def _loadRegExpr(parentContext, xmlElement, attributeToFormatMap,
formatConverterFunction):
def _processCraracterCodes(text):
"""QRegExp use \0ddd notation for character codes, where d in octal digit
i.e. \0377 is character with code 255 in the unicode table
Convert such notation to unicode text
"""
text = unicode(text)
def replFunc(matchObj):
matchText = matchObj.group(0)
charCode = eval(matchText[1:])
return chr(charCode).decode('latin1')
return re.sub(r"\\0\d\d\d", replFunc, text)
insensitive = _parseBoolAttribute(
xmlElement.attrib.get('insensitive', 'false'))
string = _safeGetRequiredAttribute(xmlElement, 'String', None)
if string is not None:
string = _processCraracterCodes(string)
wordStart = string.strip('(').startswith('\\b')
lineStart = string.strip('(').startswith('^')
else:
wordStart = False
lineStart = False
abstractRuleParams = _loadAbstractRuleParams(parentContext, xmlElement,
attributeToFormatMap,
formatConverterFunction)
return _parserModule.RegExpr(abstractRuleParams, string, insensitive,
wordStart, lineStart)
def _loadRegExpr(parentContext, xmlElement, attributeToFormatMap,
formatConverterFunction):
def _processCraracterCodes(text):
"""QRegExp use \0ddd notation for character codes, where d in octal digit
i.e. \0377 is character with code 255 in the unicode table
Convert such notation to unicode text
"""
text = str(text)
def replFunc(matchObj):
matchText = matchObj.group(0)
charCode = eval('0o' + matchText[2:])
return chr(charCode)
return re.sub(r"\\0\d\d\d", replFunc, text)
insensitive = _parseBoolAttribute(
xmlElement.attrib.get('insensitive', 'false'))
minimal = _parseBoolAttribute(xmlElement.attrib.get('minimal', 'false'))
string = _safeGetRequiredAttribute(xmlElement, 'String', None)
if string is not None:
string = _processCraracterCodes(string)
strippedString = string.strip('(')
wordStart = strippedString.startswith('\\b')
lineStart = strippedString.startswith('^')
if len(strippedString) > 1 and strippedString[
1] == '|': # ^|blabla This condition is not ideal but will cover majority of cases
wordStart = False
lineStart = False
else:
wordStart = False
lineStart = False
abstractRuleParams = _loadAbstractRuleParams(parentContext, xmlElement,
attributeToFormatMap,
formatConverterFunction)
return _parserModule.RegExpr(abstractRuleParams, string, insensitive,
minimal, wordStart, lineStart)