875a33806acea37f602d0ad20fb77cd42432bbb6,scripts/tokenize/tokenize_pad.py,,,#,6

Before Change

rcParams["debug"]=True

wl = Wordlist("pad_data_qlc.qlc")
wl.tokenize("pad_orthography_profile")
wl.output("qlc", filename="tokenized-pad_data")

After Change

print()
print("ID"+"\t"+"ORIGINAL"+"\t"+"RULES")
for line in infile:
    line = line.strip()
    tokens = line.split("\t")
    id = tokens[0]
    counterpart = tokens[2]
    grapheme_clusters =t.grapheme_clusters(counterpart)
    rules = t.rules(grapheme_clusters)
    print(id+"\t"+counterpart+"\t"+rules)



// this tokenize does not work because of the way the orthography rules are currently written, i.e. 
// they expect space delimited tokens; the wordlist.tokenize() function first apples the rules
// and the the Unicode grapheme cluster tokenization

Instances