/GPL |
---|
File deleted |
/LICENCE |
---|
File deleted |
/APACHE_LICENCE |
---|
File deleted |
/dev/naviparse.py |
---|
0,0 → 1,92 |
# -*- coding: utf-8 -*- |
import re |
strings = [ u"oe", u"nga", u"k<0><1>am<2>e", u"t<0><1><2>ìng nari", u"s<0><1><2>i", u"t<0><1><2>ìng" ] |
infixes0 = [ u"awn", u"eyk", u"us", u"äp" ] |
infixes1 = [ u"ìyev", u"iyev", 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 strings: |
regex = re.sub(u" ",u"[^ ]* [^ ]*",eachword) |
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 |
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 |
gotinfix2 = True |
break |
if gotinfix2 == False: |
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""] |
print parsefix(u"oel") |
print parsefix(u"ngati") |
print parsefix(u"kameie") |
print parsefix(u"kìyevame") |
print parsefix(u"English") |
print parsefix(u"keykivame") |
print parsefix(u"tìsusiti") |
print parsefix(u"tayìng nari") |
print parsefix(u"tìtusìng") |
/webapp/static/favicon.ico |
---|
Cannot display: file marked as a binary type. |
svn:mime-type = application/octet-stream |
/webapp/static/favicon.ico |
---|
Property changes: |
Deleted: svn:mime-type |
## -1 +0,0 ## |
-application/octet-stream |
\ No newline at end of property |
Index: webapp/main.py |
=================================================================== |
--- webapp/main.py (revision 186) |
+++ webapp/main.py (revision 48) |
@@ -1,26 +1,6 @@ |
#!/usr/bin/python |
# -*- coding: utf-8 -*- |
-# This file is part of Tsim Apiak. |
-# |
-# Tsim Apiak is free software: you can redistribute it and/or modify |
-# it under the terms of the GNU General Public Licence as published by |
-# the Free Software Foundation, either version 3 of the Licence, or |
-# (at your option) any later version. |
-# |
-# In addition to this, you must also comply with clause 4 of the |
-# Apache Licence, version 2.0, concerning attribution. Where there |
-# is a contradiction between the two licences, the GPL |
-# takes preference. |
-# |
-# Tsim Apiak is distributed in the hope that it will be useful, |
-# but WITHOUT ANY WARRANTY; without even the implied warranty of |
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
-# GNU General Public License for more details. |
-# |
-# You should have received a copy of the GNU General Public License |
-# along with Tsim Apiak. If not, see |
- |
import tornado.httpserver |
import tornado.ioloop |
import tornado.web |
@@ -29,14 +9,12 @@ |
import os |
import re |
-from tsimapiak import parsenum |
-from tsimapiak import dbconnector |
-from tsimapiak import parse |
-from tsimapiak import translate |
+from tsimapiak.parsenum import parse |
+from tsimapiak.dbconnector import getnavilist |
class Index(tornado.web.RequestHandler): |
def get(self): |
- self.render("templates/index.html") |
+ self.redirect("/number") |
class Number(tornado.web.RequestHandler): |
def get(self): |
@@ -47,12 +25,10 @@ |
num = self.get_argument("num").strip() |
except: |
self.redirect("/number") |
- numout = parsenum.parse(num.replace(" ","")) |
+ numout = parse(num.replace(" ","")) |
if numout == None: |
- numoutt = -1 |
- else: |
- numoutt = (numout["dec"], numout["oct"]) |
- self.render("templates/number.html", last=num, numout=numoutt) |
+ numout = -1 |
+ self.render("templates/number.html", last=num, numout=numout) |
class Restart(tornado.web.RequestHandler): |
def get(self): |
@@ -61,51 +37,20 @@ |
class TestDB(tornado.web.RequestHandler): |
def get(self): |
- lis = dbconnector.getnavilist() |
+ lis = getnavilist() |
text = u"id | navi | infix | partofspeech " |
text += u" ".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") |
- except: |
- self.redirect("/parse") |
- 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") |
-} |
- |
application = tornado.web.Application([ |
("/", Index), |
("/number", Number), |
("/restart", Restart), |
- ("/testdb", TestDB), |
- ("/parse", Parse), |
- ("/translate", Translate) |
-], **settings) |
+ ("/testdb", TestDB) |
+]) |
if __name__ == "__main__": |
http_server = tornado.httpserver.HTTPServer(application) |
http_server.listen(1337) |
- #tornado.autoreload.start() |
+ tornado.autoreload.start() |
tornado.ioloop.IOLoop.instance().start() |
/webapp/templates/translate.html |
---|
File deleted |
/webapp/templates/index.html |
---|
File deleted |
/webapp/templates/parse.html |
---|
File deleted |
/webapp/templates/base.html |
---|
1,28 → 1,6 |
<html> |
<!-- |
# This file is part of Tsim Apiak. |
# |
# Tsim Apiak is free software: you can redistribute it and/or modify |
# it under the terms of the GNU General Public Licence as published by |
# the Free Software Foundation, either version 3 of the Licence, or |
# (at your option) any later version. |
# |
# In addition to this, you must also comply with clause 4 of the |
# Apache Licence, version 2.0, concerning attribution. Where there |
# is a contradiction between the two licences, the GPL |
# takes preference. |
# |
# Tsim Apiak is distributed in the hope that it will be useful, |
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
# GNU General Public License for more details. |
# |
# You should have received a copy of the GNU General Public License |
# along with Tsim Apiak. If not, see <http://www.gnu.org/licenses/>. |
--> |
<head> |
<title>Tsim Apiak - {% block title %}Title{% end %}</title> |
<link rel="shortcut icon" type="image/x-icon" href="static/favicon.ico" /> |
<style type="text/css"> |
body { |
background: #145179; |
52,7 → 30,6 |
<body> |
<div id="center"> |
<h1>Tsim Apiak</h1> |
<h2>By Sh4rK and Muzer</h2> |
<h2>{% block title %}Title{% end %}</h2> |
{% block body %}Body{% end %} |
</div> |
/webapp/templates/number.html |
---|
3,28 → 3,6 |
{% block title %}Number translator{% end %} |
{% block body %} |
<!-- |
# This file is part of Tsim Apiak. |
# |
# Tsim Apiak is free software: you can redistribute it and/or modify |
# it under the terms of the GNU General Public Licence as published by |
# the Free Software Foundation, either version 3 of the Licence, or |
# (at your option) any later version. |
# |
# In addition to this, you must also comply with clause 4 of the |
# Apache Licence, version 2.0, concerning attribution. Where there |
# is a contradiction between the two licences, the GPL |
# takes preference. |
# |
# Tsim Apiak is distributed in the hope that it will be useful, |
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
# GNU General Public License for more details. |
# |
# You should have received a copy of the GNU General Public License |
# along with Tsim Apiak. If not, see <http://www.gnu.org/licenses/>. |
--> |
<b>Na'vi number:</b><br /> |
<form action="/number" method="post"> |
<input id="num" name="num" type="text" value="{{last}}" style="width: 100%;" /> |
/tsimapiak/parse.py |
---|
File deleted |
/tsimapiak/translate.py |
---|
File deleted |
/tsimapiak/dbconnector.py |
---|
1,26 → 1,6 |
#!/usr/bin/python |
# -*- coding: utf-8 -*- |
# This file is part of Tsim Apiak. |
# |
# Tsim Apiak is free software: you can redistribute it and/or modify |
# it under the terms of the GNU General Public Licence as published by |
# the Free Software Foundation, either version 3 of the Licence, or |
# (at your option) any later version. |
# |
# In addition to this, you must also comply with clause 4 of the |
# Apache Licence, version 2.0, concerning attribution. Where there |
# is a contradiction between the two licences, the GPL |
# takes preference. |
# |
# Tsim Apiak is distributed in the hope that it will be useful, |
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
# GNU General Public License for more details. |
# |
# You should have received a copy of the GNU General Public License |
# along with Tsim Apiak. If not, see <http://www.gnu.org/licenses/>. |
import tornado.database |
import re |
29,24 → 9,44 |
current = u"" |
db = tornado.database.Connection("127.0.0.1", "navi", user="navi", password="navi") |
for row in db.query(""" |
SELECT * |
SELECT *, CHAR_LENGTH(navi) AS NL |
FROM `metaWords` |
WHERE partOfSpeech <> 'num.' AND partOfSpeech <> "prefix" |
ORDER BY CHAR_LENGTH(navi) DESC"""): |
if row["infixes"]: |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["infixes"].lower(), "type": row["partOfSpeech"]}) |
ORDER BY NL DESC"""): |
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: |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["navi"].lower(), "type": row["partOfSpeech"]}) |
current = unicode(row["navi"]) |
ret.append([row["id"], row["navi"], current, row["partOfSpeech"]]) |
db.close() |
return ret |
def translate(wid,language): |
def getnavi(word): |
ret = [] |
db = tornado.database.Connection("127.0.0.1", "navi", user="navi", password="navi") |
for row in db.query(""" |
SELECT * |
FROM `localizedWords` |
WHERE id = %s AND languageCode = %s""",wid,language): |
ret = row["localized"] |
break |
FROM `metaWords` |
WHERE navi = ?""",word): |
ret.append([row["id"],row["navi"], row["infix"], row["partOfSpeech"]]) |
db.close() |
return ret |
/tsimapiak/parsenum.py |
---|
1,148 → 1,81 |
#!/usr/bin/python |
# -*- coding: utf-8 -*- |
# This file is part of Tsim Apiak. |
# |
# Tsim Apiak is free software: you can redistribute it and/or modify |
# it under the terms of the GNU General Public Licence as published by |
# the Free Software Foundation, either version 3 of the Licence, or |
# (at your option) any later version. |
# |
# In addition to this, you must also comply with clause 4 of the |
# Apache Licence, version 2.0, concerning attribution. Where there |
# is a contradiction between the two licences, the GPL |
# takes preference. |
# |
# Tsim Apiak is distributed in the hope that it will be useful, |
# but WITHOUT ANY WARRANTY; without even the implied warranty of |
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
# GNU General Public License for more details. |
# |
# You should have received a copy of the GNU General Public License |
# along with Tsim Apiak. If not, see <http://www.gnu.org/licenses/>. |
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") |
#!/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"^(?:(" + "|".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"))?$" |
numre = re.compile(numre) |
def parse(numin): |
if type(numin) != unicode: |
return None |
if numin == u"": |
return None |
numin = numin.replace(u"í",u"ì").replace(u"á",u"ä") |
try: |
mat = numre.match(numin).groups() |
except: |
return None |
numout = 0 |
numoct = 0 |
try: |
numout += rem.index(mat[4]) + 1 |
numoct += rem.index(mat[4]) + 1 |
except: |
try: |
numout += num.index(mat[4]) |
numoct += num.index(mat[4]) |
except: pass |
try: |
numout += (base.index(mat[3]) + 1) * 8 |
numoct += (base.index(mat[3]) + 1) * 10 |
except: pass |
try: |
numout += (base.index(mat[2]) + 1) * 8**2 |
numoct += (base.index(mat[2]) + 1) * 10**2 |
except: pass |
try: |
numout += (base.index(mat[1]) + 1) * 8**3 |
numoct += (base.index(mat[1]) + 1) * 10**3 |
except: pass |
try: |
numout += (base.index(mat[0]) + 1) * 8**4 |
numoct += (base.index(mat[0]) + 1) * 10**4 |
except: pass |
return numout, numoct |
if __name__ == "__main__": |
print parse(u"mrrvolaw") |