fix: missing month keys (adbar#100)

* fix: missing month key * check consistency of months
shapesinc · Oct 4, 2023 · 47fbb1c · 47fbb1c
1 parent 966488c
commit 47fbb1c
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 2 deletions.
diff --git a/htmldate/extractors.py b/htmldate/extractors.py
@@ -141,7 +141,7 @@
 MONTHS = [
     ("jan", "januar", "jänner", "january", "januari", "janvier", "ocak", "oca"),
     ("feb", "februar", "feber", "february", "februari", "février", "şubat", "şub"),
-    ("mar", "märz", "march", "maret", "mart", "mars"),
+    ("mar", "mär", "märz", "march", "maret", "mart", "mars"),
     ("apr", "april", "avril", "nisan", "nis"),
     ("may", "mai", "mei", "mayıs"),
     ("jun", "juni", "june", "juin", "haziran", "haz"),
@@ -150,7 +150,7 @@
     ("sep", "september", "septembre", "eylül", "eyl"),
     ("oct", "oktober", "october", "octobre", "okt", "ekim", "eki"),
     ("nov", "november", "kasım", "kas", "novembre"),
-    ("dec", "dezember", "december", "desember", "décembre", "aralık", "ara"),
+    ("dec", "dez", "dezember", "december", "desember", "décembre", "aralık", "ara"),
 ]
 
 TEXT_MONTHS = {

diff --git a/tests/unit_tests.py b/tests/unit_tests.py
@@ -972,6 +972,8 @@ def test_regex_parse():
     """test date extraction using rules and regular expressions"""
     assert regex_parse("3. Dezember 2008") is not None
     assert regex_parse("33. Dezember 2008") is None
+    assert regex_parse("3. Dez 2008") is not None
+    assert regex_parse("3 dez 2008") is not None
     assert regex_parse("3 Aralık 2008 Çarşamba") is not None
     assert regex_parse("3 Aralık 2008") is not None
     assert regex_parse("Tuesday, March 26th, 2019") is not None