Initial commit

{\rtf1\ansi\ansicpg1252\cocoartf1038\cocoasubrtf350

{\fonttbl\f0\fswiss\fcharset0 Helvetica;}

{\colortbl;\red255\green255\blue255;}

\margl1440\margr1440\vieww9000\viewh8400\viewkind0

\pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\ql\qnatural\pardirnatural

\f0\fs24 \cf0 No work files for this lesson...}

 No newline at end of file

{\rtf1\ansi\ansicpg1252\cocoartf1038\cocoasubrtf350

{\fonttbl\f0\fswiss\fcharset0 Helvetica;}

{\colortbl;\red255\green255\blue255;}

\margl1440\margr1440\vieww9000\viewh8400\viewkind0

\pard\tx720\tx1440\tx2160\tx2880\tx3600\tx4320\tx5040\tx5760\tx6480\tx7200\tx7920\tx8640\ql\qnatural\pardirnatural

\f0\fs24 \cf0 No work files for this lesson...}

 No newline at end of file

%% Cell type:code id: tags:

``` python

# -*- coding: utf-8 -*-

# In Python 2 you often need the line above at the top of your file

# so you can see Unicode characters

```

%% Cell type:code id: tags:

``` python

a = 'niño'

print(a)

```

%% Output

    niño

%% Cell type:code id: tags:

``` python

print(type(a))

```

%% Output

    <type 'str'>

%% Cell type:code id: tags:

``` python

# Use u'bob' to create unicode, 'bob' is str (ascii)

b = u'bob'

print(b)

print(type(b))

```

%% Output

    bob

    <type 'unicode'>

%% Cell type:code id: tags:

``` python

# Length of Unicode is the number of characters, but length of str is the number of bytes

# format command just makes things easier

print("Length of unicode: {}".format(len(u'à')))

print("Length of str (bytes): {}".format(len('à')))

```

%% Output

    Length of unicode: 1

    Length of str (bytes): 2

%% Cell type:code id: tags:

``` python

# A lot of times you will get text from some unknown encoding.

# UTF-8 is the most common representation.

# If you need to catch errros, you can remove errors='ignore'

def convert_unicode(text):

    if isinstance(text,str):

        return text.decode('utf-8',errors='ignore')

    else:

        return text

in_str = 'à'

print(type(in_str))

in_unicode = convert_unicode(in_str)

print(type(in_unicode))

```

%% Output

    <type 'str'>

    <type 'unicode'>

%% Cell type:code id: tags:

``` python

# But to write to a file, it must be encoded back to bytes

# --> Gives UnicodeEncodeError

a = u'à'

print(type(a))

with open('tmp.txt','w') as f:

    f.write(a)

print('done')

```

%% Output

    <type 'unicode'>

    ---------------------------------------------------------------------------

    UnicodeEncodeError                        Traceback (most recent call last)

    <ipython-input-7-808c054e9f11> in <module>()

          4 print(type(a))

          5 with open('tmp.txt','w') as f:

    ----> 6     f.write(a)

          7 print('done')

    UnicodeEncodeError: 'ascii' codec can't encode character u'\xe0' in position 0: ordinal not in range(128)

%% Cell type:code id: tags:

``` python

# Instead encode it like this

a = u'à'

print(type(a))

with open('tmp.txt','w') as f:

    a = a.encode('utf-8',errors='ignore')

    f.write(a)

print(type(a))

print('done')

```

%% Output

    <type 'unicode'>

    <type 'str'>

    done

%% Cell type:code id: tags:

``` python

```

%% Cell type:code id: tags:

``` python

# In Python 3 str is Unicode

a = 'niño'

print(type(a))

```

%% Output

    <class 'str'>

%% Cell type:code id: tags:

``` python

# It gives the length as one character

x = 'à'

print(len(x))

```

%% Output

    1

%% Cell type:code id: tags:

``` python

# Unicode is standard in Python 3, making life easier in that regard

print(type(x))

with open('tmp.txt','w') as f:

    f.write(x)

print('done')

```

%% Output

    <class 'str'>

    done

%% Cell type:code id: tags:

``` python

```

%% Cell type:code id: tags:

``` python

# You can add strings

a = "chicken" + "man"

print(a)

```

%% Output

    chickenman

%% Cell type:code id: tags:

``` python

# A string is a sequence of characters starting with 0

print(a[1])

print(a[2:])

print(a[2:-1])

```

%% Output

    h

    ickenman

    ickenma

%% Cell type:code id: tags:

``` python

# you can check if a string is in another string

print("hi" in a)

print("zi" in a)

print("HI" in a)

print("HI".lower() in a)

```

%% Output

    True

    False

    False

    True

%% Cell type:code id: tags:

``` python

# you can check starting and ending

print(a.startswith("ch"))

print(a.endswith("man"))

```

%% Output

    True

    True

%% Cell type:code id: tags:

``` python

# but strings cannot be changed (they are immutable)

print(a)

print(a[3])

```

%% Output

    chickenman

    c

%% Cell type:code id: tags:

``` python

# but strings cannot be changed (they are immutable)

# more immutable, you can't replace the second 'c' with 'X'

a[3] = 'X'

```

%% Output

    ---------------------------------------------------------------------------

    TypeError                                 Traceback (most recent call last)

    <ipython-input-6-643a1d946f27> in <module>()

          1 # but strings cannot be changed (they are immutable)

          2 # more immutable, you can't replace the second 'c' with 'X'

    ----> 3 a[3] = 'X'

    TypeError: 'str' object does not support item assignment

%% Cell type:code id: tags:

``` python

# if you want to change a part of the string, use +

new_string = a[:3] + 'X' + a[4:]

print(new_string)

print(a)

```

%% Output

    chiXkenman

    chickenman

%% Cell type:code id: tags:

``` python

# you can split a string based on a character

word_list = "I love to drive cars.".split(' ')

print(word_list)

```

%% Output

    ['I', 'love', 'to', 'drive', 'cars.']

%% Cell type:code id: tags:

``` python

# you can strip off line breaks ('\n')

return_at_end = "Hi there.\n"

print(return_at_end)

print("Next line.")

print(return_at_end.strip())

print("Next line.")

```

%% Output

    Hi there.

    Next line.

    Hi there.

    Next line.

%% Cell type:code id: tags:

``` python

# you can replace characters in a string

new_string = "I love tacos.".replace('love','enjoy')

print(new_string)

```

%% Output

    I enjoy tacos.

%% Cell type:code id: tags:

``` python

# strings can be ' or " or ''' or """

a = 'bob'

b = "tom"

c = '''frank'''

d = """frank"""

```

%% Cell type:code id: tags:

``` python

# need to escape

print('I can't believe it.')

```

%% Output

      File "<ipython-input-12-518b6ec77231>", line 2

        print('I can't believe it.')

                     ^

    SyntaxError: invalid syntax

%% Cell type:code id: tags:

``` python

# can escape or put it inside other kind

print("I can't believe it.")

print('I can\'t believe it.')

```

%% Output

    I can't believe it.

    I can't believe it.

%% Cell type:code id: tags:

``` python

```

%% Cell type:code id: tags:

``` python

```