Release 0.76.0

.github/workflows/docker-image.yml

@@ -0,0 +1,18 @@
+name: Docker Image CI
+
+on:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    branches: [ "main" ]
+
+jobs:
+
+  build:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v3
+    - name: Build the Docker image
+      run: docker build . --file Dockerfile --tag my-image-name:$(date +%s)

Makefile

@@ -3,6 +3,7 @@
 default:
 	@ echo "Installation Commands:"
 	@ echo "    install                         Installs Augur's full stack for production"
+	@ echo "    wizard                          Install Augur and launch the graphical setup wizard"
 	@ echo "    clean                           Removes potentially troublesome compiled files"
 	@ echo "    rebuild                         Removes build/compiled files & binaries and reinstalls the project"
 	@ echo
@@ -34,6 +35,9 @@ default:
 install:
 	@ ./scripts/install/install.sh dev
 
+wizard:
+	@ ./scripts/install/install.sh graphical
+
 install-spdx:
 	@ ./scripts/install/install-spdx.sh
 

README.md

@@ -1,4 +1,4 @@
-# Augur NEW Release v0.71.0
+# Augur NEW Release v0.76.0
 
 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/v0.71.0  
+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/v0.76.0  
 
 - 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.

augur/api/view/server/Environment.py

@@ -1,4 +1,4 @@
 import os
 
 class Environment:
     """
@@ -31,7 +31,7 @@
                 result[arg] = self[arg]
         return result
 
     def as_type(self, type, key):
         if self[key]:
             return type(self[key])
         return None
@@ -49,4 +49,4 @@
         return str(os.environ)
 
     def __iter__(self):
-        return (item for item in os.environ.items)
+        return (item for item in os.environ.items())

augur/api/view/server/__init__.py

@@ -1,3 +1,2 @@
-from .Environment import Environment
-from .ServerThread import ServerThread
 from .LoginException import LoginException
+from .Environment import Environment

augur/application/cli/backend.py

@@ -43,7 +43,7 @@
 @test_db_connection
 @with_database
 @click.pass_context
 def start(ctx, disable_collection, development, port):
     """Start Augur's backend server."""
 
     try:
@@ -73,13 +73,13 @@
     worker_vmem_cap = get_value("Celery", 'worker_process_vmem_cap')
 
     gunicorn_command = f"gunicorn -c {gunicorn_location} -b {host}:{port} augur.api.server:app --log-file gunicorn.log"
     server = subprocess.Popen(gunicorn_command.split(" "))
 
     time.sleep(3)
     logger.info('Gunicorn webserver started...')
     logger.info(f'Augur is running at: {"http" if development else "https"}://{host}:{port}')
 
     processes = start_celery_worker_processes(float(worker_vmem_cap), disable_collection)
 
     if os.path.exists("celerybeat-schedule.db"):
             logger.info("Deleting old task schedule")
@@ -88,7 +88,7 @@
     log_level = get_value("Logging", "log_level")
     celery_beat_process = None
     celery_command = f"celery -A augur.tasks.init.celery_app.celery_app beat -l {log_level.lower()}"
     celery_beat_process = subprocess.Popen(celery_command.split(" "))    
 
     if not disable_collection:
 
@@ -154,7 +154,7 @@
 
     frontend_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency=1 -n frontend:{uuid.uuid4().hex}@%h -Q frontend"
     max_process_estimate -= 1
     process_list.append(subprocess.Popen(frontend_worker.split(" ")))
     sleep_time += 6
 
     if not disable_collection:
@@ -162,25 +162,25 @@
         #2 processes are always reserved as a baseline.
         scheduling_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency=2 -n scheduling:{uuid.uuid4().hex}@%h -Q scheduling"
         max_process_estimate -= 2
         process_list.append(subprocess.Popen(scheduling_worker.split(" ")))
         sleep_time += 6
 
         #60% of estimate, Maximum value of 45 : Reduced because it can be lower
-        core_num_processes = determine_worker_processes(.15, 10)
+        core_num_processes = determine_worker_processes(.40, 50)
         logger.info(f"Starting core worker processes with concurrency={core_num_processes}")
         core_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency={core_num_processes} -n core:{uuid.uuid4().hex}@%h"
         process_list.append(subprocess.Popen(core_worker.split(" ")))
         sleep_time += 6
 
         #20% of estimate, Maximum value of 25
-        secondary_num_processes = determine_worker_processes(.70, 60)
+        secondary_num_processes = determine_worker_processes(.39, 50)
         logger.info(f"Starting secondary worker processes with concurrency={secondary_num_processes}")
         secondary_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency={secondary_num_processes} -n secondary:{uuid.uuid4().hex}@%h -Q secondary"
         process_list.append(subprocess.Popen(secondary_worker.split(" ")))
         sleep_time += 6
 
         #15% of estimate, Maximum value of 20
-        facade_num_processes = determine_worker_processes(.15, 20)
+        facade_num_processes = determine_worker_processes(.17, 20)
         logger.info(f"Starting facade worker processes with concurrency={facade_num_processes}")
         facade_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency={facade_num_processes} -n facade:{uuid.uuid4().hex}@%h -Q facade"
 
@@ -308,7 +308,7 @@
         SET facade_status='Pending', facade_task_id=NULL
         WHERE facade_status='Failed Clone' OR facade_status='Initializing';
     """))
     #TODO: write timestamp for currently running repos.
 
 def assign_orphan_repos_to_default_user(session):
     query = s.sql.text("""

augur/application/cli/collection.py

@@ -125,21 +125,21 @@ def determine_worker_processes(ratio,maximum):
     sleep_time += 6
 
     #60% of estimate, Maximum value of 45: Reduced because not needed
-    core_num_processes = determine_worker_processes(.15, 10)
+    core_num_processes = determine_worker_processes(.40, 50)
     logger.info(f"Starting core worker processes with concurrency={core_num_processes}")
     core_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency={core_num_processes} -n core:{uuid.uuid4().hex}@%h"
     process_list.append(subprocess.Popen(core_worker.split(" ")))
     sleep_time += 6
 
     #20% of estimate, Maximum value of 25
-    secondary_num_processes = determine_worker_processes(.70, 60)
+    secondary_num_processes = determine_worker_processes(.39, 50)
     logger.info(f"Starting secondary worker processes with concurrency={secondary_num_processes}")
     secondary_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency={secondary_num_processes} -n secondary:{uuid.uuid4().hex}@%h -Q secondary"
     process_list.append(subprocess.Popen(secondary_worker.split(" ")))
     sleep_time += 6
 
     #15% of estimate, Maximum value of 20
-    facade_num_processes = determine_worker_processes(.15, 20)
+    facade_num_processes = determine_worker_processes(.17, 20)
     logger.info(f"Starting facade worker processes with concurrency={facade_num_processes}")
     facade_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency={facade_num_processes} -n facade:{uuid.uuid4().hex}@%h -Q facade"
 

augur/application/cli/config.py

@@ -7,6 +7,7 @@
 import json
 import logging
 
+from augur.application.db.models import Config
 from augur.application.db.session import DatabaseSession
 from augur.application.config import AugurConfig
 from augur.application.cli import DatabaseContext, test_connection, test_db_connection, with_database
@@ -160,7 +161,7 @@ def add_section(ctx, section_name, file):
 @click.option('--section', required=True)
 @click.option('--setting', required=True)
 @click.option('--value', required=True)
-@click.option('--data-type', required=True)
+@click.option('--data-type')
 @test_connection
 @test_db_connection
 @with_database
@@ -169,6 +170,12 @@ def config_set(ctx, section, setting, value, data_type):
 
     with DatabaseSession(logger, engine=ctx.obj.engine) as session:
         config = AugurConfig(logger, session)
+
+        if not data_type:
+            result = session.query(Config).filter(Config.section_name == section, Config.setting_name == setting).all()
+            if not result:
+                return click.echo("You must specify a data-type if the setting does not already exist")
+            data_type = result[0].type
 
         if data_type not in config.accepted_types:
             print(f"Error invalid type for config. Please use one of these types: {config.accepted_types}")
@@ -218,6 +225,22 @@ def config_get(ctx, section, setting):
             else:
                 print(f"Error: {section} section not found in config")
 
