logstash-filter-ezproxy 0.1.1 → 0.2.0

data/lib/logstash/filters/lexis_webanalytics.rb

@@ -0,0 +1,81 @@
+require 'json'
+
+module LexisWebAnalytics
+  def LexisWebAnalytics.parse (path, params, uri)
+
+    raw_url = uri.to_s
+
+    data = {
+        "provider" => "lexisnexis_webanalytics"
+    }
+  
+    if (match = /^\/Document\/([\w]+)\/([\w-]+)$/i.match(path))
+      data['rtype'] = 'TOC'
+      data['mime']   = 'HTML'
+      data['unit_id'] = params['rndNum'][0]
+
+      if ((match = /([a-z_]+)_(\d+_\w+_\d+)_n_(\d+)/i.match(match[1])))
+        data['title_id'] = match[1]
+      end
+  
+
+    elsif ((match = /^\/Docview.aspx$/i.match(path)))
+      data['rtype']    = 'ARTICLE'
+      data['mime']     = 'HTML'
+      citationData = JSON.parse(params['citationData'][0])
+      data['unit_id']   = citationData['docId']
+      data['title_id'] = citationData['docId'].split('_')[1]
+    
+
+    elsif ((match = /^\/wa_k4c.watag$/i.match(path)))
+      if ((match3 = /&wa_DocId=([0-9a-zA-Z_-]+)&/i.match(raw_url)))
+        data['unit_id'] = match3[1]
+        if ((match3a = /PS_([A-Z]+)/.match(data['unit_id'])))
+          data['title_id'] = match3a[1]
+        end
+      end
+    
+      if ((match4 = /&wa_DocSourceType=([0-9a-z%é_]+)&/i.match(raw_url)))
+        docSourceType = match4[1]
+        
+        if (docSourceType == 'FicheMethodo' || docSourceType == 'FicheRevision')
+          data['rtype']    = 'ENCYCLOPAEDIA_ENTRY'
+          data['mime']     = 'HTML'
+        
+        elsif (docSourceType == 'PresseSommaire')
+          data['rtype']    = 'TOC'
+          data['mime']     = 'HTML'
+        
+        elsif (docSourceType == 'Presse')
+          data['rtype']    = 'ARTICLE'
+          data['mime']     = 'HTML'
+        
+        elsif (docSourceType == 'En_eFascicule')
+          if ((match5 = /&wa_UserAction=([a-zA-Z]+)&/i.match(raw_url)))
+            userAction = match5[1]
+
+            if (userAction == 'ViewDoc' || userAction == 'ChangeToc')
+              data['rtype']    = 'ENCYCLOPAEDIA_ENTRY'
+              data['mime']     = 'HTML'
+            end
+          end
+        end
+      end
+      
+
+      if (/L[é%C3A9]+gislationconsolid[é%C3A9]+e/.match(docSourceType))
+        if ((match6 = /&wa_UserAction=([a-zA-Z]+)&/i.match(raw_url)))
+          userAction = match6[1]
+
+          if (userAction == 'ViewDoc' || userAction == 'ChangeToc')
+            data['rtype'] = 'CODES'
+            data['mime']  = 'HTML'
+          end
+        end
+      end
+    end
+        
+    return data
+
+  end
+end

data/lib/logstash/filters/myilibrary.rb

@@ -0,0 +1,29 @@
+module MyILibrary
+  def MyILibrary.parse (path, params)
+
+    data = {
+      "provider" => "myilibrary"
+    }
+
+    if (/\/Open\.aspx/.match(path) || /\/browse\/open\.asp/i.match(path) || /^\/$/.match(path))
+      if params.key?('id')
+        data['title_id'] = params['id'][0]
+        data['unit_id'] = params['id'][0]
+        data['rtype'] = 'BOOK'
+        data['mime'] = 'MISC'
+      end
+
+    elsif (/\/Viewer\/getImage\_Servlet\.aspx/i.match(path))
+      data['rtype'] = 'BOOK_PAGE'
+      data['mime'] = 'JPG'
+
+    elsif (/\/Viewer\/get[DP]MP\_Servlet\.aspx/i.match(path))
+      data['rtype'] = 'BOOK_PAGE'
+      data['mime'] = params['t'][0]
+
+    end
+
+    return data
+
+  end
+end

data/lib/logstash/filters/oxford.rb

@@ -0,0 +1,38 @@
+module Oxford
+  def Oxford.parse (path, params)
+
+    data = {
+      "provider" => "oxford"
+    }
+
+    if (match = /\/view\/([0-9\.]+\/[a-z0-9\.\/\:]+)\/(.+?)(-([a-z][\-a-z0-9]+))?$/i.match(path))
+      data['doi'] = match[1]
+      data['title_id'] = match[2]
+      data['unit_id'] = match[2]
+
+      if (match[4])
+        match4 = match[4].downcase.split("-")
+
+        case match4[0]
+          when "chapter"
+            data['rtype'] = "BOOK_CHAPTER"
+          when "bibliography"
+            data['rtype'] = "BIBLIOGRAPHY"
+          when "indexlist"
+            data['rtype'] = 'TOC'
+        end
+      else
+        data['rtype'] = 'BOOK'
+      end
+
+      if params.key?('print')
+        data['mime'] = params['print'][0].upcase
+      end
+
+    elsif (match = /\/doc\/([0-9\.]+\/[a-z0-9\.\/\:]+)\/.+/i.match(path))
+      data['doi'] = match[1]
+    end
+
+    return data
+  end
+end

data/lib/logstash/filters/proquest.rb

@@ -0,0 +1,42 @@
+module Proquest
+  def Proquest.parse (path, params)
+    data = {
+      "provider" => "proquest"
+    }
+
+    if (/\/lib\/lancaster\/remoteDocServer\.api/i.match(path))
+      data['rtype'] = 'BOOK_PAGE'
+      data['mime'] = 'MISC'
+      data['page'] = params['pageNum'][0]
+      data['remote_id'] = params['remote_id'][0]
+
+    elsif (/\/lib\/lancaster\/detail\.action/i.match(path))
+      data['rtype'] = 'TOC'
+      data['mime'] = 'HTML'
+      data['title_id'] = params['docID'][0]
+      data['unit_id'] = params['docID'][0]
+
+    elsif (/\/lib\/lancaster\/reader\.action/i.match(path))
+      data['rtype'] = 'BOOK'
+      data['mime'] = 'MISC'
+      data['title_id'] = params['docID'][0]
+      data['unit_id'] = params['docID'][0]
+
+    elsif (/\/lib\/lancaster\/docAccess\.api/i.match(path))
+      data['rtype'] = 'TOC'
+      data['mime'] = 'JSON'
+      data['title_id'] = params['docid'][0]
+      data['unit_id'] = params['docid'][0]
+      data['remote_id'] = params['remote_id'][0]
+
+    elsif (/\/lib\/lancaster\/docSearch\.api/i.match(path))
+      data['rtype'] = 'TOC'
+      data['mime'] = 'JSON'
+      data['title_id'] = params['docid'][0]
+      data['unit_id'] = params['docid'][0]
+      data['remote_id'] = params['remote_id'][0]
+    end
+
+    return data
+  end
+end

data/lib/logstash/filters/sciencedirect.rb

@@ -4,9 +4,7 @@ require 'cgi'
 module ScienceDirect
   def ScienceDirect.parse (path, params)
 
-    data = {
-      "provider" => "sciencedirect"
-    }
+    data = {}
 
     if (params.key?("_ob"))
       if (params['_cdi'])

