- add config item too

[packages/cvsspam.git] / cvsspam-svnspam-branch.diff

--- cvsspam-0.2.12/svn_cvsspam.rb	2005-07-11 18:53:29.000000000 +0300
+++ cvsspam-svn/svn_cvsspam.rb	2008-08-07 17:27:52.632725455 +0300
@@ -18,7 +18,7 @@
 # to your cvssppam.conf
 
 
-$version = "0.2.11"
+$version = "0.2.12"
 
 
 $maxSubjectLength = 200
@@ -339,8 +339,11 @@
 
   # gets the Repository object for the first component of the given path
   def Repository.get(name)
-    name =~ /^[^\/]+/
-    name = $&
+    # Leading './' is ignored (for peeps who have done 'cvs checkout .')
+    # Trailing '/' ensures no match for files in root (we just want dirs)
+    name =~ /^(?:\.\/)?([^\/]+)\//  
+    name = $1
+    name = "/" if name.nil?  # file at top-level?  fake up a name for repo
     rep = @@repositories[name]
     if rep.nil?
       rep =  Repository.new(name)
@@ -385,6 +388,7 @@
 class FileEntry
   def initialize(path)
     @path = path
+    @fromVer = @toVer = nil
     @lineAdditions = @lineRemovals = 0
     @repository = Repository.get(path)
     @repository.merge_common_prefix(basedir())
@@ -394,7 +398,7 @@
 
   # the full path and filename within the repository
   attr_accessor :path
-  # the type of change committed 'M'=modified, 'A'=added, 'R'=removed
+  # the type of change committed 'M'=modified, 'A'=added, 'R'=removed, 'P'=properties, 'C'=copied
   attr_accessor :type
   # records number of 'addition' lines in diff output, once counted
   attr_accessor :lineAdditions
@@ -412,7 +416,7 @@
   # works out the filename part of #path
   def file
     @path =~ /.*\/(.*)/
-    $1 || @path
+    $1
   end
 
   # set the branch on which this change was committed, and add it to the list
@@ -430,7 +434,7 @@
   # works out the directory part of #path
   def basedir
     @path =~ /(.*)\/.*/
-    $1 || "/"
+    $1
   end
 
   # gives the Repository object this file was automatically associated with
@@ -449,16 +453,27 @@
   def removal?
     @type == "R"
   end
-
+  
   # was this file added during the commit?
   def addition?
     @type == "A"
   end
 
+  # was this file copied during the commit?
+  def copied?
+    @type == "C"
+  end
+
   # was this file simply modified during the commit?
   def modification?
     @type == "M"
   end
+  
+  # was this file simply modified during the commit?
+  def modifiedprops?
+    @type == "P"
+  end
+
 
   # passing true, this object remembers that a diff will appear in the email,
   # passing false, this object remembers that no diff will appear in the email.
@@ -530,6 +545,14 @@
 # TODO: consolidate these into a nicer framework,
 mailSub = proc { |match| "<a href=\"mailto:#{match}\">#{match}</a>" }
 urlSub = proc { |match| "<a href=\"#{match}\">#{match}</a>" }
+gforgeTaskSub = proc { |match|
+  match =~ /([0-9]+)/
+  "<a href=\"#{$gforgeTaskURL.sub(/%s/, $1)}\">#{match}</a>"
+}
+gforgeBugSub = proc { |match|
+  match =~ /([0-9]+)/
+  "<a href=\"#{$gforgeBugURL.sub(/%s/, $1)}\">#{match}</a>"
+}
 bugzillaSub = proc { |match|
   match =~ /([0-9]+)/
   "<a href=\"#{$bugzillaURL.sub(/%s/, $1)}\">#{match}</a>"
@@ -541,9 +564,15 @@
   match =~ /([0-9]+)/
   "<a href=\"#{$ticketURL.sub(/%s/, $1)}\">#{match}</a>"
 }
+wikiSub = proc { |match| 
+  match =~ /\[\[(.*)\]\]/
+  raw = $1
+  "<a href=\"#{$wikiURL.sub(/%s/, urlEncode(raw))}\">[[#{raw}]]</a>"
+}
 commentSubstitutions = {
 		'(?:mailto:)?[\w\.\-\+\=]+\@[\w\-]+(?:\.[\w\-]+)+\b' => mailSub,
-		'\b(?:http|https|ftp):[^ \t\n<>"]+[\w/]' => urlSub}
+		'\b(?:http|https|ftp):[^ \t\n<>"]+[\w/]' => urlSub
+		}
 
