hunter integration and refactor

Signed-off-by: Shashank Reddy Boyapally <sboyapal@redhat.com>

Author: shashank-boyapally

README.md

@@ -84,8 +84,12 @@ Orion provides flexibility in configuring its behavior by allowing users to set
 
 For enhanced troubleshooting and debugging, Orion supports the ```--debug``` flag, enabling the generation of detailed debug logs. 
 
+Activate Orion's regression detection tool for performance-scale CPT runs effortlessly with the ```--hunter-analyze``` command. This seamlessly integrates with metadata and hunter, ensuring a robust and efficient regression detection process.
+
 Additionally, users can specify a custom path for the output CSV file using the ```--output``` flag, providing control over the location where the generated CSV will be stored.
 
+
+
 Orion's seamless integration with metadata and hunter ensures a robust regression detection tool for perf-scale CPT runs.
 
 

orion.py

@@ -8,9 +8,11 @@
 import os
 
 import click
-import yaml
 import pandas as pd
+
 from fmatch.matcher import Matcher
+from utils.orion_funcs import run_hunter_analyze, get_metadata, \
+                                set_logging, load_config, get_metric_data
 
 
 @click.group()
@@ -24,7 +26,8 @@ def cli():
 @click.option("--config", default="config.yaml", help="Path to the configuration file")
 @click.option("--output", default="output.csv", help="Path to save the output csv file")
 @click.option("--debug", is_flag=True, help="log level ")
-def orion(config, debug, output):
+@click.option("--hunter-analyze",is_flag=True, help="run hunter analyze")
+def orion(config, debug, output,hunter_analyze):
     """Orion is the cli tool to detect regressions over the runs
 
     Args:
@@ -35,25 +38,22 @@ def orion(config, debug, output):
     level = logging.DEBUG if debug else logging.INFO
     logger = logging.getLogger("Orion")
     logger = set_logging(level, logger)
+    data = load_config(config,logger)
+    ES_URL=None
+
+    if "ES_SERVER" in data.keys():
+        ES_URL = data['ES_SERVER']
+    else:
+        if 'ES_SERVER' in os.environ:
+            ES_URL=os.environ.get("ES_SERVER")
+        else:
+            logger.error("ES_SERVER environment variable/config variable not set")
+            sys.exit(1)
 
-    if "ES_SERVER" not in os.environ:
-        logger.error("ES_SERVER environment variable not set")
-        sys.exit(1)
-
-    try:
-        with open(config, "r", encoding="utf-8") as file:
-            data = yaml.safe_load(file)
-            logger.debug("The %s file has successfully loaded", config)
-    except FileNotFoundError as e:
-        logger.error("Config file not found: %s", e)
-        sys.exit(1)
-    except Exception as e:  # pylint: disable=broad-exception-caught
-        logger.error("An error occurred: %s", e)
-        sys.exit(1)
     for test in data["tests"]:
         metadata = get_metadata(test, logger)
         logger.info("The test %s has started", test["name"])
-        match = Matcher(index="perf_scale_ci", level=level)
+        match = Matcher(index="perf_scale_ci", level=level, ES_URL=ES_URL)
         uuids = match.get_uuid_by_metadata(metadata)
         if len(uuids) == 0:
             print("No UUID present for given metadata")
@@ -77,103 +77,12 @@ def orion(config, debug, output):
             lambda left, right: pd.merge(left, right, on="uuid", how="inner"),
             dataframe_list,
         )
-        match.save_results(merged_df, csv_file_path=output)
-
-
-def get_metric_data(ids, index, metrics, match, logger):
-    """Gets details metrics basked on metric yaml list
+        match.save_results(merged_df, csv_file_path=output.split(".")[0]+"-"+test['name']+".csv")
 
