From ae73a39b12cd8318eb2dd7b88a51c35e50dfb052 Mon Sep 17 00:00:00 2001
From: Shashank Reddy Boyapally <sboyapal@redhat.com>
Date: Mon, 25 Mar 2024 23:49:27 -0400
Subject: [PATCH] changed accordingly to fmatch 0.0.6, and filtering
 changepoints

Signed-off-by: Shashank Reddy Boyapally <sboyapal@redhat.com>
---
 pkg/daemon.py  | 28 ++++++++++++++++++++--------
 pkg/runTest.py |  2 +-
 pkg/utils.py   | 27 +++++++++++++++------------
 3 files changed, 36 insertions(+), 21 deletions(-)

diff --git a/pkg/daemon.py b/pkg/daemon.py
index 0c2ad4d..c4d80cb 100644
--- a/pkg/daemon.py
+++ b/pkg/daemon.py
@@ -1,6 +1,7 @@
 """
 Module to run orion in daemon mode
 """
+
 import logging
 import shutil
 import os
@@ -15,7 +16,12 @@
 
 
 @app.post("/daemon")
-async def daemon(file: UploadFile = File(...), uuid: str = "", baseline: str = ""):
+async def daemon(
+    file: UploadFile = File(...),
+    uuid: str = "",
+    baseline: str = "",
+    filter_changepoints="",
+):
     """starts listening on port 8000 on url /daemon
 
     Args:
@@ -28,15 +34,21 @@ async def daemon(file: UploadFile = File(...), uuid: str = "", baseline: str = "
     new_file_name = f"{file_name}_copy{file_extension}"
     with open(new_file_name, "wb") as buffer:
         shutil.copyfileobj(file.file, buffer)
-    argDict={
-        'config': new_file_name,
-        'output_path': "output.csv",
-        'hunter_analyze': True,
-        'output_format': "json",
-        'uuid':uuid,
-        'baseline':baseline,
+    argDict = {
+        "config": new_file_name,
+        "output_path": "output.csv",
+        "hunter_analyze": True,
+        "output_format": "json",
+        "uuid": uuid,
+        "baseline": baseline,
     }
+    filter_changepoints = (
+        True if filter_changepoints == "true" else False # pylint: disable = R1719
+    )
     result = runTest.run(**argDict)
+    if filter_changepoints:
+        for key, value in result.items():
+            result[key] = list(filter(lambda x: x.get("is_changepoint", False), value))
     try:
         os.remove(new_file_name)
     except OSError as e:
diff --git a/pkg/runTest.py b/pkg/runTest.py
index c355f59..661af6e 100644
--- a/pkg/runTest.py
+++ b/pkg/runTest.py
@@ -33,7 +33,7 @@ def run(**kwargs):
         )
         if kwargs["hunter_analyze"]:
             testname, result_data = run_hunter_analyze(
-                result, test, output=kwargs["output_format"], matcher=match
+                result, test, output=kwargs["output_format"]
             )
             result_output[testname] = result_data
     return result_output
diff --git a/pkg/utils.py b/pkg/utils.py
index b38054c..4db3163 100644
--- a/pkg/utils.py
+++ b/pkg/utils.py
@@ -16,6 +16,7 @@
 
 from hunter.report import Report, ReportType
 from hunter.series import Metric, Series
+import pyshorteners
 
 from pkg.logrus import SingletonLogger
 
@@ -23,7 +24,7 @@
 
 
 
-def run_hunter_analyze(merged_df, test, output, matcher):
+def run_hunter_analyze(merged_df, test, output):
     """Start hunter analyze function
 
     Args:
@@ -35,15 +36,15 @@ def run_hunter_analyze(merged_df, test, output, matcher):
     metrics = {
         column: Metric(1, 1.0)
         for column in merged_df.columns
-        if column not in ["uuid", "timestamp"]
+        if column not in ["uuid","timestamp","buildUrl"]
     }
     data = {
         column: merged_df[column]
         for column in merged_df.columns
-        if column not in ["uuid", "timestamp"]
+        if column not in ["uuid","timestamp","buildUrl"]
     }
     attributes = {
-        column: merged_df[column] for column in merged_df.columns if column in ["uuid"]
+        column: merged_df[column] for column in merged_df.columns if column in ["uuid","buildUrl"]
     }
     series = Series(
         test_name=test["name"],
@@ -63,12 +64,12 @@ def run_hunter_analyze(merged_df, test, output, matcher):
 
     if output == "json":
         change_points_by_metric = series.analyze().change_points
-        output_json = parse_json_output(merged_df, change_points_by_metric,matcher=matcher)
+        output_json = parse_json_output(merged_df, change_points_by_metric)
         return test["name"], output_json
     return None
 
 
-def parse_json_output(merged_df, change_points_by_metric,matcher):
+def parse_json_output(merged_df, change_points_by_metric):
     """json output generator function
 
     Args:
@@ -84,11 +85,8 @@ def parse_json_output(merged_df, change_points_by_metric,matcher):
     for index, entry in enumerate(df_json):
         entry["metrics"] = {
             key: {"value": entry.pop(key), "percentage_change": 0}
-            for key in entry.keys() - {"uuid", "timestamp"}
+            for key in entry.keys() - {"uuid", "timestamp", "buildUrl"}
         }
-        entry["buildUrl"] = matcher.get_metadata_by_uuid(entry.get("uuid")).get(
-            "buildUrl"
-        )
         entry["is_changepoint"] = False
 
     for key in change_points_by_metric.keys():
@@ -261,7 +259,9 @@ def process_test(test, match, output, uuid, baseline):
     else:
         metadata = filter_metadata(uuid,match)
     logger_instance.info("The test %s has started", test["name"])
-    uuids = match.get_uuid_by_metadata(metadata)
+    runs = match.get_uuid_by_metadata(metadata)
+    uuids = [run["uuid"] for run in runs]
+    buildUrls = {run["uuid"]: run["buildUrl"] for run in runs}
     if baseline in ('', None):
         uuids = match.get_uuid_by_metadata(metadata)
         if len(uuids) == 0:
@@ -279,7 +279,10 @@ def process_test(test, match, output, uuid, baseline):
         lambda left, right: pd.merge(left, right, on="uuid", how="inner"),
         dataframe_list,
     )
-
+    shortener = pyshorteners.Shortener()
+    merged_df["buildUrl"] = merged_df["uuid"].apply(
+            lambda uuid: shortener.tinyurl.short(buildUrls[uuid]) #pylint: disable = cell-var-from-loop
+        )
     output_file_path = output.split(".")[0] + "-" + test["name"] + ".csv"
     match.save_results(merged_df, csv_file_path=output_file_path)
     return merged_df