def test_report(self):
from pyclpa.cli import report
with self.assertRaises(ParserError):
report(Mock(args=[]))
with self.assertRaises(ParserError):
report(Mock(args=["format=csv"]))
args = [self.data_path("KSL.tsv").as_posix()]
with capture(report, Mock(args=args)) as out:
self.assertIn("Convertible sounds", out)
out = self.tmp_path("test.csv")
report(Mock(args=args + ["format=csv", "outfile=" + out.as_posix()]))
self.assertEqual(self._read_tsv(out), self._read_tsv(self.data_path("KSL_report.csv")))
with capture(report, Mock(args=args + ["format=csv"])) as out:
if hasattr(out, "decode"):
out = out.decode("utf8")
self.assertIn("existing", out)
with capture(report, Mock(args=args + ["format=cldf"])) as out:
if hasattr(out, "decode"):
out = out.decode("utf8")
self.assertIn("CLPA_TOKENS", out)
out = self.tmp_path("test.md")
report(Mock(args=args + ["outfile=" + out.as_posix()]))
self.assertTrue(out.exists())
def test_report(self):
from pyclpa.cli import report
with self.assertRaises(ParserError):
report(Mock(args=[]))
with self.assertRaises(ParserError):
report(Mock(args=['format=csv']))
args = [self.data_path('KSL.tsv').as_posix()]
with capture(report, Mock(args=args)) as out:
self.assertIn('Convertible sounds', out)
out = self.tmp_path('test.csv')
report(Mock(args=args + ['format=csv', 'outfile=' + out.as_posix()]))
self.assertEqual(self._read_tsv(out),
self._read_tsv(self.data_path('KSL_report.csv')))
with capture(report, Mock(args=args + ['format=csv'])) as out:
if hasattr(out, 'decode'):
out = out.decode('utf8')
self.assertIn('existing', out)
with capture(report, Mock(args=args + ['format=cldf'])) as out:
if hasattr(out, 'decode'):
out = out.decode('utf8')
self.assertIn('CLPA_TOKENS', out)
out = self.tmp_path('test.md')
report(Mock(args=args + ['outfile=' + out.as_posix()]))
self.assertTrue(out.exists())
def test_ArgumentParser(self):
from clldutils.clilib import ArgumentParser, ParserError
def cmd(args):
"""
docstring
"""
if len(args.args) < 1:
raise ParserError('not enough arguments')
print(args.args[0])
parser = ArgumentParser('pkg', cmd)
with capture(parser.main, args=['help', 'cmd']) as out:
self.assertIn('docstring', out)
with capture(parser.main, args=['cmd', 'arg']) as out:
self.assertIn('arg', out)
self.assertEqual(parser.main(args=['cmd', 'arg']), 0)
with capture(parser.main, args=['cmd']) as out:
self.assertIn('not enough arguments', out)
with capture_all(parser.main, args=['x']) as res:
self.assertNotEqual(res[0], 0)
self.assertTrue(res[1].startswith('invalid'))
def test_lookup(self):
from pyconcepticon.commands import lookup
with capture(
lookup, MagicMock(full_search=True, args=['sky'], language='en')) as out:
self.assertIn('1732', out)
with capture(lookup, MagicMock(args=['sky'], language='en')) as out:
self.assertIn('1732', out)
def test_bibfiles(self):
c = self.api.bibfiles
with capture(c.roundtrip_all) as out:
self.assertIn('a.bib', out)
with capture(c['b.bib'].show_characters) as out:
self.assertIn('CJK UNIFIED IDEOGRAPH', out)
abib = c[0]
self.assertEqual(len(list(abib.iterentries())), 3)
assert abib.size
assert abib.mtime
def test_show(self):
from pyglottolog.commands import show
with capture(show, self._args('**a:key**')) as out:
self.assertIn('@misc'.encode('utf8') if PY2 else '@misc', out)
with capture(show, self._args('a:key')) as out:
self.assertIn('@misc'.encode('utf8') if PY2 else '@misc', out)
with capture(show, self._args('abcd1236')) as out:
self.assertIn(
'Classification'.encode('utf8') if PY2 else 'Classificat', out)
def test_union(self):
from pyconcepticon.commands import union
Args = namedtuple('Args', ['data', 'args'])
with capture(
union,
Args(data='', args=['Swadesh-1955-100', 'Swadesh-1952-200'])) as out:
self.assertEqual(208, len(out.split('\n')))
with capture(
union,
Args(data='', args=['Swadesh-1952-200', 'Matisoff-1978-200'])) as out:
self.assertEqual(301, len(out.split('\n')))
def test_Collection(self):
from pyglottolog.monsterlib._bibfiles_db import Database
if not PY2: # pragma: no cover
return
db = self.tmp_path('test.sqlite')
with capture(self.api.bibfiles.to_sqlite, db) as out:
self.assertIn('ENTRYTYPE', out)
with capture(self.api.bibfiles.to_sqlite, db) as out:
pass
with capture(self.api.bibfiles.to_sqlite, db, rebuild=True) as out:
pass
db = Database(db, self.api.bibfiles)
with capture(db.recompute, reload_priorities=self.api.bibfiles) as out:
self.assertEqual(len(out.splitlines()), 34)
with capture(db.is_uptodate, self.api.bibfiles[1:],
verbose=True) as out:
self.assertEqual(len(out.splitlines()), 3)
db.to_bibfile(self.tmp_path('out.bib'))
db.to_csvfile(self.tmp_path('out.csv'))
db.to_replacements(self.tmp_path('out.json'))
self.assertEqual(db.to_hhmapping(), {'s:Karang:Tati-Harzani': 41999})
with capture(db.trickle) as out:
self.assertIn('2 changed 1 added in a', out)
key, (entrytype, fields) = db[('b.bib', 'arakawa97')]
self.assertEqual(entrytype, 'article')
self.assertEqual(fields['volume'], '16')
with capture(db.stats) as out:
pass
for attr in ['splits', 'merges', 'identified', 'combined']:
with capture(getattr(db, 'show_' + attr)) as out:
pass
def test_map(self):
if self.api.repos.exists():
with capture(self.api.map,
self.fixture_path('conceptlist.tsv')) as out:
self.assertIn('CONCEPTICON_ID', out)
self.assertGreater(len(self.api.conceptsets['217'].concepts), 8)
def test_main(self):
from pyglottolog.monster import main
with capture(main, repos=self.repos) as out:
self.assertEqual(len(out.splitlines()), 70)
self.assertIn('2 splitted', out)
self.assertIn('2 merged', out)
def test_fts(self):
from pyglottolog.commands import refindex, refsearch, langindex, langsearch
with self.assertRaises(ValueError):
refsearch(self._args('Harzani year:1334'))
refindex(self._args())
with capture(refsearch, self._args('Harzani year:1334')) as out:
self.assertIn("'Abd-al-'Ali Karang", out)
langindex(self._args())
with capture(langsearch, self._args('id:abcd*')) as out:
self.assertIn("abcd1234", out)
with capture(langsearch, self._args('classification')) as out:
self.assertIn("abcd1234", out)
def test_intersection(self):
from pyconcepticon.commands import intersection
Args = namedtuple('Args', ['data', 'args'])
with capture(
intersection,
Args(data='', args=['Swadesh-1955-100', 'Swadesh-1952-200'])) as out:
self.assertEqual(94, len(out.split('\n')))
def test_check(self):
from pyclpa.cli import check
with self.assertRaises(ParserError):
check(Mock(args=[]))
with capture(check, Mock(args=["abcd"])) as out:
self.assertIn("?", out)
def test_monster(self):
from pyglottolog.cli import monster
if not PY2: # pragma: no cover
return
with capture(monster, Mock(repos=self.repos)) as out:
assert out
def test_tree(self):
from pyglottolog.cli import tree
with capture(tree, Mock(repos=self.repos,
args=['abcd1234', 'language'])) as out:
out = out.decode('utf8')
self.assertIn('<l>', out)
self.assertNotIn('<d>', out)
def test_monster(self):
from pyglottolog.commands import bib
if not PY2: # pragma: no cover
return
with capture(bib, self._args()) as out:
assert out
def test_check(self):
from pyclpa.cli import check
with self.assertRaises(ParserError):
check(Mock(args=[]))
with capture(check, Mock(args=['abcd'])) as out:
self.assertIn('?', out)
def test_tree(self):
from pyglottolog.cli import tree
with capture(tree, Mock(repos=self.repos, args=['abcd1234', 'language'])) as out:
if not isinstance(out, text_type):
out = out.decode('utf8')
self.assertIn('<l>', out)
self.assertNotIn('<d>', out)
def test_create(self):
from pyglottolog.commands import create
with capture(create, self._args('abcd1234', 'new name',
'language')) as out:
self.assertIn('Info written', out)
self.assertIn(
'new name',
[c.name for c in self.api.languoid('abcd1234').children])
def test_main(self):
from pyglottolog.monster import main
if not PY2: # pragma: no cover
return
with capture(main, repos=self.repos) as out:
self.assertEqual(len(out.splitlines()), 70)
self.assertIn('2 splitted', out)
self.assertIn('2 merged', out)
def test_main(self):
from pyglottolog.monster import compile
if not PY2: # pragma: no cover
return
with capture(compile, self.api) as out:
self.assertEqual(len(out.splitlines()), 43)
self.assertIn('2 splitted', out)
self.assertIn('2 merged', out)
def test_operation(self):
wl = write('csv',
make_wordlist(),
_outdir=self.tmp_path(),
delimiter=',')
args = '-o {0} operation distances csv:IWordlist:{1}:delimiter=,'.format(
self.tmp_path(), wl)
with capture(cli.main, *args.split()) as out:
self.assertIn('written', out)
self.assertTrue(bool(list(self.tmp_path().glob('*.json'))))
def test_check(self):
from pyglottolog.commands import check
with capture(check, self._args('refs')):
pass
with capture(check, self._args()) as out:
self.assertIn('family', out)
for call in self.log.error.call_args_list:
self.assertIn('unregistered glottocode', call[0][0])
self.assertEqual(self.log.error.call_count, 4)
copytree(self.api.tree.joinpath('abcd1234', 'abcd1235'),
self.api.tree.joinpath('abcd1235'))
with capture(check, self._args()):
self.assertIn(
'duplicate glottocode',
''.join(c[0][0] for c in self.log.error.call_args_list))
self.assertEqual(self.log.error.call_count, 6)
def test_datasets(self):
from pycldf.cli import datasets
with self.assertRaises(ParserError):
datasets(MagicMock(args=MagicMock()))
with self.assertRaises(ParserError):
datasets(MagicMock(args=[self.tmp_path('new').as_posix()]))
with capture(datasets, MagicMock(args=[FIXTURES.as_posix(), "dc:title"])) as out:
self.assertIn('a cldf dataset', out)
def test_tree(self):
from pyglottolog.commands import tree, ParserError
with self.assertRaises(ParserError):
tree(self._args())
with self.assertRaises(ParserError):
tree(self._args('xyz'))
with capture(tree, self._args('abc', 'language')) as out:
if not isinstance(out, text_type):
out = out.decode('utf8')
self.assertIn('language', out)
self.assertNotIn('dialect', out)
def test_stats(self):
from pycldf.cli import stats
with self.assertRaises(ParserError):
stats(MagicMock(args=MagicMock()))
with self.assertRaises(ParserError):
stats(MagicMock(args=[self.tmp_path('new').as_posix()]))
ds = make_dataset(rows=[[1, 1, 1, 1]])
ds.write(self.tmp_path(), archive=True)
with capture(stats,
MagicMock(args=[self.tmp_path('test.zip').as_posix()])) as out:
self.assertIn('languages: 1', out)
with capture(stats,
MagicMock(args=[
FIXTURES.joinpath('ds1.csv-metadata.json').as_posix()])) as out:
self.assertIn('languages: 1', out)
with capture(stats,
MagicMock(args=[FIXTURES.joinpath('ds1.csv').as_posix()])) as out:
self.assertIn('languages: 1', out)
def test_lff(self):
from pyglottolog.commands import tree2lff, lff2tree
tree2lff(self._args())
with self.api.build_path('dff.txt').open(encoding='utf8') as fp:
dfftxt = fp.read().replace('dialect', 'Dialect Name')
with self.api.build_path('dff.txt').open('w', encoding='utf8') as fp:
fp.write(dfftxt)
with capture(lff2tree, self._args()) as out:
self.assertIn('git status', out)
self.assertEqual(self.api.languoid('abcd1236').name, 'Dialect Name')
tree2lff(self._args())
with self.api.build_path('dff.txt').open(encoding='utf8') as fp:
self.assertEqual(dfftxt, fp.read())
def test_capture_all(self):
from clldutils.testing import capture_all, capture
def func():
print('hello')
print('world', file=sys.stderr)
return 5
with capture_all(func) as res:
ret, out, err = res
self.assertEqual(ret, 5)
self.assertEqual(out.strip(), 'hello')
self.assertEqual(err.strip(), 'world')
with capture(func) as out:
self.assertEqual(out.strip(), 'hello')
def test_keyid():
from pyglottolog.monsterlib._libmonster import keyid
for fields, res in [
({}, '__missingcontrib__'),
(dict(author='An Author'), 'author_no-titlend'),
(dict(editor='An Author'), 'author_no-titlend'),
(dict(author='An Author', title='A rather long title'), 'author_rather-longnd'),
(dict(author='An Author', title='Title', year='2014'), 'author_title2014'),
