def test_parse_file(self):
with tempfile.TemporaryFile(mode='w+') as fp:
fp.write(self.s3)
fp.seek(0)
lexical_units = list(parse_file(fp))
self.assertEqual(len(lexical_units), 1)
self.assertEqual(lexical_units[0].wordform, 'vino')
def test_parse_file(self):
with tempfile.TemporaryFile(mode='w+') as fp:
fp.write(self.s3)
fp.seek(0)
lexical_units = list(parse_file(fp))
self.assertEqual(len(lexical_units), 1)
self.assertEqual(lexical_units[0].wordform, 'vino')
#!/usr/bin/env python3
from streamparser import parse_file, readingToString, known
import sys
def stash(wf, r):
return "[<apertium-notrans>{}\/{}<\/apertium-notrans>]".format(
lu.wordform, readingToString(r))
for blank, lu in parse_file(sys.stdin, withText=True):
if lu.knownness == known and len(lu.readings) > 1:
print(
" ".join("{}^{}/{}$ ^./.<sent><clb>$".format(
stash(lu.wordform, r), lu.wordform, readingToString(r))
for r in lu.readings
# Skip compounds:
if len(r) == 1),
end="\n")
## A script for converting kaz-tagger mode's output into a tab-separated,
## easy-to-annotate format.
##
## INPUT: apertium-kaz$ echo "бақшада ма, қайда?" | apertium -d . kaz-tagger
## ^бақшада ма/бақша<n><loc>+ма<qst>$^,/,<cm>$ ^қайда/қайда<adv><itg>+е<cop><aor><p3><sg>$^?/?<sent>$^./.<sent>$
##
## OUTPUT: apertium-kaz$ echo "бақшада ма, қайда?" | apertium -d . kaz-tagger | python3 corpus/format.py
## бақшада ма бақша n loc +ма qst
## , , cm
## қайда қайда adv itg +е cop aor p3 sg
## ? ? sent
##. . sent
import sys, streamparser
for lu in streamparser.parse_file(sys.stdin):
print(lu.wordform, end="\t")
for r in lu.readings:
print(r[0].baseform, end="\t")
print(" ".join(r[0].tags), end="")
if len(r) > 1:
for s in r[1:]:
print(" +" + s.baseform, " ".join(s.tags), end="")
print("\t\t\t")
post = "\033[0m"
elif arg == "--context":
context = True
def fst(x):
(a, _) = x
return a
def snd(x):
(_, b) = x
return b
for blank, lu in streamparser.parse_file(sys.stdin, withText=True):
if context:
print(blank, end="")
m = set((t, s.baseform) for r in lu.readings for s in r for t in s.tags
if t.startswith("@"))
if m:
tag = pre + "".join(map(fst, m)) + post
if context:
print(lu.wordform + tag, end="")
else:
lemma = "/".join(map(snd, m))
print(lemma + tag, end="")
print("")
elif context:
print(lu.wordform, end="")
def prepros(filename):
cohorts = parse_file(open(filename))
return (cohorts)