Ruby中是如何處理字符串的？_Ruby_编程开发_程序员俱乐部

#定义字符串
"abc"

'efg'

 %Q{abc} #等价于 ""

 %{hahaha} #等价于 ""

 %q!efg! #等价于 ''

 %!hello! #等价于 ''

Q:"" 和'' 两者之间的区别？
A："" 中可以嵌入#{}输出表达式的值，或者是character escapes

str = "abc"

puts "this is #{str}" # this is abc

puts 'this is #{str}' # this is #{str}

puts "abc\nedf" # abc
                # edf

puts 'abc\nefg' # abc\nefg

Q：ruby中字符编码？
Q：在ruby中puts "中國" 出现"invalid multitype char<us-ASCII>"
A：ruby中的source code 默認的編碼是US-ACSII，不能解析中文。需要把源文件的編碼改為“適合”的方式，繁體是

#encoding： Big5

#new
my_name = "tony"

your_name = String.new(my_name)

puts my_name.object_id #5907780

puts your_name.object_id #5907768

your_name[0] = "m"

puts my_name # tony

puts your_name # mony

#String.try_convert

puts "try_convert"

puts String.try_convert("aBC") #aBC

puts String.try_convert(12345) #nil

puts String.try_convert("12345") #12345

# % format string
puts "%"
puts "str % arg -> string"

puts "%05d" % 123 #00123 formatstring = "%flag with precision name fieldtype"

puts "%0b" % 123 #1111011 

puts "%5s: %08x" % ["ID", self.object_id] #   ID: 005af846

puts "%-5s: %08X" % ["ID", self.object_id] #ID   : 005AF846

puts "%-5<name>s : %08<value>X" % {name: "hash_id", value: self.object_id} #hash_id: 005AF86

# * copies
# + concatenation 
# << append  if the object is a Fixnum it is considered to be a codepoint in the encoding
#    of str and converted to the appropriate character before being appended
# concat

puts "Ha" * 3 #HaHaHa

puts "Ha" + "Ho" #HaHo

puts "Hello" << 119 #Hellow

puts "Hello" << "Tony" #HelloTony

puts "concat"

puts "Hello".concat(" Tony") # Hello Tony

str = "hello"

str << 119

puts str << "Tony" #hellowTony

#[] []=
puts "[],[]="

str = "Hello Ruby"

puts str[-1] # y
puts str[0] # H
puts str[1] #e
puts str[9] #y
puts str[10] #nil

puts str[0..2] #hel

puts str[0...2] #he

puts str[0,2] #he

puts str["e"] #e

str[0..2] = 'haha'

puts str # hahalo Ruby

#ascii_only?
puts "ascii_only?"
puts __ENCODING__ #Big5

puts "ruby".ascii_only? #true

str = "中國"
puts str.ascii_only? #false

#bytes, chars, codepoints
#str.bytes -> enum
#str.bytes{|byte| block} -> str
#str.chars -> enum
#str.chars{|char| block}-> str
#codepoints(integers representation of the characters)
#str.codepoints -> enum
#str.codepoints {|integer| block} -> str
#getbyte
puts "bytes, getbyte"
p "ruby".bytes.to_a #[114,117,98,121]

puts "getbyte"
puts "ruby".getbyte(1) #117

result = []

puts "ruby".bytes {|byte| result << byte} #ruby

p result #[114,117,98,121]

puts "chars"

p "ruby".chars.to_a # ["r", "u", "b", "y"]

result = []

puts "ruby".chars {|char| result << char} #ruby 

p result # ["r", "u", "b", "y"]

puts "codepoints"

p "中國".codepoints.to_a # [42148, 45290]

result = []

puts "中國".codepoints {|b| result << b} #中國

p result #[42148, 45290] 

