pax_global_header 0000666 0000000 0000000 00000000064 14364016463 0014521 g ustar 00root root 0000000 0000000 52 comment=8f1b434a80608e1e313d38d263ed7c79c9ee75a9
wikiextractor-3.0.7/ 0000775 0000000 0000000 00000000000 14364016463 0014427 5 ustar 00root root 0000000 0000000 wikiextractor-3.0.7/.github/ 0000775 0000000 0000000 00000000000 14364016463 0015767 5 ustar 00root root 0000000 0000000 wikiextractor-3.0.7/.github/workflows/ 0000775 0000000 0000000 00000000000 14364016463 0020024 5 ustar 00root root 0000000 0000000 wikiextractor-3.0.7/.github/workflows/python-publish.yml 0000664 0000000 0000000 00000001540 14364016463 0023534 0 ustar 00root root 0000000 0000000 # This workflow will upload a Python Package using Twine when a release is created
# For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
name: Upload Python Package
on:
release:
types: [created]
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v2
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: '3.x'
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install setuptools wheel twine
- name: Build and publish
env:
TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
run: |
python setup.py sdist bdist_wheel
twine upload dist/*
wikiextractor-3.0.7/.gitignore 0000664 0000000 0000000 00000000656 14364016463 0016426 0 ustar 00root root 0000000 0000000 *.py[cod]
# C extensions
*.so
# Packages
*.egg
*.egg-info
dist
build
eggs
parts
bin
var
sdist
develop-eggs
.installed.cfg
lib
lib64
# Installer logs
pip-log.txt
# Unit test / coverage reports
.coverage
.tox
nosetests.xml
# Translations
*.mo
# Mr Developer
.mr.developer.cfg
.project
.pydevproject
/docs/_build
.idea
*.iml
.travis-solo
G*
*.db
*.mdb
# Vim
[._]*.s[a-w][a-z]
[._]s[a-w][a-z]
*.un~
Session.vim
.netrwhist
*~
wikiextractor-3.0.7/LICENSE 0000664 0000000 0000000 00000103333 14364016463 0015437 0 ustar 00root root 0000000 0000000 GNU AFFERO GENERAL PUBLIC LICENSE
Version 3, 19 November 2007
Copyright (C) 2007 Free Software Foundation, Inc.
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
Copyright (C)
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published
by the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see .
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
.
wikiextractor-3.0.7/README.md 0000664 0000000 0000000 00000014735 14364016463 0015720 0 ustar 00root root 0000000 0000000 # WikiExtractor
[WikiExtractor.py](http://medialab.di.unipi.it/wiki/Wikipedia_Extractor) is a Python script that extracts and cleans text from a [Wikipedia database backup dump](https://dumps.wikimedia.org/), e.g. https://dumps.wikimedia.org/enwiki/latest/enwiki-latest-pages-articles.xml.bz2 for English.
The tool is written in Python and requires Python 3 but no additional library.
**Warning**: problems have been reported on Windows due to poor support for `StringIO` in the Python implementation on Windows.
For further information, see the [Wiki](https://github.com/attardi/wikiextractor/wiki).
# Wikipedia Cirrus Extractor
`cirrus-extractor.py` is a version of the script that performs extraction from a Wikipedia Cirrus dump.
Cirrus dumps contain text with already expanded templates.
Cirrus dumps are available at:
[cirrussearch](http://dumps.wikimedia.org/other/cirrussearch/).
# Details
WikiExtractor performs template expansion by preprocessing the whole dump and extracting template definitions.
In order to speed up processing:
- multiprocessing is used for dealing with articles in parallel
- a cache is kept of parsed templates (only useful for repeated extractions).
## Installation
The script may be invoked directly:
python -m wikiextractor.WikiExtractor
It can also be installed from `PyPi` by doing:
pip install wikiextractor
or locally with:
(sudo) python setup.py install
The installer also installs two scripts for direct invocation:
wikiextractor (equivalent to python -m wikiextractor.WikiExtractor)
extractPage (to extract a single page from a dump)
## Usage
### Wikiextractor
The script is invoked with a Wikipedia dump file as an argument:
python -m wikiextractor.WikiExtractor [--templates ]
The option `--templates` extracts the templates to a local file, which can be reloaded to reduce the time to perform extraction.
The output is stored in several files of similar size in a given directory.
Each file will contains several documents in this [document format](https://github.com/attardi/wikiextractor/wiki/File-Format).
```
usage: wikiextractor [-h] [-o OUTPUT] [-b n[KMG]] [-c] [--json] [--html] [-l] [-ns ns1,ns2]
[--templates TEMPLATES] [--no-templates] [--html-safe HTML_SAFE] [--processes PROCESSES]
[-q] [--debug] [-a] [-v]
input
Wikipedia Extractor:
Extracts and cleans text from a Wikipedia database dump and stores output in a
number of files of similar size in a given directory.
Each file will contain several documents in the format:
...
If the program is invoked with the --json flag, then each file will
contain several documents formatted as json ojects, one per line, with
the following structure
{"id": "", "revid": "", "url": "", "title": "", "text": "..."}
The program performs template expansion by preprocesssng the whole dump and
collecting template definitions.
positional arguments:
input XML wiki dump file
optional arguments:
-h, --help show this help message and exit
--processes PROCESSES
Number of processes to use (default 79)
Output:
-o OUTPUT, --output OUTPUT
directory for extracted files (or '-' for dumping to stdout)
-b n[KMG], --bytes n[KMG]
maximum bytes per output file (default 1M)
-c, --compress compress output files using bzip
--json write output in json format instead of the default format
Processing:
--html produce HTML output, subsumes --links
-l, --links preserve links
-ns ns1,ns2, --namespaces ns1,ns2
accepted namespaces
--templates TEMPLATES
use or create file containing templates
--no-templates Do not expand templates
--html-safe HTML_SAFE
use to produce HTML safe output within ...
Special:
-q, --quiet suppress reporting progress info
--debug print debug info
-a, --article analyze a file containing a single article (debug option)
-v, --version print program version
```
Saving templates to a file will speed up performing extraction the next time,
assuming template definitions have not changed.
Option `--no-templates` significantly speeds up the extractor, avoiding the cost
of expanding [MediaWiki templates](https://www.mediawiki.org/wiki/Help:Templates).
For further information, visit [the documentation](http://attardi.github.io/wikiextractor).
### Cirrus Extractor
~~~
usage: cirrus-extract.py [-h] [-o OUTPUT] [-b n[KMG]] [-c] [-ns ns1,ns2] [-q]
[-v]
input
Wikipedia Cirrus Extractor:
Extracts and cleans text from a Wikipedia Cirrus dump and stores output in a
number of files of similar size in a given directory.
Each file will contain several documents in the format:
...
positional arguments:
input Cirrus Json wiki dump file
optional arguments:
-h, --help show this help message and exit
Output:
-o OUTPUT, --output OUTPUT
directory for extracted files (or '-' for dumping to
stdin)
-b n[KMG], --bytes n[KMG]
maximum bytes per output file (default 1M)
-c, --compress compress output files using bzip
Processing:
-ns ns1,ns2, --namespaces ns1,ns2
accepted namespaces
Special:
-q, --quiet suppress reporting progress info
-v, --version print program version
~~~
### extractPage
Extract a single page from a Wikipedia dump file.
~~~
usage: extractPage [-h] [--id ID] [--template] [-v] input
Wikipedia Page Extractor:
Extracts a single page from a Wikipedia dump file.
positional arguments:
input XML wiki dump file
optional arguments:
-h, --help show this help message and exit
--id ID article number
--template template number
-v, --version print program version
~~~
## License
The code is made available under the [GNU Affero General Public License v3.0](LICENSE).
## Reference
If you find this code useful, please refer it in publications as:
~~~
@misc{Wikiextractor2015,
author = {Giusepppe Attardi},
title = {WikiExtractor},
year = {2015},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/attardi/wikiextractor}}
}
~~~
wikiextractor-3.0.7/extract.sh 0000775 0000000 0000000 00000001437 14364016463 0016445 0 ustar 00root root 0000000 0000000 #!/bin/bash
#
# NOTES
#
# - Must expand templates to avoid a large loss of content.
# - Text will not (redundantly) contain the title string.
# - Keep sections. Section title will be marked by "Section::::".
# - Keep lists. List bullets will be marked by "BULLET::::".
# - Keep tables. They're mostly garbage but can be removed later (remove "^!*").
# - Remove disambiguation pages. Right now there is no use for them.
INPUT=$1
PROCESSES=$2
TEMPLATES=$3
OUTPUT=$4
python -m wikiextractor.WikiExtractor.py $INPUT \
--json \
--processes $PROCESSES \
--templates $TEMPLATES \
--output $OUTPUT \
--bytes 1M \
--compress \
--links \
--sections \
--lists \
--keep_tables \
--min_text_length 0 \
--filter_disambig_pages
wikiextractor-3.0.7/setup.py 0000664 0000000 0000000 00000002451 14364016463 0016143 0 ustar 00root root 0000000 0000000 from setuptools import setup, find_packages
import re
from wikiextractor.WikiExtractor import __version__
def get_version(version):
if re.match(r'^\d+\.\d+$', version):
return version + '.0'
return version
with open("README.md", "r") as fh:
long_description = fh.read()
setup(
name='wikiextractor',
version=get_version(__version__),
author='Giuseppe Attardi',
author_email='attardi@gmail.com',
description='A tool for extracting plain text from Wikipedia dumps',
long_description=long_description,
long_description_content_type="text/markdown",
license='GNU Affero General Public License',
install_requires=[],
url="https://github.com/attardi/wikiextractor",
packages=find_packages(include=["wikiextractor"]),
classifiers=[
'Development Status :: 5 - Production/Stable',
'Intended Audience :: Developers',
'Topic :: Text Processing :: Linguistic',
'License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)',
'Programming Language :: Python :: 3'
],
entry_points={
"console_scripts": [
"wikiextractor = wikiextractor.WikiExtractor:main",
"extractPage = wikiextractor.extractPage:main",
]
},
python_requires='>=3.6',
)
wikiextractor-3.0.7/wikiextractor/ 0000775 0000000 0000000 00000000000 14364016463 0017326 5 ustar 00root root 0000000 0000000 wikiextractor-3.0.7/wikiextractor/WikiExtractor.py 0000775 0000000 0000000 00000054277 14364016463 0022521 0 ustar 00root root 0000000 0000000 #!/usr/bin/env python
# -*- coding: utf-8 -*-
# =============================================================================
# Version: 3.0 (January 24, 2023)
# Author: Giuseppe Attardi (attardi@di.unipi.it), University of Pisa
#
# Contributors:
# Antonio Fuschetto (fuschett@aol.com)
# Leonardo Souza (lsouza@amtera.com.br)
# Juan Manuel Caicedo (juan@cavorite.com)
# Humberto Pereira (begini@gmail.com)
# Siegfried-A. Gevatter (siegfried@gevatter.com)
# Pedro Assis (pedroh2306@gmail.com)
# Wim Muskee (wimmuskee@gmail.com)
# Radics Geza (radicsge@gmail.com)
# Nick Ulven (nulven@github)
#
# =============================================================================
# Copyright (c) 2009-2023. Giuseppe Attardi (attardi@di.unipi.it).
# =============================================================================
# This file is part of Tanl.
#
# Tanl is free software; you can redistribute it and/or modify it
# under the terms of the GNU Affero General Public License, version 3,
# as published by the Free Software Foundation.
#
# Tanl is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see .
# =============================================================================
"""Wikipedia Extractor:
Extracts and cleans text from a Wikipedia database dump and stores output in a
number of files of similar size in a given directory.
Each file will contain several documents in the format:
...
If the program is invoked with the --json flag, then each file will
contain several documents formatted as json ojects, one per line, with
the following structure
{"id": "", "revid": "", "url": "", "title": "", "text": "..."}
The program performs template expansion by preprocesssng the whole dump and
collecting template definitions.
"""
import argparse
import bz2
import logging
import os.path
import re # TODO use regex when it will be standard
import sys
from io import StringIO
from multiprocessing import Queue, get_context, cpu_count
from timeit import default_timer
from .extract import Extractor, ignoreTag, define_template, acceptedNamespaces
# ===========================================================================
# Program version
__version__ = '3.0.7'
##
# Defined in
# We include as default Template, when loading external template file.
knownNamespaces = set(['Template'])
##
# The namespace used for template definitions
# It is the name associated with namespace key=10 in the siteinfo header.
templateNamespace = ''
##
# The namespace used for module definitions
# It is the name associated with namespace key=828 in the siteinfo header.
moduleNamespace = ''
# ----------------------------------------------------------------------
# Modules
# Only minimal support
# FIXME: import Lua modules.
modules = {
'convert': {
'convert': lambda x, u, *rest: x + ' ' + u, # no conversion
}
}
# ----------------------------------------------------------------------
# Expand using WikiMedia API
# import json
# def expandTemplates(text):
# """Expand templates invoking MediaWiki API"""
# text = urlib.urlencodew(text)
# base = urlbase[:urlbase.rfind('/')]
# url = base + "/w/api.php?action=expandtemplates&format=json&text=" + text
# exp = json.loads(urllib.urlopen(url))
# return exp['expandtemplates']['*']
# ------------------------------------------------------------------------------
# Output
class NextFile():
"""
Synchronous generation of next available file name.
"""
filesPerDir = 100
def __init__(self, path_name):
self.path_name = path_name
self.dir_index = -1
self.file_index = -1
def next(self):
self.file_index = (self.file_index + 1) % NextFile.filesPerDir
if self.file_index == 0:
self.dir_index += 1
dirname = self._dirname()
if not os.path.isdir(dirname):
os.makedirs(dirname)
return self._filepath()
def _dirname(self):
char1 = self.dir_index % 26
char2 = int(self.dir_index / 26) % 26
return os.path.join(self.path_name, '%c%c' % (ord('A') + char2, ord('A') + char1))
def _filepath(self):
return '%s/wiki_%02d' % (self._dirname(), self.file_index)
class OutputSplitter():
"""
File-like object, that splits output to multiple files of a given max size.
"""
def __init__(self, nextFile, max_file_size=0, compress=True):
"""
:param nextFile: a NextFile object from which to obtain filenames
to use.
:param max_file_size: the maximum size of each file.
:para compress: whether to write data with bzip compression.
"""
self.nextFile = nextFile
self.compress = compress
self.max_file_size = max_file_size
self.file = self.open(self.nextFile.next())
def reserve(self, size):
if self.file.tell() + size > self.max_file_size:
self.close()
self.file = self.open(self.nextFile.next())
def write(self, data):
self.reserve(len(data))
if self.compress:
self.file.write(data)
else:
self.file.write(data)
def close(self):
self.file.close()
def open(self, filename):
if self.compress:
return bz2.BZ2File(filename + '.bz2', 'w')
else:
return open(filename, 'w')
# ----------------------------------------------------------------------
# READER
tagRE = re.compile(r'(.*?)<(/?\w+)[^>]*>(?:([^<]*)(<.*?>)?)?')
# 1 2 3 4
def load_templates(file, output_file=None):
"""
Load templates from :param file:.
:param output_file: file where to save templates and modules.
:return: number of templates loaded.
"""
global templateNamespace
global moduleNamespace, modulePrefix
modulePrefix = moduleNamespace + ':'
articles = 0
templates = 0
page = []
inText = False
if output_file:
output = open(output_file, 'w')
for line in file:
#line = line.decode('utf-8')
if '<' not in line: # faster than doing re.search()
if inText:
page.append(line)
continue
m = tagRE.search(line)
if not m:
continue
tag = m.group(2)
if tag == 'page':
page = []
elif tag == 'title':
title = m.group(3)
if not output_file and not templateNamespace: # do not know it yet
# we reconstruct it from the first title
colon = title.find(':')
if colon > 1:
templateNamespace = title[:colon]
Extractor.templatePrefix = title[:colon + 1]
# FIXME: should reconstruct also moduleNamespace
elif tag == 'text':
inText = True
line = line[m.start(3):m.end(3)]
page.append(line)
if m.lastindex == 4: # open-close
inText = False
elif tag == '/text':
if m.group(1):
page.append(m.group(1))
inText = False
elif inText:
page.append(line)
elif tag == '/page':
if title.startswith(Extractor.templatePrefix):
define_template(title, page)
templates += 1
# save templates and modules to file
if output_file and (title.startswith(Extractor.templatePrefix) or
title.startswith(modulePrefix)):
output.write('\n')
output.write(' %s\n' % title)
output.write(' 10\n')
output.write(' ')
for line in page:
output.write(line)
output.write(' \n')
output.write('\n')
page = []
articles += 1
if articles % 100000 == 0:
logging.info("Preprocessed %d pages", articles)
if output_file:
output.close()
logging.info("Saved %d templates to '%s'", templates, output_file)
return templates
def decode_open(filename, mode='rt', encoding='utf-8'):
"""
Open a file, decode and decompress, depending on extension `gz`, or 'bz2`.
:param filename: the file to open.
"""
ext = os.path.splitext(filename)[1]
if ext == '.gz':
import gzip
return gzip.open(filename, mode, encoding=encoding)
elif ext == '.bz2':
return bz2.open(filename, mode=mode, encoding=encoding)
else:
return open(filename, mode, encoding=encoding)
def collect_pages(text):
"""
:param text: the text of a wikipedia file dump.
"""
# we collect individual lines, since str.join() is significantly faster
# than concatenation
page = []
id = ''
revid = ''
last_id = ''
inText = False
redirect = False
for line in text:
if '<' not in line: # faster than doing re.search()
if inText:
page.append(line)
continue
m = tagRE.search(line)
if not m:
continue
tag = m.group(2)
if tag == 'page':
page = []
redirect = False
elif tag == 'id' and not id:
id = m.group(3)
elif tag == 'id' and id: #
revid = m.group(3)
elif tag == 'title':
title = m.group(3)
elif tag == 'redirect':
redirect = True
elif tag == 'text':
inText = True
line = line[m.start(3):m.end(3)]
page.append(line)
if m.lastindex == 4: # open-close
inText = False
elif tag == '/text':
if m.group(1):
page.append(m.group(1))
inText = False
elif inText:
page.append(line)
elif tag == '/page':
colon = title.find(':')
if (colon < 0 or (title[:colon] in acceptedNamespaces) and id != last_id and
not redirect and not title.startswith(templateNamespace)):
yield (id, revid, title, page)
last_id = id
id = ''
revid = ''
page = []
inText = False
redirect = False
def process_dump(input_file, template_file, out_file, file_size, file_compress,
process_count, html_safe, expand_templates=True):
"""
:param input_file: name of the wikipedia dump file; '-' to read from stdin
:param template_file: optional file with template definitions.
:param out_file: directory where to store extracted data, or '-' for stdout
:param file_size: max size of each extracted file, or None for no max (one file)
:param file_compress: whether to compress files with bzip.
:param process_count: number of extraction processes to spawn.
:html_safe: whether to convert entities in text to HTML.
:param expand_templates: whether to expand templates.
"""
global knownNamespaces
global templateNamespace
global moduleNamespace, modulePrefix
urlbase = '' # This is obtained from
input = decode_open(input_file)
# collect siteinfo
for line in input:
line = line #.decode('utf-8')
m = tagRE.search(line)
if not m:
continue
tag = m.group(2)
if tag == 'base':
# discover urlbase from the xml dump file
# /mediawiki/siteinfo/base
base = m.group(3)
urlbase = base[:base.rfind("/")]
elif tag == 'namespace':
knownNamespaces.add(m.group(3))
if re.search('key="10"', line):
templateNamespace = m.group(3)
Extractor.templatePrefix = templateNamespace + ':'
elif re.search('key="828"', line):
moduleNamespace = m.group(3)
modulePrefix = moduleNamespace + ':'
elif tag == '/siteinfo':
break
if expand_templates:
# preprocess
template_load_start = default_timer()
if template_file and os.path.exists(template_file):
logging.info("Preprocessing '%s' to collect template definitions: this may take some time.", template_file)
file = decode_open(template_file)
templates = load_templates(file)
file.close()
else:
if input_file == '-':
# can't scan then reset stdin; must error w/ suggestion to specify template_file
raise ValueError("to use templates with stdin dump, must supply explicit template-file")
logging.info("Preprocessing '%s' to collect template definitions: this may take some time.", input_file)
templates = load_templates(input, template_file)
input.close()
input = decode_open(input_file)
template_load_elapsed = default_timer() - template_load_start
logging.info("Loaded %d templates in %.1fs", templates, template_load_elapsed)
if out_file == '-':
output = sys.stdout
if file_compress:
logging.warn("writing to stdout, so no output compression (use an external tool)")
else:
nextFile = NextFile(out_file)
output = OutputSplitter(nextFile, file_size, file_compress)
# process pages
logging.info("Starting page extraction from %s.", input_file)
extract_start = default_timer()
# Parallel Map/Reduce:
# - pages to be processed are dispatched to workers
# - a reduce process collects the results, sort them and print them.
# fixes MacOS error: TypeError: cannot pickle '_io.TextIOWrapper' object
Process = get_context("fork").Process
maxsize = 10 * process_count
# output queue
output_queue = Queue(maxsize=maxsize)
# Reduce job that sorts and prints output
reduce = Process(target=reduce_process, args=(output_queue, output))
reduce.start()
# initialize jobs queue
jobs_queue = Queue(maxsize=maxsize)
# start worker processes
logging.info("Using %d extract processes.", process_count)
workers = []
for _ in range(max(1, process_count)):
extractor = Process(target=extract_process,
args=(jobs_queue, output_queue, html_safe))
extractor.daemon = True # only live while parent process lives
extractor.start()
workers.append(extractor)
# Mapper process
# we collect individual lines, since str.join() is significantly faster
# than concatenation
ordinal = 0 # page count
for id, revid, title, page in collect_pages(input):
job = (id, revid, urlbase, title, page, ordinal)
jobs_queue.put(job) # goes to any available extract_process
ordinal += 1
input.close()
# signal termination
for _ in workers:
jobs_queue.put(None)
# wait for workers to terminate
for w in workers:
w.join()
# signal end of work to reduce process
output_queue.put(None)
# wait for it to finish
reduce.join()
if output != sys.stdout:
output.close()
extract_duration = default_timer() - extract_start
extract_rate = ordinal / extract_duration
logging.info("Finished %d-process extraction of %d articles in %.1fs (%.1f art/s)",
process_count, ordinal, extract_duration, extract_rate)
# ----------------------------------------------------------------------
# Multiprocess support
def extract_process(jobs_queue, output_queue, html_safe):
"""Pull tuples of raw page content, do CPU/regex-heavy fixup, push finished text
:param jobs_queue: where to get jobs.
:param output_queue: where to queue extracted text for output.
:html_safe: whether to convert entities in text to HTML.
"""
while True:
job = jobs_queue.get() # job is (id, revid, urlbase, title, page)
if job:
out = StringIO() # memory buffer
Extractor(*job[:-1]).extract(out, html_safe) # (id, urlbase, title, page)
text = out.getvalue()
output_queue.put((job[-1], text)) # (ordinal, extracted_text)
out.close()
else:
break
def reduce_process(output_queue, output):
"""
Pull finished article text, write series of files (or stdout)
:param output_queue: text to be output.
:param output: file object where to print.
"""
interval_start = default_timer()
period = 100000
# FIXME: use a heap
ordering_buffer = {} # collected pages
next_ordinal = 0 # sequence number of pages
while True:
if next_ordinal in ordering_buffer:
output.write(ordering_buffer.pop(next_ordinal))
next_ordinal += 1
# progress report
if next_ordinal % period == 0:
interval_rate = period / (default_timer() - interval_start)
logging.info("Extracted %d articles (%.1f art/s)",
next_ordinal, interval_rate)
interval_start = default_timer()
else:
# mapper puts None to signal finish
pair = output_queue.get()
if not pair:
break
ordinal, text = pair
ordering_buffer[ordinal] = text
# ----------------------------------------------------------------------
# Minimum size of output files
minFileSize = 200 * 1024
def main():
global acceptedNamespaces
global templateCache
parser = argparse.ArgumentParser(prog=os.path.basename(sys.argv[0]),
formatter_class=argparse.RawDescriptionHelpFormatter,
description=__doc__)
parser.add_argument("input",
help="XML wiki dump file")
groupO = parser.add_argument_group('Output')
groupO.add_argument("-o", "--output", default="text",
help="directory for extracted files (or '-' for dumping to stdout)")
groupO.add_argument("-b", "--bytes", default="1M",
help="maximum bytes per output file (default %(default)s); 0 means to put a single article per file",
metavar="n[KMG]")
groupO.add_argument("-c", "--compress", action="store_true",
help="compress output files using bzip")
groupO.add_argument("--json", action="store_true",
help="write output in json format instead of the default format")
groupP = parser.add_argument_group('Processing')
groupP.add_argument("--html", action="store_true",
help="produce HTML output, subsumes --links")
groupP.add_argument("-l", "--links", action="store_true",
help="preserve links")
groupP.add_argument("-ns", "--namespaces", default="", metavar="ns1,ns2",
help="accepted namespaces")
groupP.add_argument("--templates",
help="use or create file containing templates")
groupP.add_argument("--no-templates", action="store_true",
help="Do not expand templates")
groupP.add_argument("--html-safe", default=True,
help="use to produce HTML safe output within ...")
default_process_count = cpu_count() - 1
parser.add_argument("--processes", type=int, default=default_process_count,
help="Number of processes to use (default %(default)s)")
groupS = parser.add_argument_group('Special')
groupS.add_argument("-q", "--quiet", action="store_true",
help="suppress reporting progress info")
groupS.add_argument("--debug", action="store_true",
help="print debug info")
groupS.add_argument("-a", "--article", action="store_true",
help="analyze a file containing a single article (debug option)")
groupS.add_argument("-v", "--version", action="version",
version='%(prog)s ' + __version__,
help="print program version")
args = parser.parse_args()
Extractor.keepLinks = args.links
Extractor.HtmlFormatting = args.html
if args.html:
Extractor.keepLinks = True
Extractor.to_json = args.json
try:
power = 'kmg'.find(args.bytes[-1].lower()) + 1
# 0 bytes means put a single article per file.
file_size = 0 if args.bytes == '0' else int(args.bytes[:-1]) * 1024 ** power
if file_size and file_size < minFileSize:
raise ValueError()
except ValueError:
logging.error('Insufficient or invalid size: %s', args.bytes)
return
if args.namespaces:
acceptedNamespaces = set(args.namespaces.split(','))
FORMAT = '%(levelname)s: %(message)s'
logging.basicConfig(format=FORMAT)
logger = logging.getLogger()
if not args.quiet:
logger.setLevel(logging.INFO)
if args.debug:
logger.setLevel(logging.DEBUG)
input_file = args.input
if not Extractor.keepLinks:
ignoreTag('a')
# sharing cache of parser templates is too slow:
# manager = Manager()
# templateCache = manager.dict()
if args.article:
if args.templates:
if os.path.exists(args.templates):
with open(args.templates) as file:
load_templates(file)
urlbase = ''
with open(input_file) as input:
for id, revid, title, page in collect_pages(input):
Extractor(id, revid, urlbase, title, page).extract(sys.stdout)
return
output_path = args.output
if output_path != '-' and not os.path.isdir(output_path):
try:
os.makedirs(output_path)
except:
logging.error('Could not create: %s', output_path)
return
process_dump(input_file, args.templates, output_path, file_size,
args.compress, args.processes, args.html_safe, not args.no_templates)
if __name__ == '__main__':
main()
wikiextractor-3.0.7/wikiextractor/__init__.py 0000664 0000000 0000000 00000000000 14364016463 0021425 0 ustar 00root root 0000000 0000000 wikiextractor-3.0.7/wikiextractor/cirrus-extract.py 0000775 0000000 0000000 00000020574 14364016463 0022672 0 ustar 00root root 0000000 0000000 #!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# =============================================================================
# Version: 1.00 (December 15, 2015)
# Author: Giuseppe Attardi (attardi@di.unipi.it), University of Pisa
#
# =============================================================================
# Copyright (c) 2015. Giuseppe Attardi (attardi@di.unipi.it).
# =============================================================================
# This file is part of Tanl.
#
# Tanl is free software; you can redistribute it and/or modify it
# under the terms of the GNU Affero General Public License, version 3,
# as published by the Free Software Foundation.
#
# Tanl is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see .
# =============================================================================
"""Wikipedia Cirrus Extractor:
Extracts and cleans text from a Wikipedia Cirrus dump and stores output in a
number of files of similar size in a given directory.
Each file will contain several documents in the format:
...
"""
import sys, os.path, time
import re
import json
import argparse
import bz2
import gzip
import logging
# Program version
version = '3.0'
urlbase = 'http://it.wikipedia.org/'
# ----------------------------------------------------------------------
class NextFile(object):
"""
Synchronous generation of next available file name.
"""
filesPerDir = 100
def __init__(self, path_name):
self.path_name = path_name
self.dir_index = -1
self.file_index = -1
def next(self):
self.file_index = (self.file_index + 1) % NextFile.filesPerDir
if self.file_index == 0:
self.dir_index += 1
dirname = self._dirname()
if not os.path.isdir(dirname):
os.makedirs(dirname)
return self._filepath()
def _dirname(self):
char1 = self.dir_index % 26
char2 = int(self.dir_index / 26) % 26
return os.path.join(self.path_name, '%c%c' % (ord('A') + char2, ord('A') + char1))
def _filepath(self):
return '%s/wiki_%02d' % (self._dirname(), self.file_index)
class OutputSplitter(object):
"""
File-like object, that splits output to multiple files of a given max size.
"""
def __init__(self, nextFile, max_file_size=0, compress=True):
"""
:param nextfile: a NextFile object from which to obtain filenames
to use.
:param max_file_size: the maximum size of each file.
:para compress: whether to write data with bzip compression.
"""
self.nextFile = nextFile
self.compress = compress
self.max_file_size = max_file_size
self.file = self.open(self.nextFile.next())
def reserve(self, size):
if self.file.tell() + size > self.max_file_size:
self.close()
self.file = self.open(self.nextFile.next())
def write(self, data):
self.reserve(len(data))
self.file.write(data)
def close(self):
self.file.close()
def open(self, filename):
if self.compress:
return bz2.BZ2File(filename + '.bz2', 'w')
else:
return open(filename, 'w')
# ----------------------------------------------------------------------
class Extractor(object):
def extract(self, out):
"""
:param out: output file.
"""
logging.debug("%s\t%s", self.id, self.title)
text = ''.join(self.page)
url = get_url(self.id)
header = '\n' % (self.id, url, self.title, self.language, self.revision)
# Separate header from text with a newline.
header += self.title + '\n\n'
header = header.encode('utf-8')
footer = "\n\n"
out.write(header)
text = clean(self, text)
for line in compact(text):
out.write(line.encode('utf-8'))
out.write('\n')
out.write(footer)
def process_dump(input_file, out_file, file_size, file_compress):
"""
:param input_file: name of the wikipedia dump file; '-' to read from stdin
:param out_file: directory where to store extracted data, or '-' for stdout
:param file_size: max size of each extracted file, or None for no max (one file)
:param file_compress: whether to compress files with bzip.
"""
if input_file == '-':
input = sys.stdin
else:
input = gzip.open(input_file)
if out_file == '-':
output = sys.stdout
if file_compress:
logging.warn("writing to stdout, so no output compression (use external tool)")
else:
nextFile = NextFile(out_file)
output = OutputSplitter(nextFile, file_size, file_compress)
# process dump
# format
# {"index":{"_type":"page","_id":"3825914"}}
# {"namespace":0,"title":TITLE,"timestamp":"2014-06-29T15:51:09Z","text":TEXT,...}
while True:
line = input.readline()
if not line:
break
index = json.loads(line)
content = json.loads(input.readline())
type = index['index']['_type']
id = index['index']['_id']
language = content['language']
revision = content['version']
if type == 'page' and content['namespace'] == 0:
title = content['title']
text = content['text']
# drop references:
# ^ The Penguin Dictionary
text = re.sub(r' \^ .*', '', text)
url = urlbase + 'wiki?curid=' + id
header = '\n' % (id, url, title, language, revision)
page = header + title + '\n\n' + text + '\n\n'
output.write(page.encode('utf-8'))
# ----------------------------------------------------------------------
# Minimum size of output files
minFileSize = 200 * 1024
def main():
parser = argparse.ArgumentParser(prog=os.path.basename(sys.argv[0]),
formatter_class=argparse.RawDescriptionHelpFormatter,
description=__doc__)
parser.add_argument("input",
help="Cirrus Json wiki dump file")
groupO = parser.add_argument_group('Output')
groupO.add_argument("-o", "--output", default="text",
help="directory for extracted files (or '-' for dumping to stdin)")
groupO.add_argument("-b", "--bytes", default="1M",
help="maximum bytes per output file (default %(default)s)",
metavar="n[KMG]")
groupO.add_argument("-c", "--compress", action="store_true",
help="compress output files using bzip")
groupP = parser.add_argument_group('Processing')
groupP.add_argument("-ns", "--namespaces", default="", metavar="ns1,ns2",
help="accepted namespaces")
groupS = parser.add_argument_group('Special')
groupS.add_argument("-q", "--quiet", action="store_true",
help="suppress reporting progress info")
groupS.add_argument("-v", "--version", action="version",
version='%(prog)s ' + version,
help="print program version")
args = parser.parse_args()
try:
power = 'kmg'.find(args.bytes[-1].lower()) + 1
file_size = int(args.bytes[:-1]) * 1024 ** power
if file_size < minFileSize:
raise ValueError()
except ValueError:
logging.error('Insufficient or invalid size: %s', args.bytes)
return
FORMAT = '%(levelname)s: %(message)s'
logging.basicConfig(format=FORMAT)
logger = logging.getLogger()
if not args.quiet:
logger.setLevel(logging.INFO)
input_file = args.input
output_path = args.output
if output_path != '-' and not os.path.isdir(output_path):
try:
os.makedirs(output_path)
except:
logging.error('Could not create: %s', output_path)
return
process_dump(input_file, output_path, file_size, args.compress)
if __name__ == '__main__':
main()
wikiextractor-3.0.7/wikiextractor/clean.py 0000664 0000000 0000000 00000003440 14364016463 0020763 0 ustar 00root root 0000000 0000000 # =============================================================================
# Copyright (c) 2020. Giuseppe Attardi (attardi@di.unipi.it).
# =============================================================================
# This file is part of Tanl.
#
# Tanl is free software; you can redistribute it and/or modify it
# under the terms of the GNU Affero General Public License, version 3,
# as published by the Free Software Foundation.
#
# Tanl is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see .
# =============================================================================
from wikiextractor.extract import Extractor, ignoreTag, resetIgnoredTags
def clean_markup(markup, keep_links=False, ignore_headers=True):
"""
Clean Wikimarkup to produce plaintext.
:param keep_links: Set to True to keep internal and external links
:param ignore_headers: if set to True, the output list will not contain
headers, only
Returns a list of paragraphs (unicode strings).
"""
if not keep_links:
ignoreTag('a')
extractor = Extractor(0, '', [])
# returns a list of strings
paragraphs = extractor.clean_text(markup,
mark_headers=True,
expand_templates=False,
escape_doc=True)
resetIgnoredTags()
if ignore_headers:
paragraphs = filter(lambda s: not s.startswith('## '), paragraphs)
return paragraphs
wikiextractor-3.0.7/wikiextractor/extract.py 0000664 0000000 0000000 00000175351 14364016463 0021366 0 ustar 00root root 0000000 0000000 # -*- coding: utf-8 -*-
# =============================================================================
# Copyright (c) 2020. Giuseppe Attardi (attardi@di.unipi.it).
# =============================================================================
# This file is part of Tanl.
#
# Tanl is free software; you can redistribute it and/or modify it
# under the terms of the GNU Affero General Public License, version 3,
# as published by the Free Software Foundation.
#
# Tanl is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see .
# =============================================================================
import re
import html
import json
from itertools import zip_longest
from urllib.parse import quote as urlencode
from html.entities import name2codepoint
import logging
import time
# ----------------------------------------------------------------------
# match tail after wikilink
tailRE = re.compile('\w+')
syntaxhighlight = re.compile('<syntaxhighlight .*?>(.*?)</syntaxhighlight>', re.DOTALL)
## PARAMS ####################################################################
##
# Defined in
# We include as default Template, when loading external template file.
knownNamespaces = set(['Template'])
##
# Drop these elements from article text
#
discardElements = [
'gallery', 'timeline', 'noinclude', 'pre',
'table', 'tr', 'td', 'th', 'caption', 'div',
'form', 'input', 'select', 'option', 'textarea',
'ul', 'li', 'ol', 'dl', 'dt', 'dd', 'menu', 'dir',
'ref', 'references', 'img', 'imagemap', 'source', 'small'
]
##
# Recognize only these namespaces
# w: Internal links to the Wikipedia
# wiktionary: Wiki dictionary
# wikt: shortcut for Wiktionary
#
acceptedNamespaces = ['w', 'wiktionary', 'wikt']
def get_url(urlbase, uid):
return "%s?curid=%s" % (urlbase, uid)
# ======================================================================
def clean(extractor, text, expand_templates=False, html_safe=True):
"""
Transforms wiki markup. If the command line flag --escapedoc is set then the text is also escaped
@see https://www.mediawiki.org/wiki/Help:Formatting
:param extractor: the Extractor t use.
:param text: the text to clean.
:param expand_templates: whether to perform template expansion.
:param html_safe: whether to convert reserved HTML characters to entities.
@return: the cleaned text.
"""
if expand_templates:
# expand templates
# See: http://www.mediawiki.org/wiki/Help:Templates
text = extractor.expandTemplates(text)
else:
# Drop transclusions (template, parser functions)
text = dropNested(text, r'{{', r'}}')
# Drop tables
text = dropNested(text, r'{\|', r'\|}')
# replace external links
text = replaceExternalLinks(text)
# replace internal links
text = replaceInternalLinks(text)
# drop MagicWords behavioral switches
text = magicWordsRE.sub('', text)
# ############### Process HTML ###############
# turn into HTML, except for the content of
res = ''
cur = 0
for m in syntaxhighlight.finditer(text):
end = m.end()
res += unescape(text[cur:m.start()]) + m.group(1)
cur = end
text = res + unescape(text[cur:])
# Handle bold/italic/quote
if extractor.HtmlFormatting:
text = bold_italic.sub(r'\1', text)
text = bold.sub(r'\1', text)
text = italic.sub(r'\1', text)
else:
text = bold_italic.sub(r'\1', text)
text = bold.sub(r'\1', text)
text = italic_quote.sub(r'"\1"', text)
text = italic.sub(r'"\1"', text)
text = quote_quote.sub(r'"\1"', text)
# residuals of unbalanced quotes
text = text.replace("'''", '').replace("''", '"')
# Collect spans
spans = []
# Drop HTML comments
for m in comment.finditer(text):
spans.append((m.start(), m.end()))
# Drop self-closing tags
for pattern in selfClosing_tag_patterns:
for m in pattern.finditer(text):
spans.append((m.start(), m.end()))
# Drop ignored tags
for left, right in ignored_tag_patterns:
for m in left.finditer(text):
spans.append((m.start(), m.end()))
for m in right.finditer(text):
spans.append((m.start(), m.end()))
# Bulk remove all spans
text = dropSpans(spans, text)
# Drop discarded elements
for tag in discardElements:
text = dropNested(text, r'<\s*%s\b[^>/]*>' % tag, r'<\s*/\s*%s>' % tag)
if not extractor.HtmlFormatting:
# Turn into text what is left ( ) and
text = unescape(text)
# Expand placeholders
for pattern, placeholder in placeholder_tag_patterns:
index = 1
for match in pattern.finditer(text):
text = text.replace(match.group(), '%s_%d' % (placeholder, index))
index += 1
text = text.replace('<<', u'«').replace('>>', u'»')
#############################################
# Cleanup text
text = text.replace('\t', ' ')
text = spaces.sub(' ', text)
text = dots.sub('...', text)
text = re.sub(u' (,:\.\)\]»)', r'\1', text)
text = re.sub(u'(\[\(«) ', r'\1', text)
text = re.sub(r'\n\W+?\n', '\n', text, flags=re.U) # lines with only punctuations
text = text.replace(',,', ',').replace(',.', '.')
if html_safe:
text = html.escape(text, quote=False)
return text
# skip level 1, it is page name level
section = re.compile(r'(==+)\s*(.*?)\s*\1')
listOpen = {'*': '', '#': '', ';': '', ':': ''}
listClose = {'*': '
', '#': '', ';': '', ':': ''}
listItem = {'*': '%s', '#': '%s', ';': '%s',
':': '%s'}
def compact(text, mark_headers=False):
"""Deal with headers, lists, empty sections, residuals of tables.
:param text: convert to HTML
"""
page = [] # list of paragraph
headers = {} # Headers for unfilled sections
emptySection = False # empty sections are discarded
listLevel = '' # nesting of lists
for line in text.split('\n'):
if not line:
if len(listLevel): # implies Extractor.HtmlFormatting
for c in reversed(listLevel):
page.append(listClose[c])
listLevel = ''
continue
# Handle section titles
m = section.match(line)
if m:
title = m.group(2)
lev = len(m.group(1))
if Extractor.HtmlFormatting:
page.append("%s" % (lev, title, lev))
if title and title[-1] not in '!?':
title += '.'
if mark_headers:
title = "## " + title
headers[lev] = title
# drop previous headers
headers = { k:v for k,v in headers.items() if k <= lev }
emptySection = True
continue
# Handle page title
if line.startswith('++'):
title = line[2:-2]
if title:
if title[-1] not in '!?':
title += '.'
page.append(title)
# handle indents
elif line[0] == ':':
page.append(line.lstrip(':'))
# handle lists
# @see https://www.mediawiki.org/wiki/Help:Formatting
elif line[0] in '*#;':
if Extractor.HtmlFormatting:
# close extra levels
l = 0
for c in listLevel:
if l < len(line) and c != line[l]:
for extra in reversed(listLevel[l:]):
page.append(listClose[extra])
listLevel = listLevel[:l]
break
l += 1
if l < len(line) and line[l] in '*#;:':
# add new level (only one, no jumps)
# FIXME: handle jumping levels
type = line[l]
page.append(listOpen[type])
listLevel += type
line = line[l+1:].strip()
else:
# continue on same level
type = line[l-1]
line = line[l:].strip()
page.append(listItem[type] % line)
else:
continue
elif len(listLevel): # implies Extractor.HtmlFormatting
for c in reversed(listLevel):
page.append(listClose[c])
listLevel = []
# Drop residuals of lists
elif line[0] in '{|' or line[-1] == '}':
continue
# Drop irrelevant lines
elif (line[0] == '(' and line[-1] == ')') or line.strip('.-') == '':
continue
elif len(headers):
if Extractor.keepSections:
items = sorted(headers.items())
for (i, v) in items:
page.append(v)
headers.clear()
page.append(line) # first line
emptySection = False
elif not emptySection:
page.append(line)
# dangerous
# # Drop preformatted
# elif line[0] == ' ':
# continue
return page
# ----------------------------------------------------------------------
def dropNested(text, openDelim, closeDelim):
"""
A matching function for nested expressions, e.g. namespaces and tables.
"""
openRE = re.compile(openDelim, re.IGNORECASE)
closeRE = re.compile(closeDelim, re.IGNORECASE)
# partition text in separate blocks { } { }
spans = [] # pairs (s, e) for each partition
nest = 0 # nesting level
start = openRE.search(text, 0)
if not start:
return text
end = closeRE.search(text, start.end())
next = start
while end:
next = openRE.search(text, next.end())
if not next: # termination
while nest: # close all pending
nest -= 1
end0 = closeRE.search(text, end.end())
if end0:
end = end0
else:
break
spans.append((start.start(), end.end()))
break
while end.end() < next.start():
# { } {
if nest:
nest -= 1
# try closing more
last = end.end()
end = closeRE.search(text, end.end())
if not end: # unbalanced
if spans:
span = (spans[0][0], last)
else:
span = (start.start(), last)
spans = [span]
break
else:
spans.append((start.start(), end.end()))
# advance start, find next close
start = next
end = closeRE.search(text, next.end())
break # { }
if next != start:
# { { }
nest += 1
# collect text outside partitions
return dropSpans(spans, text)
def dropSpans(spans, text):
"""
Drop from text the blocks identified in :param spans:, possibly nested.
"""
spans.sort()
res = ''
offset = 0
for s, e in spans:
if offset <= s: # handle nesting
if offset < s:
res += text[offset:s]
offset = e
res += text[offset:]
return res
# ----------------------------------------------------------------------
# External links
# from: https://doc.wikimedia.org/mediawiki-core/master/php/DefaultSettings_8php_source.html
wgUrlProtocols = [
'bitcoin:', 'ftp://', 'ftps://', 'geo:', 'git://', 'gopher://', 'http://',
'https://', 'irc://', 'ircs://', 'magnet:', 'mailto:', 'mms://', 'news:',
'nntp://', 'redis://', 'sftp://', 'sip:', 'sips:', 'sms:', 'ssh://',
'svn://', 'tel:', 'telnet://', 'urn:', 'worldwind://', 'xmpp:', '//'
]
# from: https://doc.wikimedia.org/mediawiki-core/master/php/Parser_8php_source.html
# Constants needed for external link processing
# Everything except bracket, space, or control characters
# \p{Zs} is unicode 'separator, space' category. It covers the space 0x20
# as well as U+3000 is IDEOGRAPHIC SPACE for bug 19052
EXT_LINK_URL_CLASS = r'[^][<>"\x00-\x20\x7F\s]'
ExtLinkBracketedRegex = re.compile(
'\[(((?i)' + '|'.join(wgUrlProtocols) + ')' + EXT_LINK_URL_CLASS + r'+)\s*([^\]\x00-\x08\x0a-\x1F]*?)\]',
re.S | re.U)
EXT_IMAGE_REGEX = re.compile(
r"""^(http://|https://)([^][<>"\x00-\x20\x7F\s]+)
/([A-Za-z0-9_.,~%\-+&;#*?!=()@\x80-\xFF]+)\.((?i)gif|png|jpg|jpeg)$""",
re.X | re.S | re.U)
def replaceExternalLinks(text):
s = ''
cur = 0
for m in ExtLinkBracketedRegex.finditer(text):
s += text[cur:m.start()]
cur = m.end()
url = m.group(1)
label = m.group(3)
# # The characters '<' and '>' (which were escaped by
# # removeHTMLtags()) should not be included in
# # URLs, per RFC 2396.
# m2 = re.search('&(lt|gt);', url)
# if m2:
# link = url[m2.end():] + ' ' + link
# url = url[0:m2.end()]
# If the link text is an image URL, replace it with an ![]()
tag
# This happened by accident in the original parser, but some people used it extensively
m = EXT_IMAGE_REGEX.match(label)
if m:
label = makeExternalImage(label)
# Use the encoded URL
# This means that users can paste URLs directly into the text
# Funny characters like ö aren't valid in URLs anyway
# This was changed in August 2004
s += makeExternalLink(url, label) # + trail
return s + text[cur:]
def makeExternalLink(url, anchor):
"""Function applied to wikiLinks"""
if Extractor.keepLinks:
return '%s' % (urlencode(url), anchor)
else:
return anchor
def makeExternalImage(url, alt=''):
if Extractor.keepLinks:
return '
' % (url, alt)
else:
return alt
# ----------------------------------------------------------------------
# WikiLinks
# See https://www.mediawiki.org/wiki/Help:Links#Internal_links
# Can be nested [[File:..|..[[..]]..|..]], [[Category:...]], etc.
# Also: [[Help:IPA for Catalan|[andora]]]
def replaceInternalLinks(text):
"""
Replaces external links of the form:
[[title |...|label]]trail
with title concatenated with trail, when present, e.g. 's' for plural.
"""
# call this after removal of external links, so we need not worry about
# triple closing ]]].
cur = 0
res = ''
for s, e in findBalanced(text, ['[['], [']]']):
m = tailRE.match(text, e)
if m:
trail = m.group(0)
end = m.end()
else:
trail = ''
end = e
inner = text[s + 2:e - 2]
# find first |
pipe = inner.find('|')
if pipe < 0:
title = inner
label = title
else:
title = inner[:pipe].rstrip()
# find last |
curp = pipe + 1
for s1, e1 in findBalanced(inner, ['[['], [']]']):
last = inner.rfind('|', curp, s1)
if last >= 0:
pipe = last # advance
curp = e1
label = inner[pipe + 1:].strip()
res += text[cur:s] + makeInternalLink(title, label) + trail
cur = end
return res + text[cur:]
def makeInternalLink(title, label):
colon = title.find(':')
if colon > 0 and title[:colon] not in acceptedNamespaces:
return ''
if colon == 0:
# drop also :File:
colon2 = title.find(':', colon + 1)
if colon2 > 1 and title[colon + 1:colon2] not in acceptedNamespaces:
return ''
if Extractor.keepLinks:
return '%s' % (urlencode(title), label)
else:
return label
# ----------------------------------------------------------------------
# variables
class MagicWords():
"""
One copy in each Extractor.
@see https://doc.wikimedia.org/mediawiki-core/master/php/MagicWord_8php_source.html
"""
names = [
'!',
'currentmonth',
'currentmonth1',
'currentmonthname',
'currentmonthnamegen',
'currentmonthabbrev',
'currentday',
'currentday2',
'currentdayname',
'currentyear',
'currenttime',
'currenthour',
'localmonth',
'localmonth1',
'localmonthname',
'localmonthnamegen',
'localmonthabbrev',
'localday',
'localday2',
'localdayname',
'localyear',
'localtime',
'localhour',
'numberofarticles',
'numberoffiles',
'numberofedits',
'articlepath',
'pageid',
'sitename',
'server',
'servername',
'scriptpath',
'stylepath',
'pagename',
'pagenamee',
'fullpagename',
'fullpagenamee',
'namespace',
'namespacee',
'namespacenumber',
'currentweek',
'currentdow',
'localweek',
'localdow',
'revisionid',
'revisionday',
'revisionday2',
'revisionmonth',
'revisionmonth1',
'revisionyear',
'revisiontimestamp',
'revisionuser',
'revisionsize',
'subpagename',
'subpagenamee',
'talkspace',
'talkspacee',
'subjectspace',
'subjectspacee',
'talkpagename',
'talkpagenamee',
'subjectpagename',
'subjectpagenamee',
'numberofusers',
'numberofactiveusers',
'numberofpages',
'currentversion',
'rootpagename',
'rootpagenamee',
'basepagename',
'basepagenamee',
'currenttimestamp',
'localtimestamp',
'directionmark',
'contentlanguage',
'numberofadmins',
'cascadingsources',
]
def __init__(self):
self.values = {'!': '|'}
def __getitem__(self, name):
return self.values.get(name)
def __setitem__(self, name, value):
self.values[name] = value
switches = (
'__NOTOC__',
'__FORCETOC__',
'__TOC__',
'__TOC__',
'__NEWSECTIONLINK__',
'__NONEWSECTIONLINK__',
'__NOGALLERY__',
'__HIDDENCAT__',
'__NOCONTENTCONVERT__',
'__NOCC__',
'__NOTITLECONVERT__',
'__NOTC__',
'__START__',
'__END__',
'__INDEX__',
'__NOINDEX__',
'__STATICREDIRECT__',
'__DISAMBIG__'
)
magicWordsRE = re.compile('|'.join(MagicWords.switches))
# =========================================================================
#
# MediaWiki Markup Grammar
# https://www.mediawiki.org/wiki/Preprocessor_ABNF
# xml-char = %x9 / %xA / %xD / %x20-D7FF / %xE000-FFFD / %x10000-10FFFF
# sptab = SP / HTAB
# ; everything except ">" (%x3E)
# attr-char = %x9 / %xA / %xD / %x20-3D / %x3F-D7FF / %xE000-FFFD / %x10000-10FFFF
# literal = *xml-char
# title = wikitext-L3
# part-name = wikitext-L3
# part-value = wikitext-L3
# part = ( part-name "=" part-value ) / ( part-value )
# parts = [ title *( "|" part ) ]
# tplarg = "{{{" parts "}}}"
# template = "{{" parts "}}"
# link = "[[" wikitext-L3 "]]"
# comment = ""
# unclosed-comment = "', re.DOTALL)
# Match ignored tags
ignored_tag_patterns = []
def ignoreTag(tag):
left = re.compile(r'<%s\b.*?>' % tag, re.IGNORECASE | re.DOTALL) # both [ and
right = re.compile(r'' % tag, re.IGNORECASE)
ignored_tag_patterns.append((left, right))
def resetIgnoredTags():
global ignored_tag_patterns
ignored_tag_patterns = []
for tag in ignoredTags:
ignoreTag(tag)
# Match selfClosing HTML tags
selfClosing_tag_patterns = [
re.compile(r'<\s*%s\b[^>]*/\s*>' % tag, re.DOTALL | re.IGNORECASE) for tag in selfClosingTags
]
# Match HTML placeholder tags
placeholder_tag_patterns = [
(re.compile(r'<\s*%s(\s*| [^>]+?)>.*?<\s*/\s*%s\s*>' % (tag, tag), re.DOTALL | re.IGNORECASE),
repl) for tag, repl in placeholder_tags.items()
]
# Match preformatted lines
preformatted = re.compile(r'^ .*?$')
# Match external links (space separates second optional parameter)
externalLink = re.compile(r'\[\w+[^ ]*? (.*?)]')
externalLinkNoAnchor = re.compile(r'\[\w+[&\]]*\]')
# Matches bold/italic
bold_italic = re.compile(r"'''''(.*?)'''''")
bold = re.compile(r"'''(.*?)'''")
italic_quote = re.compile(r"''\"([^\"]*?)\"''")
italic = re.compile(r"''(.*?)''")
quote_quote = re.compile(r'""([^"]*?)""')
# Matches space
spaces = re.compile(r' {2,}')
# Matches dots
dots = re.compile(r'\.{4,}')
# ======================================================================
class Template(list):
"""
A Template is a list of TemplateText or TemplateArgs
"""
@classmethod
def parse(cls, body):
tpl = Template()
# we must handle nesting, s.a.
# {{{1|{{PAGENAME}}}
# {{{italics|{{{italic|}}}
# {{#if:{{{{{#if:{{{nominee|}}}|nominee|candidate}}|}}}|
#
start = 0
for s,e in findMatchingBraces(body, 3):
tpl.append(TemplateText(body[start:s]))
tpl.append(TemplateArg(body[s+3:e-3]))
start = e
tpl.append(TemplateText(body[start:])) # leftover
return tpl
def subst(self, params, extractor, depth=0):
# We perform parameter substitutions recursively.
# We also limit the maximum number of iterations to avoid too long or
# even endless loops (in case of malformed input).
# :see: http://meta.wikimedia.org/wiki/Help:Expansion#Distinction_between_variables.2C_parser_functions.2C_and_templates
#
# Parameter values are assigned to parameters in two (?) passes.
# Therefore a parameter name in a template can depend on the value of
# another parameter of the same template, regardless of the order in
# which they are specified in the template call, for example, using
# Template:ppp containing "{{{{{{p}}}}}}", {{ppp|p=q|q=r}} and even
# {{ppp|q=r|p=q}} gives r, but using Template:tvvv containing
# "{{{{{{{{{p}}}}}}}}}", {{tvvv|p=q|q=r|r=s}} gives s.
logging.debug('subst tpl (%d, %d) %s', len(extractor.frame), depth, self)
if depth > extractor.maxParameterRecursionLevels:
extractor.recursion_exceeded_3_errs += 1
return ''
return ''.join([tpl.subst(params, extractor, depth) for tpl in self])
def __str__(self):
return ''.join([str(x) for x in self])
class TemplateText(str):
"""Fixed text of template"""
def subst(self, params, extractor, depth):
return self
class TemplateArg():
"""
parameter to a template.
Has a name and a default value, both of which are Templates.
"""
def __init__(self, parameter):
"""
:param parameter: the parts of a tplarg.
"""
# the parameter name itself might contain templates, e.g.:
# appointe{{#if:{{{appointer14|}}}|r|d}}14|
# 4|{{{{{subst|}}}CURRENTYEAR}}
# any parts in a tplarg after the first (the parameter default) are
# ignored, and an equals sign in the first part is treated as plain text.
#logging.debug('TemplateArg %s', parameter)
parts = splitParts(parameter)
self.name = Template.parse(parts[0])
if len(parts) > 1:
# This parameter has a default value
self.default = Template.parse(parts[1])
else:
self.default = None
def __str__(self):
if self.default:
return '{{{%s|%s}}}' % (self.name, self.default)
else:
return '{{{%s}}}' % self.name
def subst(self, params, extractor, depth):
"""
Substitute value for this argument from dict :param params:
Use :param extractor: to evaluate expressions for name and default.
Limit substitution to the maximun :param depth:.
"""
# the parameter name itself might contain templates, e.g.:
# appointe{{#if:{{{appointer14|}}}|r|d}}14|
paramName = self.name.subst(params, extractor, depth+1)
paramName = extractor.expandTemplates(paramName)
res = ''
if paramName in params:
res = params[paramName] # use parameter value specified in template invocation
elif self.default: # use the default value
defaultValue = self.default.subst(params, extractor, depth+1)
res = extractor.expandTemplates(defaultValue)
#logging.debug('subst arg %d %s -> %s' % (depth, paramName, res))
return res
# ======================================================================
substWords = 'subst:|safesubst:'
class Extractor():
"""
An extraction task on a article.
"""
##
# Whether to preserve links in output
keepLinks = False
##
# Whether to preserve section titles
keepSections = True
##
# Whether to output text with HTML formatting elements in files.
HtmlFormatting = False
##
# Whether to produce json instead of the default output format.
toJson = False
##
# Obtained from TemplateNamespace
templatePrefix = ''
def __init__(self, id, revid, urlbase, title, page):
"""
:param page: a list of lines.
"""
self.id = id
self.revid = revid
self.url = get_url(urlbase, id)
self.title = title
self.page = page
self.magicWords = MagicWords()
self.frame = []
self.recursion_exceeded_1_errs = 0 # template recursion within expandTemplates()
self.recursion_exceeded_2_errs = 0 # template recursion within expandTemplate()
self.recursion_exceeded_3_errs = 0 # parameter recursion
self.template_title_errs = 0
def clean_text(self, text, mark_headers=False, expand_templates=True,
html_safe=True):
"""
:param mark_headers: True to distinguish headers from paragraphs
e.g. "## Section 1"
"""
self.magicWords['namespace'] = self.title[:max(0, self.title.find(":"))]
#self.magicWords['namespacenumber'] = '0' # for article,
self.magicWords['pagename'] = self.title
self.magicWords['fullpagename'] = self.title
self.magicWords['currentyear'] = time.strftime('%Y')
self.magicWords['currentmonth'] = time.strftime('%m')
self.magicWords['currentday'] = time.strftime('%d')
self.magicWords['currenthour'] = time.strftime('%H')
self.magicWords['currenttime'] = time.strftime('%H:%M:%S')
text = clean(self, text, expand_templates=expand_templates,
html_safe=html_safe)
text = compact(text, mark_headers=mark_headers)
return text
def extract(self, out, html_safe=True):
"""
:param out: a memory file.
:param html_safe: whether to escape HTML entities.
"""
logging.debug("%s\t%s", self.id, self.title)
text = ''.join(self.page)
text = self.clean_text(text, html_safe=html_safe)
if self.to_json:
json_data = {
'id': self.id,
'revid': self.revid,
'url': self.url,
'title': self.title,
'text': "\n".join(text)
}
out_str = json.dumps(json_data)
out.write(out_str)
out.write('\n')
else:
header = '\n' % (self.id, self.url, self.title)
# Separate header from text with a newline.
header += self.title + '\n\n'
footer = "\n\n"
out.write(header)
out.write('\n'.join(text))
out.write('\n')
out.write(footer)
errs = (self.template_title_errs,
self.recursion_exceeded_1_errs,
self.recursion_exceeded_2_errs,
self.recursion_exceeded_3_errs)
if any(errs):
logging.warn("Template errors in article '%s' (%s): title(%d) recursion(%d, %d, %d)",
self.title, self.id, *errs)
# ----------------------------------------------------------------------
# Expand templates
maxTemplateRecursionLevels = 30
maxParameterRecursionLevels = 16
# check for template beginning
reOpen = re.compile('(?= self.maxTemplateRecursionLevels:
self.recursion_exceeded_1_errs += 1
return res
# logging.debug(' %d %s', len(self.frame), res)
return res
def templateParams(self, parameters):
"""
Build a dictionary with positional or name key to expanded parameters.
:param parameters: the parts[1:] of a template, i.e. all except the title.
"""
templateParams = {}
if not parameters:
return templateParams
logging.debug('
# Parameters may span several lines, like:
# {{Reflist|colwidth=30em|refs=
# <ref name="Goode">Title</ref>
# The '=' might occurr within an HTML attribute:
# "<ref name=value"
# but we stop at first.
# The '=' might occurr within quotes:
# ''''cénicas'''
m = re.match(" *([^=']*?) *=(.*)", param, re.DOTALL)
if m:
# This is a named parameter. This case also handles parameter
# assignments like "2=xxx", where the number of an unnamed
# parameter ("2") is specified explicitly - this is handled
# transparently.
parameterName = m.group(1).strip()
parameterValue = m.group(2)
if ']]' not in parameterValue: # if the value does not contain a link, trim whitespace
parameterValue = parameterValue.strip()
templateParams[parameterName] = parameterValue
else:
# this is an unnamed parameter
unnamedParameterCounter += 1
if ']]' not in param: # if the value does not contain a link, trim whitespace
param = param.strip()
templateParams[str(unnamedParameterCounter)] = param
logging.debug(' templateParams> %s', '|'.join(templateParams.values()))
return templateParams
def expandTemplate(self, body):
"""Expands template invocation.
:param body: the parts of a template.
:see http://meta.wikimedia.org/wiki/Help:Expansion for an explanation
of the process.
See in particular: Expansion of names and values
http://meta.wikimedia.org/wiki/Help:Expansion#Expansion_of_names_and_values
For most parser functions all names and values are expanded,
regardless of what is relevant for the result. The branching functions
(#if, #ifeq, #iferror, #ifexist, #ifexpr, #switch) are exceptions.
All names in a template call are expanded, and the titles of the
tplargs in the template body, after which it is determined which
values must be expanded, and for which tplargs in the template body
the first part (default).
In the case of a tplarg, any parts beyond the first are never
expanded. The possible name and the value of the first part is
expanded if the title does not match a name in the template call.
:see code for braceSubstitution at
https://doc.wikimedia.org/mediawiki-core/master/php/html/Parser_8php_source.html#3397:
"""
# template = "{{" parts "}}"
# Templates and tplargs are decomposed in the same way, with pipes as
# separator, even though eventually any parts in a tplarg after the first
# (the parameter default) are ignored, and an equals sign in the first
# part is treated as plain text.
# Pipes inside inner templates and tplargs, or inside double rectangular
# brackets within the template or tplargs are not taken into account in
# this decomposition.
# The first part is called title, the other parts are simply called parts.
# If a part has one or more equals signs in it, the first equals sign
# determines the division into name = value. Equals signs inside inner
# templates and tplargs, or inside double rectangular brackets within the
# part are not taken into account in this decomposition. Parts without
# equals sign are indexed 1, 2, .., given as attribute in the tag.
if len(self.frame) >= self.maxTemplateRecursionLevels:
self.recursion_exceeded_2_errs += 1
# logging.debug(' INVOCATION> %d %s', len(self.frame), body)
return ''
logging.debug('INVOCATION %d %s', len(self.frame), body)
parts = splitParts(body)
# title is the portion before the first |
logging.debug('TITLE %s', parts[0].strip())
title = self.expandTemplates(parts[0].strip())
# SUBST
# Apply the template tag to parameters without
# substituting into them, e.g.
# {{subst:t|a{{{p|q}}}b}} gives the wikitext start-a{{{p|q}}}b-end
# @see https://www.mediawiki.org/wiki/Manual:Substitution#Partial_substitution
subst = False
if re.match(substWords, title, re.IGNORECASE):
title = re.sub(substWords, '', title, 1, re.IGNORECASE)
subst = True
if title.lower() in self.magicWords.values:
return self.magicWords[title.lower()]
# Parser functions
# The first argument is everything after the first colon.
# It has been evaluated above.
colon = title.find(':')
if colon > 1:
funct = title[:colon]
parts[0] = title[colon + 1:].strip() # side-effect (parts[0] not used later)
# arguments after first are not evaluated
ret = callParserFunction(funct, parts, self.frame)
return self.expandTemplates(ret)
title = fullyQualifiedTemplateTitle(title)
if not title:
self.template_title_errs += 1
return ''
redirected = redirects.get(title)
if redirected:
title = redirected
# get the template
if title in templateCache:
template = templateCache[title]
elif title in templates:
template = Template.parse(templates[title])
# add it to cache
templateCache[title] = template
del templates[title]
else:
# The page being included could not be identified
return ''
# logging.debug('TEMPLATE %s: %s', title, template)
# tplarg = "{{{" parts "}}}"
# parts = [ title *( "|" part ) ]
# part = ( part-name "=" part-value ) / ( part-value )
# part-name = wikitext-L3
# part-value = wikitext-L3
# wikitext-L3 = literal / template / tplarg / link / comment /
# line-eating-comment / unclosed-comment /
# xmlish-element / *wikitext-L3
# A tplarg may contain other parameters as well as templates, e.g.:
# {{{text|{{{quote|{{{1|{{error|Error: No text given}}}}}}}}}}}
# hence no simple RE like this would work:
# '{{{((?:(?!{{{).)*?)}}}'
# We must use full CF parsing.
# the parameter name itself might be computed, e.g.:
# {{{appointe{{#if:{{{appointer14|}}}|r|d}}14|}}}
# Because of the multiple uses of double-brace and triple-brace
# syntax, expressions can sometimes be ambiguous.
# Precedence rules specifed here:
# http://www.mediawiki.org/wiki/Preprocessor_ABNF#Ideal_precedence
# resolve ambiguities like this:
# {{{{ }}}} -> { {{{ }}} }
# {{{{{ }}}}} -> {{ {{{ }}} }}
#
# :see: https://en.wikipedia.org/wiki/Help:Template#Handling_parameters
params = parts[1:]
if not subst:
# Evaluate parameters, since they may contain templates, including
# the symbol "=".
# {{#ifexpr: {{{1}}} = 1 }}
params = [self.expandTemplates(p) for p in params]
# build a dict of name-values for the parameter values
params = self.templateParams(params)
# Perform parameter substitution
# extend frame before subst, since there may be recursion in default
# parameter value, e.g. {{OTRS|celebrative|date=April 2015}} in article
# 21637542 in enwiki.
self.frame.append((title, params))
instantiated = template.subst(params, self)
# logging.debug('instantiated %d %s', len(self.frame), instantiated)
value = self.expandTemplates(instantiated)
self.frame.pop()
# logging.debug(' INVOCATION> %s %d %s', title, len(self.frame), value)
return value
# ----------------------------------------------------------------------
# parameter handling
def splitParts(paramsList):
"""
:param paramsList: the parts of a template or tplarg.
Split template parameters at the separator "|".
separator "=".
Template parameters often contain URLs, internal links, text or even
template expressions, since we evaluate templates outside in.
This is required for cases like:
{{#if: {{{1}}} | {{lc:{{{1}}} | "parameter missing"}}
Parameters are separated by "|" symbols. However, we
cannot simply split the string on "|" symbols, since these
also appear inside templates and internal links, e.g.
{{if:|
|{{#if:the president|
|{{#if:|
[[Category:Hatnote templates|A{{PAGENAME}}]]
}}
}}
}}
We split parts at the "|" symbols that are not inside any pair
{{{...}}}, {{...}}, [[...]], {|...|}.
"""
# Must consider '[' as normal in expansion of Template:EMedicine2:
# #ifeq: ped|article|[http://emedicine.medscape.com/article/180-overview|[http://www.emedicine.com/ped/topic180.htm#{{#if: |section~}}
# as part of:
# {{#ifeq: ped|article|[http://emedicine.medscape.com/article/180-overview|[http://www.emedicine.com/ped/topic180.htm#{{#if: |section~}}}} ped/180{{#if: |~}}]
# should handle both tpl arg like:
# 4|{{{{{subst|}}}CURRENTYEAR}}
# and tpl parameters like:
# ||[[Category:People|{{#if:A|A|{{PAGENAME}}}}]]
sep = '|'
parameters = []
cur = 0
for s, e in findMatchingBraces(paramsList):
par = paramsList[cur:s].split(sep)
if par:
if parameters:
# portion before | belongs to previous parameter
parameters[-1] += par[0]
if len(par) > 1:
# rest are new parameters
parameters.extend(par[1:])
else:
parameters = par
elif not parameters:
parameters = [''] # create first param
# add span to last previous parameter
parameters[-1] += paramsList[s:e]
cur = e
# leftover
par = paramsList[cur:].split(sep)
if par:
if parameters:
# portion before | belongs to previous parameter
parameters[-1] += par[0]
if len(par) > 1:
# rest are new parameters
parameters.extend(par[1:])
else:
parameters = par
# logging.debug('splitParts %s %s\nparams: %s', sep, paramsList, str(parameters))
return parameters
def findMatchingBraces(text, ldelim=0):
"""
:param ldelim: number of braces to match. 0 means match [[]], {{}} and {{{}}}.
"""
# Parsing is done with respect to pairs of double braces {{..}} delimiting
# a template, and pairs of triple braces {{{..}}} delimiting a tplarg.
# If double opening braces are followed by triple closing braces or
# conversely, this is taken as delimiting a template, with one left-over
# brace outside it, taken as plain text. For any pattern of braces this
# defines a set of templates and tplargs such that any two are either
# separate or nested (not overlapping).
# Unmatched double rectangular closing brackets can be in a template or
# tplarg, but unmatched double rectangular opening brackets cannot.
# Unmatched double or triple closing braces inside a pair of
# double rectangular brackets are treated as plain text.
# Other formulation: in ambiguity between template or tplarg on one hand,
# and a link on the other hand, the structure with the rightmost opening
# takes precedence, even if this is the opening of a link without any
# closing, so not producing an actual link.
# In the case of more than three opening braces the last three are assumed
# to belong to a tplarg, unless there is no matching triple of closing
# braces, in which case the last two opening braces are are assumed to
# belong to a template.
# We must skip individual { like in:
# {{#ifeq: {{padleft:|1|}} | { | | }}
# We must resolve ambiguities like this:
# {{{{ }}}} -> { {{{ }}} }
# {{{{{ }}}}} -> {{ {{{ }}} }}
# {{#if:{{{{{#if:{{{nominee|}}}|nominee|candidate}}|}}}|...}}
# Handle:
# {{{{{|safesubst:}}}#Invoke:String|replace|{{{1|{{{{{|safesubst:}}}PAGENAME}}}}}|%s+%([^%(]-%)$||plain=false}}
# as well as expressions with stray }:
# {{{link|{{ucfirst:{{{1}}}}}} interchange}}}
if ldelim: # 2-3
reOpen = re.compile('[{]{%d,}' % ldelim) # at least ldelim
reNext = re.compile('[{]{2,}|}{2,}') # at least 2 open or close bracces
else:
reOpen = re.compile('{{2,}|\[{2,}')
reNext = re.compile('{{2,}|}{2,}|\[{2,}|]{2,}') # at least 2
cur = 0
while True:
m1 = reOpen.search(text, cur)
if not m1:
return
lmatch = m1.end() - m1.start()
if m1.group()[0] == '{':
stack = [lmatch] # stack of opening braces lengths
else:
stack = [-lmatch] # negative means [
end = m1.end()
while True:
m2 = reNext.search(text, end)
if not m2:
return # unbalanced
end = m2.end()
brac = m2.group()[0]
lmatch = m2.end() - m2.start()
if brac == '{':
stack.append(lmatch)
elif brac == '}':
while stack:
openCount = stack.pop() # opening span
if openCount == 0: # illegal unmatched [[
continue
if lmatch >= openCount:
lmatch -= openCount
if lmatch <= 1: # either close or stray }
break
else:
# put back unmatched
stack.append(openCount - lmatch)
break
if not stack:
yield m1.start(), end - lmatch
cur = end
break
elif len(stack) == 1 and 0 < stack[0] < ldelim:
# ambiguous {{{{{ }}} }}
yield m1.start() + stack[0], end
cur = end
break
elif brac == '[': # [[
stack.append(-lmatch)
else: # ]]
while stack and stack[-1] < 0: # matching [[
openCount = -stack.pop()
if lmatch >= openCount:
lmatch -= openCount
if lmatch <= 1: # either close or stray ]
break
else:
# put back unmatched (negative)
stack.append(lmatch - openCount)
break
if not stack:
yield m1.start(), end - lmatch
cur = end
break
# unmatched ]] are discarded
cur = end
def findBalanced(text, openDelim, closeDelim):
"""
Assuming that text contains a properly balanced expression using
:param openDelim: as opening delimiters and
:param closeDelim: as closing delimiters.
:return: an iterator producing pairs (start, end) of start and end
positions in text containing a balanced expression.
"""
openPat = '|'.join([re.escape(x) for x in openDelim])
# patter for delimiters expected after each opening delimiter
afterPat = {o: re.compile(openPat + '|' + c, re.DOTALL) for o, c in zip(openDelim, closeDelim)}
stack = []
start = 0
cur = 0
# end = len(text)
startSet = False
startPat = re.compile(openPat)
nextPat = startPat
while True:
next = nextPat.search(text, cur)
if not next:
return
if not startSet:
start = next.start()
startSet = True
delim = next.group(0)
if delim in openDelim:
stack.append(delim)
nextPat = afterPat[delim]
else:
opening = stack.pop()
# assert opening == openDelim[closeDelim.index(next.group(0))]
if stack:
nextPat = afterPat[stack[-1]]
else:
yield start, next.end()
nextPat = startPat
start = next.end()
startSet = False
cur = next.end()
# ----------------------------------------------------------------------
# parser functions utilities
def ucfirst(string):
""":return: a string with just its first character uppercase
We can't use title() since it coverts all words.
"""
if string:
if len(string) > 1:
return string[0].upper() + string[1:]
else:
return string.upper()
else:
return ''
def lcfirst(string):
""":return: a string with its first character lowercase"""
if string:
if len(string) > 1:
return string[0].lower() + string[1:]
else:
return string.lower()
else:
return ''
def fullyQualifiedTemplateTitle(templateTitle):
"""
Determine the namespace of the page being included through the template
mechanism
"""
if templateTitle.startswith(':'):
# Leading colon by itself implies main namespace, so strip this colon
return ucfirst(templateTitle[1:])
else:
m = re.match('([^:]*)(:.*)', templateTitle)
if m:
# colon found but not in the first position - check if it
# designates a known namespace
prefix = normalizeNamespace(m.group(1))
if prefix in knownNamespaces:
return prefix + ucfirst(m.group(2))
# The title of the page being included is NOT in the main namespace and
# lacks any other explicit designation of the namespace - therefore, it
# is resolved to the Template namespace (that's the default for the
# template inclusion mechanism).
# This is a defense against pages whose title only contains UTF-8 chars
# that are reduced to an empty string. Right now I can think of one such
# case - which represents the non-breaking space.
# In this particular case, this page is a redirect to [[Non-nreaking
# space]], but having in the system a redirect page with an empty title
# causes numerous problems, so we'll live happier without it.
if templateTitle:
return Extractor.templatePrefix + ucfirst(templateTitle)
else:
return '' # caller may log as error
def normalizeNamespace(ns):
return ucfirst(ns)
# ----------------------------------------------------------------------
# Parser functions
# see http://www.mediawiki.org/wiki/Help:Extension:ParserFunctions
# https://github.com/Wikia/app/blob/dev/extensions/ParserFunctions/ParserFunctions_body.php
class Infix():
"""Infix operators.
The calling sequence for the infix is:
x |op| y
"""
def __init__(self, function):
self.function = function
def __ror__(self, other):
return Infix(lambda x, self=self, other=other: self.function(other, x))
def __or__(self, other):
return self.function(other)
def __rlshift__(self, other):
return Infix(lambda x, self=self, other=other: self.function(other, x))
def __rshift__(self, other):
return self.function(other)
def __call__(self, value1, value2):
return self.function(value1, value2)
ROUND = Infix(lambda x, y: round(x, y))
def sharp_expr(expr):
try:
expr = re.sub('=', '==', expr)
expr = re.sub('mod', '%', expr)
expr = re.sub('\bdiv\b', '/', expr)
expr = re.sub('\bround\b', '|ROUND|', expr)
return str(eval(expr))
except:
return ''
def sharp_if(testValue, valueIfTrue, valueIfFalse=None, *args):
# In theory, we should evaluate the first argument here,
# but it was evaluated while evaluating part[0] in expandTemplate().
if testValue.strip():
# The {{#if:}} function is an if-then-else construct.
# The applied condition is: "The condition string is non-empty".
valueIfTrue = valueIfTrue.strip()
if valueIfTrue:
return valueIfTrue
elif valueIfFalse:
return valueIfFalse.strip()
return ""
def sharp_ifeq(lvalue, rvalue, valueIfTrue, valueIfFalse=None, *args):
rvalue = rvalue.strip()
if rvalue:
# lvalue is always defined
if lvalue.strip() == rvalue:
# The {{#ifeq:}} function is an if-then-else construct. The
# applied condition is "is rvalue equal to lvalue". Note that this
# does only string comparison while MediaWiki implementation also
# supports numerical comparissons.
if valueIfTrue:
return valueIfTrue.strip()
else:
if valueIfFalse:
return valueIfFalse.strip()
return ""
def sharp_iferror(test, then='', Else=None, *args):
if re.match('<(?:strong|span|p|div)\s(?:[^\s>]*\s+)*?class="(?:[^"\s>]*\s+)*?error(?:\s[^">]*)?"', test):
return then
elif Else is None:
return test.strip()
else:
return Else.strip()
def sharp_switch(primary, *params):
# FIXME: we don't support numeric expressions in primary
# {{#switch: comparison string
# | case1 = result1
# | case2
# | case4 = result2
# | 1 | case5 = result3
# | #default = result4
# }}
primary = primary.strip()
found = False # for fall through cases
default = None
rvalue = None
lvalue = ''
for param in params:
# handle cases like:
# #default = [http://www.perseus.tufts.edu/hopper/text?doc=Perseus...]
pair = param.split('=', 1)
lvalue = pair[0].strip()
rvalue = None
if len(pair) > 1:
# got "="
rvalue = pair[1].strip()
# check for any of multiple values pipe separated
if found or primary in [v.strip() for v in lvalue.split('|')]:
# Found a match, return now
return rvalue
elif lvalue == '#default':
default = rvalue
rvalue = None # avoid defaulting to last case
elif lvalue == primary:
# If the value matches, set a flag and continue
found = True
# Default case
# Check if the last item had no = sign, thus specifying the default case
if rvalue is not None:
return lvalue
elif default is not None:
return default
return ''
# Extension Scribuntu
def sharp_invoke(module, function, frame):
functions = modules.get(module)
if functions:
funct = functions.get(function)
if funct:
# find parameters in frame whose title is the one of the original
# template invocation
templateTitle = fullyQualifiedTemplateTitle(function)
if not templateTitle:
logging.warn("Template with empty title")
pair = next((x for x in frame if x[0] == templateTitle), None)
if pair:
params = pair[1]
# extract positional args
params = [params.get(str(i + 1)) for i in range(len(params))]
return funct(*params)
else:
return funct()
return ''
parserFunctions = {
'#expr': sharp_expr,
'#if': sharp_if,
'#ifeq': sharp_ifeq,
'#iferror': sharp_iferror,
'#ifexpr': lambda *args: '', # not supported
'#ifexist': lambda *args: '', # not supported
'#rel2abs': lambda *args: '', # not supported
'#switch': sharp_switch,
'# language': lambda *args: '', # not supported
'#time': lambda *args: '', # not supported
'#timel': lambda *args: '', # not supported
'#titleparts': lambda *args: '', # not supported
# This function is used in some pages to construct links
# http://meta.wikimedia.org/wiki/Help:URL
'urlencode': lambda string, *rest: urlencode(string),
'lc': lambda string, *rest: string.lower() if string else '',
'lcfirst': lambda string, *rest: lcfirst(string),
'uc': lambda string, *rest: string.upper() if string else '',
'ucfirst': lambda string, *rest: ucfirst(string),
'int': lambda string, *rest: str(int(string)),
'padleft': lambda char, width, string: string.ljust(char, int(pad)), # CHECK_ME
}
def callParserFunction(functionName, args, frame):
"""
Parser functions have similar syntax as templates, except that
the first argument is everything after the first colon.
:param functionName: nameof the parser function
:param args: the arguments to the function
:return: the result of the invocation, None in case of failure.
http://meta.wikimedia.org/wiki/Help:ParserFunctions
"""
try:
if functionName == '#invoke':
# special handling of frame
ret = sharp_invoke(args[0].strip(), args[1].strip(), frame)
# logging.debug('parserFunction> %s %s', args[1], ret)
return ret
if functionName in parserFunctions:
ret = parserFunctions[functionName](*args)
# logging.debug('parserFunction> %s(%s) %s', functionName, args, ret)
return ret
except:
return "" # FIXME: fix errors
return ""
# ----------------------------------------------------------------------
# Extract Template definition
reNoinclude = re.compile(r'(?:.*?)', re.DOTALL)
reIncludeonly = re.compile(r'|', re.DOTALL)
# These are built before spawning processes, hence they are shared.
templates = {}
redirects = {}
# cache of parser templates
# FIXME: sharing this with a Manager slows down.
templateCache = {}
def define_template(title, page):
"""
Adds a template defined in the :param page:.
@see https://en.wikipedia.org/wiki/Help:Template#Noinclude.2C_includeonly.2C_and_onlyinclude
"""
global templates
global redirects
# title = normalizeTitle(title)
# check for redirects
m = re.match('#REDIRECT.*?\[\[([^\]]*)]]', page[0], re.IGNORECASE)
if m:
redirects[title] = m.group(1) # normalizeTitle(m.group(1))
return
text = unescape(''.join(page))
# We're storing template text for future inclusion, therefore,
# remove all text and keep all text
# (but eliminate tags per se).
# However, if ... parts are present,
# then only keep them and discard the rest of the template body.
# This is because using on a text fragment is
# equivalent to enclosing it in tags **AND**
# enclosing all the rest of the template body in tags.
# remove comments
text = comment.sub('', text)
# eliminate fragments
text = reNoinclude.sub('', text)
# eliminate unterminated elements
text = re.sub(r'.*$', '', text, flags=re.DOTALL)
text = re.sub(r'', '', text)
onlyincludeAccumulator = ''
for m in re.finditer('(.*?)', text, re.DOTALL):
onlyincludeAccumulator += m.group(1)
if onlyincludeAccumulator:
text = onlyincludeAccumulator
else:
text = reIncludeonly.sub('', text)
if text:
if title in templates and templates[title] != text:
logging.warn('Redefining: %s', title)
templates[title] = text
wikiextractor-3.0.7/wikiextractor/extractPage.py 0000775 0000000 0000000 00000007465 14364016463 0022166 0 ustar 00root root 0000000 0000000 #!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# =============================================================================
# Version: 3.0 (July 22, 2020)
# Author: Giuseppe Attardi (attardi@di.unipi.it), University of Pisa
# =============================================================================
# Copyright (c) 2009. Giuseppe Attardi (attardi@di.unipi.it).
# =============================================================================
# This file is part of Tanl.
#
# Tanl is free software; you can redistribute it and/or modify it
# under the terms of the GNU Affero General Public License, version 3,
# as published by the Free Software Foundation.
#
# Tanl is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see .
# =============================================================================
"""Wikipedia Page Extractor:
Extracts a single page from a Wikipedia dump file.
"""
import sys, os.path
import re
import argparse
import bz2
# Program version
__version__ = '3.0.5'
# ----------------------------------------------------------------------
# READER
tagRE = re.compile(r'(.*?)<(/?\w+)[^>]*>(?:([^<]*)(<.*?>)?)?')
#tagRE = re.compile(r'(.*?)<(/?\w+)[^>]*>([^<]*)')
# 1 2 3
def process_data(input_file, id, templates=False):
"""
:param input_file: name of the wikipedia dump file.
:param id: article id.
:param templates: whether article is a template.
"""
if input_file.lower().endswith(".bz2"):
input = bz2.open(input_file, mode='rt', encoding='utf-8')
else:
input = open(input_file)
page = []
for line in input:
line = line
if '<' not in line: # faster than doing re.search()
if page:
page.append(line)
continue
m = tagRE.search(line)
if not m:
continue
tag = m.group(2)
if tag == 'page':
page = []
page.append(line)
inArticle = False
elif tag == 'id':
curid = m.group(3)
if id == curid:
page.append(line)
inArticle = True
elif not inArticle and not templates:
page = []
elif tag == 'title':
if templates:
if m.group(3).startswith('Template:'):
page.append(line)
else:
page = []
else:
page.append(line)
elif tag == '/page':
if page:
page.append(line)
print(''.join(page))
if not templates:
break
page = []
elif page:
page.append(line)
input.close()
def main():
parser = argparse.ArgumentParser(prog=os.path.basename(sys.argv[0]),
formatter_class=argparse.RawDescriptionHelpFormatter,
description=__doc__)
parser.add_argument("input",
help="XML wiki dump file")
parser.add_argument("--id", default="1",
help="article number")
parser.add_argument("--template", action="store_true",
help="whether article is a template")
parser.add_argument("-v", "--version", action="version",
version='%(prog)s ' + __version__,
help="print program version")
args = parser.parse_args()
process_data(args.input, args.id, args.template)
if __name__ == '__main__':
main()
]