projects / mirror_edk2.git / blame
| Commit | Line | Data |
|---|---|---|
| 3257aa99 DM |
1 | #\r |
| 2 | # ElementTree\r | |
| 3 | # $Id: ElementTree.py 3440 2008-07-18 14:45:01Z fredrik $\r | |
| 4 | #\r | |
| 5 | # light-weight XML support for Python 2.3 and later.\r | |
| 6 | #\r | |
| 7 | # history (since 1.2.6):\r | |
| 8 | # 2005-11-12 fl added tostringlist/fromstringlist helpers\r | |
| 9 | # 2006-07-05 fl merged in selected changes from the 1.3 sandbox\r | |
| 10 | # 2006-07-05 fl removed support for 2.1 and earlier\r | |
| 11 | # 2007-06-21 fl added deprecation/future warnings\r | |
| 12 | # 2007-08-25 fl added doctype hook, added parser version attribute etc\r | |
| 13 | # 2007-08-26 fl added new serializer code (better namespace handling, etc)\r | |
| 14 | # 2007-08-27 fl warn for broken /tag searches on tree level\r | |
| 15 | # 2007-09-02 fl added html/text methods to serializer (experimental)\r | |
| 16 | # 2007-09-05 fl added method argument to tostring/tostringlist\r | |
| 17 | # 2007-09-06 fl improved error handling\r | |
| 18 | # 2007-09-13 fl added itertext, iterfind; assorted cleanups\r | |
| 19 | # 2007-12-15 fl added C14N hooks, copy method (experimental)\r | |
| 20 | #\r | |
| 21 | # Copyright (c) 1999-2008 by Fredrik Lundh. All rights reserved.\r | |
| 22 | #\r | |
| 23 | # fredrik@pythonware.com\r | |
| 24 | # http://www.pythonware.com\r | |
| 25 | #\r | |
| 26 | # --------------------------------------------------------------------\r | |
| 27 | # The ElementTree toolkit is\r | |
| 28 | #\r | |
| 29 | # Copyright (c) 1999-2008 by Fredrik Lundh\r | |
| 30 | #\r | |
| 31 | # By obtaining, using, and/or copying this software and/or its\r | |
| 32 | # associated documentation, you agree that you have read, understood,\r | |
| 33 | # and will comply with the following terms and conditions:\r | |
| 34 | #\r | |
| 35 | # Permission to use, copy, modify, and distribute this software and\r | |
| 36 | # its associated documentation for any purpose and without fee is\r | |
| 37 | # hereby granted, provided that the above copyright notice appears in\r | |
| 38 | # all copies, and that both that copyright notice and this permission\r | |
| 39 | # notice appear in supporting documentation, and that the name of\r | |
| 40 | # Secret Labs AB or the author not be used in advertising or publicity\r | |
| 41 | # pertaining to distribution of the software without specific, written\r | |
| 42 | # prior permission.\r | |
| 43 | #\r | |
| 44 | # SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD\r | |
| 45 | # TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-\r | |
| 46 | # ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR\r | |
| 47 | # BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY\r | |
| 48 | # DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,\r | |
| 49 | # WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS\r | |
| 50 | # ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE\r | |
| 51 | # OF THIS SOFTWARE.\r | |
| 52 | # --------------------------------------------------------------------\r | |
| 53 | \r | |
| 54 | # Licensed to PSF under a Contributor Agreement.\r | |
| 55 | # See http://www.python.org/psf/license for licensing details.\r | |
| 56 | \r | |
| 57 | __all__ = [\r | |
| 58 | # public symbols\r | |
| 59 | "Comment",\r | |
| 60 | "dump",\r | |
| 61 | "Element", "ElementTree",\r | |
| 62 | "fromstring", "fromstringlist",\r | |
| 63 | "iselement", "iterparse",\r | |
| 64 | "parse", "ParseError",\r | |
| 65 | "PI", "ProcessingInstruction",\r | |
| 66 | "QName",\r | |
| 67 | "SubElement",\r | |
| 68 | "tostring", "tostringlist",\r | |
| 69 | "TreeBuilder",\r | |
| 70 | "VERSION",\r | |
| 71 | "XML",\r | |
| 72 | "XMLParser", "XMLTreeBuilder",\r | |
| 73 | ]\r | |
| 74 | \r | |
| 75 | VERSION = "1.3.0"\r | |
| 76 | \r | |
| 77 | ##\r | |
| 78 | # The <b>Element</b> type is a flexible container object, designed to\r | |
| 79 | # store hierarchical data structures in memory. The type can be\r | |
| 80 | # described as a cross between a list and a dictionary.\r | |
| 81 | # <p>\r | |
| 82 | # Each element has a number of properties associated with it:\r | |
| 83 | # <ul>\r | |
| 84 | # <li>a <i>tag</i>. This is a string identifying what kind of data\r | |
| 85 | # this element represents (the element type, in other words).</li>\r | |
| 86 | # <li>a number of <i>attributes</i>, stored in a Python dictionary.</li>\r | |
| 87 | # <li>a <i>text</i> string.</li>\r | |
| 88 | # <li>an optional <i>tail</i> string.</li>\r | |
| 89 | # <li>a number of <i>child elements</i>, stored in a Python sequence</li>\r | |
| 90 | # </ul>\r | |
| 91 | #\r | |
| 92 | # To create an element instance, use the {@link #Element} constructor\r | |
| 93 | # or the {@link #SubElement} factory function.\r | |
| 94 | # <p>\r | |
| 95 | # The {@link #ElementTree} class can be used to wrap an element\r | |
| 96 | # structure, and convert it from and to XML.\r | |
| 97 | ##\r | |
| 98 | \r | |
| 99 | import sys\r | |
| 100 | import re\r | |
| 101 | import warnings\r | |
| 102 | \r | |
| 103 | \r | |
| 104 | class _SimpleElementPath(object):\r | |
| 105 | # emulate pre-1.2 find/findtext/findall behaviour\r | |
| 106 | def find(self, element, tag, namespaces=None):\r | |
| 107 | for elem in element:\r | |
| 108 | if elem.tag == tag:\r | |
| 109 | return elem\r | |
| 110 | return None\r | |
| 111 | def findtext(self, element, tag, default=None, namespaces=None):\r | |
| 112 | elem = self.find(element, tag)\r | |
| 113 | if elem is None:\r | |
| 114 | return default\r | |
| 115 | return elem.text or ""\r | |
| 116 | def iterfind(self, element, tag, namespaces=None):\r | |
| 117 | if tag[:3] == ".//":\r | |
| 118 | for elem in element.iter(tag[3:]):\r | |
| 119 | yield elem\r | |
| 120 | for elem in element:\r | |
| 121 | if elem.tag == tag:\r | |
| 122 | yield elem\r | |
| 123 | def findall(self, element, tag, namespaces=None):\r | |
| 124 | return list(self.iterfind(element, tag, namespaces))\r | |
| 125 | \r | |
| 126 | try:\r | |
| 127 | from . import ElementPath\r | |
| 128 | except ImportError:\r | |
| 129 | ElementPath = _SimpleElementPath()\r | |
| 130 | \r | |
| 131 | ##\r | |
| 132 | # Parser error. This is a subclass of <b>SyntaxError</b>.\r | |
| 133 | # <p>\r | |
| 134 | # In addition to the exception value, an exception instance contains a\r | |
| 135 | # specific exception code in the <b>code</b> attribute, and the line and\r | |
| 136 | # column of the error in the <b>position</b> attribute.\r | |
| 137 | \r | |
| 138 | class ParseError(SyntaxError):\r | |
| 139 | pass\r | |
| 140 | \r | |
| 141 | # --------------------------------------------------------------------\r | |
| 142 | \r | |
| 143 | ##\r | |
| 144 | # Checks if an object appears to be a valid element object.\r | |
| 145 | #\r | |
| 146 | # @param An element instance.\r | |
| 147 | # @return A true value if this is an element object.\r | |
| 148 | # @defreturn flag\r | |
| 149 | \r | |
| 150 | def iselement(element):\r | |
| 151 | # FIXME: not sure about this; might be a better idea to look\r | |
| 152 | # for tag/attrib/text attributes\r | |
| 153 | return isinstance(element, Element) or hasattr(element, "tag")\r | |
| 154 | \r | |
| 155 | ##\r | |
| 156 | # Element class. This class defines the Element interface, and\r | |
| 157 | # provides a reference implementation of this interface.\r | |
| 158 | # <p>\r | |
| 159 | # The element name, attribute names, and attribute values can be\r | |
| 160 | # either ASCII strings (ordinary Python strings containing only 7-bit\r | |
| 161 | # ASCII characters) or Unicode strings.\r | |
| 162 | #\r | |
| 163 | # @param tag The element name.\r | |
| 164 | # @param attrib An optional dictionary, containing element attributes.\r | |
| 165 | # @param **extra Additional attributes, given as keyword arguments.\r | |
| 166 | # @see Element\r | |
| 167 | # @see SubElement\r | |
| 168 | # @see Comment\r | |
| 169 | # @see ProcessingInstruction\r | |
| 170 | \r | |
| 171 | class Element(object):\r | |
| 172 | # <tag attrib>text<child/>...</tag>tail\r | |
| 173 | \r | |
| 174 | ##\r | |
| 175 | # (Attribute) Element tag.\r | |
| 176 | \r | |
| 177 | tag = None\r | |
| 178 | \r | |
| 179 | ##\r | |
| 180 | # (Attribute) Element attribute dictionary. Where possible, use\r | |
| 181 | # {@link #Element.get},\r | |
| 182 | # {@link #Element.set},\r | |
| 183 | # {@link #Element.keys}, and\r | |
| 184 | # {@link #Element.items} to access\r | |
| 185 | # element attributes.\r | |
| 186 | \r | |
| 187 | attrib = None\r | |
| 188 | \r | |
| 189 | ##\r | |
| 190 | # (Attribute) Text before first subelement. This is either a\r | |
| 191 | # string or the value None. Note that if there was no text, this\r | |
| 192 | # attribute may be either None or an empty string, depending on\r | |
| 193 | # the parser.\r | |
| 194 | \r | |
| 195 | text = None\r | |
| 196 | \r | |
| 197 | ##\r | |
| 198 | # (Attribute) Text after this element's end tag, but before the\r | |
| 199 | # next sibling element's start tag. This is either a string or\r | |
| 200 | # the value None. Note that if there was no text, this attribute\r | |
| 201 | # may be either None or an empty string, depending on the parser.\r | |
| 202 | \r | |
| 203 | tail = None # text after end tag, if any\r | |
| 204 | \r | |
| 205 | # constructor\r | |
| 206 | \r | |
| 207 | def __init__(self, tag, attrib={}, **extra):\r | |
| 208 | attrib = attrib.copy()\r | |
| 209 | attrib.update(extra)\r | |
| 210 | self.tag = tag\r | |
| 211 | self.attrib = attrib\r | |
| 212 | self._children = []\r | |
| 213 | \r | |
| 214 | def __repr__(self):\r | |
| 215 | return "<Element %s at 0x%x>" % (repr(self.tag), id(self))\r | |
| 216 | \r | |
| 217 | ##\r | |
| 218 | # Creates a new element object of the same type as this element.\r | |
| 219 | #\r | |
| 220 | # @param tag Element tag.\r | |
| 221 | # @param attrib Element attributes, given as a dictionary.\r | |
| 222 | # @return A new element instance.\r | |
| 223 | \r | |
| 224 | def makeelement(self, tag, attrib):\r | |
| 225 | return self.__class__(tag, attrib)\r | |
| 226 | \r | |
| 227 | ##\r | |
| 228 | # (Experimental) Copies the current element. This creates a\r | |
| 229 | # shallow copy; subelements will be shared with the original tree.\r | |
| 230 | #\r | |
| 231 | # @return A new element instance.\r | |
| 232 | \r | |
| 233 | def copy(self):\r | |
| 234 | elem = self.makeelement(self.tag, self.attrib)\r | |
| 235 | elem.text = self.text\r | |
| 236 | elem.tail = self.tail\r | |
| 237 | elem[:] = self\r | |
| 238 | return elem\r | |
| 239 | \r | |
| 240 | ##\r | |
| 241 | # Returns the number of subelements. Note that this only counts\r | |
| 242 | # full elements; to check if there's any content in an element, you\r | |
| 243 | # have to check both the length and the <b>text</b> attribute.\r | |
| 244 | #\r | |
| 245 | # @return The number of subelements.\r | |
| 246 | \r | |
| 247 | def __len__(self):\r | |
| 248 | return len(self._children)\r | |
| 249 | \r | |
| 250 | def __nonzero__(self):\r | |
| 251 | warnings.warn(\r | |
| 252 | "The behavior of this method will change in future versions. "\r | |
| 253 | "Use specific 'len(elem)' or 'elem is not None' test instead.",\r | |
| 254 | FutureWarning, stacklevel=2\r | |
| 255 | )\r | |
| 256 | return len(self._children) != 0 # emulate old behaviour, for now\r | |
| 257 | \r | |
| 258 | ##\r | |
| 259 | # Returns the given subelement, by index.\r | |
| 260 | #\r | |
| 261 | # @param index What subelement to return.\r | |
| 262 | # @return The given subelement.\r | |
| 263 | # @exception IndexError If the given element does not exist.\r | |
| 264 | \r | |
| 265 | def __getitem__(self, index):\r | |
| 266 | return self._children[index]\r | |
| 267 | \r | |
| 268 | ##\r | |
| 269 | # Replaces the given subelement, by index.\r | |
| 270 | #\r | |
| 271 | # @param index What subelement to replace.\r | |
| 272 | # @param element The new element value.\r | |
| 273 | # @exception IndexError If the given element does not exist.\r | |
| 274 | \r | |
| 275 | def __setitem__(self, index, element):\r | |
| 276 | # if isinstance(index, slice):\r | |
| 277 | # for elt in element:\r | |
| 278 | # assert iselement(elt)\r | |
| 279 | # else:\r | |
| 280 | # assert iselement(element)\r | |
| 281 | self._children[index] = element\r | |
| 282 | \r | |
| 283 | ##\r | |
| 284 | # Deletes the given subelement, by index.\r | |
| 285 | #\r | |
| 286 | # @param index What subelement to delete.\r | |
| 287 | # @exception IndexError If the given element does not exist.\r | |
| 288 | \r | |
| 289 | def __delitem__(self, index):\r | |
| 290 | del self._children[index]\r | |
| 291 | \r | |
| 292 | ##\r | |
| 293 | # Adds a subelement to the end of this element. In document order,\r | |
| 294 | # the new element will appear after the last existing subelement (or\r | |
| 295 | # directly after the text, if it's the first subelement), but before\r | |
| 296 | # the end tag for this element.\r | |
| 297 | #\r | |
| 298 | # @param element The element to add.\r | |
| 299 | \r | |
| 300 | def append(self, element):\r | |
| 301 | # assert iselement(element)\r | |
| 302 | self._children.append(element)\r | |
| 303 | \r | |
| 304 | ##\r | |
| 305 | # Appends subelements from a sequence.\r | |
| 306 | #\r | |
| 307 | # @param elements A sequence object with zero or more elements.\r | |
| 308 | # @since 1.3\r | |
| 309 | \r | |
| 310 | def extend(self, elements):\r | |
| 311 | # for element in elements:\r | |
| 312 | # assert iselement(element)\r | |
| 313 | self._children.extend(elements)\r | |
| 314 | \r | |
| 315 | ##\r | |
| 316 | # Inserts a subelement at the given position in this element.\r | |
| 317 | #\r | |
| 318 | # @param index Where to insert the new subelement.\r | |
| 319 | \r | |
| 320 | def insert(self, index, element):\r | |
| 321 | # assert iselement(element)\r | |
| 322 | self._children.insert(index, element)\r | |
| 323 | \r | |
| 324 | ##\r | |
| 325 | # Removes a matching subelement. Unlike the <b>find</b> methods,\r | |
| 326 | # this method compares elements based on identity, not on tag\r | |
| 327 | # value or contents. To remove subelements by other means, the\r | |
| 328 | # easiest way is often to use a list comprehension to select what\r | |
| 329 | # elements to keep, and use slice assignment to update the parent\r | |
| 330 | # element.\r | |
| 331 | #\r | |
| 332 | # @param element What element to remove.\r | |
| 333 | # @exception ValueError If a matching element could not be found.\r | |
| 334 | \r | |
| 335 | def remove(self, element):\r | |
| 336 | # assert iselement(element)\r | |
| 337 | self._children.remove(element)\r | |
| 338 | \r | |
| 339 | ##\r | |
| 340 | # (Deprecated) Returns all subelements. The elements are returned\r | |
| 341 | # in document order.\r | |
| 342 | #\r | |
| 343 | # @return A list of subelements.\r | |
| 344 | # @defreturn list of Element instances\r | |
| 345 | \r | |
| 346 | def getchildren(self):\r | |
| 347 | warnings.warn(\r | |
| 348 | "This method will be removed in future versions. "\r | |
| 349 | "Use 'list(elem)' or iteration over elem instead.",\r | |
| 350 | DeprecationWarning, stacklevel=2\r | |
| 351 | )\r | |
| 352 | return self._children\r | |
| 353 | \r | |
| 354 | ##\r | |
| 355 | # Finds the first matching subelement, by tag name or path.\r | |
| 356 | #\r | |
| 357 | # @param path What element to look for.\r | |
| 358 | # @keyparam namespaces Optional namespace prefix map.\r | |
| 359 | # @return The first matching element, or None if no element was found.\r | |
| 360 | # @defreturn Element or None\r | |
| 361 | \r | |
| 362 | def find(self, path, namespaces=None):\r | |
| 363 | return ElementPath.find(self, path, namespaces)\r | |
| 364 | \r | |
| 365 | ##\r | |
| 366 | # Finds text for the first matching subelement, by tag name or path.\r | |
| 367 | #\r | |
| 368 | # @param path What element to look for.\r | |
| 369 | # @param default What to return if the element was not found.\r | |
| 370 | # @keyparam namespaces Optional namespace prefix map.\r | |
| 371 | # @return The text content of the first matching element, or the\r | |
| 372 | # default value no element was found. Note that if the element\r | |
| 373 | # is found, but has no text content, this method returns an\r | |
| 374 | # empty string.\r | |
| 375 | # @defreturn string\r | |
| 376 | \r | |
| 377 | def findtext(self, path, default=None, namespaces=None):\r | |
| 378 | return ElementPath.findtext(self, path, default, namespaces)\r | |
| 379 | \r | |
| 380 | ##\r | |
| 381 | # Finds all matching subelements, by tag name or path.\r | |
| 382 | #\r | |
| 383 | # @param path What element to look for.\r | |
| 384 | # @keyparam namespaces Optional namespace prefix map.\r | |
| 385 | # @return A list or other sequence containing all matching elements,\r | |
| 386 | # in document order.\r | |
| 387 | # @defreturn list of Element instances\r | |
| 388 | \r | |
| 389 | def findall(self, path, namespaces=None):\r | |
| 390 | return ElementPath.findall(self, path, namespaces)\r | |
| 391 | \r | |
| 392 | ##\r | |
| 393 | # Finds all matching subelements, by tag name or path.\r | |
| 394 | #\r | |
| 395 | # @param path What element to look for.\r | |
| 396 | # @keyparam namespaces Optional namespace prefix map.\r | |
| 397 | # @return An iterator or sequence containing all matching elements,\r | |
