html_truncator 0.3.1 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 8acdba13144c7c2f1d8ede94f1c21dc60ab6566c
-  data.tar.gz: 1ce538702c8e24d2a0781f08657a61bbe2d0300d
+  metadata.gz: d49de35db932a0034c8a82e62f0c5d48a097c1f4
+  data.tar.gz: a070c038a14da39ea4603280fc427a102ecc2155
 SHA512:
-  metadata.gz: 4011e5a3f94446bc9cddb5aa8af1afb5fc174aaa14250dfb076fcf802a3e40ef5f18b89d29f84c1ce0e69320a8d354d040517edb8a6973a5bf3a38735c10c887
-  data.tar.gz: 5241bfa96596b4cd2785666b62ffa5311be99f097dfbd0fc4478e3926abe27f93cf69195b8773a8d4cf39cdee27ace15089d6ab5c22524fd003dcbb60ed658e3
+  metadata.gz: cf893133668e3f929f264209061d4861f0670e73756c75100f9cfa6b38a0ee584ae0d4914bd8d54a73aa40d8e9b26b2de953adda75576a05694337e74bb61a15
+  data.tar.gz: 4409e5eb01fe42cbebcb78ffc49e9d8753ea61989c991a285c9f0064874dfbd4865ba3a66fc95664d6cbb8b0c274e74cfd3cee0f21079d5dd4998f9c70c0d77c

data/README.md

@@ -28,8 +28,14 @@ The HTML_Truncator class has only one method, `truncate`, with 3 arguments:
 * the number of words to keep (real words, tags and attributes aren't count)
 * some options like the ellipsis (optional, '…' by default).
 
-And an attribute, `ellipsable_tags`, which lists the tags that can contain the ellipsis
-(by default: p ol ul li div header article nav section footer aside dd dt dl).
+And 3 attributes:
+
+* `ellipsable_tags`, which lists the tags that can contain the ellipsis
+  (by default: p ol ul li div header article nav section footer aside dd dt dl)
+* `self_closing_tags`, with the tags to keep when empty
+  (by default: br hr img param embed)
+* `punctuation_chars`, with the punctation characters to remove before the
+  ellipsis (by default: , . : ; ! ?).
 
 
 Examples
@@ -48,7 +54,13 @@ If the text is too short to be truncated, it won't be modified:
 If you prefer, you can have the length in characters instead of words:
 
     HTML_Truncator.truncate("<p>Lorem ipsum dolor sit amet.</p>", 12, :length_in_chars => true)
-    # => "<p>Lorem ipsum …</p>"
+    # => "<p>Lorem ipsum…</p>"
+
+It doesn't cut inside a word but goes back to the immediately preceding word
+boundary:
+
+    HTML_Truncator.truncate("<p>Lorem ipsum dolor sit amet.</p>", 10, :length_in_chars => true)
+    # => "<p>Lorem…</p>"
 
 You can customize the ellipsis:
 
@@ -65,6 +77,11 @@ The ellipsis is put at the right place, inside `<p>`, but not `<i>`:
     HTML_Truncator.truncate("<p><i>Lorem ipsum dolor sit amet.</i></p>", 3)
     # => "<p><i>Lorem ipsum dolor</i>…</p>"
 
+And the punctation just before the ellipsis is not kept:
+
+    HTML_Truncator.truncate("<p>Lorem ipsum: lorem ipsum dolor sit amet.</p>", 2)
+    # => "<p>Lorem ipsum…</p>"
+
 You can indicate that a tag can contain the ellipsis but adding it to the ellipsable_tags:
 
     HTML_Truncator.ellipsable_tags << "blockquote"
@@ -74,7 +91,7 @@ You can indicate that a tag can contain the ellipsis but adding it to the ellips
 You can know if a string was truncated with the `html_truncated?` method:
 
     HTML_Truncator.truncate("<p>Lorem ipsum dolor sit amet.</p>", 3).html_truncated?
-    # => true 
+    # => true
 
 
 Alternatives
@@ -112,6 +129,10 @@ Credits
 -------
 
 Thanks to François de Metz for his awesome help!
-Thanks to [kuroir](https://github.com/kuroir) and [benhutton](https://github.com/benhutton) for their suggestions.
+Thanks to [kuroir](https://github.com/kuroir) and
+[benhutton](https://github.com/benhutton) for their suggestions.
+
+The code is released under the MIT license.
+See the MIT-LICENSE file for the full license.
 
-Copyright (c) 2011 Bruno Michel <bmichel@menfin.info>, released under the MIT license
+♡2011 by Bruno Michel. Copying is an act of love. Please copy and share.

data/lib/html_truncator.rb

@@ -18,10 +18,11 @@ class HTML_Truncator
   end
 
   class <<self
-    attr_accessor :ellipsable_tags, :self_closing_tags
+    attr_accessor :ellipsable_tags, :self_closing_tags, :punctuation_chars
   end
   self.ellipsable_tags = Set.new(%w(p ol ul li div header article nav section footer aside dd dt dl))
   self.self_closing_tags = Set.new(%w(br hr img param embed))
+  self.punctuation_chars = %w(, . : ; ! ?)
 end
 
 class Nokogiri::HTML::DocumentFragment
@@ -50,7 +51,8 @@ class Nokogiri::XML::Node
       inner += txt
       next if remaining >= 0
       if ellipsable?
-        inner = inner.rstrip + opts[:ellipsis]
+        r = %r/[\s#{HTML_Truncator.punctuation_chars.join}]+$/
+        inner = inner.sub(r, '') + opts[:ellipsis]
         opts[:ellipsis] = ""
         opts[:was_truncated] = true
       end

data/lib/html_truncator/version.rb

@@ -1,3 +1,3 @@
 class HTML_Truncator
-  VERSION = "0.3.1"
+  VERSION = "0.4.0"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: html_truncator
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.4.0
 platform: ruby
 authors:
 - Bruno Michel
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-07-21 00:00:00.000000000 Z
+date: 2014-03-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri