/tsimapiak/dbconnector.py |
---|
29,7 → 29,7 |
for row in db.query(""" |
SELECT * |
FROM `metaWords` |
WHERE partOfSpeech <> 'num.' AND partOfSpeech <> "prefix" |
WHERE partOfSpeech <> 'num.' AND partOfSpeech <> 'prefix' AND partOfSpeech <> 'affix' |
ORDER BY CHAR_LENGTH(navi) DESC"""): |
if row["infixes"]: |
ret.append({"id": row["id"], "navi": row["navi"], "infix": row["infixes"].lower(), "type": row["partOfSpeech"]}) |
/tsimapiak/parse.py |
---|
28,13 → 28,14 |
wordlist = dbconnector.getnavilist() |
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. |
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), (u"mengenga", u"ngenga", u"", u"", u"", [[u"me"]], (()), False), (u"pxengenga", u"ngenga", u"", u"", u"", [[u"pxe"]], (()), False), (u"kìmä", u"kä", u"", u"ìm", u"", (()), (()), False), (u"apxay", u"pxay", u"", u"", u"", [[u"a"]], (()), False), (u"akawng", u"kawng", u"", u"", u"", [[u"a"]], (()), False), (u"ka", u"ka", u"", u"", u"", (()), (()), False), (u"uo", u"uo", u"", u"", 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. |
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"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") |
PREFIXES = (u"tsay", u"fray", u"say", u"fay", u"fra", u"pxe", u"fne", u"tsa", u"kel", u"lek", 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"px", u"a", u"m", u"k") |
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") |
POSTFIXES = ADPOSITIONS + (u"tsyìp", u"eyä", u"ìri", u"aru", u"ati", u"ayä", u"ari", u"ay", 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"al", u"at", u"ar", u"ey", 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 )?)" |
108,10 → 109,18 |
temp = splitword[wor][:-3] + u"ng" |
if temp in wordin[wor]: |
center = temp |
if splitword[wor].endswith(u"fo"): |
temp = splitword[wor][:-2] + u"f" |
if temp in wordin[wor]: |
center = temp |
if splitword[wor].endswith(u"po"): |
temp = splitword[wor][:-2] + u"p" |
if temp in wordin[wor]: |
center = temp |
if splitword[wor].endswith(u"tsa"): |
temp = splitword[wor][:-3] + u"ts" |
if temp in wordin[wor]: |
center = temp |
if center == u"": |
foundit = False |
break |
/tsimapiak/translate.py |
---|
27,9 → 27,9 |
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")) |
PREFIXES = ((u"tsay", u"those"), (u"fray", u"every-PL."), (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"kel", u"ADJD.-not"), (u"lek", u"not-ADJD."), (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"px", u"TRI."), (u"a", u"ADJ.POST"), (u"m", u"DU."), (u"k", u"not")) |
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.")) |
POSTFIXES = ADPOSITIONS + ((u"tsyìp", u"DIM."), (u"eyä", u"GEN."), (u"ìri", u"TOP."), (u"ari", u"TOP."), (u"ayä", u"GEN."), (u"aru", u"DAT."), (u"ati", u"ACC."), (u"ay", u"GEN."), (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"al", u"ERG."), (u"at", u"ACC."), (u"ar", u"DAT."), (u"ey", u"GEN."), (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) |
/tsimapiak/parsenum.py |
---|
103,6 → 103,15 |
#other numbers |
notbase = False |
for n in range(len(BASE)): |
if numin.startswith(BASE[n] + u"vozazam"): |
outoct += (n + 1) * (10 ** 5) |
outdec += (n + 1) * (8 ** 5) |
if numin[len(BASE[n]) + 6:].startswith(u"mrr") or numin[len(BASE[n]) + 6:].startswith(u"me"): |
numin = numin[len(BASE[n]) + 6:] |
else: |
numin = numin[len(BASE[n]) + 7:] |
notbase = True |
for n in range(len(BASE)): |
if numin.startswith(BASE[n] + u"zazam"): |
outoct += (n + 1) * (10 ** 4) |
outdec += (n + 1) * (8 ** 4) |
/ircbot/bot.py |
---|
1,16 → 1,24 |
#! /usr/bin/env python |
# This file is part of Tsim Apiak. |
# |
# Example program using ircbot.py. |
# 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. |
# |
# Joel Rosdahl <joel@rosdahl.net> |
# 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/>.# |
"""A simple example bot. |
This is an example bot that uses the SingleServerIRCBot class from |
ircbot.py. The bot enters a channel and listens for commands in |
private messages and channel traffic. Commands in channel messages |
are given by prefixing the text by the bot name followed by a colon.""" |
from ircbot import SingleServerIRCBot |
from irclib import nm_to_n |
from tsimapiak import translate |
50,7 → 58,7 |
if (cmd.split(" ")[0] == "tr") or (cmd.split(" ")[0] == "translate"): |
lang = "eng" |
if len(cmd.split(" ")) > 1 and cmd.split(" ")[1].startswith("-"): |
if cmd.split(" ")[1][1:] in ("hu", "de", "ptbr", "est", "sv"): |
if cmd.split(" ")[1][1:] in ("hu", "de", "ptbr", "est", "sv", "nl"): |
lang = cmd.split(" ")[1][1:] |
sent = " ".join(cmd.split(" ")[2:]) |
else: |
/webapp/templates/translate.html |
---|
35,6 → 35,7 |
<option value="est">Estonian - Eesti</option> |
<option value="ptbr">Brazilian Portuguese - Português do Brasil</option> |
<option value="sv">Swedish - Svenska</option> |
<option value="nl">Dutch - Nederlands</option> |
</select> |
<input name="btn" type="submit" value="Translate!" /> |
</form> |
89,6 → 90,9 |
if("{{ lang }}" == "sv"){ |
document.getElementById("lang").selectedIndex = 5 |
} |
if("{{ lang }}" == "nl"){ |
document.getElementById("lang").selectedIndex = 6 |
} |
</script> |
{% end %} |
{% end %} |
/cliapp/README |
---|
0,0 → 1,0 |
This app is only for use on the server. |
/cliapp/tsimapiakcli.py |
---|
0,0 → 1,35 |
#!/usr/bin/env python |
# 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/>. |
from tsimapiak import translate |
import sys |
for line in sys.stdin: |
try: |
line = line.decode("utf-8") |
except: |
line = line.decode("iso-8859-1") |
translated = [] |
for word in translate.translatesent(line, "eng"): |
translated.append(word["translated"]) |
translated = " | ".join(translated) |
print translated |
Property changes: |
Added: svn:executable |
## -0,0 +1 ## |
+* |
\ No newline at end of property |