'И')
+ , ("CYRISHRT", 'Й')
+ , ("CYRK" , 'К')
+ , ("CYRL" , 'Л')
+ , ("CYRM" , 'М')
+ , ("CYRN" , 'Н')
+ , ("CYRO" , 'О')
+ , ("CYRP" , 'П')
+ , ("CYRR" , 'Р')
+ , ("CYRS" , 'С')
+ , ("CYRT" , 'Т')
+ , ("CYRU" , 'У')
+ , ("CYRF" , 'Ф')
+ , ("CYRH" , 'Х')
+ , ("CYRC" , 'Ц')
+ , ("CYRCH" , 'Ч')
+ , ("CYRSH" , 'Ш')
+ , ("CYRSHCH" , 'Щ')
+ , ("CYRHRDSN", 'Ъ')
+ , ("CYRERY" , 'Ы')
+ , ("CYRSFTSN", 'Ь')
+ , ("CYREREV" , 'Э')
+ , ("CYRYU" , 'Ю')
+ , ("CYRYA" , 'Я')
+
+
+ , ("textquoteleft" , '‘')
+ , ("textquoteright" , '’')
+ , ("nobreakspace" , ' ')
+
+
+ ]
+
+
+
+
+
diff --git a/indexing/hsindex/src/HsIndex/CharLists/Symbols.hs b/indexing/hsindex/src/HsIndex/CharLists/Symbols.hs
new file mode 100644
index 0000000000..813bacfbde
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/CharLists/Symbols.hs
@@ -0,0 +1,30 @@
+-- |
+-- Module : HsIndex.CharLists.Symbols
+-- Copyright : Jean-Luc JOULIN 2018-2019
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The list of symbols for all languages.
+
+
+module HsIndex.CharLists.Symbols where
+
+
+-- | Allowed symbols.
+allowedSymb = " &~\"'()[]{}<>*+/`^#@°=$£µ%§:;.,?"
+
+-- | Forbidden symbols.
+--
+-- These symbols
+forbiddenSymb = "!|\n\r" -- "!|{}\n\r"
+
+-- | The hyphens symbols.
+lstHyph = "-_"
+
+-- | List of digits.
+lstDigit = "0123456789"
+
+lstSpace = " "
+
+
diff --git a/indexing/hsindex/src/HsIndex/Files.hs b/indexing/hsindex/src/HsIndex/Files.hs
new file mode 100644
index 0000000000..5f1d15c3ea
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/Files.hs
@@ -0,0 +1,156 @@
+--
+-- GNU General Public License (GPLv3)
+--
+-- THIS SOFTWARE IS PROVIDED BY THE AUTHOR(S) “AS IS” AND ANY EXPRESS OR
+-- IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
+-- OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
+-- IN NO EVENT SHALL THE AUTHOR(S) BE LIABLE FOR ANY DIRECT, INDIRECT,
+-- INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
+-- BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
+-- USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
+-- ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+-- (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
+-- THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+-- |
+-- Module : HsIndex.Files
+-- Copyright : Jean-Luc JOULIN 2018-2019
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- Module for reading input and style files.
+--
+-- This module also provide the function to write output file.
+--
+
+
+
+
+module HsIndex.Files
+ (
+ -- * Read functions
+ readIndexFile
+ , readStyleFile
+ , readDefinitionFile
+ , readAllFile
+
+ -- * Writing function
+ , writeIndex
+ )
+ where
+
+import Data.Char
+import HsIndex.Functions
+import HsIndex.Show
+import HsIndex.Parser
+import HsIndex.Types
+import Text.Parsec
+import Text.Parsec.String
+import System.Directory ( doesFileExist )
+import qualified Data.Text as T
+import qualified Data.Text.IO as T
+import Data.Functor.Identity
+
+
+-- | Read an index input file.
+readIndexFile :: FilePath -- ^ The path to the index file.
+ -> ParsecT String () Identity t -- ^ The parser to apply on the file to extract datas.
+ -> (t -> IO ()) -- ^ List of operations to perform on parsed datas.
+ -> IO ()
+readIndexFile fidx parsfun fun = do
+ e <- doesFileExist fidx
+ if e
+ then do
+ f <- readFile fidx
+ case parse parsfun "(stdin)" f of
+ Left err -> do
+ putStrLn $ "/!\\ ERROR reading Index file : " ++ fidx
+ print err
+ Right resu -> fun resu
+ else
+ putStrLn
+ $ "/!\\ ERROR the Index file : "
+ ++ fidx
+ ++ " does not exist !\n"
+
+
+-- | Read a style input file
+--
+-- If no path is provided for the style file, the standard style 'styleBasic' is applied.
+--
+readStyleFile :: IndexType -- ^ The type of style.
+ -> (IndexStyle -> IO ()) -- ^ Operations to apply with the parsed style.
+ -> IO ()
+readStyleFile StyleBasic fun = do
+ putStrLn "Using the default basic style"
+ fun styleBasic
+
+readStyleFile StyleDouble fun = do
+ putStrLn "Using the default double letters style"
+ fun styleDoubleHeading
+
+
+
+readStyleFile (Stylecustom fsty) fun = do
+ e <- doesFileExist fsty
+ if e
+ then do
+ f <- readFile fsty
+ case parse (parseStyleFile styleBasic) "(stdin)" f of
+ Left err -> do
+ putStrLn $ "/!\\ ERROR reading Style file : " ++ fsty
+ print err
+ Right resu -> fun resu
+ else
+ putStrLn
+ $ "/!\\ ERROR the Style file : "
+ ++ fsty
+ ++ " does not exist !\n"
+
+
+-- | Read a language definition input file.
+readDefinitionFile :: FilePath -- ^ The path to the definition file.
+ -> (LangDef -> IO ()) -- ^ Operations to apply with the parsed style.
+ -> IO ()
+readDefinitionFile fdef fun = do
+ e <- doesFileExist fdef
+ if e
+ then do
+ f <- readFile fdef
+ case runParser (parseLanguageFile) emptyPermState "(stdin)" f of
+ Left err -> do
+ putStrLn $ "/!\\ ERROR reading Definition file : " ++ fdef
+ print err
+ Right resu -> fun resu
+ else
+ putStrLn
+ $ "/!\\ ERROR the Definition file : "
+ ++ fdef
+ ++ " does not exist !\n"
+
+
+-- | Read both an index input file and style file.
+--
+-- If no path is provided for the style file, the standard style 'styleBasic' is applied.
+--
+readAllFile :: FilePath -- ^ The path to the index file.
+ -> IndexType -- ^ The type of index.
+ -> ParsecT String () Identity t -- ^ The parser to apply on the index file.
+ -> (t -> IndexStyle -> IO ()) -- ^ Operations to apply with the parsed index data and style.
+ -> IO ()
+readAllFile fidx mbfsty parsfun fun =
+ readIndexFile fidx parsfun (readStyleFile mbfsty . fun)
+
+
+-- | Write the sorted entries in a output file with the format provided in the `IndexStyle`.
+writeIndex :: FilePath -- ^ The path to the output file
+ -> IndexStyle -- ^ The style file.
+ -> Bool -- ^ Automatic conversion to pages ranges
+ -> Index -- ^ The index.
+ -> IO ()
+writeIndex file style rng sec = do
+ putStrLn $ "Writing index to File : " ++ file
+ T.writeFile file $ showIndex style rng sec
+
+
diff --git a/indexing/hsindex/src/HsIndex/Functions.hs b/indexing/hsindex/src/HsIndex/Functions.hs
new file mode 100644
index 0000000000..344a1c515e
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/Functions.hs
@@ -0,0 +1,206 @@
+{-# LANGUAGE OverloadedStrings #-}
+-- |
+-- Module : HsIndex.Files
+-- Copyright : Jean-Luc JOULIN 2018-2020
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- This module provide miscellaneous functions for comparing
+-- and cutting list of IndexItem
+
+
+
+
+module HsIndex.Functions (
+ splitIndex
+ , concatPagesItems
+ , substituteCharInString
+ -- ~ , upperLower
+ , upperLower
+ , lowerUpper
+ , replaUpper
+ , substituted
+ , literalNewLine
+ , replaUpperLower
+ , sepArobase
+ ) where
+
+
+import HsIndex.Types
+import Data.List
+import Data.Char
+import HsIndex.Show
+import qualified Data.Text as T
+
+
+-- | Convert a list of 'IndexItem's into an 'Index' by splitting the liste
+-- according to the first letter of the equivalent name and section (layer 1).
+--
+-- The input list of 'IndexItem' must be sorted with 'sortItems' before
+-- using this function.
+--
+splitIndex :: IndexStyle -- ^ The style of the 'Index'.
+ -> [IndexItem] -- ^ List of 'IndexItem's to sort in a 'Index'.
+ -> Index -- ^ The final index.
+splitIndex style [] = []
+splitIndex style lst@(x : xs) = if null d
+ then splitIndex style f
+ else IndexSection tit (splitIndex' style d) : splitIndex style f
+ where
+ -- ~ (d, f) = span (\c -> areItemsEqual False (itemEqui c) (itemEqui x)) lst
+ (d, f) = partition (\c -> areItemsEqual False (itemEqui c) (itemEqui x)) lst
+ tit = showHeading1 style (itemEqui (head d))
+
+
+-- | Test if layer 1 equivalent names of two items are equals.
+areItemsEqual :: Bool -- ^ Test is Case sensitive
+ -> (Section, T.Text) -- ^ First equivalent name to compare.
+ -> (Section, T.Text) -- ^ Second equivalent name to compare.
+ -> Bool
+areItemsEqual True (Letters, a) (Letters, b) = T.take 1 a == T.take 1 b -- Test if the first letters are the same (Case sensitive)
+areItemsEqual False (Letters, a) (Letters, b) = T.toUpper (T.take 1 a) == T.toUpper (T.take 1 b) -- Test if the first letters are the same (Case sensitive)
+areItemsEqual _ (Numbers, a) (Numbers, b) = True -- Numbers are always number in L1
+areItemsEqual _ (Symbols, a) (Symbols, b) = True -- Symbols are always symbols in L1
+areItemsEqual _ _ _ = False
+
+
+-- | Convert a list of 'IndexItem's into an 'Index' by splitting the liste
+-- according to the first two letters of the equivalent name and section (layer 2).
+--
+-- The input list of 'IndexItem' must be sorted with 'sortItems' before
+-- using this function.
+--
+splitIndex' :: IndexStyle -- ^ The style of the 'Index'.
+ -> [IndexItem] -- ^ List of 'IndexItem's to sort in a 'Index'.
+ -> [IndexSubSection]
+splitIndex' style [] = []
+splitIndex' style lst@(x : xs) = if null d
+ then splitIndex' style f
+ else IndexSubSection tit d : splitIndex' style f
+ where
+ -- ~ (d, f) = span (\c -> areItemsEqual' False (itemEqui c) (itemEqui x)) lst
+ (d, f) = partition (\c -> areItemsEqual' False (itemEqui c) (itemEqui x)) lst
+ tit = showHeading2 style (itemEqui (head d))
+
+
+-- | Test if layer 2 equivalent names of two items are equals.
+areItemsEqual' True (Letters, a) (Letters, b) = T.take 2 a == T.take 2 b -- Test if the two first letters are the same (Case sensitive)
+areItemsEqual' True (Numbers, a) (Numbers, b) = T.take 1 a == T.take 1 b -- Test if the first numbers are the same (Case sensitive)
+areItemsEqual' True (Symbols, a) (Symbols, b) = T.take 1 a == T.take 1 b -- Test if the first symbols are the same (Case sensitive)
+areItemsEqual' False (Letters, a) (Letters, b) = T.toUpper (T.take 2 a) == T.toUpper (T.take 2 b) -- Test if the two first letters are the same (Case insensitive)
+areItemsEqual' False (Numbers, a) (Numbers, b) = T.toUpper (T.take 1 a) == T.toUpper (T.take 1 b) -- Test if the first numbers are the same (Case insensitive)
+areItemsEqual' False (Symbols, a) (Symbols, b) = T.toUpper (T.take 1 a) == T.toUpper (T.take 1 b) -- Test if the first symbols are the same (Case insensitive)
+areItemsEqual' _ _ _ = False
+
+
+-- | Extract the first letters of a string after letters substitutions.
+firstLetters :: Int
+ -> T.Text
+ -> T.Text
+firstLetters n "" = error "no letters"
+firstLetters n str = T.take n str
+
+
+-- | Substitute the string "\\n" into a String by a '\n' newline character.
+literalNewLine :: T.Text -> T.Text
+literalNewLine str = T.replace (T.pack "\\\\n") (T.pack "\n") str
+
+
+
+-- | Concatenate pages numbers of entries.
+--
+-- Pages numbers are sorted and filtered to get each page number once.
+concatPagesItems :: [IndexItem]
+ -> [IndexItem]
+concatPagesItems [] = []
+concatPagesItems lst@(IndexItem nam equ com pag sub : xs) = IndexItem nam equ com pages subentries : concatPagesItems a
+ where
+ (p, a) = partition (\e -> itemName e == nam) xs
+ pages = nub $ sort $ concat $ pag : map itemPages p
+ subentries = concatPagesSubItems $ concat $ sub : map itemContent p
+
+
+-- | Concatenate pages numbers of subentries.
+--
+-- Pages numbers are sorted and filtered to get each page number once.
+concatPagesSubItems :: [IndexSubItem]
+ -> [IndexSubItem]
+concatPagesSubItems [] = []
+concatPagesSubItems lst@(IndexSubItem nam equ com pag subsub : xs) = IndexSubItem nam equ com pages subsubentries
+ : concatPagesSubItems a
+ where
+ (p, a) = partition (\e -> subItemName e == nam) xs
+ pages = nub $ sort $ concat $ pag : map subItemPages p
+ subsubentries = concatPagesSubSubItems $ concat $ subsub : map subItemContent p
+
+
+-- | Concatenate pages numbers of subsubentries.
+--
+-- Pages numbers are sorted and filtered to get each page number once.
+concatPagesSubSubItems :: [IndexSubSubItem]
+ -> [IndexSubSubItem]
+concatPagesSubSubItems [] = []
+concatPagesSubSubItems lst@(IndexSubSubItem nam equ com pag : xs) = IndexSubSubItem nam equ com pages
+ : concatPagesSubSubItems a
+ where
+ (p, a) = partition (\e -> subSubItemName e == nam) xs
+ pages = nub $ sort $ concat $ pag : map subSubItemPages p
+
+
+-- | Substitute 'Char's listed in the 'CharSubs' list in a String
+--
+-- >>> substituteCharInString [CharSubs 'œ' "oe"] "oeil"
+--
+substituteCharInString :: [(Char,String)] -- ^ The list of substitutions
+ -> T.Text -- ^ The string where to perform substitutions
+ -> T.Text
+substituteCharInString repl text = replaces repl text
+
+
+-- | Set the substitutions to uppercase.
+replaUpper :: [(Char, String)] -> [(Char, String)]
+replaUpper = map (\(a, b) -> (toUpper a, map toUpper b))
+
+-- | Set the substitutions to lowercase.
+replaLower :: [(Char, String)] -> [(Char, String)]
+replaLower = map (\(a, b) -> (toLower a, map toLower b))
+
+
+
+
+
+upperLower [] = []
+upperLower (x : xs) = toUpper x : toLower x : upperLower xs
+
+
+lowerUpper [] = []
+lowerUpper (x : xs) = toLower x : toUpper x : lowerUpper xs
+
+
+replaUpperLower lst = replaUpper lst ++ replaLower lst
+
+
+substituted (a, b) = a -- TODO A supprimer
+
+
+replaces repl text = foldl (\t (r, s) -> T.replace (T.pack [r]) (T.pack s) t) text repl
+
+
+sepArobase str | null item = (str, "")
+ | otherwise = (tail item, equ)
+ where
+ equ = takeWhile (/= '@') str
+ item = dropWhile (/= '@') str
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/indexing/hsindex/src/HsIndex/Parser.hs b/indexing/hsindex/src/HsIndex/Parser.hs
new file mode 100644
index 0000000000..35063ab43b
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/Parser.hs
@@ -0,0 +1,542 @@
+-- |
+-- Module : HsIndex.Parser
+-- Copyright : Jean-Luc JOULIN 2018-2020
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The parsing functions for the hsindex program.
+
+
+
+module HsIndex.Parser
+ (
+ -- * Parsing the index file
+
+
+ -- * Parsing the style file
+
+
+ -- * Parsing the custom language definition file
+ --
+ -- ** Description of a custom file
+ --
+ -- A custom language can be defined with a specific file.
+ -- This file must respect the following format and contain in any order :
+ --
+ -- 1. A mandatory ordered list of letters describing the alphabet.
+ --
+ -- > LETTERS
+ -- > abcdefghijkl
+ --
+ -- 2. An optional ordered list of numbers.
+ --
+ -- > NUMBERS
+ -- > 0123456789
+ --
+ -- 3. An optional ordered list of symbols.
+ --
+ -- > SYMBOLS
+ -- > 0123456789
+ --
+ -- 4. An optional substitution list. This list describe the character substitutions
+ -- to perform before sorting the words.
+ --
+ -- > SUBSTITUTIONS
+ -- > œ->oe
+ -- > à->a
+ -- > ê->e
+ --
+ -- ** example of custom file
+ --
+ --
+ styleBasic
+ , styleDoubleHeading
+ , parseStyleFile
+ , parseLanguageFile
+ , parseIndexFile
+ , emptyDef
+ ) where
+
+
+import Data.Char
+import Data.Functor.Identity
+import Data.Functor
+import HsIndex.CharLists.French
+import HsIndex.CharLists.Russian
+import HsIndex.CharLists.SubsIEC
+import HsIndex.CharLists.Symbols
+import HsIndex.Functions
+ ( literalNewLine
+ -- ~ , upperLower
+ -- ~ , replaUpperLower
+ , sepArobase
+ )
+import HsIndex.Types
+import qualified Data.Text as T
+import Text.Parsec
+import Text.Parsec.Perm
+import Text.Parsec.Text
+
+
+
+-- | The default 'IndexStyle' applied to an index.
+--
+-- This default style have :
+--
+-- * Basic preamble and postamble
+--
+-- * Uppercase Layer 0 heading
+--
+-- * No Layer 1 heading
+--
+styleBasic = IndexStyle
+ { idxPreamble = T.pack "\\begin{theindex}\n"
+ , idxPostamble = T.pack "\n\n\\end{theindex}\n"
+ , idxHeadingFlag0 = UpperCase
+ , idxHeadingFlag1 = None
+ , idxHeadingPreL0 = T.pack "{\\vspace{1.5cm}\\huge{\\textbf{"
+ , idxHeadingSufL0 = T.pack "}}\\hfill}\\nopagebreak\n"
+ , idxHeadingPreL1 = T.pack "" -- TODO Remplacer par empty
+ , idxHeadingSufL1 = T.pack ""
+ , idxSymhead = T.pack "Symbols"
+ , idxNumhead = T.pack "Numbers"
+ , idxGroupSkip0 = T.pack "\n \\indexspace\n" -- "\n\n \\indexspace\n"
+ , idxGroupSkip1 = T.pack ""
+ , idxItem0 = T.pack "\n \\item "
+ , idxItem1 = T.pack "\n \\subitem "
+ , idxItem2 = T.pack "\n \\subsubitem "
+ , idxItem01 = T.pack "\n \\subitem "
+ , idxItem12 = T.pack "\n \\subsubitem "
+ , idxDelim0 = T.pack ", " -- \\hfill
+ , idxDelim1 = T.pack ", "
+ , idxDelim2 = T.pack ", "
+ , idxDelimn = T.pack ", "
+ , idxDelimr = T.pack "--"
+ , idxEncapPre = T.pack "{"
+ , idxEncapSuf = T.pack "}"
+ }
+
+
+-- | Another 'IndexStyle' applied to an index.
+--
+-- This default style have :
+--
+-- * Basic preamble and postamble
+--
+-- * Uppercase Layer 0 headings
+--
+-- * Uppercase Layer 1 headings
+--
+styleDoubleHeading = IndexStyle
+ { idxPreamble = T.pack "\\begin{theindex}\n"
+ , idxPostamble = T.pack "\n\n\\end{theindex}\n"
+ , idxHeadingFlag0 = UpperCase
+ , idxHeadingFlag1 = UpperCase
+ , idxHeadingPreL0 = T.pack "{\\vspace{1.5cm}\\huge{\\textbf{"
+ , idxHeadingSufL0 = T.pack "}}\\hfill}\\nopagebreak\n\n"
+ , idxHeadingPreL1 = T.pack "\n{\\vspace{0.5cm}\\large{\\textbf{"
+ , idxHeadingSufL1 = T.pack "}}\\hfill}\\nopagebreak"
+ , idxSymhead = T.pack "Symbols"
+ , idxNumhead = T.pack "Numbers"
+ , idxGroupSkip0 = T.pack "\n\n \\indexspace\n"
+ , idxGroupSkip1 = T.pack "\n\n \\indexspace\n"
+ , idxItem0 = T.pack "\n \\item "
+ , idxItem1 = T.pack "\n \\subitem "
+ , idxItem2 = T.pack "\n \\subsubitem "
+ , idxItem01 = T.pack "\n \\subitem "
+ , idxItem12 = T.pack "\n \\subsubitem "
+ , idxDelim0 = T.pack ", " -- \\hfill
+ , idxDelim1 = T.pack ", "
+ , idxDelim2 = T.pack ", "
+ , idxDelimn = T.pack ", "
+ , idxDelimr = T.pack "--"
+ , idxEncapPre = T.pack "{"
+ , idxEncapSuf = T.pack "}"
+ }
+
+
+-- | Parse a style file
+--
+-- A style file can contain several optional keywords definition to set the design
+-- of an index.
+--
+-- Keywords can be :
+--
+-- [preamble] To set the beginning of the index.
+--
+--
+-- [postamble] To set the end of the index.
+--
+parseStyleFile :: IndexStyle -- ^ The default 'Style' to use.
+ -> ParsecT String () Identity IndexStyle -- ^ The new 'Style' parsed.
+parseStyleFile sty = do
+ emptyLines -- Possibles emptylines at the beginning of the file
+ sty <- permute
+ ( IndexStyle -- all possible permutations
+ <$?> (idxPreamble sty , try $ parseStyleDef "preamble") -- Parse the preamble
+ <|?> (idxPostamble sty , try $ parseStyleDef "postamble")
+ <|?> (idxHeadingFlag0 sty, try $ parseStyleDefHead "headings_flag")
+ <|?> (idxHeadingFlag1 sty, try $ parseStyleDefHead "headings_flag1")
+ <|?> (idxHeadingPreL0 sty, try $ parseStyleDef "heading_prefix")
+ <|?> (idxHeadingSufL0 sty, try $ parseStyleDef "heading_suffix")
+ <|?> (idxHeadingPreL1 sty, try $ parseStyleDef "heading_prefix1")
+ <|?> (idxHeadingSufL1 sty, try $ parseStyleDef "heading_suffix1")
+ <|?> (idxSymhead sty , try $ parseStyleDef "symhead_positive")
+ <|?> (idxNumhead sty , try $ parseStyleDef "numhead_positive")
+ <|?> (idxGroupSkip0 sty , try $ parseStyleDef "group_skip")
+ <|?> (idxGroupSkip1 sty , try $ parseStyleDef "group_skip1")
+ <|?> (idxItem0 sty , try $ parseStyleDef "item_0")
+ <|?> (idxItem1 sty , try $ parseStyleDef "item_1")
+ <|?> (idxItem2 sty , try $ parseStyleDef "item_2")
+ <|?> (idxItem01 sty , try $ parseStyleDef "item_01")
+ <|?> (idxItem12 sty , try $ parseStyleDef "item_12")
+ <|?> (idxDelim0 sty , try $ parseStyleDef "delim_0")
+ <|?> (idxDelim1 sty , try $ parseStyleDef "delim_1")
+ <|?> (idxDelim2 sty , try $ parseStyleDef "delim_2")
+ <|?> (idxDelimn sty , try $ parseStyleDef "delim_n")
+ <|?> (idxDelimr sty , try $ parseStyleDef "delim_r")
+ <|?> (idxEncapPre sty , try $ parseStyleDef "encap_infix")
+ <|?> (idxEncapSuf sty , try $ parseStyleDef "encap_suffix")
+
+ )
+ eof -- the end of file
+ return sty
+
+
+-- | Parse many empty lines.
+emptyLines = many emptyLine
+
+
+-- | Parse an empty line.
+emptyLine = do
+ many (oneOf " \t") -- possibly some spaces and tabulations.
+ endOfLineP -- The end of line
+
+
+-- | Parse a style definition
+--
+-- > item_0 "my style definition"
+--
+parseStyleDef :: String -- ^ The name of the style
+ -> ParsecT String () Identity T.Text -- ^ The definition of the style.
+parseStyleDef str = do
+ string str
+ many1 (char ' ')
+ def <- between (char '"') (char '"') (many1 $ noneOf "\r\n\t\"")
+ many (char ' ')
+ endOfLineP
+ emptyLines
+ return (literalNewLine $ T.pack def)
+
+
+
+parseStyleDefHead str = try (parseStyleDefHeadNum str)
+ <|> try (parseStyleDefHeadNone str)
+ <|> try (parseStyleDefHeadUpper str)
+ <|> (parseStyleDefHeadLower str)
+
+
+
+parseStyleDefHeadNone :: String -> ParsecT String () Identity Heading
+parseStyleDefHeadNone str = do
+ string str
+ many1 (char ' ')
+ s <- string "None"
+ many (char ' ')
+ endOfLineP
+ emptyLines
+ return None
+
+
+parseStyleDefHeadUpper :: String -> ParsecT String () Identity Heading
+parseStyleDefHeadUpper str = do
+ string str
+ many1 (char ' ')
+ s <- string "Upper"
+ many (char ' ')
+ endOfLineP
+ emptyLines
+ return UpperCase
+
+
+parseStyleDefHeadLower :: String -> ParsecT String () Identity Heading
+parseStyleDefHeadLower str = do
+ string str
+ many1 (char ' ')
+ s <- string "Lower"
+ many (char ' ')
+ endOfLineP
+ emptyLines
+ return LowerCase
+
+
+parseStyleDefHeadNum :: String -> ParsecT String () Identity Heading
+parseStyleDefHeadNum str = do
+ string str
+ many1 (char ' ')
+ s <- option ' ' (char '-')
+ h <- many1 digit
+ many (char ' ')
+ endOfLineP
+ emptyLines
+ return (val2Heading (read (s : h)))
+
+
+
+val2Heading 0 = None
+val2Heading n = if n > 0
+ then UpperCase
+ else LowerCase
+
+
+-- | Try to parse a IeC LaTeX substitution.
+-- Return the associated character if succeed.
+lstParseIeC lst = try $ do
+ string "\\IeC"
+ many (char ' ')
+ choice $ map (\(s, r) ->
+ (try $ do
+ braces $ do
+ many (char ' ')
+ char '\\'
+ string s
+ many (char ' ')
+ return r
+ )) lst
+
+
+
+
+-- | Parse a number
+parseNumber :: ParsecT String () Identity Char
+parseNumber = try digit
+
+-- | Parse a symbol
+parseSymbol :: ParsecT String () Identity Char
+parseSymbol = try (oneOf allowedSymb)
+
+
+-- | Parse an hyphen character
+parseHyph :: ParsecT String () Identity Char
+parseHyph = try (oneOf lstHyph)
+
+
+parseAnything :: ParsecT String () Identity Char
+parseAnything = try (noneOf forbiddenSymb)
+
+
+
+braces = between (char '{') (char '}')
+
+braces' = between (char '{') (try $ do char '}';lookAhead (char '{' ))
+
+
+-- | Parse a single entry command from "imakeidx" LaTeX package.
+parseIDX :: ParsecT String () Identity Char -> ParsecT String () Identity IndexItem
+parseIDX pars = do
+ string "\\indexentry"
+ many (char ' ')
+ ((itm,itmE),com) <- braces'
+ (do
+ itm <- sepArobase <$> many1 (notFollowedBy (do char '}';char '{') >> pars)
+ com <- option "" $ try $do
+ char '|'
+ optional (char '(')
+ many (notFollowedBy (do char '}';char '{') >> parseAnything)
+ return (itm,com)
+ )
+ many (char ' ')
+ n <- braces (many1 digit)
+ return (IndexItem (T.pack itm) (Letters, T.pack itmE) (T.pack com) [read n] [])
+
+
+-- | Parse a entry command containing a subentry from "imakeidx" LaTeX package.
+parseIDXSub :: ParsecT String () Identity Char -> ParsecT String () Identity IndexItem
+parseIDXSub pars = do
+ string "\\indexentry"
+ many (char ' ')
+ ((itm,itmE), (sub,subE),com) <- braces'
+ (do
+ itm <- sepArobase <$> many1 (notFollowedBy (do char '}';char '{') >> pars)
+ char '!'
+ sub <- sepArobase <$> many1 (notFollowedBy (do char '}';char '{') >> pars)
+ -- ~ string "|hyperpage"
+ com <- option "" $ try $do
+ char '|'
+ optional (char '(')
+ many (notFollowedBy (do char '}';char '{') >> parseAnything)
+ return (itm, sub,com)
+ )
+ many (char ' ')
+ n <- braces (many1 digit)
+ return (IndexItem (T.pack itm) (Letters, T.pack itmE) T.empty [] [IndexSubItem (T.pack sub) (Letters, T.pack subE) (T.pack com) [read n] []])
+
+
+-- | Parse a entry command containing a subsubentry from "imakeidx" LaTeX package.
+parseIDXSubSub :: ParsecT String () Identity Char -> ParsecT String () Identity IndexItem
+parseIDXSubSub pars = do
+ string "\\indexentry"
+ many (char ' ')
+ ((itm,itmE), (sub,subE), (ssub,ssubE),com) <- braces'
+ (do
+ itm <- sepArobase <$> many1 (notFollowedBy (do char '}';char '{') >> pars)
+ char '!'
+ sub <- sepArobase <$> many1 (notFollowedBy (do char '}';char '{') >> pars)
+ char '!'
+ ssub <- sepArobase <$> many1 (notFollowedBy (do char '}';char '{') >> pars)
+ -- ~ string "|hyperpage"
+ com <- option "" $ try $ do
+ char '|'
+ optional (char '(')
+ many (notFollowedBy (do char '}';char '{') >> parseAnything)
+ return (itm, sub, ssub,com)
+ )
+ many (char ' ')
+ n <- braces (many1 digit)
+ return (IndexItem (T.pack itm) (Letters, T.pack itmE) T.empty [] [IndexSubItem (T.pack sub) (Letters, T.pack subE) T.empty [] [IndexSubSubItem (T.pack ssub) (Letters, T.pack ssubE) (T.pack com) [read n]]])
+
+
+-- | Parse all possible forms of entry from "imakeidx" LaTeX package.
+parseIndexItem pars = try (parseIDXSubSub pars)
+ <|> try (parseIDXSub pars)
+ <|> parseIDX pars
+
+
+parseIndexFile :: ParsecT String () Identity [IndexItem]
+parseIndexFile = do
+ emptyLines
+ itms <- endBy (parseIndexItem parseCharL) endOfLineP
+ emptyLines
+ eof
+ return itms
+
+
+
+
+-- | Parse a end of line in both UNIX and WINDOWS format.
+-- ~ endOfLineP :: ParsecT String () Identity String
+endOfLineP = try (string "\n") -- Fin de ligne Unix/Linux (LF : Line feed)
+ <|> try (string "\r\n") -- Fin de ligne Windows (CRLF : Carriage return Line feed)
+
+
+
+-- | Standard parser for chars.
+--
+-- Try to parse :
+--
+-- 1. The specific char output from the "imakeidx" LaTeX package.
+--
+-- 2. Numbers
+--
+-- 3.
+parseCharL :: ParsecT String () Identity Char
+parseCharL = lstParseIeC lstLaTeXSubs
+ <|> parseAnything
+
+
+
+
+-- | Parse a file containing the lists of chars defining a language.
+--
+parseLanguageFile :: ParsecT String PermState Identity LangDef
+parseLanguageFile = do
+ emptyLines -- Possibles emptylines at the beginning of the file
+ -- ~ putState emptyPermState
+ def <- permute
+ ( (\a b c d -> LangDef a b c d []) -- all possible permutations
+ <$$> try (parseCharDefLetters ) -- <$$>
+ <|?> ([], try $ parseCharDefNumbers )
+ <|?> (Nothing, try $ parseCharDefSymbols )
+ <|?> ([], try $ parseSubstitutions )
+ )
+ eof -- the end of file
+ stat <- getState
+ return def{lstSecOrder=order stat}
+
+
+-- | Parse a char list definition.
+--
+-- A char list is defined by:
+--
+-- * A title
+--
+-- * A list of chars describing the sorting order of letters of this language.
+--
+parseCharDefLetters = do
+ string "LETTERS"
+ endOfLineP
+ chrs <- many (noneOf "\n\t")
+ endOfLineP
+ emptyLines
+ modifyState (\st -> st{order=order st++[Letters]})
+ return ( chrs)
+
+
+parseCharDefNumbers = do
+ string "NUMBERS"
+ endOfLineP
+ chrs <- many (noneOf "\n\t")
+ endOfLineP
+ emptyLines
+ modifyState (\st -> st{order=order st++[Numbers]})
+ return ( chrs)
+
+
+-- | Parse a char list definition.
+--
+-- A char list is defined by:
+--
+-- * A title
+--
+-- * A list of chars describing the sorting order of letters of this language.
+--
+parseCharDefSymbols = do
+ string "SYMBOLS"
+ endOfLineP
+ chrs <- many (noneOf "\n\t")
+ endOfLineP
+ emptyLines
+ modifyState (\st -> st{order=order st++[Symbols]})
+ return (Just ( chrs))
+
+
+-- | Parse a list of substitutions
+--
+-- A substitution give an equivalent string to a char. A list of substitution is defined by :
+--
+-- * A title
+--
+-- * A list of substitutions :
+--
+-- > œ->oe
+-- > à->a
+-- > ê->e
+--
+-- note: The arrow -> musn't be preceded or followed by spaces.
+--
+-- A special char can be substituted by a space with the following substitution.
+--
+-- > _->
+-- > -->
+--
+parseSubstitutions = do
+ string "SUBSTITUTIONS"
+ endOfLineP
+ repl <- many1 parseSubstitution
+ emptyLines
+ return repl -- (replaUpperLower repl)
+
+parseSubstitution = do
+ cha <- noneOf "\r\n\t"
+ string "->"
+ str <- many1 (noneOf "\r\n\t")
+ -- many (char ' ')
+ endOfLineP
+ return (cha, str)
+
+
+-- | The empty list of chars.
+emptyDef = LangDef [] [] Nothing [] []
+
+
diff --git a/indexing/hsindex/src/HsIndex/Show.hs b/indexing/hsindex/src/HsIndex/Show.hs
new file mode 100644
index 0000000000..6bab73245c
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/Show.hs
@@ -0,0 +1,324 @@
+{-# LANGUAGE OverloadedStrings #-}
+-- |
+-- Module : HsIndex.Show
+-- Copyright : Jean-Luc JOULIN 2018-2019
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The functions to display data types.
+
+-- This module provide functions to
+
+module HsIndex.Show
+ (
+ -- * Function to show the whole index.
+ showIndex
+ , showHeading1
+ , showHeading2
+
+ -- * Function to show a style.
+ , showStyle
+ , showLangDef
+ ) where
+
+
+import HsIndex.Types
+import Data.List
+import Data.Char
+import qualified Data.Text as T
+
+
+
+
+
+-- | Convert a 'IndexStyle' into String
+--
+-- This string is readable by hsindex.
+--
+showStyle style = unlines
+ [ "preamble " ++ show (idxPreamble style)
+ , "postamble " ++ show (idxPostamble style)
+ , "headings_flag " ++ showStyleHeading (idxHeadingFlag0 style)
+ , "heading_prefix " ++ show (idxHeadingPreL0 style)
+ , "heading_suffix " ++ show (idxHeadingSufL0 style)
+ , "headings_flag1 " ++ showStyleHeading (idxHeadingFlag1 style)
+ , "heading_prefix1 " ++ show (idxHeadingPreL1 style)
+ , "heading_suffix1 " ++ show (idxHeadingSufL1 style)
+ , "symhead_positive " ++ show (idxSymhead style)
+ , "numhead_positive " ++ show (idxNumhead style)
+ , "group_skip " ++ show (idxGroupSkip0 style)
+ , "group_skip1 " ++ show (idxGroupSkip1 style)
+ , "item_0 " ++ show (idxItem0 style)
+ , "item_1 " ++ show (idxItem1 style)
+ , "item_2 " ++ show (idxItem2 style)
+ , "item_01 " ++ show (idxItem01 style)
+ , "item_12 " ++ show (idxItem12 style)
+ , "delim_0 " ++ show (idxDelim0 style)
+ , "delim_1 " ++ show (idxDelim1 style)
+ , "delim_2 " ++ show (idxDelim2 style)
+ , "delim_n " ++ show (idxDelimn style)
+ , "delim_r " ++ show (idxDelimr style)
+ , "encap_infix " ++ show (idxEncapPre style)
+ , "encap_suffix " ++ show (idxEncapSuf style)
+ ]
+
+
+-- | Convert 'Heading' into 'String'.
+showStyleHeading None = "None"
+showStyleHeading UpperCase = "UpperCase"
+showStyleHeading LowerCase = "LowerCase"
+
+
+showLangDef def = unlines $ ["LETTERS", lstLetters def] ++ if null (lstNumbers def)
+ then []
+ else
+ ["NUMBERS", lstNumbers def]
+
+ ++ case lstSymbols def of
+ Nothing -> []
+ Just sym -> ["SYMBOLS", sym]
+ ++ if null (lstSubs def) then [] else ["SUBSTITUTIONS"] ++ subS (lstSubs def)
+
+ where
+ subS [] = []
+ subS ((a, b) : xs) = (a : "->" ++ b) : subS xs
+
+
+-- | convert an index into a 'Text'
+showIndex :: IndexStyle -- ^ The index style.
+ -> Bool -- ^ Automatic conversion to pages ranges
+ -> [IndexSection] -- ^ The list of section of the index.
+ -> T.Text -- ^ The output string in the LaTeX format.
+showIndex style rng lst = T.concat [idxPreamble style, showIndexSections style rng lst, idxPostamble style]
+
+
+-- | convert list of 'IndexSection' into a 'Text' readable with LaTeX.
+showIndexSections :: IndexStyle -- ^ The index style.
+ -> Bool -- ^ Automatic conversion to pages ranges
+ -> [IndexSection] -- ^ The list of section of the index.
+ -> T.Text -- ^ The output string in the LaTeX format.
+showIndexSections style _ [] = T.empty
+showIndexSections style rng lst = T.intercalate (idxGroupSkip0 style) (map (showIndexSection style rng) lstf)
+ where lstf = filter (\(IndexSection tit sub) -> not (null sub)) lst
+
+
+showIndexSection :: IndexStyle -> Bool -> IndexSection -> T.Text
+showIndexSection style rng (IndexSection "" sub) =
+ showIndexSubSections style rng sub
+showIndexSection style rng (IndexSection tit []) =
+ T.concat [idxHeadingPreL0 style, tit, idxHeadingSufL0 style]
+showIndexSection style rng (IndexSection tit sub) = T.concat
+ [ idxHeadingPreL0 style
+ , tit
+ , idxHeadingSufL0 style
+ , showIndexSubSections style rng sub
+ ]
+
+
+-- | convert list of 'IndexSubSection' into a 'Text' readable with LaTeX.
+showIndexSubSections :: IndexStyle -- ^ The index style.
+ -> Bool -- ^ Automatic conversion to pages ranges
+ -> [IndexSubSection] -- ^ The list of subsection of the index.
+ -> T.Text -- ^ The output string in the LaTeX format.
+showIndexSubSections style _ [] = ""
+showIndexSubSections style rng lst = T.intercalate
+ (idxGroupSkip1 style)
+ (map (showIndexSubSection style rng) lstf)
+ where lstf = filter (\(IndexSubSection tit ent) -> not (null ent)) lst
+
+
+showIndexSubSection :: IndexStyle -> Bool -> IndexSubSection -> T.Text
+showIndexSubSection style rng (IndexSubSection "" ent) =
+ showIndexItems style rng ent
+showIndexSubSection style _ (IndexSubSection tit []) =
+ T.concat [idxHeadingPreL1 style, tit, idxHeadingSufL1 style]
+showIndexSubSection style rng (IndexSubSection tit ent) = T.concat
+ [ idxHeadingPreL1 style
+ , tit
+ , idxHeadingSufL1 style
+ , showIndexItems style rng ent
+ ]
+
+
+-- | Convert a list of 'IndexItem' into a 'Text' readable with LaTeX.
+showIndexItems :: IndexStyle -- ^ The index style.
+ -> Bool -- ^ Automatic conversion to pages ranges
+ -> [IndexItem] -- ^ The list of items of the index.
+ -> T.Text -- ^ The output string in the LaTeX format.
+showIndexItems style _ [] = ""
+showIndexItems style rng (IndexItem n _ com p [] : xs) = T.concat
+ [ idxItem0 style
+ , n
+ , idxDelim0 style
+ , showPageRange style com (if rng then 3 else 1000) p
+ , showIndexItems style rng xs
+ ]
+showIndexItems style rng (IndexItem n _ _ [] sub : xs) = T.concat
+ [ idxItem0 style
+ , n
+ , showIndexSubItems style rng sub
+ , showIndexItems style rng xs
+ ]
+showIndexItems style rng (IndexItem n _ com p sub : xs) = T.concat
+ [ idxItem0 style
+ , n
+ , idxDelim0 style
+ , showPageRange style com (if rng then 3 else 1000) p
+ , showIndexSubItems style rng sub
+ , showIndexItems style rng xs
+ ]
+
+
+-- | Convert an 'IndexSubItem' into a 'Text' readable with LaTeX.
+--
+-- This function is a transition between entry and its subentries.
+showIndexSubItems :: IndexStyle -- ^ The index style.
+ -> Bool -- ^ Automatic conversion to pages ranges
+ -> [IndexSubItem] -- ^ The list of subitems of the index.
+ -> T.Text -- ^ The output string in the LaTeX format.
+showIndexSubItems style _ [] = ""
+showIndexSubItems style rng (IndexSubItem n _ com p [] : xs) = T.concat
+ [ idxItem01 style
+ , n
+ , idxDelim1 style
+ , showPageRange style com (if rng then 3 else 1000) p
+ , showIndexSubItems' style rng xs
+ ]
+showIndexSubItems style rng (IndexSubItem n _ _ [] subsub : xs) = T.concat
+ [ idxItem01 style
+ , n
+ , showIndexSubSubItems style rng subsub
+ , showIndexSubItems' style rng xs
+ ]
+showIndexSubItems style rng (IndexSubItem n _ com p subsub : xs) = T.concat
+ [ idxItem01 style
+ , n
+ , idxDelim1 style
+ , showPageRange style com (if rng then 3 else 1000) p
+ , showIndexSubSubItems style rng subsub
+ , showIndexSubItems' style rng xs
+ ]
+
+
+-- | Convert an 'IndexItem' into a 'Text' readable with LaTeX.
+showIndexSubItems' :: IndexStyle -> Bool -> [IndexSubItem] -> T.Text
+showIndexSubItems' style _ [] = ""
+showIndexSubItems' style rng (IndexSubItem n _ com p [] : xs) = T.concat
+ [ idxItem1 style
+ , n
+ , idxDelim1 style
+ , showPageRange style com (if rng then 3 else 1000) p
+ , showIndexSubItems' style rng xs
+ ]
+showIndexSubItems' style rng (IndexSubItem n _ _ [] subsub : xs) = T.concat
+ [ idxItem1 style
+ , n
+ , showIndexSubSubItems style rng subsub
+ , showIndexSubItems' style rng xs
+ ]
+showIndexSubItems' style rng (IndexSubItem n _ com p subsub : xs) = T.concat
+ [ idxItem1 style
+ , n
+ , idxDelim1 style
+ , showPageRange style com (if rng then 3 else 1000) p
+ , showIndexSubSubItems style rng subsub
+ , showIndexSubItems' style rng xs
+ ]
+
+
+-- | Convert an 'IndexSubSubItem' into a 'Text' readable with LaTeX.
+--
+-- This function is a transition between subentries and its subsubentries.
+
+showIndexSubSubItems :: IndexStyle -- ^ The index style.
+ -> Bool -- ^ Automatic conversion to pages ranges
+ -> [IndexSubSubItem] -- ^ The list of subsubitems of the index.
+ -> T.Text -- ^ The output string in the LaTeX format.
+showIndexSubSubItems style _ [] = ""
+showIndexSubSubItems style rng (IndexSubSubItem n _ com p : xs) = T.concat
+ [ idxItem12 style
+ , n
+ , idxDelim2 style
+ , showPageRange style com (if rng then 3 else 1000) p
+ , showIndexSubSubItems' style rng xs
+ ]
+
+
+-- | Convert an 'IndexSubSubItem' into a 'Text' usable with LaTeX.
+showIndexSubSubItems' :: IndexStyle -> Bool -> [IndexSubSubItem] -> T.Text
+showIndexSubSubItems' style _ [] = ""
+showIndexSubSubItems' style rng (IndexSubSubItem n _ com p : xs) = T.concat
+ [ idxItem2 style
+ , n
+ , idxDelim2 style
+ , showPageRange style com (if rng then 3 else 1000) p
+ , showIndexSubSubItems' style rng xs
+ ]
+
+
+
+
+
+
+
+
+
+-- | Return the string of the heading (Layer 1) according to the style and
+-- the equivalent name of an item.
+showHeading1 :: IndexStyle -- ^ The index style.
+ -> (Section, T.Text) -- ^ The equivalent name.
+ -> T.Text
+showHeading1 sty (Letters, a) | idxHeadingFlag0 sty == UpperCase = T.toUpper (T.take 1 a)
+ | idxHeadingFlag0 sty == LowerCase = T.toLower (T.take 1 a)
+ | otherwise = T.empty
+
+showHeading1 sty (Numbers, a) | idxHeadingFlag0 sty == UpperCase = idxNumhead sty
+ | idxHeadingFlag0 sty == LowerCase = idxNumhead sty
+ | otherwise = T.empty
+
+showHeading1 sty (Symbols, a) | idxHeadingFlag0 sty == UpperCase = idxSymhead sty
+ | idxHeadingFlag0 sty == LowerCase = idxSymhead sty
+ | otherwise = T.empty
+
+
+-- | Return the string of the heading (Layer 1) according to the style and
+-- the equivalent name of an item.
+showHeading2 :: IndexStyle -- ^ The index style.
+ -> (Section, T.Text) -- ^ The equivalent name.
+ -> T.Text
+showHeading2 sty (Letters, a) | idxHeadingFlag1 sty == UpperCase = T.toUpper (T.take 2 a)
+ | idxHeadingFlag1 sty == LowerCase = T.toLower (T.take 2 a)
+ | otherwise = T.empty
+
+showHeading2 sty (Numbers, a) | idxHeadingFlag1 sty == UpperCase = T.take 1 a
+ | idxHeadingFlag1 sty == LowerCase = T.take 1 a
+ | otherwise = T.empty
+
+showHeading2 sty (Symbols, a) | idxHeadingFlag1 sty == UpperCase = T.take 1 a
+ | idxHeadingFlag1 sty == LowerCase = T.take 1 a
+ | otherwise = T.empty
+
+
+groupedBySuccessors [] = []
+groupedBySuccessors lst@(x : xs) = map fst ok : groupedBySuccessors (map fst nok)
+ where
+ lstC = [x ..]
+ (ok, nok) = span (\(a, b) -> a == b) $ zip lst lstC
+
+
+showPageRange style com n nums = if com == T.empty
+ then T.intercalate (idxDelimn style) (map showRange grps)
+ else T.intercalate (idxDelimn style) (map showRangeCom grps)
+ where
+ showRangeCom gr = if length gr >= n
+ then T.concat ["\\", com, idxEncapPre style, T.pack $ show (head gr), idxDelimr style, T.pack $ show (last gr), idxEncapSuf style]
+ else T.intercalate (idxDelimn style) (map (\v -> T.concat ["\\", com, idxEncapPre style, T.pack $ show v, idxEncapSuf style]) gr)
+
+ showRange gr = if length gr >= n
+ then T.concat [T.pack $ show (head gr), idxDelimr style, T.pack $ show (last gr)]
+ else T.intercalate (idxDelimn style) (map (\v -> T.concat [T.pack $ show v]) gr)
+
+ grps = groupedBySuccessors nums
+
+
diff --git a/indexing/hsindex/src/HsIndex/Sorting.hs b/indexing/hsindex/src/HsIndex/Sorting.hs
new file mode 100644
index 0000000000..4a33259947
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/Sorting.hs
@@ -0,0 +1,246 @@
+-- |
+-- Module : HsIndex.Sorting
+-- Copyright : Jean-Luc JOULIN 2018-2019
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The functions to sort data types.
+
+
+
+module HsIndex.Sorting where
+
+
+import Data.List
+import Data.Char
+import HsIndex.Types
+
+import HsIndex.Functions
+import qualified Data.Text as T
+
+
+
+-- | Generate the equivalent name of 'IndexItem's.
+--
+--
+equivItems :: Bool -- ^ Case sensitivity.
+ -> LangDef -- ^ Lists of chars in each sections.
+ -> [IndexItem]
+ -> [IndexItem]
+equivItems _ _ [] = []
+equivItems False cha (x : xs)
+ | T.head equi `elem` map toUpper (lstLetters cha) = x { itemEqui = (Letters, equi),itemContent = equivSubItems False cha (itemContent x) } : equivItems False cha xs
+ | T.head equi `elem` map toUpper (lstNumbers cha) = x { itemEqui = (Numbers, equi),itemContent = equivSubItems False cha (itemContent x) } : equivItems False cha xs
+ | otherwise = case lstSymbols cha of
+ Nothing -> x { itemEqui = (Symbols, equi) } : equivItems False cha xs
+ Just ch -> if T.head equi `elem` map toUpper ch
+ then x { itemEqui = (Symbols, equi) } : equivItems False cha xs
+ else equivItems False cha xs
+ where
+ equi =
+ T.toUpper $ if snd (itemEqui x) == T.empty
+ then substituteCharInString (lstSubs cha) (itemName x)
+ else snd (itemEqui x)
+
+equivItems True cha (x : xs)
+ | T.head equi `elem` lstLetters cha = x { itemEqui = (Letters, equi),itemContent = equivSubItems True cha (itemContent x) } : equivItems True cha xs
+ | T.head equi `elem` lstNumbers cha = x { itemEqui = (Numbers, equi),itemContent = equivSubItems True cha (itemContent x) } : equivItems True cha xs
+ | otherwise = case lstSymbols cha of
+ Nothing -> x { itemEqui = (Symbols, equi) } : equivItems True cha xs
+ Just ch -> if T.head equi `elem` ch
+ then x { itemEqui = (Symbols, equi) } : equivItems True cha xs
+ else equivItems True cha xs
+ where
+ equi =
+ if snd (itemEqui x) == T.empty
+ then substituteCharInString (lstSubs cha) (itemName x)
+ else snd (itemEqui x)
+
+
+
+equivSubItems :: Bool -- ^ Case sensitivity.
+ -> LangDef -- ^ Lists of chars in each sections.
+ -> [IndexSubItem]
+ -> [IndexSubItem]
+equivSubItems _ _ [] = []
+equivSubItems False cha (x : xs)
+ | T.head equi `elem` map toUpper (lstLetters cha) = x { subItemEqui = (Letters, equi),subItemContent = equivSubSubItems False cha (subItemContent x) } : equivSubItems False cha xs
+ | T.head equi `elem` map toUpper (lstNumbers cha) = x { subItemEqui = (Numbers, equi),subItemContent = equivSubSubItems False cha (subItemContent x) } : equivSubItems False cha xs
+ | otherwise = case lstSymbols cha of
+ Nothing -> x { subItemEqui = (Symbols, equi) } : equivSubItems False cha xs
+ Just ch -> if T.head equi `elem` map toUpper ch
+ then x { subItemEqui = (Symbols, equi) } : equivSubItems False cha xs
+ else equivSubItems False cha xs
+ where
+ equi = T.toUpper $ if snd (subItemEqui x) == T.empty
+ then substituteCharInString (lstSubs cha) (subItemName x)
+ else snd (subItemEqui x)
+
+equivSubItems True cha (x : xs)
+ | T.head equi `elem` lstLetters cha = x { subItemEqui = (Letters, equi),subItemContent = equivSubSubItems True cha (subItemContent x) } : equivSubItems True cha xs
+ | T.head equi `elem` lstNumbers cha = x { subItemEqui = (Numbers, equi),subItemContent = equivSubSubItems True cha (subItemContent x) } : equivSubItems True cha xs
+ | otherwise = case lstSymbols cha of
+ Nothing -> x { subItemEqui = (Symbols, equi) } : equivSubItems True cha xs
+ Just ch -> if T.head equi `elem` ch
+ then x { subItemEqui = (Symbols, equi) } : equivSubItems True cha xs
+ else equivSubItems True cha xs
+ where
+ equi = if snd (subItemEqui x) == T.empty
+ then substituteCharInString (lstSubs cha) (subItemName x)
+ else snd (subItemEqui x)
+
+
+equivSubSubItems :: Bool -- ^ Case sensitivity.
