Add Inuktitut to GCNotify (#270)

* Add Inuktitut to GCNotify

* encode inuktitut

* Made a new version for utils

.github/actions/waffles/requirements.txt

@@ -1,4 +1,4 @@
 docopt==0.6.2
 Flask==2.3.3
 markupsafe==2.1.4
-git+https://github.com/cds-snc/notifier-utils.git@52.0.19#egg=notifications-utils
+git+https://github.com/cds-snc/notifier-utils.git@52.1.0#egg=notifications-utils

notifications_utils/sanitise_text.py

@@ -101,6 +101,13 @@ class SanitiseSMS(SanitiseText):
     # Welsh characters not already included in GSM
     WELSH_NON_GSM_CHARACTERS = set("ÂâÊêÎîÔôÛûŴŵŶŷ")
     FRENCH_NON_GSM_CHARACTESR = set("ÀÂËÎÏÔŒÙÛâçêëîïôœû")
+    INUKTITUK_CHARACTERS = set(
+        "ᐁᐯᑌᑫᕴᒉᒣᓀᓭᓓᔦᑦᔦᕓᕂᙯᖅᑫᙰᐃᐱᑎᑭᕵᒋᒥᓂᓯ𑪶𑪰ᓕᔨᑦᔨᖨᕕᕆᕿᖅᑭᖏᙱᖠᐄᐲᑏᑮᕶᒌᒦᓃᓰ𑪷𑪱ᓖᔩᑦᔩᖩᕖᕇᖀᖅᑮᖐᙲᖡᐅᐳᑐᑯᕷᒍᒧᓄᓱ𑪸𑪲ᓗᔪᑦᔪᖪᕗᕈᖁᖅᑯᖑᙳᖢᐊᐸᑕᑲᕹᒐᒪᓇᓴ𑪺𑪴ᓚᔭᑦᔭᖬᕙᕋᖃᖅᑲᖓᙵᖤᑉᑦᒃᕻᒡᒻᓐᔅᓪᔾᑦᔾᖮᕝᕐᖅᖅᒃᖕᖖᖦᖯᕼᑊ"  # noqa: E501
+    )
+    CREE_CHARACTERS = set("ᐊᐁᐃᐅᐸᐯᐱᐳᑕᑌᑎᑐᑲᑫᑭᑯᒐᒉᒋᒍᒪᒣᒥᒧᓇᓀᓂᓄᓴᓭᓯᓱᔭᔦᔨᔪ")
+    OJIBWE_CHARACTERS = set(
+        "ᐁᐃᐅᐊᐄᐆᐋᐊᐊᐞᐊᐊᐊᐦᐊᐊᐊᐊᐦᐊᐊᐞᐊᐯᐱᐳᐸᐲᐴᐹᐊᑉᐊᣔᑌᑎᑐᑕᑏᑑᑖᐊᑦᐊᣕᑫᑭᑯᑲᑮᑰᑳᐊᒃᐊᣖᒉᒋᒍᒐᒌᒎᒑᐊᒡᐊᣗᒣᒥᒧᒪᒦᒨᒫᐊᒻᐊᣘᐊᒻᐊᐊᣘᐊᓀᓂᓄᓇᓃᓅᓈᐊᓐᐊᣙᐊᓐᐊᐊᣙᐊᓭᓯᓱᓴᓰᓲᓵᐊᔅᐊᣚᐊᔅᐊᐊᣚᐊᔐᔑᔓᔕᔒᔔᔖᐊᔥᐊᣛᐊᔥᐊᐊᣛᐊᔦᔨᔪᔭᔩᔫᔮᐊᔾᐊᐤᐊᐃᐧᐁᐧᐃᐧᐅᐧᐊᐧᐄᐧᐆᐧᐋᐊᐤᐊᐤᐊᣜᐦᐁᐦᐃᐦᐅᐦᐊᐦᐄᐦᐆᐦᐋᐊᐦᐊᐦᐊᐦᐊᐊᐦᐊ"  # noqa: E501
+    )
 
     ALLOWED_CHARACTERS = (
         set(
@@ -110,6 +117,9 @@ class SanitiseSMS(SanitiseText):
         )
         | WELSH_NON_GSM_CHARACTERS
         | FRENCH_NON_GSM_CHARACTESR
+        | INUKTITUK_CHARACTERS
+        | CREE_CHARACTERS
+        | OJIBWE_CHARACTERS
     )
 
 

pyproject.toml

@@ -5,7 +5,7 @@ include = '(notifications_utils|tests)/.*\.pyi?$'
 
 [tool.poetry]
 name = "notifications-utils"
-version = "52.0.19"
+version = "52.1.0"
 description = "Shared python code for Notification - Provides logging utils etc."
 authors = ["Canadian Digital Service"]
 license = "MIT license"

tests/test_sanitise_text.py

@@ -47,13 +47,160 @@ def test_encode_chars_the_same_for_ascii_and_sms(char, expected, cls):
     (("Ŷ", "Ŷ", "Y"), "non-gsm Welsh char (capital y with hat)"),
 )
 
+params_inuktitut = (
+    ("ᐁ", "ᐁ"),
+    ("ᐯ", "ᐯ"),
+    ("ᑌ", "ᑌ"),
+    ("ᑫ", "ᑫ"),
+    ("ᕴ", "ᕴ"),
+    ("ᒉ", "ᒉ"),
+    ("ᒣ", "ᒣ"),
+    ("ᓀ", "ᓀ"),
+    ("ᓭ", "ᓭ"),
+    ("ᓓ", "ᓓ"),
+    ("ᔦ", "ᔦ"),
+    ("ᑦ", "ᑦ"),
+    ("ᔦ", "ᔦ"),
+    ("ᕓ", "ᕓ"),
+    ("ᕂ", "ᕂ"),
+    ("ᙯ", "ᙯ"),
+    ("ᖅ", "ᖅ"),
+    ("ᑫ", "ᑫ"),
+    ("ᙰ", "ᙰ"),
+    ("ᐃ", "ᐃ"),
+    ("ᐱ", "ᐱ"),
+    ("ᑎ", "ᑎ"),
+    ("ᑭ", "ᑭ"),
+    ("ᕵ", "ᕵ"),
+    ("ᒋ", "ᒋ"),
+    ("ᒥ", "ᒥ"),
+    ("ᓂ", "ᓂ"),
+    ("ᓯ", "ᓯ"),
+    ("\U00011ab6", "\U00011ab6"),
+    ("\U00011ab0", "\U00011ab0"),
+    ("ᓕ", "ᓕ"),
+    ("ᔨ", "ᔨ"),
+    ("ᑦ", "ᑦ"),
+    ("ᔨ", "ᔨ"),
+    ("ᖨ", "ᖨ"),
+    ("ᕕ", "ᕕ"),
+    ("ᕆ", "ᕆ"),
+    ("ᕿ", "ᕿ"),
+    ("ᖅ", "ᖅ"),
+    ("ᑭ", "ᑭ"),
+    ("ᖏ", "ᖏ"),
+    ("ᙱ", "ᙱ"),
+    ("ᖠ", "ᖠ"),
+    ("ᐄ", "ᐄ"),
+    ("ᐲ", "ᐲ"),
+    ("ᑏ", "ᑏ"),
+    ("ᑮ", "ᑮ"),
+    ("ᕶ", "ᕶ"),
+    ("ᒌ", "ᒌ"),
+    ("ᒦ", "ᒦ"),
+    ("ᓃ", "ᓃ"),
+    ("ᓰ", "ᓰ"),
+    ("\U00011ab7", "\U00011ab7"),
+    ("\U00011ab1", "\U00011ab1"),
+    ("ᓖ", "ᓖ"),
+    ("ᔩ", "ᔩ"),
+    ("ᑦ", "ᑦ"),
+    ("ᔩ", "ᔩ"),
+    ("ᖩ", "ᖩ"),
+    ("ᕖ", "ᕖ"),
+    ("ᕇ", "ᕇ"),
+    ("ᖀ", "ᖀ"),
+    ("ᖅ", "ᖅ"),
+    ("ᑮ", "ᑮ"),
+    ("ᖐ", "ᖐ"),
+    ("ᙲ", "ᙲ"),
+    ("ᖡ", "ᖡ"),
+    ("ᐅ", "ᐅ"),
+    ("ᐳ", "ᐳ"),
+    ("ᑐ", "ᑐ"),
+    ("ᑯ", "ᑯ"),
+    ("ᕷ", "ᕷ"),
+    ("ᒍ", "ᒍ"),
+    ("ᒧ", "ᒧ"),
+    ("ᓄ", "ᓄ"),
+    ("ᓱ", "ᓱ"),
+    ("\U00011ab8", "\U00011ab8"),
+    ("\U00011ab2", "\U00011ab2"),
+    ("ᓗ", "ᓗ"),
+    ("ᔪ", "ᔪ"),
+    ("ᑦ", "ᑦ"),
+    ("ᔪ", "ᔪ"),
+    ("ᖪ", "ᖪ"),
+    ("ᕗ", "ᕗ"),
+    ("ᕈ", "ᕈ"),
+    ("ᖁ", "ᖁ"),
+    ("ᖅ", "ᖅ"),
+    ("ᑯ", "ᑯ"),
+    ("ᖑ", "ᖑ"),
+    ("ᙳ", "ᙳ"),
+    ("ᖢ", "ᖢ"),
+    ("ᐊ", "ᐊ"),
+    ("ᐸ", "ᐸ"),
+    ("ᑕ", "ᑕ"),
+    ("ᑲ", "ᑲ"),
+    ("ᕹ", "ᕹ"),
+    ("ᒐ", "ᒐ"),
+    ("ᒪ", "ᒪ"),
+    ("ᓇ", "ᓇ"),
+    ("ᓴ", "ᓴ"),
+    ("\U00011aba", "\U00011aba"),
+    ("\U00011ab4", "\U00011ab4"),
+    ("ᓚ", "ᓚ"),
+    ("ᔭ", "ᔭ"),
+    ("ᑦ", "ᑦ"),
+    ("ᔭ", "ᔭ"),
+    ("ᖬ", "ᖬ"),
+    ("ᕙ", "ᕙ"),
+    ("ᕋ", "ᕋ"),
+    ("ᖃ", "ᖃ"),
+    ("ᖅ", "ᖅ"),
+    ("ᑲ", "ᑲ"),
+    ("ᖓ", "ᖓ"),
+    ("ᙵ", "ᙵ"),
+    ("ᖤ", "ᖤ"),
+    ("ᑉ", "ᑉ"),
+    ("ᑦ", "ᑦ"),
+    ("ᒃ", "ᒃ"),
+    ("ᕻ", "ᕻ"),
+    ("ᒡ", "ᒡ"),
+    ("ᒻ", "ᒻ"),
+    ("ᓐ", "ᓐ"),
+    ("ᔅ", "ᔅ"),
+    ("ᓪ", "ᓪ"),
+    ("ᔾ", "ᔾ"),
+    ("ᑦ", "ᑦ"),
+    ("ᔾ", "ᔾ"),
+    ("ᖮ", "ᖮ"),
+    ("ᕝ", "ᕝ"),
+    ("ᕐ", "ᕐ"),
+    ("ᖅ", "ᖅ"),
+    ("ᖅ", "ᖅ"),
+    ("ᒃ", "ᒃ"),
+    ("ᖕ", "ᖕ"),
+    ("ᖖ", "ᖖ"),
+    ("ᖦ", "ᖦ"),
+    ("ᖯ", "ᖯ"),
+    ("ᕼ", "ᕼ"),
+    ("ᑊ", "ᑊ"),
+)
+
 
 @pytest.mark.parametrize("char, expected_sms, expected_ascii", params, ids=ids)
 def test_encode_chars_different_between_ascii_and_sms(char, expected_sms, expected_ascii):
     assert SanitiseSMS.encode_char(char) == expected_sms
     assert SanitiseASCII.encode_char(char) == expected_ascii
 
 
+@pytest.mark.parametrize("char, expected", params_inuktitut)
+def test_encode_chars_inuktitut_sms(char, expected):
+    assert SanitiseSMS.encode_char(char) == expected
+
+
 @pytest.mark.parametrize(
     "codepoint, char",
     [