Update the in-source hunspell to version 1.7.0

(cherry picked from commit c3484fa6c8)
This commit is contained in:
Jean-Marc Lasgouttes 2019-06-12 16:38:42 +02:00
parent f4314b6461
commit f5ae00132a
66 changed files with 3835 additions and 2833 deletions

View File

@ -1,5 +0,0 @@
Author of Hunspell:
Németh László nemeth (at) numbertext.org
Hunspell based on OpenOffice.org's Myspell. MySpell's author:
Kevin Hendricks kevin.hendricks (at) sympatico.ca

View File

@ -1,5 +0,0 @@
* Interactive interface has some visualization problem with long lines
* Experimental -U, -u options don't support Unicode.
* Compound handling is not thread safe in Hungarian specific code.

View File

@ -1,674 +0,0 @@
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU General Public License is a free, copyleft license for
software and other kinds of works.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
the GNU General Public License is intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users. We, the Free Software Foundation, use the
GNU General Public License for most of our software; it applies also to
any other work released this way by its authors. You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
To protect your rights, we need to prevent others from denying you
these rights or asking you to surrender the rights. Therefore, you have
certain responsibilities if you distribute copies of the software, or if
you modify it: responsibilities to respect the freedom of others.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must pass on to the recipients the same
freedoms that you received. You must make sure that they, too, receive
or can get the source code. And you must show them these terms so they
know their rights.
Developers that use the GNU GPL protect your rights with two steps:
(1) assert copyright on the software, and (2) offer you this License
giving you legal permission to copy, distribute and/or modify it.
For the developers' and authors' protection, the GPL clearly explains
that there is no warranty for this free software. For both users' and
authors' sake, the GPL requires that modified versions be marked as
changed, so that their problems will not be attributed erroneously to
authors of previous versions.
Some devices are designed to deny users access to install or run
modified versions of the software inside them, although the manufacturer
can do so. This is fundamentally incompatible with the aim of
protecting users' freedom to change the software. The systematic
pattern of such abuse occurs in the area of products for individuals to
use, which is precisely where it is most unacceptable. Therefore, we
have designed this version of the GPL to prohibit the practice for those
products. If such problems arise substantially in other domains, we
stand ready to extend this provision to those domains in future versions
of the GPL, as needed to protect the freedom of users.
Finally, every program is threatened constantly by software patents.
States should not allow patents to restrict development and use of
software on general-purpose computers, but in those that do, we wish to
avoid the special danger that patents applied to a free program could
make it effectively proprietary. To prevent this, the GPL assures that
patents cannot be used to render the program non-free.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Use with the GNU Affero General Public License.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU Affero General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the special requirements of the GNU Affero General Public License,
section 13, concerning interaction through a network will apply to the
combination as such.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If the program does terminal interaction, make it output a short
notice like this when it starts in an interactive mode:
<program> Copyright (C) <year> <name of author>
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, your program's commands
might be different; for a GUI interface, you would use an "about box".
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU GPL, see
<http://www.gnu.org/licenses/>.
The GNU General Public License does not permit incorporating your program
into proprietary programs. If your program is a subroutine library, you
may consider it more useful to permit linking proprietary applications with
the library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License. But first, please read
<http://www.gnu.org/philosophy/why-not-lgpl.html>.

View File

@ -1,165 +0,0 @@
GNU LESSER GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
This version of the GNU Lesser General Public License incorporates
the terms and conditions of version 3 of the GNU General Public
License, supplemented by the additional permissions listed below.
0. Additional Definitions.
As used herein, "this License" refers to version 3 of the GNU Lesser
General Public License, and the "GNU GPL" refers to version 3 of the GNU
General Public License.
"The Library" refers to a covered work governed by this License,
other than an Application or a Combined Work as defined below.
An "Application" is any work that makes use of an interface provided
by the Library, but which is not otherwise based on the Library.
Defining a subclass of a class defined by the Library is deemed a mode
of using an interface provided by the Library.
A "Combined Work" is a work produced by combining or linking an
Application with the Library. The particular version of the Library
with which the Combined Work was made is also called the "Linked
Version".
The "Minimal Corresponding Source" for a Combined Work means the
Corresponding Source for the Combined Work, excluding any source code
for portions of the Combined Work that, considered in isolation, are
based on the Application, and not on the Linked Version.
The "Corresponding Application Code" for a Combined Work means the
object code and/or source code for the Application, including any data
and utility programs needed for reproducing the Combined Work from the
Application, but excluding the System Libraries of the Combined Work.
1. Exception to Section 3 of the GNU GPL.
You may convey a covered work under sections 3 and 4 of this License
without being bound by section 3 of the GNU GPL.
2. Conveying Modified Versions.
If you modify a copy of the Library, and, in your modifications, a
facility refers to a function or data to be supplied by an Application
that uses the facility (other than as an argument passed when the
facility is invoked), then you may convey a copy of the modified
version:
a) under this License, provided that you make a good faith effort to
ensure that, in the event an Application does not supply the
function or data, the facility still operates, and performs
whatever part of its purpose remains meaningful, or
b) under the GNU GPL, with none of the additional permissions of
this License applicable to that copy.
3. Object Code Incorporating Material from Library Header Files.
The object code form of an Application may incorporate material from
a header file that is part of the Library. You may convey such object
code under terms of your choice, provided that, if the incorporated
material is not limited to numerical parameters, data structure
layouts and accessors, or small macros, inline functions and templates
(ten or fewer lines in length), you do both of the following:
a) Give prominent notice with each copy of the object code that the
Library is used in it and that the Library and its use are
covered by this License.
b) Accompany the object code with a copy of the GNU GPL and this license
document.
4. Combined Works.
You may convey a Combined Work under terms of your choice that,
taken together, effectively do not restrict modification of the
portions of the Library contained in the Combined Work and reverse
engineering for debugging such modifications, if you also do each of
the following:
a) Give prominent notice with each copy of the Combined Work that
the Library is used in it and that the Library and its use are
covered by this License.
b) Accompany the Combined Work with a copy of the GNU GPL and this license
document.
c) For a Combined Work that displays copyright notices during
execution, include the copyright notice for the Library among
these notices, as well as a reference directing the user to the
copies of the GNU GPL and this license document.
d) Do one of the following:
0) Convey the Minimal Corresponding Source under the terms of this
License, and the Corresponding Application Code in a form
suitable for, and under terms that permit, the user to
recombine or relink the Application with a modified version of
the Linked Version to produce a modified Combined Work, in the
manner specified by section 6 of the GNU GPL for conveying
Corresponding Source.
1) Use a suitable shared library mechanism for linking with the
Library. A suitable mechanism is one that (a) uses at run time
a copy of the Library already present on the user's computer
system, and (b) will operate properly with a modified version
of the Library that is interface-compatible with the Linked
Version.
e) Provide Installation Information, but only if you would otherwise
be required to provide such information under section 6 of the
GNU GPL, and only to the extent that such information is
necessary to install and execute a modified version of the
Combined Work produced by recombining or relinking the
Application with a modified version of the Linked Version. (If
you use option 4d0, the Installation Information must accompany
the Minimal Corresponding Source and Corresponding Application
Code. If you use option 4d1, you must provide the Installation
Information in the manner specified by section 6 of the GNU GPL
for conveying Corresponding Source.)
5. Combined Libraries.
You may place library facilities that are a work based on the
Library side by side in a single library together with other library
facilities that are not Applications and are not covered by this
License, and convey such a combined library under terms of your
choice, if you do both of the following:
a) Accompany the combined library with a copy of the same work based
on the Library, uncombined with any other library facilities,
conveyed under the terms of this License.
b) Give prominent notice with the combined library that part of it
is a work based on the Library, and explaining where to find the
accompanying uncombined form of the same work.
6. Revised Versions of the GNU Lesser General Public License.
The Free Software Foundation may publish revised and/or new versions
of the GNU Lesser 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
Library as you received it specifies that a certain numbered version
of the GNU Lesser General Public License "or any later version"
applies to it, you have the option of following the terms and
conditions either of that published version or of any later version
published by the Free Software Foundation. If the Library as you
received it does not specify a version number of the GNU Lesser
General Public License, you may choose any version of the GNU Lesser
General Public License ever published by the Free Software Foundation.
If the Library as you received it specifies that a proxy can decide
whether future versions of the GNU Lesser General Public License shall
apply, that proxy's public statement of acceptance of any version is
permanent authorization for you to choose that version for the
Library.

View File

@ -1,470 +0,0 @@
MOZILLA PUBLIC LICENSE
Version 1.1
---------------
1. Definitions.
1.0.1. "Commercial Use" means distribution or otherwise making the
Covered Code available to a third party.
1.1. "Contributor" means each entity that creates or contributes to
the creation of Modifications.
1.2. "Contributor Version" means the combination of the Original
Code, prior Modifications used by a Contributor, and the Modifications
made by that particular Contributor.
1.3. "Covered Code" means the Original Code or Modifications or the
combination of the Original Code and Modifications, in each case
including portions thereof.
1.4. "Electronic Distribution Mechanism" means a mechanism generally
accepted in the software development community for the electronic
transfer of data.
1.5. "Executable" means Covered Code in any form other than Source
Code.
1.6. "Initial Developer" means the individual or entity identified
as the Initial Developer in the Source Code notice required by Exhibit
A.
1.7. "Larger Work" means a work which combines Covered Code or
portions thereof with code not governed by the terms of this License.
1.8. "License" means this document.
1.8.1. "Licensable" means having the right to grant, to the maximum
extent possible, whether at the time of the initial grant or
subsequently acquired, any and all of the rights conveyed herein.
1.9. "Modifications" means any addition to or deletion from the
substance or structure of either the Original Code or any previous
Modifications. When Covered Code is released as a series of files, a
Modification is:
A. Any addition to or deletion from the contents of a file
containing Original Code or previous Modifications.
B. Any new file that contains any part of the Original Code or
previous Modifications.
1.10. "Original Code" means Source Code of computer software code
which is described in the Source Code notice required by Exhibit A as
Original Code, and which, at the time of its release under this
License is not already Covered Code governed by this License.
1.10.1. "Patent Claims" means any patent claim(s), now owned or
hereafter acquired, including without limitation, method, process,
and apparatus claims, in any patent Licensable by grantor.
1.11. "Source Code" means the preferred form of the Covered Code for
making modifications to it, including all modules it contains, plus
any associated interface definition files, scripts used to control
compilation and installation of an Executable, or source code
differential comparisons against either the Original Code or another
well known, available Covered Code of the Contributor's choice. The
Source Code can be in a compressed or archival form, provided the
appropriate decompression or de-archiving software is widely available
for no charge.
1.12. "You" (or "Your") means an individual or a legal entity
exercising rights under, and complying with all of the terms of, this
License or a future version of this License issued under Section 6.1.
For legal entities, "You" includes any entity which controls, is
controlled by, or is under common control with You. For purposes of
this definition, "control" means (a) the power, direct or indirect,
to cause the direction or management of such entity, whether by
contract or otherwise, or (b) ownership of more than fifty percent
(50%) of the outstanding shares or beneficial ownership of such
entity.
2. Source Code License.
2.1. The Initial Developer Grant.
The Initial Developer hereby grants You a world-wide, royalty-free,
non-exclusive license, subject to third party intellectual property
claims:
(a) under intellectual property rights (other than patent or
trademark) Licensable by Initial Developer to use, reproduce,
modify, display, perform, sublicense and distribute the Original
Code (or portions thereof) with or without Modifications, and/or
as part of a Larger Work; and
(b) under Patents Claims infringed by the making, using or
selling of Original Code, to make, have made, use, practice,
sell, and offer for sale, and/or otherwise dispose of the
Original Code (or portions thereof).
(c) the licenses granted in this Section 2.1(a) and (b) are
effective on the date Initial Developer first distributes
Original Code under the terms of this License.
(d) Notwithstanding Section 2.1(b) above, no patent license is
granted: 1) for code that You delete from the Original Code; 2)
separate from the Original Code; or 3) for infringements caused
by: i) the modification of the Original Code or ii) the
combination of the Original Code with other software or devices.
2.2. Contributor Grant.
Subject to third party intellectual property claims, each Contributor
hereby grants You a world-wide, royalty-free, non-exclusive license
(a) under intellectual property rights (other than patent or
trademark) Licensable by Contributor, to use, reproduce, modify,
display, perform, sublicense and distribute the Modifications
created by such Contributor (or portions thereof) either on an
unmodified basis, with other Modifications, as Covered Code
and/or as part of a Larger Work; and
(b) under Patent Claims infringed by the making, using, or
selling of Modifications made by that Contributor either alone
and/or in combination with its Contributor Version (or portions
of such combination), to make, use, sell, offer for sale, have
made, and/or otherwise dispose of: 1) Modifications made by that
Contributor (or portions thereof); and 2) the combination of
Modifications made by that Contributor with its Contributor
Version (or portions of such combination).
(c) the licenses granted in Sections 2.2(a) and 2.2(b) are
effective on the date Contributor first makes Commercial Use of
the Covered Code.
(d) Notwithstanding Section 2.2(b) above, no patent license is
granted: 1) for any code that Contributor has deleted from the
Contributor Version; 2) separate from the Contributor Version;
3) for infringements caused by: i) third party modifications of
Contributor Version or ii) the combination of Modifications made
by that Contributor with other software (except as part of the
Contributor Version) or other devices; or 4) under Patent Claims
infringed by Covered Code in the absence of Modifications made by
that Contributor.
3. Distribution Obligations.
3.1. Application of License.
The Modifications which You create or to which You contribute are
governed by the terms of this License, including without limitation
Section 2.2. The Source Code version of Covered Code may be
distributed only under the terms of this License or a future version
of this License released under Section 6.1, and You must include a
copy of this License with every copy of the Source Code You
distribute. You may not offer or impose any terms on any Source Code
version that alters or restricts the applicable version of this
License or the recipients' rights hereunder. However, You may include
an additional document offering the additional rights described in
Section 3.5.
3.2. Availability of Source Code.
Any Modification which You create or to which You contribute must be
made available in Source Code form under the terms of this License
either on the same media as an Executable version or via an accepted
Electronic Distribution Mechanism to anyone to whom you made an
Executable version available; and if made available via Electronic
Distribution Mechanism, must remain available for at least twelve (12)
months after the date it initially became available, or at least six
(6) months after a subsequent version of that particular Modification
has been made available to such recipients. You are responsible for
ensuring that the Source Code version remains available even if the
Electronic Distribution Mechanism is maintained by a third party.
3.3. Description of Modifications.
You must cause all Covered Code to which You contribute to contain a
file documenting the changes You made to create that Covered Code and
the date of any change. You must include a prominent statement that
the Modification is derived, directly or indirectly, from Original
Code provided by the Initial Developer and including the name of the
Initial Developer in (a) the Source Code, and (b) in any notice in an
Executable version or related documentation in which You describe the
origin or ownership of the Covered Code.
3.4. Intellectual Property Matters
(a) Third Party Claims.
If Contributor has knowledge that a license under a third party's
intellectual property rights is required to exercise the rights
granted by such Contributor under Sections 2.1 or 2.2,
Contributor must include a text file with the Source Code
distribution titled "LEGAL" which describes the claim and the
party making the claim in sufficient detail that a recipient will
know whom to contact. If Contributor obtains such knowledge after
the Modification is made available as described in Section 3.2,
Contributor shall promptly modify the LEGAL file in all copies
Contributor makes available thereafter and shall take other steps
(such as notifying appropriate mailing lists or newsgroups)
reasonably calculated to inform those who received the Covered
Code that new knowledge has been obtained.
(b) Contributor APIs.
If Contributor's Modifications include an application programming
interface and Contributor has knowledge of patent licenses which
are reasonably necessary to implement that API, Contributor must
also include this information in the LEGAL file.
(c) Representations.
Contributor represents that, except as disclosed pursuant to
Section 3.4(a) above, Contributor believes that Contributor's
Modifications are Contributor's original creation(s) and/or
Contributor has sufficient rights to grant the rights conveyed by
this License.
3.5. Required Notices.
You must duplicate the notice in Exhibit A in each file of the Source
Code. If it is not possible to put such notice in a particular Source
Code file due to its structure, then You must include such notice in a
location (such as a relevant directory) where a user would be likely
to look for such a notice. If You created one or more Modification(s)
You may add your name as a Contributor to the notice described in
Exhibit A. You must also duplicate this License in any documentation
for the Source Code where You describe recipients' rights or ownership
rights relating to Covered Code. You may choose to offer, and to
charge a fee for, warranty, support, indemnity or liability
obligations to one or more recipients of Covered Code. However, You
may do so only on Your own behalf, and not on behalf of the Initial
Developer or any Contributor. You must make it absolutely clear than
any such warranty, support, indemnity or liability obligation is
offered by You alone, and You hereby agree to indemnify the Initial
Developer and every Contributor for any liability incurred by the
Initial Developer or such Contributor as a result of warranty,
support, indemnity or liability terms You offer.
3.6. Distribution of Executable Versions.
You may distribute Covered Code in Executable form only if the
requirements of Section 3.1-3.5 have been met for that Covered Code,
and if You include a notice stating that the Source Code version of
the Covered Code is available under the terms of this License,
including a description of how and where You have fulfilled the
obligations of Section 3.2. The notice must be conspicuously included
in any notice in an Executable version, related documentation or
collateral in which You describe recipients' rights relating to the
Covered Code. You may distribute the Executable version of Covered
Code or ownership rights under a license of Your choice, which may
contain terms different from this License, provided that You are in
compliance with the terms of this License and that the license for the
Executable version does not attempt to limit or alter the recipient's
rights in the Source Code version from the rights set forth in this
License. If You distribute the Executable version under a different
license You must make it absolutely clear that any terms which differ
from this License are offered by You alone, not by the Initial
Developer or any Contributor. You hereby agree to indemnify the
Initial Developer and every Contributor for any liability incurred by
the Initial Developer or such Contributor as a result of any such
terms You offer.
3.7. Larger Works.
You may create a Larger Work by combining Covered Code with other code
not governed by the terms of this License and distribute the Larger
Work as a single product. In such a case, You must make sure the
requirements of this License are fulfilled for the Covered Code.
4. Inability to Comply Due to Statute or Regulation.
If it is impossible for You to comply with any of the terms of this
License with respect to some or all of the Covered Code due to
statute, judicial order, or regulation then You must: (a) comply with
the terms of this License to the maximum extent possible; and (b)
describe the limitations and the code they affect. Such description
must be included in the LEGAL file described in Section 3.4 and must
be included with all distributions of the Source Code. Except to the
extent prohibited by statute or regulation, such description must be
sufficiently detailed for a recipient of ordinary skill to be able to
understand it.
5. Application of this License.
This License applies to code to which the Initial Developer has
attached the notice in Exhibit A and to related Covered Code.
6. Versions of the License.
6.1. New Versions.
Netscape Communications Corporation ("Netscape") may publish revised
and/or new versions of the License from time to time. Each version
will be given a distinguishing version number.
6.2. Effect of New Versions.
Once Covered Code has been published under a particular version of the
License, You may always continue to use it under the terms of that
version. You may also choose to use such Covered Code under the terms
of any subsequent version of the License published by Netscape. No one
other than Netscape has the right to modify the terms applicable to
Covered Code created under this License.
6.3. Derivative Works.
If You create or use a modified version of this License (which you may
only do in order to apply it to code which is not already Covered Code
governed by this License), You must (a) rename Your license so that
the phrases "Mozilla", "MOZILLAPL", "MOZPL", "Netscape",
"MPL", "NPL" or any confusingly similar phrase do not appear in your
license (except to note that your license differs from this License)
and (b) otherwise make it clear that Your version of the license
contains terms which differ from the Mozilla Public License and
Netscape Public License. (Filling in the name of the Initial
Developer, Original Code or Contributor in the notice described in
Exhibit A shall not of themselves be deemed to be modifications of
this License.)
7. DISCLAIMER OF WARRANTY.
COVERED CODE IS PROVIDED UNDER THIS LICENSE ON AN "AS IS" BASIS,
WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
WITHOUT LIMITATION, WARRANTIES THAT THE COVERED CODE IS FREE OF
DEFECTS, MERCHANTABLE, FIT FOR A PARTICULAR PURPOSE OR NON-INFRINGING.
THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE COVERED CODE
IS WITH YOU. SHOULD ANY COVERED CODE PROVE DEFECTIVE IN ANY RESPECT,
YOU (NOT THE INITIAL DEVELOPER OR ANY OTHER CONTRIBUTOR) ASSUME THE
COST OF ANY NECESSARY SERVICING, REPAIR OR CORRECTION. THIS DISCLAIMER
OF WARRANTY CONSTITUTES AN ESSENTIAL PART OF THIS LICENSE. NO USE OF
ANY COVERED CODE IS AUTHORIZED HEREUNDER EXCEPT UNDER THIS DISCLAIMER.
8. TERMINATION.
8.1. This License and the rights granted hereunder will terminate
automatically if You fail to comply with terms herein and fail to cure
such breach within 30 days of becoming aware of the breach. All
sublicenses to the Covered Code which are properly granted shall
survive any termination of this License. Provisions which, by their
nature, must remain in effect beyond the termination of this License
shall survive.
8.2. If You initiate litigation by asserting a patent infringement
claim (excluding declatory judgment actions) against Initial Developer
or a Contributor (the Initial Developer or Contributor against whom
You file such action is referred to as "Participant") alleging that:
(a) such Participant's Contributor Version directly or indirectly
infringes any patent, then any and all rights granted by such
Participant to You under Sections 2.1 and/or 2.2 of this License
shall, upon 60 days notice from Participant terminate prospectively,
unless if within 60 days after receipt of notice You either: (i)
agree in writing to pay Participant a mutually agreeable reasonable
royalty for Your past and future use of Modifications made by such
Participant, or (ii) withdraw Your litigation claim with respect to
the Contributor Version against such Participant. If within 60 days
of notice, a reasonable royalty and payment arrangement are not
mutually agreed upon in writing by the parties or the litigation claim
is not withdrawn, the rights granted by Participant to You under
Sections 2.1 and/or 2.2 automatically terminate at the expiration of
the 60 day notice period specified above.
(b) any software, hardware, or device, other than such Participant's
Contributor Version, directly or indirectly infringes any patent, then
any rights granted to You by such Participant under Sections 2.1(b)
and 2.2(b) are revoked effective as of the date You first made, used,
sold, distributed, or had made, Modifications made by that
Participant.
8.3. If You assert a patent infringement claim against Participant
alleging that such Participant's Contributor Version directly or
indirectly infringes any patent where such claim is resolved (such as
by license or settlement) prior to the initiation of patent
infringement litigation, then the reasonable value of the licenses
granted by such Participant under Sections 2.1 or 2.2 shall be taken
into account in determining the amount or value of any payment or
license.
8.4. In the event of termination under Sections 8.1 or 8.2 above,
all end user license agreements (excluding distributors and resellers)
which have been validly granted by You or any distributor hereunder
prior to termination shall survive termination.
9. LIMITATION OF LIABILITY.
UNDER NO CIRCUMSTANCES AND UNDER NO LEGAL THEORY, WHETHER TORT
(INCLUDING NEGLIGENCE), CONTRACT, OR OTHERWISE, SHALL YOU, THE INITIAL
DEVELOPER, ANY OTHER CONTRIBUTOR, OR ANY DISTRIBUTOR OF COVERED CODE,
OR ANY SUPPLIER OF ANY OF SUCH PARTIES, BE LIABLE TO ANY PERSON FOR
ANY INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES OF ANY
CHARACTER INCLUDING, WITHOUT LIMITATION, DAMAGES FOR LOSS OF GOODWILL,
WORK STOPPAGE, COMPUTER FAILURE OR MALFUNCTION, OR ANY AND ALL OTHER
COMMERCIAL DAMAGES OR LOSSES, EVEN IF SUCH PARTY SHALL HAVE BEEN
INFORMED OF THE POSSIBILITY OF SUCH DAMAGES. THIS LIMITATION OF
LIABILITY SHALL NOT APPLY TO LIABILITY FOR DEATH OR PERSONAL INJURY
RESULTING FROM SUCH PARTY'S NEGLIGENCE TO THE EXTENT APPLICABLE LAW
PROHIBITS SUCH LIMITATION. SOME JURISDICTIONS DO NOT ALLOW THE
EXCLUSION OR LIMITATION OF INCIDENTAL OR CONSEQUENTIAL DAMAGES, SO
THIS EXCLUSION AND LIMITATION MAY NOT APPLY TO YOU.
10. U.S. GOVERNMENT END USERS.
The Covered Code is a "commercial item," as that term is defined in
48 C.F.R. 2.101 (Oct. 1995), consisting of "commercial computer
software" and "commercial computer software documentation," as such
terms are used in 48 C.F.R. 12.212 (Sept. 1995). Consistent with 48
C.F.R. 12.212 and 48 C.F.R. 227.7202-1 through 227.7202-4 (June 1995),
all U.S. Government End Users acquire Covered Code with only those
rights set forth herein.
11. MISCELLANEOUS.
This License represents the complete agreement concerning subject
matter hereof. If any provision of this License is held to be
unenforceable, such provision shall be reformed only to the extent
necessary to make it enforceable. This License shall be governed by
California law provisions (except to the extent applicable law, if
any, provides otherwise), excluding its conflict-of-law provisions.
With respect to disputes in which at least one party is a citizen of,
or an entity chartered or registered to do business in the United
States of America, any litigation relating to this License shall be
subject to the jurisdiction of the Federal Courts of the Northern
District of California, with venue lying in Santa Clara County,
California, with the losing party responsible for costs, including
without limitation, court costs and reasonable attorneys' fees and
expenses. The application of the United Nations Convention on
Contracts for the International Sale of Goods is expressly excluded.
Any law or regulation which provides that the language of a contract
shall be construed against the drafter shall not apply to this
License.
12. RESPONSIBILITY FOR CLAIMS.
As between Initial Developer and the Contributors, each party is
responsible for claims and damages arising, directly or indirectly,
out of its utilization of rights under this License and You agree to
work with Initial Developer and Contributors to distribute such
responsibility on an equitable basis. Nothing herein is intended or
shall be deemed to constitute any admission of liability.
13. MULTIPLE-LICENSED CODE.
Initial Developer may designate portions of the Covered Code as
"Multiple-Licensed". "Multiple-Licensed" means that the Initial
Developer permits you to utilize portions of the Covered Code under
Your choice of the NPL or the alternative licenses, if any, specified
by the Initial Developer in the file described in Exhibit A.
EXHIBIT A -Mozilla Public License.
``The contents of this file are subject to the Mozilla Public License
Version 1.1 (the "License"); you may not use this file except in
compliance with the License. You may obtain a copy of the License at
http://www.mozilla.org/MPL/
Software distributed under the License is distributed on an "AS IS"
basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the
License for the specific language governing rights and limitations
under the License.
The Original Code is ______________________________________.
The Initial Developer of the Original Code is ________________________.
Portions created by ______________________ are Copyright (C) ______
_______________________. All Rights Reserved.
Contributor(s): ______________________________________.
Alternatively, the contents of this file may be used under the terms
of the _____ license (the "[___] License"), in which case the
provisions of [______] License are applicable instead of those
above. If you wish to allow use of your version of this file only
under the terms of the [____] License and not to allow others to use
your version of this file under the MPL, indicate your decision by
deleting the provisions above and replace them with the notice and
other provisions required by the [___] License. If you do not delete
the provisions above, a recipient may use your version of this file
under either the MPL or the [___] License."
[NOTE: The text of this Exhibit A may differ slightly from the text of
the notices in the Source Code files of the Original Code. You should
use the text of this Exhibit A rather than the text found in the
Original Code Source Code for Your Modifications.]

View File

@ -1,182 +0,0 @@
About Hunspell
==============
NOTICE: Version 2 is in the works. For contributing see
[version 2 specification][v2spec] and the folder `src/hunspell2`.
[v2spec]: https://github.com/hunspell/hunspell/wiki/Version-2-Specification
Hunspell is a spell checker and morphological analyzer library and program
designed for languages with rich morphology and complex word compounding or
character encoding. Hunspell interfaces: Ispell-like terminal interface
using Curses library, Ispell pipe interface, C++ class and C functions.
Hunspell's code base comes from the OpenOffice.org MySpell
(http://lingucomponent.openoffice.org/MySpell-3.zip). See README.MYSPELL,
AUTHORS.MYSPELL and license.myspell files.
Hunspell is designed to eventually replace Myspell in OpenOffice.org.
Main features of Hunspell spell checker and morphological analyzer:
- Unicode support (affix rules work only with the first 65535 Unicode
characters)
- Morphological analysis (in custom item and arrangement style) and stemming
- Max. 65535 affix classes and twofold affix stripping (for agglutinative
languages, like Azeri, Basque, Estonian, Finnish, Hungarian, Turkish, etc.)
- Support complex compoundings (for example, Hungarian and German)
- Support language specific features (for example, special casing of
Azeri and Turkish dotted i, or German sharp s)
- Handle conditional affixes, circumfixes, fogemorphemes,
forbidden words, pseudoroots and homonyms.
- Free software. Versions 1.x are licenced under LGPL, GPL, MPL tri-license.
Version 2 is licenced only under GNU LGPL.
Compiling on GNU/Linux and Unixes
=================================
autoreconf -vfi
./configure
make
sudo make install
sudo ldconfig
For dictionary development, use the `--with-warnings` option of configure.
For interactive user interface of Hunspell executable, use the `--with-ui option`.
The developer packages you need to compile Hunspell's interface:
autoconf automake autopoint libtool g++
Optional developer packages:
- ncurses (need for --with-ui), eg. libncursesw5 for UTF-8
- readline (for fancy input line editing,
configure parameter: --with-readline)
- locale and gettext (but you can also use the
--with-included-gettext configure parameter)
Compiling on Windows
====================
## 1. Compiling with Mingw64 and MSYS2
Download Msys2, update everything and install the following packages:
pacman -S base-devel mingw-w64-x86_64-toolchain mingw-w64-x86_64-libtool
Open Mingw-w64 Win64 prompt and compile the same way as on Linux, see above.
## 2. Compiling in Cygwin environment
Download and install Cygwin environment for Windows with the following
extra packages:
- make
- automake
- autoconf
- libtool
- gcc-g++ development package
- ncurses, readline (for user interface)
- iconv (character conversion)
Then compile the same way as on Linux. Cygwin builds depend on Cygwin1.dll.
Debugging
=========
For debugging we need to create a debug build and then we need to start `gdb`.
make clean
make CXXFLAGS='-g -O0'
libtool --mode=execute gdb src/tools/hunspell
Testing
=======
Testing Hunspell (see tests in tests/ subdirectory):
make check
or with Valgrind debugger:
make check
VALGRIND=[Valgrind_tool] make check
For example:
make check
VALGRIND=memcheck make check
Documentation
=============
features and dictionary format:
man 5 hunspell
man hunspell
hunspell -h
http://hunspell.github.io/
Usage
=====
The src/tools directory contains ten executables after compiling:
- affixcompress: dictionary generation from large (millions of words)
vocabularies
- analyze: example of spell checking, stemming and morphological analysis
- chmorph: example of automatic morphological generation and conversion
- example: example of spell checking and suggestion
- hunspell: main program for spell checking and others (see manual)
- hunzip: decompressor of hzip format
- hzip: compressor of hzip format
- makealias: alias compression (Hunspell only, not back compatible with MySpell)
- munch: dictionary generation from vocabularies (it needs an affix file, too).
- unmunch: list all recognized words of a MySpell dictionary
- wordforms: word generation (Hunspell version of unmunch)
After compiling and installing (see INSTALL) you can
run the Hunspell spell checker (compiled with user interface)
with a Hunspell or Myspell dictionary:
hunspell -d en_US text.txt
or without interface:
hunspell
hunspell -d en_UK -l <text.txt
Dictionaries consist of an affix and dictionary file, see tests/
or http://wiki.services.openoffice.org/wiki/Dictionaries.
Using Hunspell library with GCC
===============================
Including in your program:
#include <hunspell.hxx>
Linking with Hunspell static library:
g++ -lhunspell example.cxx
Dictionaries
------------
Myspell & Hunspell dictionaries:
- http://extensions.libreoffice.org
- http://cgit.freedesktop.org/libreoffice/dictionaries
- http://extensions.openoffice.org
- http://wiki.services.openoffice.org/wiki/Dictionaries
Aspell dictionaries (need some conversion):
- ftp://ftp.gnu.org/gnu/aspell/dict
Conversion steps: see relevant feature request at http://hunspell.github.io/ .
László Németh
nemeth at numbertext org

View File

@ -1,136 +0,0 @@
Many thanks to the following contributors and supporters:
Mehmet Akin
Göran Andersson
Lars Aronsson
Ruud Baars
Bartkó Zoltán
Mathias Bauer
Bencsáth Boldizsár
Bíró Árpád
Ingo H. de Boer
Simon Brouwer
Jeppe Bundsgaard
Ginn Chen
Tomáš Chvátal
Aaron Digulla
Dmitri Gabinski
Dvornik László
David Einstein
Rene Engelhard
Frederik Fouvry
Flemming Frandsen
Serge Gautherie
Marek Gleń
Gavins at OOo
Gefferth András
Godó Ferenc
Goldman Eleonóra
Steinar H. Gunderson
Halácsy Péter
Chris Halls
Khaled Hosny
Izsók András
Björn Jacke
Mike Tian-Jian Jiang
Dafydd Jones
Ryan Jones
Jean-Christophe Helary
Kevin Hendricks
Martin Hollmichel
Pavel Janík
John Winters
Mohamed Kebdani
Kelemen Gábor
Shewangizaw Gulilat
Kéménczy Kálmán
Dan Kenigsberg
Pham Ngoc Khanh
Khiraly László
Koblinger Egmont
Kornai András
Tor Lillqvist
Christian Lohmaier
Robert Longson
Marot at SF dot net
Mark McClain
Caolan McNamara
Michael Meeks
Moheb Mekhaiel
Laurie Mercer
Ladislav Michnovič
Ellis Miller
Giuseppe Modugno
János Mohácsi
Bram Moolenaar
Daniel Naber
Nagy Viktor
John Nisly
Noll János
S Page
Christophe Paris
Malcolm Parsons
Sylvain Paschein
Volkov Peter
Bryan Petty
Harri Pitkänen
Davide Prina
Kevin F. Quinn
Erdal Ronahi
Olivier Ronez
Bernhard Rosenkraenzer
Sarlós Tamás
Thobias Schlemmer
Jan Seeger
Jose da Silva
Paulo Ney de Souza
Roland Smith
Munzir Taha
Timeless at bemail dot org
Tímár András
Tonal at OOo
Török László
Trón Viktor
Gianluca Turconi
Ryan VanderMeulen
Varga Dániel
Elio Voci
Miha Vrhovnik
Martijn Wargers
Michel Weimerskirch
Brett Wilson
Friedel Wolff
Daniel Yacob
Gábor Zahemszky
Taha Zerrouki
and others (see also AUTHORS.myspell)
FSF.hu Foundation
http://www.fsf.hu
LibreOffice community
http://www.libreoffice.org
MOKK Research Centre
Budapest University of Technology and Economics
Sociology and Communications Department
http://www.mokk.bme.hu
Hungarian Ministry of Informatics and Telecommunications
IMEDIA Kft.
http://www.imedia.hu
OpenOffice.org community
http://www.openoffice.org
OpenTaal Foundation, Netherlands and
Dutch Language Union (Nederlandse Taalunie)
http://opentaal.org
UHU-Linux Kft.
Thanks,
Németh László
nemeth at numbertext org

View File

@ -1,4 +0,0 @@
* shared dictionaries for multi-user environment
* improve compound handling
* Unicode unmunch (munch)
* forbiddenword and pseudoword support in unmunch

View File

@ -1 +0,0 @@
testparser

View File

@ -1,205 +0,0 @@
/* config.h.in. Generated from configure.ac by autoheader. */
/* Define to one of `_getb67', `GETB67', `getb67' for Cray-2 and Cray-YMP
systems. This function is required for `alloca.c' support on those systems.
*/
#define CRAY_STACKSEG_END 1
/* Define to 1 if using `alloca.c'. */
#define C_ALLOCA 1
/* Define to 1 if translation of program messages to the user's native
language is requested. */
#undef ENABLE_NLS
/* Define to 1 if you have `alloca', as a function or macro. */
#define HAVE_ALLOCA 1
/* Define to 1 if you have <alloca.h> and it should be used (not on Ultrix).
*/
#define HAVE_ALLOCA_H 1
/* Define to 1 if you have the <argz.h> header file. */
#define HAVE_ARGZ_H 1
/* "Define if you have the <curses.h> header" */
#undef HAVE_CURSES_H
/* Define if the GNU dcgettext() function is already present or preinstalled.
*/
#define HAVE_DCGETTEXT 1
/* Define to 1 if you have the <dlfcn.h> header file. */
#define HAVE_DLFCN_H 1
/* Define to 1 if you have the <error.h> header file. */
#define HAVE_ERROR_H 1
/* Define to 1 if you have the <fcntl.h> header file. */
#define HAVE_FCNTL_H 1
/* Define to 1 if you have the `feof_unlocked' function. */
#define HAVE_FEOF_UNLOCKED 1
/* Define to 1 if you have the `fgets_unlocked' function. */
#define HAVE_FGETS_UNLOCKED 1
/* Define to 1 if you have the `getcwd' function. */
#define HAVE_GETCWD 1
/* Define to 1 if you have the `getc_unlocked' function. */
#define HAVE_GETC_UNLOCKED 1
/* Define to 1 if you have the `getegid' function. */
#define HAVE_GETEGID 1
/* Define to 1 if you have the `geteuid' function. */
#define HAVE_GETEUID 1
/* Define to 1 if you have the `getgid' function. */
#define HAVE_GETGID 1
/* Define to 1 if you have the `getpagesize' function. */
#define HAVE_GETPAGESIZE 1
/* Define if the GNU gettext() function is already present or preinstalled. */
#define HAVE_GETTEXT 1
/* Define to 1 if you have the `getuid' function. */
#define HAVE_GETUID 1
/* Define if you have the iconv() function. */
#undef HAVE_ICONV
/* Define to 1 if you have the <inttypes.h> header file. */
#define HAVE_INTTYPES_H 1
/* Define if you have <langinfo.h> and nl_langinfo(CODESET). */
#define HAVE_LANGINFO_CODESET 1
/* Define if your <locale.h> file defines LC_MESSAGES. */
#define HAVE_LC_MESSAGES 1
/* Define to 1 if you have the <libintl.h> header file. */
#define HAVE_LIBINTL_H 1
/* Define to 1 if you have the <limits.h> header file. */
#define HAVE_LIMITS_H 1
/* Define to 1 if you have the <locale.h> header file. */
#define HAVE_LOCALE_H 1
/* Define to 1 if you have the `memchr' function. */
#define HAVE_MEMCHR 1
/* Define to 1 if you have the <memory.h> header file. */
#define HAVE_MEMORY_H 1
/* Define to 1 if you have the `mempcpy' function. */
#define HAVE_MEMPCPY 1
/* Define to 1 if you have a working `mmap' system call. */
#define HAVE_MMAP 1
/* Define to 1 if you have the `munmap' function. */
#define HAVE_MUNMAP 1
/* "Define if you have the <ncursesw/curses.h> header" */
#define HAVE_NCURSESW_H 1
/* Define to 1 if you have the <nl_types.h> header file. */
#define HAVE_NL_TYPES_H 1
/* Define to 1 if you have the `putenv' function. */
#define HAVE_PUTENV 1
/* "Define if you have fancy command input editing with Readline" */
#undef HAVE_READLINE
/* Define to 1 if you have the `setenv' function. */
#define HAVE_SETENV 1
/* Define to 1 if you have the `setlocale' function. */
#define HAVE_SETLOCALE 1
/* Define to 1 if you have the <stddef.h> header file. */
#define HAVE_STDDEF_H 1
/* Define to 1 if you have the <stdint.h> header file. */
#define HAVE_STDINT_H 1
/* Define to 1 if you have the <stdlib.h> header file. */
#define HAVE_STDLIB_H 1
/* Define to 1 if you have the `stpcpy' function. */
#define HAVE_STPCPY 1
/* Define to 1 if you have the `strcasecmp' function. */
#define HAVE_STRCASECMP 1
/* Define to 1 if you have the `strchr' function. */
#define HAVE_STRCHR 1
/* Define to 1 if you have the `strdup' function. */
#define HAVE_STRDUP 1
/* Define to 1 if you have the <strings.h> header file. */
#define HAVE_STRINGS_H 1
/* Define to 1 if you have the <string.h> header file. */
#define HAVE_STRING_H 1
/* Define to 1 if you have the `strstr' function. */
#define HAVE_STRSTR 1
/* Define to 1 if you have the `strtoul' function. */
#define HAVE_STRTOUL 1
/* Define to 1 if you have the <sys/param.h> header file. */
#define HAVE_SYS_PARAM_H 1
/* Define to 1 if you have the <sys/stat.h> header file. */
#define HAVE_SYS_STAT_H 1
/* Define to 1 if you have the <sys/types.h> header file. */
#define HAVE_SYS_TYPES_H 1
/* Define to 1 if you have the `tsearch' function. */
#define HAVE_TSEARCH 1
/* Define to 1 if you have the <unistd.h> header file. */
#define HAVE_UNISTD_H 1
/* Define to 1 if you have the `__argz_count' function. */
#define HAVE___ARGZ_COUNT 1
/* Define to 1 if you have the `__argz_next' function. */
#define HAVE___ARGZ_NEXT 1
/* Define to 1 if you have the `__argz_stringify' function. */
#define HAVE___ARGZ_STRINGIFY 1
/* "Define if you need warning messages" */
#define HUNSPELL_WARNING_ON
/* Define as const if the declaration of iconv() needs const. */
#define ICONV_CONST 1
/* Name of package */
#define PACKAGE
/* Define to the address where bug reports for this package should be sent. */
#define PACKAGE_BUGREPORT
/* Define to the full name of this package. */
#define PACKAGE_NAME
/* Define to the full name and version of this package. */
#define PACKAGE_STRING
/* Define to the one symbol short name of this package. */
#define PACKAGE_TARNAME
/* Define to the version of this package. */
#define PACKAGE_VERSION "1.6.2"
#define VERSION "1.6.2"

23
3rdparty/hunspell/1.7.0/AUTHORS vendored Normal file
View File

@ -0,0 +1,23 @@
Author: László Németh
MySpell's (Hunspell's code base) author: Kevin Hendricks
Maintainer, distinguished contributor: Caolán McNamara
Author of rule-based transformation code for phonetic suggestions
(PHONE/phonet.cxx, used by English dictionaries): Björn Jacke
Hunspell/MySpell code base is result of work of several
contributors. See git log, ./THANKS, ./Changelog, ./Changelog.O,
MySpell's README and CONTRIBUTORS files for their contributions.
Note: Following contributors are not owners and
not representatives of Hunspell, and they haven't got
permission from Hunspell's author to act on the behalf
of Hunspell project: Sander van Geloven, Dimitri Mijoski
If you would like to support Hunspell, join the
development or contact the author.

340
3rdparty/hunspell/1.7.0/COPYING vendored Normal file
View File

@ -0,0 +1,340 @@
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
License is intended to guarantee your freedom to share and change free
software--to make sure the software is free for all its users. This
General Public License applies to most of the Free Software
Foundation's software and to any other program whose authors commit to
using it. (Some other Free Software Foundation software is covered by
the GNU Lesser General Public License instead.) You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
this service if you wish), that you receive source code or can get it
if you want it, that you can change the software or use pieces of it
in new free programs; and that you know you can do these things.
To protect your rights, we need to make restrictions that forbid
anyone to deny you these rights or to ask you to surrender the rights.
These restrictions translate to certain responsibilities for you if you
distribute copies of the software, or if you modify it.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must give the recipients all the rights that
you have. You must make sure that they, too, receive or can get the
source code. And you must show them these terms so they know their
rights.
We protect your rights with two steps: (1) copyright the software, and
(2) offer you this license which gives you legal permission to copy,
distribute and/or modify the software.
Also, for each author's protection and ours, we want to make certain
that everyone understands that there is no warranty for this free
software. If the software is modified by someone else and passed on, we
want its recipients to know that what they have is not the original, so
that any problems introduced by others will not reflect on the original
authors' reputations.
Finally, any free program is threatened constantly by software
patents. We wish to avoid the danger that redistributors of a free
program will individually obtain patent licenses, in effect making the
program proprietary. To prevent this, we have made it clear that any
patent must be licensed for everyone's free use or not licensed at all.
The precise terms and conditions for copying, distribution and
modification follow.
GNU GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License applies to any program or other work which contains
a notice placed by the copyright holder saying it may be distributed
under the terms of this General Public License. The "Program", below,
refers to any such program or work, and a "work based on the Program"
means either the Program or any derivative work under copyright law:
that is to say, a work containing the Program or a portion of it,
either verbatim or with modifications and/or translated into another
language. (Hereinafter, translation is included without limitation in
the term "modification".) Each licensee is addressed as "you".
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running the Program is not restricted, and the output from the Program
is covered only if its contents constitute a work based on the
Program (independent of having been made by running the Program).
Whether that is true depends on what the Program does.
1. You may copy and distribute 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 and disclaimer of warranty; keep intact all the
notices that refer to this License and to the absence of any warranty;
and give any other recipients of the Program a copy of this License
along with the Program.
You may charge a fee for the physical act of transferring a copy, and
you may at your option offer warranty protection in exchange for a fee.
2. You may modify your copy or copies of the Program or any portion
of it, thus forming a work based on the Program, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) You must cause the modified files to carry prominent notices
stating that you changed the files and the date of any change.
b) You must cause any work that you distribute or publish, that in
whole or in part contains or is derived from the Program or any
part thereof, to be licensed as a whole at no charge to all third
parties under the terms of this License.
c) If the modified program normally reads commands interactively
when run, you must cause it, when started running for such
interactive use in the most ordinary way, to print or display an
announcement including an appropriate copyright notice and a
notice that there is no warranty (or else, saying that you provide
a warranty) and that users may redistribute the program under
these conditions, and telling the user how to view a copy of this
License. (Exception: if the Program itself is interactive but
does not normally print such an announcement, your work based on
the Program is not required to print an announcement.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Program,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Program, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Program.
In addition, mere aggregation of another work not based on the Program
with the Program (or with a work based on the Program) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may copy and distribute the Program (or a work based on it,
under Section 2) in object code or executable form under the terms of
Sections 1 and 2 above provided that you also do one of the following:
a) Accompany it with the complete corresponding machine-readable
source code, which must be distributed under the terms of Sections
1 and 2 above on a medium customarily used for software interchange; or,
b) Accompany it with a written offer, valid for at least three
years, to give any third party, for a charge no more than your
cost of physically performing source distribution, a complete
machine-readable copy of the corresponding source code, to be
distributed under the terms of Sections 1 and 2 above on a medium
customarily used for software interchange; or,
c) Accompany it with the information you received as to the offer
to distribute corresponding source code. (This alternative is
allowed only for noncommercial distribution and only if you
received the program in object code or executable form with such
an offer, in accord with Subsection b above.)
The source code for a work means the preferred form of the work for
making modifications to it. For an executable work, complete source
code means all the source code for all modules it contains, plus any
associated interface definition files, plus the scripts used to
control compilation and installation of the executable. However, as a
special exception, the source code distributed need not include
anything that is normally distributed (in either source or binary
form) with the major components (compiler, kernel, and so on) of the
operating system on which the executable runs, unless that component
itself accompanies the executable.
If distribution of executable or object code is made by offering
access to copy from a designated place, then offering equivalent
access to copy the source code from the same place counts as
distribution of the source code, even though third parties are not
compelled to copy the source along with the object code.
4. You may not copy, modify, sublicense, or distribute the Program
except as expressly provided under this License. Any attempt
otherwise to copy, modify, sublicense or distribute the Program is
void, and will automatically terminate your rights under this License.
However, parties who have received copies, or rights, from you under
this License will not have their licenses terminated so long as such
parties remain in full compliance.
5. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Program or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Program (or any work based on the
Program), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Program or works based on it.
6. Each time you redistribute the Program (or any work based on the
Program), the recipient automatically receives a license from the
original licensor to copy, distribute or modify the Program subject to
these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties to
this License.
7. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
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
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Program at all. For example, if a patent
license would not permit royalty-free redistribution of the Program by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Program.
If any portion of this section is held invalid or unenforceable under
any particular circumstance, the balance of the section is intended to
apply and the section as a whole is intended to apply in other
circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system, which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
8. If the distribution and/or use of the Program is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Program under this License
may add an explicit geographical distribution limitation excluding
those countries, so that distribution is permitted only in or among
countries not thus excluded. In such case, this License incorporates
the limitation as if written in the body of this License.
9. The Free Software Foundation may publish revised and/or new versions
of the 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 a version number of this License which applies to it and "any
later version", you have the option of following the terms and conditions
either of that version or of any later version published by the Free
Software Foundation. If the Program does not specify a version number of
this License, you may choose any version ever published by the Free Software
Foundation.
10. If you wish to incorporate parts of the Program into other free
programs whose distribution conditions are different, write to the author
to ask for permission. For software which is copyrighted by the Free
Software Foundation, write to the Free Software Foundation; we sometimes
make exceptions for this. Our decision will be guided by the two goals
of preserving the free status of all derivatives of our free software and
of promoting the sharing and reuse of software generally.
NO WARRANTY
11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, 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.
12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
REDISTRIBUTE 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.
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
convey the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License along
with this program; if not, write to the Free Software Foundation, Inc.,
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
Also add information on how to contact you by electronic and paper mail.
If the program is interactive, make it output a short notice like this
when it starts in an interactive mode:
Gnomovision version 69, Copyright (C) year name of author
Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, the commands you use may
be called something other than `show w' and `show c'; they could even be
mouse-clicks or menu items--whatever suits your program.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the program, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the program
`Gnomovision' (which makes passes at compilers) written by James Hacker.
<signature of Ty Coon>, 1 April 1989
Ty Coon, President of Vice
This General Public License does not permit incorporating your program into
proprietary programs. If your program is a subroutine library, you may
consider it more useful to permit linking proprietary applications with the
library. If this is what you want to do, use the GNU Lesser General
Public License instead of this License.

503
3rdparty/hunspell/1.7.0/COPYING.LESSER vendored Normal file
View File

@ -0,0 +1,503 @@
GNU LESSER GENERAL PUBLIC LICENSE
Version 2.1, February 1999
Copyright (C) 1991, 1999 Free Software Foundation, Inc.
51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
[This is the first released version of the Lesser GPL. It also counts
as the successor of the GNU Library Public License, version 2, hence
the version number 2.1.]
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
Licenses are intended to guarantee your freedom to share and change
free software--to make sure the software is free for all its users.
This license, the Lesser General Public License, applies to some
specially designated software packages--typically libraries--of the
Free Software Foundation and other authors who decide to use it. You
can use it too, but we suggest you first think carefully about whether
this license or the ordinary General Public License is the better
strategy to use in any particular case, based on the explanations below.
When we speak of free software, we are referring to freedom of use,
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 this service if you wish); that you receive source code or can get
it if you want it; that you can change the software and use pieces of
it in new free programs; and that you are informed that you can do
these things.
To protect your rights, we need to make restrictions that forbid
distributors to deny you these rights or to ask you to surrender these
rights. These restrictions translate to certain responsibilities for
you if you distribute copies of the library or if you modify it.
For example, if you distribute copies of the library, whether gratis
or for a fee, you must give the recipients all the rights that we gave
you. You must make sure that they, too, receive or can get the source
code. If you link other code with the library, you must provide
complete object files to the recipients, so that they can relink them
with the library after making changes to the library and recompiling
it. And you must show them these terms so they know their rights.
We protect your rights with a two-step method: (1) we copyright the
library, and (2) we offer you this license, which gives you legal
permission to copy, distribute and/or modify the library.
To protect each distributor, we want to make it very clear that
there is no warranty for the free library. Also, if the library is
modified by someone else and passed on, the recipients should know
that what they have is not the original version, so that the original
author's reputation will not be affected by problems that might be
introduced by others.
Finally, software patents pose a constant threat to the existence of
any free program. We wish to make sure that a company cannot
effectively restrict the users of a free program by obtaining a
restrictive license from a patent holder. Therefore, we insist that
any patent license obtained for a version of the library must be
consistent with the full freedom of use specified in this license.
Most GNU software, including some libraries, is covered by the
ordinary GNU General Public License. This license, the GNU Lesser
General Public License, applies to certain designated libraries, and
is quite different from the ordinary General Public License. We use
this license for certain libraries in order to permit linking those
libraries into non-free programs.
When a program is linked with a library, whether statically or using
a shared library, the combination of the two is legally speaking a
combined work, a derivative of the original library. The ordinary
General Public License therefore permits such linking only if the
entire combination fits its criteria of freedom. The Lesser General
Public License permits more lax criteria for linking other code with
the library.
We call this license the "Lesser" General Public License because it
does Less to protect the user's freedom than the ordinary General
Public License. It also provides other free software developers Less
of an advantage over competing non-free programs. These disadvantages
are the reason we use the ordinary General Public License for many
libraries. However, the Lesser license provides advantages in certain
special circumstances.
For example, on rare occasions, there may be a special need to
encourage the widest possible use of a certain library, so that it becomes
a de-facto standard. To achieve this, non-free programs must be
allowed to use the library. A more frequent case is that a free
library does the same job as widely used non-free libraries. In this
case, there is little to gain by limiting the free library to free
software only, so we use the Lesser General Public License.
In other cases, permission to use a particular library in non-free
programs enables a greater number of people to use a large body of
free software. For example, permission to use the GNU C Library in
non-free programs enables many more people to use the whole GNU
operating system, as well as its variant, the GNU/Linux operating
system.
Although the Lesser General Public License is Less protective of the
users' freedom, it does ensure that the user of a program that is
linked with the Library has the freedom and the wherewithal to run
that program using a modified version of the Library.
The precise terms and conditions for copying, distribution and
modification follow. Pay close attention to the difference between a
"work based on the library" and a "work that uses the library". The
former contains code derived from the library, whereas the latter must
be combined with the library in order to run.
GNU LESSER GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License Agreement applies to any software library or other
program which contains a notice placed by the copyright holder or
other authorized party saying it may be distributed under the terms of
this Lesser General Public License (also called "this License").
Each licensee is addressed as "you".
A "library" means a collection of software functions and/or data
prepared so as to be conveniently linked with application programs
(which use some of those functions and data) to form executables.
The "Library", below, refers to any such software library or work
which has been distributed under these terms. A "work based on the
Library" means either the Library or any derivative work under
copyright law: that is to say, a work containing the Library or a
portion of it, either verbatim or with modifications and/or translated
straightforwardly into another language. (Hereinafter, translation is
included without limitation in the term "modification".)
"Source code" for a work means the preferred form of the work for
making modifications to it. For a library, complete source code means
all the source code for all modules it contains, plus any associated
interface definition files, plus the scripts used to control compilation
and installation of the library.
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running a program using the Library is not restricted, and output from
such a program is covered only if its contents constitute a work based
on the Library (independent of the use of the Library in a tool for
writing it). Whether that is true depends on what the Library does
and what the program that uses the Library does.
1. You may copy and distribute verbatim copies of the Library's
complete source code as you receive it, in any medium, provided that
you conspicuously and appropriately publish on each copy an
appropriate copyright notice and disclaimer of warranty; keep intact
all the notices that refer to this License and to the absence of any
warranty; and distribute a copy of this License along with the
Library.
You may charge a fee for the physical act of transferring a copy,
and you may at your option offer warranty protection in exchange for a
fee.
2. You may modify your copy or copies of the Library or any portion
of it, thus forming a work based on the Library, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) The modified work must itself be a software library.
b) You must cause the files modified to carry prominent notices
stating that you changed the files and the date of any change.
c) You must cause the whole of the work to be licensed at no
charge to all third parties under the terms of this License.
d) If a facility in the modified Library refers to a function or a
table of data to be supplied by an application program that uses
the facility, other than as an argument passed when the facility
is invoked, then you must make a good faith effort to ensure that,
in the event an application does not supply such function or
table, the facility still operates, and performs whatever part of
its purpose remains meaningful.
(For example, a function in a library to compute square roots has
a purpose that is entirely well-defined independent of the
application. Therefore, Subsection 2d requires that any
application-supplied function or table used by this function must
be optional: if the application does not supply it, the square
root function must still compute square roots.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Library,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Library, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote
it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Library.
In addition, mere aggregation of another work not based on the Library
with the Library (or with a work based on the Library) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may opt to apply the terms of the ordinary GNU General Public
License instead of this License to a given copy of the Library. To do
this, you must alter all the notices that refer to this License, so
that they refer to the ordinary GNU General Public License, version 2,
instead of to this License. (If a newer version than version 2 of the
ordinary GNU General Public License has appeared, then you can specify
that version instead if you wish.) Do not make any other change in
these notices.
Once this change is made in a given copy, it is irreversible for
that copy, so the ordinary GNU General Public License applies to all
subsequent copies and derivative works made from that copy.
This option is useful when you wish to copy part of the code of
the Library into a program that is not a library.
4. You may copy and distribute the Library (or a portion or
derivative of it, under Section 2) in object code or executable form
under the terms of Sections 1 and 2 above provided that you accompany
it with the complete corresponding machine-readable source code, which
must be distributed under the terms of Sections 1 and 2 above on a
medium customarily used for software interchange.
If distribution of object code is made by offering access to copy
from a designated place, then offering equivalent access to copy the
source code from the same place satisfies the requirement to
distribute the source code, even though third parties are not
compelled to copy the source along with the object code.
5. A program that contains no derivative of any portion of the
Library, but is designed to work with the Library by being compiled or
linked with it, is called a "work that uses the Library". Such a
work, in isolation, is not a derivative work of the Library, and
therefore falls outside the scope of this License.
However, linking a "work that uses the Library" with the Library
creates an executable that is a derivative of the Library (because it
contains portions of the Library), rather than a "work that uses the
library". The executable is therefore covered by this License.
Section 6 states terms for distribution of such executables.
When a "work that uses the Library" uses material from a header file
that is part of the Library, the object code for the work may be a
derivative work of the Library even though the source code is not.
Whether this is true is especially significant if the work can be
linked without the Library, or if the work is itself a library. The
threshold for this to be true is not precisely defined by law.
If such an object file uses only numerical parameters, data
structure layouts and accessors, and small macros and small inline
functions (ten lines or less in length), then the use of the object
file is unrestricted, regardless of whether it is legally a derivative
work. (Executables containing this object code plus portions of the
Library will still fall under Section 6.)
Otherwise, if the work is a derivative of the Library, you may
distribute the object code for the work under the terms of Section 6.
Any executables containing that work also fall under Section 6,
whether or not they are linked directly with the Library itself.
6. As an exception to the Sections above, you may also combine or
link a "work that uses the Library" with the Library to produce a
work containing portions of the Library, and distribute that work
under terms of your choice, provided that the terms permit
modification of the work for the customer's own use and reverse
engineering for debugging such modifications.
You must give prominent notice with each copy of the work that the
Library is used in it and that the Library and its use are covered by
this License. You must supply a copy of this License. If the work
during execution displays copyright notices, you must include the
copyright notice for the Library among them, as well as a reference
directing the user to the copy of this License. Also, you must do one
of these things:
a) Accompany the work with the complete corresponding
machine-readable source code for the Library including whatever
changes were used in the work (which must be distributed under
Sections 1 and 2 above); and, if the work is an executable linked
with the Library, with the complete machine-readable "work that
uses the Library", as object code and/or source code, so that the
user can modify the Library and then relink to produce a modified
executable containing the modified Library. (It is understood
that the user who changes the contents of definitions files in the
Library will not necessarily be able to recompile the application
to use the modified definitions.)
b) Use a suitable shared library mechanism for linking with the
Library. A suitable mechanism is one that (1) uses at run time a
copy of the library already present on the user's computer system,
rather than copying library functions into the executable, and (2)
will operate properly with a modified version of the library, if
the user installs one, as long as the modified version is
interface-compatible with the version that the work was made with.
c) Accompany the work with a written offer, valid for at
least three years, to give the same user the materials
specified in Subsection 6a, above, for a charge no more
than the cost of performing this distribution.
d) If distribution of the work is made by offering access to copy
from a designated place, offer equivalent access to copy the above
specified materials from the same place.
e) Verify that the user has already received a copy of these
materials or that you have already sent this user a copy.
For an executable, the required form of the "work that uses the
Library" must include any data and utility programs needed for
reproducing the executable from it. However, as a special exception,
the materials to be distributed need not include anything that is
normally distributed (in either source or binary form) with the major
components (compiler, kernel, and so on) of the operating system on
which the executable runs, unless that component itself accompanies
the executable.
It may happen that this requirement contradicts the license
restrictions of other proprietary libraries that do not normally
accompany the operating system. Such a contradiction means you cannot
use both them and the Library together in an executable that you
distribute.
7. You may place library facilities that are a work based on the
Library side-by-side in a single library together with other library
facilities not covered by this License, and distribute such a combined
library, provided that the separate distribution of the work based on
the Library and of the other library facilities is otherwise
permitted, and provided that you do these two things:
a) Accompany the combined library with a copy of the same work
based on the Library, uncombined with any other library
facilities. This must be distributed under the terms of the
Sections above.
b) Give prominent notice with the combined library of the fact
that part of it is a work based on the Library, and explaining
where to find the accompanying uncombined form of the same work.
8. You may not copy, modify, sublicense, link with, or distribute
the Library except as expressly provided under this License. Any
attempt otherwise to copy, modify, sublicense, link with, or
distribute the Library is void, and will automatically terminate your
rights under this License. However, parties who have received copies,
or rights, from you under this License will not have their licenses
terminated so long as such parties remain in full compliance.
9. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Library or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Library (or any work based on the
Library), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Library or works based on it.
10. Each time you redistribute the Library (or any work based on the
Library), the recipient automatically receives a license from the
original licensor to copy, distribute, link with or modify the Library
subject to these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties with
this License.
11. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
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
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Library at all. For example, if a patent
license would not permit royalty-free redistribution of the Library by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Library.
If any portion of this section is held invalid or unenforceable under any
particular circumstance, the balance of the section is intended to apply,
and the section as a whole is intended to apply in other circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
12. If the distribution and/or use of the Library is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Library under this License may add
an explicit geographical distribution limitation excluding those countries,
so that distribution is permitted only in or among countries not thus
excluded. In such case, this License incorporates the limitation as if
written in the body of this License.
13. The Free Software Foundation may publish revised and/or new
versions of the Lesser 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 Library
specifies a version number of this License which applies to it and
"any later version", you have the option of following the terms and
conditions either of that version or of any later version published by
the Free Software Foundation. If the Library does not specify a
license version number, you may choose any version ever published by
the Free Software Foundation.
14. If you wish to incorporate parts of the Library into other free
programs whose distribution conditions are incompatible with these,
write to the author to ask for permission. For software which is
copyrighted by the Free Software Foundation, write to the Free
Software Foundation; we sometimes make exceptions for this. Our
decision will be guided by the two goals of preserving the free status
of all derivatives of our free software and of promoting the sharing
and reuse of software generally.
NO WARRANTY
15. BECAUSE THE LIBRARY IS LICENSED FREE OF CHARGE, THERE IS NO
WARRANTY FOR THE LIBRARY, TO THE EXTENT PERMITTED BY APPLICABLE LAW.
EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR
OTHER PARTIES PROVIDE THE LIBRARY "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
LIBRARY IS WITH YOU. SHOULD THE LIBRARY PROVE DEFECTIVE, YOU ASSUME
THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN
WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY
AND/OR REDISTRIBUTE THE LIBRARY 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
LIBRARY (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 LIBRARY TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
DAMAGES.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Libraries
If you develop a new library, and you want it to be of the greatest
possible use to the public, we recommend making it free software that
everyone can redistribute and change. You can do so by permitting
redistribution under these terms (or, alternatively, under the terms of the
ordinary General Public License).
To apply these terms, attach the following notices to the library. It is
safest to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least the
"copyright" line and a pointer to where the full notice is found.
<one line to give the library's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
This library 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with this library; if not, write to the Free Software
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
Also add information on how to contact you by electronic and paper mail.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the library, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the
library `Frob' (a library for tweaking knobs) written by James Random Hacker.
<signature of Ty Coon>, 1 April 1990
Ty Coon, President of Vice
That's all there is to it!

View File

@ -1683,7 +1683,7 @@ changes:
* src/hunspell/suggestmgr.cxx:
- fix missing suggestions for words with crossed prefix and suffix
- fix redundant non compound word checking
- fix redundant non-compound word checking
- fix losing suggestions problem. Bug reported by Dmitri Gabinski.
* src/hunspell/dictmgr.*:

839
3rdparty/hunspell/1.7.0/NEWS vendored Normal file
View File

@ -0,0 +1,839 @@
2018-11-12: Hunspell 1.7.0 release:
New features and bug fixes by László Németh, supported by FSF.hu Foundation:
- No annoying suggestion times any more, especially in languages with
compound word handling and complex morphology. By adding balanced
multi-level time limits, now the guaranteed suggestion time is there
within half a second, not seconds (nor dozen of seconds or more
in extreme cases) for longer misspellings, too.
- add SPELLML support for run-time dictionary extension with optional
affixation of user words. See new "Grammar By" feature of
language-specific user dictionaries of LibreOffice 6.0:
News: https://wiki.documentfoundation.org/ReleaseNotes/6.0#.E2.80.9CGrammar_By.E2.80.9D_spell_checking
Screencast with English example: https://www.youtube.com/watch?v=EsS3gaBTfOo
Screencast with German example: https://www.youtube.com/watch?v=aYVFDqCUb6I
- Improved, highly customizable suggestions on level of dictionary words:
Pronunciations and typical misspellings defined by optional "ph:" fields of
the dictionary words are used not only in n-gram suggestions, but as
elements of the REP replacement list getting the highest priority in normal
suggestions, also giving the best suggestions for short words, too.
More information: see "ph:" in man 5 hunspell.
- Handling multiple word suggestions is much more easier. Like in a
traditional spelling dictionary, for example, to get the correct suggestion
"a lot" for the typical misspelling "alot" at the first place, now it's
enough to put the following line to the dic(tionary) file:
a lot
- Limit compound overgeneration by dictionary based word pairs:
Now it's possible to filter bad compound words by listing
the correct word pairs with space in the dictionary, as in a traditional
spelling dictionary.
- clean-up suggestion:
- no n-gram and compound word suggestions, if "good" suggestion
exists, ie. uppercase, REP, ph: or dictionary word pair suggestions
- word pairs are always suggested, if they exist in the dic file
- word pairs have top priority in suggestions, and
these are the only suggestions if there is no other good suggestion.
- also dictionary word pairs separated by dash instead of space
are handled specially in two-word suggestion (depending from the
language)
- limit bad suggestions by improved n-gram suggestion rules:
don't suggest capitalized dictionary words for lower
case misspellings in n-gram suggestions, except
- PHONE usage, or
- in the case of German, where not only proper
nouns are capitalized, or
- the capitalized word has special pronunciation
and don't suggest if the difference of lengths of misspellings and
suggestions is 5 or more characters.
- Extend dotless i and dotted I rules to Crimean Tatar language
Allow dotted I in dictionary, and disable bad capitalization of i.
- BREAK: extended recursive word breaking algorithm to handle words or
words with suffixes when they already contain word break characters,
for example, "e-mail" is a dictionary word with a word break character, and
it wasn't accepted before in compounds in some languages.
- FORBIDDENWORD precedes BREAK: Now it's possible to forbid compound
forms recognized by BREAK word breaking by adding the bad compounds to
the dictionary with FORBIDDENWORD flags.
- lower limit for "doubletwochars" suggestion algorithm:
one of the typical misspellings recognized by Hunspell suggestion
mechanism is the syllable duplication. Along the old pattern
ABABA -> ABA, for example nutrITITIon -> nutrITIon, now also the
simpler ABAB -> AB pattern is recognized in non-starting position,
for example, regretTETEd -> regretTEd.
- lower limit for longswapchar and movechar: recognized only max.
4-character distances to avoid slow and bad suggestions.
- fix compound handling for new Hungarian orthography reform
- Allow suggestion search for prefix + *two suffixes*:
Remove artificial performance limit to get correct
suggestions for relatively simple misspellings in
Hungarian, etc., when the word form contains prefix
and both derivative and inflectional suffixes, too:
lefikszálása -> lefixálása
Improvements for command-line Hunspell:
- Remove false alarms during checking OpenDocument (ODF)
documents by ignoring <text:span> elements. (LibreOffice
creates a lot of <text:span> elements also within words
during text reediting, resulted often huge amount of broken
words before this fix.)
- List filenames during filtering multiple files in command-line:
Examples:
$ hunspell -l *.odt
a.odt: mispelling
b.odt: egzample
$ hunspell -l -G *.odt
a.odt: good
b.odt: words
- Dictionary search by option -D doesn't wait for the standard input
(fixed by Siva Mahadevan)
Other improvements:
- makealias dictionary compression: add option --minimize-diff
to reuse free positions of alias lists to create minimal and
readable diffs for alias compressed dictionaries stored in
revision control systems, as dictionaries of LibreOffice.
- Brazilian-Portuguese translation by Rafael Fontenelle
- Catalan translation by robert dot buj at gmail
- Minor bug fixes by several contributors, see git log
2017-09-03: Hunspell 1.6.2 release:
- Library changes: no. Same as 1.6.1.
- Command line tool:
- Added German translation
- Fixed bug with wrong output encoding, not respecting system locale.
2017-03-25: Hunspell 1.6.1 release:
- Library changes:
- Performance improvements in suggest()
- Fixes regressions for Hungarian related to compounding.
- Fixes regressions for Korean related to ICONV.
- Command line tool:
- Added Tajik translation
- Fix regarding serching of OOo dicts installed in user folder
- Manpages:
- Fix microsoft-cp1251 to cp1251. Dicts should not use the first.
- Typos.
2016-12-22: Hunspell 1.6.0 release:
- Library changes:
- Performance improvement in ngsuggest(), suggestions should be faster.
- Revert MAXWORDLEN to 100 as in 1.3.3 for performance reasons.
- MAXWORDLEN can be set during build time with -D defines.
- Fix crash when word with 102 consecutive X is spelled.
- Command line tool:
- -D shows all loaded dictionares insted of only the first.
- -D properly lists all available dictionaries on Windows.
2016-11-30: Hunspell 1.5.4 release:
- Fixes the command COMPOUNDSYLLABLE used in Hungarian dictionary.
2016-11-28: Hunspell 1.5.3 release:
- Removed a #include from hunspell.hxx that was creating trouble
2016-11-27: Hunspell 1.5.2 release:
- Reverted full backward compatibility with 1.4 public API, again
2016-11-27: Hunspell 1.5.1 release:
- Reverted full backward compatibility with 1.4 public API
2016-11-18: Hunspell 1.5.0 release:
- Lot of stability fixes
- Fixed compilation errors on various systems (Windows, FreeBSD)
- Small performance improvement compared to 1.4.0
- The C++ API is updated to use modern C++ types (string, vector).
Backward compatibility is kept for most of the functions except for
the following:
- get_wordchars();
- get_version();
- input_conv(string, string);
- removed get_csconv();
2016-04-15: Hunspell 1.4.0 release:
- various abi changes due to moving away from char* to std::string
2014-06-02: Hunspell 1.3.3 release:
- OpenDocument (ODF and Flat ODF) support (ODF needs unzip program)
- various bug fixes
2011-02-02: Hunspell 1.3.2 release:
- fix library versioning
- improved manual
2011-02-02: Hunspell 1.3.1 release:
- bug fixes
2011-01-26: Hunspell 1.2.15/1.3 release:
- new features: MAXDIFF, ONLYMAXDIFF, MAXCPDSUGS, FORBIDWARN, see manual
- bug fixes
2011-01-21:
- new features: FORCEUCASE and WARN, see manual
- new options: -r to filter potential mistakes (rare words
signed by flag WARN in the dictionary)
- limited and optimized suggestions
2011-01-06: Hunspell 1.2.14 release:
- bug fix
2011-01-03: Hunspell 1.2.13 release:
- bug fixes
- improved compound handling and
other improvements supported by OpenTaal Foundation, Netherlands
2010-07-15: Hunspell 1.2.12 release
2010-05-06: Hunspell 1.2.11 release:
- Maintenance release bug fixes
2010-04-30: Hunspell 1.2.10 release:
- Maintenance release bug fixes
2010-03-03: Hunspell 1.2.9 release:
- Maintenance release bug fixes and warnings
- MAP support for composed characters or character sequences
2008-11-01: Hunspell 1.2.8 release:
- Default BREAK feature and better hyphenated word suggestion to accept
and fix (compound) words with hyphen characters by spell checker
instead of by work breaking code of OpenOffice.org. With this feature
it's possible to accept hyphenated compound words, such as "scot-free",
where "scot" is not a correct English word.
- ICONV & OCONV: input and output conversion tables for optional character
handling or using special inner format. Example:
# Accepting de facto replacements of the Romanian comma acuted letters
SET UTF-8
ICONV 4
ICONV ÅŸ È™
ICONV ţ ț
ICONV Ş Ș
ICONV Ţ Ț
Typical usage of ICONV/OCONV is to manage an inner format for a segmental
writing system, like the Ethiopic script of the Amharic language.
- Extended CHECKCOMPOUNDPATTERN to handle conpound word alternations, like
sandhi feature of Telugu and other writing systems.
- SIMPLIFIEDTRIPLE compound word feature: allow simplified Swedish and
Norwegian compound word forms, like tillåta (till|låta) and
bussjåfør (buss|sjåfør)
- wordforms: word generator script for dictionary developers (Hunspell
version of unmunch).
- bug fixes
2008-08-15: Hunspell 1.2.7 release:
- FULLSTRIP: new option for affix handling. With FULLSTRIP, affix rules can
strip full words, not only one less characters.
- COMPOUNDRULE works with all flag types. (COMPOUNDRULE is for pattern
matching. For example, en_US dictionary of OpenOffice.org uses COMPOUNDRULE
for ordinal number recognition: 1st, 2nd, 11th, 12th, 22nd, 112th, 1000122nd
etc.).
- optimized suggestions:
- modified 1-character distance suggestion algorithms: search a TRY character
in all position instead of all TRY characters in a character position
(it can give more readable suggestion order, also better suggestions
in the first positions, when TRY characters are sorted by frequency.)
For example, suggestions for "moze":
ooze, doze, Roze, maze, more etc. (Hunspell 1.2.6),
maze, more, mote, ooze, mole etc. (Hunspell 1.2.7).
- extended compound word checking for better COMPOUNDRULE related
suggestions, for example English ordinal numbers: 121323th -> 121323rd
(it needs also a th->rd REP definition).
- bug fixes
2008-07-15: Hunspell 1.2.6 release:
- bug fix release (fix affix rule condition checking of sk_SK dictionary,
iconv support in stemming and morphological analysis of the Hunspell
utility, see also Changelog)
2008-07-09: Hunspell 1.2.5 release:
- bug fix release (fix affix rule condition checking of en_GB dictionary,
also morphological analysis by dictionaries with two-level suffixes)
2008-06-18: Hunspell 1.2.4-2 release:
- fix GCC compiler warnings
2008-06-17: Hunspell 1.2.4 release:
- add free_list() for C, C++ interfaces to deallocate suggestion lists
- bug fixes
2008-06-17: Hunspell 1.2.3 release:
- extended XML interface to use morphological functions by standard
spell checking interface, spell() and suggest(). See hunspell.3 manual page.
- default dash suggestions for compound words: newword-> new word and new-word
- new manual pages: hunspell.3, hzip.1, hunzip.1.
- bug fixes
2008-04-12: Hunspell 1.2.2 release:
- extended dictionary (dic file) support to use multiple base and
special dictionaries.
- new and improved options of command line hunspell:
-m: morphological analysis or flag debug mode (without affix
rule data it signs the flag of the affix rules)
-s: stemming mode
-D: list available dictionaries and search path
-d: support extra dictionaries by comma separated list. Example:
hunspell -d en_US,en_med,de_DE,de_med,de_geo UNESCO.txt
- forbidding in personal dictionary (with asterisk, / signs affixation)
- optional compressed dictionary format "hzip" for aff and dic files
usage:
hzip example.aff example.dic
mv example.aff example.dic /tmp
hunspell -d example
hunzip example.aff.hz >example.aff
hunzip example.dic.hz >example.dic
- new affix compression tool "affixcompress": compression tool for
large (millions of words) dictionaries.
- support encrypted dictionaries for closed OpenOffice.org extensions or
other commercial programs
- improved manual
- bug fixes
2007-11-01: Hunspell 1.2.1 release:
- new memory efficient condition checking algorithm for affix rules
- new morphological functions:
- stem() for stemming
- analyze() for morphological analysis
- generate() for morphological generation
- new demos:
- analyze: stemming, morphological analysis and generation
- chmorph: morphological conversion of texts
2007-09-05: Hunspell 1.1.12 release:
- dictionary based phonetic suggestion for words with
special or foreign pronounciation or alternative (bad) transliteration
(see Changelog, tests/phone.* and manual).
- improved data structure and memory optimization for dictionaries
with variable count fields
- bug fixes for Unicode encoding dictionaries and ngram suggestions
- improved REP suggestions with space: it works without dictionary
modification
- updated and new project files for Windows API
2007-08-27: Hunspell 1.1.11 release:
- portability fixes
2007-08-23: Hunspell 1.1.10 release:
- pronounciation based suggestion using Björn Jacke's original Aspell
phonetic transcription algorithm (http://aspell.net), relicensed under
GPL/LGPL/MPL tri-license with the permission of the author
- keyboard base suggestion by KEY (see manual)
- better time limits for suggestion search
- test environment for suggestion based on Wikipedia data
- bug fixes for non standard Mozilla platforms etc.
2007-07-25: Hunspell 1.1.9 release:
- better tokenization:
- for URLs, mail addresses and directory paths (default: skip these tokens)
- for colons in words (for Finnish and Swedish)
- new examples:
- affixation of personal dictionary words
- digits in words
- bug fixes (see ChangeLog)
2007-07-16: Hunspell 1.1.8 release:
- better Mac OS X/Cygwin and Windows compatibility
- fix Hunspell's Valgrind environment and memory handling errors
detected by Valgrind
- other bug fixes (see ChangeLog)
2007-07-06: Hunspell 1.1.7 release:
- fix warning messages of OpenOffice.org build
2007-06-29: Hunspell 1.1.6 release:
- check capitalization of the following word forms
- words with mixed capitalisation: OpenOffice.org - OPENOFFICE.ORG
- allcap words and suffixes: UNICEF's - UNICEF'S
- prefixes with apostrophe and proper names: Sant'Elia - SANT'ELIA
- suggestion for missing sentence spacing: something.The -> something. The
- Hunspell executable: improved locale support
- -i option: custom input encoding
- use locale data for default dictionary names.
- tools/hunspell.cxx: fix 8-bit tokenization (letters without
casing, like ß or Hebrew characters now are handled well)
- dictionary search path (automatic detection of OpenOffice.org directories)
- DICPATH environmental variable
- -D option: show directory path of loaded dictionary
- patches and bug fixes for Mozilla, OpenOffice.org.
2007-03-19: Hunspell 1.1.5 release:
- optimizations: 10-100% speed up, smaller code size and memory footprint
(conditional experimental code and warning messages)
- extended Unicode support:
- non BMP Unicode characters in dictionary words and affixes (except
affix rules and conditions)
- support BOM sequence in aff and dic files
- IGNORE feature for Arabic diacritics and other optional characters
- New edit distance suggestion methods:
- capitalisation: nasa -> NASA
- long swap: permenant -> permanent
- long move: Ghandi -> Gandhi, greatful -> grateful
- double two characters: vacacation -> vacation
- spaces in REP sug.: REP alot a_lot (NOTE: "a lot" must be a dictionary word)
- patches and bug fixes for Mozilla, OpenOffice.org, Emacs, MinGW, Aqua,
German and Arabic language, etc.
2006-02-01: Hunspell 1.1.4 release:
- Improved suggestion for typical OCR bugs (missing spaces between
capitalized words). For example: "aNew" -> "a New".
http://qa.openoffice.org/issues/show_bug.cgi?id=58202
- tokenization fixes (fix incomplete tokenization of input texts on big-endian
platforms, and locale-dependent tokenization of dictionary entries)
2006-01-06: Hunspell 1.1.3.2 release:
- fix Visual C++ compiling errors
2006-01-05: Hunspell 1.1.3 release:
- GPL/LGPL/MPL tri-license for Mozilla integration
- Alias compression of flag sets and morphological descriptions.
(For example, 16 MB Arabic dic file can be compressed to 1 MB.)
- Improved suggestion.
- Improved, language independent German sharp s casing with CHECKSHARPS
declaration.
- Unicode tokenization in Hunspell program.
- Bug fixes (at new and old compound word handling methods), etc.
2005-11-11: Hunspell 1.1.2 release:
- Bug fixes (MAP Unicode, COMPOUND pattern matching, ONLYINCOMPOUND
suggestions)
- Checked with 51 regression tests in Valgrind debugging environment,
and tested with 52 OOo dictionaries on i686-pc-linux platform.
2005-11-09: Hunspell 1.1.1 release:
- Compound word patterns for complex compound word handling and
simple word-level lexical scanning. Ideal for checking
Arabic and Roman numbers, ordinal numbers in English, affixed
numbers in agglutinative languages, etc.
http://qa.openoffice.org/issues/show_bug.cgi?id=53643
- Support ISO-8859-15 encoding for French (French oe ligatures are
missing from the latin-1 encoding).
http://qa.openoffice.org/issues/show_bug.cgi?id=54980
- Implemented a flag to forbid obscene word suggestion:
http://qa.openoffice.org/issues/show_bug.cgi?id=55498
- Checked with 50 regression tests in Valgrind debugging environment,
and tested with 52 OOo dictionaries.
- other improvements and bug fixes (see ChangeLog)
2005-09-19: Hunspell 1.1.0 release
* complete comparison with MySpell 3.2 (from OpenOffice.org 2 beta)
* improved ngram suggestion with swap character detection and
case insensitivity
------ examples for ngram improvement (input word and suggestions) -----
1. pernament (instead of permanent)
MySpell 3.2: tournaments, tournament, ornaments, ornament's, ornamenting, ornamented,
ornament, ornamentals, ornamental, ornamentally
Hunspell 1.0.9: ornamental, ornament, tournament
Hunspell 1.1.0: permanent
Note: swap character detection
2. PERNAMENT (instead of PERMANENT)
MySpell 3.2: -
Hunspell 1.0.9: -
Hunspell 1.1.0: PERMANENT
3. Unesco (instead of UNESCO)
MySpell 3.2: Genesco, Ionesco, Genesco's, Ionesco's, Frescoing, Fresco's,
Frescoed, Fresco, Escorts, Escorting
Hunspell 1.0.9: Genesco, Ionesco, Fresco
Hunspell 1.1.0: UNESCO
4. siggraph's (instead of SIGGRAPH's)
MySpell 3.2: serigraph's, photograph's, serigraphs, physiography's,
physiography, digraphs, serigraph, stratigraphy's, stratigraphy
epigraphs
Hunspell 1.0.9: serigraph's, epigraph's, digraph's
Hunspell 1.1.0: SIGGRAPH's
--------------- end of examples --------------------
* improved testing environment with suggestion checking and memory debugging
memory debugging of all tests with a simple command:
VALGRIND=memcheck make check
* lots of other improvements and bug fixes (see ChangeLog)
2005-08-26: Hunspell 1.0.9 release
* improved related character map suggestion
* improved ngram suggestion
------ examples for ngram improvement (O=old, N = new ngram suggestions) --
1. Permenant (instead of Permanent)
O: Endangerment, Ferment, Fermented, Deferment's, Empowerment,
Ferment's, Ferments, Fermenting, Countermen, Weathermen
N: Permanent, Supermen, Preferment
Note: Ngram suggestions was case sensitive.
2. permenant (instead of permanent)
O: supermen, newspapermen, empowerment, endangerment, preferments,
preferment, permanent, preferment's, permanently, impermanent
N: permanent, supermen, preferment
Note: new suggestions are also weighted with longest common subsequence,
first letter and common character positions
3. pernemant (instead of permanent)
O: pimpernel's, pimpernel, pimpernels, permanently, permanents, permanent,
supernatant, impermanent, semipermanent, impermanently
N: permanent, supernatant, pimpernel
Note: new method also prefers root word instead of not
relevant affixes ('s, s and ly)
4. pernament (instead of permanent)
O: tournaments, tournament, ornaments, ornament's, ornamenting, ornamented,
ornament, ornamentals, ornamental, ornamentally
N: ornamental, ornament, tournament
Note: Both ngram methods misses here.
5. obvus (instad of obvious):
O: obvious, Corvus, obverse, obviously, Jacobus, obtuser, obtuse,
obviates, obviate, Travus
N: obvious, obtuse, obverse
Note: new method also prefers common first letters.
6. unambigus (instead of unambiguous)
O: unambiguous, unambiguity, unambiguously, ambiguously, ambiguous,
unambitious, ambiguities, ambiguousness
N: unambiguous, unambiguity, unambitious
7. consecvence (instead of consequence)
O: consecutive, consecutively, consecutiveness, nonconsecutive, consequence,
consecutiveness's, convenience's, consistences, consistence
N: consequence, consecutive, consecrates
An example in a language with rich morphology:
8. Misisipiben (instead of Mississippiben [`in Mississippi' in Hungarian]):
O: Misikédéiben, Pisisedéiben, Misikéiéiben, Pisisekéiben, Misikéiben,
Misikéidéiben, Misikékéiben, Misikéikéiben, Misikéiméiben, Mississippiiben
N: Mississippiben, Mississippiiben, Misiiben
Note: Suggesting not relevant affixes was the biggest fault in ngram
suggestion for languages with a lot of affixes.
--------------- end of examples --------------------
* support twofold prefix cutting
* lots of other improvements and bug fixes (see ChangeLog)
* test Hunspell with 54 OpenOffice.org dictionaries:
source: ftp://ftp.services.openoffice.org/pub/OpenOffice.org/contrib/dictionaries
testing shell script:
-------------------------------------------------------
for i in `ls *zip | grep '^[a-z]*_[A-Z]*[.]'`
do
dic=`basename $i .zip`
mkdir $dic
echo unzip $dic
unzip -d $dic $i 2>/dev/null
cd $dic
echo unmunch and test $dic
unmunch $dic.dic $dic.aff 2>/dev/null | awk '{print$0"\t"}' |
hunspell -d $dic -l -1 >$dic.result 2>$dic.err || rm -f $dic.result
cd ..
done
--------------------------------------------------------
test result (0 size is o.k.):
$ for i in *_*/*.result; do wc -c $i; done
0 af_ZA/af_ZA.result
0 bg_BG/bg_BG.result
0 ca_ES/ca_ES.result
0 cy_GB/cy_GB.result
0 cs_CZ/cs_CZ.result
0 da_DK/da_DK.result
0 de_AT/de_AT.result
0 de_CH/de_CH.result
0 de_DE/de_DE.result
0 el_GR/el_GR.result
6 en_AU/en_AU.result
0 en_CA/en_CA.result
0 en_GB/en_GB.result
0 en_NZ/en_NZ.result
0 en_US/en_US.result
0 eo_EO/eo_EO.result
0 es_ES/es_ES.result
0 es_MX/es_MX.result
0 es_NEW/es_NEW.result
0 fo_FO/fo_FO.result
0 fr_FR/fr_FR.result
0 ga_IE/ga_IE.result
0 gd_GB/gd_GB.result
0 gl_ES/gl_ES.result
0 he_IL/he_IL.result
0 hr_HR/hr_HR.result
200694989 hu_HU/hu_HU.result
0 id_ID/id_ID.result
0 it_IT/it_IT.result
0 ku_TR/ku_TR.result
0 lt_LT/lt_LT.result
0 lv_LV/lv_LV.result
0 mg_MG/mg_MG.result
0 mi_NZ/mi_NZ.result
0 ms_MY/ms_MY.result
0 nb_NO/nb_NO.result
0 nl_NL/nl_NL.result
0 nn_NO/nn_NO.result
0 ny_MW/ny_MW.result
0 pl_PL/pl_PL.result
0 pt_BR/pt_BR.result
0 pt_PT/pt_PT.result
0 ro_RO/ro_RO.result
0 ru_RU/ru_RU.result
0 rw_RW/rw_RW.result
0 sk_SK/sk_SK.result
0 sl_SI/sl_SI.result
0 sv_SE/sv_SE.result
0 sw_KE/sw_KE.result
0 tet_ID/tet_ID.result
0 tl_PH/tl_PH.result
0 tn_ZA/tn_ZA.result
0 uk_UA/uk_UA.result
0 zu_ZA/zu_ZA.result
In en_AU dictionary, there is an abbrevation with two dots (`eqn..'), but
`eqn.' is missing. Presumably it is a dictionary bug. Myspell also
haven't accepted it.
Hungarian dictionary contains pseudoroots and forbidden words.
Unmunch haven't supported these features yet, and generates bad words, too.
* check affix rules and OOo dictionaries. Detected bugs in cs_CZ,
es_ES, es_NEW, es_MX, lt_LT, nn_NO, pt_PT, ro_RO, sk_SK and sv_SE dictionaries).
Details:
--------------------------------------------------------
cs_CZ
warning - incompatible stripping characters and condition:
SFX D us ech [^ighk]os
SFX D us y [^i]os
SFX Q os ech [^ghk]es
SFX M o ech [^ghkei]a
SFX J ém ej ám
SFX J ém ejme ám
SFX J ém ejte ám
SFX A ou¾it up oupit
SFX A ou¾it upme oupit
SFX A ou¾it upte oupit
SFX A nout l [aeiouyáéíóúýùìr][^aeiouyáéíóúýùìrl][^aeiouy
SFX A nout l [aeiouyáéíóúýùìr][^aeiouyáéíóúýùìrl][^aeiouy
es_ES
warning - incompatible stripping characters and condition:
SFX W umar úse [ae]husar
SFX W emir iñáis eñir
es_NEW
warning - incompatible stripping characters and condition:
SFX I unan únen unar
es_MX
warning - incompatible stripping characters and condition:
SFX A a ote e
SFX W umar úse [ae]husar
SFX W emir iñáis eñir
lt_LT
warning - incompatible stripping characters and condition:
SFX U ti siuosi tis
SFX U ti siuosi tis
SFX U ti siesi tis
SFX U ti siesi tis
SFX U ti sis tis
SFX U ti sis tis
SFX U ti simës tis
SFX U ti simës tis
SFX U ti sitës tis
SFX U ti sitës tis
nn_NO
warning - incompatible stripping characters and condition:
SFX D ar rar [^fmk]er
SFX U Øre orde ere
SFX U Øre ort ere
pt_PT
warning - incompatible stripping characters and condition:
SFX g ãos oas ão
SFX g ãos oas ão
ro_RO
warning - bad field number:
SFX L 0 le [^cg] i
SFX L 0 i [cg] i
SFX U 0 i [^i] ii
warning - incompatible stripping characters and condition:
SFX P l i l [<- there is an unnecessary tabulator here)
SFX I a ii [gc] a
warning - bad field number:
SFX I a ii [gc] a
SFX I a ei [^cg] a
sk_SK
warning - incompatible stripping characters and condition:
SFX T µa» olú kla»
SFX T µa» olúc kla»
SFX T sµa» ¹lú sla»
SFX T sµa» ¹lúc sla»
SFX R µc» lèiem åc»
SFX R iás» ätie mias»
SFX R iez» iem [^i]ez»
SFX R iez» ie¹ [^i]ez»
SFX R iez» ie [^i]ez»
SFX R iez» eme [^i]ez»
SFX R iez» ete [^i]ez»
SFX R iez» ú [^i]ez»
SFX R iez» úc [^i]ez»
SFX R iez» z [^i]ez»
SFX R iez» me [^i]ez»
SFX R iez» te [^i]ez»
sv_SE
warning - bad field number:
SFX C 0 net nets [^e]n
--------------------------------------------------------
2005-08-01: Hunspell 1.0.8 release
- improved compound word support
- fix German S handling
- port MySpell files and MAP feature
2005-07-22: Hunspell 1.0.7 release
2005-07-21: new home page: http://hunspell.sourceforge.net

315
3rdparty/hunspell/1.7.0/README vendored Normal file
View File

@ -0,0 +1,315 @@
# About Hunspell
Hunspell is a free spell checker and morphological analyzer library
and command-line tool, licensed under LGPL/GPL/MPL tri-license.
Hunspell is used by LibreOffice office suite, free browsers, like
Mozilla Firefox and Google Chrome, and other tools and OSes, like
Linux distributions and macOS. It is also a command-line tool for
Linux, Unix-like and other OSes.
It is designed for quick and high quality spell checking and
correcting for languages with word-level writing system,
including languages with rich morphology, complex word compounding
and character encoding.
Hunspell interfaces: Ispell-like terminal interface using Curses
library, Ispell pipe interface, C++/C APIs and shared library, also
with existing language bindings for other programming languages.
Hunspell's code base comes from OpenOffice.org's MySpell library,
developed by Kevin Hendricks (originally a C++ reimplementation of
spell checking and affixation of Geoff Kuenning's International
Ispell from scratch, later extended with eg. n-gram suggestions),
see http://lingucomponent.openoffice.org/MySpell-3.zip, and
its README, CONTRIBUTORS and license.readme (here: license.myspell) files.
Main features of Hunspell library, developed by László Németh:
- Unicode support
- Highly customizable suggestions: word-part replacement tables and
stem-level phonetic and other alternative transcriptions to recognize
and fix all typical misspellings, don't suggest offensive words etc.
- Complex morphology: dictionary and affix homonyms; twofold affix
stripping to handle inflectional and derivational morpheme groups for
agglutinative languages, like Azeri, Basque, Estonian, Finnish, Hungarian,
Turkish; 64 thousand affix classes with arbitrary number of affixes;
conditional affixes, circumfixes, fogemorphemes, zero morphemes,
virtual dictionary stems, forbidden words to avoid overgeneration etc.
- Handling complex compounds (for example, for Finno-Ugric, German and
Indo-Aryan languages): recognizing compounds made of arbitrary
number of words, handle affixation within compounds etc.
- Custom dictionaries with affixation
- Stemming
- Morphological analysis (in custom item and arrangement style)
- Morphological generation
- SPELLML XML API over plain spell() API function for easier integration
of stemming, morpological generation and custom dictionaries with affixation
- Language specific algorithms, like special casing of Azeri or Turkish
dotted i and German sharp s, and special compound rules of Hungarian.
Main features of Hunspell command line tool, developed by László Németh:
- Reimplementation of quick interactive interface of Geoff Kuenning's Ispell
- Parsing formats: text, OpenDocument, TeX/LaTeX, HTML/SGML/XML, nroff/troff
- Custom dictionaries with optional affixation, specified by a model word
- Multiple dictionary usage (for example hunspell -d en_US,de_DE,de_medical)
- Various filtering options (bad or good words/lines)
- Morphological analysis (option -m)
- Stemming (option -s)
See man hunspell, man 3 hunspell, man 5 hunspell for complete manual.
# Dependencies
Build only dependencies:
g++ make autoconf automake autopoint libtool
Runtime dependencies:
| | Mandatory | Optional |
|---------------|------------------|------------------|
|libhunspell | | |
|hunspell tool | libiconv gettext | ncurses readline |
# Compiling on GNU/Linux and Unixes
We first need to download the dependencies. On Linux, `gettext` and
`libiconv` are part of the standard library. On other Unixes we
need to manually install them.
For Ubuntu:
sudo apt install autoconf automake autopoint libtool
Then run the following commands:
autoreconf -vfi
./configure
make
sudo make install
sudo ldconfig
For dictionary development, use the `--with-warnings` option of
configure.
For interactive user interface of Hunspell executable, use the
`--with-ui option`.
Optional developer packages:
- ncurses (need for --with-ui), eg. libncursesw5 for UTF-8
- readline (for fancy input line editing, configure parameter:
--with-readline)
In Ubuntu, the packages are:
libncurses5-dev libreadline-dev
# Compiling on OSX and macOS
On macOS for compiler always use `clang` and not `g++` because Homebrew
dependencies are build with that.
brew install autoconf automake libtool gettext
brew link gettext --force
Then run autoreconf, configure, make. See above.
# Compiling on Windows
## Compiling with Mingw64 and MSYS2
Download Msys2, update everything and install the following
packages:
pacman -S base-devel mingw-w64-x86_64-toolchain mingw-w64-x86_64-libtool
Open Mingw-w64 Win64 prompt and compile the same way as on Linux, see
above.
## Compiling in Cygwin environment
Download and install Cygwin environment for Windows with the following
extra packages:
- make
- automake
- autoconf
- libtool
- gcc-g++ development package
- ncurses, readline (for user interface)
- iconv (character conversion)
Then compile the same way as on Linux. Cygwin builds depend on
Cygwin1.dll.
# Debugging
It is recommended to install a debug build of the standard library:
libstdc++6-6-dbg
For debugging we need to create a debug build and then we need to start
`gdb`.
./configure CXXFLAGS='-g -O0 -Wall -Wextra'
make
./libtool --mode=execute gdb src/tools/hunspell
You can also pass the `CXXFLAGS` directly to `make` without calling
`./configure`, but we don't recommend this way during long development
sessions.
If you like to develop and debug with an IDE, see documentation at
https://github.com/hunspell/hunspell/wiki/IDE-Setup
# Testing
Testing Hunspell (see tests in tests/ subdirectory):
make check
or with Valgrind debugger:
make check
VALGRIND=[Valgrind_tool] make check
For example:
make check
VALGRIND=memcheck make check
# Documentation
features and dictionary format:
man 5 hunspell
man hunspell
hunspell -h
http://hunspell.github.io/
# Usage
After compiling and installing (see INSTALL) you can run the Hunspell
spell checker (compiled with user interface) with a Hunspell or Myspell
dictionary:
hunspell -d en_US text.txt
or without interface:
hunspell
hunspell -d en_GB -l <text.txt
Dictionaries consist of an affix (.aff) and dictionary (.dic) file, for
example, download American English dictionary files of LibreOffice
(older version, but with stemming and morphological generation) with
wget -O en_US.aff https://cgit.freedesktop.org/libreoffice/dictionaries/plain/en/en_US.aff?id=a4473e06b56bfe35187e302754f6baaa8d75e54f
wget -O en_US.dic https://cgit.freedesktop.org/libreoffice/dictionaries/plain/en/en_US.dic?id=a4473e06b56bfe35187e302754f6baaa8d75e54f
and with command line input and output, it's possible to check its work quickly,
for example with the input words "example", "examples", "teached" and
"verybaaaaaaaaaaaaaaaaaaaaaad":
$ hunspell -d en_US
Hunspell 1.7.0
example
*
examples
+ example
teached
& teached 9 0: taught, teased, reached, teaches, teacher, leached, beached
verybaaaaaaaaaaaaaaaaaaaaaad
# verybaaaaaaaaaaaaaaaaaaaaaad 0
Where in the output, `*` and `+` mean correct (accepted) words (`*` = dictionary stem,
`+` = affixed forms of the following dictionary stem), and
`&` and `#` mean bad (rejected) words (`&` = with suggestions, `#` = without suggestions)
(see man hunspell).
Example for stemming:
$ hunspell -d en_US -s
mice
mice mouse
Example for morphological analysis (very limited with this English dictionary):
$ hunspell -d en_US -m
mice
mice st:mouse ts:Ns
cats
cats st:cat ts:0 is:Ns
cats st:cat ts:0 is:Vs
# Other executables
The src/tools directory contains the following executables after compiling.
- The main executable:
- hunspell: main program for spell checking and others (see
manual)
- Example tools:
- analyze: example of spell checking, stemming and morphological
analysis
- chmorph: example of automatic morphological generation and
conversion
- example: example of spell checking and suggestion
- Tools for dictionary development:
- affixcompress: dictionary generation from large (millions of
words) vocabularies
- makealias: alias compression (Hunspell only, not back compatible
with MySpell)
- wordforms: word generation (Hunspell version of unmunch)
- hunzip: decompressor of hzip format
- hzip: compressor of hzip format
- munch (DEPRECATED, use affixcompress): dictionary generation
from vocabularies (it needs an affix file, too).
- unmunch (DEPRECATED, use wordforms): list all recognized words
of a MySpell dictionary
Example for morphological generation:
$ ~/hunspell/src/tools/analyze en_US.aff en_US.dic /dev/stdin
cat mice
generate(cat, mice) = cats
mouse cats
generate(mouse, cats) = mice
generate(mouse, cats) = mouses
# Using Hunspell library with GCC
Including in your program:
#include <hunspell.hxx>
Linking with Hunspell static library:
g++ -lhunspell-1.7 example.cxx
# or better, use pkg-config
g++ $(pkg-config --cflags --libs hunspell) example.cxx
## Dictionaries
Hunspell (MySpell) dictionaries:
- https://wiki.documentfoundation.org/Language_support_of_LibreOffice
- http://cgit.freedesktop.org/libreoffice/dictionaries
- http://extensions.libreoffice.org
- http://extensions.openoffice.org
- http://wiki.services.openoffice.org/wiki/Dictionaries
Aspell dictionaries (conversion: man 5 hunspell):
- ftp://ftp.gnu.org/gnu/aspell/dict
László Németh, nemeth at numbertext org

206
3rdparty/hunspell/1.7.0/THANKS vendored Normal file
View File

@ -0,0 +1,206 @@
Many thanks to the following contributors and supporters:
Mehmet Akin
Göran Andersson
Lars Aronsson
Ruud Baars
Bartkó Zoltán
Mathias Bauer
Bencsáth Boldizsár
Bíró Árpád
Ingo H. de Boer
Simon Brouwer
Jeppe Bundsgaard
Ginn Chen
Tomáš Chvátal
Aaron Digulla
Dmitri Gabinski
Dvornik László
David Einstein
Rene Engelhard
Frederik Fouvry
Flemming Frandsen
Serge Gautherie
Marek Gleń
Gavins at OOo
Gefferth András
Godó Ferenc
Goldman Eleonóra
Steinar H. Gunderson
Halácsy Péter
Chris Halls
Khaled Hosny
Izsók András
Björn Jacke
Mike Tian-Jian Jiang
Dafydd Jones
Ryan Jones
Jean-Christophe Helary
Kevin Hendricks
Martin Hollmichel
Pavel Janík
John Winters
Mohamed Kebdani
Kelemen Gábor
Shewangizaw Gulilat
Kéménczy Kálmán
Dan Kenigsberg
Pham Ngoc Khanh
Khiraly László
Koblinger Egmont
Kornai András
Tor Lillqvist
Christian Lohmaier
Robert Longson
Marot at SF dot net
Mark McClain
Caolan McNamara
Michael Meeks
Moheb Mekhaiel
Laurie Mercer
Ladislav Michnovič
Ellis Miller
Giuseppe Modugno
János Mohácsi
Bram Moolenaar
Daniel Naber
Nagy Viktor
John Nisly
Noll János
S Page
Christophe Paris
Malcolm Parsons
Sylvain Paschein
Volkov Peter
Bryan Petty
Harri Pitkänen
Davide Prina
Kevin F. Quinn
Erdal Ronahi
Olivier Ronez
Bernhard Rosenkraenzer
Sarlós Tamás
Thobias Schlemmer
Jan Seeger
Jose da Silva
Paulo Ney de Souza
Roland Smith
Munzir Taha
Timeless at bemail dot org
Tímár András
Tonal at OOo
Török László
Trón Viktor
Gianluca Turconi
Ryan VanderMeulen
Varga Dániel
Elio Voci
Miha Vrhovnik
Martijn Wargers
Michel Weimerskirch
Brett Wilson
Friedel Wolff
Daniel Yacob
Gábor Zahemszky
Taha Zerrouki
and others (see also MySpell authors bellow)
FSF.hu Foundation
http://www.fsf.hu
LibreOffice community
http://www.libreoffice.org
MOKK Research Centre
Budapest University of Technology and Economics
Sociology and Communications Department
http://www.mokk.bme.hu
Hungarian Ministry of Informatics and Telecommunications
IMEDIA Kft.
http://www.imedia.hu
OpenOffice.org community
http://www.openoffice.org
OpenTaal Foundation, Netherlands and
Dutch Language Union (Nederlandse Taalunie)
http://opentaal.org
UHU-Linux Kft.
Thanks,
Németh László
nemeth at numbertext org
--------------------------
MySpell Developer Credits:
Special credit and thanks go to ispell's creator Geoff Kuenning.
Ispell affix compression code was used as the basis for the
affix code used in MySpell. Specifically Geoff's use of a
conds[] array that makes it easy to check if the conditions
required for a particular affix are present was very
ingenious! Kudos to Geoff. Very nicely done.
BTW: ispell is available under a BSD style license
from Geoff Kuennings ispell website:
http://www.cs.ucla.edu/ficus-members/geoff/ispell.html
Kevin Hendricks <kevin.hendricks@sympatico.ca> is the original
author and now maintainer of the MySpell codebase. Recent
additions include ngram support, and related character maps
to help improve and create suggestions for very poorly
spelled words.
Please send any and all contributions or improvements
to him or to dev@lingucomponent.openoffice.org.
David Einstein (Deinst@world.std.com) developed an almost
complete rewrite of MySpell for use by the Mozilla project.
David and I are now working on parallel development tracks
to help our respective projects (Mozilla and OpenOffice.org)
and we will maintain full affix file and dictionary file
compatibility and work on merging our versions of MySpell
back into a single tree. David has been a significant help
in improving MySpell.
Németh László <nemethl@gyorsposta.hu> is the author of
the Hungarian dictionary and he developed and contributed
extensive changes to MySpell including ...
* code to support compound words in MySpell
* fixed numerous problems with encoding case conversion tables.
* designed/developed replacement tables to improve suggestions
* changed affix file parsing to trees to greatly speed loading
* removed the need for malloc/free pairs in suffix_check which
speeds up spell checking in suffix rich languages by 20%
Davide Prina <davideprina@uahoo.com>, Giuseppe Modugno
<gppe.modugno@libero.it>, Gianluca Turconi <luctur@comeg.it>
all from the it_IT OpenOffice.org team performed an
extremely detailed code review of MySpell and generated
fixes for bugs, leaks, and speedup improvements.
Simon Brouwer <simon.oo.o@xs4all.nl> for fixes and enhancements
that have greatly improved MySpell auggestions
* n-gram suggestions for an initcap word have an init. cap.
* fix for too many n-gram suggestions from specialized dictionary,
* fix for long suggestions rather than close ones in case of
dictionaries with many compound words (kompuuter)
* optionally disabling split-word suggestions (controlled
by NOSPLITSUGS line in affix file)
Special Thanks to all others who have either contributed ideas or
testing for MySpell
Thanks,
Kevin Hendricks
kevin.hendricks@sympatico.ca

View File

@ -399,28 +399,28 @@ std::string PfxEntry::check_morph(const char* word,
((!needflag) || TESTAFF(he->astr, needflag, he->alen) ||
(contclass && TESTAFF(contclass, needflag, contclasslen)))) {
if (morphcode) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(morphcode);
} else
result.append(getKey());
if (!HENTRY_FIND(he, MORPH_STEM)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(MORPH_STEM);
result.append(HENTRY_WORD(he));
}
// store the pointer of the hash entry
if (HENTRY_DATA(he)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(HENTRY_DATA2(he));
} else {
// return with debug information
char* flag = pmyMgr->encode_flag(getFlag());
result.append(" ");
result.push_back(MSEP_FLD);
result.append(MORPH_FLAG);
result.append(flag);
free(flag);
}
result.append("\n");
result.push_back(MSEP_REC);
}
he = he->next_homonym;
} while (he);
@ -804,7 +804,7 @@ std::string SfxEntry::check_twosfx_morph(const char* word,
if (!st.empty()) {
if (ppfx->getMorph()) {
result.append(ppfx->getMorph());
result.append(" ");
result.push_back(MSEP_FLD);
}
result.append(st);
mychomp(result);

View File

@ -72,6 +72,7 @@
#include <string.h>
#include <stdio.h>
#include <ctype.h>
#include <time.h>
#include <algorithm>
#include <limits>
@ -96,7 +97,6 @@ AffixMgr::AffixMgr(const char* affpath,
complexprefixes = 0;
parsedmaptable = false;
parsedbreaktable = false;
parsedrep = false;
iconvtable = NULL;
oconvtable = NULL;
// allow simplified compound forms (see 3rd field of CHECKCOMPOUNDPATTERN)
@ -113,7 +113,7 @@ AffixMgr::AffixMgr(const char* affpath,
compoundforbidflag = FLAG_NULL; // compound fordidden flag for suffixed word
compoundmoresuffixes = 0; // allow more suffixes within compound words
checkcompounddup = 0; // forbid double words in compounds
checkcompoundrep = 0; // forbid bad compounds (may be non compound word with
checkcompoundrep = 0; // forbid bad compounds (may be non-compound word with
// a REP substitution)
checkcompoundcase =
0; // forbid upper and lowercase combinations at word bounds
@ -439,7 +439,7 @@ int AffixMgr::parse_file(const char* affpath, const char* key) {
}
}
/* parse in the flag used by forbidden words */
/* parse in the flag used by forbidden words (is deprecated) */
if (line.compare(0, 13, "LEMMA_PRESENT", 13) == 0) {
if (!parse_flag(line, &lemma_present, afflst)) {
finishFileMgr(afflst);
@ -463,7 +463,7 @@ int AffixMgr::parse_file(const char* affpath, const char* key) {
}
}
/* parse in the flag used by `needaffixs' */
/* parse in the flag used by `needaffixs' (is deprecated) */
if (line.compare(0, 10, "PSEUDOROOT", 10) == 0) {
if (!parse_flag(line, &needaffix, afflst)) {
finishFileMgr(afflst);
@ -529,14 +529,6 @@ int AffixMgr::parse_file(const char* affpath, const char* key) {
}
}
/* parse in the typical fault correcting table */
if (line.compare(0, 3, "REP", 3) == 0) {
if (!parse_reptable(line, afflst)) {
finishFileMgr(afflst);
return 1;
}
}
/* parse in the input conversion table */
if (line.compare(0, 5, "ICONV", 5) == 0) {
if (!parse_convtable(line, afflst, &iconvtable, "ICONV")) {
@ -545,7 +537,7 @@ int AffixMgr::parse_file(const char* affpath, const char* key) {
}
}
/* parse in the input conversion table */
/* parse in the output conversion table */
if (line.compare(0, 5, "OCONV", 5) == 0) {
if (!parse_convtable(line, afflst, &oconvtable, "OCONV")) {
finishFileMgr(afflst);
@ -1023,7 +1015,7 @@ int AffixMgr::process_sfx_order() {
// add flags to the result for dictionary debugging
std::string& AffixMgr::debugflag(std::string& result, unsigned short flag) {
char* st = encode_flag(flag);
result.append(" ");
result.push_back(MSEP_FLD);
result.append(MORPH_FLAG);
if (st) {
result.append(st);
@ -1146,7 +1138,7 @@ struct hentry* AffixMgr::prefix_check(const char* word,
return NULL;
}
// check word for prefixes
// check word for prefixes and two-level suffixes
struct hentry* AffixMgr::prefix_check_twosfx(const char* word,
int len,
char in_compound,
@ -1187,7 +1179,7 @@ struct hentry* AffixMgr::prefix_check_twosfx(const char* word,
return NULL;
}
// check word for prefixes
// check word for prefixes and morph
std::string AffixMgr::prefix_check_morph(const char* word,
int len,
char in_compound,
@ -1234,7 +1226,7 @@ std::string AffixMgr::prefix_check_morph(const char* word,
return result;
}
// check word for prefixes
// check word for prefixes and morph and two-level suffixes
std::string AffixMgr::prefix_check_twosfx_morph(const char* word,
int len,
char in_compound,
@ -1275,25 +1267,44 @@ std::string AffixMgr::prefix_check_twosfx_morph(const char* word,
return result;
}
// Is word a non compound with a REP substitution (see checkcompoundrep)?
// Is word a non-compound with a REP substitution (see checkcompoundrep)?
int AffixMgr::cpdrep_check(const char* word, int wl) {
if ((wl < 2) || reptable.empty())
if ((wl < 2) || get_reptable().empty())
return 0;
for (size_t i = 0; i < reptable.size(); ++i) {
const char* r = word;
const size_t lenp = reptable[i].pattern.size();
// search every occurence of the pattern in the word
while ((r = strstr(r, reptable[i].pattern.c_str())) != NULL) {
std::string candidate(word);
size_t type = r == word && langnum != LANG_hu ? 1 : 0;
if (r - word + reptable[i].pattern.size() == lenp && langnum != LANG_hu)
type += 2;
candidate.replace(r - word, lenp, reptable[i].outstrings[type]);
for (size_t i = 0; i < get_reptable().size(); ++i) {
// use only available mid patterns
if (!get_reptable()[i].outstrings[0].empty()) {
const char* r = word;
const size_t lenp = get_reptable()[i].pattern.size();
// search every occurence of the pattern in the word
while ((r = strstr(r, get_reptable()[i].pattern.c_str())) != NULL) {
std::string candidate(word);
candidate.replace(r - word, lenp, get_reptable()[i].outstrings[0]);
if (candidate_check(candidate.c_str(), candidate.size()))
return 1;
++r; // search for the next letter
}
}
}
return 0;
}
// forbid compound words, if they are in the dictionary as a
// word pair separated by space
int AffixMgr::cpdwordpair_check(const char * word, int wl) {
if (wl > 2) {
std::string candidate(word);
for (size_t i = 1; i < candidate.size(); i++) {
// go to end of the UTF-8 character
if (utf8 && ((word[i] & 0xc0) == 0x80))
continue;
candidate.insert(i, 1, ' ');
if (candidate_check(candidate.c_str(), candidate.size()))
return 1;
++r; // search for the next letter
candidate.erase(i, 1);
}
}
@ -1584,6 +1595,17 @@ struct hentry* AffixMgr::compound_check(const std::string& word,
int checked_prefix;
// add a time limit to handle possible
// combinatorical explosion of the overlapping words
HUNSPELL_THREAD_LOCAL clock_t timelimit;
if (wordnum == 0)
timelimit = clock();
else if (timelimit != 0 && (clock() > timelimit + TIMELIMIT)) {
timelimit = 0;
}
setcminmax(&cmin, &cmax, word.c_str(), len);
st.assign(word);
@ -1608,6 +1630,9 @@ struct hentry* AffixMgr::compound_check(const std::string& word,
do { // simplified checkcompoundpattern loop
if (timelimit == 0)
return 0;
if (scpd > 0) {
for (; scpd <= checkcpdtable.size() &&
(checkcpdtable[scpd - 1].pattern3.empty() ||
@ -1647,6 +1672,12 @@ struct hentry* AffixMgr::compound_check(const std::string& word,
affixed = 1;
rv = lookup(st.c_str()); // perhaps without prefix
// forbid dictionary stems with COMPOUNDFORBIDFLAG in
// compound words, overriding the effect of COMPOUNDPERMITFLAG
if ((rv) && compoundforbidflag &&
TESTAFF(rv->astr, compoundforbidflag, rv->alen) && !hu_mov_rule)
continue;
// search homonym with compound flag
while ((rv) && !hu_mov_rule &&
((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) ||
@ -1909,9 +1940,10 @@ struct hentry* AffixMgr::compound_check(const std::string& word,
&&
(scpd == 0 || checkcpdtable[scpd - 1].cond2 == FLAG_NULL ||
TESTAFF(rv->astr, checkcpdtable[scpd - 1].cond2, rv->alen))) {
// forbid compound word, if it is a non compound word with typical
// forbid compound word, if it is a non-compound word with typical
// fault
if (checkcompoundrep && cpdrep_check(word.c_str(), len))
if ((checkcompoundrep && cpdrep_check(word.c_str(), len)) ||
cpdwordpair_check(word.c_str(), len))
return NULL;
return rv_first;
}
@ -1989,7 +2021,9 @@ struct hentry* AffixMgr::compound_check(const std::string& word,
if (sfxappnd) {
std::string tmp(sfxappnd);
reverseword(tmp);
numsyllable -= get_syllable(tmp) + sfxextra;
numsyllable -= short(get_syllable(tmp) + sfxextra);
} else {
numsyllable -= short(sfxextra);
}
// + 1 word, if syllable number of the prefix > 1 (hungarian
@ -2024,7 +2058,6 @@ struct hentry* AffixMgr::compound_check(const std::string& word,
(TESTAFF(rv->astr, compoundroot, rv->alen))) {
wordnum++;
}
// second word is acceptable, as a word with prefix or/and suffix?
// hungarian conventions: compounding is acceptable,
// when compound forms consist 2 word, otherwise
@ -2033,9 +2066,10 @@ struct hentry* AffixMgr::compound_check(const std::string& word,
(((cpdwordmax == -1) || (wordnum + 1 < cpdwordmax)) ||
((cpdmaxsyllable != 0) && (numsyllable <= cpdmaxsyllable))) &&
((!checkcompounddup || (rv != rv_first)))) {
// forbid compound word, if it is a non compound word with typical
// forbid compound word, if it is a non-compound word with typical
// fault
if (checkcompoundrep && cpdrep_check(word.c_str(), len))
if ((checkcompoundrep && cpdrep_check(word.c_str(), len)) ||
cpdwordpair_check(word.c_str(), len))
return NULL;
return rv_first;
}
@ -2059,8 +2093,12 @@ struct hentry* AffixMgr::compound_check(const std::string& word,
rv = NULL;
}
if (rv) {
// forbid compound word, if it is a non compound word with typical
// fault
// forbid compound word, if it is a non-compound word with typical
// fault, or a dictionary word pair
if (cpdwordpair_check(word.c_str(), len))
return NULL;
if (checkcompoundrep || forbiddenword) {
if (checkcompoundrep && cpdrep_check(word.c_str(), len))
@ -2071,7 +2109,8 @@ struct hentry* AffixMgr::compound_check(const std::string& word,
char r = st[i + rv->blen];
st[i + rv->blen] = '\0';
if (checkcompoundrep && cpdrep_check(st.c_str(), i + rv->blen)) {
if ((checkcompoundrep && cpdrep_check(st.c_str(), i + rv->blen)) ||
cpdwordpair_check(st.c_str(), i + rv->blen)) {
st[ + i + rv->blen] = r;
continue;
}
@ -2162,6 +2201,17 @@ int AffixMgr::compound_check_morph(const char* word,
char affixed = 0;
hentry** oldwords = words;
// add a time limit to handle possible
// combinatorical explosion of the overlapping words
HUNSPELL_THREAD_LOCAL clock_t timelimit;
if (wordnum == 0)
timelimit = clock();
else if (timelimit != 0 && (clock() > timelimit + TIMELIMIT)) {
timelimit = 0;
}
setcminmax(&cmin, &cmax, word, len);
st.assign(word);
@ -2180,6 +2230,9 @@ int AffixMgr::compound_check_morph(const char* word,
do { // onlycpdrule loop
if (timelimit == 0)
return 0;
oldnumsyllable = numsyllable;
oldwordnum = wordnum;
checked_prefix = 0;
@ -2198,6 +2251,12 @@ int AffixMgr::compound_check_morph(const char* word,
rv = lookup(st.c_str()); // perhaps without prefix
// forbid dictionary stems with COMPOUNDFORBIDFLAG in
// compound words, overriding the effect of COMPOUNDPERMITFLAG
if ((rv) && compoundforbidflag &&
TESTAFF(rv->astr, compoundforbidflag, rv->alen) && !hu_mov_rule)
continue;
// search homonym with compound flag
while ((rv) && !hu_mov_rule &&
((needaffix && TESTAFF(rv->astr, needaffix, rv->alen)) ||
@ -2215,6 +2274,9 @@ int AffixMgr::compound_check_morph(const char* word,
rv = rv->next_homonym;
}
if (timelimit == 0)
return 0;
if (rv)
affixed = 0;
@ -2405,22 +2467,22 @@ int AffixMgr::compound_check_morph(const char* word,
if (rv && words && words[wnum + 1]) {
result.append(presult);
result.append(" ");
result.push_back(MSEP_FLD);
result.append(MORPH_PART);
result.append(word + i);
if (complexprefixes && HENTRY_DATA(rv))
result.append(HENTRY_DATA2(rv));
if (!HENTRY_FIND(rv, MORPH_STEM)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(MORPH_STEM);
result.append(HENTRY_WORD(rv));
}
// store the pointer of the hash entry
if (!complexprefixes && HENTRY_DATA(rv)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(HENTRY_DATA2(rv));
}
result.append("\n");
result.push_back(MSEP_REC);
return 0;
}
@ -2462,7 +2524,7 @@ int AffixMgr::compound_check_morph(const char* word,
((!checkcompounddup || (rv != rv_first)))) {
// bad compound word
result.append(presult);
result.append(" ");
result.push_back(MSEP_FLD);
result.append(MORPH_PART);
result.append(word + i);
@ -2470,17 +2532,17 @@ int AffixMgr::compound_check_morph(const char* word,
if (complexprefixes)
result.append(HENTRY_DATA2(rv));
if (!HENTRY_FIND(rv, MORPH_STEM)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(MORPH_STEM);
result.append(HENTRY_WORD(rv));
}
// store the pointer of the hash entry
if (!complexprefixes) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(HENTRY_DATA2(rv));
}
}
result.append("\n");
result.push_back(MSEP_REC);
ok = 1;
}
@ -2519,7 +2581,7 @@ int AffixMgr::compound_check_morph(const char* word,
line_uniq_app(m, MSEP_REC);
result.append(m);
}
result.append("\n");
result.push_back(MSEP_REC);
ok = 1;
}
}
@ -2552,7 +2614,9 @@ int AffixMgr::compound_check_morph(const char* word,
if (sfxappnd) {
std::string tmp(sfxappnd);
reverseword(tmp);
numsyllable -= get_syllable(tmp) + sfxextra;
numsyllable -= short(get_syllable(tmp) + sfxextra);
} else {
numsyllable -= short(sfxextra);
}
// + 1 word, if syllable number of the prefix > 1 (hungarian
@ -2605,8 +2669,9 @@ int AffixMgr::compound_check_morph(const char* word,
if (!m.empty()) {
result.push_back(MSEP_FLD);
result.append(MORPH_PART);
result.append(word + 1);
result.append(word + i);
line_uniq_app(m, MSEP_REC);
result.push_back(MSEP_FLD);
result.append(m);
}
result.push_back(MSEP_REC);
@ -2769,7 +2834,6 @@ struct hentry* AffixMgr::suffix_check(const char* word,
}
// check word for two-level suffixes
struct hentry* AffixMgr::suffix_check_twosfx(const char* word,
int len,
int sfxopts,
@ -2814,6 +2878,7 @@ struct hentry* AffixMgr::suffix_check_twosfx(const char* word,
return NULL;
}
// check word for two-level suffixes and morph
std::string AffixMgr::suffix_check_twosfx_morph(const char* word,
int len,
int sfxopts,
@ -2832,17 +2897,17 @@ std::string AffixMgr::suffix_check_twosfx_morph(const char* word,
if (ppfx) {
if (ppfx->getMorph()) {
result.append(ppfx->getMorph());
result.append(" ");
result.push_back(MSEP_FLD);
} else
debugflag(result, ppfx->getFlag());
}
result.append(st);
if (se->getMorph()) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(se->getMorph());
} else
debugflag(result, se->getFlag());
result.append("\n");
result.push_back(MSEP_REC);
}
}
se = se->getNext();
@ -2867,12 +2932,12 @@ std::string AffixMgr::suffix_check_twosfx_morph(const char* word,
result3.clear();
if (sptr->getMorph()) {
result3.append(" ");
result3.push_back(MSEP_FLD);
result3.append(sptr->getMorph());
} else
debugflag(result3, sptr->getFlag());
strlinecat(result2, result3);
result2.append("\n");
result2.push_back(MSEP_REC);
result.append(result2);
}
}
@ -2935,28 +3000,28 @@ std::string AffixMgr::suffix_check_morph(const char* word,
if (ppfx) {
if (ppfx->getMorph()) {
result.append(ppfx->getMorph());
result.append(" ");
result.push_back(MSEP_FLD);
} else
debugflag(result, ppfx->getFlag());
}
if (complexprefixes && HENTRY_DATA(rv))
result.append(HENTRY_DATA2(rv));
if (!HENTRY_FIND(rv, MORPH_STEM)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(MORPH_STEM);
result.append(HENTRY_WORD(rv));
}
if (!complexprefixes && HENTRY_DATA(rv)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(HENTRY_DATA2(rv));
}
if (se->getMorph()) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(se->getMorph());
} else
debugflag(result, se->getFlag());
result.append("\n");
result.push_back(MSEP_REC);
rv = se->get_next_homonym(rv, sfxopts, ppfx, cclass, needflag);
}
}
@ -3002,29 +3067,29 @@ std::string AffixMgr::suffix_check_morph(const char* word,
if (ppfx) {
if (ppfx->getMorph()) {
result.append(ppfx->getMorph());
result.append(" ");
result.push_back(MSEP_FLD);
} else
debugflag(result, ppfx->getFlag());
}
if (complexprefixes && HENTRY_DATA(rv))
result.append(HENTRY_DATA2(rv));
if (!HENTRY_FIND(rv, MORPH_STEM)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(MORPH_STEM);
result.append(HENTRY_WORD(rv));
}
if (!complexprefixes && HENTRY_DATA(rv)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(HENTRY_DATA2(rv));
}
if (sptr->getMorph()) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(sptr->getMorph());
} else
debugflag(result, sptr->getFlag());
result.append("\n");
result.push_back(MSEP_REC);
rv = sptr->get_next_homonym(rv, sfxopts, ppfx, cclass, needflag);
}
sptr = sptr->getNextEQ();
@ -3213,7 +3278,7 @@ std::string AffixMgr::morphgen(const char* ts,
// use input suffix fields, if exist
if (strstr(morph, MORPH_INFL_SFX) || strstr(morph, MORPH_DERI_SFX)) {
mymorph.assign(morph);
mymorph.append(" ");
mymorph.push_back(MSEP_FLD);
stemmorphcatpos = mymorph.size();
} else {
stemmorphcatpos = std::string::npos;
@ -3414,7 +3479,7 @@ int AffixMgr::expand_rootword(struct guessword* wlst,
// return replacing table
const std::vector<replentry>& AffixMgr::get_reptable() const {
return reptable;
return pHMgr->get_reptable();
}
// return iconv table
@ -3554,6 +3619,11 @@ FLAG AffixMgr::get_nongramsuggest() const {
return nongramsuggest;
}
// return the substandard root/affix control flag
FLAG AffixMgr::get_substandard() const {
return substandard;
}
// return the forbidden words flag modify flag
FLAG AffixMgr::get_needaffix() const {
return needaffix;
@ -3692,103 +3762,6 @@ bool AffixMgr::parse_cpdsyllable(const std::string& line, FileMgr* af) {
return true;
}
/* parse in the typical fault correcting table */
bool AffixMgr::parse_reptable(const std::string& line, FileMgr* af) {
if (parsedrep) {
HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n",
af->getlinenum());
return false;
}
parsedrep = true;
int numrep = -1;
int i = 0;
int np = 0;
std::string::const_iterator iter = line.begin();
std::string::const_iterator start_piece = mystrsep(line, iter);
while (start_piece != line.end()) {
switch (i) {
case 0: {
np++;
break;
}
case 1: {
numrep = atoi(std::string(start_piece, iter).c_str());
if (numrep < 1) {
HUNSPELL_WARNING(stderr, "error: line %d: incorrect entry number\n",
af->getlinenum());
return false;
}
reptable.reserve(numrep);
np++;
break;
}
default:
break;
}
++i;
start_piece = mystrsep(line, iter);
}
if (np != 2) {
HUNSPELL_WARNING(stderr, "error: line %d: missing data\n",
af->getlinenum());
return false;
}
/* now parse the numrep lines to read in the remainder of the table */
for (int j = 0; j < numrep; ++j) {
std::string nl;
if (!af->getline(nl))
return false;
mychomp(nl);
reptable.push_back(replentry());
iter = nl.begin();
i = 0;
int type = 0;
start_piece = mystrsep(nl, iter);
while (start_piece != nl.end()) {
switch (i) {
case 0: {
if (nl.compare(start_piece - nl.begin(), 3, "REP", 3) != 0) {
HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n",
af->getlinenum());
reptable.clear();
return false;
}
break;
}
case 1: {
if (*start_piece == '^')
type = 1;
reptable.back().pattern.assign(start_piece + type, iter);
mystrrep(reptable.back().pattern, "_", " ");
if (!reptable.back().pattern.empty() && reptable.back().pattern[reptable.back().pattern.size() - 1] == '$') {
type += 2;
reptable.back().pattern.resize(reptable.back().pattern.size() - 1);
}
break;
}
case 2: {
reptable.back().outstrings[type].assign(start_piece, iter);
mystrrep(reptable.back().outstrings[type], "_", " ");
break;
}
default:
break;
}
++i;
start_piece = mystrsep(nl, iter);
}
if (reptable.back().pattern.empty() || reptable.back().outstrings[type].empty()) {
HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n",
af->getlinenum());
reptable.clear();
return false;
}
}
return true;
}
/* parse in the typical fault correcting table */
bool AffixMgr::parse_convtable(const std::string& line,
FileMgr* af,
RepList** rl,
@ -4617,7 +4590,7 @@ bool AffixMgr::parse_affix(const std::string& line,
entry->appnd = std::string(start_piece, dash);
std::string dash_str(dash + 1, iter);
if (!ignorechars.empty()) {
if (!ignorechars.empty() && !has_no_ignored_chars(entry->appnd, ignorechars)) {
if (utf8) {
remove_ignored_chars_utf(entry->appnd, ignorechars_utf16);
} else {
@ -4653,7 +4626,7 @@ bool AffixMgr::parse_affix(const std::string& line,
} else {
entry->appnd = std::string(start_piece, iter);
if (!ignorechars.empty()) {
if (!ignorechars.empty() && !has_no_ignored_chars(entry->appnd, ignorechars)) {
if (utf8) {
remove_ignored_chars_utf(entry->appnd, ignorechars_utf16);
} else {

View File

@ -120,8 +120,6 @@ class AffixMgr {
FLAG nongramsuggest;
FLAG needaffix;
int cpdmin;
bool parsedrep;
std::vector<replentry> reptable;
RepList* iconvtable;
RepList* oconvtable;
bool parsedmaptable;
@ -251,6 +249,7 @@ class AffixMgr {
short get_syllable(const std::string& word);
int cpdrep_check(const char* word, int len);
int cpdwordpair_check(const char * word, int len);
int cpdpat_check(const char* word,
int len,
hentry* r1,
@ -311,6 +310,7 @@ class AffixMgr {
FLAG get_forbiddenword() const;
FLAG get_nosuggest() const;
FLAG get_nongramsuggest() const;
FLAG get_substandard() const;
FLAG get_needaffix() const;
FLAG get_onlyincompound() const;
const char* get_derived() const;
@ -338,7 +338,6 @@ class AffixMgr {
bool parse_flag(const std::string& line, unsigned short* out, FileMgr* af);
bool parse_num(const std::string& line, int* out, FileMgr* af);
bool parse_cpdsyllable(const std::string& line, FileMgr* af);
bool parse_reptable(const std::string& line, FileMgr* af);
bool parse_convtable(const std::string& line,
FileMgr* af,
RepList** rl,

View File

@ -95,6 +95,16 @@ static inline void HUNSPELL_WARNING(FILE*, const char*, ...) {}
#define TESTAFF(a, b, c) (std::binary_search(a, a + c, b))
// timelimit: max. ~1/4 sec (process time on Linux) for
// for a suggestion, including max. ~/10 sec for a case
// sensitive plain or compound word suggestion, within
// ~1/20 sec long time consuming suggestion functions
#define TIMELIMIT_GLOBAL (CLOCKS_PER_SEC / 4)
#define TIMELIMIT_SUGGESTION (CLOCKS_PER_SEC / 10)
#define TIMELIMIT (CLOCKS_PER_SEC / 20)
#define MINTIMER 100
#define MAXPLUSTIMER 100
struct guessword {
char* word;
bool allow;

View File

@ -69,6 +69,7 @@
*/
#include <algorithm>
#include <assert.h>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
@ -79,13 +80,6 @@
#include "atypes.hxx"
#include "langnum.hxx"
// Unicode character encoding information
struct unicode_info {
unsigned short c;
unsigned short cupper;
unsigned short clower;
};
#ifdef _WIN32
#include <windows.h>
#include <wchar.h>
@ -95,19 +89,17 @@ struct unicode_info {
#include <unicode/uchar.h>
#else
#ifndef MOZILLA_CLIENT
#include "utf_info.cxx"
#include "utf_info.hxx"
#define UTF_LST_LEN (sizeof(utf_lst) / (sizeof(unicode_info)))
#endif
#endif
#ifdef MOZILLA_CLIENT
#include "nsCOMPtr.h"
#include "nsIUnicodeEncoder.h"
#include "nsIUnicodeDecoder.h"
#include "nsUnicharUtils.h"
#include "mozilla/dom/EncodingUtils.h"
#include "mozilla/Encoding.h"
using mozilla::dom::EncodingUtils;
using namespace mozilla;
#endif
struct unicode_info2 {
@ -495,20 +487,17 @@ void uniqlist(std::vector<std::string>& list) {
namespace {
unsigned char cupper(const struct cs_info* csconv, int nIndex) {
if (nIndex < 0 || nIndex > 255)
return nIndex;
assert(nIndex >= 0 && nIndex <= 255);
return csconv[nIndex].cupper;
}
unsigned char clower(const struct cs_info* csconv, int nIndex) {
if (nIndex < 0 || nIndex > 255)
return nIndex;
assert(nIndex >= 0 && nIndex <= 255);
return csconv[nIndex].clower;
}
unsigned char ccase(const struct cs_info* csconv, int nIndex) {
if (nIndex < 0 || nIndex > 255)
return nIndex;
assert(nIndex >= 0 && nIndex <= 255);
return csconv[nIndex].ccase;
}
}
@ -2306,20 +2295,12 @@ struct cs_info* get_current_cs(const std::string& es) {
ccs[i].cupper = i;
}
nsCOMPtr<nsIUnicodeEncoder> encoder;
nsCOMPtr<nsIUnicodeDecoder> decoder;
nsresult rv;
nsAutoCString label(es.c_str());
nsAutoCString encoding;
if (!EncodingUtils::FindEncodingForLabelNoReplacement(label, encoding)) {
auto encoding = Encoding::ForLabelNoReplacement(es);
if (!encoding) {
return ccs;
}
encoder = EncodingUtils::EncoderForEncoding(encoding);
decoder = EncodingUtils::DecoderForEncoding(encoding);
encoder->SetOutputErrorBehavior(encoder->kOnError_Signal, nullptr, '?');
decoder->SetInputErrorBehavior(decoder->kOnError_Signal);
auto encoder = encoding->NewEncoder();
auto decoder = encoding->NewDecoderWithoutBOMHandling();
for (unsigned int i = 0; i <= 0xff; ++i) {
bool success = false;
@ -2327,36 +2308,50 @@ struct cs_info* get_current_cs(const std::string& es) {
// in this 1-byte character encoding. Call our encoding/decoding
// APIs separately for each byte since they may reject some of the
// bytes, and we want to handle errors separately for each byte.
char lower, upper;
uint8_t lower, upper;
do {
if (i == 0)
break;
const char source = char(i);
char16_t uni, uniCased;
int32_t charLength = 1, uniLength = 1;
uint8_t source = uint8_t(i);
char16_t uni[2];
char16_t uniCased;
uint8_t destination[4];
auto src1 = MakeSpan(&source, 1);
auto dst1 = MakeSpan(uni);
auto src2 = MakeSpan(&uniCased, 1);
auto dst2 = MakeSpan(destination);
rv = decoder->Convert(&source, &charLength, &uni, &uniLength);
// Explicitly check NS_OK because we don't want to allow
// NS_OK_UDEC_MOREOUTPUT or NS_OK_UDEC_MOREINPUT.
if (rv != NS_OK || charLength != 1 || uniLength != 1)
break;
uniCased = ToLowerCase(uni);
rv = encoder->Convert(&uniCased, &uniLength, &lower, &charLength);
// Explicitly check NS_OK because we don't want to allow
// NS_OK_UDEC_MOREOUTPUT or NS_OK_UDEC_MOREINPUT.
if (rv != NS_OK || charLength != 1 || uniLength != 1)
uint32_t result;
size_t read;
size_t written;
Tie(result, read, written) =
decoder->DecodeToUTF16WithoutReplacement(src1, dst1, true);
if (result != kInputEmpty || read != 1 || written != 1) {
break;
}
uniCased = ToUpperCase(uni);
rv = encoder->Convert(&uniCased, &uniLength, &upper, &charLength);
// Explicitly check NS_OK because we don't want to allow
// NS_OK_UDEC_MOREOUTPUT or NS_OK_UDEC_MOREINPUT.
if (rv != NS_OK || charLength != 1 || uniLength != 1)
uniCased = ToLowerCase(uni[0]);
Tie(result, read, written) =
encoder->EncodeFromUTF16WithoutReplacement(src2, dst2, true);
if (result != kInputEmpty || read != 1 || written != 1) {
break;
}
lower = destination[0];
uniCased = ToUpperCase(uni[0]);
Tie(result, read, written) =
encoder->EncodeFromUTF16WithoutReplacement(src2, dst2, true);
if (result != kInputEmpty || read != 1 || written != 1) {
break;
}
upper = destination[0];
success = true;
} while (0);
encoding->NewEncoderInto(*encoder);
encoding->NewDecoderWithoutBOMHandlingInto(*decoder);
if (success) {
ccs[i].cupper = upper;
ccs[i].clower = lower;
@ -2401,6 +2396,7 @@ static struct lang_map lang2enc[] =
{{"ar", LANG_ar}, {"az", LANG_az},
{"az_AZ", LANG_az}, // for back-compatibility
{"bg", LANG_bg}, {"ca", LANG_ca},
{"crh", LANG_crh},
{"cs", LANG_cs}, {"da", LANG_da},
{"de", LANG_de}, {"el", LANG_el},
{"en", LANG_en}, {"es", LANG_es},
@ -2458,7 +2454,7 @@ unsigned short unicodetoupper(unsigned short c, int langnum) {
// In Azeri and Turkish, I and i dictinct letters:
// There are a dotless lower case i pair of upper `I',
// and an upper I with dot pair of lower `i'.
if (c == 0x0069 && ((langnum == LANG_az) || (langnum == LANG_tr)))
if (c == 0x0069 && ((langnum == LANG_az) || (langnum == LANG_tr) || (langnum == LANG_crh)))
return 0x0130;
#ifdef OPENOFFICEORG
return static_cast<unsigned short>(u_toupper(c));
@ -2475,7 +2471,7 @@ unsigned short unicodetolower(unsigned short c, int langnum) {
// In Azeri and Turkish, I and i dictinct letters:
// There are a dotless lower case i pair of upper `I',
// and an upper I with dot pair of lower `i'.
if (c == 0x0049 && ((langnum == LANG_az) || (langnum == LANG_tr)))
if (c == 0x0049 && ((langnum == LANG_az) || (langnum == LANG_tr) || (langnum == LANG_crh)))
return 0x0131;
#ifdef OPENOFFICEORG
return static_cast<unsigned short>(u_tolower(c));

View File

@ -269,10 +269,23 @@ LIBHUNSPELL_DLL_EXPORTED void store_pointer(char* dest, char* source);
// conversion function for protected memory
LIBHUNSPELL_DLL_EXPORTED char* get_stored_pointer(const char* s);
// to avoid unnecessary string copies and Unicode conversions
// we simply check the ignored_chars characters in the word
// (in the case of UTF-8 encoded strings, "false" means
// "likely false", if ignored_chars characters are not ASCII)
inline bool has_no_ignored_chars(const std::string& word,
const std::string& ignored_chars) {
for (std::string::const_iterator it = ignored_chars.begin(), end = ignored_chars.end(); it != end; ++it)
if (word.find(*it) != std::string::npos)
return false;
return true;
}
// hash entry macros
LIBHUNSPELL_DLL_EXPORTED inline char* HENTRY_DATA(struct hentry* h) {
inline char* HENTRY_DATA(struct hentry* h) {
char* ret;
if (!h->var)
if (!(h->var & H_OPT))
ret = NULL;
else if (h->var & H_OPT_ALIASM)
ret = get_stored_pointer(HENTRY_WORD(h) + h->blen + 1);
@ -281,10 +294,10 @@ LIBHUNSPELL_DLL_EXPORTED inline char* HENTRY_DATA(struct hentry* h) {
return ret;
}
LIBHUNSPELL_DLL_EXPORTED inline const char* HENTRY_DATA(
inline const char* HENTRY_DATA(
const struct hentry* h) {
const char* ret;
if (!h->var)
if (!(h->var & H_OPT))
ret = NULL;
else if (h->var & H_OPT_ALIASM)
ret = get_stored_pointer(HENTRY_WORD(h) + h->blen + 1);
@ -294,10 +307,10 @@ LIBHUNSPELL_DLL_EXPORTED inline const char* HENTRY_DATA(
}
// NULL-free version for warning-free OOo build
LIBHUNSPELL_DLL_EXPORTED inline const char* HENTRY_DATA2(
inline const char* HENTRY_DATA2(
const struct hentry* h) {
const char* ret;
if (!h->var)
if (!(h->var & H_OPT))
ret = "";
else if (h->var & H_OPT_ALIASM)
ret = get_stored_pointer(HENTRY_WORD(h) + h->blen + 1);
@ -306,7 +319,7 @@ LIBHUNSPELL_DLL_EXPORTED inline const char* HENTRY_DATA2(
return ret;
}
LIBHUNSPELL_DLL_EXPORTED inline char* HENTRY_FIND(struct hentry* h,
inline char* HENTRY_FIND(struct hentry* h,
const char* p) {
return (HENTRY_DATA(h) ? strstr(HENTRY_DATA(h), p) : NULL);
}

View File

@ -78,6 +78,7 @@
#include "hashmgr.hxx"
#include "csutil.hxx"
#include "atypes.hxx"
#include "langnum.hxx"
// build a hash table from a munched word list
@ -182,13 +183,14 @@ int HashMgr::add_word(const std::string& in_word,
unsigned short* aff,
int al,
const std::string* in_desc,
bool onlyupcase) {
bool onlyupcase,
int captype) {
const std::string* word = &in_word;
const std::string* desc = in_desc;
std::string *word_copy = NULL;
std::string *desc_copy = NULL;
if (!ignorechars.empty() || complexprefixes) {
if ((!ignorechars.empty() && !has_no_ignored_chars(in_word, ignorechars)) || complexprefixes) {
word_copy = new std::string(in_word);
if (!ignorechars.empty()) {
@ -243,20 +245,119 @@ int HashMgr::add_word(const std::string& in_word,
hp->astr = aff;
hp->next = NULL;
hp->next_homonym = NULL;
hp->var = (captype == INITCAP) ? H_OPT_INITCAP : 0;
// store the description string or its pointer
if (desc) {
hp->var = H_OPT;
hp->var += H_OPT;
if (aliasm) {
hp->var += H_OPT_ALIASM;
store_pointer(hpw + word->size() + 1, get_aliasm(atoi(desc->c_str())));
} else {
strcpy(hpw + word->size() + 1, desc->c_str());
}
if (strstr(HENTRY_DATA(hp), MORPH_PHON))
if (strstr(HENTRY_DATA(hp), MORPH_PHON)) {
hp->var += H_OPT_PHON;
} else
hp->var = 0;
// store ph: fields (pronounciation, misspellings, old orthography etc.)
// of a morphological description in reptable to use in REP replacements.
if (reptable.capacity() < (unsigned int)(tablesize/MORPH_PHON_RATIO))
reptable.reserve(tablesize/MORPH_PHON_RATIO);
std::string fields = HENTRY_DATA(hp);
std::string::const_iterator iter = fields.begin();
std::string::const_iterator start_piece = mystrsep(fields, iter);
while (start_piece != fields.end()) {
if (std::string(start_piece, iter).find(MORPH_PHON) == 0) {
std::string ph = std::string(start_piece, iter).substr(sizeof MORPH_PHON - 1);
if (ph.size() > 0) {
std::vector<w_char> w;
size_t strippatt;
std::string wordpart;
// dictionary based REP replacement, separated by "->"
// for example "pretty ph:prity ph:priti->pretti" to handle
// both prity -> pretty and pritier -> prettiest suggestions.
if (((strippatt = ph.find("->")) != std::string::npos) &&
(strippatt > 0) && (strippatt < ph.size() - 2)) {
wordpart = ph.substr(strippatt + 2);
ph.erase(ph.begin() + strippatt, ph.end());
} else
wordpart = in_word;
// when the ph: field ends with the character *,
// strip last character of the pattern and the replacement
// to match in REP suggestions also at character changes,
// for example, "pretty ph:prity*" results "prit->prett"
// REP replacement instead of "prity->pretty", to get
// prity->pretty and pritiest->prettiest suggestions.
if (ph.at(ph.size()-1) == '*') {
strippatt = 1;
size_t stripword = 0;
if (utf8) {
while ((strippatt < ph.size()) &&
((ph.at(ph.size()-strippatt-1) & 0xc0) == 0x80))
++strippatt;
while ((stripword < wordpart.size()) &&
((wordpart.at(wordpart.size()-stripword-1) & 0xc0) == 0x80))
++stripword;
}
++strippatt;
++stripword;
if ((ph.size() > strippatt) && (wordpart.size() > stripword)) {
ph.erase(ph.size()-strippatt, strippatt);
wordpart.erase(in_word.size()-stripword, stripword);
}
}
// capitalize lowercase pattern for capitalized words to support
// good suggestions also for capitalized misspellings, eg.
// Wednesday ph:wendsay
// results wendsay -> Wednesday and Wendsay -> Wednesday, too.
if (captype==INITCAP) {
std::string ph_capitalized;
if (utf8) {
u8_u16(w, ph);
if (get_captype_utf8(w, langnum) == NOCAP) {
mkinitcap_utf(w, langnum);
u16_u8(ph_capitalized, w);
}
} else if (get_captype(ph, csconv) == NOCAP)
mkinitcap(ph_capitalized, csconv);
if (ph_capitalized.size() > 0) {
// add also lowercase word in the case of German or
// Hungarian to support lowercase suggestions lowercased by
// compound word generation or derivational suffixes
// (for example by adjectival suffix "-i" of geographical
// names in Hungarian:
// Massachusetts ph:messzecsuzec
// messzecsuzeci -> massachusettsi (adjective)
// For lowercasing by conditional PFX rules, see
// tests/germancompounding test example or the
// Hungarian dictionary.)
if (langnum == LANG_de || langnum == LANG_hu) {
std::string wordpart_lower(wordpart);
if (utf8) {
u8_u16(w, wordpart_lower);
mkallsmall_utf(w, langnum);
u16_u8(wordpart_lower, w);
} else {
mkallsmall(wordpart_lower, csconv);
}
reptable.push_back(replentry());
reptable.back().pattern.assign(ph);
reptable.back().outstrings[0].assign(wordpart_lower);
}
reptable.push_back(replentry());
reptable.back().pattern.assign(ph_capitalized);
reptable.back().outstrings[0].assign(wordpart);
}
}
reptable.push_back(replentry());
reptable.back().pattern.assign(ph);
reptable.back().outstrings[0].assign(wordpart);
}
}
start_piece = mystrsep(fields, iter);
}
}
}
struct hentry* dp = tableptr[i];
if (!dp) {
@ -347,12 +448,12 @@ int HashMgr::add_hidden_capitalized_word(const std::string& word,
mkallsmall_utf(w, langnum);
mkinitcap_utf(w, langnum);
u16_u8(st, w);
return add_word(st, wcl, flags2, flagslen + 1, dp, true);
return add_word(st, wcl, flags2, flagslen + 1, dp, true, INITCAP);
} else {
std::string new_word(word);
mkallsmall(new_word, csconv);
mkinitcap(new_word, csconv);
int ret = add_word(new_word, wcl, flags2, flagslen + 1, dp, true);
int ret = add_word(new_word, wcl, flags2, flagslen + 1, dp, true, INITCAP);
return ret;
}
}
@ -405,24 +506,8 @@ int HashMgr::remove_forbidden_flag(const std::string& word) {
if (!dp)
return 1;
while (dp) {
if (dp->astr && TESTAFF(dp->astr, forbiddenword, dp->alen)) {
if (dp->alen == 1)
dp->alen = 0; // XXX forbidden words of personal dic.
else {
unsigned short* flags2 =
(unsigned short*)malloc(sizeof(unsigned short) * (dp->alen - 1));
if (!flags2)
return 1;
int i, j = 0;
for (i = 0; i < dp->alen; i++) {
if (dp->astr[i] != forbiddenword)
flags2[j++] = dp->astr[i];
}
dp->alen--;
free(dp->astr);
dp->astr = flags2; // XXX allowed forbidden words
}
}
if (dp->astr && TESTAFF(dp->astr, forbiddenword, dp->alen))
dp->alen = 0; // XXX forbidden words of personal dic.
dp = dp->next_homonym;
}
return 0;
@ -435,7 +520,7 @@ int HashMgr::add(const std::string& word) {
int al = 0;
unsigned short* flags = NULL;
int wcl = get_clen_and_captype(word, &captype);
add_word(word, wcl, flags, al, NULL, false);
add_word(word, wcl, flags, al, NULL, false, captype);
return add_hidden_capitalized_word(word, wcl, flags, al, NULL,
captype);
}
@ -450,14 +535,14 @@ int HashMgr::add_with_affix(const std::string& word, const std::string& example)
int captype;
int wcl = get_clen_and_captype(word, &captype);
if (aliasf) {
add_word(word, wcl, dp->astr, dp->alen, NULL, false);
add_word(word, wcl, dp->astr, dp->alen, NULL, false, captype);
} else {
unsigned short* flags =
(unsigned short*)malloc(dp->alen * sizeof(unsigned short));
if (flags) {
memcpy((void*)flags, (void*)dp->astr,
dp->alen * sizeof(unsigned short));
add_word(word, wcl, flags, dp->alen, NULL, false);
add_word(word, wcl, flags, dp->alen, NULL, false, captype);
} else
return 1;
}
@ -605,7 +690,7 @@ int HashMgr::load_tables(const char* tpath, const char* key) {
int wcl = get_clen_and_captype(ts, &captype, workbuf);
const std::string *dp_str = dp.empty() ? NULL : &dp;
// add the word and its index plus its capitalized form optionally
if (add_word(ts, wcl, flags, al, dp_str, false) ||
if (add_word(ts, wcl, flags, al, dp_str, false, captype) ||
add_hidden_capitalized_word(ts, wcl, flags, al, dp_str, captype)) {
delete dict;
return 5;
@ -940,8 +1025,19 @@ int HashMgr::load_config(const char* affpath, const char* key) {
if (line.compare(0, 15, "COMPLEXPREFIXES", 15) == 0)
complexprefixes = 1;
/* parse in the typical fault correcting table */
if (line.compare(0, 3, "REP", 3) == 0) {
if (!parse_reptable(line, afflst)) {
delete afflst;
return 1;
}
}
// don't check the full affix file, yet
if (((line.compare(0, 3, "SFX", 3) == 0) ||
(line.compare(0, 3, "PFX", 3) == 0)) && line.size() > 3 && isspace(line[3]))
(line.compare(0, 3, "PFX", 3) == 0)) &&
line.size() > 3 && isspace(line[3]) &&
!reptable.empty()) // (REP table is in the end of Afrikaans aff file)
break;
}
@ -1191,3 +1287,103 @@ char* HashMgr::get_aliasm(int index) const {
HUNSPELL_WARNING(stderr, "error: bad morph. alias index: %d\n", index);
return NULL;
}
/* parse in the typical fault correcting table */
bool HashMgr::parse_reptable(const std::string& line, FileMgr* af) {
if (!reptable.empty()) {
HUNSPELL_WARNING(stderr, "error: line %d: multiple table definitions\n",
af->getlinenum());
return false;
}
int numrep = -1;
int i = 0;
int np = 0;
std::string::const_iterator iter = line.begin();
std::string::const_iterator start_piece = mystrsep(line, iter);
while (start_piece != line.end()) {
switch (i) {
case 0: {
np++;
break;
}
case 1: {
numrep = atoi(std::string(start_piece, iter).c_str());
if (numrep < 1) {
HUNSPELL_WARNING(stderr, "error: line %d: incorrect entry number\n",
af->getlinenum());
return false;
}
reptable.reserve(numrep);
np++;
break;
}
default:
break;
}
++i;
start_piece = mystrsep(line, iter);
}
if (np != 2) {
HUNSPELL_WARNING(stderr, "error: line %d: missing data\n",
af->getlinenum());
return false;
}
/* now parse the numrep lines to read in the remainder of the table */
for (int j = 0; j < numrep; ++j) {
std::string nl;
if (!af->getline(nl))
return false;
mychomp(nl);
reptable.push_back(replentry());
iter = nl.begin();
i = 0;
int type = 0;
start_piece = mystrsep(nl, iter);
while (start_piece != nl.end()) {
switch (i) {
case 0: {
if (nl.compare(start_piece - nl.begin(), 3, "REP", 3) != 0) {
HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n",
af->getlinenum());
reptable.clear();
return false;
}
break;
}
case 1: {
if (*start_piece == '^')
type = 1;
reptable.back().pattern.assign(start_piece + type, iter);
mystrrep(reptable.back().pattern, "_", " ");
if (!reptable.back().pattern.empty() && reptable.back().pattern[reptable.back().pattern.size() - 1] == '$') {
type += 2;
reptable.back().pattern.resize(reptable.back().pattern.size() - 1);
}
break;
}
case 2: {
reptable.back().outstrings[type].assign(start_piece, iter);
mystrrep(reptable.back().outstrings[type], "_", " ");
break;
}
default:
break;
}
++i;
start_piece = mystrsep(nl, iter);
}
if (reptable.back().pattern.empty() || reptable.back().outstrings[type].empty()) {
HUNSPELL_WARNING(stderr, "error: line %d: table is corrupt\n",
af->getlinenum());
reptable.clear();
return false;
}
}
return true;
}
// return replacing table
const std::vector<replentry>& HashMgr::get_reptable() const {
return reptable;
}

View File

@ -81,6 +81,12 @@
enum flag { FLAG_CHAR, FLAG_LONG, FLAG_NUM, FLAG_UNI };
// morphological description of a dictionary item can contain
// arbitrary number "ph:" (MORPH_PHON) fields to store typical
// phonetic or other misspellings of that word.
// ratio of lines/lines with "ph:" in the dic file: 1/MORPH_PHON_RATIO
#define MORPH_PHON_RATIO 500
class HashMgr {
int tablesize;
struct hentry** tableptr;
@ -99,6 +105,10 @@ class HashMgr {
unsigned short* aliasflen;
int numaliasm; // morphological desciption `compression' with aliases
char** aliasm;
// reptable created from REP table of aff file and from "ph:" fields
// of the dic file. It contains phonetic and other common misspellings
// (letters, letter groups and words) for better suggestions
std::vector<replentry> reptable;
public:
HashMgr(const char* tpath, const char* apath, const char* key = NULL);
@ -119,6 +129,7 @@ class HashMgr {
int get_aliasf(int index, unsigned short** fvec, FileMgr* af) const;
int is_aliasm() const;
char* get_aliasm(int index) const;
const std::vector<replentry>& get_reptable() const;
private:
int get_clen_and_captype(const std::string& word, int* captype);
@ -129,7 +140,8 @@ class HashMgr {
unsigned short* ap,
int al,
const std::string* desc,
bool onlyupcase);
bool onlyupcase,
int captype);
int load_config(const char* affpath, const char* key);
bool parse_aliasf(const std::string& line, FileMgr* af);
int add_hidden_capitalized_word(const std::string& word,
@ -139,6 +151,7 @@ class HashMgr {
const std::string* dp,
int captype);
bool parse_aliasm(const std::string& line, FileMgr* af);
bool parse_reptable(const std::string& line, FileMgr* af);
int remove_forbidden_flag(const std::string& word);
};

View File

@ -44,9 +44,10 @@
(v) = ((v) << (q)) | (((v) >> (32 - q)) & ((1 << (q)) - 1));
// hentry options
#define H_OPT (1 << 0)
#define H_OPT_ALIASM (1 << 1)
#define H_OPT_PHON (1 << 2)
#define H_OPT (1 << 0) // is there optional morphological data?
#define H_OPT_ALIASM (1 << 1) // using alias compression?
#define H_OPT_PHON (1 << 2) // is there ph: field in the morphological data?
#define H_OPT_INITCAP (1 << 3) // is dictionary word capitalized?
// see also csutil.hxx
#define HENTRY_WORD(h) &(h->word[0])
@ -54,6 +55,12 @@
// approx. number of user defined words
#define USERWORD 1000
#if __cplusplus >= 201103L || (defined(_MSC_VER) && _MSC_VER >= 1900)
# define HUNSPELL_THREAD_LOCAL thread_local
#else
# define HUNSPELL_THREAD_LOCAL static
#endif
struct hentry {
unsigned char blen; // word length in bytes
unsigned char clen; // word length in characters (different for UTF-8 enc.)
@ -61,7 +68,7 @@ struct hentry {
unsigned short* astr; // affix flag vector
struct hentry* next; // next word with same hash code
struct hentry* next_homonym; // next homonym word (with same hash code)
char var; // variable fields (only for special pronounciation yet)
char var; // bit vector of H_OPT hentry options
char word[1]; // variable-length word (8-bit or UTF-8 encoding)
};

View File

@ -3,7 +3,7 @@
#if defined(HUNSPELL_STATIC)
# define LIBHUNSPELL_DLL_EXPORTED
#elif defined(_MSC_VER)
#elif defined(_WIN32)
# if defined(BUILDING_LIBHUNSPELL)
# define LIBHUNSPELL_DLL_EXPORTED __declspec(dllexport)
# else

View File

@ -3,7 +3,7 @@
#if defined(HUNSPELL_STATIC)
# define LIBHUNSPELL_DLL_EXPORTED
#elif defined(_MSC_VER)
#elif defined(_WIN32)
# if defined(BUILDING_LIBHUNSPELL)
# define LIBHUNSPELL_DLL_EXPORTED __declspec(dllexport)
# else

View File

@ -178,7 +178,7 @@ int Hunzip::getbuf() {
do {
if (inc == 0) {
fin.read(in, BUFSIZE);
inbits = fin.gcount() * 8;
inbits = int(fin.gcount() * 8);
}
for (; inc < inbits; inc++) {
int b = (in[inc / 8] & (1 << (7 - (inc % 8)))) ? 1 : 0;

View File

@ -48,6 +48,7 @@ enum {
LANG_az = 100, // custom number
LANG_bg = 41,
LANG_ca = 37,
LANG_crh = 102, // custom number
LANG_cs = 42,
LANG_da = 45,
LANG_de = 49,

View File

@ -72,6 +72,7 @@
#include <string.h>
#include <stdio.h>
#include <ctype.h>
#include <time.h>
#include "suggestmgr.hxx"
#include "htypes.hxx"
@ -79,6 +80,8 @@
const w_char W_VLINE = {'\0', '|'};
#define MAX_CHAR_DISTANCE 4
SuggestMgr::SuggestMgr(const char* tryme, unsigned int maxn, AffixMgr* aptr) {
// register affix manager and check in string of chars to
// try when building candidate suggestions
@ -132,6 +135,11 @@ SuggestMgr::SuggestMgr(const char* tryme, unsigned int maxn, AffixMgr* aptr) {
ctryl = u8_u16(ctry_utf, tryme);
}
}
// language with possible dash usage
// (latin letters or dash in TRY characters)
lang_with_dash_usage = (ctry &&
((strchr(ctry, '-') != NULL) || (strchr(ctry, 'a') != NULL)));
}
SuggestMgr::~SuggestMgr() {
@ -169,10 +177,13 @@ void SuggestMgr::testsug(std::vector<std::string>& wlst,
}
}
// generate suggestions for a misspelled word
// pass in address of array of char * pointers
// onlycompoundsug: probably bad suggestions (need for ngram sugs, too)
void SuggestMgr::suggest(std::vector<std::string>& slst,
/* generate suggestions for a misspelled word
* pass in address of array of char * pointers
* onlycompoundsug: probably bad suggestions (need for ngram sugs, too)
* return value: true, if there is a good suggestion
* (REP, ph: or a dictionary word pair)
*/
bool SuggestMgr::suggest(std::vector<std::string>& slst,
const char* w,
int* onlycompoundsug) {
int nocompoundtwowords = 0;
@ -182,6 +193,7 @@ void SuggestMgr::suggest(std::vector<std::string>& slst,
std::string w2;
const char* word = w;
size_t oldSug = 0;
bool good_suggestion = false;
// word reversing wrapper for complex prefixes
if (complexprefixes) {
@ -196,34 +208,49 @@ void SuggestMgr::suggest(std::vector<std::string>& slst,
if (utf8) {
wl = u8_u16(word_utf, word);
if (wl == -1) {
return;
return false;
}
}
for (int cpdsuggest = 0; (cpdsuggest < 2) && (nocompoundtwowords == 0);
for (int cpdsuggest = 0; (cpdsuggest < 2) && (nocompoundtwowords == 0) && !good_suggestion;
cpdsuggest++) {
clock_t timelimit;
// initialize both in non-compound and compound cycles
timelimit = clock();
// limit compound suggestion
if (cpdsuggest > 0)
oldSug = slst.size();
// suggestions for an uppercase word (html -> HTML)
if (slst.size() < maxSug) {
size_t i = slst.size();
if (utf8)
capchars_utf(slst, &word_utf[0], wl, cpdsuggest);
else
capchars(slst, word, cpdsuggest);
if (slst.size() > i)
good_suggestion = true;
}
// perhaps we made a typical fault of spelling
if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) {
size_t i = slst.size();
replchars(slst, word, cpdsuggest);
if (slst.size() > i)
good_suggestion = true;
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
// perhaps we made chose the wrong char from a related set
if ((slst.size() < maxSug) &&
(!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) {
mapchars(slst, word, cpdsuggest);
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
// only suggest compound words when no other suggestion
if ((cpdsuggest == 0) && (slst.size() > nsugorig))
@ -236,6 +263,8 @@ void SuggestMgr::suggest(std::vector<std::string>& slst,
else
swapchar(slst, word, cpdsuggest);
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
// did we swap the order of non adjacent chars by mistake
if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) {
@ -244,6 +273,8 @@ void SuggestMgr::suggest(std::vector<std::string>& slst,
else
longswapchar(slst, word, cpdsuggest);
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
// did we just hit the wrong key in place of a good char (case and keyboard)
if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) {
@ -252,6 +283,8 @@ void SuggestMgr::suggest(std::vector<std::string>& slst,
else
badcharkey(slst, word, cpdsuggest);
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
// did we add a char that should not be there
if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) {
@ -260,6 +293,8 @@ void SuggestMgr::suggest(std::vector<std::string>& slst,
else
extrachar(slst, word, cpdsuggest);
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
// did we forgot a char
if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) {
@ -268,6 +303,8 @@ void SuggestMgr::suggest(std::vector<std::string>& slst,
else
forgotchar(slst, word, cpdsuggest);
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
// did we move a char
if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) {
@ -276,6 +313,8 @@ void SuggestMgr::suggest(std::vector<std::string>& slst,
else
movechar(slst, word, cpdsuggest);
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
// did we just hit the wrong key in place of a good char
if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) {
@ -284,6 +323,8 @@ void SuggestMgr::suggest(std::vector<std::string>& slst,
else
badchar(slst, word, cpdsuggest);
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
// did we double two characters
if ((slst.size() < maxSug) && (!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) {
@ -292,17 +333,25 @@ void SuggestMgr::suggest(std::vector<std::string>& slst,
else
doubletwochars(slst, word, cpdsuggest);
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
// perhaps we forgot to hit space and two words ran together
if (!nosplitsugs && (slst.size() < maxSug) &&
(!cpdsuggest || (slst.size() < oldSug + maxcpdsugs))) {
twowords(slst, word, cpdsuggest);
// (dictionary word pairs have top priority here, so
// we always suggest them, in despite of nosplitsugs, and
// drop compound word and other suggestions)
if (!cpdsuggest || (!nosplitsugs && slst.size() < oldSug + maxcpdsugs)) {
good_suggestion = twowords(slst, word, cpdsuggest, good_suggestion);
}
if (clock() > timelimit + TIMELIMIT_SUGGESTION)
return good_suggestion;
} // repeating ``for'' statement compounding support
if (!nocompoundtwowords && (!slst.empty()) && onlycompoundsug)
*onlycompoundsug = 1;
return good_suggestion;
}
// suggestions for an uppercase word (html -> HTML)
@ -450,8 +499,11 @@ int SuggestMgr::replchars(std::vector<std::string>& wlst,
return wlst.size();
}
// perhaps we doubled two characters (pattern aba -> ababa, for example vacation
// -> vacacation)
// perhaps we doubled two characters
// (for example vacation -> vacacation)
// The recognized pattern with regex back-references:
// "(.)(.)\1\2\1" or "..(.)(.)\1\2"
int SuggestMgr::doubletwochars(std::vector<std::string>& wlst,
const char* word,
int cpdsuggest) {
@ -462,7 +514,7 @@ int SuggestMgr::doubletwochars(std::vector<std::string>& wlst,
for (int i = 2; i < wl; i++) {
if (word[i] == word[i - 2]) {
state++;
if (state == 3) {
if (state == 3 || (state == 2 && i >= 4)) {
std::string candidate(word, word + i - 1);
candidate.insert(candidate.end(), word + i + 1, word + wl);
testsug(wlst, candidate, cpdsuggest, NULL, NULL);
@ -475,8 +527,11 @@ int SuggestMgr::doubletwochars(std::vector<std::string>& wlst,
return wlst.size();
}
// perhaps we doubled two characters (pattern aba -> ababa, for example vacation
// -> vacacation)
// perhaps we doubled two characters
// (for example vacation -> vacacation)
// The recognized pattern with regex back-references:
// "(.)(.)\1\2\1" or "..(.)(.)\1\2"
int SuggestMgr::doubletwochars_utf(std::vector<std::string>& wlst,
const w_char* word,
int wl,
@ -487,7 +542,7 @@ int SuggestMgr::doubletwochars_utf(std::vector<std::string>& wlst,
for (int i = 2; i < wl; i++) {
if (word[i] == word[i - 2]) {
state++;
if (state == 3) {
if (state == 3 || (state == 2 && i >= 4)) {
std::vector<w_char> candidate_utf(word, word + i - 1);
candidate_utf.insert(candidate_utf.end(), word + i + 1, word + wl);
std::string candidate;
@ -721,17 +776,22 @@ int SuggestMgr::forgotchar_utf(std::vector<std::string>& wlst,
return wlst.size();
}
/* error is should have been two words */
int SuggestMgr::twowords(std::vector<std::string>& wlst,
/* error is should have been two words
* return value is true, if there is a dictionary word pair,
* or there was already a good suggestion before calling
* this function.
*/
bool SuggestMgr::twowords(std::vector<std::string>& wlst,
const char* word,
int cpdsuggest) {
int cpdsuggest,
bool good) {
int c2;
int forbidden = 0;
int cwrd;
int wl = strlen(word);
if (wl < 3)
return wlst.size();
return false;
if (langnum == LANG_hu)
forbidden = check_forbidden(word, wl);
@ -750,63 +810,87 @@ int SuggestMgr::twowords(std::vector<std::string>& wlst,
}
if (utf8 && p[1] == '\0')
break; // last UTF-8 character
*p = '\0';
int c1 = checkword(candidate, cpdsuggest, NULL, NULL);
if (c1) {
c2 = checkword((p + 1), cpdsuggest, NULL, NULL);
if (c2) {
*p = ' ';
// spec. Hungarian code (need a better compound word support)
if ((langnum == LANG_hu) && !forbidden &&
// if 3 repeating letter, use - instead of space
(((p[-1] == p[1]) &&
// Suggest only word pairs, if they are listed in the dictionary.
// For example, adding "a lot" to the English dic file will
// result only "alot" -> "a lot" suggestion instead of
// "alto, slot, alt, lot, allot, aloft, aloe, clot, plot, blot, a lot".
// Note: using "ph:alot" keeps the other suggestions:
// a lot ph:alot
// alot -> a lot, alto, slot...
*p = ' ';
if (!cpdsuggest && checkword(candidate, cpdsuggest, NULL, NULL)) {
// remove not word pair suggestions
if (!good) {
good = true;
wlst.clear();
}
wlst.insert(wlst.begin(), candidate);
}
// word pairs with dash?
if (lang_with_dash_usage) {
*p = '-';
if (!cpdsuggest && checkword(candidate, cpdsuggest, NULL, NULL)) {
// remove not word pair suggestions
if (!good) {
good = true;
wlst.clear();
}
wlst.insert(wlst.begin(), candidate);
}
}
if (wlst.size() < maxSug && !nosplitsugs && !good) {
*p = '\0';
int c1 = checkword(candidate, cpdsuggest, NULL, NULL);
if (c1) {
c2 = checkword((p + 1), cpdsuggest, NULL, NULL);
if (c2) {
// spec. Hungarian code (TODO need a better compound word support)
if ((langnum == LANG_hu) && !forbidden &&
// if 3 repeating letter, use - instead of space
(((p[-1] == p[1]) &&
(((p > candidate + 1) && (p[-1] == p[-2])) || (p[-1] == p[2]))) ||
// or multiple compounding, with more, than 6 syllables
((c1 == 3) && (c2 >= 2))))
*p = '-';
// or multiple compounding, with more, than 6 syllables
((c1 == 3) && (c2 >= 2))))
*p = '-';
else
*p = ' ';
cwrd = 1;
for (size_t k = 0; k < wlst.size(); ++k) {
if (wlst[k] == candidate) {
cwrd = 0;
break;
}
}
if (wlst.size() < maxSug) {
if (cwrd) {
wlst.push_back(candidate);
}
} else {
free(candidate);
return wlst.size();
}
// add two word suggestion with dash, if TRY string contains
// "a" or "-"
// NOTE: cwrd doesn't modified for REP twoword sugg.
if (ctry && (strchr(ctry, 'a') || strchr(ctry, '-')) &&
mystrlen(p + 1) > 1 && mystrlen(candidate) - mystrlen(p) > 1) {
*p = '-';
cwrd = 1;
for (size_t k = 0; k < wlst.size(); ++k) {
if (wlst[k] == candidate) {
cwrd = 0;
break;
}
}
if (wlst.size() < maxSug) {
if (cwrd) {
if (cwrd && (wlst.size() < maxSug))
wlst.push_back(candidate);
// add two word suggestion with dash, depending on the language
// Note that cwrd doesn't modified for REP twoword sugg.
if ( !nosplitsugs && lang_with_dash_usage &&
mystrlen(p + 1) > 1 && mystrlen(candidate) - mystrlen(p) > 1) {
*p = '-';
for (size_t k = 0; k < wlst.size(); ++k) {
if (wlst[k] == candidate) {
cwrd = 0;
break;
}
}
} else {
free(candidate);
return wlst.size();
if ((wlst.size() < maxSug) && cwrd)
wlst.push_back(candidate);
}
}
}
}
}
free(candidate);
return wlst.size();
return good;
}
// error is adjacent letter were swapped
@ -891,7 +975,8 @@ int SuggestMgr::longswapchar(std::vector<std::string>& wlst,
// try swapping not adjacent chars one by one
for (std::string::iterator p = candidate.begin(); p < candidate.end(); ++p) {
for (std::string::iterator q = candidate.begin(); q < candidate.end(); ++q) {
if (std::abs(std::distance(q, p)) > 1) {
size_t distance = std::abs(std::distance(q, p));
if (distance > 1 && distance <= MAX_CHAR_DISTANCE) {
std::swap(*p, *q);
testsug(wlst, candidate, cpdsuggest, NULL, NULL);
std::swap(*p, *q);
@ -910,7 +995,8 @@ int SuggestMgr::longswapchar_utf(std::vector<std::string>& wlst,
// try swapping not adjacent chars
for (std::vector<w_char>::iterator p = candidate_utf.begin(); p < candidate_utf.end(); ++p) {
for (std::vector<w_char>::iterator q = candidate_utf.begin(); q < candidate_utf.end(); ++q) {
if (std::abs(std::distance(q, p)) > 1) {
size_t distance = std::abs(std::distance(q, p));
if (distance > 1 && distance <= MAX_CHAR_DISTANCE) {
std::swap(*p, *q);
std::string candidate;
u16_u8(candidate, candidate_utf);
@ -932,7 +1018,7 @@ int SuggestMgr::movechar(std::vector<std::string>& wlst,
// try moving a char
for (std::string::iterator p = candidate.begin(); p < candidate.end(); ++p) {
for (std::string::iterator q = p + 1; q < candidate.end() && std::distance(p, q) < 10; ++q) {
for (std::string::iterator q = p + 1; q < candidate.end() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) {
std::swap(*q, *(q - 1));
if (std::distance(p, q) < 2)
continue; // omit swap char
@ -942,7 +1028,7 @@ int SuggestMgr::movechar(std::vector<std::string>& wlst,
}
for (std::string::reverse_iterator p = candidate.rbegin(), pEnd = candidate.rend() - 1; p != pEnd; ++p) {
for (std::string::reverse_iterator q = p + 1, qEnd = candidate.rend(); q != qEnd && std::distance(p, q) < 10; ++q) {
for (std::string::reverse_iterator q = p + 1, qEnd = candidate.rend(); q != qEnd && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) {
std::swap(*q, *(q - 1));
if (std::distance(p, q) < 2)
continue; // omit swap char
@ -965,7 +1051,7 @@ int SuggestMgr::movechar_utf(std::vector<std::string>& wlst,
// try moving a char
for (std::vector<w_char>::iterator p = candidate_utf.begin(); p < candidate_utf.end(); ++p) {
for (std::vector<w_char>::iterator q = p + 1; q < candidate_utf.end() && std::distance(p, q) < 10; ++q) {
for (std::vector<w_char>::iterator q = p + 1; q < candidate_utf.end() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) {
std::swap(*q, *(q - 1));
if (std::distance(p, q) < 2)
continue; // omit swap char
@ -977,7 +1063,7 @@ int SuggestMgr::movechar_utf(std::vector<std::string>& wlst,
}
for (std::vector<w_char>::reverse_iterator p = candidate_utf.rbegin(); p < candidate_utf.rend(); ++p) {
for (std::vector<w_char>::reverse_iterator q = p + 1; q < candidate_utf.rend() && std::distance(p, q) < 10; ++q) {
for (std::vector<w_char>::reverse_iterator q = p + 1; q < candidate_utf.rend() && std::distance(p, q) <= MAX_CHAR_DISTANCE; ++q) {
std::swap(*q, *(q - 1));
if (std::distance(p, q) < 2)
continue; // omit swap char
@ -994,7 +1080,8 @@ int SuggestMgr::movechar_utf(std::vector<std::string>& wlst,
// generate a set of suggestions for very poorly spelled words
void SuggestMgr::ngsuggest(std::vector<std::string>& wlst,
const char* w,
const std::vector<HashMgr*>& rHMgr) {
const std::vector<HashMgr*>& rHMgr,
int captype) {
int lval;
int sc;
int lp, lpphon;
@ -1071,18 +1158,34 @@ void SuggestMgr::ngsuggest(std::vector<std::string>& wlst,
u8_u16(w_word, word);
u8_u16(w_target, target);
}
std::string f;
std::vector<w_char> w_f;
for (size_t i = 0; i < rHMgr.size(); ++i) {
while (0 != (hp = rHMgr[i]->walk_hashtable(col, hp))) {
if ((hp->astr) && (pAMgr) &&
(TESTAFF(hp->astr, forbiddenword, hp->alen) ||
TESTAFF(hp->astr, ONLYUPCASEFLAG, hp->alen) ||
TESTAFF(hp->astr, nosuggest, hp->alen) ||
TESTAFF(hp->astr, nongramsuggest, hp->alen) ||
TESTAFF(hp->astr, onlyincompound, hp->alen)))
// skip exceptions
if (
// skip it, if the word length different by 5 or
// more characters (to avoid strange suggestions)
// (except Unicode characters over BMP)
(((abs(n - hp->clen) > 4) && !nonbmp)) ||
// don't suggest capitalized dictionary words for
// lower case misspellings in ngram suggestions, except
// - PHONE usage, or
// - in the case of German, where not only proper
// nouns are capitalized, or
// - the capitalized word has special pronunciation
((captype == NOCAP) && (hp->var & H_OPT_INITCAP) &&
!ph && (langnum != LANG_de) && !(hp->var & H_OPT_PHON)) ||
// or it has one of the following special flags
((hp->astr) && (pAMgr) &&
(TESTAFF(hp->astr, forbiddenword, hp->alen) ||
TESTAFF(hp->astr, ONLYUPCASEFLAG, hp->alen) ||
TESTAFF(hp->astr, nosuggest, hp->alen) ||
TESTAFF(hp->astr, nongramsuggest, hp->alen) ||
TESTAFF(hp->astr, onlyincompound, hp->alen)))
)
continue;
if (utf8) {
@ -1105,7 +1208,7 @@ void SuggestMgr::ngsuggest(std::vector<std::string>& wlst,
sc = ngram(3, word, f, NGRAM_LONGER_WORSE) + leftcommon;
}
// check special pronounciation
// check special pronunciation
f.clear();
if ((hp->var & H_OPT_PHON) &&
copy_field(f, HENTRY_DATA(hp), MORPH_PHON)) {
@ -1559,7 +1662,8 @@ int SuggestMgr::checkword(const std::string& word,
if (rv) {
if ((rv->astr) &&
(TESTAFF(rv->astr, pAMgr->get_forbiddenword(), rv->alen) ||
TESTAFF(rv->astr, pAMgr->get_nosuggest(), rv->alen)))
TESTAFF(rv->astr, pAMgr->get_nosuggest(), rv->alen) ||
TESTAFF(rv->astr, pAMgr->get_substandard(), rv->alen)))
return 0;
while (rv) {
if (rv->astr &&
@ -1584,7 +1688,7 @@ int SuggestMgr::checkword(const std::string& word,
if (!rv && pAMgr->have_contclass()) {
rv = pAMgr->suffix_check_twosfx(word.c_str(), word.size(), 0, NULL, FLAG_NULL);
if (!rv)
rv = pAMgr->prefix_check_twosfx(word.c_str(), word.size(), 1, FLAG_NULL);
rv = pAMgr->prefix_check_twosfx(word.c_str(), word.size(), 0, FLAG_NULL);
}
// check forbidden words
@ -1649,15 +1753,15 @@ std::string SuggestMgr::suggest_morph(const std::string& in_w) {
TESTAFF(rv->astr, pAMgr->get_needaffix(), rv->alen) ||
TESTAFF(rv->astr, pAMgr->get_onlyincompound(), rv->alen))) {
if (!HENTRY_FIND(rv, MORPH_STEM)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(MORPH_STEM);
result.append(w);
}
if (HENTRY_DATA(rv)) {
result.append(" ");
result.push_back(MSEP_FLD);
result.append(HENTRY_DATA2(rv));
}
result.append("\n");
result.push_back(MSEP_REC);
}
rv = rv->next_homonym;
}
@ -1713,7 +1817,7 @@ std::string SuggestMgr::suggest_hentry_gen(hentry* rv, const char* pattern) {
HENTRY_DATA(rv), pattern, 0);
if (!aff.empty()) {
result.append(aff);
result.append("\n");
result.push_back(MSEP_REC);
}
}
@ -1737,7 +1841,7 @@ std::string SuggestMgr::suggest_hentry_gen(hentry* rv, const char* pattern) {
rv2->alen, HENTRY_DATA(rv2), pattern, 0);
if (!aff.empty()) {
result.append(aff);
result.append("\n");
result.push_back(MSEP_REC);
}
}
}

View File

@ -78,11 +78,6 @@
#define MAXPHONSUGS 2
#define MAXCOMPOUNDSUGS 3
// timelimit: max ~1/4 sec (process time on Linux) for a time consuming function
#define TIMELIMIT (CLOCKS_PER_SEC >> 2)
#define MINTIMER 100
#define MAXPLUSTIMER 100
#define NGRAM_LONGER_WORSE (1 << 0)
#define NGRAM_ANY_MISMATCH (1 << 1)
#define NGRAM_LOWERING (1 << 2)
@ -92,7 +87,6 @@
#include "affixmgr.hxx"
#include "hashmgr.hxx"
#include "langnum.hxx"
#include <time.h>
enum { LCS_UP, LCS_LEFT, LCS_UPLEFT };
@ -109,6 +103,7 @@ class SuggestMgr {
char* ctry;
size_t ctryl;
std::vector<w_char> ctry_utf;
bool lang_with_dash_usage;
AffixMgr* pAMgr;
unsigned int maxSug;
@ -124,8 +119,8 @@ class SuggestMgr {
SuggestMgr(const char* tryme, unsigned int maxn, AffixMgr* aptr);
~SuggestMgr();
void suggest(std::vector<std::string>& slst, const char* word, int* onlycmpdsug);
void ngsuggest(std::vector<std::string>& slst, const char* word, const std::vector<HashMgr*>& rHMgr);
bool suggest(std::vector<std::string>& slst, const char* word, int* onlycmpdsug);
void ngsuggest(std::vector<std::string>& slst, const char* word, const std::vector<HashMgr*>& rHMgr, int captype);
std::string suggest_morph(const std::string& word);
std::string suggest_gen(const std::vector<std::string>& pl, const std::string& pattern);
@ -149,7 +144,7 @@ class SuggestMgr {
int extrachar(std::vector<std::string>&, const char*, int);
int badcharkey(std::vector<std::string>&, const char*, int);
int badchar(std::vector<std::string>&, const char*, int);
int twowords(std::vector<std::string>&, const char*, int);
bool twowords(std::vector<std::string>&, const char*, int, bool);
void capchars_utf(std::vector<std::string>&, const w_char*, int wl, int);
int doubletwochars_utf(std::vector<std::string>&, const w_char*, int wl, int);

View File

@ -35,9 +35,15 @@
*
* ***** END LICENSE BLOCK ***** */
#include "csutil.hxx"
// Unicode character encoding information
struct unicode_info {
unsigned short c;
unsigned short cupper;
unsigned short clower;
};
/* fields: Unicode letter, toupper, tolower */
static struct unicode_info utf_lst[] = {
static const struct unicode_info utf_lst[] = {
{0x0041, 0x0041, 0x0061}, {0x0042, 0x0042, 0x0062},
{0x0043, 0x0043, 0x0063}, {0x0044, 0x0044, 0x0064},
{0x0045, 0x0045, 0x0065}, {0x0046, 0x0046, 0x0066},

View File

@ -15,4 +15,4 @@ testparser_SOURCES=firstparser.cxx firstparser.hxx xmlparser.cxx \
htmlparser.hxx odfparser.hxx odfparser.cxx
# need mystrdup()
LDADD = ../hunspell/libhunspell-1.6.la
LDADD = ../hunspell/libhunspell-1.7.la

View File

@ -69,6 +69,10 @@ static const char* PATTERN2[][2] = {
#define PATTERN_LEN2 (sizeof(PATTERN2) / (sizeof(char*) * 2))
static const char* (*PATTERN3)[2] = NULL;
#define PATTERN_LEN3 0
HTMLParser::HTMLParser(const char* wordchars)
: XMLParser(wordchars) {
}
@ -78,7 +82,7 @@ HTMLParser::HTMLParser(const w_char* wordchars, int len)
}
bool HTMLParser::next_token(std::string& t) {
return XMLParser::next_token(PATTERN, PATTERN_LEN, PATTERN2, PATTERN_LEN2, t);
return XMLParser::next_token(PATTERN, PATTERN_LEN, PATTERN2, PATTERN_LEN2, PATTERN3, PATTERN_LEN3, t);
}
HTMLParser::~HTMLParser() {}

View File

@ -47,6 +47,9 @@
using namespace std;
#endif
#define UTF8_APOS "\xe2\x80\x99"
#define APOSTROPHE "'"
static struct {
const char* pat[2];
int arg;
@ -203,7 +206,20 @@ bool LaTeXParser::next_token(std::string& t) {
break;
case 1: // wordchar
apostrophe = 0;
if (!is_wordchar(line[actual].c_str() + head) ||
if ((is_wordchar((char*)APOSTROPHE) ||
(is_utf8() && is_wordchar((char*)UTF8_APOS))) &&
!line[actual].empty() && line[actual][head] == '\'' &&
is_wordchar(line[actual].c_str() + head + 1)) {
head++;
} else if (is_utf8() &&
is_wordchar((char*)APOSTROPHE) && // add Unicode apostrophe
// to the WORDCHARS, if
// needed
strncmp(line[actual].c_str() + head, UTF8_APOS, strlen(UTF8_APOS)) ==
0 &&
is_wordchar(line[actual].c_str() + head + strlen(UTF8_APOS))) {
head += strlen(UTF8_APOS) - 1;
} else if (!is_wordchar(line[actual].c_str() + head) ||
(line[actual][head] == '\'' && line[actual][head + 1] == '\'' &&
++apostrophe)) {
state = 0;

View File

@ -71,7 +71,7 @@ bool ManParser::next_token(std::string& t) {
} else {
state = 2;
}
// no break
/* FALLTHROUGH */
case 2: // non word chars
if (is_wordchar(line[actual].c_str() + head)) {
state = 3;

View File

@ -61,6 +61,12 @@ static const char* (*PATTERN2)[2] = NULL;
#define PATTERN_LEN2 0
static const char* PATTERN3[][2] = {
{"<text:span", ">"}, // part of the reedited words
{"</text:span", ">"}}; // for example, an inserted letter
#define PATTERN_LEN3 (sizeof(PATTERN3) / (sizeof(char*) * 2))
ODFParser::ODFParser(const char* wordchars)
: XMLParser(wordchars) {
}
@ -70,7 +76,11 @@ ODFParser::ODFParser(const w_char* wordchars, int len)
}
bool ODFParser::next_token(std::string& t) {
return XMLParser::next_token(PATTERN, PATTERN_LEN, PATTERN2, PATTERN_LEN2, t);
return XMLParser::next_token(PATTERN, PATTERN_LEN, PATTERN2, PATTERN_LEN2, PATTERN3, PATTERN_LEN3, t);
}
std::string ODFParser::get_word(const std::string &tok) {
return XMLParser::get_word2(PATTERN3, PATTERN_LEN3, tok);
}
ODFParser::~ODFParser() {}

View File

@ -50,6 +50,7 @@ class ODFParser : public XMLParser {
explicit ODFParser(const char* wc);
ODFParser(const w_char* wordchars, int len);
virtual bool next_token(std::string&);
virtual std::string get_word(const std::string &tok);
virtual ~ODFParser();
};

View File

@ -222,6 +222,10 @@ int TextParser::change_token(const char* word) {
return 0;
}
std::string TextParser::get_word(const std::string &tok) {
return tok;
}
void TextParser::check_urls() {
urlline.resize(line[actual].size() + 1);
int url_state = 0;

View File

@ -78,6 +78,7 @@ class TextParser {
std::string get_line() const;
std::string get_prevline(int n) const;
virtual bool next_token(std::string&);
virtual std::string get_word(const std::string &tok);
virtual int change_token(const char* word);
void set_url_checking(int check);

View File

@ -55,22 +55,29 @@ static const char* __PATTERN__[][2] = {{"<!--", "-->"},
#define __PATTERN_LEN__ (sizeof(__PATTERN__) / (sizeof(char*) * 2))
// for checking attributes, eg. <img alt="text"> in HTML
static const char* (*__PATTERN2__)[2] = NULL;
#define __PATTERN_LEN2__ 0
// for checking words with in-word patterns
// for example, "exam<text:span>p</text:span>le" in ODT
static const char* (*__PATTERN3__)[2] = NULL;
#define __PATTERN_LEN3__ 0
#define ENTITY_APOS "&apos;"
#define UTF8_APOS "\xe2\x80\x99"
#define APOSTROPHE "'"
XMLParser::XMLParser(const char* wordchars)
: TextParser(wordchars)
, pattern_num(0), pattern2_num(0), prevstate(0), checkattr(0), quotmark(0) {
, pattern_num(0), pattern2_num(0), pattern3_num(0), prevstate(0), checkattr(0), quotmark(0) {
}
XMLParser::XMLParser(const w_char* wordchars, int len)
: TextParser(wordchars, len)
, pattern_num(0), pattern2_num(0), prevstate(0), checkattr(0), quotmark(0) {
, pattern_num(0), pattern2_num(0), pattern3_num(0), prevstate(0), checkattr(0), quotmark(0) {
}
XMLParser::~XMLParser() {}
@ -98,6 +105,8 @@ bool XMLParser::next_token(const char* PATTERN[][2],
unsigned int PATTERN_LEN,
const char* PATTERN2[][2],
unsigned int PATTERN_LEN2,
const char* PATTERN3[][2],
unsigned int PATTERN_LEN3,
std::string& t) {
t.clear();
const char* latin1;
@ -141,7 +150,19 @@ bool XMLParser::next_token(const char* PATTERN[][2],
is_wordchar(line[actual].c_str() + head + strlen(UTF8_APOS))) {
head += strlen(UTF8_APOS) - 1;
} else if (!is_wordchar(line[actual].c_str() + head)) {
// in-word patterns
if ((pattern3_num = look_pattern(PATTERN3, PATTERN_LEN3, 0)) != -1) {
size_t pos = line[actual].find(PATTERN3[pattern3_num][1], head);
if (pos != std::string::npos) {
size_t endpos = pos + strlen(PATTERN3[pattern3_num][1]) - 1;
if (is_wordchar(line[actual].c_str() + endpos + 1)) {
head = endpos;
break;
}
}
}
state = prevstate;
// return with the token, except in the case of in-word patterns
if (alloc_token(token, &head, t))
return true;
}
@ -193,7 +214,26 @@ bool XMLParser::next_token(const char* PATTERN[][2],
bool XMLParser::next_token(std::string& t) {
return next_token(__PATTERN__, __PATTERN_LEN__, __PATTERN2__,
__PATTERN_LEN2__, t);
__PATTERN_LEN2__, __PATTERN3__, __PATTERN_LEN3__, t);
}
// remove in-word patterns
std::string XMLParser::get_word2(
const char* PATTERN3[][2],
unsigned int PATTERN_LEN3,
const std::string &tok) {
std::string word = tok;
for (unsigned int i = 0; i < PATTERN_LEN3; i++) {
size_t pos;
while ((pos = word.find(PATTERN3[i][0])) != word.npos) {
size_t endpos = word.find(PATTERN3[i][1], pos);
if (endpos != word.npos) {
word.erase(pos, endpos + strlen(PATTERN3[i][1]) - pos);
} else
return word;
}
}
return word;
}
int XMLParser::change_token(const char* word) {

View File

@ -53,8 +53,13 @@ class XMLParser : public TextParser {
unsigned int len,
const char* p2[][2],
unsigned int len2,
const char* p3[][2],
unsigned int len3,
std::string&);
virtual bool next_token(std::string&);
std::string get_word2(const char* p2[][2],
unsigned int len2,
const std::string &tok);
int change_token(const char* word);
virtual ~XMLParser();
@ -62,6 +67,7 @@ class XMLParser : public TextParser {
int look_pattern(const char* p[][2], unsigned int len, int column);
int pattern_num;
int pattern2_num;
int pattern3_num;
int prevstate;
int checkattr;
char quotmark;

View File

@ -4,62 +4,59 @@ noinst_LIBRARIES = liblyxhunspell.a
EXTRA_DIST = \
CMakeLists.txt \
1.6.2/AUTHORS \
1.6.2/BUGS \
1.6.2/ChangeLog \
1.6.2/COPYING \
1.6.2/COPYING.LESSER \
1.6.2/license.hunspell \
1.6.2/README.md \
1.6.2/THANKS \
1.6.2/TODO \
1.6.2/src/hunspell/hunvisapi.h.in \
1.6.2/src/hunspell/utf_info.cxx
1.7.0/AUTHORS \
1.7.0/ChangeLog \
1.7.0/COPYING \
1.7.0/COPYING.LESSER \
1.7.0/license.hunspell \
1.7.0/NEWS \
1.7.0/README \
1.7.0/THANKS \
1.7.0/src/hunspell/hunvisapi.h.in
AM_CPPFLAGS += -DHUNSPELL_STATIC @STDLIB_DEBUG@
liblyxhunspell_a_SOURCES = \
1.6.2/src/hunspell/affentry.cxx \
1.6.2/src/hunspell/affentry.hxx \
1.6.2/src/hunspell/affixmgr.cxx \
1.6.2/src/hunspell/affixmgr.hxx \
1.6.2/src/hunspell/atypes.hxx \
1.6.2/src/hunspell/baseaffix.hxx \
1.6.2/src/hunspell/csutil.cxx \
1.6.2/src/hunspell/csutil.hxx \
1.6.2/src/hunspell/filemgr.cxx \
1.6.2/src/hunspell/filemgr.hxx \
1.6.2/src/hunspell/hashmgr.cxx \
1.6.2/src/hunspell/hashmgr.hxx \
1.6.2/src/hunspell/htypes.hxx \
1.6.2/src/hunspell/hunspell.cxx \
1.6.2/src/hunspell/hunspell.h \
1.6.2/src/hunspell/hunspell.hxx \
1.6.2/src/hunspell/hunvisapi.h \
1.6.2/src/hunspell/hunzip.cxx \
1.6.2/src/hunspell/hunzip.hxx \
1.6.2/src/hunspell/langnum.hxx \
1.6.2/src/hunspell/phonet.cxx \
1.6.2/src/hunspell/phonet.hxx \
1.6.2/src/hunspell/replist.cxx \
1.6.2/src/hunspell/replist.hxx \
1.6.2/src/hunspell/suggestmgr.cxx \
1.6.2/src/hunspell/suggestmgr.hxx \
1.6.2/src/hunspell/w_char.hxx \
1.6.2/src/parsers/firstparser.cxx \
1.6.2/src/parsers/firstparser.hxx \
1.6.2/src/parsers/htmlparser.cxx \
1.6.2/src/parsers/htmlparser.hxx \
1.6.2/src/parsers/latexparser.cxx \
1.6.2/src/parsers/latexparser.hxx \
1.6.2/src/parsers/manparser.cxx \
1.6.2/src/parsers/manparser.hxx \
1.6.2/src/parsers/odfparser.cxx \
1.6.2/src/parsers/odfparser.hxx \
1.6.2/src/parsers/testparser.cxx \
1.6.2/src/parsers/textparser.cxx \
1.6.2/src/parsers/textparser.hxx \
1.6.2/src/parsers/xmlparser.cxx \
1.6.2/src/parsers/xmlparser.hxx \
1.6.2/src/win_api/config.h
1.7.0/src/hunspell/affentry.cxx \
1.7.0/src/hunspell/affentry.hxx \
1.7.0/src/hunspell/affixmgr.cxx \
1.7.0/src/hunspell/affixmgr.hxx \
1.7.0/src/hunspell/atypes.hxx \
1.7.0/src/hunspell/baseaffix.hxx \
1.7.0/src/hunspell/csutil.cxx \
1.7.0/src/hunspell/csutil.hxx \
1.7.0/src/hunspell/filemgr.cxx \
1.7.0/src/hunspell/filemgr.hxx \
1.7.0/src/hunspell/hashmgr.cxx \
1.7.0/src/hunspell/hashmgr.hxx \
1.7.0/src/hunspell/htypes.hxx \
1.7.0/src/hunspell/hunspell.cxx \
1.7.0/src/hunspell/hunspell.h \
1.7.0/src/hunspell/hunspell.hxx \
1.7.0/src/hunspell/hunvisapi.h \
1.7.0/src/hunspell/hunzip.cxx \
1.7.0/src/hunspell/hunzip.hxx \
1.7.0/src/hunspell/langnum.hxx \
1.7.0/src/hunspell/phonet.cxx \
1.7.0/src/hunspell/phonet.hxx \
1.7.0/src/hunspell/replist.cxx \
1.7.0/src/hunspell/replist.hxx \
1.7.0/src/hunspell/suggestmgr.cxx \
1.7.0/src/hunspell/suggestmgr.hxx \
1.7.0/src/hunspell/utf_info.hxx \
1.7.0/src/hunspell/w_char.hxx \
1.7.0/src/parsers/firstparser.cxx \
1.7.0/src/parsers/firstparser.hxx \
1.7.0/src/parsers/htmlparser.cxx \
1.7.0/src/parsers/htmlparser.hxx \
1.7.0/src/parsers/latexparser.cxx \
1.7.0/src/parsers/latexparser.hxx \
1.7.0/src/parsers/manparser.cxx \
1.7.0/src/parsers/manparser.hxx \
1.7.0/src/parsers/odfparser.cxx \
1.7.0/src/parsers/odfparser.hxx \
1.7.0/src/parsers/testparser.cxx \
1.7.0/src/parsers/textparser.cxx \
1.7.0/src/parsers/textparser.hxx \
1.7.0/src/parsers/xmlparser.cxx \
1.7.0/src/parsers/xmlparser.hxx

View File

@ -121,7 +121,7 @@ AC_DEFUN([LYX_USE_INCLUDED_HUNSPELL],[
AC_MSG_RESULT([$lyx_cv_with_included_hunspell])
if test x$lyx_cv_with_included_hunspell = xyes ; then
lyx_included_libs="$lyx_included_libs hunspell"
HUNSPELL_CFLAGS='-I$(top_srcdir)/3rdparty/hunspell/1.6.2/src'
HUNSPELL_CFLAGS='-I$(top_srcdir)/3rdparty/hunspell/1.7.0/src'
HUNSPELL_LIBS='$(top_builddir)/3rdparty/hunspell/liblyxhunspell.a'
AC_SUBST(HUNSPELL_CFLAGS)
AC_SUBST(HUNSPELL_LIBS)

View File

@ -101,3 +101,6 @@ What's new
* BUILD/INSTALLATION
- Remove use of deprecated Qt methods.
- Update in-tree hunspell library to 1.7.0.