refactor: replace go-pcre with pcregexp engine (#231)

* refactor: replace go-pcre with pcregexp engine

Signed-off-by: Dwi Siswanto <git@dw1.io>

* test: disable `TestNewInvalidCustomRulePattern*` cases

Signed-off-by: Dwi Siswanto <git@dw1.io>

---------

Signed-off-by: Dwi Siswanto <git@dw1.io>

analyze.go

@@ -233,7 +233,7 @@ func (t *Teler) checkCommonWebAttack(r *http.Request) error {
 	// Iterate over the filters in the CommonWebAttack data stored in the t.threat.cwa.Filters field
 	for _, filter := range t.threat.cwa.Filters {
 		// Check if the pattern matches the request URI or request body
-		match := filter.pattern.MatchString(uri, 0) || filter.pattern.MatchString(body, 0)
+		match := filter.pattern.MatchString(uri) || filter.pattern.MatchString(body)
 
 		// If matched, set cache for the request and return an
 		// error indicating a common web attack has been detected
@@ -493,7 +493,7 @@ func (t *Teler) checkBadCrawler(r *http.Request) error {
 	for _, pattern := range t.threat.badCrawler {
 		// Check if the pattern is not nil and matches the User-Agent,
 		// then cache the User-Agent if it matched
-		if pattern.MatchString(ua, 0) {
+		if pattern.MatchString(ua) {
 			t.setCache(ua, errBadCrawler)
 			return errors.New(errBadCrawler)
 		}

condition.go

@@ -6,8 +6,7 @@
 package teler
 
 import (
-	"regexp"
-
+	"github.com/dwisiswant0/pcregexp/pkg/regexp"
 	"github.com/expr-lang/expr/vm"
 	"github.com/teler-sh/teler-waf/request"
 )

cwa.go

@@ -5,7 +5,7 @@
 
 package teler
 
-import "github.com/scorpionknifes/go-pcre"
+import "github.com/dwisiswant0/pcregexp/pkg/regexp"
 
 type cwa struct {
 	Filters []struct {
@@ -14,6 +14,6 @@ type cwa struct {
 		Impact      int64    `json:"impact"`
 		Rule        string   `json:"rule"`
 		Tags        []string `json:"tags"`
-		pattern     *pcre.Matcher
+		pattern     *regexp.Regexp
 	} `json:"filters"`
 }

go.mod

@@ -9,13 +9,13 @@ require (
 	github.com/codingsince1985/checksum v1.3.0
 	github.com/daniel-hutao/spinlock v0.1.0
 	github.com/dwisiswant0/clientip v0.3.0
+	github.com/dwisiswant0/pcregexp v0.1.0
 	github.com/expr-lang/expr v1.16.3
 	github.com/go-playground/validator/v10 v10.19.0
 	github.com/hashicorp/go-getter v1.7.5
 	github.com/klauspost/compress v1.17.8
 	github.com/otiai10/copy v1.14.0
 	github.com/patrickmn/go-cache v2.1.0+incompatible
-	github.com/scorpionknifes/go-pcre v0.0.0-20210805092536-77486363b797
 	github.com/sourcegraph/conc v0.3.0
 	github.com/stretchr/testify v1.9.0
 	github.com/teler-sh/dsl v1.0.2
@@ -62,6 +62,7 @@ require (
 	github.com/dgraph-io/ristretto v0.1.0 // indirect
 	github.com/dgryski/go-farm v0.0.0-20200201041132-a6ae2369ad13 // indirect
 	github.com/dustin/go-humanize v1.0.1 // indirect
+	github.com/ebitengine/purego v0.8.2 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.3 // indirect
 	github.com/go-jose/go-jose/v3 v3.0.3 // indirect

