Changeset 33031

Timestamp:

2019-04-22T14:58:53+12:00 (5 years ago)

Author:

cpb16

Message:

Completed numpages checking. Generated makefiles and scripts to streamline process. Need to now fix 'no such file or directory error from the RUN-META.sh file'.

Location:

other-projects/is-sheet-music-encore/trunk

Files:

• -COMPX520-README.txt (modified) (3 diffs)
• Makefile (added)
• java-gen-corpus/Makefile(DONTNEED?) (added)
• java-gen-corpus/TabProcMetaListGen.java (modified) (1 diff)
• java-gen-corpus/TabProcTextGen.java (modified) (1 diff)
• java-gen-corpus/TabRndListGen.class (modified) ( previous)
• java-gen-corpus/TabRndListGen.java (modified) (2 diffs)
• java-gen-corpus/ValidIDListGen.sh (added)

other-projects/is-sheet-music-encore/trunk/-COMPX520-README.txt

@@ -1 +1 @@
 INSTRUCTIONS
+
+The RUN scripts, think that some IDs are directories. Correct this
+
 TEST CORPUS GENERATION
 (java-gen-corpus/..):
@@ -14 +17 @@
 (COMPX520-DOWNLOADER-PNG.txt , COMPX520-RUN-PNG.sh , ddapiclient2-extended.pl
 "source ./SETUP.bash"
-"./COMPX520-DOWNLOADER-PNG.txt <java-gen-corpus/filename> <page_num>"
-
-
+"./COMPX520-DOWNLOADER-PNG.sh <java-gen-corpus/filename> <page_num>"
 
 
@@ -22 +23 @@
 (COMPX520-DOWNLOADER-ZIP.txt , COMPX520-RUN-XIP.sh , ddapiclient2-extended-ZIP.pl):
 
-  "./COMPX520-DOWNLOADER-ZIP.txt <java-gen-corpus/filename>"
+  "./COMPX520-DOWNLOADER-ZIP.sh <java-gen-corpus/filename>"
 
 

other-projects/is-sheet-music-encore/trunk/java-gen-corpus/TabProcMetaListGen.java

@@ -13 +13 @@
                 
                 
-            if (args.length != 1) {
-                System.out.println("Usage: TabProcMetaListGen <inputFilename> <outputFilename>");
+            if (args.length != 2) {
+                System.out.println("Usage: TabProcMetaListGen <inputFilename> <listFilename>");
             }
             else {
+                //Variables
                 String inputFilename = args[0];
-                //String outputFilename = args[1];
-                    
+                String listFilename = args[1];      
+                FileReader fileReader = new FileReader(inputFilename);
+                BufferedReader buf = new BufferedReader(fileReader);
+                FileWriter listWriter = new FileWriter(listFilename, true);
+                String line = null;
+                String[] item;
+                
+                String idLine = null;
+                String id = null;
+                String numpages = null;
+                                    
                 System.out.println("Processing: " + inputFilename);
                 
-                FileReader fileReader = new FileReader(inputFilename);
-                BufferedReader buf = new BufferedReader(fileReader);
-                //FileWriter fw = new FileWriter(outputFilename);
-                String line = null;
-                String[] item;
-
                 //Splits into each record
-                while ((line = buf.readLine()) != null) {
-                    
-                    //Splits by tab, leaves "" for every blank entry
-                    //Check items to be equal
-                    //System.out.println(line);
+                while ((line = buf.readLine()) != null) {                   
+                    if(line.contains("<id>")){
+                        //Isoclate and store the id from the line
+                        idLine = line.substring(line.indexOf(">")+1, line.indexOf("</"));
+                        id  = idLine.substring(idLine.lastIndexOf("meta/")+5);
+                        
+                    }   
                     if(line.contains("<htd:numpages>")){
-                        String result = line.substring(line.indexOf(">")+1, line.indexOf(">")+2);
-                        System.out.println(result);                     
-                    }
-                    if(line.contains("<id>")){
-                        String result = line.substring(line.indexOf(">")+1, line.indexOf("</"));
-                        System.out.println(result);
-                    }
-                            
-                }       
+                        //Iscolate and store the page number
+                        numpages = line.substring(line.indexOf(">")+1, line.lastIndexOf("<"));
+                                        
+                    }                                           
+                }
+                
+                //Check if there are more than 10 pages
+                if(Integer.parseInt(numpages) >= 10){
+                //Add extracted metadata to output list
+                listWriter.write(id + '\t' + numpages + '\n');
+                }
                 buf.close();
-                //fw.close();
+                listWriter.close();
             }
         }catch(Exception e){

other-projects/is-sheet-music-encore/trunk/java-gen-corpus/TabProcTextGen.java

@@ -60 +60 @@
 }
 
-//REFERNECES
+//REFERNECES 
 //https://www.javatpoint.com/java-filewriter-class
 //https://docs.oracle.com/javase/8/docs/api/index.html?java/io/FileWriter.html

other-projects/is-sheet-music-encore/trunk/java-gen-corpus/TabRndListGen.java

@@ -12 +12 @@
     try{
         if (args.length != 3){
-        System.out.println("Usage: RandomItemSelecta <inputFilename> <outputCount> <outputFilename>");
+        System.out.println("Usage: TabRndListGen <inputFilename> <outputCount> <outputFilename>");
         }
         else{
@@ -27 +27 @@
         ArrayList<String> subList;
         String line = null;
+        String[] item;
 
         //Add items to Array
         while ((line = buf.readLine()) != null) {
-            list.add(line);     
+            //Split line by tab
+            item = line.split("\t", -1);
+            //Add first element (ID)
+            list.add(item[0]);      
         }
         //randomize list