chore(dependencies): update dependencies

This commit is contained in:
Chris Lane
2020-11-03 17:59:56 -05:00
parent 0b21ccf6f8
commit b9c86b6975
164 changed files with 6825 additions and 7094 deletions

View File

@ -1,5 +1,5 @@
language: go
go:
- 1.5
- 1.9
- tip

View File

@ -43,8 +43,8 @@ The __last__ capture is embedded in each group, so `g.String()` will return the
| Category | regexp | regexp2 |
| --- | --- | --- |
| Catastrophic backtracking possible | no, constant execution time guarantees | yes, if your pattern is at risk you can use the `re.MatchTimeout` field |
| Python-style capture groups `(P<name>re)` | yes | no |
| .NET-style capture groups `(<name>re)` or `('name're)` | no | yes |
| Python-style capture groups `(?P<name>re)` | yes | no (yes in RE2 compat mode) |
| .NET-style capture groups `(?<name>re)` or `(?'name're)` | no | yes |
| comments `(?#comment)` | no | yes |
| branch numbering reset `(?\|a\|b)` | no | no |
| possessive match `(?>re)` | no | yes |
@ -54,14 +54,15 @@ The __last__ capture is embedded in each group, so `g.String()` will return the
| negative lookbehind `(?<!re)` | no | yes |
| back reference `\1` | no | yes |
| named back reference `\k'name'` | no | yes |
| named ascii character class `[[:foo:]]`| yes | no |
| conditionals `((expr)yes\|no)` | no | yes |
| named ascii character class `[[:foo:]]`| yes | no (yes in RE2 compat mode) |
| conditionals `(?(expr)yes\|no)` | no | yes |
## RE2 compatibility mode
The default behavior of `regexp2` is to match the .NET regexp engine, however the `RE2` option is provided to change the parsing to increase compatibility with RE2. Using the `RE2` option when compiling a regexp will not take away any features, but will change the following behaviors:
* add support for named ascii character classes (e.g. `[[:foo:]]`)
* add support for python-style capture groups (e.g. `(P<name>re)`)
* change singleline behavior for `$` to only match end of string (like RE2) (see [#24](https://github.com/dlclark/regexp2/issues/24))
```go
re := regexp2.MustCompile(`Your RE2-compatible pattern`, regexp2.RE2)
if isMatch, _ := re.MatchString(`Something to match`); isMatch {

View File

@ -235,17 +235,14 @@ func (re *Regexp) getRunesAndStart(s string, startAt int) ([]rune, int) {
ret[i] = r
i++
}
if startAt == len(s) {
runeIdx = i
}
return ret[:i], runeIdx
}
func getRunes(s string) []rune {
ret := make([]rune, len(s))
i := 0
for _, r := range s {
ret[i] = r
i++
}
return ret[:i]
return []rune(s)
}
// MatchRunes return true if the runes matches the regex

View File

@ -566,9 +566,22 @@ func (r *runner) execute() error {
continue
case syntax.EndZ:
if r.rightchars() > 1 || r.rightchars() == 1 && r.charAt(r.textPos()) != '\n' {
rchars := r.rightchars()
if rchars > 1 {
break
}
// RE2 and EcmaScript define $ as "asserts position at the end of the string"
// PCRE/.NET adds "or before the line terminator right at the end of the string (if any)"
if (r.re.options & (RE2 | ECMAScript)) != 0 {
// RE2/Ecmascript mode
if rchars > 0 {
break
}
} else if rchars == 1 && r.charAt(r.textPos()) != '\n' {
// "regular" mode
break
}
r.advance(0)
continue
@ -938,8 +951,8 @@ func (r *runner) advance(i int) {
}
func (r *runner) goTo(newpos int) {
// when branching backward, ensure storage
if newpos < r.codepos {
// when branching backward or in place, ensure storage
if newpos <= r.codepos {
r.ensureStorage()
}

View File

@ -1250,10 +1250,10 @@ func (p *parser) scanBasicBackslash(scanOnly bool) (*regexNode, error) {
return nil, nil
}
if p.useOptionE() || p.isCaptureSlot(capnum) {
if p.isCaptureSlot(capnum) {
return newRegexNodeM(ntRef, p.options, capnum), nil
}
if capnum <= 9 {
if capnum <= 9 && !p.useOptionE() {
return nil, p.getErr(ErrUndefinedBackRef, capnum)
}
@ -1648,7 +1648,7 @@ func (p *parser) scanOptions() {
}
// Scans \ code for escape codes that map to single unicode chars.
func (p *parser) scanCharEscape() (rune, error) {
func (p *parser) scanCharEscape() (r rune, err error) {
ch := p.moveRightGetChar()
@ -1657,16 +1657,22 @@ func (p *parser) scanCharEscape() (rune, error) {
return p.scanOctal(), nil
}
pos := p.textpos()
switch ch {
case 'x':
// support for \x{HEX} syntax from Perl and PCRE
if p.charsRight() > 0 && p.rightChar(0) == '{' {
if p.useOptionE() {
return ch, nil
}
p.moveRight(1)
return p.scanHexUntilBrace()
} else {
r, err = p.scanHex(2)
}
return p.scanHex(2)
case 'u':
return p.scanHex(4)
r, err = p.scanHex(4)
case 'a':
return '\u0007', nil
case 'b':
@ -1684,13 +1690,18 @@ func (p *parser) scanCharEscape() (rune, error) {
case 'v':
return '\u000B', nil
case 'c':
return p.scanControl()
r, err = p.scanControl()
default:
if !p.useOptionE() && IsWordChar(ch) {
return 0, p.getErr(ErrUnrecognizedEscape, string(ch))
}
return ch, nil
}
if err != nil && p.useOptionE() {
p.textto(pos)
return ch, nil
}
return
}
// Grabs and converts an ascii control character
@ -1807,12 +1818,12 @@ func (p *parser) scanOctal() rune {
//we know the first char is good because the caller had to check
i := 0
d := int(p.rightChar(0) - '0')
for c > 0 && d <= 7 {
i *= 8
i += d
if p.useOptionE() && i >= 0x20 {
for c > 0 && d <= 7 && d >= 0 {
if i >= 0x20 && p.useOptionE() {
break
}
i *= 8
i += d
c--
p.moveRight(1)