Created
October 21, 2012 19:06
-
-
Save gbedardsice/3928112 to your computer and use it in GitHub Desktop.
Verifying if a ruby string contains one or more accents
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
# encoding: utf-8 | |
class String | |
# The extended characters map used by contains_accent. The accented characters | |
# are coded here using their numerical equivalent to sidestep encoding issues. | |
# These correspond to ISO-8859-1 encoding. | |
ACCENTS_MAPPING = { | |
'E' => [200,201,202,203], | |
'e' => [232,233,234,235], | |
'A' => [192,193,194,195,196,197], | |
'a' => [224,225,226,227,228,229,230], | |
'C' => [199], | |
'c' => [231], | |
'O' => [210,211,212,213,214,216], | |
'o' => [242,243,244,245,246,248], | |
'I' => [204,205,206,207], | |
'i' => [236,237,238,239], | |
'U' => [217,218,219,220], | |
'u' => [249,250,251,252], | |
'N' => [209], | |
'n' => [241], | |
'Y' => [221], | |
'y' => [253,255], | |
'AE' => [306], | |
'ae' => [346], | |
'OE' => [188], | |
'oe' => [189] | |
} | |
def contains_accent? | |
retval = false | |
str = String.new(self) | |
String::ACCENTS_MAPPING.each do |letter, accents| | |
packed = accents.pack('U*') | |
rxp = Regexp.new("[#{packed}]", nil) | |
retval = true if str.scan(rxp).size > 0 | |
end | |
retval | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment