def match(self, text):
matches = set()
for m in SIMPLE_CALL_RE.finditer(text):
matches.add(
create_match(
(m.start(), m.end(), 'method', self.priority)))
for m in METHOD_SIGNATURE_RE.finditer(text):
matches.add(
create_match(
(m.start(), m.end(), 'method', self.priority)))
for m in CALL_CHAIN_RE.finditer(text):
call_chain = text[m.start():m.end()]
offset = m.start()
children = []
for child_match in SIMPLE_CALL_NO_TARGET_RE.finditer(call_chain):
children.append(
(child_match.start() + offset,
child_match.end() + offset,
'method',
self.priority))
# Basically, children[0] is == m except that the target
# would not be there
matches.add(
create_match(
(m.start(), m.end(), 'method', self.priority),
children[1:]))
for m in METHOD_DECLARATION_STRICT_RE.finditer(text):
matches.add(
create_match(
(m.start(), m.end(), 'method', self.priority)))
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 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 SIMPLE_CALL_TARGET_RE.finditer(text):
matches.add(
create_match(
(m.start(), m.end(), 'class', self.priority),
[(m.start(), m.end(), 'method', self.priority)]))
for m in METHOD_SIGNATURE_TARGET_RE.finditer(text):
matches.add(
create_match(
(m.start(), m.end(), 'class', self.priority),
[(m.start(), m.end(), 'method', self.priority)]))
for m in CALL_CHAIN_TARGET_RE.finditer(text):
call_chain = text[m.start():m.end()]
offset = m.start()
children = []
for child_match in SIMPLE_CALL_NO_TARGET_RE.finditer(call_chain):
children.append(
(child_match.start() + offset,
child_match.end() + offset,
'method', self.priority))
# Basically, the first child should still refer to the container
first_child = [(m.start(), m.end(), 'method', self.priority)]
matches.add(
create_match(
(m.start(), m.end(), 'class', self.priority),
first_child + children[1:]))
return matches
def match(self, text):
matches = set()
for m in XML_FILE_RE.finditer(text):
matches.add(create_match(
(m.start(), m.end(), 'xml file', self.priority)))
for m in CONF_FILE_RE.finditer(text):
matches.add(create_match(
(m.start(), m.end(), 'conf file', self.priority)))
for m in INI_FILE_RE.finditer(text):
matches.add(create_match(
(m.start(), m.end(), 'ini file', self.priority)))
for m in PROPERTIES_FILE_RE.finditer(text):
matches.add(create_match(
(m.start(), m.end(), 'properties file', self.priority)))
for m in LOG_FILE_RE.finditer(text):
matches.add(create_match(
(m.start(), m.end(), 'log file', self.priority)))
for m in JAR_FILE_RE.finditer(text):
matches.add(create_match(
(m.start(), m.end(), 'jar file', self.priority)))
for m in JAVA_FILE_RE.finditer(text):
matches.add(create_match(
(m.start(), m.end(), 'java file', self.priority)))
for m in PYTHON_FILE_RE.finditer(text):
matches.add(create_match(
(m.start(), m.end(), 'python file', self.priority)))
for m in HBM_FILE_RE.finditer(text):
matches.add(create_match(
(m.start(), m.end(), 'hbm file', self.priority)))
return matches
def match(self, text):
matches = set()
for m in FQN_RE.finditer(text):
(simple, _) = clean_java_name(m.group(0))
if len(simple) > 0:
if simple[0].islower() or CONSTANT_RE.match(simple):
matches.add(
create_match(
(m.start(), m.end(), 'class', self.priority),
[(m.start(), m.end(), 'field', self.priority)]))
for m in CONSTANT_RE.finditer(text):
matches.add(
create_match(
(m.start(), m.end(), 'field', self.priority)))
return matches
def match(self, text):
matches = set()
for m in ANNOTATION_RE.finditer(text):
matches.add(
create_match(
(m.start(), m.end(), 'annotation', self.priority)))
return matches
def match(self, text):
matches = set()
for regex in self.regexes:
for m in regex.finditer(text):
#print('IGNORED: %s' % m.group(0))
matches.add(
create_match(
(m.start(), m.end(), IGNORE_KIND, self.priority)))
return matches
def parse_text_code_words(text, code_words):
# Because there is a chance that the FQN will match...
priority = 1
matches = []
words = split_pos(text)
for (word, start, end) in words:
if word in code_words:
# Because at this stage, we force it to choose one only...
matches.append(create_match((start, end, 'class', priority)))
return matches
def parse_text_code_words(text, code_words):
# Because there is a chance that the FQN will match...
priority = 1
matches = []
words = split_pos(text)
for (word, start, end) in words:
if word in code_words:
# Because at this stage, we force it to choose one only...
matches.append(create_match((start, end, 'class', priority)))
return matches
def match(self, text):
matches = set()
for m in FQN_RE.finditer(text):
matches.add(
create_match((m.start(), m.end(), 'class', self.priority)))
for m in CAMEL_CASE_1_RE.finditer(text):
matches.add(
create_match((m.start(), m.end(), 'class', self.priority)))
for m in CAMEL_CASE_2_RE.finditer(text):
matches.add(
create_match((m.start(), m.end(), 'class', self.priority)))
for m in CAMEL_CASE_3_RE.finditer(text):
matches.add(
create_match((m.start(), m.end(), 'class', self.priority)))
for m in CAMEL_CASE_4_RE.finditer(text):
matches.add(
create_match((m.start(), m.end(), 'class', self.priority)))
for m in TYPE_IN_MIDDLE_RE.finditer(text):
if m.group('dot') is None:
matches.add(create_match(
(m.start('class'), m.end('class'), 'class', self.priority))
)
return matches
def match(self, text):
matches = set()
for m in DEFINITION_ELEMENT_RE.finditer(text):
matches.add(create_match(
(m.start(1), m.end(1), 'unknown', self.priority)))
return matches