breakout_parser 0.0.7 → 0.0.8

data/ext/breakout_parser/parser.tab.h

@@ -54,27 +54,28 @@
      FILE_LINK = 270,
      IMAGE_LINK = 271,
      URL = 272,
-     UL = 273,
-     H1 = 274,
-     H2 = 275,
-     H3 = 276,
-     H4 = 277,
-     H5 = 278,
-     INLINE_CODE = 279,
-     SPACE = 280,
-     BR = 281,
-     OLI = 282,
-     ULI = 283,
-     PRE_CODE_START = 284,
-     PRE_CODE_END = 285,
-     PRE_START = 286,
-     PRE_END = 287,
-     CODE_START = 288,
-     CODE_END = 289,
-     NOTEXTILE_START = 290,
-     NOTEXTILE_END = 291,
-     BOLD_END = 292,
-     ITALIC_END = 293
+     EMAIL = 273,
+     UL = 274,
+     H1 = 275,
+     H2 = 276,
+     H3 = 277,
+     H4 = 278,
+     H5 = 279,
+     INLINE_CODE = 280,
+     SPACE = 281,
+     BR = 282,
+     OLI = 283,
+     ULI = 284,
+     PRE_CODE_START = 285,
+     PRE_CODE_END = 286,
+     PRE_START = 287,
+     PRE_END = 288,
+     CODE_START = 289,
+     CODE_END = 290,
+     NOTEXTILE_START = 291,
+     NOTEXTILE_END = 292,
+     BOLD_END = 293,
+     ITALIC_END = 294
    };
 #endif
 
@@ -94,7 +95,7 @@ typedef union YYSTYPE
 
 
 /* Line 1676 of yacc.c  */
-#line 98 "parser.tab.h"
+#line 99 "parser.tab.h"
 } YYSTYPE;
 # define YYSTYPE_IS_TRIVIAL 1
 # define yystype YYSTYPE /* obsolescent; will be withdrawn */

data/ext/breakout_parser/parser.y

@@ -69,7 +69,7 @@ void yyerror(const char *msg)
 %token <svalue> T_WORD TICKET_LINK LINK SVN_REVISION_LINK GIT_REVISION_LINK WIKI_LINK ANCHOR_LINK
 %token <svalue> URL_WITH_PROTO_LINK URL_WITHOUT_PROTO_LINK
 %token <svalue> FILE_LINK IMAGE_LINK
-%token <svalue> URL
+%token <svalue> URL EMAIL
 %token <svalue> UL
 %token <svalue> H1 H2 H3 H4 H5
 %token <svalue> INLINE_CODE
@@ -116,6 +116,7 @@ word : chars
       | link
       | T_WORD         {concat2($1)} // TODO: somehow pass T_WORD's length here
       | URL            {process_url($1)}
+      | EMAIL          {process_email($1)}
       | BOLD_START     {$1 ? concat(" <strong>",9) : concat("<strong>",8)}
       | BOLD_END       {concat("</strong>",9)}
       | ITALIC_START   {$1 ? concat(" <em>",5) : concat("<em>",4)}
@@ -402,6 +403,21 @@ process_url(const char*url){
     const char *p;
 
     concat("<a rel=\"nofollow\" href=\"",24);
+    if( *url == 'w' ){
+        // url starts with 'www.'
+        concat("http://",7);
+    } else {
+        // assume url starts with 'http://'
+    }
     for(p=url; *p; p++) concat_raw_char(*p);
     process_link_tail(url,NULL,NULL);
 }
+
+process_email(const char*url){
+    const char *p;
+
+    concat("<a href=\"mailto:",16);
+    for(p=url; *p; p++) concat_raw_char(*p);
+    process_link_tail(url,NULL,NULL);
+}
+

data/ext/breakout_parser/ruby_ext.c

@@ -4,12 +4,14 @@
 
 void Init_breakout_parser();
 VALUE method_parse(VALUE, VALUE, VALUE);
+VALUE method_parse_links_only(VALUE, VALUE, VALUE);
 
