├── .gitignore ├── requirements.txt ├── README.rst ├── pylintdb.py └── LICENSE.TXT /.gitignore: -------------------------------------------------------------------------------- 1 | *.pyc 2 | *.db 3 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | dataset 2 | click 3 | -------------------------------------------------------------------------------- /README.rst: -------------------------------------------------------------------------------- 1 | ######### 2 | Pylint DB 3 | ######### 4 | 5 | Put pylint results into a SQLite database, then query them. 6 | 7 | Typical use: 8 | 9 | #. Run pylint in the usual way. 10 | 11 | #. Read the reports into the database:: 12 | 13 | $ python pylintdb.py read REPORTFILE.txt REPORTFILE2.txt ... 14 | 15 | #. Get the author and commit information for each violation:: 16 | 17 | $ python pylintdb.py blame 18 | 19 | #. Query the database to find violations:: 20 | 21 | $ python pylintdb.py where "author = 'ned@edx.org'" 22 | $ python pylintdb.py where "code = 'W0110' and file like 'common/%'" 23 | $ python pylintdb.py where "slug = 'unused-import'" 24 | 25 | #. You can also use the sqlite3 command (available separately):: 26 | 27 | $ sqlite3 pylint.db 28 | sqlite> select * from (select slug, count(*) c from violation where modified > '2017-03-22' group by 1 order by 2) where c >= 5; 29 | slug c 30 | ------------------------------ ---------- 31 | relative-import 5 32 | protected-access 5 33 | unused-variable 5 34 | unused-argument 8 35 | line-too-long 8 36 | unused-import 10 37 | invalid-name 10 38 | bad-continuation 14 39 | no-member 24 40 | missing-docstring 63 41 | 42 | There are details in the code that you will have to change: GIT_DIR is the 43 | location of the source you are linting, and the pylint reporting format might 44 | be specific to edX. 45 | 46 | Licensed under the Apache 2.0 license. 47 | -------------------------------------------------------------------------------- /pylintdb.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | """Put pylint violations into a SQLite database, and then query them.""" 3 | 4 | import concurrent.futures 5 | import itertools 6 | import os.path 7 | import re 8 | import subprocess 9 | 10 | import click 11 | import dataset 12 | 13 | DB = 'sqlite:///pylint.db' 14 | GIT_DIR = '/src/edx/edx-platform' 15 | 16 | def get_database(): 17 | return dataset.connect(DB) 18 | 19 | def get_table(): 20 | return get_database()['violation'] 21 | 22 | 23 | # Doing this oddly so I don't have to repeat the docstring... 24 | def cli(): 25 | pass 26 | cli.__doc__ = __doc__ 27 | cli = click.group()(cli) 28 | 29 | 30 | # edX pylint format, which might be different than the default. 31 | violation_regex = r"^(?P.*):(?P\d+): \[(?P\w+)\((?P[\w-]+)\), (?P.*)\] (?P.*)$" 32 | 33 | def read_report(violations, report): 34 | inserted = 0 35 | with click.progressbar(report, show_pos=True) as lines_bar: 36 | for line in report: 37 | m = re.search(violation_regex, line) 38 | if m: 39 | data = m.groupdict() 40 | data.update(dict( 41 | commit=None, 42 | modified=None, 43 | author=None, 44 | source=None, 45 | )) 46 | violations.insert(data) 47 | inserted += 1 48 | lines_bar.update(1) 49 | 50 | return inserted 51 | 52 | 53 | @cli.command() 54 | @click.argument('reports', nargs=-1, type=click.File('r')) 55 | def read(reports): 56 | """Read a pylint report into the database.""" 57 | violations = get_table() 58 | for report in reports: 59 | inserted = read_report(violations, report) 60 | click.echo(f"Inserted {inserted} violations from {report.name}") 61 | 62 | 63 | def blame_one(file_group): 64 | """Run git blame on one file and return the updated rows.""" 65 | filename, rows = file_group 66 | 67 | cmd = ['git', '-C', GIT_DIR, 'blame', '-e'] 68 | for row in rows: 69 | cmd.extend(["-L", f"{row['lineno']},+1"]) 70 | cmd.append(filename) 71 | 72 | try: 73 | output = subprocess.check_output(cmd, stderr=subprocess.STDOUT).decode('utf8') 74 | except subprocess.CalledProcessError: 75 | print(f"ERROR: {cmd}") 76 | return None 77 | 78 | line_blame = {} 79 | for line in output.splitlines(): 80 | # git blame output: 81 | # 38bdcabe537 ( 2012-08-13 23:23:13 -0700 4) import models 82 | m = re.search(r"^(?P\w+) .*\(\<(?P.*)\> +(?P[-+\d: ]+) +(?P\d+)\) (?P.*)$", line) 83 | if m: 84 | g = m.groupdict() 85 | line_blame[g['lineno']] = g 86 | 87 | results = [] 88 | for row in rows: 89 | data = line_blame.get(row['lineno']) 90 | if data is None: 91 | continue 92 | row.update(data) 93 | results.append(row) 94 | 95 | return results 96 | 97 | 98 | @cli.command() 99 | def blame(): 100 | """Use git blame to get the commit, author, and modified date for each violation.""" 101 | violations = get_table() 102 | rows = list(violations.find(author=None, order_by='file')) 103 | num_rows = len(rows) 104 | file_groups = itertools.groupby(rows, key=lambda r: r['file']) 105 | file_groups = [(f, list(d)) for f, d in file_groups] 106 | 107 | with click.progressbar(length=num_rows, show_pos=True) as bar: 108 | with concurrent.futures.ThreadPoolExecutor() as executor: 109 | for updates in executor.map(blame_one, file_groups): 110 | if updates is None: 111 | continue 112 | for update in updates: 113 | violations.update(update, ['id']) 114 | bar.update(1) 115 | 116 | @cli.command() 117 | @click.argument('condition') 118 | def where(condition): 119 | """List out violations, based on a SQL where-clause.""" 120 | sql = f"select * from violation where {condition}" 121 | for row in get_database().query(sql): 122 | print("{gitdir}/{file}:{lineno}: {code}({slug}) {message}".format(gitdir=GIT_DIR, **row)) 123 | 124 | 125 | @cli.command() 126 | def authors(): 127 | """List out all authors and their violation counts.""" 128 | sql = f"select author,count(*) as violationcount from violation group by author order by violationcount DESC" 129 | for row in get_database().query(sql): 130 | print(f"Author: {row['author']} - {row['violationcount']} violations") 131 | 132 | 133 | @cli.command() 134 | @click.argument("author") 135 | def authorviolations(author): 136 | """List out violation count by a particular author.""" 137 | sql = f"select code, slug, count(code) as violationcount from violation where author='{author}' group by code order by violationcount DESC" 138 | print(f"Violations for {author}\n") 139 | for row in get_database().query(sql): 140 | print(f"{row['code']}:{row['slug']} - {row['violationcount']}") 141 | 142 | 143 | if __name__ == '__main__': 144 | cli() 145 | -------------------------------------------------------------------------------- /LICENSE.TXT: -------------------------------------------------------------------------------- 1 | 2 | Apache License 3 | Version 2.0, January 2004 4 | http://www.apache.org/licenses/ 5 | 6 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 7 | 8 | 1. Definitions. 9 | 10 | "License" shall mean the terms and conditions for use, reproduction, 11 | and distribution as defined by Sections 1 through 9 of this document. 12 | 13 | "Licensor" shall mean the copyright owner or entity authorized by 14 | the copyright owner that is granting the License. 15 | 16 | "Legal Entity" shall mean the union of the acting entity and all 17 | other entities that control, are controlled by, or are under common 18 | control with that entity. For the purposes of this definition, 19 | "control" means (i) the power, direct or indirect, to cause the 20 | direction or management of such entity, whether by contract or 21 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 22 | outstanding shares, or (iii) beneficial ownership of such entity. 23 | 24 | "You" (or "Your") shall mean an individual or Legal Entity 25 | exercising permissions granted by this License. 26 | 27 | "Source" form shall mean the preferred form for making modifications, 28 | including but not limited to software source code, documentation 29 | source, and configuration files. 30 | 31 | "Object" form shall mean any form resulting from mechanical 32 | transformation or translation of a Source form, including but 33 | not limited to compiled object code, generated documentation, 34 | and conversions to other media types. 35 | 36 | "Work" shall mean the work of authorship, whether in Source or 37 | Object form, made available under the License, as indicated by a 38 | copyright notice that is included in or attached to the work 39 | (an example is provided in the Appendix below). 40 | 41 | "Derivative Works" shall mean any work, whether in Source or Object 42 | form, that is based on (or derived from) the Work and for which the 43 | editorial revisions, annotations, elaborations, or other modifications 44 | represent, as a whole, an original work of authorship. For the purposes 45 | of this License, Derivative Works shall not include works that remain 46 | separable from, or merely link (or bind by name) to the interfaces of, 47 | the Work and Derivative Works thereof. 48 | 49 | "Contribution" shall mean any work of authorship, including 50 | the original version of the Work and any modifications or additions 51 | to that Work or Derivative Works thereof, that is intentionally 52 | submitted to Licensor for inclusion in the Work by the copyright owner 53 | or by an individual or Legal Entity authorized to submit on behalf of 54 | the copyright owner. For the purposes of this definition, "submitted" 55 | means any form of electronic, verbal, or written communication sent 56 | to the Licensor or its representatives, including but not limited to 57 | communication on electronic mailing lists, source code control systems, 58 | and issue tracking systems that are managed by, or on behalf of, the 59 | Licensor for the purpose of discussing and improving the Work, but 60 | excluding communication that is conspicuously marked or otherwise 61 | designated in writing by the copyright owner as "Not a Contribution." 62 | 63 | "Contributor" shall mean Licensor and any individual or Legal Entity 64 | on behalf of whom a Contribution has been received by Licensor and 65 | subsequently incorporated within the Work. 66 | 67 | 2. Grant of Copyright License. Subject to the terms and conditions of 68 | this License, each Contributor hereby grants to You a perpetual, 69 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 70 | copyright license to reproduce, prepare Derivative Works of, 71 | publicly display, publicly perform, sublicense, and distribute the 72 | Work and such Derivative Works in Source or Object form. 73 | 74 | 3. Grant of Patent License. Subject to the terms and conditions of 75 | this License, each Contributor hereby grants to You a perpetual, 76 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 77 | (except as stated in this section) patent license to make, have made, 78 | use, offer to sell, sell, import, and otherwise transfer the Work, 79 | where such license applies only to those patent claims licensable 80 | by such Contributor that are necessarily infringed by their 81 | Contribution(s) alone or by combination of their Contribution(s) 82 | with the Work to which such Contribution(s) was submitted. If You 83 | institute patent litigation against any entity (including a 84 | cross-claim or counterclaim in a lawsuit) alleging that the Work 85 | or a Contribution incorporated within the Work constitutes direct 86 | or contributory patent infringement, then any patent licenses 87 | granted to You under this License for that Work shall terminate 88 | as of the date such litigation is filed. 89 | 90 | 4. Redistribution. You may reproduce and distribute copies of the 91 | Work or Derivative Works thereof in any medium, with or without 92 | modifications, and in Source or Object form, provided that You 93 | meet the following conditions: 94 | 95 | (a) You must give any other recipients of the Work or 96 | Derivative Works a copy of this License; and 97 | 98 | (b) You must cause any modified files to carry prominent notices 99 | stating that You changed the files; and 100 | 101 | (c) You must retain, in the Source form of any Derivative Works 102 | that You distribute, all copyright, patent, trademark, and 103 | attribution notices from the Source form of the Work, 104 | excluding those notices that do not pertain to any part of 105 | the Derivative Works; and 106 | 107 | (d) If the Work includes a "NOTICE" text file as part of its 108 | distribution, then any Derivative Works that You distribute must 109 | include a readable copy of the attribution notices contained 110 | within such NOTICE file, excluding those notices that do not 111 | pertain to any part of the Derivative Works, in at least one 112 | of the following places: within a NOTICE text file distributed 113 | as part of the Derivative Works; within the Source form or 114 | documentation, if provided along with the Derivative Works; or, 115 | within a display generated by the Derivative Works, if and 116 | wherever such third-party notices normally appear. The contents 117 | of the NOTICE file are for informational purposes only and 118 | do not modify the License. You may add Your own attribution 119 | notices within Derivative Works that You distribute, alongside 120 | or as an addendum to the NOTICE text from the Work, provided 121 | that such additional attribution notices cannot be construed 122 | as modifying the License. 123 | 124 | You may add Your own copyright statement to Your modifications and 125 | may provide additional or different license terms and conditions 126 | for use, reproduction, or distribution of Your modifications, or 127 | for any such Derivative Works as a whole, provided Your use, 128 | reproduction, and distribution of the Work otherwise complies with 129 | the conditions stated in this License. 130 | 131 | 5. Submission of Contributions. Unless You explicitly state otherwise, 132 | any Contribution intentionally submitted for inclusion in the Work 133 | by You to the Licensor shall be under the terms and conditions of 134 | this License, without any additional terms or conditions. 135 | Notwithstanding the above, nothing herein shall supersede or modify 136 | the terms of any separate license agreement you may have executed 137 | with Licensor regarding such Contributions. 138 | 139 | 6. Trademarks. This License does not grant permission to use the trade 140 | names, trademarks, service marks, or product names of the Licensor, 141 | except as required for reasonable and customary use in describing the 142 | origin of the Work and reproducing the content of the NOTICE file. 143 | 144 | 7. Disclaimer of Warranty. Unless required by applicable law or 145 | agreed to in writing, Licensor provides the Work (and each 146 | Contributor provides its Contributions) on an "AS IS" BASIS, 147 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 148 | implied, including, without limitation, any warranties or conditions 149 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 150 | PARTICULAR PURPOSE. You are solely responsible for determining the 151 | appropriateness of using or redistributing the Work and assume any 152 | risks associated with Your exercise of permissions under this License. 153 | 154 | 8. Limitation of Liability. In no event and under no legal theory, 155 | whether in tort (including negligence), contract, or otherwise, 156 | unless required by applicable law (such as deliberate and grossly 157 | negligent acts) or agreed to in writing, shall any Contributor be 158 | liable to You for damages, including any direct, indirect, special, 159 | incidental, or consequential damages of any character arising as a 160 | result of this License or out of the use or inability to use the 161 | Work (including but not limited to damages for loss of goodwill, 162 | work stoppage, computer failure or malfunction, or any and all 163 | other commercial damages or losses), even if such Contributor 164 | has been advised of the possibility of such damages. 165 | 166 | 9. Accepting Warranty or Additional Liability. While redistributing 167 | the Work or Derivative Works thereof, You may choose to offer, 168 | and charge a fee for, acceptance of support, warranty, indemnity, 169 | or other liability obligations and/or rights consistent with this 170 | License. However, in accepting such obligations, You may act only 171 | on Your own behalf and on Your sole responsibility, not on behalf 172 | of any other Contributor, and only if You agree to indemnify, 173 | defend, and hold each Contributor harmless for any liability 174 | incurred by, or claims asserted against, such Contributor by reason 175 | of your accepting any such warranty or additional liability. 176 | 177 | END OF TERMS AND CONDITIONS 178 | 179 | APPENDIX: How to apply the Apache License to your work. 180 | 181 | To apply the Apache License to your work, attach the following 182 | boilerplate notice, with the fields enclosed by brackets "[]" 183 | replaced with your own identifying information. (Don't include 184 | the brackets!) The text should be enclosed in the appropriate 185 | comment syntax for the file format. We also recommend that a 186 | file or class name and description of purpose be included on the 187 | same "printed page" as the copyright notice for easier 188 | identification within third-party archives. 189 | 190 | Copyright [yyyy] [name of copyright owner] 191 | 192 | Licensed under the Apache License, Version 2.0 (the "License"); 193 | you may not use this file except in compliance with the License. 194 | You may obtain a copy of the License at 195 | 196 | http://www.apache.org/licenses/LICENSE-2.0 197 | 198 | Unless required by applicable law or agreed to in writing, software 199 | distributed under the License is distributed on an "AS IS" BASIS, 200 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 201 | See the License for the specific language governing permissions and 202 | limitations under the License. 203 | --------------------------------------------------------------------------------