Dev update to index branch

.github/workflows/auto_merge.yml

@@ -15,8 +15,11 @@ jobs:
         with:
           fetch-depth: 0
       - run: |
+          git config user.name 'GitHub Actions'
+          git config user.email '[email protected]'
           git checkout dev
           git merge main
+          echo "Done with merge"
       - name: Push to dev
         uses: CasperWA/push-protected@v2
         with:

.pylintrc

@@ -12,7 +12,7 @@
 #refactoring checker
 #enable=R
 
-disable=E0611,E1101,W1203,R0801,W0614,W0611,C0411,C0103,C0301,C0303,C0304,C0305,W0311,E0401
+disable=E0611,E1101,W1203,R0801,W0614,W0611,C0411,C0103,C0301,C0303,C0304,C0305,W0311,E0401,C0116
 
 
 # Analyse import fallback blocks. This can be used to support both Python 2 and

README.md

@@ -1,4 +1,4 @@
-# Augur NEW Release v0.62.5
+# Augur NEW Release v0.62.6
 
 Augur is primarily a data engineering tool that makes it possible for data scientists to gather open source software community data. Less data carpentry for everyone else! 
 The primary way of looking at Augur data is through [8Knot](https://github.com/oss-aspen/8knot) ... A public instance of 8Knot is available at https://metrix.chaoss.io ... That is tied to a public instance of Augur at https://ai.chaoss.io 
@@ -10,7 +10,7 @@ The primary way of looking at Augur data is through [8Knot](https://github.com/o
 ## NEW RELEASE ALERT!
 ### [If you want to jump right in, updated docker build/compose and bare metal installation instructions are available here](docs/new-install.md)
 
-Augur is now releasing a dramatically improved new version to the main branch. It is also available here: https://github.com/chaoss/augur/releases/tag/v0.62.5
+Augur is now releasing a dramatically improved new version to the main branch. It is also available here: https://github.com/chaoss/augur/releases/tag/v0.62.6
 - The `main` branch is a stable version of our new architecture, which features:
   - Dramatic improvement in the speed of large scale data collection (100,000+ repos). All data is obtained for 100k+ repos within 2 weeks.
   - A new job management architecture that uses Celery and Redis to manage queues, and enables users to run a Flower job monitoring dashboard

augur/api/gunicorn_conf.py

@@ -1,47 +1,48 @@
 # from augur import ROOT_AUGUR_DIRECTORY
 import multiprocessing
 import logging
-import os
 from pathlib import Path
 from glob import glob
-import shutil
 
-from augur.application.db.session import DatabaseSession
-from augur.application.config import AugurConfig
+from augur.application.db.lib import get_value, get_section
+from augur.application.db import dispose_database_engine
 
 logger = logging.getLogger(__name__)
-with DatabaseSession(logger) as session:
 
-    augur_config = AugurConfig(logger, session)
-
-
-    # ROOT_AUGUR_DIRECTORY = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))
 
-    # base_log_dir = ROOT_AUGUR_DIRECTORY + "/logs/"
+# ROOT_AUGUR_DIRECTORY = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))
+
+# base_log_dir = ROOT_AUGUR_DIRECTORY + "/logs/"
+
+# Path(base_log_dir).mkdir(exist_ok=True)
 
-    # Path(base_log_dir).mkdir(exist_ok=True)
+workers = multiprocessing.cpu_count() * 2 + 1
+umask = 0o007
+reload = True
+reload_extra_files = glob(str(Path.cwd() / '**/*.j2'), recursive=True)
 
-    workers = multiprocessing.cpu_count() * 2 + 1
-    umask = 0o007
-    reload = True
-    reload_extra_files = glob(str(Path.cwd() / '**/*.j2'), recursive=True)
+# set the log location for gunicorn    
+logs_directory = get_value('Logging', 'logs_directory')
+accesslog = f"{logs_directory}/gunicorn.log"
+errorlog = f"{logs_directory}/gunicorn.log"
 
-    # set the log location for gunicorn    
-    logs_directory = augur_config.get_value('Logging', 'logs_directory')
-    accesslog = f"{logs_directory}/gunicorn.log"
-    errorlog = f"{logs_directory}/gunicorn.log"
+ssl_bool = get_value('Server', 'ssl')
+
+if ssl_bool is True: 
+
+    workers = int(get_value('Server', 'workers'))
+    bind = '%s:%s' % (get_value("Server", "host"), get_value("Server", "port"))
+    timeout = int(get_value('Server', 'timeout'))
+    certfile = str(get_value('Server', 'ssl_cert_file'))
+    keyfile = str(get_value('Server', 'ssl_key_file'))
+
+else: 
+    workers = int(get_value('Server', 'workers'))
+    bind = '%s:%s' % (get_value("Server", "host"), get_value("Server", "port"))
+    timeout = int(get_value('Server', 'timeout'))
 
-    ssl_bool = augur_config.get_value('Server', 'ssl')
 
-    if ssl_bool is True: 
+def worker_exit(server, worker):
+    print("Stopping gunicorn worker process")
+    dispose_database_engine()
 
-        workers = int(augur_config.get_value('Server', 'workers'))
-        bind = '%s:%s' % (augur_config.get_value("Server", "host"), augur_config.get_value("Server", "port"))
-        timeout = int(augur_config.get_value('Server', 'timeout'))
-        certfile = str(augur_config.get_value('Server', 'ssl_cert_file'))
-        keyfile = str(augur_config.get_value('Server', 'ssl_key_file'))
-
-    else: 
-        workers = int(augur_config.get_value('Server', 'workers'))
-        bind = '%s:%s' % (augur_config.get_value("Server", "host"), augur_config.get_value("Server", "port"))
-        timeout = int(augur_config.get_value('Server', 'timeout'))

augur/api/metrics/README.md

@@ -14,7 +14,6 @@ import datetime
 import sqlalchemy as s
 import pandas as pd
 from augur.api.util import register_metric
-from augur.application.db.engine import engine
 ```
 3. Defining the function
     1. Add the decorator @register_metric to the function

augur/api/metrics/commit.py

@@ -6,9 +6,9 @@
 import datetime
 import sqlalchemy as s
 import pandas as pd
-from augur.api.util import register_metric
+from flask import current_app
 
-from ..server import engine
+from augur.api.util import register_metric
 
 @register_metric()
 def committers(repo_group_id, repo_id=None, begin_date=None, end_date=None, period='month'):
@@ -90,7 +90,7 @@ def committers(repo_group_id, repo_id=None, begin_date=None, end_date=None, peri
             """
         )
 
-    with engine.connect() as conn:
+    with current_app.engine.connect() as conn:
         results = pd.read_sql(committersSQL, conn, params={'repo_id': repo_id, 
             'repo_group_id': repo_group_id,'begin_date': begin_date, 'end_date': end_date, 'period':period})
 
@@ -168,7 +168,7 @@ def annual_commit_count_ranked_by_new_repo_in_repo_group(repo_group_id, repo_id=
             ORDER BY YEAR ASC
         """.format(table, period))
 
-    with engine.connect() as conn:
+    with current_app.engine.connect() as conn:
         results = pd.read_sql(cdRgNewrepRankedCommitsSQL, conn, params={'repo_id': repo_id, 
             'repo_group_id': repo_group_id,'begin_date': begin_date, 'end_date': end_date})
     return results
@@ -267,7 +267,7 @@ def annual_commit_count_ranked_by_repo_in_repo_group(repo_group_id, repo_id=None
                 LIMIT 10
             """)
 
-    with engine.connect() as conn:
+    with current_app.engine.connect() as conn:
         results = pd.read_sql(cdRgTpRankedCommitsSQL, conn, params={ "repo_group_id": repo_group_id,
         "repo_id": repo_id})
     return results
@@ -299,7 +299,7 @@ def top_committers(repo_group_id, repo_id=None, year=None, threshold=0.8):
                 ORDER BY patches DESC) a
         """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(total_commits_SQL, conn,
                                 params={'year': year, 'repo_group_id': repo_group_id})
     else:
@@ -312,7 +312,7 @@ def top_committers(repo_group_id, repo_id=None, year=None, threshold=0.8):
                 ORDER BY patches DESC) a
         """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(total_commits_SQL, conn,
                                 params={'year': year, 'repo_id': repo_id})
 
@@ -339,7 +339,7 @@ def top_committers(repo_group_id, repo_id=None, year=None, threshold=0.8):
             ORDER BY commits DESC
         """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(committers_SQL, conn,
                                 params={'year': year, 'repo_group_id': repo_group_id})
     else:
@@ -359,7 +359,7 @@ def top_committers(repo_group_id, repo_id=None, year=None, threshold=0.8):
             ORDER BY commits DESC
         """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(committers_SQL, conn,
                                 params={'year': year, 'repo_id': repo_id})
 

augur/api/metrics/contributor.py

@@ -6,10 +6,10 @@
 import datetime
 import sqlalchemy as s
 import pandas as pd
+from flask import current_app
+
 from augur.api.util import register_metric
-import uuid 
 
-from ..server import engine
 
 @register_metric()
 def contributors(repo_group_id, repo_id=None, period='day', begin_date=None, end_date=None):
@@ -125,7 +125,7 @@ def contributors(repo_group_id, repo_id=None, period='day', begin_date=None, end
             ORDER BY total DESC
         """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(contributorsSQL, conn, params={'repo_id': repo_id, 'period': period,
                                                                     'begin_date': begin_date, 'end_date': end_date})
     else:
@@ -212,7 +212,7 @@ def contributors(repo_group_id, repo_id=None, period='day', begin_date=None, end
             ORDER BY total DESC
         """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(contributorsSQL, conn, params={'repo_group_id': repo_group_id, 'period': period,
                                                                 'begin_date': begin_date, 'end_date': end_date})
     return results
@@ -283,7 +283,7 @@ def contributors_new(repo_group_id, repo_id=None, period='day', begin_date=None,
             GROUP BY date, repo.repo_id, repo_name
             """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(contributorsNewSQL, conn, params={'repo_id': repo_id, 'period': period,
                                                                     'begin_date': begin_date, 'end_date': end_date})
     else:
@@ -333,7 +333,7 @@ def contributors_new(repo_group_id, repo_id=None, period='day', begin_date=None,
             GROUP BY date, repo.repo_id, repo_name
             """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(contributorsNewSQL, conn, params={'repo_group_id': repo_group_id, 'period': period,
                                                                        'begin_date': begin_date, 'end_date': end_date})
     return results
@@ -355,7 +355,7 @@ def lines_changed_by_author(repo_group_id, repo_id=None):
             GROUP BY commits.repo_id, date_trunc('week', cmt_author_date::date), cmt_author_affiliation, cmt_author_email, repo_name
             ORDER BY date_trunc('week', cmt_author_date::date) ASC;
         """)
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(linesChangedByAuthorSQL, conn, params={"repo_id": repo_id})
         return results
     else:
@@ -367,7 +367,7 @@ def lines_changed_by_author(repo_group_id, repo_id=None):
             GROUP BY repo_id, date_trunc('week', cmt_author_date::date), cmt_author_affiliation, cmt_author_email
             ORDER BY date_trunc('week', cmt_author_date::date) ASC;
         """)
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(linesChangedByAuthorSQL, conn, params={"repo_group_id": repo_group_id})
         return results
 
@@ -426,7 +426,7 @@ def contributors_code_development(repo_group_id, repo_id=None, period='all', beg
             GROUP BY a.email, a.repo_id, repo_name
         """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(contributorsSQL, conn, params={'repo_id': repo_id, 'period': period,
                                                                     'begin_date': begin_date, 'end_date': end_date})
     else:
@@ -462,7 +462,7 @@ def contributors_code_development(repo_group_id, repo_id=None, period='all', beg
             ORDER BY commits desc, email
         """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(contributorsSQL, conn, params={'repo_group_id': repo_group_id, 'period': period,
                                                                     'begin_date': begin_date, 'end_date': end_date})
     return results

augur/api/metrics/deps.py

@@ -5,10 +5,11 @@
 
 import sqlalchemy as s
 import pandas as pd
-from augur.api.util import register_metric
 import datetime
+from flask import current_app
+
+from augur.api.util import register_metric
 
-from ..server import engine
 
 @register_metric()
 def deps(repo_group_id, repo_id=None, period='day', begin_date=None, end_date=None):
@@ -46,7 +47,7 @@ def deps(repo_group_id, repo_id=None, period='day', begin_date=None, end_date=No
             AND repo_dependencies.repo_id = :repo_id
             """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(depsSQL, conn)    	
 
     else:
@@ -71,7 +72,7 @@ def deps(repo_group_id, repo_id=None, period='day', begin_date=None, end_date=No
             AND repo.repo_group_id = :repo_group_id
             """)
 
-        with engine.connect() as conn:
+        with current_app.engine.connect() as conn:
             results = pd.read_sql(depsSQL, conn)
     return results
 

augur/api/metrics/insight.py

@@ -7,7 +7,7 @@
 import pandas as pd
 from augur.api.util import register_metric
 
-from ..server import engine
+from flask import current_app
 
 @register_metric(type="repo_group_only")
 def top_insights(repo_group_id, num_repos=6):
@@ -29,6 +29,6 @@ def top_insights(repo_group_id, num_repos=6):
             LIMIT :num_repos
         )
     """)
-    with engine.connect() as conn:
+    with current_app.engine.connect() as conn:
         results = pd.read_sql(topInsightsSQL, conn, params={'repo_group_id': repo_group_id, 'num_repos': num_repos})
     return results