Skip to content

HTTPS clone URL

Subversion checkout URL

You can clone with
or
.
Download ZIP
Browse files

Initial import of GPL version of dedupe project

  • Loading branch information...
commit e2a8c4c9c12407c3204ffc22386b7a10837762cb 0 parents
Graham Poulter authored
674 LICENSE
@@ -0,0 +1,674 @@
+ GNU GENERAL PUBLIC LICENSE
+ Version 3, 29 June 2007
+
+ Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
+ Everyone is permitted to copy and distribute verbatim copies
+ of this license document, but changing it is not allowed.
+
+ Preamble
+
+ The GNU General Public License is a free, copyleft license for
+software and other kinds of works.
+
+ The licenses for most software and other practical works are designed
+to take away your freedom to share and change the works. By contrast,
+the GNU General Public License is intended to guarantee your freedom to
+share and change all versions of a program--to make sure it remains free
+software for all its users. We, the Free Software Foundation, use the
+GNU General Public License for most of our software; it applies also to
+any other work released this way by its authors. You can apply it to
+your programs, too.
+
+ When we speak of free software, we are referring to freedom, not
+price. Our General Public Licenses are designed to make sure that you
+have the freedom to distribute copies of free software (and charge for
+them if you wish), that you receive source code or can get it if you
+want it, that you can change the software or use pieces of it in new
+free programs, and that you know you can do these things.
+
+ To protect your rights, we need to prevent others from denying you
+these rights or asking you to surrender the rights. Therefore, you have
+certain responsibilities if you distribute copies of the software, or if
+you modify it: responsibilities to respect the freedom of others.
+
+ For example, if you distribute copies of such a program, whether
+gratis or for a fee, you must pass on to the recipients the same
+freedoms that you received. You must make sure that they, too, receive
+or can get the source code. And you must show them these terms so they
+know their rights.
+
+ Developers that use the GNU GPL protect your rights with two steps:
+(1) assert copyright on the software, and (2) offer you this License
+giving you legal permission to copy, distribute and/or modify it.
+
+ For the developers' and authors' protection, the GPL clearly explains
+that there is no warranty for this free software. For both users' and
+authors' sake, the GPL requires that modified versions be marked as
+changed, so that their problems will not be attributed erroneously to
+authors of previous versions.
+
+ Some devices are designed to deny users access to install or run
+modified versions of the software inside them, although the manufacturer
+can do so. This is fundamentally incompatible with the aim of
+protecting users' freedom to change the software. The systematic
+pattern of such abuse occurs in the area of products for individuals to
+use, which is precisely where it is most unacceptable. Therefore, we
+have designed this version of the GPL to prohibit the practice for those
+products. If such problems arise substantially in other domains, we
+stand ready to extend this provision to those domains in future versions
+of the GPL, as needed to protect the freedom of users.
+
+ Finally, every program is threatened constantly by software patents.
+States should not allow patents to restrict development and use of
+software on general-purpose computers, but in those that do, we wish to
+avoid the special danger that patents applied to a free program could
+make it effectively proprietary. To prevent this, the GPL assures that
+patents cannot be used to render the program non-free.
+
+ The precise terms and conditions for copying, distribution and
+modification follow.
+
+ TERMS AND CONDITIONS
+
+ 0. Definitions.
+
+ "This License" refers to version 3 of the GNU General Public License.
+
+ "Copyright" also means copyright-like laws that apply to other kinds of
+works, such as semiconductor masks.
+
+ "The Program" refers to any copyrightable work licensed under this
+License. Each licensee is addressed as "you". "Licensees" and
+"recipients" may be individuals or organizations.
+
+ To "modify" a work means to copy from or adapt all or part of the work
+in a fashion requiring copyright permission, other than the making of an
+exact copy. The resulting work is called a "modified version" of the
+earlier work or a work "based on" the earlier work.
+
+ A "covered work" means either the unmodified Program or a work based
+on the Program.
+
+ To "propagate" a work means to do anything with it that, without
+permission, would make you directly or secondarily liable for
+infringement under applicable copyright law, except executing it on a
+computer or modifying a private copy. Propagation includes copying,
+distribution (with or without modification), making available to the
+public, and in some countries other activities as well.
+
+ To "convey" a work means any kind of propagation that enables other
+parties to make or receive copies. Mere interaction with a user through
+a computer network, with no transfer of a copy, is not conveying.
+
+ An interactive user interface displays "Appropriate Legal Notices"
+to the extent that it includes a convenient and prominently visible
+feature that (1) displays an appropriate copyright notice, and (2)
+tells the user that there is no warranty for the work (except to the
+extent that warranties are provided), that licensees may convey the
+work under this License, and how to view a copy of this License. If
+the interface presents a list of user commands or options, such as a
+menu, a prominent item in the list meets this criterion.
+
+ 1. Source Code.
+
+ The "source code" for a work means the preferred form of the work
+for making modifications to it. "Object code" means any non-source
+form of a work.
+
+ A "Standard Interface" means an interface that either is an official
+standard defined by a recognized standards body, or, in the case of
+interfaces specified for a particular programming language, one that
+is widely used among developers working in that language.
+
+ The "System Libraries" of an executable work include anything, other
+than the work as a whole, that (a) is included in the normal form of
+packaging a Major Component, but which is not part of that Major
+Component, and (b) serves only to enable use of the work with that
+Major Component, or to implement a Standard Interface for which an
+implementation is available to the public in source code form. A
+"Major Component", in this context, means a major essential component
+(kernel, window system, and so on) of the specific operating system
+(if any) on which the executable work runs, or a compiler used to
+produce the work, or an object code interpreter used to run it.
+
+ The "Corresponding Source" for a work in object code form means all
+the source code needed to generate, install, and (for an executable
+work) run the object code and to modify the work, including scripts to
+control those activities. However, it does not include the work's
+System Libraries, or general-purpose tools or generally available free
+programs which are used unmodified in performing those activities but
+which are not part of the work. For example, Corresponding Source
+includes interface definition files associated with source files for
+the work, and the source code for shared libraries and dynamically
+linked subprograms that the work is specifically designed to require,
+such as by intimate data communication or control flow between those
+subprograms and other parts of the work.
+
+ The Corresponding Source need not include anything that users
+can regenerate automatically from other parts of the Corresponding
+Source.
+
+ The Corresponding Source for a work in source code form is that
+same work.
+
+ 2. Basic Permissions.
+
+ All rights granted under this License are granted for the term of
+copyright on the Program, and are irrevocable provided the stated
+conditions are met. This License explicitly affirms your unlimited
+permission to run the unmodified Program. The output from running a
+covered work is covered by this License only if the output, given its
+content, constitutes a covered work. This License acknowledges your
+rights of fair use or other equivalent, as provided by copyright law.
+
+ You may make, run and propagate covered works that you do not
+convey, without conditions so long as your license otherwise remains
+in force. You may convey covered works to others for the sole purpose
+of having them make modifications exclusively for you, or provide you
+with facilities for running those works, provided that you comply with
+the terms of this License in conveying all material for which you do
+not control copyright. Those thus making or running the covered works
+for you must do so exclusively on your behalf, under your direction
+and control, on terms that prohibit them from making any copies of
+your copyrighted material outside their relationship with you.
+
+ Conveying under any other circumstances is permitted solely under
+the conditions stated below. Sublicensing is not allowed; section 10
+makes it unnecessary.
+
+ 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
+
+ No covered work shall be deemed part of an effective technological
+measure under any applicable law fulfilling obligations under article
+11 of the WIPO copyright treaty adopted on 20 December 1996, or
+similar laws prohibiting or restricting circumvention of such
+measures.
+
+ When you convey a covered work, you waive any legal power to forbid
+circumvention of technological measures to the extent such circumvention
+is effected by exercising rights under this License with respect to
+the covered work, and you disclaim any intention to limit operation or
+modification of the work as a means of enforcing, against the work's
+users, your or third parties' legal rights to forbid circumvention of
+technological measures.
+
+ 4. Conveying Verbatim Copies.
+
+ You may convey verbatim copies of the Program's source code as you
+receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice;
+keep intact all notices stating that this License and any
+non-permissive terms added in accord with section 7 apply to the code;
+keep intact all notices of the absence of any warranty; and give all
+recipients a copy of this License along with the Program.
+
+ You may charge any price or no price for each copy that you convey,
+and you may offer support or warranty protection for a fee.
+
+ 5. Conveying Modified Source Versions.
+
+ You may convey a work based on the Program, or the modifications to
+produce it from the Program, in the form of source code under the
+terms of section 4, provided that you also meet all of these conditions:
+
+ a) The work must carry prominent notices stating that you modified
+ it, and giving a relevant date.
+
+ b) The work must carry prominent notices stating that it is
+ released under this License and any conditions added under section
+ 7. This requirement modifies the requirement in section 4 to
+ "keep intact all notices".
+
+ c) You must license the entire work, as a whole, under this
+ License to anyone who comes into possession of a copy. This
+ License will therefore apply, along with any applicable section 7
+ additional terms, to the whole of the work, and all its parts,
+ regardless of how they are packaged. This License gives no
+ permission to license the work in any other way, but it does not
+ invalidate such permission if you have separately received it.
