regexp

func (*Regexp) Expand ¶

func (re *Regexp) Expand(dst []byte, template []byte, src []byte, match []int) []byte

Expand appends template to dst and returns the result; during the append, Expand replaces variables in the template with corresponding matches drawn from src. The match slice should have been returned by FindSubmatchIndex.

In the template, a variable is denoted by a substring of the form $name or ${name}, where name is a non-empty sequence of letters, digits, and underscores. A purely numeric name like $1 refers to the submatch with the corresponding index; other names refer to capturing parentheses named with the (?P<name>...) syntax. A reference to an out of range or unmatched index or a name that is not present in the regular expression is replaced with an empty slice.

In the $name form, name is taken to be as long as possible: $1x is equivalent to ${1x}, not ${1}x, and, $10 is equivalent to ${10}, not ${1}0.

To insert a literal $ in the output, use $$ in the template.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	content := []byte(`
	# comment line
	option1: value1
	option2: value2

	# another comment line
	option3: value3
`)

	// Regex pattern captures "key: value" pair from the content.
	pattern := regexp.MustCompile(`(?m)(?P<key>\w+):\s+(?P<value>\w+)$`)

	// Template to convert "key: value" to "key=value" by
	// referencing the values captured by the regex pattern.
	template := []byte("$key=$value\n")

	result := []byte{}

	// For each match of the regex in the content.
	for _, submatches := range pattern.FindAllSubmatchIndex(content, -1) {
		// Apply the captured submatches to the template and append the output
		// to the result.
		result = pattern.Expand(result, template, content, submatches)
	}
	fmt.Println(string(result))
}

Output:

option1=value1
option2=value2
option3=value3

func (*Regexp) ExpandString ¶

func (re *Regexp) ExpandString(dst []byte, template string, src string, match []int) []byte

ExpandString is like Expand but the template and source are strings. It appends to and returns a byte slice in order to give the calling code control over allocation.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	content := `
	# comment line
	option1: value1
	option2: value2

	# another comment line
	option3: value3
`

	// Regex pattern captures "key: value" pair from the content.
	pattern := regexp.MustCompile(`(?m)(?P<key>\w+):\s+(?P<value>\w+)$`)

	// Template to convert "key: value" to "key=value" by
	// referencing the values captured by the regex pattern.
	template := "$key=$value\n"

	result := []byte{}

	// For each match of the regex in the content.
	for _, submatches := range pattern.FindAllStringSubmatchIndex(content, -1) {
		// Apply the captured submatches to the template and append the output
		// to the result.
		result = pattern.ExpandString(result, template, content, submatches)
	}
	fmt.Println(string(result))
}

Output:

option1=value1
option2=value2
option3=value3

func (*Regexp) Find ¶

func (re *Regexp) Find(b []byte) []byte

Find returns a slice holding the text of the leftmost match in b of the regular expression. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`foo.?`)
	fmt.Printf("%q\n", re.Find([]byte(`seafood fool`)))

}

Output:

"food"

func (*Regexp) FindAll ¶

func (re *Regexp) FindAll(b []byte, n int) [][]byte

FindAll is the 'All' version of Find; it returns a slice of all successive matches of the expression, as defined by the 'All' description in the package comment. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`foo.?`)
	fmt.Printf("%q\n", re.FindAll([]byte(`seafood fool`), -1))

}

Output:

["food" "fool"]

func (*Regexp) FindAllIndex ¶

func (re *Regexp) FindAllIndex(b []byte, n int) [][]int

FindAllIndex is the 'All' version of FindIndex; it returns a slice of all successive matches of the expression, as defined by the 'All' description in the package comment. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	content := []byte("London")
	re := regexp.MustCompile(`o.`)
	fmt.Println(re.FindAllIndex(content, 1))
	fmt.Println(re.FindAllIndex(content, -1))
}

Output:

[[1 3]]
[[1 3] [4 6]]

func (*Regexp) FindAllString ¶

func (re *Regexp) FindAllString(s string, n int) []string

FindAllString is the 'All' version of FindString; it returns a slice of all successive matches of the expression, as defined by the 'All' description in the package comment. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`a.`)
	fmt.Println(re.FindAllString("paranormal", -1))
	fmt.Println(re.FindAllString("paranormal", 2))
	fmt.Println(re.FindAllString("graal", -1))
	fmt.Println(re.FindAllString("none", -1))
}

Output:

[ar an al]
[ar an]
[aa]
[]

func (*Regexp) FindAllStringIndex ¶

func (re *Regexp) FindAllStringIndex(s string, n int) [][]int

FindAllStringIndex is the 'All' version of FindStringIndex; it returns a slice of all successive matches of the expression, as defined by the 'All' description in the package comment. A return value of nil indicates no match.

func (*Regexp) FindAllStringSubmatch ¶

func (re *Regexp) FindAllStringSubmatch(s string, n int) [][]string

FindAllStringSubmatch is the 'All' version of FindStringSubmatch; it returns a slice of all successive matches of the expression, as defined by the 'All' description in the package comment. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`a(x*)b`)
	fmt.Printf("%q\n", re.FindAllStringSubmatch("-ab-", -1))
	fmt.Printf("%q\n", re.FindAllStringSubmatch("-axxb-", -1))
	fmt.Printf("%q\n", re.FindAllStringSubmatch("-ab-axb-", -1))
	fmt.Printf("%q\n", re.FindAllStringSubmatch("-axxb-ab-", -1))
}

Output:

[["ab" ""]]
[["axxb" "xx"]]
[["ab" ""] ["axb" "x"]]
[["axxb" "xx"] ["ab" ""]]

func (*Regexp) FindAllStringSubmatchIndex ¶

func (re *Regexp) FindAllStringSubmatchIndex(s string, n int) [][]int

FindAllStringSubmatchIndex is the 'All' version of FindStringSubmatchIndex; it returns a slice of all successive matches of the expression, as defined by the 'All' description in the package comment. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`a(x*)b`)
	// Indices:
	//    01234567   012345678
	//    -ab-axb-   -axxb-ab-
	fmt.Println(re.FindAllStringSubmatchIndex("-ab-", -1))
	fmt.Println(re.FindAllStringSubmatchIndex("-axxb-", -1))
	fmt.Println(re.FindAllStringSubmatchIndex("-ab-axb-", -1))
	fmt.Println(re.FindAllStringSubmatchIndex("-axxb-ab-", -1))
	fmt.Println(re.FindAllStringSubmatchIndex("-foo-", -1))
}

Output:

[[1 3 2 2]]
[[1 5 2 4]]
[[1 3 2 2] [4 7 5 6]]
[[1 5 2 4] [6 8 7 7]]
[]

func (*Regexp) FindAllSubmatch ¶

func (re *Regexp) FindAllSubmatch(b []byte, n int) [][][]byte

FindAllSubmatch is the 'All' version of FindSubmatch; it returns a slice of all successive matches of the expression, as defined by the 'All' description in the package comment. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`foo(.?)`)
	fmt.Printf("%q\n", re.FindAllSubmatch([]byte(`seafood fool`), -1))

}

Output:

[["food" "d"] ["fool" "l"]]

func (*Regexp) FindAllSubmatchIndex ¶

func (re *Regexp) FindAllSubmatchIndex(b []byte, n int) [][]int

FindAllSubmatchIndex is the 'All' version of FindSubmatchIndex; it returns a slice of all successive matches of the expression, as defined by the 'All' description in the package comment. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	content := []byte(`
	# comment line
	option1: value1
	option2: value2
`)
	// Regex pattern captures "key: value" pair from the content.
	pattern := regexp.MustCompile(`(?m)(?P<key>\w+):\s+(?P<value>\w+)$`)
	allIndexes := pattern.FindAllSubmatchIndex(content, -1)
	for _, loc := range allIndexes {
		fmt.Println(loc)
		fmt.Println(string(content[loc[0]:loc[1]]))
		fmt.Println(string(content[loc[2]:loc[3]]))
		fmt.Println(string(content[loc[4]:loc[5]]))
	}
}

Output:

[18 33 18 25 27 33]
option1: value1
option1
value1
[35 50 35 42 44 50]
option2: value2
option2
value2

func (*Regexp) FindIndex ¶

func (re *Regexp) FindIndex(b []byte) (loc []int)

FindIndex returns a two-element slice of integers defining the location of the leftmost match in b of the regular expression. The match itself is at b[loc[0]:loc[1]]. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	content := []byte(`
	# comment line
	option1: value1
	option2: value2
`)
	// Regex pattern captures "key: value" pair from the content.
	pattern := regexp.MustCompile(`(?m)(?P<key>\w+):\s+(?P<value>\w+)$`)

	loc := pattern.FindIndex(content)
	fmt.Println(loc)
	fmt.Println(string(content[loc[0]:loc[1]]))
}

