mirror of
https://github.com/StrawberryMaster/wayback-machine-downloader.git
synced 2025-12-17 17:56:44 +00:00
Refactor tidy_bytes.rb
I'm not sure if we can easily determine the encoding behind each site (and I don't think Wayback Machine does that), *but* we can at least translate it and get it to download. This should be mostly useful for other, non-Western European languages. See #25
This commit is contained in:
parent
2bf04aff48
commit
bc868e6b39
@ -1,74 +1,42 @@
|
|||||||
# frozen_string_literal: true
|
# frozen_string_literal: true
|
||||||
|
|
||||||
|
# essentially, this is for converting a string with a potentially
|
||||||
|
# broken or unknown encoding into a valid UTF-8 string
|
||||||
module TidyBytes
|
module TidyBytes
|
||||||
# precomputing CP1252 to UTF-8 mappings for bytes 128-159
|
def tidy_bytes
|
||||||
CP1252_MAP = (128..159).map do |byte|
|
# return if the string is already valid UTF-8
|
||||||
case byte
|
return self if self.valid_encoding? && self.encoding == Encoding::UTF_8
|
||||||
when 128 then [226, 130, 172] # EURO SIGN
|
|
||||||
when 130 then [226, 128, 154] # SINGLE LOW-9 QUOTATION MARK
|
|
||||||
when 131 then [198, 146] # LATIN SMALL LETTER F WITH HOOK
|
|
||||||
when 132 then [226, 128, 158] # DOUBLE LOW-9 QUOTATION MARK
|
|
||||||
when 133 then [226, 128, 166] # HORIZONTAL ELLIPSIS
|
|
||||||
when 134 then [226, 128, 160] # DAGGER
|
|
||||||
when 135 then [226, 128, 161] # DOUBLE DAGGER
|
|
||||||
when 136 then [203, 134] # MODIFIER LETTER CIRCUMFLEX ACCENT
|
|
||||||
when 137 then [226, 128, 176] # PER MILLE SIGN
|
|
||||||
when 138 then [197, 160] # LATIN CAPITAL LETTER S WITH CARON
|
|
||||||
when 139 then [226, 128, 185] # SINGLE LEFT-POINTING ANGLE QUOTATION MARK
|
|
||||||
when 140 then [197, 146] # LATIN CAPITAL LIGATURE OE
|
|
||||||
when 142 then [197, 189] # LATIN CAPITAL LETTER Z WITH CARON
|
|
||||||
when 145 then [226, 128, 152] # LEFT SINGLE QUOTATION MARK
|
|
||||||
when 146 then [226, 128, 153] # RIGHT SINGLE QUOTATION MARK
|
|
||||||
when 147 then [226, 128, 156] # LEFT DOUBLE QUOTATION MARK
|
|
||||||
when 148 then [226, 128, 157] # RIGHT DOUBLE QUOTATION MARK
|
|
||||||
when 149 then [226, 128, 162] # BULLET
|
|
||||||
when 150 then [226, 128, 147] # EN DASH
|
|
||||||
when 151 then [226, 128, 148] # EM DASH
|
|
||||||
when 152 then [203, 156] # SMALL TILDE
|
|
||||||
when 153 then [226, 132, 162] # TRADE MARK SIGN
|
|
||||||
when 154 then [197, 161] # LATIN SMALL LETTER S WITH CARON
|
|
||||||
when 155 then [226, 128, 186] # SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
|
|
||||||
when 156 then [197, 147] # LATIN SMALL LIGATURE OE
|
|
||||||
when 158 then [197, 190] # LATIN SMALL LETTER Z WITH CARON
|
|
||||||
when 159 then [197, 184] # LATIN SMALL LETTER Y WITH DIAERESIS
|
|
||||||
else nil # ANYTHING ELSE...
|
|
||||||
end
|
|
||||||
end.freeze
|
|
||||||
|
|
||||||
# precomputing all possible byte conversions
|
# create a mutable copy so we don't modify the original string
|
||||||
CP1252_TO_UTF8 = Array.new(256) do |b|
|
str = self.dup
|
||||||
if (128..159).cover?(b)
|
|
||||||
CP1252_MAP[b - 128]&.pack('C*')
|
# attempt to encode to UTF-8
|
||||||
elsif b < 128
|
begin
|
||||||
b.chr
|
return str.encode(Encoding::UTF-8)
|
||||||
else
|
rescue Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError
|
||||||
b < 192 ? [194, b].pack('C*') : [195, b - 64].pack('C*')
|
end
|
||||||
|
|
||||||
|
# if it failed, force the encoding to ISO-8859-1, transcode the
|
||||||
|
# string to UTF-8, and use replacement options for any characters
|
||||||
|
# that might still be problematic
|
||||||
|
str.force_encoding(Encoding::ISO_8859_1).encode(Encoding::UTF_8, invalid: :replace, undef: :replace, replace: '<27>')
|
||||||
|
end
|
||||||
|
|
||||||
|
def tidy_bytes!
|
||||||
|
replace(self.tidy_bytes)
|
||||||
end
|
end
|
||||||
end.freeze
|
|
||||||
|
|
||||||
def self.included(base)
|
def self.included(base)
|
||||||
base.class_eval do
|
base.send(:include, InstanceMethods)
|
||||||
def tidy_bytes(force = false)
|
|
||||||
return nil if empty?
|
|
||||||
|
|
||||||
if force
|
|
||||||
buffer = String.new(capacity: bytesize)
|
|
||||||
each_byte { |b| buffer << CP1252_TO_UTF8[b] }
|
|
||||||
return buffer.force_encoding(Encoding::UTF_8)
|
|
||||||
end
|
end
|
||||||
|
|
||||||
begin
|
module InstanceMethods
|
||||||
encode('UTF-8')
|
def tidy_bytes
|
||||||
rescue Encoding::UndefinedConversionError, Encoding::InvalidByteSequenceError
|
TidyBytes.instance_method(:tidy_bytes).bind(self).call
|
||||||
buffer = String.new(capacity: bytesize)
|
|
||||||
scrub { |b| CP1252_TO_UTF8[b.ord] }
|
|
||||||
end
|
|
||||||
end
|
end
|
||||||
|
|
||||||
def tidy_bytes!(force = false)
|
def tidy_bytes!
|
||||||
result = tidy_bytes(force)
|
TidyBytes.instance_method(:tidy_bytes!).bind(self).call
|
||||||
result ? replace(result) : self
|
|
||||||
end
|
|
||||||
end
|
end
|
||||||
end
|
end
|
||||||
end
|
end
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user