breakout_parser 0.0.2-x86-mswin32 → 0.0.3-x86-mswin32

data/spec/parser_spec.rb

@@ -2,7 +2,11 @@ require 'breakout_parser'
 
 describe 'BreakoutParser' do
   def self.hex_string s
-    s.each_byte.to_a.map{ |c| "%02x" % c }.join
+    ## sexier, but not runs on ruby 1.8.6 patchlevel 383 i386-mingw32:
+    #s.each_byte.to_a.map{ |c| "%02x" % c }.join
+    r = ''
+    s.each_byte{ |c| r << "%02x" % c }
+    r
   end
   def hex_string s; self.class.hex_string(s); end
 
@@ -43,16 +47,16 @@ describe 'BreakoutParser' do
     parse("\r\n\t   \t  \n  \r   \n   \t  \t\n\r   aaa").should == "aaa"
   end
 
-  it "converts two or more \\n to single empty line" do
+  it "converts each newline to <br />" do
     parse("aaa\n\nbbb").should == "aaa<br /><br />bbb"
     parse("aaa\n  \nbbb").should == "aaa<br /><br />bbb"
-    parse("aaa\n\n\nbbb").should == "aaa<br /><br />bbb"
-    parse("aaa\n   \n    \nbbb").should == "aaa<br /><br />bbb"
-    parse("aaa\r\n   \r\n    \r\nbbb").should == "aaa<br /><br />bbb"
-    parse("aaa\n   \n\n    \nbbb").should == "aaa<br /><br />bbb"
-    parse("aaa\n   \n\n\n    \nbbb").should == "aaa<br /><br />bbb"
-    parse("aaa\n\n\n\n\n\n\nbbb").should == "aaa<br /><br />bbb"
-    parse("aaa\r\n\r\n\r\nbbb").should == "aaa<br /><br />bbb"
+    parse("aaa\n\n\nbbb").should == "aaa<br /><br /><br />bbb"
+    parse("aaa\n   \n    \nbbb").should == "aaa<br /><br /><br />bbb"
+    parse("aaa\r\n   \r\n    \r\nbbb").should == "aaa<br /><br /><br />bbb"
+    parse("aaa\n   \n\n    \nbbb").should == "aaa<br /><br /><br /><br />bbb"
+    parse("aaa\n   \n\n\n    \nbbb").should == "aaa" + "<br />"*5 + "bbb"
+    parse("aaa\n\n\n\n\n\n\nbbb").should == "aaa" + "<br />"*7 + "bbb"
+    parse("aaa\r\n\r\n\r\nbbb").should == "aaa" + "<br />"*3 + "bbb"
   end
 
 ###############################################################################
@@ -354,68 +358,123 @@ describe 'BreakoutParser' do
 
