example-code-2e/03-dict-set/index_default.py

# adapted from Alex Martelli's example in "Re-learning Python"
# http://www.aleax.it/Python/accu04_Relearn_Python_alex.pdf
# (slide 41) Ex: lines-by-word file index

# tag::INDEX_DEFAULT[]
"""Build an index mapping word -> list of occurrences"""

import collections
import re
import sys

WORD_RE = re.compile(r'\w+')

index = collections.defaultdict(list)     # <1>
with open(sys.argv[1], encoding='utf-8') as fp:
    for line_no, line in enumerate(fp, 1):
        for match in WORD_RE.finditer(line):
            word = match.group()
            column_no = match.start() + 1
            location = (line_no, column_no)
            index[word].append(location)  # <2>

# display in alphabetical order
for word in sorted(index, key=str.upper):
    print(word, index[word])
# end::INDEX_DEFAULT[]