From 5b45e526c74faf55110ff0afdcba19797d7e0f4d Mon Sep 17 00:00:00 2001 From: Evgeny Fadeev Date: Fri, 10 Jul 2009 19:14:09 -0400 Subject: deleted all --- utils/html.py | 51 --------------------------------------------------- 1 file changed, 51 deletions(-) delete mode 100644 utils/html.py (limited to 'utils/html.py') diff --git a/utils/html.py b/utils/html.py deleted file mode 100644 index 602e1a76..00000000 --- a/utils/html.py +++ /dev/null @@ -1,51 +0,0 @@ -"""Utilities for working with HTML.""" -import html5lib -from html5lib import sanitizer, serializer, tokenizer, treebuilders, treewalkers - -class HTMLSanitizerMixin(sanitizer.HTMLSanitizerMixin): - acceptable_elements = ('a', 'abbr', 'acronym', 'address', 'b', 'big', - 'blockquote', 'br', 'caption', 'center', 'cite', 'code', 'col', - 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'font', - 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'ins', 'kbd', - 'li', 'ol', 'p', 'pre', 'q', 's', 'samp', 'small', 'span', 'strike', - 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'tfoot', 'th', 'thead', - 'tr', 'tt', 'u', 'ul', 'var') - - acceptable_attributes = ('abbr', 'align', 'alt', 'axis', 'border', - 'cellpadding', 'cellspacing', 'char', 'charoff', 'charset', 'cite', - 'cols', 'colspan', 'datetime', 'dir', 'frame', 'headers', 'height', - 'href', 'hreflang', 'hspace', 'lang', 'longdesc', 'name', 'nohref', - 'noshade', 'nowrap', 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', - 'span', 'src', 'start', 'summary', 'title', 'type', 'valign', 'vspace', - 'width') - - allowed_elements = acceptable_elements - allowed_attributes = acceptable_attributes - allowed_css_properties = () - allowed_css_keywords = () - allowed_svg_properties = () - -class HTMLSanitizer(tokenizer.HTMLTokenizer, HTMLSanitizerMixin): - def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True, - lowercaseElementName=True, lowercaseAttrName=True): - tokenizer.HTMLTokenizer.__init__(self, stream, encoding, parseMeta, - useChardet, lowercaseElementName, - lowercaseAttrName) - - def __iter__(self): - for token in tokenizer.HTMLTokenizer.__iter__(self): - token = self.sanitize_token(token) - if token: - yield token - -def sanitize_html(html): - """Sanitizes an HTML fragment.""" - p = html5lib.HTMLParser(tokenizer=HTMLSanitizer, - tree=treebuilders.getTreeBuilder("dom")) - dom_tree = p.parseFragment(html) - walker = treewalkers.getTreeWalker("dom") - stream = walker(dom_tree) - s = serializer.HTMLSerializer(omit_optional_tags=False, - quote_attr_values=True) - output_generator = s.serialize(stream) - return u''.join(output_generator) -- cgit v1.2.3-1-g7c22 From 35b666224a05fbd249b1c51a0a48fb95b246fe9a Mon Sep 17 00:00:00 2001 From: Evgeny Fadeev Date: Fri, 10 Jul 2009 19:15:28 -0400 Subject: adding all files again --- utils/html.py | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 51 insertions(+) create mode 100644 utils/html.py (limited to 'utils/html.py') diff --git a/utils/html.py b/utils/html.py new file mode 100644 index 00000000..602e1a76 --- /dev/null +++ b/utils/html.py @@ -0,0 +1,51 @@ +"""Utilities for working with HTML.""" +import html5lib +from html5lib import sanitizer, serializer, tokenizer, treebuilders, treewalkers + +class HTMLSanitizerMixin(sanitizer.HTMLSanitizerMixin): + acceptable_elements = ('a', 'abbr', 'acronym', 'address', 'b', 'big', + 'blockquote', 'br', 'caption', 'center', 'cite', 'code', 'col', + 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'font', + 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'ins', 'kbd', + 'li', 'ol', 'p', 'pre', 'q', 's', 'samp', 'small', 'span', 'strike', + 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'tfoot', 'th', 'thead', + 'tr', 'tt', 'u', 'ul', 'var') + + acceptable_attributes = ('abbr', 'align', 'alt', 'axis', 'border', + 'cellpadding', 'cellspacing', 'char', 'charoff', 'charset', 'cite', + 'cols', 'colspan', 'datetime', 'dir', 'frame', 'headers', 'height', + 'href', 'hreflang', 'hspace', 'lang', 'longdesc', 'name', 'nohref', + 'noshade', 'nowrap', 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', + 'span', 'src', 'start', 'summary', 'title', 'type', 'valign', 'vspace', + 'width') + + allowed_elements = acceptable_elements + allowed_attributes = acceptable_attributes + allowed_css_properties = () + allowed_css_keywords = () + allowed_svg_properties = () + +class HTMLSanitizer(tokenizer.HTMLTokenizer, HTMLSanitizerMixin): + def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True, + lowercaseElementName=True, lowercaseAttrName=True): + tokenizer.HTMLTokenizer.__init__(self, stream, encoding, parseMeta, + useChardet, lowercaseElementName, + lowercaseAttrName) + + def __iter__(self): + for token in tokenizer.HTMLTokenizer.__iter__(self): + token = self.sanitize_token(token) + if token: + yield token + +def sanitize_html(html): + """Sanitizes an HTML fragment.""" + p = html5lib.HTMLParser(tokenizer=HTMLSanitizer, + tree=treebuilders.getTreeBuilder("dom")) + dom_tree = p.parseFragment(html) + walker = treewalkers.getTreeWalker("dom") + stream = walker(dom_tree) + s = serializer.HTMLSerializer(omit_optional_tags=False, + quote_attr_values=True) + output_generator = s.serialize(stream) + return u''.join(output_generator) -- cgit v1.2.3-1-g7c22 From 20a7ce5657bf3d8683bdb4f9b860dbad044fb2f3 Mon Sep 17 00:00:00 2001 From: Evgeny Fadeev Date: Tue, 4 Aug 2009 23:25:57 -0400 Subject: included changes by Adolfo and Chaitanya and found temporary fix for languages --- utils/html.py | 102 +++++++++++++++++++++++++++++----------------------------- 1 file changed, 51 insertions(+), 51 deletions(-) (limited to 'utils/html.py') diff --git a/utils/html.py b/utils/html.py index 602e1a76..25a74a4a 100644 --- a/utils/html.py +++ b/utils/html.py @@ -1,51 +1,51 @@ -"""Utilities for working with HTML.""" -import html5lib -from html5lib import sanitizer, serializer, tokenizer, treebuilders, treewalkers - -class HTMLSanitizerMixin(sanitizer.HTMLSanitizerMixin): - acceptable_elements = ('a', 'abbr', 'acronym', 'address', 'b', 'big', - 'blockquote', 'br', 'caption', 'center', 'cite', 'code', 'col', - 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'font', - 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'ins', 'kbd', - 'li', 'ol', 'p', 'pre', 'q', 's', 'samp', 'small', 'span', 'strike', - 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'tfoot', 'th', 'thead', - 'tr', 'tt', 'u', 'ul', 'var') - - acceptable_attributes = ('abbr', 'align', 'alt', 'axis', 'border', - 'cellpadding', 'cellspacing', 'char', 'charoff', 'charset', 'cite', - 'cols', 'colspan', 'datetime', 'dir', 'frame', 'headers', 'height', - 'href', 'hreflang', 'hspace', 'lang', 'longdesc', 'name', 'nohref', - 'noshade', 'nowrap', 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', - 'span', 'src', 'start', 'summary', 'title', 'type', 'valign', 'vspace', - 'width') - - allowed_elements = acceptable_elements - allowed_attributes = acceptable_attributes - allowed_css_properties = () - allowed_css_keywords = () - allowed_svg_properties = () - -class HTMLSanitizer(tokenizer.HTMLTokenizer, HTMLSanitizerMixin): - def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True, - lowercaseElementName=True, lowercaseAttrName=True): - tokenizer.HTMLTokenizer.__init__(self, stream, encoding, parseMeta, - useChardet, lowercaseElementName, - lowercaseAttrName) - - def __iter__(self): - for token in tokenizer.HTMLTokenizer.__iter__(self): - token = self.sanitize_token(token) - if token: - yield token - -def sanitize_html(html): - """Sanitizes an HTML fragment.""" - p = html5lib.HTMLParser(tokenizer=HTMLSanitizer, - tree=treebuilders.getTreeBuilder("dom")) - dom_tree = p.parseFragment(html) - walker = treewalkers.getTreeWalker("dom") - stream = walker(dom_tree) - s = serializer.HTMLSerializer(omit_optional_tags=False, - quote_attr_values=True) - output_generator = s.serialize(stream) - return u''.join(output_generator) +"""Utilities for working with HTML.""" +import html5lib +from html5lib import sanitizer, serializer, tokenizer, treebuilders, treewalkers + +class HTMLSanitizerMixin(sanitizer.HTMLSanitizerMixin): + acceptable_elements = ('a', 'abbr', 'acronym', 'address', 'b', 'big', + 'blockquote', 'br', 'caption', 'center', 'cite', 'code', 'col', + 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt', 'em', 'font', + 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'ins', 'kbd', + 'li', 'ol', 'p', 'pre', 'q', 's', 'samp', 'small', 'span', 'strike', + 'strong', 'sub', 'sup', 'table', 'tbody', 'td', 'tfoot', 'th', 'thead', + 'tr', 'tt', 'u', 'ul', 'var') + + acceptable_attributes = ('abbr', 'align', 'alt', 'axis', 'border', + 'cellpadding', 'cellspacing', 'char', 'charoff', 'charset', 'cite', + 'cols', 'colspan', 'datetime', 'dir', 'frame', 'headers', 'height', + 'href', 'hreflang', 'hspace', 'lang', 'longdesc', 'name', 'nohref', + 'noshade', 'nowrap', 'rel', 'rev', 'rows', 'rowspan', 'rules', 'scope', + 'span', 'src', 'start', 'summary', 'title', 'type', 'valign', 'vspace', + 'width') + + allowed_elements = acceptable_elements + allowed_attributes = acceptable_attributes + allowed_css_properties = () + allowed_css_keywords = () + allowed_svg_properties = () + +class HTMLSanitizer(tokenizer.HTMLTokenizer, HTMLSanitizerMixin): + def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True, + lowercaseElementName=True, lowercaseAttrName=True): + tokenizer.HTMLTokenizer.__init__(self, stream, encoding, parseMeta, + useChardet, lowercaseElementName, + lowercaseAttrName) + + def __iter__(self): + for token in tokenizer.HTMLTokenizer.__iter__(self): + token = self.sanitize_token(token) + if token: + yield token + +def sanitize_html(html): + """Sanitizes an HTML fragment.""" + p = html5lib.HTMLParser(tokenizer=HTMLSanitizer, + tree=treebuilders.getTreeBuilder("dom")) + dom_tree = p.parseFragment(html) + walker = treewalkers.getTreeWalker("dom") + stream = walker(dom_tree) + s = serializer.HTMLSerializer(omit_optional_tags=False, + quote_attr_values=True) + output_generator = s.serialize(stream) + return u''.join(output_generator) -- cgit v1.2.3-1-g7c22