def test_direct_usage(self):
"""Test RscHtmlReader used directly to parse file."""
r = RscHtmlReader()
fname = '10.1039_C6OB02074G.html'
f = io.open(os.path.join(os.path.dirname(__file__), 'data', 'rsc', fname), 'rb')
content = f.read()
d = r.readstring(content)
self.assertEqual(len(d.elements), 61)
def test_fig_id_detection(self):
""" Tests RscHtmlReader can detect the right number of figures and fig captions"""
r = RscHtmlReader()
fname = '10.1039_C6OB02074G.html'
f = io.open(
os.path.join(os.path.dirname(__file__), 'data', 'rsc', fname),
'rb')
content = f.read()
d = r.readstring(content)
figs = d.figures
ids = [fig.id for fig in figs]
self.assertEqual(len(ids), 4)
def test_fig_and_fig_cation_detection(self):
""" Tests RscHtmlReader can detect the right number of figures and fig captions"""
r = RscHtmlReader()
fname = 'B9PP00180H.html'
f = io.open(
os.path.join(os.path.dirname(__file__), 'data', 'rsc', fname),
'rb')
content = f.read()
d = r.readstring(content)
figs = d.figures
captions = [
fig.caption for fig in figs if fig.caption.text != ('\n' or '')
]
self.assertEqual(len(figs), 6)
self.assertEqual(len(captions), 6)
self.assertEqual(len(captions[1].sentences), 1)