+
+ d) If the work has interactive user interfaces, each must display
+ Appropriate Legal Notices; however, if the Program has interactive
+ interfaces that do not display Appropriate Legal Notices, your
+ work need not make them do so.
+
+ A compilation of a covered work with other separate and independent
+works, which are not by their nature extensions of the covered work,
+and which are not combined with it such as to form a larger program,
+in or on a volume of a storage or distribution medium, is called an
+"aggregate" if the compilation and its resulting copyright are not
+used to limit the access or legal rights of the compilation's users
+beyond what the individual works permit. Inclusion of a covered work
+in an aggregate does not cause this License to apply to the other
+parts of the aggregate.
+
+ 6. Conveying Non-Source Forms.
+
+ You may convey a covered work in object code form under the terms
+of sections 4 and 5, provided that you also convey the
+machine-readable Corresponding Source under the terms of this License,
+in one of these ways:
+
+ a) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by the
+ Corresponding Source fixed on a durable physical medium
+ customarily used for software interchange.
+
+ b) Convey the object code in, or embodied in, a physical product
+ (including a physical distribution medium), accompanied by a
+ written offer, valid for at least three years and valid for as
+ long as you offer spare parts or customer support for that product
+ model, to give anyone who possesses the object code either (1) a
+ copy of the Corresponding Source for all the software in the
+ product that is covered by this License, on a durable physical
+ medium customarily used for software interchange, for a price no
+ more than your reasonable cost of physically performing this
+ conveying of source, or (2) access to copy the
+ Corresponding Source from a network server at no charge.
+
+ c) Convey individual copies of the object code with a copy of the
+ written offer to provide the Corresponding Source. This
+ alternative is allowed only occasionally and noncommercially, and
+ only if you received the object code with such an offer, in accord
+ with subsection 6b.
+
+ d) Convey the object code by offering access from a designated
+ place (gratis or for a charge), and offer equivalent access to the
+ Corresponding Source in the same way through the same place at no
+ further charge. You need not require recipients to copy the
+ Corresponding Source along with the object code. If the place to
+ copy the object code is a network server, the Corresponding Source
+ may be on a different server (operated by you or a third party)
+ that supports equivalent copying facilities, provided you maintain
+ clear directions next to the object code saying where to find the
+ Corresponding Source. Regardless of what server hosts the
+ Corresponding Source, you remain obligated to ensure that it is
+ available for as long as needed to satisfy these requirements.
+
+ e) Convey the object code using peer-to-peer transmission, provided
+ you inform other peers where the object code and Corresponding
+ Source of the work are being offered to the general public at no
+ charge under subsection 6d.
+
+ A separable portion of the object code, whose source code is excluded
+from the Corresponding Source as a System Library, need not be
+included in conveying the object code work.
+
+ A "User Product" is either (1) a "consumer product", which means any
+tangible personal property which is normally used for personal, family,
+or household purposes, or (2) anything designed or sold for incorporation
+into a dwelling. In determining whether a product is a consumer product,
+doubtful cases shall be resolved in favor of coverage. For a particular
+product received by a particular user, "normally used" refers to a
+typical or common use of that class of product, regardless of the status
+of the particular user or of the way in which the particular user
+actually uses, or expects or is expected to use, the product. A product
+is a consumer product regardless of whether the product has substantial
+commercial, industrial or non-consumer uses, unless such uses represent
+the only significant mode of use of the product.
+
+ "Installation Information" for a User Product means any methods,
+procedures, authorization keys, or other information required to install
+and execute modified versions of a covered work in that User Product from
+a modified version of its Corresponding Source. The information must
+suffice to ensure that the continued functioning of the modified object
+code is in no case prevented or interfered with solely because
+modification has been made.
+
+ If you convey an object code work under this section in, or with, or
+specifically for use in, a User Product, and the conveying occurs as
+part of a transaction in which the right of possession and use of the
+User Product is transferred to the recipient in perpetuity or for a
+fixed term (regardless of how the transaction is characterized), the
+Corresponding Source conveyed under this section must be accompanied
+by the Installation Information. But this requirement does not apply
+if neither you nor any third party retains the ability to install
+modified object code on the User Product (for example, the work has
+been installed in ROM).
+
+ The requirement to provide Installation Information does not include a
+requirement to continue to provide support service, warranty, or updates
+for a work that has been modified or installed by the recipient, or for
+the User Product in which it has been modified or installed. Access to a
+network may be denied when the modification itself materially and
+adversely affects the operation of the network or violates the rules and
+protocols for communication across the network.
+
+ Corresponding Source conveyed, and Installation Information provided,
+in accord with this section must be in a format that is publicly
+documented (and with an implementation available to the public in
+source code form), and must require no special password or key for
+unpacking, reading or copying.
+
+ 7. Additional Terms.
+
+ "Additional permissions" are terms that supplement the terms of this
+License by making exceptions from one or more of its conditions.
+Additional permissions that are applicable to the entire Program shall
+be treated as though they were included in this License, to the extent
+that they are valid under applicable law. If additional permissions
+apply only to part of the Program, that part may be used separately
+under those permissions, but the entire Program remains governed by
+this License without regard to the additional permissions.
+
+ When you convey a copy of a covered work, you may at your option
+remove any additional permissions from that copy, or from any part of
+it. (Additional permissions may be written to require their own
+removal in certain cases when you modify the work.) You may place
+additional permissions on material, added by you to a covered work,
+for which you have or can give appropriate copyright permission.
+
+ Notwithstanding any other provision of this License, for material you
+add to a covered work, you may (if authorized by the copyright holders of
+that material) supplement the terms of this License with terms:
+
+ a) Disclaiming warranty or limiting liability differently from the
+ terms of sections 15 and 16 of this License; or
+
+ b) Requiring preservation of specified reasonable legal notices or
+ author attributions in that material or in the Appropriate Legal
+ Notices displayed by works containing it; or
+
+ c) Prohibiting misrepresentation of the origin of that material, or
+ requiring that modified versions of such material be marked in
+ reasonable ways as different from the original version; or
+
+ d) Limiting the use for publicity purposes of names of licensors or
+ authors of the material; or
+
+ e) Declining to grant rights under trademark law for use of some
+ trade names, trademarks, or service marks; or
+
+ f) Requiring indemnification of licensors and authors of that
+ material by anyone who conveys the material (or modified versions of
+ it) with contractual assumptions of liability to the recipient, for
+ any liability that these contractual assumptions directly impose on
+ those licensors and authors.
+
+ All other non-permissive additional terms are considered "further
+restrictions" within the meaning of section 10. If the Program as you
+received it, or any part of it, contains a notice stating that it is
+governed by this License along with a term that is a further
+restriction, you may remove that term. If a license document contains
+a further restriction but permits relicensing or conveying under this
+License, you may add to a covered work material governed by the terms
+of that license document, provided that the further restriction does
+not survive such relicensing or conveying.
+
+ If you add terms to a covered work in accord with this section, you
+must place, in the relevant source files, a statement of the
+additional terms that apply to those files, or a notice indicating
+where to find the applicable terms.
+
+ Additional terms, permissive or non-permissive, may be stated in the
+form of a separately written license, or stated as exceptions;
+the above requirements apply either way.
+
+ 8. Termination.
+
+ You may not propagate or modify a covered work except as expressly
+provided under this License. Any attempt otherwise to propagate or
+modify it is void, and will automatically terminate your rights under
+this License (including any patent licenses granted under the third
+paragraph of section 11).
+
+ However, if you cease all violation of this License, then your
+license from a particular copyright holder is reinstated (a)
+provisionally, unless and until the copyright holder explicitly and
+finally terminates your license, and (b) permanently, if the copyright
+holder fails to notify you of the violation by some reasonable means
+prior to 60 days after the cessation.
+
+ Moreover, your license from a particular copyright holder is
+reinstated permanently if the copyright holder notifies you of the
+violation by some reasonable means, this is the first time you have
+received notice of violation of this License (for any work) from that
+copyright holder, and you cure the violation prior to 30 days after
+your receipt of the notice.
+
+ Termination of your rights under this section does not terminate the
+licenses of parties who have received copies or rights from you under
+this License. If your rights have been terminated and not permanently
+reinstated, you do not qualify to receive new licenses for the same
+material under section 10.
+
+ 9. Acceptance Not Required for Having Copies.
+
+ You are not required to accept this License in order to receive or
+run a copy of the Program. Ancillary propagation of a covered work
+occurring solely as a consequence of using peer-to-peer transmission
+to receive a copy likewise does not require acceptance. However,
+nothing other than this License grants you permission to propagate or
+modify any covered work. These actions infringe copyright if you do
+not accept this License. Therefore, by modifying or propagating a
+covered work, you indicate your acceptance of this License to do so.
+
+ 10. Automatic Licensing of Downstream Recipients.
+
+ Each time you convey a covered work, the recipient automatically
+receives a license from the original licensors, to run, modify and
+propagate that work, subject to this License. You are not responsible
+for enforcing compliance by third parties with this License.
+
+ An "entity transaction" is a transaction transferring control of an
+organization, or substantially all assets of one, or subdividing an
+organization, or merging organizations. If propagation of a covered
+work results from an entity transaction, each party to that
+transaction who receives a copy of the work also receives whatever
+licenses to the work the party's predecessor in interest had or could
+give under the previous paragraph, plus a right to possession of the
+Corresponding Source of the work from the predecessor in interest, if
+the predecessor has it or can get it with reasonable efforts.
+
+ You may not impose any further restrictions on the exercise of the
+rights granted or affirmed under this License. For example, you may
+not impose a license fee, royalty, or other charge for exercise of
+rights granted under this License, and you may not initiate litigation
+(including a cross-claim or counterclaim in a lawsuit) alleging that
+any patent claim is infringed by making, using, selling, offering for
+sale, or importing the Program or any portion of it.
+
+ 11. Patents.
+
+ A "contributor" is a copyright holder who authorizes use under this
+License of the Program or a work on which the Program is based. The
+work thus licensed is called the contributor's "contributor version".
+
+ A contributor's "essential patent claims" are all patent claims
+owned or controlled by the contributor, whether already acquired or
+hereafter acquired, that would be infringed by some manner, permitted
+by this License, of making, using, or selling its contributor version,
+but do not include claims that would be infringed only as a
+consequence of further modification of the contributor version. For
+purposes of this definition, "control" includes the right to grant
+patent sublicenses in a manner consistent with the requirements of
+this License.
+
+ Each contributor grants you a non-exclusive, worldwide, royalty-free
+patent license under the contributor's essential patent claims, to
+make, use, sell, offer for sale, import and otherwise run, modify and
+propagate the contents of its contributor version.
+
+ In the following three paragraphs, a "patent license" is any express
+agreement or commitment, however denominated, not to enforce a patent
+(such as an express permission to practice a patent or covenant not to
+sue for patent infringement). To "grant" such a patent license to a
+party means to make such an agreement or commitment not to enforce a
+patent against the party.
+
+ If you convey a covered work, knowingly relying on a patent license,
+and the Corresponding Source of the work is not available for anyone
+to copy, free of charge and under the terms of this License, through a
+publicly available network server or other readily accessible means,
+then you must either (1) cause the Corresponding Source to be so
+available, or (2) arrange to deprive yourself of the benefit of the
+patent license for this particular work, or (3) arrange, in a manner
+consistent with the requirements of this License, to extend the patent
+license to downstream recipients. "Knowingly relying" means you have
+actual knowledge that, but for the patent license, your conveying the
+covered work in a country, or your recipient's use of the covered work
+in a country, would infringe one or more identifiable patents in that
+country that you have reason to believe are valid.
+
+ If, pursuant to or in connection with a single transaction or
+arrangement, you convey, or propagate by procuring conveyance of, a
+covered work, and grant a patent license to some of the parties
+receiving the covered work authorizing them to use, propagate, modify
+or convey a specific copy of the covered work, then the patent license
+you grant is automatically extended to all recipients of the covered
+work and works based on it.
+
+ A patent license is "discriminatory" if it does not include within
+the scope of its coverage, prohibits the exercise of, or is
+conditioned on the non-exercise of one or more of the rights that are
+specifically granted under this License. You may not convey a covered
+work if you are a party to an arrangement with a third party that is
+in the business of distributing software, under which you make payment
+to the third party based on the extent of your activity of conveying
+the work, and under which the third party grants, to any of the
+parties who would receive the covered work from you, a discriminatory
+patent license (a) in connection with copies of the covered work
+conveyed by you (or copies made from those copies), or (b) primarily
+for and in connection with specific products or compilations that
+contain the covered work, unless you entered into that arrangement,
+or that patent license was granted, prior to 28 March 2007.
+
+ Nothing in this License shall be construed as excluding or limiting
+any implied license or other defenses to infringement that may
+otherwise be available to you under applicable patent law.
+
+ 12. No Surrender of Others' Freedom.
+
+ If conditions are imposed on you (whether by court order, agreement or
+otherwise) that contradict the conditions of this License, they do not
+excuse you from the conditions of this License. If you cannot convey a
+covered work so as to satisfy simultaneously your obligations under this
+License and any other pertinent obligations, then as a consequence you may
+not convey it at all. For example, if you agree to terms that obligate you
+to collect a royalty for further conveying from those to whom you convey
+the Program, the only way you could satisfy both those terms and this
+License would be to refrain entirely from conveying the Program.
+
+ 13. Use with the GNU Affero General Public License.
+
+ Notwithstanding any other provision of this License, you have
+permission to link or combine any covered work with a work licensed
+under version 3 of the GNU Affero General Public License into a single
+combined work, and to convey the resulting work. The terms of this
+License will continue to apply to the part which is the covered work,
+but the special requirements of the GNU Affero General Public License,
+section 13, concerning interaction through a network will apply to the
+combination as such.
+
+ 14. Revised Versions of this License.
+
+ The Free Software Foundation may publish revised and/or new versions of
+the GNU General Public License from time to time. Such new versions will
+be similar in spirit to the present version, but may differ in detail to
+address new problems or concerns.
+
+ Each version is given a distinguishing version number. If the
+Program specifies that a certain numbered version of the GNU General
+Public License "or any later version" applies to it, you have the
+option of following the terms and conditions either of that numbered
+version or of any later version published by the Free Software
+Foundation. If the Program does not specify a version number of the
+GNU General Public License, you may choose any version ever published
+by the Free Software Foundation.
+
+ If the Program specifies that a proxy can decide which future
+versions of the GNU General Public License can be used, that proxy's
+public statement of acceptance of a version permanently authorizes you
+to choose that version for the Program.
+
+ Later license versions may give you additional or different
+permissions. However, no additional obligations are imposed on any
+author or copyright holder as a result of your choosing to follow a
+later version.
+
+ 15. Disclaimer of Warranty.
+
+ THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
+APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
+HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
+OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
+THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
+IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+ 16. Limitation of Liability.
+
+ IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
+WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
+THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
+USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
+DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
+PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
+EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
+SUCH DAMAGES.
+
+ 17. Interpretation of Sections 15 and 16.
+
+ If the disclaimer of warranty and limitation of liability provided
+above cannot be given local legal effect according to their terms,
+reviewing courts shall apply local law that most closely approximates
+an absolute waiver of all civil liability in connection with the
+Program, unless a warranty or assumption of liability accompanies a
+copy of the Program in return for a fee.
+
+ END OF TERMS AND CONDITIONS
+
+ How to Apply These Terms to Your New Programs
+
+ If you develop a new program, and you want it to be of the greatest
+possible use to the public, the best way to achieve this is to make it
+free software which everyone can redistribute and change under these terms.
+
+ To do so, attach the following notices to the program. It is safest
+to attach them to the start of each source file to most effectively
+state the exclusion of warranty; and each file should have at least
+the "copyright" line and a pointer to where the full notice is found.
+
+ <one line to give the program's name and a brief idea of what it does.>
+ Copyright (C) <year> <name of author>
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>.
+
+Also add information on how to contact you by electronic and paper mail.
+
+ If the program does terminal interaction, make it output a short
+notice like this when it starts in an interactive mode:
+
+ <program> Copyright (C) <year> <name of author>
+ This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
+ This is free software, and you are welcome to redistribute it
+ under certain conditions; type `show c' for details.
+
+The hypothetical commands `show w' and `show c' should show the appropriate
+parts of the General Public License. Of course, your program's commands
+might be different; for a GUI interface, you would use an "about box".
+
+ You should also get your employer (if you work as a programmer) or school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.
+For more information on this, and how to apply and follow the GNU GPL, see
+<http://www.gnu.org/licenses/>.
+
+ The GNU General Public License does not permit incorporating your program
+into proprietary programs. If your program is a subroutine library, you
+may consider it more useful to permit linking proprietary applications with
+the library. If this is what you want to do, use the GNU Lesser General
+Public License instead of this License. But first, please read
+<http://www.gnu.org/philosophy/why-not-lgpl.html>.
21 dedupe/__init__.py
@@ -0,0 +1,21 @@
+"""
+Dedupe - Detect similar groups of records within a table of records,
+or match pairs of records across two different tables.
+
+@author: Graham Poulter
+@copyright: MIH Holdings
+@license: GPL
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>.
+"""
79 dedupe/classification.py
@@ -0,0 +1,79 @@
+"""Classification algorithms. The K-Means depends on FEBRL and the
+classifiers work on the comparisons object produced by L{indexer.Indeces}
+class.
+
+Each comparison is a vector of similarity values, each in the 0.0 to 1.0 range,
+being the field-by-field similarity of a pair of records.
+
+@author: Graham Poulter
+@copyright: MIH Holdings
+@license: GPL
+"""
+
+from febrl.classification import KMeans
+import math
+
+def distL2(vec1, vec2):
+ """L2 distance , also known as Euclidean distance.
+ @note: Python implementation to avoid a numpy dependency for now.
+ """
+ #assert len(vec1) == len(vec2)
+ return math.sqrt(sum((float(a)-float(b))**2 for a,b in zip(vec1, vec2)))
+
+
+def dist_norm_L2(vec1, vec2, stdevs):
+ """Normalised L2 distance, being the Mahalanobis distance with a
+ diagonal covariance matrix.
+
+ @param stdevs: Standard deviations for vector components
+ (higher variance gives less weight to that component).
+ """
+ #assert len(vec1) == len(vec2) == len(stdevs)
+ return math.sqrt(sum(((a-b)/s)**2 for a,b,s in zip(vec1, vec2, stdevs)))
+
+
+def classify_kmeans(comparisons, distance=distL2):
+ """Classify each pair of comparisons as match or nonmatch, by clustering
+ weight vectors around "match centroind" and "nonmatch centroid"
+
+ @param comparisons: mapping (rec1,rec2):weights from record pair to
+ field-by-field comparison vector.
+
+ @param distance: Vector distance function.
+
+ @return: set of matched pairs of records, set of non-matched pairs of records.
+ """
+ if not comparisons: # Nothing to classify
+ return {}, []
+ kmeans = KMeans(dist_measure = distance,
+ max_iter_count = 50,
+ centroid_init = "min/max",
+ sample = 100.0)
+ kmeans.train(comparisons, None, None) # Identify the centroids
+ [match, nomatch, probablematch] = kmeans.classify(comparisons)
+ return match, nomatch
+
+
+def classify_nearest(comparisons, examples, distance):
+ """Nearest-neighbour classification of comparisons vectors.
+
+ @param comparisons: Map (item1,item2):comparison
+
+ @param examples: List of (comparison, boolean) example pairs - True for
+ match and False for non-match.
+
+ @param distance: Function to compute distance between comparison vectors.
+
+ @return: set of matched record pair, set of non-matched record pairs.
+ """
+ match = set()
+ nomatch = set()
+ for pair, comparison in comparisons.iteritems():
+ min_dist, ismatch = min((distance(comparison, example), ismatch)
+ for example, ismatch in examples)
+ if ismatch:
+ match.add(pair)
+ else:
+ nomatch.add(pair)
+ return match, nomatch
+
47 dedupe/comparators.py
@@ -0,0 +1,47 @@
+"""Configured text comparison functions from FEBRL
+
+@author: Graham Poulter
+@copyright: MIH Holdings
+@license: GPL
+"""
+
+from febrl.comparison import (
+ FieldComparatorDaLeDist,
+ FieldComparatorSWDist,
+ FieldComparatorKeyDiff)
+
+dale5 = FieldComparatorDaLeDist(
+ agree_weight = 1.0,
+ disagree_weight = 0.0,
+ missing_values = [None,''],
+ missing_weight = 0.2,
+ threshold = 0.5).compare
+
+dale7 = FieldComparatorDaLeDist(
+ agree_weight = 1.0,
+ disagree_weight = 0.0,
+ missing_values = [None,''],
+ missing_weight = 0.2,
+ threshold = 0.7).compare
+
+dale5nomissing = FieldComparatorDaLeDist(
+ agree_weight = 1.0,
+ disagree_weight = 0.0,
+ missing_values = [None,''],
+ missing_weight = 0.0,
+ threshold = 0.5).compare
+
+sw5 = FieldComparatorSWDist(
+ common_divisor = 'average',
+ agree_weight = 1.0,
+ disagree_weight = 0.0,
+ missing_values = [None,''],
+ missing_weight = 0.2,
+ threshold = 0.5).compare
+
+keydiff = FieldComparatorKeyDiff(
+ max_key_diff = 3,
+ agree_weight = 1.0,
+ disagree_weight = 0.0,
+ missing_values = [None,''],
+ missing_weight = 0.2).compare
12 dedupe/compat/__init__.py
@@ -0,0 +1,12 @@
+"""Compatibility module for handy classes that may only available in newer
+versions of Python."""
+
+try:
+ from collections import namedtuple
+except ImportError:
+ from namedtuple import namedtuple
+
+try:
+ from collections import OrderedDict
+except ImportError:
+ from ordereddict import OrderedDict
137 dedupe/compat/namedtuple.py
@@ -0,0 +1,137 @@
+"""Creates subclasses of tuple with named fields.
+
+@note: Source code from http://code.activestate.com/recipes/500261/
+
+@author: Raymond Hettinger (2007)
+"""
+
+from operator import itemgetter as _itemgetter
+from keyword import iskeyword as _iskeyword
+import sys as _sys
+
+def namedtuple(typename, field_names, verbose=False):
+ """Returns a new subclass of tuple with named fields.
+
+ >>> Point = namedtuple('Point', 'x y')
+ >>> Point.__doc__ # docstring for the new class
+ 'Point(x, y)'
+ >>> p = Point(11, y=22) # instantiate with positional args or keywords
+ >>> p[0] + p[1] # indexable like a plain tuple
+ 33
+ >>> x, y = p # unpack like a regular tuple
+ >>> x, y
+ (11, 22)
+ >>> p.x + p.y # fields also accessable by name
+ 33
+ >>> d = p._asdict() # convert to a dictionary
+ >>> d['x']
+ 11
+ >>> Point(**d) # convert from a dictionary
+ Point(x=11, y=22)
+ >>> p._replace(x=100) # _replace() is like str.replace() but targets named fields
+ Point(x=100, y=22)
+
+ """
+
+ # Parse and validate the field names. Validation serves two purposes,
+ # generating informative error messages and preventing template injection attacks.
+ if isinstance(field_names, basestring):
+ field_names = field_names.replace(',', ' ').split() # names separated by whitespace and/or commas
+ field_names = tuple(map(str, field_names))
+ for name in (typename,) + field_names:
+ if not min(c.isalnum() or c=='_' for c in name):
+ raise ValueError('Type names and field names can only contain alphanumeric characters and underscores: %r' % name)
+ if _iskeyword(name):
+ raise ValueError('Type names and field names cannot be a keyword: %r' % name)
+ if name[0].isdigit():
+ raise ValueError('Type names and field names cannot start with a number: %r' % name)
+ seen_names = set()
+ for name in field_names:
+ if name.startswith('_'):
+ raise ValueError('Field names cannot start with an underscore: %r' % name)
+ if name in seen_names:
+ raise ValueError('Encountered duplicate field name: %r' % name)
+ seen_names.add(name)
+
+ # Create and fill-in the class template
+ numfields = len(field_names)
+ argtxt = repr(field_names).replace("'", "")[1:-1] # tuple repr without parens or quotes
+ reprtxt = ', '.join('%s=%%r' % name for name in field_names)
+ dicttxt = ', '.join('%r: t[%d]' % (name, pos) for pos, name in enumerate(field_names))
+ template = '''class %(typename)s(tuple):
+ '%(typename)s(%(argtxt)s)' \n
+ __slots__ = () \n
+ _fields = %(field_names)r \n
+ def __new__(cls, %(argtxt)s):
+ return tuple.__new__(cls, (%(argtxt)s)) \n
+ @classmethod
+ def _make(cls, iterable, new=tuple.__new__, len=len):
+ 'Make a new %(typename)s object from a sequence or iterable'
+ result = new(cls, iterable)
+ if len(result) != %(numfields)d:
+ raise TypeError('Expected %(numfields)d arguments, got %%d' %% len(result))
+ return result \n
+ def __repr__(self):
+ return '%(typename)s(%(reprtxt)s)' %% self \n
+ def _asdict(t):
+ 'Return a new dict which maps field names to their values'
+ return {%(dicttxt)s} \n
+ def _replace(self, **kwds):
+ 'Return a new %(typename)s object replacing specified fields with new values'
+ result = self._make(map(kwds.pop, %(field_names)r, self))
+ if kwds:
+ raise ValueError('Got unexpected field names: %%r' %% kwds.keys())
+ return result \n
+ def __getnewargs__(self):
+ return tuple(self) \n\n''' % locals()
+ for i, name in enumerate(field_names):
+ template += ' %s = property(itemgetter(%d))\n' % (name, i)
+ if verbose:
+ print template
+
+ # Execute the template string in a temporary namespace
+ namespace = dict(itemgetter=_itemgetter)
+ try:
+ exec template in namespace
+ except SyntaxError, e:
+ raise SyntaxError(e.message + ':\n' + template)
+ result = namespace[typename]
+
+ # For pickling to work, the __module__ variable needs to be set to the frame
+ # where the named tuple is created. Bypass this step in enviroments where
+ # sys._getframe is not defined (Jython for example).
+ if hasattr(_sys, '_getframe') and _sys.platform != 'cli':
+ result.__module__ = _sys._getframe(1).f_globals['__name__']
+
+ return result
+
+
+if __name__ == '__main__':
+ # verify that instances can be pickled
+ from cPickle import loads, dumps
+ Point = namedtuple('Point', 'x, y', True)
+ p = Point(x=10, y=20)
+ assert p == loads(dumps(p, -1))
+
+ # test and demonstrate ability to override methods
+ class Point(namedtuple('Point', 'x y')):
+ @property
+ def hypot(self):
+ return (self.x ** 2 + self.y ** 2) ** 0.5
+ def __str__(self):
+ return 'Point: x=%6.3f y=%6.3f hypot=%6.3f' % (self.x, self.y, self.hypot)
+
+ for p in Point(3,4), Point(14,5), Point(9./7,6):
+ print p
+
+ class Point(namedtuple('Point', 'x y')):
+ 'Point class with optimized _make() and _replace() without error-checking'
+ _make = classmethod(tuple.__new__)
+ def _replace(self, _map=map, **kwds):
+ return self._make(_map(kwds.get, ('x', 'y'), self))
+
+ print Point(11, 22)._replace(x=100)
+
+ import doctest
+ TestResults = namedtuple('TestResults', 'failed attempted')
+ print TestResults(*doctest.testmod())
320 dedupe/compat/ordereddict.py
@@ -0,0 +1,320 @@
+"""
+odict
+~~~~~
+
+Source: http://dev.pocoo.org/hg/sandbox/raw-file/tip/odict.py
+
+This module is an example implementation of an ordered dict for the
+collections module. It's not written for performance (it actually
+performs pretty bad) but to show how the API works.