| 398 | # in document order.\r | |
| 399 | # @defreturn a generated sequence of Element instances\r | |
| 400 | \r | |
| 401 | def iterfind(self, path, namespaces=None):\r | |
| 402 | return ElementPath.iterfind(self, path, namespaces)\r | |
| 403 | \r | |
| 404 | ##\r | |
| 405 | # Resets an element. This function removes all subelements, clears\r | |
| 406 | # all attributes, and sets the <b>text</b> and <b>tail</b> attributes\r | |
| 407 | # to None.\r | |
| 408 | \r | |
| 409 | def clear(self):\r | |
| 410 | self.attrib.clear()\r | |
| 411 | self._children = []\r | |
| 412 | self.text = self.tail = None\r | |
| 413 | \r | |
| 414 | ##\r | |
| 415 | # Gets an element attribute. Equivalent to <b>attrib.get</b>, but\r | |
| 416 | # some implementations may handle this a bit more efficiently.\r | |
| 417 | #\r | |
| 418 | # @param key What attribute to look for.\r | |
| 419 | # @param default What to return if the attribute was not found.\r | |
| 420 | # @return The attribute value, or the default value, if the\r | |
| 421 | # attribute was not found.\r | |
| 422 | # @defreturn string or None\r | |
| 423 | \r | |
| 424 | def get(self, key, default=None):\r | |
| 425 | return self.attrib.get(key, default)\r | |
| 426 | \r | |
| 427 | ##\r | |
| 428 | # Sets an element attribute. Equivalent to <b>attrib[key] = value</b>,\r | |
| 429 | # but some implementations may handle this a bit more efficiently.\r | |
| 430 | #\r | |
| 431 | # @param key What attribute to set.\r | |
| 432 | # @param value The attribute value.\r | |
| 433 | \r | |
| 434 | def set(self, key, value):\r | |
| 435 | self.attrib[key] = value\r | |
| 436 | \r | |
| 437 | ##\r | |
| 438 | # Gets a list of attribute names. The names are returned in an\r | |
| 439 | # arbitrary order (just like for an ordinary Python dictionary).\r | |
| 440 | # Equivalent to <b>attrib.keys()</b>.\r | |
| 441 | #\r | |
| 442 | # @return A list of element attribute names.\r | |
| 443 | # @defreturn list of strings\r | |
| 444 | \r | |
| 445 | def keys(self):\r | |
| 446 | return self.attrib.keys()\r | |
| 447 | \r | |
| 448 | ##\r | |
| 449 | # Gets element attributes, as a sequence. The attributes are\r | |
| 450 | # returned in an arbitrary order. Equivalent to <b>attrib.items()</b>.\r | |
| 451 | #\r | |
| 452 | # @return A list of (name, value) tuples for all attributes.\r | |
| 453 | # @defreturn list of (string, string) tuples\r | |
| 454 | \r | |
| 455 | def items(self):\r | |
| 456 | return self.attrib.items()\r | |
| 457 | \r | |
| 458 | ##\r | |
| 459 | # Creates a tree iterator. The iterator loops over this element\r | |
| 460 | # and all subelements, in document order, and returns all elements\r | |
| 461 | # with a matching tag.\r | |
| 462 | # <p>\r | |
| 463 | # If the tree structure is modified during iteration, new or removed\r | |
| 464 | # elements may or may not be included. To get a stable set, use the\r | |
| 465 | # list() function on the iterator, and loop over the resulting list.\r | |
| 466 | #\r | |
| 467 | # @param tag What tags to look for (default is to return all elements).\r | |
| 468 | # @return An iterator containing all the matching elements.\r | |
| 469 | # @defreturn iterator\r | |
| 470 | \r | |
| 471 | def iter(self, tag=None):\r | |
| 472 | if tag == "*":\r | |
| 473 | tag = None\r | |
| 474 | if tag is None or self.tag == tag:\r | |
| 475 | yield self\r | |
| 476 | for e in self._children:\r | |
| 477 | for e in e.iter(tag):\r | |
| 478 | yield e\r | |
| 479 | \r | |
| 480 | # compatibility\r | |
| 481 | def getiterator(self, tag=None):\r | |
| 482 | # Change for a DeprecationWarning in 1.4\r | |
| 483 | warnings.warn(\r | |
| 484 | "This method will be removed in future versions. "\r | |
| 485 | "Use 'elem.iter()' or 'list(elem.iter())' instead.",\r | |
| 486 | PendingDeprecationWarning, stacklevel=2\r | |
| 487 | )\r | |
| 488 | return list(self.iter(tag))\r | |
| 489 | \r | |
| 490 | ##\r | |
| 491 | # Creates a text iterator. The iterator loops over this element\r | |
| 492 | # and all subelements, in document order, and returns all inner\r | |
| 493 | # text.\r | |
| 494 | #\r | |
| 495 | # @return An iterator containing all inner text.\r | |
| 496 | # @defreturn iterator\r | |
| 497 | \r | |
| 498 | def itertext(self):\r | |
| 499 | tag = self.tag\r | |
| 500 | if not isinstance(tag, basestring) and tag is not None:\r | |
| 501 | return\r | |
| 502 | if self.text:\r | |
| 503 | yield self.text\r | |
| 504 | for e in self:\r | |
| 505 | for s in e.itertext():\r | |
| 506 | yield s\r | |
| 507 | if e.tail:\r | |
| 508 | yield e.tail\r | |
| 509 | \r | |
| 510 | # compatibility\r | |
| 511 | _Element = _ElementInterface = Element\r | |
| 512 | \r | |
| 513 | ##\r | |
| 514 | # Subelement factory. This function creates an element instance, and\r | |
| 515 | # appends it to an existing element.\r | |
| 516 | # <p>\r | |
| 517 | # The element name, attribute names, and attribute values can be\r | |
| 518 | # either 8-bit ASCII strings or Unicode strings.\r | |
| 519 | #\r | |
| 520 | # @param parent The parent element.\r | |
| 521 | # @param tag The subelement name.\r | |
| 522 | # @param attrib An optional dictionary, containing element attributes.\r | |
| 523 | # @param **extra Additional attributes, given as keyword arguments.\r | |
| 524 | # @return An element instance.\r | |
| 525 | # @defreturn Element\r | |
| 526 | \r | |
| 527 | def SubElement(parent, tag, attrib={}, **extra):\r | |
| 528 | attrib = attrib.copy()\r | |
| 529 | attrib.update(extra)\r | |
| 530 | element = parent.makeelement(tag, attrib)\r | |
| 531 | parent.append(element)\r | |
| 532 | return element\r | |
| 533 | \r | |
| 534 | ##\r | |
| 535 | # Comment element factory. This factory function creates a special\r | |
| 536 | # element that will be serialized as an XML comment by the standard\r | |
| 537 | # serializer.\r | |
| 538 | # <p>\r | |
| 539 | # The comment string can be either an 8-bit ASCII string or a Unicode\r | |
| 540 | # string.\r | |
| 541 | #\r | |
| 542 | # @param text A string containing the comment string.\r | |
| 543 | # @return An element instance, representing a comment.\r | |
| 544 | # @defreturn Element\r | |
| 545 | \r | |
| 546 | def Comment(text=None):\r | |
| 547 | element = Element(Comment)\r | |
| 548 | element.text = text\r | |
| 549 | return element\r | |
| 550 | \r | |
| 551 | ##\r | |
| 552 | # PI element factory. This factory function creates a special element\r | |
| 553 | # that will be serialized as an XML processing instruction by the standard\r | |
| 554 | # serializer.\r | |
| 555 | #\r | |
| 556 | # @param target A string containing the PI target.\r | |
| 557 | # @param text A string containing the PI contents, if any.\r | |
| 558 | # @return An element instance, representing a PI.\r | |
| 559 | # @defreturn Element\r | |
| 560 | \r | |
| 561 | def ProcessingInstruction(target, text=None):\r | |
| 562 | element = Element(ProcessingInstruction)\r | |
| 563 | element.text = target\r | |
| 564 | if text:\r | |
| 565 | element.text = element.text + " " + text\r | |
| 566 | return element\r | |
| 567 | \r | |
| 568 | PI = ProcessingInstruction\r | |
| 569 | \r | |
| 570 | ##\r | |
| 571 | # QName wrapper. This can be used to wrap a QName attribute value, in\r | |
| 572 | # order to get proper namespace handling on output.\r | |
| 573 | #\r | |
| 574 | # @param text A string containing the QName value, in the form {uri}local,\r | |
| 575 | # or, if the tag argument is given, the URI part of a QName.\r | |
| 576 | # @param tag Optional tag. If given, the first argument is interpreted as\r | |
| 577 | # an URI, and this argument is interpreted as a local name.\r | |
| 578 | # @return An opaque object, representing the QName.\r | |
| 579 | \r | |
| 580 | class QName(object):\r | |
| 581 | def __init__(self, text_or_uri, tag=None):\r | |
| 582 | if tag:\r | |
| 583 | text_or_uri = "{%s}%s" % (text_or_uri, tag)\r | |
| 584 | self.text = text_or_uri\r | |
| 585 | def __str__(self):\r | |
| 586 | return self.text\r | |
| 587 | def __hash__(self):\r | |
| 588 | return hash(self.text)\r | |
| 589 | def __cmp__(self, other):\r | |
| 590 | if isinstance(other, QName):\r | |
| 591 | return cmp(self.text, other.text)\r | |
| 592 | return cmp(self.text, other)\r | |
| 593 | \r | |
| 594 | # --------------------------------------------------------------------\r | |
| 595 | \r | |
| 596 | ##\r | |
| 597 | # ElementTree wrapper class. This class represents an entire element\r | |
| 598 | # hierarchy, and adds some extra support for serialization to and from\r | |
| 599 | # standard XML.\r | |
| 600 | #\r | |
| 601 | # @param element Optional root element.\r | |
| 602 | # @keyparam file Optional file handle or file name. If given, the\r | |
| 603 | # tree is initialized with the contents of this XML file.\r | |
| 604 | \r | |
| 605 | class ElementTree(object):\r | |
| 606 | \r | |
| 607 | def __init__(self, element=None, file=None):\r | |
| 608 | # assert element is None or iselement(element)\r | |
| 609 | self._root = element # first node\r | |
| 610 | if file:\r | |
| 611 | self.parse(file)\r | |
| 612 | \r | |
| 613 | ##\r | |
| 614 | # Gets the root element for this tree.\r | |
| 615 | #\r | |
| 616 | # @return An element instance.\r | |
| 617 | # @defreturn Element\r | |
| 618 | \r | |
| 619 | def getroot(self):\r | |
| 620 | return self._root\r | |
| 621 | \r | |
| 622 | ##\r | |
| 623 | # Replaces the root element for this tree. This discards the\r | |
| 624 | # current contents of the tree, and replaces it with the given\r | |
| 625 | # element. Use with care.\r | |
| 626 | #\r | |
| 627 | # @param element An element instance.\r | |
| 628 | \r | |
| 629 | def _setroot(self, element):\r | |
| 630 | # assert iselement(element)\r | |
| 631 | self._root = element\r | |
| 632 | \r | |
| 633 | ##\r | |
| 634 | # Loads an external XML document into this element tree.\r | |
| 635 | #\r | |
| 636 | # @param source A file name or file object. If a file object is\r | |
| 637 | # given, it only has to implement a <b>read(n)</b> method.\r | |
| 638 | # @keyparam parser An optional parser instance. If not given, the\r | |
| 639 | # standard {@link XMLParser} parser is used.\r | |
| 640 | # @return The document root element.\r | |
| 641 | # @defreturn Element\r | |
| 642 | # @exception ParseError If the parser fails to parse the document.\r | |
| 643 | \r | |
| 644 | def parse(self, source, parser=None):\r | |
| 645 | close_source = False\r | |
| 646 | if not hasattr(source, "read"):\r | |
| 647 | source = open(source, "rb")\r | |
| 648 | close_source = True\r | |
| 649 | try:\r | |
| 650 | if not parser:\r | |
| 651 | parser = XMLParser(target=TreeBuilder())\r | |
| 652 | while 1:\r | |
| 653 | data = source.read(65536)\r | |
| 654 | if not data:\r | |
| 655 | break\r | |
| 656 | parser.feed(data)\r | |
| 657 | self._root = parser.close()\r | |
| 658 | return self._root\r | |
| 659 | finally:\r | |
| 660 | if close_source:\r | |
| 661 | source.close()\r | |
| 662 | \r | |
| 663 | ##\r | |
| 664 | # Creates a tree iterator for the root element. The iterator loops\r | |
| 665 | # over all elements in this tree, in document order.\r | |
| 666 | #\r | |
| 667 | # @param tag What tags to look for (default is to return all elements)\r | |
| 668 | # @return An iterator.\r | |
| 669 | # @defreturn iterator\r | |
| 670 | \r | |
| 671 | def iter(self, tag=None):\r | |
| 672 | # assert self._root is not None\r | |
| 673 | return self._root.iter(tag)\r | |
| 674 | \r | |
| 675 | # compatibility\r | |
| 676 | def getiterator(self, tag=None):\r | |
| 677 | # Change for a DeprecationWarning in 1.4\r | |
| 678 | warnings.warn(\r | |
| 679 | "This method will be removed in future versions. "\r | |
| 680 | "Use 'tree.iter()' or 'list(tree.iter())' instead.",\r | |
| 681 | PendingDeprecationWarning, stacklevel=2\r | |
| 682 | )\r | |
| 683 | return list(self.iter(tag))\r | |
| 684 | \r | |
| 685 | ##\r | |
| 686 | # Same as getroot().find(path), starting at the root of the\r | |
| 687 | # tree.\r | |
| 688 | #\r | |
| 689 | # @param path What element to look for.\r | |
| 690 | # @keyparam namespaces Optional namespace prefix map.\r | |
| 691 | # @return The first matching element, or None if no element was found.\r | |
| 692 | # @defreturn Element or None\r | |
| 693 | \r | |
| 694 | def find(self, path, namespaces=None):\r | |
| 695 | # assert self._root is not None\r | |
| 696 | if path[:1] == "/":\r | |
| 697 | path = "." + path\r | |
| 698 | warnings.warn(\r | |
| 699 | "This search is broken in 1.3 and earlier, and will be "\r | |
| 700 | "fixed in a future version. If you rely on the current "\r | |
| 701 | "behaviour, change it to %r" % path,\r | |
| 702 | FutureWarning, stacklevel=2\r | |
| 703 | )\r | |
| 704 | return self._root.find(path, namespaces)\r | |
| 705 | \r | |
| 706 | ##\r | |
| 707 | # Same as getroot().findtext(path), starting at the root of the tree.\r | |
| 708 | #\r | |
| 709 | # @param path What element to look for.\r | |
| 710 | # @param default What to return if the element was not found.\r | |
| 711 | # @keyparam namespaces Optional namespace prefix map.\r | |
| 712 | # @return The text content of the first matching element, or the\r | |
| 713 | # default value no element was found. Note that if the element\r | |
| 714 | # is found, but has no text content, this method returns an\r | |
| 715 | # empty string.\r | |
| 716 | # @defreturn string\r | |
| 717 | \r | |
| 718 | def findtext(self, path, default=None, namespaces=None):\r | |
| 719 | # assert self._root is not None\r | |
| 720 | if path[:1] == "/":\r | |
| 721 | path = "." + path\r | |
| 722 | warnings.warn(\r | |
| 723 | "This search is broken in 1.3 and earlier, and will be "\r | |
| 724 | "fixed in a future version. If you rely on the current "\r | |
| 725 | "behaviour, change it to %r" % path,\r | |
| 726 | FutureWarning, stacklevel=2\r | |
| 727 | )\r | |
| 728 | return self._root.findtext(path, default, namespaces)\r | |
| 729 | \r | |
| 730 | ##\r | |
| 731 | # Same as getroot().findall(path), starting at the root of the tree.\r | |
| 732 | #\r | |
| 733 | # @param path What element to look for.\r | |
| 734 | # @keyparam namespaces Optional namespace prefix map.\r | |
| 735 | # @return A list or iterator containing all matching elements,\r | |
| 736 | # in document order.\r | |
| 737 | # @defreturn list of Element instances\r | |
| 738 | \r | |
| 739 | def findall(self, path, namespaces=None):\r | |
| 740 | # assert self._root is not None\r | |
| 741 | if path[:1] == "/":\r | |
| 742 | path = "." + path\r | |
| 743 | warnings.warn(\r | |
| 744 | "This search is broken in 1.3 and earlier, and will be "\r | |
| 745 | "fixed in a future version. If you rely on the current "\r | |
| 746 | "behaviour, change it to %r" % path,\r | |
| 747 | FutureWarning, stacklevel=2\r | |
| 748 | )\r | |
| 749 | return self._root.findall(path, namespaces)\r | |
| 750 | \r | |
| 751 | ##\r | |
| 752 | # Finds all matching subelements, by tag name or path.\r | |
| 753 | # Same as getroot().iterfind(path).\r | |
| 754 | #\r | |
| 755 | # @param path What element to look for.\r | |
| 756 | # @keyparam namespaces Optional namespace prefix map.\r | |
| 757 | # @return An iterator or sequence containing all matching elements,\r | |
| 758 | # in document order.\r | |
| 759 | # @defreturn a generated sequence of Element instances\r | |
| 760 | \r | |
| 761 | def iterfind(self, path, namespaces=None):\r | |
| 762 | # assert self._root is not None\r | |
| 763 | if path[:1] == "/":\r | |
| 764 | path = "." + path\r | |
| 765 | warnings.warn(\r | |
| 766 | "This search is broken in 1.3 and earlier, and will be "\r | |
| 767 | "fixed in a future version. If you rely on the current "\r | |
| 768 | "behaviour, change it to %r" % path,\r | |
| 769 | FutureWarning, stacklevel=2\r | |
| 770 | )\r | |
| 771 | return self._root.iterfind(path, namespaces)\r | |
| 772 | \r | |
| 773 | ##\r | |
| 774 | # Writes the element tree to a file, as XML.\r | |
| 775 | #\r | |
| 776 | # @def write(file, **options)\r | |
| 777 | # @param file A file name, or a file object opened for writing.\r | |
| 778 | # @param **options Options, given as keyword arguments.\r | |
| 779 | # @keyparam encoding Optional output encoding (default is US-ASCII).\r | |
| 780 | # @keyparam xml_declaration Controls if an XML declaration should\r | |
| 781 | # be added to the file. Use False for never, True for always,\r | |
| 782 | # None for only if not US-ASCII or UTF-8. None is default.\r | |
| 783 | # @keyparam default_namespace Sets the default XML namespace (for "xmlns").\r | |
| 784 | # @keyparam method Optional output method ("xml", "html", "text" or\r | |
| 785 | # "c14n"; default is "xml").\r | |
| 786 | \r | |
| 787 | def write(self, file_or_filename,\r | |
| 788 | # keyword arguments\r | |
| 789 | encoding=None,\r | |
| 790 | xml_declaration=None,\r | |
| 791 | default_namespace=None,\r | |
| 792 | method=None):\r | |
| 793 | # assert self._root is not None\r | |
| 794 | if not method:\r | |
| 795 | method = "xml"\r | |
| 796 | elif method not in _serialize:\r | |
| 797 | # FIXME: raise an ImportError for c14n if ElementC14N is missing?\r | |
| 798 | raise ValueError("unknown method %r" % method)\r | |
| 799 | if hasattr(file_or_filename, "write"):\r | |
| 800 | file = file_or_filename\r | |
| 801 | else:\r | |
| 802 | file = open(file_or_filename, "wb")\r | |
| 803 | write = file.write\r | |
| 804 | if not encoding:\r | |
| 805 | if method == "c14n":\r | |
| 806 | encoding = "utf-8"\r | |
| 807 | else:\r | |
| 808 | encoding = "us-ascii"\r | |
| 809 | elif xml_declaration or (xml_declaration is None and\r | |
| 810 | encoding not in ("utf-8", "us-ascii")):\r | |
| 811 | if method == "xml":\r | |
| 812 | write("<?xml version='1.0' encoding='%s'?>\n" % encoding)\r | |
| 813 | if method == "text":\r | |
| 814 | _serialize_text(write, self._root, encoding)\r | |
| 815 | else:\r | |
| 816 | qnames, namespaces = _namespaces(\r | |
| 817 | self._root, encoding, default_namespace\r | |
| 818 | )\r | |
| 819 | serialize = _serialize[method]\r | |
| 820 | serialize(write, self._root, encoding, qnames, namespaces)\r | |
| 821 | if file_or_filename is not file:\r | |
| 822 | file.close()\r | |
| 823 | \r | |
| 824 | def write_c14n(self, file):\r | |
| 825 | # lxml.etree compatibility. use output method instead\r | |
| 826 | return self.write(file, method="c14n")\r | |
| 827 | \r | |
| 828 | # --------------------------------------------------------------------\r | |
| 829 | # serialization support\r | |
| 830 | \r | |
| 831 | def _namespaces(elem, encoding, default_namespace=None):\r | |
| 832 | # identify namespaces used in this tree\r | |
| 833 | \r | |
| 834 | # maps qnames to *encoded* prefix:local names\r | |
| 835 | qnames = {None: None}\r | |
| 836 | \r | |
| 837 | # maps uri:s to prefixes\r | |
| 838 | namespaces = {}\r | |
| 839 | if default_namespace:\r | |
| 840 | namespaces[default_namespace] = ""\r | |
| 841 | \r | |
| 842 | def encode(text):\r | |
| 843 | return text.encode(encoding)\r | |
| 844 | \r | |
| 845 | def add_qname(qname):\r | |
| 846 | # calculate serialized qname representation\r | |
| 847 | try:\r | |
| 848 | if qname[:1] == "{":\r | |
| 849 | uri, tag = qname[1:].rsplit("}", 1)\r | |
| 850 | prefix = namespaces.get(uri)\r | |
| 851 | if prefix is None:\r | |
| 852 | prefix = _namespace_map.get(uri)\r | |
| 853 | if prefix is None:\r | |
| 854 | prefix = "ns%d" % len(namespaces)\r | |
| 855 | if prefix != "xml":\r | |
| 856 | namespaces[uri] = prefix\r | |
| 857 | if prefix:\r | |
| 858 | qnames[qname] = encode("%s:%s" % (prefix, tag))\r | |
| 859 | else:\r | |
| 860 | qnames[qname] = encode(tag) # default element\r | |
| 861 | else:\r | |
| 862 | if default_namespace:\r | |
| 863 | # FIXME: can this be handled in XML 1.0?\r | |
| 864 | raise ValueError(\r | |
| 865 | "cannot use non-qualified names with "\r | |
| 866 | "default_namespace option"\r | |
| 867 | )\r | |
| 868 | qnames[qname] = encode(qname)\r | |
| 869 | except TypeError:\r | |
| 870 | _raise_serialization_error(qname)\r | |
| 871 | \r | |
| 872 | # populate qname and namespaces table\r | |
| 873 | try:\r | |
| 874 | iterate = elem.iter\r | |
| 875 | except AttributeError:\r | |
| 876 | iterate = elem.getiterator # cET compatibility\r | |
| 877 | for elem in iterate():\r | |
| 878 | tag = elem.tag\r | |
| 879 | if isinstance(tag, QName):\r | |
| 880 | if tag.text not in qnames:\r | |
| 881 | add_qname(tag.text)\r | |
| 882 | elif isinstance(tag, basestring):\r | |
| 883 | if tag not in qnames:\r | |
| 884 | add_qname(tag)\r | |
| 885 | elif tag is not None and tag is not Comment and tag is not PI:\r | |
| 886 | _raise_serialization_error(tag)\r | |
| 887 | for key, value in elem.items():\r | |
| 888 | if isinstance(key, QName):\r | |
| 889 | key = key.text\r | |
| 890 | if key not in qnames:\r | |
| 891 | add_qname(key)\r | |
| 892 | if isinstance(value, QName) and value.text not in qnames:\r | |
| 893 | add_qname(value.text)\r | |
| 894 | text = elem.text\r | |
| 895 | if isinstance(text, QName) and text.text not in qnames:\r | |
| 896 | add_qname(text.text)\r | |
| 897 | return qnames, namespaces\r | |
| 898 | \r | |
| 899 | def _serialize_xml(write, elem, encoding, qnames, namespaces):\r | |
| 900 | tag = elem.tag\r | |
| 901 | text = elem.text\r | |
| 902 | if tag is Comment:\r | |
| 903 | write("<!--%s-->" % _encode(text, encoding))\r | |
| 904 | elif tag is ProcessingInstruction:\r | |
| 905 | write("<?%s?>" % _encode(text, encoding))\r | |
| 906 | else:\r | |
| 907 | tag = qnames[tag]\r | |
| 908 | if tag is None:\r | |
| 909 | if text:\r | |
| 910 | write(_escape_cdata(text, encoding))\r | |
| 911 | for e in elem:\r | |
| 912 | _serialize_xml(write, e, encoding, qnames, None)\r | |
| 913 | else:\r | |
| 914 | write("<" + tag)\r | |
| 915 | items = elem.items()\r | |
| 916 | if items or namespaces:\r | |
| 917 | if namespaces:\r | |
| 918 | for v, k in sorted(namespaces.items(),\r | |
| 919 | key=lambda x: x[1]): # sort on prefix\r | |
| 920 | if k:\r | |
| 921 | k = ":" + k\r | |
| 922 | write(" xmlns%s=\"%s\"" % (\r | |
| 923 | k.encode(encoding),\r | |
| 924 | _escape_attrib(v, encoding)\r | |
| 925 | ))\r | |
| 926 | for k, v in sorted(items): # lexical order\r | |
| 927 | if isinstance(k, QName):\r | |
| 928 | k = k.text\r | |
| 929 | if isinstance(v, QName):\r | |
| 930 | v = qnames[v.text]\r | |
| 931 | else:\r | |
| 932 | v = _escape_attrib(v, encoding)\r | |
| 933 | write(" %s=\"%s\"" % (qnames[k], v))\r | |
| 934 | if text or len(elem):\r | |
| 935 | write(">")\r | |
| 936 | if text:\r | |
| 937 | write(_escape_cdata(text, encoding))\r | |
| 938 | for e in elem:\r | |
| 939 | _serialize_xml(write, e, encoding, qnames, None)\r | |
| 940 | write("</" + tag + ">")\r | |
| 941 | else:\r | |
| 942 | write(" />")\r | |
| 943 | if elem.tail:\r | |
| 944 | write(_escape_cdata(elem.tail, encoding))\r | |
| 945 | \r | |
| 946 | HTML_EMPTY = ("area", "base", "basefont", "br", "col", "frame", "hr",\r | |
| 947 | "img", "input", "isindex", "link", "meta", "param")\r | |
| 948 | \r | |
| 949 | try:\r | |
| 950 | HTML_EMPTY = set(HTML_EMPTY)\r | |
| 951 | except NameError:\r | |
| 952 | pass\r | |
| 953 | \r | |
| 954 | def _serialize_html(write, elem, encoding, qnames, namespaces):\r | |
| 955 | tag = elem.tag\r | |
| 956 | text = elem.text\r | |
| 957 | if tag is Comment:\r | |
| 958 | write("<!--%s-->" % _escape_cdata(text, encoding))\r | |
| 959 | elif tag is ProcessingInstruction:\r | |
| 960 | write("<?%s?>" % _escape_cdata(text, encoding))\r | |
| 961 | else:\r | |
| 962 | tag = qnames[tag]\r | |
| 963 | if tag is None:\r | |
| 964 | if text:\r | |
| 965 | write(_escape_cdata(text, encoding))\r | |
| 966 | for e in elem:\r | |
| 967 | _serialize_html(write, e, encoding, qnames, None)\r | |
| 968 | else:\r | |
| 969 | write("<" + tag)\r | |
| 970 | items = elem.items()\r | |
| 971 | if items or namespaces:\r | |
| 972 | if namespaces:\r | |
| 973 | for v, k in sorted(namespaces.items(),\r | |
| 974 | key=lambda x: x[1]): # sort on prefix\r | |
| 975 | if k:\r | |
| 976 | k = ":" + k\r | |
| 977 | write(" xmlns%s=\"%s\"" % (\r | |
| 978 | k.encode(encoding),\r | |
| 979 | _escape_attrib(v, encoding)\r | |
| 980 | ))\r | |
| 981 | for k, v in sorted(items): # lexical order\r | |
| 982 | if isinstance(k, QName):\r | |
| 983 | k = k.text\r | |
| 984 | if isinstance(v, QName):\r | |
| 985 | v = qnames[v.text]\r | |
| 986 | else:\r | |
| 987 | v = _escape_attrib_html(v, encoding)\r | |
| 988 | # FIXME: handle boolean attributes\r | |
| 989 | write(" %s=\"%s\"" % (qnames[k], v))\r | |
| 990 | write(">")\r | |
| 991 | ltag = tag.lower()\r | |
| 992 | if text:\r | |
| 993 | if ltag == "script" or ltag == "style":\r | |
| 994 | write(_encode(text, encoding))\r | |
| 995 | else:\r | |
| 996 | write(_escape_cdata(text, encoding))\r | |
| 997 | for e in elem:\r | |
| 998 | _serialize_html(write, e, encoding, qnames, None)\r | |
| 999 | if ltag not in HTML_EMPTY:\r | |
| 1000 | write("</" + tag + ">")\r | |
| 1001 | if elem.tail:\r | |
| 1002 | write(_escape_cdata(elem.tail, encoding))\r | |
| 1003 | \r | |
| 1004 | def _serialize_text(write, elem, encoding):\r | |
| 1005 | for part in elem.itertext():\r | |
| 1006 | write(part.encode(encoding))\r | |
| 1007 | if elem.tail:\r | |
| 1008 | write(elem.tail.encode(encoding))\r | |
| 1009 | \r | |
| 1010 | _serialize = {\r | |
| 1011 | "xml": _serialize_xml,\r | |
| 1012 | "html": _serialize_html,\r | |
| 1013 | "text": _serialize_text,\r | |
| 1014 | # this optional method is imported at the end of the module\r | |
| 1015 | # "c14n": _serialize_c14n,\r | |
| 1016 | }\r | |
| 1017 | \r | |
| 1018 | ##\r | |
| 1019 | # Registers a namespace prefix. The registry is global, and any\r | |
| 1020 | # existing mapping for either the given prefix or the namespace URI\r | |
| 1021 | # will be removed.\r | |
| 1022 | #\r | |
| 1023 | # @param prefix Namespace prefix.\r | |
| 1024 | # @param uri Namespace uri. Tags and attributes in this namespace\r | |
| 1025 | # will be serialized with the given prefix, if at all possible.\r | |
| 1026 | # @exception ValueError If the prefix is reserved, or is otherwise\r | |
| 1027 | # invalid.\r | |
| 1028 | \r | |
| 1029 | def register_namespace(prefix, uri):\r | |
| 1030 | if re.match("ns\d+$", prefix):\r | |
| 1031 | raise ValueError("Prefix format reserved for internal use")\r | |
| 1032 | for k, v in _namespace_map.items():\r | |
| 1033 | if k == uri or v == prefix:\r | |
| 1034 | del _namespace_map[k]\r | |
| 1035 | _namespace_map[uri] = prefix\r | |
| 1036 | \r | |
| 1037 | _namespace_map = {\r | |
| 1038 | # "well-known" namespace prefixes\r | |
| 1039 | "http://www.w3.org/XML/1998/namespace": "xml",\r | |
| 1040 | "http://www.w3.org/1999/xhtml": "html",\r | |
| 1041 | "http://www.w3.org/1999/02/22-rdf-syntax-ns#": "rdf",\r | |
| 1042 | "http://schemas.xmlsoap.org/wsdl/": "wsdl",\r | |
| 1043 | # xml schema\r | |
| 1044 | "http://www.w3.org/2001/XMLSchema": "xs",\r | |
| 1045 | "http://www.w3.org/2001/XMLSchema-instance": "xsi",\r | |
| 1046 | # dublin core\r | |
| 1047 | "http://purl.org/dc/elements/1.1/": "dc",\r | |
| 1048 | }\r | |
| 1049 | \r | |
| 1050 | def _raise_serialization_error(text):\r | |
| 1051 | raise TypeError(\r | |
| 1052 | "cannot serialize %r (type %s)" % (text, type(text).__name__)\r | |
| 1053 | )\r | |
| 1054 | \r | |
| 1055 | def _encode(text, encoding):\r | |
| 1056 | try:\r | |
| 1057 | return text.encode(encoding, "xmlcharrefreplace")\r | |
| 1058 | except (TypeError, AttributeError):\r | |
| 1059 | _raise_serialization_error(text)\r | |
| 1060 | \r | |
| 1061 | def _escape_cdata(text, encoding):\r | |
| 1062 | # escape character data\r | |
| 1063 | try:\r | |
| 1064 | # it's worth avoiding do-nothing calls for strings that are\r | |
| 1065 | # shorter than 500 character, or so. assume that's, by far,\r | |
| 1066 | # the most common case in most applications.\r | |
| 1067 | if "&" in text:\r | |
| 1068 | text = text.replace("&", "&")\r | |
| 1069 | if "<" in text:\r | |
| 1070 | text = text.replace("<", "<")\r | |
| 1071 | if ">" in text:\r | |
| 1072 | text = text.replace(">", ">")\r | |
| 1073 | return text.encode(encoding, "xmlcharrefreplace")\r | |
| 1074 | except (TypeError, AttributeError):\r | |
| 1075 | _raise_serialization_error(text)\r | |
| 1076 | \r | |
| 1077 | def _escape_attrib(text, encoding):\r | |
| 1078 | # escape attribute value\r | |
| 1079 | try:\r | |
| 1080 | if "&" in text:\r | |
| 1081 | text = text.replace("&", "&")\r | |
| 1082 | if "<" in text:\r | |
| 1083 | text = text.replace("<", "<")\r | |
| 1084 | if ">" in text:\r | |
| 1085 | text = text.replace(">", ">")\r | |
| 1086 | if "\"" in text:\r | |
| 1087 | text = text.replace("\"", """)\r | |
| 1088 | if "\n" in text:\r | |
| 1089 | text = text.replace("\n", " ")\r | |
| 1090 | return text.encode(encoding, "xmlcharrefreplace")\r | |
| 1091 | except (TypeError, AttributeError):\r | |
| 1092 | _raise_serialization_error(text)\r | |
| 1093 | \r | |
| 1094 | def _escape_attrib_html(text, encoding):\r | |
| 1095 | # escape attribute value\r | |
| 1096 | try:\r | |
| 1097 | if "&" in text:\r | |
| 1098 | text = text.replace("&", "&")\r | |
| 1099 | if ">" in text:\r | |
| 1100 | text = text.replace(">", ">")\r | |
| 1101 | if "\"" in text:\r | |
| 1102 | text = text.replace("\"", """)\r | |
| 1103 | return text.encode(encoding, "xmlcharrefreplace")\r | |
| 1104 | except (TypeError, AttributeError):\r | |
| 1105 | _raise_serialization_error(text)\r | |
| 1106 | \r | |
| 1107 | # --------------------------------------------------------------------\r | |
| 1108 | \r | |
| 1109 | ##\r | |
| 1110 | # Generates a string representation of an XML element, including all\r | |
| 1111 | # subelements.\r | |
| 1112 | #\r | |
| 1113 | # @param element An Element instance.\r | |
| 1114 | # @keyparam encoding Optional output encoding (default is US-ASCII).\r | |
| 1115 | # @keyparam method Optional output method ("xml", "html", "text" or\r | |
| 1116 | # "c14n"; default is "xml").\r | |
| 1117 | # @return An encoded string containing the XML data.\r | |
| 1118 | # @defreturn string\r | |
| 1119 | \r | |
| 1120 | def tostring(element, encoding=None, method=None):\r | |
| 1121 | class dummy:\r | |
| 1122 | pass\r | |
| 1123 | data = []\r | |
| 1124 | file = dummy()\r | |
| 1125 | file.write = data.append\r | |
| 1126 | ElementTree(element).write(file, encoding, method=method)\r | |
| 1127 | return "".join(data)\r | |
| 1128 | \r | |
| 1129 | ##\r | |
| 1130 | # Generates a string representation of an XML element, including all\r | |
| 1131 | # subelements. The string is returned as a sequence of string fragments.\r | |
| 1132 | #\r | |
| 1133 | # @param element An Element instance.\r | |
| 1134 | # @keyparam encoding Optional output encoding (default is US-ASCII).\r | |
| 1135 | # @keyparam method Optional output method ("xml", "html", "text" or\r | |
| 1136 | # "c14n"; default is "xml").\r | |
| 1137 | # @return A sequence object containing the XML data.\r | |
| 1138 | # @defreturn sequence\r | |
| 1139 | # @since 1.3\r | |
| 1140 | \r | |
| 1141 | def tostringlist(element, encoding=None, method=None):\r | |
| 1142 | class dummy:\r | |
| 1143 | pass\r | |
| 1144 | data = []\r | |
| 1145 | file = dummy()\r | |
| 1146 | file.write = data.append\r | |
| 1147 | ElementTree(element).write(file, encoding, method=method)\r | |
| 1148 | # FIXME: merge small fragments into larger parts\r | |
| 1149 | return data\r | |
| 1150 | \r | |
| 1151 | ##\r | |
| 1152 | # Writes an element tree or element structure to sys.stdout. This\r | |
| 1153 | # function should be used for debugging only.\r | |
| 1154 | # <p>\r | |
| 1155 | # The exact output format is implementation dependent. In this\r | |
| 1156 | # version, it's written as an ordinary XML file.\r | |
| 1157 | #\r | |
| 1158 | # @param elem An element tree or an individual element.\r | |
| 1159 | \r | |
| 1160 | def dump(elem):\r | |
| 1161 | # debugging\r | |
| 1162 | if not isinstance(elem, ElementTree):\r | |
| 1163 | elem = ElementTree(elem)\r | |
| 1164 | elem.write(sys.stdout)\r | |
| 1165 | tail = elem.getroot().tail\r | |
| 1166 | if not tail or tail[-1] != "\n":\r | |
| 1167 | sys.stdout.write("\n")\r | |
| 1168 | \r | |
| 1169 | # --------------------------------------------------------------------\r | |
| 1170 | # parsing\r | |
| 1171 | \r | |
| 1172 | ##\r | |
| 1173 | # Parses an XML document into an element tree.\r | |
| 1174 | #\r | |
| 1175 | # @param source A filename or file object containing XML data.\r | |
| 1176 | # @param parser An optional parser instance. If not given, the\r | |
| 1177 | # standard {@link XMLParser} parser is used.\r | |
| 1178 | # @return An ElementTree instance\r | |
| 1179 | \r | |
| 1180 | def parse(source, parser=None):\r | |
| 1181 | tree = ElementTree()\r | |
| 1182 | tree.parse(source, parser)\r | |
| 1183 | return tree\r | |
| 1184 | \r | |
| 1185 | ##\r | |
| 1186 | # Parses an XML document into an element tree incrementally, and reports\r | |
| 1187 | # what's going on to the user.\r | |
| 1188 | #\r | |
| 1189 | # @param source A filename or file object containing XML data.\r | |
| 1190 | # @param events A list of events to report back. If omitted, only "end"\r | |
| 1191 | # events are reported.\r | |
| 1192 | # @param parser An optional parser instance. If not given, the\r | |
| 1193 | # standard {@link XMLParser} parser is used.\r | |
| 1194 | # @return A (event, elem) iterator.\r | |
| 1195 | \r | |
| 1196 | def iterparse(source, events=None, parser=None):\r | |
| 1197 | close_source = False\r | |
| 1198 | if not hasattr(source, "read"):\r | |
| 1199 | source = open(source, "rb")\r | |
| 1200 | close_source = True\r | |
| 1201 | if not parser:\r | |
| 1202 | parser = XMLParser(target=TreeBuilder())\r | |
| 1203 | return _IterParseIterator(source, events, parser, close_source)\r | |
| 1204 | \r | |
| 1205 | class _IterParseIterator(object):\r | |
| 1206 | \r | |
| 1207 | def __init__(self, source, events, parser, close_source=False):\r | |
| 1208 | self._file = source\r | |
| 1209 | self._close_file = close_source\r | |
| 1210 | self._events = []\r | |
| 1211 | self._index = 0\r | |
| 1212 | self._error = None\r | |
| 1213 | self.root = self._root = None\r | |
| 1214 | self._parser = parser\r | |
| 1215 | # wire up the parser for event reporting\r | |
| 1216 | parser = self._parser._parser\r | |
| 1217 | append = self._events.append\r | |
| 1218 | if events is None:\r | |
| 1219 | events = ["end"]\r | |
| 1220 | for event in events:\r | |
| 1221 | if event == "start":\r | |
| 1222 | try:\r | |
| 1223 | parser.ordered_attributes = 1\r | |
| 1224 | parser.specified_attributes = 1\r | |
| 1225 | def handler(tag, attrib_in, event=event, append=append,\r | |
| 1226 | start=self._parser._start_list):\r | |
| 1227 | append((event, start(tag, attrib_in)))\r | |
| 1228 | parser.StartElementHandler = handler\r | |
| 1229 | except AttributeError:\r | |
| 1230 | def handler(tag, attrib_in, event=event, append=append,\r | |
| 1231 | start=self._parser._start):\r | |
| 1232 | append((event, start(tag, attrib_in)))\r | |
| 1233 | parser.StartElementHandler = handler\r | |
| 1234 | elif event == "end":\r | |
| 1235 | def handler(tag, event=event, append=append,\r | |
| 1236 | end=self._parser._end):\r | |
| 1237 | append((event, end(tag)))\r | |
| 1238 | parser.EndElementHandler = handler\r | |
| 1239 | elif event == "start-ns":\r | |
| 1240 | def handler(prefix, uri, event=event, append=append):\r | |
| 1241 | try:\r | |
| 1242 | uri = (uri or "").encode("ascii")\r | |
| 1243 | except UnicodeError:\r | |
| 1244 | pass\r | |
| 1245 | append((event, (prefix or "", uri or "")))\r | |
| 1246 | parser.StartNamespaceDeclHandler = handler\r | |
| 1247 | elif event == "end-ns":\r | |
| 1248 | def handler(prefix, event=event, append=append):\r | |
| 1249 | append((event, None))\r | |
| 1250 | parser.EndNamespaceDeclHandler = handler\r | |
| 1251 | else:\r | |
| 1252 | raise ValueError("unknown event %r" % event)\r | |
| 1253 | \r | |
| 1254 | def next(self):\r | |
| 1255 | while 1:\r | |
| 1256 | try:\r | |
| 1257 | item = self._events[self._index]\r | |
| 1258 | self._index += 1\r | |
| 1259 | return item\r | |
| 1260 | except IndexError:\r | |
| 1261 | pass\r | |
| 1262 | if self._error:\r | |
| 1263 | e = self._error\r | |
| 1264 | self._error = None\r | |
| 1265 | raise e\r | |
| 1266 | if self._parser is None:\r | |
| 1267 | self.root = self._root\r | |
| 1268 | if self._close_file:\r | |
| 1269 | self._file.close()\r | |
| 1270 | raise StopIteration\r | |
| 1271 | # load event buffer\r | |
| 1272 | del self._events[:]\r | |
| 1273 | self._index = 0\r | |
| 1274 | data = self._file.read(16384)\r | |
| 1275 | if data:\r | |
| 1276 | try:\r | |
| 1277 | self._parser.feed(data)\r | |
| 1278 | except SyntaxError as exc:\r | |
| 1279 | self._error = exc\r | |
| 1280 | else:\r | |
| 1281 | self._root = self._parser.close()\r | |
| 1282 | self._parser = None\r | |
| 1283 | \r | |
| 1284 | def __iter__(self):\r | |
| 1285 | return self\r | |
| 1286 | \r | |
| 1287 | ##\r | |
| 1288 | # Parses an XML document from a string constant. This function can\r | |
| 1289 | # be used to embed "XML literals" in Python code.\r | |
| 1290 | #\r | |
| 1291 | # @param source A string containing XML data.\r | |
| 1292 | # @param parser An optional parser instance. If not given, the\r | |
| 1293 | # standard {@link XMLParser} parser is used.\r | |
| 1294 | # @return An Element instance.\r | |
| 1295 | # @defreturn Element\r | |
| 1296 | \r | |
| 1297 | def XML(text, parser=None):\r | |
| 1298 | if not parser:\r | |
| 1299 | parser = XMLParser(target=TreeBuilder())\r | |
| 1300 | parser.feed(text)\r | |
| 1301 | return parser.close()\r | |
| 1302 | \r | |
| 1303 | ##\r | |
| 1304 | # Parses an XML document from a string constant, and also returns\r | |
| 1305 | # a dictionary which maps from element id:s to elements.\r | |
| 1306 | #\r | |
| 1307 | # @param source A string containing XML data.\r | |
| 1308 | # @param parser An optional parser instance. If not given, the\r | |
| 1309 | # standard {@link XMLParser} parser is used.\r | |
| 1310 | # @return A tuple containing an Element instance and a dictionary.\r | |
| 1311 | # @defreturn (Element, dictionary)\r | |
| 1312 | \r | |
| 1313 | def XMLID(text, parser=None):\r | |
| 1314 | if not parser:\r | |
| 1315 | parser = XMLParser(target=TreeBuilder())\r | |
| 1316 | parser.feed(text)\r | |
| 1317 | tree = parser.close()\r | |
| 1318 | ids = {}\r | |
| 1319 | for elem in tree.iter():\r | |
| 1320 | id = elem.get("id")\r | |
| 1321 | if id:\r | |
| 1322 | ids[id] = elem\r | |
| 1323 | return tree, ids\r | |
| 1324 | \r | |
| 1325 | ##\r | |
| 1326 | # Parses an XML document from a string constant. Same as {@link #XML}.\r | |
| 1327 | #\r | |
| 1328 | # @def fromstring(text)\r | |
| 1329 | # @param source A string containing XML data.\r | |
| 1330 | # @return An Element instance.\r | |
| 1331 | # @defreturn Element\r | |
| 1332 | \r | |
| 1333 | fromstring = XML\r | |
| 1334 | \r | |
| 1335 | ##\r | |
| 1336 | # Parses an XML document from a sequence of string fragments.\r | |
| 1337 | #\r | |
| 1338 | # @param sequence A list or other sequence containing XML data fragments.\r | |
| 1339 | # @param parser An optional parser instance. If not given, the\r | |
| 1340 | # standard {@link XMLParser} parser is used.\r | |
| 1341 | # @return An Element instance.\r | |
| 1342 | # @defreturn Element\r | |
| 1343 | # @since 1.3\r | |
| 1344 | \r | |
| 1345 | def fromstringlist(sequence, parser=None):\r | |
| 1346 | if not parser:\r | |
| 1347 | parser = XMLParser(target=TreeBuilder())\r | |
| 1348 | for text in sequence:\r | |
| 1349 | parser.feed(text)\r | |
| 1350 | return parser.close()\r | |
| 1351 | \r | |
| 1352 | # --------------------------------------------------------------------\r | |
| 1353 | \r | |
| 1354 | ##\r | |
| 1355 | # Generic element structure builder. This builder converts a sequence\r | |
| 1356 | # of {@link #TreeBuilder.start}, {@link #TreeBuilder.data}, and {@link\r | |
| 1357 | # #TreeBuilder.end} method calls to a well-formed element structure.\r | |
| 1358 | # <p>\r | |
| 1359 | # You can use this class to build an element structure using a custom XML\r | |
| 1360 | # parser, or a parser for some other XML-like format.\r | |
| 1361 | #\r | |
| 1362 | # @param element_factory Optional element factory. This factory\r | |
| 1363 | # is called to create new Element instances, as necessary.\r | |
| 1364 | \r | |
| 1365 | class TreeBuilder(object):\r | |
| 1366 | \r | |
| 1367 | def __init__(self, element_factory=None):\r | |
| 1368 | self._data = [] # data collector\r | |
| 1369 | self._elem = [] # element stack\r | |
| 1370 | self._last = None # last element\r | |
| 1371 | self._tail = None # true if we're after an end tag\r | |
| 1372 | if element_factory is None:\r | |
| 1373 | element_factory = Element\r | |
| 1374 | self._factory = element_factory\r | |
| 1375 | \r | |
| 1376 | ##\r | |
| 1377 | # Flushes the builder buffers, and returns the toplevel document\r | |
| 1378 | # element.\r | |
| 1379 | #\r | |
| 1380 | # @return An Element instance.\r | |
| 1381 | # @defreturn Element\r | |
| 1382 | \r | |
| 1383 | def close(self):\r | |
| 1384 | assert len(self._elem) == 0, "missing end tags"\r | |
| 1385 | assert self._last is not None, "missing toplevel element"\r | |
| 1386 | return self._last\r | |
| 1387 | \r | |
| 1388 | def _flush(self):\r | |
| 1389 | if self._data:\r | |
| 1390 | if self._last is not None:\r | |
| 1391 | text = "".join(self._data)\r | |
| 1392 | if self._tail:\r | |
| 1393 | assert self._last.tail is None, "internal error (tail)"\r | |
| 1394 | self._last.tail = text\r | |
| 1395 | else:\r | |
| 1396 | assert self._last.text is None, "internal error (text)"\r | |
| 1397 | self._last.text = text\r | |
| 1398 | self._data = []\r | |
| 1399 | \r | |
| 1400 | ##\r | |
| 1401 | # Adds text to the current element.\r | |
| 1402 | #\r | |
| 1403 | # @param data A string. This should be either an 8-bit string\r | |
| 1404 | # containing ASCII text, or a Unicode string.\r | |
| 1405 | \r | |
| 1406 | def data(self, data):\r | |
| 1407 | self._data.append(data)\r | |
| 1408 | \r | |
| 1409 | ##\r | |
| 1410 | # Opens a new element.\r | |
| 1411 | #\r | |
| 1412 | # @param tag The element name.\r | |
| 1413 | # @param attrib A dictionary containing element attributes.\r | |
| 1414 | # @return The opened element.\r | |
| 1415 | # @defreturn Element\r | |
| 1416 | \r | |
| 1417 | def start(self, tag, attrs):\r | |
| 1418 | self._flush()\r | |
| 1419 | self._last = elem = self._factory(tag, attrs)\r | |
| 1420 | if self._elem:\r | |
| 1421 | self._elem[-1].append(elem)\r | |
| 1422 | self._elem.append(elem)\r | |
| 1423 | self._tail = 0\r | |
| 1424 | return elem\r | |
| 1425 | \r | |
| 1426 | ##\r | |
| 1427 | # Closes the current element.\r | |
| 1428 | #\r | |
| 1429 | # @param tag The element name.\r | |
| 1430 | # @return The closed element.\r | |
| 1431 | # @defreturn Element\r | |
| 1432 | \r | |
| 1433 | def end(self, tag):\r | |
| 1434 | self._flush()\r | |
| 1435 | self._last = self._elem.pop()\r | |
| 1436 | assert self._last.tag == tag,\\r | |
| 1437 | "end tag mismatch (expected %s, got %s)" % (\r | |
| 1438 | self._last.tag, tag)\r | |
| 1439 | self._tail = 1\r | |
| 1440 | return self._last\r | |
| 1441 | \r | |
| 1442 | ##\r | |
| 1443 | # Element structure builder for XML source data, based on the\r | |
| 1444 | # <b>expat</b> parser.\r | |
| 1445 | #\r | |
| 1446 | # @keyparam target Target object. If omitted, the builder uses an\r | |
| 1447 | # instance of the standard {@link #TreeBuilder} class.\r | |
| 1448 | # @keyparam html Predefine HTML entities. This flag is not supported\r | |
| 1449 | # by the current implementation.\r | |
| 1450 | # @keyparam encoding Optional encoding. If given, the value overrides\r | |
| 1451 | # the encoding specified in the XML file.\r | |
| 1452 | # @see #ElementTree\r | |
| 1453 | # @see #TreeBuilder\r | |
| 1454 | \r | |
| 1455 | class XMLParser(object):\r | |
| 1456 | \r | |
| 1457 | def __init__(self, html=0, target=None, encoding=None):\r | |
| 1458 | try:\r | |
| 1459 | from xml.parsers import expat\r | |
| 1460 | except ImportError:\r | |
| 1461 | try:\r | |
| 1462 | import pyexpat as expat\r | |
| 1463 | except ImportError:\r | |
| 1464 | raise ImportError(\r | |
| 1465 | "No module named expat; use SimpleXMLTreeBuilder instead"\r | |
| 1466 | )\r | |
| 1467 | parser = expat.ParserCreate(encoding, "}")\r | |
| 1468 | if target is None:\r | |
| 1469 | target = TreeBuilder()\r | |
| 1470 | # underscored names are provided for compatibility only\r | |
| 1471 | self.parser = self._parser = parser\r | |
| 1472 | self.target = self._target = target\r | |
| 1473 | self._error = expat.error\r | |
| 1474 | self._names = {} # name memo cache\r | |
| 1475 | # callbacks\r | |
| 1476 | parser.DefaultHandlerExpand = self._default\r | |
| 1477 | parser.StartElementHandler = self._start\r | |
| 1478 | parser.EndElementHandler = self._end\r | |
| 1479 | parser.CharacterDataHandler = self._data\r | |
| 1480 | # optional callbacks\r | |
| 1481 | parser.CommentHandler = self._comment\r | |
| 1482 | parser.ProcessingInstructionHandler = self._pi\r | |
| 1483 | # let expat do the buffering, if supported\r | |
| 1484 | try:\r | |
| 1485 | self._parser.buffer_text = 1\r | |
| 1486 | except AttributeError:\r | |
| 1487 | pass\r | |
| 1488 | # use new-style attribute handling, if supported\r | |
| 1489 | try:\r | |
| 1490 | self._parser.ordered_attributes = 1\r | |
| 1491 | self._parser.specified_attributes = 1\r | |
| 1492 | parser.StartElementHandler = self._start_list\r | |
| 1493 | except AttributeError:\r | |
| 1494 | pass\r | |
| 1495 | self._doctype = None\r | |
| 1496 | self.entity = {}\r | |
| 1497 | try:\r | |
| 1498 | self.version = "Expat %d.%d.%d" % expat.version_info\r | |
| 1499 | except AttributeError:\r | |
| 1500 | pass # unknown\r | |
| 1501 | \r | |
| 1502 | def _raiseerror(self, value):\r | |
| 1503 | err = ParseError(value)\r | |
| 1504 | err.code = value.code\r | |
| 1505 | err.position = value.lineno, value.offset\r | |
| 1506 | raise err\r | |
| 1507 | \r | |
| 1508 | def _fixtext(self, text):\r | |
| 1509 | # convert text string to ascii, if possible\r | |
| 1510 | try:\r | |
| 1511 | return text.encode("ascii")\r | |
| 1512 | except UnicodeError:\r | |
| 1513 | return text\r | |
| 1514 | \r | |
| 1515 | def _fixname(self, key):\r | |
| 1516 | # expand qname, and convert name string to ascii, if possible\r | |
| 1517 | try:\r | |
| 1518 | name = self._names[key]\r | |
| 1519 | except KeyError:\r | |
| 1520 | name = key\r | |
| 1521 | if "}" in name:\r | |
| 1522 | name = "{" + name\r | |
| 1523 | self._names[key] = name = self._fixtext(name)\r | |
| 1524 | return name\r | |
| 1525 | \r | |
| 1526 | def _start(self, tag, attrib_in):\r | |
| 1527 | fixname = self._fixname\r | |
| 1528 | fixtext = self._fixtext\r | |
| 1529 | tag = fixname(tag)\r | |
| 1530 | attrib = {}\r | |
| 1531 | for key, value in attrib_in.items():\r | |
| 1532 | attrib[fixname(key)] = fixtext(value)\r | |
| 1533 | return self.target.start(tag, attrib)\r | |
| 1534 | \r | |
| 1535 | def _start_list(self, tag, attrib_in):\r | |
| 1536 | fixname = self._fixname\r | |
| 1537 | fixtext = self._fixtext\r | |
| 1538 | tag = fixname(tag)\r | |
| 1539 | attrib = {}\r | |
| 1540 | if attrib_in:\r | |
| 1541 | for i in range(0, len(attrib_in), 2):\r | |
| 1542 | attrib[fixname(attrib_in[i])] = fixtext(attrib_in[i+1])\r | |
| 1543 | return self.target.start(tag, attrib)\r | |
| 1544 | \r | |
| 1545 | def _data(self, text):\r | |
| 1546 | return self.target.data(self._fixtext(text))\r | |
| 1547 | \r | |
| 1548 | def _end(self, tag):\r | |
| 1549 | return self.target.end(self._fixname(tag))\r | |
| 1550 | \r | |
| 1551 | def _comment(self, data):\r | |
| 1552 | try:\r | |
| 1553 | comment = self.target.comment\r | |
| 1554 | except AttributeError:\r | |
| 1555 | pass\r | |
| 1556 | else:\r | |
| 1557 | return comment(self._fixtext(data))\r | |
| 1558 | \r | |
| 1559 | def _pi(self, target, data):\r | |
| 1560 | try:\r | |
| 1561 | pi = self.target.pi\r | |
| 1562 | except AttributeError:\r | |
| 1563 | pass\r | |
| 1564 | else:\r | |
| 1565 | return pi(self._fixtext(target), self._fixtext(data))\r | |
| 1566 | \r | |
| 1567 | def _default(self, text):\r | |
| 1568 | prefix = text[:1]\r | |
| 1569 | if prefix == "&":\r | |
| 1570 | # deal with undefined entities\r | |
| 1571 | try:\r | |
| 1572 | self.target.data(self.entity[text[1:-1]])\r | |
| 1573 | except KeyError:\r | |
| 1574 | from xml.parsers import expat\r | |
| 1575 | err = expat.error(\r | |
| 1576 | "undefined entity %s: line %d, column %d" %\r | |
| 1577 | (text, self._parser.ErrorLineNumber,\r | |
| 1578 | self._parser.ErrorColumnNumber)\r | |
| 1579 | )\r | |
| 1580 | err.code = 11 # XML_ERROR_UNDEFINED_ENTITY\r | |
| 1581 | err.lineno = self._parser.ErrorLineNumber\r | |
| 1582 | err.offset = self._parser.ErrorColumnNumber\r | |
| 1583 | raise err\r | |
| 1584 | elif prefix == "<" and text[:9] == "<!DOCTYPE":\r | |
| 1585 | self._doctype = [] # inside a doctype declaration\r | |
| 1586 | elif self._doctype is not None:\r | |
| 1587 | # parse doctype contents\r | |
| 1588 | if prefix == ">":\r | |
| 1589 | self._doctype = None\r | |
| 1590 | return\r | |
| 1591 | text = text.strip()\r | |
| 1592 | if not text:\r | |
| 1593 | return\r | |
| 1594 | self._doctype.append(text)\r | |
| 1595 | n = len(self._doctype)\r | |
| 1596 | if n > 2:\r | |
| 1597 | type = self._doctype[1]\r | |
| 1598 | if type == "PUBLIC" and n == 4:\r | |
| 1599 | name, type, pubid, system = self._doctype\r | |
| 1600 | elif type == "SYSTEM" and n == 3:\r | |
| 1601 | name, type, system = self._doctype\r | |
| 1602 | pubid = None\r | |
| 1603 | else:\r | |
| 1604 | return\r | |
| 1605 | if pubid:\r | |
| 1606 | pubid = pubid[1:-1]\r | |
| 1607 | if hasattr(self.target, "doctype"):\r | |
| 1608 | self.target.doctype(name, pubid, system[1:-1])\r | |
| 1609 | elif self.doctype is not self._XMLParser__doctype:\r | |
| 1610 | # warn about deprecated call\r | |
| 1611 | self._XMLParser__doctype(name, pubid, system[1:-1])\r | |
| 1612 | self.doctype(name, pubid, system[1:-1])\r | |
| 1613 | self._doctype = None\r | |
| 1614 | \r | |
| 1615 | ##\r | |
| 1616 | # (Deprecated) Handles a doctype declaration.\r | |
| 1617 | #\r | |
| 1618 | # @param name Doctype name.\r | |
| 1619 | # @param pubid Public identifier.\r | |
| 1620 | # @param system System identifier.\r | |
| 1621 | \r | |
| 1622 | def doctype(self, name, pubid, system):\r | |
| 1623 | """This method of XMLParser is deprecated."""\r | |
| 1624 | warnings.warn(\r | |
| 1625 | "This method of XMLParser is deprecated. Define doctype() "\r | |
| 1626 | "method on the TreeBuilder target.",\r | |
| 1627 | DeprecationWarning,\r | |
| 1628 | )\r | |
| 1629 | \r | |
| 1630 | # sentinel, if doctype is redefined in a subclass\r | |
| 1631 | __doctype = doctype\r | |
| 1632 | \r | |
| 1633 | ##\r | |
| 1634 | # Feeds data to the parser.\r | |
| 1635 | #\r | |
| 1636 | # @param data Encoded data.\r | |
| 1637 | \r | |
| 1638 | def feed(self, data):\r | |
| 1639 | try:\r | |
| 1640 | self._parser.Parse(data, 0)\r | |
| 1641 | except self._error, v:\r | |
| 1642 | self._raiseerror(v)\r | |
| 1643 | \r | |
| 1644 | ##\r | |
| 1645 | # Finishes feeding data to the parser.\r | |
| 1646 | #\r | |
| 1647 | # @return An element structure.\r | |
| 1648 | # @defreturn Element\r | |
| 1649 | \r | |
| 1650 | def close(self):\r | |
| 1651 | try:\r | |
| 1652 | self._parser.Parse("", 1) # end of data\r | |
| 1653 | except self._error, v:\r | |
| 1654 | self._raiseerror(v)\r | |
| 1655 | tree = self.target.close()\r | |
| 1656 | del self.target, self._parser # get rid of circular references\r | |
| 1657 | return tree\r | |
| 1658 | \r | |
| 1659 | # compatibility\r | |
| 1660 | XMLTreeBuilder = XMLParser\r | |
| 1661 | \r | |
| 1662 | # workaround circular import.\r | |
| 1663 | try:\r | |
| 1664 | from ElementC14N import _serialize_c14n\r | |
| 1665 | _serialize["c14n"] = _serialize_c14n\r | |
| 1666 | except ImportError:\r | |
| 1667 | pass\r |