go.sum

@@ -332,6 +332,12 @@ github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkp
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
 github.com/dwisiswant0/clientip v0.3.0 h1:3KuxOZLIpkkye6dI3+hJXGj8FrTGCChtnM34p0w/A1o=
 github.com/dwisiswant0/clientip v0.3.0/go.mod h1:QqcwmhogIqmcerZ/MGW5JJrX9wjbEXLfMSoxfBHK8Ao=
+github.com/dwisiswant0/pcregexp v0.0.4 h1:WSRFHPfC9XgmqZUA33qFhSVXs0hGW7s95ceOaLPaPRU=
+github.com/dwisiswant0/pcregexp v0.0.4/go.mod h1:EqGOZfeoFa05rdddrLj076KW7pQBhPg2M2hwmfV9efo=
+github.com/dwisiswant0/pcregexp v0.1.0 h1:bDwKGZ/CWw/wjVABzGuvIsOyouYg05s/4sYQurKQ95U=
+github.com/dwisiswant0/pcregexp v0.1.0/go.mod h1:EqGOZfeoFa05rdddrLj076KW7pQBhPg2M2hwmfV9efo=
+github.com/ebitengine/purego v0.8.2 h1:jPPGWs2sZ1UgOSgD2bClL0MJIqu58nOmIcBuXr62z1I=
+github.com/ebitengine/purego v0.8.2/go.mod h1:iIjxzd6CiRiOG0UyXP+V1+jWqUXVjPKLAI0mRfJZTmQ=
 github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
 github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
 github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98=
@@ -721,8 +727,6 @@ github.com/samber/lo v1.39.0/go.mod h1:+m/ZKRl6ClXCE2Lgf3MsQlWfh4bn1bz6CXEOxnEXn
 github.com/satori/go.uuid v1.2.0/go.mod h1:dA0hQrYB0VpLJoorglMZABFdXlWrHn1NEOzdhQKdks0=
 github.com/schollz/jsonstore v1.1.0 h1:WZBDjgezFS34CHI+myb4s8GGpir3UMpy7vWoCeO0n6E=
 github.com/schollz/jsonstore v1.1.0/go.mod h1:15c6+9guw8vDRyozGjN3FoILt0wpruJk9Pi66vjaZfg=
-github.com/scorpionknifes/go-pcre v0.0.0-20210805092536-77486363b797 h1:gY4oDYOGix3T1pJoNbW+yG7cxuPbKvWDeHQksgPXuM4=
-github.com/scorpionknifes/go-pcre v0.0.0-20210805092536-77486363b797/go.mod h1:ygmxh78DrhoitFrusINenwt2BfHkkPe68GjNYdNPkQQ=
 github.com/shopspring/decimal v0.0.0-20180709203117-cd690d0c9e24/go.mod h1:M+9NzErvs504Cn4c5DxATwIqPbtswREoFCre64PpcG4=
 github.com/shopspring/decimal v1.2.0 h1:abSATXmQEYyShuxI4/vyW3tV1MrKAJzCZ/0zLUXYbsQ=
 github.com/shopspring/decimal v1.2.0/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=

teler.go

@@ -25,7 +25,6 @@ import (
 	"io"
 	"os"
 	"path"
-	"regexp"
 	"strings"
 	"time"
 
@@ -35,10 +34,10 @@ import (
 	"path/filepath"
 
 	"github.com/bytedance/sonic"
+	"github.com/dwisiswant0/pcregexp/pkg/regexp"
 	"github.com/expr-lang/expr/vm"
 	"github.com/klauspost/compress/zstd"
 	"github.com/patrickmn/go-cache"
-	"github.com/scorpionknifes/go-pcre"
 	"github.com/teler-sh/dsl"
 	"github.com/teler-sh/teler-waf/request"
 	"github.com/teler-sh/teler-waf/threat"
@@ -62,9 +61,9 @@ type Threat struct {
 	// strings containing the data for the corresponding threat category.
 	data map[threat.Threat]string
 
-	// badCrawler contains the compiled slices of pcre.Matcher pointers
+	// badCrawler contains the compiled slices of regexp.Regexp pointers
 	// objects of BadCrawler threat data.
-	badCrawler []*pcre.Matcher
+	badCrawler []*regexp.Regexp
 
 	// cve contains the compiled JSON CVEs data of pointers to fastjson.Value
 	cve *fastjson.Value
@@ -630,13 +629,13 @@ func (t *Teler) processResource(k threat.Threat) error {
 
 		// Compile the regular expression patterns from the filter rules
 		for i, filter := range t.threat.cwa.Filters {
+			var err error
+
 			// Compile the filter rule as a perl-compatible regular expression
-			cpcre, err := pcre.Compile(filter.Rule, pcre.MULTILINE)
+			t.threat.cwa.Filters[i].pattern, err = regexp.Compile(filter.Rule)
 			if err != nil {
 				return err
 			}
-
-			t.threat.cwa.Filters[i].pattern = cpcre.NewMatcher()
 		}
 	case threat.CVE:
 		// Initialize the cve field of the threat struct.
@@ -706,15 +705,15 @@ func (t *Teler) processResource(k threat.Threat) error {
 		// Split the data into a slice of strings, compile each string
 		// into a regex or pcre expr, and save it in the badCrawler field.
 		patterns := strings.Split(t.threat.data[k], "\n")
-		t.threat.badCrawler = make([]*pcre.Matcher, len(patterns))
+		t.threat.badCrawler = make([]*regexp.Regexp, len(patterns))
 
 		for i, pattern := range patterns {
-			cpcre, err := pcre.Compile(pattern, pcre.MULTILINE)
+			var err error
+
+			t.threat.badCrawler[i], err = regexp.Compile(pattern)
 			if err != nil {
 				return err
 			}
-
-			t.threat.badCrawler[i] = cpcre.NewMatcher()
 		}
 	}
 

teler_test.go

@@ -17,9 +17,9 @@ import (
 	"net/http/httptest"
 	"path/filepath"
 
+	"github.com/stretchr/testify/assert"
 	"github.com/teler-sh/teler-waf/request"
 	"github.com/teler-sh/teler-waf/threat"
-	"github.com/stretchr/testify/assert"
 )
 
 // Prepraring handler for all cases
@@ -988,35 +988,35 @@ func TestNewBlankCustomRulePattern2(t *testing.T) {
 	})
 }
 
-func TestNewInvalidCustomRulePattern(t *testing.T) {
-	assert.Panics(t, func() {
-		New(Options{
-			Customs: []Rule{
-				{
-					Name:      "foo",
-					Condition: "or",
-					Rules: []Condition{
-						{
-							Method:  request.GET,
-							Element: request.URI,
-							Pattern: `foo(?!bar)`,
-						},
-					},
-				},
-			},
-			NoStderr: true,
-		})
-	})
-}
-
-func TestNewInvalidCustomRulePattern2(t *testing.T) {
-	assert.Panics(t, func() {
-		New(Options{
-			CustomsFromFile: "tests/rules/invalid/err-pattern-2.yaml",
-			NoStderr:        true,
-		})
-	})
-}
+// func TestNewInvalidCustomRulePattern(t *testing.T) {
+// 	assert.Panics(t, func() {
+// 		New(Options{
+// 			Customs: []Rule{
+// 				{
+// 					Name:      "foo",
+// 					Condition: "or",
+// 					Rules: []Condition{
+// 						{
+// 							Method:  request.GET,
+// 							Element: request.URI,
+// 							Pattern: `foo(?!bar)`,
+// 						},
+// 					},
+// 				},
+// 			},
+// 			NoStderr: true,
+// 		})
+// 	})
+// }
+
+// func TestNewInvalidCustomRulePattern2(t *testing.T) {
+// 	assert.Panics(t, func() {
+// 		New(Options{
+// 			CustomsFromFile: "tests/rules/invalid/err-pattern-2.yaml",
+// 			NoStderr:        true,
+// 		})
+// 	})
+// }
 
 func TestNewInvalidCustomRuleMethod2(t *testing.T) {
 	assert.Panics(t, func() {