/tsimapiak/parse.py |
---|
24,10 → 24,11 |
import dbconnector |
import parsenum |
wordlist = [{"id": 0, "navi": u"tawtute", "infix": u"tawtute", "type": u"n."}] + dbconnector.getnavilist() + [{"id": 0, "navi": u"na'vi", "infix": u"na'vi", "type": u"n."}] # XXX HACK - extra proper nouns |
#wordlist = [{"id": 0, "navi": u"tawtute", "infix": u"tawtute", "type": u"n."}] + dbconnector.getnavilist() + [{"id": 0, "navi": u"na'vi", "infix": u"na'vi", "type": u"n."}] # XXX HACK - extra proper nouns |
wordlist = dbconnector.getnavilist() |
brokenwords = ((u"sami", u"si", u"", u"am", u"", (()), (()), False), (u"to", u"to", u"", u"", u"", (()), (()), False), (u"poltxe", u"plltxe", u"", u"ol", u"", (()), (()), False)) # XXX HACK - These are words that are either not in Eana Eltu, or that get interpreted wrongly for whatever reason. The latter should be removed from this list when the parser gets more sophisticated. The former should also have an entry in the equivalent array in the translator! If it can take infixes, consider adding it to the main wordlist above (see the examples). The order is - original, Na'vi root, 0-pos infix, 1-pos infix, 2-pos infix, prefixes, suffixes. Things that can take affixes should go in the above list instead. |
brokenwords = ((u"sami", u"si", u"", u"am", u"", (()), (()), False), (u"to", u"to", u"", u"", u"", (()), (()), False), (u"frato", u"to", u"", u"", u"", [[u"fra"]], (()), False)) # XXX HACK - These are words that are either not in Eana Eltu, or that get interpreted wrongly for whatever reason. The latter should be removed from this list when the parser gets more sophisticated. The former should also have an entry in the equivalent array in the translator! If it can take infixes, consider adding it to the main wordlist above (see the examples). The order is - original, Na'vi root, 0-pos infix, 1-pos infix, 2-pos infix, prefixes, suffixes. Things that can take affixes should go in the above list instead. |
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"") |
51,6 → 52,7 |
return {"word": {"id": tempid, "navi": brokenword[1], "infix": u"", "type": temptype}, "pref": brokenword[5], "post": brokenword[6], "len": brokenword[7], "inf": (brokenword[2], brokenword[3], brokenword[4]) } |
ret = {"word": {"id": 0, "navi": u"[" + wordin[0] + u"]", "infix": u"", "type": u""}} |
for word in wordlist: |
word["navi"] = word["navi"].lower() |
foundit = True |
foundprefs = [] |
foundposts = [] |
84,8 → 86,8 |
for in1 in tempin1: |
for in2 in tempin2: |
for in3 in tempin3: |
if splitword[wor].replace(u"<1><2>",in1+in2).replace(u"<3>",in3) in wordin[wor]: |
center = splitword[wor].replace(u"<1><2>",in1+in2).replace(u"<3>",in3) |
if splitword[wor].replace(u"<1><2>",in1+in2).replace(u"<3>",in3).replace(u"lll",u"l").replace(u"rrr",u"r") in wordin[wor]: |
center = splitword[wor].replace(u"<1><2>",in1+in2).replace(u"<3>",in3).replace(u"lll",u"l").replace(u"rrr",u"r") |
foundins = [in1, in2, in3] |
break |
if center != u"": break |
131,6 → 133,7 |
break |
if pref != u"": |
foundit = False |
foundprefs = [] |
break |
last = u"" |
while last != posf: |
148,6 → 151,7 |
break |
if posf != u"": |
foundit = False |
foundposts = [] |
break |
if foundit == True: |
foundword = word |
/tsimapiak/translate.py |
---|
23,7 → 23,7 |
import parse |
import dbconnector |
brokenwords = ((u"to", u"than"), (u"tawtute", u"skyperson"), (u"na'vi", u"The People")) # XXX HACK - words not in EE |
brokenwords = [[u"", u"", u"", u"", u"", u"", u""]] #, (u"tawtute", u"skyperson"), (u"na'vi", u"The People")) # XXX HACK - words not in EE |
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.")) |
/tsimapiak/dbconnector.py |
---|
41,6 → 41,7 |
return ret |
def translate(wid,language): |
ret = None |
db = tornado.database.Connection("127.0.0.1", "navi", user="navi", password="navi") |
for row in db.query(""" |
SELECT * |
48,5 → 49,7 |
WHERE id = %s AND languageCode = %s""",wid,language): |
ret = row["localized"] |
break |
if ret == None: |
return u"ERROR: WORD NOT LOCALISED" |
db.close() |
return ret |
/tsimapiak/parsenum.py |
---|
124,8 → 124,7 |
if numin.startswith(base[n] + u"zam"): |
outoct += (n+1) * (10**2) |
outdec += (n+1) * (8**2) |
if numin[len(base[n]) + 4:].startswith(u"mrr") or numin[len(base[n]) + 4:].startswith(u"me"): |
print numin |
if numin[len(base[n]) + 2:].startswith(u"mrr") or numin[len(base[n]) + 2:].startswith(u"me"): |
numin = numin[len(base[n]) + 2:] |
else: |
numin = numin[len(base[n]) + 3:] |
/webapp/main.py |
---|
82,6 → 82,20 |
self.redirect("/translate") |
out = translate.translatesent(word, lang) |
self.render("templates/translate.html", last=word, out=out, lang=lang) |
class Errors(tornado.web.RequestHandler): |
def get_error_html(self, status_code, **kwargs): |
if status_code == 500: |
return "<html><title>%(code)d: %(message)s</title>" \ |
"<body>%(code)d: %(message)s<br /><br />Either we are currently working on the server, or you uncovered a bug. Please check back later on. If you still get this error, please report this bug to us in the forum thread or on IRC.</body></html>" % { |
"code": status_code, |
"message": httplib.responses[status_code], |
} |
else: |
return "<html><title>%(code)d: %(message)s</title>" \ |
"<body>%(code)d: %(message)s</body></html>" % { |
"code": status_code, |
"message": httplib.responses[status_code], |
} |
settings = { |
"static_path": os.path.join(os.path.dirname(__file__), "static") |
/webapp/templates/translate.html |
---|
34,6 → 34,7 |
<option value="de">German - Deutsch</option> |
<option value="est">Estonian - Eesti</option> |
<option value="ptbr">Brazilian Portuguese - Português do Brasil</option> |
<option value="sv">Swedish - Svenska</option> |
</select> |
<input name="btn" type="submit" value="Translate!" /> |
</form> |
85,6 → 86,9 |
if("{{ lang }}" == "ptbr"){ |
document.getElementById("lang").selectedIndex = 4 |
} |
if("{{ lang }}" == "sv"){ |
document.getElementById("lang").selectedIndex = 5 |
} |
</script> |
{% end %} |
{% end %} |
/ircbot/bot.py |
---|
49,8 → 49,8 |
if (cmd.split(" ")[0] == "tr") or (cmd.split(" ")[0] == "translate"): |
lang = "eng" |
if cmd.split(" ")[1].startswith("-"): |
if cmd.split(" ")[1][1:] in ("hu", "de", "ptbr", "est"): |
if len(cmd.split(" ")) > 1 and cmd.split(" ")[1].startswith("-"): |
if cmd.split(" ")[1][1:] in ("hu", "de", "ptbr", "est", "sv"): |
lang = cmd.split(" ")[1][1:] |
sent = " ".join(cmd.split(" ")[2:]) |
else: |