+
+
+Questions and Answers
+=====================
+
+Why would anyone need ordered dicts?
+
+ Dicts in python are unordered which means that the order of items when
+ iterating over dicts is undefined. As a matter of fact it is most of
+ the time useless and differs from implementation to implementation.
+
+ Many developers stumble upon that problem sooner or later when
+ comparing the output of doctests which often does not match the order
+ the developer thought it would.
+
+ Also XML systems such as Genshi have their problems with unordered
+ dicts as the input and output ordering of tag attributes is often
+ mixed up because the ordering is lost when converting the data into
+ a dict. Switching to lists is often not possible because the
+ complexity of a lookup is too high.
+
+ Another very common case is metaprogramming. The default namespace
+ of a class in python is a dict. With Python 3 it becomes possible
+ to replace it with a different object which could be an ordered dict.
+ Django is already doing something similar with a hack that assigns
+ numbers to some descriptors initialized in the class body of a
+ specific subclass to restore the ordering after class creation.
+
+ When porting code from programming languages such as PHP and Ruby
+ where the item-order in a dict is guaranteed it's also a great help
+ to have an equivalent data structure in Python to ease the transition.
+
+Where are new keys added?
+
+ At the end. This behavior is consistent with Ruby 1.9 Hashmaps
+ and PHP Arrays. It also matches what common ordered dict
+ implementations do currently.
+
+What happens if an existing key is reassigned?
+
+ The key is *not* moved. This is consitent with existing
+ implementations and can be changed by a subclass very easily::
+
+ class movingodict(odict):
+ def __setitem__(self, key, value):
+ self.pop(key, None)
+ odict.__setitem__(self, key, value)
+
+ Moving keys to the end of a ordered dict on reassignment is not
+ very useful for most applications.
+
+Does it mean the dict keys are sorted by a sort expression?
+
+ That's not the case. The odict only guarantees that there is an order
+ and that newly inserted keys are inserted at the end of the dict. If
+ you want to sort it you can do so, but newly added keys are again added
+ at the end of the dict.
+
+I initializes the odict with a dict literal but the keys are not
+ordered like they should!
+
+ Dict literals in Python generate dict objects and as such the order of
+ their items is not guaranteed. Before they are passed to the odict
+ constructor they are already unordered.
+
+What happens if keys appear multiple times in the list passed to the
+constructor?
+
+ The same as for the dict. The latter item overrides the former. This
+ has the side-effect that the position of the first key is used because
+ the key is actually overwritten:
+
+ >>> odict([('a', 1), ('b', 2), ('a', 3)])
+ odict.odict([('a', 3), ('b', 2)])
+
+ This behavor is consistent with existing implementation in Python
+ and the PHP array and the hashmap in Ruby 1.9.
+
+This odict doesn't scale!
+
+ Yes it doesn't. The delitem operation is O(n). This is file is a
+ mockup of a real odict that could be implemented for collections
+ based on an linked list.
+
+Why is there no .insert()?
+
+ There are few situations where you really want to insert a key at
+ an specified index. To now make the API too complex the proposed
+ solution for this situation is creating a list of items, manipulating
+ that and converting it back into an odict:
+
+ >>> d = odict([('a', 42), ('b', 23), ('c', 19)])
+ >>> l = d.items()
+ >>> l.insert(1, ('x', 0))
+ >>> odict(l)
+ odict.odict([('a', 42), ('x', 0), ('b', 23), ('c', 19)])
+"""
+from itertools import izip, imap
+from copy import deepcopy
+
+missing = object()
+
+class OrderedDict(dict):
+ """
+ Ordered dict example implementation.
+
+ This is the proposed interface for a an ordered dict as proposed on the
+ Python mailinglist (proposal_).
+
+ It's a dict subclass and provides some list functions. The implementation
+ of this class is inspired by the implementation of Babel but incorporates
+ some ideas from the `ordereddict`_ and Django's ordered dict.
+
+ The constructor and `update()` both accept iterables of tuples as well as
+ mappings:
+
+ >>> d = odict([('a', 'b'), ('c', 'd')])
+ >>> d.update({'foo': 'bar'})
+ >>> d
+ odict.odict([('a', 'b'), ('c', 'd'), ('foo', 'bar')])
+
+ Keep in mind that when updating from dict-literals the order is not
+ preserved as these dicts are unsorted!
+
+ You can copy an odict like a dict by using the constructor, `copy.copy`
+ or the `copy` method and make deep copies with `copy.deepcopy`:
+
+ >>> from copy import copy, deepcopy
+ >>> copy(d)
+ odict.odict([('a', 'b'), ('c', 'd'), ('foo', 'bar')])
+ >>> d.copy()
+ odict.odict([('a', 'b'), ('c', 'd'), ('foo', 'bar')])
+ >>> odict(d)
+ odict.odict([('a', 'b'), ('c', 'd'), ('foo', 'bar')])
+ >>> d['spam'] = []
+ >>> d2 = deepcopy(d)
+ >>> d2['spam'].append('eggs')
+ >>> d
+ odict.odict([('a', 'b'), ('c', 'd'), ('foo', 'bar'), ('spam', [])])
+ >>> d2
+ odict.odict([('a', 'b'), ('c', 'd'), ('foo', 'bar'), ('spam', ['eggs'])])
+
+ All iteration methods as well as `keys`, `values` and `items` return
+ the values ordered by the the time the key-value pair is inserted:
+
+ >>> d.keys()
+ ['a', 'c', 'foo', 'spam']
+ >>> d.values()
+ ['b', 'd', 'bar', []]
+ >>> d.items()
+ [('a', 'b'), ('c', 'd'), ('foo', 'bar'), ('spam', [])]
+ >>> list(d.iterkeys())
+ ['a', 'c', 'foo', 'spam']
+ >>> list(d.itervalues())
+ ['b', 'd', 'bar', []]
+ >>> list(d.iteritems())
+ [('a', 'b'), ('c', 'd'), ('foo', 'bar'), ('spam', [])]
+
+ Index based lookup is supported too by `byindex` which returns the
+ key/value pair for an index:
+
+ >>> d.byindex(2)
+ ('foo', 'bar')
+
+ You can reverse the odict as well:
+
+ >>> d.reverse()
+ >>> d
+ odict.odict([('spam', []), ('foo', 'bar'), ('c', 'd'), ('a', 'b')])
+
+ And sort it like a list:
+
+ >>> d.sort(key=lambda x: x[0].lower())
+ >>> d
+ odict.odict([('a', 'b'), ('c', 'd'), ('foo', 'bar'), ('spam', [])])
+
+ .. _proposal: http://thread.gmane.org/gmane.comp.python.devel/95316
+ .. _ordereddict: http://www.xs4all.nl/~anthon/Python/ordereddict/
+ """
+
+ def __init__(self, *args, **kwargs):
+ dict.__init__(self)
+ self._keys = []
+ self.update(*args, **kwargs)
+
+ def __delitem__(self, key):
+ dict.__delitem__(self, key)
+ self._keys.remove(key)
+
+ def __setitem__(self, key, item):
+ if key not in self:
+ self._keys.append(key)
+ dict.__setitem__(self, key, item)
+
+ def __deepcopy__(self, memo=None):
+ if memo is None:
+ memo = {}
+ d = memo.get(id(self), missing)
+ if d is not missing:
+ return d
+ memo[id(self)] = d = self.__class__()
+ dict.__init__(d, deepcopy(self.items(), memo))
+ d._keys = self._keys[:]
+ return d
+
+ def __getstate__(self):
+ return {'items': dict(self), 'keys': self._keys}
+
+ def __setstate__(self, d):
+ self._keys = d['keys']
+ dict.update(d['items'])
+
+ def __reversed__(self):
+ return reversed(self._keys)
+
+ def __eq__(self, other):
+ if isinstance(other, odict):
+ if not dict.__eq__(self, other):
+ return False
+ return self.items() == other.items()
+ return dict.__eq__(self, other)
+
+ def __ne__(self, other):
+ return not self.__eq__(other)
+
+ def __cmp__(self, other):
+ if isinstance(other, odict):
+ return cmp(self.items(), other.items())
+ elif isinstance(other, dict):
+ return dict.__cmp__(self, other)
+ return NotImplemented
+
+ @classmethod
+ def fromkeys(cls, iterable, default=None):
+ return cls((key, default) for key in iterable)
+
+ def clear(self):
+ del self._keys[:]
+ dict.clear(self)
+
+ def copy(self):
+ return self.__class__(self)
+
+ def items(self):
+ return zip(self._keys, self.values())
+
+ def iteritems(self):
+ return izip(self._keys, self.itervalues())
+
+ def keys(self):
+ return self._keys[:]
+
+ def iterkeys(self):
+ return iter(self._keys)
+
+ def pop(self, key, default=missing):
+ if default is missing:
+ return dict.pop(self, key)
+ elif key not in self:
+ return default
+ self._keys.remove(key)
+ return dict.pop(self, key, default)
+
+ def popitem(self, key):
+ self._keys.remove(key)
+ return dict.popitem(key)
+
+ def setdefault(self, key, default=None):
+ if key not in self:
+ self._keys.append(key)
+ dict.setdefault(self, key, default)
+
+ def update(self, *args, **kwargs):
+ sources = []
+ if len(args) == 1:
+ if hasattr(args[0], 'iteritems'):
+ sources.append(args[0].iteritems())
+ else:
+ sources.append(iter(args[0]))
+ elif args:
+ raise TypeError('expected at most one positional argument')
+ if kwargs:
+ sources.append(kwargs.iteritems())
+ for iterable in sources:
+ for key, val in iterable:
+ self[key] = val
+
+ def values(self):
+ return map(self.get, self._keys)
+
+ def itervalues(self):
+ return imap(self.get, self._keys)
+
+ def index(self, item):
+ return self._keys.index(item)
+
+ def byindex(self, item):
+ key = self._keys[item]
+ return (key, dict.__getitem__(self, key))
+
+ def reverse(self):
+ self._keys.reverse()
+
+ def sort(self, *args, **kwargs):
+ self._keys.sort(*args, **kwargs)
+
+ def __repr__(self):
+ return 'odict.odict(%r)' % self.items()
+
+ __copy__ = copy
+ __iter__ = iterkeys
874 dedupe/dmetaphone.py
@@ -0,0 +1,874 @@
+"""Compute the Double Metaphone code for a string.
