1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 | Lib/xml/dom/pulldom.py
import xml.sax import xml.sax.handler import types try: _StringTypes = [types.StringType, types.UnicodeType] except AttributeError: _StringTypes = [types.StringType] START_ELEMENT = "START_ELEMENT" END_ELEMENT = "END_ELEMENT" COMMENT = "COMMENT" START_DOCUMENT = "START_DOCUMENT" END_DOCUMENT = "END_DOCUMENT" PROCESSING_INSTRUCTION = "PROCESSING_INSTRUCTION" IGNORABLE_WHITESPACE = "IGNORABLE_WHITESPACE" CHARACTERS = "CHARACTERS" class PullDOM(xml.sax.ContentHandler): _locator = None document = None def __init__(self, documentFactory=None): from xml.dom import XML_NAMESPACE self.documentFactory = documentFactory self.firstEvent = [None, None] self.lastEvent = self.firstEvent self.elementStack = [] self.push = self.elementStack.append try: self.pop = self.elementStack.pop except AttributeError: # use class' pop instead pass self._ns_contexts = [{XML_NAMESPACE:'xml'}] # contains uri -> prefix dicts self._current_context = self._ns_contexts[-1] self.pending_events = [] def pop(self): result = self.elementStack[-1] del self.elementStack[-1] return result def setDocumentLocator(self, locator): self._locator = locator def startPrefixMapping(self, prefix, uri): if not hasattr(self, '_xmlns_attrs'): self._xmlns_attrs = [] self._xmlns_attrs.append((prefix or 'xmlns', uri)) self._ns_contexts.append(self._current_context.copy()) self._current_context[uri] = prefix or None def endPrefixMapping(self, prefix): self._current_context = self._ns_contexts.pop() def startElementNS(self, name, tagName , attrs): # Retrieve xml namespace declaration attributes. xmlns_uri = 'http://www.w3.org/2000/xmlns/' xmlns_attrs = getattr(self, '_xmlns_attrs', None) if xmlns_attrs is not None: for aname, value in xmlns_attrs: attrs._attrs[(xmlns_uri, aname)] = value self._xmlns_attrs = [] uri, localname = name if uri: # When using namespaces, the reader may or may not # provide us with the original name. If not, create # *a* valid tagName from the current context. if tagName is None: prefix = self._current_context[uri] if prefix: tagName = prefix + ":" + localname else: tagName = localname if self.document: node = self.document.createElementNS(uri, tagName) else: node = self.buildDocument(uri, tagName) else: # When the tagname is not prefixed, it just appears as # localname if self.document: node = self.document.createElement(localname) else: node = self.buildDocument(None, localname) for aname,value in attrs.items(): a_uri, a_localname = aname if a_uri == xmlns_uri: if a_localname == 'xmlns': qname = a_localname else: qname = 'xmlns:' + a_localname attr = self.document.createAttributeNS(a_uri, qname) node.setAttributeNodeNS(attr) elif a_uri: prefix = self._current_context[a_uri] if prefix: qname = prefix + ":" + a_localname else: qname = a_localname attr = self.document.createAttributeNS(a_uri, qname) node.setAttributeNodeNS(attr) else: attr = self.document.createAttribute(a_localname) node.setAttributeNode(attr) attr.value = value self.lastEvent[1] = [(START_ELEMENT, node), None] self.lastEvent = self.lastEvent[1] self.push(node) def endElementNS(self, name, tagName): self.lastEvent[1] = [(END_ELEMENT, self.pop()), None] self.lastEvent = self.lastEvent[1] def startElement(self, name, attrs): if self.document: node = self.document.createElement(name) else: node = self.buildDocument(None, name) for aname,value in attrs.items(): attr = self.document.createAttribute(aname) attr.value = value node.setAttributeNode(attr) self.lastEvent[1] = [(START_ELEMENT, node), None] self.lastEvent = self.lastEvent[1] self.push(node) def endElement(self, name): self.lastEvent[1] = [(END_ELEMENT, self.pop()), None] self.lastEvent = self.lastEvent[1] def comment(self, s): if self.document: node = self.document.createComment(s) self.lastEvent[1] = [(COMMENT, node), None] self.lastEvent = self.lastEvent[1] else: event = [(COMMENT, s), None] self.pending_events.append(event) def processingInstruction(self, target, data): if self.document: node = self.document.createProcessingInstruction(target, data) self.lastEvent[1] = [(PROCESSING_INSTRUCTION, node), None] self.lastEvent = self.lastEvent[1] else: event = [(PROCESSING_INSTRUCTION, target, data), None] self.pending_events.append(event) def ignorableWhitespace(self, chars): node = self.document.createTextNode(chars) self.lastEvent[1] = [(IGNORABLE_WHITESPACE, node), None] self.lastEvent = self.lastEvent[1] def characters(self, chars): node = self.document.createTextNode(chars) self.lastEvent[1] = [(CHARACTERS, node), None] self.lastEvent = self.lastEvent[1] def startDocument(self): if self.documentFactory is None: import