-    Args:
-        ids (list): list of all uuids
-        index (dict): index in es of where to find data
-        metrics (dict): metrics to gather data on
-        match (Matcher): current matcher instance
-        logger (logger): log data to one output
-
-    Returns:
-        dataframe_list: dataframe of the all metrics
-    """
-    dataframe_list = []
-    for metric in metrics:
-        metric_name = metric['name']
-        logger.info("Collecting %s", metric_name)
-        metric_of_interest = metric['metric_of_interest']
-
-        if "agg" in metric.keys():
-            try:
-                cpu = match.get_agg_metric_query(
-                    ids, index, metric
-                )
-                agg_value = metric['agg']['value']
-                agg_type = metric['agg']['agg_type']
-                agg_name = agg_value + "_" + agg_type
-                cpu_df = match.convert_to_df(cpu, columns=["uuid", agg_name])
-                cpu_df = cpu_df.rename(
-                    columns={agg_name: metric_name+ "_" +  agg_name}
-                )
-                dataframe_list.append(cpu_df)
-                logger.debug(cpu_df)
-
-            except Exception as e:  # pylint: disable=broad-exception-caught
-                logger.error(
-                    "Couldn't get agg metrics %s, exception %s",
-                    metric_name,
-                    e,
-                )
-        else:
-            try:
-                podl = match.getResults("", ids, index, metric)
-                podl_df = match.convert_to_df(
-                    podl, columns=["uuid", "timestamp", metric_of_interest]
-                )
-                dataframe_list.append(podl_df)
-                logger.debug(podl_df)
-            except Exception as e:  # pylint: disable=broad-exception-caught
-                logger.error(
-                    "Couldn't get metrics %s, exception %s",
-                    metric_name,
-                    e,
-                )
-    return dataframe_list
-
-def get_metadata(test,logger):
-    """Gets metadata of the run from each test
+        if hunter_analyze:
+            run_hunter_analyze(merged_df,test)
 
-    Args:
-        test (dict): test dictionary
 
-    Returns:
-        dict: dictionary of the metadata
-    """
-    metadata = {}
-    for k,v in test.items():
-        if k in ["metrics","name"]:
-            continue
-        metadata[k] = v
-    metadata["ocpVersion"] = str(metadata["ocpVersion"])
-    logger.debug('metadata' + str(metadata))
-    return metadata
-
-
-def set_logging(level, logger):
-    """sets log level and format
-
-    Args:
-        level (_type_): level of the log
-        logger (_type_): logger object
-
-    Returns:
-        logging.Logger: a formatted and level set logger
-    """
-    logger.setLevel(level)
-    handler = logging.StreamHandler(sys.stdout)
-    handler.setLevel(level)
-    formatter = logging.Formatter(
-        "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
-    )
-    handler.setFormatter(formatter)
-    logger.addHandler(handler)
-    return logger
 
 
 if __name__ == "__main__":

requirements.txt

@@ -1,14 +1,47 @@
+astroid==3.0.2
 certifi==2023.11.17
+charset-normalizer==3.3.2
 click==8.1.7
+dateparser==1.2.0
+DateTime==5.4
+decorator==5.1.1
+dill==0.3.7
 elastic-transport==8.11.0
 elasticsearch==8.11.1
 elasticsearch7==7.13.0
+expandvars==0.6.5
+gevent==23.9.1
+greenlet==3.0.3
+hunter @ git+https://github.com/datastax-labs/hunter.git@8ff166979d000780ad548e49f006ef2a15d54123
+idna==3.6
+isort==5.13.2
+mccabe==0.7.0
+more-itertools==8.14.0
+numpy==1.24.0
 fmatch==0.0.4
-numpy==1.26.3
 pandas==2.1.4
+platformdirs==4.1.0
+pylint==3.0.3
+pystache==0.6.5
 python-dateutil==2.8.2
 pytz==2023.3.post1
 PyYAML==6.0.1
+regex==2023.12.25
+requests==2.31.0
+ruamel.yaml==0.17.21
+ruamel.yaml.clib==0.2.8
+scipy==1.12.0
+signal-processing-algorithms==1.3.5
 six==1.16.0
+slack_sdk==3.26.2
+structlog==19.2.0
+tabulate==0.8.10
+tomlkit==0.12.3
+typed-ast==1.5.5
+typing-extensions==3.10.0.2
 tzdata==2023.4
+tzlocal==5.2
 urllib3==1.26.18
+validators==0.18.2
+zope.event==5.0
+zope.interface==6.1

setup.py

@@ -2,7 +2,7 @@
 """
 setup.py for orion cli tool
 """
-from setuptools import setup
+from setuptools import setup, find_packages
 
 setup(
     name='orion',
@@ -17,6 +17,8 @@
             'orion = orion:orion',
         ],
     },
+    packages=find_packages(),
+    package_data={'utils': ['utils.py'],'hunter': ['*.py']},
     classifiers=[
         'Programming Language :: Python :: 3',
         'License :: OSI Approved :: MIT License',