Add count_syllables to ch08

.travis.yml

@@ -6,7 +6,10 @@
 # https://travis-ci.com/JoseALermaIII
 dist: bionic  # required for Python >= 3.7
 language: python
-cache: pip  # Don't delete pip install
+cache:
+  pip: true  # Don't delete pip install
+  directories:
+    - $HOME/nltk_data/corpora/
 # Branch safelist
 branches:
   only:

docs/source/conf.py

@@ -55,6 +55,7 @@
 intersphinx_mapping = {
     'python': ('https://docs.python.org/3/', None),
     'docx': ('https://python-docx.readthedocs.io/en/latest/', None),
+    'nltk': ('http://www.nltk.org/', None),
 }
 
 # Default options for autodoc directives.

docs/source/src.ch08.rst

@@ -0,0 +1,22 @@
+src.ch08 package
+================
+
+Submodules
+----------
+
+src.ch08.p1\_count\_syllables module
+------------------------------------
+
+.. automodule:: src.ch08.p1_count_syllables
+   :members:
+   :undoc-members:
+   :show-inheritance:
+
+
+Module contents
+---------------
+
+.. automodule:: src.ch08
+   :members:
+   :undoc-members:
+   :show-inheritance:

docs/source/src.rst

@@ -13,6 +13,7 @@ Subpackages
    src.ch05
    src.ch06
    src.ch07
+   src.ch08
 
 Module contents
 ---------------

requirements.txt

@@ -1 +1,2 @@
-python-docx==0.8.10
+python-docx==0.8.10
+nltk==3.4.5

src/ch08/__init__.py

@@ -0,0 +1 @@
+"""Chapter 8."""

src/ch08/p1_count_syllables.py

@@ -0,0 +1,113 @@
+"""Test count_syllables with a word dictionary file.
+
+Randomly select words from a word dictionary file and pass them through
+:func:`count_syllables` to find their syllable counts. Output each word with
+their respective syllable count.
+
+Attributes:
+    CMUDICT (dict): Dictionary of CMUdict's phonemes with the word as a key
+        and its phonemes as a list of lists.
+    MISSING_WORDS (dict): Dictionary with syllable counts of words
+        missing from CMUdict's phoneme list where the word is the key and
+        its syllable count as an integer value.
+
+"""
+import json
+import os
+from random import sample
+from string import punctuation
+
+import nltk
+from nltk.corpus import cmudict
+
+from src.ch02 import DICTIONARY_FILE_PATH
+from src.ch02.p1_cleanup_dictionary import cleanup_dict
+
+if not os.path.exists(
+        os.path.expanduser('~/nltk_data/corpora/cmudict/cmudict')):
+    # pylint: disable=fixme
+    # FIXME: This is nearly impossible to test.
+    #  Patching os affects every use of os in the module.
+    nltk.download('cmudict')
+
+# Convert CMUdict into a dictionary.
+CMUDICT = cmudict.dict()
+
+with open(os.path.join(os.path.dirname(__file__),
+                       'p1files/missing_words.json')) as in_file:
+    # Load local dictionary of words with syllable counts.
+    # Words as strings are keys and integers are values.
+    MISSING_WORDS = json.load(in_file)
+
+
+def format_words(words: str) -> list:
+    """Format words for processing.
+
+    Remove hyphens, convert to lowercase, and strip both punctuation and
+    possessives from word or phrase.
+
+    Args:
+        words (str): Word or phrase to format for processing.
+
+    Returns:
+        List of strings containing processed words.
+
+    """
+    words = words.replace('-', ' ')
+    word_list = words.lower().split()
+    for i, word in enumerate(word_list):
+        word = word.strip(punctuation)
+        if any([word.endswith("'s"), word.endswith("’s")]):
+            word_list[i] = word[:-2]
+        else:
+            word_list[i] = word
+    return word_list
+
+
+def count_syllables(words: list) -> int:
+    """Use CMUdict to count syllables in English word.
+
+    Calculate sum of syllable counts for each word in **words**. Checks
+    syllable counts in the :py:mod:`nltk.corpus` CMUdict phoneme list, if word
+    is not found in CMUdict, also checks local dictionary with syllable
+    counts.
+
+    Args:
+        words (list): List of strings to sum number of syllables.
+
+    Returns:
+        Integer representing number of syllables in **words**.
+
+    Note:
+        Defaults to first element in CMUdict phoneme list. So, multiple
+        syllable counts are ignored.
+
+    """
+    syllables = 0
+    for word in words:
+        if word in MISSING_WORDS:
+            syllables += MISSING_WORDS[word]
+        else:
+            for phonemes in CMUDICT[word][0]:
+                for phoneme in phonemes:
+                    if phoneme[-1].isdigit():
+                        syllables += 1
+    return syllables
+
+
+def main():
+    """Demonstrate count_syllables with a word dictionary file."""
+    word_list = cleanup_dict(DICTIONARY_FILE_PATH)
+    sample_list = sample(word_list, 15)
+    for word in sample_list:
+        try:
+            syllables = count_syllables(format_words(word))
+        except KeyError:
+            # Skip words in neither dictionary.
+            print(f'Not found: {word}')
+            continue
+        print(f'{word} {syllables}')
+
+
+if __name__ == '__main__':
+    main()

src/ch08/p1files/missing_words.json

@@ -0,0 +1 @@
+{"househusband":  3, "ibices":  3, "smooching": 2, "handpicking": 3, "tuxes":  2}

tests/data/ch08/dictionary.txt

@@ -0,0 +1,78 @@
+a
+aardvark
+abracadabra
+b
+bee
+boson
+c
+cat
+catatonic
+d
+dog
+dirge
+e
+echo
+ebeneezer
+f
+fox
+finicky
+g
+gecko
+gopher
+h
+hemoglobin
+hermit
+i
+imp
+indigo
+j
+jack-o-lantern
+journey
+k
+kangaroo
+kilometer
+l
+lemon
+lime
+m
+mesolithic
+moonlight
+n
+none
+night
+o
+opaque
+opulent
+p
+penny
+pepper
+q
+quasar
+quark
+r
+riddle
+rubber
+s
+slight
+swift
+t
+tonberry
+tomato
+u
+ultraviolet
+umbra
+v
+venus
+vertiginous
+w
+whip
+whirl
+x
+xena
+xenon
+y
+yacht
+yggdrasil
+z
+zen
+zero

tests/data/ch08/main/count_syllables.txt

@@ -0,0 +1,15 @@
+Not found: yggdrasil
+dog 1
+hermit 2
+jack-o-lantern 4
+journey 2
+bee 1
+abracadabra 5
+penny 2
+hemoglobin 4
+opaque 2
+venus 2
+umbra 2
+cat 1
+whirl 1
+zen 1

tests/test_chapter08.py

@@ -0,0 +1,58 @@
+"""Test Chapter 8."""
+import unittest.mock
+import os
+from random import Random
+from io import StringIO
+
+import src.ch08.p1_count_syllables as count_syllables
+
+
+class TestCountSyllables(unittest.TestCase):
+    """Test Count Syllables."""
+
+    @classmethod
+    def setUpClass(cls):
+        """Configure attributes for use in this class only."""
+        cls.random = Random()
+
+    def test_format_words(self):
+        """Test format_words."""
+        # Test convert to lowercase.
+        for word in ['YOU', 'You', 'yOu', 'yoU', 'yOU', 'YOu', 'YoU', 'you']:
+            self.assertEqual(count_syllables.format_words(word), ['you'])
+        # Test remove hyphens.
+        self.assertEqual(count_syllables.format_words('nit-pick'), ['nit', 'pick'])
+        # Test remove punctuation.
+        self.assertEqual(count_syllables.format_words('nit-pick!'), ['nit', 'pick'])
+        # Test remove possessives.
+        for word in ['test’s', 'test\'s']:
+            self.assertEqual(count_syllables.format_words(word), ['test'])
+        # Test phrase.
+        self.assertEqual(count_syllables.format_words('TEST nit-pick'), ['test', 'nit', 'pick'])
+
+    def test_count_syllables(self):
+        """Test count_syllables."""
+        # Test word not in CMUdict.
+        self.assertEqual(count_syllables.count_syllables(['tuxes']), 2)
+        # Test word in CMUdict.
+        self.assertEqual(count_syllables.count_syllables(['test']), 1)
+
+    @unittest.mock.patch('src.ch08.p1_count_syllables.DICTIONARY_FILE_PATH', 'tests/data/ch08/dictionary.txt')
+    @unittest.mock.patch('sys.stdout', new_callable=StringIO)
+    @unittest.mock.patch('src.ch08.p1_count_syllables.sample')
+    def test_main(self, mock_sample, mock_stdout):
+        """Test demo main function."""
+        self.random.seed(222)
+        mock_sample.side_effect = self.random.sample
+
+        count_syllables.main()
+
+        # Test sys.stdout output.
+        with open(os.path.normpath('tests/data/ch08/main/count_syllables.txt'),
+                  'r') as file:
+            file_data = ''.join(file.readlines())
+        self.assertEqual(mock_stdout.getvalue(), file_data)
+
+
+if __name__ == '__main__':
+    unittest.main()

tox.ini

@@ -6,7 +6,7 @@
 [tox]
 envlist = py36, py37, lint, pydocstyle, sphinx
 skip_missing_interpreters = True
-skipsdist=True
+skipsdist = True
 
 [testenv]
 deps =