Profile of /home/x/provenance.db/ generated 2014/05/12 09:16:58

├── .gitignore ├── .project ├── .settings ├── org.eclipse.jdt.core.prefs └── org.eclipse.m2e.core.prefs ├── .vscode └── settings.json ├── LICENSE.TXT ├── README.md ├── SAMPLE.cypher ├── pom.xml ├── sample-report.html └── src └── main ├── java └── org │ └── mitre │ └── neoprofiler │ ├── NeoProfiler.java │ ├── html │ ├── HTMLMaker.java │ └── package-info.java │ ├── markdown │ ├── MarkdownMaker.java │ └── package-info.java │ ├── package-info.java │ ├── profile │ ├── DBProfile.java │ ├── LabelProfile.java │ ├── LabelPropertyProfile.java │ ├── NeoConstraint.java │ ├── NeoProfile.java │ ├── NeoProperty.java │ ├── NodesProfile.java │ ├── ParameterizedNeoProfile.java │ ├── RelationshipTypeProfile.java │ ├── RelationshipsProfile.java │ ├── SchemaProfile.java │ └── package-info.java │ └── profiler │ ├── LabelProfiler.java │ ├── LabelPropertyProfiler.java │ ├── NodesProfiler.java │ ├── PathsProfiler.java │ ├── Profiler.java │ ├── QueryRunner.java │ ├── RelationshipTypeProfiler.java │ ├── RelationshipsProfiler.java │ ├── SchemaProfiler.java │ ├── UnlabeledNodeProfiler.java │ └── package-info.java └── resources ├── .shell_history └── template.html /.gitignore: -------------------------------------------------------------------------------- 1 | target/ 2 | *~ 3 | .classpath 4 | *.classpath 5 | .externalToolBuilders 6 | *.html 7 | .idea 8 | /bin 9 | -------------------------------------------------------------------------------- /.project: -------------------------------------------------------------------------------- 1 | 2 | 3 | neoprofiler 4 | 5 | 6 | 7 | 8 | 9 | org.eclipse.jdt.core.javabuilder 10 | 11 | 12 | 13 | 14 | org.eclipse.m2e.core.maven2Builder 15 | 16 | 17 | 18 | 19 | 20 | org.eclipse.m2e.core.maven2Nature 21 | org.eclipse.jdt.core.javanature 22 | 23 | 24 | -------------------------------------------------------------------------------- /.settings/org.eclipse.jdt.core.prefs: -------------------------------------------------------------------------------- 1 | eclipse.preferences.version=1 2 | org.eclipse.jdt.core.compiler.codegen.inlineJsrBytecode=enabled 3 | org.eclipse.jdt.core.compiler.codegen.targetPlatform=1.7 4 | org.eclipse.jdt.core.compiler.codegen.unusedLocal=preserve 5 | org.eclipse.jdt.core.compiler.compliance=1.7 6 | org.eclipse.jdt.core.compiler.debug.lineNumber=generate 7 | org.eclipse.jdt.core.compiler.debug.localVariable=generate 8 | org.eclipse.jdt.core.compiler.debug.sourceFile=generate 9 | org.eclipse.jdt.core.compiler.problem.assertIdentifier=error 10 | org.eclipse.jdt.core.compiler.problem.enumIdentifier=error 11 | org.eclipse.jdt.core.compiler.problem.forbiddenReference=warning 12 | org.eclipse.jdt.core.compiler.source=1.7 13 | -------------------------------------------------------------------------------- /.settings/org.eclipse.m2e.core.prefs: -------------------------------------------------------------------------------- 1 | activeProfiles= 2 | eclipse.preferences.version=1 3 | resolveWorkspaceProjects=true 4 | version=1 5 | -------------------------------------------------------------------------------- /.vscode/settings.json: -------------------------------------------------------------------------------- 1 | { 2 | "java.configuration.updateBuildConfiguration": "automatic" 3 | } -------------------------------------------------------------------------------- /LICENSE.TXT: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ## Synopsis 2 | 3 | This package is a lightweight set of profiling utilities for Neo4J databases. 4 | This is intended to quickly help users derive the rough structure and 5 | population of a new Neo4J database. 6 | 7 | ## Quick Start 8 | 9 | **Clone the repo**: `git clone https://github.com/moxious/neoprofiler.git` 10 | 11 | **Package the application**: `mvn package` 12 | 13 | Note that packaging includes the creation of a runnable "One JAR" which includes all necessary dependencies. 14 | 15 | **Run from the command line**: 16 | `java -jar target/neoprofiler-0.15.jar -db path_to_db -format html -output db_profile_report.html` 17 | 18 | The argument given to the application should be the path to a directory containing a neo4j database. 19 | 20 | ## Usage 21 | 22 | ``` 23 | usage: NeoProfiler 24 | -db Path to directory where neo4j database is located 25 | -format Output format: valid values are json, markdown, or 26 | html 27 | -output Name of output file to write; program will print to 28 | console if not specified. 29 | ``` 30 | 31 | ## Motivation 32 | 33 | If you work with many Neo4J databases, it's often convenient to get a 34 | high-level picture of what is in a particular dataset before you jump in. If 35 | you write application code which interacts with a Neo4J database, it's good to 36 | be able to verify that the population of nodes and relationships you're writing 37 | have the properties that you expect. 38 | 39 | ## Output Example 40 | 41 | The program knows how to output JSON, Markdown, and HTML as output. To see 42 | a sample HTML report, download [sample-report.html](sample-report.html) and 43 | view it in a browser. 44 | 45 | ## Metagraphs 46 | 47 | One of the things that the profiler outputs is what we call a "metagraph". Neo4J 48 | database structures themselves can be described as a graph. The nodes in the metagraph 49 | describe what kinds of labeled nodes, relationships, and so on are in your database. 50 | The relationships in the metagraph outline how these things connect. 51 | 52 | Here's an example of a [metagraph](https://imgur.com/qsPvQFY). 53 | 54 |

55 | 56 | Notice that there are lighter grey and darker grey nodes; the light grey nodes whose label 57 | starts with "REL" are actually referring to relationships in the neo4j database. This 58 | graph indicates that nodes labeled "emp" can have a "leads_project" relationship to nodes 59 | labeled "project". Additionally, "project" nodes themselves can have a "leads_project" 60 | relationship to other "project" nodes. 61 | 62 | Nodes labeled "dept" can have "part_of" relationships back to other "dept" nodes; this is 63 | what a hierarchy might look like as expressed via a metagraph. 64 | 65 | A longer discussion of metagraphs can be [found here](http://gist.neo4j.org/?8640853). 66 | 67 | ## FAQ 68 | 69 | ### How does it work? 70 | 71 | The program contains a number of profilers, most of which run very simple 72 | Cypher queries against your database and provide summary statistics. Some 73 | profilers will actually discover data in your graph and then spawn other 74 | profilers which will run later. For example, if a label called "Person" is 75 | discovered in the data, a label profiler will be added to the run queue to 76 | inspect the population of nodes with that label. 77 | 78 | Right now, the focus is on simple queries that return descriptive statistics. 79 | 80 | Additionally, profiling right now must occur while the database is offline, 81 | because the profiler opens the database in embedded mode. 82 | 83 | ### Can I profile a database available via a URL? 84 | 85 | No, not yet - but this is part of the plan, and is in the works. 86 | 87 | ### Will the profiler modify my database? 88 | 89 | Absolutely not. All queries are read-only; any storage that is needed will 90 | happen in memory or via another method, to guarantee no modifications are 91 | made to the database being profiled. 92 | 93 | ### What version of Neo4J Does it use? ### 94 | 95 | At present, the code trunk uses 2.1.2. Because of some non-backwards compatible 96 | database format changes, this may require that you upgrade older databases to 97 | the format that 2.1 expects. 98 | 99 | -------------------------------------------------------------------------------- /SAMPLE.cypher: -------------------------------------------------------------------------------- 1 | // This is a sample cypher file intended to create a trivial small 2 | // database for testing purposes. 3 | // 4 | // The sample database contains a few individuals, and a few relationships 5 | // amongst them, for the profiler to discover and report on. 6 | 7 | create (p:Person {name:"Bob", age:35, gender:"M" }) 8 | -[:KNOWS]->(m:Person {name:"Susan", age:43, gender:"F"}); 9 | create (p:Person {name:"Sam", age:23, gender:"M" }) 10 | -[:KNOWS]->(m:Person {name:"Michael", age:22, gender:"M"}); 11 | 12 | match (boss:Person {name:"Susan"}), (emp:Person {name:"Sam"}), 13 | (emp2:Person {name:"Michael"}) 14 | create emp-[:WORKS_FOR]->boss, emp2-[:WORKS_FOR]->boss; 15 | 16 | -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- 1 | 3 | 4.0.0 4 | org.mitre 5 | neoprofiler 6 | 0.15 7 | Neo4J Database Profiler 8 | Software which can examine Neo4J databases and build descriptions of their contents. 9 | 10 | 11 | org.neo4j 12 | neo4j 13 | ${neo4j-version} 14 | 15 | 16 | org.neo4j 17 | neo4j-cypher 18 | ${neo4j-version} 19 | 20 | 21 | com.google.code.gson 22 | gson 23 | 2.8.2 24 | 25 | 26 | commons-cli 27 | commons-cli 28 | 1.4 29 | 30 | 31 | org.apache.velocity 32 | velocity 33 | 1.7 34 | 35 | 36 | org.neo4j.driver 37 | neo4j-java-driver 38 | 1.4.4 39 | 40 | 41 | org.springframework.boot 42 | spring-boot-starter-web 43 | 1.4.2.RELEASE 44 | 45 | 46 | 47 | 48 | 49 | 50 | org.springframework.boot 51 | spring-boot-maven-plugin 52 | 1.4.2.RELEASE 53 | 54 | true 55 | org.mitre.neoprofiler.NeoProfiler 56 | ZIP 57 | 58 | 59 | 60 | 61 | repackage 62 | 63 | 64 | 65 | 66 | 67 | 68 | org.apache.maven.plugins 69 | maven-compiler-plugin 70 | 3.1 71 | 72 | 1.7 73 | 1.7 74 | 75 | 76 | 77 | 78 | 79 | 80 | https://github.com/moxious/neoprofiler 81 | 82 | https://github.com/moxious/neoprofiler 83 | 84 | https://github.com/moxious/neoprofiler/issues 85 | 86 | 87 | 3.3.0 88 | 89 | 90 | -------------------------------------------------------------------------------- /sample-report.html: -------------------------------------------------------------------------------- 1 | 2 | 3 | 4 | Profile of /home/x/provenance.db/ generated 2014/05/12 09:16:58 5 | 6 | 64 | 65 | 66 | 67 | 68 |

69 | 70 |

71 | 72 | 194 | 195 | 196 | 197 | 198 | # Profile of /home/x/provenance.db/ generated 2014/05/12 09:16:58 199 | /home/x/provenance.db/ 200 | 201 | ## Schema 202 | *Information about Neo4J's database schema* 203 | 204 | ### Indexes 205 | * Constraint On nodes labeled Provenance. Property keys: 206 | * oid 207 | * Constraint On nodes labeled Actor. Property keys: 208 | * aid 209 | * Constraint On nodes labeled PrivilegeClass. Property keys: 210 | * pid 211 | * Constraint On nodes labeled NonProvenance. Property keys: 212 | * npid 213 | 214 | ### Non-Index Constraints 215 | * Constraint Type UNIQUENESS On nodes labeled Provenance. Property keys: 216 | * oid 217 | * Constraint Type UNIQUENESS On nodes labeled Actor. Property keys: 218 | * aid 219 | * Constraint Type UNIQUENESS On nodes labeled PrivilegeClass. Property keys: 220 | * pid 221 | * Constraint Type UNIQUENESS On nodes labeled NonProvenance. Property keys: 222 | * npid 223 | 224 | ### Observations 225 | * Run Time (ms): 3 226 | 227 | 228 | ## Label '(Unlabeled)' 229 | *Profile of nodes labeled '(Unlabeled)'* 230 | 231 | ### Observations 232 | * Outbound relationship types: 233 | * N/A 234 | * Run Time (ms): 2340 235 | * Sample properties: 236 | * Total: 0 237 | 238 | 239 | ## Nodes 240 | *Summary statistics about nodes in the graph* 241 | 242 | ### Observations 243 | * Node Labels: 244 | * [Provenance] 245 | * [Actor] 246 | * [PrivilegeClass] 247 | * Run Time (ms): 239 248 | * Total: 13266 249 | 250 | 251 | ## Relationships 252 | *Summary statistics about relationships in the graph* 253 | 254 | ### Observations 255 | * Available Relationship Types: 256 | * dominates 257 | * owns 258 | * triggered 259 | * controlledBy 260 | * contributed 261 | * generated 262 | * input to 263 | * Run Time (ms): 268 264 | * Total Relationships: 11948 265 | 266 | 267 | ## Label 'Provenance' 268 | *Profile of nodes labeled 'Provenance'* 269 | 270 | ### Observations 271 | * Outbound relationship types: 272 | * triggered 273 | * contributed 274 | * generated 275 | * input to 276 | * owns 277 | * Run Time (ms): 441 278 | * Sample properties: 279 | * oid (String) required 280 | * when_start (String) optional 281 | * workflow (String) optional 282 | * name (String) required 283 | * SGFs (String[]) optional 284 | * subtype (String) required 285 | * ownerid (String) required 286 | * when_end (String) optional 287 | * certainty (String) required 288 | * activity (String) optional 289 | * type (String) required 290 | * content (String) optional 291 | * created (Long) required 292 | * metadata:implus:motif (String) optional 293 | * Total nodes: 13225 294 | 295 | 296 | ## Label 'Actor' 297 | *Profile of nodes labeled 'Actor'* 298 | 299 | ### Observations 300 | * Outbound relationship types: 301 | * N/A 302 | * Run Time (ms): 44 303 | * Sample properties: 304 | * created (Long) optional 305 | * aid (String) optional 306 | * name (String) optional 307 | * type (String) optional 308 | * displayName (String) optional 309 | * Total nodes: 25 310 | 311 | 312 | ## Label 'PrivilegeClass' 313 | *Profile of nodes labeled 'PrivilegeClass'* 314 | 315 | ### Observations 316 | * Outbound relationship types: 317 | * dominates 318 | * controlledBy 319 | * Run Time (ms): 41 320 | * Sample properties: 321 | * name (String) optional 322 | * type (String) optional 323 | * pid (String) optional 324 | * created (Long) optional 325 | * description (String) optional 326 | * Total nodes: 16 327 | 328 | 329 | ## Relationships Typed 'dominates' 330 | *Profile of relationships of type 'dominates'* 331 | 332 | ### Observations 333 | * Run Time (ms): 190 334 | * Sample properties: 335 | * Total relationships: 16 336 | * domain: 337 | * PrivilegeClass 338 | * range: 339 | * PrivilegeClass 340 | 341 | 342 | ## Relationships Typed 'owns' 343 | *Profile of relationships of type 'owns'* 344 | 345 | ### Observations 346 | * Run Time (ms): 132 347 | * Sample properties: 348 | * Total relationships: 77 349 | * domain: 350 | * Actor 351 | * range: 352 | * Provenance 353 | 354 | 355 | ## Relationships Typed 'triggered' 356 | *Profile of relationships of type 'triggered'* 357 | 358 | ### Observations 359 | * Run Time (ms): 108 360 | * Sample properties: 361 | * workflow (String) required 362 | * Total relationships: 1257 363 | * domain: 364 | * Provenance 365 | * range: 366 | * Provenance 367 | 368 | 369 | ## Relationships Typed 'controlledBy' 370 | *Profile of relationships of type 'controlledBy'* 371 | 372 | ### Observations 373 | * Run Time (ms): 80 374 | * Sample properties: 375 | * Total relationships: 178 376 | * domain: 377 | * Provenance 378 | * range: 379 | * PrivilegeClass 380 | 381 | 382 | ## Relationships Typed 'contributed' 383 | *Profile of relationships of type 'contributed'* 384 | 385 | ### Observations 386 | * Run Time (ms): 93 387 | * Sample properties: 388 | * workflow (String) required 389 | * Total relationships: 483 390 | * domain: 391 | * Provenance 392 | * range: 393 | * Provenance 394 | 395 | 396 | ## Relationships Typed 'generated' 397 | *Profile of relationships of type 'generated'* 398 | 399 | ### Observations 400 | * Run Time (ms): 114 401 | * Sample properties: 402 | * workflow (String) required 403 | * Total relationships: 2911 404 | * domain: 405 | * Provenance 406 | * range: 407 | * Provenance 408 | 409 | 410 | ## Relationships Typed 'input to' 411 | *Profile of relationships of type 'input to'* 412 | 413 | ### Observations 414 | * Run Time (ms): 139 415 | * Sample properties: 416 | * workflow (String) required 417 | * Total relationships: 7026 418 | * domain: 419 | * Provenance 420 | * range: 421 | * Provenance 422 | 423 | 424 | 425 | 426 | 427 | 428 | -------------------------------------------------------------------------------- /src/main/java/org/mitre/neoprofiler/NeoProfiler.java: -------------------------------------------------------------------------------- 1 | package org.mitre.neoprofiler; 2 | 3 | import java.io.File; 4 | import java.io.FileWriter; 5 | import java.io.IOException; 6 | import java.io.StringWriter; 7 | import java.io.Writer; 8 | import java.util.ArrayList; 9 | import java.util.List; 10 | 11 | import org.apache.commons.cli.CommandLine; 12 | import org.apache.commons.cli.CommandLineParser; 13 | import org.apache.commons.cli.GnuParser; 14 | import org.apache.commons.cli.HelpFormatter; 15 | import org.apache.commons.cli.OptionBuilder; 16 | import org.apache.commons.cli.Options; 17 | import org.apache.commons.cli.ParseException; 18 | import org.mitre.neoprofiler.html.HTMLMaker; 19 | import org.mitre.neoprofiler.markdown.MarkdownMaker; 20 | import org.mitre.neoprofiler.profile.DBProfile; 21 | import org.mitre.neoprofiler.profile.NeoProfile; 22 | import org.mitre.neoprofiler.profiler.NodesProfiler; 23 | import org.mitre.neoprofiler.profiler.Profiler; 24 | import org.mitre.neoprofiler.profiler.RelationshipsProfiler; 25 | import org.mitre.neoprofiler.profiler.SchemaProfiler; 26 | import org.mitre.neoprofiler.profiler.UnlabeledNodeProfiler; 27 | import org.neo4j.graphdb.GraphDatabaseService; 28 | import org.neo4j.graphdb.factory.GraphDatabaseFactory; 29 | 30 | import org.neo4j.driver.v1.AuthTokens; 31 | import org.neo4j.driver.v1.Driver; 32 | import org.neo4j.driver.v1.GraphDatabase; 33 | import org.neo4j.driver.v1.Session; 34 | import org.neo4j.driver.v1.StatementResult; 35 | import org.neo4j.driver.v1.Transaction; 36 | import org.neo4j.driver.v1.TransactionWork; 37 | 38 | import com.google.gson.Gson; 39 | import com.google.gson.GsonBuilder; 40 | 41 | public class NeoProfiler { 42 | protected Driver driver = null; 43 | protected String storageLoc = null; 44 | protected Session session = null; 45 | protected List schedule = new ArrayList(); 46 | 47 | public enum Format { MARKDOWN, HTML, JSON }; 48 | 49 | public NeoProfiler(String storageLoc, Driver driver) { 50 | this.driver = driver; 51 | this.storageLoc = storageLoc; 52 | } 53 | 54 | public Driver getDriver() { return driver; } 55 | public Transaction beginTx() { 56 | if (this.session == null) { 57 | this.session = driver.session(); 58 | } 59 | 60 | return this.session.beginTransaction(); 61 | } 62 | 63 | public void schedule(Profiler p) { 64 | schedule.add(p); 65 | } 66 | 67 | public DBProfile run() { 68 | DBProfile p = new DBProfile(storageLoc); 69 | 70 | schedule(new SchemaProfiler()); 71 | schedule(new UnlabeledNodeProfiler()); 72 | schedule(new NodesProfiler()); 73 | schedule(new RelationshipsProfiler()); 74 | 75 | int x=0; 76 | 77 | while(x < schedule.size()) { 78 | Profiler profiler = schedule.get(x); 79 | System.out.println("Running " + profiler.describe() + " (" + (x+1) + " of " + schedule.size() + ")"); 80 | long t1 = System.currentTimeMillis(); 81 | 82 | NeoProfile prof = null; 83 | 84 | try { 85 | prof = profiler.run(this); 86 | } catch(Exception exc) { 87 | System.err.println(profiler.getClass().getName() + " failed: " + exc.getMessage()); 88 | exc.printStackTrace(); 89 | x++; 90 | continue; 91 | } 92 | long t2 = System.currentTimeMillis(); 93 | 94 | prof.addObservation("Run Time (ms)", (t2 - t1)); 95 | 96 | if(prof != null) p.addProfile(prof); 97 | x++; 98 | } 99 | 100 | return p; 101 | } // End run 102 | 103 | public static Options makeCLIOptions() { 104 | Options options = new Options(); 105 | 106 | options.addOption(OptionBuilder.withArgName("db") 107 | .hasArg() 108 | .isRequired() 109 | .withDescription("Path to directory where neo4j database is located") 110 | .create("db")); 111 | 112 | options.addOption(OptionBuilder.withArgName("format") 113 | .hasArg() 114 | .isRequired() 115 | .withDescription("Output format: valid values are json, markdown, or html") 116 | .create("format")); 117 | 118 | options.addOption(OptionBuilder.withArgName("output") 119 | .hasArg() 120 | .isRequired(false) 121 | .withDescription("Name of output file to write; program will print to console if not specified.") 122 | .create("output")); 123 | 124 | return options; 125 | } 126 | 127 | public static void main(String [] args) throws Exception { 128 | CommandLineParser parser = new GnuParser(); 129 | 130 | try { 131 | CommandLine line = parser.parse(makeCLIOptions(), args ); 132 | 133 | String path = line.getOptionValue("db"); 134 | String format = line.getOptionValue("format"); 135 | String output = line.getOptionValue("output"); 136 | 137 | Writer destination = null; 138 | if(output == null) destination = new StringWriter(); 139 | 140 | File f = new File(path); 141 | 142 | Format fmt = Format.HTML; 143 | 144 | if(format == null) fmt = Format.HTML; 145 | else if("html".equals(format)) fmt = Format.HTML; 146 | else if("json".equals(format)) fmt = Format.JSON; 147 | else if("markdown".equals(format)) fmt = Format.MARKDOWN; 148 | else { 149 | System.err.println("Invalid or unrecognized format '" + format + "': using default of html"); 150 | } 151 | 152 | if(output != null) { 153 | try { destination = new FileWriter(output); } 154 | catch(IOException exc) { 155 | System.err.println("Can not create output file at " + output + ": " + exc.getMessage()); 156 | usage(); 157 | System.exit(1); 158 | } 159 | } else { 160 | // Instead of writing to a file, accumulate in this buffer then print out later. 161 | destination = new StringWriter(); 162 | } 163 | 164 | // Run the profile. 165 | profile(path, fmt, destination); 166 | 167 | // Check for if final results are written to console, or out to a file. 168 | if(output == null) System.out.println(((StringWriter)destination).getBuffer()); 169 | else destination.close(); 170 | 171 | System.out.println("Done."); 172 | System.exit(0); 173 | } catch(ParseException exc) { 174 | System.err.println(exc.getMessage()); 175 | usage(); 176 | System.exit(1); 177 | } 178 | } 179 | 180 | public static void usage() { 181 | HelpFormatter formatter = new HelpFormatter(); 182 | formatter.printHelp("NeoProfiler", makeCLIOptions()); 183 | } 184 | 185 | public static void profile(String path, Format fmt, Writer output) throws IOException { 186 | String uri = "bolt://localhost"; 187 | String user = "neo4j"; 188 | String password = "admin"; 189 | 190 | Driver driver = GraphDatabase.driver(uri, AuthTokens.basic( user, password ) ); 191 | 192 | NeoProfiler profiler = new NeoProfiler(path, driver); 193 | 194 | DBProfile profile = profiler.run(); 195 | MarkdownMaker mm = new MarkdownMaker(); 196 | 197 | System.out.println("Writing report..."); 198 | switch(fmt) { 199 | case JSON: 200 | Gson gson = new GsonBuilder().setPrettyPrinting().create(); 201 | output.write(gson.toJson(profile)); 202 | break; 203 | 204 | case MARKDOWN: 205 | mm.markdown(profile, output); 206 | break; 207 | 208 | case HTML: 209 | new HTMLMaker().html(profile, output); 210 | break; 211 | 212 | default: 213 | throw new RuntimeException("Invalid format"); 214 | } 215 | } 216 | } // End NeoProfiler 217 | -------------------------------------------------------------------------------- /src/main/java/org/mitre/neoprofiler/html/HTMLMaker.java: -------------------------------------------------------------------------------- 1 | package org.mitre.neoprofiler.html; 2 | 3 | import java.io.IOException; 4 | import java.io.StringWriter; 5 | import java.io.Writer; 6 | import java.util.Collection; 7 | import java.util.List; 8 | 9 | import org.apache.velocity.Template; 10 | import org.apache.velocity.VelocityContext; 11 | import org.apache.velocity.app.VelocityEngine; 12 | import org.apache.velocity.runtime.RuntimeConstants; 13 | import org.apache.velocity.runtime.resource.loader.ClasspathResourceLoader; 14 | import org.mitre.neoprofiler.markdown.MarkdownMaker; 15 | import org.mitre.neoprofiler.profile.DBProfile; 16 | import org.mitre.neoprofiler.profile.LabelProfile; 17 | import org.mitre.neoprofiler.profile.NeoProfile; 18 | import org.mitre.neoprofiler.profile.RelationshipTypeProfile; 19 | 20 | /** 21 | * Class that renders a DBProfile as HTML. 22 | * The general approach is to write a graph structure in JSON rendered via D3.js, and to populate the rest 23 | * of the page with regular markdown from the MarkdownGenerator, rendered to HTML by strapdown.js. 24 | * @author moxious 25 | */ 26 | public class HTMLMaker { 27 | public HTMLMaker() { ; } 28 | 29 | public String generateGraph(DBProfile profile) { 30 | StringBuffer b = new StringBuffer("var links = [\n"); 31 | 32 | for(NeoProfile p : profile.getProfiles()) { 33 | if(p instanceof LabelProfile) { 34 | LabelProfile lp = (LabelProfile)p; 35 | String label = (String)lp.getParameter("label"); 36 | 37 | List