├── .gitignore ├── .gitattributes ├── tests ├── logs │ ├── common.log │ ├── custom_regex_custom_date.log │ ├── common_vhost.log │ ├── icecast2.log │ ├── ncsa_extended.log │ ├── ovh.log │ ├── common_complete.log │ ├── shoutcast.log │ ├── s3.log │ ├── elb.log │ ├── netscaler.log │ ├── amazon_cloudfront_web.log │ ├── iis.log │ ├── amazon_cloudfront_rtmp.log │ ├── iis_custom.log │ ├── nginx_json.log │ └── logs_to_tests.log ├── run_tests.sh └── tests.py ├── .travis.yml ├── CONTRIBUTING.md ├── LEGALNOTICE ├── README.md ├── LICENSE.txt └── import_logs.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.pyc -------------------------------------------------------------------------------- /.gitattributes: -------------------------------------------------------------------------------- 1 | # Auto detect text files and perform LF normalization 2 | * text eol=lf 3 | -------------------------------------------------------------------------------- /tests/logs/common.log: -------------------------------------------------------------------------------- 1 | 1.2.3.4 - theuser [10/Feb/2012:16:42:07 -0500] "GET / HTTP/1.0" 301 368 2 | -------------------------------------------------------------------------------- /tests/logs/custom_regex_custom_date.log: -------------------------------------------------------------------------------- 1 | 1.2.3.4 - - [February - 10, 2012:16:42:07] "GET / HTTP/1.0" 301 368 2 | -------------------------------------------------------------------------------- /tests/logs/common_vhost.log: -------------------------------------------------------------------------------- 1 | www.example.com 1.2.3.4 - theuser [10/Feb/2012:16:42:07 -0500] "GET / HTTP/1.0" 301 368 2 | -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- 1 | language: python 2 | 3 | python: 4 | - "2.6" 5 | - "2.7" 6 | # 3.0 is not supported 7 | 8 | sudo: false 9 | 10 | script: 11 | - cd tests 12 | - ./run_tests.sh 13 | 14 | -------------------------------------------------------------------------------- /tests/logs/icecast2.log: -------------------------------------------------------------------------------- 1 | 1.2.3.4 - theuser [10/Feb/2012:16:42:07 -0500] "GET / HTTP/1.0" 301 368 "-" "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11" 1807 -------------------------------------------------------------------------------- /tests/logs/ncsa_extended.log: -------------------------------------------------------------------------------- 1 | 1.2.3.4 - theuser [10/Feb/2012:16:42:07 -0500] "GET / HTTP/1.0" 301 368 "-" "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11" 2 | -------------------------------------------------------------------------------- /tests/logs/ovh.log: -------------------------------------------------------------------------------- 1 | 1.2.3.4 www.example.com theuser [10/Feb/2012:16:42:07 -0500] "GET / HTTP/1.1" 301 368 "-" "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11" 2 | -------------------------------------------------------------------------------- /tests/logs/common_complete.log: -------------------------------------------------------------------------------- 1 | www.example.com 1.2.3.4 - theuser [10/Feb/2012:16:42:07 -0500] "GET / HTTP/1.0" 301 368 "-" "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11" 2 | -------------------------------------------------------------------------------- /tests/run_tests.sh: -------------------------------------------------------------------------------- 1 | #!/bin/sh 2 | 3 | cd $(dirname $0) 4 | 5 | # Make sure nosetests is installed. 6 | nosetests -V >/dev/null 2>&1 || (echo "nose (http://readthedocs.org/docs/nose/en/latest/) must be installed"; exit 1) 7 | 8 | PYTHONPATH=.. nosetests tests.py $* 9 | -------------------------------------------------------------------------------- /tests/logs/shoutcast.log: -------------------------------------------------------------------------------- 1 | #Software: SHOUTcast 2 | #Version: 2.4.7.256 3 | #Fields: c-ip c-dns date time cs-uri-stem c-status cs(User-Agent) sc-bytes x-duration avgbandwidth 4 | 1.2.3.4 5.6.7.8 2015-12-07 10:37:05 /stream?title=UKR%20Nights 200 NSPlayer%2F10.0.0.3702%20WMFSDK%2F10.0 65580 1 524640 -------------------------------------------------------------------------------- /tests/logs/s3.log: -------------------------------------------------------------------------------- 1 | b659b576cff1e15e4c0313ff8930fba9f53e6794567f5c60dab3abf2f8dfb6cc www.example.com [10/Feb/2012:16:42:07 -0500] 1.2.3.4 arn:aws:iam::179580289999:user/phillip.boss EB3502676500C6BE WEBSITE.GET.OBJECT index "GET /index HTTP/1.1" 200 - 368 368 10 9 "-" "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11" -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- 1 | # How to contribute 2 | 3 | Great to have you here! 4 | 5 | ## How to submit a bug report or suggest a feature? 6 | 7 | Please read the recommendations on writing a good [bug report](https://developer.piwik.org/guides/core-team-workflow#submitting-a-bug-report) or [feature request](https://developer.piwik.org/guides/core-team-workflow#submitting-a-feature-request). 8 | 9 | -------------------------------------------------------------------------------- /tests/logs/elb.log: -------------------------------------------------------------------------------- 1 | 2015-05-13T23:39:43.945958Z my-loadbalancer 1.2.3.4:2817 10.0.0.1:80 0.000086 0.001048 0.001337 200 200 0 57 "GET https://www.example.com:443/path/index.html HTTP/1.1" "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11" DHE-RSA-AES128-SHA TLSv1.2 2 | # line below should be ignored, as it is a TCP request, not containing any HTTP request data 3 | 2015-05-13T23:39:43.945958Z my-loadbalancer 192.168.131.39:2817 10.0.0.1:80 0.001069 0.000028 0.000041 - - 82 305 "- - - " "-" - - -------------------------------------------------------------------------------- /tests/logs/netscaler.log: -------------------------------------------------------------------------------- 1 | #Version: 1.0 2 | #Software: Netscaler Web Logging(NSWL) 3 | #Date: 2014-02-18 11:55:13 4 | #Fields: date time c-ip cs-username sc-servicename s-ip s-port cs-method cs-uri-stem cs-uri-query sc-status cs-bytes sc-bytes time-taken cs-version cs(User-Agent) cs(Cookie) cs(Referer) 5 | 2012-08-16 11:55:13 172.20.1.0 - HTTP 192.168.6.254 8080 GET /Citrix/XenApp/Wan/auth/login.jsp - 302 247 355 1 HTTP/1.1 Mozilla/4.0+(compatible;+MSIE+7.0;+Windows+NT+5.1;+Trident/4.0;+.NET+CLR+1.1.4322;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.04506.648;+.NET+CLR+3.5.21022) - - 6 | -------------------------------------------------------------------------------- /tests/logs/amazon_cloudfront_web.log: -------------------------------------------------------------------------------- 1 | #Version: 1.0 2 | #Fields: date time x-edge-location sc-bytes c-ip cs-method cs(Host) cs-uri-stem sc-status cs(Referer) cs(User-Agent) cs-uri-query cs(Cookie) x-edge-result-type x-edge-request-id x-host-header cs-protocol cs-bytes time-taken 3 | 2014-05-23 01:13:11 FRA2 182 192.0.2.10 GET d111111abcdef8.cloudfront.net /view/my/file.html 200 www.displaymyfiles.com Mozilla/4.0%20(compatible;%20MSIE%205.0b1;%20Mac_PowerPC) - zip=98101 RefreshHit MRVMF7KydIvxMWfJIglgwHQwZsbG2IhRJ07sn9AkKUFSHS9EXAMPLE== d111111abcdef8.cloudfront.net http - 0.001 4 | -------------------------------------------------------------------------------- /tests/logs/iis.log: -------------------------------------------------------------------------------- 1 | #Software: Microsoft Internet Information Services 6.0 2 | #Version: 1.0 3 | #Date: 2012-04-01 00:00:13 4 | #Fields: date time s-sitename s-computername s-ip cs-method cs-uri-stem cs-uri-query s-port cs-username c-ip cs-version cs(User-Agent) cs(Cookie) cs(Referer) cs-host sc-status sc-substatus sc-win32-status sc-bytes cs-bytes time-taken 5 | 2012-04-01 00:00:13 W3SVC834221556 PXQD1 5.6.7.8 GET /foo/bar topCat1=divinity&submit=Search 80 theuser 1.2.3.4 HTTP/1.1 Mozilla/5.0+(X11;+U;+Linux+i686;+en-US;+rv:1.9.2.7)+Gecko/20100722+Firefox/3.6.7 "ASP.NET_SessionId=sldfkjs; __utma=21468.206199.142713.144683.183.1; utmccn=(direct)|utmcsr=(direct)|utmcmd=(none)" - example.com 200 654 456 27028 214 1687 6 | -------------------------------------------------------------------------------- /LEGALNOTICE: -------------------------------------------------------------------------------- 1 | COPYRIGHT 2 | 3 | Matomo - free/libre analytics platform 4 | 5 | The software package is: 6 | 7 | Copyright (C) 2014 Matthieu Aubry 8 | 9 | Individual contributions, components, and libraries are copyright 10 | of their respective authors. 11 | 12 | 13 | SOFTWARE LICENSE 14 | 15 | The free software license of Matomo is GNU General Public License v3 16 | or later. A copy of GNU GPL v3 should have been included in this 17 | software package in LICENCE.txt. 18 | 19 | 20 | TRADEMARK 21 | 22 | Matomo (TM) is an internationally registered trademark. 23 | 24 | The software license does not grant any rights under trademark 25 | law for use of the trademark. Refer to https://matomo.org/trademark/ 26 | for up-to-date trademark licensing information. 27 | -------------------------------------------------------------------------------- /tests/logs/amazon_cloudfront_rtmp.log: -------------------------------------------------------------------------------- 1 | #Version: 1.0 2 | #Fields: date time x-edge-location c-ip x-event sc-bytes x-cf-status x-cf-client-id cs-uri-stem cs-uri-query c-referrer x-page-url​ c-user-agent x-sname x-sname-query x-file-ext x-sid 3 | 2010-03-12 23:51:20 SEA4 192.0.2.147 connect 2014 OK bfd8a98bee0840d9b871b7f6ade9908f rtmp://shqshne4jdp4b6.cloudfront.net/cfx/st​ key=value http://player.longtailvideo.com/player.swf http://www.longtailvideo.com/support/jw-player-setup-wizard?example=204 LNX%2010,0,32,18 - - - - 4 | 2010-03-12 23:51:21 SEA4 192.0.2.222 play 3914 OK bfd8a98bee0840d9b871b7f6ade9908f rtmp://shqshne4jdp4b6.cloudfront.net/cfx/st​ key=value http://player.longtailvideo.com/player.swf http://www.longtailvideo.com/support/jw-player-setup-wizard?example=204 LNX%2010,0,32,18 myvideo p=2&q=4 flv 1 5 | -------------------------------------------------------------------------------- /tests/logs/iis_custom.log: -------------------------------------------------------------------------------- 1 | #Software: IIS Advanced Logging Module 2 | 3 | #Version: 1.0 4 | 5 | #Start-Date: 2014-11-18 00:00:00.128 6 | 7 | #Fields: date-local time-local s-ip cs-method cs-uri-stem cs-uri-query s-port cs-username c-ip cs(User-Agent) cs(Referer) cs(Host) sc-status sc-substatus sc-win32-status TimeTakenMS 8 | 2012-08-15 17:00:00.363 1.2.3.4 GET /Products/theProduct - 80 - "70.95.0.0" "Mozilla/5.0 (Linux; Android 4.4.4; SM-G900V Build/KTU84P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.59 Mobile Safari/537.36" "http://example.com/Search/SearchResults.pg?informationRecipient.languageCode.c=en" "xzy.example.com" 200 0 0 109 9 | 2012-08-15 17:00:00.660 10.10.28.140 GET /Topic/hw43061 - 80 - - "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.1 Safari/537.36" - "example.hello.com" 301 0 0 0 10 | 2012-08-15 17:00:00.675 10.10.28.140 GET /hello/world/6,681965 - 80 - "173.5.0.0" "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.124 Safari/537.36" - "hello.example.com" 404 " garbage w/ spaces " 0 359 11 | -------------------------------------------------------------------------------- /tests/logs/nginx_json.log: -------------------------------------------------------------------------------- 1 | {"idsite":1,"ip": "1.2.3.4","host": "www.piwik.org","path": "/piwik.php?action_name=Clearcode%20-%20Web%20and%20Mobile%20Development%20%7C%20Technology%20With%20Passion&idsite=1&rec=1&r=983420&h=17&m=31&s=25&url=http%3A%2F%2Fclearcode.cc%2F&urlref=http%3A%2F%2Fclearcode.cc%2Fwelcome&_id=1da79fc743e8bcc4&_idts=1360047661&_idvc=1&_idn=0&_refts=1360047661&_viewts=1360047661&_ref=http%3A%2F%2Fpiwik.org%2Fthank-you-all%2F&pdf=1&qt=1&realp=0&wma=1&dir=1&fla=1&java=1&gears=0&ag=1&cookie=1&res=1680x1050","status": "200","referrer": "http://clearcode.cc/","user_agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.57 Safari/537.17","length": 192,"generation_time_milli": 0.008,"date": "2013-10-10T16:52:00+02:00"} 2 | {"idsite":1,"ip": "1.2.3.4","host": "www.piwik.org","path": "/piwik.php?action_name=AdviserBrief%20-%20Track%20Your%20Investments%20and%20Plan%20Financial%20Future%20%7C%20Clearcode&idsite=1&rec=1&r=109464&h=17&m=31&s=40&url=http%3A%2F%2Fclearcode.cc%2Fcase%2Fadviserbrief-track-your-investments-and-plan-financial-future%2F&urlref=http%3A%2F%2Fclearcode.cc%2Fwelcome&_id=1da79fc743e8bcc4&_idts=1360047661&_idvc=1&_idn=0&_refts=1360047661&_viewts=1360047661&_ref=http%3A%2F%2Fpiwik.org%2Fthank-you-all%2F&pdf=1&qt=1&realp=0&wma=1&dir=1&fla=1&java=1&gears=0&ag=1&cookie=1&res=1680x1050","status": "200","referrer": "http://clearcode.cc/","user_agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.57 Safari/537.17","length": 192,"generation_time_milli": 0.008,"date": "2013-10-10T16:52:00+02:00"} 3 | -------------------------------------------------------------------------------- /tests/logs/logs_to_tests.log: -------------------------------------------------------------------------------- 1 | 203.38.78.246 - - [05/Feb/2013:07:01:26 +0000] "GET /piwik.php?action_name=Clearcode%20-%20Web%20and%20Mobile%20Development%20%7C%20Technology%20With%20Passion&idsite=1&rec=1&r=983420&h=17&m=31&s=25&url=http%3A%2F%2Fclearcode.cc%2F&urlref=http%3A%2F%2Fclearcode.cc%2Fwelcome&_id=1da79fc743e8bcc4&_idts=1360047661&_idvc=1&_idn=0&_refts=1360047661&_viewts=1360047661&_ref=http%3A%2F%2Fpiwik.org%2Fthank-you-all%2F&pdf=1&qt=1&realp=0&wma=1&dir=1&fla=1&java=1&gears=0&ag=1&cookie=1&res=1680x1050 HTTP/1.1" 200 192 "http://clearcode.cc/" "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.57 Safari/537.17" 2 | 203.38.78.246 - - [05/Feb/2013:07:01:41 +0000] "GET /piwik.php?action_name=AdviserBrief%20-%20Track%20Your%20Investments%20and%20Plan%20Financial%20Future%20%7C%20Clearcode&idsite=1&rec=1&r=109464&h=17&m=31&s=40&url=http%3A%2F%2Fclearcode.cc%2Fcase%2Fadviserbrief-track-your-investments-and-plan-financial-future%2F&urlref=http%3A%2F%2Fclearcode.cc%2Fwelcome&_id=1da79fc743e8bcc4&_idts=1360047661&_idvc=1&_idn=0&_refts=1360047661&_viewts=1360047661&_ref=http%3A%2F%2Fpiwik.org%2Fthank-you-all%2F&pdf=1&qt=1&realp=0&wma=1&dir=1&fla=1&java=1&gears=0&ag=1&cookie=1&res=1680x1050 HTTP/1.1" 200 192 "http://clearcode.cc/case/adviserbrief-track-your-investments-and-plan-financial-future" "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.57 Safari/537.17" 3 | 203.38.78.246 - - [05/Feb/2013:07:01:46 +0000] "GET /piwik.php?action_name=ATL%20Apps%20-%20American%20Tailgating%20League%20Mobile%20Android%20IOS%20Games%20%7C%20Clearcode&idsite=1&rec=1&r=080064&h=17&m=31&s=46&url=http%3A%2F%2Fclearcode.cc%2Fcase%2Fatl-apps-mobile-android-ios-games%2F&urlref=http%3A%2F%2Fclearcode.cc%2Fwelcome&_id=1da79fc743e8bcc4&_idts=1360047661&_idvc=1&_idn=0&_refts=1360047661&_viewts=1360047661&_ref=http%3A%2F%2Fpiwik.org%2Fthank-you-all%2F&pdf=1&qt=1&realp=0&wma=1&dir=1&fla=1&java=1&gears=0&ag=1&cookie=1&res=1680x1050 HTTP/1.1" 200 192 "http://clearcode.cc/case/atl-apps-mobile-android-ios-games" "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.57 Safari/537.17" 4 | 5 | # Request with invalid length should not error out 6 | 95.81.66.139 - - [29/Oct/2013:00:48:46 +0100] "HEAD / HTTP/1.0" 403 - "-" "-" -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Matomo Server Log Analytics 2 | 3 | Import your server logs in Matomo with this powerful and easy to use tool. 4 | 5 | ## Requirements 6 | 7 | * Python 2.6 or 2.7. Python 3.x is not supported. 8 | * Matomo >= 2.14.0 9 | 10 | Build status (master branch) [![Build Status](https://travis-ci.org/matomo-org/matomo-log-analytics.svg?branch=master)](https://travis-ci.org/matomo/matomo-log-analytics) 11 | 12 | ## Supported log formats 13 | 14 | 15 | The script will import all standard web server log files, and some files with non-standard formats. The following log formats are supported: 16 | * all default log formats for: Nginx, Apache, IIS, Tomcat 17 | * all log formats commonly used such as: NCSA Common log format, Extended log format, W3C Extended log files, Nginx JSON, OVH 18 | * log files of some popular Cloud services: Amazon AWS CloudFront logs, AWS S3 logs, AWS ELB logs. 19 | * streaming media server log files such as: Icecast 20 | * log files with and without the virtual host will be imported 21 | 22 | In general, many fields are left optional to make the log importer very flexible. 23 | 24 | ## Get involved 25 | 26 | We're looking for contributors! Feel free to submit Pull requests on Github. 27 | 28 | ### Submit a new log format 29 | 30 | The Log Analytics importer is designed to detect and import into Matomo as many log files as possible. Help us add your log formats! 31 | 32 | * Implement your new log format in the import_logs.py file (look for `FORMATS = {` variable where the log formats are defined), 33 | * Add a new test in [tests/tests.py](https://github.com/matomo-org/matomo-log-analytics/blob/master/tests/tests.py), 34 | * Test that the logs are imported successfully as you expected (`tests/run_tests.sh`), 35 | * Open a Pull Request, 36 | * Check the test you have added works (the build should be green), 37 | * One Matomo team member will review and merge the Pull Request as soon as possible. 38 | 39 | We look forward to your contributions! 40 | 41 | ### Improve this guide 42 | 43 | This readme page could be improved and maybe you would like to help? feel free to create a "edit" this page and create a pull request. 44 | 45 | ### Implement new features or fixes 46 | 47 | if you're a Python developer and would like to contribute to open source log importer, check out the [list of issues for import_logs.py](https://github.com/matomo-org/matomo-log-analytics/issues) which lists all issues and suggestions. 48 | 49 | ## How to use this script? 50 | 51 | The most simple way to import your logs is to run: 52 | 53 | ./import_logs.py --url=matomo.example.com /path/to/access.log 54 | 55 | You must specify your Matomo URL with the `--url` argument. 56 | The script will automatically read your config.inc.php file to get the authentication 57 | token and communicate with your Matomo install to import the lines. 58 | The default mode will try to mimic the Javascript tracker as much as possible, 59 | and will not track bots, static files, or error requests. 60 | 61 | If you wish to track all requests the following command would be used: 62 | 63 | python /path/to/matomo/misc/log-analytics/import_logs.py --url=http://mysite/matomo/ --idsite=1234 --recorders=4 --enable-http-errors --enable-http-redirects --enable-static --enable-bots access.log 64 | 65 | 66 | ### Format Specific Details 67 | 68 | * If you are importing Netscaler log files, make sure to specify the `--iis-time-taken-secs` option. Netscaler stores 69 | the time-taken field in seconds while most other formats use milliseconds. Using this option will ensure that the 70 | log importer interprets the field correctly. 71 | 72 | * Some log formats can't be detected automatically as they would conflict with other formats. In order to import those logfiles make sure to specify the `--log-format-name` option. 73 | Those log formats are: OVH 74 | 75 | ## How to import your logs automatically every day? 76 | 77 | You must first make sure your logs are automatically rotated every day. The most 78 | popular ways to implement this are using either: 79 | 80 | * logrotate: http://www.linuxcommand.org/man_pages/logrotate8.html 81 | It will work with any HTTP daemon. 82 | * rotatelogs: http://httpd.apache.org/docs/2.0/programs/rotatelogs.html 83 | Only works with Apache. 84 | * let us know what else is useful and we will add it to the list 85 | 86 | Your logs should be automatically rotated and stored on your webserver, for instance in daily logs 87 | `/var/log/apache/access-%Y-%m-%d.log` (where %Y, %m and %d represent the year, 88 | month and day). 89 | You can then import your logs automatically each day (at 0:01). Setup a cron job with the command: 90 | 91 | 0 1 * * * /path/to/matomo/misc/log-analytics/import-logs.py -u matomo.example.com `date --date=yesterday +/var/log/apache/access-\%Y-\%m-\%d.log` 92 | 93 | ## Using Basic access authentication 94 | 95 | If you protect your site with Basic access authentication then you can pass the credentials via your 96 | cron job. 97 | 98 | Apache configuration: 99 | ``` 100 | 101 | AuthType basic 102 | AuthName "Site requires authentication" 103 | # Where all the external login/passwords are 104 | AuthUserFile /etc/apache2/somefile 105 | Require valid-user 106 | 107 | ``` 108 | 109 | cron job: 110 | ``` 111 | 5 0 * * * /var/www/html/matomo/misc/log-analytics/import_logs.py --url https://www.mysite.com/matomo --auth-user=someuser --auth-password=somepassword --exclude-path=*/matomo/index.php --enable-http-errors --enable-reverse-dns --idsite=1 date --date=yesterday +/var/log/apache2/access-ssl-\%Y-\%m-\%d.log > /opt/scripts/import-logs.log 112 | ``` 113 | 114 | Security tips: 115 | * Currently the credentials are not encrypted in the cron job. This should be a future enhancement. 116 | * Always use HTTPS with Basic access authentication to ensure you are not passing credentials clear text. 117 | 118 | ## Performance 119 | 120 | With an Intel Core i5-2400 @ 3.10GHz (2 cores, 4 virtual cores with Hyper-threading), 121 | running Matomo and its MySQL database, between 250 and 300 records were imported per second. 122 | 123 | The import_logs.py script needs CPU to read and parse the log files, but it is actually 124 | Matomo server itself (i.e. PHP/MySQL) which will use more CPU during data import. 125 | 126 | To improve performance, 127 | 128 | 1. by default, the script one thread to parse and import log lines. 129 | you can use the `--recorders` option to specify the number of parallel threads which will 130 | import hits into Matomo. We recommend to set `--recorders=N` to the number N of CPU cores 131 | that the server hosting Matomo has. The parsing will still be single-threaded, 132 | but several hits will be tracked in Matomo at the same time. 133 | 2. the script will issue hundreds of requests to matomo.php - to improve the Matomo webserver performance 134 | you can disable server access logging for these requests. 135 | Each Matomo webserver (Apache, Nginx, IIS) can also be tweaked a bit to handle more req/sec. 136 | 137 | ## Advanced uses 138 | 139 | ### Example Nginx Virtual Host Log Format 140 | 141 | nginx's default access log is parsed with the `--log-format-name=ncsa_extended` option. 142 | 143 | To log multiple virtual hosts in nginx's access log, use the following configuration: 144 | 145 | ``` 146 | log_format vhosts '$host $remote_addr - $remote_user [$time_local] "$request" $status $body_bytes_sent "$http_referer" "$http_user_agent"'; 147 | access_log /PATH/TO/access.log vhosts; 148 | ``` 149 | 150 | When executing `import_logs.py`, use `--log-format-name=common_complete`. 151 | 152 | ### How do I import Page Speed Metric from logs? 153 | 154 | In Matomo> Actions> Page URLs and Page Title reports, Matomo reports the Avg. generation time, as an indicator of your website speed. 155 | This metric works by default when using the Javascript tracker, but you can use it with log file as well. 156 | 157 | Apache can log the generation time in microseconds using `%D` in the LogFormat. 158 | This metric can be imported using a custom log format in this script. 159 | In the command line, add the `--log-format-regex` parameter that contains the group `generation_time_micro`. 160 | 161 | Here's an example: 162 | ``` 163 | Apache LogFormat "%h %l %u %t \"%r\" %>s %b %D" 164 | --log-format-regex="(?P\S+) \S+ \S+ \[(?P.*?) (?P.*?)\] \"\S+ (?P.*?) \S+\" (?P\S+) (?P\S+) (?P\S+)" 165 | ``` 166 | 167 | Note: the group `` is also available if your server logs generation time in milliseconds rather than microseconds. 168 | 169 | ### How do I setup Nginx to directly import to Matomo via syslog? 170 | 171 | Since nginx 1.7.1 you can [log to syslog](http://nginx.org/en/docs/syslog.html) and import them live to Matomo. 172 | 173 | Path: nginx -> syslog -> (syslog central server) -> import_logs.py -> matomo 174 | 175 | As a syslog central server you could use rsyslog or syslog-ng, use relevant parts of documentation below. Rsyslog part is tested with Ubuntu 16.10 and is working out-of-the-box. 176 | 177 | You can use any log format that this script can handle, like Apache Combined, and Json format which needs less processing. 178 | 179 | ##### Setup Nginx logs 180 | 181 | ``` 182 | http { 183 | ... 184 | log_format matomo '{"ip": "$remote_addr",' 185 | '"host": "$host",' 186 | '"path": "$request_uri",' 187 | '"status": "$status",' 188 | '"referrer": "$http_referer",' 189 | '"user_agent": "$http_user_agent",' 190 | '"length": $bytes_sent,' 191 | '"generation_time_milli": $request_time,' 192 | '"date": "$time_iso8601"}'; 193 | ... 194 | server { 195 | ... 196 | # for syslog-ng 197 | access_log syslog:server=127.0.0.1,severity=info matomo; 198 | # for rsyslog 199 | access_log syslog:server=unix:/var/cache/nginx/access.socket,facility=local0 matomo; 200 | ... 201 | } 202 | } 203 | ``` 204 | 205 | ##### Setup syslog-ng 206 | 207 | This is the config for the central server if any. If not, you can also use this config on the same server as Nginx. 208 | 209 | ``` 210 | options { 211 | stats_freq(600); stats_level(1); 212 | log_fifo_size(1280000); 213 | log_msg_size(8192); 214 | }; 215 | source s_nginx { udp(); }; 216 | destination d_matomo { 217 | program("/usr/local/matomo/matomo.sh" template("$MSG\n")); 218 | }; 219 | log { source(s_nginx); filter(f_info); destination(d_matomo); }; 220 | ``` 221 | 222 | ###### matomo.sh, syslog-ng version 223 | 224 | Just needed to configure the best params for import_logs.py, file `/usr/local/matomo/matomo.sh`: 225 | ``` 226 | #!/bin/sh 227 | 228 | /path/to/misc/log-analytics/import_logs.py \ 229 | --url=http://localhost/matomo/ \ 230 | --idsite=1 --recorders=4 --enable-http-errors --enable-http-redirects --enable-static --enable-bots \ 231 | --log-format-name=nginx_json - 232 | ``` 233 | 234 | ##### Example of regex for syslog format (centralized logs) 235 | 236 | ###### log format exemple 237 | 238 | ``` 239 | Aug 31 23:59:59 tt-srv-name www.tt.com: 1.1.1.1 - - [31/Aug/2014:23:59:59 +0200] "GET /index.php HTTP/1.0" 200 3838 "http://www.tt.com/index.php" "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:31.0) Gecko/20100101 Firefox/31.0" 365020 www.tt.com 240 | ``` 241 | 242 | ###### Corresponding regex 243 | 244 | ``` 245 | --log-format-regex='.* ((?P\S+) \S+ \S+ \[(?P.*?) (?P.*?)\] "\S+ (?P.*?) \S+" (?P\S+) (?P\S+) "(?P.*?)" "(?P.*?)").*' 246 | ``` 247 | 248 | ##### Setup rsyslog 249 | 250 | Create new file `/etc/rsyslog.d/10-matomo.conf` with following content and restart rsyslog service afterwards: 251 | ``` 252 | # socket to which you should send nginx data 253 | $AddUnixListenSocket /var/cache/nginx/access.socket 254 | 255 | # message starts with tag, "nginx: <...>", which we remove 256 | $template matomo,"%msg:9:$%\n" 257 | 258 | # uncomment following line to debug what is sent to matomo and in which format 259 | # to check script part you could issue following command 260 | # and expected result is "1 requests imported successfully": 261 | # 'tail -1 /var/tmp/nginx.tmp | /usr/local/matomo/matomo.sh' 262 | 263 | #local0.* /var/tmp/nginx.tmp;matomo 264 | if $syslogfacility-text == 'local0' then ^/usr/local/matomo/matomo.sh;matomo 265 | ``` 266 | 267 | ###### matomo.sh, rsyslog version 268 | 269 | `/usr/local/matomo/matomo.sh`, won't work without `--token-auth` parameter: 270 | ``` 271 | #!/bin/sh 272 | 273 | echo "${@}" | /path/to/misc/log-analytics/import_logs.py \ 274 | --url=https://localhost/matomo/ --token-auth= \ 275 | --enable-http-errors --enable-http-redirects --enable-static --enable-bots \ 276 | --idsite=1 --recorders=4 --log-format-name=nginx_json - 277 | ``` 278 | 279 | 280 | ### Setup Apache CustomLog that directly imports in Matomo 281 | 282 | Since apache CustomLog directives can send log data to a script, it is possible to import hits into matomo server-side in real-time rather than processing a logfile each day. 283 | 284 | This approach has many advantages, including real-time data being available on your matomo site, using real logs files instead of relying on client-side Javacsript, and not having a surge of CPU/RAM usage during log processing. 285 | The disadvantage is that if Matomo is unavailable, logging data will be lost. Therefore we recommend to also log into a standard log file. Bear in mind also that apache processes will wait until a request is logged before processing a new request, so if matomo runs slow so does your site: it's therefore important to tune `--recorders` to the right level. 286 | 287 | ##### Basic setup example 288 | 289 | You might have in your main config section: 290 | 291 | ``` 292 | # Set up your log format as a normal extended format, with hostname at the start 293 | LogFormat "%v %h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"" myLogFormat 294 | # Log to a file as usual 295 | CustomLog /path/to/logfile myLogFormat 296 | # Log to matomo as well 297 | CustomLog "|/path/to/import_logs.py --option1 --option2 ... -" myLogFormat 298 | ``` 299 | 300 | Note: on Debian/Ubuntu, the default configuration defines the `vhost_combined` format. You can use it instead of defining `myLogFormat`. 301 | 302 | Here is another example on Apache defining the custom log: 303 | ``` 304 | LogFormat "%v %h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-agent}i\"" matomoLogFormat 305 | 306 | CustomLog "||/var/www/virtual/test.tld/matomo/htdocs/misc/log-analytics/import_logs.py \ 307 | --debug --enable-http-errors --enable-http-redirects --enable-bots \ 308 | --url=http://matomo.test.tld --output=/var/log/matomo.log --recorders=1 \ 309 | --recorder-max-payload-size=1 --log-format-name=common_complete \ 310 | -" matomoLogFormat 311 | ``` 312 | 313 | Useful options here are: 314 | 315 | * `--add-sites-new-hosts` (creates new websites in matomo based on %v in the LogFormat) 316 | * `--output=/path/to/matomo.log` (puts any output into a log file for reference/debugging later) 317 | * `--recorders=4` (use whatever value seems sensible for you - higher traffic sites will need more recorders to keep up) 318 | * `-` so it reads straight from /dev/stdin 319 | 320 | You can have as many CustomLog statements as you like. However, if you define any CustomLog directives within a block, all CustomLogs in the main config will be overridden. Therefore if you require custom logging for particular VirtualHosts, it is recommended to use mod_macro to make configuration more maintainable. 321 | 322 | 323 | ##### Advanced setup: Apache vhost, custom logs, automatic website creation 324 | 325 | As a rather extreme example of what you can do, here is an apache config with: 326 | 327 | * standard logging in the main config area for the majority of VirtualHosts 328 | * customised logging in a particular virtualhost to change the hostname (for instance, if a particular virtualhost should be logged as if it were a different site) 329 | * customised logging in another virtualhost which creates new websites in matomo for subsites (e.g. to have domain.com/subsite1 as a whole website in its own right). This requires setting up a custom `--log-format-regex` to allow "/" in the hostname section (NB the escaping necessary for apache to pass through the regex to matomo properly), and also to have multiple CustomLog directives so the subsite gets logged to both domain.com and domain.com/subsite1 websites in matomo 330 | * we also use mod_rewrite to set environment variables so that if you have multiple subsites with the same format , e.g. /subsite1, /subsite2, etc, you can automatically create a new matomo website for each one without having to configure them manually 331 | 332 | NB use of mod_macro to ensure consistency and maintainability 333 | 334 | Apache configuration source code: 335 | 336 | ``` 337 | # Set up macro with the options 338 | # * $vhost (this will be used as the matomo website name), 339 | # * $logname (the name of the LogFormat we're using), 340 | # * $output (which logfile to save import_logs.py output to), 341 | # * $env (CustomLog can be set only to fire if an environment variable is set - this contains that environment variable, so subsites only log when it's set) 342 | # NB the --log-format-regex line is exactly the same regex as import_logs.py's own 'common_vhost' format, but with "\/" added in the "host" section's allowed characters 343 | 344 | LogFormat "$vhost %h %l %u %t \"%r\" %>s %b \"%{Referer}i\" \"%{User-Agent}i\"" $logname 345 | CustomLog "|/path/to/matomo/misc/log-analytics/import_logs.py \ 346 | --add-sites-new-hosts \ 347 | --config=/path/to/matomo/config/config.ini.php \ 348 | --url='http://your.matomo.install/' \ 349 | --recorders=4 \ 350 | --log-format-regex='(?P[\\\\w\\\\-\\\\.\\\\/]*)(?::\\\\d+)? (?P\\\\S+) \\\\S+ \\\\S+ \\\\[(?P.*?) (?P.*?)\\\\] \\\"\\\\S+ (?P.*?) \\\\S+\\\" (?P\\\\S+) (?P\\\\S+) \\\"(?P.*?)\\\" \\\"(?P.*?)\\\"' \ 351 | --output=/var/log/matomo/$output.log \ 352 | -" \ 353 | $logname \ 354 | $env 355 | 356 | # Set up main apache logging, with: 357 | 358 | # * normal %v as hostname, 359 | # * vhost_common as logformat name, 360 | # * /var/log/matomo/main.log as the logfile, 361 | # * no env variable needed since we always want to trigger 362 | Use matomolog %v vhost_common main " " 363 | 364 | ServerName example.com 365 | # Set this host to log to matomo with a different hostname (and using a different output file, /var/log/matomo/example_com.log) 366 | Use matomolog "another-host.com" vhost_common example_com " " 367 | 368 | 369 | 370 | ServerName domain.com 371 | # We want to log this normally, so repeat the CustomLog from the main section 372 | # (if this is omitted, our other CustomLogs below will override the one in the main section, so the main site won't be logged) 373 | Use matomolog %v vhost_common main " " 374 | 375 | # Now set up mod_rewrite to detect our subsites and set up new matomo websites to track just hits to these (this is a bit like profiles in Google Analytics). 376 | # We want to match domain.com/anothersubsite and domain.com/subsite[0-9]+ 377 | 378 | # First to be on the safe side, unset the env we'll use to test if we're in a subsite: 379 | UnsetEnv vhostLogName 380 | 381 | # Subsite definitions. NB check for both URI and REFERER (some files used in a page, or downloads linked from a page, may not reside within our subsite directory): 382 | # Do the one-off subsite first: 383 | RewriteCond %{REQUEST_URI} ^/anothersubsite(/|$) [OR] 384 | RewriteCond %{HTTP_REFERER} domain\.com/anothersubsite(/|$) 385 | RewriteRule ^/.* - [E=vhostLogName:anothersubsite] 386 | # Subsite of the form /subsite[0-9]+. NB the capture brackets in the RewriteCond rules which get mapped to %1 in the RewriteRule 387 | RewriteCond %{REQUEST_URI} ^/(subsite[0-9]+)(/|$)) [OR] 388 | RewriteCond %{HTTP_REFERER} domain\.com/(subsite[0-9]+)(/|$) 389 | RewriteRule ^/.* - [E=vhostLogName:subsite%1] 390 | 391 | # Now set the logging to matomo setting: 392 | # * the hostname to domain.com/ 393 | # * the logformat to vhost_domain_com_subsites (can be anything so long as it's unique) 394 | # * the output to go to /var/log/matomo/domain_com_subsites.log (again, can be anything) 395 | # * triggering only when the env variable is set, so requests to other URIs on this domain don't call this logging rule 396 | Use matomolog domain.com/%{vhostLogName}e vhost_domain_com_subsites domain_com_subsites env=vhostLogName 397 | 398 | ``` 399 | 400 | ### License 401 | 402 | As [matomo](`https://github.com/matomo-org/matomo`) (which includes this code as a git reference), matomo-log-analytics is released under the GPLv3 or later. Please refer to [LEGALNOTICE](LEGALNOTICE) for copyright and trademark statements and [LICENSE.txt](LICENSE.txt) for the full text of the GPLv3. 403 | 404 | ### And that's all ! 405 | 406 | 407 | ***This documentation is a community effort, we welcome your pull requests to [improve this documentation](https://github.com/matomo-org/matomo-log-analytics/edit/master/README.md).*** 408 | -------------------------------------------------------------------------------- /LICENSE.txt: -------------------------------------------------------------------------------- 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 | 635 | Copyright (C) 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 | Copyright (C) 656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. 657 | This is free software, and you are welcome to redistribute it 658 | under certain conditions; type `show c' for details. 659 | 660 | The hypothetical commands `show w' and `show c' should show the appropriate 661 | parts of the General Public License. Of course, your program's commands 662 | might be different; for a GUI interface, you would use an "about box". 663 | 664 | You should also get your employer (if you work as a programmer) or school, 665 | if any, to sign a "copyright disclaimer" for the program, if necessary. 666 | For more information on this, and how to apply and follow the GNU GPL, see 667 | . 668 | 669 | The GNU General Public License does not permit incorporating your program 670 | into proprietary programs. If your program is a subroutine library, you 671 | may consider it more useful to permit linking proprietary applications with 672 | the library. If this is what you want to do, use the GNU Lesser General 673 | Public License instead of this License. But first, please read 674 | . 675 | -------------------------------------------------------------------------------- /tests/tests.py: -------------------------------------------------------------------------------- 1 | # vim: et sw=4 ts=4: 2 | import functools 3 | import os 4 | import datetime 5 | import re 6 | 7 | import import_logs 8 | 9 | # utility functions 10 | def add_junk_to_file(path): 11 | file = open(path) 12 | contents = file.read() 13 | file.close() 14 | 15 | file = open('tmp.log', 'w') 16 | file.write(contents + ' junk') 17 | file.close() 18 | 19 | return 'tmp.log' 20 | 21 | def add_multiple_spaces_to_file(path): 22 | file = open(path) 23 | contents = file.read() 24 | file.close() 25 | 26 | # replace spaces that aren't between " quotes 27 | contents = contents.split('"') 28 | for i in xrange(0, len(contents), 2): 29 | contents[i] = re.sub(' ', " ", contents[i]) 30 | contents = '"'.join(contents) 31 | import_logs.logging.debug(contents) 32 | 33 | assert " " in contents # sanity check 34 | 35 | file = open('tmp.log', 'w') 36 | file.write(contents) 37 | file.close() 38 | 39 | return 'tmp.log' 40 | 41 | def use_ipv6_in_file(path): 42 | file = open(path) 43 | contents = file.read() 44 | file.close() 45 | 46 | if '1.2.3.4' not in contents: 47 | raise RuntimeError('could not find ipv4 IP in ' + path + 48 | ', make sure the IP 1.2.3.4 is used for tests') 49 | 50 | contents = contents.replace('1.2.3.4', '0:0:0:0:0:ffff:7b2d:4359') 51 | 52 | file = open('tmp.log', 'w') 53 | file.write(contents) 54 | file.close() 55 | 56 | return 'tmp.log' 57 | 58 | def tearDownModule(): 59 | if os.path.exists('tmp.log'): 60 | os.remove('tmp.log') 61 | 62 | def test_format_detection(): 63 | def _test(format_name, log_file = None): 64 | if log_file is None: 65 | log_file = 'logs/%s.log' % format_name 66 | 67 | file = open(log_file) 68 | import_logs.config = Config() 69 | format = import_logs.Parser.detect_format(file) 70 | assert(format is not None) 71 | assert(format.name == format_name) 72 | 73 | def _test_junk(format_name, log_file = None): 74 | if log_file is None: 75 | log_file = 'logs/%s.log' % format_name 76 | 77 | tmp_path = add_junk_to_file(log_file) 78 | 79 | file = open(tmp_path) 80 | import_logs.config = Config() 81 | format = import_logs.Parser.detect_format(file) 82 | assert(format is not None) 83 | assert(format.name == format_name) 84 | 85 | def _test_multiple_spaces(format_name, log_file = None): 86 | if log_file is None: 87 | log_file = 'logs/%s.log' % format_name 88 | 89 | tmp_path = add_multiple_spaces_to_file(log_file) 90 | 91 | file = open(tmp_path) 92 | import_logs.config = Config() 93 | format = import_logs.Parser.detect_format(file) 94 | assert(format is not None) 95 | assert(format.name == format_name) 96 | 97 | def _test_ipv6(format_name, log_file = None): 98 | if log_file is None: 99 | log_file = 'logs/%s.log' % format_name 100 | 101 | tmp_path = use_ipv6_in_file(log_file) 102 | 103 | # test correct format is detected first 104 | file = open(tmp_path) 105 | import_logs.config = Config() 106 | format = import_logs.Parser.detect_format(file) 107 | assert(format is not None) 108 | assert(format.name == format_name) 109 | 110 | # then parse the file and test the IP is parsed correctly 111 | groups = parse_log_file_line(format_name, tmp_path) 112 | assert groups['ip'] == '0:0:0:0:0:ffff:7b2d:4359' 113 | 114 | for format_name in import_logs.FORMATS.iterkeys(): 115 | # w3c extended tested by iis and netscaler log files; amazon cloudfront tested later 116 | if format_name == 'w3c_extended' or format_name == 'amazon_cloudfront' or format_name == 'ovh': 117 | continue 118 | 119 | f = functools.partial(_test, format_name) 120 | f.description = 'Testing autodetection of format ' + format_name 121 | yield f 122 | 123 | f = functools.partial(_test_junk, format_name) 124 | f.description = 'Testing autodetection of format ' + format_name + ' w/ garbage at end of line' 125 | yield f 126 | 127 | f = functools.partial(_test_multiple_spaces, format_name) 128 | f.description = 'Testing autodetection of format ' + format_name + ' when multiple spaces separate fields' 129 | yield f 130 | 131 | f = functools.partial(_test_ipv6, format_name) 132 | f.description = 'Testing parsing of IPv6 address with format ' + format_name 133 | yield f 134 | 135 | # add tests for amazon cloudfront (normal web + rtmp) 136 | f = functools.partial(_test, 'amazon_cloudfront', 'logs/amazon_cloudfront_web.log') 137 | f.description = 'Testing autodetection of amazon cloudfront (web) logs.' 138 | yield f 139 | 140 | f = functools.partial(_test_junk, 'amazon_cloudfront', 'logs/amazon_cloudfront_web.log') 141 | f.description = 'Testing autodetection of amazon cloudfront (web) logs w/ garbage at end of line' 142 | yield f 143 | 144 | f = functools.partial(_test_multiple_spaces, 'amazon_cloudfront', 'logs/amazon_cloudfront_web.log') 145 | f.description = 'Testing autodetection of format amazon cloudfront (web) logs when multiple spaces separate fields' 146 | yield f 147 | 148 | f = functools.partial(_test, 'amazon_cloudfront', 'logs/amazon_cloudfront_rtmp.log') 149 | f.description = 'Testing autodetection of amazon cloudfront (rtmp) logs.' 150 | yield f 151 | 152 | f = functools.partial(_test_junk, 'amazon_cloudfront', 'logs/amazon_cloudfront_rtmp.log') 153 | f.description = 'Testing autodetection of amazon cloudfront (rtmp) logs w/ garbage at end of line.' 154 | yield f 155 | 156 | f = functools.partial(_test_multiple_spaces, 'amazon_cloudfront', 'logs/amazon_cloudfront_rtmp.log') 157 | f.description = 'Testing autodetection of format amazon cloudfront (rtmp) logs when multiple spaces separate fields' 158 | yield f 159 | 160 | class Options(object): 161 | """Mock config options necessary to run checkers from Parser class.""" 162 | debug = False 163 | encoding = 'utf-8' 164 | log_hostname = 'foo' 165 | query_string_delimiter = '?' 166 | piwik_token_auth = False 167 | piwik_url = 'http://example.com' 168 | recorder_max_payload_size = 200 169 | replay_tracking = True 170 | show_progress = False 171 | skip = False 172 | hostnames = [] 173 | excluded_paths = [] 174 | excluded_useragents = [] 175 | enable_bots = [] 176 | force_lowercase_path = False 177 | included_paths = [] 178 | enable_http_errors = False 179 | download_extensions = 'doc,pdf' 180 | custom_w3c_fields = {} 181 | dump_log_regex = False 182 | w3c_time_taken_in_millisecs = False 183 | w3c_fields = None 184 | w3c_field_regexes = {} 185 | regex_group_to_visit_cvars_map = {} 186 | regex_group_to_page_cvars_map = {} 187 | regex_groups_to_ignore = None 188 | replay_tracking_expected_tracker_file = 'piwik.php' 189 | debug_request_limit = None 190 | exclude_host = [] 191 | include_host = [] 192 | exclude_older_than = None 193 | exclude_newer_than = None 194 | track_http_method = True 195 | seconds_to_add_to_date = 0 196 | request_suffix = None 197 | 198 | class Config(object): 199 | """Mock configuration.""" 200 | options = Options() 201 | format = import_logs.FORMATS['ncsa_extended'] 202 | 203 | class Resolver(object): 204 | """Mock resolver which doesn't check connection to real piwik.""" 205 | def check_format(self, format_): 206 | pass 207 | 208 | class Recorder(object): 209 | """Mock recorder which collects hits but doesn't put their in database.""" 210 | recorders = [] 211 | 212 | @classmethod 213 | def add_hits(cls, hits): 214 | cls.recorders.extend(hits) 215 | 216 | def test_replay_tracking_arguments(): 217 | """Test data parsing from sample log file.""" 218 | file_ = 'logs/logs_to_tests.log' 219 | 220 | import_logs.stats = import_logs.Statistics() 221 | import_logs.config = Config() 222 | import_logs.resolver = Resolver() 223 | import_logs.Recorder = Recorder() 224 | import_logs.parser = import_logs.Parser() 225 | import_logs.parser.parse(file_) 226 | 227 | hits = [hit.args for hit in import_logs.Recorder.recorders] 228 | 229 | assert hits[0]['_idn'] == '0' 230 | assert hits[0]['ag'] == '1' 231 | assert hits[0]['_viewts'] == '1360047661' 232 | assert hits[0]['urlref'] == 'http://clearcode.cc/welcome' 233 | assert hits[0]['_ref'] == 'http://piwik.org/thank-you-all/' 234 | assert hits[0]['_idts'] == '1360047661' 235 | assert hits[0]['java'] == '1' 236 | assert hits[0]['res'] == '1680x1050' 237 | assert hits[0]['idsite'] == '1' 238 | assert hits[0]['realp'] == '0' 239 | assert hits[0]['wma'] == '1' 240 | assert hits[0]['_idvc'] == '1' 241 | assert hits[0]['action_name'] == 'Clearcode - Web and Mobile Development | Technology With Passion' 242 | assert hits[0]['cookie'] == '1' 243 | assert hits[0]['rec'] == '1' 244 | assert hits[0]['qt'] == '1' 245 | assert hits[0]['url'] == 'http://clearcode.cc/' 246 | assert hits[0]['h'] == '17' 247 | assert hits[0]['m'] == '31' 248 | assert hits[0]['s'] == '25' 249 | assert hits[0]['r'] == '983420' 250 | assert hits[0]['gears'] == '0' 251 | assert hits[0]['fla'] == '1' 252 | assert hits[0]['pdf'] == '1' 253 | assert hits[0]['_id'] == '1da79fc743e8bcc4' 254 | assert hits[0]['dir'] == '1' 255 | assert hits[0]['_refts'] == '1360047661' 256 | 257 | assert hits[1]['_idn'] == '0' 258 | assert hits[1]['ag'] == '1' 259 | assert hits[1]['_viewts'] == '1360047661' 260 | assert hits[1]['urlref'] == 'http://clearcode.cc/welcome' 261 | assert hits[1]['_ref'] == 'http://piwik.org/thank-you-all/' 262 | assert hits[1]['_idts'] == '1360047661' 263 | assert hits[1]['java'] == '1' 264 | assert hits[1]['res'] == '1680x1050' 265 | assert hits[1]['idsite'] == '1' 266 | assert hits[1]['realp'] == '0' 267 | assert hits[1]['wma'] == '1' 268 | assert hits[1]['_idvc'] == '1' 269 | assert hits[1]['action_name'] == 'AdviserBrief - Track Your Investments and Plan Financial Future | Clearcode' 270 | assert hits[1]['cookie'] == '1' 271 | assert hits[1]['rec'] == '1' 272 | assert hits[1]['qt'] == '1' 273 | assert hits[1]['url'] == 'http://clearcode.cc/case/adviserbrief-track-your-investments-and-plan-financial-future/' 274 | assert hits[1]['h'] == '17' 275 | assert hits[1]['m'] == '31' 276 | assert hits[1]['s'] == '40' 277 | assert hits[1]['r'] == '109464' 278 | assert hits[1]['gears'] == '0' 279 | assert hits[1]['fla'] == '1' 280 | assert hits[1]['pdf'] == '1' 281 | assert hits[1]['_id'] == '1da79fc743e8bcc4' 282 | assert hits[1]['dir'] == '1' 283 | assert hits[1]['_refts'] == '1360047661' 284 | 285 | assert hits[2]['_idn'] == '0' 286 | assert hits[2]['ag'] == '1' 287 | assert hits[2]['_viewts'] == '1360047661' 288 | assert hits[2]['urlref'] == 'http://clearcode.cc/welcome' 289 | assert hits[2]['_ref'] == 'http://piwik.org/thank-you-all/' 290 | assert hits[2]['_idts'] == '1360047661' 291 | assert hits[2]['java'] == '1' 292 | assert hits[2]['res'] == '1680x1050' 293 | assert hits[2]['idsite'] == '1' 294 | assert hits[2]['realp'] == '0' 295 | assert hits[2]['wma'] == '1' 296 | assert hits[2]['_idvc'] == '1' 297 | assert hits[2]['action_name'] == 'ATL Apps - American Tailgating League Mobile Android IOS Games | Clearcode' 298 | assert hits[2]['cookie'] == '1' 299 | assert hits[2]['rec'] == '1' 300 | assert hits[2]['qt'] == '1' 301 | assert hits[2]['url'] == 'http://clearcode.cc/case/atl-apps-mobile-android-ios-games/' 302 | assert hits[2]['h'] == '17' 303 | assert hits[2]['m'] == '31' 304 | assert hits[2]['s'] == '46' 305 | assert hits[2]['r'] == '080064' 306 | assert hits[2]['gears'] == '0' 307 | assert hits[2]['fla'] == '1' 308 | assert hits[2]['pdf'] == '1' 309 | assert hits[2]['_id'] == '1da79fc743e8bcc4' 310 | assert hits[2]['dir'] == '1' 311 | assert hits[2]['_refts'] == '1360047661' 312 | 313 | def parse_log_file_line(format_name, file_): 314 | format = import_logs.FORMATS[format_name] 315 | 316 | import_logs.config.options.custom_w3c_fields = {} 317 | 318 | file = open(file_) 319 | match = format.check_format(file) 320 | file.close() 321 | 322 | return format.get_all() 323 | 324 | # check parsing groups 325 | def check_common_groups(groups): 326 | assert groups['ip'] == '1.2.3.4' 327 | assert groups['date'] == '10/Feb/2012:16:42:07' 328 | assert groups['timezone'] == '-0500' 329 | assert groups['path'] == '/' 330 | assert groups['status'] == '301' 331 | assert groups['length'] == '368' 332 | assert groups['userid'] == 'theuser' 333 | 334 | def check_ncsa_extended_groups(groups): 335 | check_common_groups(groups) 336 | 337 | assert groups['referrer'] == '-' 338 | assert groups['user_agent'] == 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11' 339 | 340 | def check_common_vhost_groups(groups): 341 | check_common_groups(groups) 342 | 343 | assert groups['host'] == 'www.example.com' 344 | 345 | def check_common_complete_groups(groups): 346 | check_ncsa_extended_groups(groups) 347 | 348 | assert groups['host'] == 'www.example.com' 349 | 350 | def check_iis_groups(groups): 351 | assert groups['date'] == '2012-04-01 00:00:13' 352 | assert groups['path'] == '/foo/bar' 353 | assert groups['query_string'] == 'topCat1=divinity&submit=Search' 354 | assert groups['ip'] == '1.2.3.4' 355 | assert groups['referrer'] == '-' 356 | assert groups['user_agent'] == 'Mozilla/5.0+(X11;+U;+Linux+i686;+en-US;+rv:1.9.2.7)+Gecko/20100722+Firefox/3.6.7' 357 | assert groups['status'] == '200' 358 | assert groups['length'] == '27028' 359 | assert groups['host'] == 'example.com' 360 | 361 | expected_hit_properties = ['date', 'path', 'query_string', 'ip', 'referrer', 'user_agent', 362 | 'status', 'length', 'host', 'userid', 'generation_time_milli', 363 | '__win32_status', 'cookie', 'method'] 364 | 365 | for property_name in groups.keys(): 366 | assert property_name in expected_hit_properties 367 | 368 | def check_s3_groups(groups): 369 | assert groups['host'] == 'www.example.com' 370 | assert groups['date'] == '10/Feb/2012:16:42:07' 371 | assert groups['timezone'] == '-0500' 372 | assert groups['ip'] == '1.2.3.4' 373 | assert groups['userid'] == 'arn:aws:iam::179580289999:user/phillip.boss' 374 | assert groups['path'] == '/index' 375 | assert groups['status'] == '200' 376 | assert groups['length'] == '368' 377 | assert groups['referrer'] == '-' 378 | assert groups['user_agent'] == 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11' 379 | 380 | def check_nginx_json_groups(groups): 381 | assert groups['host'] == 'www.piwik.org' 382 | assert groups['status'] == '200' 383 | assert groups['ip'] == '1.2.3.4' 384 | assert groups['length'] == 192 385 | assert groups['user_agent'] == 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.17 (KHTML, like Gecko) Chrome/24.0.1312.57 Safari/537.17' 386 | assert groups['date'] == '2013-10-10T16:52:00+02:00' 387 | 388 | def check_icecast2_groups(groups): 389 | check_ncsa_extended_groups(groups) 390 | 391 | assert groups['session_time'] == '1807' 392 | 393 | def check_match_groups(format_name, groups): 394 | symbols = globals() 395 | check_function = symbols['check_' + format_name + '_groups'] 396 | return check_function(groups) 397 | 398 | def check_ovh_groups(groups): 399 | check_common_complete_groups(groups) 400 | 401 | # parsing tests 402 | def test_format_parsing(): 403 | # test format regex parses correctly 404 | def _test(format_name, path): 405 | groups = parse_log_file_line(format_name, path) 406 | check_match_groups(format_name, groups) 407 | 408 | # test format regex parses correctly when there's added junk at the end of the line 409 | def _test_with_junk(format_name, path): 410 | tmp_path = add_junk_to_file(path) 411 | _test(format_name, tmp_path) 412 | 413 | for format_name in import_logs.FORMATS.iterkeys(): 414 | # w3c extended tested by IIS and netscaler logs; amazon cloudfront tested individually 415 | if format_name == 'w3c_extended' or format_name == 'amazon_cloudfront' or format_name == 'shoutcast' or format_name == 'elb': 416 | continue 417 | 418 | f = functools.partial(_test, format_name, 'logs/' + format_name + '.log') 419 | f.description = 'Testing parsing of format "%s"' % format_name 420 | yield f 421 | 422 | f = functools.partial(_test_with_junk, format_name, 'logs/' + format_name + '.log') 423 | f.description = 'Testing parsing of format "%s" with junk appended to path' % format_name 424 | yield f 425 | 426 | f = functools.partial(_test, 'common', 'logs/ncsa_extended.log') 427 | f.description = 'Testing parsing of format "common" with ncsa_extended log' 428 | yield f 429 | 430 | def test_iis_custom_format(): 431 | """test IIS custom format name parsing.""" 432 | 433 | file_ = 'logs/iis_custom.log' 434 | 435 | # have to override previous globals override for this test 436 | import_logs.config.options.custom_w3c_fields = { 437 | 'date-local': 'date', 438 | 'time-local': 'time', 439 | 'cs(Host)': 'cs-host', 440 | 'TimeTakenMS': 'time-taken' 441 | } 442 | Recorder.recorders = [] 443 | import_logs.parser = import_logs.Parser() 444 | import_logs.config.format = None 445 | import_logs.config.options.enable_http_redirects = True 446 | import_logs.config.options.enable_http_errors = True 447 | import_logs.config.options.replay_tracking = False 448 | # import_logs.config.options.w3c_time_taken_in_millisecs = True test that even w/o this, we get the right values 449 | import_logs.parser.parse(file_) 450 | 451 | hits = [hit.__dict__ for hit in Recorder.recorders] 452 | 453 | assert hits[0]['status'] == '200' 454 | assert hits[0]['is_error'] == False 455 | assert hits[0]['extension'] == u'/products/theproduct' 456 | assert hits[0]['is_download'] == False 457 | assert hits[0]['referrer'] == u'http://example.com/Search/SearchResults.pg?informationRecipient.languageCode.c=en' 458 | assert hits[0]['args'] == {'cvar': {1: ['HTTP-method', 'GET']}} 459 | assert hits[0]['generation_time_milli'] == 109 460 | assert hits[0]['host'] == 'foo' 461 | assert hits[0]['filename'] == 'logs/iis_custom.log' 462 | assert hits[0]['is_redirect'] == False 463 | assert hits[0]['date'] == datetime.datetime(2012, 8, 15, 17, 0) 464 | assert hits[0]['lineno'] == 7 465 | assert hits[0]['ip'] == u'70.95.0.0' 466 | assert hits[0]['query_string'] == '' 467 | assert hits[0]['path'] == u'/Products/theProduct' 468 | assert hits[0]['is_robot'] == False 469 | assert hits[0]['full_path'] == u'/Products/theProduct' 470 | assert hits[0]['user_agent'] == u'Mozilla/5.0 (Linux; Android 4.4.4; SM-G900V Build/KTU84P) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.59 Mobile Safari/537.36' 471 | 472 | assert hits[1]['status'] == u'301' 473 | assert hits[1]['is_error'] == False 474 | assert hits[1]['extension'] == u'/topic/hw43061' 475 | assert hits[1]['is_download'] == False 476 | assert hits[1]['referrer'] == '' 477 | assert hits[1]['args'] == {'cvar': {1: ['HTTP-method', 'GET']}} 478 | assert hits[1]['generation_time_milli'] == 0 479 | assert hits[1]['host'] == 'foo' 480 | assert hits[1]['filename'] == 'logs/iis_custom.log' 481 | assert hits[1]['is_redirect'] == True 482 | assert hits[1]['date'] == datetime.datetime(2012, 8, 15, 17, 0) 483 | assert hits[1]['lineno'] == 8 484 | assert hits[1]['ip'] == '-' 485 | assert hits[1]['query_string'] == '' 486 | assert hits[1]['path'] == u'/Topic/hw43061' 487 | assert hits[1]['is_robot'] == False 488 | assert hits[1]['full_path'] == u'/Topic/hw43061' 489 | assert hits[1]['user_agent'] == u'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.1 Safari/537.36' 490 | 491 | assert hits[2]['status'] == u'404' 492 | assert hits[2]['is_error'] == True 493 | assert hits[2]['extension'] == u'/hello/world/6,681965' 494 | assert hits[2]['is_download'] == False 495 | assert hits[2]['referrer'] == '' 496 | assert hits[2]['args'] == {'cvar': {1: ['HTTP-method', 'GET']}} 497 | assert hits[2]['generation_time_milli'] == 359 498 | assert hits[2]['host'] == 'foo' 499 | assert hits[2]['filename'] == 'logs/iis_custom.log' 500 | assert hits[2]['is_redirect'] == False 501 | assert hits[2]['date'] == datetime.datetime(2012, 8, 15, 17, 0) 502 | assert hits[2]['lineno'] == 9 503 | assert hits[2]['ip'] == u'173.5.0.0' 504 | assert hits[2]['query_string'] == '' 505 | assert hits[2]['path'] == u'/hello/world/6,681965' 506 | assert hits[2]['is_robot'] == False 507 | assert hits[2]['full_path'] == u'/hello/world/6,681965' 508 | assert hits[2]['user_agent'] == u'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.124 Safari/537.36' 509 | 510 | def test_netscaler_parsing(): 511 | """test parsing of netscaler logs (which use extended W3C log format)""" 512 | 513 | file_ = 'logs/netscaler.log' 514 | 515 | # have to override previous globals override for this test 516 | import_logs.config.options.custom_w3c_fields = {} 517 | Recorder.recorders = [] 518 | import_logs.parser = import_logs.Parser() 519 | import_logs.config.format = None 520 | import_logs.config.options.enable_http_redirects = True 521 | import_logs.config.options.enable_http_errors = True 522 | import_logs.config.options.replay_tracking = False 523 | import_logs.config.options.w3c_time_taken_in_millisecs = False 524 | import_logs.parser.parse(file_) 525 | 526 | hits = [hit.__dict__ for hit in Recorder.recorders] 527 | 528 | assert hits[0]['status'] == u'302' 529 | assert hits[0]['userid'] == None 530 | assert hits[0]['is_error'] == False 531 | assert hits[0]['extension'] == u'jsp' 532 | assert hits[0]['is_download'] == False 533 | assert hits[0]['referrer'] == '' 534 | assert hits[0]['args'] == {'cvar': {1: ['HTTP-method', 'GET']}} 535 | assert hits[0]['generation_time_milli'] == 1000 536 | assert hits[0]['host'] == 'foo' 537 | assert hits[0]['filename'] == 'logs/netscaler.log' 538 | assert hits[0]['is_redirect'] == True 539 | assert hits[0]['date'] == datetime.datetime(2012, 8, 16, 11, 55, 13) 540 | assert hits[0]['lineno'] == 4 541 | assert hits[0]['ip'] == u'172.20.1.0' 542 | assert hits[0]['query_string'] == '' 543 | assert hits[0]['path'] == u'/Citrix/XenApp/Wan/auth/login.jsp' 544 | assert hits[0]['is_robot'] == False 545 | assert hits[0]['full_path'] == u'/Citrix/XenApp/Wan/auth/login.jsp' 546 | assert hits[0]['user_agent'] == u'Mozilla/4.0+(compatible;+MSIE+7.0;+Windows+NT+5.1;+Trident/4.0;+.NET+CLR+1.1.4322;+.NET+CLR+2.0.50727;+.NET+CLR+3.0.04506.648;+.NET+CLR+3.5.21022)' 547 | 548 | def test_shoutcast_parsing(): 549 | """test parsing of shoutcast logs (which use extended W3C log format)""" 550 | 551 | file_ = 'logs/shoutcast.log' 552 | 553 | # have to override previous globals override for this test 554 | import_logs.config.options.custom_w3c_fields = {} 555 | Recorder.recorders = [] 556 | import_logs.parser = import_logs.Parser() 557 | import_logs.config.format = None 558 | import_logs.config.options.enable_http_redirects = True 559 | import_logs.config.options.enable_http_errors = True 560 | import_logs.config.options.replay_tracking = False 561 | import_logs.config.options.w3c_time_taken_in_millisecs = False 562 | import_logs.parser.parse(file_) 563 | 564 | hits = [hit.__dict__ for hit in Recorder.recorders] 565 | 566 | assert hits[0]['status'] == u'200' 567 | assert hits[0]['userid'] == None 568 | assert hits[0]['is_error'] == False 569 | assert hits[0]['extension'] == u'/stream' 570 | assert hits[0]['is_download'] == False 571 | assert hits[0]['referrer'] == '' 572 | assert hits[0]['args'] == {} 573 | assert hits[0]['generation_time_milli'] == 1000.0 574 | assert hits[0]['host'] == 'foo' 575 | assert hits[0]['filename'] == 'logs/shoutcast.log' 576 | assert hits[0]['is_redirect'] == False 577 | assert hits[0]['date'] == datetime.datetime(2015, 12, 7, 10, 37, 5) 578 | assert hits[0]['lineno'] == 3 579 | assert hits[0]['ip'] == u'1.2.3.4' 580 | assert hits[0]['query_string'] == u'title=UKR%20Nights' 581 | assert hits[0]['path'] == u'/stream' 582 | assert hits[0]['is_robot'] == False 583 | assert hits[0]['full_path'] == u'/stream?title=UKR%20Nights' 584 | assert hits[0]['user_agent'] == u'NSPlayer/10.0.0.3702 WMFSDK/10.0' 585 | assert hits[0]['length'] == 65580 586 | 587 | def test_elb_parsing(): 588 | """test parsing of elb logs""" 589 | 590 | file_ = 'logs/elb.log' 591 | 592 | # have to override previous globals override for this test 593 | import_logs.config.options.custom_w3c_fields = {} 594 | Recorder.recorders = [] 595 | import_logs.parser = import_logs.Parser() 596 | import_logs.config.format = None 597 | import_logs.config.options.enable_http_redirects = True 598 | import_logs.config.options.enable_http_errors = True 599 | import_logs.config.options.replay_tracking = False 600 | import_logs.config.options.w3c_time_taken_in_millisecs = False 601 | import_logs.parser.parse(file_) 602 | 603 | hits = [hit.__dict__ for hit in Recorder.recorders] 604 | 605 | assert len(hits) == 1 606 | 607 | assert hits[0]['status'] == u'200' 608 | assert hits[0]['userid'] == None 609 | assert hits[0]['is_error'] == False 610 | assert hits[0]['extension'] == u'html' 611 | assert hits[0]['is_download'] == False 612 | assert hits[0]['referrer'] == '' 613 | assert hits[0]['args'] == {} 614 | assert hits[0]['generation_time_milli'] == 1.048 615 | assert hits[0]['host'] == 'foo' 616 | assert hits[0]['filename'] == 'logs/elb.log' 617 | assert hits[0]['is_redirect'] == False 618 | assert hits[0]['date'] == datetime.datetime(2015, 05, 13, 23, 39, 43) 619 | assert hits[0]['lineno'] == 0 620 | assert hits[0]['ip'] == u'1.2.3.4' 621 | assert hits[0]['query_string'] == u'' 622 | assert hits[0]['path'] == u'/path/index.html' 623 | assert hits[0]['is_robot'] == False 624 | assert hits[0]['full_path'] == u'/path/index.html' 625 | assert hits[0]['user_agent'] == u'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11' 626 | assert hits[0]['length'] == 57 627 | 628 | def test_amazon_cloudfront_web_parsing(): 629 | """test parsing of amazon cloudfront logs (which use extended W3C log format)""" 630 | 631 | file_ = 'logs/amazon_cloudfront_web.log' 632 | 633 | # have to override previous globals override for this test 634 | import_logs.config.options.custom_w3c_fields = {} 635 | Recorder.recorders = [] 636 | import_logs.parser = import_logs.Parser() 637 | import_logs.config.format = None 638 | import_logs.config.options.enable_http_redirects = True 639 | import_logs.config.options.enable_http_errors = True 640 | import_logs.config.options.replay_tracking = False 641 | import_logs.config.options.w3c_time_taken_in_millisecs = False 642 | import_logs.parser.parse(file_) 643 | 644 | hits = [hit.__dict__ for hit in Recorder.recorders] 645 | 646 | assert hits[0]['status'] == u'200' 647 | assert hits[0]['userid'] == None 648 | assert hits[0]['is_error'] == False 649 | assert hits[0]['extension'] == u'html' 650 | assert hits[0]['is_download'] == False 651 | assert hits[0]['referrer'] == u'www.displaymyfiles.com' 652 | assert hits[0]['args'] == {'cvar': {1: ['HTTP-method', 'GET']}} 653 | assert hits[0]['generation_time_milli'] == 1.0 654 | assert hits[0]['host'] == 'foo' 655 | assert hits[0]['filename'] == 'logs/amazon_cloudfront_web.log' 656 | assert hits[0]['is_redirect'] == False 657 | assert hits[0]['date'] == datetime.datetime(2014, 5, 23, 1, 13, 11) 658 | assert hits[0]['lineno'] == 2 659 | assert hits[0]['ip'] == u'192.0.2.10' 660 | assert hits[0]['query_string'] == '' 661 | assert hits[0]['path'] == u'/view/my/file.html' 662 | assert hits[0]['is_robot'] == False 663 | assert hits[0]['full_path'] == u'/view/my/file.html' 664 | assert hits[0]['user_agent'] == u'Mozilla/4.0 (compatible; MSIE 5.0b1; Mac_PowerPC)' 665 | 666 | assert len(hits) == 1 667 | 668 | def test_ovh_parsing(): 669 | """test parsing of ovh logs (which needs to be forced, as it's not autodetected)""" 670 | 671 | file_ = 'logs/ovh.log' 672 | 673 | # have to override previous globals override for this test 674 | import_logs.config.options.custom_w3c_fields = {} 675 | Recorder.recorders = [] 676 | import_logs.parser = import_logs.Parser() 677 | import_logs.config.format = import_logs.FORMATS['ovh'] 678 | import_logs.config.options.log_hostname = None 679 | import_logs.config.options.enable_http_redirects = True 680 | import_logs.config.options.enable_http_errors = True 681 | import_logs.config.options.replay_tracking = False 682 | import_logs.config.options.w3c_time_taken_in_millisecs = False 683 | import_logs.parser.parse(file_) 684 | 685 | hits = [hit.__dict__ for hit in Recorder.recorders] 686 | 687 | assert hits[0]['status'] == u'301' 688 | assert hits[0]['userid'] == u'theuser' 689 | assert hits[0]['is_error'] == False 690 | assert hits[0]['extension'] == u'/' 691 | assert hits[0]['is_download'] == False 692 | assert hits[0]['referrer'] == u'' 693 | assert hits[0]['args'] == {'uid': u'theuser'} 694 | assert hits[0]['generation_time_milli'] == 0 695 | assert hits[0]['host'] == 'www.example.com' 696 | assert hits[0]['filename'] == 'logs/ovh.log' 697 | assert hits[0]['is_redirect'] == True 698 | assert hits[0]['date'] == datetime.datetime(2012, 2, 10, 21, 42, 07) 699 | assert hits[0]['lineno'] == 0 700 | assert hits[0]['ip'] == u'1.2.3.4' 701 | assert hits[0]['query_string'] == '' 702 | assert hits[0]['path'] == u'/' 703 | assert hits[0]['is_robot'] == False 704 | assert hits[0]['full_path'] == u'/' 705 | assert hits[0]['user_agent'] == u'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11' 706 | 707 | assert len(hits) == 1 708 | 709 | import_logs.config.options.log_hostname = 'foo' 710 | 711 | def test_amazon_cloudfront_rtmp_parsing(): 712 | """test parsing of amazon cloudfront rtmp logs (which use extended W3C log format w/ custom fields for event info)""" 713 | 714 | file_ = 'logs/amazon_cloudfront_rtmp.log' 715 | 716 | # have to override previous globals override for this test 717 | import_logs.config.options.custom_w3c_fields = {} 718 | Recorder.recorders = [] 719 | import_logs.parser = import_logs.Parser() 720 | import_logs.config.format = None 721 | import_logs.config.options.enable_http_redirects = True 722 | import_logs.config.options.enable_http_errors = True 723 | import_logs.config.options.replay_tracking = False 724 | import_logs.config.options.w3c_time_taken_in_millisecs = False 725 | import_logs.parser.parse(file_) 726 | 727 | hits = [hit.__dict__ for hit in Recorder.recorders] 728 | 729 | assert hits[0]['is_download'] == False 730 | assert hits[0]['ip'] == u'192.0.2.147' 731 | assert hits[0]['is_redirect'] == False 732 | assert hits[0]['filename'] == 'logs/amazon_cloudfront_rtmp.log' 733 | assert hits[0]['event_category'] == 'cloudfront_rtmp' 734 | assert hits[0]['event_action'] == u'connect' 735 | assert hits[0]['lineno'] == 2 736 | assert hits[0]['status'] == '200' 737 | assert hits[0]['is_error'] == False 738 | assert hits[0]['event_name'] == None 739 | assert hits[0]['args'] == {} 740 | assert hits[0]['host'] == 'foo' 741 | assert hits[0]['date'] == datetime.datetime(2010, 3, 12, 23, 51, 20) 742 | assert hits[0]['path'] == u'/shqshne4jdp4b6.cloudfront.net/cfx/st\u200b' 743 | assert hits[0]['extension'] == u'net/cfx/st\u200b' 744 | assert hits[0]['referrer'] == '' 745 | assert hits[0]['userid'] == None 746 | assert hits[0]['user_agent'] == u'LNX 10,0,32,18' 747 | assert hits[0]['generation_time_milli'] == 0 748 | assert hits[0]['query_string'] == u'key=value' 749 | assert hits[0]['is_robot'] == False 750 | assert hits[0]['full_path'] == u'/shqshne4jdp4b6.cloudfront.net/cfx/st\u200b' 751 | 752 | assert hits[1]['is_download'] == False 753 | assert hits[1]['ip'] == u'192.0.2.222' 754 | assert hits[1]['is_redirect'] == False 755 | assert hits[1]['filename'] == 'logs/amazon_cloudfront_rtmp.log' 756 | assert hits[1]['event_category'] == 'cloudfront_rtmp' 757 | assert hits[1]['event_action'] == u'play' 758 | assert hits[1]['lineno'] == 3 759 | assert hits[1]['status'] == '200' 760 | assert hits[1]['is_error'] == False 761 | assert hits[1]['event_name'] == u'myvideo' 762 | assert hits[1]['args'] == {} 763 | assert hits[1]['host'] == 'foo' 764 | assert hits[1]['date'] == datetime.datetime(2010, 3, 12, 23, 51, 21) 765 | assert hits[1]['path'] == u'/shqshne4jdp4b6.cloudfront.net/cfx/st\u200b' 766 | assert hits[1]['extension'] == u'net/cfx/st\u200b' 767 | assert hits[1]['referrer'] == '' 768 | assert hits[1]['userid'] == None 769 | assert hits[1]['length'] == 3914 770 | assert hits[1]['user_agent'] == u'LNX 10,0,32,18' 771 | assert hits[1]['generation_time_milli'] == 0 772 | assert hits[1]['query_string'] == u'key=value' 773 | assert hits[1]['is_robot'] == False 774 | assert hits[1]['full_path'] == u'/shqshne4jdp4b6.cloudfront.net/cfx/st\u200b' 775 | 776 | assert len(hits) == 2 777 | 778 | def test_ignore_groups_option_removes_groups(): 779 | """Test that the --ignore-groups option removes groups so they do not appear in hits.""" 780 | 781 | file_ = 'logs/iis.log' 782 | 783 | # have to override previous globals override for this test 784 | import_logs.config.options.custom_w3c_fields = {} 785 | Recorder.recorders = [] 786 | import_logs.parser = import_logs.Parser() 787 | import_logs.config.format = None 788 | import_logs.config.options.enable_http_redirects = True 789 | import_logs.config.options.enable_http_errors = True 790 | import_logs.config.options.replay_tracking = False 791 | import_logs.config.options.w3c_time_taken_in_millisecs = True 792 | import_logs.config.options.regex_groups_to_ignore = set(['userid','generation_time_milli']) 793 | import_logs.parser.parse(file_) 794 | 795 | hits = [hit.__dict__ for hit in Recorder.recorders] 796 | 797 | assert hits[0]['userid'] == None 798 | assert hits[0]['generation_time_milli'] == 0 799 | 800 | def test_regex_group_to_custom_var_options(): 801 | """Test that the --regex-group-to-visit-cvar and --regex-group-to-page-cvar track regex groups to custom vars.""" 802 | 803 | file_ = 'logs/iis.log' 804 | 805 | # have to override previous globals override for this test 806 | import_logs.config.options.custom_w3c_fields = {} 807 | Recorder.recorders = [] 808 | import_logs.parser = import_logs.Parser() 809 | import_logs.config.format = None 810 | import_logs.config.options.enable_http_redirects = True 811 | import_logs.config.options.enable_http_errors = True 812 | import_logs.config.options.replay_tracking = False 813 | import_logs.config.options.w3c_time_taken_in_millisecs = True 814 | import_logs.config.options.regex_groups_to_ignore = set() 815 | import_logs.config.options.regex_group_to_visit_cvars_map = { 816 | 'userid': "User Name", 817 | 'date': "The Date" 818 | } 819 | import_logs.config.options.regex_group_to_page_cvars_map = { 820 | 'generation_time_milli': 'Geneartion Time', 821 | 'referrer': 'The Referrer' 822 | } 823 | import_logs.parser.parse(file_) 824 | 825 | hits = [hit.__dict__ for hit in Recorder.recorders] 826 | 827 | assert hits[0]['args']['_cvar'] == {1: ['The Date', '2012-04-01 00:00:13'], 2: ['User Name', 'theuser']} # check visit custom vars 828 | assert hits[0]['args']['cvar'] == {1: ['Geneartion Time', '1687'], 2: ['HTTP-method', 'GET']} # check page custom vars 829 | 830 | assert hits[0]['userid'] == 'theuser' 831 | assert hits[0]['date'] == datetime.datetime(2012, 4, 1, 0, 0, 13) 832 | assert hits[0]['generation_time_milli'] == 1687 833 | assert hits[0]['referrer'] == '' 834 | 835 | def test_w3c_custom_field_regex_option(): 836 | """Test that --w3c-field-regex can be used to match custom W3C log fields.""" 837 | 838 | file_ = 'logs/iis.log' 839 | 840 | # have to override previous globals override for this test 841 | import_logs.config.options.custom_w3c_fields = {} 842 | Recorder.recorders = [] 843 | import_logs.parser = import_logs.Parser() 844 | import_logs.config.format = None 845 | import_logs.config.options.enable_http_redirects = True 846 | import_logs.config.options.enable_http_errors = True 847 | import_logs.config.options.replay_tracking = False 848 | import_logs.config.options.w3c_time_taken_in_millisecs = True 849 | import_logs.config.options.w3c_field_regexes = { 850 | 'sc-substatus': '(?P\S+)', 851 | 'sc-win32-status': '(?P\S+)' 852 | } 853 | 854 | format = import_logs.W3cExtendedFormat() 855 | 856 | file_handle = open(file_) 857 | format.check_format(file_handle) 858 | match = None 859 | while not match: 860 | line = file_handle.readline() 861 | if not line: 862 | break 863 | match = format.match(line) 864 | file_handle.close() 865 | 866 | assert match is not None 867 | assert format.get('substatus') == '654' 868 | assert format.get('win32_status') == '456' 869 | 870 | def test_custom_log_date_format_option(): 871 | """Test that --log-date-format will change how dates are parsed in a custom log format.""" 872 | 873 | file_ = 'logs/custom_regex_custom_date.log' 874 | 875 | # have to override previous globals override for this test 876 | Recorder.recorders = [] 877 | import_logs.parser = import_logs.Parser() 878 | import_logs.config.options.w3c_field_regexes = None 879 | import_logs.config.options.regex_group_to_visit_cvars_map = None 880 | import_logs.config.options.regex_group_to_page_cvars_map = None 881 | import_logs.config.options.log_format_regex = ( 882 | '(?P\S+)\s+\S+\s+\S+\s+\[(?P.*?)\]\s+' 883 | '"\S+\s+(?P.*?)\s+\S+"\s+(?P\S+)\s+(?P\S+)' 884 | ) 885 | import_logs.config.options.log_date_format = '%B - %d, %Y:%H:%M:%S' 886 | import_logs.config.format = import_logs.RegexFormat('custom', import_logs.config.options.log_format_regex, 887 | import_logs.config.options.log_date_format) 888 | 889 | import_logs.parser.parse(file_) 890 | 891 | hits = [hit.__dict__ for hit in Recorder.recorders] 892 | 893 | assert hits[0]['date'] == datetime.datetime(2012, 2, 10, 16, 42, 7) 894 | -------------------------------------------------------------------------------- /import_logs.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/python 2 | # vim: et sw=4 ts=4: 3 | # -*- coding: utf-8 -*- 4 | # 5 | # Matomo - free/libre analytics platform 6 | # 7 | # @link https://matomo.org 8 | # @license https://www.gnu.org/licenses/gpl-3.0.html GPL v3 or later 9 | # @version $Id$ 10 | # 11 | # For more info see: https://matomo.org/log-analytics/ and https://matomo.org/docs/log-analytics-tool-how-to/ 12 | # 13 | # Requires Python 2.6 or 2.7 14 | # 15 | 16 | import sys 17 | 18 | if sys.version_info[0] != 2: 19 | print('The log importer currently does not work with Python 3 (or higher)') 20 | print('Please use Python 2.6 or 2.7') 21 | sys.exit(1) 22 | 23 | import base64 24 | import bz2 25 | import ConfigParser 26 | import datetime 27 | import fnmatch 28 | import gzip 29 | import hashlib 30 | import httplib 31 | import inspect 32 | import itertools 33 | import logging 34 | import optparse 35 | import os 36 | import os.path 37 | import Queue 38 | import re 39 | import ssl 40 | import sys 41 | import threading 42 | import time 43 | import urllib 44 | import urllib2 45 | import urlparse 46 | import subprocess 47 | import functools 48 | import traceback 49 | import socket 50 | import textwrap 51 | 52 | try: 53 | import json 54 | except ImportError: 55 | try: 56 | import simplejson as json 57 | except ImportError: 58 | if sys.version_info < (2, 6): 59 | print >> sys.stderr, 'simplejson (http://pypi.python.org/pypi/simplejson/) is required.' 60 | sys.exit(1) 61 | 62 | 63 | 64 | ## 65 | ## Constants. 66 | ## 67 | 68 | STATIC_EXTENSIONS = set(( 69 | 'gif jpg jpeg png bmp ico svg svgz ttf otf eot woff woff2 class swf css js xml robots.txt webp' 70 | ).split()) 71 | 72 | DOWNLOAD_EXTENSIONS = set(( 73 | '7z aac arc arj asf asx avi bin csv deb dmg doc docx exe flac flv gz gzip hqx ' 74 | 'ibooks jar json mpg mp2 mp3 mp4 mpeg mov movie msi msp odb odf odg odp ' 75 | 'ods odt ogg ogv pdf phps ppt pptx qt qtm ra ram rar rpm rtf sea sit tar tbz ' 76 | 'bz2 tbz tgz torrent txt wav webm wma wmv wpd xls xlsx xml xsd z zip ' 77 | 'azw3 epub mobi apk' 78 | ).split()) 79 | 80 | # A good source is: http://phpbb-bots.blogspot.com/ 81 | # user agents must be lowercase 82 | EXCLUDED_USER_AGENTS = ( 83 | 'adsbot-google', 84 | 'ask jeeves', 85 | 'baidubot', 86 | 'bot-', 87 | 'bot/', 88 | 'ccooter/', 89 | 'crawl', 90 | 'curl', 91 | 'echoping', 92 | 'exabot', 93 | 'feed', 94 | 'googlebot', 95 | 'ia_archiver', 96 | 'java/', 97 | 'libwww', 98 | 'mediapartners-google', 99 | 'msnbot', 100 | 'netcraftsurvey', 101 | 'panopta', 102 | 'pingdom.com_bot_', 103 | 'robot', 104 | 'spider', 105 | 'surveybot', 106 | 'twiceler', 107 | 'voilabot', 108 | 'yahoo', 109 | 'yandex', 110 | ) 111 | 112 | MATOMO_DEFAULT_MAX_ATTEMPTS = 3 113 | MATOMO_DEFAULT_DELAY_AFTER_FAILURE = 10 114 | DEFAULT_SOCKET_TIMEOUT = 300 115 | 116 | MATOMO_EXPECTED_IMAGE = base64.b64decode( 117 | 'R0lGODlhAQABAIAAAAAAAAAAACH5BAEAAAAALAAAAAABAAEAAAICRAEAOw==' 118 | ) 119 | 120 | ## 121 | ## Formats. 122 | ## 123 | 124 | class BaseFormatException(Exception): pass 125 | 126 | class BaseFormat(object): 127 | def __init__(self, name): 128 | self.name = name 129 | self.regex = None 130 | self.date_format = '%d/%b/%Y:%H:%M:%S' 131 | 132 | def check_format(self, file): 133 | line = file.readline() 134 | try: 135 | file.seek(0) 136 | except IOError: 137 | pass 138 | 139 | return self.check_format_line(line) 140 | 141 | def check_format_line(self, line): 142 | return False 143 | 144 | class JsonFormat(BaseFormat): 145 | def __init__(self, name): 146 | super(JsonFormat, self).__init__(name) 147 | self.json = None 148 | self.date_format = '%Y-%m-%dT%H:%M:%S' 149 | 150 | def check_format_line(self, line): 151 | try: 152 | self.json = json.loads(line) 153 | return True 154 | except: 155 | return False 156 | 157 | def match(self, line): 158 | try: 159 | # nginx outputs malformed JSON w/ hex escapes when confronted w/ non-UTF input. we have to 160 | # workaround this by converting hex escapes in strings to unicode escapes. the conversion is naive, 161 | # so it does not take into account the string's actual encoding (which we don't have access to). 162 | line = line.replace('\\x', '\\u00') 163 | 164 | self.json = json.loads(line) 165 | return self 166 | except: 167 | self.json = None 168 | return None 169 | 170 | def get(self, key): 171 | # Some ugly patchs ... 172 | if key == 'generation_time_milli': 173 | self.json[key] = int(float(self.json[key]) * 1000) 174 | # Patch date format ISO 8601 175 | elif key == 'date': 176 | tz = self.json[key][19:] 177 | self.json['timezone'] = tz.replace(':', '') 178 | self.json[key] = self.json[key][:19] 179 | 180 | try: 181 | return self.json[key] 182 | except KeyError: 183 | raise BaseFormatException() 184 | 185 | def get_all(self,): 186 | return self.json 187 | 188 | def remove_ignored_groups(self, groups): 189 | for group in groups: 190 | del self.json[group] 191 | 192 | class RegexFormat(BaseFormat): 193 | 194 | def __init__(self, name, regex, date_format=None): 195 | super(RegexFormat, self).__init__(name) 196 | if regex is not None: 197 | self.regex = re.compile(regex) 198 | if date_format is not None: 199 | self.date_format = date_format 200 | self.matched = None 201 | 202 | def check_format_line(self, line): 203 | return self.match(line) 204 | 205 | def match(self,line): 206 | if not self.regex: 207 | return None 208 | match_result = self.regex.match(line) 209 | if match_result: 210 | self.matched = match_result.groupdict() 211 | else: 212 | self.matched = None 213 | return match_result 214 | 215 | def get(self, key): 216 | try: 217 | return self.matched[key] 218 | except KeyError: 219 | raise BaseFormatException("Cannot find group '%s'." % key) 220 | 221 | def get_all(self,): 222 | return self.matched 223 | 224 | def remove_ignored_groups(self, groups): 225 | for group in groups: 226 | del self.matched[group] 227 | 228 | class W3cExtendedFormat(RegexFormat): 229 | 230 | FIELDS_LINE_PREFIX = '#Fields: ' 231 | 232 | fields = { 233 | 'date': '(?P\d+[-\d+]+', 234 | 'time': '[\d+:]+)[.\d]*?', # TODO should not assume date & time will be together not sure how to fix ATM. 235 | 'cs-uri-stem': '(?P/\S*)', 236 | 'cs-uri-query': '(?P\S*)', 237 | 'c-ip': '"?(?P[\w*.:-]*)"?', 238 | 'cs(User-Agent)': '(?P".*?"|\S*)', 239 | 'cs(Referer)': '(?P\S+)', 240 | 'sc-status': '(?P\d+)', 241 | 'sc-bytes': '(?P\S+)', 242 | 'cs-host': '(?P\S+)', 243 | 'cs-method': '(?P\S+)', 244 | 'cs-username': '(?P\S+)', 245 | 'time-taken': '(?P[.\d]+)' 246 | } 247 | 248 | def __init__(self): 249 | super(W3cExtendedFormat, self).__init__('w3c_extended', None, '%Y-%m-%d %H:%M:%S') 250 | 251 | def check_format(self, file): 252 | self.create_regex(file) 253 | 254 | # if we couldn't create a regex, this file does not follow the W3C extended log file format 255 | if not self.regex: 256 | try: 257 | file.seek(0) 258 | except IOError: 259 | pass 260 | 261 | return 262 | 263 | first_line = file.readline() 264 | 265 | try: 266 | file.seek(0) 267 | except IOError: 268 | pass 269 | 270 | return self.check_format_line(first_line) 271 | 272 | def create_regex(self, file): 273 | fields_line = None 274 | if config.options.w3c_fields: 275 | fields_line = config.options.w3c_fields 276 | 277 | # collect all header lines up until the Fields: line 278 | # if we're reading from stdin, we can't seek, so don't read any more than the Fields line 279 | header_lines = [] 280 | while fields_line is None: 281 | line = file.readline().strip() 282 | 283 | if not line: 284 | continue 285 | 286 | if not line.startswith('#'): 287 | break 288 | 289 | if line.startswith(W3cExtendedFormat.FIELDS_LINE_PREFIX): 290 | fields_line = line 291 | else: 292 | header_lines.append(line) 293 | 294 | if not fields_line: 295 | return 296 | 297 | # store the header lines for a later check for IIS 298 | self.header_lines = header_lines 299 | 300 | # Parse the 'Fields: ' line to create the regex to use 301 | full_regex = [] 302 | 303 | expected_fields = type(self).fields.copy() # turn custom field mapping into field => regex mapping 304 | 305 | # if the --w3c-time-taken-millisecs option is used, make sure the time-taken field is interpreted as milliseconds 306 | if config.options.w3c_time_taken_in_millisecs: 307 | expected_fields['time-taken'] = '(?P[\d.]+)' 308 | 309 | for mapped_field_name, field_name in config.options.custom_w3c_fields.iteritems(): 310 | expected_fields[mapped_field_name] = expected_fields[field_name] 311 | del expected_fields[field_name] 312 | 313 | # add custom field regexes supplied through --w3c-field-regex option 314 | for field_name, field_regex in config.options.w3c_field_regexes.iteritems(): 315 | expected_fields[field_name] = field_regex 316 | 317 | # Skip the 'Fields: ' prefix. 318 | fields_line = fields_line[9:].strip() 319 | for field in re.split('\s+', fields_line): 320 | try: 321 | regex = expected_fields[field] 322 | except KeyError: 323 | regex = '(?:".*?"|\S+)' 324 | full_regex.append(regex) 325 | full_regex = '\s+'.join(full_regex) 326 | 327 | logging.debug("Based on 'Fields:' line, computed regex to be %s", full_regex) 328 | 329 | self.regex = re.compile(full_regex) 330 | 331 | def check_for_iis_option(self): 332 | if not config.options.w3c_time_taken_in_millisecs and self._is_time_taken_milli() and self._is_iis(): 333 | logging.info("WARNING: IIS log file being parsed without --w3c-time-taken-milli option. IIS" 334 | " stores millisecond values in the time-taken field. If your logfile does this, the aforementioned" 335 | " option must be used in order to get accurate generation times.") 336 | 337 | def _is_iis(self): 338 | return len([line for line in self.header_lines if 'internet information services' in line.lower() or 'iis' in line.lower()]) > 0 339 | 340 | def _is_time_taken_milli(self): 341 | return 'generation_time_milli' not in self.regex.pattern 342 | 343 | class IisFormat(W3cExtendedFormat): 344 | 345 | fields = W3cExtendedFormat.fields.copy() 346 | fields.update({ 347 | 'time-taken': '(?P[.\d]+)', 348 | 'sc-win32-status': '(?P<__win32_status>\S+)' # this group is useless for log importing, but capturing it 349 | # will ensure we always select IIS for the format instead of 350 | # W3C logs when detecting the format. This way there will be 351 | # less accidental importing of IIS logs w/o --w3c-time-taken-milli. 352 | }) 353 | 354 | def __init__(self): 355 | super(IisFormat, self).__init__() 356 | 357 | self.name = 'iis' 358 | 359 | class ShoutcastFormat(W3cExtendedFormat): 360 | 361 | fields = W3cExtendedFormat.fields.copy() 362 | fields.update({ 363 | 'c-status': '(?P\d+)', 364 | 'x-duration': '(?P[.\d]+)' 365 | }) 366 | 367 | def __init__(self): 368 | super(ShoutcastFormat, self).__init__() 369 | 370 | self.name = 'shoutcast' 371 | 372 | def get(self, key): 373 | if key == 'user_agent': 374 | user_agent = super(ShoutcastFormat, self).get(key) 375 | return urllib2.unquote(user_agent) 376 | else: 377 | return super(ShoutcastFormat, self).get(key) 378 | 379 | class AmazonCloudFrontFormat(W3cExtendedFormat): 380 | 381 | fields = W3cExtendedFormat.fields.copy() 382 | fields.update({ 383 | 'x-event': '(?P\S+)', 384 | 'x-sname': '(?P\S+)', 385 | 'cs-uri-stem': '(?:rtmp:/)?(?P/\S*)', 386 | 'c-user-agent': '(?P".*?"|\S+)', 387 | 388 | # following are present to match cloudfront instead of W3C when we know it's cloudfront 389 | 'x-edge-location': '(?P".*?"|\S+)', 390 | 'x-edge-result-type': '(?P".*?"|\S+)', 391 | 'x-edge-request-id': '(?P".*?"|\S+)', 392 | 'x-host-header': '(?P".*?"|\S+)' 393 | }) 394 | 395 | def __init__(self): 396 | super(AmazonCloudFrontFormat, self).__init__() 397 | 398 | self.name = 'amazon_cloudfront' 399 | 400 | def get(self, key): 401 | if key == 'event_category' and 'event_category' not in self.matched: 402 | return 'cloudfront_rtmp' 403 | elif key == 'status' and 'status' not in self.matched: 404 | return '200' 405 | elif key == 'user_agent': 406 | user_agent = super(AmazonCloudFrontFormat, self).get(key) 407 | return urllib2.unquote(user_agent) 408 | else: 409 | return super(AmazonCloudFrontFormat, self).get(key) 410 | 411 | _HOST_PREFIX = '(?P[\w\-\.]*)(?::\d+)?\s+' 412 | 413 | _COMMON_LOG_FORMAT = ( 414 | '(?P[\w*.:-]+)\s+\S+\s+(?P\S+)\s+\[(?P.*?)\s+(?P.*?)\]\s+' 415 | '"(?P\S+)\s+(?P.*?)\s+\S+"\s+(?P\d+)\s+(?P\S+)' 416 | ) 417 | _NCSA_EXTENDED_LOG_FORMAT = (_COMMON_LOG_FORMAT + 418 | '\s+"(?P.*?)"\s+"(?P.*?)"' 419 | ) 420 | _S3_LOG_FORMAT = ( 421 | '\S+\s+(?P\S+)\s+\[(?P.*?)\s+(?P.*?)\]\s+(?P[\w*.:-]+)\s+' 422 | '(?P\S+)\s+\S+\s+\S+\s+\S+\s+"(?P\S+)\s+(?P.*?)\s+\S+"\s+(?P\d+)\s+\S+\s+(?P\S+)\s+' 423 | '\S+\s+\S+\s+\S+\s+"(?P.*?)"\s+"(?P.*?)"' 424 | ) 425 | _ICECAST2_LOG_FORMAT = ( _NCSA_EXTENDED_LOG_FORMAT + 426 | '\s+(?P[0-9-]+)' 427 | ) 428 | _ELB_LOG_FORMAT = ( 429 | '(?P[0-9-]+T[0-9:]+)\.\S+\s+\S+\s+(?P[\w*.:-]+):\d+\s+\S+:\d+\s+\S+\s+(?P\S+)\s+\S+\s+' 430 | '(?P\d+)\s+\S+\s+\S+\s+(?P\S+)\s+' 431 | '"\S+\s+\w+:\/\/(?P[\w\-\.]*):\d+(?P\/\S*)\s+[^"]+"\s+"(?P[^"]+)"\s+\S+\s+\S+' 432 | ) 433 | 434 | _OVH_FORMAT = ( 435 | '(?P\S+)\s+' + _HOST_PREFIX + '(?P\S+)\s+\[(?P.*?)\s+(?P.*?)\]\s+' 436 | '"\S+\s+(?P.*?)\s+\S+"\s+(?P\S+)\s+(?P\S+)' 437 | '\s+"(?P.*?)"\s+"(?P.*?)"' 438 | ) 439 | 440 | FORMATS = { 441 | 'common': RegexFormat('common', _COMMON_LOG_FORMAT), 442 | 'common_vhost': RegexFormat('common_vhost', _HOST_PREFIX + _COMMON_LOG_FORMAT), 443 | 'ncsa_extended': RegexFormat('ncsa_extended', _NCSA_EXTENDED_LOG_FORMAT), 444 | 'common_complete': RegexFormat('common_complete', _HOST_PREFIX + _NCSA_EXTENDED_LOG_FORMAT), 445 | 'w3c_extended': W3cExtendedFormat(), 446 | 'amazon_cloudfront': AmazonCloudFrontFormat(), 447 | 'iis': IisFormat(), 448 | 'shoutcast': ShoutcastFormat(), 449 | 's3': RegexFormat('s3', _S3_LOG_FORMAT), 450 | 'icecast2': RegexFormat('icecast2', _ICECAST2_LOG_FORMAT), 451 | 'elb': RegexFormat('elb', _ELB_LOG_FORMAT, '%Y-%m-%dT%H:%M:%S'), 452 | 'nginx_json': JsonFormat('nginx_json'), 453 | 'ovh': RegexFormat('ovh', _OVH_FORMAT) 454 | } 455 | 456 | ## 457 | ## Code. 458 | ## 459 | 460 | class Configuration(object): 461 | """ 462 | Stores all the configuration options by reading sys.argv and parsing, 463 | if needed, the config.inc.php. 464 | 465 | It has 2 attributes: options and filenames. 466 | """ 467 | 468 | class Error(Exception): 469 | pass 470 | 471 | def _create_parser(self): 472 | """ 473 | Initialize and return the OptionParser instance. 474 | """ 475 | option_parser = optparse.OptionParser( 476 | usage='Usage: %prog [options] log_file [ log_file [...] ]', 477 | description="Import HTTP access logs to Matomo. " 478 | "log_file is the path to a server access log file (uncompressed, .gz, .bz2, or specify - to read from stdin). " 479 | " You may also import many log files at once (for example set log_file to *.log or *.log.gz)." 480 | " By default, the script will try to produce clean reports and will exclude bots, static files, discard http error and redirects, etc. This is customizable, see below.", 481 | epilog="About Matomo Server Log Analytics: https://matomo.org/log-analytics/ " 482 | " Found a bug? Please create a ticket in https://dev.matomo.org/ " 483 | " Please send your suggestions or successful user story to hello@matomo.org " 484 | ) 485 | 486 | # Basic auth user 487 | option_parser.add_option( 488 | '--auth-user', dest='auth_user', 489 | help="Basic auth user", 490 | ) 491 | # Basic auth password 492 | option_parser.add_option( 493 | '--auth-password', dest='auth_password', 494 | help="Basic auth password", 495 | ) 496 | option_parser.add_option( 497 | '--debug', '-d', dest='debug', action='count', default=0, 498 | help="Enable debug output (specify multiple times for more verbose)", 499 | ) 500 | option_parser.add_option( 501 | '--debug-tracker', dest='debug_tracker', action='store_true', default=False, 502 | help="Appends &debug=1 to tracker requests and prints out the result so the tracker can be debugged. If " 503 | "using the log importer results in errors with the tracker or improperly recorded visits, this option can " 504 | "be used to find out what the tracker is doing wrong. To see debug tracker output, you must also set the " 505 | "[Tracker] debug_on_demand INI config to 1 in your Matomo's config.ini.php file." 506 | ) 507 | option_parser.add_option( 508 | '--debug-request-limit', dest='debug_request_limit', type='int', default=None, 509 | help="Debug option that will exit after N requests are parsed. Can be used w/ --debug-tracker to limit the " 510 | "output of a large log file." 511 | ) 512 | option_parser.add_option( 513 | '--url', dest='matomo_url', 514 | help="REQUIRED Your Matomo server URL, eg. http://example.com/matomo/ or http://analytics.example.net", 515 | ) 516 | option_parser.add_option( 517 | '--api-url', dest='matomo_api_url', 518 | help="This URL will be used to send API requests (use it if your tracker URL differs from UI/API url), " 519 | "eg. http://other-example.com/matomo/ or http://analytics-api.example.net", 520 | ) 521 | option_parser.add_option( 522 | '--dry-run', dest='dry_run', 523 | action='store_true', default=False, 524 | help="Perform a trial run with no tracking data being inserted into Matomo", 525 | ) 526 | option_parser.add_option( 527 | '--show-progress', dest='show_progress', 528 | action='store_true', default=os.isatty(sys.stdout.fileno()), 529 | help="Print a progress report X seconds (default: 1, use --show-progress-delay to override)" 530 | ) 531 | option_parser.add_option( 532 | '--show-progress-delay', dest='show_progress_delay', 533 | type='int', default=1, 534 | help="Change the default progress delay" 535 | ) 536 | option_parser.add_option( 537 | '--add-sites-new-hosts', dest='add_sites_new_hosts', 538 | action='store_true', default=False, 539 | help="When a hostname is found in the log file, but not matched to any website " 540 | "in Matomo, automatically create a new website in Matomo with this hostname to " 541 | "import the logs" 542 | ) 543 | option_parser.add_option( 544 | '--idsite', dest='site_id', 545 | help= ("When specified, " 546 | "data in the specified log files will be tracked for this Matomo site ID." 547 | " The script will not auto-detect the website based on the log line hostname (new websites will not be automatically created).") 548 | ) 549 | option_parser.add_option( 550 | '--idsite-fallback', dest='site_id_fallback', 551 | help="Default Matomo site ID to use if the hostname doesn't match any " 552 | "known Website's URL. New websites will not be automatically created. " 553 | " Used only if --add-sites-new-hosts or --idsite are not set", 554 | ) 555 | default_config = os.path.abspath( 556 | os.path.join(os.path.dirname(__file__), 557 | '../../config/config.ini.php'), 558 | ) 559 | option_parser.add_option( 560 | '--config', dest='config_file', default=default_config, 561 | help=( 562 | "This is only used when --login and --password is not used. " 563 | "Matomo will read the configuration file (default: %default) to " 564 | "fetch the Super User token_auth from the config file. " 565 | ) 566 | ) 567 | option_parser.add_option( 568 | '--login', dest='login', 569 | help="You can manually specify the Matomo Super User login" 570 | ) 571 | option_parser.add_option( 572 | '--password', dest='password', 573 | help="You can manually specify the Matomo Super User password" 574 | ) 575 | option_parser.add_option( 576 | '--token-auth', dest='matomo_token_auth', 577 | help="Matomo user token_auth, the token_auth is found in Matomo > Settings > API. " 578 | "You must use a token_auth that has at least 'admin' or 'super user' permission. " 579 | "If you use a token_auth for a non admin user, your users' IP addresses will not be tracked properly. " 580 | ) 581 | 582 | option_parser.add_option( 583 | '--hostname', dest='hostnames', action='append', default=[], 584 | help="Accepted hostname (requests with other hostnames will be excluded). " 585 | " You may use the star character * " 586 | " Example: --hostname=*domain.com" 587 | " Can be specified multiple times" 588 | ) 589 | option_parser.add_option( 590 | '--exclude-path', dest='excluded_paths', action='append', default=[], 591 | help="Any URL path matching this exclude-path will not be imported in Matomo. " 592 | " You must use the star character *. " 593 | " Example: --exclude-path=*/admin/*" 594 | " Can be specified multiple times. " 595 | ) 596 | option_parser.add_option( 597 | '--exclude-path-from', dest='exclude_path_from', 598 | help="Each line from this file is a path to exclude. Each path must contain the character * to match a string. (see: --exclude-path)" 599 | ) 600 | option_parser.add_option( 601 | '--include-path', dest='included_paths', action='append', default=[], 602 | help="Paths to include. Can be specified multiple times. If not specified, all paths are included." 603 | ) 604 | option_parser.add_option( 605 | '--include-path-from', dest='include_path_from', 606 | help="Each line from this file is a path to include" 607 | ) 608 | option_parser.add_option( 609 | '--useragent-exclude', dest='excluded_useragents', 610 | action='append', default=[], 611 | help="User agents to exclude (in addition to the standard excluded " 612 | "user agents). Can be specified multiple times", 613 | ) 614 | option_parser.add_option( 615 | '--enable-static', dest='enable_static', 616 | action='store_true', default=False, 617 | help="Track static files (images, css, js, ico, ttf, etc.)" 618 | ) 619 | option_parser.add_option( 620 | '--enable-bots', dest='enable_bots', 621 | action='store_true', default=False, 622 | help="Track bots. All bot visits will have a Custom Variable set with name='Bot' and value='$Bot_user_agent_here$'" 623 | ) 624 | option_parser.add_option( 625 | '--enable-http-errors', dest='enable_http_errors', 626 | action='store_true', default=False, 627 | help="Track HTTP errors (status code 4xx or 5xx)" 628 | ) 629 | option_parser.add_option( 630 | '--enable-http-redirects', dest='enable_http_redirects', 631 | action='store_true', default=False, 632 | help="Track HTTP redirects (status code 3xx except 304)" 633 | ) 634 | option_parser.add_option( 635 | '--enable-reverse-dns', dest='reverse_dns', 636 | action='store_true', default=False, 637 | help="Enable reverse DNS, used to generate the 'Providers' report in Matomo. " 638 | "Disabled by default, as it impacts performance" 639 | ) 640 | option_parser.add_option( 641 | '--strip-query-string', dest='strip_query_string', 642 | action='store_true', default=False, 643 | help="Strip the query string from the URL" 644 | ) 645 | option_parser.add_option( 646 | '--query-string-delimiter', dest='query_string_delimiter', default='?', 647 | help="The query string delimiter (default: %default)" 648 | ) 649 | option_parser.add_option( 650 | '--log-format-name', dest='log_format_name', default=None, 651 | help=("Access log format to detect (supported are: %s). " 652 | "When not specified, the log format will be autodetected by trying all supported log formats." 653 | % ', '.join(sorted(FORMATS.iterkeys()))) 654 | ) 655 | available_regex_groups = ['date', 'path', 'query_string', 'ip', 'user_agent', 'referrer', 'status', 656 | 'length', 'host', 'userid', 'generation_time_milli', 'event_action', 657 | 'event_name', 'timezone', 'session_time'] 658 | option_parser.add_option( 659 | '--log-format-regex', dest='log_format_regex', default=None, 660 | help="Regular expression used to parse log entries. Regexes must contain named groups for different log fields. " 661 | "Recognized fields include: %s. For an example of a supported Regex, see the source code of this file. " 662 | "Overrides --log-format-name." % (', '.join(available_regex_groups)) 663 | ) 664 | option_parser.add_option( 665 | '--log-date-format', dest='log_date_format', default=None, 666 | help="Format string used to parse dates. You can specify any format that can also be specified to " 667 | "the strptime python function." 668 | ) 669 | option_parser.add_option( 670 | '--log-hostname', dest='log_hostname', default=None, 671 | help="Force this hostname for a log format that doesn't include it. All hits " 672 | "will seem to come to this host" 673 | ) 674 | option_parser.add_option( 675 | '--skip', dest='skip', default=0, type='int', 676 | help="Skip the n first lines to start parsing/importing data at a given line for the specified log file", 677 | ) 678 | option_parser.add_option( 679 | '--recorders', dest='recorders', default=1, type='int', 680 | help="Number of simultaneous recorders (default: %default). " 681 | "It should be set to the number of CPU cores in your server. " 682 | "You can also experiment with higher values which may increase performance until a certain point", 683 | ) 684 | option_parser.add_option( 685 | '--recorder-max-payload-size', dest='recorder_max_payload_size', default=200, type='int', 686 | help="Maximum number of log entries to record in one tracking request (default: %default). " 687 | ) 688 | option_parser.add_option( 689 | '--replay-tracking', dest='replay_tracking', 690 | action='store_true', default=False, 691 | help="Replay piwik.php requests found in custom logs (only piwik.php requests expected). \nSee https://matomo.org/faq/how-to/faq_17033/" 692 | ) 693 | option_parser.add_option( 694 | '--replay-tracking-expected-tracker-file', dest='replay_tracking_expected_tracker_file', default='piwik.php', 695 | help="The expected suffix for tracking request paths. Only logs whose paths end with this will be imported. Defaults " 696 | "to 'piwik.php' so only requests to the piwik.php file will be imported." 697 | ) 698 | option_parser.add_option( 699 | '--output', dest='output', 700 | help="Redirect output (stdout and stderr) to the specified file" 701 | ) 702 | option_parser.add_option( 703 | '--encoding', dest='encoding', default='utf8', 704 | help="Log files encoding (default: %default)" 705 | ) 706 | option_parser.add_option( 707 | '--disable-bulk-tracking', dest='use_bulk_tracking', 708 | default=True, action='store_false', 709 | help="Disables use of bulk tracking so recorders record one hit at a time." 710 | ) 711 | option_parser.add_option( 712 | '--debug-force-one-hit-every-Ns', dest='force_one_action_interval', default=False, type='float', 713 | help="Debug option that will force each recorder to record one hit every N secs." 714 | ) 715 | option_parser.add_option( 716 | '--force-lowercase-path', dest='force_lowercase_path', default=False, action='store_true', 717 | help="Make URL path lowercase so paths with the same letters but different cases are " 718 | "treated the same." 719 | ) 720 | option_parser.add_option( 721 | '--enable-testmode', dest='enable_testmode', default=False, action='store_true', 722 | help="If set, it will try to get the token_auth from the matomo_tests directory" 723 | ) 724 | option_parser.add_option( 725 | '--download-extensions', dest='download_extensions', default=None, 726 | help="By default Matomo tracks as Downloads the most popular file extensions. If you set this parameter (format: pdf,doc,...) then files with an extension found in the list will be imported as Downloads, other file extensions downloads will be skipped." 727 | ) 728 | option_parser.add_option( 729 | '--add-download-extensions', dest='extra_download_extensions', default=None, 730 | help="Add extensions that should be treated as downloads. See --download-extensions for more info." 731 | ) 732 | option_parser.add_option( 733 | '--w3c-map-field', action='callback', callback=functools.partial(self._set_option_map, 'custom_w3c_fields'), type='string', 734 | help="Map a custom log entry field in your W3C log to a default one. Use this option to load custom log " 735 | "files that use the W3C extended log format such as those from the Advanced Logging W3C module. Used " 736 | "as, eg, --w3c-map-field my-date=date. Recognized default fields include: %s\n\n" 737 | "Formats that extend the W3C extended log format (like the cloudfront RTMP log format) may define more " 738 | "fields that can be mapped." 739 | % (', '.join(W3cExtendedFormat.fields.keys())) 740 | ) 741 | option_parser.add_option( 742 | '--w3c-time-taken-millisecs', action='store_true', default=False, dest='w3c_time_taken_in_millisecs', 743 | help="If set, interprets the time-taken W3C log field as a number of milliseconds. This must be set for importing" 744 | " IIS logs." 745 | ) 746 | option_parser.add_option( 747 | '--w3c-fields', dest='w3c_fields', default=None, 748 | help="Specify the '#Fields:' line for a log file in the W3C Extended log file format. Use this option if " 749 | "your log file doesn't contain the '#Fields:' line which is required for parsing. This option must be used " 750 | "in conjuction with --log-format-name=w3c_extended.\n" 751 | "Example: --w3c-fields='#Fields: date time c-ip ...'" 752 | ) 753 | option_parser.add_option( 754 | '--w3c-field-regex', action='callback', callback=functools.partial(self._set_option_map, 'w3c_field_regexes'), type='string', 755 | help="Specify a regex for a field in your W3C extended log file. You can use this option to parse fields the " 756 | "importer does not natively recognize and then use one of the --regex-group-to-XXX-cvar options to track " 757 | "the field in a custom variable. For example, specifying --w3c-field-regex=sc-win32-status=(?P\\S+) " 758 | "--regex-group-to-page-cvar=\"win32_status=Windows Status Code\" will track the sc-win32-status IIS field " 759 | "in the 'Windows Status Code' custom variable. Regexes must contain a named group." 760 | ) 761 | option_parser.add_option( 762 | '--title-category-delimiter', dest='title_category_delimiter', default='/', 763 | help="If --enable-http-errors is used, errors are shown in the page titles report. If you have " 764 | "changed General.action_title_category_delimiter in your Matomo configuration, you need to set this " 765 | "option to the same value in order to get a pretty page titles report." 766 | ) 767 | option_parser.add_option( 768 | '--dump-log-regex', dest='dump_log_regex', action='store_true', default=False, 769 | help="Prints out the regex string used to parse log lines and exists. Can be useful for using formats " 770 | "in newer versions of the script in older versions of the script. The output regex can be used with " 771 | "the --log-format-regex option." 772 | ) 773 | 774 | option_parser.add_option( 775 | '--ignore-groups', dest='regex_groups_to_ignore', default=None, 776 | help="Comma separated list of regex groups to ignore when parsing log lines. Can be used to, for example, " 777 | "disable normal user id tracking. See documentation for --log-format-regex for list of available " 778 | "regex groups." 779 | ) 780 | 781 | option_parser.add_option( 782 | '--regex-group-to-visit-cvar', action='callback', callback=functools.partial(self._set_option_map, 'regex_group_to_visit_cvars_map'), type='string', 783 | help="Track an attribute through a custom variable with visit scope instead of through Matomo's normal " 784 | "approach. For example, to track usernames as a custom variable instead of through the uid tracking " 785 | "parameter, supply --regex-group-to-visit-cvar=\"userid=User Name\". This will track usernames in a " 786 | "custom variable named 'User Name'. The list of available regex groups can be found in the documentation " 787 | "for --log-format-regex (additional regex groups you may have defined " 788 | "in --log-format-regex can also be used)." 789 | ) 790 | option_parser.add_option( 791 | '--regex-group-to-page-cvar', action='callback', callback=functools.partial(self._set_option_map, 'regex_group_to_page_cvars_map'), type='string', 792 | help="Track an attribute through a custom variable with page scope instead of through Matomo's normal " 793 | "approach. For example, to track usernames as a custom variable instead of through the uid tracking " 794 | "parameter, supply --regex-group-to-page-cvar=\"userid=User Name\". This will track usernames in a " 795 | "custom variable named 'User Name'. The list of available regex groups can be found in the documentation " 796 | "for --log-format-regex (additional regex groups you may have defined " 797 | "in --log-format-regex can also be used)." 798 | ) 799 | option_parser.add_option( 800 | '--track-http-method', dest='track_http_method', default=False, 801 | help="Enables tracking of http method as custom page variable if method group is available in log format." 802 | ) 803 | option_parser.add_option( 804 | '--retry-max-attempts', dest='max_attempts', default=MATOMO_DEFAULT_MAX_ATTEMPTS, type='int', 805 | help="The maximum number of times to retry a failed tracking request." 806 | ) 807 | option_parser.add_option( 808 | '--retry-delay', dest='delay_after_failure', default=MATOMO_DEFAULT_DELAY_AFTER_FAILURE, type='int', 809 | help="The number of seconds to wait before retrying a failed tracking request." 810 | ) 811 | option_parser.add_option( 812 | '--request-timeout', dest='request_timeout', default=DEFAULT_SOCKET_TIMEOUT, type='int', 813 | help="The maximum number of seconds to wait before terminating an HTTP request to Matomo." 814 | ) 815 | option_parser.add_option( 816 | '--include-host', action='callback', type='string', callback=functools.partial(self._add_to_array, 'include_host'), 817 | help="Only import logs from the specified host(s)." 818 | ) 819 | option_parser.add_option( 820 | '--exclude-host', action='callback', type='string', callback=functools.partial(self._add_to_array, 'exclude_host'), 821 | help="Only import logs that are not from the specified host(s)." 822 | ) 823 | option_parser.add_option( 824 | '--exclude-older-than', action='callback', type='string', default=None, callback=functools.partial(self._set_date, 'exclude_older_than'), 825 | help="Ignore logs older than the specified date. Exclusive. Date format must be YYYY-MM-DD hh:mm:ss +/-0000. The timezone offset is required." 826 | ) 827 | option_parser.add_option( 828 | '--exclude-newer-than', action='callback', type='string', default=None, callback=functools.partial(self._set_date, 'exclude_newer_than'), 829 | help="Ignore logs newer than the specified date. Exclusive. Date format must be YYYY-MM-DD hh:mm:ss +/-0000. The timezone offset is required." 830 | ) 831 | option_parser.add_option( 832 | '--add-to-date', dest='seconds_to_add_to_date', default=0, type='int', 833 | help="A number of seconds to add to each date value in the log file." 834 | ) 835 | option_parser.add_option( 836 | '--request-suffix', dest='request_suffix', default=None, type='string', help="Extra parameters to append to tracker and API requests." 837 | ) 838 | option_parser.add_option( 839 | '--accept-invalid-ssl-certificate', 840 | dest='accept_invalid_ssl_certificate', action='store_true', 841 | default=False, 842 | help="Do not verify the SSL / TLS certificate when contacting the Matomo server. This is the default when running on Python 2.7.8 or older." 843 | ) 844 | return option_parser 845 | 846 | def _set_date(self, option_attr_name, option, opt_str, value, parser): 847 | try: 848 | (date_str, timezone) = value.rsplit(' ', 1) 849 | except: 850 | fatal_error("Invalid date value '%s'." % value) 851 | 852 | if not re.match('[-+][0-9]{4}', timezone): 853 | fatal_error("Invalid date value '%s': expected valid timzeone like +0100 or -1200, got '%s'" % (value, timezone)) 854 | 855 | timezone = float(timezone) 856 | 857 | date = datetime.datetime.strptime(date_str, '%Y-%m-%d %H:%M:%S') 858 | date -= datetime.timedelta(hours=timezone/100) 859 | 860 | setattr(parser.values, option_attr_name, date) 861 | 862 | def _add_to_array(self, option_attr_name, option, opt_str, value, parser): 863 | if not hasattr(parser.values, option_attr_name) or not getattr(parser.values, option_attr_name): 864 | setattr(parser.values, option_attr_name, []) 865 | getattr(parser.values, option_attr_name).append(value) 866 | 867 | def _set_option_map(self, option_attr_name, option, opt_str, value, parser): 868 | """ 869 | Sets a key-value mapping in a dict that is built from command line options. Options that map 870 | string keys to string values (like --w3c-map-field) can set the callback to a bound partial 871 | of this method to handle the option. 872 | """ 873 | 874 | parts = value.split('=') 875 | 876 | if len(parts) != 2: 877 | fatal_error("Invalid %s option: '%s'" % (opt_str, value)) 878 | 879 | key, value = parts 880 | 881 | if not hasattr(parser.values, option_attr_name): 882 | setattr(parser.values, option_attr_name, {}) 883 | 884 | getattr(parser.values, option_attr_name)[key] = value 885 | 886 | def _parse_args(self, option_parser): 887 | """ 888 | Parse the command line args and create self.options and self.filenames. 889 | """ 890 | self.options, self.filenames = option_parser.parse_args(sys.argv[1:]) 891 | 892 | if self.options.output: 893 | sys.stdout = sys.stderr = open(self.options.output, 'a+', 0) 894 | 895 | if not self.filenames: 896 | print(option_parser.format_help()) 897 | sys.exit(1) 898 | 899 | # Configure logging before calling logging.{debug,info}. 900 | logging.basicConfig( 901 | format='%(asctime)s: [%(levelname)s] %(message)s', 902 | level=logging.DEBUG if self.options.debug >= 1 else logging.INFO, 903 | ) 904 | 905 | self.options.excluded_useragents = set([s.lower() for s in self.options.excluded_useragents]) 906 | 907 | if self.options.exclude_path_from: 908 | paths = [path.strip() for path in open(self.options.exclude_path_from).readlines()] 909 | self.options.excluded_paths.extend(path for path in paths if len(path) > 0) 910 | if self.options.excluded_paths: 911 | self.options.excluded_paths = set(self.options.excluded_paths) 912 | logging.debug('Excluded paths: %s', ' '.join(self.options.excluded_paths)) 913 | 914 | if self.options.include_path_from: 915 | paths = [path.strip() for path in open(self.options.include_path_from).readlines()] 916 | self.options.included_paths.extend(path for path in paths if len(path) > 0) 917 | if self.options.included_paths: 918 | self.options.included_paths = set(self.options.included_paths) 919 | logging.debug('Included paths: %s', ' '.join(self.options.included_paths)) 920 | 921 | if self.options.hostnames: 922 | logging.debug('Accepted hostnames: %s', ', '.join(self.options.hostnames)) 923 | else: 924 | logging.debug('Accepted hostnames: all') 925 | 926 | if self.options.log_format_regex: 927 | self.format = RegexFormat('custom', self.options.log_format_regex, self.options.log_date_format) 928 | elif self.options.log_format_name: 929 | try: 930 | self.format = FORMATS[self.options.log_format_name] 931 | except KeyError: 932 | fatal_error('invalid log format: %s' % self.options.log_format_name) 933 | else: 934 | self.format = None 935 | 936 | if not hasattr(self.options, 'custom_w3c_fields'): 937 | self.options.custom_w3c_fields = {} 938 | elif self.format is not None: 939 | # validate custom field mappings 940 | for custom_name, default_name in self.options.custom_w3c_fields.iteritems(): 941 | if default_name not in type(format).fields: 942 | fatal_error("custom W3C field mapping error: don't know how to parse and use the '%' field" % default_name) 943 | return 944 | 945 | if not hasattr(self.options, 'regex_group_to_visit_cvars_map'): 946 | self.options.regex_group_to_visit_cvars_map = {} 947 | 948 | if not hasattr(self.options, 'regex_group_to_page_cvars_map'): 949 | self.options.regex_group_to_page_cvars_map = {} 950 | 951 | if not hasattr(self.options, 'w3c_field_regexes'): 952 | self.options.w3c_field_regexes = {} 953 | else: 954 | # make sure each custom w3c field regex has a named group 955 | for field_name, field_regex in self.options.w3c_field_regexes.iteritems(): 956 | if '(?P<' not in field_regex: 957 | fatal_error("cannot find named group in custom w3c field regex '%s' for field '%s'" % (field_regex, field_name)) 958 | return 959 | 960 | if not self.options.matomo_url: 961 | fatal_error('no URL given for Matomo') 962 | 963 | if not (self.options.matomo_url.startswith('http://') or self.options.matomo_url.startswith('https://')): 964 | self.options.matomo_url = 'http://' + self.options.matomo_url 965 | logging.debug('Matomo Tracker API URL is: %s', self.options.matomo_url) 966 | 967 | if not self.options.matomo_api_url: 968 | self.options.matomo_api_url = self.options.matomo_url 969 | 970 | if not (self.options.matomo_api_url.startswith('http://') or self.options.matomo_api_url.startswith('https://')): 971 | self.options.matomo_api_url = 'http://' + self.options.matomo_api_url 972 | logging.debug('Matomo Analytics API URL is: %s', self.options.matomo_api_url) 973 | 974 | if self.options.recorders < 1: 975 | self.options.recorders = 1 976 | 977 | download_extensions = DOWNLOAD_EXTENSIONS 978 | if self.options.download_extensions: 979 | download_extensions = set(self.options.download_extensions.split(',')) 980 | 981 | if self.options.extra_download_extensions: 982 | download_extensions.update(self.options.extra_download_extensions.split(',')) 983 | self.options.download_extensions = download_extensions 984 | 985 | if self.options.regex_groups_to_ignore: 986 | self.options.regex_groups_to_ignore = set(self.options.regex_groups_to_ignore.split(',')) 987 | 988 | def __init__(self): 989 | self._parse_args(self._create_parser()) 990 | 991 | def _get_token_auth(self): 992 | """ 993 | If the token auth is not specified in the options, get it from Matomo. 994 | """ 995 | # Get superuser login/password from the options. 996 | logging.debug('No token-auth specified') 997 | 998 | if self.options.login and self.options.password: 999 | matomo_login = self.options.login 1000 | matomo_password = hashlib.md5(self.options.password).hexdigest() 1001 | 1002 | logging.debug('Using credentials: (login = %s, password = %s)', matomo_login, matomo_password) 1003 | try: 1004 | api_result = matomo.call_api('UsersManager.getTokenAuth', 1005 | userLogin=matomo_login, 1006 | md5Password=matomo_password, 1007 | _token_auth='', 1008 | _url=self.options.matomo_api_url, 1009 | ) 1010 | except urllib2.URLError as e: 1011 | fatal_error('error when fetching token_auth from the API: %s' % e) 1012 | 1013 | try: 1014 | return api_result['value'] 1015 | except KeyError: 1016 | # Happens when the credentials are invalid. 1017 | message = api_result.get('message') 1018 | fatal_error( 1019 | 'error fetching authentication token token_auth%s' % ( 1020 | ': %s' % message if message else '') 1021 | ) 1022 | else: 1023 | # Fallback to the given (or default) configuration file, then 1024 | # get the token from the API. 1025 | logging.debug( 1026 | 'No credentials specified, reading them from "%s"', 1027 | self.options.config_file, 1028 | ) 1029 | config_file = ConfigParser.RawConfigParser() 1030 | success = len(config_file.read(self.options.config_file)) > 0 1031 | if not success: 1032 | fatal_error( 1033 | "the configuration file" + self.options.config_file + " could not be read. Please check permission. This file must be readable by the user running this script to get the authentication token" 1034 | ) 1035 | 1036 | updatetokenfile = os.path.abspath( 1037 | os.path.join(os.path.dirname(__file__), 1038 | '../../misc/cron/updatetoken.php'), 1039 | ) 1040 | 1041 | phpBinary = 'php' 1042 | 1043 | is_windows = sys.platform.startswith('win') 1044 | if is_windows: 1045 | try: 1046 | processWin = subprocess.Popen('where php.exe', stdout=subprocess.PIPE, stderr=subprocess.PIPE) 1047 | [stdout, stderr] = processWin.communicate() 1048 | if processWin.returncode == 0: 1049 | phpBinary = stdout.strip() 1050 | else: 1051 | fatal_error("We couldn't detect PHP. It might help to add your php.exe to the path or alternatively run the importer using the --login and --password option") 1052 | except: 1053 | fatal_error("We couldn't detect PHP. You can run the importer using the --login and --password option to fix this issue") 1054 | 1055 | command = [phpBinary, updatetokenfile] 1056 | if self.options.enable_testmode: 1057 | command.append('--testmode') 1058 | 1059 | hostname = urlparse.urlparse( self.options.matomo_url ).hostname 1060 | command.append('--piwik-domain=' + hostname ) 1061 | 1062 | command = subprocess.list2cmdline(command) 1063 | 1064 | # logging.debug(command); 1065 | 1066 | process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True) 1067 | [stdout, stderr] = process.communicate() 1068 | if process.returncode != 0: 1069 | fatal_error("`" + command + "` failed with error: " + stderr + ".\nReponse code was: " + str(process.returncode) + ". You can alternatively run the importer using the --login and --password option") 1070 | 1071 | filename = stdout 1072 | credentials = open(filename, 'r').readline() 1073 | credentials = credentials.split('\t') 1074 | return credentials[1] 1075 | 1076 | def get_resolver(self): 1077 | if self.options.site_id: 1078 | logging.debug('Resolver: static') 1079 | return StaticResolver(self.options.site_id) 1080 | else: 1081 | logging.debug('Resolver: dynamic') 1082 | return DynamicResolver() 1083 | 1084 | def init_token_auth(self): 1085 | if not self.options.matomo_token_auth: 1086 | try: 1087 | self.options.matomo_token_auth = self._get_token_auth() 1088 | except Matomo.Error as e: 1089 | fatal_error(e) 1090 | logging.debug('Authentication token token_auth is: %s', self.options.matomo_token_auth) 1091 | 1092 | 1093 | class Statistics(object): 1094 | """ 1095 | Store statistics about parsed logs and recorded entries. 1096 | Can optionally print statistics on standard output every second. 1097 | """ 1098 | 1099 | class Counter(object): 1100 | """ 1101 | Simple integers cannot be used by multithreaded programs. See: 1102 | http://stackoverflow.com/questions/6320107/are-python-ints-thread-safe 1103 | """ 1104 | def __init__(self): 1105 | # itertools.count's implementation in C does not release the GIL and 1106 | # therefore is thread-safe. 1107 | self.counter = itertools.count(1) 1108 | self.value = 0 1109 | 1110 | def increment(self): 1111 | self.value = self.counter.next() 1112 | 1113 | def advance(self, n): 1114 | for i in range(n): 1115 | self.increment() 1116 | 1117 | def __str__(self): 1118 | return str(int(self.value)) 1119 | 1120 | def __init__(self): 1121 | self.time_start = None 1122 | self.time_stop = None 1123 | 1124 | self.matomo_sites = set() # sites ID 1125 | self.matomo_sites_created = [] # (hostname, site ID) 1126 | self.matomo_sites_ignored = set() # hostname 1127 | 1128 | self.count_lines_parsed = self.Counter() 1129 | self.count_lines_recorded = self.Counter() 1130 | 1131 | # requests that the Matomo tracker considered invalid (or failed to track) 1132 | self.invalid_lines = [] 1133 | 1134 | # Do not match the regexp. 1135 | self.count_lines_invalid = self.Counter() 1136 | # Were filtered out. 1137 | self.count_lines_filtered = self.Counter() 1138 | # No site ID found by the resolver. 1139 | self.count_lines_no_site = self.Counter() 1140 | # Hostname filtered by config.options.hostnames 1141 | self.count_lines_hostname_skipped = self.Counter() 1142 | # Static files. 1143 | self.count_lines_static = self.Counter() 1144 | # Ignored user-agents. 1145 | self.count_lines_skipped_user_agent = self.Counter() 1146 | # Ignored HTTP erors. 1147 | self.count_lines_skipped_http_errors = self.Counter() 1148 | # Ignored HTTP redirects. 1149 | self.count_lines_skipped_http_redirects = self.Counter() 1150 | # Downloads 1151 | self.count_lines_downloads = self.Counter() 1152 | # Ignored downloads when --download-extensions is used 1153 | self.count_lines_skipped_downloads = self.Counter() 1154 | 1155 | # Misc 1156 | self.dates_recorded = set() 1157 | self.monitor_stop = False 1158 | 1159 | def set_time_start(self): 1160 | self.time_start = time.time() 1161 | 1162 | def set_time_stop(self): 1163 | self.time_stop = time.time() 1164 | 1165 | def _compute_speed(self, value, start, end): 1166 | delta_time = end - start 1167 | if value == 0: 1168 | return 0 1169 | if delta_time == 0: 1170 | return 'very high!' 1171 | else: 1172 | return value / delta_time 1173 | 1174 | def _round_value(self, value, base=100): 1175 | return round(value * base) / base 1176 | 1177 | def _indent_text(self, lines, level=1): 1178 | """ 1179 | Return an indented text. 'lines' can be a list of lines or a single 1180 | line (as a string). One level of indentation is 4 spaces. 1181 | """ 1182 | prefix = ' ' * (4 * level) 1183 | if isinstance(lines, basestring): 1184 | return prefix + lines 1185 | else: 1186 | return '\n'.join( 1187 | prefix + line 1188 | for line in lines 1189 | ) 1190 | 1191 | def print_summary(self): 1192 | invalid_lines_summary = '' 1193 | if self.invalid_lines: 1194 | invalid_lines_summary = '''Invalid log lines 1195 | ----------------- 1196 | 1197 | The following lines were not tracked by Matomo, either due to a malformed tracker request or error in the tracker: 1198 | 1199 | %s 1200 | 1201 | ''' % textwrap.fill(", ".join(self.invalid_lines), 80) 1202 | 1203 | print(''' 1204 | %(invalid_lines)sLogs import summary 1205 | ------------------- 1206 | 1207 | %(count_lines_recorded)d requests imported successfully 1208 | %(count_lines_downloads)d requests were downloads 1209 | %(total_lines_ignored)d requests ignored: 1210 | %(count_lines_skipped_http_errors)d HTTP errors 1211 | %(count_lines_skipped_http_redirects)d HTTP redirects 1212 | %(count_lines_invalid)d invalid log lines 1213 | %(count_lines_filtered)d filtered log lines 1214 | %(count_lines_no_site)d requests did not match any known site 1215 | %(count_lines_hostname_skipped)d requests did not match any --hostname 1216 | %(count_lines_skipped_user_agent)d requests done by bots, search engines... 1217 | %(count_lines_static)d requests to static resources (css, js, images, ico, ttf...) 1218 | %(count_lines_skipped_downloads)d requests to file downloads did not match any --download-extensions 1219 | 1220 | Website import summary 1221 | ---------------------- 1222 | 1223 | %(count_lines_recorded)d requests imported to %(total_sites)d sites 1224 | %(total_sites_existing)d sites already existed 1225 | %(total_sites_created)d sites were created: 1226 | %(sites_created)s 1227 | %(total_sites_ignored)d distinct hostnames did not match any existing site: 1228 | %(sites_ignored)s 1229 | %(sites_ignored_tips)s 1230 | 1231 | Performance summary 1232 | ------------------- 1233 | 1234 | Total time: %(total_time)d seconds 1235 | Requests imported per second: %(speed_recording)s requests per second 1236 | 1237 | Processing your log data 1238 | ------------------------ 1239 | 1240 | In order for your logs to be processed by Matomo, you may need to run the following command: 1241 | ./console core:archive --force-all-websites --force-all-periods=315576000 --force-date-last-n=1000 --url='%(url)s' 1242 | ''' % { 1243 | 1244 | 'count_lines_recorded': self.count_lines_recorded.value, 1245 | 'count_lines_downloads': self.count_lines_downloads.value, 1246 | 'total_lines_ignored': sum([ 1247 | self.count_lines_invalid.value, 1248 | self.count_lines_filtered.value, 1249 | self.count_lines_skipped_user_agent.value, 1250 | self.count_lines_skipped_http_errors.value, 1251 | self.count_lines_skipped_http_redirects.value, 1252 | self.count_lines_static.value, 1253 | self.count_lines_skipped_downloads.value, 1254 | self.count_lines_no_site.value, 1255 | self.count_lines_hostname_skipped.value, 1256 | ]), 1257 | 'count_lines_invalid': self.count_lines_invalid.value, 1258 | 'count_lines_filtered': self.count_lines_filtered.value, 1259 | 'count_lines_skipped_user_agent': self.count_lines_skipped_user_agent.value, 1260 | 'count_lines_skipped_http_errors': self.count_lines_skipped_http_errors.value, 1261 | 'count_lines_skipped_http_redirects': self.count_lines_skipped_http_redirects.value, 1262 | 'count_lines_static': self.count_lines_static.value, 1263 | 'count_lines_skipped_downloads': self.count_lines_skipped_downloads.value, 1264 | 'count_lines_no_site': self.count_lines_no_site.value, 1265 | 'count_lines_hostname_skipped': self.count_lines_hostname_skipped.value, 1266 | 'total_sites': len(self.matomo_sites), 1267 | 'total_sites_existing': len(self.matomo_sites - set(site_id for hostname, site_id in self.matomo_sites_created)), 1268 | 'total_sites_created': len(self.matomo_sites_created), 1269 | 'sites_created': self._indent_text( 1270 | ['%s (ID: %d)' % (hostname, site_id) for hostname, site_id in self.matomo_sites_created], 1271 | level=3, 1272 | ), 1273 | 'total_sites_ignored': len(self.matomo_sites_ignored), 1274 | 'sites_ignored': self._indent_text( 1275 | self.matomo_sites_ignored, level=3, 1276 | ), 1277 | 'sites_ignored_tips': ''' 1278 | TIPs: 1279 | - if one of these hosts is an alias host for one of the websites 1280 | in Matomo, you can add this host as an "Alias URL" in Settings > Websites. 1281 | - use --add-sites-new-hosts if you wish to automatically create 1282 | one website for each of these hosts in Matomo rather than discarding 1283 | these requests. 1284 | - use --idsite-fallback to force all these log lines with a new hostname 1285 | to be recorded in a specific idsite (for example for troubleshooting/visualizing the data) 1286 | - use --idsite to force all lines in the specified log files 1287 | to be all recorded in the specified idsite 1288 | - or you can also manually create a new Website in Matomo with the URL set to this hostname 1289 | ''' if self.matomo_sites_ignored else '', 1290 | 'total_time': self.time_stop - self.time_start, 1291 | 'speed_recording': self._round_value(self._compute_speed( 1292 | self.count_lines_recorded.value, 1293 | self.time_start, self.time_stop, 1294 | )), 1295 | 'url': config.options.matomo_api_url, 1296 | 'invalid_lines': invalid_lines_summary 1297 | }) 1298 | 1299 | ## 1300 | ## The monitor is a thread that prints a short summary each second. 1301 | ## 1302 | 1303 | def _monitor(self): 1304 | latest_total_recorded = 0 1305 | while not self.monitor_stop: 1306 | current_total = stats.count_lines_recorded.value 1307 | time_elapsed = time.time() - self.time_start 1308 | print('%d lines parsed, %d lines recorded, %d records/sec (avg), %d records/sec (current)' % ( 1309 | stats.count_lines_parsed.value, 1310 | current_total, 1311 | current_total / time_elapsed if time_elapsed != 0 else 0, 1312 | (current_total - latest_total_recorded) / config.options.show_progress_delay, 1313 | )) 1314 | latest_total_recorded = current_total 1315 | time.sleep(config.options.show_progress_delay) 1316 | 1317 | def start_monitor(self): 1318 | t = threading.Thread(target=self._monitor) 1319 | t.daemon = True 1320 | t.start() 1321 | 1322 | def stop_monitor(self): 1323 | self.monitor_stop = True 1324 | 1325 | class Matomo(object): 1326 | """ 1327 | Make requests to Matomo. 1328 | """ 1329 | 1330 | class Error(Exception): 1331 | 1332 | def __init__(self, message, code = None): 1333 | super(Exception, self).__init__(message) 1334 | 1335 | self.code = code 1336 | 1337 | class RedirectHandlerWithLogging(urllib2.HTTPRedirectHandler): 1338 | """ 1339 | Special implementation of HTTPRedirectHandler that logs redirects in debug mode 1340 | to help users debug system issues. 1341 | """ 1342 | 1343 | def redirect_request(self, req, fp, code, msg, hdrs, newurl): 1344 | logging.debug("Request redirected (code: %s) to '%s'" % (code, newurl)) 1345 | 1346 | return urllib2.HTTPRedirectHandler.redirect_request(self, req, fp, code, msg, hdrs, newurl) 1347 | 1348 | @staticmethod 1349 | def _call(path, args, headers=None, url=None, data=None): 1350 | """ 1351 | Make a request to the Matomo site. It is up to the caller to format 1352 | arguments, to embed authentication, etc. 1353 | """ 1354 | if url is None: 1355 | url = config.options.matomo_url 1356 | headers = headers or {} 1357 | 1358 | if data is None: 1359 | # If Content-Type isn't defined, PHP do not parse the request's body. 1360 | headers['Content-type'] = 'application/x-www-form-urlencoded' 1361 | data = urllib.urlencode(args) 1362 | elif not isinstance(data, basestring) and headers['Content-type'] == 'application/json': 1363 | data = json.dumps(data) 1364 | 1365 | if args: 1366 | path = path + '?' + urllib.urlencode(args) 1367 | 1368 | if config.options.request_suffix: 1369 | path = path + ('&' if '?' in path else '?') + config.options.request_suffix 1370 | 1371 | headers['User-Agent'] = 'Matomo/LogImport' 1372 | 1373 | try: 1374 | timeout = config.options.request_timeout 1375 | except: 1376 | timeout = None # the config global object may not be created at this point 1377 | 1378 | request = urllib2.Request(url + path, data, headers) 1379 | 1380 | # Handle basic auth if auth_user set 1381 | try: 1382 | auth_user = config.options.auth_user 1383 | auth_password = config.options.auth_password 1384 | except: 1385 | auth_user = None 1386 | auth_password = None 1387 | 1388 | if auth_user is not None: 1389 | base64string = base64.encodestring('%s:%s' % (auth_user, auth_password)).replace('\n', '') 1390 | request.add_header("Authorization", "Basic %s" % base64string) 1391 | 1392 | # Use non-default SSL context if invalid certificates shall be 1393 | # accepted. 1394 | if config.options.accept_invalid_ssl_certificate and \ 1395 | sys.version_info >= (2, 7, 9): 1396 | ssl_context = ssl.create_default_context() 1397 | ssl_context.check_hostname = False 1398 | ssl_context.verify_mode = ssl.CERT_NONE 1399 | https_handler_args = {'context': ssl_context} 1400 | else: 1401 | https_handler_args = {} 1402 | opener = urllib2.build_opener( 1403 | Matomo.RedirectHandlerWithLogging(), 1404 | urllib2.HTTPSHandler(**https_handler_args)) 1405 | response = opener.open(request, timeout = timeout) 1406 | result = response.read() 1407 | response.close() 1408 | return result 1409 | 1410 | @staticmethod 1411 | def _call_api(method, **kwargs): 1412 | """ 1413 | Make a request to the Matomo API taking care of authentication, body 1414 | formatting, etc. 1415 | """ 1416 | args = { 1417 | 'module' : 'API', 1418 | 'format' : 'json2', 1419 | 'method' : method, 1420 | 'filter_limit' : '-1', 1421 | } 1422 | # token_auth, by default, is taken from config. 1423 | token_auth = kwargs.pop('_token_auth', None) 1424 | if token_auth is None: 1425 | token_auth = config.options.matomo_token_auth 1426 | if token_auth: 1427 | args['token_auth'] = token_auth 1428 | 1429 | url = kwargs.pop('_url', None) 1430 | if url is None: 1431 | url = config.options.matomo_api_url 1432 | 1433 | 1434 | if kwargs: 1435 | args.update(kwargs) 1436 | 1437 | # Convert lists into appropriate format. 1438 | # See: http://developer.matomo.org/api-reference/reporting-api#passing-an-array-of-data-as-a-parameter 1439 | # Warning: we have to pass the parameters in order: foo[0], foo[1], foo[2] 1440 | # and not foo[1], foo[0], foo[2] (it will break Matomo otherwise.) 1441 | final_args = [] 1442 | for key, value in args.iteritems(): 1443 | if isinstance(value, (list, tuple)): 1444 | for index, obj in enumerate(value): 1445 | final_args.append(('%s[%d]' % (key, index), obj)) 1446 | else: 1447 | final_args.append((key, value)) 1448 | 1449 | 1450 | # logging.debug('%s' % final_args) 1451 | # logging.debug('%s' % url) 1452 | 1453 | res = Matomo._call('/', final_args, url=url) 1454 | 1455 | 1456 | try: 1457 | return json.loads(res) 1458 | except ValueError: 1459 | raise urllib2.URLError('Matomo returned an invalid response: ' + res) 1460 | 1461 | @staticmethod 1462 | def _call_wrapper(func, expected_response, on_failure, *args, **kwargs): 1463 | """ 1464 | Try to make requests to Matomo at most MATOMO_FAILURE_MAX_RETRY times. 1465 | """ 1466 | errors = 0 1467 | while True: 1468 | try: 1469 | response = func(*args, **kwargs) 1470 | if expected_response is not None and response != expected_response: 1471 | if on_failure is not None: 1472 | error_message = on_failure(response, kwargs.get('data')) 1473 | else: 1474 | error_message = "didn't receive the expected response. Response was %s " % response 1475 | 1476 | raise urllib2.URLError(error_message) 1477 | return response 1478 | except (urllib2.URLError, httplib.HTTPException, ValueError, socket.timeout) as e: 1479 | logging.info('Error when connecting to Matomo: %s', e) 1480 | 1481 | code = None 1482 | if isinstance(e, urllib2.HTTPError): 1483 | # See Python issue 13211. 1484 | message = 'HTTP Error %s %s' % (e.code, e.msg) 1485 | code = e.code 1486 | elif isinstance(e, urllib2.URLError): 1487 | message = e.reason 1488 | else: 1489 | message = str(e) 1490 | 1491 | # decorate message w/ HTTP response, if it can be retrieved 1492 | if hasattr(e, 'read'): 1493 | message = message + ", response: " + e.read() 1494 | 1495 | try: 1496 | delay_after_failure = config.options.delay_after_failure 1497 | max_attempts = config.options.max_attempts 1498 | except NameError: 1499 | delay_after_failure = MATOMO_DEFAULT_DELAY_AFTER_FAILURE 1500 | max_attempts = MATOMO_DEFAULT_MAX_ATTEMPTS 1501 | 1502 | errors += 1 1503 | if errors == max_attempts: 1504 | logging.info("Max number of attempts reached, server is unreachable!") 1505 | 1506 | raise Matomo.Error(message, code) 1507 | else: 1508 | logging.info("Retrying request, attempt number %d" % (errors + 1)) 1509 | 1510 | time.sleep(delay_after_failure) 1511 | 1512 | @classmethod 1513 | def call(cls, path, args, expected_content=None, headers=None, data=None, on_failure=None): 1514 | return cls._call_wrapper(cls._call, expected_content, on_failure, path, args, headers, 1515 | data=data) 1516 | 1517 | @classmethod 1518 | def call_api(cls, method, **kwargs): 1519 | return cls._call_wrapper(cls._call_api, None, None, method, **kwargs) 1520 | 1521 | ## 1522 | ## Resolvers. 1523 | ## 1524 | ## A resolver is a class that turns a hostname into a Matomo site ID. 1525 | ## 1526 | 1527 | class StaticResolver(object): 1528 | """ 1529 | Always return the same site ID, specified in the configuration. 1530 | """ 1531 | 1532 | def __init__(self, site_id): 1533 | self.site_id = site_id 1534 | # Go get the main URL 1535 | site = matomo.call_api( 1536 | 'SitesManager.getSiteFromId', idSite=self.site_id 1537 | ) 1538 | if site.get('result') == 'error': 1539 | fatal_error( 1540 | "cannot get the main URL of this site: %s" % site.get('message') 1541 | ) 1542 | self._main_url = site['main_url'] 1543 | stats.matomo_sites.add(self.site_id) 1544 | 1545 | def resolve(self, hit): 1546 | return (self.site_id, self._main_url) 1547 | 1548 | def check_format(self, format): 1549 | pass 1550 | 1551 | class DynamicResolver(object): 1552 | """ 1553 | Use Matomo API to determine the site ID. 1554 | """ 1555 | 1556 | _add_site_lock = threading.Lock() 1557 | 1558 | def __init__(self): 1559 | self._cache = {} 1560 | if config.options.replay_tracking: 1561 | # get existing sites 1562 | self._cache['sites'] = matomo.call_api('SitesManager.getAllSites') 1563 | 1564 | def _get_site_id_from_hit_host(self, hit): 1565 | return matomo.call_api( 1566 | 'SitesManager.getSitesIdFromSiteUrl', 1567 | url=hit.host, 1568 | ) 1569 | 1570 | def _add_site(self, hit): 1571 | main_url = 'http://' + hit.host 1572 | DynamicResolver._add_site_lock.acquire() 1573 | 1574 | try: 1575 | # After we obtain the lock, make sure the site hasn't already been created. 1576 | res = self._get_site_id_from_hit_host(hit) 1577 | if res: 1578 | return res[0]['idsite'] 1579 | 1580 | # The site doesn't exist. 1581 | logging.debug('No Matomo site found for the hostname: %s', hit.host) 1582 | if config.options.site_id_fallback is not None: 1583 | logging.debug('Using default site for hostname: %s', hit.host) 1584 | return config.options.site_id_fallback 1585 | elif config.options.add_sites_new_hosts: 1586 | if config.options.dry_run: 1587 | # Let's just return a fake ID. 1588 | return 0 1589 | logging.debug('Creating a Matomo site for hostname %s', hit.host) 1590 | result = matomo.call_api( 1591 | 'SitesManager.addSite', 1592 | siteName=hit.host, 1593 | urls=[main_url], 1594 | ) 1595 | if result.get('result') == 'error': 1596 | logging.error("Couldn't create a Matomo site for host %s: %s", 1597 | hit.host, result.get('message'), 1598 | ) 1599 | return None 1600 | else: 1601 | site_id = result['value'] 1602 | stats.matomo_sites_created.append((hit.host, site_id)) 1603 | return site_id 1604 | else: 1605 | # The site doesn't exist, we don't want to create new sites and 1606 | # there's no default site ID. We thus have to ignore this hit. 1607 | return None 1608 | finally: 1609 | DynamicResolver._add_site_lock.release() 1610 | 1611 | def _resolve(self, hit): 1612 | res = self._get_site_id_from_hit_host(hit) 1613 | if res: 1614 | # The site already exists. 1615 | site_id = res[0]['idsite'] 1616 | else: 1617 | site_id = self._add_site(hit) 1618 | if site_id is not None: 1619 | stats.matomo_sites.add(site_id) 1620 | return site_id 1621 | 1622 | def _resolve_when_replay_tracking(self, hit): 1623 | """ 1624 | If parsed site ID found in the _cache['sites'] return site ID and main_url, 1625 | otherwise return (None, None) tuple. 1626 | """ 1627 | site_id = hit.args['idsite'] 1628 | if site_id in self._cache['sites']: 1629 | stats.matomo_sites.add(site_id) 1630 | return (site_id, self._cache['sites'][site_id]['main_url']) 1631 | else: 1632 | return (None, None) 1633 | 1634 | def _resolve_by_host(self, hit): 1635 | """ 1636 | Returns the site ID and site URL for a hit based on the hostname. 1637 | """ 1638 | try: 1639 | site_id = self._cache[hit.host] 1640 | except KeyError: 1641 | logging.debug( 1642 | 'Site ID for hostname %s not in cache', hit.host 1643 | ) 1644 | site_id = self._resolve(hit) 1645 | logging.debug('Site ID for hostname %s: %s', hit.host, site_id) 1646 | self._cache[hit.host] = site_id 1647 | return (site_id, 'http://' + hit.host) 1648 | 1649 | def resolve(self, hit): 1650 | """ 1651 | Return the site ID from the cache if found, otherwise call _resolve. 1652 | If replay_tracking option is enabled, call _resolve_when_replay_tracking. 1653 | """ 1654 | if config.options.replay_tracking: 1655 | # We only consider requests with piwik.php which don't need host to be imported 1656 | return self._resolve_when_replay_tracking(hit) 1657 | else: 1658 | # Workaround for empty Host bug issue #126 1659 | if hit.host.strip() == '': 1660 | hit.host = 'no-hostname-found-in-log' 1661 | return self._resolve_by_host(hit) 1662 | 1663 | def check_format(self, format): 1664 | if config.options.replay_tracking: 1665 | pass 1666 | elif format.regex is not None and 'host' not in format.regex.groupindex and not config.options.log_hostname: 1667 | fatal_error( 1668 | "the selected log format doesn't include the hostname: you must " 1669 | "specify the Matomo site ID with the --idsite argument" 1670 | ) 1671 | 1672 | class Recorder(object): 1673 | """ 1674 | A Recorder fetches hits from the Queue and inserts them into Matomo using 1675 | the API. 1676 | """ 1677 | 1678 | recorders = [] 1679 | 1680 | def __init__(self): 1681 | self.queue = Queue.Queue(maxsize=2) 1682 | 1683 | # if bulk tracking disabled, make sure we can store hits outside of the Queue 1684 | if not config.options.use_bulk_tracking: 1685 | self.unrecorded_hits = [] 1686 | 1687 | @classmethod 1688 | def launch(cls, recorder_count): 1689 | """ 1690 | Launch a bunch of Recorder objects in a separate thread. 1691 | """ 1692 | for i in xrange(recorder_count): 1693 | recorder = Recorder() 1694 | cls.recorders.append(recorder) 1695 | 1696 | run = recorder._run_bulk if config.options.use_bulk_tracking else recorder._run_single 1697 | t = threading.Thread(target=run) 1698 | 1699 | t.daemon = True 1700 | t.start() 1701 | logging.debug('Launched recorder') 1702 | 1703 | @classmethod 1704 | def add_hits(cls, all_hits): 1705 | """ 1706 | Add a set of hits to the recorders queue. 1707 | """ 1708 | # Organize hits so that one client IP will always use the same queue. 1709 | # We have to do this so visits from the same IP will be added in the right order. 1710 | hits_by_client = [[] for r in cls.recorders] 1711 | for hit in all_hits: 1712 | hits_by_client[hit.get_visitor_id_hash() % len(cls.recorders)].append(hit) 1713 | 1714 | for i, recorder in enumerate(cls.recorders): 1715 | recorder.queue.put(hits_by_client[i]) 1716 | 1717 | @classmethod 1718 | def wait_empty(cls): 1719 | """ 1720 | Wait until all recorders have an empty queue. 1721 | """ 1722 | for recorder in cls.recorders: 1723 | recorder._wait_empty() 1724 | 1725 | def _run_bulk(self): 1726 | while True: 1727 | try: 1728 | hits = self.queue.get() 1729 | except: 1730 | # TODO: we should log something here, however when this happens, logging.etc will throw 1731 | return 1732 | 1733 | if len(hits) > 0: 1734 | try: 1735 | self._record_hits(hits) 1736 | except Matomo.Error as e: 1737 | fatal_error(e, hits[0].filename, hits[0].lineno) # approximate location of error 1738 | self.queue.task_done() 1739 | 1740 | def _run_single(self): 1741 | while True: 1742 | if config.options.force_one_action_interval != False: 1743 | time.sleep(config.options.force_one_action_interval) 1744 | 1745 | if len(self.unrecorded_hits) > 0: 1746 | hit = self.unrecorded_hits.pop(0) 1747 | 1748 | try: 1749 | self._record_hits([hit]) 1750 | except Matomo.Error as e: 1751 | fatal_error(e, hit.filename, hit.lineno) 1752 | else: 1753 | self.unrecorded_hits = self.queue.get() 1754 | self.queue.task_done() 1755 | 1756 | def _wait_empty(self): 1757 | """ 1758 | Wait until the queue is empty. 1759 | """ 1760 | while True: 1761 | if self.queue.empty(): 1762 | # We still have to wait for the last queue item being processed 1763 | # (queue.empty() returns True before queue.task_done() is 1764 | # called). 1765 | self.queue.join() 1766 | return 1767 | time.sleep(1) 1768 | 1769 | def date_to_matomo(self, date): 1770 | date, time = date.isoformat(sep=' ').split() 1771 | return '%s %s' % (date, time.replace('-', ':')) 1772 | 1773 | def _get_hit_args(self, hit): 1774 | """ 1775 | Returns the args used in tracking a hit, without the token_auth. 1776 | """ 1777 | site_id, main_url = resolver.resolve(hit) 1778 | if site_id is None: 1779 | # This hit doesn't match any known Matomo site. 1780 | if config.options.replay_tracking: 1781 | stats.matomo_sites_ignored.add('unrecognized site ID %s' % hit.args.get('idsite')) 1782 | else: 1783 | stats.matomo_sites_ignored.add(hit.host) 1784 | stats.count_lines_no_site.increment() 1785 | return 1786 | 1787 | stats.dates_recorded.add(hit.date.date()) 1788 | 1789 | path = hit.path 1790 | if hit.query_string and not config.options.strip_query_string: 1791 | path += config.options.query_string_delimiter + hit.query_string 1792 | 1793 | # only prepend main url / host if it's a path 1794 | url_prefix = self._get_host_with_protocol(hit.host, main_url) if hasattr(hit, 'host') else main_url 1795 | url = (url_prefix if path.startswith('/') else '') + path[:1024] 1796 | 1797 | # handle custom variables before generating args dict 1798 | if config.options.enable_bots: 1799 | if hit.is_robot: 1800 | hit.add_visit_custom_var("Bot", hit.user_agent) 1801 | else: 1802 | hit.add_visit_custom_var("Not-Bot", hit.user_agent) 1803 | 1804 | hit.add_page_custom_var("HTTP-code", hit.status) 1805 | 1806 | args = { 1807 | 'rec': '1', 1808 | 'apiv': '1', 1809 | 'url': url.encode('utf8'), 1810 | 'urlref': hit.referrer[:1024].encode('utf8'), 1811 | 'cip': hit.ip, 1812 | 'cdt': self.date_to_matomo(hit.date), 1813 | 'idsite': site_id, 1814 | 'dp': '0' if config.options.reverse_dns else '1', 1815 | 'ua': hit.user_agent.encode('utf8') 1816 | } 1817 | 1818 | if config.options.replay_tracking: 1819 | # prevent request to be force recorded when option replay-tracking 1820 | args['rec'] = '0' 1821 | 1822 | # idsite is already determined by resolver 1823 | if 'idsite' in hit.args: 1824 | del hit.args['idsite'] 1825 | 1826 | args.update(hit.args) 1827 | 1828 | if hit.is_download: 1829 | args['download'] = args['url'] 1830 | 1831 | if config.options.enable_bots: 1832 | args['bots'] = '1' 1833 | 1834 | if hit.is_error or hit.is_redirect: 1835 | args['action_name'] = '%s%sURL = %s%s' % ( 1836 | hit.status, 1837 | config.options.title_category_delimiter, 1838 | urllib.quote(args['url'], ''), 1839 | ("%sFrom = %s" % ( 1840 | config.options.title_category_delimiter, 1841 | urllib.quote(args['urlref'], '') 1842 | ) if args['urlref'] != '' else '') 1843 | ) 1844 | 1845 | if hit.generation_time_milli > 0: 1846 | args['gt_ms'] = int(hit.generation_time_milli) 1847 | 1848 | if hit.event_category and hit.event_action: 1849 | args['e_c'] = hit.event_category 1850 | args['e_a'] = hit.event_action 1851 | 1852 | if hit.event_name: 1853 | args['e_n'] = hit.event_name 1854 | 1855 | if hit.length: 1856 | args['bw_bytes'] = hit.length 1857 | 1858 | # convert custom variable args to JSON 1859 | if 'cvar' in args and not isinstance(args['cvar'], basestring): 1860 | args['cvar'] = json.dumps(args['cvar']) 1861 | 1862 | if '_cvar' in args and not isinstance(args['_cvar'], basestring): 1863 | args['_cvar'] = json.dumps(args['_cvar']) 1864 | 1865 | return args 1866 | 1867 | def _get_host_with_protocol(self, host, main_url): 1868 | if '://' not in host: 1869 | parts = urlparse.urlparse(main_url) 1870 | host = parts.scheme + '://' + host 1871 | return host 1872 | 1873 | def _record_hits(self, hits): 1874 | """ 1875 | Inserts several hits into Matomo. 1876 | """ 1877 | if not config.options.dry_run: 1878 | data = { 1879 | 'token_auth': config.options.matomo_token_auth, 1880 | 'requests': [self._get_hit_args(hit) for hit in hits] 1881 | } 1882 | try: 1883 | args = {} 1884 | 1885 | if config.options.debug_tracker: 1886 | args['debug'] = '1' 1887 | 1888 | response = matomo.call( 1889 | '/piwik.php', args=args, 1890 | expected_content=None, 1891 | headers={'Content-type': 'application/json'}, 1892 | data=data, 1893 | on_failure=self._on_tracking_failure 1894 | ) 1895 | 1896 | if config.options.debug_tracker: 1897 | logging.debug('tracker response:\n%s' % response) 1898 | 1899 | # check for invalid requests 1900 | try: 1901 | response = json.loads(response) 1902 | except: 1903 | logging.info("bulk tracking returned invalid JSON") 1904 | 1905 | # don't display the tracker response if we're debugging the tracker. 1906 | # debug tracker output will always break the normal JSON output. 1907 | if not config.options.debug_tracker: 1908 | logging.info("tracker response:\n%s" % response) 1909 | 1910 | response = {} 1911 | 1912 | if ('invalid_indices' in response and isinstance(response['invalid_indices'], list) and 1913 | response['invalid_indices']): 1914 | invalid_count = len(response['invalid_indices']) 1915 | 1916 | invalid_lines = [str(hits[index].lineno) for index in response['invalid_indices']] 1917 | invalid_lines_str = ", ".join(invalid_lines) 1918 | 1919 | stats.invalid_lines.extend(invalid_lines) 1920 | 1921 | logging.info("The Matomo tracker identified %s invalid requests on lines: %s" % (invalid_count, invalid_lines_str)) 1922 | elif 'invalid' in response and response['invalid'] > 0: 1923 | logging.info("The Matomo tracker identified %s invalid requests." % response['invalid']) 1924 | except Matomo.Error as e: 1925 | # if the server returned 400 code, BulkTracking may not be enabled 1926 | if e.code == 400: 1927 | fatal_error("Server returned status 400 (Bad Request).\nIs the BulkTracking plugin disabled?", hits[0].filename, hits[0].lineno) 1928 | 1929 | raise 1930 | 1931 | stats.count_lines_recorded.advance(len(hits)) 1932 | 1933 | def _is_json(self, result): 1934 | try: 1935 | json.loads(result) 1936 | return True 1937 | except ValueError as e: 1938 | return False 1939 | 1940 | def _on_tracking_failure(self, response, data): 1941 | """ 1942 | Removes the successfully tracked hits from the request payload so 1943 | they are not logged twice. 1944 | """ 1945 | try: 1946 | response = json.loads(response) 1947 | except: 1948 | # the response should be in JSON, but in case it can't be parsed just try another attempt 1949 | logging.debug("cannot parse tracker response, should be valid JSON") 1950 | return response 1951 | 1952 | # remove the successfully tracked hits from payload 1953 | tracked = response['tracked'] 1954 | data['requests'] = data['requests'][tracked:] 1955 | 1956 | return response['message'] 1957 | 1958 | class Hit(object): 1959 | """ 1960 | It's a simple container. 1961 | """ 1962 | def __init__(self, **kwargs): 1963 | for key, value in kwargs.iteritems(): 1964 | setattr(self, key, value) 1965 | super(Hit, self).__init__() 1966 | 1967 | if config.options.force_lowercase_path: 1968 | self.full_path = self.full_path.lower() 1969 | 1970 | def get_visitor_id_hash(self): 1971 | visitor_id = self.ip 1972 | 1973 | if config.options.replay_tracking: 1974 | for param_name_to_use in ['uid', 'cid', '_id', 'cip']: 1975 | if param_name_to_use in self.args: 1976 | visitor_id = self.args[param_name_to_use] 1977 | break 1978 | 1979 | return abs(hash(visitor_id)) 1980 | 1981 | def add_page_custom_var(self, key, value): 1982 | """ 1983 | Adds a page custom variable to this Hit. 1984 | """ 1985 | self._add_custom_var(key, value, 'cvar') 1986 | 1987 | def add_visit_custom_var(self, key, value): 1988 | """ 1989 | Adds a visit custom variable to this Hit. 1990 | """ 1991 | self._add_custom_var(key, value, '_cvar') 1992 | 1993 | def _add_custom_var(self, key, value, api_arg_name): 1994 | if api_arg_name not in self.args: 1995 | self.args[api_arg_name] = {} 1996 | 1997 | if isinstance(self.args[api_arg_name], basestring): 1998 | logging.debug("Ignoring custom %s variable addition [ %s = %s ], custom var already set to string." % (api_arg_name, key, value)) 1999 | return 2000 | 2001 | index = len(self.args[api_arg_name]) + 1 2002 | self.args[api_arg_name][index] = [key, value] 2003 | 2004 | class Parser(object): 2005 | """ 2006 | The Parser parses the lines in a specified file and inserts them into 2007 | a Queue. 2008 | """ 2009 | 2010 | def __init__(self): 2011 | self.check_methods = [method for name, method 2012 | in inspect.getmembers(self, predicate=inspect.ismethod) 2013 | if name.startswith('check_')] 2014 | 2015 | ## All check_* methods are called for each hit and must return True if the 2016 | ## hit can be imported, False otherwise. 2017 | 2018 | def check_hostname(self, hit): 2019 | # Check against config.hostnames. 2020 | if not hasattr(hit, 'host') or not config.options.hostnames: 2021 | return True 2022 | 2023 | # Accept the hostname only if it matches one pattern in the list. 2024 | result = any( 2025 | fnmatch.fnmatch(hit.host, pattern) 2026 | for pattern in config.options.hostnames 2027 | ) 2028 | if not result: 2029 | stats.count_lines_hostname_skipped.increment() 2030 | return result 2031 | 2032 | def check_static(self, hit): 2033 | if hit.extension in STATIC_EXTENSIONS: 2034 | if config.options.enable_static: 2035 | hit.is_download = True 2036 | return True 2037 | else: 2038 | stats.count_lines_static.increment() 2039 | return False 2040 | return True 2041 | 2042 | def check_download(self, hit): 2043 | if hit.extension in config.options.download_extensions: 2044 | stats.count_lines_downloads.increment() 2045 | hit.is_download = True 2046 | return True 2047 | # the file is not in the white-listed downloads 2048 | # if it's a know download file, we shall skip it 2049 | elif hit.extension in DOWNLOAD_EXTENSIONS: 2050 | stats.count_lines_skipped_downloads.increment() 2051 | return False 2052 | return True 2053 | 2054 | def check_user_agent(self, hit): 2055 | user_agent = hit.user_agent.lower() 2056 | for s in itertools.chain(EXCLUDED_USER_AGENTS, config.options.excluded_useragents): 2057 | if s in user_agent: 2058 | if config.options.enable_bots: 2059 | hit.is_robot = True 2060 | return True 2061 | else: 2062 | stats.count_lines_skipped_user_agent.increment() 2063 | return False 2064 | return True 2065 | 2066 | def check_http_error(self, hit): 2067 | if hit.status[0] in ('4', '5'): 2068 | if config.options.replay_tracking: 2069 | # process error logs for replay tracking, since we don't care if matomo error-ed the first time 2070 | return True 2071 | elif config.options.enable_http_errors: 2072 | hit.is_error = True 2073 | return True 2074 | else: 2075 | stats.count_lines_skipped_http_errors.increment() 2076 | return False 2077 | return True 2078 | 2079 | def check_http_redirect(self, hit): 2080 | if hit.status[0] == '3' and hit.status != '304': 2081 | if config.options.enable_http_redirects: 2082 | hit.is_redirect = True 2083 | return True 2084 | else: 2085 | stats.count_lines_skipped_http_redirects.increment() 2086 | return False 2087 | return True 2088 | 2089 | def check_path(self, hit): 2090 | for excluded_path in config.options.excluded_paths: 2091 | if fnmatch.fnmatch(hit.path, excluded_path): 2092 | return False 2093 | # By default, all paths are included. 2094 | if config.options.included_paths: 2095 | for included_path in config.options.included_paths: 2096 | if fnmatch.fnmatch(hit.path, included_path): 2097 | return True 2098 | return False 2099 | return True 2100 | 2101 | @staticmethod 2102 | def check_format(lineOrFile): 2103 | format = False 2104 | format_groups = 0 2105 | for name, candidate_format in FORMATS.iteritems(): 2106 | logging.debug("Check format %s", name) 2107 | 2108 | # skip auto detection for formats that can't be detected automatically 2109 | if name == 'ovh': 2110 | continue 2111 | 2112 | match = None 2113 | try: 2114 | if isinstance(lineOrFile, basestring): 2115 | match = candidate_format.check_format_line(lineOrFile) 2116 | else: 2117 | match = candidate_format.check_format(lineOrFile) 2118 | except Exception as e: 2119 | logging.debug('Error in format checking: %s', traceback.format_exc()) 2120 | pass 2121 | 2122 | if match: 2123 | logging.debug('Format %s matches', name) 2124 | 2125 | # compare format groups if this *BaseFormat has groups() method 2126 | try: 2127 | # if there's more info in this match, use this format 2128 | match_groups = len(match.groups()) 2129 | 2130 | logging.debug('Format match contains %d groups' % match_groups) 2131 | 2132 | if format_groups < match_groups: 2133 | format = candidate_format 2134 | format_groups = match_groups 2135 | except AttributeError: 2136 | format = candidate_format 2137 | 2138 | else: 2139 | logging.debug('Format %s does not match', name) 2140 | 2141 | # if the format is W3cExtendedFormat, check if the logs are from IIS and if so, issue a warning if the 2142 | # --w3c-time-taken-milli option isn't set 2143 | if isinstance(format, W3cExtendedFormat): 2144 | format.check_for_iis_option() 2145 | 2146 | return format 2147 | 2148 | @staticmethod 2149 | def detect_format(file): 2150 | """ 2151 | Return the best matching format for this file, or None if none was found. 2152 | """ 2153 | logging.debug('Detecting the log format') 2154 | 2155 | format = False 2156 | 2157 | # check the format using the file (for formats like the W3cExtendedFormat one) 2158 | format = Parser.check_format(file) 2159 | 2160 | # check the format using the first N lines (to avoid irregular ones) 2161 | lineno = 0 2162 | limit = 100000 2163 | while not format and lineno < limit: 2164 | line = file.readline() 2165 | if not line: # if at eof, don't keep looping 2166 | break 2167 | 2168 | lineno = lineno + 1 2169 | 2170 | logging.debug("Detecting format against line %i" % lineno) 2171 | format = Parser.check_format(line) 2172 | 2173 | try: 2174 | file.seek(0) 2175 | except IOError: 2176 | pass 2177 | 2178 | if not format: 2179 | fatal_error("cannot automatically determine the log format using the first %d lines of the log file. " % limit + 2180 | "\nMaybe try specifying the format with the --log-format-name command line argument." ) 2181 | return 2182 | 2183 | logging.debug('Format %s is the best match', format.name) 2184 | return format 2185 | 2186 | def is_filtered(self, hit): 2187 | host = None 2188 | if hasattr(hit, 'host'): 2189 | host = hit.host 2190 | else: 2191 | try: 2192 | host = urlparse.urlparse(hit.path).hostname 2193 | except: 2194 | pass 2195 | 2196 | if host: 2197 | if config.options.exclude_host and len(config.options.exclude_host) > 0 and host in config.options.exclude_host: 2198 | return (True, 'host matched --exclude-host') 2199 | 2200 | if config.options.include_host and len(config.options.include_host) > 0 and host not in config.options.include_host: 2201 | return (True, 'host did not match --include-host') 2202 | 2203 | if config.options.exclude_older_than and hit.date < config.options.exclude_older_than: 2204 | return (True, 'date is older than --exclude-older-than') 2205 | 2206 | if config.options.exclude_newer_than and hit.date > config.options.exclude_newer_than: 2207 | return (True, 'date is newer than --exclude-newer-than') 2208 | 2209 | return (False, None) 2210 | 2211 | def parse(self, filename): 2212 | """ 2213 | Parse the specified filename and insert hits in the queue. 2214 | """ 2215 | def invalid_line(line, reason): 2216 | stats.count_lines_invalid.increment() 2217 | if config.options.debug >= 2: 2218 | logging.debug('Invalid line detected (%s): %s' % (reason, line)) 2219 | 2220 | def filtered_line(line, reason): 2221 | stats.count_lines_filtered.increment() 2222 | if config.options.debug >= 2: 2223 | logging.debug('Filtered line out (%s): %s' % (reason, line)) 2224 | 2225 | if filename == '-': 2226 | filename = '(stdin)' 2227 | file = sys.stdin 2228 | else: 2229 | if not os.path.exists(filename): 2230 | print >> sys.stderr, "\n=====> Warning: File %s does not exist <=====" % filename 2231 | return 2232 | else: 2233 | if filename.endswith('.bz2'): 2234 | open_func = bz2.BZ2File 2235 | elif filename.endswith('.gz'): 2236 | open_func = gzip.open 2237 | else: 2238 | open_func = open 2239 | file = open_func(filename, 'r') 2240 | 2241 | if config.options.show_progress: 2242 | print('Parsing log %s...' % filename) 2243 | 2244 | if config.format: 2245 | # The format was explicitely specified. 2246 | format = config.format 2247 | 2248 | if isinstance(format, W3cExtendedFormat): 2249 | format.create_regex(file) 2250 | 2251 | if format.regex is None: 2252 | return fatal_error( 2253 | "File is not in the correct format, is there a '#Fields:' line? " 2254 | "If not, use the --w3c-fields option." 2255 | ) 2256 | else: 2257 | # If the file is empty, don't bother. 2258 | data = file.read(100) 2259 | if len(data.strip()) == 0: 2260 | return 2261 | try: 2262 | file.seek(0) 2263 | except IOError: 2264 | pass 2265 | 2266 | format = self.detect_format(file) 2267 | if format is None: 2268 | return fatal_error( 2269 | 'Cannot guess the logs format. Please give one using ' 2270 | 'either the --log-format-name or --log-format-regex option' 2271 | ) 2272 | # Make sure the format is compatible with the resolver. 2273 | resolver.check_format(format) 2274 | 2275 | if config.options.dump_log_regex: 2276 | logging.info("Using format '%s'." % format.name) 2277 | if format.regex: 2278 | logging.info("Regex being used: %s" % format.regex.pattern) 2279 | else: 2280 | logging.info("Format %s does not use a regex to parse log lines." % format.name) 2281 | logging.info("--dump-log-regex option used, aborting log import.") 2282 | os._exit(0) 2283 | 2284 | valid_lines_count = 0 2285 | 2286 | hits = [] 2287 | lineno = -1 2288 | while True: 2289 | line = file.readline() 2290 | if not line: break 2291 | lineno = lineno + 1 2292 | 2293 | try: 2294 | line = line.decode(config.options.encoding) 2295 | except UnicodeDecodeError: 2296 | invalid_line(line, 'invalid encoding') 2297 | continue 2298 | 2299 | stats.count_lines_parsed.increment() 2300 | if stats.count_lines_parsed.value <= config.options.skip: 2301 | continue 2302 | 2303 | match = format.match(line) 2304 | if not match: 2305 | invalid_line(line, 'line did not match') 2306 | continue 2307 | 2308 | valid_lines_count = valid_lines_count + 1 2309 | if config.options.debug_request_limit and valid_lines_count >= config.options.debug_request_limit: 2310 | if len(hits) > 0: 2311 | Recorder.add_hits(hits) 2312 | logging.info("Exceeded limit specified in --debug-request-limit, exiting.") 2313 | return 2314 | 2315 | hit = Hit( 2316 | filename=filename, 2317 | lineno=lineno, 2318 | status=format.get('status'), 2319 | full_path=format.get('path'), 2320 | is_download=False, 2321 | is_robot=False, 2322 | is_error=False, 2323 | is_redirect=False, 2324 | args={}, 2325 | ) 2326 | 2327 | if config.options.regex_group_to_page_cvars_map: 2328 | self._add_custom_vars_from_regex_groups(hit, format, config.options.regex_group_to_page_cvars_map, True) 2329 | 2330 | if config.options.regex_group_to_visit_cvars_map: 2331 | self._add_custom_vars_from_regex_groups(hit, format, config.options.regex_group_to_visit_cvars_map, False) 2332 | 2333 | if config.options.regex_groups_to_ignore: 2334 | format.remove_ignored_groups(config.options.regex_groups_to_ignore) 2335 | 2336 | # Add http method page cvar 2337 | try: 2338 | httpmethod = format.get('method') 2339 | if config.options.track_http_method and httpmethod != '-': 2340 | hit.add_page_custom_var('HTTP-method', httpmethod) 2341 | except: 2342 | pass 2343 | 2344 | try: 2345 | hit.query_string = format.get('query_string') 2346 | hit.path = hit.full_path 2347 | except BaseFormatException: 2348 | hit.path, _, hit.query_string = hit.full_path.partition(config.options.query_string_delimiter) 2349 | 2350 | # W3cExtendedFormat detaults to - when there is no query string, but we want empty string 2351 | if hit.query_string == '-': 2352 | hit.query_string = '' 2353 | 2354 | hit.extension = hit.path.rsplit('.')[-1].lower() 2355 | 2356 | try: 2357 | hit.referrer = format.get('referrer') 2358 | 2359 | if hit.referrer.startswith('"'): 2360 | hit.referrer = hit.referrer[1:-1] 2361 | except BaseFormatException: 2362 | hit.referrer = '' 2363 | if hit.referrer == '-': 2364 | hit.referrer = '' 2365 | 2366 | try: 2367 | hit.user_agent = format.get('user_agent') 2368 | 2369 | # in case a format parser included enclosing quotes, remove them so they are not 2370 | # sent to Matomo 2371 | if hit.user_agent.startswith('"'): 2372 | hit.user_agent = hit.user_agent[1:-1] 2373 | except BaseFormatException: 2374 | hit.user_agent = '' 2375 | 2376 | hit.ip = format.get('ip') 2377 | try: 2378 | hit.length = int(format.get('length')) 2379 | except (ValueError, BaseFormatException): 2380 | # Some lines or formats don't have a length (e.g. 304 redirects, W3C logs) 2381 | hit.length = 0 2382 | 2383 | try: 2384 | hit.generation_time_milli = float(format.get('generation_time_milli')) 2385 | except (ValueError, BaseFormatException): 2386 | try: 2387 | hit.generation_time_milli = float(format.get('generation_time_micro')) / 1000 2388 | except (ValueError, BaseFormatException): 2389 | try: 2390 | hit.generation_time_milli = float(format.get('generation_time_secs')) * 1000 2391 | except (ValueError, BaseFormatException): 2392 | hit.generation_time_milli = 0 2393 | 2394 | if config.options.log_hostname: 2395 | hit.host = config.options.log_hostname 2396 | else: 2397 | try: 2398 | hit.host = format.get('host').lower().strip('.') 2399 | 2400 | if hit.host.startswith('"'): 2401 | hit.host = hit.host[1:-1] 2402 | except BaseFormatException: 2403 | # Some formats have no host. 2404 | pass 2405 | 2406 | # Add userid 2407 | try: 2408 | hit.userid = None 2409 | 2410 | userid = format.get('userid') 2411 | if userid != '-': 2412 | hit.args['uid'] = hit.userid = userid 2413 | except: 2414 | pass 2415 | 2416 | # add event info 2417 | try: 2418 | hit.event_category = hit.event_action = hit.event_name = None 2419 | 2420 | hit.event_category = format.get('event_category') 2421 | hit.event_action = format.get('event_action') 2422 | 2423 | hit.event_name = format.get('event_name') 2424 | if hit.event_name == '-': 2425 | hit.event_name = None 2426 | except: 2427 | pass 2428 | 2429 | # Check if the hit must be excluded. 2430 | if not all((method(hit) for method in self.check_methods)): 2431 | continue 2432 | 2433 | # Parse date. 2434 | # We parse it after calling check_methods as it's quite CPU hungry, and 2435 | # we want to avoid that cost for excluded hits. 2436 | date_string = format.get('date') 2437 | try: 2438 | hit.date = datetime.datetime.strptime(date_string, format.date_format) 2439 | hit.date += datetime.timedelta(seconds = config.options.seconds_to_add_to_date) 2440 | except ValueError as e: 2441 | invalid_line(line, 'invalid date or invalid format: %s' % str(e)) 2442 | continue 2443 | 2444 | # Parse timezone and substract its value from the date 2445 | try: 2446 | timezone = float(format.get('timezone')) 2447 | except BaseFormatException: 2448 | timezone = 0 2449 | except ValueError: 2450 | invalid_line(line, 'invalid timezone') 2451 | continue 2452 | 2453 | if timezone: 2454 | hit.date -= datetime.timedelta(hours=timezone/100) 2455 | 2456 | if config.options.replay_tracking: 2457 | # we need a query string and we only consider requests with piwik.php 2458 | if not hit.query_string or not hit.path.lower().endswith(config.options.replay_tracking_expected_tracker_file): 2459 | invalid_line(line, 'no query string, or ' + hit.path.lower() + ' does not end with piwik.php') 2460 | continue 2461 | 2462 | query_arguments = urlparse.parse_qs(hit.query_string) 2463 | if not "idsite" in query_arguments: 2464 | invalid_line(line, 'missing idsite') 2465 | continue 2466 | 2467 | try: 2468 | hit.args.update((k, v.pop().encode('raw_unicode_escape').decode(config.options.encoding)) for k, v in query_arguments.iteritems()) 2469 | except UnicodeDecodeError: 2470 | invalid_line(line, 'invalid encoding') 2471 | continue 2472 | 2473 | (is_filtered, reason) = self.is_filtered(hit) 2474 | if is_filtered: 2475 | filtered_line(line, reason) 2476 | continue 2477 | 2478 | hits.append(hit) 2479 | 2480 | if len(hits) >= config.options.recorder_max_payload_size * len(Recorder.recorders): 2481 | Recorder.add_hits(hits) 2482 | hits = [] 2483 | 2484 | # add last chunk of hits 2485 | if len(hits) > 0: 2486 | Recorder.add_hits(hits) 2487 | 2488 | def _add_custom_vars_from_regex_groups(self, hit, format, groups, is_page_var): 2489 | for group_name, custom_var_name in groups.iteritems(): 2490 | if group_name in format.get_all(): 2491 | value = format.get(group_name) 2492 | 2493 | # don't track the '-' empty placeholder value 2494 | if value == '-': 2495 | continue 2496 | 2497 | if is_page_var: 2498 | hit.add_page_custom_var(custom_var_name, value) 2499 | else: 2500 | hit.add_visit_custom_var(custom_var_name, value) 2501 | 2502 | def main(): 2503 | """ 2504 | Start the importing process. 2505 | """ 2506 | stats.set_time_start() 2507 | 2508 | if config.options.show_progress: 2509 | stats.start_monitor() 2510 | 2511 | recorders = Recorder.launch(config.options.recorders) 2512 | 2513 | try: 2514 | for filename in config.filenames: 2515 | parser.parse(filename) 2516 | 2517 | Recorder.wait_empty() 2518 | except KeyboardInterrupt: 2519 | pass 2520 | 2521 | stats.set_time_stop() 2522 | 2523 | if config.options.show_progress: 2524 | stats.stop_monitor() 2525 | 2526 | stats.print_summary() 2527 | 2528 | def fatal_error(error, filename=None, lineno=None): 2529 | print >> sys.stderr, 'Fatal error: %s' % error 2530 | if filename and lineno is not None: 2531 | print >> sys.stderr, ( 2532 | 'You can restart the import of "%s" from the point it failed by ' 2533 | 'specifying --skip=%d on the command line.\n' % (filename, lineno) 2534 | ) 2535 | os._exit(1) 2536 | 2537 | if __name__ == '__main__': 2538 | try: 2539 | config = Configuration() 2540 | # The matomo object depends on the config object, so we have to create 2541 | # it after creating the configuration. 2542 | matomo = Matomo() 2543 | # The init_token_auth method may need the matomo option, so we must call 2544 | # it after creating the matomo object. 2545 | config.init_token_auth() 2546 | stats = Statistics() 2547 | resolver = config.get_resolver() 2548 | parser = Parser() 2549 | main() 2550 | sys.exit(0) 2551 | except KeyboardInterrupt: 2552 | pass 2553 | --------------------------------------------------------------------------------