#bytesize, length, size
puts "bytesize, length"

puts "ruby".length #4
puts "ruby".bytesize #4
puts "ruby".size #4

puts "中國".length # 2
puts "中國".bytesize # 4
puts "中國".size #2

#capitalize, capitalize!
#capitalize  return a copy of str with the first character converted to 
#            uppcase and the remainder to lowercase
#capitalize! Modified str by converting the first character to uppercase and the 
#            ramainder to lowercase .Returns nil if no changes are made
puts "capitalize, capitalize! "

str = "hello Ruby"
puts "str = hello Ruby"

puts "str.capitalize = > #{str.capitalize}" #Hello ruby

puts "str = > #{str}" # hello Ruby

puts "str.capitalize! = > #{str.capitalize!}" # Hello Ruby

puts "str = > #{str}" # Hello Ruby

puts "str.capitalize! = > #{str.capitalize!}" # nil

puts "str = > #{str}" # Hello Ruby

#<=>, casecmp
puts "<=> , casecmp"

puts "abc" <=> "Abc" #1

puts "abc".casecmp("Abc") # 0

puts "abc" <=> "ab" #1

puts "abc".casecmp("ab") #1

puts "ab" <=> "abc" #-1

puts "ab".casecmp("abc") #-1

#center
puts "center"

str = "ruby"

puts str.center(4) #ruby

puts str.center(5) #ruby

puts str.center(10, '*') #***ruby***

puts str # ruby

#chr return the first character

puts "chr"

puts "ruby".chr # r

puts "中國".chr # 中

#clear removes the content(but not the associated encoding) of str

puts "clear"

str = "ruby"
puts str.clear #nil

puts str.length #0

#encoding: Big5
puts str.encoding #Big5

#chomp, chomp!
#chomp return new string with given record separator remove from the end of str
#str.chomp(rs = $/) -> string
puts "chomp, chomp!"

str =  "ruby"

p str.chomp # ruby

p str.chomp("y") # rub

str = "ruby\n"

p str.chomp # ruby

str = "ruby\n\r"

p str.chomp # ruby\n

str = "ruby\r\n"

p str.chomp # ruby

str = "ru \n by"
p str.chomp # ru \n by

#chop, chop!
#remove last character

puts "chop"
p "ruby".chop #rub
p "ruby\n".chop # ruby
p "ruby\r\n".chop #ruby
p "R".chop.chop # ""

#count, delete, delete! 
#str.count(<string>+)->int
#Each string parameter difines a set of characters to count.
#the intersection of these sets defines the characters to count in str
#Any parameter that starts with a caret(^) is negated
#The sequence c1-c2 means all characters between c1 and c2
puts "count"

str = "hello world"
puts str.count "lo" #5 在str 中 有 3 個 l 和 兩個 0 => 3 + 2 = 5

puts str.count "el" #4

puts str.count "lo", "o" #2 [l,o],[o]的交集是 0 在str中出現2個

puts str.count "ej-m" # 4 [e,j,k,l,m] 在str 中有 1個 e 3個l 總共 4

puts "delete"
puts str.delete "lo" # he wrd

puts str # hello world

puts str.delete! "e" # hllo world

puts str # hllo world

#crypt 加密
puts "crypt"

puts "ruby".crypt "ruby"

#downcase, downcase!
puts "downcase downcase!"

puts "ABC".downcase #abc

#dump
#Produces a version of str with all nonprinting characters replaced by \nnn notation
#and all special characters escaped
puts "dump"

p "ABC".dump #"\"ABC"\"

p "ABC" #"ABC"

#empty?
puts "empty?"

puts "hello".empty? # false

puts "".empty? #true

#encode, encode!, encoding, force_encoding
puts "encoding"

str = "ruby"

puts str.encoding #GBK

puts str.encode("utf-8") # ruby

puts str.encoding #GBK

puts str.encode!("utf-8") # ruby

puts str.encoding #utf-8

str.force_encoding("GBK")

puts str.encoding  #GBK

#gsub, gsub! 與正則表達式連用搜索字符串

#start_with? end_with?
puts "start_with?, end_with"

puts "Apache".end_with?("ache") # true

puts "ruby code".end_with?("python", "perl", "code") # true

puts "Apache".start_with?("Apa") # true

puts "ruby code".start_with?("python","perl","ruby") #true

#index
puts "index"

puts "hello".index("e") #1

puts "hello".index("a") #nil

puts "hello".index(/[aeiou]/, -3) #4

puts "hello".index("lo",4) #nil 第二參數開始搜索的位置

#insert
puts "insert"

puts "abcd".insert(0,"X") #Xabcd

puts "abcd".insert(-1, "X") #abcdX

puts "abcd".insert(1, "X") #aXbcd

puts "abcd".insert(-2, "X") #abcXd

#intern
#Return the Symbol corresponding to str, creatin the symbol if it did not 
#previously exist
puts "intern"

p "ruby".intern #:ruby