Unicode superscripts and subscripts normalized via NFKC

superscripts_subscripts_normalized_via_nfkc.yml

---
:subscripts: 
  "₀": '0'
  "₁": '1'
  "₂": '2'
  "₃": '3'
  "₄": '4'
  "₅": '5'
  "₆": '6'
  "₇": '7'
  "₈": '8'
  "₉": '9'
  "₍": "("
  "₎": ")"
  "₊": "+"
  "₌": "="
  "₋": "−"
  ₐ: a
  ₑ: e
  ₕ: h
  ᵢ: i
  ⱼ: j
  ₖ: k
  ₗ: l
  ₘ: m
  ₙ: n
  ₒ: o
  ₚ: p
  ᵣ: r
  ₛ: s
  ₜ: t
  ᵤ: u
  ᵥ: v
  ₓ: x
  ₔ: ə
  ᵦ: β
  ᵧ: γ
  ᵨ: ρ
  ᵩ: φ
  ᵪ: χ
:superscripts: 
  "⁰": '0'
  "¹": '1'
  "²": '2'
  "³": '3'
  "⁴": '4'
  "⁵": '5'
  "⁶": '6'
  "⁷": '7'
  "⁸": '8'
  "⁹": '9'
  "⁽": "("
  "⁾": ")"
  "⁺": "+"
  "⁼": "="
  ᴬ: A
  ᴮ: B
  ᴰ: D
  ᴱ: E
  ᴳ: G
  ᴴ: H
  ᴵ: I
  ᴶ: J
  ᴷ: K
  ᴸ: L
  ᴹ: M
  ᴺ: N
  ᴼ: O
  ᴾ: P
  ᴿ: R
  ᵀ: T
  ᵁ: U
  ⱽ: V
  ᵂ: W
  ª: a
  ᵃ: a
  ᵇ: b
  ᶜ: c
  ᵈ: d
  ᵉ: e
  ᶠ: f
  ᵍ: g
  ʰ: h
  ⁱ: i
  ʲ: j
  ᵏ: k
  ˡ: l
  ᵐ: m
  ⁿ: n
  º: o
  ᵒ: o
  ᵖ: p
  ʳ: r
  ˢ: s
  ᵗ: t
  ᵘ: u
  ᵛ: v
  ʷ: w
  ˣ: x
  ʸ: y
  ᶻ: z
  ᴭ: Æ
  ᶞ: ð
  ꟸ: Ħ
  ᵑ: ŋ
  ꟹ: œ
  ᴲ: Ǝ
  ᶵ: ƫ
  ᴽ: Ȣ
  ᵄ: ɐ
  ᵅ: ɑ
  ᶛ: ɒ
  ᵓ: ɔ
  ᶝ: ɕ
  ᵊ: ə
  ᵋ: ɛ
  ᵌ: ɜ
  ᶟ: ɜ
  ᶡ: ɟ
  ᶢ: ɡ
  ˠ: ɣ
  ᶣ: ɥ
  ʱ: ɦ
  ᶤ: ɨ
  ᶥ: ɩ
  ᶦ: ɪ
  ꭞ: ɫ
  ᶩ: ɭ
  ᵚ: ɯ
  ᶭ: ɰ
  ᶬ: ɱ
  ᶮ: ɲ
  ᶯ: ɳ
  ᶰ: ɴ
  ᶱ: ɵ
  ᶲ: ɸ
  ʴ: ɹ
  ʵ: ɻ
  ʶ: ʁ
  ᶳ: ʂ
  ᶴ: ʃ
  ᶶ: ʉ
  ᶷ: ʊ
  ᶹ: ʋ
  ᶺ: ʌ
  ᶼ: ʐ
  ᶽ: ʑ
  ᶾ: ʒ
  ˤ: ʕ
  ᶨ: ʝ
  ᶫ: ʟ
  ᵝ: β
  ᵞ: γ
  ᵟ: δ
  ᶿ: θ
  ᵠ: φ
  ᵡ: χ
  ᵸ: н
  ꚜ: ъ
  ꚝ: ь
  ჼ: ნ
  ᵆ: ᴂ
  ᵔ: ᴖ
  ᵕ: ᴗ
  ᶸ: ᴜ
  ᵙ: ᴝ
  ᵜ: ᴥ
  ᶧ: ᵻ
  ᶪ: ᶅ
  "⁻": "−"
  ⵯ: ⵡ
  "㆒": 一
  "㆜": 丁
  "㆔": 三
  "㆖": 上
  "㆘": 下
  "㆛": 丙
  "㆗": 中
  "㆚": 乙
  "㆓": 二
  "㆟": 人
  "㆕": 四
  "㆞": 地
  "㆝": 天
  "㆙": 甲
  ꭜ: ꜧ
  ꝰ: ꝯ
  ꭝ: ꬷ
  ꭟ: ꭒ

superscripts_subscripts_normalized_via_nfkc_as_ruby_regex.yml

--- # As Ruby regular expressions:
:subscripts: !ruby/regexp /[₀₁₂₃₄₅₆₇₈₉₍₎₊₌₋ₐₑₕᵢⱼₖₗₘₙₒₚᵣₛₜᵤᵥₓₔᵦᵧᵨᵩᵪ]+/
:superscripts: !ruby/regexp /[⁰¹²³⁴⁵⁶⁷⁸⁹⁽⁾⁺⁼ᴬᴮᴰᴱᴳᴴᴵᴶᴷᴸᴹᴺᴼᴾᴿᵀᵁⱽᵂªᵃᵇᶜᵈᵉᶠᵍʰⁱʲᵏˡᵐⁿºᵒᵖʳˢᵗᵘᵛʷˣʸᶻᴭᶞꟸᵑꟹᴲᶵᴽᵄᵅᶛᵓᶝᵊᵋᵌᶟᶡᶢˠᶣʱᶤᶥᶦꭞᶩᵚᶭᶬᶮᶯᶰᶱᶲʴʵʶᶳᶴᶶᶷᶹᶺᶼᶽᶾˤᶨᶫᵝᵞᵟᶿᵠᵡᵸꚜꚝჼᵆᵔᵕᶸᵙᵜᶧᶪ⁻ⵯ㆒㆜㆔㆖㆘㆛㆗㆚㆓㆟㆕㆞㆝㆙ꭜꝰꭝꭟ]+/

unicode_sub_and_superscripts_to_sub_and_sup_tags.rb

# Method for processing HTML to replace Unicode subscript and superscript 
# characters with normalized characters wrapped in `<sub>` and `<sup>` tags. 
# Uses regular expressions to identify sequences of sub- and superscripts. 
# Examples:
# 
#     "1ˢᵗ 2ⁿᵈ 3ʳᵈ" => "1<sup>st</sup> 2<sup>nd</sup> 3<sup>rd</sup>"
#     "PO₄³⁻ ion" => "PO<sub>4</sub><sup>3−</sup> ion"

REGEXPS = {
  # Less-thorough regular expressions: 
  sub: /[₀₁₂₃₄₅₆₇₈₉₍₎₊₌₋ₐₑₕᵢⱼₖₗₘₙₒₚᵣₛₜᵤᵥₓ]+/, 
  sup: /[⁰¹²³⁴⁵⁶⁷⁸⁹⁽⁾⁺⁼⁻ᴬᴮᴰᴱᴳᴴᴵᴶᴷᴸᴹᴺᴼᴾᴿᵀᵁⱽᵂªᵃᵇᶜᵈᵉᶠᵍʰⁱʲᵏˡᵐⁿºᵒᵖʳˢᵗᵘᵛʷˣʸᶻ]+/, 

  # # More-thorough versions: 
  # sub: /[₀₁₂₃₄₅₆₇₈₉₍₎₊₌₋ₐₑₕᵢⱼₖₗₘₙₒₚᵣₛₜᵤᵥₓₔᵦᵧᵨᵩᵪ]+/, 
  # sup: /[⁰¹²³⁴⁵⁶⁷⁸⁹⁽⁾⁺⁼ᴬᴮᴰᴱᴳᴴᴵᴶᴷᴸᴹᴺᴼᴾᴿᵀᵁⱽᵂªᵃᵇᶜᵈᵉᶠᵍʰⁱʲᵏˡᵐⁿºᵒᵖʳˢᵗᵘᵛʷˣʸᶻᴭᶞꟸᵑꟹᴲᶵᴽᵄᵅᶛᵓᶝᵊᵋᵌᶟᶡᶢˠᶣʱᶤᶥᶦꭞᶩᵚᶭᶬᶮᶯᶰᶱᶲʴʵʶᶳᶴᶶᶷᶹᶺᶼᶽᶾˤᶨᶫᵝᵞᵟᶿᵠᵡᵸꚜꚝჼᵆᵔᵕᶸᵙᵜᶧᶪ⁻ⵯ㆒㆜㆔㆖㆘㆛㆗㆚㆓㆟㆕㆞㆝㆙ꭜꝰꭝꭟ]+/, 
}

# "Dihydrogen monoxide, or H₂O, can be very dangerous."
# => "Dihydrogen monoxide, or H<sub>2</sub>O, can be very dangerous."
def subscripts_to_sub_tags(html)
  capture_normalize_and_wrap(html, 
    REGEXPS[:sub], # /[₀₁₂₃₄₅ ...
    'sub')
end

# "He wore a white <i>gat</i>¹."
# => "He wore a white <i>gat</i><sup>1</sup>."
def superscripts_to_sup_tags(html)
  capture_normalize_and_wrap(html, 
    REGEXPS[:sup], # /[⁰¹²³⁴⁵ ...
    'sup')
end

def capture_normalize_and_wrap(html, rx, tag, log: true)
  scanned,to_scan = "",html
  while m=rx.match(to_scan)
    str = "<#{tag}>#{m[0].unicode_normalize(:nfkc)}</#{tag}>"
    (puts str) if log
    scanned += (m.pre_match + str)
    to_scan = m.post_match
  end
  return scanned + to_scan
end

# "PO₄³⁻" => "PO<sub>4</sub><sup>3−</sup>"
def process_html(html="PO₄³⁻")
  REGEXPS.each do |tag, rx|
    html = capture_normalize_and_wrap(html, rx, tag)
  end
  return html
end

def process_html_file(in_fname='sample_in.html', out_fname='sample_out.html')
  html = process_html File.read(in_fname)
  File.write(out_fname, html)
  return html
end