/webapp/main.py |
---|
12,6 → 12,7 |
from tsimapiak import parsenum |
from tsimapiak import dbconnector |
from tsimapiak import parse |
from tsimapiak import translate |
class Index(tornado.web.RequestHandler): |
def get(self): |
57,6 → 58,19 |
out = parse.parsesent(word) |
self.render("templates/parse.html", last=word, out=out) |
class Translate(tornado.web.RequestHandler): |
def get(self): |
self.render("templates/translate.html", last="", out=None) |
def post(self): |
try: |
word = self.get_argument("word") |
lang = self.get_argument("lang") |
except: |
self.redirect("/translate") |
out = translate.translatesent(word, lang) |
self.render("templates/translate.html", last=word, out=out) |
settings = { |
"static_path": os.path.join(os.path.dirname(__file__), "static") |
} |
66,7 → 80,8 |
("/number", Number), |
("/restart", Restart), |
("/testdb", TestDB), |
("/parse", Parse) |
("/parse", Parse), |
("/translate", Translate) |
], **settings) |
if __name__ == "__main__": |
/webapp/templates/translate.html |
---|
0,0 → 1,52 |
{% extends "base.html" %} |
{% block title %}Translator{% end %} |
{% block body %} |
<b>Na'vi sentence:</b><br /> |
<form action="/translate" method="post"> |
<input id="word" name="word" type="text" value="{{last}}" style="width: 100%;" /> |
<select name="lang"> |
<option value="eng" selected="">English</option> |
<option value="hu">Hungarian - Magyar</option> |
<option value="de">German - Deutsch</option> |
<option value="est">Estonian - Eesti</option> |
<option value="ptbr">Brazilian Portuguese - Português do Brasil</option> |
</select> |
<input name="btn" type="submit" value="Parse!" /> |
</form> |
{% if out %} |
<table border="1"> |
<tr> |
<th>Words</th> |
<th>English</th> |
<th>Parts</th> |
<th>Data</th> |
</tr> |
{% for wor in out %} |
<tr> |
<td rowspan="4">{{ wor["word"]["navi"] }}</td> |
<td rowspan="4">{{ wor["translated"] }}</td> |
<td>Infixes:</td> |
<td>{{ u", ".join(wor["inf"]) }}</td> |
</tr> |
<tr> |
<td>Prefixes:</td> |
<td>{{ u"; ".join(u", ".join(x) for x in wor["pref"]) }}</td> |
</tr> |
<tr> |
<td>Postfixes:</td> |
<td>{{ u"; ".join(u", ".join(x) for x in wor["post"]) }}</td> |
</tr> |
<tr> |
<td>Lenited:</td> |
<td>{{ str(wor["len"]) }}</td> |
</tr> |
{% end %} |
</table> |
{% end %} |
<p>This program uses Eana Eltu for the list of words and infix positions (but nothing else), created by Tuiq and Taronyu. Thanks also go to the rest of the Learn Na'vi community!</p> |
<script type="text/javascript"> |
document.getElementById("word").focus(); |
</script> |
{% end %} |
/webapp/templates/parse.html |
---|
12,7 → 12,6 |
<table border="1"> |
<tr> |
<th>Words</th> |
<th>English</th> |
<th>Parts</th> |
<th>Data</th> |
</tr> |
19,7 → 18,6 |
{% for wor in out %} |
<tr> |
<td rowspan="4">{{ wor["word"]["navi"] }}</td> |
<td rowspan="4">{{ wor["translated"] }}</td> |
<td>Infixes:</td> |
<td>{{ u", ".join(wor["inf"]) }}</td> |
</tr> |
/tsimapiak/parsenum.py |
---|
1,90 → 1,129 |
#!/usr/bin/python |
# -*- coding: utf-8 -*- |
import re |
num = [u"kew", |
u"'aw", |
u"mune", |
u"pxey", |
u"tsìng", |
u"mrr", |
u"pukap", |
u"kinä"] |
rem = [u"aw", |
u"mun", |
u"pey", |
u"sìng", |
u"mrr", |
u"fu", |
u"hin"] |
base = [u"", |
u"me", |
u"pxe", |
u"tsì", |
u"mrr", |
u"pu", |
u"ki"] |
numre = \ |
u"^(a?)(?:(" + "|".join(base) + u")zazam??)?" + \ |
u"(?:(" + "|".join(base) + u")vozam??)?" + \ |
u"(?:(" + "|".join(base) + u")zam??)?" + \ |
u"(?:(" + "|".join(base) + u")vo(?:l(?=a|))?)?" + \ |
u"((?:" + "|".join(rem) + u")|" + \ |
u"(?:" + "|".join(num) + u"))?((?:ve)?)(a?)$" |
numre = re.compile(numre) |
def parse(numin): |
if numin in (u"a", u"aa", u"ave", u"avea", u"ve", u"vea"): |
return None |
try: |
mat = numre.match(numin).groups() |
except: |
return None |
numout = 0 |
numoct = 0 |
try: |
numout += rem.index(mat[5]) + 1 |
numoct += rem.index(mat[5]) + 1 |
except: |
try: |
numout += num.index(mat[5]) |
numoct += num.index(mat[5]) |
except: pass |
try: |
numout += (base.index(mat[4]) + 1) * 8 |
numoct += (base.index(mat[4]) + 1) * 10 |
except: pass |
try: |
numout += (base.index(mat[3]) + 1) * 8**2 |
numoct += (base.index(mat[3]) + 1) * 10**2 |
except: pass |
try: |
numout += (base.index(mat[2]) + 1) * 8**3 |
numoct += (base.index(mat[2]) + 1) * 10**3 |
except: pass |
try: |
numout += (base.index(mat[1]) + 1) * 8**4 |
numoct += (base.index(mat[1]) + 1) * 10**4 |
except: pass |
retnum = unicode(numout) |
if mat[6] != u"": |
retnum += u"." |
prefs = [] |
posts = [] |
if mat[0] != u"": |
prefs.append(mat[0]) |
if mat[6] != u"": |
posts.append(mat[6]) |
if mat[7] != u"": |
posts.append(mat[7]) |
return {"word": {"id": 0, "navi": retnum, "infix": u"", "type": u""}, "pref": [prefs], "post": [posts], "inf": [u"", u"", u""], "len": False, "dec": numout, "oct": numoct} |
#return numout, numoct |
if __name__ == "__main__": |
print parse(u"mrrvolawvea") |
#!/usr/bin/python |
# -*- coding: utf-8 -*- |
num = [u"kew", |
u"'aw", |
u"mune", |
u"pxey", |
u"tsìng", |
u"mrr", |
u"pukap", |
u"kinä"] |
numord = [u"kew", |
u"'aw", |
u"mu", |
u"pxey", |
u"tsì", |
u"mrr", |
u"pu", |
u"ki"] |
rem = [u"aw", |
u"mun", |
u"pey", |
u"sìng", |
u"mrr", |
u"fu", |
u"hin"] |
remord = [u"aw", |
u"mu", |
u"pey", |
u"sì", |
u"mrr", |
u"fu", |
u"hi"] |
base = [u"", |
u"me", |
u"pxe", |
u"tsì", |
u"mrr", |
u"pu", |
u"ki"] |
def parse(numin): |
if u"mm" in numin: |
return None |
if (numin[0] == u"a") and (numin[len(numin)-1] == u"a"): |
return None |
prefs = [] |
posts = [] |
outoct = 0 |
outdec = 0 |
ret = {"word": {"id": 0, "navi": u"", "infix": u"", "type": u""}, "pref": [prefs], "post": [posts], "inf": [u"", u"", u""], "len": False, "dec": outdec, "oct": outoct} |
if numin[0] == u"a": |
prefs.append(u"a") |
numin = numin[1:] |
if numin[len(numin)-1] == u"a": |
posts.append(u"a") |
numin = numin[:-1] |
if numin[-2:] == u"ve": |
posts.append(u"ve") |
numin = numin[:-2] |
#base numbers |
for n in range(len(num)): |
if u"ve" in posts: |
if numin == numord[n]: |
outoct = n |
outdec = n |
ret["word"]["navi"] = unicode(outdec) + u"." |
ret["dec"] = outdec |
ret["oct"] = outoct |
return ret |
else: |
if numin == num[n]: |
outoct = n |
outdec = n |
ret["word"]["navi"] = unicode(outdec) |
ret["dec"] = outdec |
ret["oct"] = outoct |
return ret |
#other numbers |
for n in range(len(base)): |
if numin.startswith(base[n] + u"zazam"): |
outoct += (n+1) * (10**4) |
outdec += (n+1) * (8**4) |
numin = numin[len(base[n]) + 5:] |
for n in range(len(base)): |
if numin.startswith(base[n] + u"vozam"): |
outoct += (n+1) * (10**3) |
outdec += (n+1) * (8**3) |
numin = numin[len(base[n]) + 5:] |
for n in range(len(base)): |
if numin.startswith(base[n] + u"zam"): |
outoct += (n+1) * (10**2) |
outdec += (n+1) * (8**2) |
numin = numin[len(base[n]) + 3:] |
for n in range(len(base)): |
if numin.startswith(base[n] + u"vol"): |
outoct += (n+1) * 10 |
outdec += (n+1) * 8 |
numin = numin[len(base[n]) + 3:] |
if numin.startswith(base[n] + u"vo"): |
outoct += (n+1) * 10 |
outdec += (n+1) * 8 |
numin = numin[len(base[n]) + 2:] |
for n in range(len(rem)): |
if u"ve" in posts: |
if numin == remord[n]: |
outoct += n + 1 |
outdec += n + 1 |
numin = u"" |
else: |
if numin == rem[n]: |
outoct += n + 1 |
outdec += n + 1 |
numin = u"" |
if numin == u"": |
ret["word"]["navi"] = unicode(outdec) if not u"ve" in posts else unicode(outdec) + u"." |
ret["dec"] = outdec |
ret["oct"] = outoct |
return ret |
else: |
return None |
if __name__ == "__main__": |
print parse(u"mevolawve") |
/tsimapiak/parse.py |
---|
127,9 → 127,5 |
if word == None: |
word = parseword(sent[-left:]) |
left -= len(word["word"]["navi"].split(" ")) |
if word["word"]["id"] != 0: |
word["translated"] = dbconnector.translate(word["word"]["id"],"eng") |
else: |
word["translated"] = word["word"]["navi"] |
ret.append(word) |
return ret |
/tsimapiak/translate.py |
---|
0,0 → 1,10 |
import parse |
def translatesent(sent, lang): |
sent = parse.parsesent(sent) |
for word in sent: |
if word["word"]["id"] != 0: |
word["translated"] = dbconnector.translate(word["word"]["id"],lang) |
else: |
word["translated"] = word["word"]["navi"] |
return sent |
/tsimapiak/dbconnector.py |
---|
20,26 → 20,13 |
db.close() |
return ret |
def getnavi(word): |
ret = [] |
def translate(wid,language): |
db = tornado.database.Connection("127.0.0.1", "navi", user="navi", password="navi") |
for row in db.query(""" |
SELECT * |
FROM `metaWords` |
WHERE navi = ?""",word): |
if row["infixes"]: |
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"].lower(), "type": row["partOfSpeech"]}) |
db.close() |
return ret |
def translate(id,language): |
db = tornado.database.Connection("127.0.0.1", "navi", user="navi", password="navi") |
for row in db.query(""" |
SELECT * |
FROM `localizedWords` |
WHERE id = ? AND languageCode = ?""",id,language): |
WHERE id = %s AND languageCode = %s""",wid,language): |
ret = row["localized"] |
break |
db.close() |
return ret |
return ret |