Hello ${hello}

Index: /trunk/COPYING =================================================================== --- /trunk/COPYING (revision 30) +++ /trunk/COPYING (revision 30) @@ -0,0 +1,28 @@ +Copyright (C) 2006 Christopher Lenz +All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions +are met: + + 1. Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + 2. Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in + the documentation and/or other materials provided with the + distribution. + 3. The name of the author may not be used to endorse or promote + products derived from this software without specific prior + written permission. + +THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS +OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED +WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY +DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE +GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS +INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER +IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR +OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN +IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. Index: /trunk/README.txt =================================================================== --- /trunk/README.txt (revision 30) +++ /trunk/README.txt (revision 30) @@ -0,0 +1,11 @@ +About Markup +============ + +Markup is a Python library that provides a integrated set of components +for parsing, generating, and processing HTML or XML content in a uniform +manner. The major feature is a template language, which is heavily +inspired by Kid. + +For more information visit the Markup web site: + + Index: /trunk/examples/basic/kidrun.py =================================================================== --- /trunk/examples/basic/kidrun.py (revision 20) +++ /trunk/examples/basic/kidrun.py (revision 30) @@ -7,6 +7,5 @@ def test(): base_path = os.path.dirname(os.path.abspath(__file__)) - kid.path = kid.TemplatePath([os.path.join(base_path, 'common'), - os.path.join(base_path, 'module')]) + kid.path = kid.TemplatePath([base_path]) ctxt = dict(hello='', hey='ZYX', bozz=None, Index: /trunk/examples/basic/layout.html =================================================================== --- /trunk/examples/basic/layout.html (revision 30) +++ /trunk/examples/basic/layout.html (revision 30) @@ -0,0 +1,15 @@ +

+ + Hello ${hello} + + +

reference me, please

+ Hello ${name.title()} +

+ + Hello ${select('@name')} + + +

Index: /trunk/examples/basic/layout.kid =================================================================== --- /trunk/examples/basic/layout.kid (revision 30) +++ /trunk/examples/basic/layout.kid (revision 30) @@ -0,0 +1,15 @@ +

+ + Hello ${hello} + + +

reference me, please

+ Hello ${name.title()} +

+ + Hello ${item.get('name')} + + +

Index: /trunk/examples/basic/run.py =================================================================== --- /trunk/examples/basic/run.py (revision 20) +++ /trunk/examples/basic/run.py (revision 30) @@ -10,7 +10,5 @@ def test(): base_path = os.path.dirname(os.path.abspath(__file__)) - loader = TemplateLoader([os.path.join(base_path, 'common'), - os.path.join(base_path, 'module')], - auto_reload=True) + loader = TemplateLoader([base_path], auto_reload=True) start = datetime.now() Index: /trunk/examples/basic/test.html =================================================================== --- /trunk/examples/basic/test.html (revision 30) +++ /trunk/examples/basic/test.html (revision 30) @@ -0,0 +1,23 @@ + + + + + +

Item $prefix${item.split()[-1]}

+ ${macro1()} ${macro1()} ${macro1()} + ${macro2('john')} + ${macro2('kate', classname='collapsed')} +

Replace me

+ + + Hello Silicon + + Index: /trunk/examples/basic/test.kid =================================================================== --- /trunk/examples/basic/test.kid (revision 30) +++ /trunk/examples/basic/test.kid (revision 30) @@ -0,0 +1,21 @@ + + + +

Item $prefix${item.split()[-1]}

+ ${macro1()} ${macro1()} ${macro1()} + ${macro2('john')} + ${macro2('kate', classname='collapsed')} +

Replace me

+ + + Hello Silicon + + Index: /trunk/examples/includes/common/macros.html =================================================================== --- /trunk/examples/includes/common/macros.html (revision 30) +++ /trunk/examples/includes/common/macros.html (revision 30) @@ -0,0 +1,12 @@ +

reference me, please

+ Hello ${name.title()} +

+ + Hello ${select('@name')} + + +

Index: /trunk/examples/includes/module/test.html =================================================================== --- /trunk/examples/includes/module/test.html (revision 30) +++ /trunk/examples/includes/module/test.html (revision 30) @@ -0,0 +1,22 @@ + + + + + +

Item ${item.split()[-1]}

+ ${macro1()} ${macro1()} ${macro1()} + ${macro2('john')} + ${macro2('kate', classname='collapsed')} +

Replace me

+ + + Hello Silicon + + Index: /trunk/examples/includes/run.py =================================================================== --- /trunk/examples/includes/run.py (revision 30) +++ /trunk/examples/includes/run.py (revision 30) @@ -0,0 +1,49 @@ +#!/usr/bin/python +# -*- coding: utf-8 -*- + +import os +import sys +import timing + +from markup.template import Context, TemplateLoader + +def test(): + base_path = os.path.dirname(os.path.abspath(__file__)) + loader = TemplateLoader([os.path.join(base_path, 'skins'), + os.path.join(base_path, 'module'), + os.path.join(base_path, 'common')]) + + timing.start() + tmpl = loader.load('test.html') + timing.finish() + print ' --> parse stage: %dms' % timing.milli() + + data = dict(hello='', skin='default', hey='ZYX', bozz=None, + items=['Number %d' % num for num in range(1, 15)]) + + print tmpl.generate(Context(**data)).render(method='html') + + times = [] + for i in range(100): + timing.start() + list(tmpl.generate(Context(**data))) + timing.finish() + times.append(timing.milli()) + sys.stdout.write('.') + sys.stdout.flush() + print + + print ' --> render stage: %dms (avg), %dms (min), %dms (max)' % ( + sum(times) / len(times), min(times), max(times)) + +if __name__ == '__main__': + if '-p' in sys.argv: + import hotshot, hotshot.stats + prof = hotshot.Profile("template.prof") + benchtime = prof.runcall(test) + stats = hotshot.stats.load("template.prof") + stats.strip_dirs() + stats.sort_stats('time', 'calls') + stats.print_stats() + else: + test() Index: /trunk/examples/includes/skins/default/footer.html =================================================================== --- /trunk/examples/includes/skins/default/footer.html (revision 30) +++ /trunk/examples/includes/skins/default/footer.html (revision 30) @@ -0,0 +1,4 @@ + Index: /trunk/examples/includes/skins/default/header.html =================================================================== --- /trunk/examples/includes/skins/default/header.html (revision 30) +++ /trunk/examples/includes/skins/default/header.html (revision 30) @@ -0,0 +1,3 @@ + Index: /trunk/examples/includes/skins/default/layout.html =================================================================== --- /trunk/examples/includes/skins/default/layout.html (revision 30) +++ /trunk/examples/includes/skins/default/layout.html (revision 30) @@ -0,0 +1,17 @@ + + + + Hello ${hello} + + + + +

+ ${select('body/*')} +

+ + + Index: /trunk/markup/__init__.py =================================================================== --- /trunk/markup/__init__.py (revision 20) +++ /trunk/markup/__init__.py (revision 30) @@ -6,9 +6,9 @@ # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. """This package provides various means for generating and processing web markup @@ -48,10 +48,9 @@ >>> from markup.builder import tag ->>> doc = tag.DOC(tag.TITLE('My document'), lang='en') +>>> doc = tag.doc(tag.title('My document'), lang='en') >>> doc.generate().render(method='html') 'My document' - """ from markup.core import * -from markup.input import XML, HTML +from markup.input import ParseError, XML, HTML Index: /trunk/markup/builder.py =================================================================== --- /trunk/markup/builder.py (revision 20) +++ /trunk/markup/builder.py (revision 30) @@ -6,9 +6,9 @@ # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. from markup.core import Attributes, Namespace, QName, Stream @@ -18,4 +18,7 @@ class Fragment(object): + """Represents a markup fragment, which is basically just a list of element + or text nodes. + """ __slots__ = ['children'] @@ -49,5 +52,5 @@ def generate(self): - """Generator that yield tags and text nodes as strings.""" + """Return a markup event stream for the fragment.""" def _generate(): for child in self.children: @@ -161,5 +164,5 @@ def generate(self): - """Generator that yield tags and text nodes as strings.""" + """Return a markup event stream for the fragment.""" def _generate(): yield Stream.START, (self.tag, self.attrib), (-1, -1) @@ -171,14 +174,48 @@ class ElementFactory(object): + """Factory for `Element` objects. + + A new element is created simply by accessing a correspondingly named + attribute of the factory object: + + >>> factory = ElementFactory() + >>> print factory.foo + + >>> print factory.foo(id=2) + + + A factory can also be bound to a specific namespace: + + >>> factory = ElementFactory('http://www.w3.org/1999/xhtml') + >>> print factory.html(lang="en") + + + The namespace for a specific element can be altered on an existing factory + by specifying the new namespace using item access: + + >>> factory = ElementFactory() + >>> print factory.html(factory['http://www.w3.org/2000/svg'].g(id=3)) + + + Usually, the `ElementFactory` class is not be used directly. Rather, the + `tag` instance should be used to create elements. + """ def __init__(self, namespace=None): - if not isinstance(namespace, Namespace): + """Create the factory, optionally bound to the given namespace. + + @param namespace: the namespace URI for any created elements, or `None` + for no namespace + """ + if namespace and not isinstance(namespace, Namespace): namespace = Namespace(namespace) self.namespace = namespace def __getitem__(self, namespace): + """Return a new factory that is bound to the specified namespace.""" return ElementFactory(namespace) def __getattr__(self, name): + """Create an `Element` with the given name.""" return Element(self.namespace and self.namespace[name] or name) Index: /trunk/markup/core.py =================================================================== --- /trunk/markup/core.py (revision 20) +++ /trunk/markup/core.py (revision 30) @@ -6,9 +6,9 @@ # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. """Core classes for markup processing.""" @@ -58,5 +58,5 @@ """Initialize the stream with a sequence of markup events. - @oaram events: a sequence or iterable providing the events + @param events: a sequence or iterable providing the events """ self.events = events @@ -112,5 +112,5 @@ 'html': output.HTMLSerializer}[method] else: - assert issubclass(cls, serializers.Serializer) + assert issubclass(cls, output.Serializer) serializer = cls(**kwargs) @@ -169,5 +169,7 @@ of `(name, value)` tuples. """ - list.__init__(self, map(lambda (k, v): (QName(k), v), attrib or [])) + if attrib is None: + attrib = [] + list.__init__(self, [(QName(name), value) for name, value in attrib]) def __contains__(self, name): @@ -175,5 +177,5 @@ name. """ - return name in [attr for attr, value in self] + return name in [attr for attr, _ in self] def get(self, name, default=None): @@ -217,8 +219,8 @@ __slots__ = [] - def __new__(self, text='', *args): + def __new__(cls, text='', *args): if args: text %= tuple([escape(arg) for arg in args]) - return unicode.__new__(self, text) + return unicode.__new__(cls, text) def __add__(self, other): @@ -258,5 +260,6 @@ else: # character entity ref = match.group(2) - if keepxmlentities and ref in ('amp', 'apos', 'gt', 'lt', 'quot'): + if keepxmlentities and ref in ('amp', 'apos', 'gt', 'lt', + 'quot'): return '&%s;' % ref try: Index: /trunk/markup/eval.py =================================================================== --- /trunk/markup/eval.py (revision 20) +++ /trunk/markup/eval.py (revision 30) @@ -6,9 +6,11 @@ # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. + +"""Support for "safe" evaluation of Python expressions.""" import __builtin__ @@ -102,8 +104,17 @@ def __init__(self, source): + """Create the expression. + + @param source: the expression as string + """ self.source = source self.ast = None def evaluate(self, data): + """Evaluate the expression against the given data dictionary. + + @param data: a mapping containing the data to evaluate against + @return: the result of the evaluation + """ if not self.ast: self.ast = compiler.parse(self.source, 'eval') Index: /trunk/markup/filters.py =================================================================== --- /trunk/markup/filters.py (revision 20) +++ /trunk/markup/filters.py (revision 30) @@ -6,9 +6,9 @@ # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. """Implementation of a number of stream filters.""" @@ -54,5 +54,4 @@ in_fallback = False include_href, fallback_stream = None, None - indent = 0 for kind, data, pos