+ -> LangDef -- ^ Lists of chars in each sections.
+ -> [IndexSubSubItem]
+ -> [IndexSubSubItem]
+equivSubSubItems _ _ [] = []
+equivSubSubItems False cha (x : xs)
+ | T.head equi `elem` map toUpper (lstLetters cha)
+ = x { subSubItemEqui = (Letters, equi) } : equivSubSubItems False cha xs
+ | T.head equi `elem` map toUpper (lstNumbers cha)
+ = x { subSubItemEqui = (Numbers, equi) } : equivSubSubItems False cha xs
+ | otherwise
+ = case lstSymbols cha of
+ Nothing -> x { subSubItemEqui = (Symbols, equi) } : equivSubSubItems False cha xs
+ Just ch -> if T.head equi `elem` map toUpper ch
+ then x { subSubItemEqui = (Symbols, equi) } : equivSubSubItems False cha xs
+ else equivSubSubItems False cha xs
+ where
+ equi = T.toUpper $ if snd (subSubItemEqui x) == T.empty
+ then substituteCharInString (lstSubs cha) (subSubItemName x)
+ else snd (subSubItemEqui x)
+
+
+equivSubSubItems True cha (x : xs)
+ | T.head equi `elem` lstLetters cha = x { subSubItemEqui = (Letters, equi) } : equivSubSubItems True cha xs
+ | T.head equi `elem` lstNumbers cha = x { subSubItemEqui = (Numbers, equi) } : equivSubSubItems True cha xs
+ | otherwise = case lstSymbols cha of
+ Nothing -> x { subSubItemEqui = (Symbols, equi) } : equivSubSubItems True cha xs
+ Just ch -> if T.head equi `elem` ch
+ then x { subSubItemEqui = (Symbols, equi) } : equivSubSubItems True cha xs
+ else equivSubSubItems True cha xs
+ where
+ equi = if snd (subSubItemEqui x) == T.empty
+ then substituteCharInString (lstSubs cha) (subSubItemName x)
+ else snd (subSubItemEqui x)
+
+
+sortItems :: Bool
+ -> LangDef -- ^ The list of 'Char's for each section.
+ -> [IndexItem]
+ -> [IndexItem]
+sortItems True cha lst = sortBy (\a b -> compareBySection True cha (itemEqui a) (itemEqui b)) nlst
+ where nlst = map (\itm -> itm { itemContent = sortSubItems True cha (itemContent itm) }) lst
+
+
+sortItems False cha lst = sortBy (\a b -> compareBySection False cha ( itemEqui a) ( itemEqui b)) nlst
+ where nlst = map (\itm -> itm { itemContent = sortSubItems False cha (itemContent itm) }) lst
+
+
+
+
+sortSubItems :: Bool
+ -> LangDef -- ^ The list of 'Char's for each section.
+ -> [IndexSubItem]
+ -> [IndexSubItem]
+sortSubItems True cha lst = sortBy (\a b -> compareBySection True cha (subItemEqui a) (subItemEqui b)) nlst
+ where nlst = map (\itm -> itm { subItemContent = sortSubSubItems True cha (subItemContent itm) }) lst
+
+
+sortSubItems False cha lst = sortBy (\a b -> compareBySection False cha (subItemEqui a) (subItemEqui b)) nlst
+ where nlst = map (\itm -> itm { subItemContent = sortSubSubItems False cha (subItemContent itm) }) lst
+
+
+sortSubSubItems :: Bool
+ -> LangDef -- ^ The list of 'Char's for each section.
+ -> [IndexSubSubItem]
+ -> [IndexSubSubItem]
+sortSubSubItems True cha lst = sortBy (\a b -> compareBySection True cha (subSubItemEqui a) (subSubItemEqui b)) lst
+
+sortSubSubItems False cha lst = sortBy (\a b -> compareBySection False cha (subSubItemEqui a) (subSubItemEqui b)) lst
+
+
+
+-- | compareBySection two items according to :
+--
+-- 1. The 'Section' they belongs to. The section order is given in argument.
+--
+-- 2. Their alphabetical order given by a list of 'Char's.
+--
+compareBySection :: Bool
+ -> LangDef -- ^ The list of 'Char's for each section.
+ -> (Section, T.Text) -- ^ The first item to compareBySection.
+ -> (Section, T.Text) -- ^ The second index to compareBySection.
+ -> Ordering -- ^ The 'Ordering'.
+compareBySection cas cha (seca, stra) (secb, strb) = case (ind_a, ind_b) of
+ (Just ia, Just ib) | ia == ib -> if cas
+ then compareByString (genListChar cha) (T.unpack stra) (T.unpack strb)
+ else compareByString' (genListChar cha) (T.unpack stra) (T.unpack strb)
+ | ia < ib -> LT
+ | otherwise -> GT
+ where
+ recu
+ | seca == Letters = if cas
+ then compareByString (lstLetters cha) (T.unpack stra) (T.unpack strb)
+ else compareByString' (lstLetters cha) (T.unpack stra) (T.unpack strb)
+ | seca == Numbers = if cas
+ then compareByString (lstNumbers cha) (T.unpack stra) (T.unpack strb)
+ else compareByString' (lstNumbers cha) (T.unpack stra) (T.unpack strb)
+ | seca == Symbols = case lstSymbols cha of
+ Nothing -> EQ -- error "No list of symbols defined"
+ Just ch -> if cas
+ then compareByString ch (T.unpack stra) (T.unpack strb)
+ else compareByString' ch (T.unpack stra) (T.unpack strb)
+ (Nothing, _ ) -> error ""
+ (_ , Nothing) -> error ""
+ where
+ ind_a = elemIndex seca (lstSecOrder cha)
+ ind_b = elemIndex secb (lstSecOrder cha)
+
+
+compareByString' ord stra strb = compareByString (map toUpper ord) (map toUpper stra) (map toUpper strb)
+
+
+-- | Compare two 'String's according to a list of 'Char'.
+compareByString :: String -- ^ The list of Char's giving the order.
+ -> String -- ^ The first 'String' to compare.
+ -> String -- ^ The second 'String' to compare.
+ -> Ordering -- ^ The 'Ordering' result.
+compareByString ordlst [] [] = EQ
+compareByString ordlst [] (b : bx) = LT -- GT
+compareByString ordlst (a : ax) [] = GT -- LT
+compareByString ordlst (a : ax) (b : bx) = case (ind_a, ind_b) of
+ -- If both char are presents in the ordering list, we compare their indexes
+ (Just ia, Just ib) | ia == ib -> compareByString ordlst ax bx -- Same indexes, we compare the next chars
+ | ia < ib -> LT
+ | otherwise -> GT
+ (Nothing, Nothing) -> compareByString ordlst ax bx -- compare a b
+ (Nothing, _ ) -> LT
+ (_ , Nothing) -> GT
+ where
+ ind_a = elemIndex a ordlst -- Seek the char index of the first string in the ordering list
+ ind_b = elemIndex b ordlst -- Seek the char index of the second string in the ordering list
+
+
+
+-- | Generate the concatenated list of Char of all Sections in
+-- the sorting order.
+genListChar cha = genListChar' cha (lstSecOrder cha)
+ where
+ genListChar' _ [] = ""
+ genListChar' cha (Letters : xs) = lstLetters cha ++ genListChar' cha xs
+ genListChar' cha (Numbers : xs) = lstNumbers cha ++ genListChar' cha xs
+ genListChar' cha (Symbols : xs) = case lstSymbols cha of
+ Nothing -> genListChar' cha xs
+ Just str -> str ++ genListChar' cha xs
+
+
+
+
+
+
+
+
+
diff --git a/indexing/hsindex/src/HsIndex/Types.hs b/indexing/hsindex/src/HsIndex/Types.hs
new file mode 100644
index 0000000000..cc7340d7d2
--- /dev/null
+++ b/indexing/hsindex/src/HsIndex/Types.hs
@@ -0,0 +1,205 @@
+-- |
+-- Module : HsIndex.Types
+-- Copyright : Jean-Luc JOULIN 2018-2020
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The definition of main types for HsIndex.
+
+
+
+
+module HsIndex.Types where
+
+
+import Text.Parsec
+import Text.Parsec.String
+
+import Data.Char
+import qualified Data.Text as T
+
+--
+-- The main data structure of an index is made like this
+--
+-- * Section ""
+--
+-- * Subsection ""
+--
+-- * Entry "" [4]
+--
+-- * Entry "" [17,12]
+--
+-- * SubEntry "" [21]
+--
+-- * SubSubEntry "" [22]
+--
+-- * SubEntry "" [29]
+--
+-- * Subsection ""
+--
+--
+-- * Section B"
+--
+-- * ....
+--
+-- * ....
+--
+--
+-- Sections are made to store SubSections starting with the same first letter.
+--
+-- SubSections are made to store Entries starting with the same two letters.
+--
+-- Entry is made to store a word, it's pages numbers and a list of SubEntries. It's equivalent to "imakeidx" items.
+--
+-- SubEntry is made to store a word, it's pages numbers and a list of SubSubEntries. It's equivalent to "imakeidx" subitems.
+--
+-- SubSubEntry is made to store a word and it's pages numbers. It's equivalent to "imakeidx" subsubitems.
+--
+--
+-- This data structure is deep enough to comply with "imakeidx" LaTeX package.
