diff options
author | Yoshiki Shibukawa <yoshiki@shibu.jp> | 2013-10-11 07:37:00 -0700 |
---|---|---|
committer | Yoshiki Shibukawa <yoshiki@shibu.jp> | 2013-10-11 07:37:00 -0700 |
commit | c697d308906ea526cb56778b3856ad908b958d94 (patch) | |
tree | 83ce3d5449fdd44b0fb7181fda07f93e889807b8 /sample/testapp.py | |
parent | eebe65816ad97fa561c9c10b8a337138fb7cf9a3 (diff) | |
parent | afa6d43a23ea7c7781b9faf23cf0adebaeaeef58 (diff) | |
download | snowballstemmer-c697d308906ea526cb56778b3856ad908b958d94.tar.gz |
Merge pull request #1 from wallunit/master
Fixed typo in function call to _clear_cache().
Diffstat (limited to 'sample/testapp.py')
-rw-r--r-- | sample/testapp.py | 28 |
1 files changed, 28 insertions, 0 deletions
diff --git a/sample/testapp.py b/sample/testapp.py new file mode 100644 index 0000000..1566134 --- /dev/null +++ b/sample/testapp.py @@ -0,0 +1,28 @@ +import sys +import re +import snowballstemmer + + +def usage(): + print("testapp.py <algorithm> \"sentence\"...") + +def main(): + argv = sys.argv + if len(argv) < 1: + usage() + return + algorithm = 'english' + if len(argv) > 2: + algorithm = argv[1] + argv = argv[2:] + else: + argv = argv[1:] + stemmer = snowballstemmer.stemmer(algorithm) + splitter = re.compile(r"[\s\.-]") + for arg in argv: + for word in splitter.split(arg): + if word == '': + continue + original = word.lower() + print(original + " -> " + stemmer.stemWord(original)) +main() |