syllablecount.py

import re
from nltk.corpus import cmudict
d = cmudict.dict()

VOWEL_RUNS = re.compile("[aeiouy]+", flags=re.I)
EXCEPTIONS = re.compile(
    # fixes trailing e issues:
    # smite, scared
    "[^aeiou]e[sd]?$|"
    # fixes adverbs:
    # nicely
    + "[^e]ely$",
    flags=re.I
)
ADDITIONAL = re.compile(
    # fixes incorrect subtractions from exceptions:
    # smile, scarred, raises, fated
    "[^aeioulr][lr]e[sd]?$|[csgz]es$|[td]ed$|"
    # fixes miscellaneous issues:
    # flying, piano, video, prism, fire, evaluate
    + ".y[aeiou]|ia(?!n$)|eo|ism$|[^aeiou]ire$|[^gq]ua",
    flags=re.I
)


def count_syllables(word):
    try:
        # assume first pronunciation
        return [len(list(y for y in x if y[-1].isdigit())) for x in d[word.lower()]][0]
    except KeyError:
        # if word not found in cmudict
        return weak_count_syllables(word)


def weak_count_syllables(word):
    vowel_runs = len(VOWEL_RUNS.findall(word))
    exceptions = len(EXCEPTIONS.findall(word))
    additional = len(ADDITIONAL.findall(word))
    return max(1, vowel_runs - exceptions + additional)