bco-htmlproof

#!/usr/bin/env ruby

require 'html/proofer'

if ARGV[0].nil?
  path_to_check="./_site"
else
  path_to_check=ARGV[0]
end

## Will throw an exception (exiting false) if any internal links don't
## work. The Makefile will terminate on the failure
HTML::Proofer.new(
    ## To test, uncomment the array below and comment out ./_site and :disable_external
    #[ "/foo/bar#baz", "/foo/bar", "#", "#wallet", "/foo.css", "/bar.png", "/zh_TW/bitcoin-for-businesses" ],
    path_to_check,

    {
        ## Disable external link checking by default to avoid spurious
        ## Travis CI failures. TODO: take an argument to optionally
        ## enable external link checking as part of the Makefile
        ## manual checks
        :disable_external => true,

        ## Check whether HTML is well-formed
        :check_html => true,

        ## Links to ignore
        :href_ignore => [
          '#',           ## hrefs pointing to the current page (htmlproofer fails them)
          /^$/,          ## anchors with no href attribute set (for clickable javascript elements)
          /^\/bin/,      ## /bin dir is not part of repository; holds Bitcoin Core binaries
          'bitcoin:3FkenCiXpSLqD8L79intRNXUgjRoH9sjXa',    ## bitcoin address handlers
          /^\/stats/     ## /stats dir is not part of repository; generated by separate stats script
        ],

        ## Mangle links. If we enable external link checking, this will
        ## require updating
        :href_swap => {
          ## (Hack) Append '$' to the ends of filenames we don't want to append .html to
          /(css|png|rss|pdf|jpg|asc|xml)$/ => '\1$',

          ## Append .html to end of most URLs so proofer can find the local files
          /^(
           [^#]+   ## Don't match URL containing a hash, we'll deal with them separately
           [^\/$]  ## Don't match URLs ending in a slash or $
          )$/x => '\1.html',

          ## Insert .html between page and anchor, but only if there's a
          ## page name
          /^(.+)(#.+)/ => '\1.html\2',

          /\/(.html#.+)/ => '\1',

          ## (Un-hack) Remove previously-appended '$' from URLs
          /\$$/ => '',
        },

        ## It'd be nice if we had a _local_config.yaml file or something
        ## for settings specific to particular systems, but for now I
        ## think 2 is a good setting for Travis CI ("1.5 processors")
        ## and me (usually 2 processors)
        :parallel => { :in_processes => 2 }
    }
).run