Coverage for /pythoncovmergedfiles/medio/medio/usr/lib/python3.9/xml/etree/ElementPath.py: 25%
259 statements
« prev ^ index » next coverage.py v7.3.2, created at 2023-10-20 07:00 +0000
1#
2# ElementTree
3# $Id: ElementPath.py 3375 2008-02-13 08:05:08Z fredrik $
4#
5# limited xpath support for element trees
6#
7# history:
8# 2003-05-23 fl created
9# 2003-05-28 fl added support for // etc
10# 2003-08-27 fl fixed parsing of periods in element names
11# 2007-09-10 fl new selection engine
12# 2007-09-12 fl fixed parent selector
13# 2007-09-13 fl added iterfind; changed findall to return a list
14# 2007-11-30 fl added namespaces support
15# 2009-10-30 fl added child element value filter
16#
17# Copyright (c) 2003-2009 by Fredrik Lundh. All rights reserved.
18#
19# fredrik@pythonware.com
20# http://www.pythonware.com
21#
22# --------------------------------------------------------------------
23# The ElementTree toolkit is
24#
25# Copyright (c) 1999-2009 by Fredrik Lundh
26#
27# By obtaining, using, and/or copying this software and/or its
28# associated documentation, you agree that you have read, understood,
29# and will comply with the following terms and conditions:
30#
31# Permission to use, copy, modify, and distribute this software and
32# its associated documentation for any purpose and without fee is
33# hereby granted, provided that the above copyright notice appears in
34# all copies, and that both that copyright notice and this permission
35# notice appear in supporting documentation, and that the name of
36# Secret Labs AB or the author not be used in advertising or publicity
37# pertaining to distribution of the software without specific, written
38# prior permission.
39#
40# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
41# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
42# ABILITY AND FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
43# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
44# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
45# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
46# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
47# OF THIS SOFTWARE.
48# --------------------------------------------------------------------
50# Licensed to PSF under a Contributor Agreement.
51# See http://www.python.org/psf/license for licensing details.
53##
54# Implementation module for XPath support. There's usually no reason
55# to import this module directly; the <b>ElementTree</b> does this for
56# you, if needed.
57##
59import re
61xpath_tokenizer_re = re.compile(
62 r"("
63 r"'[^']*'|\"[^\"]*\"|"
64 r"::|"
65 r"//?|"
66 r"\.\.|"
67 r"\(\)|"
68 r"[/.*:\[\]\(\)@=])|"
69 r"((?:\{[^}]+\})?[^/\[\]\(\)@=\s]+)|"
70 r"\s+"
71 )
73def xpath_tokenizer(pattern, namespaces=None):
74 default_namespace = namespaces.get('') if namespaces else None
75 parsing_attribute = False
76 for token in xpath_tokenizer_re.findall(pattern):
77 ttype, tag = token
78 if tag and tag[0] != "{":
79 if ":" in tag:
80 prefix, uri = tag.split(":", 1)
81 try:
82 if not namespaces:
83 raise KeyError
84 yield ttype, "{%s}%s" % (namespaces[prefix], uri)
85 except KeyError:
86 raise SyntaxError("prefix %r not found in prefix map" % prefix) from None
87 elif default_namespace and not parsing_attribute:
88 yield ttype, "{%s}%s" % (default_namespace, tag)
89 else:
90 yield token
91 parsing_attribute = False
92 else:
93 yield token
94 parsing_attribute = ttype == '@'
97def get_parent_map(context):
98 parent_map = context.parent_map
99 if parent_map is None:
100 context.parent_map = parent_map = {}
101 for p in context.root.iter():
102 for e in p:
103 parent_map[e] = p
104 return parent_map
107def _is_wildcard_tag(tag):
108 return tag[:3] == '{*}' or tag[-2:] == '}*'
111def _prepare_tag(tag):
112 _isinstance, _str = isinstance, str
113 if tag == '{*}*':
114 # Same as '*', but no comments or processing instructions.
115 # It can be a surprise that '*' includes those, but there is no
116 # justification for '{*}*' doing the same.
117 def select(context, result):
118 for elem in result:
119 if _isinstance(elem.tag, _str):
120 yield elem
121 elif tag == '{}*':
122 # Any tag that is not in a namespace.
123 def select(context, result):
124 for elem in result:
125 el_tag = elem.tag
126 if _isinstance(el_tag, _str) and el_tag[0] != '{':
127 yield elem
128 elif tag[:3] == '{*}':
129 # The tag in any (or no) namespace.
130 suffix = tag[2:] # '}name'
131 no_ns = slice(-len(suffix), None)
132 tag = tag[3:]
133 def select(context, result):
134 for elem in result:
135 el_tag = elem.tag
136 if el_tag == tag or _isinstance(el_tag, _str) and el_tag[no_ns] == suffix:
137 yield elem
138 elif tag[-2:] == '}*':
139 # Any tag in the given namespace.
140 ns = tag[:-1]
141 ns_only = slice(None, len(ns))
142 def select(context, result):
143 for elem in result:
144 el_tag = elem.tag
145 if _isinstance(el_tag, _str) and el_tag[ns_only] == ns:
146 yield elem
147 else:
148 raise RuntimeError(f"internal parser error, got {tag}")
149 return select
152def prepare_child(next, token):
153 tag = token[1]
154 if _is_wildcard_tag(tag):
155 select_tag = _prepare_tag(tag)
156 def select(context, result):
157 def select_child(result):
158 for elem in result:
159 yield from elem
160 return select_tag(context, select_child(result))
161 else:
162 if tag[:2] == '{}':
163 tag = tag[2:] # '{}tag' == 'tag'
164 def select(context, result):
165 for elem in result:
166 for e in elem:
167 if e.tag == tag:
168 yield e
169 return select
171def prepare_star(next, token):
172 def select(context, result):
173 for elem in result:
174 yield from elem
175 return select
177def prepare_self(next, token):
178 def select(context, result):
179 yield from result
180 return select
182def prepare_descendant(next, token):
183 try:
184 token = next()
185 except StopIteration:
186 return
187 if token[0] == "*":
188 tag = "*"
189 elif not token[0]:
190 tag = token[1]
191 else:
192 raise SyntaxError("invalid descendant")
194 if _is_wildcard_tag(tag):
195 select_tag = _prepare_tag(tag)
196 def select(context, result):
197 def select_child(result):
198 for elem in result:
199 for e in elem.iter():
200 if e is not elem:
201 yield e
202 return select_tag(context, select_child(result))
203 else:
204 if tag[:2] == '{}':
205 tag = tag[2:] # '{}tag' == 'tag'
206 def select(context, result):
207 for elem in result:
208 for e in elem.iter(tag):
209 if e is not elem:
210 yield e
211 return select
213def prepare_parent(next, token):
214 def select(context, result):
215 # FIXME: raise error if .. is applied at toplevel?
216 parent_map = get_parent_map(context)
217 result_map = {}
218 for elem in result:
219 if elem in parent_map:
220 parent = parent_map[elem]
221 if parent not in result_map:
222 result_map[parent] = None
223 yield parent
224 return select
226def prepare_predicate(next, token):
227 # FIXME: replace with real parser!!! refs:
228 # http://effbot.org/zone/simple-iterator-parser.htm
229 # http://javascript.crockford.com/tdop/tdop.html
230 signature = []
231 predicate = []
232 while 1:
233 try:
234 token = next()
235 except StopIteration:
236 return
237 if token[0] == "]":
238 break
239 if token == ('', ''):
240 # ignore whitespace
241 continue
242 if token[0] and token[0][:1] in "'\"":
243 token = "'", token[0][1:-1]
244 signature.append(token[0] or "-")
245 predicate.append(token[1])
246 signature = "".join(signature)
247 # use signature to determine predicate type
248 if signature == "@-":
249 # [@attribute] predicate
250 key = predicate[1]
251 def select(context, result):
252 for elem in result:
253 if elem.get(key) is not None:
254 yield elem
255 return select
256 if signature == "@-='":
257 # [@attribute='value']
258 key = predicate[1]
259 value = predicate[-1]
260 def select(context, result):
261 for elem in result:
262 if elem.get(key) == value:
263 yield elem
264 return select
265 if signature == "-" and not re.match(r"\-?\d+$", predicate[0]):
266 # [tag]
267 tag = predicate[0]
268 def select(context, result):
269 for elem in result:
270 if elem.find(tag) is not None:
271 yield elem
272 return select
273 if signature == ".='" or (signature == "-='" and not re.match(r"\-?\d+$", predicate[0])):
274 # [.='value'] or [tag='value']
275 tag = predicate[0]
276 value = predicate[-1]
277 if tag:
278 def select(context, result):
279 for elem in result:
280 for e in elem.findall(tag):
281 if "".join(e.itertext()) == value:
282 yield elem
283 break
284 else:
285 def select(context, result):
286 for elem in result:
287 if "".join(elem.itertext()) == value:
288 yield elem
289 return select
290 if signature == "-" or signature == "-()" or signature == "-()-":
291 # [index] or [last()] or [last()-index]
292 if signature == "-":
293 # [index]
294 index = int(predicate[0]) - 1
295 if index < 0:
296 raise SyntaxError("XPath position >= 1 expected")
297 else:
298 if predicate[0] != "last":
299 raise SyntaxError("unsupported function")
300 if signature == "-()-":
301 try:
302 index = int(predicate[2]) - 1
303 except ValueError:
304 raise SyntaxError("unsupported expression")
305 if index > -2:
306 raise SyntaxError("XPath offset from last() must be negative")
307 else:
308 index = -1
309 def select(context, result):
310 parent_map = get_parent_map(context)
311 for elem in result:
312 try:
313 parent = parent_map[elem]
314 # FIXME: what if the selector is "*" ?
315 elems = list(parent.findall(elem.tag))
316 if elems[index] is elem:
317 yield elem
318 except (IndexError, KeyError):
319 pass
320 return select
321 raise SyntaxError("invalid predicate")
323ops = {
324 "": prepare_child,
325 "*": prepare_star,
326 ".": prepare_self,
327 "..": prepare_parent,
328 "//": prepare_descendant,
329 "[": prepare_predicate,
330 }
332_cache = {}
334class _SelectorContext:
335 parent_map = None
336 def __init__(self, root):
337 self.root = root
339# --------------------------------------------------------------------
341##
342# Generate all matching objects.
344def iterfind(elem, path, namespaces=None):
345 # compile selector pattern
346 if path[-1:] == "/":
347 path = path + "*" # implicit all (FIXME: keep this?)
349 cache_key = (path,)
350 if namespaces:
351 cache_key += tuple(sorted(namespaces.items()))
353 try:
354 selector = _cache[cache_key]
355 except KeyError:
356 if len(_cache) > 100:
357 _cache.clear()
358 if path[:1] == "/":
359 raise SyntaxError("cannot use absolute path on element")
360 next = iter(xpath_tokenizer(path, namespaces)).__next__
361 try:
362 token = next()
363 except StopIteration:
364 return
365 selector = []
366 while 1:
367 try:
368 selector.append(ops[token[0]](next, token))
369 except StopIteration:
370 raise SyntaxError("invalid path") from None
371 try:
372 token = next()
373 if token[0] == "/":
374 token = next()
375 except StopIteration:
376 break
377 _cache[cache_key] = selector
378 # execute selector pattern
379 result = [elem]
380 context = _SelectorContext(elem)
381 for select in selector:
382 result = select(context, result)
383 return result
385##
386# Find first matching object.
388def find(elem, path, namespaces=None):
389 return next(iterfind(elem, path, namespaces), None)
391##
392# Find all matching objects.
394def findall(elem, path, namespaces=None):
395 return list(iterfind(elem, path, namespaces))
397##
398# Find text for first matching object.
400def findtext(elem, path, default=None, namespaces=None):
401 try:
402 elem = next(iterfind(elem, path, namespaces))
403 return elem.text or ""
404 except StopIteration:
405 return default