diff scripts/comment_parser.py @ 1457:c8a9825aaa05

Merge from branch "WAC2016"

--- a/scripts/comment_parser.py	Tue Oct 13 10:20:04 2015 +0100
+++ b/scripts/comment_parser.py	Mon Nov 23 09:13:12 2015 +0000
@@ -4,9 +4,35 @@
 import xml.etree.ElementTree as ET
 import os
 import csv
+import sys
 
-# XML results files location (modify as needed):
-folder_name = "../saves"    # Looks in 'saves/' folder from 'scripts/' folder
+# COMMAND LINE ARGUMENTS
+
+assert len(sys.argv)<3, "comment_parser takes at most 1 command line argument\n"+\
+                        "Use: python score_parser.py [rating_folder_location]"
+
+# XML results files location
+if len(sys.argv) == 1:
+    folder_name = "../saves"    # Looks in 'saves/' folder from 'scripts/' folder
+    print "Use: python  comment_parser.py [XML_files_location]"
+    print "Using default path: " + folder_name
+elif len(sys.argv) == 2:
+    folder_name = sys.argv[1]   # First command line argument is folder
+
+# check if folder_name exists
+if not os.path.exists(folder_name):
+    #the file is not there
+    print "Folder '"+folder_name+"' does not exist."
+    sys.exit() # terminate script execution
+elif not os.access(os.path.dirname(folder_name), os.W_OK):
+    #the file does exist but write privileges are not given
+    print "No write privileges in folder '"+folder_name+"'."
+
+
+# CODE
+
+# remember which files have been opened this time
+file_history = []
 
 # get every XML file in folder
 for file in os.listdir(folder_name): 
@@ -33,23 +59,28 @@
                     
                     csv_name = folder_name +'/' + page_name+'/'+page_name+'-comments-'+audio_id+'.csv'
 
-                    # append (!) to file [page_name]/[page_name]-comments-[id].csv
-                    with open(csv_name, 'a') as csvfile:
-                        writer = csv.writer(csvfile, 
-                                            delimiter=',', 
-                                            dialect="excel",
-                                            quoting=csv.QUOTE_ALL)
-                        commentstr = audioelement.find("./comment/response").text
+                    # If file hasn't been opened yet this time, empty
+                    if csv_name not in file_history:
+                        csvfile = open(csv_name, 'w')
+                        file_history.append(csv_name) # remember this file has been written to this time around
+                    else: 
+                        # append (!) to file [page_name]/[page_name]-comments-[id].csv
+                        csvfile = open(csv_name, 'a')
+                    writer = csv.writer(csvfile, 
+                                        delimiter=',', 
+                                        dialect="excel",
+                                        quoting=csv.QUOTE_ALL)
+                    commentstr = audioelement.find("./comment/response").text
                         
-                        if commentstr is None:
-                           commentstr = '';
-                            
-                        # anonymous comments:
-                        #writer.writerow([commentstr.encode("utf-8")]) 
-                        # comments with (file) name:
-                        writer.writerow([file[:-4]] + [commentstr.encode("utf-8")]) 
+                    if commentstr is None:
+                       commentstr = ''
+                        
+                    # anonymous comments:
+                    #writer.writerow([commentstr.encode("utf-8")]) 
+                    # comments with (file) name:
+                    writer.writerow([file[:-4]] + [commentstr.encode("utf-8")]) 
 
-                        #TODO Replace 'new line' in comment with something else?
+                    #TODO Replace 'new line' in comment with something else?
                         
 # PRO TIP: Change from csv to txt by running this in bash: 
 # $ cd folder_where_csvs_are/