commit 1379ef705a50ccc7da5ddb79bfddd5a98548998b Author: Starow Date: Wed Aug 6 11:43:40 2014 +0200 Initial import of AIL framework - Analysis Information Leak framework AIL is a modular framework to analyse potential information leak from unstructured data source like pastes from Past ebin or similar services. AIL framework is flexible and can be extended to support other functionalities to mine sen sitive information diff --git a/LICENSE b/LICENSE new file mode 100644 index 00000000..dba13ed2 --- /dev/null +++ b/LICENSE @@ -0,0 +1,661 @@ + GNU AFFERO GENERAL PUBLIC LICENSE + Version 3, 19 November 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU Affero General Public License is a free, copyleft license for +software and other kinds of works, specifically designed to ensure +cooperation with the community in the case of network server software. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +our General Public Licenses are intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + Developers that use our General Public Licenses protect your rights +with two steps: (1) assert copyright on the software, and (2) offer +you this License which gives you legal permission to copy, distribute +and/or modify the software. + + A secondary benefit of defending all users' freedom is that +improvements made in alternate versions of the program, if they +receive widespread use, become available for other developers to +incorporate. Many developers of free software are heartened and +encouraged by the resulting cooperation. However, in the case of +software used on network servers, this result may fail to come about. +The GNU General Public License permits making a modified version and +letting the public access it on a server without ever releasing its +source code to the public. + + The GNU Affero General Public License is designed specifically to +ensure that, in such cases, the modified source code becomes available +to the community. It requires the operator of a network server to +provide the source code of the modified version running there to the +users of that server. Therefore, public use of a modified version, on +a publicly accessible server, gives the public access to the source +code of the modified version. + + An older license, called the Affero General Public License and +published by Affero, was designed to accomplish similar goals. This is +a different license, not a version of the Affero GPL, but Affero has +released a new version of the Affero GPL which permits relicensing under +this license. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU Affero General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Remote Network Interaction; Use with the GNU General Public License. + + Notwithstanding any other provision of this License, if you modify the +Program, your modified version must prominently offer all users +interacting with it remotely through a computer network (if your version +supports such interaction) an opportunity to receive the Corresponding +Source of your version by providing access to the Corresponding Source +from a network server at no charge, through some standard or customary +means of facilitating copying of software. This Corresponding Source +shall include the Corresponding Source for any work covered by version 3 +of the GNU General Public License that is incorporated pursuant to the +following paragraph. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the work with which it is combined will remain governed by version +3 of the GNU General Public License. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU Affero General Public License from time to time. Such new versions +will be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU Affero General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU Affero General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU Affero General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + + Copyright (C) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see . + +Also add information on how to contact you by electronic and paper mail. + + If your software can interact with users remotely through a computer +network, you should also make sure that it provides a way for users to +get its source. For example, if your program is a web application, its +interface could display a "Source" link that leads users to an archive +of the code. There are many ways you could offer source, and different +solutions will be better for different programs; see section 13 for the +specific requirements. + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU AGPL, see +. diff --git a/README.md b/README.md new file mode 100644 index 00000000..b5883c3b --- /dev/null +++ b/README.md @@ -0,0 +1,187 @@ +AIL +=== + +AIL framework - Analysis Information Leak framework + +AIL is a modular framework to analyse potential information leak from unstructured data source like pastes from Pastebin or similar services. AIL framework is flexible and can be extended to support other functionalities to mine sensitive information. + +![Dashboard](./doc/screenshots/DashboardAIL.png?raw=true "AIL framework dashboard") +![Trending](./doc/screenshots/WordtrendingAIL.png?raw=true "AIL framework wordtrending") + +Requirements & Installation +--------------------------- + +Obviously: +``sudo apt-get install python2.7`` + +But also pip, virtualenv and screen. +``` +sudo apt-get install python-pip +sudo pip install virtualenv +sudo apt-get install screen +``` + +You need to create a variable AILENV that will be the installation path: + +``export AILENV="/home/user/ail"`` + +Then create a Python virtual environment: + +``virtualenv AILENV`` + +And install these few more packets: +``` +sudo apt-get install g++ +sudo apt-get install python-dev +sudo apt-get install python-tk +sudo apt-get install screen +``` + +Then these modules need to be install with pip inside the virtual environment: +(Activating virtualenv) +``` +. ./AILENV/bin/activate +``` + +You'll need to clone langid: +[https://github.com/saffsd/langid.py] +And install it: +``` +python setup.py install +``` + +That's all the packages you can install with pip: + +``` +pip install redis +pip install networkx +pip install crcmod +pip install mmh3 +pip install dnspython +pip install pyzmq +pip install texttable ----- Queues Monitoring (Optional) +pip install -U textblob +python -m textblob.download_corpora +pip install python-magic +pip install numpy +pip install flask ----- (Optional) +pip install nltk +pip install matplotlib ----- (sudo ln -s freetype2/ft2build.h in /usr/include/) +pip install pybloomfiltermmap ----- (you may need to sudo apt-get install libssl-dev) +``` + +Installing Redis & Level DB +--------------------------- + +Assuming that you install everything under /opt/ with adequate permissions: + +``` +wget http://download.redis.io/releases/redis-2.8.12.tar.gz +tar -xvf redis-2.8.12.tar.gz -C /opt/ +``` +And follow the README after extraction. + +When redis is properly installed you can edit your own config files for +the different required databases or just take the config from the project +located under ``/config/`` + +``` +git clone https://github.com/KDr2/redis-leveldb.git +``` +Follow the redis-leveldb README. + +Then create these directories + +``` +cd $AILENV + mkdir PASTES + mkdir Blooms + mkdir dumps + +mkdir LEVEL_DB_DATA +cd LEVEL_DB_DATA/ + mkdir 2014 + mkdir 2013 +``` + +Starting AIL +------------ + +If you installed all the requirements described above, you should be able to start AIL framework: + +``` +cd $AILENV +cd bin +./LAUNCH.sh +``` + +Then you can browse the status of the AIL framework at the following URL: + + ``http://localhost:7000/`` + +Create a new module +------------------- + +Assuming you already download the project and configure everything: + +* Redis databases [http://redis.io/] +* Redis Level DB [https://github.com/KDr2/redis-leveldb] + +This module will be recover from a stream all the Tor .onion addresses: +"http://3g2upl4pq6kufc4m.onion/" Which look like this. + +Basically we want to match all paste in with ``.onion`` addresses inside. + +For that you can already use the module ``ZMQ_PubSub_Categ`` and just +create your own category file in: ``/file/`` here it will be ``/file/onion_categ``. + +You need also to link this file inside another file (list_categ_files). + +Inside the file "onion_categ", you will add the word "onion" (don't forget the carriage return). + +Once it's done, at the launch of the AIL framework, every paste with the word onion inside them +will be forwarded on a specific channel (onion_categ). + +Then what you want to do it's recovering these pastes to extract these .onion addresses. + +To do that, you'll need to create 2 scripts: + ``ZMQ_Sub_Onion_Q.py`` (Redis bufferizing) + ``ZMQ_Sub_Onion.py`` (The extraction) + +Those two files are there as an example. + +Overview +-------- + +Here is a "chained tree" to show how all ZMQ Modules are linked and how the informations +(mainly the paste) is going through them. + +The onion module is interfaced at top down level of this tree (like the ZMQ_Sub_Urls module). + +All modules that you want to create using the "tokenization method" and the "categories system" need to be created at this level. + +If you want to create a general module (e.g. using all pastes), this module need to be created at the same level than ZMQ_Sub_Duplicate. + +![ZMQTree](./doc/dia/ZMQ_Queuing_Tree.jpg?raw=true "ZMQ Tree") + +LICENSE +------- + +``` + Copyright (C) 2014 Jules Debra + Copyright (C) 2014 CIRCL - Computer Incident Response Center Luxembourg (℅ smile gie) + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see . +``` + diff --git a/bin/Dir.py b/bin/Dir.py new file mode 100755 index 00000000..353beeb3 --- /dev/null +++ b/bin/Dir.py @@ -0,0 +1,46 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +import argparse +import redis +from bin.pubsublogger import publisher +from bin.packages.lib_words import create_dirfile +import ConfigParser + + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read('./packages/config.cfg') + + parser = argparse.ArgumentParser( + description='''This script is a part of the Analysis Information Leak + framework. It create a redis list called "listfile" which contain + the absolute filename of all the files from the directory given in + the argument "directory".''', + epilog='Example: ./Dir.py /home/2013/03/') + + parser.add_argument('directory', type=str, + help='The directory to run inside', action='store') + + parser.add_argument('-db', type=int, default=0, + help='The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], action='store') + + parser.add_argument('-ow', help='trigger the overwritting mode', + action='store_true') + + args = parser.parse_args() + + r_serv = redis.StrictRedis(host=cfg.get("Redis_Queues", "host"), + port=cfg.getint("Redis_Queues", "port"), + db=cfg.getint("Redis_Queues", "db")) + + publisher.channel = "Script" + + create_dirfile(r_serv, args.directory, args.ow) + +if __name__ == "__main__": + main() diff --git a/bin/LAUNCH.sh b/bin/LAUNCH.sh new file mode 100755 index 00000000..5b4ffdf8 --- /dev/null +++ b/bin/LAUNCH.sh @@ -0,0 +1,226 @@ +#!/bin/bash + +GREEN="\\033[1;32m" +DEFAULT="\\033[0;39m" +RED="\\033[1;31m" +ROSE="\\033[1;35m" +BLUE="\\033[1;34m" +WHITE="\\033[0;02m" +YELLOW="\\033[1;33m" +CYAN="\\033[1;36m" + +#Modify these PATH +export PATH=$(pwd):$PATH +export PATH=/opt/redis-2.8.12/src/:$PATH +export PATH=/opt/redis-leveldb/:$PATH + +function helptext { + echo -e $YELLOW" + + .o. ooooo ooooo + .888. \`888' \`888' + .8\"888. 888 888 + .8' \`888. 888 888 + .88ooo8888. 888 888 + .8' \`888. 888 888 o + o88o o8888o o o888o o o888ooooood8 + + Analysis Information Leak framework + "$DEFAULT" + This script launch: + "$CYAN" + - All the ZMQ queuing modules. + - All the ZMQ processing modules. + - All Redis in memory servers. + - All Level-DB on disk servers. + "$DEFAULT" + (Inside screen Daemons) + "$RED" + But first of all you'll need to edit few path where you installed + your redis & leveldb servers. + "$DEFAULT" + Usage: + ----- + " +} + +function launching_redis { + conf_dir='/home/user/AIL/configs/' + + screen -dmS "Redis" + sleep 0.1 + echo -e $GREEN"\t* Launching Redis servers"$DEFAULT + screen -S "Redis" -X screen -t "6379" bash -c 'redis-server '$conf_dir'6379.conf ; read x' + sleep 0.1 + screen -S "Redis" -X screen -t "6380" bash -c 'redis-server '$conf_dir'6380.conf ; read x' + sleep 0.1 + screen -S "Redis" -X screen -t "6381" bash -c 'redis-server '$conf_dir'6381.conf ; read x' +} + +function launching_lvldb { + #Want to launch more level_db? + lvdbhost='127.0.0.1' + lvdbdir='/home/user/LEVEL_DB_DATA/' + db1_y='2013' + db2_y='2014' + nb_db=13 + + screen -dmS "LevelDB" + sleep 0.1 + echo -e $GREEN"\t* Launching Levels DB servers"$DEFAULT + #Add lines here with appropriates options. + screen -S "LevelDB" -X screen -t "2013" bash -c 'redis-leveldb -H '$lvdbhost' -D '$lvdbdir'2013/ -P '$db1_y' -M '$nb_db'; read x' + sleep 0.1 + screen -S "LevelDB" -X screen -t "2014" bash -c 'redis-leveldb -H '$lvdbhost' -D '$lvdbdir'2014/ -P '$db2_y' -M '$nb_db'; read x' +} + +function launching_logs { + screen -dmS "Logging" + sleep 0.1 + echo -e $GREEN"\t* Launching logging process"$DEFAULT + screen -S "Logging" -X screen -t "LogQueue" bash -c './log_subscriber -p 6380 -c Queuing -l ../logs/; read x' + sleep 0.1 + screen -S "Logging" -X screen -t "LogScript" bash -c './log_subscriber -p 6380 -c Script -l ../logs/; read x' +} + +function launching_queues { + screen -dmS "Queue" + sleep 0.1 + + echo -e $GREEN"\t* Launching redis ZMQ queues"$DEFAULT + screen -S "Queue" -X screen -t "QFeed" bash -c './ZMQ_Feed_Q.py; read x' + sleep 0.1 + screen -S "Queue" -X screen -t "QDuplicate" bash -c './ZMQ_Sub_Duplicate_Q.py; read x' + sleep 0.1 + screen -S "Queue" -X screen -t "QAttributes" bash -c './ZMQ_Sub_Attributes_Q.py; read x' + sleep 0.1 + screen -S "Queue" -X screen -t "Qlines" bash -c './ZMQ_PubSub_Lines_Q.py; read x' + sleep 0.1 + screen -S "Queue" -X screen -t "QCateg" bash -c './ZMQ_PubSub_Categ_Q.py; read x' + sleep 0.1 + screen -S "Queue" -X screen -t "QTokenize" bash -c './ZMQ_PubSub_Tokenize_Q.py; read x' + sleep 0.1 + screen -S "Queue" -X screen -t "Qcreditcard" bash -c './ZMQ_Sub_CreditCards_Q.py; read x' + sleep 0.1 + screen -S "Queue" -X screen -t "QOnion" bash -c './ZMQ_Sub_Onion_Q.py; read x' + sleep 0.1 + screen -S "Queue" -X screen -t "Qmails" bash -c './ZMQ_Sub_Mails_Q.py; read x' + sleep 0.1 + screen -S "Queue" -X screen -t "Qurls" bash -c './ZMQ_Sub_Urls_Q.py; read x' + sleep 0.1 + screen -S "Queue" -X screen -t "QCurve" bash -c './ZMQ_Sub_Curve_Q.py; read x' +} + +function launching_scripts { + screen -dmS "Script" + sleep 0.1 + + echo -e $GREEN"\t* Launching ZMQ scripts"$DEFAULT + + screen -S "Script" -X screen -t "Feed" bash -c './ZMQ_Feed.py; read x' + sleep 0.1 + screen -S "Script" -X screen -t "Duplicate" bash -c './ZMQ_Sub_Duplicate.py; read x' + sleep 0.1 + screen -S "Script" -X screen -t "Attributes" bash -c './ZMQ_Sub_Attributes.py; read x' + sleep 0.1 + screen -S "Script" -X screen -t "Lines" bash -c './ZMQ_PubSub_Lines.py; read x' + sleep 0.1 + screen -S "Script" -X screen -t "Categ" bash -c './ZMQ_PubSub_Categ.py; read x' + sleep 0.1 + screen -S "Script" -X screen -t "Tokenize" bash -c './ZMQ_PubSub_Tokenize.py; read x' + sleep 0.1 + screen -S "Script" -X screen -t "Creditcard" bash -c './ZMQ_Sub_CreditCards.py; read x' + sleep 0.1 + screen -S "Script" -X screen -t "Onion" bash -c './ZMQ_Sub_Onion.py; read x' + sleep 0.1 + screen -S "Script" -X screen -t "Mails" bash -c './ZMQ_Sub_Mails.py; read x' + sleep 0.1 + screen -S "Script" -X screen -t "Urls" bash -c './ZMQ_Sub_Urls.py; read x' + sleep 0.1 + screen -S "Script" -X screen -t "Curve" bash -c './ZMQ_Sub_Curve.py; read x' +} + +#If no params, display the help +#[[ $@ ]] || { helptext; exit 1;} + +helptext; + +############### TESTS ################### +isredis=`screen -ls | awk '/\.Redis\t/ {print strtonum($1)}'` +islvldb=`screen -ls | awk '/\.LevelDB\t/ {print strtonum($1)}'` +islogged=`screen -ls | awk '/\.Logging\t/ {print strtonum($1)}'` +isqueued=`screen -ls | awk '/\.Queue\t/ {print strtonum($1)}'` +isscripted=`screen -ls | awk '/\.Script\t/ {print strtonum($1)}'` + +options=("Redis" "LevelDB" "Logs" "Queues" "Scripts" "Killall" "Shutdown") + +menu() { + echo "What do you want to Launch?:" + for i in ${!options[@]}; do + printf "%3d%s) %s\n" $((i+1)) "${choices[i]:- }" "${options[i]}" + done + [[ "$msg" ]] && echo "$msg"; : +} + +prompt="Check an option (again to uncheck, ENTER when done): " +while menu && read -rp "$prompt" num && [[ "$num" ]]; do + [[ "$num" != *[![:digit:]]* ]] && (( num > 0 && num <= ${#options[@]} )) || { + msg="Invalid option: $num"; continue + } + ((num--)); msg="${options[num]} was ${choices[num]:+un}checked" + [[ "${choices[num]}" ]] && choices[num]="" || choices[num]="+" +done + +for i in ${!options[@]}; do + if [[ "${choices[i]}" ]]; then + case ${options[i]} in + Redis) + if [[ ! $isredis ]]; then + launching_redis; + else + echo -e $RED"\t* A screen is already launched"$DEFAULT + fi + ;; + LevelDB) + if [[ ! $islvldb ]]; then + launching_lvldb; + else + echo -e $RED"\t* A screen is already launched"$DEFAULT + fi + ;; + Logs) + if [[ ! $islogged ]]; then + launching_logs; + else + echo -e $RED"\t* A screen is already launched"$DEFAULT + fi + ;; + Queues) + if [[ ! $isqueued ]]; then + launching_queues; + else + echo -e $RED"\t* A screen is already launched"$DEFAULT + fi + ;; + Scripts) + if [[ ! $isscripted ]]; then + launching_scripts; + else + echo -e $RED"\t* A screen is already launched"$DEFAULT + fi + ;; + Killall) + if [[ $isredis || $islvldb || $islogged || $isqueued || $isscripted ]]; then + kill $isredis $islvldb $islogged $isqueued $isscripted + echo -e $ROSE`screen -ls`$DEFAULT + echo -e $GREEN"\t* $isredis $islvldb $islogged $isqueued $isscripted killed."$DEFAULT + else + echo -e $RED"\t* No screen to kill"$DEFAULT + fi + ;; + Shutdown) + bash -c "./Shutdown.py" + ;; + esac + fi +done diff --git a/bin/Queues_Monitoring.py b/bin/Queues_Monitoring.py new file mode 100755 index 00000000..2439e838 --- /dev/null +++ b/bin/Queues_Monitoring.py @@ -0,0 +1,61 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +import redis +import argparse +import ConfigParser +import time +import os +from pubsublogger import publisher +import texttable + + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read('./packages/config.cfg') + + # SCRIPT PARSER # + parser = argparse.ArgumentParser( + description='''This script is a part of the Assisted Information Leak framework.''', + epilog='''''') + + parser.add_argument('-db', type=int, default=0, + help='The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], action='store') + + # REDIS # + r_serv = redis.StrictRedis( + host=cfg.get("Redis_Queues", "host"), + port=cfg.getint("Redis_Queues", "port"), + db=cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + channel = cfg.get("PubSub_Global", "channel") + + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format(channel)) + + while True: + table = texttable.Texttable() + table.header(["Queue name", "#Items"]) + row = [] + for queue in r_serv.smembers("queues"): + current = r_serv.llen(queue) + current = current - r_serv.llen(queue) + row.append((queue, r_serv.llen(queue))) + + time.sleep(0.5) + row.sort() + table.add_rows(row, header=False) + os.system('clear') + print table.draw() + + +if __name__ == "__main__": + main() diff --git a/bin/Repartition_graph.py b/bin/Repartition_graph.py new file mode 100755 index 00000000..09889310 --- /dev/null +++ b/bin/Repartition_graph.py @@ -0,0 +1,97 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +import redis, argparse, zmq, ConfigParser, time, os +from pubsublogger import publisher +from packages import ZMQ_PubSub +import texttable + +import numpy as np +import matplotlib.pyplot as plt +from pylab import * + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read('./packages/config.cfg') + + # SCRIPT PARSER # + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information + Leak framework.''', + epilog = '''''') + + parser.add_argument('-f', + type = str, + metavar = "filename", + default = "figure", + help = 'The absolute path name of the "figure.png"', + action = 'store') + + args = parser.parse_args() + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Level_DB_Hashs", "host"), + port = cfg.getint("Redis_Level_DB_Hashs", "port"), + db = cfg.getint("Redis_Level_DB_Hashs", "db")) + + # LOGGING # + publisher.channel = "Graph" + + # FUNCTIONS # + publisher.info("""Creating the Repartition Graph""") + + total_list = [] + codepad_list = [] + pastie_list = [] + pastebin_list = [] + for hash in r_serv.keys(): + total_list.append(r_serv.scard(hash)) + + code = 0 + pastie = 0 + pastebin = 0 + for paste in r_serv.smembers(hash): + source = paste.split("/")[5] + + if source == "codepad.org": + code = code + 1 + elif source == "pastie.org": + pastie = pastie + 1 + elif source == "pastebin.com": + pastebin = pastebin + 1 + + codepad_list.append(code) + pastie_list.append(pastie) + pastebin_list.append(pastebin) + + codepad_list.sort(reverse = True) + pastie_list.sort(reverse = True) + pastebin_list.sort(reverse = True) + + total_list.sort(reverse = True) + + + plt.plot(codepad_list, 'b', label='Codepad.org') + plt.plot(pastebin_list, 'g', label='Pastebin.org') + plt.plot(pastie_list, 'y', label='Pastie.org') + plt.plot(total_list, 'r', label='Total') + + plt.xscale('log') + plt.xlabel('Hashs') + plt.ylabel('Occur[Hash]') + plt.title('Repartition') + plt.legend() + plt.grid() + plt.tight_layout() + + plt.savefig(args.f+".png", dpi=None, facecolor='w', edgecolor='b', + orientation='portrait', papertype=None, format="png", + transparent=False, bbox_inches=None, pad_inches=0.1, + frameon=True) + +if __name__ == "__main__": + main() diff --git a/bin/Shutdown.py b/bin/Shutdown.py new file mode 100755 index 00000000..ae0e3024 --- /dev/null +++ b/bin/Shutdown.py @@ -0,0 +1,65 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_Feed_Q Module +===================== + +This module is consuming the Redis-list created by the ZMQ_Feed_Q Module, +And save the paste on disk to allow others modules to work on them. + +..todo:: Be able to choose to delete or not the saved paste after processing. +..todo:: Store the empty paste (unprocessed) somewhere in Redis. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Need running Redis instances. +*Need the ZMQ_Feed_Q Module running to be able to work properly. + +""" +import redis, ConfigParser +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + #REDIS + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + +#### SCRIPTS #### + r_serv.sadd("SHUTDOWN_FLAGS", "Feed") + r_serv.sadd("SHUTDOWN_FLAGS", "Categ") + r_serv.sadd("SHUTDOWN_FLAGS", "Lines") + r_serv.sadd("SHUTDOWN_FLAGS", "Tokenize") + r_serv.sadd("SHUTDOWN_FLAGS", "Attributes") + r_serv.sadd("SHUTDOWN_FLAGS", "Creditcards") + r_serv.sadd("SHUTDOWN_FLAGS", "Duplicate") + r_serv.sadd("SHUTDOWN_FLAGS", "Mails") + r_serv.sadd("SHUTDOWN_FLAGS", "Onion") + r_serv.sadd("SHUTDOWN_FLAGS", "Urls") + + r_serv.sadd("SHUTDOWN_FLAGS", "Feed_Q") + r_serv.sadd("SHUTDOWN_FLAGS", "Categ_Q") + r_serv.sadd("SHUTDOWN_FLAGS", "Lines_Q") + r_serv.sadd("SHUTDOWN_FLAGS", "Tokenize_Q") + r_serv.sadd("SHUTDOWN_FLAGS", "Attributes_Q") + r_serv.sadd("SHUTDOWN_FLAGS", "Creditcards_Q") + r_serv.sadd("SHUTDOWN_FLAGS", "Duplicate_Q") + r_serv.sadd("SHUTDOWN_FLAGS", "Mails_Q") + r_serv.sadd("SHUTDOWN_FLAGS", "Onion_Q") + r_serv.sadd("SHUTDOWN_FLAGS", "Urls_Q") + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Feed.py b/bin/ZMQ_Feed.py new file mode 100755 index 00000000..710088f4 --- /dev/null +++ b/bin/ZMQ_Feed.py @@ -0,0 +1,103 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_Feed_Q Module +===================== + +This module is consuming the Redis-list created by the ZMQ_Feed_Q Module, +And save the paste on disk to allow others modules to work on them. + +..todo:: Be able to choose to delete or not the saved paste after processing. +..todo:: Store the empty paste (unprocessed) somewhere in Redis. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Need running Redis instances. +*Need the ZMQ_Feed_Q Module running to be able to work properly. + +""" +import redis, zmq, ConfigParser, sys, base64, gzip, os, time +#import zlib +from pubsublogger import publisher +from packages import ZMQ_PubSub + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + #REDIS + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # ZMQ # + channel = cfg.get("Feed", "topicfilter") + + #Subscriber + subscriber_name = "feed" + subscriber_config_section = "Feed" + #Publisher + publisher_name = "pubfed" + publisher_config_section = "PubSub_Global" + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, channel, subscriber_name) + PubGlob = ZMQ_PubSub.ZMQPub(configfile, publisher_config_section, publisher_name) + + # LOGGING # + publisher.channel = "Script" + publisher.info("Feed Script started to receive & publish.") + + while True: + + message = Sub.get_msg_from_queue(r_serv) + #Recovering the streamed message informations. + if message != None: + if len(message.split()) == 3: + topic, paste, gzip64encoded = message.split() + print paste + else: + #TODO Store the name of the empty paste inside a Redis-list. + print "Empty Paste: not processed" + publisher.debug("Empty Paste: {0} not processed".format(paste)) + continue + else: + if r_serv.sismember("SHUTDOWN_FLAGS", "Feed"): + r_serv.srem("SHUTDOWN_FLAGS", "Feed") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + print "Empty Queues: Waiting..." + time.sleep(10) + continue + #Creating the full filepath + filename = cfg.get("Directories", "pastes") + paste + + if not os.path.exists(filename.rsplit("/", 1)[0]): + os.makedirs(filename.rsplit("/", 1)[0]) + else: + #Path already existing + pass + + decoded_gzip = base64.standard_b64decode(gzip64encoded) + #paste, zlib.decompress(decoded_gzip, zlib.MAX_WBITS|16) + + with open(filename, 'wb') as F: + F.write(decoded_gzip) + + msg = cfg.get("PubSub_Global", "channel")+" "+filename + PubGlob.send_message(msg) + publisher.debug("{0} Published".format(msg)) + + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Feed_Q.py b/bin/ZMQ_Feed_Q.py new file mode 100755 index 00000000..4f267552 --- /dev/null +++ b/bin/ZMQ_Feed_Q.py @@ -0,0 +1,64 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +""" +The ZMQ_Feed_Q Module +===================== + +This module is the first of the ZMQ tree processing. +It's subscribe to a data stream and put the received messages +into a Redis-list waiting to be popped later by others scripts + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Need running Redis instances. +*Messages from the stream should be formated as follow: + "channel_name"+" "+/path/to/the/paste.gz+" "base64_data_encoded_paste" + +""" +import redis, zmq, ConfigParser +from pubsublogger import publisher +from packages import ZMQ_PubSub + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + p_serv = r_serv.pipeline(False) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + channel = cfg.get("Feed", "topicfilter") + Sub = ZMQ_PubSub.ZMQSub(configfile, "Feed", channel, "feed") + + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format(channel)) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Feed_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Feed_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_PubSub_Categ.py b/bin/ZMQ_PubSub_Categ.py new file mode 100755 index 00000000..f41daf14 --- /dev/null +++ b/bin/ZMQ_PubSub_Categ.py @@ -0,0 +1,138 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_PubSub_Categ Module +============================ + +This module is consuming the Redis-list created by the ZMQ_PubSub_Tokenize_Q Module. + +Each words files created under /files/ are representing categories. +This modules take these files and compare them to +the stream of data given by the ZMQ_PubSub_Tokenize_Q Module. + +When a word from a paste match one or more of these words file, the filename of +the paste is published/forwarded to the next modules. + +Each category (each files) are representing a dynamic channel. +This mean that if you create 1000 files under /files/ you'll have 1000 channels +where every time there is a matching word to a category, the paste containing +this word will be pushed to this specific channel. + +..note:: The channel will have the name of the file created. + +Implementing modules can start here, create your own category file, +and then create your own module to treat the specific paste matching this category. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Need running Redis instances. (Redis) +*Categories files of words in /files/ need to be created +*Need the ZMQ_PubSub_Tokenize_Q Module running to be able to work properly. + +""" +import redis, argparse, zmq, ConfigParser, time +from packages import Paste as P +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # SCRIPT PARSER # + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information + Leak framework.''', + epilog = '''''') + + parser.add_argument('-l', + type = str, + default = "../files/list_categ_files", + help = 'Path to the list_categ_files (../files/list_categ_files)', + action = 'store') + + args = parser.parse_args() + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + channel = cfg.get("PubSub_Words", "channel_0") + subscriber_name = "categ" + subscriber_config_section = "PubSub_Words" + + publisher_name = "pubcateg" + publisher_config_section = "PubSub_Categ" + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, channel, subscriber_name) + Pub = ZMQ_PubSub.ZMQPub(configfile, publisher_config_section, publisher_name) + + # FUNCTIONS # + publisher.info("Script Categ subscribed to channel {0}".format(cfg.get("PubSub_Words", "channel_0"))) + + with open(args.l, 'rb') as L: + tmp_dict = {} + + for num, fname in enumerate(L): + #keywords temp list + tmp_list = [] + + with open(fname[:-1], 'rb') as LS: + + for num, kword in enumerate(LS): + tmp_list.append(kword[:-1]) + + tmp_dict[fname.split('/')[-1][:-1]] = tmp_list + + paste_words = [] + message = Sub.get_msg_from_queue(r_serv) + prec_filename = None + + while True: + if message != None: + channel, filename, word, score = message.split() + + if prec_filename == None or filename != prec_filename: + PST = P.Paste(filename) + + prec_filename = filename + + for categ, list in tmp_dict.items(): + + if word.lower() in list: + channel = categ + msg = channel+" "+PST.p_path+" "+word+" "+score + Pub.send_message(msg) + #dico_categ.add(categ) + + publisher.info('{0};{1};{2};{3};{4}'.format("Categ", PST.p_source, PST.p_date, PST.p_name,"Detected "+score+" "+word)) + + else: + if r_serv.sismember("SHUTDOWN_FLAGS", "Categ"): + r_serv.srem("SHUTDOWN_FLAGS", "Categ") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + publisher.debug("Script Categ is Idling 10s") + time.sleep(10) + + message = Sub.get_msg_from_queue(r_serv) + + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_PubSub_Categ_Q.py b/bin/ZMQ_PubSub_Categ_Q.py new file mode 100755 index 00000000..f823a9f8 --- /dev/null +++ b/bin/ZMQ_PubSub_Categ_Q.py @@ -0,0 +1,61 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_PubSub_Categ_Q Module +============================ + +This module subscribe to a Publisher stream and put the received messages +into a Redis-list waiting to be popped later by others scripts. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Running Redis instances. +*Should register to the Publisher "ZMQ_PubSub_Tokenize" + +""" +import redis, zmq, ConfigParser +from pubsublogger import publisher +from packages import ZMQ_PubSub + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + channel = cfg.get("PubSub_Words", "channel_0") + subscriber_name = "categ" + subscriber_config_section = "PubSub_Words" + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, channel, subscriber_name) + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format(channel)) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Categ_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Categ_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_PubSub_Lines.py b/bin/ZMQ_PubSub_Lines.py new file mode 100755 index 00000000..8f440f6f --- /dev/null +++ b/bin/ZMQ_PubSub_Lines.py @@ -0,0 +1,128 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +""" +The ZMQ_PubSub_Lines Module +============================ + +This module is consuming the Redis-list created by the ZMQ_PubSub_Line_Q Module. + +It perform a sorting on the line's length and publish/forward them to differents +channels: + +*Channel 1 if max length(line) < max +*Channel 2 if max length(line) > max + +The collected informations about the processed pastes +(number of lines and maximum length line) are stored in Redis. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Need running Redis instances. (LevelDB & Redis) +*Need the ZMQ_PubSub_Line_Q Module running to be able to work properly. + +""" +import redis, argparse, zmq, ConfigParser, time +from packages import Paste as P +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # SCRIPT PARSER # + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information + Leak framework.''', + epilog = '''''') + + parser.add_argument('-max', + type = int, + default = 500, + help = 'The limit between "short lines" and "long lines" (500)', + action = 'store') + + args = parser.parse_args() + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Data_Merging", "host"), + port = cfg.getint("Redis_Data_Merging", "port"), + db = cfg.getint("Redis_Data_Merging", "db")) + + r_serv1 = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + p_serv = r_serv.pipeline(False) + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + #Subscriber + channel = cfg.get("PubSub_Global", "channel") + subscriber_name = "line" + subscriber_config_section = "PubSub_Global" + + #Publisher + publisher_config_section = "PubSub_Longlines" + publisher_name = "publine" + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, channel, subscriber_name) + + Pub = ZMQ_PubSub.ZMQPub(configfile, publisher_config_section, publisher_name) + + channel_0 = cfg.get("PubSub_Longlines", "channel_0") + channel_1 = cfg.get("PubSub_Longlines", "channel_1") + + # FUNCTIONS # + publisher.info("""Lines script Subscribed to channel {0} and Start to publish + on channel {1}, {2}""".format(cfg.get("PubSub_Global", "channel"), + cfg.get("PubSub_Longlines", "channel_0"), + cfg.get("PubSub_Longlines", "channel_1"))) + + while True: + try: + message = Sub.get_msg_from_queue(r_serv1) + if message != None: + PST = P.Paste(message.split(" ",-1)[-1]) + else: + if r_serv1.sismember("SHUTDOWN_FLAGS", "Lines"): + r_serv1.srem("SHUTDOWN_FLAGS", "Lines") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + publisher.debug("Tokeniser is idling 10s") + time.sleep(10) + continue + + lines_infos = PST.get_lines_info() + + PST.save_attribute_redis(r_serv, "p_nb_lines", lines_infos[0]) + PST.save_attribute_redis(r_serv, "p_max_length_line", lines_infos[1]) + + r_serv.sadd("Pastes_Objects",PST.p_path) + if lines_infos[1] >= args.max: + msg = channel_0+" "+PST.p_path + else: + msg = channel_1+" "+PST.p_path + + Pub.send_message(msg) + except IOError: + print "CRC Checksum Error on : ", PST.p_path + pass + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_PubSub_Lines_Q.py b/bin/ZMQ_PubSub_Lines_Q.py new file mode 100755 index 00000000..722fdcf5 --- /dev/null +++ b/bin/ZMQ_PubSub_Lines_Q.py @@ -0,0 +1,62 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_PubSub_Line_Q Module +============================ + +This module subscribe to a Publisher stream and put the received messages +into a Redis-list waiting to be popped later by others scripts. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Running Redis instances. +*Should register to the Publisher "ZMQ_Feed" + +""" + +import redis, zmq, ConfigParser +from pubsublogger import publisher +from packages import ZMQ_PubSub + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + channel = cfg.get("PubSub_Global", "channel") + subscriber_name = "line" + + Sub = ZMQ_PubSub.ZMQSub(configfile,"PubSub_Global", channel, subscriber_name) + + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format(channel)) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Lines_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Lines_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_PubSub_Tokenize.py b/bin/ZMQ_PubSub_Tokenize.py new file mode 100755 index 00000000..88f01e01 --- /dev/null +++ b/bin/ZMQ_PubSub_Tokenize.py @@ -0,0 +1,89 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_PubSub_Lines Module +============================ + +This module is consuming the Redis-list created by the ZMQ_PubSub_Tokenize_Q Module. + +It tokenize the content of the paste and publish the result in the following format: + channel_name+' '+/path/of/the/paste.gz+' '+tokenized_word+' '+scoring + + ..seealso:: Paste method (_get_top_words) + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Need running Redis instances. (Redis) +*Need the ZMQ_PubSub_Tokenize_Q Module running to be able to work properly. + +""" +import redis, zmq, ConfigParser, time +from packages import Paste as P +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + channel = cfg.get("PubSub_Longlines", "channel_1") + subscriber_name = "tokenize" + subscriber_config_section = "PubSub_Longlines" + + #Publisher + publisher_config_section = "PubSub_Words" + publisher_name = "pubtokenize" + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, channel, subscriber_name) + Pub = ZMQ_PubSub.ZMQPub(configfile, publisher_config_section, publisher_name) + + channel_0 = cfg.get("PubSub_Words", "channel_0") + + # FUNCTIONS # + publisher.info("Tokeniser subscribed to channel {0}".format(cfg.get("PubSub_Longlines", "channel_1"))) + + while True: + message = Sub.get_msg_from_queue(r_serv) + print message + if message != None: + PST = P.Paste(message.split(" ",-1)[-1]) + else: + if r_serv.sismember("SHUTDOWN_FLAGS", "Tokenize"): + r_serv.srem("SHUTDOWN_FLAGS", "Tokenize") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + publisher.debug("Tokeniser is idling 10s") + time.sleep(10) + print "sleepin" + continue + + for word, score in PST._get_top_words().items(): + if len(word) >= 4: + msg = channel_0+' '+PST.p_path+' '+str(word)+' '+str(score) + Pub.send_message(msg) + print msg + else: + pass + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_PubSub_Tokenize_Q.py b/bin/ZMQ_PubSub_Tokenize_Q.py new file mode 100755 index 00000000..60204daa --- /dev/null +++ b/bin/ZMQ_PubSub_Tokenize_Q.py @@ -0,0 +1,62 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_PubSub_Tokenize_Q Module +============================ + +This module subscribe to a Publisher stream and put the received messages +into a Redis-list waiting to be popped later by others scripts. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Running Redis instances. +*Should register to the Publisher "ZMQ_PubSub_Line" channel 1 + +""" +import redis, zmq, ConfigParser +from pubsublogger import publisher +from packages import ZMQ_PubSub + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + channel = cfg.get("PubSub_Longlines", "channel_1") + subscriber_name = "tokenize" + subscriber_config_section = "PubSub_Longlines" + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, channel, subscriber_name) + + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format(channel)) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Tokenize_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Tokenize_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Pub_Global.py b/bin/ZMQ_Pub_Global.py new file mode 100755 index 00000000..7b52e01d --- /dev/null +++ b/bin/ZMQ_Pub_Global.py @@ -0,0 +1,66 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_Pub_Global Module +========================= + +This module is consuming the Redis-list created by the script ./Dir.py. +This module is as the same level of the ZMQ tree than the Module ZMQ_Feed + +Whereas the ZMQ_Feed is poping the list created in redis by ZMQ_Feed_Q which is +listening a stream, ZMQ_Pub_Global is poping the list created in redis by ./Dir.py. + +Thanks to this Module there is now two way to Feed the ZMQ tree: +*By a continuous stream ..seealso:: ZMQ_Feed Module +*Manually with this module and ./Dir.py script. + +Requirements +------------ + +*Need running Redis instances. (Redis) + +""" +import redis, zmq, ConfigParser, time +from packages import Paste as P +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read('./packages/config.cfg') + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Global" + + # ZMQ # + PubGlob = ZMQ_PubSub.ZMQPub(configfile, "PubSub_Global", "global") + + # FONCTIONS # + publisher.info("Starting to publish.") + + while True: + filename = r_serv.lpop("filelist") + + if filename != None: + + msg = cfg.get("PubSub_Global", "channel")+" "+filename + PubGlob.send_message(msg) + publisher.debug("{0} Published".format(msg)) + else: + time.sleep(10) + publisher.debug("Nothing to publish") + + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Attributes.py b/bin/ZMQ_Sub_Attributes.py new file mode 100755 index 00000000..081e26ff --- /dev/null +++ b/bin/ZMQ_Sub_Attributes.py @@ -0,0 +1,102 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +""" +The ZMQ_Sub_Attribute Module +============================ + +This module is consuming the Redis-list created by the ZMQ_PubSub_Line_Q Module. + +It perform a sorting on the line's length and publish/forward them to differents +channels: + +*Channel 1 if max length(line) < max +*Channel 2 if max length(line) > max + +The collected informations about the processed pastes +(number of lines and maximum length line) are stored in Redis. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Need running Redis instances. (LevelDB & Redis) +*Need the ZMQ_PubSub_Line_Q Module running to be able to work properly. + +""" +import redis, zmq, ConfigParser, time +from packages import Paste as P +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Data_Merging", "host"), + port = cfg.getint("Redis_Data_Merging", "port"), + db = cfg.getint("Redis_Data_Merging", "db")) + + r_serv1 = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + p_serv = r_serv.pipeline(False) + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + #Subscriber + channel = cfg.get("PubSub_Global", "channel") + subscriber_name = "attributes" + subscriber_config_section = "PubSub_Global" + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, channel, subscriber_name) + + # FUNCTIONS # + publisher.info("""ZMQ Attribute is Running""") + + while True: + try: + message = Sub.get_msg_from_queue(r_serv1) + + if message != None: + PST = P.Paste(message.split(" ",-1)[-1]) + else: + if r_serv1.sismember("SHUTDOWN_FLAGS", "Attributes"): + r_serv1.srem("SHUTDOWN_FLAGS", "Attributes") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + publisher.debug("Script Attribute is idling 10s") + time.sleep(10) + continue + + encoding = PST._get_p_encoding() + language = PST._get_p_language() + + PST.save_attribute_redis(r_serv, "p_encoding", encoding) + PST.save_attribute_redis(r_serv, "p_language", language) + + r_serv.sadd("Pastes_Objects",PST.p_path) + + PST.save_all_attributes_redis(r_serv) + except IOError: + print "CRC Checksum Failed on :", PST.p_path + publisher.error('{0};{1};{2};{3};{4}'.format("Duplicate", PST.p_source, PST.p_date, PST.p_name, "CRC Checksum Failed" )) + pass + + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Attributes_Q.py b/bin/ZMQ_Sub_Attributes_Q.py new file mode 100755 index 00000000..07b494ee --- /dev/null +++ b/bin/ZMQ_Sub_Attributes_Q.py @@ -0,0 +1,62 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_Sub_Attributes_Q Module +============================ + +This module subscribe to a Publisher stream and put the received messages +into a Redis-list waiting to be popped later by others scripts. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Running Redis instances. +*Should register to the Publisher "ZMQ_Feed" + +""" + +import redis, zmq, ConfigParser +from pubsublogger import publisher +from packages import ZMQ_PubSub + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + channel = cfg.get("PubSub_Global", "channel") + subscriber_name = "attributes" + + Sub = ZMQ_PubSub.ZMQSub(configfile, "PubSub_Global", channel, subscriber_name) + + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format(channel)) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Attributes_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Attributes_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_CreditCards.py b/bin/ZMQ_Sub_CreditCards.py new file mode 100755 index 00000000..3fc57926 --- /dev/null +++ b/bin/ZMQ_Sub_CreditCards.py @@ -0,0 +1,91 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +import redis, zmq, ConfigParser, json, pprint, time +from packages import Paste as P +from packages import lib_refine +from packages import ZMQ_PubSub +from pubsublogger import publisher + + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + r_serv1 = redis.StrictRedis( + host = cfg.get("Redis_Data_Merging", "host"), + port = cfg.getint("Redis_Data_Merging", "port"), + db = cfg.getint("Redis_Data_Merging", "db")) + + p_serv = r_serv.pipeline(False) + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + Sub = ZMQ_PubSub.ZMQSub(configfile, "PubSub_Categ", "creditcard_categ", "cards") + + # FUNCTIONS # + publisher.info("Creditcard script subscribed to channel creditcard_categ") + + message = Sub.get_msg_from_queue(r_serv) + prec_filename = None + + creditcard_regex = "4[0-9]{12}(?:[0-9]{3})?" + + mastercard_regex = "5[1-5]\d{2}([\ \-]?)\d{4}\1\d{4}\1\d{4}" + visa_regex = "4\d{3}([\ \-]?)\d{4}\1\d{4}\1\d{4}" + discover_regex = "6(?:011\d\d|5\d{4}|4[4-9]\d{3}|22(?:1(?:2[6-9]|[3-9]\d)|[2-8]\d\d|9(?:[01]\d|2[0-5])))\d{10}" + jcb_regex = "35(?:2[89]|[3-8]\d)([\ \-]?)\d{4}\1\d{4}\1\d{4}" + amex_regex = "3[47]\d\d([\ \-]?)\d{6}\1\d{5}" + chinaUP_regex = "62[0-5]\d{13,16}" + maestro_regex = "(?:5[0678]\d\d|6304|6390|67\d\d)\d{8,15}" + + while True: + if message != None: + channel, filename, word, score = message.split() + + if prec_filename == None or filename != prec_filename: + Creditcard_set = set([]) + PST = P.Paste(filename) + + for x in PST.get_regex(creditcard_regex): + if lib_refine.is_luhn_valid(x): + Creditcard_set.add(x) + + + PST.__setattr__(channel, Creditcard_set) + PST.save_attribute_redis(r_serv1, channel, Creditcard_set) + + pprint.pprint(Creditcard_set) + if (len(Creditcard_set) > 0): + publisher.warning('{0};{1};{2};{3};{4}'.format("CreditCard", PST.p_source, PST.p_date, PST.p_name, str(len(Creditcard_set))+" Valid number(s)" )) + else: + publisher.info('{0};{1};{2};{3};{4}'.format("CreditCard", PST.p_source, PST.p_date, PST.p_name, "CreditCard Related" )) + + prec_filename = filename + + else: + if r_serv.sismember("SHUTDOWN_FLAGS", "Creditcards"): + r_serv.srem("SHUTDOWN_FLAGS", "Creditcards") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + publisher.debug("Script creditcard is idling 1m") + time.sleep(60) + + message = Sub.get_msg_from_queue(r_serv) + + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_CreditCards_Q.py b/bin/ZMQ_Sub_CreditCards_Q.py new file mode 100755 index 00000000..392ee22c --- /dev/null +++ b/bin/ZMQ_Sub_CreditCards_Q.py @@ -0,0 +1,42 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +import redis, zmq, ConfigParser +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + Sub = ZMQ_PubSub.ZMQSub(configfile, "PubSub_Categ", "creditcard_categ", "cards") + + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format("creditcard_categ")) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Creditcards_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Creditcards_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Curve.py b/bin/ZMQ_Sub_Curve.py new file mode 100755 index 00000000..4eed4171 --- /dev/null +++ b/bin/ZMQ_Sub_Curve.py @@ -0,0 +1,123 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_Sub_Curve Module +============================ + +This module is consuming the Redis-list created by the ZMQ_PubSub_Tokenize_Q Module. + +Each words files created under /files/ are representing categories. +This modules take these files and compare them to +the stream of data given by the ZMQ_PubSub_Tokenize_Q Module. + +When a word from a paste match one or more of these words file, the filename of +the paste is published/forwarded to the next modules. + +Each category (each files) are representing a dynamic channel. +This mean that if you create 1000 files under /files/ you'll have 1000 channels +where every time there is a matching word to a category, the paste containing +this word will be pushed to this specific channel. + +..note:: The channel will have the name of the file created. + +Implementing modules can start here, create your own category file, +and then create your own module to treat the specific paste matching this category. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Need running Redis instances. (Redis) +*Categories files of words in /files/ need to be created +*Need the ZMQ_PubSub_Tokenize_Q Module running to be able to work properly. + +""" +import redis, argparse, zmq, ConfigParser, time +from packages import Paste as P +from packages import ZMQ_PubSub +from pubsublogger import publisher +from packages import lib_words + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # SCRIPT PARSER # + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information + Leak framework.''', + epilog = '''''') + + parser.add_argument('-l', + type = str, + default = "../files/list_categ_files", + help = 'Path to the list_categ_files (../files/list_categ_files)', + action = 'store') + + args = parser.parse_args() + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + r_serv1 = redis.StrictRedis( + host = cfg.get("Redis_Level_DB", "host"), + port = cfg.get("Redis_Level_DB", "port"), + db = 0) + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + channel = cfg.get("PubSub_Words", "channel_0") + subscriber_name = "curve" + subscriber_config_section = "PubSub_Words" + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, channel, subscriber_name) + + # FUNCTIONS # + publisher.info("Script Curve subscribed to channel {0}".format(cfg.get("PubSub_Words", "channel_0"))) + + paste_words = [] + message = Sub.get_msg_from_queue(r_serv) + prec_filename = None + while True: + if message != None: + channel, filename, word, score = message.split() + if prec_filename == None or filename != prec_filename: + PST = P.Paste(filename) + lib_words.create_curve_with_word_file(r_serv1, "/home/user/AIL/var/www/static/csv/wordstrendingdata", "/home/user/AIL/files/wordfile", int(PST.p_date.year), int(PST.p_date.month)) + + prec_filename = filename + prev_score = r_serv1.hget(word.lower(), PST.p_date) + print prev_score + if prev_score != None: + r_serv1.hset(word.lower(), PST.p_date, int(prev_score) + int(score)) + else: + r_serv1.hset(word.lower(), PST.p_date, score) + #r_serv.expire(word,86400) #1day + + else: + if r_serv.sismember("SHUTDOWN_FLAGS", "Curve"): + r_serv.srem("SHUTDOWN_FLAGS", "Curve") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + publisher.debug("Script Curve is Idling") + print "sleepin" + time.sleep(1) + + message = Sub.get_msg_from_queue(r_serv) + + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Curve_Q.py b/bin/ZMQ_Sub_Curve_Q.py new file mode 100755 index 00000000..54737e3e --- /dev/null +++ b/bin/ZMQ_Sub_Curve_Q.py @@ -0,0 +1,61 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_Sub_Curve_Q Module +============================ + +This module subscribe to a Publisher stream and put the received messages +into a Redis-list waiting to be popped later by others scripts. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Running Redis instances. +*Should register to the Publisher "ZMQ_PubSub_Tokenize" + +""" +import redis, zmq, ConfigParser +from pubsublogger import publisher +from packages import ZMQ_PubSub + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + channel = cfg.get("PubSub_Words", "channel_0") + subscriber_name = "curve" + subscriber_config_section = "PubSub_Words" + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, channel, subscriber_name) + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format(channel)) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Curve_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Curve_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Duplicate.py b/bin/ZMQ_Sub_Duplicate.py new file mode 100755 index 00000000..e7a7ea5a --- /dev/null +++ b/bin/ZMQ_Sub_Duplicate.py @@ -0,0 +1,196 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +""" +The Duplicate module +==================== + +This huge module is, in short term, checking duplicates. + +Requirements: +------------- + + +""" +import redis, zmq, ConfigParser, time, datetime, pprint, time, os +from packages import Paste as P +from packages import ZMQ_PubSub +from datetime import date +from pubsublogger import publisher +from pybloomfilter import BloomFilter + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + # DB QUEUE ( MEMORY ) + r_Q_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + r_serv_merge = redis.StrictRedis( + host = cfg.get("Redis_Data_Merging", "host"), + port = cfg.getint("Redis_Data_Merging", "port"), + db = cfg.getint("Redis_Data_Merging", "db")) + + + # REDIS # + # DB OBJECT & HASHS ( DISK ) + dico_redis = {} + for year in xrange(2013, 2015): + for month in xrange(0,16): + dico_redis[str(year)+str(month).zfill(2)] = redis.StrictRedis( + host = cfg.get("Redis_Level_DB", "host"), + port = year, + db = month) + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + channel = cfg.get("PubSub_Global", "channel") + subscriber_name = "duplicate" + subscriber_config_section = "PubSub_Global" + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, channel, subscriber_name) + + # FUNCTIONS # + publisher.info("""Script duplicate subscribed to channel {0}""".format(cfg.get("PubSub_Global", "channel"))) + + set_limit = 100 + + while True: + try: + super_dico = {} + hash_dico = {} + dupl = [] + nb_hash_current = 0 + + x = time.time() + + message = Sub.get_msg_from_queue(r_Q_serv) + if message != None: + path = message.split(" ",-1)[-1] + PST = P.Paste(path) + else: + publisher.debug("Script Attribute is idling 10s") + time.sleep(10) + if r_Q_serv.sismember("SHUTDOWN_FLAGS", "Duplicate"): + r_Q_serv.srem("SHUTDOWN_FLAGS", "Duplicate") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + continue + + PST._set_p_hash_kind("md5") + + #Assignate the correct redis connexion + r_serv1 = dico_redis[PST.p_date.year + PST.p_date.month] + + #Creating the bloom filter name: bloomyyyymm + bloomname = 'bloom' + PST.p_date.year + PST.p_date.month + + bloompath = cfg.get("Directories", "bloomfilters") + + filebloompath = bloompath + bloomname + + #datetime.date(int(PST.p_date.year),int(PST.p_date.month),int(PST.p_date.day)).timetuple().tm_yday % 7 + + if os.path.exists(filebloompath): + bloom = BloomFilter.open(filebloompath) + else: + bloom = BloomFilter(100000000, 0.01, filebloompath) + r_Q_serv.sadd("bloomlist", filebloompath) + + # UNIQUE INDEX HASHS TABLE + r_serv0 = dico_redis["201300"] + r_serv0.incr("current_index") + index = r_serv0.get("current_index")+str(PST.p_date) + # HASHTABLES PER MONTH (because of r_serv1 changing db) + r_serv1.set(index, PST.p_path) + r_serv1.sadd("INDEX", index) + + #For each bloom filter + opened_bloom = [] + for bloo in r_Q_serv.smembers("bloomlist"): + #Opening blooms + opened_bloom.append(BloomFilter.open(bloo)) + + # For each hash of the paste + for hash in PST._get_hash_lines(min = 5, start = 1, jump = 0): + nb_hash_current += 1 + + #Adding the hash in Redis & limiting the set + if r_serv1.scard(hash) <= set_limit: + r_serv1.sadd(hash, index) + r_serv1.sadd("HASHS", hash) + #Adding the hash in the bloom of the month + bloom.add(hash) + + #Go throught the Database of the bloom filter (of the month) + for bloo in opened_bloom: + if hash in bloo: + db = bloo.name[-6:] + #Go throught the Database of the bloom filter (of the month) + r_serv_bloom = dico_redis[db] + + #set of index paste: set([1,2,4,65]) + hash_current = r_serv_bloom.smembers(hash) + #removing itself from the list + hash_current = hash_current - set([index]) + + # if the hash is present at least in 1 files (already processed) + if len(hash_current) != 0: + hash_dico[hash] = hash_current + + #if there is data in this dictionnary + if len(hash_dico) != 0: + super_dico[index] = hash_dico + else: + # The hash is not in this bloom + pass + + ########################################################################################### + + #if there is data in this dictionnary + if len(super_dico) != 0: + # current = current paste, phash_dico = {hash: set, ...} + occur_dico = {} + for current, phash_dico in super_dico.items(): + nb_similar_hash = len(phash_dico) + # phash = hash, pset = set([ pastes ...]) + for phash, pset in hash_dico.items(): + + for p_fname in pset: + occur_dico.setdefault(p_fname, 0) + # Count how much hash is similar per file occuring in the dictionnary + if occur_dico[p_fname] >= 0: + occur_dico[p_fname] = occur_dico[p_fname] + 1 + + for paste, count in occur_dico.items(): + percentage = round((count/float(nb_hash_current))*100, 2) + if percentage >= 50: + dupl.append((paste, percentage)) + + # Creating the object attribute and save it. + if dupl != []: + PST.__setattr__("p_duplicate", dupl) + PST.save_attribute_redis(r_serv_merge, "p_duplicate", dupl) + + y = time.time() + + publisher.debug('{0};{1};{2};{3};{4}'.format("Duplicate", PST.p_source, PST.p_date, PST.p_name, "Processed in "+str(y-x)+ " sec" )) + except IOError: + print "CRC Checksum Failed on :", PST.p_path + publisher.error('{0};{1};{2};{3};{4}'.format("Duplicate", PST.p_source, PST.p_date, PST.p_name, "CRC Checksum Failed" )) + pass + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Duplicate_Q.py b/bin/ZMQ_Sub_Duplicate_Q.py new file mode 100755 index 00000000..d3e8d3bf --- /dev/null +++ b/bin/ZMQ_Sub_Duplicate_Q.py @@ -0,0 +1,43 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +import redis, zmq, ConfigParser +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + channel = cfg.get("PubSub_Global", "channel") + Sub = ZMQ_PubSub.ZMQSub(configfile, "PubSub_Global", channel, "duplicate") + + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format(channel)) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Duplicate_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Duplicate_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Longlines.py b/bin/ZMQ_Sub_Longlines.py new file mode 100755 index 00000000..86f7176d --- /dev/null +++ b/bin/ZMQ_Sub_Longlines.py @@ -0,0 +1,43 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +import redis, zmq, ConfigParser +from packages import Paste as P +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_default", "host"), + port = cfg.getint("Redis_default", "port"), + db = args.db) + + p_serv = r_serv.pipeline(False) + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + channel = cfg.get("PubSub_Longlines", "channel_0") + Sub = ZMQ_PubSub.ZMQSub(configfile, "PubSub_Longlines", channel) + + # FUNCTIONS # + publisher.info("Longlines ubscribed to channel {0}".format(cfg.get("PubSub_Longlines", "channel_0"))) + + while True: + PST = P.Paste(Sub.get_message().split(" ", -1)[-1]) + r_serv.sadd("Longlines", PST.p_mime) + PST.save_in_redis(r_serv, PST.p_mime) + + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Mails.py b/bin/ZMQ_Sub_Mails.py new file mode 100755 index 00000000..8cc8108f --- /dev/null +++ b/bin/ZMQ_Sub_Mails.py @@ -0,0 +1,82 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +import redis, zmq, ConfigParser, json, pprint, time +from packages import Paste as P +from packages import lib_refine +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + r_serv1 = redis.StrictRedis( + host = cfg.get("Redis_Data_Merging", "host"), + port = cfg.getint("Redis_Data_Merging", "port"), + db = cfg.getint("Redis_Data_Merging", "db")) + + r_serv2 = redis.StrictRedis( + host = cfg.get("Redis_Cache", "host"), + port = cfg.getint("Redis_Cache", "port"), + db = cfg.getint("Redis_Cache", "db")) + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + Sub = ZMQ_PubSub.ZMQSub(configfile,"PubSub_Categ", "mails_categ", "emails") + + # FUNCTIONS # + publisher.info("Suscribed to channel mails_categ") + + message = Sub.get_msg_from_queue(r_serv) + prec_filename = None + + email_regex = "[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,6}" + + while True: + if message != None: + channel, filename, word, score = message.split() + + if prec_filename == None or filename != prec_filename: + PST = P.Paste(filename) + MX_values = lib_refine.checking_MX_record(r_serv2, PST.get_regex(email_regex)) + + if MX_values[0] >= 1: + + PST.__setattr__(channel, MX_values) + PST.save_attribute_redis(r_serv1, channel, (MX_values[0], list(MX_values[1]))) + + pprint.pprint(MX_values) + if MX_values[0] > 10: + publisher.warning('{0};{1};{2};{3};{4}'.format("Mails", PST.p_source, PST.p_date, PST.p_name, str(MX_values[0])+ " e-mails detected" )) + else: + publisher.info('{0};{1};{2};{3};{4}'.format("Mails", PST.p_source, PST.p_date, PST.p_name, str(MX_values[0])+ " e-mails detected" )) + prec_filename = filename + + else: + if r_serv.sismember("SHUTDOWN_FLAGS", "Mails"): + r_serv.srem("SHUTDOWN_FLAGS", "Mails") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + publisher.debug("Script Mails is Idling 10s") + time.sleep(10) + + message = Sub.get_msg_from_queue(r_serv) + + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Mails_Q.py b/bin/ZMQ_Sub_Mails_Q.py new file mode 100755 index 00000000..5d725672 --- /dev/null +++ b/bin/ZMQ_Sub_Mails_Q.py @@ -0,0 +1,42 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +import redis, zmq, ConfigParser +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + Sub = ZMQ_PubSub.ZMQSub(configfile,"PubSub_Categ", "mails_categ", "emails") + + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format("mails_categ")) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Mails_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Mails_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Onion.py b/bin/ZMQ_Sub_Onion.py new file mode 100755 index 00000000..1e71a9f0 --- /dev/null +++ b/bin/ZMQ_Sub_Onion.py @@ -0,0 +1,114 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_Sub_Onion Module +============================ + +This module is consuming the Redis-list created by the ZMQ_Sub_Onion_Q Module. + +It trying to extract url from paste and returning only ones which are tor related +(.onion) + + ..seealso:: Paste method (get_regex) + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them. + +Requirements +------------ + +*Need running Redis instances. (Redis) +*Need the ZMQ_Sub_Onion_Q Module running to be able to work properly. + +""" +import redis, zmq, ConfigParser, json, pprint, time +from packages import Paste as P +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + r_serv1 = redis.StrictRedis( + host = cfg.get("Redis_Data_Merging", "host"), + port = cfg.getint("Redis_Data_Merging", "port"), + db = cfg.getint("Redis_Data_Merging", "db")) + + r_serv2 = redis.StrictRedis( + host = cfg.get("Redis_Cache", "host"), + port = cfg.getint("Redis_Cache", "port"), + db = cfg.getint("Redis_Cache", "db")) + + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + Sub = ZMQ_PubSub.ZMQSub(configfile, "PubSub_Categ", "onion_categ", "tor") + + # FUNCTIONS # + publisher.info("Script subscribed to channel onion_categ") + + + #Getting the first message from redis. + message = Sub.get_msg_from_queue(r_serv) + prec_filename = None + + #Thanks to Faup project for this regex + # https://github.com/stricaud/faup + url_regex = "([a-zA-Z0-9\.\-]+(\:[a-zA-Z0-9\.&%\$\-]+)*@)*((25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])|localhost|([a-zA-Z0-9\-]+\.)*[a-zA-Z0-9\-]+\.(com|edu|gov|int|mil|net|org|biz|arpa|info|name|pro|aero|coop|museum|onion|[a-zA-Z]{2}))(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&%\$#\=~_\-]+))*" + + while True: + if message != None: + channel, filename, word, score = message.split() + + # "For each new paste" + if prec_filename == None or filename != prec_filename: + domains_list = [] + PST = P.Paste(filename) + + for x in PST.get_regex(url_regex): + #Extracting url with regex + credential, subdomain, domain, host, tld, port, resource_path, query_string, f1, f2, f3, f4 = x + + if f1 == "onion": + domains_list.append(domain) + + #Saving the list of extracted onion domains. + PST.__setattr__(channel, domains_list) + PST.save_attribute_redis(r_serv1, channel, domains_list) + pprint.pprint(domains_list) + print PST.p_path + if len(domains_list) > 0: + publisher.warning('{0};{1};{2};{3};{4}'.format("Onion", PST.p_source, PST.p_date, PST.p_name, str(len(domains_list))+" .onions detected" )) + else: + publisher.info('{0};{1};{2};{3};{4}'.format("Onion", PST.p_source, PST.p_date, PST.p_name, "Onion related" )) + + prec_filename = filename + + else: + if r_serv.sismember("SHUTDOWN_FLAGS", "Onion"): + r_serv.srem("SHUTDOWN_FLAGS", "Onion") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + publisher.debug("Script url is Idling 10s") + time.sleep(10) + + message = Sub.get_msg_from_queue(r_serv) + + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Onion_Q.py b/bin/ZMQ_Sub_Onion_Q.py new file mode 100755 index 00000000..6b822d9f --- /dev/null +++ b/bin/ZMQ_Sub_Onion_Q.py @@ -0,0 +1,58 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +""" +The ZMQ_Sub_Onion_Q Module +============================ + +This module subscribe to a Publisher stream and put the received messages +into a Redis-list waiting to be popped later by ZMQ_Sub_Onion. + +..note:: Module ZMQ_Something_Q and ZMQ_Something are closely bound, always put +the same Subscriber name in both of them (here "tor") + +Requirements +------------ + +*Running Redis instances. +*Should register to the Publisher "ZMQ_PubSub_Categ" + +""" +import redis, zmq, ConfigParser +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + Sub = ZMQ_PubSub.ZMQSub(configfile,"PubSub_Categ", "onion_categ", "tor") + + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format("onion_categ")) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Onion_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Onion_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Urls.py b/bin/ZMQ_Sub_Urls.py new file mode 100755 index 00000000..e64f6d2b --- /dev/null +++ b/bin/ZMQ_Sub_Urls.py @@ -0,0 +1,102 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* +import redis, zmq, ConfigParser, json, pprint, time +from packages import Paste as P +from packages import lib_refine +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + r_serv1 = redis.StrictRedis( + host = cfg.get("Redis_Data_Merging", "host"), + port = cfg.getint("Redis_Data_Merging", "port"), + db = cfg.getint("Redis_Data_Merging", "db")) + + r_serv2 = redis.StrictRedis( + host = cfg.get("Redis_Cache", "host"), + port = cfg.getint("Redis_Cache", "port"), + db = cfg.getint("Redis_Cache", "db")) + + + # LOGGING # + publisher.channel = "Script" + + # ZMQ # + #Subscriber + subscriber_name = "urls" + subscriber_config_section = "PubSub_Categ" + + #Publisher + publisher_config_section = "PubSub_Url" + publisher_name = "adress" + pubchannel = cfg.get("PubSub_Url", "channel") + + Sub = ZMQ_PubSub.ZMQSub(configfile, subscriber_config_section, "web_categ", subscriber_name) + Pub = ZMQ_PubSub.ZMQPub(configfile, publisher_config_section, publisher_name) + + #Sub = ZMQ_PubSub.ZMQSub(configfile, "PubSub_Categ", "web_categ", "urls") + + # FUNCTIONS # + publisher.info("Script URL subscribed to channel web_categ") + + message = Sub.get_msg_from_queue(r_serv) + prec_filename = None + + url_regex = "(http|https|ftp)\://([a-zA-Z0-9\.\-]+(\:[a-zA-Z0-9\.&%\$\-]+)*@)*((25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])|localhost|([a-zA-Z0-9\-]+\.)*[a-zA-Z0-9\-]+\.(com|edu|gov|int|mil|net|org|biz|arpa|info|name|pro|aero|coop|museum|[a-zA-Z]{2}))(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&%\$#\=~_\-]+))*" + + while True: + if message != None: + channel, filename, word, score = message.split() + + if prec_filename == None or filename != prec_filename: + domains_list = [] + PST = P.Paste(filename) + + for x in PST.get_regex(url_regex): + scheme, credential, subdomain, domain, host, tld, port, resource_path, query_string, f1, f2, f3, f4 = x + domains_list.append(domain) + msg = pubchannel + " " + str(x) + Pub.send_message(msg) + publisher.debug('{0} Published'.format(x)) + + if f1 == "onion": + print domain + + A_values = lib_refine.checking_A_record(r_serv2, domains_list) + + if A_values[0] >= 1: + PST.__setattr__(channel, A_values) + PST.save_attribute_redis(r_serv1, channel, (A_values[0],list(A_values[1]))) + + pprint.pprint(A_values) + publisher.info('{0};{1};{2};{3};{4}'.format("Url", PST.p_source, PST.p_date, PST.p_name, str(A_values[0])+" Valid url detected" )) + prec_filename = filename + + else: + if r_serv.sismember("SHUTDOWN_FLAGS", "Urls"): + r_serv.srem("SHUTDOWN_FLAGS", "Urls") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + publisher.debug("Script url is Idling 10s") + time.sleep(10) + + message = Sub.get_msg_from_queue(r_serv) + + +if __name__ == "__main__": + main() diff --git a/bin/ZMQ_Sub_Urls_Q.py b/bin/ZMQ_Sub_Urls_Q.py new file mode 100755 index 00000000..bb6f1ee5 --- /dev/null +++ b/bin/ZMQ_Sub_Urls_Q.py @@ -0,0 +1,42 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +import redis, zmq, ConfigParser +from packages import ZMQ_PubSub +from pubsublogger import publisher + +configfile = './packages/config.cfg' + +def main(): + """Main Function""" + + # CONFIG # + cfg = ConfigParser.ConfigParser() + cfg.read(configfile) + + # REDIS # + r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + + # LOGGING # + publisher.channel = "Queuing" + + # ZMQ # + Sub = ZMQ_PubSub.ZMQSub(configfile, "PubSub_Categ", "web_categ", "urls") + + # FUNCTIONS # + publisher.info("""Suscribed to channel {0}""".format("web_categ")) + + while True: + Sub.get_and_lpush(r_serv) + + if r_serv.sismember("SHUTDOWN_FLAGS", "Urls_Q"): + r_serv.srem("SHUTDOWN_FLAGS", "Urls_Q") + print "Shutdown Flag Up: Terminating" + publisher.warning("Shutdown Flag Up: Terminating.") + break + +if __name__ == "__main__": + main() diff --git a/bin/__init__.py b/bin/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/bin/log_subscriber b/bin/log_subscriber new file mode 100755 index 00000000..1d9c7413 --- /dev/null +++ b/bin/log_subscriber @@ -0,0 +1,45 @@ +#!/usr/bin/env python2 +# -*- coding: utf-8 -*- + +import argparse +import signal +from pubsublogger import subscriber + + +def signal_handler(signal, frame): + if subscriber.pubsub is not None: + subscriber.stop() + print "Subscriber closed." + +signal.signal(signal.SIGINT, signal_handler) + +if __name__ == '__main__': + + parser = argparse.ArgumentParser(description='Configure a logging subscriber.') + + parser.add_argument("-H", "--hostname", default='localhost', + type=str, help='Set the hostname of the server.') + parser.add_argument("-p", "--port", default=6379, + type=int, help='Set the server port.') + parser.add_argument('-s', '--use_unix_socket', action='store_true', + help='Use a unix socket path instead of a tcp socket.') + parser.add_argument("--unix_socket_path", default='/tmp/redis.sock', + type=str, help='Unix socket path.') + parser.add_argument("-c", "--channel", + type=str, required=True, help='Channel to subscribe to.') + parser.add_argument("-l", "--log_path", + required=True, help='Path where the logs will be written') + parser.add_argument("-d", "--debug", action="store_true", + help='Also log debug messages.') + parser.add_argument("-m", "--mail", type=file, default=None, + help='Path to the config file used to send errors by email.') + + args = parser.parse_args() + + if args.use_unix_socket: + subscriber.unix_socket = args.unix_socket_path + else: + subscriber.hostname = args.hostname + subscriber.port = args.port + subscriber.run(args.channel, args.log_path, args.debug, args.mail) + diff --git a/bin/packages/Date.py b/bin/packages/Date.py new file mode 100644 index 00000000..eca18de2 --- /dev/null +++ b/bin/packages/Date.py @@ -0,0 +1,34 @@ +class Date(object): + """docstring for Date""" + def __init__(self, *args): + if len(args) == 3: + self.year = str(args[0]) + self.month = str(args[1]) + self.day = str(args[2]).zfill(2) + if len(args) == 1: + self.year = str(args[0])[:4] + self.month = str(args[0])[4:6] + self.day = str(args[0])[6:] + + def __str__(self): + return "{0}{1}{2}".format(self.year, self.month, self.day) + + def _get_year(self): + return self.year + + def _get_month(self): + return self.month + + def _get_day(self): + return self.day + + def _set_year(self, year): + self.year = year + + def _set_month(self, month): + self.month = month + + def _set_day(self, day): + self.day = day + + diff --git a/bin/packages/Hash.py b/bin/packages/Hash.py new file mode 100644 index 00000000..0640e48c --- /dev/null +++ b/bin/packages/Hash.py @@ -0,0 +1,32 @@ +import hashlib, crcmod, mmh3 + +class Hash(object): + """docstring for Hash""" + def __init__(self, name): + self.name = name + + def __str__(self): + return "{0}".format(self.name) + + def _get_hash_name(self): + return self.name + + def _set_hash_name(self, name): + self.p_hash_name = name + + def Calculate(self, string): + if self.name == "md5": + hash = hashlib.md5(string).hexdigest() + + elif self.name == "sha1": + hash = hashlib.sha1(string).hexdigest() + + elif self.name == "crc": + crc32 = crcmod.Crc(0x104c11db7, initCrc=0, xorOut=0xFFFFFFFF) + crc32.update(string) + hash = crc32.hexdigest() + + elif self.name == "murmur": + hash = mmh3.hash(string) + + return hash \ No newline at end of file diff --git a/bin/packages/Paste.py b/bin/packages/Paste.py new file mode 100755 index 00000000..eb953e78 --- /dev/null +++ b/bin/packages/Paste.py @@ -0,0 +1,366 @@ +#!/usr/bin/python2.7 + +""" +The ``Paste Class`` +=================== + +Use it to create an object from an existing paste or other random file. + +Conditions to fulfill to be able to use this class correctly: +------------------------------------------------------------- + +1/ The paste need to be saved on disk somewhere (have an accessible path) +2/ The paste need to be gziped. +3/ The filepath need to look like something like this: + /directory/source/year/month/day/paste.gz + +""" + +import os, magic, gzip, langid, pprint, redis, operator, string, re, json +from Date import Date +from Hash import Hash + +from langid.langid import LanguageIdentifier, model + +from nltk.tokenize import RegexpTokenizer +from textblob import TextBlob + +from lib_refine import * + +clean = lambda dirty: ''.join(filter(string.printable.__contains__, dirty)) +"""It filters out non-printable characters from the string it receives.""" + +class Paste(object): + """ + This class representing a Paste as an object. + When created, the object will have by default some "main attributes" + such as the size or the date of the paste already calculated, whereas other + attributes are not set and need to be "asked to be calculated" by their methods. + It was design like this because some attributes take time to be calculated + such as the langage or the duplicate... + + :Example: + + PST = Paste("/home/2013/ZEeGaez5.gz") + + """ + + def __init__(self, p_path): + self.p_path = p_path + + self.p_name = self.p_path.split('/')[-1] + + self.p_size = round(os.path.getsize(self.p_path)/1024.0,2) + + self.p_mime = magic.from_buffer(self.get_p_content(), mime = True) + + self.p_encoding = None + + #Assuming that the paste will alway be in a day folder which is itself + # in a month folder which is itself in a year folder. + # /year/month/day/paste.gz + var = self.p_path.split('/') + self.p_date = Date(var[-4], var[-3], var[-2]) + + self.p_hash_kind = None + self.p_hash = None + + self.p_langage = None + + self.p_nb_lines = None + self.p_max_length_line = None + + self.p_source = var[-5] + + + def get_p_content(self): + """ + Returning the content of the Paste + + :Example: + + PST.get_p_content() + + """ + with gzip.open(self.p_path, 'rb') as F: + return F.read() + + def get_lines_info(self): + """ + Returning and setting the number of lines and the maximum lenght of the + lines of the paste. + + :return: tuple (#lines, max_length_line) + + :Example: PST.get_lines_info() + + """ + max_length_line = 0 + with gzip.open(self.p_path, 'rb') as F: + for nb_line in enumerate(F): + if len(nb_line[1]) >= max_length_line: + max_length_line = len(nb_line[1]) + + self.p_nb_lines = nb_line[0] + self.p_max_length_line = max_length_line + return (nb_line[0], max_length_line) + + def _get_p_encoding(self): + """ + Setting the encoding of the paste. + + :Example: PST._set_p_encoding() + + """ + try: + return magic.Magic(mime_encoding = True).from_buffer(self.get_p_content()) + except magic.MagicException: + pass + + + def _set_p_hash_kind(self, hashkind): + """ + Setting the hash (as an object) used for futur operation on it. + + :Example: PST._set_p_hash_kind("md5") + + .. seealso:: Hash.py Object to get the available hashs. + + """ + self.p_hash_kind = Hash(hashkind) + + def _get_p_hash(self): + """ + Setting the hash of the paste as a kind of "uniq" identificator + + :return: hash string (md5, sha1....) + + :Example: PST._get_p_hash() + + .. note:: You need first to "declare which kind of hash you want to use + before using this function + .. seealso:: _set_p_hash_kind("md5") + + """ + self.p_hash = self.p_hash_kind.Calculate(self.get_p_content()) + return self.p_hash + + def _get_p_language(self): + """ + Returning and setting the language of the paste (guessing) + + :Example: PST._get_p_language() + + ..note:: The language returned is purely guessing and may not be accurate + if the paste doesn't contain any human dictionnary words + ..seealso: git@github.com:saffsd/langid.py.git + + """ + + identifier = LanguageIdentifier.from_modelstring(model, norm_probs=True) + + return identifier.classify(self.get_p_content()) + + def _get_p_hash_kind(self): + return self.p_hash_kind + + def _get_p_date(self): + return self.p_date + + def _get_hash_lines(self, min = 1, start = 1, jump = 10): + """ + Returning all the lines of the paste hashed. + + :param min: -- (int) Minimum line length to be hashed. + :param start: -- (int) Number the line where to start. + :param jump: -- (int) Granularity of the hashing 0 or 1 means no jumps + (Maximum Granularity) + + :return: a set([]) of hash. + + .. warning:: Using a set here mean that this function will only return uniq hash. + + If the paste is composed with 1000 time the same line, this function will return + just once the line. + + This choice was made to avoid a certain redundancy and useless hash checking. + + :Example: PST._get_hash_lines(1, 1, 0) + + .. note:: You need first to "declare which kind of hash you want to use + before using this function + .. seealso:: _set_p_hash_kind("md5") + + """ + S = set([]) + with gzip.open(self.p_path, 'rb') as F: + + for num, line in enumerate(F, start): + + if len(line) >= min: + if jump > 1: + if (num % jump) == 1 : + S.add(self.p_hash_kind.Calculate(line)) + else: + S.add(self.p_hash_kind.Calculate(line)) + return S + + + def is_duplicate(self, obj, min = 1, percent = 50, start = 1, jump = 10): + """ + Returning the percent of similarity with another paste. + ( Using the previous hashing method ) + + :param obj: (Paste) The paste to compare with + :param min: -- (int) Minimum line length to be hashed. + :param percent: -- (int) + :param start: -- (int) Number the line where to start. + :param jump: -- (int) Granularity of the hashing 0 or 1 means no jumps + (Maximum Granularity) + + :return: (tuple) (bool, percent) + + :Example: + PST.is_duplicate(PST) + + >>> return (True, 100.0) + + ..seealso: _get_hash_lines() + + """ + + set1 = self._get_hash_lines(min, start, jump) + set2 = obj._get_hash_lines(min, start, jump) + + inter = set.intersection(set1, set2) + + numerator = len(inter) + denominator = float((len(set1) + len(set2)) / 2) + + try: + var = round((numerator / denominator)*100, 2) + except ZeroDivisionError: + var = 0.0 + + if var >= percent: + return True, var + else: + return False, var + + + def save_all_attributes_redis(self, r_serv, key = None): + """ + Saving all the attributes in a "Redis-like" Database (Redis, LevelDB) + + :param r_serv: -- Connexion to the Database. + :param key: -- Key of an additionnal set. + + Example: + import redis + + r_serv = redis.StrictRedis(host = 127.0.0.1, port = 6739, db = 0) + + PST = Paste("/home/Zkopkmlk.gz") + PST.save_all_attributes_redis(r_serv) + + """ + #LevelDB Compatibility + r_serv.hset(self.p_path, "p_name", self.p_name) + r_serv.hset(self.p_path, "p_size", self.p_size) + r_serv.hset(self.p_path, "p_mime", self.p_mime) + #r_serv.hset(self.p_path, "p_encoding", self.p_encoding) + r_serv.hset(self.p_path, "p_date", self._get_p_date()) + r_serv.hset(self.p_path, "p_hash_kind", self._get_p_hash_kind()) + r_serv.hset(self.p_path, "p_hash", self.p_hash) + #r_serv.hset(self.p_path, "p_langage", self.p_langage) + #r_serv.hset(self.p_path, "p_nb_lines", self.p_nb_lines) + #r_serv.hset(self.p_path, "p_max_length_line", self.p_max_length_line) + #r_serv.hset(self.p_path, "p_categories", self.p_categories) + r_serv.hset(self.p_path, "p_source", self.p_source) + if key != None: + r_serv.sadd(key, self.p_path) + else: + pass + + def save_attribute_redis(self, r_serv, attr_name, value): + """ + Save an attribute as a field + """ + if type(value) == set: + r_serv.hset(self.p_path, attr_name, json.dumps(list(value))) + else: + r_serv.hset(self.p_path, attr_name, json.dumps(value)) + + def _get_from_redis(self,r_serv): + return r_serv.hgetall(self.p_hash) + + + def _get_top_words(self, sort = False): + """ + Tokenising method: Returning a sorted list or a set of paste's words + + :param sort: Selecting the output: sorted list or a set. (set by default) + + :return: set or sorted list of tuple [(word, occurency)...] + + :Example: PST._get_top_words(False) + + """ + words = {} + tokenizer = RegexpTokenizer('[\&\~\:\;\,\.\(\)\{\}\|\[\]\\\\/\-/\=\'\"\%\$\?\@\+\#\_\^\<\>\!\*\n\r\t\s]+', + gaps = True, + discard_empty = True) + + blob = TextBlob(clean(self.get_p_content()), + tokenizer = tokenizer) + + for word in blob.tokens: + if word in words.keys(): + num = words[word] + else: + num = 0 + + words[word] = num + 1 + + if sort: + var = sorted(words.iteritems(), key = operator.itemgetter(1), reverse = True) + else: + var = words + + return var + + + def _get_word(self, word): + """ + Returning a specific word and his occurence if present in the paste + + :param word: (str) The word + + :return: (tuple) ("foo", 1337) + + """ + return [item for item in self._get_top_words() if item[0] == word] + + + def get_regex(self, regex): + """ + Returning matches with the regex given as an argument. + + :param regex: -- (str) a regex + + :return: (list) + + :Example: PST.get_regex("4[0-9]{12}(?:[0-9]{3})?") + + + """ + matchs = [] + for match in re.findall(regex, self.get_p_content()): + if match != '' and len(match) < 100: + matchs.append(match) + return matchs + + +if __name__ == "__main__": + pp = pprint.PrettyPrinter(indent=4) + main() diff --git a/bin/packages/ZMQ_PubSub.py b/bin/packages/ZMQ_PubSub.py new file mode 100755 index 00000000..644be4c4 --- /dev/null +++ b/bin/packages/ZMQ_PubSub.py @@ -0,0 +1,159 @@ +#!/usr/bin/python2.7 +""" +The ``ZMQ PubSub`` Modules +========================== + +""" + +import zmq, ConfigParser, redis, pprint, os, sys +#from pubsublogger import publisher + +class PubSub(object): + """ + The PubSub class is a ``Virtual Class`` which regroup the shared attribute + of a Publisher ZeroMQ and a Subcriber ZeroMQ + + :param file_conf: -- (str) The filepath of the configuration file used (.cfg) + :param log_channel: -- (str) The channel used as a log channel + :param ps_name: -- (str) The "ID" of the Publisher/Subcriber + + :return: PubSub Object + + ..note:: The ps_name was implemented to separate subscriber queues in redis + when they are listening on a same "stream" + ..seealso:: Method of the ZMQSub class + + ..todo:: Create Implementing a log channel as an attribute of this virtual class. + + """ + def __init__(self, file_conf, log_channel, ps_name): + self._ps_name = ps_name + self._config_parser = ConfigParser.ConfigParser() + self._config_file = file_conf # "./packages/config.cfg" + + self._config_parser.read(self._config_file) + + self._context_zmq = zmq.Context() + + #self._logging_publisher_channel = log_channel # "Default" + #publisher.channel(self._logging_publisher_channel) + + +class ZMQPub(PubSub): + """ + This class create a ZMQ Publisher which is able to send_message to a choosen socket. + + :param pub_config_section: -- (str) The name of the section in the config file to get the settings + + :return: ZMQPub Object + + :Example: + Extract of the config file: + [PubSub_Categ] + adress = tcp://127.0.0.1:5003 + + Creating the object and sending message: + MyPublisher = ZMQPub('./packages/config.cfg', 'PubSub_Categ', 'pubcateg') + + msg = "categ1"+" "+"Im the data sent on the categ1 channel" + MyPublisher.send_message(msg) + + ..note:: The ps_name attribute for a publisher is "optionnal" but still required to be + instantiated correctly. + + """ + def __init__(self, file_conf, pub_config_section, ps_name): + super(ZMQPub, self).__init__(file_conf, "Default", ps_name) + + self._pub_config_section = pub_config_section + self._pubsocket = self._context_zmq.socket(zmq.PUB) + self._pub_adress = self._config_parser.get(self._pub_config_section, "adress") + + self._pubsocket.bind(self._config_parser.get(self._pub_config_section, "adress")) + + def send_message(self, message): + """Send a message throught the publisher socket""" + self._pubsocket.send(message) + + +class ZMQSub(PubSub): + """ + This class create a ZMQ Subcriber which is able to receive message directly or + throught redis as a buffer. + + The redis buffer is usefull when the subcriber do a time consuming job which is + desynchronising it from the stream of data received. + The redis buffer ensures that no data will be loss waiting to be processed. + + :param sub_config_section: -- (str) The name of the section in the config file to get the settings + :param channel: -- (str) The listening channel of the Subcriber. + + :return: ZMQSub Object + + :Example: + Extract of the config file: + [PubSub_Global] + adress = tcp://127.0.0.1:5000 + channel = filelist + + Creating the object and receiving data + pushing to redis (redis buffering): + + r_serv = redis.StrictRedis( + host = 127.0.0.1, + port = 6387, + db = 0) + + channel = cfg.get("PubSub_Global", "channel") + MySubscriber = ZMQSub('./packages/config.cfg',"PubSub_Global", channel, "duplicate") + + while True: + MySubscriber.get_and_lpush(r_serv) + + + Inside another script use this line to retrive the data from redis. + ... + while True: + MySubscriber.get_msg_from_queue(r_serv) + ... + + ..note:: If you don't want any redis buffering simply use the "get_message" method + + """ + def __init__(self, file_conf, sub_config_section, channel, ps_name): + super(ZMQSub, self).__init__(file_conf, "Default", ps_name) + + self._sub_config_section = sub_config_section + self._subsocket = self._context_zmq.socket(zmq.SUB) + self._sub_adress = self._config_parser.get(self._sub_config_section, "adress") + + self._subsocket.connect(self._config_parser.get(self._sub_config_section, "adress")) + + self._channel = channel + self._subsocket.setsockopt(zmq.SUBSCRIBE, self._channel) + + def get_message(self): + """ + Get the first sent message from a Publisher. + :return: (str) Message from Publisher + + """ + return self._subsocket.recv() + + def get_and_lpush(self, r_serv): + """ + Get the first sent message from a Publisher and storing it in redis + + ..note:: This function also create a set named "queue" for monitoring needs + + """ + r_serv.sadd("queues",self._channel+self._ps_name) + r_serv.lpush(self._channel+self._ps_name, self._subsocket.recv()) + + def get_msg_from_queue(self, r_serv): + """ + Get the first sent message from a Redis List + + :return: (str) Message from Publisher + + """ + return r_serv.rpop(self._channel+self._ps_name) \ No newline at end of file diff --git a/bin/packages/__init__.py b/bin/packages/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/bin/packages/config.cfg b/bin/packages/config.cfg new file mode 100644 index 00000000..fd43b98b --- /dev/null +++ b/bin/packages/config.cfg @@ -0,0 +1,61 @@ +[Directories] +bloomfilters = /home/user/Blooms/ +pastes = /home/user/PASTES/ + +##### Redis ##### +[Redis_Cache] +host = localhost +port = 6379 +db = 0 + +[Redis_Log] +host = localhost +port = 6380 +db = 0 + +[Redis_Queues] +host = localhost +port = 6381 +db = 0 + +[Redis_Data_Merging] +host = localhost +port = 6379 +db = 1 + +##### LevelDB ##### +[Redis_Level_DB] +host = localhost +port = 2013 +db = 0 + +[Redis_Level_DB_Hashs] +host = localhost +port = 2013 +db = 1 + +# PUB / SUB : ZMQ +[Feed] +adress = tcp://crf.circl.lu:5556 +topicfilter = 102 + +[PubSub_Global] +adress = tcp://127.0.0.1:5000 +channel = filelist + +[PubSub_Longlines] +adress = tcp://127.0.0.1:5001 +channel_0 = Longlines +channel_1 = Shortlines + +[PubSub_Words] +adress = tcp://127.0.0.1:5002 +channel_0 = words + +[PubSub_Categ] +adress = tcp://127.0.0.1:5003 +#Channels are dynamic (1 channel per categ) + +[PubSub_Url] +adress = tcp://127.0.0.1:5004 +channel = urls diff --git a/bin/packages/config.cfg.sample b/bin/packages/config.cfg.sample new file mode 100644 index 00000000..fd43b98b --- /dev/null +++ b/bin/packages/config.cfg.sample @@ -0,0 +1,61 @@ +[Directories] +bloomfilters = /home/user/Blooms/ +pastes = /home/user/PASTES/ + +##### Redis ##### +[Redis_Cache] +host = localhost +port = 6379 +db = 0 + +[Redis_Log] +host = localhost +port = 6380 +db = 0 + +[Redis_Queues] +host = localhost +port = 6381 +db = 0 + +[Redis_Data_Merging] +host = localhost +port = 6379 +db = 1 + +##### LevelDB ##### +[Redis_Level_DB] +host = localhost +port = 2013 +db = 0 + +[Redis_Level_DB_Hashs] +host = localhost +port = 2013 +db = 1 + +# PUB / SUB : ZMQ +[Feed] +adress = tcp://crf.circl.lu:5556 +topicfilter = 102 + +[PubSub_Global] +adress = tcp://127.0.0.1:5000 +channel = filelist + +[PubSub_Longlines] +adress = tcp://127.0.0.1:5001 +channel_0 = Longlines +channel_1 = Shortlines + +[PubSub_Words] +adress = tcp://127.0.0.1:5002 +channel_0 = words + +[PubSub_Categ] +adress = tcp://127.0.0.1:5003 +#Channels are dynamic (1 channel per categ) + +[PubSub_Url] +adress = tcp://127.0.0.1:5004 +channel = urls diff --git a/bin/packages/lib_gephi.py b/bin/packages/lib_gephi.py new file mode 100644 index 00000000..6fe35492 --- /dev/null +++ b/bin/packages/lib_gephi.py @@ -0,0 +1,64 @@ +import networkx as nx +import xml.sax.saxutils as xlm +import redis + +def Gephi_Graph(r_serv, graphpath, mincard, maxcard, insert_type): + """Create Gephi Graph by calling a "Sub function": Create_Graph + + :param r_serv: -- connexion to redis database + :param graphpath: -- the absolute path of the .gephi graph created. + :param mincard: -- the minimum links between 2 nodes to be created + :param maxcard: -- the maximum links between 2 nodes to be created + :param insert_type: -- the type of datastructure used to create the graph. + + In fact this function is juste here to be able to choose between two kind of + Redis database structure: One which is a Sorted set and the other a simple + set. + + """ + g = nx.Graph() + + if (insert_type == 0): + + for h in r_serv.smembers("hash"): + Create_Graph(r_serv, g, h, graphpath, mincard, maxcard) + + elif (insert_type == 2): + + for h in r_serv.zrange("hash", 0, -1): + Create_Graph(r_serv, g, h, graphpath, mincard, maxcard) + + nx.write_gexf(g,graphpath) + print nx.info(g) + + + + +def Create_Graph(r_serv, graph, h, graphpath, mincard, maxcard): + """Create Gephi Graph. + + :param r_serv: -- connexion to redis database + :param graph: -- networkx graph object + :param h: -- (str) the hash which will be transform into a node. + :param graphpath: -- the absolute path of the .gephi graph created. + :param mincard: -- the minimum links between 2 nodes to be created + :param maxcard: -- the maximum links between 2 nodes to be created + + This function link all the pastes with theirs own hashed lines. + Of course a paste can have multiple hashed lines and an hashed line can be + contained in multiple paste. + In this case it's a common hash. + + """ + if (r_serv.scard(h) >= mincard) and (r_serv.scard(h) <= maxcard): + + for filename in r_serv.smembers(h): + + for line in r_serv.smembers(filename): + + line = line.decode('UTF-8', errors='ignore') + line = xlm.quoteattr(line, {'"':'"', "'":"'"}) + + graph.add_edge(h, line+" -- "+filename) + +#OK \ No newline at end of file diff --git a/bin/packages/lib_jobs.py b/bin/packages/lib_jobs.py new file mode 100644 index 00000000..67a5ab3e --- /dev/null +++ b/bin/packages/lib_jobs.py @@ -0,0 +1,151 @@ +import redis, time, sys, os, inspect + +from datetime import timedelta, date, datetime + +from pubsublogger import publisher + +def set_listof_pid(r_serv, filename, name): + """Create the pid list and it's pid members + + :param r_serv: -- Connexion to redis. + :param filename: -- the absolute pastes path name. + :param name: -- the traditionnal argv[0] (The name of the launched script) + + This function create a hashes in redis as follows and a set of pid. + + +------------+------------+---------------------+ + | Keys | Fields | Values | + +============+============+=====================+ + | 2045 | startime | 2014-05-09_11:44:17 | + +------------+------------+---------------------+ + | ... | prog | ./programme | + +------------+------------+---------------------+ + | ... | pid | 2045 | + +------------+------------+---------------------+ + | ... | paste | /home/folder/aux.gz | + +------------+------------+---------------------+ + | ... | kb | 54.12 | + +------------+------------+---------------------+ + + +------------+------------+ + | Keys | Members | + +============+============+ + | pid | 2045 | + +------------+------------+ + | ... | 2480 | + +------------+------------+ + + """ + r_serv.sadd("pid", os.getpid()) + r_serv.hmset(os.getpid(), + { + "startime":time.strftime("%Y-%m-%d_%H:%M:%S"), + "prog":name, + "pid":str(os.getpid()), + "paste":filename, + "Kb":round(os.path.getsize(filename)/1024.0,2) + }) + + + + +def update_listof_pid(r_serv): + """Remove pid from the pid list + + :param r_serv: -- Connexion to redis. + + Remove from the list and redis, pid which are terminated. + + """ + r_serv.srem("pid", os.getpid()) + r_serv.delete(os.getpid()) + + + + +def flush_list_of_pid(r_serv): + """Flush the datas in redis + + :param r_serv: -- Connexion to redis. + + Clean the redis database from the previous pid and pidlist inserted + + """ + for x in r_serv.smembers("pid"): + r_serv.delete(x) + + r_serv.delete("pid") + + + + +def format_display_listof_pid(dico, arg): + """Formating data for shell and human + + :param dico: (dict) dictionnary + :param arg: (str) Choosing argument + + :returns: (str) + + This function provide different displaying formats for the dictionnary's data. + + """ + if arg == 'pid': + var = "{0}".format(dico['pid']) + elif arg == 'up': + var = "{0}".format(dico['uptime']) + elif arg == 'kb': + var = "{0}".format(dico['Kb']) + elif arg == 'paste': + var = "{0}".format(dico['paste']) + elif arg == 'startime': + var = "{0}".format(dico['startime']) + elif arg == 'prg': + var = "{0}".format(dico['prog']) + else: + var = "PID:{0},uptime:{1},kb:{2},paste:{3},prog:{4},startime:{5}".format(dico['pid'], + dico['uptime'], + dico['Kb'], + dico['paste'], + dico['prog'], + dico['startime']) + + return var + + + + +def display_listof_pid(r_serv, arg): + """Display the pid list from redis + + This function display infos in the shell about lauched process + + """ + jobs = {} + joblist = [] + try: + for job in r_serv.smembers("pid"): + jobs = r_serv.hgetall(job) + + if jobs != None: + start = datetime.strptime(r_serv.hget(job, "startime"), "%Y-%m-%d_%H:%M:%S") + + end = datetime.strptime(time.strftime("%Y-%m-%d_%H:%M:%S"), "%Y-%m-%d_%H:%M:%S") + jobs['uptime'] = str(abs(start - end)) + joblist.append(jobs) + else: + publisher.debug("display_list_of_pid Aborted due to lack of Information in Redis") + + joblist = sorted(joblist, key=lambda k: k['uptime'], reverse=True) + + for job in joblist: + print format_display_listof_pid(job, arg) + + if arg == "remain": + print "Remaining: {0}".format(r_serv.llen("filelist")) + + if arg == "processed": + print "processed: {0}".format(r_serv.llen("processed")) + + except TypeError: + publisher.error("TypeError for display_listof_pid") diff --git a/bin/packages/lib_redis_insert.py b/bin/packages/lib_redis_insert.py new file mode 100644 index 00000000..3896e28d --- /dev/null +++ b/bin/packages/lib_redis_insert.py @@ -0,0 +1,203 @@ +import sys, hashlib, os, os.path, gzip, string, glob, itertools, copy, shutil +import redis, crcmod, mmh3, time, fileinput +import crcmod, mmh3 + +from operator import itemgetter, attrgetter +from pubsublogger import publisher + + + + +def listdirectory(path): + """Path Traversing Function. + + :param path: -- The absolute pathname to a directory. + + This function is returning all the absolute path of the files contained in + the argument directory. + + """ + fichier=[] + for root, dirs, files in os.walk(path): + + for i in files: + + fichier.append(os.path.join(root, i)) + + return fichier + + + + +clean = lambda dirty: ''.join(filter(string.printable.__contains__, dirty)) +"""It filters out non-printable characters from the string it receives.""" + + + +def select_hash(hashkind, line): + """Select the kind of hashing for the line. + + :param hashkind: -- (str) The name of the hash + :param line: -- (str) The string to hash. + + This function is a kind of hash selector which will use the hash passed + in argument to hash the string also passed in argument. + + """ + if hashkind == "md5": + hashline = hashlib.md5(line).hexdigest() + + elif hashkind == "sha1": + hashline = hashlib.sha1(line).hexdigest() + + elif hashkind == "crc": + crc32 = crcmod.Crc(0x104c11db7, initCrc=0, xorOut=0xFFFFFFFF) + crc32.update(line) + hashline = crc32.hexdigest() + + elif hashkind == "murmur": + hashline = mmh3.hash(line) + + return str(hashline) + + + + +def redis_populate(pipe, folder, minline, hashkind, jmp, insert_type): + """Call another function with different "mode" + + :param pipe: -- Redis pipe + :param folder: -- the absolute path name to the folder where to process + :param minline: -- the minimum lenght of line to hash + :param hashkind: -- the hash to use + :param jmp: -- (bool) trigger the jumping line mode or not + :param insert_type: -- which kind of datastructure to create in redis. + + This Function actually call the function "insert_redis" with differents + method to process it. + In one way, x lines are jumped before the Insertion. + In another, all the line are hashed and inserted in redis. + + """ + for filename in folder: + + with gzip.open(filename, 'rb') as F: + start_line = 1 + + for num, line in enumerate(F, start_line): + + if jmp != 1: + + if (num % jmp) == 1 : + insert_redis(filename, + line, + pipe, + minline, + hashkind, + num, + insert_type) + + else: + insert_redis(filename, + line, + pipe, + minline, + hashkind, + num, + insert_type) + + pipe.execute() + + + + +def insert_redis(filename, line, pipe, minline, hashkind, num, insert_type): + """Insert hashed line in redis. + + :param filename: -- the absolute path name to the folder where to process + :param line: -- the clear line which will be hashed. + :param pipe: -- Redis pipe + :param minline: -- the minimum lenght of line to hash + :param hashkind: -- the hash to use + :param num: -- (int) the first line of the file (better human read) + :param insert_type: -- (int) Choose the datastructure used in redis. + + This function insert hashed lines in the selected redis datastructure + The datastructure is represented as follow: + + case one: ALLIN + "hash"[hashedline][occurence] => to index all different hashs + scoring + "hashedline"[filename.gz] => to associate the file.gz to his hashedline + "L:hashedline"[clearline] => for the correspondance + + case two: SORTED SET (for the ./top.py script) + "hash"[hashedline][occurence] => to index all different hashs + scoring + "hashedline"[filename.gz] => to associate the file.gz to his hashedline + + case tree: BASIC SET (for ./Graph.py) + "hash"[hashedline] to index all different hashs (without scores) + "hashedline"[filename.gz] => to associate the file.gz to his hashedline + "filename.gz"[firstline] => for human reading + + """ + if (insert_type == 2): # ALLIN + if len(line) >= minline: + + pipe.zincrby("hash", select_hash(hashkind, line), 1) + pipe.sadd(select_hash(hashkind,line), filename.split('/',20)[-1]) + pipe.sadd("L:"+select_hash(hashkind, line), clean(line)) + + if (num == 1): + + pipe.sadd(filename.split('/',20)[-1], clean(line[0:80])) + + + elif (insert_type == 1): # SORTED SET FOR TOP100.py + + if len(line) >= minline: + + pipe.zincrby("hash", select_hash(hashkind, line), 1) + pipe.sadd(select_hash(hashkind, line), clean(line)) + + + elif (insert_type == 0): # SET FOR THE GRAPH + + if len(line) >= minline: + + pipe.sadd("hash", select_hash(hashkind, line)) + pipe.sadd(select_hash(hashkind,line), filename.split('/',20)[-1]) + + if (num == 1): + + pipe.sadd(filename.split('/',20)[-1], clean(line[0:80])) + + + + +def remove_pure_doppelganger(r_serv, nb): + """Remove identic paste + + :param r_serv: -- Redis connexion database + :param nb: -- (int) Number of execution wanted + + Add to a temporary list the hash of wholes files and compare the new hash + to the element of this list. If the hash is already inside, the file + is deleted otherwise the hash is added in the list. + + """ + hashlist = [] + for x in xrange(0,nb): + filename = r_serv.lpop("filelist") + + with open(filename, 'rb') as L: + hashline = hashlib.md5(L.read()).hexdigest() + + print len(hashlist) + + if hashline in hashlist: + + os.remove(filename) + publisher.debug("{0} removed".format(filename)) + print "{0} removed".format(filename) + else: + hashlist.append(hashline) diff --git a/bin/packages/lib_refine.py b/bin/packages/lib_refine.py new file mode 100644 index 00000000..3d4d4867 --- /dev/null +++ b/bin/packages/lib_refine.py @@ -0,0 +1,310 @@ +import gzip, string, sys, os, redis, re +import dns.resolver + +from pubsublogger import publisher + +from lib_jobs import * +from operator import itemgetter + +import numpy as np +import matplotlib.pyplot as plt +from pylab import * + +import calendar as cal +from datetime import date, timedelta +from dateutil.rrule import rrule, DAILY + + + +def create_graph_by_day_datastruct(r_serv, r_key, year, month): + """Creating a datastructure in redis. + + :param r_serv: -- Redis connexion database + :param r_key: -- (str) The name of the key read in redis (often the name of + the keywords category list) + :param year: -- (integer) The year to process + :param month: -- (integer) The month to process + + + """ + a = date(year, month, 01) + b = date(year, month, cal.monthrange(year, month)[1]) + + for dt in rrule(DAILY, dtstart = a, until = b): + r_serv.zadd(r_key+'_by_day',0,dt.strftime("%Y%m%d")) + + for Tfilename in r_serv.zrange(r_key+'_occur', 0, -1, withscores = True): + r_serv.zincrby(r_key+'_by_day', + Tfilename[0][-22:-12].replace('/',''), + Tfilename[1]) + + + + +def is_luhn_valid(card_number): + """Apply the Luhn algorithm to validate credit card. + + :param card_number: -- (int) card number + + + """ + r = [int(ch) for ch in str(card_number)][::-1] + return (sum(r[0::2]) + sum(sum(divmod(d*2,10)) for d in r[1::2])) % 10 == 0 + + + + +def checking_MX_record(r_serv, adress_set): + """Check if emails MX domains are responding. + + :param r_serv: -- Redis connexion database + :param adress_set: -- (set) This is a set of emails adress + :return: (int) Number of adress with a responding and valid MX domains + + This function will split the email adress and try to resolve their domains + names: on example@gmail.com it will try to resolve gmail.com + + """ + score = 0 + num = len(adress_set) + WalidMX = set([]) + # Transforming the set into a string + MXdomains = re.findall("@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,20}", str(adress_set).lower()) + + if MXdomains != []: + + for MXdomain in set(MXdomains): + try: + #Already in Redis living. + if r_serv.exists(MXdomain[1:]): + score += 1 + WalidMX.add(MXdomain[1:]) + # Not already in Redis + else: + # If I'm Walid MX domain + if dns.resolver.query(MXdomain[1:], rdtype = dns.rdatatype.MX): + # Gonna be added in redis. + r_serv.setex(MXdomain[1:],timedelta(days=1),1) + score += 1 + WalidMX.add(MXdomain[1:]) + else: + pass + + except dns.resolver.NoNameservers: + publisher.debug('NoNameserver, No non-broken nameservers are available to answer the query.') + + except dns.resolver.NoAnswer: + publisher.debug('NoAnswer, The response did not contain an answer to the question.') + + except dns.name.EmptyLabel: + publisher.debug('SyntaxError: EmptyLabel') + + except dns.resolver.NXDOMAIN: + publisher.debug('The query name does not exist.') + + except dns.name.LabelTooLong: + publisher.debug('The Label is too long') + + finally: + pass + + publisher.debug("emails before: {0} after: {1} (valid)".format(num, score)) + return (num, WalidMX) + + + + +def checking_A_record(r_serv, domains_set): + score = 0 + num = len(domains_set) + WalidA = set([]) + + for Adomain in domains_set: + try: + #Already in Redis living. + if r_serv.exists(Adomain): + score += 1 + WalidA.add(Adomain) + # Not already in Redis + else: + # If I'm Walid domain + if dns.resolver.query(Adomain, rdtype = dns.rdatatype.A): + # Gonna be added in redis. + r_serv.setex(Adomain,timedelta(days=1),1) + score += 1 + WalidA.add(Adomain) + else: + pass + + except dns.resolver.NoNameservers: + publisher.debug('NoNameserver, No non-broken nameservers are available to answer the query.') + + except dns.resolver.NoAnswer: + publisher.debug('NoAnswer, The response did not contain an answer to the question.') + + except dns.name.EmptyLabel: + publisher.debug('SyntaxError: EmptyLabel') + + except dns.resolver.NXDOMAIN: + publisher.debug('The query name does not exist.') + + except dns.name.LabelTooLong: + publisher.debug('The Label is too long') + + finally: + pass + + publisher.debug("URLs before: {0} after: {1} (valid)".format(num, score)) + return (num, WalidA) + + + + +def refining_regex_dataset(r_serv, r_key, regex, min_match, year, month, luhn = True, dnscheck = True): + """Refine the "raw dataset" of paste with regulars expressions + + :param r_serv: -- Redis connexion database + :param r_key: -- (str) The name of the key read in redis (often the name of + the keywords category list) + :param min_match: -- (int) Below this number file are deleted + :param regex: -- Regular expression which will be match. + + This function Refine database created with classify_token_paste function. + It opening again the files which matchs the keywords category list, found + regular expression inside it and count how many time is found. + + If there is not too much match about the regular expression the file is + deleted from the list. + + Than it finally merge the result by day to be able to create a bar graph + which will represent how many occurence by day the regex match. + + """ + for filename in r_serv.zrange(r_key, 0, -1): + + with gzip.open(filename, 'rb') as F: + var = 0 + matchs = set([]) + + for num, kword in enumerate(F): + + match = re.findall(regex, kword) + var += len(match) + + for y in match: + if y != '' and len(y) < 100: + matchs.add(y) + # If there is less match than min_match delete it (False pos) + if len(matchs) <= min_match : + r_serv.zrem(r_key, filename) + publisher.debug("{0} deleted".format(filename)) + else: + # else changing the score. + if r_key == "creditcard_categ" and luhn: + for card_number in matchs: + if is_luhn_valid(card_number): + + r_serv.zincrby(r_key+'_occur', filename, 1) + + publisher.info("{1} is valid in the file {0}".format(filename, card_number)) + else: + publisher.debug("{0} card is invalid".format(card_number)) + + if r_key == "mails_categ" and dnscheck: + r_serv.zadd(r_key+'_occur', checking_MX_record(r_serv, matchs), filename) + + else: + # LUHN NOT TRIGGERED (Other Categs) + r_serv.zadd(r_key+'_occur', + len(matchs), + filename) + + create_graph_by_day_datastruct(r_serv, r_key, year, month) + + + + +def graph_categ_by_day(r_serv, filename, year, month, r_key): + """Create a bargraph representing regex matching by day + + :param r_serv: -- Redis connexion database + :param filename: -- (str) The absolute path where to save the figure.png + :param r_key: -- (str) The name of the key read in redis (often the name of + the keywords category list) + :param year: -- (integer) The year to process + :param month: -- (integer) The month to process + + This function display the amount of the category per day. + + """ + adate = [] + categ_num = [] + rcParams['figure.figsize'] = 15, 10 + + a = date(year, month, 01) + b = date(year, month, cal.monthrange(year, month)[1]) + + for dt in rrule(DAILY, dtstart = a, until = b): + adate.append(dt.strftime("%d")) + categ_num.append(r_serv.zscore(r_key+'_by_day',dt.strftime("%Y%m%d"))) + + n_groups = len(categ_num) + adress_scores = tuple(categ_num) + + index = np.arange(n_groups) + bar_width = 0.5 + opacity = 0.6 + + ladress = plt.bar(index, adress_scores, bar_width, + alpha = opacity, + color = 'b', + label = r_key) + + + plt.plot(tuple(categ_num), 'r--') + #plt.yscale('log') + plt.xlabel('Days') + plt.ylabel('Amount') + plt.title('Occurence of '+r_key+' by day') + plt.xticks(index + bar_width/2 , tuple(adate)) + + plt.legend() + plt.grid() + + plt.tight_layout() + + plt.savefig(filename+".png", dpi=None, facecolor='w', edgecolor='b', + orientation='portrait', papertype=None, format="png", + transparent=False, bbox_inches=None, pad_inches=0.1, + frameon=True) + + publisher.info(filename+".png"+" saved!") + + + + +def create_tld_list(url = "https://mxr.mozilla.org/mozilla-central/source/netwerk/dns/effective_tld_names.dat?raw=1"): + """Recover a tld list from url. + + :param url: -- The url of the tld list. + :return: -- list + + This function recover from mozilla.org the list of the effective tld names, + Save it as a file, and return a list of all the tld. + + + """ + domains = [] + htmlSource = urllib.urlopen(url).read() + with open("ICCANdomain", 'wb') as F: + F.write(htmlSource) + + with open("ICCANdomain", 'rb') as F: + + for num, line in enumerate(F): + if re.match(r"^\/\/|\n", line) == None: + domains.append(re.sub(r'\*', '', line[:-1])) + else: + publisher.info("Comment line ignored.") + + return domains diff --git a/bin/packages/lib_search.py b/bin/packages/lib_search.py new file mode 100644 index 00000000..8ec8973b --- /dev/null +++ b/bin/packages/lib_search.py @@ -0,0 +1,103 @@ +import redis +import string + + +def create_common_hash_file(r_serv, zmin, zmax, filename): + """ Create a "top100".txt file. + + :param r_serv: -- connexion to redis database + :param zmin: -- (int) Offset of the top list + :param zmax: -- (int) Number of element wanted to be in the top list. + :param filename: -- the pathname to the created file. + + This Function create a ranking list between zmin and zman of the most common + hashs. + Line are written as follow in the file: + hash:[md5hash]:[cardinality]:[line] + All hashes represent a full line which mean it can be one char or more... + + """ + with open(filename, 'wb') as F: + + for h, num in r_serv.zrevrangebyscore("hash", "+inf", "-inf", zmin, zmax, True): + + F.write("hash:{0}:{1}:{2}\n".format(h, num, list(r_serv.smembers('L:'+h)))) + + + + +def paste_searching(r_serv, filename, pastename, mincard, maxcard): + """Search similar hashs from a given file. + + :param r_serv: -- connexion to redis database + :param filename: -- the pathname to the created file. + :param pastename: -- the name of the paste used to search in redis database. + :param mincard: -- the minimum occurence needed of an hash to be taken in count. + :param maxcard: -- the maximum occurence needed of an hash to be taken in count. + + This function return a text file which is a kind of synthesis about + where (in the others pastes) the hash of the given pastename have been found. + + """ + P = set([pastename]) + tmp_h = str() + tmp_set = set([]) + + with open(filename, 'wb') as F: + + F.write("Paste: {0}\nOptions used:\nMincard: {1}\nMaxcard: {2}\n\nContaining Following Hash:\n".format(pastename,mincard,maxcard)) + + for h in r_serv.smembers("hash"): + + if (r_serv.smembers(h).intersection(P) and r_serv.scard(h) >= mincard and r_serv.scard(h) <= maxcard): + + F.write(h+'\n') + tmp_set = tmp_set.union(r_serv.smembers(h).union(r_serv.smembers(tmp_h))) + + tmp_h = h + + F.write("\nSimilar Files:\n") + + for n, s in enumerate(tmp_set): + + F.write(str(n) + ': ' + s + '\n') + + + + +def paste_searching2(r_serv, filename, pastename, mincard, maxcard): + """Search similar hashs from a given file. + (On another kind of redis data structure) + + :param r_serv: -- connexion to redis database + :param filename: -- the pathname to the created file. + :param pastename: -- the name of the paste used to search in redis database. + :param mincard: -- the minimum occurence needed of an hash to be taken in count. + :param maxcard: -- the maximum occurence needed of an hash to be taken in count. + + This function return a text file which is a kind of synthesis about + where (in the others pastes) the hash of the given pastename have been found. + + """ + P = set([pastename]) + tmp_h = str() + tmp_set = set([]) + + with open(filename, 'wb') as F: + + F.write("Paste: {0}\nOptions used:\nMincard: {1}\nMaxcard: {2}\n\n###Containing Following Hash:### ###Occur### ###### Corresponding Line ######\n".format(pastename,mincard,maxcard)) + + for h in r_serv.zrange("hash", 0, -1): + + if (r_serv.smembers(h).intersection(P) and r_serv.scard(h) >= mincard and r_serv.scard(h) <= maxcard): + + F.write(h + ' -- ' + str(r_serv.zscore("hash",h)) + ' -- ' + str(list(r_serv.smembers('L:' + h))) + '\n') + tmp_set = tmp_set.union(r_serv.smembers(h).union(r_serv.smembers(tmp_h))) + + tmp_h = h + + F.write("\nSimilar Files:\n") + + for n, s in enumerate(tmp_set): + + F.write(str(n) + ': ' + s + '\n') diff --git a/bin/packages/lib_words.py b/bin/packages/lib_words.py new file mode 100644 index 00000000..7920f74c --- /dev/null +++ b/bin/packages/lib_words.py @@ -0,0 +1,614 @@ +import redis, gzip + +import numpy as np +import matplotlib.pyplot as plt +from pylab import * + +from textblob import TextBlob +from nltk.corpus import stopwords +from nltk.tokenize import RegexpTokenizer + +from lib_redis_insert import clean, listdirectory +from lib_jobs import * + +from pubsublogger import publisher + +import calendar as cal +from datetime import date, timedelta +from dateutil.rrule import rrule, DAILY + +from packages import * + +def redis_words_ranking(pipe, r_serv, nb, minlength, maxlength): + """Looping function + + :param pipe: -- Redis pipe. + :param nb: -- (int) Number of pastes proceeded by function + :param minlength: -- (int) passed to the next function + :param maxlength: -- (int) passed to the next function + + """ + try: + for n in xrange(0,nb): + + path = r_serv.lpop("filelist") + + if path != None: + set_listof_pid(r_serv, path, sys.argv[0]) + + redis_zincr_words(pipe, path, minlength, maxlength) + + update_listof_pid(r_serv) + + r_serv.lpush("processed",path) + + publisher.debug(path) + else: + publisher.debug("Empty list") + break + except (KeyboardInterrupt, SystemExit) as e: + flush_list_of_pid(r_serv) + publisher.debug("Pid list flushed") + + + + + +def redis_zincr_words(pipe, filename, minlength, maxlength): + """Create news sorted set in redis. + + :param minlength: -- (int) Minimum words length inserted + :param maxlength: -- (int) Maximum words length inserted + :param filename: -- The absolute path to the file.gz to process. + + Representation of the set in redis: + + +------------+------------+-----------+ + | Keys | Members | Scores | + +============+============+===========+ + | 20131001 | word1 | 142 | + +------------+------------+-----------+ + | ... | word2 | 120 | + +------------+------------+-----------+ + | 20131002 | ... | ... | + +------------+------------+-----------+ + + This function store all words between minlength and maxlength in redis. + Redis will count as well how much time each word will appear by day: + The cardinality. + + """ + tokenizer = RegexpTokenizer('[\&\~\:\;\,\.\(\)\{\}\|\[\]\\\\/\-/\=\'\"\%\$\?\@\+\#\_\^\<\>\!\*\n\r\t\s]+', gaps = True, discard_empty = True) + + with gzip.open(filename, 'rb') as F: + + blob = TextBlob(clean(F.read()), tokenizer = tokenizer) + + for word in blob.tokens: + + if (len(word) >= minlength) and (len(word) <= maxlength): + pipe.zincrby(filename[-22:-12].replace('/',''), word, 1) + + if (len(word) >= maxlength): + publisher.info("word bigger than {0} detected at {1}".format(maxlength, filename)) + publisher.info(word) + + pipe.execute() + + + + +def classify_token_paste(r_serv, listname, choicedatastruct, nb, r_set): + """Tokenizing on word category + + :param r_serv: -- Redis database connexion + :param listname: -- (str) path to the file containing the list of path of category files + :param choicedatastruct: -- (bool) Changing the index of datastructure + :param nb: -- (int) Number of pastes proceeded by function + + Redis data structures cas be choose as follow: + + +---------------+------------+-----------+ + | Keys | Members | Scores | + +===============+============+===========+ + | mails_categ | filename | 25000 | + +---------------+------------+-----------+ + | ... | filename2 | 2400 | + +---------------+------------+-----------+ + | web_categ | ... | ... | + +---------------+------------+-----------+ + + Or + + +--------------+-------------+-----------+ + | Keys | Members | Scores | + +==============+=============+===========+ + | filename | mails_categ | 100000 | + +--------------+-------------+-----------+ + | ... | web_categ | 24050 | + +--------------+-------------+-----------+ + | filename2 | ... | ... | + +--------------+-------------+-----------+ + + This function tokenise on all special characters like: @^\|[{#~}]!:;$^= + And insert data in redis if the token match the keywords in a list previously + created. + These lists of keywords can be list of everything you want but it's better + to create "category" of keywords. + + """ + + try: + for n in xrange(0,nb): + filename = r_serv.lpop(r_set) + + if filename != None: + + tokenizer = RegexpTokenizer('[\&\~\:\;\,\.\(\)\{\}\|\[\]\\\\/\-/\=\'\"\%\$\?\@\+\#\_\^\<\>\!\*\n\r\t\s]+', gaps = True, discard_empty = True) + set_listof_pid(r_serv, filename, sys.argv[0]) + + with open(listname, 'rb') as L: + # for each "categ" listed in the file + for num, fname in enumerate(L): + # contain keywords by categ + tmp_list = [] + #for each keywords + with open(fname[:-1], 'rb') as LS: + + for num, kword in enumerate(LS): + tmp_list.append(kword[:-1]) + + # for each paste + with gzip.open(filename, 'rb') as F: + + blob = TextBlob(clean(F.read()), + tokenizer = tokenizer) + + # for each paste token + for word in blob.tokens.lower(): + + if word in tmp_list: + # choosing between two data structures. + if choicedatastruct: + r_serv.zincrby(filename, + fname.split('/')[-1][:-1], + 1) + else: + r_serv.zincrby(fname.split('/')[-1][:-1], + filename, + 1) + + update_listof_pid(r_serv) + + else: + publisher.debug("Empty list") + #r_serv.save() + break + + except (KeyboardInterrupt, SystemExit) as e: + flush_list_of_pid(r_serv) + publisher.debug("Pid list flushed") + + + + +def dectect_longlines(r_serv, r_key, store = False, maxlength = 500): + """Store longlines's linenumbers in redis + + :param r_serv: -- The redis connexion database + :param r_key: -- (str) The key name in redis + :param store: -- (bool) Store the line numbers or not. + :param maxlength: -- The limit between "short lines" and "long lines" + + This function connect to a redis list of filename (pastes filename); + Open the paste and check inside if there is some line with their + length >= to maxlength. + If yes, the paste is "tagged" as containing a longlines in another + redis structures, and the linenumber (of the long lines) can be stored + in addition if the argument store is at True. + + """ + try: + while True: + #r_key_list (categ) + filename = r_serv.lpop(r_key) + + if filename != None: + + set_listof_pid(r_serv, filename, sys.argv[0]) + + # for each pastes + with gzip.open(filename, 'rb') as F: + var = True + for num, line in enumerate(F): + + if len(line) >= maxlength: + #publisher.debug("Longline:{0}".format(line)) + if var: + r_serv.rpush("longlines", filename) + var = False + + if store: + r_serv.sadd(filename, num) + else: + publisher.debug("Line numbers of longlines not stored") + + update_listof_pid(r_serv) + else: + publisher.debug("Empty list") + return False + break + + except (KeyboardInterrupt, SystemExit) as e: + flush_list_of_pid(r_serv) + publisher.debug("Pid list flushed") + + + + +# NOT USED RIGHT NOW # +def recovering_longlines(r_serv): + """Get longlines with linenumbers + + """ + try: + for n in xrange(0,nb): + filename = r_serv.lpop("longlines") + + if filename != None: + # For each values in redis (longline's line number) + for numline in r_serv.smembers(filename): + + with gzip.open(filename,'rb') as F: + + for num, line in enumerate(F): + #When corresponding. + if int(num) == int(numline): + pass + # TREATMENT + else: + publisher.debug("Empty list") + r_serv.save() + break + + except (KeyboardInterrupt, SystemExit) as e: + flush_list_of_pid(r_serv) + publisher.debug("Pid list flushed") + + + + +def remove_longline_from_categ(r_serv, r_key, delete, store, maxlength): + """Remove from a set, file with long lines. + + :param r_serv: -- The redis connexion database + :param r_key: -- (str) The key name in redis + :param store: -- (bool) Store the line numbers or not. + :param delete: -- (bool) If true, delete the used key from redis. + :param maxlength: -- The limit between "short lines" and "long lines" + + """ + publisher.info("Number of file before:{0}".format(r_serv.zcard(r_key))) + + #Create a list of file to proceed (1) + for filename in r_serv.zrange(r_key, 0, -1): + r_serv.rpush(r_key+"_list", filename) + + #detecting longlines in pastes + dectect_longlines(r_serv, r_key+"_list", store, maxlength) + + #remove false positive members + while True: + fp_filename = r_serv.lpop("longlines") + + if fp_filename == None: + break + + else: + # if wanted, delete in addition the set with linenumbers (created with store) + if delete: + r_serv.zrem(r_key, fp_filename) + r_serv.delete(fp_filename) + + else: + #remove the file with longline from the r_key zset. + r_serv.zrem(r_key, fp_filename) + + publisher.info("Longline file removed from {0}, {1} Files remaining".format(r_key, r_serv.zcard(r_key))) + + + + +def detect_longline_from_list(r_serv, nb): + try: + for n in xrange(0,nb): + + if not dectect_longlines(r_serv, "filelist", True): + break + + except (KeyboardInterrupt, SystemExit) as e: + flush_list_of_pid(r_serv) + publisher.debug("Pid list flushed") + + + + +def create_dirfile(r_serv, directory, overwrite): + """Create a file of path. + + :param r_serv: -- connexion to redis database + :param directory: -- The folder where to launch the listing of the .gz files + + This function create a list in redis with inside the absolute path + of all the pastes needed to be proceeded by function using parallel + (like redis_words_ranking) + + """ + if overwrite: + r_serv.delete("filelist") + + for x in listdirectory(directory): + r_serv.rpush("filelist",x) + + publisher.info("The list was overwritten") + + else: + if r_serv.llen("filelist") == 0: + + for x in listdirectory(directory): + r_serv.rpush("filelist",x) + + publisher.info("New list created") + else: + + for x in listdirectory(directory): + r_serv.rpush("filelist",x) + + publisher.info("The list was updated with new elements") + + + + +def redis_interbargraph_set(r_serv, year, month, overwrite): + """Create a Redis sorted set. + + :param r_serv: -- connexion to redis database + :param year: -- (integer) The year to process + :param month: -- (integer) The month to process + :param overwrite: -- (bool) trigger the overwrite mode + + This function create inside redis the intersection of all days in + a month two by two. + Example: + For a month of 31days it will create 30 sorted set between day and + day+1 until the last day. + The overwrite mode delete the intersets and re-create them. + + """ + a = date(year, month, 01) + b = date(year, month, cal.monthrange(year, month)[1]) + + if overwrite: + r_serv.delete("InterSet") + + for dt in rrule(DAILY, dtstart = a, until = b - timedelta(1)): + dayafter = dt+timedelta(1) + + r_serv.delete(str(dt.strftime("%Y%m%d"))+str(dayafter.strftime("%Y%m%d"))) + + r_serv.zinterstore( + str(dt.strftime("%Y%m%d"))+str(dayafter.strftime("%Y%m%d")), + {str(dt.strftime("%Y%m%d")):1, + str(dayafter.strftime("%Y%m%d")):-1}) + + r_serv.zadd( + "InterSet", + 1, + str(dt.strftime("%Y%m%d"))+str(dayafter.strftime("%Y%m%d"))) + else: + for dt in rrule(DAILY, dtstart = a, until = b - timedelta(1)): + dayafter = dt+timedelta(1) + + if r_serv.zcard(str(dt.strftime("%Y%m%d"))+str(dayafter.strftime("%Y%m%d"))) == 0: + + r_serv.zinterstore( + str(dt.strftime("%Y%m%d"))+str(dayafter.strftime("%Y%m%d")), + {str(dt.strftime("%Y%m%d")):1, + str(dayafter.strftime("%Y%m%d")):-1}) + + r_serv.zadd( + "InterSet", + 1, + str(dt.strftime("%Y%m%d"))+str(dayafter.strftime("%Y%m%d"))) + + publisher.info(str(dt.strftime("%Y%m%d"))+str(dayafter.strftime("%Y%m%d"))+" Intersection Created") + + else: + publisher.warning("Data already exist, operation aborted.") + + + + + +def word_bar_graph(r_serv, year, month, filename): + """Create an histogram. + + :param r_serv: -- connexion to redis database + :param year: -- (integer) The year to process + :param month: -- (integer) The month to process + :param filename: -- The absolute path where to save the figure.png + + This function use matplotlib to create an histogram. + The redis database need obviously to be populated first + with functions: redis_words_ranking and redis_interbargraph_set. + + """ + lw = [] + adate = [] + inter = [0] + rcParams['figure.figsize'] = 15, 10 + + a = date(year, month, 01) + b = date(year, month, cal.monthrange(year,month)[1]) + + for dt in rrule(DAILY, dtstart = a, until = b): + lw.append(r_serv.zcard(dt.strftime("%Y%m%d"))) + adate.append(dt.strftime("%d")) + + for x in r_serv.zrange("InterSet", 0, 31): + inter.append(r_serv.zcard(x)) + + n_groups = len(lw) + card_words = tuple(lw) + card_interword = tuple(inter) + + index = np.arange(n_groups) + bar_width = 0.5 + opacity = 0.6 + + words = plt.bar(index, card_words, bar_width, + alpha=opacity, + color='g', + label='Words/day') + + lwords = plt.bar(index - 0.5, card_interword, bar_width, + alpha=opacity, + color='r', + label='Intersection') + + + plt.plot(tuple(inter), 'b--') + plt.xlabel(str(year)+'/'+str(month)+' Days') + plt.ylabel('Words') + plt.title('Words Cardinality & Intersection Histogram') + plt.xticks(index + bar_width/2 , tuple(adate)) + + plt.legend() + plt.grid() + + plt.tight_layout() + + plt.savefig(filename+".png", dpi=None, facecolor='w', edgecolor='b', + orientation='portrait', papertype=None, format="png", + transparent=False, bbox_inches=None, pad_inches=0.1, + frameon=True) + + publisher.info(filename+".png"+" saved!") + + + + +def create_data_words_curve(r_serv, r_serv2, year, month, filename): + """Create a Redis hashes. + + :param r_serv: -- connexion to redis database (read) + :param r_serv2: -- connexion to redis database (write) + :param year: -- (integer) The year to process + :param month: -- (integer) The month to process + :param filename: -- the path to the file which contain a list of words. + + + The hashes of redis is created as follow: + + +------------+------------+-----------+ + | Keys | Field | Values | + +============+============+===========+ + | word1 | 20131001 | 150 | + +------------+------------+-----------+ + | ... | 20131002 | 145 | + +------------+------------+-----------+ + | word2 | ... | ... | + +------------+------------+-----------+ + + The filename need to be a list of words separated by a carriage return + with an empty line at the end. + This function create datas which is used by the function + create_curve_with_word_file which create a csv file. + + """ + stop = stopwords.words('english') + a = date(year, month, 01) + b = date(year, month, cal.monthrange(year,month)[1]) + + with open(filename, 'rb') as F: + + for line in F: + + for dt in rrule(DAILY, dtstart = a, until = b): + + if r_serv.zscore(dt.strftime("%Y%m%d"), line[:-1]) is not None: + #tester si ca existe deja "en option" et ajouter un WARNING log + r_serv2.hmset(line[:-1], {str(dt.strftime("%Y%m%d")):r_serv.zscore(dt.strftime("%Y%m%d"), line[:-1])}) + else: + pass + + + + +def create_curve_with_word_file(r_serv, csvfilename, feederfilename, year, month): + """Create a csv file used with dygraph. + + :param r_serv: -- connexion to redis database + :param csvfilename: -- the path to the .csv file created + :param feederfilename: -- the path to the file which contain a list of words. + :param year: -- (integer) The year to process + :param month: -- (integer) The month to process + + This function create a .csv file using datas in redis. + It's checking if the words contained in feederfilename and + their respectives values by days exists. If these values are missing + (Word not present during a day) it's will automatically put a 0 + to keep the timeline of the curve correct. + + """ + a = date(year, month, 01) + b = date(year, month, cal.monthrange(year,month)[1]) + days = {} + words = [] + + with open(feederfilename, 'rb') as F: + for word in F: # words of the files + words.append(word[:-1]) # list of words (sorted as in the file) + + for dt in rrule(DAILY, dtstart = a, until = b): # for each days + + mot = [] + mot1 = [] + mot2 = [] + + days[dt.strftime("%Y%m%d")] = '' + for word in sorted(words): # from the 1srt day to the last of the list + if r_serv.hexists(word, dt.strftime("%Y%m%d")): # if the word have a value for the day + mot1.append(str(word)) + mot2.append(r_serv.hget(word, dt.strftime("%Y%m%d"))) + + mot = zip(mot1, mot2) + + days[dt.strftime("%Y%m%d")] = mot + else: + + mot1.append(str(word)) + mot2.append(0) + + mot = zip(mot1, mot2) + + days[dt.strftime("%Y%m%d")] = mot + + with open(csvfilename+".csv", 'wb') as F: + F.write("Date," + ",".join(sorted(words)) + '\n') + + for x, s in days.items(): + val = [] + for y in s: + val.append(y[1]) + + F.write(x + ',' + str(val) + '\n') + + with open(csvfilename+".csv", 'rb') as F: + h = F.read() + h = h.replace("[","") + h = h.replace("]","") + h = h.replace('\'',"") + + with open(csvfilename+".csv", 'wb') as F: + F.write(h) diff --git a/bin/pubsublogger/__init__.py b/bin/pubsublogger/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/bin/pubsublogger/exceptions.py b/bin/pubsublogger/exceptions.py new file mode 100644 index 00000000..adab92db --- /dev/null +++ b/bin/pubsublogger/exceptions.py @@ -0,0 +1,13 @@ +#!/usr/bin/python +# -*- coding: utf-8 -*- + +"Core exceptions raised by the PubSub module" + +class PubSubError(Exception): + pass + +class InvalidErrorLevel(PubSubError): + pass + +class NoChannelError(PubSubError): + pass diff --git a/bin/pubsublogger/publisher.py b/bin/pubsublogger/publisher.py new file mode 100644 index 00000000..7b30f293 --- /dev/null +++ b/bin/pubsublogger/publisher.py @@ -0,0 +1,99 @@ +#!/usr/bin/python +# -*- coding: utf-8 -*- + +""" +:mod:`publisher` -- Publish logging messages on a redis channel + +To use this module, you have to define at least a channel name. + +.. note:: + The channel name should represent the area of the program you want + to log. It can be whatever you want. + + +""" + +import redis + +from pubsublogger.exceptions import InvalidErrorLevel, NoChannelError + +# use a TCP Socket by default +use_tcp_socket = True + +#default config for a UNIX socket +unix_socket = '/tmp/redis.sock' +# default config for a TCP socket +hostname = 'localhost' +port = 6380 + +channel = None +redis_instance = None + +__error_levels = ('DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL') + + +def __connect(): + """ + Connect to a redis instance. + """ + global redis_instance + if use_tcp_socket: + redis_instance = redis.StrictRedis(host=hostname, port=port) + else: + redis_instance = redis.StrictRedis(unix_socket_path = unix_socket) + + +def log(level, message): + """ + Publish `message` with the `level` the redis `channel`. + + :param level: the level of the message + :param message: the message you want to log + """ + if redis_instance is None: + __connect() + + if level not in __error_levels: + raise InvalidErrorLevel('You have used an invalid error level. \ + Please choose in: ' + ', '.join(__error_levels)) + if channel is None: + raise NoChannelError('Please set a channel.') + c = '{channel}.{level}'.format(channel=channel, level=level) + redis_instance.publish(c, message) + + +def debug(message): + """ + Publush a DEBUG `message` + """ + log('DEBUG', message) + + +def info(message): + """ + Publush an INFO `message` + """ + log('INFO', message) + + +def warning(message): + """ + Publush a WARNING `message` + """ + log('WARNING', message) + + +def error(message): + """ + Publush an ERROR `message` + """ + log('ERROR', message) + + +def critical(message): + """ + Publush a CRITICAL `message` + """ + log('CRITICAL', message) + + diff --git a/bin/pubsublogger/subscriber.py b/bin/pubsublogger/subscriber.py new file mode 100644 index 00000000..8c13cd53 --- /dev/null +++ b/bin/pubsublogger/subscriber.py @@ -0,0 +1,140 @@ +#!/usr/bin/python +# -*- coding: utf-8 -*- + +""" +:mod:`subscriber` -- Subscribe to a redis channel and gather logging messages. + +To use this module, you have to define at least a channel name. +""" + + +import redis +from logbook import Logger +import ConfigParser +from logbook import NestedSetup, NullHandler, FileHandler, MailHandler +import os + +# use a TCP Socket by default +use_tcp_socket = True + +#default config for a UNIX socket +unix_socket = '/tmp/redis.sock' +# default config for a TCP socket +hostname = 'localhost' +port = 6379 + +pubsub = None +channel = None + +# Required only if you want to send emails +dest_mails = [] +smtp_server = None +smtp_port = 0 +src_server = None + +def setup(name, path = 'log', enable_debug = False): + """ + Prepare a NestedSetup. + + :param name: the channel name + :param path: the path where the logs will be written + :param enable_debug: do we want to save the message at the DEBUG level + + :return a nested Setup + """ + path_tmpl = os.path.join(path, '{name}_{level}.log') + info = path_tmpl.format(name = name, level = 'info') + warn = path_tmpl.format(name = name, level = 'warn') + err = path_tmpl.format(name = name, level = 'err') + crit = path_tmpl.format(name = name, level = 'crit') + # a nested handler setup can be used to configure more complex setups + setup = [ + # make sure we never bubble up to the stderr handler + # if we run out of setup handling + NullHandler(), + # then write messages that are at least info to to a logfile + FileHandler(info, level='INFO', encoding='utf-8'), + # then write messages that are at least warnings to to a logfile + FileHandler(warn, level='WARNING', encoding='utf-8'), + # then write messages that are at least errors to to a logfile + FileHandler(err, level='ERROR', encoding='utf-8'), + # then write messages that are at least critical errors to to a logfile + FileHandler(crit, level='CRITICAL', encoding='utf-8'), + ] + if enable_debug: + debug = path_tmpl.format(name = name, level = 'debug') + setup.insert(1, FileHandler(debug, level='DEBUG', encoding='utf-8')) + if src_server is not None and smtp_server is not None \ + and smtp_port != 0 and len(dest_mails) != 0: + mail_tmpl = '{name}_error@{src}' + from_mail = mail_tmpl.format(name = name, src = src_server) + subject = 'Error in {}'.format(name) + # errors should then be delivered by mail and also be kept + # in the application log, so we let them bubble up. + setup.append(MailHandler(from_mail, dest_mails, subject, + level='ERROR', bubble=True, server_addr=(smtp_server, smtp_port))) + + return NestedSetup(setup) + +def mail_setup(path): + """ + Set the variables to be able to send emails. + + :param path: path to the config file + """ + global dest_mails + global smtp_server + global smtp_port + global src_server + config = ConfigParser.RawConfigParser() + config.readfp(path) + dest_mails = config.get('mail', 'dest_mail').split(',') + smtp_server = config.get('mail', 'smtp_server') + smtp_port = config.get('mail', 'smtp_port') + src_server = config.get('mail', 'src_server') + +def run(log_name, path, debug = False, mail = None): + """ + Run a subscriber and pass the messages to the logbook setup. + Stays alive as long as the pubsub instance listen to something. + + :param log_name: the channel to listen to + :param path: the path where the log files will be written + :param debug: True if you want to save the debug messages too + :param mail: Path to the config file for the mails + + """ + global pubsub + global channel + channel = log_name + if use_tcp_socket: + r = redis.StrictRedis(host=hostname, port=port) + else: + r = redis.StrictRedis(unix_socket_path = unix_socket) + pubsub = r.pubsub() + pubsub.psubscribe(channel + '.*') + + logger = Logger(channel) + if mail is not None: + mail_setup(mail) + if os.path.exists(path) and not os.path.isdir(path): + raise Exception("The path you want to use to save the file is invalid (not a directory).") + if not os.path.exists(path): + os.mkdir(path) + with setup(channel, path, debug): + for msg in pubsub.listen(): + if msg['type'] == 'pmessage': + level = msg['channel'].split('.')[1] + message = msg['data'] + try: + message = message.decode('utf-8') + except: + pass + logger.log(level, message) + + +def stop(): + """ + Unsubscribe to the channel, stop the script. + """ + pubsub.punsubscribe(channel + '.*') diff --git a/bin/tests/Bargraph.py b/bin/tests/Bargraph.py new file mode 100755 index 00000000..f0dc4cd1 --- /dev/null +++ b/bin/tests/Bargraph.py @@ -0,0 +1,56 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_words import * +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information Leak + framework. It create an histogram which display the occurency + of the words per day but also the intersection of day and day-1 of these + occurencies''', + epilog = '''The Redis database need to be populated by the script + Wordsranking_Populate.py before using this one.''') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('y', + type = int, + metavar = "year", + help = 'The year processed.', + action = 'store') + + parser.add_argument('m', + type = int, + metavar = "month", + help = 'The month processed.', + action = 'store') + + parser.add_argument('-f', + type = str, + metavar = "filename", + default = "figure", + help = 'The absolute path name of the "figure.png"', + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline(False) + + word_bar_graph(r,args.y,args.m, args.f) + +if __name__ == "__main__": + main() diff --git a/bin/tests/Bargraph_categ_by_day.py b/bin/tests/Bargraph_categ_by_day.py new file mode 100755 index 00000000..72ef2d6c --- /dev/null +++ b/bin/tests/Bargraph_categ_by_day.py @@ -0,0 +1,64 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_refine import * +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information Leak + framework. It create an histogram which display the occurency + of the word category per days.''', + epilog = '''The Redis database need to be populated by the script + Classify_Paste_Token.py before. + It's also usefull to launch Remove_longline_fp.py and Refine_with_regex.py + to create a more accurate histogram. + example: ./Bargraph_categ_by_day.py 2013 12 mails_categ''') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('-f', + type = str, + metavar = "filename", + default = "figure", + help = 'The absolute path name of the "figure.png"', + action = 'store') + + parser.add_argument('y', + type = int, + metavar = "year", + help = 'The year processed', + action = 'store') + + parser.add_argument('m', + type = int, + metavar = "month", + help = 'The month processed', + action = 'store') + + parser.add_argument('key', + type = str, + help ='name of the key to process in redis (the word_categ concerned)', + action = 'store') + + args = parser.parse_args() + + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline(False) + + graph_categ_by_day(r, args.f, args.y, args.m, args.key) + +if __name__ == "__main__": + main() diff --git a/bin/tests/Classify_Paste_Token.py b/bin/tests/Classify_Paste_Token.py new file mode 100755 index 00000000..e744ed35 --- /dev/null +++ b/bin/tests/Classify_Paste_Token.py @@ -0,0 +1,61 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_words import * +from packages.imported import * +from pubsublogger import publisher + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information Leak + framework. It create sets in redis as much as category + defined in the file given by the argument -l ''', + epilog = '''Example : seq 5000 | parallel -n0 -j 10 + ./classify_Paste_Token.py -nbp 200''') + + parser.add_argument('-l', + type = str, + default = "../files/list_categ_files", + help = 'Path to the list_categ_files (../files/list_categ_files)', + action = 'store') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('-s', + help = 'Datastruct type, swapping between keys & members', + action = 'store_true') + + parser.add_argument('-nbp', + type = int, + default = 200, + help = 'Nbpaste', + action = 'store') + + parser.add_argument('-set', + type = str, + default = 'filelist', + help = 'The name of the list in redis which contain the filename to tokenise', + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline(False) + + publisher.channel = "youpi" + + classify_token_paste(r, args.l, args.s, args.nbp, args.set) + +if __name__ == "__main__": + main() diff --git a/bin/tests/Display_pid.py b/bin/tests/Display_pid.py new file mode 100755 index 00000000..a41008fc --- /dev/null +++ b/bin/tests/Display_pid.py @@ -0,0 +1,46 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_words import * +from packages.imported import * +from pubsublogger import publisher + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information Leak + framework. It's here to monitor some script which take time + and lauched in parallel, You can display which process is running on which + paste and how much time it spent processing it''', + epilog = 'example : ./Display_pid -p pid -db 1 -d remain') + + parser.add_argument('-d', + type = str, + default = 'all', + choices=['paste', 'up', 'start', 'kb', 'all', 'pid', 'prg', 'remain', 'processed'], + help = 'Which info to display ?', + action = 'store') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline(False) + + publisher.channel = "youpi" + + display_listof_pid(r, args.d) + +if __name__ == "__main__": + main() diff --git a/bin/tests/Graph.py b/bin/tests/Graph.py new file mode 100755 index 00000000..d5a43181 --- /dev/null +++ b/bin/tests/Graph.py @@ -0,0 +1,65 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_gephi import * +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information + Leak framework. It create a gephi graph to have a global + view of the pastes but also which one are similar.''', + epilog = '''The Redis database need to be populated by the script + Populate.py before using this one.''') + + parser.add_argument('-t', + type = int, + default = 0, + help = 'Type of the Redis population (Same arg than in Populate.py)', + choices=[0, 2], + action = 'store') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('-min', + type = int, + default = 3, + help = 'minimum linked nodes (default 3)', + action = 'store') + + parser.add_argument('-max', + type = int, + default = 50, + help = 'maximum linked nodes created (execute top.py before for more info)', + action = 'store') + + parser.add_argument('-p', + type = str, + default = '../graph/out', + metavar = 'path', + help = "pathname of the graph file created. ex: /home/graph", + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db, + unix_socket_path='/tmp/redis.sock') + + + Gephi_Graph(r, args.p+".gexf", args.min, args.max, args.t) + cprint("GRAPH CREATED AT:{0}.gexf".format(args.p),"green") + +if __name__ == "__main__": + main() + +#OK \ No newline at end of file diff --git a/bin/tests/Interset.py b/bin/tests/Interset.py new file mode 100755 index 00000000..82ea6496 --- /dev/null +++ b/bin/tests/Interset.py @@ -0,0 +1,52 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_words import * +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information + Leak framework. It create in redis the intersection + between all the days two by two of the date given in argument.''', + epilog = '''The Redis database need to be populated by the script + Wordsranking_Populate.py before using this one.''') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('y', + type = int, + metavar = "year", + help = 'The year', + action = 'store') + + parser.add_argument('m', + type = int, + metavar = "month", + help = 'The month', + action = 'store') + + parser.add_argument('-ow', + help = 'trigger the overwritting mode', + action = 'store_true') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline(False) + + redis_interbargraph_set(r, args.y, args.m, args.ow) + +if __name__ == "__main__": + main() diff --git a/bin/tests/Populate.py b/bin/tests/Populate.py new file mode 100755 index 00000000..8de61b74 --- /dev/null +++ b/bin/tests/Populate.py @@ -0,0 +1,75 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_redis_insert import * +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information + Leak framework. Is Populate the Redis database with + the pastes names and theirs hashed line''', + epilog = '''This script need to be run first in order to use the others: + Graph.py, Search.py, Top.py ...''') + + parser.add_argument('input', + type = str, + metavar = 'pathfolder', + help = 'Input folder', + action = 'store') + + parser.add_argument('-t', + type = int, + default = 0, + help = 'type of population wanted 0 = set 1 = zset 2 = mix', + choices=[0, 1, 2], + action = 'store') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('-H', + type = str, + default = 'md5', + metavar='hash', + help = 'The hash method (default md5)', + choices=["md5", "sha1", "crc", "murmur"], + action = 'store') + + parser.add_argument('-jmp', + type = int, + default = 10, + metavar = 'jump', + help = '''Jumping line factor. 1 = All the line are taken. X = jump X line + (default 10)''', + action = 'store') + + parser.add_argument('-ml', + type = int, + default = 1, + metavar = 'minlnline', + help = '''Length line factor. 1 = All the line are taken. + X = each line >= X char (default 1)''', + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline() + + redis_populate(p, listdirectory(args.input), args.ml, args.H, args.jmp, args.t) + +if __name__ == "__main__": + main() + +#OK \ No newline at end of file diff --git a/bin/tests/Refine_with_regex.py b/bin/tests/Refine_with_regex.py new file mode 100755 index 00000000..cd2d7e5a --- /dev/null +++ b/bin/tests/Refine_with_regex.py @@ -0,0 +1,78 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_refine import * +from packages.imported import * +from pubsublogger import publisher + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information + Leak framework. Is refining a redis set by + re analysing set with regex and changing the score by the number of + regex matching''', + epilog = '''example of use: ./Refine_with_regex.py 2013 12 -regex mail + -key mails_categ''') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('-nbm', + type = int, + default = 1, + help = 'Minimum matching regex occurence per file to keep in redis (1)', + action = 'store') + + parser.add_argument('-regex', + type = str, + default = 'mail', + choices=['mail', 'card', 'url', 'bitcoin'], + help = 'Which regex wanted to be use to match', + action = 'store') + + parser.add_argument('-key', + type = str, + default = "mails_categ", + help = 'Name of the key to process in redis (same name than the wordlist concerned)', + action = 'store') + + parser.add_argument('y', + type = int, + metavar = "year", + help = 'The year processed', + action = 'store') + + parser.add_argument('m', + type = int, + metavar = "month", + help = 'The month processed', + action = 'store') + + args = parser.parse_args() + + if args.regex == 'mail': + regex = "[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,6}" + elif args.regex == 'card': + regex = "4[0-9]{12}(?:[0-9]{3})?" + elif args.regex == 'bitcoin': + regex = "[13][1-9A-HJ-NP-Za-km-z]{26,33}" + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline(False) + + publisher.channel = "youpi" + + refining_regex_dataset(r, args.key, regex, args.nbm, args.y, args.m) + +if __name__ == "__main__": + main() diff --git a/bin/tests/Remove_Doppelganger.py b/bin/tests/Remove_Doppelganger.py new file mode 100755 index 00000000..08266af8 --- /dev/null +++ b/bin/tests/Remove_Doppelganger.py @@ -0,0 +1,44 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_redis_insert import * +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information + Leak framework. It Add to a temporary list the hash + of wholes files and compare the new hash to the element of this + list. If the hash is already inside, the file is deleted + otherwise the hash is added in the list.''', + epilog = '''This script need Redis to be populated before by + ./Dir.py''') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('-nbp', + type = int, + default = 200, + help = 'nbpaste', + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline(False) + + remove_pure_doppelganger(r, args.nbp) + +if __name__ == "__main__": + main() \ No newline at end of file diff --git a/bin/tests/Remove_longline_fp.py b/bin/tests/Remove_longline_fp.py new file mode 100755 index 00000000..ec00a711 --- /dev/null +++ b/bin/tests/Remove_longline_fp.py @@ -0,0 +1,57 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_words import * +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information Leak + framework. It removes the line which are in redis under + the "key" name argument''', + epilog = '''This script is usually usefull launched after using + ./Classify_Paste_Token.py example: ./Remove_longline_fp.py mails_categ''') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('key', + type = str, + help = 'Name of the key to process in redis ("")', + action = 'store') + + parser.add_argument('-d', + help = 'Delete the set of longline created?', + action = 'store_true') + + parser.add_argument('-s', + help = 'Store the longline numbers inside a set?', + action = 'store_true') + + parser.add_argument('-max', + type = int, + default = 500, + help = 'The limit between "short lines" and "long lines" (500)', + action = 'store') + + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline(False) + + #remove_longline_from_categ(r, args.key, args.d, args.s, args.max) + detect_longline_from_list(r,args.max) + +if __name__ == "__main__": + main() \ No newline at end of file diff --git a/bin/tests/Search.py b/bin/tests/Search.py new file mode 100755 index 00000000..1ea0f408 --- /dev/null +++ b/bin/tests/Search.py @@ -0,0 +1,72 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_search import * +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = 'Analysis Information Leak framework', + epilog = 'MSc Student Internship') + + parser.add_argument('-db', + default = 0, + type = int, + help = 'The name of the Redis DB', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('name', + type = str, + metavar = 'pastename', + help = 'The name of the paste', + action = 'store') + + parser.add_argument('-min', + type = int, + default = 3, + help = 'minimum linked hashs (default 3)', + action = 'store') + + parser.add_argument('-max', + type = int, + default = 50, + help = 'maximum linked hash (execute top.py to be more aware)', + action = 'store') + + parser.add_argument('-p', + type = str, + default = '../graph/Search_', + metavar = 'path', + help = "pathname of the file created.", + action = 'store') + + parser.add_argument('-t', + type = int, + default = 0, + help = 'Type of the Redis population (Same arg than in Populate.py)', + choices=[0, 2], + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db, + unix_socket_path='/tmp/redis.sock') + + + if args.t == 2: + paste_searching2(r, args.p+args.name+".txt", args.name, args.min, args.max) + cprint("GRAPH CREATED AT:{0}{1}.txt".format(args.p,args.name),"green") + elif args.t == 0: + paste_searching(r, args.p+args.name+".txt", args.name, args.min, args.max) + cprint("GRAPH CREATED AT:{0}{1}.txt".format(args.p,args.name),"green") + pass + + +if __name__ == "__main__": + main() diff --git a/bin/tests/Top.py b/bin/tests/Top.py new file mode 100755 index 00000000..3af48d6f --- /dev/null +++ b/bin/tests/Top.py @@ -0,0 +1,58 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_search import Create_Common_Hash_File +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = '''This script is a part of the Analysis Information Leak + framework. It create a text file with the top common hash + which are in the redis database''', + epilog = '''The Redis database need to be populated by the script + Populate.py before using this one.''') + + parser.add_argument('-db', + default = 0, + type = int, + help = 'The name of the Redis DB', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('-off', + default = 1, + type = int, + metavar = 'offset', + help = 'Starting point of the toplist', + action = 'store') + + parser.add_argument('-top', + default = 100, + type = int, + metavar = '100', + help = 'How many occurence? top 10-50-100 ?', + action = 'store') + + parser.add_argument('-p', + type = str, + default = '../graph/top', + metavar = 'path', + help = "pathname of the file created ex: /home/top", + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + create_common_cash_file(r, args.off, args.top, args.p+str(args.top)+".top") + cprint("LIST CREATED","green") + +if __name__ == "__main__": + main() + +#OK \ No newline at end of file diff --git a/bin/tests/WordsCurve_Populate.py b/bin/tests/WordsCurve_Populate.py new file mode 100755 index 00000000..2ca6b71c --- /dev/null +++ b/bin/tests/WordsCurve_Populate.py @@ -0,0 +1,64 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_words import * +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = 'Analysis Information Leak framework', + epilog = 'Thats drawing') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB To get the info (0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('-db1', + type = int, + default = 1, + help = 'The name of the Redis DB To store (1)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('f', + type = str, + metavar= "file", + help = 'Words filename', + action = 'store') + + parser.add_argument('y', + type = int, + metavar = "year", + help = 'The year', + action = 'store') + + parser.add_argument('m', + type = int, + metavar = "month", + help = 'The month', + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + r2 = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db1) + + + p = r.pipeline(False) + + create_data_words_curve(r, r2, args.y, args.m, args.f) + +if __name__ == "__main__": + main() diff --git a/bin/tests/WordsCurves.py b/bin/tests/WordsCurves.py new file mode 100755 index 00000000..5796f111 --- /dev/null +++ b/bin/tests/WordsCurves.py @@ -0,0 +1,57 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_words import * +from packages.imported import * + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = 'Analysis Information Leak framework', + epilog = 'Thats drawing') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('-cvs', + type = str, + metavar = "filename", + default = "wordstrendingdata", + help = 'The name of the cvs file wanted to be created', + action = 'store') + + parser.add_argument('f', + type = str, + help = 'The file with the list of words', + action = 'store') + + parser.add_argument('y', + type = int, + metavar = "year", + help = 'The year', + action = 'store') + + parser.add_argument('m', + type = int, + metavar = "month", + help = 'The month', + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline(False) + + create_curve_with_word_file(r, args.cvs, args.f, args.y, args.m) + +if __name__ == "__main__": + main() diff --git a/bin/tests/Wordsranking_Populate.py b/bin/tests/Wordsranking_Populate.py new file mode 100755 index 00000000..0b0d0e7b --- /dev/null +++ b/bin/tests/Wordsranking_Populate.py @@ -0,0 +1,54 @@ +#!/usr/bin/python2.7 +# -*-coding:UTF-8 -* + +from packages.lib_words import * +from packages.imported import * +from pubsublogger import publisher + +def main(): + """Main Function""" + + parser = argparse.ArgumentParser( + description = 'Analysis Information Leak framework', + epilog = 'example : seq 2 | parallel ./Wordsranking_Populate.py -nbp 20') + + parser.add_argument('-nbp', + type = int, + default = 200, + help = 'nbpaste', + action = 'store') + + parser.add_argument('-db', + type = int, + default = 0, + help = 'The name of the Redis DB (default 0)', + choices=[0, 1, 2, 3, 4], + action = 'store') + + parser.add_argument('-min', + type = int, + default = 4, + help = 'Minimum length of the inserted words (default 4)', + action = 'store') + + parser.add_argument('-max', + type = int, + default = 200, + help = 'Maximum length of the inserted words (default 200)', + action = 'store') + + args = parser.parse_args() + + r = redis.StrictRedis( + host='localhost', + port=6379, + db=args.db) + + p = r.pipeline(False) + + publisher.channel = "youpi" + + redis_words_ranking(p, r, args.nbp, args.min, args.max) + +if __name__ == "__main__": + main() diff --git a/configs/6379.conf b/configs/6379.conf new file mode 100644 index 00000000..52829bd8 --- /dev/null +++ b/configs/6379.conf @@ -0,0 +1,717 @@ +# Redis configuration file example + +# Note on units: when memory size is needed, it is possible to specify +# it in the usual form of 1k 5GB 4M and so forth: +# +# 1k => 1000 bytes +# 1kb => 1024 bytes +# 1m => 1000000 bytes +# 1mb => 1024*1024 bytes +# 1g => 1000000000 bytes +# 1gb => 1024*1024*1024 bytes +# +# units are case insensitive so 1GB 1Gb 1gB are all the same. + +################################## INCLUDES ################################### + +# Include one or more other config files here. This is useful if you +# have a standard template that goes to all Redis server but also need +# to customize a few per-server settings. Include files can include +# other files, so use this wisely. +# +# Notice option "include" won't be rewritten by command "CONFIG REWRITE" +# from admin or Redis Sentinel. Since Redis always uses the last processed +# line as value of a configuration directive, you'd better put includes +# at the beginning of this file to avoid overwriting config change at runtime. +# +# If instead you are interested in using includes to override configuration +# options, it is better to use include as the last line. +# +# include /path/to/local.conf +# include /path/to/other.conf + +################################ GENERAL ##################################### + +# By default Redis does not run as a daemon. Use 'yes' if you need it. +# Note that Redis will write a pid file in /var/run/redis.pid when daemonized. +daemonize no + +# When running daemonized, Redis writes a pid file in /var/run/redis.pid by +# default. You can specify a custom pid file location here. +pidfile /var/run/redis.pid + +# Accept connections on the specified port, default is 6379. +# If port 0 is specified Redis will not listen on a TCP socket. +port 6379 + +# TCP listen() backlog. +# +# In high requests-per-second environments you need an high backlog in order +# to avoid slow clients connections issues. Note that the Linux kernel +# will silently truncate it to the value of /proc/sys/net/core/somaxconn so +# make sure to raise both the value of somaxconn and tcp_max_syn_backlog +# in order to get the desired effect. +tcp-backlog 511 + +# By default Redis listens for connections from all the network interfaces +# available on the server. It is possible to listen to just one or multiple +# interfaces using the "bind" configuration directive, followed by one or +# more IP addresses. +# +# Examples: +# +# bind 192.168.1.100 10.0.0.1 +# bind 127.0.0.1 + +# Specify the path for the Unix socket that will be used to listen for +# incoming connections. There is no default, so Redis will not listen +# on a unix socket when not specified. +# +unixsocket /tmp/redis.sock +unixsocketperm 755 + +# Close the connection after a client is idle for N seconds (0 to disable) +timeout 0 + +# TCP keepalive. +# +# If non-zero, use SO_KEEPALIVE to send TCP ACKs to clients in absence +# of communication. This is useful for two reasons: +# +# 1) Detect dead peers. +# 2) Take the connection alive from the point of view of network +# equipment in the middle. +# +# On Linux, the specified value (in seconds) is the period used to send ACKs. +# Note that to close the connection the double of the time is needed. +# On other kernels the period depends on the kernel configuration. +# +# A reasonable value for this option is 60 seconds. +tcp-keepalive 0 + +# Specify the server verbosity level. +# This can be one of: +# debug (a lot of information, useful for development/testing) +# verbose (many rarely useful info, but not a mess like the debug level) +# notice (moderately verbose, what you want in production probably) +# warning (only very important / critical messages are logged) +loglevel notice + +# Specify the log file name. Also the empty string can be used to force +# Redis to log on the standard output. Note that if you use standard +# output for logging but daemonize, logs will be sent to /dev/null +logfile "" + +# To enable logging to the system logger, just set 'syslog-enabled' to yes, +# and optionally update the other syslog parameters to suit your needs. +# syslog-enabled no + +# Specify the syslog identity. +# syslog-ident redis + +# Specify the syslog facility. Must be USER or between LOCAL0-LOCAL7. +# syslog-facility local0 + +# Set the number of databases. The default database is DB 0, you can select +# a different one on a per-connection basis using SELECT where +# dbid is a number between 0 and 'databases'-1 +databases 16 + +################################ SNAPSHOTTING ################################ +# +# Save the DB on disk: +# +# save +# +# Will save the DB if both the given number of seconds and the given +# number of write operations against the DB occurred. +# +# In the example below the behaviour will be to save: +# after 900 sec (15 min) if at least 1 key changed +# after 300 sec (5 min) if at least 10 keys changed +# after 60 sec if at least 10000 keys changed +# +# Note: you can disable saving at all commenting all the "save" lines. +# +# It is also possible to remove all the previously configured save +# points by adding a save directive with a single empty string argument +# like in the following example: +# +# save "" + +#save 900 1 +#save 300 10 +#save 60 10000 + +# By default Redis will stop accepting writes if RDB snapshots are enabled +# (at least one save point) and the latest background save failed. +# This will make the user aware (in a hard way) that data is not persisting +# on disk properly, otherwise chances are that no one will notice and some +# disaster will happen. +# +# If the background saving process will start working again Redis will +# automatically allow writes again. +# +# However if you have setup your proper monitoring of the Redis server +# and persistence, you may want to disable this feature so that Redis will +# continue to work as usual even if there are problems with disk, +# permissions, and so forth. +stop-writes-on-bgsave-error yes + +# Compress string objects using LZF when dump .rdb databases? +# For default that's set to 'yes' as it's almost always a win. +# If you want to save some CPU in the saving child set it to 'no' but +# the dataset will likely be bigger if you have compressible values or keys. +rdbcompression yes + +# Since version 5 of RDB a CRC64 checksum is placed at the end of the file. +# This makes the format more resistant to corruption but there is a performance +# hit to pay (around 10%) when saving and loading RDB files, so you can disable it +# for maximum performances. +# +# RDB files created with checksum disabled have a checksum of zero that will +# tell the loading code to skip the check. +rdbchecksum yes + +# The filename where to dump the DB +dbfilename dump.rdb + +# The working directory. +# +# The DB will be written inside this directory, with the filename specified +# above using the 'dbfilename' configuration directive. +# +# The Append Only File will also be created inside this directory. +# +# Note that you must specify a directory here, not a file name. +dir /home/user/dumps/ + +################################# REPLICATION ################################# + +# Master-Slave replication. Use slaveof to make a Redis instance a copy of +# another Redis server. Note that the configuration is local to the slave +# so for example it is possible to configure the slave to save the DB with a +# different interval, or to listen to another port, and so on. +# +# slaveof + +# If the master is password protected (using the "requirepass" configuration +# directive below) it is possible to tell the slave to authenticate before +# starting the replication synchronization process, otherwise the master will +# refuse the slave request. +# +# masterauth + +# When a slave loses its connection with the master, or when the replication +# is still in progress, the slave can act in two different ways: +# +# 1) if slave-serve-stale-data is set to 'yes' (the default) the slave will +# still reply to client requests, possibly with out of date data, or the +# data set may just be empty if this is the first synchronization. +# +# 2) if slave-serve-stale-data is set to 'no' the slave will reply with +# an error "SYNC with master in progress" to all the kind of commands +# but to INFO and SLAVEOF. +# +slave-serve-stale-data yes + +# You can configure a slave instance to accept writes or not. Writing against +# a slave instance may be useful to store some ephemeral data (because data +# written on a slave will be easily deleted after resync with the master) but +# may also cause problems if clients are writing to it because of a +# misconfiguration. +# +# Since Redis 2.6 by default slaves are read-only. +# +# Note: read only slaves are not designed to be exposed to untrusted clients +# on the internet. It's just a protection layer against misuse of the instance. +# Still a read only slave exports by default all the administrative commands +# such as CONFIG, DEBUG, and so forth. To a limited extent you can improve +# security of read only slaves using 'rename-command' to shadow all the +# administrative / dangerous commands. +slave-read-only yes + +# Slaves send PINGs to server in a predefined interval. It's possible to change +# this interval with the repl_ping_slave_period option. The default value is 10 +# seconds. +# +# repl-ping-slave-period 10 + +# The following option sets the replication timeout for: +# +# 1) Bulk transfer I/O during SYNC, from the point of view of slave. +# 2) Master timeout from the point of view of slaves (data, pings). +# 3) Slave timeout from the point of view of masters (REPLCONF ACK pings). +# +# It is important to make sure that this value is greater than the value +# specified for repl-ping-slave-period otherwise a timeout will be detected +# every time there is low traffic between the master and the slave. +# +# repl-timeout 60 + +# Disable TCP_NODELAY on the slave socket after SYNC? +# +# If you select "yes" Redis will use a smaller number of TCP packets and +# less bandwidth to send data to slaves. But this can add a delay for +# the data to appear on the slave side, up to 40 milliseconds with +# Linux kernels using a default configuration. +# +# If you select "no" the delay for data to appear on the slave side will +# be reduced but more bandwidth will be used for replication. +# +# By default we optimize for low latency, but in very high traffic conditions +# or when the master and slaves are many hops away, turning this to "yes" may +# be a good idea. +repl-disable-tcp-nodelay no + +# Set the replication backlog size. The backlog is a buffer that accumulates +# slave data when slaves are disconnected for some time, so that when a slave +# wants to reconnect again, often a full resync is not needed, but a partial +# resync is enough, just passing the portion of data the slave missed while +# disconnected. +# +# The biggest the replication backlog, the longer the time the slave can be +# disconnected and later be able to perform a partial resynchronization. +# +# The backlog is only allocated once there is at least a slave connected. +# +# repl-backlog-size 1mb + +# After a master has no longer connected slaves for some time, the backlog +# will be freed. The following option configures the amount of seconds that +# need to elapse, starting from the time the last slave disconnected, for +# the backlog buffer to be freed. +# +# A value of 0 means to never release the backlog. +# +# repl-backlog-ttl 3600 + +# The slave priority is an integer number published by Redis in the INFO output. +# It is used by Redis Sentinel in order to select a slave to promote into a +# master if the master is no longer working correctly. +# +# A slave with a low priority number is considered better for promotion, so +# for instance if there are three slaves with priority 10, 100, 25 Sentinel will +# pick the one with priority 10, that is the lowest. +# +# However a special priority of 0 marks the slave as not able to perform the +# role of master, so a slave with priority of 0 will never be selected by +# Redis Sentinel for promotion. +# +# By default the priority is 100. +slave-priority 100 + +# It is possible for a master to stop accepting writes if there are less than +# N slaves connected, having a lag less or equal than M seconds. +# +# The N slaves need to be in "online" state. +# +# The lag in seconds, that must be <= the specified value, is calculated from +# the last ping received from the slave, that is usually sent every second. +# +# This option does not GUARANTEES that N replicas will accept the write, but +# will limit the window of exposure for lost writes in case not enough slaves +# are available, to the specified number of seconds. +# +# For example to require at least 3 slaves with a lag <= 10 seconds use: +# +# min-slaves-to-write 3 +# min-slaves-max-lag 10 +# +# Setting one or the other to 0 disables the feature. +# +# By default min-slaves-to-write is set to 0 (feature disabled) and +# min-slaves-max-lag is set to 10. + +################################## SECURITY ################################### + +# Require clients to issue AUTH before processing any other +# commands. This might be useful in environments in which you do not trust +# others with access to the host running redis-server. +# +# This should stay commented out for backward compatibility and because most +# people do not need auth (e.g. they run their own servers). +# +# Warning: since Redis is pretty fast an outside user can try up to +# 150k passwords per second against a good box. This means that you should +# use a very strong password otherwise it will be very easy to break. +# +# requirepass foobared + +# Command renaming. +# +# It is possible to change the name of dangerous commands in a shared +# environment. For instance the CONFIG command may be renamed into something +# hard to guess so that it will still be available for internal-use tools +# but not available for general clients. +# +# Example: +# +# rename-command CONFIG b840fc02d524045429941cc15f59e41cb7be6c52 +# +# It is also possible to completely kill a command by renaming it into +# an empty string: +# +# rename-command CONFIG "" +# +# Please note that changing the name of commands that are logged into the +# AOF file or transmitted to slaves may cause problems. + +################################### LIMITS #################################### + +# Set the max number of connected clients at the same time. By default +# this limit is set to 10000 clients, however if the Redis server is not +# able to configure the process file limit to allow for the specified limit +# the max number of allowed clients is set to the current file limit +# minus 32 (as Redis reserves a few file descriptors for internal uses). +# +# Once the limit is reached Redis will close all the new connections sending +# an error 'max number of clients reached'. +# +# maxclients 10000 + +# Don't use more memory than the specified amount of bytes. +# When the memory limit is reached Redis will try to remove keys +# according to the eviction policy selected (see maxmemory-policy). +# +# If Redis can't remove keys according to the policy, or if the policy is +# set to 'noeviction', Redis will start to reply with errors to commands +# that would use more memory, like SET, LPUSH, and so on, and will continue +# to reply to read-only commands like GET. +# +# This option is usually useful when using Redis as an LRU cache, or to set +# a hard memory limit for an instance (using the 'noeviction' policy). +# +# WARNING: If you have slaves attached to an instance with maxmemory on, +# the size of the output buffers needed to feed the slaves are subtracted +# from the used memory count, so that network problems / resyncs will +# not trigger a loop where keys are evicted, and in turn the output +# buffer of slaves is full with DELs of keys evicted triggering the deletion +# of more keys, and so forth until the database is completely emptied. +# +# In short... if you have slaves attached it is suggested that you set a lower +# limit for maxmemory so that there is some free RAM on the system for slave +# output buffers (but this is not needed if the policy is 'noeviction'). +# +# maxmemory + +# MAXMEMORY POLICY: how Redis will select what to remove when maxmemory +# is reached. You can select among five behaviors: +# +# volatile-lru -> remove the key with an expire set using an LRU algorithm +# allkeys-lru -> remove any key accordingly to the LRU algorithm +# volatile-random -> remove a random key with an expire set +# allkeys-random -> remove a random key, any key +# volatile-ttl -> remove the key with the nearest expire time (minor TTL) +# noeviction -> don't expire at all, just return an error on write operations +# +# Note: with any of the above policies, Redis will return an error on write +# operations, when there are not suitable keys for eviction. +# +# At the date of writing this commands are: set setnx setex append +# incr decr rpush lpush rpushx lpushx linsert lset rpoplpush sadd +# sinter sinterstore sunion sunionstore sdiff sdiffstore zadd zincrby +# zunionstore zinterstore hset hsetnx hmset hincrby incrby decrby +# getset mset msetnx exec sort +# +# The default is: +# +# maxmemory-policy volatile-lru + +# LRU and minimal TTL algorithms are not precise algorithms but approximated +# algorithms (in order to save memory), so you can select as well the sample +# size to check. For instance for default Redis will check three keys and +# pick the one that was used less recently, you can change the sample size +# using the following configuration directive. +# +# maxmemory-samples 3 + +############################## APPEND ONLY MODE ############################### + +# By default Redis asynchronously dumps the dataset on disk. This mode is +# good enough in many applications, but an issue with the Redis process or +# a power outage may result into a few minutes of writes lost (depending on +# the configured save points). +# +# The Append Only File is an alternative persistence mode that provides +# much better durability. For instance using the default data fsync policy +# (see later in the config file) Redis can lose just one second of writes in a +# dramatic event like a server power outage, or a single write if something +# wrong with the Redis process itself happens, but the operating system is +# still running correctly. +# +# AOF and RDB persistence can be enabled at the same time without problems. +# If the AOF is enabled on startup Redis will load the AOF, that is the file +# with the better durability guarantees. +# +# Please check http://redis.io/topics/persistence for more information. + +appendonly no + +# The name of the append only file (default: "appendonly.aof") + +appendfilename "appendonly.aof" + +# The fsync() call tells the Operating System to actually write data on disk +# instead to wait for more data in the output buffer. Some OS will really flush +# data on disk, some other OS will just try to do it ASAP. +# +# Redis supports three different modes: +# +# no: don't fsync, just let the OS flush the data when it wants. Faster. +# always: fsync after every write to the append only log . Slow, Safest. +# everysec: fsync only one time every second. Compromise. +# +# The default is "everysec", as that's usually the right compromise between +# speed and data safety. It's up to you to understand if you can relax this to +# "no" that will let the operating system flush the output buffer when +# it wants, for better performances (but if you can live with the idea of +# some data loss consider the default persistence mode that's snapshotting), +# or on the contrary, use "always" that's very slow but a bit safer than +# everysec. +# +# More details please check the following article: +# http://antirez.com/post/redis-persistence-demystified.html +# +# If unsure, use "everysec". + +# appendfsync always +appendfsync everysec +# appendfsync no + +# When the AOF fsync policy is set to always or everysec, and a background +# saving process (a background save or AOF log background rewriting) is +# performing a lot of I/O against the disk, in some Linux configurations +# Redis may block too long on the fsync() call. Note that there is no fix for +# this currently, as even performing fsync in a different thread will block +# our synchronous write(2) call. +# +# In order to mitigate this problem it's possible to use the following option +# that will prevent fsync() from being called in the main process while a +# BGSAVE or BGREWRITEAOF is in progress. +# +# This means that while another child is saving, the durability of Redis is +# the same as "appendfsync none". In practical terms, this means that it is +# possible to lose up to 30 seconds of log in the worst scenario (with the +# default Linux settings). +# +# If you have latency problems turn this to "yes". Otherwise leave it as +# "no" that is the safest pick from the point of view of durability. + +no-appendfsync-on-rewrite no + +# Automatic rewrite of the append only file. +# Redis is able to automatically rewrite the log file implicitly calling +# BGREWRITEAOF when the AOF log size grows by the specified percentage. +# +# This is how it works: Redis remembers the size of the AOF file after the +# latest rewrite (if no rewrite has happened since the restart, the size of +# the AOF at startup is used). +# +# This base size is compared to the current size. If the current size is +# bigger than the specified percentage, the rewrite is triggered. Also +# you need to specify a minimal size for the AOF file to be rewritten, this +# is useful to avoid rewriting the AOF file even if the percentage increase +# is reached but it is still pretty small. +# +# Specify a percentage of zero in order to disable the automatic AOF +# rewrite feature. + +auto-aof-rewrite-percentage 100 +auto-aof-rewrite-min-size 64mb + +################################ LUA SCRIPTING ############################### + +# Max execution time of a Lua script in milliseconds. +# +# If the maximum execution time is reached Redis will log that a script is +# still in execution after the maximum allowed time and will start to +# reply to queries with an error. +# +# When a long running script exceed the maximum execution time only the +# SCRIPT KILL and SHUTDOWN NOSAVE commands are available. The first can be +# used to stop a script that did not yet called write commands. The second +# is the only way to shut down the server in the case a write commands was +# already issue by the script but the user don't want to wait for the natural +# termination of the script. +# +# Set it to 0 or a negative value for unlimited execution without warnings. +lua-time-limit 5000 + +################################## SLOW LOG ################################### + +# The Redis Slow Log is a system to log queries that exceeded a specified +# execution time. The execution time does not include the I/O operations +# like talking with the client, sending the reply and so forth, +# but just the time needed to actually execute the command (this is the only +# stage of command execution where the thread is blocked and can not serve +# other requests in the meantime). +# +# You can configure the slow log with two parameters: one tells Redis +# what is the execution time, in microseconds, to exceed in order for the +# command to get logged, and the other parameter is the length of the +# slow log. When a new command is logged the oldest one is removed from the +# queue of logged commands. + +# The following time is expressed in microseconds, so 1000000 is equivalent +# to one second. Note that a negative number disables the slow log, while +# a value of zero forces the logging of every command. +slowlog-log-slower-than 10000 + +# There is no limit to this length. Just be aware that it will consume memory. +# You can reclaim memory used by the slow log with SLOWLOG RESET. +slowlog-max-len 128 + +############################# Event notification ############################## + +# Redis can notify Pub/Sub clients about events happening in the key space. +# This feature is documented at http://redis.io/topics/keyspace-events +# +# For instance if keyspace events notification is enabled, and a client +# performs a DEL operation on key "foo" stored in the Database 0, two +# messages will be published via Pub/Sub: +# +# PUBLISH __keyspace@0__:foo del +# PUBLISH __keyevent@0__:del foo +# +# It is possible to select the events that Redis will notify among a set +# of classes. Every class is identified by a single character: +# +# K Keyspace events, published with __keyspace@__ prefix. +# E Keyevent events, published with __keyevent@__ prefix. +# g Generic commands (non-type specific) like DEL, EXPIRE, RENAME, ... +# $ String commands +# l List commands +# s Set commands +# h Hash commands +# z Sorted set commands +# x Expired events (events generated every time a key expires) +# e Evicted events (events generated when a key is evicted for maxmemory) +# A Alias for g$lshzxe, so that the "AKE" string means all the events. +# +# The "notify-keyspace-events" takes as argument a string that is composed +# by zero or multiple characters. The empty string means that notifications +# are disabled at all. +# +# Example: to enable list and generic events, from the point of view of the +# event name, use: +# +# notify-keyspace-events Elg +# +# Example 2: to get the stream of the expired keys subscribing to channel +# name __keyevent@0__:expired use: +# +# notify-keyspace-events Ex +# +# By default all notifications are disabled because most users don't need +# this feature and the feature has some overhead. Note that if you don't +# specify at least one of K or E, no events will be delivered. +notify-keyspace-events "" + +############################### ADVANCED CONFIG ############################### + +# Hashes are encoded using a memory efficient data structure when they have a +# small number of entries, and the biggest entry does not exceed a given +# threshold. These thresholds can be configured using the following directives. +hash-max-ziplist-entries 512 +hash-max-ziplist-value 64 + +# Similarly to hashes, small lists are also encoded in a special way in order +# to save a lot of space. The special representation is only used when +# you are under the following limits: +list-max-ziplist-entries 512 +list-max-ziplist-value 64 + +# Sets have a special encoding in just one case: when a set is composed +# of just strings that happens to be integers in radix 10 in the range +# of 64 bit signed integers. +# The following configuration setting sets the limit in the size of the +# set in order to use this special memory saving encoding. +set-max-intset-entries 512 + +# Similarly to hashes and lists, sorted sets are also specially encoded in +# order to save a lot of space. This encoding is only used when the length and +# elements of a sorted set are below the following limits: +zset-max-ziplist-entries 128 +zset-max-ziplist-value 64 + +# Active rehashing uses 1 millisecond every 100 milliseconds of CPU time in +# order to help rehashing the main Redis hash table (the one mapping top-level +# keys to values). The hash table implementation Redis uses (see dict.c) +# performs a lazy rehashing: the more operation you run into a hash table +# that is rehashing, the more rehashing "steps" are performed, so if the +# server is idle the rehashing is never complete and some more memory is used +# by the hash table. +# +# The default is to use this millisecond 10 times every second in order to +# active rehashing the main dictionaries, freeing memory when possible. +# +# If unsure: +# use "activerehashing no" if you have hard latency requirements and it is +# not a good thing in your environment that Redis can reply form time to time +# to queries with 2 milliseconds delay. +# +# use "activerehashing yes" if you don't have such hard requirements but +# want to free memory asap when possible. +activerehashing yes + +# The client output buffer limits can be used to force disconnection of clients +# that are not reading data from the server fast enough for some reason (a +# common reason is that a Pub/Sub client can't consume messages as fast as the +# publisher can produce them). +# +# The limit can be set differently for the three different classes of clients: +# +# normal -> normal clients +# slave -> slave clients and MONITOR clients +# pubsub -> clients subscribed to at least one pubsub channel or pattern +# +# The syntax of every client-output-buffer-limit directive is the following: +# +# client-output-buffer-limit +# +# A client is immediately disconnected once the hard limit is reached, or if +# the soft limit is reached and remains reached for the specified number of +# seconds (continuously). +# So for instance if the hard limit is 32 megabytes and the soft limit is +# 16 megabytes / 10 seconds, the client will get disconnected immediately +# if the size of the output buffers reach 32 megabytes, but will also get +# disconnected if the client reaches 16 megabytes and continuously overcomes +# the limit for 10 seconds. +# +# By default normal clients are not limited because they don't receive data +# without asking (in a push way), but just after a request, so only +# asynchronous clients may create a scenario where data is requested faster +# than it can read. +# +# Instead there is a default limit for pubsub and slave clients, since +# subscribers and slaves receive data in a push fashion. +# +# Both the hard or the soft limit can be disabled by setting them to zero. +client-output-buffer-limit normal 0 0 0 +client-output-buffer-limit slave 256mb 64mb 60 +client-output-buffer-limit pubsub 32mb 8mb 60 + +# Redis calls an internal function to perform many background tasks, like +# closing connections of clients in timeout, purging expired keys that are +# never requested, and so forth. +# +# Not all tasks are performed with the same frequency, but Redis checks for +# tasks to perform accordingly to the specified "hz" value. +# +# By default "hz" is set to 10. Raising the value will use more CPU when +# Redis is idle, but at the same time will make Redis more responsive when +# there are many keys expiring at the same time, and timeouts may be +# handled with more precision. +# +# The range is between 1 and 500, however a value over 100 is usually not +# a good idea. Most users should use the default of 10 and raise this up to +# 100 only in environments where very low latency is required. +hz 10 + +# When a child rewrites the AOF file, if the following option is enabled +# the file will be fsync-ed every 32 MB of data generated. This is useful +# in order to commit the file to the disk more incrementally and avoid +# big latency spikes. +aof-rewrite-incremental-fsync yes + diff --git a/configs/6380.conf b/configs/6380.conf new file mode 100644 index 00000000..9b0e83e8 --- /dev/null +++ b/configs/6380.conf @@ -0,0 +1,717 @@ +# Redis configuration file example + +# Note on units: when memory size is needed, it is possible to specify +# it in the usual form of 1k 5GB 4M and so forth: +# +# 1k => 1000 bytes +# 1kb => 1024 bytes +# 1m => 1000000 bytes +# 1mb => 1024*1024 bytes +# 1g => 1000000000 bytes +# 1gb => 1024*1024*1024 bytes +# +# units are case insensitive so 1GB 1Gb 1gB are all the same. + +################################## INCLUDES ################################### + +# Include one or more other config files here. This is useful if you +# have a standard template that goes to all Redis server but also need +# to customize a few per-server settings. Include files can include +# other files, so use this wisely. +# +# Notice option "include" won't be rewritten by command "CONFIG REWRITE" +# from admin or Redis Sentinel. Since Redis always uses the last processed +# line as value of a configuration directive, you'd better put includes +# at the beginning of this file to avoid overwriting config change at runtime. +# +# If instead you are interested in using includes to override configuration +# options, it is better to use include as the last line. +# +# include /path/to/local.conf +# include /path/to/other.conf + +################################ GENERAL ##################################### + +# By default Redis does not run as a daemon. Use 'yes' if you need it. +# Note that Redis will write a pid file in /var/run/redis.pid when daemonized. +daemonize no + +# When running daemonized, Redis writes a pid file in /var/run/redis.pid by +# default. You can specify a custom pid file location here. +pidfile /var/run/redis.pid + +# Accept connections on the specified port, default is 6379. +# If port 0 is specified Redis will not listen on a TCP socket. +port 6380 + +# TCP listen() backlog. +# +# In high requests-per-second environments you need an high backlog in order +# to avoid slow clients connections issues. Note that the Linux kernel +# will silently truncate it to the value of /proc/sys/net/core/somaxconn so +# make sure to raise both the value of somaxconn and tcp_max_syn_backlog +# in order to get the desired effect. +tcp-backlog 511 + +# By default Redis listens for connections from all the network interfaces +# available on the server. It is possible to listen to just one or multiple +# interfaces using the "bind" configuration directive, followed by one or +# more IP addresses. +# +# Examples: +# +# bind 192.168.1.100 10.0.0.1 +# bind 127.0.0.1 + +# Specify the path for the Unix socket that will be used to listen for +# incoming connections. There is no default, so Redis will not listen +# on a unix socket when not specified. +# +unixsocket /tmp/redis.sock +unixsocketperm 755 + +# Close the connection after a client is idle for N seconds (0 to disable) +timeout 0 + +# TCP keepalive. +# +# If non-zero, use SO_KEEPALIVE to send TCP ACKs to clients in absence +# of communication. This is useful for two reasons: +# +# 1) Detect dead peers. +# 2) Take the connection alive from the point of view of network +# equipment in the middle. +# +# On Linux, the specified value (in seconds) is the period used to send ACKs. +# Note that to close the connection the double of the time is needed. +# On other kernels the period depends on the kernel configuration. +# +# A reasonable value for this option is 60 seconds. +tcp-keepalive 0 + +# Specify the server verbosity level. +# This can be one of: +# debug (a lot of information, useful for development/testing) +# verbose (many rarely useful info, but not a mess like the debug level) +# notice (moderately verbose, what you want in production probably) +# warning (only very important / critical messages are logged) +loglevel notice + +# Specify the log file name. Also the empty string can be used to force +# Redis to log on the standard output. Note that if you use standard +# output for logging but daemonize, logs will be sent to /dev/null +logfile "" + +# To enable logging to the system logger, just set 'syslog-enabled' to yes, +# and optionally update the other syslog parameters to suit your needs. +# syslog-enabled no + +# Specify the syslog identity. +# syslog-ident redis + +# Specify the syslog facility. Must be USER or between LOCAL0-LOCAL7. +# syslog-facility local0 + +# Set the number of databases. The default database is DB 0, you can select +# a different one on a per-connection basis using SELECT where +# dbid is a number between 0 and 'databases'-1 +databases 16 + +################################ SNAPSHOTTING ################################ +# +# Save the DB on disk: +# +# save +# +# Will save the DB if both the given number of seconds and the given +# number of write operations against the DB occurred. +# +# In the example below the behaviour will be to save: +# after 900 sec (15 min) if at least 1 key changed +# after 300 sec (5 min) if at least 10 keys changed +# after 60 sec if at least 10000 keys changed +# +# Note: you can disable saving at all commenting all the "save" lines. +# +# It is also possible to remove all the previously configured save +# points by adding a save directive with a single empty string argument +# like in the following example: +# +# save "" + +#save 900 1 +#save 300 10 +#save 60 10000 + +# By default Redis will stop accepting writes if RDB snapshots are enabled +# (at least one save point) and the latest background save failed. +# This will make the user aware (in a hard way) that data is not persisting +# on disk properly, otherwise chances are that no one will notice and some +# disaster will happen. +# +# If the background saving process will start working again Redis will +# automatically allow writes again. +# +# However if you have setup your proper monitoring of the Redis server +# and persistence, you may want to disable this feature so that Redis will +# continue to work as usual even if there are problems with disk, +# permissions, and so forth. +stop-writes-on-bgsave-error yes + +# Compress string objects using LZF when dump .rdb databases? +# For default that's set to 'yes' as it's almost always a win. +# If you want to save some CPU in the saving child set it to 'no' but +# the dataset will likely be bigger if you have compressible values or keys. +rdbcompression yes + +# Since version 5 of RDB a CRC64 checksum is placed at the end of the file. +# This makes the format more resistant to corruption but there is a performance +# hit to pay (around 10%) when saving and loading RDB files, so you can disable it +# for maximum performances. +# +# RDB files created with checksum disabled have a checksum of zero that will +# tell the loading code to skip the check. +rdbchecksum yes + +# The filename where to dump the DB +dbfilename dump2.rdb + +# The working directory. +# +# The DB will be written inside this directory, with the filename specified +# above using the 'dbfilename' configuration directive. +# +# The Append Only File will also be created inside this directory. +# +# Note that you must specify a directory here, not a file name. +dir /home/user/dumps/ + +################################# REPLICATION ################################# + +# Master-Slave replication. Use slaveof to make a Redis instance a copy of +# another Redis server. Note that the configuration is local to the slave +# so for example it is possible to configure the slave to save the DB with a +# different interval, or to listen to another port, and so on. +# +# slaveof + +# If the master is password protected (using the "requirepass" configuration +# directive below) it is possible to tell the slave to authenticate before +# starting the replication synchronization process, otherwise the master will +# refuse the slave request. +# +# masterauth + +# When a slave loses its connection with the master, or when the replication +# is still in progress, the slave can act in two different ways: +# +# 1) if slave-serve-stale-data is set to 'yes' (the default) the slave will +# still reply to client requests, possibly with out of date data, or the +# data set may just be empty if this is the first synchronization. +# +# 2) if slave-serve-stale-data is set to 'no' the slave will reply with +# an error "SYNC with master in progress" to all the kind of commands +# but to INFO and SLAVEOF. +# +slave-serve-stale-data yes + +# You can configure a slave instance to accept writes or not. Writing against +# a slave instance may be useful to store some ephemeral data (because data +# written on a slave will be easily deleted after resync with the master) but +# may also cause problems if clients are writing to it because of a +# misconfiguration. +# +# Since Redis 2.6 by default slaves are read-only. +# +# Note: read only slaves are not designed to be exposed to untrusted clients +# on the internet. It's just a protection layer against misuse of the instance. +# Still a read only slave exports by default all the administrative commands +# such as CONFIG, DEBUG, and so forth. To a limited extent you can improve +# security of read only slaves using 'rename-command' to shadow all the +# administrative / dangerous commands. +slave-read-only yes + +# Slaves send PINGs to server in a predefined interval. It's possible to change +# this interval with the repl_ping_slave_period option. The default value is 10 +# seconds. +# +# repl-ping-slave-period 10 + +# The following option sets the replication timeout for: +# +# 1) Bulk transfer I/O during SYNC, from the point of view of slave. +# 2) Master timeout from the point of view of slaves (data, pings). +# 3) Slave timeout from the point of view of masters (REPLCONF ACK pings). +# +# It is important to make sure that this value is greater than the value +# specified for repl-ping-slave-period otherwise a timeout will be detected +# every time there is low traffic between the master and the slave. +# +# repl-timeout 60 + +# Disable TCP_NODELAY on the slave socket after SYNC? +# +# If you select "yes" Redis will use a smaller number of TCP packets and +# less bandwidth to send data to slaves. But this can add a delay for +# the data to appear on the slave side, up to 40 milliseconds with +# Linux kernels using a default configuration. +# +# If you select "no" the delay for data to appear on the slave side will +# be reduced but more bandwidth will be used for replication. +# +# By default we optimize for low latency, but in very high traffic conditions +# or when the master and slaves are many hops away, turning this to "yes" may +# be a good idea. +repl-disable-tcp-nodelay no + +# Set the replication backlog size. The backlog is a buffer that accumulates +# slave data when slaves are disconnected for some time, so that when a slave +# wants to reconnect again, often a full resync is not needed, but a partial +# resync is enough, just passing the portion of data the slave missed while +# disconnected. +# +# The biggest the replication backlog, the longer the time the slave can be +# disconnected and later be able to perform a partial resynchronization. +# +# The backlog is only allocated once there is at least a slave connected. +# +# repl-backlog-size 1mb + +# After a master has no longer connected slaves for some time, the backlog +# will be freed. The following option configures the amount of seconds that +# need to elapse, starting from the time the last slave disconnected, for +# the backlog buffer to be freed. +# +# A value of 0 means to never release the backlog. +# +# repl-backlog-ttl 3600 + +# The slave priority is an integer number published by Redis in the INFO output. +# It is used by Redis Sentinel in order to select a slave to promote into a +# master if the master is no longer working correctly. +# +# A slave with a low priority number is considered better for promotion, so +# for instance if there are three slaves with priority 10, 100, 25 Sentinel will +# pick the one with priority 10, that is the lowest. +# +# However a special priority of 0 marks the slave as not able to perform the +# role of master, so a slave with priority of 0 will never be selected by +# Redis Sentinel for promotion. +# +# By default the priority is 100. +slave-priority 100 + +# It is possible for a master to stop accepting writes if there are less than +# N slaves connected, having a lag less or equal than M seconds. +# +# The N slaves need to be in "online" state. +# +# The lag in seconds, that must be <= the specified value, is calculated from +# the last ping received from the slave, that is usually sent every second. +# +# This option does not GUARANTEES that N replicas will accept the write, but +# will limit the window of exposure for lost writes in case not enough slaves +# are available, to the specified number of seconds. +# +# For example to require at least 3 slaves with a lag <= 10 seconds use: +# +# min-slaves-to-write 3 +# min-slaves-max-lag 10 +# +# Setting one or the other to 0 disables the feature. +# +# By default min-slaves-to-write is set to 0 (feature disabled) and +# min-slaves-max-lag is set to 10. + +################################## SECURITY ################################### + +# Require clients to issue AUTH before processing any other +# commands. This might be useful in environments in which you do not trust +# others with access to the host running redis-server. +# +# This should stay commented out for backward compatibility and because most +# people do not need auth (e.g. they run their own servers). +# +# Warning: since Redis is pretty fast an outside user can try up to +# 150k passwords per second against a good box. This means that you should +# use a very strong password otherwise it will be very easy to break. +# +# requirepass foobared + +# Command renaming. +# +# It is possible to change the name of dangerous commands in a shared +# environment. For instance the CONFIG command may be renamed into something +# hard to guess so that it will still be available for internal-use tools +# but not available for general clients. +# +# Example: +# +# rename-command CONFIG b840fc02d524045429941cc15f59e41cb7be6c52 +# +# It is also possible to completely kill a command by renaming it into +# an empty string: +# +# rename-command CONFIG "" +# +# Please note that changing the name of commands that are logged into the +# AOF file or transmitted to slaves may cause problems. + +################################### LIMITS #################################### + +# Set the max number of connected clients at the same time. By default +# this limit is set to 10000 clients, however if the Redis server is not +# able to configure the process file limit to allow for the specified limit +# the max number of allowed clients is set to the current file limit +# minus 32 (as Redis reserves a few file descriptors for internal uses). +# +# Once the limit is reached Redis will close all the new connections sending +# an error 'max number of clients reached'. +# +# maxclients 10000 + +# Don't use more memory than the specified amount of bytes. +# When the memory limit is reached Redis will try to remove keys +# according to the eviction policy selected (see maxmemory-policy). +# +# If Redis can't remove keys according to the policy, or if the policy is +# set to 'noeviction', Redis will start to reply with errors to commands +# that would use more memory, like SET, LPUSH, and so on, and will continue +# to reply to read-only commands like GET. +# +# This option is usually useful when using Redis as an LRU cache, or to set +# a hard memory limit for an instance (using the 'noeviction' policy). +# +# WARNING: If you have slaves attached to an instance with maxmemory on, +# the size of the output buffers needed to feed the slaves are subtracted +# from the used memory count, so that network problems / resyncs will +# not trigger a loop where keys are evicted, and in turn the output +# buffer of slaves is full with DELs of keys evicted triggering the deletion +# of more keys, and so forth until the database is completely emptied. +# +# In short... if you have slaves attached it is suggested that you set a lower +# limit for maxmemory so that there is some free RAM on the system for slave +# output buffers (but this is not needed if the policy is 'noeviction'). +# +# maxmemory + +# MAXMEMORY POLICY: how Redis will select what to remove when maxmemory +# is reached. You can select among five behaviors: +# +# volatile-lru -> remove the key with an expire set using an LRU algorithm +# allkeys-lru -> remove any key accordingly to the LRU algorithm +# volatile-random -> remove a random key with an expire set +# allkeys-random -> remove a random key, any key +# volatile-ttl -> remove the key with the nearest expire time (minor TTL) +# noeviction -> don't expire at all, just return an error on write operations +# +# Note: with any of the above policies, Redis will return an error on write +# operations, when there are not suitable keys for eviction. +# +# At the date of writing this commands are: set setnx setex append +# incr decr rpush lpush rpushx lpushx linsert lset rpoplpush sadd +# sinter sinterstore sunion sunionstore sdiff sdiffstore zadd zincrby +# zunionstore zinterstore hset hsetnx hmset hincrby incrby decrby +# getset mset msetnx exec sort +# +# The default is: +# +# maxmemory-policy volatile-lru + +# LRU and minimal TTL algorithms are not precise algorithms but approximated +# algorithms (in order to save memory), so you can select as well the sample +# size to check. For instance for default Redis will check three keys and +# pick the one that was used less recently, you can change the sample size +# using the following configuration directive. +# +# maxmemory-samples 3 + +############################## APPEND ONLY MODE ############################### + +# By default Redis asynchronously dumps the dataset on disk. This mode is +# good enough in many applications, but an issue with the Redis process or +# a power outage may result into a few minutes of writes lost (depending on +# the configured save points). +# +# The Append Only File is an alternative persistence mode that provides +# much better durability. For instance using the default data fsync policy +# (see later in the config file) Redis can lose just one second of writes in a +# dramatic event like a server power outage, or a single write if something +# wrong with the Redis process itself happens, but the operating system is +# still running correctly. +# +# AOF and RDB persistence can be enabled at the same time without problems. +# If the AOF is enabled on startup Redis will load the AOF, that is the file +# with the better durability guarantees. +# +# Please check http://redis.io/topics/persistence for more information. + +appendonly no + +# The name of the append only file (default: "appendonly.aof") + +appendfilename "appendonly.aof" + +# The fsync() call tells the Operating System to actually write data on disk +# instead to wait for more data in the output buffer. Some OS will really flush +# data on disk, some other OS will just try to do it ASAP. +# +# Redis supports three different modes: +# +# no: don't fsync, just let the OS flush the data when it wants. Faster. +# always: fsync after every write to the append only log . Slow, Safest. +# everysec: fsync only one time every second. Compromise. +# +# The default is "everysec", as that's usually the right compromise between +# speed and data safety. It's up to you to understand if you can relax this to +# "no" that will let the operating system flush the output buffer when +# it wants, for better performances (but if you can live with the idea of +# some data loss consider the default persistence mode that's snapshotting), +# or on the contrary, use "always" that's very slow but a bit safer than +# everysec. +# +# More details please check the following article: +# http://antirez.com/post/redis-persistence-demystified.html +# +# If unsure, use "everysec". + +# appendfsync always +appendfsync everysec +# appendfsync no + +# When the AOF fsync policy is set to always or everysec, and a background +# saving process (a background save or AOF log background rewriting) is +# performing a lot of I/O against the disk, in some Linux configurations +# Redis may block too long on the fsync() call. Note that there is no fix for +# this currently, as even performing fsync in a different thread will block +# our synchronous write(2) call. +# +# In order to mitigate this problem it's possible to use the following option +# that will prevent fsync() from being called in the main process while a +# BGSAVE or BGREWRITEAOF is in progress. +# +# This means that while another child is saving, the durability of Redis is +# the same as "appendfsync none". In practical terms, this means that it is +# possible to lose up to 30 seconds of log in the worst scenario (with the +# default Linux settings). +# +# If you have latency problems turn this to "yes". Otherwise leave it as +# "no" that is the safest pick from the point of view of durability. + +no-appendfsync-on-rewrite no + +# Automatic rewrite of the append only file. +# Redis is able to automatically rewrite the log file implicitly calling +# BGREWRITEAOF when the AOF log size grows by the specified percentage. +# +# This is how it works: Redis remembers the size of the AOF file after the +# latest rewrite (if no rewrite has happened since the restart, the size of +# the AOF at startup is used). +# +# This base size is compared to the current size. If the current size is +# bigger than the specified percentage, the rewrite is triggered. Also +# you need to specify a minimal size for the AOF file to be rewritten, this +# is useful to avoid rewriting the AOF file even if the percentage increase +# is reached but it is still pretty small. +# +# Specify a percentage of zero in order to disable the automatic AOF +# rewrite feature. + +auto-aof-rewrite-percentage 100 +auto-aof-rewrite-min-size 64mb + +################################ LUA SCRIPTING ############################### + +# Max execution time of a Lua script in milliseconds. +# +# If the maximum execution time is reached Redis will log that a script is +# still in execution after the maximum allowed time and will start to +# reply to queries with an error. +# +# When a long running script exceed the maximum execution time only the +# SCRIPT KILL and SHUTDOWN NOSAVE commands are available. The first can be +# used to stop a script that did not yet called write commands. The second +# is the only way to shut down the server in the case a write commands was +# already issue by the script but the user don't want to wait for the natural +# termination of the script. +# +# Set it to 0 or a negative value for unlimited execution without warnings. +lua-time-limit 5000 + +################################## SLOW LOG ################################### + +# The Redis Slow Log is a system to log queries that exceeded a specified +# execution time. The execution time does not include the I/O operations +# like talking with the client, sending the reply and so forth, +# but just the time needed to actually execute the command (this is the only +# stage of command execution where the thread is blocked and can not serve +# other requests in the meantime). +# +# You can configure the slow log with two parameters: one tells Redis +# what is the execution time, in microseconds, to exceed in order for the +# command to get logged, and the other parameter is the length of the +# slow log. When a new command is logged the oldest one is removed from the +# queue of logged commands. + +# The following time is expressed in microseconds, so 1000000 is equivalent +# to one second. Note that a negative number disables the slow log, while +# a value of zero forces the logging of every command. +slowlog-log-slower-than 10000 + +# There is no limit to this length. Just be aware that it will consume memory. +# You can reclaim memory used by the slow log with SLOWLOG RESET. +slowlog-max-len 128 + +############################# Event notification ############################## + +# Redis can notify Pub/Sub clients about events happening in the key space. +# This feature is documented at http://redis.io/topics/keyspace-events +# +# For instance if keyspace events notification is enabled, and a client +# performs a DEL operation on key "foo" stored in the Database 0, two +# messages will be published via Pub/Sub: +# +# PUBLISH __keyspace@0__:foo del +# PUBLISH __keyevent@0__:del foo +# +# It is possible to select the events that Redis will notify among a set +# of classes. Every class is identified by a single character: +# +# K Keyspace events, published with __keyspace@__ prefix. +# E Keyevent events, published with __keyevent@__ prefix. +# g Generic commands (non-type specific) like DEL, EXPIRE, RENAME, ... +# $ String commands +# l List commands +# s Set commands +# h Hash commands +# z Sorted set commands +# x Expired events (events generated every time a key expires) +# e Evicted events (events generated when a key is evicted for maxmemory) +# A Alias for g$lshzxe, so that the "AKE" string means all the events. +# +# The "notify-keyspace-events" takes as argument a string that is composed +# by zero or multiple characters. The empty string means that notifications +# are disabled at all. +# +# Example: to enable list and generic events, from the point of view of the +# event name, use: +# +# notify-keyspace-events Elg +# +# Example 2: to get the stream of the expired keys subscribing to channel +# name __keyevent@0__:expired use: +# +# notify-keyspace-events Ex +# +# By default all notifications are disabled because most users don't need +# this feature and the feature has some overhead. Note that if you don't +# specify at least one of K or E, no events will be delivered. +notify-keyspace-events "" + +############################### ADVANCED CONFIG ############################### + +# Hashes are encoded using a memory efficient data structure when they have a +# small number of entries, and the biggest entry does not exceed a given +# threshold. These thresholds can be configured using the following directives. +hash-max-ziplist-entries 512 +hash-max-ziplist-value 64 + +# Similarly to hashes, small lists are also encoded in a special way in order +# to save a lot of space. The special representation is only used when +# you are under the following limits: +list-max-ziplist-entries 512 +list-max-ziplist-value 64 + +# Sets have a special encoding in just one case: when a set is composed +# of just strings that happens to be integers in radix 10 in the range +# of 64 bit signed integers. +# The following configuration setting sets the limit in the size of the +# set in order to use this special memory saving encoding. +set-max-intset-entries 512 + +# Similarly to hashes and lists, sorted sets are also specially encoded in +# order to save a lot of space. This encoding is only used when the length and +# elements of a sorted set are below the following limits: +zset-max-ziplist-entries 128 +zset-max-ziplist-value 64 + +# Active rehashing uses 1 millisecond every 100 milliseconds of CPU time in +# order to help rehashing the main Redis hash table (the one mapping top-level +# keys to values). The hash table implementation Redis uses (see dict.c) +# performs a lazy rehashing: the more operation you run into a hash table +# that is rehashing, the more rehashing "steps" are performed, so if the +# server is idle the rehashing is never complete and some more memory is used +# by the hash table. +# +# The default is to use this millisecond 10 times every second in order to +# active rehashing the main dictionaries, freeing memory when possible. +# +# If unsure: +# use "activerehashing no" if you have hard latency requirements and it is +# not a good thing in your environment that Redis can reply form time to time +# to queries with 2 milliseconds delay. +# +# use "activerehashing yes" if you don't have such hard requirements but +# want to free memory asap when possible. +activerehashing yes + +# The client output buffer limits can be used to force disconnection of clients +# that are not reading data from the server fast enough for some reason (a +# common reason is that a Pub/Sub client can't consume messages as fast as the +# publisher can produce them). +# +# The limit can be set differently for the three different classes of clients: +# +# normal -> normal clients +# slave -> slave clients and MONITOR clients +# pubsub -> clients subscribed to at least one pubsub channel or pattern +# +# The syntax of every client-output-buffer-limit directive is the following: +# +# client-output-buffer-limit +# +# A client is immediately disconnected once the hard limit is reached, or if +# the soft limit is reached and remains reached for the specified number of +# seconds (continuously). +# So for instance if the hard limit is 32 megabytes and the soft limit is +# 16 megabytes / 10 seconds, the client will get disconnected immediately +# if the size of the output buffers reach 32 megabytes, but will also get +# disconnected if the client reaches 16 megabytes and continuously overcomes +# the limit for 10 seconds. +# +# By default normal clients are not limited because they don't receive data +# without asking (in a push way), but just after a request, so only +# asynchronous clients may create a scenario where data is requested faster +# than it can read. +# +# Instead there is a default limit for pubsub and slave clients, since +# subscribers and slaves receive data in a push fashion. +# +# Both the hard or the soft limit can be disabled by setting them to zero. +client-output-buffer-limit normal 0 0 0 +client-output-buffer-limit slave 256mb 64mb 60 +client-output-buffer-limit pubsub 32mb 8mb 60 + +# Redis calls an internal function to perform many background tasks, like +# closing connections of clients in timeout, purging expired keys that are +# never requested, and so forth. +# +# Not all tasks are performed with the same frequency, but Redis checks for +# tasks to perform accordingly to the specified "hz" value. +# +# By default "hz" is set to 10. Raising the value will use more CPU when +# Redis is idle, but at the same time will make Redis more responsive when +# there are many keys expiring at the same time, and timeouts may be +# handled with more precision. +# +# The range is between 1 and 500, however a value over 100 is usually not +# a good idea. Most users should use the default of 10 and raise this up to +# 100 only in environments where very low latency is required. +hz 10 + +# When a child rewrites the AOF file, if the following option is enabled +# the file will be fsync-ed every 32 MB of data generated. This is useful +# in order to commit the file to the disk more incrementally and avoid +# big latency spikes. +aof-rewrite-incremental-fsync yes + diff --git a/configs/6381.conf b/configs/6381.conf new file mode 100644 index 00000000..3d11c318 --- /dev/null +++ b/configs/6381.conf @@ -0,0 +1,717 @@ +# Redis configuration file example + +# Note on units: when memory size is needed, it is possible to specify +# it in the usual form of 1k 5GB 4M and so forth: +# +# 1k => 1000 bytes +# 1kb => 1024 bytes +# 1m => 1000000 bytes +# 1mb => 1024*1024 bytes +# 1g => 1000000000 bytes +# 1gb => 1024*1024*1024 bytes +# +# units are case insensitive so 1GB 1Gb 1gB are all the same. + +################################## INCLUDES ################################### + +# Include one or more other config files here. This is useful if you +# have a standard template that goes to all Redis server but also need +# to customize a few per-server settings. Include files can include +# other files, so use this wisely. +# +# Notice option "include" won't be rewritten by command "CONFIG REWRITE" +# from admin or Redis Sentinel. Since Redis always uses the last processed +# line as value of a configuration directive, you'd better put includes +# at the beginning of this file to avoid overwriting config change at runtime. +# +# If instead you are interested in using includes to override configuration +# options, it is better to use include as the last line. +# +# include /path/to/local.conf +# include /path/to/other.conf + +################################ GENERAL ##################################### + +# By default Redis does not run as a daemon. Use 'yes' if you need it. +# Note that Redis will write a pid file in /var/run/redis.pid when daemonized. +daemonize no + +# When running daemonized, Redis writes a pid file in /var/run/redis.pid by +# default. You can specify a custom pid file location here. +pidfile /var/run/redis.pid + +# Accept connections on the specified port, default is 6379. +# If port 0 is specified Redis will not listen on a TCP socket. +port 6381 + +# TCP listen() backlog. +# +# In high requests-per-second environments you need an high backlog in order +# to avoid slow clients connections issues. Note that the Linux kernel +# will silently truncate it to the value of /proc/sys/net/core/somaxconn so +# make sure to raise both the value of somaxconn and tcp_max_syn_backlog +# in order to get the desired effect. +tcp-backlog 511 + +# By default Redis listens for connections from all the network interfaces +# available on the server. It is possible to listen to just one or multiple +# interfaces using the "bind" configuration directive, followed by one or +# more IP addresses. +# +# Examples: +# +# bind 192.168.1.100 10.0.0.1 +# bind 127.0.0.1 + +# Specify the path for the Unix socket that will be used to listen for +# incoming connections. There is no default, so Redis will not listen +# on a unix socket when not specified. +# +unixsocket /tmp/redis.sock +unixsocketperm 755 + +# Close the connection after a client is idle for N seconds (0 to disable) +timeout 0 + +# TCP keepalive. +# +# If non-zero, use SO_KEEPALIVE to send TCP ACKs to clients in absence +# of communication. This is useful for two reasons: +# +# 1) Detect dead peers. +# 2) Take the connection alive from the point of view of network +# equipment in the middle. +# +# On Linux, the specified value (in seconds) is the period used to send ACKs. +# Note that to close the connection the double of the time is needed. +# On other kernels the period depends on the kernel configuration. +# +# A reasonable value for this option is 60 seconds. +tcp-keepalive 0 + +# Specify the server verbosity level. +# This can be one of: +# debug (a lot of information, useful for development/testing) +# verbose (many rarely useful info, but not a mess like the debug level) +# notice (moderately verbose, what you want in production probably) +# warning (only very important / critical messages are logged) +loglevel notice + +# Specify the log file name. Also the empty string can be used to force +# Redis to log on the standard output. Note that if you use standard +# output for logging but daemonize, logs will be sent to /dev/null +logfile "" + +# To enable logging to the system logger, just set 'syslog-enabled' to yes, +# and optionally update the other syslog parameters to suit your needs. +# syslog-enabled no + +# Specify the syslog identity. +# syslog-ident redis + +# Specify the syslog facility. Must be USER or between LOCAL0-LOCAL7. +# syslog-facility local0 + +# Set the number of databases. The default database is DB 0, you can select +# a different one on a per-connection basis using SELECT where +# dbid is a number between 0 and 'databases'-1 +databases 16 + +################################ SNAPSHOTTING ################################ +# +# Save the DB on disk: +# +# save +# +# Will save the DB if both the given number of seconds and the given +# number of write operations against the DB occurred. +# +# In the example below the behaviour will be to save: +# after 900 sec (15 min) if at least 1 key changed +# after 300 sec (5 min) if at least 10 keys changed +# after 60 sec if at least 10000 keys changed +# +# Note: you can disable saving at all commenting all the "save" lines. +# +# It is also possible to remove all the previously configured save +# points by adding a save directive with a single empty string argument +# like in the following example: +# +# save "" + +#save 900 1 +#save 300 10 +#save 60 10000 + +# By default Redis will stop accepting writes if RDB snapshots are enabled +# (at least one save point) and the latest background save failed. +# This will make the user aware (in a hard way) that data is not persisting +# on disk properly, otherwise chances are that no one will notice and some +# disaster will happen. +# +# If the background saving process will start working again Redis will +# automatically allow writes again. +# +# However if you have setup your proper monitoring of the Redis server +# and persistence, you may want to disable this feature so that Redis will +# continue to work as usual even if there are problems with disk, +# permissions, and so forth. +stop-writes-on-bgsave-error yes + +# Compress string objects using LZF when dump .rdb databases? +# For default that's set to 'yes' as it's almost always a win. +# If you want to save some CPU in the saving child set it to 'no' but +# the dataset will likely be bigger if you have compressible values or keys. +rdbcompression yes + +# Since version 5 of RDB a CRC64 checksum is placed at the end of the file. +# This makes the format more resistant to corruption but there is a performance +# hit to pay (around 10%) when saving and loading RDB files, so you can disable it +# for maximum performances. +# +# RDB files created with checksum disabled have a checksum of zero that will +# tell the loading code to skip the check. +rdbchecksum yes + +# The filename where to dump the DB +dbfilename dump3.rdb + +# The working directory. +# +# The DB will be written inside this directory, with the filename specified +# above using the 'dbfilename' configuration directive. +# +# The Append Only File will also be created inside this directory. +# +# Note that you must specify a directory here, not a file name. +dir /home/user/dumps/ + +################################# REPLICATION ################################# + +# Master-Slave replication. Use slaveof to make a Redis instance a copy of +# another Redis server. Note that the configuration is local to the slave +# so for example it is possible to configure the slave to save the DB with a +# different interval, or to listen to another port, and so on. +# +# slaveof + +# If the master is password protected (using the "requirepass" configuration +# directive below) it is possible to tell the slave to authenticate before +# starting the replication synchronization process, otherwise the master will +# refuse the slave request. +# +# masterauth + +# When a slave loses its connection with the master, or when the replication +# is still in progress, the slave can act in two different ways: +# +# 1) if slave-serve-stale-data is set to 'yes' (the default) the slave will +# still reply to client requests, possibly with out of date data, or the +# data set may just be empty if this is the first synchronization. +# +# 2) if slave-serve-stale-data is set to 'no' the slave will reply with +# an error "SYNC with master in progress" to all the kind of commands +# but to INFO and SLAVEOF. +# +slave-serve-stale-data yes + +# You can configure a slave instance to accept writes or not. Writing against +# a slave instance may be useful to store some ephemeral data (because data +# written on a slave will be easily deleted after resync with the master) but +# may also cause problems if clients are writing to it because of a +# misconfiguration. +# +# Since Redis 2.6 by default slaves are read-only. +# +# Note: read only slaves are not designed to be exposed to untrusted clients +# on the internet. It's just a protection layer against misuse of the instance. +# Still a read only slave exports by default all the administrative commands +# such as CONFIG, DEBUG, and so forth. To a limited extent you can improve +# security of read only slaves using 'rename-command' to shadow all the +# administrative / dangerous commands. +slave-read-only yes + +# Slaves send PINGs to server in a predefined interval. It's possible to change +# this interval with the repl_ping_slave_period option. The default value is 10 +# seconds. +# +# repl-ping-slave-period 10 + +# The following option sets the replication timeout for: +# +# 1) Bulk transfer I/O during SYNC, from the point of view of slave. +# 2) Master timeout from the point of view of slaves (data, pings). +# 3) Slave timeout from the point of view of masters (REPLCONF ACK pings). +# +# It is important to make sure that this value is greater than the value +# specified for repl-ping-slave-period otherwise a timeout will be detected +# every time there is low traffic between the master and the slave. +# +# repl-timeout 60 + +# Disable TCP_NODELAY on the slave socket after SYNC? +# +# If you select "yes" Redis will use a smaller number of TCP packets and +# less bandwidth to send data to slaves. But this can add a delay for +# the data to appear on the slave side, up to 40 milliseconds with +# Linux kernels using a default configuration. +# +# If you select "no" the delay for data to appear on the slave side will +# be reduced but more bandwidth will be used for replication. +# +# By default we optimize for low latency, but in very high traffic conditions +# or when the master and slaves are many hops away, turning this to "yes" may +# be a good idea. +repl-disable-tcp-nodelay no + +# Set the replication backlog size. The backlog is a buffer that accumulates +# slave data when slaves are disconnected for some time, so that when a slave +# wants to reconnect again, often a full resync is not needed, but a partial +# resync is enough, just passing the portion of data the slave missed while +# disconnected. +# +# The biggest the replication backlog, the longer the time the slave can be +# disconnected and later be able to perform a partial resynchronization. +# +# The backlog is only allocated once there is at least a slave connected. +# +# repl-backlog-size 1mb + +# After a master has no longer connected slaves for some time, the backlog +# will be freed. The following option configures the amount of seconds that +# need to elapse, starting from the time the last slave disconnected, for +# the backlog buffer to be freed. +# +# A value of 0 means to never release the backlog. +# +# repl-backlog-ttl 3600 + +# The slave priority is an integer number published by Redis in the INFO output. +# It is used by Redis Sentinel in order to select a slave to promote into a +# master if the master is no longer working correctly. +# +# A slave with a low priority number is considered better for promotion, so +# for instance if there are three slaves with priority 10, 100, 25 Sentinel will +# pick the one with priority 10, that is the lowest. +# +# However a special priority of 0 marks the slave as not able to perform the +# role of master, so a slave with priority of 0 will never be selected by +# Redis Sentinel for promotion. +# +# By default the priority is 100. +slave-priority 100 + +# It is possible for a master to stop accepting writes if there are less than +# N slaves connected, having a lag less or equal than M seconds. +# +# The N slaves need to be in "online" state. +# +# The lag in seconds, that must be <= the specified value, is calculated from +# the last ping received from the slave, that is usually sent every second. +# +# This option does not GUARANTEES that N replicas will accept the write, but +# will limit the window of exposure for lost writes in case not enough slaves +# are available, to the specified number of seconds. +# +# For example to require at least 3 slaves with a lag <= 10 seconds use: +# +# min-slaves-to-write 3 +# min-slaves-max-lag 10 +# +# Setting one or the other to 0 disables the feature. +# +# By default min-slaves-to-write is set to 0 (feature disabled) and +# min-slaves-max-lag is set to 10. + +################################## SECURITY ################################### + +# Require clients to issue AUTH before processing any other +# commands. This might be useful in environments in which you do not trust +# others with access to the host running redis-server. +# +# This should stay commented out for backward compatibility and because most +# people do not need auth (e.g. they run their own servers). +# +# Warning: since Redis is pretty fast an outside user can try up to +# 150k passwords per second against a good box. This means that you should +# use a very strong password otherwise it will be very easy to break. +# +# requirepass foobared + +# Command renaming. +# +# It is possible to change the name of dangerous commands in a shared +# environment. For instance the CONFIG command may be renamed into something +# hard to guess so that it will still be available for internal-use tools +# but not available for general clients. +# +# Example: +# +# rename-command CONFIG b840fc02d524045429941cc15f59e41cb7be6c52 +# +# It is also possible to completely kill a command by renaming it into +# an empty string: +# +# rename-command CONFIG "" +# +# Please note that changing the name of commands that are logged into the +# AOF file or transmitted to slaves may cause problems. + +################################### LIMITS #################################### + +# Set the max number of connected clients at the same time. By default +# this limit is set to 10000 clients, however if the Redis server is not +# able to configure the process file limit to allow for the specified limit +# the max number of allowed clients is set to the current file limit +# minus 32 (as Redis reserves a few file descriptors for internal uses). +# +# Once the limit is reached Redis will close all the new connections sending +# an error 'max number of clients reached'. +# +# maxclients 10000 + +# Don't use more memory than the specified amount of bytes. +# When the memory limit is reached Redis will try to remove keys +# according to the eviction policy selected (see maxmemory-policy). +# +# If Redis can't remove keys according to the policy, or if the policy is +# set to 'noeviction', Redis will start to reply with errors to commands +# that would use more memory, like SET, LPUSH, and so on, and will continue +# to reply to read-only commands like GET. +# +# This option is usually useful when using Redis as an LRU cache, or to set +# a hard memory limit for an instance (using the 'noeviction' policy). +# +# WARNING: If you have slaves attached to an instance with maxmemory on, +# the size of the output buffers needed to feed the slaves are subtracted +# from the used memory count, so that network problems / resyncs will +# not trigger a loop where keys are evicted, and in turn the output +# buffer of slaves is full with DELs of keys evicted triggering the deletion +# of more keys, and so forth until the database is completely emptied. +# +# In short... if you have slaves attached it is suggested that you set a lower +# limit for maxmemory so that there is some free RAM on the system for slave +# output buffers (but this is not needed if the policy is 'noeviction'). +# +# maxmemory + +# MAXMEMORY POLICY: how Redis will select what to remove when maxmemory +# is reached. You can select among five behaviors: +# +# volatile-lru -> remove the key with an expire set using an LRU algorithm +# allkeys-lru -> remove any key accordingly to the LRU algorithm +# volatile-random -> remove a random key with an expire set +# allkeys-random -> remove a random key, any key +# volatile-ttl -> remove the key with the nearest expire time (minor TTL) +# noeviction -> don't expire at all, just return an error on write operations +# +# Note: with any of the above policies, Redis will return an error on write +# operations, when there are not suitable keys for eviction. +# +# At the date of writing this commands are: set setnx setex append +# incr decr rpush lpush rpushx lpushx linsert lset rpoplpush sadd +# sinter sinterstore sunion sunionstore sdiff sdiffstore zadd zincrby +# zunionstore zinterstore hset hsetnx hmset hincrby incrby decrby +# getset mset msetnx exec sort +# +# The default is: +# +# maxmemory-policy volatile-lru + +# LRU and minimal TTL algorithms are not precise algorithms but approximated +# algorithms (in order to save memory), so you can select as well the sample +# size to check. For instance for default Redis will check three keys and +# pick the one that was used less recently, you can change the sample size +# using the following configuration directive. +# +# maxmemory-samples 3 + +############################## APPEND ONLY MODE ############################### + +# By default Redis asynchronously dumps the dataset on disk. This mode is +# good enough in many applications, but an issue with the Redis process or +# a power outage may result into a few minutes of writes lost (depending on +# the configured save points). +# +# The Append Only File is an alternative persistence mode that provides +# much better durability. For instance using the default data fsync policy +# (see later in the config file) Redis can lose just one second of writes in a +# dramatic event like a server power outage, or a single write if something +# wrong with the Redis process itself happens, but the operating system is +# still running correctly. +# +# AOF and RDB persistence can be enabled at the same time without problems. +# If the AOF is enabled on startup Redis will load the AOF, that is the file +# with the better durability guarantees. +# +# Please check http://redis.io/topics/persistence for more information. + +appendonly no + +# The name of the append only file (default: "appendonly.aof") + +appendfilename "appendonly.aof" + +# The fsync() call tells the Operating System to actually write data on disk +# instead to wait for more data in the output buffer. Some OS will really flush +# data on disk, some other OS will just try to do it ASAP. +# +# Redis supports three different modes: +# +# no: don't fsync, just let the OS flush the data when it wants. Faster. +# always: fsync after every write to the append only log . Slow, Safest. +# everysec: fsync only one time every second. Compromise. +# +# The default is "everysec", as that's usually the right compromise between +# speed and data safety. It's up to you to understand if you can relax this to +# "no" that will let the operating system flush the output buffer when +# it wants, for better performances (but if you can live with the idea of +# some data loss consider the default persistence mode that's snapshotting), +# or on the contrary, use "always" that's very slow but a bit safer than +# everysec. +# +# More details please check the following article: +# http://antirez.com/post/redis-persistence-demystified.html +# +# If unsure, use "everysec". + +# appendfsync always +appendfsync everysec +# appendfsync no + +# When the AOF fsync policy is set to always or everysec, and a background +# saving process (a background save or AOF log background rewriting) is +# performing a lot of I/O against the disk, in some Linux configurations +# Redis may block too long on the fsync() call. Note that there is no fix for +# this currently, as even performing fsync in a different thread will block +# our synchronous write(2) call. +# +# In order to mitigate this problem it's possible to use the following option +# that will prevent fsync() from being called in the main process while a +# BGSAVE or BGREWRITEAOF is in progress. +# +# This means that while another child is saving, the durability of Redis is +# the same as "appendfsync none". In practical terms, this means that it is +# possible to lose up to 30 seconds of log in the worst scenario (with the +# default Linux settings). +# +# If you have latency problems turn this to "yes". Otherwise leave it as +# "no" that is the safest pick from the point of view of durability. + +no-appendfsync-on-rewrite no + +# Automatic rewrite of the append only file. +# Redis is able to automatically rewrite the log file implicitly calling +# BGREWRITEAOF when the AOF log size grows by the specified percentage. +# +# This is how it works: Redis remembers the size of the AOF file after the +# latest rewrite (if no rewrite has happened since the restart, the size of +# the AOF at startup is used). +# +# This base size is compared to the current size. If the current size is +# bigger than the specified percentage, the rewrite is triggered. Also +# you need to specify a minimal size for the AOF file to be rewritten, this +# is useful to avoid rewriting the AOF file even if the percentage increase +# is reached but it is still pretty small. +# +# Specify a percentage of zero in order to disable the automatic AOF +# rewrite feature. + +auto-aof-rewrite-percentage 100 +auto-aof-rewrite-min-size 64mb + +################################ LUA SCRIPTING ############################### + +# Max execution time of a Lua script in milliseconds. +# +# If the maximum execution time is reached Redis will log that a script is +# still in execution after the maximum allowed time and will start to +# reply to queries with an error. +# +# When a long running script exceed the maximum execution time only the +# SCRIPT KILL and SHUTDOWN NOSAVE commands are available. The first can be +# used to stop a script that did not yet called write commands. The second +# is the only way to shut down the server in the case a write commands was +# already issue by the script but the user don't want to wait for the natural +# termination of the script. +# +# Set it to 0 or a negative value for unlimited execution without warnings. +lua-time-limit 5000 + +################################## SLOW LOG ################################### + +# The Redis Slow Log is a system to log queries that exceeded a specified +# execution time. The execution time does not include the I/O operations +# like talking with the client, sending the reply and so forth, +# but just the time needed to actually execute the command (this is the only +# stage of command execution where the thread is blocked and can not serve +# other requests in the meantime). +# +# You can configure the slow log with two parameters: one tells Redis +# what is the execution time, in microseconds, to exceed in order for the +# command to get logged, and the other parameter is the length of the +# slow log. When a new command is logged the oldest one is removed from the +# queue of logged commands. + +# The following time is expressed in microseconds, so 1000000 is equivalent +# to one second. Note that a negative number disables the slow log, while +# a value of zero forces the logging of every command. +slowlog-log-slower-than 10000 + +# There is no limit to this length. Just be aware that it will consume memory. +# You can reclaim memory used by the slow log with SLOWLOG RESET. +slowlog-max-len 128 + +############################# Event notification ############################## + +# Redis can notify Pub/Sub clients about events happening in the key space. +# This feature is documented at http://redis.io/topics/keyspace-events +# +# For instance if keyspace events notification is enabled, and a client +# performs a DEL operation on key "foo" stored in the Database 0, two +# messages will be published via Pub/Sub: +# +# PUBLISH __keyspace@0__:foo del +# PUBLISH __keyevent@0__:del foo +# +# It is possible to select the events that Redis will notify among a set +# of classes. Every class is identified by a single character: +# +# K Keyspace events, published with __keyspace@__ prefix. +# E Keyevent events, published with __keyevent@__ prefix. +# g Generic commands (non-type specific) like DEL, EXPIRE, RENAME, ... +# $ String commands +# l List commands +# s Set commands +# h Hash commands +# z Sorted set commands +# x Expired events (events generated every time a key expires) +# e Evicted events (events generated when a key is evicted for maxmemory) +# A Alias for g$lshzxe, so that the "AKE" string means all the events. +# +# The "notify-keyspace-events" takes as argument a string that is composed +# by zero or multiple characters. The empty string means that notifications +# are disabled at all. +# +# Example: to enable list and generic events, from the point of view of the +# event name, use: +# +# notify-keyspace-events Elg +# +# Example 2: to get the stream of the expired keys subscribing to channel +# name __keyevent@0__:expired use: +# +# notify-keyspace-events Ex +# +# By default all notifications are disabled because most users don't need +# this feature and the feature has some overhead. Note that if you don't +# specify at least one of K or E, no events will be delivered. +notify-keyspace-events "" + +############################### ADVANCED CONFIG ############################### + +# Hashes are encoded using a memory efficient data structure when they have a +# small number of entries, and the biggest entry does not exceed a given +# threshold. These thresholds can be configured using the following directives. +hash-max-ziplist-entries 512 +hash-max-ziplist-value 64 + +# Similarly to hashes, small lists are also encoded in a special way in order +# to save a lot of space. The special representation is only used when +# you are under the following limits: +list-max-ziplist-entries 512 +list-max-ziplist-value 64 + +# Sets have a special encoding in just one case: when a set is composed +# of just strings that happens to be integers in radix 10 in the range +# of 64 bit signed integers. +# The following configuration setting sets the limit in the size of the +# set in order to use this special memory saving encoding. +set-max-intset-entries 512 + +# Similarly to hashes and lists, sorted sets are also specially encoded in +# order to save a lot of space. This encoding is only used when the length and +# elements of a sorted set are below the following limits: +zset-max-ziplist-entries 128 +zset-max-ziplist-value 64 + +# Active rehashing uses 1 millisecond every 100 milliseconds of CPU time in +# order to help rehashing the main Redis hash table (the one mapping top-level +# keys to values). The hash table implementation Redis uses (see dict.c) +# performs a lazy rehashing: the more operation you run into a hash table +# that is rehashing, the more rehashing "steps" are performed, so if the +# server is idle the rehashing is never complete and some more memory is used +# by the hash table. +# +# The default is to use this millisecond 10 times every second in order to +# active rehashing the main dictionaries, freeing memory when possible. +# +# If unsure: +# use "activerehashing no" if you have hard latency requirements and it is +# not a good thing in your environment that Redis can reply form time to time +# to queries with 2 milliseconds delay. +# +# use "activerehashing yes" if you don't have such hard requirements but +# want to free memory asap when possible. +activerehashing yes + +# The client output buffer limits can be used to force disconnection of clients +# that are not reading data from the server fast enough for some reason (a +# common reason is that a Pub/Sub client can't consume messages as fast as the +# publisher can produce them). +# +# The limit can be set differently for the three different classes of clients: +# +# normal -> normal clients +# slave -> slave clients and MONITOR clients +# pubsub -> clients subscribed to at least one pubsub channel or pattern +# +# The syntax of every client-output-buffer-limit directive is the following: +# +# client-output-buffer-limit +# +# A client is immediately disconnected once the hard limit is reached, or if +# the soft limit is reached and remains reached for the specified number of +# seconds (continuously). +# So for instance if the hard limit is 32 megabytes and the soft limit is +# 16 megabytes / 10 seconds, the client will get disconnected immediately +# if the size of the output buffers reach 32 megabytes, but will also get +# disconnected if the client reaches 16 megabytes and continuously overcomes +# the limit for 10 seconds. +# +# By default normal clients are not limited because they don't receive data +# without asking (in a push way), but just after a request, so only +# asynchronous clients may create a scenario where data is requested faster +# than it can read. +# +# Instead there is a default limit for pubsub and slave clients, since +# subscribers and slaves receive data in a push fashion. +# +# Both the hard or the soft limit can be disabled by setting them to zero. +client-output-buffer-limit normal 0 0 0 +client-output-buffer-limit slave 256mb 64mb 60 +client-output-buffer-limit pubsub 32mb 8mb 60 + +# Redis calls an internal function to perform many background tasks, like +# closing connections of clients in timeout, purging expired keys that are +# never requested, and so forth. +# +# Not all tasks are performed with the same frequency, but Redis checks for +# tasks to perform accordingly to the specified "hz" value. +# +# By default "hz" is set to 10. Raising the value will use more CPU when +# Redis is idle, but at the same time will make Redis more responsive when +# there are many keys expiring at the same time, and timeouts may be +# handled with more precision. +# +# The range is between 1 and 500, however a value over 100 is usually not +# a good idea. Most users should use the default of 10 and raise this up to +# 100 only in environments where very low latency is required. +hz 10 + +# When a child rewrites the AOF file, if the following option is enabled +# the file will be fsync-ed every 32 MB of data generated. This is useful +# in order to commit the file to the disk more incrementally and avoid +# big latency spikes. +aof-rewrite-incremental-fsync yes + diff --git a/doc/dia/ZMQ_Queuing_Tree.jpg b/doc/dia/ZMQ_Queuing_Tree.jpg new file mode 100644 index 00000000..b4297340 Binary files /dev/null and b/doc/dia/ZMQ_Queuing_Tree.jpg differ diff --git a/doc/screenshots/DashboardAIL.png b/doc/screenshots/DashboardAIL.png new file mode 100644 index 00000000..7a36b2e5 Binary files /dev/null and b/doc/screenshots/DashboardAIL.png differ diff --git a/doc/screenshots/WordtrendingAIL.png b/doc/screenshots/WordtrendingAIL.png new file mode 100644 index 00000000..823dbc46 Binary files /dev/null and b/doc/screenshots/WordtrendingAIL.png differ diff --git a/docsphinx/source/conf.py b/docsphinx/source/conf.py new file mode 100644 index 00000000..9189291c --- /dev/null +++ b/docsphinx/source/conf.py @@ -0,0 +1,246 @@ +# -*- coding: utf-8 -*- +# +# AIL documentation build configuration file, created by +# sphinx-quickstart on Tue May 6 09:36:37 2014. +# +# This file is execfile()d with the current directory set to its containing dir. +# +# Note that not all possible configuration values are present in this +# autogenerated file. +# +# All configuration values have a default; values that are commented out +# serve to show the default. + +import sys, os + +# If extensions (or modules to document with autodoc) are in another directory, +# add these directories to sys.path here. If the directory is relative to the +# documentation root, use os.path.abspath to make it absolute, like shown here. +sys.path.insert(0, os.path.abspath('../../bin/')) + +# -- General configuration ----------------------------------------------------- + +# If your documentation needs a minimal Sphinx version, state it here. +#needs_sphinx = '1.0' + +# Add any Sphinx extension module names here, as strings. They can be extensions +# coming with Sphinx (named 'sphinx.ext.*') or your custom ones. +extensions = ['sphinx.ext.autodoc', 'sphinx.ext.intersphinx', 'sphinx.ext.ifconfig', 'sphinx.ext.viewcode'] + +# Add any paths that contain templates here, relative to this directory. +templates_path = ['_templates'] + +# The suffix of source filenames. +source_suffix = '.rst' + +# The encoding of source files. +#source_encoding = 'utf-8-sig' + +# The master toctree document. +master_doc = 'index' + +# General information about the project. +project = u'AIL' +copyright = u'2014, Jules Debra and CIRCL - Computer Incident Response Center Luxembourg' + +# The version info for the project you're documenting, acts as replacement for +# |version| and |release|, also used in various other places throughout the +# built documents. +# +# The short X.Y version. +version = '0.0.1' +# The full version, including alpha/beta/rc tags. +release = '0.0.1' + +# The language for content autogenerated by Sphinx. Refer to documentation +# for a list of supported languages. +#language = None + +# There are two options for replacing |today|: either, you set today to some +# non-false value, then it is used: +#today = '' +# Else, today_fmt is used as the format for a strftime call. +#today_fmt = '%B %d, %Y' + +# List of patterns, relative to source directory, that match files and +# directories to ignore when looking for source files. +exclude_patterns = [] + +# The reST default role (used for this markup: `text`) to use for all documents. +#default_role = None + +# If true, '()' will be appended to :func: etc. cross-reference text. +#add_function_parentheses = True + +# If true, the current module name will be prepended to all description +# unit titles (such as .. function::). +#add_module_names = True + +# If true, sectionauthor and moduleauthor directives will be shown in the +# output. They are ignored by default. +#show_authors = False + +# The name of the Pygments (syntax highlighting) style to use. +pygments_style = 'sphinx' + +# A list of ignored prefixes for module index sorting. +#modindex_common_prefix = [] + + +# -- Options for HTML output --------------------------------------------------- + +# The theme to use for HTML and HTML Help pages. See the documentation for +# a list of builtin themes. +html_theme = 'default' + +# Theme options are theme-specific and customize the look and feel of a theme +# further. For a list of options available for each theme, see the +# documentation. +#html_theme_options = {} + +# Add any paths that contain custom themes here, relative to this directory. +#html_theme_path = [] + +# The name for this set of Sphinx documents. If None, it defaults to +# " v documentation". +#html_title = None + +# A shorter title for the navigation bar. Default is the same as html_title. +#html_short_title = None + +# The name of an image file (relative to this directory) to place at the top +# of the sidebar. +#html_logo = None + +# The name of an image file (within the static path) to use as favicon of the +# docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32 +# pixels large. +#html_favicon = None + +# Add any paths that contain custom static files (such as style sheets) here, +# relative to this directory. They are copied after the builtin static files, +# so a file named "default.css" will overwrite the builtin "default.css". +html_static_path = ['_static'] + +# If not '', a 'Last updated on:' timestamp is inserted at every page bottom, +# using the given strftime format. +#html_last_updated_fmt = '%b %d, %Y' + +# If true, SmartyPants will be used to convert quotes and dashes to +# typographically correct entities. +#html_use_smartypants = True + +# Custom sidebar templates, maps document names to template names. +#html_sidebars = {} + +# Additional templates that should be rendered to pages, maps page names to +# template names. +#html_additional_pages = {} + +# If false, no module index is generated. +#html_domain_indices = True + +# If false, no index is generated. +#html_use_index = True + +# If true, the index is split into individual pages for each letter. +#html_split_index = False + +# If true, links to the reST sources are added to the pages. +#html_show_sourcelink = True + +# If true, "Created using Sphinx" is shown in the HTML footer. Default is True. +#html_show_sphinx = True + +# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True. +#html_show_copyright = True + +# If true, an OpenSearch description file will be output, and all pages will +# contain a tag referring to it. The value of this option must be the +# base URL from which the finished HTML is served. +#html_use_opensearch = '' + +# This is the file name suffix for HTML files (e.g. ".xhtml"). +#html_file_suffix = None + +# Output file base name for HTML help builder. +htmlhelp_basename = 'AILdoc' + + +# -- Options for LaTeX output -------------------------------------------------- + +latex_elements = { +# The paper size ('letterpaper' or 'a4paper'). +#'papersize': 'letterpaper', + +# The font size ('10pt', '11pt' or '12pt'). +#'pointsize': '10pt', + +# Additional stuff for the LaTeX preamble. +#'preamble': '', +} + +# Grouping the document tree into LaTeX files. List of tuples +# (source start file, target name, title, author, documentclass [howto/manual]). +latex_documents = [ + ('index', 'AIL.tex', u'AIL Documentation', + u'Jules Debra', 'manual'), +] + +# The name of an image file (relative to this directory) to place at the top of +# the title page. +#latex_logo = None + +# For "manual" documents, if this is true, then toplevel headings are parts, +# not chapters. +#latex_use_parts = False + +# If true, show page references after internal links. +#latex_show_pagerefs = False + +# If true, show URL addresses after external links. +#latex_show_urls = False + +# Documents to append as an appendix to all manuals. +#latex_appendices = [] + +# If false, no module index is generated. +#latex_domain_indices = True + + +# -- Options for manual page output -------------------------------------------- + +# One entry per manual page. List of tuples +# (source start file, name, description, authors, manual section). +man_pages = [ + ('index', 'ail', u'AIL Documentation', + [u'Jules Debra'], 1) +] + +# If true, show URL addresses after external links. +#man_show_urls = False + + +# -- Options for Texinfo output ------------------------------------------------ + +# Grouping the document tree into Texinfo files. List of tuples +# (source start file, target name, title, author, +# dir menu entry, description, category) +texinfo_documents = [ + ('index', 'AIL', u'AIL Documentation', + u'Jules Debra', 'AIL', 'One line description of project.', + 'Miscellaneous'), +] + +# Documents to append as an appendix to all manuals. +#texinfo_appendices = [] + +# If false, no module index is generated. +#texinfo_domain_indices = True + +# How to display URL addresses: 'footnote', 'no', or 'inline'. +#texinfo_show_urls = 'footnote' + + +# Example configuration for intersphinx: refer to the Python standard library. +intersphinx_mapping = {'http://docs.python.org/': None} diff --git a/docsphinx/source/index.rst b/docsphinx/source/index.rst new file mode 100644 index 00000000..e405c46e --- /dev/null +++ b/docsphinx/source/index.rst @@ -0,0 +1,52 @@ +.. AIL documentation master file, created by + sphinx-quickstart on Tue May 6 09:36:37 2014. + You can adapt this file completely to your liking, but it should at least + contain the root `toctree` directive. + +Welcome to AIL's documentation! +******************************* +.. toctree:: + :maxdepth: 2 + +.. warning:: + This is not the final version + +lib_words +========= +.. automodule:: packages.lib_words + :members: + +lib_gephi +========= +.. automodule:: packages.lib_gephi + :members: + +lib_redis_insert +================ +.. automodule:: packages.lib_redis_insert + :members: + +lib_search +========== +.. automodule:: packages.lib_search + :members: + +Paste +===== +.. automodule:: packages.Paste + :members: + +ZMQ_PubSub +========== +.. automodule:: packages.ZMQ_PubSub + :members: + + + +Indices and tables +================== + +* :ref:`genindex` +* :ref:`modindex` +* :ref:`search` + diff --git a/files/creditcard_categ b/files/creditcard_categ new file mode 100644 index 00000000..165fd135 --- /dev/null +++ b/files/creditcard_categ @@ -0,0 +1,16 @@ +mastercard +MA +visa +jcb +discover +americanexpress +amex +dankort +cogeban +banrisul +interac +discovercard +unionpay +CB +rupay +verve diff --git a/files/javascript_categ b/files/javascript_categ new file mode 100644 index 00000000..1512b681 --- /dev/null +++ b/files/javascript_categ @@ -0,0 +1,6 @@ +isFinite +isNaN +eval +var +parseFloat +javascript diff --git a/files/list_categ_files b/files/list_categ_files new file mode 100644 index 00000000..286fa36d --- /dev/null +++ b/files/list_categ_files @@ -0,0 +1,6 @@ +../files/mails_categ +../files/creditcard_categ +../files/pass_categ +../files/web_categ +../files/javascript_categ +../files/onion_categ diff --git a/files/mails_categ b/files/mails_categ new file mode 100644 index 00000000..f3b8ef7d --- /dev/null +++ b/files/mails_categ @@ -0,0 +1,22 @@ +gmail +hotmail +yahoo +orange +seznam +yandex +gmx +laposte +wanadoo +numericable +darty +bouygues +aol +outlook +hushmail +yandex +runbox +rediff +rackspace +mail +email +msn diff --git a/files/onion_categ b/files/onion_categ new file mode 100644 index 00000000..5c9980e2 --- /dev/null +++ b/files/onion_categ @@ -0,0 +1 @@ +onion diff --git a/files/pass_categ b/files/pass_categ new file mode 100644 index 00000000..20d2f3f3 --- /dev/null +++ b/files/pass_categ @@ -0,0 +1,23 @@ +123456 +password +12345678 +qwerty +abc123 +123456789 +1234567 +iloveyou +adobe123 +123123 +admin +1234567890 +letmein +photoshop +1234 +monkey +shadow +sunshine +12345 +password1 +princess +azerty +trustno1 diff --git a/files/web_categ b/files/web_categ new file mode 100644 index 00000000..2c98f678 --- /dev/null +++ b/files/web_categ @@ -0,0 +1,3 @@ +http +https +wwww diff --git a/files/wordfile b/files/wordfile new file mode 100644 index 00000000..548894a9 --- /dev/null +++ b/files/wordfile @@ -0,0 +1,46 @@ +password +oppetrol +bitcoin +opsavegaza +AnonGhost +Israel +Gaza +creditcard +tracker +compromise +malware +cert +flaw +exploit +0day +leak +database +terrorist +anonymous +opsyria +OpHackingCup +OpIsrael +OpBigBrother +dump +forex +vulnerable +phishing +account +stolen +wikileaks +gmail +hotmail +hackingteam +finfisher +gamma-international +COTTONMOUTH +COTTONMOUTH-I +COTTONMOUTH-II +COTTONMOUTH-III +DISHFIRE +TURMOIL +SCREAMINGHARPY +SECUREINSIGHT +SHAREDTAFFY +WAGONBED +WILLOWVIXEN diff --git a/installing_deps.sh b/installing_deps.sh new file mode 100644 index 00000000..da9588d8 --- /dev/null +++ b/installing_deps.sh @@ -0,0 +1,20 @@ +#!/bin/bash + +set -e +set -x + +sudo apt-get update + +sudo apt-get install python-pip +sudo apt-get install python-virtualenv +sudo apt-get install python-dev +sudo apt-get install libfreetype6-dev + + +virtualenv AILENV + +. ./AILENV/bin/activate + +pip install -r requirements.txt --upgrade + +python -m textblob.download_corpora \ No newline at end of file diff --git a/pip_packages_requirement.txt b/pip_packages_requirement.txt new file mode 100644 index 00000000..50ab481d --- /dev/null +++ b/pip_packages_requirement.txt @@ -0,0 +1,26 @@ +#Essential +redis +pyzmq +dnspython + +#Graph +numpy +matplotlib +networkx + +#Tokeniser +-U textblob +nltk + +# Hashlib +crcmod +mmh3 + +#Others +python-magic + + +#optionnal +ipython +flask +texttable \ No newline at end of file diff --git a/var/www/Flask_server.py b/var/www/Flask_server.py new file mode 100755 index 00000000..e363c609 --- /dev/null +++ b/var/www/Flask_server.py @@ -0,0 +1,66 @@ +#!/usr/bin/env python2 +# -*-coding:UTF-8 -* + +import redis, ConfigParser, json +from datetime import date, datetime, time +from flask import Flask, request, render_template, jsonify +import flask + +# CONFIG # +cfg = ConfigParser.ConfigParser() +cfg.read('../../bin/packages/config.cfg') + +# REDIS # +r_serv = redis.StrictRedis( + host = cfg.get("Redis_Queues", "host"), + port = cfg.getint("Redis_Queues", "port"), + db = cfg.getint("Redis_Queues", "db")) + +r_serv_log = redis.StrictRedis( + host = cfg.get("Redis_Log", "host"), + port = cfg.getint("Redis_Log", "port"), + db = cfg.getint("Redis_Log", "db")) + + +app = Flask(__name__, static_url_path='/static/') + +def event_stream(): + pubsub = r_serv_log.pubsub() + pubsub.psubscribe("Script" + '.*') + for msg in pubsub.listen(): + level = msg['channel'].split('.')[1] + if msg['type'] == 'pmessage' and level != "DEBUG": + yield 'data: %s\n\n' % json.dumps(msg) + +@app.route("/_logs") +def logs(): + return flask.Response(event_stream(), mimetype="text/event-stream") + + +@app.route("/_stuff", methods = ['GET']) +def stuff(): + row1 = [] + for queue in r_serv.smembers("queues"): + row1.append((queue, r_serv.llen(queue))) + return jsonify(row1=row1) + +@app.route("/") +def index(): + row = [] + for queue in r_serv.smembers("queues"): + row.append((queue, r_serv.llen(queue))) + + return render_template("index.html", queues_name = row) + +@app.route("/monitoring/") +def monitoring(): + for queue in r_serv.smembers("queues"): + return render_template("Queue_live_Monitoring.html",last_value = queue) + +@app.route("/wordstrending/") +def wordstrending(): + return render_template("Wordstrending.html") + + +if __name__ == "__main__": + app.run(host='172.16.100.123' ,port=7000, threaded=True) diff --git a/var/www/static/css/dygraph_gallery.css b/var/www/static/css/dygraph_gallery.css new file mode 100644 index 00000000..55793d76 --- /dev/null +++ b/var/www/static/css/dygraph_gallery.css @@ -0,0 +1,6 @@ +#WordTrending .dygraph-legend > span { display: none; } +#WordTrending .dygraph-legend > span.highlight { display: inline; } + +.dygraph-title { font-size: 42px; text-shadow: 2px 2px 2px gray; } + +.dygraph-label { font-size: 18px; text-shadow: -2px 2px 2px gray; } diff --git a/var/www/static/csv/.keepdir b/var/www/static/csv/.keepdir new file mode 100644 index 00000000..e69de29b diff --git a/var/www/static/js/indexjavascript.js b/var/www/static/js/indexjavascript.js new file mode 100644 index 00000000..eef01bbb --- /dev/null +++ b/var/www/static/js/indexjavascript.js @@ -0,0 +1,175 @@ +function initfunc( csvay, scroot) { + window.csv = csvay; + window.scroot = scroot; +}; + +function update_values() { + //$SCRIPT_ROOT = {{request.script_root|tojson|safe}} ; + $SCRIPT_ROOT = window.scroot ; + $.getJSON($SCRIPT_ROOT+"/_stuff", + function(data) { + window.glob_tabvar = data; + }); + }; + +var source = new EventSource('/_logs'); + +source.onmessage = function(event) { + var feed = jQuery.parseJSON( event.data ); + create_log_table(feed); +}; + +function create_log_table(obj_json) { + tableBody = document.getElementById("tab_body") + var tr = document.createElement('TR') + var chan = document.createElement('TD') + var level = document.createElement('TD') + var scrpt = document.createElement('TD') + var src = document.createElement('TD') + var pdate = document.createElement('TD') + var nam = document.createElement('TD') + var msage = document.createElement('TD') + + var chansplit = obj_json.channel.split('.'); + var parsedmess = obj_json.data.split(';'); + + if( chansplit[1] == "INFO" ){ + tr.className = "info"; + } + else if ( chansplit[1] == "WARNING" ){ + tr.className = "warning"; + } + + source_link = document.createElement("A"); + if (parsedmess[1] == "slexy.org"){ + soruce_url = "http://"+parsedmess[1]+"/view/"+parsedmess[3].split(".")[0]; + } + else{ + source_url = "http://"+parsedmess[1]+"/"+parsedmess[3].split(".")[0]; + } + source_link.setAttribute("HREF",source_url); + source_link.setAttribute("TARGET", "_blank") + source_link.appendChild(document.createTextNode(parsedmess[1])); + + src.appendChild(source_link); + + chan.appendChild(document.createTextNode(chansplit[0])); + level.appendChild(document.createTextNode(chansplit[1])); + + scrpt.appendChild(document.createTextNode(parsedmess[0])); + //src.appendChild(document.createTextNode(parsedmess[1])); + pdate.appendChild(document.createTextNode(parsedmess[2])); + nam.appendChild(document.createTextNode(parsedmess[3])); + msage.appendChild(document.createTextNode(parsedmess[4])); + + tr.appendChild(chan); + tr.appendChild(level); + tr.appendChild(scrpt); + tr.appendChild(src); + tr.appendChild(pdate); + tr.appendChild(nam); + tr.appendChild(msage); + + var sel = document.getElementById("log_select") + tableBody.appendChild(tr); + if (tableBody.rows.length > sel.options[sel.options.selectedIndex].value){ + while (tableBody.rows.length != sel.options[sel.options.selectedIndex].value){ + tableBody.deleteRow(0); + } + } +} + +$(document).ready(function () { + var interval = 1000; //number of mili seconds between each call + var refresh = function() { + $.ajax({ + url: "", + cache: false, + success: function(html) { + $('#server-name').html(html); + setTimeout(function() { + refresh(); + update_values(); + create_queue_table(); + }, interval); + } + }); + }; + refresh(); +}); + +function create_queue_table() { + document.getElementById("queueing").innerHTML = ""; + var Tablediv = document.getElementById("queueing") + var table = document.createElement('TABLE') + table.className = "table table-bordered table-hover table-striped"; + var tableHead = document.createElement('THEAD') + var tableBody = document.createElement('TBODY') + + table.appendChild(tableHead); + table.appendChild(tableBody); + var heading = new Array(); + heading[0] = "Queue Name" + heading[1] = "Amount" + var tr = document.createElement('TR'); + tableHead.appendChild(tr); + + for (i = 0; i < heading.length; i++) { + var th = document.createElement('TH') + th.width = '100'; + th.appendChild(document.createTextNode(heading[i])); + tr.appendChild(th); + } + + for(i = 0; i < (glob_tabvar.row1).length;i++){ + var tr = document.createElement('TR') + for(j = 0; j < (glob_tabvar.row1[i]).length; j++){ + var td = document.createElement('TD') + td.appendChild(document.createTextNode(glob_tabvar.row1[i][j])); + tr.appendChild(td) + } + tableBody.appendChild(tr); + } + Tablediv.appendChild(table); +} + +$(document).ready(function () { + var data = []; + var x = new Date(); + data.push([x, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]); + + var g = new Dygraph(document.getElementById("Graph"), data, + { + labels: ["Time", "Duplicate", "CreditCard", "Words", "102", "Mails", "Lines", "Curve", "Onion", "Web", "Tokenize"], + drawPoints: false, + showRoller: true, + rollPeriod: 10, + labelsKMB: true, + logscale: true, + connectSeparatedPoints: true, + fillGraph: true, + stepPlot: true, + includeZero: true, + }); + + // It sucks that these things aren't objects, and we need to store state in window. + window.intervalId = setInterval(function() { + var x = new Date(); // current time + y = glob_tabvar.row1[0][1]; + a = glob_tabvar.row1[1][1]; + b = glob_tabvar.row1[2][1]; + c = glob_tabvar.row1[3][1]; + d = glob_tabvar.row1[4][1]; + e = glob_tabvar.row1[5][1]; + f = glob_tabvar.row1[6][1]; + k = glob_tabvar.row1[7][1]; + h = glob_tabvar.row1[8][1]; + i = glob_tabvar.row1[9][1]; + + data.push([x, y, a, b, c, d, e, f, k, h, i]); + if (data.length > 1800) { + data.shift(); + } + g.updateOptions( { 'file': data } ); + }, 1000); +}); diff --git a/var/www/templates/Queue_live_Monitoring.html b/var/www/templates/Queue_live_Monitoring.html new file mode 100644 index 00000000..b8e5791e --- /dev/null +++ b/var/www/templates/Queue_live_Monitoring.html @@ -0,0 +1,43 @@ + + + + + + +WordsTrend + + + +
+ + + \ No newline at end of file diff --git a/var/www/templates/Wordstrending.html b/var/www/templates/Wordstrending.html new file mode 100644 index 00000000..3b8662d2 --- /dev/null +++ b/var/www/templates/Wordstrending.html @@ -0,0 +1,209 @@ + + + + + + + + Analysis Information Leak framework Dashboard + + + + + + + + + + + + + + +
+ +
+
+
+

Wordtrending

+
+ +
+ +
+
+
+
+ Words Trend +
+
+ + +
+
+
+ +
+ +
+
+ +
+
+ +
+ + +
+ + + + diff --git a/var/www/templates/index.html b/var/www/templates/index.html new file mode 100644 index 00000000..a363255b --- /dev/null +++ b/var/www/templates/index.html @@ -0,0 +1,147 @@ + + + + + + + + Analysis Information Leak framework Dashboard + + + + + + + + + + + + + + +
+ +
+
+
+

Dashboard

+
+ +
+ +
+
+
+
+ Queues Monitor +
+
+
+
+
+
+
+
+ +
+ +
+ +
+ +
+
+
+ Logs +
+
+
+
+
+
+ +
+
+
+ + + + + + + + + + + + + + +
ChannelLevelScript NameSourceDatePaste nameMessage
+ + + + + + + + + + + + + + + + + + + + diff --git a/var/www/update_thirdparty.sh b/var/www/update_thirdparty.sh new file mode 100755 index 00000000..66897e7b --- /dev/null +++ b/var/www/update_thirdparty.sh @@ -0,0 +1,36 @@ +#!/bin/bash + +set -e + +wget http://dygraphs.com/dygraph-combined.js -O ./static/js/dygraph-combined.js + +SBADMIN_VERSION=2 +filename="sb-admin-${SBADMIN_VERSION}" + +rm -rf temp +mkdir temp + +wget http://startbootstrap.com/downloads/${filename}".zip" -O temp/${filename}".zip" + +unzip temp/${filename}".zip" -d temp/ + +JQVERSION="1.11.1" +wget http://code.jquery.com/jquery-${JQVERSION}.js -O ./static/js/jquery.js + +wget https://collabdev.googlecode.com/svn-history/r5/trunk/static/js/jquery.timers-1.0.0.js -O ./static/js/jquery.timers-1.0.0.js + +#Here to fix an error about an hard dependency in a obscur script of bootstrap.. +wget http://code.jquery.com/jquery-1.4.2.js -O ./static/js/jquery-1.4.2.js + +rm -rf ./static/js/plugins +mv temp/${filename}/js/* ./static/js/ + +rm -rf ./static/fonts/ ./static/font-awesome-4.1.0/ + +mv temp/${filename}/fonts/ ./static/ +mv temp/${filename}/font-awesome-4.1.0/ ./static/ + +rm -rf ./static/css/plugins/ +mv temp/${filename}/css/* ./static/css/ + +rm -rf temp/