pax_global_header 0000666 0000000 0000000 00000000064 12454273704 0014522 g ustar 00root root 0000000 0000000 52 comment=22bd2bf61d2dabee08f68413b6a8ff3cd4df4565
xapers-0.6/ 0000775 0000000 0000000 00000000000 12454273704 0012671 5 ustar 00root root 0000000 0000000 xapers-0.6/.gitignore 0000664 0000000 0000000 00000000044 12454273704 0014657 0 ustar 00root root 0000000 0000000 *~
*.pyc
dist
build
xapers.egg-info
xapers-0.6/COPYING 0000664 0000000 0000000 00000001213 12454273704 0013721 0 ustar 00root root 0000000 0000000 Xapers 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, (in the COPYING-GPL-3 file in this
directory). If not, see http://www.gnu.org/licenses/
xapers-0.6/COPYING-GPL-3 0000664 0000000 0000000 00000104374 12454273704 0014515 0 ustar 00root root 0000000 0000000
GNU GENERAL PUBLIC LICENSE
Version 3, 29 June 2007
Copyright (C) 2007 Free Software Foundation, Inc.
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU 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.
Copyright (C)
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 .
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:
Copyright (C)
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
.
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
.
xapers-0.6/Makefile 0000664 0000000 0000000 00000001725 12454273704 0014336 0 ustar 00root root 0000000 0000000 # -*- makefile -*-
VERSION:=$(shell git describe --tags | sed -e s/_/~/ -e s/-/+/ -e s/-/~/)
PV_FILE=lib/xapers/version.py
.PHONY: all
all:
.PHONY: test
test:
./test/xapers-test
.PHONY: update-version
update-version:
echo "__version__ = '$(VERSION)'" >$(PV_FILE)
.PHONY: release
ifdef V
update-version: VERSION:=$(V)
release: VERSION:=$(V)
release: update-version
make test
git commit -m "Update version for release $(VERSION)." $(PV_FILE)
git tag --sign -m "Xapers $(VERSION) release." $(VERSION)
else
release:
git tag -l | grep -v debian/
endif
.PHONY: deb-snapshot
deb-snapshot:
rm -rf build/snapshot
mkdir -p build/snapshot/debian
git archive HEAD | tar -x -C build/snapshot/
git archive debian:debian | tar -x -C build/snapshot/debian/
cd build/snapshot; make update-version
cd build/snapshot; dch -b -v $(VERSION) -D UNRELEASED 'test build, not for upload'
cd build/snapshot; echo '3.0 (native)' > debian/source/format
cd build/snapshot; debuild -us -uc
xapers-0.6/NEWS 0000664 0000000 0000000 00000002037 12454273704 0013372 0 ustar 00root root 0000000 0000000 Xapers 0.6 (2015-01-10)
=======================
* lib: Document year is now indexed as a proper value, supporting both
'year:' binary and 'year:..' range searches. Will
require running 'restore' from the cli to re-index previously added
articles. Thanks to Rafael Laboissi猫re for the contribution.
* lib: Much improved performance of Document prefixed term retrieval.
* cli: Much improved search output performance. Default output limit
of 20 has been removed.
* nci: Curses interface now loads entries dynamically, so search
results are no longer limited.
* nci: Cleaner results display. Document 'summary' has been removed,
but other information has been added, such as journal article, year,
file info, and document match information.
* nci: Extended navigation commands.
* sources: Now support PDF download from sources, if the source
supports it.
* sources: New IACR 'crytoeprint' source. Thanks to Daniel Kahn
Gillmor for the contribution.
* Other cleanup, bug fixes, and performance improvements.
xapers-0.6/README 0000664 0000000 0000000 00000011270 12454273704 0013552 0 ustar 00root root 0000000 0000000 Xapers - personal journal article management system
===================================================
Xapers is a personal document indexing system, geared towards academic
journal articles. Think of it as your own personal document search
engine, or a local cache of online libraries. It provides fast search
of document text and bibliographic data and simple document and bibtex
retrieval.
Document files (in PDF format) and source identifiers (e.g. DOI) are
parsed and indexed into a Xapian search engine [0]. Document text is
extracted from the PDF and fully indexed. Bibliographic information
downloaded from online libraries is indexed as prefixed search terms.
Existing bibtex databases can be easily imported as well, including
import of pdf files specified in Jabref/Mendeley format. Documents
can be arbitrarily tagged. Original document files are easily
retrievable from a simple curses search UI. The command line
interface allows for exporting bibtex [1] from arbitrary searches,
allowing seamless integration into LaTeX work flows.
Xapers provides source modules for some common online libraries:
* DOI: http://www.doi.org/
* arXiv: http://arxiv.org/
Contributions of additional source interface modules is highly
encouraged. See the SOURCES file, included with the xapers source,
for info on creating new sources.
Xapers is heavily inspired by the notmuch mail indexing system [2].
[0] http://www.xapian.org/
[1] http://www.bibtex.org/
[2] http://notmuchmail.org/
Contact
=======
Xapers was written by:
Jameson Graef Rollins
Xapers has a mailing list:
xapers@lists.mayfirst.org
https://lists.mayfirst.org/mailman/listinfo/xapers
We also hang out on IRC:
channel: #xapers
server: irc.oftc.net
Getting Xapers
==============
Source
------
Clone the repo:
$ git clone git://finestructure.net/xapers
$ cd xapers
Dependencies :
* python (>= 2.6)
* python-xapian - Python Xapian search engine bindings
* pybtex - Python bibtex parser
Recommends (for curses UI) :
* poppler-utils - PDF processing tools
* pycurl - Python bindings to libcurl
* python-urwid - Python Urwid curses library
* xdg-utils - Desktop tools for opening files and URLs
* xclip - X clipboard support for copying document fields
On Debian:
$ sudo apt-get install python-xapian poppler-utils python-pycurl pybtex python-urwid xdg-utils xclip
Run the tests:
$ make test
Debian
------
Debian/Ubuntu snapshot packages can be easily made from the git
source. You can build the package from any branch but it requires an
up-to-date local branch of origin/debian, e.g.:
$ git branch debian origin/debian
Then:
$ sudo apt-get install build-essential devscripts pkg-config python-all-dev python-setuptools debhelper dpkg-dev fakeroot
$ make debian-snapshot
$ sudo dpkg -i build/xapers_0.1_amd64.deb
Using Xapers
============
See the included xapers(1) man page for detailed usage and information
on source modules and searching.
Command line interface
----------------------
The main interface to Xapers is the xapers command line utility. From
this interface you can import documents, search, tag, etc.
The "add" command allows importing or updating single documents with
sources. The "import" command allows importing an entire bibtex
databases (.bib file). If the bibtex entries include "file" fields
(ala. Mendeley or Jabref), then those files are retrieved, indexed,
and imported as well.
Curses interface
----------------
The curses interface (accessed through 'xapers show ...') provides a
simple way to search the database and retrieve files. Documents
matching searches are displayed with their bibliographic information
and a short text summary. Document tags can be manipulated, files can
be viewed, and source URLs can be opened in a browser.
xapers-adder
------------
xapers-adder is a simple script that helps the adding of individual
documents to your Xapers database. It can be used e.g. as a PDF
handler in your favorite browser. It displays the PDF then presents
the user with the option to import the document into Xapers. The user
is prompted for any sources to retrieve and any initial tags to add.
If the source is known, bibtex is retrieved and indexed. The
resulting xapers entry for the document is displayed.
Development of more clever import methods is highly encouraged.
Python library
--------------
Xapers is really a python library interface under the hood:
>>> import xapers
>>> db = xapers.Database('~/.xapers/docs')
>>> docs = db.search('tag:new')
>>> for doc in docs:
doc.add_tags(['foo'])
...
>>>
Development of new interfaces to the underlying library is highly
encouraged.
xapers-0.6/SOURCES.txt 0000664 0000000 0000000 00000006101 12454273704 0014553 0 ustar 00root root 0000000 0000000 = SOURCES =
A Xapers "source" is a python module that describes how to interact
with a single online journal database, from which document files and
bibliographic data can be retrieved.
Sources are assigned unique prefixes (e.g. "doi"). Online libraries
associate unique document identifiers to individual documents
(e.g. "10.1364/JOSAA.29.002092"). A particular online document is
therefore described by a unique "source identifier", or "sid", which
can take two equivalent forms:
full URL http://dx.doi.org/10.1364/JOSAA.29.002092
: doi:10.1364/JOSAA.29.002092
== CUSTOM SOURCE MODULES ==
Custom source modules may be written to extend the base functionality
of Xapers. A source module is described by a single python module
(although it may import arbitrary other modules). The base name of
the module file is interpreted as the nickname or 'prefix' for the
source (e.g. if the module is named "doi.py" the source nickname will
be "doi").
The module should include the following properties and functions. If
any are missing, some xapers functionality may be undefined.
description: a brief string description of the source, e.g.:
description = "Digital Object Identifier"
url: base URL of source, e.g.:
url = 'http://dx.doi.org/'
url_format: a printf format string that produces a valid source URL
for a specified source identifier string, e.g.:
url_format = 'http://dx.doi.org/%s'
url_regex: a regular expression string that will match the source
identifier string from a given full URL, e.g.:
url_regex = 'http://dx.doi.org/(10\.\d{4,}[\w\d\:\.\-\/]+)'
scan_regex: a regular expression string that will match the source
identifier string in a scan of a documents plain text, e.g.:
scan_regex = '(?:doi|DOI)[\s\.\:]{0,2}' + id_regex
fetch_bibtex(id): a function that will return a bibtex string for a
source document specified by id.
fetch_file(id): a function that will return a (file_name, file_data)
tuple for a source document specified by id. File should be in
PDF format.
If your source does not provide bibliographic data directly in bibtex
format, the xapers.bibtex module has several helper functions for
creating bibtex strings from python dictionaries (data2bib) or json
objects (json2bib).
See existing source module contributed with the xapers source as
examples (lib/xapers/sources/).
== SOURCE MODULE PATH ==
Once a custom source module has been created, place it
~/.xapers/sources. The module path can be overridden with the
XAPERS_SOURCE_PATH environment variable, which can be a
colon-separated list of directories to search for modules.
== TESTING ==
Once a module is in place, use the xapers source* commands (sources,
source2url, source2bib, source2file) to test it's functionality. Your
new module should show up in the source listing with the "sources"
command, and should be able to print the relevant data with the other
commands.
== CONTRIBUTING ==
If you think your module is stable and of general usefulness to the
community, please consider contributing it upstream. Thanks!
xapers-0.6/TODO 0000664 0000000 0000000 00000002660 12454273704 0013365 0 ustar 00root root 0000000 0000000 * DB VERSION
* add only opens writable db on doc.sync()
* set/get title, author, tags as data or values (is this faster?)
* pdf thumbnails:
"convert -thumbnail 500x -background white -alpha remove file.pdf[0] thumb.png"
([0] == pdf page)
* gtk gui, with pdf thumbs
* rework db/doc interface
* doc is just directory and xapian_doc
* db does write/index on sync
doc:
* add ability to remove source sid
* add ability to replace/remove file
* what to do with doc 'data' field:
* snippet/summary (current)
* data for fast retrieval?
* bib abstract
* custom annotations/notes
* nothing
cli:
* utilize meta-data pulled from parser
* update should re-pull from existing source if available
* export should produce full mirror of xapers document structure
nci:
* custom keybindings
* customize helper commands
* how to test??
* add update/add commands
* customizable palette
sources:
* add 'hdl': http://handle.net/proxy.html
parser:
* extract metadata from pdfs
* better handle parse errors
* better pdf parser (native python: https://gist.github.com/pazz/5455090)
* parsers for other document types
?
* emacs UI (need json/sexp output)
* rename file when importing and copying into docdir?
* store bib data in different format (json instead of bibtex)?
* clear old indexed terms when importing new file/bib?
* vcs integration (git of root)?
BUGS
====
* capitalized prefixed terms are not searchable
- dcc:T00000
- key:HaEA2009a
xapers-0.6/bin/ 0000775 0000000 0000000 00000000000 12454273704 0013441 5 ustar 00root root 0000000 0000000 xapers-0.6/bin/xapers 0000775 0000000 0000000 00000000045 12454273704 0014670 0 ustar 00root root 0000000 0000000 #!/bin/sh
exec python -m xapers "$@"
xapers-0.6/bin/xapers-adder 0000775 0000000 0000000 00000001412 12454273704 0015744 0 ustar 00root root 0000000 0000000 #!/bin/bash -e
if [ -z "$1" ] || [[ "$1" == '--help' ]] || [[ "$1" == '-h' ]]; then
echo "usage: $(basename $0) [--noterm] " >&2
exit 1
fi
if [[ "$1" == '--noterm' ]]; then
term=false
shift
else
term=true
fi
infile="$1"
if [ ! -e "$infile" ] ;then
echo "File not found: $infile" >&2
exit 1
fi
# open the file with preferred application
nohup xdg-open "$infile" &>/dev/null &
cmd="
echo 'Xapers-adder'
echo '============'
echo 'Type C-c at any time to cancel...'
echo
while ! xapers add --file=\"$infile\" --tags=new --prompt --view; do
read -N1 -p 'ENTER to try again, or C-c to quit:' OK
done
"
if [[ "$term" == 'true' ]] ; then
exec x-terminal-emulator \
-title "xapers-adder" \
-e bash -c "$cmd"
else
eval "$cmd"
fi
xapers-0.6/lib/ 0000775 0000000 0000000 00000000000 12454273704 0013437 5 ustar 00root root 0000000 0000000 xapers-0.6/lib/xapers/ 0000775 0000000 0000000 00000000000 12454273704 0014741 5 ustar 00root root 0000000 0000000 xapers-0.6/lib/xapers/__init__.py 0000664 0000000 0000000 00000001571 12454273704 0017056 0 ustar 00root root 0000000 0000000 """
This file is part of xapers.