+
+The Original Software is: "encode.py". The Initial Developer of the Original
+Software is Dr Peter Christen (Department of Computer Science, Australian
+National University).
+
+Copyright (C) 2002 - 2008 the Australian National University and
+others. All Rights Reserved.
+
+Freely extensible biomedical record linkage (Febrl) - Version 0.4.1
+
+See: http://datamining.anu.edu.au/linkage.html
+
+dmetaphone is based on:
+ - Lawrence Philips C++ code as published in C/C++ Users Journal (June 2000)
+ and available at:
+ http://www.cuj.com/articles/2000/0006/0006d/0006d.htm
+ - Perl/C implementation
+ http://www.cpan.org/modules/by-authors/id/MAURICE/
+
+See also:
+ - http://aspell.sourceforge.net/metaphone/
+ - http://www.nist.gov/dads/HTML/doubleMetaphone.html
+"""
+
+__license__ = """
+Copyright (C) 2008-2008 the Australian National University
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program. If not, see <http://www.gnu.org/licenses/>.
+"""
+
+def dmetaphone(s, maxlen=4):
+ """Compute the Double Metaphone code for a string.
+
+ @param s: A string containing a name.
+
+ @param maxlen: Maximal length of the returned code. If a code is longer
+ than 'maxlen' it is truncated. Default value is 4.
+
+
+ DESCRIPTION:
+ """
+
+ if (not s):
+ return ''
+
+ primary = ''
+ secondary = ''
+ alternate = ''
+ primary_len = 0
+ secondary_len = 0
+
+ # Sub routines - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ #
+ def isvowel(c):
+ if (c in 'aeiouy'):
+ return 1
+ else:
+ return 0
+
+ def slavogermanic(str):
+ if (str.find('w')>-1) or (str.find('k')>-1) or (str.find('cz')>-1) or \
+ (str.find('witz')>-1):
+ return 1
+ else:
+ return 0
+
+ # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+
+ length = len(s)
+ if (length < 1):
+ return ''
+ last = length-1
+
+ current = 0 # Current position in string
+ workstr = s+' '
+
+ if (workstr[0:2] in ['gn','kn','pn','wr','ps']):
+ current = current+1 # Skip first character
+
+ if (workstr[0] == 'x'): # Initial 'x' is pronounced like 's'
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ current = current+1
+
+ if (maxlen < 1): # Calculate maximum length to check
+ check_maxlen = length
+ else:
+ check_maxlen = maxlen
+
+ while (primary_len < check_maxlen) or (secondary_len < check_maxlen):
+ if (current >= length):
+ break
+
+ # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ # Main loop, analyse current character
+ #
+ c = workstr[current]
+
+ if (c in 'aeiouy'):
+ if (current == 0): # All initial vowels map to 'a'
+ primary = primary+'a'
+ primary_len = primary_len+1
+ secondary = secondary+'a'
+ secondary_len = secondary_len+1
+ current=current+1
+
+ elif (c == 'b'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ primary = primary+'p'
+ primary_len = primary_len+1
+ secondary = secondary+'p'
+ secondary_len = secondary_len+1
+ if (workstr[current+1] == 'b'):
+ current=current+2
+ else:
+ current=current+1
+
+ # elif (s == 'c'): # C
+ # primary = primary+'s'
+ # primary_len = primary_len+1
+ # secondary = secondary+'s'
+ # secondary_len = secondary_len+1
+ # current = current+1
+
+ elif (c == 'c'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (current > 1) and (not isvowel(workstr[current-2])) and \
+ workstr[current-1:current+2] == 'ach' and \
+ (workstr[current+2] != 'i' and \
+ (workstr[current+2] != 'e' or \
+ workstr[current-2:current+4] in ['bacher','macher'])):
+ primary = primary+'k' # Various germanic special cases
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current = current+2
+ elif (current == 0) and (workstr[0:6] == 'caesar'):
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ current = current+2
+ elif (workstr[current:current+4] == 'chia'): # Italian 'chianti'
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current = current+2
+ elif (workstr[current:current+2] == 'ch'):
+ if (current > 0) and (workstr[current:current+4] == 'chae'):
+ primary = primary+'k' # Find 'michael'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current = current+2
+ elif (current == 0) and \
+ (workstr[current+1:current+6] in ['harac','haris'] or \
+ workstr[current+1:current+4] in \
+ ['hor','hym','hia','hem']) and \
+ workstr[0:6] != 'chore':
+ primary = primary+'k' # Greek roots, eg. 'chemistry'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current = current+2
+ elif (workstr[0:4] in ['van ','von '] or \
+ workstr[0:3] == 'sch') or \
+ workstr[current-2:current+4] in \
+ ['orches','archit','orchid'] or \
+ workstr[current+2] in ['t','s'] or \
+ ((workstr[current-1] in ['a','o','u','e'] or \
+ current==0) and \
+ workstr[current+2] in \
+ ['l','r','n','m','b','h','f','v','w',' ']):
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current = current+2
+ else:
+ if (current > 0):
+ if (workstr[0:2] == 'mc'):
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current = current+2
+ else:
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current = current+2
+ else:
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (workstr[current:current+2] == 'cz') and \
+ (workstr[current-2:current+2] != 'wicz'):
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (workstr[current+1:current+4] == 'cia'):
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current=current+3
+ elif (workstr[current:current+2] == 'cc') and \
+ not (current==1 and workstr[0] == 'm'):
+ if (workstr[current+2] in ['i','e','h']) and \
+ (workstr[current+2:current+4] != 'hu'):
+ if (current == 1 and workstr[0] == 'a') or \
+ (workstr[current-1:current+4] in ['uccee','ucces']):
+ primary = primary+'ks'
+ primary_len = primary_len+2
+ secondary = secondary+'ks'
+ secondary_len = secondary_len+2
+ current=current+3
+ else:
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current=current+3
+ else: # Pierce's rule
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (workstr[current:current+2] in ['ck','cg','cq']):
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (workstr[current:current+2] in ['ci','ce','cy']):
+ if (workstr[current:current+3] in ['cio','cie','cia']):
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ if (workstr[current+1:current+3] in [' c',' q',' g']):
+ current=current+3
+ else:
+ if (workstr[current+1] in ['c','k','q']) and \
+ (workstr[current+1:current+3] not in ['ce','ci']):
+ current=current+2
+ else:
+ current=current+1
+
+ elif (c == 'd'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current:current+2] == 'dg'):
+ if (workstr[current+2] in ['i','e','y']): # Eg. 'edge'
+ primary = primary+'j'
+ primary_len = primary_len+1
+ secondary = secondary+'j'
+ secondary_len = secondary_len+1
+ current=current+3
+ else: # Eg. 'edgar'
+ primary = primary+'tk'
+ primary_len = primary_len+2
+ secondary = secondary+'tk'
+ secondary_len = secondary_len+2
+ current=current+2
+ elif (workstr[current:current+2] in ['dt','dd']):
+ primary = primary+'t'
+ primary_len = primary_len+1
+ secondary = secondary+'t'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ primary = primary+'t'
+ primary_len = primary_len+1
+ secondary = secondary+'t'
+ secondary_len = secondary_len+1
+ current=current+1
+
+ elif (c == 'f'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current+1] == 'f'):
+ current=current+2
+ else:
+ current=current+1
+ primary = primary+'f'
+ primary_len = primary_len+1
+ secondary = secondary+'f'
+ secondary_len = secondary_len+1
+
+ elif (c == 'g'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current+1] == 'h'):
+ if (current > 0 and not isvowel(workstr[current-1])):
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (current==0):
+ if (workstr[current+2] == 'i'): # Eg. ghislane, ghiradelli
+ primary = primary+'j'
+ primary_len = primary_len+1
+ secondary = secondary+'j'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (current>1 and workstr[current-2] in ['b','h','d']) or \
+ (current>2 and workstr[current-3] in ['b','h','d']) or \
+ (current>3 and workstr[current-4] in ['b','h']):
+ current=current+2
+ else:
+ if (current > 2) and (workstr[current-1] == 'u') and \
+ (workstr[current-3] in ['c','g','l','r','t']):
+ primary = primary+'f'
+ primary_len = primary_len+1
+ secondary = secondary+'f'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ if (current > 0) and (workstr[current-1] != 'i'):
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ current=current+2
+ elif (workstr[current+1] == 'n'):
+ if (current==1) and (isvowel(workstr[0])) and \
+ (not slavogermanic(workstr)):
+ primary = primary+'kn'
+ primary_len = primary_len+2
+ secondary = secondary+'n'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ if (workstr[current+2:current+4] != 'ey') and \
+ (workstr[current+1] != 'y') and \
+ (not slavogermanic(workstr)):
+ primary = primary+'n'
+ primary_len = primary_len+1
+ secondary = secondary+'kn'
+ secondary_len = secondary_len+2
+ current=current+2
+ else:
+ primary = primary+'kn'
+ primary_len = primary_len+2
+ secondary = secondary+'kn'
+ secondary_len = secondary_len+2
+ current=current+2
+ elif (workstr[current+1:current+3] == 'li') and \
+ (not slavogermanic(workstr)):
+ primary = primary+'kl'
+ primary_len = primary_len+2
+ secondary = secondary+'l'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (current==0) and ((workstr[current+1] == 'y') or \
+ (workstr[current+1:current+3] in \
+ ['es','ep','eb','el','ey','ib','il','in','ie','ei','er'])):
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'j'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (workstr[current+1:current+3] == 'er' or \
+ workstr[current+1] == 'y') and \
+ workstr[0:6] not in ['danger','ranger','manger'] and \
+ workstr[current-1] not in ['e','i'] and \
+ workstr[current-1:current+2] not in ['rgy','ogy']:
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'j'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (workstr[current+1] in ['e','i','y']) or \
+ (workstr[current-1:current+3] in ['aggi','oggi']):
+ if (workstr[0:4] in ['van ','von ']) or \
+ (workstr[0:3] == 'sch') or \
+ (workstr[current+1:current+3] == 'et'):
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ if (workstr[current+1:current+5] == 'ier '):
+ primary = primary+'j'
+ primary_len = primary_len+1
+ secondary = secondary+'j'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ primary = primary+'j'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ if (workstr[current+1] == 'g'):
+ current=current+2
+ else:
+ current=current+1
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+
+ elif (c =='h'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (current == 0 or isvowel(workstr[current-1])) and \
+ isvowel(workstr[current+1]):
+ primary = primary+'h'
+ primary_len = primary_len+1
+ secondary = secondary+'h'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ current=current+1
+
+ elif (c =='j'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current:current+4] == 'jose') or \
+ (workstr[0:4] == 'san '):
+ if (current == 0 and workstr[4] == ' ') or \
+ (workstr[0:4] == 'san '):
+ primary = primary+'h'
+ primary_len = primary_len+1
+ secondary = secondary+'h'
+ secondary_len = secondary_len+1
+ current=current+1
+ else:
+ primary = primary+'j'
+ primary_len = primary_len+1
+ secondary = secondary+'h'
+ secondary_len = secondary_len+1
+ current=current+1
+ elif (current==0) and (workstr[0:4] != 'jose'):
+ primary = primary+'j'
+ primary_len = primary_len+1
+ secondary = secondary+'a'
+ secondary_len = secondary_len+1
+ if (workstr[current+1] == 'j'):
+ current=current+2
+ else:
+ current=current+1
+ else:
+ if (isvowel(workstr[current-1])) and \
+ (not slavogermanic(workstr)) and \
+ (workstr[current+1] in ['a','o']):
+ primary = primary+'j'
+ primary_len = primary_len+1
+ secondary = secondary+'h'
+ secondary_len = secondary_len+1
+ else:
+ if (current == last):
+ primary = primary+'j'
+ primary_len = primary_len+1
+ #secondary = secondary+''
+ #secondary_len = secondary_len+0
+ else:
+ if (workstr[current+1] not in \
+ ['l','t','k','s','n','m','b','z']) and \
+ (workstr[current-1] not in ['s','k','l']):
+ primary = primary+'j'
+ primary_len = primary_len+1
+ secondary = secondary+'j'
+ secondary_len = secondary_len+1
+ if (workstr[current+1] == 'j'):
+ current=current+2
+ else:
+ current=current+1
+
+ elif (c =='k'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current+1] == 'k'):
+ current=current+2
+ else:
+ current=current+1
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+
+ elif (c == 'l'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current+1] == 'l'):
+ if (current == (length-3)) and \
+ (workstr[current-1:current+3] in ['illo','illa','alle']) or \
+ ((workstr[last-1:last+1] in ['as','os'] or
+ workstr[last] in ['a','o']) and \
+ workstr[current-1:current+3] == 'alle'):
+ primary = primary+'l'
+ primary_len = primary_len+1
+ #secondary = secondary+''
+ #secondary_len = secondary_len+0
+ current=current+2
+ else:
+ primary = primary+'l'
+ primary_len = primary_len+1
+ secondary = secondary+'l'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ primary = primary+'l'
+ primary_len = primary_len+1
+ secondary = secondary+'l'
+ secondary_len = secondary_len+1
+ current=current+1
+
+ elif (c == 'm'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current-1:current+2] == 'umb' and \
+ ((current+1) == last or \
+ workstr[current+2:current+4] == 'er')) or \
+ workstr[current+1] == 'm':
+ current=current+2
+ else:
+ current=current+1
+ primary = primary+'m'
+ primary_len = primary_len+1
+ secondary = secondary+'m'
+ secondary_len = secondary_len+1
+
+ elif (c == 'n'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current+1] == 'n'):
+ current=current+2
+ else:
+ current=current+1
+ primary = primary+'n'
+ primary_len = primary_len+1
+ secondary = secondary+'n'
+ secondary_len = secondary_len+1
+
+ elif (c == 'p'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current+1] == 'h'):
+ primary = primary+'f'
+ primary_len = primary_len+1
+ secondary = secondary+'f'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (workstr[current+1] in ['p','b']):
+ primary = primary+'p'
+ primary_len = primary_len+1
+ secondary = secondary+'p'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ primary = primary+'p'
+ primary_len = primary_len+1
+ secondary = secondary+'p'
+ secondary_len = secondary_len+1
+ current=current+1
+
+ elif (c == 'q'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current+1] == 'q'):
+ current=current+2
+ else:
+ current=current+1
+ primary = primary+'k'
+ primary_len = primary_len+1
+ secondary = secondary+'k'
+ secondary_len = secondary_len+1
+
+ elif (c == 'r'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (current==last) and (not slavogermanic(workstr)) and \
+ (workstr[current-2:current] == 'ie') and \
+ (workstr[current-4:current-2] not in ['me','ma']):
+ # primary = primary+''
+ # primary_len = primary_len+0
+ secondary = secondary+'r'
+ secondary_len = secondary_len+1
+ else:
+ primary = primary+'r'
+ primary_len = primary_len+1
+ secondary = secondary+'r'
+ secondary_len = secondary_len+1
+ if (workstr[current+1] == 'r'):
+ current=current+2
+ else:
+ current=current+1
+
+ elif (c == 's'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current-1:current+2] in ['isl','ysl']):
+ current=current+1
+ elif (current==0) and (workstr[0:5] == 'sugar'):
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ current=current+1
+ elif (workstr[current:current+2] == 'sh'):
+ if (workstr[current+1:current+5] in \
+ ['heim','hoek','holm','holz']):
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (workstr[current:current+3] in ['sio','sia']) or \
+ (workstr[current:current+4] == 'sian'):
+ if (not slavogermanic(workstr)):
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current=current+3
+ else:
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ current=current+3
+ elif ((current==0) and (workstr[1] in ['m','n','l','w'])) or \
+ (workstr[current+1] == 'z'):
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ if (workstr[current+1] == 'z'):
+ current=current+2
+ else:
+ current=current+1
+ elif (workstr[current:current+2] == 'sc'):
+ if (workstr[current+2] == 'h'):
+ if (workstr[current+3:current+5] in \
+ ['oo','er','en','uy','ed','em']):
+ if (workstr[current+3:current+5] in ['er','en']):
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'sk'
+ secondary_len = secondary_len+2
+ current=current+3
+ else:
+ primary = primary+'sk'
+ primary_len = primary_len+2
+ secondary = secondary+'sk'
+ secondary_len = secondary_len+2
+ current=current+3
+ else:
+ if (current==0) and (not isvowel(workstr[3])) and \
+ (workstr[3] != 'w'):
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ current=current+3
+ else:
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current=current+3
+ elif (workstr[current+2] in ['i','e','y']):
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ current=current+3
+ else:
+ primary = primary+'sk'
+ primary_len = primary_len+2
+ secondary = secondary+'sk'
+ secondary_len = secondary_len+2
+ current=current+3
+ elif (current==last) and \
+ (workstr[current-2:current] in ['ai','oi']):
+ # primary = primary+''
+ # primary_len = primary_len+0
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ if (workstr[current+1] in ['s','z']):
+ current=current+2
+ else:
+ current=current+1
+ else:
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ if (workstr[current+1] in ['s','z']):
