def test_initial_markers(self):
"""Should not find any collapsed markers and should find all of the
markers at the beginning of the text"""
text = '(k)(2)(iii) abc (j)'
result = [m for m in reg_text.initial_markers(text)]
self.assertEqual(['k', '2', 'iii'], result)
text = '(i)(A) The minimum period payment'
result = [m for m in reg_text.initial_markers(text)]
self.assertEqual(['i', 'A'], result)
def test_initial_markers(self):
"""Should not find any collapsed markers and should find all of the
markers at the beginning of the text"""
text = '(k)(2)(iii) abc (j)'
result = [m for m in reg_text.initial_markers(text)]
self.assertEqual(['k', '2', 'iii'], result)
text = '(i)(A) The minimum period payment'
result = [m for m in reg_text.initial_markers(text)]
self.assertEqual(['i', 'A'], result)
def overwrite_marker(origin, new_label):
""" The node passed in has a label, but we're going to give it a
new one (new_label). This is necessary during node moves. """
if origin.node_type == Node.REGTEXT:
marker_list = reg_text.initial_markers(origin.text)
if len(marker_list) > 0:
marker = '(%s)' % marker_list[0]
new_marker = '(%s)' % new_label
origin.text = origin.text.replace(marker, new_marker, 1)
elif origin.node_type == Node.INTERP:
marker = interpretations.get_first_interp_marker(origin.text)
marker = marker + '.'
new_marker = new_label + '.'
origin.text = origin.text.replace(marker, new_marker, 1)
return origin
def overwrite_marker(origin, new_label):
""" The node passed in has a label, but we're going to give it a
new one (new_label). This is necessary during node moves. """
if origin.node_type == Node.REGTEXT:
marker_list = reg_text.initial_markers(origin.text)
if len(marker_list) > 0:
marker = '(%s)' % marker_list[0]
new_marker = '(%s)' % new_label
origin.text = origin.text.replace(marker, new_marker, 1)
elif origin.node_type == Node.INTERP:
marker = interpretations.get_first_interp_marker(origin.text)
marker = marker + '.'
new_marker = new_label + '.'
origin.text = origin.text.replace(marker, new_marker, 1)
return origin
def get_subsections_for_paragraph(self, paragraph, next_paragraph):
subsections = []
if next_paragraph:
next_markers = initial_markers(next_paragraph)
if len(next_markers) > 0:
next_marker = next_markers[0]
else:
next_marker = "MARKERLESS"
else:
next_marker = None
markers = get_markers(paragraph, next_marker)
if not markers:
subsections.append(('MARKERLESS', paragraph))
else:
marker_regex = ".*" + "(\( ?%s ?\).*)"*len(markers) % tuple(markers)
match = re.match(marker_regex, paragraph, re.S)
subsections.extend(zip(markers, match.groups()))
return subsections
def get_subsections_for_paragraph(self, paragraph, next_paragraph):
subsections = []
if next_paragraph:
next_markers = initial_markers(next_paragraph)
if len(next_markers) > 0:
next_marker = next_markers[0]
else:
next_marker = "MARKERLESS"
else:
next_marker = None
markers = get_markers(paragraph, next_marker)
if not markers:
subsections.append(('MARKERLESS', paragraph))
else:
tail = paragraph
for marker in markers:
head, tail = self.split_text_by_marker(marker, tail)
subsections.append((marker, tail))
return subsections