| /ircbot/bot.py |
|---|
| 66,7 → 66,7 |
| if (cmd.split(" ")[0] == "tr") or (cmd.split(" ")[0] == "translate"): |
| lang = "en" |
| if len(cmd.split(" ")) > 1 and cmd.split(" ")[1].startswith("-"): |
| if cmd.split(" ")[1][1:] in ("hu", "de", "ptbr", "est", "sv", "nl"): |
| if cmd.split(" ")[1][1:] in ("hu", "de", "pt", "et", "sv", "nl", "es", "fr", "pl", "ru", "tr", "uk"): |
| lang = cmd.split(" ")[1][1:] |
| sent = " ".join(cmd.split(" ")[2:]) |
| else: |
| /webapp/templates/translate.html |
|---|
| 36,6 → 36,12 |
| <option value="pt">Brazilian Portuguese - Português do Brasil</option> |
| <option value="sv">Swedish - Svenska</option> |
| <option value="nl">Dutch - Nederlands</option> |
| <option value="es">Spanish - Español</option> |
| <option value="fr">French - Français</option> |
| <option value="pl">Polish - Polski</option> |
| <option value="ru">Russian - Русский</option> |
| <option value="tr">Turkish - Türkçe</option> |
| <option value="uk">Ukrainian - Türkçe</option> |
| </select> |
| <input name="btn" type="submit" value="Translate!" /> |
| </form> |
| 81,10 → 87,10 |
| if("{{ lang }}" == "de"){ |
| document.getElementById("lang").selectedIndex = 2 |
| } |
| if("{{ lang }}" == "est"){ |
| if("{{ lang }}" == "et"){ |
| document.getElementById("lang").selectedIndex = 3 |
| } |
| if("{{ lang }}" == "ptbr"){ |
| if("{{ lang }}" == "pt"){ |
| document.getElementById("lang").selectedIndex = 4 |
| } |
| if("{{ lang }}" == "sv"){ |
| 93,6 → 99,21 |
| if("{{ lang }}" == "nl"){ |
| document.getElementById("lang").selectedIndex = 6 |
| } |
| if("{{ lang }}" == "fr"){ |
| document.getElementById("lang").selectedIndex = 7 |
| } |
| if("{{ lang }}" == "pl"){ |
| document.getElementById("lang").selectedIndex = 8 |
| } |
| if("{{ lang }}" == "ru"){ |
| document.getElementById("lang").selectedIndex = 9 |
| } |
| if("{{ lang }}" == "tr"){ |
| document.getElementById("lang").selectedIndex = 10 |
| } |
| if("{{ lang }}" == "uk"){ |
| document.getElementById("lang").selectedIndex = 11 |
| } |
| </script> |
| {% end %} |
| {% end %} |
| /tsimapiak/dbconnector.py |
|---|
| 36,7 → 36,7 |
| if row["infixes"] and row["infixes"] != "NULL": # yeah seriously |
| ret.append({"id": row["id"], "navi": row["navi"].replace("+", "").replace("-", ""), "infix": row["infixes"].lower(), "type": row["partOfSpeech"]}) |
| else: |
| ret.append({"id": row["id"], "navi": row["navi"].replace("+", "").replace("-", ""), "infix": row["navi"].lower(), "type": row["partOfSpeech"]}) |
| ret.append({"id": row["id"], "navi": row["navi"].replace("+", "").replace("-", ""), "infix": row["navi"].replace("+", "").replace("-", "").lower(), "type": row["partOfSpeech"]}) |
| cur.close() |
| db.close() |
| return ret |
| 50,17 → 50,24 |
| FROM `metaInfixes` |
| ORDER BY CHAR_LENGTH(navi) DESC""") |
| for row in cur: |
| endfix = False |
| if row["navi"] and row["navi"][0] == "-": |
| ret[2].append({"id": row["id"], "navi": row["navi"].replace("-", ""), "gloss": row["shorthand"].upper()}) |
| elif row["navi"] and row["navi"][-1] in ("-", "+"): |
| ret[0].append({"id": row["id"], "navi": row["navi"].replace("-", ""), "gloss": row["shorthand"].upper()}) |
| else: |
| endfix = True |
| if row["navi"] and row["navi"][-1] in ("-", "+"): |
| ret[0].append({"id": row["id"], "navi": row["navi"].replace("-", "").replace("+", ""), "gloss": row["shorthand"].upper()}) |
| endfix = True |
| if not endfix: |
| if not row["position"] or row["position"] == "NULL": |
| # not actually an affix |
| continue |
| ret[1].append({"id": row["id"], "navi": row["navi"].replace("-", ""), "gloss": row["shorthand"].upper(), "position": int(row["position"])}) |
| ret[1].append({"id": row["id"], "navi": row["navi"], "gloss": row["shorthand"].upper(), "position": int(row["position"])}) |
| cur.close() |
| db.close() |
| for subret in ret: |
| subret.sort(key=lambda x: len(x["navi"]), reverse=True) |
| return ret |
| def translate(wid, language): |
| /tsimapiak/parse.py |
|---|
| 39,9 → 39,9 |
| (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), # TODO remember why on earth this is needed; how is awng interpreted as awnga? |
| (u"kawnga", u"kawng", u"", u"", u"", (()), [[(u"a", None)]], False), |
| (u"kawng", u"kawng", u"", u"", u"", (()), (()), False), |
| #(u"akawng", u"kawng", u"", u"", u"", [[u"a"]], (()), False), |
| #(u"kawnga", u"kawng", u"", u"", u"", (()), [[(u"a", None)]], False), |
| #(u"kawng", u"kawng", u"", u"", u"", (()), (()), False), |
| (u"ka", u"ka", u"", u"", u"", (()), (()), False), |
| (u"uo", u"uo", u"", u"", u"", (()), (()), False), |
| (u"sìk", u"sìk", u"", u"", u"", (()), (()), False), |
| 57,10 → 57,33 |
| #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 )?)" |
| EXTRAINFIXES = [ |
| {"id": "-1", "navi": "eiy", "gloss": "LAUD.", "position": 2}, |
| {"id": "-2", "navi": "eng", "gloss": "PEJ.", "position": 2}, |
| ] |
| EXTRAPOSTFIXES = [ |
| {"id": "-3", "navi": "eyä", "gloss": "GEN."}, |
| ] |
| EXTRAADP = (("to", [x["id"] for x in wordlist if x["navi"] == "to"][0]), ("sì", [x["id"] for x in wordlist if x["navi"] == "sì"][0])) # words that act like adpositions but technically aren't |
| LENIT = ((u"px", u"p"), (u"tx", u"t"), (u"kx", u"k"), (u"ts", u"s"), (u"t", u"s"), (u"p", u"f"), (u"k", u"h"), (u"'", u"")) |
| # Let's lenit the prefixes |
| extraprefixes = [] |
| for prefix in prefixes: |
| for letter, replacement in LENIT: |
| if prefix["navi"].startswith(letter): |
| new_prefix = prefix["navi"].replace(letter, replacement, 1) |
| if not [x for x in prefixes if x["navi"] == new_prefix]: # always assume a dictionary word over a lenited prefix |
| extraprefixes.append({"id": prefix["id"], "navi": new_prefix, "gloss": prefix["gloss"] + ".LENTD"}) |
| break |
| prefixes = sorted(prefixes + extraprefixes, key=lambda x: len(x["navi"]), reverse=True) |
| infixes = sorted(infixes + EXTRAINFIXES, key=lambda x: len(x["navi"]), reverse=True) |
| postfixes = sorted(postfixes + EXTRAPOSTFIXES, key=lambda x: len(x["navi"]), reverse=True) |
| def parseword(wordin): |
| tempid = 0 |
| temptype = u"" |
| 126,21 → 149,45 |
| center = temp |
| if center == u"": |
| if splitword[wor].endswith(u"nga"): |
| temp = splitword[wor][:-3] + u"ng" |
| temp = splitword[wor][:-3] + u"nge" |
| if temp in wordin[wor]: |
| center = temp |
| if splitword[wor].endswith(u"fo"): |
| temp = splitword[wor][:-2] + u"f" |
| temp = splitword[wor][:-2] + u"fe" |
| if temp in wordin[wor]: |
| center = temp |
| if splitword[wor].endswith(u"po"): |
| temp = splitword[wor][:-2] + u"p" |
| temp = splitword[wor][:-2] + u"pe" |
| if temp in wordin[wor]: |
| center = temp |
| if splitword[wor].endswith(u"tsa"): |
| temp = splitword[wor][:-3] + u"ts" |
| temp = splitword[wor][:-3] + u"tse" |
| if temp in wordin[wor]: |
| center = temp |
| if splitword[wor].endswith(u"fko"): |
| temp = splitword[wor][:-3] + u"fke" |
| if temp in wordin[wor]: |
| center = temp |
| if splitword[wor].endswith(u"tsa'u"): |
| temp = splitword[wor][:-5] + u"tse" |
| if temp in wordin[wor]: |
| center = temp |
| if splitword[wor].endswith(u"sa'u"): |
| temp = splitword[wor][:-4] + u"se" |
| if temp in wordin[wor]: |
| center = temp |
| if splitword[wor].endswith(u"sa"): |
| temp = splitword[wor][:-2] + u"se" |
| if temp in wordin[wor]: |
| center = temp |
| if splitword[wor].endswith(u"sno"): |
| temp = splitword[wor][:-3] + u"sne" |
| if temp in wordin[wor]: |
| center = temp |
| if splitword[wor].endswith(u"ayla"): |
