3-2 从单词中获取单词出现的频率信息，并把他们写进对应的列表里

 1 import sys
 2 import re
 3 
 4 WORD_RE = re.compile(r‘\w+‘)
 5 
 6 index = {}
 7 
 8 with open(sys.argv[1], encoding=‘utf-8‘) as fp:
 9     for line_no, line in enumerate(fp, 1):
10         for match in WORD_RE.finditer(line):
11             word = match.group()
12             column_no = match.start() + 1
13             location = (line_no, column_no)
14             occurrences = index.get(word, [])
15             occurrences.append(location)
16             index[word] = occurrences
17 
18 for word in sorted(index, key=str.upper):
19     print(word, index[word])

1 # 在index0.py下创建一个aa.txt文件，存入单词
2 F:\python_interface_test\python_interface_test\prepare_data>python index0.py aa.txt
3 16 [(14, 19)]
4 2006 [(11, 93)]
5 21 [(1, 51)]
6 21st [(8, 29)]
7 27 [(1, 41)]
8 a [(2, 60), (5, 30), (6, 73)]
9 against [(4, 61)]

 1 import sys
 2 import re
 3 
 4 WORD_RE = re.compile(r‘\w+‘)
 5 
 6 index = {}
 7 
 8 with open(sys.argv[1], encoding=‘utf-8‘) as fp:
 9     for line_no, line in enumerate(fp, 1):
10         for match in WORD_RE.finditer(line):
11             word = match.group()
12             column_no = match.start() + 1
13             location = (line_no, column_no)
14             
15             index.setdefault(word, []).append(location )
16 
17 for word in sorted(index, key=str.upper):
18     print(word, index[word])