experiments
/
STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Character checking: be more verbose if something fails 

This way one can easily debug what file causes problems
This commit is contained in:
Jan Engelmohr 2018-12-03 12:08:19 +01:00
parent de279168ec
commit 18ef670b05
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
util/check_characters.py
View File

@ -29,14 +29,18 @@ else:
print("### Reading in the following transcript files: ###") print("### Reading in the following transcript files: ###")
print(inFiles) print(inFiles)
allText = set() allText = set()
for inFile in (inFiles): for inFile in (inFiles):
with open(inFile, 'r') as csvFile: with open(inFile, 'r') as csvFile:
reader = csv.reader(csvFile) reader = csv.reader(csvFile)
for row in reader: try:
allText |= set(str(row[2])) for row in reader:
csvFile.close() allText |= set(str(row[2]))
except IndexError as ie:
print("Your input file",inFile,"is not formatted properly. Check if there are 3 columns with the 3rd containing the transcript")
sys.exit(-1)
finally:
csvFile.close()
print("### The following unique characters were found in your transcripts: ###") print("### The following unique characters were found in your transcripts: ###")
print(list(allText)) print(list(allText))