format: Add a function for formatting sort keys

This function casefolds the input string and makes a series of
substitutions before splitting the string into a tuple of strings that
can be compared against.

Signed-off-by: Anna Schumaker <Anna@NoWheyCreamery.com>

emmental/format.py

@@ -1,5 +1,8 @@
 # Copyright 2022 (c) Anna Schumaker
 """Helper functions for formatting strings."""
+import re
+
+IGNORE_WORDS = set(["a", "an", "the", ""])
 
 
 def search(input: str) -> str | None:
@@ -19,3 +22,14 @@ def search(input: str) -> str | None:
         input += "*"
 
     return input
+
+
+def sort_key(input: str) -> tuple:
+    """Translate the input string into a sort key."""
+    if len(input) == 0:
+        return ()
+    input = re.sub(r"[\"\'’“”]", "", input.casefold())
+    res = re.split(r"[ /_-]", input)
+    if len(res) > 1 and res[0] in IGNORE_WORDS:
+        res = res[1:]
+    return tuple(res)

tests/test_format.py

@@ -18,3 +18,30 @@ class TestFormatter(unittest.TestCase):
         self.assertEqual(format.search("*Test$"), "*test")
         self.assertEqual(format.search("^"), "*")
         self.assertEqual(format.search("$"), "*")
+
+    def test_ignore_words(self):
+        """Test words that aren't included at the start of the sort key."""
+        self.assertSetEqual(format.IGNORE_WORDS, set(["a", "an", "the", ""]))
+
+    def test_sort_key(self):
+        """Test translating a string into a sort key."""
+        self.assertEqual(format.sort_key(""), ())
+        self.assertEqual(format.sort_key("Test Text"), ("test", "text"))
+        self.assertEqual(format.sort_key("Tést Téxt"), ("tést", "téxt"))
+        self.assertEqual(format.sort_key("A Test"), ("test",))
+        self.assertEqual(format.sort_key("A"), ("a",))
+        self.assertEqual(format.sort_key("An Extra Test"), ("extra", "test",))
+        self.assertEqual(format.sort_key("An"), ("an",))
+        self.assertEqual(format.sort_key("The Test"), ("test",))
+        self.assertEqual(format.sort_key("The"), ("the",))
+        self.assertEqual(format.sort_key("Test The"), ("test", "the"))
+        self.assertEqual(format.sort_key("Test-Text"), ("test", "text"))
+        self.assertEqual(format.sort_key("Test_Text"), ("test", "text"))
+        self.assertEqual(format.sort_key("\"Test\" Text"), ("test", "text"))
+        self.assertEqual(format.sort_key("“Test” Text"), ("test", "text"))
+        self.assertEqual(format.sort_key("'Test' Text"), ("test", "text"))
+        self.assertEqual(format.sort_key("Fish N’ Chips"),
+                         ("fish", "n", "chips"))
+        self.assertEqual(format.sort_key("ac/dc"), ("ac", "dc"))
+        self.assertEqual(format.sort_key("/a/B/c/D"),
+                         ("a", "b", "c", "d"))