├── .gitignore ├── LICENSE ├── README.md ├── merge ├── merge_comp_freqs.py └── merge_comp_freqs_test.py ├── miner ├── complexity_analysis.py ├── complexity_calculations.py ├── desc_stats.py ├── git_complexity_diff.py ├── git_complexity_trend.py ├── git_interactions.py ├── git_proximity_analysis.py └── proximity.py └── transform ├── code_age_csv_as_enclosure_json.py ├── communication_csv_as_edge_bundling.py ├── csv_as_enclosure_json.py └── csv_main_dev_as_knowledge_json.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | 5 | # C extensions 6 | *.so 7 | 8 | # Distribution / packaging 9 | .Python 10 | env/ 11 | bin/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | eggs/ 16 | lib/ 17 | lib64/ 18 | parts/ 19 | sdist/ 20 | var/ 21 | *.egg-info/ 22 | .installed.cfg 23 | *.egg 24 | 25 | # Installer logs 26 | pip-log.txt 27 | pip-delete-this-directory.txt 28 | 29 | # Unit test / coverage reports 30 | htmlcov/ 31 | .tox/ 32 | .coverage 33 | .cache 34 | nosetests.xml 35 | coverage.xml 36 | 37 | # Translations 38 | *.mo 39 | 40 | # Mr Developer 41 | .mr.developer.cfg 42 | .project 43 | .pydevproject 44 | 45 | # Rope 46 | .ropeproject 47 | 48 | # Django stuff: 49 | *.log 50 | *.pot 51 | 52 | # Sphinx documentation 53 | docs/_build/ 54 | 55 | -------------------------------------------------------------------------------- /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 | . -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | maat-scripts 2 | ============ 3 | 4 | Scripts used to post-process the results from Code Maat. 5 | 6 | These scripts are referenced from my book [Your Code as a Crime Scene](https://pragprog.com/titles/atcrime/your-code-as-a-crime-scene/). 7 | 8 | The scripts are intended for teaching purposes, and represent a good way to get started and explore the fascinating world of behavioral code analysis. If you came looking for production quality visualizations and tools, then make sure to check out [CodeScene](https://codescene.com/) and its free [Community Edition](https://codescene.com/community-edition). 9 | 10 | ## Python 3 11 | 12 | All scripts have been ported to Python 3 and are available on the [python3](https://github.com/adamtornhill/maat-scripts/tree/python3) branch. 13 | 14 | ## Python 2 15 | 16 | The [master](https://github.com/adamtornhill/maat-scripts/tree/master) branch still contains the original scripts, compatible with Python 2.7. In the future, I hope to deprecate that support but need to keep it for as long as the 1st edition of the book is around. 17 | -------------------------------------------------------------------------------- /merge/merge_comp_freqs.py: -------------------------------------------------------------------------------- 1 | ## Merges two CSV documents. 2 | ## 3 | 4 | import csv 5 | import sys 6 | import os 7 | 8 | class MergeError(Exception): 9 | def __init__(self, message): 10 | Exception.__init__(self, message) 11 | 12 | class Merged(object): 13 | def __init__(self): 14 | self._all_modules_with_complexity = {} 15 | self._merged = {} 16 | 17 | def sorted_result(self): 18 | # Sort on descending order: 19 | ordered = sorted(self._merged.items(), key=lambda item: int(item[1][0]), reverse=True) 20 | return ordered 21 | 22 | def extend_with(self, name, freqs): 23 | if name in self._all_modules_with_complexity: 24 | complexity = self._all_modules_with_complexity[name] 25 | self._merged[name] = freqs, complexity 26 | 27 | def record_detected(self, name, complexity): 28 | self._all_modules_with_complexity[name] = complexity 29 | 30 | def skip_heading(f): 31 | next(f) 32 | 33 | def read_heading_from(r): 34 | p = r.next() 35 | while p == []: 36 | p = r.next() 37 | return p 38 | 39 | def validate_content_by(heading, expected): 40 | comparison = expected.split(',') 41 | stripped = heading[0:len(comparison)] # allow extra fields 42 | if stripped != comparison: 43 | raise MergeError('Erroneous content. Expected = ' + expected + ', got = ' + ','.join(heading)) 44 | 45 | def parse_csv(merged, filename, parse_action, expected_format): 46 | with open(filename, 'rb') as csvfile: 47 | r = csv.reader(csvfile, delimiter=',') 48 | heading = read_heading_from(r) 49 | validate_content_by(heading, expected_format) 50 | for row in r: 51 | parse_action(merged, row) 52 | 53 | def write_csv(stats): 54 | print 'module,revisions,code' 55 | for s in stats: 56 | name, (f,c) = s 57 | print name + ',' + f + ',' + c 58 | 59 | def as_os_aware_path(name): 60 | return os.path.normpath(name) 61 | 62 | def parse_complexity(merged, row): 63 | name = as_os_aware_path(row[1]) 64 | complexity = row[4] 65 | merged.record_detected(name, complexity) 66 | 67 | def parse_freqs(merged, row): 68 | name = as_os_aware_path(row[0]) 69 | freqs = row[1] 70 | merged.extend_with(name, freqs) 71 | 72 | def merge(revs_file, comp_file): 73 | merged = Merged() 74 | parse_csv(merged, comp_file, parse_complexity, expected_format='language,filename,blank,comment,code') 75 | parse_csv(merged, revs_file, parse_freqs, expected_format='entity,n-revs') 76 | write_csv(merged.sorted_result()) 77 | 78 | if __name__ == '__main__': 79 | if len(sys.argv) != 3: 80 | raise MergeError('Wrong arguments. Require one CSV file with frequencies and one with the complexity') 81 | revs_file = sys.argv[1] 82 | comp_file = sys.argv[2] 83 | merge(revs_file, comp_file) 84 | -------------------------------------------------------------------------------- /merge/merge_comp_freqs_test.py: -------------------------------------------------------------------------------- 1 | import unittest 2 | import merge_comp_freqs 3 | 4 | class MergeCompFreqsTest(unittest.TestCase): 5 | FAKED_COMPLEXITY_METRIC = 42 6 | FAKED_MODULE = 'some/file/here.py' 7 | FAKED_FREQS_METRIC = 26 8 | 9 | def setUp(self): 10 | self._merger = merge_comp_freqs.Merged() 11 | self._simulate_existing(self.FAKED_MODULE, self.FAKED_COMPLEXITY_METRIC) 12 | 13 | def test_starts_empty(self): 14 | m = merge_comp_freqs.Merged() 15 | self.assertEqual(m.sorted_result(), []) 16 | 17 | def test_parses_freqs_row(self): 18 | a_row = [self.FAKED_MODULE, self.FAKED_FREQS_METRIC] 19 | merge_comp_freqs.parse_freqs(self._merger, a_row) 20 | updated = self._merger.sorted_result() 21 | self.assertEqual(updated, [(self.FAKED_MODULE, (self.FAKED_FREQS_METRIC, self.FAKED_COMPLEXITY_METRIC))]) 22 | 23 | def test_ignores_non_existent_change_records(self): 24 | """ Since we're using historic data, some modules may no longer exist. 25 | In that case we're just ignore them in the merge. 