Hello all,

I know Aaron and I had talked a little bit about the script for this and how we were going to handle it during the CI meeting, so I figured I would raise this on the mailing list so anyone could provide input. One of the points we had mentioned was whether this was something we wanted to use pwclient or instead make it a separate script that is just dedicated to collecting retest requests. I'm not completely sure which one would be the better option, but as I mentioned during the meeting I did write a little bit of a draft for a dedicated script that I thought might be something that would be good to bring up. The below code is just a simple python script that allows you to pass in the name of contexts you would like to collect for retesting and it just follows the event schema listed in the previous email. The thought process with this is every lab could maintain a list of labels they would like to capture and the timestamp since the last time they ran the script and gathered retesting requests and use that to run this script periodically.

There are a couple of things to consider with this script before it is completely polished like where to send the output and how people want to handle it, or if we even want to use it rather than just use pwclient and write something to allow it to handle collecting these requests. I also wasn't sure if a comma or space separated list would be preferred for input, so I'm open to suggestions on that as well if we decide to use this script. I wrote something to handle both comma and space delimiters but it required flattening the list and a little extra complexity, so I left it out of the code below. Let me know if anyone has any thoughts on the matter and how we wanted to handle collecting the requests.

Thanks,

Jeremy

+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(c) 2023 University of New Hampshire
+
+import re
+import requests
+import argparse
+class RerunProcessor:
+    """Class for finding reruns inside an email using the patchworks events API.
+
+    The idea of this class is to use regex to find certain patterns that represent
+    desired contexts to rerun.
+    """
+    desired_contexts: list[str] = []
+    collection_of_retests: dict = {}
+    #^ is start of line and $ is end
+    # ((?:[a-xA-Z-]+(?:, ?\n?)?)+) is a capture group that gets all test labels after "Recheck-request: "
+    #   (?:[a-xA-Z-]+(?:, ?\n?)?)+ means 1 or more of the first match group
+    #       [a-xA-Z-]+ means 1 more more of any character in the ranges a-z or A-Z, or the character '-'
+    #       (?:, ?\n?)? means 1 or none of this match group which expects exactly 1 comma followed by
+    #                   1 or no spaces followed by 1 or no newlines.
+    # VALID MATCHES:
+    #   Recheck-request: iol-unit-testing, iol-something-else, iol-one-more, intel-example-testing
+    #   Recheck-request: iol-unit-testing,iol-something-else,iol-one-more, intel-example-testing,
+    #   Recheck-request: iol-unit-testing, iol-example, iol-another-example, intel-example-testing,
+    #   more-intel-testing
+    # INVALID MATCHES:
+    #   Recheck-request: iol-unit-testing, iol-something-else,iol-one-more,  intel-example-testing
+    #   Recheck-request: iol-unit-testing iol-something-else,iol-one-more, intel-example-testing,
+    #   Recheck-request: iol-unit-testing,iol-something-else,iol-one-more, intel-example-testing,
+    #
+    #   more-intel-testing
+    regex:str = "^Recheck-request: ((?:[a-xA-Z-]+(?:, ?\n?)?)+)"
+
+    def __init__(self, desired_contexts: list) -> None:
+        self.desired_contexts = desired_contexts
+
+    def process_comment_info(self, list_of_comment_blobs: list[str]) -> None:
+        """Takes the list of json blobs of comment information and associates them
+        with their patches.
+
+        Collects retest labels from a list of comments on patches represented in
+        list_of_comment_blobs and creates a dictionary that associates them with their
+        corresponding patch series ID. The labels that need to be retested are collected
+        by passing the comments body into get_test_names() method.
+
+        Args:
+            list_of_comment_blobs: a list of JSON blobs that represent comment information
+        """
+        for comment in list_of_comment_blobs:
+            comment_info = requests.get(
+                comment["comment"]["url"]
+            )
+            labels_to_rerun = self.get_test_name(comment_info.json()["content"])
+            patch_id = comment["payload"]["patch"]["id"]
+            #appending to the list if it already exists, or creating it if it doesn't
+            self.collection_of_retests[patch_id] = [*self.collection_of_retests.get(patch_id, []), *labels_to_rerun]
+
+    def get_test_names(self, email_body:str) -> list[str]:
+        """Uses the regex in the class to get the information from the email.
+
+        When it gets the test names from the email, it will all be in one capture group.
+        We expect a comma separated list of patchwork labels to be retested.
+
+        Returns:
+            A list of contexts found in the email that match your list of desired
+            contexts to capture
+        """
+        rerun_section = re.findall(self.regex, email_body, re.MULTILINE)
+        rerun_list = list(map(str.strip, rerun_section[0].split(",")))
+        valid_test_labels = []
+        for test_name in rerun_list:
+            if not test_name: #handle the capturing of empty string
+                continue
+            if test_name in self.desired_contexts:
+                valid_test_labels.append(test_name)
+        return valid_test_labels
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description="Help text for getting reruns")
+    parser.add_argument('-ts', '--time-since', dest="time_since", required=True, help="Get all patches since this timestamp")
+    parser.add_argument('--no-cover-comment', dest="no_cover_comment", default=False, help="Option to ignore comments on cover letters")
+    parser.add_argument('--no-patch-comment', dest="no_patch_comment", default=False, help="Option to ignore comments on patch emails")
+    parser.add_argument('--contexts', dest="contexts_to_capture", nargs='*', required=True, help="List of patchwork contexts you would like to capture")
+    args = parser.parse_args()
+    rerun_processor = RerunProcessor(args.contexts_to_capture)
+    patchwork_url = f"http://patches.dpdk.org/api/events/?since={args.time_since}"
+    if args.no_cover_comment and args.no_patch_comment:
+        exit(0)
+    if not args.no_cover_comment:
+        patchwork_url += "&category=cover-comment-created"
+    if not args.no_patch_comment:
+        patchwork_url += "&category=patch-comment-created"
+    comment_request_info = requests.get(patchwork_url)
+    rerun_processor.process_comment_info(comment_request_info.json())