1
0
Fork 0
mirror of https://github.com/ruby/ruby.git synced 2022-11-09 12:17:21 -05:00

normalize.rb: remove redundant hash

* lib/unicode_normalize/normalize.rb (UnicodeNormalize): REGEXP_K
  matches only single chars which are keys of KOMPATIBLE_TABLE, so
  string in nfkd_one is always single char and one of the key of
  KOMPATIBLE_TABLE, that is that the default proc of NF_HASH_K only
  copies a pair in KOMPATIBLE_TABLE.  therefore NF_HASH_K is a
  part of KOMPATIBLE_TABLE always, and just redundant.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@49929 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
This commit is contained in:
nobu 2015-03-11 03:56:44 +00:00
parent 97e21517a3
commit 84b5bb9802

View file

@ -21,10 +21,6 @@ module UnicodeNormalize
hash.shift if hash.length>MAX_HASH_LENGTH # prevent DoS attack
hash[key] = nfc_one(key)
end
NF_HASH_K = Hash.new do |hash, key|
hash.shift if hash.length>MAX_HASH_LENGTH # prevent DoS attack
hash[key] = nfkd_one(key)
end
## Constants For Hangul
# for details such as the meaning of the identifiers below, please see
@ -88,10 +84,6 @@ module UnicodeNormalize
canonical_ordering_one(hangul_decomp_one(string))
end
def self.nfkd_one(string)
string.chars.map! {|c| KOMPATIBLE_TABLE[c] || c}.join('')
end
def self.nfc_one(string)
nfd_string = nfd_one string
start = nfd_string[0]
@ -119,9 +111,9 @@ module UnicodeNormalize
when :nfd then
string.gsub REGEXP_D, NF_HASH_D
when :nfkc then
string.gsub(REGEXP_K, NF_HASH_K).gsub REGEXP_C, NF_HASH_C
string.gsub(REGEXP_K, KOMPATIBLE_TABLE).gsub(REGEXP_C, NF_HASH_C)
when :nfkd then
string.gsub(REGEXP_K, NF_HASH_K).gsub REGEXP_D, NF_HASH_D
string.gsub(REGEXP_K, KOMPATIBLE_TABLE).gsub(REGEXP_D, NF_HASH_D)
else
raise ArgumentError, "Invalid normalization form #{form}."
end