julia：字符串操作

s1 = "The quick brown fox jumps over the lazy dog α,β,γ"

# returns the first index of a char
i = search(s1, 'b')
println(i)
#> 11
# the second argument is equivalent to the second argument of split, see below

# or a range if called with another string
r = search(s1, "brown")
println(typeof(r))
#> UnitRange{Int64}
println(r)
#> 11:15


# string replace is done thus:
r = replace(s1, "brown", "red")
show(r); println()
#> "The quick red fox jumps over the lazy dog"

# search and replace can also take a [regular expressions] by preceding the string with 'r'
r = search(s1, r"b[\w]*n")  # 这里[\w]为固定格式
println(r)
#> 11:15

# again with a regular expression
r = replace(s1, r"b[\w]*n", "red")
show(r); println()
#> "The quick red fox jumps over the lazy dog"

# there are also functions for regular expressions that return RegexMatch types
# [match] scans left to right for the first match (specified starting index optional)
r = match(r"b[\w]*n", s1)
println(r)
#> RegexMatch("brown")

# RegexMatch types have a property match that holds the matched string
show(r.match); println()
#> "brown"

# [matchall] returns a vector with RegexMatches for each match
r = matchall(r"[\w]{5,}", s1)  # 寻找s1中字符长度大于等于5的
println(r)
#> SubString{String}["quick", "brown", "jumps"]

# [eachmatch] returns an iterator over all the matches
r = eachmatch(r"[\w]{5,}", s1)

for i in r
    print("\"$(i.match)\" ")
end
println()
#> "quick" "brown" "jumps"

# a string can be repeated using the [repeat] function,
# or more succinctly with the [^ syntax]:
r = "hello "^3
show(r); println() #> "hello hello hello "

# the [strip] function works the same as python:
# e.g., with one argument it strips the outer whitespace # 去掉外部空格
r = strip(" hello ")
show(r); println() #> "hello"
# or with a second argument of an array of chars it strips any of them;
r = strip("hello ", ['h', ' ']) # or r = strip("hello ", 'h')
show(r); println() #> "ello"
# (note the array is of chars and not strings)

# similarly [split] works in basically the same way as python:
r = split("hello, there,bob", ',')  # 一个字符用单引号
show(r); println() #> ["hello"," there","bob"]
r = split("hello, there,bob", ", ") # 多于1个字符用双引号
show(r); println() #> ["hello","there,bob"]
r = split("hello, there,bob", [',', ' '], limit=0, keep=false)
show(r); println() #> ["hello","there","bob"]
# (the last two arguements are limit and include_empty, see docs)

# the opposite of split: [join] is simply
# join函数加添相应的符号
r = join(collect(1:10), ", ")
println(r) #> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10