def __read_script(script, encoding = 'utf8'):
file_reg = '\[(.*)\]'
cmd_reg = '(\w+)\s*:\s*(.*)'
tag_file = None
cmd_set = {}
if isinstance(script, str):
content = text_file.read_file(script, 'all', encoding, True)
elif isinstance(script, list):
content = script
elif isinstance(script, dict):
return script
else:
raise IOError('script must be a filename or script command list')
for line in content:
if str_utils.is_empty(line):
continue
line = line.strip()
if str_utils.startswith(line, '#'):
continue
if regex_utils.check_line(file_reg, line):
tag_file = regex_utils.parse_line(file_reg, line)[0]
if str_utils.is_not_empty(tag_file):
tag_file = tag_file.strip()
elif regex_utils.check_line(cmd_reg, line):
cmd_item = regex_utils.parse_line(cmd_reg, line)
if tag_file is not None and cmd_item is not None and len(cmd_item) == 2:
cmd_list = cmd_set.get(tag_file) if cmd_set.has_key(tag_file) else []
cmd_list.append(cmd_item)
cmd_set[tag_file] = cmd_list
return cmd_set
def parse(string, rule_list):
if string_utils.is_blank(string) or not rule_list:
return None
string = string.strip()
for rule in rule_list:
rule_type = rule.get('type').strip() if rule.has_key('type') else ''
rule_type = 'regex' if rule_type == '' else rule_type
pattern = rule.get('pattern') if rule.has_key('pattern') else ''
if rule_type == 'regex':
if regex_utils.check_line(pattern, string):
value_list = regex_utils.parse_line(pattern, string)
map_index = __build_map_index(rule)
return __map_with_index(value_list, map_index)
elif rule_type == 'split':
match = rule.get('match') if rule.has_key('match') else ''
if __is_match(match, string):
value_list = string.split(pattern)
map_index = __build_map_index(rule)
return __map_with_index(value_list, map_index)
elif rule_type == 'keyword':
match = rule.get('match') if rule.has_key('match') else ''
if __is_match(match, string):
map_index = __build_map_index(rule)
return __map_with_keyword(string, map_index.values())
return None
def parse(string, rule_list):
if string_utils.is_blank(string) or not rule_list:
return None
string = string.strip()
for rule in rule_list:
rule_type = rule.get('type').strip() if rule.has_key('type') else ''
rule_type = 'regex' if rule_type == '' else rule_type
pattern = rule.get('pattern') if rule.has_key('pattern') else ''
if rule_type == 'regex':
if regex_utils.check_line(pattern, string):
value_list = regex_utils.parse_line(pattern, string)
map_index = __build_map_index(rule)
return __map_with_index(value_list, map_index)
elif rule_type == 'split':
match = rule.get('match') if rule.has_key('match') else ''
if __is_match(match, string):
value_list = string.split(pattern)
map_index = __build_map_index(rule)
return __map_with_index(value_list, map_index)
elif rule_type == 'keyword':
match = rule.get('match') if rule.has_key('match') else ''
if __is_match(match, string):
map_index = __build_map_index(rule)
return __map_with_keyword(string, map_index.values())
return None
def __read_script(script, encoding='utf8'):
file_reg = '\[(.*)\]'
cmd_reg = '(\w+)\s*:\s*(.*)'
tag_file = None
cmd_set = {}
if isinstance(script, str):
content = text_file.read_file(script, 'all', encoding, True)
elif isinstance(script, list):
content = script
elif isinstance(script, dict):
return script
else:
raise IOError('script must be a filename or script command list')
for line in content:
if str_utils.is_empty(line):
continue
line = line.strip()
if str_utils.startswith(line, '#'):
continue
if regex_utils.check_line(file_reg, line):
tag_file = regex_utils.parse_line(file_reg, line)[0]
if str_utils.is_not_empty(tag_file):
tag_file = tag_file.strip()
elif regex_utils.check_line(cmd_reg, line):
cmd_item = regex_utils.parse_line(cmd_reg, line)
if tag_file is not None and cmd_item is not None and len(
cmd_item) == 2:
cmd_list = cmd_set.get(tag_file) if cmd_set.has_key(
tag_file) else []
cmd_list.append(cmd_item)
cmd_set[tag_file] = cmd_list
return cmd_set
def __is_match(match, line):
result = False
if isinstance(match, basestring):
if regex_utils.check_line('(\S+)\((\S+)\)', match):
fun, value = regex_utils.parse_line('(\S+)\((\S+)\)', match)
if fun == 'startswith':
result = line.startswith(value)
elif fun == 'endswith':
result = line.endswith(value)
elif fun == 'in':
result = value in line
elif type(match) == types.FunctionType:
try:
result = match(line)
except:
result = False
return result
def __is_match(match, line):
result = False
if isinstance(match, basestring):
if regex_utils.check_line('(\S+)\((\S+)\)', match):
fun, value = regex_utils.parse_line('(\S+)\((\S+)\)', match)
if fun == 'startswith':
result = line.startswith(value)
elif fun == 'endswith':
result = line.endswith(value)
elif fun == 'in':
result = value in line
elif type(match) == types.FunctionType:
try:
result = match(line)
except:
result = False
return result
