From 0e45735e8b72a7e2cf12e9b30b0161b2e63db305 Mon Sep 17 00:00:00 2001
From: Neïl Zaim <49716072+NeilZaim@users.noreply.github.com>
Date: Tue, 13 Jun 2023 19:52:57 +0200
Subject: Add python script to update benchmarks from Azure output (#2355)

* Add python script to update benchmarks from Azure output

* Update Regression/Checksum/update_benchmarks_from_azure_output.py

Co-authored-by: Edoardo Zoni <59625522+EZoni@users.noreply.github.com>

* Cleaner python script

* Remove empirical numbers and read and write the json files once

* Also read dashes in test names

* Move script to Tools/DevUtils folder

* Add documentation

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Directly parse the new file

* Apply suggestions from code review

Co-authored-by: Roelof Groenewald <40245517+roelof-groenewald@users.noreply.github.com>

---------

Co-authored-by: Edoardo Zoni <59625522+EZoni@users.noreply.github.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Roelof Groenewald <40245517+roelof-groenewald@users.noreply.github.com>
---
 .../update_benchmarks_from_azure_output.py         | 65 ++++++++++++++++++++++
 1 file changed, 65 insertions(+)
 create mode 100644 Tools/DevUtils/update_benchmarks_from_azure_output.py

(limited to 'Tools/DevUtils/update_benchmarks_from_azure_output.py')

diff --git a/Tools/DevUtils/update_benchmarks_from_azure_output.py b/Tools/DevUtils/update_benchmarks_from_azure_output.py
new file mode 100644
index 000000000..28c3dc6b5
--- /dev/null
+++ b/Tools/DevUtils/update_benchmarks_from_azure_output.py
@@ -0,0 +1,65 @@
+# Copyright 2023 Neil Zaim
+#
+# This file is part of WarpX.
+#
+# License: BSD-3-Clause-LBNL
+
+import json
+import re
+import sys
+
+'''
+This Python script updates the Azure benchmarks automatically using a raw Azure output textfile
+that is given as the first and only argument of the script.
+
+In the Azure output, we read the lines contained between
+"New file for Test_Name:"
+and the next occurrence of
+"'----------------'"
+And use these lines to update the benchmarks
+'''
+
+azure_output_filename = sys.argv[1]
+
+pattern_test_name = 'New file for (?P<testname>[\w\-]*)'
+closing_string = '----------------'
+benchmark_path = "../../Regression/Checksum/benchmarks_json/"
+benchmark_suffix = ".json"
+
+first_line_read = False
+current_test = ""
+
+with open(azure_output_filename, "r") as f:
+    for line in f:
+
+        if current_test == "":
+            # Here we search lines that read, for example,
+            # "New file for LaserAcceleration_BTD"
+            # and we set current_test = "LaserAcceleration_BTD"
+            match_test_name = re.search(pattern_test_name, line)
+            if match_test_name:
+                current_test = match_test_name.group('testname')
+                new_file_string = ""
+
+        else:
+            # We add each line to the new file string until we find the line containing
+            # "----------------"
+            # which indicates that we have read the new file entirely
+
+            if not closing_string in line:
+                if not first_line_read:
+                    # Raw Azure output comes with a prefix at the beginning of each line that we do
+                    # not need here. The first line that we will read is the prefix followed by the
+                    # "{" character, so we determine how long the prefix is by finding the last
+                    # occurence of the "{" character in this line.
+                    azure_indent = line.rfind('{')
+                    first_line_read = True
+                new_file_string += line[azure_indent:]
+
+            else:
+                # We have read the new file entirely. Dump it in the json file.
+                new_file_json = json.loads(new_file_string)
+                json_filepath = benchmark_path+current_test+benchmark_suffix
+                with open(json_filepath, "w") as f_json:
+                    json.dump(new_file_json, f_json, indent=2)
+                current_test = ""
-- 
cgit v1.2.3