Xapers 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.
Xapers 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 notmuch. If not, see .
Copyright 2012
Jameson Rollins
"""
from database import Database
from database import DatabaseError
from database import DatabaseUninitializedError
from database import DatabaseLockError
from documents import Documents, Document
xapers-0.6/lib/xapers/__main__.py 0000775 0000000 0000000 00000042353 12454273704 0017045 0 ustar 00root root 0000000 0000000 """
This file is part of xapers.
Xapers 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.
Xapers 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 notmuch. If not, see .
Copyright 2012-2014
Jameson Rollins
"""
import os
import sys
import codecs
import signal
import cli
from source import Sources, SourceError
from bibtex import Bibtex, BibtexError
from parser import ParseError
########################################################################
PROG = 'xapers'
def usage():
print "Usage:", PROG, " [args...]"
print """
Commands:
add [options] [] Add a new document or update existing.
If provided, search should match a single
document.
--source=[|] source id, for online retrieval, or
bibtex file path
--file[=] PDF file to index and archive
--tags=[,...] initial tags
--prompt prompt for unspecified options
--view view entry after adding
import Import entries from a bibtex database.
--tags=[,...] tags to apply to all imported documents
delete Delete documents from database.
--noprompt do not prompt to confirm deletion
restore Restore database from an existing xapers
root directory.
tag +|- [...] [--]
Add/remove tags.
search [options] Search for documents.
--output=[summary|bibtex|tags|sources|keys|files]
output format (default is 'summary')
--limit=N limit number of results returned
bibtex Short for \"search --output=bibtex\".
view View search in curses UI.
count Count matches.
export Export documents to a directory of files
named for document titles.
sources List available sources.
source2url [...] Output URLs for sources.
source2bib [...] Retrieve bibtex for sources and print to
stdout.
source2file Retrieve file for source and write to
stdout.
scandoc Scan PDF file for source ids.
version Print version number.
help [search] This usage, or search term help.
The xapers document store is specified by the XAPERS_ROOT environment
variable, or defaults to '~/.xapers/docs' if not specified (the
directory is allowed to be a symlink).
See 'xapers help search' for more information on term definitions and
search syntax."""
def usage_search():
print """Xapers supports a common syntax for search terms.
Search can consist of free-form text and quoted phrases. Terms can be
combined with standard Boolean operators. All terms are combined with
a logical OR by default. Parentheses can be used to group operators,
but must be protect from shell interpretation. The string '*' will
match all documents.
Additionally, the following prefixed terms are understood (where
indicate user-supplied values):
id: Xapers document id
author: string in authors (also a:)
title: string in title (also t:)
tag: specific user tag
: specific source id (sid)
source: specific Xapers source
key: specific bibtex citation key
year: specific publication year (also y:)
year:.. publication year range (also y:)
year:..
year:..
Publication years must be four-digit integers.
See the following for more information on search terms:
http://xapian.org/docs/queryparser.html"""
########################################################################
# combine a list of terms with spaces between, so that simple queries
# don't have to be quoted at the shell level.
def make_query_string(terms, require=True):
string = str.join(' ', terms)
if string == '':
if require:
print >>sys.stderr, "Must specify a search term."
sys.exit(1)
else:
string = '*'
return string
def import_nci():
try:
import nci
except ImportError:
print >>sys.stderr, "The python-urwid package does not appear to be installed."
print >>sys.stderr, "Please install to be able to use the curses UI."
sys.exit(1)
return nci
def set_stdout_codec():
# set the stdout codec to properly handle utf8 characters
SYS_STDOUT = sys.stdout
sys.stdout = codecs.getwriter('utf8')(sys.stdout)
########################################################################
if __name__ == '__main__':
signal.signal(signal.SIGINT, signal.SIG_DFL)
signal.signal(signal.SIGPIPE, signal.SIG_DFL)
if len(sys.argv) > 1:
cmd = sys.argv[1]
else:
cmd = []
########################################
if cmd in ['add','a']:
tags = None
infile = None
sid = None
prompt = False
view = False
query = None
argc = 2
while True:
if argc >= len(sys.argv):
break
elif '--source=' in sys.argv[argc]:
sid = sys.argv[argc].split('=',1)[1]
elif '--file' in sys.argv[argc]:
if '=' in sys.argv[argc]:
infile = sys.argv[argc].split('=',1)[1]
else:
infile = True
elif '--tags=' in sys.argv[argc]:
tags = sys.argv[argc].split('=',1)[1].split(',')
elif '--prompt' in sys.argv[argc]:
prompt = True
elif '--view' in sys.argv[argc]:
view = True
else:
break
argc += 1
if argc == (len(sys.argv) - 1):
query = make_query_string(sys.argv[argc:])
with cli.initdb(writable=True, create=True) as db:
docid = cli.add(db, query, infile=infile, sid=sid, tags=tags, prompt=prompt)
if view and docid:
nci = import_nci()
nci.UI(cmd=['search', 'id:'+str(docid)])
########################################
elif cmd in ['import','i']:
tags = []
argc = 2
while True:
if argc >= len(sys.argv):
break
elif '--tags=' in sys.argv[argc]:
tags = sys.argv[argc].split('=',1)[1].split(',')
elif '--overwrite' in sys.argv[argc]:
overwrite = True
else:
break
argc += 1
try:
bibfile = sys.argv[argc]
except IndexError:
print >>sys.stderr, "Must specify bibtex file to import."
sys.exit(1)
if not os.path.exists(bibfile):
print >>sys.stderr, "File not found: %s" % bibfile
sys.exit(1)
with cli.initdb(writable=True, create=True) as db:
cli.importbib(db, bibfile, tags=tags)
########################################
elif cmd in ['update']:
argc = 2
query = make_query_string(sys.argv[argc:])
with cli.initdb(writable=True) as db:
for doc in db.search(query):
try:
print >>sys.stderr, "Updating %s..." % doc.docid,
doc.update_from_bibtex()
doc.sync()
print >>sys.stderr, "done."
except:
print >>sys.stderr, "\n"
raise
########################################
elif cmd in ['delete']:
prompt = True
argc = 2
while True:
if argc >= len(sys.argv):
break
elif '--noprompt' in sys.argv[argc]:
prompt = False
else:
break
argc += 1
query = make_query_string(sys.argv[argc:])
with cli.initdb(writable=True) as db:
count = db.count(query)
if count == 0:
print >>sys.stderr, "No documents found for query."
sys.exit(1)
for doc in db.search(query):
if prompt:
resp = raw_input("Type 'yes' to delete document id:%d: " % doc.docid)
if resp != 'yes':
continue
print >>sys.stderr, "deleting id:%d..." % doc.docid,
doc.purge()
print >>sys.stderr, "done."
########################################
elif cmd in ['search','s']:
oformat = 'summary'
limit = 0
argc = 2
while True:
if argc >= len(sys.argv):
break
if '--output=' in sys.argv[argc]:
oformat = sys.argv[argc].split('=')[1]
elif '--limit=' in sys.argv[argc]:
limit = int(sys.argv[argc].split('=')[1])
else:
break
argc += 1
if oformat not in ['summary','bibtex','tags','sources','keys','files']:
print >>sys.stderr, "Unknown output format."
sys.exit(1)
query = make_query_string(sys.argv[argc:])
set_stdout_codec()
with cli.initdb() as db:
cli.search(db, query, oformat=oformat, limit=limit)
########################################
elif cmd in ['bibtex','bib','b']:
argc = 2
query = make_query_string(sys.argv[argc:])
set_stdout_codec()
with cli.initdb() as db:
cli.search(db, query, oformat='bibtex')
########################################
elif cmd in ['nci','view','show','select']:
nci = import_nci()
if cmd == 'nci':
args = sys.argv[2:]
else:
query = make_query_string(sys.argv[2:], require=False)
args = ['search', query]
nci.UI(cmd=args)
########################################
elif cmd in ['tag','t']:
add_tags = []
remove_tags = []
argc = 2
for arg in sys.argv[argc:]:
if argc >= len(sys.argv):
break
if arg == '--':
argc += 1
continue
if arg[0] == '+':
add_tags.append(arg[1:])
elif arg[0] == '-':
remove_tags.append(arg[1:])
else:
break
argc += 1
if not add_tags and not remove_tags:
print >>sys.stderr, "Must specify tags to add or remove."
sys.exit(1)
if '' in add_tags:
print >>sys.stderr, "Null tags not allowed."
sys.exit(1)
query = make_query_string(sys.argv[argc:])
with cli.initdb(writable=True) as db:
for doc in db.search(query):
doc.add_tags(add_tags)
doc.remove_tags(remove_tags)
doc.sync()
########################################
elif cmd in ['dumpterms']:
prefix = None
argc = 2
while True:
if argc >= len(sys.argv):
break
if '--prefix=' in sys.argv[argc]:
prefix = sys.argv[argc].split('=')[1]
else:
break
argc += 1
query = make_query_string(sys.argv[argc:], require=True)
with cli.initdb() as db:
if query == '*':
for term in db.term_iter(prefix):
print term
else:
for doc in db.search(query):
for term in doc.term_iter(prefix):
print term
########################################
elif cmd in ['maxid']:
docid = 0
with cli.initdb() as db:
for doc in db.search('*'):
docid = max(docid, doc.docid)
print 'id:%d' % docid
########################################
elif cmd in ['count']:
query = make_query_string(sys.argv[2:], require=False)
with cli.initdb() as db:
print db.count(query)
########################################
elif cmd in ['export']:
outdir = sys.argv[2]
query = make_query_string(sys.argv[3:])
set_stdout_codec()
with cli.initdb() as db:
cli.export(db, outdir, query)
########################################
elif cmd in ['restore']:
with cli.initdb(writable=True, create=True, force=True) as db:
db.restore(log=True)
########################################
elif cmd in ['sources']:
sources = Sources()
w = 0
for source in sources:
w = max(len(source.name), w)
format = '%'+str(w)+'s: %s[%s]'
for source in sources:
name = source.name
desc = ''
try:
desc += '%s ' % source.description
except AttributeError:
pass
try:
desc += '(%s) ' % source.url
except AttributeError:
pass
if source.is_builtin:
path = 'builtin'
else:
path = source.path
print format % (name, desc, path)
########################################
elif cmd in ['source2bib', 's2b', 'source2url', 's2u', 'source2file', 's2f']:
outraw = False
argc = 2
for arg in sys.argv[argc:]:
if argc >= len(sys.argv):
break
elif sys.argv[argc] == '--raw':
outraw = True
else:
break
argc += 1
try:
sss = sys.argv[argc:]
except IndexError:
print >>sys.stderr, "Must specify source to retrieve."
sys.exit(1)
if cmd in ['source2file', 's2f']:
if len(sss) > 1:
print >>sys.stderr, "source2file can only retrieve file for single source."
sys.exit(1)
sources = Sources()
for ss in sss:
try:
item = sources.match_source(ss)
except SourceError as e:
print >>sys.stderr, e
sys.exit(1)
if cmd in ['source2url', 's2u']:
print item.url
continue
elif cmd in ['source2bib', 's2b']:
try:
bibtex = item.fetch_bibtex()
except Exception as e:
print >>sys.stderr, "Could not retrieve bibtex: %s" % e
sys.exit(1)
if outraw:
print bibtex
else:
try:
print Bibtex(bibtex)[0].as_string()
except:
print >>sys.stderr, "Failed to parse retrieved bibtex data."
print >>sys.stderr, "Use --raw option to view raw retrieved data."
sys.exit(1)
elif cmd in ['source2file', 's2f']:
try:
name, data = item.fetch_file()
print data
except Exception as e:
print >>sys.stderr, "Could not retrieve file: %s" % e
sys.exit(1)
########################################
elif cmd in ['scandoc','sd']:
try:
infile = sys.argv[2]
except IndexError:
print >>sys.stderr, "Must specify document to scan."
sys.exit(1)
try:
items = Sources().scan_file(infile)
except ParseError as e:
print >>sys.stderr, "Parse error: %s" % e
print >>sys.stderr, "Is file '%s' a PDF?" % infile
sys.exit(1)
for item in items:
print item
########################################
elif cmd in ['version','--version','-v']:
import version
print 'xapers', version.__version__
########################################
elif cmd in ['help','h','--help','-h']:
if len(sys.argv) > 2:
if sys.argv[2] == 'search':
usage_search()
else:
usage()
########################################
else:
if cmd:
print >>sys.stderr, "Unknown command '%s'." % cmd
else:
print >>sys.stderr, "Command not specified."
print >>sys.stderr, "See \"help\" for more information."
sys.exit(1)
xapers-0.6/lib/xapers/bibtex.py 0000664 0000000 0000000 00000012150 12454273704 0016567 0 ustar 00root root 0000000 0000000 import os
import sys
import io
import json
import pybtex
from pybtex.core import Entry, Person
from pybtex.bibtex.utils import split_name_list
from pybtex.database.input import bibtex as inparser
from pybtex.database.output import bibtex as outparser
def clean_bib_string(string):
for char in ['{', '}']:
string = string.replace(char,'')
return string
##################################################
class BibtexError(Exception):
"""Base class for Xapers bibtex exceptions."""
def __init__(self, msg):
self.msg = msg
def __str__(self):
return self.msg
##################################################
class Bibtex():
"""Represents a bibtex database."""
# http://www.bibtex.org/Format/
def __init__(self, bibtex):
parser = inparser.Parser(encoding='utf-8')
if os.path.exists(bibtex):
bibdata = parser.parse_file(bibtex)
else:
# StringIO requires unicode input
# http://nedbatchelder.com/text/unipain.html
assert type(bibtex) is unicode, "Bibtex strings must be unicode"
with io.StringIO(bibtex) as stream:
bibdata = parser.parse_stream(stream)
self.keys = bibdata.entries.keys()
self.entries = bibdata.entries.values()
self.index = -1
self.max = len(self.entries)
def __getitem__(self, index):
key = self.keys[index]
entry = self.entries[index]
return Bibentry(key, entry)
def __iter__(self):
return self
def __len__(self):
return self.max
def next(self):
self.index = self.index + 1
if self.index == self.max:
raise StopIteration
return self[self.index]
##################################################
class Bibentry():
"""Represents an individual entry in a bibtex database"""
def __init__(self, key, entry):
self.key = key
self.entry = entry
def get_authors(self):
"""Return a list of authors."""
authors = []
if 'author' in self.entry.persons:
for p in self.entry.persons['author']:
authors.append(clean_bib_string(unicode(p)))
return authors
def get_fields(self):
"""Return a dict of non-author fields."""
bibfields = self.entry.fields
# entry.fields is actually already a dict, but we want to
# clean the strings first
fields = {}
for field in bibfields:
fields[field] = unicode(clean_bib_string(bibfields[field]))
return fields
def set_file(self, path):
# FIXME: what's the REAL proper format for this
self.entry.fields['file'] = ':%s:%s' % (path, 'pdf')
def get_file(self):
"""Returns file path if file field exists.
Expects either single path string or Mendeley/Jabref format."""
try:
parsed = self.entry.fields['file'].split(':')
if len(parsed) > 1:
return parsed[1]
else:
return parsed[0]
except KeyError:
return None
except IndexError:
return None
def _entry2db(self):
db = pybtex.database.BibliographyData()
db.add_entry(self.key, self.entry)
return db
def as_string(self):
"""Return entry as formatted bibtex string."""
writer = outparser.Writer()
with io.StringIO() as stream:
writer.write_stream(self._entry2db(), stream)
string = stream.getvalue()
string = string.strip()
return string
def to_file(self, path):
"""Write entry bibtex to file."""
writer = outparser.Writer(encoding='utf-8')
writer.write_file(self._entry2db(), path)
##################################################
def data2bib(data, key, type='article'):
"""Convert a python dict into a Bibentry object."""
if not data:
return
# need to remove authors field from data
authors = None
if 'authors' in data:
authors = data['authors']
if isinstance(authors, str):
authors = split_name_list(authors)
if len(authors) == 1:
authors = authors[0].split(',')
del data['authors']
entry = Entry(type, fields=data)
if authors:
for p in authors:
entry.add_person(Person(p), 'author')
return Bibentry(key, entry).as_string()
def json2bib(jsonstring, key, type='article'):
"""Convert a json string into a Bibentry object."""
if not json:
return
data = json.loads(jsonstring)
# need to remove authors field from data
authors = None
if 'author' in data:
authors = data['author']
del data['author']
if 'issued' in data:
data['year'] = str(data['issued']['date-parts'][0][0])
del data['issued']
# delete other problematic fields
if 'editor' in data:
del data['editor']
entry = Entry(type, fields=data)
if authors:
for author in authors:
entry.add_person(Person(first=author['given'], last=author['family']), 'author')
return Bibentry(key, entry).as_string()
xapers-0.6/lib/xapers/cli.py 0000664 0000000 0000000 00000032756 12454273704 0016077 0 ustar 00root root 0000000 0000000 """
This file is part of xapers.
Xapers 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.
Xapers 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 notmuch. If not, see .
Copyright 2012, 2013
Jameson Rollins
"""
import os
import sys
import sets
import shutil
import readline
import database
from documents import Document
from source import Sources, SourceError
from parser import ParseError
from bibtex import Bibtex, BibtexError
############################################################
def initdb(writable=False, create=False, force=False):
xroot = os.getenv('XAPERS_ROOT',
os.path.expanduser(os.path.join('~','.xapers','docs')))
try:
return database.Database(xroot, writable=writable, create=create, force=force)
except database.DatabaseUninitializedError as e:
print >>sys.stderr, e
print >>sys.stderr, "Import a document to initialize."
sys.exit(1)
except database.DatabaseInitializationError as e:
print >>sys.stderr, e
print >>sys.stderr, "Either clear the directory and add new files, or use 'retore' to restore from existing data."
sys.exit(1)
except database.DatabaseError as e:
print >>sys.stderr, e
sys.exit(1)
############################################################
# readline completion class
class Completer:
def __init__(self, words):
self.words = words
def terms(self, prefix, index):
matching_words = [
w for w in self.words if w.startswith(prefix)
]
try:
return matching_words[index]
except IndexError:
return None
def prompt_for_file(infile):
if infile:
print >>sys.stderr, 'file: %s' % infile
else:
readline.set_startup_hook()
readline.parse_and_bind('')
readline.set_completer()
infile = raw_input('file: ')
if infile == '':
infile = None
return infile
def prompt_for_source(db, sources):
if sources:
readline.set_startup_hook(lambda: readline.insert_text(sources[0]))
elif db:
sources = list(db.term_iter('source'))
readline.parse_and_bind("tab: complete")
completer = Completer(sources)
readline.set_completer(completer.terms)
readline.set_completer_delims(' ')
source = raw_input('source: ')
if source == '':
source = None
return source
def prompt_for_tags(db, tags):
# always prompt for tags, and append to initial
if tags:
print >>sys.stderr, 'initial tags: %s' % ' '.join(tags)
else:
tags = []
if db:
itags = list(db.term_iter('tag'))
else:
itags = None
readline.set_startup_hook()
readline.parse_and_bind("tab: complete")
completer = Completer(itags)
readline.set_completer(completer.terms)
readline.set_completer_delims(' ')
while True:
tag = raw_input('tag: ')
if tag and tag != '':
tags.append(tag.strip())
else:
break
return tags
############################################################
def print_doc_summary(doc):
docid = doc.docid
title = doc.get_title()
if not title:
title = ''
tags = doc.get_tags()
sources = doc.get_sids()
key = doc.get_key()
if not key:
key = ''
print "id:%d [%s] {%s} (%s) \"%s\"" % (
docid,
' '.join(sources),
key,
' '.join(tags),
title,
)
############################################################
def add(db, query_string, infile=None, sid=None, tags=None, prompt=False):
doc = None
bibtex = None
sources = Sources()
doc_sid = sid
source = None
file_data = None
if infile and infile is not True:
infile = os.path.expanduser(infile)
##################################
# if query provided, find single doc to update
if query_string:
if db.count(query_string) != 1:
print >>sys.stderr, "Search '%s' did not match a single document." % query_string
print >>sys.stderr, "Aborting."
sys.exit(1)
for doc in db.search(query_string):
break
##################################
# do fancy option prompting
if prompt:
doc_sids = []
if doc_sid:
doc_sids = [doc_sid]
# scan the file for source info
if infile is not True:
infile = prompt_for_file(infile)
print >>sys.stderr, "Scanning document for source identifiers..."
try:
ss = sources.scan_file(infile)
except ParseError as e:
print >>sys.stderr, "\n"
print >>sys.stderr, "Parse error: %s" % e
sys.exit(1)
if len(ss) == 0:
print >>sys.stderr, "0 source ids found."
else:
if len(ss) == 1:
print >>sys.stderr, "1 source id found:"
else:
print >>sys.stderr, "%d source ids found:" % (len(ss))
for sid in ss:
print >>sys.stderr, " %s" % (sid)
doc_sids += [s.sid for s in ss]
doc_sid = prompt_for_source(db, doc_sids)
tags = prompt_for_tags(db, tags)
if not query_string and not infile and not doc_sid:
print >>sys.stderr, "Must specify file or source to import, or query to update existing document."
sys.exit(1)
##################################
# process source and get bibtex
# check if source is a file, in which case interpret it as bibtex
if doc_sid and os.path.exists(doc_sid):
bibtex = doc_sid
elif doc_sid:
# get source object for sid string
try:
source = sources.match_source(doc_sid)
except SourceError as e:
print >>sys.stderr, e
sys.exit(1)
# check that the source doesn't match an existing doc
sdoc = db.doc_for_source(source.sid)
if sdoc:
if doc and sdoc != doc:
print >>sys.stderr, "A different document already exists for source '%s'." % (doc_sid)
print >>sys.stderr, "Aborting."
sys.exit(1)
print >>sys.stderr, "Source '%s' found in database. Updating existing document..." % (doc_sid)
doc = sdoc
try:
print >>sys.stderr, "Retrieving bibtex...",
bibtex = source.fetch_bibtex()
print >>sys.stderr, "done."
except SourceError as e:
print >>sys.stderr, "\n"
print >>sys.stderr, "Could not retrieve bibtex: %s" % e
sys.exit(1)
if infile is True:
try:
print >>sys.stderr, "Retrieving file...",
file_name, file_data = source.fetch_file()
print >>sys.stderr, "done."
except SourceError as e:
print >>sys.stderr, "\n"
print >>sys.stderr, "Could not retrieve file: %s" % e
sys.exit(1)
elif infile is True:
print >>sys.stderr, "Must specify source with retrieve file option."
sys.exit(1)
if infile and not file_data:
with open(infile, 'r') as f:
file_data = f.read()
file_name = os.path.basename(infile)
##################################
# if we still don't have a doc, create a new one
if not doc:
doc = Document(db)
##################################
# add stuff to the doc
if bibtex:
try:
print >>sys.stderr, "Adding bibtex...",
doc.add_bibtex(bibtex)
print >>sys.stderr, "done."
except BibtexError as e:
print >>sys.stderr, "\n"
print >>sys.stderr, e
print >>sys.stderr, "Bibtex must be a plain text file with a single bibtex entry."
sys.exit(1)
except:
print >>sys.stderr, "\n"
raise
# add source sid if it hasn't been added yet
if source and not doc.get_sids():
doc.add_sid(source.sid)
if infile:
try:
print >>sys.stderr, "Adding file...",
doc.add_file_data(file_name, file_data)
print >>sys.stderr, "done."
except ParseError as e:
print >>sys.stderr, "\n"
print >>sys.stderr, "Parse error: %s" % e
sys.exit(1)
except:
print >>sys.stderr, "\n"
raise
if tags:
try:
print >>sys.stderr, "Adding tags...",
doc.add_tags(tags)
print >>sys.stderr, "done."
except:
print >>sys.stderr, "\n"
raise
##################################
# sync the doc to db and disk
try:
print >>sys.stderr, "Syncing document...",
doc.sync()
print >>sys.stderr, "done.\n",
except:
print >>sys.stderr, "\n"
raise
print_doc_summary(doc)
return doc.docid
############################################
def importbib(db, bibfile, tags=[], overwrite=False):
errors = []
sources = Sources()
for entry in sorted(Bibtex(bibfile), key=lambda entry: entry.key):
print >>sys.stderr, entry.key
try:
docs = []
# check for doc with this bibkey
bdoc = db.doc_for_bib(entry.key)
if bdoc:
docs.append(bdoc)
# check for known sids
for source in sources.scan_bibentry(entry):
sdoc = db.doc_for_source(source.sid)
# FIXME: why can't we match docs in list?
if sdoc and sdoc.docid not in [doc.docid for doc in docs]:
docs.append(sdoc)
if len(docs) == 0:
doc = Document(db)
elif len(docs) > 0:
if len(docs) > 1:
print >>sys.stderr, " Multiple distinct docs found for entry. Using first found."
doc = docs[0]
print >>sys.stderr, " Updating id:%d..." % (doc.docid)
doc.add_bibentry(entry)
filepath = entry.get_file()
if filepath:
print >>sys.stderr, " Adding file: %s" % filepath
doc.add_file(filepath)
doc.add_tags(tags)
doc.sync()
except BibtexError as e:
print >>sys.stderr, " Error processing entry %s: %s" % (entry.key, e)
print >>sys.stderr
errors.append(entry.key)
if errors:
print >>sys.stderr
print >>sys.stderr, "Failed to import %d" % (len(errors)),
if len(errors) == 1:
print >>sys.stderr, "entry",
else:
print >>sys.stderr, "entries",
print >>sys.stderr, "from bibtex:"
for error in errors:
print >>sys.stderr, " %s" % (error)
sys.exit(1)
else:
sys.exit(0)
############################################
def search(db, query_string, oformat='summary', limit=None):
if query_string == '*' and oformat in ['tags','sources','keys']:
if oformat == 'tags':
for tag in db.term_iter('tag'):
print tag
elif oformat == 'sources':
for source in db.get_sids():
print source
elif oformat == 'keys':
for key in db.term_iter('key'):
print key
return
otags = set([])
osources = set([])
okeys = set([])
for doc in db.search(query_string, limit=limit):
if oformat in ['summary']:
print_doc_summary(doc)
continue
elif oformat in ['file','files']:
for path in doc.get_fullpaths():
print "%s" % (path)
continue
elif oformat == 'bibtex':
bibtex = doc.get_bibtex()
if not bibtex:
print >>sys.stderr, "No bibtex for doc id:%d." % doc.docid
else:
print bibtex
print
continue
if oformat == 'tags':
otags = otags | set(doc.get_tags())
elif oformat == 'sources':
osources = osources | set(doc.get_sids())
elif oformat == 'keys':
key = doc.get_key()
if key:
print key
if oformat == 'tags':
for tag in otags:
print tag
elif oformat == 'sources':
for source in osources:
print source
############################################
def export(db, outdir, query_string):
try:
os.makedirs(outdir)
except:
pass
import pipes
for doc in db.search(query_string):
title = doc.get_title()
origpaths = doc.get_fullpaths()
nfiles = len(origpaths)
for path in origpaths:
if not title:
name = os.path.basename(os.path.splitext(path)[0])
else:
name = '%s' % (title.replace(' ','_'))
ind = 0
if nfiles > 1:
name += '.%s' % ind
ind += 1
name += '.pdf'
outpath = os.path.join(outdir,name)
print outpath
shutil.copyfile(path, outpath.encode('utf-8'))
xapers-0.6/lib/xapers/database.py 0000664 0000000 0000000 00000027550 12454273704 0017070 0 ustar 00root root 0000000 0000000 """
This file is part of xapers.
