Gecko [ gtgates.com ]

Name	Size	Permission	Date
ElementSoup.py	319 B	-rw-r--r--	2011-09-25 16:58
ElementSoup.pyc	622 B	-rw-r--r--	2022-04-21 13:54
ElementSoup.pyo	622 B	-rw-r--r--	2022-04-21 13:54
__init__.py	63.37 KB	-rw-r--r--	2018-03-13 20:13
__init__.pyc	65.5 KB	-rw-r--r--	2022-04-21 13:54
__init__.pyo	65.22 KB	-rw-r--r--	2022-04-21 13:54
_diffcommand.py	2.08 KB	-rw-r--r--	2017-09-17 07:43
_diffcommand.pyc	2.84 KB	-rw-r--r--	2022-04-21 13:54
_diffcommand.pyo	2.84 KB	-rw-r--r--	2022-04-21 13:54
_html5builder.py	3.17 KB	-rw-r--r--	2012-09-28 19:13
_html5builder.pyc	4.49 KB	-rw-r--r--	2022-04-21 13:54
_html5builder.pyo	4.49 KB	-rw-r--r--	2022-04-21 13:54
_setmixin.py	1.08 KB	-rw-r--r--	2016-05-05 07:08
_setmixin.pyc	2.49 KB	-rw-r--r--	2022-04-21 13:54
_setmixin.pyo	2.49 KB	-rw-r--r--	2022-04-21 13:54
builder.py	4.21 KB	-rw-r--r--	2011-09-25 16:58
builder.pyc	3.83 KB	-rw-r--r--	2022-04-21 13:54
builder.pyo	3.83 KB	-rw-r--r--	2022-04-21 13:54
clean.py	26.49 KB	-rw-r--r--	2022-04-21 13:53
clean.pyc	19.67 KB	-rw-r--r--	2022-04-21 13:54
clean.pyo	19.58 KB	-rw-r--r--	2022-04-21 13:54
clean.so	268.93 KB	-rwxr-xr-x	2022-04-21 13:54
defs.py	4.11 KB	-rw-r--r--	2022-04-21 13:53
defs.pyc	3.84 KB	-rw-r--r--	2022-04-21 13:54
defs.pyo	3.84 KB	-rw-r--r--	2022-04-21 13:54
diff.py	29.79 KB	-rw-r--r--	2017-05-01 14:11
diff.pyc	27.94 KB	-rw-r--r--	2022-04-21 13:54
diff.pyo	27.6 KB	-rw-r--r--	2022-04-21 13:54
diff.so	363.35 KB	-rwxr-xr-x	2022-04-21 13:54
formfill.py	9.46 KB	-rw-r--r--	2017-06-03 16:47
formfill.pyc	9.52 KB	-rw-r--r--	2022-04-21 13:54
formfill.pyo	9.28 KB	-rw-r--r--	2022-04-21 13:54
html5parser.py	8.43 KB	-rw-r--r--	2017-09-17 07:43
html5parser.pyc	7.79 KB	-rw-r--r--	2022-04-21 13:54
html5parser.pyo	7.79 KB	-rw-r--r--	2022-04-21 13:54
soupparser.py	9.96 KB	-rw-r--r--	2017-09-17 07:43
soupparser.pyc	9.57 KB	-rw-r--r--	2022-04-21 13:54
soupparser.pyo	9.57 KB	-rw-r--r--	2022-04-21 13:54
usedoctest.py	249 B	-rw-r--r--	2011-09-25 16:58
usedoctest.pyc	464 B	-rw-r--r--	2022-04-21 13:54
usedoctest.pyo	464 B	-rw-r--r--	2022-04-21 13:54

Rename

# FIXME: this should all be confirmed against what a DTD says
# (probably in a test; this may not match the DTD exactly, but we
# should document just how it differs).

# Data taken from http://www.w3.org/TR/html401/index/elements.html
# and http://www.w3.org/community/webed/wiki/HTML/New_HTML5_Elements
# for html5_tags.

empty_tags = frozenset([
    'area', 'base', 'basefont', 'br', 'col', 'frame', 'hr',
    'img', 'input', 'isindex', 'link', 'meta', 'param'])

deprecated_tags = frozenset([
    'applet', 'basefont', 'center', 'dir', 'font', 'isindex',
    'menu', 's', 'strike', 'u'])

# archive actually takes a space-separated list of URIs
link_attrs = frozenset([
    'action', 'archive', 'background', 'cite', 'classid',
    'codebase', 'data', 'href', 'longdesc', 'profile', 'src',
    'usemap',
    # Not standard:
    'dynsrc', 'lowsrc',
    # HTML5 formaction
    'formaction'
    ])

# Not in the HTML 4 spec:
# onerror, onresize
event_attrs = frozenset([
    'onblur', 'onchange', 'onclick', 'ondblclick', 'onerror',
    'onfocus', 'onkeydown', 'onkeypress', 'onkeyup', 'onload',
    'onmousedown', 'onmousemove', 'onmouseout', 'onmouseover',
    'onmouseup', 'onreset', 'onresize', 'onselect', 'onsubmit',
    'onunload',
    ])

safe_attrs = frozenset([
    'abbr', 'accept', 'accept-charset', 'accesskey', 'action', 'align',
    'alt', 'axis', 'border', 'cellpadding', 'cellspacing', 'char', 'charoff',
    'charset', 'checked', 'cite', 'class', 'clear', 'cols', 'colspan',
    'color', 'compact', 'coords', 'datetime', 'dir', 'disabled', 'enctype',
    'for', 'frame', 'headers', 'height', 'href', 'hreflang', 'hspace', 'id',
    'ismap', 'label', 'lang', 'longdesc', 'maxlength', 'media', 'method',
    'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'prompt', 'readonly',
    'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', 'selected', 'shape',
    'size', 'span', 'src', 'start', 'summary', 'tabindex', 'target', 'title',
    'type', 'usemap', 'valign', 'value', 'vspace', 'width'])

# From http://htmlhelp.com/reference/html40/olist.html
top_level_tags = frozenset([
    'html', 'head', 'body', 'frameset',
    ])

head_tags = frozenset([
    'base', 'isindex', 'link', 'meta', 'script', 'style', 'title',
    ])

general_block_tags = frozenset([
    'address',
    'blockquote',
    'center',
    'del',
    'div',
    'h1',
    'h2',
    'h3',
    'h4',
    'h5',
    'h6',
    'hr',
    'ins',
    'isindex',
    'noscript',
    'p',
    'pre',
    ])

list_tags = frozenset([
    'dir', 'dl', 'dt', 'dd', 'li', 'menu', 'ol', 'ul',
    ])

table_tags = frozenset([
    'table', 'caption', 'colgroup', 'col',
    'thead', 'tfoot', 'tbody', 'tr', 'td', 'th',
    ])

# just this one from
# http://www.georgehernandez.com/h/XComputers/HTML/2BlockLevel.htm
block_tags = general_block_tags | list_tags | table_tags | frozenset([
    # Partial form tags
    'fieldset', 'form', 'legend', 'optgroup', 'option',
    ])

form_tags = frozenset([
    'form', 'button', 'fieldset', 'legend', 'input', 'label',
    'select', 'optgroup', 'option', 'textarea',
    ])

special_inline_tags = frozenset([
    'a', 'applet', 'basefont', 'bdo', 'br', 'embed', 'font', 'iframe',
    'img', 'map', 'area', 'object', 'param', 'q', 'script',
    'span', 'sub', 'sup',
    ])

phrase_tags = frozenset([
    'abbr', 'acronym', 'cite', 'code', 'del', 'dfn', 'em',
    'ins', 'kbd', 'samp', 'strong', 'var',
    ])

font_style_tags = frozenset([
    'b', 'big', 'i', 's', 'small', 'strike', 'tt', 'u',
    ])

frame_tags = frozenset([
    'frameset', 'frame', 'noframes',
    ])
    
html5_tags = frozenset([
    'article', 'aside', 'audio', 'canvas', 'command', 'datalist',
    'details', 'embed', 'figcaption', 'figure', 'footer', 'header',
    'hgroup', 'keygen', 'mark', 'math', 'meter', 'nav', 'output',
    'progress', 'rp', 'rt', 'ruby', 'section', 'source', 'summary',
    'svg', 'time', 'track', 'video', 'wbr'
    ])

# These tags aren't standard
nonstandard_tags = frozenset(['blink', 'marquee'])