genshi/genshi-test: genshi/filters/transform.py comparison

comparison genshi/filters/transform.py @ 933:feba07fc925b

Merge r1141 from py3k: add support for python 3 to genshi.filters: * minor changes to track encoding=None API change in core genshi modules. * renamed genshi/filters/tests/html.py to test_html.py to avoid clashes with Python 3 top-level html module when running tests subset. * did not rename genshi/filters/html.py. * i18n filters: * ugettext and friends are gone in Python 3 (and only gettext and friends exist and they now handle unicode) * Some \ line continuations inside doctests confused 2to3 and so were removed them. * Testing picked up a problem (already present in trunk) where Translator.__call__ could end up defining gettext as an endlessly recursive function. Noted with a TODO.

author	hodgestar
date	Fri, 18 Mar 2011 09:11:53 +0000
parents	24733a5854d9
children

comparison

equal deleted inserted replaced

-:e53161c2773c
+:feba07fc925b
 >>> html = HTML('''<html>
 ...  <head><title>Some Title</title></head>
 ...  <body>
 ...    Some <em>body</em> text.
 ...  </body>
-... </html>''')
+... </html>''',
+... encoding='utf-8')
 >>> print(html | Transformer('body/em').map(unicode.upper, TEXT)
 ...                                    .unwrap().wrap(tag.u))
 <html>
 <head><title>Some Title</title></head>
 <body>
 contained `INSIDE` any selected XML/HTML element. A non-element match
 outside a `START`/`END` container (e.g. ``text()``) will yield an `OUTSIDE`
 mark.
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 Transformations act on selected stream events matching an XPath expression.
 Here's an example of removing some markup (the title, in this case)
 selected by an expression:
 ...     for mark, (kind, data, pos) in stream:
 ...         if mark and kind is TEXT:
 ...             yield mark, (kind, data.upper(), pos)
 ...         else:
 ...             yield mark, (kind, data, pos)
->>> short_stream = HTML('<body>Some <em>test</em> text</body>')
+>>> short_stream = HTML('<body>Some <em>test</em> text</body>',
+...                      encoding='utf-8')
 >>> print(short_stream | Transformer('.//em/text()').apply(upper))
 <body>Some <em>TEST</em> text</body>
 """
 transformer = Transformer()
 transformer.transforms = self.transforms[:]
 def select(self, path):
 """Mark events matching the given XPath expression, within the current
 selection.
->>> html = HTML('<body>Some <em>test</em> text</body>')
+>>> html = HTML('<body>Some <em>test</em> text</body>', encoding='utf-8')
 >>> print(html | Transformer().select('.//em').trace())
 (None, ('START', (QName('body'), Attrs()), (None, 1, 0)))
 (None, ('TEXT', u'Some ', (None, 1, 6)))
 ('ENTER', ('START', (QName('em'), Attrs()), (None, 1, 11)))
 ('INSIDE', ('TEXT', u'test', (None, 1, 15)))
 versa.
 Specificaly, all marks are converted to null marks, and all null marks
 are converted to OUTSIDE marks.
->>> html = HTML('<body>Some <em>test</em> text</body>')
+>>> html = HTML('<body>Some <em>test</em> text</body>', encoding='utf-8')
 >>> print(html | Transformer('//em').invert().trace())
 ('OUTSIDE', ('START', (QName('body'), Attrs()), (None, 1, 0)))
 ('OUTSIDE', ('TEXT', u'Some ', (None, 1, 6)))
 (None, ('START', (QName('em'), Attrs()), (None, 1, 11)))
 (None, ('TEXT', u'test', (None, 1, 15)))
 def end(self):
 """End current selection, allowing all events to be selected.
 Example:
->>> html = HTML('<body>Some <em>test</em> text</body>')
+>>> html = HTML('<body>Some <em>test</em> text</body>', encoding='utf-8')
 >>> print(html | Transformer('//em').end().trace())
 ('OUTSIDE', ('START', (QName('body'), Attrs()), (None, 1, 0)))
 ('OUTSIDE', ('TEXT', u'Some ', (None, 1, 6)))
 ('OUTSIDE', ('START', (QName('em'), Attrs()), (None, 1, 11)))
 ('OUTSIDE', ('TEXT', u'test', (None, 1, 15)))
 """Empty selected elements of all content.
 Example:
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('.//em').empty())
 <html><head><title>Some Title</title></head><body>Some <em/>
 text.</body></html>
 :rtype: `Transformer`
 """Remove selection from the stream.
 Example:
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('.//em').remove())
 <html><head><title>Some Title</title></head><body>Some
 text.</body></html>
 :rtype: `Transformer`
 """Remove outermost enclosing elements from selection.
 Example:
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('.//em').unwrap())
 <html><head><title>Some Title</title></head><body>Some body
 text.</body></html>
 :rtype: `Transformer`
 def wrap(self, element):
 """Wrap selection in an element.
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('.//em').wrap('strong'))
 <html><head><title>Some Title</title></head><body>Some
 <strong><em>body</em></strong> text.</body></html>
 :param element: either a tag name (as string) or an `Element` object
 def replace(self, content):
 """Replace selection with content.
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('.//title/text()').replace('New Title'))
 <html><head><title>New Title</title></head><body>Some <em>body</em>
 text.</body></html>
 :param content: Either a callable, an iterable of events, or a string
 In this example we insert the word 'emphasised' before the <em> opening
 tag:
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('.//em').before('emphasised '))
 <html><head><title>Some Title</title></head><body>Some emphasised
 <em>body</em> text.</body></html>
 :param content: Either a callable, an iterable of events, or a string
 """Insert content after selection.
 Here, we insert some text after the </em> closing tag:
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('.//em').after(' rock'))
 <html><head><title>Some Title</title></head><body>Some <em>body</em>
 rock text.</body></html>
 :param content: Either a callable, an iterable of events, or a string
 """Insert content after the ENTER event of the selection.
 Inserting some new text at the start of the <body>:
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('.//body').prepend('Some new body text. '))
 <html><head><title>Some Title</title></head><body>Some new body text.
 Some <em>body</em> text.</body></html>
 :param content: Either a callable, an iterable of events, or a string
 def append(self, content):
 """Insert content before the END event of the selection.
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('.//body').append(' Some new body text.'))
 <html><head><title>Some Title</title></head><body>Some <em>body</em>
 text. Some new body text.</body></html>
 :param content: Either a callable, an iterable of events, or a string
 If `value` evaulates to `None` the attribute will be deleted from the
 element:
 >>> html = HTML('<html><head><title>Some Title</title></head>'
 ...             '<body>Some <em class="before">body</em> <em>text</em>.</body>'
-...             '</html>')
+...             '</html>', encoding='utf-8')
 >>> print(html | Transformer('body/em').attr('class', None))
 <html><head><title>Some Title</title></head><body>Some <em>body</em>
 <em>text</em>.</body></html>
 Otherwise the attribute will be set to `value`:
 be appended to the buffer rather than replacing it.
 >>> from genshi.builder import tag
 >>> buffer = StreamBuffer()
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('head/title/text()').copy(buffer)
 ...     .end().select('body').prepend(tag.h1(buffer)))
 <html><head><title>Some Title</title></head><body><h1>Some
 Title</h1>Some <em>body</em> text.</body></html>
 Element attributes can also be copied for later use:
 >>> html = HTML('<html><head><title>Some Title</title></head>'
 ...             '<body><em>Some</em> <em class="before">body</em>'
-...             '<em>text</em>.</body></html>')
+...             '<em>text</em>.</body></html>',
+...             encoding='utf-8')
 >>> buffer = StreamBuffer()
 >>> def apply_attr(name, entry):
 ...     return list(buffer)[0][1][1].get('class')
 >>> print(html | Transformer('body/em[@class]/@class').copy(buffer)
 ...     .end().buffer().select('body/em[not(@class)]')
 """Copy selection into buffer and remove the selection from the stream.
 >>> from genshi.builder import tag
 >>> buffer = StreamBuffer()
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...             '<body>Some <em>body</em> text.</body></html>')
+...             '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('.//em/text()').cut(buffer)
 ...     .end().select('.//em').after(tag.h1(buffer)))
 <html><head><title>Some Title</title></head><body>Some
 <em/><h1>body</h1> text.</body></html>
 For example, to move all <note> elements inside a <notes> tag at the
 top of the document:
 >>> doc = HTML('<doc><notes></notes><body>Some <note>one</note> '
-...            'text <note>two</note>.</body></doc>')
+...            'text <note>two</note>.</body></doc>',
+...             encoding='utf-8')
 >>> buffer = StreamBuffer()
 >>> print(doc | Transformer('body/note').cut(buffer, accumulate=True)
 ...     .end().buffer().select('notes').prepend(buffer))
 <doc><notes><note>one</note><note>two</note></notes><body>Some  text
 .</body></doc>
 """Apply a normal stream filter to the selection. The filter is called
 once for each contiguous block of marked events.
 >>> from genshi.filters.html import HTMLSanitizer
 >>> html = HTML('<html><body>Some text<script>alert(document.cookie)'
-...             '</script> and some more text</body></html>')
+...             '</script> and some more text</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('body/*').filter(HTMLSanitizer()))
 <html><body>Some text and some more text</body></html>
 :param filter: The stream filter to apply.
 :rtype: `Transformer`
 def map(self, function, kind):
 """Applies a function to the ``data`` element of events of ``kind`` in
 the selection.
 >>> html = HTML('<html><head><title>Some Title</title></head>'
-...               '<body>Some <em>body</em> text.</body></html>')
+...               '<body>Some <em>body</em> text.</body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('head/title').map(unicode.upper, TEXT))
 <html><head><title>SOME TITLE</title></head><body>Some <em>body</em>
 text.</body></html>
 :param function: the function to apply
 Refer to the documentation for ``re.sub()`` for details.
 >>> html = HTML('<html><body>Some text, some more text and '
 ...             '<b>some bold text</b>\\n'
-...             '<i>some italicised text</i></body></html>')
+...             '<i>some italicised text</i></body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('body/b').substitute('(?i)some', 'SOME'))
 <html><body>Some text, some more text and <b>SOME bold text</b>
 <i>some italicised text</i></body></html>
 >>> tags = tag.html(tag.body('Some text, some more text and\\n',
 ...      Markup('<b>some bold text</b>')))
 def rename(self, name):
 """Rename matching elements.
 >>> html = HTML('<html><body>Some text, some more text and '
-...             '<b>some bold text</b></body></html>')
+...             '<b>some bold text</b></body></html>',
+...             encoding='utf-8')
 >>> print(html | Transformer('body/b').rename('strong'))
 <html><body>Some text, some more text and <strong>some bold text</strong></body></html>
 """
 return self.apply(RenameTransformation(name))
 def trace(self, prefix='', fileobj=None):
 """Print events as they pass through the transform.
->>> html = HTML('<body>Some <em>test</em> text</body>')
+>>> html = HTML('<body>Some <em>test</em> text</body>', encoding='utf-8')
 >>> print(html | Transformer('em').trace())
 (None, ('START', (QName('body'), Attrs()), (None, 1, 0)))
 (None, ('TEXT', u'Some ', (None, 1, 6)))
 ('ENTER', ('START', (QName('em'), Attrs()), (None, 1, 11)))
 ('INSIDE', ('TEXT', u'test', (None, 1, 15)))
 ...     def __call__(self, stream):
 ...         for event in self._inject():
 ...             yield event
 ...         for event in stream:
 ...             yield event
->>> html = HTML('<body>Some <em>test</em> text</body>')
+>>> html = HTML('<body>Some <em>test</em> text</body>', encoding='utf-8')
 >>> print(html | Transformer('.//em').apply(Top('Prefix ')))
 Prefix <body>Some <em>test</em> text</body>
 """
 def __init__(self, content):
 """Create a new injector.

Mercurial > genshi > genshi-test

comparison genshi/filters/transform.py @ 933:feba07fc925b