summaryrefslogtreecommitdiffstats
path: root/Lib/xml/etree/ElementPath.py
blob: 341dac0204b8e4428a537b1d784881a902e771a5 (plain)
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
#
# ElementTree
# $Id: ElementPath.py 3375 2008-02-13 08:05:08Z fredrik $
#
# limited xpath support for element trees
#
# history:
# 2003-05-23 fl   created
# 2003-05-28 fl   added support for // etc
# 2003-08-27 fl   fixed parsing of periods in element names
# 2007-09-10 fl   new selection engine
# 2007-09-12 fl   fixed parent selector
# 2007-09-13 fl   added iterfind; changed findall to return a list
# 2007-11-30 fl   added namespaces support
# 2009-10-30 fl   added child element value filter
#
# Copyright (c) 2003-2009 by Fredrik Lundh.  All rights reserved.
#
# fredrik@pythonware.com
# http://www.pythonware.com
#
# --------------------------------------------------------------------
# The ElementTree toolkit is
#
# Copyright (c) 1999-2009 by Fredrik Lundh
#
# By obtaining, using, and/or copying this software and/or its
# associated documentation, you agree that you have read, understood,
# and will comply with the following terms and conditions:
#
# Permission to use, copy, modify, and distribute this software and
# its associated documentation for any purpose and without fee is
# hereby granted, provided that the above copyright notice appears in
# all copies, and that both that copyright notice and this permission
# notice appear in supporting documentation, and that the name of
# Secret Labs AB or the author not be used in advertising or publicity
# pertaining to distribution of the software without specific, written
# prior permission.
#
# SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD
# TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANT-
# ABILITY AND FITNESS.  IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR
# BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY
# DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
# WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
# ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
# OF THIS SOFTWARE.
# --------------------------------------------------------------------

# Licensed to PSF under a Contributor Agreement.
# See http://www.python.org/psf/license for licensing details.

##
# Implementation module for XPath support.  There's usually no reason
# to import this module directly; the <b>ElementTree</b> does this for
# you, if needed.
##

import re

xpath_tokenizer_re = re.compile(
    "("
    "'[^']*'|\"[^\"]*\"|"
    "::|"
    "//?|"
    "\.\.|"
    "\(\)|"
    "[/.*:\[\]\(\)@=])|"
    "((?:\{[^}]+\})?[^/\[\]\(\)@=\s]+)|"
    "\s+"
    )

def xpath_tokenizer(pattern, namespaces=None):
    for token in xpath_tokenizer_re.findall(pattern):
        tag = token[1]
        if tag and tag[0] != "{" and ":" in tag:
            try:
                prefix, uri = tag.split(":", 1)
                if not namespaces:
                    raise KeyError
                yield token[0], "{%s}%s" % (namespaces[prefix], uri)
            except KeyError:
                raise SyntaxError("prefix %r not found in prefix map" % prefix)
        else:
            yield token

def get_parent_map(context):
    parent_map = context.parent_map
    if parent_map is None:
        context.parent_map = parent_map = {}
        for p in context.root.iter():
            for e in p:
                parent_map[e] = p
    return parent_map

def prepare_child(next, token):
    tag = token[1]
    def select(context, result):
        for elem in result:
            for e in elem:
                if e.tag == tag:
                    yield e
    return select

def prepare_star(next, token):
    def select(context, result):
        for elem in result:
            yield from elem
    return select

def prepare_self(next, token):
    def select(context, result):
        yield from result
    return select

def prepare_descendant(next, token):
    token = next()
    if token[0] == "*":
        tag = "*"
    elif not token[0]:
        tag = token[1]
    else:
        raise SyntaxError("invalid descendant")
    def select(context, result):
        for elem in result:
            for e in elem.iter(tag):
                if e is not elem:
                    yield e
    return select

def prepare_parent(next, token):
    def select(context, result):
        # FIXME: raise error if .. is applied at toplevel?
        parent_map = get_parent_map(context)
        result_map = {}
        for elem in result:
            if elem in parent_map:
                parent = parent_map[elem]
                if parent not in result_map:
                    result_map[parent] = None
                    yield parent
    return select

