Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix: update regex engine to support possessive match and lookbehind syntaxes #1147

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

fix: update regex engine to support possessive match and lookbehind syntaxes #1147

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
9b67b7c
fix: update engine_regexp compile to use '{','}' as start, end delimi…
cmmoran Jan 31, 2024
ae8fb6e
Merge branch 'master' into fix/regexp-possessive-match-and-lookbehinds
cmmoran May 2, 2024
4106bed
Merge branch 'master' into fix/regexp-possessive-match-and-lookbehinds
cmmoran May 23, 2024
e3e9566
Merge branch 'master' into fix/regexp-possessive-match-and-lookbehinds
cmmoran Jun 6, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 14 additions & 2 deletions rule/engine_regexp.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,8 +4,10 @@
package rule

import (
"errors"
"hash/crc64"
"strings"

"github.com/pkg/errors"

"github.com/dlclark/regexp2"

Expand All @@ -23,7 +25,17 @@ func (re *regexpMatchingEngine) compile(pattern string) error {
re.table = crc64.MakeTable(polynomial)
}
if checksum := crc64.Checksum([]byte(pattern), re.table); checksum != re.checksum {
compiled, err := compiler.CompileRegex(pattern, '<', '>')
startDelim := byte('<')
endDelim := byte('>')
if strings.Contains(pattern, "(?>") || strings.Contains(pattern, "(?<") {
if strings.ContainsRune(pattern, '{') && strings.ContainsRune(pattern, '}') {
startDelim = byte('{')
endDelim = byte('}')
} else {
return errors.Errorf("attempted to use regex 'possessive match' or regex 'lookbehind' without changing delimiters from '<...>' to '{...}' in: %s", pattern)
}
}
compiled, err := compiler.CompileRegex(pattern, startDelim, endDelim)
if err != nil {
return err
}
Expand Down
45 changes: 45 additions & 0 deletions rule/engine_regexp_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,24 @@ func TestFindStringSubmatch(t *testing.T) {
want: nil,
wantErr: true,
},
{
name: "bad lookbehind (wrong delimiters)",
args: args{
pattern: `urn:foo:<(?<=foo:)foobar>`,
matchAgainst: "urn:foo:foobar",
},
want: nil,
wantErr: true,
},
{
name: "bad possessive (wrong delimiters)",
args: args{
pattern: `urn:foo:<(?>=foo:)foobar>`,
matchAgainst: "urn:foo:foobar",
},
want: nil,
wantErr: true,
},
{
name: "one group",
args: args{
Expand Down Expand Up @@ -56,6 +74,33 @@ func TestFindStringSubmatch(t *testing.T) {
want: []string{"bar"},
wantErr: false,
},
{
name: "positive lookbehind (?<=foo)bar",
args: args{
pattern: `urn:foo:{(?<=foo:)foobar}`,
matchAgainst: "urn:foo:foobar",
},
want: []string{"foobar"},
wantErr: false,
},
{
name: "negative lookbehind (?<!boo)foobar",
args: args{
pattern: `urn:foo:{(?<!boo:)foobar}`,
matchAgainst: "urn:foo:foobar",
},
want: []string{"foobar"},
wantErr: false,
},
{
name: "negative lookbehind (?<!boo)foobar, not match",
args: args{
pattern: `urn:foo:{(?<!boo:)foobar}`,
matchAgainst: "urn:boo:foobar",
},
want: nil,
wantErr: true,
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
Expand Down
Loading