Fixed that TextHelper#excerpt would include one character too many (c…

…loses #11268) [Irfy]

git-svn-id: http://svn-commit.rubyonrails.org/rails/trunk@9030 5ecf4fe2-1ee6-0310-87b1-e25e094e27de

actionpack/CHANGELOG

@@ -1,5 +1,7 @@
 *SVN*
 
+* Fixed that TextHelper#excerpt would include one character too many #11268 [Irfy]
+
 * Fix more obscure nested parameter hash parsing bug.  #10797 [thomas.lee]
 
 * Added ActionView::Helpers::register_javascript/stylesheet_expansion to make it easier for plugin developers to inject multiple assets #10350 [lotswholetime]

actionpack/lib/action_view/helpers/text_helper.rb

@@ -92,21 +92,21 @@ def highlight(text, phrases, highlighter = '<strong class="highlight">\1</strong
         # Extracts an excerpt from +text+ that matches the first instance of +phrase+. 
         # The +radius+ expands the excerpt on each side of the first occurrence of +phrase+ by the number of characters
         # defined in +radius+ (which defaults to 100). If the excerpt radius overflows the beginning or end of the +text+,
-        # then the +excerpt_string+ will be prepended/appended accordingly. If the +phrase+ 
-        # isn't found, nil is returned.
+        # then the +excerpt_string+ will be prepended/appended accordingly. The resulting string will be stripped in any case.
+        # If the +phrase+ isn't found, nil is returned.
         #
         # ==== Examples
         #   excerpt('This is an example', 'an', 5) 
-        #   # => "...s is an examp..."
+        #   # => "...s is an exam..."
         #
         #   excerpt('This is an example', 'is', 5) 
-        #   # => "This is an..."
+        #   # => "This is a..."
         #
         #   excerpt('This is an example', 'is') 
         #   # => "This is an example"
         #
         #   excerpt('This next thing is an example', 'ex', 2) 
-        #   # => "...next t..."
+        #   # => "...next..."
         #
         #   excerpt('This is also an example', 'an', 8, '<chop> ')
         #   # => "<chop> is also an example"
@@ -116,10 +116,10 @@ def excerpt(text, phrase, radius = 100, excerpt_string = "...")
 
             if found_pos = text.chars =~ /(#{phrase})/i
               start_pos = [ found_pos - radius, 0 ].max
-              end_pos   = [ found_pos + phrase.chars.length + radius, text.chars.length ].min
+              end_pos   = [ [ found_pos + phrase.chars.length + radius - 1, 0].max, text.chars.length ].min
 
               prefix  = start_pos > 0 ? excerpt_string : ""
-              postfix = end_pos < text.chars.length ? excerpt_string : ""
+              postfix = end_pos < text.chars.length - 1 ? excerpt_string : ""
 
               prefix + text.chars[start_pos..end_pos].strip + postfix
             else
@@ -134,10 +134,10 @@ def excerpt(text, phrase, radius = 100, excerpt_string = "...") #:nodoc:
 
             if found_pos = text =~ /(#{phrase})/i
               start_pos = [ found_pos - radius, 0 ].max
-              end_pos   = [ found_pos + phrase.length + radius, text.length ].min
+              end_pos   = [ [ found_pos + phrase.length + radius - 1, 0].max, text.length ].min
 
               prefix  = start_pos > 0 ? excerpt_string : ""
-              postfix = end_pos < text.length ? excerpt_string : ""
+              postfix = end_pos < text.length - 1 ? excerpt_string : ""
 
               prefix + text[start_pos..end_pos].strip + postfix
             else

actionpack/test/template/text_helper_test.rb

@@ -102,30 +102,47 @@ def test_highlighting_multiple_phrases_in_one_pass
   end
 
   def test_excerpt
-    assert_equal("...is a beautiful morni...", excerpt("This is a beautiful morning", "beautiful", 5))
+    assert_equal("...is a beautiful morn...", excerpt("This is a beautiful morning", "beautiful", 5))
     assert_equal("This is a...", excerpt("This is a beautiful morning", "this", 5))
     assert_equal("...iful morning", excerpt("This is a beautiful morning", "morning", 5))
     assert_nil excerpt("This is a beautiful morning", "day")
   end
 
+  def test_excerpt_in_borderline_cases
+    assert_equal("", excerpt("", "", 0))
+    assert_equal("a", excerpt("a", "a", 0))
+    assert_equal("...b...", excerpt("abc", "b", 0))
+    assert_equal("abc", excerpt("abc", "b", 1))
+    assert_equal("abc...", excerpt("abcd", "b", 1))
+    assert_equal("...abc", excerpt("zabc", "b", 1))
+    assert_equal("...abc...", excerpt("zabcd", "b", 1))
+    assert_equal("zabcd", excerpt("zabcd", "b", 2))
+
+    # excerpt strips the resulting string before ap-/prepending excerpt_string.
+    # whether this behavior is meaningful when excerpt_string is not to be
+    # appended is questionable.
+    assert_equal("zabcd", excerpt("  zabcd  ", "b", 4))
+    assert_equal("...abc...", excerpt("z  abc  d", "b", 1))
+  end
+
   def test_excerpt_with_regex
-    assert_equal('...is a beautiful! morn...', excerpt('This is a beautiful! morning', 'beautiful', 5))
-    assert_equal('...is a beautiful? morn...', excerpt('This is a beautiful? morning', 'beautiful', 5))
+    assert_equal('...is a beautiful! mor...', excerpt('This is a beautiful! morning', 'beautiful', 5))
+    assert_equal('...is a beautiful? mor...', excerpt('This is a beautiful? morning', 'beautiful', 5))
   end
 
   if RUBY_VERSION < '1.9'
     def test_excerpt_with_utf8
       with_kcode('u') do
-        assert_equal("...fficiency could not be h...", excerpt("That's why efficiency could not be helped", 'could', 8))
+        assert_equal("...fficiency could not be...", excerpt("That's why efficiency could not be helped", 'could', 8))
       end
       with_kcode('none') do
-        assert_equal("...\203ciency could not be h...", excerpt("That's why efficiency could not be helped", 'could', 8))
+        assert_equal("...\203ciency could not be...", excerpt("That's why efficiency could not be helped", 'could', 8))
       end
     end
   else
     def test_excerpt_with_utf8
-      assert_equal("...fficiency could not be h...".force_encoding('UTF-8'), excerpt("That's why efficiency could not be helped".force_encoding('UTF-8'), 'could', 8))
-      assert_equal("...\203ciency could not be h...", excerpt("That's why efficiency could not be helped", 'could', 8))
+      assert_equal("...fficiency could not be...".force_encoding('UTF-8'), excerpt("That's why efficiency could not be helped".force_encoding('UTF-8'), 'could', 8))
+      assert_equal("...\203ciency could not be...", excerpt("That's why efficiency could not be helped", 'could', 8))
     end
   end