parse-mdn-svg-documents

#!/usr/bin/env ruby

# TOO UGLY!
#
# Offline MDN SVG: https://frankfurt.kapeli.com/feeds/zzz/mdn/SVG.tgz

ELEMENTS = %w[
  a
  animate
  animateMotion
  animateTransform
  circle
  clipPath
  defs
  desc
  ellipse
  feBlend
  feColorMatrix
  feComponentTransfer
  feComposite
  feConvolveMatrix
  feDiffuseLighting
  feDisplacementMap
  feDistantLight
  feDropShadow
  feFlood
  feFuncA
  feFuncB
  feFuncG
  feFuncR
  feGaussianBlur
  feImage
  feMerge
  feMergeNode
  feMorphology
  feOffset
  fePointLight
  feSpecularLighting
  feSpotLight
  feTile
  feTurbulence
  filter
  foreignObject
  g
  hatch
  hatchpath
  image
  line
  linearGradient
  marker
  mask
  metadata
  mpath
  path
  pattern
  polygon
  polyline
  radialGradient
  rect
  script
  set
  stop
  style
  svg
  switch
  symbol
  text
  textPath
  title
  tspan
  use
  view
]

ATTRIBUTES = %w[
  accent-height
  accumulate
  additive
  alignment-baseline
  alphabetic
  amplitude
  arabic-form
  ascent
  attributeName
  attributeType
  azimuth
  baseFrequency
  baseline-shift
  baseProfile
  bbox
  begin
  bias
  by
  calcMode
  cap-height
  class
  clip
  clipPathUnits
  clip-path
  clip-rule
  color
  color-interpolation
  color-interpolation-filters
  color-profile
  color-rendering
  contentScriptType
  contentStyleType
  crossorigin
  cursor
  cx
  cy
  d
  decelerate
  descent
  diffuseConstant
  direction
  display
  divisor
  dominant-baseline
  dur
  dx
  dy
  edgeMode
  elevation
  enable-background
  end
  exponent
  fill
  fill-opacity
  fill-rule
  filter
  filterRes
  filterUnits
  flood-color
  flood-opacity
  font-family
  font-size
  font-size-adjust
  font-stretch
  font-style
  font-variant
  font-weight
  format
  from
  fr
  fx
  fy
  g1
  g2
  glyph-name
  glyph-orientation-horizontal
  glyph-orientation-vertical
  glyphRef
  gradientTransform
  gradientUnits
  hanging
  height
  href
  hreflang
  horiz-adv-x
  horiz-origin-x
  id
  ideographic
  image-rendering
  in
  in2
  intercept
  k
  k1
  k2
  k3
  k4
  kernelMatrix
  kernelUnitLength
  kerning
  keyPoints
  keySplines
  keyTimes
  lang
  lengthAdjust
  letter-spacing
  lighting-color
  limitingConeAngle
  local
  marker-end
  marker-mid
  marker-start
  markerHeight
  markerUnits
  markerWidth
  mask
  maskContentUnits
  maskUnits
  mathematical
  max
  media
  method
  min
  mode
  name
  numOctaves
  offset
  opacity
  operator
  order
  orient
  orientation
  origin
  overflow
  overline-position
  overline-thickness
  panose-1
  paint-order
  path
  pathLength
  patternContentUnits
  patternTransform
  patternUnits
  ping
  pointer-events
  points
  pointsAtX
  pointsAtY
  pointsAtZ
  preserveAlpha
  preserveAspectRatio
  primitiveUnits
  r
  radius
  referrerPolicy
  refX
  refY
  rel
  rendering-intent
  repeatCount
  repeatDur
  requiredExtensions
  requiredFeatures
  restart
  result
  rotate
  rx
  ry
  scale
  seed
  shape-rendering
  slope
  spacing
  specularConstant
  specularExponent
  speed
  spreadMethod
  startOffset
  stdDeviation
  stemh
  stemv
  stitchTiles
  stop-color
  stop-opacity
  strikethrough-position
  strikethrough-thickness
  string
  stroke
  stroke-dasharray
  stroke-dashoffset
  stroke-linecap
  stroke-linejoin
  stroke-miterlimit
  stroke-opacity
  stroke-width
  style
  surfaceScale
  systemLanguage
  tabindex
  tableValues
  target
  targetX
  targetY
  text-anchor
  text-decoration
  text-rendering
  textLength
  to
  transform
  transform-origin
  type
  u1
  u2
  underline-position
  underline-thickness
  unicode
  unicode-bidi
  unicode-range
  units-per-em
  v-alphabetic
  v-hanging
  v-ideographic
  v-mathematical
  values
  vector-effect
  version
  vert-adv-y
  vert-origin-x
  vert-origin-y
  viewBox
  viewTarget
  visibility
  width
  widths
  word-spacing
  writing-mode
  x
  x-height
  x1
  x2
  xChannelSelector
  xlink:actuate
  xlink:arcrole
  xlink:href
  xlink:role
  xlink:show
  xlink:title
  xlink:type
  xml:base
  xml:lang
  xml:space
  y
  y1
  y2
  yChannelSelector
  z
  zoomAndPan
]

def do_attributes
  attributes_with_element_list = []
  attributes_with_element_hash = {}
  attributes_with_any_list = []
  attributes_deprecated = []

  ATTRIBUTES.each do |attribute|
    file = "Attribute/#{attribute}.html"
    file = "Attribute/#{attribute.capitalize}.html" unless File.exist?(file)
    next unless File.exist?(file)

    lines = File.readlines(file)

    if (i = lines.find_index { |line| line =~ /following SVG element[s]?:/ })
      attributes_with_element_list << attribute

      start = i + 1
      lines[start..(start + 100)].each do |line|
        if (m = line.match(%r{"[.][.]/Element/(?<element>[^.]+).html"}))
          (attributes_with_element_hash[attribute] ||= []) << m[:element]
        end
      end
    end

    if (lines.find { |line| line =~ /with any SVG element/ })
      attributes_with_any_list << attribute
    end

    if (lines.find { |line| line =~ %r{<strong>Deprecated:?</strong>} })
      attributes_deprecated << attribute
    end
  end

  warn "All attributes: #{ATTRIBUTES.size}"
  warn
  warn "With element: #{attributes_with_element_list.size}"
  warn
  attributes_without_element_list = ATTRIBUTES - attributes_with_element_list
  warn "Without element: #{attributes_without_element_list.size}"
  warn
  warn "With any element: #{attributes_with_any_list.size}"
  warn
  warn "Deprecated: #{attributes_deprecated.size}"
  warn
  # warn attributes_with_any_list
  # warn attributes_deprecated
  puts attributes_without_element_list
  exit

  puts  "specifications("
  attributes_with_element_hash.each do |attribute, elements|
    puts %{  "#{attribute}": %i[}
    elements.each do |element|
      puts "    #{element}"
    end
    puts "  ],"

    puts
  end
  puts ")"
end

def do_elements
  elements_contentful = []

  ELEMENTS.each do |element|
    file = "Element/#{element}.html"
    file = "Element/#{element.capitalize}.html" unless File.exist?(file)
    next unless File.exist?(file)

    lines = File.readlines(file)

    # if (i = lines.find_index { |line| line =~ %r{[<]th.*Permitted content[<][/]th[>]} })
    if (i = lines.find_index { |line| line =~ %r{Permitted content} })
      start = i
      lines[start..(start + 10)].each do |line|
        if line =~ /[Cc]haracter data/
          elements_contentful << element
        end
      end
    end
  end

  puts elements_contentful
end

do_elements