lxml 6.0.0__cp39-cp39-musllinux_1_2_armv7l.whl

lxml/ElementInclude.py

@@ -0,0 +1,244 @@
+#
+# ElementTree
+# $Id: ElementInclude.py 1862 2004-06-18 07:31:02Z Fredrik $
+#
+# limited xinclude support for element trees
+#
+# history:
+# 2003-08-15 fl   created
+# 2003-11-14 fl   fixed default loader
+#
+# Copyright (c) 2003-2004 by Fredrik Lundh.  All rights reserved.
+#
+# fredrik@pythonware.com
+# http://www.pythonware.com
+#
+# --------------------------------------------------------------------
+# The ElementTree toolkit is
+#
+# Copyright (c) 1999-2004 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.
+# --------------------------------------------------------------------
+
+"""
+Limited XInclude support for the ElementTree package.
+
+While lxml.etree has full support for XInclude (see
+`etree.ElementTree.xinclude()`), this module provides a simpler, pure
+Python, ElementTree compatible implementation that supports a simple
+form of custom URL resolvers.
+"""
+
+from lxml import etree
+try:
+    from urlparse import urljoin
+    from urllib2 import urlopen
+except ImportError:
+    # Python 3
+    from urllib.parse import urljoin
+    from urllib.request import urlopen
+
+XINCLUDE = "{http://www.w3.org/2001/XInclude}"
+
+XINCLUDE_INCLUDE = XINCLUDE + "include"
+XINCLUDE_FALLBACK = XINCLUDE + "fallback"
+XINCLUDE_ITER_TAG = XINCLUDE + "*"
+
+# For security reasons, the inclusion depth is limited to this read-only value by default.
+DEFAULT_MAX_INCLUSION_DEPTH = 6
+
+
+##
+# Fatal include error.
+
+class FatalIncludeError(etree.LxmlSyntaxError):
+    pass
+
+
+class LimitedRecursiveIncludeError(FatalIncludeError):
+    pass
+
+
+##
+# ET compatible default loader.
+# This loader reads an included resource from disk.
+#
+# @param href Resource reference.
+# @param parse Parse mode.  Either "xml" or "text".
+# @param encoding Optional text encoding.
+# @return The expanded resource.  If the parse mode is "xml", this
+#    is an ElementTree instance.  If the parse mode is "text", this
+#    is a Unicode string.  If the loader fails, it can return None
+#    or raise an IOError exception.
+# @throws IOError If the loader fails to load the resource.
+
+def default_loader(href, parse, encoding=None):
+    file = open(href, 'rb')
+    if parse == "xml":
+        data = etree.parse(file).getroot()
+    else:
+        data = file.read()
+        if not encoding:
+            encoding = 'utf-8'
+        data = data.decode(encoding)
+    file.close()
+    return data
+
+
+##
+# Default loader used by lxml.etree - handles custom resolvers properly
+# 
+
+def _lxml_default_loader(href, parse, encoding=None, parser=None):
+    if parse == "xml":
+        data = etree.parse(href, parser).getroot()
+    else:
+        if "://" in href:
+            f = urlopen(href)
+        else:
+            f = open(href, 'rb')
+        data = f.read()
+        f.close()
+        if not encoding:
+            encoding = 'utf-8'
+        data = data.decode(encoding)
+    return data
+
+
+##
+# Wrapper for ET compatibility - drops the parser
+
+def _wrap_et_loader(loader):
+    def load(href, parse, encoding=None, parser=None):
+        return loader(href, parse, encoding)
+    return load
+
+
+##
+# Expand XInclude directives.
+#
+# @param elem Root element.
+# @param loader Optional resource loader.  If omitted, it defaults
+#     to {@link default_loader}.  If given, it should be a callable
+#     that implements the same interface as <b>default_loader</b>.
+# @param base_url The base URL of the original file, to resolve
+#     relative include file references.
+# @param max_depth The maximum number of recursive inclusions.
+#     Limited to reduce the risk of malicious content explosion.
+#     Pass None to disable the limitation.
+# @throws LimitedRecursiveIncludeError If the {@link max_depth} was exceeded.
+# @throws FatalIncludeError If the function fails to include a given
+#     resource, or if the tree contains malformed XInclude elements.
+# @throws IOError If the function fails to load a given resource.
+# @returns the node or its replacement if it was an XInclude node
+
+def include(elem, loader=None, base_url=None,
+            max_depth=DEFAULT_MAX_INCLUSION_DEPTH):
+    if max_depth is None:
+        max_depth = -1
+    elif max_depth < 0:
+        raise ValueError("expected non-negative depth or None for 'max_depth', got %r" % max_depth)
+
+    if base_url is None:
+        if hasattr(elem, 'getroot'):
+            tree = elem
+            elem = elem.getroot()
+        else:
+            tree = elem.getroottree()
+        if hasattr(tree, 'docinfo'):
+            base_url = tree.docinfo.URL
+    elif hasattr(elem, 'getroot'):
+        elem = elem.getroot()
+    _include(elem, loader, base_url, max_depth)
+
+
+def _include(elem, loader=None, base_url=None,
+             max_depth=DEFAULT_MAX_INCLUSION_DEPTH, _parent_hrefs=None):
+    if loader is not None:
+        load_include = _wrap_et_loader(loader)
+    else:
+        load_include = _lxml_default_loader
+
+    if _parent_hrefs is None:
+        _parent_hrefs = set()
+
+    parser = elem.getroottree().parser
+
+    include_elements = list(
+        elem.iter(XINCLUDE_ITER_TAG))
+
+    for e in include_elements:
+        if e.tag == XINCLUDE_INCLUDE:
+            # process xinclude directive
+            href = urljoin(base_url, e.get("href"))
+            parse = e.get("parse", "xml")
+            parent = e.getparent()
+            if parse == "xml":
+                if href in _parent_hrefs:
+                    raise FatalIncludeError(
+                        "recursive include of %r detected" % href
+                        )
+                if max_depth == 0:
+                    raise LimitedRecursiveIncludeError(
+                        "maximum xinclude depth reached when including file %s" % href)
+                node = load_include(href, parse, parser=parser)
+                if node is None:
+                    raise FatalIncludeError(
+                        "cannot load %r as %r" % (href, parse)
+                        )
+                node = _include(node, loader, href, max_depth - 1, {href} | _parent_hrefs)
+                if e.tail:
+                    node.tail = (node.tail or "") + e.tail
+                if parent is None:
+                    return node # replaced the root node!
+                parent.replace(e, node)
+            elif parse == "text":
+                text = load_include(href, parse, encoding=e.get("encoding"))
+                if text is None:
+                    raise FatalIncludeError(
+                        "cannot load %r as %r" % (href, parse)
+                        )
+                predecessor = e.getprevious()
+                if predecessor is not None:
+                    predecessor.tail = (predecessor.tail or "") + text
+                elif parent is None:
+                    return text # replaced the root node!
+                else:
+                    parent.text = (parent.text or "") + text + (e.tail or "")
+                parent.remove(e)
+            else:
+                raise FatalIncludeError(
+                    "unknown parse type in xi:include tag (%r)" % parse
+                )
+        elif e.tag == XINCLUDE_FALLBACK:
+            parent = e.getparent()
+            if parent is not None and parent.tag != XINCLUDE_INCLUDE:
+                raise FatalIncludeError(
+                    "xi:fallback tag must be child of xi:include (%r)" % e.tag
+                    )
+        else:
+            raise FatalIncludeError(
+                "Invalid element found in XInclude namespace (%r)" % e.tag
+                )
+    return elem

lxml/__init__.py

@@ -0,0 +1,22 @@
+# this is a package
+
+__version__ = "6.0.0"
+
+
+def get_include():
+    """
+    Returns a list of header include paths (for lxml itself, libxml2
+    and libxslt) needed to compile C code against lxml if it was built
+    with statically linked libraries.
+    """
+    import os
+    lxml_path = __path__[0]
+    include_path = os.path.join(lxml_path, 'includes')
+    includes = [include_path, lxml_path]
+
+    for name in os.listdir(include_path):
+        path = os.path.join(include_path, name)
+        if os.path.isdir(path):
+            includes.append(path)
+
+    return includes

lxml/_elementpath.py

@@ -0,0 +1,343 @@
+# cython: language_level=3
+
+#
+# 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.
+# --------------------------------------------------------------------
+
+##
+# 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(
+    "("
+    "'[^']*'|\"[^\"]*\"|"
+    "::|"
+    "//?|"
+    r"\.\.|"
+    r"\(\)|"
+    r"[/.*:\[\]\(\)@=])|"
+    r"((?:\{[^}]+\})?[^/\[\]\(\)@=\s]+)|"
+    r"\s+"
+    )
+
+def xpath_tokenizer(pattern, namespaces=None, with_prefixes=True):
+    # ElementTree uses '', lxml used None originally.
+    default_namespace = (namespaces.get(None) or namespaces.get('')) if namespaces else None
+    parsing_attribute = False
+    for token in xpath_tokenizer_re.findall(pattern):
+        ttype, tag = token
+        if tag and tag[0] != "{":
+            if ":" in tag and with_prefixes:
+                prefix, uri = tag.split(":", 1)
+                try:
+                    if not namespaces:
+                        raise KeyError
+                    yield ttype, "{%s}%s" % (namespaces[prefix], uri)
+                except KeyError:
+                    raise SyntaxError("prefix %r not found in prefix map" % prefix)
+            elif tag.isdecimal():
+                yield token  # index
+            elif default_namespace and not parsing_attribute:
+                yield ttype, "{%s}%s" % (default_namespace, tag)
+            else:
+                yield token
+            parsing_attribute = False
+        else:
+            yield token
+            parsing_attribute = ttype == '@'
+
+
+def prepare_child(next, token):
+    tag = token[1]
+    def select(result):
+        for elem in result:
+            yield from elem.iterchildren(tag)
+    return select
+
+def prepare_star(next, token):
+    def select(result):
+        for elem in result:
+            yield from elem.iterchildren('*')
+    return select
+
+def prepare_self(next, token):
+    def select(result):
+        return 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(result):
+        for elem in result:
+            yield from elem.iterdescendants(tag)
+    return select
+
+def prepare_parent(next, token):
+    def select(result):
+        for elem in result:
+            parent = elem.getparent()
+            if parent is not 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 == ('', ''):
+            # ignore whitespace
+            continue
+        if token[0] and token[0][:1] in "'\"":
+            token = "'", token[0][1:-1]
+        signature += token[0] or "-"
+        predicate.append(token[1])
+
+    # use signature to determine predicate type
+    if signature == "@-":
+        # [@attribute] predicate
+        key = predicate[1]
+        def select(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(result):
+            for elem in result:
+                if elem.get(key) == value:
+                    yield elem
+        return select
+    if signature == "-" and not re.match(r"-?\d+$", predicate[0]):
+        # [tag]
+        tag = predicate[0]
+        def select(result):
+            for elem in result:
+                for _ in elem.iterchildren(tag):
+                    yield elem
+                    break
+        return select
+    if signature == ".='" or (signature == "-='" and not re.match(r"-?\d+$", predicate[0])):
+        # [.='value'] or [tag='value']
+        tag = predicate[0]
+        value = predicate[-1]
+        if tag:
+            def select(result):
+                for elem in result:
+                    for e in elem.iterchildren(tag):
+                        if "".join(e.itertext()) == value:
+                            yield elem
+                            break
+        else:
+            def select(result):
+                for elem in result:
+                    if "".join(elem.itertext()) == value:
+                        yield elem
+        return select
+    if signature == "-" or signature == "-()" or signature == "-()-":
+        # [index] or [last()] or [last()-index]
+        if signature == "-":
+            # [index]
+            index = int(predicate[0]) - 1
+            if index < 0:
+                if index == -1:
+                    raise SyntaxError(
+                        "indices in path predicates are 1-based, not 0-based")
+                else:
+                    raise SyntaxError("path index >= 1 expected")
+        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(result):
+            for elem in result:
+                parent = elem.getparent()
+                if parent is None:
+                    continue
+                try:
+                    # FIXME: what if the selector is "*" ?
+                    elems = list(parent.iterchildren(elem.tag))
+                    if elems[index] is elem:
+                        yield elem
+                except IndexError:
+                    pass
+        return select
+    raise SyntaxError("invalid predicate")
+
+ops = {
+    "": prepare_child,
+    "*": prepare_star,
+    ".": prepare_self,
+    "..": prepare_parent,
+    "//": prepare_descendant,
+    "[": prepare_predicate,
+}
+
+
+# --------------------------------------------------------------------
+
+_cache = {}
+
+
+def _build_path_iterator(path, namespaces, with_prefixes=True):
+    """compile selector pattern"""
+    if path[-1:] == "/":
+        path += "*"  # implicit all (FIXME: keep this?)
+
+    cache_key = (path,)
+    if namespaces:
+        # lxml originally used None for the default namespace but ElementTree uses the
+        # more convenient (all-strings-dict) empty string, so we support both here,
+        # preferring the more convenient '', as long as they aren't ambiguous.
+        if None in namespaces:
+            if '' in namespaces and namespaces[None] != namespaces['']:
+                raise ValueError("Ambiguous default namespace provided: %r versus %r" % (
+                    namespaces[None], namespaces['']))
+            cache_key += (namespaces[None],) + tuple(sorted(
+                item for item in namespaces.items() if item[0] is not None))
+        else:
+            cache_key += tuple(sorted(namespaces.items()))
+
+    try:
+        return _cache[cache_key]
+    except KeyError:
+        pass
+    if len(_cache) > 100:
+        _cache.clear()
+
+    if path[:1] == "/":
+        raise SyntaxError("cannot use absolute path on element")
+    stream = iter(xpath_tokenizer(path, namespaces, with_prefixes=with_prefixes))
+    try:
+        _next = stream.next
+    except AttributeError:
+        # Python 3
+        _next = stream.__next__
+    try:
+        token = _next()
+    except StopIteration:
+        raise SyntaxError("empty path expression")
+    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[cache_key] = selector
+    return selector
+
+
+##
+# Iterate over the matching nodes
+
+def iterfind(elem, path, namespaces=None, with_prefixes=True):
+    selector = _build_path_iterator(path, namespaces, with_prefixes=with_prefixes)
+    result = iter((elem,))
+    for select in selector:
+        result = select(result)
+    return result
+
+
+##
+# Find first matching object.
+
+def find(elem, path, namespaces=None, with_prefixes=True):
+    it = iterfind(elem, path, namespaces, with_prefixes=with_prefixes)
+    try:
+        return next(it)
+    except StopIteration:
+        return None
+
+
+##
+# Find all matching objects.
+
+def findall(elem, path, namespaces=None, with_prefixes=True):
+    return list(iterfind(elem, path, namespaces))
+
+
+##
+# Find text for first matching object.
+
+def findtext(elem, path, default=None, namespaces=None, with_prefixes=True):
+    el = find(elem, path, namespaces, with_prefixes=with_prefixes)
+    if el is None:
+        return default
+    else:
+        return el.text or ''