Created
June 6, 2020 00:55
-
-
Save mackuba/2f67a565d287f7833d6c5378c9b8ce0a to your computer and use it in GitHub Desktop.
Code for formatting hand-written plain text notes into formatted HTML
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class NoteCompiler | |
def build(text, info) | |
note = NoteContent.new(text, info) | |
note.compile_html | |
end | |
class NoteContent | |
def initialize(text, info) | |
@text = text | |
@info = info | |
end | |
def compile_html | |
@html = '' | |
@code_block = nil | |
@text_block = '' | |
@current_list = nil | |
@text.lines.each do |line| | |
line.chomp!('') | |
content = line.strip | |
if @code_block | |
if content == '```' | |
close_code_block | |
else | |
@code_block << line + "\n" | |
end | |
else | |
case content | |
when '```' | |
close_text_block | |
open_code_block | |
when '' | |
close_text_block | |
when /^\-\>? (.*)$/ | |
open_list('ul') | |
@text_block << "<li>#{process_line($1)}</li>\n" | |
when /^\d+\. (.*)$/ | |
open_list('ol') | |
@text_block << "<li>#{process_line(content)}</li>\n" # todo | |
when /^\=+\s*(\w.*)$/ | |
close_text_block | |
@html << %(<h3>#{$1}</h3>\n) | |
else | |
close_list | |
@text_block << "<p>#{process_line(content)}</p>\n" | |
end | |
end | |
end | |
if @code_block | |
raise "Unfinished code block" | |
else | |
close_text_block | |
end | |
@html | |
end | |
private | |
def open_code_block | |
@html << %(<pre class="brush: swift">) | |
@code_block = '' | |
end | |
def close_code_block | |
@html << process_code_block(@code_block.chop) + %(</pre>\n) | |
@code_block = nil | |
end | |
def process_code_block(code) | |
code.gsub(/\</, '<').gsub(/\>/, '>') | |
end | |
def close_text_block | |
close_list | |
if @text_block.length > 0 | |
@html << %(<div class="block">\n#{@text_block}</div>\n) | |
@text_block = '' | |
end | |
end | |
def open_list(list_type) | |
if @current_list.nil? | |
@text_block << "<#{list_type}>\n" | |
elsif @current_list != list_type | |
@text_block << "</#{@current_list}>\n" | |
@text_block << "<#{list_type}>\n" | |
end | |
@current_list = list_type | |
end | |
def close_list | |
if @current_list | |
@text_block << "</#{@current_list}>\n" | |
@current_list = nil | |
end | |
end | |
def process_line(line) | |
line = line.clone | |
line.gsub!(/\&/, '&') | |
line.gsub!(/\</, '<') | |
line.gsub!(/\>/, '>') | |
line.gsub!(/^(\p{Pi}.*\p{Pf})$/, "<em>\\1</em>") | |
pieces = line.split(/`/, -1) | |
raise "Unmatched code block mark: #{line.inspect}" if pieces.length.even? | |
pieces.each_with_index.map { |piece, i| | |
if i.even? | |
process_line_piece(piece) | |
else | |
%(<code>#{piece}</code>) | |
end | |
}.join | |
end | |
def process_line_piece(line) | |
line = line.clone | |
code_blocks = find_code_blocks(line) | |
updated_code_blocks = apply_code_blocks(code_blocks, line) | |
replacements = [ | |
[/ - /, ' – '], | |
[/<->/, ' ⭤ '], | |
[/->/, ' ⭢ '], | |
] | |
replacements.each do |pattern, new_text| | |
line.gsub!(pattern) do | |
range = Regexp.last_match.offset(0) | |
if updated_code_blocks.any? { |s, f| s < range[1] && f > range[0] } | |
line[range[0]...range[1]] | |
else | |
new_text | |
end | |
end | |
end | |
# don't break line before emoticons | |
[':)', ';)', ':>', ':]', ':(', ':\\', ':/', ':|', 'o_O'].each do |emot| | |
regexp = emot.split(//).map { |ch| "\\" + ch }.join | |
line.gsub!(%r(\s#{regexp}), " #{emot}") | |
end | |
line | |
end | |
def find_code_blocks(line) | |
code_blocks = [] | |
non_code_identifiers = %w(SwiftUI e.g. e.g iPhone iPhones iPad iPads WatchConnectivity) | |
non_code_patterns = [/^\w+Kit$/, /^Core[A-Z]\w+$/, /^[a-z]+OS$/, /^[A-Z]+$/, /^[A-Z]+s$/, /^[A-Z]+Ses$/] | |
code_regexps = [ | |
# x(), x.y() | |
[/(\B(\.|@))?\b(\w[\w\.\*]*\w\([^)]*\))\B/, 0], | |
# x { ... }, x() { ... } | |
[/(\B(\.|@))?\b(\w[\w\.\*]*\w(\([^)]*\))?\s*\{[^}]*\})\B/, 0], | |
# x -> y | |
[/\b([a-z][\w\.\*]*[A-Z][\w\.\*]*\w\s*->\s*\w*(\?\B|\*\B|\w\b))/, 0], | |
# x() -> y | |
[/\b(\w[\w\.\*]*\w\([^)]*\)\s*->\s*\w*(\?\B|\*\B|\w\b))/, 0], | |
# x:y: -> y | |
[/\b(\w[\w\*]*\:(\w[\w\*]*\:)+\s*->\s*\w*(\?\B|\*\B|\w\b))/, 0], | |
# x.y | |
[/\b([\w\*]+\.([\w\*]+\*\B|[\w\*]+\b|\*\B))/, 0], | |
# X<Y> | |
[/\b([\w\*]+<[\w\*]+>)\B/, 0], | |
# @zxc | |
[/\B@([\w\*]+)(\*\B|\b)/, 0], | |
# identifier | |
[/(\B\.)?\b(\w[\w\*]*[A-Z][\w\*]*)(\*\B|\?\B|\b)/, 0], | |
# identifier: | |
[/\b([a-z][\w\*]*[A-Z][\w\*]*)\:\B/, 1], | |
# foo:will:bar: | |
[/\b\w[\w\*]*\:(\w[\w\*]*\:)+\B/, 0] | |
] | |
code_regexps.each do |pattern, i| | |
line.scan(pattern) do |names| | |
match = Regexp.last_match | |
name = match[i] | |
unless non_code_identifiers.include?(name) || non_code_patterns.any? { |pt| name =~ pt } | |
code_blocks << match.offset(0) | |
end | |
end | |
end | |
code_blocks | |
end | |
def apply_code_blocks(code_blocks, line) | |
code_blocks.sort_by(&:first).reduce([]) { |list, block| | |
if list.empty? | |
[block] | |
elsif block[0] <= list.last[1] | |
prev = list.pop | |
new_end = [prev[1], block[1]].max | |
new_block = [prev[0], new_end] | |
list + [new_block] | |
else | |
list + [block] | |
end | |
}.each_with_index.map { |block, i| | |
start = block[0] + 13 * i | |
finish = block[1] + 13 * i | |
line[start...finish] = "<code>" + line[start...finish] + "</code>" | |
[start, finish + 13] | |
} | |
end | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment