Bump-up version to 8.2.2 and update Changelog

Remove trailing spaces

.clang-format

@@ -0,0 +1,12 @@
+BasedOnStyle:  Google
+BinPackArguments: false
+BinPackParameters: false
+BreakBeforeBinaryOperators: All
+BreakBeforeBraces: Linux
+DerivePointerAlignment: false
+SpacesInContainerLiterals: false
+Standard: Cpp11
+
+AllowShortFunctionsOnASingleLine: Inline
+AllowShortIfStatementsOnASingleLine: false
+AllowShortLoopsOnASingleLine: false

.codecov.yml

@@ -0,0 +1,12 @@
+codecov:
+  notify:
+    require_ci_to_pass: yes
+
+coverage:
+  status:
+    project:
+      default:
+        threshold: 1%
+
+ignore:
+  - "test"

.github/FUNDING.yml

@@ -0,0 +1,12 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+custom: https://kiwix.org/support-us/

.github/move.yml

@@ -0,0 +1,27 @@
+# Configuration for Move Issues - https://github.com/dessant/move-issues
+
+# Delete the command comment when it contains no other content
+deleteCommand: true
+
+# Close the source issue after moving
+closeSourceIssue: true
+
+# Lock the source issue after moving
+lockSourceIssue: false
+
+# Mention issue and comment authors
+mentionAuthors: true
+
+# Preserve mentions in the issue content
+keepContentMentions: true
+
+# Move labels that also exist on the target repository
+moveLabels: true
+
+# Set custom aliases for targets
+# aliases:
+#   r: repo
+#   or: owner/repo
+
+# Repository to extend settings from
+# _extends: repo

.github/stale.yml

@@ -0,0 +1,15 @@
+daysUntilClose: false
+staleLabel: stale
+
+issues:
+  daysUntilStale: 60
+  markComment: >
+    This issue has been automatically marked as stale because it has not had
+    recent activity. It will be now be reviewed manually. Thank you
+    for your contributions.
+pulls:
+   daysUntilStale: 7
+   markComment: >
+     This pull request has been automatically marked as stale because it has not had
+     recent activity. It will be now be reviewed manually. Thank you
+     for your contributions.

.gitignore

@@ -0,0 +1,3 @@
+.idea/
+*.swp
+subprojects/googletest-release*

.travis.yml

@@ -0,0 +1,42 @@
+language: cpp
+dist: xenial
+sudo: true
+cache: ccache
+before_install:
+- PATH=$PATH:$HOME/bin
+install: travis/install_deps.sh
+script: travis/compile.sh
+env:
+  matrix:
+    - PLATFORM="native_static"
+    - PLATFORM="native_dyn"
+    - PLATFORM="win32_static"
+    - PLATFORM="win32_dyn"
+    - PLATFORM="android_arm"
+    - PLATFORM="android_arm64"
+addons:
+  apt:
+    packages:
+      - cmake
+      - python3.5
+      - python3-pip
+      - libbz2-dev
+      - ccache
+      - zlib1g-dev
+      - uuid-dev
+      - libctpp2-dev
+      - ctpp2-utils
+      - libmicrohttpd-dev
+      - g++-mingw-w64-i686
+      - gcc-mingw-w64-i686
+      - gcc-mingw-w64-base
+      - mingw-w64-tools
+      - gcovr
+  homebrew:
+    update: true
+    packages:
+      - gcovr
+matrix:
+  include:
+    - env: PLATFORM="native_dyn"
+      os: osx

AUTHORS

@@ -0,0 +1,17 @@
+Automactic <christopherliqd@gmail.com>
+Ayoub DARDORY <ayoubuto@gmail.com>
+Cristian Patrasciuc <cristip@google.com>
+Dattaz <taz@dattaz.fr>
+Elad Keyshawn <elad.keyshawn@gmail.com>
+Emmanuel Engelhart <kelson@kiwix.org>
+Isaac <mhutti1@gmail.com>
+jleow00 <leow.yonghan.jerome@gmail.com>
+Julian Harty <julianharty@gmail.com>
+Kiran Mathew Koshy <kiranmathewkoshy@gmail.com>
+Kunal Mehta <legoktm@member.fsf.org>
+Matthieu Gautier <mgautier@kymeria.fr>
+Rashiq Ahmad <rashiq.z@gmail.com>
+Renaud Gaudin <reg@kiwix.org>
+Shivam <ssarodia@gmail.com>
+Steve Wills <steve@mouf.net>
+Synhershko <synhershko@users.sourceforge.net>

COPYING

@@ -0,0 +1,676 @@
+
+		    GNU GENERAL PUBLIC LICENSE
+		       Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+			    Preamble
+
+  The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+  The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works.  By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users.  We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors.  You can apply it to
+your programs, too.
+
+  When we speak of free software, we are referring to freedom, not
+price.  Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+  To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights.  Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+  For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received.  You must make sure that they, too, receive
+or can get the source code.  And you must show them these terms so they
+know their rights.
+
+  Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+  For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software.  For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+  Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so.  This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software.  The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable.  Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products.  If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+  Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary.  To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+  The precise terms and conditions for copying, distribution and
+modification follow.
+
+		       TERMS AND CONDITIONS
+
+  0. Definitions.
+
+  "This License" refers to version 3 of the GNU General Public License.
+
+  "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+  "The Program" refers to any copyrightable work licensed under this
+License.  Each licensee is addressed as "you".  "Licensees" and
+"recipients" may be individuals or organizations.
+
+  To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy.  The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+  A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+  To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy.  Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+  To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies.  Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+  An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License.  If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+  1. Source Code.
+
+  The "source code" for a work means the preferred form of the work
+for making modifications to it.  "Object code" means any non-source
+form of a work.
+
+  A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+  The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form.  A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+  The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities.  However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work.  For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+  The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+  The Corresponding Source for a work in source code form is that
+same work.
+
+  2. Basic Permissions.
+
+  All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met.  This License explicitly affirms your unlimited
+permission to run the unmodified Program.  The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work.  This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+  You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force.  You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright.  Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+  Conveying under any other circumstances is permitted solely under
+the conditions stated below.  Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+  3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+  No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+  When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+  4. Conveying Verbatim Copies.
+
+  You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+  You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+  5. Conveying Modified Source Versions.
+
+  You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+    a) The work must carry prominent notices stating that you modified
+    it, and giving a relevant date.
+
+    b) The work must carry prominent notices stating that it is
+    released under this License and any conditions added under section
+    7.  This requirement modifies the requirement in section 4 to
+    "keep intact all notices".
+
+    c) You must license the entire work, as a whole, under this
+    License to anyone who comes into possession of a copy.  This
+    License will therefore apply, along with any applicable section 7
+    additional terms, to the whole of the work, and all its parts,
+    regardless of how they are packaged.  This License gives no
+    permission to license the work in any other way, but it does not
+    invalidate such permission if you have separately received it.
+
+    d) If the work has interactive user interfaces, each must display
+    Appropriate Legal Notices; however, if the Program has interactive
+    interfaces that do not display Appropriate Legal Notices, your
+    work need not make them do so.
+
+  A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit.  Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+  6. Conveying Non-Source Forms.
+
+  You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+    a) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by the
+    Corresponding Source fixed on a durable physical medium
+    customarily used for software interchange.
+
+    b) Convey the object code in, or embodied in, a physical product
+    (including a physical distribution medium), accompanied by a
+    written offer, valid for at least three years and valid for as
+    long as you offer spare parts or customer support for that product
+    model, to give anyone who possesses the object code either (1) a
+    copy of the Corresponding Source for all the software in the
+    product that is covered by this License, on a durable physical
+    medium customarily used for software interchange, for a price no
+    more than your reasonable cost of physically performing this
+    conveying of source, or (2) access to copy the
+    Corresponding Source from a network server at no charge.
+
+    c) Convey individual copies of the object code with a copy of the
+    written offer to provide the Corresponding Source.  This
+    alternative is allowed only occasionally and noncommercially, and
+    only if you received the object code with such an offer, in accord
+    with subsection 6b.
+
+    d) Convey the object code by offering access from a designated
+    place (gratis or for a charge), and offer equivalent access to the
+    Corresponding Source in the same way through the same place at no
+    further charge.  You need not require recipients to copy the
+    Corresponding Source along with the object code.  If the place to
+    copy the object code is a network server, the Corresponding Source
+    may be on a different server (operated by you or a third party)
+    that supports equivalent copying facilities, provided you maintain
+    clear directions next to the object code saying where to find the
+    Corresponding Source.  Regardless of what server hosts the
+    Corresponding Source, you remain obligated to ensure that it is
+    available for as long as needed to satisfy these requirements.
+
+    e) Convey the object code using peer-to-peer transmission, provided
+    you inform other peers where the object code and Corresponding
+    Source of the work are being offered to the general public at no
+    charge under subsection 6d.
+
+  A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+  A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling.  In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage.  For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product.  A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+  "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source.  The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+  If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information.  But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+  The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed.  Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+  Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+  7. Additional Terms.
+
+  "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law.  If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+  When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it.  (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.)  You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+  Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+    a) Disclaiming warranty or limiting liability differently from the
+    terms of sections 15 and 16 of this License; or
+
+    b) Requiring preservation of specified reasonable legal notices or
+    author attributions in that material or in the Appropriate Legal
+    Notices displayed by works containing it; or
+
+    c) Prohibiting misrepresentation of the origin of that material, or
+    requiring that modified versions of such material be marked in
+    reasonable ways as different from the original version; or
+
+    d) Limiting the use for publicity purposes of names of licensors or
+    authors of the material; or
+
+    e) Declining to grant rights under trademark law for use of some
+    trade names, trademarks, or service marks; or
+
+    f) Requiring indemnification of licensors and authors of that
+    material by anyone who conveys the material (or modified versions of
+    it) with contractual assumptions of liability to the recipient, for
+    any liability that these contractual assumptions directly impose on
+    those licensors and authors.
+
+  All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10.  If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term.  If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+  If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+  Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+  8. Termination.
+
+  You may not propagate or modify a covered work except as expressly
+provided under this License.  Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+  However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+  Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+  Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License.  If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+  9. Acceptance Not Required for Having Copies.
+
+  You are not required to accept this License in order to receive or
+run a copy of the Program.  Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance.  However,
+nothing other than this License grants you permission to propagate or
+modify any covered work.  These actions infringe copyright if you do
+not accept this License.  Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+  10. Automatic Licensing of Downstream Recipients.
+
+  Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License.  You are not responsible
+for enforcing compliance by third parties with this License.
+
+  An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations.  If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+  You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License.  For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+  11. Patents.
+
+  A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based.  The
+work thus licensed is called the contributor's "contributor version".
+
+  A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version.  For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+  Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+  In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement).  To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+  If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients.  "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+  If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+  A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License.  You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+  Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+  12. No Surrender of Others' Freedom.
+
+  If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License.  If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all.  For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+  13. Use with the GNU Affero General Public License.
+
+  Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work.  The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+  14. Revised Versions of this License.
+
+  The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time.  Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+  Each version is given a distinguishing version number.  If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation.  If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+  If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+  Later license versions may give you additional or different
+permissions.  However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+  15. Disclaimer of Warranty.
+
+  THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW.  EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+  16. Limitation of Liability.
+
+  IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+  17. Interpretation of Sections 15 and 16.
+
+  If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+		     END OF TERMS AND CONDITIONS
+
+	    How to Apply These Terms to Your New Programs
+
+  If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+  To do so, attach the following notices to the program.  It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+    <one line to give the program's name and a brief idea of what it does.>
+    Copyright (C) <year>  <name of author>
+
+    This program is free software: you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation, either version 3 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+  If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+    <program>  Copyright (C) <year>  <name of author>
+    This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+    This is free software, and you are welcome to redistribute it
+    under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License.  Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+  You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<http://www.gnu.org/licenses/>.
+
+  The GNU General Public License does not permit incorporating your program
+into proprietary programs.  If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library.  If this is what you want to do, use the GNU Lesser General
+Public License instead of this License.  But first, please read
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.
+

ChangeLog

@@ -0,0 +1,305 @@
+kiwix-lib 8.2.2
+===============
+
+ * Improve a few compilation scripts
+
+kiwix-lib 8.2.1
+===============
+
+ * Reintroduce kiwix-serve taskbar
+
+kiwix-lib 8.2.0
+===============
+
+ * More debug information if aria2c command fails
+ * Allow to set kiwix-serve port
+ * Better (dead) bookmarks mgmt
+
+kiwix-lib 8.1.0
+===============
+
+ * Fix pathTools manipulation.
+ * Add missing implementation of getArticleCount and getMediaCount on android.
+ * Correctly convert windows path to utf8.
+ * Add code coverage in the CI
+
+kiwix-lib 8.0.1
+===============
+
+ * Fix join function
+
+kiwix-lib 8.0.0
+===============
+
+ * Add new methods to get all (and new) metadata from the zim file.
+ * Add methods to get the value of a specific tag.
+ * [API Change] Convert tags value to the new convention.
+ * [API Change] Rename `getMatatag` method to `getMetadata`
+ * [ABI Change] Correctly detect executable path in appimage.
+
+kiwix-lib 7.0.0
+===============
+
+ * [API break] Add a argument to kiwix-serve to specify the library to use.
+
+kiwix-lib 6.0.4
+===============
+
+ * Fix HTML rendering of the search result if there is no result.
+ * Do not crash at html rendering if request ask for 0 results (start == end)
+ * Correctly find the executable path if we are using AppImage
+
+kiwix-lib 6.0.3
+===============
+
+ * force one column suggestion in kiwix-serve suggestions
+ * fix fulltext search link in suggestions
+ * UI fixes in kiwix-serve rendering
+
+kiwix-lib 6.0.2
+===============
+
+ * Correctly set the groupId in the pom file.
+
+kiwix-lib 6.0.1
+===============
+
+ * Generate the pom file for android/maven
+
+kiwix-lib 6.0.0
+===============
+
+ * Move the server code in kiwix-lib (from kiwix-serve).
+ * Add unit test on regex functions.
+ * Fix computerAbsolutePath (thread safe, memory leak).
+ * Correctly set the book's path as valid if we construct the book from a
+   reader.
+ * [JNI] Add a method to know if a article is a redirection.
+ * Do not embed the gtest dependency.
+ * [JNI] Add a constructor to JNIKiwixString.
+ * Change order of search of the favicon urls.
+ * Clean a lot of unecessary includes in headers. (potential "API break")
+
+kiwix-lib 5.2.0
+===============
+
+ * kiwix-serve integration (as a seperated process).
+ * Fix crash in the suggestion search.
+ * Better API to filter the library books.
+ * New kiwix-lib application for android. (.aar)
+ * Use ReLinker to link with libkiwix.so in android.
+ * Correctly set the verbosity of zim search.
+
+kiwix-lib 5.1.0
+===============
+
+ * Add function to pause, resume and stop downloads.
+ * Add zim's tags in the opds stream.
+ * Addapt to new libzim 5.0.0 API.
+
+kiwix-lib 5.0.0
+===============
+
+ * Remove error message when trying to open an wrong zim file.
+ * Rewrite `makeTmpDirectory` to not use uuid functions on windows.
+ * [API break] Remove `getNetworkInterfaces` and `getBestPublicIp`.
+ * Remove rpath
+ * Detect infinite (and too long) redirect loops.
+
+kiwix-lib 4.1.0
+===============
+
+ * Allow the library to be filtered by tags.
+ * Fix language mapping.
+ * Update README about mustache dependency.
+
+kiwix-lib 4.0.1
+===============
+
+ * Fix "maybe uninitialize variable" issue.
+ * Ensure path are stored correctly (absolute path) in the library.
+ * [CI] Use the new deps archive xz
+
+kiwix-lib 4.0.0
+===============
+
+ * [API break] Remove support for external index.
+ * Move to the mustache templating system instead of ctpp2.
+ * Make meson.build works for meson>=0.43.0
+ * [API break] Move the basic tools from the `common` directory to `tools`.
+
+kiwix-lib 3.1.1
+===============
+
+ * The OPDS feed book's date must be the date of the book, not the date of the
+ feed generation.
+ * Convert the standard opds date to our format (YYYY-MM-DD)
+ * Remove duplicate language attribute in the libxml dumper.
+ * Create the datadirectory to not fail to write a file in a non-existent
+   directory
+
+kiwix-lib 3.1.0
+===============
+
+ * Add a method to get the favicon url of book (if available).
+ * Move dump code of library.xml in a specific class.
+ * Add a first support to bookmarks
+
+kiwix-lib 3.0.3
+===============
+
+ * Add the 'en' language to the mapping alpha2-code ('en') to alpha3-code
+ ('eng').
+ * Correctly write the 'ArticleCount' and 'MediaCount' in the library.xml.
+ * Correctly fill the book size for the zim file size.
+ * Fix launch of aria2c.
+
+kiwix-lib 3.0.2
+===============
+
+ * Use the correct path separator when computing relativePath on Windows.
+
+kiwix-lib 3.0.1
+===============
+
+ * Small fix about parsing the opdsStream.
+
+kiwix-lib 3.0.0
+===============
+
+ * Change the downloader to use aria2 using a separated process (with rpc)
+   instead of using the libaria2. This simplify a lot the link process to
+   libaria2 on Windows.
+    - kiwix-lib doesn't depend on libaria2 anymore.
+    - kiwix-lib now depends on libcurl.
+ * [API break] Library class API has been updated :
+    - Books are referenced by id, not index. A lot of methods have been
+      updated this way.
+    - Books "list" is now private.
+    - There is no more "current" book.
+    - listBooksIds's filters have been updated.
+ * [API break] Book class API has been updated :
+    - Move the definition of Book in `book.h`.
+    - Use getter/setter methods instead public members.
+    - Size (getSize/setSize) is now returned in bytes, not kB.
+    - Dependending of how the book has been initialized (opdsfeed), the
+      faviconUrl may be stored in the book, the favicon being downloaded when
+      using `getFavicon`.
+    - The path (and indexPath) are always absolute path.
+    - Book has now a downloadId, corresponding to the aria2 download id (if
+      exists)
+  * [API break] Manager class API has been updated :
+    - The manager is mainly use to fill a Libray from a "library.xml" file or
+      opds feed. Other operations (has removeBookById, setBookPath, filter, ...)
+      have been removed.
+    - The manager use a intermediate class (LibraryManipulator) to add book to
+      the library. This dependency injection allow caller code to hook the add
+      of a book to the library.
+    - The manager work on a existing Library. It doesn't how a internal
+      Library.
+  * [API break] OpdsDumper class API has been updated :
+    - dumpOPDSFeed method now take the list of bookIds to dump instead of
+      dumping all books in the library.
+    - OpdsDumper can now dump openSearch result information (total result
+      count, start index, ...).
+  * [API break] Common tools API has been updated :
+    - `base64_encode` and `base64_decode` take std::string as arguments.
+    - New `download` function in networkTools.h using libcurl.
+    - New `getDataDirectory` function in pathTools.
+    - Better `beautifyInteger` and `beautifyFileSize` functions.
+    - New `nodeToString` function serializing a pugi::xml_node to a string.
+    - New `converta2toa3` function to convert alpha2 language code to aplha3
+      language code.
+
+
+kiwix-lib 2.0.2
+===============
+
+ * [Android] Forward c++ errors message de Java world.
+ * Follow redirection of favicon.
+ * Make aria2 dependency optional.
+ * Inculde unistd.h only on unix platform.
+
+kiwix-lib 2.0.1
+===============
+
+ * Fix parsing of url.
+ * Remove unused static resources.
+ * Correctly decode reserved characters in URLs.
+ * Explicitly use icu namespace to allow use of packaged icu lib.
+
+kiwix-lib 2.0.0
+===============
+
+ * Introduce a new API to retrive content from a reader.
+   * Introduce the `Entry` class.
+   * Reader's methods return an `Entry`.
+   * Content and other information can be retrieved from the `Entry`.
+   * Older Reader's methods are depreciated.
+ * Add an `OPDSDumper` class to dump a whole `Library` as an OPDS feed.
+ * Add a tool function to get the content of a file.
+ * Add a tool function to create a tempory directory.
+ * Add a `Downloader` class to download a file.
+ * Allow the manager to populate a `Library` from an OPDS feed.
+ * Try to locate libctpp2 in default system libdir and then fallback in 'lib'
+   directory.
+ * Build kiwix-lib setting RPATH.
+ * Build kiwix-lib without warning (werror=true)
+ * Build kiwix-lib on macos.
+
+kiwix-lib 1.1.1
+===============
+
+ * Correct the name of kiwix-lib (from `kiwixlib`) in meson.build to generate
+   dist archive with the correct name.
+ * Libzim version need to be at least 3.2.0
+
+kiwix-lib 1.1.0
+===============
+
+ * Allow for more than 70 search result per page in html results rendering
+   (kiwix/kiwix-tools#92)
+ * Add a small api to do geo queries.
+ * Add multi-search support in the JNI (#67)
+ * Add an API to get only one part of an article.
+ * Add an API to get direct location of an article content in the zim file.
+ * Improve urlencoding
+ * Fix pagination in html results rendering.
+ * Compile using gcc-5 on Travis.
+ * Allow JNI to access search snippets.
+ * JNI throw an exception instead of returning an invalid object if something
+   goes wrong.
+ * Add doctext documentation. (#116)
+ * Various bug fixes.
+
+kiwix-lib 1.0.0
+===============
+
+ * Correctly regenerate template resource using cttp2c at compilation time.
+ * Suggestion use xapian database when available
+ * Support multi-zim search in kiwix-lib (a search can now search on several
+   embedded database in zims in the same time)
+ * Fix some wording
+ * Fix license issues
+ * Add out argument to jni getContent* method to get the title of article in
+   the same time we get the content
+ * Rename `compile_resources.py` script to `kiwix-compile-resources`
+ * Use static lib when building for android or in "static mode"
+ * Make the ResourceNotFound exception public
+
+kiwix-lib 0.2.0
+===============
+
+ * Generate the snippet from the article content if the snippet is not
+ directly in the database.
+   This provide better snippets as they now depending of the query.
+ * Use the stopwords and the language stored in the fulltext index database to
+ parse the user query.
+ * Remove the indexer functionnality.
+ * Move to C++11 standard.
+ * Use the fulltext search of the zimlib.
+   We still have the fulltext search code in kiwix-lib to be able to search in
+   fulltext index by side of a zim file. (To be remove in the future)
+ * Few API hanges
+   * Change a lot of `Reader` methods to const methods.
+ * Fix some crashes.

README.md

@@ -0,0 +1,144 @@
+Kiwix library
+=============
+
+The Kiwix library provides the [Kiwix](https://kiwix.org) software
+suite core. It contains the code shared by all Kiwix ports (Windows,
+GNU/Linux, macOS, Android, iOS, ...).
+
+[![Download](https://api.bintray.com/packages/kiwix/kiwix/kiwixlib/images/download.svg)](https://bintray.com/kiwix/kiwix/kiwixlib/_latestVersion)
+[![AUR version](https://img.shields.io/aur/version/kiwix-lib)](https://aur.archlinux.org/packages/kiwix-lib/)
+[![Build Status](https://travis-ci.com/kiwix/kiwix-lib.svg?branch=master)](https://travis-ci.com/kiwix/kiwix-lib)
+[![CodeFactor](https://www.codefactor.io/repository/github/kiwix/kiwix-lib/badge)](https://www.codefactor.io/repository/github/kiwix/kiwix-lib)
+[![Codecov](https://codecov.io/gh/kiwix/kiwix-lib/branch/master/graph/badge.svg)](https://codecov.io/gh/kiwix/kiwix-lib)
+[![License: GPL v3](https://img.shields.io/badge/License-GPLv3-blue.svg)](https://www.gnu.org/licenses/gpl-3.0)
+
+Disclaimer
+----------
+
+This document assumes you have a little knowledge about software
+compilation. If you experience difficulties with the dependencies or
+with the Kiwix libary compilation itself, we recommend to have a look
+to [kiwix-build](https://github.com/kiwix/kiwix-build).
+
+Preamble
+--------
+
+Although the Kiwix library can be (cross-)compiled on/for many
+sytems, the following documentation explains how to do it on POSIX
+ones. It is primarly thought for GNU/Linux systems and has been tested
+on recent releases of Ubuntu and Fedora.
+
+Dependencies
+------------
+
+The Kiwix library relies on many third parts software libraries. They
+are prerequisites to the Kiwix library compilation. Following
+libraries need to be available:
+
+* [ICU](https://site.icu-project.org/) (package `libicu-dev` on Ubuntu)
+* [ZIM](https://openzim.org/) (package `libzim-dev` on Ubuntu)
+* [Pugixml](https://pugixml.org/) (package `libpugixml-dev` on Ubuntu)
+* [Aria2](https://aria2.github.io/) (package `aria2` on Ubuntu)
+* [Mustache](https://github.com/kainjow/Mustache) (Just copy the
+header `mustache.hpp` somewhere it can be found by the compiler and/or
+set CPPFLAGS with correct `-I` option)
+
+These dependencies may or may not be packaged by your operating
+system. They may also be packaged but only in an older version. The
+compilation script will tell you if one of them is missing or too old.
+In the worse case, you will have to download and compile bleeding edge
+version by hand.
+
+If you want to install these dependencies locally, then use the
+`kiwix-lib` directory as install prefix.
+
+Environment
+-------------
+
+The Kiwix library builds using [Meson](https://mesonbuild.com/) version
+0.43 or higher. Meson relies itself on Ninja, pkg-config and few other
+compilation tools.
+
+Install first the few common compilation tools:
+* [Meson](https://mesonbuild.com/)
+* [Ninja](https://ninja-build.org/)
+* [pkg-config](https://www.freedesktop.org/wiki/Software/pkg-config/)
+
+These tools should be packaged if you use a cutting edge operating
+system. If not, have a look to the [Troubleshooting](#Troubleshooting)
+section.
+
+Compilation
+-----------
+
+Once all dependencies are installed, you can compile the Kiwix library
+with:
+```bash
+meson . build
+ninja -C build
+```
+
+By default, it will compile dynamic linked libraries. All binary files
+will be created in the "build" directory created automatically by
+Meson. If you want statically linked libraries, you can add
+`--default-library=static` option to the Meson command.
+
+Depending of you system, `ninja` may be called `ninja-build`.
+
+Installation
+------------
+
+If you want to install the Kiwix library and the headers you just have
+compiled on your system, here we go:
+```bash
+ninja -C build install
+```
+
+You might need to run the command as root (or using `sudo`), depending
+where you want to install the libraries. After the installation
+succeeded, you may need to run `ldconfig` (as `root`).
+
+Uninstallation
+------------
+
+If you want to uninstall the Kiwix library:
+```bash
+ninja -C build uninstall
+```
+
+Like for the installation, you might need to run the command as `root`
+(or using `sudo`).
+
+Troubleshooting
+---------------
+
+If you need to install Meson "manually":
+```bash
+virtualenv -p python3 ./ # Create virtualenv
+source bin/activate      # Activate the virtualenv
+pip3 install meson       # Install Meson
+hash -r                  # Refresh bash paths
+```
+
+If you need to install Ninja "manually":
+```bash
+git clone git://github.com/ninja-build/ninja.git
+cd ninja
+git checkout release
+./configure.py --bootstrap
+mkdir ../bin
+cp ninja ../bin
+cd ..
+```
+
+If the compilation still fails, you might need to get a more recent
+version of a dependency than the one packaged by your Linux
+distribution. Try then with a source tarball distributed by the
+problematic upstream project or even directly from the source code
+repository.
+
+License
+-------
+
+[GPLv3](https://www.gnu.org/licenses/gpl-3.0) or later, see
+[COPYING](COPYING) for more details.

android-kiwix-lib-publisher/.gitignore

@@ -0,0 +1,13 @@
+*.iml
+.gradle
+/local.properties
+/.idea/caches
+/.idea/libraries
+/.idea/modules.xml
+/.idea/workspace.xml
+/.idea/navEditor.xml
+/.idea/assetWizardSettings.xml
+.DS_Store
+/build
+/captures
+.externalNativeBuild

android-kiwix-lib-publisher/build.gradle

@@ -0,0 +1,25 @@
+// Top-level build file where you can add configuration options common to all sub-projects/modules.
+
+buildscript {
+    repositories {
+        google()
+        jcenter()
+
+    }
+    dependencies {
+        classpath 'com.android.tools.build:gradle:3.4.1'
+        // NOTE: Do not place your application dependencies here; they belong
+        // in the individual module build.gradle files
+    }
+}
+
+allprojects {
+    repositories {
+        google()
+        jcenter()
+    }
+}
+
+task clean(type: Delete) {
+    delete rootProject.buildDir
+}

android-kiwix-lib-publisher/gradle.properties

@@ -0,0 +1,15 @@
+# Project-wide Gradle settings.
+# IDE (e.g. Android Studio) users:
+# Gradle settings configured through the IDE *will override*
+# any settings specified in this file.
+# For more details on how to configure your build environment visit
+# http://www.gradle.org/docs/current/userguide/build_environment.html
+# Specifies the JVM arguments used for the daemon process.
+# The setting is particularly useful for tweaking memory settings.
+org.gradle.jvmargs=-Xmx1536m
+# When configured, Gradle will run in incubating parallel mode.
+# This option should only be used with decoupled projects. More details, visit
+# http://www.gradle.org/docs/current/userguide/multi_project_builds.html#sec:decoupled_projects
+# org.gradle.parallel=true
+# Kotlin code style for this project: "official" or "obsolete":
+kotlin.code.style=official

android-kiwix-lib-publisher/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Wed Jun 19 15:28:39 BST 2019
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-5.1.1-all.zip

android-kiwix-lib-publisher/gradlew

@@ -0,0 +1,172 @@
+#!/usr/bin/env sh
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# Attempt to set APP_HOME
+# Resolve links: $0 may be a link
+PRG="$0"
+# Need this for relative symlinks.
+while [ -h "$PRG" ] ; do
+    ls=`ls -ld "$PRG"`
+    link=`expr "$ls" : '.*-> \(.*\)$'`
+    if expr "$link" : '/.*' > /dev/null; then
+        PRG="$link"
+    else
+        PRG=`dirname "$PRG"`"/$link"
+    fi
+done
+SAVED="`pwd`"
+cd "`dirname \"$PRG\"`/" >/dev/null
+APP_HOME="`pwd -P`"
+cd "$SAVED" >/dev/null
+
+APP_NAME="Gradle"
+APP_BASE_NAME=`basename "$0"`
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn () {
+    echo "$*"
+}
+
+die () {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+nonstop=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+  NONSTOP* )
+    nonstop=true
+    ;;
+esac
+
+CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
+
+# Determine the Java command to use to start the JVM.
+if [ -n "$JAVA_HOME" ] ; then
+    if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
+        # IBM's JDK on AIX uses strange locations for the executables
+        JAVACMD="$JAVA_HOME/jre/sh/java"
+    else
+        JAVACMD="$JAVA_HOME/bin/java"
+    fi
+    if [ ! -x "$JAVACMD" ] ; then
+        die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+    fi
+else
+    JAVACMD="java"
+    which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+fi
+
+# Increase the maximum file descriptors if we can.
+if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
+    MAX_FD_LIMIT=`ulimit -H -n`
+    if [ $? -eq 0 ] ; then
+        if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
+            MAX_FD="$MAX_FD_LIMIT"
+        fi
+        ulimit -n $MAX_FD
+        if [ $? -ne 0 ] ; then
+            warn "Could not set maximum file descriptor limit: $MAX_FD"
+        fi
+    else
+        warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
+    fi
+fi
+
+# For Darwin, add options to specify how the application appears in the dock
+if $darwin; then
+    GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
+fi
+
+# For Cygwin, switch paths to Windows format before running java
+if $cygwin ; then
+    APP_HOME=`cygpath --path --mixed "$APP_HOME"`
+    CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
+    JAVACMD=`cygpath --unix "$JAVACMD"`
+
+    # We build the pattern for arguments to be converted via cygpath
+    ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
+    SEP=""
+    for dir in $ROOTDIRSRAW ; do
+        ROOTDIRS="$ROOTDIRS$SEP$dir"
+        SEP="|"
+    done
+    OURCYGPATTERN="(^($ROOTDIRS))"
+    # Add a user-defined pattern to the cygpath arguments
+    if [ "$GRADLE_CYGPATTERN" != "" ] ; then
+        OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
+    fi
+    # Now convert the arguments - kludge to limit ourselves to /bin/sh
+    i=0
+    for arg in "$@" ; do
+        CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
+        CHECK2=`echo "$arg"|egrep -c "^-"`                                 ### Determine if an option
+
+        if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then                    ### Added a condition
+            eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
+        else
+            eval `echo args$i`="\"$arg\""
+        fi
+        i=$((i+1))
+    done
+    case $i in
+        (0) set -- ;;
+        (1) set -- "$args0" ;;
+        (2) set -- "$args0" "$args1" ;;
+        (3) set -- "$args0" "$args1" "$args2" ;;
+        (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
+        (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
+        (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
+        (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
+        (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
+        (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
+    esac
+fi
+
+# Escape application args
+save () {
+    for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
+    echo " "
+}
+APP_ARGS=$(save "$@")
+
+# Collect all arguments for the java command, following the shell quoting and substitution rules
+eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
+
+# by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
+if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
+  cd "$(dirname "$0")"
+fi
+
+exec "$JAVACMD" "$@"

android-kiwix-lib-publisher/gradlew.bat

@@ -0,0 +1,84 @@
+@if "%DEBUG%" == "" @echo off
+@rem ##########################################################################
+@rem
+@rem  Gradle startup script for Windows
+@rem
+@rem ##########################################################################
+
+@rem Set local scope for the variables with windows NT shell
+if "%OS%"=="Windows_NT" setlocal
+
+set DIRNAME=%~dp0
+if "%DIRNAME%" == "" set DIRNAME=.
+set APP_BASE_NAME=%~n0
+set APP_HOME=%DIRNAME%
+
+@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+set DEFAULT_JVM_OPTS=
+
+@rem Find java.exe
+if defined JAVA_HOME goto findJavaFromJavaHome
+
+set JAVA_EXE=java.exe
+%JAVA_EXE% -version >NUL 2>&1
+if "%ERRORLEVEL%" == "0" goto init
+
+echo.
+echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:findJavaFromJavaHome
+set JAVA_HOME=%JAVA_HOME:"=%
+set JAVA_EXE=%JAVA_HOME%/bin/java.exe
+
+if exist "%JAVA_EXE%" goto init
+
+echo.
+echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:init
+@rem Get command-line arguments, handling Windows variants
+
+if not "%OS%" == "Windows_NT" goto win9xME_args
+
+:win9xME_args
+@rem Slurp the command line arguments.
+set CMD_LINE_ARGS=
+set _SKIP=2
+
+:win9xME_args_slurp
+if "x%~1" == "x" goto execute
+
+set CMD_LINE_ARGS=%*
+
+:execute
+@rem Setup the command line
+
+set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
+
+@rem Execute Gradle
+"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
+
+:end
+@rem End local scope for the variables with windows NT shell
+if "%ERRORLEVEL%"=="0" goto mainEnd
+
+:fail
+rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
+rem the _cmd.exe /c_ return code!
+if  not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
+exit /b 1
+
+:mainEnd
+if "%OS%"=="Windows_NT" endlocal
+
+:omega

android-kiwix-lib-publisher/kiwixLibAndroid/.gitignore

@@ -0,0 +1 @@
+/build

android-kiwix-lib-publisher/kiwixLibAndroid/build.gradle

@@ -0,0 +1,64 @@
+apply plugin: 'com.android.library'
+apply plugin: 'maven'
+
+android {
+    compileSdkVersion 28
+    defaultConfig {
+        minSdkVersion 15
+        targetSdkVersion 28
+        versionCode 1
+        versionName "1.0"
+    }
+    buildTypes {
+        release {
+            minifyEnabled false
+            proguardFiles getDefaultProguardFile('proguard-android-optimize.txt'), 'proguard-rules.pro'
+        }
+    }
+}
+
+dependencies {
+    implementation 'com.getkeepsafe.relinker:relinker:1.3.1'
+}
+
+task writePom {
+  pom {
+    project {
+        groupId 'org.kiwix.kiwixlib'
+        artifactId 'kiwixlib'
+        version '8.2.2' + (System.env.KIWIXLIB_BUILDVERSION == null ? '' : '-'+System.env.KIWIXLIB_BUILDVERSION)
+        packaging 'aar'
+        name 'kiwixlib'
+        url 'https://github.com/kiwix/kiwix-lib'
+        licenses {
+            license {
+                name 'GPLv3'
+                url 'https://www.gnu.org/licenses/gpl-3.0.en.html'
+            }
+        }
+      developers {
+          developer {
+              id 'kiwix'
+              name 'kiwix'
+              email 'contact@kiwix.org'
+          }
+      }
+      scm {
+          connection 'https://github.com/kiwix/kiwix-lib.git'
+          developerConnection 'https://github.com/kiwix/kiwix-lib.git'
+          url 'https://github.com/kiwix/kiwix-lib'
+      }
+    }
+  }.withXml {
+    def dependenciesNode = asNode().appendNode('dependencies')
+
+    //Iterate over the implementation dependencies, adding a <dependency> node for each
+    configurations.implementation.allDependencies.each {
+      def dependencyNode = dependenciesNode.appendNode('dependency')
+      dependencyNode.appendNode('groupId', it.group)
+      dependencyNode.appendNode('artifactId', it.name)
+      dependencyNode.appendNode('version', it.version)
+    }
+  }.writeTo("$buildDir/pom.xml")
+}
+

android-kiwix-lib-publisher/kiwixLibAndroid/proguard-rules.pro

@@ -0,0 +1,21 @@
+# Add project specific ProGuard rules here.
+# You can control the set of applied configuration files using the
+# proguardFiles setting in build.gradle.
+#
+# For more details, see
+#   http://developer.android.com/guide/developing/tools/proguard.html
+
+# If your project uses WebView with JS, uncomment the following
+# and specify the fully qualified class name to the JavaScript interface
+# class:
+#-keepclassmembers class fqcn.of.javascript.interface.for.webview {
+#   public *;
+#}
+
+# Uncomment this to preserve the line number information for
+# debugging stack traces.
+#-keepattributes SourceFile,LineNumberTable
+
+# If you keep the line number information, uncomment this to
+# hide the original source file name.
+#-renamesourcefileattribute SourceFile

android-kiwix-lib-publisher/kiwixLibAndroid/src/main/AndroidManifest.xml

@@ -0,0 +1,10 @@
+<manifest xmlns:android="http://schemas.android.com/apk/res/android"
+    package="kiwix.org.kiwixlib">
+
+    <application
+        android:allowBackup="true"
+        android:supportsRtl="true">
+
+    </application>
+
+</manifest>

android-kiwix-lib-publisher/settings.gradle

@@ -0,0 +1 @@
+include ':kiwixLibAndroid'

format_code.sh

@@ -0,0 +1,36 @@
+#!/usr/bin/bash
+
+files=(
+"include/library.h"
+"include/common/stringTools.h"
+"include/common/pathTools.h"
+"include/common/otherTools.h"
+"include/common/regexTools.h"
+"include/common/networkTools.h"
+"include/manager.h"
+"include/reader.h"
+"include/kiwix.h"
+"include/xapianSearcher.h"
+"include/searcher.h"
+"src/library.cpp"
+"src/android/kiwix.cpp"
+"src/android/org/kiwix/kiwixlib/JNIKiwixBool.java"
+"src/android/org/kiwix/kiwixlib/JNIKiwix.java"
+"src/android/org/kiwix/kiwixlib/JNIKiwixString.java"
+"src/android/org/kiwix/kiwixlib/JNIKiwixInt.java"
+"src/searcher.cpp"
+"src/common/pathTools.cpp"
+"src/common/regexTools.cpp"
+"src/common/otherTools.cpp"
+"src/common/networkTools.cpp"
+"src/common/stringTools.cpp"
+"src/xapianSearcher.cpp"
+"src/manager.cpp"
+"src/reader.cpp"
+)
+
+for i in "${files[@]}"
+do
+  echo $i
+  clang-format -i -style=file $i
+done

include/book.h

@@ -0,0 +1,119 @@
+/*
+ * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_BOOK_H
+#define KIWIX_BOOK_H
+
+#include <string>
+
+namespace pugi {
+class xml_node;
+}
+
+namespace kiwix
+{
+
+class OPDSDumper;
+class Reader;
+
+/**
+ * A class to store information about a book (a zim file)
+ */
+class Book
+{
+ public:
+  Book();
+  ~Book();
+
+  bool update(const Book& other);
+  void update(const Reader& reader);
+  void updateFromXml(const pugi::xml_node& node, const std::string& baseDir);
+  void updateFromOpds(const pugi::xml_node& node, const std::string& urlHost);
+  std::string getHumanReadableIdFromPath() const;
+
+  bool readOnly() const { return m_readOnly; }
+  const std::string& getId() const { return m_id; }
+  const std::string& getPath() const { return m_path; }
+  bool isPathValid() const { return m_pathValid; }
+  const std::string& getTitle() const { return m_title; }
+  const std::string& getDescription() const { return m_description; }
+  const std::string& getLanguage() const { return m_language; }
+  const std::string& getCreator() const { return m_creator; }
+  const std::string& getPublisher() const { return m_publisher; }
+  const std::string& getDate() const { return m_date; }
+  const std::string& getUrl() const { return m_url; }
+  const std::string& getName() const { return m_name; }
+  const std::string& getTags() const { return m_tags; }
+  const std::string& getOrigId() const { return m_origId; }
+  const uint64_t& getArticleCount() const { return m_articleCount; }
+  const uint64_t& getMediaCount() const { return m_mediaCount; }
+  const uint64_t& getSize() const { return m_size; }
+  const std::string& getFavicon() const;
+  const std::string& getFaviconUrl() const { return m_faviconUrl; }
+  const std::string& getFaviconMimeType() const { return m_faviconMimeType; }
+  const std::string& getDownloadId() const { return m_downloadId; }
+
+  void setReadOnly(bool readOnly) { m_readOnly = readOnly; }
+  void setId(const std::string& id) { m_id = id; }
+  void setPath(const std::string& path);
+  void setPathValid(bool valid) { m_pathValid = valid; }
+  void setTitle(const std::string& title) { m_title = title; }
+  void setDescription(const std::string& description) { m_description = description; }
+  void setLanguage(const std::string& language) { m_language = language; }
+  void setCreator(const std::string& creator) { m_creator = creator; }
+  void setPublisher(const std::string& publisher) { m_publisher = publisher; }
+  void setDate(const std::string& date) { m_date = date; }
+  void setUrl(const std::string& url) { m_url = url; }
+  void setName(const std::string& name) { m_name = name; }
+  void setTags(const std::string& tags) { m_tags = tags; }
+  void setOrigId(const std::string& origId) { m_origId = origId; }
+  void setArticleCount(uint64_t articleCount) { m_articleCount = articleCount; }
+  void setMediaCount(uint64_t mediaCount) { m_mediaCount = mediaCount; }
+  void setSize(uint64_t size) { m_size = size; }
+  void setFavicon(const std::string& favicon) { m_favicon = favicon; }
+  void setFaviconMimeType(const std::string& faviconMimeType) { m_faviconMimeType = faviconMimeType; }
+  void setDownloadId(const std::string& downloadId) { m_downloadId = downloadId; }
+
+ protected:
+  std::string m_id;
+  std::string m_downloadId;
+  std::string m_path;
+  bool m_pathValid;
+  std::string m_title;
+  std::string m_description;
+  std::string m_language;
+  std::string m_creator;
+  std::string m_publisher;
+  std::string m_date;
+  std::string m_url;
+  std::string m_name;
+  std::string m_tags;
+  std::string m_origId;
+  uint64_t m_articleCount;
+  uint64_t m_mediaCount;
+  bool m_readOnly;
+  uint64_t m_size;
+  mutable std::string m_favicon;
+  std::string m_faviconUrl;
+  std::string m_faviconMimeType;
+};
+
+}
+
+#endif

include/bookmark.h

@@ -0,0 +1,68 @@
+/*
+ * Copyright 2018 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_BOOKMARK_H
+#define KIWIX_BOOKMARK_H
+
+#include <string>
+
+namespace pugi {
+class xml_node;
+}
+
+namespace kiwix
+{
+
+/**
+ * A class to store information about a bookmark (an article in a book)
+ */
+class Bookmark
+{
+ public:
+  Bookmark();
+  ~Bookmark();
+
+  void updateFromXml(const pugi::xml_node& node);
+
+  const std::string& getBookId() const { return m_bookId; }
+  const std::string& getBookTitle()  const { return m_bookTitle; }
+  const std::string& getUrl() const { return m_url; }
+  const std::string& getTitle() const { return m_title; }
+  const std::string& getLanguage() const { return m_language; }
+  const std::string& getDate() const { return m_date; }
+
+  void setBookId(const std::string& bookId) { m_bookId = bookId; }
+  void setBookTitle(const std::string& bookTitle) { m_bookTitle = bookTitle; }
+  void setUrl(const std::string& url) { m_url = url; }
+  void setTitle(const std::string& title) { m_title = title; }
+  void setLanguage(const std::string& language) { m_language = language; }
+  void setDate(const std::string& date) { m_date = date; }
+
+ protected:
+  std::string m_bookId;
+  std::string m_bookTitle;
+  std::string m_url;
+  std::string m_title;
+  std::string m_language;
+  std::string m_date;
+};
+
+}
+
+#endif

include/common.h

@@ -0,0 +1,24 @@
+
+#ifndef _KIWIX_COMMON_H_
+#define _KIWIX_COMMON_H_
+
+#include <zim/zim.h>
+
+#ifdef __GNUC__
+#define DEPRECATED __attribute__((deprecated))
+#elif defined(_MSC_VER)
+#define DEPRECATED __declspec(deprecated)
+#else
+#praga message("WARNING: You need to implement DEPRECATED for this compiler")
+#define DEPRECATED
+#endif
+
+
+namespace kiwix {
+
+typedef zim::size_type size_type;
+typedef zim::offset_type offset_type;
+
+}
+
+#endif //_KIWIX_COMMON_H_

include/downloader.h

@@ -0,0 +1,108 @@
+/*
+ * Copyright 2018 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_DOWNLOADER_H
+#define KIWIX_DOWNLOADER_H
+
+#include <string>
+#include <vector>
+#include <map>
+#include <pthread.h>
+#include <memory>
+
+namespace kiwix
+{
+
+class Aria2;
+struct DownloadedFile {
+  DownloadedFile()
+   : success(false) {}
+  bool success;
+  std::string path;
+};
+
+class AriaError : public std::runtime_error {
+ public:
+  AriaError(const std::string& message) : std::runtime_error(message) {}
+};
+
+
+class Download {
+ public:
+  typedef enum { K_ACTIVE, K_WAITING, K_PAUSED, K_ERROR, K_COMPLETE, K_REMOVED, K_UNKNOWN } StatusResult;
+
+  Download() :
+    m_status(K_UNKNOWN) {}
+  Download(std::shared_ptr<Aria2> p_aria, std::string did)
+    : mp_aria(p_aria),
+      m_status(K_UNKNOWN),
+      m_did(did) {};
+  void updateStatus(bool follow=false);
+  void pauseDownload();
+  void resumeDownload();
+  void cancelDownload();
+  StatusResult getStatus()          { return m_status; }
+  std::string  getDid()             { return m_did; }
+  std::string  getFollowedBy()      { return m_followedBy; }
+  uint64_t     getTotalLength()     { return m_totalLength; }
+  uint64_t     getCompletedLength() { return m_completedLength; }
+  uint64_t     getDownloadSpeed()   { return m_downloadSpeed; }
+  uint64_t     getVerifiedLength()  { return m_verifiedLength; }
+  std::string  getPath()            { return m_path; }
+  std::vector<std::string>&  getUris()             { return m_uris; }
+
+ protected:
+  std::shared_ptr<Aria2> mp_aria;
+  StatusResult m_status;
+  std::string m_did = "";
+  std::string m_followedBy = "";
+  uint64_t m_totalLength;
+  uint64_t m_completedLength;
+  uint64_t m_downloadSpeed;
+  uint64_t m_verifiedLength;
+  std::vector<std::string> m_uris;
+  std::string m_path;
+};
+
+/**
+ * A tool to download things.
+ *
+ */
+class Downloader
+{
+ public:
+  Downloader();
+  virtual ~Downloader();
+
+  void close();
+
+  Download* startDownload(const std::string& uri);
+  Download* getDownload(const std::string& did);
+
+  size_t getNbDownload() { return m_knownDownloads.size(); }
+  std::vector<std::string> getDownloadIds();
+  const std::string &getAria2LaunchCmd();
+
+ private:
+  std::map<std::string, std::unique_ptr<Download>> m_knownDownloads;
+  std::shared_ptr<Aria2> mp_aria;
+};
+}
+
+#endif

include/entry.h

@@ -0,0 +1,192 @@
+/*
+ * Copyright 2018 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_ENTRY_H
+#define KIWIX_ENTRY_H
+
+#include <stdio.h>
+#include <zim/article.h>
+#include <exception>
+#include <string>
+
+#include "common.h"
+
+using namespace std;
+
+namespace kiwix
+{
+
+
+class NoEntry : public std::exception {};
+
+/**
+ * A entry represent an.. entry in a zim file.
+ */
+class Entry
+{
+  public:
+    /**
+     * Default constructor.
+     *
+     * Construct an invalid entry.
+     */
+    Entry() = default;
+
+    /**
+     * Construct an entry making reference to an zim article.
+     *
+     * @param article a zim::Article object
+     */
+    Entry(zim::Article article);
+    virtual ~Entry() = default;
+
+    /**
+     * Get the path of the entry.
+     *
+     * The path is the "key" of an entry.
+     *
+     * @return the path of the entry.
+     */
+    std::string getPath() const;
+
+    /**
+     * Get the title of the entry.
+     *
+     * @return the title of the entry.
+     */
+    std::string getTitle() const;
+
+    /**
+     * Get the content of the entry.
+     *
+     * The string is a copy of the content.
+     * If you don't want to do a copy, use get_blob.
+     *
+     * @return the content of the entry.
+     */
+    std::string getContent() const;
+
+    /**
+     * Get the blob of the entry.
+     *
+     * A blob make reference to the content without copying it.
+     *
+     * @param offset The starting offset of the blob.
+     * @return the blob of the entry.
+     */
+    zim::Blob   getBlob(offset_type offset = 0) const;
+
+    /**
+     * Get the blob of the entry.
+     *
+     * A blob make reference to the content without copying it.
+     *
+     * @param offset The starting offset of the blob.
+     * @param size The size of the blob.
+     * @return the blob of the entry.
+     */
+    zim::Blob   getBlob(offset_type offset, size_type size) const;
+
+    /**
+     * Get the info for direct access to the content of the entry.
+     *
+     * Some entry (ie binary ones) have their content plain stored
+     * in the zim file. Knowing the offset where the content is stored
+     * an user can directly read the content in the zim file bypassing the
+     * kiwix-lib/libzim.
+     *
+     * @return A pair specifying where to read the content.
+     *         The string is the real file to read (may be different that .zim
+     *         file if zim is cut).
+     *         The offset is the offset to read in the file.
+     *         Return <"",0> if is not possible to read directly.
+     */
+    std::pair<std::string, offset_type> getDirectAccessInfo() const;
+
+    /**
+     * Get the size of the entry.
+     *
+     * @return the size of the entry.
+     */
+    size_type   getSize() const;
+
+    /**
+     * Get the mime_type of the entry.
+     *
+     * @return the mime_type of the entry.
+     */
+    std::string getMimetype() const;
+
+
+    /**
+     * Get if the entry is a redirect entry.
+     *
+     * @return True if the entry is a redirect.
+     */
+    bool isRedirect() const;
+
+    /**
+     * Get if the entry is a link target entry.
+     *
+     * @return True if the entry is a link target.
+     */
+    bool isLinkTarget() const;
+
+    /**
+     * Get if the entry is a deleted entry.
+     *
+     * @return True if the entry is a deleted entry.
+     */
+    bool isDeleted() const;
+
+    /**
+     * Get the entry pointed by this entry.
+     *
+     * @return the entry pointed.
+     * @throw NoEntry if the entry is not a redirected entry.
+     */
+    Entry getRedirectEntry() const;
+
+    /**
+     * Get the final entry pointed by this entry.
+     *
+     * Follow the redirection until a "not redirecting" entry is found.
+     * If the entry is not a redirected entry, return the entry itself.
+     *
+     * @return the final entry.
+     */
+    Entry getFinalEntry() const;
+
+    /**
+     * Convert the entry to a boolean value.
+     *
+     * @return True if the entry is valid.
+     */
+    explicit operator bool() const { return good(); }
+
+  private:
+    zim::Article article;
+    mutable zim::Article final_article;
+
+    bool good() const { return article.good(); }
+};
+
+}
+
+#endif // KIWIX_ENTRY_H

include/kiwix.h

@@ -17,28 +17,9 @@
  * MA 02110-1301, USA.
  */
 
-#ifndef KIWIX_COMPONENTTOOLS_H
-#define KIWIX_COMPONENTTOOLS_H
+#ifndef KIWIX_H
+#define KIWIX_H
 
-#ifdef _WIN32
-  #include <mozilla/Char16.h>
-#endif
+#include "library.h"
 
-#include<string>
-
-#ifdef __APPLE__
-  #include <stdint.h>
-#endif
-
-#ifdef _WIN32
-  #include <stdlib.h>
-#endif
-
-#include "nsStringAPI.h"
-#include "nsEmbedString.h"
-
-const char *nsStringToCString(const nsAString &str);
-std::string nsStringToString(const nsEmbedString &str);
-const char *nsStringToUTF8(const nsAString &str);
-
-#endif
+#endif

include/kiwixserve.h

@@ -0,0 +1,30 @@
+#ifndef KIWIXLIB_KIWIX_SERVE_H_
+#define KIWIXLIB_KIWIX_SERVE_H_
+
+#include <memory>
+#include <string>
+
+class Subprocess;
+namespace kiwix {
+
+class KiwixServe
+{
+  public:
+    KiwixServe(const std::string& libraryPath, int port = 8181);
+    ~KiwixServe();
+
+    void run();
+    void shutDown();
+    bool isRunning();
+    int getPort() { return m_port; }
+    int setPort(int port);
+
+  private:
+  std::unique_ptr<Subprocess> mp_kiwixServe;
+  int m_port;
+  std::string m_libraryPath;
+};
+
+}; //end namespace kiwix
+
+#endif // KIWIXLIB_KIWIX_SERVE_H_

include/library.h

@@ -0,0 +1,286 @@
+/*
+ * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_LIBRARY_H
+#define KIWIX_LIBRARY_H
+
+#include <string>
+#include <vector>
+#include <map>
+#include <memory>
+
+#include "book.h"
+#include "bookmark.h"
+#include "common.h"
+
+#define KIWIX_LIBRARY_VERSION "20110515"
+
+namespace kiwix
+{
+
+class OPDSDumper;
+
+enum supportedListSortBy { UNSORTED, TITLE, SIZE, DATE, CREATOR, PUBLISHER };
+enum supportedListMode {
+  ALL = 0,
+  LOCAL = 1,
+  REMOTE = 1 << 1,
+  NOLOCAL = 1 << 2,
+  NOREMOTE = 1 << 3,
+  VALID = 1 << 4,
+  NOVALID = 1 << 5
+};
+
+class Filter {
+  private:
+    uint64_t activeFilters;
+    std::vector<std::string> _acceptTags;
+    std::vector<std::string> _rejectTags;
+    std::string _lang;
+    std::string _publisher;
+    std::string _creator;
+    size_t _maxSize;
+    std::string _query;
+
+  public:
+    Filter();
+    ~Filter() = default;
+
+    /**
+     *  Set the filter to check local.
+     *
+     *  A local book is a book with a path.
+     *  If accept is true, only local book are accepted.
+     *  If accept is false, only non local book are accepted.
+     */
+    Filter& local(bool accept);
+
+    /**
+     *  Set the filter to check remote.
+     *
+     *  A remote book is a book with a url.
+     *  If accept is true, only remote book are accepted.
+     *  If accept is false, only non remote book are accepted.
+     */
+    Filter& remote(bool accept);
+
+    /**
+     *  Set the filter to check validity.
+     *
+     *  A valid book is a book with a path pointing to a existing zim file.
+     *  If accept is true, only valid book are accepted.
+     *  If accept is false, only non valid book are accepted.
+     */
+    Filter& valid(bool accept);
+
+    /**
+     * Set the filter to only accept book with corresponding tag.
+     */
+    Filter& acceptTags(std::vector<std::string> tags);
+    Filter& rejectTags(std::vector<std::string> tags);
+
+    Filter& lang(std::string lang);
+    Filter& publisher(std::string publisher);
+    Filter& creator(std::string creator);
+    Filter& maxSize(size_t size);
+    Filter& query(std::string query);
+
+    bool accept(const Book& book) const;
+};
+
+
+/**
+ * A Library store several books.
+ */
+class Library
+{
+  std::map<std::string, kiwix::Book> m_books;
+  std::map<std::string, std::shared_ptr<Reader>> m_readers;
+  std::vector<kiwix::Bookmark> m_bookmarks;
+
+ public:
+  Library();
+  ~Library();
+
+  /**
+   * Add a book to the library.
+   *
+   * If a book already exist in the library with the same id, update
+   * the existing book instead of adding a new one.
+   *
+   * @param book The book to add.
+   * @return True if the book has been added.
+   *         False if a book has been updated.
+   */
+  bool addBook(const Book& book);
+
+  /**
+   * Add a bookmark to the library.
+   *
+   * @param bookmark the book to add.
+   */
+  void addBookmark(const Bookmark& bookmark);
+
+  /**
+   * Remove a bookmarkk
+   *
+   * @param zimId The zimId of the bookmark.
+   * @param url The url of the bookmark.
+   * @return True if the bookmark has been removed.
+   */
+  bool removeBookmark(const std::string& zimId, const std::string& url);
+
+  Book& getBookById(const std::string& id);
+  std::shared_ptr<Reader> getReaderById(const std::string& id);
+
+  /**
+   * Remove a book from the library.
+   *
+   * @param id the id of the book to remove.
+   * @return True if the book were in the lirbrary and has been removed.
+   */
+  bool removeBookById(const std::string& id);
+
+  /**
+   * Write the library to a file.
+   *
+   * @param path the path of the file to write to.
+   * @return True if the library has been correctly saved.
+   */
+  bool writeToFile(const std::string& path);
+
+  /**
+   * Write the library bookmarks to a file.
+   *
+   * @param path the path of the file to write to.
+   * @return True if the library has been correctly saved.
+   */
+  bool writeBookmarksToFile(const std::string& path);
+
+  /**
+   * Get the number of book in the library.
+   *
+   * @param localBooks If we must count local books (books with a path).
+   * @param remoteBooks If we must count remote books (books with an url)
+   * @return The number of books.
+   */
+  unsigned int getBookCount(const bool localBooks, const bool remoteBooks);
+
+  /**
+   * Get all langagues of the books in the library.
+   *
+   * @return A list of languages.
+   */
+  std::vector<std::string> getBooksLanguages();
+
+  /**
+   * Get all book creators of the books in the library.
+   *
+   * @return A list of book creators.
+   */
+  std::vector<std::string> getBooksCreators();
+
+  /**
+   * Get all book publishers of the books in the library.
+   *
+   * @return A list of book publishers.
+   */
+  std::vector<std::string> getBooksPublishers();
+
+  /**
+   * Get all bookmarks.
+   *
+   * @return A list of bookmarks
+   */
+  const std::vector<kiwix::Bookmark> getBookmarks(bool onlyValidBookmarks = true);
+
+  /**
+   * Get all book ids of the books in the library.
+   *
+   * @return A list of book ids.
+   */
+  std::vector<std::string> getBooksIds();
+
+  /**
+   * Filter the library and generate a new one with the keep elements.
+   *
+   * This is equivalent to `listBookIds(ALL, UNSORTED, search)`.
+   *
+   * @param search List only books with search in the title or description.
+   * @return The list of bookIds corresponding to the query.
+   */
+  DEPRECATED std::vector<std::string> filter(const std::string& search);
+
+
+  /**
+   * Filter the library and return the id of the keep elements.
+   *
+   * @param filter The filter to use.
+   * @return The list of bookIds corresponding to the filter.
+   */
+  std::vector<std::string> filter(const Filter& filter);
+
+
+  /**
+   * Sort (in place) bookIds using the given comparator.
+   *
+   * @param bookIds the list of book Ids to sort
+   * @param comparator how to sort the books
+   * @return The sorted list of books
+   */
+  void sort(std::vector<std::string>& bookIds, supportedListSortBy sortBy, bool ascending);
+
+  /**
+   * List books in the library.
+   *
+   * @param mode The mode of listing :
+   *             - LOCAL    : list only local books (with a path).
+   *             - REMOTE   : list only remote books (with an url).
+   *             - VALID    : list only valid books (without a path or with a
+   *                          path pointing to a valid zim file).
+   *             - NOLOCAL  : list only books without valid path.
+   *             - NOREMOTE : list only books without url.
+   *             - NOVALID  : list only books not valid.
+   *             - ALL : Do not do any filter (LOCAL or REMOTE)
+   *             - Flags can be combined.
+   * @param sortBy Attribute to sort by the book list.
+   * @param search List only books with search in the title, description.
+   * @param language List only books in this language.
+   * @param creator List only books of this creator.
+   * @param publisher List only books of this publisher.
+   * @param maxSize Do not list book bigger than maxSize.
+   *                Set to 0 to cancel this filter.
+   * @return The list of bookIds corresponding to the query.
+   */
+  DEPRECATED std::vector<std::string> listBooksIds(
+    int supportedListMode = ALL,
+    supportedListSortBy sortBy = UNSORTED,
+    const std::string& search = "",
+    const std::string& language = "",
+    const std::string& creator = "",
+    const std::string& publisher = "",
+    const std::vector<std::string>& tags = {},
+    size_t maxSize = 0);
+
+  friend class OPDSDumper;
+  friend class libXMLDumper;
+};
+}
+
+#endif

include/libxml_dumper.h

@@ -0,0 +1,83 @@
+/*
+ * Copyright 2018 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_LIBXML_DUMPER_H
+#define KIWIX_LIBXML_DUMPER_H
+
+#include <string>
+#include <vector>
+
+#include <pugixml.hpp>
+
+#include "library.h"
+
+namespace kiwix
+{
+
+/**
+ * A tool to dump a `Library` into a basic library.xml
+ *
+ */
+class LibXMLDumper
+{
+ public:
+  LibXMLDumper() = default;
+  LibXMLDumper(Library* library);
+  ~LibXMLDumper();
+
+  /**
+   * Dump the library.xml
+   *
+   * @param id The id of the library.
+   * @return The library.xml content.
+   */
+  std::string dumpLibXMLContent(const std::vector<std::string>& bookIds);
+
+
+  /**
+   * Dump the bookmark of the library.
+   *
+   * @return The bookmark.xml content.
+   */
+  std::string dumpLibXMLBookmark();
+
+  /**
+   * Set the base directory used.
+   *
+   * @param baseDir the base directory to use.
+   */
+  void setBaseDir(const std::string& baseDir) { this->baseDir = baseDir; }
+
+  /**
+   * Set the library to dump.
+   *
+   * @param library The library to dump.
+   */
+  void setLibrary(Library* library) { this->library = library; }
+
+ protected:
+  kiwix::Library* library;
+  std::string baseDir;
+ private:
+  void handleBook(Book book, pugi::xml_node root_node);
+  void handleBookmark(Bookmark bookmark, pugi::xml_node root_node);
+};
+}
+
+#endif // KIWIX_OPDS_DUMPER_H

include/manager.h

@@ -0,0 +1,179 @@
+/*
+ * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_MANAGER_H
+#define KIWIX_MANAGER_H
+
+#include "book.h"
+#include "library.h"
+#include "reader.h"
+
+#include <string>
+#include <vector>
+
+namespace pugi {
+class xml_document;
+}
+
+namespace kiwix
+{
+
+class LibraryManipulator {
+ public:
+  virtual ~LibraryManipulator() {}
+  virtual bool addBookToLibrary(Book book) = 0;
+  virtual void addBookmarkToLibrary(Bookmark bookmark) = 0;
+};
+
+class DefaultLibraryManipulator : public LibraryManipulator {
+ public:
+  DefaultLibraryManipulator(Library* library) :
+    library(library) {}
+  virtual ~DefaultLibraryManipulator() {}
+  bool addBookToLibrary(Book book) {
+    return library->addBook(book);
+  }
+  void addBookmarkToLibrary(Bookmark bookmark) {
+    library->addBookmark(bookmark);
+  }
+ private:
+   kiwix::Library* library;
+};
+
+/**
+ * A tool to manage a `Library`.
+ */
+class Manager
+{
+ public:
+  Manager(LibraryManipulator* manipulator);
+  Manager(Library* library);
+  ~Manager();
+
+  /**
+   * Read a `library.xml` and add book in the file to the library.
+   *
+   * @param path The path to the `library.xml`.
+   * @param readOnly Set if the libray path could be overwritten latter with
+   *                 updated content.
+   * @return True if file has been properly parsed.
+   */
+  bool readFile(const std::string& path, const bool readOnly = true);
+
+  /**
+   * Read a `library.xml` and add book in the file to the library.
+   *
+   * @param nativePath The path of the `library.xml`
+   * @param UTF8Path The utf8 version (?) of the path. Also the path where the
+   *                 library will be writen i readOnly is False.
+   * @param readOnly Set if the libray path could be overwritten latter with
+   *                 updated content.
+   * @return True if file has been properly parsed.
+   */
+  bool readFile(const std::string& nativePath,
+                const std::string& UTF8Path,
+                const bool readOnly = true);
+
+  /**
+   * Load a library content store in the string.
+   *
+   * @param xml The content corresponding of the library xml
+   * @param readOnly Set if the libray path could be overwritten latter with
+   *                 updated content.
+   * @param libraryPath The library path (used to resolve relative path)
+   * @return True if the content has been properly parsed.
+   */
+  bool readXml(const std::string& xml,
+               const bool readOnly = true,
+               const std::string& libraryPath = "");
+
+  /**
+   * Load a library content stored in a OPDS stream.
+   *
+   * @param content The content of the OPDS stream.
+   * @param readOnly Set if the library path could be overwritten later with
+   *                 updated content.
+   * @param libraryPath The library path (used to resolve relative path)
+   * @return True if the content has been properly parsed.
+   */
+  bool readOpds(const std::string& content, const std::string& urlHost);
+
+
+  /**
+   * Load a bookmark file.
+   *
+   * @param path The path of the file to read.
+   * @return True if the content has been properly parsed.
+   */
+  bool readBookmarkFile(const std::string& path);
+
+  /**
+   * Add a book to the library.
+   *
+   * @param pathToOpen The path to the zim file to add.
+   * @param pathToSave The path to store in the library in place of pathToOpen.
+   * @param url        The url of the book to store in the library.
+   * @param checMetaData Tell if we check metadata before adding book to the
+   *                     library.
+   * @return The id of the book if the book has been added to the library.
+   *         Else, an empty string.
+   */
+  std::string addBookFromPathAndGetId(const std::string& pathToOpen,
+                                 const std::string& pathToSave = "",
+                                 const std::string& url = "",
+                                 const bool checkMetaData = false);
+
+  /**
+   * Add a book to the library.
+   *
+   * @param pathToOpen The path to the zim file to add.
+   * @param pathToSave The path to store in the library in place of pathToOpen.
+   * @param url        The url of the book to store in the library.
+   * @param checMetaData Tell if we check metadata before adding book to the
+   *                     library.
+   * @return True if the book has been added to the library.
+   */
+
+  bool addBookFromPath(const std::string& pathToOpen,
+                       const std::string& pathToSave = "",
+                       const std::string& url = "",
+                       const bool checkMetaData = false);
+
+  std::string writableLibraryPath;
+
+  bool m_hasSearchResult = false;
+  uint64_t m_totalBooks = 0;
+  uint64_t m_startIndex = 0;
+  uint64_t m_itemsPerPage = 0;
+
+ protected:
+  kiwix::LibraryManipulator* manipulator;
+  bool mustDeleteManipulator;
+
+  bool readBookFromPath(const std::string& path, Book* book);
+  bool parseXmlDom(const pugi::xml_document& doc,
+                   const bool readOnly,
+                   const std::string& libraryPath);
+  bool parseOpdsDom(const pugi::xml_document& doc,
+                    const std::string& urlHost);
+
+};
+}
+
+#endif

include/meson.build

@@ -0,0 +1,31 @@
+headers = [
+  'book.h',
+  'bookmark.h',
+  'common.h',
+  'library.h',
+  'manager.h',
+  'libxml_dumper.h',
+  'opds_dumper.h',
+  'downloader.h',
+  'reader.h',
+  'entry.h',
+  'searcher.h',
+  'search_renderer.h',
+  'server.h',
+  'kiwixserve.h',
+  'name_mapper.h'
+]
+
+install_headers(headers, subdir:'kiwix')
+
+install_headers(
+  'tools/base64.h',
+  'tools/networkTools.h',
+  'tools/otherTools.h',
+  'tools/pathTools.h',
+  'tools/regexTools.h',
+  'tools/stringTools.h',
+  'tools/lock.h',
+  subdir:'kiwix/tools'
+)
+

include/name_mapper.h

@@ -0,0 +1,61 @@
+/*
+ * Copyright 2019 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_NAMEMAPPER_H
+#define KIWIX_NAMEMAPPER_H
+
+#include <string>
+#include <map>
+
+namespace kiwix
+{
+
+class Library;
+
+class NameMapper {
+  public:
+    virtual ~NameMapper() = default;
+    virtual std::string getNameForId(const std::string& id) = 0;
+    virtual std::string getIdForName(const std::string& name) = 0;
+};
+
+
+class IdNameMapper : public NameMapper {
+  public:
+    virtual std::string getNameForId(const std::string& id) { return id; };
+    virtual std::string getIdForName(const std::string& name) { return name; };
+};
+
+class HumanReadableNameMapper : public NameMapper {
+  private:
+    std::map<std::string, std::string> m_idToName;
+    std::map<std::string, std::string> m_nameToId;
+
+  public:
+    HumanReadableNameMapper(kiwix::Library& library, bool withAlias);
+    virtual ~HumanReadableNameMapper() = default;
+    virtual std::string getNameForId(const std::string& id);
+    virtual std::string getIdForName(const std::string& name);
+};
+
+
+
+}
+
+#endif

include/opds_dumper.h

@@ -0,0 +1,120 @@
+/*
+ * Copyright 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_OPDS_DUMPER_H
+#define KIWIX_OPDS_DUMPER_H
+
+#include <time.h>
+#include <sstream>
+#include <string>
+
+#include <pugixml.hpp>
+
+#include "tools/base64.h"
+#include "tools/pathTools.h"
+#include "tools/regexTools.h"
+#include "library.h"
+#include "reader.h"
+
+using namespace std;
+
+namespace kiwix
+{
+
+/**
+ * A tool to dump a `Library` into a opds stream.
+ *
+ */
+class OPDSDumper
+{
+ public:
+  OPDSDumper() = default;
+  OPDSDumper(Library* library);
+  ~OPDSDumper();
+
+  /**
+   * Dump the OPDS feed.
+   *
+   * @param id The id of the library.
+   * @return The OPDS feed.
+   */
+  std::string dumpOPDSFeed(const std::vector<std::string>& bookIds);
+
+  /**
+   * Set the id of the opds stream.
+   *
+   * @param id the id to use.
+   */
+  void setId(const std::string& id) { this->id = id;}
+
+  /**
+   * Set the title oft the opds stream.
+   *
+   * @param title the title to use.
+   */
+  void setTitle(const std::string& title) { this->title = title; }
+
+  /**
+   * Set the root location used when generating url.
+   *
+   * @param rootLocation the root location to use.
+   */
+  void setRootLocation(const std::string& rootLocation) { this->rootLocation = rootLocation; }
+
+  /**
+   * Set the search url.
+   *
+   * @param searchUrl the search url to use.
+   */
+  void setSearchDescriptionUrl(const std::string& searchDescriptionUrl) { this->searchDescriptionUrl = searchDescriptionUrl; }
+
+  /**
+   * Set some informations about the search results.
+   *
+   * @param totalResult the total number of results of the search.
+   * @param startIndex the start index of the result.
+   * @param count the number of result of the current set (or page).
+   */
+  void setOpenSearchInfo(int totalResult, int startIndex, int count);
+
+  /**
+   * Set the library to dump.
+   *
+   * @param library The library to dump.
+   */
+  void setLibrary(Library* library) { this->library = library; }
+
+ protected:
+  kiwix::Library* library;
+  std::string id;
+  std::string title;
+  std::string date;
+  std::string rootLocation;
+  std::string searchDescriptionUrl;
+  int m_totalResults;
+  int m_startIndex;
+  int m_count;
+  bool m_isSearchResult = false;
+
+ private:
+  pugi::xml_node handleBook(Book book, pugi::xml_node root_node);
+};
+}
+
+#endif // KIWIX_OPDS_DUMPER_H

include/reader.h

@@ -0,0 +1,570 @@
+/*
+ * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_READER_H
+#define KIWIX_READER_H
+
+#include <stdio.h>
+#include <zim/article.h>
+#include <zim/file.h>
+#include <zim/fileiterator.h>
+#include <zim/zim.h>
+#include <exception>
+#include <map>
+#include <sstream>
+#include <string>
+#include "common.h"
+#include "entry.h"
+#include "tools/pathTools.h"
+#include "tools/stringTools.h"
+
+using namespace std;
+
+namespace kiwix
+{
+
+/**
+ * The Reader class is the class who allow to get an entry content from a zim
+ * file.
+ */
+class Reader
+{
+ public:
+  /**
+   * Create a Reader to read a zim file specified by zimFilePath.
+   *
+   * @param zimFilePath The path to the zim file to read.
+   *                    The zim file can be splitted (.zimaa, .zimab, ...).
+   *                    In this case, the file path must still point to the
+   *                    unsplitted path as if the file were not splitted
+   *                    (.zim extesion).
+   */
+  Reader(const string zimFilePath);
+  ~Reader();
+
+  /**
+   * Get the number of "displayable" entries in the zim file.
+   *
+   * @return If the zim file has a /M/Counter metadata, return the number of
+   *         entries with the 'text/html' MIMEtype specified in the metadata.
+   *         Else return the number of entries in the 'A' namespace.
+   */
+  unsigned int getArticleCount() const;
+
+  /**
+   * Get the number of media in the zim file.
+   *
+   * @return If the zim file has a /M/Counter metadata, return the number of
+   *         entries with the 'image/jpeg', 'image/gif' and 'image/png' in
+   *         the metadata.
+   *         Else return the number of entries in the 'I' namespace.
+   */
+  unsigned int getMediaCount() const;
+
+  /**
+   * Get the number of all entries in the zim file.
+   *
+   * @return Return the number of all the entries, whatever their MIMEtype or
+   *         their namespace.
+   */
+  unsigned int getGlobalCount() const;
+
+  /**
+   * Get the path of the zim file.
+   *
+   * @return the path of the zim file as given in the constructor.
+   */
+  string getZimFilePath() const;
+
+  /**
+   * Get the Id of the zim file.
+   *
+   * @return The uuid stored in the zim file.
+   */
+  string getId() const;
+
+  /**
+   * Get the url of a random page.
+   *
+   * Deprecated : Use `getRandomPage` instead.
+   *
+   * @return Url of a random page. The page is picked from all entries in
+   *         the 'A' namespace.
+   *         The main page is excluded from the potential results.
+   */
+  DEPRECATED string getRandomPageUrl() const;
+
+  /**
+   * Get a random page.
+   *
+   * @return A random Entry. The entry is picked from all entries in
+   *         the 'A' namespace.
+   *         The main entry is excluded from the potential results.
+   */
+  Entry getRandomPage() const;
+
+  /**
+   * Get the url of the first page.
+   *
+   * Deprecated : Use `getFirstPage` instead.
+   *
+   * @return Url of the first entry in the 'A' namespace.
+   */
+  DEPRECATED string getFirstPageUrl() const;
+
+  /**
+   * Get the entry of the first page.
+   *
+   * @return The first entry in the 'A' namespace.
+   */
+  Entry getFirstPage() const;
+
+  /**
+   * Get the url of the main page.
+   *
+   * Deprecated : Use `getMainPage` instead.
+   *
+   * @return Url of the main page as specified in the zim file.
+   */
+  DEPRECATED string getMainPageUrl() const;
+
+  /**
+   * Get the entry of the main page.
+   *
+   * @return Entry of the main page as specified in the zim file.
+   */
+  Entry getMainPage() const;
+
+  /**
+   * Get the content of a metadata.
+   *
+   * @param[in]  name The name of the metadata.
+   * @param[out] value The value will be set to the content of the metadata.
+   * @return True if it was possible to get the content of the metadata.
+   */
+  bool getMetadata(const string& name, string& value) const;
+
+  /**
+   * Get the name of the zim file.
+   *
+   * @return The name of the zim file as specified in the zim metadata.
+   */
+  string getName() const;
+
+  /**
+   * Get the title of the zim file.
+   *
+   * @return The title of zim file as specified in the zim metadata.
+   *         If no title has been set, return a title computed from the
+   *         file path.
+   */
+  string getTitle() const;
+
+  /**
+   * Get the creator of the zim file.
+   *
+   * @return The creator of the zim file as specified in the zim metadata.
+   */
+  string getCreator() const;
+
+  /**
+   * Get the publisher of the zim file.
+   *
+   * @return The publisher of the zim file as specified in the zim metadata.
+   */
+  string getPublisher() const;
+
+  /**
+   * Get the date of the zim file.
+   *
+   * @return The date of the zim file as specified in the zim metadata.
+   */
+  string getDate() const;
+
+  /**
+   * Get the description of the zim file.
+   *
+   * @return The description of the zim file as specified in the zim metadata.
+   *         If no description has been set, return the subtitle.
+   */
+  string getDescription() const;
+
+  /**
+   * Get the long description of the zim file.
+   *
+   * @return The long description of the zim file as specifed in the zim metadata.
+   */
+  string getLongDescription() const;
+
+  /**
+   * Get the language of the zim file.
+   *
+   * @return The language of the zim file as specified in the zim metadata.
+   */
+  string getLanguage() const;
+
+  /**
+   * Get the license of the zim file.
+   *
+   * @return The license of the zim file as specified in the zim metadata.
+   */
+  string getLicense() const;
+
+  /**
+   * Get the tags of the zim file.
+   *
+   * @param original If true, return the original tags as specified in the zim metadata.
+   *                 Else, try to convert it to the new 'normalized' format.
+   * @return The tags of the zim file.
+   */
+  string getTags(bool original=false) const;
+
+  /**
+   * Get the value (as a string) of a specific tag.
+   *
+   * According to https://wiki.openzim.org/wiki/Tags
+   *
+   * @return The value of the specified tag.
+   * @throw  std::out_of_range if the specified tag is not found.
+   */
+  string getTagStr(const std::string& tagName) const;
+
+  /**
+   * Get the boolean value of a specific tag.
+   *
+   * According to https://wiki.openzim.org/wiki/Tags
+   *
+   * @return The boolean value of the specified tag.
+   * @throw  std::out_of_range if the specified tag is not found.
+   *         std::domain_error if the value of the tag cannot be convert to bool.
+   */
+  bool getTagBool(const std::string& tagName) const;
+
+  /**
+   * Get the relations of the zim file.
+   *
+   * @return The relation of the zim file as specified in the zim metadata.
+   */
+  string getRelation() const;
+
+  /**
+   * Get the flavour of the zim file.
+   *
+   * @return The flavour of the zim file as specified in the zim metadata.
+   */
+  string getFlavour() const;
+
+  /**
+   * Get the source of the zim file.
+   *
+   * @return The source of the zim file as specified in the zim metadata.
+   */
+  string getSource() const;
+
+  /**
+   * Get the scraper of the zim file.
+   *
+   * @return The scraper of the zim file as specified in the zim metadata.
+   */
+  string getScraper() const;
+
+  /**
+   * Get the origId of the zim file.
+   *
+   * The origId is only used in the case of patch zim file and is the Id
+   * of the original zim file.
+   *
+   * @return The origId of the zim file as specified in the zim metadata.
+   */
+  string getOrigId() const;
+
+  /**
+   * Get the favicon of the zim file.
+   *
+   * @param[out] content The content of the favicon.
+   * @param[out] mimeType The mimeType of the favicon.
+   * @return True if a favicon has been found.
+   */
+  bool getFavicon(string& content, string& mimeType) const;
+
+  /**
+   * Get an entry associated to an path.
+   *
+   * @param path The path of the entry.
+   * @return The entry.
+   * @throw NoEntry If no entry correspond to the path.
+   */
+  Entry getEntryFromPath(const std::string& path) const;
+
+  /**
+   * Get an entry associated to an url encoded path.
+   *
+   * Equivalent to `getEntryFromPath(urlDecode(path));`
+   *
+   * @param path The url encoded path.
+   * @return The entry.
+   * @throw NoEntry If no entry correspond to the path.
+   */
+  Entry getEntryFromEncodedPath(const std::string& path) const;
+
+  /**
+   * Get un entry associated to a title.
+   *
+   * @param title The title.
+   * @return The entry
+   * throw NoEntry If no entry correspond to the url.
+   */
+  Entry getEntryFromTitle(const std::string& title) const;
+
+  /**
+   * Get the url of a page specified by a title.
+   *
+   * @param[in] title the title of the page.
+   * @param[out] url the url of the page.
+   * @return True if the page can be found.
+   */
+  DEPRECATED bool getPageUrlFromTitle(const string& title, string& url) const;
+
+  /**
+   * Get the mimetype of a entry specified by a url.
+   *
+   * @param[in] url the url of the entry.
+   * @param[out] mimeType the mimeType of the entry.
+   * @return True if the mimeType has been found.
+   */
+  DEPRECATED bool getMimeTypeByUrl(const string& url, string& mimeType) const;
+
+  /**
+   * Get the content of an entry specifed by a url.
+   *
+   * Alias to `getContentByEncodedUrl`
+   */
+  DEPRECATED bool getContentByUrl(const string& url,
+                       string& content,
+                       string& title,
+                       unsigned int& contentLength,
+                       string& contentType) const;
+
+  /**
+   * Get the content of an entry specified by a url encoded url.
+   *
+   * Equivalent to getContentByDecodedUrl(urlDecode(url), ...).
+   */
+  DEPRECATED bool getContentByEncodedUrl(const string& url,
+                              string& content,
+                              string& title,
+                              unsigned int& contentLength,
+                              string& contentType,
+                              string& baseUrl) const;
+
+  /**
+   * Get the content of an entry specified by an url encoded url.
+   *
+   * Equivalent to getContentByEncodedUrl but without baseUrl.
+   */
+  DEPRECATED bool getContentByEncodedUrl(const string& url,
+                              string& content,
+                              string& title,
+                              unsigned int& contentLength,
+                              string& contentType) const;
+
+  /**
+   * Get the content of an entry specified by a url.
+   *
+   * @param[in] url The url of the entry.
+   * @param[out] content The content of the entry.
+   * @param[out] title the title of the entry.
+   * @param[out] contentLength The size of the entry (size of content).
+   * @param[out] contentType The mimeType of the entry.
+   * @param[out] baseUrl Return the true url of the entry.
+   *                     If the specified entry is a redirection, contains
+   *                     the url of the targeted entry.
+   * @return True if the entry has been found.
+   */
+  DEPRECATED bool getContentByDecodedUrl(const string& url,
+                              string& content,
+                              string& title,
+                              unsigned int& contentLength,
+                              string& contentType,
+                              string& baseUrl) const;
+  /**
+   * Get the content of an entry specified by a url.
+   *
+   * Equivalent to getContentByDecodedUrl but withou the baseUrl.
+   */
+  DEPRECATED bool getContentByDecodedUrl(const string& url,
+                              string& content,
+                              string& title,
+                              unsigned int& contentLength,
+                              string& contentType) const;
+
+  /**
+   * Search for entries with title starting with prefix (case sensitive).
+   *
+   * Suggestions are stored in an internal vector and can be retrieved using
+   * `getNextSuggestion` method.
+   *
+   * @param prefix The prefix to search.
+   * @param suggestionsCount How many suggestions to search for.
+   * @param reset If true, remove previous suggestions in the internal vector.
+   *              If false, add suggestions to the internal vector
+   *              (until internal vector size is suggestionCount (or no more
+   *               suggestion))
+   * @return True if some suggestions where added to the internal vector.
+   */
+  bool searchSuggestions(const string& prefix,
+                         unsigned int suggestionsCount,
+                         const bool reset = true);
+
+  /**
+   * Search for entries for the given prefix.
+   *
+   * If the zim file has a internal fulltext index, the suggestions will be
+   * searched using it.
+   * Else the suggestions will be search using `searchSuggestions` while trying
+   * to be smart about case sensitivity (using `getTitleVariants`).
+   *
+   * In any case, suggestions are stored in an internal vector and can be
+   * retrieved using `getNextSuggestion` method.
+   * The internal vector will be reset.
+   *
+   * @param prefix The prefix to search for.
+   * @param suggestionsCount How many suggestions to search for.
+   */
+  bool searchSuggestionsSmart(const string& prefix,
+                              unsigned int suggestionsCount);
+
+  /**
+   * Check if the url exists in the zim file.
+   *
+   * Deprecated : Use `pathExists` instead.
+   *
+   * @param url the url to check.
+   * @return True if the url exits in the zim file.
+   */
+  DEPRECATED bool urlExists(const string& url) const;
+
+  /**
+   * Check if the path exists in the zim file.
+   *
+   * @param path the path to check.
+   * @return True if the path exists in the zim file.
+   */
+  bool pathExists(const string& path) const;
+
+  /**
+   * Check if the zim file has a embedded fulltext index.
+   *
+   * @return True if the zim file has a embedded fulltext index
+   *         and is not split (else the fulltext is not accessible).
+   */
+  bool hasFulltextIndex() const;
+
+  /**
+   * Get potential case title variations for a title.
+   *
+   * @param title a title.
+   * @return the list of variantions.
+   */
+  std::vector<std::string> getTitleVariants(const std::string& title) const;
+
+  /**
+   * Get the next suggestion title.
+   *
+   * @param[out] title the title of the suggestion.
+   * @return True if title has been set.
+   */
+  bool getNextSuggestion(string& title);
+
+  /**
+   * Get the next suggestion title and url.
+   *
+   * @param[out] title the title of the suggestion.
+   * @param[out] url the url of the suggestion.
+   * @return True if title and url have been set.
+   */
+  bool getNextSuggestion(string& title, string& url);
+
+  /**
+   * Get if we can check zim file integrity (has a checksum).
+   *
+   * @return True if zim file have a checksum.
+   */
+  bool canCheckIntegrity() const;
+
+  /**
+   * Check is zim file is corrupted.
+   *
+   * @return True if zim file is corrupted.
+   */
+  bool isCorrupted() const;
+
+  /**
+   * Parse a full url into a namespace and url.
+   *
+   * @param[in] url The full url ("/N/url").
+   * @param[out] ns The namespace (N).
+   * @param[out] title The url (url).
+   * @return True
+   */
+  DEPRECATED bool parseUrl(const string& url, char* ns, string& title) const;
+
+  /**
+   * Return the total size of the zim file.
+   *
+   * If zim file is split, return the sum of all parts' size.
+   *
+   * @return Size of the size file is KiB.
+   */
+  unsigned int getFileSize() const;
+
+  /**
+   * Get the zim file handler.
+   *
+   * @return The libzim file handler.
+   */
+  zim::File* getZimFileHandler() const;
+
+  /**
+   * Get the zim article object associated to a url.
+   *
+   * @param[in] url The url of the article.
+   * @param[out] article The libzim article object.
+   * @return True if the url is good (article.good()).
+   */
+  DEPRECATED bool getArticleObjectByDecodedUrl(const string& url,
+                                    zim::Article& article) const;
+
+ protected:
+  zim::File* zimFileHandler;
+  zim::size_type firstArticleOffset;
+  zim::size_type lastArticleOffset;
+  zim::size_type nsACount;
+  zim::size_type nsICount;
+  std::string zimFilePath;
+
+  std::vector<std::vector<std::string>> suggestions;
+  std::vector<std::vector<std::string>>::iterator suggestionsOffset;
+
+ private:
+  std::map<const std::string, unsigned int> parseCounterMetadata() const;
+};
+}
+
+#endif

include/search_renderer.h

@@ -0,0 +1,85 @@
+/*
+ * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_SEARCH_RENDERER_H
+#define KIWIX_SEARCH_RENDERER_H
+
+#include <string>
+
+namespace kiwix
+{
+
+class Searcher;
+class NameMapper;
+/**
+ * The SearcherRenderer class is used to render a search result to a html page.
+ */
+class SearchRenderer
+{
+ public:
+  /**
+   * The default constructor.
+   *
+   * @param humanReadableName The global zim's humanReadableName.
+   *                          Used to generate pagination links.
+   */
+  SearchRenderer(Searcher* searcher, NameMapper* mapper);
+
+  ~SearchRenderer();
+
+  void setSearchPattern(const std::string& pattern);
+
+  /**
+   * Set the search content id.
+   */
+  void setSearchContent(const std::string& name);
+
+  /**
+   * Set protocol prefix.
+   */
+  void setProtocolPrefix(const std::string& prefix);
+
+  /**
+   * Set search protocol prefix.
+   */
+  void setSearchProtocolPrefix(const std::string& prefix);
+
+  /**
+   * Generate the html page with the resutls of the search.
+   */
+  std::string getHtml();
+
+ protected:
+  std::string beautifyInteger(const unsigned int number);
+  Searcher* mp_searcher;
+  NameMapper* mp_nameMapper;
+  std::string searchContent;
+  std::string searchPattern;
+  std::string protocolPrefix;
+  std::string searchProtocolPrefix;
+  unsigned int resultCountPerPage;
+  unsigned int estimatedResultCount;
+  unsigned int resultStart;
+  unsigned int resultEnd;
+};
+
+
+}
+
+#endif

include/searcher.h

@@ -0,0 +1,172 @@
+/*
+ * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_SEARCHER_H
+#define KIWIX_SEARCHER_H
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unicode/putil.h>
+#include <algorithm>
+#include <cctype>
+#include <locale>
+#include <string>
+#include <vector>
+#include <vector>
+#include "tools/pathTools.h"
+#include "tools/stringTools.h"
+#include "kiwix_config.h"
+
+using namespace std;
+
+namespace kiwix
+{
+class Reader;
+class Result
+{
+ public:
+  virtual ~Result(){};
+  virtual std::string get_url() = 0;
+  virtual std::string get_title() = 0;
+  virtual int get_score() = 0;
+  virtual std::string get_snippet() = 0;
+  virtual std::string get_content() = 0;
+  virtual int get_wordCount() = 0;
+  virtual int get_size() = 0;
+  virtual int get_readerIndex() = 0;
+};
+
+struct SearcherInternal;
+/**
+ * The Searcher class is reponsible to do different kind of search using the
+ * fulltext index.
+ */
+class Searcher
+{
+ public:
+  /**
+   * The default constructor.
+   */
+  Searcher();
+
+  ~Searcher();
+
+  /**
+   * Add a reader (containing embedded fulltext index) to the search.
+   *
+   * @param reader The Reader for the zim containing the fulltext index.
+   * @return true if the reader has been added.
+   *         false if the reader cannot be added (no embedded fulltext index present)
+   */
+  bool add_reader(Reader* reader);
+
+
+  Reader* get_reader(int index);
+
+  /**
+   * Start a search on the zim associated to the Searcher.
+   *
+   * Search results should be retrived using the getNextResult method.
+   *
+   * @param search The search query.
+   * @param resultStart the start offset of the search results (used for pagination).
+   * @param resultEnd the end offset of the search results (used for pagination).
+   * @param verbose print some info on stdout if true.
+   */
+  void search(std::string& search,
+              unsigned int resultStart,
+              unsigned int resultEnd,
+              const bool verbose = false);
+
+  /**
+   * Start a geographique search.
+   * The search return result for entry in a disc of center latitude/longitude
+   * and radius distance.
+   *
+   * Search results should be retrived using the getNextResult method.
+   *
+   * @param latitude The latitude of the center point.
+   * @param longitude The longitude of the center point.
+   * @param distance The radius of the disc.
+   * @param resultStart the start offset of the search results (used for pagination).
+   * @param resultEnd the end offset of the search results (used for pagination).
+   * @param verbose print some info on stdout if true.
+   */
+  void geo_search(float latitude, float longitude, float distance,
+                  unsigned int resultStart,
+                  unsigned int resultEnd,
+                  const bool verbose = false);
+
+  /**
+   * Start a suggestion search.
+   * The search made depend of the "version" of the embedded index.
+   *  - If the index is newer enough and have a title namespace, the search is
+   *    made in the titles only.
+   *  - Else the search is made on the whole article content.
+   * In any case, the search is made "partial" (as adding '*' at the end of the query)
+   *
+   * @param search The search query.
+   * @param verbose print some info on stdout if true.
+   */
+  void suggestions(std::string& search, const bool verbose = false);
+
+  /**
+   * Get the next result of a started search.
+   * This is the method to use to loop hover the search results.
+   */
+  Result* getNextResult();
+
+  /**
+   * Restart the previous search.
+   * Next call to getNextResult will return the first result.
+   */
+  void restart_search();
+
+  /**
+   * Get a estimation of the result count.
+   */
+  unsigned int getEstimatedResultCount();
+
+  unsigned int getResultStart() { return resultStart; }
+  unsigned int getResultEnd() { return resultEnd; }
+
+ protected:
+  std::string beautifyInteger(const unsigned int number);
+  void closeIndex();
+  void searchInIndex(string& search,
+                     const unsigned int resultStart,
+                     const unsigned int resultEnd,
+                     const bool verbose = false);
+
+  std::vector<Reader*> readers;
+  SearcherInternal* internal;
+  std::string searchPattern;
+  unsigned int estimatedResultCount;
+  unsigned int resultStart;
+  unsigned int resultEnd;
+
+ private:
+  void reset();
+
+};
+
+
+}
+
+#endif

include/server.h

@@ -0,0 +1,75 @@
+/*
+ * Copyright 2019 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_SERVER_H
+#define KIWIX_SERVER_H
+
+#include <string>
+#include <memory>
+
+namespace kiwix
+{
+  class Library;
+  class NameMapper;
+  class InternalServer;
+
+  class Server {
+     public:
+       /**
+        * The default constructor.
+        *
+        * @param library The library to serve.
+        */
+       Server(Library* library, NameMapper* nameMapper=nullptr);
+
+       virtual ~Server();
+
+       /**
+        * Serve the content.
+        */
+       bool start();
+
+       /**
+        * Stop the daemon.
+        */
+       void stop();
+
+       void setRoot(const std::string& root);
+       void setAddress(const std::string& addr) { m_addr = addr; }
+       void setPort(int port) { m_port = port; }
+       void setNbThreads(int threads) { m_nbThreads = threads; }
+       void setVerbose(bool verbose) { m_verbose = verbose; }
+       void setTaskbar(bool withTaskbar, bool withLibraryButton)
+         { m_withTaskbar = withTaskbar; m_withLibraryButton = withLibraryButton; }
+
+     protected:
+       Library* mp_library;
+       NameMapper* mp_nameMapper;
+       std::string m_root = "";
+       std::string m_addr = "";
+       int m_port = 80;
+       int m_nbThreads = 1;
+       bool m_verbose = false;
+       bool m_withTaskbar = true;
+       bool m_withLibraryButton = true;
+       std::unique_ptr<InternalServer> mp_server;
+  };
+}
+
+#endif

include/tools/base64.h

@@ -0,0 +1,4 @@
+#include <string>
+
+std::string base64_encode(const std::string& inString);
+std::string base64_decode(const std::string& s);

include/tools/lock.h

@@ -0,0 +1,46 @@
+
+
+#ifndef KIWIXLIB_TOOL_LOCK_H
+#define KIWIXLIB_TOOL_LOCK_H
+
+#include <pthread.h>
+
+namespace kiwix {
+
+class Lock
+{
+  public:
+    explicit Lock(pthread_mutex_t* mutex) :
+      mp_mutex(mutex)
+    {
+      pthread_mutex_lock(mp_mutex);
+    }
+    ~Lock() {
+      if (mp_mutex != nullptr) {
+        pthread_mutex_unlock(mp_mutex);
+      }
+    }
+    Lock(Lock && other) :
+      mp_mutex(other.mp_mutex)
+    {
+      other.mp_mutex = nullptr;
+    }
+    Lock & operator=(Lock && other)
+    {
+      mp_mutex = other.mp_mutex;
+      other.mp_mutex = nullptr;
+      return *this;
+    }
+
+
+  private:
+    pthread_mutex_t* mp_mutex;
+
+    Lock(Lock const &) = delete;
+    Lock & operator=(Lock const &) = delete;
+};
+
+
+}
+
+#endif //KIWIXLIB_TOOL_LOCK_H

include/tools/networkTools.h

@@ -1,5 +1,5 @@
 /*
- * Copyright 2014 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright 2012 Emmanuel Engelhart <kelson@kiwix.org>
  *
  * 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
@@ -17,12 +17,14 @@
  * MA 02110-1301, USA.
  */
 
-#include "otherTools.h"
+#ifndef KIWIX_NETWORKTOOLS_H
+#define KIWIX_NETWORKTOOLS_H
 
-void kiwix::sleep(unsigned int milliseconds) {
-#ifdef _WIN32
-      Sleep(milliseconds);
-#else
-      usleep(1000 * milliseconds);
-#endif
+#include <string>
+
+namespace kiwix
+{
+std::string download(const std::string& url);
 }
+
+#endif

include/tools/otherTools.h

@@ -20,14 +20,17 @@
 #ifndef KIWIX_OTHERTOOLS_H
 #define KIWIX_OTHERTOOLS_H
 
-#ifdef _WIN32
-#include <Windows.h>
-#else
-#include <unistd.h>
-#endif
+#include <string>
 
-namespace kiwix {
-  void sleep(unsigned int milliseconds);
+namespace pugi {
+  class xml_node;
+}
+
+namespace kiwix
+{
+void sleep(unsigned int milliseconds);
+std::string nodeToString(const pugi::xml_node& node);
+std::string converta2toa3(const std::string& a2code);
 }
 
 #endif

include/tools/pathTools.h

@@ -0,0 +1,44 @@
+/*
+ * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_PATHTOOLS_H
+#define KIWIX_PATHTOOLS_H
+
+#include <string>
+
+bool isRelativePath(const std::string& path);
+std::string computeAbsolutePath(const std::string& path, const std::string& relativePath);
+std::string computeRelativePath(const std::string& path, const std::string& absolutePath);
+std::string removeLastPathElement(const std::string& path);
+std::string appendToDirectory(const std::string& directoryPath, const std::string& filename);
+
+unsigned int getFileSize(const std::string& path);
+std::string getFileSizeAsString(const std::string& path);
+std::string getFileContent(const std::string& path);
+bool fileExists(const std::string& path);
+bool makeDirectory(const std::string& path);
+std::string makeTmpDirectory();
+bool copyFile(const std::string& sourcePath, const std::string& destPath);
+std::string getLastPathElement(const std::string& path);
+std::string getExecutablePath(bool realPathOnly = false);
+std::string getCurrentDirectory();
+std::string getDataDirectory();
+bool writeTextFile(const std::string& path, const std::string& content);
+std::string getMimeTypeForFile(const std::string& filename);
+#endif

include/tools/regexTools.h

@@ -20,13 +20,14 @@
 #ifndef KIWIX_REGEXTOOLS_H
 #define KIWIX_REGEXTOOLS_H
 
-#include <unicode/regex.h>
-#include <unicode/ucnv.h>
 #include <string>
-#include <map>
 
-bool matchRegex(const std::string &content, const std::string &regex);
-std::string replaceRegex(const std::string &content, const std::string &replacement, const std::string &regex);
-std::string appendToFirstOccurence(const std::string &content, const std::string regex, const std::string &replacement);
+bool matchRegex(const std::string& content, const std::string& regex);
+std::string replaceRegex(const std::string& content,
+                         const std::string& replacement,
+                         const std::string& regex);
+std::string appendToFirstOccurence(const std::string& content,
+                                   const std::string& regex,
+                                   const std::string& replacement);
 
 #endif

include/tools/stringTools.h

@@ -0,0 +1,74 @@
+/*
+ * Copyright 2011-2012 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#ifndef KIWIX_STRINGTOOLS_H
+#define KIWIX_STRINGTOOLS_H
+
+#include <unicode/unistr.h>
+
+#include <string>
+#include <vector>
+#include <sstream>
+
+namespace kiwix
+{
+std::string beautifyInteger(uint64_t number);
+std::string beautifyFileSize(uint64_t number);
+void printStringInHexadecimal(const char* s);
+void printStringInHexadecimal(icu::UnicodeString s);
+void stringReplacement(std::string& str,
+                       const std::string& oldStr,
+                       const std::string& newStr);
+std::string encodeDiples(const std::string& str);
+
+std::string removeAccents(const std::string& text);
+void loadICUExternalTables();
+
+std::string urlEncode(const std::string& value, bool encodeReserved = false);
+std::string urlDecode(const std::string& value, bool component = false);
+
+std::vector<std::string> split(const std::string&, const std::string&, bool trimEmpty = true);
+std::string join(const std::vector<std::string>& list, const std::string& sep);
+
+std::string ucAll(const std::string& word);
+std::string lcAll(const std::string& word);
+std::string ucFirst(const std::string& word);
+std::string lcFirst(const std::string& word);
+std::string toTitle(const std::string& word);
+
+std::string normalize(const std::string& word);
+template<typename T>
+std::string to_string(T value)
+{
+    std::ostringstream oss;
+    oss << value;
+    return oss.str();
+}
+
+template<typename T>
+T extractFromString(const std::string& str) {
+    std::istringstream iss(str);
+    T ret;
+    iss >> ret;
+    return ret;
+}
+
+bool startsWith(const std::string& base, const std::string& start);
+} //namespace kiwix
+#endif

kiwix.pc.in

@@ -0,0 +1,10 @@
+prefix=@prefix@
+libdir=${prefix}/lib64
+includedir=${prefix}/include
+
+Name: libkiwix
+Description: A library that contains a lot of things used by used by other kiwix programs
+Version: @version@
+Requires: @requires@
+Libs: -L${libdir} -lkiwix @extra_libs@
+Cflags: -I${includedir}/ @extra_cflags@

meson.build

@@ -0,0 +1,64 @@
+project('kiwix-lib', 'cpp',
+  version : '8.2.2', # Also change this in android-kiwix-lib-publisher/kiwixLibAndroid/build.gradle
+  license : 'GPL',
+  default_options : ['c_std=c11', 'cpp_std=c++11', 'werror=true'])
+
+compiler = meson.get_compiler('cpp')
+
+static_deps = get_option('android') or get_option('default_library') == 'static'
+if get_option('android')
+  extra_libs = ['-llog']
+else
+  extra_libs = []
+endif
+
+thread_dep = dependency('threads')
+libicu_dep = dependency('icu-i18n', static:static_deps)
+libzim_dep = dependency('libzim', version : '>=5.0.0', static:static_deps)
+pugixml_dep = dependency('pugixml', static:static_deps)
+libcurl_dep = dependency('libcurl', static:static_deps)
+microhttpd_dep = dependency('libmicrohttpd', static:static_deps)
+
+if not compiler.has_header('mustache.hpp')
+  error('Cannot found header mustache.hpp')
+endif
+
+extra_cflags = ''
+if target_machine.system() == 'windows' and static_deps
+  add_project_arguments('-DCURL_STATICLIB', language : 'cpp')
+  extra_cflags += '-DCURL_STATICLIB'
+endif
+
+all_deps = [thread_dep, libicu_dep, libzim_dep, pugixml_dep, libcurl_dep, microhttpd_dep]
+
+inc = include_directories('include')
+
+conf = configuration_data()
+conf.set('VERSION', '"@0@"'.format(meson.project_version()))
+
+if build_machine.system() == 'windows'
+     extra_link_args = ['-lshlwapi', '-lwinmm']
+else
+     extra_link_args = []
+endif
+
+subdir('include')
+subdir('scripts')
+subdir('static')
+subdir('src')
+subdir('test')
+
+pkg_requires = ['libzim', 'icu-i18n', 'pugixml', 'libcurl']
+
+pkg_conf = configuration_data()
+pkg_conf.set('prefix', get_option('prefix'))
+pkg_conf.set('requires', ' '.join(pkg_requires))
+pkg_conf.set('extra_libs', ' '.join(extra_libs))
+pkg_conf.set('extra_cflags', extra_cflags)
+pkg_conf.set('version', meson.project_version())
+configure_file(output : 'kiwix.pc',
+               configuration : pkg_conf,
+               input : 'kiwix.pc.in',
+               install_dir: get_option('libdir')+'/pkgconfig'
+              )
+

meson_options.txt

@@ -0,0 +1,2 @@
+option('android', type : 'boolean', value : false,
+  description : 'Do we make a kiwix-lib for android')

scripts/kiwix-compile-resources

@@ -0,0 +1,201 @@
+#!/usr/bin/env python3
+
+'''
+Copyright 2016 Matthieu Gautier <mgautier@kymeria.fr>
+
+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 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, write to the Free Software
+Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+02110-1301, USA.
+'''
+
+import argparse
+import os.path
+import re
+
+def full_identifier(filename):
+    parts = os.path.normpath(filename).split(os.sep)
+    parts = [to_identifier(part) for part in parts]
+    print(filename, parts)
+    return parts
+
+def to_identifier(name):
+    ident = re.sub(r'[^0-9a-zA-Z]', '_', name)
+    if ident[0].isnumeric():
+        return "_"+ident
+    return ident
+
+resource_impl_template = """
+static const unsigned char {data_identifier}[] = {{
+    {resource_content}
+}};
+
+namespace RESOURCE {{
+{namespaces_open}
+const std::string {identifier} = init_resource("{env_identifier}", {data_identifier}, {resource_len});
+{namespaces_close}
+}}
+"""
+
+resource_getter_template = """
+    if (name == "{common_name}")
+        return RESOURCE::{identifier};
+"""
+
+resource_decl_template = """{namespaces_open}
+extern const std::string {identifier};
+{namespaces_close}"""
+
+class Resource:
+    def __init__(self, base_dirs, filename):
+        filename = filename.strip()
+        self.filename = filename
+        self.identifier = full_identifier(filename)
+        found = False
+        for base_dir in base_dirs:
+            try:
+                with open(os.path.join(base_dir, filename), 'rb') as f:
+                    self.data = f.read()
+                found = True
+                break
+            except FileNotFoundError:
+                continue
+        if not found:
+            raise Exception("Impossible to found {}".format(filename))
+
+    def dump_impl(self):
+        nb_row = len(self.data)//16 + (1 if len(self.data) % 16 else 0)
+        sliced = (self.data[i*16:(i+1)*16] for i in range(nb_row))
+
+        return resource_impl_template.format(
+            data_identifier="_".join([""]+self.identifier),
+            resource_content=",\n    ".join(", ".join("{:#04x}".format(i) for i in r) for r in sliced),
+            resource_len=len(self.data),
+            namespaces_open=" ".join("namespace {} {{".format(id) for id in self.identifier[:-1]),
+            namespaces_close=" ".join(["}"]*(len(self.identifier)-1)),
+            identifier=self.identifier[-1],
+            env_identifier="RES_"+"_".join(self.identifier)+"_PATH"
+        )
+
+    def dump_getter(self):
+        return resource_getter_template.format(
+            common_name=self.filename,
+            identifier="::".join(self.identifier)
+        )
+
+    def dump_decl(self):
+        return resource_decl_template.format(
+            namespaces_open=" ".join("namespace {} {{".format(id) for id in self.identifier[:-1]),
+            namespaces_close=" ".join(["}"]*(len(self.identifier)-1)),
+            identifier=self.identifier[-1]
+        )
+
+
+
+master_c_template = """//This file is automaically generated. Do not modify it.
+
+#include <stdlib.h>
+#include <fstream>
+#include "{include_file}"
+
+static std::string init_resource(const char* name, const unsigned char* content, int len)
+{{
+    char * resPath = getenv(name);
+    if (NULL == resPath)
+        return std::string(reinterpret_cast<const char*>(content), len);
+
+    std::ifstream ifs(resPath);
+    if (!ifs.good())
+        return std::string(reinterpret_cast<const char*>(content), len);
+    return std::string( (std::istreambuf_iterator<char>(ifs)),
+                        (std::istreambuf_iterator<char>()   ));
+}}
+
+const std::string& getResource_{basename}(const std::string& name) {{
+{RESOURCES_GETTER}
+    throw ResourceNotFound("Resource not found.");
+}}
+
+{RESOURCES}
+
+"""
+
+def gen_c_file(resources, basename):
+    return master_c_template.format(
+       RESOURCES="\n\n".join(r.dump_impl() for r in resources),
+       RESOURCES_GETTER="\n\n".join(r.dump_getter() for r in resources),
+       include_file=basename,
+       basename=to_identifier(basename)
+    )
+
+
+
+master_h_template = """//This file is automaically generated. Do not modify it.
+#ifndef KIWIX_{BASENAME}
+#define KIWIX_{BASENAME}
+
+#include <string>
+#include <stdexcept>
+
+namespace RESOURCE {{
+    {RESOURCES}
+}};
+
+class ResourceNotFound : public std::runtime_error {{
+  public:
+    ResourceNotFound(const std::string& what_arg):
+      std::runtime_error(what_arg)
+    {{ }};
+}};
+
+const std::string& getResource_{basename}(const std::string& name);
+
+#define getResource(a) (getResource_{basename}(a))
+
+#endif // KIWIX_{BASENAME}
+
+"""
+
+def gen_h_file(resources, basename):
+    return master_h_template.format(
+       RESOURCES="\n    ".join(r.dump_decl() for r in resources),
+       BASENAME=basename.upper(),
+       basename=basename,
+    )
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--cxxfile',
+                        help='The Cpp file name to generate')
+    parser.add_argument('--hfile',
+                        help='The h file name to generate')
+    parser.add_argument('--source_dir',
+                        help="Additional directory where to look for resources.",
+                        action='append')
+    parser.add_argument('resource_file',
+                        help='The list of resources to compile.')
+    args = parser.parse_args()
+
+    base_dir = os.path.dirname(os.path.realpath(args.resource_file))
+    source_dir = args.source_dir or []
+    with open(args.resource_file, 'r') as f:
+        resources = [Resource([base_dir]+source_dir, filename)
+                        for filename in f.readlines()]
+
+    h_identifier = to_identifier(os.path.basename(args.hfile))
+    with open(args.hfile, 'w') as f:
+        f.write(gen_h_file(resources, h_identifier))
+
+    with open(args.cxxfile, 'w') as f:
+        f.write(gen_c_file(resources, os.path.basename(args.hfile)))
+

scripts/meson.build

@@ -0,0 +1,4 @@
+
+res_compiler = find_program('kiwix-compile-resources')
+
+install_data(res_compiler.path(), install_dir:get_option('bindir'))

src/android/AndroidManifest.xml

@@ -0,0 +1,13 @@
+<manifest xmlns:android="http://schemas.android.com/apk/res/android"
+
+  package="kiwix.org.kiwixlib"
+>
+
+  <application android:allowBackup="true"
+    android:label="@string/app_name"
+    android:supportsRtl="true"
+  >
+
+  </application>
+
+</manifest>

src/android/kiwixicu.cpp

@@ -0,0 +1,44 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#include <jni.h>
+#include "org_kiwix_kiwixlib_JNIICU.h"
+
+#include <iostream>
+#include <string>
+
+#include "unicode/putil.h"
+
+#include "utils.h"
+
+pthread_mutex_t globalLock = PTHREAD_RECURSIVE_MUTEX_INITIALIZER;
+
+JNIEXPORT void JNICALL Java_org_kiwix_kiwixlib_JNIICU_setDataDirectory(
+    JNIEnv* env, jclass kclass, jstring dirStr)
+{
+  std::string cPath = jni2c(dirStr, env);
+
+  Lock l;
+  try {
+    u_setDataDirectory(cPath.c_str());
+  } catch (...) {
+    std::cerr << "Unable to set data directory " << cPath << std::endl;
+  }
+}

src/android/kiwixlibrary.cpp

@@ -0,0 +1,72 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+
+#include <jni.h>
+#include <android/log.h>
+#include "org_kiwix_kiwixlib_JNIKiwixLibrary.h"
+
+#include "library.h"
+#include "reader.h"
+#include "utils.h"
+
+/* Kiwix Reader JNI functions */
+JNIEXPORT jlong JNICALL Java_org_kiwix_kiwixlib_JNIKiwixLibrary_getNativeLibrary(
+    JNIEnv* env, jobject obj)
+{
+  __android_log_print(ANDROID_LOG_INFO, "kiwix", "Attempting to create library");
+  Lock l;
+  try {
+    kiwix::Library* library = new kiwix::Library();
+    return reinterpret_cast<jlong>(new Handle<kiwix::Library>(library));
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", "Error creating ZIM library");
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
+    return 0;
+  }
+}
+
+JNIEXPORT void JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixLibrary_dispose(JNIEnv* env, jobject obj)
+{
+  Handle<kiwix::Library>::dispose(env, obj);
+}
+
+#define LIBRARY (Handle<kiwix::Library>::getHandle(env, obj))
+
+/* Kiwix library functions */
+JNIEXPORT jboolean JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixLibrary_addBook(JNIEnv* env, jobject obj, jstring path)
+{
+  std::string cPath = jni2c(path, env);
+  bool ret;
+
+  try {
+    kiwix::Reader reader(cPath);
+    kiwix::Book book;
+    book.update(reader);
+    ret = LIBRARY->addBook(book);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to add the book");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    ret = false;
+  }
+  return ret;
+}

src/android/kiwixreader.cpp

@@ -0,0 +1,474 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+
+#include <jni.h>
+#include <zim/file.h>
+#include <android/log.h>
+#include "org_kiwix_kiwixlib_JNIKiwixReader.h"
+
+#include "tools/base64.h"
+#include "reader.h"
+#include "utils.h"
+
+/* Kiwix Reader JNI functions */
+JNIEXPORT jlong JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getNativeReader(
+    JNIEnv* env, jobject obj, jstring filename)
+{
+  std::string cPath = jni2c(filename, env);
+
+  __android_log_print(ANDROID_LOG_INFO, "kiwix", "Attempting to create reader with: %s", cPath.c_str());
+  Lock l;
+  try {
+    kiwix::Reader* reader = new kiwix::Reader(cPath);
+    return reinterpret_cast<jlong>(new Handle<kiwix::Reader>(reader));
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", "Error opening ZIM file");
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
+    return 0;
+  }
+}
+
+JNIEXPORT void JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_dispose(JNIEnv* env, jobject obj)
+{
+  Handle<kiwix::Reader>::dispose(env, obj);
+}
+
+#define READER (Handle<kiwix::Reader>::getHandle(env, obj))
+
+/* Kiwix library functions */
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getMainPage(JNIEnv* env, jobject obj)
+{
+  jstring url;
+
+  try {
+    std::string cUrl = READER->getMainPage().getPath();
+    url = c2jni(cUrl, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM main page");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    url = NULL;
+  }
+  return url;
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getId(JNIEnv* env, jobject obj)
+{
+  jstring id;
+
+  try {
+    std::string cId = READER->getId();
+    id = c2jni(cId, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM id");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    id = NULL;
+  }
+
+  return id;
+}
+
+JNIEXPORT jint JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getFileSize(JNIEnv* env, jobject obj)
+{
+  jint size = 0;
+
+  try {
+    int cSize = READER->getFileSize();
+    size = c2jni(cSize);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM file size");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+  }
+
+  return size;
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getCreator(JNIEnv* env, jobject obj)
+{
+  jstring creator;
+
+  try {
+    std::string cCreator = READER->getCreator();
+    creator = c2jni(cCreator, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM creator");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    creator = NULL;
+  }
+
+  return creator;
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getPublisher(JNIEnv* env, jobject obj)
+{
+  jstring publisher;
+
+  try {
+    std::string cPublisher = READER->getPublisher();
+    publisher = c2jni(cPublisher, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM publish");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    publisher = NULL;
+  }
+  return publisher;
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getName(JNIEnv* env, jobject obj)
+{
+  jstring name;
+
+  try {
+    std::string cName = READER->getName();
+    name = c2jni(cName, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM name");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    name = NULL;
+  }
+  return name;
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getFavicon(JNIEnv* env, jobject obj)
+{
+  jstring favicon;
+
+  try {
+    std::string cContent;
+    std::string cMime;
+    READER->getFavicon(cContent, cMime);
+    favicon = c2jni(
+        base64_encode(cContent),
+        env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM favicon");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    favicon = NULL;
+  }
+  return favicon;
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getDate(JNIEnv* env, jobject obj)
+{
+  jstring date;
+
+  try {
+    std::string cDate = READER->getDate();
+    date = c2jni(cDate, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM date");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    date = NULL;
+  }
+  return date;
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getLanguage(JNIEnv* env, jobject obj)
+{
+  jstring language;
+
+  try {
+    std::string cLanguage = READER->getLanguage();
+    language = c2jni(cLanguage, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get ZIM language");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    language = NULL;
+  }
+
+  return language;
+}
+
+JNIEXPORT jstring JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getMimeType(
+    JNIEnv* env, jobject obj, jstring url)
+{
+  jstring mimeType;
+
+  std::string cUrl = jni2c(url, env);
+  try {
+    auto entry = READER->getEntryFromEncodedPath(cUrl);
+    auto cMimeType = entry.getMimetype();
+    mimeType = c2jni(cMimeType, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get mime-type for url: %s", cUrl.c_str());
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    mimeType = NULL;
+  }
+  return mimeType;
+}
+
+JNIEXPORT jstring JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_checkUrl(
+     JNIEnv* env, jobject obj, jstring url)
+{
+  jstring finalUrl;
+  std::string cUrl = jni2c(url, env);
+  try {
+    auto entry = READER->getEntryFromEncodedPath(cUrl);
+    entry = entry.getFinalEntry();
+    finalUrl = c2jni(entry.getPath(), env);
+  } catch (std::exception& e) {
+    finalUrl = c2jni("", env);
+  }
+  return finalUrl;
+}
+
+JNIEXPORT jbyteArray JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getContent(
+    JNIEnv* env, jobject obj, jobject url, jobject titleObj, jobject mimeTypeObj, jobject sizeObj)
+{
+  /* Default values */
+  setStringObjValue("", titleObj, env);
+  setStringObjValue("", mimeTypeObj, env);
+  setIntObjValue(0, sizeObj, env);
+  jbyteArray data = env->NewByteArray(0);
+
+  /* Retrieve the content */
+  std::string cUrl = getStringObjValue(url, env);
+  unsigned int cSize = 0;
+
+  try {
+    auto entry = READER->getEntryFromEncodedPath(cUrl);
+    bool isRedirect = entry.isRedirect();
+    entry = entry.getFinalEntry();
+    cSize = entry.getSize();
+    setIntObjValue(cSize, sizeObj, env);
+    setStringObjValue(entry.getMimetype(), mimeTypeObj, env);
+    setStringObjValue(entry.getTitle(), titleObj, env);
+    if (isRedirect) {
+      setStringObjValue(entry.getPath(), url, env);
+    } else {
+      data = env->NewByteArray(cSize);
+      env->SetByteArrayRegion(
+          data, 0, cSize, reinterpret_cast<const jbyte*>(entry.getBlob().data()));
+    }
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get content for url: %s", cUrl.c_str());
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+  }
+
+  return data;
+}
+
+JNIEXPORT jbyteArray JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getContentPart(
+    JNIEnv* env, jobject obj, jstring url, jint offset, jint len, jobject sizeObj)
+{
+  jbyteArray data = env->NewByteArray(0);
+  setIntObjValue(0, sizeObj, env);
+
+  /* Default values */
+  /* Retrieve the content */
+  std::string cUrl = jni2c(url, env);
+  unsigned int cOffset = jni2c(offset);
+  unsigned int cLen = jni2c(len);
+  try {
+    auto entry = READER->getEntryFromEncodedPath(cUrl);
+    entry = entry.getFinalEntry();
+
+    if (cLen == 0) {
+      setIntObjValue(entry.getSize(), sizeObj, env);
+    } else if (cOffset+cLen < entry.getSize()) {
+      auto blob = entry.getBlob(cOffset, cLen);
+      data = env->NewByteArray(cLen);
+      env->SetByteArrayRegion(
+          data, 0, cLen, reinterpret_cast<const jbyte*>(blob.data()));
+      setIntObjValue(cLen, sizeObj, env);
+    }
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get partial content for url: %s (%u : %u)", cUrl.c_str(), cOffset, cLen);
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+  }
+  return data;
+}
+
+JNIEXPORT jobject JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getDirectAccessInformation(
+    JNIEnv* env, jobject obj, jstring url)
+{
+   jclass classPair = env->FindClass("org/kiwix/kiwixlib/Pair");
+   jmethodID midPairinit = env->GetMethodID(classPair, "<init>", "()V");
+   jobject pair = env->NewObject(classPair, midPairinit);
+   setPairObjValue("", 0, pair, env);
+
+   std::string cUrl = jni2c(url, env);
+   try {
+    auto entry = READER->getEntryFromEncodedPath(cUrl);
+    entry = entry.getFinalEntry();
+    auto part_info = entry.getDirectAccessInfo();
+    setPairObjValue(part_info.first, part_info.second, pair, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get direct access info for url: %s", cUrl.c_str());
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+  }
+  return pair;
+}
+
+JNIEXPORT jboolean JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_searchSuggestions(JNIEnv* env,
+                                                         jobject obj,
+                                                         jstring prefix,
+                                                         jint count)
+{
+  jboolean retVal = JNI_FALSE;
+  std::string cPrefix = jni2c(prefix, env);
+  unsigned int cCount = jni2c(count);
+
+  try {
+    if (READER->searchSuggestionsSmart(cPrefix, cCount)) {
+      retVal = JNI_TRUE;
+    }
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", "Unable to get search results for pattern: %s", cPrefix.c_str());
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
+  }
+
+  return retVal;
+}
+
+JNIEXPORT jboolean JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getNextSuggestion(JNIEnv* env,
+                                                         jobject obj,
+                                                         jobject titleObj,
+                                                         jobject urlObj)
+{
+  jboolean retVal = JNI_FALSE;
+  std::string cTitle;
+  std::string cUrl;
+
+  try {
+    if (READER->getNextSuggestion(cTitle, cUrl)) {
+      setStringObjValue(cTitle, titleObj, env);
+      setStringObjValue(cUrl, urlObj, env);
+      retVal = JNI_TRUE;
+    }
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", "Unable to get next suggestion");
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
+  }
+
+  return retVal;
+}
+
+JNIEXPORT jboolean JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getPageUrlFromTitle(JNIEnv* env,
+                                                           jobject obj,
+                                                           jstring title,
+                                                           jobject urlObj)
+{
+  std::string cTitle = jni2c(title, env);
+
+  try {
+    auto entry = READER->getEntryFromTitle(cTitle);
+    entry = entry.getFinalEntry();
+    setStringObjValue(entry.getPath(), urlObj, env);
+    return JNI_TRUE;
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", "Unable to get url for title %s: ", cTitle.c_str());
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
+  }
+
+  return JNI_FALSE;
+}
+
+JNIEXPORT jstring JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getTitle(
+    JNIEnv* env, jobject obj)
+{
+  jstring title;
+
+  try {
+    std::string cTitle = READER->getTitle();
+    title = c2jni(cTitle, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get zim title");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    title = NULL;
+  }
+  return title;
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getDescription(JNIEnv* env, jobject obj)
+{
+  jstring description;
+
+  try {
+    std::string cDescription = READER->getDescription();
+    description = c2jni(cDescription, env);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get zim description");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+    description = NULL;
+  }
+  return description;
+}
+
+JNIEXPORT jint JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getArticleCount(JNIEnv* env, jobject obj)
+{
+  jint articleCount = 0;
+  try {
+    auto cArticleCount = READER->getArticleCount();
+    articleCount = c2jni(cArticleCount);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get article count.");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+  }
+  return articleCount;
+}
+
+JNIEXPORT jint JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixReader_getMediaCount(JNIEnv* env, jobject obj)
+{
+  jint mediaCount = 0;
+  try {
+    auto cMediaCount = READER->getMediaCount();
+    mediaCount = c2jni(cMediaCount);
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get media count.");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+  }
+  return mediaCount;
+}
+
+
+JNIEXPORT jboolean JNICALL Java_org_kiwix_kiwixlib_JNIKiwixReader_getRandomPage(
+    JNIEnv* env, jobject obj, jobject urlObj)
+{
+  jboolean retVal = JNI_FALSE;
+  std::string cUrl;
+
+  try {
+    std::string cUrl = READER->getRandomPage().getPath();
+    setStringObjValue(cUrl, urlObj, env);
+    retVal = JNI_TRUE;
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", "Unable to get random page");
+    __android_log_print(ANDROID_LOG_ERROR, "kiwix", e.what());
+  }
+  return retVal;
+}

src/android/kiwixsearcher.cpp

@@ -0,0 +1,124 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+
+#include <zim/file.h>
+#include "org_kiwix_kiwixlib_JNIKiwixSearcher.h"
+#include "org_kiwix_kiwixlib_JNIKiwixSearcher_Result.h"
+
+#include "reader.h"
+#include "searcher.h"
+#include "utils.h"
+
+#define SEARCHER (Handle<kiwix::Searcher>::getHandle(env, obj))
+#define RESULT (Handle<kiwix::Result>::getHandle(env, obj))
+
+
+JNIEXPORT void JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixSearcher_dispose(JNIEnv* env, jobject obj)
+{
+  Handle<kiwix::Searcher>::dispose(env, obj);
+}
+
+/* Kiwix Reader JNI functions */
+JNIEXPORT jlong JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixSearcher_getNativeHandle(JNIEnv* env,
+                                                          jobject obj)
+{
+  kiwix::Searcher* searcher = new kiwix::Searcher();
+  return reinterpret_cast<jlong>(new Handle<kiwix::Searcher>(searcher));
+}
+
+/* Kiwix library functions */
+JNIEXPORT void JNICALL Java_org_kiwix_kiwixlib_JNIKiwixSearcher_addReader(
+    JNIEnv* env, jobject obj, jobject reader)
+{
+  auto searcher = SEARCHER;
+
+  searcher->add_reader(*(Handle<kiwix::Reader>::getHandle(env, reader)));
+}
+
+JNIEXPORT void JNICALL Java_org_kiwix_kiwixlib_JNIKiwixSearcher_search(
+    JNIEnv* env, jobject obj, jstring query, jint count)
+{
+  std::string cquery = jni2c(query, env);
+  unsigned int ccount = jni2c(count);
+
+  SEARCHER->search(cquery, 0, ccount);
+}
+
+JNIEXPORT jobject JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixSearcher_getNextResult(JNIEnv* env,
+                                                         jobject obj)
+{
+  jobject result = nullptr;
+
+  kiwix::Result* cresult = SEARCHER->getNextResult();
+  if (cresult != nullptr) {
+    jclass resultclass
+        = env->FindClass("org/kiwix/kiwixlib/JNIKiwixSearcher$Result");
+    jmethodID ctor = env->GetMethodID(
+        resultclass, "<init>", "(Lorg/kiwix/kiwixlib/JNIKiwixSearcher;JLorg/kiwix/kiwixlib/JNIKiwixSearcher;)V");
+    result = env->NewObject(resultclass, ctor, obj, reinterpret_cast<jlong>(new Handle<kiwix::Result>(cresult)), obj);
+  }
+  return result;
+}
+
+JNIEXPORT void JNICALL Java_org_kiwix_kiwixlib_JNIKiwixSearcher_00024Result_dispose(
+    JNIEnv* env, jobject obj)
+{
+  Handle<kiwix::Result>::dispose(env, obj);
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixSearcher_00024Result_getUrl(JNIEnv* env,
+                                                        jobject obj)
+{
+  try {
+    return c2jni(RESULT->get_url(), env);
+  } catch (...) {
+    return nullptr;
+  }
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixSearcher_00024Result_getTitle(JNIEnv* env,
+                                                          jobject obj)
+{
+  try {
+    return c2jni(RESULT->get_title(), env);
+  } catch (...) {
+    return nullptr;
+  }
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixSearcher_00024Result_getSnippet(JNIEnv* env,
+                                                            jobject obj)
+{
+  return c2jni(RESULT->get_snippet(), env);
+}
+
+JNIEXPORT jstring JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixSearcher_00024Result_getContent(JNIEnv* env,
+                                                            jobject obj)
+{
+  return c2jni(RESULT->get_content(), env);
+}

src/android/kiwixserver.cpp

@@ -0,0 +1,99 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+
+#include <jni.h>
+#include <zim/file.h>
+#include <android/log.h>
+#include "org_kiwix_kiwixlib_JNIKiwixServer.h"
+
+#include "tools/base64.h"
+#include "server.h"
+#include "utils.h"
+
+/* Kiwix Reader JNI functions */
+JNIEXPORT jlong JNICALL Java_org_kiwix_kiwixlib_JNIKiwixServer_getNativeServer(
+    JNIEnv* env, jobject obj, jobject jLibrary)
+{
+  __android_log_print(ANDROID_LOG_INFO, "kiwix", "Attempting to create server");
+  Lock l;
+  try {
+    auto library = Handle<kiwix::Library>::getHandle(env, jLibrary);
+    kiwix::Server* server = new kiwix::Server(*library);
+    return reinterpret_cast<jlong>(new Handle<kiwix::Server>(server));
+  } catch (std::exception& e) {
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", "Error creating the server");
+    __android_log_print(ANDROID_LOG_WARN, "kiwix", e.what());
+    return 0;
+  }
+}
+
+JNIEXPORT void JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixServer_dispose(JNIEnv* env, jobject obj)
+{
+  Handle<kiwix::Server>::dispose(env, obj);
+}
+
+#define SERVER (Handle<kiwix::Server>::getHandle(env, obj))
+
+/* Kiwix library functions */
+JNIEXPORT void JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixServer_setRoot(JNIEnv* env, jobject obj, jstring jRoot)
+{
+  std::string root = jni2c(jRoot, env);
+  SERVER->setRoot(root);
+}
+
+JNIEXPORT void JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixServer_setAddress(JNIEnv* env, jobject obj, jstring jAddress)
+{
+  std::string address = jni2c(jAddress, env);
+  SERVER->setAddress(address);
+}
+
+JNIEXPORT void JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixServer_setPort(JNIEnv* env, jobject obj, int port)
+{
+  SERVER->setPort(port);
+}
+
+JNIEXPORT void JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixServer_setNbThreads(JNIEnv* env, jobject obj, int threads)
+{
+  SERVER->setNbThreads(threads);
+}
+
+JNIEXPORT void JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixServer_setTaskbar(JNIEnv* env, jobject obj, jboolean withTaskbar, jboolean withLibraryButton)
+{
+  SERVER->setTaskbar(withTaskbar, withLibraryButton);
+}
+
+JNIEXPORT jboolean JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixServer_start(JNIEnv* env, jobject obj)
+{
+  return SERVER->start();
+}
+
+JNIEXPORT void JNICALL
+Java_org_kiwix_kiwixlib_JNIKiwixServer_stop(JNIEnv* env, jobject obj)
+{
+  SERVER->stop();
+}

src/android/meson.build

@@ -0,0 +1,32 @@
+
+kiwix_jni = custom_target('jni',
+  input: ['org/kiwix/kiwixlib/JNIICU.java',
+          'org/kiwix/kiwixlib/JNIKiwixReader.java',
+          'org/kiwix/kiwixlib/JNIKiwixLibrary.java',
+          'org/kiwix/kiwixlib/JNIKiwixSearcher.java',
+          'org/kiwix/kiwixlib/JNIKiwixServer.java',
+          'org/kiwix/kiwixlib/JNIKiwixInt.java',
+          'org/kiwix/kiwixlib/JNIKiwixString.java',
+          'org/kiwix/kiwixlib/JNIKiwixBool.java',
+          'org/kiwix/kiwixlib/JNIKiwixException.java',
+          'org/kiwix/kiwixlib/Pair.java'],
+  output: ['org_kiwix_kiwixlib_JNIKiwix.h',
+           'org_kiwix_kiwixlib_JNIKiwixReader.h',
+           'org_kiwix_kiwixlib_JNIKiwixLibrary.h',
+           'org_kiwix_kiwixlib_JNIKiwixServer.h',
+           'org_kiwix_kiwixlib_JNIKiwixSearcher.h',
+           'org_kiwix_kiwixlib_JNIKiwixSearcher_Result.h'],
+  command:['javac', '-d', '@OUTDIR@', '-h', '@OUTDIR@', '@INPUT@']
+)
+
+kiwix_sources += [
+    'android/kiwixicu.cpp',
+    'android/kiwixreader.cpp',
+    'android/kiwixlibrary.cpp',
+    'android/kiwixsearcher.cpp',
+    'android/kiwixserver.cpp',
+    kiwix_jni]
+
+install_subdir('org', install_dir: 'kiwix-lib/java')
+install_subdir('res', install_dir: 'kiwix-lib')
+install_data('AndroidManifest.xml', install_dir: 'kiwix-lib')

src/android/org/kiwix/kiwixlib/JNIICU.java

@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+package org.kiwix.kiwixlib;
+
+public class JNIICU
+{
+  static public native void setDataDirectory(String icuDataDir);
+}

src/android/org/kiwix/kiwixlib/JNIKiwix.java

@@ -0,0 +1,36 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+package org.kiwix.kiwixlib;
+
+import android.content.Context;
+import com.getkeepsafe.relinker.ReLinker;
+import org.kiwix.kiwixlib.JNIICU;
+
+public class JNIKiwix
+{
+  public JNIKiwix(final Context context){
+    ReLinker.loadLibrary(context, "kiwix");
+  }
+
+  public void setDataDirectory(String icuDataDir) {
+    JNIICU.setDataDirectory(icuDataDir);
+  }
+}

src/android/org/kiwix/kiwixlib/JNIKiwixBool.java

@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+package org.kiwix.kiwixlib;
+
+public class JNIKiwixBool
+{
+  public boolean value;
+}

src/android/org/kiwix/kiwixlib/JNIKiwixException.java

@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+package org.kiwix.kiwixlib;
+
+public class JNIKiwixException extends Exception
+{
+  public JNIKiwixException(String message) {
+    super(message);
+  }
+}

src/android/org/kiwix/kiwixlib/JNIKiwixInt.java

@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+package org.kiwix.kiwixlib;
+
+public class JNIKiwixInt
+{
+  public int value;
+}

src/android/org/kiwix/kiwixlib/JNIKiwixLibrary.java

@@ -1,5 +1,6 @@
 /*
- * Copyright 2012 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
  *
  * 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
@@ -17,32 +18,21 @@
  * MA 02110-1301, USA.
  */
 
-#ifndef KIWIX_NETWORKTOOLS_H
-#define KIWIX_NETWORKTOOLS_H
+package org.kiwix.kiwixlib;
 
-#ifdef _WIN32
-#include <winsock2.h>
-#include <ws2tcpip.h>
-#else
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <sys/ioctl.h>
-#include <sys/socket.h>
-#include <sys/types.h>
-#include <net/if.h>
-#include <netdb.h>
-#endif
+import org.kiwix.kiwixlib.JNIKiwixException;
 
-#include <iostream>
-#include <vector>
-#include <string>
-#include <map>
+public class JNIKiwixLibrary
+{
+  public native boolean addBook(String path) throws JNIKiwixException;
 
-namespace kiwix {
-  std::map<std::string, std::string> getNetworkInterfaces();
-  std::string getBestPublicIp();
+  public JNIKiwixLibrary()
+  {
+    nativeHandle = getNativeLibrary();
+  }
+
+  public native void dispose();
+
+  private native long getNativeLibrary();
+  private long nativeHandle;
 }
-
-#endif

src/android/org/kiwix/kiwixlib/JNIKiwixReader.java

@@ -0,0 +1,151 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+package org.kiwix.kiwixlib;
+
+import org.kiwix.kiwixlib.JNIKiwixException;
+import org.kiwix.kiwixlib.JNIKiwixString;
+import org.kiwix.kiwixlib.JNIKiwixInt;
+import org.kiwix.kiwixlib.JNIKiwixSearcher;
+import org.kiwix.kiwixlib.Pair;
+
+public class JNIKiwixReader
+{
+  public native String getMainPage();
+
+  public native String getTitle();
+
+  public native String getId();
+
+  public native String getLanguage();
+
+  public native String getMimeType(String url);
+
+  /**
+   * Check if a url exists and is a redirect or not.
+   *
+   * Return an empty string if the url doesn't exist in the reader.
+   * Return the url of the "final" entry.
+   * - equal to the input url if the entry is not a redirection.
+   * - different if the url is a redirection (and the webview should redirect to it).
+   */
+  public native String checkUrl(String url);
+
+  /**
+   * Get the content of a article.
+   *
+   * Return a byte array of the content of the article.
+   * Set the title, mimeType to the title and mimeType of the article.
+   * Set the size to the size of the returned array.
+   *
+   * If the entry doesn't exist :
+   *  - return a empty byte array
+   *  - set all arguments (except url) to empty/0.
+   * If the entry exist but is a redirection :
+   *  - return an empty byte array
+   *  - set all arguments (including url) to information of the targeted article.
+   */
+  public native byte[] getContent(JNIKiwixString url,
+                                  JNIKiwixString title,
+                                  JNIKiwixString mimeType,
+                                  JNIKiwixInt size);
+
+  /**
+   * getContentPart.
+   *
+   * Get only a part of the content of the article.
+   * Return a byte array of `len` size starting from offset `offset`.
+   * Set `size` to the number of bytes read
+   * (`len` if everything is ok, 0 in case of error).
+   * If `len` == 0, no bytes are read but `size` is set to the total size of the
+   * article.
+   */
+  public native byte[] getContentPart(String url,
+                                      int offest,
+                                      int len,
+                                      JNIKiwixInt size);
+
+  /**
+   * getDirectAccessInformation.
+   *
+   * Return information giving where the content is located in the zim file.
+   *
+   * Some contents (binary content) are stored uncompressed in the zim file.
+   * Knowing this information, it could be interesting to directly open
+   * the zim file (or zim part) and directly read the content from it (and so
+   * bypassing the libzim).
+   *
+   * Return a `Pair` (filename, offset) where the content is located.
+   *
+   * If the content cannot be directly accessed (content is compressed or zim
+   * file is cut in the middle of the content), the filename is an empty string
+   * and offset is zero.
+   */
+  public native Pair getDirectAccessInformation(String url);
+
+  public native boolean searchSuggestions(String prefix, int count);
+
+  public native boolean getNextSuggestion(JNIKiwixString title, JNIKiwixString url);
+
+  public native boolean getPageUrlFromTitle(String title, JNIKiwixString url);
+
+  public native String getDescription();
+
+  public native String getDate();
+
+  public native String getFavicon();
+
+  public native String getCreator();
+
+  public native String getPublisher();
+
+  public native String getName();
+
+  public native int getFileSize();
+
+  public native int getArticleCount();
+
+  public native int getMediaCount();
+
+  public native boolean getRandomPage(JNIKiwixString url);
+
+  public JNIKiwixSearcher search(String query, int count)
+  {
+    JNIKiwixSearcher searcher = new JNIKiwixSearcher();
+    searcher.addKiwixReader(this);
+    searcher.search(query, count);
+    return searcher;
+  }
+
+  public JNIKiwixReader(String filename) throws JNIKiwixException
+  {
+    nativeHandle = getNativeReader(filename);
+    if (nativeHandle == 0) {
+        throw new JNIKiwixException("Cannot open zimfile "+filename);
+    }
+  }
+  public JNIKiwixReader() {
+
+  }
+  public native void dispose();
+
+  private native long getNativeReader(String filename);
+  private long nativeHandle;
+}

src/android/org/kiwix/kiwixlib/JNIKiwixSearcher.java

@@ -0,0 +1,67 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+
+package org.kiwix.kiwixlib;
+
+import org.kiwix.kiwixlib.JNIKiwixReader;
+import java.util.Vector;
+
+public class JNIKiwixSearcher
+{
+  public class Result
+  {
+    private long nativeHandle;
+    private JNIKiwixSearcher searcher;
+    public Result(long handle, JNIKiwixSearcher _searcher)
+    {
+      nativeHandle = handle;
+      searcher = _searcher;
+    }
+    public native String getUrl();
+    public native String getTitle();
+    public native String getContent();
+    public native String getSnippet();
+    public native void dispose();
+  }
+
+  public JNIKiwixSearcher()
+  {
+    nativeHandle = getNativeHandle();
+    usedReaders = new Vector();
+  }
+  public native void dispose();
+
+  private native long getNativeHandle();
+  private long nativeHandle;
+  private Vector usedReaders;
+
+  public native void addReader(JNIKiwixReader reader);
+  public void addKiwixReader(JNIKiwixReader reader)
+  {
+    addReader(reader);
+    usedReaders.addElement(reader);
+  };
+
+  public native void search(String query, int count);
+
+  public native Result getNextResult();
+  public native boolean hasMoreResult();
+}

src/android/org/kiwix/kiwixlib/JNIKiwixServer.java

@@ -0,0 +1,48 @@
+/*
+ * Copyright (C) 2019 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+package org.kiwix.kiwixlib;
+
+import org.kiwix.kiwixlib.JNIKiwixException;
+import org.kiwix.kiwixlib.JNIKiwixLibrary;
+
+public class JNIKiwixServer
+{
+  public native void setRoot(String root);
+
+  public native void setAddress(String address);
+
+  public native void setPort(int port);
+
+  public native void setNbThreads(int nbTreads);
+
+  public native void setTaskbar(boolean withTaskBar, boolean witLibraryButton);
+
+  public native boolean start();
+
+  public native void stop();
+
+  public JNIKiwixServer(JNIKiwixLibrary library)
+  {
+    nativeHandle = getNativeServer(library);
+  }
+
+  private native long getNativeServer(JNIKiwixLibrary library);
+  private long nativeHandle;
+}

src/android/org/kiwix/kiwixlib/JNIKiwixString.java

@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+package org.kiwix.kiwixlib;
+
+public class JNIKiwixString
+{
+  public String value;
+
+  public JNIKiwixString(String value) {
+    this.value = value;
+  }
+
+  public JNIKiwixString() {
+    this("");
+  }
+
+  public String getValue() {
+    return value;
+  }
+}

src/android/org/kiwix/kiwixlib/Pair.java

@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+package org.kiwix.kiwixlib;
+
+public class Pair
+{
+  public String filename;
+  public int offset;
+}

src/android/res/values/strings.xml

@@ -0,0 +1,3 @@
+<resources>
+  <string name="app_name">Kiwix Lib</string>
+</resources>

src/android/utils.h

@@ -0,0 +1,157 @@
+/*
+ * Copyright (C) 2013 Emmanuel Engelhart <kelson@kiwix.org>
+ * Copyright (C) 2017 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+
+#ifndef _ANDROID_JNI_UTILS_H
+#define _ANDROID_JNI_UTILS_H
+
+#include <jni.h>
+
+#include <pthread.h>
+#include <string>
+
+extern pthread_mutex_t globalLock;
+
+inline jfieldID getHandleField(JNIEnv* env, jobject obj)
+{
+  jclass c = env->GetObjectClass(obj);
+  // J is the type signature for long:
+  return env->GetFieldID(c, "nativeHandle", "J");
+}
+
+class Lock
+{
+ protected:
+  pthread_mutex_t* lock;
+
+ public:
+  Lock() : lock(&globalLock) { pthread_mutex_lock(lock); }
+  Lock(const Lock&) = delete;
+  Lock& operator=(const Lock&) = delete;
+  Lock(Lock&& other) : lock(&globalLock) { other.lock = nullptr; }
+  virtual ~Lock()
+  {
+    if (lock) {
+      pthread_mutex_unlock(lock);
+    }
+  }
+};
+
+template <class T>
+class LockedHandle;
+
+template <class T>
+class Handle
+{
+ protected:
+  T* h;
+
+ public:
+  Handle(T* h) : h(h){};
+
+  // No destructor. This must and will be handled by dispose method.
+
+  static LockedHandle<T> getHandle(JNIEnv* env, jobject obj)
+  {
+    jlong handle = env->GetLongField(obj, getHandleField(env, obj));
+    return LockedHandle<T>(reinterpret_cast<Handle<T>*>(handle));
+  }
+
+  static void dispose(JNIEnv* env, jobject obj)
+  {
+    auto lHandle = getHandle(env, obj);
+    auto handle = lHandle.h;
+    delete handle->h;
+    delete handle;
+  }
+  friend class LockedHandle<T>;
+};
+
+template <class T>
+struct LockedHandle : public Lock {
+  Handle<T>* h;
+  LockedHandle(Handle<T>* h) : h(h) {}
+  T* operator->() { return h->h; }
+  T* operator*() { return h->h; }
+  operator bool() const { return (h->h != nullptr); }
+};
+
+/* c2jni type conversion functions */
+inline jboolean c2jni(const bool& val) { return val ? JNI_TRUE : JNI_FALSE; }
+inline jstring c2jni(const std::string& val, JNIEnv* env)
+{
+  return env->NewStringUTF(val.c_str());
+}
+
+inline jint c2jni(const int val) { return (jint)val; }
+inline jint c2jni(const unsigned val) { return (unsigned)val; }
+/* jni2c type conversion functions */
+inline bool jni2c(const jboolean& val) { return val == JNI_TRUE; }
+inline std::string jni2c(const jstring& val, JNIEnv* env)
+{
+  const char* chars = env->GetStringUTFChars(val, 0);
+  std::string ret(chars);
+  env->ReleaseStringUTFChars(val, chars);
+  return ret;
+}
+
+inline int jni2c(const jint val) { return (int)val; }
+/* Method to deal with variable passed by reference */
+inline std::string getStringObjValue(const jobject obj, JNIEnv* env)
+{
+  jclass objClass = env->GetObjectClass(obj);
+  jfieldID objFid = env->GetFieldID(objClass, "value", "Ljava/lang/String;");
+  jstring jstr = (jstring)env->GetObjectField(obj, objFid);
+  return jni2c(jstr, env);
+}
+inline void setStringObjValue(const std::string& value,
+                              const jobject obj,
+                              JNIEnv* env)
+{
+  jclass objClass = env->GetObjectClass(obj);
+  jfieldID objFid = env->GetFieldID(objClass, "value", "Ljava/lang/String;");
+  env->SetObjectField(obj, objFid, c2jni(value, env));
+}
+
+inline void setIntObjValue(const int value, const jobject obj, JNIEnv* env)
+{
+  jclass objClass = env->GetObjectClass(obj);
+  jfieldID objFid = env->GetFieldID(objClass, "value", "I");
+  env->SetIntField(obj, objFid, value);
+}
+
+inline void setBoolObjValue(const bool value, const jobject obj, JNIEnv* env)
+{
+  jclass objClass = env->GetObjectClass(obj);
+  jfieldID objFid = env->GetFieldID(objClass, "value", "Z");
+  env->SetIntField(obj, objFid, c2jni(value));
+}
+
+inline void setPairObjValue(const std::string& filename, const int offset,
+                            const jobject obj, JNIEnv* env)
+{
+  jclass objClass = env->GetObjectClass(obj);
+  jfieldID filenameFid = env->GetFieldID(objClass, "filename", "Ljava/lang/String;");
+  env->SetObjectField(obj, filenameFid, c2jni(filename, env));
+  jfieldID offsetFid = env->GetFieldID(objClass, "offset", "I");
+  env->SetIntField(obj, offsetFid, offset);
+}
+
+#endif // _ANDROID_JNI_UTILS_H

src/aria2.cpp

@@ -0,0 +1,261 @@
+
+
+#include "aria2.h"
+#include "xmlrpc.h"
+#include <iostream>
+#include <sstream>
+#include <thread>
+#include <chrono>
+#include <tools/otherTools.h>
+#include <tools/pathTools.h>
+#include <tools/stringTools.h>
+#include <downloader.h> // For AriaError
+
+#ifdef _WIN32
+# define ARIA2_CMD "aria2c.exe"
+#else
+# define ARIA2_CMD "aria2c"
+# include <unistd.h>
+#endif
+
+
+
+namespace kiwix {
+
+Aria2::Aria2():
+  mp_aria(nullptr),
+  m_port(42042),
+  m_secret("kiwixariarpc"),
+  mp_curl(nullptr),
+  m_lock(PTHREAD_MUTEX_INITIALIZER)
+{
+  m_downloadDir = getDataDirectory();
+  makeDirectory(m_downloadDir);
+  std::vector<const char*> callCmd;
+
+  std::string rpc_port = "--rpc-listen-port=" + to_string(m_port);
+  std::string download_dir = "--dir=" + getDataDirectory();
+  std::string session_file = appendToDirectory(getDataDirectory(), "kiwix.session");
+  std::string session = "--save-session=" + session_file;
+  std::string inputFile = "--input-file=" + session_file;
+//  std::string log_dir = "--log=\"" + logDir + "\"";
+#ifdef _WIN32
+  int pid = GetCurrentProcessId();
+#else
+  pid_t pid = getpid();
+#endif
+  std::string stop_with_pid = "--stop-with-process=" + to_string(pid);
+  std::string rpc_secret = "--rpc-secret=" + m_secret;
+  m_secret = "token:"+m_secret;
+
+  std::string aria2cmd = appendToDirectory(
+    removeLastPathElement(getExecutablePath(true)),
+    ARIA2_CMD);
+  if (fileExists(aria2cmd)) {
+    // A local aria2c exe exists (packaged with kiwix-desktop), use it.
+    callCmd.push_back(aria2cmd.c_str());
+  } else {
+    // Try to use a potential installed aria2c.
+    callCmd.push_back(ARIA2_CMD);
+  }
+  callCmd.push_back("--enable-rpc");
+  callCmd.push_back(rpc_secret.c_str());
+  callCmd.push_back(rpc_port.c_str());
+  callCmd.push_back(download_dir.c_str());
+  if (fileExists(session_file)) {
+    callCmd.push_back(inputFile.c_str());
+  }
+  callCmd.push_back(session.c_str());
+//  callCmd.push_back(log_dir.c_str());
+  callCmd.push_back("--auto-save-interval=10");
+  callCmd.push_back(stop_with_pid.c_str());
+  callCmd.push_back("--allow-overwrite=true");
+  callCmd.push_back("--dht-entry-point=router.bittorrent.com:6881");
+  callCmd.push_back("--dht-entry-point6=router.bittorrent.com:6881");
+  callCmd.push_back("--quiet=true");
+  callCmd.push_back("--bt-enable-lpd=true");
+  callCmd.push_back("--always-resume=true");
+  callCmd.push_back("--max-concurrent-downloads=42");
+  callCmd.push_back("--rpc-max-request-size=6M");
+  callCmd.push_back("--file-allocation=none");
+  for (auto &cmd : callCmd) {
+      m_launchCmd.append(cmd).append(" ");
+  }
+  mp_aria = Subprocess::run(callCmd);
+  mp_curl = curl_easy_init();
+  char errbuf[CURL_ERROR_SIZE];
+  curl_easy_setopt(mp_curl, CURLOPT_URL, "http://localhost/rpc");
+  curl_easy_setopt(mp_curl, CURLOPT_PORT, m_port);
+  curl_easy_setopt(mp_curl, CURLOPT_POST, 1L);
+  curl_easy_setopt(mp_curl, CURLOPT_ERRORBUFFER, errbuf);
+
+  int watchdog = 50;
+  while(--watchdog) {
+    sleep(10);
+    errbuf[0] = 0;
+    auto res = curl_easy_perform(mp_curl);
+    if (res == CURLE_OK) {
+      break;
+    } else if (watchdog == 1) {
+      std::cerr <<" curl_easy_perform() failed." << std::endl;
+      fprintf(stderr, "\nlibcurl: (%d) ", res);
+      if (errbuf[0] != 0) {
+        std::cerr << errbuf << std::endl;
+      } else {
+        std::cerr << curl_easy_strerror(res) << std::endl;
+      }
+    }
+  }
+  if (!watchdog) {
+    curl_easy_cleanup(mp_curl);
+    throw std::runtime_error("Cannot connect to aria2c rpc");
+  }
+}
+
+Aria2::~Aria2()
+{
+  curl_easy_cleanup(mp_curl);
+}
+
+void Aria2::close()
+{
+  saveSession();
+  shutdown();
+}
+
+size_t write_callback_to_iss(char* ptr, size_t size, size_t nmemb, void* userdata)
+{
+  auto str = static_cast<std::stringstream*>(userdata);
+  str->write(ptr, nmemb);
+  return nmemb;
+}
+
+std::string Aria2::doRequest(const MethodCall& methodCall)
+{
+  pthread_mutex_lock(&m_lock);
+  auto requestContent = methodCall.toString();
+  std::stringstream stringstream;
+  CURLcode res;
+  curl_easy_setopt(mp_curl, CURLOPT_POSTFIELDSIZE, requestContent.size());
+  curl_easy_setopt(mp_curl, CURLOPT_POSTFIELDS, requestContent.c_str());
+  curl_easy_setopt(mp_curl, CURLOPT_WRITEFUNCTION, &write_callback_to_iss);
+  curl_easy_setopt(mp_curl, CURLOPT_WRITEDATA, &stringstream);
+  res = curl_easy_perform(mp_curl);
+  if (res == CURLE_OK) {
+    long response_code;
+    curl_easy_getinfo(mp_curl, CURLINFO_RESPONSE_CODE, &response_code);
+    pthread_mutex_unlock(&m_lock);
+    if (response_code != 200) {
+      throw std::runtime_error("Invalid return code from aria");
+    }
+    auto responseContent = stringstream.str();
+    MethodResponse response(responseContent);
+    if (response.isFault()) {
+      throw AriaError(response.getFault().getFaultString());
+    }
+    return responseContent;
+  }
+  pthread_mutex_unlock(&m_lock);
+  throw std::runtime_error("Cannot perform request");
+}
+
+std::string Aria2::addUri(const std::vector<std::string>& uris)
+{
+  MethodCall methodCall("aria2.addUri", m_secret);
+  auto uriParams = methodCall.newParamValue().getArray();
+  for (auto& uri : uris) {
+    uriParams.addValue().set(uri);
+  }
+  auto ret = doRequest(methodCall);
+  MethodResponse response(ret);
+  return response.getParamValue(0).getAsS();
+}
+
+std::string Aria2::tellStatus(const std::string& gid, const std::vector<std::string>& statusKey)
+{
+  MethodCall methodCall("aria2.tellStatus", m_secret);
+  methodCall.newParamValue().set(gid);
+  if (!statusKey.empty()) {
+    auto statusArray = methodCall.newParamValue().getArray();
+    for (auto& key : statusKey) {
+      statusArray.addValue().set(key);
+    }
+  }
+  return doRequest(methodCall);
+}
+
+std::vector<std::string> Aria2::tellActive()
+{
+  MethodCall methodCall("aria2.tellActive", m_secret);
+  auto statusArray = methodCall.newParamValue().getArray();
+  statusArray.addValue().set(std::string("gid"));
+  auto responseContent = doRequest(methodCall);
+  MethodResponse response(responseContent);
+  std::vector<std::string> activeGID;
+  int index = 0;
+  while(true) {
+    try {
+      auto structNode = response.getParamValue(0).getArray().getValue(index++).getStruct();
+      auto gidNode = structNode.getMember("gid");
+      activeGID.push_back(gidNode.getValue().getAsS());
+    } catch (InvalidRPCNode& e) { break; }
+  }
+  return activeGID;
+}
+
+std::vector<std::string> Aria2::tellWaiting()
+{
+  MethodCall methodCall("aria2.tellWaiting", m_secret);
+  methodCall.newParamValue().set(0);
+  methodCall.newParamValue().set(99); // max number of downloads to be returned, don't know how to set this properly assumed that there will not be more than 99 paused downloads.
+  auto statusArray = methodCall.newParamValue().getArray();
+  statusArray.addValue().set(std::string("gid"));
+  auto responseContent = doRequest(methodCall);
+  MethodResponse response(responseContent);
+  std::vector<std::string> waitingGID;
+  int index = 0;
+  while(true) {
+    try {
+      auto structNode = response.getParamValue(0).getArray().getValue(index++).getStruct();
+      auto gidNode = structNode.getMember("gid");
+      waitingGID.push_back(gidNode.getValue().getAsS());
+    } catch (InvalidRPCNode& e) { break; }
+  }
+  return waitingGID;
+}
+
+void Aria2::saveSession()
+{
+  MethodCall methodCall("aria2.saveSession", m_secret);
+  doRequest(methodCall);
+  std::cout << "session saved" << std::endl;
+}
+
+void Aria2::shutdown()
+{
+  MethodCall methodCall("aria2.shutdown", m_secret);
+  doRequest(methodCall);
+}
+
+void Aria2::pause(const std::string& gid)
+{
+    MethodCall methodCall("aria2.pause", m_secret);
+    methodCall.newParamValue().set(gid);
+    doRequest(methodCall);
+}
+
+void Aria2::unpause(const std::string& gid)
+{
+    MethodCall methodCall("aria2.unpause", m_secret);
+    methodCall.newParamValue().set(gid);
+    doRequest(methodCall);
+}
+
+void Aria2::remove(const std::string& gid)
+{
+    MethodCall methodCall("aria2.remove", m_secret);
+    methodCall.newParamValue().set(gid);
+    doRequest(methodCall);
+}
+
+} // end namespace kiwix

src/aria2.h

@@ -0,0 +1,52 @@
+
+
+#ifndef KIWIXLIB_ARIA2_H_
+#define KIWIXLIB_ARIA2_H_
+
+#ifdef _WIN32
+// winsock2.h need to be included before windows.h (included by curl.h)
+# include <winsock2.h>
+#endif
+
+#include "subprocess.h"
+#include "xmlrpc.h"
+
+#include <memory>
+#include <curl/curl.h>
+#include <pthread.h>
+
+namespace kiwix {
+
+class Aria2
+{
+  private:
+    std::unique_ptr<Subprocess> mp_aria;
+    int m_port;
+    std::string m_secret;
+    std::string m_downloadDir;
+    CURL* mp_curl;
+    pthread_mutex_t m_lock;
+    std::string m_launchCmd;
+
+    std::string doRequest(const MethodCall& methodCall);
+
+  public:
+    Aria2();
+    virtual ~Aria2();
+    void close();
+
+    std::string addUri(const std::vector<std::string>& uri);
+    std::string tellStatus(const std::string& gid, const std::vector<std::string>& statusKey);
+    std::vector<std::string> tellActive();
+    std::vector<std::string> tellWaiting();
+    void saveSession();
+    void shutdown();
+    void pause(const std::string& gid);
+    void unpause(const std::string& gid);
+    void remove(const std::string& gid);
+    const std::string &getLaunchCmd() { return m_launchCmd; };
+};
+
+}; //end namespace kiwix
+
+#endif // KIWIXLIB_ARIA2_H_

src/book.cpp

@@ -0,0 +1,200 @@
+/*
+ * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#include "book.h"
+#include "reader.h"
+
+#include "tools/base64.h"
+#include "tools/regexTools.h"
+#include "tools/networkTools.h"
+
+#include <pugixml.hpp>
+
+namespace kiwix
+{
+/* Constructor */
+Book::Book() :
+  m_pathValid(false),
+  m_readOnly(false)
+{
+}
+/* Destructor */
+Book::~Book()
+{
+}
+
+bool Book::update(const kiwix::Book& other)
+{
+  if (m_readOnly)
+    return false;
+
+  m_readOnly = other.m_readOnly;
+
+  if (m_path.empty()) {
+    m_path = other.m_path;
+    m_pathValid = other.m_pathValid;
+  }
+
+  if (m_url.empty()) {
+    m_url = other.m_url;
+  }
+
+  if (m_tags.empty()) {
+    m_tags = other.m_tags;
+  }
+
+  if (m_name.empty()) {
+    m_name = other.m_name;
+  }
+
+  if (m_faviconMimeType.empty()) {
+    m_favicon = other.m_favicon;
+    m_faviconMimeType = other.m_faviconMimeType;
+  }
+  return true;
+}
+
+void Book::update(const kiwix::Reader& reader)
+{
+  m_path = reader.getZimFilePath();
+  m_id = reader.getId();
+  m_description = reader.getDescription();
+  m_language = reader.getLanguage();
+  m_date = reader.getDate();
+  m_creator = reader.getCreator();
+  m_publisher = reader.getPublisher();
+  m_title = reader.getTitle();
+  m_name = reader.getName();
+  m_tags = reader.getTags();
+  m_origId = reader.getOrigId();
+  m_articleCount = reader.getArticleCount();
+  m_mediaCount = reader.getMediaCount();
+  m_size = static_cast<uint64_t>(reader.getFileSize()) << 10;
+  m_pathValid = true;
+
+  reader.getFavicon(m_favicon, m_faviconMimeType);
+}
+
+#define ATTR(name) node.attribute(name).value()
+void Book::updateFromXml(const pugi::xml_node& node, const std::string& baseDir)
+{
+  m_id = ATTR("id");
+  std::string path = ATTR("path");
+  if (isRelativePath(path)) {
+    path = computeAbsolutePath(baseDir, path);
+  }
+  m_path = path;
+  m_title = ATTR("title");
+  m_name = ATTR("name");
+  m_tags = ATTR("tags");
+  m_description = ATTR("description");
+  m_language = ATTR("language");
+  m_date = ATTR("date");
+  m_creator = ATTR("creator");
+  m_publisher = ATTR("publisher");
+  m_url = ATTR("url");
+  m_origId = ATTR("origId");
+  m_articleCount = strtoull(ATTR("articleCount"), 0, 0);
+  m_mediaCount = strtoull(ATTR("mediaCount"), 0, 0);
+  m_size = strtoull(ATTR("size"), 0, 0) << 10;
+  m_favicon = base64_decode(ATTR("favicon"));
+  m_faviconMimeType = ATTR("faviconMimeType");
+  try {
+    m_downloadId = ATTR("downloadId");
+  } catch(...) {}
+}
+#undef ATTR
+
+
+static std::string fromOpdsDate(const std::string& date)
+{
+  //The opds date use the standard <YYYY>-<MM>-<DD>T<HH>:<mm>:<SS>Z
+  //and we want <YYYY>-<MM>-<DD>. That's easy, let's take the first 10 char
+  return date.substr(0, 10);
+}
+
+
+#define VALUE(name) node.child(name).child_value()
+void Book::updateFromOpds(const pugi::xml_node& node, const std::string& urlHost)
+{
+  m_id = VALUE("id");
+  if (!m_id.compare(0, 9, "urn:uuid:")) {
+    m_id.erase(0, 9);
+  }
+  m_title = VALUE("title");
+  m_description = VALUE("description");
+  m_language = VALUE("language");
+  m_date = fromOpdsDate(VALUE("updated"));
+  m_creator = node.child("author").child("name").child_value();
+  m_tags = VALUE("tags");
+  for(auto linkNode = node.child("link"); linkNode;
+           linkNode = linkNode.next_sibling("link")) {
+    std::string rel = linkNode.attribute("rel").value();
+
+    if (rel == "http://opds-spec.org/acquisition/open-access") {
+      m_url = linkNode.attribute("href").value();
+      m_size = strtoull(linkNode.attribute("length").value(), 0, 0);
+    }
+    if (rel == "http://opds-spec.org/image/thumbnail") {
+      m_faviconUrl = urlHost + linkNode.attribute("href").value();
+      m_faviconMimeType = linkNode.attribute("type").value();
+    }
+ }
+
+}
+#undef VALUE
+
+std::string Book::getHumanReadableIdFromPath() const
+{
+  std::string id = m_path;
+  if (!id.empty()) {
+    kiwix::removeAccents(id);
+
+#ifdef _WIN32
+    id = replaceRegex(id, "", "^.*\\\\");
+#else
+    id = replaceRegex(id, "", "^.*/");
+#endif
+
+    id = replaceRegex(id, "", "\\.zim[a-z]*$");
+    id = replaceRegex(id, "_", " ");
+    id = replaceRegex(id, "plus", "\\+");
+  }
+  return id;
+}
+
+void Book::setPath(const std::string& path)
+{
+ m_path = isRelativePath(path)
+   ? computeAbsolutePath(getCurrentDirectory(), path)
+   : path;
+}
+
+const std::string& Book::getFavicon() const {
+  if (m_favicon.empty() && !m_faviconUrl.empty()) {
+    try {
+      m_favicon = download(m_faviconUrl);
+    } catch(...) {
+      std::cerr << "Cannot download favicon from " << m_faviconUrl;
+    }
+  }
+  return m_favicon;
+}
+
+}

src/bookmark.cpp

@@ -0,0 +1,47 @@
+/*
+ * Copyright 2018 Matthieu Gautier <mgautier@kymeria.fr>
+ *
+ * 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
+ * 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, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
+ * MA 02110-1301, USA.
+ */
+
+#include "bookmark.h"
+
+#include <pugixml.hpp>
+
+namespace kiwix
+{
+/* Constructor */
+Bookmark::Bookmark()
+{
+}
+
+/* Destructor */
+Bookmark::~Bookmark()
+{
+}
+
+void Bookmark::updateFromXml(const pugi::xml_node& node)
+{
+  auto bookNode = node.child("book");
+  m_bookId = bookNode.child("id").child_value();
+  m_bookTitle = bookNode.child("title").child_value();
+  m_language = bookNode.child("language").child_value();
+  m_date = bookNode.child("date").child_value();
+  m_title = node.child("title").child_value();
+  m_url = node.child("url").child_value();
+}
+
+}

src/common/base64.h

@@ -1,4 +0,0 @@
-#include <string>
-
-std::string base64_encode(unsigned char const* , unsigned int len);
-std::string base64_decode(std::string const& s);

src/common/componentTools.cpp

@@ -1,84 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "componentTools.h"
-
-const char *nsStringToCString(const nsAString &str) {
-  const char *cStr;
-  nsCString tmpStr;
-
-#ifdef _WIN32
-  LossyCopyUTF16toASCII(str, tmpStr);
-#else
-  CopyUTF16toUTF8(str, tmpStr);
-#endif
-
-  NS_CStringGetData(tmpStr, &cStr);
-
-#ifdef _WIN32
-  return _strdup(cStr);
-#else
-  return strdup(cStr);
-#endif
-}
-
-std::string nsStringToString(const nsEmbedString &str) {
-#ifdef _WIN32
-  PRUnichar *start = (PRUnichar *)str.get();
-  PRUnichar *end = start +  str.Length();
-  wchar_t wca[4096];
-  wchar_t *wstart = wca;
-  wchar_t *wpr = wstart;
-        
-  for(; start < end; ++start)
-    {
-      *wstart = (wchar_t) *start;
-      ++wstart;
-    }
-  *wstart = 0;
-
-  std::string ptr;
-  ptr.resize(4096);
-  size_t size = wcstombs((char*)ptr.data(), wpr, 4096);
-  ptr.resize(size);
-
-  return ptr;
-#else
-  const char *cStr;
-  nsCString tmpStr;
-
-  CopyUTF16toUTF8(str, tmpStr);
-  NS_CStringGetData(tmpStr, &cStr);
-  return std::string(cStr);
-#endif
-
-}
-
-const char *nsStringToUTF8(const nsAString &str) {
-  const char *cStr;
-  nsCString tmpStr;
-  CopyUTF16toUTF8(str, tmpStr);
-  NS_CStringGetData(tmpStr, &cStr);
-
-#ifdef _WIN32
-  return _strdup(cStr);
-#else
-  return strdup(cStr);
-#endif
-}

src/common/kiwix/ctpp2/CTPP2VMStringLoader.cpp

@@ -1,210 +0,0 @@
-/*
- * Copyright 2013 Renaud Gaudin <reg@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "CTPP2VMStringLoader.hpp"
-
-namespace CTPP // C++ Template Engine
-{
-
-//
-// Convert byte order
-//
-static void ConvertExecutable(VMExecutable * oCore)
-{
-	// Code entry point
-	oCore -> entry_point = Swap32(oCore -> entry_point);
-	// Offset of code segment
-	oCore -> code_offset = Swap32(oCore -> code_offset);
-
-	// Code segment size
-	oCore -> code_size   = Swap32(oCore -> code_size);
-
-	// Offset of static text segment
-	oCore -> syscalls_offset    = Swap32(oCore -> syscalls_offset);
-	// Static text segment size
-	oCore -> syscalls_data_size = Swap32(oCore -> syscalls_data_size);
-
-	// Offset of static text index segment
-	oCore -> syscalls_index_offset = Swap32(oCore -> syscalls_index_offset);
-	// Static text index segment size
-	oCore -> syscalls_index_size   = Swap32(oCore -> syscalls_index_size);
-
-	// Offset of static data segment
-	oCore -> static_data_offset    = Swap32(oCore -> static_data_offset);
-
-	// Static data segment size
-	oCore -> static_data_data_size = Swap32(oCore -> static_data_data_size);
-
-	// Offset of static text segment
-	oCore -> static_text_offset    = Swap32(oCore -> static_text_offset);
-	// Static text segment size
-	oCore -> static_text_data_size = Swap32(oCore -> static_text_data_size);
-
-	// Offset of static text index segment
-	oCore -> static_text_index_offset = Swap32(oCore -> static_text_index_offset);
-	// Static text index segment size
-	oCore -> static_text_index_size   = Swap32(oCore -> static_text_index_size);
-
-	// Version 2.2+
-	// Offset of static data bit index
-	oCore -> static_data_bit_index_offset = Swap32(oCore -> static_data_bit_index_offset);
-	/// Offset of static data bit index
-	oCore -> static_data_bit_index_size = Swap32(oCore -> static_data_bit_index_size);
-
-	// Platform
-	oCore -> platform      = Swap64(oCore -> platform);
-
-	// Ugly-jolly hack!
-	// ... dereferencing type-punned pointer will break strict-aliasing rules ...
-	UINT_64 iTMP;
-	memcpy(&iTMP, &(oCore -> ieee754double), sizeof(UINT_64));
-	iTMP = Swap64(iTMP);
-	memcpy(&(oCore -> ieee754double), &iTMP, sizeof(UINT_64));
-
-	// Cyclic Redundancy Check
-	oCore -> crc = 0;
-
-	// Convert data structures
-
-	// Convert code segment
-	VMInstruction * pInstructions = const_cast<VMInstruction *>(VMExecutable::GetCodeSeg(oCore));
-	UINT_32 iI = 0;
-	UINT_32 iSteps = oCore -> code_size / sizeof(VMInstruction);
-	for(iI = 0; iI < iSteps; ++iI)
-	{
-		pInstructions -> instruction = Swap32(pInstructions -> instruction);
-		pInstructions -> argument    = Swap32(pInstructions -> argument);
-		pInstructions -> reserved    = Swap64(pInstructions -> reserved);
-		++pInstructions;
-	}
-
-	// Convert syscalls index
-	TextDataIndex * pTextIndex = const_cast<TextDataIndex *>(VMExecutable::GetSyscallsIndexSeg(oCore));
-	iSteps = oCore -> syscalls_index_size / sizeof(TextDataIndex);
-	for(iI = 0; iI < iSteps; ++iI)
-	{
-		pTextIndex -> offset = Swap32(pTextIndex -> offset);
-		pTextIndex -> length = Swap32(pTextIndex -> length);
-		++pTextIndex;
-	}
-
-	// Convert static text index
-	pTextIndex = const_cast<TextDataIndex *>(VMExecutable::GetStaticTextIndexSeg(oCore));
-	iSteps = oCore -> static_text_index_size / sizeof(TextDataIndex);
-	for(iI = 0; iI < iSteps; ++iI)
-	{
-		pTextIndex -> offset = Swap32(pTextIndex -> offset);
-		pTextIndex -> length = Swap32(pTextIndex -> length);
-		++pTextIndex;
-	}
-
-	// Convert static data
-	StaticDataVar * pStaticDataVar = const_cast<StaticDataVar *>(VMExecutable::GetStaticDataSeg(oCore));
-	iSteps = oCore -> static_data_data_size / sizeof(StaticDataVar);
-	for(iI = 0; iI < iSteps; ++iI)
-	{
-		(*pStaticDataVar).i_data = Swap64((*pStaticDataVar).i_data);
-		++pStaticDataVar;
-	}
-}
-
-//
-// Constructor
-//
-VMStringLoader::VMStringLoader(CCHAR_P rawContent, size_t rawContentSize)
-{
-    oCore = (VMExecutable *)malloc(rawContentSize + 1);
-    memcpy(oCore, rawContent, rawContentSize);
-
-	if (oCore -> magic[0] == 'C' &&
-	    oCore -> magic[1] == 'T' &&
-	    oCore -> magic[2] == 'P' &&
-	    oCore -> magic[3] == 'P')
-	{
-		// Check version
-		if (oCore -> version[0] >= 1)
-		{
-			// Platform-dependent data (byte order)
-			if (oCore -> platform == 0x4142434445464748ull)
-			{
-#ifdef _DEBUG
-				fprintf(stderr, "Big/Little Endian conversion: Nothing to do\n");
-#endif
-
-				// Nothing to do, only check crc
-				UINT_32 iCRC = oCore -> crc;
-				oCore -> crc = 0;
-
-				// Calculate CRC of file
-                // KELSON: next line used to refer to oStat.st_size
-                // changed it to rawContentSize
-				if (iCRC != crc32((UCCHAR_P)oCore, rawContentSize))
-				{
-					free(oCore);
-					throw CTPPLogicError("CRC checksum invalid");
-				}
-			}
-			// Platform-dependent data (byte order)
-			else if (oCore -> platform == 0x4847464544434241ull)
-			{
-				// Need to reconvert data
-#ifdef _DEBUG
-				fprintf(stderr, "Big/Little Endian conversion: Need to reconvert core\n");
-#endif
-				ConvertExecutable(oCore);
-			}
-			else
-			{
-				free(oCore);
-				throw CTPPLogicError("Conversion of middle-end architecture does not supported.");
-			}
-
-			// Check IEEE 754 format
-			if (oCore -> ieee754double != 15839800103804824402926068484019465486336.0)
-			{
-				free(oCore);
-				throw CTPPLogicError("IEEE 754 format is broken, cannot convert file");
-			}
-		}
-
-		pVMMemoryCore = new VMMemoryCore(oCore);
-	}
-	else
-	{
-		free(oCore);
-		throw CTPPLogicError("Not an CTPP bytecode file.");
-	}
-}
-
-//
-// Get ready-to-run program
-//
-const VMMemoryCore * VMStringLoader::GetCore() const { return pVMMemoryCore; }
-
-//
-// A destructor
-//
-VMStringLoader::~VMStringLoader() throw()
-{
-	delete pVMMemoryCore;
-	free(oCore);
-}
-
-} // namespace CTPP
-// End.

src/common/kiwix/ctpp2/CTPP2VMStringLoader.hpp

@@ -1,80 +0,0 @@
-/*
- * Copyright 2013 Renaud Gaudin <reg@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef _CTPP2_VM_STRING_LOADER_HPP__
-#define _CTPP2_VM_STRING_LOADER_HPP__ 1
-
-#include "ctpp2/CTPP2VMLoader.hpp"
-#include "ctpp2/CTPP2Util.hpp"
-#include "ctpp2/CTPP2Exception.hpp"
-#include "ctpp2/CTPP2VMExecutable.hpp"
-#include "ctpp2/CTPP2VMInstruction.hpp"
-#include "ctpp2/CTPP2VMMemoryCore.hpp"
-
-#include <sys/types.h>
-#include <sys/stat.h>
-
-#include <errno.h>
-#include <stdio.h>
-#include <stdlib.h>
-
-#include <resourceTools.h>
-#include <iostream>
-#include <string>
-
-/**
-  @file VMStringLoader.hpp
-  @brief Load program core from file
-*/
-
-namespace CTPP // C++ Template Engine
-{
-// FWD
-struct VMExecutable;
-
-/**
-  @class VMStringLoader CTPP2VMStringLoader.hpp <CTPP2VMStringLoader.hpp>
-  @brief Load program core from file
-*/
-class CTPP2DECL VMStringLoader:
-  public VMLoader
-{
-public:
-	/**
-	*/
-	VMStringLoader(CCHAR_P rawContent, size_t rawContentSize);
-	/**
-	  @brief Get ready-to-run program
-	*/
-	const VMMemoryCore * GetCore() const;
-
-	/**
-	  @brief A destructor
-	*/
-	~VMStringLoader() throw();
-private:
-	/** Program core             */
-	VMExecutable  * oCore;
-	/** Ready-to-run program     */
-	VMMemoryCore  * pVMMemoryCore;
-};
-
-} // namespace CTPP
-#endif // _CTPP2_VM_STRING_LOADER_HPP__
-// End.

src/common/kiwix/indexer.cpp

@@ -1,526 +0,0 @@
-/*
- * Copyright 2011-2014 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "indexer.h"
-
-namespace kiwix {
-
-  /* Count word */
-  unsigned int Indexer::countWords(const string &text) {
-    unsigned int numWords = 1;
-    unsigned int length = text.size();
-
-    for(unsigned int i=0; i<length;) {
-      while(i<length && text[i] != ' ') {
-	i++;
-      }
-      numWords++;
-      i++;
-    }
-
-    return numWords;
-  }
-  
-  /* Constructor */
-  Indexer::Indexer() :
-    keywordsBoostFactor(3),
-    verboseFlag(false) {
-
-    /* Initialize mutex */
-    pthread_mutex_init(&threadIdsMutex, NULL);
-    pthread_mutex_init(&toParseQueueMutex, NULL);
-    pthread_mutex_init(&toIndexQueueMutex, NULL);
-    pthread_mutex_init(&articleExtractorRunningMutex, NULL);
-    pthread_mutex_init(&articleParserRunningMutex, NULL);
-    pthread_mutex_init(&articleIndexerRunningMutex, NULL);
-    pthread_mutex_init(&articleCountMutex, NULL);
-    pthread_mutex_init(&zimPathMutex, NULL);
-    pthread_mutex_init(&zimIdMutex, NULL);
-    pthread_mutex_init(&indexPathMutex, NULL);
-    pthread_mutex_init(&progressionMutex, NULL);
-    pthread_mutex_init(&verboseMutex, NULL);
-  }
-
-  /* Destructor */
-  Indexer::~Indexer() {
-  }
-
-  /* Read the stopwords */
-  void Indexer::readStopWords(const string languageCode) {
-    std::string stopWord;
-    std::istringstream file(getResourceAsString("stopwords/" + languageCode));
-
-    this->stopWords.clear();
-
-    while (getline(file, stopWord, '\n')) {
-      this->stopWords.push_back(stopWord);
-    }
-    
-    if (this->verboseFlag) {
-      std::cout << "Read stop words, lang code:" << languageCode << ", count:" << this->stopWords.size() << std::endl;
-    }
-  }
-  
-#pragma mark - Extractor
-  
-  /* Article extractor methods */
-  void *Indexer::extractArticles(void *ptr) {
-    pthread_setcanceltype(PTHREAD_CANCEL_DEFERRED, NULL);
-    kiwix::Indexer *self = (kiwix::Indexer *)ptr;
-
-    /* Get the number of article to index and the ZIM id */
-    kiwix::Reader reader(self->getZimPath());
-    unsigned int articleCount = reader.getArticleCount();
-    self->setArticleCount(articleCount);
-    string zimId = reader.getId();
-    self->setZimId(zimId);
-
-    /* Progression */
-    unsigned int readArticleCount = 0;
-    unsigned int currentProgression = 0;
-    self->setProgression(currentProgression);
-    unsigned int newProgress;
-
-    /* StopWords */
-    self->readStopWords(reader.getLanguage());
-
-    /* Goes trough all articles */
-    zim::File *zimHandler = reader.getZimFileHandler();
-    unsigned int currentOffset = zimHandler->getNamespaceBeginOffset('A');
-    unsigned int lastOffset = zimHandler->getNamespaceEndOffset('A');
-    zim::Article currentArticle;
-
-    while (currentOffset < lastOffset) {
-      currentArticle = zimHandler->getArticle(currentOffset);
-      
-      if (!currentArticle.isRedirect()) {
-        /* Add articles to the queue */
-        indexerToken token;
-        token.title = currentArticle.getTitle();
-        token.url = currentArticle.getLongUrl();
-        token.content = string(currentArticle.getData().data(), currentArticle.getData().size());
-        self->pushToParseQueue(token);
-        readArticleCount += 1;
-        
-        /* Update progress */
-        if (self->progressCallback) {
-            self->progressCallback(readArticleCount, articleCount);
-        }
-        newProgress = (unsigned int)((float)readArticleCount / (float)articleCount * 100);
-        if (newProgress != currentProgression) {
-          self->setProgression(newProgress);
-        }
-      }
-        
-      currentOffset += 1;
-
-      /* Test if the thread should be cancelled */
-      pthread_testcancel();
-    } 
-
-    self->articleExtractorRunning(false);
-    pthread_exit(NULL);
-    return NULL;
-  }
-  
-  void Indexer::articleExtractorRunning(bool value) {
-    pthread_mutex_lock(&articleExtractorRunningMutex);
-    this->articleExtractorRunningFlag = value;
-    pthread_mutex_unlock(&articleExtractorRunningMutex); 
-  }
-  
-  bool Indexer::isArticleExtractorRunning() {
-    pthread_mutex_lock(&articleExtractorRunningMutex);
-    bool retVal = this->articleExtractorRunningFlag;
-    pthread_mutex_unlock(&articleExtractorRunningMutex); 
-    return retVal;
-  }
-  
-#pragma mark - Parser
-  
-  /* Article parser methods */
-  void *Indexer::parseArticles(void *ptr) {
-    pthread_setcanceltype(PTHREAD_CANCEL_DEFERRED, NULL);
-    kiwix::Indexer *self = (kiwix::Indexer *)ptr;
-    size_t found;
-    indexerToken token;
-
-    while (self->popFromToParseQueue(token)) {
-      MyHtmlParser htmlParser;
-
-      /* The parser generate a lot of exceptions which should be avoided */
-      try {
-	htmlParser.parse_html(token.content, "UTF-8", true);
-      } catch (...) {
-      }
-
-      /* If content does not have the noindex meta tag */
-      /* Seems that the parser generates an exception in such case */
-      found = htmlParser.dump.find("NOINDEX");
-      
-      if (found == string::npos) {
-	/* Get the accented title */
-	token.accentedTitle = (htmlParser.title.empty() ? token.title : htmlParser.title);
-
-	/* count words */
-	stringstream countWordStringStream;
-	countWordStringStream << self->countWords(htmlParser.dump);
-	token.wordCount = countWordStringStream.str();
-	
-	/* snippet */
-	std::string snippet = std::string(htmlParser.dump, 0, 300);
-	std::string::size_type last = snippet.find_last_of('.');
-	if (last == snippet.npos)
-	  last = snippet.find_last_of(' ');
-	if (last != snippet.npos)
-	  snippet = snippet.substr(0, last);
-	token.snippet = snippet;
-
-	/* size */
-	stringstream sizeStringStream;
-	sizeStringStream << token.content.size() / 1024;
-	token.size = sizeStringStream.str();
-
-	/* Remove accent */
-	token.title = kiwix::removeAccents(token.accentedTitle);
-	token.keywords = kiwix::removeAccents(htmlParser.keywords);
-	token.content = kiwix::removeAccents(htmlParser.dump);
-	self->pushToIndexQueue(token);
-      }
-
-      /* Test if the thread should be cancelled */
-      pthread_testcancel(); 
-    }
-    
-    self->articleParserRunning(false);
-    pthread_exit(NULL);
-    return NULL;
-  }
-
-  void Indexer::articleParserRunning(bool value) {
-    pthread_mutex_lock(&articleParserRunningMutex);
-    this->articleParserRunningFlag = value;
-    pthread_mutex_unlock(&articleParserRunningMutex); 
-  }
-  
-  bool Indexer::isArticleParserRunning() {
-    pthread_mutex_lock(&articleParserRunningMutex);
-    bool retVal = this->articleParserRunningFlag;
-    pthread_mutex_unlock(&articleParserRunningMutex); 
-    return retVal;
-  }
-  
-#pragma mark - Indexer
-
-  /* Article indexer methods */
-  void *Indexer::indexArticles(void *ptr) {
-    pthread_setcanceltype(PTHREAD_CANCEL_DEFERRED, NULL);
-    kiwix::Indexer *self = (kiwix::Indexer *)ptr;
-    unsigned int indexedArticleCount = 0;
-    indexerToken token;
-
-    self->indexingPrelude(self->getIndexPath()); 
-
-    while (self->popFromToIndexQueue(token)) {
-      self->index(token.url, 
-		  token.accentedTitle,
-		  token.title, 
-		  token.keywords,
-		  token.content,
-		  token.snippet,
-		  token.size,
-		  token.wordCount
-		  );
-
-      indexedArticleCount += 1;
-
-      /* Make a hard-disk flush every 10.000 articles */
-      if (indexedArticleCount % 5000 == 0) {
-	self->flush();
-      }
-
-      /* Test if the thread should be cancelled */
-      pthread_testcancel();
-    }
-    self->indexingPostlude(self->getIndexPath());
-
-    /* Write content id file */
-    string path = appendToDirectory(self->getIndexPath(), "content.id");
-    writeTextFile(path, self->getZimId());
-
-    self->setProgression(100);
-    kiwix::sleep(100);
-
-    self->articleIndexerRunning(false);
-    pthread_exit(NULL);
-    return NULL;
-  }
-
-  void Indexer::articleIndexerRunning(bool value) {
-    pthread_mutex_lock(&articleIndexerRunningMutex);
-    this->articleIndexerRunningFlag = value;
-    pthread_mutex_unlock(&articleIndexerRunningMutex); 
-  }
-  
-  bool Indexer::isArticleIndexerRunning() {
-    pthread_mutex_lock(&articleIndexerRunningMutex);
-    bool retVal = this->articleIndexerRunningFlag;
-    pthread_mutex_unlock(&articleIndexerRunningMutex); 
-    return retVal;
-  }
-  
-#pragma mark - Parse Queue
-
-  /* ToParseQueue methods */
-  bool Indexer::isToParseQueueEmpty() {
-    pthread_mutex_lock(&toParseQueueMutex);
-    bool retVal = this->toParseQueue.empty();
-    pthread_mutex_unlock(&toParseQueueMutex);
-    return retVal;
-  }
-
-  void Indexer::pushToParseQueue(indexerToken &token) {
-    pthread_mutex_lock(&toParseQueueMutex); 
-    this->toParseQueue.push(token);
-    pthread_mutex_unlock(&toParseQueueMutex); 
-    kiwix::sleep(int(this->toParseQueue.size() / 200) / 10 * 1000);
-  }
-
-  bool Indexer::popFromToParseQueue(indexerToken &token) {
-    while (this->isToParseQueueEmpty() && this->isArticleExtractorRunning()) {
-      kiwix::sleep(500);
-      if (this->getVerboseFlag()) {
-	std::cout << "Waiting... ToParseQueue is empty for now..." << std::endl;
-      }
-
-      pthread_testcancel();
-    }
-
-    if (!this->isToParseQueueEmpty()) {
-      pthread_mutex_lock(&toParseQueueMutex); 
-      token = this->toParseQueue.front();
-      this->toParseQueue.pop();
-      pthread_mutex_unlock(&toParseQueueMutex); 
-    } else {
-      return false;
-    }
-
-    return true;
-  }
-  
-#pragma mark - Index Queue
-
-  /* ToIndexQueue methods */
-  bool Indexer::isToIndexQueueEmpty() {
-    pthread_mutex_lock(&toIndexQueueMutex);
-    bool retVal = this->toIndexQueue.empty();
-    pthread_mutex_unlock(&toIndexQueueMutex);
-    return retVal;
-  }
-
-  void Indexer::pushToIndexQueue(indexerToken &token) {
-    pthread_mutex_lock(&toIndexQueueMutex); 
-    this->toIndexQueue.push(token);
-    pthread_mutex_unlock(&toIndexQueueMutex);
-    kiwix::sleep(int(this->toIndexQueue.size() / 200) / 10 * 1000);
-  }
-
-  bool Indexer::popFromToIndexQueue(indexerToken &token) {
-    while (this->isToIndexQueueEmpty() && this->isArticleParserRunning()) {
-      kiwix::sleep(500);
-      if (this->getVerboseFlag()) {
-	std::cout << "Waiting... ToIndexQueue is empty for now..." << std::endl;
-      }
-
-      pthread_testcancel();
-    }
-
-    if (!this->isToIndexQueueEmpty()) {
-      pthread_mutex_lock(&toIndexQueueMutex); 
-      token = this->toIndexQueue.front();
-      this->toIndexQueue.pop();
-      pthread_mutex_unlock(&toIndexQueueMutex); 
-    } else {
-      return false;
-    }
-
-    return true;
-  }
-  
-#pragma mark - Properties Getter & Setter
-
-  /* ZIM & Index methods */
-  void Indexer::setZimPath(const string path) {
-    pthread_mutex_lock(&zimPathMutex);
-    this->zimPath = path;
-    pthread_mutex_unlock(&zimPathMutex); 
-  }
-
-  string Indexer::getZimPath() {
-    pthread_mutex_lock(&zimPathMutex); 
-    string retVal = this->zimPath;
-    pthread_mutex_unlock(&zimPathMutex);
-    return retVal;
-  }
-
-  void Indexer::setIndexPath(const string path) {
-    pthread_mutex_lock(&indexPathMutex); 
-    this->indexPath = path;
-    pthread_mutex_unlock(&indexPathMutex); 
-  }
-
-  string Indexer::getIndexPath() {
-    pthread_mutex_lock(&indexPathMutex); 
-    string retVal = this->indexPath;
-    pthread_mutex_unlock(&indexPathMutex);
-    return retVal;
-  }
-
-  void Indexer::setArticleCount(const unsigned int articleCount) {
-    pthread_mutex_lock(&articleCountMutex);
-    this->articleCount = articleCount;
-    pthread_mutex_unlock(&articleCountMutex); 
-  }
-
-  unsigned int Indexer::getArticleCount() {
-    pthread_mutex_lock(&articleCountMutex);
-    unsigned int retVal = this->articleCount;
-    pthread_mutex_unlock(&articleCountMutex);
-    return retVal;
-  }
-
-  void Indexer::setProgression(const unsigned int progression) {
-    pthread_mutex_lock(&progressionMutex); 
-    this->progression = progression;
-    pthread_mutex_unlock(&progressionMutex); 
-  }
-
-  unsigned int Indexer::getProgression() {
-    pthread_mutex_lock(&progressionMutex); 
-    unsigned int retVal = this->progression;
-    pthread_mutex_unlock(&progressionMutex); 
-    return retVal;
-  }
-
-  void Indexer::setZimId(const string id) {
-    pthread_mutex_lock(&zimIdMutex);
-    this->zimId = id;
-    pthread_mutex_unlock(&zimIdMutex); 
-  }
-
-  string Indexer::getZimId() {
-    pthread_mutex_lock(&zimIdMutex); 
-    string retVal = this->zimId;
-    pthread_mutex_unlock(&zimIdMutex);
-    return retVal;
-  }
-  
-#pragma mark - Status Management
-
-  /* Manage */
-  bool Indexer::start(const string zimPath, const string indexPath, ProgressCallback callback) {
-    if (this->getVerboseFlag()) {
-      std::cout << "Indexing of '" << zimPath << "' starting..." <<std::endl;
-    }
-    
-    if (callback) {
-        this->progressCallback = callback;
-    }
-
-    this->setArticleCount(0);
-    this->setProgression(0);
-    this->setZimPath(zimPath);
-    this->setIndexPath(indexPath);
-
-    pthread_mutex_lock(&threadIdsMutex); 
-    this->articleExtractorRunning(true);
-    pthread_create(&(this->articleExtractor), NULL, Indexer::extractArticles, (void*)this);
-    pthread_detach(this->articleExtractor);
-
-    while(this->isArticleExtractorRunning() && this->getArticleCount() == 0) {
-      kiwix::sleep(100);
-    }
-    
-    this->articleParserRunning(true);
-    pthread_create(&(this->articleParser), NULL, Indexer::parseArticles, (void*)this);
-    pthread_detach(this->articleParser);
-
-    this->articleIndexerRunning(true);
-    pthread_create(&(this->articleIndexer), NULL, Indexer::indexArticles, (void*)this);
-    pthread_detach(this->articleIndexer);
-    pthread_mutex_unlock(&threadIdsMutex);
-
-    return true;
-  }
-
-  bool Indexer::isRunning() {
-      if (this->getVerboseFlag()) {
-	std::cout << "isArticleExtractor running: " << (this->isArticleExtractorRunning() ? "yes" : "no") << std::endl;
-	std::cout << "isArticleParser running: " << (this->isArticleParserRunning() ? "yes" : "no") << std::endl;
-	std::cout << "isArticleIndexer running: " << (this->isArticleIndexerRunning() ? "yes" : "no") << std::endl;
-      }
-
-    return this->isArticleExtractorRunning() || this->isArticleIndexerRunning() || this->isArticleParserRunning();
-  }
-
-  bool Indexer::stop() {
-    if (this->isRunning()) {
-      bool isArticleExtractorRunning = this->isArticleExtractorRunning();
-      bool isArticleIndexerRunning = this->isArticleIndexerRunning();
-      bool isArticleParserRunning = this->isArticleParserRunning();
-      
-      pthread_mutex_lock(&threadIdsMutex); 
-      
-      if (isArticleIndexerRunning) {
-	pthread_cancel(this->articleIndexer);
-	this->articleIndexerRunning(false);
-      }
-      if (isArticleParserRunning) {
-	pthread_cancel(this->articleParser);
-	this->articleParserRunning(false);
-      }
-      if (isArticleExtractorRunning) {
-	pthread_cancel(this->articleExtractor);
-	this->articleExtractorRunning(false);
-      }
-
-      pthread_mutex_unlock(&threadIdsMutex); 
-    }
-
-    return true;
-  }
-  
-#pragma mark - verbose
-
-  /* Manage the verboseFlag */
-  void Indexer::setVerboseFlag(const bool value) {
-    pthread_mutex_lock(&verboseMutex);
-    this->verboseFlag = value;
-    pthread_mutex_unlock(&verboseMutex);
-  }
-
-  bool Indexer::getVerboseFlag() {
-    bool value;
-    pthread_mutex_lock(&verboseMutex);
-    value = this->verboseFlag;
-    pthread_mutex_unlock(&verboseMutex);
-    return value;
-  }
-
-}

src/common/kiwix/indexer.h

@@ -1,175 +0,0 @@
-/*
- * Copyright 2014 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_INDEXER_H
-#define KIWIX_INDEXER_H
-
-#include <string>
-#include <vector>
-#include <stack>
-#include <queue>
-#include <fstream>
-#include <iostream>
-#include <sstream>
-
-#include <pthread.h>
-#include <stringTools.h>
-#include <otherTools.h>
-#include <resourceTools.h>
-#include <zim/file.h>
-#include <zim/article.h>
-#include <zim/fileiterator.h>
-#include "reader.h"
-#include "xapian/myhtmlparse.h"
-
-using namespace std;
-
-namespace kiwix {
-
-  struct indexerToken {
-    string url;
-    string accentedTitle;
-    string title;
-    string keywords;
-    string content;
-    string snippet;
-    string size;
-    string wordCount;
-  };
-  
-  class Indexer {
-      
-  typedef void (* ProgressCallback)(const unsigned int processedArticleCount, const unsigned int totalArticleCount);
-      
-  public:
-    Indexer();
-    virtual ~Indexer();
-
-    bool start(const string zimPath, const string indexPath, ProgressCallback callback = NULL);
-    bool stop();
-    bool isRunning();
-    unsigned int getProgression();
-    void setVerboseFlag(const bool value);
-
-  protected:
-    virtual void indexingPrelude(const string indexPath) = 0;
-    virtual void index(const string &url, 
-		       const string &title, 
-		       const string &unaccentedTitle,
-		       const string &keywords, 
-		       const string &content,
-		       const string &snippet,
-		       const string &size,
-		       const string &wordCount) = 0;
-    virtual void flush() = 0;
-    virtual void indexingPostlude(const string indexPath) = 0;
-
-    /* Stop words */
-    std::vector<std::string> stopWords;
-    void readStopWords(const string languageCode);
-
-    /* Others */
-    unsigned int countWords(const string &text);
-
-    /* Boost factor */
-    unsigned int keywordsBoostFactor;
-    inline unsigned int getTitleBoostFactor(const unsigned int contentLength) {
-      return contentLength / 500 + 1;
-    }
-
-    /* Verbose */
-    pthread_mutex_t verboseMutex;
-    bool getVerboseFlag();
-    bool verboseFlag;
-
-  private:
-    ProgressCallback progressCallback;
-    pthread_mutex_t threadIdsMutex;
-
-    /* Article extraction */
-    pthread_t articleExtractor;
-    pthread_mutex_t articleExtractorRunningMutex;
-    static void *extractArticles(void *ptr);
-    bool articleExtractorRunningFlag;
-    bool isArticleExtractorRunning();
-    void articleExtractorRunning(bool value);
-
-    /* Article parsing */
-    pthread_t articleParser;
-    pthread_mutex_t articleParserRunningMutex;
-    static void *parseArticles(void *ptr);
-    bool articleParserRunningFlag;
-    bool isArticleParserRunning();
-    void articleParserRunning(bool value);
-
-    /* Index writting */
-    pthread_t articleIndexer;
-    pthread_mutex_t articleIndexerRunningMutex;
-    static void *indexArticles(void *ptr);
-    bool articleIndexerRunningFlag;
-    bool isArticleIndexerRunning();
-    void articleIndexerRunning(bool value);
-
-    /* To parse queue */
-    std::queue<indexerToken> toParseQueue;
-    pthread_mutex_t toParseQueueMutex;
-    void pushToParseQueue(indexerToken &token);
-    bool popFromToParseQueue(indexerToken &token);
-    bool isToParseQueueEmpty();
-
-    /* To index queue */
-    std::queue<indexerToken> toIndexQueue;
-    pthread_mutex_t toIndexQueueMutex;
-    void pushToIndexQueue(indexerToken &token);
-    bool popFromToIndexQueue(indexerToken &token);
-    bool isToIndexQueueEmpty();
-
-    /* Article Count & Progression */
-    unsigned int articleCount;
-    pthread_mutex_t articleCountMutex;
-    void setArticleCount(const unsigned int articleCount);
-    unsigned int getArticleCount();
-
-    /* Progression */
-    unsigned int progression;
-    pthread_mutex_t progressionMutex;
-    void setProgression(const unsigned int progression);
-    /* getProgression() is public */
-
-    /* ZIM path */
-    pthread_mutex_t zimPathMutex;
-    string zimPath;
-    void setZimPath(const string path);
-    string getZimPath();
-
-    /* Index path */
-    pthread_mutex_t indexPathMutex;
-    string indexPath;
-    void setIndexPath(const string path);
-    string getIndexPath();
-
-    /* ZIM id */
-    pthread_mutex_t zimIdMutex;
-    string zimId;
-    void setZimId(const string id);
-    string getZimId();
-  };
-}
-
-#endif

src/common/kiwix/library.cpp

@@ -1,143 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "library.h"
-
-namespace kiwix {
-
-  /* Constructor */
-  Book::Book():
-    readOnly(false) {
-  }
-  
-  /* Destructor */
-  Book::~Book() {
-  }
-
-  /* Sort functions */
-  bool Book::sortByLastOpen(const kiwix::Book &a, const kiwix::Book &b) {
-    return atoi(a.last.c_str()) > atoi(b.last.c_str());
-  }
-
-  bool Book::sortByTitle(const kiwix::Book &a, const kiwix::Book &b) {
-    return strcmp(a.title.c_str(), b.title.c_str()) < 0;
-  }
-
-  bool Book::sortByDate(const kiwix::Book &a, const kiwix::Book &b) {
-    return strcmp(a.date.c_str(), b.date.c_str()) > 0;
-  }
-
-  bool Book::sortBySize(const kiwix::Book &a, const kiwix::Book &b) {
-    return atoi(a.size.c_str()) < atoi(b.size.c_str());
-  }
-
-  bool Book::sortByPublisher(const kiwix::Book &a, const kiwix::Book &b) {
-    return strcmp(a.publisher.c_str(), b.publisher.c_str()) < 0;
-  }
-
-  bool Book::sortByCreator(const kiwix::Book &a, const kiwix::Book &b) {
-    return strcmp(a.creator.c_str(), b.creator.c_str()) < 0;
-  }
-
-  bool Book::sortByLanguage(const kiwix::Book &a, const kiwix::Book &b) {
-    return strcmp(a.language.c_str(), b.language.c_str()) < 0;
-  }
-
-  std::string Book::getHumanReadableIdFromPath() {
-    std::string id = pathAbsolute;
-    if (!id.empty()) {
-      kiwix::removeAccents(id);
-
-#ifdef _WIN32
-      id = replaceRegex(id, "", "^.*\\\\");
-#else
-      id = replaceRegex(id, "", "^.*/");
-#endif
-
-      id = replaceRegex(id, "", "\\.zim[a-z]*$");
-      id = replaceRegex(id, "_", " ");
-      id = replaceRegex(id, "plus", "\\+");
-    }
-    return id;
-  }
-
-  /* Constructor */
-  Library::Library():
-    version(KIWIX_LIBRARY_VERSION) {
-  }
-  
-  /* Destructor */
-  Library::~Library() {
-  }
-
-  bool Library::addBook(const Book &book) {
-
-    /* Try to find it */
-    std::vector<kiwix::Book>::iterator itr;
-    for ( itr = this->books.begin(); itr != this->books.end(); ++itr ) {
-      if (itr->id == book.id) {
-	if (!itr->readOnly) {
-	  itr->readOnly = book.readOnly;
-	  
-	  if (itr->path.empty())
-	    itr->path = book.path;
-	  
-	  if (itr->pathAbsolute.empty()) 
-	    itr->pathAbsolute = book.pathAbsolute;
-	  
-	  if (itr->url.empty())
-	    itr->url = book.url;
-
-	  if (itr->tags.empty())
-	    itr->tags = book.tags;
-
-	  if (itr->name.empty())
-	    itr->name = book.name;
-	  
-	  if (itr->indexPath.empty()) {
-	    itr->indexPath = book.indexPath;
-	    itr->indexType = book.indexType;
-	  }
-	  
-	  if (itr->indexPathAbsolute.empty()) {
-	    itr->indexPathAbsolute = book.indexPathAbsolute;
-	    itr->indexType = book.indexType;
-	  }
-	  
-	  if (itr->faviconMimeType.empty()) {
-	    itr->favicon = book.favicon;
-	    itr->faviconMimeType = book.faviconMimeType;
-	  }
-	}
-
-	return false;
-      }
-    }
-
-    /* otherwise */
-    this->books.push_back(book);
-    return true;
-  }
-
-  bool Library::removeBookByIndex(const unsigned int bookIndex) {
-    books.erase(books.begin()+bookIndex);
-    return true;
-  }
-
-}

src/common/kiwix/library.h

@@ -1,107 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_LIBRARY_H
-#define KIWIX_LIBRARY_H
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string>
-#include <string.h>
-#include <vector>
-#include <stack>
-
-#include <stringTools.h>
-#include <regexTools.h>
-
-#define KIWIX_LIBRARY_VERSION "20110515"
-
-using namespace std;
-
-namespace kiwix {
-
-  enum supportedIndexType { UNKNOWN, XAPIAN };
-
-  class Book {
-
-  public:
-    Book();
-    ~Book();
-
-    static bool sortByLastOpen(const Book &a, const Book &b);
-    static bool sortByTitle(const Book &a, const Book &b);
-    static bool sortBySize(const Book &a, const Book &b);
-    static bool sortByDate(const Book &a, const Book &b);
-    static bool sortByCreator(const Book &a, const Book &b);
-    static bool sortByPublisher(const Book &a, const Book &b);
-    static bool sortByLanguage(const Book &a, const Book &b);
-    string getHumanReadableIdFromPath();
-
-    string id;
-    string path;
-    string pathAbsolute;
-    string last;
-    string indexPath;
-    string indexPathAbsolute;
-    supportedIndexType indexType;
-    string title;
-    string description;
-    string language;
-    string creator;
-    string publisher;
-    string date;
-    string url;
-    string name;
-    string tags;
-    string origId;
-    string articleCount;
-    string mediaCount;
-    bool readOnly;
-    string size;
-    string favicon;
-    string faviconMimeType;
-  };
-
-  class Library {
-
-  public:
-    Library();
-    ~Library();
-
-    string version;
-    bool addBook(const Book &book);
-    bool removeBookByIndex(const unsigned int bookIndex);
-    vector <kiwix::Book> books;
-
-    /*
-     * 'current' is the variable storing the current content/book id
-     * in the library. This is used to be able to load per default a
-     * content. As Kiwix may work with many library XML files, you may
-     * have "current" defined many time with different values. The
-     * last XML file read has the priority, Although we do not have an
-     * library object for each file, we want to be able to fallback to
-     * an 'old' current book if the one which should be load
-     * failed. That is the reason why we need a stack here
-     */
-    stack<string> current;
-  };
-
-}
-
-#endif

src/common/kiwix/manager.cpp

@@ -1,562 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "manager.h"
-
-namespace kiwix {
-
-  /* Constructor */
-  Manager::Manager() :
-    writableLibraryPath("") {
-  }
-
-  /* Destructor */
-  Manager::~Manager() {
-  }
-
-  bool Manager::parseXmlDom(const pugi::xml_document &doc, const bool readOnly, const string libraryPath) {
-    pugi::xml_node libraryNode = doc.child("library");
-
-    if (strlen(libraryNode.attribute("current").value()))
-      this->setCurrentBookId(libraryNode.attribute("current").value());
-
-    string libraryVersion = libraryNode.attribute("version").value();
-
-    for (pugi::xml_node bookNode = libraryNode.child("book"); bookNode; bookNode = bookNode.next_sibling("book")) {
-      bool ok = true;
-      kiwix::Book book;
-
-      book.readOnly = readOnly;
-      book.id = bookNode.attribute("id").value();
-      book.path = bookNode.attribute("path").value();
-      book.last = (std::string(bookNode.attribute("last").value()) != "undefined" ?
-		   bookNode.attribute("last").value() : "");
-      book.indexPath = bookNode.attribute("indexPath").value();
-      book.indexType = XAPIAN;
-      book.title = bookNode.attribute("title").value();
-      book.name = bookNode.attribute("name").value();
-      book.tags = bookNode.attribute("tags").value();
-      book.description = bookNode.attribute("description").value();
-      book.language = bookNode.attribute("language").value();
-      book.date = bookNode.attribute("date").value();
-      book.creator = bookNode.attribute("creator").value();
-      book.publisher = bookNode.attribute("publisher").value();
-      book.url = bookNode.attribute("url").value();
-      book.origId = bookNode.attribute("origId").value();
-      book.articleCount = bookNode.attribute("articleCount").value();
-      book.mediaCount = bookNode.attribute("mediaCount").value();
-      book.size = bookNode.attribute("size").value();
-      book.favicon = bookNode.attribute("favicon").value();
-      book.faviconMimeType = bookNode.attribute("faviconMimeType").value();
-
-      /* Check absolute and relative paths */
-      this->checkAndCleanBookPaths(book, libraryPath);
-
-      /* Update the book properties with the new importer */
-      if (libraryVersion.empty() || atoi(libraryVersion.c_str()) <= atoi(KIWIX_LIBRARY_VERSION)) {
-	if (!book.path.empty()) {
-	  ok = this->readBookFromPath(book.pathAbsolute);
-	}
-      }
-
-      if (ok) {
-	library.addBook(book);
-      }
-    }
-
-    return true;
-  }
-
-  bool Manager::readXml(const string xml, const bool readOnly, const string libraryPath) {
-    pugi::xml_document doc;
-    pugi::xml_parse_result result = doc.load_buffer_inplace((void*)xml.data(), xml.size());
-
-    if (result) {
-      this->parseXmlDom(doc, readOnly, libraryPath);
-    }
-
-    return true;
-  }
-
-  bool Manager::readFile(const string path, const bool readOnly) {
-    return this->readFile(path, path, readOnly);
-  }
-
-  bool Manager::readFile(const string nativePath, const string UTF8Path, const bool readOnly) {
-    bool retVal = true;
-    pugi::xml_document doc;
-    pugi::xml_parse_result result = doc.load_file(nativePath.c_str());
-
-    if (result) {
-      this->parseXmlDom(doc, readOnly, UTF8Path);
-    } else {
-      retVal = false;
-    }
-
-    /* This has to be set (although if the file does not exists) to be
-     * able to know where to save the library if new content are
-     * available */
-    if (!readOnly) {
-      this->writableLibraryPath = UTF8Path;
-    }
-
-    return retVal;
-  }
-
-  bool Manager::writeFile(const string path) {
-    pugi::xml_document doc;
-
-    /* Add the library node */
-    pugi::xml_node libraryNode = doc.append_child("library");
-
-    if (!getCurrentBookId().empty()) {
-      libraryNode.append_attribute("current") = getCurrentBookId().c_str();
-    }
-
-    if (!library.version.empty())
-      libraryNode.append_attribute("version") = library.version.c_str();
-
-    /* Add each book */
-    std::vector<kiwix::Book>::iterator itr;
-    for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-
-      if (!itr->readOnly) {
-	this->checkAndCleanBookPaths(*itr, path);
-
-	pugi::xml_node bookNode = libraryNode.append_child("book");
-	bookNode.append_attribute("id") = itr->id.c_str();
-
-	if (!itr->path.empty())
-	  bookNode.append_attribute("path") = itr->path.c_str();
-
-	if (!itr->last.empty() && itr->last != "undefined") {
-	  bookNode.append_attribute("last") = itr->last.c_str();
-	}
-
-	if (!itr->indexPath.empty())
-	  bookNode.append_attribute("indexPath") = itr->indexPath.c_str();
-
-	if (!itr->indexPath.empty() || !itr->indexPathAbsolute.empty()) {
-	  if (itr->indexType == XAPIAN)
-	    bookNode.append_attribute("indexType") = "xapian";
-	}
-
-	if (itr->origId.empty()) {
-	  if (!itr->title.empty())
-	    bookNode.append_attribute("title") = itr->title.c_str();
-
-	  if (!itr->name.empty())
-	    bookNode.append_attribute("name") = itr->name.c_str();
-
-	  if (!itr->tags.empty())
-	    bookNode.append_attribute("tags") = itr->tags.c_str();
-	  
-	  if (!itr->description.empty())
-	    bookNode.append_attribute("description") = itr->description.c_str();
-	  
-	  if (!itr->language.empty())
-	    bookNode.append_attribute("language") = itr->language.c_str();
-	  
-	  if (!itr->creator.empty())
-	    bookNode.append_attribute("creator") = itr->creator.c_str();
-	  
-	  if (!itr->publisher.empty())
-	    bookNode.append_attribute("publisher") = itr->publisher.c_str();
-	  
-	  if (!itr->favicon.empty())
-	    bookNode.append_attribute("favicon") = itr->favicon.c_str();
-	  
-	  if (!itr->faviconMimeType.empty())
-	    bookNode.append_attribute("faviconMimeType") = itr->faviconMimeType.c_str();
-	}
-
-	if (!itr->date.empty())
-	  bookNode.append_attribute("date") = itr->date.c_str();
-
-	if (!itr->url.empty())
-	  bookNode.append_attribute("url") = itr->url.c_str();
-	
-	if (!itr->origId.empty())
-	  bookNode.append_attribute("origId") = itr->origId.c_str();
-	
-	if (!itr->articleCount.empty())
-	  bookNode.append_attribute("articleCount") = itr->articleCount.c_str();
-
-	if (!itr->mediaCount.empty())
-	  bookNode.append_attribute("mediaCount") = itr->mediaCount.c_str();
-
-	if (!itr->size.empty())
-	  bookNode.append_attribute("size") = itr->size.c_str();
-      }
-    }
-
-    /* saving file */
-    doc.save_file(path.c_str());
-
-    return true;
-  }
-
-  bool Manager::setCurrentBookId(const string id) {
-    if (library.current.empty() || library.current.top() != id) {
-      if (id.empty() && !library.current.empty())
-	library.current.pop();
-      else
-	library.current.push(id);
-    }
-    return true;
-  }
-
-  string Manager::getCurrentBookId() {
-    return library.current.empty() ?
-      "" : library.current.top();
-  }
-
-  /* Add a book to the library. Return empty string if failed, book id otherwise */
-  string Manager::addBookFromPathAndGetId(const string pathToOpen, const string pathToSave,
-					  const string url, const bool checkMetaData) {
-    kiwix::Book book;
-
-    if (this->readBookFromPath(pathToOpen, &book)) {
-
-      if (pathToSave != pathToOpen) {
-	book.path = pathToSave;
-	book.pathAbsolute = isRelativePath(pathToSave) ?
-	  computeAbsolutePath(removeLastPathElement(writableLibraryPath, true, false), pathToSave) : pathToSave;
-      }
-
-      if (!checkMetaData ||
-	  (checkMetaData && !book.title.empty() && !book.language.empty() && !book.date.empty())) {
-	book.url = url;
-	library.addBook(book);
-	return book.id;
-      }
-    }
-
-    return "";
-  }
-
-  /* Wrapper over Manager::addBookFromPath which return a bool instead of a string */
-  bool Manager::addBookFromPath(const string pathToOpen, const string pathToSave, const string url, const bool checkMetaData) {
-    return !(this->addBookFromPathAndGetId(pathToOpen, pathToSave, url, checkMetaData).empty());
-  }
-
-  bool Manager::readBookFromPath(const string path, kiwix::Book *book) {
-    try {
-      kiwix::Reader *reader = new kiwix::Reader(path);
-
-      if (book != NULL) {
-	book->path = path;
-	book->pathAbsolute = path;
-	book->id = reader->getId();
-	book->description = reader->getDescription();
-	book->language = reader->getLanguage();
-	book->date = reader->getDate();
-	book->creator = reader->getCreator();
-	book->publisher = reader->getPublisher();
-	book->title = reader->getTitle();
-	book->name = reader->getName();
-	book->tags = reader->getTags();
-	book->origId = reader->getOrigId();
-	std::ostringstream articleCountStream;
-	articleCountStream << reader->getArticleCount();
-	book->articleCount = articleCountStream.str();
-
-	std::ostringstream mediaCountStream;
-	mediaCountStream << reader->getMediaCount();
-	book->mediaCount = mediaCountStream.str();
-
-	ostringstream convert; convert << reader->getFileSize();
-	book->size = convert.str();
-
-	string favicon;
-	string faviconMimeType;
-	if (reader->getFavicon(favicon, faviconMimeType)) {
-	  book->favicon = base64_encode(reinterpret_cast<const unsigned char*>(favicon.c_str()), favicon.length());
-	  book->faviconMimeType = faviconMimeType;
-	}
-      }
-
-      delete reader;
-    } catch (const std::exception& e) {
-      std::cerr << e.what() << std::endl;
-      return false;
-    }
-
-    return true;
-  }
-
-  bool Manager::removeBookByIndex(const unsigned int bookIndex) {
-    return this->library.removeBookByIndex(bookIndex);
-  }
-
-  bool Manager::removeBookById(const string id) {
-    unsigned int bookIndex = 0;
-    std::vector<kiwix::Book>::iterator itr;
-    for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-      if ( itr->id == id) {
-	return this->library.removeBookByIndex(bookIndex);
-      }
-      bookIndex++;
-    }
-    return false;
-  }
-
-  vector<string> Manager::getBooksLanguages() {
-    std::vector<string> booksLanguages;
-    std::vector<kiwix::Book>::iterator itr;
-    std::map<string, bool> booksLanguagesMap;
-
-    std::sort(library.books.begin(), library.books.end(), kiwix::Book::sortByLanguage);
-    for (itr = library.books.begin(); itr != library.books.end(); ++itr) {
-      if (booksLanguagesMap.find(itr->language) == booksLanguagesMap.end()) {
-        if (itr->origId.empty()) {
-	  booksLanguagesMap[itr->language] = true;
-	  booksLanguages.push_back(itr->language);
-        }
-      }
-    }
-
-    return booksLanguages;
-  }
-
-  vector<string> Manager::getBooksCreators() {
-    std::vector<string> booksCreators;
-    std::vector<kiwix::Book>::iterator itr;
-    std::map<string, bool> booksCreatorsMap;
-
-    std::sort(library.books.begin(), library.books.end(), kiwix::Book::sortByCreator);
-    for (itr = library.books.begin(); itr != library.books.end(); ++itr) {
-      if (booksCreatorsMap.find(itr->creator) == booksCreatorsMap.end()) {
-        if (itr->origId.empty()) {
-	  booksCreatorsMap[itr->creator] = true;
-	  booksCreators.push_back(itr->creator);
-        }
-      }
-    }
-
-    return booksCreators;
-  }
-
-
-  vector<string> Manager::getBooksIds() {
-    std::vector<string> booksIds;
-    std::vector<kiwix::Book>::iterator itr;
-
-    for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-      booksIds.push_back(itr->id);
-    }
-
-    return booksIds;
-  }
-
-  vector<string> Manager::getBooksPublishers() {
-    std::vector<string> booksPublishers;
-    std::vector<kiwix::Book>::iterator itr;
-    std::map<string, bool> booksPublishersMap;
-
-    std::sort(library.books.begin(), library.books.end(), kiwix::Book::sortByPublisher);
-    for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-      if (booksPublishersMap.find(itr->publisher) == booksPublishersMap.end()) {
-        if (itr->origId.empty()) {
-	  booksPublishersMap[itr->publisher] = true;
-	  booksPublishers.push_back(itr->publisher);
-        }
-      }
-    }
-
-    return booksPublishers;
-  }
-
-  kiwix::Library Manager::cloneLibrary() {
-    return this->library;
-  }
-
-  bool Manager::getCurrentBook(Book &book) {
-    string currentBookId = getCurrentBookId();
-    if (currentBookId.empty()) {
-      return false;
-    } else {
-      getBookById(currentBookId, book);
-      return true;
-    }
-  }
-
-  bool Manager::getBookById(const string id, Book &book) {
-    std::vector<kiwix::Book>::iterator itr;
-    for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-      if ( itr->id == id) {
-	book = *itr;
-	return true;
-      }
-    }
-    return false;
-  }
-
-  bool Manager::updateBookLastOpenDateById(const string id) {
-    std::vector<kiwix::Book>::iterator itr;
-    for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-      if ( itr->id == id) {
-	char unixdate[12];
-	sprintf (unixdate, "%d", (int)time(NULL));
-	itr->last = unixdate;
-	return true;
-      }
-    }
-
-    return false;
-  }
-
-  bool Manager::setBookIndex(const string id, const string path, const supportedIndexType type) {
-    std::vector<kiwix::Book>::iterator itr;
-    for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-      if ( itr->id == id) {
-	itr->indexPath = path;
-	itr->indexPathAbsolute = isRelativePath(path) ?
-	  computeAbsolutePath(removeLastPathElement(writableLibraryPath, true, false), path) : path;
-	itr->indexType = type;
-	return true;
-      }
-    }
-
-    return false;
-  }
-
-  bool Manager::setBookIndex(const string id, const string path) {
-    return this->setBookIndex(id, path, XAPIAN);
-  }
-
-  bool Manager::setBookPath(const string id, const string path) {
-    std::vector<kiwix::Book>::iterator itr;
-    for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-      if ( itr->id == id) {
-	itr->path = path;
-	itr->pathAbsolute = isRelativePath(path) ?
-	  computeAbsolutePath(removeLastPathElement(writableLibraryPath, true, false), path) : path;
-	return true;
-      }
-    }
-
-    return false;
-  }
-
-  void Manager::removeBookPaths() {
-    std::vector<kiwix::Book>::iterator itr;
-    for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-      itr->path = "";
-      itr->pathAbsolute = "";
-    }
-  }
-
-  unsigned int Manager::getBookCount(const bool localBooks, const bool remoteBooks) {
-    unsigned int result = 0;
-    std::vector<kiwix::Book>::iterator itr;
-    for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-      if ((!itr->path.empty() && localBooks) || (itr->path.empty() && remoteBooks))
-	result++;
-    }
-    return result;
-  }
-
-  bool Manager::listBooks(const supportedListMode mode, const supportedListSortBy sortBy,
-			  const unsigned int maxSize, const string language, const string creator,
-			  const string publisher, const string search) {
-    this->bookIdList.clear();
-    std::vector<kiwix::Book>::iterator itr;
-
-    /* Sort */
-    if (sortBy == TITLE) {
-      std::sort(library.books.begin(), library.books.end(), kiwix::Book::sortByTitle);
-    } else if (sortBy == SIZE) {
-      std::sort(library.books.begin(), library.books.end(), kiwix::Book::sortBySize);
-    } else if (sortBy == DATE) {
-      std::sort(library.books.begin(), library.books.end(), kiwix::Book::sortByDate);
-    } else if (sortBy == CREATOR) {
-      std::sort(library.books.begin(), library.books.end(), kiwix::Book::sortByCreator);
-    } else if (sortBy == PUBLISHER) {
-      std::sort(library.books.begin(), library.books.end(), kiwix::Book::sortByPublisher);
-    }
-
-    /* Special sort for LASTOPEN */
-    if (mode == LASTOPEN) {
-      std::sort(library.books.begin(), library.books.end(), kiwix::Book::sortByLastOpen);
-      for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-	if (!itr->last.empty())
-	  this->bookIdList.push_back(itr->id);
-      }
-    } else {
-      /* Generate the list of book id */
-      for ( itr = library.books.begin(); itr != library.books.end(); ++itr ) {
-	bool ok = true;
-
-	if (mode == LOCAL && itr->path.empty())
-	  ok = false;
-
-	if (ok == true && mode == REMOTE && (!itr->path.empty() || itr->url.empty()))
-	  ok = false;
-
-	if (ok == true && maxSize != 0 && (unsigned int)atoi(itr->size.c_str()) > maxSize * 1024 * 1024)
-	  ok = false;
-
-	if (ok == true && !language.empty() && !matchRegex(itr->language, language))
-	  ok = false;
-
-	if (ok == true && !creator.empty() && itr->creator != creator)
-	  ok = false;
-
-	if (ok == true && !publisher.empty() && itr->publisher != publisher)
-	  ok = false;
-
-	if ((ok == true && !search.empty()) && !(matchRegex(itr->title, "\\Q" + search + "\\E") || 
-						 matchRegex(itr->description,  "\\Q" + search + "\\E") ||
-						 matchRegex(itr->language,  "\\Q" + search + "\\E")
-						 ))
-	  ok = false;
-
-	if (ok == true) {
-	  this->bookIdList.push_back(itr->id);
-	}
-      }
-    }
-
-    return true;
-  }
-
-  void Manager::checkAndCleanBookPaths(Book &book, const string &libraryPath) {
-    if (!book.path.empty()) {
-      if (isRelativePath(book.path)) {
-	book.pathAbsolute = computeAbsolutePath(removeLastPathElement(libraryPath, true, false), book.path);
-      } else {
-	book.pathAbsolute = book.path;
-	book.path = computeRelativePath(removeLastPathElement(libraryPath, true, false), book.pathAbsolute);
-      }
-    }
-
-    if (!book.indexPath.empty()) {
-      if (isRelativePath(book.indexPath)) {
-	book.indexPathAbsolute =
-	  computeAbsolutePath(removeLastPathElement(libraryPath, true, false), book.indexPath);
-      } else {
-	book.indexPathAbsolute = book.indexPath;
-	book.indexPath =
-	  computeRelativePath(removeLastPathElement(libraryPath, true, false), book.indexPathAbsolute);
-      }
-    }
-  }
-
-}

src/common/kiwix/manager.h

@@ -1,92 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_MANAGER_H
-#define KIWIX_MANAGER_H
-
-#include <string>
-#include <sstream>
-#include <time.h>
-
-#include <pugixml.hpp>
-
-#include "../base64.h"
-#include "../regexTools.h"
-#include "../pathTools.h"
-#include <kiwix/library.h>
-#include <kiwix/reader.h>
-
-using namespace std;
-
-namespace kiwix {
-
-  enum supportedListMode { LASTOPEN, REMOTE, LOCAL };
-  enum supportedListSortBy { TITLE, SIZE, DATE, CREATOR, PUBLISHER };
-
-  class Manager {
-
-  public:
-    Manager();
-    ~Manager();
-
-    bool readFile(const string path, const bool readOnly = true);
-    bool readFile(const string nativePath, const string UTF8Path, const bool readOnly = true);
-    bool readXml(const string xml, const bool readOnly = true, const string libraryPath = "");
-    bool writeFile(const string path);
-    bool removeBookByIndex(const unsigned int bookIndex);
-    bool removeBookById(const string id);
-    bool setCurrentBookId(const string id);
-    string getCurrentBookId();
-    bool setBookIndex(const string id, const string path, const supportedIndexType type);
-    bool setBookIndex(const string id, const string path);
-    bool setBookPath(const string id, const string path);
-    string addBookFromPathAndGetId(const string pathToOpen, const string pathToSave = "", const string url = "",
-				   const bool checkMetaData = false);
-    bool addBookFromPath(const string pathToOpen, const string pathToSave = "", const string url = "",
-			 const bool checkMetaData = false);
-    Library cloneLibrary();
-    bool getBookById(const string id, Book &book);
-    bool getCurrentBook(Book &book);
-    unsigned int getBookCount(const bool localBooks, const bool remoteBooks);
-    bool updateBookLastOpenDateById(const string id);
-    void removeBookPaths();
-    bool listBooks(const supportedListMode mode, const supportedListSortBy sortBy, const unsigned int maxSize,
-		   const string language, const string creator, const string publisher, const string search);
-    vector<string> getBooksLanguages();
-    vector<string> getBooksCreators();
-    vector<string> getBooksPublishers();
-    vector<string> getBooksIds();
-
-    string writableLibraryPath;
-
-    vector<std::string> bookIdList;
-
-  protected:
-    kiwix::Library library;
-
-    bool readBookFromPath(const string path, Book *book = NULL);
-    bool parseXmlDom(const pugi::xml_document &doc, const bool readOnly, const string libraryPath);
-
-  private:
-    void checkAndCleanBookPaths(Book &book, const string &libraryPath);
-  };
-
-}
-
-#endif

src/common/kiwix/reader.cpp

@@ -1,690 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "reader.h"
-
-inline char hi(char v) {
-    char hex[] = "0123456789abcdef";
-    return hex[(v >> 4) & 0xf];
-}
-
-inline char lo(char v) {
-    char hex[] = "0123456789abcdef";
-    return hex[v & 0xf];
-}
-
-std::string hexUUID (std::string in) {
-    std::ostringstream out;
-    for (unsigned n = 0; n < 4; ++n)
-      out << hi(in[n]) << lo(in[n]);
-    out << '-';
-    for (unsigned n = 4; n < 6; ++n)
-      out << hi(in[n]) << lo(in[n]);
-    out << '-';
-    for (unsigned n = 6; n < 8; ++n)
-      out << hi(in[n]) << lo(in[n]);
-    out << '-';
-    for (unsigned n = 8; n < 10; ++n)
-      out << hi(in[n]) << lo(in[n]);
-    out << '-';
-    for (unsigned n = 10; n < 16; ++n)
-      out << hi(in[n]) << lo(in[n]);
-    std::string op=out.str();
-    return op;
-}
-
-namespace kiwix {
-
-  /* Constructor */
-  Reader::Reader(const string zimFilePath)
-    : zimFileHandler(NULL) {
-    string tmpZimFilePath = zimFilePath;
-
-    /* Remove potential trailing zimaa */
-    size_t found = tmpZimFilePath.rfind("zimaa");
-    if (found != string::npos &&
-	tmpZimFilePath.size() > 5 &&
-	found == tmpZimFilePath.size() - 5) {
-      tmpZimFilePath.resize(tmpZimFilePath.size() - 2);
-    }
-
-    this->zimFileHandler = new zim::File(tmpZimFilePath);
-
-    if (this->zimFileHandler != NULL) {
-      this->firstArticleOffset = this->zimFileHandler->getNamespaceBeginOffset('A');
-      this->lastArticleOffset = this->zimFileHandler->getNamespaceEndOffset('A');
-      this->currentArticleOffset = this->firstArticleOffset;
-      this->nsACount = this->zimFileHandler->getNamespaceCount('A');
-      this->nsICount = this->zimFileHandler->getNamespaceCount('I');
-      this->zimFilePath = zimFilePath;
-    }
-
-    /* initialize random seed: */
-    srand ( time(NULL) );
-  }
-
-  /* Destructor */
-  Reader::~Reader() {
-    if (this->zimFileHandler != NULL) {
-      delete this->zimFileHandler;
-    }
-  }
-
-  zim::File* Reader::getZimFileHandler() {
-    return this->zimFileHandler;
-  }
-
-  /* Reset the cursor for GetNextArticle() */
-  void Reader::reset() {
-    this->currentArticleOffset = this->firstArticleOffset;
-  }
-
-  std::map<std::string, unsigned int> Reader::parseCounterMetadata() {
-    std::map<std::string, unsigned int> counters;
-    string content, mimeType, item, counterString;
-    unsigned int contentLength, counter;
-    string counterUrl = "/M/Counter";
-
-    this->getContentByUrl(counterUrl, content, contentLength, mimeType);
-    stringstream ssContent(content);
-
-    while(getline(ssContent, item,  ';')) {
-      stringstream ssItem(item);
-      getline(ssItem, mimeType, '=');
-      getline(ssItem, counterString, '=');
-      if (!counterString.empty() && !mimeType.empty()) {
-	sscanf(counterString.c_str(), "%u", &counter);
-	counters.insert(pair<string, int>(mimeType, counter));
-      }
-    }
-
-    return counters;
-  }
-
-  /* Get the count of articles which can be indexed/displayed */
-  unsigned int Reader::getArticleCount() {
-    std::map<std::string, unsigned int> counterMap = this->parseCounterMetadata();
-    unsigned int counter = 0;
-
-    if (counterMap.empty()) {
-      counter = this->nsACount;
-    } else {
-      std::map<std::string, unsigned int>::const_iterator it = counterMap.find("text/html");
-      if (it != counterMap.end())
-	counter = it->second;
-    }
-
-    return counter;
-  }
-
-  /* Get the count of medias content in the ZIM file */
-  unsigned int Reader::getMediaCount() {
-    std::map<std::string, unsigned int> counterMap = this->parseCounterMetadata();
-    unsigned int counter = 0;
-
-    if (counterMap.empty())
-      counter = this->nsICount;
-    else {
-      std::map<std::string, unsigned int>::const_iterator it;
-
-      it = counterMap.find("image/jpeg");
-      if (it != counterMap.end())
-	counter += it->second;
-
-      it = counterMap.find("image/gif");
-      if (it != counterMap.end())
-	counter += it->second;
-
-      it = counterMap.find("image/png");
-      if (it != counterMap.end())
-	counter += it->second;
-    }
-
-    return counter;
-  }
-
-  /* Get the total of all items of a ZIM file, redirects included */
-  unsigned int Reader::getGlobalCount() {
-    return this->zimFileHandler->getCountArticles();
-  }
-
-  /* Return the UID of the ZIM file */
-  string Reader::getId() {
-    std::ostringstream s;
-    s << this->zimFileHandler->getFileheader().getUuid();
-    return  s.str();
-  }
-
-  /* Return a page url from a title */
-  bool Reader::getPageUrlFromTitle(const string &title, string &url) {
-    /* Extract the content from the zim file */
-    std::pair<bool, zim::File::const_iterator> resultPair = zimFileHandler->findxByTitle('A', title);
-
-    /* Test if the article was found */
-    if (resultPair.first == true) {
-
-      /* Get the article */
-      zim::Article article = *resultPair.second;
-
-      /* If redirect */
-      unsigned int loopCounter = 0;
-      while (article.isRedirect() && loopCounter++<42) {
-	article = article.getRedirectArticle();
-      }
-
-      url = article.getLongUrl();
-      return true;
-    }
-
-    return false;
-  }
-
-  /* Return an URL from a title*/
-  string Reader::getRandomPageUrl() {
-    zim::Article article;
-    zim::size_type idx;
-    std::string mainPageUrl = this->getMainPageUrl();
-    
-    do {
-      idx = this->firstArticleOffset +
-	(zim::size_type)((double)rand() / ((double)RAND_MAX + 1) * this->nsACount);
-      article = zimFileHandler->getArticle(idx);
-    } while (article.getLongUrl() == mainPageUrl);
-
-    return article.getLongUrl().c_str();
-  }
-
-  /* Return the welcome page URL */
-  string Reader::getMainPageUrl() {
-    string url = "";
-
-    if (this->zimFileHandler->getFileheader().hasMainPage()) {
-      zim::Article article = zimFileHandler->getArticle(this->zimFileHandler->getFileheader().getMainPage());
-      url = article.getLongUrl();
-
-      if (url.empty()) {
-	url = getFirstPageUrl();
-      }
-    } else {
-	url = getFirstPageUrl();
-    }
-
-    return url;
-  }
-
-  bool Reader::getFavicon(string &content, string &mimeType) {
-    unsigned int contentLength = 0;
-
-    this->getContentByUrl( "/-/favicon.png", content,
-			   contentLength, mimeType);
-
-    if (content.empty()) {
-      this->getContentByUrl( "/I/favicon.png", content,
-			     contentLength, mimeType);
-
-
-      if (content.empty()) {
-	this->getContentByUrl( "/I/favicon", content,
-			       contentLength, mimeType);
-
-	if (content.empty()) {
-	  this->getContentByUrl( "/-/favicon", content,
-				 contentLength, mimeType);
-	}
-      }
-    }
-
-    return content.empty() ? false : true;
-  }
-
-  string Reader::getZimFilePath() {
-    return this->zimFilePath;
-  }
-
-  /* Return a metatag value */
-  bool Reader::getMetatag(const string &name, string &value) {
-    unsigned int contentLength = 0;
-    string contentType = "";
-
-    return this->getContentByUrl( "/M/" + name, value,
-				  contentLength, contentType);
-  }
-
-  string Reader::getTitle() {
-    string value;
-    this->getMetatag("Title", value);
-    if (value.empty()) {
-      value = getLastPathElement(zimFileHandler->getFilename());
-      std::replace(value.begin(), value.end(), '_', ' ');
-      size_t pos = value.find(".zim");
-      value = value.substr(0, pos);
-    }
-    return value;
-  }
-
-  string Reader::getName() {
-    string value;
-    this->getMetatag("Name", value);
-    return value;
-  }
-
-  string Reader::getTags() {
-    string value;
-    this->getMetatag("Tags", value);
-    return value;
-  }
-
-  string Reader::getDescription() {
-    string value;
-    this->getMetatag("Description", value);
-
-    /* Mediawiki Collection tends to use the "Subtitle" name */
-    if (value.empty()) {
-      this->getMetatag("Subtitle", value);
-    }
-
-    return value;
-  }
-
-  string Reader::getLanguage() {
-    string value;
-    this->getMetatag("Language", value);
-    return value;
-  }
-
-  string Reader::getDate() {
-    string value;
-    this->getMetatag("Date", value);
-    return value;
-  }
-
-  string Reader::getCreator() {
-    string value;
-    this->getMetatag("Creator", value);
-    return value;
-  }
-
-  string Reader::getPublisher() {
-    string value;
-    this->getMetatag("Publisher", value);
-    return value;
-  }
-
-  string Reader::getOrigId() {
-    string value;
-    this->getMetatag("startfileuid", value);
-    if(value.empty())
-        return "";
-    std::string id=value;
-    std::string origID;
-    std::string temp="";
-    unsigned int k=0;
-    char tempArray[16]="";
-    for(unsigned int i=0; i<id.size(); i++)
-    {
-        if(id[i]=='\n')
-        {
-            tempArray[k]= atoi(temp.c_str());
-            temp="";
-            k++;
-        }
-        else
-        {
-            temp+=id[i];
-        }
-    }
-    origID=hexUUID(tempArray);
-    return origID;
-  }
-
-  /* Return the first page URL */
-  string Reader::getFirstPageUrl() {
-    string url;
-
-    zim::size_type firstPageOffset = zimFileHandler->getNamespaceBeginOffset('A');
-    zim::Article article = zimFileHandler->getArticle(firstPageOffset);
-    url = article.getLongUrl();
-
-    return url;
-  }
-
-  bool Reader::parseUrl(const string &url, char *ns, string &title) {
-    /* Offset to visit the url */
-    unsigned int urlLength = url.size();
-    unsigned int offset = 0;
-
-    /* Ignore the '/' */
-    while ((offset < urlLength) && (url[offset] == '/')) offset++;
-
-    /* Get namespace */
-    while ((offset < urlLength) && (url[offset] != '/')) {
-      *ns= url[offset];
-      offset++;
-    }
-
-    /* Ignore the '/' */
-    while ((offset < urlLength) && (url[offset] == '/')) offset++;
-
-    /* Get content title */
-    unsigned int titleOffset = offset;
-    while (offset < urlLength) {
-      offset++;
-    }
-
-    /* unescape title */
-    title = url.substr(titleOffset, offset - titleOffset);
-
-    return true;
-  }
-
-  /* Return article by url */
-  bool Reader::getArticleObjectByDecodedUrl(const string &url, zim::Article &article) {
-    bool retVal = false;
-    
-    if (this->zimFileHandler != NULL) {
-      
-      /* Parse the url */
-      char ns = 0;
-      string titleStr;
-      this->parseUrl(url, &ns, titleStr);
-      
-      /* Main page */
-      if (titleStr.empty() && ns == 0) {
-	this->parseUrl(this->getMainPageUrl(), &ns, titleStr);
-      }
-      
-      /* Extract the content from the zim file */
-      std::pair<bool, zim::File::const_iterator> resultPair = zimFileHandler->findx(ns, titleStr);
-      
-      /* Test if the article was found */
-      if (resultPair.first == true) {
-	article = zimFileHandler->getArticle(resultPair.second.getIndex());
-	retVal = true;
-      }
-
-    }
-    
-    return retVal;
-  }
-
-  /* Return the mimeType without the content */
-  bool Reader::getMimeTypeByUrl(const string &url, string &mimeType) {
-    bool retVal = false;
-
-    if (this->zimFileHandler != NULL) {
-
-      zim::Article article;
-      if (this->getArticleObjectByDecodedUrl(url, article)) {
-	  try {
-	    mimeType = string(article.getMimeType().data(), article.getMimeType().size());
-	  } catch (exception &e) {
-	    cerr << "Unable to get the mimetype for "<< url << ":" << e.what() << endl;
-	    mimeType = "application/octet-stream";
-	  }	
-	  retVal = true;
-      } else {
-	mimeType = "";
-      }
-     
-    }
-
-    return retVal;
-  }
-
-  /* Get a content from a zim file */
-  bool Reader::getContentByUrl(const string &url, string &content, unsigned int &contentLength, string &contentType) {
-    return this->getContentByEncodedUrl(url, content, contentLength, contentType);
-  }
-
-  bool Reader::getContentByEncodedUrl(const string &url, string &content, unsigned int &contentLength, string &contentType, string &baseUrl) {
-    return this->getContentByDecodedUrl(kiwix::urlDecode(url), content, contentLength, contentType, baseUrl);
-  }
-
-  bool Reader::getContentByEncodedUrl(const string &url, string &content, unsigned int &contentLength, string &contentType) {
-    std::string stubRedirectUrl;
-    return this->getContentByEncodedUrl(kiwix::urlDecode(url), content, contentLength, contentType, stubRedirectUrl); 
-  }
-
-  bool Reader::getContentByDecodedUrl(const string &url, string &content, unsigned int &contentLength, string &contentType) {
-    std::string stubRedirectUrl;
-    return this->getContentByDecodedUrl(kiwix::urlDecode(url), content, contentLength, contentType, stubRedirectUrl);
-  }
-
-  bool Reader::getContentByDecodedUrl(const string &url, string &content, unsigned int &contentLength, string &contentType, string &baseUrl) {
-    bool retVal = false;
-    content="";
-    contentType="";
-    contentLength = 0;
-    if (this->zimFileHandler != NULL) {
-
-      zim::Article article;
-      if (this->getArticleObjectByDecodedUrl(url, article)) {
-	
-	/* If redirect */
-	unsigned int loopCounter = 0;
-	while (article.isRedirect() && loopCounter++<42) {
-	  article = article.getRedirectArticle();
-	}
-
-	if (loopCounter < 42) {
-	  /* Compute base url (might be different from the url if redirects */
-	  baseUrl = "/" + std::string(1, article.getNamespace()) + "/" + article.getUrl();
-	  
-	  /* Get the content mime-type */
-	  try {
-	    contentType = string(article.getMimeType().data(), article.getMimeType().size());
-	  } catch (exception &e) {
-	    cerr << "Unable to get the mimetype for "<< baseUrl<< ":" << e.what() << endl;
-	    contentType = "application/octet-stream";
-	  }
-
-	  /* Get the data */
-	  content = string(article.getData().data(), article.getArticleSize());
-	}
-
-	/* Try to set a stub HTML header/footer if necesssary */
-	if (contentType.find("text/html") != string::npos && 
-	    content.find("<body") == std::string::npos &&
-	    content.find("<BODY") == std::string::npos) {
-	  content = "<html><head><title>" + article.getTitle() + "</title><meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" /></head><body>" + content + "</body></html>";
-	}
-
-	/* Get the data length */
-	contentLength = article.getArticleSize();
-
-	/* Set return value */
-	retVal = true;
-      }
-    }
-
-    return retVal;
-  }
-
-  /* Check if an article exists */
-  bool Reader::urlExists(const string &url) {
-    char ns = 0;
-    string titleStr;
-    this->parseUrl(url, &ns, titleStr);
-    titleStr = "/" + titleStr;
-    zim::File::const_iterator findItr = zimFileHandler->find(ns, titleStr);
-    return findItr != zimFileHandler->end() && findItr->getUrl() == titleStr;
-  }
-
-  /* Does the ZIM file has a fulltext index */
-  bool Reader::hasFulltextIndex() {
-    return this->urlExists("/Z/fulltextIndex/xapian");
-  }
-
-  /* Search titles by prefix */
-  bool Reader::searchSuggestions(const string &prefix, unsigned int suggestionsCount, const bool reset) {
-    bool retVal = false;
-    zim::File::const_iterator articleItr;
-
-    /* Reset the suggestions otherwise check if the suggestions number is less than the suggestionsCount */
-    if (reset) {
-      this->suggestions.clear();
-      this->suggestionsOffset = this->suggestions.begin();
-    } else {
-      if (this->suggestions.size() > suggestionsCount) {
-	return false;
-      }
-    }
-
-    /* Return if no prefix */
-    if (prefix.size() == 0) {
-      return false;
-    }
-
-    for (articleItr = zimFileHandler->findByTitle('A', prefix);
-	 articleItr != zimFileHandler->end() &&
-	   articleItr->getTitle().compare(0, prefix.size(), prefix) == 0 &&
-	   this->suggestions.size() < suggestionsCount ;
-	 ++articleItr) {
-
-      /* Extract the interesting part of article title & url */
-      std::string normalizedArticleTitle = kiwix::normalize(articleItr->getTitle());
-      std::string articleFinalUrl = "/A/"+articleItr->getUrl();
-      if (articleItr->isRedirect()) {
-	zim::Article article = *articleItr;
-	unsigned int loopCounter = 0;
-	while (article.isRedirect() && loopCounter++<42) {
-	  article = article.getRedirectArticle();
-	}
-	articleFinalUrl = "/A/"+article.getUrl();
-      }
-
-      /* Go through all already found suggestions and skip if this
-	 article is already in the suggestions list (with an other
-	 title) */
-      bool insert = true;
-      std::vector< std::vector<std::string> >::iterator suggestionItr;
-      for (suggestionItr = this->suggestions.begin(); suggestionItr != this->suggestions.end(); suggestionItr++) {
-	int result = normalizedArticleTitle.compare((*suggestionItr)[2]);
-	if (result == 0 && articleFinalUrl.compare((*suggestionItr)[1]) == 0) {
-	  insert = false;
-	  break;
-	} else if (result < 0) {
-	  break;
-	}
-      }
-
-      /* Insert if possible */
-      if (insert) {
-	std::vector<std::string> suggestion;
-	suggestion.push_back(articleItr->getTitle());
-	suggestion.push_back(articleFinalUrl);
-	suggestion.push_back(normalizedArticleTitle);
-	this->suggestions.insert(suggestionItr, suggestion);
-      }
-
-      /* Suggestions where found */
-      retVal = true;
-    }
-
-    /* Set the cursor to the begining */
-    this->suggestionsOffset = this->suggestions.begin();
-
-    return retVal;
-  }
-
-  std::vector<std::string> Reader::getTitleVariants(const std::string &title) {
-    std::vector<std::string> variants;
-    variants.push_back(title);
-    variants.push_back(kiwix::ucFirst(title));
-    variants.push_back(kiwix::lcFirst(title));
-    variants.push_back(kiwix::toTitle(title));
-    return variants;
-  }
-
-  /* Try also a few variations of the prefix to have better results */
-  bool Reader::searchSuggestionsSmart(const string &prefix, unsigned int suggestionsCount) {
-    std::vector<std::string> variants = this->getTitleVariants(prefix);
-    bool retVal;
-    
-    this->suggestions.clear();
-    this->suggestionsOffset = this->suggestions.begin();
-    for (std::vector<std::string>::iterator variantsItr = variants.begin();
-	 variantsItr != variants.end();
-	 variantsItr++) {
-      retVal = this->searchSuggestions(*variantsItr, suggestionsCount, false) || retVal;
-    }
-
-    return retVal;
-  }
-
-  /* Get next suggestion */
-  bool Reader::getNextSuggestion(string &title) {
-    if (this->suggestionsOffset != this->suggestions.end()) {
-      /* title */
-      title = (*(this->suggestionsOffset))[0];
-
-      /* increment the cursor for the next call */
-      this->suggestionsOffset++;
-
-      return true;
-    }
-
-    return false;
-  }
-
-  bool Reader::getNextSuggestion(string &title, string &url) {
-    if (this->suggestionsOffset != this->suggestions.end()) {
-      /* title */
-      title = (*(this->suggestionsOffset))[0];
-      url = (*(this->suggestionsOffset))[1];
-
-      /* increment the cursor for the next call */
-      this->suggestionsOffset++;
-
-      return true;
-    }
-
-    return false;
-  }
-
-  /* Check if the file has as checksum */
-  bool Reader::canCheckIntegrity() {
-    return this->zimFileHandler->getChecksum() != "";
-  }
-
-  /* Return true if corrupted, false otherwise */
-  bool Reader::isCorrupted() {
-    try {
-      if (this->zimFileHandler->verify() == true)
-	return false;
-    } catch (exception &e) {
-      cerr << e.what() << endl;
-      return true;
-    }
-
-    return true;
-  }
-
-  /* Return the file size, works also for splitted files */
-  unsigned int Reader::getFileSize() {
-    zim::File *file = this->getZimFileHandler();
-    zim::offset_type size = 0;
-
-    if (file != NULL) {
-      size = file->getFilesize();
-    }
-
-    return (size / 1024);
-  }
-}

src/common/kiwix/reader.h

@@ -1,105 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_READER_H
-#define KIWIX_READER_H
-
-#include <zim/zim.h>
-#include <zim/file.h>
-#include <zim/article.h>
-#include <zim/fileiterator.h>
-#include <stdio.h>
-#include <string>
-#include <exception>
-#include <sstream>
-#include <map>
-#include "time.h"
-#include <pathTools.h>
-#include <stringTools.h>
-
-using namespace std;
-
-namespace kiwix {
-
-  class Reader {
-
-  public:
-    Reader(const string zimFilePath);
-    ~Reader();
-
-    void reset();
-    unsigned int getArticleCount();
-    unsigned int getMediaCount();
-    unsigned int getGlobalCount();
-    string getZimFilePath();
-    string getId();
-    string getRandomPageUrl();
-    string getFirstPageUrl();
-    string getMainPageUrl();
-    bool getMetatag(const string &url, string &content);
-    string getTitle();
-    string getDescription();
-    string getLanguage();
-    string getName();
-    string getTags();
-    string getDate();
-    string getCreator();
-    string getPublisher();
-    string getOrigId();
-    bool getFavicon(string &content, string &mimeType);
-    bool getPageUrlFromTitle(const string &title, string &url);
-    bool getMimeTypeByUrl(const string &url, string &mimeType);
-    bool getContentByUrl(const string &url, string &content, unsigned int &contentLength, string &contentType);
-    bool getContentByEncodedUrl(const string &url, string &content, unsigned int &contentLength, string &contentType, string &baseUrl);
-    bool getContentByEncodedUrl(const string &url, string &content, unsigned int &contentLength, string &contentType);
-    bool getContentByDecodedUrl(const string &url, string &content, unsigned int &contentLength, string &contentType, string &baseUrl);
-    bool getContentByDecodedUrl(const string &url, string &content, unsigned int &contentLength, string &contentType);
-    bool searchSuggestions(const string &prefix, unsigned int suggestionsCount, const bool reset = true);
-    bool searchSuggestionsSmart(const string &prefix, unsigned int suggestionsCount);
-    bool urlExists(const string &url);
-    bool hasFulltextIndex();
-    std::vector<std::string> getTitleVariants(const std::string &title);
-    bool getNextSuggestion(string &title);
-    bool getNextSuggestion(string &title, string &url);
-    bool canCheckIntegrity();
-    bool isCorrupted();
-    bool parseUrl(const string &url, char *ns, string &title);
-    unsigned int getFileSize();
-    zim::File* getZimFileHandler();
-    bool getArticleObjectByDecodedUrl(const string &url, zim::Article &article);
-
-  protected:
-    zim::File* zimFileHandler;
-    zim::size_type firstArticleOffset;
-    zim::size_type lastArticleOffset;
-    zim::size_type currentArticleOffset;
-    zim::size_type nsACount;
-    zim::size_type nsICount;
-    std::string zimFilePath;
-    
-    std::vector< std::vector<std::string> > suggestions;
-    std::vector< std::vector<std::string> >::iterator suggestionsOffset;
-
-  private:
-    std::map<std::string, unsigned int> parseCounterMetadata();
-  };
-
-}
-
-#endif

src/common/kiwix/searcher.cpp

@@ -1,212 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "searcher.h"
-
-
-namespace kiwix {
-
-  /* Constructor */
-  Searcher::Searcher() :
-    searchPattern(""),
-    protocolPrefix("zim://"),
-    searchProtocolPrefix("search://?"),
-    resultCountPerPage(0),
-    estimatedResultCount(0),
-    resultStart(0),
-    resultEnd(0)
-  {
-    template_ct2 = getResourceAsString("results.ct2");
-    loadICUExternalTables();
-  }
-  
-  /* Destructor */
-  Searcher::~Searcher() {}
-  
-  /* Search strings in the database */
-  void Searcher::search(std::string &search, unsigned int resultStart,
-			unsigned int resultEnd, const bool verbose) {
-    this->reset();
-
-    if (verbose == true) {
-      cout << "Performing query `" << search << "'" << endl;
-    }
-
-    /* If resultEnd & resultStart inverted */
-    if (resultStart > resultEnd) {
-      resultEnd += resultStart;
-      resultStart = resultEnd - resultStart;
-      resultEnd -= resultStart; 
-    }
-
-    /* Try to find results */
-    if (resultStart != resultEnd) {
-
-      /* Avoid big researches */
-      this->resultCountPerPage = resultEnd - resultStart;
-      if (this->resultCountPerPage > 70) {
-	resultEnd = resultStart + 70;
-	this->resultCountPerPage = 70;
-      }
-
-      /* Perform the search */
-      this->searchPattern = search;
-      this->resultStart = resultStart;
-      this->resultEnd = resultEnd;
-      string unaccentedSearch = removeAccents(search);
-      searchInIndex(unaccentedSearch, resultStart, resultEnd, verbose);
-      this->resultOffset = this->results.begin();
-    }
-
-    return;
-  }
-
-  /* Reset the results */
-  void Searcher::reset() {
-    this->results.clear();
-    this->resultOffset = this->results.begin();
-    this->estimatedResultCount = 0;
-    this->searchPattern = "";
-    return;
-  }
-
-  /* Return the result count estimation */
-  unsigned int Searcher::getEstimatedResultCount() {
-    return this->estimatedResultCount;
-  }
-
-  /* Get next result */
-  bool Searcher::getNextResult(string &url, string &title, unsigned int &score) {
-    bool retVal = false;
-
-    if (this->resultOffset != this->results.end()) {
-
-      /* url */
-      url = this->resultOffset->url;
-
-      /* title */
-      title = this->resultOffset->title;
-
-      /* score */
-      score =  this->resultOffset->score;
-
-      /* increment the cursor for the next call */
-      this->resultOffset++;
-
-      retVal = true;
-    }
-
-    return retVal;
-  }
-
-  bool Searcher::setProtocolPrefix(const std::string prefix) {
-    this->protocolPrefix = prefix;
-    return true;
-  }
-
-  bool Searcher::setSearchProtocolPrefix(const std::string prefix) {
-    this->searchProtocolPrefix = prefix;
-    return true;
-  }
-
-  void Searcher::setContentHumanReadableId(const string &contentHumanReadableId) {
-    this->contentHumanReadableId = contentHumanReadableId;
-  }
-
-#ifndef __ANDROID__
-  
-  string Searcher::getHtml() {
-
-    SimpleVM oSimpleVM;
-
-    // Fill data
-    CDT oData;
-    CDT resultsCDT(CDT::ARRAY_VAL);
-
-    this->resultOffset = this->results.begin();
-    while (this->resultOffset != this->results.end()) {
-      CDT result;
-      result["title"] = this->resultOffset->title;
-      result["url"] = this->resultOffset->url;
-      result["snippet"] = this->resultOffset->snippet;
-
-      if (this->resultOffset->size >= 0)
-    result["size"] = kiwix::beautifyInteger(this->resultOffset->size);
-
-      if (this->resultOffset->wordCount >= 0)
-    result["wordCount"] = kiwix::beautifyInteger(this->resultOffset->wordCount);
-
-      resultsCDT.PushBack(result);
-      this->resultOffset++;
-    }
-    this->resultOffset = this->results.begin();
-    oData["results"] = resultsCDT;
-
-    // pages
-    CDT pagesCDT(CDT::ARRAY_VAL);
-
-    unsigned int pageStart = this->resultStart / this->resultCountPerPage >= 5 ? this->resultStart / this->resultCountPerPage - 4 : 0;
-    unsigned int pageCount = this->estimatedResultCount / this->resultCountPerPage + 1 - pageStart;
-
-    if (pageCount > 10)
-      pageCount = 10;
-    else if (pageCount == 1)
-      pageCount = 0;
-
-    for (unsigned int i=pageStart; i<pageStart+pageCount; i++) {
-      CDT page;
-      page["label"] = i + 1;
-      page["start"] = i * this->resultCountPerPage;
-      page["end"] = (i+1) * this->resultCountPerPage;
-
-      if (i * this->resultCountPerPage == this->resultStart)
-    page["selected"] = true;
-
-      pagesCDT.PushBack(page);
-    }
-    oData["pages"] = pagesCDT;
-
-    oData["count"] = kiwix::beautifyInteger(this->estimatedResultCount);
-    oData["searchPattern"] = kiwix::encodeDiples(this->searchPattern);
-    oData["searchPatternEncoded"] = urlEncode(this->searchPattern);
-    oData["resultStart"] = this->resultStart + 1;
-    oData["resultEnd"] = (this->resultEnd > this->estimatedResultCount ? this->estimatedResultCount : this->resultEnd);
-    oData["resultRange"] = this->resultCountPerPage;
-    oData["resultLastPageStart"] = this->estimatedResultCount > this->resultCountPerPage ? this->estimatedResultCount - this->resultCountPerPage : 0;
-    oData["protocolPrefix"] = this->protocolPrefix;
-    oData["searchProtocolPrefix"] = this->searchProtocolPrefix;
-    oData["contentId"] = this->contentHumanReadableId;
-
-    VMStringLoader oLoader(template_ct2.c_str(), template_ct2.size());
-
-    FileLogger oLogger(stderr);
-
-    // DEBUG only (write output to stdout)
-    // oSimpleVM.Run(oData, oLoader, stdout, oLogger);
-
-    std::string sResult;
-    oSimpleVM.Run(oData, oLoader, sResult, oLogger);
-
-    return sResult;
-
-  }
-
-#endif
-
-}

src/common/kiwix/searcher.h

@@ -1,99 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_SEARCHER_H
-#define KIWIX_SEARCHER_H
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string>
-#include <algorithm>
-#include <vector>
-#include <locale>
-#include <cctype>
-#include <vector>
-#include <resourceTools.h>
-#include <pathTools.h>
-#include <stringTools.h>
-#include "unicode/putil.h"
-
-#ifndef __ANDROID__
-#include <ctpp2/CDT.hpp>
-#include <ctpp2/CTPP2FileLogger.hpp>
-#include <ctpp2/CTPP2SimpleVM.hpp>
-#include "kiwix/ctpp2/CTPP2VMStringLoader.hpp"
-
-using namespace CTPP;
-#endif
-
-using namespace std;
-
-struct Result
-{
-  string url;
-  string title;
-  int score;
-  string snippet;
-  int wordCount;
-  int size;
-};
-
-namespace kiwix {
-
-  class Searcher {
-
-  public:
-    Searcher();
-    ~Searcher();
-
-    void search(std::string &search, unsigned int resultStart,
-		unsigned int resultEnd, const bool verbose=false);
-    bool getNextResult(string &url, string &title, unsigned int &score);
-    unsigned int getEstimatedResultCount();
-    bool setProtocolPrefix(const std::string prefix);
-    bool setSearchProtocolPrefix(const std::string prefix);
-    void reset();
-    void setContentHumanReadableId(const string &contentHumanReadableId);
-
-#ifndef __ANDROID__
-    string getHtml();
-#endif
-    
-  protected:
-    std::string beautifyInteger(const unsigned int number);
-    virtual void closeIndex() = 0;
-    virtual void searchInIndex(string &search, const unsigned int resultStart,
-			       const unsigned int resultEnd, const bool verbose=false) = 0;
-
-    std::vector<Result> results;
-    std::vector<Result>::iterator resultOffset;
-    std::string searchPattern;
-    std::string protocolPrefix;
-    std::string searchProtocolPrefix;
-    std::string template_ct2;
-    unsigned int resultCountPerPage;
-    unsigned int estimatedResultCount;
-    unsigned int resultStart;
-    unsigned int resultEnd;
-    std::string contentHumanReadableId;
-  };
-
-}
-
-#endif

src/common/kiwix/xapian/htmlparse.cc

@@ -1,373 +0,0 @@
-/* htmlparse.cc: simple HTML parser for omega indexer
- *
- * Copyright 1999,2000,2001 BrightStation PLC
- * Copyright 2001 Ananova Ltd
- * Copyright 2002,2006,2007,2008 Olly Betts
- *
- * 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 2 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, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
- * USA
- */
-
-// #include <config.h>
-
-#include "htmlparse.h"
-
-#include <xapian.h>
-
-// #include "utf8convert.h"
-
-#include <algorithm>
-
-#include <ctype.h>
-#include <cstring>
-#include <stdio.h>
-#include <stdlib.h>
-
-using namespace std;
-
-inline void
-lowercase_string(string &str)
-{
-    for (string::iterator i = str.begin(); i != str.end(); ++i) {
-	*i = tolower(static_cast<unsigned char>(*i));
-    }
-}
-
-map<string, unsigned int> HtmlParser::named_ents;
-
-inline static bool
-p_notdigit(char c)
-{
-    return !isdigit(static_cast<unsigned char>(c));
-}
-
-inline static bool
-p_notxdigit(char c)
-{
-    return !isxdigit(static_cast<unsigned char>(c));
-}
-
-inline static bool
-p_notalnum(char c)
-{
-    return !isalnum(static_cast<unsigned char>(c));
-}
-
-inline static bool
-p_notwhitespace(char c)
-{
-    return !isspace(static_cast<unsigned char>(c));
-}
-
-inline static bool
-p_nottag(char c)
-{
-    return !isalnum(static_cast<unsigned char>(c)) &&
-	c != '.' && c != '-' && c != ':'; // ':' for XML namespaces.
-}
-
-inline static bool
-p_whitespacegt(char c)
-{
-    return isspace(static_cast<unsigned char>(c)) || c == '>';
-}
-
-inline static bool
-p_whitespaceeqgt(char c)
-{
-    return isspace(static_cast<unsigned char>(c)) || c == '=' || c == '>';
-}
-
-bool
-HtmlParser::get_parameter(const string & param, string & value)
-{
-    map<string, string>::const_iterator i = parameters.find(param);
-    if (i == parameters.end()) return false;
-    value = i->second;
-    return true;
-}
-
-HtmlParser::HtmlParser()
-{
-    static const struct ent { const char *n; unsigned int v; } ents[] = {
-#include "namedentities.h"
-	{ NULL, 0 }
-    };
-    if (named_ents.empty()) {
-	const struct ent *i = ents;
-	while (i->n) {
-	    named_ents[string(i->n)] = i->v;
-	    ++i;
-	}
-    }
-}
-
-void
-HtmlParser::decode_entities(string &s)
-{
-    // We need a const_iterator version of s.end() - otherwise the
-    // find() and find_if() templates don't work...
-    string::const_iterator amp = s.begin(), s_end = s.end();
-    while ((amp = find(amp, s_end, '&')) != s_end) {
-	unsigned int val = 0;
-	string::const_iterator end, p = amp + 1;
-	if (p != s_end && *p == '#') {
-	    p++;
-	    if (p != s_end && (*p == 'x' || *p == 'X')) {
-		// hex
-		p++;
-		end = find_if(p, s_end, p_notxdigit);
-		sscanf(s.substr(p - s.begin(), end - p).c_str(), "%x", &val);
-	    } else {
-		// number
-		end = find_if(p, s_end, p_notdigit);
-		val = atoi(s.substr(p - s.begin(), end - p).c_str());
-	    }
-	} else {
-	    end = find_if(p, s_end, p_notalnum);
-	    string code = s.substr(p - s.begin(), end - p);
-	    map<string, unsigned int>::const_iterator i;
-	    i = named_ents.find(code);
-	    if (i != named_ents.end()) val = i->second;
-	}
-	if (end < s_end && *end == ';') end++;
-	if (val) {
-	    string::size_type amp_pos = amp - s.begin();
-	    if (val < 0x80) {
-		s.replace(amp_pos, end - amp, 1u, char(val));
-	    } else {
-		// Convert unicode value val to UTF-8.
-		char seq[4];
-		unsigned len = Xapian::Unicode::nonascii_to_utf8(val, seq);
-		s.replace(amp_pos, end - amp, seq, len);
-	    }
-	    s_end = s.end();
-	    // We've modified the string, so the iterators are no longer
-	    // valid...
-	    amp = s.begin() + amp_pos + 1;
-	} else {
-	    amp = end;
-	}
-    }
-}
-
-void
-HtmlParser::parse_html(const string &body)
-{
-    in_script = false;
-
-    parameters.clear();
-    string::const_iterator start = body.begin();
-
-    while (true) {
-	// Skip through until we find an HTML tag, a comment, or the end of
-	// document.  Ignore isolated occurrences of `<' which don't start
-	// a tag or comment.
-	string::const_iterator p = start;
-	while (true) {
-	    p = find(p, body.end(), '<');
-	    if (p == body.end()) break;
-	    unsigned char ch = *(p + 1);
-
-	    // Tag, closing tag, or comment (or SGML declaration).
-	    if ((!in_script && isalpha(ch)) || ch == '/' || ch == '!') break;
-
-	    if (ch == '?') {
-		// PHP code or XML declaration.
-		// XML declaration is only valid at the start of the first line.
-		// FIXME: need to deal with BOMs...
-		if (p != body.begin() || body.size() < 20) break;
-
-		// XML declaration looks something like this:
-		// <?xml version="1.0" encoding="UTF-8"?>
-		if (p[2] != 'x' || p[3] != 'm' || p[4] != 'l') break;
-		if (strchr(" \t\r\n", p[5]) == NULL) break;
-
-		string::const_iterator decl_end = find(p + 6, body.end(), '?');
-		if (decl_end == body.end()) break;
-
-		// Default charset for XML is UTF-8.
-		charset = "UTF-8";
-
-		string decl(p + 6, decl_end);
-		size_t enc = decl.find("encoding");
-		if (enc == string::npos) break;
-
-		enc = decl.find_first_not_of(" \t\r\n", enc + 8);
-		if (enc == string::npos || enc == decl.size()) break;
-
-		if (decl[enc] != '=') break;
-		
-		enc = decl.find_first_not_of(" \t\r\n", enc + 1);
-		if (enc == string::npos || enc == decl.size()) break;
-
-		if (decl[enc] != '"' && decl[enc] != '\'') break;
-
-		char quote = decl[enc++];
-		size_t enc_end = decl.find(quote, enc);
-
-		if (enc != string::npos)
-		    charset = decl.substr(enc, enc_end - enc);
-
-		break;
-	    }
-	    p++;
-	}
-
-	// Process text up to start of tag.
-	if (p > start) {
-	    string text = body.substr(start - body.begin(), p - start);
-	    // convert_to_utf8(text, charset);
-	    decode_entities(text);
-	    process_text(text);
-	}
-
-	if (p == body.end()) break;
-
-	start = p + 1;
-
-	if (start == body.end()) break;
-
-	if (*start == '!') {
-	    if (++start == body.end()) break;
-	    if (++start == body.end()) break;
-	    // comment or SGML declaration
-	    if (*(start - 1) == '-' && *start == '-') {
-		++start;
-		string::const_iterator close = find(start, body.end(), '>');
-		// An unterminated comment swallows rest of document
-		// (like Netscape, but unlike MSIE IIRC)
-		if (close == body.end()) break;
-
-		p = close;
-		// look for -->
-		while (p != body.end() && (*(p - 1) != '-' || *(p - 2) != '-'))
-		    p = find(p + 1, body.end(), '>');
-
-		if (p != body.end()) {
-		    // Check for htdig's "ignore this bit" comments.
-		    if (p - start == 15 && string(start, p - 2) == "htdig_noindex") {
-			string::size_type i;
-			i = body.find("<!--/htdig_noindex-->", p + 1 - body.begin());
-			if (i == string::npos) break;
-			start = body.begin() + i + 21;
-			continue;
-		    }
-		    // If we found --> skip to there.
-		    start = p;
-		} else {
-		    // Otherwise skip to the first > we found (as Netscape does).
-		    start = close;
-		}
-	    } else {
-		// just an SGML declaration, perhaps giving the DTD - ignore it
-		start = find(start - 1, body.end(), '>');
-		if (start == body.end()) break;
-	    }
-	    ++start;
-	} else if (*start == '?') {
-	    if (++start == body.end()) break;
-	    // PHP - swallow until ?> or EOF
-	    start = find(start + 1, body.end(), '>');
-
-	    // look for ?>
-	    while (start != body.end() && *(start - 1) != '?')
-		start = find(start + 1, body.end(), '>');
-
-	    // unterminated PHP swallows rest of document (rather arbitrarily
-	    // but it avoids polluting the database when things go wrong)
-	    if (start != body.end()) ++start;
-	} else {
-	    // opening or closing tag
-	    int closing = 0;
-
-	    if (*start == '/') {
-		closing = 1;
-		start = find_if(start + 1, body.end(), p_notwhitespace);
-	    }
-
-	    p = start;
-	    start = find_if(start, body.end(), p_nottag);
-	    string tag = body.substr(p - body.begin(), start - p);
-	    // convert tagname to lowercase
-	    lowercase_string(tag);
-
-	    if (closing) {
-		closing_tag(tag);
-		if (in_script && tag == "script") in_script = false;
-
-		/* ignore any bogus parameters on closing tags */
-		p = find(start, body.end(), '>');
-		if (p == body.end()) break;
-		start = p + 1;
-	    } else {
-		// FIXME: parse parameters lazily.
-		while (start < body.end() && *start != '>') {
-		    string name, value;
-
-		    p = find_if(start, body.end(), p_whitespaceeqgt);
-
-		    name.assign(body, start - body.begin(), p - start);
-
-		    p = find_if(p, body.end(), p_notwhitespace);
-
-		    start = p;
-		    if (start != body.end() && *start == '=') {
-			start = find_if(start + 1, body.end(), p_notwhitespace);
-
-			p = body.end();
-
-			int quote = *start;
-			if (quote == '"' || quote == '\'') {
-			    start++;
-			    p = find(start, body.end(), quote);
-			}
-
-			if (p == body.end()) {
-			    // unquoted or no closing quote
-			    p = find_if(start, body.end(), p_whitespacegt);
-			}
-			value.assign(body, start - body.begin(), p - start);
-			start = find_if(p, body.end(), p_notwhitespace);
-
-			if (!name.empty()) {
-			    // convert parameter name to lowercase
-			    lowercase_string(name);
-			    // in case of multiple entries, use the first
-			    // (as Netscape does)
-			    parameters.insert(make_pair(name, value));
-			}
-		    }
-		}
-#if 0
-		cout << "<" << tag;
-		map<string, string>::const_iterator x;
-		for (x = parameters.begin(); x != parameters.end(); x++) {
-		    cout << " " << x->first << "=\"" << x->second << "\"";
-		}
-		cout << ">\n";
-#endif
-		opening_tag(tag);
-		parameters.clear();
-
-		// In <script> tags we ignore opening tags to avoid problems
-		// with "a<b".
-		if (tag == "script") in_script = true;
-
-		if (start != body.end() && *start == '>') ++start;
-	    }
-	}
-    }
-}

src/common/kiwix/xapian/htmlparse.h

@@ -1,49 +0,0 @@
-/* htmlparse.h: simple HTML parser for omega indexer
- *
- * Copyright 1999,2000,2001 BrightStation PLC
- * Copyright 2002,2006,2008 Olly Betts
- *
- * 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 2 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, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
- * USA
- */
-
-#ifndef OMEGA_INCLUDED_HTMLPARSE_H
-#define OMEGA_INCLUDED_HTMLPARSE_H
-
-#include <string>
-#include <map>
-
-using std::string;
-using std::map;
-
-class HtmlParser {
-	map<string, string> parameters;
-    protected:
-	void decode_entities(string &s);
-	bool in_script;
-	string charset;
-	static map<string, unsigned int> named_ents;
-
-	bool get_parameter(const string & param, string & value);
-    public:
-	virtual void process_text(const string &/*text*/) { }
-	virtual void opening_tag(const string &/*tag*/) { }
-	virtual void closing_tag(const string &/*tag*/) { }
-	virtual void parse_html(const string &text);
-	HtmlParser();
-	virtual ~HtmlParser() { }
-};
-
-#endif // OMEGA_INCLUDED_HTMLPARSE_H

src/common/kiwix/xapian/myhtmlparse.cc

@@ -1,302 +0,0 @@
-/* myhtmlparse.cc: subclass of HtmlParser for extracting text.
- *
- * Copyright 1999,2000,2001 BrightStation PLC
- * Copyright 2002,2003,2004,2006,2007,2008 Olly Betts
- *
- * 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 2 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, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
- * USA
- */
-
-// #include <config.h>
-
-#include "myhtmlparse.h"
-
-// #include "utf8convert.h"
-
-#include <ctype.h>
-#include <string.h>
-
-inline void
-lowercase_string(string &str)
-{
-    for (string::iterator i = str.begin(); i != str.end(); ++i) {
-	*i = tolower(static_cast<unsigned char>(*i));
-    }
-}
-
-void
-MyHtmlParser::parse_html(const string &text, const string &charset_,
-			 bool charset_from_meta_)
-{
-    charset = charset_;
-    charset_from_meta = charset_from_meta_;
-    HtmlParser::parse_html(text);
-}
-
-void
-MyHtmlParser::process_text(const string &text)
-{
-    if (!text.empty() && !in_script_tag && !in_style_tag) {
-	string::size_type b = text.find_first_not_of(WHITESPACE);
-	if (b) pending_space = true;
-	while (b != string::npos) {
-	    if (pending_space && !dump.empty()) dump += ' ';
-	    string::size_type e = text.find_first_of(WHITESPACE, b);
-	    pending_space = (e != string::npos);
-	    if (!pending_space) {
-		dump.append(text.data() + b, text.size() - b);
-		return;
-	    }
-	    dump.append(text.data() + b, e - b);
-	    b = text.find_first_not_of(WHITESPACE, e + 1);
-	}
-    }
-}
-
-void
-MyHtmlParser::opening_tag(const string &tag)
-{
-    if (tag.empty()) return;
-    switch (tag[0]) {
-	case 'a':
-	    if (tag == "address") pending_space = true;
-	    break;
-	case 'b':
-	    if (tag == "body") {
-		dump.resize(0);
-		break;
-	    }
-	    if (tag == "blockquote" || tag == "br") pending_space = true;
-	    break;
-	case 'c':
-	    if (tag == "center") pending_space = true;
-	    break;
-	case 'd':
-	    if (tag == "dd" || tag == "dir" || tag == "div" || tag == "dl" ||
-		tag == "dt") pending_space = true;
-	    break;
-	case 'e':
-	    if (tag == "embed") pending_space = true;
-	    break;
-	case 'f':
-	    if (tag == "fieldset" || tag == "form") pending_space = true;
-	    break;
-	case 'h':
-	    // hr, and h1, ..., h6
-	    if (tag.length() == 2 && strchr("r123456", tag[1]))
-		pending_space = true;
-	    break;
-	case 'i':
-	    if (tag == "iframe" || tag == "img" || tag == "isindex" ||
-		tag == "input") pending_space = true;
-	    break;
-	case 'k':
-	    if (tag == "keygen") pending_space = true;
-	    break;
-	case 'l':
-	    if (tag == "legend" || tag == "li" || tag == "listing")
-		pending_space = true;
-	    break;
-	case 'm':
-	    if (tag == "meta") {
-		string content;
-		if (get_parameter("content", content)) {
-		    string name;
-		    if (get_parameter("name", name)) {
-			lowercase_string(name);
-			if (name == "description") {
-			    if (sample.empty()) {
-				swap(sample, content);
-				// convert_to_utf8(sample, charset);
-				decode_entities(sample);
-			    }
-			} else if (name == "keywords") {
-			    if (!keywords.empty()) keywords += ' ';
-			    // convert_to_utf8(content, charset);
-			    decode_entities(content);
-			    keywords += content;
-			} else if (name == "robots") {
-			    decode_entities(content);
-			    lowercase_string(content);
-			    if (content.find("none") != string::npos ||
-				content.find("noindex") != string::npos) {
-				indexing_allowed = false;
-				throw true;
-			    }
-			}
-			break;
-		    }
-		    // If the current charset came from a meta tag, don't
-		    // force reparsing again!
-		    if (charset_from_meta) break;
-		    string hdr;
-		    if (get_parameter("http-equiv", hdr)) {
-			lowercase_string(hdr);
-			if (hdr == "content-type") {
-			    lowercase_string(content);
-			    size_t start = content.find("charset=");
-			    if (start == string::npos) break;
-			    start += 8;
-			    if (start == content.size()) break;
-			    size_t end = start;
-			    if (content[start] != '"') {
-				while (end < content.size()) {
-				    unsigned char ch = content[end];
-				    if (ch <= 32 || ch >= 127 ||
-					strchr(";()<>@,:\\\"/[]?={}", ch))
-					break;
-				    ++end;
-				}
-			    } else {
-				++start;
-				++end;
-				while (end < content.size()) {
-				    unsigned char ch = content[end];
-				    if (ch == '"') break;
-				    if (ch == '\\') content.erase(end, 1);
-				    ++end;
-				}
-			    }
-			    string newcharset(content, start, end - start);
-			    if (charset != newcharset) {
-				throw newcharset;
-			    }
-			}
-		    }
-		    break;
-		}
-		if (charset_from_meta) break;
-		string newcharset;
-		if (get_parameter("charset", newcharset)) {
-		    // HTML5 added: <meta charset="...">
-		    lowercase_string(newcharset);
-		    if (charset != newcharset) {
-			throw newcharset;
-		    }
-		}
-		break;
-	    }
-	    if (tag == "marquee" || tag == "menu" || tag == "multicol")
-		pending_space = true;
-	    break;
-	case 'o':
-	    if (tag == "ol" || tag == "option") pending_space = true;
-	    break;
-	case 'p':
-	    if (tag == "p" || tag == "pre" || tag == "plaintext")
-		pending_space = true;
-	    break;
-	case 'q':
-	    if (tag == "q") pending_space = true;
-	    break;
-	case 's':
-	    if (tag == "style") {
-		in_style_tag = true;
-		break;
-	    }
-	    if (tag == "script") {
-		in_script_tag = true;
-		break;
-	    }
-	    if (tag == "select") pending_space = true;
-	    break;
-	case 't':
-	    if (tag == "table" || tag == "td" || tag == "textarea" ||
-		tag == "th") pending_space = true;
-	    break;
-	case 'u':
-	    if (tag == "ul") pending_space = true;
-	    break;
-	case 'x':
-	    if (tag == "xmp") pending_space = true;
-	    break;
-    }
-}
-
-void
-MyHtmlParser::closing_tag(const string &tag)
-{
-    if (tag.empty()) return;
-    switch (tag[0]) {
-	case 'a':
-	    if (tag == "address") pending_space = true;
-	    break;
-	case 'b':
-	    if (tag == "body") {
-		throw true;
-	    }
-	    if (tag == "blockquote" || tag == "br") pending_space = true;
-	    break;
-	case 'c':
-	    if (tag == "center") pending_space = true;
-	    break;
-	case 'd':
-	    if (tag == "dd" || tag == "dir" || tag == "div" || tag == "dl" ||
-		tag == "dt") pending_space = true;
-	    break;
-	case 'f':
-	    if (tag == "fieldset" || tag == "form") pending_space = true;
-	    break;
-	case 'h':
-	    // hr, and h1, ..., h6
-	    if (tag.length() == 2 && strchr("r123456", tag[1]))
-		pending_space = true;
-	    break;
-	case 'i':
-	    if (tag == "iframe") pending_space = true;
-	    break;
-	case 'l':
-	    if (tag == "legend" || tag == "li" || tag == "listing")
-		pending_space = true;
-	    break;
-	case 'm':
-	    if (tag == "marquee" || tag == "menu") pending_space = true;
-	    break;
-	case 'o':
-	    if (tag == "ol" || tag == "option") pending_space = true;
-	    break;
-	case 'p':
-	    if (tag == "p" || tag == "pre") pending_space = true;
-	    break;
-	case 'q':
-	    if (tag == "q") pending_space = true;
-	    break;
-	case 's':
-	    if (tag == "style") {
-		in_style_tag = false;
-		break;
-	    }
-	    if (tag == "script") {
-		in_script_tag = false;
-		break;
-	    }
-	    if (tag == "select") pending_space = true;
-	    break;
-	case 't':
-	    if (tag == "title") {
-		if (title.empty()) swap(title, dump);
-		break;
-	    }
-	    if (tag == "table" || tag == "td" || tag == "textarea" ||
-		tag == "th") pending_space = true;
-	    break;
-	case 'u':
-	    if (tag == "ul") pending_space = true;
-	    break;
-	case 'x':
-	    if (tag == "xmp") pending_space = true;
-	    break;
-    }
-}

src/common/kiwix/xapian/myhtmlparse.h

@@ -1,65 +0,0 @@
-/* myhtmlparse.h: subclass of HtmlParser for extracting text
- *
- * Copyright 1999,2000,2001 BrightStation PLC
- * Copyright 2002,2003,2004,2006,2008 Olly Betts
- *
- * 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 2 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, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301
- * USA
- */
-
-#ifndef OMEGA_INCLUDED_MYHTMLPARSE_H
-#define OMEGA_INCLUDED_MYHTMLPARSE_H
-
-#include "htmlparse.h"
-
-// FIXME: Should we include \xa0 which is non-breaking space in iso-8859-1, but
-// not in all charsets and perhaps spans of all \xa0 should become a single
-// \xa0?
-#define WHITESPACE " \t\n\r"
-
-class MyHtmlParser : public HtmlParser {
-    public:
-	bool in_script_tag;
-	bool in_style_tag;
-	bool pending_space;
-	bool indexing_allowed;
-	bool charset_from_meta;
-	string title, sample, keywords, dump;
-	void process_text(const string &text);
-	void opening_tag(const string &tag);
-	void closing_tag(const string &tag);
-	void parse_html(const string &text, const string &charset_,
-			bool charset_from_meta_);
-	MyHtmlParser() :
-		in_script_tag(false),
-		in_style_tag(false),
-		pending_space(false),
-		indexing_allowed(true),
-		charset_from_meta(false) { }
-
-	void reset() {
-	    in_script_tag = false;
-	    in_style_tag = false;
-	    pending_space = false;
-	    indexing_allowed = true;
-	    charset_from_meta = false;
-	    title.resize(0);
-	    sample.resize(0);
-	    keywords.resize(0);
-	    dump.resize(0);
-	}
-};
-
-#endif // OMEGA_INCLUDED_MYHTMLPARSE_H

src/common/kiwix/xapian/namedentities.h

@@ -1,279 +0,0 @@
-/* namedentities.h: named HTML entities.
- *
- * Copyright (C) 2006,2007 Olly Betts
- *
- * 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 2 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, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA
- */
-
-#ifndef OMEGA_INCLUDED_NAMEDENTITIES_H
-#define OMEGA_INCLUDED_NAMEDENTITIES_H
-
-// Names and values from: "Character entity references in HTML 4"
-// http://www.w3.org/TR/html4/sgml/entities.html
-{ "quot", 34 },
-{ "amp", 38 },
-{ "apos", 39 }, // Not in HTML 4 list but used in OpenOffice XML.
-{ "lt", 60 },
-{ "gt", 62 },
-{ "nbsp", 160 },
-{ "iexcl", 161 },
-{ "cent", 162 },
-{ "pound", 163 },
-{ "curren", 164 },
-{ "yen", 165 },
-{ "brvbar", 166 },
-{ "sect", 167 },
-{ "uml", 168 },
-{ "copy", 169 },
-{ "ordf", 170 },
-{ "laquo", 171 },
-{ "not", 172 },
-{ "shy", 173 },
-{ "reg", 174 },
-{ "macr", 175 },
-{ "deg", 176 },
-{ "plusmn", 177 },
-{ "sup2", 178 },
-{ "sup3", 179 },
-{ "acute", 180 },
-{ "micro", 181 },
-{ "para", 182 },
-{ "middot", 183 },
-{ "cedil", 184 },
-{ "sup1", 185 },
-{ "ordm", 186 },
-{ "raquo", 187 },
-{ "frac14", 188 },
-{ "frac12", 189 },
-{ "frac34", 190 },
-{ "iquest", 191 },
-{ "Agrave", 192 },
-{ "Aacute", 193 },
-{ "Acirc", 194 },
-{ "Atilde", 195 },
-{ "Auml", 196 },
-{ "Aring", 197 },
-{ "AElig", 198 },
-{ "Ccedil", 199 },
-{ "Egrave", 200 },
-{ "Eacute", 201 },
-{ "Ecirc", 202 },
-{ "Euml", 203 },
-{ "Igrave", 204 },
-{ "Iacute", 205 },
-{ "Icirc", 206 },
-{ "Iuml", 207 },
-{ "ETH", 208 },
-{ "Ntilde", 209 },
-{ "Ograve", 210 },
-{ "Oacute", 211 },
-{ "Ocirc", 212 },
-{ "Otilde", 213 },
-{ "Ouml", 214 },
-{ "times", 215 },
-{ "Oslash", 216 },
-{ "Ugrave", 217 },
-{ "Uacute", 218 },
-{ "Ucirc", 219 },
-{ "Uuml", 220 },
-{ "Yacute", 221 },
-{ "THORN", 222 },
-{ "szlig", 223 },
-{ "agrave", 224 },
-{ "aacute", 225 },
-{ "acirc", 226 },
-{ "atilde", 227 },
-{ "auml", 228 },
-{ "aring", 229 },
-{ "aelig", 230 },
-{ "ccedil", 231 },
-{ "egrave", 232 },
-{ "eacute", 233 },
-{ "ecirc", 234 },
-{ "euml", 235 },
-{ "igrave", 236 },
-{ "iacute", 237 },
-{ "icirc", 238 },
-{ "iuml", 239 },
-{ "eth", 240 },
-{ "ntilde", 241 },
-{ "ograve", 242 },
-{ "oacute", 243 },
-{ "ocirc", 244 },
-{ "otilde", 245 },
-{ "ouml", 246 },
-{ "divide", 247 },
-{ "oslash", 248 },
-{ "ugrave", 249 },
-{ "uacute", 250 },
-{ "ucirc", 251 },
-{ "uuml", 252 },
-{ "yacute", 253 },
-{ "thorn", 254 },
-{ "yuml", 255 },
-{ "OElig", 338 },
-{ "oelig", 339 },
-{ "Scaron", 352 },
-{ "scaron", 353 },
-{ "Yuml", 376 },
-{ "fnof", 402 },
-{ "circ", 710 },
-{ "tilde", 732 },
-{ "Alpha", 913 },
-{ "Beta", 914 },
-{ "Gamma", 915 },
-{ "Delta", 916 },
-{ "Epsilon", 917 },
-{ "Zeta", 918 },
-{ "Eta", 919 },
-{ "Theta", 920 },
-{ "Iota", 921 },
-{ "Kappa", 922 },
-{ "Lambda", 923 },
-{ "Mu", 924 },
-{ "Nu", 925 },
-{ "Xi", 926 },
-{ "Omicron", 927 },
-{ "Pi", 928 },
-{ "Rho", 929 },
-{ "Sigma", 931 },
-{ "Tau", 932 },
-{ "Upsilon", 933 },
-{ "Phi", 934 },
-{ "Chi", 935 },
-{ "Psi", 936 },
-{ "Omega", 937 },
-{ "alpha", 945 },
-{ "beta", 946 },
-{ "gamma", 947 },
-{ "delta", 948 },
-{ "epsilon", 949 },
-{ "zeta", 950 },
-{ "eta", 951 },
-{ "theta", 952 },
-{ "iota", 953 },
-{ "kappa", 954 },
-{ "lambda", 955 },
-{ "mu", 956 },
-{ "nu", 957 },
-{ "xi", 958 },
-{ "omicron", 959 },
-{ "pi", 960 },
-{ "rho", 961 },
-{ "sigmaf", 962 },
-{ "sigma", 963 },
-{ "tau", 964 },
-{ "upsilon", 965 },
-{ "phi", 966 },
-{ "chi", 967 },
-{ "psi", 968 },
-{ "omega", 969 },
-{ "thetasym", 977 },
-{ "upsih", 978 },
-{ "piv", 982 },
-{ "ensp", 8194 },
-{ "emsp", 8195 },
-{ "thinsp", 8201 },
-{ "zwnj", 8204 },
-{ "zwj", 8205 },
-{ "lrm", 8206 },
-{ "rlm", 8207 },
-{ "ndash", 8211 },
-{ "mdash", 8212 },
-{ "lsquo", 8216 },
-{ "rsquo", 8217 },
-{ "sbquo", 8218 },
-{ "ldquo", 8220 },
-{ "rdquo", 8221 },
-{ "bdquo", 8222 },
-{ "dagger", 8224 },
-{ "Dagger", 8225 },
-{ "bull", 8226 },
-{ "hellip", 8230 },
-{ "permil", 8240 },
-{ "prime", 8242 },
-{ "Prime", 8243 },
-{ "lsaquo", 8249 },
-{ "rsaquo", 8250 },
-{ "oline", 8254 },
-{ "frasl", 8260 },
-{ "euro", 8364 },
-{ "image", 8465 },
-{ "weierp", 8472 },
-{ "real", 8476 },
-{ "trade", 8482 },
-{ "alefsym", 8501 },
-{ "larr", 8592 },
-{ "uarr", 8593 },
-{ "rarr", 8594 },
-{ "darr", 8595 },
-{ "harr", 8596 },
-{ "crarr", 8629 },
-{ "lArr", 8656 },
-{ "uArr", 8657 },
-{ "rArr", 8658 },
-{ "dArr", 8659 },
-{ "hArr", 8660 },
-{ "forall", 8704 },
-{ "part", 8706 },
-{ "exist", 8707 },
-{ "empty", 8709 },
-{ "nabla", 8711 },
-{ "isin", 8712 },
-{ "notin", 8713 },
-{ "ni", 8715 },
-{ "prod", 8719 },
-{ "sum", 8721 },
-{ "minus", 8722 },
-{ "lowast", 8727 },
-{ "radic", 8730 },
-{ "prop", 8733 },
-{ "infin", 8734 },
-{ "ang", 8736 },
-{ "and", 8743 },
-{ "or", 8744 },
-{ "cap", 8745 },
-{ "cup", 8746 },
-{ "int", 8747 },
-{ "there4", 8756 },
-{ "sim", 8764 },
-{ "cong", 8773 },
-{ "asymp", 8776 },
-{ "ne", 8800 },
-{ "equiv", 8801 },
-{ "le", 8804 },
-{ "ge", 8805 },
-{ "sub", 8834 },
-{ "sup", 8835 },
-{ "nsub", 8836 },
-{ "sube", 8838 },
-{ "supe", 8839 },
-{ "oplus", 8853 },
-{ "otimes", 8855 },
-{ "perp", 8869 },
-{ "sdot", 8901 },
-{ "lceil", 8968 },
-{ "rceil", 8969 },
-{ "lfloor", 8970 },
-{ "rfloor", 8971 },
-{ "lang", 9001 },
-{ "rang", 9002 },
-{ "loz", 9674 },
-{ "spades", 9824 },
-{ "clubs", 9827 },
-{ "hearts", 9829 },
-{ "diams", 9830 },
-
-#endif // OMEGA_INCLUDED_NAMEDENTITIES_H

src/common/kiwix/xapianIndexer.cpp

@@ -1,111 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "xapianIndexer.h"
-
-namespace kiwix {
-
-  /* Constructor */
-  XapianIndexer::XapianIndexer() {
-    /*
-    stemmer(Xapian::Stem("french")) {
-    this->indexer.set_stemmer(this->stemmer);
-    */ 
-  }
-
-  void XapianIndexer::indexingPrelude(const string indexPath) {
-    this->writableDatabase = Xapian::WritableDatabase(indexPath+".tmp", Xapian::DB_CREATE_OR_OVERWRITE | Xapian::DB_BACKEND_GLASS);
-    this->writableDatabase.begin_transaction(true);
-
-    /* Insert the stopwords */
-    if (!this->stopWords.empty()) {
-      std::vector<std::string>::iterator it = this->stopWords.begin();
-      for( ; it != this->stopWords.end(); ++it) {
-	this->stopper.add(*it);
-      }
-
-      this->indexer.set_stopper(&(this->stopper));
-    }
-  }
-  
-  void XapianIndexer::index(const string &url, 
-			    const string &title, 
-			    const string &unaccentedTitle,
-			    const string &keywords, 
-			    const string &content,
-			    const string &snippet,
-			    const string &size,
-			    const string &wordCount) {
-    
-    /* Put the data in the document */
-    Xapian::Document currentDocument; 
-    currentDocument.clear_values();
-    currentDocument.add_value(0, title);
-    currentDocument.add_value(1, snippet);
-    currentDocument.add_value(2, size);
-    currentDocument.add_value(3, wordCount);
-    currentDocument.set_data(url);
-    indexer.set_document(currentDocument);
-
-    /* Index the title */
-    if (!unaccentedTitle.empty()) {
-      this->indexer.index_text_without_positions(unaccentedTitle, this->getTitleBoostFactor(content.size()));
-    }
-    
-    /* Index the keywords */
-    if (!keywords.empty()) {
-      this->indexer.index_text_without_positions(keywords, keywordsBoostFactor);
-    }
-    
-    /* Index the content */
-    if (!content.empty()) {
-      this->indexer.index_text_without_positions(content);
-    }
-    
-    /* add to the database */
-    this->writableDatabase.add_document(currentDocument);
-  }
-  
-  void XapianIndexer::flush() {
-    this->writableDatabase.commit_transaction();
-    this->writableDatabase.begin_transaction(true);
-  }
-
-  void XapianIndexer::indexingPostlude(const string indexPath) {
-    this->flush();
-    this->writableDatabase.commit_transaction();
-#ifdef _WIN32
-    this->writableDatabase.close();
-#endif
-    
-    /* Compacting the index */
-    Xapian::Compactor compactor;
-    try {
-      Xapian::Database src;
-      src.add_database(Xapian::Database(indexPath+".tmp"));
-      src.compact(indexPath, Xapian::Compactor::FULL | Xapian::DBCOMPACT_SINGLE_FILE, 0, compactor);
-    } catch (const Xapian::Error &error) {
-      cerr << indexPath << ": " << error.get_description() << endl;
-      exit(1);
-    } catch (const char * msg) {
-      cerr << indexPath << ": " << msg << endl;
-      exit(1);
-    }
-  }
-}

src/common/kiwix/xapianIndexer.h

@@ -1,56 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_XAPIAN_INDEXER_H
-#define KIWIX_XAPIAN_INDEXER_H
-
-#include <xapian.h>
-#include "indexer.h"
-
-using namespace std;
-
-namespace kiwix {
-  
-  class XapianIndexer : public Indexer {
-    
-  public:
-    XapianIndexer();
-    
-  protected:
-    void indexingPrelude(const string indexPath);
-    void index(const string &url, 
-	       const string &title, 
-	       const string &unaccentedTitle,
-	       const string &keywords, 
-	       const string &content,
-	       const string &snippet,
-	       const string &size,
-	       const string &wordCount);
-    void flush();
-    void indexingPostlude(const string indexPath);
-    
-    Xapian::WritableDatabase writableDatabase;
-    Xapian::Stem stemmer;
-    Xapian::SimpleStopper stopper;
-    Xapian::TermGenerator indexer;
-  };
-
-}
-
-#endif

src/common/kiwix/xapianSearcher.cpp

@@ -1,99 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#include "xapianSearcher.h"
-#include <zim/zim.h>
-#include <zim/file.h>
-#include <zim/article.h>
-#include <zim/error.h>
-#include <sys/types.h>
-#include <unistd.h>
-
-namespace kiwix {
-
-  /* Constructor */
-  XapianSearcher::XapianSearcher(const string &xapianDirectoryPath) 
-    : Searcher(),
-      stemmer(Xapian::Stem("english")) {
-    this->openIndex(xapianDirectoryPath);
-  }
-
-  /* Open Xapian readable database */
-  void XapianSearcher::openIndex(const string &directoryPath) {
-    try
-    {
-      zim::File zimFile = zim::File(directoryPath);
-      zim::Article xapianArticle = zimFile.getArticle('Z', "/fulltextIndex/xapian");
-      if (!xapianArticle.good())
-	throw NoXapianIndexInZim();
-      zim::offset_type dbOffset = xapianArticle.getOffset();
-      int databasefd = open(directoryPath.c_str(), O_RDONLY);
-      lseek(databasefd, dbOffset, SEEK_SET);
-      this->readableDatabase = Xapian::Database(databasefd);
-    } catch (...) {
-      this->readableDatabase = Xapian::Database(directoryPath);
-    }
-  }
-  
-  /* Close Xapian writable database */
-  void XapianSearcher::closeIndex() {
-    return;
-  }
-  
-  /* Search strings in the database */
-  void XapianSearcher::searchInIndex(string &search, const unsigned int resultStart, 
-				     const unsigned int resultEnd, const bool verbose) {
-    /* Create the query */
-    Xapian::QueryParser queryParser;
-    Xapian::Query query = queryParser.parse_query(search);    
-
-    /* Create the enquire object */
-    Xapian::Enquire enquire(this->readableDatabase);
-    enquire.set_query(query);
-
-    /* Get the results */
-    Xapian::MSet matches = enquire.get_mset(resultStart, resultEnd - resultStart);
-    
-    Xapian::MSetIterator i;
-    for (i = matches.begin(); i != matches.end(); ++i) {
-      Xapian::Document doc = i.get_document();
-      
-      Result result;
-      result.url = doc.get_data();
-      result.title = doc.get_value(0);
-      result.snippet = doc.get_value(1);
-      result.size = (doc.get_value(2).empty() == true ? -1 : atoi(doc.get_value(2).c_str()));
-      result.wordCount = (doc.get_value(3).empty() == true ? -1 : atoi(doc.get_value(3).c_str()));
-      result.score = i.get_percent();
-      
-      this->results.push_back(result);
-
-      if (verbose) {
-	std::cout << "Document ID " << *i << "   \t";
-	std::cout << i.get_percent() << "% ";
-	std::cout << "\t[" << doc.get_data() << "] - " << doc.get_value(0) << std::endl;
-      }
-    }
-
-    /* Update the global resultCount value*/
-    this->estimatedResultCount = matches.get_matches_estimated();
-
-    return;
-  }
-}

src/common/kiwix/xapianSearcher.h

@@ -1,53 +0,0 @@
-/*
- * Copyright 2011 Emmanuel Engelhart <kelson@kiwix.org>
- *
- * 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
- * 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, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
- */
-
-#ifndef KIWIX_XAPIAN_SEARCHER_H
-#define KIWIX_XAPIAN_SEARCHER_H
-
-#include <xapian.h>
-#include "searcher.h"
-
-using namespace std;
-
-namespace kiwix {
-
-  class NoXapianIndexInZim: public exception {
-    virtual const char* what() const throw() {
-      return "There is no fulltext index in the zim file";
-    }
-  };
-
-  class XapianSearcher : public Searcher {
-    
-  public:
-    XapianSearcher(const string &xapianDirectoryPath);
-    void searchInIndex(string &search, const unsigned int resultStart, const unsigned int resultEnd, 
-		       const bool verbose=false);
-
-  protected:
-    void closeIndex();
-    void openIndex(const string &xapianDirectoryPath);
-
-    Xapian::Database readableDatabase;
-    Xapian::Stem stemmer;
-  };
-
-}
-
-#endif