giuliomoro@15: #!/usr/bin/python
giuliomoro@15: # -*- coding: utf-8 -*-
giuliomoro@15: 
giuliomoro@15: import xml.etree.ElementTree as ET
giuliomoro@15: import os
giuliomoro@15: import csv
giuliomoro@15: import sys
giuliomoro@15: 
giuliomoro@15: # COMMAND LINE ARGUMENTS
giuliomoro@15: 
giuliomoro@15: assert len(sys.argv)<3, "comment_parser takes at most 1 command line argument\n"+\
giuliomoro@15:                         "Use: python score_parser.py [rating_folder_location]"
giuliomoro@15: 
giuliomoro@15: # XML results files location
giuliomoro@15: if len(sys.argv) == 1:
giuliomoro@15:     folder_name = "../saves"    # Looks in 'saves/' folder from 'scripts/' folder
giuliomoro@15:     print("Use: python comment_parser.py [XML_files_location]")
giuliomoro@15:     print("Using default path: " + folder_name)
giuliomoro@15: elif len(sys.argv) == 2:
giuliomoro@15:     folder_name = sys.argv[1]   # First command line argument is folder
giuliomoro@15: 
giuliomoro@15: # check if folder_name exists
giuliomoro@15: if not os.path.exists(folder_name):
giuliomoro@15:     #the file is not there
giuliomoro@15:     print("Folder '"+folder_name+"' does not exist.")
giuliomoro@15:     sys.exit() # terminate script execution
giuliomoro@15: elif not os.access(os.path.dirname(folder_name), os.W_OK):
giuliomoro@15:     #the file does exist but write privileges are not given
giuliomoro@15:     print("No write privileges in folder '"+folder_name+"'.")
giuliomoro@15: 
giuliomoro@15: 
giuliomoro@15: # CODE
giuliomoro@15: 
giuliomoro@15: # remember which files have been opened this time
giuliomoro@15: file_history = []
giuliomoro@15: 
giuliomoro@15: # get every XML file in folder
giuliomoro@15: for file in os.listdir(folder_name): 
giuliomoro@15:     if file.endswith(".xml"):
giuliomoro@15:         tree = ET.parse(folder_name + '/' + file)
giuliomoro@15:         root = tree.getroot()
giuliomoro@15:         
giuliomoro@15:         # get list of all page names
giuliomoro@15:         for audioholder in root.findall("./page"):   # iterate over pages
giuliomoro@15:             page_name = audioholder.get('ref')               # get page name
giuliomoro@15:             
giuliomoro@15:             if page_name is None: # ignore 'empty' audio_holders
giuliomoro@15:                 print("WARNING: " + file + " contains empty page. (comment_parser.py)")
giuliomoro@15:                 break
giuliomoro@15:                 
giuliomoro@15:             if audioholder.get("state") != "complete":
giuliomoro@15:                 print("WARNING: " + file + "test page " + page_name + " is not complete, skipping.")
giuliomoro@15:             else:
giuliomoro@15:                 # create folder [page_name] if not yet created
giuliomoro@15:                 if not os.path.exists(folder_name + "/" + page_name):
giuliomoro@15:                     os.makedirs(folder_name + "/" + page_name)
giuliomoro@15: 
giuliomoro@15:                 # for page [page_name], print comments related to fragment [id]
giuliomoro@15:                 for audioelement in audioholder.findall("./audioelement"):
giuliomoro@15:                     if audioelement is not None: # Check it exists
giuliomoro@15:                         audio_id = str(audioelement.get('ref'))
giuliomoro@15: 
giuliomoro@15:                         csv_name = folder_name +'/' + page_name+'/'+page_name+'-comments-'+audio_id+'.csv'
giuliomoro@15: 
giuliomoro@15:                         # If file hasn't been opened yet this time, empty
giuliomoro@15:                         if csv_name not in file_history:
giuliomoro@15:                             csvfile = open(csv_name, 'w')
giuliomoro@15:                             file_history.append(csv_name) # remember this file has been written to this time around
giuliomoro@15:                         else: 
giuliomoro@15:                             # append (!) to file [page_name]/[page_name]-comments-[id].csv
giuliomoro@15:                             csvfile = open(csv_name, 'a')
giuliomoro@15:                         writer = csv.writer(csvfile, 
giuliomoro@15:                                             delimiter=',', 
giuliomoro@15:                                             dialect="excel",
giuliomoro@15:                                             quoting=csv.QUOTE_ALL)
giuliomoro@15:                         commentstr = audioelement.find("./comment/response").text
giuliomoro@15: 
giuliomoro@15:                         if commentstr is None:
giuliomoro@15:                            commentstr = ''
giuliomoro@15: 
giuliomoro@15:                         # anonymous comments:
giuliomoro@15:                         #writer.writerow([commentstr])  # .encode("utf-8")
giuliomoro@15:                         # comments with (file) name:
giuliomoro@15:                         writer.writerow([file[:-4]] + [commentstr]) 
giuliomoro@15: 
giuliomoro@15:                     #TODO Replace 'new line' in comment with something else?
giuliomoro@15:                         
giuliomoro@15: # PRO TIP: Change from csv to txt by running this in bash: 
giuliomoro@15: # $ cd folder_where_csvs_are/
giuliomoro@15: # $ for i in *.csv; do mv "$i" "${i/.csv}".txt; done