#String Operators

#Let's do a substring
fullname = 'David Lucus'

#string slicing
#Let's just grab the first 5 letters
fname = fullname[:5]
print(fname)

#Let's grab the last 5 characters
lname = fullname[6:]
print(lname)

#Let's grab the middle 5 characters
randomtext = fullname[3:7]
print(randomtext)

#Bad fullname
fullnameBad = 'David Lucus '

#Let's split on spaces
#split removes the character you are searching for and makes an
#array item for each step that is found.  example, let's split on a
#space in the variable fullnameBad
#Note, this is frankly, one of hte most useful string functions available.  Example,
#if you wanted to parse out a text document to be word by word in an array for analysis,
#in this case, just split on the spaces, or by the periods to get by sentence, or by the
#\n for paragraphs, etc.
arr = fullnameBad.split(' ')
print(len(arr))
ssn = '555-05-5332'
ssnarr = ssn.split('-')
#Note the built in function list in the slides.
#here we use strip to remove all leading and trailing spaces
#I use concatenation, so you can see the trailing space is gone.
print('Unstripped:  ' + '|' + fullnameBad + '|')
print('Stripped:  ' + '|' + fullnameBad.strip() + '|')


#Final sentence example
#Note, in a real example, we would parse out all other markers like commas
#unless we are trying to deal at the phrase level.
paragraph = 'Hello, my name is bob.  I like dogs.'

#Let's get a list of sentences:
sentences = paragraph.split('.')
#let's iterate over the sentences:
for s in sentences:
    print(s)

#What if we wanted to iterate over words, then we need a split inside the loop that we iterate on
for s in sentences:
    words = s.split(' ')
    for w in words:
        #you could test w if it was positive ('like, love, etc') or negative ('dislike, hate, etc')
        print(w)