2024 Q1 metrics update

* Added missing people * Fixed error handling in pull request metrics GitHub library
MariaDB · Apr 23, 2024 · b73623f · b73623f
1 parent e4b7c89
commit b73623f
Show file tree

Hide file tree

Showing 4 changed files with 31 additions and 15 deletions.
diff --git a/commits/config/categories b/commits/config/categories
@@ -23,6 +23,7 @@
 "Stellar Science"         Provider
 "Sun Microsystems"        Provider
 "Trail of Bits"           Other
+"University of Sydney"    Other
 "Wind River"              Provider
 "Worldline Global"        Provider
 Aerospike                 Provider

diff --git a/commits/config/employers b/commits/config/employers
@@ -7,6 +7,7 @@
 1136268146@qq.com                                   Independent
 15198894161@139.com                                 Independent
 22895992+paragoumba@users.noreply.github.com        Independent
+3001893+sophist-uk@users.noreply.github.com         Independent
 3310288189@qq.com                                   GSoC
 33860799+a97410985@users.noreply.github.com         Independent
 344369869@qq.com                                    Independent
@@ -39,11 +40,13 @@ alan.cuevamr@gmail.com                              GSoC
 alex.fan.q@gmail.com                                Gentoo
 andrew@linuxjedi.co.uk                              MariaDB Plc. < 2020-08-15
 andrew@linuxjedi.co.uk                              MariaDB Foundation
+andrew.daugherity@gmail.com                         Independent
 angeloudy@gmail.com                                 Independent
 anthonyryan1@gmail.com                              Whatbox
 arkamar@atlas.cz                                    Gentoo
 askeblad@outlook.com                                Independent
 aun.sokolov@gmail.com                               Independent
+aurelien@aurel32.net                                Independent
 bertrandop@gmail.com                                CONNECT
 bluemrp9@gmail.com                                  Independent
 brad@comstyle.com                                   OpenBSD
@@ -101,6 +104,7 @@ hsspig@gmail.com                                    Independent
 jonas.karlsson@kau.se                               Independent
 jonathan.sabbe@gmail.com                            Worldline Global
 jordy@pwning.systems                                Independent
+jtojnar@gmail.com                                   Independent
 justin@jagieniak.net                                Independent
 junqi_xie@outlook.com                               GSoC
 # A large Ruby on Rails contributor
@@ -170,6 +174,7 @@ pavlich_eng00@mail.ru                               Independent
 pkubaj@users.noreply.github.com                     HardenedBSD
 plainbanana@mustardon.tokyo                         Independent
 pmacontrol@68koncept.com                            Independent
+psz@maths.usyd.edu.au                               University of Sydney
 rahulanand16nov@gmail.com                           Independent
 raj.khem@gmail.com                                  Comcast
 rantal5030@gmail.com                                Independent

diff --git a/pull-requests/README.md b/pull-requests/README.md
@@ -2,7 +2,7 @@
 
 ### get_prs.py
 
-This tool gets the PR counts for 2022 and stores them in `prs-<START>..<END<.csv`. There is a deliberate 2 second pause between each request so as not to hit the GitHub rate limit (30 requests per minute).
+This tool gets the PR counts for 2022 and stores them in `prs-<START>..<END>.csv`. There is rate-limit handling built in because some calls are only allowed to do 30 requests per minute. It will also pause and retry upon 500 server errors.
 
 To execute this you will need a GitHub token from https://github.com/settings/tokens/new and set this as the environment variable `GITHUB_TOKEN`. You need to provide a date range using week numbers. For example, to generate a 2022 report:
 

diff --git a/pull-requests/pr_github.py b/pull-requests/pr_github.py
@@ -11,21 +11,31 @@
 
 
 def get_data(url, verbose):
-    response = requests.get(url, headers = auth_header)
-    if response.status_code != 200:
-        print("Failed to get json data: " + str(response.headers))
-        exit()
-    if (int(response.headers['X-RateLimit-Remaining']) <= 2):
-        if verbose:
-            print("\nRate limit low, remaining " + response.headers['X-RateLimit-Remaining'] + " sleeping for 30 seconds", end='')
+    while(True):
+        response = requests.get(url, headers = auth_header)
+        if response.status_code == 500:
+            if verbose:
+                print("\nServer error, retrying in 30 seconds")
+            else:
+                print('*', end='')
+            sys.stdout.flush()
+            time.sleep(30)
+        elif response.status_code != 200:
+            print("\nFailed to get json data: " + str(response.headers))
+            print("URL: " + url)
+            print("Status code: " + str(response.status_code))
+            exit()
+        elif (int(response.headers['X-RateLimit-Remaining']) <= 2):
+            if verbose:
+                print("\nRate limit low, remaining " + response.headers['X-RateLimit-Remaining'] + " sleeping for 30 seconds", end='')
+            else:
+                print('_', end='')
+            sys.stdout.flush()
+            time.sleep(30)
         else:
-            print('_', end='')
-        time.sleep(30)
-    else:
-        print('.', end='')
-    sys.stdout.flush()
-
-    return response
+            print('.', end='')
+            sys.stdout.flush()
+            return response
 
 def get_paginated_data(url, verbose):
     data = []