V1.1 RC1

.github/workflows/bandit.yml

@@ -13,12 +13,12 @@
 name: Bandit
 on:
   push:
-    branches: [ "main", "release" ]
+    branches: ["main", "release"]
   pull_request:
     # The branches below must be a subset of the branches above
-    branches: [ "main" ]
+    branches: ["main"]
   schedule:
-    - cron: '24 2 * * 2'
+    - cron: "24 2 * * 2"
 
 jobs:
   bandit:
@@ -30,7 +30,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
       - name: Bandit Scan
-        uses: shundor/python-bandit-scan@ab1d87dfccc5a0ffab88be3aaac6ffe35c10d6cd
+        uses: reactive-firewall/python-bandit-scan@11a72c7c18aab77758bf6f5d9456f1018ec107b0
         with: # optional arguments
           # exit with 0, even with results found
           exit_zero: true # optional, default is DEFAULT
@@ -43,9 +43,9 @@ jobs:
           # Report only issues of a given confidence level or higher. Can be LOW, MEDIUM or HIGH. Default is UNDEFINED (everything)
           # confidence: # optional, default is UNDEFINED
           # comma-separated list of paths (glob patterns supported) to exclude from scan (note that these are in addition to the excluded paths provided in the config file) (default: .svn,CVS,.bzr,.hg,.git,__pycache__,.tox,.eggs,*.egg)
-          excluded_paths: tests
+          # excluded_paths:
           # comma-separated list of test IDs to skip
           # skips: # optional, default is DEFAULT
           # path to a .bandit file that supplies command line arguments
           # ini_path: # optional, default is DEFAULT
-
+          config_path: pyproject.toml

.github/workflows/build_docker.yml

@@ -178,12 +178,12 @@ jobs:
           docker compose -f docker-compose.yml up --no-build 2>&1 \
             | (./scripts/ci/await_all.py /tmp/regex_matches.txt \
                 && docker compose -f docker-compose.yml down)
-        timeout-minutes: 3
+        timeout-minutes: 8
         env:
-          AUGUR_GITHUB_API_KEY: ${{ secrets.GITHUB_TOKEN }}
-          AUGUR_GITHUB_USERNAME: ${{ github.repository_owner }}
-          AUGUR_GITLAB_API_KEY: dummy
-          AUGUR_GITLAB_USERNAME: dummy
+          COLLECTOSS_GITHUB_API_KEY: ${{ secrets.GITHUB_TOKEN }}
+          COLLECTOSS_GITHUB_USERNAME: ${{ github.repository_owner }}
+          COLLECTOSS_GITLAB_API_KEY: dummy
+          COLLECTOSS_GITLAB_USERNAME: dummy
 
       - name: Dump logs
         # Always run this step to get logs, even if the previous step fails
@@ -294,18 +294,19 @@ jobs:
           podman compose -f docker-compose.yml up --no-build 2>&1 \
             | (./scripts/ci/await_all.py /tmp/regex_matches.txt \
                 && podman compose -f docker-compose.yml down)
-        timeout-minutes: 3
+        timeout-minutes: 8
         env:
-          AUGUR_GITHUB_API_KEY: ${{ secrets.GITHUB_TOKEN }}
-          AUGUR_GITHUB_USERNAME: ${{ github.repository_owner }}
-          AUGUR_GITLAB_API_KEY: dummy
-          AUGUR_GITLAB_USERNAME: dummy
+          COLLECTOSS_GITHUB_API_KEY: ${{ secrets.GITHUB_TOKEN }}
+          COLLECTOSS_GITHUB_USERNAME: ${{ github.repository_owner }}
+          COLLECTOSS_GITLAB_API_KEY: dummy
+          COLLECTOSS_GITLAB_USERNAME: dummy
 
       - name: Dump logs
         # Always run this step to get logs, even if the previous step fails
         if: always()
         # We use tail so that we can see the name of each file as it's printed
-        run: "podman run -t --rm -v augur_logs:/logs bash -c 'find /logs -type f | xargs
+        run:
+          "podman run -t --rm -v augur_logs:/logs bash -c 'find /logs -type f | xargs
           tail -n +0'"
 
   push-image:
@@ -358,7 +359,7 @@ jobs:
           # Releases update the *:latest tag and the *:<version> tag
           tags: |
             type=raw,value=devel-latest,enable=${{ github.ref == 'refs/heads/main' }}
-            type=raw,value=latest,enable=${{ github.event_name == 'release' }}
+            type=raw,value=latest,enable=${{ github.event_name == 'release' && !github.event.release.prerelease }}
             type=raw,value=${{ github.event.release.tag_name }},enable=${{ github.event_name == 'release' }}
 
       - name: Build and push

.github/workflows/functional_test.yml

@@ -27,5 +27,4 @@ jobs:
       - name: Run Tests
         run: |
           uv run --python ${{ matrix.env }} pytest \
-            tests/test_classes \
             --color=yes

CONTRIBUTING.md

@@ -9,7 +9,7 @@ These resources are a great way to meet the people behind the project, ask quest
 
 ## Learn about the project
 
-If you aren't already familiar with what CollectOSS is, please make sure you've read the [README](README.md) to get a primer on our project, and maybe take a look around the [documentation](https://collectoss.readthedocs.io/en/release/) so you know what we are about. You can also hang out in Slack or join our community meetings to learn more about what we do.
+If you aren't already familiar with what CollectOSS is, please make sure you've read the [README](README.md) to get a primer on our project, and maybe take a look around the [documentation](https://docs.collectoss.org/en/release/) so you know what we are about. You can also hang out in Slack or join our community meetings to learn more about what we do.
 
 ## Opening an issue
 If you're experiencing an issue with CollectOSS you can search for your problem or question on our [issues](https://github.com/chaoss/collectoss/issues) page to see if someone else has already reported it. If you cannot find your issue, please feel free to [open a new one](https://github.com/chaoss/collectoss/issues/new/choose).
@@ -53,7 +53,7 @@ Github has an article called [Syncing a fork](https://docs.github.com/en/pull-re
 
 ## Helpful Links
 
-- [CollectOSS stable documentation](https://collectoss.readthedocs.io/en/release/)
+- [CollectOSS stable documentation](https://docs.collectoss.org/en/release/)
 - [CHAOSS Getting Started page](https://chaoss.community/kb-getting-started/)
 
 **Git & GitHub**

CREDITS.md

@@ -13,6 +13,8 @@ The list of current CollectOSS maintainers can be found in the [MAINTAINERS](./M
 
 Augur has been supported by the University of Missouri through funding provided by the Alfred P. Sloan Foundation, Mozilla, The Reynolds Journalism Institute with contributions from VMWare, Red Hat LLC, Grace Hopper's Open Source Day, GitHub, Microsoft, Twitter, Adobe, the Gluster Project, Open Source Summit (NA/Europe), and the Linux Foundation Compliance Summit.
 
+Augur has also been supported by the University of Nebraska at Omaha.
+
 Significant design contributors include Kate Stewart, Dawn Foster, Duane O'Brien, Remy Decausemaker, Google Summer of Code Students, and others including:
 
 ### Maintainers
@@ -43,6 +45,18 @@ Significant design contributors include Kate Stewart, Dawn Foster, Duane O'Brien
 - [Gary P. White](https://github.com/garypwhite)
 - [Shlok Gilda](https://github.com/shlokgilda)
 
+### Credited Copyright Holders
+These names came from the LICENSE.md file in the Augur project:
+- Matt Germonprez
+- Sean Goggins
+- Gabe Heim
+- Derek Howard
+- Carter Landis
+- Matt Snell
+- Brian Warner
+- University of Nebraska at Omaha
+- University of Missouri
+
 ### GSoC 2025 Participants
 - [Akshat Baranwal](https://github.com/akshatb2006)
 - [Asish Kumar](https://github.com/officialasishkumar)

GOVERNANCE.md

@@ -121,7 +121,7 @@ While most business in CollectOSS is conducted by "[lazy consensus](https://comm
 periodically the Maintainers may need to vote on specific actions or changes.
 A vote can be taken on the project's public Slack channel (#wg-collectoss-8knot in the [CHAOSS Slack](https://chaoss.community/kb-getting-started/)) or 
 the private Maintainer Slack channel for security or conduct matters.  
-Votes may also be taken at the biweely developer meeting.  Any Maintainer may
+Votes may also be taken at the biweekly developer meeting.  Any Maintainer may
 demand a vote be taken.
 
 Most votes require a simple majority of all Maintainers to succeed, except where

README.md

@@ -10,7 +10,7 @@ CollectOSS's main focus is to measure the overall health and sustainability of o
 
 The data CollectOSS collects covers more than just code contributions and extends to anything that can be derived from forge data, including comments, change reviews, releases, and other project activity or interactions. This data is stored in a relational database (PostgreSQL), enabling large-scale data aggregation across any number of repositories to provide context about the way these communities evolve.
 
-CollectOSS is part of [CHAOSS](https://chaoss.community), which is a Linux Foundation® project. Many of our metrics are implementations of the [metrics](https://chaoss.community/metrics/) defined by the CHAOSS community.
+CollectOSS is part of [CHAOSS](https://chaoss.community), which is a Linux Foundation® project. Many of our metrics are implementations of the [metrics](https://chaoss.community/kb-metrics-and-metrics-models/) defined by the CHAOSS community.
 
 ## Versions and support
 CollectOSS is a Python project distributed via container images and aims to support all currently-supported versions of Python on macOS and Linux platforms. Docker is the primary supported container runtime, but Podman is also supported and used by some maintainers, although it requires configuring some extra permissions to run correctly.
@@ -25,7 +25,7 @@ Basic initial setup can be completed in a few minutes as follows:
 3. Copy the `environment.txt` file to a new file called `.env` and fill in values for the required variables
 4. Run `docker compose up` to start the containers
 
-Check out the [CollectOSS Documentation](https://collectoss.readthedocs.io) for more detailed setup instructions and troubleshooting steps.
+Check out the [CollectOSS Documentation](https://docs.collectoss.org) for more detailed setup instructions and troubleshooting steps.
 
 ## Contributing
 We strongly believe that communities are what makes open source so impactful. We invite you to join our community, regardless of your experience level or coding abilities! 

collectoss/api/gunicorn_conf.py

@@ -7,6 +7,7 @@
 
 from collectoss.application.db.lib import get_value
 from collectoss.application.db import dispose_database_engine
+from collectoss.application.environment import SystemEnv
 
 logger = logging.getLogger(__name__)
 
@@ -20,8 +21,8 @@
 workers = multiprocessing.cpu_count() * 2 + 1
 umask = 0o007
 reload = True
-
-is_dev = os.getenv("AUGUR_DEV", 'False').lower() in ('true', '1', 't', 'y', 'yes')
+# this satisfies the type checker
+is_dev = SystemEnv.get_bool("AUGUR_DEV", False)
 
 if is_dev:
 
@@ -40,7 +41,8 @@
 # set the log location for gunicorn    
 logs_directory = get_value('Logging', 'logs_directory')
 
-is_docker = os.getenv("AUGUR_DOCKER_DEPLOY", 'False').lower() in ('true', '1', 't', 'y', 'yes')
+# this syntax satisfies the type checker
+is_docker = SystemEnv.get_bool("AUGUR_DOCKER_DEPLOY", False)
 accesslog = f"{logs_directory}/gunicorn.log"
 errorlog = f"{logs_directory}/gunicorn.log"
 

collectoss/api/metrics/commit.py

@@ -231,7 +231,7 @@ def annual_commit_count_ranked_by_repo_in_repo_group(repo_group_id, repo_id=None
         if timeframe == 'all':
             cdRgTpRankedCommitsSQL = s.sql.text("""
                 SELECT repo.repo_id, repo_name as name, SUM(added - removed - whitespace) as net, patches
-                FROM augur_data.dm_repo_annual, repo, repo_groups
+                FROM data.dm_repo_annual, repo, repo_groups
                 WHERE repo.repo_group_id = :repo_group_id
                 AND repo.repo_group_id = repo_groups.repo_group_id
                 AND dm_repo_annual.repo_id = repo.repo_id

collectoss/api/metrics/deps.py

@@ -33,13 +33,13 @@ def deps(repo_group_id, repo_id=None, period='day', begin_date=None, end_date=No
 
         depsSQL = s.sql.text("""
             SELECT
-            augur_data.repo_dependencies.*,
-            augur_data.repo_groups.repo_group_id 
+            data.repo_dependencies.*,
+            data.repo_groups.repo_group_id 
             FROM
-            augur_data.repo_dependencies,
-            augur_data.repo_groups,
-            augur_data.repo,
-            ( SELECT MAX ( date_trunc( 'day', augur_data.repo_dependencies.data_collection_date ) ) AS data_collection_date FROM repo_dependencies WHERE repo_id = repo_id ) C 
+            data.repo_dependencies,
+            data.repo_groups,
+            data.repo,
+            ( SELECT MAX ( date_trunc( 'day', data.repo_dependencies.data_collection_date ) ) AS data_collection_date FROM repo_dependencies WHERE repo_id = repo_id ) C 
             WHERE
             repo_dependencies.repo_id = repo.repo_id 
             AND repo.repo_group_id = repo_groups.repo_group_id 
@@ -54,13 +54,13 @@ def deps(repo_group_id, repo_id=None, period='day', begin_date=None, end_date=No
 
         depsSQL = s.sql.text("""
             SELECT
-            augur_data.repo_dependencies.*,
-            augur_data.repo_groups.repo_group_id 
+            data.repo_dependencies.*,
+            data.repo_groups.repo_group_id 
             FROM
-            augur_data.repo_dependencies,
-            augur_data.repo_groups,
-            augur_data.repo,
-            ( SELECT MAX ( date_trunc( 'day', augur_data.repo_dependencies.data_collection_date ) ) AS data_collection_date 
+            data.repo_dependencies,
+            data.repo_groups,
+            data.repo,
+            ( SELECT MAX ( date_trunc( 'day', data.repo_dependencies.data_collection_date ) ) AS data_collection_date 
             FROM repo_dependencies, repo, repo_groups 
             WHERE repo.repo_group_id = repo_groups.repo_group_id and 
             repo_dependencies.repo_id = repo.repo_id and
@@ -134,8 +134,8 @@ def libyear(repo_group_id, repo_id=None, period='day', begin_date=None, end_date
                     f.libyear, 
                     f.data_collection_date
                 FROM
-                    ( SELECT repo_id, NAME, MAX ( data_collection_date ) AS data_collection_date FROM augur_data.repo_deps_libyear WHERE repo_id = :repo_id GROUP BY repo_id, NAME ORDER BY NAME ) e,
-                    augur_data.repo_deps_libyear f 
+                    ( SELECT repo_id, NAME, MAX ( data_collection_date ) AS data_collection_date FROM data.repo_deps_libyear WHERE repo_id = :repo_id GROUP BY repo_id, NAME ORDER BY NAME ) e,
+                    data.repo_deps_libyear f 
                 WHERE
                     e.data_collection_date = f.data_collection_date and 
                     e.repo_id = f.repo_id 
@@ -203,8 +203,8 @@ def libyear(repo_group_id, repo_id=None, period='day', begin_date=None, end_date
                     f.libyear, 
                     f.data_collection_date
                 FROM
-                    ( SELECT repo_id, NAME, MAX ( data_collection_date ) AS data_collection_date FROM augur_data.repo_deps_libyear GROUP BY repo_id, NAME ORDER BY NAME ) e,
-                    augur_data.repo_deps_libyear f 
+                    ( SELECT repo_id, NAME, MAX ( data_collection_date ) AS data_collection_date FROM data.repo_deps_libyear GROUP BY repo_id, NAME ORDER BY NAME ) e,
+                    data.repo_deps_libyear f 
                 WHERE
                     e.data_collection_date = f.data_collection_date and 
                     e.repo_id = f.repo_id 

collectoss/api/metrics/message.py

@@ -40,12 +40,12 @@ def repo_messages(repo_group_id, repo_id=None, period='day', begin_date=None, en
                 COUNT ( * ),
                 repo_name 
             FROM
-                augur_data.repo,
-                augur_data.message 
+                data.repo,
+                data.message 
             WHERE
-                augur_data.repo.repo_id = augur_data.message.repo_id 
+                data.repo.repo_id = data.message.repo_id 
                 AND
-                augur_data.repo.repo_id = :repo_id 
+                data.repo.repo_id = :repo_id 
                 AND 
                 message.msg_timestamp BETWEEN :begin_date AND :end_date
             GROUP BY
@@ -69,14 +69,14 @@ def repo_messages(repo_group_id, repo_id=None, period='day', begin_date=None, en
                 COUNT ( * ),
                 rg_name 
             FROM
-                augur_data.repo,
-                augur_data.repo_groups,
-                augur_data.message 
+                data.repo,
+                data.repo_groups,
+                data.message 
             WHERE
-                augur_data.repo.repo_id = augur_data.message.repo_id 
-                AND augur_data.repo_groups.repo_group_id = repo.repo_group_id 
+                data.repo.repo_id = data.message.repo_id 
+                AND data.repo_groups.repo_group_id = repo.repo_group_id 
                 AND
-                augur_data.repo_groups.repo_group_id = :repo_group_id 
+                data.repo_groups.repo_group_id = :repo_group_id 
                 AND 
                 message.msg_timestamp BETWEEN :begin_date AND :end_date
             GROUP BY

collectoss/api/metrics/pull_request.py

@@ -787,8 +787,8 @@ def pull_request_average_commit_counts(repo_group_id, repo_id=None, group_by='mo
                 pr_merged_at,
                 pr_closed_at,
                 pr_created_at
-            FROM augur_data.pull_request_commits, augur_data.pull_request_meta,augur_data.repo_groups, 
-            augur_data.pull_requests JOIN repo ON pull_requests.repo_id = repo.repo_id
+            FROM data.pull_request_commits, data.pull_request_meta,data.repo_groups, 
+            data.pull_requests JOIN repo ON pull_requests.repo_id = repo.repo_id
             WHERE pull_requests.repo_id IN 
                 (SELECT repo_id FROM repo WHERE repo_group_id = :repo_group_id)
                 AND pull_requests.pull_request_id = pull_request_commits.pull_request_id
@@ -821,7 +821,7 @@ def pull_request_average_commit_counts(repo_group_id, repo_id=None, group_by='mo
             pr_merged_at,
             pr_closed_at,
             pr_created_at
-        FROM augur_data.pull_request_commits, augur_data.pull_requests, augur_data.pull_request_meta
+        FROM data.pull_request_commits, data.pull_requests, data.pull_request_meta
         WHERE pull_requests.pull_request_id = pull_request_commits.pull_request_id
             AND pull_requests.pull_request_id = pull_request_meta.pull_request_id
             AND pull_requests.repo_id = :repo_id

collectoss/api/metrics/repo_meta.py

@@ -190,7 +190,7 @@ def sbom_download(repo_group_id, repo_id=None):
     :return: dosocs sbom
     """
     dosocs_SQL = s.sql.text("""
-        select * from augur_data.repo_sbom_scans
+        select * from data.repo_sbom_scans
         where repo_id = :repo_id;
     """)
 
@@ -313,15 +313,15 @@ def cii_best_practices_badge(repo_group_id, repo_id=None):
     if not repo_id:
         cii_best_practices_badge_SQL = s.sql.text("""
             SELECT data
-            FROM augur_data.repo_badging
+            FROM data.repo_badging
             WHERE repo_id IN (SELECT repo_id FROM repo WHERE repo_group_id = :repo_group_id)
             ORDER BY created_at DESC
             LIMIT 1
         """)
     else:
         cii_best_practices_badge_SQL = s.sql.text("""
             SELECT data
-            FROM augur_data.repo_badging
+            FROM data.repo_badging
             WHERE repo_id = :repo_id
             ORDER BY created_at DESC
             LIMIT 1
@@ -1270,7 +1270,7 @@ def clones(repo_group_id, repo_id=None, begin_date=None, end_date=None):
                 clone_data_timestamp AS date,
                 count_clones AS total_clones,
                 unique_clones
-            FROM augur_data.repo_clones_data
+            FROM data.repo_clones_data
             WHERE repo_id = :repo_id
               AND clone_data_timestamp BETWEEN :begin_date AND :end_date
             ORDER BY clone_data_timestamp
@@ -1289,9 +1289,9 @@ def clones(repo_group_id, repo_id=None, begin_date=None, end_date=None):
                 clone_data_timestamp AS date,
                 count_clones AS total_clones,
                 unique_clones
-            FROM augur_data.repo_clones_data
+            FROM data.repo_clones_data
             WHERE repo_id IN (
-                SELECT repo_id FROM augur_data.repo WHERE repo_group_id = :repo_group_id
+                SELECT repo_id FROM data.repo WHERE repo_group_id = :repo_group_id
             )
               AND clone_data_timestamp BETWEEN :begin_date AND :end_date
             ORDER BY repo_id, clone_data_timestamp

collectoss/api/metrics/toss.py

@@ -114,7 +114,7 @@ def toss_repo_info(repo_id):
         repo_info.default_branch,
         repo.repo_git
     FROM
-        augur_data.repo_info
+        data.repo_info
         JOIN repo ON repo.repo_id = repo_info.repo_id
     WHERE
         repo_info.repo_id = :repo_id