Mercurial Repositories > eric / file comparison
comparison: E4XML/XMLHandlerBase.py
E4XML/XMLHandlerBase.py
- changeset 12
- 1d8dd9706f46
- parent 0
- de9c2efb9d02
- child 13
- 1af94a91f439
equal
deleted
inserted
replaced
| 11:b0996e4a289e | 12:1d8dd9706f46 |
|---|---|
| 6 """ | 6 """ |
| 7 Module implementing a base class for all of eric4s XML handlers. | 7 Module implementing a base class for all of eric4s XML handlers. |
| 8 """ | 8 """ |
| 9 | 9 |
| 10 import sys | 10 import sys |
| 11 from types import UnicodeType | 11 ##from types import UnicodeType |
| 12 try: | 12 import pickle as pickle |
| 13 import cPickle as pickle | |
| 14 except ImportError: | |
| 15 import pickle | |
| 16 | 13 |
| 17 from xml.sax.handler import ContentHandler | 14 from xml.sax.handler import ContentHandler |
| 18 | 15 |
| 19 class XMLHandlerBase(ContentHandler): | 16 class XMLHandlerBase(ContentHandler): |
| 20 """ | 17 """ |
| 43 | 40 |
| 44 self.buffer = "" | 41 self.buffer = "" |
| 45 self.stack = [] | 42 self.stack = [] |
| 46 self._marker = '__MARKER__' | 43 self._marker = '__MARKER__' |
| 47 | 44 |
| 48 self.NEWPARA = unichr(0x2029) | 45 self.NEWPARA = chr(0x2029) |
| 49 self.NEWLINE = unichr(0x2028) | 46 self.NEWLINE = chr(0x2028) |
| 50 | 47 |
| 51 def utf8_to_code(self, text): | 48 def utf8_to_code(self, text): |
| 52 """ | 49 """ |
| 53 Public method to convert a string to unicode and encode it for XML. | 50 Public method to convert a string to unicode and encode it for XML. |
| 54 | 51 |
| 55 @param text the text to encode (string) | 52 @param text the text to encode (string) |
| 56 """ | 53 """ |
| 57 if type(text) is not UnicodeType: | 54 # TODO: convert calls to this method to not use it anymore |
| 58 text = unicode(text, "utf-8") | 55 ## if not isinstance(text, UnicodeType): |
| 56 ## text = str(text, "utf-8") | |
| 59 return text | 57 return text |
| 60 | 58 |
| 61 def unescape(self, text, attribute = False): | 59 def unescape(self, text, attribute = False): |
| 62 """ | 60 """ |
| 63 Public method used to unescape certain characters. | 61 Public method used to unescape certain characters. |
| 156 | 154 |
| 157 def endLong(self): | 155 def endLong(self): |
| 158 """ | 156 """ |
| 159 Handler method for the "long" end tag. | 157 Handler method for the "long" end tag. |
| 160 """ | 158 """ |
| 161 self.stack.append(long(self.buffer.strip())) | 159 self.stack.append(int(self.buffer.strip())) |
| 162 | 160 |
| 163 def endBool(self): | 161 def endBool(self): |
| 164 """ | 162 """ |
| 165 Handler method for the "bool" end tag. | 163 Handler method for the "bool" end tag. |
| 166 """ | 164 """ |
| 191 | 189 |
| 192 def endUnicode(self): | 190 def endUnicode(self): |
| 193 """ | 191 """ |
| 194 Handler method for the "unicode" end tag. | 192 Handler method for the "unicode" end tag. |
| 195 """ | 193 """ |
| 196 u = unicode(self.utf8_to_code(self.unescape(self.buffer))) | 194 u = str(self.utf8_to_code(self.unescape(self.buffer))) |
| 197 self.stack.append(u) | 195 self.stack.append(u) |
| 198 | 196 |
| 199 def startList(self, attrs): | 197 def startList(self, attrs): |
| 200 """ | 198 """ |
| 201 Handler method for the "list" start tag. | 199 Handler method for the "list" start tag. |