Output:

[18 33]
option1: value1

func (*Regexp) FindReaderIndex ¶

func (re *Regexp) FindReaderIndex(r io.RuneReader) (loc []int)

FindReaderIndex returns a two-element slice of integers defining the location of the leftmost match of the regular expression in text read from the RuneReader. The match text was found in the input stream at byte offset loc[0] through loc[1]-1. A return value of nil indicates no match.

func (*Regexp) FindReaderSubmatchIndex ¶

func (re *Regexp) FindReaderSubmatchIndex(r io.RuneReader) []int

FindReaderSubmatchIndex returns a slice holding the index pairs identifying the leftmost match of the regular expression of text read by the RuneReader, and the matches, if any, of its subexpressions, as defined by the 'Submatch' and 'Index' descriptions in the package comment. A return value of nil indicates no match.

func (*Regexp) FindString ¶

func (re *Regexp) FindString(s string) string

FindString returns a string holding the text of the leftmost match in s of the regular expression. If there is no match, the return value is an empty string, but it will also be empty if the regular expression successfully matches an empty string. Use FindStringIndex or FindStringSubmatch if it is necessary to distinguish these cases.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`foo.?`)
	fmt.Printf("%q\n", re.FindString("seafood fool"))
	fmt.Printf("%q\n", re.FindString("meat"))
}

Output:

"food"
""

func (*Regexp) FindStringIndex ¶

func (re *Regexp) FindStringIndex(s string) (loc []int)

FindStringIndex returns a two-element slice of integers defining the location of the leftmost match in s of the regular expression. The match itself is at s[loc[0]:loc[1]]. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`ab?`)
	fmt.Println(re.FindStringIndex("tablett"))
	fmt.Println(re.FindStringIndex("foo") == nil)
}

Output:

[1 3]
true

func (*Regexp) FindStringSubmatch ¶

func (re *Regexp) FindStringSubmatch(s string) []string

FindStringSubmatch returns a slice of strings holding the text of the leftmost match of the regular expression in s and the matches, if any, of its subexpressions, as defined by the 'Submatch' description in the package comment. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`a(x*)b(y|z)c`)
	fmt.Printf("%q\n", re.FindStringSubmatch("-axxxbyc-"))
	fmt.Printf("%q\n", re.FindStringSubmatch("-abzc-"))
}

Output:

["axxxbyc" "xxx" "y"]
["abzc" "" "z"]

func (*Regexp) FindStringSubmatchIndex ¶

func (re *Regexp) FindStringSubmatchIndex(s string) []int

FindStringSubmatchIndex returns a slice holding the index pairs identifying the leftmost match of the regular expression in s and the matches, if any, of its subexpressions, as defined by the 'Submatch' and 'Index' descriptions in the package comment. A return value of nil indicates no match.

func (*Regexp) FindSubmatch ¶

func (re *Regexp) FindSubmatch(b []byte) [][]byte

FindSubmatch returns a slice of slices holding the text of the leftmost match of the regular expression in b and the matches, if any, of its subexpressions, as defined by the 'Submatch' descriptions in the package comment. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`foo(.?)`)
	fmt.Printf("%q\n", re.FindSubmatch([]byte(`seafood fool`)))

}

Output:

["food" "d"]

func (*Regexp) FindSubmatchIndex ¶

func (re *Regexp) FindSubmatchIndex(b []byte) []int

FindSubmatchIndex returns a slice holding the index pairs identifying the leftmost match of the regular expression in b and the matches, if any, of its subexpressions, as defined by the 'Submatch' and 'Index' descriptions in the package comment. A return value of nil indicates no match.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`a(x*)b`)
	// Indices:
	//    01234567   012345678
	//    -ab-axb-   -axxb-ab-
	fmt.Println(re.FindSubmatchIndex([]byte("-ab-")))
	fmt.Println(re.FindSubmatchIndex([]byte("-axxb-")))
	fmt.Println(re.FindSubmatchIndex([]byte("-ab-axb-")))
	fmt.Println(re.FindSubmatchIndex([]byte("-axxb-ab-")))
	fmt.Println(re.FindSubmatchIndex([]byte("-foo-")))
}

Output:

[1 3 2 2]
[1 5 2 4]
[1 3 2 2]
[1 5 2 4]
[]

func (*Regexp) LiteralPrefix ¶

func (re *Regexp) LiteralPrefix() (prefix string, complete bool)

LiteralPrefix returns a literal string that must begin any match of the regular expression re. It returns the boolean true if the literal string comprises the entire regular expression.

func (*Regexp) Longest ¶

func (re *Regexp) Longest()

Longest makes future searches prefer the leftmost-longest match. That is, when matching against text, the regexp returns a match that begins as early as possible in the input (leftmost), and among those it chooses a match that is as long as possible. This method modifies the Regexp and may not be called concurrently with any other methods.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`a(|b)`)
	fmt.Println(re.FindString("ab"))
	re.Longest()
	fmt.Println(re.FindString("ab"))
}

Output:

a
ab

func (*Regexp) Match ¶

func (re *Regexp) Match(b []byte) bool

Match reports whether the byte slice b contains any match of the regular expression re.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`foo.?`)
	fmt.Println(re.Match([]byte(`seafood fool`)))
	fmt.Println(re.Match([]byte(`something else`)))

}

Output:

true
false

func (*Regexp) MatchReader ¶

func (re *Regexp) MatchReader(r io.RuneReader) bool

MatchReader reports whether the text returned by the RuneReader contains any match of the regular expression re.

func (*Regexp) MatchString ¶

func (re *Regexp) MatchString(s string) bool

MatchString reports whether the string s contains any match of the regular expression re.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`(gopher){2}`)
	fmt.Println(re.MatchString("gopher"))
	fmt.Println(re.MatchString("gophergopher"))
	fmt.Println(re.MatchString("gophergophergopher"))
}

Output:

false
true
true

func (*Regexp) NumSubexp ¶

func (re *Regexp) NumSubexp() int

NumSubexp returns the number of parenthesized subexpressions in this Regexp.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re0 := regexp.MustCompile(`a.`)
	fmt.Printf("%d\n", re0.NumSubexp())

	re := regexp.MustCompile(`(.*)((a)b)(.*)a`)
	fmt.Println(re.NumSubexp())
}

Output:

0
4

func (*Regexp) ReplaceAll ¶

func (re *Regexp) ReplaceAll(src, repl []byte) []byte

ReplaceAll returns a copy of src, replacing matches of the Regexp with the replacement text repl. Inside repl, $ signs are interpreted as in Expand, so for instance $1 represents the text of the first submatch.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`a(x*)b`)
	fmt.Printf("%s\n", re.ReplaceAll([]byte("-ab-axxb-"), []byte("T")))
	fmt.Printf("%s\n", re.ReplaceAll([]byte("-ab-axxb-"), []byte("$1")))
	fmt.Printf("%s\n", re.ReplaceAll([]byte("-ab-axxb-"), []byte("$1W")))
	fmt.Printf("%s\n", re.ReplaceAll([]byte("-ab-axxb-"), []byte("${1}W")))
}

Output:

-T-T-
--xx-
---
-W-xxW-

func (*Regexp) ReplaceAllFunc ¶

func (re *Regexp) ReplaceAllFunc(src []byte, repl func([]byte) []byte) []byte

ReplaceAllFunc returns a copy of src in which all matches of the Regexp have been replaced by the return value of function repl applied to the matched byte slice. The replacement returned by repl is substituted directly, without using Expand.

func (*Regexp) ReplaceAllLiteral ¶

func (re *Regexp) ReplaceAllLiteral(src, repl []byte) []byte

ReplaceAllLiteral returns a copy of src, replacing matches of the Regexp with the replacement bytes repl. The replacement repl is substituted directly, without using Expand.

func (*Regexp) ReplaceAllLiteralString ¶

func (re *Regexp) ReplaceAllLiteralString(src, repl string) string

ReplaceAllLiteralString returns a copy of src, replacing matches of the Regexp with the replacement string repl. The replacement repl is substituted directly, without using Expand.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`a(x*)b`)
	fmt.Println(re.ReplaceAllLiteralString("-ab-axxb-", "T"))
	fmt.Println(re.ReplaceAllLiteralString("-ab-axxb-", "$1"))
	fmt.Println(re.ReplaceAllLiteralString("-ab-axxb-", "${1}"))
}

Output:

-T-T-
-$1-$1-
-${1}-${1}-

func (*Regexp) ReplaceAllString ¶

func (re *Regexp) ReplaceAllString(src, repl string) string

ReplaceAllString returns a copy of src, replacing matches of the Regexp with the replacement string repl. Inside repl, $ signs are interpreted as in Expand, so for instance $1 represents the text of the first submatch.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`a(x*)b`)
	fmt.Println(re.ReplaceAllString("-ab-axxb-", "T"))
	fmt.Println(re.ReplaceAllString("-ab-axxb-", "$1"))
	fmt.Println(re.ReplaceAllString("-ab-axxb-", "$1W"))
	fmt.Println(re.ReplaceAllString("-ab-axxb-", "${1}W"))
}

Output:

-T-T-
--xx-
---
-W-xxW-

func (*Regexp) ReplaceAllStringFunc ¶

func (re *Regexp) ReplaceAllStringFunc(src string, repl func(string) string) string

ReplaceAllStringFunc returns a copy of src in which all matches of the Regexp have been replaced by the return value of function repl applied to the matched substring. The replacement returned by repl is substituted directly, without using Expand.

package main

import (
	"fmt"
	"regexp"
	"strings"
)

func main() {
	re := regexp.MustCompile(`[^aeiou]`)
	fmt.Println(re.ReplaceAllStringFunc("seafood fool", strings.ToUpper))
}

Output:

SeaFooD FooL

func (*Regexp) Split ¶

func (re *Regexp) Split(s string, n int) []string

Split slices s into substrings separated by the expression and returns a slice of the substrings between those expression matches.

The slice returned by this method consists of all the substrings of s not contained in the slice returned by FindAllString. When called on an expression that contains no metacharacters, it is equivalent to strings.SplitN.

Example:

s := regexp.MustCompile("a*").Split("abaabaccadaaae", 5)
// s: ["", "b", "b", "c", "cadaaae"]

The count determines the number of substrings to return:

n > 0: at most n substrings; the last substring will be the unsplit remainder.
n == 0: the result is nil (zero substrings)
n < 0: all substrings

package main

import (
	"fmt"
	"regexp"
)

func main() {
	a := regexp.MustCompile(`a`)
	fmt.Println(a.Split("banana", -1))
	fmt.Println(a.Split("banana", 0))
	fmt.Println(a.Split("banana", 1))
	fmt.Println(a.Split("banana", 2))
	zp := regexp.MustCompile(`z+`)
	fmt.Println(zp.Split("pizza", -1))
	fmt.Println(zp.Split("pizza", 0))
	fmt.Println(zp.Split("pizza", 1))
	fmt.Println(zp.Split("pizza", 2))
}

Output:

[b n n ]
[]
[banana]
[b nana]
[pi a]
[]
[pizza]
[pi a]

func (*Regexp) String ¶

func (re *Regexp) String() string

String returns the source text used to compile the regular expression.

func (*Regexp) SubexpIndex ¶

func (re *Regexp) SubexpIndex(name string) int

SubexpIndex returns the index of the first subexpression with the given name, or -1 if there is no subexpression with that name.

Note that multiple subexpressions can be written using the same name, as in (?P<bob>a+)(?P<bob>b+), which declares two subexpressions named "bob". In this case, SubexpIndex returns the index of the leftmost such subexpression in the regular expression.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`(?P<first>[a-zA-Z]+) (?P<last>[a-zA-Z]+)`)
	fmt.Println(re.MatchString("Alan Turing"))
	matches := re.FindStringSubmatch("Alan Turing")
	lastIndex := re.SubexpIndex("last")
	fmt.Printf("last => %d\n", lastIndex)
	fmt.Println(matches[lastIndex])
}

Output:

true
last => 2
Turing

func (*Regexp) SubexpNames ¶

func (re *Regexp) SubexpNames() []string

SubexpNames returns the names of the parenthesized subexpressions in this Regexp. The name for the first sub-expression is names[1], so that if m is a match slice, the name for m[i] is SubexpNames()[i]. Since the Regexp as a whole cannot be named, names[0] is always the empty string. The slice should not be modified.

package main

import (
	"fmt"
	"regexp"
)

func main() {
	re := regexp.MustCompile(`(?P<first>[a-zA-Z]+) (?P<last>[a-zA-Z]+)`)
	fmt.Println(re.MatchString("Alan Turing"))
	fmt.Printf("%q\n", re.SubexpNames())
	reversed := fmt.Sprintf("${%s} ${%s}", re.SubexpNames()[2], re.SubexpNames()[1])
	fmt.Println(reversed)
	fmt.Println(re.ReplaceAllString("Alan Turing", reversed))
}

Output:

true
["" "first" "last"]
${last} ${first}
Turing Alan