| 22,6 → 22,7 |
|---|
| |
| import tsimapiak.dbconnector as dbconnector |
| import tsimapiak.parsenum as parsenum |
| import itertools |
| import re |
| |
| #wordlist = [{"id": 0, "navi": u"tawtute", "infix": u"tawtute", "type": u"n."}] + dbconnector.getnavilist() + [{"id": 0, "navi": u"na'vi", "infix": u"na'vi", "type": u"n."}] # XXX HACK - extra proper nouns |
| 88,11 → 89,35 |
|---|
| # Let's lenit the dictionary |
| extrawords = [] |
| for word in wordlist: |
| for letter, replacement in LENIT: |
| if word["navi"].startswith(letter): |
| new_word = word["navi"].replace(letter, replacement, 1) |
| new_infix = word["infix"].replace(letter, replacement, 1) |
| extrawords.append({"id": word["id"], "navi": new_word, "infix": new_infix, "type": word["type"], "lenited": True}) |
| splitword = word["navi"].split(" ") |
| splitinfix = word["infix"].split(" ") |
| lenitword = {} |
| lenitinfix = {} |
| for i, wor in enumerate(splitword): |
| for letter, replacement in LENIT: |
| if wor.startswith(letter): |
| lenitword[i] = wor.replace(letter, replacement, 1) |
| lenitinfix[i] = splitinfix[i].replace(letter, replacement, 1) |
| break |
| |
| s = list(lenitword.keys()) |
| for lenits in itertools.chain.from_iterable(itertools.combinations(s, r) for r in range(1, len(s)+1)): |
| new_word = "" |
| new_infix = "" |
| for i, wor in enumerate(splitword): |
| if i in lenits: |
| new_word += lenitword[i] |
| new_infix += lenitinfix[i] |
| else: |
| new_word += wor |
| new_infix += splitinfix[i] |
| new_word += " " |
| new_infix += " " |
| print(f"Generated lenited {new_word} from {word['navi']}") |
| new_word = new_word[:-1] |
| new_infix = new_infix[:-1] |
| extrawords.append({"id": word["id"], "navi": new_word, "infix": new_infix, "type": word["type"], "lenited": True}) |
| |
| wordlist = sorted(wordlist + extrawords, key=lambda x: len(x["navi"]) * 2 + (0 if x["lenited"] else 1), reverse=True) |
| |
| def parseword(wordin): |