| temp = splitword[wor][:-3] + u"ayle" |
| if temp in wordin[wor]: |
| center = temp |
| if center == u"": |
| foundit = False |
| break |
| 167,7 → 214,7 |
| last = u"" |
| while last != posf: |
| last = posf |
| for pos, posid in [(x["navi"], None) for x in postfixes] + [(x["navi"], x["id"]) for x in wordlist if x["type"] == "adp."] + list(EXTRAADP): |
| for pos, posid in sorted([(x["navi"], None) for x in postfixes] + [(x["navi"], x["id"]) for x in wordlist if x["type"] == "adp."] + list(EXTRAADP), key=lambda x: len(x[0]), reverse=True): |
| if posf != u"": |
| if posf.startswith(pos): |
| if (pos, posid) in foundposts[wor]: |
| /tsimapiak/translate.py |
|---|
| 31,8 → 31,6 |
| #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"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.")) |
| prefixes, infixes, postfixes = dbconnector.getaffixlists() |
| def translatesent(sent, lang): |
| sent = parse.parsesent(sent) |
| for word in sent: |
| 46,25 → 44,25 |
| if word["translated"] == u"": |
| word["translated"] = word["word"]["navi"] |
| if word["inf"][0] != u"": |
| for fix in [(x["navi"], x["gloss"]) for x in infixes if x["position"] == 0]: |
| for fix in [(x["navi"], x["gloss"]) for x in parse.infixes if x["position"] == 0]: |
| if fix[0] == word["inf"][0]: |
| word["translated"] += '-' + fix[1] |
| if word["inf"][1] != u"": |
| for fix in [(x["navi"], x["gloss"]) for x in infixes if x["position"] == 1]: |
| for fix in [(x["navi"], x["gloss"]) for x in parse.infixes if x["position"] == 1]: |
| if fix[0] == word["inf"][1]: |
| word["translated"] += '-' + fix[1] |
| if word["inf"][2] != u"": |
| for fix in [(x["navi"], x["gloss"]) for x in infixes if x["position"] == 2]: |
| for fix in [(x["navi"], x["gloss"]) for x in parse.infixes if x["position"] == 2]: |
| if fix[0] == word["inf"][2]: |
| word["translated"] += '-' + fix[1] |
| for temp in word["pref"]: |
| for navf in temp: |
| for fix in [(x["navi"], x["gloss"]) for x in prefixes]: |
| for fix in [(x["navi"], x["gloss"]) for x in parse.prefixes]: |
| if fix[0] == navf: |
| word["translated"] += '-' + fix[1] |
| for temp in word["post"]: |
| for navf, navfid in temp: |
| for fix in [(x["navi"], x["gloss"]) for x in postfixes]: |
| for fix in [(x["navi"], x["gloss"]) for x in parse.postfixes]: |
| if fix[0] == navf: |
| word["translated"] += '-' + fix[1] |
| break |
| /discordbot/README.txt |
|---|
| 0,0 → 1,3 |
| This is a Discord bot for TsimApiak. |
| To use it you have to put the tsimapiak directory inside this dir, and run bot.py. |
| /discordbot/bot.py |
|---|
| 0,0 → 1,60 |
| #! /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/>.# |
| import os |
| import discord |
| import dotenv |
| from typing import Optional |
| from tsimapiak import translate |
| dotenv.load_dotenv(dotenv.find_dotenv()) |
| intents = discord.Intents.default() |
| client = discord.Client(intents=intents) |
| tree = discord.app_commands.CommandTree(client) |
| @client.event |
| async def on_ready(): |
| print(f"{client.user} Connected to discord") |
| await tree.sync() |
| @tree.command( |
| name="translate", |
| description="Translate (gloss) Na'vi to English" |
| ) |
| async def on_translate(interaction: discord.Interaction, argument: str, language: Optional[str]): |
| if not language: |
| language = "en" |
| translated = [] |
| for word in translate.translatesent(argument, language): |
| translated.append(word["translated"]) |
| await interaction.response.send_message(argument + "\n" + " | ".join(translated)) |
| def main(): |
| TOKEN = os.getenv('DISCORD_TOKEN') |
| client.run(TOKEN) |
| if __name__ == "__main__": |
| main() |
| Property changes: |
| Added: svn:executable |
| ## -0,0 +1 ## |
| +* |
| \ No newline at end of property |