xml.dom.minidom self.documentFactory = xml.dom.minidom.Document.implementation def buildDocument(self, uri, tagname): # Can't do that in startDocument, since we need the tagname # XXX: obtain DocumentType node = self.documentFactory.createDocument(uri, tagname, None) self.document = node self.lastEvent[1] = [(START_DOCUMENT, node), None] self.lastEvent = self.lastEvent[1] self.push(node) # Put everything we have seen so far into the document for e in self.pending_events: if e[0][0] == PROCESSING_INSTRUCTION: _,target,data = e[0] n = self.document.createProcessingInstruction(target, data) e[0] = (PROCESSING_INSTRUCTION, n) elif e[0][0] == COMMENT: n = self.document.createComment(e[0][1]) e[0] = (COMMENT, n) else: raise AssertionError("Unknown pending event ",e[0][0]) self.lastEvent[1] = e self.lastEvent = e self.pending_events = None return node.firstChild def endDocument(self): self.lastEvent[1] = [(END_DOCUMENT, self.document), None] self.pop() def clear(self): "clear(): Explicitly release parsing structures" self.document = None class ErrorHandler: def warning(self, exception): print exception def error(self, exception): raise exception def fatalError(self, exception): raise exception class DOMEventStream: def __init__(self, stream, parser, bufsize): self.stream = stream self.parser = parser self.bufsize = bufsize if not hasattr(self.parser, 'feed'): self.getEvent = self._slurp self.reset() def reset(self): self.pulldom = PullDOM() # This content handler relies on namespace support self.parser.setFeature(xml.sax.handler.feature_namespaces, 1) self.parser.setContentHandler(self.pulldom) def __getitem__(self, pos): rc = self.getEvent() if rc: return rc raise IndexError def next(self): rc = self.getEvent() if rc: return rc raise StopIteration def __iter__(self): return self def expandNode(self, node): event = self.getEvent() parents = [node] while event: token, cur_node = event if cur_node is node: return if token != END_ELEMENT: parents[-1].appendChild(cur_node) if token == START_ELEMENT: parents.append(cur_node) elif token == END_ELEMENT: del parents[-1] event = self.getEvent() def getEvent(self): # use IncrementalParser interface, so we get the desired # pull effect if not self.pulldom.firstEvent[1]: self.pulldom.lastEvent = self.pulldom.firstEvent while not self.pulldom.firstEvent[1]: buf = self.stream.read(self.bufsize) if not buf: self.parser.close() return None self.parser.feed(buf) rc = self.pulldom.firstEvent[1][0] self.pulldom.firstEvent[1] = self.pulldom.firstEvent[1][1] return rc def _slurp(self): """ Fallback replacement for getEvent() using the standard SAX2 interface, which means we slurp the SAX events into memory (no performance gain, but we are compatible to all SAX parsers). """ self.parser.parse(self.stream) self.getEvent = self._emit return self._emit() def _emit(self): """ Fallback replacement for getEvent() that emits the events that _slurp() read previously. """ rc = self.pulldom.firstEvent[1][0] self.pulldom.firstEvent[1] = self.pulldom.firstEvent[1][1] return rc def clear(self): """clear(): Explicitly release parsing objects""" self.pulldom.clear() del self.pulldom self.parser = None self.stream = None class SAX2DOM(PullDOM): def startElementNS(self, name, tagName , attrs): PullDOM.startElementNS(self, name, tagName, attrs) curNode = self.elementStack[-1] parentNode = self.elementStack[-2] parentNode.appendChild(curNode) def startElement(self, name, attrs): PullDOM.startElement(self, name, attrs) curNode = self.elementStack[-1] parentNode = self.elementStack[-2] parentNode.appendChild(curNode) def processingInstruction(self, target, data): PullDOM.processingInstruction(self, target, data) node = self.lastEvent[0][1] parentNode = self.elementStack[-1] parentNode.appendChild(node) def ignorableWhitespace(self, chars): PullDOM.ignorableWhitespace(self, chars) node = self.lastEvent[0][1] parentNode = self.elementStack[-1] parentNode.appendChild(node) def characters(self, chars): PullDOM.characters(self, chars) node = self.lastEvent[0][1] parentNode = self.elementStack[-1] parentNode.appendChild(node) default_bufsize = (2 ** 14) - 20 def parse(stream_or_string, parser=None, bufsize=None): if bufsize is None: bufsize = default_bufsize if type(stream_or_string) in _StringTypes: stream = open(stream_or_string) else: stream = stream_or_string if not parser: parser = xml.sax.make_parser() return DOMEventStream(stream, parser, bufsize) def parseString(string, parser=None): try: from cStringIO import StringIO except ImportError: from StringIO import StringIO bufsize = len(string) buf = StringIO(string) if not parser: parser = xml.sax.make_parser() return DOMEventStream(buf, parser, bufsize) |