Merge pull request #45 from github/labels

feat: add time in labels

Author: zkoppert

.env-example

@@ -1,5 +1,7 @@
 GH_TOKEN = " "
 SEARCH_QUERY = "repo:owner/repo is:open is:issue"
+LABELS_TO_MEASURE = "waiting-for-review,waiting-for-manager"
 HIDE_TIME_TO_FIRST_RESPONSE = False
 HIDE_TIME_TO_CLOSE = False
 HIDE_TIME_TO_ANSWER = False
+HIDE_LABEL_METRICS = False

.pylintrc

@@ -3,4 +3,6 @@ disable=
 	redefined-argument-from-local,
 	too-many-arguments,
 	too-few-public-methods,
-	duplicate-code,
+	duplicate-code,
+	too-many-locals,
+	too-many-branches,

README.md

@@ -2,10 +2,16 @@
 
 [![CodeQL](https://github.com/github/issue-metrics/actions/workflows/codeql-analysis.yml/badge.svg)](https://github.com/github/issue-metrics/actions/workflows/codeql-analysis.yml) [![Docker Image CI](https://github.com/github/issue-metrics/actions/workflows/docker-image.yml/badge.svg)](https://github.com/github/issue-metrics/actions/workflows/docker-image.yml) [![Python package](https://github.com/github/issue-metrics/actions/workflows/python-package.yml/badge.svg)](https://github.com/github/issue-metrics/actions/workflows/python-package.yml)
 
-This is a GitHub Action that searches for pull requests/issues/discussions in a repository and measures
-the time to first response for each one. It then calculates the average time
-to first response and writes the issues/pull requests/discussions with their metrics
-to a Markdown file. The issues/pull requests/discussions to search for can be filtered by using a search query.
+This is a GitHub Action that searches for pull requests/issues/discussions in a repository and measures and reports on
+several metrics. The issues/pull requests/discussions to search for can be filtered by using a search query.
+
+The metrics that are measured are:
+| Metric | Description |
+|--------|-------------|
+| Time to first response | The time between when an issue/pull request/discussion is created and when the first comment or review is made. |
+| Time to close | The time between when an issue/pull request/discussion is created and when it is closed. |
+| Time to answer | (Discussions only) The time between when a discussion is created and when it is answered. |
+| Time in label | The time between when a label has a specific label appplied to an issue/pull request/discussion and when it is removed. This requires the LABELS_TO_MEASURE env variable to be set. |
 
 This action was developed by the GitHub OSPO for our own use and developed in a way that we could open source it that it might be useful to you as well! If you want to know more about how we use it, reach out in an issue in this repository.
 
@@ -37,9 +43,11 @@ Below are the allowed configuration options:
 |-----------------------|----------|---------|-------------|
 | `GH_TOKEN`            | True     |         | The GitHub Token used to scan the repository. Must have read access to all repository you are interested in scanning. |
 | `SEARCH_QUERY`        | True     |         | The query by which you can filter issues/prs which must contain a `repo:` entry or an `org:` entry. For discussions, include `type:discussions` in the query. |
+| `LABELS_TO_MEASURE`   | False    |         | A comma separated list of labels to measure how much time the label is applied. If not provided, no labels durations will be measured. Not compatible with discussions at this time. |
 | `HIDE_TIME_TO_FIRST_RESPONSE` | False | False | If set to true, the time to first response will not be displayed in the generated markdown file. |
 | `HIDE_TIME_TO_CLOSE` | False | False | If set to true, the time to close will not be displayed in the generated markdown file. |
 | `HIDE_TIME_TO_ANSWER` | False | False | If set to true, the time to answer a discussion will not be displayed in the generated markdown file. |
+| `HIDE_LABEL_METRICS` | False | False | If set to true, the time in label metrics will not be displayed in the generated markdown file. |
 
 ### Example workflows
 
@@ -197,6 +205,65 @@ jobs:
         assignees: <YOUR_GITHUB_HANDLE_HERE>
 ```
 
+## Measuring time spent in labels
+
+**Note**: The discussions API currently doesn't support the `LabeledEvent` so this action cannot measure the time spent in a label for discussions.
+
+Sometimes it is helpful to know how long an issue or pull request spent in a particular label. This action can be configured to measure the time spent in a label. This is different from only wanting to measure issues with a specific label. If that is what you want, see the section on [configuring your search query](https://github.com/github/issue-metrics/blob/main/README.md#search_query-issues-or-pull-requests-open-or-closed).
+
+Here is an example workflow that does this:
+
+```yaml
+name: Monthly issue metrics
+on:
+  workflow_dispatch:
+
+jobs:
+  build:
+    name: issue metrics
+    runs-on: ubuntu-latest
+    
+    steps:
+
+    - name: Run issue-metrics tool
+      uses: github/issue-metrics@v2
+      env:
+        GH_TOKEN: ${{ secrets.GH_TOKEN }}
+        LABELS_TO_MEASURE: 'waiting-for-manager-approval,waiting-for-security-review'
+        SEARCH_QUERY: 'repo:owner/repo is:issue created:2023-05-01..2023-05-31 -reason:"not planned"'
+
+    - name: Create issue
+      uses: peter-evans/create-issue-from-file@v4
+      with:
+        title: Monthly issue metrics report
+        content-filepath: ./issue_metrics.md
+        assignees: <YOUR_GITHUB_HANDLE_HERE>
+
+```
+
+then the report will look like this:
+
+```markdown
+# Issue Metrics
+
+| Metric | Value |
+| --- | ---: |
+| Average time to first response | 0:50:44.666667 |
+| Average time to close | 6 days, 7:08:52 |
+| Average time to answer | 1 day |
+| Average time spent in waiting-for-manager-approval | 0:00:41 |
+| Average time spent in waiting-for-security-review | 2 days, 4:25:03 |
+| Number of items that remain open | 2 |
+| Number of items closed | 1 |
+| Total number of items created | 3 |
+
+| Title | URL | Time to first response | Time to close | Time to answer | Time spent in waiting-for-manager-approval | Time spent in waiting-for-security-review |
+| --- | --- | --- | --- | --- | --- | --- |
+| Pull Request Title 1 | https://github.com/user/repo/pulls/1 | 0:05:26 | None | None | None | None |
+| Issue Title 2 | https://github.com/user/repo/issues/2 | 2:26:07 | None | None | 0:00:41 | 2 days, 4:25:03 |
+
+```
+
 ## Example issue_metrics.md output
 
 Here is the output with no hidden columns:
@@ -234,7 +301,7 @@ Here is the output with all hidable columns hidden:
 | --- | --- |
 | Discussion Title 1 | https://github.com/user/repo/discussions/1 |
 | Pull Request Title 2 | https://github.com/user/repo/pulls/2 |
-| Issue Title 3 | https://github.com/user/repo/issues/3 | 2:26:07 |
+| Issue Title 3 | https://github.com/user/repo/issues/3 |
 
 ```
 

classes.py

@@ -17,6 +17,7 @@ class IssueWithMetrics:
         time_to_close (timedelta, optional): The time it took to close the issue.
         time_to_answer (timedelta, optional): The time it took to answer the
             discussions in the issue.
+        label_metrics (dict, optional): A dictionary containing the label metrics
 
     """
 
@@ -27,9 +28,11 @@ def __init__(
         time_to_first_response=None,
         time_to_close=None,
         time_to_answer=None,
+        labels_metrics=None,
     ):
         self.title = title
         self.html_url = html_url
         self.time_to_first_response = time_to_first_response
         self.time_to_close = time_to_close
         self.time_to_answer = time_to_answer
+        self.label_metrics = labels_metrics

issue_metrics.py

@@ -32,6 +32,7 @@
 from classes import IssueWithMetrics
 from discussions import get_discussions
 from json_writer import write_to_json
+from labels import get_average_time_in_labels, get_label_metrics
 from markdown_writer import write_to_markdown
 from time_to_answer import get_average_time_to_answer, measure_time_to_answer
 from time_to_close import get_average_time_to_close, measure_time_to_close
@@ -102,6 +103,7 @@ def auth_to_github() -> github3.GitHub:
 def get_per_issue_metrics(
     issues: Union[List[dict], List[github3.issues.Issue]],  # type: ignore
     discussions: bool = False,
+    labels: Union[List[str], None] = None,
 ) -> tuple[List, int, int]:
     """
     Calculate the metrics for each issue/pr/discussion in a list provided.
@@ -111,6 +113,7 @@ def get_per_issue_metrics(
             GitHub issues or discussions.
         discussions (bool, optional): Whether the issues are discussions or not.
             Defaults to False.
+        labels (List[str]): A list of labels to measure time spent in. Defaults to empty list.
 
