view scripts/comment_parser.py @ 1116:c44fbf72f7f2

All interfaces support comment boxes. Comment box identification matches presented tag (for instance, AB will be Comment on fragment A, rather than 1). Tighter buffer loading protocol, audioObjects register with the buffer rather than checking for buffer existence (which can be buggy depending on the buffer state). Buffers now have a state to ensure exact location in loading chain (downloading, decoding, LUFS, ready).
author Nicholas Jillings <n.g.r.jillings@se14.qmul.ac.uk>
date Fri, 29 Jan 2016 11:11:57 +0000
parents
children 1b6fa37d46a4 235594325b84 b5bf2f57187c
line wrap: on
line source
#!/usr/bin/python
# -*- coding: utf-8 -*-

import xml.etree.ElementTree as ET
import os
import csv
import sys

# 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): 
    if file.endswith(".xml"):
        tree = ET.parse(folder_name + '/' + file)
        root = tree.getroot()
        
        # get list of all page names
        for audioholder in root.findall("./audioholder"):   # iterate over pages
            page_name = audioholder.get('id')               # get page name
            
            if page_name is None: # ignore 'empty' audio_holders
                print "WARNING: " + file + " contains empty audio holder. (comment_parser.py)"
                break

            # create folder [page_name] if not yet created
            if not os.path.exists(folder_name + "/" + page_name):
                os.makedirs(folder_name + "/" + page_name)

            # for page [page_name], print comments related to fragment [id]
            for audioelement in audioholder.findall("./audioelement"):
                if audioelement is not None: # Check it exists
                    audio_id = str(audioelement.get('id'))
                    
                    csv_name = folder_name +'/' + page_name+'/'+page_name+'-comments-'+audio_id+'.csv'

                    # 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")]) 

                    #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/
# $ for i in *.csv; do mv "$i" "${i/.csv}".txt; done