updated from Atlas

03-dict-set/index_default.py

@@ -0,0 +1,26 @@
+# 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
+
+# BEGIN INDEX_DEFAULT
+"""Build an index mapping word -> list of occurrences"""
+
+import sys
+import re
+import collections
+
+WORD_RE = re.compile('\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>
+
+# print in alphabetical order
+for word in sorted(index, key=str.upper):
+    print(word, index[word])
+# END INDEX_DEFAULT