diff options
author | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2012-11-05 15:29:46 +0100 |
---|---|---|
committer | Patrick Simianer <simianer@cl.uni-heidelberg.de> | 2012-11-05 15:29:46 +0100 |
commit | 6f29f345dc06c1a1033475eac1d1340781d1d603 (patch) | |
tree | 6fa4cdd7aefd7d54c9585c2c6274db61bb8b159a /gi/morf-segmentation/morfsegment.py | |
parent | b510da2e562c695c90d565eb295c749569c59be8 (diff) | |
parent | c615c37501fa8576584a510a9d2bfe2fdd5bace7 (diff) |
merge upstream/master
Diffstat (limited to 'gi/morf-segmentation/morfsegment.py')
-rwxr-xr-x | gi/morf-segmentation/morfsegment.py | 50 |
1 files changed, 0 insertions, 50 deletions
diff --git a/gi/morf-segmentation/morfsegment.py b/gi/morf-segmentation/morfsegment.py deleted file mode 100755 index 85b9d4fb..00000000 --- a/gi/morf-segmentation/morfsegment.py +++ /dev/null @@ -1,50 +0,0 @@ -#!/usr/bin/python - -import sys -import gzip - -#usage: morfsegment.py inputvocab.gz segmentation.ready -# stdin: the data to segment -# stdout: the segmented data - -if len(sys.argv) < 3: - print "usage: morfsegment.py inputvocab.gz segmentation.ready [marker]" - print " stdin: the data to segment" - print " stdout: the segmented data" - sys.exit() - -#read index: -split_index={} - -marker="##" - -if len(sys.argv) > 3: - marker=sys.argv[3] - -word_vocab=gzip.open(sys.argv[1], 'rb') #inputvocab.gz -seg_vocab=open(sys.argv[2], 'r') #segm.ready.. - -for seg in seg_vocab: - #seg = ver# #wonder\n - #wordline = 1 verwonder\n - word = word_vocab.readline().strip().split(' ') - assert(len(word) == 2) - word = word[1] - seg=seg.strip() - - if seg != word: - split_index[word] = seg - -word_vocab.close() -seg_vocab.close() - -for line in sys.stdin: - words = line.strip().split() - - newsent = [] - for word in words: - splitword = split_index.get(word, word) - newsent.append(splitword) - - print ' '.join(newsent) - |