(dict(author='An Author', volume='IV'), 'author_no-titleivnd'),
(dict(author='An Author', extra_hash='a'), 'author_no-titlenda'),
]:
assert_equal(keyid(fields, {}), res)
with capture(keyid, dict(author='An Author and '), {}) as out:
assert 'Unparsed' in out
def test_keyid():
from pyglottolog.monsterlib._libmonster import keyid
for fields, res in [
({}, '__missingcontrib__'),
(dict(author='An Author'), 'author_no-titlend'),
(dict(editor='An Author'), 'author_no-titlend'),
(dict(author='An Author',
title='A rather long title'), 'author_rather-longnd'),
(dict(author='An Author', title='Title',
year='2014'), 'author_title2014'),
(dict(author='An Author', volume='IV'), 'author_no-titleivnd'),
(dict(author='An Author', extra_hash='a'), 'author_no-titlenda'),
]:
assert_equal(keyid(fields, {}), res)
with capture(keyid, dict(author='An Author and '), {}) as out:
assert 'Unparsed' in out
def test_link(self):
from pyconcepticon.commands import link
with self.assertRaises(ParserError):
link(Mock(args=['.'], data=None))
def nattr(p, attr):
return len(nfilter([getattr(i, attr, None) for i in read_all(p)]))
test = self.tmp_path('test.tsv')
copy(self.fixture_path('conceptlist.tsv'), test)
self.assertEqual(nattr(test, 'CONCEPTICON_GLOSS'), 0)
link(Mock(args=[test], data=None))
self.assertEqual(nattr(test, 'CONCEPTICON_GLOSS'), 1)
copy(self.fixture_path('conceptlist2.tsv'), test)
with capture(link, Mock(args=[test], data=None)) as out:
self.assertIn('unknown CONCEPTICON_GLOSS', out)
self.assertIn('mismatch', out)
def test_Collection(self):
from pyglottolog.monsterlib._bibfiles import Collection
from pyglottolog.monsterlib._bibfiles_db import Database
if not PY2: # pragma: no cover
return
c = Collection(self.references.joinpath('bibtex'))
with capture(c.check_all) as out:
self.assertNotIn('invalid', out)
with capture(c.roundtrip_all) as out:
self.assertIn('a.bib', out)
with capture(c['b.bib'].show_characters) as out:
self.assertIn('CJK UNIFIED IDEOGRAPH', out)
abib = c[0]
self.assertEqual(len(list(abib.iterentries())), 2)
assert abib.size
assert abib.mtime
db = self.tmp_path('test.sqlite').as_posix()
with capture(c.to_sqlite, db) as out:
self.assertIn('entries total', out)
with capture(c.to_sqlite, db) as out:
pass
with capture(c.to_sqlite, db, rebuild=True) as out:
pass
db = Database(db)
with capture(db.recompute, reload_priorities=c) as out:
self.assertEqual(len(out.splitlines()), 32)
with capture(db.is_uptodate, c[1:], verbose=True) as out:
self.assertEqual(len(out.splitlines()), 3)
db.to_bibfile(self.tmp_path('out.bib'))
db.to_csvfile(self.tmp_path('out.csv'))
db.to_replacements(self.tmp_path('out.json'))
self.assertEqual(db.to_hhmapping(), {'s:Karang:Tati-Harzani': 41999})
with capture(db.trickle, c) as out:
self.assertIn('2 changed 0 added in a.bib', out)
key, (entrytype, fields) = db[('b.bib', 'arakawa97')]
self.assertEqual(entrytype, 'article')
self.assertEqual(fields['volume'], '16')
with capture(db.stats) as out:
pass
for attr in ['splits', 'merges', 'identified', 'combined']:
with capture(getattr(db, 'show_' + attr)) as out:
pass
def test_attributes(self):
from pyconcepticon.commands import attributes
with capture(attributes, MagicMock(data=None)) as out:
self.assertIn('Occurrences', out)
def test_metadata(self):
from pyglottolog.commands import metadata
with capture(metadata, self._args()) as out:
self.assertIn("longitude", out)
def test_attributes(self):
from pyconcepticon.commands import attributes
with capture(attributes, MagicMock()) as out:
self.assertIn('Columns', out)
def test_help(self):
with capture(cli.main, 'help', 'operation') as out:
self.assertIn('positional arguments', out)
def test_monster(self):
from pyglottolog.cli import monster
with capture(monster, Mock(repos=self.repos)) as out:
assert out
def test_newick(self):
from pyglottolog.commands import newick
with capture(newick, self._args('abcd1235')) as out:
self.assertIn('language', out)