 ###############################################################################
 
-  describe "<pre><code>..</code></pre>" do
-    it "works" do
-      s = <<-EOF
-    for ( n = 0; n < max_size && \
-           (c = getc( yyin )) != EOF && c != '\\n'; ++n ) \
-      buf[n] = (char) c; \
-
-      EOF
-
-      parse("<pre><code>#{s.strip}</code></pre>").should ==
-        "<pre><code>#{h(s.strip)}</code></pre>"
-
-      s = <<-EOF
-          while ( 1 < 2 ) do
-            puts "<b>12345\\t54321</b>"
-            // *bold* comment
-            // _italic_ comment
-          end
-          ---
-          * aaa
-          * bbb
-          * ccc
-
-      EOF
-      parse("<pre><code>#{s.strip}</code></pre>").should ==
-        "<pre><code>#{h(s.strip)}</code></pre>"
-    end
-    it "not parses *bold*" do
-      s = "<pre><code> *bold*</code></pre>"
-      parse(s).should == s
-    end
-    it "not parses _italic_" do
-      s = "<pre><code> _italic_</code></pre>"
-      parse(s).should == s
-    end
-    it "not parses UL lists" do
-      s = "<pre><code>\n * l1\n * l2\n * l3</code></pre>"
-      parse(s).should == s.sub("<code>\n","<code>")
-    end
-    it "not parses OL lists" do
-      s = "<pre><code>\n # l1\n # l2\n # l3</code></pre>"
-      parse(s).should == s.sub("<code>\n","<code>")
-    end
-    it "not parses H1..H5" do
-      1.upto(5) do |i|
-        s = "<pre><code>\nh#{i}. zzzzzzz\n</code></pre>"
-        parse(s).should == "<pre><code>h#{i}. zzzzzzz</code></pre>"
+  [
+    %w'<pre><code> </code></pre>',
+    %w'<pre> </pre>'
+  ].each do |ot,ct|
+    # ot - opening tag
+    # ct - closing tag
+
+    describe "#{ot}..#{ct}" do
+      it "works" do
+        s = <<-EOF
+      for ( n = 0; n < max_size && \
+             (c = getc( yyin )) != EOF && c != '\\n'; ++n ) \
+        buf[n] = (char) c; \
+
+        EOF
+
+        parse("#{ot}#{s.strip}#{ct}").should ==
+          "#{ot}#{h(s.strip)}#{ct}"
+
+        s = <<-EOF
+            while ( 1 < 2 ) do
+              puts "<b>12345\\t54321</b>"
+              // *bold* comment
+              // _italic_ comment
+            end
+            ---
+            * aaa
+            * bbb
+            * ccc
+
+        EOF
+        parse("#{ot}#{s.strip}#{ct}").should ==
+          "#{ot}#{h(s.strip)}#{ct}"
+      end
+      it "not parses *bold*" do
+        s = "#{ot} *bold*#{ct}"
+        parse(s).should == s
+      end
+      it "not parses _italic_" do
+        s = "#{ot} _italic_#{ct}"
+        parse(s).should == s
+      end
+      it "not parses UL lists" do
+        s = "#{ot}\n * l1\n * l2\n * l3#{ct}"
+        parse(s).should == s.sub(">\n",">")
+      end
+      it "not parses OL lists" do
+        s = "#{ot}\n # l1\n # l2\n # l3#{ct}"
+        parse(s).should == s.sub(">\n",">")
+      end
+      it "not parses H1..H5" do
+        1.upto(5) do |i|
+          s = "#{ot}\nh#{i}. zzzzzzz\n#{ct}"
+          parse(s).should == "#{ot}h#{i}. zzzzzzz#{ct}"
+        end
+      end
+      it "not parses raw text links" do
+        s = "#{ot}xxx http://www.ru yyy#{ct}"
+        parse(s).should == s
+        s = "#{ot}http://www.ru#{ct}"
+        parse(s).should == s
+      end
+      it "keeps newlines" do
+        s = "#{ot}aaa\nbbb#{ct}"
+        parse(s).should == s
+        s = "#{ot}aaa\n\nbbb\nccc#{ct}"
+        parse(s).should == s
+      end
+
+      it "w/o closing tags" do
+        s = "#{ot}aaa"
+        parse(s).should match(%r"#{ot}aaa\n?#{ct}")
+      end
+
+      it "in middle of text" do
+        s = "xxx #{ot}yyyy#{ct} jjj"
+        parse(s).should == s
+      end
+
+      it "with 2 instances" do
+        s = "xxx #{ot}yyyy#{ct} <jjj> #{ot}asdkjaslkd#{ct} END"
+        parse(s).should == s.sub('<jjj>','&lt;jjj&gt;')
+      end
+
+      it "works with unicode" do
+        s = "привет #{ot} жжж #{ct} пока!"
+        parse(s).should match(%r|привет ?#{ot} жжж#{ct} ?пока!|)
+
+        s = 'абвгдеёжзийклмнопрстуфхцчшщьыъэюя'
+        parse(s).should == s
+
+        s = 'АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЬЫЪЭЮЯ'
+        parse(s).should == s
+
+        s = '☸☹☺☻☼☽☾☿'
+        parse(s).should == s
+      end
+
+      it "should escape lone closing tags" do
+        s = "#{ct}"
+        parse(s).should == h(s)
+      end
+
+      it "should skip newlines and spaces at end" do
+        s = "#{ot} aaa bbb ccc \n\n\n  \t\n\n\n\r\n\r\n   \t  #{ct}"
+        parse(s).should == "#{ot} aaa bbb ccc#{ct}"
+      end
+
+      it "escapes html chars" do
+        HTML_ESCAPE.each do |k,v|
+          parse("#{ot}#{k}#{ct}").should == "#{ot}#{v}#{ct}"
+        end
       end
     end
-    it "not parses raw text links" do
-      s = "<pre><code>xxx http://www.ru yyy</code></pre>"
-      parse(s).should == s
-      s = "<pre><code>http://www.ru</code></pre>"
-      parse(s).should == s
-    end
-    it "keeps newlines" do
-      s = "<pre><code>aaa\nbbb</code></pre>"
-      parse(s).should == s
-      s = "<pre><code>aaa\n\nbbb\nccc</code></pre>"
-      parse(s).should == s
-    end
+  end
 
+  describe "<pre><code>..</code></pre>" do
     it "with no spaces between <pre> and <code>" do
       s = "<pre><code>aaa</code></pre>"
       parse(s).should == s
@@ -429,50 +488,64 @@ describe 'BreakoutParser' do
       s = "<pre>    <code>  aaa   bbb   </code>           </pre>"
       parse(s).should == "<pre><code>  aaa   bbb</code></pre>"
     end
+  end
 
-    it "w/o closing tags" do
-      s = "<pre><code>aaa"
-      parse(s).should match(%r"<pre><code>aaa\n?</code></pre>")
-    end
+###############################################################################
 
-    it "in middle of text" do
-      s = "xxx <pre><code>yyyy</code></pre> jjj"
+  describe "<code>..</code>" do
+    it "keeps <code> tags" do
+      s = "<code>aaa</code>"
       parse(s).should == s
     end
-
-    it "with 2 instances" do
-      s = "xxx <pre><code>yyyy</code></pre> <jjj> <pre><code>asdkjaslkd</code></pre> END"
-      parse(s).should == s.sub('<jjj>','&lt;jjj&gt;')
+    it "strips heading & tailing whitespace" do
+      s = "<code> \r\n \t  \t\r  aaa \r\n\t  \t\r  </code>"
+      parse(s).should == s.tr(" \r\n\t","")
     end
-
-    it "works with unicode" do
-      s = "привет <pre><code> жжж </code></pre> пока!"
-      parse(s).should match(%r|привет ?<pre><code> жжж</code></pre> ?пока!|)
-
-      s = 'абвгдеёжзийклмнопрстуфхцчшщьыъэюя'
+    it "not parses *bold*" do
+      s = "<code>aaa *bbb* ccc</code>"
       parse(s).should == s
-
-      s = 'АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЬЫЪЭЮЯ'
+    end
+    it "not parses _italic_" do
+      s = "<code>aaa _bbb_ ccc</code>"
       parse(s).should == s
-
-      s = '☸☹☺☻☼☽☾☿'
+    end
+    it "not parses headers" do
+      s = "<code>aaa\nh1. bbb\nccc</code>"
       parse(s).should == s
     end
-
-    it "should escape lone closing tags" do
-      s = "</code></pre>"
-      parse(s).should == h(s)
+    it "not parses <pre>" do
+      s = "<code>aaa <pre>bbb</pre> ccc</code>"
+      parse(s).should == "<code>aaa &lt;pre&gt;bbb&lt;/pre&gt; ccc</code>"
     end
-
-    it "should skip newlines and spaces at end" do
-      s = "<pre><code> aaa bbb ccc \n\n\n  \t\n\n\n\r\n\r\n   \t  </code></pre>"
-      parse(s).should == "<pre><code> aaa bbb ccc</code></pre>"
+    it "closes unclosed <code>" do
+      s = "aaa <code>bbb"
+      parse(s).should == "#{s}</code>"
     end
-
-    it "escapes html chars" do
-      HTML_ESCAPE.each do |k,v|
-        parse("<pre><code>#{k}</code></pre>").should == "<pre><code>#{v}</code></pre>"
-      end
+    it "escapes '&'" do
+      s = "<code>aaa & bbb</code>"
+      parse(s).should == s.sub('&','&amp;')
+    end
+    it "not parses links" do
+      s = "<code>aaa #1 #2 #3 http://www.ru [[wiki:jjj]] [[url:http://www.ru]] bbb</code>"
+      parse(s).should == s
+    end
+    it "works two times" do
+      s = "<code>aaa & bbb</code> xxx <code>jjj&hhh</code>"
+      parse(s).should == s.gsub('&','&amp;')
+      s = "<code>   aaa      </code>xxx<code>      jjj      </code>"
+      parse(s).should == s.gsub(' ','')
+    end
+    it "keeps code bold" do
+      s = "*aaa <code>bbb</code> ccc*"
+      parse(s).should == "<strong>aaa <code>bbb</code> ccc</strong>"
+      s = "*<code>aaa</code>*"
+      parse(s).should == "<strong><code>aaa</code></strong>"
+    end
+    it "keeps code italic" do
+      s = "_aaa <code>bbb</code> ccc_"
+      parse(s).should == "<em>aaa <code>bbb</code> ccc</em>"
+      s = "_<code>aaa</code>_"
+      parse(s).should == "<em><code>aaa</code></em>"
     end
   end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: breakout_parser
 version: !ruby/object:Gem::Version 
-  version: 0.0.2
+  version: 0.0.3
 platform: x86-mswin32
 authors: 
 - Andrey "Zed" Zaikin
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-01-19 00:00:00 +05:00
+date: 2010-01-20 00:00:00 +05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency