replace internal copy of ElementTree with standard library's ElementTree

tests/etree13/ElementPath.py

@@ -1,226 +0,0 @@
-#
-# ElementTree
-# $Id$
-#
-# 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
-#
-# Copyright (c) 2003-2007 by Fredrik Lundh.  All rights reserved.
-#
-# fredrik@pythonware.com
-# http://www.pythonware.com
-#
-# --------------------------------------------------------------------
-# The ElementTree toolkit is
-#
-# Copyright (c) 1999-2007 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.compile(
-    "("
-    "'[^']*'|\"[^\"]*\"|"
-    "::|"
-    "//?|"
-    "\.\.|"
-    "\(\)|"
-    "[/.*:\[\]\(\)@=])|"
-    "((?:\{[^}]+\})?[^/:\[\]\(\)@=\s]+)|"
-    "\s+"
-    ).findall
-
-def prepare_tag(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:
-            for e in elem:
-                yield e
-    return select
-
-def prepare_dot(next, token):
-    def select(context, result):
-        for elem in result:
-            yield elem
-    return select
-
-def prepare_iter(next, token):
-    token = next()
-    if token[0] == "*":
-        tag = "*"
-    elif not token[0]:
-        tag = token[1]
-    else:
-        raise SyntaxError
-    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_dot_dot(next, token):
-    def select(context, result):
-        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
-        for elem in result:
-            if elem in parent_map:
-                yield parent_map[elem]
-    return select
-
-def prepare_predicate(next, token):
-    # this one should probably be refactored...
-    token = next()
-    if token[0] == "@":
-        # attribute
-        token = next()
-        if token[0]:
-            raise SyntaxError("invalid attribute predicate")
-        key = token[1]
-        token = next()
-        if token[0] == "]":
-            def select(context, result):
-                for elem in result:
-                    if elem.get(key) is not None:
-                        yield elem
-        elif token[0] == "=":
-            value = next()[0]
-            if value[:1] == "'" or value[:1] == '"':
-                value = value[1:-1]
-            else:
-                raise SyntaxError("invalid comparision target")
-            token = next()
-            def select(context, result):
-                for elem in result:
-                    if elem.get(key) == value:
-                        yield elem
-        if token[0] != "]":
-            raise SyntaxError("invalid attribute predicate")
-    elif not token[0]:
-        tag = token[1]
-        token = next()
-        if token[0] != "]":
-            raise SyntaxError("invalid node predicate")
-        def select(context, result):
-            for elem in result:
-                if elem.find(tag) is not None:
-                    yield elem
-    else:
-        raise SyntaxError("invalid predicate")
-    return select
-
-ops = {
-    "": prepare_tag,
-    "*": prepare_star,
-    ".": prepare_dot,
-    "..": prepare_dot_dot,
-    "//": prepare_iter,
-    "[": prepare_predicate,
-    }
-
-_cache = {}
-
-class _SelectorContext:
-    parent_map = None
-    def __init__(self, root):
-        self.root = root
-
-# --------------------------------------------------------------------
-
-##
-# Find first matching object.
-
-def find(elem, path):
-    try:
-        return next(findall(elem, path))
-    except StopIteration:
-        return None
-
-##
-# Find all matching objects.
-
-def findall(elem, path):
-    # compile selector pattern
-    try:
-        selector = _cache[path]
-    except KeyError:
-        if len(_cache) > 100:
-            _cache.clear()
-        if path[:1] == "/":
-            raise SyntaxError("cannot use absolute path on element")
-        stream = iter(xpath_tokenizer(path))
-        next_ = lambda: next(stream); 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 text for first matching object.
-
-def findtext(elem, path, default=None):
-    try:
-        elem = next(findall(elem, path))
-        return elem.text
-    except StopIteration:
-        return default

tests/etree13/HTMLTreeBuilder.py

@@ -1,233 +0,0 @@
-from __future__ import absolute_import
-#
-# ElementTree
-# $Id$
-#
-# a simple tree builder, for HTML input
-#
-# history:
-# 2002-04-06 fl   created
-# 2002-04-07 fl   ignore IMG and HR end tags
-# 2002-04-07 fl   added support for 1.5.2 and later
-# 2003-04-13 fl   added HTMLTreeBuilder alias
-# 2004-12-02 fl   don't feed non-ASCII charrefs/entities as 8-bit strings
-# 2004-12-05 fl   don't feed non-ASCII CDATA as 8-bit strings
-#
-# Copyright (c) 1999-2004 by Fredrik Lundh.  All rights reserved.
-#
-# fredrik@pythonware.com
-# http://www.pythonware.com
-#
-# --------------------------------------------------------------------
-# The ElementTree toolkit is
-#
-# Copyright (c) 1999-2007 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.
-# --------------------------------------------------------------------
-
-##
-# Tools to build element trees from HTML files.
-##
-
-import htmlentitydefs
-import re, string, sys
-import mimetools, StringIO
-
-from six import text_type
-
-from . import ElementTree
-
-AUTOCLOSE = "p", "li", "tr", "th", "td", "head", "body"
-IGNOREEND = "img", "hr", "meta", "link", "br"
-
-if sys.version[:3] == "1.5":
-    is_not_ascii = re.compile(r"[\x80-\xff]").search # 1.5.2
-else:
-    is_not_ascii = re.compile(eval(r'u"[\u0080-\uffff]"')).search
-
-try:
-    from HTMLParser import HTMLParser
-except ImportError:
-    from sgmllib import SGMLParser
-    # hack to use sgmllib's SGMLParser to emulate 2.2's HTMLParser
-    class HTMLParser(SGMLParser):
-        # the following only works as long as this class doesn't
-        # provide any do, start, or end handlers
-        def unknown_starttag(self, tag, attrs):
-            self.handle_starttag(tag, attrs)
-        def unknown_endtag(self, tag):
-            self.handle_endtag(tag)
-
-##
-# ElementTree builder for HTML source code.  This builder converts an
-# HTML document or fragment to an ElementTree.
-# <p>
-# The parser is relatively picky, and requires balanced tags for most
-# elements.  However, elements belonging to the following group are
-# automatically closed: P, LI, TR, TH, and TD.  In addition, the
-# parser automatically inserts end tags immediately after the start
-# tag, and ignores any end tags for the following group: IMG, HR,
-# META, and LINK.
-#
-# @keyparam builder Optional builder object.  If omitted, the parser
-#     uses the standard <b>elementtree</b> builder.
-# @keyparam encoding Optional character encoding, if known.  If omitted,
-#     the parser looks for META tags inside the document.  If no tags
-#     are found, the parser defaults to ISO-8859-1.  Note that if your
-#     document uses a non-ASCII compatible encoding, you must decode
-#     the document before parsing.
-#
-# @see elementtree.ElementTree
-
-class HTMLTreeBuilder(HTMLParser):
-
-    # FIXME: shouldn't this class be named Parser, not Builder?
-
-    def __init__(self, builder=None, encoding=None):
-        self.__stack = []
-        if builder is None:
-            builder = ElementTree.TreeBuilder()
-        self.__builder = builder
-        self.encoding = encoding or "iso-8859-1"
-        HTMLParser.__init__(self)
-
-    ##
-    # Flushes parser buffers, and return the root element.
-    #
-    # @return An Element instance.
-
-    def close(self):
-        HTMLParser.close(self)
-        return self.__builder.close()
-
-    ##
-    # (Internal) Handles start tags.
-
-    def handle_starttag(self, tag, attrs):
-        if tag == "meta":
-            # look for encoding directives
-            http_equiv = content = None
-            for k, v in attrs:
-                if k == "http-equiv":
-                    http_equiv = string.lower(v)
-                elif k == "content":
-                    content = v
-            if http_equiv == "content-type" and content:
-                # use mimetools to parse the http header
-                header = mimetools.Message(
-                    StringIO.StringIO("%s: %s\n\n" % (http_equiv, content))
-                    )
-                encoding = header.getparam("charset")
-                if encoding:
-                    self.encoding = encoding
-        if tag in AUTOCLOSE:
-            if self.__stack and self.__stack[-1] == tag:
-                self.handle_endtag(tag)
-        self.__stack.append(tag)
-        attrib = {}
-        if attrs:
-            for k, v in attrs:
-                attrib[string.lower(k)] = v
-        self.__builder.start(tag, attrib)
-        if tag in IGNOREEND:
-            self.__stack.pop()
-            self.__builder.end(tag)
-
-    ##
-    # (Internal) Handles end tags.
-
-    def handle_endtag(self, tag):
-        if tag in IGNOREEND:
-            return
-        lasttag = self.__stack.pop()
-        if tag != lasttag and lasttag in AUTOCLOSE:
-            self.handle_endtag(lasttag)
-        self.__builder.end(tag)
-
-    ##
-    # (Internal) Handles character references.
-
-    def handle_charref(self, char):
-        if char[:1] == "x":
-            char = int(char[1:], 16)
-        else:
-            char = int(char)
-        if 0 <= char < 128:
-            self.__builder.data(chr(char))
-        else:
-            self.__builder.data(unichr(char))
-
-    ##
-    # (Internal) Handles entity references.
-
-    def handle_entityref(self, name):
-        entity = htmlentitydefs.entitydefs.get(name)
-        if entity:
-            if len(entity) == 1:
-                entity = ord(entity)
-            else:
-                entity = int(entity[2:-1])
-            if 0 <= entity < 128:
-                self.__builder.data(chr(entity))
-            else:
-                self.__builder.data(unichr(entity))
-        else:
-            self.unknown_entityref(name)
-
-    ##
-    # (Internal) Handles character data.
-
-    def handle_data(self, data):
-        if isinstance(data, type('')) and is_not_ascii(data):
-            # convert to unicode, but only if necessary
-            data = text_type(data, self.encoding, "ignore")
-        self.__builder.data(data)
-
-    ##
-    # (Hook) Handles unknown entity references.  The default action
-    # is to ignore unknown entities.
-
-    def unknown_entityref(self, name):
-        pass # ignore by default; override if necessary
-
-##
-# An alias for the <b>HTMLTreeBuilder</b> class.
-
-TreeBuilder = HTMLTreeBuilder
-
-##
-# Parse an HTML document or document fragment.
-#
-# @param source A filename or file object containing HTML data.
-# @param encoding Optional character encoding, if known.  If omitted,
-#     the parser looks for META tags inside the document.  If no tags
-#     are found, the parser defaults to ISO-8859-1.
-# @return An ElementTree instance
-
-def parse(source, encoding=None):
-    return ElementTree.parse(source, HTMLTreeBuilder(encoding=encoding))
-
-if __name__ == "__main__":
-    import sys
-    ElementTree.dump(parse(open(sys.argv[1])))

tests/etree13/__init__.py

@@ -1,30 +0,0 @@
-# $Id$
-# elementtree package
-
-# --------------------------------------------------------------------
-# The ElementTree toolkit is
-#
-# Copyright (c) 1999-2007 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.
-# --------------------------------------------------------------------

tests/test_build_html.py

@@ -17,7 +17,7 @@ from six import PY3
 
 from sphinx import __display_version__
 from util import remove_unicode_literals, strip_escseq
-from etree13 import ElementTree
+import xml.etree.cElementTree as ElementTree
 from html5lib import getTreeBuilder, HTMLParser
 import pytest