Module: Hpricot

Defined in:

lib/rfeedparser/scrub.rb

Overview

This used to be based on Michael Moen’s Hpricot#scrub, but that seems to have only been part of its evolution. Hpricot#scrub is cool code, though. underpantsgnome.com/2007/01/20/hpricot-scrub

Defined Under Namespace

Classes: BogusETag, Comment, Elem, Elements, Text

Constant Summary

Acceptable_Elements =

['a', 'abbr', 'acronym', 'address', 'area', 'b',
  'big', 'blockquote', 'br', 'button', 'caption', 'center', 'cite',
  'code', 'col', 'colgroup', 'dd', 'del', 'dfn', 'dir', 'div', 'dl', 'dt',
  'em', 'fieldset', 'font', 'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
  'hr', 'i', 'img', 'input', 'ins', 'kbd', 'label', 'legend', 'li', 'map',
  'menu', 'ol', 'optgroup', 'option', 'p', 'pre', 'q', 's', 'samp',
  'select', 'small', 'span', 'strike', 'strong', 'sub', 'sup', 'table',
  'tbody', 'td', 'textarea', 'tfoot', 'th', 'thead', 'tr', 'tt', 'u',
  'ul', 'var'
]

Acceptable_Attributes =

['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', 'xml:lang'
]

Unacceptable_Elements_With_End_Tag =

['script', 'applet']

Acceptable_Css_Properties =

['azimuth', 'background-color',
  'border-bottom-color', 'border-collapse', 'border-color',
  'border-left-color', 'border-right-color', 'border-top-color', 'clear',
  'color', 'cursor', 'direction', 'display', 'elevation', 'float', 'font',
  'font-family', 'font-size', 'font-style', 'font-variant', 'font-weight',
  'height', 'letter-spacing', 'line-height', 'overflow', 'pause',
  'pause-after', 'pause-before', 'pitch', 'pitch-range', 'richness',
  'speak', 'speak-header', 'speak-numeral', 'speak-punctuation',
  'speech-rate', 'stress', 'text-align', 'text-decoration', 'text-indent',
  'unicode-bidi', 'vertical-align', 'voice-family', 'volume',
  'white-space', 'width'
]

Acceptable_Css_Keywords =

survey of common keywords found in feeds

['auto', 'aqua', 'black', 'block', 'blue',
  'bold', 'both', 'bottom', 'brown', 'center', 'collapse', 'dashed',
  'dotted', 'fuchsia', 'gray', 'green', '!important', 'italic', 'left',
  'lime', 'maroon', 'medium', 'none', 'navy', 'normal', 'nowrap', 'olive',
  'pointer', 'purple', 'red', 'right', 'solid', 'silver', 'teal', 'top',
  'transparent', 'underline', 'white', 'yellow'
]

Mathml_Elements =

['maction', 'math', 'merror', 'mfrac', 'mi',
  'mmultiscripts', 'mn', 'mo', 'mover', 'mpadded', 'mphantom',
  'mprescripts', 'mroot', 'mrow', 'mspace', 'msqrt', 'mstyle', 'msub',
  'msubsup', 'msup', 'mtable', 'mtd', 'mtext', 'mtr', 'munder',
  'munderover', 'none'
]

Mathml_Attributes =

['actiontype', 'align', 'columnalign', 'columnalign',
  'columnalign', 'columnlines', 'columnspacing', 'columnspan', 'depth',
  'display', 'displaystyle', 'equalcolumns', 'equalrows', 'fence',
  'fontstyle', 'fontweight', 'frame', 'height', 'linethickness', 'lspace',
  'mathbackground', 'mathcolor', 'mathvariant', 'mathvariant', 'maxsize',
  'minsize', 'other', 'rowalign', 'rowalign', 'rowalign', 'rowlines',
  'rowspacing', 'rowspan', 'rspace', 'scriptlevel', 'selection',
  'separator', 'stretchy', 'width', 'width', 'xlink:href', 'xlink:show',
  'xlink:type', 'xmlns', 'xmlns:xlink'
]

Svg_Elements =

svgtiny - foreignObject + linearGradient + radialGradient + stop

['a', 'animate', 'animateColor', 'animateMotion',
  'animateTransform', 'circle', 'defs', 'desc', 'ellipse', 'font-face',
  'font-face-name', 'font-face-src', 'g', 'glyph', 'hkern', 'image',
  'linearGradient', 'line', 'metadata', 'missing-glyph', 'mpath', 'path',
  'polygon', 'polyline', 'radialGradient', 'rect', 'set', 'stop', 'svg',
  'switch', 'text', 'title', 'use'
]

Svg_Attributes =

svgtiny + class + opacity + offset + xmlns + xmlns:xlink

['accent-height', 'accumulate', 'additive', 'alphabetic',
  'arabic-form', 'ascent', 'attributeName', 'attributeType',
  'baseProfile', 'bbox', 'begin', 'by', 'calcMode', 'cap-height',
  'class', 'color', 'color-rendering', 'content', 'cx', 'cy', 'd',
  'descent', 'display', 'dur', 'end', 'fill', 'fill-rule', 'font-family',
  'font-size', 'font-stretch', 'font-style', 'font-variant',
  'font-weight', 'from', 'fx', 'fy', 'g1', 'g2', 'glyph-name', 
  'gradientUnits', 'hanging', 'height', 'horiz-adv-x', 'horiz-origin-x',
  'id', 'ideographic', 'k', 'keyPoints', 'keySplines', 'keyTimes',
  'lang', 'mathematical', 'max', 'min', 'name', 'offset', 'opacity',
  'origin', 'overline-position', 'overline-thickness', 'panose-1',
  'path', 'pathLength', 'points', 'preserveAspectRatio', 'r',
  'repeatCount', 'repeatDur', 'requiredExtensions', 'requiredFeatures',
  'restart', 'rotate', 'rx', 'ry', 'slope', 'stemh', 'stemv', 
  'stop-color', 'stop-opacity', 'strikethrough-position',
  'strikethrough-thickness', 'stroke', 'stroke-dasharray',
  'stroke-dashoffset', 'stroke-linecap', 'stroke-linejoin',
  'stroke-miterlimit', 'stroke-width', 'systemLanguage', 'target',
  'text-anchor', 'to', 'transform', 'type', 'u1', 'u2',
  'underline-position', 'underline-thickness', 'unicode',
  'unicode-range', 'units-per-em', 'values', 'version', 'viewBox',
  'visibility', 'width', 'widths', 'x', 'x-height', 'x1', 'x2',
  'xlink:actuate', 'xlink:arcrole', 'xlink:href', 'xlink:role',
  'xlink:show', 'xlink:title', 'xlink:type', 'xml:base', 'xml:lang',
  'xml:space', 'xmlns', 'xmlns:xlink', 'y', 'y1', 'y2', 'zoomAndPan'
]

Svg_Attr_Map =

nil

Svg_Elem_Map =

nil

Acceptable_Svg_Properties =

[ 'fill', 'fill-opacity', 'fill-rule',
  'stroke', 'stroke-width', 'stroke-linecap', 'stroke-linejoin',
  'stroke-opacity'
]

@@acceptable_tag_specific_attributes =

{}