data/lib/logstash/filters/scopus.rb

@@ -0,0 +1,57 @@
+
+module Scopus
+  def Scopus.parse (path, params)
+
+    data = {
+      "provider" => "scopus"
+    }
+
+    if (/^\/results\/citedbyresults.ur[il]$/i.match(path))
+      data['mime']   = 'HTML'
+      data['rtype']  = 'REF'
+      data['unit_id'] = params['cite'][0]
+
+    elsif (match = /^\/record\/([a-z]+)\.ur[il]$/i.match(path))
+      case (match[1])
+      when 'display'
+        data['mime']   = 'HTML'
+        data['rtype']  = 'ABS'
+        data['unit_id'] = params['eid'][0]
+        
+      when 'references'
+        data['mime']   = 'HTML'
+        data['rtype']  = 'REF'
+        data['unit_id'] = params['currentRecordPageEID'][0]
+        
+      when 'detail'
+        data['mime']  = 'HTML'
+        data['rtype'] = 'BIO'
+        if (params.key?('authorId'))
+          data['unit_id'] = params['authorId'][0]
+        end
+        
+      when 'pdfdownload'
+        data['rtype']  = 'REF'
+        data['mime']   = 'PDF'
+        data['unit_id'] = params['eid'][0]
+      end
+    
+    elsif (/^\/authid\/detail\.ur[il]$/i.match(path))
+      data['mime']  = 'HTML'
+      data['rtype'] = 'BIO'
+      if (params.key?('authorId'))
+        data['unit_id'] = params['authorId'][0]
+      end
+    
+    elsif (/^\/citation\/print\.ur[il]$/i.match(path))
+      data['mime']  = 'PRINT'
+      data['rtype'] = 'REF'
+      if (params.key?('eid'))
+        data['unit_id'] = params['eid'][0]
+      end
+    end
+    
+    return data
+
+  end
+end

data/lib/logstash/filters/springer.rb

@@ -115,7 +115,7 @@ module Springer
 
 
     elsif ((match = /^\/(download|static)\/([a-z]+)\/(([0-9.]*)\/([^\/]*)).epub/.match(path)))
-      if (/([0-9]+)\.([0-9]+)/.test(match[4]))
+      if (/([0-9]+)\.([0-9]+)/.match(match[4]))
         data['doi']      = match[3]
         data['unit_id']   = match[5] + '.epub'
         data['print_identifier'] = match[5]

data/lib/logstash/filters/webofknowledge.rb

@@ -0,0 +1,85 @@
+module WebOfKnowledge
+  def WebOfKnowledge.parse (path, params)
+
+    data = {
+        "provider" => "dawsonera"
+    }
+
+    if (match = /^\/([a-z_]+)\.do$/i.match(path))
+
+      if (params.key?('product'))                
+        productId = params['product'][0].kind_of?(Array) ? params['product'][0][0] : params['product'][0]
+      end
+
+      case (match[1])
+      when 'Search', 'InterService'
+        data['rtype'] = 'TOC'
+        data['mime']  = 'HTML'
+        if (productId)
+          data['title_id'] = productId
+        end
+
+      when 'full_record'
+        data['rtype'] = 'REF'
+        data['mime']  = 'HTML'
+        if (productId)
+          data['title_id'] = productId
+        end
+        
+      when 'CitationReport'
+        data['rtype'] = 'ANALYSIS'
+        data['mime']  = 'MISC'
+        if (productId)
+          data['title_id'] = productId
+        end
+      end
+    
+      if (/^([a-z]+)_GeneralSearch_input/i.match(match[1]))
+        data['rtype'] = 'SEARCH'
+        data['mime']  = 'HTML'
+
+        if (productId)
+          data['title_id'] = productId
+        end
+      end
+    
+
+    elsif (match = /^\/([a-zA-z_]*)\.action$/i.match(path))
+                  
+      case (match[1])
+      when 'JCRJournalHomeAction'
+        data['rtype'] = 'TOC'
+        data['mime']  = 'HTML'
+      when 'JCRJournalProfileAction'
+        data['rtype'] = 'TABLE'
+        data['mime']  = 'HTML'
+
+        if (params.key?('journalTitle'))
+          data['publication_title'] = params['journalTitle'][0]
+        end
+        if (params.key?('journal'))
+          data['title_id'] = params['journal'][0]
+          data['unit_id']   = "impact/" +  params['journal'][0] + "/" + params['year'][0]
+        end
+
+      when 'IndicatorsAction'
+        data['rtype'] = 'MAP'
+        data['mime']  = 'MISC'
+
+      when 'DocumentsAction'
+        data['rtype'] = 'GRAPH'
+        data['mime']  = 'MISC'
+
+      else
+        return {}
+      end
+
+    elsif ((match = /^\/([a-z]{2,3})\/analyze\.do$/i.match(path)))
+      data['rtype'] = 'ANALYSIS'
+      data['mime']  = 'MISC'
+    end
+
+    return data
+
+  end
+end

data/lib/logstash/filters/wiley.rb

@@ -6,185 +6,223 @@ module Wiley
     data = {
       "provider" => "wiley"
     }
-        
-    if ((match = /\/journal\/(10\.[0-9]+\/(\(ISSN\)([0-9]{4}-[0-9]{3}[0-9xX])))/i.match(path)))
-      data['doi']    = match[1];
-      data['unit_id'] = match[2];
-      data['rtype']  = 'TOC';
-      data['mime']   = 'MISC';
 