Xapers 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.
Xapers 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 notmuch. If not, see .
Copyright 2012, 2013
Jameson Rollins
"""
import os
import sys
import xapian
from source import Sources
from documents import Documents, Document
# FIXME: add db schema documentation
##################################################
class DatabaseError(Exception):
"""Base class for Xapers database exceptions."""
def __init__(self, msg):
self.msg = msg
def __str__(self):
return self.msg
class DatabaseUninitializedError(DatabaseError):
pass
class DatabaseInitializationError(DatabaseError):
pass
class DatabaseLockError(DatabaseError):
pass
##################################################
class Database():
"""Represents a Xapers database"""
# http://xapian.org/docs/omega/termprefixes.html
BOOLEAN_PREFIX_INTERNAL = {
# FIXME: use this for doi?
#'url': 'U',
'file': 'P',
# FIXME: use this for doc mime type
'type': 'T',
}
BOOLEAN_PREFIX_EXTERNAL = {
'id': 'Q',
'key': 'XBIB|',
'source': 'XSOURCE|',
'tag': 'K',
'year': 'Y',
'y': 'Y',
}
PROBABILISTIC_PREFIX = {
'title': 'S',
't': 'S',
'author': 'A',
'a': 'A',
}
# http://xapian.org/docs/facets
NUMBER_VALUE_FACET = {
'year': 0,
'y': 0,
}
# FIXME: need to set the following value fields:
# publication date
# added date
# modified date
# FIXME: need database version
def _find_prefix(self, name):
if name in self.BOOLEAN_PREFIX_INTERNAL:
return self.BOOLEAN_PREFIX_INTERNAL[name]
if name in self.BOOLEAN_PREFIX_EXTERNAL:
return self.BOOLEAN_PREFIX_EXTERNAL[name]
if name in self.PROBABILISTIC_PREFIX:
return self.PROBABILISTIC_PREFIX[name]
def _find_facet(self, name):
if name in self.NUMBER_VALUE_FACET:
return self.NUMBER_VALUE_FACET[name]
def _make_source_prefix(self, source):
return 'X%s|' % (source.upper())
########################################
def __init__(self, root, writable=False, create=False, force=False):
# xapers root
self.root = os.path.abspath(os.path.expanduser(root))
# xapers db directory
xapers_path = os.path.join(self.root, '.xapers')
# xapes directory initialization
if not os.path.exists(xapers_path):
if create:
if os.path.exists(self.root):
if os.listdir(self.root) and not force:
raise DatabaseInitializationError('Uninitialized Xapers root directory exists but is not empty.')
os.makedirs(xapers_path)
else:
if os.path.exists(self.root):
raise DatabaseInitializationError("Xapers directory '%s' does not contain a database." % (self.root))
else:
raise DatabaseUninitializedError("Xapers directory '%s' not found." % (self.root))
# the Xapian db
xapian_path = os.path.join(xapers_path, 'xapian')
if writable:
try:
self.xapian = xapian.WritableDatabase(xapian_path, xapian.DB_CREATE_OR_OPEN)
except xapian.DatabaseLockError:
raise DatabaseLockError("Xapers database locked.")
else:
self.xapian = xapian.Database(xapian_path)
stemmer = xapian.Stem("english")
# The Xapian TermGenerator
# http://trac.xapian.org/wiki/FAQ/TermGenerator
self.term_gen = xapian.TermGenerator()
self.term_gen.set_stemmer(stemmer)
# The Xapian QueryParser
self.query_parser = xapian.QueryParser()
self.query_parser.set_database(self.xapian)
self.query_parser.set_stemmer(stemmer)
self.query_parser.set_stemming_strategy(xapian.QueryParser.STEM_SOME)
self.query_parser.set_default_op(xapian.Query.OP_AND)
# add boolean internal prefixes
for name, prefix in self.BOOLEAN_PREFIX_EXTERNAL.iteritems():
self.query_parser.add_boolean_prefix(name, prefix)
# add probabalistic prefixes
for name, prefix in self.PROBABILISTIC_PREFIX.iteritems():
self.query_parser.add_prefix(name, prefix)
# add value facets
for name, facet in self.NUMBER_VALUE_FACET.iteritems():
self.query_parser.add_valuerangeprocessor(
xapian.NumberValueRangeProcessor(facet, name+':')
)
# register known source prefixes
# FIXME: can we do this by just finding all XSOURCE terms in
# db? Would elliminate dependence on source modules at
# search time.
for source in Sources():
name = source.name
self.query_parser.add_boolean_prefix(name, self._make_source_prefix(name))
def __enter__(self):
return self
def __exit__(self, exc_type, exc_value, traceback):
self.xapian.close()
def reopen(self):
self.xapian.reopen()
def __contains__(self, docid):
try:
self.xapian.get_document(docid)
return True
except xapian.DocNotFoundError:
return False
def __getitem__(self, docid):
if type(docid) not in [int, long]:
raise TypeError("docid must be an int")
xapian_doc = self.xapian.get_document(docid)
return Document(self, xapian_doc)
########################################
# generate a new doc id, based on the last availabe doc id
def _generate_docid(self):
return self.xapian.get_lastdocid() + 1
########################################
# return a list of terms for prefix
def _term_iter(self, prefix=None):
term_iter = iter(self.xapian)
if prefix:
plen = len(prefix)
term = term_iter.skip_to(prefix)
if not term.term.startswith(prefix):
return
yield term.term[plen:]
for term in term_iter:
if prefix:
if not term.term.startswith(prefix):
break
yield term.term[plen:]
else:
yield term.term
def term_iter(self, name=None):
"""Iterator over all terms in the database.
If a prefix is provided, will iterate over only the prefixed
terms, and the prefix will be removed from the returned terms.
"""
prefix = None
if name:
prefix = self._find_prefix(name)
if not prefix:
prefix = name
return self._term_iter(prefix)
def get_sids(self):
"""Get all sources in database."""
sids = []
# FIXME: do this more efficiently
for source in self.term_iter('source'):
for oid in self._term_iter(self._make_source_prefix(source)):
sids.append('%s:%s' % (source, oid))
return sids
########################################
# search for documents based on query string
def _search(self, query_string, limit=None):
enquire = xapian.Enquire(self.xapian)
if query_string == "*":
query = xapian.Query.MatchAll
else:
# parse the query string to produce a Xapian::Query object.
query = self.query_parser.parse_query(query_string)
if os.getenv('XAPERS_DEBUG_QUERY'):
print >>sys.stderr, "query string:", query_string
print >>sys.stderr, "final query:", query
# FIXME: need to catch Xapian::Error when using enquire
enquire.set_query(query)
# set order of returned docs as newest first
# FIXME: make this user specifiable
enquire.set_docid_order(xapian.Enquire.DESCENDING)
if limit:
mset = enquire.get_mset(0, limit)
else:
mset = enquire.get_mset(0, self.xapian.get_doccount())
return mset
def search(self, query_string, limit=0):
"""Search for documents in the database."""
mset = self._search(query_string, limit)
return Documents(self, mset)
def count(self, query_string):
"""Count documents matching search terms."""
return self._search(query_string).get_matches_estimated()
def _doc_for_term(self, term):
enquire = xapian.Enquire(self.xapian)
query = xapian.Query(term)
enquire.set_query(query)
mset = enquire.get_mset(0, 2)
# FIXME: need to throw an exception if more than one match found
if mset:
return Document(self, mset[0].document)
else:
return None
def doc_for_path(self, path):
"""Return document for specified path."""
term = self._find_prefix('file') + path
return self._doc_for_term(term)
def doc_for_source(self, sid):
"""Return document for source id string."""
source, oid = sid.split(':', 1)
term = self._make_source_prefix(source) + oid
return self._doc_for_term(term)
def doc_for_bib(self, bibkey):
"""Return document for bibtex key."""
term = self._find_prefix('key') + bibkey
return self._doc_for_term(term)
########################################
def replace_document(self, docid, doc):
"""Replace (sync) document to database."""
self.xapian.replace_document(docid, doc)
def delete_document(self, docid):
"""Delete document from database."""
self.xapian.delete_document(docid)
########################################
def restore(self, log=False):
"""Restore a database from an existing root."""
docdirs = os.listdir(self.root)
docdirs.sort()
for ddir in docdirs:
if ddir == '.xapers':
continue
docdir = os.path.join(self.root, ddir)
if not os.path.isdir(docdir):
# skip things that aren't directories
continue
if log:
print >>sys.stderr, docdir
# if we can't convert the directory name into an integer,
# assume it's not relevant to us and continue
try:
docid = int(ddir)
except ValueError:
continue
docfiles = os.listdir(docdir)
if not docfiles:
# skip empty directories
continue
if log:
print >>sys.stderr, ' docid:', docid
try:
doc = self[docid]
except xapian.DocNotFoundError:
doc = Document(self, docid=docid)
for dfile in docfiles:
dpath = os.path.join(docdir, dfile)
if dfile == 'bibtex':
if log:
print >>sys.stderr, ' adding bibtex'
doc.add_bibtex(dpath)
elif os.path.splitext(dpath)[1] == '.pdf':
if log:
print >>sys.stderr, ' adding file:', dfile
doc.add_file(dpath)
elif dfile == 'tags':
if log:
print >>sys.stderr, ' adding tags'
with open(dpath, 'r') as f:
tags = f.read().strip().split('\n')
doc.add_tags(tags)
doc.sync()
xapers-0.6/lib/xapers/documents.py 0000664 0000000 0000000 00000035572 12454273704 0017330 0 ustar 00root root 0000000 0000000 """
This file is part of xapers.
Xapers 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.
Xapers 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 notmuch. If not, see .
Copyright 2012, 2013
Jameson Rollins
"""
import os
import shutil
import xapian
from parser import parse_data
from source import Sources
from bibtex import Bibtex
##################################################
class DocumentError(Exception):
"""Base class for Xapers document exceptions."""
def __init__(self, msg):
self.msg = msg
def __str__(self):
return self.msg
##################################################
class Documents():
"""Represents a set of Xapers documents given a Xapian mset."""
def __init__(self, db, mset):
self.db = db
self.mset = mset
self.index = -1
self.max = len(mset)
def __getitem__(self, index):
m = self.mset[index]
doc = Document(self.db, m.document)
doc.matchp = m.percent
return doc
def __iter__(self):
return self
def __len__(self):
return self.max
def next(self):
self.index = self.index + 1
if self.index == self.max:
raise StopIteration
return self[self.index]
##################################################
class Document():
"""Represents a single Xapers document."""
def __init__(self, db, xapian_doc=None, docid=None):
# Xapers db
self.db = db
# if Xapian doc provided, initiate for that document
if xapian_doc:
self.xapian_doc = xapian_doc
self.docid = xapian_doc.get_docid()
# else, create a new empty document
# document won't be added to database until sync is called
else:
self.xapian_doc = xapian.Document()
# use specified docid if provided
if docid:
if docid in self.db:
raise DocumentError('Document already exists for id %d.' % docid)
self.docid = docid
else:
self.docid = self.db._generate_docid()
self._add_term(self.db._find_prefix('id'), self.docid)
# specify a directory in the Xapers root for document data
self.docdir = os.path.join(self.db.root, '%010d' % self.docid)
self.bibentry = None
self._infiles = {}
def get_docid(self):
"""Return document id of document."""
return self.docid
def _make_docdir(self):
if os.path.exists(self.docdir):
if not os.path.isdir(self.docdir):
raise DocumentError('File exists at intended docdir location: %s' % self.docdir)
else:
os.makedirs(self.docdir)
def _write_files(self):
for name, data in self._infiles.iteritems():
path = os.path.join(self.docdir, name)
with open(path, 'w') as f:
f.write(data)
def _write_bibfile(self):
bibpath = self.get_bibpath()
# reload bibtex only if we have new files
paths = self.get_fullpaths()
if paths:
self._load_bib()
if self.bibentry:
# we put only the first file in the bibtex
# FIXME: does jabref/mendeley spec allow for multiple files?
if paths and not self.bibentry.get_file():
self.bibentry.set_file(paths[0])
self.bibentry.to_file(bibpath)
def _write_tagfile(self):
with open(os.path.join(self.docdir, 'tags'), 'w') as f:
for tag in self.get_tags():
f.write(tag)
f.write('\n')
def _rm_docdir(self):
if os.path.exists(self.docdir) and os.path.isdir(self.docdir):
shutil.rmtree(self.docdir)
def sync(self):
"""Sync document to database."""
