def _test_trees(self):
if not self._trees:
self._trees = {}
for i, tstr in enumerate([TSTR0, TSTR1]):
self._trees["tstr%d" % i] = parse.parse_rst_dt_tree(tstr)
for i in glob.glob('tests/*.dis'):
bname = os.path.basename(i)
tfile = os.path.splitext(i)[0]
self._trees[bname] = parse.read_annotation_file(i, tfile)
return self._trees
def _test_trees(self):
if not self._trees:
self._trees = {}
for i, tstr in enumerate([TSTR0, TSTR1]):
self._trees["tstr%d" % i] = parse.parse_rst_dt_tree(tstr)
for i in glob.glob('tests/*.dis'):
bname = os.path.basename(i)
tfile = os.path.splitext(i)[0]
self._trees[bname] = parse.read_annotation_file(i, tfile)
return self._trees
def slurp_subcorpus(self, cfiles, verbose=False):
"""
See `educe.rst_dt.parse` for a description of `RSTTree`
"""
corpus={}
counter=0
for k in cfiles.keys():
if verbose:
sys.stderr.write("\rSlurping corpus dir [%d/%d]" % (counter, len(cfiles)))
f = cfiles[k]
annotations=parse.read_annotation_file(f)
annotations.set_origin(k)
corpus[k]=annotations
counter=counter+1
if verbose:
sys.stderr.write("\rSlurping corpus dir [%d/%d done]\n" % (counter, len(cfiles)))
return corpus
def slurp_subcorpus(self, cfiles, verbose=False):
"""
See `educe.rst_dt.parse` for a description of `RSTTree`
"""
corpus = {}
counter = 0
for k in cfiles.keys():
if verbose:
sys.stderr.write("\rSlurping corpus dir [%d/%d]" %
(counter, len(cfiles)))
annotations = parse.read_annotation_file(*cfiles[k])
annotations.set_origin(k)
corpus[k] = annotations
counter = counter + 1
if verbose:
sys.stderr.write("\rSlurping corpus dir [%d/%d done]\n" %
(counter, len(cfiles)))
return corpus
def test_from_files(self):
for i in glob.glob('tests/*.dis'):
t = read_annotation_file(i, os.path.splitext(i)[0])
self.assertEqual(len(t.text()), treenode(t).span.char_end)
def test_from_files(self):
for i in glob.glob('tests/*.dis'):
t = read_annotation_file(i, os.path.splitext(i)[0])
self.assertEqual(len(t.text()), treenode(t).span.char_end)