1 files changed, 37 insertions, 29 deletions

diff --git a/lib/rubygems/text.rb b/lib/rubygems/text.rb
index b944b62c27..0550dc473d 100644
--- a/lib/rubygems/text.rb
+++ b/lib/rubygems/text.rb
@@ -1,16 +1,23 @@
 # frozen_string_literal: true
-require 'rubygems'
 
 ##
 # A collection of text-wrangling methods
 
 module Gem::Text
-
   ##
   # Remove any non-printable characters and make the text suitable for
   # printing.
   def clean_text(text)
-    text.gsub(/[\000-\b\v-\f\016-\037\177]/, ".".freeze)
+    text = text.gsub(/[\000-\b\v-\f\016-\037\177]/, ".")
+
+    # Match C1 control characters (U+0080-U+009F) as codepoints. This requires
+    # a valid UTF-8 string so the regexp does not split a multibyte sequence;
+    # strings in other encodings are left unchanged.
+    if text.encoding == Encoding::UTF_8 && text.valid_encoding?
+      text = text.gsub(/[\u0080-\u009f]/, ".")
+    end
+
+    text
   end
 
   def truncate_text(text, description, max_length = 100_000)
@@ -23,12 +30,12 @@ module Gem::Text
   # Wraps +text+ to +wrap+ characters and optionally indents by +indent+
   # characters
 
-  def format_text(text, wrap, indent=0)
+  def format_text(text, wrap, indent = 0)
     result = []
     work = clean_text(text)
 
     while work.length > wrap do
-      if work =~ /^(.{0,#{wrap}})[ \n]/ then
+      if work =~ /^(.{0,#{wrap}})[ \n]/
         result << $1.rstrip
         work.slice!(0, $&.length)
       else
@@ -40,47 +47,48 @@ module Gem::Text
     result.join("\n").gsub(/^/, " " * indent)
   end
 
-  def min3 a, b, c # :nodoc:
-    if a < b && a < c then
+  def min3(a, b, c) # :nodoc:
+    if a < b && a < c
       a
-    elsif b < c then
+    elsif b < c
       b
     else
       c
     end
   end
 
-  # This code is based directly on the Text gem implementation
   # Returns a value representing the "cost" of transforming str1 into str2
-  def levenshtein_distance str1, str2
-    s = str1
-    t = str2
-    n = s.length
-    m = t.length
-
-    return m if (0 == n)
-    return n if (0 == m)
+  # Vendored version of DidYouMean::Levenshtein.distance from the ruby/did_you_mean gem @ 1.4.0
+  # https://github.com/ruby/did_you_mean/blob/2ddf39b874808685965dbc47d344cf6c7651807c/lib/did_you_mean/levenshtein.rb#L7-L37
+  def levenshtein_distance(str1, str2)
+    n = str1.length
+    m = str2.length
+    return m if n.zero?
+    return n if m.zero?
 
     d = (0..m).to_a
     x = nil
 
-    str1.each_char.each_with_index do |char1,i|
-      e = i+1
+    # to avoid duplicating an enumerable object, create it outside of the loop
+    str2_codepoints = str2.codepoints
 
-      str2.each_char.each_with_index do |char2,j|
-        cost = (char1 == char2) ? 0 : 1
+    str1.each_codepoint.with_index(1) do |char1, i|
+      j = 0
+      while j < m
+        cost = char1 == str2_codepoints[j] ? 0 : 1
         x = min3(
-             d[j+1] + 1, # insertion
-             e + 1,      # deletion
-             d[j] + cost # substitution
-            )
-        d[j] = e
-        e = x
+          d[j + 1] + 1, # insertion
+          i + 1,      # deletion
+          d[j] + cost # substitution
+        )
+        d[j] = i
+        i = x
+
+        j += 1
       end
-
       d[m] = x
     end
 
-    return x
+    x
   end
 end