+ current=current+2
+ else:
+ current=current+1
+
+ elif (c == 't'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current:current+4] == 'tion'):
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current=current+3
+ elif (workstr[current:current+3] in ['tia','tch']):
+ primary = primary+'x'
+ primary_len = primary_len+1
+ secondary = secondary+'x'
+ secondary_len = secondary_len+1
+ current=current+3
+ elif (workstr[current:current+2] == 'th') or \
+ (workstr[current:current+3] == 'tth'):
+ if (workstr[current+2:current+4] in ['om','am']) or \
+ (workstr[0:4] in ['von ','van ']) or (workstr[0:3] == 'sch'):
+ primary = primary+'t'
+ primary_len = primary_len+1
+ secondary = secondary+'t'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ primary = primary+'0'
+ primary_len = primary_len+1
+ secondary = secondary+'t'
+ secondary_len = secondary_len+1
+ current=current+2
+ elif (workstr[current+1] in ['t','d']):
+ primary = primary+'t'
+ primary_len = primary_len+1
+ secondary = secondary+'t'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ primary = primary+'t'
+ primary_len = primary_len+1
+ secondary = secondary+'t'
+ secondary_len = secondary_len+1
+ current=current+1
+
+ elif (c == 'v'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current+1] == 'v'):
+ current=current+2
+ else:
+ current=current+1
+ primary = primary+'f'
+ primary_len = primary_len+1
+ secondary = secondary+'f'
+ secondary_len = secondary_len+1
+
+ elif (c == 'w'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current:current+2] == 'wr'):
+ primary = primary+'r'
+ primary_len = primary_len+1
+ secondary = secondary+'r'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ if (current==0) and (isvowel(workstr[1]) or \
+ workstr[0:2] == 'wh'):
+ if (isvowel(workstr[current+1])):
+ primary = primary+'a'
+ primary_len = primary_len+1
+ secondary = secondary+'f'
+ secondary_len = secondary_len+1
+ #current=current+1
+ else:
+ primary = primary+'a'
+ primary_len = primary_len+1
+ secondary = secondary+'a'
+ secondary_len = secondary_len+1
+ #current=current+1
+ if (current==last and isvowel(workstr[current-1])) or \
+ workstr[current-1:current+4] in \
+ ['ewski','ewsky','owski','owsky'] or \
+ workstr[0:3] == 'sch':
+ # primary = primary+''
+ # primary_len = primary_len+0
+ secondary = secondary+'f'
+ secondary_len = secondary_len+1
+ current=current+1
+ elif (workstr[current:current+4] in ['witz','wicz']):
+ primary = primary+'ts'
+ primary_len = primary_len+2
+ secondary = secondary+'fx'
+ secondary_len = secondary_len+2
+ current=current+4
+ else:
+ current=current+1
+
+ elif (c == 'x'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if not (current==last and \
+ (workstr[current-3:current] in ['iau','eau'] or \
+ workstr[current-2:current] in ['au','ou'])):
+ primary = primary+'ks'
+ primary_len = primary_len+2
+ secondary = secondary+'ks'
+ secondary_len = secondary_len+2
+ if (workstr[current+1] in ['c','x']):
+ current=current+2
+ else:
+ current=current+1
+
+ elif (c == 'z'): # - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ if (workstr[current+1] == 'h'):
+ primary = primary+'j'
+ primary_len = primary_len+1
+ secondary = secondary+'j'
+ secondary_len = secondary_len+1
+ current=current+2
+ else:
+ if (workstr[current+1:current+3] in ['zo','zi','za']) or \
+ (slavogermanic(workstr) and \
+ (current > 0 and workstr[current-1] != 't')):
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'ts'
+ secondary_len = secondary_len+2
+ if (workstr[current+1] == 'z'):
+ current=current+2
+ else:
+ current=current+1
+ else:
+ primary = primary+'s'
+ primary_len = primary_len+1
+ secondary = secondary+'s'
+ secondary_len = secondary_len+1
+ if (workstr[current+1] == 'z'):
+ current=current+2
+ else:
+ current=current+1
+
+ else: # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
+ current=current+1
+
+ # End main loop
+
+ if (primary == secondary):
+ # If both codes are the same set the second's length to 0 so it's not used
+ secondary_len = 0
+
+# else:
+# print 'Two D-metaphone codes for "%s": "%s" / "%s"' % (s,primary,secondary)
+
+ # if (secondary_len > 0):
+ # return [primary[:maxlen], secondary[:maxlen]]
+ # else:
+ # return [primary[:maxlen]]
+
+ if (maxlen > 0):
+ resstr = primary[:maxlen] # Only return primary encoding
+ else:
+ resstr = primary
+
+ return resstr
88 dedupe/encoders.py
@@ -0,0 +1,88 @@
+"""Field value encoding functions.
+
+Be careful to combine encoders in a compatible type sequence. If one encoder
+produces a floating point value, don't wrap it in one that expects a string.
+
+@author: Graham Poulter
+@copyright: MIH Holdings
+@license: GPL
+"""
+
+import re
+
+from functools import partial
+
+from dmetaphone import dmetaphone
+
+from indexer import getfield
+
+def identity(x):
+ """Identity function, returns its argument."""
+ return x
+
+def strip(text):
+ """Strip multiple and trailing spaces."""
+ return re.sub(r"\s+", " ", text.strip())
+
+def lowstrip(text):
+ """Lowcase and strip extra space."""
+ return strip(text.lower())
+
+def nospace(text):
+ """Strip all whitespace."""
+ return re.sub(r"\s+", "", text.strip())
+
+def digits(text):
+ """Strip all except digits (for phone numbers)."""
+ return re.sub(r"\D+", "", text.strip())
+
+def sorted_words(text):
+ """Sort words."""
+ return ' '.join(sorted(text.split(' ')))
+
+def reverse(text):
+ """Reverse text."""
+ return text[::-1]
+
+def urldomain(text):
+ """Obtain the domain from the text of a URL."""
+ match = re.match(r'(?:http://)?(?:www\.)?([^/]+)(?:/.*)?', text)
+ if match is None: return text
+ return match.group(1)
+
+def emaildomain(text):
+ """Obtain the domain from the text of an email address"""
+ match = re.match(r'([^@]+)@(.+)', text)
+ if match is None: return text
+ return match.group(2)
+
+def wrap(*funcs):
+ """Create a composited function from a list of unitary functions.
+ @note: wrap(f1, f2, f3)(text) == f1(f2(f3(text)))"""
+ def _wrapper(text):
+ # Innermost function gets applies first
+ for func in funcs[::-1]:
+ text = func(text)
+ return text
+ return _wrapper
+
+
+## Function factories for creating computed fields that contain a set of values
+## instead of a single value. The factories generate functions that can
+## that split up a single delimited column or combines multiple columns.
+
+def combined_fields(fields):
+ """Creates a function that computes a set-type field from several string columns."""
+ def set_of_fields(record):
+ """Construct a set-type field from columns %s."""
+ return [getfield(record, field).strip() for field in fields if getfield(record, field).strip()]
+ set_of_fields.__doc__ %= ", ".join(fields) # Document the function
+ return set_of_fields
+
+def split_field(field, sep=";"):
+ """Create a function to compute a set-type field from a delimited string column."""
+ def set_from_field(record):
+ """Create a set-type field from column %s using delimiter %s."""
+ return [s.strip() for s in getfield(record, field).split(sep) if s.strip()]
+ set_from_field.__doc__ %= (field, sep) # Document the function
+ return set_from_field
114 dedupe/geocompare.py
@@ -0,0 +1,114 @@
+"""Functions for encoding and comparing geographic coordinates.
+
+@author: Graham Poulter
+@copyright: MIH Holdings
+@license: GPL
+"""
+
+from __future__ import division
+
+__license__ = "GPL3"
+
+from functools import wraps, partial
+from indexer import getfield
+
+def geofield(latfield, lonfield, record):
+ """Retrive the (latitude,longitude) float pair from a record using
+ field specifiers. Returns None if one or both of the
+ fields are empty strings."""
+ if not (latfield.strip() and lonfield.strip()):
+ return None
+ lat = float(getfield(record, latfield))
+ lon = float(getfield(record, lonfield))
+ return (lat,lon)
+
+def handle_missing(comparator, missing_weight=None, is_present=bool):
+ """Wraps a comparator to handle missing values.
+ @param comparator: Function taking two values and returning their similarity.
+ @param missing_weight: What to return whene one/both of the values is not present.
+ @param is_present: Predicate to determines whether the value is present.
+ """
+ @wraps(comparator)
+ def wrapped_compare(x, y):
+ """Compare the values only if both are valid."""
+ if not (is_present(x) and is_present(y)):
+ return missing_weight
+ else:
+ return comparator(x,y)
+ return wrapped_compare
+
+def transform_linear(value, inputrange, outputrange, none_value=None):
+ """Scale a value from the input range to the output range, such that the
+ left-end value of the input is matched to the left-end value in the
+ output. Values past the ends of the input range are mapped to the
+ correspondind ends of the output range: