| /webapp/static/favicon.ico |
|---|
| Cannot display: file marked as a binary type. |
| svn:mime-type = application/octet-stream |
| /webapp/templates/translate.html |
|---|
| 0,0 → 1,68 |
| {% 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" id="lang"> |
| <option value="eng" selected="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="Translate!" /> |
| </form> |
| {% if out %} |
| <table border="1"> |
| <tr> |
| <th>Words</th> |
| <th>Translated</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> |
| {% if lang != "eng" %} |
| <script type="text/javascript"> |
| if("{{ lang }}" == "hu"){ |
| document.getElementById("lang").selectedIndex = 1 |
| } |
| if("{{ lang }}" == "de"){ |
| document.getElementById("lang").selectedIndex = 2 |
| } |
| if("{{ lang }}" == "est"){ |
| document.getElementById("lang").selectedIndex = 3 |
| } |
| if("{{ lang }}" == "ptbr"){ |
| document.getElementById("lang").selectedIndex = 4 |
| } |
| </script> |
| {% end %} |
| {% end %} |
| /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, lang="eng") |
| 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, lang=lang) |
| 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__": |
| /tsimapiak/parse.py |
|---|
| 10,8 → 10,8 |
| infixes1 = (u"awn", u"eyk", u"us", u"äp", u"") |
| infixes2 = (u"ìyev", u"iyev", u"ìmìy", u"arm", u"asy", u"ilv", u"ìmv", u"imv", u"ìrm", u"irv", u"ìsy", u"aly", u"ary", u"ìly", u"ìry", u"ìlm", u"alm", u"am", u"ay", u"er", u"ìm", u"iv", u"ìy", u"ol", u"") |
| infixes3 = (u"äng", u"ats", u"eiy", u"ei", u"uy", u"") |
| prefixes = (u"tsay", u"fay", u"fra", u"pxe", u"fne", u"tsa", u"pe", u"le", u"nì", u"sä", u"tì", u"ay", u"me", u"fì", u"ke", u"a") |
| adpositions = (u"mungwrr", u"kxamlä", u"pximaw", u"pxisre", u"tafkip", u"nemfa", u"takip", u"mìkam", u"teri", u"fkip", u"luke", u"pxel", u"pxaw", u"rofa", u"ìla", u"fpi", u"ftu", u"kip", u"lok", u"maw", u"sre", u"sìn", u"vay", u"eo", u"fa", u"hu", u"io", u"ka", u"mì", u"na", u"ne", u"ro", u"ta", u"uo", u"wä", u"äo", u"to") |
| prefixes = (u"tsay", u"say", u"fay", u"fra", u"pxe", u"fne", u"tsa", u"sa", u"pe", u"fe", u"le", u"nì", u"sä", u"tì", u"sì", u"ay", u"me", u"fì", u"ke", u"he", u"a") |
| adpositions = (u"mungwrr", u"kxamlä", u"pximaw", u"pxisre", u"tafkip", u"nemfa", u"takip", u"mìkam", u"teri", u"fkip", u"luke", u"pxel", u"pxaw", u"rofa", u"ìlä", u"fpi", u"ftu", u"kip", u"lok", u"maw", u"sre", u"sìn", u"vay", u"eo", u"fa", u"hu", u"io", u"ka", u"mì", u"na", u"ne", u"ro", u"ta", u"uo", u"wä", u"äo", u"to", u"sì") |
| postfixes = adpositions + (u"tsyìp", u"eyä", u"ìri", u"ìl", u"it", u"lo", u"ri", u"ru", u"ti", u"ur", u"ve", u"yä", u"ya", u"tu", u"vi", u"yu", u"an", u"ng", u"ke", u"e", u"o", u"l", u"t", u"y", u"a", u"ä", u"r") |
| #prefixesn = ur"(?P<npr>(?:(?:fì|tsa)?(?:me|pxe|ay|fra)?|(?:fay)?|(?:tsay)?)(?:fne)?(?:tì|sä)?" |
| #prefixesv = ur"(?P<vpr>(?:nì|sä|tì|rä'ä |ke )?)" |
| 26,6 → 26,7 |
| foundposts = [] |
| lenited = False |
| splitword = word["infix"].split(u" ") |
| foundins = [u"", u"", u""] |
| if len(wordin) < len(splitword): |
| foundit = False |
| next |
| 35,7 → 36,6 |
| foundprefs.append([]) |
| foundposts.append([]) |
| center = u"" |
| foundins = [u"", u"", u""] |
| pre = [] |
| post = [] |
| if u"<1>" in splitword[wor]: |
| 128,4 → 128,4 |
| word = parseword(sent[-left:]) |
| left -= len(word["word"]["navi"].split(" ")) |
| ret.append(word) |
| return ret |
| return ret |
| /tsimapiak/translate.py |
|---|
| 0,0 → 1,43 |
| # -*- coding: utf-8 -*- |
| import parse |
| import dbconnector |
| infixes1 = ((u"awn", u"P.PART"), (u"eyk", u"CAUS"), (u"us", u"A.PART"), (u"äp", u"REFL.")) |
| infixes2 = ((u"ìyev", u"FUT.SUBJ"), (u"iyev", u"FUT.SUBJ"), (u"ìmìy", u"REC.PAST.REC.FUT"), (u"arm", u"IMPF.PAST"), (u"asy", u"FUT.D"), (u"ilv", u"PRES.PER.SUBJ"), (u"ìmv", u"REC.PAST.SUBJ"), (u"imv", u"PAST.SUBJ"), (u"ìrm", u"IMPF.REC.PAST"), (u"irv", u"PRES.IMPF.SUBJ"), (u"ìsy", u"IMM.FUT.D"), (u"aly", u"PERF.FUT"), (u"ary", u"IMPF.FUT"), (u"ìly", u"PERF.IMM.FUT"), (u"ìry", u"IMPF.IMM.FUT"), (u"ìlm", u"PERF.REC.PAST"), (u"alm", u"PERF.PAST"), (u"am", u"PAST."), (u"ay", u"FUT."), (u"er", u"IMPF."), (u"ìm", u"REC.PAST"), (u"iv", u"SUBJ."), (u"ìy", u"IMM.FUT"), (u"ol", u"PERF.")) |
| infixes3 = ((u"äng", u"PEJ."), (u"ats", u"INFR."), (u"eiy", u"LAUD."), (u"ei", u"LAUD."), (u"uy", u"HON.")) |
| prefixes = ((u"tsay", u"those"), (u"say", u"those-LENTD"), (u"fay", u"these"), (u"fra", u"every"), (u"pxe", u"TRI."), (u"fne", u"type"), (u"tsa", u"that"), (u"sa", u"that-LENTD"), (u"pe", u"what"), (u"fe", u"what-LENTD"), (u"le", u"ADJD."), (u"nì", u"ADVD."), (u"sä", u"INSTD."), (u"tì", u"NOUND."), (u"sì", u"NOUND.-LENTD"), (u"ay", u"PL."), (u"me", u"DU."), (u"fì", u"this"), (u"ke", u"not"), (u"he", u"not-LENTD"), (u"a", u"ADJ.POST")) |
| adpositions = ((u"mungwrr", u"except"), (u"kxamlä", u"through"), (u"pximaw", u"right.after"), (u"pxisre", u"right.before"), (u"tafkip", u"from.up.among"), (u"nemfa", u"into.inside"), (u"takip", u"from among"), (u"mìkam", u"between"), (u"teri", u"about.concerning"), (u"fkip", u"up.among"), (u"luke", u"without"), (u"pxel", u"like.as"), (u"pxaw", u"around"), (u"rofa", u"beside.alongside"), (u"ìlä", u"by.via.following"), (u"fpi", u"for.the.sake/benefit.of"), (u"ftu", u"from.direction"), (u"kip", u"among"), (u"lok", u"close.to"), (u"maw", u"after.time"), (u"sre", u"before.time"), (u"sìn", u"on.onto"), (u"vay", u"up.to"), (u"eo", u"before.in.front.of"), (u"fa", u"with.by.means.of"), (u"hu", u"with.accompaniment"), (u"io", u"above"), (u"ka", u"across"), (u"mì", u"in.on"), (u"na", u"like.as"), (u"ne", u"to.towards"), (u"ro", u"at.locative"), (u"ta", u"from"), (u"uo", u"behind"), (u"wä", u"against.opposition"), (u"äo", u"below"), (u"to", u"than"), (u"sì", u"and")) |
| postfixes = adpositions + ((u"tsyìp", u"DIM."), (u"eyä", u"GEN."), (u"ìri", u"TOP."), (u"ìl", u"ERG."), (u"it", u"ACC"), (u"lo", u"MULT."), (u"ri", u"TOP."), (u"ru", u"DAT."), (u"ti", u"ACC."), (u"ur", u"DAT."), (u"ve", u"ORD."), (u"yä", u"GEN."), (u"ya", u"VOC."), (u"tu", u"OBJD."), (u"vi", u"PART."), (u"yu", u"AGENTD."), (u"an", u"MASC."), (u"ng", u"INCL."), (u"ke", u"not"), (u"e", u"FEM."), (u"o", u"INDEF."), (u"l", u"ERG."), (u"t", u"ACC."), (u"y", u"GEN."), (u"a", u"ADJ.PRE"), (u"ä", u"GEN."), (u"r", u"DAT.")) |
| 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"] |
| if word["inf"][0] != u"": |
| for fix in infixes1: |
| if fix[0] == word["inf"][0]: |
| word["translated"] += '-' + fix[1] |
| if word["inf"][1] != u"": |
| for fix in infixes2: |
| if fix[0] == word["inf"][1]: |
| word["translated"] += '-' + fix[1] |
| if word["inf"][2] != u"": |
| for fix in infixes3: |
| if fix[0] == word["inf"][2]: |
| word["translated"] += '-' + fix[1] |
| for temp in word["pref"]: # double array? WTF? |
| for navf in temp: |
| for fix in prefixes: |
| if fix[0] == navf: |
| word["translated"] += '-' + fix[1] |
| for temp in word["post"]: # double array? WTF? |
| for navf in temp: |
| for fix in postfixes: |
| if fix[0] == navf: |
| word["translated"] += '-' + fix[1] |
| if word["len"]: |
| word["translated"] += '-' + 'LENTD' |
| return sent |
| /tsimapiak/parsenum.py |
|---|
| 1,107 → 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"] |
| numord = [u"kewve", |
| u"'awve", |
| u"muve", |
| u"pxeyve", |
| u"tsìve", |
| u"mrrve", |
| u"puve", |
| u"kive"] |
| rem = [u"aw", |
| u"mun", |
| u"pey", |
| u"sìng", |
| u"mrr", |
| u"fu", |
| u"hin"] |
| remord = [u"awve", |
| u"muve", |
| u"peyve", |
| u"sìve", |
| u"mrrve", |
| u"fuve", |
| u"hive"] |
| base = [u"", |
| u"me", |
| u"pxe", |
| u"tsì", |
| u"mrr", |
| u"pu", |
| u"ki"] |
| numre = \ |
| u"^(a?)(?:(?:(" + "|".join(base) + u")zaza(?=m)(?:ve(?=$))?)?" + \ |
| u"(?:(" + "|".join(base) + u")voza(?=m)(?:ve(?=$))?)?" + \ |
| u"(?:(" + "|".join(base) + u")za(?=m)(?:ve(?=$))?)?" + \ |
| u"(?:(" + "|".join(base) + u")(?:vol|vo(?=a|$))(?:ve(?=$))?)?" + \ |
| u"(?:" + "|".join(remord + rem) + u"))|" + \ |
| u"(?:" + "|".join(numord + num) + u")?(a?)$" |
| 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/dbconnector.py |
|---|
| 20,16 → 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"]}) |
| FROM `localizedWords` |
| WHERE id = %s AND languageCode = %s""",wid,language): |
| ret = row["localized"] |
| break |
| db.close() |
| return ret |