+--
+
+
+
+
+
+
+
+
+
+
+
+-- | The type to describe the style of the Index
+--
+-- preamble
+--
+-- prefix heading layer1 suffix
+--
+-- name1 delimiters 1, 3, 4
+--
+-- name2 delimiters 4, 9
+--
+-- name3 delimiters 9, 12
+--
+-- postamble
+--
+data IndexStyle =
+ IndexStyle { idxPreamble :: T.Text -- ^ The preamble
+ , idxPostamble :: T.Text -- ^ The postamble
+ , idxHeadingFlag0 :: Heading -- ^ The flag for the layer 0 heading, in connection with 'IndexSection's
+ , idxHeadingFlag1 :: Heading -- ^ The flag for the layer 1 heading, in connection with 'IndexSubSection's
+ , idxHeadingPreL0 :: T.Text -- ^ The prefix for the Layer 0 heading, in connection with 'IndexSection's
+ , idxHeadingSufL0 :: T.Text -- ^ The suffix for the Layer 0 heading, in connection with 'IndexSection's
+ , idxHeadingPreL1 :: T.Text -- ^ The prefix for the Layer 1 heading, in connection with 'IndexSubSection's
+ , idxHeadingSufL1 :: T.Text -- ^ The suffix for the Layer 1 heading, in connection with 'IndexSubSection's
+ , idxSymhead :: T.Text -- ^ The title for the "symbols" section
+ , idxNumhead :: T.Text -- ^ The title for the "numbers" section
+ , idxGroupSkip0 :: T.Text -- ^ The skip command after a layer 0 group ('IndexSection')
+ , idxGroupSkip1 :: T.Text -- ^ The skip command after a layer 1 group ('IndexSubSection')
+ , idxItem0 :: T.Text -- ^ The command to place before the index "items"
+ , idxItem1 :: T.Text -- ^ The command to place before the index "subitems"
+ , idxItem2 :: T.Text -- ^ The command to place before the index "subsubitems"
+ , idxItem01 :: T.Text -- ^ The command to place between an index "items" and an index "subitems"
+ , idxItem12 :: T.Text -- ^ The command to place between an index "subitems" and an index "subsubitems"
+ , idxDelim0 :: T.Text -- ^ The delimiter between the name and the pages numbers for "items"
+ , idxDelim1 :: T.Text -- ^ The delimiter between the name and the pages numbers for "subitems"
+ , idxDelim2 :: T.Text -- ^ The delimiter between the name and the pages numbers for "subsubitems"
+ , idxDelimn :: T.Text -- ^ The delimiter between pages numbers.
+ , idxDelimr :: T.Text -- ^ The delimiter between pages range.
+ , idxEncapPre :: T.Text
+ , idxEncapSuf :: T.Text
+ }
+
+
+-- | The list of chars to define a language.
+data LangDef = LangDef { lstLetters :: [Char] -- ^ Chars considered as letters.
+ , lstNumbers :: [Char] -- ^ Chars considered as numbers.
+ , lstSymbols :: Maybe [Char] -- ^ Chars considered as symbols.
+ , lstSubs :: [(Char,String)] -- ^ List of substitutions to perform.
+ , lstSecOrder :: [Section]
+ }
+
+
+-- | The style of a heading.
+data Heading = None -- ^ No heading
+ | UpperCase -- ^ Upper case heading
+ | LowerCase -- ^ Lower case heading
+ deriving (Eq)
+
+
+-- | The category of a section.
+--
+-- A section can be one of these three categories :
+--
+-- * Letters
+--
+-- * Numbers
+--
+-- * Symbols
+--
+data Section = Letters
+ | Numbers
+ | Symbols
+ deriving (Eq, Show)
+
+-- | An alias for a list of 'IndexSection's
+type Index = [IndexSection]
+
+
+-- | The type for a section.
+data IndexSection =
+ IndexSection { secTitle :: T.Text -- ^ The section title.
+ , secSubSections :: [IndexSubSection] -- ^ The subsections.
+ }
+ deriving (Show)
+
+-- | The type for a subsection.
+data IndexSubSection =
+ IndexSubSection { subSecTitle :: T.Text -- ^ The subsection title.
+ , subSecEntries :: [IndexItem] -- ^ The entries.
+ }
+ deriving (Show)
+
+-- | The type for an item.
+data IndexItem =
+ IndexItem { itemName :: T.Text -- ^ The name of the index item.
+ , itemEqui :: (Section, T.Text) -- ^ The equivalent name and the section of the item.
+ , itemPageCommand :: T.Text -- ^ The command to insert before page number
+ , itemPages :: [Int] -- ^ The pages numbers it refers to.
+ , itemContent :: [IndexSubItem] -- ^ The subitems.
+ }
+ deriving (Show)
+
+-- | The type for a subitem.
+data IndexSubItem =
+ IndexSubItem { subItemName :: T.Text -- ^ The name of the index subitem.
+ , subItemEqui :: (Section, T.Text) -- ^ The equivalent name and the section of the subitem.
+ , subItemPageCommand :: T.Text -- ^ The command to insert before page number
+ , subItemPages :: [Int] -- ^ The pages numbers it refers to.
+ , subItemContent :: [IndexSubSubItem] -- ^ The subsubitems.
+ }
+ deriving (Show)
+
+-- | The type for a subsubitem.
+data IndexSubSubItem =
+ IndexSubSubItem { subSubItemName :: T.Text -- ^ The name of the index subsubitem.
+ , subSubItemEqui :: (Section, T.Text) -- ^ The equivalent name and the section of the subsubitem.
+ , subSubItemPageCommand :: T.Text -- ^ The command to insert before page number
+ , subSubItemPages :: [Int] -- ^ The pages numbers it refers to.
+ }
+ deriving (Show)
+
+
+-- | The type of index to use
+data IndexType = StyleBasic -- ^ The default basic style
+ | StyleDouble -- ^ The default double header style
+ | Stylecustom FilePath -- ^ A custom style (path to the style file).
+
+
+-- | A state to accumulate the 'Section' order.
+data PermState = PermState{ order::[Section]}
+
+-- | The empty state
+emptyPermState = PermState []
+
diff --git a/indexing/hsindex/src/hsindex.hs b/indexing/hsindex/src/hsindex.hs
new file mode 100644
index 0000000000..bee37119cf
--- /dev/null
+++ b/indexing/hsindex/src/hsindex.hs
@@ -0,0 +1,395 @@
+-- |
+-- Module : HsIndex.Files
+-- Copyright : Jean-Luc JOULIN 2018-2020
+-- License : General Public Licence (GPLv3)
+-- Maintainer : Jean-Luc JOULIN <jean-luc-joulin@orange.fr>
+-- Stability : alpha
+-- Portability : portable
+-- The Main program for the index generator
+--
+
+
+import Prelude hiding (getContents, putStrLn)
+
+
+
+import Control.Monad
+
+import Data.Char
+import Data.Function
+import Data.List
+import Data.Maybe
+import Data.Ord
+import Debug.Trace
+import GHC.IO.Encoding -- solve bug commitBuffer: invalid argument (invalid character)
+import HsIndex.CharLists.English
+import HsIndex.CharLists.French
+import HsIndex.CharLists.German
+import HsIndex.CharLists.Russian
+import HsIndex.Files
+import HsIndex.Functions
+import HsIndex.Parser
+import HsIndex.Show
+import HsIndex.Sorting
+import HsIndex.Types
+import qualified Prelude (getContents, putStrLn)
+import System.Console.CmdArgs.Explicit
+import System.Console.CmdArgs.Text
+import System.Environment
+import System.Exit
+import System.IO
+import Text.Parsec
+import Text.Printf
+
+import System.Directory
+import System.FilePath
+
+
+-- | The ASCII art for the CLI title.
+logo =
+ [
+ " _ _ _____ _____ __ __ "
+ , " | | | | |_ _| | __ \\ \\ \\ / / "
+ , " | |__| |___ | | _ __ | | | | ___ \\ V / "
+ , " | __ / __| | | | '_ \\| | | |/ _ \\ > < "
+ , " | | | \\__ \\_| |_| | | | |__| | __// . \\ "
+ , " |_| |_|___/_____|_| |_|_____/ \\___/_/ \\_\\ "
+ ]
+
+
+-- | Available options for the CLI.
+data MyModes =
+
+ IndexRussian { fileIn :: FilePath -- ^ The input file
+ , fileOut :: FilePath -- ^ The output file
+ , fileStyle :: IndexType -- ^ The style type
+ , autoRange :: Bool
+ , caseSens :: Bool
+ }
+ | IndexFrench { fileIn :: FilePath
+ , fileOut :: FilePath
+ , fileStyle :: IndexType -- ^ The style type
+ , autoRange :: Bool
+ , caseSens :: Bool
+ }
+ | IndexGerman { fileIn :: FilePath
+ , fileOut :: FilePath
+ , fileStyle :: IndexType -- ^ The style type
+ , autoRange :: Bool
+ , caseSens :: Bool
+ }
+ | IndexEnglish { fileIn :: FilePath
+ , fileOut :: FilePath
+ , fileStyle :: IndexType -- ^ The style type
+ , autoRange :: Bool
+ , caseSens :: Bool
+ }
+ | IndexCustom { fileIn :: FilePath
+ , fileOut :: FilePath
+ , fileStyle :: IndexType -- ^ The style type
+ , autoRange :: Bool
+ , caseSens :: Bool
+ , fileDef :: FilePath
+ }
+ | IndexCheck { checkInternalStyle :: Bool
+ , checkLanguageDef :: Maybe String
+ }
+
+ | ArgHelp
+ | ArgVersion
+
+
+-- | The basic options for English language.
+initialOptsIndexEnglish = IndexEnglish "" "" StyleBasic False True
+
+-- | The basic options for French language.
+initialOptsIndexFrench = IndexFrench "" "" StyleBasic False True
+
+-- | The basic options for German language.
+initialOptsIndexGerman = IndexGerman "" "" StyleBasic False True
+
+-- | The basic options for Russian language.
+initialOptsIndexRussian = IndexRussian "" "" StyleBasic False True
+
+-- | The basic options for custom language.
+initialOptsIndexCustom = IndexCustom "" "" StyleBasic False True ""
+
+-- | The basic options for cheking the program.
+initialOptsCheck = IndexCheck False Nothing
+
+
+-- | The cli mode for English language.
+modeGenIndexEnglish :: Mode MyModes
+modeGenIndexEnglish = mode "english" initialOptsIndexEnglish description unnamedArg convertFlags
+ where
+ description = "Generate a English index"
+ unnamedArg = Arg { argValue = updateUnnamed, argType = "", argRequire = False }
+ where updateUnnamed str opts = Left ("Error unknown argument : " ++ str)
+
+ convertFlags =
+ [ flagReq ["input", "i"] setInputFile "<File>" "Input file"
+ , flagReq ["output", "o"] setOutpuFile "<File>" "Output file"
+ , flagReq ["style", "s"] setStyleFile "<File>" "Style file"
+ , flagNone ["range"] setRange "Convert sequences of page into range"
+ , flagNone ["nocase"] setNoCase "Case insensitive ordering"
+ , flagNone ["dbl"] setDblHeader "Two letters headers"
+ ]
+
+-- | The cli mode for French language.
