#18128: use standard +NNNN timezone format in POT-Creation-Date header.

Patch by Michael McFadden, with a few small style tweaks.

Doc/whatsnew/3.5.rst

@@ -814,6 +814,10 @@ Changes in the Python API
  * The :mod:`socket` module now exports the CAN_RAW_FD_FRAMES constant on linux
    3.6 and greater.
 
+* The `pygettext.py` Tool now uses the standard +NNNN format for timezones in
+  the POT-Creation-Date header.
+
+
 Changes in the C API
 --------------------
 

Lib/test/test_tools/test_i18n.py

+"""Tests to cover the Tools/i18n package"""
+
+import os
+import unittest
+
+from test.script_helper import assert_python_ok
+from test.test_tools import toolsdir
+from test.support import temp_cwd
+
+class Test_pygettext(unittest.TestCase):
+    """Tests for the pygettext.py tool"""
+
+    script = os.path.join(toolsdir,'i18n', 'pygettext.py')
+
+    def get_header(self, data):
+        """ utility: return the header of a .po file as a dictionary """
+        headers = {}
+        for line in data.split('\n'):
+            if not line or line.startswith(('#', 'msgid','msgstr')):
+                continue
+            line = line.strip('"')
+            key, val = line.split(':',1)
+            headers[key] = val.strip()
+        return headers
+
+    def test_header(self):
+        """Make sure the required fields are in the header, according to:
+           http://www.gnu.org/software/gettext/manual/gettext.html#Header-Entry
+        """
+        with temp_cwd(None) as cwd:
+            assert_python_ok(self.script)
+            with open('messages.pot') as fp:
+                data = fp.read()
+            header = self.get_header(data)
+
+            self.assertIn("Project-Id-Version", header)
+            self.assertIn("POT-Creation-Date", header)
+            self.assertIn("PO-Revision-Date", header)
+            self.assertIn("Last-Translator", header)
+            self.assertIn("Language-Team", header)
+            self.assertIn("MIME-Version", header)
+            self.assertIn("Content-Type", header)
+            self.assertIn("Content-Transfer-Encoding", header)
+            self.assertIn("Generated-By", header)
+
+            # not clear if these should be required in POT (template) files
+            #self.assertIn("Report-Msgid-Bugs-To", header)
+            #self.assertIn("Language", header)
+
+            #"Plural-Forms" is optional
+
+
+    def test_POT_Creation_Date(self):
+        """ Match the date format from xgettext for POT-Creation-Date """
+        from datetime import datetime
+        with temp_cwd(None) as cwd:
+            assert_python_ok(self.script)
+            with open('messages.pot') as fp:
+                data = fp.read()
+            header = self.get_header(data)
+            creationDate = header['POT-Creation-Date']
+
+            # peel off the escaped newline at the end of string
+            if creationDate.endswith('\\n'):
+                creationDate = creationDate[:-len('\\n')]
+
+            # This will raise if the date format does not exactly match.
+            datetime.strptime(creationDate, '%Y-%m-%d %H:%M%z')

Misc/ACKS

@@ -911,6 +911,7 @@ Jack McCracken
 Rebecca McCreary
 Kirk McDonald
 Chris McDonough
+Michael McFadden
 Greg McFarlane
 Alan McIntyre
 Jessica McKellar

Misc/NEWS

@@ -187,6 +187,9 @@ Tests
 Tools/Demos
 -----------
 
+- Issue #18128: pygettext now uses standard +NNNN format in the
+  POT-Creation-Date header.
+
 - Issue #23935: Argument Clinic's understanding of format units
   accepting bytes, bytearrays, and buffers is now consistent with
   both the documentation and the implementation.

Tools/i18n/pygettext.py

@@ -441,9 +441,7 @@ class TokenEater:
 
     def write(self, fp):
         options = self.__options
-        timestamp = time.strftime('%Y-%m-%d %H:%M+%Z')
-        # The time stamp in the header doesn't have the same format as that
-        # generated by xgettext...
+        timestamp = time.strftime('%Y-%m-%d %H:%M%z')
         encoding = fp.encoding if fp.encoding else 'UTF-8'
         print(pot_header % {'time': timestamp, 'version': __version__,
                             'charset': encoding,