diff options
| author | Peng Wu <alexepico@gmail.com> | 2013-10-09 16:20:32 +0800 |
|---|---|---|
| committer | Peng Wu <alexepico@gmail.com> | 2013-10-09 16:22:13 +0800 |
| commit | 14cb5e3da9b4b498f0afca3e016c54dd01d446ef (patch) | |
| tree | f81e9b2175bae481bd6f987bcbc2c220a0d2181b | |
| parent | 76887bf63a219ca1f82098e139139f13c7751ab3 (diff) | |
| download | trainer-14cb5e3da9b4b498f0afca3e016c54dd01d446ef.tar.gz trainer-14cb5e3da9b4b498f0afca3e016c54dd01d446ef.tar.xz trainer-14cb5e3da9b4b498f0afca3e016c54dd01d446ef.zip | |
add comments
| -rwxr-xr-x | partialword.py | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/partialword.py b/partialword.py index f67ac97..61c8e7d 100755 --- a/partialword.py +++ b/partialword.py @@ -216,6 +216,9 @@ def doCombineWord(high_cur, low_cur, words): words_str = sep + prefix + sep + postfix + sep #print(words_str) + #if the to-be-merged sequence has several matched pairs, + # then several sequences will be added to lower-gram. + #TODO: maybe consider equally divide the matched_freq. for item in matched_items: (matched_words_str, matched_freq) = item assert words_str in matched_words_str |