Merged revisions 65283,65303,65316-65317,65372-65375,65377,65380,65483-65485,65494 via svnmerge from

svn+ssh://pythondev@svn.python.org/doctools/branches/0.4.x

........
  r65283 | georg.brandl | 2008-07-29 10:07:26 +0000 (Tue, 29 Jul 2008) | 2 lines

  Update ez_setup.py.
........
  r65303 | benjamin.peterson | 2008-07-30 12:35:34 +0000 (Wed, 30 Jul 2008) | 1 line

  add a with_testapp decorator for test functions that passes the TestApp instance in a cleans up after it
........
  r65316 | benjamin.peterson | 2008-07-30 23:12:07 +0000 (Wed, 30 Jul 2008) | 1 line

  make the app for test_markup global to the module
........
  r65317 | benjamin.peterson | 2008-07-30 23:31:29 +0000 (Wed, 30 Jul 2008) | 1 line

  make TestApp.cleanup more aggressive
........
  r65372 | georg.brandl | 2008-08-01 19:11:22 +0000 (Fri, 01 Aug 2008) | 2 lines

  Add more tests, fix a few bugs in image handling.
........
  r65373 | georg.brandl | 2008-08-01 19:28:33 +0000 (Fri, 01 Aug 2008) | 2 lines

  Fix oversight.
........
  r65374 | benjamin.peterson | 2008-08-01 19:36:32 +0000 (Fri, 01 Aug 2008) | 1 line

  fix one broken test
........
  r65375 | georg.brandl | 2008-08-01 19:41:11 +0000 (Fri, 01 Aug 2008) | 2 lines

  Fix the handling of non-ASCII input in quickstart.
........
  r65377 | georg.brandl | 2008-08-01 19:48:24 +0000 (Fri, 01 Aug 2008) | 2 lines

  Allow REs in markup checks.
........
  r65380 | georg.brandl | 2008-08-01 20:31:18 +0000 (Fri, 01 Aug 2008) | 2 lines

  Don't rely on mtimes being different for changed files.
........
  r65483 | georg.brandl | 2008-08-04 09:01:40 +0000 (Mon, 04 Aug 2008) | 4 lines

  Add an "encoding" option to literalinclude.

  Add tests for include directives.
........
  r65484 | georg.brandl | 2008-08-04 09:11:17 +0000 (Mon, 04 Aug 2008) | 2 lines

  Add changelog entry.
........
  r65485 | georg.brandl | 2008-08-04 09:21:58 +0000 (Mon, 04 Aug 2008) | 2 lines

  Fix markup.
........
  r65494 | georg.brandl | 2008-08-04 16:34:59 +0000 (Mon, 04 Aug 2008) | 2 lines

  Correctly use HTML file suffix in templates.
........

1 files changed, 230 insertions, 0 deletions

diff --git a/tests/etree13/HTMLTreeBuilder.py b/tests/etree13/HTMLTreeBuilder.py
new file mode 100644
index 00000000..4c5a24f6
--- /dev/null
+++ b/tests/etree13/HTMLTreeBuilder.py
@@ -0,0 +1,230 @@
+#
+# 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
+
+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 = unicode(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])))