diff options
| author | Martin Czygan <martin.czygan@gmail.com> | 2020-11-07 00:53:03 +0100 |
|---|---|---|
| committer | Martin Czygan <martin.czygan@gmail.com> | 2020-11-07 00:53:03 +0100 |
| commit | 3963772ae9401395eb17fca16de9a27fe7bf6681 (patch) | |
| tree | b1866529839f72c632c7085ee51bfc22f9691370 | |
| parent | e5c8e80fa246899fe95008fe7b599b6efe0e686e (diff) | |
| download | fuzzycat-3963772ae9401395eb17fca16de9a27fe7bf6681.tar.gz fuzzycat-3963772ae9401395eb17fca16de9a27fe7bf6681.zip | |
emit title slug
| -rw-r--r-- | fuzzycat/build.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/fuzzycat/build.py b/fuzzycat/build.py index a37453d..ee128c8 100644 --- a/fuzzycat/build.py +++ b/fuzzycat/build.py @@ -99,6 +99,6 @@ class NgramLookup: tokens = [tok for tok in word_tokenize(title.lower()) if tok not in self.stopwords] prefix = "-".join(tokens[:self.n]) suffix = "-".join(tokens[-self.n:]) - print("{}\t{}\t{}".format(id, prefix, suffix)) + print("{}\t{}\t{}\t{}-{}".format(id, prefix, suffix, prefix, suffix)) except KeyError as exc: print("skipping doc w/o title: {} - {}".format(line, exc), file=sys.stderr) |