├── .coveragerc ├── .gitignore ├── .travis.yml ├── CHANGELOG.md ├── LICENSE ├── MANIFEST.in ├── README.rst ├── ckanext ├── __init__.py └── extractor │ ├── __init__.py │ ├── config.py │ ├── fanstatic │ └── .gitignore │ ├── i18n │ └── ckanext-extractor.pot │ ├── interfaces.py │ ├── lib.py │ ├── logic │ ├── __init__.py │ ├── action.py │ ├── auth.py │ ├── helpers.py │ └── schema.py │ ├── model.py │ ├── paster.py │ ├── plugin.py │ ├── public │ └── .gitignore │ ├── tasks.py │ ├── templates │ └── .gitignore │ └── tests │ ├── __init__.py │ ├── helpers.py │ ├── logic │ ├── __init__.py │ └── test_action.py │ ├── test.pdf │ ├── test_interfaces.py │ ├── test_lib.py │ ├── test_plugin.py │ └── test_tasks.py ├── dev-requirements.txt ├── requirements.txt ├── runtests.sh ├── setup.cfg ├── setup.py ├── test-local.ini.example ├── test.ini └── travis ├── build.bash ├── run.bash ├── solr ├── ckan-2.6 │ ├── schema.xml │ └── solrconfig.xml ├── ckan-2.7 │ ├── schema.xml │ └── solrconfig.xml ├── ckan-2.8 │ ├── schema.xml │ └── solrconfig.xml ├── ckan-master │ ├── schema.xml │ └── solrconfig.xml └── solrconfig.xml └── test-local.ini /.coveragerc: -------------------------------------------------------------------------------- 1 | [report] 2 | omit = 3 | */site-packages/* 4 | */python?.?/* 5 | ckan/* -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | /test-local.ini 2 | /README.html 3 | 4 | .ropeproject 5 | node_modules 6 | bower_components 7 | 8 | # Byte-compiled / optimized / DLL files 9 | __pycache__/ 10 | *.py[cod] 11 | 12 | # C extensions 13 | *.so 14 | 15 | # Distribution / packaging 16 | .Python 17 | env/ 18 | build/ 19 | develop-eggs/ 20 | dist/ 21 | sdist/ 22 | *.egg-info/ 23 | .installed.cfg 24 | *.egg 25 | 26 | # PyInstaller 27 | # Usually these files are written by a python script from a template 28 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 29 | *.manifest 30 | *.spec 31 | 32 | # Installer logs 33 | pip-log.txt 34 | pip-delete-this-directory.txt 35 | 36 | # Unit test / coverage reports 37 | htmlcov/ 38 | .tox/ 39 | .coverage 40 | .cache 41 | nosetests.xml 42 | coverage.xml 43 | 44 | # Sphinx documentation 45 | docs/_build/ 46 | 47 | # Vim 48 | .*.swp 49 | -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- 1 | language: python 2 | 3 | sudo: required 4 | 5 | python: 6 | - "2.7" 7 | 8 | services: 9 | - postgresql 10 | - redis-server 11 | 12 | addons: 13 | postgresql: "9.4" 14 | 15 | env: 16 | - CKANVERSION=master 17 | - CKANVERSION=2.8 18 | - CKANVERSION=2.7 19 | - CKANVERSION=2.6 20 | 21 | install: bash travis/build.bash 22 | 23 | script: bash travis/run.bash 24 | 25 | after_success: coveralls 26 | 27 | -------------------------------------------------------------------------------- /CHANGELOG.md: -------------------------------------------------------------------------------- 1 | # Change Log for ckanext-extractor 2 | 3 | The format of this file is based on [Keep a Changelog], and this 4 | project uses [Semantic Versioning]. 5 | 6 | 7 | ## [Unreleased] 8 | 9 | ### Fixed 10 | 11 | - Improved the update of the search index after extraction (reported by 12 | [@jbothma](https://github.com/stadt-karlsruhe/ckanext-extractor/issues/16)) 13 | 14 | 15 | ## [0.4.0] (2018-01-29) 16 | 17 | ### Changed 18 | 19 | - Moved from CKAN's deprecated, Celery-based background task system to the 20 | [new system](http://docs.ckan.org/en/latest/maintaining/background-tasks.html) 21 | introduced in CKAN 2.7. Users of CKAN 2.6 and older need to install 22 | [ckanext-rq](https://github.com/ckan/ckanext-rq). See the README for details 23 | ([#9](https://github.com/stadt-karlsruhe/ckanext-extractor/issues/9)) 24 | 25 | ### Fixed 26 | 27 | - Handling of multiple values for the same metadata field (reported by 28 | [@gjackson12](https://github.com/stadt-karlsruhe/ckanext-extractor/issues/11)) 29 | 30 | 31 | ## [0.3.1] (2017-11-22) 32 | 33 | ### Fixed 34 | 35 | - Don't validate package dicts when re-indexing them (reported and contributed 36 | by [@wardi](https://github.com/stadt-karlsruhe/ckanext-extractor/pull/6)) 37 | 38 | - Fixed a crash when trying to extract from a resource in a private dataset. 39 | Private datasets are now ignored. (reported by 40 | [@gjackson12](https://github.com/stadt-karlsruhe/ckanext-extractor/issues/8)) 41 | 42 | 43 | ## [0.3.0] (2017-05-10) 44 | 45 | ### Added 46 | 47 | - `IExtractorRequest` interface for adjusting the download request (contributed 48 | by [@metaodi](https://github.com/stadt-karlsruhe/ckanext-extractor/pull/5)) 49 | 50 | ### Changed 51 | 52 | - Moved change log to a separate file 53 | 54 | ### Fixed 55 | 56 | - Improved handling of errors when downloading resource data (reported by 57 | [@phisqb](https://github.com/stadt-karlsruhe/ckanext-extractor/issues/4)) 58 | 59 | 60 | ## [0.2.0] (2016-10-19) 61 | 62 | ### Added 63 | 64 | - `IExtractorPostprocessor` interface for postprocessing extraction results 65 | 66 | ### Fixed 67 | 68 | - Fixed logging problems in `paster` commands 69 | 70 | 71 | ## 0.1.0 (2016-06-14) 72 | 73 | - First release 74 | 75 | 76 | [Keep a Changelog]: http://keepachangelog.com 77 | [Semantic Versioning]: http://semver.org/ 78 | 79 | [Unreleased]: https://github.com/stadt-karlsruhe/ckanext-extractor/compare/v0.4.0...master 80 | [0.4.0]: https://github.com/stadt-karlsruhe/ckanext-extractor/compare/v0.3.1...v0.4.0 81 | [0.3.1]: https://github.com/stadt-karlsruhe/ckanext-extractor/compare/v0.3.0...v0.3.1 82 | [0.3.0]: https://github.com/stadt-karlsruhe/ckanext-extractor/compare/v0.2.0...v0.3.0 83 | [0.2.0]: https://github.com/stadt-karlsruhe/ckanext-extractor/compare/v0.1.0...v0.2.0 84 | 85 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU AFFERO GENERAL PUBLIC LICENSE 2 | Version 3, 19 November 2007 3 | 4 | Copyright (C) 2007 Free Software Foundation, Inc. 5 | Everyone is permitted to copy and distribute verbatim copies 6 | of this license document, but changing it is not allowed. 7 | 8 | Preamble 9 | 10 | The GNU Affero General Public License is a free, copyleft license for 11 | software and other kinds of works, specifically designed to ensure 12 | cooperation with the community in the case of network server software. 13 | 14 | The licenses for most software and other practical works are designed 15 | to take away your freedom to share and change the works. By contrast, 16 | our General Public Licenses are intended to guarantee your freedom to 17 | share and change all versions of a program--to make sure it remains free 18 | software for all its users. 19 | 20 | When we speak of free software, we are referring to freedom, not 21 | price. Our General Public Licenses are designed to make sure that you 22 | have the freedom to distribute copies of free software (and charge for 23 | them if you wish), that you receive source code or can get it if you 24 | want it, that you can change the software or use pieces of it in new 25 | free programs, and that you know you can do these things. 26 | 27 | Developers that use our General Public Licenses protect your rights 28 | with two steps: (1) assert copyright on the software, and (2) offer 29 | you this License which gives you legal permission to copy, distribute 30 | and/or modify the software. 31 | 32 | A secondary benefit of defending all users' freedom is that 33 | improvements made in alternate versions of the program, if they 34 | receive widespread use, become available for other developers to 35 | incorporate. Many developers of free software are heartened and 36 | encouraged by the resulting cooperation. However, in the case of 37 | software used on network servers, this result may fail to come about. 38 | The GNU General Public License permits making a modified version and 39 | letting the public access it on a server without ever releasing its 40 | source code to the public. 41 | 42 | The GNU Affero General Public License is designed specifically to 43 | ensure that, in such cases, the modified source code becomes available 44 | to the community. It requires the operator of a network server to 45 | provide the source code of the modified version running there to the 46 | users of that server. Therefore, public use of a modified version, on 47 | a publicly accessible server, gives the public access to the source 48 | code of the modified version. 49 | 50 | An older license, called the Affero General Public License and 51 | published by Affero, was designed to accomplish similar goals. This is 52 | a different license, not a version of the Affero GPL, but Affero has 53 | released a new version of the Affero GPL which permits relicensing under 54 | this license. 55 | 56 | The precise terms and conditions for copying, distribution and 57 | modification follow. 58 | 59 | TERMS AND CONDITIONS 60 | 61 | 0. Definitions. 62 | 63 | "This License" refers to version 3 of the GNU Affero General Public License. 64 | 65 | "Copyright" also means copyright-like laws that apply to other kinds of 66 | works, such as semiconductor masks. 67 | 68 | "The Program" refers to any copyrightable work licensed under this 69 | License. Each licensee is addressed as "you". "Licensees" and 70 | "recipients" may be individuals or organizations. 71 | 72 | To "modify" a work means to copy from or adapt all or part of the work 73 | in a fashion requiring copyright permission, other than the making of an 74 | exact copy. The resulting work is called a "modified version" of the 75 | earlier work or a work "based on" the earlier work. 76 | 77 | A "covered work" means either the unmodified Program or a work based 78 | on the Program. 79 | 80 | To "propagate" a work means to do anything with it that, without 81 | permission, would make you directly or secondarily liable for 82 | infringement under applicable copyright law, except executing it on a 83 | computer or modifying a private copy. Propagation includes copying, 84 | distribution (with or without modification), making available to the 85 | public, and in some countries other activities as well. 86 | 87 | To "convey" a work means any kind of propagation that enables other 88 | parties to make or receive copies. Mere interaction with a user through 89 | a computer network, with no transfer of a copy, is not conveying. 90 | 91 | An interactive user interface displays "Appropriate Legal Notices" 92 | to the extent that it includes a convenient and prominently visible 93 | feature that (1) displays an appropriate copyright notice, and (2) 94 | tells the user that there is no warranty for the work (except to the 95 | extent that warranties are provided), that licensees may convey the 96 | work under this License, and how to view a copy of this License. If 97 | the interface presents a list of user commands or options, such as a 98 | menu, a prominent item in the list meets this criterion. 99 | 100 | 1. Source Code. 101 | 102 | The "source code" for a work means the preferred form of the work 103 | for making modifications to it. "Object code" means any non-source 104 | form of a work. 105 | 106 | A "Standard Interface" means an interface that either is an official 107 | standard defined by a recognized standards body, or, in the case of 108 | interfaces specified for a particular programming language, one that 109 | is widely used among developers working in that language. 110 | 111 | The "System Libraries" of an executable work include anything, other 112 | than the work as a whole, that (a) is included in the normal form of 113 | packaging a Major Component, but which is not part of that Major 114 | Component, and (b) serves only to enable use of the work with that 115 | Major Component, or to implement a Standard Interface for which an 116 | implementation is available to the public in source code form. A 117 | "Major Component", in this context, means a major essential component 118 | (kernel, window system, and so on) of the specific operating system 119 | (if any) on which the executable work runs, or a compiler used to 120 | produce the work, or an object code interpreter used to run it. 121 | 122 | The "Corresponding Source" for a work in object code form means all 123 | the source code needed to generate, install, and (for an executable 124 | work) run the object code and to modify the work, including scripts to 125 | control those activities. However, it does not include the work's 126 | System Libraries, or general-purpose tools or generally available free 127 | programs which are used unmodified in performing those activities but 128 | which are not part of the work. For example, Corresponding Source 129 | includes interface definition files associated with source files for 130 | the work, and the source code for shared libraries and dynamically 131 | linked subprograms that the work is specifically designed to require, 132 | such as by intimate data communication or control flow between those 133 | subprograms and other parts of the work. 134 | 135 | The Corresponding Source need not include anything that users 136 | can regenerate automatically from other parts of the Corresponding 137 | Source. 138 | 139 | The Corresponding Source for a work in source code form is that 140 | same work. 141 | 142 | 2. Basic Permissions. 143 | 144 | All rights granted under this License are granted for the term of 145 | copyright on the Program, and are irrevocable provided the stated 146 | conditions are met. This License explicitly affirms your unlimited 147 | permission to run the unmodified Program. The output from running a 148 | covered work is covered by this License only if the output, given its 149 | content, constitutes a covered work. This License acknowledges your 150 | rights of fair use or other equivalent, as provided by copyright law. 151 | 152 | You may make, run and propagate covered works that you do not 153 | convey, without conditions so long as your license otherwise remains 154 | in force. You may convey covered works to others for the sole purpose 155 | of having them make modifications exclusively for you, or provide you 156 | with facilities for running those works, provided that you comply with 157 | the terms of this License in conveying all material for which you do 158 | not control copyright. Those thus making or running the covered works 159 | for you must do so exclusively on your behalf, under your direction 160 | and control, on terms that prohibit them from making any copies of 161 | your copyrighted material outside their relationship with you. 162 | 163 | Conveying under any other circumstances is permitted solely under 164 | the conditions stated below. Sublicensing is not allowed; section 10 165 | makes it unnecessary. 166 | 167 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 168 | 169 | No covered work shall be deemed part of an effective technological 170 | measure under any applicable law fulfilling obligations under article 171 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 172 | similar laws prohibiting or restricting circumvention of such 173 | measures. 174 | 175 | When you convey a covered work, you waive any legal power to forbid 176 | circumvention of technological measures to the extent such circumvention 177 | is effected by exercising rights under this License with respect to 178 | the covered work, and you disclaim any intention to limit operation or 179 | modification of the work as a means of enforcing, against the work's 180 | users, your or third parties' legal rights to forbid circumvention of 181 | technological measures. 182 | 183 | 4. Conveying Verbatim Copies. 184 | 185 | You may convey verbatim copies of the Program's source code as you 186 | receive it, in any medium, provided that you conspicuously and 187 | appropriately publish on each copy an appropriate copyright notice; 188 | keep intact all notices stating that this License and any 189 | non-permissive terms added in accord with section 7 apply to the code; 190 | keep intact all notices of the absence of any warranty; and give all 191 | recipients a copy of this License along with the Program. 192 | 193 | You may charge any price or no price for each copy that you convey, 194 | and you may offer support or warranty protection for a fee. 195 | 196 | 5. Conveying Modified Source Versions. 197 | 198 | You may convey a work based on the Program, or the modifications to 199 | produce it from the Program, in the form of source code under the 200 | terms of section 4, provided that you also meet all of these conditions: 201 | 202 | a) The work must carry prominent notices stating that you modified 203 | it, and giving a relevant date. 204 | 205 | b) The work must carry prominent notices stating that it is 206 | released under this License and any conditions added under section 207 | 7. This requirement modifies the requirement in section 4 to 208 | "keep intact all notices". 209 | 210 | c) You must license the entire work, as a whole, under this 211 | License to anyone who comes into possession of a copy. This 212 | License will therefore apply, along with any applicable section 7 213 | additional terms, to the whole of the work, and all its parts, 214 | regardless of how they are packaged. This License gives no 215 | permission to license the work in any other way, but it does not 216 | invalidate such permission if you have separately received it. 217 | 218 | d) If the work has interactive user interfaces, each must display 219 | Appropriate Legal Notices; however, if the Program has interactive 220 | interfaces that do not display Appropriate Legal Notices, your 221 | work need not make them do so. 222 | 223 | A compilation of a covered work with other separate and independent 224 | works, which are not by their nature extensions of the covered work, 225 | and which are not combined with it such as to form a larger program, 226 | in or on a volume of a storage or distribution medium, is called an 227 | "aggregate" if the compilation and its resulting copyright are not 228 | used to limit the access or legal rights of the compilation's users 229 | beyond what the individual works permit. Inclusion of a covered work 230 | in an aggregate does not cause this License to apply to the other 231 | parts of the aggregate. 232 | 233 | 6. Conveying Non-Source Forms. 234 | 235 | You may convey a covered work in object code form under the terms 236 | of sections 4 and 5, provided that you also convey the 237 | machine-readable Corresponding Source under the terms of this License, 238 | in one of these ways: 239 | 240 | a) Convey the object code in, or embodied in, a physical product 241 | (including a physical distribution medium), accompanied by the 242 | Corresponding Source fixed on a durable physical medium 243 | customarily used for software interchange. 244 | 245 | b) Convey the object code in, or embodied in, a physical product 246 | (including a physical distribution medium), accompanied by a 247 | written offer, valid for at least three years and valid for as 248 | long as you offer spare parts or customer support for that product 249 | model, to give anyone who possesses the object code either (1) a 250 | copy of the Corresponding Source for all the software in the 251 | product that is covered by this License, on a durable physical 252 | medium customarily used for software interchange, for a price no 253 | more than your reasonable cost of physically performing this 254 | conveying of source, or (2) access to copy the 255 | Corresponding Source from a network server at no charge. 256 | 257 | c) Convey individual copies of the object code with a copy of the 258 | written offer to provide the Corresponding Source. This 259 | alternative is allowed only occasionally and noncommercially, and 260 | only if you received the object code with such an offer, in accord 261 | with subsection 6b. 262 | 263 | d) Convey the object code by offering access from a designated 264 | place (gratis or for a charge), and offer equivalent access to the 265 | Corresponding Source in the same way through the same place at no 266 | further charge. You need not require recipients to copy the 267 | Corresponding Source along with the object code. If the place to 268 | copy the object code is a network server, the Corresponding Source 269 | may be on a different server (operated by you or a third party) 270 | that supports equivalent copying facilities, provided you maintain 271 | clear directions next to the object code saying where to find the 272 | Corresponding Source. Regardless of what server hosts the 273 | Corresponding Source, you remain obligated to ensure that it is 274 | available for as long as needed to satisfy these requirements. 275 | 276 | e) Convey the object code using peer-to-peer transmission, provided 277 | you inform other peers where the object code and Corresponding 278 | Source of the work are being offered to the general public at no 279 | charge under subsection 6d. 280 | 281 | A separable portion of the object code, whose source code is excluded 282 | from the Corresponding Source as a System Library, need not be 283 | included in conveying the object code work. 284 | 285 | A "User Product" is either (1) a "consumer product", which means any 286 | tangible personal property which is normally used for personal, family, 287 | or household purposes, or (2) anything designed or sold for incorporation 288 | into a dwelling. In determining whether a product is a consumer product, 289 | doubtful cases shall be resolved in favor of coverage. For a particular 290 | product received by a particular user, "normally used" refers to a 291 | typical or common use of that class of product, regardless of the status 292 | of the particular user or of the way in which the particular user 293 | actually uses, or expects or is expected to use, the product. A product 294 | is a consumer product regardless of whether the product has substantial 295 | commercial, industrial or non-consumer uses, unless such uses represent 296 | the only significant mode of use of the product. 297 | 298 | "Installation Information" for a User Product means any methods, 299 | procedures, authorization keys, or other information required to install 300 | and execute modified versions of a covered work in that User Product from 301 | a modified version of its Corresponding Source. The information must 302 | suffice to ensure that the continued functioning of the modified object 303 | code is in no case prevented or interfered with solely because 304 | modification has been made. 305 | 306 | If you convey an object code work under this section in, or with, or 307 | specifically for use in, a User Product, and the conveying occurs as 308 | part of a transaction in which the right of possession and use of the 309 | User Product is transferred to the recipient in perpetuity or for a 310 | fixed term (regardless of how the transaction is characterized), the 311 | Corresponding Source conveyed under this section must be accompanied 312 | by the Installation Information. But this requirement does not apply 313 | if neither you nor any third party retains the ability to install 314 | modified object code on the User Product (for example, the work has 315 | been installed in ROM). 316 | 317 | The requirement to provide Installation Information does not include a 318 | requirement to continue to provide support service, warranty, or updates 319 | for a work that has been modified or installed by the recipient, or for 320 | the User Product in which it has been modified or installed. Access to a 321 | network may be denied when the modification itself materially and 322 | adversely affects the operation of the network or violates the rules and 323 | protocols for communication across the network. 324 | 325 | Corresponding Source conveyed, and Installation Information provided, 326 | in accord with this section must be in a format that is publicly 327 | documented (and with an implementation available to the public in 328 | source code form), and must require no special password or key for 329 | unpacking, reading or copying. 330 | 331 | 7. Additional Terms. 332 | 333 | "Additional permissions" are terms that supplement the terms of this 334 | License by making exceptions from one or more of its conditions. 335 | Additional permissions that are applicable to the entire Program shall 336 | be treated as though they were included in this License, to the extent 337 | that they are valid under applicable law. If additional permissions 338 | apply only to part of the Program, that part may be used separately 339 | under those permissions, but the entire Program remains governed by 340 | this License without regard to the additional permissions. 341 | 342 | When you convey a copy of a covered work, you may at your option 343 | remove any additional permissions from that copy, or from any part of 344 | it. (Additional permissions may be written to require their own 345 | removal in certain cases when you modify the work.) You may place 346 | additional permissions on material, added by you to a covered work, 347 | for which you have or can give appropriate copyright permission. 348 | 349 | Notwithstanding any other provision of this License, for material you 350 | add to a covered work, you may (if authorized by the copyright holders of 351 | that material) supplement the terms of this License with terms: 352 | 353 | a) Disclaiming warranty or limiting liability differently from the 354 | terms of sections 15 and 16 of this License; or 355 | 356 | b) Requiring preservation of specified reasonable legal notices or 357 | author attributions in that material or in the Appropriate Legal 358 | Notices displayed by works containing it; or 359 | 360 | c) Prohibiting misrepresentation of the origin of that material, or 361 | requiring that modified versions of such material be marked in 362 | reasonable ways as different from the original version; or 363 | 364 | d) Limiting the use for publicity purposes of names of licensors or 365 | authors of the material; or 366 | 367 | e) Declining to grant rights under trademark law for use of some 368 | trade names, trademarks, or service marks; or 369 | 370 | f) Requiring indemnification of licensors and authors of that 371 | material by anyone who conveys the material (or modified versions of 372 | it) with contractual assumptions of liability to the recipient, for 373 | any liability that these contractual assumptions directly impose on 374 | those licensors and authors. 375 | 376 | All other non-permissive additional terms are considered "further 377 | restrictions" within the meaning of section 10. If the Program as you 378 | received it, or any part of it, contains a notice stating that it is 379 | governed by this License along with a term that is a further 380 | restriction, you may remove that term. If a license document contains 381 | a further restriction but permits relicensing or conveying under this 382 | License, you may add to a covered work material governed by the terms 383 | of that license document, provided that the further restriction does 384 | not survive such relicensing or conveying. 385 | 386 | If you add terms to a covered work in accord with this section, you 387 | must place, in the relevant source files, a statement of the 388 | additional terms that apply to those files, or a notice indicating 389 | where to find the applicable terms. 390 | 391 | Additional terms, permissive or non-permissive, may be stated in the 392 | form of a separately written license, or stated as exceptions; 393 | the above requirements apply either way. 394 | 395 | 8. Termination. 396 | 397 | You may not propagate or modify a covered work except as expressly 398 | provided under this License. Any attempt otherwise to propagate or 399 | modify it is void, and will automatically terminate your rights under 400 | this License (including any patent licenses granted under the third 401 | paragraph of section 11). 402 | 403 | However, if you cease all violation of this License, then your 404 | license from a particular copyright holder is reinstated (a) 405 | provisionally, unless and until the copyright holder explicitly and 406 | finally terminates your license, and (b) permanently, if the copyright 407 | holder fails to notify you of the violation by some reasonable means 408 | prior to 60 days after the cessation. 409 | 410 | Moreover, your license from a particular copyright holder is 411 | reinstated permanently if the copyright holder notifies you of the 412 | violation by some reasonable means, this is the first time you have 413 | received notice of violation of this License (for any work) from that 414 | copyright holder, and you cure the violation prior to 30 days after 415 | your receipt of the notice. 416 | 417 | Termination of your rights under this section does not terminate the 418 | licenses of parties who have received copies or rights from you under 419 | this License. If your rights have been terminated and not permanently 420 | reinstated, you do not qualify to receive new licenses for the same 421 | material under section 10. 422 | 423 | 9. Acceptance Not Required for Having Copies. 424 | 425 | You are not required to accept this License in order to receive or 426 | run a copy of the Program. Ancillary propagation of a covered work 427 | occurring solely as a consequence of using peer-to-peer transmission 428 | to receive a copy likewise does not require acceptance. However, 429 | nothing other than this License grants you permission to propagate or 430 | modify any covered work. These actions infringe copyright if you do 431 | not accept this License. Therefore, by modifying or propagating a 432 | covered work, you indicate your acceptance of this License to do so. 433 | 434 | 10. Automatic Licensing of Downstream Recipients. 435 | 436 | Each time you convey a covered work, the recipient automatically 437 | receives a license from the original licensors, to run, modify and 438 | propagate that work, subject to this License. You are not responsible 439 | for enforcing compliance by third parties with this License. 440 | 441 | An "entity transaction" is a transaction transferring control of an 442 | organization, or substantially all assets of one, or subdividing an 443 | organization, or merging organizations. If propagation of a covered 444 | work results from an entity transaction, each party to that 445 | transaction who receives a copy of the work also receives whatever 446 | licenses to the work the party's predecessor in interest had or could 447 | give under the previous paragraph, plus a right to possession of the 448 | Corresponding Source of the work from the predecessor in interest, if 449 | the predecessor has it or can get it with reasonable efforts. 450 | 451 | You may not impose any further restrictions on the exercise of the 452 | rights granted or affirmed under this License. For example, you may 453 | not impose a license fee, royalty, or other charge for exercise of 454 | rights granted under this License, and you may not initiate litigation 455 | (including a cross-claim or counterclaim in a lawsuit) alleging that 456 | any patent claim is infringed by making, using, selling, offering for 457 | sale, or importing the Program or any portion of it. 458 | 459 | 11. Patents. 460 | 461 | A "contributor" is a copyright holder who authorizes use under this 462 | License of the Program or a work on which the Program is based. The 463 | work thus licensed is called the contributor's "contributor version". 464 | 465 | A contributor's "essential patent claims" are all patent claims 466 | owned or controlled by the contributor, whether already acquired or 467 | hereafter acquired, that would be infringed by some manner, permitted 468 | by this License, of making, using, or selling its contributor version, 469 | but do not include claims that would be infringed only as a 470 | consequence of further modification of the contributor version. For 471 | purposes of this definition, "control" includes the right to grant 472 | patent sublicenses in a manner consistent with the requirements of 473 | this License. 474 | 475 | Each contributor grants you a non-exclusive, worldwide, royalty-free 476 | patent license under the contributor's essential patent claims, to 477 | make, use, sell, offer for sale, import and otherwise run, modify and 478 | propagate the contents of its contributor version. 479 | 480 | In the following three paragraphs, a "patent license" is any express 481 | agreement or commitment, however denominated, not to enforce a patent 482 | (such as an express permission to practice a patent or covenant not to 483 | sue for patent infringement). To "grant" such a patent license to a 484 | party means to make such an agreement or commitment not to enforce a 485 | patent against the party. 486 | 487 | If you convey a covered work, knowingly relying on a patent license, 488 | and the Corresponding Source of the work is not available for anyone 489 | to copy, free of charge and under the terms of this License, through a 490 | publicly available network server or other readily accessible means, 491 | then you must either (1) cause the Corresponding Source to be so 492 | available, or (2) arrange to deprive yourself of the benefit of the 493 | patent license for this particular work, or (3) arrange, in a manner 494 | consistent with the requirements of this License, to extend the patent 495 | license to downstream recipients. "Knowingly relying" means you have 496 | actual knowledge that, but for the patent license, your conveying the 497 | covered work in a country, or your recipient's use of the covered work 498 | in a country, would infringe one or more identifiable patents in that 499 | country that you have reason to believe are valid. 500 | 501 | If, pursuant to or in connection with a single transaction or 502 | arrangement, you convey, or propagate by procuring conveyance of, a 503 | covered work, and grant a patent license to some of the parties 504 | receiving the covered work authorizing them to use, propagate, modify 505 | or convey a specific copy of the covered work, then the patent license 506 | you grant is automatically extended to all recipients of the covered 507 | work and works based on it. 508 | 509 | A patent license is "discriminatory" if it does not include within 510 | the scope of its coverage, prohibits the exercise of, or is 511 | conditioned on the non-exercise of one or more of the rights that are 512 | specifically granted under this License. You may not convey a covered 513 | work if you are a party to an arrangement with a third party that is 514 | in the business of distributing software, under which you make payment 515 | to the third party based on the extent of your activity of conveying 516 | the work, and under which the third party grants, to any of the 517 | parties who would receive the covered work from you, a discriminatory 518 | patent license (a) in connection with copies of the covered work 519 | conveyed by you (or copies made from those copies), or (b) primarily 520 | for and in connection with specific products or compilations that 521 | contain the covered work, unless you entered into that arrangement, 522 | or that patent license was granted, prior to 28 March 2007. 523 | 524 | Nothing in this License shall be construed as excluding or limiting 525 | any implied license or other defenses to infringement that may 526 | otherwise be available to you under applicable patent law. 527 | 528 | 12. No Surrender of Others' Freedom. 529 | 530 | If conditions are imposed on you (whether by court order, agreement or 531 | otherwise) that contradict the conditions of this License, they do not 532 | excuse you from the conditions of this License. If you cannot convey a 533 | covered work so as to satisfy simultaneously your obligations under this 534 | License and any other pertinent obligations, then as a consequence you may 535 | not convey it at all. For example, if you agree to terms that obligate you 536 | to collect a royalty for further conveying from those to whom you convey 537 | the Program, the only way you could satisfy both those terms and this 538 | License would be to refrain entirely from conveying the Program. 539 | 540 | 13. Remote Network Interaction; Use with the GNU General Public License. 541 | 542 | Notwithstanding any other provision of this License, if you modify the 543 | Program, your modified version must prominently offer all users 544 | interacting with it remotely through a computer network (if your version 545 | supports such interaction) an opportunity to receive the Corresponding 546 | Source of your version by providing access to the Corresponding Source 547 | from a network server at no charge, through some standard or customary 548 | means of facilitating copying of software. This Corresponding Source 549 | shall include the Corresponding Source for any work covered by version 3 550 | of the GNU General Public License that is incorporated pursuant to the 551 | following paragraph. 552 | 553 | Notwithstanding any other provision of this License, you have 554 | permission to link or combine any covered work with a work licensed 555 | under version 3 of the GNU General Public License into a single 556 | combined work, and to convey the resulting work. The terms of this 557 | License will continue to apply to the part which is the covered work, 558 | but the work with which it is combined will remain governed by version 559 | 3 of the GNU General Public License. 560 | 561 | 14. Revised Versions of this License. 562 | 563 | The Free Software Foundation may publish revised and/or new versions of 564 | the GNU Affero General Public License from time to time. Such new versions 565 | will be similar in spirit to the present version, but may differ in detail to 566 | address new problems or concerns. 567 | 568 | Each version is given a distinguishing version number. If the 569 | Program specifies that a certain numbered version of the GNU Affero General 570 | Public License "or any later version" applies to it, you have the 571 | option of following the terms and conditions either of that numbered 572 | version or of any later version published by the Free Software 573 | Foundation. If the Program does not specify a version number of the 574 | GNU Affero General Public License, you may choose any version ever published 575 | by the Free Software Foundation. 576 | 577 | If the Program specifies that a proxy can decide which future 578 | versions of the GNU Affero General Public License can be used, that proxy's 579 | public statement of acceptance of a version permanently authorizes you 580 | to choose that version for the Program. 581 | 582 | Later license versions may give you additional or different 583 | permissions. However, no additional obligations are imposed on any 584 | author or copyright holder as a result of your choosing to follow a 585 | later version. 586 | 587 | 15. Disclaimer of Warranty. 588 | 589 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 590 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 591 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 592 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 593 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 594 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 595 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 596 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 597 | 598 | 16. Limitation of Liability. 599 | 600 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 601 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 602 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 603 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 604 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 605 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 606 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 607 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 608 | SUCH DAMAGES. 609 | 610 | 17. Interpretation of Sections 15 and 16. 611 | 612 | If the disclaimer of warranty and limitation of liability provided 613 | above cannot be given local legal effect according to their terms, 614 | reviewing courts shall apply local law that most closely approximates 615 | an absolute waiver of all civil liability in connection with the 616 | Program, unless a warranty or assumption of liability accompanies a 617 | copy of the Program in return for a fee. 618 | 619 | END OF TERMS AND CONDITIONS 620 | 621 | How to Apply These Terms to Your New Programs 622 | 623 | If you develop a new program, and you want it to be of the greatest 624 | possible use to the public, the best way to achieve this is to make it 625 | free software which everyone can redistribute and change under these terms. 626 | 627 | To do so, attach the following notices to the program. It is safest 628 | to attach them to the start of each source file to most effectively 629 | state the exclusion of warranty; and each file should have at least 630 | the "copyright" line and a pointer to where the full notice is found. 631 | 632 | 633 | Copyright (C) 634 | 635 | This program is free software: you can redistribute it and/or modify 636 | it under the terms of the GNU Affero General Public License as published 637 | by the Free Software Foundation, either version 3 of the License, or 638 | (at your option) any later version. 639 | 640 | This program is distributed in the hope that it will be useful, 641 | but WITHOUT ANY WARRANTY; without even the implied warranty of 642 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 643 | GNU Affero General Public License for more details. 644 | 645 | You should have received a copy of the GNU Affero General Public License 646 | along with this program. If not, see . 647 | 648 | Also add information on how to contact you by electronic and paper mail. 649 | 650 | If your software can interact with users remotely through a computer 651 | network, you should also make sure that it provides a way for users to 652 | get its source. For example, if your program is a web application, its 653 | interface could display a "Source" link that leads users to an archive 654 | of the code. There are many ways you could offer source, and different 655 | solutions will be better for different programs; see section 13 for the 656 | specific requirements. 657 | 658 | You should also get your employer (if you work as a programmer) or school, 659 | if any, to sign a "copyright disclaimer" for the program, if necessary. 660 | For more information on this, and how to apply and follow the GNU AGPL, see 661 | . -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include README.rst 2 | include requirements.txt 3 | recursive-include ckanext/extractor *.html *.json *.js *.less *.css *.mo 4 | -------------------------------------------------------------------------------- /README.rst: -------------------------------------------------------------------------------- 1 | ckanext-extractor 2 | ################# 3 | 4 | .. image:: https://travis-ci.org/stadt-karlsruhe/ckanext-extractor.svg?branch=master 5 | :target: https://travis-ci.org/stadt-karlsruhe/ckanext-extractor 6 | 7 | .. image:: https://coveralls.io/repos/github/stadt-karlsruhe/ckanext-extractor/badge.svg?branch=master 8 | :target: https://coveralls.io/github/stadt-karlsruhe/ckanext-extractor 9 | 10 | A CKAN_ extension for automatically extracting text and metadata from datasets. 11 | 12 | *ckanext-extractor* automatically extracts text and metadata from your 13 | resources and adds them to the search index so that they can be used to find 14 | your data. 15 | 16 | .. _CKAN: https://www.ckan.org 17 | 18 | 19 | Requirements 20 | ============ 21 | *ckanext-extractor* has been developed and tested with CKAN 2.6 and later. 22 | Other versions may or may not work. 23 | 24 | Since *ckanext-extractor* relies on the background job system introduced in 25 | CKAN 2.7, users of earlier CKAN versions need to also install ckanext-rq_. 26 | 27 | .. _ckanext-rq: https://github.com/ckan/ckanext-rq 28 | 29 | 30 | Installation 31 | ============ 32 | **Note:** The following steps assume a standard CKAN source installation. 33 | 34 | Install Python Package 35 | ---------------------- 36 | Activate your CKAN virtualenv:: 37 | 38 | . /usr/lib/ckan/default/bin/activate 39 | 40 | Install the latest development version of *ckanext-extractor* and its 41 | dependencies:: 42 | 43 | cd /usr/lib/ckan/default 44 | pip install -e git+https://github.com/stadt-karlsruhe/ckanext-extractor#egg=ckanext-extractor 45 | pip install -r src/ckanext-extractor/requirements.txt 46 | 47 | On a production system you'll probably want to pin a certain `release version`_ 48 | of *ckanext-extractor* instead:: 49 | 50 | pip install -e git+https://github.com/stadt-karlsruhe/ckanext-extractor@v0.4.0#egg=ckanext-extractor 51 | 52 | .. _release version: https://github.com/stadt-karlsruhe/ckanext-extractor/releases 53 | 54 | Configure CKAN 55 | -------------- 56 | Open your CKAN configuration file (e.g. ``/etc/ckan/default/production.ini``) 57 | and add ``extractor`` to the list of plugins:: 58 | 59 | ckan.plugins = ... extractor 60 | 61 | Initialize the database:: 62 | 63 | paster --plugin=ckanext-extractor init -c /etc/ckan/default/production.ini 64 | 65 | 66 | Start Background Worker 67 | ----------------------- 68 | *ckanext-extractor* uses background jobs to perform the extraction 69 | asynchronously so that they do not block the web server. You therefore need to 70 | make sure that a CKAN background worker is running:: 71 | 72 | paster --plugin=ckan jobs worker --config=/etc/ckan/default/production.ini 73 | 74 | See the `CKAN documentation`_ for more information on background jobs and for 75 | tips on how to run workers in production environments. 76 | 77 | .. _`CKAN documentation`: http://docs.ckan.org/en/latest/maintaining/background-tasks.html 78 | 79 | 80 | Configure Solr 81 | -------------- 82 | For the actual extraction CKAN's Apache Solr server is used. However, the 83 | necessary Solr plugins are deactivated by default. To enable them, find your 84 | main Solr configuration file (usually ``/etc/solr/conf/solrconfig.xml``) and 85 | add/uncomment the following lines:: 86 | 87 | 88 | 89 | 90 | **Note:** The Solr packages on Ubuntu are broken_ and do not contain the 91 | necessary files. You can simply download an `official release`_ of the same 92 | version, unpack it to a suitable location (without installing it) and adjust 93 | the ``dir`` arguments in the configuration lines above accordingly. For 94 | example, if you have unpacked the files to ``/var/lib/apache-solr``, then you 95 | would need to put the following lines into ``solrconfig.xml``:: 96 | 97 | 98 | 99 | 100 | .. _broken: https://bugs.launchpad.net/ubuntu/+source/lucene-solr/+bug/1565637 101 | .. _`official release`: http://archive.apache.org/dist/lucene/solr 102 | 103 | Once the text and metadata have been extracted they need to be added to the 104 | Solr index, which requires appropriate Solr fields. To set them up add the 105 | following lines to your Solr schema configuration (usually 106 | ``/etc/solr/conf/schema.xml``):: 107 | 108 | # Directly before the line that says "" 109 | 110 | 111 | # Directly before the line that says "" 112 | 113 | 114 | Make sure to restart Solr after you have applied the changes. For example, if 115 | you're using Jetty as an application server for Solr, then 116 | 117 | :: 118 | 119 | sudo service jetty restart 120 | 121 | 122 | Restart CKAN 123 | ------------ 124 | Finally, restart your CKAN server:: 125 | 126 | sudo service apache2 restart 127 | 128 | 129 | Test your Installation 130 | ---------------------- 131 | The installation is now complete. To verify that everything is working open the 132 | URL ``/api/3/action/extractor_list``, e.g. via 133 | 134 | :: 135 | 136 | wget -qO - http://localhost/api/3/action/extractor_list 137 | 138 | The output should look like this (in particular, ``success`` should be ``true``):: 139 | 140 | {"help": "http://localhost/api/3/action/help_show?name=extractor_list", "success": true, "result": []} 141 | 142 | 143 | You're Done! 144 | ------------ 145 | Your installation of *ckanext-extractor* is now complete, and new/updated 146 | resources will have their metadata automatically indexed. You may want to 147 | adapt the configuration to your needs, see below for details. Once that is 148 | done you may also want to extract metadata from your existing resources:: 149 | 150 | . /usr/lib/ckan/default/bin/activate 151 | paster --plugin=ckanext-extractor extract all -c /etc/ckan/default/production.ini 152 | 153 | This and other ``paster`` administration commands are explained below in more 154 | detail. 155 | 156 | 157 | Configuration 158 | ============= 159 | *ckanext-extractor* can be configured via the usual CKAN configuration file (e.g. 160 | ``/etc/ckan/default/production.ini``). You must restart your CKAN server after 161 | updating the configuration. 162 | 163 | Formats for Extraction 164 | ---------------------- 165 | While Solr can extract text and metadata from many file formats not all of 166 | them might be of interest to you. You can therefore configure for which formats 167 | extraction is performed via the ``ckanext.extractor.indexed_formats`` option. It 168 | takes a list of space-separated formats, where the format is the one specified 169 | in a resource's CKAN metadata (and not the file extension or MIME type):: 170 | 171 | ckanext.extractor.indexed_formats = pdf txt 172 | 173 | Formats are case-insensitive. You can use wildcards (``*`` and ``?``) to match 174 | multiple formats. To extract data from all formats simply set 175 | 176 | :: 177 | 178 | ckanext.extractor.indexed_formats = * 179 | 180 | By default, extraction is only enabled for the PDF format:: 181 | 182 | ckanext.extractor.indexed_formats = pdf 183 | 184 | Fields for Indexing 185 | ------------------- 186 | Once text and metadata have been extracted they can be added to the search 187 | index. Again, Solr supports more metadata fields than one usually needs. You 188 | can therefore configure which fields are indexed via the 189 | ``ckanext.extractor.indexed_fields`` option. It takes a space-separated list of 190 | field names:: 191 | 192 | ckanext.extractor.indexed_fields = fulltext author 193 | 194 | The full text of a document is available via the ``fulltext`` field. Field names 195 | are case-insensitive. You can use wildcards (``*`` and ``?``) to match multiple 196 | field names. To index all fields simply set 197 | 198 | :: 199 | 200 | ckanext.extractor.indexed_fields = * 201 | 202 | By default, only the full text of a document is indexed:: 203 | 204 | ckanext.extractor.indexed_fields = fulltext 205 | 206 | **Note:** *ckanext-extractor* normalizes the field names reported by Solr by 207 | replacing underscores (``_``) with hyphens (``-``). In addition, multiple 208 | values for the same field in the same document are collapsed into a single 209 | value. 210 | 211 | 212 | Paster Commands 213 | =============== 214 | In general, *ckanext-extractor* works automatically: whenever a new resource is 215 | created or an existing resource changes, its metadata is extracted and indexed. 216 | However, for administration purposes, metadata can also be managed from the 217 | command line using the paster_ tool. 218 | 219 | .. _paster: http://docs.ckan.org/en/latest/maintaining/paster.html 220 | 221 | **Note:** You have to activate your virtualenv before you can use these 222 | commands:: 223 | 224 | . /usr/lib/ckan/default/bin/activate 225 | 226 | The general form for a paster command is 227 | 228 | :: 229 | 230 | paster --plugin=ckanext-extractor COMMAND ARGUMENTS --config=/etc/ckan/default/production.ini 231 | 232 | Replace ``COMMAND`` and ``ARGUMENTS`` as described below. For example:: 233 | 234 | paster --plugin=ckanext-extractor extract all --config=/etc/ckan/default/production.ini 235 | 236 | 237 | - ``delete (all | ID [ID [...]])``: Delete metadata. You can specify one or 238 | more resource IDs or a single ``all`` argument (in which case all metadata is 239 | deleted). 240 | 241 | - ``extract [--force] (all | ID [ID [...]])``: Extract metadata. You can 242 | specify one or more resource IDs or a single ``all`` argument (in which case 243 | metadata is extracted from all resources with appropriate formats). An 244 | optional ``--force`` argument can be used to force extraction even if the 245 | resource is unchanged, or if another extraction job already has been 246 | scheduled for that resource. 247 | 248 | Note that this command only schedules the necessary extraction background 249 | tasks. A background jobs worker has to be running for the extraction to 250 | actually happen. 251 | 252 | - ``init``: Initialize the database tables for *ckanext-extractor*. You only 253 | need to use this once (during the installation). 254 | 255 | - ``list``: List the IDs of all resources for which metadata has been 256 | extracted. 257 | 258 | - ``show (all | ID [ID [...]])``: Show extracted metadata. You can specify one 259 | or more resource IDs or a single ``all`` argument (in which case all metadata 260 | is shown). 261 | 262 | 263 | API 264 | === 265 | Metadata can be managed via the standard `CKAN API`_. Unless noted otherwise 266 | all commands are only available via POST requests to authenticated users. 267 | 268 | .. _`CKAN API`: http://docs.ckan.org/en/latest/api/index.html 269 | 270 | ``extractor_delete`` 271 | -------------------- 272 | Delete metadata. 273 | 274 | Only available to administrators. 275 | 276 | Parameters: 277 | 278 | :id: ID of the resource for which metadata should be deleted. 279 | 280 | 281 | ``extractor_extract`` 282 | --------------------- 283 | Extract metadata. 284 | 285 | This function schedules a background task for extracting metadata from a 286 | resource. 287 | 288 | Only available to administrators. 289 | 290 | Parameters: 291 | 292 | :id: ID of the resource for which metadata should be extracted. 293 | 294 | :force: Optional boolean flag to force extraction even if the resource is 295 | unchanged, or if an extraction task has already been scheduled for that 296 | resource. 297 | 298 | Returns a dict with the following entries: 299 | 300 | :status: A string describing the state of the metadata. This can be one of the 301 | following: 302 | 303 | :new: if no metadata for the resource existed before 304 | 305 | :update: if metadata existed but is going to be updated 306 | 307 | :unchanged: if metadata existed but won't get updated (for example because 308 | the resource's URL did not change since the last extraction) 309 | 310 | :inprogress: if a background extraction task for this resource is already 311 | in progress 312 | 313 | :ignored: if the resource format is configured to be ignored 314 | 315 | Note that if ``force`` is true then an extraction job will be scheduled 316 | regardless of the status reported, unless that state is ``ignored``. 317 | 318 | :task_id: The ID of the background task. If ``state`` is ``new`` or ``update`` 319 | then this is the ID of a newly created task. If ``state`` is ``inprogress`` 320 | then it's the ID of the existing task. Otherwise it is ``null``. 321 | 322 | If ``force`` is true then this is the ID of the new extraction task. 323 | 324 | ``extractor_list`` 325 | ------------------ 326 | List resources with metadata. 327 | 328 | Returns a list with the IDs of all resources for which metadata has been 329 | extracted. 330 | 331 | Available to all (even anonymous) users via GET and POST. 332 | 333 | ``extractor_show`` 334 | ------------------ 335 | Show the metadata for a resource. 336 | 337 | Parameters: 338 | 339 | :id: ID of the resource for which metadata should be extracted. 340 | 341 | Returns a dict with the resource's metadata and information about the last 342 | extraction. 343 | 344 | Available to all (even anonymous) users via GET and POST. 345 | 346 | 347 | Postprocessing Extraction Results 348 | ================================= 349 | The ``ckanext.extractor.interfaces.IExtractorPostprocessor`` interface can be 350 | used to hook into the extraction process. It allows you to postprocess 351 | extraction results and to automatically trigger actions that use the extraction 352 | results for other purposes. 353 | 354 | The interface offers 3 hooks: 355 | 356 | - ``extractor_after_extract(resource_dict, extracted)`` is called right after 357 | the extraction before the extracted metadata ``extracted`` is filtered and 358 | stored. You can modify ``extracted`` (in-place) and the changes will end up 359 | in the database. 360 | 361 | - ``extractor_after_save(resource_dict, metadata_dict)`` is called after the 362 | metadata has been filtered and stored in the database but before it is 363 | indexed. ``metadata_dict`` is a dict-representation of a 364 | ``ckanext.extractor.model.ResourceMetadata`` instance and contains both the 365 | extracted metadata and information about the extraction process 366 | (meta-metadata, so to speak). 367 | 368 | - ``extractor_after_index(resource_dict, metadata_dict)`` is called at the very 369 | end of the extraction process, after the metadata has been extracted, 370 | filtered, stored and indexed. 371 | 372 | 373 | Adjusting the download request 374 | ============================== 375 | The ``ckanext.extractor.interfaces.IExtractorRequest`` interface can be used to 376 | modify the HTTP request made for downloading a resource file for extraction. A 377 | typical use case would be to add custom authentication headers required by the 378 | remote server which are normally provided by the user's browser. 379 | 380 | The interface offers 1 hook: 381 | 382 | - ``extractor_before_request(request)`` is called before a request is sent to 383 | download a resource file for extraction. The ``request`` parameter is a 384 | ``PreparedRequest`` object `from the requests library 385 | `_. 386 | 387 | 388 | Development 389 | =========== 390 | 391 | :: 392 | 393 | . /usr/lib/ckan/default/bin/activate 394 | git clone https://github.com/stadt-karlsruhe/ckanext-extractor.git 395 | cd ckanext-extractor 396 | python setup.py develop 397 | pip install -r dev-requirements.txt 398 | 399 | 400 | Running the Tests 401 | ----------------- 402 | To run the tests, activate your CKAN virtualenv and do:: 403 | 404 | ./runtests.sh 405 | 406 | Any additional arguments are passed on to ``nosetests``. 407 | 408 | 409 | Change Log 410 | ========== 411 | See the file `CHANGELOG.md`. 412 | 413 | 414 | License 415 | ======= 416 | Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 417 | 418 | Distributed under the GNU Affero General Public License. See the file 419 | ``LICENSE`` for details. 420 | 421 | -------------------------------------------------------------------------------- /ckanext/__init__.py: -------------------------------------------------------------------------------- 1 | # this is a namespace package 2 | try: 3 | import pkg_resources 4 | pkg_resources.declare_namespace(__name__) 5 | except ImportError: 6 | import pkgutil 7 | __path__ = pkgutil.extend_path(__path__, __name__) 8 | -------------------------------------------------------------------------------- /ckanext/extractor/__init__.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | __version__ = '0.4.0' 23 | 24 | -------------------------------------------------------------------------------- /ckanext/extractor/config.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | from fnmatch import fnmatch 23 | import logging.config 24 | import os.path 25 | from string import lower 26 | 27 | import paste.deploy 28 | from paste.registry import Registry 29 | from pylons import config, translator 30 | 31 | from ckan.plugins import toolkit 32 | from ckan.config.environment import load_environment 33 | from ckan.lib.cli import MockTranslator 34 | 35 | 36 | DEFAULTS = { 37 | 'ckanext.extractor.indexed_formats': 'pdf', 38 | 'ckanext.extractor.indexed_fields': 'fulltext', 39 | } 40 | 41 | TRANSFORMATIONS = { 42 | 'ckanext.extractor.indexed_formats': [lower, toolkit.aslist], 43 | 'ckanext.extractor.indexed_fields': [lower, toolkit.aslist], 44 | } 45 | 46 | 47 | def get(setting): 48 | """ 49 | Get configuration setting. 50 | 51 | ``setting`` is the setting without the ``ckanext.extractor.`` 52 | prefix. 53 | 54 | Handles defaults and transformations. 55 | """ 56 | setting = 'ckanext.extractor.' + setting 57 | value = config.get(setting, DEFAULTS[setting]) 58 | for transformation in TRANSFORMATIONS[setting]: 59 | value = transformation(value) 60 | return value 61 | 62 | 63 | # Adapted from ckanext-archiver 64 | def load_config(ini_path): 65 | """ 66 | Load CKAN configuration. 67 | """ 68 | ini_path = os.path.abspath(ini_path) 69 | logging.config.fileConfig(ini_path, disable_existing_loggers=False) 70 | conf = paste.deploy.appconfig('config:' + ini_path) 71 | load_environment(conf.global_conf, conf.local_conf) 72 | _register_translator() 73 | 74 | 75 | # Adapted from ckanext-archiver 76 | def _register_translator(): 77 | """ 78 | Register a translator in this thread. 79 | """ 80 | global registry 81 | try: 82 | registry 83 | except NameError: 84 | registry = Registry() 85 | registry.prepare() 86 | global translator_obj 87 | try: 88 | translator_obj 89 | except NameError: 90 | translator_obj = MockTranslator() 91 | registry.register(translator, translator_obj) 92 | 93 | 94 | def _any_match(s, patterns): 95 | """ 96 | Check if a string matches at least one pattern. 97 | """ 98 | return any(fnmatch(s, pattern) for pattern in patterns) 99 | 100 | 101 | def is_field_indexed(field): 102 | """ 103 | Check if a metadata field is configured to be indexed. 104 | """ 105 | return _any_match(field.lower(), get('indexed_fields')) 106 | 107 | 108 | def is_format_indexed(format): 109 | """ 110 | Check if a resource format is configured to be indexed. 111 | """ 112 | return _any_match(format.lower(), get('indexed_formats')) 113 | 114 | -------------------------------------------------------------------------------- /ckanext/extractor/fanstatic/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stadt-karlsruhe/ckanext-extractor/1d49dd615493db21ce0004b40f2ae0bb68f3869f/ckanext/extractor/fanstatic/.gitignore -------------------------------------------------------------------------------- /ckanext/extractor/i18n/ckanext-extractor.pot: -------------------------------------------------------------------------------- 1 | # Translations template for ckanext-extractor. 2 | # Copyright (C) 2016 ORGANIZATION 3 | # This file is distributed under the same license as the ckanext-extractor 4 | # project. 5 | # FIRST AUTHOR , 2016. 6 | # 7 | #, fuzzy 8 | msgid "" 9 | msgstr "" 10 | "Project-Id-Version: ckanext-extractor 0.0.1\n" 11 | "Report-Msgid-Bugs-To: EMAIL@ADDRESS\n" 12 | "POT-Creation-Date: 2016-04-25 12:20+0200\n" 13 | "PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n" 14 | "Last-Translator: FULL NAME \n" 15 | "Language-Team: LANGUAGE \n" 16 | "MIME-Version: 1.0\n" 17 | "Content-Type: text/plain; charset=utf-8\n" 18 | "Content-Transfer-Encoding: 8bit\n" 19 | "Generated-By: Babel 0.9.6\n" 20 | 21 | #: ckanext/extractor/logic/action.py:28 22 | msgid "No metadata found for resource '{resource}'." 23 | msgstr "" 24 | 25 | -------------------------------------------------------------------------------- /ckanext/extractor/interfaces.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | from ckan import plugins 23 | 24 | 25 | class IExtractorPostprocessor(plugins.Interface): 26 | ''' 27 | Postprocess extracted metadata. 28 | 29 | This interfaces provides hooks for postprocess resource metadata 30 | after its extraction. They can be used to modify the metadata before 31 | it is stored or to automatically trigger actions that use the 32 | extraction results for other purposes. 33 | 34 | Note that none of the hooks are called if an exception ocurred 35 | during the extraction. 36 | ''' 37 | def extractor_after_extract(self, resource_dict, extracted): 38 | ''' 39 | Postprocess metadata after extraction. 40 | 41 | Called directly after metadata has been extracted and 42 | normalized. ``extracted`` is a dict containing the metadata. 43 | 44 | Implementations can modify ``extracted`` in place, the return 45 | value of the function is ignored. 46 | 47 | Note that filtering of metadata according to 48 | ``ckanext.extractor.indexed_fields`` is done after this function 49 | is called. 50 | ''' 51 | 52 | def extractor_after_save(self, resource_dict, metadata_dict): 53 | ''' 54 | Postprocess metadata after it has been saved. 55 | 56 | Called after metadata has been extracted and saved in the 57 | database. 58 | 59 | ``metadata_dict`` is a dict-representation of the resource's 60 | ``ckanext.extractor.model.ResourceMetadata`` instance. Changes 61 | to ``metadata_dict`` and the return value of the function are 62 | ignored. 63 | 64 | Note: When this function is called the fields have been filtered 65 | according to ``ckanext.extractor.indexed_fields``, but the 66 | extracted metadata hasn't been indexed, yet. 67 | ''' 68 | 69 | def extractor_after_index(self, resource_dict, metadata_dict): 70 | ''' 71 | Postprocess metadata after it has been indexed. 72 | 73 | Called after the package of the resource whose metadata has been 74 | extracted has been re-indexed after the extraction. 75 | 76 | ``resource_dict`` and ``metadata_dict`` are dict-representations 77 | of the resource and the metadata, respectively. Changes to them 78 | and the return value of the function are ignored. 79 | 80 | Note: When this function is called the fields have been filtered 81 | according to ``ckanext.extractor.indexed_fields``. 82 | ''' 83 | 84 | 85 | class IExtractorRequest(plugins.Interface): 86 | ''' 87 | Alter HTTP download requests. 88 | 89 | This interface allows you to modify the HTTP request for downloading 90 | a resource file, e.g. if the remote server requires certain 91 | authentication headers. 92 | ''' 93 | def extractor_before_request(self, request): 94 | ''' 95 | Alter a HTTP download request. 96 | 97 | ``request`` is a ``PreparedRequest`` object. 98 | 99 | This function must return a ``PreparedRequest`` object, which 100 | can either be the original request after it has been modified or 101 | a completely new one. 102 | 103 | Details can be found in the `requests documentation 104 | `_. 105 | ''' 106 | return request 107 | -------------------------------------------------------------------------------- /ckanext/extractor/lib.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import datetime 23 | import tempfile 24 | 25 | from ckan.plugins import PluginImplementations 26 | from .interfaces import IExtractorRequest 27 | 28 | from pylons import config 29 | import pysolr 30 | from requests import Request, Session 31 | 32 | 33 | def download_and_extract(resource_url): 34 | """ 35 | Download resource and extract metadata using Solr. 36 | 37 | The extracted metadata is cleaned and returned. 38 | """ 39 | session = Session() 40 | request = Request('GET', resource_url).prepare() 41 | for plugin in PluginImplementations(IExtractorRequest): 42 | request = plugin.extractor_before_request(request) 43 | with tempfile.NamedTemporaryFile() as f: 44 | r = session.send(request, stream=True) 45 | r.raise_for_status() 46 | for chunk in r.iter_content(chunk_size=1024): 47 | f.write(chunk) 48 | f.flush() 49 | f.seek(0) 50 | data = pysolr.Solr(config['solr_url']).extract(f, extractFormat='text') 51 | data['metadata']['fulltext'] = data['contents'] 52 | return dict(clean_metadatum(*x) for x in data['metadata'].iteritems()) 53 | 54 | 55 | def clean_metadatum(key, value): 56 | """ 57 | Clean an extracted metadatum. 58 | 59 | Takes a key/value pair and returns it in cleaned form. 60 | """ 61 | if isinstance(value, list) and len(value) == 1: 62 | # Flatten 1-element lists 63 | value = value[0] 64 | key = key.lower().replace('_', '-') 65 | return key, value 66 | 67 | -------------------------------------------------------------------------------- /ckanext/extractor/logic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stadt-karlsruhe/ckanext-extractor/1d49dd615493db21ce0004b40f2ae0bb68f3869f/ckanext/extractor/logic/__init__.py -------------------------------------------------------------------------------- /ckanext/extractor/logic/action.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import logging 23 | 24 | import ckan.plugins.toolkit as toolkit 25 | from ckan.logic import validate 26 | from pylons import config 27 | from sqlalchemy.orm.exc import NoResultFound 28 | 29 | from . import schema 30 | from .helpers import check_access 31 | from ..model import ResourceMetadata, ResourceMetadatum 32 | from ..config import is_format_indexed 33 | from ..tasks import extract 34 | 35 | try: 36 | enqueue_job = toolkit.enqueue_job 37 | except AttributeError: 38 | # CKAN 2.6 or older 39 | from ckanext.rq.jobs import enqueue as enqueue_job 40 | 41 | 42 | log = logging.getLogger(__name__) 43 | 44 | 45 | def _get_metadata(resource_id): 46 | try: 47 | return ResourceMetadata.one(resource_id=resource_id) 48 | except NoResultFound: 49 | raise toolkit.ObjectNotFound( 50 | toolkit._("No metadata found for resource '{resource}'.").format( 51 | resource=resource_id)) 52 | 53 | 54 | @check_access('extractor_delete') 55 | @validate(schema.extractor_delete) 56 | def extractor_delete(context, data_dict): 57 | """ 58 | Delete the metadata for a resource. 59 | 60 | :param string id: The ID or the name of the resource 61 | """ 62 | log.debug('extractor_delete {}'.format(data_dict['id'])) 63 | metadata = _get_metadata(data_dict['id']) 64 | metadata.delete().commit() 65 | 66 | 67 | @check_access('extractor_extract') 68 | @validate(schema.extractor_extract) 69 | def extractor_extract(context, data_dict): 70 | """ 71 | Extract and store metadata for a resource. 72 | 73 | Metadata extraction is done in an asynchronous background job, so 74 | this function may return before extraction is complete. 75 | 76 | :param string id: The ID or name of the resource 77 | 78 | :param boolean force: Extract metadata even if the resource hasn't 79 | changed, or if an extraction task is already scheduled for the 80 | resource (optional). 81 | 82 | :rtype: A dict with the following keys: 83 | 84 | :status: A string describing the state of the metadata. This 85 | can be one of the following: 86 | 87 | :new: if no metadata for the resource existed before 88 | 89 | :update: if metadata existed but is going to be updated 90 | 91 | :unchanged: if metadata existed but won't get updated 92 | (for example because the resource's URL did not 93 | change since the last extraction) 94 | 95 | :inprogress: if a background extraction task for this 96 | resource is already in progress 97 | 98 | :ignored: if the resource format is configured to be 99 | ignored 100 | 101 | Note that if ``force`` is true then an extraction job will 102 | be scheduled regardless of the status reported, unless that 103 | status is ``ignored``. 104 | 105 | :task_id: The ID of the background task. If ``state`` is ``new`` 106 | or ``update`` then this is the ID of a newly created task. 107 | If ``state`` is ``inprogress`` then it's the ID of the 108 | existing task. Otherwise it is ``null``. 109 | 110 | If ``force`` is true then this is the ID of the new 111 | extraction task. 112 | 113 | """ 114 | log.debug('extractor_extract {}'.format(data_dict['id'])) 115 | force = data_dict.get('force', False) 116 | resource = toolkit.get_action('resource_show')(context, data_dict) 117 | task_id = None 118 | metadata = None 119 | try: 120 | metadata = ResourceMetadata.one(resource_id=resource['id']) 121 | if metadata.task_id: 122 | status = 'inprogress' 123 | task_id = metadata.task_id 124 | elif not is_format_indexed(resource['format']): 125 | metadata.delete() 126 | metadata.commit() 127 | metadata = None 128 | status = 'ignored' 129 | elif (metadata.last_url != resource['url'] 130 | or metadata.last_format != resource['format']): 131 | status = 'update' 132 | else: 133 | status = 'unchanged' 134 | except NoResultFound: 135 | if is_format_indexed(resource['format']): 136 | status = 'new' 137 | else: 138 | status = 'ignored' 139 | if status in ('new', 'update') or (status != 'ignored' and force): 140 | args = (config['__file__'], resource) 141 | title = 'Metadata extraction for resource {}'.format(resource['id']) 142 | if metadata is None: 143 | metadata = ResourceMetadata.create(resource_id=resource['id']) 144 | job = enqueue_job(extract, args, title=title) 145 | task_id = metadata.task_id = job.id 146 | metadata.save() 147 | return { 148 | 'status': status, 149 | 'task_id': task_id, 150 | } 151 | 152 | 153 | @toolkit.side_effect_free 154 | @check_access('extractor_list') 155 | @validate(schema.extractor_list) 156 | def extractor_list(context, data_dict): 157 | """ 158 | List resources that have metadata. 159 | 160 | Returns a list with the IDs of the resources which have metadata 161 | associated with them. 162 | 163 | :rtype: list 164 | """ 165 | log.debug('extractor_list') 166 | return [m.resource_id for m in ResourceMetadata.filter_by(task_id=None)] 167 | 168 | 169 | @toolkit.side_effect_free 170 | @check_access('extractor_show') 171 | @validate(schema.extractor_show) 172 | def extractor_show(context, data_dict): 173 | """ 174 | Show the stored metadata for a resource. 175 | 176 | :param string id: The ID or name of the resource 177 | 178 | :rtype: dict 179 | """ 180 | log.debug('extractor_show {}'.format(data_dict['id'])) 181 | metadata = _get_metadata(data_dict['id']) 182 | result = metadata.as_dict() 183 | result['meta'] = dict(metadata.meta) 184 | return result 185 | 186 | -------------------------------------------------------------------------------- /ckanext/extractor/logic/auth.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import logging 23 | 24 | import ckan.plugins.toolkit as toolkit 25 | 26 | 27 | log = logging.getLogger(__name__) 28 | 29 | 30 | def _only_sysadmins(context, datadict): 31 | return {'success': False} 32 | 33 | 34 | @toolkit.auth_allow_anonymous_access 35 | def _everybody(context, datadict): 36 | return {'success': True} 37 | 38 | 39 | extractor_delete = _only_sysadmins 40 | extractor_extract = _only_sysadmins 41 | extractor_list = _everybody 42 | extractor_show = _everybody 43 | 44 | -------------------------------------------------------------------------------- /ckanext/extractor/logic/helpers.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import functools 23 | import logging 24 | 25 | from ckan.plugins import toolkit 26 | 27 | 28 | log = logging.getLogger(__name__) 29 | 30 | 31 | def check_access(auth_func_name): 32 | """ 33 | Decorator for API function authorization. 34 | 35 | Calls the auth function of the given name to make sure that the 36 | user is authorized to execute the function. 37 | """ 38 | def decorator(f): 39 | @functools.wraps(f) 40 | def wrapped(context, data_dict): 41 | toolkit.check_access(auth_func_name, context, data_dict) 42 | return f(context, data_dict) 43 | return wrapped 44 | return decorator 45 | 46 | -------------------------------------------------------------------------------- /ckanext/extractor/logic/schema.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | from inspect import getmembers 23 | import logging 24 | 25 | from ckan.lib.navl.validators import ignore_missing, not_empty 26 | from ckan.logic.schema import default_pagination_schema 27 | from ckan.logic.validators import boolean_validator 28 | 29 | 30 | log = logging.getLogger(__name__) 31 | 32 | 33 | class _Schema(object): 34 | """ 35 | Pseudo-class for composable schema definitions. 36 | 37 | Creating an instance of this class will return a dict with the 38 | class' variables instead of a real instance. This allows you to 39 | define composable schemas via inheritance:: 40 | 41 | class Schema1(_Schema): 42 | field1 = [not_empty, unicode] 43 | 44 | class Schema2(Schema1): 45 | field2 = [ignore_missing, unicode] 46 | 47 | print(Schema2()) 48 | # { 49 | # 'field1': [not_empty, unicode], 50 | # 'field2': [ignore_missing, unicode] 51 | # } 52 | """ 53 | def __new__(cls): 54 | return {key: value for key, value in getmembers(cls) if not 55 | key.startswith('__')} 56 | 57 | 58 | class _MandatoryID(_Schema): 59 | id = [not_empty, unicode] 60 | 61 | extractor_delete = _MandatoryID 62 | 63 | class extractor_extract(_MandatoryID): 64 | force = [ignore_missing, boolean_validator] 65 | 66 | extractor_list = default_pagination_schema 67 | extractor_show = _MandatoryID 68 | 69 | -------------------------------------------------------------------------------- /ckanext/extractor/model.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | """ 21 | Data model. 22 | 23 | The metadata fields extracted by Solr/Tika vary from one filetype to 24 | another. Therefore a flexible way of storing a resource's metadata is 25 | required instead of a fixed set of columns. We achieve this using a 26 | separate table in which we store both the name and the value of each 27 | individual metadatum. Using SQLAlchemy's ``association_proxy`` and 28 | ``attribute_mapped_collection`` that table is then accessed in a dict- 29 | like fashion using the ``ResourceMetadata`` class. This means that you 30 | will probably never need to use the ``ResourceMetadatum`` class. 31 | 32 | In addition to the resource metadata, the class ``ResourceMetadata`` 33 | also stores information about the extraction process. 34 | """ 35 | 36 | from __future__ import absolute_import, print_function, unicode_literals 37 | 38 | import logging 39 | 40 | from sqlalchemy import Column, ForeignKey, Table, types 41 | from sqlalchemy.ext.associationproxy import association_proxy 42 | from sqlalchemy.orm import relationship 43 | from sqlalchemy.orm.collections import attribute_mapped_collection 44 | 45 | from ckan.model.domain_object import DomainObject 46 | from ckan.model.meta import mapper, metadata 47 | 48 | 49 | log = logging.getLogger(__name__) 50 | 51 | resource_metadatum_table = None 52 | RESOURCE_METADATUM_TABLE_NAME = 'ckanext_extractor_resource_metadatum' 53 | 54 | resource_metadata_table = None 55 | RESOURCE_METADATA_TABLE_NAME = 'ckanext_extractor_resource_metadata' 56 | 57 | 58 | class BaseObject(DomainObject): 59 | """ 60 | Base class for data models. 61 | """ 62 | @classmethod 63 | def filter_by(cls, **kwargs): 64 | return cls.Session.query(cls).filter_by(**kwargs) 65 | 66 | @classmethod 67 | def one(cls, **kwargs): 68 | return cls.filter_by(**kwargs).one() 69 | 70 | @classmethod 71 | def create(cls, **kwargs): 72 | instance = cls(**kwargs) 73 | cls.Session.add(instance) 74 | cls.Session.commit() 75 | return instance 76 | 77 | def delete(self): 78 | super(BaseObject, self).delete() 79 | return self 80 | 81 | 82 | def setup(): 83 | """ 84 | Set up ORM. 85 | 86 | Does not create any database tables, see :py:func:`create_tables` 87 | for that. 88 | """ 89 | global resource_metadata_table 90 | if resource_metadata_table is None: 91 | log.debug('Defining resource metadata table') 92 | resource_metadata_table = Table( 93 | RESOURCE_METADATA_TABLE_NAME, 94 | metadata, 95 | Column('resource_id', types.UnicodeText, ForeignKey('resource.id', 96 | ondelete='CASCADE', onupdate='CASCADE'), nullable=False, 97 | primary_key=True), 98 | Column('last_extracted', types.DateTime), 99 | Column('last_url', types.UnicodeText), 100 | Column('last_format', types.UnicodeText), 101 | Column('task_id', types.UnicodeText) 102 | ) 103 | mapper( 104 | ResourceMetadata, 105 | resource_metadata_table, 106 | properties={ 107 | '_meta': relationship(ResourceMetadatum, collection_class= 108 | attribute_mapped_collection('key'), 109 | cascade='all, delete, delete-orphan'), 110 | } 111 | ) 112 | else: 113 | log.debug('Resource metadata table already defined') 114 | global resource_metadatum_table 115 | if resource_metadatum_table is None: 116 | log.debug('Defining resource metadatum table') 117 | resource_metadatum_table = Table( 118 | RESOURCE_METADATUM_TABLE_NAME, 119 | metadata, 120 | Column('id', types.Integer, nullable=False, primary_key=True), 121 | Column('resource_id', types.UnicodeText, ForeignKey( 122 | RESOURCE_METADATA_TABLE_NAME + '.resource_id', 123 | ondelete='CASCADE', onupdate='CASCADE'), nullable=False), 124 | Column('key', types.UnicodeText, nullable=False), 125 | Column('value', types.UnicodeText) 126 | ) 127 | mapper(ResourceMetadatum, resource_metadatum_table) 128 | else: 129 | log.debug('Resource metadatum table already defined') 130 | 131 | 132 | def create_tables(): 133 | """ 134 | Create database tables. 135 | """ 136 | setup() 137 | if not resource_metadata_table.exists(): 138 | log.info('Creating resource metadata table') 139 | resource_metadata_table.create() 140 | else: 141 | log.info('Resource metadata table already exists') 142 | if not resource_metadatum_table.exists(): 143 | log.info('Creating resource metadatum table') 144 | resource_metadatum_table.create() 145 | else: 146 | log.info('Resource metadatum table already exists') 147 | 148 | 149 | class ResourceMetadatum(BaseObject): 150 | """ 151 | A single metadatum of a resource (e.g. ``fulltext``) and its value. 152 | """ 153 | def __init__(self, key, value=None): 154 | self.key = key 155 | self.value = value 156 | 157 | 158 | class ResourceMetadata(BaseObject): 159 | """ 160 | A resource's metadata and information about their extraction. 161 | """ 162 | meta = association_proxy('_meta', 'value') 163 | 164 | def as_dict(self): 165 | d = super(ResourceMetadata, self).as_dict() 166 | # DomainObject.as_dict doesn't include association proxies 167 | d['meta'] = dict(self.meta) 168 | return d 169 | 170 | -------------------------------------------------------------------------------- /ckanext/extractor/paster.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import sys 23 | 24 | from sqlalchemy import inspect 25 | 26 | from ckan.lib.cli import CkanCommand 27 | 28 | # Do not import modules for CKAN or ckanext-extractor here (unless you know 29 | # what you're doing), since their loggers won't work if imported before the 30 | # CKAN configuration has been loaded. 31 | 32 | 33 | def _error(msg): 34 | sys.exit('ERROR: ' + msg) 35 | 36 | 37 | def _compress(s, n=50): 38 | s = unicode(s) 39 | if len(s) < n: 40 | return s 41 | else: 42 | return s[:n/2] + ' ... ' + s[-n/2:] 43 | 44 | 45 | class ExtractorCommand(CkanCommand): 46 | """ 47 | Base class for ckanext.extractor Paster commands. 48 | """ 49 | def _get_ids(self, only_with_metadata=False): 50 | """ 51 | Get list of resource IDs from command line arguments. 52 | 53 | Returns the specific IDs listed or all IDs if ``all`` was passed. 54 | 55 | If ``only_with_metadata`` is true and ``all`` was passed then only 56 | IDs of resources which have metadata are returned. 57 | """ 58 | from ckan.plugins import toolkit 59 | if len(self.args) < 1: 60 | _error('Missing argument. Specify one or more resource IDs ' 61 | + 'or "all".') 62 | if len(self.args) == 1 and self.args[0].lower() == 'all': 63 | if only_with_metadata: 64 | return sorted(toolkit.get_action('extractor_list')({}, {})) 65 | else: 66 | from ckan.model import Resource 67 | return sorted(r.id for r in Resource.active()) 68 | else: 69 | return self.args[:] 70 | 71 | 72 | class DeleteCommand(ExtractorCommand): 73 | """ 74 | Delete metadata 75 | 76 | delete (all | ID [ID [...]]) 77 | """ 78 | max_args = None 79 | min_args = 1 80 | usage = __doc__ 81 | summary = __doc__.strip().split('\n')[0] 82 | 83 | def command(self): 84 | self._load_config() 85 | from ckan.plugins import toolkit 86 | delete = toolkit.get_action('extractor_delete') 87 | for id in self._get_ids(True): 88 | print(id) 89 | delete({}, {'id': id}) 90 | 91 | 92 | class ExtractCommand(ExtractorCommand): 93 | """ 94 | Extract metadata 95 | 96 | extract [--force] (all | ID [ID [...]]) 97 | 98 | If --force is given then extraction is performed even if the 99 | the resource hasn't changed or another extraction task for the 100 | resource is already in progress. 101 | 102 | Note that a background jobs worker must be running, this command 103 | only schedules the necessary background tasks. 104 | """ 105 | max_args = None 106 | min_args = None 107 | usage = __doc__ 108 | summary = __doc__.strip().split('\n')[0] 109 | 110 | def __init__(self, name): 111 | super(ExtractCommand, self).__init__(name) 112 | self.parser.add_option('--force', default=False, 113 | help='Force extraction', 114 | action='store_true') 115 | 116 | def command(self): 117 | self._load_config() 118 | from ckan.plugins import toolkit 119 | extract = toolkit.get_action('extractor_extract') 120 | for id in self._get_ids(): 121 | print(id + ': ', end='') 122 | result = extract({}, {'id': id, 'force': self.options.force}) 123 | status = result['status'] 124 | if result['task_id']: 125 | status += ' (task {})'.format(result['task_id']) 126 | print(status) 127 | 128 | 129 | class InitCommand(ExtractorCommand): 130 | """ 131 | Initialize database tables. 132 | """ 133 | max_args = 0 134 | min_args = 0 135 | usage = __doc__ 136 | summary = __doc__.strip().split('\n')[0] 137 | 138 | def command(self): 139 | self._load_config() 140 | from .model import create_tables 141 | create_tables() 142 | 143 | 144 | class ListCommand(ExtractorCommand): 145 | """ 146 | List resources with metadata 147 | """ 148 | max_args = 0 149 | min_args = 0 150 | usage = __doc__ 151 | summary = __doc__.strip().split('\n')[0] 152 | 153 | def command(self): 154 | self._load_config() 155 | from ckan.plugins import toolkit 156 | result = toolkit.get_action('extractor_list')({}, {}) 157 | print('\n'.join(sorted(result))) 158 | 159 | 160 | class ShowCommand(ExtractorCommand): 161 | """ 162 | Show metadata 163 | 164 | show (all | ID [ID [...]]) 165 | """ 166 | max_args = None 167 | min_args = 1 168 | usage = __doc__ 169 | summary = __doc__.strip().split('\n')[0] 170 | 171 | def command(self): 172 | self._load_config() 173 | from ckan.plugins import toolkit 174 | from ckan.logic import NotFound 175 | show = toolkit.get_action('extractor_show') 176 | ids = self._get_ids(True) 177 | for i, id in enumerate(ids): 178 | try: 179 | result = show({}, {'id': id}) 180 | except NotFound as e: 181 | print(e) 182 | continue 183 | print('{}:'.format(id)) 184 | for key in sorted(result): 185 | if key in ('resource_id', 'meta'): 186 | continue 187 | print(' {}: {!r}'.format(key, result[key])) 188 | print(' meta:') 189 | meta = result['meta'] 190 | for key in sorted(meta): 191 | print(' {}: {!r}'.format(key, _compress(meta[key]))) 192 | if i < len(ids) - 1: 193 | print('') 194 | 195 | -------------------------------------------------------------------------------- /ckanext/extractor/plugin.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import collections 23 | import json 24 | import logging 25 | 26 | from ckan import plugins 27 | from ckan.logic import NotFound 28 | from ckan.plugins import toolkit 29 | 30 | from .config import is_field_indexed, is_format_indexed 31 | from .logic import action, auth 32 | from . import model 33 | 34 | 35 | log = logging.getLogger(__name__) 36 | get_action = toolkit.get_action 37 | 38 | 39 | # Template for the Solr field names 40 | SOLR_FIELD = 'ckanext-extractor_{id}_{key}' 41 | 42 | 43 | def _is_resource(obj): 44 | """ 45 | Check if a dict describes a resource. 46 | 47 | This is a very simple, duck-typing style test that only checks 48 | whether the dict contains an ``package_id`` entry. 49 | """ 50 | return 'package_id' in obj 51 | 52 | 53 | class ExtractorPlugin(plugins.SingletonPlugin): 54 | plugins.implements(plugins.IConfigurer) 55 | plugins.implements(plugins.IPackageController, inherit=True) 56 | plugins.implements(plugins.IResourceController, inherit=True) 57 | plugins.implements(plugins.IActions) 58 | plugins.implements(plugins.IAuthFunctions) 59 | plugins.implements(plugins.IConfigurable) 60 | 61 | # 62 | # IConfigurer 63 | # 64 | 65 | def update_config(self, config): 66 | toolkit.add_template_directory(config, 'templates') 67 | toolkit.add_public_directory(config, 'public') 68 | toolkit.add_resource('fanstatic', 'extractor') 69 | 70 | # 71 | # IConfigurable 72 | # 73 | 74 | def configure(self, config): 75 | model.setup() 76 | 77 | # 78 | # IPackageController / IResourceController 79 | # 80 | 81 | def after_create(self, context, obj): 82 | if _is_resource(obj): 83 | ctx = dict(context, ignore_auth=True) 84 | get_action('extractor_extract')(ctx, obj) 85 | 86 | def after_update(self, context, obj): 87 | if _is_resource(obj): 88 | ctx = dict(context, ignore_auth=True) 89 | get_action('extractor_extract')(ctx, obj) 90 | else: 91 | # If a previously private package became public then we need to 92 | # extract all its resources. However, we don't have the old 93 | # package dict (there's no `before_update` in IPackageController), 94 | # so we simply re-extract all resources if for any updated public 95 | # dataset. If the resources didn't change then this won't add much 96 | # overhead. 97 | # 98 | # If, on the other hand, the package is private then we prune all 99 | # the metadata for all its resources to avoid leaking information 100 | # via the `extractor_list` and `extractor_show` action functions. 101 | if obj.get('private', True): 102 | for res_dict in obj.get('resources', []): 103 | try: 104 | ctx = dict(context, ignore_auth=True) 105 | get_action('extractor_delete')(ctx, res_dict) 106 | except toolkit.ObjectNotFound: 107 | pass 108 | else: 109 | for res_dict in obj.get('resources', []): 110 | ctx = dict(context, ignore_auth=True) 111 | get_action('extractor_extract')(ctx, res_dict) 112 | 113 | # 114 | # IResourceController 115 | # 116 | 117 | def before_delete(self, context, res_dict, res_dicts): 118 | ctx = dict(context, ignore_auth=True) 119 | try: 120 | get_action('extractor_delete')(ctx, res_dict) 121 | except NotFound: 122 | # Resource didn't have any metadata 123 | pass 124 | 125 | # 126 | # IPackageController 127 | # 128 | 129 | def before_index(self, pkg_dict): 130 | data_dict = json.loads(pkg_dict['data_dict']) 131 | for resource in data_dict['resources']: 132 | if not is_format_indexed(resource['format']): 133 | continue 134 | try: 135 | metadata = get_action('extractor_show')({}, resource) 136 | except NotFound: 137 | continue 138 | for key, value in metadata['meta'].iteritems(): 139 | if is_field_indexed(key): 140 | field = SOLR_FIELD.format(id=resource['id'], key=key) 141 | pkg_dict[field] = value 142 | return pkg_dict 143 | 144 | # 145 | # IActions 146 | # 147 | 148 | def get_actions(self): 149 | return { 150 | 'extractor_delete': action.extractor_delete, 151 | 'extractor_extract': action.extractor_extract, 152 | 'extractor_list': action.extractor_list, 153 | 'extractor_show': action.extractor_show, 154 | } 155 | 156 | # 157 | # IAuthFunctions 158 | # 159 | 160 | def get_auth_functions(self): 161 | return { 162 | 'extractor_delete': auth.extractor_delete, 163 | 'extractor_extract': auth.extractor_extract, 164 | 'extractor_list': auth.extractor_list, 165 | 'extractor_show': auth.extractor_show, 166 | } 167 | 168 | -------------------------------------------------------------------------------- /ckanext/extractor/public/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stadt-karlsruhe/ckanext-extractor/1d49dd615493db21ce0004b40f2ae0bb68f3869f/ckanext/extractor/public/.gitignore -------------------------------------------------------------------------------- /ckanext/extractor/tasks.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import datetime 23 | import logging 24 | import tempfile 25 | 26 | from sqlalchemy.orm.exc import NoResultFound 27 | from requests.exceptions import RequestException 28 | 29 | from ckan.lib import search 30 | from ckan.plugins import PluginImplementations, toolkit 31 | 32 | from .config import is_field_indexed, load_config 33 | from .model import ResourceMetadata, ResourceMetadatum 34 | from .lib import download_and_extract 35 | from .interfaces import IExtractorPostprocessor 36 | 37 | 38 | log = logging.getLogger(__name__) 39 | 40 | 41 | def extract(ini_path, res_dict): 42 | """ 43 | Download resource, extract and store metadata. 44 | 45 | The extracted metadata is stored in the database. 46 | 47 | Note that this task does check whether the resource exists in the 48 | database, whether the resource's format is indexed or whether there 49 | is an existing task working on the resource's metadata. This is the 50 | responsibility of the caller. 51 | 52 | The task does check which metadata fields are configured to be 53 | indexed and only stores those in the database. 54 | 55 | Any previously stored metadata for the resource is cleared. 56 | """ 57 | load_config(ini_path) 58 | 59 | # Get package data before doing any hard work so that we can fail 60 | # early if the package is private. 61 | try: 62 | toolkit.get_action('package_show')({'validate': False}, 63 | {'id': res_dict['package_id']}) 64 | except toolkit.NotAuthorized: 65 | log.debug(('Not extracting resource {} since it belongs to the ' + 66 | 'private dataset {}.').format(res_dict['id'], 67 | res_dict['package_id'])) 68 | return 69 | 70 | try: 71 | metadata = ResourceMetadata.one(resource_id=res_dict['id']) 72 | except NoResultFound: 73 | metadata = ResourceMetadata.create(resource_id=res_dict['id']) 74 | try: 75 | metadata.last_url = res_dict['url'] 76 | metadata.last_format = res_dict['format'] 77 | metadata.last_extracted = datetime.datetime.now() 78 | metadata.meta.clear() 79 | extracted = download_and_extract(res_dict['url']) 80 | for plugin in PluginImplementations(IExtractorPostprocessor): 81 | plugin.extractor_after_extract(res_dict, extracted) 82 | for key, value in extracted.iteritems(): 83 | if not is_field_indexed(key): 84 | continue 85 | 86 | # Some documents contain multiple values for the same field. This 87 | # is not supported in our database model, hence we collapse these 88 | # into a single value. 89 | if isinstance(value, list): 90 | log.debug('Collapsing multiple values for metadata field ' + 91 | '"{}" in resource {} into a single value.'.format(key, 92 | res_dict['id'])) 93 | value = ', '.join(value) 94 | 95 | metadata.meta[key] = value 96 | except RequestException as e: 97 | log.warn('Failed to download resource data from "{}": {}'.format( 98 | res_dict['url'], e.message)) 99 | finally: 100 | metadata.task_id = None 101 | metadata.save() 102 | 103 | for plugin in PluginImplementations(IExtractorPostprocessor): 104 | plugin.extractor_after_save(res_dict, metadata.as_dict()) 105 | 106 | # We need to update the search index for the package here. Note that 107 | # we cannot rely on the automatic update that happens when a resource 108 | # is changed, since our extraction task runs asynchronously and may 109 | # be finished only when the automatic index update has already run. 110 | search.rebuild(package_id=res_dict['package_id']) 111 | 112 | for plugin in PluginImplementations(IExtractorPostprocessor): 113 | plugin.extractor_after_index(res_dict, metadata.as_dict()) 114 | 115 | -------------------------------------------------------------------------------- /ckanext/extractor/templates/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stadt-karlsruhe/ckanext-extractor/1d49dd615493db21ce0004b40f2ae0bb68f3869f/ckanext/extractor/templates/.gitignore -------------------------------------------------------------------------------- /ckanext/extractor/tests/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /ckanext/extractor/tests/helpers.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import contextlib 23 | import datetime 24 | import os.path 25 | import re 26 | from SimpleHTTPServer import SimpleHTTPRequestHandler 27 | from SocketServer import TCPServer 28 | from threading import Thread 29 | import time 30 | 31 | import mock 32 | from nose.tools import assert_raises, assert_true, assert_false 33 | from sqlalchemy.orm.exc import NoResultFound 34 | 35 | from ckan.logic import NotAuthorized, ValidationError 36 | from ckan.tests.helpers import call_action 37 | 38 | from ..model import ResourceMetadata, ResourceMetadatum 39 | 40 | 41 | def assert_equal(actual, expected, msg=''): 42 | """ 43 | Assert that two values are equal. 44 | 45 | Like ``nose.tools.assert_equal`` but upon mismatch also displays the 46 | expected and actual values even if a message is given. 47 | """ 48 | if actual == expected: 49 | return 50 | diff_msg = 'Got {!r} but expected {!r}.'.format(actual, expected) 51 | raise AssertionError((msg + ' ' + diff_msg).strip()) 52 | 53 | 54 | def fake_process(res_dict): 55 | """ 56 | Mark resource metadata as processed by removing its task ID. 57 | """ 58 | metadata = get_metadata(res_dict) 59 | metadata.task_id = None 60 | metadata.last_url = res_dict['url'] 61 | metadata.last_format = res_dict['format'] 62 | metadata.save() 63 | 64 | 65 | def assert_no_metadata(res_dict): 66 | """ 67 | Assert that no metadata are stored for a resource. 68 | """ 69 | if ResourceMetadata.filter_by(resource_id=res_dict['id']).count() > 0: 70 | raise AssertionError(('Found unexcepted metadata for resource ' 71 | + '"{id}".').format(id=res_dict['id'])) 72 | if ResourceMetadatum.filter_by(resource_id=res_dict['id']).count() > 0: 73 | raise AssertionError(('Found unexcepted metadatum for resource ' 74 | + '"{id}".').format(id=res_dict['id'])) 75 | 76 | 77 | def assert_metadata(res_dict): 78 | """ 79 | Assert that metadata is stored for a resource. 80 | """ 81 | try: 82 | get_metadata(res_dict) 83 | except NoResultFound: 84 | raise AssertionError('No metadata found for resource "{id}".'.format( 85 | id=res_dict['id'])) 86 | 87 | 88 | def get_metadata(res_dict): 89 | """ 90 | Shortcut to get metadata for a resource. 91 | """ 92 | return ResourceMetadata.one(resource_id=res_dict['id']) 93 | 94 | 95 | def call_action_with_auth(action, context=None, **kwargs): 96 | """ 97 | Call an action with authorization checks. 98 | 99 | Like ``ckan.tests.helpers.call_action``, but authorization are 100 | not bypassed. 101 | """ 102 | if context is None: 103 | context = {} 104 | context['ignore_auth'] = False 105 | return call_action(action, context, **kwargs) 106 | 107 | 108 | def assert_authorized(user_dict, action, msg, **kwargs): 109 | """ 110 | Assert that a user is authorized to perform an action. 111 | 112 | Raises an ``AssertionError`` if access was denied. 113 | """ 114 | context = {'user': user_dict['name']} 115 | try: 116 | call_action_with_auth(action, context, **kwargs) 117 | except NotAuthorized: 118 | raise AssertionError(msg) 119 | 120 | 121 | def assert_not_authorized(user_dict, action, msg, **kwargs): 122 | """ 123 | Assert that a user is not authorized to perform an action. 124 | 125 | Raises an ``AssertionError`` if access was granted. 126 | """ 127 | context = {'user': user_dict['name']} 128 | try: 129 | call_action_with_auth(action, context, **kwargs) 130 | except NotAuthorized: 131 | return 132 | raise AssertionError(msg) 133 | 134 | 135 | def assert_anonymous_access(action, **kwargs): 136 | """ 137 | Assert that an action can be called anonymously. 138 | """ 139 | context = {'user': ''} 140 | try: 141 | call_action_with_auth(action, context, **kwargs) 142 | except NotAuthorized: 143 | raise AssertionError('"{}" cannot be called anonymously.'.format( 144 | action)) 145 | 146 | 147 | def assert_no_anonymous_access(action, **kwargs): 148 | """ 149 | Assert that an action cannot be called anonymously. 150 | """ 151 | context = {'user': ''} 152 | try: 153 | call_action_with_auth(action, context, **kwargs) 154 | except NotAuthorized: 155 | return 156 | raise AssertionError('"{}" can be called anonymously.'.format(action)) 157 | 158 | 159 | def assert_validation_fails(action, msg=None, **kwargs): 160 | """ 161 | Assert that an action call doesn't validate. 162 | """ 163 | try: 164 | call_action(action, **kwargs) 165 | except ValidationError: 166 | return 167 | if msg is None: 168 | msg = ('Validation succeeded unexpectedly for action "{action}" with ' 169 | + 'input {input!r}.').format(action=action, input=kwargs) 170 | raise AssertionError(msg) 171 | 172 | 173 | class AddressReuseServer(TCPServer): 174 | allow_reuse_address = True 175 | 176 | 177 | class HTTPRequestHandler(SimpleHTTPRequestHandler): 178 | """ 179 | Serves files from a given directory instead of current directory. 180 | """ 181 | def __init__(self, dir, *args, **kwargs): 182 | self.dir = os.path.abspath(dir) 183 | SimpleHTTPRequestHandler.__init__(self, *args, **kwargs) 184 | 185 | def translate_path(self, path): 186 | return os.path.join(self.dir, path.lstrip('/')) 187 | 188 | 189 | class SimpleServer(Thread): 190 | """ 191 | HTTP server that serves a directory in a separate thread. 192 | 193 | If ``dir`` is not given the current directory is used. 194 | """ 195 | def __init__(self, dir=None, port=8000): 196 | super(SimpleServer, self).__init__() 197 | if dir is None: 198 | dir = os.getcwd() 199 | 200 | def factory(*args, **kwargs): 201 | return HTTPRequestHandler(dir, *args, **kwargs) 202 | 203 | self.httpd = AddressReuseServer(("", port), factory) 204 | 205 | def run(self): 206 | try: 207 | self.httpd.serve_forever() 208 | finally: 209 | self.httpd.server_close() 210 | 211 | def stop(self): 212 | self.httpd.shutdown() 213 | 214 | 215 | def assert_time_span(start, stop=None, min=None, max=None): 216 | """ 217 | Assert validity of a time span. 218 | 219 | ``start`` and ``stop`` are ``datetime.datetime`` instances. If 220 | ``stop`` is not given the current date and time is used. 221 | 222 | The length of the time span between ``start`` and ``stopped`` is 223 | computed (in seconds). If ``min`` (``max``) is given and larger 224 | (smaller) than the time span then an ``AssertionError`` is raised. 225 | """ 226 | if stop is None: 227 | stop = datetime.datetime.now() 228 | span = (stop - start).total_seconds() 229 | if (min is not None) and (min > span): 230 | msg = 'Time span {span}s is too small (must be >={min}s).'.format( 231 | span=span, min=min) 232 | raise AssertionError(msg) 233 | if (max is not None) and (max < span): 234 | msg = 'Time span {span}s is too large (must be <={max}s).'.format( 235 | span=span, max=max) 236 | raise AssertionError(max) 237 | 238 | 239 | def is_package_found(query, pkg_id): 240 | """ 241 | Check if a package is found via a query. 242 | """ 243 | result = call_action('package_search', q=query) 244 | return any(pkg['id'] == pkg_id for pkg in result['results']) 245 | 246 | 247 | def assert_package_found(query, id, msg=None): 248 | """ 249 | Assert that a package is found via a query. 250 | """ 251 | assert_true(is_package_found(query, id), msg) 252 | 253 | 254 | def assert_package_not_found(query, id, msg=None): 255 | """ 256 | Assert that a package is not found via a query. 257 | """ 258 | assert_false(is_package_found(query, id), msg) 259 | 260 | 261 | try: 262 | from ckan.tests.helpers import recorded_logs 263 | except ImportError: 264 | import collections 265 | import logging 266 | 267 | # Copied from CKAN 2.7 268 | @contextlib.contextmanager 269 | def recorded_logs(logger=None, level=logging.DEBUG, 270 | override_disabled=True, override_global_level=True): 271 | u''' 272 | Context manager for recording log messages. 273 | 274 | :param logger: The logger to record messages from. Can either be a 275 | :py:class:`logging.Logger` instance or a string with the 276 | logger's name. Defaults to the root logger. 277 | 278 | :param int level: Temporary log level for the target logger while 279 | the context manager is active. Pass ``None`` if you don't want 280 | the level to be changed. The level is automatically reset to its 281 | original value when the context manager is left. 282 | 283 | :param bool override_disabled: A logger can be disabled by setting 284 | its ``disabled`` attribute. By default, this context manager 285 | sets that attribute to ``False`` at the beginning of its 286 | execution and resets it when the context manager is left. Set 287 | ``override_disabled`` to ``False`` to keep the current value 288 | of the attribute. 289 | 290 | :param bool override_global_level: The ``logging.disable`` function 291 | allows one to install a global minimum log level that takes 292 | precedence over a logger's own level. By default, this context 293 | manager makes sure that the global limit is at most ``level``, 294 | and reduces it if necessary during its execution. Set 295 | ``override_global_level`` to ``False`` to keep the global limit. 296 | 297 | :returns: A recording log handler that listens to ``logger`` during 298 | the execution of the context manager. 299 | :rtype: :py:class:`RecordingLogHandler` 300 | 301 | Example:: 302 | 303 | import logging 304 | 305 | logger = logging.getLogger(__name__) 306 | 307 | with recorded_logs(logger) as logs: 308 | logger.info(u'Hello, world!') 309 | 310 | logs.assert_log(u'info', u'world') 311 | ''' 312 | if logger is None: 313 | logger = logging.getLogger() 314 | elif not isinstance(logger, logging.Logger): 315 | logger = logging.getLogger(logger) 316 | handler = RecordingLogHandler() 317 | old_level = logger.level 318 | manager_level = logger.manager.disable 319 | disabled = logger.disabled 320 | logger.addHandler(handler) 321 | try: 322 | if level is not None: 323 | logger.setLevel(level) 324 | if override_disabled: 325 | logger.disabled = False 326 | if override_global_level: 327 | if (level is None) and (manager_level > old_level): 328 | logger.manager.disable = old_level 329 | elif (level is not None) and (manager_level > level): 330 | logger.manager.disable = level 331 | yield handler 332 | finally: 333 | logger.handlers.remove(handler) 334 | logger.setLevel(old_level) 335 | logger.disabled = disabled 336 | logger.manager.disable = manager_level 337 | 338 | 339 | # Copied from CKAN 2.7 340 | class RecordingLogHandler(logging.Handler): 341 | u''' 342 | Log handler that records log messages for later inspection. 343 | 344 | You can inspect the recorded messages via the ``messages`` attribute 345 | (a dict that maps log levels to lists of messages) or by using 346 | ``assert_log``. 347 | 348 | This class is rarely useful on its own, instead use 349 | :py:func:`recorded_logs` to temporarily record log messages. 350 | ''' 351 | def __init__(self, *args, **kwargs): 352 | super(RecordingLogHandler, self).__init__(*args, **kwargs) 353 | self.clear() 354 | 355 | def emit(self, record): 356 | self.messages[record.levelname.lower()].append(record.getMessage()) 357 | 358 | def assert_log(self, level, pattern, msg=None): 359 | u''' 360 | Assert that a certain message has been logged. 361 | 362 | :param string pattern: A regex which the message has to match. 363 | The match is done using ``re.search``. 364 | 365 | :param string level: The message level (``'debug'``, ...). 366 | 367 | :param string msg: Optional failure message in case the expected 368 | log message was not logged. 369 | 370 | :raises AssertionError: If the expected message was not logged. 371 | ''' 372 | compiled_pattern = re.compile(pattern) 373 | for log_msg in self.messages[level]: 374 | if compiled_pattern.search(log_msg): 375 | return 376 | if not msg: 377 | if self.messages[level]: 378 | lines = u'\n '.join(self.messages[level]) 379 | msg = (u'Pattern "{}" was not found in the log messages for ' 380 | + u'level "{}":\n {}').format(pattern, level, lines) 381 | else: 382 | msg = (u'Pattern "{}" was not found in the log messages for ' 383 | + u'level "{}" (no messages were recorded for that ' 384 | + u'level).').format(pattern, level) 385 | raise AssertionError(msg) 386 | 387 | def clear(self): 388 | u''' 389 | Clear all captured log messages. 390 | ''' 391 | self.messages = collections.defaultdict(list) 392 | 393 | -------------------------------------------------------------------------------- /ckanext/extractor/tests/logic/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stadt-karlsruhe/ckanext-extractor/1d49dd615493db21ce0004b40f2ae0bb68f3869f/ckanext/extractor/tests/logic/__init__.py -------------------------------------------------------------------------------- /ckanext/extractor/tests/logic/test_action.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import uuid 23 | 24 | import mock 25 | from nose.tools import assert_false, assert_raises, assert_true 26 | 27 | from ckan.logic import NotFound 28 | from ckan.model import Resource 29 | from ckan.tests.helpers import call_action, FunctionalTestBase 30 | from ckan.tests import factories 31 | 32 | from ...model import ResourceMetadata 33 | from ..helpers import (assert_anonymous_access, assert_authorized, assert_equal, 34 | assert_no_anonymous_access, assert_no_metadata, 35 | assert_not_authorized, get_metadata, fake_process, 36 | assert_validation_fails) 37 | 38 | 39 | def enqueue_job(*args, **kwargs): 40 | return mock.Mock(id=str(uuid.uuid4())) 41 | 42 | 43 | class TestExtractorList(FunctionalTestBase): 44 | 45 | def test_extractor_list_empty(self): 46 | """ 47 | extractor_list when no metadata exist. 48 | """ 49 | assert_equal(call_action('extractor_list'), []) 50 | 51 | def test_extractor_list_inprogress(self): 52 | """ 53 | extractor_list does not list metadata that is in progress. 54 | """ 55 | factories.Resource(format='pdf') 56 | assert_equal(call_action('extractor_list'), []) 57 | 58 | def test_extractor_list_some(self): 59 | """ 60 | extractor_list when some metadata exist. 61 | """ 62 | res_dict = factories.Resource(format='pdf') 63 | fake_process(res_dict) 64 | assert_equal(call_action('extractor_list'), [res_dict['id']]) 65 | 66 | def test_extractor_list_auth(self): 67 | """ 68 | Authorization for extractor_show. 69 | """ 70 | assert_authorized(factories.User(), 'extractor_list', 71 | "Normal user wasn't allowed to extractor_list") 72 | assert_anonymous_access('extractor_list') 73 | 74 | 75 | @mock.patch('ckanext.extractor.logic.action.enqueue_job', 76 | side_effect=enqueue_job) 77 | class TestExtractorExtract(FunctionalTestBase): 78 | 79 | def test_extractor_extract_new_indexed(self, enqueue_job): 80 | """ 81 | extractor_extract for a new resource with indexed format. 82 | """ 83 | res_dict = factories.Resource(format='pdf') 84 | get_metadata(res_dict).delete().commit() 85 | enqueue_job.reset_mock() 86 | result = call_action('extractor_extract', id=res_dict['id']) 87 | assert_equal(result['status'], 'new', 'Wrong state') 88 | assert_false(result['task_id'] is None, 'Missing task ID') 89 | assert_equal(result['task_id'], get_metadata(res_dict).task_id, 90 | 'Task IDs differ.') 91 | assert_equal(enqueue_job.call_count, 1, 92 | 'Wrong number of extraction tasks.') 93 | 94 | def test_extractor_extract_new_ignored(self, enqueue_job): 95 | """ 96 | extractor_extract for a new resource with ignored format. 97 | """ 98 | res_dict = factories.Resource(format='foo') 99 | result = call_action('extractor_extract', id=res_dict['id']) 100 | assert_equal(result['status'], 'ignored', 'Wrong state') 101 | assert_true(result['task_id'] is None, 'Unexpected task ID') 102 | assert_equal(enqueue_job.call_count, 0, 103 | 'Wrong number of extraction tasks.') 104 | 105 | def test_extractor_extract_unchanged(self, enqueue_job): 106 | """ 107 | extractor_extract for a resource with unchanged format and URL. 108 | """ 109 | res_dict = factories.Resource(format='pdf') 110 | enqueue_job.reset_mock() 111 | fake_process(res_dict) 112 | result = call_action('extractor_extract', id=res_dict['id']) 113 | assert_equal(result['status'], 'unchanged', 'Wrong state') 114 | assert_true(result['task_id'] is None, 'Unexpected task ID') 115 | assert_equal(result['task_id'], get_metadata(res_dict).task_id, 116 | 'Task IDs differ.') 117 | assert_equal(enqueue_job.call_count, 0, 118 | 'Wrong number of extraction tasks.') 119 | 120 | def test_extractor_extract_update_indexed_format(self, enqueue_job): 121 | """ 122 | extractor_extract for a resource with updated, indexed format. 123 | """ 124 | res_dict = factories.Resource(format='pdf') 125 | enqueue_job.reset_mock() 126 | fake_process(res_dict) 127 | 128 | resource = Resource.get(res_dict['id']) 129 | resource.format = 'doc' 130 | resource.save() 131 | 132 | result = call_action('extractor_extract', id=res_dict['id']) 133 | assert_equal(result['status'], 'update', 'Wrong state') 134 | assert_false(result['task_id'] is None, 'Missing task ID') 135 | assert_equal(result['task_id'], get_metadata(res_dict).task_id, 136 | 'Task IDs differ.') 137 | assert_equal(enqueue_job.call_count, 1, 138 | 'Wrong number of extraction tasks.') 139 | 140 | def test_extractor_extract_update_ignored_format(self, enqueue_job): 141 | """ 142 | extractor_extract for a resource with updated, ignored format. 143 | """ 144 | res_dict = factories.Resource(format='pdf') 145 | enqueue_job.reset_mock() 146 | fake_process(res_dict) 147 | 148 | resource = Resource.get(res_dict['id']) 149 | resource.format = 'foo' 150 | resource.save() 151 | 152 | result = call_action('extractor_extract', id=res_dict['id']) 153 | assert_equal(result['status'], 'ignored', 'Wrong state') 154 | assert_true(result['task_id'] is None, 'Unexpected task ID') 155 | assert_equal(enqueue_job.call_count, 0, 156 | 'Wrong number of extraction tasks.') 157 | assert_no_metadata(res_dict) 158 | 159 | def test_extractor_extract_inprogress(self, enqueue_job): 160 | """ 161 | extractor_extract for a resource that's already being extracted. 162 | """ 163 | res_dict = factories.Resource(format='pdf') 164 | enqueue_job.reset_mock() 165 | old_task_id = get_metadata(res_dict).task_id 166 | result = call_action('extractor_extract', id=res_dict['id']) 167 | assert_equal(result['status'], 'inprogress', 'Wrong state') 168 | assert_equal(result['task_id'], old_task_id, 'Task IDs differ.') 169 | assert_equal(enqueue_job.call_count, 0, 170 | 'Wrong number of extraction tasks.') 171 | 172 | def test_extractor_extract_unexisting(self, enqueue_job): 173 | """ 174 | extractor_extract for a resource that does not exist. 175 | """ 176 | assert_raises( 177 | NotFound, lambda: call_action('extractor_extract', 178 | id='does-not-exist')) 179 | 180 | def test_extractor_extract_auth(self, enqueue_job): 181 | """ 182 | Authorization for extractor_extract. 183 | """ 184 | res_dict = factories.Resource(format='pdf') 185 | assert_not_authorized(factories.User(), 'extractor_extract', 186 | 'Normal user was allowed to extractor_extract', 187 | id=res_dict['id']) 188 | assert_no_anonymous_access('extractor_extract', id=res_dict['id']) 189 | assert_authorized(factories.Sysadmin(), 'extractor_extract', 190 | "Sysadmin wasn't allowed to extractor_extract", 191 | id=res_dict['id']) 192 | 193 | def test_extractor_extract_validation(self, enqueue_job): 194 | """ 195 | Input validation for extractor_extract. 196 | """ 197 | assert_validation_fails('extractor_extract', 'ID was not required.') 198 | assert_validation_fails('extractor_extract', 199 | 'Wrong force type was accepted', 200 | force='maybe') 201 | 202 | def test_extractor_extract_force_ignored_format(self, enqueue_job): 203 | """ 204 | Forcing extractor_extract with ignored format. 205 | """ 206 | res_dict = factories.Resource(format='foo') 207 | result = call_action('extractor_extract', id=res_dict['id'], 208 | force=True) 209 | assert_equal(result['status'], 'ignored', 'Wrong state') 210 | assert_true(result['task_id'] is None, 'Unexpected task ID') 211 | assert_equal(enqueue_job.call_count, 0, 212 | 'Wrong number of extraction tasks.') 213 | 214 | def test_extractor_extract_force_unchanged(self, enqueue_job): 215 | """ 216 | Forcing extractor_extract with unchanged resource. 217 | """ 218 | res_dict = factories.Resource(format='pdf') 219 | enqueue_job.reset_mock() 220 | fake_process(res_dict) 221 | result = call_action('extractor_extract', id=res_dict['id'], 222 | force=True) 223 | assert_equal(result['status'], 'unchanged', 'Wrong state') 224 | assert_false(result['task_id'] is None, 'Missing task ID') 225 | assert_equal(result['task_id'], get_metadata(res_dict).task_id, 226 | 'Task IDs differ.') 227 | assert_equal(enqueue_job.call_count, 1, 228 | 'Wrong number of extraction tasks.') 229 | 230 | def test_extractor_extract_force_inprogress(self, enqueue_job): 231 | """ 232 | Forcing extractor_extract with existing task. 233 | """ 234 | res_dict = factories.Resource(format='pdf') 235 | enqueue_job.reset_mock() 236 | old_task_id = get_metadata(res_dict).task_id 237 | 238 | result = call_action('extractor_extract', id=res_dict['id'], 239 | force=True) 240 | assert_equal(result['status'], 'inprogress', 'Wrong state') 241 | assert_false(result['task_id'] is None, 'Missing task ID') 242 | assert_equal(result['task_id'], get_metadata(res_dict).task_id, 243 | 'Task IDs differ.') 244 | assert_false(result['task_id'] == old_task_id, 245 | 'Task ID was not updated.') 246 | assert_equal(enqueue_job.call_count, 1, 247 | 'Wrong number of extraction tasks.') 248 | 249 | 250 | @mock.patch('ckanext.extractor.logic.action.enqueue_job', 251 | return_value=mock.Mock(id='test-id')) 252 | class TestExtractorShow(FunctionalTestBase): 253 | 254 | def test_extractor_show_unexisting(self, enqueue_job): 255 | """ 256 | extractor_show for a resource that does not exist. 257 | """ 258 | assert_raises( 259 | NotFound, lambda: call_action('extractor_show', 260 | id='does-not-exist')) 261 | 262 | def test_extractor_show_inprogress(self, enqueue_job): 263 | """ 264 | extractor_show for metadata that is in progress. 265 | """ 266 | res_dict = factories.Resource(format='pdf') 267 | result = call_action('extractor_show', id=res_dict['id']) 268 | assert_equal(result['task_id'], 'test-id', 'Wrong task ID.') 269 | 270 | def test_extractor_show_normal(self, enqueue_job): 271 | """ 272 | extractor_show for normal metadata. 273 | """ 274 | res_dict = factories.Resource(format='pdf') 275 | fake_process(res_dict) 276 | metadata = get_metadata(res_dict) 277 | metadata.meta['fulltext'] = 'foobar' 278 | metadata.meta['author'] = 'John Doe' 279 | metadata.save() 280 | result = call_action('extractor_show', id=res_dict['id']) 281 | assert_equal(result['meta']['fulltext'], 'foobar', 'Wrong fulltext.') 282 | assert_equal(result['meta']['author'], 'John Doe', 'Wrong author.') 283 | assert_equal(result['resource_id'], res_dict['id'], 284 | 'Wrong resource ID.') 285 | assert_true(result['task_id'] is None, 'Unexpected task ID.') 286 | 287 | def test_extractor_show_auth(self, enqueue_job): 288 | """ 289 | Authorization for extractor_show. 290 | """ 291 | res_dict = factories.Resource(format='pdf') 292 | assert_authorized(factories.User(), 'extractor_show', 293 | "Normal user wasn't allowed to extractor_show", 294 | id=res_dict['id']) 295 | assert_anonymous_access('extractor_show', id=res_dict['id']) 296 | 297 | def test_extractor_show_validation(self, enqueue_job): 298 | """ 299 | Input validation for extractor_show. 300 | """ 301 | assert_validation_fails('extractor_show', 302 | 'ID was not required.') 303 | 304 | 305 | @mock.patch('ckanext.extractor.logic.action.enqueue_job', 306 | side_effect=enqueue_job) 307 | class TestExtractorDelete(FunctionalTestBase): 308 | 309 | def test_extractor_delete_unexisting(self, enqueue_job): 310 | """ 311 | extractor_delete for a resource that does not exist. 312 | """ 313 | assert_raises( 314 | NotFound, lambda: call_action('extractor_delete', 315 | id='does-not-exist')) 316 | 317 | def test_extractor_delete_normal(self, enqueue_job): 318 | """ 319 | extractor_delete for a normal resource. 320 | """ 321 | res_dict = factories.Resource(format='pdf') 322 | fake_process(res_dict) 323 | call_action('extractor_delete', id=res_dict['id']) 324 | assert_no_metadata(res_dict) 325 | 326 | def test_extractor_delete_auth(self, enqueue_job): 327 | """ 328 | Authorization for extractor_delete. 329 | """ 330 | res_dict = factories.Resource(format='pdf') 331 | assert_not_authorized(factories.User(), 'extractor_delete', 332 | 'Normal user was allowed to extractor_delete', 333 | id=res_dict['id']) 334 | assert_no_anonymous_access('extractor_delete', id=res_dict['id']) 335 | assert_authorized(factories.Sysadmin(), 'extractor_delete', 336 | "Sysadmin wasn't allowed to extractor_delete", 337 | id=res_dict['id']) 338 | 339 | def test_extractor_delete_validation(self, enqueue_job): 340 | """ 341 | Input validation for extractor_delete. 342 | """ 343 | assert_validation_fails('extractor_delete', 'ID was not required.') 344 | 345 | -------------------------------------------------------------------------------- /ckanext/extractor/tests/test.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/stadt-karlsruhe/ckanext-extractor/1d49dd615493db21ce0004b40f2ae0bb68f3869f/ckanext/extractor/tests/test.pdf -------------------------------------------------------------------------------- /ckanext/extractor/tests/test_interfaces.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | from collections import defaultdict 23 | import functools 24 | import requests 25 | 26 | import mock 27 | from pylons import config 28 | 29 | from ckan.tests import factories, helpers 30 | from ckan.plugins import implements, SingletonPlugin, PluginImplementations 31 | 32 | from ..interfaces import IExtractorPostprocessor, IExtractorRequest 33 | from ..tasks import extract 34 | from .helpers import (assert_equal, get_metadata, assert_package_found, 35 | assert_package_not_found) 36 | from nose.tools import assert_true 37 | 38 | 39 | RES_DICT = { 40 | 'url': 'https://does-not-matter', 41 | 'format': 'PDF', 42 | } 43 | 44 | METADATA = { 45 | 'fulltext': 'foobar', 46 | 'author': 'john_doe', 47 | 'created': 'yesterday', 48 | } 49 | 50 | 51 | def filter_metadata(d): 52 | keys = config['ckanext.extractor.indexed_fields'].split() 53 | return dict((key, value) for key, value in d.iteritems() if key in keys) 54 | 55 | 56 | class MockPostprocessor(SingletonPlugin): 57 | 58 | def __init__(self): 59 | SingletonPlugin.__init__(self) 60 | self.called = 0 61 | 62 | 63 | class MockAfterExtractPostprocessor(MockPostprocessor): 64 | implements(IExtractorPostprocessor, inherit=True) 65 | 66 | def extractor_after_extract(self, res_dict, extracted): 67 | self.called += 1 68 | for key, value in RES_DICT.iteritems(): 69 | assert_equal(value, res_dict[key]) 70 | assert_equal(extracted, METADATA) 71 | extracted['fulltext'] = 'i can change this' 72 | 73 | 74 | class MockAfterSavePostprocessor(MockPostprocessor): 75 | implements(IExtractorPostprocessor, inherit=True) 76 | 77 | def extractor_after_save(self, res_dict, metadata_dict): 78 | self.called += 1 79 | for key, value in RES_DICT.iteritems(): 80 | assert_equal(value, res_dict[key]) 81 | assert_equal(metadata_dict['meta'], filter_metadata(METADATA)) 82 | assert_package_not_found(METADATA['fulltext'], res_dict['package_id']) 83 | 84 | 85 | class MockAfterIndexPostprocessor(MockPostprocessor): 86 | implements(IExtractorPostprocessor, inherit=True) 87 | 88 | def extractor_after_index(self, res_dict, metadata_dict): 89 | self.called += 1 90 | for key, value in RES_DICT.iteritems(): 91 | assert_equal(value, res_dict[key]) 92 | assert_equal(metadata_dict['meta'], filter_metadata(METADATA)) 93 | assert_package_found(METADATA['fulltext'], res_dict['package_id']) 94 | 95 | 96 | class MockBeforeRequest(MockPostprocessor): 97 | implements(IExtractorRequest, inherit=True) 98 | 99 | def extractor_before_request(self, request): 100 | self.called += 1 101 | assert_true(isinstance(request, requests.PreparedRequest)) 102 | request.url = 'http://test-url.example.com/file.pdf' 103 | return request 104 | 105 | 106 | MockPostprocessor().disable() 107 | MockAfterExtractPostprocessor().disable() 108 | MockAfterSavePostprocessor().disable() 109 | MockAfterIndexPostprocessor().disable() 110 | MockBeforeRequest().disable() 111 | 112 | 113 | def with_plugin(cls): 114 | ''' 115 | Activate a plugin during a function's execution. 116 | ''' 117 | def decorator(f): 118 | plugin = cls() 119 | @functools.wraps(f) 120 | def wrapped(*args, **kwargs): 121 | plugin.activate() 122 | try: 123 | plugin.enable() 124 | args = list(args) + [plugin] 125 | return f(*args, **kwargs) 126 | finally: 127 | plugin.disable() 128 | return wrapped 129 | return decorator 130 | 131 | 132 | @mock.patch('ckanext.extractor.tasks.load_config') 133 | @mock.patch('ckanext.extractor.tasks.download_and_extract', 134 | side_effect=lambda _: METADATA.copy()) 135 | class TestIExtractorPostprocessor(object): 136 | 137 | @with_plugin(MockAfterExtractPostprocessor) 138 | def test_after_extract(self, download_and_extract, load_config, plugin): 139 | res_dict = factories.Resource(**RES_DICT) 140 | get_metadata(res_dict).delete().commit() 141 | extract(config['__file__'], res_dict) 142 | assert_equal(plugin.called, 1) 143 | metadata = get_metadata(res_dict) 144 | assert_equal(metadata.meta['fulltext'], 'i can change this') 145 | 146 | @with_plugin(MockAfterSavePostprocessor) 147 | def test_after_save(self, download_and_extract, load_config, plugin): 148 | res_dict = factories.Resource(**RES_DICT) 149 | get_metadata(res_dict).delete().commit() 150 | extract(config['__file__'], res_dict) 151 | assert_equal(plugin.called, 1) 152 | 153 | @with_plugin(MockAfterIndexPostprocessor) 154 | def test_after_index(self, download_and_extract, load_config, plugin): 155 | res_dict = factories.Resource(**RES_DICT) 156 | get_metadata(res_dict).delete().commit() 157 | extract(config['__file__'], res_dict) 158 | assert_equal(plugin.called, 1) 159 | 160 | @mock.patch('ckanext.extractor.tasks.load_config') 161 | @mock.patch('ckanext.extractor.tasks.toolkit') 162 | @mock.patch('ckanext.extractor.tasks.search') 163 | @mock.patch('ckanext.extractor.lib.pysolr.Solr') 164 | @mock.patch('ckanext.extractor.lib.Session') 165 | class TestIExtractorRequest(object): 166 | 167 | def setup(self): 168 | self.res_dict = factories.Resource(**RES_DICT) 169 | 170 | @with_plugin(MockBeforeRequest) 171 | def test_before_request(self, session, solr, search, toolkit, load_config, plugin): 172 | extract(config['__file__'], self.res_dict) 173 | assert_equal(plugin.called, 1) 174 | assert_true(session.called) 175 | 176 | name, args, kwargs = session.mock_calls[1] 177 | assert_equal(name, '().send') 178 | assert_equal(args[0].url, 'http://test-url.example.com/file.pdf') 179 | -------------------------------------------------------------------------------- /ckanext/extractor/tests/test_lib.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import os.path 23 | 24 | from nose.tools import assert_true 25 | 26 | from ..lib import clean_metadatum, download_and_extract 27 | from .helpers import assert_equal, SimpleServer 28 | 29 | 30 | class TestDownloadAndExtract(object): 31 | 32 | PORT = 8000 33 | 34 | def __init__(self): 35 | self.server = SimpleServer(os.path.dirname(__file__), self.PORT) 36 | 37 | def setup(self): 38 | self.server.start() 39 | 40 | def teardown(self): 41 | self.server.stop() 42 | 43 | def test_download_and_extract(self): 44 | pdf_url = 'http://localhost:{port}/test.pdf'.format(port=self.PORT) 45 | metadata = download_and_extract(pdf_url) 46 | assert_true('Foobarium' in metadata['fulltext'], 'Incorrect fulltext.') 47 | assert_equal(metadata['content-type'], 'application/pdf') 48 | 49 | 50 | def test_clean_metadatum(): 51 | assert_equal(clean_metadatum('X_y', ['X_y']), ('x-y', 'X_y')) 52 | 53 | -------------------------------------------------------------------------------- /ckanext/extractor/tests/test_plugin.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import datetime 23 | 24 | import mock 25 | from sqlalchemy.orm.exc import NoResultFound 26 | 27 | from ckan.model import Package 28 | from ckan.lib.search import index_for 29 | from ckan.tests import factories, helpers 30 | 31 | from .helpers import (assert_equal, get_metadata, assert_metadata, 32 | assert_no_metadata, assert_package_found, 33 | assert_package_not_found) 34 | from ..model import ResourceMetadata 35 | from ..plugin import ExtractorPlugin 36 | 37 | 38 | RES_DICT = { 39 | 'url': 'does-not-matter', 40 | 'format': 'pdf', 41 | } 42 | 43 | METADATA = { 44 | 'fulltext': 'foobar', 45 | 'author': 'john_doe', 46 | 'created': 'yesterday', 47 | } 48 | 49 | 50 | def enqueue_job(name, args, **opts): 51 | res_dict = args[1] 52 | try: 53 | metadata = get_metadata(res_dict) 54 | except NoResultFound: 55 | metadata = ResourceMetadata.create(resource_id=res_dict['id']) 56 | metadata.last_format = res_dict['format'] 57 | metadata.last_url = res_dict['url'] 58 | metadata.last_extracted = datetime.datetime.now() 59 | metadata.task_id = None 60 | metadata.meta.update(METADATA) 61 | metadata.save() 62 | pkg_dict = helpers.call_action('package_show', id=res_dict['package_id']) 63 | index_for('package').update_dict(pkg_dict) 64 | return mock.Mock(id=None) 65 | 66 | 67 | @mock.patch('ckanext.extractor.logic.action.enqueue_job', 68 | side_effect=enqueue_job) 69 | class TestHooks(helpers.FunctionalTestBase): 70 | """ 71 | Test that extraction and indexing happens automatically. 72 | """ 73 | def test_extraction_upon_resource_creation(self, enqueue_job): 74 | """ 75 | Metadata is extracted and indexed after resource creation. 76 | """ 77 | factories.Resource(**RES_DICT) 78 | assert_equal(enqueue_job.call_count, 1, 79 | 'Wrong number of extraction tasks.') 80 | 81 | def test_extraction_upon_resource_update(self, enqueue_job): 82 | """ 83 | Metadata is extracted and indexed after resource update. 84 | """ 85 | res_dict = factories.Resource(**RES_DICT) 86 | enqueue_job.reset_mock() 87 | res_dict['format'] = 'doc' # Change format to trigger new extraction 88 | helpers.call_action('resource_update', **res_dict) 89 | assert_equal(enqueue_job.call_count, 1, 90 | 'Wrong number of extraction tasks.') 91 | 92 | def test_deletion_upon_resource_deletion(self, enqueue_job): 93 | """ 94 | Metadata is removed when a resource is deleted. 95 | """ 96 | res_dict = factories.Resource(**RES_DICT) 97 | assert_package_found(METADATA['fulltext'], res_dict['package_id'], 98 | 'Metadata not added to index.') 99 | assert_package_found(METADATA['author'], res_dict['package_id'], 100 | 'Metadata not added to index.') 101 | helpers.call_action('resource_delete', **res_dict) 102 | assert_package_not_found(METADATA['fulltext'], res_dict['package_id'], 103 | 'Metadata not removed from index.') 104 | assert_package_not_found(METADATA['author'], res_dict['package_id'], 105 | 'Metadata not removed from index.') 106 | assert_no_metadata(res_dict) 107 | 108 | def test_resource_deletion_with_no_metadata(self, enqueue_job): 109 | """ 110 | A resource that doesn't have metadata can be removed. 111 | """ 112 | res_dict = factories.Resource(url='foo', format='not-indexed') 113 | helpers.call_action('resource_delete', {'ignore_auth': True}, **res_dict) 114 | 115 | def test_extraction_after_public_dataset_update(self, enqueue_job): 116 | """ 117 | If a public dataset is updated then its resources are extracted. 118 | """ 119 | pkg_dict = factories.Dataset() 120 | res_dict = factories.Resource(package_id=pkg_dict['id'], **RES_DICT) 121 | pkg_dict = helpers.call_action('package_show', id=pkg_dict['id']) 122 | helpers.call_action('extractor_delete', id=res_dict['id']) 123 | enqueue_job.reset_mock() 124 | helpers.call_action('package_update', **pkg_dict) 125 | assert_equal(enqueue_job.call_count, 1, 126 | 'Wrong number of extraction tasks.') 127 | 128 | def test_deletion_after_private_dataset_update(self, enqueue_job): 129 | """ 130 | If a private dataset is updated its resources' metadata is removed. 131 | """ 132 | user = factories.Sysadmin() 133 | org_dict = factories.Organization() 134 | pkg_dict = factories.Dataset(owner_org=org_dict['id']) 135 | res_dict = factories.Resource(package_id=pkg_dict['id'], **RES_DICT) 136 | pkg_dict = helpers.call_action('package_show', id=pkg_dict['id']) 137 | pkg_dict['private'] = True 138 | assert_metadata(res_dict) 139 | helpers.call_action('package_update', {'user': user['id']}, **pkg_dict) 140 | assert_no_metadata(res_dict) 141 | 142 | -------------------------------------------------------------------------------- /ckanext/extractor/tests/test_tasks.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # -*- coding: utf-8 -*- 3 | 4 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 5 | # 6 | # This program is free software: you can redistribute it and/or modify 7 | # it under the terms of the GNU Affero General Public License as published 8 | # by the Free Software Foundation, either version 3 of the License, or 9 | # (at your option) any later version. 10 | # 11 | # This program is distributed in the hope that it will be useful, 12 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 | # GNU Affero General Public License for more details. 15 | # 16 | # You should have received a copy of the GNU Affero General Public License 17 | # along with this program. If not, see . 18 | 19 | 20 | from __future__ import absolute_import, print_function, unicode_literals 21 | 22 | import datetime 23 | import logging 24 | import re 25 | 26 | import mock 27 | from pylons import config 28 | from nose.tools import assert_false, assert_true 29 | from requests.exceptions import RequestException 30 | 31 | from ckan.lib import search 32 | from ckan.plugins import toolkit 33 | from ckan.tests import factories 34 | from ckan.tests.helpers import FunctionalTestBase 35 | 36 | from ..tasks import extract 37 | from .helpers import (assert_equal, assert_time_span, get_metadata, 38 | assert_package_found, assert_package_not_found, 39 | recorded_logs) 40 | 41 | 42 | RES_DICT = { 43 | 'url': 'does-not-matter', 44 | 'format': 'pdf', 45 | } 46 | 47 | METADATA = { 48 | 'fulltext': 'foobar', 49 | 'author': 'john_doe', 50 | 'created': 'yesterday', 51 | } 52 | 53 | 54 | @mock.patch('ckanext.extractor.tasks.download_and_extract', 55 | return_value=METADATA) 56 | @mock.patch('ckanext.extractor.tasks.load_config') 57 | class TestMetadataExtractTask(FunctionalTestBase): 58 | 59 | def test_new(self, lc_mock, dae_mock): 60 | """ 61 | Metadata extraction without previous metadata. 62 | """ 63 | res_dict = factories.Resource(**RES_DICT) 64 | get_metadata(res_dict).delete().commit() 65 | extract(config['__file__'], res_dict) 66 | metadata = get_metadata(res_dict) 67 | assert_equal(metadata.meta['fulltext'], METADATA['fulltext'], 68 | 'Wrong fulltext.') 69 | assert_equal(metadata.meta['author'], METADATA['author'], 70 | 'Wrong author.') 71 | assert_false('created' in metadata.meta, 72 | '"created" field was not ignored.') 73 | assert_equal(metadata.last_format, res_dict['format'], 74 | 'Wrong last_format') 75 | assert_equal(metadata.last_url, res_dict['url'], 'Wrong last_url.') 76 | assert_true(metadata.task_id is None, 'Unexpected task ID.') 77 | assert_time_span(metadata.last_extracted, max=5) 78 | assert_package_found(METADATA['fulltext'], res_dict['package_id'], 79 | 'Metadata not indexed.') 80 | assert_package_found(METADATA['author'], res_dict['package_id'], 81 | 'Metadata not indexed.') 82 | assert_package_not_found(METADATA['created'], res_dict['package_id'], 83 | 'Wrong metadata indexed.') 84 | 85 | def test_update(self, lc_mock, dae_mock): 86 | """ 87 | Metadata extraction of indexed format with previous metadata. 88 | """ 89 | res_dict = factories.Resource(**RES_DICT) 90 | metadata = get_metadata(res_dict) 91 | metadata.meta['fulltext'] = 'old fulltext' 92 | metadata.meta['author'] = 'old author' 93 | metadata.meta['updated'] = 'should be removed' 94 | metadata.meta['last_extracted'] = datetime.datetime(2000, 1, 1) 95 | metadata.last_format = 'old format' 96 | metadata.last_url = 'old url' 97 | metadata.save() 98 | extract(config['__file__'], res_dict) 99 | metadata = get_metadata(res_dict) 100 | assert_equal(metadata.meta['fulltext'], METADATA['fulltext'], 101 | 'Wrong fulltext.') 102 | assert_equal(metadata.meta['author'], METADATA['author'], 103 | 'Wrong author.') 104 | assert_false('created' in metadata.meta, 105 | '"created" field was not ignored.') 106 | assert_false('updated' in metadata.meta, 107 | '"updated" field was not removed.') 108 | assert_equal(metadata.last_format, res_dict['format'], 109 | 'Wrong last_format') 110 | assert_equal(metadata.last_url, res_dict['url'], 'Wrong last_url.') 111 | assert_true(metadata.task_id is None, 'Unexpected task ID.') 112 | assert_time_span(metadata.last_extracted, max=5) 113 | assert_package_found(METADATA['fulltext'], res_dict['package_id'], 114 | 'Metadata not indexed.') 115 | assert_package_found(METADATA['author'], res_dict['package_id'], 116 | 'Metadata not indexed.') 117 | assert_package_not_found(METADATA['created'], res_dict['package_id'], 118 | 'Wrong metadata indexed.') 119 | 120 | def test_download_errors(self, lc_mock, dae_mock): 121 | """ 122 | Handling of errors during resource downloading. 123 | """ 124 | dae_mock.side_effect = RequestException('OH NOES') 125 | res_dict = factories.Resource(**RES_DICT) 126 | with recorded_logs() as logs: 127 | extract(config['__file__'], res_dict) 128 | logs.assert_log('warning', re.escape(res_dict['url'])) 129 | logs.assert_log('warning', 'OH NOES') 130 | 131 | def test_extraction_from_private_dataset(self, lc_mock, dae_mock): 132 | """ 133 | Handling of resources in private datasets. 134 | """ 135 | # See https://github.com/stadt-karlsruhe/ckanext-extractor/issues/8 136 | org_dict = factories.Organization() 137 | pkg_dict = factories.Dataset(private=True, owner_org=org_dict['id']) 138 | res_dict = factories.Resource(package_id=pkg_dict['id'], **RES_DICT) 139 | with recorded_logs() as logs: 140 | extract(config['__file__'], res_dict) 141 | logs.assert_log('debug', 'private') 142 | dae_mock.assert_not_called() 143 | 144 | def test_multiple_values_for_the_same_field(self, lc_mock, dae_mock): 145 | """ 146 | Handling of multiple values for the same metadata field. 147 | """ 148 | # See https://github.com/stadt-karlsruhe/ckanext-extractor/issues/11 149 | dae_mock.return_value = { 150 | 'fulltext': 'foobar', 151 | 'author': ['john_doe', 'jane_doe'], 152 | } 153 | res_dict = factories.Resource(**RES_DICT) 154 | with recorded_logs() as logs: 155 | extract(config['__file__'], res_dict) 156 | logs.assert_log('debug', 'Collapsing.*author') 157 | metadata = get_metadata(res_dict) 158 | assert_equal(metadata.meta['author'], 'john_doe, jane_doe') 159 | 160 | def test_package_update_race_condition(self, lc_mock, dae_mock): 161 | """ 162 | Handling of package updates during extraction. 163 | """ 164 | res_dict = factories.Resource(**RES_DICT) 165 | sysadmin = factories.Sysadmin() 166 | 167 | def download_and_extract(*args, **kwargs): 168 | # Simulate a change to the package by another party during 169 | # the download and extraction process. 170 | toolkit.get_action('package_patch')({'user': sysadmin['name']}, 171 | {'id': res_dict['package_id'], 172 | 'title': 'A changed title'}) 173 | return {'fulltext': 'foobar'} 174 | 175 | dae_mock.side_effect = download_and_extract 176 | extract(config['__file__'], res_dict) 177 | 178 | # Make sure that the changed package metadata is kept and indexed 179 | pkg_dict = toolkit.get_action('package_show')( 180 | {}, {'id': res_dict['package_id']}) 181 | assert_equal(pkg_dict['title'], 'A changed title') 182 | indexed_pkg_dict = search.show(res_dict['package_id']) 183 | assert_equal(indexed_pkg_dict['title'], 'A changed title') 184 | 185 | -------------------------------------------------------------------------------- /dev-requirements.txt: -------------------------------------------------------------------------------- 1 | nose==1.3.7 2 | mock==1.0.1 3 | 4 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | pysolr>=3.4.0 2 | requests>=2.7.0 3 | 4 | -------------------------------------------------------------------------------- /runtests.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | # Run the tests for ckanext-extractor. 4 | # 5 | # Any arguments are forwarded to nosetests. 6 | 7 | # Create database tables if necessary 8 | paster --plugin=ckanext-extractor init -c test.ini 9 | 10 | # Run tests 11 | nosetests --ckan \ 12 | --with-pylons=test.ini \ 13 | --with-coverage \ 14 | --cover-package=ckanext.extractor \ 15 | --cover-erase \ 16 | --cover-inclusive \ 17 | $@ 18 | 19 | -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- 1 | [extract_messages] 2 | keywords = translate isPlural 3 | add_comments = TRANSLATORS: 4 | output_file = ckanext/extractor/i18n/ckanext-extractor.pot 5 | width = 80 6 | 7 | [init_catalog] 8 | domain = ckanext-extractor 9 | input_file = ckanext/extractor/i18n/ckanext-extractor.pot 10 | output_dir = ckanext/extractor/i18n 11 | 12 | [update_catalog] 13 | domain = ckanext-extractor 14 | input_file = ckanext/extractor/i18n/ckanext-extractor.pot 15 | output_dir = ckanext/extractor/i18n 16 | previous = true 17 | 18 | [compile_catalog] 19 | domain = ckanext-extractor 20 | directory = ckanext/extractor/i18n 21 | statistics = true 22 | 23 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | 3 | # Copyright (C) 2016-2018 Stadt Karlsruhe (www.karlsruhe.de) 4 | # 5 | # This program is free software: you can redistribute it and/or modify 6 | # it under the terms of the GNU Affero General Public License as published 7 | # by the Free Software Foundation, either version 3 of the License, or 8 | # (at your option) any later version. 9 | # 10 | # This program is distributed in the hope that it will be useful, 11 | # but WITHOUT ANY WARRANTY; without even the implied warranty of 12 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 13 | # GNU Affero General Public License for more details. 14 | # 15 | # You should have received a copy of the GNU Affero General Public License 16 | # along with this program. If not, see . 17 | 18 | 19 | from setuptools import setup, find_packages 20 | import codecs 21 | import os.path 22 | import re 23 | 24 | 25 | HERE = os.path.abspath(os.path.dirname(__file__)) 26 | 27 | # Get the long description from the README 28 | with codecs.open(os.path.join(HERE, 'README.rst'), encoding='utf-8') as f: 29 | long_description = f.read() 30 | 31 | # Extract version 32 | INIT_PY = os.path.join(HERE, 'ckanext', 'extractor', '__init__.py') 33 | version = None 34 | with codecs.open(INIT_PY) as f: 35 | for line in f: 36 | m = re.match(r'__version__\s*=\s*[\'"](.*)[\'"]', line) 37 | if m: 38 | version = m.groups()[0] 39 | break 40 | if version is None: 41 | raise RuntimeError('Could not extract version from "{}".'.format(INIT_PY)) 42 | 43 | setup( 44 | name='''ckanext-extractor''', 45 | 46 | # Versions should comply with PEP440. For a discussion on single-sourcing 47 | # the version across setup.py and the project code, see 48 | # http://packaging.python.org/en/latest/tutorial.html#version 49 | version=version, 50 | 51 | description='''A full text and metadata extractor for CKAN''', 52 | long_description=long_description, 53 | 54 | # The project's main homepage. 55 | url='https://github.com/stadt-karlsruhe/ckanext-extractor', 56 | 57 | # Author details 58 | author='''Stadt Karlsruhe''', 59 | author_email='''transparenz@karlsruhe.de''', 60 | 61 | # Choose your license 62 | license='AGPL', 63 | 64 | # See https://pypi.python.org/pypi?%3Aaction=list_classifiers 65 | classifiers=[ 66 | # How mature is this project? Common values are 67 | # 3 - Alpha 68 | # 4 - Beta 69 | # 5 - Production/Stable 70 | 'Development Status :: 4 - Beta', 71 | 72 | # Pick your license as you wish (should match "license" above) 73 | 'License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)', 74 | 75 | # Specify the Python versions you support here. In particular, ensure 76 | # that you indicate whether you support Python 2, Python 3 or both. 77 | 'Programming Language :: Python :: 2.7', 78 | ], 79 | 80 | 81 | # What does your project relate to? 82 | keywords='''CKAN metadata meta data extraction fulltext full text search 83 | solr tika index''', 84 | 85 | # You can just specify the packages manually here if your project is 86 | # simple. Or you can use find_packages(). 87 | packages=find_packages(exclude=['contrib', 'docs', 'tests*']), 88 | namespace_packages=['ckanext'], 89 | 90 | # List run-time dependencies here. These will be installed by pip when your 91 | # project is installed. For an analysis of "install_requires" vs pip's 92 | # requirements files see: 93 | # https://packaging.python.org/en/latest/technical.html#install-requires-vs-requirements-files 94 | install_requires=[], 95 | 96 | # If there are data files included in your packages that need to be 97 | # installed, specify them here. If using Python 2.6 or less, then these 98 | # have to be included in MANIFEST.in as well. 99 | include_package_data=True, 100 | package_data={}, 101 | 102 | # Although 'package_data' is the preferred approach, in some case you may 103 | # need to place data files outside of your packages. 104 | # see http://docs.python.org/3.4/distutils/setupscript.html#installing-additional-files 105 | # In this case, 'data_file' will be installed into '/my_data' 106 | data_files=[], 107 | 108 | # To provide executable scripts, use entry points in preference to the 109 | # "scripts" keyword. Entry points provide cross-platform support and allow 110 | # pip to create the appropriate form of executable for the target platform. 111 | entry_points=''' 112 | [ckan.plugins] 113 | extractor=ckanext.extractor.plugin:ExtractorPlugin 114 | 115 | [babel.extractors] 116 | ckan = ckan.lib.extract:extract_ckan 117 | 118 | [paste.paster_command] 119 | delete = ckanext.extractor.paster:DeleteCommand 120 | extract = ckanext.extractor.paster:ExtractCommand 121 | init = ckanext.extractor.paster:InitCommand 122 | list = ckanext.extractor.paster:ListCommand 123 | show = ckanext.extractor.paster:ShowCommand 124 | ''', 125 | 126 | # If you are changing from the default layout of your extension, you may 127 | # have to change the message extractors, you can read more about babel 128 | # message extraction at 129 | # http://babel.pocoo.org/docs/messages/#extraction-method-mapping-and-configuration 130 | message_extractors={ 131 | 'ckanext': [ 132 | ('**.py', 'python', None), 133 | ('**.js', 'javascript', None), 134 | ('**/templates/**.html', 'ckan', None), 135 | ], 136 | } 137 | ) 138 | 139 | -------------------------------------------------------------------------------- /test-local.ini.example: -------------------------------------------------------------------------------- 1 | # Example file for local test settings. Copy to `test-local.ini` 2 | 3 | # Test Configuration settings for your particular system (e.g. database 4 | # connection, Solr URL) should go into this file (`test-local.ini`). It 5 | # is automatically included in `test.ini` and not tracked by Git. 6 | 7 | [app:main] 8 | # Include default CKAN test configuration. You may have to update the 9 | # path if the CKAN sources are not in an adjacent directory. 10 | use = config:../ckan/test-core.ini 11 | 12 | -------------------------------------------------------------------------------- /test.ini: -------------------------------------------------------------------------------- 1 | # ATTENTION: Do not edit this file directly for configurations related 2 | # to your particular system (e.g. database connection, Solr URL, etc.). 3 | # Put these into `test-local.ini` which is automatically included here 4 | # and not tracked by Git. See `test-local.ini.example` for details. 5 | 6 | [DEFAULT] 7 | debug = false 8 | smtp_server = localhost 9 | error_email_from = paste@localhost 10 | 11 | [server:main] 12 | use = egg:Paste#http 13 | host = 0.0.0.0 14 | port = 5000 15 | 16 | [app:main] 17 | use = config:test-local.ini 18 | 19 | ckan.plugins = extractor 20 | 21 | # Our tests assume that certain formats and fields are indexed while 22 | # others are ignored. 23 | ckanext.extractor.indexed_formats = pdf doc 24 | ckanext.extractor.indexed_fields = fulltext author 25 | 26 | # Logging configuration 27 | [loggers] 28 | keys = root, ckan, ckanext, sqlalchemy 29 | 30 | [handlers] 31 | keys = console 32 | 33 | [formatters] 34 | keys = generic 35 | 36 | [logger_root] 37 | level = WARN 38 | handlers = console 39 | 40 | [logger_ckan] 41 | qualname = ckan 42 | handlers = console 43 | level = INFO 44 | propagate = 0 45 | 46 | [logger_ckanext] 47 | qualname = ckanext 48 | handlers = console 49 | level = DEBUG 50 | propagate = 0 51 | 52 | [logger_sqlalchemy] 53 | handlers = console 54 | qualname = sqlalchemy.engine 55 | level = WARN 56 | propagate = 0 57 | 58 | [handler_console] 59 | class = StreamHandler 60 | args = (sys.stdout,) 61 | level = NOTSET 62 | formatter = generic 63 | 64 | [formatter_generic] 65 | format = %(asctime)s %(levelname)-5.5s [%(name)s] %(message)s 66 | -------------------------------------------------------------------------------- /travis/build.bash: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | set -e 3 | 4 | echo "This is travis-build.bash..." 5 | 6 | SOLR_VERSION=3.6.2 7 | 8 | echo "Installing the packages that CKAN requires..." 9 | sudo apt-get update -qq 10 | sudo apt-get install solr-tomcat=$SOLR_VERSION\* 11 | 12 | echo "Downloading Solr plugins" 13 | wget http://archive.apache.org/dist/lucene/solr/$SOLR_VERSION/apache-solr-$SOLR_VERSION.tgz 14 | tar xzf apache-solr-$SOLR_VERSION.tgz 15 | sudo mv -v apache-solr-$SOLR_VERSION /var/apache-solr 16 | 17 | echo "Configure Solr" 18 | sudo cp -v travis/solr/ckan-$CKANVERSION/* /etc/solr/conf/ 19 | 20 | echo "Restarting Tomcat" 21 | sudo service tomcat6 restart 22 | 23 | echo "Checking that Tomcat is up" 24 | sudo service tomcat6 status 25 | curl http://127.0.0.1:8080 26 | 27 | echo "Checking that Solr is up" 28 | curl http://127.0.0.1:8080/solr/admin/ping 29 | 30 | echo "Installing CKAN and its Python dependencies..." 31 | git clone https://github.com/ckan/ckan 32 | pushd ckan 33 | if [ $CKANVERSION == 'master' ] 34 | then 35 | echo "CKAN version: master" 36 | else 37 | CKAN_TAG=$(git tag | grep ^ckan-$CKANVERSION | sort --version-sort | tail -n 1) 38 | git checkout $CKAN_TAG 39 | echo "CKAN version: ${CKAN_TAG#ckan-}" 40 | 41 | if [ $CKANVERSION == '2.6' ] 42 | then 43 | echo "Installing ckanext-rq" 44 | pushd .. 45 | git clone https://github.com/ckan/ckanext-rq.git 46 | cd ckanext-rq 47 | python setup.py develop 48 | pip install -r requirements.txt 49 | cd .. 50 | # Add `rq` to the list of active CKAN plugins 51 | sed -i '/^\s*ckan.plugins\s*=/ s/$/ rq/' test.ini 52 | popd 53 | fi 54 | fi 55 | # Unpin CKAN's psycopg2 dependency get an important bugfix 56 | # https://stackoverflow.com/questions/47044854/error-installing-psycopg2-2-6-2 57 | sed -i '/psycopg2/c\psycopg2' requirements.txt 58 | python setup.py develop 59 | pip install -r requirements.txt 60 | pip install -r dev-requirements.txt 61 | popd 62 | 63 | echo "Creating the PostgreSQL user and database..." 64 | sudo -u postgres psql -c "CREATE USER ckan_default WITH PASSWORD 'pass';" 65 | sudo -u postgres psql -c 'CREATE DATABASE ckan_test WITH OWNER ckan_default;' 66 | 67 | echo "Installing ckanext-extractor and its requirements..." 68 | python setup.py develop 69 | pip install -r requirements.txt 70 | pip install -r dev-requirements.txt 71 | 72 | echo "Moving test.ini into a subdir..." 73 | mkdir subdir 74 | mv test.ini subdir 75 | 76 | echo "Copying test-local.ini" 77 | cp -v travis/test-local.ini subdir/ 78 | 79 | echo "Initialising the database..." 80 | pushd ckan 81 | paster db init -c test-core.ini 82 | popd 83 | 84 | echo "Initializing database for ckanext-extractor..." 85 | paster --plugin=ckanext-extractor init -c subdir/test.ini 86 | 87 | echo "travis-build.bash is done." 88 | 89 | -------------------------------------------------------------------------------- /travis/run.bash: -------------------------------------------------------------------------------- 1 | #!/bin/bash 2 | set -e 3 | 4 | nosetests --ckan \ 5 | --with-pylons=subdir/test.ini \ 6 | --with-coverage \ 7 | --cover-package=ckanext.extractor \ 8 | --cover-erase \ 9 | --cover-inclusive \ 10 | ckanext 11 | 12 | -------------------------------------------------------------------------------- /travis/solr/ckan-2.6/schema.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 23 | 24 | 27 | 28 | 29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 | 47 | 48 | 49 | 50 | 51 | 52 | 53 | 54 | 55 | 56 | 57 | 58 | 59 | 60 | 61 | 62 | 63 | 64 | 65 | 66 | 67 | 68 | 69 | 70 | 71 | 72 | 73 | 74 | 75 | 76 | 77 | 78 | 79 | 80 | 81 | 82 | 83 | 84 | 85 | 86 | 87 | 88 | 89 | 90 | 91 | 92 | 93 | 94 | 95 | 96 | 97 | 98 | 99 | 100 | 101 | 102 | 103 | 104 | 105 | 106 | 107 | 108 | 109 | 110 | 111 | 112 | 113 | 114 | 115 | 117 | 118 | 119 | 120 | 121 | 122 | 123 | 124 | 125 | 126 | 127 | 128 | 129 | 130 | 131 | 132 | 133 | 134 | 135 | 136 | 137 | 138 | 140 | 141 | 142 | 143 | 144 | 145 | 146 | 147 | 148 | 149 | 150 | 151 | 152 | 153 | 154 | 155 | 156 | index_id 157 | text 158 | 159 | 160 | 161 | 162 | 163 | 164 | 165 | 166 | 167 | 168 | 169 | 170 | 171 | 172 | 173 | 174 | 175 | 176 | 177 | 178 | 179 | 180 | 181 | 182 | 183 | -------------------------------------------------------------------------------- /travis/solr/ckan-2.6/solrconfig.xml: -------------------------------------------------------------------------------- 1 | ../solrconfig.xml -------------------------------------------------------------------------------- /travis/solr/ckan-2.7/schema.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 23 | 24 | 27 | 28 | 29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 | 47 | 48 | 49 | 50 | 51 | 52 | 53 | 54 | 55 | 56 | 57 | 58 | 59 | 60 | 61 | 62 | 63 | 64 | 65 | 66 | 67 | 68 | 69 | 70 | 71 | 72 | 73 | 74 | 75 | 76 | 77 | 78 | 79 | 80 | 81 | 82 | 83 | 84 | 85 | 86 | 87 | 88 | 89 | 90 | 91 | 92 | 93 | 94 | 95 | 96 | 97 | 98 | 99 | 100 | 101 | 102 | 103 | 104 | 105 | 106 | 107 | 108 | 109 | 110 | 111 | 112 | 113 | 114 | 115 | 116 | 117 | 118 | 119 | 120 | 121 | 122 | 123 | 125 | 126 | 127 | 128 | 129 | 130 | 131 | 132 | 133 | 134 | 135 | 136 | 137 | 138 | 139 | 140 | 141 | 142 | 143 | 144 | 145 | 146 | 148 | 149 | 150 | 151 | 152 | 153 | 154 | 155 | 156 | 157 | 158 | 159 | 160 | 161 | 162 | 163 | 164 | index_id 165 | text 166 | 167 | 168 | 169 | 170 | 171 | 172 | 173 | 174 | 175 | 176 | 177 | 178 | 179 | 180 | 181 | 182 | 183 | 184 | 185 | 186 | 187 | 188 | 189 | 190 | 191 | -------------------------------------------------------------------------------- /travis/solr/ckan-2.7/solrconfig.xml: -------------------------------------------------------------------------------- 1 | ../solrconfig.xml -------------------------------------------------------------------------------- /travis/solr/ckan-2.8/schema.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 23 | 24 | 27 | 28 | 29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 | 47 | 48 | 49 | 50 | 51 | 52 | 53 | 54 | 55 | 56 | 57 | 58 | 59 | 60 | 61 | 62 | 63 | 64 | 65 | 66 | 67 | 68 | 69 | 70 | 71 | 72 | 73 | 74 | 75 | 76 | 77 | 78 | 79 | 80 | 81 | 82 | 83 | 84 | 85 | 86 | 87 | 88 | 89 | 90 | 91 | 92 | 93 | 94 | 95 | 96 | 97 | 98 | 99 | 100 | 101 | 102 | 103 | 104 | 105 | 106 | 107 | 108 | 109 | 110 | 111 | 112 | 113 | 114 | 115 | 116 | 117 | 118 | 119 | 120 | 121 | 122 | 123 | 125 | 126 | 127 | 128 | 129 | 130 | 131 | 132 | 133 | 134 | 135 | 136 | 137 | 138 | 139 | 140 | 141 | 142 | 143 | 144 | 145 | 146 | 148 | 149 | 150 | 151 | 152 | 153 | 154 | 155 | 156 | 157 | 158 | 159 | 160 | 161 | 162 | 163 | 164 | index_id 165 | text 166 | 167 | 168 | 169 | 170 | 171 | 172 | 173 | 174 | 175 | 176 | 177 | 178 | 179 | 180 | 181 | 182 | 183 | 184 | 185 | 186 | 187 | 188 | 189 | 190 | 191 | -------------------------------------------------------------------------------- /travis/solr/ckan-2.8/solrconfig.xml: -------------------------------------------------------------------------------- 1 | ../solrconfig.xml -------------------------------------------------------------------------------- /travis/solr/ckan-master/schema.xml: -------------------------------------------------------------------------------- 1 | 2 | 18 | 19 | 23 | 24 | 27 | 28 | 29 | 30 | 31 | 32 | 33 | 34 | 35 | 36 | 37 | 38 | 39 | 40 | 41 | 42 | 43 | 44 | 45 | 46 | 47 | 48 | 49 | 50 | 51 | 52 | 53 | 54 | 55 | 56 | 57 | 58 | 59 | 60 | 61 | 62 | 63 | 64 | 65 | 66 | 67 | 68 | 69 | 70 | 71 | 72 | 73 | 74 | 75 | 76 | 77 | 78 | 79 | 80 | 81 | 82 | 83 | 84 | 85 | 86 | 87 | 88 | 89 | 90 | 91 | 92 | 93 | 94 | 95 | 96 | 97 | 98 | 99 | 100 | 101 | 102 | 103 | 104 | 105 | 106 | 107 | 108 | 109 | 110 | 111 | 112 | 113 | 114 | 115 | 116 | 117 | 118 | 119 | 120 | 121 | 122 | 123 | 125 | 126 | 127 | 128 | 129 | 130 | 131 | 132 | 133 | 134 | 135 | 136 | 137 | 138 | 139 | 140 | 141 | 142 | 143 | 144 | 145 | 146 | 148 | 149 | 150 | 151 | 152 | 153 | 154 | 155 | 156 | 157 | 158 | 159 | 160 | 161 | 162 | 163 | 164 | index_id 165 | text 166 | 167 | 168 | 169 | 170 | 171 | 172 | 173 | 174 | 175 | 176 | 177 | 178 | 179 | 180 | 181 | 182 | 183 | 184 | 185 | 186 | 187 | 188 | 189 | 190 | 191 | -------------------------------------------------------------------------------- /travis/solr/ckan-master/solrconfig.xml: -------------------------------------------------------------------------------- 1 | ../solrconfig.xml -------------------------------------------------------------------------------- /travis/test-local.ini: -------------------------------------------------------------------------------- 1 | [app:main] 2 | use = config:../ckan/test-core.ini 3 | solr_url = http://127.0.0.1:8080/solr 4 | 5 | --------------------------------------------------------------------------------