Adding Apache Superset to openctest framework

core/README.md

@@ -14,13 +14,15 @@ A prototype for generating and running ctests. Below are the projects we current
 - Hbase 2.2.2: `hbase-server`.
 - ZooKeeper 3.5.6: `zookeeper-server`.
 - Alluxio 2.1.0: `core`.
+- Superset 3.0.2: `superset-websocket`.
 
 We also provided our instrumented versions of the above projects:
 
 - Hadoop 2.8.5: https://github.com/xlab-uiuc/hadoop
 - Hbase 2.2.2: https://github.com/xlab-uiuc/hbase
 - ZooKeeper 3.5.6: https://github.com/xlab-uiuc/zookeeper
 - Alluxio 2.1.0: https://github.com/xlab-uiuc/alluxio
+- Superset 3.0.2: https://github.com/ishitakarna/superset
 
 Our instrumented version projects have two branches: 
 - `ctest-injection`: branch with "Intercept Configuration API" instrumentation (See `ADDING_NEW_PROJECT.md`). This branch is used by `generate_ctest` and `run_ctest`.
@@ -59,7 +61,7 @@ To generate ctests or run ctest, you need to first clone the target project.
 1. In `openctest/core`, run `./add_project.sh <main project>` to clone the project, switch to and build the branch `ctest-injection`. This branch will be later used by `generate_ctest` and `run_ctest`.
 2. In `openctest/core/identify_param`, run `./add_project.sh <main project>` to clone the project, switch to and build the branch `ctest-logging`. This branch will be later used by `identify_param`.
 
-`<main project>` can be `hadoop`, `hbase`, `zookeeper` or `alluxio`.
+`<main project>` can be `hadoop`, `hbase`, `zookeeper`, `alluxio`, or `superset`.
 
 ## Usage
 

core/add_project.sh

@@ -48,6 +48,13 @@ function setup_alluxio() {
     mvn clean install -DskipTests -Dcheckstyle.skip -Dlicense.skip -Dfindbugs.skip -Dmaven.javadoc.skip=true
 }
 
+function setup_superset() {
+    [ ! -d "app/superset" ] && git clone https://github.com/ishitakarna/superset app/superset
+    cd app/superset
+    git fetch && git checkout ctest
+    npm install
+}
+
 function usage() {
     echo "Usage: add_project.sh <main project>"
     exit 1
@@ -64,6 +71,7 @@ function main() {
             hbase) setup_hbase ;;
             zookeeper) setup_zookeeper ;;
             alluxio) setup_alluxio ;;
+            superset) setup_superset ;;
             *) echo "Unexpected project: $project - only support hadoop, hbase, zookeeper and alluxio." ;;
         esac
     fi

core/default_configs/superset-default.tsv

@@ -0,0 +1,23 @@
+gcChannelsIntervalMs	120000	Time interval for garbage collecting inactive channels
+jwtAlgorithms.0	HS256	First algorithm used for JSON Web Token (JWT) encoding/decoding
+jwtChannelIdKey	channel	Key name in JWT for identifying the channel
+jwtCookieName	test-async-token	Name of the cookie used for storing the JWT
+jwtSecret	test123-test123-test123-test123-test123-test123-test123	This is the secret key used for signing JSON Web Tokens (JWTs)
+logFilename	app.log	Name of the file where logs are written
+logLevel	info	Severity level of the logs being recorded (e.g., info, debug)
+logToFile	FALSE	Boolean indicating whether to log to a file (true) or not (false)
+pingSocketsIntervalMs	20000	Interval for pinging sockets to check their connectivity
+port	8125	Network port used for connecting
+redis.db	10	This parameter specifies the database number to be used in the Redis data store
+redis.host	127.0.0.1	This parameter specifies the hostname or IP address of the Redis server
+redis.password	some pwd	This is the password used for authentication to the Redis server
+redis.port	6379	This defines the port number on which the Redis server is running and accepting connections
+redis.ssl	FALSE	A boolean parameter indicating whether SSL encryption should be used for the connection to the Redis server
+redis.username	default	Username for authenticating with the Redis server
+redis.validateHostname	TRUE	Boolean indicating whether to validate the Redis server's hostname
+redisStreamPrefix	test-async-events-	Prefix for Redis stream keys
+redisStreamReadBlockMs	5000	Time in milliseconds to block when reading from a Redis stream
+redisStreamReadCount	100	Number of messages to read from a Redis stream in one go
+socketResponseTimeoutMs	60000	Timeout in milliseconds for socket responses
+statsd.host	127.0.0.1	This is the hostname or IP address of the StatsD server
+statsd.port	8125	This parameter specifies the port number on which the StatsD server is listening

core/generate_ctest/gen_ctest.py

@@ -0,0 +1,91 @@
+import subprocess
+import csv
+import json
+import os
+
+
+def read_tsv(file_path):
+    params = {}
+    with open(file_path) as file:
+        reader = csv.reader(file, delimiter='\t')
+        for row in reader:
+            param, *values = row
+            params[param] = values
+    return params
+
+
+def read_json(file_path):
+    with open(file_path) as file:
+        return json.load(file)
+
+
+def run_test_case(param, value, test_cases, report):
+    for test_case in test_cases:
+        test_file, test_name = test_case.split(": ")
+        test_name = test_name.replace('_', ' ')
+        test_file_path = f"/home/ikarna2/project/fork/superset/superset-websocket/spec{test_file}"
+
+
+        # Generate the JSON configuration command
+        gen_json_cmd = ["python3", "gen_json.py", param, value, "config.test.override.json"]
+        print("Executing command:", ' '.join(gen_json_cmd))
+        subprocess.run(gen_json_cmd)
+
+        # Run the test case command
+        test_cmd = ["python3", "ctest_runner_json_override.py", "config.test.override.json",
+            "/home/ikarna2/project/fork/superset/superset-websocket", test_file_path, f'"{test_name}"']
+        print("Executing command:", ' '.join(test_cmd))
+        result = subprocess.run(test_cmd, capture_output=True, text=True)
+
+
+        # Process the result
+        if result.returncode == 0:
+            test_result = 'p'
+        else:
+            test_result = 'f'
+
+        # Assuming the execution time is part of the result output
+        execution_time = extract_execution_time(result.stdout)
+
+
+        report.append([param, test_case, value, test_result, execution_time])
+
+
+
+
+def extract_execution_time(output):
+    # Extract execution time from the output
+    # Placeholder for actual implementation
+    return "time_placeholder"
+
+
+def write_report(report, file_path):
+    with open(file_path, 'w', newline='') as file:
+        writer = csv.writer(file)
+        for row in report:
+            writer.writerow(row)
+
+
+def main():
+    tsv_file = 'default_params.tsv'  # Placeholder for TSV file path
+    json_file = 'flattened_params_to_tests.json'  # Placeholder for JSON file path
+    report_file = 'test_report.csv'
+
+
+    params = read_tsv(tsv_file)
+    test_mapping = read_json(json_file)
+    report = []
+
+
+    for param, values in params.items():
+        test_cases = test_mapping.get(param, [])
+        for value in values:
+            if value != 'SKIP':
+                run_test_case(param, value, test_cases, report)
+
+
+    write_report(report, report_file)
+
+
+if __name__ == "__main__":
+    main()

core/generate_ctest/gen_json.py

@@ -0,0 +1,61 @@
+import json
+import sys
+
+
+def create_json_from_flattened_key(key, value):
+    parts = key.split('.')
+    json_obj = {}
+    current_level = json_obj
+
+
+    for i, part in enumerate(parts):
+        is_last_part = i == len(parts) - 1
+
+
+        if part.isdigit():  # If part is a number, handle as a list
+            part = int(part)
+            # Ensure current level is a list
+            if not isinstance(current_level, list):
+                current_level = []
+            # Expand the list if necessary
+            while len(current_level) <= part:
+                current_level.append({} if not is_last_part else None)
+            if is_last_part:
+                current_level[part] = value
+            else:
+                current_level = current_level[part]
+        else:  # Handle as a dict
+            if part not in current_level:
+                current_level[part] = [] if (i+1 < len(parts) and parts[i+1].isdigit()) else {}
+            if is_last_part:
+                current_level[part] = value
+            else:
+                current_level = current_level[part]
+
+
+    return json_obj
+
+
+def write_json_to_file(json_data, filename):
+    with open(filename, 'w') as file:
+        json.dump(json_data, file, indent=4)
+
+
+def main():
+    if len(sys.argv) != 4:
+        print("Usage: script.py <flattened_key> <value> <output_file>")
+        sys.exit(1)
+
+
+    flattened_key = sys.argv[1]
+    value = sys.argv[2]
+    output_file = sys.argv[3]
+
+
+    json_data = create_json_from_flattened_key(flattened_key, value)
+    write_json_to_file(json_data, output_file)
+    print(f"JSON data written to {output_file}")
+
+
+if __name__ == "__main__":
+    main()