pymeldlite.py

用python实现的邮件过滤器

            return
        raise KeyError, "No element named %r" % name

    def __iadd__(self, other):
        """`object1 += object2` appends a string or a clone of a Meld to
        the end of another Meld's content.  This is used to build things
        like HTML tables, which are collections of other objects (eg. table
        rows).  See *Real-world example* in the main documentation."""

        if self._readonly:
            raise ReadOnlyError, READ_ONLY_MESSAGE
        if isinstance(other, Meld):
            nodes = [other._tree.getElementNode().clone()]
        else:
            nodes = self._nodeListFromSource(other)
        self._tree.children.extend(nodes)
        return self

    def __mod__(self, values):
        """`object % value`, `object % sequence`, or `object % dictionary` all
        mimic the `%` operator for strings:

        >>> xml = '<x><y id="greeting">Hello</y> <z id="who">World</z></x>'
        >>> x = Meld(xml)
        >>> print x % ("Howdy", "everybody")
        <x><y id="greeting">Howdy</y> <z id="who">everybody</z></x>
        >>> print x % {'who': 'all'}
        <x><y id="greeting">Hello</y> <z id="who">all</z></x>

        Assignment for sequences happens in the same order that nodes with
        'id' attributes appear in the document, not including the top-level
        node (because if the top-level node were included, you'd only ever
        be able to assign to that and nothing else):

        >>> xml = '''<a id="a">
        ... <b>  <!-- `b` has no ID, hence is ignored. -->
        ...     <c id="c">First one</c>
        ...     <d id="d">Second one</d>
        ... </b>
        ... <e id="e">Third one; the content includes 'f':
        ...     <f id="f">Removed when 'e' is assigned to</f>
        ... </e>
        ... </a>'''
        >>> a = Meld(xml)
        >>> print a % ('One, with a <z id="new">new</z> node', 'Two', 'Three')
        <a id="a">
        <b>  <!-- `b` has no ID, hence is ignored. -->
            <c id="c">One, with a <z id="new">new</z> node</c>
            <d id="d">Two</d>
        </b>
        <e id="e">Three</e>
        </a>

        Giving the wrong number of elements to `%` raises the same exceptions
        as the builtin string `%` operator.  Unlike the builtin `%` operator,
        dictionaries don't need to specify all the keys:

        >>> print x % "Howdy"
        Traceback (most recent call last):
        ...
        TypeError: not enough arguments
        >>> print x % ("Howdy", "everybody", "everywhere")
        Traceback (most recent call last):
        ...
        TypeError: not all arguments converted
        >>> print x % {"greeting": "Howdy"}
        <x><y id="greeting">Howdy</y> <z id="who">World</z></x>
        """

        # Figure out whether we have a dictionary, a sequence, or a lone value.
        returnObject = self.clone()
        if hasattr(values, 'values') and callable(values.values):
            # It's a dictionary.
            keys = values.keys()
            sequence = values.values()
        elif hasattr(values, '__getitem__') and \
             not isinstance(values, str):
            # It's a sequence.
            keys = None
            sequence = list(values)
        else:
            # Assume it's a plain value.
            keys = None
            sequence = [values]

        # If we've derived a set of keys, just assign the values.
        if keys:
            for key, value in zip(keys, sequence):
                node = returnObject._findByID(returnObject._tree, key)
                if node:
                    returnObject._replaceNodeContent(node, value)
        else:
            # No keys, so set the values in the order they appear.  This is
            # a depth-first in-order search, pruned wherever we find a match
            # (otherwise we'd start assigning into places we'd just
            # assigned).  We reverse the sequences so we can use pop().
            stack = returnObject._tree.getElementNode().children[:]
            stack.reverse()
            sequence.reverse()
            while stack and sequence:
                element = stack.pop()
                if element.attributes.has_key('id'):
                    self._replaceNodeContent(element, sequence.pop())
                else:
                    for index in range(len(element.children)):
                        stack.append(element.children[-1 - index])

            if sequence:
                raise TypeError, "not all arguments converted"
            while stack:
                if stack.pop().attributes.has_key('id'):
                    raise TypeError, "not enough arguments"

        return returnObject

    def __add__(self, other):
        """`object1 + object2` turns both objects into strings and returns the
        concatenation of the strings:

        >>> a = Meld('<html><span id="x">1</span></html>')
        >>> b = Meld('<html><span id="y">2</span></html>')
        >>> c = Meld('<html><span id="z">3</span></html>')
        >>> print a + b
        <html><span id="x">1</span></html><html><span id="y">2</span></html>
        >>> print a.x + b.y + c.z
        <span id="x">1</span><span id="y">2</span><span id="z">3</span>
        """

        if isinstance(other, Meld):
            other = other._tree.toText()
        return self._tree.toText() + other

    def __radd__(self, other):
        """See `__add__`"""
        # The case where `other` is a Meld can never happen, because
        # __add__ will be called instead.
        return other + self._tree.toText()

    def __str__(self):
        """Returns the XML that this `Meld` represents.  Don't call
        this directly - instead convert a `Meld` to a string using
        `str(object)`.  `print` does this automatically, which is why
        none of the examples calls `str`."""
        return str(self._tree.toText())


###########################################################################
##
## Self-test code.
##

# Extra tests, for features that aren't tested by the (visible) docstrings:
__test__ = {
'_Node': _Node,
'_RootNode': _RootNode,
'_ElementNode': _ElementNode,
'_TextNode': _TextNode,
'_TreeGenerator': _TreeGenerator,
'_generateTree': _generateTree,

'<?xml>': """
>>> print Meld('''<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
... <html>Stuff</html>''')
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<html>Stuff</html>
""",

'DOCTYPE (system)': """
>>> print Meld('''<!DOCTYPE NAME SYSTEM "name.dtd">
... <name>Stuff</name>''')
<!DOCTYPE name SYSTEM "name.dtd">
<name>Stuff</name>
""",

'DOCTYPE (small)': """
>>> print Meld('''<!DOCTYPE name PUBLIC "-//ORG//NAME//EN" "name.dtd">
... <name>Stuff</name>''')
<!DOCTYPE name PUBLIC "-//ORG//NAME//EN" "name.dtd">
<name>Stuff</name>
""",

'DOCTYPE (full)': """
>>> print Meld('''<!DOCTYPE name [
...     <!ELEMENT terms (hhItem1, hhItem2)>
...     <!ELEMENT hhItem1 (#PCDATA)>
...     <!ELEMENT hhItem2 (#PCDATA)>
... ]>
... <name>Stuff</name>''')
<!DOCTYPE name [
    <!ELEMENT terms (hhItem1, hhItem2)>
    <!ELEMENT hhItem1 (#PCDATA)>
    <!ELEMENT hhItem2 (#PCDATA)>
]>
<name>Stuff</name>
""",

'DOCTYPE (HTML hackery)': """
>>> html = '''<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
... <html>Stuff</html>'''
>>> print Meld(html)
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>Stuff</html>
""",

'XML proc': """
>>> print Meld('''<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
... <?codewarrior exportversion="1.0.1" ideversion="4.2" ?>
... <!DOCTYPE PROJECT [
... <!ELEMENT PROJECT (TARGETLIST, TARGETORDER, GROUPLIST, DESIGNLIST?)>
... ]>
... <PROJECT>Stuff</PROJECT>''')
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<?codewarrior exportversion="1.0.1" ideversion="4.2" ?>
<!DOCTYPE PROJECT [
<!ELEMENT PROJECT (TARGETLIST, TARGETORDER, GROUPLIST, DESIGNLIST?)>
]>
<PROJECT>Stuff</PROJECT>
""",

'comment': """
>>> page = Meld('''<x><!-- Comment --></x>''')
>>> print page
<x><!-- Comment --></x>
""",

'entities and charrefs': """
>>> page = Meld('''<html><body>&bull; This "and&#160;that"...
... <span id="s" title="&quot;Quoted&quot; &amp; Not">x</span></body></html>''')
>>> print page.s.title
"Quoted" & Not
>>> page.s.title = page.s.title + " <>"
>>> print page.s.title
"Quoted" & Not <>
>>> print page.s
<span id="s" title="&quot;Quoted&quot; &amp; Not &lt;&gt;">x</span>
""",

'self-closing tags': """
>>> page = Meld('''<span id="spam">Stuff</span>''')
>>> page.spam = ""
>>> print page
<span id="spam"/>
>>> page = Meld('''<textarea name="spam"/>''')  # nonSelfClose special case
>>> print page
<textarea name="spam"></textarea>
""",

'assigning to _content': """
>>> page = Meld('''<html><span id="s">Old</span></html>''')
>>> page.s._content = "New"
>>> print page
<html><span id="s">New</span></html>
>>> page._content = "All new"
>>> print page
<html>All new</html>
""",

'deleting _content': """
>>> page = Meld('''<html><span id="s">Old</span></html>''')
>>> del page.s._content
>>> print page
<html><span id="s"/></html>
""",

'constructing from an unknown type': """
>>> page = Meld(1)
Traceback (most recent call last):
...
TypeError: Melds must be constructed from ASCII strings
""",

'accessing a non-existent attribute': """
>>> page = Meld('<html></html>')
>>> print page.spam
Traceback (most recent call last):
...
AttributeError: No element or attribute named 'spam'
>>> del page.spam
Traceback (most recent call last):
...
AttributeError: No element or attribute named 'spam'
""",

'cdata': """
>>> html = '''<html><script id="cdataExample">//<![CDATA[
... window.alert("This is not valid XML: <spam> << & >> etc.");
... //]]>
... </script></html>'''
>>> page = Meld(html)
>>> print page.cdataExample
<script id="cdataExample">//<![CDATA[
window.alert("This is not valid XML: <spam> << & >> etc.");
//]]>
</script>
""",

'add new things':"""
>>> page = Meld('''<html><textarea id="empty"></textarea></html>''')
>>> page.empty = "Not any more"
>>> page.empty.cols = 60
>>> print page
<html><textarea cols="60" id="empty">Not any more</textarea></html>
""",

'readonly': """
>>> page = Meld('''<html><span id='no'>No!</span></html>''', readonly=True)
>>> page.no = "Yes?"
Traceback (most recent call last):
...
ReadOnlyError: You can't modify this read-only Meld object

>>> page.no.attribute = "Yes?"
Traceback (most recent call last):
...
ReadOnlyError: You can't modify this read-only Meld object

>>> page.no += "More?"
Traceback (most recent call last):
...
ReadOnlyError: You can't modify this read-only Meld object

>>> del page.no
Traceback (most recent call last):
...
ReadOnlyError: You can't modify this read-only Meld object
""",

'copy from one to another': """
>>> a = Meld('<html><span id="one">One</span></html>')
>>> b = Meld('<html><span id="two">Two</span></html>')
>>> a.one = b.two
>>> print a
<html><span id="one"><span id="two">Two</span></span></html>
>>> b.two = "New"
>>> print a  # Checking for side-effects
<html><span id="one"><span id="two">Two</span></span></html>
""",

'mixed-type add, radd and iadd': """
>>> a = Meld('<html><span id="one">1</span></html>')
>>> print a.one + "x"
<span id="one">1</span>x
>>> print "x" + a.one
x<span id="one">1</span>
>>> a.one += "y<z></z>"
>>> print a
<html><span id="one">1y<z/></span></html>
""",

'no unicode': r"""
>>> u = Meld(u'<html><span id="one">One</span></html>')
Traceback (most recent call last):
...
TypeError: Melds must be constructed from ASCII strings
""",

'private attributes': """
>>> page = Meld('<html>x</html>')
>>> page._private = "Spam"
>>> print repr(page._private)
'Spam'
>>> print page
<html>x</html>
>>> del page._private
>>> print repr(page._private)
Traceback (most recent call last):
...
AttributeError: _private
>>> del page._private
Traceback (most recent call last):
...
AttributeError: _private
>>> print page
<html>x</html>
""",

'bad XML characters': """
>>> page = Meld('''<x>
... Valentines Day Special \x96 2 bikinis for the price of one \x01
... </x>''')    # No exception.
>>> print page
<x>
Valentines Day Special &#150; 2 bikinis for the price of one ?
</x>
"""
}


# Entrian.Coverage: Pragma Stop

def test():
    """Tests the `PyMeldLite` module, performing code coverage analysis if
    `Entrian.Coverage` is available.  Returns `(failed, total)`, a la
    `doctest.testmod`."""

    import doctest
    try:
        from Entrian import Coverage
        Coverage.start('PyMeldLite')
    except ImportError:
        Coverage = False

    import PyMeldLite
    result = doctest.testmod(PyMeldLite)

    if Coverage:
        analysis = Coverage.getAnalysis()
        analysis.printAnalysis()
    return result

if __name__ == '__main__':
    failed, total = test()
    if failed == 0:     # Else `doctest.testmod` prints the failures.
        print "All %d tests passed." % total