+@cli.command('get_all_json')
+def config_get_all_json():
+    data = {}
+    try:
+        with DatabaseSession(logger) as session:
+            sections = session.query(Config.section_name).distinct().all()
+            for section in sections:
+                data[section[0]] = {}
+
+            for row in session.query(Config).all():
+                data[row.section_name][row.setting_name] = row.value
+    except:
+        pass
+
+    print(json.dumps(data, indent=4))
+
 @cli.command('clear')
 @test_connection
 @test_db_connection

augur/application/cli/tasks.py

@@ -36,8 +36,8 @@ def start():
     secondary_worker_process = None
 
     scheduling_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency=1 -n scheduling:{uuid.uuid4().hex}@%h -Q scheduling"
-    core_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency=20 -n core:{uuid.uuid4().hex}@%h"
-    secondary_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency=60 -n secondary:{uuid.uuid4().hex}@%h -Q secondary"
+    core_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency=50 -n core:{uuid.uuid4().hex}@%h"
+    secondary_worker = f"celery -A augur.tasks.init.celery_app.celery_app worker -l info --concurrency=50 -n secondary:{uuid.uuid4().hex}@%h -Q secondary"
 
     scheduling_worker_process = subprocess.Popen(scheduling_worker.split(" "))
     core_worker_process = subprocess.Popen(core_worker.split(" "))

augur/application/config.py

@@ -161,7 +161,7 @@ def get_section(self, section_name) -> dict:
         Returns:
             The section data as a dict
         """
-        query = self.session.query(Config).filter_by(section_name=section_name)
+        query = self.session.query(Config).filter_by(section_name=section_name).order_by(Config.setting_name.asc())
         section_data = execute_session_query(query, 'all')
 
         section_dict = {}
@@ -213,7 +213,7 @@ def load_config(self) -> dict:
             The config from the database
         """
         # get all the sections in the config table
-        query = self.session.query(Config.section_name)
+        query = self.session.query(Config.section_name).order_by(Config.section_name.asc())
         section_names = execute_session_query(query, 'all')
 
         config = {}

augur/application/db/lib.py

@@ -9,7 +9,7 @@
 from psycopg2.errors import DeadlockDetected
 from typing import List, Any, Optional, Union
 
-from augur.application.db.models import Config, Repo, Commit, WorkerOauth, Issue, PullRequest, PullRequestReview, ContributorsAlias,    UnresolvedCommitEmail, Contributor, CollectionStatus
+from augur.application.db.models import Config, Repo, Commit, WorkerOauth, Issue, PullRequest, PullRequestReview, ContributorsAlias,UnresolvedCommitEmail, Contributor, CollectionStatus
 from augur.tasks.util.collection_state import CollectionState
 from augur.application.db import get_session, get_engine
 from augur.application.db.util import execute_session_query
@@ -25,7 +25,7 @@ def convert_type_of_value(config_dict, logger=None):
     if data_type == "str" or data_type is None:
         return config_dict
 
-    elif data_type == "int":
+    if data_type == "int":
         config_dict["value"] = int(config_dict["value"])
 
     elif data_type == "bool":
@@ -509,4 +509,31 @@ def update_issue_closed_cntrbs_by_repo_id(repo_id):
                 WHERE issue_id = :issue_id
                 AND repo_id = :repo_id
             """)
-            connection.execute(update_stmt, update_data)
+            connection.execute(update_stmt, update_data)
+
+def get_core_data_last_collected(repo_id):
+
+    with get_session() as session:
+        try:
+           return session.query(CollectionStatus).filter(CollectionStatus.repo_id == repo_id).one().core_data_last_collected 
+        except s.orm.exc.NoResultFound:
+            return None
+
+def get_secondary_data_last_collected(repo_id):
+
+    with get_session() as session:
+        try:
+           return session.query(CollectionStatus).filter(CollectionStatus.repo_id == repo_id).one().secondary_data_last_collected 
+        except s.orm.exc.NoResultFound:
+            return None
+
+def get_updated_prs(repo_id, since):
+
+    with get_session() as session:
+        return session.query(PullRequest).filter(PullRequest.repo_id == repo_id, PullRequest.pr_updated_at >= since).order_by(PullRequest.pr_src_number).all()
+
+def get_updated_issues(repo_id, since):
+
+    with get_session() as session:
+        return session.query(Issue).filter(Issue.repo_id == repo_id, Issue.updated_at >= since).order_by(Issue.gh_issue_number).all()
+