 # outputs commit log comment text supplied by LogReader as preformatted HTML
 class CommentHandler < LineConsumer
@@ -661,6 +690,12 @@
   def diff(file)
     '-&gt;'
   end
+
+  # may be overridden by subclasses that are able to make a hyperlink to a
+  # history log for a file
+  def log(file)
+    ''
+  end
 end
 
 # Superclass for objects that can link to CVS frontends on the web (ViewCVS,
@@ -701,6 +736,14 @@
     "<a href=\"#{diff_url(file)}\">#{super(file)}</a>"
   end
 
+  def log(file)
+    link = log_url(file)
+    if link
+      return "<span id=\"info\">(<a href=\"#{link}\">log</a>)</span>"
+    end
+    return nil
+  end
+
  protected
   def add_repo(url)
     if @repository_name
@@ -713,6 +756,10 @@
       url
     end
   end
+
+  def log_url(file)
+    nil
+  end
 end
 
 # Link to ViewCVS
@@ -771,6 +818,17 @@
   def diff_url(file)
     add_repo("#{@base_url}#{urlEncode(file.path)}.diff?r1=text&amp;tr1=#{file.fromVer}&amp;r2=text&amp;tr2=#{file.toVer}&amp;f=h")
   end
+
+  protected
+
+  def log_url(file)
+    if file.toVer
+      log_anchor = "#rev#{file.toVer}"
+    else
+      log_anchor = ""
+    end
+    add_repo("#{@base_url}#{urlEncode(file.path)}#{log_anchor}")
+  end
 end
 
 
@@ -792,6 +850,15 @@
   end
 end
 
+# Note when LogReader finds record of a file that was copied in this commit
+class CopiedFileHandler < FileHandler
+  def handleFile(file)
+    file.type="C"
+    file.fromVer=$fromVer
+    file.toVer=$toVer
+  end
+end
+
 # Note when LogReader finds record of a file that was modified in this commit
 class ModifiedFileHandler < FileHandler
   def handleFile(file)
@@ -801,6 +868,15 @@
   end
 end
 
+# Note when LogReader finds record of a file whose properties were modified in this commit
+class ModifiedPropsFileHandler < FileHandler
+  def handleFile(file)
+    file.type="P"
+    file.fromVer=$fromVer
+    file.toVer=$toVer
+  end
+end
+
 
 # Used by UnifiedDiffHandler to record the number of added and removed lines
 # appearing in a unidiff.
@@ -967,11 +1043,21 @@
         print($frontend.path($file.basedir, $file.tag))
         println("</span><br />")
         println("<div class=\"fileheader\" id=\"removed\"><big><b>#{htmlEncode($file.file)}</b></big> <small id=\"info\">removed after #{$frontend.version($file.path,$file.fromVer)}</small></div>")
+      when "C"
+        print("<span class=\"pathname\" id=\"copied\">")
+        print($frontend.path($file.basedir, $file.tag))
+        println("</span><br />")
+        println("<div class=\"fileheader\" id=\"copied\"><big><b>#{htmlEncode($file.file)}</b></big> <small id=\"info\">copied from #{$frontend.version($file.path,$file.fromVer)}</small></div>")
       when "M"
         print("<span class=\"pathname\">")
         print($frontend.path($file.basedir, $file.tag))
         println("</span><br />")
         println("<div class=\"fileheader\"><big><b>#{htmlEncode($file.file)}</b></big> <small id=\"info\">#{$frontend.version($file.path,$file.fromVer)} #{$frontend.diff($file)} #{$frontend.version($file.path,$file.toVer)}</small></div>")
+      when "P"
+        print("<span class=\"pathname\">")
+        print($frontend.path($file.basedir, $file.tag))
+        println("</span><br />")
+        println("<div class=\"fileheader\"><big><b>#{htmlEncode($file.file)}</b></big> <small id=\"info\">#{$frontend.version($file.path,$file.fromVer)} #{$frontend.diff($file)} #{$frontend.version($file.path,$file.toVer)}</small></div>")
     end
     print("<pre class=\"diff\"><small id=\"info\">")
     lines.each do |line|
@@ -1045,7 +1131,7 @@
      else
       @stats.consume(line)
       if $file.wants_diff_in_mail?
-        if @stats.diffLines < $maxLinesPerDiff
+        if $maxLinesPerDiff.nil? || @stats.diffLines < $maxLinesPerDiff
           @colour.consume(line)
         elsif @stats.diffLines == $maxLinesPerDiff
           @colour.consume(line)
@@ -1062,7 +1148,7 @@
       $file.isBinary = true
     else
       if $file.wants_diff_in_mail?
-        if @stats.diffLines > $maxLinesPerDiff
+        if $maxLinesPerDiff && @stats.diffLines > $maxLinesPerDiff
           println("</pre>")
           println("<strong class=\"error\">[truncated at #{$maxLinesPerDiff} lines; #{@stats.diffLines-$maxLinesPerDiff} more skipped]</strong>")
         else
@@ -1230,13 +1316,18 @@
 $users_file = "#{cvsroot_dir}/users"
 
 $debug = false
+$svn = false
 $recipients = Array.new
 $sendmail_prog = "/usr/sbin/sendmail"
+$hostname = ENV['HOSTNAME'] || 'localhost'
 $no_removed_file_diff = false
 $no_added_file_diff = false
 $no_diff = false
-$task_keywords = ['TODO', 'FIXME']
+$task_keywords = ['TODO', 'FIXME', 'FIXIT', 'todo']
 $bugzillaURL = nil
+$gforgeBugURL = nil
+$gforgeTaskURL = nil
+$wikiURL = nil
 $jiraURL = nil
 $ticketURL = nil
 $viewcvsURL = nil
@@ -1257,6 +1348,7 @@
   [ "--to",     "-t", GetoptLong::REQUIRED_ARGUMENT ],
   [ "--config", "-c", GetoptLong::REQUIRED_ARGUMENT ],
   [ "--debug",  "-d", GetoptLong::NO_ARGUMENT ],
+  [ "--svn",    "-s", GetoptLong::NO_ARGUMENT ],
   [ "--from",   "-u", GetoptLong::REQUIRED_ARGUMENT ],
   [ "--charset",      GetoptLong::REQUIRED_ARGUMENT ]
 )
@@ -1265,6 +1357,7 @@
   $recipients << EmailAddress.new(arg) if opt=="--to"
   $config = arg if opt=="--config"
   $debug = true if opt=="--debug"
+  $svn = true if opt=="--svn"
   $from_address = EmailAddress.new(arg) if opt=="--from"
   # must use different variable as the config is readed later.
   $arg_charset = arg if opt == "--charset"
@@ -1277,12 +1370,13 @@
   else
     $stderr.puts "missing required file argument"
   end
-  puts "Usage: cvsspam.rb [ --to <email> ] [ --config <file> ] <collect_diffs file>"
+  puts "Usage: cvsspam.rb [ --svn ] [ --to <email> ] [ --config <file> ] <collect_diffs file>"
   exit(-1)
 end
 
 $logfile = ARGV[0]
 
+
 $additionalHeaders = Array.new
 $problemHeaders = Array.new
 
@@ -1343,12 +1437,21 @@
 if $bugzillaURL != nil
   commentSubstitutions['\b[Bb][Uu][Gg]\s*#?[0-9]+'] = bugzillaSub
 end
+if $gforgeBugURL != nil
+  commentSubstitutions['\B\[#[0-9]+\]'] = gforgeBugSub
+end
+if $gforgeTaskURL != nil
+  commentSubstitutions['\B\[[Tt][0-9]+\]'] = gforgeTaskSub
+end
 if $jiraURL != nil
   commentSubstitutions['\b[a-zA-Z]+-[0-9]+\b'] = jiraSub
 end
 if $ticketURL != nil
   commentSubstitutions['\b[Tt][Ii][Cc][Kk][Ee][Tt]\s*#?[0-9]+\b'] = ticketSub
 end
+if $wikiURL != nil
+  commentSubstitutions['\[\[.+\]\]'] = wikiSub
+end
 $commentEncoder = MultiSub.new(commentSubstitutions)
 
 
@@ -1359,12 +1462,16 @@
 		 "T" => tagHandler,
 		 "A" => AddedFileHandler.new,
 		 "R" => RemovedFileHandler.new,
+		 "C" => CopiedFileHandler.new,
 		 "M" => ModifiedFileHandler.new,
+		 "P" => ModifiedPropsFileHandler.new,
 		 "V" => VersionHandler.new]
 
 $handlers["A"].setTagHandler(tagHandler)
 $handlers["R"].setTagHandler(tagHandler)
+$handlers["C"].setTagHandler(tagHandler)
 $handlers["M"].setTagHandler(tagHandler)
+$handlers["P"].setTagHandler(tagHandler)
 
 $fileEntries = Array.new
 $task_list = Array.new
@@ -1374,7 +1481,8 @@
 
   $diff_output_limiter = OutputSizeLimiter.new(mail, $mail_size_limit)
 
-    reader = LogReader.new($stdin)
+  File.open($logfile) do |log|
+    reader = LogReader.new(log)
 
     until reader.eof
       handler = $handlers[reader.currentLineCode]
@@ -1383,11 +1491,16 @@
       end
       handler.handleLines(reader.getLines, $diff_output_limiter)
     end
+  end
 
 end
 
 if $subjectPrefix == nil
-  $subjectPrefix = "[SVN #{Repository.array.join(',')}]"
+  if $svn
+    $subjectPrefix = "[SVN #{Repository.array.join(',')}]"
+  else
+    $subjectPrefix = "[CVS #{Repository.array.join(',')}]"
+  end
 end
 
 if $files_in_subject
@@ -1434,13 +1547,15 @@
   #removed {background-color:#ffdddd;}
   #removedchars {background-color:#ff9999;font-weight:bolder;}
   tr.alt #removed {background-color:#f7cccc;}
+  #copied {background-color:#ccccff;}
+  tr.alt #copied {background-color:#bbbbf7;}
   #info {color:#888888;}
   #context {background-color:#eeeeee;}
   td {padding-left:.3em;padding-right:.3em;}
   tr.head {border-bottom-width:1px;border-bottom-style:solid;}
   tr.head td {padding:0;padding-top:.2em;}
   .task {background-color:#ffff00;}
-  .comment {padding:4px;border:1px dashed #000000;background-color:#ffffdd}
+  .comment {white-space:-moz-pre-wrap;white-space:-pre-wrap;white-space:-o-pre-wrap;white-space:pre-wrap;word-wrap:break-word;padding:4px;border:1px dashed #000000;background-color:#ffffdd}
   .error {color:red;}
   hr {border-width:0px;height:2px;background:black;}
 --></style>
@@ -1466,7 +1581,9 @@
 
   filesAdded = 0
   filesRemoved = 0
+  filesCopied = 0
   filesModified  = 0
+  filesModifiedProps  = 0
   totalLinesAdded = 0
   totalLinesRemoved = 0
   file_count = 0
@@ -1475,24 +1592,26 @@
   $fileEntries.each do |file|
     unless file.repository == last_repository
       last_repository = file.repository
-      mail.print("<tr class=\"head\"><td colspan=\"#{last_repository.has_multiple_tags ? 5 : 4}\">")
+      mail.print("<tr class=\"head\"><td colspan=\"#{last_repository.has_multiple_tags ? 6 : 5}\">")
       if last_repository.has_multiple_tags
         mail.print("Mixed-tag commit")
       else
         mail.print("Commit")
       end
       mail.print(" in <b><tt>#{htmlEncode(last_repository.common_prefix)}</tt></b>")
-      if last_repository.trunk_only?
-        mail.print("<span id=\"info\"> on MAIN</span>")
-      else
-        mail.print(" on ")
-        tagCount = 0
-        last_repository.each_tag do |tag|
-          tagCount += 1
-          if tagCount > 1
-            mail.print tagCount<last_repository.tag_count ? ", " : " &amp; "
+      if !$svn
+        if last_repository.trunk_only?
+          mail.print("<span id=\"info\"> on MAIN</span>")
+        else
+          mail.print(" on ")
+          tagCount = 0
+          last_repository.each_tag do |tag|
+            tagCount += 1
+            if tagCount > 1
+              mail.print tagCount<last_repository.tag_count ? ", " : " &amp; "
+            end
+            mail.print tag ? htmlEncode(tag) : "<span id=\"info\">MAIN</span>"
           end
-          mail.print tag ? htmlEncode(tag) : "<span id=\"info\">MAIN</span>"
         end
       end
       mail.puts("</td></tr>")
@@ -1507,8 +1626,12 @@
       filesAdded += 1
     elsif file.removal?
       filesRemoved += 1
+    elsif file.copied?
+      filesCopied += 1
     elsif file.modification?
       filesModified += 1
+    elsif file.modifiedprops?
+      filesModifiedProps += 1
     end
     name = htmlEncode(file.name_after_common_prefix)
     slashPos = name.rindex("/")
@@ -1528,17 +1651,29 @@
       name = "<span id=\"added\">#{name}</span>"
     elsif file.removal?
       name = "<span id=\"removed\">#{name}</span>"
+    elsif file.copied?
+      name = "<span id=\"copied\">#{name}</span>"
     end
+    mail.print("<td>")
     if file.has_diff?
-      mail.print("<td><tt>#{prefix}<a href=\"#file#{file_count}\">#{name}</a></tt></td>")
+      mail.print("<tt>#{prefix}<a href=\"#file#{file_count}\">#{name}</a></tt>")
     else
-      mail.print("<td><tt>#{prefix}#{name}</tt></td>")
+      mail.print("<tt>#{prefix}#{name}</tt>")
     end
-    if file.isEmpty
-      mail.print("<td colspan=\"2\" align=\"center\"><small id=\"info\">[empty]</small></td>")
+    mail.print(" #{$frontend.log(file)}")
+    mail.print("</td>")
+    if file.copied?
+      mail.print("<td colspan=\"3\" align=\"center\"><small id=\"info\">[copied]</small></td>")
+    elsif file.isEmpty
+      mail.print("<td colspan=\"3\" align=\"center\"><small id=\"info\">[empty]</small></td>")
     elsif file.isBinary
-      mail.print("<td colspan=\"2\" align=\"center\"><small id=\"info\">[binary]</small></td>")
+      mail.print("<td colspan=\"3\" align=\"center\"><small id=\"info\">[binary]</small></td>")
     else
+      if file.modifiedprops?
+        mail.print("<td align=\"right\"><small id=\"info\">[props]</small></td>")
+      else
+        mail.print("<td></td>")
+      end
       if file.lineAdditions>0
         totalLinesAdded += file.lineAdditions
         mail.print("<td align=\"right\" id=\"added\">+#{file.lineAdditions}</td>")
@@ -1565,15 +1700,19 @@
       mail.print("<td nowrap=\"nowrap\" align=\"right\">added #{$frontend.version(file.path,file.toVer)}</td>")
     elsif file.removal?
       mail.print("<td nowrap=\"nowrap\">#{$frontend.version(file.path,file.fromVer)} removed</td>")
+    elsif file.copied?
+      mail.print("<td nowrap=\"nowrap\" align=\"center\">#{$frontend.version(file.path,file.fromVer)} #{$frontend.diff(file)} #{$frontend.version(file.path,file.toVer)}</td>")
     elsif file.modification?
       mail.print("<td nowrap=\"nowrap\" align=\"center\">#{$frontend.version(file.path,file.fromVer)} #{$frontend.diff(file)} #{$frontend.version(file.path,file.toVer)}</td>")
+    elsif file.modifiedprops?
+      mail.print("<td nowrap=\"nowrap\" align=\"center\">#{$frontend.version(file.path,file.fromVer)} #{$frontend.diff(file)} #{$frontend.version(file.path,file.toVer)}</td>")
     end
 
     mail.puts("</tr>")
   end
   if $fileEntries.size>1 && (totalLinesAdded+totalLinesRemoved)>0
     # give total number of lines added/removed accross all files
-    mail.print("<tr><td></td>")
+    mail.print("<tr><td></td><td></td>")
     if totalLinesAdded>0
       mail.print("<td align=\"right\" id=\"added\">+#{totalLinesAdded}</td>")
     else
@@ -1590,7 +1729,7 @@
   
   mail.puts("</table>")
 
-  totalFilesChanged = filesAdded+filesRemoved+filesModified
+  totalFilesChanged = filesAdded+filesRemoved+filesCopied+filesModified+filesModifiedProps
   if totalFilesChanged > 1
     mail.print("<small id=\"info\">")
     changeKind = 0
@@ -1603,11 +1742,21 @@
       mail.print("#{filesRemoved} removed")
       changeKind += 1
     end
+    if filesCopied>0
+      mail.print(" + ") if changeKind>0
+      mail.print("#{filesCopied} copied")
+      changeKind += 1
+    end
     if filesModified>0
       mail.print(" + ") if changeKind>0
       mail.print("#{filesModified} modified")
       changeKind += 1
     end
+    if filesModifiedProps>0
+      mail.print(" + ") if changeKind>0
+      mail.print("#{filesModifiedProps} modified properties")
+      changeKind += 1
+    end
     mail.print(", total #{totalFilesChanged}") if changeKind > 1
     mail.puts(" files</small><br />")
   end
@@ -1742,7 +1891,7 @@
       from = EmailAddress.new(ENV['USER'] || ENV['USERNAME'] || 'cvsspam')
     end  
     unless from.address =~ /@/
-      from.address = "#{from.address}@#{ENV['HOSTNAME']||'localhost'}"
+      from.address = "#{from.address}@#{$hostname}"
     end
     smtp = Net::SMTP.new(@smtp_host)
     blah("connecting to '#{@smtp_host}'")
@@ -1758,6 +1907,40 @@
   end
 end
 
+
+def make_msg_id(localpart, hostpart)
+  "<cvsspam-#{localpart}@#{hostpart}>"
+end
+
+
+# replaces control characters, and a selection of other characters that
+# may not appear unquoted in an RFC822 'word', with underscores.  (It
+# doesn't actually zap '.' though.)
+def zap_header_special_chars(text)
+  text.gsub(/<>()\[\]@,;:\\[\000-\037\177]/, "_")
+end
+
+
+# Mail clients will try to 'thread' together a conversation over
+# several email messages by inspecting the In-Reply-To and References headers,
+# which should refer to previous emails in the conversation by mentioning
+# the value of the previous message's Message-Id header.  This function invents
+# values for these headers so that, in the special case where a *single* file
+# is committed to repeatedly, the emails giving notification of these commits
+# can be threaded together automatically by the mail client.
+def inject_threading_headers(mail)
+  return unless $fileEntries.length == 1
+  file = $fileEntries[0]
+  name = zap_header_special_chars(file.path)
+  if file.fromVer
+    mail.header("References", make_msg_id("#{name}.#{file.fromVer}", $hostname))
+  end
+  if file.toVer
+    mail.header("Message-ID", make_msg_id("#{name}.#{file.toVer}", $hostname))
+  end
+end
+
+
 if $smtp_host
   require 'net/smtp'
   mailer = SMTPMailer.new($smtp_host)
@@ -1769,6 +1952,7 @@
 
 mailer.send($from_address, $recipients) do |mail|
   mail.header("Subject", mailSubject)
+  inject_threading_headers(mail)
   mail.header("MIME-Version", "1.0")
   mail.header("Content-Type", "text/html" + ($charset.nil? ? "" : "; charset=\"#{$charset}\""))
   if ENV['REMOTE_HOST']