26 | """ 27 | row_with_nonexistent = ['another/module', self.FAKED_FREQS_METRIC] 28 | merge_comp_freqs.parse_freqs(self._merger, row_with_nonexistent) 29 | updated = self._merger.sorted_result() 30 | empty_merge_result = [] 31 | self.assertEqual(updated, empty_merge_result) 32 | 33 | def test_sorts_output_on_freqs(self): 34 | a_new_module = 'hello' 35 | complexity_of_new_module = 120 36 | freqs_of_new_module = 2 37 | self._simulate_existing(a_new_module, complexity_of_new_module) 38 | rows = [[self.FAKED_MODULE, self.FAKED_FREQS_METRIC], [a_new_module, freqs_of_new_module]] 39 | for a_row in rows: 40 | merge_comp_freqs.parse_freqs(self._merger, a_row) 41 | updated = self._merger.sorted_result() 42 | self.assertEqual(updated, [(self.FAKED_MODULE, (self.FAKED_FREQS_METRIC, self.FAKED_COMPLEXITY_METRIC)), 43 | (a_new_module, (freqs_of_new_module, complexity_of_new_module))]) 44 | 45 | def _simulate_existing(self, module, complexity): 46 | self._merger.record_detected(module, complexity) -------------------------------------------------------------------------------- /miner/complexity_analysis.py: -------------------------------------------------------------------------------- 1 | ###################################################################### 2 | ## This program calculates the whitespace complexity of a file. 3 | ###################################################################### 4 | 5 | #!/bin/env python 6 | import argparse 7 | import desc_stats 8 | import complexity_calculations 9 | 10 | ###################################################################### 11 | ## Statistics from complexity 12 | ###################################################################### 13 | 14 | def as_stats(revision, complexity_by_line): 15 | return desc_stats.DescriptiveStats(revision, complexity_by_line) 16 | 17 | ###################################################################### 18 | ## Output 19 | ###################################################################### 20 | 21 | def as_csv(stats): 22 | print 'n,total,mean,sd,max' 23 | fields_of_interest = [stats.n_revs, stats.total, round(stats.mean(),2), round(stats.sd(),2), stats.max_value()] 24 | printable = [str(field) for field in fields_of_interest] 25 | print ','.join(printable) 26 | 27 | ###################################################################### 28 | ## Main 29 | ###################################################################### 30 | 31 | def run(args): 32 | with open (args.file, "r") as file_to_calc: 33 | complexity_by_line = complexity_calculations.calculate_complexity_in(file_to_calc.read()) 34 | stats = desc_stats.DescriptiveStats(args.file, complexity_by_line) 35 | as_csv(stats) 36 | 37 | if __name__ == "__main__": 38 | parser = argparse.ArgumentParser(description='Calculates whitespace complexity of the given file.') 39 | parser.add_argument('file', type=str, help='The file to calculate complexity on') 40 | args = parser.parse_args() 41 | run(args) 42 | -------------------------------------------------------------------------------- /miner/complexity_calculations.py: -------------------------------------------------------------------------------- 1 | import re 2 | 3 | ###################################################################### 4 | ## Complexity calculations 5 | ###################################################################### 6 | 7 | leading_tabs_expr = re.compile(r'^(\t+)') 8 | leading_spaces_expr = re.compile(r'^( +)') 9 | empty_line_expr = re.compile(r'^\s*$') 10 | 11 | def n_log_tabs(line): 12 | pattern = re.compile(r' +') 13 | wo_spaces = re.sub(pattern, '', line) 14 | m = leading_tabs_expr.search(wo_spaces) 15 | if m: 16 | tabs = m.group() 17 | return len(tabs) 18 | return 0 19 | 20 | def n_log_spaces(line): 21 | pattern = re.compile(r'\t+') 22 | wo_tabs = re.sub(pattern, '', line) 23 | m = leading_spaces_expr.search(wo_tabs) 24 | if m: 25 | spaces = m.group() 26 | return len(spaces) 27 | return 0 28 | 29 | def contains_code(line): 30 | return not empty_line_expr.match(line) 31 | 32 | def complexity_of(line): 33 | return n_log_tabs(line) + (n_log_spaces(line) / 4) # hardcoded indentation 34 | 35 | ###################################################################### 36 | ## Statistics from complexity 37 | ###################################################################### 38 | 39 | def calculate_complexity_in(source): 40 | return [complexity_of(line) for line in source.split("\n") if contains_code(line)] -------------------------------------------------------------------------------- /miner/desc_stats.py: -------------------------------------------------------------------------------- 1 | ## Basic mathematical statistics (yes, I know - NumPy would be better, 2 | ## but I want to make the scripts stand-alone for now). 3 | 4 | class DescriptiveStats(object): 5 | def __init__(self, name, all_values): 6 | self.name = name 7 | self._all_values = all_values 8 | self.total = sum(all_values) 9 | self.n_revs = len(all_values) 10 | 11 | def mean(self): 12 | return self.total / float(self._protected_n()) 13 | 14 | def max_value(self): 15 | return max(self._all_values) 16 | 17 | def min_value(self): 18 | return min(self._all_values) 19 | 20 | def sd(self): 21 | from math import sqrt 22 | std = 0 23 | mean = self.mean() 24 | for a in self._all_values: 25 | std = std + (a - mean)**2 26 | std = sqrt(std / float(self._protected_n())) 27 | return std 28 | 29 | def _protected_n(self): 30 | n = self.n_revs 31 | return max(n, 1) -------------------------------------------------------------------------------- /miner/git_complexity_diff.py: -------------------------------------------------------------------------------- 1 | #!/bin/env python 2 | import sys, subprocess, re 3 | from collections import defaultdict 4 | import argparse 5 | import git_interactions 6 | import desc_stats 7 | import complexity_calculations 8 | 9 | ###################################################################### 10 | ## Statistics from complexity 11 | ###################################################################### 12 | 13 | class AggregatedStats(object): 14 | """ Aggregates statistics for added and removed complexity. 15 | """ 16 | def __init__(self, added, removed): 17 | self.added = self._stats_for(added) 18 | self.removed = self._stats_for(removed) 19 | 20 | def _stats_for(self, all_values): 21 | relevant = [r for r in all_values if r != 0] 22 | return desc_stats.DescriptiveStats('aggregate', relevant) 23 | 24 | def parse_complexity_changes_in(revision, git_diff): 25 | cadded = [] 26 | cremoved = [] 27 | 28 | # Queries on the lines in the diff: 29 | def marks_empty(line): 30 | return not line 31 | def marks_file_hunk(line): 32 | return (len(line) >= 4) and line[:3] in ('---', '+++') 33 | def marks_added(line): 34 | return not marks_empty(line) and line[0] == '+' 35 | def marks_removed(line): 36 | return not marks_empty(line) and line[0] == '-' 37 | # Extractors: 38 | def complexity_from_modified(line): 39 | return complexity_calculations.complexity_of(line[1:]) 40 | 41 | for line in git_diff.split("\n"): 42 | if marks_empty(line): 43 | continue 44 | elif marks_file_hunk(line): 45 | continue 46 | elif marks_added(line): 47 | cadded.append(complexity_from_modified(line)) 48 | elif marks_removed(line): 49 | cremoved.append(complexity_from_modified(line)) 50 | 51 | stats = AggregatedStats(cadded, cremoved) 52 | return (revision, stats) 53 | 54 | def delta_complexity_of(aggregated_stats): 55 | added_complexity = aggregated_stats.added.total 56 | removed_complexity = aggregated_stats.removed.total 57 | return added_complexity - removed_complexity 58 | 59 | #print 'date, rev1, rev2, nAdded, totalAdded, meanAdded, nRemoved, totalRemoved, meanRemoved, totalDelta, meanDelta' 60 | 61 | ###################################################################### 62 | ## Output 63 | ###################################################################### 64 | 65 | def as_csv(result): 66 | print 'rev,growth,nadded,addedtotal,addedmean,sd,nremoved,removedtotal,removedmean' 67 | for rev, stats in result: 68 | added = stats.added 69 | removed = stats.removed 70 | growth = delta_complexity_of(stats) 71 | fields_of_interest = [rev, growth, added.n_revs, added.total, round(added.mean(),2), round(added.sd(),2), 72 | removed.n_revs, removed.total, round(removed.mean(), 2)] 73 | printable = [str(field) for field in fields_of_interest] 74 | print ','.join(printable) 75 | 76 | ###################################################################### 77 | ## Main 78 | ###################################################################### 79 | 80 | def parse_complexity_delta_in(file_name, revision_range): 81 | start_rev, end_rev = revision_range 82 | revs = git_interactions.read_revs_for(file_name, start_rev, end_rev) 83 | complexity_by_rev = [] 84 | for i in range(len(revs) - 1): 85 | first_revision = revs[i] 86 | revision_to_compare = revs[i+1] 87 | git_diff = git_interactions.read_file_diff_for(file_name, first_revision, revision_to_compare) 88 | complexity_in_one_rev = parse_complexity_changes_in(first_revision,git_diff) 89 | complexity_by_rev.append(complexity_in_one_rev) 90 | return complexity_by_rev 91 | 92 | def run(args): 93 | revision_range = args.start, args.end 94 | complexity_delta_in_revs = parse_complexity_delta_in(args.file, revision_range) 95 | as_csv(complexity_delta_in_revs) 96 | 97 | if __name__ == "__main__": 98 | parser = argparse.ArgumentParser(description='Calculates whitespace complexity trends over a range of revisions.') 99 | parser.add_argument('--start', required=True, help='The first commit hash to include') 100 | parser.add_argument('--end', required=True, help='The last commit hash to include') 101 | parser.add_argument('--file', required=True, type=str, help='The file to calculate complexity on') 102 | 103 | args = parser.parse_args() 104 | run(args) 105 | -------------------------------------------------------------------------------- /miner/git_complexity_trend.py: -------------------------------------------------------------------------------- 1 | ###################################################################### 2 | ## This program calculates the complexity trend over a range of 3 | ## revisions in a Git repo. 4 | ###################################################################### 5 | 6 | #!/bin/env python 7 | import argparse 8 | import git_interactions 9 | import desc_stats 10 | import complexity_calculations 11 | 12 | ###################################################################### 13 | ## Statistics from complexity 14 | ###################################################################### 15 | 16 | def as_stats(revision, complexity_by_line): 17 | return desc_stats.DescriptiveStats(revision, complexity_by_line) 18 | 19 | ###################################################################### 20 | ## Output 21 | ###################################################################### 22 | 23 | def as_csv(result): 24 | print 'rev,n,total,mean,sd' 25 | for stats in result: 26 | fields_of_interest = [stats.name, stats.n_revs, stats.total, round(stats.mean(),2), round(stats.sd(),2)] 27 | printable = [str(field) for field in fields_of_interest] 28 | print ','.join(printable) 29 | 30 | ###################################################################### 31 | ## Main 32 | ###################################################################### 33 | 34 | def calculate_complexity_over_range(file_name, revision_range): 35 | start_rev, end_rev = revision_range 36 | revs = git_interactions.read_revs_for(file_name, start_rev, end_rev) 37 | complexity_by_rev = [] 38 | for rev in revs: 39 | historic_version = git_interactions.read_version_matching(file_name, rev) 40 | complexity_by_line = complexity_calculations.calculate_complexity_in(historic_version) 41 | complexity_by_rev.append(as_stats(rev, complexity_by_line)) 42 | return complexity_by_rev 43 | 44 | def run(args): 45 | revision_range = args.start, args.end 46 | complexity_trend = calculate_complexity_over_range(args.file, revision_range) 47 | as_csv(complexity_trend) 48 | 49 | if __name__ == "__main__": 50 | parser = argparse.ArgumentParser(description='Calculates whitespace complexity trends over a range of revisions.') 51 | parser.add_argument('--start', required=True, help='The first commit hash to include') 52 | parser.add_argument('--end', required=True, help='The last commit hash to include') 53 | parser.add_argument('--file', required=True, type=str, help='The file to calculate complexity on') 54 | 55 | args = parser.parse_args() 56 | run(args) 57 | -------------------------------------------------------------------------------- /miner/git_interactions.py: -------------------------------------------------------------------------------- 1 | import subprocess 2 | import re 3 | 4 | def _as_rev_range(start, end): 5 | return start + '..' + end 6 | 7 | def _run_git_cmd(git_arguments): 8 | return subprocess.Popen(git_arguments, stdout=subprocess.PIPE).communicate()[0] 9 | 10 | def _read_revisions_matching(git_arguments): 11 | git_log = _run_git_cmd(git_arguments) 12 | revs = [] 13 | # match a line like: d804759 Documented tree map visualizations 14 | # ignore everything except the commit number: 15 | rev_expr = re.compile(r'([^\s]+)') 16 | for line in git_log.split("\n"): 17 | m = rev_expr.search(line) 18 | if m: 19 | revs.append(m.group(1)) 20 | return revs[::-1] 21 | 22 | def _git_cmd_for(rev_start, rev_end): 23 | rev_range = rev_start + '..' + rev_end 24 | return ['git', 'log', rev_range, '--oneline'] 25 | 26 | def read_revs(rev_start, rev_end): 27 | """ Returns a list of all commits in the given range. 28 | """ 29 | return _read_revisions_matching(git_arguments=_git_cmd_for(rev_start, rev_end)) 30 | 31 | def read_revs_for(file_name, rev_start, rev_end): 32 | return _read_revisions_matching(git_arguments=_git_cmd_for(rev_start, rev_end) + [file_name]) 33 | 34 | def read_diff_for(rev1, rev2): 35 | return _run_git_cmd(['git', 'diff', rev1, rev2]) 36 | 37 | def read_file_diff_for(file_name, rev1, rev2): 38 | return _run_git_cmd(['git', 'diff', rev1, rev2, file_name]) 39 | 40 | def read_version_matching(file_name, rev): 41 | return _run_git_cmd(['git', 'show', rev + ':' + file_name]) 42 | -------------------------------------------------------------------------------- /miner/git_proximity_analysis.py: -------------------------------------------------------------------------------- 1 | #!/bin/env python 2 | import sys, subprocess, re 3 | from collections import defaultdict 4 | import proximity 5 | import argparse 6 | import git_interactions 7 | 8 | ## Calculates the proximity between changes over a range of commits. 9 | ## 10 | ## Run the program as: 11 | ## 12 | ## python git_proximity_analysis.py --start 540e8de --end d804759 13 | ## 14 | ## where the two arguments specify the range of revisions of interest. 15 | ## Note that you must run the program from within a git repo. 16 | ## 17 | 18 | ###################################################################### 19 | ## Git interaction 20 | ###################################################################### 21 | 22 | # git log --pretty=format:"%cd %h %s" --date=short 23 | # => 24 | # 2013-12-13 1c2f3c1 Introduced layers 25 | 26 | new_module_expr = re.compile(r'^--- a\/(.+)') 27 | 28 | def maybe_new_module(line): 29 | """ Search for a line like: 30 | --- a/src/code_maat/analysis/authors.clj 31 | Return the file name (sans the pre-fix) if found. 32 | """ 33 | m = new_module_expr.search(line) 34 | if m: 35 | return m.group(1) 36 | 37 | change_line_expr = re.compile(r'@@ -(\d+),') 38 | 39 | def changed_line(line): 40 | """ Search for a line like: 41 | @@ -65,7 +65,7 @@ 42 | This is a diff on the unified format. We extract 43 | the line number of the modification from the original 44 | file and return it. 45 | """ 46 | m = change_line_expr.search(line) 47 | if m: 48 | offset = m.group(1) 49 | return int(offset) 50 | 51 | def parse_changes_per_file_in(git_diff): 52 | files_with_changes = {} 53 | file_name = None 54 | 55 | for line in git_diff.split("\n"): 56 | # read ahead until we note the diff for a file: 57 | new_file = maybe_new_module(line) 58 | if new_file: 59 | file_name=new_file 60 | # one we have the diff of a file, accumulate the changes: 61 | if file_name: 62 | change = changed_line(line) 63 | proximity.record_change_to(file_name, change,files_with_changes) 64 | return files_with_changes 65 | 66 | ###################################################################### 67 | ## Output 68 | ###################################################################### 69 | 70 | def as_csv(result): 71 | print 'file,revs,total,mean,sd,max' 72 | for p in result: 73 | fields_of_interest = [p.name, p.n_revs + 1, p.total, round(p.mean(),2), round(p.sd(),2), p.max_value()] 74 | printable = [str(field) for field in fields_of_interest] 75 | print ','.join(printable) 76 | 77 | ###################################################################### 78 | ## Main 79 | ###################################################################### 80 | 81 | def read_proximities_from(revision_range): 82 | start_rev, end_rev = revision_range 83 | revs = git_interactions.read_revs(start_rev, end_rev) 84 | proximities = [] 85 | for i in range(len(revs) - 1): 86 | first_revision = revs[i] 87 | revision_to_compare = revs[i+1] 88 | git_diff = git_interactions.read_diff_for(first_revision, revision_to_compare) 89 | changes = parse_changes_per_file_in(git_diff) 90 | proximities.append(proximity.calc_proximity(changes)) 91 | return proximities 92 | 93 | def run(args): 94 | revision_range = args.start, args.end 95 | proximities = read_proximities_from(revision_range) 96 | stats = proximity.sum_proximity_stats(proximities) 97 | presentation_order = proximity.sorted_on_proximity(stats) 98 | as_csv(presentation_order) 99 | 100 | if __name__ == "__main__": 101 | parser = argparse.ArgumentParser(description='Calculates proximity of changes recorded in the revision history.') 102 | parser.add_argument('--start', required=True, help='The first commit hash to include') 103 | parser.add_argument('--end', required=True, help='The last commit hash to include') 104 | 105 | args = parser.parse_args() 106 | run(args) 107 | 108 | -------------------------------------------------------------------------------- /miner/proximity.py: -------------------------------------------------------------------------------- 1 | import collections 2 | from operator import itemgetter 3 | import desc_stats 4 | 5 | ## Functions for calculating proximity/distance 6 | 7 | def _pdistance(positions): 8 | return sum([j-i for i,j in zip(positions[:-1], positions[1:])]) 9 | 10 | def calc_proximity(changes): 11 | return dict([(name, _pdistance(change)) for name, change in changes.iteritems()]) 12 | 13 | def record_change_to(file_name, change, acc): 14 | if not change: 15 | return 16 | 17 | existing = [] 18 | if file_name in acc: 19 | existing = acc[file_name] 20 | existing.append(change) 21 | acc[file_name]=existing 22 | 23 | def _as_stats(all_proximities): 24 | return [desc_stats.DescriptiveStats(name, proximities_for_one) for name, proximities_for_one in all_proximities.iteritems()] 25 | 26 | def _group_by(one_file, proximity, all_grouped): 27 | existing = [] 28 | if one_file in all_grouped: 29 | existing = all_grouped[one_file] 30 | existing.append(proximity) 31 | return existing 32 | 33 | def sum_proximity_stats(all_proximities): 34 | """ Received all proximities as a list of dictionaries. 35 | Each dictionary represents the proximities in the changed 36 | in one revision. 37 | Take this list and group all changes per item. 38 | """ 39 | all_grouped = {} 40 | for one_rev_proximity in all_proximities: 41 | for (one_file, proximity) in one_rev_proximity.iteritems(): 42 | all_grouped[one_file] = _group_by(one_file, proximity, all_grouped) 43 | return _as_stats(all_grouped) 44 | 45 | def sorted_on_proximity(proximity_stats): 46 | return sorted(proximity_stats, key=lambda p: p.total, reverse=True) -------------------------------------------------------------------------------- /transform/code_age_csv_as_enclosure_json.py: -------------------------------------------------------------------------------- 1 | #!/bin/env python 2 | 3 | ####################################################################### 4 | ## This program generates a JSON document suitable for a D3.js 5 | ## enclosure diagram visualization. This script is used together with 6 | ## a Code Maat age analysis in order to calculate the exponential 7 | ## decay and stabilization of code. 8 | ## 9 | ## The input data is read from two CSV files: 10 | ## 1) The complete system structure, including size metrics. 11 | ## 2) A code age analysis result used to assign weights to the modules. 12 | ####################################################################### 13 | 14 | import argparse 15 | import csv 16 | import json 17 | import sys 18 | 19 | class MergeError(Exception): 20 | def __init__(self, message): 21 | Exception.__init__(self, message) 22 | 23 | class Merged(object): 24 | def __init__(self): 25 | self._all_modules_with_complexity = {} 26 | self._merged = {} 27 | 28 | def sorted_result(self): 29 | # Sort on descending order: 30 | ordered = sorted(self._merged.items(), key=lambda item: item[1][0], reverse=True) 31 | return ordered 32 | 33 | def extend_with(self, name, freqs): 34 | if name in self._all_modules_with_complexity: 35 | complexity = self._all_modules_with_complexity[name] 36 | self._merged[name] = freqs, complexity 37 | 38 | def record_detected(self, name, complexity): 39 | self._all_modules_with_complexity[name] = complexity 40 | 41 | def write_csv(stats): 42 | print 'module,revisions,code' 43 | for s in stats: 44 | name, (f,c) = s 45 | print name + ',' + f + ',' + c 46 | 47 | def parse_complexity(merged, row): 48 | name = row[1][2:] 49 | complexity = row[4] 50 | merged.record_detected(name, complexity) 51 | 52 | def parse_freqs(merged, row): 53 | name = row[0] 54 | freqs = row[1] 55 | merged.extend_with(name, freqs) 56 | 57 | def merge(revs_file, comp_file): 58 | merged = Merged() 59 | parse_csv(merged, comp_file, parse_complexity, expected_format='language,filename,blank,comment,code') 60 | parse_csv(merged, revs_file, parse_freqs, expected_format='entity,n-revs') 61 | write_csv(merged.sorted_result()) 62 | 63 | ###################################################################### 64 | ## Parse input 65 | ###################################################################### 66 | 67 | def validate_content_by(heading, expected): 68 | if not expected: 69 | return # no validation 70 | comparison = expected.split(',') 71 | stripped = heading[0:len(comparison)] # allow extra fields 72 | if stripped != comparison: 73 | raise MergeError('Erroneous content. Expected = ' + expected + ', got = ' + ','.join(heading)) 74 | 75 | def parse_csv(filename, parse_action, expected_format=None): 76 | def read_heading_from(r): 77 | p = r.next() 78 | while p == []: 79 | p = r.next() 80 | return p 81 | with open(filename, 'rb') as csvfile: 82 | r = csv.reader(csvfile, delimiter=',') 83 | heading = read_heading_from(r) 84 | validate_content_by(heading, expected_format) 85 | return [parse_action(row) for row in r] 86 | 87 | class StructuralElement(object): 88 | def __init__(self, name, complexity): 89 | self.name = name 90 | self.complexity = complexity 91 | def parts(self): 92 | return self.name.split('/') 93 | 94 | def parse_structural_element(csv_row): 95 | name = csv_row[1][2:] 96 | complexity = csv_row[4] 97 | return StructuralElement(name, complexity) 98 | 99 | def make_element_weight_parser(weight_column): 100 | """ Parameterize with the column - this allows us 101 | to generate data from different analysis result types. 102 | """ 103 | def parse_element_weight(csv_row): 104 | name = csv_row[0] 105 | weight = float(csv_row[weight_column]) # Assert not zero? 106 | return name, weight 107 | return parse_element_weight 108 | 109 | ###################################################################### 110 | ## Calculating weights from the given CSV analysis file 111 | ###################################################################### 112 | 113 | class WeightCalculator(object): 114 | """ 115 | Calculates code age using exponential decay. 116 | """ 117 | def __init__(self, half_life, analysis_results): 118 | self._half_life_months = float(half_life) 119 | def as_half_life(age): 120 | return 1 / 2**(float(age)/self._half_life_months) 121 | def as_color(age): 122 | if age < self._half_life_months: 123 | return "darkred" 124 | return "DodgerBlue" 125 | def as_colored_weight(age): 126 | return as_half_life(age), as_color(age) 127 | self._colored_weights = dict([(name, as_colored_weight(n)) for name,n in analysis_results]) 128 | 129 | def weight_for(self, module_name): 130 | if module_name in self._colored_weights: 131 | weight, _ = self._colored_weights[module_name] 132 | return weight 133 | return 0.0 134 | 135 | def color_of(self, module_name): 136 | if module_name in self._colored_weights: 137 | _, color = self._colored_weights[module_name] 138 | return color 139 | return "gray" 140 | 141 | ###################################################################### 142 | ## Building the structure of the system 143 | ###################################################################### 144 | 145 | def _matching_part_in(hierarchy, part): 146 | return next((x for x in hierarchy if x['name']==part), None) 147 | 148 | def _ensure_branch_exists(hierarchy, branch): 149 | existing = _matching_part_in(hierarchy, branch) 150 | if not existing: 151 | new_branch = {'name':branch, 'children':[]} 152 | hierarchy.append(new_branch) 153 | existing = new_branch 154 | return existing 155 | 156 | def _add_leaf(hierarchy, module, weight_calculator, name): 157 | new_leaf = {'name':name, 'children':[], 158 | 'size':module.complexity, 159 | 'weight':weight_calculator.weight_for(module.name), 160 | 'color':weight_calculator.color_of(module.name)} 161 | hierarchy.append(new_leaf) 162 | return hierarchy 163 | 164 | def _insert_parts_into(hierarchy, module, weight_calculator, parts): 165 | """ Recursively traverse the hierarchy and insert the individual parts 166 | of the module, one by one. 167 | The parts specify branches. If any branch is missing, it's 168 | created during the traversal. 169 | The final part specifies a module name (sans its path, of course). 170 | This is where we add size and weight to the leaf. 171 | """ 172 | if len(parts) == 1: 173 | return _add_leaf(hierarchy, module, weight_calculator, name=parts[0]) 174 | next_branch = parts[0] 175 | existing_branch = _ensure_branch_exists(hierarchy, next_branch) 176 | return _insert_parts_into(existing_branch['children'], 177 | module, 178 | weight_calculator, 179 | parts=parts[1:]) 180 | 181 | def generate_structure_from(modules, weight_calculator): 182 | hierarchy = [] 183 | for module in modules: 184 | parts = module.parts() 185 | _insert_parts_into(hierarchy, module, weight_calculator, parts) 186 | 187 | structure = {'name':'root', 'children':hierarchy} 188 | return structure 189 | 190 | ###################################################################### 191 | ## Output 192 | ###################################################################### 193 | 194 | def write_json(result): 195 | print json.dumps(result) 196 | 197 | ###################################################################### 198 | ## Main 199 | ###################################################################### 200 | 201 | def run(args): 202 | raw_weights = parse_csv(args.weights, parse_action=make_element_weight_parser(args.weightcolumn)) 203 | weight_calculator = WeightCalculator(args.halflife, raw_weights) 204 | 205 | structure_input = parse_csv(args.structure, 206 | expected_format='language,filename,blank,comment,code', 207 | parse_action=parse_structural_element) 208 | weighted_system_structure = generate_structure_from(structure_input, weight_calculator) 209 | write_json(weighted_system_structure) 210 | 211 | if __name__ == "__main__": 212 | parser = argparse.ArgumentParser(description='Generates a JSON document suitable for enclosure diagrams.') 213 | parser.add_argument('--structure', required=True, help='A CSV file generated by cloc') 214 | parser.add_argument('--weights', required=True, help='A CSV file with code age results from Code Maat') 215 | parser.add_argument('--weightcolumn', type=int, default=1, help="The index specifying the column to use in the weight table") 216 | parser.add_argument('--halflife', type=int, default=1, help="Specifies the half life for a module in months") 217 | 218 | args = parser.parse_args() 219 | run(args) -------------------------------------------------------------------------------- /transform/communication_csv_as_edge_bundling.py: -------------------------------------------------------------------------------- 1 | #!/bin/env python 2 | 3 | ####################################################################### 4 | ## This program generates a JSON document suitable for a D3.js 5 | ## Hierarchical Edge Bundling visualization (see https://gist.github.com/mbostock/7607999) 6 | ## 7 | ## The input data is read from a Code Maat CSV file containing the result 8 | ## of a analysis. 9 | ####################################################################### 10 | 11 | import argparse 12 | import csv 13 | import json 14 | import sys 15 | 16 | ###################################################################### 17 | ## Parse input 18 | ###################################################################### 19 | 20 | def validate_content_by(heading, expected): 21 | if not expected: 22 | return # no validation 23 | comparison = expected.split(',') 24 | stripped = heading[0:len(comparison)] # allow extra fields 25 | if stripped != comparison: 26 | raise MergeError('Erroneous content. Expected = ' + expected + ', got = ' + ','.join(heading)) 27 | 28 | def parse_csv(filename, parse_action, expected_format=None): 29 | def read_heading_from(r): 30 | p = r.next() 31 | while p == []: 32 | p = r.next() 33 | return p 34 | with open(filename, 'rb') as csvfile: 35 | r = csv.reader(csvfile, delimiter=',') 36 | heading = read_heading_from(r) 37 | validate_content_by(heading, expected_format) 38 | return [parse_action(row) for row in r] 39 | 40 | class LinkBetweenPeer(object): 41 | def __init__(self, author, peer, strength): 42 | self.author = author 43 | self.peer = peer 44 | self.strength = int(strength) 45 | 46 | def parse_peers(csv_row): 47 | return LinkBetweenPeer(csv_row[0], csv_row[1], csv_row[4]) 48 | 49 | ###################################################################### 50 | ## Assemble the individual entries into an aggregated structure 51 | ###################################################################### 52 | 53 | def link_to(existing_authors, new_link): 54 | if not new_link.author in existing_authors: 55 | return {'name':new_link.author, 'size':new_link.strength, 'imports':[new_link.peer]} 56 | existing_author = existing_authors[new_link.author] 57 | existing_author['imports'].append(new_link.peer) 58 | existing_author['size'] = existing_author['size'] + new_link.strength 59 | return existing_author 60 | 61 | def aggregate_links_per_author_in(peer_links): 62 | links_per_author = {} 63 | for peer in peer_links: 64 | links_per_author[peer.author] = link_to(links_per_author, peer) 65 | return links_per_author 66 | 67 | ###################################################################### 68 | ## Output 69 | ###################################################################### 70 | 71 | def write_json(result): 72 | print json.dumps(result) 73 | 74 | ###################################################################### 75 | ## Main 76 | ###################################################################### 77 | 78 | def run(args): 79 | peer_links = parse_csv(args.communication, 80 | expected_format='author,peer,shared,average,strength', 81 | parse_action=parse_peers) 82 | links_by_author = aggregate_links_per_author_in(peer_links) 83 | write_json(links_by_author.values()) 84 | 85 | if __name__ == "__main__": 86 | parser = argparse.ArgumentParser(description='Generates a JSON document suitable for communication diagrams.') 87 | parser.add_argument('--communication', required=True, help='A CSV file containing the result of a communication analysis') 88 | 89 | args = parser.parse_args() 90 | run(args) -------------------------------------------------------------------------------- /transform/csv_as_enclosure_json.py: -------------------------------------------------------------------------------- 1 | #!/bin/env python 2 | 3 | ####################################################################### 4 | ## This program generates a JSON document suitable for a D3.js 5 | ## enclosure diagram visualization. 6 | ## The input data is read from two CSV files: 7 | ## 1) The complete system structure, including size metrics. 8 | ## 2) A hotspot analysis result used to assign weights to the modules. 9 | ####################################################################### 10 | 11 | import argparse 12 | import csv 13 | import json 14 | import sys 15 | import os 16 | 17 | class MergeError(Exception): 18 | def __init__(self, message): 19 | Exception.__init__(self, message) 20 | 21 | class Merged(object): 22 | def __init__(self): 23 | self._all_modules_with_complexity = {} 24 | self._merged = {} 25 | 26 | def sorted_result(self): 27 | # Sort on descending order: 28 | ordered = sorted(self._merged.items(), key=lambda item: item[1][0], reverse=True) 29 | return ordered 30 | 31 | def extend_with(self, name, freqs): 32 | if name in self._all_modules_with_complexity: 33 | complexity = self._all_modules_with_complexity[name] 34 | self._merged[name] = freqs, complexity 35 | 36 | def record_detected(self, name, complexity): 37 | self._all_modules_with_complexity[name] = complexity 38 | 39 | def write_csv(stats): 40 | print 'module,revisions,code' 41 | for s in stats: 42 | name, (f,c) = s 43 | print name + ',' + f + ',' + c 44 | 45 | def parse_complexity(merged, row): 46 | name = row[1][2:] 47 | complexity = row[4] 48 | merged.record_detected(name, complexity) 49 | 50 | def parse_freqs(merged, row): 51 | name = row[0] 52 | freqs = row[1] 53 | merged.extend_with(name, freqs) 54 | 55 | def merge(revs_file, comp_file): 56 | merged = Merged() 57 | parse_csv(merged, comp_file, parse_complexity, expected_format='language,filename,blank,comment,code') 58 | parse_csv(merged, revs_file, parse_freqs, expected_format='entity,n-revs') 59 | write_csv(merged.sorted_result()) 60 | 61 | ###################################################################### 62 | ## Parse input 63 | ###################################################################### 64 | 65 | def validate_content_by(heading, expected): 66 | if not expected: 67 | return # no validation 68 | comparison = expected.split(',') 69 | stripped = heading[0:len(comparison)] # allow extra fields 70 | if stripped != comparison: 71 | raise MergeError('Erroneous content. Expected = ' + expected + ', got = ' + ','.join(heading)) 72 | 73 | def parse_csv(filename, parse_action, expected_format=None): 74 | def read_heading_from(r): 75 | p = r.next() 76 | while p == []: 77 | p = r.next() 78 | return p 79 | with open(filename, 'rb') as csvfile: 80 | r = csv.reader(csvfile, delimiter=',') 81 | heading = read_heading_from(r) 82 | validate_content_by(heading, expected_format) 83 | return [parse_action(row) for row in r] 84 | 85 | class StructuralElement(object): 86 | def __init__(self, name, complexity): 87 | self.name = name 88 | self.complexity = complexity 89 | def parts(self): 90 | res = [x for x in self.pathParts()] 91 | res.reverse() 92 | return res 93 | def pathParts(self): 94 | (hd, tl) = os.path.split(self.name) 95 | while tl != '': 96 | yield tl 97 | (hd, tl) = os.path.split(hd) 98 | 99 | def parse_structural_element(csv_row): 100 | name = csv_row[1] 101 | if name.startswith('./'): 102 | name = name[2:] 103 | complexity = csv_row[4] 104 | return StructuralElement(name, complexity) 105 | 106 | def make_element_weight_parser(weight_column): 107 | """ Parameterize with the column - this allows us 108 | to generate data from different analysis result types. 109 | """ 110 | def parse_element_weight(csv_row): 111 | name = csv_row[0] 112 | weight = float(csv_row[weight_column]) # Assert not zero? 113 | return name, weight 114 | return parse_element_weight 115 | 116 | ###################################################################### 117 | ## Calculating weights from the given CSV analysis file 118 | ###################################################################### 119 | 120 | def module_weight_calculator_from(analysis_results): 121 | max_raw_weight = max(analysis_results, key=lambda e: e[1]) 122 | max_value = max_raw_weight[1] 123 | normalized_weights = dict([(name, (1.0 / max_value) * n) for name,n in analysis_results]) 124 | def normalized_weight_for(module_name): 125 | if module_name in normalized_weights: 126 | return normalized_weights[module_name] 127 | return 0.0 128 | return normalized_weight_for 129 | 130 | ###################################################################### 131 | ## Building the structure of the system 132 | ###################################################################### 133 | 134 | def _matching_part_in(hierarchy, part): 135 | return next((x for x in hierarchy if x['name']==part), None) 136 | 137 | def _ensure_branch_exists(hierarchy, branch): 138 | existing = _matching_part_in(hierarchy, branch) 139 | if not existing: 140 | new_branch = {'name':branch, 'children':[]} 141 | hierarchy.append(new_branch) 142 | existing = new_branch 143 | return existing 144 | 145 | def _add_leaf(hierarchy, module, weight_calculator, name): 146 | # TODO: augment with weight here! 147 | new_leaf = {'name':name, 'children':[], 148 | 'size':module.complexity, 149 | 'weight':weight_calculator(module.name)} 150 | hierarchy.append(new_leaf) 151 | return hierarchy 152 | 153 | def _insert_parts_into(hierarchy, module, weight_calculator, parts): 154 | """ Recursively traverse the hierarchy and insert the individual parts 155 | of the module, one by one. 156 | The parts specify branches. If any branch is missing, it's 157 | created during the traversal. 158 | The final part specifies a module name (sans its path, of course). 159 | This is where we add size and weight to the leaf. 160 | """ 161 | if len(parts) == 1: 162 | return _add_leaf(hierarchy, module, weight_calculator, name=parts[0]) 163 | next_branch = parts[0] 164 | existing_branch = _ensure_branch_exists(hierarchy, next_branch) 165 | return _insert_parts_into(existing_branch['children'], 166 | module, 167 | weight_calculator, 168 | parts=parts[1:]) 169 | 170 | def generate_structure_from(modules, weight_calculator): 171 | hierarchy = [] 172 | for module in modules: 173 | parts = module.parts() 174 | if len(parts) == 0: 175 | continue 176 | _insert_parts_into(hierarchy, module, weight_calculator, parts) 177 | 178 | structure = {'name':'root', 'children':hierarchy} 179 | return structure 180 | 181 | ###################################################################### 182 | ## Output 183 | ###################################################################### 184 | 185 | def write_json(result): 186 | print json.dumps(result) 187 | 188 | ###################################################################### 189 | ## Main 190 | ###################################################################### 191 | 192 | # TODO: turn it around: parse the weights first and add them to individual elements 193 | # as the raw structure list is built! 194 | 195 | def run(args): 196 | raw_weights = parse_csv(args.weights, parse_action=make_element_weight_parser(args.weightcolumn)) 197 | weight_calculator = module_weight_calculator_from(raw_weights) 198 | 199 | structure_input = parse_csv(args.structure, 200 | expected_format='language,filename,blank,comment,code', 201 | parse_action=parse_structural_element) 202 | weighted_system_structure = generate_structure_from(structure_input, weight_calculator) 203 | write_json(weighted_system_structure) 204 | 205 | if __name__ == "__main__": 206 | parser = argparse.ArgumentParser(description='Generates a JSON document suitable for enclosure diagrams.') 207 | parser.add_argument('--structure', required=True, help='A CSV file generated by cloc') 208 | parser.add_argument('--weights', required=True, help='A CSV file with hotspot results from Code Maat') 209 | parser.add_argument('--weightcolumn', type=int, default=1, help="The index specifying the column to use in the weight table") 210 | # TODO: add arguments to specify which CSV columns to use! 211 | 212 | args = parser.parse_args() 213 | run(args) 214 | -------------------------------------------------------------------------------- /transform/csv_main_dev_as_knowledge_json.py: -------------------------------------------------------------------------------- 1 | #!/bin/env python 2 | 3 | ####################################################################### 4 | ## This program generates a JSON document suitable for a D3.js 5 | ## enclosure diagram visualization. 6 | ## The input data is read from three CSV files: 7 | ## 1) A cloc output file specifying the static structure of the system. 8 | ## 2) A file containing Code Maat main developer results. 9 | ## 3) A file specifying the color to use for a certain author. If that 10 | ## information is absent, this script will treat that code as a 11 | ## dead spot. 12 | ## This CSV file must have two columns: author, color 13 | ####################################################################### 14 | 15 | import argparse 16 | import csv 17 | import json 18 | import sys 19 | 20 | ###################################################################### 21 | ## Parse input 22 | ###################################################################### 23 | 24 | def validate_content_by(heading, expected): 25 | if not expected: 26 | return # no validation 27 | comparison = expected.split(',') 28 | stripped = heading[0:len(comparison)] # allow extra fields 29 | if stripped != comparison: 30 | raise MergeError('Erroneous content. Expected = ' + expected + ', got = ' + ','.join(heading)) 31 | 32 | def parse_csv(filename, parse_action, expected_format=None): 33 | def read_heading_from(r): 34 | p = r.next() 35 | while p == []: 36 | p = r.next() 37 | return p 38 | with open(filename, 'rb') as csvfile: 39 | r = csv.reader(csvfile, delimiter=',') 40 | heading = read_heading_from(r) 41 | validate_content_by(heading, expected_format) 42 | return [parse_action(row) for row in r] 43 | 44 | class StructuralElement(object): 45 | def __init__(self, name, complexity): 46 | self.name = name 47 | self.complexity = complexity 48 | def parts(self): 49 | return self.name.split('/') 50 | 51 | def parse_structural_element(csv_row): 52 | name = csv_row[1][2:] 53 | complexity = csv_row[4] 54 | return StructuralElement(name, complexity) 55 | 56 | def parse_author_color(csv_row): 57 | author = csv_row[0] 58 | color = csv_row[1] 59 | return author,color 60 | 61 | class Ownership(object): 62 | def __init__(self, module, main_author, ownership): 63 | self.module = module 64 | self.main_author = main_author 65 | self.ownership = ownership 66 | 67 | def parse_ownership(csv_row): 68 | module = csv_row[0] 69 | main_author = csv_row[1] 70 | ownership = csv_row[4] 71 | return Ownership(module, main_author,ownership) 72 | 73 | ###################################################################### 74 | ## Organizational information to augment the structure 75 | ###################################################################### 76 | 77 | class Knowledge(object): 78 | DEFAULT_COLOR = "black" 79 | def __init__(self, authors_colors, ownerships): 80 | self._authors_colors = authors_colors 81 | self._ownership = dict([(o.module, o) for o in ownerships]) 82 | 83 | def color_of(self, author): 84 | if author in self._authors_colors: 85 | return self._authors_colors[author] 86 | return self.DEFAULT_COLOR 87 | 88 | def owner_of(self, module_name): 89 | if module_name in self._ownership: 90 | o = self._ownership[module_name] 91 | return o.main_author 92 | return None 93 | 94 | def degree_of_ownership_for(self, module_name): 95 | if module_name in self._ownership: 96 | o = self._ownership[module_name] 97 | return o.ownership 98 | return 0.0 99 | 100 | ###################################################################### 101 | ## Building the structure of the system 102 | ###################################################################### 103 | 104 | def _matching_part_in(hierarchy, part): 105 | return next((x for x in hierarchy if x['name']==part), None) 106 | 107 | def _ensure_branch_exists(hierarchy, branch): 108 | existing = _matching_part_in(hierarchy, branch) 109 | if not existing: 110 | new_branch = {'name':branch, 'children':[]} 111 | hierarchy.append(new_branch) 112 | existing = new_branch 113 | return existing 114 | 115 | def _add_leaf(hierarchy, module, knowledge, name): 116 | owner = knowledge.owner_of(module.name) 117 | new_leaf = {'name':name, 'children':[], 118 | 'size':module.complexity, 119 | 'weight':knowledge.degree_of_ownership_for(module.name), 120 | 'author_color':knowledge.color_of(owner)} 121 | hierarchy.append(new_leaf) 122 | return hierarchy 123 | 124 | def _insert_parts_into(hierarchy, module, knowledge, parts): 125 | """ Recursively traverse the hierarchy and insert the individual parts 126 | of the module, one by one. 127 | The parts specify branches. If any branch is missing, it's 128 | created during the traversal. 129 | The final part specifies a module name (sans its path, of course). 130 | This is where we add size and weight to the leaf. 131 | """ 132 | if len(parts) == 1: 133 | return _add_leaf(hierarchy, module, knowledge, name=parts[0]) 134 | next_branch = parts[0] 135 | existing_branch = _ensure_branch_exists(hierarchy, next_branch) 136 | return _insert_parts_into(existing_branch['children'], 137 | module, 138 | knowledge, 139 | parts=parts[1:]) 140 | 141 | def generate_structure_from(modules, knowledge): 142 | hierarchy = [] 143 | for module in modules: 144 | parts = module.parts() 145 | _insert_parts_into(hierarchy, module, knowledge, parts) 146 | 147 | structure = {'name':'root', 'children':hierarchy} 148 | return structure 149 | 150 | ###################################################################### 151 | ## Output 152 | ###################################################################### 153 | 154 | def write_json(result): 155 | print json.dumps(result) 156 | 157 | ###################################################################### 158 | ## Main 159 | ###################################################################### 160 | 161 | def run(args): 162 | authors_colors = dict(parse_csv(args.authors, 163 | expected_format='author,color', 164 | parse_action=parse_author_color)) 165 | module_ownership = parse_csv(args.owners, 166 | expected_format='entity,main-dev,added,total-added,ownership', 167 | parse_action=parse_ownership) 168 | structure_input = parse_csv(args.structure, 169 | expected_format='language,filename,blank,comment,code', 170 | parse_action=parse_structural_element) 171 | knowledge = Knowledge(authors_colors, module_ownership) 172 | knowledge_structure = generate_structure_from(structure_input, knowledge) 173 | write_json(knowledge_structure) 174 | 175 | if __name__ == "__main__": 176 | parser = argparse.ArgumentParser(description='Generates a JSON document suitable for knowledge diagrams.') 177 | parser.add_argument('--structure', required=True, help='A CSV file generated by cloc') 178 | parser.add_argument('--owners', required=True, help='A CSV file generated by a Code Maat main-dev analysis') 179 | parser.add_argument('--authors', required=True, help='A CSV file specifying the color to use for each author') 180 | 181 | args = parser.parse_args() 182 | run(args) --------------------------------------------------------------------------------