from nltk_lite import tag, chunk

sent = chunk.tagstr2tree("the/DT little/JJ cat/NN sat/VBD on/IN the/DT mat/NN in/IN New/NNP York/NNP")

print sent

rule1 = chunk.ChunkRule('<DT><JJ>*<NN>', 'Chunk sequences of DT, JJ and NN')
chunkparser = chunk.RegexpChunk([rule1], chunk_node='NP', top_node='S')

chunk_tree = chunkparser.parse(sent, trace=1)
print chunk_tree


rule2 = chunk.ChunkRule('<NNP>+', "Chunk proper nouns")
chunkparser = chunk.RegexpChunk([rule1, rule2], chunk_node='NP', top_node='S')

chunk_tree = chunkparser.parse(sent, trace=1)
print chunk_tree

chunk_tree.draw()

chunkall_rule = chunk.ChunkRule('<.*>+', 'Chunk everything')
remove_rule = chunk.ChinkRule('<VBD|IN>+', 'Remove sequences of VBD and IN')

chunkparser = chunk.RegexpChunk([chunkall_rule, remove_rule], chunk_node='NP', top_node='S')


chunk_tree = chunkparser.parse(sent, trace=1)
print chunk_tree

chink_rule = chunk.ChinkRule('<NN|DT>+',
                           'Chink sequences of NN and DT')
chunk_rule = chunk.ChunkRule('<NN|DT|JJ>+',
                       'Chunk sequences of NN, JJ, and DT')
chunkparser = chunk.RegexpChunk([chunk_rule, chink_rule],
                chunk_node='NP', top_node='S')
chunk_tree = chunkparser.parse(sent, trace=1)

print chunk_tree