in stream: @@ -63,5 +62,4 @@ if tag.localname == 'include': include_href = attrib.get('href') - indent = pos[1] elif tag.localname == 'fallback': in_fallback = True @@ -74,5 +72,6 @@ raise TemplateError('Include misses required ' 'attribute "href"') - template = self.loader.load(include_href) + template = self.loader.load(include_href, + relative_to=pos[0]) for event in template.generate(ctxt): yield event @@ -86,5 +85,4 @@ include_href = None fallback_stream = None - indent = 0 elif data.localname == 'fallback': Index: /trunk/markup/input.py =================================================================== --- /trunk/markup/input.py (revision 20) +++ /trunk/markup/input.py (revision 30) @@ -6,9 +6,9 @@ # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. from xml.parsers import expat @@ -19,16 +19,44 @@ import HTMLParser as html import htmlentitydefs -import re from StringIO import StringIO from markup.core import Attributes, Markup, QName, Stream + + +class ParseError(Exception): + """Exception raised when fatal syntax errors are found in the input being + parsed.""" + + def __init__(self, message, filename='', lineno=-1, offset=-1): + Exception.__init__(self, message) + self.filename = filename + self.lineno = lineno + self.offset = offset class XMLParser(object): """Generator-based XML parser based on roughly equivalent code in - Kid/ElementTree.""" - - def __init__(self, source): + Kid/ElementTree. + + The parsing is initiated by iterating over the parser object: + + >>> parser = XMLParser(StringIO('Foo')) + >>> for kind, data, pos in parser: + ... print kind, data + START (u'root', [(u'id', u'2')]) + START (u'child', []) + TEXT Foo + END child + END root + """ + + def __init__(self, source, filename=None): + """Initialize the parser for the given XML text. + + @param source: the XML text as a file-like object + @param filename: the name of the file, if appropriate + """ self.source = source + self.filename = filename # Setup the Expat parser @@ -49,62 +77,72 @@ # Location reporting is only support in Python >= 2.4 if not hasattr(parser, 'CurrentLineNumber'): - self.getpos = self._getpos_unknown + self._getpos = self._getpos_unknown self.expat = parser - self.queue = [] + self._queue = [] def __iter__(self): - bufsize = 4 * 1024 # 4K - done = False - while True: - while not done and len(self.queue) == 0: - data = self.source.read(bufsize) - if data == '': # end of data - if hasattr(self, 'expat'): - self.expat.Parse('', True) - del self.expat # get rid of circular references - done = True - else: - self.expat.Parse(data, False) - for event in self.queue: - yield event - self.queue = [] - if done: - break + try: + bufsize = 4 * 1024 # 4K + done = False + while True: + while not done and len(self._queue) == 0: + data = self.source.read(bufsize) + if data == '': # end of data + if hasattr(self, 'expat'): + self.expat.Parse('', True) + del self.expat # get rid of circular references + done = True + else: + self.expat.Parse(data, False) + for event in self._queue: + yield event + self._queue = [] + if done: + break + except expat.ExpatError, e: + msg = str(e) + if self.filename: + msg += ', in ' + self.filename + raise ParseError(msg, self.filename, e.lineno, e.offset) + + def _enqueue(self, kind, data, pos=None): + if pos is None: + pos = self._getpos() + self._queue.append((kind, data, pos)) def _getpos_unknown(self): - return (-1, -1) - - def getpos(self): - return self.expat.CurrentLineNumber, self.expat.CurrentColumnNumber + return (self.filename or '', -1, -1) + + def _getpos(self): + return (self.filename or '', self.expat.CurrentLineNumber, + self.expat.CurrentColumnNumber) def _handle_start(self, tag, attrib): - self.queue.append((Stream.START, (QName(tag), Attributes(attrib.items())), - self.getpos())) + self._enqueue(Stream.START, (QName(tag), Attributes(attrib.items()))) def _handle_end(self, tag): - self.queue.append((Stream.END, QName(tag), self.getpos())) + self._enqueue(Stream.END, QName(tag)) def _handle_data(self, text): - self.queue.append((Stream.TEXT, text, self.getpos())) + self._enqueue(Stream.TEXT, text) def _handle_prolog(self, version, encoding, standalone): - self.queue.append((Stream.PROLOG, (version, encoding, standalone), - self.getpos())) + self._enqueue(Stream.PROLOG, (version, encoding, standalone)) def _handle_doctype(self, name, sysid, pubid, has_internal_subset): - self.queue.append((Stream.DOCTYPE, (name, pubid, sysid), self.getpos())) + self._enqueue(Stream.DOCTYPE, (name, pubid, sysid)) def _handle_start_ns(self, prefix, uri): - self.queue.append((Stream.START_NS, (prefix or '', uri), self.getpos())) + self._enqueue(Stream.START_NS, (prefix or '', uri)) def _handle_end_ns(self, prefix): - self.queue.append((Stream.END_NS, prefix or '', self.getpos())) + self._enqueue(Stream.END_NS, prefix or '') def _handle_pi(self, target, data): - self.queue.append((Stream.PI, (target, data), self.getpos())) + self._enqueue(Stream.PI, (target, data)) def _handle_comment(self, text): - self.queue.append((Stream.COMMENT, text, self.getpos())) + self._enqueue(Stream.COMMENT, text) def _handle_other(self, text): @@ -113,7 +151,7 @@ try: text = unichr(htmlentitydefs.name2codepoint[text[1:-1]]) - self.queue.append((Stream.TEXT, text, self.getpos())) + self._enqueue(Stream.TEXT, text) except KeyError: - lineno, offset = self.getpos() + lineno, offset = self._getpos() raise expat.error("undefined entity %s: line %d, column %d" % (text, lineno, offset)) @@ -124,9 +162,20 @@ -class HTMLParser(html.HTMLParser): +class HTMLParser(html.HTMLParser, object): """Parser for HTML input based on the Python `HTMLParser` module. This class provides the same interface for generating stream events as `XMLParser`, and attempts to automatically balance tags. + + The parsing is initiated by iterating over the parser object: + + >>> parser = HTMLParser(StringIO('

')) + >>> for kind, data, pos in parser: + ... print kind, data + START (u'ul', [(u'compact', u'compact')]) + START (u'li', []) + TEXT Foo + END li + END ul """ @@ -135,36 +184,57 @@ 'param']) - def __init__(self, source): + def __init__(self, source, filename=None): html.HTMLParser.__init__(self) self.source = source - self.queue = [] + self.filename = filename + self._queue = [] self._open_tags = [] def __iter__(self): - bufsize = 4 * 1024 # 4K - done = False - while True: - while not done and len(self.queue) == 0: - data = self.source.read(bufsize) - if data == '': # end of data - self.close() - done = True - else: - self.feed(data) - for kind, data, pos in self.queue: - yield kind, data, pos - self.queue = [] - if done: - open_tags = self._open_tags - open_tags.reverse() - for tag in open_tags: - yield Stream.END, QName(tag), pos - break + try: + bufsize = 4 * 1024 # 4K + done = False + while True: + while not done and len(self._queue) == 0: + data = self.source.read(bufsize) + if data == '': # end of data + self.close() + done = True + else: + self.feed(data) + for kind, data, pos in self._queue: + yield kind, data, pos + self._queue = [] + if done: + open_tags = self._open_tags + open_tags.reverse() + for tag in open_tags: + yield Stream.END, QName(tag), pos + break + except html.HTMLParseError, e: + msg = '%s: line %d, column %d' % (e.msg, e.lineno, e.offset) + if self.filename: + msg += ', in %s' % self.filename + raise ParseError(msg, self.filename, e.lineno, e.offset) + + def _enqueue(self, kind, data, pos=None): + if pos is None: + pos = self._getpos() + self._queue.append((kind, data, pos)) + + def _getpos(self): + lineno, column = self.getpos() + return (self.filename, lineno, column) def handle_starttag(self, tag, attrib): - pos = self.getpos() - self.queue.append((Stream.START, (QName(tag), Attributes(attrib)), pos)) + fixed_attrib = [] + for name, value in attrib: # Fixup minimized attributes + if value is None: + value = name + fixed_attrib.append((name, unicode(value))) + + self._enqueue(Stream.START, (QName(tag), Attributes(fixed_attrib))) if tag in self._EMPTY_ELEMS: - self.queue.append((Stream.END, QName(tag), pos)) + self._enqueue(Stream.END, QName(tag)) else: self._open_tags.append(tag) @@ -172,29 +242,27 @@ def handle_endtag(self, tag): if tag not in self._EMPTY_ELEMS: - pos = self.getpos() while self._open_tags: open_tag = self._open_tags.pop() if open_tag.lower() == tag.lower(): break - self.queue.append((Stream.END, QName(open_tag), pos)) - self.queue.append((Stream.END, QName(tag), pos)) + self._enqueue(Stream.END, QName(open_tag)) + self._enqueue(Stream.END, QName(tag)) def handle_data(self, text): - self.queue.append((Stream.TEXT, text, self.getpos())) + self._enqueue(Stream.TEXT, text) def handle_charref(self, name): - self.queue.append((Stream.TEXT, Markup('&#%s;' % name), self.getpos())) + self._enqueue(Stream.TEXT, Markup('&#%s;' % name)) def handle_entityref(self, name): - self.queue.append((Stream.TEXT, Markup('&%s;' % name), self.getpos())) + self._enqueue(Stream.TEXT, Markup('&%s;' % name)) def handle_pi(self, data): target, data = data.split(maxsplit=1) data = data.rstrip('?') - self.queue.append((Stream.PI, (target.strip(), data.strip()), - self.getpos())) + self._enqueue(Stream.PI, (target.strip(), data.strip())) def handle_comment(self, text): - self.queue.append((Stream.COMMENT, text, self.getpos())) + self._enqueue(Stream.COMMENT, text) Index: /trunk/markup/output.py =================================================================== --- /trunk/markup/output.py (revision 20) +++ /trunk/markup/output.py (revision 30) @@ -6,9 +6,9 @@ # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. """This module provides different kinds of serialization methods for XML event @@ -22,5 +22,4 @@ from markup.core import Markup, Namespace, QName, Stream -from markup.filters import WhitespaceFilter __all__ = ['Serializer', 'XMLSerializer', 'HTMLSerializer'] @@ -31,4 +30,10 @@ def serialize(self, stream): + """Must be implemented by concrete subclasses to serialize the given + stream. + + This method must be implemented as a generator, producing the + serialized output incrementally as unicode strings. + """ raise NotImplementedError @@ -38,5 +43,5 @@ >>> from markup.builder import tag - >>> elem = tag.DIV(tag.A(href='foo'), tag.BR, tag.HR(noshade=True)) + >>> elem = tag.div(tag.a(href='foo'), tag.br, tag.hr(noshade=True)) >>> print ''.join(XMLSerializer().serialize(elem.generate()))

@@ -47,5 +52,5 @@ ns_mapping = {} - stream = PushbackIterator(stream) + stream = _PushbackIterator(stream) for kind, data, pos in stream: @@ -82,9 +87,5 @@ attrname = attr.localname if attr.namespace: - try: - prefix = ns_mapping[attr.namespace] - except KeyError: - # FIXME: synthesize a prefix for the attribute? - prefix = '' + prefix = ns_mapping.get(attr.namespace) if prefix: attrname = prefix + ':' + attrname @@ -104,10 +105,7 @@ tagname = tag.localname if tag.namespace: - try: - prefix = ns_mapping[tag.namespace] - if prefix: - tagname = prefix + ':' + tag.localname - except KeyError: - pass + prefix = ns_mapping.get(tag.namespace) + if prefix: + tagname = prefix + ':' + tag.localname yield Markup('' % tagname) @@ -120,5 +118,5 @@ >>> from markup.builder import tag - >>> elem = tag.DIV(tag.A(href='foo'), tag.BR, tag.HR(noshade=True)) + >>> elem = tag.div(tag.a(href='foo'), tag.br, tag.hr(noshade=True)) >>> print ''.join(HTMLSerializer().serialize(elem.generate()))

@@ -137,5 +135,5 @@ ns_mapping = {} - stream = PushbackIterator(stream) + stream = _PushbackIterator(stream) for kind, data, pos in stream: @@ -180,5 +178,5 @@ -class PushbackIterator(object): +class _PushbackIterator(object): """A simple wrapper for iterators that allows pushing items back on the queue via the `pushback()` method. Index: /trunk/markup/path.py =================================================================== --- /trunk/markup/path.py (revision 20) +++ /trunk/markup/path.py (revision 30) @@ -1,14 +1,14 @@ # -*- coding: utf-8 -*- # -# Copyright (C) 2006 Edgewall Software +# Copyright (C) 2006 Christopher Lenz # All rights reserved. # # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. """Basic support for evaluating XPath expressions against streams.""" @@ -20,83 +20,22 @@ __all__ = ['Path'] -_QUOTES = (("'", "'"), ('"', '"')) class Path(object): - """Basic XPath support on markup event streams. + """Implements basic XPath support on streams. - >>> from markup.input import XML - - Selecting specific tags: - - >>> Path('root').select(XML('')).render() - '' - >>> Path('//root').select(XML('')).render() - '' - - Using wildcards for tag names: - - >>> Path('*').select(XML('')).render() - '' - >>> Path('//*').select(XML('')).render() - '' - - Selecting attribute values: - - >>> Path('@foo').select(XML('')).render() - '' - >>> Path('@foo').select(XML('')).render() - 'bar' - - Selecting descendants: - - >>> Path("root/*").select(XML('')).render() - '' - >>> Path("root/bar").select(XML('')).render() - '' - >>> Path("root/baz").select(XML('')).render() - '' - >>> Path("root/foo/*").select(XML('')).render() - '' - - Selecting text nodes: - >>> Path("item/text()").select(XML('Foo')).render() - 'Foo' - >>> Path("item/text()").select(XML('FooBar')).render() - 'FooBar' - - Skipping ancestors: - - >>> Path("foo/bar").select(XML('')).render() - '' - >>> Path("foo/*").select(XML('')).render() - '' - >>> Path("root/bar").select(XML('')).render() - '' - >>> Path("root/bar").select(XML('')).render() - '' - >>> Path("root/*/bar").select(XML('')).render() - '' - >>> Path("root//bar").select(XML('')).render() - '' - >>> Path("root//bar").select(XML('')).render() - '' - - Using simple attribute predicates: - >>> Path("root/item[@important]").select(XML('')).render() - '' - >>> Path('root/item[@important="very"]').select(XML('')).render() - '' - >>> Path("root/item[@important='very']").select(XML('')).render() - '' - >>> Path("root/item[@important!='very']").select( - ... XML('')).render() - '' + Instances of this class represent a "compiled" XPath expression, and provide + methods for testing the path against a stream, as well as extracting a + substream matching that path. """ - _TOKEN_RE = re.compile('(::|\.\.||[/.:\[\]@=!])|' '([^/:\[\]@=!\s]+)|' '\s+') + _QUOTES = (("'", "'"), ('"', '"')) def __init__(self, text): + """Create the path object from a string. + + @param text: the path expression + """ self.source = text @@ -113,5 +52,5 @@ elif op.startswith('('): if cur_tag == 'text': - steps[-1] = (False, self.fn_text(), []) + steps[-1] = (False, self._FunctionText(), []) else: raise NotImplementedError('XPath function "%s" not ' @@ -124,21 +63,23 @@ if cur_op == '@': if tag == '*': - node_test = self.any_attribute() + node_test = self._AnyAttribute() else: - node_test = self.attribute_by_name(tag) + node_test = self._AttributeByName(tag) else: if tag == '*': - node_test = self.any_element() + node_test = self._AnyElement() elif in_predicate: - if len(tag) > 1 and (tag[0], tag[-1]) in _QUOTES: - node_test = self.literal_string(tag[1:-1]) + if len(tag) > 1 and (tag[0], tag[-1]) in self._QUOTES: + node_test = self._LiteralString(tag[1:-1]) if cur_op == '=': - node_test = self.op_eq(steps[-1][2][-1], node_test) + node_test = self._OperatorEq(steps[-1][2][-1], + node_test) steps[-1][2].pop() elif cur_op == '!=': - node_test = self.op_neq(steps[-1][2][-1], node_test) + node_test = self._OperatorNeq(steps[-1][2][-1], + node_test) steps[-1][2].pop() else: - node_test = self.element_by_name(tag) + node_test = self._ElementByName(tag) if in_predicate: steps[-1][2].append(node_test) @@ -153,6 +94,13 @@ def select(self, stream): + """Returns a substream of the given stream that matches the path. + + If there are no matches, this method returns an empty stream. + + @param stream: the stream to select from + @return: the substream matching the path, or an empty stream + """ stream = iter(stream) - def _generate(tests): + def _generate(): test = self.test() for kind, data, pos in stream: @@ -171,12 +119,18 @@ elif result: yield result - return Stream(_generate(self.steps)) + return Stream(_generate()) def test(self): + """Returns a function that can be used to track whether the path matches + a specific stream event. + + The function returned expects the positional arguments `kind`, `data`, + and `pos`, i.e. basically an unpacked stream event. If the path matches + the event, the function returns the match (for example, a `START` or + `TEXT` event.) Otherwise, it returns `None` or `False`. + """ stack = [0] # stack of cursors into the location path def _test(kind, data, pos): - #print '\nTracker %r test [%s] %r' % (self, kind, data) - if not stack: return False @@ -192,5 +146,4 @@ closure, node_test, predicates = self.steps[stack[-1]] - #print ' Testing against %r' % node_test matched = node_test(kind, data, pos) if matched and predicates: @@ -202,15 +155,13 @@ if matched: if stack[-1] == len(self.steps) - 1: - #print ' Last step %r... returned %r' % (node_test, matched) return matched - #print ' Matched intermediate step %r... proceed to next step %r' % (node_test, self.steps[stack[-1] + 1]) stack[-1] += 1 elif kind is Stream.START and not closure: - # FIXME: If this step is not a closure, it cannot be matched - # until the current element is closed... so we need to - # move the cursor back to the last closure and retest - # that against the current element + # If this step is not a closure, it cannot be matched until the + # current element is closed... so we need to move the cursor + # back to the last closure and retest that against the current + # element closures = [step for step in self.steps[:stack[-1]] if step[0]] closures.reverse() @@ -227,6 +178,7 @@ return _test - class any_element(object): - def __call__(self, kind, data, pos): + class _AnyElement(object): + """Node test that matches any element.""" + def __call__(self, kind, *_): if kind is Stream.START: return True @@ -235,8 +187,9 @@ return '<%s>' % self.__class__.__name__ - class element_by_name(object): + class _ElementByName(object): + """Node test that matches an element with a specific tag name.""" def __init__(self, name): self.name = QName(name) - def __call__(self, kind, data, pos): + def __call__(self, kind, data, _): if kind is Stream.START: return data[0].localname == self.name @@ -245,8 +198,9 @@ return '<%s "%s">' % (self.__class__.__name__, self.name) - class any_attribute(object): - def __call__(self, kind, data, pos): - if kind is Stream.START: - text = ''.join([val for name, val in data[1]]) + class _AnyAttribute(object): + """Node test that matches any attribute.""" + def __call__(self, kind, data, pos): + if kind is Stream.START: + text = ''.join([val for _, val in data[1]]) if text: return Stream.TEXT, text, pos @@ -256,5 +210,6 @@ return '<%s>' % (self.__class__.__name__) - class attribute_by_name(object): + class _AttributeByName(object): + """Node test that matches an attribute with a specific name.""" def __init__(self, name): self.name = QName(name) @@ -268,5 +223,6 @@ return '<%s "%s">' % (self.__class__.__name__, self.name) - class fn_text(object): + class _FunctionText(object): + """Function that returns text content.""" def __call__(self, kind, data, pos): if kind is Stream.TEXT: @@ -276,13 +232,15 @@ return '<%s>' % (self.__class__.__name__) - class literal_string(object): + class _LiteralString(object): + """Always returns a literal string.""" def __init__(self, value): self.value = value - def __call__(self, kind, data, pos): + def __call__(self, *_): return Stream.TEXT, self.value, (-1, -1) def __repr__(self): return '<%s>' % (self.__class__.__name__) - class op_eq(object): + class _OperatorEq(object): + """Equality comparison operator.""" def __init__(self, lval, rval): self.lval = lval @@ -296,5 +254,6 @@ self.rval) - class op_neq(object): + class _OperatorNeq(object): + """Inequality comparison operator.""" def __init__(self, lval, rval): self.lval = lval Index: /trunk/markup/plugin.py =================================================================== --- /trunk/markup/plugin.py (revision 20) +++ /trunk/markup/plugin.py (revision 30) @@ -1,14 +1,19 @@ # -*- coding: utf-8 -*- # -# Copyright (C) 2006 Mattew Good +# Copyright (C) 2006 Matthew Good +# Copyright (C) 2006 Christopher Lenz # All rights reserved. # # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. + +"""Basic support for the template engine plugin API used by TurboGears and +CherryPy/Buffet. +""" import os @@ -19,4 +24,5 @@ class TemplateEnginePlugin(object): + """Implementation of the plugin API.""" def __init__(self, extra_vars_func=None, options=None): @@ -35,16 +41,14 @@ package = templatename[:divider] basename = templatename[divider + 1:] + '.html' - fullpath = resource_filename(package, basename) - dirname, templatename = os.path.split(fullpath) - self.loader.search_path.append(dirname) # Kludge + templatename = resource_filename(package, basename) return self.loader.load(templatename) def render(self, info, format='html', fragment=False, template=None): - """Renders the template to a string using the provided info.""" + """Render the template to a string using the provided info.""" return self.transform(info, template).render(method=format) def transform(self, info, template): - "Render the output to Elements" + """Render the output to an event stream.""" if not isinstance(template, Template): template = self.load_template(template) Index: /trunk/markup/template.py =================================================================== --- /trunk/markup/template.py (revision 20) +++ /trunk/markup/template.py (revision 30) @@ -6,9 +6,9 @@ # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. """Template engine that is compatible with Kid (http://kid.lesscode.org) to a @@ -44,4 +44,5 @@ import compiler import os +import posixpath import re from StringIO import StringIO @@ -49,5 +50,4 @@ from markup.core import Attributes, Namespace, Stream, StreamEventKind from markup.eval import Expression -from markup.filters import IncludeFilter from markup.input import HTML, XMLParser, XML from markup.path import Path @@ -123,6 +123,6 @@ def __getitem__(self, key): - """Get a variable's value, starting at the current context and going - upward. + """Get a variable's value, starting at the current context frame and + going upward. """ return self.get(key) @@ -136,4 +136,7 @@ def get(self, key): + """Get a variable's value, starting at the current context frame and + going upward. + """ for frame in self.stack: if key in frame: @@ -141,7 +144,12 @@ def push(self, **data): + """Push a new context frame on the stack.""" self.stack.insert(0, data) def pop(self): + """Pop the top-most context frame from the stack. + + If the stack is empty, an `AssertionError` is raised. + """ assert self.stack, 'Pop from empty context stack' self.stack.pop(0) @@ -168,5 +176,5 @@ __slots__ = ['expr'] - def __init__(self, template, value, pos): + def __init__(self, value): self.expr = value and Expression(value) or None @@ -290,6 +298,6 @@ __slots__ = ['name', 'args', 'defaults', 'stream'] - def __init__(self, template, args, pos): - Directive.__init__(self, template, None, pos) + def __init__(self, args): + Directive.__init__(self, None) ast = compiler.parse(args, 'eval').node self.args = [] @@ -341,8 +349,8 @@ __slots__ = ['targets'] - def __init__(self, template, value, pos): - targets, expr_source = value.split(' in ', 1) + def __init__(self, value): + targets, value = value.split(' in ', 1) self.targets = [str(name.strip()) for name in targets.split(',')] - Directive.__init__(self, template, expr_source, pos) + Directive.__init__(self, value) def __call__(self, stream, ctxt): @@ -447,6 +455,6 @@ __slots__ = ['path', 'stream'] - def __init__(self, template, value, pos): - Directive.__init__(self, template, None, pos) + def __init__(self, value): + Directive.__init__(self, None) self.path = Path(value) self.stream = [] @@ -575,5 +583,5 @@ _dir_order = [directive[1] for directive in directives] - def __init__(self, source, filename=None): + def __init__(self, source, basedir=None, filename=None): """Initialize a template from either a string or a file-like object.""" if isinstance(source, basestring): @@ -581,12 +589,16 @@ else: self.source = source + self.basedir = basedir self.filename = filename or '' - - self.filters = [self._eval, self._match] + if basedir and filename: + self.filepath = os.path.join(basedir, filename) + else: + self.filepath = '' + + self.filters = [] self.parse() def __repr__(self): - return '<%s "%s">' % (self.__class__.__name__, - os.path.basename(self.filename)) + return '<%s "%s">' % (self.__class__.__name__, self.filename) def parse(self): @@ -604,5 +616,5 @@ depth = 0 - for kind, data, pos in XMLParser(self.source): + for kind, data, pos in XMLParser(self.source, filename=self.filename): if kind is Stream.START_NS: @@ -629,7 +641,7 @@ cls = self._dir_by_name.get(name.localname) if cls is None: - raise BadDirectiveError(name, self.filename, pos[0]) + raise BadDirectiveError(name, self.filename, pos[1]) else: - directives.append(cls(self, value, pos)) + directives.append(cls(value)) else: value = list(self._interpolate(value, *pos)) @@ -667,5 +679,5 @@ _SHORT_EXPR_RE = re.compile(r'(?alert("foo")') - self.assertRaises(HTMLParseError, markup.sanitize().render) + self.assertRaises(ParseError, markup.sanitize().render) markup = Markup('') - self.assertRaises(HTMLParseError, markup.sanitize().render) + self.assertRaises(ParseError, markup.sanitize().render) def test_sanitize_remove_onclick_attr(self): @@ -157,5 +157,5 @@ # Grave accents (not parsed) markup = Markup('

') - self.assertRaises(HTMLParseError, markup.sanitize().render) + self.assertRaises(ParseError, markup.sanitize().render) # Protocol encoded using UTF-8 numeric entities markup = Markup('

') + self.assertEqual('', Path('root').select(xml).render()) + self.assertEqual('', Path('//root').select(xml).render()) + + def test_1step_wildcard(self): + xml = XML('') + self.assertEqual('', Path('*').select(xml).render()) + self.assertEqual('', Path('//*').select(xml).render()) + + def test_1step_attribute(self): + path = Path('@foo') + self.assertEqual('', path.select(XML('')).render()) + self.assertEqual('bar', path.select(XML('')).render()) + + def test_1step_attribute(self): + path = Path('@foo') + self.assertEqual('', path.select(XML('')).render()) + self.assertEqual('bar', path.select(XML('')).render()) + + def test_2step(self): + xml = XML('') + self.assertEqual('', Path('root/*').select(xml).render()) + self.assertEqual('', Path('root/bar').select(xml).render()) + self.assertEqual('', Path('root/baz').select(xml).render()) + + def test_2step_complex(self): + xml = XML('') + self.assertEqual('', Path('foo/bar').select(xml).render()) + self.assertEqual('', Path('foo/*').select(xml).render()) + self.assertEqual('', Path('root/bar').select(xml).render()) + + xml = XML('') + self.assertEqual('', Path('root/bar').select(xml).render()) + + def test_2step_text(self): + xml = XML('Foo') + self.assertEqual('Foo', Path('item/text()').select(xml).render()) + xml = XML('FooBar') + self.assertEqual('FooBar', Path('item/text()').select(xml).render()) + + def test_3step(self): + xml = XML('') + self.assertEqual('', Path('root/foo/*').select(xml).render()) + + def test_3step_complex(self): + xml = XML('') + self.assertEqual('', Path('root/*/bar').select(xml).render()) + xml = XML('') + self.assertEqual('', + Path('root//bar').select(xml).render()) + + def test_predicate_attr(self): + xml = XML('') + self.assertEqual('', + Path('root/item[@important]').select(xml).render()) + self.assertEqual('', + Path('root/item[@important="very"]').select(xml).render()) + + xml = XML('') + self.assertEqual('', + Path('root/item[@important="very"]').select(xml).render()) + self.assertEqual('', + Path('root/item[@important!="very"]').select(xml).render()) def suite(): suite = unittest.TestSuite() - suite.addTest(doctest.DocTestSuite(path)) + suite.addTest(doctest.DocTestSuite(Path.__module__)) + suite.addTest(unittest.makeSuite(PathTestCase, 'test')) return suite Index: /trunk/markup/tests/template.py =================================================================== --- /trunk/markup/tests/template.py (revision 20) +++ /trunk/markup/tests/template.py (revision 30) @@ -1,14 +1,14 @@ # -*- coding: utf-8 -*- # -# Copyright (C) 2006 Edgewall Software +# Copyright (C) 2006 Christopher Lenz # All rights reserved. # # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. import doctest @@ -70,5 +70,5 @@ xml = '

' try: - tmpl = Template(xml, 'test.html') + tmpl = Template(xml, filename='test.html') except BadDirectiveError, e: self.assertEqual('test.html', e.filename) @@ -78,5 +78,5 @@ def test_directive_value_syntax_error(self): xml = '

' - tmpl = Template(xml, 'test.html') + tmpl = Template(xml, filename='test.html') try: list(tmpl.generate(Context())) Index: /trunk/setup.py =================================================================== --- /trunk/setup.py (revision 20) +++ /trunk/setup.py (revision 30) @@ -7,9 +7,9 @@ # This software is licensed as described in the file COPYING, which # you should have received as part of this distribution. The terms -# are also available at http://trac.edgewall.com/license.html. +# are also available at http://markup.cmlenz.net/wiki/License. # # This software consists of voluntary contributions made by many # individuals. For the exact contribution history, see the revision -# history and logs, available at http://projects.edgewall.com/trac/. +# history and logs, available at http://markup.cmlenz.net/log/. from setuptools import setup, find_packages

And goodbye

Welcome