dawg: build committed dictionary DAWGs (en SOWPODS, ru Scrabble, ru Эрудит)

- cmd/builddict: add -alphabet latin|russian (russian = alphabet.Embedded(LangRu)).
- dictprep/fold_yo.py: fold Ё→Е and de-dup, the Эрудит dictionary prep.
- Makefile: `make dawg` rebuilds dawg/{en_sowpods,ru_scrabble,ru_erudit}.dawg.
- dawg/: committed DAWGs verified by enumeration — 267752 / 83385 / 83343 words.

cmd/builddict/main.go

@@ -1,6 +1,5 @@
-// Command builddict converts a word list into a serialized DAWG, cached under testdata
-// for the tests and the benchmark. By default it reads the English SOWPODS list from
-// the dictionaries submodule.
+// Command builddict converts a word list into a serialized DAWG. By default it reads the
+// English SOWPODS list (Latin alphabet); pass -alphabet russian for the Cyrillic lists.
 package main
 
 import (
@@ -23,9 +22,18 @@ func main() {
 	name := flag.String("name", "sowpods", "base name for the output file")
 	minLen := flag.Int("min", 2, "minimum word length")
 	maxLen := flag.Int("max", 15, "maximum word length")
+	alpha := flag.String("alphabet", "latin", "alphabet: latin (English) or russian")
 	flag.Parse()
 
-	idx := alphabet.Latin()
+	var idx alphabet.Indexer
+	switch *alpha {
+	case "latin":
+		idx = alphabet.Latin()
+	case "russian":
+		idx = alphabet.Embedded(alphabet.Langs.LangRu)
+	default:
+		log.Fatalf("unknown -alphabet %q (want latin or russian)", *alpha)
+	}
 
 	t0 := time.Now()
 	words, err := wordlist.Read(*dict, idx, *minLen, *maxLen)