Merge ~racb/git-ubuntu:changelog-date-edge-cases into git-ubuntu:main

[Robie Basak]

Make Jenkins happy

[Server Team CI bot (server-team-bot)]

PASSED: Continuous integration, rev:f24300f657a413c91be9c222478a0bb9498d380d
https://jenkins.canonical.com/server-team/job/git-ubuntu-ci/15/
Executed test runs:
    SUCCESS: VM Setup
    SUCCESS: Build
    SUCCESS: VM Reset
    SUCCESS: Unit Tests
    IN_PROGRESS: Declarative: Post Actions

Click here to trigger a rebuild:
https://jenkins.canonical.com/server-team/job/git-ubuntu-ci/15//rebuild

review: Approve (continuous-integration)

[Bryce Harrington (bryce)]

"abbreviation" -> "abbreviations"

Grammatically three 'as' in the same sentence reads funny, but the comment is perfectly comprehensible. I might suggest changing the third 'as' to 'since'.

Otherwise LGTM, +1.

review: Approve

[Robie Basak (racb)]

Thanks! I've adopted all your suggestions. I also fixed a minor docstring omission I noticed. I'll just wait for CI to pass, then merge.

[Server Team CI bot (server-team-bot)]

PASSED: Continuous integration, rev:66cd050ce92c1a0960a22aae0336f0165a6e468c
https://jenkins.canonical.com/server-team/job/git-ubuntu-ci/16/
Executed test runs:
    SUCCESS: VM Setup
    SUCCESS: Build
    SUCCESS: VM Reset
    SUCCESS: Unit Tests
    IN_PROGRESS: Declarative: Post Actions

Click here to trigger a rebuild:
https://jenkins.canonical.com/server-team/job/git-ubuntu-ci/16//rebuild

review: Approve (continuous-integration)

diff --git a/gitubuntu/git_repository.py b/gitubuntu/git_repository.py
index 2c2a3da..27ed645 100644
--- a/gitubuntu/git_repository.py
+++ b/gitubuntu/git_repository.py
@@ -517,6 +517,23 @@ def unescape_dot_git(path):
 class ChangelogError(Exception):
     pass
 
+
+def _apply_re_substitutions(original_string, subs):
+    """Apply a sequence of regular expression substitutions to a string
+
+    :param str original_string: the string to which to apply substitutions
+    :param list(str, str) subs: a list of substitutions to apply. The first
+        element of each tuple is the regexp to match, and the second is what to
+        replace it with.
+    :rtype: str
+    :returns: the original string but altered by all the substitutions
+    """
+    changed_string = original_string
+    for regex, replacement in subs:
+        changed_string = re.sub(regex, replacement, changed_string)
+    return changed_string
+
+
 class Changelog:
     '''Representation of a debian/changelog file found inside a git tree-ish
 
@@ -792,14 +809,17 @@ class Changelog:
         # time.strptime ignores time zones, so we must use datetime.strptime()
 
         # strptime doesn't support anything other than standard locale names
-        # for days of the week, so handle the "Thur" abbreviation as a special
-        # case as defined in the spec as it is unambiguous.
-        adjusted_changelog_timestamp_string = re.sub(
-            r'^Thur,',
-            'Thu,',
-            changelog_timestamp_string,
+        # for days of the week, so handle "Thur", "Thurs", "Tues" and "Sept"
+        # abbreviations as special cases as defined in the spec since they are
+        # unambiguous.
+        adjusted_changelog_timestamp_string = _apply_re_substitutions(
+            original_string=changelog_timestamp_string,
+            subs=[
+                (r'^Thur(s)?,', 'Thu,'),
+                (r'^Tues,', 'Tue,'),
+                (r'\bSept\b', 'Sep'),
+            ],
         )
-
         acceptable_date_formats = [
             '%a, %d %b %Y %H:%M:%S %z',  # standard
             '%A, %d %b %Y %H:%M:%S %z',  # full day of week
diff --git a/gitubuntu/git_repository_test.py b/gitubuntu/git_repository_test.py
index 838c31e..05bc157 100644
--- a/gitubuntu/git_repository_test.py
+++ b/gitubuntu/git_repository_test.py
@@ -136,6 +136,17 @@ def test_changelog_multiple_angle_brackets():
     # Part-abbreviated day of week name, such as in:
     #     kubuntu-meta 1.76
     ('Thur, 15 May 2016 08:14:34 -0700', (2016, 5, 15, 8, 14, 34, -7)),
+    #     apachetop 0.12.5-7
+    ('Thurs, 12 Jan 2006 12:09:58 +0000', (2006, 1, 12, 12, 9, 58, 0)),
+    #     easychem 0.6-0ubuntu1
+    ('Tues, 20 Dec 2005 16:57:16 -0500', (2005, 12, 20, 16, 57, 16, -5)),
+    # Part-abbreviated month name, such as in:
+    #     libapp-cache-perl 0.35-1
+    ('Wed, 24 Sept 2008 19:32:23 +0200', (2008, 9, 24, 19, 32, 23, 2)),
+    #     libcrypt-hcesha-perl 0.70-2
+    ('Wed,  24 Sept 2008 19:44:01 +0200', (2008, 9, 24, 19, 44, 1, 2)),
+    #     gnome-shell-extension-tilix-shortcut 1.0.1-1
+    ('Tue, 19 Sept 2017 14:23:17 +0200', (2017, 9, 19, 14, 23, 17, 2)),
 ])
 def test_parse_changelog_date(input_date_string, expected_result):
     """_parse_changelog_date should parse a basic date string correctly