+modeGenIndexFrench :: Mode MyModes
+modeGenIndexFrench = mode "french" initialOptsIndexFrench description unnamedArg convertFlags
+ where
+ description = "Generate a French index"
+ unnamedArg = Arg { argValue = updateUnnamed, argType = "", argRequire = False }
+ where updateUnnamed str opts = Left ("Error unknown argument : " ++ str)
+ convertFlags =
+ [ flagReq ["input", "i"] setInputFile "<File>" "Input file"
+ , flagReq ["output", "o"] setOutpuFile "<File>" "Output file"
+ , flagReq ["style", "s"] setStyleFile "<File>" "Style file"
+ , flagNone ["range"] setRange "Convert sequences of page into range"
+ , flagNone ["nocase"] setNoCase "Case insensitive ordering"
+ , flagNone ["dbl"] setDblHeader "Two letters headers"
+ ]
+
+-- | The cli mode for German language.
+modeGenIndexGerman :: Mode MyModes
+modeGenIndexGerman = mode "german" initialOptsIndexGerman description unnamedArg convertFlags
+ where
+ description = "Generate a German index"
+ unnamedArg = Arg { argValue = updateUnnamed, argType = "", argRequire = False }
+ where updateUnnamed str opts = Left ("Error unknown argument : " ++ str)
+ convertFlags =
+ [ flagReq ["input", "i"] setInputFile "<File>" "Input file"
+ , flagReq ["output", "o"] setOutpuFile "<File>" "Output file"
+ , flagReq ["style", "s"] setStyleFile "<File>" "Style file"
+ , flagNone ["range"] setRange "Convert sequences of page into range"
+ , flagNone ["nocase"] setNoCase "Case insensitive ordering"
+ , flagNone ["dbl"] setDblHeader "Two letters headers"
+ ]
+
+-- | The cli mode for Russian language.
+modeGenIndexRussian :: Mode MyModes
+modeGenIndexRussian = mode "russian" initialOptsIndexRussian description unnamedArg convertFlags
+ where
+ description = "Generate a Russian index"
+ unnamedArg = Arg { argValue = updateUnnamed, argType = "", argRequire = False }
+ where updateUnnamed str opts = Left ("Error unknown argument : " ++ str)
+ convertFlags =
+ [ flagReq ["input", "i"] setInputFile "<File>" "Input file"
+ , flagReq ["output", "o"] setOutpuFile "<File>" "Output file"
+ , flagReq ["style", "s"] setStyleFile "<File>" "Style file"
+ , flagNone ["range"] setRange "Convert sequences of page into range"
+ , flagNone ["nocase"] setNoCase "Case insensitive ordering"
+ , flagNone ["dbl"] setDblHeader "Two letters headers"
+ ]
+
+-- | The cli mode for a custom language.
+modeGenIndexCustom :: Mode MyModes
+modeGenIndexCustom = mode "custom" initialOptsIndexCustom description unnamedArg convertFlags
+ where
+ description = "Generate a index with a custom language"
+ unnamedArg = Arg { argValue = updateUnnamed, argType = "", argRequire = False }
+ where updateUnnamed str opts = Left ("Error unknown argument : " ++ str)
+
+ convertFlags =
+ [ flagReq ["input", "i"] setInputFile "<File>" "Input file"
+ , flagReq ["output", "o"] setOutpuFile "<File>" "Output file"
+ , flagReq ["style", "s"] setStyleFile "<File>" "Style file"
+ , flagReq ["def", "d"] setDefFile "<File>" "Definition file"
+ , flagNone ["range"] setRange "Convert sequences of page into range"
+ , flagNone ["nocase"] setNoCase "Case insensitive ordering"
+ , flagNone ["dbl"] setDblHeader "Two letters headers"
+ ]
+
+-- | The cli mode for a checking the program.
+modeGenCheck :: Mode MyModes
+modeGenCheck = mode "check" initialOptsCheck description unnamedArg convertFlags
+ where
+ description = "Check the internal parameter of the program"
+ unnamedArg = Arg { argValue = updateUnnamed, argType = "", argRequire = False }
+ where updateUnnamed str opts = Left ("Error unknown argument : " ++ str)
+
+ convertFlags =
+ [ flagNone ["style"] setCheckStyle "Check built-in default style"
+ , flagReq ["language", "l"] setCheckLanguage "<Lang>" "Check built-in language definition"
+ ]
+
+
+
+
+-- | Set the input file.
+setInputFile str opts = Right $ opts { fileIn = str }
+
+-- | Set the output file.
+setOutpuFile str opts = Right $ opts { fileOut = str }
+
+-- | Set the style file.
+setStyleFile str opts = Right $ opts { fileStyle = Stylecustom str }
+
+-- | Set the definition file.
+setDefFile str opts = Right $ opts { fileDef = str }
+
+-- | Enable automatic conversion of pages sequences into ranges.
+setRange opts = opts { autoRange = True }
+
+-- | Enable the checking of the internal default style.
+setCheckStyle opts = opts { checkInternalStyle = True }
+
+-- | Disable case sensitivity in ordering.
+setNoCase opts = opts { caseSens = False }
+
+-- | Enable the two letters defaults header
+setDblHeader opts = opts { fileStyle = StyleDouble }
+
+
+-- | Set the language definition to check
+setCheckLanguage "english" opts = Right $ opts { checkLanguageDef = Just "english" }
+setCheckLanguage "french" opts = Right $ opts { checkLanguageDef = Just "french" }
+setCheckLanguage "german" opts = Right $ opts { checkLanguageDef = Just "german" }
+setCheckLanguage "russian" opts = Right $ opts { checkLanguageDef = Just "russian" }
+setCheckLanguage str opts = Left $ "/!\\ ERROR The language " ++ str ++ " is not recognized"
+
+
+-- | List of all possibles cli modes.
+lstModes :: [Mode MyModes]
+lstModes =
+ [ modeGenIndexEnglish
+ , modeGenIndexFrench
+ , modeGenIndexGerman
+ , modeGenIndexRussian
+ , modeGenIndexCustom
+ , modeGenCheck
+ ]
+
+
+
+-- | The main cli mode.
+--
+-- Contain all the languages modes with the help and version flags.
+modesCLI mods = (modes _ProgName ArgHelp "" mods) { modeGroupFlags = toGroup [helpFlag, versionFlag] }
+ where
+ helpFlag = flagNone ["help", "h", "?"] (const ArgHelp) "Help message"
+ versionFlag = flagNone ["version", "V"] (const ArgVersion) "Version informations"
+
+
+
+_ProgName = "hsindex"
+_ProgDetails = "A program to create indexes for LaTeX and XeTeX"
+_Auteur = "(c) Jean-Luc JOULIN 2018-2020"
+_Version = "0.12.0"
+
+
+-- | The main function.
+main :: IO ()
+main = do
+ setLocaleEncoding utf8 -- solve bug commitBuffer: invalid argument (invalid character)
+ opts <- processArgs $ modesCLI lstModes
+ outputScreen opts
+
+
+-- | Main function to output result to screen.
+outputScreen opts@(IndexEnglish fin fou fsty rng cas ) = do
+ let fout = if null fou then ((dropExtension fin) ++ ".ind") else fou
+ readAllFile
+ fin
+ fsty
+ parseIndexFile
+ (\ent idx -> do
+ let entc = concatPagesItems ent
+ ents = sortItems cas langDefEnglish (equivItems True langDefEnglish entc)
+ entd = splitIndex idx ents
+ writeIndex fout idx rng entd
+ )
+
+outputScreen opts@(IndexFrench fin fou fsty rng cas ) = do
+ let fout = if null fou then ((dropExtension fin) ++ ".ind") else fou
+ readAllFile
+ fin
+ fsty
+ parseIndexFile
+ (\ent idx -> do
+ let entc = concatPagesItems ent
+ ents = sortItems cas langDefFrench (equivItems True langDefFrench entc)
+ entd = splitIndex idx ents
+ writeIndex fout idx rng entd
+ )
+
+outputScreen opts@(IndexGerman fin fou fsty rng cas ) = do
+ let fout = if null fou then ((dropExtension fin) ++ ".ind") else fou
+ readAllFile
+ fin
+ fsty
+ parseIndexFile
+ (\ent idx -> do
+ let entc = concatPagesItems ent
+ ents = sortItems cas langDefGerman (equivItems True langDefGerman entc)
+ entd = splitIndex idx ents
+ writeIndex fout idx rng entd
+ )
+
+outputScreen opts@(IndexRussian fin fou fsty rng cas ) = do
+ let fout = if null fou then ((dropExtension fin) ++ ".ind") else fou
+ readAllFile
+ fin
+ fsty
+ parseIndexFile
+ (\ent idx -> do
+ let entc = concatPagesItems ent
+ ents = sortItems cas langDefRussian (equivItems True langDefRussian entc)
+ entd = splitIndex idx ents
+ writeIndex fout idx rng entd
+ )
+
+outputScreen opts@(IndexCustom fin fou fsty rng cas fdef) = do
+ let fout = if null fou then ((dropExtension fin) ++ ".ind") else fou
+ readDefinitionFile
+ fdef
+ (\def -> readAllFile
+ fin
+ fsty
+ parseIndexFile
+ (\ent idx -> do
+ let entc = concatPagesItems ent
+ ents = sortItems cas def { lstLetters = (lstLetters def) } (equivItems True def entc)
+ entd = splitIndex idx ents
+ putStrLn $ "Building index with custom language definition"
+ putStrLn $ showLangDef def
+ writeIndex fout idx rng entd
+ )
+ )
+
+outputScreen opts@(IndexCheck sty mblang ) = do
+ if sty
+ then do
+ putStrLn $ showStyle styleBasic
+ else putStrLn ""
+ case mblang of
+ Nothing -> do
+ putStrLn ""
+ Just "english" -> putStrLn $ showLangDef langDefEnglish
+ Just "french" -> putStrLn $ showLangDef langDefFrench
+ Just "german" -> putStrLn $ showLangDef langDefGerman
+ Just "russian" -> putStrLn $ showLangDef langDefRussian
+
+outputScreen opts@ArgHelp = do
+ putStrLn $ unlines logo
+ putStrLn $ " " ++ _ProgDetails
+ putStrLn $ " " ++ _Auteur
+ putStrLn $ " Version : " ++ _Version
+ print $ helpText [] HelpFormatAll (modesCLI lstModes)
+ exitSuccess
+
+outputScreen opts@ArgVersion = do
+ putStrLn $ unlines logo
+ putStrLn $ " " ++ _ProgDetails
+ putStrLn $ " " ++ _Auteur
+ putStrLn $ " Version : " ++ _Version
+ exitSuccess
+
+
+
+
+
+
+
+