 VALUE breakout_parser = Qnil;
 
 void Init_breakout_parser() {
     breakout_parser = rb_define_class("BreakoutParser",rb_cObject);
     rb_define_singleton_method(breakout_parser, "parse", method_parse, 2);
+    rb_define_singleton_method(breakout_parser, "parse_links_only", method_parse_links_only, 2);
 }
 
 extern char *buf, *bufptr;
@@ -17,7 +19,9 @@ extern char *in_buf, *in_pos;
 extern const char *space_name;
 extern size_t in_buf_len, bufsize, space_name_len;
 
-VALUE method_parse(VALUE self, VALUE text, VALUE r_space_name) {
+extern int parse_links_only;
+
+VALUE do_parse(VALUE self, VALUE text, VALUE r_space_name) {
     VALUE s;
     char *p;
 
@@ -69,4 +73,14 @@ VALUE method_parse(VALUE self, VALUE text, VALUE r_space_name) {
     return s;
 }
 
+VALUE method_parse(VALUE self, VALUE text, VALUE r_space_name) {
+    parse_links_only = 0;
+    return do_parse(self,text,r_space_name);
+}
+
+VALUE method_parse_links_only(VALUE self, VALUE text, VALUE r_space_name) {
+    parse_links_only = 1;
+    return do_parse(self,text,r_space_name);
+}
+
 #endif // ifdef RUBY_VERSION

data/spec/parser_spec.rb

@@ -97,7 +97,7 @@ describe 'BreakoutParser' do
     end
     it "not confuses" do
       parse("look at @this code@ and mail me at xxx@yyy.com").should ==
-        'look at <code>this code</code> and mail me at xxx@yyy.com'
+        'look at <code>this code</code> and mail me at <a href="mailto:xxx@yyy.com">xxx@yyy.com</a>'
     end
     it "w/o closing tag" do
       parse("@smth").should == '@smth'
@@ -359,35 +359,99 @@ describe 'BreakoutParser' do
 ###############################################################################
 
   describe "raw text links" do
-    it "at the beginning" do
-      parse("http://www.ru").should == "<a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a>"
-    end
-    it "in middle of other words" do
-      parse("aaa bbb ccc http://www.ru ddd eee fff").should ==
-        "aaa bbb ccc <a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a> ddd eee fff"
-    end
-    it "in new line" do
-      parse("aaa bbb ccc\nhttp://www.ru\nddd eee fff").should match(
-        %r"aaa bbb ccc ?<br /> ?<a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a> ?<br /> ?ddd eee fff"
-      )
-    end
-    it "escapes '&' in link _text_" do
-      parse("http://www.ru/?a=1&b=2").should == "<a rel=\"nofollow\" href=\"http://www.ru/?a=1&b=2\">http://www.ru/?a=1&amp;b=2</a>"
+    describe "starting with 'http://'" do
+      it "at the beginning" do
+        parse("http://asd.ru").should == "<a rel=\"nofollow\" href=\"http://asd.ru\">http://asd.ru</a>"
+      end
+      it "in middle of other words" do
+        parse("aaa bbb ccc http://asd.ru ddd eee fff").should ==
+          "aaa bbb ccc <a rel=\"nofollow\" href=\"http://asd.ru\">http://asd.ru</a> ddd eee fff"
+      end
+      it "in new line" do
+        parse("aaa bbb ccc\nhttp://asd.ru\nddd eee fff").should match(
+          %r"aaa bbb ccc ?<br /> ?<a rel=\"nofollow\" href=\"http://asd.ru\">http://asd.ru</a> ?<br /> ?ddd eee fff"
+        )
+      end
+      it "escapes '&' in link _text_" do
+        parse("http://asd.ru/?a=1&b=2").should == "<a rel=\"nofollow\" href=\"http://asd.ru/?a=1&b=2\">http://asd.ru/?a=1&amp;b=2</a>"
+      end
+
+      it "parses https://" do
+        parse("https://asd.ru").should == "<a rel=\"nofollow\" href=\"https://asd.ru\">https://asd.ru</a>"
+      end
+
+      %w', .'.each do |c|
+        it "stops parsing on \"#{c} \"" do
+          parse("http://asd.ru#{c}").should == "<a rel=\"nofollow\" href=\"http://asd.ru\">http://asd.ru</a>#{c}"
+          parse(" http://asd.ru#{c} ").should == "<a rel=\"nofollow\" href=\"http://asd.ru\">http://asd.ru</a>#{c}"
+          parse(" http://asd.ru#{c} hello!").should == "<a rel=\"nofollow\" href=\"http://asd.ru\">http://asd.ru</a>#{c} hello!"
+          parse("xxx http://asd.ru#{c} hello!").should == "xxx <a rel=\"nofollow\" href=\"http://asd.ru\">http://asd.ru</a>#{c} hello!"
+          parse(" http://asd.ru/#{c} hello!").should == "<a rel=\"nofollow\" href=\"http://asd.ru/\">http://asd.ru/</a>#{c} hello!"
+          parse(" http://aaa.com#{c} http://bbb.com").should ==
+            "<a rel=\"nofollow\" href=\"http://aaa.com\">http://aaa.com</a>#{c} <a rel=\"nofollow\" href=\"http://bbb.com\">http://bbb.com</a>"
+        end
+      end
     end
 
