hashirama/goldendict-ng
hashirama/goldendict-ng
0
0
Fork 0
mirror of https://github.com/xiaoyifang/goldendict-ng.git synced 2024-11-23 20:14:05 +00:00
Code Issues Actions 1 Projects Releases Wiki Activity

Created /trunk/src and moved everything there.

Browse source
This commit is contained in:
Konstantin Isakov 2009-01-28 20:55:45 +00:00
commit c05781368b
340 changed files with 24040 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

691
src/LICENSE.txt Normal file
View file

@ -0,0 +1,691 @@
GoldenDict, a dictionary lookup program.
Copyright (C) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
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.
The text of the license follows.
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>.

116
src/article_maker.cc Normal file
View file

@ -0,0 +1,116 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "article_maker.hh"
#include "config.hh"
#include "htmlescape.hh"
#include "utf8.hh"
#include <QFile>
#include <set>
using std::vector;
using std::string;
using std::wstring;
using std::set;
ArticleMaker::ArticleMaker( vector< sptr< Dictionary::Class > > const & dictionaries_,
vector< Instances::Group > const & groups_ ):
dictionaries( dictionaries_ ),
groups( groups_ )
{
}
string ArticleMaker::makeDefinitionFor( QString const & inWord,
QString const & group ) const
{
printf( "group = %ls\n", group.toStdWString().c_str() );
wstring word = inWord.trimmed().toStdWString();
string result =
"<html><head>"
"<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\">";
QFile cssFile( Config::getUserCssFileName() );
if ( cssFile.open( QFile::ReadOnly ) )
{
result += "<style type=\"text/css\">\n";
result += cssFile.readAll().data();
result += "</style>\n";
}
result += "<title>" + Html::escape( Utf8::encode( word ) ) + "</title>";
// Find the given group
Instances::Group const * activeGroup = 0;
for( unsigned x = 0; x < groups.size(); ++x )
if ( groups[ x ].name == group )
{
activeGroup = &groups[ x ];
break;
}
// If we've found a group, use its dictionaries; otherwise, use the global
// heap.
std::vector< sptr< Dictionary::Class > > const & activeDicts =
activeGroup ? activeGroup->dictionaries : dictionaries;
if ( activeGroup && activeGroup->icon.size() )
{
// This doesn't seem to be much of influence right now, but we'll keep
// it anyway.
result += "<link rel=\"icon\" type=\"image/png\" href=\"qrcx://localhost/flags/" + Html::escape( activeGroup->icon.toUtf8().data() ) + "\" />\n";
}
result += "</head><body>";
// Accumulate main forms
vector< wstring > alts;
{
set< wstring > altsSet;
for( unsigned x = 0; x < activeDicts.size(); ++x )
{
vector< wstring > found = activeDicts[ x ]->findHeadwordsForSynonym( word );
altsSet.insert( found.begin(), found.end() );
}
alts.insert( alts.begin(), altsSet.begin(), altsSet.end() );
}
for( unsigned x = 0; x < alts.size(); ++x )
{
printf( "Alt: %ls\n", alts[ x ].c_str() );
}
for( unsigned x = 0; x < activeDicts.size(); ++x )
{
try
{
string body = activeDicts[ x ]->getArticle( word, alts );
printf( "From %s: %s\n", activeDicts[ x ]->getName().c_str(), body.c_str() );
result += "<div class=\"gddictname\">From " + Html::escape( activeDicts[ x ]->getName() ) + "</div>" + body;
}
catch( Dictionary::exNoSuchWord & )
{
continue;
}
}
result += "</body></html>";
return result;
}

30
src/article_maker.hh Normal file
View file

@ -0,0 +1,30 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __ARTICLE_MAKER_HH_INCLUDED__
#define __ARTICLE_MAKER_HH_INCLUDED__
#include "dictionary.hh"
#include "instances.hh"
/// This class generates the article's body for the given lookup request
class ArticleMaker
{
std::vector< sptr< Dictionary::Class > > const & dictionaries;
std::vector< Instances::Group > const & groups;
public:
/// On construction, a reference to all dictionaries and a reference all
/// groups' instances are to be passed. Those references are kept stored as
/// references, and as such, any changes to them would reflect on the results
/// of the inquiries, altthough those changes are perfectly legal.
ArticleMaker( std::vector< sptr< Dictionary::Class > > const & dictionaries,
std::vector< Instances::Group > const & groups );
/// Looks up the given word within the given group, and creates a full html
/// page text containing its definition.
std::string makeDefinitionFor( QString const & word, QString const & group ) const;
};
#endif

146
src/article_netmgr.cc Normal file
View file

@ -0,0 +1,146 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "article_netmgr.hh"
using std::string;
QNetworkReply * ArticleNetworkAccessManager::createRequest( Operation op,
QNetworkRequest const & req,
QIODevice * outgoingData )
{
if ( op == GetOperation )
{
if ( req.url().scheme() == "qrcx" )
{
// We have to override the local load policy for the qrc scheme, hence
// we use qrcx and redirect it here back to qrc
QUrl newUrl( req.url() );
newUrl.setScheme( "qrc" );
newUrl.setHost( "" );
QNetworkRequest newReq( req );
newReq.setUrl( newUrl );
return QNetworkAccessManager::createRequest( op, newReq, outgoingData );
}
vector< char > data;
QString contentType;
if ( getResource( req.url(), data, contentType ) )
return new ArticleResourceReply( this, req, data, contentType );
}
return QNetworkAccessManager::createRequest( op, req, outgoingData );
}
bool ArticleNetworkAccessManager::getResource( QUrl const & url,
vector< char > & data,
QString & contentType )
{
//printf( "getResource: %ls\n", url.toString().toStdWString().c_str() );
//printf( "scheme: %ls\n", url.scheme().toStdWString().c_str() );
//printf( "host: %ls\n", url.host().toStdWString().c_str() );
if ( url.scheme() == "gdlookup" )
{
string result = articleMaker.makeDefinitionFor( url.queryItemValue( "word" ),
url.queryItemValue( "group" ) );
data.resize( result.size() );
memcpy( &data.front(), result.data(), data.size() );
contentType = "text/html";
return true;
}
if ( ( url.scheme() == "bres" || url.scheme() == "gdau" ) &&
url.path().size() )
{
//printf( "Get %s\n", req.url().host().toLocal8Bit().data() );
//printf( "Get %s\n", req.url().path().toLocal8Bit().data() );
string id = url.host().toStdString();
bool search = ( id == "search" );
for( unsigned x = 0; x < dictionaries.size(); ++x )
{
if ( search || dictionaries[ x ]->getId() == id )
{
try
{
dictionaries[ x ]->getResource( url.path().mid( 1 ).toUtf8().data(),
data );
return true;
}
catch( Dictionary::exNoSuchResource & )
{
if ( !search )
break;
}
}
}
}
return false;
}
ArticleResourceReply::ArticleResourceReply( QObject * parent,
QNetworkRequest const & req,
vector< char > const & data_,
QString const & contentType ):
QNetworkReply( parent ), data( data_ ), left( data.size() )
{
setRequest( req );
setOpenMode( ReadOnly );
if ( contentType.size() )
setHeader( QNetworkRequest::ContentTypeHeader, contentType );
connect( this, SIGNAL( readyReadSignal() ),
this, SLOT( readyReadSlot() ), Qt::QueuedConnection );
connect( this, SIGNAL( finishedSignal() ),
this, SLOT( finishedSlot() ), Qt::QueuedConnection );
emit readyReadSignal();
emit finishedSignal();
}
qint64 ArticleResourceReply::bytesAvailable() const
{
return left + QNetworkReply::bytesAvailable();
}
qint64 ArticleResourceReply::readData( char * out, qint64 maxSize )
{
printf( "====reading %d bytes\n", (int)maxSize );
size_t toRead = maxSize < left ? maxSize : left;
memcpy( out, &data[ data.size() - left ], toRead );
left -= toRead;
if ( !toRead )
return -1;
else
return toRead;
}
void ArticleResourceReply::readyReadSlot()
{
readyRead();
}
void ArticleResourceReply::finishedSlot()
{
finished();
}

81
src/article_netmgr.hh Normal file
View file

@ -0,0 +1,81 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __ARTICLE_NETMGR_HH_INCLUDED__
#define __ARTICLE_NETMGR_HH_INCLUDED__
#include <QtNetwork>
#include "dictionary.hh"
#include "article_maker.hh"
using std::vector;
/// A custom QNetworkAccessManager version which fetches images from the
/// dictionaries when requested.
class ArticleNetworkAccessManager: public QNetworkAccessManager
{
vector< sptr< Dictionary::Class > > const & dictionaries;
ArticleMaker const & articleMaker;
public:
ArticleNetworkAccessManager( QObject * parent,
vector< sptr< Dictionary::Class > > const &
dictionaries_,
ArticleMaker const & articleMaker_ ):
QNetworkAccessManager( parent ), dictionaries( dictionaries_ ),
articleMaker( articleMaker_ )
{}
/// Tries reading a resource referenced by a "bres://" url. If it succeeds,
/// the vector is filled with data, and true is returned. If it doesn't
/// succeed, it returns false. The function can optionally set the Content-Type
/// header correspondingly.
bool getResource( QUrl const & url, vector< char > & data,
QString & contentType );
protected:
virtual QNetworkReply * createRequest( Operation op,
QNetworkRequest const & req,
QIODevice * outgoingData );
};
class ArticleResourceReply: public QNetworkReply
{
Q_OBJECT
vector< char > data;
size_t left;
public:
ArticleResourceReply( QObject * parent,
QNetworkRequest const &,
vector< char > const & data,
QString const & contentType );
protected:
virtual qint64 bytesAvailable() const;
virtual void abort()
{}
virtual qint64 readData( char * data, qint64 maxSize );
// We use the hackery below to work around the fact that we need to emit
// ready/finish signals after we've been constructed.
signals:
void readyReadSignal();
void finishedSignal();
private slots:
void readyReadSlot();
void finishedSlot();
};
#endif

216
src/articleview.cc Normal file
View file

@ -0,0 +1,216 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "articleview.hh"
#include "externalviewer.hh"
#include <QMessageBox>
#include <QWebHitTestResult>
#include <QMenu>
ArticleView::ArticleView( QWidget * parent, ArticleNetworkAccessManager & nm,
Instances::Groups const & groups_, bool popupView_ ):
QFrame( parent ),
articleNetMgr( nm ),
groups( groups_ ),
popupView( popupView_ )
{
ui.setupUi( this );
ui.definition->setContextMenuPolicy( Qt::CustomContextMenu );
ui.definition->page()->setLinkDelegationPolicy( QWebPage::DelegateAllLinks );
ui.definition->page()->setNetworkAccessManager( &articleNetMgr );
connect( ui.definition, SIGNAL( titleChanged( QString const & ) ),
this, SLOT( handleTitleChanged( QString const & ) ) );
connect( ui.definition, SIGNAL( urlChanged( QUrl const & ) ),
this, SLOT( handleUrlChanged( QUrl const & ) ) );
connect( ui.definition, SIGNAL( customContextMenuRequested( QPoint const & ) ),
this, SLOT( contextMenuRequested( QPoint const & ) ) );
connect( ui.definition, SIGNAL( linkClicked( QUrl const & ) ),
this, SLOT( linkClicked( QUrl const & ) ) );
}
void ArticleView::showDefinition( QString const & word, QString const & group )
{
QUrl req;
req.setScheme( "gdlookup" );
req.setHost( "localhost" );
req.addQueryItem( "word", word );
req.addQueryItem( "group", group );
ui.definition->load( req );
}
void ArticleView::handleTitleChanged( QString const & title )
{
emit titleChanged( this, title );
}
void ArticleView::handleUrlChanged( QUrl const & url )
{
QIcon icon;
QString group = getGroup( url );
if ( group.size() )
{
// Find the group's instance corresponding to the fragment value
for( unsigned x = 0; x < groups.size(); ++x )
if ( groups[ x ].name == group )
{
// Found it
if ( groups[ x ].icon.size() )
icon = QIcon( ":/flags/" + groups[ x ].icon );
else
break;
}
}
emit iconChanged( this, icon );
}
QString ArticleView::getGroup( QUrl const & url )
{
if ( url.scheme() == "gdlookup" && url.hasQueryItem( "group" ) )
return url.queryItemValue( "group" );
return QString();
}
void ArticleView::linkClicked( QUrl const & url )
{
printf( "clicked %s\n", url.toString().toLocal8Bit().data() );
if ( url.scheme() == "bword" )
showDefinition( url.host().startsWith( "xn--" ) ?
QUrl::fromPunycode( url.host().toLatin1() ) :
url.host(),
getGroup( ui.definition->url() ) );
else
if ( url.scheme() == "gdlookup" ) // Plain html links inherit gdlookup scheme
showDefinition( url.path().mid( 1 ),
getGroup( ui.definition->url() ) );
else
if ( url.scheme() == "bres" || url.scheme() == "gdau" )
{
vector< char > data;
// Download it
QString contentType;
if ( !articleNetMgr.getResource( url, data, contentType ) )
{
QMessageBox::critical( this, tr( "GoldenDict" ), tr( "The referenced resource doesn't exist." ) );
return;
}
// Decide the viewer
QString program, extension;
if ( url.scheme() == "gdau" )
{
program = "mplayer";
extension = "wav";
}
else
if ( url.path().endsWith( ".pdf", Qt::CaseInsensitive ) )
{
program = "evince";
extension = "pdf";
}
else
if ( url.path().endsWith( ".rtf", Qt::CaseInsensitive ) )
{
program = "oowriter";
extension = "rtf";
}
else
{
QMessageBox::critical( this, tr( "GoldenDict" ), tr( "Don't know how to handle the specified resource." ) );
return;
}
try
{
ExternalViewer * viewer = new ExternalViewer( this, data, extension, program );
try
{
viewer->start();
// Once started, it will erase itself
}
catch( ... )
{
delete viewer;
throw;
}
}
catch( ExternalViewer::Ex & e )
{
printf( "%s\n", e.what() );
}
}
}
void ArticleView::contextMenuRequested( QPoint const & pos )
{
// Is that a link? Is there a selection?
QWebHitTestResult r = ui.definition->page()->currentFrame()->
hitTestContent( pos );
QMenu menu( this );
QAction * followLink = 0;
QAction * lookupSelection = 0;
if ( !r.linkUrl().isEmpty() )
{
followLink = new QAction( tr( "Open the link" ), &menu );
menu.addAction( followLink );
}
QString selectedText = ui.definition->selectedText();
if ( selectedText.size() )
{
lookupSelection = new QAction( tr( "Look up \"%1\"" ).arg( ui.definition->selectedText() ), &menu );
menu.addAction( lookupSelection );
}
if ( !menu.isEmpty() )
{
QAction * result = menu.exec( ui.definition->mapToGlobal( pos ) );
if ( result == followLink )
linkClicked( r.linkUrl() );
else
if ( result == lookupSelection )
showDefinition( selectedText, getGroup( ui.definition->url() ) );
}
#if 0
printf( "%s\n", r.linkUrl().isEmpty() ? "null" : "not null" );
printf( "url = %s\n", r.linkUrl().toString().toLocal8Bit().data() );
printf( "title = %s\n", r.title().toLocal8Bit().data() );
#endif
}
void ArticleView::showEvent( QShowEvent * ev )
{
QFrame::showEvent( ev );
ui.searchFrame->hide();
}

70
src/articleview.hh Normal file
View file

@ -0,0 +1,70 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __ARTICLEVIEW_HH_INCLUDED__
#define __ARTICLEVIEW_HH_INCLUDED__
#include <QWebView>
#include <QUrl>
#include "article_netmgr.hh"
#include "instances.hh"
#include "ui_articleview.h"
/// A widget with the web view tailored to view and handle articles -- it
/// uses the appropriate netmgr, handles link clicks, rmb clicks etc
class ArticleView: public QFrame
{
Q_OBJECT
ArticleNetworkAccessManager & articleNetMgr;
Instances::Groups const & groups;
bool popupView;
Ui::ArticleView ui;
public:
/// The popupView flag influences contents of the context menus to be
/// appropriate to the context of the view.
/// The groups aren't copied -- rather than that, the reference is kept
ArticleView( QWidget * parent,
ArticleNetworkAccessManager &,
Instances::Groups const &,
bool popupView );
/// Shows the definition of the given word with the given group
void showDefinition( QString const & word, QString const & group );
/// Goes back in history
void back()
{ ui.definition->back(); }
/// Goes forward in history
void forward()
{ ui.definition->forward(); }
signals:
void iconChanged( ArticleView *, QIcon const & icon );
void titleChanged( ArticleView *, QString const & title );
private slots:
void handleTitleChanged( QString const & title );
void handleUrlChanged( QUrl const & url );
void linkClicked( QUrl const & );
void contextMenuRequested( QPoint const & );
private:
/// Deduces group from the url. If there doesn't seem to be any group,
/// returns empty string.
QString getGroup( QUrl const & );
protected:
// We need this to hide the search bar when we're showed
void showEvent( QShowEvent * );
};
#endif

163
src/articleview.ui Normal file
View file

@ -0,0 +1,163 @@
<ui version="4.0" >
<class>ArticleView</class>
<widget class="QWidget" name="ArticleView" >
<property name="geometry" >
<rect>
<x>0</x>
<y>0</y>
<width>833</width>
<height>634</height>
</rect>
</property>
<property name="windowTitle" >
<string>Form</string>
</property>
<layout class="QVBoxLayout" name="verticalLayout_2" >
<property name="margin" >
<number>0</number>
</property>
<item>
<widget class="QFrame" name="frame" >
<property name="frameShape" >
<enum>QFrame::StyledPanel</enum>
</property>
<property name="frameShadow" >
<enum>QFrame::Raised</enum>
</property>
<layout class="QVBoxLayout" name="verticalLayout" >
<property name="margin" >
<number>0</number>
</property>
<item>
<widget class="QWebView" name="definition" >
<property name="palette" >
<palette>
<active>
<colorrole role="Base" >
<brush brushstyle="SolidPattern" >
<color alpha="255" >
<red>254</red>
<green>253</green>
<blue>235</blue>
</color>
</brush>
</colorrole>
<colorrole role="Window" >
<brush brushstyle="SolidPattern" >
<color alpha="255" >
<red>255</red>
<green>255</green>
<blue>255</blue>
</color>
</brush>
</colorrole>
</active>
<inactive>
<colorrole role="Base" >
<brush brushstyle="SolidPattern" >
<color alpha="255" >
<red>254</red>
<green>253</green>
<blue>235</blue>
</color>
</brush>
</colorrole>
<colorrole role="Window" >
<brush brushstyle="SolidPattern" >
<color alpha="255" >
<red>255</red>
<green>255</green>
<blue>255</blue>
</color>
</brush>
</colorrole>
</inactive>
<disabled>
<colorrole role="Base" >
<brush brushstyle="SolidPattern" >
<color alpha="255" >
<red>255</red>
<green>255</green>
<blue>255</blue>
</color>
</brush>
</colorrole>
<colorrole role="Window" >
<brush brushstyle="SolidPattern" >
<color alpha="255" >
<red>255</red>
<green>255</green>
<blue>255</blue>
</color>
</brush>
</colorrole>
</disabled>
</palette>
</property>
<property name="url" >
<url>
<string>about:blank</string>
</url>
</property>
</widget>
</item>
</layout>
</widget>
</item>
<item>
<widget class="QFrame" name="searchFrame" >
<property name="frameShape" >
<enum>QFrame::NoFrame</enum>
</property>
<property name="frameShadow" >
<enum>QFrame::Raised</enum>
</property>
<layout class="QHBoxLayout" name="horizontalLayout" >
<property name="margin" >
<number>0</number>
</property>
<item>
<widget class="QToolButton" name="searchCloseButton" >
<property name="text" >
<string>x</string>
</property>
</widget>
</item>
<item>
<widget class="QLabel" name="label" >
<property name="text" >
<string>Find:</string>
</property>
</widget>
</item>
<item>
<widget class="QLineEdit" name="searchText" />
</item>
<item>
<spacer name="horizontalSpacer" >
<property name="orientation" >
<enum>Qt::Horizontal</enum>
</property>
<property name="sizeHint" stdset="0" >
<size>
<width>40</width>
<height>20</height>
</size>
</property>
</spacer>
</item>
</layout>
</widget>
</item>
</layout>
</widget>
<customwidgets>
<customwidget>
<class>QWebView</class>
<extends>QWidget</extends>
<header>QtWebKit/QWebView</header>
</customwidget>
</customwidgets>
<resources/>
<connections/>
</ui>

758
src/bgl.cc Normal file
View file

@ -0,0 +1,758 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "bgl.hh"
#include "btreeidx.hh"
#include "bgl_babylon.hh"
#include "file.hh"
#include "folding.hh"
#include "utf8.hh"
#include "chunkedstorage.hh"
#include <map>
#include <set>
#include <list>
#include <zlib.h>
#include <ctype.h>
namespace Bgl {
using std::map;
using std::multimap;
using std::set;
using std::wstring;
using std::list;
using std::pair;
using BtreeIndexing::WordArticleLink;
using BtreeIndexing::IndexedWords;
namespace
{
enum
{
Signature = 0x584c4742, // BGLX on little-endian, XLGB on big-endian
CurrentFormatVersion = 12 + BtreeIndexing::FormatVersion
};
struct IdxHeader
{
uint32_t signature; // First comes the signature, BGLX
uint32_t formatVersion; // File format version, currently 1.
uint32_t parserVersion; // Version of the parser used to parse the BGL file.
// If it's lower than the current one, the file is to
// be re-parsed.
uint32_t foldingVersion; // Version of the folding algorithm used when building
// index. If it's different from the current one,
// the file is to be rebuilt.
uint32_t articleCount; // Total number of articles, for informative purposes only
uint32_t wordCount; // Total number of words, for informative purposes only
/// Add more fields here, like name, description, author and such.
uint32_t chunksOffset; // The offset to chunks' storage
uint32_t indexOffset; // The offset of the index in the file.
uint32_t resourceListOffset; // The offset of the list of resources
uint32_t resourcesCount; // Number of resources stored
} __attribute__((packed));
bool indexIsOldOrBad( string const & indexFile )
{
File::Class idx( indexFile, "rb" );
IdxHeader header;
return idx.readRecords( &header, sizeof( header ), 1 ) != 1 ||
header.signature != Signature ||
header.formatVersion != CurrentFormatVersion ||
header.parserVersion != Babylon::ParserVersion ||
header.foldingVersion != Folding::Version;
}
// Removes the $1$-like postfix
string removePostfix( string const & in )
{
if ( in.size() && in[ in.size() - 1 ] == '$' )
{
// Find the end of it and cut it, barring any unexpectedness
for( long x = in.size() - 2; x >= 0; x-- )
{
if ( in[ x ] == '$' )
return in.substr( 0, x );
else
if ( !isdigit( in[ x ] ) )
break;
}
}
return in;
}
// Removes any leading or trailing whitespace
void trimWs( string & word )
{
if ( word.size() )
{
unsigned begin = 0;
while( begin < word.size() && isspace( word[ begin ] ) )
++begin;
if ( begin == word.size() ) // Consists of ws entirely?
word.clear();
else
{
unsigned end = word.size();
// Doesn't consist of ws entirely, so must end with just isspace()
// condition.
while( isspace( word[ end - 1 ] ) )
--end;
if ( end != word.size() || begin )
word = string( word, begin, end - begin );
}
}
}
void addEntryToIndex( string & word,
uint32_t articleOffset,
IndexedWords & indexedWords,
vector< wchar_t > & wcharBuffer )
{
// Strip any leading or trailing whitespaces
trimWs( word );
// Check the input word for a superscript postfix ($1$, $2$ etc), which
// signifies different meaning in Bgl files. We emit different meaning
// as different articles, but they appear in the index as the same word.
if ( word.size() && word[ word.size() - 1 ] == '$' )
{
word = removePostfix( word );
trimWs( word );
}
// Convert the word from utf8 to wide chars
if ( wcharBuffer.size() <= word.size() )
wcharBuffer.resize( word.size() + 1 );
long result = Utf8::decode( word.c_str(), word.size(),
&wcharBuffer.front() );
if ( result < 0 )
{
fprintf( stderr, "Failed to decode utf8 of headword %s, skipping it.\n",
word.c_str() );
return;
}
wcharBuffer[ result ] = 0;
// Now make its folded version
wstring folded = Folding::apply( &wcharBuffer.front() );
/// Try to conserve the memory usage of the string
folded.reserve( folded.size() );
// Insert new entry into an index
IndexedWords::iterator i = indexedWords.insert(
IndexedWords::value_type( folded, vector< WordArticleLink >() ) ).first;
// Try to conserve memory somewhat -- slow insertions are ok
i->second.reserve( i->second.size() + 1 );
i->second.push_back( WordArticleLink( word, articleOffset ) );
}
DEF_EX( exFailedToDecompressArticle, "Failed to decompress article's body", Dictionary::Ex )
DEF_EX( exChunkIndexOutOfRange, "Chunk index is out of range", Dictionary::Ex )
class BglDictionary: public BtreeIndexing::BtreeDictionary
{
File::Class idx;
IdxHeader idxHeader;
string dictionaryName;
ChunkedStorage::Reader chunks;
public:
BglDictionary( string const & id, string const & indexFile,
string const & dictionaryFile );
virtual string getName() throw()
{ return dictionaryName; }
virtual map< Dictionary::Property, string > getProperties() throw()
{ return map< Dictionary::Property, string >(); }
virtual unsigned long getArticleCount() throw()
{ return idxHeader.articleCount; }
virtual unsigned long getWordCount() throw()
{ return idxHeader.wordCount; }
virtual vector< wstring > findHeadwordsForSynonym( wstring const & )
throw( std::exception );
virtual string getArticle( wstring const &, vector< wstring > const & alts )
throw( Dictionary::exNoSuchWord, std::exception );
virtual void getResource( string const & name,
vector< char > & data ) throw( Dictionary::exNoSuchResource,
std::exception );
private:
/// Loads an article with the given offset, filling the given strings.
void loadArticle( uint32_t offset, string & headword,
string & displayedHeadword, string & articleText );
void replaceCharsetEntities( string & );
};
BglDictionary::BglDictionary( string const & id, string const & indexFile,
string const & dictionaryFile ):
BtreeDictionary( id, vector< string >( 1, dictionaryFile ) ),
idx( indexFile, "rb" ),
idxHeader( idx.read< IdxHeader >() ),
chunks( idx, idxHeader.chunksOffset )
{
idx.seek( sizeof( idxHeader ) );
// Read the dictionary's name
size_t len = idx.read< uint32_t >();
vector< char > nameBuf( len );
idx.read( &nameBuf.front(), len );
dictionaryName = string( &nameBuf.front(), len );
// Initialize the index
idx.seek( idxHeader.indexOffset );
openIndex( idx );
}
void BglDictionary::loadArticle( uint32_t offset, string & headword,
string & displayedHeadword,
string & articleText )
{
vector< char > chunk;
char * articleData = chunks.getBlock( offset, chunk );
headword = articleData;
displayedHeadword = articleData + headword.size() + 1;
articleText =
string( articleData + headword.size() +
displayedHeadword.size() + 2 );
}
vector< wstring > BglDictionary::findHeadwordsForSynonym( wstring const & str )
throw( std::exception )
{
vector< wstring > result;
vector< WordArticleLink > chain = findArticles( str );
wstring caseFolded = Folding::applySimpleCaseOnly( str );
for( unsigned x = 0; x < chain.size(); ++x )
{
string headword, displayedHeadword, articleText;
loadArticle( chain[ x ].articleOffset,
headword, displayedHeadword, articleText );
wstring headwordDecoded = Utf8::decode( removePostfix( headword ) );
if ( caseFolded != Folding::applySimpleCaseOnly( headwordDecoded ) )
{
// The headword seems to differ from the input word, which makes the
// input word its synonym.
result.push_back( headwordDecoded );
}
}
return result;
}
// Converts a $1$-like postfix to a <sup>1</sup> one
string postfixToSuperscript( string const & in )
{
if ( !in.size() || in[ in.size() - 1 ] != '$' )
return in;
for( long x = in.size() - 2; x >= 0; x-- )
{
if ( in[ x ] == '$' )
{
if ( in.size() - x - 2 > 2 )
{
// Large postfixes seem like something we wouldn't want to show --
// some dictionaries seem to have each word numbered using the
// postfix.
return in.substr( 0, x );
}
else
return in.substr( 0, x ) + "<sup>" + in.substr( x + 1, in.size() - x - 2 ) + "</sup>";
}
else
if ( !isdigit( in[ x ] ) )
break;
}
return in;
}
string BglDictionary::getArticle( wstring const & word,
vector< wstring > const & alts )
throw( Dictionary::exNoSuchWord, std::exception )
{
vector< WordArticleLink > chain = findArticles( word );
for( unsigned x = 0; x < alts.size(); ++x )
{
/// Make an additional query for each alt
vector< WordArticleLink > altChain = findArticles( alts[ x ] );
chain.insert( chain.end(), altChain.begin(), altChain.end() );
}
multimap< wstring, pair< string, string > > mainArticles, alternateArticles;
set< uint32_t > articlesIncluded; // Some synonims make it that the articles
// appear several times. We combat this
// by only allowing them to appear once.
wstring wordCaseFolded = Folding::applySimpleCaseOnly( word );
for( unsigned x = 0; x < chain.size(); ++x )
{
if ( articlesIncluded.find( chain[ x ].articleOffset ) != articlesIncluded.end() )
continue; // We already have this article in the body.
// Now grab that article
string headword, displayedHeadword, articleText;
loadArticle( chain[ x ].articleOffset,
headword, displayedHeadword, articleText );
// Ok. Now, does it go to main articles, or to alternate ones? We list
// main ones first, and alternates after.
// We do the case-folded and postfix-less comparison here.
wstring headwordStripped =
Folding::applySimpleCaseOnly( Utf8::decode( removePostfix( headword ) ) );
multimap< wstring, pair< string, string > > & mapToUse =
( wordCaseFolded == headwordStripped ) ?
mainArticles : alternateArticles;
mapToUse.insert( pair< wstring, pair< string, string > >(
Folding::applySimpleCaseOnly( Utf8::decode( headword ) ),
pair< string, string >(
displayedHeadword.size() ? displayedHeadword : headword,
articleText ) ) );
articlesIncluded.insert( chain[ x ].articleOffset );
}
if ( mainArticles.empty() && alternateArticles.empty() )
throw Dictionary::exNoSuchWord();
string result;
multimap< wstring, pair< string, string > >::const_iterator i;
string cleaner = "</font>""</font>""</font>""</font>""</font>""</font>"
"</font>""</font>""</font>""</font>""</font>""</font>"
"</b></b></b></b></b></b></b></b>"
"</i></i></i></i></i></i></i></i>";
for( i = mainArticles.begin(); i != mainArticles.end(); ++i )
{
result += "<h3>";
result += postfixToSuperscript( i->second.first );
result += "</h3>";
result += i->second.second;
result += cleaner;
}
for( i = alternateArticles.begin(); i != alternateArticles.end(); ++i )
{
result += "<h3>";
result += postfixToSuperscript( i->second.first );
result += "</h3>";
result += i->second.second;
result += cleaner;
}
// Do some cleanups in the text
replaceCharsetEntities( result );
return result;
}
void BglDictionary::getResource( string const & name,
vector< char > & data )
throw( Dictionary::exNoSuchResource, std::exception )
{
string nameLowercased = name;
for( string::iterator i = nameLowercased.begin(); i != nameLowercased.end();
++i )
*i = tolower( *i );
idx.seek( idxHeader.resourceListOffset );
for( size_t count = idxHeader.resourcesCount; count--; )
{
vector< char > nameData( idx.read< uint32_t >() );
idx.read( &nameData.front(), nameData.size() );
for( size_t x = nameData.size(); x--; )
nameData[ x ] = tolower( nameData[ x ] );
uint32_t offset = idx.read< uint32_t >();
if ( string( &nameData.front(), nameData.size() ) == nameLowercased )
{
// We have a match.
idx.seek( offset );
data.resize( idx.read< uint32_t >() );
vector< unsigned char > compressedData( idx.read< uint32_t >() );
idx.read( &compressedData.front(), compressedData.size() );
unsigned long decompressedLength = data.size();
if ( uncompress( (unsigned char *)&data.front(),
&decompressedLength,
&compressedData.front(),
compressedData.size() ) != Z_OK ||
decompressedLength != data.size() )
{
printf( "Failed to decompress resource %s, ignoring it.\n",
name.c_str() );
throw Dictionary::exNoSuchResource();
}
return;
}
}
throw Dictionary::exNoSuchResource();
}
/// Replaces <CHARSET c="t">1234;</CHARSET> occurences with &#x1234;
void BglDictionary::replaceCharsetEntities( string & text )
{
string lowercased = text;
// Make a lowercased version of text, used for searching only. Only touch
// symbols < 0x80 to avoid any weird results.
for( unsigned x = lowercased.size(); x--; )
if ( (unsigned char )lowercased[ x ] < 0x80 )
lowercased[ x ] = tolower( lowercased[ x ] );
size_t prevPos = 0;
for( ;; )
{
size_t pos = lowercased.find( "<charset c=\"t\">", prevPos );
if ( pos == string::npos )
break;
if ( lowercased.size() - pos < 30 )
{
// This is not right, the string is too short, leave it alone
break;
}
prevPos = pos + 1;
if ( lowercased.substr( pos + 15 + 4, 11 ) != ";</charset>" )
{
// The ending doesn't match
printf( "!!!!!!ending mismatch\n" );
continue;
}
// Check if digits are all hex
if ( !isxdigit( lowercased[ pos + 15 ] ) ||
!isxdigit( lowercased[ pos + 16 ] ) ||
!isxdigit( lowercased[ pos + 17 ] ) ||
!isxdigit( lowercased[ pos + 18 ] ) )
{
printf( "!!!!!!!!not hex digits\n" );
continue;
}
// Ok, replace now.
lowercased.replace( pos, 15, "&#x" );
lowercased.erase( pos + 8, 10 );
text.replace( pos, 15, "&#x" );
text.erase( pos + 8, 10 );
}
prevPos = 0;
// Copy-pasted version for <charset c=t>. This should all be replaced
// by regexps.
for( ;; )
{
size_t pos = lowercased.find( "<charset c=t>", prevPos );
if ( pos == string::npos )
break;
if ( lowercased.size() - pos < 28 )
{
// This is not right, the string is too short, leave it alone
break;
}
prevPos = pos + 1;
if ( lowercased.substr( pos + 13 + 4, 11 ) != ";</charset>" )
{
// The ending doesn't match
printf( "!!!!!!ending mismatch\n" );
continue;
}
// Check if digits are all hex
if ( !isxdigit( lowercased[ pos + 13 ] ) ||
!isxdigit( lowercased[ pos + 14 ] ) ||
!isxdigit( lowercased[ pos + 15 ] ) ||
!isxdigit( lowercased[ pos + 16 ] ) )
{
printf( "!!!!!!!!not hex digits\n" );
continue;
}
// Ok, replace now.
lowercased.replace( pos, 13, "&#x" );
lowercased.erase( pos + 8, 10 );
text.replace( pos, 13, "&#x" );
text.erase( pos + 8, 10 );
}
}
class ResourceHandler: public Babylon::ResourceHandler
{
File::Class & idxFile;
list< pair< string, uint32_t > > resources;
public:
ResourceHandler( File::Class & idxFile_ ): idxFile( idxFile_ )
{}
list< pair< string, uint32_t > > const & getResources() const
{ return resources; }
protected:
virtual void handleBabylonResource( string const & filename,
char const * data, size_t size );
};
void ResourceHandler::handleBabylonResource( string const & filename,
char const * data, size_t size )
{
//printf( "Handling resource file %s (%u bytes)\n", filename.c_str(), size );
vector< unsigned char > compressedData( compressBound( size ) );
unsigned long compressedSize = compressedData.size();
if ( compress( &compressedData.front(), &compressedSize,
(unsigned char const *) data, size ) != Z_OK )
{
fprintf( stderr, "Failed to compress the body of resource %s, dropping it.\n",
filename.c_str() );
return;
}
resources.push_back( pair< string, uint32_t >( filename, idxFile.tell() ) );
idxFile.write< uint32_t >( size );
idxFile.write< uint32_t >( compressedSize );
idxFile.write( &compressedData.front(), compressedSize );
}
}
vector< sptr< Dictionary::Class > > Format::makeDictionaries(
vector< string > const & fileNames,
string const & indicesDir,
Dictionary::Initializing & initializing )
throw( std::exception )
{
vector< sptr< Dictionary::Class > > dictionaries;
for( vector< string >::const_iterator i = fileNames.begin(); i != fileNames.end();
++i )
{
// Skip files with the extensions different to .bgl to speed up the
// scanning
if ( i->size() < 4 ||
strcasecmp( i->c_str() + ( i->size() - 4 ), ".bgl" ) != 0 )
continue;
Babylon b( *i );
if ( !b.open() )
continue;
// Got the file -- check if we need to rebuid the index
vector< string > dictFiles( 1, *i );
string dictId = makeDictionaryId( dictFiles );
string indexFile = indicesDir + dictId;
if ( needToRebuildIndex( dictFiles, indexFile ) || indexIsOldOrBad( indexFile ) )
{
// Building the index
std::string sourceCharset, targetCharset;
if ( !b.read( sourceCharset, targetCharset ) )
{
fprintf( stderr, "Failed to start reading from %s, skipping it\n", i->c_str() );
continue;
}
initializing.indexingDictionary( b.title() );
File::Class idx( indexFile, "wb" );
IdxHeader idxHeader;
memset( &idxHeader, 0, sizeof( idxHeader ) );
// We write a dummy header first. At the end of the process the header
// will be rewritten with the right values.
idx.write( idxHeader );
idx.write< uint32_t >( b.title().size() );
idx.write( b.title().data(), b.title().size() );
// This is our index data that we accumulate during the loading process.
// For each new word encountered, we emit the article's body to the file
// immediately, inserting the word itself and its offset in this map.
// This map maps folded words to the original words and the corresponding
// articles' offsets.
IndexedWords indexedWords;
// We use this buffer to decode utf8 into it.
vector< wchar_t > wcharBuffer;
ChunkedStorage::Writer chunks( idx );
uint32_t articleCount = 0, wordCount = 0;
ResourceHandler resourceHandler( idx );
b.setResourcePrefix( string( "bres://" ) + dictId + "/" );
for( ; ; )
{
bgl_entry e = b.readEntry( &resourceHandler );
if ( e.headword.empty() )
break;
// Save the article's body itself first
uint32_t articleAddress = chunks.startNewBlock();
chunks.addToBlock( e.headword.c_str(), e.headword.size() + 1 );
chunks.addToBlock( e.displayedHeadword.c_str(), e.displayedHeadword.size() + 1 );
chunks.addToBlock( e.definition.c_str(), e.definition.size() + 1 );
// Add entries to the index
addEntryToIndex( e.headword, articleAddress, indexedWords, wcharBuffer );
for( unsigned x = 0; x < e.alternates.size(); ++x )
addEntryToIndex( e.alternates[ x ], articleAddress, indexedWords, wcharBuffer );
wordCount += 1 + e.alternates.size();
++articleCount;
}
// Finish with the chunks
idxHeader.chunksOffset = chunks.finish();
printf( "Writing index...\n" );
// Good. Now build the index
idxHeader.indexOffset = BtreeIndexing::buildIndex( indexedWords, idx );
// Save the resource's list.
idxHeader.resourceListOffset = idx.tell();
idxHeader.resourcesCount = resourceHandler.getResources().size();
for( list< pair< string, uint32_t > >::const_iterator i =
resourceHandler.getResources().begin();
i != resourceHandler.getResources().end(); ++i )
{
idx.write< uint32_t >( i->first.size() );
idx.write( i->first.data(), i->first.size() );
idx.write< uint32_t >( i->second );
}
// That concludes it. Update the header.
idxHeader.signature = Signature;
idxHeader.formatVersion = CurrentFormatVersion;
idxHeader.parserVersion = Babylon::ParserVersion;
idxHeader.foldingVersion = Folding::Version;
idxHeader.articleCount = articleCount;
idxHeader.wordCount = wordCount;
idx.rewind();
idx.write( &idxHeader, sizeof( idxHeader ) );
}
dictionaries.push_back( new BglDictionary( dictId,
indexFile,
*i ) );
}
return dictionaries;
}
}

28
src/bgl.hh Normal file
View file

@ -0,0 +1,28 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __BGL_HH_INCLUDED__
#define __BGL_HH_INCLUDED__
#include "dictionary.hh"
/// Support for the Babylon's .bgl dictionaries.
namespace Bgl {
using std::vector;
using std::string;
class Format: public Dictionary::Format
{
public:
virtual vector< sptr< Dictionary::Class > > makeDictionaries(
vector< string > const & fileNames,
string const & indicesDir,
Dictionary::Initializing & )
throw( std::exception );
};
}
#endif

547
src/bgl_babylon.cc Normal file
View file

@ -0,0 +1,547 @@
/***************************************************************************
* Copyright (C) 2007 by Raul Fernandes and Karl Grill *
* rgbr@yahoo.com.br *
* *
* 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. *
***************************************************************************/
/* Various improvements were made by Konstantin Isakov for the GoldenDict
* program. */
#include "bgl_babylon.hh"
#include<stdlib.h>
#include<stdio.h>
#include <iconv.h>
#ifdef _WIN32
#include <io.h>
#define DUP _dup
#else
#define DUP dup
#endif
Babylon::Babylon( std::string filename )
{
m_filename = filename;
file = NULL;
}
Babylon::~Babylon()
{
close();
}
bool Babylon::open()
{
FILE *f;
unsigned char buf[6];
int i;
f = fopen( m_filename.c_str(), "rb" );
if( f == NULL )
return false;
i = fread( buf, 1, 6, f );
/* First four bytes: BGL signature 0x12340001 or 0x12340002 (big-endian) */
if( i < 6 || memcmp( buf, "\x12\x34\x00", 3 ) || buf[3] == 0 || buf[3] > 2 )
{
fclose( f );
return false;
}
/* Calculate position of gz header */
i = buf[4] << 8 | buf[5];
if( i < 6 )
{
fclose( f );
return false;
}
if( fseek( f, i, SEEK_SET ) ) /* can't seek - emulate */
for(int j=0;j < i - 6;j++) fgetc( f );
if( ferror( f ) || feof( f ) )
{
fclose( f );
return false;
}
/* we need to flush the file because otherwise some nfs mounts don't seem
* to properly update the file position for the following reopen */
fflush( f );
file = gzdopen( DUP( fileno( f ) ), "r" );
fclose( f );
if( file == NULL )
return false;
return true;
}
void Babylon::close()
{
if ( file )
{
gzclose( file );
file = 0;
}
}
bool Babylon::readBlock( bgl_block &block )
{
if( gzeof( file ) || file == NULL )
return false;
block.length = bgl_readnum( 1 );
block.type = block.length & 0xf;
if( block.type == 4 ) return false; // end of file marker
block.length >>= 4;
block.length = block.length < 4 ? bgl_readnum( block.length + 1 ) : block.length - 4 ;
if( block.length )
{
block.data = (char *)malloc( block.length );
gzread( file, block.data, block.length );
}
return true;
}
unsigned int Babylon::bgl_readnum( int bytes )
{
unsigned char buf[4];
unsigned val = 0;
if ( bytes < 1 || bytes > 4 ) return (0);
gzread( file, buf, bytes );
for(int i=0;i<bytes;i++) val= (val << 8) | buf[i];
return val;
}
bool Babylon::read(std::string &source_charset, std::string &target_charset)
{
if( file == NULL ) return false;
bgl_block block;
unsigned int pos;
unsigned int type;
std::string headword;
std::string definition;
m_sourceCharset = source_charset;
m_targetCharset = target_charset;
m_numEntries = 0;
while( readBlock( block ) )
{
headword.clear();
definition.clear();
switch( block.type )
{
case 0:
switch( block.data[0] )
{
case 8:
type = (unsigned int)block.data[2];
if( type > 64 ) type -= 65;
if ( type >= 14 )
type = 0;
m_defaultCharset = bgl_charset[type];
break;
default:
break;
}
break;
case 1:
case 10:
// Only count entries
m_numEntries++;
break;
case 3:
pos = 2;
switch( block.data[1] )
{
case 1:
headword.reserve( block.length - 2 );
for(unsigned int a=0;a<block.length-2;a++) headword += block.data[pos++];
m_title = headword;
break;
case 2:
headword.reserve( block.length - 2 );
for(unsigned int a=0;a<block.length-2;a++) headword += block.data[pos++];
m_author = headword;
break;
case 3:
headword.reserve( block.length - 2 );
for(unsigned int a=0;a<block.length-2;a++) headword += block.data[pos++];
m_email = headword;
break;
case 4:
headword.reserve( block.length - 2 );
for(unsigned int a=0;a<block.length-2;a++) headword += block.data[pos++];
m_copyright = headword;
break;
case 7:
headword = bgl_language[(unsigned char)(block.data[5])];
m_sourceLang = headword;
break;
case 8:
headword = bgl_language[(unsigned char)(block.data[5])];
m_targetLang = headword;
break;
case 9:
headword.reserve( block.length - 2 );
for(unsigned int a=0;a<block.length-2;a++) {
if (block.data[pos] == '\r') {
} else if (block.data[pos] == '\n') {
headword += "<br>";
} else {
headword += block.data[pos];
}
pos++;
}
m_description = headword;
break;
case 26:
type = (unsigned int)block.data[2];
if( type > 64 ) type -= 65;
if ( type >= 14 )
type = 0;
if (m_sourceCharset.empty())
m_sourceCharset = bgl_charset[type];
break;
case 27:
type = (unsigned int)block.data[2];
if( type > 64 ) type -= 65;
if ( type >= 14 )
type = 0;
if (m_targetCharset.empty())
m_targetCharset = bgl_charset[type];
break;
default:
break;
}
break;
default:
;
}
if( block.length ) free( block.data );
}
gzseek( file, 0, SEEK_SET );
convertToUtf8( m_title, TARGET_CHARSET );
convertToUtf8( m_author, TARGET_CHARSET );
convertToUtf8( m_email, TARGET_CHARSET );
convertToUtf8( m_copyright, TARGET_CHARSET );
convertToUtf8( m_description, TARGET_CHARSET );
printf("Default charset: %s\nSource Charset: %s\nTargetCharset: %s\n", m_defaultCharset.c_str(), m_sourceCharset.c_str(), m_targetCharset.c_str());
return true;
}
bgl_entry Babylon::readEntry( ResourceHandler * resourceHandler )
{
bgl_entry entry;
if( file == NULL )
{
entry.headword = "";
return entry;
}
bgl_block block;
unsigned int len, pos;
std::string headword, displayedHeadword;
std::string definition;
std::string temp;
std::vector<std::string> alternates;
std::string alternate;
while( readBlock( block ) )
{
switch( block.type )
{
case 2:
{
pos = 0;
len = (unsigned char)block.data[pos++];
std::string filename( block.data+pos, len );
//if (filename != "8EAF66FD.bmp" && filename != "C2EEF3F6.html") {
pos += len;
if ( resourceHandler )
resourceHandler->handleBabylonResource( filename,
block.data + pos,
block.length - pos );
#if 0
FILE *ifile = fopen(filename.c_str(), "w");
fwrite(block.data + pos, 1, block.length -pos, ifile);
fclose(ifile);
#endif
break;
}
case 1:
case 10:
alternate.clear();
headword.clear();
displayedHeadword.clear();
definition.clear();
temp.clear();
pos = 0;
// Headword
len = 0;
len = (unsigned char)block.data[pos++];
headword.reserve( len );
for(unsigned int a=0;a<len;a++)
headword += block.data[pos++];
convertToUtf8( headword, SOURCE_CHARSET );
// Definition
len = 0;
len = (unsigned char)block.data[pos++] << 8;
len |= (unsigned char)block.data[pos++];
definition.reserve( len );
for(unsigned int a=0;a<len;a++)
{
if( (unsigned char)block.data[pos] == 0x0a )
{
definition += "<br>";
pos++;
}
else if ( (unsigned char)block.data[pos] == 6 )
{
// Something
pos += 2;
++a;
}
else if ( (unsigned char)block.data[pos] >= 0x40 &&
len - a >= 2 &&
(unsigned char)block.data[pos + 1 ] == 0x18 )
{
// Hidden displayed headword (a displayed headword which
// contains some garbage and shouldn't probably be visible).
unsigned length = (unsigned char)block.data[ pos ] - 0x3F;
if ( length > len - a - 2 )
{
fprintf( stderr, "Hidden displayed headword is too large %s\n", headword.c_str() );
pos += len - a;
break;
}
pos += length + 2;
a += length + 1;
}
else if ( (unsigned char)block.data[pos] == 0x18 )
{
// Displayed headword
unsigned length = (unsigned char)block.data[ pos + 1 ];
if ( length > len - a - 2 )
{
fprintf( stderr, "Displayed headword's length is too large for headword %s\n", headword.c_str() );
pos += len - a;
break;
}
displayedHeadword = std::string( block.data + pos + 2, length );
pos += length + 2;
a += length + 1;
}
else if ( (unsigned char)block.data[pos] == 0x50 && len - a - 1 >= 2 &&
(unsigned char)block.data[pos + 1 ] == 0x1B )
{
// 1-byte-sized transcription
unsigned length = (unsigned char)block.data[pos + 2 ];
if ( length > len - a - 3 )
{
fprintf( stderr, "1-byte-sized transcription's length is too large for headword %s\n", headword.c_str() );
pos += len - a;
break;
}
std::string transcription( block.data + pos + 3, length );
definition = std::string( "<span class=\"bgltrn\">" ) + transcription + "</span>" + definition;
pos += length + 3;
a += length + 2;
}
else if ( (unsigned char)block.data[pos] == 0x60 && len - a - 1 >= 3 &&
(unsigned char)block.data[pos + 1 ] == 0x1B )
{
// 2-byte-sized transcription
unsigned length = (unsigned char)block.data[pos + 2 ];
length <<= 8;
length += (unsigned char)block.data[pos + 3 ];
if ( length > len - a - 4)
{
fprintf( stderr, "2-byte-sized transcription's length is too large for headword %s\n", headword.c_str() );
pos += len - a;
break;
}
std::string transcription( block.data + pos + 4, length );
definition = std::string( "<span class=\"bgltrn\">" ) + transcription + "</span>" + definition;
pos += length + 4;
a += length + 3;
}
else if ( (unsigned char)block.data[pos] == 0x1E )
{
// Resource reference begin marker
definition += m_resourcePrefix;
++pos;
}
else if ( (unsigned char)block.data[pos] == 0x1F )
{
// Resource reference end marker
++pos;
}
else if( (unsigned char)block.data[pos] < 0x20 )
{
if( a <= len - 3 && block.data[pos] == 0x14 && block.data[pos+1] == 0x02 ) {
int index = (unsigned char)block.data[pos+2] - 0x30;
if (index >= 0 && index <= 10) {
definition = "<span class=\"bglpos\">" + partOfSpeech[index] + "</span> " + definition;
}
pos += 3;
a += 2;
//pos += len - a;
//break;
} else if (block.data[pos] == 0x14) {
pos++;
} else {
definition += block.data[pos++];
}
}else definition += block.data[pos++];
}
convertToUtf8( definition, TARGET_CHARSET );
if ( displayedHeadword.size() )
convertToUtf8( displayedHeadword, TARGET_CHARSET );
// Alternate forms
while( pos != block.length )
{
len = (unsigned char)block.data[pos++];
alternate.reserve( len );
for(unsigned int a=0;a<len;a++) alternate += block.data[pos++];
convertToUtf8( alternate, SOURCE_CHARSET );
alternates.push_back( alternate );
alternate.clear();
}
entry.headword = headword;
entry.displayedHeadword = displayedHeadword;
entry.definition = definition;
entry.alternates = alternates;
if( block.length ) free( block.data );
return entry;
break;
default:
;
}
if( block.length ) free( block.data );
}
entry.headword = "";
return entry;
}
void Babylon::convertToUtf8( std::string &s, unsigned int type )
{
if( s.size() < 1 ) return;
if( type > 2 ) return;
std::string charset;
switch( type )
{
case DEFAULT_CHARSET:
if(!m_defaultCharset.empty()) charset = m_defaultCharset;
else charset = m_sourceCharset;
break;
case SOURCE_CHARSET:
if(!m_sourceCharset.empty()) charset = m_sourceCharset;
else charset = m_defaultCharset;
break;
case TARGET_CHARSET:
if(!m_targetCharset.empty()) charset = m_targetCharset;
else charset = m_defaultCharset;
break;
default:
;
}
iconv_t cd = iconv_open( "UTF-8", charset.c_str() );
if( cd == (iconv_t)(-1) )
{
printf( "Error openning iconv library\n" );
exit(1);
}
char *outbuf, *defbuf;
size_t inbufbytes, outbufbytes;
inbufbytes = s.size();
outbufbytes = s.size() * 6;
#ifdef _WIN32
const char *inbuf;
inbuf = s.data();
#else
char *inbuf;
inbuf = (char *)s.data();
#endif
outbuf = (char*)malloc( outbufbytes + 1 );
memset( outbuf, '\0', outbufbytes + 1 );
defbuf = outbuf;
while (inbufbytes) {
if (iconv(cd, &inbuf, &inbufbytes, &outbuf, &outbufbytes) == (size_t)-1) {
printf( "\n%s\n", inbuf );
printf( "Error in iconv conversion\n" );
inbuf++;
inbufbytes--;
}
}
s = std::string( defbuf );
free( defbuf );
iconv_close( cd );
}

220
src/bgl_babylon.hh Normal file
View file

@ -0,0 +1,220 @@
/***************************************************************************
* Copyright (C) 2007 by Raul Fernandes and Karl Grill *
* rgbr@yahoo.com.br *
* *
* 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. *
***************************************************************************/
#ifndef BABYLON_H
#define BABYLON_H
#include <stdlib.h>
#include <zlib.h>
#include <string>
#include <vector>
const std::string bgl_language[] = {
"English",
"French",
"Italian",
"Spanish",
"Dutch",
"Portuguese",
"German",
"Russian",
"Japanese",
"Traditional Chinese",
"Simplified Chinese",
"Greek",
"Korean",
"Turkish",
"Hebrew",
"Arabic",
"Thai",
"Other",
"Other Simplified Chinese dialects",
"Other Traditional Chinese dialects",
"Other Eastern-European languages",
"Other Western-European languages",
"Other Russian languages",
"Other Japanese languages",
"Other Baltic languages",
"Other Greek languages",
"Other Korean dialects",
"Other Turkish dialects",
"Other Thai dialects",
"Polish",
"Hungarian",
"Czech",
"Lithuanian",
"Latvian",
"Catalan",
"Croatian",
"Serbian",
"Slovak",
"Albanian",
"Urdu",
"Slovenian",
"Estonian",
"Bulgarian",
"Danish",
"Finnish",
"Icelandic",
"Norwegian",
"Romanian",
"Swedish",
"Ukrainian",
"Belarusian",
"Farsi",
"Basque",
"Macedonian",
"Afrikaans",
"Faeroese",
"Latin",
"Esperanto",
"Tamazight",
"Armenian"};
const std::string bgl_charsetname[] = {
"Default" ,
"Latin",
"Eastern European",
"Cyrillic",
"Japanese",
"Traditional Chinese",
"Simplified Chinese",
"Baltic",
"Greek",
"Korean",
"Turkish",
"Hebrew",
"Arabic",
"Thai" };
const std::string bgl_charset[] = {
"ISO-8859-1", /*Default*/
"ISO-8859-1", /*Latin*/
"ISO-8859-2", /*Eastern European*/
"WINDOWS-1251", /*Cyriilic*/
"SJIS-WIN", /*Japanese*/
"BIG5", /*Traditional Chinese*/
"GB18030", /*Simplified Chinese*/
"CP1257", /*Baltic*/
"CP1253", /*Greek*/
"EUC-KR", /*Korean*/
"ISO-8859-9", /*Turkish*/
"WINDOWS-1255", /*Hebrew*/
"CP1256", /*Arabic*/
"CP874" /*Thai*/ };
const std::string partOfSpeech[] = {
"n.",
"adj.",
"v.",
"adv.",
"interj.",
"pron.",
"prep.",
"conj.",
"suff.",
"pref.",
"art." };
typedef struct {
unsigned type;
unsigned length;
char * data;
} bgl_block;
typedef struct {
std::string headword;
std::string definition;
std::string displayedHeadword;
std::vector<std::string> alternates;
} bgl_entry;
class Babylon
{
public:
Babylon( std::string );
~Babylon();
// Subclass this to store resources
class ResourceHandler
{
public:
virtual void handleBabylonResource( std::string const & filename,
char const * data, size_t size )=0;
virtual ~ResourceHandler()
{}
};
/// Sets a prefix string to append to each resource reference in hyperlinks.
void setResourcePrefix( std::string const & prefix )
{ m_resourcePrefix = prefix; }
bool open();
void close();
bool readBlock( bgl_block& );
bool read(std::string &source_charset, std::string &target_charset);
bgl_entry readEntry( ResourceHandler * = 0 );
inline std::string title() const { return m_title; };
inline std::string author() const { return m_author; };
inline std::string email() const { return m_email; };
inline std::string description() const { return m_description; };
inline std::string copyright() const { return m_copyright; };
inline std::string sourceLang() const { return m_sourceLang; };
inline std::string targetLang() const { return m_targetLang; };
inline unsigned int numEntries() const { return m_numEntries; };
inline std::string charset() const { return m_defaultCharset; };
inline std::string filename() const { return m_filename; };
enum
{
ParserVersion = 2
};
private:
unsigned int bgl_readnum( int );
void convertToUtf8( std::string &, unsigned int = 0 );
std::string m_filename;
gzFile file;
std::string m_title;
std::string m_author;
std::string m_email;
std::string m_description;
std::string m_copyright;
std::string m_sourceLang;
std::string m_targetLang;
unsigned int m_numEntries;
std::string m_defaultCharset;
std::string m_sourceCharset;
std::string m_targetCharset;
std::string m_resourcePrefix;
enum CHARSET { DEFAULT_CHARSET, SOURCE_CHARSET, TARGET_CHARSET };
};
#endif // BABYLON_H

643
src/btreeidx.cc Normal file
View file

@ -0,0 +1,643 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "btreeidx.hh"
#include "folding.hh"
#include "utf8.hh"
#include <math.h>
//#define __BTREE_USE_LZO
// LZO mode is experimental and unsupported. Tests didn't show any substantial
// speed improvements.
#ifdef __BTREE_USE_LZO
#include <lzo/lzo1x.h>
namespace {
struct __LzoInit
{
__LzoInit()
{
lzo_init();
}
} __lzoInit;
}
#else
#include <zlib.h>
#endif
namespace BtreeIndexing {
enum
{
BtreeMinElements = 64,
BtreeMaxElements = 2048
};
BtreeDictionary::BtreeDictionary( string const & id,
vector< string > const & dictionaryFiles ):
Dictionary::Class( id, dictionaryFiles ), idxFile( 0 )
{
}
void BtreeDictionary::openIndex( File::Class & file )
{
indexNodeSize = file.read< uint32_t >();
rootOffset = file.read< uint32_t >();
idxFile = &file;
}
vector< WordArticleLink > BtreeDictionary::findArticles( wstring const & str )
{
vector< WordArticleLink > result;
wstring folded = Folding::apply( str );
bool exactMatch;
vector< char > leaf;
uint32_t nextLeaf;
char const * chainOffset = findChainOffsetExactOrPrefix( folded, exactMatch,
leaf, nextLeaf );
if ( chainOffset && exactMatch )
{
result = readChain( chainOffset );
antialias( str, result );
}
return result;
}
void BtreeDictionary::findExact( wstring const & str,
vector< wstring > & exactMatches,
vector< wstring > & prefixMatches,
unsigned long maxPrefixResults )
throw( std::exception )
{
exactMatches.clear();
prefixMatches.clear();
wstring folded = Folding::apply( str );
bool exactMatch;
vector< char > leaf;
uint32_t nextLeaf;
char const * chainOffset = findChainOffsetExactOrPrefix( folded, exactMatch,
leaf, nextLeaf );
if ( !chainOffset )
return;
for( ; ; )
{
//printf( "offset = %u, size = %u\n", chainOffset - &leaf.front(), leaf.size() );
vector< WordArticleLink > chain = readChain( chainOffset );
vector< wstring > wstrings = convertChainToWstrings( chain );
wstring resultFolded = Folding::apply( wstrings[ 0 ] );
if ( resultFolded == folded )
// Exact match
exactMatches.insert( exactMatches.end(), wstrings.begin(), wstrings.end() );
else
if ( resultFolded.size() > folded.size() && !resultFolded.compare( 0, folded.size(), folded ) )
{
// Prefix match
prefixMatches.insert( prefixMatches.end(), wstrings.begin(), wstrings.end() );
if ( prefixMatches.size() >= maxPrefixResults )
{
// For now we actually allow more than maxPrefixResults if the last
// chain yield more than one result. That's ok and maybe even more
// desirable.
break;
}
}
else
// No match at all, end this
break;
// Fetch new leaf if we're out of chains here
if ( chainOffset > &leaf.back() )
{
// We're past the current leaf, fetch the next one
//printf( "advancing\n" );
if ( nextLeaf )
{
readNode( nextLeaf, leaf );
nextLeaf = idxFile->read< uint32_t >();
chainOffset = &leaf.front() + sizeof( uint32_t );
uint32_t leafEntries = *(uint32_t *)&leaf.front();
if ( leafEntries == 0xffffFFFF )
{
//printf( "bah!\n" );
exit( 1 );
}
}
else
break; // That was the last leaf
}
}
}
void BtreeDictionary::readNode( uint32_t offset, vector< char > & out )
{
idxFile->seek( offset );
uint32_t uncompressedSize = idxFile->read< uint32_t >();
uint32_t compressedSize = idxFile->read< uint32_t >();
//printf( "%x,%x\n", uncompressedSize, compressedSize );
out.resize( uncompressedSize );
vector< unsigned char > compressedData( compressedSize );
idxFile->read( &compressedData.front(), compressedData.size() );
#ifdef __BTREE_USE_LZO
lzo_uint decompressedLength = out.size();
if ( lzo1x_decompress( &compressedData.front(), compressedData.size(),
(unsigned char *)&out.front(), &decompressedLength, 0 )
!= LZO_E_OK || decompressedLength != out.size() )
throw exFailedToDecompressNode();
#else
unsigned long decompressedLength = out.size();
if ( uncompress( (unsigned char *)&out.front(),
&decompressedLength,
&compressedData.front(),
compressedData.size() ) != Z_OK ||
decompressedLength != out.size() )
throw exFailedToDecompressNode();
#endif
}
char const * BtreeDictionary::findChainOffsetExactOrPrefix( wstring const & target,
bool & exactMatch,
vector< char > & leaf,
uint32_t & nextLeaf )
{
if ( !idxFile )
throw exIndexWasNotOpened();
// Lookup the index by traversing the index btree
vector< char > charBuffer;
vector< wchar_t > wcharBuffer;
vector< char > wordsBuffer;
exactMatch = false;
// Read a node
uint32_t currentNodeOffset = rootOffset;
for( ; ; )
{
//printf( "reading node at %x\n", currentNodeOffset );
readNode( currentNodeOffset, leaf );
// Is it a leaf or a node?
uint32_t leafEntries = *(uint32_t *)&leaf.front();
if ( leafEntries == 0xffffFFFF )
{
// A node
//printf( "=>a node\n" );
uint32_t const * offsets = (uint32_t *)&leaf.front() + 1;
char const * ptr = &leaf.front() + sizeof( uint32_t ) +
( indexNodeSize + 1 ) * sizeof( uint32_t );
unsigned entry;
for( entry = 0; entry < indexNodeSize; ++entry )
{
//printf( "checking node agaist word %s\n", ptr );
size_t wordSize = strlen( ptr );
if ( wcharBuffer.size() <= wordSize )
wcharBuffer.resize( wordSize + 1 );
long result = Utf8::decode( ptr, wordSize, &wcharBuffer.front() );
if ( result < 0 )
throw Utf8::exCantDecode( ptr );
wcharBuffer[ result ] = 0;
int compareResult = target.compare( &wcharBuffer.front() );
if ( !compareResult )
{
// The target string matches the current one.
// Go to the right, since it's there where we store such results.
currentNodeOffset = offsets[ entry + 1 ];
break;
}
if ( compareResult < 0 )
{
// The target string is smaller than the current one.
// Go to the left.
currentNodeOffset = offsets[ entry ];
break;
}
ptr += wordSize + 1;
}
if ( entry == indexNodeSize )
{
// We iterated through all entries, but our string is larger than
// all of them. Go the the rightmost node.
currentNodeOffset = offsets[ entry ];
}
}
else
{
//printf( "=>a leaf\n" );
// A leaf
nextLeaf = idxFile->read< uint32_t >();
// Iterate through chains until we find one that matches
char const * ptr = &leaf.front() + sizeof( uint32_t );
uint32_t chainSize;
while( leafEntries-- )
{
memcpy( &chainSize, ptr, sizeof( uint32_t ) );
ptr += sizeof( uint32_t );
if( chainSize )
{
size_t wordSize = strlen( ptr );
if ( wcharBuffer.size() <= wordSize )
wcharBuffer.resize( wordSize + 1 );
//printf( "checking agaist word %s, left = %u\n", ptr, leafEntries );
long result = Utf8::decode( ptr, wordSize, &wcharBuffer.front() );
if ( result < 0 )
throw Utf8::exCantDecode( ptr );
wcharBuffer[ result ] = 0;
wstring foldedWord = Folding::apply( &wcharBuffer.front() );
int compareResult = target.compare( foldedWord );
if ( !compareResult )
{
// Exact match -- return and be done
exactMatch = true;
return ptr - sizeof( uint32_t );
}
else
if ( compareResult < 0 )
{
// The target string is smaller than the current one.
// No point in travering further, return this result.
return ptr - sizeof( uint32_t );
}
ptr += chainSize;
}
}
// Well, our target is larger than all the chains here. This would mean
// that the next leaf is the right one.
if ( nextLeaf )
{
readNode( nextLeaf, leaf );
nextLeaf = idxFile->read< uint32_t >();
return &leaf.front() + sizeof( uint32_t );
}
else
return 0; // This was the last leaf
}
}
}
vector< WordArticleLink > BtreeDictionary::readChain( char const * & ptr )
{
uint32_t chainSize;
memcpy( &chainSize, ptr, sizeof( uint32_t ) );
ptr += sizeof( uint32_t );
vector< WordArticleLink > result;
vector< char > charBuffer;
while( chainSize )
{
string str = ptr;
ptr += str.size() + 1;
uint32_t articleOffset;
memcpy( &articleOffset, ptr, sizeof( uint32_t ) );
ptr += sizeof( uint32_t );
result.push_back( WordArticleLink( str, articleOffset ) );
if ( chainSize < str.size() + 1 + sizeof( uint32_t ) )
throw exCorruptedChainData();
else
chainSize -= str.size() + 1 + sizeof( uint32_t );
}
return result;
}
vector< wstring > BtreeDictionary::convertChainToWstrings(
vector< WordArticleLink > const & chain )
{
vector< wchar_t > wcharBuffer;
vector< wstring > result;
for( unsigned x = 0; x < chain.size(); ++x )
{
unsigned wordSize = chain[ x ].word.size();
if ( wcharBuffer.size() <= wordSize )
wcharBuffer.resize( wordSize + 1 );
long len = Utf8::decode( chain[ x ].word.data(), wordSize,
&wcharBuffer.front() );
if ( len < 0 )
{
fprintf( stderr, "Failed to decode utf8 of a word %s, skipping it.\n",
chain[ x ].word.c_str() );
continue;
}
wcharBuffer[ len ] = 0;
result.push_back( &wcharBuffer.front() );
}
return result;
}
void BtreeDictionary::antialias( wstring const & str,
vector< WordArticleLink > & chain )
{
wstring caseFolded = Folding::applySimpleCaseOnly( str );
for( unsigned x = chain.size(); x--; )
{
// If after applying case folding to each word they wouldn't match, we
// drop the entry.
if ( Folding::applySimpleCaseOnly( Utf8::decode( chain[ x ].word ) ) !=
caseFolded )
chain.erase( chain.begin() + x );
}
}
/// A function which recursively creates btree node.
/// The nextIndex iterator is being iterated over and increased when building
/// leaf nodes.
static uint32_t buildBtreeNode( IndexedWords::const_iterator & nextIndex,
size_t indexSize,
File::Class & file, size_t maxElements,
uint32_t & lastLeafLinkOffset )
{
// We compress all the node data. This buffer would hold it.
vector< unsigned char > uncompressedData;
bool isLeaf = indexSize <= maxElements;
if ( isLeaf )
{
// A leaf.
uint32_t totalChainsLength = 0;
IndexedWords::const_iterator nextWord = nextIndex;
for( unsigned x = indexSize; x--; ++nextWord )
{
totalChainsLength += sizeof( uint32_t );
vector< WordArticleLink > const & chain = nextWord->second;
for( unsigned y = 0; y < chain.size(); ++y )
totalChainsLength += chain[ y ].word.size() + 1 + sizeof( uint32_t );
}
uncompressedData.resize( sizeof( uint32_t ) + totalChainsLength );
// First uint32_t indicates that this is a leaf.
*(uint32_t *)&uncompressedData.front() = indexSize;
unsigned char * ptr = &uncompressedData.front() + sizeof( uint32_t );
for( unsigned x = indexSize; x--; ++nextIndex )
{
vector< WordArticleLink > const & chain = nextIndex->second;
unsigned char * saveSizeHere = ptr;
ptr += sizeof( uint32_t );
uint32_t size = 0;
for( unsigned y = 0; y < chain.size(); ++y )
{
memcpy( ptr, chain[ y ].word.c_str(), chain[ y ].word.size() + 1 );
ptr += chain[ y ].word.size() + 1;
memcpy( ptr, &(chain[ y ].articleOffset), sizeof( uint32_t ) );
ptr += sizeof( uint32_t );
size += chain[ y ].word.size() + 1 + sizeof( uint32_t );
}
memcpy( saveSizeHere, &size, sizeof( uint32_t ) );
}
}
else
{
// A node which will have children.
uncompressedData.resize( sizeof( uint32_t ) + ( maxElements + 1 ) * sizeof( uint32_t ) );
// First uint32_t indicates that this is a node.
*(uint32_t *)&uncompressedData.front() = 0xffffFFFF;
unsigned prevEntry = 0;
vector< char > charBuffer;
for( unsigned x = 0; x < maxElements; ++x )
{
unsigned curEntry = (uint64_t) indexSize * ( x + 1 ) / ( maxElements + 1 );
uint32_t offset = buildBtreeNode( nextIndex,
curEntry - prevEntry,
file, maxElements,
lastLeafLinkOffset );
memcpy( &uncompressedData.front() + sizeof( uint32_t ) + x * sizeof( uint32_t ), &offset, sizeof( uint32_t ) );
if ( charBuffer.size() < nextIndex->first.size() * 4 )
charBuffer.resize( nextIndex->first.size() * 4 );
size_t sz = Utf8::encode( nextIndex->first.data(), nextIndex->first.size(),
&charBuffer.front() );
size_t prevSize = uncompressedData.size();
uncompressedData.resize( prevSize + sz + 1 );
memcpy( &uncompressedData.front() + prevSize, &charBuffer.front(), sz );
uncompressedData.back() = 0;
prevEntry = curEntry;
}
// Rightmost child
uint32_t offset = buildBtreeNode( nextIndex,
indexSize - prevEntry,
file, maxElements,
lastLeafLinkOffset );
memcpy( &uncompressedData.front() + sizeof( uint32_t ) +
maxElements * sizeof( uint32_t ), &offset, sizeof( offset ) );
}
// Save the result.
#ifdef __BTREE_USE_LZO
vector< unsigned char > compressedData( uncompressedData.size() + uncompressedData.size() / 16 + 64 + 3 );
char workMem[ LZO1X_1_MEM_COMPRESS ];
lzo_uint compressedSize;
if ( lzo1x_1_compress( &uncompressedData.front(), uncompressedData.size(),
&compressedData.front(), &compressedSize, workMem )
!= LZO_E_OK )
{
fprintf( stderr, "Failed to compress btree node.\n" );
abort();
}
#else
vector< unsigned char > compressedData( compressBound( uncompressedData.size() ) );
unsigned long compressedSize = compressedData.size();
if ( compress( &compressedData.front(), &compressedSize,
&uncompressedData.front(), uncompressedData.size() ) != Z_OK )
{
fprintf( stderr, "Failed to compress btree node.\n" );
abort();
}
#endif
uint32_t offset = file.tell();
file.write< uint32_t >( uncompressedData.size() );
file.write< uint32_t >( compressedSize );
file.write( &compressedData.front(), compressedSize );
if ( isLeaf )
{
// A link to the next leef, which is zero and which will be updated
// should we happen to have another leaf.
file.write( ( uint32_t ) 0 );
uint32_t here = file.tell();
if ( lastLeafLinkOffset )
{
// Update the previous leaf to have the offset of this one.
file.seek( lastLeafLinkOffset );
file.write( offset );
file.seek( here );
}
// Make sure next leaf knows where to write its offset for us.
lastLeafLinkOffset = here - sizeof( uint32_t );
}
return offset;
}
uint32_t buildIndex( IndexedWords const & indexedWords, File::Class & file )
{
// We try to stick to two-level tree for most dictionaries. Try finding
// the right size for it.
size_t btreeMaxElements = ( (size_t) sqrt( indexedWords.size() ) ) + 1;
if ( btreeMaxElements < BtreeMinElements )
btreeMaxElements = BtreeMinElements;
else
if ( btreeMaxElements > BtreeMaxElements )
btreeMaxElements = BtreeMaxElements;
printf( "Building a tree of %u elements\n", btreeMaxElements );
IndexedWords::const_iterator nextIndex = indexedWords.begin();
uint32_t lastLeafOffset = 0;
uint32_t rootOffset = buildBtreeNode( nextIndex, indexedWords.size(),
file, btreeMaxElements,
lastLeafOffset );
// We need to save btreeMaxElements. For simplicity, we just save it here
// along with root offset, and then return that record's offset as the
// offset of the index itself.
uint32_t indexOffset = file.tell();
file.write( btreeMaxElements );
file.write( rootOffset );
return indexOffset;
}
}

128
src/btreeidx.hh Normal file
View file

@ -0,0 +1,128 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __BTREEIDX_HH_INCLUDED__
#define __BTREEIDX_HH_INCLUDED__
#include "dictionary.hh"
#include "file.hh"
#include <string>
#include <vector>
#include <map>
/// A base for the dictionary which creates a btree index to look up
/// the words.
namespace BtreeIndexing {
using std::string;
using std::wstring;
using std::vector;
using std::map;
enum
{
/// This is to be bumped up each time the internal format changes.
/// The value isn't used here by itself, it is supposed to be added
/// to each dictionary's internal format version.
FormatVersion = 1
};
// These exceptions which might be thrown during the index traversal
DEF_EX( exIndexWasNotOpened, "The index wasn't opened", Dictionary::Ex )
DEF_EX( exFailedToDecompressNode, "Failed to decompress a btree's node", Dictionary::Ex )
DEF_EX( exCorruptedChainData, "Corrupted chain data in the leaf of a btree encountered", Dictionary::Ex )
/// This structure describes a word linked to its translation. The
/// translation is represented as an abstract 32-bit offset.
struct WordArticleLink
{
string word; // in utf8
uint32_t articleOffset;
WordArticleLink()
{}
WordArticleLink( string const & word_, uint32_t articleOffset_ ):
word( word_ ), articleOffset( articleOffset_ )
{}
};
/// A base for the dictionary that utilizes a btree index build using
/// buildIndex() function declared below.
class BtreeDictionary: public Dictionary::Class
{
public:
BtreeDictionary( string const & id, vector< string > const & dictionaryFiles );
/// This function does the search using the btree index. Derivatives
/// need not to implement this function.
virtual void findExact( wstring const &,
vector< wstring > &,
vector< wstring > &,
unsigned long ) throw( std::exception );
protected:
/// Opens the index. The file must be positioned at the offset previously
/// returned by buildIndex(). The file reference is saved to be used for
/// subsequent lookups.
void openIndex( File::Class & );
/// Finds articles that match the given string. A case-insensitive search
/// is performed.
vector< WordArticleLink > findArticles( wstring const & );
private:
File::Class * idxFile;
uint32_t indexNodeSize;
uint32_t rootOffset;
/// Finds the offset in the btree leaf for the given word, either matching
/// by an exact match, or by finding the smallest entry that might match
/// by prefix. It can return zero if there isn't even a possible prefx
/// match. The input string must already be folded. The exactMatch is set
/// to true when an exact match is located, and to false otherwise.
/// The located leaf is loaded to 'leaf', and the pointer to the next
/// leaf is saved to 'nextLeaf'.
char const * findChainOffsetExactOrPrefix( wstring const & target,
bool & exactMatch,
vector< char > & leaf,
uint32_t & nextLeaf );
/// Reads a node or leaf at the given offset. Just uncompresses its data
/// to the given vector and does nothing more.
void readNode( uint32_t offset, vector< char > & out );
/// Reads the word-article links' chain at the given offset. The pointer
/// is updated to point to the next chain, if there's any.
vector< WordArticleLink > readChain( char const * & );
/// Converts words in a chain to a vector of wide strings. The article
/// offsets don't get used.
vector< wstring > convertChainToWstrings( vector< WordArticleLink > const & );
/// Drops any alises which arose due to folding. Only case-folded aliases
/// are left.
void antialias( wstring const &, vector< WordArticleLink > & );
};
// Everything below is for building the index data.
/// This represents the index in its source form, as a map which binds folded
/// words to sequences of their unfolded source forms and the corresponding
/// article offsets.
typedef map< wstring, vector< WordArticleLink > > IndexedWords;
/// Builds the index, as a compressed btree. Returns offset to its root.
/// All the data is stored to the given file, beginning from its current
/// position.
uint32_t buildIndex( IndexedWords const &, File::Class & file );
}
#endif

136
src/chunkedstorage.cc Normal file
View file

@ -0,0 +1,136 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "chunkedstorage.hh"
#include <zlib.h>
namespace ChunkedStorage {
enum
{
ChunkMaxSize = 65536 // Can't be more since it would overflow the address
};
Writer::Writer( File::Class & f ):
file( f ), chunkStarted( false ), bufferUsed( 0 )
{
}
uint32_t Writer::startNewBlock()
{
if ( bufferUsed >= ChunkMaxSize )
{
// Need to flush first.
saveCurrentChunk();
}
chunkStarted = true;
// The address is comprised of the offset within the chunk (in lower
// 16 bits, always fits there since ChunkMaxSize-1 does) and the
// number of the chunk, which is therefore limited to be 65535 max.
return bufferUsed | ( (uint32_t)offsets.size() << 16 );
}
void Writer::addToBlock( void const * data, size_t size )
{
if ( !size )
return;
if ( buffer.size() - bufferUsed < size )
buffer.resize( bufferUsed + size );
memcpy( &buffer.front() + bufferUsed, data, size );
bufferUsed += size;
chunkStarted = false;
}
void Writer::saveCurrentChunk()
{
size_t maxCompressedSize = compressBound( bufferUsed );
if ( bufferCompressed.size() < maxCompressedSize )
bufferCompressed.resize( maxCompressedSize );
unsigned long compressedSize = bufferCompressed.size();
if ( compress( &bufferCompressed.front(), &compressedSize,
&buffer.front(), bufferUsed ) != Z_OK )
throw exFailedToCompressChunk();
offsets.push_back( file.tell() );
file.write( (uint32_t) bufferUsed );
file.write( (uint32_t) compressedSize );
file.write( &bufferCompressed.front(), compressedSize );
bufferUsed = 0;
chunkStarted = false;
}
uint32_t Writer::finish()
{
if ( bufferUsed || chunkStarted )
saveCurrentChunk();
uint32_t offset = file.tell();
file.write( (uint32_t) offsets.size() );
file.write( &offsets.front(), offsets.size() * sizeof( uint32_t ) );
offsets.clear();
chunkStarted = false;
return offset;
}
Reader::Reader( File::Class & f, uint32_t offset ): file( f )
{
file.seek( offset );
offsets.resize( file.read< uint32_t >() );
file.read( &offsets.front(), offsets.size() * sizeof( uint32_t ) );
}
char * Reader::getBlock( uint32_t address, vector< char > & chunk )
{
size_t chunkIdx = address >> 16;
if ( chunkIdx >= offsets.size() )
throw exAddressOutOfRange();
// Read and decompress the chunk
{
file.seek( offsets[ chunkIdx ] );
uint32_t uncompressedSize = file.read< uint32_t >();
uint32_t compressedSize = file.read< uint32_t >();
chunk.resize( uncompressedSize );
vector< unsigned char > compressedData( compressedSize );
file.read( &compressedData.front(), compressedData.size() );
unsigned long decompressedLength = chunk.size();
if ( uncompress( (unsigned char *)&chunk.front(),
&decompressedLength,
&compressedData.front(),
compressedData.size() ) != Z_OK ||
decompressedLength != chunk.size() )
throw exFailedToDecompressChunk();
}
size_t offsetInChunk = address & 0xffFF;
if ( offsetInChunk > chunk.size() ) // It can be equal to for 0-sized blocks
throw exAddressOutOfRange();
return &chunk.front() + offsetInChunk;
}
}

87
src/chunkedstorage.hh Normal file
View file

@ -0,0 +1,87 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __CHUNKEDSTORAGE_HH_INCLUDED__
#define __CHUNKEDSTORAGE_HH_INCLUDED__
#include "ex.hh"
#include "file.hh"
#include <vector>
/// A chunked compression storage. We use this for articles' bodies. The idea
/// is to store data in a separately-compressed chunks, much like in dictzip,
/// but without any fancy gzip-compatibility or whatever. Another difference
/// is that any block of data saved is always contained without one chunk,
/// even if its size does exceed its maximum allowed size. This is very
/// handy since we're retrieving the data by the same blocks we used to save
/// it as, that' the only kind of seek we support, really.
namespace ChunkedStorage {
using std::vector;
DEF_EX( Ex, "Chunked storage exception", std::exception )
DEF_EX( exFailedToCompressChunk, "Failed to compress a chunk", Ex )
DEF_EX( exAddressOutOfRange, "The given chunked address is out of range", Ex )
DEF_EX( exFailedToDecompressChunk, "Failed to decompress a chunk", Ex )
/// This class writes data blocks in chunks.
class Writer
{
vector< uint32_t > offsets;
File::Class & file;
public:
Writer( File::Class & );
/// Starts new block. Returns its address.
uint32_t startNewBlock();
/// Add data to the previously started block.
void addToBlock( void const * data, size_t size );
/// Finishes writing chunks and returns the offset to the chunk table which
/// gets written at the moment of finishing.
uint32_t finish();
private:
/// Indicates that an address was allocated, which would mean the writeout
/// of the pending chunk is required even if its size is zero.
bool chunkStarted;
// This buffer accumulates the chunk data until either enough data is
// stored (>=ChunkMaxSize), or there's no more data left to store.
vector< unsigned char > buffer;
// Here we compress the chunk before writing it out to file.
vector< unsigned char > bufferCompressed;
// The amount of data stored in buffer so far. We keep it separate
// from buffer.size() for performance reasons; the latter one only
// grows, but never shrinks.
size_t bufferUsed;
void saveCurrentChunk();
};
/// This class reads data blocks previously written by Writer.
class Reader
{
vector< uint32_t > offsets;
File::Class & file;
public:
/// Creates reader by giving it a file to read from and the offset returned
/// by Writer::finish().
Reader( File::Class &, uint32_t );
/// Reads the block previously written by Writer, identified by its address.
/// Uses the user-provided storage to load the entire chunk, and then to
/// return a pointer to the requested block inside it.
char * getBlock( uint32_t address, vector< char > & );
};
}
#endif

203
src/config.cc Normal file
View file

@ -0,0 +1,203 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "config.hh"
#include <QDir>
#include <QFile>
#include <QtXml>
namespace Config {
namespace
{
QDir getHomeDir()
{
QDir result = QDir::home();
char const * pathInHome =
#ifdef Q_OS_WIN32
"Application Data/GoldenDict"
#else
".goldendict"
#endif
;
result.mkpath( pathInHome );
if ( !result.cd( pathInHome ) )
throw exCantUseHomeDir();
return result;
}
QString getConfigFileName()
{
return getHomeDir().absoluteFilePath( "config" );
}
}
Class load() throw( exError )
{
QString configName = getConfigFileName();
if ( !QFile::exists( configName ) )
{
// Make the default config, save it and return it
Class c;
#ifdef Q_OS_LINUX
if ( QDir( "/usr/share/stardict/dic" ).exists() )
c.paths.push_back( "/usr/share/stardict/dic" );
#endif
save( c );
return c;
}
QFile configFile( configName );
if ( !configFile.open( QFile::ReadOnly ) )
throw exCantReadConfigFile();
QDomDocument dd;
QString errorStr;
int errorLine, errorColumn;
if ( !dd.setContent( &configFile, false, &errorStr, &errorLine, &errorColumn ) )
{
printf( "Error: %s at %d,%d\n", errorStr.toLocal8Bit().constData(), errorLine, errorColumn );
throw exMalformedConfigFile();
}
configFile.close();
QDomNode root = dd.namedItem( "config" );
Class c;
QDomNode paths = root.namedItem( "paths" );
if ( !paths.isNull() )
{
QDomNodeList nl = paths.toElement().elementsByTagName( "path" );
for( unsigned x = 0; x < nl.length(); ++x )
c.paths.push_back( nl.item( x ).toElement().text() );
}
QDomNode groups = root.namedItem( "groups" );
if ( !groups.isNull() )
{
QDomNodeList nl = groups.toElement().elementsByTagName( "group" );
for( unsigned x = 0; x < nl.length(); ++x )
{
QDomElement grp = nl.item( x ).toElement();
Group g;
g.name = grp.attribute( "name" );
g.icon = grp.attribute( "icon" );
QDomNodeList dicts = grp.elementsByTagName( "dictionary" );
for( unsigned y = 0; y < dicts.length(); ++y )
g.dictionaries.push_back( dicts.item( y ).toElement().text() );
c.groups.push_back( g );
}
}
return c;
}
void save( Class const & c ) throw( exError )
{
QFile configFile( getConfigFileName() );
if ( !configFile.open( QFile::WriteOnly ) )
throw exCantWriteConfigFile();
QDomDocument dd;
QDomElement root = dd.createElement( "config" );
dd.appendChild( root );
{
QDomElement paths = dd.createElement( "paths" );
root.appendChild( paths );
for( Paths::const_iterator i = c.paths.begin(); i != c.paths.end(); ++i )
{
QDomElement path = dd.createElement( "path" );
paths.appendChild( path );
QDomText value = dd.createTextNode( *i );
path.appendChild( value );
}
}
{
QDomElement groups = dd.createElement( "groups" );
root.appendChild( groups );
for( Groups::const_iterator i = c.groups.begin(); i != c.groups.end(); ++i )
{
QDomElement group = dd.createElement( "group" );
groups.appendChild( group );
QDomAttr name = dd.createAttribute( "name" );
name.setValue( i->name );
group.setAttributeNode( name );
if ( i->icon.size() )
{
QDomAttr icon = dd.createAttribute( "icon" );
icon.setValue( i->icon );
group.setAttributeNode( icon );
}
for( vector< QString >::const_iterator j = i->dictionaries.begin(); j != i->dictionaries.end(); ++j )
{
QDomElement dictionary = dd.createElement( "dictionary" );
group.appendChild( dictionary );
QDomText value = dd.createTextNode( *j );
dictionary.appendChild( value );
}
}
}
configFile.write( dd.toByteArray() );
}
QString getIndexDir() throw( exError )
{
QDir result = getHomeDir();
result.mkpath( "index" );
if ( !result.cd( "index" ) )
throw exCantUseIndexDir();
return result.path() + QDir::separator();
}
QString getUserCssFileName() throw( exError )
{
return getHomeDir().filePath( "style.css" );
}
}

57
src/config.hh Normal file
View file

@ -0,0 +1,57 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __CONFIG_HH_INCLUDED__
#define __CONFIG_HH_INCLUDED__
#include <vector>
#include <QString>
#include "ex.hh"
/// GoldenDict's configuration
namespace Config {
using std::vector;
/// A list of paths where to search for the dictionaries
typedef vector< QString > Paths;
/// A dictionary group
struct Group
{
QString name, icon;
vector< QString > dictionaries; // consists of dictionary's ids
};
/// All the groups
typedef vector< Group > Groups;
struct Class
{
Paths paths;
Groups groups;
};
DEF_EX( exError, "Error with the program's configuration", std::exception )
DEF_EX( exCantUseHomeDir, "Can't use home directory to store GoldenDict preferences", exError )
DEF_EX( exCantUseIndexDir, "Can't use index directory to store GoldenDict index files", exError )
DEF_EX( exCantReadConfigFile, "Can't read the configuration file", exError )
DEF_EX( exCantWriteConfigFile, "Can't write the configuration file", exError )
DEF_EX( exMalformedConfigFile, "The configuration file is malformed", exError )
/// Loads the configuration, or creates the default one if none is present
Class load() throw( exError );
/// Saves the configuration
void save( Class const & ) throw( exError );
/// Returns the index directory, where the indices are to be stored.
QString getIndexDir() throw( exError );
/// Returns the user .css file name.
QString getUserCssFileName() throw( exError );
}
#endif

61
src/dictgroupwidget.ui Normal file
View file

@ -0,0 +1,61 @@
<ui version="4.0" >
<class>DictGroupWidget</class>
<widget class="QWidget" name="DictGroupWidget" >
<property name="geometry" >
<rect>
<x>0</x>
<y>0</y>
<width>403</width>
<height>333</height>
</rect>
</property>
<property name="windowTitle" >
<string>Form</string>
</property>
<layout class="QVBoxLayout" name="verticalLayout" >
<item>
<widget class="DictListWidget" name="dictionaries" />
</item>
<item>
<layout class="QHBoxLayout" name="horizontalLayout" >
<item>
<widget class="QLabel" name="label" >
<property name="text" >
<string>Group icon:</string>
</property>
</widget>
</item>
<item>
<widget class="QComboBox" name="groupIcon" >
<property name="sizeAdjustPolicy" >
<enum>QComboBox::AdjustToContents</enum>
</property>
</widget>
</item>
<item>
<spacer name="horizontalSpacer" >
<property name="orientation" >
<enum>Qt::Horizontal</enum>
</property>
<property name="sizeHint" stdset="0" >
<size>
<width>40</width>
<height>20</height>
</size>
</property>
</spacer>
</item>
</layout>
</item>
</layout>
</widget>
<customwidgets>
<customwidget>
<class>DictListWidget</class>
<extends>QListWidget</extends>
<header>groups_widgets.hh</header>
</customwidget>
</customwidgets>
<resources/>
<connections/>
</ui>

77
src/dictionary.cc Normal file
View file

@ -0,0 +1,77 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include <vector>
#include <algorithm>
#include <cstdio>
#include "dictionary.hh"
#include "md5.h"
// For needToRebuildIndex(), read below
#include <QFileInfo>
#include <QDateTime>
namespace Dictionary {
Class::Class( string const & id_, vector< string > const & dictionaryFiles_ ):
id( id_ ), dictionaryFiles( dictionaryFiles_ )
{
}
string Format::makeDictionaryId( vector< string > const & dictionaryFiles ) throw()
{
std::vector< string > sortedList( dictionaryFiles );
std::sort( sortedList.begin(), sortedList.end() );
md5_state_t context;
md5_init( &context );
for( std::vector< string >::const_iterator i = sortedList.begin();
i != sortedList.end(); ++i )
md5_append( &context, (unsigned char const *)i->c_str(), i->size() + 1 );
unsigned char digest[ 16 ];
md5_finish( &context, digest );
char result[ sizeof( digest ) * 2 + 1 ];
for( unsigned x = 0; x < sizeof( digest ); ++x )
sprintf( result + x * 2, "%02x", digest[ x ] );
return result;
}
// While this file is not supposed to have any Qt stuff since it's used by
// the dictionary backends, there's no platform-independent way to get hold
// of a timestamp of the file, so we use here Qt anyway. It is supposed to
// be fixed in the future when it's needed.
bool Format::needToRebuildIndex( vector< string > const & dictionaryFiles,
string const & indexFile ) throw()
{
unsigned long lastModified = 0;
for( std::vector< string >::const_iterator i = dictionaryFiles.begin();
i != dictionaryFiles.end(); ++i )
{
QFileInfo fileInfo( QString::fromStdString( *i ) );
if ( !fileInfo.exists() )
return true;
unsigned long ts = fileInfo.lastModified().toTime_t();
if ( ts > lastModified )
lastModified = ts;
}
QFileInfo fileInfo( QString::fromStdString( indexFile ) );
if ( !fileInfo.exists() )
return true;
return fileInfo.lastModified().toTime_t() < lastModified;
}
}

163
src/dictionary.hh Normal file
View file

@ -0,0 +1,163 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __DICTIONARY_HH_INCLUDED__
#define __DICTIONARY_HH_INCLUDED__
#include <vector>
#include <string>
#include <map>
#include "sptr.hh"
#include "ex.hh"
/// Abstract dictionary-related stuff
namespace Dictionary {
using std::vector;
using std::string;
using std::wstring;
using std::map;
enum Property
{
Author,
Copyright,
Description,
Email
};
DEF_EX( Ex, "Dictionary error", std::exception )
DEF_EX( exNoSuchWord, "The given word does not exist", Ex )
DEF_EX( exNoSuchResource, "The given resource does not exist", Ex )
/// A dictionary. Can be used to query words.
class Class
{
string id;
vector< string > dictionaryFiles;
public:
/// Creates a dictionary. The id should be made using
/// Format::makeDictionaryId(), the dictionaryFiles is the file names the
/// dictionary consists of.
Class( string const & id, vector< string > const & dictionaryFiles );
/// Returns the dictionary's id.
string getId() throw()
{ return id; }
/// Returns the list of file names the dictionary consists of.
vector< string > const & getDictionaryFilenames() throw()
{ return dictionaryFiles; }
/// Returns the dictionary's full name, utf8.
virtual string getName() throw()=0;
/// Returns all the available properties, like the author's name, copyright,
/// description etc. All strings are in utf8.
virtual map< Property, string > getProperties() throw()=0;
/// Returns the number of articles in the dictionary.
virtual unsigned long getArticleCount() throw()=0;
/// Returns the number of words in the dictionary. This can be equal to
/// the number of articles, or can be larger if some synonyms are present.
virtual unsigned long getWordCount() throw()=0;
/// Looks up a given word in the dictionary, aiming for exact matches. The
/// result is a list of such matches. If it is possible to also look up words
/// that begin with the given substring without much expense, they should be
/// put into the prefix results (if not, it should be left empty). Not more
/// than maxPrefixResults prefix results should be stored. The whole
/// operation is supposed to be fast and is executed in a GUI thread.
virtual void findExact( wstring const &,
vector< wstring > & exactMatches,
vector< wstring > & prefixMatches,
unsigned long maxPrefixResults ) throw( std::exception )=0;
/// Finds known headwords for the given word, that is, the words for which
/// the given word is a synonym. If a dictionary can't perform this operation,
/// it should leave the default implementation which always returns an empty
/// vector.
virtual vector< wstring > findHeadwordsForSynonym( wstring const & )
throw( std::exception )
{ return vector< wstring >(); }
/// Returns a definition for the given word. The definition should
/// be an html fragment (without html/head/body tags) in an utf8 encoding.
/// The 'alts' vector could contain a list of words the definitions of which
/// should be included in the output as well, being treated as additional
/// synonyms for the main word.
virtual string getArticle( wstring const &, vector< wstring > const & alts )
throw( exNoSuchWord, std::exception )=0;
/// Loads contents of a resource named 'name' into the 'data' vector. This is
/// usually a picture file referenced in the article or something like that.
virtual void getResource( string const & name,
vector< char > & data ) throw( exNoSuchResource,
std::exception )
{ throw exNoSuchResource(); }
virtual ~Class()
{}
};
/// Callbacks to be used when the dictionaries are being initialized.
class Initializing
{
public:
/// Called by the Format instance to notify the caller that the given
/// dictionary is being indexed. Since indexing can take some time, this
/// is useful to show in some kind of a splash screen.
/// The dictionaryName is in utf8.
virtual void indexingDictionary( string const & dictionaryName ) throw()=0;
virtual ~Initializing()
{}
};
/// A dictionary format. This is a factory to create dictionaries' instances.
/// It is fed filenames to check if they are dictionaries, and it creates
/// instances when they are.
class Format
{
public:
/// Should go through the given list of file names, trying each one as a
/// possible dictionary of the supported format. Upon finding one, creates a
/// corresponding dictionary instance. As a result, a list of dictionaries
/// is created.
/// indicesDir indicates a directory where index files can be created, should
/// there be need for them. The index file name must be the same as the
/// dictionary's id, made by makeDictionaryId() from the list of file names.
/// Any exception thrown would terminate the program with an error.
virtual vector< sptr< Class > > makeDictionaries( vector< string > const & fileNames,
string const & indicesDir,
Initializing & )
throw( std::exception )=0;
virtual ~Format()
{}
public://protected:
/// Generates an id based on the set of file names which the dictionary
/// consists of. The resulting id is an alphanumeric hex value made by
/// hashing the file names. This id should be used to identify dictionary
/// and for the index file name, if one is needed.
static string makeDictionaryId( vector< string > const & dictionaryFiles ) throw();
/// Checks if it is needed to regenerate index file based on its timestamp
/// and the timestamps of the dictionary files. If some files are newer than
/// the index file, or the index file doesn't exist, returns true. If some
/// dictionary files don't exist, returns true, too.
static bool needToRebuildIndex( vector< string > const & dictionaryFiles,
string const & indexFile ) throw();
};
}
#endif

679
src/dictzip.c Normal file
View file

@ -0,0 +1,679 @@
/* Made up from data.c and other supplementary files of dictd-1.0.11 for the
* GoldenDict program.
*/
/* data.c --
* Created: Tue Jul 16 12:45:41 1996 by faith@dict.org
* Revised: Sat Mar 30 10:46:06 2002 by faith@dict.org
* Copyright 1996, 1997, 1998, 2000, 2002 Rickard E. Faith (faith@dict.org)
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
* Free Software Foundation; either version 1, 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.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include "dictzip.h"
#include <limits.h>
#include <stdarg.h>
#include <errno.h>
#include <stdlib.h>
#include <string.h>
#define BUFFERSIZE 10240
#define OUT_BUFFER_SIZE 0xffffL
#define IN_BUFFER_SIZE ((unsigned long)((double)(OUT_BUFFER_SIZE - 12) * 0.89))
/* For gzip-compatible header, as defined in RFC 1952 */
/* Magic for GZIP (rfc1952) */
#define GZ_MAGIC1 0x1f /* First magic byte */
#define GZ_MAGIC2 0x8b /* Second magic byte */
/* FLaGs (bitmapped), from rfc1952 */
#define GZ_FTEXT 0x01 /* Set for ASCII text */
#define GZ_FHCRC 0x02 /* Header CRC16 */
#define GZ_FEXTRA 0x04 /* Optional field (random access index) */
#define GZ_FNAME 0x08 /* Original name */
#define GZ_COMMENT 0x10 /* Zero-terminated, human-readable comment */
#define GZ_MAX 2 /* Maximum compression */
#define GZ_FAST 4 /* Fasted compression */
/* These are from rfc1952 */
#define GZ_OS_FAT 0 /* FAT filesystem (MS-DOS, OS/2, NT/Win32) */
#define GZ_OS_AMIGA 1 /* Amiga */
#define GZ_OS_VMS 2 /* VMS (or OpenVMS) */
#define GZ_OS_UNIX 3 /* Unix */
#define GZ_OS_VMCMS 4 /* VM/CMS */
#define GZ_OS_ATARI 5 /* Atari TOS */
#define GZ_OS_HPFS 6 /* HPFS filesystem (OS/2, NT) */
#define GZ_OS_MAC 7 /* Macintosh */
#define GZ_OS_Z 8 /* Z-System */
#define GZ_OS_CPM 9 /* CP/M */
#define GZ_OS_TOPS20 10 /* TOPS-20 */
#define GZ_OS_NTFS 11 /* NTFS filesystem (NT) */
#define GZ_OS_QDOS 12 /* QDOS */
#define GZ_OS_ACORN 13 /* Acorn RISCOS */
#define GZ_OS_UNKNOWN 255 /* unknown */
#define GZ_RND_S1 'R' /* First magic for random access format */
#define GZ_RND_S2 'A' /* Second magic for random access format */
#define GZ_ID1 0 /* GZ_MAGIC1 */
#define GZ_ID2 1 /* GZ_MAGIC2 */
#define GZ_CM 2 /* Compression Method (Z_DEFALTED) */
#define GZ_FLG 3 /* FLaGs (see above) */
#define GZ_MTIME 4 /* Modification TIME */
#define GZ_XFL 8 /* eXtra FLags (GZ_MAX or GZ_FAST) */
#define GZ_OS 9 /* Operating System */
#define GZ_XLEN 10 /* eXtra LENgth (16bit) */
#define GZ_FEXTRA_START 12 /* Start of extra fields */
#define GZ_SI1 12 /* Subfield ID1 */
#define GZ_SI2 13 /* Subfield ID2 */
#define GZ_SUBLEN 14 /* Subfield length (16bit) */
#define GZ_VERSION 16 /* Version for subfield format */
#define GZ_CHUNKLEN 18 /* Chunk length (16bit) */
#define GZ_CHUNKCNT 20 /* Number of chunks (16bit) */
#define GZ_RNDDATA 22 /* Random access data (16bit) */
#define DBG_VERBOSE (0<<30|1<< 0) /* Verbose */
#define DBG_ZIP (0<<30|1<< 1) /* Zip */
#define DBG_UNZIP (0<<30|1<< 2) /* Unzip */
#define DBG_SEARCH (0<<30|1<< 3) /* Search */
#define DBG_SCAN (0<<30|1<< 4) /* Config file scan */
#define DBG_PARSE (0<<30|1<< 5) /* Config file parse */
#define DBG_INIT (0<<30|1<< 6) /* Database initialization */
#define DBG_PORT (0<<30|1<< 7) /* Log port number for connections */
#define DBG_LEV (0<<30|1<< 8) /* Levenshtein matching */
#define DBG_AUTH (0<<30|1<< 9) /* Debug authentication */
#define DBG_NODETACH (0<<30|1<<10) /* Don't detach as a background proc. */
#define DBG_NOFORK (0<<30|1<<11) /* Don't fork (single threaded) */
#define DBG_ALT (0<<30|1<<12) /* altcompare() */
#define LOG_SERVER (0<<30|1<< 0) /* Log server diagnostics */
#define LOG_CONNECT (0<<30|1<< 1) /* Log connection information */
#define LOG_STATS (0<<30|1<< 2) /* Log termination information */
#define LOG_COMMAND (0<<30|1<< 3) /* Log commands */
#define LOG_FOUND (0<<30|1<< 4) /* Log words found */
#define LOG_NOTFOUND (0<<30|1<< 5) /* Log words not found */
#define LOG_CLIENT (0<<30|1<< 6) /* Log client */
#define LOG_HOST (0<<30|1<< 7) /* Log remote host name */
#define LOG_TIMESTAMP (0<<30|1<< 8) /* Log with timestamps */
#define LOG_MIN (0<<30|1<< 9) /* Log a few minimal things */
#define LOG_AUTH (0<<30|1<<10) /* Log authentication denials */
#define DICT_LOG_TERM 0
#define DICT_LOG_DEFINE 1
#define DICT_LOG_MATCH 2
#define DICT_LOG_NOMATCH 3
#define DICT_LOG_CLIENT 4
#define DICT_LOG_TRACE 5
#define DICT_LOG_COMMAND 6
#define DICT_LOG_AUTH 7
#define DICT_LOG_CONNECT 8
#define DICT_UNKNOWN 0
#define DICT_TEXT 1
#define DICT_GZIP 2
#define DICT_DZIP 3
/* For now, just always enable the mmap mode */
#define HAVE_MMAP
#include <sys/stat.h>
#ifdef HAVE_MMAP
#include <sys/mman.h>
#endif
#include <ctype.h>
#include <fcntl.h>
#include <assert.h>
#ifdef HAVE_MMAP
#include <sys/mman.h>
#endif
#include <sys/stat.h>
#define USE_CACHE 1
#ifdef HAVE_MMAP
int mmap_mode = 1; /* dictd uses mmap() function (the default) */
#else
int mmap_mode = 0;
#endif
#define dict_data_filter( ... )
#define PRINTF( ... )
#define xmalloc malloc
#define xfree free
static const char * _err_programName = "GoldenDict";
#define log_error( ... )
#define log_error_va( ... )
static void err_fatal( const char *routine, const char *format, ... )
{
va_list ap;
fflush( stdout );
if (_err_programName) {
if (routine)
fprintf( stderr, "%s (%s): ", _err_programName, routine );
else
fprintf( stderr, "%s: ", _err_programName );
} else {
if (routine) fprintf( stderr, "%s: ", routine );
}
va_start( ap, format );
vfprintf( stderr, format, ap );
log_error_va( routine, format, ap );
va_end( ap );
fflush( stderr );
fflush( stdout );
exit ( 1 );
}
/* \doc |err_fatal_errno| flushes "stdout", prints a fatal error report on
"stderr", prints the system error corresponding to |errno|, flushes
"stderr" and "stdout", and calls |exit|. |routine| is the name of the
routine in which the error took place. */
static void err_fatal_errno( const char *routine, const char *format, ... )
{
va_list ap;
int errorno = errno;
fflush( stdout );
if (_err_programName) {
if (routine)
fprintf( stderr, "%s (%s): ", _err_programName, routine );
else
fprintf( stderr, "%s: ", _err_programName );
} else {
if (routine) fprintf( stderr, "%s: ", routine );
}
va_start( ap, format );
vfprintf( stderr, format, ap );
log_error_va( routine, format, ap );
va_end( ap );
#if HAVE_STRERROR
fprintf( stderr, "%s: %s\n", routine, strerror( errorno ) );
log_error( routine, "%s: %s\n", routine, strerror( errorno ) );
#else
errno = errorno;
perror( routine );
log_error( routine, "%s: errno = %d\n", routine, errorno );
#endif
fflush( stderr );
fflush( stdout );
exit( 1 );
}
/* \doc |err_internal| flushes "stdout", prints the fatal error message,
flushes "stderr" and "stdout", and calls |abort| so that a core dump is
generated. */
static void err_internal( const char *routine, const char *format, ... )
{
va_list ap;
fflush( stdout );
if (_err_programName) {
if (routine)
fprintf( stderr, "%s (%s): Internal error\n ",
_err_programName, routine );
else
fprintf( stderr, "%s: Internal error\n ", _err_programName );
} else {
if (routine) fprintf( stderr, "%s: Internal error\n ", routine );
else fprintf( stderr, "Internal error\n " );
}
va_start( ap, format );
vfprintf( stderr, format, ap );
log_error( routine, format, ap );
va_end( ap );
if (_err_programName)
fprintf( stderr, "Aborting %s...\n", _err_programName );
else
fprintf( stderr, "Aborting...\n" );
fflush( stderr );
fflush( stdout );
abort();
}
static int dict_read_header( const char *filename,
dictData *header, int computeCRC )
{
FILE *str;
int id1, id2, si1, si2;
char buffer[BUFFERSIZE];
int extraLength, subLength;
int i;
char *pt;
int c;
struct stat sb;
unsigned long crc = crc32( 0L, Z_NULL, 0 );
int count;
unsigned long offset;
if (!(str = fopen( filename, "r" )))
err_fatal_errno( __func__,
"Cannot open data file \"%s\" for read\n", filename );
header->filename = NULL;//str_find( filename );
header->headerLength = GZ_XLEN - 1;
header->type = DICT_UNKNOWN;
id1 = getc( str );
id2 = getc( str );
if (id1 != GZ_MAGIC1 || id2 != GZ_MAGIC2) {
header->type = DICT_TEXT;
fstat( fileno( str ), &sb );
header->compressedLength = header->length = sb.st_size;
header->origFilename = NULL;//str_find( filename );
header->mtime = sb.st_mtime;
if (computeCRC) {
rewind( str );
while (!feof( str )) {
if ((count = fread( buffer, 1, BUFFERSIZE, str ))) {
crc = crc32( crc, buffer, count );
}
}
}
header->crc = crc;
fclose( str );
return 0;
}
header->type = DICT_GZIP;
header->method = getc( str );
header->flags = getc( str );
header->mtime = getc( str ) << 0;
header->mtime |= getc( str ) << 8;
header->mtime |= getc( str ) << 16;
header->mtime |= getc( str ) << 24;
header->extraFlags = getc( str );
header->os = getc( str );
if (header->flags & GZ_FEXTRA) {
extraLength = getc( str ) << 0;
extraLength |= getc( str ) << 8;
header->headerLength += extraLength + 2;
si1 = getc( str );
si2 = getc( str );
if (si1 == GZ_RND_S1 && si2 == GZ_RND_S2) {
subLength = getc( str ) << 0;
subLength |= getc( str ) << 8;
header->version = getc( str ) << 0;
header->version |= getc( str ) << 8;
if (header->version != 1)
err_internal( __func__,
"dzip header version %d not supported\n",
header->version );
header->chunkLength = getc( str ) << 0;
header->chunkLength |= getc( str ) << 8;
header->chunkCount = getc( str ) << 0;
header->chunkCount |= getc( str ) << 8;
if (header->chunkCount <= 0) {
fclose( str );
return 5;
}
header->chunks = xmalloc( sizeof( header->chunks[0] )
* header->chunkCount );
for (i = 0; i < header->chunkCount; i++) {
header->chunks[i] = getc( str ) << 0;
header->chunks[i] |= getc( str ) << 8;
}
header->type = DICT_DZIP;
} else {
fseek( str, header->headerLength, SEEK_SET );
}
}
if (header->flags & GZ_FNAME) { /* FIXME! Add checking against header len */
pt = buffer;
while ((c = getc( str )) && c != EOF){
*pt++ = c;
if (pt == buffer + sizeof (buffer)){
err_fatal (
__func__,
"too long FNAME field in dzip file \"%s\"\n", filename);
}
}
*pt = '\0';
header->origFilename = NULL;//str_find( buffer );
header->headerLength += strlen( buffer ) + 1;
} else {
header->origFilename = NULL;
}
if (header->flags & GZ_COMMENT) { /* FIXME! Add checking for header len */
pt = buffer;
while ((c = getc( str )) && c != EOF){
*pt++ = c;
if (pt == buffer + sizeof (buffer)){
err_fatal (
__func__,
"too long COMMENT field in dzip file \"%s\"\n", filename);
}
}
*pt = '\0';
header->comment = NULL;//str_find( buffer );
header->headerLength += strlen( header->comment ) + 1;
} else {
header->comment = NULL;
}
if (header->flags & GZ_FHCRC) {
getc( str );
getc( str );
header->headerLength += 2;
}
if (ftell( str ) != header->headerLength + 1)
err_internal( __func__,
"File position (%lu) != header length + 1 (%d)\n",
ftell( str ), header->headerLength + 1 );
fseek( str, -8, SEEK_END );
header->crc = getc( str ) << 0;
header->crc |= getc( str ) << 8;
header->crc |= getc( str ) << 16;
header->crc |= getc( str ) << 24;
header->length = getc( str ) << 0;
header->length |= getc( str ) << 8;
header->length |= getc( str ) << 16;
header->length |= getc( str ) << 24;
header->compressedLength = ftell( str );
/* Compute offsets */
header->offsets = xmalloc( sizeof( header->offsets[0] )
* header->chunkCount );
for (offset = header->headerLength + 1, i = 0;
i < header->chunkCount;
i++)
{
header->offsets[i] = offset;
offset += header->chunks[i];
}
fclose( str );
return 0;
}
dictData *dict_data_open( const char *filename, int computeCRC )
{
dictData *h = NULL;
struct stat sb;
int j;
if (!filename)
return NULL;
h = xmalloc( sizeof( struct dictData ) );
memset( h, 0, sizeof( struct dictData ) );
h->initialized = 0;
if (dict_read_header( filename, h, computeCRC )) {
err_fatal( __func__,
"\"%s\" not in text or dzip format\n", filename );
}
if ((h->fd = open( filename, O_RDONLY )) < 0)
err_fatal_errno( __func__,
"Cannot open data file \"%s\"\n", filename );
if (fstat( h->fd, &sb ))
err_fatal_errno( __func__,
"Cannot stat data file \"%s\"\n", filename );
h->size = sb.st_size;
if (mmap_mode){
#ifdef HAVE_MMAP
h->start = mmap( NULL, h->size, PROT_READ, MAP_SHARED, h->fd, 0 );
if ((void *)h->start == (void *)(-1))
err_fatal_errno(
__func__,
"Cannot mmap data file \"%s\"\n", filename );
#else
err_fatal (__func__, "This should not happen");
#endif
}else{
h->start = xmalloc (h->size);
if (-1 == read (h->fd, (char *) h->start, h->size))
err_fatal_errno (
__func__,
"Cannot read data file \"%s\"\n", filename );
close (h -> fd);
h -> fd = 0;
}
h->end = h->start + h->size;
for (j = 0; j < DICT_CACHE_SIZE; j++) {
h->cache[j].chunk = -1;
h->cache[j].stamp = -1;
h->cache[j].inBuffer = NULL;
h->cache[j].count = 0;
}
return h;
}
void dict_data_close( dictData *header )
{
int i;
if (!header)
return;
if (header->fd >= 0) {
if (mmap_mode){
#ifdef HAVE_MMAP
munmap( (void *)header->start, header->size );
close( header->fd );
header->fd = 0;
header->start = header->end = NULL;
#else
err_fatal (__func__, "This should not happen");
#endif
}else{
if (header -> start)
xfree ((char *) header -> start);
}
}
if (header->chunks) xfree( header->chunks );
if (header->offsets) xfree( header->offsets );
if (header->initialized) {
if (inflateEnd( &header->zStream ))
err_internal( __func__,
"Cannot shut down inflation engine: %s\n",
header->zStream.msg );
}
for (i = 0; i < DICT_CACHE_SIZE; ++i){
if (header -> cache [i].inBuffer)
xfree (header -> cache [i].inBuffer);
}
memset( header, 0, sizeof( struct dictData ) );
xfree( header );
}
char *dict_data_read_ (
dictData *h, unsigned long start, unsigned long size,
const char *preFilter, const char *postFilter )
{
char *buffer, *pt;
unsigned long end;
int count;
char *inBuffer;
char outBuffer[OUT_BUFFER_SIZE];
int firstChunk, lastChunk;
int firstOffset, lastOffset;
int i, j;
int found, target, lastStamp;
static int stamp = 0;
end = start + size;
buffer = xmalloc( size + 1 );
PRINTF(DBG_UNZIP,
("dict_data_read( %p, %lu, %lu, %s, %s )\n",
h, start, size, preFilter, postFilter ));
assert( h != NULL);
switch (h->type) {
case DICT_GZIP:
err_fatal( __func__,
"Cannot seek on pure gzip format files.\n"
"Use plain text (for performance)"
" or dzip format (for space savings).\n" );
break;
case DICT_TEXT:
memcpy( buffer, h->start + start, size );
buffer[size] = '\0';
break;
case DICT_DZIP:
if (!h->initialized) {
++h->initialized;
h->zStream.zalloc = NULL;
h->zStream.zfree = NULL;
h->zStream.opaque = NULL;
h->zStream.next_in = 0;
h->zStream.avail_in = 0;
h->zStream.next_out = NULL;
h->zStream.avail_out = 0;
if (inflateInit2( &h->zStream, -15 ) != Z_OK)
err_internal( __func__,
"Cannot initialize inflation engine: %s\n",
h->zStream.msg );
}
firstChunk = start / h->chunkLength;
firstOffset = start - firstChunk * h->chunkLength;
lastChunk = end / h->chunkLength;
lastOffset = end - lastChunk * h->chunkLength;
PRINTF(DBG_UNZIP,
(" start = %lu, end = %lu\n"
"firstChunk = %d, firstOffset = %d,"
" lastChunk = %d, lastOffset = %d\n",
start, end, firstChunk, firstOffset, lastChunk, lastOffset ));
for (pt = buffer, i = firstChunk; i <= lastChunk; i++) {
/* Access cache */
found = 0;
target = 0;
lastStamp = INT_MAX;
for (j = 0; j < DICT_CACHE_SIZE; j++) {
#if USE_CACHE
if (h->cache[j].chunk == i) {
found = 1;
target = j;
break;
}
#endif
if (h->cache[j].stamp < lastStamp) {
lastStamp = h->cache[j].stamp;
target = j;
}
}
h->cache[target].stamp = ++stamp;
if (found) {
count = h->cache[target].count;
inBuffer = h->cache[target].inBuffer;
} else {
h->cache[target].chunk = i;
if (!h->cache[target].inBuffer)
h->cache[target].inBuffer = xmalloc( IN_BUFFER_SIZE );
inBuffer = h->cache[target].inBuffer;
if (h->chunks[i] >= OUT_BUFFER_SIZE ) {
err_internal( __func__,
"h->chunks[%d] = %d >= %ld (OUT_BUFFER_SIZE)\n",
i, h->chunks[i], OUT_BUFFER_SIZE );
}
memcpy( outBuffer, h->start + h->offsets[i], h->chunks[i] );
dict_data_filter( outBuffer, &count, OUT_BUFFER_SIZE, preFilter );
h->zStream.next_in = outBuffer;
h->zStream.avail_in = h->chunks[i];
h->zStream.next_out = inBuffer;
h->zStream.avail_out = IN_BUFFER_SIZE;
if (inflate( &h->zStream, Z_PARTIAL_FLUSH ) != Z_OK)
err_fatal( __func__, "inflate: %s\n", h->zStream.msg );
if (h->zStream.avail_in)
err_internal( __func__,
"inflate did not flush (%d pending, %d avail)\n",
h->zStream.avail_in, h->zStream.avail_out );
count = IN_BUFFER_SIZE - h->zStream.avail_out;
dict_data_filter( inBuffer, &count, IN_BUFFER_SIZE, postFilter );
h->cache[target].count = count;
}
if (i == firstChunk) {
if (i == lastChunk) {
memcpy( pt, inBuffer + firstOffset, lastOffset-firstOffset);
pt += lastOffset - firstOffset;
} else {
if (count != h->chunkLength )
err_internal( __func__,
"Length = %d instead of %d\n",
count, h->chunkLength );
memcpy( pt, inBuffer + firstOffset,
h->chunkLength - firstOffset );
pt += h->chunkLength - firstOffset;
}
} else if (i == lastChunk) {
memcpy( pt, inBuffer, lastOffset );
pt += lastOffset;
} else {
assert( count == h->chunkLength );
memcpy( pt, inBuffer, h->chunkLength );
pt += h->chunkLength;
}
}
*pt = '\0';
break;
case DICT_UNKNOWN:
err_fatal( __func__, "Cannot read unknown file type\n" );
break;
}
return buffer;
}

97
src/dictzip.h Normal file
View file

@ -0,0 +1,97 @@
/* Made up from data.h and other supplementary files of dictd-1.0.11 for the
* GoldenDict program.
*/
/* data.h --
* Created: Sat Mar 15 18:04:25 2003 by Aleksey Cheusov <vle@gmx.net>
* Copyright 1994-2003 Rickard E. Faith (faith@dict.org)
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
* Free Software Foundation; either version 1, 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.,
* 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _DICTZIP_H_
#define _DICTZIP_H_
#include <stdio.h>
#include <zlib.h>
#ifdef __cplusplus
extern "C"
{
#endif
/* Excerpts from defs.h */
#define DICT_CACHE_SIZE 5
typedef struct dictCache {
int chunk;
char *inBuffer;
int stamp;
int count;
} dictCache;
typedef struct dictData {
int fd; /* file descriptor */
const char *start; /* start of mmap'd area */
const char *end; /* end of mmap'd area */
unsigned long size; /* size of mmap */
int type;
const char *filename;
z_stream zStream;
int initialized;
int headerLength;
int method;
int flags;
time_t mtime;
int extraFlags;
int os;
int version;
int chunkLength;
int chunkCount;
int *chunks;
unsigned long *offsets; /* Sum-scan of chunks. */
const char *origFilename;
const char *comment;
unsigned long crc;
unsigned long length;
unsigned long compressedLength;
dictCache cache[DICT_CACHE_SIZE];
} dictData;
/* initialize .data file */
extern dictData *dict_data_open (
const char *filename, int computeCRC);
/* */
extern void dict_data_close (
dictData *data);
extern char *dict_data_read_ (
dictData *data,
unsigned long start, unsigned long end,
const char *preFilter,
const char *postFilter );
extern int mmap_mode;
#ifdef __cplusplus
} /* end extern "C" */
#endif
#endif /* _DICTZIP_H_ */

986
src/dsl.cc Normal file
View file

@ -0,0 +1,986 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "dsl.hh"
#include "dsl_details.hh"
#include "btreeidx.hh"
#include "folding.hh"
#include "utf8.hh"
#include "chunkedstorage.hh"
#include "dictzip.h"
#include "htmlescape.hh"
#include "iconv.hh"
#include "filetype.hh"
#include "fsencoding.hh"
#include <zlib.h>
#include <map>
#include <set>
#include <string>
#include <vector>
#include <list>
#include <wctype.h>
// For TIFF conversion
#include <QImage>
#include <QByteArray>
#include <QBuffer>
namespace Dsl {
using namespace Details;
using std::map;
using std::multimap;
using std::pair;
using std::set;
using std::string;
using std::wstring;
using std::vector;
using std::list;
using BtreeIndexing::WordArticleLink;
using BtreeIndexing::IndexedWords;
namespace {
DEF_EX_STR( exCantReadFile, "Can't read file", Dictionary::Ex )
enum
{
Signature = 0x584c5344, // DSLX on little-endian, XLSD on big-endian
CurrentFormatVersion = 6 + BtreeIndexing::FormatVersion + Folding::Version
};
struct IdxHeader
{
uint32_t signature; // First comes the signature, DSLX
uint32_t formatVersion; // File format version (CurrentFormatVersion)
int dslEncoding; // Which encoding is used for the file indexed
uint32_t chunksOffset; // The offset to chunks' storage
uint32_t hasAbrv; // Non-zero means file has abrvs at abrvAddress
uint32_t abrvAddress; // Address of abrv map in the chunked storage
uint32_t indexOffset; // The offset of the index in the file
} __attribute__((packed));
bool indexIsOldOrBad( string const & indexFile )
{
File::Class idx( indexFile, "rb" );
IdxHeader header;
return idx.readRecords( &header, sizeof( header ), 1 ) != 1 ||
header.signature != Signature ||
header.formatVersion != CurrentFormatVersion;
}
class DslDictionary: public BtreeIndexing::BtreeDictionary
{
File::Class idx;
IdxHeader idxHeader;
ChunkedStorage::Reader chunks;
string dictionaryName;
map< string, string > abrv;
dictData * dz;
public:
DslDictionary( string const & id, string const & indexFile,
vector< string > const & dictionaryFiles );
~DslDictionary();
virtual string getName() throw()
{ return dictionaryName; }
virtual map< Dictionary::Property, string > getProperties() throw()
{ return map< Dictionary::Property, string >(); }
virtual unsigned long getArticleCount() throw()
{ return 0; }
virtual unsigned long getWordCount() throw()
{ return 0; }
virtual vector< wstring > findHeadwordsForSynonym( wstring const & )
throw( std::exception )
{
return vector< wstring >();
}
virtual string getArticle( wstring const &, vector< wstring > const & alts )
throw( Dictionary::exNoSuchWord, std::exception );
virtual void getResource( string const & name,
vector< char > & data )
throw( Dictionary::exNoSuchResource, std::exception );
private:
/// Loads the article. Does not process the DSL language.
void loadArticle( uint32_t address,
string & headword,
list< wstring > & displayedHeadwords,
wstring & articleText );
/// Converts DSL language to an Html.
string dslToHtml( wstring const & );
// Parts of dslToHtml()
string nodeToHtml( ArticleDom::Node const & );
string processNodeChildren( ArticleDom::Node const & node );
};
DslDictionary::DslDictionary( string const & id,
string const & indexFile,
vector< string > const & dictionaryFiles ):
BtreeDictionary( id, dictionaryFiles ),
idx( indexFile, "rb" ),
idxHeader( idx.read< IdxHeader >() ),
chunks( idx, idxHeader.chunksOffset )
{
// Open the .dict file
dz = dict_data_open( dictionaryFiles[ 0 ].c_str(), 0 );
if ( !dz )
throw exCantReadFile( dictionaryFiles[ 0 ] );
// Read the dictionary name
idx.seek( sizeof( idxHeader ) );
vector< char > dName( idx.read< uint32_t >() );
idx.read( &dName.front(), dName.size() );
dictionaryName = string( &dName.front(), dName.size() );
// Read the abrv, if any
if ( idxHeader.hasAbrv )
{
vector< char > chunk;
char * abrvBlock = chunks.getBlock( idxHeader.abrvAddress, chunk );
uint32_t total;
memcpy( &total, abrvBlock, sizeof( uint32_t ) );
abrvBlock += sizeof( uint32_t );
printf( "Loading %u abbrv\n", total );
while( total-- )
{
uint32_t keySz;
memcpy( &keySz, abrvBlock, sizeof( uint32_t ) );
abrvBlock += sizeof( uint32_t );
char * key = abrvBlock;
abrvBlock += keySz;
uint32_t valueSz;
memcpy( &valueSz, abrvBlock, sizeof( uint32_t ) );
abrvBlock += sizeof( uint32_t );
abrv[ string( key, keySz ) ] = string( abrvBlock, valueSz );
abrvBlock += valueSz;
}
}
// Initialize the index
idx.seek( idxHeader.indexOffset );
openIndex( idx );
}
DslDictionary::~DslDictionary()
{
if ( dz )
dict_data_close( dz );
}
void DslDictionary::loadArticle( uint32_t address,
string & headword,
list< wstring > & displayedHeadwords,
wstring & articleText )
{
wstring articleData;
{
vector< char > chunk;
char * articleProps = chunks.getBlock( address, chunk );
uint32_t articleOffset, articleSize;
memcpy( &articleOffset, articleProps, sizeof( articleOffset ) );
memcpy( &articleSize, articleProps + sizeof( articleOffset ),
sizeof( articleSize ) );
printf( "offset = %x\n", articleOffset );
char * articleBody = dict_data_read_( dz, articleOffset, articleSize, 0, 0 );
if ( !articleBody )
throw exCantReadFile( getDictionaryFilenames()[ 0 ] );
try
{
articleData =
DslIconv::toWstring(
DslIconv::getEncodingNameFor( DslEncoding( idxHeader.dslEncoding ) ),
articleBody, articleSize );
}
catch( ... )
{
free( articleBody );
throw;
}
}
size_t pos = articleData.find_first_of( L"\n\r" );
if ( pos == wstring::npos )
pos = articleData.size();
wstring firstHeadword( articleData, 0, pos );
printf( "first headword = %ls\n", firstHeadword.c_str() );
// Make a headword
{
wstring str( firstHeadword );
list< wstring > lst;
processUnsortedParts( str, true );
expandOptionalParts( str, lst );
headword = Utf8::encode( lst.front() );
}
// Generate displayed headwords
displayedHeadwords.clear();
processUnsortedParts( firstHeadword, false );
expandOptionalParts( firstHeadword, displayedHeadwords );
// Now skip alts until we reach the body itself
while ( pos != articleData.size() )
{
if ( articleData[ pos ] == '\r' )
++pos;
if ( pos != articleData.size() )
{
if ( articleData[ pos ] == '\n' )
++pos;
}
if ( pos != articleData.size() && !iswblank( articleData[ pos ] ) )
{
// Skip any alt headwords
pos = articleData.find_first_of( L"\n\r", pos );
if ( pos == wstring::npos )
pos = articleData.size();
}
else
break;
}
if ( pos != articleData.size() )
articleText = wstring( articleData, pos );
else
articleText = L"";
}
string DslDictionary::dslToHtml( wstring const & str )
{
ArticleDom dom( str );
string html = processNodeChildren( dom.root );
// Lines seem to indicate paragraphs in Dsls, so we enclose each line within
// a <p></p>.
for( size_t x = html.size(); x--; )
if ( html[ x ] == '\n' )
html.insert( x + 1, "</p><p>" );
return "<!-- DSL Source:\n" + Utf8::encode( str ) + "\n-->"
"<p>" + html + "</p>";
}
string DslDictionary::processNodeChildren( ArticleDom::Node const & node )
{
string result;
for( ArticleDom::Node::const_iterator i = node.begin(); i != node.end();
++i )
result += nodeToHtml( *i );
return result;
}
string DslDictionary::nodeToHtml( ArticleDom::Node const & node )
{
if ( !node.isTag )
return Html::escape( Utf8::encode( node.text ) );
string result;
if ( node.tagName == L"b" )
result += "<b class=\"dsl_b\">" + processNodeChildren( node ) + "</b>";
else
if ( node.tagName == L"i" )
result += "<i class=\"dsl_i\">" + processNodeChildren( node ) + "</i>";
else
if ( node.tagName == L"u" )
result += "<span class=\"dsl_u\">" + processNodeChildren( node ) + "</span>";
else
if ( node.tagName == L"c" )
{
result += "<font color=\"" + ( node.tagAttrs.size() ?
Html::escape( Utf8::encode( node.tagAttrs ) ) : string( "c_default_color" ) )
+ "\">" + processNodeChildren( node ) + "</font>";
}
else
if ( node.tagName == L"*" )
result += "<span class=\"dsl_opt\">" + processNodeChildren( node ) + "</span>";
else
if ( node.tagName.size() == 2 && node.tagName[ 0 ] == L'm' &&
iswdigit( node.tagName[ 1 ] ) )
result += "<div class=\"dsl_" + Utf8::encode( node.tagName ) + "\">" + processNodeChildren( node ) + "</div>";
else
if ( node.tagName == L"trn" )
result += "<span class=\"dsl_trn\">" + processNodeChildren( node ) + "</span>";
else
if ( node.tagName == L"ex" )
result += "<span class=\"dsl_ex\">" + processNodeChildren( node ) + "</span>";
else
if ( node.tagName == L"com" )
result += "<span class=\"dsl_com\">" + processNodeChildren( node ) + "</span>";
else
if ( node.tagName == L"s" )
{
string filename = Utf8::encode( node.renderAsText() );
if ( Filetype::isNameOfSound( filename ) )
{
// If we have the file here, do the exact reference to this dictionary.
// Otherwise, make a global 'search' one.
string n =
FsEncoding::dirname( getDictionaryFilenames()[ 0 ] ) +
FsEncoding::separator() +
FsEncoding::encode( filename );
bool search = true;
try
{
File::Class f( n, "r" );
search = false;
}
catch( File::Ex & )
{
}
string ref = "\"gdau://" + ( search ? string( "search" ) : getId() ) +
"/" + Html::escape( filename ) +"\"";
result += "<span class=\"dsl_s_wav\"><a href=" + ref
+ "><img src=\"qrcx://localhost/icons/playsound.png\" border=\"0\" align=\"absmiddle\" alt=\"Play\"/></a></span>";
}
else
if ( Filetype::isNameOfPicture( filename ) )
{
result += "<img src=\"bres://" + getId() + "/" + Html::escape( filename )
+ "\" alt=\"" + Html::escape( filename ) + "\"/>";
}
else
{
// Unknown file type, downgrade to a hyperlink
result += "<a class=\"dsl_s\" href=\"bres://" + getId() + "/" + Html::escape( filename )
+ "\">" + processNodeChildren( node ) + "</a>";
}
}
else
if ( node.tagName == L"url" )
result += "<a class=\"dsl_url\" href=\"" + Html::escape( Utf8::encode( node.renderAsText() ) ) +"\">" + processNodeChildren( node ) + "</a>";
else
if ( node.tagName == L"!trs" )
result += "<span class=\"dsl_trs\">" + processNodeChildren( node ) + "</span>";
else
if ( node.tagName == L"p" )
{
result += "<span class=\"dsl_p\"";
string val = Utf8::encode( node.renderAsText() );
// If we have such a key, display a title
map< string, string >::const_iterator i = abrv.find( val );
if ( i != abrv.end() )
result += " title=\"" + Html::escape( i->second ) + "\"";
result += ">" + processNodeChildren( node ) + "</span>";
}
else
if ( node.tagName == L"'" )
{
result += "<span class=\"dsl_stress\">" + processNodeChildren( node ) + "<span class=\"dsl_stacc\">" + Utf8::encode( wstring( 1, 0x301 ) ) + "</span></span>";
}
else
if ( node.tagName == L"lang" )
{
result += "<span class=\"dsl_lang\">" + processNodeChildren( node ) + "</span>";
}
else
if ( node.tagName == L"ref" )
{
result += "<a class=\"dsl_ref\" href=\"bword://" + Html::escape( Utf8::encode( node.renderAsText() ) ) +"\">" + processNodeChildren( node ) + "</a>";
}
else
if ( node.tagName == L"sub" )
{
result += "<sub>" + processNodeChildren( node ) + "</sub>";
}
else
if ( node.tagName == L"sup" )
{
result += "<sup>" + processNodeChildren( node ) + "</sup>";
}
else
if ( node.tagName == L"t" )
{
result += "<span class=\"dsl_t\">" + processNodeChildren( node ) + "</span>";
}
else
result += "<span class=\"dsl_unknown\">" + processNodeChildren( node ) + "</span>";
return result;
}
#if 0
vector< wstring > StardictDictionary::findHeadwordsForSynonym( wstring const & str )
throw( std::exception )
{
vector< wstring > result;
vector< WordArticleLink > chain = findArticles( str );
wstring caseFolded = Folding::applySimpleCaseOnly( str );
for( unsigned x = 0; x < chain.size(); ++x )
{
string headword, articleText;
loadArticle( chain[ x ].articleOffset,
headword, articleText );
wstring headwordDecoded = Utf8::decode( headword );
if ( caseFolded != Folding::applySimpleCaseOnly( headwordDecoded ) )
{
// The headword seems to differ from the input word, which makes the
// input word its synonym.
result.push_back( headwordDecoded );
}
}
return result;
}
#endif
string DslDictionary::getArticle( wstring const & word,
vector< wstring > const & alts )
throw( Dictionary::exNoSuchWord, std::exception )
{
vector< WordArticleLink > chain = findArticles( word );
for( unsigned x = 0; x < alts.size(); ++x )
{
/// Make an additional query for each alt
vector< WordArticleLink > altChain = findArticles( alts[ x ] );
chain.insert( chain.end(), altChain.begin(), altChain.end() );
}
multimap< wstring, string > mainArticles, alternateArticles;
set< uint32_t > articlesIncluded; // Some synonims make it that the articles
// appear several times. We combat this
// by only allowing them to appear once.
wstring wordCaseFolded = Folding::applySimpleCaseOnly( word );
for( unsigned x = 0; x < chain.size(); ++x )
{
if ( articlesIncluded.find( chain[ x ].articleOffset ) != articlesIncluded.end() )
continue; // We already have this article in the body.
// Now grab that article
string headword;
list< wstring > displayedHeadwords;
wstring articleBody;
loadArticle( chain[ x ].articleOffset, headword, displayedHeadwords,
articleBody );
string articleText;
articleText += "<span class=\"dsl_article\">";
articleText += "<div class=\"dsl_headwords\">";
for( list< wstring >::const_iterator i = displayedHeadwords.begin();
i != displayedHeadwords.end(); ++i )
articleText += dslToHtml( *i );
articleText += "</div>";
if ( displayedHeadwords.size() )
expandTildes( articleBody, displayedHeadwords.front() );
articleText += "<div class=\"dsl_definition\">";
articleText += dslToHtml( articleBody );
articleText += "</div>";
articleText += "</span>";
// Ok. Now, does it go to main articles, or to alternate ones? We list
// main ones first, and alternates after.
// We do the case-folded comparison here.
wstring headwordStripped =
Folding::applySimpleCaseOnly( Utf8::decode( headword ) );
multimap< wstring, string > & mapToUse =
( wordCaseFolded == headwordStripped ) ?
mainArticles : alternateArticles;
mapToUse.insert( pair< wstring, string >(
Folding::applySimpleCaseOnly( Utf8::decode( headword ) ),
articleText ) );
articlesIncluded.insert( chain[ x ].articleOffset );
}
if ( mainArticles.empty() && alternateArticles.empty() )
throw Dictionary::exNoSuchWord();
string result;
multimap< wstring, string >::const_iterator i;
for( i = mainArticles.begin(); i != mainArticles.end(); ++i )
result += i->second;
for( i = alternateArticles.begin(); i != alternateArticles.end(); ++i )
result += i->second;
return result;
}
void DslDictionary::getResource( string const & name,
vector< char > & data )
throw( Dictionary::exNoSuchResource, std::exception )
{
string n =
FsEncoding::dirname( getDictionaryFilenames()[ 0 ] ) +
FsEncoding::separator() +
FsEncoding::encode( name );
printf( "n is %s\n", n.c_str() );
try
{
File::Class f( n, "r" );
f.seekEnd();
data.resize( f.tell() );
f.rewind();
f.read( &data.front(), data.size() );
if ( Filetype::isNameOfTiff( name ) )
{
// Convert it
QImage img = QImage::fromData( (unsigned char *) &data.front(),
data.size() );
if ( img.isNull() )
{
// Failed to load, return data as is
return;
}
QByteArray ba;
QBuffer buffer( &ba );
buffer.open( QIODevice::WriteOnly );
img.save( &buffer, "BMP" );
data.resize( buffer.size() );
memcpy( &data.front(), buffer.data(), data.size() );
}
}
catch( File::Ex & )
{
throw Dictionary::exNoSuchResource();
}
}
} // anonymous namespace
static bool tryPossibleName( string const & name, string & copyTo )
{
try
{
File::Class f( name, "rb" );
copyTo = name;
return true;
}
catch( ... )
{
return false;
}
}
#if 0
static void findCorrespondingFiles( string const & ifo,
string & idx, string & dict, string & syn,
bool needSyn )
{
string base( ifo, 0, ifo.size() - 3 );
if ( !(
tryPossibleName( base + "idx", idx ) ||
tryPossibleName( base + "idx.gz", idx ) ||
tryPossibleName( base + "idx.dz", idx ) ||
tryPossibleName( base + "IDX", idx ) ||
tryPossibleName( base + "IDX.GZ", idx ) ||
tryPossibleName( base + "IDX.DZ", idx )
) )
throw exNoIdxFile( ifo );
if ( !(
tryPossibleName( base + "dict", dict ) ||
tryPossibleName( base + "dict.dz", dict ) ||
tryPossibleName( base + "DICT", dict ) ||
tryPossibleName( base + "dict.DZ", dict )
) )
throw exNoDictFile( ifo );
if ( needSyn && !(
tryPossibleName( base + "syn", syn ) ||
tryPossibleName( base + "syn.gz", syn ) ||
tryPossibleName( base + "syn.dz", syn ) ||
tryPossibleName( base + "SYN", syn ) ||
tryPossibleName( base + "SYN.GZ", syn ) ||
tryPossibleName( base + "SYN.DZ", syn )
) )
throw exNoSynFile( ifo );
}
#endif
vector< sptr< Dictionary::Class > > Format::makeDictionaries(
vector< string > const & fileNames,
string const & indicesDir,
Dictionary::Initializing & initializing )
throw( std::exception )
{
vector< sptr< Dictionary::Class > > dictionaries;
for( vector< string >::const_iterator i = fileNames.begin(); i != fileNames.end();
++i )
{
// Try .dsl and .dsl.dz suffixes
if ( ( i->size() < 4 ||
strcasecmp( i->c_str() + ( i->size() - 4 ), ".dsl" ) != 0 ) &&
( i->size() < 7 ||
strcasecmp( i->c_str() + ( i->size() - 7 ), ".dsl.dz" ) != 0 ) )
continue;
try
{
vector< string > dictFiles( 1, *i );
// Check if there is an 'abrv' file present
string baseName = ( (*i)[ i->size() - 4 ] == '.' ) ?
string( *i, 0, i->size() - 4 ) : string( *i, 0, i->size() - 7 );
string abrvFileName;
if ( tryPossibleName( baseName + "_abrv.dsl", abrvFileName ) ||
tryPossibleName( baseName + "_abrv.dsl.dz", abrvFileName ) ||
tryPossibleName( baseName + "_ABRV.DSL", abrvFileName ) ||
tryPossibleName( baseName + "_ABRV.DSL.DZ", abrvFileName ) ||
tryPossibleName( baseName + "_ABRV.DSL.dz", abrvFileName ) )
dictFiles.push_back( abrvFileName );
string dictId = makeDictionaryId( dictFiles );
string indexFile = indicesDir + dictId;
if ( needToRebuildIndex( dictFiles, indexFile ) ||
indexIsOldOrBad( indexFile ) )
{
DslScanner scanner( *i );
if ( scanner.getDictionaryName() == L"Abbrev" )
continue; // For now just skip abbreviations
// Building the index
initializing.indexingDictionary( Utf8::encode( scanner.getDictionaryName() ) );
printf( "Dictionary name: %ls\n", scanner.getDictionaryName().c_str() );
File::Class idx( indexFile, "wb" );
IdxHeader idxHeader;
memset( &idxHeader, 0, sizeof( idxHeader ) );
// We write a dummy header first. At the end of the process the header
// will be rewritten with the right values.
idx.write( idxHeader );
string dictionaryName = Utf8::encode( scanner.getDictionaryName() );
idx.write( (uint32_t) dictionaryName.size() );
idx.write( dictionaryName.data(), dictionaryName.size() );
idxHeader.dslEncoding = scanner.getEncoding();
IndexedWords indexedWords;
ChunkedStorage::Writer chunks( idx );
// Read the abbreviations
if ( abrvFileName.size() )
{
try
{
DslScanner abrvScanner( abrvFileName );
map< string, string > abrv;
wstring curString;
size_t curOffset;
for( ; ; )
{
// Skip any whitespace
if ( !abrvScanner.readNextLine( curString, curOffset ) )
break;
if ( curString.empty() || iswblank( curString[ 0 ] ) )
continue;
string key = Utf8::encode( curString );
if ( !abrvScanner.readNextLine( curString, curOffset ) )
{
fprintf( stderr, "Warning: premature end of file %s\n", abrvFileName.c_str() );
break;
}
if ( curString.empty() || !iswblank( curString[ 0 ] ) )
{
fprintf( stderr, "Warning: malformed file %s\n", abrvFileName.c_str() );
break;
}
curString.erase( 0, curString.find_first_not_of( L" \t" ) );
abrv[ key ] = Utf8::encode( curString );
}
idxHeader.hasAbrv = 1;
idxHeader.abrvAddress = chunks.startNewBlock();
uint32_t sz = abrv.size();
chunks.addToBlock( &sz, sizeof( uint32_t ) );
for( map< string, string >::const_iterator i = abrv.begin();
i != abrv.end(); ++i )
{
printf( "%s:%s\n", i->first.c_str(), i->second.c_str() );
sz = i->first.size();
chunks.addToBlock( &sz, sizeof( uint32_t ) );
chunks.addToBlock( i->first.data(), sz );
sz = i->second.size();
chunks.addToBlock( &sz, sizeof( uint32_t ) );
chunks.addToBlock( i->second.data(), sz );
}
}
catch( std::exception & e )
{
fprintf( stderr, "Error reading abrv file %s: %s. Skipping it.\n",
abrvFileName.c_str(), e.what() );
}
}
bool hasString = false;
wstring curString;
size_t curOffset;
for( ; ; )
{
// Find the main headword
if ( !hasString && !scanner.readNextLine( curString, curOffset ) )
break; // Clean end of file
hasString = false;
// The line read should either consist of pure whitespace, or be a
// headword
if ( curString.empty() )
continue;
if ( iswblank( curString[ 0 ] ) )
{
// The first character is blank. Let's make sure that all other
// characters are blank, too.
for( size_t x = 1; x < curString.size(); ++x )
{
if ( !iswblank( curString[ x ] ) )
{
fprintf( stderr, "Warning: garbage string in %s at offset 0x%X\n", i->c_str(), curOffset );
break;
}
}
continue;
}
// Ok, got the headword
list< wstring > allEntryWords;
processUnsortedParts( curString, true );
expandOptionalParts( curString, allEntryWords );
uint32_t articleOffset = curOffset;
//printf( "Headword: %ls\n", curString.c_str() );
// More headwords may follow
for( ; ; )
{
if ( ! ( hasString = scanner.readNextLine( curString, curOffset ) ) )
{
fprintf( stderr, "Warning: premature end of file %s\n", i->c_str() );
exit( 0 );
break;
}
if ( curString.empty() || iswblank( curString[ 0 ] ) )
break; // No more headwords
printf( "Alt headword: %ls\n", curString.c_str() );
processUnsortedParts( curString, true );
expandTildes( curString, allEntryWords.front() );
expandOptionalParts( curString, allEntryWords );
}
if ( !hasString )
break;
// Insert new entry
uint32_t descOffset = chunks.startNewBlock();
chunks.addToBlock( &articleOffset, sizeof( articleOffset ) );
for( list< wstring >::iterator j = allEntryWords.begin();
j != allEntryWords.end(); ++j )
{
unescapeDsl( *j );
wstring folded = Folding::apply( *j );
IndexedWords::iterator e = indexedWords.insert(
IndexedWords::value_type( folded, vector< WordArticleLink >() ) ).first;
// Try to conserve memory somewhat -- slow insertions are ok
e->second.reserve( e->second.size() + 1 );
e->second.push_back( WordArticleLink( Utf8::encode( *j ), descOffset ) );
}
// Skip the article's body
for( ; ; )
{
if ( ! ( hasString = scanner.readNextLine( curString, curOffset ) ) )
break;
if ( curString.size() && !iswblank( curString[ 0 ] ) )
break;
}
// Now that we're having read the first string after the article
// itself, we can use its offset to calculate the article's size.
// An end of file works here, too.
uint32_t articleSize = ( curOffset - articleOffset );
chunks.addToBlock( &articleSize, sizeof( articleSize ) );
if ( !hasString )
break;
}
// Finish with the chunks
idxHeader.chunksOffset = chunks.finish();
// Build index
idxHeader.indexOffset = BtreeIndexing::buildIndex( indexedWords, idx );
// That concludes it. Update the header.
idxHeader.signature = Signature;
idxHeader.formatVersion = CurrentFormatVersion;
idx.rewind();
idx.write( &idxHeader, sizeof( idxHeader ) );
}
dictionaries.push_back( new DslDictionary( dictId,
indexFile,
dictFiles ) );
}
catch( std::exception & e )
{
fprintf( stderr, "DSL dictionary reading failed: %s, error: %s\n",
i->c_str(), e.what() );
}
}
return dictionaries;
}
}

28
src/dsl.hh Normal file
View file

@ -0,0 +1,28 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __DSL_HH_INCLUDED__
#define __DSL_HH_INCLUDED__
#include "dictionary.hh"
/// Support for the ABBYY Lingo .DSL files.
namespace Dsl {
using std::vector;
using std::string;
class Format: public Dictionary::Format
{
public:
virtual vector< sptr< Dictionary::Class > > makeDictionaries(
vector< string > const & fileNames,
string const & indicesDir,
Dictionary::Initializing & )
throw( std::exception );
};
}
#endif

750
src/dsl_details.cc Normal file
View file

@ -0,0 +1,750 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "dsl_details.hh"
#include <wctype.h>
namespace Dsl {
namespace Details {
using std::wstring;
using std::list;
/////////////// ArticleDom
wstring ArticleDom::Node::renderAsText() const
{
if ( !isTag )
return text;
wstring result;
for( list< Node >::const_iterator i = begin(); i != end(); ++i )
result += i->renderAsText();
return result;
}
// Returns true if src == 'm' and dest is 'mX', where X is a digit
static inline bool checkM( wstring const & dest, wstring const & src )
{
return ( src == L"m" && dest.size() == 2 &&
dest[ 0 ] == L'm' && iswdigit( dest[ 1 ] ) );
}
ArticleDom::ArticleDom( wstring const & str ):
root( Node::Tag(), L"", L"" ), stringPos( str.c_str() )
{
list< Node * > stack; // Currently opened tags
Node * textNode = 0; // A leaf node which currently accumulates text.
try
{
for( ;; )
{
nextChar();
if ( ch == L'[' && !escaped )
{
// Beginning of a tag.
do
{
nextChar();
} while( iswblank( ch ) );
bool isClosing;
if ( ch == L'/' && !escaped )
{
// A closing tag.
isClosing = true;
nextChar();
}
else
isClosing = false;
// Read tag's name
wstring name;
while( ( ch != L']' || escaped ) && !iswblank( ch ) )
{
name.push_back( ch );
nextChar();
}
while( iswblank( ch ) )
nextChar();
// Read attrs
wstring attrs;
while( ch != L']' || escaped )
{
attrs.push_back( ch );
nextChar();
}
// Add the tag, or close it
if ( textNode )
{
// Close the currently opened text node
stack.pop_back();
textNode = 0;
}
if ( !isClosing )
{
Node node( Node::Tag(), name, attrs );
if ( stack.empty() )
{
root.push_back( node );
stack.push_back( &root.back() );
}
else
{
stack.back()->push_back( node );
stack.push_back( &stack.back()->back() );
}
}
else
{
// Find the tag which is to be closed
list< Node * >::reverse_iterator n;
for( n = stack.rbegin(); n != stack.rend(); ++n )
{
if ( (*n)->tagName == name || checkM( (*n)->tagName, name ) )
{
// Found it
break;
}
}
if ( n != stack.rend() )
{
// If there is a corresponding tag, close all tags above it,
// then close the tag itself, then reopen all the tags which got
// closed.
list< Node > nodesToReopen;
while( stack.size() )
{
bool found = stack.back()->tagName == name ||
checkM( stack.back()->tagName, name );
if ( !found )
nodesToReopen.push_back( Node( Node::Tag(), stack.back()->tagName,
stack.back()->tagAttrs ) );
if ( stack.back()->empty() )
{
// Empty nodes are deleted since they're no use
stack.pop_back();
Node * parent = stack.size() ? stack.back() : &root;
parent->pop_back();
}
else
stack.pop_back();
if ( found )
break;
}
while( nodesToReopen.size() )
{
if ( stack.empty() )
{
root.push_back( nodesToReopen.back() );
stack.push_back( &root.back() );
}
else
{
stack.back()->push_back( nodesToReopen.back() );
stack.push_back( &stack.back()->back() );
}
nodesToReopen.pop_back();
}
}
else
{
fprintf( stderr, "Warning: no corresponding opening tag for closing tag \"/%ls\" found.\n",
name.c_str() );
}
} // if ( isClosing )
continue;
} // if ( ch == '[' )
if ( ch == L'<' && !escaped )
{
// Special case: the <<name>> link
nextChar();
if ( ch != L'<' || escaped )
{
// Ok, it's not it.
--stringPos;
if ( escaped )
{
--stringPos;
escaped = false;
}
ch = L'<';
}
else
{
// Get the link's body
do
{
nextChar();
} while( iswblank( ch ) );
wstring linkTo;
for( ; ; nextChar() )
{
// Is it the end?
if ( ch == L'>' && !escaped )
{
nextChar();
if ( ch == L'>' && !escaped )
break;
else
{
linkTo.push_back( L'>' );
linkTo.push_back( ch );
}
}
else
linkTo.push_back( ch );
}
// Add the corresponding node
if ( textNode )
{
// Close the currently opened text node
stack.pop_back();
textNode = 0;
}
Node link( Node::Tag(), L"ref", L"" );
link.push_back( Node( Node::Text(), linkTo ) );
if ( stack.empty() )
root.push_back( link );
else
stack.back()->push_back( link );
continue;
}
} // if ( ch == '<' )
// If we're here, we've got a normal symbol, to be saved as text.
// If there's currently no text node, open one
if ( !textNode )
{
Node text( Node::Text(), L"" );
if ( stack.empty() )
{
root.push_back( text );
stack.push_back( &root.back() );
}
else
{
stack.back()->push_back( text );
stack.push_back( &stack.back()->back() );
}
textNode = stack.back();
}
textNode->text.push_back( ch );
} // for( ; ; )
}
catch( eot )
{
}
if ( textNode )
stack.pop_back();
if ( stack.size() )
fprintf( stderr, "Warning: %u tags were unclosed.\n", stack.size() );
}
void ArticleDom::nextChar() throw( eot )
{
if ( !*stringPos )
throw eot();
ch = *stringPos++;
if ( ch == L'\\' )
{
if ( !*stringPos )
throw eot();
ch = *stringPos++;
escaped = true;
}
else
escaped = false;
}
/////////////// DslScanner
DslScanner::DslScanner( string const & fileName ) throw( Ex, Iconv::Ex ):
encoding( Windows1252 ), iconv( encoding ), readBufferPtr( readBuffer ),
readBufferLeft( 0 )
{
// Since .dz is backwards-compatible with .gz, we use gz- functions to
// read it -- they are much nicer than the dict_data- ones.
f = gzopen( fileName.c_str(), "rb");
if ( !f )
throw exCantOpen( fileName );
// Now try guessing the encoding by reading the first two bytes
unsigned char firstBytes[ 2 ];
if ( gzread( f, firstBytes, sizeof( firstBytes ) ) != sizeof( firstBytes ) )
{
// Apparently the file's too short
gzclose( f );
throw exMalformedDslFile( fileName );
}
bool needExactEncoding = false;
// If the file begins with the dedicated Unicode marker, we just consume
// it. If, on the other hand, it's not, we return the bytes back
if ( firstBytes[ 0 ] == 0xFF && firstBytes[ 1 ] == 0xFE )
encoding = Utf16LE;
else
if ( firstBytes[ 0 ] == 0xFE && firstBytes[ 1 ] == 0xFF )
encoding = Utf16BE;
else
{
if ( firstBytes[ 0 ] && !firstBytes[ 1 ] )
encoding = Utf16LE;
else
if ( !firstBytes[ 0 ] && firstBytes[ 1 ] )
encoding = Utf16BE;
else
{
// Ok, this doesn't look like 16-bit Unicode. We will start with a
// 8-bit encoding with an intent to find out the exact one from
// the header.
needExactEncoding = true;
encoding = Windows1251;
}
if ( gzrewind( f ) )
{
gzclose( f );
throw exCantOpen( fileName );
}
}
iconv.reinit( encoding );
// We now can use our own readNextLine() function
wstring str;
size_t offset;
for( ; ; )
{
if ( !readNextLine( str, offset ) )
{
gzclose( f );
throw exMalformedDslFile( fileName );
}
if ( str.empty() || str[ 0 ] != L'#' )
break;
bool isName = false;
if ( !str.compare( 0, 5, L"#NAME", 5 ) )
isName = true;
else
if ( str.compare( 0, 17, L"#SOURCE_CODE_PAGE", 17 ) )
continue;
// Locate the argument
size_t beg = str.find_first_of( L'"' );
if ( beg == wstring::npos )
throw exMalformedDslFile( fileName );
size_t end = str.find_last_of( L'"' );
if ( end == beg )
throw exMalformedDslFile( fileName );
wstring arg( str, beg + 1, end - beg - 1 );
if ( isName )
dictionaryName = arg;
else
{
// The encoding
if ( !needExactEncoding )
{
// We don't need that!
fprintf( stderr, "Warning: encoding was specified in a Unicode file, ignoring.\n" );
}
else
if ( !wcscasecmp( arg.c_str(), L"Latin" ) )
encoding = Windows1252;
else
if ( !wcscasecmp( arg.c_str(), L"Cyrillic" ) )
encoding = Windows1251;
else
if ( !wcscasecmp( arg.c_str(), L"EasternEuropean" ) )
encoding = Windows1250;
else
{
gzclose( f );
throw exUnknownCodePage();
}
}
}
// The loop will always end up reading a line which was not a #-directive.
// We need to rewind to that line so readNextLine() would return it again
// next time it's called. To do that, we just use the slow gzseek() and
// empty the read buffer.
gzseek( f, offset, SEEK_SET );
readBufferPtr = readBuffer;
readBufferLeft = 0;
if ( needExactEncoding )
iconv.reinit( encoding );
}
DslScanner::~DslScanner() throw()
{
gzclose( f );
}
bool DslScanner::readNextLine( wstring & out, size_t & offset ) throw( Ex,
Iconv::Ex )
{
offset = (size_t)( gztell( f ) - readBufferLeft );
// For now we just read one char at a time
size_t readMultiple = distanceToBytes( 1 );
size_t leftInOut = wcharBuffer.size();
wchar_t * outPtr = &wcharBuffer.front();
for( ; ; )
{
// Check that we have bytes to read
if ( !readBufferLeft )
{
if ( gzeof( f ) )
return false;
// Read some more bytes to readBuffer
int result = gzread( f, readBuffer, sizeof( readBuffer ) );
if ( result == -1 )
throw exCantReadDslFile();
readBufferPtr = readBuffer;
readBufferLeft = (size_t) result;
}
if ( readBufferLeft < readMultiple )
{
// No more data. Return what we've got so far, forget the last byte if
// it was a 16-bit Unicode and a file had an odd number of bytes.
readBufferLeft = 0;
if ( outPtr != &wcharBuffer.front() )
{
// If there was a stray \r, remove it
if ( outPtr[ -1 ] == L'\r' )
--outPtr;
out = wstring( &wcharBuffer.front(), outPtr - &wcharBuffer.front() );
return true;
}
else
return false;
}
// Check that we have chars to write
if ( !leftInOut )
{
wcharBuffer.resize( wcharBuffer.size() + 64 );
outPtr = &wcharBuffer.front() + wcharBuffer.size() - 64;
leftInOut += 64;
}
// Ok, now convert one char
size_t inBytesLeft = readMultiple;
size_t outBytesLeft = sizeof( wchar_t );
if ( iconv.convert( (void const *&)readBufferPtr, inBytesLeft,
(void *&)outPtr, outBytesLeft ) !=
Iconv::Success || inBytesLeft || outBytesLeft )
throw exEncodingError();
readBufferLeft -= readMultiple;
--leftInOut;
// Have we got \n?
if ( outPtr[ -1 ] == L'\n' )
{
--outPtr;
// Now kill a \r if there is one, and return the result.
if ( outPtr != &wcharBuffer.front() && outPtr[ -1 ] == L'\r' )
--outPtr;
out = wstring( &wcharBuffer.front(), outPtr - &wcharBuffer.front() );
return true;
}
}
}
/////////////// DslScanner
DslIconv::DslIconv( DslEncoding e ) throw( Iconv::Ex ):
Iconv( Iconv::Wchar_t, getEncodingNameFor( e ) )
{
}
void DslIconv::reinit( DslEncoding e ) throw( Iconv::Ex )
{
Iconv::reinit( Iconv::Wchar_t, getEncodingNameFor( e ) );
}
char const * DslIconv::getEncodingNameFor( DslEncoding e )
{
switch( e )
{
case Utf16LE:
return "UTF-16LE";
case Utf16BE:
return "UTF-16BE";
case Windows1252:
return "WINDOWS-1252";
case Windows1251:
return "WINDOWS-1251";
case Windows1250:
default:
return "WINDOWS-1250";
}
}
void processUnsortedParts( wstring & str, bool strip )
{
int refCount = 0;
size_t startPos = 0;
for( size_t x = 0; x < str.size(); )
{
wchar_t ch = str[ x ];
if ( ch == L'\\' )
{
// Escape code
x += 2;
continue;
}
if ( ch == '{' )
{
++refCount;
if ( !strip )
{
// Just remove it and continue
str.erase( x, 1 );
continue;
}
else
if ( refCount == 1 )
{
// First opening brace. Save this position, we will be erasing the
// whole range when we encounter the last closing brace.
startPos = x;
}
}
else
if ( ch == '}' )
{
--refCount;
if ( refCount < 0 )
{
fprintf( stderr, "Warning: an unmatched closing brace was encountered.\n" );
refCount = 0;
// But we remove that thing either way
str.erase( x, 1 );
continue;
}
if ( !strip )
{
// Just remove it and continue
str.erase( x, 1 );
continue;
}
else
if ( !refCount )
{
// The final closing brace -- we can erase the whole range now.
str.erase( startPos, x - startPos + 1 );
x = startPos;
continue;
}
}
++x;
}
if ( strip && refCount )
{
fprintf( stderr, "Warning: unclosed brace(s) encountered.\n" );
str.erase( startPos );
}
}
void expandOptionalParts( wstring & str, list< wstring > & result,
size_t x )
{
for( ; x < str.size(); )
{
wchar_t ch = str[ x ];
if ( ch == L'\\' )
{
// Escape code
x += 2;
}
else
if ( ch == L'(' )
{
// First, handle the case where this block is removed
{
int refCount = 1;
for( size_t y = x + 1; y < str.size(); ++y )
{
wchar_t ch = str[ y ];
if ( ch == L'\\' )
{
// Escape code
++y;
}
else
if ( ch == L'(' )
++refCount;
else
if ( ch == L')' )
{
if ( !--refCount )
{
// Now that the closing parenthesis is found,
// cut the whole thing out and be done.
if ( y != x + 1 ) // Only do for non-empty cases
{
wstring removed( str, 0, x );
removed.append( str, y + 1, str.size() - y - 1 );
expandOptionalParts( removed, result, x );
}
break;
}
}
}
if ( refCount && x != str.size() - 1 )
{
// Closing paren not found? Chop it.
wstring removed( str, 0, x );
result.push_back( removed );
}
}
// Now, handling the case where it is kept -- we just erase
// the paren and go on
str.erase( x, 1 );
}
else
if ( ch == L')' )
{
// Closing paren doesn't mean much -- just erase it
str.erase( x, 1 );
}
else
++x;
}
result.push_back( str );
}
void expandTildes( wstring & str, wstring const & tildeReplacement )
{
for( size_t x = 0; x < str.size(); )
if ( str[ x ] == L'\\' )
x+=2;
else
if ( str[ x ] == L'~' )
{
str.replace( x, 1, tildeReplacement );
x += tildeReplacement.size();
}
else
++x;
}
void unescapeDsl( wstring & str )
{
for( size_t x = 0; x < str.size(); ++x )
if ( str[ x ] == L'\\' )
str.erase( x, 1 ); // ++x would skip the next char without processing it
}
}
}

171
src/dsl_details.hh Normal file
View file

@ -0,0 +1,171 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __DSL_DETAILS_HH_INCLUDED__
#define __DSL_DETAILS_HH_INCLUDED__
#include <string>
#include <list>
#include <vector>
#include <zlib.h>
#include "dictionary.hh"
#include "iconv.hh"
// Implementation details for Dsl, not part of its interface
namespace Dsl {
namespace Details {
using std::string;
using std::wstring;
using std::list;
using std::vector;
// Those are possible encodings for .dsl files
enum DslEncoding
{
Utf16LE,
Utf16BE,
Windows1252,
Windows1251,
Windows1250
};
/// Parses the DSL language, representing it in its structural DOM form.
struct ArticleDom
{
struct Node: public list< Node >
{
bool isTag; // true if it is a tag with subnodes, false if it's a leaf text
// data.
// Those are only used if isTag is true
wstring tagName;
wstring tagAttrs;
wstring text; // This is only used if isTag is false
class Text {};
class Tag {};
Node( Tag, wstring const & name, wstring const & attrs ): isTag( true ),
tagName( name ), tagAttrs( attrs )
{}
Node( Text, wstring const & text_ ): isTag( false ), text( text_ )
{}
/// Concatenates all childen text nodes recursively to form all text
/// the node contains stripped of any markup.
wstring renderAsText() const;
};
/// Does the parse at construction. Refer to the 'root' member variable
/// afterwards.
ArticleDom( wstring const & );
/// Root of DOM's tree
Node root;
private:
wchar_t const * stringPos;
class eot {};
wchar_t ch;
bool escaped;
void nextChar() throw( eot );
};
/// A adapted version of Iconv which takes Dsl encoding and decodes to wchar_t.
class DslIconv: public Iconv
{
public:
DslIconv( DslEncoding ) throw( Iconv::Ex );
void reinit( DslEncoding ) throw( Iconv::Ex );
/// Returns a name to be passed to iconv for the given dsl encoding.
static char const * getEncodingNameFor( DslEncoding );
};
/// Opens the .dsl or .dsl.dz file and allows line-by-line reading. Auto-detects
/// the encoding, and reads all headers by itself.
class DslScanner
{
gzFile f;
DslEncoding encoding;
DslIconv iconv;
wstring dictionaryName;
char readBuffer[ 65536 ];
char * readBufferPtr;
size_t readBufferLeft;
vector< wchar_t > wcharBuffer;
public:
DEF_EX( Ex, "Dsl scanner exception", Dictionary::Ex )
DEF_EX_STR( exCantOpen, "Can't open .dsl file", Ex )
DEF_EX( exCantReadDslFile, "Can't read .dsl file", Ex )
DEF_EX_STR( exMalformedDslFile, "The .dsl file is malformed:", Ex )
DEF_EX( exUnknownCodePage, "The .dsl file specified an unknown code page", Ex )
DEF_EX( exEncodingError, "Encoding error", Ex ) // Should never happen really
DslScanner( string const & fileName ) throw( Ex, Iconv::Ex );
~DslScanner() throw();
/// Returns the detected encoding of this file.
DslEncoding getEncoding() const
{ return encoding; }
/// Returns the dictionary's name, as was read from file's headers.
wstring const & getDictionaryName() const
{ return dictionaryName; }
/// Reads next line from the file. Returns true if reading succeeded --
/// the string gets stored in the one passed, along with its physical
/// file offset in the file (the uncompressed one if the file is compressed).
/// If end of file is reached, false is returned.
/// Reading begins from the first line after the headers (ones which start
/// with #).
bool readNextLine( wstring &, size_t & offset ) throw( Ex, Iconv::Ex );
/// Converts the given number of characters to the number of bytes they
/// would occupy in the file, knowing its encoding. It's possible to know
/// that because no multibyte encodings are supported in .dsls.
inline size_t distanceToBytes( size_t ) const;
};
/// This function either removes parts of string enclosed in braces, or leaves
/// them intact. The braces themselves are removed always, though.
void processUnsortedParts( wstring & str, bool strip );
/// Expands optional parts of a headword (ones marked with parentheses),
/// producing all possible combinations where they are present or absent.
void expandOptionalParts( wstring & str, list< wstring > & result,
size_t x = 0 );
/// Expands all unescaped tildes, inserting tildeReplacement text instead of
/// them.
void expandTildes( wstring & str, wstring const & tildeReplacement );
// Unescapes any escaped chars. Be sure to handle all their special meanings
// before unescaping them.
void unescapeDsl( wstring & str );
inline size_t DslScanner::distanceToBytes( size_t x ) const
{
switch( encoding )
{
case Utf16LE:
case Utf16BE:
return x*2;
default:
return x;
}
}
}
}
#endif

37
src/ex.hh Normal file
View file

@ -0,0 +1,37 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __EX_HH_INCLUDED__
#define __EX_HH_INCLUDED__
#include <string>
/// A way to declare an exception class fast
/// Do like this:
/// DEF_EX( exErrorInFoo, "An error in foo encountered", std::exception )
/// DEF_EX( exFooNotFound, "Foo was not found", exErrorInFoo )
#define DEF_EX( exName, exDescription, exParent ) \
class exName: public exParent { \
public: \
virtual const char * what() const throw() { return (exDescription); } \
virtual ~exName() throw() {} };
/// Same as DEF_EX, but takes a runtime string argument, which gets concatenated
/// with the description.
///
/// DEF_EX_STR( exCantOpen, "can't open file", std::exception )
/// ...
/// throw exCantOpen( "example.txt" );
///
/// what() would return "can't open file example.txt"
#define DEF_EX_STR( exName, exDescription, exParent ) \
class exName: public exParent { \
std::string value; \
public: \
exName( std::string const & value_ ): value( std::string( exDescription ) + " " + value_ ) {} \
virtual const char * what() const throw() { return value.c_str(); } \
virtual ~exName() throw() {} };
#endif

61
src/externalviewer.cc Normal file
View file

@ -0,0 +1,61 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "externalviewer.hh"
#include <QDir>
using std::vector;
ExternalViewer::ExternalViewer( QObject * parent, vector< char > const & data,
QString const & extension,
QString const & viewerProgram_ )
throw( exCantCreateTempFile ):
QObject( parent ),
tempFile( QDir::temp().filePath( QString( "gd-XXXXXXXX." ) + extension ) ),
viewer( this ),
viewerProgram( viewerProgram_ )
{
if ( !tempFile.open() || tempFile.write( &data.front(), data.size() ) != data.size() )
throw exCantCreateTempFile();
tempFileName = tempFile.fileName(); // For some reason it loses it after it was closed()
tempFile.close();
printf( "%s\n", tempFile.fileName().toLocal8Bit().data() );
connect( &viewer, SIGNAL( finished( int, QProcess::ExitStatus ) ),
this, SLOT( viewerFinished( int, QProcess::ExitStatus ) ) );
connect( this, SIGNAL( finished( ExternalViewer * ) ),
&ExternalViewerDeleter::instance(), SLOT( deleteExternalViewer( ExternalViewer * ) ),
Qt::QueuedConnection );
}
void ExternalViewer::start() throw( exCantRunViewer )
{
viewer.start( viewerProgram, QStringList( tempFileName ), QIODevice::NotOpen );
if ( !viewer.waitForStarted() )
throw exCantRunViewer( viewerProgram.toStdString() );
}
void ExternalViewer::viewerFinished( int, QProcess::ExitStatus )
{
emit finished( this );
}
ExternalViewerDeleter & ExternalViewerDeleter::instance()
{
static ExternalViewerDeleter evd( 0 );
return evd;
}
void ExternalViewerDeleter::deleteExternalViewer( ExternalViewer * e )
{
printf( "Deleting external viewer\n" );
delete e;
}

63
src/externalviewer.hh Normal file
View file

@ -0,0 +1,63 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __EXTERNALVIEWER_HH_INCLUDED__
#define __EXTERNALVIEWER_HH_INCLUDED__
#include <QObject>
#include <QTemporaryFile>
#include <QProcess>
#include <vector>
#include "ex.hh"
/// An external viewer, opens resources in other programs
class ExternalViewer: public QObject
{
Q_OBJECT
QTemporaryFile tempFile;
QProcess viewer;
QString viewerProgram;
QString tempFileName;
public:
DEF_EX( Ex, "External viewer exception", std::exception )
DEF_EX( exCantCreateTempFile, "Couldn't create temporary file.", Ex )
DEF_EX_STR( exCantRunViewer, "Couldn't run external viewer:", Ex )
ExternalViewer( QObject * parent, std::vector< char > const & data,
QString const & extension, QString const & viewerProgram )
throw( exCantCreateTempFile );
void start() throw( exCantRunViewer );
private slots:
void viewerFinished( int, QProcess::ExitStatus );
signals:
void finished( ExternalViewer * );
};
class ExternalViewerDeleter: public QObject
{
Q_OBJECT
public:
static ExternalViewerDeleter & instance();
public slots:
void deleteExternalViewer( ExternalViewer * e );
private:
ExternalViewerDeleter( QObject * parent ): QObject( parent )
{}
};
#endif

268
src/file.cc Normal file
View file

@ -0,0 +1,268 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "file.hh"
#include <cstring>
#include <cerrno>
namespace File {
enum
{
// We employ a writing buffer to considerably speed up file operations when
// they consists of many small writes. The default size for the buffer is 64k
WriteBufferSize = 65536
};
void Class::open( char const * filename, char const * mode ) throw( exCantOpen )
{
f = fopen( filename, mode );
if ( !f )
throw exCantOpen( std::string( filename ) + ": " + strerror( errno ) );
}
Class::Class( char const * filename, char const * mode ) throw( exCantOpen ):
writeBuffer( 0 )
{
open( filename, mode );
}
Class::Class( std::string const & filename, char const * mode )
throw( exCantOpen ): writeBuffer( 0 )
{
open( filename.c_str(), mode );
}
void Class::read( void * buf, size_t size ) throw( exReadError, exWriteError )
{
if ( !size )
return;
if ( writeBuffer )
flushWriteBuffer();
size_t result = fread( buf, size, 1, f );
if ( result != 1 )
throw exReadError();
}
size_t Class::readRecords( void * buf, size_t size, size_t count ) throw( exWriteError )
{
if ( writeBuffer )
flushWriteBuffer();
return fread( buf, size, count, f );
}
void Class::write( void const * buf, size_t size ) throw( exWriteError )
{
if ( !size )
return;
if ( size >= WriteBufferSize )
{
// If the write is large, there's not much point in buffering
flushWriteBuffer();
size_t result = fwrite( buf, size, 1, f );
if ( result != 1 )
throw exWriteError();
return;
}
if ( !writeBuffer )
{
// Allocate the writing buffer since we don't have any yet
writeBuffer = new char[ WriteBufferSize ];
writeBufferLeft = WriteBufferSize;
}
size_t toAdd = size < writeBufferLeft ? size : writeBufferLeft;
memcpy( writeBuffer + ( WriteBufferSize - writeBufferLeft ),
buf, toAdd );
size -= toAdd;
writeBufferLeft -= toAdd;
if ( !writeBufferLeft ) // Out of buffer? Flush it.
{
flushWriteBuffer();
if ( size ) // Something's still left? Add to buffer.
{
memcpy( writeBuffer, (char const *)buf + toAdd, size );
writeBufferLeft -= size;
}
}
}
size_t Class::writeRecords( void const * buf, size_t size, size_t count )
throw( exWriteError )
{
flushWriteBuffer();
return fwrite( buf, size, count, f );
}
char * Class::gets( char * s, int size, bool stripNl )
throw( exWriteError )
{
if ( writeBuffer )
flushWriteBuffer();
char * result = fgets( s, size, f );
if ( result && stripNl )
{
size_t len = strlen( result );
char * last = result + len;
while( len-- )
{
--last;
if ( *last == '\n' || *last == '\r' )
*last = 0;
else
break;
}
}
return result;
}
std::string Class::gets( bool stripNl ) throw( exReadError, exWriteError )
{
char buf[ 1024 ];
if ( !gets( buf, sizeof( buf ), stripNl ) )
throw exReadError();
return std::string( buf );
}
void Class::seek( long offset ) throw( exSeekError, exWriteError )
{
if ( writeBuffer )
flushWriteBuffer();
if ( fseek( f, offset, SEEK_SET ) != 0 )
throw exSeekError();
}
void Class::seekCur( long offset ) throw( exSeekError, exWriteError )
{
if ( writeBuffer )
flushWriteBuffer();
if ( fseek( f, offset, SEEK_CUR ) != 0 )
throw exSeekError();
}
void Class::seekEnd( long offset ) throw( exSeekError, exWriteError )
{
if ( writeBuffer )
flushWriteBuffer();
if ( fseek( f, offset, SEEK_END ) != 0 )
throw exSeekError();
}
void Class::rewind() throw( exSeekError, exWriteError )
{
seek( 0 );
}
size_t Class::tell() throw( exSeekError )
{
long result = ftell( f );
if ( result == -1 )
throw exSeekError();
if ( writeBuffer )
result += ( WriteBufferSize - writeBufferLeft );
return ( size_t ) result;
}
bool Class::eof() throw( exWriteError )
{
if ( writeBuffer )
flushWriteBuffer();
return feof( f );
}
FILE * Class::file() throw( exWriteError )
{
flushWriteBuffer();
return f;
}
FILE * Class::release() throw( exWriteError )
{
releaseWriteBuffer();
FILE * c = f;
f = 0;
return c;
}
void Class::close() throw( exWriteError )
{
fclose( release() );
}
Class::~Class() throw()
{
if ( f )
{
try
{
releaseWriteBuffer();
}
catch( exWriteError & )
{
}
fclose( f );
}
}
void Class::flushWriteBuffer() throw( exWriteError )
{
if ( writeBuffer && writeBufferLeft != WriteBufferSize )
{
size_t result = fwrite( writeBuffer, WriteBufferSize - writeBufferLeft, 1, f );
if ( result != 1 )
throw exWriteError();
writeBufferLeft = WriteBufferSize;
}
}
void Class::releaseWriteBuffer() throw( exWriteError )
{
flushWriteBuffer();
if ( writeBuffer )
{
delete [] writeBuffer;
writeBuffer = 0;
}
}
}

117
src/file.hh Normal file
View file

@ -0,0 +1,117 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __FILE_HH_INCLUDED__
#define __FILE_HH_INCLUDED__
#include <cstdio>
#include <string>
#include "ex.hh"
/// A simple wrapper over FILE * operations with added write-buffering,
/// used for non-Qt parts of code.
/// It is possible to ifdef implementation details for some platforms.
namespace File {
DEF_EX( Ex, "File exception", std::exception )
DEF_EX_STR( exCantOpen, "Can't open", Ex )
DEF_EX( exReadError, "Error reading from the file", Ex )
DEF_EX( exWriteError, "Error writing to the file", Ex )
DEF_EX( exSeekError, "File seek error", Ex )
class Class
{
FILE * f;
char * writeBuffer;
size_t writeBufferLeft;
void open( char const * filename, char const * mode ) throw( exCantOpen );
public:
Class( char const * filename, char const * mode ) throw( exCantOpen );
Class( std::string const & filename, char const * mode ) throw( exCantOpen );
/// Reads the number of bytes to the buffer, throws an error if it
/// failed to fill the whole buffer (short read, i/o error etc).
void read( void * buf, size_t size ) throw( exReadError, exWriteError );
template< typename T >
void read( T & value ) throw( exReadError, exWriteError )
{ read( &value, sizeof( value ) ); }
template< typename T >
T read() throw( exReadError, exWriteError )
{ T value; read( value ); return value; }
/// Attempts reading at most 'count' records sized 'size'. Returns
/// the number of records it managed to read, up to 'count'.
size_t readRecords( void * buf, size_t size, size_t count ) throw( exWriteError );
/// Writes the number of bytes from the buffer, throws an error if it
/// failed to write the whole buffer (short write, i/o error etc).
/// This function employs write buffering, and as such, writes may not
/// end up on disk immediately, or a short write may occur later
/// than it really did. If you don't want write buffering, use
/// writeRecords() function instead.
void write( void const * buf, size_t size ) throw( exWriteError );
template< typename T >
void write( T const & value ) throw( exWriteError )
{ write( &value, sizeof( value ) ); }
/// Attempts writing at most 'count' records sized 'size'. Returns
/// the number of records it managed to write, up to 'count'.
/// This function does not employ buffering, but flushes the buffer if it
/// was used before.
size_t writeRecords( void const * buf, size_t size, size_t count )
throw( exWriteError );
/// Reads a string from the file. Unlike the normal fgets(), this one
/// can strip the trailing newline character, if this was requested.
/// Returns either s or 0 if no characters were read.
char * gets( char * s, int size, bool stripNl = false ) throw( exWriteError );
/// Like the above, but uses its own local internal buffer (1024 bytes
/// currently), and strips newlines by default.
std::string gets( bool stripNl = true ) throw( exReadError, exWriteError );
/// Seeks in the file, relative to its beginning.
void seek( long offset ) throw( exSeekError, exWriteError );
/// Seeks in the file, relative to the current position.
void seekCur( long offset ) throw( exSeekError, exWriteError );
/// Seeks in the file, relative to the end of file.
void seekEnd( long offset = 0 ) throw( exSeekError, exWriteError );
/// Seeks to the beginning of file
void rewind() throw( exSeekError, exWriteError );
/// Tells the current position within the file, relative to its beginning.
size_t tell() throw( exSeekError );
/// Returns true if end-of-file condition is set.
bool eof() throw( exWriteError );
/// Returns the underlying FILE * record, so other operations can be
/// performed on it.
FILE * file() throw( exWriteError );
/// Releases the file handle out of the control of the class. No further
/// operations are valid. The file will not be closed on destruction.
FILE * release() throw( exWriteError );
/// Closes the file. No further operations are valid.
void close() throw( exWriteError );
~Class() throw();
private:
void flushWriteBuffer() throw( exWriteError );
void releaseWriteBuffer() throw( exWriteError );
};
}
#endif

85
src/filetype.cc Normal file
View file

@ -0,0 +1,85 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#include "filetype.hh"
#include <ctype.h>
namespace Filetype {
namespace {
/// Removes any trailing or leading spaces and lowercases the string.
/// The lowercasing is done simplistically, but it is enough for file
/// extensions.
string simplifyString( string const & str )
{
string result;
size_t beginPos = 0;
while( beginPos < str.size() && isblank( str[ beginPos ] ) );
size_t endPos = str.size();
while( endPos && isblank( str[ endPos - 1 ] ) )
--endPos;
result.reserve( endPos - beginPos );
while( beginPos < endPos )
result.push_back( tolower( str[ beginPos++ ] ) );
return result;
}
/// Checks if the given string ends with the given substring
bool endsWith( string const & str, string const & tail )
{
return str.size() >= tail.size() &&
str.compare( str.size() - tail.size(), tail.size(), tail ) == 0;
}
}
bool isNameOfSound( string const & name )
{
string s = simplifyString( name );
return
endsWith( s, ".wav" ) ||
endsWith( s, ".au" ) ||
endsWith( s, ".voc" ) ||
endsWith( s, ".ogg" ) ||
endsWith( s, ".mp3" );
}
bool isNameOfPicture( string const & name )
{
string s = simplifyString( name );
return
endsWith( s, ".jpg" ) ||
endsWith( s, ".jpeg" ) ||
endsWith( s, ".jpe" ) ||
endsWith( s, ".png" ) ||
endsWith( s, ".gif" ) ||
endsWith( s, ".bmp" ) ||
endsWith( s, ".tif" ) ||
endsWith( s, ".tiff" ) ||
endsWith( s, ".tga" ) ||
endsWith( s, ".pcx" ) ||
endsWith( s, ".ico" ) ||
endsWith( s, ".svg" );
}
bool isNameOfTiff( string const & name )
{
string s = simplifyString( name );
return
endsWith( s, ".tif" ) ||
endsWith( s, ".tiff" );
}
}

28
src/filetype.hh Normal file
View file

@ -0,0 +1,28 @@
/* This file is (c) 2008-2009 Konstantin Isakov <ikm@users.sf.net>
* Part of GoldenDict. Licensed under GPLv3 or later, see the LICENSE file */
#ifndef __FILETYPE_HH_INCLUDED__
#define __FILETYPE_HH_INCLUDED__
#include <string>
/// Utilities to guess file types based on their names.
namespace Filetype {
using std::string;
/// Returns true if the name resembles the one of a sound file (i.e. ends
/// with .wav, .ogg and such).
bool isNameOfSound( string const & );
/// Returns true if the name resembles the one of a picture file (i.e. ends
/// with .jpg, .png and such).
bool isNameOfPicture( string const & );
/// Returns true if the name resembles the one of a .tiff file (i.e. ends
/// with .tif or tiff). We have this one separately since we need to reconvert
/// TIFF files as WebKit doesn't seem to support them.
bool isNameOfTiff( string const & );
}
#endif

251
src/flags.qrc Normal file
View file

@ -0,0 +1,251 @@
<RCC>
<qresource>
<file>flags/ad.png</file>
<file>flags/ae.png</file>
<file>flags/af.png</file>
<file>flags/ag.png</file>
<file>flags/ai.png</file>
<file>flags/al.png</file>
<file>flags/am.png</file>
<file>flags/an.png</file>
<file>flags/ao.png</file>
<file>flags/ar.png</file>
<file>flags/as.png</file>
<file>flags/at.png</file>
<file>flags/au.png</file>
<file>flags/aw.png</file>
<file>flags/ax.png</file>
<file>flags/az.png</file>
<file>flags/ba.png</file>
<file>flags/bb.png</file>
<file>flags/bd.png</file>
<file>flags/be.png</file>
<file>flags/bf.png</file>
<file>flags/bg.png</file>
<file>flags/bh.png</file>
<file>flags/bi.png</file>
<file>flags/bj.png</file>
<file>flags/bm.png</file>
<file>flags/bn.png</file>
<file>flags/bo.png</file>
<file>flags/br.png</file>
<file>flags/bs.png</file>
<file>flags/bt.png</file>
<file>flags/bv.png</file>
<file>flags/bw.png</file>
<file>flags/by.png</file>
<file>flags/bz.png</file>
<file>flags/ca.png</file>
<file>flags/catalonia.png</file>
<file>flags/cc.png</file>
<file>flags/cd.png</file>
<file>flags/cf.png</file>
<file>flags/cg.png</file>
<file>flags/ch.png</file>
<file>flags/ci.png</file>
<file>flags/ck.png</file>
<file>flags/cl.png</file>
<file>flags/cm.png</file>
<file>flags/cn.png</file>
<file>flags/co.png</file>
<file>flags/cr.png</file>
<file>flags/cs.png</file>
<file>flags/cu.png</file>
<file>flags/cv.png</file>
<file>flags/cx.png</file>
<file>flags/cy.png</file>
<file>flags/cz.png</file>
<file>flags/de.png</file>
<file>flags/dj.png</file>
<file>flags/dk.png</file>
<file>flags/dm.png</file>
<file>flags/do.png</file>
<file>flags/dz.png</file>
<file>flags/ec.png</file>
<file>flags/ee.png</file>
<file>flags/eg.png</file>
<file>flags/eh.png</file>
<file>flags/england.png</file>
<file>flags/er.png</file>
<file>flags/es.png</file>
<file>flags/et.png</file>
<file>flags/europeanunion.png</file>
<file>flags/fam.png</file>
<file>flags/fi.png</file>
<file>flags/fj.png</file>
<file>flags/fk.png</file>
<file>flags/fm.png</file>
<file>flags/fo.png</file>
<file>flags/fr.png</file>
<file>flags/ga.png</file>
<file>flags/gb.png</file>
<file>flags/gd.png</file>
<file>flags/ge.png</file>
<file>flags/gf.png</file>
<file>flags/gh.png</file>
<file>flags/gi.png</file>
<file>flags/gl.png</file>
<file>flags/gm.png</file>
<file>flags/gn.png</file>
<file>flags/gp.png</file>
<file>flags/gq.png</file>
<file>flags/gr.png</file>
<file>flags/gs.png</file>
<file>flags/gt.png</file>
<file>flags/gu.png</file>
<file>flags/gw.png</file>
<file>flags/gy.png</file>
<file>flags/hk.png</file>
<file>flags/hm.png</file>
<file>flags/hn.png</file>
<file>flags/hr.png</file>
<file>flags/ht.png</file>
<file>flags/hu.png</file>
<file>flags/id.png</file>
<file>flags/ie.png</file>
<file>flags/il.png</file>
<file>flags/in.png</file>
<file>flags/io.png</file>
<file>flags/iq.png</file>
<file>flags/ir.png</file>
<file>flags/is.png</file>
<file>flags/it.png</file>
<file>flags/jm.png</file>
<file>flags/jo.png</file>
<file>flags/jp.png</file>
<file>flags/ke.png</file>
<file>flags/kg.png</file>
<file>flags/kh.png</file>
<file>flags/ki.png</file>
<file>flags/km.png</file>
<file>flags/kn.png</file>
<file>flags/kp.png</file>
<file>flags/kr.png</file>
<file>flags/kw.png</file>
<file>flags/ky.png</file>
<file>flags/kz.png</file>
<file>flags/la.png</file>
<file>flags/lb.png</file>
<file>flags/lc.png</file>
<file>flags/li.png</file>
<file>flags/lk.png</file>
<file>flags/lr.png</file>
<file>flags/ls.png</file>
<file>flags/lt.png</file>
<file>flags/lu.png</file>
<file>flags/lv.png</file>
<file>flags/ly.png</file>
<file>flags/ma.png</file>
<file>flags/mc.png</file>
<file>flags/md.png</file>
<file>flags/me.png</file>
<file>flags/mg.png</file>
<file>flags/mh.png</file>
<file>flags/mk.png</file>
<file>flags/ml.png</file>
<file>flags/mm.png</file>
<file>flags/mn.png</file>
<file>flags/mo.png</file>
<file>flags/mp.png</file>
<file>flags/mq.png</file>
<file>flags/mr.png</file>
<file>flags/ms.png</file>
<file>flags/mt.png</file>
<file>flags/mu.png</file>
<file>flags/mv.png</file>
<file>flags/mw.png</file>
<file>flags/mx.png</file>
<file>flags/my.png</file>
<file>flags/mz.png</file>
<file>flags/na.png</file>
<file>flags/nc.png</file>
<file>flags/ne.png</file>
<file>flags/nf.png</file>
<file>flags/ng.png</file>
<file>flags/ni.png</file>
<file>flags/nl.png</file>
<file>flags/no.png</file>
<file>flags/np.png</file>
<file>flags/nr.png</file>
<file>flags/nu.png</file>
<file>flags/nz.png</file>
<file>flags/om.png</file>
<file>flags/pa.png</file>
<file>flags/pe.png</file>
<file>flags/pf.png</file>
<file>flags/pg.png</file>
<file>flags/ph.png</file>
<file>flags/pk.png</file>
<file>flags/pl.png</file>
<file>flags/pm.png</file>
<file>flags/pn.png</file>
<file>flags/pr.png</file>
<file>flags/ps.png</file>
<file>flags/pt.png</file>
<file>flags/pw.png</file>
<file>flags/py.png</file>
<file>flags/qa.png</file>
<file>flags/re.png</file>
<file>flags/ro.png</file>
<file>flags/rs.png</file>
<file>flags/ru.png</file>
<file>flags/rw.png</file>
<file>flags/sa.png</file>
<file>flags/sb.png</file>
<file>flags/scotland.png</file>
<file>flags/sc.png</file>
<file>flags/sd.png</file>
<file>flags/se.png</file>
<file>flags/sg.png</file>
<file>flags/sh.png</file>
<file>flags/si.png</file>
<file>flags/sj.png</file>
<file>flags/sk.png</file>
<file>flags/sl.png</file>
<file>flags/sm.png</file>
<file>flags/sn.png</file>
<file>flags/so.png</file>
<file>flags/sr.png</file>
<file>flags/st.png</file>
<file>flags/sv.png</file>
<file>flags/sy.png</file>
<file>flags/sz.png</file>
<file>flags/tc.png</file>
<file>flags/td.png</file>
<file>flags/tf.png</file>
<file>flags/tg.png</file>
<file>flags/th.png</file>
<file>flags/tj.png</file>
<file>flags/tk.png</file>
<file>flags/tl.png</file>
<file>flags/tm.png</file>
<file>flags/tn.png</file>
<file>flags/to.png</file>
<file>flags/tr.png</file>
<file>flags/tt.png</file>
<file>flags/tv.png</file>
<file>flags/tw.png</file>
<file>flags/tz.png</file>
<file>flags/ua.png</file>
<file>flags/ug.png</file>
<file>flags/um.png</file>
<file>flags/us.png</file>
<file>flags/uy.png</file>
<file>flags/uz.png</file>
<file>flags/va.png</file>
<file>flags/vc.png</file>
<file>flags/ve.png</file>
<file>flags/vg.png</file>
<file>flags/vi.png</file>
<file>flags/vn.png</file>
<file>flags/vu.png</file>
<file>flags/wales.png</file>
<file>flags/wf.png</file>
<file>flags/ws.png</file>
<file>flags/ye.png</file>
<file>flags/yt.png</file>
<file>flags/za.png</file>
<file>flags/zm.png</file>
<file>flags/zw.png</file>
</qresource>
</RCC>

6
src/flags/00readme.txt Normal file
View file

@ -0,0 +1,6 @@
These icons were taken from http://www.famfamfam.com/lab/icons/flags/
Licensed under the following conditions:
"These flag icons are available for free use for any purpose with no
requirement for attribution."

BIN
src/flags/ad.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 643 B

BIN
src/flags/ae.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 408 B

BIN
src/flags/af.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 604 B

BIN
src/flags/ag.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 591 B

BIN
src/flags/ai.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 643 B

BIN
src/flags/al.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 600 B

BIN
src/flags/am.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 497 B

BIN
src/flags/an.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 488 B

BIN
src/flags/ao.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 428 B

BIN
src/flags/ar.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 506 B

BIN
src/flags/as.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 647 B

BIN
src/flags/at.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 403 B

BIN
src/flags/au.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 673 B

BIN
src/flags/aw.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 524 B

BIN
src/flags/ax.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 663 B

BIN
src/flags/az.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 589 B

BIN
src/flags/ba.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 593 B

BIN
src/flags/bb.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 585 B

BIN
src/flags/bd.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 504 B

BIN
src/flags/be.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 449 B

BIN
src/flags/bf.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 497 B

BIN
src/flags/bg.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 462 B

BIN
src/flags/bh.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 457 B

BIN
src/flags/bi.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 675 B

BIN
src/flags/bj.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 486 B

BIN
src/flags/bm.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 611 B

BIN
src/flags/bn.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 639 B

BIN
src/flags/bo.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 500 B

BIN
src/flags/br.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 593 B

BIN
src/flags/bs.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 526 B

BIN
src/flags/bt.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 631 B

BIN
src/flags/bv.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 512 B

BIN
src/flags/bw.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 443 B

BIN
src/flags/by.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 514 B

BIN
src/flags/bz.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 600 B

BIN
src/flags/ca.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 628 B

BIN
src/flags/catalonia.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 398 B

BIN
src/flags/cc.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 625 B

BIN
src/flags/cd.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 528 B

BIN
src/flags/cf.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 614 B

BIN
src/flags/cg.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 521 B

BIN
src/flags/ch.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 367 B

BIN
src/flags/ci.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 453 B

BIN
src/flags/ck.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 586 B

BIN
src/flags/cl.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 450 B

BIN
src/flags/cm.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 525 B

BIN
src/flags/cn.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 472 B

BIN
src/flags/co.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 483 B

BIN
src/flags/cr.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 477 B

BIN
src/flags/cs.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 439 B

BIN
src/flags/cu.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 563 B

BIN
src/flags/cv.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 529 B

BIN
src/flags/cx.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 608 B

BIN
src/flags/cy.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 428 B

BIN
src/flags/cz.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 476 B

BIN
src/flags/de.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 545 B

BIN
src/flags/dj.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 572 B

BIN
src/flags/dk.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 495 B

BIN
src/flags/dm.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 620 B

BIN
src/flags/do.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 508 B

BIN
src/flags/dz.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 582 B

BIN
src/flags/ec.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 500 B

BIN
src/flags/ee.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 429 B

BIN
src/flags/eg.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 465 B

Some files were not shown because too many files have changed in this diff Show more