| /webapp/templates/parse2.html |
|---|
| 0,0 → 1,20 |
| {% extends "base.html" %} |
| {% block title %}Word parser{% end %} |
| {% block body %} |
| <b>Na'vi word:</b><br /> |
| <form action="/parse2" method="post"> |
| <input id="word" name="word" type="text" value="{{last}}" style="width: 100%;" /> |
| <input name="btn" type="submit" value="Parse!" /> |
| </form> |
| {% if type(out) == list %} |
| {{ out[0][1]}} <br /> |
| {% for elem in out[1:] %} |
| {{ elem }} <br /> |
| {% end %} |
| {% end %} |
| <script type="text/javascript"> |
| document.getElementById("word").focus(); |
| </script> |
| {% end %} |
| /webapp/templates/parse.html |
|---|
| 0,0 → 1,20 |
| {% extends "base.html" %} |
| {% block title %}Word parser{% end %} |
| {% block body %} |
| <b>Na'vi word:</b><br /> |
| <form action="/parse" method="post"> |
| <input id="word" name="word" type="text" value="{{last}}" style="width: 100%;" /> |
| <input name="btn" type="submit" value="Parse!" /> |
| </form> |
| {% if type(out) == list %} |
| {{ out[0]}} <br /> |
| {{ out[1]}} <br /> |
| {{ out[2]}} <br /> |
| {{ out[3]}} |
| {% end %} |
| <script type="text/javascript"> |
| document.getElementById("word").focus(); |
| </script> |
| {% end %} |
| /webapp/templates/base.html |
|---|
| 1,6 → 1,6 |
| <html> |
| <head> |
| <title>{% block title %}Title{% end %}</title> |
| <title>Tsim Apiak - {% block title %}Title{% end %}</title> |
| <style type="text/css"> |
| body { |
| background: #145179; |
| 14,6 → 14,10 |
| text-align: center; |
| font-size: 52px; |
| } |
| h2 { |
| text-align: center; |
| font-size: 24px; |
| } |
| #center { |
| background: #2594DE; |
| width: 760px; |
| 25,7 → 29,8 |
| </head> |
| <body> |
| <div id="center"> |
| <h1>{% block title %}Title{% end %}</h1> |
| <h1>Tsim Apiak</h1> |
| <h2>{% block title %}Title{% end %}</h2> |
| {% block body %}Body{% end %} |
| </div> |
| </body> |
| /webapp/templates/number.html |
|---|
| 1,6 → 1,6 |
| {% extends "base.html" %} |
| {% block title %}Na'vi number translator{% end %} |
| {% block title %}Number translator{% end %} |
| {% block body %} |
| <b>Na'vi number:</b><br /> |
| /webapp/main.py |
|---|
| 5,11 → 5,14 |
| import tornado.ioloop |
| import tornado.web |
| import tornado.autoreload |
| import tornado.database |
| import os |
| import re |
| from navi.parsenum import parse |
| from tsimapiak import parsenum |
| from tsimapiak import dbconnector |
| from tsimapiak import parse |
| from tsimapiak import parse2 |
| class Index(tornado.web.RequestHandler): |
| def get(self): |
| 24,7 → 27,7 |
| num = self.get_argument("num").strip() |
| except: |
| self.redirect("/number") |
| numout = parse(num.replace(" ","")) |
| numout = parsenum.parse(num.replace(" ","")) |
| if numout == None: |
| numout = -1 |
| self.render("templates/number.html", last=num, numout=numout) |
| 33,19 → 36,45 |
| def get(self): |
| os.system("/usr/bin/restartnavi") |
| class TestDB(tornado.web.RequestHandler): |
| def get(self): |
| text = "" |
| db = tornado.database.Connection("127.0.0.1", "navi", user="navi", password="navi") |
| for thing in db.query("SELECT * FROM test"): |
| text = "<br />".join((text, str(thing.id) + " - " + thing.asd)) |
| lis = dbconnector.getnavilist() |
| text = u"id | navi | infix | partofspeech<br />" |
| text += u"<br />".join(u" | ".join(unicode(y) for y in x) for x in lis) |
| self.write(text) |
| class Parse(tornado.web.RequestHandler): |
| def get(self): |
| self.render("templates/parse.html", last="", out=None) |
| def post(self): |
| try: |
| word = self.get_argument("word").strip() |
| except: |
| self.redirect("/parse") |
| out = parse.parsefix(word) |
| self.render("templates/parse.html", last=word, out=out) |
| class Parse2(tornado.web.RequestHandler): |
| def get(self): |
| self.render("templates/parse2.html", last="", out=None) |
| def post(self): |
| try: |
| word = self.get_argument("word").strip() |
| except: |
| self.redirect("/parse2") |
| out = parse2.parseword(word) |
| self.render("templates/parse2.html", last=word, out=out) |
| application = tornado.web.Application([ |
| ("/", Index), |
| ("/number", Number), |
| ("/restart", Restart), |
| ("/testdb", TestDB) |
| ("/testdb", TestDB), |
| ("/parse", Parse), |
| ("/parse2", Parse2) |
| ]) |
| if __name__ == "__main__": |
| /tsimapiak/parse2.py |
|---|
| 0,0 → 1,25 |
| #!/usr/bin/python |
| # -*- coding: utf-8 -*- |
| import re |
| import dbconnector |
| infixes0 = ur"(?P<in0>(?:awn|eyk|us|äp)?)" |
| infixes1 = ur"(?P<in1>(?:ìyev|iyev|ìmìy|arm|asy|ilv|ìmv|imv|ìrm|irv|ìsy|aly|ary|ìly|ìry|ìlm|alm|am|ay|er|ìm|iv|ìy|ol)?)" |
| infixes2 = ur"(?P<in2>(?:äng|ats|eiy|ei|uy)?)" |
| #prefixesn = ur"(?P<npr>(?:(?:fì|tsa)?(?:me|pxe|ay|fra)?|(?:fay)?|(?:tsay)?)(?:fne)?(?:tì|sä)?" |
| prefixes = ur"((?:ay|me|pxe|pe|a|le|nì|sä|tì|ke|fì|fay|tsa|tsay|fra|ke |kea |rä'ä )*)" |
| #postfixesv = ur"(?P<vpr>(?:nì|sä|tì|rä'ä |ke )?)" |
| def parseword(wordin): |
| wordfound = [0, u"", u"", u""] |
| wordre = None |
| ret = [wordfound, u"", u"", u""] |
| for word in dbconnector.getnavilist(): |
| wordre = u" ".join(prefixes + x + ur"(\w*?)" for x in word[2].split(u" ")).replace(u"<0><1>", infixes0 + infixes1).replace(u"<2>",infixes2) |
| rem = re.match(wordre,wordin) |
| if rem: |
| wordfound = word |
| ret = [wordfound] + list(rem.groups()) |
| break |
| return ret |
| /tsimapiak/parse.py |
|---|
| 0,0 → 1,86 |
| #!/usr/bin/python |
| # -*- coding: utf-8 -*- |
| import re |
| from dbconnector import getnavilist |
| wordlist = getnavilist() |
| infixes0 = [ u"awn", u"eyk", u"us", u"äp" ] |
| infixes1 = [ 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" ] |
| infixes2 = [ u"äng", u"ats", u"eiy", u"ei", u"uy" ] |
| # Returns array with Word,Infix 0,Infix 1,Infix 2,Case,Gender,Number suffixes,Inclusive,Indefinite,Vocative (suffix),Plural,Adposition,Adject pre,Adject suff,am/ay/tu/vi/yu,adverbial,nominalise,sä,fne,lenited? |
| def parsefix(original): |
| realword = u"" |
| infix0 = u"" |
| infix1 = u"" |
| infix2 = u"" |
| infix01 = u"" |
| infix_1 = u"" |
| infix_2 = u"" |
| for eachword in wordlist: |
| regex = re.sub(u" ",u"[^ ]* [^ ]*",eachword[2]) |
| regex = re.sub(u"^",u"[^ ]*",regex) |
| regex = re.sub(u"$",u"[^ ]*",regex) |
| regex = re.sub(u"<0><1>",u"[^ ]*",regex) |
| regex = re.sub(u"<2>",u"[^ ]*",regex) |
| if re.match(regex,original): |
| realword = eachword[2] |
| break |
| if realword == u"": |
| return [u"[" + original + u"]",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u""] |
| else: |
| if re.search(u"<",realword): |
| beginning = re.sub(u"<0><1>.*",u"",realword) |
| middle = re.sub(u".*<0><1>(.*)<2>.*",ur"\1",realword) |
| end = re.sub(u".*<2>",u"",realword) |
| infix01 = re.sub(u".*?" + re.sub(u"<0><1>",u"([^ ]*)",re.sub(u"<2>",u"[^ ]*",realword)) + u".*?",ur"\1",original) |
| infix_2 = re.sub(u".*?" + re.sub(u"<2>",u"([^ ]*)",re.sub(u"<0><1>",u"[^ ]*",realword)) + u".*?",ur"\1",original) |
| for eachinfix in infixes0: |
| if infix01.startswith(eachinfix): |
| infix0 = eachinfix |
| infix_1 = infix01[len(eachinfix):] |
| break |
| else: |
| infix0 = u"" |
| infix_1 = infix01 |
| gotinfix1 = False |
| for eachinfix in infixes1: |
| if infix_1.startswith(eachinfix): |
| infix1 = eachinfix |
| infix_1 = infix_1[len(eachinfix):] |
| if infix_1 != u"": |
| if re.search(u"<0><1><2>",realword): |
| infix_2 = infix_1 |
| else: |
| return [u"[" + original + u"]",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u""] |
| gotinfix1 = True |
| break |
| if gotinfix1 == False: |
| if re.search(u"<0><1><2>",realword): |
| if infix_1 == u"": |
| infix_2 = infix_1 |
| infix1 = u"" |
| elif infix_1 == u"": |
| infix1 = u"" |
| else: |
| return [u"[" + original + u"]",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u""] |
| gotinfix2 = False |
| for eachinfix in infixes2: |
| if infix_2.startswith(eachinfix): |
| infix2 = infix_2[:len(eachinfix)] |
| infix_2 = infix_2[len(eachinfix) - 1:] |
| gotinfix2 = True |
| break |
| if gotinfix2 == False or infix_2 != u"": |
| if infix_2.startswith(end): |
| suffixes = infix2[len(end) - 1:] + end |
| elif infix_2 == u"": |
| infix2 = u"" |
| else: |
| return [u"[" + original + u"]",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u""] |
| # print u"0" + unicode(infix0) + u" 1" + unicode(infix1) + u" 2" + unicode(infix2) |
| return [realword,infix0,infix1,infix2,u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u""] |
| else: |
| return [realword,u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u"",u""] |
| /tsimapiak/dbconnector.py |
|---|
| 0,0 → 1,70 |
| #!/usr/bin/python |
| # -*- coding: utf-8 -*- |
| import tornado.database |
| import re |
| def getnavilist(): |
| ret = [] |
| current = u"" |
| db = tornado.database.Connection("127.0.0.1", "navi", user="navi", password="navi") |
| for row in db.query(""" |
| SELECT *, CHAR_LENGTH(navi) AS NL |
| FROM `metaWords` |
| ORDER BY NL DESC"""): |
| infix = makeinfix(row) |
| ret.append([row["id"], row["navi"], infix, row["partOfSpeech"]]) |
| db.close() |
| return ret |
| def getnavi(word): |
| ret = [] |
| db = tornado.database.Connection("127.0.0.1", "navi", user="navi", password="navi") |
| for row in db.query(""" |
| SELECT * |
| FROM `metaWords` |
| WHERE navi = ?""",word): |
| infix = makeinfix(row) |
| ret.append([row["id"],row["navi"], infix, row["partOfSpeech"]]) |
| db.close() |
| return ret |
| def makeinfix(row): |
| if row["partOfSpeech"] in (u"v.", u"vin.", u"vtr."): |
| current = unicode(row["ipa"]) |
| current = current.replace(ur"ɛ",ur"e").replace(ur".",ur"").replace(ur"ɾ",ur"r") \ |
| .replace(ur"ɪ",ur"ì").replace(ur"ˈ",ur"").replace(ur"'",ur"x") \ |
| .replace(ur"ŋ",ur"ng").replace(ur"j",ur"y").replace(ur"ʔ",ur"'") \ |
| .replace(ur"æ",ur"ä").replace(ur"ˌ",ur"").replace(ur"\t{ts}",ur"ts") \ |
| .replace(ur"ṛ",ur"rr").replace(ur"ḷ",ur"ll").replace(ur"k̚",ur"k ") \ |
| .replace(ur"p̚",ur"p ").replace(ur"t̚",ur"t ").replace(ur"'̚",ur"' ") \ |
| .replace(u"\\",ur"").replace(ur"(",ur"").replace(ur")",ur"") \ |
| .replace(ur"[",ur"").replace(ur"]",ur"").replace(ur" "," ") \ |
| .strip() |
| current = re.sub(ur" or.*","",current) |
| current = re.sub(ur"z(.*)engk(.*)e",ur"z\1enk\2e",current) |
| current = re.sub(ur"t(.*)ì(m|n)\ ",ur"t\1ìng ",current) |
| current = current.split(ur"$cdot$") |
| if len(current) == 3: |
| current = current[0] + u"<0><1>" + current[1] + u"<2>" + current[2] |
| elif len(current) == 2: |
| current = current[0] + u"<0><1><2>" + current[1] |
| else: |
| current = u"<0><1><2>" + current[0] |
| else: |
| current = unicode(row["navi"]) |
| return current |
| #def gettrans(id, cod): |
| #ret = [] |
| #if cod not in (u"est",u"ptbr",u"de",u"eng",u"all"): |
| #return ret |
| #db = tornado.database.Connection("127.0.0.1", "navi", user="navi", password="navi") |
| #if cod == "all": |
| #for row in db.query(""" |
| #SELECT * |
| #FROM `metaWords` |
| #WHERE id = ?""",idd): |
| #infix = makeinfix(row) |
| #ret.append([row["id"],row["navi"], infix, row["partOfSpeech"]]) |
| #db.close() |