# FIXME: add value for modification time
# FIXME: catch db not writable errors
try:
self._make_docdir()
self._write_files()
self._write_bibfile()
self._write_tagfile()
self.db.replace_document(self.docid, self.xapian_doc)
except:
self._rm_docdir()
raise
def purge(self):
"""Purge document from database and root."""
# FIXME: catch db not writable errors
try:
self.db.delete_document(self.docid)
except xapian.DocNotFoundError:
pass
self._rm_docdir()
self.docid = None
########################################
# internal stuff
# add an individual prefix'd term for the document
def _add_term(self, prefix, value):
term = '%s%s' % (prefix, value)
self.xapian_doc.add_term(term)
# remove an individual prefix'd term for the document
def _remove_term(self, prefix, value):
term = '%s%s' % (prefix, value)
try:
self.xapian_doc.remove_term(term)
except xapian.InvalidArgumentError:
pass
# Parse 'text' and add a term to 'message' for each parsed
# word. Each term will be added both prefixed (if prefix is not
# None) and non-prefixed.
# http://xapian.org/docs/bindings/python/
# http://xapian.org/docs/quickstart.html
# http://www.flax.co.uk/blog/2009/04/02/xapian-search-architecture/
def _gen_terms(self, prefix, text):
term_gen = self.db.term_gen
term_gen.set_document(self.xapian_doc)
if prefix:
term_gen.index_text(text, 1, prefix)
term_gen.index_text(text)
# return a list of terms for prefix
def _term_iter(self, prefix=None):
term_iter = iter(self.xapian_doc)
if prefix:
plen = len(prefix)
term = term_iter.skip_to(prefix)
if not term.term.startswith(prefix):
return
yield term.term[plen:]
for term in term_iter:
if prefix:
if not term.term.startswith(prefix):
break
yield term.term[plen:]
else:
yield term.term
def term_iter(self, name=None):
"""Iterator over all terms in the document.
If a prefix is provided, will iterate over only the prefixed
terms, and the prefix will be removed from the returned terms.
"""
prefix = None
if name:
prefix = self.db._find_prefix(name)
if not prefix:
prefix = name
return self._term_iter(prefix)
# set the data object for the document
def _set_data(self, text):
self.xapian_doc.set_data(text)
def get_data(self):
"""Get data object for document."""
return self.xapian_doc.get_data()
########################################
# files
def add_file_data(self, name, data):
"""Add a file data to document.
'name' is the name of the file, 'data is the file data.
File will not copied in to docdir until sync().
"""
# FIXME: set mime type term
# parse the file data into text
text = parse_data(data)
# generate terms from the text
self._gen_terms(None, text)
# set data to be text sample
# FIXME: is this the right thing to put in the data?
summary = text[0:997] + '...'
self._set_data(summary)
# FIXME: should files be renamed to something generic (0.pdf)?
prefix = self.db._find_prefix('file')
self._add_term(prefix, name)
# add it to the cache to be written at sync()
self._infiles[name] = data
def add_file(self, infile):
"""Add a file to document.
Added file will have the same name.
File will not copied in to docdir until sync().
"""
with open(infile, 'r') as f:
data = f.read()
name = os.path.basename(infile)
self.add_file_data(name, data)
def get_files(self):
"""Return files associated with document."""
return list(self.term_iter('file'))
def get_fullpaths(self):
"""Return fullpaths of files associated with document."""
list = []
for path in self.get_files():
# FIXME: this is a hack for old path specifications that
# included the docdir
path = os.path.basename(path)
list.append(os.path.join(self.docdir, path))
return list
########################################
# SOURCES
def _purge_sources_prefix(self, source):
# purge all terms for a given source prefix
prefix = self.db._make_source_prefix(source)
for i in self._term_iter(prefix):
self._remove_term(prefix, i)
self._remove_term(self.db._find_prefix('source'), source)
def add_sid(self, sid):
"""Add source sid to document."""
source, oid = sid.split(':', 1)
source = source.lower()
# remove any existing terms for this source
self._purge_sources_prefix(source)
# add a term for the source
self._add_term(self.db._find_prefix('source'), source)
# add a term for the sid, with source as prefix
self._add_term(self.db._make_source_prefix(source), oid)
def get_sids(self):
"""Return a list of sids for document."""
sids = []
for source in self.term_iter('source'):
for oid in self._term_iter(self.db._make_source_prefix(source)):
sids.append('%s:%s' % (source, oid))
return sids
# TAGS
def add_tags(self, tags):
"""Add tags from list to document."""
prefix = self.db._find_prefix('tag')
for tag in tags:
self._add_term(prefix, tag)
def get_tags(self):
"""Return a list of tags associated with document."""
return list(self.term_iter('tag'))
def remove_tags(self, tags):
"""Remove tags from a document."""
prefix = self.db._find_prefix('tag')
for tag in tags:
self._remove_term(prefix, tag)
# TITLE
def _set_title(self, title):
pt = self.db._find_prefix('title')
for term in self._term_iter(pt):
self._remove_term(pt, term)
# FIXME: what's the clean way to get these prefixes?
for term in self._term_iter('ZS'):
self._remove_term('ZS', term)
self._gen_terms(pt, title)
# AUTHOR
def _set_authors(self, authors):
pa = self.db._find_prefix('author')
for term in self._term_iter(pa):
self._remove_term(pa, term)
# FIXME: what's the clean way to get these prefixes?
for term in self._term_iter('ZA'):
self._remove_term('ZA', term)
self._gen_terms(pa, authors)
# YEAR
def _set_year(self, year):
# FIXME: what to do if year is not an int?
try:
year = int(year)
except ValueError:
pass
prefix = self.db._find_prefix('year')
for term in self._term_iter(prefix):
self._remove_term(prefix, year)
self._add_term(prefix, year)
facet = self.db._find_facet('year')
self.xapian_doc.add_value(facet, xapian.sortable_serialise(year))
########################################
# bibtex
def get_bibpath(self):
"""Return path to document bibtex file."""
return os.path.join(self.docdir, 'bibtex')
def _set_bibkey(self, key):
prefix = self.db._find_prefix('key')
for term in self._term_iter(prefix):
self._remove_term(prefix, term)
self._add_term(prefix, key)
def _index_bibentry(self, bibentry):
authors = bibentry.get_authors()
fields = bibentry.get_fields()
if 'title' in fields:
self._set_title(fields['title'])
if 'year' in fields:
self._set_year(fields['year'])
if authors:
# authors should be a list, so we make a single text string
# FIXME: better way to do this?
self._set_authors(' '.join(authors))
# add any sources in the bibtex
for source in Sources().scan_bibentry(bibentry):
self.add_sid(source.sid)
# FIXME: index 'keywords' field as regular terms
self._set_bibkey(bibentry.key)
def add_bibentry(self, bibentry):
"""Add bibentry object."""
self.bibentry = bibentry
self._index_bibentry(self.bibentry)
def add_bibtex(self, bibtex):
"""Add bibtex to document, as string or file path."""
self.add_bibentry(Bibtex(bibtex)[0])
def _load_bib(self):
if self.bibentry:
return
bibpath = self.get_bibpath()
if os.path.exists(bibpath):
self.bibentry = Bibtex(bibpath)[0]
def get_bibtex(self):
"""Get the bib for document as a bibtex string."""
bibpath = self.get_bibpath()
if os.path.exists(bibpath):
with open(bibpath, 'r') as f:
bibtex = f.read().decode('utf-8')
return bibtex.strip()
def get_bibdata(self):
self._load_bib()
if self.bibentry:
data = self.bibentry.get_fields()
data['authors'] = self.bibentry.get_authors()
return data
def update_from_bibtex(self):
"""Update document metadata from document bibtex."""
self._load_bib()
self._index_bibentry(self.bibentry)
########################################
def get_key(self):
self._load_bib()
if not self.bibentry:
return
return self.bibentry.key
def get_title(self):
"""Get the title from document bibtex."""
self._load_bib()
if not self.bibentry:
return
fields = self.bibentry.get_fields()
if 'title' in fields:
return fields['title']
def get_year(self):
"""Get the title from document bibtex."""
self._load_bib()
if not self.bibentry:
return
fields = self.bibentry.get_fields()
if 'year' in fields:
return fields['year']
def get_urls(self):
"""Get all URLs associated with document."""
sources = Sources()
urls = []
# get urls associated with known sources
for sid in self.get_sids():
urls.append(sources[sid].url)
# get urls from bibtex
self._load_bib()
if self.bibentry:
fields = self.bibentry.get_fields()
if 'url' in fields:
urls.append(fields['url'])
if 'adsurl' in fields:
urls.append(fields['adsurl'])
return urls
xapers-0.6/lib/xapers/nci/ 0000775 0000000 0000000 00000000000 12454273704 0015512 5 ustar 00root root 0000000 0000000 xapers-0.6/lib/xapers/nci/__init__.py 0000664 0000000 0000000 00000001311 12454273704 0017617 0 ustar 00root root 0000000 0000000 """
This file is part of xapers.
Xapers 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.
Xapers 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 notmuch. If not, see .
Copyright 2012
Jameson Rollins
"""
from ui import UI
xapers-0.6/lib/xapers/nci/bibview.py 0000664 0000000 0000000 00000001414 12454273704 0017513 0 ustar 00root root 0000000 0000000 import urwid
from ..cli import initdb
############################################################
class Bibview(urwid.WidgetWrap):
def __init__(self, ui, query):
self.ui = ui
self.ui.set_header([urwid.Text("bibtex: " + query)])
string = ''
with initdb() as db:
if db.count(query) == 0:
self.ui.set_status('No documents found.')
else:
for doc in db.search(query, limit=20):
bibtex = doc.get_bibtex()
if bibtex:
string = string + bibtex + '\n'
self.box = urwid.Filler(urwid.Text(string))
w = self.box
self.__super.__init__(w)
def keypress(self, size, key):
self.ui.keypress(key)
xapers-0.6/lib/xapers/nci/defaults/ 0000775 0000000 0000000 00000000000 12454273704 0017321 5 ustar 00root root 0000000 0000000 xapers-0.6/lib/xapers/nci/defaults/bindings 0000664 0000000 0000000 00000000443 12454273704 0021042 0 ustar 00root root 0000000 0000000 [global]
?: help
s: promptSearch
S: promptSearch
A: promptAdd
q: killBuffer
Q: quit
[search]
n: nextEntry
p: prevEntry]
enter: viewFile
u: viewURL
b: viewBibtex
+: addTags
-: removeTags
u: update
a: archive
meta i: copyID
meta f: copyPath
meta u: copyURL
meta b: copyBibtex
f: filterSearch
xapers-0.6/lib/xapers/nci/help.py 0000664 0000000 0000000 00000002507 12454273704 0017020 0 ustar 00root root 0000000 0000000 import urwid
############################################################
class Help(urwid.WidgetWrap):
def __init__(self, ui, target=None):
self.ui = ui
self.target = target
if self.target:
tname = self.target.__class__.__name__
self.ui.set_header([urwid.Text("help: " + tname)])
else:
self.ui.set_header([urwid.Text("help")])
pile = []
if self.target and hasattr(self.target, 'keys'):
pile.append(urwid.Text('%s commands:' % (tname)))
pile.append(urwid.Text(''))
for key, cmd in self.target.keys.iteritems():
pile.append(self.row('target', cmd, key))
pile.append(urwid.Text(''))
pile.append(urwid.Text(''))
pile.append(urwid.Text('Global commands:'))
pile.append(urwid.Text(''))
for key, cmd in self.ui.keys.iteritems():
pile.append(self.row('ui', cmd, key))
w = urwid.Filler(urwid.Pile(pile))
self.__super.__init__(w)
def row(self, c, cmd, key):
hstring = eval('str(self.%s.%s.__doc__)' % (c, cmd))
return urwid.Columns([('fixed', 10, urwid.Text(key)),
urwid.Text(hstring),
])
def keypress(self, size, key):
self.ui.keypress(key)
xapers-0.6/lib/xapers/nci/search.py 0000664 0000000 0000000 00000031174 12454273704 0017337 0 ustar 00root root 0000000 0000000 import os
import urwid
import subprocess
import collections
from ..cli import initdb
from ..database import DatabaseLockError
############################################################
def xclip(text, isfile=False):
"""Copy text or file contents into X clipboard."""
f = None
if isfile:
f = open(text, 'r')
sin = f
else:
sin = subprocess.PIPE
p = subprocess.Popen(["xclip", "-i"],
stdin=sin)
p.communicate(text)
if f:
f.close()
############################################################
class DocItem(urwid.WidgetWrap):
FIELDS = ['title',
'authors',
'journal',
'year',
'source',
#'tags',
'file',
#'summary',
]
def __init__(self, doc, doc_ind, total_docs):
self.doc = doc
self.docid = self.doc.docid
c1width = 10
field_data = dict.fromkeys(self.FIELDS, '')
field_data['tags'] = ' '.join(self.doc.get_tags())
bibdata = self.doc.get_bibdata()
if bibdata:
for field, value in bibdata.iteritems():
if 'title' == field:
field_data[field] = value
elif 'authors' == field:
field_data[field] = ' and '.join(value[:4])
if len(value) > 4:
field_data[field] += ' et al.'
elif 'year' == field:
field_data[field] = value
if field_data['journal'] == '':
if 'journal' == field:
field_data['journal'] = value
elif 'container-title' == field:
field_data['journal'] = value
elif 'arxiv' == field:
field_data['journal'] = 'arXiv.org'
elif 'dcc' == field:
field_data['journal'] = 'LIGO DCC'
urls = self.doc.get_urls()
if urls:
field_data['source'] = urls[0]
summary = self.doc.get_data()
if not summary:
summary = 'NO FILE'
field_data['summary'] = summary
files = self.doc.get_files()
if files:
field_data['file'] = os.path.basename(files[0])
def gen_field_row(field, value):
if field in ['journal', 'year', 'source']:
color = 'journal'
elif field in ['file']:
color = 'field'
else:
color = field
return urwid.Columns([
('fixed', c1width, urwid.Text(('field', field + ':'))),
urwid.Text((color, value)),
])
self.tag_field = urwid.Text(field_data['tags'])
header = urwid.AttrMap(urwid.Columns([
('fixed', c1width, urwid.Text('id:%d' % (self.docid))),
urwid.AttrMap(self.tag_field, 'tags'),
urwid.Text('%s%% match (%s/%s)' % (doc.matchp, doc_ind, total_docs), align='right'),
]),
'head')
pile = [urwid.AttrMap(urwid.Divider(' '), '', ''),
header
] + [gen_field_row(field, field_data[field]) for field in self.FIELDS]
w = urwid.AttrMap(urwid.AttrMap(urwid.Pile(pile), 'field'),
'',
{'head': 'head focus',
'field': 'field focus',
'tags': 'tags focus',
'title': 'title focus',
'authors': 'authors focus',
'journal': 'journal focus',
},
)
self.__super.__init__(w)
def selectable(self):
return True
def keypress(self, size, key):
return key
############################################################
class DocWalker(urwid.ListWalker):
def __init__(self, docs):
self.docs = docs
self.ndocs = len(docs)
self.focus = 0
self.items = {}
def __getitem__(self, pos):
if pos < 0:
raise IndexError
if pos not in self.items:
self.items[pos] = DocItem(self.docs[pos], pos+1, self.ndocs)
return self.items[pos]
def set_focus(self, focus):
if focus == -1:
focus = self.ndocs - 1
self.focus = focus
self._modified()
def next_position(self, pos):
return pos + 1
def prev_position(self, pos):
return pos - 1
############################################################
class Search(urwid.WidgetWrap):
palette = [
('head', 'dark blue, bold', ''),
('head focus', 'white, bold', 'dark blue'),
('field', 'light gray', ''),
('field focus', '', 'dark gray', '', '', 'g19'),
('tags', 'dark green', ''),
('tags focus', 'light green', 'dark blue'),
('title', 'yellow', ''),
('title focus', 'yellow', 'dark gray', '', 'yellow', 'g19'),
('authors', 'light cyan', ''),
('authors focus', 'light cyan', 'dark gray', '', 'light cyan', 'g19'),
('journal', 'dark magenta', '',),
('journal focus', 'dark magenta', 'dark gray', '', 'dark magenta', 'g19'),
]
keys = collections.OrderedDict([
('n', "nextEntry"),
('down', "nextEntry"),
('p', "prevEntry"),
('up', "prevEntry"),
('<', "firstEntry"),
('>', "lastEntry"),
('=', "refresh"),
('l', "filterSearch"),
('enter', "viewFile"),
('u', "viewURL"),
('b', "viewBibtex"),
('+', "addTags"),
('-', "removeTags"),
('a', "archive"),
('meta i', "copyID"),
('meta f', "copyPath"),
('meta u', "copyURL"),
('meta b', "copyBibtex"),
])
def __init__(self, ui, query=None):
self.ui = ui
self.query = query
count = self.ui.db.count(query)
if count == 0:
self.ui.set_status('No documents found.')
docs = []
else:
docs = [doc for doc in self.ui.db.search(query)]
if count == 1:
cstring = "%d result" % (count)
else:
cstring = "%d results" % (count)
self.ui.set_header([urwid.Columns([
urwid.Text("search: \"%s\"" % (self.query)),
urwid.Text(cstring, align='right'),
])])
self.lenitems = count
self.docwalker = DocWalker(docs)
self.listbox = urwid.ListBox(self.docwalker)
w = self.listbox
self.__super.__init__(w)
def keypress(self, size, key):
if key in self.keys:
cmd = "self.%s()" % (self.keys[key])
eval(cmd)
else:
self.ui.keypress(key)
##########
def refresh(self):
"""refresh current search results"""
entry, pos = self.listbox.get_focus()
self.ui.newbuffer(['search', self.query])
self.ui.killBuffer()
def filterSearch(self):
"""filter current search with additional terms"""
prompt = 'filter search: '
urwid.connect_signal(self.ui.prompt(prompt), 'done', self._filterSearch_done)
def _filterSearch_done(self, newquery):
self.ui.view.set_focus('body')
urwid.disconnect_signal(self.ui, self.ui.prompt, 'done', self._filterSearch_done)
if not newquery:
self.ui.set_status()
return
self.ui.newbuffer(['search', self.query, newquery])
def nextEntry(self):
"""next entry"""
entry, pos = self.listbox.get_focus()
if not entry: return
if pos + 1 >= self.lenitems: return
self.listbox.set_focus(pos + 1)
def prevEntry(self):
"""previous entry"""
entry, pos = self.listbox.get_focus()
if not entry: return
if pos == 0: return
self.listbox.set_focus(pos - 1)
def lastEntry(self):
"""last entry"""
self.listbox.set_focus(-1)
def firstEntry(self):
"""first entry"""
self.listbox.set_focus(0)
def viewFile(self):
"""open document file"""
entry = self.listbox.get_focus()[0]
if not entry: return
path = entry.doc.get_fullpaths()
if not path:
self.ui.set_status('No file for document id:%d.' % entry.docid)
return
path = path[0]
if not os.path.exists(path):
self.ui.set_status('ERROR: id:%d: file not found.' % entry.docid)
return
self.ui.set_status('opening file: %s...' % path)
subprocess.Popen(['xdg-open', path],
stdin=self.ui.devnull,
stdout=self.ui.devnull,
stderr=self.ui.devnull)
def viewURL(self):
"""open document URL in browser"""
entry = self.listbox.get_focus()[0]
if not entry: return
urls = entry.doc.get_urls()
if not urls:
self.ui.set_status('ERROR: id:%d: no URLs found.' % entry.docid)
return
# FIXME: open all instead of just first?
url = urls[0]
self.ui.set_status('opening url: %s...' % url)
subprocess.call(['xdg-open', url],
stdin=self.ui.devnull,
stdout=self.ui.devnull,
stderr=self.ui.devnull)
def viewBibtex(self):
"""view document bibtex"""
entry = self.listbox.get_focus()[0]
if not entry: return
self.ui.newbuffer(['bibview', 'id:' + str(entry.docid)])
def copyID(self):
"""copy document ID to clipboard"""
entry = self.listbox.get_focus()[0]
if not entry: return
docid = "id:%d" % entry.docid
xclip(docid)
self.ui.set_status('yanked docid: %s' % docid)
def copyPath(self):
"""copy document file path to clipboard"""
entry = self.listbox.get_focus()[0]
if not entry: return
path = entry.doc.get_fullpaths()[0]
if not path:
self.ui.set_status('ERROR: id:%d: file path not found.' % entry.docid)
return
xclip(path)
self.ui.set_status('yanked path: %s' % path)
def copyURL(self):
"""copy document URL to clipboard"""
entry = self.listbox.get_focus()[0]
if not entry: return
urls = entry.doc.get_urls()
if not urls:
self.ui.set_status('ERROR: id:%d: URL not found.' % entry.docid)
return
# FIXME: copy all instead of just first?
url = urls[0]
xclip(url)
self.ui.set_status('yanked url: %s' % url)
def copyBibtex(self):
"""copy document bibtex to clipboard"""
entry = self.listbox.get_focus()[0]
if not entry: return
bibtex = entry.doc.get_bibpath()
if not bibtex:
self.ui.set_status('ERROR: id:%d: bibtex not found.' % entry.docid)
return
xclip(bibtex, isfile=True)
self.ui.set_status('yanked bibtex: %s' % bibtex)
def addTags(self):
"""add tags to document (space separated)"""
self.promptTag('+')
def removeTags(self):
"""remove tags from document (space separated)"""
self.promptTag('-')
def promptTag(self, sign):
entry = self.listbox.get_focus()[0]
if not entry: return
if sign is '+':
# FIXME: autocomplete to existing tags
prompt = 'add tags: '
elif sign is '-':
# FIXME: autocomplete to doc tags only
prompt = 'remove tags: '
urwid.connect_signal(self.ui.prompt(prompt), 'done', self._promptTag_done, sign)
def _promptTag_done(self, tag_string, sign):
self.ui.view.set_focus('body')
urwid.disconnect_signal(self, self.ui.prompt, 'done', self._promptTag_done)
if not tag_string:
self.ui.set_status('No tags set.')
return
entry = self.listbox.get_focus()[0]
try:
with initdb(writable=True) as db:
doc = db[entry.docid]
tags = tag_string.split()
if sign is '+':
doc.add_tags(tags)
msg = "Added tags: %s" % (tag_string)
elif sign is '-':
doc.remove_tags(tags)
msg = "Removed tags: %s" % (tag_string)
doc.sync()
tags = doc.get_tags()
entry.tag_field.set_text(' '.join(tags))
except DatabaseLockError as e:
msg = e.msg
self.ui.db.reopen()
self.ui.set_status(msg)
def archive(self):
"""archive document (remove 'new' tag) and advance"""
self._promptTag_done('new', '-')
self.nextEntry()
xapers-0.6/lib/xapers/nci/ui.py 0000664 0000000 0000000 00000011156 12454273704 0016505 0 ustar 00root root 0000000 0000000 """
This file is part of xapers.
Xapers 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.
Xapers 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 notmuch. If not, see .
Copyright 2012, 2013
Jameson Rollins
"""
import os
import sys
import urwid
import collections
from ..cli import initdb
from search import Search
from bibview import Bibview
from help import Help
############################################################
class UI():
palette = [
('header', 'white', 'dark blue'),
('footer', 'white', 'dark blue'),
('prompt', 'black', 'light green'),
]
keys = collections.OrderedDict([
('s', "promptSearch"),
('q', "killBuffer"),
('Q', "quit"),
('?', "help"),
])
def __init__(self, cmd=None):
self.db = initdb()
self.header_string = "Xapers"
self.status_string = "s: search, q: kill buffer, Q: quit Xapers, ?: help and additional commands"
self.view = urwid.Frame(urwid.SolidFill())
self.set_header()
self.set_status()
self.devnull = open('/dev/null', 'rw')
if not cmd:
cmd = ['search', '*']
if cmd[0] == 'search':
query = ' '.join(cmd[1:])
self.buffer = Search(self, query)
elif cmd[0] == 'bibview':
query = ' '.join(cmd[1:])
self.buffer = Bibview(self, query)
elif cmd[0] == 'help':
target = None
if len(cmd) > 1:
target = cmd[1]
if isinstance(target, str):
target = None
self.buffer = Help(self, target)
else:
self.buffer = Help(self)
self.set_status("Unknown command '%s'." % (cmd[0]))
self.merge_palette(self.buffer)
self.view.body = urwid.AttrMap(self.buffer, 'body')
self.mainloop = urwid.MainLoop(
self.view,
self.palette,
unhandled_input=self.keypress,
handle_mouse=False,
)
self.mainloop.screen.set_terminal_properties(colors=88)
self.mainloop.run()
##########
def merge_palette(self, buffer):
if hasattr(buffer, 'palette'):
self.palette = list(set(self.palette) | set(buffer.palette))
def set_header(self, widget=[]):
header = urwid.Columns([('pack', urwid.Text('Xapers '))] + widget)
self.view.set_header(urwid.AttrMap(header, 'header'))
def set_status(self, text=None):
if text:
self.status_string = '%s' % (text)
self.view.set_footer(urwid.AttrMap(urwid.Text(self.status_string), 'footer'))
def newbuffer(self, cmd):
UI(cmd=cmd)
self.set_status()
def prompt(self, string):
prompt = PromptEdit(string)
self.view.set_footer(urwid.AttrMap(prompt, 'prompt'))
self.view.set_focus('footer')
return prompt
##########
def promptSearch(self):
"""search database"""
prompt = 'search: '
urwid.connect_signal(self.prompt(prompt), 'done', self._promptSearch_done)
def _promptSearch_done(self, query):
self.view.set_focus('body')
urwid.disconnect_signal(self, self.prompt, 'done', self._promptSearch_done)
if not query:
self.set_status()
return
self.newbuffer(['search', query])
def killBuffer(self):
"""kill current buffer (quit if last buffer)"""
raise urwid.ExitMainLoop()
def quit(self):
"""quit Xapers"""
sys.exit()
def help(self):
"""help"""
self.newbuffer(['help', self.buffer])
def keypress(self, key):
if key in self.keys:
cmd = "self.%s()" % (self.keys[key])
eval(cmd)
############################################################
class PromptEdit(urwid.Edit):
__metaclass__ = urwid.signals.MetaSignals
signals = ['done']
def keypress(self, size, key):
if key == 'enter':
urwid.emit_signal(self, 'done', self.get_edit_text())
return
elif key == 'esc':
urwid.emit_signal(self, 'done', None)
return
urwid.Edit.keypress(self, size, key)
xapers-0.6/lib/xapers/parser.py 0000664 0000000 0000000 00000002605 12454273704 0016612 0 ustar 00root root 0000000 0000000 import os
##################################################
class ParseError(Exception):
"""Base class for Xapers parser exceptions."""
def __init__(self, msg):
self.msg = msg
def __str__(self):
return self.msg
##################################################
class ParserBase():
"""Base class for Xapers document parsering."""
def __init__(self, path):
self.path = os.path.expanduser(path)
def extract(self):
pass
##################################################
def parse_data(data):
# FIXME: determine mime type
mimetype = 'pdf'
from xapers.parsers.pdf import extract
try:
text = extract(data)
except Exception, e:
raise ParseError("Could not parse file: %s" % e)
return text
def parse_file(path):
# FIXME: determine mime type
mimetype = 'pdf'
try:
mod = __import__('xapers.parsers.' + mimetype, fromlist=['Parser'])
pmod = getattr(mod, 'Parser')
except ImportError:
raise ParseError("Unknown parser '%s'." % mimetype)
if not os.path.exists(path):
raise ParseError("File '%s' not found." % path)
if not os.path.isfile(path):
raise ParseError("File '%s' is not a regular file." % path)
try:
text = pmod(path).extract()
except Exception, e:
raise ParseError("Could not parse file: %s" % e)
return text
xapers-0.6/lib/xapers/parsers/ 0000775 0000000 0000000 00000000000 12454273704 0016420 5 ustar 00root root 0000000 0000000 xapers-0.6/lib/xapers/parsers/__init__.py 0000664 0000000 0000000 00000000000 12454273704 0020517 0 ustar 00root root 0000000 0000000 xapers-0.6/lib/xapers/parsers/pdf.py 0000664 0000000 0000000 00000001135 12454273704 0017543 0 ustar 00root root 0000000 0000000 from ..parser import ParserBase
import subprocess
def extract(data):
cmd = ['pdftotext', '-', '-']
proc = subprocess.Popen(cmd,
stdin=subprocess.PIPE,
stdout=subprocess.PIPE,
stderr=open('/dev/null','w'),
)
(stdout, stderr) = proc.communicate(input=data)
proc.wait()
return stdout
class Parser(ParserBase):
def extract(self):
cmd = ['pdftotext', self.path, '-']
text = subprocess.check_output(cmd, stderr=open('/dev/null','w'))
return text
xapers-0.6/lib/xapers/source.py 0000664 0000000 0000000 00000016015 12454273704 0016616 0 ustar 00root root 0000000 0000000 import os
import re
import pkgutil
from urlparse import urlparse
import sources
from parser import parse_file
##################################################
class SourceError(Exception):
pass
class SourceAttributeError(SourceError):
def __init__(self, source, msg):
self.source = source
self.msg = msg
def __str__(self):
return "Source '%s' does not include a %s." % (self.source.name, self.msg)
##################################################
class Source(object):
"""Xapers class representing an online document source.
The Source object is build from a source nickname (name) and
possibly user-defined source module.
"""
def __init__(self, name, module):
self.name = name
self.module = module
def __repr__(self):
return '%s(%s, %s)' % (self.__class__, self.name, self.module)
def __str__(self):
return self.name
def __getitem__(self, id):
return SourceItem(self, id)
@property
def path(self):
return self.module.__file__
@property
def is_builtin(self):
bpath = os.path.dirname(sources.__file__)
spath = os.path.dirname(self.path)
return os.path.commonprefix([bpath, spath]) == bpath
@property
def description(self):
try:
return self.module.description
except AttributeError:
raise SourceAttributeError(self, "'description' property")
@property
def url(self):
try:
return self.module.url
except AttributeError:
raise SourceAttributeError(self, "'url' property")
@property
def url_regex(self):
try:
return self.module.url_regex
except AttributeError:
raise SourceAttributeError(self, "'url_regex' property")
@property
def scan_regex(self):
try:
return self.module.scan_regex
except AttributeError:
raise SourceAttributeError(self, "'scan_regex' property")
def fetch_bibtex(self, id):
try:
return self.module.fetch_bibtex(id)
except AttributeError:
raise SourceAttributeError(self, "fetch_bibtex() function")
def fetch_file(self, id):
try:
return self.module.fetch_file(id)
except AttributeError:
raise SourceAttributeError(self, "fetch_file() function")
class SourceItem(Source):
"""Xapers class representing an item from an online source.
"""
def __init__(self, source, id):
super(SourceItem, self).__init__(source.name, source.module)
self.id = id
self.sid = '%s:%s' % (self.name, self.id)
def __repr__(self):
s = super(SourceItem, self).__repr__()
return '%s(%s, %s)' % (self.__class__, s, self.id)
def __hash__(self):
return hash(self.sid)
def __eq__(self, other):
if isinstance(other, self.__class__):
return self.sid == other.sid
return NotImplemented
def __ne__(self, other):
return not self.__eq__(other)
def __str__(self):
return self.sid
@property
def url(self):
try:
return self.module.url_format % self.id
except AttributeError:
raise SourceAttributeError(self, "'url_format' property")
def fetch_bibtex(self):
return super(SourceItem, self).fetch_bibtex(self.id)
def fetch_file(self):
return super(SourceItem, self).fetch_file(self.id)
##################################################
class Sources(object):
def __init__(self):
self.sourcespath = sources.__path__
extra = os.getenv('XAPERS_SOURCE_PATH', None)
if extra:
for path in extra.split(':'):
if path:
sourcespath.insert(0, path)
else:
self.sourcespath.insert(0, os.path.expanduser(os.path.join('~','.xapers','sources')))
self._sources = {}
for (loader, name, ispkg) in pkgutil.walk_packages(self.sourcespath):
if ispkg:
continue
#self._modules[name] = loader.find_module(name).load_module(name)
module = loader.find_module(name).load_module(name)
self._sources[name] = Source(name, module)
def __repr__(self):
return '%s(%s)' % (self.__class__, self.sourcespath)
def get_source(self, name, id=None):
try:
source = self._sources[name]
except KeyError:
raise SourceError("unknown source: %s" % name)
if id:
return source[id]
else:
return source
def __contains__(self, source):
return source in self._sources
def __getitem__(self, sid):
name = None
id = None
try:
vals = sid.split(':')
except ValueError:
raise SourceError("could not parse sid string")
name = vals[0]
if len(vals) > 1:
id = vals[1]
return self.get_source(name, id)
def __iter__(self):
return self._sources.itervalues()
def match_source(self, string):
"""Return Source object from URL or source identifier string.
"""
o = urlparse(string)
# if the scheme is http, look for source match
if o.scheme in ['http', 'https']:
for source in self:
try:
match = re.match(source.url_regex, string)
except SourceAttributeError:
# FIXME: warning?
continue
if match:
return source[match.group(1)]
elif o.scheme != '' and o.path != '':
return self.get_source(o.scheme, o.path)
raise SourceError('String matches no known source.')
def scan_file(self, file):
"""Scan document file for source identifiers
Source 'scan_regex' attributes are used.
Returns a list of SourceItem objects.
"""
text = parse_file(file)
items = set()
for source in self:
try:
regex = re.compile(source.scan_regex)
except SourceAttributeError:
# FIXME: warning?
continue
matches = regex.findall(text)
if not matches:
continue
for match in matches:
items.add(source[match])
return list(items)
def scan_bibentry(self, bibentry):
"""Scan bibentry for source identifiers.
Bibentry keys are searched for source names, and bibentry
values are assumed to be individual identifier strings.
Returns a list of SourceItem objects.
"""
fields = bibentry.get_fields()
items = set()
for field, value in fields.iteritems():
field = field.lower()
if field in self:
items.add(self.get_source(field, value))
# FIXME: how do we get around special exception for this?
if 'eprint' in fields:
items.add(self.get_source('arxiv', fields['eprint']))
return list(items)
xapers-0.6/lib/xapers/sources/ 0000775 0000000 0000000 00000000000 12454273704 0016424 5 ustar 00root root 0000000 0000000 xapers-0.6/lib/xapers/sources/__init__.py 0000664 0000000 0000000 00000000000 12454273704 0020523 0 ustar 00root root 0000000 0000000 xapers-0.6/lib/xapers/sources/arxiv.py 0000664 0000000 0000000 00000004126 12454273704 0020132 0 ustar 00root root 0000000 0000000 import urllib
from HTMLParser import HTMLParser
from xapers.bibtex import data2bib
description = "Open access e-print service"
url = 'http://arxiv.org/'
url_format = 'http://arxiv.org/abs/%s'
url_regex = 'http://arxiv.org/(?:abs|pdf|format)/([^/]*)'
# html parser override to override handler methods
class MyHTMLParser(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.lefthead = False
self.title = None
self.author = []
self.year = None
self.sid = None
def handle_starttag(self, tag, attrs):
title = False
author = False
date = False
sid = False
if self.lefthead:
return
if tag != 'meta':
return
for attr in attrs:
if attr[0] == 'name':
if attr[1] == 'citation_title':
title = True
if attr[1] == 'citation_author':
author = True
if attr[1] == 'citation_date':
date = True
if attr[1] == 'citation_arxiv_id':
sid = True
if attr[0] == 'content':
if title:
self.title = attr[1]
if author:
self.author.append(attr[1])
if date:
self.year = attr[1].split('/')[0]
if sid:
self.sid = attr[1]
def handle_endtag(self, tag):
if tag == 'head':
self.lefthead = True
def fetch_bibtex(id):
url = url_format % id
f = urllib.urlopen(url)
html = f.read()
f.close()
parser = MyHTMLParser()
parser.feed(html)
data = {
'arxiv': id,
'title': parser.title,
'authors': parser.author,
'year': parser.year,
'eprint': id,
'url': url_format % id,
}
return data2bib(data, 'arxiv:%s' % id)
def fetch_file(id):
url = 'http://arxiv.org/pdf/%s' % id
f = urllib.urlopen(url)
data = f.read()
f.close()
name = '%s.pdf' % id
return name, data
xapers-0.6/lib/xapers/sources/cryptoeprint.py 0000664 0000000 0000000 00000002500 12454273704 0021535 0 ustar 00root root 0000000 0000000 import urllib
from HTMLParser import HTMLParser
description = "Cryptology ePrint Archive"
url = "https://eprint.iacr.org/"
url_format = 'https://eprint.iacr.org/%s'
url_regex = 'https?://eprint.iacr.org/(\d{4,}/\d{3,})'
