def test_node_encoding(self):
'''
Test that tgrep search strings handles bytes and strs the same
way.
'''
tree = ParentedTree.fromstring('(S (NP (DT the) (JJ big) (NN dog)) '
'(VP bit) (NP (DT a) (NN cat)))')
self.assertEqual(list(tgrep.tgrep_positions(b('NN'), [tree])),
list(tgrep.tgrep_positions('NN', [tree])))
self.assertEqual(list(tgrep.tgrep_nodes(b('NN'), [tree])),
list(tgrep.tgrep_nodes('NN', [tree])))
self.assertEqual(list(tgrep.tgrep_positions(b('NN|JJ'), [tree])),
list(tgrep.tgrep_positions('NN|JJ', [tree])))
def test_node_encoding(self):
'''
Test that tgrep search strings handles bytes and strs the same
way.
'''
tree = ParentedTree.fromstring(
'(S (NP (DT the) (JJ big) (NN dog)) '
'(VP bit) (NP (DT a) (NN cat)))')
self.assertEqual(list(tgrep.tgrep_positions(b('NN'), [tree])),
list(tgrep.tgrep_positions('NN', [tree])))
self.assertEqual(list(tgrep.tgrep_nodes(b('NN'), [tree])),
list(tgrep.tgrep_nodes('NN', [tree])))
self.assertEqual(list(tgrep.tgrep_positions(b('NN|JJ'), [tree])),
list(tgrep.tgrep_positions('NN|JJ', [tree])))
def test_tokenize_encoding(self):
'''
Test that tokenization handles bytes and strs the same way.
'''
self.assertEqual(
tgrep.tgrep_tokenize(b('A .. (B !< C . D) | ![<< (E , F) $ G]')),
tgrep.tgrep_tokenize('A .. (B !< C . D) | ![<< (E , F) $ G]'))
def test_tokenize_encoding(self):
'''
Test that tokenization handles bytes and strs the same way.
'''
self.assertEqual(
tgrep.tgrep_tokenize(b('A .. (B !< C . D) | ![<< (E , F) $ G]')),
tgrep.tgrep_tokenize('A .. (B !< C . D) | ![<< (E , F) $ G]'))
def __init__(self, term_stream=sys.stdout):
# If the stream isn't a tty, then assume it has no capabilities.
if not term_stream.isatty(): return
if self.FORCE_SIMPLE_TERM: return
# Curses isn't available on all platforms
try:
import curses
except:
# If it's not available, then try faking enough to get a
# simple progress bar.
self.BOL = '\r'
self.CLEAR_LINE = '\r' + ' ' * self.COLS + '\r'
# Check the terminal type. If we fail, then assume that the
# terminal has no capabilities.
try:
curses.setupterm()
except:
return
# Look up numeric capabilities.
self.COLS = curses.tigetnum('cols')
# Look up string capabilities.
for capability in self._STRING_CAPABILITIES:
(attrib, cap_name) = capability.split('=')
s = self._tigetstr(cap_name) or ''
if isinstance(s, bytes): s = s.decode('utf-8')
setattr(self, attrib, s)
if self.BOL and self.CLEAR_EOL:
self.CLEAR_LINE = self.BOL + self.CLEAR_EOL
# Colors
set_fg = self._tigetstr('setf')
if set_fg:
for i, color in enumerate(self._COLORS):
s = curses.tparm(b(set_fg), i) or ''
if isinstance(s, bytes): s = s.decode('utf-8')
setattr(self, color, s)
set_fg_ansi = self._tigetstr('setaf')
if set_fg_ansi:
for i, color in enumerate(self._ANSICOLORS):
s = curses.tparm(b(set_fg_ansi), i) or ''
if isinstance(s, bytes): s = s.decode('utf-8')
setattr(self, color, s)
def __init__(self, term_stream=sys.stdout):
# If the stream isn't a tty, then assume it has no capabilities.
if not term_stream.isatty(): return
if self.FORCE_SIMPLE_TERM: return
# Curses isn't available on all platforms
try: import curses
except:
# If it's not available, then try faking enough to get a
# simple progress bar.
self.BOL = '\r'
self.CLEAR_LINE = '\r' + ' '*self.COLS + '\r'
# Check the terminal type. If we fail, then assume that the
# terminal has no capabilities.
try: curses.setupterm()
except: return
# Look up numeric capabilities.
self.COLS = curses.tigetnum('cols')
# Look up string capabilities.
for capability in self._STRING_CAPABILITIES:
(attrib, cap_name) = capability.split('=')
s = self._tigetstr(cap_name) or ''
if isinstance(s, bytes): s = s.decode('utf-8')
setattr(self, attrib, s)
if self.BOL and self.CLEAR_EOL:
self.CLEAR_LINE = self.BOL+self.CLEAR_EOL
# Colors
set_fg = self._tigetstr('setf')
if set_fg:
for i,color in enumerate(self._COLORS):
s = curses.tparm(b(set_fg), i) or ''
if isinstance(s, bytes): s = s.decode('utf-8')
setattr(self, color, s)
set_fg_ansi = self._tigetstr('setaf')
if set_fg_ansi:
for i,color in enumerate(self._ANSICOLORS):
s = curses.tparm(b(set_fg_ansi), i) or ''
if isinstance(s, bytes): s = s.decode('utf-8')
setattr(self, color, s)