augur/static/css/first_time.css

@@ -1,50 +1,102 @@
+:root {
+    --color-bg: #1A233A;
+    --color-bg-light: #272E48;
+    --color-bg-contrast: #646683;
+    --color-fg: white;
+    --color-fg-dark: #b0bdd6;
+    --color-fg-contrast: black;
+    --color-accent: #6f42c1;
+    --color-accent-dark: #6134b3;
+    --color-notice: #00ddff;
+    --color-notice-contrast: #006979;
+}
+
 body{
     margin-top:20px;
-    color: #bcd0f7;
-    background: #1A233A;
+    background-color: var(--color-bg);
+    color: var(--color-fg);
 }
+
 h1 {
     font-size: 2rem;
 }
+
 .sidebar .sidebar-top {
     margin: 0 0 1rem 0;
     padding-bottom: 1rem;
     text-align: center;
 }
+
 .sidebar .sidebar-top .brand-logo {
     margin: 0 0 1rem 0;
 }
+
 .sidebar .sidebar-top .brand-logo img {
     height: 90px;
     -webkit-border-radius: 100px;
     -moz-border-radius: 100px;
     border-radius: 100px;
 }
+
 .sidebar .about {
     margin: 1rem 0 0 0;
     font-size: 0.8rem;
     text-align: center;
 }
+
+.subtitle {
+    color: var(--color-fg-dark);
+    margin-bottom: .5rem;
+    margin-left: 15px;
+}
+
+.no-margin-bottom {
+    margin-bottom: 0;
+}
+
 .card {
-    background: #272E48;
+    background: var(--color-bg-light);
     -webkit-border-radius: 5px;
     -moz-border-radius: 5px;
     border-radius: 5px;
     border: 0;
     margin-bottom: 1rem;
 }
+
 .form-control {
     border: 1px solid #596280;
     -webkit-border-radius: 2px;
     -moz-border-radius: 2px;
     border-radius: 2px;
     font-size: .825rem;
-    background: #1A233A;
-    color: #bcd0f7;
+    background: var(--color-bg-light);
+    color: var(--color-fg);
+}
+
+.input-textbox {
+    color: var(--color-fg);
+    background-color: var(--color-bg);
+    border-color: var(--color-accent-dark);
 }
+
+.input-textbox::placeholder {
+    color: var(--color-fg-dark);
+}
+
+.input-textbox:focus {
+    color: var(--color-fg);
+    background-color: var(--color-bg);
+    border-color: var(--color-accent-dark);
+}
+
+.input-textbox:focus::placeholder {
+    color: var(--color-fg-dark);
+}
+
 .modal-content {
-    color: black;
+    color: var(--color-fg-contrast);
 }
+
 .editor-container {
     height: 300px !important;
 }

augur/tasks/data_analysis/__init__.py

@@ -1,7 +1,7 @@
 from celery import chain
 import logging 
 
-def machine_learning_phase(repo_git):
+def machine_learning_phase(repo_git, full_collection):
     from augur.tasks.data_analysis.clustering_worker.tasks import clustering_task
     from augur.tasks.data_analysis.discourse_analysis.tasks import discourse_analysis_task
     from augur.tasks.data_analysis.insight_worker.tasks import insight_task
@@ -15,7 +15,7 @@ def machine_learning_phase(repo_git):
     ml_tasks.append(discourse_analysis_task.si(repo_git))
     ml_tasks.append(insight_task.si(repo_git))
     ml_tasks.append(message_insight_task.si(repo_git))
-    ml_tasks.append(pull_request_analysis_task.si(repo_git)) 
+    #ml_tasks.append(pull_request_analysis_task.si(repo_git)) 
 
     logger.info(f"Machine learning sequence: {ml_tasks}")
     return chain(*ml_tasks)

augur/tasks/data_analysis/clustering_worker/setup.py

@@ -22,13 +22,13 @@ def read(filename):
     packages=find_packages(),
     install_requires=[
         'Flask==2.0.2',
-        'Flask-Cors==3.0.10',
+        'Flask-Cors==4.0.1',
         'Flask-Login==0.5.0',
         'Flask-WTF==1.0.0',
-        'requests==2.28.0',
+        'requests==2.32.0',
         'psycopg2-binary==2.9.3',
         #'sklearn==0.0.0',
-        'scikit-learn==1.1.3',
+        'scikit-learn==1.5.0',
         'numpy==1.26.0',
         'nltk==3.6.6',
         'seaborn==0.11.1',