ruby 学习 -- string --1

# define
french_string = "il xc3xa9tait une fois"
long_string = <<EOF
Here is a long string
With many paragraphs
EOF

puts long_string.empty?
puts long_string.include? "many"

puts french_string + long_string

# concatenate
hash = { key1: "val1", key2: "val2" }
string = ""
str2 = ""
hash.each{|k,v| string << k.to_s << " is " << v << "
" }
hash.each{|k,v| str2 << "#{k}" << " is " << "#{v}" << "
"}
puts string
puts str2

# join
data = ['1', '2', '3']
s = ''
data.each { |x| s << x << ' and a '}
puts s # => "1 and a 2 and a 3 and a "
puts data.join(' and a ')

# number
number = 5
puts "The number is #{number}." # => "The number is 5."
puts "The number is #{5}." # => "The number is 5."
puts "The number after #{number} is #{number.next}."
# => "The number after 5 is 6."
puts "The number prior to #{number} is #{number-1}."
# => "The number prior to 5 is 4."
puts "We're ##{number}!" # => "We're #5!"

puts "I've set x to #{x = 5; x += 1}."

# Escaping
puts "#{foo}"
puts '#{foo}'
# puts "#{foo}" # error because no variable of foo defined.

template = 'Oceania has always been at war with %s.'
puts template % 'Eurasia' # => "Oceania has always been at war with Eurasia."

puts 'To 2 decimal places: %.4f' % Math::PI
puts 'Zero-padded: %.3d' % Math::PI

JSP, ASP type

require 'erb'
template = ERB.new %q{Chunky <%= food %>!}
food = "bacon"
puts template.result(binding) # => "Chunky bacon!"
food = "peanut butter"
puts template.result(binding) # => "Chunky peanut butter!"
puts template.result

 reverse, reverse!, split

 reverse 和 reverse! 的区别：reverse 不改变 string 本身， reverse! 相当于 s=s.reverse

s = ".sdrawkcab si gnirts sihT"
puts s.reverse
puts s
puts s.reverse!
puts s.split(/(s+)/) # ["This", " ", "string", " ", "is", " ", "backwards."]
puts s.split(/s+/) # => ["This", "sting", "is", "backwards."]
puts s.split(' ')     # => ["This", "sting", "is", "backwards."]

八进制 和 十六进制 的定义

octal = "00011020"
octal.each_byte { |x| puts x }
# 0
# 1
# 8
# 16
hexadecimal = "x00x01x10x20"
hexadecimal.each_byte { |x| puts x }
# 0
# 1
# 16
# 32

This makes it possible to represent UTF-8 characters even when you can’t type them or display them in your terminal.

Try running this program, and then opening the generated file smiley.html in your web browser:

open('smiley.html', 'wb') do |f|
    f << '<meta http-equiv="Content-Type" content="text/html;charset=UTF-8">'
    f << "xe2x98xBA"
end

特殊字符：

"a" == "x07" # => true # ASCII 0x07 = BEL (Sound system bell)
"" == "x08" # => true # ASCII 0x08 = BS (Backspace)
"e" == "x1b" # => true # ASCII 0x1B = ESC (Escape)
"f" == "x0c" # => true # ASCII 0x0C = FF (Form feed)
"
" == "x0a" # => true # ASCII 0x0A = LF (Newline/line feed)
"
" == "x0d" # => true # ASCII 0x0D = CR (Carriage return)
"	" == "x09" # => true # ASCII 0x09 = HT (Tab/horizontal tab)
"v" == "x0b" # => true # ASCII 0x0B = VT (Vertical tab)

ruby里，如果是可读的ASCII字符，即使是以十六进制表示，print出来的还是可读字符。不可读，输出的为十六进制（以x开头）字符表示形式。

"x10x11xfexff" # => "u0010u0011xFExFF"
"x48145x6cx6c157x0a" # => "Hello
"

为了避免混淆，统一的，单反斜线由双反斜线表示：  => \

"\".size # => 1
"\" == "x5c" # => true
"\n"[0] == ?\ # => true
"\n"[1] == ?n # => true
"\n" =~ /
/ # => nil

组合键的表示. =~ 是正则匹配符号。

"C-aC-bC-c" # => "u0001u0002u0003"
"M-aM-bM-c" # => "xE1xE2xE3"

?C-a # => "u0001"
?M-z # => "xFA"

contains_control_chars = /[C-a-C-^]/
'Foobar' =~ contains_control_chars # => nil
"FooC-zbar" =~ contains_control_chars # => 3

def snoop_on_keylog(input)
    input.each_char do |b|
        case b
          when ?C-c; puts 'Control-C: stopped a process?'
          when ?C-z; puts 'Control-Z: suspended a process?'
          when ?
; puts 'Newline.'
          when ?M-x; puts 'Meta-x: using Emacs?'
        end
     end
end

snoop_on_keylog("ls -ltR03emacsHello12370rot13-other-window1232")
# Control-C: stopped a process?
# Newline.
# Meta-x: using Emacs?
# Newline.
# Control-Z: suspended a process?

字符串定义

puts "foo	bar"
# foo bar
puts %{foo	bar}
# foo bar
puts %Q{foo	bar}
# foo bar
puts 'foo	bar'
# foo	bar
puts %q{foo	bar}
# foo	bar

统计单词个数。

class String
    def word_count
        frequencies = Hash.new(0)
        self.downcase.scan(/(w+([-'.]w+)*)/) { |word, ignore| frequencies[word] += 1 }
        return frequencies
    end
end
puts %{"The F.B.I. fella--he's quite the man-about-town."}.word_count
# => {"f.b.i"=>1, "fella"=>1, "he's"=>1,
# "quite"=>1, "the"=>2, "man-about-town"=>1}

end with 2.9 cookbook

to be continued...