1. 单词搜索
#在给定的文献列表里,找含有关键字的索引下标,并返回列表
def word_search(doc_list, keyword):
indices = [] #store the result
# Iterate through the indices (i) and elements (doc) of documents
for i, doc in enumerate(doc_list):
# Split the string doc into a list of words (according to whitespace)
tokens = doc.split()
# Make a transformed list where we 'normalize' each word to facilitate matching.
# Periods and commas are removed from the end of each word, and it's set to all lowercase.
normalized = [token.rstrip('.,').lower() for token in tokens]
# Is there a match? If so, update the list of matching indices.
if keyword.lower() in normalized:
indices.append(i)
return indices