-      data['online_identifier'] = match[3];
+    if ((match = /^\/pdf\/(10\.[0-9]+\/([0-9x]+))(\.ch[0-9]+)$/i.match(path)))
+      data['rtype']  = 'BOOK_SECTION'
+      data['mime']   = 'PDF'
+      data['doi']    = match[1]
+      data['unit_id'] = match[2] + match[3]
+      data['online_identifier'] = match[2]
+
+    elsif ((match = /^\/doi(\/[a-z]+)?\/(10\.[0-9]+\/([a-z0-9._-]+))$/i.match(path)))
+      data['doi']    = match[2]
+      data['unit_id'] = match[3]
+
+      case (match[1])
+      when '/pdf', '/epdf'
+       data['rtype'] = 'ARTICLE'
+        data['mime']  = 'PDF'
+
+      when '/full'
+        data['rtype'] = 'ARTICLE'
+        data['mime']  = 'HTML'
+
+      when '/abs'
+        data['rtype'] = 'ABS'
+        data['mime']  = 'HTML'
+
+      else
+        data['rtype'] = 'ARTICLE'
+        data['mime']  = 'HTML'
+      end
+ 
+
+    elsif ((match = /^\/toc\/toc\/(([0-9]+)\/([0-9]+)\/([0-9]+))$/i.match(path)))
+      data['rtype']    = 'TOC'
+      data['mime']     = 'MISC'
+      data['unit_id']   = match[1]
+      data['title_id'] = match[2]
+      data['vol']      = match[3]
+      data['issue']    = match[4]
+
+    elsif ((match = /^\/journal\/([0-9]+)$/i.match(path)))
+      data['rtype']    = 'TOC'
+      data['mime']     = 'MISC'
+      data['title_id'] = match[1]
+        
+    elsif ((match = /\/journal\/(10\.[0-9]+\/(\(ISSN\)([0-9]{4}-[0-9]{3}[0-9xX])))/i.match(path)))
+      data['doi']    = match[1]
+      data['unit_id'] = match[2]
+      data['rtype']  = 'TOC'
+      data['mime']   = 'MISC'
+      data['online_identifier'] = match[3]
 
     elsif ((match = /^\/doi\/(10\.[0-9]+\/(([^.]+)\.([0-9]{4})\.[^.]+\.[^.]+))\/issuetoc$/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[3].upcase;
-      data['rtype']    = 'TOC';
-      data['mime']     = 'MISC';
-
-      data['publication_date'] = match[4];
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[3].upcase
+      data['rtype']    = 'TOC'
+      data['mime']     = 'MISC'
+      data['publication_date'] = match[4]
 
     elsif ((match = /^\/doi\/(10\.[0-9]+\/(j\.([0-9]{4}-[0-9]{3}[0-9xX])\.([0-9]{4})\.[^.]+\.[^.]+))\/abstract$/i.match(path)))
-      data['doi']    = match[1];
-      data['unit_id'] = match[2];
-      data['rtype']  = 'ABS';
-      data['mime']   = 'MISC';
-
-      data['online_identifier'] = match[3];
-      data['publication_date']  = match[4];
+      data['doi']    = match[1]
+      data['unit_id'] = match[2]
+      data['rtype']  = 'ABS'
+      data['mime']   = 'MISC'
+      data['online_identifier'] = match[3]
+      data['publication_date']  = match[4]
 
     elsif ((match = /^\/doi\/(10\.[0-9]+\/(([^.]+)\.([0-9]{4})[0-9]+))\/abstract$/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[3].upcase;
-      data['rtype']    = 'ABS';
-      data['mime']     = 'MISC';
-
-      data['publication_date'] = match[4];
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[3].upcase
+      data['rtype']    = 'ABS'
+      data['mime']     = 'MISC'
+      data['publication_date'] = match[4]
 
     elsif ((match = /^\/doi\/(10\.[0-9]+\/(([^.]+)\.[0-9]+))\/full$/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[3].upcase;
-      data['rtype']    = 'ARTICLE';
-      data['mime']     = 'HTML';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[3].upcase
+      data['rtype']    = 'ARTICLE'
+      data['mime']     = 'HTML'
 
     elsif ((match = /^\/doi\/(10\.[0-9]+\/(j\.([0-9]{4}-[0-9]{3}[0-9xX])\.([0-9]{4})\.[^.]+\.[^.]+))\/pdf$/i.match(path)))
-      data['doi']    = match[1];
-      data['unit_id'] = match[2];
-      data['rtype']  = 'ARTICLE';
-      data['mime']   = 'PDF';
-
-      data['online_identifier'] = match[3];
-      data['publication_date']  = match[4];
+      data['doi']    = match[1]
+      data['unit_id'] = match[2]
+      data['rtype']  = 'ARTICLE'
+      data['mime']   = 'PDF'
+      data['online_identifier'] = match[3]
+      data['publication_date']  = match[4]
 
     elsif ((match = /^\/doi\/(10\.[0-9]+\/(([^.]+)\.[0-9]+))\/pdf$/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[3].upcase;
-      data['rtype']    = 'ARTICLE';
-      data['mime']     = 'PDF';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[3].upcase
+      data['rtype']    = 'ARTICLE'
+      data['mime']     = 'PDF'
 
     elsif ((match = /^\/book\/(10\.[0-9]+\/([0-9]+))$/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[2].upcase;
-      data['rtype']    = 'TOC';
-      data['mime']     = 'MISC';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[2].upcase
+      data['rtype']    = 'TOC'
+      data['mime']     = 'MISC'
 
-      data['print_identifier']  = match[2];
+      data['print_identifier']  = match[2]
 
     elsif (match = /^\/doi\/(10\.[0-9]+\/(([0-9]+)\.[^.]+))\/pdf$/i.match(path))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[3].upcase;
-      data['rtype']    = 'BOOK_SECTION';
-      data['mime']     = 'PDF';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[3].upcase
+      data['rtype']    = 'BOOK_SECTION'
+      data['mime']     = 'PDF'
 
-      data['print_identifier']  = match[3];
+      data['print_identifier']  = match[3]
 
     elsif (match = /^\/enhanced\/doi\/(10\.[0-9]+\/(([^.]+)\.[^\/]+))\/?$/i.match(path))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[3].upcase;
-      data['rtype']    = 'ARTICLE';
-      data['mime']     = 'HTML';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[3].upcase
+      data['rtype']    = 'ARTICLE'
+      data['mime']     = 'HTML'
 
     elsif ((match = /^\/enhanced\/doi\/(10\.[0-9]+\/(([0-9]{4})([a-z0-9]{2})[a-z0-9]+))\/?$/i.match(path)))
 
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[4].upcase;
-      data['rtype']    = 'ARTICLE';
-      data['mime']     = 'HTML';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[4].upcase
+      data['rtype']    = 'ARTICLE'
+      data['mime']     = 'HTML'
 
-      data['publication_date'] = match[3];
+      data['publication_date'] = match[3]
 
     elsif ((match = /^\/agu\/issue\/(10\.[0-9]+\/(([^.]+)\.[^\/]+))\/?$/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[3].upcase;
-      data['rtype']    = 'TOC';
-      data['mime']     = 'HTML';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[3].upcase
+      data['rtype']    = 'TOC'
+      data['mime']     = 'HTML'
 
     elsif (/^\/readcube$/i.match(path))
-      data['rtype'] = 'ARTICLE';
-      data['mime']  = 'READCUBE';
+      data['rtype'] = 'ARTICLE'
+      data['mime']  = 'READCUBE'
 
       if (params.key?("resource"))
 
-        data['doi']    = params["resource"][0];
-        data['unit_id'] = params["resource"][0].split('/')[1];
+        data['doi']    = params["resource"][0]
+        data['unit_id'] = params["resource"][0].split('/')[1]
         if ((match = /(10\.[0-9]+)\/([0-9]{4})([a-z0-9]{2})([^\/]+)$/i.match(params['resource'][0])))
-            data['title_id'] = match[3].upcase;
+            data['title_id'] = match[3].upcase
         end
       end
       
 
 
     elsif ((match = /^\/doi\/(10\.[0-9]+\/([a-z]{1}[0-9]{8}([0-9]{2})[a-z0-9]+))\/pdf$/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[2].upcase;
-      data['rtype']    = 'ARTICLE';
-      data['mime']     = 'PDF';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[2].upcase
+      data['rtype']    = 'ARTICLE'
+      data['mime']     = 'PDF'
 
-      data['publication_date'] = '20' + match[3];
+      data['publication_date'] = '20' + match[3]
 
     elsif ((match = /^\/iucr\/(10\.[0-9]+\/([a-z]{1}[0-9]{8}([0-9]{2})[0-9a-z]+))/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2] ;
-      data['title_id'] = match[2].upcase;
-      data['rtype']    = 'ARTICLE';
-      data['mime']     = 'HTML';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2] 
+      data['title_id'] = match[2].upcase
+      data['rtype']    = 'ARTICLE'
+      data['mime']     = 'HTML'
 
-      data['publication_date'] = '20' + match[3];
+      data['publication_date'] = '20' + match[3]
 
     elsif ((match = /^\/doi\/(10\.[0-9]+\/([a-z]{1}[0-9]{8}([0-9]{2})[0-9a-z]+))\/([a-z]+)$/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[2].upcase;
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[2].upcase
 
-      data['publication_date'] = '20' + match[3];
+      data['publication_date'] = '20' + match[3]
 
       case (match[4])
       when 'abstract'
-        data['rtype'] = 'ABS';
-        data['mime']  = 'MISC';
+        data['rtype'] = 'ABS'
+        data['mime']  = 'MISC'
       when 'pdf'
-        data['rtype'] = 'ARTICLE';
-        data['mime']  = 'PDF';
+        data['rtype'] = 'ARTICLE'
+        data['mime']  = 'PDF'
       when 'full'
-        data['mime']  = 'PDF';
-        data['rtype'] = 'HTML';
+        data['mime']  = 'PDF'
+        data['rtype'] = 'HTML'
       end
 
     elsif ((match = /^\/store\/(10\.[0-9]+\/(([a-z]+)\.([0-9]{4})[0-9]+))\/asset\/[a-z]+[0-9]+.pdf$/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[3].upcase;
-      data['mime']     = 'PDF';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[3].upcase
+      data['mime']     = 'PDF'
 
-      data['publication_date'] = match[4];
+      data['publication_date'] = match[4]
 
     elsif ((match = /^\/doi\/(10\.[0-9]+\/(([0-9]{2,4})([a-z]+)[0-9]+))\/(pdf|full)$/i.match(path)))
-      data['doi']      = match[1];
-      data['unit_id']   = match[2];
-      data['title_id'] = match[4].upcase;
-      data['rtype']    = 'ARTICLE';
-      data['mime']     = match[5] == 'pdf' ? 'PDF' : 'HTML';
+      data['doi']      = match[1]
+      data['unit_id']   = match[2]
+      data['title_id'] = match[4].upcase
+      data['rtype']    = 'ARTICLE'
+      data['mime']     = match[5] == 'pdf' ? 'PDF' : 'HTML'
 
-      data['publication_date'] = match[3];
+      data['publication_date'] = match[3]
 
       if (match[3].length === 2)
-        data['publication_date'] = '19' + match[3];
+        data['publication_date'] = '19' + match[3]
       end
 
     elsif ((match = /^\/doi\/(10\.[0-9]+\/([^.]+))\/(pdf|full)$/i.match(path)))
-      data['doi']    = match[1];
-      data['unit_id'] = match[2];
-      data['rtype']  = 'ARTICLE';
-      data['mime']   = match[3] === 'pdf' ? 'PDF' : 'HTML';
+      data['doi']    = match[1]
+      data['unit_id'] = match[2]
+      data['rtype']  = 'ARTICLE'
+      data['mime']   = match[3] === 'pdf' ? 'PDF' : 'HTML'
     end
 
     return data