def test_suite(): #Few tests of "add_vectors" function
test(wdt.cleanword("what?") == "what")
test(wdt.cleanword("'now!'") == "now")
test(wdt.cleanword("?+='w-o-r-d!,@$()'") == "word")
test(wdt.has_dashdash("distance--but"))
test(not wdt.has_dashdash("several"))
test(wdt.has_dashdash("spoke--"))
test(wdt.has_dashdash("distance--but"))
test(not wdt.has_dashdash("-yo-yo-"))
test(wdt.extract_words("Now is the time! 'Now', is the time? Yes, now.") == ['now','is','the','time','now','is','the','time','yes','now'])
test(wdt.extract_words("she tried to curtsey as she spoke--fancy") == ['she','tried','to','curtsey','as','she','spoke','fancy'])
test(wdt.wordcount("now", ["now","is","time","is","now","is","is"]) == 2)
test(wdt.wordcount("is", ["now","is","time","is","now","the","is"]) == 3)
test(wdt.wordcount("time", ["now","is","time","is","now","is","is"]) == 1)
test(wdt.wordcount("frog", ["now","is","time","is","now","is","is"]) == 0)
test(wdt.wordset(["now", "is", "time", "is", "now", "is", "is"]) == ["is", "now", "time"])
test(wdt.wordset(["I", "a", "a", "is", "a", "is", "I", "am"]) == ["I", "a", "am", "is"])
test(wdt.wordset(["or", "a", "am", "is", "are", "be", "but", "am"]) == ["a", "am", "are", "be", "but", "is", "or"])
test(wdt.longestword(["a", "apple", "pear", "grape"]) == 5)
test(wdt.longestword(["a", "am", "I", "be"]) == 2)
test(wdt.longestword(["this","supercalifragilisticexpialidocious"]) == 34)
test(wdt.longestword([ ]) == 0)
wordtools.test(wordtools.has_dashdash("distance--but"), 1)
print("test(not has_dashdash(\"several\")")
wordtools.test(wordtools.has_dashdash("spoke--"), 1)
print("test(has_dashdash(\"distance--but\")")
wordtools.test(wordtools.has_dashdash("distance--but"), 1)
print("test(not has_dashdash(\"-yo-yo-\")")
wordtools.test(wordtools.has_dashdash("-yo-yo-"), 0)
print(
"test(extract_words(\"Now is the time! 'Now', is the time? Yes, now.\") == \['now','is','the','time','now','is','the','time','yes','now'\]"
)
wordtools.test(
wordtools.extract_words("Now is the time! 'Now', is the time? Yes, now."),
['now', 'is', 'the', 'time', 'now', 'is', 'the', 'time', 'yes', 'now'])
print(
"test(extract_words(\"she tried to curtsey as she spoke--fancy\") == \['she','tried','to','curtsey','as','she','spoke','fancy'\]"
)
wordtools.test(
wordtools.extract_words("she tried to curtsey as she spoke--fancy"),
['she', 'tried', 'to', 'curtsey', 'as', 'she', 'spoke', 'fancy'])
print(
"test(wordcount(\"now\", [\"now\",\"is\",\"time\",\"is\",\"now\",\"is\",\"is\"]) == 2)"
)
a = wordtools.wordcount("now", ["now", "is", "time", "is", "now", "is", "is"])
wordtools.test(2, 2)
print('clean word:')
test(cleanword("what?") == "what")
test(cleanword("'now!'") == "now")
test(cleanword("?+='w-o-r-d!,@$()'") == "word")
print()
print('has dash dash:')
test(has_dashdash("distance--but"))
test(not has_dashdash("several"))
test(has_dashdash("spoke--"))
test(has_dashdash("distance--but"))
test(not has_dashdash("-yo-yo-"))
print()
print('extract words:')
test(extract_words("Now is the time! 'Now', is the time? Yes, now.") ==\
['now','is','the','time','now','is','the','time','yes','now'])
test(extract_words("she tried to curtsey as she spoke--fancy") ==\
['she','tried','to','curtsey','as','she','spoke','fancy'])
print()
print('wordcount:')
test(wordcount("now", ["now", "is", "time", "is", "now", "is", "is"]) == 2)
test(wordcount("is", ["now", "is", "time", "is", "now", "the", "is"]) == 3)
test(wordcount("time", ["now", "is", "time", "is", "now", "is", "is"]) == 1)
test(wordcount("frog", ["now", "is", "time", "is", "now", "is", "is"]) == 0)
print()
print('wordset:')
test(wordset(["now", "is", "time", "is", "now", "is","is"]) ==\
["is", "now", "time"])
# exercise 20.3
import urllib.request
import wordtools
def retrieve_page(url):
my_socket = urllib.request.urlopen(url)
dta = str(my_socket.read())
my_socket.close()
return dta
alice_book = retrieve_page("http://www.gutenberg.org/cache/epub/11/pg11.txt")
alice_book = alice_book[801:158020]
rn_removed = ' '.join(alice_book.split("\\r\\n"))
words = wordtools.extract_words(rn_removed)
word_occurences = {}
for word in words:
if not word == "":
word_occurences[word] = word_occurences.get(word, 0) + 1
alice_words = open("alice_words.txt", "w")
alice_words.write("Word\t\t\tCount\n")
alice_words.write("==============================\n")
for (u, v) in sorted(word_occurences.items()):
alice_words.write("{0:25}{1}\n".format(u, v))
print("The word 'alice' occurs {0} times in the book.".format(word_occurences["alice"]))
import wordtools
def retrieve_page(url):
""" Retrieve the contents of a web page.
The contents is converted to a string before returning it.
"""
my_socket = urllib.request.urlopen(url)
dta = str(my_socket.read())
my_socket.close()
return dta
#get text from a internet site
the_text = retrieve_page(
"http://www.gutenberg.org/cache/epub/28885/pg28885.txt")
output_file = open("alice_words.txt", "w")
#prepare the output file
output_file.writelines(
["Word Count\n", "=======================\n"])
#count every word
db_word = {}
for word in wordtools.extract_words(the_text):
db_word[word] = db_word.get(word, 0) + 1
for word in sorted(db_word):
output_file.write("{0:<18}{1}\n".format(word, db_word[word]))
output_file.close()