breakout_parser 0.0.3 → 0.0.4

data/ext/breakout_parser/parser.tab.h

@@ -51,25 +51,27 @@
      ANCHOR_LINK = 267,
      URL_WITH_PROTO_LINK = 268,
      URL_WITHOUT_PROTO_LINK = 269,
-     URL = 270,
-     UL = 271,
-     H1 = 272,
-     H2 = 273,
-     H3 = 274,
-     H4 = 275,
-     H5 = 276,
-     SPACE = 277,
-     BR = 278,
-     OLI = 279,
-     ULI = 280,
-     PRE_CODE_START = 281,
-     PRE_CODE_END = 282,
-     PRE_START = 283,
-     PRE_END = 284,
-     CODE_START = 285,
-     CODE_END = 286,
-     BOLD_END = 287,
-     ITALIC_END = 288
+     FILE_LINK = 270,
+     IMAGE_LINK = 271,
+     URL = 272,
+     UL = 273,
+     H1 = 274,
+     H2 = 275,
+     H3 = 276,
+     H4 = 277,
+     H5 = 278,
+     SPACE = 279,
+     BR = 280,
+     OLI = 281,
+     ULI = 282,
+     PRE_CODE_START = 283,
+     PRE_CODE_END = 284,
+     PRE_START = 285,
+     PRE_END = 286,
+     CODE_START = 287,
+     CODE_END = 288,
+     BOLD_END = 289,
+     ITALIC_END = 290
    };
 #endif
 
@@ -89,7 +91,7 @@ typedef union YYSTYPE
 
 
 /* Line 1676 of yacc.c  */
-#line 93 "parser.tab.h"
+#line 95 "parser.tab.h"
 } YYSTYPE;
 # define YYSTYPE_IS_TRIVIAL 1
 # define yystype YYSTYPE /* obsolescent; will be withdrawn */

data/ext/breakout_parser/parser.y

@@ -68,6 +68,7 @@ void yyerror(const char *msg)
 %token <ivalue> T_CHAR BOLD_START ITALIC_START
 %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> UL
 %token <svalue> H1 H2 H3 H4 H5
@@ -125,6 +126,8 @@ link: TICKET_LINK            {process_ticket_link($1)}
     | URL_WITHOUT_PROTO_LINK {process_url_link($1,"http://")}
     | WIKI_LINK              {process_wiki_link($1)}
     | ANCHOR_LINK            {process_anchor_link($1)}
+    | FILE_LINK              {process_file_link($1)}
+    | IMAGE_LINK             {process_image_link($1)}
 
 chars:
      | char chars
@@ -252,7 +255,7 @@ process_anchor_link(const char*target){
 
 process_url_link(const char*target,const char* proto){
     const char *c;
-    concat("<a href=\"",9);
+    concat("<a rel=\"nofollow\" href=\"",24);
     if(proto) concat2(proto);
     for(c=target; *c && *c != ']' && *c != '|'; c++) concat_raw_char(*c);
     process_link_tail(target,NULL,proto);
@@ -287,6 +290,30 @@ process_wiki_link(const char*target){
     process_link_tail(target,NULL,NULL);
 }
 
+process_file_link(const char*target){
+    const char *c;
+    concat("<a href=\"/spaces/",17);
+    concat(space_name,space_name_len);
+    concat("/documents/download/",20);
+    for(c=target; *c && *c!=']' && *c!='|'; c++) concat_raw_char(*c);
+    process_link_tail(target,NULL,"file:");
+}
+
+process_image_link(const char*target){
+    const char *c, *p;
+    concat("<img src=\"/spaces/",18);
+    concat(space_name,space_name_len);
+    concat("/documents/download/",20);
+    for(c=target; *c && *c!=']' && *c!='|'; c++) concat_raw_char(*c);
+    concat("\" alt=\"",7);
+    if(p = strchr(target,'|')){
+        for(c=p+1; *c && *c!=']' && *c!='|'; c++) concat_raw_char(*c);
+    } else {
+        for(c=target; *c && *c!=']' && *c!='|'; c++) concat_raw_char(*c);
+    }
+    concat("\" />",4);
+}
+
 process_ticket_link(const char*ticket_id){
     const char *c;
     while(*ticket_id && (*ticket_id < '0' || *ticket_id > '9') ) ticket_id++;
@@ -356,7 +383,7 @@ concat_escaping_html(const char*what){
 process_url(const char*url){
     const char *p;
 
-    concat("<a href=\"",9);
+    concat("<a rel=\"nofollow\" href=\"",24);
     for(p=url; *p; p++) concat_raw_char(*p);
     process_link_tail(url,NULL,NULL);
 }

data/spec/parser_spec.rb

@@ -168,23 +168,23 @@ describe 'BreakoutParser' do
     {'ul' => '*', 'ol' => '#'}.each do |l,c|
       it "raw text link inside #{l.upcase}> #1" do
         s = "#{c} aaa http://www.ru"
-        parse(s).should == "<#{l}><li>aaa <a href=\"http://www.ru\">http://www.ru</a></li></#{l}>"
+        parse(s).should == "<#{l}><li>aaa <a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a></li></#{l}>"
       end
       it "raw text link inside #{l.upcase}> #2" do
         s = "#{c} aaa http://www.ru\n#{c} bbb"
-        parse(s).should == "<#{l}><li>aaa <a href=\"http://www.ru\">http://www.ru</a></li><li>bbb</li></#{l}>"
+        parse(s).should == "<#{l}><li>aaa <a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a></li><li>bbb</li></#{l}>"
       end
       it "raw text link inside #{l.upcase}> #3" do
         s = "#{c} http://www.ru"
-        parse(s).should == "<#{l}><li><a href=\"http://www.ru\">http://www.ru</a></li></#{l}>"
+        parse(s).should == "<#{l}><li><a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a></li></#{l}>"
       end
       it "raw text link inside #{l.upcase}> #4" do
         s = "#{c} aaa http://www.ru bbb"
-        parse(s).should == "<#{l}><li>aaa <a href=\"http://www.ru\">http://www.ru</a> bbb</li></#{l}>"
+        parse(s).should == "<#{l}><li>aaa <a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a> bbb</li></#{l}>"
       end
       it "two links inside #{l.upcase}>" do
         s = "#{c} aaa http://www.ru http://ya.ru bbb"
-        parse(s).should == "<#{l}><li>aaa <a href=\"http://www.ru\">http://www.ru</a> <a href=\"http://ya.ru\">http://ya.ru</a> bbb</li></#{l}>"
+        parse(s).should == "<#{l}><li>aaa <a rel=\"nofollow\" href=\"http://www.ru\">http://www.ru</a> <a rel=\"nofollow\" href=\"http://ya.ru\">http://ya.ru</a> bbb</li></#{l}>"
       end
     end
   end
@@ -303,34 +303,34 @@ describe 'BreakoutParser' do
 
   describe "raw text links" do
     it "at the beginning" do
-      parse("http://www.ru").should == "<a href=\"http://www.ru\">http://www.ru</a>"
+      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 href=\"http://www.ru\">http://www.ru</a> ddd eee fff"
+        "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 href=\"http://www.ru\">http://www.ru</a> ?<br /> ?ddd eee fff"
+        %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 href=\"http://www.ru/?a=1&b=2\">http://www.ru/?a=1&amp;b=2</a>"
+      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>"
     end
 
     it "parses https://" do
-      parse("https://www.ru").should == "<a href=\"https://www.ru\">https://www.ru</a>"
+      parse("https://www.ru").should == "<a rel=\"nofollow\" href=\"https://www.ru\">https://www.ru</a>"
     end
 
     %w', .'.each do |c|
       it "stops parsing on \"#{c} \"" do
-        parse("http://www.ru#{c}").should == "<a href=\"http://www.ru\">http://www.ru</a>#{c}"
-        parse(" http://www.ru#{c} ").should == "<a href=\"http://www.ru\">http://www.ru</a>#{c}"
-        parse(" http://www.ru#{c} hello!").should == "<a href=\"http://www.ru\">http://www.ru</a>#{c} hello!"
-        parse("xxx http://www.ru#{c} hello!").should == "xxx <a href=\"http://www.ru\">http://www.ru</a>#{c} hello!"
-        parse(" http://www.ru/#{c} hello!").should == "<a href=\"http://www.ru/\">http://www.ru/</a>#{c} hello!"
+        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 href=\"http://aaa.com\">http://aaa.com</a>#{c} <a href=\"http://bbb.com\">http://bbb.com</a>"
+          "<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
@@ -572,12 +572,17 @@ describe 'BreakoutParser' do
     a["r:2345"] = '<a href="http://code.assembla.com/test_space/svn/changesets/2345">revision:2345</a>'
     a["r:2345ef"] = '<a href="http://code.assembla.com/test_space/git/changesets/2345ef">revision:2345ef</a>'
 
-    a["url:http://www.ru"]   = '<a href="http://www.ru">http://www.ru</a>'
-    a["url:https://www.ru"]  = '<a href="https://www.ru">https://www.ru</a>'
-    a["url:www.ru"]          = '<a href="http://www.ru">http://www.ru</a>'
-    a["url:www.ru/?a=1&b=2"] = '<a href="http://www.ru/?a=1&b=2">http://www.ru/?a=1&amp;b=2</a>'
-    a["url:ftp://www.ru"]    = '<a href="ftp://www.ru">ftp://www.ru</a>'
-    a["url:/spaces/x2"]      = '<a href="/spaces/x2">/spaces/x2</a>'
+    a["url:http://www.ru"]   = '<a rel="nofollow" href="http://www.ru">http://www.ru</a>'
+    a["url:https://www.ru"]  = '<a rel="nofollow" href="https://www.ru">https://www.ru</a>'
+    a["url:www.ru"]          = '<a rel="nofollow" href="http://www.ru">http://www.ru</a>'
+    a["url:www.ru/?a=1&b=2"] = '<a rel="nofollow" href="http://www.ru/?a=1&b=2">http://www.ru/?a=1&amp;b=2</a>'
+    a["url:ftp://www.ru"]    = '<a rel="nofollow" href="ftp://www.ru">ftp://www.ru</a>'
+    a["url:/spaces/x2"]      = '<a rel="nofollow" href="/spaces/x2">/spaces/x2</a>'
+
+    a["file:ExistingFile.txt"] =
+      '<a href="/spaces/test_space/documents/download/ExistingFile.txt">file:ExistingFile.txt</a>'
+    a["file:cVJUz6ejWr35pEab_qKWB8"] =
+      '<a href="/spaces/test_space/documents/download/cVJUz6ejWr35pEab_qKWB8">file:cVJUz6ejWr35pEab_qKWB8</a>'
 
     a.each do |k,v|
       it "parses [[#{k}]]" do
@@ -591,7 +596,25 @@ describe 'BreakoutParser' do
       end
     end
 
-    it "keeps unknown link types" do
+    a = {}
+    a["image:ExistingImage.png"] =
+      '<img src="/spaces/test_space/documents/download/ExistingImage.png" alt="ALT" />'
+    a["image:cVJUz6ejWr35pEab_qKWB8"] =
+      '<img src="/spaces/test_space/documents/download/cVJUz6ejWr35pEab_qKWB8" alt="ALT" />'
+
+    a.each do |k,v|
+      it "parses [[#{k}]]" do
+        parse("[[#{k}]]").should == v.sub('ALT',k.sub('image:',''))
+      end
+      it "parses [[#{k}|привет тест]]" do
+        parse("[[#{k}|привет тест]]").should == v.sub('ALT','привет тест')
+      end
+      it "parses [[#{k}|test & here]]" do
+        parse("[[#{k}|test & here]]").should == v.sub('ALT','test & here')
+      end
+    end
+
+    it "ignores unknown link types" do
       s = "[[zzz:xxx]]"
       parse(s).should == s
       s = "[[abcd:1234]]"
@@ -600,10 +623,21 @@ describe 'BreakoutParser' do
       parse(s).should == s
     end
 
-    it "links to ExistingFile.txt"
-    it "links to NotExistingFile.txt"
-    it "links to ExistingImage.png"
-    it "links to NotExistingImage.png"
+    it "ignores file & image links with forbidden symbols" do
+      s = "[[file:aaa/bbb]]"
+      parse(s).should == s
+      s = "[[file:aaa\\bbb]]"
+      parse(s).should == s
+      s = "[[file:aaa bbb]]"
+      parse(s).should == s
+
+      s = "[[image:aaa/bbb]]"
+      parse(s).should == s
+      s = "[[image:aaa\\bbb]]"
+      parse(s).should == s
+      s = "[[image:aaa bbb]]"
+      parse(s).should == s
+    end
   end
 
 ###############################################################################

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: breakout_parser
 version: !ruby/object:Gem::Version 
-  version: 0.0.3
+  version: 0.0.4
 platform: ruby
 authors: 
 - Andrey "Zed" Zaikin
@@ -9,7 +9,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-01-20 00:00:00 +05:00
+date: 2010-02-03 00:00:00 +05:00
 default_executable: 
 dependencies: 
 - !ruby/object:Gem::Dependency