     Returns:
         tuple[List[IssueWithMetrics], int, int]: A tuple containing a
@@ -130,6 +133,7 @@ def get_per_issue_metrics(
                 None,
                 None,
                 None,
+                None,
             )
             issue_with_metrics.time_to_first_response = measure_time_to_first_response(
                 None, issue
@@ -147,10 +151,13 @@ def get_per_issue_metrics(
                 None,
                 None,
                 None,
+                None,
             )
             issue_with_metrics.time_to_first_response = measure_time_to_first_response(
                 issue, None
             )
+            if labels:
+                issue_with_metrics.label_metrics = get_label_metrics(issue, labels)
             if issue.state == "closed":  # type: ignore
                 issue_with_metrics.time_to_close = measure_time_to_close(issue, None)
                 num_issues_closed += 1
@@ -240,13 +247,24 @@ def main():
             (ie. repo:owner/repo) or an organization (ie. org:organization)"
         )
 
+    # Determine if there are label to measure
+    labels = os.environ.get("LABELS_TO_MEASURE")
+    if labels:
+        labels = labels.split(",")
+    else:
+        labels = []
+
     # Search for issues
     # If type:discussions is in the search_query, search for discussions using get_discussions()
     if "type:discussions" in search_query:
+        if labels:
+            raise ValueError(
+                "The search query for discussions cannot include labels to measure"
+            )
         issues = get_discussions(token, search_query)
         if len(issues) <= 0:
             print("No discussions found")
-            write_to_markdown(None, None, None, None, None, None)
+            write_to_markdown(None, None, None, None, None, None, None)
             return
     else:
         if owner is None or repo_name is None:
@@ -257,13 +275,14 @@ def main():
         issues = search_issues(search_query, github_connection)
         if len(issues.items) <= 0:
             print("No issues found")
-            write_to_markdown(None, None, None, None, None, None)
+            write_to_markdown(None, None, None, None, None, None, None)
             return
 
     # Get all the metrics
     issues_with_metrics, num_issues_open, num_issues_closed = get_per_issue_metrics(
         issues,
         discussions="type:discussions" in search_query,
+        labels=labels,
     )
 
     average_time_to_first_response = get_average_time_to_first_response(
@@ -275,12 +294,17 @@ def main():
 
     average_time_to_answer = get_average_time_to_answer(issues_with_metrics)
 
+    # Get the average time in label for each label and store it in a dictionary
+    # where the key is the label and the value is the average time
+    average_time_in_labels = get_average_time_in_labels(issues_with_metrics, labels)
+
     # Write the results to json and a markdown file
     write_to_json(
         issues_with_metrics,
         average_time_to_first_response,
         average_time_to_close,
         average_time_to_answer,
+        average_time_in_labels,
         num_issues_open,
         num_issues_closed,
     )
@@ -289,8 +313,10 @@ def main():
         average_time_to_first_response,
         average_time_to_close,
         average_time_to_answer,
+        average_time_in_labels,
         num_issues_open,
         num_issues_closed,
+        labels,
     )
 
 

json_writer.py

@@ -27,6 +27,7 @@ def write_to_json(
     average_time_to_first_response: Union[timedelta, None],
     average_time_to_close: Union[timedelta, None],
     average_time_to_answer: Union[timedelta, None],
+    average_time_in_labels: Union[dict, None],
     num_issues_opened: Union[int, None],
     num_issues_closed: Union[int, None],
 ) -> str:
@@ -48,13 +49,18 @@ def write_to_json(
                 "time_to_first_response": "3 days, 0:00:00",
                 "time_to_close": "6 days, 0:00:00",
                 "time_to_answer": "None",
+                "label_metrics": {
+                    "bug": "1 day, 16:24:12"
+                }
             },
             {
                 "title": "Issue 2",
                 "html_url": "https://github.com/owner/repo/issues/2",
                 "time_to_first_response": "2 days, 0:00:00",
                 "time_to_close": "4 days, 0:00:00",
                 "time_to_answer": "1 day, 0:00:00",
+                "label_metrics": {
+                }
             },
         ],
     }
@@ -66,10 +72,15 @@ def write_to_json(
         return ""
 
     # Create a dictionary with the metrics
+    labels_metrics = {}
+    if average_time_in_labels:
+        for label, time in average_time_in_labels.items():
+            labels_metrics[label] = str(time)
     metrics = {
         "average_time_to_first_response": str(average_time_to_first_response),
         "average_time_to_close": str(average_time_to_close),
         "average_time_to_answer": str(average_time_to_answer),
+        "average_time_in_labels": labels_metrics,
         "num_items_opened": num_issues_opened,
         "num_items_closed": num_issues_closed,
         "total_item_count": len(issues_with_metrics),
@@ -78,13 +89,18 @@ def write_to_json(
     # Create a list of dictionaries with the issues and metrics
     issues = []
     for issue in issues_with_metrics:
+        formatted_label_metrics = {}
+        if issue.label_metrics:
+            for label, time in issue.label_metrics.items():
+                formatted_label_metrics[label] = str(time)
         issues.append(
             {
                 "title": issue.title,
                 "html_url": issue.html_url,
                 "time_to_first_response": str(issue.time_to_first_response),
                 "time_to_close": str(issue.time_to_close),
                 "time_to_answer": str(issue.time_to_answer),
+                "label_metrics": formatted_label_metrics,
             }
         )