unicodedata: add ot_tag_to_script function

returns the Unicode script code for a given OpenType script tag, or None if no match is found

Lib/fontTools/unicodedata/OTTags.py

@@ -35,3 +35,7 @@ NEW_SCRIPT_TAGS = {
     "Telu": ("tel2",),
     "Mymr": ("mym2",),
 }
+
+NEW_SCRIPT_TAGS_REVERSED = {
+    value: key for key, values in NEW_SCRIPT_TAGS.items() for value in values
+}

Lib/fontTools/unicodedata/__init__.py

@@ -40,6 +40,7 @@ __all__ = [tostr(s) for s in (
     "script_code",
     "script_horizontal_direction",
     "ot_tags_from_script",
+    "ot_tag_to_script",
 )]
 
 
@@ -239,3 +240,37 @@ def ot_tags_from_script(script_code):
         script_tags.reverse()  # last in, first out
 
     return script_tags
+
+
+def ot_tag_to_script(tag):
+    """ Return the Unicode script code for the given OpenType script tag, or
+    None for "DFLT" tag or if there is no Unicode script associated with it.
+    Raises ValueError if the tag is invalid.
+    """
+    tag = tostr(tag).strip()
+    if not tag or " " in tag or len(tag) > 4:
+        raise ValueError("invalid OpenType tag: %r" % tag)
+
+    while len(tag) != 4:
+        tag += str(" ")  # pad with spaces
+
+    if tag == OTTags.DEFAULT_SCRIPT:
+        # it's unclear which Unicode script the "DFLT" OpenType tag maps to,
+        # so here we return None
+        return None
+
+    if tag in OTTags.NEW_SCRIPT_TAGS_REVERSED:
+        return OTTags.NEW_SCRIPT_TAGS_REVERSED[tag]
+
+    # This side of the conversion is fully algorithmic
+
+    # Any spaces at the end of the tag are replaced by repeating the last
+    # letter. Eg 'nko ' -> 'Nkoo'.
+    # Change first char to uppercase
+    script_code = tag[0].upper() + tag[1]
+    for i in range(2, 4):
+        script_code += (script_code[i-1] if tag[i] == " " else tag[i])
+
+    if script_code not in Scripts.NAMES:
+        return None
+    return script_code

Tests/unicodedata_test.py

@@ -218,6 +218,26 @@ def test_ot_tags_from_script():
     assert unicodedata.ot_tags_from_script("Aaaa") == ["DFLT"]
 
 
+def test_ot_tag_to_script():
+    assert unicodedata.ot_tag_to_script("latn") == "Latn"
+    assert unicodedata.ot_tag_to_script("kana") == "Kana"
+    assert unicodedata.ot_tag_to_script("DFLT") == None
+    assert unicodedata.ot_tag_to_script("aaaa") == None
+    assert unicodedata.ot_tag_to_script("beng") == "Beng"
+    assert unicodedata.ot_tag_to_script("bng2") == "Beng"
+    assert unicodedata.ot_tag_to_script("dev2") == "Deva"
+    assert unicodedata.ot_tag_to_script("gjr2") == "Gujr"
+    assert unicodedata.ot_tag_to_script("yi  ") == "Yiii"
+    assert unicodedata.ot_tag_to_script("nko ") == "Nkoo"
+    assert unicodedata.ot_tag_to_script("vai ") == "Vaii"
+    assert unicodedata.ot_tag_to_script("lao ") == "Laoo"
+    assert unicodedata.ot_tag_to_script("yi") == "Yiii"
+
+    for invalid_value in ("", " ", "z zz", "zzzzz"):
+        with pytest.raises(ValueError, match="invalid OpenType tag"):
+            unicodedata.ot_tag_to_script(invalid_value)
+
+
 def test_script_horizontal_direction():
     assert unicodedata.script_horizontal_direction("Latn") == "LTR"
     assert unicodedata.script_horizontal_direction("Arab") == "RTL"