/tsimapiak/parse2.py |
---|
15,7 → 15,7 |
#prefixesv = ur"(?P<vpr>(?:nì|sä|tì|rä'ä |ke )?)" |
def parseword(wordin): |
ret = {"word": {"id": 0, "navi": u" ".join(wordin), "infix": u"", "type": u""}} |
ret = {"word": {"id": 0, "navi": u"[" + u" ".wordin[0] + u"]", "infix": u"", "type": u""}} |
for word in wordlist: |
foundit = True |
foundprefs = [] |
67,14 → 67,18 |
if foundit == True: |
foundword = word |
break |
ret["pref"] = foundprefs |
ret["post"] = foundposts |
ret["inf"] = foundins |
if foundit == True: |
ret["pref"] = foundprefs |
ret["post"] = foundposts |
ret["inf"] = foundins |
ret["word"] = foundword |
return ret |
def parsesent(sent): |
sent = sent.strip().lower() |
sent = re.sub(ur"[^\w ]",u"",sent) |
sent = re.sub(ur"\ +",u" ",sent) |
sent = sent.split(u" ") |
ret = [] |
left = len(sent) |
while left: |
/tsimapiak/dbconnector.py |
---|
13,9 → 13,9 |
FROM `metaWords` |
ORDER BY NL DESC"""): |
if row["infixes"]: |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["infixes"], "type": row["partOfSpeech"]}) |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["infixes"].lower(), "type": row["partOfSpeech"]}) |
else: |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["navi"], "type": row["partOfSpeech"]}) |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["navi"].lower(), "type": row["partOfSpeech"]}) |
db.close() |
return ret |
27,9 → 27,9 |
FROM `metaWords` |
WHERE navi = ?""",word): |
if row["infixes"]: |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["infixes"], "type": row["partOfSpeech"]}) |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["infixes"].lower(), "type": row["partOfSpeech"]}) |
else: |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["navi"], "type": row["partOfSpeech"]}) |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["navi"].lower(), "type": row["partOfSpeech"]}) |
db.close() |
return ret |
/webapp/main.py |
---|
62,10 → 62,10 |
def post(self): |
try: |
word = self.get_argument("word").strip() |
word = self.get_argument("word") |
except: |
self.redirect("/parse2") |
out = parse2.parsesent(word.split(u" ")) |
out = parse2.parsesent(word) |
self.render("templates/parse2.html", last=word, out=out) |
application = tornado.web.Application([ |