def mark_tags_in_text(text, matches):
'''
produce a text with the tags written as markup
:param text: text to tags
:param matches: tags to encode
:return:
'''
text_to_tag = text
tagged_abstract = ''
if isinstance(text, str):
text_to_tag = text
try:
tagged_abstract = ChangeCollector(text_to_tag)
for i, tag in enumerate(
sorted(matches, key=lambda x: (x['start'], -x['end']))):
if isinstance(tag['reference'], (list, tuple)):
tag_reference = '|'.join(tag['reference'])
else:
tag_reference = tag['reference']
tagged_abstract.add_change(
tag['start'], tag['start'],
'<mark-%s data-entity="%s" reference-db="%s" reference="%s">'
% (str(i), tag['category'], tag['reference_db'],
tag_reference))
tagged_abstract.add_change(tag['end'], tag['end'],
'</mark-%s>' % str(i))
tagged_abstract = '<div class="entities">%s</div></br>' % tagged_abstract.get_changed(
)
except UnicodeDecodeError:
logging.error(
'cannot generate maked text for unicode decode error')
return tagged_abstract
def substitute(self, mapping):
collector = ChangeCollector(self.template)
for name, occurrences in self.names.items():
for region in occurrences:
original = mapping[name]
result = self.twist(eval(original))
collector.add_change(region[0], region[1], result)
result = collector.get_changed()
if result is None:
return self.template
return result
def substitute(self, mapping):
collector = ChangeCollector(self.template)
for name, occurrences in self.names.items():
for region in occurrences:
original = mapping[name]
result = self.twist(eval(original))
collector.add_change(region[0], region[1], result)
result = collector.get_changed()
if result is None:
return self.template
return result
def print_code(self):
region = self.node.region
lines_min, lines_max = self.lines.get_line_number(region[0]), self.lines.get_line_number(region[1])
lines_min -= 1
if lines_min < 0:
lines_min = 0
lines_max += 2
if lines_max > self.lines.length():
lines_max = self.lines.length()
min_offset = self.lines.get_line_start(lines_min)
max_offset = self.lines.get_line_end(lines_max)
code = self.lines.code[min_offset: max_offset]
region_min = region[0] - min_offset
region_max = region[1] - min_offset
orig_offset = self.lines.get_line_start(self.node.lineno) + self.node.col_offset
orig_offset = orig_offset - min_offset
orig_f_offset = None
if hasattr(self.node, 'f_lineno') and hasattr(self.node, 'f_offset'):
try:
orig_f_offset = self.lines.get_line_start(self.node.f_lineno) + self.node.f_offset
orig_f_offset = orig_f_offset - min_offset
except:
pass
rnd = lambda : ''.join(random.choice(string.ascii_uppercase + string.digits) for _ in range(20))
a1, a2, a3, a4, a5, a6 = tuple(rnd() for _ in range(6))
t = {
a1: u'<span style="background-color:#339999;">',
a2: u'</span>',
a3: u'<span style="background-color:#660000;">',
a4: u'</span>',
a5: u'<span style="background-color:#060f0f;">',
a6: u'</span>',
}
c = ChangeCollector(code)
c.add_change(region_min, region_min, a1)
c.add_change(region_max, region_max, a2)
c.add_change(orig_offset, orig_offset, a3)
c.add_change(orig_offset+1, orig_offset+1, a4)
if orig_f_offset:
c.add_change(orig_f_offset, orig_f_offset, a5)
c.add_change(orig_f_offset+1, orig_f_offset+1, a6)
code = markupsafe.escape(code)
rend_code = c.get_changed()
for w, h in t.items():
rend_code = rend_code.replace(w,h)
return rend_code