annotate scripts/comment_parser.py @ 294:df7263170715 Dev_main

Bug #1370: Fragments marked as outside reference are no longer checked for movement parameters in APE.
author Nicholas Jillings <n.g.r.jillings@se14.qmul.ac.uk>
date Thu, 10 Sep 2015 12:32:56 +0100
parents 3c5689af726b
children f32e58635091
rev   line source
b@230 1 #!/usr/bin/python
b@241 2 # -*- coding: utf-8 -*-
b@230 3
b@146 4 import xml.etree.ElementTree as ET
b@146 5 import os
b@146 6 import csv
b@146 7
b@245 8 # XML results files location (modify as needed):
b@245 9 folder_name = "../saves" # Looks in 'saves/' folder from 'scripts/' folder
b@245 10
b@146 11 # get every XML file in folder
b@245 12 for file in os.listdir(folder_name):
b@146 13 if file.endswith(".xml"):
b@245 14 tree = ET.parse(folder_name + '/' + file)
b@146 15 root = tree.getroot()
b@251 16
b@147 17 # get list of all page names
b@147 18 for audioholder in root.findall("./audioholder"): # iterate over pages
b@147 19 page_name = audioholder.get('id') # get page name
b@206 20
b@206 21 if page_name is None: # ignore 'empty' audio_holders
b@251 22 print "WARNING: " + file + " contains empty audio holder. (comment_parser.py)"
b@206 23 break
b@146 24
b@147 25 # create folder [page_name] if not yet created
b@245 26 if not os.path.exists(folder_name + "/" + page_name):
b@245 27 os.makedirs(folder_name + "/" + page_name)
b@146 28
b@147 29 # for page [page_name], print comments related to fragment [id]
b@245 30 for audioelement in audioholder.findall("./audioelement"):
b@206 31 if audioelement is not None: # Check it exists
b@206 32 audio_id = str(audioelement.get('id'))
b@230 33
b@245 34 csv_name = folder_name +'/' + page_name+'/'+page_name+'-comments-'+audio_id+'.csv'
b@146 35
b@230 36 # append (!) to file [page_name]/[page_name]-comments-[id].csv
b@230 37 with open(csv_name, 'a') as csvfile:
b@230 38 writer = csv.writer(csvfile,
b@230 39 delimiter=',',
b@230 40 dialect="excel",
b@230 41 quoting=csv.QUOTE_ALL)
b@245 42 commentstr = audioelement.find("./comment/response").text
b@245 43
b@206 44 if commentstr is None:
b@245 45 commentstr = '';
b@245 46
b@245 47 # anonymous comments:
b@245 48 #writer.writerow([commentstr.encode("utf-8")])
b@245 49 # comments with (file) name:
b@245 50 writer.writerow([file[:-4]] + [commentstr.encode("utf-8")])
b@146 51
b@230 52 #TODO Replace 'new line' in comment with something else?
b@230 53
b@230 54 # PRO TIP: Change from csv to txt by running this in bash:
b@230 55 # $ cd folder_where_csvs_are/
b@230 56 # $ for i in *.csv; do mv "$i" "${i/.csv}".txt; done