-
-
Save chrismdp/4266213 to your computer and use it in GitHub Desktop.
This file contains hidden or 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 CodePoint | |
def initialize(b) | |
@b = b | |
end | |
def hex | |
@b.to_s(16) | |
end | |
def char_windows | |
@b.chr.force_encoding("Windows-1252") | |
end | |
def char_utf8 | |
char_windows.encode("utf-8") rescue nil | |
end | |
def double_encoded | |
char_utf8.force_encoding("Windows-1252").encode("utf-8") rescue nil | |
end | |
end | |
puts (128..255).map {|b| CodePoint.new(b)}.map { |c| "#{c.hex}: #{c.char_utf8 || " "} => #{c.double_encoded}" }.join("\n") | |
r = windows_1252.map{|pair| pair[1] }.compact.map(&:first).sort.uniq.join("|") | |
bodies = Record.all.select {|s| s.body =~ /(#{r})/ }; 0 | |
bodies.map do |record| | |
[record.id, record.body[[0, (record.body =~ /(#{r})/) - 50].max, 100]] | |
end |
This file contains hidden or 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
80: € => € | |
81: => | |
82: ‚ => ‚ | |
83: ƒ => Æ’ | |
84: „ => „ | |
85: … => … | |
86: † => †| |
87: ‡ => ‡ | |
88: ˆ => ˆ | |
89: ‰ => ‰ | |
8a: Š => Å | |
8b: ‹ => ‹ | |
8c: Œ => Å’ | |
8d: => | |
8e: Ž => Ž | |
8f: => | |
90: => | |
91: ‘ => ‘ | |
92: ’ => ’ | |
93: “ => “ | |
94: ” => | |
95: • => • | |
96: – => – | |
97: — => — | |
98: ˜ => Ëœ | |
99: ™ => â„¢ | |
9a: š => Å¡ | |
9b: › => › | |
9c: œ => Å“ | |
9d: => | |
9e: ž => ž | |
9f: Ÿ => Ÿ | |
a0: => Â | |
a1: ¡ => ¡ | |
a2: ¢ => ¢ | |
a3: £ => £ | |
a4: ¤ => ¤ | |
a5: ¥ => Â¥ | |
a6: ¦ => ¦ | |
a7: § => § | |
a8: ¨ => ¨ | |
a9: © => © | |
aa: ª => ª | |
ab: « => « | |
ac: ¬ => ¬ | |
ad: => Â | |
ae: ® => ® | |
af: ¯ => ¯ | |
b0: ° => ° | |
b1: ± => ± | |
b2: ² => ² | |
b3: ³ => ³ | |
b4: ´ => ´ | |
b5: µ => µ | |
b6: ¶ => ¶ | |
b7: · => · | |
b8: ¸ => ¸ | |
b9: ¹ => ¹ | |
ba: º => º | |
bb: » => » | |
bc: ¼ => ¼ | |
bd: ½ => ½ | |
be: ¾ => ¾ | |
bf: ¿ => ¿ | |
c0: À => À | |
c1: Á => | |
c2:  => Â | |
c3: à => Ã | |
c4: Ä => Ä | |
c5: Å => Ã… | |
c6: Æ => Æ | |
c7: Ç => Ç | |
c8: È => È | |
c9: É => É | |
ca: Ê => Ê | |
cb: Ë => Ë | |
cc: Ì => ÃŒ | |
cd: Í => | |
ce: Î => ÃŽ | |
cf: Ï => | |
d0: Ð => | |
d1: Ñ => Ñ | |
d2: Ò => Ã’ | |
d3: Ó => Ó | |
d4: Ô => Ô | |
d5: Õ => Õ | |
d6: Ö => Ö | |
d7: × => × | |
d8: Ø => Ø | |
d9: ٠=> Ù | |
da: Ú => Ú | |
db: Û => Û | |
dc: Ü => Ü | |
dd: Ý => | |
de: Þ => Þ | |
df: ß => ß | |
e0: à => Ã | |
e1: á => á | |
e2: â => â | |
e3: ã => ã | |
e4: ä => ä | |
e5: å => Ã¥ | |
e6: æ => æ | |
e7: ç => ç | |
e8: è => è | |
e9: é => é | |
ea: ê => ê | |
eb: ë => ë | |
ec: ì => ì | |
ed: í => Ã | |
ee: î => î | |
ef: ï => ï | |
f0: ð => ð | |
f1: ñ => ñ | |
f2: ò => ò | |
f3: ó => ó | |
f4: ô => ô | |
f5: õ => õ | |
f6: ö => ö | |
f7: ÷ => ÷ | |
f8: ø => ø | |
f9: ù => ù | |
fa: ú => ú | |
fb: û => û | |
fc: ü => ü | |
fd: ý => ý | |
fe: þ => þ | |
ff: ÿ => ÿ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment