mailcvt 0.2.27 → 0.2.28

data/lib/encoded_word.rb

@@ -12,13 +12,42 @@ class EncodedWord
     end
 
     def decode
+        decode_all_mlog
+        combine_all_mlog_plain
+    end
+
+    def combine_all_mlog_plain
+        File.open(File.join(@inputdir, 'all_mlog.csv'), 'w:utf-8') do |out|
+            out.puts '"key","","","date","from","to","cc","bcc","subject","attach"'
+            Dir.glob(File.join(@inputdir, File.join('**', '*.plain'))).select do |f|
+                puts f
+                File.open(f, 'r:utf-8').each_line do |line|
+                    parts = mysplit(line)
+                    key = parts[3]
+                    date = parts[0]
+                    subject = parts[2]
+                    from = parts[3]
+                    to = parts[4].gsub("\a", ';')
+                    cc = parts[5].gsub("\a", ';')
+                    attach = parts[6].gsub("\a", ';')
+                    out.puts %Q("#{key}","","","#{date}","#{from}","#{to}","#{cc}","","#{subject}","#{attach}")
+                end
+            end
+        end
+    end
+ 
+    def decode_all_mlog
         Dir.glob(File.join(@inputdir, File.join('**', '*.mlog'))).select do |f|
             puts f
-            File.open(f + '.plain', 'w') do |out|
+            mids = {}
+            File.open(f + '.plain', 'w:utf-8') do |out|
                 File.open(f) do |input|
                     @input_enc = input.external_encoding
                     input.each_line do |line|
                         parts = mysplit(line)
+                        next if mids.has_key?(parts[1])
+                        mids[parts[1]] = 0
+
                         newparts = []
                         newparts << format_date(parts[0]) #date
                         newparts << parts[1] #message-id
@@ -26,7 +55,7 @@ class EncodedWord
                         newparts << trim_emails(parts[3]) #from
                         newparts << trim_emails(parts[4]) #to
                         newparts << trim_emails(parts[5]) #cc
-                        newparts << decode_attachments(parts[6]) unless parts.length == 6 #attachment
+                        newparts << decode_attaches(parts)
                         out.puts newparts.join("\t")
                     end
                 end
@@ -39,6 +68,7 @@ class EncodedWord
         return [] unless line.length > 0
 
         parts = []
+        last = -1
         pos1 = -1
         while true do
             pos1 += 1
@@ -47,7 +77,8 @@ class EncodedWord
                 parts << line[pos1...pos2]
                 pos1 = pos2
             else
-                parts << line[pos1..-1]
+                last -= 1 if line[last] == "\n"
+                parts << line[pos1..last]
                 break
             end
         end
@@ -99,15 +130,24 @@ class EncodedWord
         line[pos1..pos2]
     end
 
-    def decode_attachments(attachments)
-        return '' unless attachments and attachments.length > 0
-        attachments = attachments.encode('utf-8', @input_enc, :undef=>:replace, :invalid=>:replace)
-        parts = mysplit(attachments, "\a")
+    def decode_attaches(parts)
+        attaches = []
+        6.upto(parts.length-1) do |i|
+            attaches << decode_attach(parts[i])
+        end
+        return '' unless attaches.length > 0
+        attaches.join("\a")
+    end
+
+    def decode_attach(attach)
+        return '' unless attach and attach.length > 0
+        attach = attach.encode('utf-8', @input_enc, :undef=>:replace, :invalid=>:replace)
+        parts = mysplit(attach, "\a")
         newparts = []
         parts.each do |p|
             newparts << mime_decode(p)
         end
-        newparts.join("\a")
+        newparts.join('')
     end
 
     def mime_decode(input, out_charset = 'utf-8')

data/lib/mailcvt/version.rb

@@ -1,3 +1,3 @@
 module Mailcvt
-  VERSION = '0.2.27'
+  VERSION = '0.2.28'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: mailcvt
 version: !ruby/object:Gem::Version
-  version: 0.2.27
+  version: 0.2.28
   prerelease: 
 platform: ruby
 authors: