Adding homophone.py

AllenDowney · AllenDowney · commit fe91fc43b562 · 2015-11-09T11:24:51.000-05:00
diff --git a/code/homophone.py b/code/homophone.py
@@ -0,0 +1,74 @@
+"""This module contains a code example related to
+
+Think Python, 2nd Edition
+by Allen Downey
+http://thinkpython2.com
+
+Copyright 2015 Allen Downey
+
+License: http://creativecommons.org/licenses/by/4.0/
+"""
+
+from __future__ import print_function, division
+
+from pronounce import read_dictionary
+
+
+def make_word_dict():
+    """Read. the words in words.txt and return a dictionary
+    that contains the words as keys."""
+    d = dict()
+    fin = open('words.txt')
+    for line in fin:
+        word = line.strip().lower()
+        d[word] = word
+
+    return d
+
+
+def homophones(a, b, phonetic):
+    """Checks if words two can be pronounced the same way.
+
+    If either word is not in the pronouncing dictionary, return False
+
+    a, b: strings
+    phonetic: map from words to pronunciation codes
+    """
+    if a not in phonetic or b not in phonetic:
+        return False
+
+    return phonetic[a] == phonetic[b]
+
+
+def check_word(word, word_dict, phonetic):
+    """Checks to see if the word has the following property:
+    removing the first letter yields a word with the same
+    pronunciation, and removing the second letter yields a word
+    with the same pronunciation.
+
+    word: string
+    word_dict: dictionary with words as keys
+    phonetic: map from words to pronunciation codes
+    """
+    word1 = word[1:] 
+    if word1 not in word_dict:
+        return False
+    if not homophones(word, word1, phonetic):
+        return False
+
+    word2 = word[0] + word[2:]
+    if word2 not in word_dict:
+        return False
+    if not homophones(word, word2, phonetic):
+        return False
+
+    return True
+
+
+if __name__ == '__main__':
+    phonetic = read_dictionary()
+    word_dict = make_word_dict()
+
+    for word in word_dict:
+        if check_word(word, word_dict, phonetic):
+            print(word, word[1:], word[0] + word[2:])
diff --git a/code/invert_dict.py b/code/invert_dict.py
@@ -23,14 +23,16 @@ def invert_dict(d):
     Returns: dict
     """
     inverse = {}
-    for key, val in d.items():
+    for key in d:
+        val = d[key]
         inverse.setdefault(val, []).append(key)
     return inverse
 
 
 if __name__ == '__main__':
     d = dict(a=1, b=2, c=3, z=1)
     inverse = invert_dict(d)
-    for val, keys in inverse.items():
+    for val in inverse:
+        keys = inverse[val]
         print(val, keys)
 
diff --git a/code/pronounce.py b/code/pronounce.py
@@ -0,0 +1,44 @@
+"""This module contains a code example related to
+
+Think Python, 2nd Edition
+by Allen Downey
+http://thinkpython2.com
+
+Copyright 2015 Allen Downey
+
+License: http://creativecommons.org/licenses/by/4.0/
+"""
+
+from __future__ import print_function, division
+
+
+def read_dictionary(filename='c06d'):
+    """Reads from a file and builds a dictionary that maps from
+    each word to a string that describes its primary pronunciation.
+
+    Secondary pronunciations are added to the dictionary with
+    a number, in parentheses, at the end of the key, so the
+    key for the second pronunciation of "abdominal" is "abdominal(2)".
+
+    filename: string
+    returns: map from string to pronunciation
+    """
+    d = dict()
+    fin = open(filename)
+    for line in fin:
+
+        # skip over the comments
+        if line[0] == '#': continue
+
+        t = line.split()
+        word = t[0].lower()
+        pron = ' '.join(t[1:])
+        d[word] = pron
+
+    return d
+
+
+if __name__ == '__main__':
+    d = read_dictionary()
+    for k, v in d.items():
+        print(k, v)