# don't know what a scan_regex looks like for IACR eprints. i don't
# think there is one, because i think the submission process happens
# after the pdf is formalized.
# custom definitions for IACR eprints:
bibtex_url = 'https://eprint.iacr.org/eprint-bin/cite.pl?entry=%s'
pdf_url = 'https://eprint.iacr.org/%s.pdf'
# html parser override to override handler methods
class IACRParser(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.pre = False
self.data = None
def handle_starttag(self, tag, attrs):
if (tag == 'pre'):
self.pre = True
def handle_endtag(self, tag):
if (tag == 'pre'):
self.pre = False
def handle_data(self, data):
if (self.pre):
self.data = data
def fetch_bibtex(id):
url = bibtex_url % id
f = urllib.urlopen(url)
html = f.read()
f.close()
p = IACRParser()
p.feed(html)
return unicode(p.data)
def fetch_file(id):
url = pdf_url % id
f = urllib.urlopen(url)
pdf = f.read()
f.close()
return (id.split('/').pop() + '.pdf', pdf)
xapers-0.6/lib/xapers/sources/dcc.py 0000664 0000000 0000000 00000004604 12454273704 0017533 0 ustar 00root root 0000000 0000000 import sys
import pycurl
import cStringIO
import tempfile
from xapers.bibtex import data2bib
description = "LIGO Document Control Center"
url = 'https://dcc.ligo.org/'
url_format = 'https://dcc.ligo.org/%s'
url_regex = 'https://dcc.ligo.org/(?:LIGO-)?([^/]*)'
def dccRetrieveXML(docid):
url = 'https://dcc.ligo.org/Shibboleth.sso/Login?target=https%3A%2F%2Fdcc.ligo.org%2Fcgi-bin%2Fprivate%2FDocDB%2FShowDocument?docid=' + docid + '%26outformat=xml&entityID=https%3A%2F%2Flogin.ligo.org%2Fidp%2Fshibboleth'
curl = pycurl.Curl()
cookies = tempfile.NamedTemporaryFile()
curl.setopt(pycurl.URL, url)
curl.setopt(pycurl.UNRESTRICTED_AUTH, 1)
curl.setopt(pycurl.HTTPAUTH, pycurl.HTTPAUTH_GSSNEGOTIATE)
curl.setopt(pycurl.COOKIEJAR, cookies.name)
curl.setopt(pycurl.USERPWD, ':')
curl.setopt(pycurl.FOLLOWLOCATION, 1)
doc = cStringIO.StringIO()
curl.setopt(pycurl.WRITEFUNCTION, doc.write)
try:
curl.perform()
except:
import traceback
traceback.print_exc(file=sys.stderr)
sys.stderr.flush()
xml = doc.getvalue()
curl.close()
cookies.close()
doc.close()
return xml
def dccXMLExtract(xmlstring):
from xml.dom.minidom import parse, parseString
xml = parseString(xmlstring)
etitle = xml.getElementsByTagName("title")[0].firstChild
if etitle:
title = etitle.data
else:
title = None
alist = xml.getElementsByTagName("author")
authors = []
for author in alist:
authors.append(author.getElementsByTagName("fullname")[0].firstChild.data)
eabstract = xml.getElementsByTagName("abstract")[0].firstChild
if eabstract:
abstract = eabstract.data
else:
abstract = None
# FIXME: find year/date
year = None
return title, authors, year, abstract
def fetch_bibtex(id):
xml = dccRetrieveXML(id)
try:
title, authors, year, abstract = dccXMLExtract(xml)
except:
print >>sys.stderr, xml
raise
data = {
'institution': 'LIGO Laboratory',
'number': id,
'dcc': id,
'url': url_format % id
}
if title:
data['title'] = title
if authors:
data['authors'] = authors
if abstract:
data['abstract'] = abstract
if year:
data['year'] = year
key = 'dcc:%s' % id
btype = '@techreport'
return data2bib(data, key, type=btype)
xapers-0.6/lib/xapers/sources/doi.py 0000664 0000000 0000000 00000002317 12454273704 0017554 0 ustar 00root root 0000000 0000000 import urllib2
description = "Digital Object Identifier"
url = 'https://dx.doi.org/'
# produces URL string when supplied with valid source identifier
url_format = 'https://dx.doi.org/%s'
id_regex = '(10\.\d{4,}[\w\d\:\.\-\/]+)'
# for regex matching a supplied URL. match group 1 should return the
# source identifier string
url_regex = 'https?://dx.doi.org/(10\.\d{4,}[\w\d\:\.\-\/]+)'
# for regex scanning of document text
#scan_regex = '[doi|DOI][\s\.\:]{0,2}(10\.\d{4}[\d\:\.\-\/a-z]+)[A-Z\s]'
#scan_regex = '\b(10[.][0-9]{4,}(?:[.][0-9]+)*/(?:(?!["&\'<>])[[:graph:]])+)\b'
#scan_regex = '(doi|DOI)(10[.][0-9]{4,}(?:[.][0-9]+)*[\/\.](?:(?!["&\'<>])[[:graph:]])+)'
#scan_regex = '(?:doi|DOI)[\s\.\:]{0,2}(10\.\d{4,}[\w\d\:\.\-\/]+)'
scan_regex = '(?:doi|DOI)[\s\.\:]{0,2}' + id_regex
# function to fetch a bibtex entry for a given source identifier
def fetch_bibtex(id):
# http://www.crosscite.org/cn/
url = url_format % id
req = urllib2.Request(url)
req.add_header('Accept', 'application/x-bibtex')
req.add_header('Accept-Charset', 'utf-8')
f = urllib2.urlopen(req)
# DECODE the returned byte string to get a unicode string
bibtex = f.read().decode('utf-8')
f.close
return bibtex
xapers-0.6/lib/xapers/version.py 0000664 0000000 0000000 00000000024 12454273704 0016774 0 ustar 00root root 0000000 0000000 __version__ = '0.6'
xapers-0.6/man/ 0000775 0000000 0000000 00000000000 12454273704 0013444 5 ustar 00root root 0000000 0000000 xapers-0.6/man/man1/ 0000775 0000000 0000000 00000000000 12454273704 0014300 5 ustar 00root root 0000000 0000000 xapers-0.6/man/man1/xapers-adder.1 0000664 0000000 0000000 00000002542 12454273704 0016744 0 ustar 00root root 0000000 0000000 .\" xapers - journal article indexing system
.\"
.\" Copyright 漏 2013 Jameson Rollins
.\"
.\" Xapers 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.
.\"
.\" Xapers 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/ .
.\"
.\" Author: Jameson Rollins
.TH XAPERS 1
.SH NAME
xapers-adder \- "gui" to import individual documents into Xapers database
.SH SYNOPSIS
.B xapers-adder
.IR file.pdf
.SH DESCRIPTION
The specified PDF file is displayed (using \fBxdg-open\fR(1)), then a
terminal is opened (\fBx-terminal-emulator\fR(1)) executing the
following command:
xapers add \-\-file= \-\-tags=new \-\-prompt \-\-view
This program is useful to use as your PDF handler in your browser.
See \fBxapers\fR(1) for more information.
.SH CONTACT
Feel free to email the author:
Jameson Rollins
xapers-0.6/man/man1/xapers.1 0000664 0000000 0000000 00000021571 12454273704 0015672 0 ustar 00root root 0000000 0000000 .\" xapers - journal article indexing system
.\"
.\" Copyright 漏 2013 Jameson Rollins
.\"
.\" Xapers 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.
.\"
.\" Xapers 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/ .
.\"
.\" Author: Jameson Rollins
.TH XAPERS 1
.SH NAME
xapers \- personal journal article indexing system
.
.SH SYNOPSIS
.B xapers
.IR command " [" args " ...]"
.
.SH DESCRIPTION
Xapers is a personal document indexing system, geared towards academic
journal articles. It provides fast search of document text and
bibliographic data (synced from online libraries) and simple document
and bibtex retrieval.
Xapers takes as input document files (as PDF) and source identifiers.
Documents are copied into a local document store (~/.xapers/docs by
default) and text is extracted from the PDF and fully indexed into a
Xapian database. Source identifiers are used to download document
bibliographic data from online digital libraries (see \fBSOURCES\fR
below), which are then parsed and indexed to prefixed terms in the
database. The bibliographic data is also stored as bibtex in the
document store for easy retrieval. Documents can be arbitrarily
tagged.
A curses UI is provided for simple access to documents (see the
\fBview\fR command below). Xapers is ultimately a document indexing
library, though, so development of alternate user interfaces is
encouraged.
Underlying Xapers is the wonderful Xapian database/search engine. See
http://xapian.org/ for more information.
.
.SH MAIN COMMANDS
The following are the main xapers commands. See \fBSEARCH TERMS\fR
below for details of the supported syntax for .
.
.SS add [options] []
Add a document, or update an existing document. Must specify at least
one of \-\-file or \-\-source. If search terms are provided they must
match exactly one document and the matching document is updated with
the newly provided information. Available options:
.RS 4
.TP 4
.BR \-\-source=[|]
Source identifier for document. See \fBSOURCES\fR below. This may
also be a path to a file that contains a single bibtex entry.
.RE
.RS 4
.TP 4
.BR \-\-file[=]
Document file (as PDF) to add. Text of document will be extracted and
indexed. A copy of the file will be placed in the Xapers document
store. If provided without path, xapers will attempt to download file
from source, assuming source supports file downloads.
.RE
.RS 4
.TP 4
.BR \-\-tags=[,...]
Initial tags to apply to document. Multiple tags can be specified,
comma separated.
.RE
.RS 4
.TP 4
.BR \-\-prompt
Prompt user for source/file/tags, if not specified. When prompting
for source information input files are automatically scanned for
source IDs and found ids are displayed.
.RE
.RS 4
.TP 4
.BR \-\-view
View resulting entry in curses UI when done. See the \fBviewP\fR
command below for more info.
.RE
.
.SS import [options]
Import an existing bibtex database. Each bibtex entry will be added
as a new document. If bibtex key, or any sources found in bibtex,
match an existing document, that document is instead updated (this
makes the command effectively idempotent). Any "file" fields will be
parsed for document files to add. Files can be specified as a single
path, or in Mendeley/Jabref format. Available options:
.RS 4
.TP 4
.BR \-\-tags=[,...]
Tags to apply to all imported documents. Multiple tags can be
specified, comma separated.
.RE
.
.SS tag +|- [...] [--]
Add/remove tags from documents. '--' can be used to separate tagging
operations from search terms.
.
.SS search [options]
Search for documents in the database. Document information is printed
to stdout.
.RS 4
.TP 4
.BR \-\-output=[summary|bibtex|tags|sources|keys|files]
Specify document information to be output:
.B summary
outputs a single-line summary of the documents (default).
.B bibtex
outputs bibtex for all documents (if available).
.B tags
outputs all tags associated with documents.
.B sources
outputs all sources associated with documents.
.B keys
outputs all bibtex citation keys associated with documents.
.B files
outputs the full paths to all files associated with documents.
Default is
.B summary.
.RE
.RS 4
.TP 4
.BR \-\-limit=N
Limit number of results returned to N.
.RE
.
.SS bibtex
Short for "search \-\-output=bibtex ".
.
.SS count
Return a simple count of search results.
.
.SS view []
.SS show []
View search results in curses search UI. Documents matching search
are displayed with their bibliographic information and a short text
summary. It allows for manipulating document tags and for retrieved
for document files and source URLs for viewing (see
.B xdg-open(1)
for more info). Initial search terms can be provided, but further
searches can be performed from within the UI. While in the UI type
"?" for available commands.
NOTE: At the moment only the top 20 search results are displayed, due
to synchronous loading restrictions. This obviously needs to be
fixed.
.
.SS export
Copy PDF files of resulting documents into , named with
document titles when available.
.
.SS delete
Delete documents from the database. All document files will purged
from the document store.
.RS 4
.TP 4
.BR \-\-noprompt
Do not prompt to confirm deletion of documents.
.RE
.
.SS restore
Restore a database from existing xapers root.
.
.SH SOURCE COMMANDS
These commands provide access to some of the source module methods. See
\fBSOURCES\fR below.
.
.SS sources
List available sources.
.
.SS source2url [...]
Parse a source identifier string and print the corresponding source
URL.
.
.SS source2bib [...]
Retrieve bibtex from source for a specified URL or source id, and
write to stdout.
.
.SS source2file
Retrieve file from source for a specified URL or source id, and write
to stdout.
.
.SS scandoc
Scan a document file (PDF) for source IDs, and print and recognized
source ids to stdout.
.
.SH SOURCES
Sources are online databases from which document bibliographic data
can be retrieved. In Xapers, online libraries are assigned unique
prefixes. The online libraries associate unique document identifiers
to individual documents. See 'xapers sources' for a list of available
online sources.
Xapers recognizes document a source identifier, or \fBsid\fR, in two
forms:
full URL http://dx.doi.org/10.1364/JOSAA.29.002092
sid of form : doi:10.1364/JOSAA.29.002092
URLs are parsed into sources and source ids when recognized, and this
information is used to retrieve bibtex from the online library
databases. The sources and sids for a given document are stored as
prefixed terms in the Xapers database (see below).
.
.SH SEARCH TERMS
Xapers supports a common syntax for search terms.
Search can consist of free-form text and quoted phrases. Terms can be
combined with standard Boolean operators. All terms are combined with
a logical OR by default. Parentheses can be used to group operators,
but must be protect from shell interpretation. The string '*' will
match all documents in the database.
Additionally, the following prefixed terms are understood (where
indicate user-supplied values):
id: Xapers document ID
author: string in authors (also a:)
title: string in title (also t:)
tag: specific user tag
: specific source id (sid)
source: specific source
key: specific bibtex citation key
year: specific publication year (also y:)
year:.. publication year range (also y:)
year:..
year:..
Publication years must be four-digit integers.
See the following for more information on search terms:
http://xapian.org/docs/queryparser.html
.
.SH ENVIRONMENT
The following environment variables can be used to control the
behavior of xapers:
.
.SS XAPERS_ROOT
Location of the Xapers document store. Defaults to "~/.xapers/docs"
if not specified.
.
.SS XAPERS_SOURCE_PATH
Path specification for location of additional custom Xapers source
modules. Defaults to "~/.xapers/sources" if not specified.
.
.SH CONTACT
Feel free to email the author:
Jameson Rollins
xapers-0.6/screenshot.png 0000664 0000000 0000000 00000064347 12454273704 0015572 0 ustar 00root root 0000000 0000000 塒NG
IHDR _ 9' sBIT坩O IDATx^頋崓$森ngy>瑎欢葊k3@鹅$謳y堀枹H#22楚4,>灛╀DuV @ @ 丩鄘69睡* @ 烡i/熢紷 $鹱&懻镞O~&-桍z报&|喷-! 仯t(熶貙羈廣Y飨c;(佽想"A @ 鵰礰J6i<`淙桠ㄓM囍烏隽鐍鉲y膵? 瑼 漶,~倈Ah;衰\?闖o支G搬砇K|B鎙Y裞导f逰)p L挓畜碸婺@ <伵If4kI*?掬塘!OV0縢yZC踭e)k|8咫f閅曶?'=购inBE-邙@ 闶h2雪#O2J脾屜19sㄒ<黶轺蓀瞱h 嫲湩獲D<涨