-    it "parses https://" do
-      parse("https://www.ru").should == "<a rel=\"nofollow\" href=\"https://www.ru\">https://www.ru</a>"
+    describe "starting with 'www.'" do
+      it "at the beginning" do
+        parse("www.ru").should == "<a rel=\"nofollow\" href=\"http://www.ru\">www.ru</a>"
+      end
+      it "in middle of other words" do
+        parse("aaa bbb ccc www.ru ddd eee fff").should ==
+          "aaa bbb ccc <a rel=\"nofollow\" href=\"http://www.ru\">www.ru</a> ddd eee fff"
+      end
+      it "in new line" do
+        parse("aaa bbb ccc\nwww.ru\nddd eee fff").should match(
+          %r"aaa bbb ccc ?<br /> ?<a rel=\"nofollow\" href=\"http://www.ru\">www.ru</a> ?<br /> ?ddd eee fff"
+        )
+      end
+      it "escapes '&' in link _text_" do
+        parse("www.ru/?a=1&b=2").should == "<a rel=\"nofollow\" href=\"http://www.ru/?a=1&b=2\">www.ru/?a=1&amp;b=2</a>"
+      end
+
+      %w', .'.each do |c|
+        it "stops parsing on \"#{c} \"" do
+          parse("www.ru#{c}").should == "<a rel=\"nofollow\" href=\"http://www.ru\">www.ru</a>#{c}"
+          parse(" www.ru#{c} ").should == "<a rel=\"nofollow\" href=\"http://www.ru\">www.ru</a>#{c}"
+          parse(" www.ru#{c} hello!").should == "<a rel=\"nofollow\" href=\"http://www.ru\">www.ru</a>#{c} hello!"
+          parse("xxx www.ru#{c} hello!").should == "xxx <a rel=\"nofollow\" href=\"http://www.ru\">www.ru</a>#{c} hello!"
+          parse(" www.ru/#{c} hello!").should == "<a rel=\"nofollow\" href=\"http://www.ru/\">www.ru/</a>#{c} hello!"
+          parse(" www.aaa.com#{c} www.bbb.com").should ==
+            "<a rel=\"nofollow\" href=\"http://www.aaa.com\">www.aaa.com</a>#{c} <a rel=\"nofollow\" href=\"http://www.bbb.com\">www.bbb.com</a>"
+        end
+      end
     end
 
-    %w', .'.each do |c|
-      it "stops parsing on \"#{c} \"" do
-        parse("http://www.ru#{c}").should == "<a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a>#{c}"
-        parse(" http://www.ru#{c} ").should == "<a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a>#{c}"
-        parse(" http://www.ru#{c} hello!").should == "<a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a>#{c} hello!"
-        parse("xxx http://www.ru#{c} hello!").should == "xxx <a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a>#{c} hello!"
-        parse(" http://www.ru/#{c} hello!").should == "<a rel=\"nofollow\" href=\"http://www.ru/\">http://www.ru/</a>#{c} hello!"
-        parse(" http://aaa.com#{c} http://bbb.com").should ==
-          "<a rel=\"nofollow\" href=\"http://aaa.com\">http://aaa.com</a>#{c} <a rel=\"nofollow\" href=\"http://bbb.com\">http://bbb.com</a>"
+    describe 'e-mails' do
+      it "at the beginning" do
+        parse("aaa@bbb.com").should == "<a href=\"mailto:aaa@bbb.com\">aaa@bbb.com</a>"
+      end
+      it "in middle of other words" do
+        parse("aaa bbb ccc xx@yy.cn ddd eee fff").should ==
+          "aaa bbb ccc <a href=\"mailto:xx@yy.cn\">xx@yy.cn</a> ddd eee fff"
+      end
+      it "in new line" do
+        parse("aaa bbb ccc\naa.bb@cc.dd.ee\nddd eee fff").should match(
+          %r"aaa bbb ccc ?<br /> ?<a href=\"mailto:aa.bb@cc.dd.ee\">aa.bb@cc.dd.ee</a> ?<br /> ?ddd eee fff"
+        )
+      end
+
+      %w', .'.each do |c|
+        it "stops parsing on \"#{c} \"" do
+          parse("a-b@c-d.efghjikl#{c}").should == "<a href=\"mailto:a-b@c-d.efghjikl\">a-b@c-d.efghjikl</a>#{c}"
+          parse(" a-b@c-d.efghjikl#{c} ").should == "<a href=\"mailto:a-b@c-d.efghjikl\">a-b@c-d.efghjikl</a>#{c}"
+          parse(" a-b@c-d.efghjikl#{c} hello!").should == "<a href=\"mailto:a-b@c-d.efghjikl\">a-b@c-d.efghjikl</a>#{c} hello!"
+          parse("xxx a-b@c-d.efghjikl#{c} hello!").should == "xxx <a href=\"mailto:a-b@c-d.efghjikl\">a-b@c-d.efghjikl</a>#{c} hello!"
+          parse(" a-b@c-d.efghjikl#{c} hello!").should == "<a href=\"mailto:a-b@c-d.efghjikl\">a-b@c-d.efghjikl</a>#{c} hello!"
+          parse(" www@aaa.com#{c} www@bbb.com").should ==
+            "<a href=\"mailto:www@aaa.com\">www@aaa.com</a>#{c} <a href=\"mailto:www@bbb.com\">www@bbb.com</a>"
+        end
+      end
+
+      it "not parses bad emails" do
+        s="a@b.c a@b a.b@c a.b@@c a@b@c.d a#b@c.d"
+        parse(s).should == s
       end
     end
   end
@@ -693,7 +757,7 @@ describe 'BreakoutParser' do
       parse(s).should == s
       s = "[[abcd:1234]]"
       parse(s).should == s
-      s = "[[abcd::1234]] [[abcd:1234]] [[uri:www.ru]]"
+      s = "[[abcd::1234]] [[abcd:1234]] [[uri:ww.ru]]"
       parse(s).should == s
     end
 
@@ -718,7 +782,9 @@ describe 'BreakoutParser' do
 ###############################################################################
 ###############################################################################
 
-  HTML_ESCAPE   =   { '&' => '&amp;', '>' => '&gt;', '<' => '&lt;', '"' => '&quot;' }
+  unless defined?HTML_ESCAPE
+    HTML_ESCAPE   =   { '&' => '&amp;', '>' => '&gt;', '<' => '&lt;', '"' => '&quot;' }
+  end
 
   def h s
     s.to_s.gsub(/[&"><]/) { |special| HTML_ESCAPE[special] }

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: breakout_parser
 version: !ruby/object:Gem::Version 
-  version: 0.0.7
+  version: 0.0.8
 platform: ruby
 authors: 
 - Andrey "Zed" Zaikin
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-03-09 00:00:00 +05:00
+date: 2010-03-12 00:00:00 +05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency