def match(self, text):
matches = set()
for m in XML_PATTERN_RE.finditer(text):
if ANCHOR_URL_PATTERN_RE.search(m.group(0)) or\
ANCHOR_EMAIL_PATTERN_RE.match(m.group(0)):
continue
xml_element = m.group(0)
offset = m.start()
children = get_xml_pair(xml_element, offset, self.priority)
matches.add(
create_match(
(m.start(), m.end(), 'xml element', self.priority),
children))
for m in FUZZY_XML_PATTERN_RE.finditer(text):
if ANCHOR_URL_PATTERN_RE.match(m.group(0)) or\
ANCHOR_EMAIL_PATTERN_RE.match(m.group(0)):
continue
xml_element = m.group(0)
offset = m.start()
children = get_xml_pair(xml_element, offset, self.priority)
matches.add(
create_match(
(m.start(), m.end(), 'xml element', self.priority),
children))
return matches
def match(self, text):
matches = set()
for m in XML_PATTERN_RE.finditer(text):
if ANCHOR_URL_PATTERN_RE.search(m.group(0)) or\
ANCHOR_EMAIL_PATTERN_RE.match(m.group(0)):
continue
xml_element = m.group(0)
offset = m.start()
children = get_xml_pair(xml_element,offset,self.priority)
matches.add(
create_match(
(m.start(), m.end(), 'xml element', self.priority),
children))
for m in FUZZY_XML_PATTERN_RE.finditer(text):
if ANCHOR_URL_PATTERN_RE.match(m.group(0)) or\
ANCHOR_EMAIL_PATTERN_RE.match(m.group(0)):
continue
xml_element = m.group(0)
offset = m.start()
children = get_xml_pair(xml_element,offset,self.priority)
matches.add(
create_match(
(m.start(), m.end(), 'xml element', self.priority),
children))
return matches
def is_xml_lines(lines):
xml_lines = 0
empty_lines = 0
confidence = 0.0
lines_size = len(lines)
for line in lines:
if len(line.strip()) == 0:
empty_lines += 1
elif (XML_STRICT_PATTERN1_RE.match(line) or
XML_STRICT_PATTERN2_RE.match(line) or
XML_STRICT_COMMENT_RE.match(line)) and not \
(ANCHOR_URL_PATTERN_RE.search(line) or \
ANCHOR_EMAIL_PATTERN_RE.search(line)):
xml_lines += 1
elif lines_size > 1:
if XML_STRICT_OPENING_RE.match(line) or \
XML_STRICT_CLOSING_RE.match(line) or \
line.strip().startswith('<--') or \
line.strip().endswith('-->') or \
XML_ATTRIBUTE_VALUE_PAIR_STRICT_RE.search(line):
xml_lines += 1
non_empty_lines = lines_size - empty_lines
if non_empty_lines > 0:
confidence = float(xml_lines) / (len(lines) - empty_lines)
if -0.10 <= (confidence - THRESHOLD_XML) <= 0:
logger.info('Almost reached XML threshold: {0}'.format(lines))
return (confidence >= THRESHOLD_XML, confidence)
def is_xml_lines(lines):
xml_lines = 0
empty_lines = 0
confidence = 0.0
lines_size = len(lines)
for line in lines:
if len(line.strip()) == 0:
empty_lines += 1
elif (XML_STRICT_PATTERN1_RE.match(line) or
XML_STRICT_PATTERN2_RE.match(line) or
XML_STRICT_COMMENT_RE.match(line)) and not \
(ANCHOR_URL_PATTERN_RE.search(line) or \
ANCHOR_EMAIL_PATTERN_RE.search(line)):
xml_lines += 1
elif lines_size > 1:
if XML_STRICT_OPENING_RE.match(line) or \
XML_STRICT_CLOSING_RE.match(line) or \
line.strip().startswith('<--') or \
line.strip().endswith('-->') or \
XML_ATTRIBUTE_VALUE_PAIR_STRICT_RE.search(line):
xml_lines += 1
non_empty_lines = lines_size - empty_lines
if non_empty_lines > 0:
confidence = float(xml_lines) / (len(lines) - empty_lines)
if -0.10 <= (confidence - THRESHOLD_XML) <= 0:
logger.info('Almost reached XML threshold: {0}'.format(lines))
return (confidence >= THRESHOLD_XML, confidence)