fix(ci_visibility): properly strip .git from repo URL when getting re…

…po name [backport 2.10] (#10559)

Backport aa04928 from #10556 to 2.10.

Fixes issue #10554 where `rstrip` was being used to remove the `.git`
suffix from repo URLs, causing repo names that end in one or more of
`g`, `i`, or `t` to be incorrectly extracted. eg: `fastapi.git` ->
`fastap` or `test-environment` -> `test-environmen` .

## Checklist
- [x] PR author has checked that all the criteria below are met
- The PR description includes an overview of the change
- The PR description articulates the motivation for the change
- The change includes tests OR the PR description describes a testing
strategy
- The PR description notes risks associated with the change, if any
- Newly-added code is easy to change
- The change follows the [library release note
guidelines](https://ddtrace.readthedocs.io/en/stable/releasenotes.html)
- The change includes or references documentation updates if necessary
- Backport labels are set (if
[applicable](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting))

## Reviewer Checklist
- [x] Reviewer has checked that all the criteria below are met 
- Title is accurate
- All changes are related to the pull request's stated goal
- Avoids breaking
[API](https://ddtrace.readthedocs.io/en/stable/versioning.html#interfaces)
changes
- Testing strategy adequately addresses listed risks
- Newly-added code is easy to change
- Release note makes sense to a user of the library
- If necessary, author has acknowledged and discussed the performance
implications of this PR as reported in the benchmarks PR comment
- Backport labels are set in a manner that is consistent with the
[release branch maintenance
policy](https://ddtrace.readthedocs.io/en/latest/contributing.html#backporting)

Co-authored-by: Romain Komorn <136473744+romainkomorndatadog@users.noreply.github.com>

ddtrace/internal/ci_visibility/recorder.py

@@ -3,6 +3,7 @@
 import json
 import os
 from pathlib import Path
+import re
 import socket
 from typing import TYPE_CHECKING  # noqa:F401
 from typing import NamedTuple  # noqa:F401
@@ -102,12 +103,17 @@ class CIVisibilityAuthenticationException(Exception):
     pass
 
 
-def _extract_repository_name_from_url(repository_url):
-    # type: (str) -> str
+def _extract_repository_name_from_url(repository_url: str) -> str:
+    _REPO_NAME_REGEX = r".*/(?P<repo_name>.*?)(\.git)?$"
+
     try:
-        return parse.urlparse(repository_url).path.rstrip(".git").rpartition("/")[-1]
+        url_path = parse.urlparse(repository_url).path
+        matches = re.match(_REPO_NAME_REGEX, url_path, flags=re.IGNORECASE)
+        if matches:
+            return matches.group("repo_name")
+        log.warning("Cannot extract repository name from unexpected URL path: %s", url_path)
+        return repository_url
     except ValueError:
-        # In case of parsing error, default to repository url
         log.warning("Repository name cannot be parsed from repository_url: %s", repository_url)
         return repository_url
 

releasenotes/notes/ci_visibility-fix_properly_strip_dotgit_from_repo_url-523a908075aea559.yaml

@@ -0,0 +1,5 @@
+---
+fixes:
+  - |
+    CI Visibility: Fixes a bug where ``.git`` was incorrectly being stripped from repository URLs when extracting service names, 
+    resulting in ``g``, ``i``, or ``t`` being removed (eg: ``test-environment.git`` incorrectly becoming ``test-environmen``)

tests/ci_visibility/test_ci_visibility.py

@@ -292,6 +292,16 @@ def test_ci_visibility_service_disable():
         ("git+git://github.com/org/repo-name.git", "repo-name"),
         ("git+ssh://github.com/org/repo-name.git", "repo-name"),
         ("git+https://github.com/org/repo-name.git", "repo-name"),
+        ("https://github.com/fastapi/fastapi.git", "fastapi"),
+        ("git@github.com:fastapi/fastapi.git", "fastapi"),
+        ("git@github.com:fastapi/fastapi.gitttttt", "fastapi.gitttttt"),
+        ("git@github.com:fastapi/fastapiiiititititi.git", "fastapiiiititititi"),
+        ("https://github.com/fastapi/fastapitttttt.git", "fastapitttttt"),
+        ("this is definitely not a valid git repo URL", "this is definitely not a valid git repo URL"),
+        ("git@github.com:fastapi/FastAPI.GiT", "FastAPI"),
+        ("git+https://github.com/org/REPO-NAME.GIT", "REPO-NAME"),
+        ("https://github.com/DataDog/DD-TRACE-py", "DD-TRACE-py"),
+        ("https://github.com/DataDog/dd-trace-py.GIT", "dd-trace-py"),
     ],
 )
 def test_repository_name_extracted(repository_url, repository_name):