pax_global_header00006660000000000000000000000064127526760220014523gustar00rootroot0000000000000052 comment=0263e3cf9da236bf583350741560f8726676e367 rows-0.2.1/000077500000000000000000000000001275267602200125155ustar00rootroot00000000000000rows-0.2.1/.gitignore000066400000000000000000000001741275267602200145070ustar00rootroot00000000000000*.egg-info/ *.pyc *~ .*.sw? .coverage .directory .env .idea/* .tox MANIFEST build/* dist/* reg_settings.py rows.1 .DS_Store rows-0.2.1/AUTHORS.md000066400000000000000000000013021275267602200141600ustar00rootroot00000000000000# Authors and Contributors of `rows` Library Project page: . ## Author/Maintainer Created and maintained by Álvaro Justen aka turicas: - - - ## Contributors - Érico Andrei - Bernardo Fontes - Alexandre Brandão (slex) - Paulo Roberto Alves de Oliveira (aka kretcheu) - Jean Ferri - Evaldo Junior - Rhenan Bartels - Mauro Baraldi rows-0.2.1/CHANGELOG.md000066400000000000000000000160201275267602200143250ustar00rootroot00000000000000# rows' Log of Changes ## Version `0.2.1` **Released on: 2016-08-10** ### Backwards Incompatible Changes - `rows.utils.export_to_uri` signature is now like `rows.export_to_*` (first the `rows.Table` object, then the URI) - Changed default table name in `import_from_sqlite` and `export_to_sqlite` (from `rows` and `rows_{number}` to `table{number}`) ### Bug Fixes - [#170](https://github.com/turicas/rows/issues/170) (SQLite plugin) Error converting `int` and `float` when value is `None`. - [#168](https://github.com/turicas/rows/issues/168) Use `Field.serialize` if does not know the field type (affecting: XLS, XLSX and SQLite plugins). - [#167](https://github.com/turicas/rows/issues/167) Use more data to detect dialect, delimit the possible delimiters and fallback to excel if can't detect. - [#176](https://github.com/turicas/rows/issues/176) Problem using quotes on CSV plugin. - [#179](https://github.com/turicas/rows/issues/179) Fix double underscore problem on `rows.utils.slug` - [#175](https://github.com/turicas/rows/issues/175) Fix `None` serialization/deserialization in all plugins (and also field types) - [#172](https://github.com/turicas/rows/issues/172) Expose all tables in `rows query` for SQLite databases - Fix `examples/cli/convert.sh` (missing `-`) - Avoids SQL injection in table name ### Enhancements and Refactorings - Refactor `rows.utils.import_from_uri` - Encoding and file type are better detected on `rows.utils.import_from_uri` - Added helper functions to `rows.utils` regarding encoding and file type/plugin detection - There's a better description of plugin metadata (MIME types accepted) on `rows.utils` (should be refactored to be inside each plugin) - Moved `slug` and `ipartition` functions to `rows.plugins.utils` - Optimize `rows query` when using only one SQLite source ## Version `0.2.0` **Released on: 2016-07-15** ### Backwards Incompatible Changes - `rows.fields.UnicodeField` was renamed to `rows.fields.TextField` - `rows.fields.BytesField` was renamed to `rows.fields.BinaryField` ### Bug Fixes - Fix import errors on older versions of urllib3 and Python (thanks to [@jeanferri](https://github.com/jeanferri)) - [#156](https://github.com/turicas/rows/issues/156) `BoolField` should not accept "0" and "1" as possible values - [#86](https://github.com/turicas/rows/issues/86) Fix `Content-Type` parsing - Fix locale-related tests - [#85](https://github.com/turicas/rows/issues/85) Fix `preserve_html` if `fields` is not provided - Fix problem with big integers - [#131](https://github.com/turicas/rows/issues/131) Fix problem when empty sample data - Fix problem with `unicode` and `DateField` - Fix `PercentField.serialize(None)` - Fix bug with `Decimal` receiving `''` - Fix bug in `PercentField.serialize(Decimal('0'))` - Fix nested table behaviour on HTML plugin ### General Changes - (EXPERIMENTAL) Add `rows.FlexibleTable` class (with help on tests from [@maurobaraildi](https://github.com/maurobaraldi)) - Lots of refactorings - Add `rows.operations.transpose` - Add `Table.__repr__` - Renamte `rows.fields.UnicodeField` to `rows.fields.TextField` and `rows.fields.ByteField` to `rows.fields.BinaryField` - Add a man page (thanks to [@kretcheu](https://github.com/kretcheu)) - [#40](https://github.com/turicas/rows/issues/40) The package is available on Debian! - [#120](https://github.com/turicas/rows/issues/120) The package is available on Fedora! - Add some examples - [#138](https://github.com/turicas/rows/issues/138) Add `rows.fields.JSONField` - [#146](https://github.com/turicas/rows/issues/146) Add `rows.fields.EmailField` - Enhance encoding detection using [file-magic](https://pypi.python.org/pypi/file-magic) library - [#160](https://github.com/turicas/rows/issues/160) Add support for column get/set/del in `rows.Table` ### Tests - Fix "\r\n" on tests to work on Windows - Enhance tests with `mock` to assure some functions are being called - Improve some tests ### Plugins - Add plugin JSON (thanks [@sxslex](https://github.com/sxslex)) - [#107](https://github.com/turicas/rows/issues/107) Add `import_from_txt` - [#149](https://github.com/turicas/rows/issues/149) Add `import_from_xpath` - (EXPERIMENTAL) Add `import_from_ods` - (EXPERIMENTAL) Add `import_from_parquet` - Add `import_from_sqlite` and `export_to_sqlite` (implemented by [@turicas](https://github.com/turicas) with help from [@infog](https://github.com/infog)) - Add `import_from_xlsx` and `export_to_xlsx` (thanks to [@RhenanBartels](https://github.com/turicas/RhenanBartels)) - Autodetect delimiter in CSV files - Export to TXT, JSON and XLS also support an already opened file and CSV can export to memory (thanks to [@jeanferri](https://github.com/jeanferri)) - [#93](https://github.com/turicas/rows/issues/93) Add HTML helpers inside `rows.plugins.html`: `count_tables`, `extract_text`, `extract_links` and `tag_to_dict` - [#162](https://github.com/turicas/rows/issues/162) Add `import_from_dicts` and `export_to_dicts` - Refactor `export_to_txt` ### Utils - Create `rows.plugins.utils` - [#119](https://github.com/turicas/rows/issues/119) Rename field name if name is duplicated (to "field_2", "field_3", ..., "field_N") or if starts with a number. - Add option to import only some fields (`import_fields` parameter inside `create_table`) - Add option to export only some fields (`export_fields` parameter inside `prepare_to_export`) - Add option `force_types` to force field types in some columns (instead of detecting) on `create_table`. - Support lazy objects on `create_table` - Add `samples` parameter to `create_table` ### CLI - Add option to disable SSL verification (`--verify-ssl=no`) - Add `print` subcommand - Add `--version` - CLI is not installed by default (should be installed as `pip install rows[cli]`) - Automatically detect default encoding (if not specified) - Add `--order-by` to some subcommands and remove `sort` subcommand. #111 - Do not use locale by default - Add `query` subcommand: converts (from many sources) internally to SQLite, execute the query and then export ## Version `0.1.1` **Released on: 2015-09-03** - Fix code to run on Windows (thanks [@sxslex](https://github.com/sxslex)) - Fix locale (name, default name etc.) - Remove `filemagic` dependency (waiting for `python-magic` to be available on PyPI) - Write log of changes for `0.1.0` and `0.1.1` ## Version `0.1.0` **Released on: 2015-08-29** - Implement `Table` and its basic methods - Implement basic plugin support with many utilities and the following formats: - `csv` (input/output) - `html` (input/output) - `txt` (output) - `xls` (input/output) - Implement the following field types - many of them with locale support: - `ByteField` - `BoolField` - `IntegerField` - `FloatField` - `DecimalField` - `PercentField` - `DateField` - `DatetimeField` - `UnicodeField` - Implement basic `Table` operations: - `sum` - `join` - `transform` - `serialize` - Implement a command-line interface with the following subcommands: - `convert` - `join` - `sort` - `sum` - Add examples to the repository rows-0.2.1/LICENSE000066400000000000000000001045131275267602200135260ustar00rootroot00000000000000 GNU GENERAL PUBLIC LICENSE Version 3, 29 June 2007 Copyright (C) 2007 Free Software Foundation, Inc. Everyone is permitted to copy and distribute verbatim copies of this license document, but changing it is not allowed. Preamble The GNU General Public License is a free, copyleft license for software and other kinds of works. The licenses for most software and other practical works are designed to take away your freedom to share and change the works. By contrast, the GNU General Public License is intended to guarantee your freedom to share and change all versions of a program--to make sure it remains free software for all its users. We, the Free Software Foundation, use the GNU General Public License for most of our software; it applies also to any other work released this way by its authors. You can apply it to your programs, too. When we speak of free software, we are referring to freedom, not price. Our General Public Licenses are designed to make sure that you have the freedom to distribute copies of free software (and charge for them if you wish), that you receive source code or can get it if you want it, that you can change the software or use pieces of it in new free programs, and that you know you can do these things. To protect your rights, we need to prevent others from denying you these rights or asking you to surrender the rights. Therefore, you have certain responsibilities if you distribute copies of the software, or if you modify it: responsibilities to respect the freedom of others. For example, if you distribute copies of such a program, whether gratis or for a fee, you must pass on to the recipients the same freedoms that you received. You must make sure that they, too, receive or can get the source code. And you must show them these terms so they know their rights. Developers that use the GNU GPL protect your rights with two steps: (1) assert copyright on the software, and (2) offer you this License giving you legal permission to copy, distribute and/or modify it. For the developers' and authors' protection, the GPL clearly explains that there is no warranty for this free software. For both users' and authors' sake, the GPL requires that modified versions be marked as changed, so that their problems will not be attributed erroneously to authors of previous versions. Some devices are designed to deny users access to install or run modified versions of the software inside them, although the manufacturer can do so. This is fundamentally incompatible with the aim of protecting users' freedom to change the software. The systematic pattern of such abuse occurs in the area of products for individuals to use, which is precisely where it is most unacceptable. Therefore, we have designed this version of the GPL to prohibit the practice for those products. If such problems arise substantially in other domains, we stand ready to extend this provision to those domains in future versions of the GPL, as needed to protect the freedom of users. Finally, every program is threatened constantly by software patents. States should not allow patents to restrict development and use of software on general-purpose computers, but in those that do, we wish to avoid the special danger that patents applied to a free program could make it effectively proprietary. To prevent this, the GPL assures that patents cannot be used to render the program non-free. The precise terms and conditions for copying, distribution and modification follow. TERMS AND CONDITIONS 0. Definitions. "This License" refers to version 3 of the GNU General Public License. "Copyright" also means copyright-like laws that apply to other kinds of works, such as semiconductor masks. "The Program" refers to any copyrightable work licensed under this License. Each licensee is addressed as "you". "Licensees" and "recipients" may be individuals or organizations. To "modify" a work means to copy from or adapt all or part of the work in a fashion requiring copyright permission, other than the making of an exact copy. The resulting work is called a "modified version" of the earlier work or a work "based on" the earlier work. A "covered work" means either the unmodified Program or a work based on the Program. To "propagate" a work means to do anything with it that, without permission, would make you directly or secondarily liable for infringement under applicable copyright law, except executing it on a computer or modifying a private copy. Propagation includes copying, distribution (with or without modification), making available to the public, and in some countries other activities as well. To "convey" a work means any kind of propagation that enables other parties to make or receive copies. Mere interaction with a user through a computer network, with no transfer of a copy, is not conveying. An interactive user interface displays "Appropriate Legal Notices" to the extent that it includes a convenient and prominently visible feature that (1) displays an appropriate copyright notice, and (2) tells the user that there is no warranty for the work (except to the extent that warranties are provided), that licensees may convey the work under this License, and how to view a copy of this License. If the interface presents a list of user commands or options, such as a menu, a prominent item in the list meets this criterion. 1. Source Code. The "source code" for a work means the preferred form of the work for making modifications to it. "Object code" means any non-source form of a work. A "Standard Interface" means an interface that either is an official standard defined by a recognized standards body, or, in the case of interfaces specified for a particular programming language, one that is widely used among developers working in that language. The "System Libraries" of an executable work include anything, other than the work as a whole, that (a) is included in the normal form of packaging a Major Component, but which is not part of that Major Component, and (b) serves only to enable use of the work with that Major Component, or to implement a Standard Interface for which an implementation is available to the public in source code form. A "Major Component", in this context, means a major essential component (kernel, window system, and so on) of the specific operating system (if any) on which the executable work runs, or a compiler used to produce the work, or an object code interpreter used to run it. The "Corresponding Source" for a work in object code form means all the source code needed to generate, install, and (for an executable work) run the object code and to modify the work, including scripts to control those activities. However, it does not include the work's System Libraries, or general-purpose tools or generally available free programs which are used unmodified in performing those activities but which are not part of the work. For example, Corresponding Source includes interface definition files associated with source files for the work, and the source code for shared libraries and dynamically linked subprograms that the work is specifically designed to require, such as by intimate data communication or control flow between those subprograms and other parts of the work. The Corresponding Source need not include anything that users can regenerate automatically from other parts of the Corresponding Source. The Corresponding Source for a work in source code form is that same work. 2. Basic Permissions. All rights granted under this License are granted for the term of copyright on the Program, and are irrevocable provided the stated conditions are met. This License explicitly affirms your unlimited permission to run the unmodified Program. The output from running a covered work is covered by this License only if the output, given its content, constitutes a covered work. This License acknowledges your rights of fair use or other equivalent, as provided by copyright law. You may make, run and propagate covered works that you do not convey, without conditions so long as your license otherwise remains in force. You may convey covered works to others for the sole purpose of having them make modifications exclusively for you, or provide you with facilities for running those works, provided that you comply with the terms of this License in conveying all material for which you do not control copyright. Those thus making or running the covered works for you must do so exclusively on your behalf, under your direction and control, on terms that prohibit them from making any copies of your copyrighted material outside their relationship with you. Conveying under any other circumstances is permitted solely under the conditions stated below. Sublicensing is not allowed; section 10 makes it unnecessary. 3. Protecting Users' Legal Rights From Anti-Circumvention Law. No covered work shall be deemed part of an effective technological measure under any applicable law fulfilling obligations under article 11 of the WIPO copyright treaty adopted on 20 December 1996, or similar laws prohibiting or restricting circumvention of such measures. When you convey a covered work, you waive any legal power to forbid circumvention of technological measures to the extent such circumvention is effected by exercising rights under this License with respect to the covered work, and you disclaim any intention to limit operation or modification of the work as a means of enforcing, against the work's users, your or third parties' legal rights to forbid circumvention of technological measures. 4. Conveying Verbatim Copies. You may convey verbatim copies of the Program's source code as you receive it, in any medium, provided that you conspicuously and appropriately publish on each copy an appropriate copyright notice; keep intact all notices stating that this License and any non-permissive terms added in accord with section 7 apply to the code; keep intact all notices of the absence of any warranty; and give all recipients a copy of this License along with the Program. You may charge any price or no price for each copy that you convey, and you may offer support or warranty protection for a fee. 5. Conveying Modified Source Versions. You may convey a work based on the Program, or the modifications to produce it from the Program, in the form of source code under the terms of section 4, provided that you also meet all of these conditions: a) The work must carry prominent notices stating that you modified it, and giving a relevant date. b) The work must carry prominent notices stating that it is released under this License and any conditions added under section 7. This requirement modifies the requirement in section 4 to "keep intact all notices". c) You must license the entire work, as a whole, under this License to anyone who comes into possession of a copy. This License will therefore apply, along with any applicable section 7 additional terms, to the whole of the work, and all its parts, regardless of how they are packaged. This License gives no permission to license the work in any other way, but it does not invalidate such permission if you have separately received it. d) If the work has interactive user interfaces, each must display Appropriate Legal Notices; however, if the Program has interactive interfaces that do not display Appropriate Legal Notices, your work need not make them do so. A compilation of a covered work with other separate and independent works, which are not by their nature extensions of the covered work, and which are not combined with it such as to form a larger program, in or on a volume of a storage or distribution medium, is called an "aggregate" if the compilation and its resulting copyright are not used to limit the access or legal rights of the compilation's users beyond what the individual works permit. Inclusion of a covered work in an aggregate does not cause this License to apply to the other parts of the aggregate. 6. Conveying Non-Source Forms. You may convey a covered work in object code form under the terms of sections 4 and 5, provided that you also convey the machine-readable Corresponding Source under the terms of this License, in one of these ways: a) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by the Corresponding Source fixed on a durable physical medium customarily used for software interchange. b) Convey the object code in, or embodied in, a physical product (including a physical distribution medium), accompanied by a written offer, valid for at least three years and valid for as long as you offer spare parts or customer support for that product model, to give anyone who possesses the object code either (1) a copy of the Corresponding Source for all the software in the product that is covered by this License, on a durable physical medium customarily used for software interchange, for a price no more than your reasonable cost of physically performing this conveying of source, or (2) access to copy the Corresponding Source from a network server at no charge. c) Convey individual copies of the object code with a copy of the written offer to provide the Corresponding Source. This alternative is allowed only occasionally and noncommercially, and only if you received the object code with such an offer, in accord with subsection 6b. d) Convey the object code by offering access from a designated place (gratis or for a charge), and offer equivalent access to the Corresponding Source in the same way through the same place at no further charge. You need not require recipients to copy the Corresponding Source along with the object code. If the place to copy the object code is a network server, the Corresponding Source may be on a different server (operated by you or a third party) that supports equivalent copying facilities, provided you maintain clear directions next to the object code saying where to find the Corresponding Source. Regardless of what server hosts the Corresponding Source, you remain obligated to ensure that it is available for as long as needed to satisfy these requirements. e) Convey the object code using peer-to-peer transmission, provided you inform other peers where the object code and Corresponding Source of the work are being offered to the general public at no charge under subsection 6d. A separable portion of the object code, whose source code is excluded from the Corresponding Source as a System Library, need not be included in conveying the object code work. A "User Product" is either (1) a "consumer product", which means any tangible personal property which is normally used for personal, family, or household purposes, or (2) anything designed or sold for incorporation into a dwelling. In determining whether a product is a consumer product, doubtful cases shall be resolved in favor of coverage. For a particular product received by a particular user, "normally used" refers to a typical or common use of that class of product, regardless of the status of the particular user or of the way in which the particular user actually uses, or expects or is expected to use, the product. A product is a consumer product regardless of whether the product has substantial commercial, industrial or non-consumer uses, unless such uses represent the only significant mode of use of the product. "Installation Information" for a User Product means any methods, procedures, authorization keys, or other information required to install and execute modified versions of a covered work in that User Product from a modified version of its Corresponding Source. The information must suffice to ensure that the continued functioning of the modified object code is in no case prevented or interfered with solely because modification has been made. If you convey an object code work under this section in, or with, or specifically for use in, a User Product, and the conveying occurs as part of a transaction in which the right of possession and use of the User Product is transferred to the recipient in perpetuity or for a fixed term (regardless of how the transaction is characterized), the Corresponding Source conveyed under this section must be accompanied by the Installation Information. But this requirement does not apply if neither you nor any third party retains the ability to install modified object code on the User Product (for example, the work has been installed in ROM). The requirement to provide Installation Information does not include a requirement to continue to provide support service, warranty, or updates for a work that has been modified or installed by the recipient, or for the User Product in which it has been modified or installed. Access to a network may be denied when the modification itself materially and adversely affects the operation of the network or violates the rules and protocols for communication across the network. Corresponding Source conveyed, and Installation Information provided, in accord with this section must be in a format that is publicly documented (and with an implementation available to the public in source code form), and must require no special password or key for unpacking, reading or copying. 7. Additional Terms. "Additional permissions" are terms that supplement the terms of this License by making exceptions from one or more of its conditions. Additional permissions that are applicable to the entire Program shall be treated as though they were included in this License, to the extent that they are valid under applicable law. If additional permissions apply only to part of the Program, that part may be used separately under those permissions, but the entire Program remains governed by this License without regard to the additional permissions. When you convey a copy of a covered work, you may at your option remove any additional permissions from that copy, or from any part of it. (Additional permissions may be written to require their own removal in certain cases when you modify the work.) You may place additional permissions on material, added by you to a covered work, for which you have or can give appropriate copyright permission. Notwithstanding any other provision of this License, for material you add to a covered work, you may (if authorized by the copyright holders of that material) supplement the terms of this License with terms: a) Disclaiming warranty or limiting liability differently from the terms of sections 15 and 16 of this License; or b) Requiring preservation of specified reasonable legal notices or author attributions in that material or in the Appropriate Legal Notices displayed by works containing it; or c) Prohibiting misrepresentation of the origin of that material, or requiring that modified versions of such material be marked in reasonable ways as different from the original version; or d) Limiting the use for publicity purposes of names of licensors or authors of the material; or e) Declining to grant rights under trademark law for use of some trade names, trademarks, or service marks; or f) Requiring indemnification of licensors and authors of that material by anyone who conveys the material (or modified versions of it) with contractual assumptions of liability to the recipient, for any liability that these contractual assumptions directly impose on those licensors and authors. All other non-permissive additional terms are considered "further restrictions" within the meaning of section 10. If the Program as you received it, or any part of it, contains a notice stating that it is governed by this License along with a term that is a further restriction, you may remove that term. If a license document contains a further restriction but permits relicensing or conveying under this License, you may add to a covered work material governed by the terms of that license document, provided that the further restriction does not survive such relicensing or conveying. If you add terms to a covered work in accord with this section, you must place, in the relevant source files, a statement of the additional terms that apply to those files, or a notice indicating where to find the applicable terms. Additional terms, permissive or non-permissive, may be stated in the form of a separately written license, or stated as exceptions; the above requirements apply either way. 8. Termination. You may not propagate or modify a covered work except as expressly provided under this License. Any attempt otherwise to propagate or modify it is void, and will automatically terminate your rights under this License (including any patent licenses granted under the third paragraph of section 11). However, if you cease all violation of this License, then your license from a particular copyright holder is reinstated (a) provisionally, unless and until the copyright holder explicitly and finally terminates your license, and (b) permanently, if the copyright holder fails to notify you of the violation by some reasonable means prior to 60 days after the cessation. Moreover, your license from a particular copyright holder is reinstated permanently if the copyright holder notifies you of the violation by some reasonable means, this is the first time you have received notice of violation of this License (for any work) from that copyright holder, and you cure the violation prior to 30 days after your receipt of the notice. Termination of your rights under this section does not terminate the licenses of parties who have received copies or rights from you under this License. If your rights have been terminated and not permanently reinstated, you do not qualify to receive new licenses for the same material under section 10. 9. Acceptance Not Required for Having Copies. You are not required to accept this License in order to receive or run a copy of the Program. Ancillary propagation of a covered work occurring solely as a consequence of using peer-to-peer transmission to receive a copy likewise does not require acceptance. However, nothing other than this License grants you permission to propagate or modify any covered work. These actions infringe copyright if you do not accept this License. Therefore, by modifying or propagating a covered work, you indicate your acceptance of this License to do so. 10. Automatic Licensing of Downstream Recipients. Each time you convey a covered work, the recipient automatically receives a license from the original licensors, to run, modify and propagate that work, subject to this License. You are not responsible for enforcing compliance by third parties with this License. An "entity transaction" is a transaction transferring control of an organization, or substantially all assets of one, or subdividing an organization, or merging organizations. If propagation of a covered work results from an entity transaction, each party to that transaction who receives a copy of the work also receives whatever licenses to the work the party's predecessor in interest had or could give under the previous paragraph, plus a right to possession of the Corresponding Source of the work from the predecessor in interest, if the predecessor has it or can get it with reasonable efforts. You may not impose any further restrictions on the exercise of the rights granted or affirmed under this License. For example, you may not impose a license fee, royalty, or other charge for exercise of rights granted under this License, and you may not initiate litigation (including a cross-claim or counterclaim in a lawsuit) alleging that any patent claim is infringed by making, using, selling, offering for sale, or importing the Program or any portion of it. 11. Patents. A "contributor" is a copyright holder who authorizes use under this License of the Program or a work on which the Program is based. The work thus licensed is called the contributor's "contributor version". A contributor's "essential patent claims" are all patent claims owned or controlled by the contributor, whether already acquired or hereafter acquired, that would be infringed by some manner, permitted by this License, of making, using, or selling its contributor version, but do not include claims that would be infringed only as a consequence of further modification of the contributor version. For purposes of this definition, "control" includes the right to grant patent sublicenses in a manner consistent with the requirements of this License. Each contributor grants you a non-exclusive, worldwide, royalty-free patent license under the contributor's essential patent claims, to make, use, sell, offer for sale, import and otherwise run, modify and propagate the contents of its contributor version. In the following three paragraphs, a "patent license" is any express agreement or commitment, however denominated, not to enforce a patent (such as an express permission to practice a patent or covenant not to sue for patent infringement). To "grant" such a patent license to a party means to make such an agreement or commitment not to enforce a patent against the party. If you convey a covered work, knowingly relying on a patent license, and the Corresponding Source of the work is not available for anyone to copy, free of charge and under the terms of this License, through a publicly available network server or other readily accessible means, then you must either (1) cause the Corresponding Source to be so available, or (2) arrange to deprive yourself of the benefit of the patent license for this particular work, or (3) arrange, in a manner consistent with the requirements of this License, to extend the patent license to downstream recipients. "Knowingly relying" means you have actual knowledge that, but for the patent license, your conveying the covered work in a country, or your recipient's use of the covered work in a country, would infringe one or more identifiable patents in that country that you have reason to believe are valid. If, pursuant to or in connection with a single transaction or arrangement, you convey, or propagate by procuring conveyance of, a covered work, and grant a patent license to some of the parties receiving the covered work authorizing them to use, propagate, modify or convey a specific copy of the covered work, then the patent license you grant is automatically extended to all recipients of the covered work and works based on it. A patent license is "discriminatory" if it does not include within the scope of its coverage, prohibits the exercise of, or is conditioned on the non-exercise of one or more of the rights that are specifically granted under this License. You may not convey a covered work if you are a party to an arrangement with a third party that is in the business of distributing software, under which you make payment to the third party based on the extent of your activity of conveying the work, and under which the third party grants, to any of the parties who would receive the covered work from you, a discriminatory patent license (a) in connection with copies of the covered work conveyed by you (or copies made from those copies), or (b) primarily for and in connection with specific products or compilations that contain the covered work, unless you entered into that arrangement, or that patent license was granted, prior to 28 March 2007. Nothing in this License shall be construed as excluding or limiting any implied license or other defenses to infringement that may otherwise be available to you under applicable patent law. 12. No Surrender of Others' Freedom. If conditions are imposed on you (whether by court order, agreement or otherwise) that contradict the conditions of this License, they do not excuse you from the conditions of this License. If you cannot convey a covered work so as to satisfy simultaneously your obligations under this License and any other pertinent obligations, then as a consequence you may not convey it at all. For example, if you agree to terms that obligate you to collect a royalty for further conveying from those to whom you convey the Program, the only way you could satisfy both those terms and this License would be to refrain entirely from conveying the Program. 13. Use with the GNU Affero General Public License. Notwithstanding any other provision of this License, you have permission to link or combine any covered work with a work licensed under version 3 of the GNU Affero General Public License into a single combined work, and to convey the resulting work. The terms of this License will continue to apply to the part which is the covered work, but the special requirements of the GNU Affero General Public License, section 13, concerning interaction through a network will apply to the combination as such. 14. Revised Versions of this License. The Free Software Foundation may publish revised and/or new versions of the GNU General Public License from time to time. Such new versions will be similar in spirit to the present version, but may differ in detail to address new problems or concerns. Each version is given a distinguishing version number. If the Program specifies that a certain numbered version of the GNU General Public License "or any later version" applies to it, you have the option of following the terms and conditions either of that numbered version or of any later version published by the Free Software Foundation. If the Program does not specify a version number of the GNU General Public License, you may choose any version ever published by the Free Software Foundation. If the Program specifies that a proxy can decide which future versions of the GNU General Public License can be used, that proxy's public statement of acceptance of a version permanently authorizes you to choose that version for the Program. Later license versions may give you additional or different permissions. However, no additional obligations are imposed on any author or copyright holder as a result of your choosing to follow a later version. 15. Disclaimer of Warranty. THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 16. Limitation of Liability. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. 17. Interpretation of Sections 15 and 16. If the disclaimer of warranty and limitation of liability provided above cannot be given local legal effect according to their terms, reviewing courts shall apply local law that most closely approximates an absolute waiver of all civil liability in connection with the Program, unless a warranty or assumption of liability accompanies a copy of the Program in return for a fee. END OF TERMS AND CONDITIONS How to Apply These Terms to Your New Programs If you develop a new program, and you want it to be of the greatest possible use to the public, the best way to achieve this is to make it free software which everyone can redistribute and change under these terms. To do so, attach the following notices to the program. It is safest to attach them to the start of each source file to most effectively state the exclusion of warranty; and each file should have at least the "copyright" line and a pointer to where the full notice is found. Copyright (C) This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version. This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. You should have received a copy of the GNU General Public License along with this program. If not, see . Also add information on how to contact you by electronic and paper mail. If the program does terminal interaction, make it output a short notice like this when it starts in an interactive mode: Copyright (C) This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. This is free software, and you are welcome to redistribute it under certain conditions; type `show c' for details. The hypothetical commands `show w' and `show c' should show the appropriate parts of the General Public License. Of course, your program's commands might be different; for a GUI interface, you would use an "about box". You should also get your employer (if you work as a programmer) or school, if any, to sign a "copyright disclaimer" for the program, if necessary. For more information on this, and how to apply and follow the GNU GPL, see . The GNU General Public License does not permit incorporating your program into proprietary programs. If your program is a subroutine library, you may consider it more useful to permit linking proprietary applications with the library. If this is what you want to do, use the GNU Lesser General Public License instead of this License. But first, please read . rows-0.2.1/Makefile000066400000000000000000000010511275267602200141520ustar00rootroot00000000000000test: coverage erase nosetests -dsv --with-yanc --with-coverage --cover-package rows tests/*.py clean: find -regex '.*\.pyc' -exec rm {} \; find -regex '.*~' -exec rm {} \; rm -rf reg-settings.py rm -rf MANIFEST dist build *.egg-info rm -rf rows.1 install: make clean make uninstall python setup.py install uninstall: pip uninstall -y rows lint: pylint rows/*.py lint-tests: pylint tests/*.py man: head -1 rows.1.txt > rows.1 txt2man rows.1.txt | egrep -v '^\.TH' >> rows.1 .PHONY: test clean lint lint-tests install uninstall man rows-0.2.1/README.md000066400000000000000000000370211275267602200137770ustar00rootroot00000000000000# rows [![Join the chat at https://gitter.im/turicas/rows](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/turicas/rows?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge) [![License: GPLv3](https://img.shields.io/pypi/l/rows.svg)](https://github.com/turicas/rows/blob/develop/LICENSE) [![Current version at PyPI](https://img.shields.io/pypi/v/rows.svg)](https://pypi.python.org/pypi/rows) [![Downloads per month on PyPI](https://img.shields.io/pypi/dm/rows.svg)](https://pypi.python.org/pypi/rows) ![Supported Python Versions](https://img.shields.io/pypi/pyversions/rows.svg) ![Software status](https://img.shields.io/pypi/status/rows.svg) [![Donate](https://img.shields.io/gratipay/turicas.svg?style=social&label=Donate)](https://www.gratipay.com/turicas) No matter in which format your tabular data is: `rows` will import it, automatically detect types and give you high-level Python objects so you can start **working with the data** instead of **trying to parse it**. It is also locale-and-unicode aware. :) > Note: if you're using [rows][rows] in some project please [tell > us][rows-issue-103]! :-) ## Showcase - [Convert files tabular files using rows][rows-showcase] ([source code][rows-showcase-source]) - (Portuguese) [Talk (videos + slides) on rows by Álvaro Justen][rows-talk-pt] ## Architecture The library is composed by: - A common interface to tabular data (the `Table` class) - A set of plugins to populate `Table` objects (CSV, XLS, XLSX, HTML and XPath, Parquet, TXT, JSON, SQLite -- more coming soon!) - A set of common fields (such as `BoolField`, `IntegerField`) which know exactly how to serialize and deserialize data for each object type you'll get - A set of utilities (such as field type recognition) to help working with tabular data - A command-line interface so you can have easy access to the most used features: convert between formats, sum, join and sort tables. Just `import rows` and relax. ## Core Values - Simple, easy and flexible API - Code quality - Don't Repeat Yourself ## Installation Directly from [PyPI][pypi-rows]: pip install rows You can also install directly from the GitHub repository to have the newest features (not pretty stable) by running: pip install git+https://github.com/turicas/rows.git@develop or: git clone https://github.com/turicas/rows.git cd rows python setup.py install The plugins `csv`, `txt`, `json` and `sqlite` are built-in by default but if you want to use another one you need to explicitly install its dependencies, for example: pip install rows[html] pip install rows[xls] You also need to install some dependencies to use the [command-line interface][rows-cli]. You can do it installing the `cli` extra requirement: pip install rows[cli] And - easily - you can install all the dependencies by using the `all` extra requirement: pip install rows[all] If you use Debian [sid][debian-sid] or [testing][debian-testing] you can install it directly from the main repository by running: aptitude install python-rows # Python library only aptitude install rows # Python library + CLI And in Fedora: dnf install python-row # Python library + CLI ## Basic Usage You can create a `Table` object and populate it with some data programmatically: ```python from collections import OrderedDict from rows import fields, Table my_fields = OrderedDict([('name', fields.TextField), ('age', fields.IntegerField), ('can', fields.BoolField)]) table = Table(fields=my_fields) table.append({'name': u'Álvaro Justen', 'age': 28, 'can': False}) table.append({'name': u'Another Guy', 'age': 42, 'can': True}) ``` A common use case is to have a `list` of `dict`s -- you can also import it, and `rows` will automatically fill in the blanks (your `dict`s don't need to have the same keys) and convert data: ```python import rows data = [{'name': u'Álvaro Justen', 'age': 28, 'can': False}, {'name': u'Another Guy', 'age': 42, 'can': True},] table = rows.import_from_dicts(data) ``` In this case, `table.fields` will be created automatically (`rows` will identify the field type for each `dict` key). Then you can iterate over it: ```python def print_person(person): can = 'can' if person.can else "just can't" print u'{} is {} years old and {}'.format(person.name, person.age, can) for person in table: print_person(person) # namedtuples are returned ``` You'll see: ``` Álvaro Justen is 28 years old and just can't. Another Guy is 42 years old and can. ``` As you specified field types (`my_fields`) you don't need to insert data using the correct types. Actually you can insert strings and the library will automatically convert it for you: ```python table.append({'name': '...', 'age': '', 'can': 'false'}) print_person(table[-1]) # yes, you can index it! ``` And the output: ``` ... is None years old and just can't ``` ### Importing Data `rows` will help you importing data: its plugins will do the hard job of parsing each supported file format so you don't need to. They can help you exporting data also. For example, let's download a CSV from the Web and import it: ```python import requests import rows from io import BytesIO url = 'http://unitedstates.sunlightfoundation.com/legislators/legislators.csv' csv = requests.get(url).content # Download CSV data legislators = rows.import_from_csv(BytesIO(csv)) # already imported! print 'Hey, rows automatically identified the types:' for field_name, field_type in legislators.fields.items(): print '{} is {}'.format(field_name, field_type) ``` And you'll see something like this: ``` [...] in_office is gender is [...] birthdate is ``` We can then work on this data: ```python women_in_office = filter(lambda row: row.in_office and row.gender == 'F', legislators) men_in_office = filter(lambda row: row.in_office and row.gender == 'M', legislators) print 'Women vs Men: {} vs {}'.format(len(women_in_office), len(men_in_office)) ``` Then you'll see effects of our sexist society: ``` Women vs Men: 108 vs 432 ``` Now, let's compare ages: ```python legislators.order_by('birthdate') older, younger = legislators[-1], legislators[0] print '{}, {} is older than {}, {}'.format(older.lastname, older.firstname, younger.lastname, younger.firstname) ``` The output: ``` Stefanik, Elise is older than Byrd, Robert ``` You can also get a whole column, like this: ```python >>> legislators[u'gender'] [u'M', u'M', u'M', u'M', u'M', u'M', u'M', u'M', u'M', u'M', u'M', u'M', u'M', u'M', u'F', u'M', ...] ``` And change the whole column (or add a new one): ```python >>> legislators[u'gender'] = [u'male' if gender == u'M' else u'female' for gender in legislators[u'gender']] >>> legislators[u'gender'] [u'male', u'male', u'male', u'male', u'male', u'male', u'male', u'male', u'male', u'male', u'male', u'male', u'female', u'male', ...] ``` Or delete it: ```python >>> u'gender' in legislators.field_names True >>> del legislators[u'gender'] >>> u'gender' in legislators.field_names False >>> legislators[0].gender [...] AttributeError: 'Row' object has no attribute 'gender' ``` > Note that **native Python objects** are returned for each row inside a > `namedtuple`! The library recognizes each field type and converts it > *automagically* no matter which plugin you're using to import the data. #### Common Parameters Each plugin has its own parameters (like `index` in `import_from_html` and `sheet_name` in `import_from_xls`) but all plugins create a `rows.Table` object so they also have some common parameters you can pass to `import_from_X`. They are: - `fields`: an `OrderedDict` with field names and types (disable automatic detection of types). - `skip_header`: Ignore header row. Only used if `fields` is not `None`. Default: `True`. - `import_fields`: a `list` with field names to import (other fields will be ignored) -- fields will be imported in this order. - `samples`: number of sample rows to use on field type autodetect algorithm. Default: `None` (use all rows). ### Exporting Data If you have a `Table` object you can export it to all available plugins which have the "export" feature. Let's use the HTML plugin: ```python rows.export_to_html(legislators, 'legislators.html') ``` And you'll get: ``` $ head legislators.html ``` Now you have finished the quickstart guide. See the `examples` folder for more examples. ### Available Plugins The idea behing plugins is very simple: you write a little piece of code which extracts data from/to some specific format and the library will do the other tasks for you. So writing a plugin is as easy as reading from/writing to the file format you want. Currently we have the following plugins: - CSV: use `rows.import_from_csv` and `rows.export_to_csv` (dependencies are installed by default) - TXT: use `rows.export_to_txt` (no dependencies) - JSON: use `rows.import_from_json` and `rows.export_to_json` (no dependencies) - HTML: use `rows.import_from_html` and `rows.export_to_html` (dependencies must be installed with `pip install rows[html]`) - XPath: use `rows.import_from_xpath` passing the following arguments: `filename_or_fobj`, `rows_xpath` and `fields_xpath` (dependencies must be installed with `pip install rows[xpath]`) -- see an example in `examples/library/ecuador_radiodifusoras.py`. - Parquet: use `rows.import_from_parquet` passing the filename (dependencies must be installed with `pip install rows[parquet]` and if the data is compressed using snappy you also need to install `rows[parquet-snappy]` and the `libsnappy-dev` system library) -- read [this blog post][blog-rows-parquet] for more details and one example - XLS: use `rows.import_from_xls` and `rows.export_to_xls` (dependencies must be installed with `pip install rows[xls]`) - XLSX: use `rows.import_from_xlsx` and `rows.export_to_xlsx` (dependencies must be installed with `pip install rows[xlsx]`) - SQLite: use `rows.import_from_sqlite` and `rows.export_to_sqlite` (no dependencies) - ODS: use `rows.import_from_ods` (dependencies must be installed with `pip install rows[ods]`) More plugins are coming (like PDF, DBF etc.) and we're going to re-design the plugin interface so you can create your own easily. Feel free to contribute. :-) #### Common Parameters Each plugin has its own parameters (like `encoding` in `import_from_html` and `sheet_name` in `import_from_xls`) but all plugins use the same mechanism to prepare a `rows.Table` before exporting, so they also have some common parameters you can pass to `export_to_X`. They are: - `export_fields`: a `list` with field names to export (other fields will be ignored) -- fields will be exported in this order. ## Command-Line Interface `rows` exposes a command-line interface with the common operations such as convert data between plugins, sum, sort and join `Table`s. Run `rows --help` to see the available commands and take a look at `rows/cli.py`. We still need to improve the CLI docs, sorry. ## Locale Many fields inside `rows.fields` are locale-aware. If you have some data using Brazilian Portuguese number formatting, for example (`,` as decimal separators and `.` as thousands separator) you can configure this into the library and `rows` will automatically understand these numbers! Let's see it working by extracting the population of cities in Rio de Janeiro state: ```python import locale import requests import rows from io import BytesIO url = 'http://cidades.ibge.gov.br/comparamun/compara.php?idtema=1&codv=v01&coduf=33' html = requests.get(url).content with rows.locale_context(name='pt_BR.UTF-8', category=locale.LC_NUMERIC): rio = rows.import_from_html(BytesIO(html)) total_population = sum(city.pessoas for city in rio) # 'pessoas' is the fieldname related to the number of people in each city print 'Rio de Janeiro has {} inhabitants'.format(total_population) ``` The column `pessoas` will be imported as an `IntegerField` and the result is: ``` Rio de Janeiro has 15989929 inhabitants ``` ## Operations Available operations: `join`, `transform` and `serialize`. TODO. See `rows/operations.py`. ## Developing Create the virtualenv: mkvirtualenv rows Install all plugins' dependencies: pip install --editable .[all] Install development dependencies: pip install -r requirements-development.txt Run tests: make test or (if you don't have `make`): nosetests -dsv --with-yanc --with-coverage --cover-package rows tests/*.py To create the man page you'll need to install [txt2man][txt2man]. In Debian (and Debian-based distributions) you can install by running: ```bash aptitude install txt2man ``` Then, you can generate the `rows.1` file by running: ```bash make man ``` ## Similar Projects - [OKFN's goodtables](https://github.com/okfn/goodtables) - [OKFN's messytables](https://github.com/okfn/messytables) - [csvcat](https://pypi.python.org/pypi/csvcat) - [csvstudio](https://github.com/mdipierro/csvstudio) - [odo](https://github.com/blaze/odo) - [pandashells](https://github.com/robdmc/pandashells) (and pandas DataFrame) - [tablib](https://tablib.readthedocs.org/en/latest/) - [textql](https://github.com/dinedal/textql) ## Related Projects - [libextract](https://github.com/datalib/libextract) - [scrapy](http://scrapy.org/) - [grablib](https://github.com/lorien/grab) - [streamtools](http://blog.nytlabs.com/streamtools/) - [multicorn](https://github.com/Kozea/Multicorn) - [webscraper.io](http://webscraper.io/) - [import.io](http://import.io/) - [Tabula](http://tabula.technology/) ## Known Issues - [Lack of Python 3 support][rows-issue-46] - [Create a better plugin interface so anyone can benefit of it][rows-issue-27] - [Create an object to represent a set of `rows.Table`s, like `TableSet`][rows-issue-47] - Performance: the automatic type detection algorithm can cost time: it iterates over all rows to determine the type of each column. You can disable it by passing `samples=0` to any `import_from_*` function or either changing the number of sample rows (any positive number is accepted). - [Code design issues][rows-issue-31] ## Semantic Versioning `rows` uses [semantic versioning][semver]. Note that it means we do not guarantee API backwards compatibility on `0.x.y` versions. ## License This library is released under the [GNU General Public License version 3][gpl3]. [blog-rows-parquet]: http://blog.justen.eng.br/2016/03/reading-parquet-files-in-python-with-rows.html [debian-sid]: https://www.debian.org/releases/sid/ [debian-testing]: https://www.debian.org/releases/testing/ [gpl3]: http://www.gnu.org/licenses/gpl-3.0.html [pypi-rows]: http://pypi.python.org/pypi/rows [rows-cli]: #command-line-interface [rows-issue-103]: https://github.com/turicas/rows/issues/103 [rows-issue-27]: https://github.com/turicas/rows/issues/27 [rows-issue-31]: https://github.com/turicas/rows/issues/31 [rows-issue-46]: https://github.com/turicas/rows/issues/46 [rows-issue-47]: https://github.com/turicas/rows/issues/47 [rows-showcase-source]: https://github.com/leonardocsantoss/django-rows [rows-showcase]: http://rows.irdx.com.br/ [rows-talk-pt]: http://blog.justen.eng.br/2016/05/dados-tabulares-a-maneira-pythonica.html [rows]: https://github.com/turicas/rows/ [semver]: http://semver.org/ [txt2man]: http://mvertes.free.fr/ rows-0.2.1/examples/000077500000000000000000000000001275267602200143335ustar00rootroot00000000000000rows-0.2.1/examples/cli/000077500000000000000000000000001275267602200151025ustar00rootroot00000000000000rows-0.2.1/examples/cli/convert.sh000077500000000000000000000013271275267602200171240ustar00rootroot00000000000000#!/bin/bash URL="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=1&codv=v01&coduf=43" LOCALE="pt_BR.UTF-8" FILENAME="populacao-rs" rows convert --input-locale=$LOCALE --input-encoding=utf-8 $URL $FILENAME.csv rows convert $FILENAME.csv $FILENAME.html rows convert $FILENAME.html $FILENAME.xls rows convert $FILENAME.xls $FILENAME.txt rows convert $FILENAME.txt $FILENAME.xlsx rows convert $FILENAME.xlsx $FILENAME.sqlite rows convert $FILENAME.sqlite $FILENAME.json # When converting to JSON we cannot guarantee field order! # `convert` can also sort the data before saving it into the CSV file rows convert --input-locale=$LOCALE --input-encoding=utf-8 \ --order-by=^pessoas $URL $FILENAME-sorted.csv rows-0.2.1/examples/cli/join.sh000077500000000000000000000002461275267602200164020ustar00rootroot00000000000000#!/bin/bash KEYS="uf,municipio" SOURCE1="populacao-sudeste.csv" SOURCE2="area-sudeste.csv" DESTINATION="sudeste.csv" rows join $KEYS $SOURCE1 $SOURCE2 $DESTINATION rows-0.2.1/examples/cli/query.sh000077500000000000000000000023021275267602200166030ustar00rootroot00000000000000#!/bin/bash # This script will run rows' "query" subcommand passing the URL of two HTML # sources, a SQL query and a output CSV filename. rows CLI will: # - Download each file, identify its format (HTML) and import as a table # - Convert the two tables into one SQLite in-memory database # - Run the query into the database # - Export the results to a CSV file # Rio de Janeiro: inhabitants (per city) SOURCE1="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=1&codv=v01&coduf=33" # Rio de Janeiro: area in km² (per city) SOURCE2="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=16&codv=v01&coduf=33" LOCALE="pt_BR.UTF-8" SOURCES="$SOURCE1 $SOURCE2" # $SOURCE1 (inhabitants) will be "table1" # $SOURCE2 (area) will be "table2" QUERY="SELECT table1.uf AS state, table1.municipio AS city, table1.pessoas AS inhabitants, table2.km2 as area, (table1.pessoas / table2.km2) AS demographic_density FROM table1, table2 WHERE table1.uf = table2.uf AND table1.municipio = table2.municipio" OUTPUT="rj-density.csv" rows query --input-locale=$LOCALE --input-encoding=utf-8 "$QUERY" $SOURCES \ --output=$OUTPUT rows-0.2.1/examples/cli/sum.sh000077500000000000000000000020661275267602200162510ustar00rootroot00000000000000#!/bin/bash # population SOURCE1="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=1&codv=v01&coduf=33" SOURCE2="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=1&codv=v01&coduf=35" SOURCE3="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=1&codv=v01&coduf=31" SOURCE4="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=1&codv=v01&coduf=32" DESTINATION="populacao-sudeste.csv" LOCALE="pt_BR.UTF-8" rows sum --input-locale=$LOCALE --input-encoding=utf-8 \ $SOURCE1 $SOURCE2 $SOURCE3 $SOURCE4 \ $DESTINATION # area SOURCE5="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=16&codv=v01&coduf=33" SOURCE6="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=16&codv=v01&coduf=35" SOURCE7="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=16&codv=v01&coduf=31" SOURCE8="http://cidades.ibge.gov.br/comparamun/compara.php?idtema=16&codv=v01&coduf=32" DESTINATION="area-sudeste.csv" rows sum --input-locale=$LOCALE --input-encoding=utf-8 \ $SOURCE5 $SOURCE6 $SOURCE7 $SOURCE8 \ $DESTINATION rows-0.2.1/examples/data/000077500000000000000000000000001275267602200152445ustar00rootroot00000000000000rows-0.2.1/examples/data/tesouro-direto.csv000066400000000000000000000035521275267602200207520ustar00rootroot00000000000000timestamp,titulo,vencimento,taxa_compra,taxa_venda,preco_compra,preco_venda 2015-11-06T17:43:00,Tesouro IPCA+ com Juros Semestrais 2017 (NTNB),2017-05-15,7.02%,6.3%,0.0,2792.97 2015-11-06T17:43:00,Tesouro IPCA+ 2019 (NTNB Princ),2019-05-15,7.02%,7.06%,2150.33,2147.53 2015-11-06T17:43:00,Tesouro IPCA+ com Juros Semestrais 2020 (NTNB),2020-08-15,7.14%,7.18%,2644.22,2640.14 2015-11-06T17:43:00,Tesouro IPCA+ com Juros Semestrais 2024 (NTNB),2024-08-15,7.02%,7.39%,0.0,2531.91 2015-11-06T17:43:00,Tesouro IPCA+ 2024 (NTNB Princ),2024-08-15,7.38%,7.44%,1463.24,1456.12 2015-11-06T17:43:00,Tesouro IPCA+ com Juros Semestrais 2035 (NTNB),2035-05-15,7.03%,7.11%,2520.76,2500.2 2015-11-06T17:43:00,Tesouro IPCA+ 2035 (NTNB Princ),2035-05-15,6.97%,7.05%,735.21,724.6 2015-11-06T17:43:00,Tesouro IPCA+ com Juros Semestrais 2045 (NTNB),2045-05-15,7.02%,7.1%,0.0,2449.17 2015-11-06T17:43:00,Tesouro IPCA+ com Juros Semestrais 2050 (NTNB),2050-08-15,6.94%,7.04%,2440.99,2409.92 2015-11-06T17:43:00,Tesouro Prefixado 2016 (LTN),2016-01-01,7.02%,14.27%,0.0,980.08 2015-11-06T17:43:00,Tesouro Prefixado com Juros Semestrais 2017 (NTNF),2017-01-01,7.02%,15.32%,0.0,982.94 2015-11-06T17:43:00,Tesouro Prefixado 2017 (LTN),2017-01-01,7.02%,15.33%,0.0,849.1 2015-11-06T17:43:00,Tesouro Prefixado 2018 (LTN),2018-01-01,15.59%,15.65%,733.95,733.14 2015-11-06T17:43:00,Tesouro Prefixado 2021 (LTN),2021-01-01,15.58%,15.64%,475.99,474.72 2015-11-06T17:43:00,Tesouro Prefixado com Juros Semestrais 2021 (NTNF),2021-01-01,7.02%,15.61%,0.0,851.42 2015-11-06T17:43:00,Tesouro Prefixado com Juros Semestrais 2023 (NTNF),2023-01-01,7.02%,15.61%,0.0,809.9 2015-11-06T17:43:00,Tesouro Prefixado com Juros Semestrais 2025 (NTNF),2025-01-01,15.59%,15.65%,779.41,777.19 2015-11-06T17:43:00,Tesouro Selic 2017 (LFT),2017-03-07,7.02%,0.02%,0.0,7259.64 2015-11-06T17:43:00,Tesouro Selic 2021 (LFT),2021-03-01,0%,0.04%,7261.57,7246.25 rows-0.2.1/examples/library/000077500000000000000000000000001275267602200157775ustar00rootroot00000000000000rows-0.2.1/examples/library/airports.py000066400000000000000000000013411275267602200202130ustar00rootroot00000000000000# coding: utf-8 # This script downloads the list of airport codes and cities from # worldnetlogistics.com and creates a `dict` called `code_to_city` with the # correspondent mapping. # # Install dependencies: # pip install requests rows # or # aptitude install python-requests python-rows from io import BytesIO import requests import rows # Get data url = 'http://www.worldnetlogistics.com/information/iata-city-airport-codes/' response = requests.get(url) html = response.content # Parse/normalize data table = rows.import_from_html(BytesIO(html), index=4) code_to_city = {} for row in table: code_to_city[row.code] = row.city if row.city_2 is not None: code_to_city[row.code_2] = row.city_2 # Have fun! rows-0.2.1/examples/library/brazilian_cities_wikipedia.py000066400000000000000000000023451275267602200237160ustar00rootroot00000000000000# coding: utf-8 from __future__ import unicode_literals import re from collections import OrderedDict from io import BytesIO from urllib2 import urlparse import requests import rows # Get data from Portuguese Wikipedia city_list_url = 'https://pt.wikipedia.org/wiki/Lista_de_munic%C3%ADpios_do_Brasil' response = requests.get(city_list_url) html = response.content # Extract desired data using XPath cities = rows.import_from_xpath( BytesIO(html), rows_xpath='//table/tr/td/ul/li', fields_xpath=OrderedDict([('name', './/text()'), ('link', './/a/@href')])) regexp_city_state = re.compile(r'(.*) \(([A-Z]{2})\)') def transform(row, table): 'Transform row "link" into full URL and add "state" based on "name"' data = row._asdict() data['link'] = urlparse.urljoin('https://pt.wikipedia.org', data['link']) data['name'], data['state'] = regexp_city_state.findall(data['name'])[0] return data new_fields = OrderedDict() new_fields['name'] = cities.fields['name'] new_fields['state'] = rows.fields.TextField # new field new_fields['link'] = cities.fields['link'] cities = rows.transform(new_fields, transform, cities) rows.export_to_csv(cities, 'brazilian-cities.csv') rows-0.2.1/examples/library/ecuador_radiodifusoras.py000066400000000000000000000014751275267602200231000ustar00rootroot00000000000000# coding: utf-8 import sys from collections import OrderedDict import rows # taken from: # http://www.supercom.gob.ec/es/informate-y-participa/directorio-de-medios/21-radiodifusoras filename = 'tests/data/ecuador-medios-radiodifusoras.html' rows_xpath = '//*[@class="entry-container"]/*[@class="row-fluid"]/*[@class="span6"]' fields_xpath = OrderedDict([ ('url', '//h2/a/@href'), ('name', '//h2/a/text()'), ('address', '//div[@class="spField field_direccion"]/text()'), ('phone', '//div[@class="spField field_telefono"]/text()'), ('website', '//div[@class="spField field_sitio_web"]/text()'), ('email', '//div[@class="spField field_email"]/text()'), ]) table = rows.import_from_xpath(filename, rows_xpath, fields_xpath) rows.export_to_csv(table, 'ecuador-radiodifusoras.csv') rows-0.2.1/examples/library/extract_links.py000066400000000000000000000015741275267602200212320ustar00rootroot00000000000000# coding: utf-8 from __future__ import unicode_literals from io import BytesIO import requests import rows from rows.plugins.html import extract_links, extract_text # Get the HTML url = 'http://wnpp.debian.net/' response = requests.get(url) html = response.content # Import data, preserving cell's HTML packages = rows.import_from_html(BytesIO(html), index=10, preserve_html=True) def transform(row, table): 'Extract links from "project" field and remove HTML from all' data = row._asdict() data['links'] = ' '.join(extract_links(row.project)) for key, value in data.items(): if isinstance(value, basestring): data[key] = extract_text(value) return data new_fields = packages.fields.copy() new_fields['links'] = rows.fields.TextField packages = rows.transform(new_fields, transform, packages) rows.export_to_csv(packages, 'debian-wnpp.csv') rows-0.2.1/examples/library/organizaciones.py000066400000000000000000000014301275267602200213620ustar00rootroot00000000000000# coding: utf-8 # This example downloads some Ecuatorian organizations in JSON, extracts the # desired `dict`s, then import then into a `rows.Table` object to finally # export as XLS. # Install dependencies by running: pip install rows[xls] import json import urllib import rows URL = 'http://www.onumujeres-ecuador.org/geovisor/data/organizaciones.php' def download_organizations(): 'Download organizations JSON and extract its properties' page = urllib.urlopen(URL) data = json.loads(page.read()) organizations = [organization['properties'] for organization in data['features']] return rows.import_from_dicts(organizations) if __name__ == '__main__': table = download_organizations() rows.export_to_xls(table, 'organizaciones.xls') rows-0.2.1/examples/library/slip_opinions.py000066400000000000000000000010441275267602200212350ustar00rootroot00000000000000# coding: utf-8 # This example was based on: # https://github.com/compjour/search-script-scrape/blob/master/scripts/42.py from io import BytesIO from urlparse import urljoin import requests import rows from rows.plugins.html import tag_to_dict url = 'http://www.supremecourt.gov/opinions/slipopinions.aspx' html = requests.get(url).content table = rows.import_from_html(BytesIO(html), index=1, preserve_html=True) for element in table: attributes = tag_to_dict(element.name) print attributes['text'], urljoin(url, attributes['href']) rows-0.2.1/examples/library/tests_uwsgi_log.py000066400000000000000000000034071275267602200215760ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . import datetime import unittest from rows.table import Table from uwsgi_log_plugin import import_from_uwsgi_log class UwsgiLogPluginTestCase(unittest.TestCase): def test_import_from_uwsgi_log(self): filename = 'uwsgi.log' table = import_from_uwsgi_log(filename) self.assertEqual(len(table), 2) first = table.Row(pid=879, ip=u'127.0.0.1', datetime=datetime.datetime(2015, 6, 1, 11, 23, 16), http_verb=u'GET', http_path=u'/something', generation_time=0.17378, http_version=1.1, http_status=404) second = table.Row(pid=31460, ip=u'127.0.1.1', datetime=datetime.datetime(2015, 7, 15, 23, 49, 20), http_verb=u'OPTIONS', http_path=u'/about', generation_time=0.000466, http_version=1.1, http_status=200) self.assertEqual(table[0], first) self.assertEqual(table[1], second) rows-0.2.1/examples/library/usa_legislators.py000066400000000000000000000022701275267602200215520ustar00rootroot00000000000000# coding: utf-8 # This example was based on: # https://github.com/compjour/search-script-scrape/blob/master/scripts/101.py from io import BytesIO import requests import rows # Capture url = 'http://unitedstates.sunlightfoundation.com/legislators/legislators.csv' csv = BytesIO(requests.get(url).content) # Normalize table = rows.import_from_csv(csv) # Analyze total = len(table) total_in_office = len(filter(lambda row: row.in_office, table)) men = len(filter(lambda row: row.gender == 'M', table)) men_in_office = len(filter(lambda row: row.gender == 'M' and row.in_office, table)) women = len(filter(lambda row: row.gender == 'F', table)) women_in_office = len(filter(lambda row: row.gender == 'F' and row.in_office, table)) # View print (' Men: {}/{} ({:02.2f}%), in office: {}/{} ({:02.2f}%)' .format(men, total, 100 * men / float(total), men_in_office, total_in_office, 100 * men_in_office / float(total))) print ('Women: {}/{} ({:02.2f}%), in office: {}/{} ({:02.2f}%)' .format(women, total, 100 * women / float(total), women_in_office, total_in_office, 100 * women_in_office / float(total))) rows-0.2.1/examples/library/uwsgi.log000066400000000000000000000075351275267602200176520ustar00rootroot00000000000000*** Starting uWSGI 2.0.8 (64bit) on [Mon Jun 1 11:08:58 2015] *** compiled with version: 4.8.2 on 01 June 2015 11:01:28 os: Linux-3.13.0-48-generic #80-Ubuntu SMP Thu Mar 12 11:16:15 UTC 2015 nodename: localhost.localdomain machine: x86_64 clock source: unix detected number of CPU cores: 1 current working directory: /home/ubuntu writing pidfile to /home/ubuntu/uwsgi/uwsgi.pid detected binary path: /home/ubuntu/venv/bin/uwsgi !!! no internal routing support, rebuild with pcre support !!! chdir() to /home/ubuntu/repo your processes number limit is 7862 your memory page size is 4096 bytes detected max file descriptor number: 1024 lock engine: pthread robust mutexes thunder lock: disabled (you can enable it with --thunder-lock) uwsgi socket 0 bound to TCP address 127.0.0.1:8001 fd 3 Python version: 2.7.6 (default, Mar 22 2014, 23:03:41) [GCC 4.8.2] Set PythonHome to /home/ubuntu/venv *** Python threads support is disabled. You can enable it with --enable-threads *** Python main interpreter initialized at 0x14d9cf0 your server socket listen backlog is limited to 100 connections your mercy for graceful operations on workers is 60 seconds mapped 363840 bytes (355 KB) for 4 cores *** Operational MODE: preforking *** WSGI app 0 (mountpoint='') ready in 0 seconds on interpreter 0x14d9cf0 pid: 32310 (default app) *** uWSGI is running in multiple interpreter mode *** spawned uWSGI master process (pid: 32310) spawned uWSGI worker 1 (pid: 32317, cores: 1) spawned uWSGI worker 2 (pid: 32318, cores: 1) spawned uWSGI worker 3 (pid: 32319, cores: 1) spawned uWSGI worker 4 (pid: 32320, cores: 1) *** Stats server enabled on 127.0.0.1:8002 fd: 16 *** SIGINT/SIGQUIT received...killing workers... worker 1 buried after 1 seconds worker 2 buried after 1 seconds worker 3 buried after 1 seconds worker 4 buried after 1 seconds goodbye to uWSGI. VACUUM: pidfile removed. *** Starting uWSGI 2.0.8 (64bit) on [Mon Jun 1 11:20:46 2015] *** compiled with version: 4.8.2 on 01 June 2015 11:01:28 os: Linux-3.13.0-48-generic #80-Ubuntu SMP Thu Mar 12 11:16:15 UTC 2015 nodename: localhost.localdomain machine: x86_64 clock source: unix detected number of CPU cores: 1 current working directory: /home/ubuntu writing pidfile to /home/ubuntu/uwsgi/uwsgi.pid detected binary path: /home/ubuntu/venv/bin/uwsgi !!! no internal routing support, rebuild with pcre support !!! chdir() to /home/ubuntu/repo your processes number limit is 7862 your memory page size is 4096 bytes detected max file descriptor number: 1024 lock engine: pthread robust mutexes thunder lock: disabled (you can enable it with --thunder-lock) uwsgi socket 0 bound to TCP address 127.0.0.1:8001 fd 3 Python version: 2.7.6 (default, Mar 22 2014, 23:03:41) [GCC 4.8.2] Set PythonHome to /home/ubuntu/venv *** Python threads support is disabled. You can enable it with --enable-threads *** Python main interpreter initialized at 0xf6dcf0 your server socket listen backlog is limited to 100 connections your mercy for graceful operations on workers is 60 seconds mapped 363840 bytes (355 KB) for 4 cores *** Operational MODE: preforking *** WSGI app 0 (mountpoint='') ready in 1 seconds on interpreter 0xf6dcf0 pid: 872 (default app) *** uWSGI is running in multiple interpreter mode *** spawned uWSGI master process (pid: 872) spawned uWSGI worker 1 (pid: 879, cores: 1) spawned uWSGI worker 2 (pid: 880, cores: 1) spawned uWSGI worker 3 (pid: 881, cores: 1) spawned uWSGI worker 4 (pid: 882, cores: 1) *** Stats server enabled on 127.0.0.1:8002 fd: 16 *** [pid: 879|app: 0|req: 1/1] 127.0.0.1 () {40 vars in 743 bytes} [Mon Jun 1 11:23:16 2015] GET /something => generated 93 bytes in 173780 micros (HTTP/1.1 404) 2 headers in 80 bytes (1 switches on core 0) [pid: 31460|app: 0|req: 21/2786] 127.0.1.1 () {46 vars in 840 bytes} [Wed Jul 15 23:49:20 2015] OPTIONS /about => generated 0 bytes in 466 micros (HTTP/1.1 200) 6 headers in 327 bytes (1 switches on core 0) rows-0.2.1/examples/library/uwsgi_log_plugin.py000066400000000000000000000035421275267602200217320ustar00rootroot00000000000000# coding: utf-8 from __future__ import unicode_literals import datetime import re from collections import OrderedDict import rows.fields from rows.table import Table REGEXP_UWSGI_LOG = re.compile(r'\[pid: ([0-9]+)\|app: [0-9]+\|req: ' r'[0-9]+/[0-9]+\] ' r'([0-9]+\.[0-9]+\.[0-9]+\.[0-9]+) .+ \[(.+)\] ' r'([^ ]+) (.+) => generated .+ in ([0-9]+) ' r'micros \(HTTP/([^ ]+) ([^)]+)\)') UWSGI_FIELDS = OrderedDict([('pid', rows.fields.IntegerField), ('ip', rows.fields.TextField), ('datetime', rows.fields.DatetimeField), ('http_verb', rows.fields.TextField), ('http_path', rows.fields.TextField), ('generation_time', rows.fields.FloatField), ('http_version', rows.fields.FloatField), ('http_status', rows.fields.IntegerField)]) UWSGI_DATETIME_FORMAT = '%a %b %d %H:%M:%S %Y' strptime = datetime.datetime.strptime def import_from_uwsgi_log(filename): fields = UWSGI_FIELDS.keys() table = Table(fields=UWSGI_FIELDS) with open(filename) as fobj: for line in fobj: result = REGEXP_UWSGI_LOG.findall(line) if result: data = list(result[0]) # Convert datetime data[2] = strptime(data[2], UWSGI_DATETIME_FORMAT) # Convert generation time (micros -> seconds) data[5] = float(data[5]) / 1000000 table.append({field_name: value for field_name, value in zip(fields, data)}) return table if __name__ == '__main__': table = import_from_uwsgi_log('uwsgi.log') for row in table: print row rows-0.2.1/requirements-development.txt000066400000000000000000000002741275267602200203240ustar00rootroot00000000000000-r requirements.txt # Everything except install_requires click lxml openpyxl parquet requests xlrd xlwt file-magic # Test tools coverage ipdb mock nose pylint yanc # PyPI tools pypissh rows-0.2.1/requirements.txt000066400000000000000000000000051275267602200157740ustar00rootroot00000000000000-e . rows-0.2.1/rows.1.txt000066400000000000000000000055011275267602200144100ustar00rootroot00000000000000.TH ROWS "1" "Sep 2015" "ROWS 0.1.0" "common, beautiful interface to tabular data, no matter the format" NAME rows - common, beautiful interface to tabular data, no matter the format SYNOPSIS rows [OPTIONS] COMMAND [ARGS] ... DESCRIPTION No matter in which format your tabular data is: rows will import it, automatically detect types and give you high-level Python objects so you can start working with the data instead of trying to parse it. It is also locale-and-unicode aware. OPTIONS --help Show this message and exit COMMANDS . convert - Convert table on `source` URI to... join - Join tables from `source` URIs using `key(s)`... sort - Sort from `source` by `key(s)` and save into... sum - Sum tables from `source` URIs and save into... SYNOPSIS rows convert [OPTIONS] SOURCE DESTINATION DESCRIPTION Convert table on `source` URI to `destination` OPTIONS --input-encoding TEXT --output-encoding TEXT --input-locale TEXT --output-locale TEXT --help Show this message and exit. SYNOPSIS rows join [OPTIONS] KEYS SOURCES ... DESTINATION DESCRIPTION Join tables from `source` URIs using `key(s)` to group rows and save into destination` OPTIONS --input-encoding TEXT --output-encoding TEXT --input-locale TEXT --output-locale TEXT --help Show this message and exit. SYNOPSIS rows sort [OPTIONS] KEY SOURCE DESTINATION DESCRIPTION Sort from `source` by `key(s)` and save into `destination` OPTIONS --input-encoding TEXT --output-encoding TEXT --input-locale TEXT --output-locale TEXT --help Show this message and exit. SYNOPSIS rows sum [OPTIONS] SOURCES ... DESTINATION DESCRIPTION Sum tables from `source` URIs and save into `destination` OPTIONS --input-encoding TEXT --output-encoding TEXT --input-locale TEXT --output-locale TEXT --help Show this message and exit. EXAMPLES - To export csv from site and converting locales from pt_BR to en both UTF-8 rows convert \-\-input-locale pt_BR.UTF-8 \-\-output-locale en.UTF-8 "" data.csv - To export xls from site and no changes locales rows convert "" data.xls - To convert csv to xls rows convert file.csv file.xls REPORTING BUGS To report a bug please visit rows' issue tracking system at . AUTHOR Written by Álvaro Justen . This manual page was written by Paulo Roberto Alves de Oliveira (aka kretcheu) for the Debian project (but may be used by others). COPYRIGHT Copyright © 2014-2015 Álvaro Justen. License GPLv3+: GNU GPL version 3 or later . This is free software: you are free to change and redistribute it. There is NO WARRANTY, to the extent permitted by law. rows-0.2.1/rows/000077500000000000000000000000001275267602200135075ustar00rootroot00000000000000rows-0.2.1/rows/__init__.py000066400000000000000000000036661275267602200156330ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals # General imports from rows.operations import join, transform, transpose from rows.table import Table, FlexibleTable from rows.localization import locale_context # Don't have dependencies or dependencies installed on `install_requires` from rows.plugins._json import import_from_json, export_to_json from rows.plugins.dicts import import_from_dicts, export_to_dicts from rows.plugins.csv import import_from_csv, export_to_csv from rows.plugins.txt import import_from_txt, export_to_txt # Have dependencies try: from rows.plugins.html import import_from_html, export_to_html from rows.plugins.xpath import import_from_xpath except ImportError: pass try: from rows.plugins.ods import import_from_ods except ImportError: pass try: from rows.plugins.sqlite import import_from_sqlite, export_to_sqlite except ImportError: pass try: from rows.plugins.xls import import_from_xls, export_to_xls except ImportError: pass try: from rows.plugins.xlsx import import_from_xlsx, export_to_xlsx except ImportError: pass try: from rows.plugins._parquet import import_from_parquet except ImportError: pass __version__ = '0.2.1' rows-0.2.1/rows/cli.py000077500000000000000000000331551275267602200146420ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2016 Álvaro Justen # # 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 . # TODO: define exit codes # TODO: move default options to base command # TODO: may move all 'destination' to '--output' # TODO: test this whole module # TODO: add option to pass 'create_table' options in command-line (like force # fields) import shlex import sqlite3 import sys from io import BytesIO import click import requests.exceptions import rows from rows.utils import (detect_source, export_to_uri, import_from_source, import_from_uri) from rows.plugins.utils import make_header DEFAULT_INPUT_ENCODING = 'utf-8' DEFAULT_OUTPUT_ENCODING = 'utf-8' DEFAULT_INPUT_LOCALE = 'C' DEFAULT_OUTPUT_LOCALE = 'C' def _import_table(source, encoding, verify_ssl=True, *args, **kwargs): try: table = import_from_uri(source, default_encoding=DEFAULT_INPUT_ENCODING, verify_ssl=verify_ssl, encoding=encoding, *args, **kwargs) except requests.exceptions.SSLError: click.echo('ERROR: SSL verification failed! ' 'Use `--verify-ssl=no` if you want to ignore.', err=True) sys.exit(2) else: return table def _get_field_names(field_names, table_field_names, permit_not=False): new_field_names = make_header(field_names.split(','), permit_not=permit_not) if not permit_not: diff = set(new_field_names) - set(table_field_names) else: diff = set(field_name.replace('^', '') for field_name in new_field_names) - set(table_field_names) if diff: missing = ', '.join(['"{}"'.format(field) for field in diff]) click.echo('Table does not have fields: {}'.format(missing), err=True) sys.exit(1) else: return new_field_names @click.group() @click.version_option(version=rows.__version__, prog_name='rows') def cli(): pass @cli.command(help='Convert table on `source` URI to `destination`') @click.option('--input-encoding') @click.option('--output-encoding') @click.option('--input-locale') @click.option('--output-locale') @click.option('--verify-ssl', default=True, type=bool) @click.option('--order-by') @click.argument('source') @click.argument('destination') def convert(input_encoding, output_encoding, input_locale, output_locale, verify_ssl, order_by, source, destination): # TODO: may use sys.stdout.encoding if output_file = '-' output_encoding = output_encoding or DEFAULT_OUTPUT_ENCODING if input_locale is not None: with rows.locale_context(input_locale): table = _import_table(source, encoding=input_encoding, verify_ssl=verify_ssl) else: table = _import_table(source, encoding=input_encoding, verify_ssl=verify_ssl) if order_by is not None: order_by = _get_field_names(order_by, table.fields.keys(), permit_not=True) # TODO: use complete list of `order_by` fields table.order_by(order_by[0].replace('^', '-')) if output_locale is not None: with rows.locale_context(output_locale): export_to_uri(table, destination, encoding=output_encoding) else: export_to_uri(table, destination, encoding=output_encoding) @cli.command(help='Join tables from `source` URIs using `key(s)` to group ' 'rows and save into `destination`') @click.option('--input-encoding') @click.option('--output-encoding') @click.option('--input-locale') @click.option('--output-locale') @click.option('--verify-ssl', default=True, type=bool) @click.option('--order-by') @click.argument('keys') @click.argument('sources', nargs=-1, required=True) @click.argument('destination') def join(input_encoding, output_encoding, input_locale, output_locale, verify_ssl, order_by, keys, sources, destination): # TODO: may use sys.stdout.encoding if output_file = '-' output_encoding = output_encoding or DEFAULT_OUTPUT_ENCODING keys = [key.strip() for key in keys.split(',')] if input_locale is not None: with rows.locale_context(input_locale): tables = [_import_table(source, encoding=input_encoding, verify_ssl=verify_ssl) for source in sources] else: tables = [_import_table(source, encoding=input_encoding, verify_ssl=verify_ssl) for source in sources] result = rows.join(keys, tables) if order_by is not None: order_by = _get_field_names(order_by, result.fields.keys(), permit_not=True) # TODO: use complete list of `order_by` fields result.order_by(order_by[0].replace('^', '-')) if output_locale is not None: with rows.locale_context(output_locale): export_to_uri(result, destination, encoding=output_encoding) else: export_to_uri(result, destination, encoding=output_encoding) @cli.command(name='sum', help='Sum tables from `source` URIs and save into `destination`') @click.option('--input-encoding') @click.option('--output-encoding') @click.option('--input-locale') @click.option('--output-locale') @click.option('--verify-ssl', default=True, type=bool) @click.option('--order-by') @click.argument('sources', nargs=-1, required=True) @click.argument('destination') def sum_(input_encoding, output_encoding, input_locale, output_locale, verify_ssl, order_by, sources, destination): # TODO: may use sys.stdout.encoding if output_file = '-' output_encoding = output_encoding or DEFAULT_OUTPUT_ENCODING if input_locale is not None: with rows.locale_context(input_locale): tables = [_import_table(source, encoding=input_encoding, verify_ssl=verify_ssl) for source in sources] else: tables = [_import_table(source, encoding=input_encoding, verify_ssl=verify_ssl) for source in sources] result = sum(tables) if order_by is not None: order_by = _get_field_names(order_by, result.fields.keys(), permit_not=True) # TODO: use complete list of `order_by` fields result.order_by(order_by[0].replace('^', '-')) if output_locale is not None: with rows.locale_context(output_locale): export_to_uri(result, destination, encoding=output_encoding) else: export_to_uri(result, destination, encoding=output_encoding) @cli.command(name='print', help='Print a table') @click.option('--input-encoding') @click.option('--output-encoding') @click.option('--input-locale') @click.option('--output-locale') @click.option('--table-index', default=0) @click.option('--verify-ssl', default=True, type=bool) @click.option('--fields') @click.option('--fields-except') @click.option('--order-by') @click.argument('source', required=True) def print_(input_encoding, output_encoding, input_locale, output_locale, table_index, verify_ssl, fields, fields_except, order_by, source): if fields is not None and fields_except is not None: click.echo('ERROR: `--fields` cannot be used with `--fields-except`', err=True) sys.exit(20) output_encoding = output_encoding or sys.stdout.encoding or \ DEFAULT_OUTPUT_ENCODING # TODO: may use `import_fields` for better performance if input_locale is not None: with rows.locale_context(input_locale): table = _import_table(source, encoding=input_encoding, verify_ssl=verify_ssl, index=table_index) else: table = _import_table(source, encoding=input_encoding, verify_ssl=verify_ssl, index=table_index) table_field_names = table.fields.keys() if fields is not None: fields = _get_field_names(fields, table_field_names) if fields_except is not None: fields_except = _get_field_names(fields_except, table_field_names) # TODO: should set `export_fields = None` if `--fields` and # `--fields-except` are `None` if fields is not None and fields_except is None: export_fields = fields elif fields is not None and fields_except is not None: export_fields = list(fields) map(export_fields.remove, fields_except) elif fields is None and fields_except is not None: export_fields = list(table_field_names) map(export_fields.remove, fields_except) else: export_fields = table_field_names if order_by is not None: order_by = _get_field_names(order_by, table_field_names, permit_not=True) # TODO: use complete list of `order_by` fields table.order_by(order_by[0].replace('^', '-')) fobj = BytesIO() if output_locale is not None: with rows.locale_context(output_locale): rows.export_to_txt(table, fobj, encoding=output_encoding, export_fields=export_fields) else: rows.export_to_txt(table, fobj, encoding=output_encoding, export_fields=export_fields) fobj.seek(0) # TODO: may pass unicode to click.echo if output_encoding is not provided click.echo(fobj.read()) @cli.command(name='query', help='Query a table using SQL') @click.option('--input-encoding') @click.option('--output-encoding') @click.option('--input-locale') @click.option('--output-locale') @click.option('--verify-ssl', default=True, type=bool) @click.option('--fields') @click.option('--output') @click.argument('query', required=True) @click.argument('sources', nargs=-1, required=True) def query(input_encoding, output_encoding, input_locale, output_locale, verify_ssl, fields, output, query, sources): # TODO: may use sys.stdout.encoding if output_file = '-' output_encoding = output_encoding or sys.stdout.encoding or \ DEFAULT_OUTPUT_ENCODING if not query.lower().startswith('select'): field_names = '*' if fields is None else fields table_names = ', '.join(['table{}'.format(index) for index in range(1, len(sources) + 1)]) query = 'SELECT {} FROM {} WHERE {}'.format(field_names, table_names, query) if len(sources) == 1: source = detect_source(sources[0], verify_ssl=verify_ssl) if source.plugin_name != 'sqlite': if input_locale is not None: with rows.locale_context(input_locale): table = import_from_source(source, DEFAULT_INPUT_ENCODING) else: table = import_from_source(source, DEFAULT_INPUT_ENCODING) sqlite_connection = sqlite3.Connection(':memory:') rows.export_to_sqlite(table, sqlite_connection, table_name='table1') result = rows.import_from_sqlite(sqlite_connection, query=query) else: # Optimization: query the SQLite database directly result = import_from_source(source, DEFAULT_INPUT_ENCODING, query=query) else: if input_locale is not None: with rows.locale_context(input_locale): tables = [_import_table(source, encoding=input_encoding, verify_ssl=verify_ssl) for source in sources] else: tables = [_import_table(source, encoding=input_encoding, verify_ssl=verify_ssl) for source in sources] sqlite_connection = sqlite3.Connection(':memory:') for index, table in enumerate(tables, start=1): rows.export_to_sqlite(table, sqlite_connection, table_name='table{}'.format(index)) result = rows.import_from_sqlite(sqlite_connection, query=query) if output is None: fobj = BytesIO() if output_locale is not None: with rows.locale_context(output_locale): rows.export_to_txt(result, fobj, encoding=output_encoding) else: rows.export_to_txt(result, fobj, encoding=output_encoding) fobj.seek(0) click.echo(fobj.read()) else: if output_locale is not None: with rows.locale_context(output_locale): export_to_uri(result, output, encoding=output_encoding) else: export_to_uri(result, output, encoding=output_encoding) if __name__ == '__main__': cli() rows-0.2.1/rows/fields.py000066400000000000000000000373051275267602200153370ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import collections import datetime import json import locale import re import types from decimal import Decimal, InvalidOperation # Order matters here __all__ = ['BoolField', 'IntegerField', 'FloatField', 'DatetimeField', 'DateField', 'DecimalField', 'PercentField', 'JSONField', 'EmailField', 'TextField', 'BinaryField', 'Field'] REGEXP_ONLY_NUMBERS = re.compile('[^0-9]') SHOULD_NOT_USE_LOCALE = True # This variable is changed by rows.locale_manager NULL = (b'-', b'null', b'none', b'nil', b'n/a', b'na') class Field(object): """Base Field class - all fields should inherit from this As the fallback for all other field types are the BinaryField, this Field actually implements what is expected in the BinaryField """ TYPE = (types.NoneType, ) @classmethod def serialize(cls, value, *args, **kwargs): """Serialize a value to be exported `cls.serialize` should always return an unicode value, except for BinaryField """ if value is None: value = '' return value @classmethod def deserialize(cls, value, *args, **kwargs): """Deserialize a value just after importing it `cls.deserialize` should always return a value of type `cls.TYPE` or `None`. """ if isinstance(value, cls.TYPE): return value elif is_null(value): return None else: return value class BinaryField(Field): """Field class to represent byte arrays Is not locale-aware (does not need to be) """ TYPE = (types.StringType, ) @classmethod def serialize(cls, value, *args, **kwargs): if value is None: value = '' return cls.TYPE[0](value) @classmethod def deserialize(cls, value, *args, **kwargs): if value is None: return None else: return cls.TYPE[0](value) class BoolField(Field): """Base class to representing boolean Is not locale-aware (if you need to, please customize by changing its attributes like `TRUE_VALUES` and `FALSE_VALUES`) """ TYPE = (types.BooleanType, ) SERIALIZED_VALUES = {True: 'true', False: 'false', None: ''} TRUE_VALUES = ('true', 'yes') FALSE_VALUES = ('false', 'no') @classmethod def serialize(cls, value, *args, **kwargs): # TODO: should we serialize `None` as well or give it to the plugin? return cls.SERIALIZED_VALUES[value] @classmethod def deserialize(cls, value, *args, **kwargs): value = super(BoolField, cls).deserialize(value) if value is None or isinstance(value, cls.TYPE): return value value = as_string(value).lower() if value in cls.TRUE_VALUES: return True elif value in cls.FALSE_VALUES: return False else: raise ValueError('Value is not boolean') class IntegerField(Field): """Field class to represent integer Is locale-aware """ TYPE = (types.IntType, ) @classmethod def serialize(cls, value, *args, **kwargs): if value is None: return '' if SHOULD_NOT_USE_LOCALE: return types.UnicodeType(value) else: grouping = kwargs.get('grouping', None) return locale.format('%d', value, grouping=grouping) @classmethod def deserialize(cls, value, *args, **kwargs): value = super(IntegerField, cls).deserialize(value) if value is None or isinstance(value, cls.TYPE): return value elif isinstance(value, float): new_value = int(value) if new_value != value: raise ValueError("It's float, not integer") else: value = new_value value = as_string(value) return int(value) if SHOULD_NOT_USE_LOCALE \ else locale.atoi(value) class FloatField(Field): """Field class to represent float Is locale-aware """ TYPE = (types.FloatType, ) @classmethod def serialize(cls, value, *args, **kwargs): if value is None: return '' if SHOULD_NOT_USE_LOCALE: return types.UnicodeType(value) else: grouping = kwargs.get('grouping', None) return locale.format('%f', value, grouping=grouping) @classmethod def deserialize(cls, value, *args, **kwargs): value = super(FloatField, cls).deserialize(value) if value is None or isinstance(value, cls.TYPE): return value value = as_string(value) if SHOULD_NOT_USE_LOCALE: return float(value) else: return locale.atof(value) class DecimalField(Field): """Field class to represent decimal data (as Python's decimal.Decimal) Is locale-aware """ TYPE = (Decimal, ) @classmethod def serialize(cls, value, *args, **kwargs): if value is None: return '' value_as_string = types.UnicodeType(value) if SHOULD_NOT_USE_LOCALE: return value_as_string else: grouping = kwargs.get('grouping', None) has_decimal_places = value_as_string.find('.') != -1 if not has_decimal_places: string_format = '%d' else: decimal_places = len(value_as_string.split('.')[1]) string_format = '%.{}f'.format(decimal_places) return locale.format(string_format, value, grouping=grouping) @classmethod def deserialize(cls, value, *args, **kwargs): value = super(DecimalField, cls).deserialize(value) if value is None or isinstance(value, cls.TYPE): return value elif type(value) in (int, float): return Decimal(str(value)) if SHOULD_NOT_USE_LOCALE: try: return Decimal(value) except InvalidOperation: raise ValueError("Can't be {}".format(cls.__name__)) else: locale_vars = locale.localeconv() decimal_separator = locale_vars['decimal_point'] interesting_vars = ['decimal_point', 'mon_decimal_point', 'mon_thousands_sep', 'negative_sign', 'positive_sign', 'thousands_sep'] chars = (locale_vars[x].replace('.', r'\.').replace('-', r'\-') for x in interesting_vars) interesting_chars = ''.join(set(chars)) regexp = re.compile(r'[^0-9{} ]'.format(interesting_chars)) value = as_string(value) if regexp.findall(value): raise ValueError("Can't be {}".format(cls.__name__)) parts = [REGEXP_ONLY_NUMBERS.subn('', number)[0] for number in value.split(decimal_separator)] if len(parts) > 2: raise ValueError("Can't deserialize with this locale.") try: value = Decimal(parts[0]) if len(parts) == 2: decimal_places = len(parts[1]) value = value + (Decimal(parts[1]) / (10 ** decimal_places)) except InvalidOperation: raise ValueError("Can't be {}".format(cls.__name__)) return value class PercentField(DecimalField): """Field class to represent percent values Is locale-aware (inherit this behaviour from `rows.DecimalField`) """ @classmethod def serialize(cls, value, *args, **kwargs): if value is None: return '' elif value == Decimal('0'): return '0.00%' value = Decimal(str(value * 100)[:-2]) value = super(PercentField, cls).serialize(value, *args, **kwargs) return '{}%'.format(value) @classmethod def deserialize(cls, value, *args, **kwargs): if isinstance(value, cls.TYPE): return value elif is_null(value): return None value = as_string(value) if '%' not in value: raise ValueError("Can't be {}".format(cls.__name__)) value = value.replace('%', '') return super(PercentField, cls).deserialize(value) / 100 class DateField(Field): """Field class to represent date Is not locale-aware (does not need to be) """ TYPE = (datetime.date, ) INPUT_FORMAT = '%Y-%m-%d' OUTPUT_FORMAT = '%Y-%m-%d' @classmethod def serialize(cls, value, *args, **kwargs): if value is None: return '' return types.UnicodeType(value.strftime(cls.OUTPUT_FORMAT)) @classmethod def deserialize(cls, value, *args, **kwargs): value = super(DateField, cls).deserialize(value) if value is None or isinstance(value, cls.TYPE): return value value = as_string(value) if isinstance(value, unicode): value = value.encode('utf-8') dt_object = datetime.datetime.strptime(value, cls.INPUT_FORMAT) return datetime.date(dt_object.year, dt_object.month, dt_object.day) class DatetimeField(Field): """Field class to represent date-time Is not locale-aware (does not need to be) """ TYPE = (datetime.datetime, ) DATETIME_REGEXP = re.compile('^([0-9]{4})-([0-9]{2})-([0-9]{2})[ T]' '([0-9]{2}):([0-9]{2}):([0-9]{2})$') @classmethod def serialize(cls, value, *args, **kwargs): if value is None: return '' return types.UnicodeType(value.isoformat()) @classmethod def deserialize(cls, value, *args, **kwargs): value = super(DatetimeField, cls).deserialize(value) if value is None or isinstance(value, cls.TYPE): return value value = as_string(value) # TODO: may use iso8601 groups = cls.DATETIME_REGEXP.findall(value) if not groups: raise ValueError("Can't be {}".format(cls.__name__)) else: return datetime.datetime(*[int(x) for x in groups[0]]) class TextField(Field): """Field class to represent unicode strings Is not locale-aware (does not need to be) """ TYPE = (types.UnicodeType, ) @classmethod def deserialize(cls, value, *args, **kwargs): if value is None or isinstance(value, cls.TYPE): return value elif 'encoding' in kwargs: return as_string(value).decode(kwargs['encoding']) else: return cls.TYPE[0](value) class EmailField(TextField): """Field class to represent e-mail addresses Is not locale-aware (does not need to be) """ EMAIL_REGEXP = re.compile(r'^[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]+$', flags=re.IGNORECASE) @classmethod def serialize(cls, value, *args, **kwargs): if value is None: return '' return types.UnicodeType(value) @classmethod def deserialize(cls, value, *args, **kwargs): value = super(EmailField, cls).deserialize(value) if value is None or not value.strip(): return None result = cls.EMAIL_REGEXP.findall(value) if not result: raise ValueError("Can't be {}".format(cls.__name__)) else: return result[0] class JSONField(Field): """Field class to represent JSON-encoded strings Is not locale-aware (does not need to be) """ TYPE = (types.ListType, types.DictType) @classmethod def serialize(cls, value, *args, **kwargs): return json.dumps(value) @classmethod def deserialize(cls, value, *args, **kwargs): if isinstance(value, types.UnicodeType): value = value.encode('utf-8') if value is None or isinstance(value, cls.TYPE): return value else: return json.loads(value) AVAILABLE_FIELD_TYPES = [locals()[element] for element in __all__ if 'Field' in element and element != 'Field'] def as_string(value): if isinstance(value, types.StringTypes): return value else: return types.StringType(value) def is_null(value): if value is None: return True value_str = as_string(value).strip().lower() return not value_str or value_str in NULL def unique_values(values): value_types = set(type(value) for value in values) if dict not in value_types: return set([value for value in set(values) if not is_null(value)]) else: result = [] for value in values: if not is_null(value) and value not in result: result.append(value) return result def detect_types(field_names, field_values, field_types=AVAILABLE_FIELD_TYPES, *args, **kwargs): """Where the magic happens""" # TODO: look strategy of csv.Sniffer.has_header # TODO: may receive 'type hints' # TODO: should support receiving unicode objects directly # TODO: should expect data in unicode or will be able to use binary data? field_values = list(field_values) if not field_values: return collections.OrderedDict([(field_name, BinaryField) for field_name in field_names]) number_of_fields = len(field_names) columns = zip(*[row for row in field_values if len(row) == number_of_fields]) if len(columns) != number_of_fields: raise ValueError('Number of fields differ') detected_types = collections.OrderedDict([(field_name, None) for field_name in field_names]) for index, field_name in enumerate(field_names): data = unique_values(columns[index]) if not data: # all rows with an empty field -> BinaryField (can't identify) identified_type = BinaryField else: # ok, let's try to identify the type of this column by # converting every non-null value in the sample possible_types = list(field_types) for value in data: cant_be = set() for type_ in possible_types: try: type_.deserialize(value, *args, **kwargs) except (ValueError, TypeError): cant_be.add(type_) for type_to_remove in cant_be: possible_types.remove(type_to_remove) identified_type = possible_types[0] # priorities matter detected_types[field_name] = identified_type return detected_types TYPES = [(key, locals().get(key)) for key in __all__] def identify_type(value): value_type = type(value) if value_type not in (str, unicode): possible_types = [type_class for type_name, type_class in TYPES if value_type in type_class.TYPE] if not possible_types: detected = detect_types(['some_field'], [[value]])['some_field'] else: detected = possible_types[0] else: detected = detect_types(['some_field'], [[value]])['some_field'] return detected rows-0.2.1/rows/localization.py000066400000000000000000000012151275267602200165500ustar00rootroot00000000000000# coding: utf-8 from __future__ import unicode_literals import contextlib import locale import types import rows.fields @contextlib.contextmanager def locale_context(name, category=locale.LC_ALL): old_name = locale.getlocale(category) if None not in old_name: old_name = '.'.join(old_name) if isinstance(name, types.UnicodeType): name = str(name) if old_name != name: locale.setlocale(category, name) rows.fields.SHOULD_NOT_USE_LOCALE = False try: yield finally: if old_name != name: locale.setlocale(category, old_name) rows.fields.SHOULD_NOT_USE_LOCALE = True rows-0.2.1/rows/operations.py000066400000000000000000000053361275267602200162530ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals from collections import OrderedDict from rows.table import Table from rows.plugins.utils import create_table def join(keys, tables): """Merge a list of `Table` objects using `keys` to group rows""" # Make new (merged) Table fields fields = OrderedDict() map(lambda table: fields.update(table.fields), tables) # TODO: may raise an error if a same field is different in some tables # Check if all keys are inside merged Table's fields fields_keys = set(fields.keys()) for key in keys: if key not in fields_keys: raise ValueError('Invalid key: "{}"'.format(key)) # Group rows by key, without missing ordering none_fields = lambda: OrderedDict({field: None for field in fields.keys()}) data = OrderedDict() for table in tables: for row in table: row_key = tuple([getattr(row, key) for key in keys]) if row_key not in data: data[row_key] = none_fields() data[row_key].update(row._asdict()) merged = Table(fields=fields) merged.extend(data.values()) return merged def transform(fields, function, *tables): "Return a new table based on other tables and a transformation function" new_table = Table(fields=fields) for table in tables: map(new_table.append, filter(bool, map(lambda row: function(row, table), table))) return new_table def transpose(table, fields_column, *args, **kwargs): field_names = [] new_rows = [{} for _ in range(len(table.fields) - 1)] for row in table: row = row._asdict() field_name = row[fields_column] field_names.append(field_name) del row[fields_column] for index, value in enumerate(row.values()): new_rows[index][field_name] = value table_rows = [[row[field_name] for field_name in field_names] for row in new_rows] return create_table([field_names] + table_rows, *args, **kwargs) rows-0.2.1/rows/plugins/000077500000000000000000000000001275267602200151705ustar00rootroot00000000000000rows-0.2.1/rows/plugins/__init__.py000066400000000000000000000000001275267602200172670ustar00rootroot00000000000000rows-0.2.1/rows/plugins/_json.py000066400000000000000000000055201275267602200166540ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import datetime import decimal import json from rows import fields from rows.plugins.utils import (create_table, export_data, get_filename_and_fobj, prepare_to_export) def import_from_json(filename_or_fobj, encoding='utf-8', *args, **kwargs): 'Import data from a JSON file' kwargs['encoding'] = encoding filename, fobj = get_filename_and_fobj(filename_or_fobj) json_obj = json.load(fobj, encoding=encoding) field_names = json_obj[0].keys() table_rows = [[item[key] for key in field_names] for item in json_obj] data = [field_names] + table_rows meta = {'imported_from': 'json', 'filename': filename, } return create_table(data, meta=meta, *args, **kwargs) def _convert(value, field_type, *args, **kwargs): if value is None or field_type in ( fields.BinaryField, fields.BoolField, fields.FloatField, fields.IntegerField, fields.JSONField, fields.TextField, ): # If the field_type is one of those, the value can be passed directly # to the JSON encoder return value else: # The field type is not represented natively in JSON, then it needs to # be serialized (converted to a string) return field_type.serialize(value, *args, **kwargs) def export_to_json(table, filename_or_fobj=None, encoding='utf-8', indent=None, *args, **kwargs): # TODO: will work only if table.fields is OrderedDict fields = table.fields prepared_table = prepare_to_export(table, *args, **kwargs) field_names = prepared_table.next() data = [{field_name: _convert(value, fields[field_name], *args, **kwargs) for field_name, value in zip(field_names, row)} for row in prepared_table] result = json.dumps(data, indent=indent) if indent is not None: # clean up empty spaces at the end of lines result = '\n'.join(line.rstrip() for line in result.splitlines()) return export_data(filename_or_fobj, result) rows-0.2.1/rows/plugins/_parquet.py000066400000000000000000000032271275267602200173660ustar00rootroot00000000000000# coding: utf-8 # Copyright 2016 Álvaro Justen # # 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 . from __future__ import unicode_literals import logging from collections import namedtuple from rows.plugins.utils import create_table class NullHandler(logging.Handler): def emit(self, record): pass logging.getLogger("parquet").addHandler(NullHandler()) import parquet OPTIONS = namedtuple('Options', ['col', 'format'])(col=None, format='custom') def _callback(*args): return args def import_from_parquet(filename, encoding='utf-8', *args, **kwargs): 'Import data from a Parquet file' # TODO: should be able to used fobj also data, field_names = parquet.dump(filename, OPTIONS, _callback) length = len(data[field_names[0]]) table_rows = [[data[field_name][index] for field_name in field_names] for index in range(length)] meta = {'imported_from': 'parquet', 'filename': filename,} return create_table([field_names] + table_rows, meta=meta, *args, **kwargs) rows-0.2.1/rows/plugins/csv.py000066400000000000000000000045601275267602200163420ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals from io import BytesIO import unicodecsv from rows.plugins.utils import create_table, get_filename_and_fobj, serialize sniffer = unicodecsv.Sniffer() def import_from_csv(filename_or_fobj, encoding='utf-8', dialect=None, sample_size=8192, *args, **kwargs): 'Import data from a CSV file' filename, fobj = get_filename_and_fobj(filename_or_fobj) if dialect is None: sample = fobj.read(sample_size) try: dialect = sniffer.sniff(sample, delimiters=(',', ';', '\t')) except unicodecsv.Error: # Could not detect dialect, fall back to 'excel' dialect = unicodecsv.excel fobj.seek(0) kwargs['encoding'] = encoding csv_reader = unicodecsv.reader(fobj, encoding=encoding, dialect=dialect) meta = {'imported_from': 'csv', 'filename': filename,} return create_table(csv_reader, meta=meta, *args, **kwargs) def export_to_csv(table, filename_or_fobj=None, encoding='utf-8', *args, **kwargs): # TODO: will work only if table.fields is OrderedDict # TODO: should use fobj? What about creating a method like json.dumps? kwargs['encoding'] = encoding if filename_or_fobj is not None: _, fobj = get_filename_and_fobj(filename_or_fobj, mode='w') else: fobj = BytesIO() csv_writer = unicodecsv.writer(fobj, encoding=encoding) map(csv_writer.writerow, serialize(table, *args, **kwargs)) if filename_or_fobj is not None: fobj.flush() return fobj else: fobj.seek(0) result = fobj.read() fobj.close() return result rows-0.2.1/rows/plugins/dicts.py000066400000000000000000000025331275267602200166530ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2016 Álvaro Justen # # 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 . from __future__ import unicode_literals from rows.plugins.utils import create_table def import_from_dicts(data, *args, **kwargs): 'Import data from a list of dicts' headers = set() for row in data: headers.update(row.keys()) headers = sorted(list(headers)) data = [[row.get(header, None) for header in headers] for row in data] meta = {'imported_from': 'dicts', } return create_table([headers] + data, meta=meta, *args, **kwargs) def export_to_dicts(table, *args, **kwargs): return [{key: getattr(row, key) for key in table.field_names} for row in table] rows-0.2.1/rows/plugins/html.py000066400000000000000000000120711275267602200165070ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import HTMLParser import string from lxml.html import document_fromstring from lxml.etree import tostring as to_string, strip_tags from rows.plugins.utils import (create_table, export_data, get_filename_and_fobj, serialize) unescape = HTMLParser.HTMLParser().unescape def _get_content(element): content = to_string(element) content = content[content.find('>') + 1:content.rfind('<')].strip() return unescape(content) def _get_row(row, column_tag, preserve_html, properties): if not preserve_html: data = map(_extract_node_text, row.xpath(column_tag)) else: data = map(_get_content, row.xpath(column_tag)) if properties: data.append(dict(row.attrib)) return data def import_from_html(filename_or_fobj, encoding='utf-8', index=0, ignore_colspan=True, preserve_html=False, properties=False, table_tag='table', row_tag='tr', column_tag='td|th', *args, **kwargs): filename, fobj = get_filename_and_fobj(filename_or_fobj) kwargs['encoding'] = encoding html = fobj.read().decode(encoding) html_tree = document_fromstring(html) tables = html_tree.xpath('//{}'.format(table_tag)) table = tables[index] strip_tags(table, 'thead') strip_tags(table, 'tbody') row_elements = table.xpath(row_tag) table_rows = [_get_row(row, column_tag=column_tag, preserve_html=preserve_html, properties=properties) for row in row_elements] if properties: table_rows[0][-1] = 'properties' if preserve_html and kwargs.get('fields', None) is None: # The field names will be the first table row, so we need to strip HTML # from it even if `preserve_html` is `True` (it's `True` only for rows, # not for the header). table_rows[0] = map(_extract_node_text, row_elements[0]) max_columns = max(map(len, table_rows)) if ignore_colspan: table_rows = filter(lambda row: len(row) == max_columns, table_rows) meta = {'imported_from': 'html', 'filename': filename,} return create_table(table_rows, meta=meta, *args, **kwargs) def export_to_html(table, filename_or_fobj=None, encoding='utf-8', *args, **kwargs): kwargs['encoding'] = encoding serialized_table = serialize(table, *args, **kwargs) fields = serialized_table.next() result = ['
title firstname middlename lastname name_suffix nickname
\n\n', ' \n', ' \n'] header = [' \n'.format(field) for field in fields] result.extend(header) result.extend([' \n', ' \n', '\n', ' \n', '\n']) for index, row in enumerate(serialized_table, start=1): css_class = 'odd' if index % 2 == 1 else 'even' result.append(' \n'.format(css_class)) for value in row: result.extend([' \n']) result.append(' \n\n') result.append(' \n\n
{}
', value, '
\n') new_result = [value.encode(encoding) if isinstance(value, unicode) else value for value in result] html = ''.encode(encoding).join(new_result) return export_data(filename_or_fobj, html) def _extract_node_text(node): 'Extract text from a given lxml node' texts = map(string.strip, map(unescape, node.xpath('.//text()'))) return ' '.join(text for text in texts if text) def count_tables(filename_or_fobj, encoding='utf-8', table_tag='table'): filename, fobj = get_filename_and_fobj(filename_or_fobj) html = fobj.read().decode(encoding) html_tree = document_fromstring(html) tables = html_tree.xpath('//{}'.format(table_tag)) return len(tables) def tag_to_dict(html): "Extract tag's attributes into a `dict`" element = document_fromstring(html).xpath('//html/body/child::*')[0] attributes = dict(element.attrib) attributes['text'] = element.text_content() return attributes def extract_text(html): 'Extract text from a given HTML' return _extract_node_text(document_fromstring(html)) def extract_links(html): 'Extract the href values from a given HTML (returns a list of strings)' return document_fromstring(html).xpath('.//@href') rows-0.2.1/rows/plugins/ods.py000066400000000000000000000077441275267602200163430ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import zipfile from decimal import Decimal from lxml.etree import tostring as xml_to_string, fromstring as xml_from_string from rows.plugins.utils import create_table, get_filename_and_fobj def xpath(element, xpath, namespaces): return xml_from_string(xml_to_string(element)).xpath(xpath, namespaces=namespaces) def attrib(cell, namespace, name): return cell.attrib['{{{}}}{}'.format(namespace, name)] def complete_with_None(lists, size): for element in lists: element.extend([None] * (size - len(element))) yield element def import_from_ods(filename_or_fobj, index=0, *args, **kwargs): # TODO: import spreadsheet by name # TODO: unescape values filename, _ = get_filename_and_fobj(filename_or_fobj) ods_file = zipfile.ZipFile(filename) content_fobj = ods_file.open('content.xml') xml = content_fobj.read() # will return bytes content_fobj.close() document = xml_from_string(xml) namespaces = document.nsmap spreadsheet = document.xpath('//office:spreadsheet', namespaces=namespaces)[0] tables = xpath(spreadsheet, '//table:table', namespaces) table = tables[index] table_rows_obj = xpath(table, '//table:table-row', namespaces) table_rows = [] for row_obj in table_rows_obj: row = [] for cell in xpath(row_obj, '//table:table-cell', namespaces): children = cell.getchildren() if not children: continue # TODO: evalute 'boolean' and 'time' types value_type = attrib(cell, namespaces['office'], 'value-type') if value_type == 'date': cell_value = attrib(cell, namespaces['office'], 'date-value') elif value_type == 'float': cell_value = attrib(cell, namespaces['office'], 'value') elif value_type == 'percentage': cell_value = attrib(cell, namespaces['office'], 'value') cell_value = Decimal(str(Decimal(cell_value) * 100)[:-2]) cell_value = '{}%'.format(cell_value) elif value_type == 'string': try: # get computed string (from formula, for example) cell_value = attrib(cell, namespaces['office'], 'string-value') except KeyError: # computed string not present => get from

...

cell_value = children[0].text else: # value_type == some type we don't know cell_value = children[0].text try: repeat = attrib(cell, namespaces['table'], 'number-columns-repeated') except KeyError: row.append(cell_value) else: for _ in range(int(repeat)): row.append(cell_value) if row: table_rows.append(row) max_length = max(len(row) for row in table_rows) full_rows = complete_with_None(table_rows, max_length) meta = {'imported_from': 'ods', 'filename': filename,} return create_table(full_rows, meta=meta, *args, **kwargs) rows-0.2.1/rows/plugins/sqlite.py000066400000000000000000000127221275267602200170470ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2016 Álvaro Justen # # 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 . from __future__ import unicode_literals import datetime import sqlite3 import string import rows.fields as fields from rows.plugins.utils import (create_table, get_filename_and_fobj, ipartition, make_unique_name, prepare_to_export) SQL_TABLE_NAMES = 'SELECT name FROM sqlite_master WHERE type="table"' SQL_CREATE_TABLE = 'CREATE TABLE IF NOT EXISTS "{table_name}" ({field_types})' SQL_SELECT_ALL = 'SELECT * FROM "{table_name}"' SQL_INSERT = 'INSERT INTO "{table_name}" ({field_names}) VALUES ({placeholders})' SQLITE_TYPES = { fields.BinaryField: 'BLOB', fields.BoolField: 'INTEGER', fields.DateField: 'TEXT', fields.DatetimeField: 'TEXT', fields.DecimalField: 'REAL', fields.FloatField: 'REAL', fields.IntegerField: 'INTEGER', fields.PercentField: 'REAL', fields.TextField: 'TEXT', } DEFAULT_TYPE = 'BLOB' def _python_to_sqlite(field_types): def convert_value(field_type, value): if field_type in ( fields.BinaryField, fields.BoolField, fields.DateField, fields.DatetimeField, fields.FloatField, fields.IntegerField, fields.TextField ): return value elif field_type in (fields.DecimalField, fields.PercentField): return float(value) if value is not None else None else: # don't know this field return field_type.serialize(value) def convert_row(row): return [convert_value(field_type, value) for field_type, value in zip(field_types, row)] return convert_row def _get_connection(filename_or_connection): if isinstance(filename_or_connection, basestring): # filename return sqlite3.connect(filename_or_connection) else: # already a connection return filename_or_connection def _valid_table_name(name): '''Verify if a given table name is valid for `rows` Rules: - Should start with a letter or '_' - Letters can be capitalized or not - Acceps letters, numbers and _ ''' if name[0] not in '_' + string.letters or \ not set(name).issubset('_' + string.letters + string.digits): return False else: return True def import_from_sqlite(filename_or_connection, table_name='table1', query=None, *args, **kwargs): connection = _get_connection(filename_or_connection) cursor = connection.cursor() if query is None: if not _valid_table_name(table_name): raise ValueError('Invalid table name: {}'.format(table_name)) query = SQL_SELECT_ALL.format(table_name=table_name) table_rows = list(cursor.execute(query)) # TODO: may be lazy header = [info[0] for info in cursor.description] cursor.close() # TODO: should close connection also? meta = {'imported_from': 'sqlite', 'filename': filename_or_connection, } return create_table([header] + table_rows, meta=meta, *args, **kwargs) def export_to_sqlite(table, filename_or_connection, table_name=None, table_name_format='table{index}', batch_size=100, *args, **kwargs): # TODO: should add transaction support? prepared_table = prepare_to_export(table, *args, **kwargs) connection = _get_connection(filename_or_connection) cursor = connection.cursor() if table_name is None: table_names = [item[0] for item in cursor.execute(SQL_TABLE_NAMES)] table_name = make_unique_name(table_name_format.format(index=1), existing_names=table_names, name_format=table_name_format, start=1) elif not _valid_table_name(table_name): raise ValueError('Invalid table name: {}'.format(table_name)) field_names = prepared_table.next() field_types = map(table.fields.get, field_names) columns = ['{} {}'.format(field_name, SQLITE_TYPES.get(field_type, DEFAULT_TYPE)) for field_name, field_type in zip(field_names, field_types)] cursor.execute(SQL_CREATE_TABLE.format(table_name=table_name, field_types=', '.join(columns))) insert_sql = SQL_INSERT.format( table_name=table_name, field_names=', '.join(field_names), placeholders=', '.join('?' for _ in field_names)) _convert_row = _python_to_sqlite(field_types) for batch in ipartition(prepared_table, batch_size): cursor.executemany(insert_sql, map(_convert_row, batch)) connection.commit() return connection rows-0.2.1/rows/plugins/txt.py000066400000000000000000000056741275267602200163750ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals from rows.plugins.utils import (create_table, export_data, get_filename_and_fobj, serialize) DASH, PLUS, PIPE = '-', '+', '|' def _max_column_sizes(field_names, table_rows): columns = zip(*([field_names] + table_rows)) return {field_name: max(len(value) for value in column) for field_name, column in zip(field_names, columns)} def import_from_txt(filename_or_fobj, encoding='utf-8', *args, **kwargs): # TODO: should be able to change DASH, PLUS and PIPE filename, fobj = get_filename_and_fobj(filename_or_fobj) kwargs['encoding'] = encoding contents = fobj.read().decode(encoding).strip().splitlines() # remove '+----+----+' lines contents = contents[1:-1] del contents[1] table_rows = [[value.strip() for value in row.split(PIPE)[1:-1]] for row in contents] meta = {'imported_from': 'txt', 'filename': filename,} return create_table(table_rows, meta=meta, *args, **kwargs) def export_to_txt(table, filename_or_fobj=None, encoding='utf-8', *args, **kwargs): # TODO: should be able to change DASH, PLUS and PIPE # TODO: will work only if table.fields is OrderedDict # TODO: should use fobj? What about creating a method like json.dumps? kwargs['encoding'] = encoding serialized_table = serialize(table, *args, **kwargs) field_names = serialized_table.next() table_rows = list(serialized_table) max_sizes = _max_column_sizes(field_names, table_rows) dashes = [DASH * (max_sizes[field] + 2) for field in field_names] header = [field.center(max_sizes[field]) for field in field_names] header = '{} {} {}'.format(PIPE, ' {} '.format(PIPE).join(header), PIPE) split_line = PLUS + PLUS.join(dashes) + PLUS result = [split_line, header, split_line] for row in table_rows: values = [value.rjust(max_sizes[field_name]) for field_name, value in zip(field_names, row)] row_data = ' {} '.format(PIPE).join(values) result.append('{} {} {}'.format(PIPE, row_data, PIPE)) result.extend([split_line, '']) data = '\n'.join(result).encode(encoding) return export_data(filename_or_fobj, data) rows-0.2.1/rows/plugins/utils.py000066400000000000000000000175661275267602200167210ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals from collections import Iterator, OrderedDict from itertools import chain, islice from unicodedata import normalize from rows.fields import detect_types from rows.table import FlexibleTable, Table SLUG_CHARS = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_' def slug(text, encoding=None, separator='_', permitted_chars=SLUG_CHARS, replace_with_separator=' -_'): '''Slugfy text Example: ' ÁLVARO justen% ' -> 'alvaro_justen' ''' # Convert everything to unicode. # Example: b' ÁLVARO justen% ' -> u' ÁLVARO justen% ' if isinstance(text, str): text = text.decode(encoding or 'ascii') # Strip non-ASCII characters # Example: u' ÁLVARO justen% ' -> ' ALVARO justen% ' text = normalize('NFKD', text.strip()).encode('ascii', 'ignore') # Replace spaces and other chars with separator # Example: u' ALVARO justen% ' -> u'_ALVARO__justen%_' for char in replace_with_separator: text = text.replace(char, separator) # Remove non-permitted characters and put everything to lowercase # Example: u'_ALVARO__justen%_' -> u'_alvaro__justen_' text = filter(lambda char: char in permitted_chars, text).lower() # Remove double occurrencies of separator # Example: u'_alvaro__justen_' -> u'_alvaro_justen_' double_separator = separator + separator while double_separator in text: text = text.replace(double_separator, separator) # Strip separators # Example: u'_alvaro_justen_' -> u'alvaro_justen' return text.strip(separator) def ipartition(iterable, partition_size): if not isinstance(iterable, Iterator): iterator = iter(iterable) else: iterator = iterable finished = False while not finished: data = [] for _ in range(partition_size): try: data.append(iterator.next()) except StopIteration: finished = True break if data: yield data def get_filename_and_fobj(filename_or_fobj, mode='r', dont_open=False): if getattr(filename_or_fobj, 'read', None) is not None: fobj = filename_or_fobj filename = getattr(fobj, 'name', None) else: fobj = open(filename_or_fobj, mode=mode) if not dont_open else None filename = filename_or_fobj return filename, fobj def make_unique_name(name, existing_names, name_format='{name}_{index}', start=2): '''Return a unique name based on `name_format` and `name`.''' index = start new_name = name while new_name in existing_names: new_name = name_format.format(name=name, index=index) index += 1 return new_name def make_header(field_names, permit_not=False): 'Return unique and slugged field names' slug_chars = SLUG_CHARS if not permit_not else SLUG_CHARS + '^' header = [slug(field_name, permitted_chars=slug_chars) for field_name in field_names] result = [] for index, field_name in enumerate(header): if not field_name: field_name = 'field_{}'.format(index) elif field_name[0].isdigit(): field_name = 'field_{}'.format(field_name) if field_name in result: field_name = make_unique_name(name=field_name, existing_names=result, start=2) result.append(field_name) return result def create_table(data, meta=None, fields=None, skip_header=True, import_fields=None, samples=None, force_types=None, *args, **kwargs): # TODO: add auto_detect_types=True parameter table_rows = iter(data) sample_rows = [] if fields is None: header = make_header(table_rows.next()) if samples is not None: sample_rows = list(islice(table_rows, 0, samples)) else: sample_rows = list(table_rows) fields = detect_types(header, sample_rows, *args, **kwargs) if force_types is not None: # TODO: optimize field detection (ignore fields on `force_types`) for field_name, field_type in force_types.items(): fields[field_name] = field_type else: if not isinstance(fields, OrderedDict): raise ValueError('`fields` must be an `OrderedDict`') if skip_header: _ = table_rows.next() header = make_header(fields.keys()) fields = OrderedDict([(field_name, fields[key]) for field_name, key in zip(header, fields)]) if import_fields is not None: # TODO: can optimize if import_fields is not None. # Example: do not detect all columns import_fields = make_header(import_fields) diff = set(import_fields) - set(header) if diff: field_names = ', '.join('"{}"'.format(field) for field in diff) raise ValueError("Invalid field names: {}".format(field_names)) new_fields = OrderedDict() for field_name in import_fields: new_fields[field_name] = fields[field_name] fields = new_fields table = Table(fields=fields, meta=meta) # TODO: put this inside Table.__init__ for row in chain(sample_rows, table_rows): table.append({field_name: value for field_name, value in zip(header, row)}) return table def prepare_to_export(table, export_fields=None, *args, **kwargs): # TODO: optimize for more used cases (export_fields=None) table_type = type(table) if table_type not in (FlexibleTable, Table): raise ValueError('Table type not recognized') if export_fields is None: # we use already slugged-fieldnames export_fields = table.fields.keys() else: # we need to slug all the field names export_fields = make_header(export_fields) fields = table.fields table_field_names = fields.keys() diff = set(export_fields) - set(table_field_names) if diff: field_names = ', '.join('"{}"'.format(field) for field in diff) raise ValueError("Invalid field names: {}".format(field_names)) yield export_fields if table_type is Table: field_indexes = map(table_field_names.index, export_fields) for row in table._rows: yield [row[field_index] for field_index in field_indexes] elif table_type is FlexibleTable: for row in table._rows: yield [row[field_name] for field_name in export_fields] def serialize(table, *args, **kwargs): prepared_table = prepare_to_export(table, *args, **kwargs) field_names = prepared_table.next() yield field_names field_types = [table.fields[field_name] for field_name in field_names] for row in prepared_table: yield [field_type.serialize(value, *args, **kwargs) for value, field_type in zip(row, field_types)] def export_data(filename_or_fobj, data, mode='w'): if filename_or_fobj is not None: _, fobj = get_filename_and_fobj(filename_or_fobj, mode=mode) fobj.write(data) fobj.flush() return fobj else: return data rows-0.2.1/rows/plugins/xls.py000066400000000000000000000126201275267602200163510ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import datetime from io import BytesIO import xlrd import xlwt import rows.fields as fields from rows.plugins.utils import (create_table, get_filename_and_fobj, prepare_to_export) CELL_TYPES = {xlrd.XL_CELL_BLANK: fields.BinaryField, xlrd.XL_CELL_DATE: fields.DatetimeField, xlrd.XL_CELL_ERROR: None, xlrd.XL_CELL_TEXT: fields.TextField, xlrd.XL_CELL_BOOLEAN: fields.BoolField, xlrd.XL_CELL_EMPTY: None, xlrd.XL_CELL_NUMBER: fields.FloatField,} # TODO: add more formatting styles for other types such as currency # TODO: styles may be influenced by locale FORMATTING_STYLES = { fields.DateField: xlwt.easyxf(num_format_str='yyyy-mm-dd'), fields.DatetimeField: xlwt.easyxf(num_format_str='yyyy-mm-dd hh:mm:ss'), fields.PercentField: xlwt.easyxf(num_format_str='0.00%'), } def _python_to_xls(field_types): def convert_value(field_type, value): data = {} if field_type in FORMATTING_STYLES: data['style'] = FORMATTING_STYLES[field_type] if field_type in ( fields.BinaryField, fields.BoolField, fields.DateField, fields.DatetimeField, fields.DecimalField, fields.FloatField, fields.IntegerField, fields.PercentField, fields.TextField, ): return value, data else: # don't know this field return field_type.serialize(value), data def convert_row(row): return [convert_value(field_type, value) for field_type, value in zip(field_types, row)] return convert_row def cell_value(sheet, row, col): cell = sheet.cell(row, col) field_type = CELL_TYPES[cell.ctype] if field_type is None: return None # TODO: this approach will not work if using locale value = cell.value if field_type is fields.DatetimeField: time_tuple = xlrd.xldate_as_tuple(value, sheet.book.datemode) value = field_type.serialize(datetime.datetime(*time_tuple)) return value.split('T00:00:00')[0] elif field_type is fields.BoolField: if value == 0: return False elif value == 1: return True else: book = sheet.book xf = book.xf_list[cell.xf_index] fmt = book.format_map[xf.format_key] if fmt.format_str.endswith('%'): # TODO: we may optimize this approach: we're converting to string # and the library is detecting the type when we could just say to # the library this value is PercentField return '{}%'.format(value * 100) if value else None elif type(value) == float and int(value) == value: return int(value) else: return value def import_from_xls(filename_or_fobj, sheet_name=None, sheet_index=0, start_row=0, start_column=0, *args, **kwargs): filename, _ = get_filename_and_fobj(filename_or_fobj) book = xlrd.open_workbook(filename, formatting_info=True) if sheet_name is not None: sheet = book.sheet_by_name(sheet_name) else: sheet = book.sheet_by_index(sheet_index) # TODO: may re-use Excel data types # Get header and rows table_rows = [[cell_value(sheet, row_index, column_index) for column_index in range(start_column, sheet.ncols)] for row_index in range(start_row, sheet.nrows)] meta = {'imported_from': 'xls', 'filename': filename,} return create_table(table_rows, meta=meta, *args, **kwargs) def export_to_xls(table, filename_or_fobj=None, sheet_name='Sheet1', *args, **kwargs): work_book = xlwt.Workbook() sheet = work_book.add_sheet(sheet_name) prepared_table = prepare_to_export(table, *args, **kwargs) field_names = prepared_table.next() for column_index, field_name in enumerate(field_names): sheet.write(0, column_index, field_name) _convert_row = _python_to_xls(map(table.fields.get, field_names)) for row_index, row in enumerate(prepared_table, start=1): for column_index, (value, data) in enumerate(_convert_row(row)): sheet.write(row_index, column_index, value, **data) if filename_or_fobj is not None: _, fobj = get_filename_and_fobj(filename_or_fobj, mode='wb') work_book.save(fobj) fobj.flush() return fobj else: fobj = BytesIO() work_book.save(fobj) fobj.seek(0) result = fobj.read() fobj.close() return result rows-0.2.1/rows/plugins/xlsx.py000066400000000000000000000076111275267602200165450ustar00rootroot00000000000000# coding: utf-8 from __future__ import unicode_literals import datetime import decimal from io import BytesIO from openpyxl import load_workbook, Workbook from rows import fields from rows.plugins.utils import (create_table, get_filename_and_fobj, prepare_to_export) def _cell_to_python(cell): '''Convert a PyOpenXL's `Cell` object to the corresponding Python object''' value = cell.value if value == '=TRUE()': return True elif value == '=FALSE()': return False elif cell.number_format.lower() == 'yyyy-mm-dd': return str(value).split(' 00:00:00')[0] elif cell.number_format.lower() == 'yyyy-mm-dd hh:mm:ss': return str(value).split('.')[0] elif cell.number_format.endswith('%'): return '{}%'.format(value * 100) if value else None elif value is None: return '' else: return value def import_from_xlsx(filename_or_fobj, sheet_name=None, sheet_index=0, start_row=0, start_column=0, *args, **kwargs): workbook = load_workbook(filename_or_fobj) if sheet_name is None: sheet_name = workbook.sheetnames[sheet_index] sheet = workbook.get_sheet_by_name(sheet_name) start_row, end_row = max(start_row, sheet.min_row), sheet.max_row start_col, end_col = max(start_column, sheet.min_column), sheet.max_column table_rows = [[_cell_to_python(sheet.cell(row=row_index, column=col_index)) for col_index in range(start_col, end_col + 1)] for row_index in range(start_row, end_row + 1)] filename, _ = get_filename_and_fobj(filename_or_fobj, dont_open=True) metadata = {'imported_from': 'xlsx', 'filename': filename, } return create_table(table_rows, meta=metadata, *args, **kwargs) FORMATTING_STYLES = { fields.DateField: 'YYYY-MM-DD', fields.DatetimeField: 'YYYY-MM-DD HH:MM:SS', fields.PercentField: '0.00%', } def _python_to_cell(field_types): def convert_value(field_type, value): number_format = FORMATTING_STYLES.get(field_type, None) if field_type not in ( fields.BoolField, fields.DateField, fields.DatetimeField, fields.DecimalField, fields.FloatField, fields.IntegerField, fields.PercentField, fields.TextField, ): # BinaryField, DatetimeField, JSONField or unknown value = field_type.serialize(value) return value, number_format def convert_row(row): return [convert_value(field_type, value) for field_type, value in zip(field_types, row)] return convert_row def export_to_xlsx(table, filename_or_fobj=None, sheet_name='Sheet1', *args, **kwargs): workbook = Workbook() sheet = workbook.active sheet.title = sheet_name prepared_table = prepare_to_export(table, *args, **kwargs) # Write header field_names = prepared_table.next() for col_index, field_name in enumerate(field_names): cell = sheet.cell(row=1, column=col_index + 1) cell.value = field_name # Write sheet rows _convert_row = _python_to_cell(map(table.fields.get, field_names)) for row_index, row in enumerate(prepared_table, start=1): for col_index, (value, number_format) in enumerate(_convert_row(row)): cell = sheet.cell(row=row_index + 1, column=col_index + 1) cell.value = value if number_format is not None: cell.number_format = number_format if filename_or_fobj is not None: _, fobj = get_filename_and_fobj(filename_or_fobj, mode='wb') workbook.save(fobj) fobj.flush() return fobj else: fobj = BytesIO() workbook.save(fobj) fobj.seek(0) result = fobj.read() fobj.close() return result rows-0.2.1/rows/plugins/xpath.py000066400000000000000000000040401275267602200166640ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import HTMLParser import string from lxml.html import fromstring as tree_from_string from lxml.etree import strip_tags from lxml.etree import tostring as to_string from rows.plugins.utils import create_table, get_filename_and_fobj unescape = HTMLParser.HTMLParser().unescape def _get_row_data(row, fields_xpath): row = tree_from_string(to_string(row)) data = [] for field_name, field_xpath in fields_xpath.items(): result = row.xpath(field_xpath) if result: texts = map(string.strip, map(unescape, result)) result = ' '.join(text for text in texts if text) else: result = None data.append(result) return data def import_from_xpath(filename_or_fobj, rows_xpath, fields_xpath, encoding='utf-8', *args, **kwargs): filename, fobj = get_filename_and_fobj(filename_or_fobj) kwargs['encoding'] = encoding xml = fobj.read().decode(encoding) tree = tree_from_string(xml) row_elements = tree.xpath(rows_xpath) header = fields_xpath.keys() result_rows = [_get_row_data(row, fields_xpath) for row in row_elements] meta = {'imported_from': 'xpath', 'filename': filename,} return create_table([header] + result_rows, meta=meta, *args, **kwargs) rows-0.2.1/rows/table.py000066400000000000000000000171311275267602200151530ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals from collections import MutableSequence, namedtuple, OrderedDict, Sized from operator import itemgetter from rows.fields import identify_type class Table(MutableSequence): def __init__(self, fields, meta=None): # TODO: should we really use OrderedDict here? # TODO: should use slug on each field name automatically or inside each # plugin? self.fields = OrderedDict(fields) # TODO: should be able to customize row return type (namedtuple, dict # etc.) self.Row = namedtuple('Row', self.field_names) self._rows = [] self.meta = dict(meta) if meta is not None else {} @property def field_names(self): return self.fields.keys() @property def field_types(self): return self.fields.values() def __repr__(self): length = len(self._rows) if isinstance(self._rows, Sized) else '?' imported = '' if 'imported_from' in self.meta: imported = ' (from {})'.format(self.meta['imported_from']) return u''.format(imported, len(self.fields), length) def _make_row(self, row): # TODO: should be able to customize row type (namedtuple, dict etc.) return [field_type.deserialize(row.get(field_name, None)) for field_name, field_type in self.fields.items()] def append(self, row): """Add a row to the table. Should be a dict""" self._rows.append(self._make_row(row)) def __len__(self): return len(self._rows) def __getitem__(self, key): key_type = type(key) if key_type == int: return self.Row(*self._rows[key]) elif key_type == slice: return [self.Row(*row) for row in self._rows[key]] elif key_type == unicode: # TODO: change to 'str' on Python3 try: field_index = self.field_names.index(key) except ValueError: raise KeyError(key) # TODO: should change the line below to return a generator exp? return [row[field_index] for row in self._rows] else: raise ValueError('Unsupported key type: {}' .format(type(key).__name__)) def __setitem__(self, key, value): key_type = type(key) if key_type == int: self._rows[key] = self._make_row(value) elif key_type == unicode: # TODO: change to 'str' on Python3 values = list(value) # I'm not lazy, sorry if len(values) != len(self): raise ValueError('Values length ({}) should be the same as ' 'Table length ({})' .format(len(values), len(self))) from rows.fields import detect_types from rows.plugins.utils import slug field_name = slug(key) is_new_field = field_name not in self.field_names field_type = detect_types([field_name], [[value] for value in values])[field_name] self.fields[field_name] = field_type self.Row = namedtuple('Row', self.field_names) if is_new_field: for row, value in zip(self._rows, values): row.append(field_type.deserialize(value)) else: field_index = self.field_names.index(field_name) for row, value in zip(self._rows, values): row[field_index] = field_type.deserialize(value) else: raise ValueError('Unsupported key type: {}' .format(type(key).__name__)) def __delitem__(self, key): key_type = type(key) if key_type == int: del self._rows[key] elif key_type == unicode: # TODO: change to 'str' on Python3 try: field_index = self.field_names.index(key) except ValueError: raise KeyError(key) del self.fields[key] self.Row = namedtuple('Row', self.field_names) for row in self._rows: row.pop(field_index) else: raise ValueError('Unsupported key type: {}' .format(type(key).__name__)) def insert(self, index, row): self._rows.insert(index, self._make_row(row)) def __radd__(self, other): if other == 0: return self raise ValueError() # TODO: fix "table += other" def __add__(self, other): if other == 0: return self if not isinstance(self, type(other)) or self.fields != other.fields: raise ValueError('Tables have incompatible fields') table = Table(fields=self.fields) map(lambda row: table.append(row._asdict()), self) map(lambda row: table.append(row._asdict()), other) return table def order_by(self, key): # TODO: implement locale # TODO: implement for more than one key reverse = False if key.startswith('-'): key = key[1:] reverse = True field_names = self.fields.keys() if key not in field_names: raise ValueError('Field "{}" does not exist'.format(key)) key_index = field_names.index(key) self._rows.sort(key=itemgetter(key_index), reverse=reverse) class FlexibleTable(Table): def __init__(self, fields=None, meta=None): if fields is None: fields = {} super(FlexibleTable, self).__init__(fields, meta) def __getitem__(self, key): if isinstance(key, int): return self.Row(**self._rows[key]) elif isinstance(key, slice): return [self.Row(**row) for row in self._rows[key]] else: raise ValueError('Unsupported key type: {}' .format(type(key).__name__)) def _add_field(self, field_name, field_type): self.fields[field_name] = field_type self.field_names.append(field_name) self.field_types.append(field_type) self.Row = namedtuple('Row', self.field_names) def _make_row(self, row): field_names = row.keys() for field_name in field_names: if field_name not in self.field_names: self._add_field(field_name, identify_type(row[field_name])) return {field_name: field_type.deserialize(row.get(field_name, None)) for field_name, field_type in self.fields.items()} def insert(self, index, row): self._rows.insert(index, self._make_row(row)) def __setitem__(self, key, value): self._rows[key] = self._make_row(value) def append(self, row): """Add a row to the table. Should be a dict""" self._rows.append(self._make_row(row)) rows-0.2.1/rows/utils.py000066400000000000000000000217661275267602200152350ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import cgi import mimetypes import os import tempfile from urlparse import urlparse try: import magic except ImportError: magic = None else: if not hasattr(magic, 'detect_from_content'): # This is not the file-magic library magic = None import requests chardet = requests.compat.chardet try: import urllib3 except ImportError: from requests.packages import urllib3 else: try: urllib3.disable_warnings() except AttributeError: # old versions of urllib3 or requests pass import rows # TODO: should get this information from the plugins TEXT_PLAIN = { 'txt': 'text/txt', 'text': 'text/txt', 'csv': 'text/csv', 'json': 'application/json', } OCTET_STREAM = { 'microsoft ooxml': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'par archive data': 'application/parquet', } FILE_EXTENSIONS = { 'csv': 'text/csv', 'db': 'application/x-sqlite3', 'htm': 'text/html', 'html': 'text/html', 'json': 'application/json', 'ods': 'application/vnd.oasis.opendocument.spreadsheet', 'parquet': 'application/parquet', 'sqlite': 'application/x-sqlite3', 'text': 'text/txt', 'tsv': 'text/csv', 'txt': 'text/txt', 'xls': 'application/vnd.ms-excel', 'xlsx': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', } MIME_TYPE_TO_PLUGIN_NAME = { 'application/json': 'json', 'application/parquet': 'parquet', 'application/vnd.ms-excel': 'xls', 'application/vnd.oasis.opendocument.spreadsheet': 'ods', 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': 'xlsx', 'application/x-sqlite3': 'sqlite', 'text/csv': 'csv', 'text/html': 'html', 'text/txt': 'txt', } class Source(object): 'Define a source to import a `rows.Table`' __slots__ = ['plugin_name', 'uri', 'encoding', 'delete'] def __init__(self, plugin_name=None, uri=None, encoding=None, delete=False): self.plugin_name = plugin_name self.uri = uri self.delete = delete self.encoding = encoding def __repr__(self): return 'Source(plugin_name={}, uri={}, encoding={}, delete={})'\ .format(self.plugin_name, self.uri, self.encoding, self.delete) def plugin_name_by_uri(uri): 'Return the plugin name based on the URI' # TODO: parse URIs like 'sqlite://' also parsed = urlparse(uri) basename = os.path.basename(parsed.path) if not basename.strip(): raise RuntimeError('Could not identify file format.') plugin_name = basename.split('.')[-1].lower() if plugin_name in FILE_EXTENSIONS: plugin_name = MIME_TYPE_TO_PLUGIN_NAME[FILE_EXTENSIONS[plugin_name]] return plugin_name def extension_by_plugin_name(plugin_name): 'Return the file extension used by this plugin' # TODO: should get this information from the plugin return plugin_name def normalize_mime_type(mime_type, mime_name, file_extension): file_extension = file_extension.lower() if file_extension else '' mime_name = mime_name.lower() if mime_name else '' mime_type = mime_type.lower() if mime_type else '' if mime_type == 'text/plain' and file_extension in TEXT_PLAIN: return TEXT_PLAIN[file_extension] elif mime_type == 'application/octet-stream' and mime_name in OCTET_STREAM: return OCTET_STREAM[mime_name] elif file_extension in FILE_EXTENSIONS: return FILE_EXTENSIONS[file_extension] else: return mime_type def plugin_name_by_mime_type(mime_type, mime_name, file_extension): 'Return the plugin name based on the MIME type' return MIME_TYPE_TO_PLUGIN_NAME.get( normalize_mime_type(mime_type, mime_name, file_extension), None) def detect_local_source(path, content, mime_type=None, encoding=None): # TODO: may add sample_size filename = os.path.basename(path) parts = filename.split('.') extension = parts[-1] if len(parts) > 1 else None if magic is not None: detected = magic.detect_from_content(content) encoding = detected.encoding or encoding mime_name = detected.name mime_type = detected.mime_type or mime_type else: encoding = chardet.detect(content)['encoding'] or encoding mime_name = None mime_type = mime_type or mimetypes.guess_type(filename)[0] plugin_name = plugin_name_by_mime_type(mime_type, mime_name, extension) if encoding == 'binary': encoding = None return Source(uri=path, plugin_name=plugin_name, encoding=encoding) def local_file(path, sample_size=8192): # TODO: may change sample_size with open(path, 'rb') as fobj: content = fobj.read(sample_size) source = detect_local_source(path, content, mime_type=None, encoding=None) return Source(uri=path, plugin_name=source.plugin_name, encoding=source.encoding, delete=False) def download_file(uri, verify_ssl=True, timeout=5): response = requests.get(uri, verify=verify_ssl, timeout=timeout) content = response.content filename = uri encoding = None mime_type = None # Extract data from headers to help plugin + encoding detection, if # available headers = response.headers if 'content-type' in headers: mime_type, options = cgi.parse_header(headers['content-type']) encoding = options.get('charset', encoding) if 'content-disposition' in headers: _, options = cgi.parse_header(headers['content-disposition']) filename = options.get('filename', filename) # TODO: may send only a sample (chardet can be very slow if content is big) source = detect_local_source(filename, content, mime_type, encoding) # Save file locally extension = extension_by_plugin_name(source.plugin_name) tmp = tempfile.NamedTemporaryFile() filename = '{}.{}'.format(tmp.name, extension) tmp.close() with open(filename, 'wb') as fobj: fobj.write(content) return Source(uri=filename, plugin_name=source.plugin_name, encoding=source.encoding, delete=True) def detect_source(uri, verify_ssl, timeout=5): '''Return a `rows.Source` with information for a given URI If URI starts with "http" or "https" the file will be downloaded. This function should only be used if the URI already exists because it's going to download/open the file to detect its encoding and MIME type. ''' # TODO: should also supporte other schemes, like file://, sqlite:// etc. if uri.startswith('http://') or uri.startswith('https://'): return download_file(uri, verify_ssl=verify_ssl, timeout=timeout) else: return local_file(uri) def import_from_source(source, default_encoding, *args, **kwargs): 'Import data described in a `rows.Source` into a `rows.Table`' plugin_name = source.plugin_name kwargs['encoding'] = kwargs.get('encoding', None) or \ source.encoding or \ default_encoding try: import_function = getattr(rows, 'import_from_{}'.format(plugin_name)) except AttributeError: raise ValueError('Plugin (import) "{}" not found'.format(plugin_name)) table = import_function(source.uri, *args, **kwargs) if source.delete: os.unlink(source.uri) return table def import_from_uri(uri, default_encoding, verify_ssl=True, *args, **kwargs): 'Given an URI, detects plugin and encoding and imports into a `rows.Table`' # TODO: support '-' also source = detect_source(uri, verify_ssl=verify_ssl) return import_from_source(source, default_encoding, *args, **kwargs) def export_to_uri(table, uri, *args, **kwargs): 'Given a `rows.Table` and an URI, detects plugin (from URI) and exports' # TODO: support '-' also plugin_name = plugin_name_by_uri(uri) try: export_function = getattr(rows, 'export_to_{}'.format(plugin_name)) except AttributeError: raise ValueError('Plugin (export) "{}" not found'.format(plugin_name)) return export_function(table, uri, *args, **kwargs) rows-0.2.1/setup.py000066400000000000000000000056651275267602200142430ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2016 Álvaro Justen # # 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 . from setuptools import setup EXTRA_REQUIREMENTS = { 'csv': ['unicodecsv'], 'cli': ['click', 'requests'], 'html': ['lxml'], # apt: libxslt-dev libxml2-dev 'ods': ['lxml'], 'parquet': ['parquet'], 'xls': ['xlrd', 'xlwt'], 'xlsx': ['openpyxl'], 'xpath': ['lxml'], 'detect': ['file-magic'], } EXTRA_REQUIREMENTS['all'] = sum(EXTRA_REQUIREMENTS.values(), []) INSTALL_REQUIREMENTS = EXTRA_REQUIREMENTS['csv'] LONG_DESCRIPTION = ''' No matter in which format your tabular data is: rows will import it, automatically detect types and give you high-level Python objects so you can start working with the data instead of trying to parse it. It is also locale-and-unicode aware. :) See a quick start tutorial at: https://github.com/turicas/rows/blob/develop/README.md '''.strip() setup(name='rows', description=('A common, beautiful interface to tabular data, ' 'no matter the format'), long_description=LONG_DESCRIPTION, version='0.2.1', author=u'Álvaro Justen', author_email='alvarojusten@gmail.com', url='https://github.com/turicas/rows/', packages=['rows', 'rows.plugins'], install_requires=INSTALL_REQUIREMENTS, extras_require=EXTRA_REQUIREMENTS, keywords=['tabular', 'table', 'csv', 'xls', 'xlsx', 'xpath', 'sqlite', 'html', 'rows', 'data', 'opendata'], entry_points = { 'console_scripts': [ 'rows = rows.cli:cli', ], }, classifiers = [ 'Development Status :: 5 - Production/Stable', 'Environment :: Console', 'Intended Audience :: Developers', 'Intended Audience :: Science/Research', 'Intended Audience :: System Administrators', 'License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)', 'Natural Language :: English', 'Operating System :: OS Independent', 'Programming Language :: Python :: 2.7', 'Topic :: Database', 'Topic :: Software Development :: Libraries :: Python Modules', 'Topic :: Text Processing :: Markup :: HTML', 'Topic :: Utilities', ] ) rows-0.2.1/tests/000077500000000000000000000000001275267602200136575ustar00rootroot00000000000000rows-0.2.1/tests/__init__.py000066400000000000000000000000001275267602200157560ustar00rootroot00000000000000rows-0.2.1/tests/data/000077500000000000000000000000001275267602200145705ustar00rootroot00000000000000rows-0.2.1/tests/data/all-field-types.csv000066400000000000000000000010171275267602200202770ustar00rootroot00000000000000bool_column,integer_column,float_column,decimal_column,percent_column,date_column,datetime_column,unicode_column True,1,3.141592,3.141592,1%,2015-01-01,2015-08-18T15:10:00,Álvaro False,2,1.234,1.234,11.69%,1999-02-03,1999-02-03T00:01:02,àáãâä¹²³ true,3,4.56,4.56,12%,2050-01-02,2050-01-02T23:45:31,éèẽêë false,4,7.89,7.89,13.64%,2015-08-18,2015-08-18T22:21:33,~~~~ yes,5,9.87,9.87,13.14%,2015-03-04,2015-03-04T16:00:01,álvaro no,6,1.2345,1.2345,2%,2015-05-06,2015-05-06T12:01:02,test ,-,null,nil,none,n/a,null, rows-0.2.1/tests/data/all-field-types.html000066400000000000000000000035611275267602200204560ustar00rootroot00000000000000
bool_column integer_column float_column decimal_column percent_column date_column datetime_column unicode_column
True 1 3.141592 3.141592 1% 2015-01-01 2015-08-18T15:10:00 Álvaro
False 2 1.234 1.234 11.69% 1999-02-03 1999-02-03T00:01:02 àáãâä¹²³
true 3 4.56 4.56 12% 2050-01-02 2050-01-02T23:45:31 éèẽêë
false 4 7.89 7.89 13.64% 2015-08-18 2015-08-18T22:21:33 ~~~~
yes 5 9.87 9.87 13.14% 2015-03-04 2015-03-04T16:00:01 álvaro
no 6 1.2345 1.2345 2% 2015-05-06 2015-05-06T12:01:02 test
- null nil none n/a null
rows-0.2.1/tests/data/all-field-types.json000066400000000000000000000040741275267602200204630ustar00rootroot00000000000000[ { "float_column": 3.141592, "decimal_column": 3.141592, "bool_column": "True", "integer_column": 1, "date_column": "2015-01-01", "datetime_column": "2015-08-18T15:10:00", "percent_column": "1%", "unicode_column": "Álvaro" }, { "float_column": 1.234, "decimal_column": 1.234, "bool_column": "False", "integer_column": 2, "date_column": "1999-02-03", "datetime_column": "1999-02-03T00:01:02", "percent_column": "11.69%", "unicode_column": "àáãâä¹²³" }, { "float_column": 4.56, "decimal_column": 4.56, "bool_column": true, "integer_column": 3, "date_column": "2050-01-02", "datetime_column": "2050-01-02T23:45:31", "percent_column": "12%", "unicode_column": "éèẽêë" }, { "float_column": 7.89, "decimal_column": 7.89, "bool_column": false, "integer_column": 4, "date_column": "2015-08-18", "datetime_column": "2015-08-18T22:21:33", "percent_column": "13.64%", "unicode_column": "~~~~" }, { "float_column": 9.87, "decimal_column": 9.87, "bool_column": "yes", "integer_column": 5, "date_column": "2015-03-04", "datetime_column": "2015-03-04T16:00:01", "percent_column": "13.14%", "unicode_column": "álvaro" }, { "float_column": 1.2345, "decimal_column": 1.2345, "bool_column": "no", "integer_column": 6, "date_column": "2015-05-06", "datetime_column": "2015-05-06T12:01:02", "percent_column": "2%", "unicode_column": "test" }, { "float_column": "", "decimal_column": "-", "bool_column": "null", "integer_column": "nil", "date_column": "none", "datetime_column": "n/a", "percent_column": "null", "unicode_column": "" } ] rows-0.2.1/tests/data/all-field-types.ods000066400000000000000000000251221275267602200202740ustar00rootroot00000000000000PKCIl9..mimetypeapplication/vnd.oasis.opendocument.spreadsheetPKCI$$Thumbnails/thumbnail.pngPNG  IHDRkyܒPLTE===DDDKKKTTT[[[ccclllsss|||rXIDATxά64/N"EIb`_Qdz 6lذaÆ 6lذaÆ 6lذaÆ 6l~e;r_͎gR.]1Ҕ间Q(<џʦmW;vheۤof~F#~*=Uϩ~.pY7 -N)}D=H}Hkg[U?C(DkMvJlMB+G/$XxA_?OKɽظ {kv3-D5s}[}w(i>:]lyx4Uvb^J%4B'a+y6Gpi%ҹөQVby^ٸz/#Nn$!aasn,Ǝz\n5vIߗcOοAU}HRIذaÆ 6lذaÆ 6lذaÆ 6lذaÆ 6lذaÆ 6lذaÆ 6lذaÆ 6lذaÆ 6lذaÆ 6lذaÆ 6lذaÆ 6lذaÆ 6lذaÆ 6ߕC>IENDB`PKCI settings.xmlY]s8}_NqRR3qJC>lpd[,y$C~)v;tѹW՗eOqDIC $6ѰsYN&ȃuzQ8Pم1R#^' .: !]_K,1"2"W*qgM+U]+mW k*d@ژrqMh4vͫ $9vgQ&tG~F0w}3hv#Q_lci'u-͉7˪8 t<уZxZ~/HPMzwd`ۚW~i#c퐱s`Tv5mNt3 GzzqmYջִ8aW#5xV[ TUN\(|W$֍%tkIjO3V1Tav ױ푕V;$d(NuF~q%kQlDŕ2 :]{bU_W6Ä2l3C"ttlbª,ɗSa[8!-U$ZU94kܺ{?,N`[B:|OY4'=B#i<;8,4CCR͘7=N=ź~oIϝ8X4=6OKLqm򋡈 ඬ r.V55>2G:j? 7$|q-0lUS!1(t@!54d>'GmvJqG0 |~~ 톥@P02qh^^A#iXVF/a0Cߔ~ T y)eq2(-A3"j,7'~6爟mP.=0ed4A$~.lΥ]Mx?l'{%t-*2>EbpS3 '|7",ad Q?3p3^Ƽ@L/ ٧ !3TfAH $<:wwf5"&wEwx9'N.2A9HA`WA>V!q ijCD"+ݭK@MäĠ ]<E%TcδUi<tNԓ3ڙ{96۞=%Y@Es{7E$dkRDUSV>>,CQBy\(%7%&z/⍀*5\'6̋Ss"99"$V&~V(i[pXh*~ U"^'7q˚U {DtN=3Cbj% yFtOu^?{5;Nm@^ 5eQ>|ȸ#!IoE)gէ+>nѭza\o}.z^fwo_qY;KBJ~&oZh+YTKiwiX%oz Kb(r*>8f;#09Z(KCsԊpԄiRbж:J Ʀ .Ұ3!G:90ٶ䭙Q]=Bh31 D0tܑg >l2l(bڎi:rFg-s-Z53J˲{_onZ<OD]xn2/n -Bf8yTmYiQ,NRH=W0ݚey/Ͽ}OioR;CBഫᴣj p;Ha+ɨUv:>[`8 &'F9K6e$$(نLT7r)5".9c' \t3~e\0t;YOwt,vi"NZE$j=NWz\uFP>HJe8=E {+DŌh> A Md%]t4fwt$QTg_Ml(iT9P@CקXшDnXp'Mߟd:\TnjPL3D$$<'Ysqߵ~s4;742#fx+QP!>/Qdlm\m5[ 5d4OJZUV1c5lD 9%2*VUމQZ$GuEQ߾1?]Ciig[5X3LW9G?oDMw2,L`t޲x-M, .EY%4g8e_ F#Wb;+U|M,+w(ܑy%:D";iH+؃ N> v*N?~Lj_OaOgݓeM3Vqq\v1be"L ntMx5gO]*?VSPlM57=ޟ?ux10z_6xLtT;ǏK,p}-3:C^l\!O<ܿףԎ&|6>{':3~x]gjчIJi3З'B٨נpv'8tu`~(08=OjLu(ѯxzaێCqբI9ԈOu9[8nZbT;P$ФwP.zot^]j_a2z=JJsRGSW aiJXqުs>H+:m'$," 6<Hr ZrN{8t5=`MPxSw( 2K LgyP+97v(8H8 j {z55{u)PBڮ ׇ ;ɥ&c\ZV$ꯝv㢡~ao(Vik6}LcwQ `Xm"$I^0qlb77eOmlG)DS u~mwvj4꓀5o4*aiJ0Cv{EC^/Oxฤ*63E%"/Q 춖m G4**!MP%ʎNS;&+ Rzq_WhPb,D=(9&Zq;HsKT+#i#y,rҜH3ʶb߄-l^Y2R vˏ\Yr^˳pSPΞU|ʢߵQ[6$kacuqw ɒ/:\X|8v`cf7hbr7{wy\b# WdUFVu^WI+"8EخxXH!IQ\ )Js!绫 teaX#=Sؤ^& 'sJq(f k@@ݵ=1d?PK qDPKCIConfigurations2/images/Bitmaps/PKCIConfigurations2/popupmenu/PKCIConfigurations2/statusbar/PKCIConfigurations2/toolpanel/PKCI'Configurations2/accelerator/current.xmlPKPKCIConfigurations2/floater/PKCIConfigurations2/menubar/PKCIConfigurations2/toolbar/PKCIConfigurations2/progressbar/PKCI manifest.rdf͓n02]sUWy|Vw:6B|HwPvʣ`ySR`ZPSl%|qM#ӃXݐyajLOy|qy:(gع\kƬlYrvU/a.ԯ` PKK!EPKCIl9..mimetypePKCI$$TThumbnails/thumbnail.pngPKCI;0c settings.xmlPKCI_!GA  content.xmlPKCIM5meta.xmlPKCI qD styles.xmlPKCI!Configurations2/images/Bitmaps/PKCIN!Configurations2/popupmenu/PKCI!Configurations2/statusbar/PKCI!Configurations2/toolpanel/PKCI'!Configurations2/accelerator/current.xmlPKCIM"Configurations2/floater/PKCI"Configurations2/menubar/PKCI"Configurations2/toolbar/PKCI"Configurations2/progressbar/PKCIh )#manifest.rdfPKCIK!Eh$META-INF/manifest.xmlPKp%rows-0.2.1/tests/data/all-field-types.sqlite000066400000000000000000000200001275267602200207760ustar00rootroot00000000000000SQLite format 3@ - ''Vtabletable1table1CREATE TABLE table1 (bool_column INTEGER, integer_column INTEGER, float_column FLOAT, decimal_column FLOAT, percent_column TEXT, date_column TEXT, datetime_column TEXT, unicode_column TEXT) ,gJ,  -nullnilnonen/anull? !3no?n?n2%2015-05-062015-05-06T12:01:02testG !3yes@#p =@#p =13.14%2015-03-042015-03-04T16:00:01álvaroF !3false@\(@\(13.64%2015-08-182015-08-18T22:21:33~~~~I !3#true@=p =@=p =12%2050-01-022050-01-02T23:45:31éèẽêëR !3-False?vȴ9X?vȴ9X11.69%1999-02-031999-02-03T00:01:02àáãâä¹²³C  !3True@ !z@ !z1%2015-01-012015-08-18T15:10:00Álvarorows-0.2.1/tests/data/all-field-types.txt000066400000000000000000000027351275267602200203330ustar00rootroot00000000000000+-------------+----------------+--------------+----------------+----------------+-------------+---------------------+----------------+ | bool_column | integer_column | float_column | decimal_column | percent_column | date_column | datetime_column | unicode_column | +-------------+----------------+--------------+----------------+----------------+-------------+---------------------+----------------+ | True | 1 | 3.141592 | 3.141592 | 1% | 2015-01-01 | 2015-08-18T15:10:00 | Álvaro | | False | 2 | 1.234 | 1.234 | 11.69% | 1999-02-03 | 1999-02-03T00:01:02 | àáãâä¹²³ | | true | 3 | 4.56 | 4.56 | 12% | 2050-01-02 | 2050-01-02T23:45:31 | éèẽêë | | false | 4 | 7.89 | 7.89 | 13.64% | 2015-08-18 | 2015-08-18T22:21:33 | ~~~~ | | yes | 5 | 9.87 | 9.87 | 13.14% | 2015-03-04 | 2015-03-04T16:00:01 | álvaro | | no | 6 | 1.2345 | 1.2345 | 2% | 2015-05-06 | 2015-05-06T12:01:02 | test | | | - | null | nil | none | n/a | null | | +-------------+----------------+--------------+----------------+----------------+-------------+---------------------+----------------+ rows-0.2.1/tests/data/all-field-types.xls000066400000000000000000000160001275267602200203100ustar00rootroot00000000000000ࡱ;   Root Entry  !"#$%&'()*+,-./025678:  \pCalc Ba==@ 8@"1Arial1Arial1Arial1Arial General 0.00%MMM\ D", "YYYYYYYY\-MM\-DD\ HH:MM:SS@                + ) , *           `Sheet1TZR3  @@   bool_columninteger_column float_columndecimal_columnpercent_column date_columndatetime_columnunicode_columnlvaro乲truefalse~~~~yeslvaronotest-nullnilnonen/acc   dMbP?_%*+&C&P&C&F&333333?'333333?(-؂-؂?)[[?" d,,??U }  } } x}  %%%%%%%%        ~ z! @z! @V98T@ ~  X9v?X9v?(?~ 5@@   ~ > ףp=@> ףp=@3X@   W W R!u?~ ]@  ~ = ףp#@= ףp#@X?~ NmUu@  ~ n?n? JP@       PH0(  >@gg  FMicrosoft Excel 97-TabelleBiff8Oh+'0 px 7@Ύ@@@ܭ,՜.+,D՜.+,\Root EntryFWorkbook6 CompObj1IOle 3SummaryInformation(48DocumentSummaryInformation89trows-0.2.1/tests/data/all-field-types.xlsx000066400000000000000000000125251275267602200205100ustar00rootroot00000000000000PKI _rels/.relsJ1}{wDdЛH}a70u}{ZI~7CfGFoZ+{kW#VJ$cʪl n0\QX^:`dd{m]_dhVFw^F9W-(F/3ODSUNl/w{N([qTu| V/y$E'0l4ekzwpPW)f}vvo84_ R>/PK\uRPKIxl/_rels/workbook.xml.relsMk0 FIc8AQ6ֵ~.[ eГH4C vV͢h%؀I/Z8Y.b;]JNɺQ/IӜS[n+Psc _{0 r3Rb+/2m=?"#ʯR6w _fz o ۭP~$E|PKOz%PKIxl/workbook.xmlSn0+m-v\۰8MΔ4XS@(+MzY\K bu!.fy* bvn'm{W6fb3}WPs; (4;6xa+įPCe)rXPĀHm%˖RHxx|5N̙|x&옕\ZF+}}#.% ΂qFʤ2lONw56E+r-eՈ(_m;Gy~Чъ.o'w}Vh:}w vl"!Al6XtE N@Ztv֟ru_-U: t: +2I\PCaݜ/ 'B ']ĊЮ\5HDra ghѝW%IM$EfӏFI4Ih 77 ݤ) .Y''ʡI: #Pn/s'U9 WO{a,PKĥuPKI xl/styles.xmlYn0SX4!IKfY'-SդҦu.`8mҧ@ ]MZ*ۇ;>>92p6C\6›A,  yerE4X! #vG'>!)F 8I 6Maб"2._09V]|63,/7?\̮o`|i![*yh4[˯%_N"oht ./'tK. 32lmvj'J7SVb>D죐Е Hii'7iD(-ljC 8vĂUd*R.35C4M@V[JH y-C#h7Ј?tl}I)yd$$RPUk\TT.tL/z"]ϧ#KjHgU͔5P՘'$R,p!茒9 F2]RرQ.ȓN^<[ L7x!x)DEiz()00/X=AIX2=rTj)XNkZu}tnUNnlS{n5b1FL#>픝^앚>g1FsU+/K/L/4jVǶ^c[mulԶmf/5#\KWf@Ar8YZ2nA$,kX \c6i.xխH *Be@3wU0*Lݙ*ޟ]a7^ *DDCz'PK0PKIxl/worksheets/sheet1.xmlXKs6Wpx贇Leeb=8'r`1! ؿ ($$ra}4v7k95H1>/JLPIk|c|?m{[` pP7fyζu+Z5U#m0d=lj stхۖӪ4hGC ߡLFMå EÉ)Jt u7u&N#nu{19b#sRG;#uD|DؠQ2x20WV5/_9oAN>:· SUK (.;?nPEPXnK4L5K V'Ek+tkO|&(&DYn sG]&`:.`peX8T}(:  旀JʴXFaJwDYizQoHE uNnC]E$[2痀H~‘P[wOwPn k?oUd[_Q4G&Gs90QwP"Po[$Hlޕ'r_JξaJāO+N'j,].Ui e+rh d'2(*FLwE59`G51QtNY D{=km-x %3:ƩzE1l\&""I+|{.e%0@^s^Wie䕺ο4Q`mh24D@8MPKuv7PKI[Content_Types].xmlAK1KmG-Xnnfb{'k"B[ZdɃ}mzWiQ ƺ/ˇVgj @:Ect p|ث[ldPzey#w\cqh d QP Б,*/AbBY"'7;RR=@W $} E; W+={0Ҁ[F DZG8}פ>8th?<߼_'}Y)S@PZÏuХ7$2?hyȯA{Tr(fPK_6X0WPKIf; _rels/.relsPKI@5}docProps/app.xmlPKI\uRCdocProps/core.xmlPKIOz%xl/_rels/workbook.xml.relsPKIĥuxl/workbook.xmlPKI0 )xl/styles.xmlPKIJNWy xl/worksheets/sheet1.xmlPKIuv7xl/sharedStrings.xmlPKI_6X0W[Content_Types].xmlPK ?rows-0.2.1/tests/data/colspan-table.html000066400000000000000000000004071275267602200202030ustar00rootroot00000000000000
huge title
field1 field2
row1field1 row1field2
row2field1 row2field2
rows-0.2.1/tests/data/ecuador-medios-radiodifusoras.csv000066400000000000000000000061411275267602200232230ustar00rootroot00000000000000url,name,address,phone,website,email /es/informate-y-participa/directorio-de-medios/28-ecos-de-cayambe-1470-am,Ecos de Cayambe (1470 AM),Terán 52-91 y 10 de Agosto,02 236 0047 / 236 3055,www.ecosdecayambe.es.tl,ecos@pi.pro.ec /es/informate-y-participa/directorio-de-medios/29-jm-radio-88-9-fm,JM Radio (88.9 FM),Cristóbal Colón y Panzaleo,02 231 6642,,www.jmradio.net /es/informate-y-participa/directorio-de-medios/191-activa-88-5fm,Activa (88.5FM),"Av. Miguel Cordero y Av. Paucarbamba Ed. Work Center Piso 5, Of. 508",07 281 4688 / 281 9992 / 288 1088,www.fm88radioactiva.com,radio@cadencactiva.com /es/informate-y-participa/directorio-de-medios/192-alfa-musical-1140am,Alfa Musical (1140AM),Hermano Miguel 1068 y Gran Colombia,07 283 8451,,radioalfa1140am@hotmail.com /es/informate-y-participa/directorio-de-medios/193-catolica-nacional-98-1fm-cuenca-paute-gualaceo,"Católica Nacional (98.1FM) (Cuenca, Paute, Gualaceo)",Bolívar 9-49 y Luis Cordero,07 282 5845 / 283 8292 / 283 2280,www.radiocatolicacuenca.com.ec,radiocatolicacuenca@gmail.com /es/informate-y-participa/directorio-de-medios/194-contacot-xg-1260am,Contacot XG (1260AM),Jesús Dávila y Cornelio Merchán,07 288 1240 / 281 4164,www.contactoxg.webpin.com,radionexo.fem@hotmail.com /es/informate-y-participa/directorio-de-medios/195-cosmos-fm-97-3fm-cuenca-paute,"Cosmos FM (97.3FM) (Cuenca, Paute)",Av. Abelardo J. Andrade 2-07 y Francisco Tamariz,07 283 1423 / 284 2837,www.cosmos.ec,cosmos@rcgrupo.com /es/informate-y-participa/directorio-de-medios/196-cuenca-la-voz-de-los-cuatro-rios-1180am,Cuenca La Voz de los Cuatro Ríos (1180AM),Bomboíza 1-83 entre Loja y Pastaza,07 288 4128,www.radiocuenca.com,kleberpinosabad@yahoo.es / radiocuenca1180@hotmail.com /es/informate-y-participa/directorio-de-medios/197-el-mercurio-1200am,El Mercurio (1200AM),Av. de las Américas y Francisco Azcásubi Ed. Mercurio,07 409 5684 / 409 5645,www.radioelmercurio.com.ec,radioinfo@radioelmercurio.com.ec /es/informate-y-participa/directorio-de-medios/198-la-voz-de-tomebamba-am-fm-1-070am-102-1fm-cuenca-giron-paute,"La Voz de Tomebamba AM / FM (1.070AM; 102.1FM) (Cuenca, Girón, Paute)","Benigno Malo 15-91 y Muñoz Vernaza, esquina",07 284 2000 / 282 5301 / 284 2222,www.lavozdeltomebamba.com,info@lavozdeltomebamba.com /es/informate-y-participa/directorio-de-medios/199-ondas-azuayas-1110-am,Ondas Azuayas (1110 AM),Héroes de Verdeloma 915 y Francisco Tamariz,07 282 3911 / 283 1975 / 283 1792 / 284 4485,www.ondasazuayas.ec,max_azuayas@hotmail.com /es/informate-y-participa/directorio-de-medios/200-infinito-fm-97-5-fm,Infinito FM (97.5 FM),Av. Sixto Durán Ballen y Vega Dávila,07 294 4899,www.radioinfinito.ser.ec,radioinfinito@hotmail.com /es/informate-y-participa/directorio-de-medios/201-radio-super-94-9fm-cuenca-giron-paute,"Radio Súper (94.9FM) (Cuenca, Girón, Paute)","Benigno Malo 1591 y Muñoz Vernaza, esquina",07 284 2949 / 284 2949 / 282 5301,www.super949.com,Súper949@gmail.com /es/informate-y-participa/directorio-de-medios/202-tropicana-1380am,Tropicana (1390AM),Av. Pumapungo 5-50 y Juan Benigno Vela,07 280 7970 / 280 9644,www.radiotropicana1390.com,radiotropicana1390@hotmail.com rows-0.2.1/tests/data/ecuador-medios-radiodifusoras.html000066400000000000000000002127631275267602200234050ustar00rootroot00000000000000 Directorio de medios - Radiodifusoras - Página 1 de 7

Radiodifusoras

Ecos de Cayambe (1470 AM)

D: Terán 52-91 y 10 de Agosto
T: 02 236 0047 / 236 3055
W: www.ecosdecayambe.es.tl
E: ecos@pi.pro.ec

JM Radio (88.9 FM)

D: Cristóbal Colón y Panzaleo
T: 02 231 6642
F: 02 231 0836
E: www.jmradio.net

Activa (88.5FM)

D: Av. Miguel Cordero y Av. Paucarbamba Ed. Work Center Piso 5, Of. 508
T: 07 281 4688 / 281 9992 / 288 1088
F: 07 281 9992
W: www.fm88radioactiva.com
E: radio@cadencactiva.com
T: @fm88radioactiva

Alfa Musical (1140AM)

D: Hermano Miguel 1068 y Gran Colombia
T: 07 283 8451
F: 07 283 8714
E: radioalfa1140am@hotmail.com
T: @radioalfaec

Católica Nacional (98.1FM) (Cuenca, Paute, Gualaceo)

D: Bolívar 9-49 y Luis Cordero
T: 07 282 5845 / 283 8292 / 283 2280
F: 07 282 5845 / 254 1557 / 284 4436
W: www.radiocatolicacuenca.com.ec
E: radiocatolicacuenca@gmail.com
T: @RadioCatolicaC

Contacot XG (1260AM)

D: Jesús Dávila y Cornelio Merchán
T: 07 288 1240 / 281 4164
F: 07 288 0691
W: www.contactoxg.webpin.com
E: radionexo.fem@hotmail.com

Cosmos FM (97.3FM) (Cuenca, Paute)

D: Av. Abelardo J. Andrade 2-07 y Francisco Tamariz
T: 07 283 1423 / 284 2837
F: 07 284 3727
W: www.cosmos.ec
E: cosmos@rcgrupo.com

Cuenca La Voz de los Cuatro Ríos (1180AM)

D: Bomboíza 1-83 entre Loja y Pastaza
T: 07 288 4128
F: 07 288 4128
W: www.radiocuenca.com
E: kleberpinosabad@yahoo.es / radiocuenca1180@hotmail.com

El Mercurio (1200AM)

D: Av. de las Américas y Francisco Azcásubi Ed. Mercurio
T: 07 409 5684 / 409 5645
F: 07 409 5684
W: www.radioelmercurio.com.ec
E: radioinfo@radioelmercurio.com.ec
T: @radioelmercurio

La Voz de Tomebamba AM / FM (1.070AM; 102.1FM) (Cuenca, Girón, Paute)

D: Benigno Malo 15-91 y Muñoz Vernaza, esquina
T: 07 284 2000 / 282 5301 / 284 2222
F: 07 284 2222
W: www.lavozdeltomebamba.com
E: info@lavozdeltomebamba.com
T: @tomebamba

Ondas Azuayas (1110 AM)

D: Héroes de Verdeloma 915 y Francisco Tamariz
T: 07 282 3911 / 283 1975 / 283 1792 / 284 4485
F: 07 283 9067
W: www.ondasazuayas.ec
E: max_azuayas@hotmail.com
T: @ondasazuayas

Infinito FM (97.5 FM)

D: Av. Sixto Durán Ballen y Vega Dávila
T: 07 294 4899
W: www.radioinfinito.ser.ec
E: radioinfinito@hotmail.com
T: @RADIOINFINITOFM

Radio Súper (94.9FM) (Cuenca, Girón, Paute)

D: Benigno Malo 1591 y Muñoz Vernaza, esquina
T: 07 284 2949 / 284 2949 / 282 5301
F: 07 284 2222
W: www.super949.com
E: Súper949@gmail.com
T: @super949

Tropicana (1390AM)

D: Av. Pumapungo 5-50 y Juan Benigno Vela
T: 07 280 7970 / 280 9644
F: 07 280 9644
W: www.radiotropicana1390.com
E: radiotropicana1390@hotmail.com
¡Haga clic para escuchar el texto resaltado!
rows-0.2.1/tests/data/ibge-censo.html000066400000000000000000000672161275267602200175050ustar00rootroot00000000000000
uf município pessoas
RJ Angra dos Reis 169.511
RJ Aperibé 10.213
RJ Araruama 112.008
RJ Areal 11.423
RJ Armação dos Búzios 27.560
RJ Arraial do Cabo 27.715
RJ Barra do Piraí 94.778
RJ Barra Mansa 177.813
RJ Belford Roxo 469.332
RJ Bom Jardim 25.333
RJ Bom Jesus do Itabapoana 35.411
RJ Cabo Frio 186.227
RJ Cachoeiras de Macacu 54.273
RJ Cambuci 14.827
RJ Campos dos Goytacazes 463.731
RJ Cantagalo 19.830
RJ Carapebus 13.359
RJ Cardoso Moreira 12.600
RJ Carmo 17.434
RJ Casimiro de Abreu 35.347
RJ Comendador Levy Gasparian 8.180
RJ Conceição de Macabu 21.211
RJ Cordeiro 20.430
RJ Duas Barras 10.930
RJ Duque de Caxias 855.048
RJ Engenheiro Paulo de Frontin 13.237
RJ Guapimirim 51.483
RJ Iguaba Grande 22.851
RJ Itaboraí 218.008
RJ Itaguaí 109.091
RJ Italva 14.063
RJ Itaocara 22.899
RJ Itaperuna 95.841
RJ Itatiaia 28.783
RJ Japeri 95.492
RJ Laje do Muriaé 7.487
RJ Macaé 206.728
RJ Macuco 5.269
RJ Magé 227.322
RJ Mangaratiba 36.456
RJ Maricá 127.461
RJ Mendes 17.935
RJ Mesquita 168.376
RJ Miguel Pereira 24.642
RJ Miracema 26.843
RJ Natividade 15.082
RJ Nilópolis 157.425
RJ Niterói 487.562
RJ Nova Friburgo 182.082
RJ Nova Iguaçu 796.257
RJ Paracambi 47.124
RJ Paraíba do Sul 41.084
RJ Paraty 37.533
RJ Paty do Alferes 26.359
RJ Petrópolis 295.917
RJ Pinheiral 22.719
RJ Piraí 26.314
RJ Porciúncula 17.760
RJ Porto Real 16.592
RJ Quatis 12.793
RJ Queimados 137.962
RJ Quissamã 20.242
RJ Resende 119.769
RJ Rio Bonito 55.551
RJ Rio Claro 17.425
RJ Rio das Flores 8.561
RJ Rio das Ostras 105.676
RJ Rio de Janeiro 6.320.446
RJ Santa Maria Madalena 10.321
RJ Santo Antônio de Pádua 40.589
RJ São Fidélis 37.543
RJ São Francisco de Itabapoana 41.354
RJ São Gonçalo 999.728
RJ São João da Barra 32.747
RJ São João de Meriti 458.673
RJ São José de Ubá 7.003
RJ São José do Vale do Rio Preto 20.251
RJ São Pedro da Aldeia 87.875
RJ São Sebastião do Alto 8.895
RJ Sapucaia 17.525
RJ Saquarema 74.234
RJ Seropédica 78.186
RJ Silva Jardim 21.349
RJ Sumidouro 14.900
RJ Tanguá 30.732
RJ Teresópolis 163.746
RJ Trajano de Moraes 10.289
RJ Três Rios 77.432
RJ Valença 71.843
RJ Varre-Sai 9.475
RJ Vassouras 34.410
RJ Volta Redonda 257.803
rows-0.2.1/tests/data/merged.csv000066400000000000000000000001421275267602200165450ustar00rootroot00000000000000id,username,birthday,gender 1,turicas,1987-04-29,M 2,abc,,F 3,def,2000-01-01,F 4,qwe,1999-12-31,F rows-0.2.1/tests/data/nation.dict.parquet000077500000000000000000000054421275267602200204150ustar00rootroot00000000000000PAR1,22 L2ALGERIA ARGENTINABRAZILCANADAEGYPTETHIOPIAFRANCEGERMANYINDIA INDONESIAIRANIRAQJAPANJORDANKENYAMOROCCO MOZAMBIQUEPERUCHINAROMANIA SAUDI ARABIAVIETNAMRUSSIAUNITED KINGDOM UNITED STATES88,22 A9(Ś{0I,22L23 haggle. carefully final deposits detect slyly agaiLal foxes promise slyly according to the regular accounts. bold requests alonky alongside of the pending deposits. carefully special packages are about the ironic forges. slyly special eeas hang ironic, silent packages. slyly regular packages are furiously over the tithes. fluffily boldcy above the carefully unusual theodolites. final dugouts are quickly across the furiously regular dven packages wake quickly. regu&refully final requests. regular, ironi:l platelets. regular accounts x-ray: unusual, regular accoAss excuses cajole slyly across the packages. deposits print arounr slyly express asymptotes. regular deposits haggle slyly. carefully ironic hockey players sleep blithely. carefull2efully alongside of the slyly final dependencies. Bnic deposits boost atop the quickly final requests? quickly regula$ously. final, express gifts cajole a7ic deposits are blithely about the carefully regular pa] pending excuses haggle furiously deposits. pending, express pinto beans wake fluffily past tZrns. blithely bold courts among the closely regular packages use furiously bold platelets?-s. ironic, unusual asymptotes wake blithely rjplatelets. blithely pending dependencies use fluffily across the even pinto beans. carefully silent accoun[c dependencies. furiously express notornis sleep slyly regular accounts. ideas sleep. deposoular asymptotes are about the furious multipliers. express dependencies nag above the ironically ironic accountNts. silent requests haggle. closely express packages sleep across the blithely.hely enticingly express accounts. even, final O requests against the platelets use never according to the quickly regular pint=eans boost carefully special requests. accounts are. carefullny final packages. slow foxes cajole quickly. quickly silent platelets breach ironic accounts. unusual pinto be88,22 A9(Ś{0I\Hm% nation_key %name% region_key % comment_col2L& nation_key2&& name2&& region_key2&&   comment_col2& 2( parquet-mrPAR1rows-0.2.1/tests/data/nested-table.html000066400000000000000000000022271275267602200200300ustar00rootroot00000000000000
t0,0r0c0 t0,0r0c1 t0,0r0c2
t0,0r1c0 t0,0r1c1 t0,0r1c2
t0,0r2c0
t0,1r0c0 t0,1r0c1
t0,1r1c0 t0,1r1c1
t0,1r2c0 t0,1r2c1
t0,2r0c0 t0,2r0c1
t0,2r1c0 t0,2r1c1
t0,1r3c1
t0,1r4c0 t0,1r4c1
t0,1r5c0 t0,1r5c1
t0,0r2c2
t0,0r3c0 t0,0r3c1 t0,0r3c2
rows-0.2.1/tests/data/properties-table.html000066400000000000000000000004521275267602200207400ustar00rootroot00000000000000
field1 field2
row1field1 row1field2
row2field1 row2field2
rows-0.2.1/tests/data/scripts/000077500000000000000000000000001275267602200162575ustar00rootroot00000000000000rows-0.2.1/tests/data/scripts/create_sqlite.py000066400000000000000000000022621275267602200214570ustar00rootroot00000000000000# coding: utf-8 import os import sqlite3 from collections import OrderedDict input_filename = '../all-field-types.csv' output_filename = '../all-field-types.sqlite' field_types = OrderedDict([ ('bool_column', 'INTEGER'), ('integer_column', 'INTEGER'), ('float_column', 'FLOAT'), ('decimal_column', 'FLOAT'), ('percent_column', 'TEXT'), ('date_column', 'TEXT'), ('datetime_column', 'TEXT'), ('unicode_column', 'TEXT'), ]) column_types = ', '.join(['{} {}'.format(key, value) for key, value in field_types.items()]) create_sql = 'CREATE TABLE table1 ({})'.format(column_types) field_names = ', '.join(field_types.keys()) placeholders = ', '.join(['?' for _ in field_types]) insert_sql = 'INSERT INTO table1 ({}) VALUES ({})'.format(field_names, placeholders) if os.path.exists(output_filename): os.unlink(output_filename) connection = sqlite3.connect(output_filename) connection.execute(create_sql) with open(input_filename) as fobj: data = fobj.read().decode('utf-8').splitlines() for row in data[1:]: connection.execute(insert_sql, row.split(',')) connection.commit() rows-0.2.1/tests/data/simple-table.html000066400000000000000000000005121275267602200200320ustar00rootroot00000000000000
t0r0c0 t0r0c1
t0r1c0 t0r1c1
t1r0c0 t1r0c1
t1r1c0 t1r1c1
t1r2c0 t1r2c1
rows-0.2.1/tests/data/table-thead-tbody.html000066400000000000000000000003141275267602200207450ustar00rootroot00000000000000
t1 t2
456 123
qqq aaa
rows-0.2.1/tests/data/table-with-sections.html000066400000000000000000000031131275267602200213410ustar00rootroot00000000000000
t2r0c0 t2r0c1
t2r0c0 t2r0c1
t2r1c0 t2r1c1
t2r2c0 t2r2c1
id username name signup_date
1 turicas Álvaro Justen 2014-04-01
2 test Test User 2014-04-02
3 example Example User 2014-04-03
4 python Python Heavy User 2014-04-04
5 erlang Erlang User 2014-04-05
rows-0.2.1/tests/data/to-merge-1.csv000066400000000000000000000000421275267602200171560ustar00rootroot00000000000000id,username 1,turicas 2,abc 3,def rows-0.2.1/tests/data/to-merge-2.csv000066400000000000000000000001141275267602200171570ustar00rootroot00000000000000id,username,birthday 1,turicas,1987-04-29 3,def,2000-01-01 4,qwe,1999-12-31 rows-0.2.1/tests/data/to-merge-3.csv000066400000000000000000000000671275267602200171670ustar00rootroot00000000000000id,username,gender 1,turicas,M 2,abc,F 3,def,F 4,qwe,F rows-0.2.1/tests/tests_cli.py000066400000000000000000000016221275267602200162230ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import unittest import rows.cli as cli class CliTestCase(unittest.TestCase): # TODO: test everything pass rows-0.2.1/tests/tests_fields.py000066400000000000000000000460271275267602200167320ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import collections import datetime import json import platform import types import unittest from decimal import Decimal import rows from rows import fields if platform.system() == 'Windows': locale_name = str('ptb_bra') else: locale_name = 'pt_BR.UTF-8' class FieldsTestCase(unittest.TestCase): def test_Field(self): self.assertEqual(fields.Field.TYPE, (types.NoneType, )) self.assertIs(fields.Field.deserialize(None), None) self.assertEqual(fields.Field.deserialize('Álvaro'), 'Álvaro') self.assertEqual(fields.Field.serialize(None), '') self.assertIs(type(fields.Field.serialize(None)), types.UnicodeType) self.assertEqual(fields.Field.serialize('Álvaro'), 'Álvaro') self.assertIs(type(fields.Field.serialize('Álvaro')), types.UnicodeType) def test_BinaryField(self): serialized = 'Álvaro'.encode('utf-8') self.assertEqual(fields.BinaryField.TYPE, (types.StringType, )) self.assertIs(fields.BinaryField.deserialize(None), None) self.assertEqual(fields.BinaryField.deserialize(serialized), serialized) self.assertIs(type(fields.BinaryField.deserialize(serialized)), types.StringType) self.assertEqual(fields.BinaryField.serialize(None), '') self.assertIs(type(fields.BinaryField.serialize(None)), types.StringType) self.assertEqual(fields.BinaryField.serialize(serialized), serialized) self.assertIs(type(fields.BinaryField.serialize(serialized)), types.StringType) def test_BoolField(self): self.assertEqual(fields.BoolField.TYPE, (bool, )) self.assertEqual(fields.BoolField.serialize(None), '') false_values = ('False', b'False', 'false', b'false', 'no', b'no', False) for value in false_values: self.assertIs(fields.BoolField.deserialize(value), False) self.assertIs(fields.BoolField.deserialize(None), None) self.assertEqual(fields.BoolField.deserialize(''), None) true_values = ('True', b'True', 'true', b'true', 'yes', b'yes', True) for value in true_values: self.assertIs(fields.BoolField.deserialize(value), True) self.assertEqual(fields.BoolField.serialize(False), 'false') self.assertIs(type(fields.BoolField.serialize(False)), types.UnicodeType) self.assertEqual(fields.BoolField.serialize(True), 'true') self.assertIs(type(fields.BoolField.serialize(True)), types.UnicodeType) # '0' and '1' should be not accepted as boolean values because the # sample could not contain other integers but the actual type could be # integer with self.assertRaises(ValueError): fields.BoolField.deserialize('0') with self.assertRaises(ValueError): fields.BoolField.deserialize(b'0') with self.assertRaises(ValueError): fields.BoolField.deserialize('1') with self.assertRaises(ValueError): fields.BoolField.deserialize(b'1') def test_IntegerField(self): self.assertEqual(fields.IntegerField.TYPE, (int, )) self.assertEqual(fields.IntegerField.serialize(None), '') self.assertIs(type(fields.IntegerField.serialize(None)), types.UnicodeType) self.assertIn(type(fields.IntegerField.deserialize('42')), fields.IntegerField.TYPE) self.assertEqual(fields.IntegerField.deserialize('42'), 42) self.assertEqual(fields.IntegerField.deserialize(42), 42) self.assertEqual(fields.IntegerField.serialize(42), '42') self.assertIs(type(fields.IntegerField.serialize(42)), types.UnicodeType) self.assertEqual(fields.IntegerField.deserialize(None), None) self.assertEqual(fields.IntegerField.deserialize('10152709355006317'), 10152709355006317) with rows.locale_context(locale_name): self.assertEqual(fields.IntegerField.serialize(42000), '42000') self.assertIs(type(fields.IntegerField.serialize(42000)), types.UnicodeType) self.assertEqual(fields.IntegerField.serialize(42000, grouping=True), '42.000') self.assertEqual(fields.IntegerField.deserialize('42.000'), 42000) self.assertEqual(fields.IntegerField.deserialize(42), 42) self.assertEqual(fields.IntegerField.deserialize(42.0), 42) with self.assertRaises(ValueError): fields.IntegerField.deserialize(1.23) def test_FloatField(self): self.assertEqual(fields.FloatField.TYPE, (float, )) self.assertEqual(fields.FloatField.serialize(None), '') self.assertIs(type(fields.FloatField.serialize(None)), types.UnicodeType) self.assertIn(type(fields.FloatField.deserialize('42.0')), fields.FloatField.TYPE) self.assertEqual(fields.FloatField.deserialize('42.0'), 42.0) self.assertEqual(fields.FloatField.deserialize(42.0), 42.0) self.assertEqual(fields.FloatField.deserialize(42), 42.0) self.assertEqual(fields.FloatField.deserialize(None), None) self.assertEqual(fields.FloatField.serialize(42.0), '42.0') self.assertIs(type(fields.FloatField.serialize(42.0)), types.UnicodeType) with rows.locale_context(locale_name): self.assertEqual(fields.FloatField.serialize(42000.0), '42000,000000') self.assertIs(type(fields.FloatField.serialize(42000.0)), types.UnicodeType) self.assertEqual(fields.FloatField.serialize(42000, grouping=True), '42.000,000000') self.assertEqual(fields.FloatField.deserialize('42.000,00'), 42000.0) self.assertEqual(fields.FloatField.deserialize(42), 42.0) self.assertEqual(fields.FloatField.deserialize(42.0), 42.0) def test_DecimalField(self): deserialized = Decimal('42.010') self.assertEqual(fields.DecimalField.TYPE, (Decimal, )) self.assertEqual(fields.DecimalField.serialize(None), '') self.assertIs(type(fields.DecimalField.serialize(None)), types.UnicodeType) self.assertEqual(fields.DecimalField.deserialize(''), None) self.assertIn(type(fields.DecimalField.deserialize('42.0')), fields.DecimalField.TYPE) self.assertEqual(fields.DecimalField.deserialize('42.0'), Decimal('42.0')) self.assertEqual(fields.DecimalField.deserialize(deserialized), deserialized) self.assertEqual(fields.DecimalField.serialize(deserialized), '42.010') self.assertEqual(type(fields.DecimalField.serialize(deserialized)), types.UnicodeType) self.assertEqual(fields.DecimalField.deserialize('21.21657469231'), Decimal('21.21657469231')) self.assertEqual(fields.DecimalField.deserialize(None), None) with rows.locale_context(locale_name): self.assertEqual( types.UnicodeType, type(fields.DecimalField.serialize(deserialized)) ) self.assertEqual(fields.DecimalField.serialize(Decimal('4200')), '4200') self.assertEqual(fields.DecimalField.serialize(Decimal('42.0')), '42,0') self.assertEqual(fields.DecimalField.serialize(Decimal('42000.0')), '42000,0') self.assertEqual(fields.DecimalField.deserialize('42.000,00'), Decimal('42000.00')) self.assertEqual( fields.DecimalField.serialize( Decimal('42000.0'), grouping=True ), '42.000,0' ) self.assertEqual(fields.DecimalField.deserialize(42000), Decimal('42000')) self.assertEqual(fields.DecimalField.deserialize(42000.0), Decimal('42000')) def test_PercentField(self): deserialized = Decimal('0.42010') self.assertEqual(fields.PercentField.TYPE, (Decimal, )) self.assertIn(type(fields.PercentField.deserialize('42.0%')), fields.PercentField.TYPE) self.assertEqual(fields.PercentField.deserialize('42.0%'), Decimal('0.420')) self.assertEqual(fields.PercentField.deserialize(Decimal('0.420')), Decimal('0.420')) self.assertEqual(fields.PercentField.deserialize(deserialized), deserialized) self.assertEqual(fields.PercentField.deserialize(None), None) self.assertEqual(fields.PercentField.serialize(deserialized), '42.010%') self.assertEqual(type(fields.PercentField.serialize(deserialized)), types.UnicodeType) self.assertEqual(fields.PercentField.serialize(Decimal('42.010')), '4201.0%') self.assertEqual(fields.PercentField.serialize(Decimal('0')), '0.00%') self.assertEqual(fields.PercentField.serialize(None), '') self.assertEqual(fields.PercentField.serialize(Decimal('0.01')), '1%') with rows.locale_context(locale_name): self.assertEqual( type(fields.PercentField.serialize(deserialized)), types.UnicodeType ) self.assertEqual(fields.PercentField.serialize(Decimal('42.0')), '4200%') self.assertEqual(fields.PercentField.serialize(Decimal('42000.0')), '4200000%') self.assertEqual(fields.PercentField.deserialize('42.000,00%'), Decimal('420.0000')) self.assertEqual(fields.PercentField.serialize(Decimal('42000.00'), grouping=True), '4.200.000%') with self.assertRaises(ValueError): fields.PercentField.deserialize(42) def test_DateField(self): # TODO: test timezone-aware datetime.date serialized = types.StringType('2015-05-27') deserialized = datetime.date(2015, 5, 27) self.assertEqual(fields.DateField.TYPE, (datetime.date, )) self.assertEqual(fields.DateField.serialize(None), '') self.assertIs(type(fields.DateField.serialize(None)), types.UnicodeType) self.assertIn(type(fields.DateField.deserialize(serialized)), fields.DateField.TYPE) self.assertEqual(fields.DateField.deserialize(serialized), deserialized) self.assertEqual(fields.DateField.deserialize(deserialized), deserialized) self.assertEqual(fields.DateField.deserialize(None), None) self.assertEqual(fields.DateField.deserialize(''), None) self.assertEqual(fields.DateField.serialize(deserialized), serialized) self.assertIs(type(fields.DateField.serialize(deserialized)), types.UnicodeType) with self.assertRaises(ValueError): fields.DateField.deserialize(42) with self.assertRaises(ValueError): fields.DateField.deserialize(serialized + 'T00:00:00') with self.assertRaises(ValueError): fields.DateField.deserialize('Álvaro') def test_DatetimeField(self): # TODO: test timezone-aware datetime.date serialized = types.StringType('2015-05-27T01:02:03') self.assertEqual(fields.DatetimeField.TYPE, (datetime.datetime, )) deserialized = fields.DatetimeField.deserialize(serialized) self.assertIn(type(deserialized), fields.DatetimeField.TYPE) self.assertEqual(fields.DatetimeField.serialize(None), '') self.assertIs(type(fields.DatetimeField.serialize(None)), types.UnicodeType) value = datetime.datetime(2015, 5, 27, 1, 2, 3) self.assertEqual(fields.DatetimeField.deserialize(serialized), value) self.assertEqual(fields.DatetimeField.deserialize(deserialized), deserialized) self.assertEqual(fields.DatetimeField.deserialize(None), None) self.assertEqual(fields.DatetimeField.serialize(value), serialized) self.assertIs(type(fields.DatetimeField.serialize(value)), types.UnicodeType) with self.assertRaises(ValueError): fields.DatetimeField.deserialize(42) with self.assertRaises(ValueError): fields.DatetimeField.deserialize('2015-01-01') with self.assertRaises(ValueError): fields.DatetimeField.deserialize('Álvaro') def test_EmailtimeField(self): # TODO: accept spaces also serialized = b'test@domain.com' self.assertEqual(fields.EmailField.TYPE, (types.UnicodeType, )) deserialized = fields.EmailField.deserialize(serialized) self.assertIn(type(deserialized), fields.EmailField.TYPE) self.assertEqual(fields.EmailField.serialize(None), '') self.assertIs(type(fields.EmailField.serialize(None)), types.UnicodeType) value = u'test@domain.com' self.assertEqual(fields.EmailField.deserialize(serialized), value) self.assertEqual(fields.EmailField.deserialize(deserialized), deserialized) self.assertEqual(fields.EmailField.deserialize(None), None) self.assertEqual(fields.EmailField.deserialize(''), None) self.assertEqual(fields.EmailField.serialize(value), serialized) self.assertIs(type(fields.EmailField.serialize(value)), types.UnicodeType) with self.assertRaises(ValueError): fields.EmailField.deserialize(42) with self.assertRaises(ValueError): fields.EmailField.deserialize('2015-01-01') with self.assertRaises(ValueError): fields.EmailField.deserialize('Álvaro') def test_TextField(self): self.assertEqual(fields.TextField.TYPE, (unicode, )) self.assertEqual(fields.TextField.serialize(None), '') self.assertIs(type(fields.TextField.serialize(None)), types.UnicodeType) self.assertIn(type(fields.TextField.deserialize('test')), fields.TextField.TYPE) self.assertEqual( fields.TextField.deserialize( 'Álvaro'.encode('utf-8'), encoding='utf-8' ), 'Álvaro' ) self.assertEqual(fields.TextField.deserialize('Álvaro'), 'Álvaro') self.assertIs(fields.TextField.deserialize(None), None) self.assertIs(fields.TextField.deserialize(''), '') self.assertEqual(fields.TextField.serialize('Álvaro'), 'Álvaro') self.assertIs(type(fields.TextField.serialize('Álvaro')), types.UnicodeType) def test_JSONField(self): self.assertEqual(fields.JSONField.TYPE, (types.ListType, types.DictType)) self.assertEqual(type(fields.JSONField.deserialize('[]')), list) self.assertEqual(type(fields.JSONField.deserialize('{}')), dict) deserialized = {'a': 123, 'b': 3.14, 'c': [42, 24], } serialized = json.dumps(deserialized) self.assertEqual(fields.JSONField.deserialize(serialized), deserialized) class FieldUtilsTestCase(unittest.TestCase): maxDiff = None def setUp(self): with open('tests/data/all-field-types.csv') as fobj: lines = fobj.read().splitlines() lines = [line.split(','.encode('utf-8')) for line in lines] self.fields = lines[0] self.data = lines[1:] self.expected = { 'bool_column': fields.BoolField, 'integer_column': fields.IntegerField, 'float_column': fields.FloatField, 'decimal_column': fields.FloatField, 'percent_column': fields.PercentField, 'date_column': fields.DateField, 'datetime_column': fields.DatetimeField, 'unicode_column': fields.TextField, } def test_detect_types_utf8(self): result = fields.detect_types( self.fields, self.data, encoding='utf-8' ) self.assertEqual(type(result), collections.OrderedDict) self.assertEqual(result.keys(), self.fields) self.assertDictEqual(dict(result), self.expected) def test_detect_types_unicode(self): data = [[field.decode('utf-8') for field in row] for row in self.data] result = fields.detect_types(self.fields, data) self.assertDictEqual(dict(result), self.expected) def test_detect_types_no_sample(self): expected = {key: fields.BinaryField for key in self.expected.keys()} result = fields.detect_types(self.fields, []) self.assertDictEqual(dict(result), expected) class FieldsFunctionsTestCase(unittest.TestCase): def test_is_null(self): self.assertEqual(fields.is_null(None), True) self.assertEqual(fields.is_null(''), True) self.assertEqual(fields.is_null(' \t '), True) self.assertEqual(fields.is_null('null'), True) self.assertEqual(fields.is_null('nil'), True) self.assertEqual(fields.is_null('none'), True) self.assertEqual(fields.is_null('-'), True) self.assertEqual(fields.is_null('Álvaro'), False) self.assertEqual(fields.is_null('Álvaro'.encode('utf-8')), False) def test_as_string(self): self.assertEqual(fields.as_string(None), 'None') self.assertEqual(fields.as_string(42), '42') self.assertEqual(fields.as_string(3.141592), '3.141592') self.assertEqual(fields.as_string('Álvaro'), 'Álvaro') self.assertEqual(fields.as_string('Álvaro'.encode('utf-8')), 'Álvaro'.encode('utf-8')) rows-0.2.1/tests/tests_localization.py000066400000000000000000000027411275267602200201470ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import unittest import platform import rows import rows.fields from rows.localization import locale_context class LocalizationTestCase(unittest.TestCase): def test_locale_context_present_in_main_namespace(self): self.assertIn('locale_context', dir(rows)) self.assertIs(locale_context, rows.locale_context) def test_locale_context(self): self.assertTrue(rows.fields.SHOULD_NOT_USE_LOCALE) if platform.system() == 'Windows': name = str('ptb_bra') else: name = 'pt_BR.UTF-8' with locale_context(name): self.assertFalse(rows.fields.SHOULD_NOT_USE_LOCALE) self.assertTrue(rows.fields.SHOULD_NOT_USE_LOCALE) rows-0.2.1/tests/tests_operations.py000066400000000000000000000101521275267602200176350ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import datetime import unittest from collections import OrderedDict import rows import rows.operations import utils class OperationsTestCase(utils.RowsTestMixIn, unittest.TestCase): def test_join_imports(self): self.assertIs(rows.join, rows.operations.join) def test_join_feature(self): tables = [rows.import_from_csv('tests/data/to-merge-1.csv'), rows.import_from_csv('tests/data/to-merge-2.csv'), rows.import_from_csv('tests/data/to-merge-3.csv'),] merged = rows.join(keys=('id', 'username'), tables=tables) expected = rows.import_from_csv('tests/data/merged.csv') self.assert_table_equal(merged, expected) def test_transform_imports(self): self.assertIs(rows.transform, rows.operations.transform) def test_transform_feature(self): def transformation_function(row, table): if row.percent_column < 0.1269: return None # discard this row new = row._asdict() new['meta'] = ', '.join(['{} => {}'.format(key, value) for key, value in table._meta.items()]) return new fields = utils.table.fields.copy() fields.update({'meta': rows.fields.TextField, }) tables = [utils.table] * 3 result = rows.transform(fields, transformation_function, *tables) self.assertEqual(result.fields, fields) not_discarded = [transformation_function(row, utils.table) for row in utils.table] * 3 not_discarded = [row for row in not_discarded if row is not None] self.assertEqual(len(result), len(not_discarded)) for expected_row, row in zip(not_discarded, result): self.assertEqual(expected_row, dict(row._asdict())) def test_transpose_imports(self): self.assertIs(rows.transpose, rows.operations.transpose) def test_transpose_feature(self): new_fields = OrderedDict([('key', rows.fields.TextField), ('value_1', rows.fields.TextField), ('value_2', rows.fields.TextField)]) table = rows.Table(fields=new_fields) table.append({'key': 'first_key', 'value_1': 'first_value_1', 'value_2': 'first_value_2', }) table.append({'key': 'second_key', 'value_1': 1, 'value_2': 2, }) table.append({'key': 'third_key', 'value_1': 3.14, 'value_2': 2.71, }) table.append({'key': 'fourth_key', 'value_1': '2015-09-04', 'value_2': '2015-08-29', }) new_table = rows.transpose(table, fields_column='key') self.assertEqual(len(new_table), 2) self.assertEqual(len(new_table.fields), len(table)) self.assertEqual(new_table.fields.keys(), [row.key for row in table]) self.assertEqual(new_table[0].first_key, 'first_value_1') self.assertEqual(new_table[0].second_key, 1) self.assertEqual(new_table[0].third_key, 3.14) self.assertEqual(new_table[0].fourth_key, datetime.date(2015, 9, 4)) self.assertEqual(new_table[1].first_key, 'first_value_2') self.assertEqual(new_table[1].second_key, 2) self.assertEqual(new_table[1].third_key, 2.71) self.assertEqual(new_table[1].fourth_key, datetime.date(2015, 8, 29)) rows-0.2.1/tests/tests_plugin_csv.py000066400000000000000000000223711275267602200176310ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import tempfile import textwrap import unittest from collections import OrderedDict from io import BytesIO import mock import rows import rows.plugins.csv import utils def make_csv_data(quote_char, field_delimiter, line_delimiter): data = [['field1', 'field2', 'field3'], ['value1', 'value2', 'value3']] lines = [['{}{}{}'.format(quote_char, value, quote_char) for value in line] for line in data] lines = line_delimiter.join([field_delimiter.join(line) for line in data]) return data, lines class PluginCsvTestCase(utils.RowsTestMixIn, unittest.TestCase): plugin_name = 'csv' file_extension = 'csv' filename = 'tests/data/all-field-types.csv' encoding = 'utf-8' def test_imports(self): self.assertIs(rows.import_from_csv, rows.plugins.csv.import_from_csv) self.assertIs(rows.export_to_csv, rows.plugins.csv.export_to_csv) @mock.patch('rows.plugins.csv.create_table') def test_import_from_csv_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'encoding': 'utf-8', 'some_key': 123, 'other': 456, } result = rows.import_from_csv(self.filename, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'csv', 'filename': self.filename, } self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins.csv.create_table') def test_import_from_csv_retrieve_desired_data(self, mocked_create_table): mocked_create_table.return_value = 42 # import using filename table_1 = rows.import_from_csv(self.filename) call_args = mocked_create_table.call_args_list[0] self.assert_create_table_data(call_args) # import using fobj with open(self.filename, 'rb') as fobj: table_2 = rows.import_from_csv(fobj) call_args = mocked_create_table.call_args_list[1] self.assert_create_table_data(call_args) @mock.patch('rows.plugins.csv.create_table') def test_import_from_csv_discover_dialect(self, mocked_create_table): data, lines = make_csv_data(quote_char="'", field_delimiter=";", line_delimiter="\r\n") fobj = BytesIO() fobj.write(lines.encode('utf-8')) fobj.seek(0) rows.import_from_csv(fobj) call_args = mocked_create_table.call_args_list[0] self.assertEqual(data, list(call_args[0][0])) @mock.patch('rows.plugins.csv.create_table') def test_import_from_csv_force_dialect(self, mocked_create_table): data, lines = make_csv_data(quote_char="'", field_delimiter="\t", line_delimiter="\r\n") fobj = BytesIO() fobj.write(lines.encode('utf-8')) fobj.seek(0) rows.import_from_csv(fobj, dialect='excel-tab') call_args = mocked_create_table.call_args_list[0] self.assertEqual(data, list(call_args[0][0])) def test_detect_dialect_more_data(self): temp = tempfile.NamedTemporaryFile(delete=False) filename = '{}.{}'.format(temp.name, self.file_extension) self.files_to_delete.append(filename) # If the sniffer reads only the first line, it will think the delimiter # is ',' instead of ';' data = textwrap.dedent(''' field1,samefield;field2,other row1value1;row1value2 row2value1;row2value2 ''').strip() with open(filename, 'w') as fobj: fobj.write(data.encode('utf-8')) table = rows.import_from_csv(filename, encoding='utf-8') self.assertEqual(table.field_names, ['field1samefield', 'field2other']) self.assertEqual(table[0].field1samefield, 'row1value1') self.assertEqual(table[0].field2other, 'row1value2') self.assertEqual(table[1].field1samefield, 'row2value1') self.assertEqual(table[1].field2other, 'row2value2') def test_detect_dialect_using_json(self): temp = tempfile.NamedTemporaryFile(delete=False) filename = '{}.{}'.format(temp.name, self.file_extension) encoding = 'utf-8' self.files_to_delete.append(filename) # Using JSON will force the sniffer to do not include ':', '}' in the # possible delimiters table = rows.Table(fields=OrderedDict([ ('jsoncolumn1', rows.fields.JSONField), ('jsoncolumn2', rows.fields.JSONField), ])) table.append({ 'jsoncolumn1': '{"a": 42}', 'jsoncolumn2': '{"b": 43}', }) table.append({ 'jsoncolumn1': '{"c": 44}', 'jsoncolumn2': '{"d": 45}', }) rows.export_to_csv(table, filename, encoding=encoding) table = rows.import_from_csv(filename, encoding=encoding) self.assertEqual(table.field_names, ['jsoncolumn1', 'jsoncolumn2']) self.assertDictEqual(table[0].jsoncolumn1, {'a': 42}) self.assertDictEqual(table[0].jsoncolumn2, {'b': 43}) self.assertDictEqual(table[1].jsoncolumn1, {'c': 44}) self.assertDictEqual(table[1].jsoncolumn2, {'d': 45}) @mock.patch('rows.plugins.csv.serialize') def test_export_to_csv_uses_serialize(self, mocked_serialize): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) kwargs = {'test': 123, 'parameter': 3.14, 'encoding': 'utf-8', } mocked_serialize.return_value = iter([utils.table.fields.keys()]) rows.export_to_csv(utils.table, temp.name, **kwargs) self.assertTrue(mocked_serialize.called) self.assertEqual(mocked_serialize.call_count, 1) call = mocked_serialize.call_args self.assertEqual(call[0], (utils.table, )) self.assertEqual(call[1], kwargs) def test_export_to_csv_filename(self): # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_csv(utils.table, temp.name) table = rows.import_from_csv(temp.name) self.assert_table_equal(table, utils.table) temp.file.seek(0) result = temp.file.read() export_in_memory = rows.export_to_csv(utils.table, None) self.assertEqual(result, export_in_memory) def test_export_to_csv_fobj(self): # TODO: may test with codecs.open passing an encoding # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_csv(utils.table, temp.file) table = rows.import_from_csv(temp.name) self.assert_table_equal(table, utils.table) def test_issue_168(self): temp = tempfile.NamedTemporaryFile(delete=False) filename = '{}.{}'.format(temp.name, self.file_extension) self.files_to_delete.append(filename) table = rows.Table(fields=OrderedDict([ ('jsoncolumn', rows.fields.JSONField), ])) table.append({'jsoncolumn': '{"python": 42}'}) rows.export_to_csv(table, filename) table2 = rows.import_from_csv(filename) self.assert_table_equal(table, table2) def test_quotes(self): temp = tempfile.NamedTemporaryFile(delete=False) filename = '{}.{}'.format(temp.name, self.file_extension) self.files_to_delete.append(filename) table = rows.Table(fields=OrderedDict([ ('field_1', rows.fields.TextField), ('field_2', rows.fields.TextField), ('field_3', rows.fields.TextField), ('field_4', rows.fields.TextField), ])) table.append({ 'field_1': '"quotes"', 'field_2': 'test "quotes"', 'field_3': '"quotes" test', 'field_4': 'test "quotes" test', }) # we need this line row since `"quotes"` on `field_1` could be # `JSONField` or `TextField` table.append({ 'field_1': 'noquotes', 'field_2': 'test "quotes"', 'field_3': '"quotes" test', 'field_4': 'test "quotes" test', }) rows.export_to_csv(table, filename) table2 = rows.import_from_csv(filename) self.assert_table_equal(table, table2) rows-0.2.1/tests/tests_plugin_dicts.py000066400000000000000000000075021275267602200201430ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2016 Álvaro Justen # # 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 . from __future__ import unicode_literals import tempfile import unittest from io import BytesIO import mock import rows import rows.plugins.dicts import utils class PluginDictTestCase(utils.RowsTestMixIn, unittest.TestCase): plugin_name = 'dicts' data = [{'name': 'Álvaro', 'ids': 123, 'number': 3, }, {'name': 'Test', 'ids': '456', }, # missing 'number', 'ids' as str {'name': 'Python', 'ids': '123, 456', 'other': 3.14, },] def test_imports(self): self.assertIs(rows.import_from_dicts, rows.plugins.dicts.import_from_dicts) self.assertIs(rows.export_to_dicts, rows.plugins.dicts.export_to_dicts) @mock.patch('rows.plugins.dicts.create_table') def test_import_from_dicts_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'some_key': 123, 'other': 456, } result = rows.import_from_dicts(self.data, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'dicts', } self.assertEqual(call[1], kwargs) def test_import_from_dicts_return_desired_data(self): table = rows.import_from_dicts(self.data) self.assertEqual(len(table), 3) self.assertEqual(len(table.fields), 4) self.assertEqual(set(table.field_names), set(['ids', 'name', 'number', 'other'])) self.assertEqual(table.fields['name'], rows.fields.TextField) self.assertEqual(table.fields['ids'], rows.fields.TextField) self.assertEqual(table.fields['number'], rows.fields.IntegerField) self.assertEqual(table.fields['other'], rows.fields.FloatField) self.assertEqual(table[0].name, 'Álvaro') self.assertEqual(table[0].ids, '123') self.assertEqual(table[0].number, 3) self.assertEqual(table[0].other, None) self.assertEqual(table[1].name, 'Test') self.assertEqual(table[1].ids, '456') self.assertEqual(table[1].number, None) self.assertEqual(table[1].other, None) self.assertEqual(table[2].name, 'Python') self.assertEqual(table[2].ids, '123, 456') self.assertEqual(table[2].number, None) self.assertEqual(table[2].other, 3.14) def test_export_to_dicts(self): table = rows.import_from_dicts(self.data) result = rows.export_to_dicts(table) full_data = [ {'name': 'Álvaro', 'ids': '123', 'number': 3, 'other': None, }, {'name': 'Test', 'ids': '456', 'number': None, 'other': None, }, {'name': 'Python', 'ids': '123, 456', 'number': None, 'other': 3.14, },] self.assertEqual(len(result), len(table)) for expected, actual in zip(full_data, result): self.assertDictEqual(expected, actual) rows-0.2.1/tests/tests_plugin_html.py000066400000000000000000000412731275267602200200040ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import tempfile import unittest from collections import OrderedDict import mock import rows import rows.plugins.html import utils # TODO: test unescape # TODO: test colspan # TODO: test rowspan # TODO: test more nested tables # URL = 'https://finance.yahoo.com/q;_ylt=At7WXTIEGzyrIHemoSMI7I.iuYdG;_ylu=X3oDMTBxdGVyNzJxBHNlYwNVSCAzIERlc2t0b3AgU2VhcmNoIDEx;_ylg=X3oDMTByaDM4cG9kBGxhbmcDZW4tVVMEcHQDMgR0ZXN0AzUxMjAxMw--;_ylv=3?s=GOOG&uhb=uhb2&type=2button&fr=uh3_finance_web_gs' # URL_2 = 'http://www.rio.rj.gov.br/dlstatic/10112/2147539/DLFE-237833.htm/paginanova2.0.0.0._B.htm' def cleanup_lines(lines): return [line.strip() for line in lines.strip().split('\n') if line.strip()] class PluginHtmlTestCase(utils.RowsTestMixIn, unittest.TestCase): plugin_name = 'html' file_extension = 'html' filename = 'tests/data/all-field-types.html' encoding = 'utf-8' def test_imports(self): self.assertIs(rows.import_from_html, rows.plugins.html.import_from_html) self.assertIs(rows.export_to_html, rows.plugins.html.export_to_html) def test_import_from_html_filename(self): table = rows.import_from_html(self.filename, encoding=self.encoding) self.assert_table_equal(table, utils.table) expected_meta = {'imported_from': 'html', 'filename': self.filename,} self.assertEqual(table.meta, expected_meta) def test_import_from_html_fobj(self): # TODO: may test with codecs.open passing an encoding with open(self.filename) as fobj: table = rows.import_from_html(fobj, encoding=self.encoding) self.assert_table_equal(table, utils.table) expected_meta = {'imported_from': 'html', 'filename': self.filename,} self.assertEqual(table.meta, expected_meta) @mock.patch('rows.plugins.html.create_table') def test_import_from_html_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'encoding': 'iso-8859-15', 'some_key': 123, 'other': 456, } result = rows.import_from_html(self.filename, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'html', 'filename': self.filename, } self.assertEqual(call[1], kwargs) def test_export_to_html_filename(self): # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_html(utils.table, temp.name) table = rows.import_from_html(temp.name) self.assert_table_equal(table, utils.table) def test_export_to_html_fobj(self): # TODO: may test with codecs.open passing an encoding # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_html(utils.table, temp.file) table = rows.import_from_html(temp.name) self.assert_table_equal(table, utils.table) @mock.patch('rows.plugins.html.serialize') def test_export_to_html_uses_serialize(self, mocked_serialize): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) kwargs = {'test': 123, 'parameter': 3.14, 'encoding': 'utf-8', } mocked_serialize.return_value = iter([utils.table.fields.keys()]) rows.export_to_html(utils.table, temp.name, **kwargs) self.assertTrue(mocked_serialize.called) self.assertEqual(mocked_serialize.call_count, 1) call = mocked_serialize.call_args self.assertEqual(call[0], (utils.table, )) self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins.html.export_data') def test_export_to_html_uses_export_data(self, mocked_export_data): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) kwargs = {'test': 123, 'parameter': 3.14, 'encoding': 'utf-8', } mocked_export_data.return_value = 42 result = rows.export_to_html(utils.table, temp.name, **kwargs) self.assertTrue(mocked_export_data.called) self.assertEqual(mocked_export_data.call_count, 1) self.assertEqual(result, 42) call = mocked_export_data.call_args self.assertEqual(call[0][0], temp.name) self.assertEqual(call[1], {}) def test_export_to_html_none(self): # TODO: may test with codecs.open passing an encoding # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) result = rows.export_to_html(utils.table) rows.export_to_html(utils.table, temp.file) temp.file.seek(0) self.assertEqual(temp.file.read(), result) def test_table_index(self): filename = 'tests/data/simple-table.html' fobj = open(filename) table_1 = rows.import_from_html(fobj) self.assertEqual(set(table_1.fields.keys()), set(['t0r0c0', 't0r0c1'])) self.assertEqual(len(table_1), 1) self.assertEqual(table_1[0].t0r0c0, 't0r1c0') self.assertEqual(table_1[0].t0r0c1, 't0r1c1') fobj.seek(0) table_2 = rows.import_from_html(fobj, index=1) self.assertEqual(set(table_2.fields.keys()), set(['t1r0c0', 't1r0c1'])) self.assertEqual(len(table_2), 2) self.assertEqual(table_2[0].t1r0c0, 't1r1c0') self.assertEqual(table_2[0].t1r0c1, 't1r1c1') self.assertEqual(table_2[1].t1r0c0, 't1r2c0') self.assertEqual(table_2[1].t1r0c1, 't1r2c1') def test_table_thead_tbody(self): filename = 'tests/data/table-thead-tbody.html' fobj = open(filename) table = rows.import_from_html(fobj) self.assertEqual(set(table.fields.keys()), set(['t1', 't2'])) self.assertEqual(len(table), 2) self.assertEqual(table[0].t1, '456') self.assertEqual(table[0].t2, '123') self.assertEqual(table[1].t1, 'qqq') self.assertEqual(table[1].t2, 'aaa') def test_nested_tables_outer(self): filename = 'tests/data/nested-table.html' fobj = open(filename) table = rows.import_from_html(fobj) self.assertEqual(set(table.fields.keys()), set(['t00r0c0', 't00r0c1', 't00r0c2'])) self.assertEqual(len(table), 3) self.assertEqual(table[0].t00r0c0, 't0,0r1c0') self.assertEqual(table[0].t00r0c1, 't0,0r1c1') self.assertEqual(table[0].t00r0c2, 't0,0r1c2') # if there are nested tables, the inner ones will be represented as # strings (each ... element will return only one string, even # if there is a inside it) inner_table = ('t0,1r0c0 t0,1r0c1 t0,1r1c0 t0,1r1c1 t0,1r2c0 ' 't0,1r2c1 t0,2r0c0 t0,2r0c1 t0,2r1c0 t0,2r1c1 ' 't0,1r3c1 t0,1r4c0 t0,1r4c1 t0,1r5c0 t0,1r5c1') self.assertEqual(table[1].t00r0c0, 't0,0r2c0') self.assertEqual(table[1].t00r0c1, inner_table) self.assertEqual(table[1].t00r0c2, 't0,0r2c2') self.assertEqual(table[2].t00r0c0, 't0,0r3c0') self.assertEqual(table[2].t00r0c1, 't0,0r3c1') self.assertEqual(table[2].t00r0c2, 't0,0r3c2') def test_nested_tables_first_inner(self): filename = 'tests/data/nested-table.html' fobj = open(filename) table = rows.import_from_html(fobj, index=1) self.assertEqual(set(table.fields.keys()), set(['t01r0c0', 't01r0c1'])) self.assertEqual(len(table), 5) self.assertEqual(table[0].t01r0c0, 't0,1r1c0') self.assertEqual(table[0].t01r0c1, 't0,1r1c1') self.assertEqual(table[1].t01r0c0, 't0,1r2c0') self.assertEqual(table[1].t01r0c1, 't0,1r2c1') inner_table = 't0,2r0c0 t0,2r0c1 t0,2r1c0 t0,2r1c1' self.assertEqual(table[2].t01r0c0, inner_table) self.assertEqual(table[2].t01r0c1, 't0,1r3c1') self.assertEqual(table[3].t01r0c0, 't0,1r4c0') self.assertEqual(table[3].t01r0c1, 't0,1r4c1') self.assertEqual(table[4].t01r0c0, 't0,1r5c0') self.assertEqual(table[4].t01r0c1, 't0,1r5c1') def test_nested_tables_second_inner(self): filename = 'tests/data/nested-table.html' fobj = open(filename) table = rows.import_from_html(fobj, index=2) self.assertEqual(set(table.fields.keys()), set(['t02r0c0', 't02r0c1'])) self.assertEqual(len(table), 1) self.assertEqual(table[0].t02r0c0, 't0,2r1c0') self.assertEqual(table[0].t02r0c1, 't0,2r1c1') def test_preserve_html(self): filename = 'tests/data/nested-table.html' fobj = open(filename) table = rows.import_from_html(fobj, preserve_html=True) expected_data = [ '
', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '', '
t0,1r0c0 t0,1r0c1
t0,1r1c0 t0,1r1c1
t0,1r2c0 t0,1r2c1
', '', '', '', '', '', '', '', '', '', '
t0,2r0c0 t0,2r0c1
t0,2r1c0 t0,2r1c1
', '		 t0,1r3c1
t0,1r4c0 t0,1r4c1
t0,1r5c0 t0,1r5c1
'] self.assertEqual(cleanup_lines(table[1].t00r0c1), expected_data) @mock.patch('rows.plugins.html.create_table') def test_preserve_html_and_not_skip_header(self, mocked_create_table): filename = 'tests/data/table-with-sections.html' # If `import_from_html` needs to identify field names, then it # should not preserve HTML inside first row table_1 = rows.import_from_html(filename, index=1, preserve_html=True) call_args = mocked_create_table.call_args_list.pop() data = call_args[0][0] kwargs = call_args[1] self.assertEqual(kwargs.get('fields', None), None) self.assertEqual(len(data), 6) self.assertNotIn('<', data[0][1]) self.assertNotIn('>', data[0][1]) for row in data[1:]: # Second field has HTML self.assertIn('<', row[1]) self.assertIn('>', row[1]) # If we provide fields and ask to preserve HTML and to don't skip # header then it should strip HTML from every row fields = OrderedDict([('first', rows.fields.TextField), ('second', rows.fields.TextField), ('third', rows.fields.TextField), ('fourth', rows.fields.TextField)]) table_2 = rows.import_from_html(filename, index=1, fields=fields, preserve_html=True, skip_header=False) call_args = mocked_create_table.call_args_list.pop() data = call_args[0][0] kwargs = call_args[1] self.assertEqual(kwargs.get('fields', None), fields) self.assertEqual(len(data), 6) for row in data: # Second field has HTML and should not be stripped self.assertIn('<', row[1]) self.assertIn('>', row[1]) def test_ignore_colspan(self): filename = 'tests/data/colspan-table.html' fobj = open(filename) table = rows.import_from_html(fobj, ignore_colspan=True) self.assertEqual(set(table.fields.keys()), set(['field1', 'field2'])) self.assertEqual(len(table), 2) self.assertEqual(table[0].field1, 'row1field1') self.assertEqual(table[0].field2, 'row1field2') self.assertEqual(table[1].field1, 'row2field1') self.assertEqual(table[1].field2, 'row2field2') fobj = open(filename) with self.assertRaises(ValueError) as raises: table = rows.import_from_html(fobj, ignore_colspan=False) self.assertEqual(raises.exception.message, 'Number of fields differ') def test_extract_properties(self): filename = 'tests/data/properties-table.html' fobj = open(filename) table = rows.import_from_html(fobj, properties=True) self.assertEqual(table.fields.keys(), ['field1', 'field2', 'properties']) self.assertEqual(table.fields.values(), [rows.fields.TextField, rows.fields.TextField, rows.fields.JSONField]) properties_1 = {'class': 'some-class another-class', 'data-test': 'value', } properties_2 = {'class': 'css-class', 'data-test': 'value2', } self.assertEqual(len(table), 2) self.assertEqual(table[0].field1, 'row1field1') self.assertEqual(table[0].field2, 'row1field2') self.assertEqual(table[0].properties, properties_1) self.assertEqual(table[1].field1, 'row2field1') self.assertEqual(table[1].field2, 'row2field2') self.assertEqual(table[1].properties, properties_2) def test_issue_168(self): temp = tempfile.NamedTemporaryFile(delete=False) filename = '{}.{}'.format(temp.name, self.file_extension) self.files_to_delete.append(filename) table = rows.Table(fields= OrderedDict([('jsoncolumn', rows.fields.JSONField)])) table.append({'jsoncolumn': '{"python": 42}'}) rows.export_to_html(table, filename) table2 = rows.import_from_html(filename) self.assert_table_equal(table, table2) class PluginHtmlUtilsTestCase(unittest.TestCase): html = ' some text other' def test_tag_to_dict(self): result = rows.plugins.html.tag_to_dict(self.html) expected = {'text': ' some text ', 'class': 'some-class', 'href': 'some-url'} self.assertEqual(result, expected) def test_extract_node_text(self): from lxml.html import document_fromstring html = '''''' node = document_fromstring(html) desired_node = node.xpath('//a')[0] expected = 'bold link bold text' result = rows.plugins.html._extract_node_text(desired_node) self.assertEqual(result, expected) def test_extract_text_from_html(self): expected = 'some text other' result = rows.plugins.html.extract_text(self.html) self.assertEqual(result, expected) # Real HTML from # html = ''' 0 ( 0 %) ''' expected = '0 ( 0 %)' result = rows.plugins.html.extract_text(html) self.assertEqual(result, expected) # test HTML unescape html = 'Álvaro & Python' expected = 'Álvaro & Python' result = rows.plugins.html.extract_text(html) self.assertEqual(result, expected) def test_extract_links_from_html(self): # Real HTML from # html = ''' abcl [1] [2] ''' expected = ['http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=608466', 'http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=701712'] result = rows.plugins.html.extract_links(html) self.assertEqual(result, expected) rows-0.2.1/tests/tests_plugin_json.py000066400000000000000000000200251275267602200200010ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import itertools import json import tempfile import unittest from collections import Counter from collections import OrderedDict from collections import defaultdict from textwrap import dedent import mock import rows import utils class PluginJsonTestCase(utils.RowsTestMixIn, unittest.TestCase): plugin_name = 'json' file_extension = 'json' filename = 'tests/data/all-field-types.json' encoding = 'utf-8' def test_imports(self): self.assertIs(rows.import_from_json, rows.plugins._json.import_from_json) self.assertIs(rows.export_to_json, rows.plugins._json.export_to_json) @mock.patch('rows.plugins._json.create_table') def test_import_from_json_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'encoding': self.encoding, 'some_key': 123, 'other': 456, } result = rows.import_from_json(self.filename, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'json', 'filename': self.filename, } self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins._json.create_table') def test_import_from_json_retrieve_desired_data(self, mocked_create_table): mocked_create_table.return_value = 42 # import using filename table_1 = rows.import_from_json(self.filename) call_args = mocked_create_table.call_args_list[0] self.assert_create_table_data(call_args, field_ordering=False) # import using fobj with open(self.filename, 'rb') as fobj: table_2 = rows.import_from_json(fobj) call_args = mocked_create_table.call_args_list[1] self.assert_create_table_data(call_args, field_ordering=False) @mock.patch('rows.plugins._json.create_table') def test_import_from_json_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'encoding': 'iso-8859-15', 'some_key': 123, 'other': 456, } result = rows.import_from_json(self.filename, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'json', 'filename': self.filename, } self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins._json.prepare_to_export') def test_export_to_json_uses_prepare_to_export(self, mocked_prepare_to_export): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) kwargs = {'test': 123, 'parameter': 3.14, } mocked_prepare_to_export.return_value = \ iter([utils.table.fields.keys()]) rows.export_to_json(utils.table, temp.name, **kwargs) self.assertTrue(mocked_prepare_to_export.called) self.assertEqual(mocked_prepare_to_export.call_count, 1) call = mocked_prepare_to_export.call_args self.assertEqual(call[0], (utils.table, )) self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins._json.export_data') def test_export_to_json_uses_export_data(self, mocked_export_data): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) kwargs = {'test': 123, 'parameter': 3.14, } mocked_export_data.return_value = 42 result = rows.export_to_json(utils.table, temp.name, **kwargs) self.assertTrue(mocked_export_data.called) self.assertEqual(mocked_export_data.call_count, 1) self.assertEqual(result, 42) call = mocked_export_data.call_args self.assertEqual(call[0][0], temp.name) self.assertEqual(call[1], {}) def test_export_to_json_filename(self): # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_json(utils.table, temp.name) table = rows.import_from_json(temp.name) self.assert_table_equal(table, utils.table) def test_export_to_json_fobj(self): # TODO: may test with codecs.open passing an encoding # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_json(utils.table, temp.file) table = rows.import_from_json(temp.name) self.assert_table_equal(table, utils.table) def test_export_to_json_filename_save_data_in_correct_format(self): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_json(utils.table, temp.name) with open(temp.name, 'rb') as fobj: imported_json = json.load(fobj) COLUMN_TYPE = { 'float_column': float, 'decimal_column': float, 'bool_column': bool, 'integer_column': int, 'date_column': unicode, 'datetime_column': unicode, 'percent_column': unicode, 'unicode_column': unicode, } field_types = defaultdict(list) for row in imported_json: for field_name, value in row.items(): field_types[field_name].append(type(value)) # We test if the JSON was created serializing all the fields correctly # (some as native JSON values, like int and float) and others needed to # be serialized, like date, datetime etc. for field_name, value_types in field_types.items(): if field_name != 'unicode_column': self.assertEqual(Counter(value_types), Counter({type(None): 1, COLUMN_TYPE[field_name]: 6})) else: self.assertEqual(Counter(value_types), Counter({COLUMN_TYPE[field_name]: 7})) def test_export_to_json_indent(self): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) table = rows.Table(fields=utils.table.fields) table.append(utils.table[0]._asdict()) rows.export_to_json(table, temp.name, indent=2) temp.file.seek(0) result = temp.file.read().strip().replace('\r\n', '\n').splitlines() self.assertEqual(result[0], '[') self.assertEqual(result[1], ' {') for line in result[2:-2]: self.assertTrue(line.startswith(' ')) self.assertEqual(result[-2], ' }') self.assertEqual(result[-1], ']') def test_issue_168(self): temp = tempfile.NamedTemporaryFile(delete=False) filename = '{}.{}'.format(temp.name, self.file_extension) self.files_to_delete.append(filename) table = rows.Table(fields= OrderedDict([('jsoncolumn', rows.fields.JSONField)])) table.append({'jsoncolumn': '{"python": 42}'}) rows.export_to_json(table, filename) table2 = rows.import_from_json(filename) self.assert_table_equal(table, table2) rows-0.2.1/tests/tests_plugin_ods.py000066400000000000000000000045171275267602200176250ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import unittest import mock import rows import rows.fields as fields import rows.plugins.ods import utils class PluginOdsTestCase(utils.RowsTestMixIn, unittest.TestCase): plugin_name = 'ods' filename = 'tests/data/all-field-types.ods' def test_imports(self): self.assertIs(rows.import_from_ods, rows.plugins.ods.import_from_ods) @mock.patch('rows.plugins.ods.create_table') def test_import_from_ods_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'encoding': 'test', 'some_key': 123, 'other': 456, } result = rows.import_from_ods(self.filename, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'ods', 'filename': self.filename, } self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins.ods.create_table') def test_import_from_ods_retrieve_desired_data(self, mocked_create_table): mocked_create_table.return_value = 42 # import using filename table_1 = rows.import_from_ods(self.filename) call_args = mocked_create_table.call_args_list[0] self.assert_create_table_data(call_args) # import using fobj with open(self.filename, 'rb') as fobj: table_2 = rows.import_from_ods(fobj) call_args = mocked_create_table.call_args_list[1] self.assert_create_table_data(call_args) rows-0.2.1/tests/tests_plugin_parquet.py000066400000000000000000000114511275267602200205140ustar00rootroot00000000000000# coding: utf-8 # Copyright 2016 Álvaro Justen # # 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 . from __future__ import unicode_literals import unittest import mock import rows import rows.plugins._parquet DATA = [['nation_key', 'name', 'region_key', 'comment_col'], [0, 'ALGERIA', 0, ' haggle. carefully final deposits detect slyly agai'], [1, 'ARGENTINA', 1, 'al foxes promise slyly according to the regular accounts. bold requests alon'], [2, 'BRAZIL', 1, 'y alongside of the pending deposits. carefully special packages are about the ironic forges. slyly special '], [3, 'CANADA', 1, 'eas hang ironic, silent packages. slyly regular packages are furiously over the tithes. fluffily bold'], [4, 'EGYPT', 4, 'y above the carefully unusual theodolites. final dugouts are quickly across the furiously regular d'], [5, 'ETHIOPIA', 0, 'ven packages wake quickly. regu'], [6, 'FRANCE', 3, 'refully final requests. regular, ironi'], [7, 'GERMANY', 3, 'l platelets. regular accounts x-ray: unusual, regular acco'], [8, 'INDIA', 2, 'ss excuses cajole slyly across the packages. deposits print aroun'], [9, 'INDONESIA', 2, ' slyly express asymptotes. regular deposits haggle slyly. carefully ironic hockey players sleep blithely. carefull'], [10, 'IRAN', 4, 'efully alongside of the slyly final dependencies. '], [11, 'IRAQ', 4, 'nic deposits boost atop the quickly final requests? quickly regula'], [12, 'JAPAN', 2, 'ously. final, express gifts cajole a'], [13, 'JORDAN', 4, 'ic deposits are blithely about the carefully regular pa'], [14, 'KENYA', 0, ' pending excuses haggle furiously deposits. pending, express pinto beans wake fluffily past t'], [15, 'MOROCCO', 0, 'rns. blithely bold courts among the closely regular packages use furiously bold platelets?'], [16, 'MOZAMBIQUE', 0, 's. ironic, unusual asymptotes wake blithely r'], [17, 'PERU', 1, 'platelets. blithely pending dependencies use fluffily across the even pinto beans. carefully silent accoun'], [18, 'CHINA', 2, 'c dependencies. furiously express notornis sleep slyly regular accounts. ideas sleep. depos'], [19, 'ROMANIA', 3, 'ular asymptotes are about the furious multipliers. express dependencies nag above the ironically ironic account'], [20, 'SAUDI ARABIA', 4, 'ts. silent requests haggle. closely express packages sleep across the blithely'], [21, 'VIETNAM', 2, 'hely enticingly express accounts. even, final '], [22, 'RUSSIA', 3, ' requests against the platelets use never according to the quickly regular pint'], [23, 'UNITED KINGDOM', 3, 'eans boost carefully special requests. accounts are. carefull'], [24, 'UNITED STATES', 1, 'y final packages. slow foxes cajole quickly. quickly silent platelets breach ironic accounts. unusual pinto be']] class PluginParquetTestCase(unittest.TestCase): plugin_name = 'parquet' filename = 'tests/data/nation.dict.parquet' def test_imports(self): self.assertIs(rows.import_from_parquet, rows.plugins._parquet.import_from_parquet) @mock.patch('rows.plugins._parquet.create_table') def test_import_from_parquet_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'some_key': 123, 'other': 456, } result = rows.import_from_parquet(self.filename, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'parquet', 'filename': self.filename, } self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins._parquet.create_table') def test_import_from_parquet_retrieve_desired_data(self, mocked_create_table): mocked_create_table.return_value = 42 # import using filename table = rows.import_from_parquet(self.filename) args = mocked_create_table.call_args[0][0] self.assertEqual(args, DATA) rows-0.2.1/tests/tests_plugin_sqlite.py000066400000000000000000000167621275267602200203460ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2016 Álvaro Justen # # 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 . from __future__ import unicode_literals import sqlite3 import tempfile import unittest from collections import OrderedDict import mock import rows import rows.plugins.sqlite import rows.plugins.utils import utils from rows import fields class PluginSqliteTestCase(utils.RowsTestMixIn, unittest.TestCase): plugin_name = 'sqlite' file_extension = 'sqlite' filename = 'tests/data/all-field-types.sqlite' override_fields = {'percent_column': fields.FloatField, 'bool_column': fields.IntegerField, } # SQLite does not support "Decimal" type, so `PercentField` will be # identified as a float and also does not support "boolean" type, so it's # saved as integer internally def test_imports(self): self.assertIs(rows.import_from_sqlite, rows.plugins.sqlite.import_from_sqlite) self.assertIs(rows.export_to_sqlite, rows.plugins.sqlite.export_to_sqlite) @mock.patch('rows.plugins.sqlite.create_table') def test_import_from_sqlite_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'encoding': 'test', 'some_key': 123, 'other': 456, } result = rows.import_from_sqlite(self.filename, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'sqlite', 'filename': self.filename, } self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins.sqlite.create_table') def test_import_from_sqlite_retrieve_desired_data(self, mocked_create_table): mocked_create_table.return_value = 42 # import using filename table_1 = rows.import_from_sqlite(self.filename) call_args = mocked_create_table.call_args_list[0] self.assert_create_table_data(call_args) # import using connection connection = sqlite3.connect(self.filename) table_2 = rows.import_from_sqlite(connection) call_args = mocked_create_table.call_args_list[1] self.assert_create_table_data(call_args, filename=connection) connection.close() def test_sqlite_injection(self): connection = rows.export_to_sqlite(utils.table, ':memory:') with self.assertRaises(ValueError): rows.import_from_sqlite(connection, table_name='table1", "sqlite_master') with self.assertRaises(ValueError): rows.export_to_sqlite(utils.table, ':memory:', table_name='table1", "sqlite_master') def test_export_to_sqlite_filename(self): # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_sqlite(utils.table, temp.name) table = rows.import_from_sqlite(temp.name) self.assert_table_equal(table, utils.table) def test_export_to_sqlite_connection(self): # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False, mode='wb') self.files_to_delete.append(temp.name) connection = sqlite3.connect(temp.name) rows.export_to_sqlite(utils.table, connection) connection.close() table = rows.import_from_sqlite(temp.name) self.assert_table_equal(table, utils.table) def test_export_to_sqlite_create_unique_table_name(self): # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) first_table = utils.table second_table = utils.table + utils.table rows.export_to_sqlite(first_table, temp.name) # table1 rows.export_to_sqlite(second_table, temp.name) # table2 result_first_table = rows.import_from_sqlite(temp.name, table_name='table1') result_second_table = rows.import_from_sqlite(temp.name, table_name='table2') self.assert_table_equal(result_first_table, first_table) self.assert_table_equal(result_second_table, second_table) def test_export_to_sqlite_forcing_table_name_appends_rows(self): # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_sqlite(utils.table, temp.name, table_name='rows') rows.export_to_sqlite(utils.table, temp.name, table_name='rows') result_table = rows.import_from_sqlite(temp.name, table_name='rows') self.assertEqual(len(result_table), 2 * len(utils.table)) self.assert_table_equal(result_table, utils.table + utils.table) @mock.patch('rows.plugins.sqlite.prepare_to_export') def test_export_to_sqlite_uses_prepare_to_export(self, mocked_prepare_to_export): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) encoding = 'iso-8859-15' kwargs = {'test': 123, 'parameter': 3.14, } mocked_prepare_to_export.return_value = \ iter(rows.plugins.utils.prepare_to_export(utils.table)) rows.export_to_sqlite(utils.table, temp.name, encoding=encoding, **kwargs) self.assertTrue(mocked_prepare_to_export.called) self.assertEqual(mocked_prepare_to_export.call_count, 1) call = mocked_prepare_to_export.call_args self.assertEqual(call[0], (utils.table, )) kwargs['encoding'] = encoding self.assertEqual(call[1], kwargs) def test_issue_170(self): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) table = rows.Table(fields= OrderedDict([('intvalue', rows.fields.IntegerField), ('floatvalue', rows.fields.FloatField)])) table.append({'intvalue': 42, 'floatvalue': 3.14}) table.append({'intvalue': None, 'floatvalue': None}) # should not raise an exception rows.export_to_sqlite(table, temp.name) def test_issue_168(self): temp = tempfile.NamedTemporaryFile(delete=False) filename = '{}.{}'.format(temp.name, self.file_extension) self.files_to_delete.append(filename) table = rows.Table(fields= OrderedDict([('jsoncolumn', rows.fields.JSONField)])) table.append({'jsoncolumn': '{"python": 42}'}) rows.export_to_sqlite(table, filename) table2 = rows.import_from_sqlite(filename) self.assert_table_equal(table, table2) rows-0.2.1/tests/tests_plugin_txt.py000066400000000000000000000122201275267602200176450ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import tempfile import unittest from collections import OrderedDict import mock import rows import rows.plugins.txt import utils class PluginTxtTestCase(utils.RowsTestMixIn, unittest.TestCase): plugin_name = 'txt' file_extension = 'txt' filename = 'tests/data/all-field-types.txt' encoding = 'utf-8' def test_imports(self): self.assertIs(rows.import_from_txt, rows.plugins.txt.import_from_txt) self.assertIs(rows.export_to_txt, rows.plugins.txt.export_to_txt) @mock.patch('rows.plugins.txt.create_table') def test_import_from_txt_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'encoding': self.encoding, 'some_key': 123, 'other': 456, } result = rows.import_from_txt(self.filename, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'txt', 'filename': self.filename, } self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins.txt.create_table') def test_import_from_txt_retrieve_desired_data(self, mocked_create_table): mocked_create_table.return_value = 42 # import using filename table_1 = rows.import_from_txt(self.filename) call_args = mocked_create_table.call_args_list[0] self.assert_create_table_data(call_args) # import using fobj with open(self.filename, 'rb') as fobj: table_2 = rows.import_from_txt(fobj) call_args = mocked_create_table.call_args_list[1] self.assert_create_table_data(call_args) @mock.patch('rows.plugins.txt.serialize') def test_export_to_txt_uses_serialize(self, mocked_serialize): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) kwargs = {'encoding': 'utf-8', 'test': 123, 'parameter': 3.14, } mocked_serialize.return_value = iter([utils.table.fields.keys()]) rows.export_to_txt(utils.table, temp.name, **kwargs) self.assertTrue(mocked_serialize.called) self.assertEqual(mocked_serialize.call_count, 1) call = mocked_serialize.call_args self.assertEqual(call[0], (utils.table, )) self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins.txt.export_data') def test_export_to_txt_uses_export_data(self, mocked_export_data): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) kwargs = {'encoding': 'utf-8', 'test': 123, 'parameter': 3.14, } mocked_export_data.return_value = 42 result = rows.export_to_txt(utils.table, temp.name, **kwargs) self.assertTrue(mocked_export_data.called) self.assertEqual(mocked_export_data.call_count, 1) self.assertEqual(result, 42) call = mocked_export_data.call_args self.assertEqual(call[0][0], temp.name) self.assertEqual(call[1], {}) def test_export_to_txt_filename(self): # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_txt(utils.table, temp.name) table = rows.import_from_txt(temp.name) self.assert_table_equal(table, utils.table) with open(temp.name) as fobj: content = fobj.read() self.assertEqual(content[-10:].count('\n'), 1) def test_export_to_txt_fobj(self): # TODO: may test with codecs.open passing an encoding # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_txt(utils.table, temp.file) table = rows.import_from_txt(temp.name) self.assert_table_equal(table, utils.table) def test_issue_168(self): temp = tempfile.NamedTemporaryFile(delete=False) filename = '{}.{}'.format(temp.name, self.file_extension) self.files_to_delete.append(filename) table = rows.Table(fields= OrderedDict([('jsoncolumn', rows.fields.JSONField)])) table.append({'jsoncolumn': '{"python": 42}'}) rows.export_to_txt(table, filename) table2 = rows.import_from_txt(filename) self.assert_table_equal(table, table2) rows-0.2.1/tests/tests_plugin_utils.py000066400000000000000000000345571275267602200202070ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import itertools import random import tempfile import types import unittest from collections import OrderedDict import mock import rows import rows.plugins.utils as plugins_utils from rows import fields import utils class GenericUtilsTestCase(unittest.TestCase): def test_slug(self): self.assertEqual(plugins_utils.slug('Álvaro Justen'), 'alvaro_justen') self.assertEqual(plugins_utils.slug("Moe's Bar"), 'moes_bar') self.assertEqual(plugins_utils.slug("-----te-----st------"), 'te_st') # As in self.assertEqual( plugins_utils.slug('Query Occurrence"( % ),"First Seen'), 'query_occurrence_first_seen') self.assertEqual(plugins_utils.slug(' ÁLVARO justen% '), 'alvaro_justen') def test_ipartition(self): iterable = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10] result = plugins_utils.ipartition(iterable, 3) self.assertEqual(type(result), types.GeneratorType) self.assertEqual(list(result), [[1, 2, 3], [4, 5, 6], [7, 8, 9], [10]]) result = plugins_utils.ipartition(iterable, 2) self.assertEqual(type(result), types.GeneratorType) self.assertEqual(list(result), [[1, 2], [3, 4], [5, 6], [7, 8], [9, 10]]) def possible_field_names_errors(error_fields): error_fields = ['"{}"'.format(field_name) for field_name in error_fields] fields_permutations = itertools.permutations(error_fields, len(error_fields)) fields_permutations_str = [', '.join(field_names) for field_names in fields_permutations] return ['Invalid field names: {}'.format(field_names) for field_names in fields_permutations_str] class PluginUtilsTestCase(utils.RowsTestMixIn, unittest.TestCase): def test_create_table_skip_header(self): field_types = OrderedDict([('integer', fields.IntegerField), ('string', fields.TextField),]) data = [['1', 'Álvaro'], ['2', 'turicas'], ['3', 'Justen']] table_1 = plugins_utils.create_table(data, fields=field_types, skip_header=True) table_2 = plugins_utils.create_table(data, fields=field_types, skip_header=False) self.assertEqual(field_types, table_1.fields) self.assertEqual(table_1.fields, table_2.fields) self.assertEqual(len(table_1), 2) self.assertEqual(len(table_2), 3) first_row = {'integer': 1, 'string': 'Álvaro'} second_row = {'integer': 2, 'string': 'turicas'} third_row = {'integer': 3, 'string': 'Justen'} self.assertEqual(dict(table_1[0]._asdict()), second_row) self.assertEqual(dict(table_2[0]._asdict()), first_row) self.assertEqual(dict(table_1[1]._asdict()), third_row) self.assertEqual(dict(table_2[1]._asdict()), second_row) self.assertEqual(dict(table_2[2]._asdict()), third_row) def test_create_table_import_fields(self): header = ['field1', 'field2', 'field3'] table_rows = [['1', 3.14, 'Álvaro'], ['2', 2.71, 'turicas'], ['3', 1.23, 'Justen']] table = plugins_utils.create_table([header] + table_rows, import_fields=None) self.assertEqual(table.fields.keys(), header) self.assertEqual(table[0].field1, 1) self.assertEqual(table[0].field2, 3.14) self.assertEqual(table[0].field3, 'Álvaro') import_fields = ['field3', 'field2'] table = plugins_utils.create_table([header] + table_rows, import_fields=import_fields) self.assertEqual(table.fields.keys(), import_fields) self.assertEqual(table[0]._asdict(), OrderedDict([('field3', 'Álvaro'), ('field2', 3.14)])) def test_create_table_import_fields_dont_exist(self): header = ['field1', 'field2', 'field3'] table_rows = [['1', 3.14, 'Álvaro'], ['2', 2.71, 'turicas'], ['3', 1.23, 'Justen']] error_fields = ['doesnt_exist', 'ruby'] import_fields = list(header)[:-1] + error_fields with self.assertRaises(ValueError) as exception_context: plugins_utils.create_table([header] + table_rows, import_fields=import_fields) self.assertIn(exception_context.exception.message, possible_field_names_errors(error_fields)) def test_create_table_repeated_field_names(self): header = ['first', 'first', 'first'] table_rows = [['1', 3.14, 'Álvaro'], ['2', 2.71, 'turicas'], ['3', 1.23, 'Justen']] table = plugins_utils.create_table([header] + table_rows) self.assertEqual(table.fields.keys(), ['first', 'first_2', 'first_3']) self.assertEqual(table[0].first, 1) self.assertEqual(table[0].first_2, 3.14) self.assertEqual(table[0].first_3, 'Álvaro') header = ['field', '', 'field'] table_rows = [['1', 3.14, 'Álvaro'], ['2', 2.71, 'turicas'], ['3', 1.23, 'Justen']] table = plugins_utils.create_table([header] + table_rows) self.assertEqual(table.fields.keys(), ['field', 'field_1', 'field_2']) self.assertEqual(table[0].field, 1) self.assertEqual(table[0].field_1, 3.14) self.assertEqual(table[0].field_2, 'Álvaro') def test_create_table_empty_data(self): header = ['first', 'first', 'first'] table_rows = [] table = plugins_utils.create_table([header] + table_rows) self.assertEqual(table.fields.keys(), ['first', 'first_2', 'first_3']) self.assertEqual(len(table), 0) def test_create_table_force_types(self): header = ['field1', 'field2', 'field3'] table_rows = [['1', '3.14', 'Álvaro'], ['2', '2.71', 'turicas'], ['3', '1.23', 'Justen']] force_types = {'field2': rows.fields.DecimalField} table = plugins_utils.create_table([header] + table_rows, force_types=force_types) for field_name, field_type in force_types.items(): self.assertEqual(table.fields[field_name], field_type) def test_prepare_to_export_all_fields(self): result = plugins_utils.prepare_to_export(utils.table, export_fields=None) self.assertEqual(utils.table.fields.keys(), result.next()) for row in utils.table._rows: self.assertEqual(row, result.next()) with self.assertRaises(StopIteration): result.next() def test_prepare_to_export_some_fields(self): field_names = utils.table.fields.keys() number_of_fields = random.randint(2, len(field_names) - 1) some_fields = [field_names[index] for index in range(number_of_fields)] random.shuffle(some_fields) result = plugins_utils.prepare_to_export(utils.table, export_fields=some_fields) self.assertEqual(some_fields, result.next()) for row in utils.table: expected_row = [getattr(row, field_name) for field_name in some_fields] self.assertEqual(expected_row, result.next()) with self.assertRaises(StopIteration): result.next() def test_prepare_to_export_some_fields_dont_exist(self): field_names = utils.table.fields.keys() error_fields = ['does_not_exist', 'java'] export_fields = field_names + error_fields result = plugins_utils.prepare_to_export(utils.table, export_fields=export_fields) with self.assertRaises(ValueError) as exception_context: result.next() self.assertIn(exception_context.exception.message, possible_field_names_errors(error_fields)) def test_prepare_to_export_with_FlexibleTable(self): flexible = rows.FlexibleTable() for row in utils.table: flexible.append(row._asdict()) field_names = flexible.fields.keys() field_types = flexible.fields.values() prepared = plugins_utils.prepare_to_export(flexible) self.assertEqual(prepared.next(), field_names) for row, expected_row in zip(prepared, flexible._rows): values = [expected_row[field_name] for field_name in field_names] self.assertEqual(values, row) def test_prepare_to_export_with_FlexibleTable_and_export_fields(self): flexible = rows.FlexibleTable() for row in utils.table: flexible.append(row._asdict()) field_names = flexible.fields.keys() field_types = flexible.fields.values() export_fields = field_names[:len(field_names) // 2] prepared = plugins_utils.prepare_to_export(flexible, export_fields=export_fields) self.assertEqual(prepared.next(), export_fields) for row, expected_row in zip(prepared, flexible._rows): values = [expected_row[field_name] for field_name in export_fields] self.assertEqual(values, row) def test_prepare_to_export_wrong_obj_type(self): '''`prepare_to_export` raises exception if obj isn't `*Table`''' expected_message = 'Table type not recognized' with self.assertRaises(ValueError) as exception_context: plugins_utils.prepare_to_export(1).next() self.assertEqual(exception_context.exception.message, expected_message) with self.assertRaises(ValueError) as exception_context: plugins_utils.prepare_to_export(42.0).next() self.assertEqual(exception_context.exception.message, expected_message) with self.assertRaises(ValueError) as exception_context: plugins_utils.prepare_to_export([list('abc'), [1, 2, 3]]).next() self.assertEqual(exception_context.exception.message, expected_message) @mock.patch('rows.plugins.utils.prepare_to_export') def test_serialize_should_call_prepare_to_export(self, mocked_prepare_to_export): table = utils.table kwargs = {'export_fields': 123, 'other_parameter': 3.14, } result = plugins_utils.serialize(table, **kwargs) self.assertFalse(mocked_prepare_to_export.called) field_names = result.next() table_rows = list(result) self.assertTrue(mocked_prepare_to_export.called) self.assertEqual(mocked_prepare_to_export.call_count, 1) self.assertEqual(mock.call(table, **kwargs), mocked_prepare_to_export.call_args) def test_serialize(self): result = plugins_utils.serialize(utils.table) field_types = utils.table.fields.values() self.assertEqual(result.next(), utils.table.fields.keys()) for row, expected_row in zip(result, utils.table._rows): values = [field_type.serialize(value) for field_type, value in zip(field_types, expected_row)] self.assertEqual(values, row) def test_make_header_should_add_underscore_if_starts_with_number(self): result = plugins_utils.make_header(['123', '456', '123']) expected_result = ['field_123', 'field_456', 'field_123_2'] self.assertEqual(result, expected_result) def test_make_header_should_not_ignore_permit_not(self): result = plugins_utils.make_header(['abc', '^qwe', 'rty'], permit_not=True) expected_result = ['abc', '^qwe', 'rty'] self.assertEqual(result, expected_result) def test_make_unique_name(self): name = 'test' existing_names = [] name_format = '{index}_{name}' result = plugins_utils.make_unique_name(name, existing_names, name_format) self.assertEqual(result, name) existing_names = ['test'] result = plugins_utils.make_unique_name(name, existing_names, name_format) self.assertEqual(result, '2_test') existing_names = ['test', '2_test', '3_test', '5_test'] result = plugins_utils.make_unique_name(name, existing_names, name_format) self.assertEqual(result, '4_test') existing_names = ['test', '2_test', '3_test', '5_test'] result = plugins_utils.make_unique_name(name, existing_names, name_format, start=1) self.assertEqual(result, '1_test') def test_export_data(self): data = 'python rules'.encode('utf-8') temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) filename_or_fobj = temp.file result = plugins_utils.export_data(filename_or_fobj, data) temp.file.seek(0) output = temp.file.read() self.assertIs(result, temp.file) self.assertEqual(output, data) filename_or_fobj = None result = plugins_utils.export_data(filename_or_fobj, data) self.assertIs(result, data) # TODO: test make_header # TODO: test all features of create_table # TODO: test if error is raised if len(row) != len(fields) # TODO: test get_fobj_and_filename (BytesIO should return filename = None) rows-0.2.1/tests/tests_plugin_xls.py000066400000000000000000000116231275267602200176420ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import datetime import tempfile import time import unittest from collections import OrderedDict import mock import rows import rows.fields as fields import rows.plugins.xls import utils def date_to_datetime(value): return datetime.datetime.fromtimestamp(time.mktime(value.timetuple())) class PluginXlsTestCase(utils.RowsTestMixIn, unittest.TestCase): plugin_name = 'xls' file_extension = 'xls' filename = 'tests/data/all-field-types.xls' def test_imports(self): self.assertIs(rows.import_from_xls, rows.plugins.xls.import_from_xls) self.assertIs(rows.export_to_xls, rows.plugins.xls.export_to_xls) @mock.patch('rows.plugins.xls.create_table') def test_import_from_xls_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'encoding': 'test', 'some_key': 123, 'other': 456, } result = rows.import_from_xls(self.filename, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'xls', 'filename': self.filename, } self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins.xls.create_table') def test_import_from_xls_retrieve_desired_data(self, mocked_create_table): mocked_create_table.return_value = 42 # import using filename table_1 = rows.import_from_xls(self.filename) call_args = mocked_create_table.call_args_list[0] self.assert_create_table_data(call_args) # import using fobj with open(self.filename, 'rb') as fobj: table_2 = rows.import_from_xls(fobj) call_args = mocked_create_table.call_args_list[1] self.assert_create_table_data(call_args) def test_export_to_xls_filename(self): # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) rows.export_to_xls(utils.table, temp.name) table = rows.import_from_xls(temp.name) self.assert_table_equal(table, utils.table) temp.file.seek(0) result = temp.file.read() export_in_memory = rows.export_to_xls(utils.table, None) self.assertEqual(result, export_in_memory) def test_export_to_xls_fobj(self): # TODO: may test with codecs.open passing an encoding # TODO: may test file contents temp = tempfile.NamedTemporaryFile(delete=False, mode='wb') self.files_to_delete.append(temp.name) rows.export_to_xls(utils.table, temp.file) temp.file.close() table = rows.import_from_xls(temp.name) self.assert_table_equal(table, utils.table) @mock.patch('rows.plugins.xls.prepare_to_export') def test_export_to_xls_uses_prepare_to_export(self, mocked_prepare_to_export): temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) encoding = 'iso-8859-15' kwargs = {'test': 123, 'parameter': 3.14, } mocked_prepare_to_export.return_value = \ iter([utils.table.fields.keys()]) rows.export_to_xls(utils.table, temp.name, encoding=encoding, **kwargs) self.assertTrue(mocked_prepare_to_export.called) self.assertEqual(mocked_prepare_to_export.call_count, 1) call = mocked_prepare_to_export.call_args self.assertEqual(call[0], (utils.table, )) kwargs['encoding'] = encoding self.assertEqual(call[1], kwargs) def test_issue_168(self): temp = tempfile.NamedTemporaryFile(delete=False) filename = '{}.{}'.format(temp.name, self.file_extension) self.files_to_delete.append(filename) table = rows.Table(fields= OrderedDict([('jsoncolumn', rows.fields.JSONField)])) table.append({'jsoncolumn': '{"python": 42}'}) rows.export_to_xls(table, filename) table2 = rows.import_from_xls(filename) self.assert_table_equal(table, table2) rows-0.2.1/tests/tests_plugin_xlsx.py000066400000000000000000000116031275267602200200300ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import tempfile import unittest from collections import OrderedDict from io import BytesIO import mock import rows import rows.plugins.xlsx import utils class PluginXlsxTestCase(utils.RowsTestMixIn, unittest.TestCase): plugin_name = 'xlsx' file_extension = 'xlsx' filename = 'tests/data/all-field-types.xlsx' def test_imports(self): self.assertIs(rows.import_from_xlsx, rows.plugins.xlsx.import_from_xlsx) self.assertIs(rows.export_to_xlsx, rows.plugins.xlsx.export_to_xlsx) @mock.patch('rows.plugins.xlsx.create_table') def test_import_from_xlsx_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'encoding': 'iso-8859-15', 'some_key': 123, 'other': 456, } result = rows.import_from_xlsx(self.filename, **kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'xlsx', 'filename': self.filename, } self.assertEqual(call[1], kwargs) @mock.patch('rows.plugins.xlsx.create_table') def test_import_from_xlsx_retrieve_desired_data(self, mocked_create_table): mocked_create_table.return_value = 42 # import using filename table_1 = rows.import_from_xlsx(self.filename) call_args = mocked_create_table.call_args_list[0] self.assert_create_table_data(call_args) # import using fobj with open(self.filename, 'rb') as fobj: table_2 = rows.import_from_xlsx(fobj) call_args = mocked_create_table.call_args_list[1] self.assert_create_table_data(call_args) def test_export_to_xlsx_filename(self): temp = tempfile.NamedTemporaryFile() filename = temp.name + '.xlsx' temp.close() self.files_to_delete.append(filename) rows.export_to_xlsx(utils.table, filename) table = rows.import_from_xlsx(filename) self.assert_table_equal(table, utils.table) export_in_memory = rows.export_to_xlsx(utils.table, None) result_fobj = BytesIO() result_fobj.write(export_in_memory) result_fobj.seek(0) result_table = rows.import_from_xlsx(result_fobj) self.assert_table_equal(result_table, utils.table) def test_export_to_xlsx_fobj(self): temp = tempfile.NamedTemporaryFile() filename = temp.name + '.xlsx' temp.close() fobj = open(filename, 'wb') self.files_to_delete.append(filename) rows.export_to_xlsx(utils.table, fobj) fobj.close() table = rows.import_from_xlsx(filename) self.assert_table_equal(table, utils.table) @mock.patch('rows.plugins.xlsx.prepare_to_export') def test_export_to_xlsx_uses_prepare_to_export(self, mocked_prepare_to_export): temp = tempfile.NamedTemporaryFile() filename = temp.name + '.xlsx' temp.file.close() fobj = open(filename, 'wb') self.files_to_delete.append(filename) kwargs = {'test': 123, 'parameter': 3.14, } mocked_prepare_to_export.return_value = \ iter([utils.table.fields.keys()]) rows.export_to_xlsx(utils.table, temp.name, **kwargs) self.assertTrue(mocked_prepare_to_export.called) self.assertEqual(mocked_prepare_to_export.call_count, 1) call = mocked_prepare_to_export.call_args self.assertEqual(call[0], (utils.table, )) self.assertEqual(call[1], kwargs) def test_issue_168(self): temp = tempfile.NamedTemporaryFile(delete=False) filename = '{}.{}'.format(temp.name, self.file_extension) self.files_to_delete.append(filename) table = rows.Table(fields= OrderedDict([('jsoncolumn', rows.fields.JSONField)])) table.append({'jsoncolumn': '{"python": 42}'}) rows.export_to_xlsx(table, filename) table2 = rows.import_from_xlsx(filename) self.assert_table_equal(table, table2) rows-0.2.1/tests/tests_plugin_xpath.py000066400000000000000000000116171275267602200201630ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2016 Álvaro Justen # # 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 . from __future__ import unicode_literals import tempfile import unittest from collections import OrderedDict from io import BytesIO import mock import rows import rows.plugins.xpath import utils class PluginXPathTestCase(utils.RowsTestMixIn, unittest.TestCase): filename = 'tests/data/ecuador-medios-radiodifusoras.html' encoding = 'utf-8' expected_data = 'tests/data/ecuador-medios-radiodifusoras.csv' def setUp(self): rows_xpath = '//*[@class="entry-container"]/*[@class="row-fluid"]/*[@class="span6"]' fields_xpath = OrderedDict([ ('url', '//h2/a/@href'), ('name', '//h2/a/text()'), ('address', '//div[@class="spField field_direccion"]/text()'), ('phone', '//div[@class="spField field_telefono"]/text()'), ('website', '//div[@class="spField field_sitio_web"]/text()'), ('email', '//div[@class="spField field_email"]/text()'), ]) self.kwargs = {'rows_xpath': rows_xpath, 'fields_xpath': fields_xpath, } self.expected_table = rows.import_from_csv(self.expected_data) self.files_to_delete = [] def test_imports(self): self.assertIs(rows.import_from_xpath, rows.plugins.xpath.import_from_xpath) def test_import_from_xpath_filename(self): table = rows.import_from_xpath(self.filename, encoding=self.encoding, **self.kwargs) expected_meta = {'imported_from': 'xpath', 'filename': self.filename,} self.assertEqual(table.meta, expected_meta) temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) fobj = temp.file rows.export_to_csv(table, fobj) fobj.seek(0) table = rows.import_from_csv(fobj) self.assert_table_equal(table, self.expected_table) def test_import_from_xpath_fobj(self): # TODO: may test with codecs.open passing an encoding with open(self.filename) as fobj: table = rows.import_from_xpath(fobj, encoding=self.encoding, **self.kwargs) expected_meta = {'imported_from': 'xpath', 'filename': self.filename,} self.assertEqual(table.meta, expected_meta) temp = tempfile.NamedTemporaryFile(delete=False) self.files_to_delete.append(temp.name) fobj = temp.file rows.export_to_csv(table, fobj) fobj.seek(0) table = rows.import_from_csv(fobj) self.assert_table_equal(table, self.expected_table) def test_import_from_xpath_unescape_and_extract_text(self): html = ''' '''.encode('utf-8') rows_xpath = '//ul/li' fields_xpath = OrderedDict([('name', './/text()'), ('link', './/a/@href')]) table = rows.import_from_xpath(BytesIO(html), rows_xpath=rows_xpath, fields_xpath=fields_xpath, encoding='utf-8') self.assertEqual(table[0].name, 'Abadia de Goiás (GO)') self.assertEqual(table[1].name, 'Abadiânia (GO)') @mock.patch('rows.plugins.xpath.create_table') def test_import_from_xpath_uses_create_table(self, mocked_create_table): mocked_create_table.return_value = 42 kwargs = {'encoding': 'iso-8859-15', 'some_key': 123, 'other': 456, } self.kwargs.update(kwargs) result = rows.import_from_xpath(self.filename, **self.kwargs) self.assertTrue(mocked_create_table.called) self.assertEqual(mocked_create_table.call_count, 1) self.assertEqual(result, 42) call = mocked_create_table.call_args kwargs['meta'] = {'imported_from': 'xpath', 'filename': self.filename,} self.assertEqual(call[1], kwargs) rows-0.2.1/tests/tests_table.py000066400000000000000000000341601275267602200165460ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import datetime import unittest from collections import OrderedDict import rows import rows.fields as fields from rows.table import FlexibleTable, Table class TableTestCase(unittest.TestCase): def setUp(self): self.table = Table(fields={'name': rows.fields.TextField, 'birthdate': rows.fields.DateField, }) self.first_row = {'name': u'Álvaro Justen', 'birthdate': datetime.date(1987, 4, 29)} self.table.append(self.first_row) self.table.append({'name': u'Somebody', 'birthdate': datetime.date(1990, 2, 1)}) self.table.append({'name': u'Douglas Adams', 'birthdate': '1952-03-11'}) def test_Table_is_present_on_main_namespace(self): self.assertIn('Table', dir(rows)) self.assertIs(Table, rows.Table) def test_table_iteration(self): # TODO: may test with all field types (using tests.utils.table) table_rows = [row for row in self.table] self.assertEqual(len(table_rows), 3) self.assertEqual(table_rows[0].name, u'Álvaro Justen') self.assertEqual(table_rows[0].birthdate, datetime.date(1987, 4, 29)) self.assertEqual(table_rows[1].name, u'Somebody') self.assertEqual(table_rows[1].birthdate, datetime.date(1990, 2, 1)) self.assertEqual(table_rows[2].name, u'Douglas Adams') self.assertEqual(table_rows[2].birthdate, datetime.date(1952, 3, 11)) def test_table_slicing(self): self.assertEqual(len(self.table[::2]), 2) self.assertEqual(self.table[::2][0].name, u'Álvaro Justen') def test_table_slicing_error(self): with self.assertRaises(ValueError) as context_manager: self.table[[1]] self.assertEqual(type(context_manager.exception), ValueError) def test_table_insert_row(self): self.table.insert(1, {'name': u'Grace Hopper', 'birthdate': datetime.date(1909, 12, 9)}) self.assertEqual(self.table[1].name, u'Grace Hopper') def test_table_append_error(self): # TODO: may mock these validations and test only on *Field tests with self.assertRaises(ValueError) as context_manager: self.table.append({'name': 'Álvaro Justen'.encode('utf-8'), 'birthdate': '1987-04-29'}) self.assertEqual(type(context_manager.exception), UnicodeDecodeError) with self.assertRaises(ValueError) as context_manager: self.table.append({'name': u'Álvaro Justen', 'birthdate': 'WRONG'}) self.assertEqual(type(context_manager.exception), ValueError) self.assertIn('does not match format', context_manager.exception.message) def test_table_getitem_invalid_type(self): with self.assertRaises(ValueError) as exception_context: self.table[3.14] self.assertEqual(exception_context.exception.message, 'Unsupported key type: float') with self.assertRaises(ValueError) as exception_context: self.table[b'name'] self.assertEqual(exception_context.exception.message, 'Unsupported key type: str') # TODO: should change to 'bytes' on Python3 def test_table_getitem_column_doesnt_exist(self): with self.assertRaises(KeyError) as exception_context: self.table['doesnt-exist'] self.assertEqual(exception_context.exception.message, 'doesnt-exist') def test_table_getitem_column_happy_path(self): expected_values = ['Álvaro Justen', 'Somebody', 'Douglas Adams'] self.assertEqual(self.table['name'], expected_values) expected_values = [ datetime.date(1987, 4, 29), datetime.date(1990, 2, 1), datetime.date(1952, 3, 11)] self.assertEqual(self.table['birthdate'], expected_values) def test_table_setitem_row(self): self.first_row['name'] = 'turicas' self.first_row['birthdate'] = datetime.date(2000, 1, 1) self.table[0] = self.first_row self.assertEqual(self.table[0].name, 'turicas') self.assertEqual(self.table[0].birthdate, datetime.date(2000, 1, 1)) def test_field_names_and_types(self): self.assertEqual(self.table.field_names, self.table.fields.keys()) self.assertEqual(self.table.field_types, self.table.fields.values()) def test_table_setitem_column_happy_path_new_column(self): number_of_fields = len(self.table.fields) self.assertEqual(len(self.table), 3) self.table['user_id'] = [4, 5, 6] self.assertEqual(len(self.table), 3) self.assertEqual(len(self.table.fields), number_of_fields + 1) self.assertIn('user_id', self.table.fields) self.assertIs(self.table.fields['user_id'], rows.fields.IntegerField) self.assertEqual(self.table[0].user_id, 4) self.assertEqual(self.table[1].user_id, 5) self.assertEqual(self.table[2].user_id, 6) def test_table_setitem_column_happy_path_replace_column(self): number_of_fields = len(self.table.fields) self.assertEqual(len(self.table), 3) self.table['name'] = [4, 5, 6] # change values *and* type self.assertEqual(len(self.table), 3) self.assertEqual(len(self.table.fields), number_of_fields) self.assertIn('name', self.table.fields) self.assertIs(self.table.fields['name'], rows.fields.IntegerField) self.assertEqual(self.table[0].name, 4) self.assertEqual(self.table[1].name, 5) self.assertEqual(self.table[2].name, 6) def test_table_setitem_column_slug_field_name(self): self.assertNotIn('user_id', self.table.fields) self.table['User ID'] = [4, 5, 6] self.assertIn('user_id', self.table.fields) def test_table_setitem_column_invalid_length(self): number_of_fields = len(self.table.fields) self.assertEqual(len(self.table), 3) with self.assertRaises(ValueError) as exception_context: self.table['user_id'] = [4, 5] # list len should be 3 self.assertEqual(len(self.table), 3) self.assertEqual(len(self.table.fields), number_of_fields) self.assertEqual(exception_context.exception.message, 'Values length (2) should be the same as Table ' 'length (3)') def test_table_setitem_invalid_type(self): fields = self.table.fields.copy() self.assertEqual(len(self.table), 3) with self.assertRaises(ValueError) as exception_context: self.table[3.14] = [] self.assertEqual(len(self.table), 3) # should not add any row self.assertDictEqual(fields, self.table.fields) # should not add field self.assertEqual(exception_context.exception.message, 'Unsupported key type: float') with self.assertRaises(ValueError) as exception_context: self.table[b'some_value'] = [] self.assertEqual(len(self.table), 3) # should not add any row self.assertDictEqual(fields, self.table.fields) # should not add field self.assertEqual(exception_context.exception.message, 'Unsupported key type: str') # TODO: should change to 'bytes' on Python3 def test_table_delitem_row(self): table_rows = [row for row in self.table] before = len(self.table) del self.table[0] after = len(self.table) self.assertEqual(after, before - 1) for row, expected_row in zip(self.table, table_rows[1:]): self.assertEqual(row, expected_row) def test_table_delitem_column_doesnt_exist(self): with self.assertRaises(KeyError) as exception_context: del self.table['doesnt-exist'] self.assertEqual(exception_context.exception.message, 'doesnt-exist') def test_table_delitem_column_happy_path(self): fields = self.table.fields.copy() self.assertEqual(len(self.table), 3) del self.table['name'] self.assertEqual(len(self.table), 3) # should not del any row self.assertEqual(len(self.table.fields), len(fields) - 1) self.assertDictEqual(dict(self.table[0]._asdict()), {'birthdate': datetime.date(1987, 4, 29)}) self.assertDictEqual(dict(self.table[1]._asdict()), {'birthdate': datetime.date(1990, 2, 1)}) self.assertDictEqual(dict(self.table[2]._asdict()), {'birthdate': datetime.date(1952, 3, 11)}) def test_table_delitem_column_invalid_type(self): fields = self.table.fields.copy() self.assertEqual(len(self.table), 3) with self.assertRaises(ValueError) as exception_context: del self.table[3.14] self.assertEqual(len(self.table), 3) # should not del any row self.assertDictEqual(fields, self.table.fields) # should not del field self.assertEqual(exception_context.exception.message, 'Unsupported key type: float') with self.assertRaises(ValueError) as exception_context: self.table[b'name'] = [] # u'name' actually exists self.assertEqual(len(self.table), 3) # should not del any row self.assertDictEqual(fields, self.table.fields) # should not del field self.assertEqual(exception_context.exception.message, 'Unsupported key type: str') # TODO: should change to 'bytes' on Python3 def test_table_add(self): self.assertIs(self.table + 0, self.table) self.assertIs(0 + self.table, self.table) new_table = self.table + self.table self.assertEqual(new_table.fields, self.table.fields) self.assertEqual(len(new_table), 2 * len(self.table)) self.assertEqual(list(new_table), list(self.table) * 2) def test_table_add_error(self): with self.assertRaises(ValueError): self.table + 1 with self.assertRaises(ValueError): 1 + self.table def test_table_order_by(self): with self.assertRaises(ValueError): self.table.order_by('doesnt_exist') before = [row.birthdate for row in self.table] self.table.order_by('birthdate') after = [row.birthdate for row in self.table] self.assertNotEqual(before, after) self.assertEqual(sorted(before), after) self.table.order_by('-birthdate') final = [row.birthdate for row in self.table] self.assertEqual(final, list(reversed(after))) self.table.order_by('name') expected_rows = [ {'name': 'Douglas Adams', 'birthdate': datetime.date(1952, 3, 11)}, {'name': 'Somebody', 'birthdate': datetime.date(1990, 2, 1)}, {'name': 'Álvaro Justen', 'birthdate': datetime.date(1987, 4, 29)}] for expected_row, row in zip(expected_rows, self.table): self.assertEqual(expected_row, dict(row._asdict())) def test_table_repr(self): expected = '' self.assertEqual(expected, repr(self.table)) class TestFlexibleTable(unittest.TestCase): def setUp(self): self.table = FlexibleTable() def test_FlexibleTable_is_present_on_main_namespace(self): self.assertIn('FlexibleTable', dir(rows)) self.assertIs(FlexibleTable, rows.FlexibleTable) def test_inheritance(self): self.assertTrue(issubclass(FlexibleTable, Table)) def test_flexible_append_detect_field_type(self): self.assertEqual(len(self.table.fields), 0) self.table.append({'a': 123, 'b': 3.14, }) self.assertEqual(self.table[0].a, 123) self.assertEqual(self.table[0].b, 3.14) self.assertEqual(self.table.fields, OrderedDict([('a', fields.IntegerField), ('b', fields.FloatField)])) # Values are checked based on field types when appending with self.assertRaises(ValueError): self.table.append({'a': 'spam', 'b': 1.23}) # invalid value for 'a' with self.assertRaises(ValueError): self.table.append({'a': 42, 'b': 'ham'}) # invalid value or 'b' # Values are converted self.table.append({'a': '42', 'b': '2.71'}) self.assertEqual(self.table[1].a, 42) self.assertEqual(self.table[1].b, 2.71) def test_flexible_insert_row(self): self.table.append({'a': 123, 'b': 3.14, }) self.table.insert(0, {'a': 2357, 'b': 1123}) self.assertEqual(self.table[0].a, 2357) def test_flexible_update_row(self): self.table.append({'a': 123, 'b': 3.14, }) self.table[0] = {'a': 2357, 'b': 1123} self.assertEqual(self.table[0].a, 2357) def test_table_slicing(self): self.table.append({'a': 123, 'b': 3.14, }) self.table.append({'a': 2357, 'b': 1123}) self.table.append({'a': 8687, 'b': 834798}) self.assertEqual(len(self.table[::2]), 2) self.assertEqual(self.table[::2][0].a, 123) def test_table_slicing_error(self): self.table.append({'a': 123, 'b': 3.14, }) self.table.append({'a': 2357, 'b': 1123}) self.table.append({'a': 8687, 'b': 834798}) with self.assertRaises(ValueError) as context_manager: self.table[[1]] self.assertEqual(type(context_manager.exception), ValueError) rows-0.2.1/tests/tests_utils.py000066400000000000000000000022021275267602200166070ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import unittest # TODO: test detect_local_source # TODO: test detect_source # TODO: test download_file # TODO: test export_to_uri # TODO: test extension_by_plugin_name # TODO: test import_from_source # TODO: test import_from_uri # TODO: test local_file # TODO: test normalize_mime_type # TODO: test plugin_name_by_mime_type # TODO: test plugin_name_by_uri rows-0.2.1/tests/utils.py000066400000000000000000000267561275267602200154110ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014-2015 Álvaro Justen # # 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 . from __future__ import unicode_literals import copy import datetime import os from collections import OrderedDict from decimal import Decimal import rows.fields as fields from rows.table import Table NONE_VALUES = list(fields.NULL) + ['', None] FIELDS = OrderedDict([ ('bool_column', fields.BoolField), ('integer_column', fields.IntegerField), ('float_column', fields.FloatField), ('decimal_column', fields.FloatField), ('percent_column', fields.PercentField), ('date_column', fields.DateField), ('datetime_column', fields.DatetimeField), ('unicode_column', fields.TextField), ]) FIELD_NAMES = FIELDS.keys() EXPECTED_ROWS = [ { 'float_column': 3.141592, 'decimal_column': 3.141592, 'bool_column': True, 'integer_column': 1, 'date_column': datetime.date(2015, 1, 1), 'datetime_column': datetime.datetime(2015, 8, 18, 15, 10), 'percent_column': Decimal('0.01'), 'unicode_column': 'Álvaro', }, { 'float_column': 1.234, 'decimal_column': 1.234, 'bool_column': False, 'integer_column': 2, 'date_column': datetime.date(1999, 2, 3), 'datetime_column': datetime.datetime(1999, 2, 3, 0, 1, 2), 'percent_column': Decimal('0.1169'), 'unicode_column': 'àáãâä¹²³', }, { 'float_column': 4.56, 'decimal_column': 4.56, 'bool_column': True, 'integer_column': 3, 'date_column': datetime.date(2050, 1, 2), 'datetime_column': datetime.datetime(2050, 1, 2, 23, 45, 31), 'percent_column': Decimal('0.12'), 'unicode_column': 'éèẽêë', }, { 'float_column': 7.89, 'decimal_column': 7.89, 'bool_column': False, 'integer_column': 4, 'date_column': datetime.date(2015, 8, 18), 'datetime_column': datetime.datetime(2015, 8, 18, 22, 21, 33), 'percent_column': Decimal('0.1364'), 'unicode_column': '~~~~', }, { 'float_column': 9.87, 'decimal_column': 9.87, 'bool_column': True, 'integer_column': 5, 'date_column': datetime.date(2015, 3, 4), 'datetime_column': datetime.datetime(2015, 3, 4, 16, 0, 1), 'percent_column': Decimal('0.1314'), 'unicode_column': 'álvaro', }, { 'float_column': 1.2345, 'decimal_column': 1.2345, 'bool_column': False, 'integer_column': 6, 'date_column': datetime.date(2015, 5, 6), 'datetime_column': datetime.datetime(2015, 5, 6, 12, 1, 2), 'percent_column': Decimal('0.02'), 'unicode_column': 'test', }, { 'float_column': None, 'decimal_column': None, 'bool_column': None, 'integer_column': None, 'date_column': None, 'datetime_column': None, 'percent_column': None, 'unicode_column': '', } ] table = Table(fields=FIELDS) for row in EXPECTED_ROWS: table.append(row) table._meta = {'test': 123} class RowsTestMixIn(object): maxDiff = None override_fields = None def setUp(self): self.files_to_delete = [] def tearDown(self): for filename in self.files_to_delete: if os.path.exists(filename): os.unlink(filename) def assert_table_equal(self, first, second): expected_fields = dict(second.fields) if self.override_fields is None: override_fields = {} else: override_fields = self.override_fields expected_fields = copy.deepcopy(expected_fields) for key, value in override_fields.items(): if key in expected_fields: expected_fields[key] = value self.assertDictEqual(dict(first.fields), expected_fields) self.assertEqual(len(first), len(second)) for first_row, second_row in zip(first, second): first_row = dict(first_row._asdict()) second_row = dict(second_row._asdict()) for field_name, field_type in expected_fields.items(): value = first_row[field_name] expected_value = second_row[field_name] if field_name in override_fields: expected_value = override_fields[field_name]\ .deserialize(expected_value) if float not in (type(value), type(expected_value)): self.assertEqual(value, expected_value) else: self.assertAlmostEqual(value, expected_value) def assert_file_contents_equal(self, first_filename, second_filename): with open(first_filename, 'rb') as fobj: first = fobj.read() with open(second_filename, 'rb') as fobj: second = fobj.read() self.assertEqual(first, second) def assert_create_table_data(self, call_args, field_ordering=True, filename=None): if filename is None: filename = self.filename kwargs = call_args[1] expected_meta = {'imported_from': self.plugin_name, 'filename': filename, } self.assertEqual(kwargs['meta'], expected_meta) del kwargs['meta'] self.assert_table_data(call_args[0][0], args=[], kwargs=kwargs, field_ordering=field_ordering) def assert_table_data(self, data, args, kwargs, field_ordering): data = list(data) if field_ordering: self.assertEqual(data[0], FIELD_NAMES) for row_index, row in enumerate(data[1:]): for column_index, value in enumerate(row): field_name = FIELD_NAMES[column_index] expected_value = EXPECTED_ROWS[row_index][field_name] self.field_assert(field_name, expected_value, value, *args, **kwargs) else: self.assertEqual(set(data[0]), set(FIELD_NAMES)) for row_index, row in enumerate(data[1:]): for column_index, value in enumerate(row): field_name = data[0][column_index] expected_value = EXPECTED_ROWS[row_index][field_name] self.field_assert(field_name, expected_value, value, *args, **kwargs) # Fields asserts: input values we expect from plugins def field_assert(self, field_name, expected_value, value, *args, **kwargs): asserts = {'bool_column': self.assert_BoolField, 'integer_column': self.assert_IntegerField, 'float_column': self.assert_FloatField, 'decimal_column': self.assert_DecimalField, 'percent_column': self.assert_PercentField, 'date_column': self.assert_DateField, 'datetime_column': self.assert_DatetimeField, 'unicode_column': self.assert_TextField, } return asserts[field_name](expected_value, value, *args, **kwargs) def assert_BoolField(self, expected_value, value, *args, **kwargs): if expected_value is None: assert value is None or value.lower() in NONE_VALUES elif expected_value is True: assert str(value).lower() in ('true', b'true', 'yes', b'yes') elif expected_value is False: assert str(value).lower() in ('false', b'false', 'no', b'no') else: raise ValueError('expected_value is not True or False') def assert_IntegerField(self, expected_value, value, *args, **kwargs): if expected_value is None: assert value is None or value.lower() in NONE_VALUES else: self.assertIn(value, (expected_value, str(expected_value))) def assert_FloatField(self, expected_value, value, *args, **kwargs): if expected_value is None: assert value is None or value.lower() in NONE_VALUES elif type(value) != type(expected_value): self.assertEqual(value, str(expected_value)) else: self.assertAlmostEqual(expected_value, value, places=5) def assert_DecimalField(self, expected_value, value, *args, **kwargs): if expected_value is None: assert value is None or value.lower() in NONE_VALUES else: self.assert_FloatField(expected_value, value) def assert_PercentField(self, expected_value, value, *args, **kwargs): if expected_value is None: assert value is None or value.lower() in NONE_VALUES else: float_value = float(expected_value) * 100 possible_values = [str(float_value) + '%', str(float_value) + '.0%', str(float_value) + '.00%'] if int(float_value) == float_value: possible_values.append(str(int(float_value)) + '%') self.assertIn(value, possible_values) def assert_DateField(self, expected_value, value, *args, **kwargs): if expected_value is None: assert value is None or value.lower() in NONE_VALUES else: value = str(value) if value.endswith('00:00:00'): value = value[:-9] self.assertEqual(str(expected_value), value) def assert_DatetimeField(self, expected_value, value, *args, **kwargs): if expected_value is None: assert value is None or value.lower() in NONE_VALUES elif type(value) is datetime.datetime and \ type(expected_value) is datetime.datetime: # if both types are datetime, check delta # XLSX plugin has not a good precision and will change milliseconds delta_1 = expected_value - value delta_2 = value - expected_value self.assertTrue(str(delta_1).startswith('0:00:00') or str(delta_2).startswith('0:00:00')) else: # if not, convert values to string and verify if are equal value = str(value) self.assertEqual(str(expected_value).replace(' ', 'T'), value) def assert_TextField(self, expected_value, value, *args, **kwargs): if expected_value is None: assert value is None or value.lower() in NONE_VALUES elif expected_value == '': # Some plugins return `None` instead of empty strings for cells # with blank values and we don't have an way to differentiate assert value in (None, '') else: self.assertEqual(expected_value, value) rows-0.2.1/to-do/000077500000000000000000000000001275267602200135375ustar00rootroot00000000000000rows-0.2.1/to-do/plugin_mysql.py000066400000000000000000000137661275267602200166510ustar00rootroot00000000000000# coding: utf-8 # Copyright 2014 Álvaro Justen # 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 . import datetime import MySQLdb from .rows import Table from .utils import ipartition, slug __all__ = [ 'import_from_mysql', 'export_to_mysql'] # TODO: replace 'None' with '' on export_to_* # TODO: need converters in and out # TODO: lazy=True|False # TODO: datetime.time on MYSQL_TYPE # TODO: import from mysql # TODO: logging? # TODO: _mysql_exceptions.OperationalError: (2006, 'MySQL server has gone # # away') MYSQL_TYPE = {str: 'TEXT', int: 'INT', float: 'FLOAT', datetime.date: 'DATE', datetime.datetime: 'DATETIME', bool: 'BOOL'} # 'BOOL' on MySQL is a shortcut to TINYINT(1) MYSQLDB_TYPE = {getattr(MySQLdb.FIELD_TYPE, x): x \ for x in dir(MySQLdb.FIELD_TYPE) if not x.startswith('_')} MYSQLDB_TO_PYTHON = {'ENUM': str, 'STRING': str, 'VAR_STRING': str, 'BLOB': bytes, 'LONG_BLOB': bytes, 'MEDIUM_BLOB': bytes, 'TINY_BLOB': bytes, 'DECIMAL': float, 'DOUBLE': float, 'FLOAT': float, 'INT24': int, 'LONG': int, 'LONGLONG': int, 'TINY': int, 'YEAR': int, 'DATE': datetime.date, 'NEWDATE': datetime.date, 'TIME': int, 'TIMESTAMP': int, 'DATETIME': datetime.datetime} def _get_mysql_config(connection_str): colon_index = connection_str.index(':') at_index = connection_str.index('@') slash_index = connection_str.index('/') config = {} config['user'] = connection_str[:colon_index] config['passwd'] = connection_str[colon_index + 1:at_index] config['host'] = connection_str[at_index + 1:slash_index] config['port'] = 3306 if ':' in config['host']: data = config['host'].split(':') config['host'] = data[0] config['port'] = int(data[1]) if connection_str.count('/') == 1: table_name = None config['db'] = connection_str[slash_index + 1:] else: second_slash_index = connection_str.index('/', slash_index + 1) config['db'] = connection_str[slash_index + 1:second_slash_index] table_name = connection_str[second_slash_index + 1:] return config, table_name def _connect_to_mysql(config): return MySQLdb.connect(**config) def import_from_mysql(connection_string, limit=None, order_by=None, query=''): #TODO: add 'lazy' option config, table_name = _get_mysql_config(connection_string) connection = _connect_to_mysql(config) cursor = connection.cursor() if query: sql = query else: sql = 'SELECT * FROM ' + table_name if limit is not None: sql += ' LIMIT {0[0]}, {0[1]}'.format(limit) if order_by is not None: sql += ' ORDER BY ' + order_by cursor.execute(sql) column_info = [(x[0], x[1]) for x in cursor.description] table = Table(fields=[x[0] for x in cursor.description]) table.types = {name: MYSQLDB_TO_PYTHON[MYSQLDB_TYPE[type_]] \ for name, type_ in column_info} table_rows = [list(row) for row in cursor.fetchall()] encoding = connection.character_set_name() for row in table_rows: for column_index, value in enumerate(row): if type(value) is str: row[column_index] = value.decode(encoding) table._rows = table_rows cursor.close() connection.close() return table def export_to_mysql(table, connection_string, encoding=None, batch_size=1000, commit_every=10000, callback=None, callback_every=10000): config, table_name = _get_mysql_config(connection_string) connection = _connect_to_mysql(config) cursor = connection.cursor() # Create table fields, types = table.fields, table.types field_slugs = [slug(field) for field in fields] field_types = [MYSQL_TYPE[types[field]] for field in fields] columns_definition = ['{} {}'.format(field, type_) for field, type_ in zip(field_slugs, field_types)] sql = 'CREATE TABLE IF NOT EXISTS {} ({})'\ .format(table_name, ', '.join(columns_definition)) cursor.execute(sql) # Insert items columns = ', '.join(field_slugs) #placeholders = ['%s' if types[field] in (int, float, bool) else '"%s"' # for field in fields] # TODO: fix this string/formatting problem placeholders = ['%s' for field in fields] sql = 'INSERT INTO {} ({}) VALUES ({})'.format(table_name, columns, ', '.join(placeholders)) total = last_commit = last_callback = 0 for rows in ipartition(iter(table), batch_size): values = [[row[field] for field in fields] for row in rows] added = len(values) total += added last_commit += added last_callback += added cursor.executemany(sql, values) if last_commit >= commit_every: connection.commit() last_commit = 0 if callback is not None and last_callback >= callback_every: callback(total) last_callback = 0 if callback is not None and last_callback > 0: callback(total) if last_commit > 0: connection.commit() connection.close()