├── .gitignore ├── .travis.yml ├── LICENSE ├── Makefile ├── README.md ├── requirements.txt ├── resources ├── TokenQuery_example_1.png ├── Token_query_logo.png └── TokenrRegex_logo.png ├── setup.cfg ├── setup.py └── tokenquery ├── __init__.py ├── acceptors ├── __init__.py ├── core │ ├── __init__.py │ ├── date_opr.py │ ├── int_opr.py │ ├── string_opr.py │ ├── vector_opr.py │ └── web_opr.py └── extended │ └── __init__.py ├── models ├── __init__.py ├── chunk.py ├── fsa.py ├── stack.py └── token.py ├── nlp ├── __init__.py ├── google_nlp_api.py ├── importer.py ├── pos_tagger.py └── tokenizer.py ├── tests ├── __init__.py ├── acceptors │ └── core │ │ ├── int_opr_test.py │ │ ├── string_opr_test.py │ │ ├── vector_opr_test.py │ │ └── web_opr_test.py ├── models │ ├── fsa_test.py │ ├── stack_test.py │ └── token_test.py ├── nlp │ ├── data │ │ └── test.conllu │ ├── importer_test.py │ ├── pos_tagger_test.py │ └── tokenizer_test.py └── tokenquery_test.py └── tokenquery.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.DS_Store 2 | 3 | # Byte-compiled / optimized / DLL files 4 | __pycache__/ 5 | *.py[cod] 6 | *$py.class 7 | 8 | # C extensions 9 | *.so 10 | 11 | # Distribution / packaging 12 | .Python 13 | env/ 14 | build/ 15 | develop-eggs/ 16 | dist/ 17 | downloads/ 18 | eggs/ 19 | .eggs/ 20 | lib/ 21 | lib64/ 22 | parts/ 23 | sdist/ 24 | var/ 25 | *.egg-info/ 26 | .installed.cfg 27 | *.egg 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .coverage 43 | .coverage.* 44 | .cache 45 | nosetests.xml 46 | coverage.xml 47 | *,cover 48 | .hypothesis/ 49 | 50 | # Translations 51 | *.mo 52 | *.pot 53 | 54 | # Django stuff: 55 | *.log 56 | local_settings.py 57 | 58 | # Flask stuff: 59 | instance/ 60 | .webassets-cache 61 | 62 | # Scrapy stuff: 63 | .scrapy 64 | 65 | # Sphinx documentation 66 | docs/_build/ 67 | 68 | # PyBuilder 69 | target/ 70 | 71 | # IPython Notebook 72 | .ipynb_checkpoints 73 | 74 | # pyenv 75 | .python-version 76 | 77 | # celery beat schedule file 78 | celerybeat-schedule 79 | 80 | # dotenv 81 | .env 82 | 83 | # virtualenv 84 | venv/ 85 | ENV/ 86 | 87 | # Spyder project settings 88 | .spyderproject 89 | 90 | # Rope project settings 91 | .ropeproject 92 | -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- 1 | language: python 2 | python: 3 | - "3.4" 4 | # command to install dependencies 5 | install: 6 | - pip install -r requirements.txt 7 | # command to run tests 8 | script: make test 9 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | GNU GENERAL PUBLIC LICENSE 2 | Version 3, 29 June 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 General Public License is a free, copyleft license for 11 | software and other kinds of works. 12 | 13 | The licenses for most software and other practical works are designed 14 | to take away your freedom to share and change the works. By contrast, 15 | the GNU General Public License is intended to guarantee your freedom to 16 | share and change all versions of a program--to make sure it remains free 17 | software for all its users. We, the Free Software Foundation, use the 18 | GNU General Public License for most of our software; it applies also to 19 | any other work released this way by its authors. You can apply it to 20 | your programs, too. 21 | 22 | When we speak of free software, we are referring to freedom, not 23 | price. Our General Public Licenses are designed to make sure that you 24 | have the freedom to distribute copies of free software (and charge for 25 | them if you wish), that you receive source code or can get it if you 26 | want it, that you can change the software or use pieces of it in new 27 | free programs, and that you know you can do these things. 28 | 29 | To protect your rights, we need to prevent others from denying you 30 | these rights or asking you to surrender the rights. Therefore, you have 31 | certain responsibilities if you distribute copies of the software, or if 32 | you modify it: responsibilities to respect the freedom of others. 33 | 34 | For example, if you distribute copies of such a program, whether 35 | gratis or for a fee, you must pass on to the recipients the same 36 | freedoms that you received. You must make sure that they, too, receive 37 | or can get the source code. And you must show them these terms so they 38 | know their rights. 39 | 40 | Developers that use the GNU GPL protect your rights with two steps: 41 | (1) assert copyright on the software, and (2) offer you this License 42 | giving you legal permission to copy, distribute and/or modify it. 43 | 44 | For the developers' and authors' protection, the GPL clearly explains 45 | that there is no warranty for this free software. For both users' and 46 | authors' sake, the GPL requires that modified versions be marked as 47 | changed, so that their problems will not be attributed erroneously to 48 | authors of previous versions. 49 | 50 | Some devices are designed to deny users access to install or run 51 | modified versions of the software inside them, although the manufacturer 52 | can do so. This is fundamentally incompatible with the aim of 53 | protecting users' freedom to change the software. The systematic 54 | pattern of such abuse occurs in the area of products for individuals to 55 | use, which is precisely where it is most unacceptable. Therefore, we 56 | have designed this version of the GPL to prohibit the practice for those 57 | products. If such problems arise substantially in other domains, we 58 | stand ready to extend this provision to those domains in future versions 59 | of the GPL, as needed to protect the freedom of users. 60 | 61 | Finally, every program is threatened constantly by software patents. 62 | States should not allow patents to restrict development and use of 63 | software on general-purpose computers, but in those that do, we wish to 64 | avoid the special danger that patents applied to a free program could 65 | make it effectively proprietary. To prevent this, the GPL assures that 66 | patents cannot be used to render the program non-free. 67 | 68 | The precise terms and conditions for copying, distribution and 69 | modification follow. 70 | 71 | TERMS AND CONDITIONS 72 | 73 | 0. Definitions. 74 | 75 | "This License" refers to version 3 of the GNU General Public License. 76 | 77 | "Copyright" also means copyright-like laws that apply to other kinds of 78 | works, such as semiconductor masks. 79 | 80 | "The Program" refers to any copyrightable work licensed under this 81 | License. Each licensee is addressed as "you". "Licensees" and 82 | "recipients" may be individuals or organizations. 83 | 84 | To "modify" a work means to copy from or adapt all or part of the work 85 | in a fashion requiring copyright permission, other than the making of an 86 | exact copy. The resulting work is called a "modified version" of the 87 | earlier work or a work "based on" the earlier work. 88 | 89 | A "covered work" means either the unmodified Program or a work based 90 | on the Program. 91 | 92 | To "propagate" a work means to do anything with it that, without 93 | permission, would make you directly or secondarily liable for 94 | infringement under applicable copyright law, except executing it on a 95 | computer or modifying a private copy. Propagation includes copying, 96 | distribution (with or without modification), making available to the 97 | public, and in some countries other activities as well. 98 | 99 | To "convey" a work means any kind of propagation that enables other 100 | parties to make or receive copies. Mere interaction with a user through 101 | a computer network, with no transfer of a copy, is not conveying. 102 | 103 | An interactive user interface displays "Appropriate Legal Notices" 104 | to the extent that it includes a convenient and prominently visible 105 | feature that (1) displays an appropriate copyright notice, and (2) 106 | tells the user that there is no warranty for the work (except to the 107 | extent that warranties are provided), that licensees may convey the 108 | work under this License, and how to view a copy of this License. If 109 | the interface presents a list of user commands or options, such as a 110 | menu, a prominent item in the list meets this criterion. 111 | 112 | 1. Source Code. 113 | 114 | The "source code" for a work means the preferred form of the work 115 | for making modifications to it. "Object code" means any non-source 116 | form of a work. 117 | 118 | A "Standard Interface" means an interface that either is an official 119 | standard defined by a recognized standards body, or, in the case of 120 | interfaces specified for a particular programming language, one that 121 | is widely used among developers working in that language. 122 | 123 | The "System Libraries" of an executable work include anything, other 124 | than the work as a whole, that (a) is included in the normal form of 125 | packaging a Major Component, but which is not part of that Major 126 | Component, and (b) serves only to enable use of the work with that 127 | Major Component, or to implement a Standard Interface for which an 128 | implementation is available to the public in source code form. A 129 | "Major Component", in this context, means a major essential component 130 | (kernel, window system, and so on) of the specific operating system 131 | (if any) on which the executable work runs, or a compiler used to 132 | produce the work, or an object code interpreter used to run it. 133 | 134 | The "Corresponding Source" for a work in object code form means all 135 | the source code needed to generate, install, and (for an executable 136 | work) run the object code and to modify the work, including scripts to 137 | control those activities. However, it does not include the work's 138 | System Libraries, or general-purpose tools or generally available free 139 | programs which are used unmodified in performing those activities but 140 | which are not part of the work. For example, Corresponding Source 141 | includes interface definition files associated with source files for 142 | the work, and the source code for shared libraries and dynamically 143 | linked subprograms that the work is specifically designed to require, 144 | such as by intimate data communication or control flow between those 145 | subprograms and other parts of the work. 146 | 147 | The Corresponding Source need not include anything that users 148 | can regenerate automatically from other parts of the Corresponding 149 | Source. 150 | 151 | The Corresponding Source for a work in source code form is that 152 | same work. 153 | 154 | 2. Basic Permissions. 155 | 156 | All rights granted under this License are granted for the term of 157 | copyright on the Program, and are irrevocable provided the stated 158 | conditions are met. This License explicitly affirms your unlimited 159 | permission to run the unmodified Program. The output from running a 160 | covered work is covered by this License only if the output, given its 161 | content, constitutes a covered work. This License acknowledges your 162 | rights of fair use or other equivalent, as provided by copyright law. 163 | 164 | You may make, run and propagate covered works that you do not 165 | convey, without conditions so long as your license otherwise remains 166 | in force. You may convey covered works to others for the sole purpose 167 | of having them make modifications exclusively for you, or provide you 168 | with facilities for running those works, provided that you comply with 169 | the terms of this License in conveying all material for which you do 170 | not control copyright. Those thus making or running the covered works 171 | for you must do so exclusively on your behalf, under your direction 172 | and control, on terms that prohibit them from making any copies of 173 | your copyrighted material outside their relationship with you. 174 | 175 | Conveying under any other circumstances is permitted solely under 176 | the conditions stated below. Sublicensing is not allowed; section 10 177 | makes it unnecessary. 178 | 179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law. 180 | 181 | No covered work shall be deemed part of an effective technological 182 | measure under any applicable law fulfilling obligations under article 183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or 184 | similar laws prohibiting or restricting circumvention of such 185 | measures. 186 | 187 | When you convey a covered work, you waive any legal power to forbid 188 | circumvention of technological measures to the extent such circumvention 189 | is effected by exercising rights under this License with respect to 190 | the covered work, and you disclaim any intention to limit operation or 191 | modification of the work as a means of enforcing, against the work's 192 | users, your or third parties' legal rights to forbid circumvention of 193 | technological measures. 194 | 195 | 4. Conveying Verbatim Copies. 196 | 197 | You may convey verbatim copies of the Program's source code as you 198 | receive it, in any medium, provided that you conspicuously and 199 | appropriately publish on each copy an appropriate copyright notice; 200 | keep intact all notices stating that this License and any 201 | non-permissive terms added in accord with section 7 apply to the code; 202 | keep intact all notices of the absence of any warranty; and give all 203 | recipients a copy of this License along with the Program. 204 | 205 | You may charge any price or no price for each copy that you convey, 206 | and you may offer support or warranty protection for a fee. 207 | 208 | 5. Conveying Modified Source Versions. 209 | 210 | You may convey a work based on the Program, or the modifications to 211 | produce it from the Program, in the form of source code under the 212 | terms of section 4, provided that you also meet all of these conditions: 213 | 214 | a) The work must carry prominent notices stating that you modified 215 | it, and giving a relevant date. 216 | 217 | b) The work must carry prominent notices stating that it is 218 | released under this License and any conditions added under section 219 | 7. This requirement modifies the requirement in section 4 to 220 | "keep intact all notices". 221 | 222 | c) You must license the entire work, as a whole, under this 223 | License to anyone who comes into possession of a copy. This 224 | License will therefore apply, along with any applicable section 7 225 | additional terms, to the whole of the work, and all its parts, 226 | regardless of how they are packaged. This License gives no 227 | permission to license the work in any other way, but it does not 228 | invalidate such permission if you have separately received it. 229 | 230 | d) If the work has interactive user interfaces, each must display 231 | Appropriate Legal Notices; however, if the Program has interactive 232 | interfaces that do not display Appropriate Legal Notices, your 233 | work need not make them do so. 234 | 235 | A compilation of a covered work with other separate and independent 236 | works, which are not by their nature extensions of the covered work, 237 | and which are not combined with it such as to form a larger program, 238 | in or on a volume of a storage or distribution medium, is called an 239 | "aggregate" if the compilation and its resulting copyright are not 240 | used to limit the access or legal rights of the compilation's users 241 | beyond what the individual works permit. Inclusion of a covered work 242 | in an aggregate does not cause this License to apply to the other 243 | parts of the aggregate. 244 | 245 | 6. Conveying Non-Source Forms. 246 | 247 | You may convey a covered work in object code form under the terms 248 | of sections 4 and 5, provided that you also convey the 249 | machine-readable Corresponding Source under the terms of this License, 250 | in one of these ways: 251 | 252 | a) Convey the object code in, or embodied in, a physical product 253 | (including a physical distribution medium), accompanied by the 254 | Corresponding Source fixed on a durable physical medium 255 | customarily used for software interchange. 256 | 257 | b) Convey the object code in, or embodied in, a physical product 258 | (including a physical distribution medium), accompanied by a 259 | written offer, valid for at least three years and valid for as 260 | long as you offer spare parts or customer support for that product 261 | model, to give anyone who possesses the object code either (1) a 262 | copy of the Corresponding Source for all the software in the 263 | product that is covered by this License, on a durable physical 264 | medium customarily used for software interchange, for a price no 265 | more than your reasonable cost of physically performing this 266 | conveying of source, or (2) access to copy the 267 | Corresponding Source from a network server at no charge. 268 | 269 | c) Convey individual copies of the object code with a copy of the 270 | written offer to provide the Corresponding Source. This 271 | alternative is allowed only occasionally and noncommercially, and 272 | only if you received the object code with such an offer, in accord 273 | with subsection 6b. 274 | 275 | d) Convey the object code by offering access from a designated 276 | place (gratis or for a charge), and offer equivalent access to the 277 | Corresponding Source in the same way through the same place at no 278 | further charge. You need not require recipients to copy the 279 | Corresponding Source along with the object code. If the place to 280 | copy the object code is a network server, the Corresponding Source 281 | may be on a different server (operated by you or a third party) 282 | that supports equivalent copying facilities, provided you maintain 283 | clear directions next to the object code saying where to find the 284 | Corresponding Source. Regardless of what server hosts the 285 | Corresponding Source, you remain obligated to ensure that it is 286 | available for as long as needed to satisfy these requirements. 287 | 288 | e) Convey the object code using peer-to-peer transmission, provided 289 | you inform other peers where the object code and Corresponding 290 | Source of the work are being offered to the general public at no 291 | charge under subsection 6d. 292 | 293 | A separable portion of the object code, whose source code is excluded 294 | from the Corresponding Source as a System Library, need not be 295 | included in conveying the object code work. 296 | 297 | A "User Product" is either (1) a "consumer product", which means any 298 | tangible personal property which is normally used for personal, family, 299 | or household purposes, or (2) anything designed or sold for incorporation 300 | into a dwelling. In determining whether a product is a consumer product, 301 | doubtful cases shall be resolved in favor of coverage. For a particular 302 | product received by a particular user, "normally used" refers to a 303 | typical or common use of that class of product, regardless of the status 304 | of the particular user or of the way in which the particular user 305 | actually uses, or expects or is expected to use, the product. A product 306 | is a consumer product regardless of whether the product has substantial 307 | commercial, industrial or non-consumer uses, unless such uses represent 308 | the only significant mode of use of the product. 309 | 310 | "Installation Information" for a User Product means any methods, 311 | procedures, authorization keys, or other information required to install 312 | and execute modified versions of a covered work in that User Product from 313 | a modified version of its Corresponding Source. The information must 314 | suffice to ensure that the continued functioning of the modified object 315 | code is in no case prevented or interfered with solely because 316 | modification has been made. 317 | 318 | If you convey an object code work under this section in, or with, or 319 | specifically for use in, a User Product, and the conveying occurs as 320 | part of a transaction in which the right of possession and use of the 321 | User Product is transferred to the recipient in perpetuity or for a 322 | fixed term (regardless of how the transaction is characterized), the 323 | Corresponding Source conveyed under this section must be accompanied 324 | by the Installation Information. But this requirement does not apply 325 | if neither you nor any third party retains the ability to install 326 | modified object code on the User Product (for example, the work has 327 | been installed in ROM). 328 | 329 | The requirement to provide Installation Information does not include a 330 | requirement to continue to provide support service, warranty, or updates 331 | for a work that has been modified or installed by the recipient, or for 332 | the User Product in which it has been modified or installed. Access to a 333 | network may be denied when the modification itself materially and 334 | adversely affects the operation of the network or violates the rules and 335 | protocols for communication across the network. 336 | 337 | Corresponding Source conveyed, and Installation Information provided, 338 | in accord with this section must be in a format that is publicly 339 | documented (and with an implementation available to the public in 340 | source code form), and must require no special password or key for 341 | unpacking, reading or copying. 342 | 343 | 7. Additional Terms. 344 | 345 | "Additional permissions" are terms that supplement the terms of this 346 | License by making exceptions from one or more of its conditions. 347 | Additional permissions that are applicable to the entire Program shall 348 | be treated as though they were included in this License, to the extent 349 | that they are valid under applicable law. If additional permissions 350 | apply only to part of the Program, that part may be used separately 351 | under those permissions, but the entire Program remains governed by 352 | this License without regard to the additional permissions. 353 | 354 | When you convey a copy of a covered work, you may at your option 355 | remove any additional permissions from that copy, or from any part of 356 | it. (Additional permissions may be written to require their own 357 | removal in certain cases when you modify the work.) You may place 358 | additional permissions on material, added by you to a covered work, 359 | for which you have or can give appropriate copyright permission. 360 | 361 | Notwithstanding any other provision of this License, for material you 362 | add to a covered work, you may (if authorized by the copyright holders of 363 | that material) supplement the terms of this License with terms: 364 | 365 | a) Disclaiming warranty or limiting liability differently from the 366 | terms of sections 15 and 16 of this License; or 367 | 368 | b) Requiring preservation of specified reasonable legal notices or 369 | author attributions in that material or in the Appropriate Legal 370 | Notices displayed by works containing it; or 371 | 372 | c) Prohibiting misrepresentation of the origin of that material, or 373 | requiring that modified versions of such material be marked in 374 | reasonable ways as different from the original version; or 375 | 376 | d) Limiting the use for publicity purposes of names of licensors or 377 | authors of the material; or 378 | 379 | e) Declining to grant rights under trademark law for use of some 380 | trade names, trademarks, or service marks; or 381 | 382 | f) Requiring indemnification of licensors and authors of that 383 | material by anyone who conveys the material (or modified versions of 384 | it) with contractual assumptions of liability to the recipient, for 385 | any liability that these contractual assumptions directly impose on 386 | those licensors and authors. 387 | 388 | All other non-permissive additional terms are considered "further 389 | restrictions" within the meaning of section 10. If the Program as you 390 | received it, or any part of it, contains a notice stating that it is 391 | governed by this License along with a term that is a further 392 | restriction, you may remove that term. If a license document contains 393 | a further restriction but permits relicensing or conveying under this 394 | License, you may add to a covered work material governed by the terms 395 | of that license document, provided that the further restriction does 396 | not survive such relicensing or conveying. 397 | 398 | If you add terms to a covered work in accord with this section, you 399 | must place, in the relevant source files, a statement of the 400 | additional terms that apply to those files, or a notice indicating 401 | where to find the applicable terms. 402 | 403 | Additional terms, permissive or non-permissive, may be stated in the 404 | form of a separately written license, or stated as exceptions; 405 | the above requirements apply either way. 406 | 407 | 8. Termination. 408 | 409 | You may not propagate or modify a covered work except as expressly 410 | provided under this License. Any attempt otherwise to propagate or 411 | modify it is void, and will automatically terminate your rights under 412 | this License (including any patent licenses granted under the third 413 | paragraph of section 11). 414 | 415 | However, if you cease all violation of this License, then your 416 | license from a particular copyright holder is reinstated (a) 417 | provisionally, unless and until the copyright holder explicitly and 418 | finally terminates your license, and (b) permanently, if the copyright 419 | holder fails to notify you of the violation by some reasonable means 420 | prior to 60 days after the cessation. 421 | 422 | Moreover, your license from a particular copyright holder is 423 | reinstated permanently if the copyright holder notifies you of the 424 | violation by some reasonable means, this is the first time you have 425 | received notice of violation of this License (for any work) from that 426 | copyright holder, and you cure the violation prior to 30 days after 427 | your receipt of the notice. 428 | 429 | Termination of your rights under this section does not terminate the 430 | licenses of parties who have received copies or rights from you under 431 | this License. If your rights have been terminated and not permanently 432 | reinstated, you do not qualify to receive new licenses for the same 433 | material under section 10. 434 | 435 | 9. Acceptance Not Required for Having Copies. 436 | 437 | You are not required to accept this License in order to receive or 438 | run a copy of the Program. Ancillary propagation of a covered work 439 | occurring solely as a consequence of using peer-to-peer transmission 440 | to receive a copy likewise does not require acceptance. However, 441 | nothing other than this License grants you permission to propagate or 442 | modify any covered work. These actions infringe copyright if you do 443 | not accept this License. Therefore, by modifying or propagating a 444 | covered work, you indicate your acceptance of this License to do so. 445 | 446 | 10. Automatic Licensing of Downstream Recipients. 447 | 448 | Each time you convey a covered work, the recipient automatically 449 | receives a license from the original licensors, to run, modify and 450 | propagate that work, subject to this License. You are not responsible 451 | for enforcing compliance by third parties with this License. 452 | 453 | An "entity transaction" is a transaction transferring control of an 454 | organization, or substantially all assets of one, or subdividing an 455 | organization, or merging organizations. If propagation of a covered 456 | work results from an entity transaction, each party to that 457 | transaction who receives a copy of the work also receives whatever 458 | licenses to the work the party's predecessor in interest had or could 459 | give under the previous paragraph, plus a right to possession of the 460 | Corresponding Source of the work from the predecessor in interest, if 461 | the predecessor has it or can get it with reasonable efforts. 462 | 463 | You may not impose any further restrictions on the exercise of the 464 | rights granted or affirmed under this License. For example, you may 465 | not impose a license fee, royalty, or other charge for exercise of 466 | rights granted under this License, and you may not initiate litigation 467 | (including a cross-claim or counterclaim in a lawsuit) alleging that 468 | any patent claim is infringed by making, using, selling, offering for 469 | sale, or importing the Program or any portion of it. 470 | 471 | 11. Patents. 472 | 473 | A "contributor" is a copyright holder who authorizes use under this 474 | License of the Program or a work on which the Program is based. The 475 | work thus licensed is called the contributor's "contributor version". 476 | 477 | A contributor's "essential patent claims" are all patent claims 478 | owned or controlled by the contributor, whether already acquired or 479 | hereafter acquired, that would be infringed by some manner, permitted 480 | by this License, of making, using, or selling its contributor version, 481 | but do not include claims that would be infringed only as a 482 | consequence of further modification of the contributor version. For 483 | purposes of this definition, "control" includes the right to grant 484 | patent sublicenses in a manner consistent with the requirements of 485 | this License. 486 | 487 | Each contributor grants you a non-exclusive, worldwide, royalty-free 488 | patent license under the contributor's essential patent claims, to 489 | make, use, sell, offer for sale, import and otherwise run, modify and 490 | propagate the contents of its contributor version. 491 | 492 | In the following three paragraphs, a "patent license" is any express 493 | agreement or commitment, however denominated, not to enforce a patent 494 | (such as an express permission to practice a patent or covenant not to 495 | sue for patent infringement). To "grant" such a patent license to a 496 | party means to make such an agreement or commitment not to enforce a 497 | patent against the party. 498 | 499 | If you convey a covered work, knowingly relying on a patent license, 500 | and the Corresponding Source of the work is not available for anyone 501 | to copy, free of charge and under the terms of this License, through a 502 | publicly available network server or other readily accessible means, 503 | then you must either (1) cause the Corresponding Source to be so 504 | available, or (2) arrange to deprive yourself of the benefit of the 505 | patent license for this particular work, or (3) arrange, in a manner 506 | consistent with the requirements of this License, to extend the patent 507 | license to downstream recipients. "Knowingly relying" means you have 508 | actual knowledge that, but for the patent license, your conveying the 509 | covered work in a country, or your recipient's use of the covered work 510 | in a country, would infringe one or more identifiable patents in that 511 | country that you have reason to believe are valid. 512 | 513 | If, pursuant to or in connection with a single transaction or 514 | arrangement, you convey, or propagate by procuring conveyance of, a 515 | covered work, and grant a patent license to some of the parties 516 | receiving the covered work authorizing them to use, propagate, modify 517 | or convey a specific copy of the covered work, then the patent license 518 | you grant is automatically extended to all recipients of the covered 519 | work and works based on it. 520 | 521 | A patent license is "discriminatory" if it does not include within 522 | the scope of its coverage, prohibits the exercise of, or is 523 | conditioned on the non-exercise of one or more of the rights that are 524 | specifically granted under this License. You may not convey a covered 525 | work if you are a party to an arrangement with a third party that is 526 | in the business of distributing software, under which you make payment 527 | to the third party based on the extent of your activity of conveying 528 | the work, and under which the third party grants, to any of the 529 | parties who would receive the covered work from you, a discriminatory 530 | patent license (a) in connection with copies of the covered work 531 | conveyed by you (or copies made from those copies), or (b) primarily 532 | for and in connection with specific products or compilations that 533 | contain the covered work, unless you entered into that arrangement, 534 | or that patent license was granted, prior to 28 March 2007. 535 | 536 | Nothing in this License shall be construed as excluding or limiting 537 | any implied license or other defenses to infringement that may 538 | otherwise be available to you under applicable patent law. 539 | 540 | 12. No Surrender of Others' Freedom. 541 | 542 | If conditions are imposed on you (whether by court order, agreement or 543 | otherwise) that contradict the conditions of this License, they do not 544 | excuse you from the conditions of this License. If you cannot convey a 545 | covered work so as to satisfy simultaneously your obligations under this 546 | License and any other pertinent obligations, then as a consequence you may 547 | not convey it at all. For example, if you agree to terms that obligate you 548 | to collect a royalty for further conveying from those to whom you convey 549 | the Program, the only way you could satisfy both those terms and this 550 | License would be to refrain entirely from conveying the Program. 551 | 552 | 13. Use with the GNU Affero General Public License. 553 | 554 | Notwithstanding any other provision of this License, you have 555 | permission to link or combine any covered work with a work licensed 556 | under version 3 of the GNU Affero General Public License into a single 557 | combined work, and to convey the resulting work. The terms of this 558 | License will continue to apply to the part which is the covered work, 559 | but the special requirements of the GNU Affero General Public License, 560 | section 13, concerning interaction through a network will apply to the 561 | combination as such. 562 | 563 | 14. Revised Versions of this License. 564 | 565 | The Free Software Foundation may publish revised and/or new versions of 566 | the GNU General Public License from time to time. Such new versions will 567 | be similar in spirit to the present version, but may differ in detail to 568 | address new problems or concerns. 569 | 570 | Each version is given a distinguishing version number. If the 571 | Program specifies that a certain numbered version of the GNU General 572 | Public License "or any later version" applies to it, you have the 573 | option of following the terms and conditions either of that numbered 574 | version or of any later version published by the Free Software 575 | Foundation. If the Program does not specify a version number of the 576 | GNU General Public License, you may choose any version ever published 577 | by the Free Software Foundation. 578 | 579 | If the Program specifies that a proxy can decide which future 580 | versions of the GNU General Public License can be used, that proxy's 581 | public statement of acceptance of a version permanently authorizes you 582 | to choose that version for the Program. 583 | 584 | Later license versions may give you additional or different 585 | permissions. However, no additional obligations are imposed on any 586 | author or copyright holder as a result of your choosing to follow a 587 | later version. 588 | 589 | 15. Disclaimer of Warranty. 590 | 591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY 592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT 593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY 594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, 595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM 597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF 598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION. 599 | 600 | 16. Limitation of Liability. 601 | 602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING 603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS 604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY 605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE 606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF 607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD 608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), 609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF 610 | SUCH DAMAGES. 611 | 612 | 17. Interpretation of Sections 15 and 16. 613 | 614 | If the disclaimer of warranty and limitation of liability provided 615 | above cannot be given local legal effect according to their terms, 616 | reviewing courts shall apply local law that most closely approximates 617 | an absolute waiver of all civil liability in connection with the 618 | Program, unless a warranty or assumption of liability accompanies a 619 | copy of the Program in return for a fee. 620 | 621 | END OF TERMS AND CONDITIONS 622 | 623 | How to Apply These Terms to Your New Programs 624 | 625 | If you develop a new program, and you want it to be of the greatest 626 | possible use to the public, the best way to achieve this is to make it 627 | free software which everyone can redistribute and change under these terms. 628 | 629 | To do so, attach the following notices to the program. It is safest 630 | to attach them to the start of each source file to most effectively 631 | state the exclusion of warranty; and each file should have at least 632 | the "copyright" line and a pointer to where the full notice is found. 633 | 634 | {one line to give the program's name and a brief idea of what it does.} 635 | Copyright (C) {year} {name of author} 636 | 637 | This program is free software: you can redistribute it and/or modify 638 | it under the terms of the GNU General Public License as published by 639 | the Free Software Foundation, either version 3 of the License, or 640 | (at your option) any later version. 641 | 642 | This program is distributed in the hope that it will be useful, 643 | but WITHOUT ANY WARRANTY; without even the implied warranty of 644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 645 | GNU General Public License for more details. 646 | 647 | You should have received a copy of the GNU General Public License 648 | along with this program. If not, see . 649 | 650 | Also add information on how to contact you by electronic and paper mail. 651 | 652 | If the program does terminal interaction, make it output a short 653 | notice like this when it starts in an interactive mode: 654 | 655 | {project} Copyright (C) {year} {fullname} 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- 1 | init: 2 | pip install -r requirements.txt 3 | 4 | test: 5 | pip install -r requirements.txt 6 | python -m unittest discover . "*_test.py" -v -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 |

2 | 3 |

4 | 5 | **TokenQuery** is a query language over any labeled text (sequence of tokens); very similar to regular expressions but on top of tokens. TokenQuery can be viewed as an interface to query for specific patterns in a sequence of tokens using information provided by diverse NLP engines. 6 | 7 | 8 | ## What is a `Token`? 9 | In order to process text (natural language text), the common approach for natural language processing (NLP) is to break the text down into smaller processing units (tokens). Options include phonemes, morphemes, lexical information, phrases, sentences, or paragraphs. For example, this sentence :`President Obama delivered his Farewell Address in Chicago on January 10, 2017.` can be divided into tokens shown in blue highlights. 10 | 11 |

12 | 13 |

14 | Inside TokenQuery each token contains a text (textual content of token), start and end index of the span inside the original text and a set of labels (i.e. key/value pairs) provided by NLP engines. In our example, the red labels (POS tags) are coming from Stanford POS tagger, the orange labels are from Google NLP API, and purple ones are coming from an internal topic extractor. One of the challeneges for natural language processing, is the fact that each unit is providing isolated information about each token in different formats and currently is really hard to have a query considering labels coming from different processing units. 15 | 16 | TokenQuery enables us to 17 | - Combine labels from different NLP engines 18 | - Query and reasoning over tokenized text 19 | - Defining extentions for desired query functions 20 | 21 | The inital idea came from *Angel Chang* and *Christopher Manning* presented in [this paper](http://nlp.stanford.edu/pubs/tokensregex-tr-2014.pdf). They have implemeneted it (TOKENSREGEX) in Java inside *Stanford CoreNLP* software package. Our version uses a different language for the query which is extensible, more structured, and supporting more features. 22 | 23 | 24 | ## TokenQuery language 25 | The language is defined as follow. Each query consists of a group of tokens shown each inside `[` `]`s. If you want to use `]` inside your token matches you can simply use `\` to skip. 26 | 27 | 28 | ``` 29 | [expr_for_token1][expr_for_token2][expr_for_token3] 30 | ``` 31 | which means we are searching for a sequence of three tokens that the first token satisfies the condition provided by `expr_for_token1`, the second token satisfies the condition provided by `expr_for_token2` and so on. 32 | 33 | ## Quantifiers 34 | Likewise regular expressions, you can use quantifiers to have more compact queries. For example, the following query will match zero or more tokens satisfying the condition provided by `expr_for_token1` followed by another token satisfies condition provided by `expr_for_token2`. 35 | ``` 36 | [expr_for_token1]*[expr_for_token2] 37 | ``` 38 | | type | occurrence | example | 39 | | ---- | ---- | ---- | 40 | | `?` | once or not at all | `[expr_for_token]?` | 41 | | `*` | zero or more times | `[expr_for_token]*` | 42 | | `+` | one or more times | `[expr_for_token]+` | 43 | | `{x}` | x number of times | `[expr_for_token]{3}` | 44 | | `{x,y}` | between x and y number of times | `[expr_for_token]{3,5}` | 45 | 46 | ## Capturing Groups 47 | Like reguar expressions, you can define capturing groups by parentheses. 48 | for example `([expr_for_token1]+) [expr_for_token2] [expr_for_token3]` returns a group containing sequence of tokens with satisfies the condition provided by expr_for_token1. Hence, `([expr_for_token1]+) [expr_for_token2] ([expr_for_token3])` returns two groups (`chunk1` and `chunk2`) with a list of tokens matched inside each parentheses. You can also use named capturing by using `(name )`. For example `(name [expr_for_token1])` captures results under the name of `name`. 49 | If you don't provide any, it will capture all as a single group; in other words, `[expr_for_token1]+ [expr_for_token2] [expr_for_token3]` is equal to `([expr_for_token1]+ [expr_for_token2] [expr_for_token3])`. 50 | 51 | ## Token Expression 52 | Expressions (like `expr_for_token1` in the above examples) can be viewed as a list of acceptors for each token. 53 | 54 | ### Basic expressions 55 | `[label:operation(operation_input)]` is the base unit for defining a token expression, which means running `operation` on the value of `label` for this token returns if we should accept this token or not. `operation` is a function that accepts a token and optional extra setting string (`operation_input`) and returns `True` or `False`. 56 | For example, `[pos:str_eq(VBZ)]` matches any token that has a label `pos` and the string value for that is equal to `VBZ`. `str_eq` is an standard string operation check if the string is equal the extra setting string. 57 | or `[pos:str_reg(V.*)]` matches any token that has a `pos` label and the value for that label matches regex `V.*`. (i.e. any verbs) 58 | Note: If you want to check if a label exists or not and you don't care about the value of the label you can simply use this `[pos:str_reg(.*)]`. 59 | If no label provided the default will consider the text of the token. For example, `[str_reg(.*)]` will match any token or `[str_reg('painter')]` matches any token that has 'painter' as text. 60 | 61 | ### core operations (acceptors) 62 | Here is the list of predefined operations. You can extend this framework with your own defined operations. 63 | 64 | #### String 65 | This package provides string operations described below. 66 | 67 | | operation | description | examples | 68 | | ---- | ---- | ---- | 69 | | `str_eq` | string equals to extra setting string | `[str_eq(Obama)]` , `[pos:str_eq(VBZ)]` | 70 | | `str_reg` | string matches regex provided by extra setting string | `[str_req(an?)]`, `[pos:str_eq(V.*)]` | 71 | | `str_len` | lenght of the string compared to the value of extra setting string. (`==`, `>`, `<`, `!=` ,`>=`, `<=`) | `[str_len(=12)]`, `[ner:str_len(>6)]`, `[str_len(!=2)]` | 72 | 73 | **Shortened versions** 74 | For the convinence of use, exact string match is possible by having the text you want to match inside `"`s. 75 | For example `["painter"]` will match any token that its text is `painter` but not `Painter`. 76 | If you want to find tokens that matches a regex you can have your regex inside `/`s . For example `[/an?/]` matches tokens having text `a` or `an`. 77 | `[/Al.*/]` matches any token starting with `Al`. 78 | `[/km|kilometers?/]` matches `km`, `kilometer` and `kilometers` 79 | 80 | #### Int 81 | This package provides operations that will cast the value of labels into an integer and apply arithmetic operations on that. 82 | 83 | | operation | description | examples | 84 | | ---- | ---- | ---- | 85 | | `int_value` | casts the value of label into an integer and compare it to the integer provided by extra setting string (`==`, `>`, `<`, `!=` ,`>=`, `<=`) | `[int_value(==5)]` , `[month:int_value(>1)]`, `[year:int_value(>1990)]` | 86 | | `int_e` | casts the value of label into an integer and check if it is equal to int provided by extra setting string. | `[int_value(5)]` , `[month:int_value(1)]` | 87 | | `int_g` | `int_g(X)` is equivalent to use `int_value(>X)` | `[month:int_g(1)]` | 88 | | `int_l` | `int_l(X)` is equivalent to use `int_value(=X)` | `[int_ge(0)]` | 92 | 93 | #### Web 94 | This package provides operations for capturing meaningful web patterns. 95 | 96 | | operation | description | examples | 97 | | ---- | ---- | ---- | 98 | | `web_is_url` | the string is a web url | `[text:web_is_url()]` , `[freebase_id:web_is_url()]`| 99 | | `web_is_email` | the string is an email | `[text:web_is_email()]` , `[contact:web_is_email()]`| 100 | | `web_is_emoji` | the string is an emoji or emojicon | `[text:web_is_emoji()]` | 101 | | `web_is_hex_code` | the string is a hex code | `[color:web_is_hex_code()]` | 102 | | `web_is_hashtag` | the string is a hashtag | `[tag:web_is_hashtag()]` | 103 | 104 | #### Date 105 | This package provides operations for working with date and time info in iso format. 106 | 107 | | operation | description | examples | 108 | | ---- | ---- | ---- | 109 | | `date_is` | the date in iso format is same as extra setting string | `[date:date_is(2008-09-15T15:53:00)]`| 110 | | `date_is_after` | the date in iso format is after the date in extra setting string | `[date:date_is_after(2008-09-15)]` | 111 | | `date_is_before` | the date in iso format is before the date in extra setting string | `[date:date_is_before(2008-09-15)]` | 112 | | `date_y_is` | the year of the date in iso format is equal to the month in extra setting | `[date:date_y_is(2008)]` | 113 | | `date_m_is` | the month of the date in iso format is equal to the month in extra setting | `[date:date_m_is(9)]`, `[date:date_m_is(09)]`| 114 | | `date_d_is` | the day of the date in iso format is equal to the month in extra setting | `[date:date_y_is(15)]` | 115 | 116 | #### Vector 117 | 118 | | operation | description | examples | 119 | | ---- | ---- | ---- | 120 | | `vec_cos_sim` | cosine similarity between two vectors | `[word2vec:vec_cos_sim([1, 0, -2, 1.5]>0.5)]`| 121 | | `vec_cos_dist` | cosine distance between two vectors | `[word2vec:vec_cos_dist([1, 0, -2, 1.5]==0)]` | 122 | | `vec_man_dist` | manhattan distance between two vectors | `[word2vec:vec_man_dist([1, 0, -2, 1.5]>=10)]` | 123 | 124 | 125 | ## compound expressions 126 | For each token is possible to compound several basic expressions to support more complex patterns. Compounding is done using `!` (not), `&` (and) and `|` (or) symbols. For example, `[!pos:str_reg(V.*)]` means any token that it is not a verb. 127 | `[pos:str_reg(V.*)&!str_eq(is)]` matches any verb except `is`. 128 | The `!` has the highest proiority and the `&` and `|` has same priority and right associative. You can change the priority by using parentheses. 129 | ``` 130 | !X and Y <=> ( (!(X)) and Y ) 131 | !(X and Y) <=> ( !(X and Y) ) 132 | !(X and Y) or Z <=> ( ( !(X and Y) ) or Z ) 133 | (X and Y) or Z <=> ( ( X and Y) or Z ) 134 | X and Y or Z <=> ( X and (Y or Z) ) 135 | ``` 136 | 137 | # How to install 138 | ``` 139 | pip install tokenquery 140 | ``` 141 | It has been test to work on python 2.7+ 142 | 143 | ## How to use 144 | You can use your own tokenizer and create tokens or use our nltk wrapper to do the tokenization (see examples). 145 | We highly recommend to use a tokenizer that provides start and end of each token in the original text and the normalized value. This is surprizing helpful for visualization and debugging. For instance NLTK PTB tokenizer does not provide these info; so we wrote an script to estimate these from the output for our goal. 146 | Yes, this tool can be seen as an attempt to combine different types of information provided by NLP technologies considering using same tokenization. Currently we have integration with NLTK tokenizer and POS tagger and we are working to connect it to Spacy and google NLP API. 147 | 148 | ## NLP Examples 149 | We belive a big portion of NLP information can be expressed in terms of labels on top of tokens. Here is a list of the ones currently we use and how we represent it. 150 | - Part Of Speech tags (e.g. `[pos:/V.*/]`) 151 | 152 | - Lemma (e.g. `[lemma:'be']`) 153 | 154 | - Named-Entity tags (e.g. `[ner:"PERSON"]`) 155 | 156 | - Brown clusters 157 | 158 | | label | We | need | a | lawyer | . | 159 | |----|----|----|----|----|----| 160 | | POS | `PRP` | `VBP` | `DT` | `NN` | `.` | 161 | | bcluster| | | |`1000001101000` | 162 | 163 | And we can query members inside a cluster by tokenquery like this: 164 | `[bcluster:/100000110[0-1]+/])` 165 | which will match all of these and more. (for more info see Miller et al., NAACL 2004) 166 | 167 | | word | code | 168 | |--------|-----| 169 | | lawyer | 1000001101000 | 170 | | newspaperman | 100000110100100 | 171 | | stewardess | 100000110100101 | 172 | | toxicologist | 10000011010011 | 173 | | slang | 1000001101010 | 174 | | babysitter | 100000110101100 | 175 | | conspirator | 1000001101011010 | 176 | | womanizer | 1000001101011011 | 177 | | mailman | 10000011010111 | 178 | | salesman | 100000110110000 | 179 | | bookkeeper | 1000001101100010 | 180 | | troubleshooter | 10000011011000110 | 181 | | bouncer | 10000011011000111 | 182 | | technician | 1000001101100100 | 183 | | janitor | 1000001101100101 | 184 | | saleswoman | 1000001101100110 | 185 | 186 | 187 | - Word embeddings 188 | For word embeddings you can use exact match. You can also define fancy metrics for comparision like cosine similarity as an operation. implemente more like . 189 | e.g. `[w2v:cos_sim(A0F892<0.5)])` 190 | 191 | #### Chunks and Phrases 192 | For chunks we recommend to use IOB formatting. 193 | 194 | - Noun phrases 195 | We use label `N-PH` for noun phrase, `B-NP` as a value for starting a noun phrase and `I-NP` for Continue of a noun phrase. Or you can use directly `B-NP` as lable and keep the value for the id of that phrase in your knowledge base if any. 196 | 197 | ### Examples 198 | 199 | #### Detecting name of painters 200 | ``` 201 | from tokenquery.nlp.tokenizer import Tokenizer 202 | from tokenquery.nlp.pos_tagger import POSTagger 203 | from tokenquery.tokenquery import TokenQuery 204 | 205 | # Penn Tree Bank Tokenizer 206 | tokenizer = Tokenizer('PTBTokenizer') 207 | # NLTK POS tagger 208 | pos_tagger = POSTagger() 209 | 210 | # Test sentence 211 | input_text = 'David is a painter and I work as a writer.' 212 | # Tokenizing the sentence 213 | input_tokens = tokenizer.tokenize(input_text) 214 | # adding pos tags 215 | input_tokens = pos_tagger.tag(input_tokens) 216 | 217 | # token regex to extract name of the painters 218 | token_query_1 = TokenQuery('([pos:"NNP"]) [pos:"VBZ"] [/an?/] ["painter"]') 219 | token_query_1.match_tokens(input_tokens) 220 | 221 | # lets change the sentence 222 | input_text = 'David is a famous painter and I work as a writer.' 223 | input_tokens = tokenizer.tokenize(input_text) 224 | input_tokens = pos_tagger.tag(input_tokens) 225 | 226 | # because of `famous` now your token regex 1 isn't working anymore 227 | token_query_1.match_tokens(input_tokens) 228 | 229 | # Adding possible adjectives 230 | token_query_2 = TokenQuery('([pos:"NNP"]) [pos:"VBZ"] [/an?/] [pos:"JJ"]* ["painter"]') 231 | token_query_2.match_tokens(input_tokens) 232 | 233 | # You can add labels directly 234 | input_tokens[0].add_a_label('ner', 'PERSON') 235 | 236 | # A mixture of labels will give you the same result 237 | token_query_3 = TokenQuery('([ner:"PERSON"]) [pos:"VBZ"] [/an?/] [pos:"JJ"]* ["painter"]') 238 | token_query_3.match_tokens(input_tokens) 239 | 240 | # To cover names with more tokens 241 | token_query_4 = TokenQuery('([ner:"PERSON"]+) [pos:"VBZ"] [/an?/] [pos:"JJ"]* ["painter"]') 242 | token_query_4.match_tokens(input_tokens) 243 | 244 | ``` -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | nltk 2 | conllu 3 | google-api-python-client 4 | scipy 5 | sklearn -------------------------------------------------------------------------------- /resources/TokenQuery_example_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ramtinms/tokenquery/a6bcba2f40c7e9d0e0851b24bddad5d6dd25b273/resources/TokenQuery_example_1.png -------------------------------------------------------------------------------- /resources/Token_query_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ramtinms/tokenquery/a6bcba2f40c7e9d0e0851b24bddad5d6dd25b273/resources/Token_query_logo.png -------------------------------------------------------------------------------- /resources/TokenrRegex_logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ramtinms/tokenquery/a6bcba2f40c7e9d0e0851b24bddad5d6dd25b273/resources/TokenrRegex_logo.png -------------------------------------------------------------------------------- /setup.cfg: -------------------------------------------------------------------------------- 1 | [metadata] 2 | description-file = README.md 3 | 4 | -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from distutils.core import setup 2 | from setuptools import find_packages 3 | setup( 4 | name='tokenquery', 5 | packages=find_packages(), 6 | version='0.1.0', 7 | description='Tokenquery - query language for tokens ', 8 | author='Ramtin Seraj', 9 | author_email='mehdizadeh.ramtin@gmail.com', 10 | url='https://github.com/ramtinms/tokenquery', 11 | download_url='https://github.com/ramtinms/tokenquery/tarball/0.1', 12 | keywords=['natural language processing', 'nlp', 'regex', 'regular expressions', 'tokenizer', 'query'], 13 | classifiers=['Intended Audience :: Information Technology', 14 | 'Intended Audience :: Science/Research', 15 | 'Topic :: Scientific/Engineering', 16 | 'Topic :: Scientific/Engineering :: Artificial Intelligence', 17 | 'Topic :: Scientific/Engineering :: Human Machine Interfaces', 18 | 'Topic :: Scientific/Engineering :: Information Analysis', 19 | 'Topic :: Text Processing', 20 | 'Topic :: Text Processing :: Filters', 21 | 'Topic :: Text Processing :: General', 22 | 'Topic :: Text Processing :: Indexing', 23 | 'Topic :: Text Processing :: Linguistic', 24 | ], 25 | install_requires=[ 26 | "requests", 27 | "nltk", 28 | "conllu", 29 | "google-api-python-client", 30 | "sklearn", 31 | ], 32 | 33 | ) 34 | -------------------------------------------------------------------------------- /tokenquery/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ramtinms/tokenquery/a6bcba2f40c7e9d0e0851b24bddad5d6dd25b273/tokenquery/__init__.py -------------------------------------------------------------------------------- /tokenquery/acceptors/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ramtinms/tokenquery/a6bcba2f40c7e9d0e0851b24bddad5d6dd25b273/tokenquery/acceptors/__init__.py -------------------------------------------------------------------------------- /tokenquery/acceptors/core/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ramtinms/tokenquery/a6bcba2f40c7e9d0e0851b24bddad5d6dd25b273/tokenquery/acceptors/core/__init__.py -------------------------------------------------------------------------------- /tokenquery/acceptors/core/date_opr.py: -------------------------------------------------------------------------------- 1 | import datetime 2 | import dateutil.parser 3 | 4 | # date (Iso format) 5 | # '2013-12-25T19:20:41.391393' 6 | 7 | 8 | def date_is(token_input, operation_input): 9 | # simple version compare two strings 10 | if 'T' in token_input: 11 | date1 = token_input.split('T')[0] 12 | else: 13 | date1 = token_input 14 | 15 | if 'T' in operation_input: 16 | date2 = operation_input.split('T')[0] 17 | else: 18 | date2 = operation_input 19 | 20 | if date1 == date2: 21 | return True 22 | 23 | return False 24 | 25 | 26 | def date_is_after(token_input, operation_input): 27 | # simple version compare two strings 28 | if 'T' in token_input: 29 | date1 = token_input.split('T')[0] 30 | else: 31 | date1 = token_input 32 | 33 | if 'T' in operation_input: 34 | date2 = operation_input.split('T')[0] 35 | else: 36 | date2 = operation_input 37 | 38 | if date1 > date2: 39 | return True 40 | 41 | return False 42 | 43 | 44 | def date_is_before(token_input, operation_input): 45 | # simple version compare two strings 46 | if 'T' in token_input: 47 | date1 = token_input.split('T')[0] 48 | else: 49 | date1 = token_input 50 | 51 | if 'T' in operation_input: 52 | date2 = operation_input.split('T')[0] 53 | else: 54 | date2 = operation_input 55 | 56 | if date1 < date2: 57 | return True 58 | 59 | return False 60 | 61 | 62 | def date_y_is(token_input, operation_input): 63 | if 'T' in token_input: 64 | date1 = token_input.split('T')[0] 65 | year = date1.split('-')[0] 66 | else: 67 | year = token_input.split('-')[0] 68 | 69 | if year == operation_input: 70 | return True 71 | return False 72 | 73 | 74 | def date_m_is(token_input, operation_input): 75 | if 'T' in token_input: 76 | date1 = token_input.split('T')[0] 77 | month = date1.split('-')[1] 78 | else: 79 | month = token_input.split('-')[1] 80 | if month == operation_input: 81 | return True 82 | return False 83 | 84 | 85 | def date_d_is(token_input, operation_input): 86 | if 'T' in token_input: 87 | date1 = token_input.split('T')[0] 88 | day = date1.split('-')[2] 89 | else: 90 | day = token_input.split('-')[2] 91 | if day == operation_input: 92 | return True 93 | return False 94 | 95 | # def date_is_x_days_before(token_input, operation_input): 96 | # # utc = pytz.UTC 97 | # # publish_date = dateutil.parser.parse(selected_date) 98 | # # event_start = utc.localize(dateutil.parser.parse(event_start_date)) 99 | # # margin = datetime.timedelta(days=margin_days) 100 | # # if event_start - margin <= publish_date 101 | # # return True 102 | # # else: 103 | # # return False 104 | -------------------------------------------------------------------------------- /tokenquery/acceptors/core/int_opr.py: -------------------------------------------------------------------------------- 1 | def int_value(token_input, operation_input): 2 | # parsing operation_input 3 | 4 | cond_type = "" 5 | comp_part = operation_input.lstrip().strip()[:2] 6 | if comp_part in ['==', '>=', '<=', '!=', '<>']: 7 | cond_type = comp_part 8 | try: 9 | cond_value = int(operation_input.lstrip().strip()[2:]) 10 | except ValueError: 11 | # TODO raise tokenregex error 12 | return False 13 | elif comp_part[0] in ['=', '>', '<']: 14 | cond_type = comp_part[0] 15 | try: 16 | cond_value = int(operation_input.lstrip().strip()[1:]) 17 | except ValueError: 18 | # TODO raise tokenregex error 19 | return False 20 | 21 | try: 22 | text_value = int(token_input) 23 | if cond_type == "=" or cond_type == "==": 24 | return text_value == cond_value 25 | elif cond_type == "<": 26 | return text_value < cond_value 27 | elif cond_type == ">": 28 | return text_value > cond_value 29 | elif cond_type == ">=": 30 | return text_value >= cond_value 31 | elif cond_type == "<=": 32 | return text_value <= cond_value 33 | elif cond_type == "!=" or cond_type == "<>": 34 | return text_value != cond_value 35 | else: 36 | return False 37 | except ValueError: 38 | # TODO raise tokenregex error 39 | return False 40 | 41 | 42 | def int_e(token_input, operation_input): 43 | try: 44 | text_value = int(token_input) 45 | op_value = int(operation_input) 46 | return text_value == op_value 47 | except ValueError: 48 | # TODO raise tokenregex error 49 | return False 50 | 51 | 52 | def int_g(token_input, operation_input): 53 | try: 54 | text_value = int(token_input) 55 | op_value = int(operation_input) 56 | return text_value > op_value 57 | except ValueError: 58 | # TODO raise tokenregex error 59 | return False 60 | 61 | 62 | def int_l(token_input, operation_input): 63 | try: 64 | text_value = int(token_input) 65 | op_value = int(operation_input) 66 | return text_value < op_value 67 | except ValueError: 68 | # TODO raise tokenregex error 69 | return False 70 | 71 | 72 | def int_ne(token_input, operation_input): 73 | try: 74 | text_value = int(token_input) 75 | op_value = int(operation_input) 76 | return text_value != op_value 77 | except ValueError: 78 | # TODO raise tokenregex error 79 | return False 80 | 81 | 82 | def int_le(token_input, operation_input): 83 | try: 84 | text_value = int(token_input) 85 | op_value = int(operation_input) 86 | return text_value <= op_value 87 | except ValueError: 88 | # TODO raise tokenregex error 89 | return False 90 | 91 | 92 | def int_ge(token_input, operation_input): 93 | try: 94 | text_value = int(token_input) 95 | op_value = int(operation_input) 96 | return text_value >= op_value 97 | except ValueError: 98 | # TODO raise tokenregex error 99 | return False 100 | 101 | # TODO 102 | # add M , K , ... 103 | # add float 104 | -------------------------------------------------------------------------------- /tokenquery/acceptors/core/string_opr.py: -------------------------------------------------------------------------------- 1 | import re 2 | 3 | # String operations 4 | 5 | 6 | def str_eq(token_input, operation_input): 7 | if token_input == operation_input: 8 | return True 9 | return False 10 | 11 | 12 | def str_reg(token_input, operation_input): 13 | if not token_input: 14 | return False 15 | if re.match(operation_input, token_input): 16 | return True 17 | else: 18 | return False 19 | 20 | 21 | def str_len(token_input, operation_input): 22 | # parsing operation_input 23 | cond_type = '' 24 | comp_part = operation_input.lstrip().strip()[:2] 25 | if comp_part in ['==', '>=', '<=', '!=', '<>']: 26 | cond_type = comp_part 27 | try: 28 | cond_value = int(operation_input.lstrip().strip()[2:]) 29 | except ValueError: 30 | # TODO raise tokenregex error 31 | return False 32 | elif comp_part[0] in ['=', '>', '<']: 33 | cond_type = comp_part[0] 34 | try: 35 | cond_value = int(operation_input.lstrip().strip()[1:]) 36 | except ValueError: 37 | # TODO raise tokenregex error 38 | return False 39 | else: 40 | return 'unknown operation' 41 | 42 | try: 43 | text_len = len(token_input) 44 | if cond_type == "==" or cond_type == "=": 45 | return text_len == cond_value 46 | elif cond_type == "<": 47 | return text_len < cond_value 48 | elif cond_type == ">": 49 | return text_len > cond_value 50 | elif cond_type == ">=": 51 | return text_len >= cond_value 52 | elif cond_type == "<=": 53 | return text_len <= cond_value 54 | elif cond_type == "!=" or cond_type == "<>": 55 | return text_len != cond_value 56 | else: 57 | return False 58 | except ValueError: 59 | # TODO raise tokenregex error 60 | return False 61 | 62 | # TODO 63 | # def str_edit_dist(token_input, operation_input): 64 | # pass 65 | # has acrylic letters 66 | # is punctuation 67 | # is stop word 68 | # is a number : 2 two II 69 | -------------------------------------------------------------------------------- /tokenquery/acceptors/core/vector_opr.py: -------------------------------------------------------------------------------- 1 | from sklearn.metrics.pairwise import cosine_similarity 2 | from sklearn.metrics.pairwise import cosine_distances 3 | from sklearn.metrics.pairwise import manhattan_distances 4 | import numpy as np 5 | 6 | 7 | def change_string_to_vector(string): 8 | # comma seperated, spaces will be ignored 9 | vector = [] 10 | string = string.split('[')[1] 11 | string = string.split(']')[0] 12 | string = string.replace(r'\s', '') 13 | for value_string in string.split(','): 14 | vector.append(float(value_string)) 15 | return np.array(vector).reshape(1, -1) 16 | 17 | 18 | def vec_cos_sim(token_input, operation_input): 19 | operation_string = None 20 | ref_vector_string = None 21 | cond_value_string = None 22 | for opr_sign in ['==', '>=', '<=', '!=', '<>', '<', '>', '=']: 23 | if opr_sign in operation_input: 24 | ref_vector_string = operation_input.split(opr_sign)[0] 25 | operation_string = opr_sign 26 | cond_value_string = operation_input.split(opr_sign)[1] 27 | break 28 | 29 | if ref_vector_string and cond_value_string and operation_string: 30 | try: 31 | cond_value = float(cond_value_string) 32 | ref_vector = change_string_to_vector(ref_vector_string) 33 | token_vector = change_string_to_vector(token_input) 34 | if len(ref_vector) != len(token_vector): 35 | print ('len of vectors does not match') 36 | return False 37 | if operation_string == "=" or operation_string == "==": 38 | return cosine_similarity(token_vector, ref_vector) == cond_value 39 | elif operation_string == "<": 40 | return cosine_similarity(token_vector, ref_vector) < cond_value 41 | elif operation_string == ">": 42 | return cosine_similarity(token_vector, ref_vector) > cond_value 43 | elif operation_string == ">=": 44 | return cosine_similarity(token_vector, ref_vector) >= cond_value 45 | elif operation_string == "<=": 46 | return cosine_similarity(token_vector, ref_vector) <= cond_value 47 | elif operation_string == "!=" or operation_string == "<>": 48 | return cosine_similarity(token_vector, ref_vector) != cond_value 49 | else: 50 | return False 51 | except ValueError: 52 | # TODO raise tokenregex error 53 | return False 54 | 55 | else: 56 | # TODO raise tokenregex error 57 | print ('Problem with the operation input') 58 | 59 | 60 | def vec_cos_dist(token_input, operation_input): 61 | operation_string = None 62 | ref_vector_string = None 63 | cond_value_string = None 64 | for opr_sign in ['==', '>=', '<=', '!=', '<>', '<', '>', '=']: 65 | if opr_sign in operation_input: 66 | ref_vector_string = operation_input.split(opr_sign)[0] 67 | operation_string = opr_sign 68 | cond_value_string = operation_input.split(opr_sign)[1] 69 | break 70 | 71 | if ref_vector_string and cond_value_string and operation_string: 72 | try: 73 | cond_value = float(cond_value_string) 74 | ref_vector = change_string_to_vector(ref_vector_string) 75 | token_vector = change_string_to_vector(token_input) 76 | if len(ref_vector) != len(token_vector): 77 | print ('len of vectors does not match') 78 | return False 79 | if operation_string == "=" or operation_string == "==": 80 | return cosine_distances(token_vector, ref_vector) == cond_value 81 | elif operation_string == "<": 82 | return cosine_distances(token_vector, ref_vector) < cond_value 83 | elif operation_string == ">": 84 | return cosine_distances(token_vector, ref_vector) > cond_value 85 | elif operation_string == ">=": 86 | return cosine_distances(token_vector, ref_vector) >= cond_value 87 | elif operation_string == "<=": 88 | return cosine_distances(token_vector, ref_vector) <= cond_value 89 | elif operation_string == "!=" or operation_string == "<>": 90 | return cosine_distances(token_vector, ref_vector) != cond_value 91 | else: 92 | return False 93 | except ValueError: 94 | # TODO raise tokenregex error 95 | return False 96 | 97 | else: 98 | # TODO raise tokenregex error 99 | print ('Problem with the operation input') 100 | 101 | 102 | def vec_man_dist(token_input, operation_input): 103 | operation_string = None 104 | ref_vector_string = None 105 | cond_value_string = None 106 | for opr_sign in ['==', '>=', '<=', '!=', '<>', '<', '>', '=']: 107 | if opr_sign in operation_input: 108 | ref_vector_string = operation_input.split(opr_sign)[0] 109 | operation_string = opr_sign 110 | cond_value_string = operation_input.split(opr_sign)[1] 111 | break 112 | 113 | if ref_vector_string and cond_value_string and operation_string: 114 | try: 115 | cond_value = float(cond_value_string) 116 | ref_vector = change_string_to_vector(ref_vector_string) 117 | token_vector = change_string_to_vector(token_input) 118 | print(manhattan_distances(token_vector, ref_vector)) 119 | if len(ref_vector) != len(token_vector): 120 | print ('len of vectors does not match') 121 | return False 122 | if operation_string == "=" or operation_string == "==": 123 | return manhattan_distances(token_vector, ref_vector) == cond_value 124 | elif operation_string == "<": 125 | return manhattan_distances(token_vector, ref_vector) < cond_value 126 | elif operation_string == ">": 127 | return manhattan_distances(token_vector, ref_vector) > cond_value 128 | elif operation_string == ">=": 129 | return manhattan_distances(token_vector, ref_vector) >= cond_value 130 | elif operation_string == "<=": 131 | return manhattan_distances(token_vector, ref_vector) <= cond_value 132 | elif operation_string == "!=" or operation_string == "<>": 133 | return manhattan_distances(token_vector, ref_vector) != cond_value 134 | else: 135 | return False 136 | except ValueError: 137 | # TODO raise tokenregex error 138 | return False 139 | 140 | else: 141 | # TODO raise tokenregex error 142 | print ('Problem with the operation input') 143 | -------------------------------------------------------------------------------- /tokenquery/acceptors/core/web_opr.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | from tokenquery.acceptors.core.string_opr import str_reg 3 | 4 | 5 | def web_is_url(token_input): 6 | url_regex = r'^((http[s]?|ftp):\/)?\/?([^:\/\s]+)((\/\w+)*\/)([\w\-\.]+[^#?\s]+)(.*)?(#[\w\-]+)?$' 7 | return str_reg(token_input, url_regex) 8 | 9 | 10 | def web_is_email(token_input): 11 | email_regex = r"(^[mailto:]?[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$)" 12 | return str_reg(token_input, email_regex) 13 | 14 | 15 | def web_is_hex_code(token_input): 16 | hex_regex = r'^#([A-Fa-f0-9]{6}|[A-Fa-f0-9]{3})$' 17 | return str_reg(token_input, hex_regex) 18 | 19 | 20 | def web_is_hashtag(token_input): 21 | if token_input[0] == "#" and ' ' not in token_input: 22 | return True 23 | else: 24 | return False 25 | 26 | 27 | def web_is_emoji(token_input, operation_input): 28 | unicode_regex = r"()" 29 | if str_reg(token_input, unicode_regex): 30 | return True 31 | else: 32 | emojicons = r'(^|\s)(:D|:\/)(?=\s|[^[:alnum:]+-]|$)' 33 | return str_reg(token_input, emojicons) 34 | return False 35 | -------------------------------------------------------------------------------- /tokenquery/acceptors/extended/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ramtinms/tokenquery/a6bcba2f40c7e9d0e0851b24bddad5d6dd25b273/tokenquery/acceptors/extended/__init__.py -------------------------------------------------------------------------------- /tokenquery/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ramtinms/tokenquery/a6bcba2f40c7e9d0e0851b24bddad5d6dd25b273/tokenquery/models/__init__.py -------------------------------------------------------------------------------- /tokenquery/models/chunk.py: -------------------------------------------------------------------------------- 1 | import re 2 | 3 | 4 | class Chunk: 5 | """ Any sequence of tokens that shares a label, 6 | this can be used to stote sentences, entities 7 | and ... 8 | """ 9 | 10 | def __init__(self, chunk_id, tokens): 11 | self.chunk_id = chunk_id 12 | self.tokens = tokens 13 | self.start_span, self.end_span, self.text = change_tokenlist_to_chunk(tokens) 14 | 15 | def change_tokenlist_to_chunk(self, token_list): 16 | if not token_list: 17 | return None 18 | start_span = token_list[0].span_start 19 | end_span = token_list[0].span_end 20 | string = token_list[0].get_text() 21 | 22 | if len(token_list) == 1: 23 | return (start_span, end_span, string) 24 | 25 | else: 26 | for token in token_list[1:]: 27 | end_span = token.span_end 28 | string += ' ' + token.get_text() 29 | 30 | return (start_span, end_span, string) 31 | 32 | def add_a_label(self, label_name, label_value): 33 | for counter, token in enumerate(self.tokens): 34 | if counter == 0: 35 | token.add_a_label(label_name+'~B', label_value) 36 | else: 37 | token.add_a_label(label_name+'~I', label_value) 38 | 39 | def get_a_label(self, label_name): 40 | # ??? 41 | return self.tokens[0].get_a_label(label_name) 42 | 43 | def get_text(self): 44 | return self.text 45 | -------------------------------------------------------------------------------- /tokenquery/models/fsa.py: -------------------------------------------------------------------------------- 1 | class State: 2 | 3 | def __init__(self, state_name, capture_name, acceptors, is_final=False): 4 | self.transitions = [] 5 | self.state_name = state_name 6 | self.capture_name = capture_name 7 | self.acceptors = acceptors 8 | self.is_final = is_final 9 | 10 | def __str__(self): 11 | return self.state_name 12 | 13 | def get_state_name(self): 14 | return self.state_name 15 | 16 | def capture_name(self): 17 | return self.capture_name 18 | 19 | def accept(self, acceptor, token): 20 | # print (acceptor) 21 | if acceptor['type'] == 'comp_not': 22 | return not self.accept(acceptor['opr1'], token) 23 | 24 | elif acceptor['type'] == 'comp_and': 25 | res1 = self.accept(acceptor['opr1'], token) 26 | res2 = self.accept(acceptor['opr2'], token) 27 | return res1 and res2 28 | 29 | elif acceptor['type'] == 'comp_or': 30 | res1 = self.accept(acceptor['opr1'], token) 31 | res2 = self.accept(acceptor['opr2'], token) 32 | return res1 or res2 33 | 34 | elif acceptor['type'] in self.acceptors: 35 | opr_input = acceptor.get('opr_input', None) 36 | 37 | if acceptor['label'] == 'text': 38 | token_input = token.get_text() 39 | else: 40 | token_input = token.get_a_label(acceptor['label']) 41 | 42 | # if not token_input: 43 | # print ("something went wrong, token input is empty") 44 | 45 | if opr_input: 46 | return self.acceptors[acceptor['type']](token_input, opr_input) 47 | else: 48 | return self.acceptors[acceptor['type']](token_input) 49 | else: 50 | print ("something went wrong! unknown operation {}".format(acceptor['type'])) 51 | 52 | def next(self, input_token): 53 | nexts = [] 54 | for transition, next_state in self.transitions: 55 | if self.accept(transition, input_token): 56 | nexts.append(next_state) 57 | return nexts 58 | 59 | def add_a_next(self, segment_condition, next_state): 60 | self.transitions.append((segment_condition, next_state)) 61 | 62 | 63 | class StateMachine: 64 | 65 | def __init__(self, initialState, states, max_stack_size=200, verbose=False): 66 | self.currentState = initialState 67 | self.states = states 68 | self.max_stack_size = max_stack_size 69 | self.verbose = verbose 70 | 71 | def print_state_machine(self): 72 | print ("<>"*20) 73 | for state in self.states: 74 | print ('state name: ', state.state_name) 75 | print ('capture name :', state.capture_name) 76 | print ('is final :', state.is_final) 77 | for cond, next in state.transitions: 78 | print (cond, ' ---> ', next.state_name) 79 | 80 | # exuastive search 81 | def runAll(self, inputs): 82 | captured_dictionary = {} 83 | captured_info_item = [] 84 | capture_name = self.currentState.capture_name 85 | curser = 0 86 | # Stack 87 | stack = [(self.currentState, curser, captured_dictionary, captured_info_item, capture_name)] 88 | groups = [] 89 | 90 | # push down automata 91 | while stack and len(stack) < self.max_stack_size: 92 | currentState, curser, captured_dictionary, captured_info_item, capture_name = stack.pop() 93 | # print (currentState, curser, captured_dictionary, captured_info_item) 94 | # if captured_info_item: 95 | # print ('capturer : ', ' '.join([token.get_text() for token in captured_info_item])) 96 | 97 | if curser < len(inputs): 98 | token = inputs[curser] 99 | # print ('token : ', token.get_text()) 100 | # capturing 101 | nexts = currentState.next(token) 102 | if nexts: 103 | for next in nexts: 104 | if next.is_final: 105 | if captured_info_item: 106 | captured_dictionary[capture_name] = captured_info_item 107 | if captured_dictionary not in groups: 108 | groups.append(captured_dictionary) 109 | else: 110 | # print (token.get_text(), capture_name, next.capture_name, captured_info_item) 111 | if next.capture_name and not capture_name: 112 | # starting mode 113 | if token not in captured_info_item: 114 | captured_info_item.append(token) 115 | 116 | elif next.capture_name and next.capture_name == capture_name: 117 | if token not in captured_info_item: 118 | captured_info_item.append(token) 119 | 120 | elif next.capture_name != capture_name: 121 | if captured_info_item: 122 | captured_dictionary[capture_name] = captured_info_item 123 | captured_info_item = [] 124 | if next.capture_name: 125 | captured_info_item.append(token) 126 | 127 | capture_name = next.capture_name 128 | stack.append((next, curser+1, captured_dictionary, captured_info_item, capture_name)) 129 | else: 130 | if currentState.is_final: 131 | if captured_info_item: 132 | captured_dictionary[capture_name] = captured_info_item 133 | if captured_dictionary: 134 | if captured_dictionary not in groups: 135 | groups.append(captured_dictionary) 136 | 137 | return groups 138 | -------------------------------------------------------------------------------- /tokenquery/models/stack.py: -------------------------------------------------------------------------------- 1 | class Stack: 2 | def __init__(self, items=[]): 3 | self.items = items 4 | 5 | def is_empty(self): 6 | return self.items == [] 7 | 8 | def push(self, item): 9 | self.items.append(item) 10 | 11 | def pop(self): 12 | if not self.is_empty(): 13 | return self.items.pop() 14 | return None 15 | 16 | def peek(self): 17 | if len(self.items) > 0: 18 | return self.items[len(self.items)-1] 19 | else: 20 | return None 21 | 22 | def size(self): 23 | return len(self.items) 24 | -------------------------------------------------------------------------------- /tokenquery/models/token.py: -------------------------------------------------------------------------------- 1 | class Token: 2 | def __init__(self, token_id, token_text, span_start, span_end): 3 | self.token_id = token_id 4 | self.token_text = token_text 5 | self.span_start = span_start 6 | self.span_end = span_end 7 | self.labels = {} 8 | 9 | def get_token_id(self): 10 | return self.token_id 11 | 12 | def set_token_id(self, token_id): 13 | self.token_id = token_id 14 | 15 | def add_a_label(self, label_name, label_value): 16 | self.labels[label_name] = label_value 17 | 18 | def get_a_label(self, label_name): 19 | return self.labels.get(label_name, None) 20 | 21 | def set_text(self, text): 22 | self.token_text = text 23 | 24 | def get_text(self): 25 | return self.token_text 26 | 27 | def set_span(self, span_start, span_end): 28 | self.span_start = span_start 29 | self.span_end = span_end 30 | 31 | def get_span(self): 32 | return (self.span_start, self.span_end) 33 | 34 | def print_token(self): 35 | print ('token_id', self.token_id) 36 | print ('token_text', self.token_text) 37 | print ('span_start', self.span_start) 38 | print ('span_end', self.span_end) 39 | for label in self.labels: 40 | print (label, self.labels[label]) 41 | -------------------------------------------------------------------------------- /tokenquery/nlp/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ramtinms/tokenquery/a6bcba2f40c7e9d0e0851b24bddad5d6dd25b273/tokenquery/nlp/__init__.py -------------------------------------------------------------------------------- /tokenquery/nlp/google_nlp_api.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python 2 | # Copyright 2016 Google Inc. All Rights Reserved. 3 | # 4 | # Licensed under the Apache License, Version 2.0 (the "License"); 5 | # you may not use this file except in compliance with the License. 6 | # You may obtain a copy of the License at 7 | # 8 | # http://www.apache.org/licenses/LICENSE-2.0 9 | # 10 | # Unless required by applicable law or agreed to in writing, software 11 | # distributed under the License is distributed on an "AS IS" BASIS, 12 | # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 13 | # See the License for the specific language governing permissions and 14 | # limitations under the License. 15 | 16 | import argparse 17 | import sys 18 | import textwrap 19 | import json 20 | 21 | from googleapiclient import discovery 22 | import httplib2 23 | from oauth2client.client import GoogleCredentials 24 | 25 | from tokenquery.models.token import Token 26 | 27 | ################################ 28 | #### Google API functions #### 29 | ################################ 30 | 31 | def call_google_nlp(text): 32 | """Use the NL API to analyze the given text string, and returns the 33 | response from the API. Requests an encodingType that matches 34 | the encoding used natively by Python. Raises an 35 | errors.HTTPError if there is a connection problem. 36 | """ 37 | 38 | # TODO check cred exists .... 39 | 40 | # check GOOGLE_APPLICATION_CREDENTIALS 41 | credentials = GoogleCredentials.get_application_default() 42 | scoped_credentials = credentials.create_scoped( 43 | ['https://www.googleapis.com/auth/cloud-platform']) 44 | http = httplib2.Http() 45 | scoped_credentials.authorize(http) 46 | service = discovery.build( 47 | 'language', 'v1beta1', http=http) 48 | body = { 49 | 'document': { 50 | 'type': 'PLAIN_TEXT', 51 | 'content': text 52 | }, 53 | 'features': { 54 | # 'extract_syntax': True, 55 | 'extractEntities': True 56 | }, 57 | 'encodingType': get_native_encoding_type(), 58 | } 59 | request = service.documents().annotateText(body=body) 60 | return request.execute() 61 | 62 | def get_native_encoding_type(): 63 | """Returns the encoding type that matches Python's native strings.""" 64 | if sys.maxunicode == 65535: 65 | return 'UTF16' 66 | else: 67 | return 'UTF32' 68 | 69 | 70 | def get_tokens(text): 71 | final_tokens = [] 72 | tokens = call_google_nlp(text).get() 73 | for token in tokens: 74 | # begin = tokens[head_index]['text']['beginOffset'] 75 | # end = begin + len(tokens[head_index]['text']['content']) 76 | 77 | print (token) 78 | # Token() 79 | 80 | return final_tokens 81 | 82 | ################################ 83 | #### Dep-parsing Helpers #### 84 | ################################ 85 | 86 | def dependents(tokens, head_index): 87 | """Returns an ordered list of the token indices of the dependents for 88 | the given head.""" 89 | # Create head->dependency index. 90 | head_to_deps = {} 91 | for i, token in enumerate(tokens): 92 | head = token['dependencyEdge']['headTokenIndex'] 93 | if i != head: 94 | head_to_deps.setdefault(head, []).append(i) 95 | return head_to_deps.get(head_index, ()) 96 | 97 | def phrase_text_for_head(tokens, text, head_index): 98 | """Returns the entire phrase containing the head token 99 | and its dependents. 100 | """ 101 | begin, end = phrase_extent_for_head(tokens, head_index) 102 | return text[begin:end] 103 | 104 | 105 | def all_phrase_text_for_head(tokens, text, head_index): 106 | """Returns the entire phrase containing the head token 107 | and its dependents. 108 | """ 109 | results = [] 110 | for (begin, end) in all_phrases_for_head(tokens, head_index): 111 | results.append(text[begin:end]) 112 | return results 113 | 114 | 115 | def phrase_extent_for_head(tokens, head_index): 116 | """Returns the begin and end offsets for the entire phrase 117 | containing the head token and its dependents. 118 | """ 119 | begin = tokens[head_index]['text']['beginOffset'] 120 | end = begin + len(tokens[head_index]['text']['content']) 121 | for child in dependents(tokens, head_index): 122 | child_begin, child_end = phrase_extent_for_head(tokens, child) 123 | begin = min(begin, child_begin) 124 | end = max(end, child_end) 125 | return (begin, end) 126 | 127 | 128 | def all_phrases_for_head(tokens, head_index): 129 | """Returns the begin and end offsets for the entire phrase 130 | containing the head token and its dependents. 131 | """ 132 | results = [] 133 | begin = tokens[head_index]['text']['beginOffset'] 134 | end = begin + len(tokens[head_index]['text']['content']) 135 | head_begin = begin 136 | head_end = end 137 | 138 | results.append((begin, end)) 139 | for child in dependents(tokens, head_index): 140 | child_begin, child_end = phrase_extent_for_head(tokens, child) 141 | results.append((min(head_begin, child_begin), max(head_end, child_end))) 142 | begin = min(begin, child_begin) 143 | end = max(end, child_end) 144 | # TODO two combination 145 | # return (begin, end) 146 | return results 147 | 148 | 149 | if __name__ == "__main__": 150 | get_tokens("I love to travel.") 151 | -------------------------------------------------------------------------------- /tokenquery/nlp/importer.py: -------------------------------------------------------------------------------- 1 | from conllu.parser import parse, parse_tree 2 | from tokenquery.models.token import Token 3 | 4 | 5 | class Importer: 6 | 7 | @classmethod 8 | def load_from_conll_u_file(self, file_path): 9 | tokens = [] 10 | with open(file_path) as input_file: 11 | data = input_file.read() 12 | paresed_data = parse(data) 13 | total_counter = 0 14 | total_span_counter = 0 15 | for sent_counter, sentence in enumerate(paresed_data): 16 | for token_counter, token in enumerate(sentence): 17 | 18 | new_token = Token(total_counter, 19 | token['form'], 20 | total_span_counter, 21 | total_span_counter + len(token['form'])) 22 | 23 | total_span_counter += len(token['form']) + 1 24 | 25 | if token_counter == 0: 26 | new_token.add_a_label('SentenceBegin', str(sent_counter)) 27 | 28 | if token['lemma']: 29 | new_token.add_a_label('lemma', token.get('lemma')) 30 | 31 | if token['upostag']: 32 | new_token.add_a_label('upostag', token.get('upostag')) 33 | 34 | if token['xpostag']: 35 | new_token.add_a_label('xpostag', token.get('xpostag')) 36 | 37 | feats = token['feats'] 38 | if feats: 39 | for feat in feats: 40 | new_token.add_a_label('feat-' + feat, feats[feat]) 41 | 42 | if token['head']: 43 | new_token.add_a_label('head', str(token.get('head'))) 44 | 45 | if token['deprel']: 46 | new_token.add_a_label('deprel', str(token.get('deprel'))) 47 | 48 | if token['deps']: 49 | new_token.add_a_label('deps', token.get('deps')) 50 | 51 | misc = token['misc'] 52 | if misc: 53 | for feat in misc: 54 | new_token.add_a_label('misc-' + feat, misc[feat]) 55 | 56 | tokens.append(new_token) 57 | total_counter += 1 58 | 59 | return tokens 60 | -------------------------------------------------------------------------------- /tokenquery/nlp/pos_tagger.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | from nltk import pos_tag 3 | 4 | 5 | class POSTagger: 6 | """ 7 | NLTK pos tagger 8 | """ 9 | 10 | def __init__(self): 11 | try: 12 | nltk.data.find('taggers/averaged_perceptron_tagger/averaged_perceptron_tagger.pickle') 13 | except LookupError: 14 | nltk.download('averaged_perceptron_tagger') 15 | 16 | def tag(self, tokens): 17 | """ 18 | add pos tags to token objects 19 | 20 | :param tokens: list of token objects 21 | :type tokens: list(Token) 22 | :return: label augmented list of Token objects 23 | :rtype: list(Token) 24 | """ 25 | tags = pos_tag([token.get_text() for token in tokens]) 26 | for token, tag in zip(tokens, tags): 27 | token.add_a_label('pos', tag[1]) 28 | return tokens 29 | -------------------------------------------------------------------------------- /tokenquery/nlp/tokenizer.py: -------------------------------------------------------------------------------- 1 | import nltk 2 | from nltk.tokenize import word_tokenize 3 | from tokenquery.models.token import Token 4 | from nltk.tokenize.regexp import RegexpTokenizer 5 | from nltk.tokenize import WhitespaceTokenizer 6 | 7 | 8 | class Tokenizer: 9 | """ 10 | Tokenizer will break text into a list of Token objects. 11 | Currently it supports SpaceTokenizer, NLTKWhiteSpaceTokenizer, 12 | and PTBTokenizer (default) using NLTK lib. Since NLTK PTBTokenizer 13 | does not provide spans for tokens, we have a wrapper 14 | over PTB tokenizer to capture start and end of the tokens 15 | but is currently in beta mode. please report any potential 16 | problems. 17 | 18 | :param tokenizer_type: type of tokenizer one of 'SpaceTokenizer', 19 | 'NLTKWhiteSpaceTokenizer', 'PTBTokenizer' 20 | :type tokenizer_type: str 21 | """ 22 | def __init__(self, tokenizer_type="PTBTokenizer"): 23 | 24 | # Sanity checks 25 | if tokenizer_type in ['SpaceTokenizer', 'NLTKWhiteSpaceTokenizer', 'PTBTokenizer']: 26 | self.tokenizer_type = tokenizer_type 27 | else: 28 | print ("Unrecognized tokenizer type : setting back to default (PTBTokenizer)") 29 | self.tokenizer_type = "PTBTokenizer" 30 | try: 31 | nltk.data.find('punkt.zip') 32 | except LookupError: 33 | nltk.download('punkt') 34 | 35 | def tokenize(self, text): 36 | """ 37 | tokenize text into a list of Token objects 38 | 39 | :param text: text to be tokenized (might contains several sentences) 40 | :type text: str 41 | :return: List of Token objects 42 | :rtype: list(Token) 43 | """ 44 | tokens = [] 45 | 46 | if self.tokenizer_type == "SpaceTokenizer": 47 | operator = RegexpTokenizer('\w+|\$[\d\.]+|\S+') 48 | for counter, span in enumerate(operator.span_tokenize(text)): 49 | new_token = Token(counter, text[span[0]:span[1]], span[0], span[1]) 50 | tokens.append(new_token) 51 | 52 | elif self.tokenizer_type == "NLTKWhiteSpaceTokenizer": 53 | operator = WhitespaceTokenizer() 54 | for counter, span in enumerate(operator.span_tokenize(text)): 55 | new_token = Token(counter, text[span[0]:span[1]], span[0], span[1]) 56 | tokens.append(new_token) 57 | 58 | elif self.tokenizer_type == "PTBTokenizer": 59 | ptb_tokens = word_tokenize(text) 60 | counter = 0 61 | for token, span in self._penn_treebank_tokens_with_spans(text, ptb_tokens): 62 | new_token = Token(counter, token, span[0], span[1]) 63 | counter += 1 64 | tokens.append(new_token) 65 | 66 | return tokens 67 | 68 | def _penn_treebank_tokens_with_spans(self, text, tokens): 69 | text_from_tokens = "" 70 | 71 | for token in tokens: 72 | norm_token = token.replace('``', '"') \ 73 | .replace("''", '"') \ 74 | .replace('-LRB-', '(') \ 75 | .replace('-RRB-', ')') \ 76 | .replace('-LSB-', '[') \ 77 | .replace('-RSB-', ']') \ 78 | .replace('-LCB-', '{') \ 79 | .replace('-RCB-', '}') 80 | 81 | text_from_tokens += " " + norm_token 82 | text_from_tokens = text_from_tokens.strip().lstrip() 83 | spans = [] 84 | start_of_span = 0 85 | t_index = 0 86 | for t_f_t_index, t_char in enumerate(text_from_tokens): 87 | # assumption we dont have two space in a row for normalized text 88 | if t_char == " ": 89 | spans.append((start_of_span, t_index)) 90 | start_of_span = t_index 91 | continue 92 | if text[t_index].isspace(): 93 | while (text[t_index].isspace() and t_index < len(text)): 94 | t_index += 1 95 | start_of_span = t_index 96 | if text[t_index] != t_char: 97 | raise Exception("something went wrong while finding spans for PTB tokens {} does not match {}".format(text[t_index], t_char)) 98 | else: 99 | t_index += 1 100 | 101 | spans.append((start_of_span, t_index)) 102 | 103 | assert len(spans) == len(tokens) 104 | 105 | return zip(tokens, spans) 106 | -------------------------------------------------------------------------------- /tokenquery/tests/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/ramtinms/tokenquery/a6bcba2f40c7e9d0e0851b24bddad5d6dd25b273/tokenquery/tests/__init__.py -------------------------------------------------------------------------------- /tokenquery/tests/acceptors/core/int_opr_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.acceptors.int_opr import int_value 3 | from tokenquery.acceptors.int_opr import int_ne 4 | from tokenquery.acceptors.int_opr import int_e 5 | from tokenquery.acceptors.int_opr import int_l 6 | from tokenquery.acceptors.int_opr import int_le 7 | 8 | 9 | class TestIntegerCoreAcceptorsClass(unittest.TestCase): 10 | 11 | def test_integer_methods(self): 12 | self.assertEqual(int_value('5', '=5'), True) 13 | self.assertEqual(int_value('5.6', '>a'), False) 14 | self.assertEqual(int_value('3', '=5.3'), False) 15 | self.assertEqual(int_value('token', '=4'), False) 16 | self.assertEqual(int_value('21', '=21'), True) 17 | self.assertEqual(int_ne('6', '5'), True) 18 | self.assertEqual(int_e('6', '5'), False) 19 | self.assertEqual(int_e('5', '5'), True) 20 | self.assertEqual(int_l('5', '6'), True) 21 | self.assertEqual(int_le('4', '5'), True) 22 | self.assertEqual(int_le('5', '5'), True) 23 | 24 | if __name__ == '__main__': 25 | unittest.main() 26 | -------------------------------------------------------------------------------- /tokenquery/tests/acceptors/core/string_opr_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.acceptors.string_opr import str_eq 3 | from tokenquery.acceptors.string_opr import str_reg 4 | from tokenquery.acceptors.string_opr import str_len 5 | 6 | 7 | class TestStringCoreAcceptorsClass(unittest.TestCase): 8 | 9 | def test_string_methods(self): 10 | 11 | self.assertEqual(str_eq('equal', u'equal'), True) 12 | self.assertEqual(str_eq('equal', 'equal'), True) 13 | self.assertEqual(str_eq('equal', 'nequal'), False) 14 | self.assertEqual(str_reg('equal', 'eq.*'), True) 15 | self.assertEqual(str_reg('equal', '^eq.*'), True) 16 | self.assertEqual(str_reg('equal', 'neq.*'), False) 17 | self.assertEqual(str_reg('equal', '(eq.*)'), True) 18 | self.assertEqual(str_len('token', ',5'), True) 19 | self.assertEqual(str_len('token', '=5'), True) 20 | self.assertEqual(str_len('token', '>a'), False) 21 | self.assertEqual(str_len('token', ',5.3'), False) 22 | self.assertEqual(str_len('token', ',4'), False) 23 | self.assertEqual(str_len('token', ',-1'), False) 24 | 25 | if __name__ == '__main__': 26 | unittest.main() 27 | -------------------------------------------------------------------------------- /tokenquery/tests/acceptors/core/vector_opr_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.acceptors.vector_opr import change_string_to_vector 3 | from tokenquery.acceptors.vector_opr import vec_cos_sim 4 | from tokenquery.acceptors.vector_opr import vec_cos_dist 5 | from tokenquery.acceptors.vector_opr import vec_man_dist 6 | 7 | 8 | class TestVectorCoreAcceptorsClass(unittest.TestCase): 9 | 10 | def test_change_to_vector_method(self): 11 | self.assertEqual(change_string_to_vector('[0, 1, 0.06, 3,4,5.4, 0.0, -1]'), 12 | [0.0, 1.0, 0.06, 3.0, 4.0, 5.4, 0.0, -1.0]) 13 | 14 | def test_cos_sim_method(self): 15 | input_token_string = '[0.0, 1.0, 0.06, 3.0, 4.0, 5.4, 0.0]' 16 | param_string = '[0.0, 1.0, 0.06, 3.0, 4.0, 5.4, 0.0] > 0.5' 17 | self.assertEqual(vec_cos_sim(input_token_string, param_string), True) 18 | 19 | input_token_string = '[0.0, 1.0, 0.06, 3.0, 4.0, 5.4, 0.0]' 20 | param_string = '[12.0, -1.0, 1.00, 3.0, -4.0, 5.4, 0.0] > 0.5' 21 | self.assertEqual(vec_cos_sim(input_token_string, param_string), False) 22 | 23 | def test_cos_dist_method(self): 24 | input_token_string = '[0.0, 1.0, 0.06, 3.0, 4.0, 5.4, 0.0]' 25 | param_string = '[0.0, 1.0, 0.06, 3.0, 4.0, 5.4, 0.0] > 0.5' 26 | self.assertEqual(vec_cos_dist(input_token_string, param_string), False) 27 | 28 | input_token_string = '[0.0, 1.0, 0.06, 3.0, 4.0, 5.4, 0.0]' 29 | param_string = '[12.0, -1.0, 1.00, 3.0, -4.0, 5.4, 0.0] > 0.5' 30 | self.assertEqual(vec_cos_dist(input_token_string, param_string), True) 31 | 32 | def test_man_dist_method(self): 33 | input_token_string = '[0.0, 1.0, 0.06, 3.0, 4.0, 5.4, 0.0]' 34 | param_string = '[0.0, 1.0, 0.06, 3.0, 4.0, 5.4, 0.0] == 0' 35 | self.assertEqual(vec_man_dist(input_token_string, param_string), True) 36 | 37 | input_token_string = '[0.0, 1.0, 0.06, 3.0, 4.0, 5.4, 0.0]' 38 | param_string = '[12.0, -1.0, 1.00, 3.0, -4.0, 5.4, 0.0] > 20' 39 | self.assertEqual(vec_man_dist(input_token_string, param_string), True) 40 | 41 | 42 | if __name__ == '__main__': 43 | unittest.main() 44 | -------------------------------------------------------------------------------- /tokenquery/tests/acceptors/core/web_opr_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.acceptors.web_opr import web_is_url 3 | from tokenquery.acceptors.web_opr import web_is_email 4 | 5 | 6 | class TestWebCoreAcceptorsClass(unittest.TestCase): 7 | 8 | def test_web_methods(self): 9 | self.assertEqual(web_is_url('http://test.com'), True) 10 | self.assertEqual(web_is_url('localhost'), True) 11 | self.assertEqual(web_is_email('mailto:ramtin@yahoo.com'), True) 12 | self.assertEqual(web_is_email('ramtin@yahoo.com'), True) 13 | self.assertEqual(web_is_email('ramtin@yahoo.co.us'), True) 14 | self.assertEqual(web_is_email('yahoo.co.us'), False) 15 | 16 | if __name__ == '__main__': 17 | unittest.main() 18 | -------------------------------------------------------------------------------- /tokenquery/tests/models/fsa_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.models.fsa import State 3 | from tokenquery.models.fsa import StateMachine 4 | 5 | 6 | class TestFSAClass(unittest.TestCase): 7 | 8 | def test_state(self): 9 | test_state = State('state_name', 'capture_name', None) 10 | self.assertEqual(test_state.get_state_name(), True) 11 | 12 | # TODO add more test 13 | 14 | def test_state_machine(self): 15 | pass 16 | 17 | if __name__ == '__main__': 18 | unittest.main() 19 | -------------------------------------------------------------------------------- /tokenquery/tests/models/stack_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.models.stack import Stack 3 | 4 | 5 | class TestStackClass(unittest.TestCase): 6 | 7 | def test_stack(self): 8 | test_stack = Stack() 9 | 10 | self.assertEqual(test_stack.is_empty(), True) 11 | self.assertEqual(test_stack.size(), 0) 12 | self.assertEqual(test_stack.peek(), None) 13 | self.assertEqual(test_stack.pop(), None) 14 | test_stack.push('A') 15 | test_stack.push('B') 16 | test_stack.push('C') 17 | 18 | if __name__ == '__main__': 19 | unittest.main() 20 | -------------------------------------------------------------------------------- /tokenquery/tests/models/token_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.models.token import Token 3 | 4 | 5 | class TestTokenClass(unittest.TestCase): 6 | 7 | def test_token(self): 8 | test_token = Token(1, 'test_string', 12, 16) 9 | self.assertEqual(test_token.get_token_id(), 1) 10 | self.assertEqual(test_token.get_span(), (12, 16)) 11 | self.assertEqual(test_token.get_text(), 'test_string') 12 | 13 | test_token.add_a_label('test_label', 'test_label_value') 14 | self.assertEqual(test_token.get_a_label('test_label'), 'test_label_value') 15 | 16 | test_token.set_token_id('h1') 17 | self.assertEqual(test_token.get_token_id(), 'h1') 18 | 19 | test_token.set_text('test_string2') 20 | self.assertEqual(test_token.get_text(), 'test_string2') 21 | 22 | test_token.set_span(13, 17) 23 | self.assertEqual(test_token.get_span(), (13, 17)) 24 | 25 | 26 | if __name__ == '__main__': 27 | unittest.main() 28 | -------------------------------------------------------------------------------- /tokenquery/tests/nlp/data/test.conllu: -------------------------------------------------------------------------------- 1 | 1 The the DET DT Definite=Def|PronType=Art 4 det _ _ 2 | 2 quick quick ADJ JJ Degree=Pos 4 amod _ _ 3 | 3 brown brown ADJ JJ Degree=Pos 4 amod _ _ 4 | 4 fox fox NOUN NN Number=Sing 5 nsubj _ _ 5 | 5 jumps jump VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 0 root _ _ 6 | 6 over over ADP IN _ 9 case _ _ 7 | 7 the the DET DT Definite=Def|PronType=Art 9 det _ _ 8 | 8 lazy lazy ADJ JJ Degree=Pos 9 amod _ _ 9 | 9 dog dog NOUN NN Number=Sing 5 nmod _ SpaceAfter=No 10 | 10 . . PUNCT . _ 5 punct _ _ 11 | 12 | 1 The the DET DT Definite=Def|PronType=Art 4 det _ _ 13 | 2 quick quick ADJ JJ Degree=Pos 4 amod _ _ 14 | 3 brown brown ADJ JJ Degree=Pos 4 amod _ _ 15 | 4 fox fox NOUN NN Number=Sing 5 nsubj _ _ 16 | 5 jumps jump VERB VBZ Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin 0 root _ _ 17 | 6 over over ADP IN _ 9 case _ _ 18 | 7 the the DET DT Definite=Def|PronType=Art 9 det _ _ 19 | 8 lazy lazy ADJ JJ Degree=Pos 9 amod _ _ 20 | 9 dog dog NOUN NN Number=Sing 5 nmod _ SpaceAfter=No 21 | 10 . . PUNCT . _ 5 punct _ _ 22 | -------------------------------------------------------------------------------- /tokenquery/tests/nlp/importer_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.nlp.importer import Importer 3 | 4 | 5 | class TestImporter(unittest.TestCase): 6 | 7 | def test_load_conllu(self): 8 | tokens = Importer.load_from_conll_u_file('tokenquery/tests/nlp/data/test.conllu') 9 | expected_tokens = ['The', 'quick', 'brown', 'fox', 'jumps', 10 | 'over', 'the', 'lazy', 'dog', '.', 11 | 'The', 'quick', 'brown', 'fox', 'jumps', 12 | 'over', 'the', 'lazy', 'dog', '.'] 13 | self.assertListEqual(expected_tokens, [token.get_text() for token in tokens]) 14 | 15 | if __name__ == "__main__": 16 | unittest.main() 17 | -------------------------------------------------------------------------------- /tokenquery/tests/nlp/pos_tagger_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.nlp.tokenizer import Tokenizer 3 | from tokenquery.nlp.pos_tagger import POSTagger 4 | 5 | 6 | class TestPOSTagger(unittest.TestCase): 7 | 8 | def test_pos_tags(self): 9 | tokenizer = Tokenizer('PTBTokenizer') 10 | test_text = """ 11 | this cannot be true; I'm sure it was 2.8$, not $ 4 to buy @this #umbrella. this 12 | mentioned while shoping! Then he said: "you are responsible for this issue (extra price for fast-food and diet_coke) and \n I am 13 | not [happy] about it". Writer: xyz -- nyt 14 | """ 15 | tokens = tokenizer.tokenize(test_text) 16 | unit = POSTagger() 17 | updated_tokens = unit.tag(tokens) 18 | expected_tags = ['DT','MD','RB','VB','JJ',':','PRP', 19 | 'VBP','JJ','PRP','VBD','CD','$',',', 20 | 'RB','$','CD','TO','VB','NNP','DT', 21 | '#','NN','.','DT','JJ','NN','NN', 22 | 'VBD','IN','VBG','.','RB','PRP','VBD', 23 | ':','``','PRP','VBP','JJ','IN','DT', 24 | 'NN','(','JJ','NN','IN','NN','CC','NN', 25 | ')','CC','PRP','VBP','RB','NNP','JJ', 26 | 'NN','IN','PRP',"''",'.','NN',':','NN', 27 | ':','NN'] 28 | 29 | self.assertListEqual(expected_tags, [token.get_a_label('pos') for token in tokens]) 30 | 31 | if __name__ == "__main__": 32 | unittest.main() 33 | -------------------------------------------------------------------------------- /tokenquery/tests/nlp/tokenizer_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.nlp.tokenizer import Tokenizer 3 | 4 | 5 | class TestTokenizer(unittest.TestCase): 6 | 7 | def test_ptb_wrapper(self): 8 | unit = Tokenizer('PTBTokenizer') 9 | test_text = """ 10 | this cannot be true; I'm sure it was 2.8$, not $ 4 to buy @this #umbrella. this 11 | mentioned while shoping! Then he said: "you are responsible for this issue (extra price for fast-food and diet_coke) and \n I am 12 | not [happy] about it". Writer: xyz -- nyt 13 | """ 14 | 15 | expected_tokens = ['this','can','not','be','true',';','I','\'m', 16 | 'sure','it','was','2.8','$',',','not','$', 17 | '4','to','buy','@','this','#','umbrella', 18 | '.','this','<','sentence','>','mentioned', 19 | 'while','shoping','!','Then','he','said',':', 20 | '``','you','are','responsible','for','this','issue', 21 | '(','extra','price','for','fast-food','and', 22 | 'diet_coke',')','and','I','am','not','[','happy', 23 | ']','about','it',"''",'.','Writer',':','xyz','--','nyt'] 24 | tokens = unit.tokenize(test_text) 25 | self.assertListEqual(expected_tokens, [token.get_text() for token in tokens]) 26 | 27 | def test_ptb_utf8(self): 28 | unit = Tokenizer('PTBTokenizer') 29 | test_text = u""" 30 | «ταБЬℓσ»: 1<2 & 4+1>3, now 40% off! 31 | """ 32 | expected_tokens = [u'«ταБЬℓσ»',u':',u'1',u'<',u'2',u'&',u'4+1', 33 | u'>',u'3',u',',u'now',u'40',u'%',u'off',u'!'] 34 | tokens = unit.tokenize(test_text) 35 | self.assertListEqual(expected_tokens, [token.get_text() for token in tokens]) 36 | 37 | def test_space_tokenizer(self): 38 | unit = Tokenizer('SpaceTokenizer') 39 | test_text = """ 40 | this cannot be true; I'm sure it was 2.8$, not $ 4 to buy @this #umbrella. this 41 | mentioned while shoping! Then he said: "you are responsible for this issue (extra price for fast-food and diet_coke) and \n I am 42 | not [happy] about it". Writer: xyz -- nyt 43 | """ 44 | expected_tokens = ['this','cannot','be','true',';','I',"'m", 45 | 'sure','it','was','2','.8$,','not','$','4', 46 | 'to','buy','@this','#umbrella.','this', 47 | '','mentioned','while','shoping', 48 | '!','Then','he','said',':','"you','are','responsible', 49 | 'for','this','issue','(extra','price','for', 50 | 'fast','-food','and','diet_coke',')', 51 | 'and','I','am','not','[happy]','about', 52 | 'it','".','Writer',':','xyz','--','nyt'] 53 | 54 | 55 | tokens = unit.tokenize(test_text) 56 | self.assertListEqual(expected_tokens, [token.get_text() for token in tokens]) 57 | 58 | def test_nltk_white_space_tokenizer(self): 59 | unit = Tokenizer('NLTKWhiteSpaceTokenizer') 60 | test_text = """ 61 | this cannot be true; I'm sure it was 2.8$, not $ 4 to buy @this #umbrella. this 62 | mentioned while shoping! Then he said: "you are responsible for this issue (extra price for fast-food and diet_coke) and \n I am 63 | not [happy] about it". Writer: xyz -- nyt 64 | """ 65 | expected_tokens = ['this','cannot','be','true;',"I'm",'sure','it', 66 | 'was','2.8$,','not','$','4','to','buy','@this', 67 | '#umbrella.','this','','mentioned', 68 | 'while','shoping!','Then','he','said:','"you', 69 | 'are','responsible','for','this','issue', 70 | '(extra','price','for','fast-food','and','diet_coke)', 71 | 'and','I','am','not','[happy]','about','it".', 72 | 'Writer:','xyz','--','nyt'] 73 | 74 | 75 | tokens = unit.tokenize(test_text) 76 | self.assertListEqual(expected_tokens, [token.get_text() for token in tokens]) 77 | 78 | if __name__ == "__main__": 79 | unittest.main() 80 | -------------------------------------------------------------------------------- /tokenquery/tests/tokenquery_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | from tokenquery.nlp.tokenizer import Tokenizer 3 | from tokenquery.nlp.pos_tagger import POSTagger 4 | from tokenquery.tokenquery import TokenQuery 5 | 6 | 7 | class TestTokenQueryClass(unittest.TestCase): 8 | 9 | def show_results(self, result): 10 | for group in result: 11 | print ('==='*3) 12 | for chunk_name in group: 13 | print ('---' + chunk_name + '---') 14 | chunk = group[chunk_name] 15 | for token in chunk: 16 | print (token.get_token_id()) 17 | print (token.get_text()) 18 | 19 | def assert_result(self, result, desired_result): 20 | self.assertEqual(len(result), len(desired_result)) 21 | for group, desired_group in zip(result, desired_result): 22 | for chunk_name in group: 23 | self.assertIn(chunk_name, desired_group) 24 | chunk = group[chunk_name] 25 | desired_chunk = desired_group[chunk_name] 26 | for token, desired_token in zip(chunk, desired_chunk): 27 | self.assertEqual(token.get_token_id(), desired_token.get_token_id()) 28 | 29 | def test_regex_match(self): 30 | t = Tokenizer() 31 | input_tokens = t.tokenize('David is a painter and Ramtin Muller is an artist.') 32 | input_tokens[0].add_a_label('ner', 'PERSON') 33 | input_tokens[1].add_a_label('pos', 'VBZ') 34 | input_tokens[2].add_a_label('pos', 'DT') 35 | input_tokens[5].add_a_label('ner', 'PERSON') 36 | input_tokens[6].add_a_label('ner', 'PERSON') 37 | input_tokens[7].add_a_label('pos', 'VBZ') 38 | 39 | test_cases = [] 40 | desired_results = [] 41 | test_cases += ['[ner:"PERSON"]+ [pos:"VBZ"] [/an?/] [/artist|painter/]'] 42 | desired_results.append([{'chunk 1': input_tokens[:4]}, # David is a painter 43 | {'chunk 1': input_tokens[5:10]}] # Ramtin Muller is an artist 44 | ) 45 | 46 | # desired_results 47 | test_cases += ['([ner:"NUMBER"]+) [/km|kilometers?/]'] 48 | desired_results.append([]) 49 | 50 | test_cases += ['[ner:"PERSON"]? [pos:/V.*/]'] 51 | desired_results.append([{'chunk 1': input_tokens[:2]}, # David is 52 | {'chunk 1': input_tokens[6:8]}] # Muller is 53 | ) 54 | 55 | for test_case, desired_result in zip(test_cases, desired_results): 56 | # print('<>'*30) 57 | # print (test_case) 58 | # print('<>'*20) 59 | # unit = TokenQuery(test_case, verbose=True) 60 | unit = TokenQuery(test_case) 61 | result = unit.match_tokens(input_tokens) 62 | # self.show_results(result) 63 | self.assert_result(result, desired_result) 64 | 65 | def test_repetition(self): 66 | t = Tokenizer() 67 | input_tokens = t.tokenize('David is a painter and Ramtin Muller is an artist. Sir Isaac Newton ...') 68 | input_tokens[0].add_a_label('ner', 'PERSON') 69 | input_tokens[1].add_a_label('pos', 'VBZ') 70 | input_tokens[2].add_a_label('pos', 'DT') 71 | input_tokens[5].add_a_label('ner', 'PERSON') 72 | input_tokens[6].add_a_label('ner', 'PERSON') 73 | input_tokens[7].add_a_label('pos', 'VBZ') 74 | input_tokens[11].add_a_label('ner', 'PERSON') 75 | input_tokens[12].add_a_label('ner', 'PERSON') 76 | input_tokens[13].add_a_label('ner', 'PERSON') 77 | 78 | test_cases = [] 79 | desired_results = [] 80 | test_cases += ['[ner:str_eq(PERSON)]*'] # ??? 81 | desired_results.append([{'chunk 1': input_tokens[:1]}, # David 82 | {'chunk 1': input_tokens[5:7]}, # Ramtin Muller 83 | {'chunk 1': input_tokens[11:14]}] # Sir Isaac Newton 84 | ) 85 | 86 | test_cases += ['[ner:str_eq(PERSON)]?'] # ??? 87 | desired_results.append([{'chunk 1': input_tokens[:1]}, # David 88 | {'chunk 1': input_tokens[5:6]}, # Ramtin 89 | {'chunk 1': input_tokens[6:7]}, # Muller 90 | {'chunk 1': input_tokens[11:12]}, # Sir 91 | {'chunk 1': input_tokens[12:13]}, # Isaac 92 | {'chunk 1': input_tokens[13:14]}] # Newton 93 | ) 94 | 95 | test_cases += ['[ner:str_eq(PERSON)]+'] 96 | desired_results.append([{'chunk 1': input_tokens[:1]}, # David 97 | {'chunk 1': input_tokens[5:7]}, # Ramtin Muller 98 | {'chunk 1': input_tokens[11:14]}] # Sir Isaac Newton 99 | ) 100 | 101 | test_cases += ['[ner:str_eq(PERSON)]{2}'] 102 | desired_results.append([{'chunk 1': input_tokens[5:7]}, # Ramtin Muller 103 | {'chunk 1': input_tokens[11:13]}] # Sir Isaac 104 | ) 105 | 106 | test_cases += ['[ner:str_eq(PERSON)]{1,2}'] 107 | desired_results.append([{'chunk 1': input_tokens[:1]}, # David 108 | {'chunk 1': input_tokens[5:7]}, # Ramtin Muller 109 | {'chunk 1': input_tokens[11:13]}, # Sir Isaac 110 | {'chunk 1': input_tokens[13:14]}] # Newton 111 | ) 112 | 113 | # test range repetition 114 | # test_cases += ['[ner:str_eq(PERSON)]{1,3} [pos:str_eq(VBZ)]'] 115 | # test_cases += ['[ner:str_eq(PERSON)]{2,3} [pos:str_eq(VBZ)]'] 116 | # test_cases += ['[ner:str_eq(PERSON)]{3,6} [pos:str_eq(VBZ)]'] 117 | # test_cases += ['[ner:str_eq(PERSON)]{1,2} [pos:str_eq(VBZ)]'] 118 | # test_cases += ['[ner:str_eq(PERSON)]{1,6} [pos:str_eq(VBZ)]'] 119 | 120 | for test_case, desired_result in zip(test_cases, desired_results): 121 | # print('<>'*30) 122 | # print (test_case) 123 | # print('<>'*20) 124 | # unit = TokenQuery(test_case, verbose=True) 125 | unit = TokenQuery(test_case) 126 | result = unit.match_tokens(input_tokens) 127 | # self.show_results(result) 128 | self.assert_result(result, desired_result) 129 | 130 | 131 | def test_logics(self): 132 | t = Tokenizer() 133 | input_tokens = t.tokenize('David is a painter and Ramtin Muller is an artist. Sir Isaac Newton ...') 134 | input_tokens[0].add_a_label('ner', 'PERSON') 135 | input_tokens[1].add_a_label('pos', 'VBZ') 136 | input_tokens[2].add_a_label('pos', 'DT') 137 | input_tokens[5].add_a_label('ner', 'PERSON') 138 | input_tokens[6].add_a_label('ner', 'PERSON') 139 | input_tokens[7].add_a_label('pos', 'VBZ') 140 | input_tokens[11].add_a_label('ner', 'PERSON') 141 | input_tokens[12].add_a_label('ner', 'PERSON') 142 | input_tokens[13].add_a_label('ner', 'PERSON') 143 | 144 | test_cases = [] 145 | desired_results = [] 146 | 147 | test_cases += ['[ner:str_eq(PERSON)]+ [pos:str_eq(VBZ)] [/an?/] [str_eq(painter)]'] 148 | desired_results.append([{'chunk 1': input_tokens[0:4]}] # David is a painter 149 | ) 150 | 151 | test_cases += ['[ner:str_eq(PERSON)]+ [pos:str_eq(VBZ)] [/an?/] [str_eq(painter)|str_eq(artist)]'] 152 | desired_results.append([{'chunk 1': input_tokens[0:4]}, # David is a painter 153 | {'chunk 1': input_tokens[5:10]}] # Ramtin Muller is an artist 154 | ) 155 | 156 | test_cases += ['[ner:str_eq(PERSON)]+ [pos:str_eq(VBZ)] [/an?/] [(str_eq(painter)&str_reg(paint.*))|str_eq(artist)]'] 157 | desired_results.append([{'chunk 1': input_tokens[0:4]}, # David is a painter 158 | {'chunk 1': input_tokens[5:10]}] # Ramtin Muller is an artist 159 | ) 160 | 161 | test_cases += ['[ner:str_eq(PERSON)]+ [pos:str_eq(VBZ)] [/an?/&"a"] [str_eq(painter)]'] 162 | desired_results.append([{'chunk 1': input_tokens[0:4]}] # David is a painter 163 | ) 164 | 165 | test_cases += ['[ner:str_eq(PERSON)]+ [pos:str_eq(VBZ)] [/an?/&"an"] [str_eq(painter)]'] 166 | desired_results.append([]) 167 | 168 | test_cases += ['[ner:str_eq(PERSON)]+ [pos:str_eq(VBZ)] [/an?/&pos:"DT"] [str_eq(painter)]'] 169 | desired_results.append([{'chunk 1': input_tokens[0:4]}] # David is a painter 170 | ) 171 | 172 | test_cases += ['[ner:str_eq(PERSON)]+ [pos:str_eq(VBZ)] [/an?/&pos:str_eq(DT)] [str_eq(painter)]'] 173 | desired_results.append([{'chunk 1': input_tokens[0:4]}] # David is a painter 174 | ) 175 | 176 | # TODO add more test cases 177 | for test_case, desired_result in zip(test_cases, desired_results): 178 | # print('<>'*30) 179 | # print (test_case) 180 | # print('<>'*20) 181 | # unit = TokenQuery(test_case, verbose=True) 182 | unit = TokenQuery(test_case) 183 | result = unit.match_tokens(input_tokens) 184 | # self.show_results(result) 185 | self.assert_result(result, desired_result) 186 | 187 | def test_capturing(self): 188 | t = Tokenizer() 189 | input_tokens = t.tokenize('David is a painter and Ramtin Muller is an artist. Sir Isaac Newton ...') 190 | input_tokens[0].add_a_label('ner', 'PERSON') 191 | input_tokens[1].add_a_label('pos', 'VBZ') 192 | input_tokens[2].add_a_label('pos', 'DT') 193 | input_tokens[5].add_a_label('ner', 'PERSON') 194 | input_tokens[6].add_a_label('ner', 'PERSON') 195 | input_tokens[7].add_a_label('pos', 'VBZ') 196 | input_tokens[11].add_a_label('ner', 'PERSON') 197 | input_tokens[12].add_a_label('ner', 'PERSON') 198 | input_tokens[13].add_a_label('ner', 'PERSON') 199 | 200 | test_cases = [] 201 | desired_results = [] 202 | test_cases += ['[ner:"PERSON"]+ [pos:"VBZ"] [/an?/] ["painter"]'] 203 | desired_results.append([{'chunk 1': input_tokens[0:4]}] # David is a painter 204 | ) 205 | 206 | test_cases += ['([ner:"PERSON"]+) [pos:"VBZ"] [/an?/] ["painter"]'] 207 | desired_results.append([{'chunk 1': input_tokens[0:1]}] # David 208 | ) 209 | 210 | test_cases += ['([ner:"PERSON"]+ [pos:"VBZ"]) [/an?/] ["painter"]'] 211 | desired_results.append([{'chunk 1': input_tokens[0:2]}] # chunk1: David is 212 | ) 213 | 214 | test_cases += ['([ner:"PERSON"]+ [pos:"VBZ"] )[/an?/] ["painter"]'] 215 | desired_results.append([{'chunk 1': input_tokens[0:2]}] # chunk1: David is 216 | ) 217 | 218 | test_cases += ['[ner:"PERSON"]+ ([pos:"VBZ"] [/an?/] ["painter"])'] 219 | desired_results.append([{'chunk 1': input_tokens[1:4]}] # chunk1: is a painter 220 | ) 221 | 222 | test_cases += ['(person [ner:"PERSON"]+) (rest [pos:"VBZ"] [/an?/] ["painter"])'] 223 | desired_results.append([{'person': input_tokens[0:1], 'rest': input_tokens[1:4]}] # person: David rest :is a painter 224 | ) 225 | 226 | test_cases += ['(person [ner:"PERSON"])+ (rest [pos:"VBZ"] [/an?/] ["painter"|"artist"])'] 227 | desired_results.append([{'person': input_tokens[0:1], 'rest': input_tokens[1:4]}, # person: David rest :is a painter 228 | {'person': input_tokens[5:7], 'rest': input_tokens[7:10]} # person: Ramtin Muller rest :is an artist 229 | ] 230 | ) 231 | 232 | for test_case, desired_result in zip(test_cases, desired_results): 233 | # print('<>'*30) 234 | # print (test_case) 235 | # print('<>'*20) 236 | # unit = TokenQuery(test_case, verbose=True) 237 | unit = TokenQuery(test_case) 238 | # unit.machine.print_state_machine() 239 | result = unit.match_tokens(input_tokens) 240 | # self.show_results(result) 241 | self.assert_result(result, desired_result) 242 | 243 | if __name__ == "__main__": 244 | unittest.main() 245 | -------------------------------------------------------------------------------- /tokenquery/tokenquery.py: -------------------------------------------------------------------------------- 1 | from tokenquery.models.fsa import StateMachine 2 | from tokenquery.models.fsa import State 3 | from tokenquery.models.stack import Stack 4 | from tokenquery.acceptors.core.string_opr import str_eq 5 | from tokenquery.acceptors.core.string_opr import str_reg 6 | from tokenquery.acceptors.core.string_opr import str_len 7 | from tokenquery.acceptors.core.int_opr import * 8 | from tokenquery.acceptors.core.web_opr import * 9 | 10 | 11 | class TokenQuery: 12 | 13 | def __init__(self, token_query_string, verbose=False): 14 | self.acceptors = {} 15 | self.acceptors['str_eq'] = str_eq 16 | self.acceptors['str_reg'] = str_reg 17 | self.acceptors['str_len'] = str_len 18 | self.verbose = verbose 19 | parsed_token_query_string = self.parse(token_query_string) 20 | if self.verbose: 21 | print (parsed_token_query_string) 22 | self.machine = self.compile(parsed_token_query_string) 23 | if self.verbose: 24 | self.machine.print_state_machine() 25 | 26 | def match_tokens(self, input_tokens): 27 | final_results = [] 28 | # ranges = {} 29 | last_matched = -1 30 | for start_point in range(len(input_tokens)): 31 | # skip from the matched ones 32 | if start_point > last_matched: 33 | sub_input_tokens = input_tokens[start_point:] 34 | result_set = self.machine.runAll(sub_input_tokens) 35 | if result_set: 36 | final_results += result_set 37 | for result_item in result_set: 38 | for group_key in result_item: 39 | group = result_item[group_key] 40 | if len(group) > 0: 41 | last_matched_token = group[-1].get_token_id() 42 | if last_matched_token > last_matched: 43 | last_matched = last_matched_token 44 | 45 | # change into max match 46 | 47 | # for result in result_set: 48 | # ranges.append(range(result[0],result[0]) 49 | return final_results 50 | 51 | def parse(self, token_query_string): 52 | """ 53 | Parsing token query string 54 | """ 55 | 56 | parser_stack = Stack() 57 | 58 | parsed = [] 59 | capturing_inside_a_token_mode = False 60 | capturing_expr_for_token_mode = False 61 | capture_chunk_id = 1 62 | capture_mode_name = None 63 | 64 | not_mode = False 65 | repetition_capture_mode = False 66 | repetition = 0 67 | 68 | # shorthand modes 69 | expr_regex_shorthand_mode = False 70 | expr_string_shorthand_mode = False 71 | 72 | for next_char in token_query_string: 73 | if self.verbose: 74 | print ('next char : ', next_char) 75 | print ('current stack : ', parser_stack.items) 76 | # print ('capturing_inside_a_token_mode : ', capturing_inside_a_token_mode) 77 | # print ('expr_regex_shorthand_mode : ', expr_regex_shorthand_mode) 78 | # print ('expr_string_shorthand_mode : ', expr_string_shorthand_mode) 79 | # ignore white spaces 80 | if next_char.isspace(): 81 | continue 82 | 83 | # inside a token 84 | if capturing_inside_a_token_mode: 85 | 86 | # inside an expression 87 | if capturing_expr_for_token_mode: 88 | 89 | # String shorthand mode 90 | if expr_string_shorthand_mode: 91 | if next_char == '"': 92 | active_operation['type'] = 'str_eq' 93 | active_operation['opr_input'] = capturer 94 | expr_string_shorthand_mode = False 95 | capturer = "" 96 | parser_stack.push(active_operation) 97 | capturing_expr_for_token_mode = False 98 | continue 99 | else: 100 | capturer += next_char 101 | 102 | # Regex shorthand mode 103 | elif expr_regex_shorthand_mode: 104 | if next_char == '/': 105 | active_operation['type'] = 'str_reg' 106 | active_operation['opr_input'] = capturer 107 | expr_regex_shorthand_mode = False 108 | capturer = "" 109 | parser_stack.push(active_operation) 110 | capturing_expr_for_token_mode = False 111 | continue 112 | else: 113 | capturer += next_char 114 | 115 | # Normal mode 116 | else: 117 | # go to string shorthand mode 118 | if capturer == '"': 119 | capturer = next_char 120 | expr_string_shorthand_mode = True 121 | continue 122 | 123 | # go to regex shorthand mode 124 | if capturer == '/': 125 | capturer = next_char 126 | expr_regex_shorthand_mode = True 127 | continue 128 | 129 | # end of label 130 | if next_char == ':': 131 | # previous captured thing is a label 132 | active_operation['label'] = capturer 133 | capturer = "" 134 | 135 | # start of operation 136 | elif next_char == '(': 137 | # previous captured thing is a label 138 | active_operation['type'] = capturer 139 | capturer = "" 140 | 141 | # end of operation 142 | elif next_char == ')': 143 | # push a new operation 144 | if capturer: 145 | active_operation['opr_input'] = capturer 146 | 147 | # if not mode 148 | if not_mode: 149 | negated_operation = {'opr1': active_operation, 150 | 'type': 'comp_not'} 151 | not_mode = False 152 | parser_stack.push(negated_operation) 153 | 154 | # adding new operation 155 | else: 156 | parser_stack.push(active_operation) 157 | capturing_expr_for_token_mode = False 158 | 159 | # add char to the capturer 160 | else: 161 | capturer += next_char 162 | 163 | # deal with this later 164 | # if char == '"': 165 | # capturing_expr_for_token_mode = True 166 | 167 | # if next_char == "\\" and not scape_mode: 168 | # scape_mode = True 169 | 170 | # outside an expression (compounding stuff) 171 | else: 172 | if next_char == "(": 173 | parser_stack.push('(') 174 | elif next_char == "&": 175 | parser_stack.push('&') 176 | elif next_char == "|": 177 | parser_stack.push('|') 178 | elif next_char == "!": 179 | not_mode = True 180 | 181 | elif next_char == ")": 182 | while(parser_stack.size() > 2): 183 | item2 = parser_stack.pop() 184 | op = parser_stack.pop() 185 | item1 = parser_stack.pop() 186 | if op == '&': 187 | new_acceptor = {'opr1': item1, 188 | 'opr2': item2, 189 | 'type': 'comp_and'} 190 | if op == "|": 191 | new_acceptor = {'opr1': item1, 192 | 'opr2': item2, 193 | 'type': 'comp_or'} 194 | 195 | if parser_stack.size() == 0: 196 | parser_stack.push(new_acceptor) 197 | break 198 | 199 | if parser_stack.peek() == '(': 200 | parser_stack.pop() 201 | parser_stack.push(new_acceptor) 202 | break 203 | 204 | parser_stack.push(new_acceptor) 205 | 206 | if parser_stack.size() != 1: 207 | raise ValueError('Parssing error! parser stack: {} .'.format(parser_stack)) 208 | 209 | # start of a token 210 | if next_char == "]": 211 | parsed.append({'type': 'segment', 'value': active_operation}) 212 | capturing_inside_a_token_mode = False 213 | # reset capturer 214 | capturer = "" 215 | continue 216 | 217 | elif next_char == "]": 218 | while(parser_stack.size() > 2): 219 | item2 = parser_stack.pop() 220 | op = parser_stack.pop() 221 | item1 = parser_stack.pop() 222 | if op == '&': 223 | new_acceptor = {'opr1': item1, 224 | 'opr2': item2, 225 | 'type': 'comp_and'} 226 | if op == "|": 227 | new_acceptor = {'opr1': item1, 228 | 'opr2': item2, 229 | 'type': 'comp_or'} 230 | 231 | if parser_stack.size() == 0: 232 | parser_stack.push(new_acceptor) 233 | break 234 | 235 | if parser_stack.peek() == '(': 236 | parser_stack.pop() 237 | parser_stack.push(new_acceptor) 238 | break 239 | 240 | parser_stack.push(new_acceptor) 241 | 242 | if parser_stack.size() != 1: 243 | raise ValueError('Parssing error! parser stack: {} .'.format(parser_stack)) 244 | 245 | active_operation = parser_stack.pop() 246 | parsed.append({'type': 'segment', 'value': active_operation}) 247 | capturing_inside_a_token_mode = False 248 | capturer = "" 249 | continue 250 | 251 | # start of an expression 252 | else: 253 | capturer = next_char 254 | active_operation = {'type': '', 'label': 'text'} 255 | capturing_expr_for_token_mode = True 256 | 257 | # outside a token 258 | else: 259 | if repetition_capture_mode: 260 | if next_char == "}": 261 | if start_repetition: 262 | parsed.append({'type': 'repetition_range', 'start': start_repetition, 'end': repetition}) 263 | else: 264 | parsed.append({'type': 'repetition', 'value': repetition}) 265 | repetition = 0 266 | start_repetition = None 267 | repetition_capture_mode = False 268 | 269 | elif next_char.isdigit(): 270 | repetition = repetition * 10 + int(next_char) 271 | 272 | elif next_char == ",": 273 | start_repetition = repetition 274 | repetition = 0 275 | 276 | else: 277 | raise ValueError('Parser is not able to parse {} beacuse of invalid repetition char {} .'.format(token_query_string, char)) 278 | continue 279 | 280 | if capture_mode_name != None: 281 | if next_char in ["(", " ", "["]: 282 | if capture_mode_name: 283 | name = capture_mode_name 284 | else: 285 | name = "chunk " + str(capture_chunk_id) 286 | capture_chunk_id += 1 287 | parsed.append({'type': 'capture', 'value': 'On', 'name': name}) 288 | capture_mode_name = None 289 | else: 290 | capture_mode_name += next_char 291 | continue 292 | 293 | if next_char == "*": 294 | # zero or more times 295 | parsed.append({'type': 'repetition', 'value': '*'}) 296 | if next_char == "?": 297 | # once or not at all 298 | parsed.append({'type': 'repetition', 'value': '?'}) 299 | if next_char == "+": 300 | # one or more time 301 | parsed.append({'type': 'repetition', 'value': '+'}) 302 | 303 | if next_char == "{": 304 | # fixed number 305 | repetition = 0 306 | start_repetition = None 307 | repetition_capture_mode = True 308 | 309 | if next_char == "(": 310 | capture_mode_name = "" 311 | 312 | if next_char == ")": 313 | parsed.append({'type': 'capture', 'value': 'Off'}) 314 | capture_mode_name = None 315 | 316 | if next_char == "[": 317 | parser_stack = Stack() 318 | capturing_inside_a_token_mode = True 319 | continue 320 | 321 | return parsed 322 | 323 | def compile(self, parsed_token_regex): 324 | # add start node 325 | # capture_mode = False 326 | capture_name = None 327 | no_capture_at_all = True 328 | previous_connection = False 329 | 330 | start_state = State('start', capture_name, self.acceptors) 331 | states = [start_state] 332 | current_state = start_state 333 | prev_state = None 334 | prev_segment = None 335 | 336 | state_counter = 1 337 | for item in parsed_token_regex: 338 | 339 | if item['type'] == 'segment': 340 | next_state = State('state ' + str(state_counter), capture_name, self.acceptors) 341 | states.append(next_state) 342 | state_counter += 1 343 | # machine.add_a_transition(Transition(item['value'], current_state, next_state)) 344 | current_state.add_a_next(item['value'], next_state) 345 | 346 | if previous_connection: 347 | # machine.add_a_transition(Transition(item['value'], prev_state, next_state)) 348 | prev_state.add_a_next(item['value'], next_state) 349 | 350 | previous_connection = False 351 | prev_state = current_state 352 | current_state = next_state 353 | prev_segment = item['value'] 354 | 355 | elif item['type'] == 'capture': 356 | if item['value'] == "On": 357 | # capture_mode = True 358 | capture_name = item['name'] 359 | # fix start state capture mode 360 | if len(states) == 1: 361 | states[0].capture_name = capture_name 362 | no_capture_at_all = False 363 | else: 364 | capture_name = None 365 | # capture_mode = False 366 | 367 | elif item['type'] == 'repetition': 368 | if item['value'] == "*": 369 | current_state.add_a_next(prev_segment, current_state) 370 | # machine.add_a_transition(Transition(prev_segment, current_state, current_state)) 371 | previous_connection = True 372 | elif item['value'] == "?": 373 | previous_connection = True 374 | 375 | elif item['value'] == "+": 376 | current_state.add_a_next(prev_segment, current_state) 377 | # machine.add_a_transition(Transition(prev_segment, current_state, current_state )) 378 | 379 | elif item['value']: 380 | if item['value'] > 1: 381 | for i in range(item['value']-1): 382 | next_state = State('state ' + str(state_counter), capture_name, self.acceptors) 383 | states.append(next_state) 384 | state_counter += 1 385 | current_state.add_a_next(prev_segment, next_state) 386 | # machine.add_a_transition(Transition(prev_segment, current_state, next_state)) 387 | prev_state = current_state 388 | current_state = next_state 389 | 390 | elif item['type'] == 'repetition_range': 391 | # repetition starts from 1 392 | source_state = prev_state # current_state 393 | if item['end'] - item['start'] > 0: 394 | for i in range(item['end']-item['start']): 395 | next_state = State('state ' + str(state_counter), capture_name, self.acceptors) 396 | states.append(next_state) 397 | state_counter += 1 398 | current_state.add_a_next(prev_segment, next_state) 399 | #if i > 0: 400 | source_state.add_a_next(prev_segment, next_state) 401 | 402 | # machine.add_a_transition(Transition(prev_segment, current_state, next_state)) 403 | prev_state = current_state 404 | current_state = next_state 405 | 406 | if item['start'] > 1: 407 | for i in range(item['start']-1): 408 | next_state = State('state ' + str(state_counter), capture_name, self.acceptors) 409 | states.append(next_state) 410 | state_counter += 1 411 | current_state.add_a_next(prev_segment, next_state) 412 | # machine.add_a_transition(Transition(prev_segment, current_state, next_state)) 413 | prev_state = current_state 414 | current_state = next_state 415 | # previous_connection = True 416 | # elif item['start'] == 1: 417 | # previous_connection = True 418 | 419 | last_state = State('end', capture_name, self.acceptors, True) 420 | any_rule = {'type': 'str_reg', 421 | 'label': 'text', 422 | 'opr_input': '.*|[\r\n]+'} 423 | current_state.add_a_next(any_rule, last_state) 424 | 425 | states.append(last_state) 426 | 427 | # if no capture, capture all 428 | if no_capture_at_all: 429 | for state in states: 430 | state.capture_name = 'chunk 1' 431 | 432 | return StateMachine(start_state, states) 433 | --------------------------------------------------------------------------------