def prepare_predicate(next, token):
    # FIXME: replace with real parser!!! refs:
    # http://effbot.org/zone/simple-iterator-parser.htm
    # http://javascript.crockford.com/tdop/tdop.html
    signature = []
    predicate = []
    while 1:
        token = next()
        if token[0] == "]":
            break
        if token[0] and token[0][:1] in "'\"":
            token = "'", token[0][1:-1]
        signature.append(token[0] or "-")
        predicate.append(token[1])
    signature = "".join(signature)
    # use signature to determine predicate type
    if signature == "@-":
        # [@attribute] predicate
        key = predicate[1]
        def select(context, result):
            for elem in result:
                if elem.get(key) is not None:
                    yield elem
        return select
    if signature == "@-='":
        # [@attribute='value']
        key = predicate[1]
        value = predicate[-1]
        def select(context, result):
            for elem in result:
                if elem.get(key) == value:
                    yield elem
        return select
    if signature == "-" and not re.match("\d+$", predicate[0]):
        # [tag]
        tag = predicate[0]
        def select(context, result):
            for elem in result:
                if elem.find(tag) is not None:
                    yield elem
        return select
    if signature == "-='" and not re.match("\d+$", predicate[0]):
        # [tag='value']
        tag = predicate[0]
        value = predicate[-1]
        def select(context, result):
            for elem in result:
                for e in elem.findall(tag):
                    if "".join(e.itertext()) == value:
                        yield elem
                        break
        return select
    if signature == "-" or signature == "-()" or signature == "-()-":
        # [index] or [last()] or [last()-index]
        if signature == "-":
            index = int(predicate[0]) - 1
        else:
            if predicate[0] != "last":
                raise SyntaxError("unsupported function")
            if signature == "-()-":
                try:
                    index = int(predicate[2]) - 1
                except ValueError:
                    raise SyntaxError("unsupported expression")
            else:
                index = -1
        def select(context, result):
            parent_map = get_parent_map(context)
            for elem in result:
                try:
                    parent = parent_map[elem]
                    # FIXME: what if the selector is "*" ?
                    elems = list(parent.findall(elem.tag))
                    if elems[index] is elem:
                        yield elem
                except (IndexError, KeyError):
                    pass
        return select
    raise SyntaxError("invalid predicate")

ops = {
    "": prepare_child,
    "*": prepare_star,
    ".": prepare_self,
    "..": prepare_parent,
    "//": prepare_descendant,
    "[": prepare_predicate,
    }

_cache = {}

class _SelectorContext:
    parent_map = None
    def __init__(self, root):
        self.root = root

# --------------------------------------------------------------------

##
# Generate all matching objects.

def iterfind(elem, path, namespaces=None):
    # compile selector pattern
    if path[-1:] == "/":
        path = path + "*" # implicit all (FIXME: keep this?)
    try:
        selector = _cache[path]
    except KeyError:
        if len(_cache) > 100:
            _cache.clear()
        if path[:1] == "/":
            raise SyntaxError("cannot use absolute path on element")
        next = iter(xpath_tokenizer(path, namespaces)).__next__
        token = next()
        selector = []
        while 1:
            try:
                selector.append(ops[token[0]](next, token))
            except StopIteration:
                raise SyntaxError("invalid path")
            try:
                token = next()
                if token[0] == "/":
                    token = next()
            except StopIteration:
                break
        _cache[path] = selector
    # execute selector pattern
    result = [elem]
    context = _SelectorContext(elem)
    for select in selector:
        result = select(context, result)
    return result

##
# Find first matching object.

def find(elem, path, namespaces=None):
    try:
        return next(iterfind(elem, path, namespaces))
    except StopIteration:
        return None

##
# Find all matching objects.

def findall(elem, path, namespaces=None):
    return list(iterfind(elem, path, namespaces))

##
# Find text for first matching object.

def findtext(elem, path, default=None, namespaces=None):
    try:
        elem = next(iterfind(elem, path, namespaces))
        return elem.text or ""
    except StopIteration:
        return default