Sha256: 9219b80f07fa1134b59e74f3e376d5e04d6a48764a968b9c8feeca7526441435
Contents?: true
Size: 1.64 KB
Versions: 23
Compression:
Stored size: 1.64 KB
Contents
# frozen_string_literal: true
module Asciidoctor
module PDF
module Sanitizer
XMLSpecialChars = {
'<' => '<',
'>' => '>',
'&' => '&',
}
XMLSpecialCharsRx = /(?:#{XMLSpecialChars.keys.join '|'})/
InverseXMLSpecialChars = XMLSpecialChars.invert
InverseXMLSpecialCharsRx = /[#{InverseXMLSpecialChars.keys.join}]/
(BuiltInNamedEntities = {
'amp' => '&',
'apos' => ?',
'gt' => '>',
'lt' => '<',
'nbsp' => ' ',
'quot' => '"',
}).default = '?'
SanitizeXMLRx = /<[^>]+>/
CharRefRx = /&(?:amp;)?(?:([a-z][a-z]+\d{0,2})|#(?:(\d\d\d{0,4})|x(\h\h\h{0,3})));/
UnescapedAmpersandRx = /&(?!(?:[a-z][a-z]+\d{0,2}|#(?:\d\d\d{0,4}|x\h\h\h{0,3}));)/
# Strip leading, trailing and repeating whitespace, remove XML tags and
# resolve all entities in the specified string.
#
# FIXME: move to a module so we can mix it in elsewhere
# FIXME: add option to control escaping entities, or a filter mechanism in general
def sanitize string
string = string.gsub SanitizeXMLRx, '' if string.include? '<'
string = string.gsub(CharRefRx) { $1 ? BuiltInNamedEntities[$1] : ([$2 ? $2.to_i : ($3.to_i 16)].pack 'U1') } if string.include? '&'
string.strip.tr_s ' ', ' '
end
def escape_xml string
string.gsub InverseXMLSpecialCharsRx, InverseXMLSpecialChars
end
def escape_amp string
string.gsub UnescapedAmpersandRx, '&'
end
def encode_quotes string
(string.include? '"') ? (string.gsub '"', '"') : string
end
end
end
end
Version data entries
23 entries across 23 versions & 1 rubygems