def usage():
from pkg_resources import get_distribution
print("Unidic2UD Version " + get_distribution("unidic2ud").version,
file=sys.stderr)
print("Usage: unidic2ud -U Dict [-u|-t|-t2] file", file=sys.stderr)
print(" unidic2ud --download=Dict", file=sys.stderr)
s = " Dict:\n" + unidic2ud.dictlist().replace(".udpipe", "(udpipe)")
print(s.replace("\n", " ").rstrip(), file=sys.stderr)
sys.exit()
def main():
argc = len(sys.argv)
d = "japanese-modern"
optu = optt = False
i = w = 1
while i < argc:
o = sys.argv[i]
if o == "-h" or o == "--help" or o == "-v" or o == "--version":
usage()
elif o.startswith("-U"):
if o == "-U":
i += 1
d = sys.argv[i]
else:
d = sys.argv[i][2:]
elif o == "-u":
optu = True
elif o == "-t" or o == "-t1":
optt = True
w = 1
elif o == "-t2":
optt = True
w = 2
elif o.startswith("--download="):
d = sys.argv[i][11:]
if d > "":
s = unidic2ud.dictlist().replace(".udpipe", "").split()
if d in s:
print("unidic2ud: " + d + " was already downloaded",
file=sys.stderr)
else:
unidic2ud.download(d)
usage()
else:
break
i += 1
else:
if d.find("-") > 0:
nlp = unidic2ud.load(None, d)
else:
nlp = unidic2ud.load(d)
while True:
try:
s = input()
except:
return
print(output(nlp, optu, optt, w, s), end="")
if d.find("-") > 0:
nlp = unidic2ud.load(None, d)
else:
nlp = unidic2ud.load(d)
while i < argc:
f = open(sys.argv[i], "r", encoding="utf-8")
s = f.read()
f.close()
print(output(nlp, optu, optt, w, s), end="")
i += 1
def usage():
from pkg_resources import get_distribution
from unidic2ud import dictlist
print("UniDic2UD Version " + get_distribution("unidic2ud").version,
file=sys.stderr)
print("Usage: udcabocha -U Dict [-f 0-8] file", file=sys.stderr)
print(" udcabocha --download=Dict", file=sys.stderr)
s = " Dict:\n" + dictlist().replace(".udpipe", "(udpipe)")
print(s.replace("\n", " ").rstrip(), file=sys.stderr)
sys.exit()
def main():
argc = len(sys.argv)
i = 1
f = 0
u = None
while i < argc:
o = sys.argv[i]
if o.startswith("-f"):
if o == "-f":
i += 1
f = int(sys.argv[i])
else:
f = int(sys.argv[i][2:])
if f < 0 or f > 8:
usage()
elif o.startswith("-U"):
if o == "-U":
i += 1
u = sys.argv[i]
else:
u = sys.argv[i][2:]
elif o.startswith("--download="):
d = sys.argv[i][11:]
if d > "":
from unidic2ud import download, dictlist
s = dictlist().replace(".udpipe", "").split()
if d in s:
print("udcabocha: " + d + " was already downloaded",
file=sys.stderr)
else:
download(d)
usage()
elif o == "-h" or o == "--help" or o == "-v" or o == "--version":
usage()
else:
break
i += 1
else:
ja = parser(u, f)
while True:
try:
s = input()
except:
return
print(ja(s), end="")
ja = parser(u, f)
while i < argc:
p = open(sys.argv[i], "r", encoding="utf-8")
s = p.read()
p.close()
print(ja(s), end="")
i += 1
def run(self):
try:
import unidic2ud
if unidic2ud.dictlist().find("qkana\n") < 0:
import subprocess
subprocess.check_call(["unidic2ud", "--download=qkana"])
except:
import os, ssl, urllib.request, zipfile, glob
ssl._create_default_https_context = ssl._create_unverified_context
f, h = urllib.request.urlretrieve(QKANA_URL)
with zipfile.ZipFile(f) as z:
z.extractall("build")
os.renames(
glob.glob("build/UniDic-qkana*")[0],
"build/lib/udkundoku/qkana")
install.run(self)
#! /usr/bin/python -i
# coding=utf-8
import udkanbun
import unidic2ud
if unidic2ud.dictlist().find("qkana\n") < 0:
import os
p = os.path.join(os.path.abspath(os.path.dirname(__file__)), "qkana")
if os.path.isdir(p):
import shutil
shutil.move(p, unidic2ud.DOWNLOAD_DIR)
else:
unidic2ud.download("qkana", "unidic")
QKANA = unidic2ud.UniDic2UD("qkana", None)
from udkundoku.adp import ADP
from udkundoku.adv import ADV
from udkundoku.aux import AUX
from udkundoku.part import PART
from udkundoku.verb import VERB
class UDKundokuToken(object):
def __init__(self, id, form, lemma, upos, xpos, feats, deprel, deps, misc):
self.id = id
self.form = form
self.lemma = lemma
self.upos = upos
self.xpos = xpos
self.feats = feats
self.deprel = deprel