Compare commits

..

2 Commits

Author SHA1 Message Date
Ahrav Dutta 52b74f9727 fix. 2023-09-02 17:59:23 -07:00
Ahrav Dutta 607997c4eb PR 39 of 40 2023-08-25 21:41:45 -07:00
32 changed files with 172 additions and 376 deletions
+1 -1
View File
@@ -32,7 +32,7 @@ Have questions? Feedback? Jump in slack or discord and hang out with us
Join our [Slack Community](https://join.slack.com/t/trufflehog-community/shared_invite/zt-pw2qbi43-Aa86hkiimstfdKH9UCpPzQ)
Join the [Secret Scanning Discord](https://discord.gg/8Hzbrnkr7E)
Join the [Secret Scanning Discord](https://discord.gg/sydS6AHTUP)
# :tv: Demo
+2
View File
@@ -43,6 +43,8 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
instanceMatches := instancePat.FindAllStringSubmatch(dataStr, -1)
tokenMatches := accessTokenPat.FindAllStringSubmatch(dataStr, -1)
fmt.Printf("instanceMatches: %v\n", instanceMatches)
for _, instance := range instanceMatches {
if len(instance) != 1 {
continue
+9 -15
View File
@@ -1,10 +1,10 @@
package zapierwebhook
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -13,44 +13,38 @@ import (
type Scanner struct{}
// Ensure the Scanner satisfies the interface at compile time.
var _ detectors.Detector = (*Scanner)(nil)
var (
client = common.SaneHttpClient()
// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
keyPat = regexp.MustCompile(`(https:\/\/hooks\.zapier\.com\/hooks\/catch\/[A-Za-z0-9\/]{16})`)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"hooks.zapier.com/hooks/catch/"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("hooks.zapier.com/hooks/catch/")}
}
// FromData will find and optionally verify ZapierWebhook secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_ZapierWebhook,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
req, err := http.NewRequestWithContext(ctx, "POST", "https://hooks.zapier.com/hooks/catch/"+resMatch, nil)
req, err := http.NewRequestWithContext(ctx, "POST", "https://hooks.zapier.com/hooks/catch/"+string(resMatch), nil)
if err != nil {
continue
}
res, err := client.Do(req)
if err == nil {
defer res.Body.Close()
+18 -24
View File
@@ -1,12 +1,12 @@
package zendeskapi
import (
"bytes"
"context"
b64 "encoding/base64"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -15,7 +15,6 @@ import (
type Scanner struct{}
// Ensure the Scanner satisfies the interface at compile time.
var _ detectors.Detector = (*Scanner)(nil)
var (
@@ -26,38 +25,33 @@ var (
domain = regexp.MustCompile(`\b([a-zA-Z-0-9]{3,16}\.zendesk\.com)\b`)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zendesk"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zendesk")}
}
// FromData will find and optionally verify ZendeskApi secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
tokens := token.FindAllStringSubmatch(dataStr, -1)
domains := domain.FindAllStringSubmatch(dataStr, -1)
emails := email.FindAllStringSubmatch(dataStr, -1)
tokens := token.FindAllSubmatch(data, -1)
domains := domain.FindAllSubmatch(data, -1)
emails := email.FindAllSubmatch(data, -1)
for _, token := range tokens {
if len(token) != 2 {
for _, matchToken := range tokens {
if len(matchToken) != 2 {
continue
}
resMatch := strings.TrimSpace(token[1])
resMatch := bytes.TrimSpace(matchToken[1])
var resDomain string
for _, domain := range domains {
if len(domain) != 2 {
for _, matchDomain := range domains {
if len(matchDomain) != 2 {
continue
}
resDomain = strings.TrimSpace(domain[1])
resDomain := bytes.TrimSpace(matchDomain[1])
for _, email := range emails {
if len(email) != 2 {
for _, matchEmail := range emails {
if len(matchEmail) != 2 {
continue
}
resEmail := strings.TrimSpace(email[1])
resEmail := bytes.TrimSpace(matchEmail[1])
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
continue
@@ -65,13 +59,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_ZendeskApi,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
data := fmt.Sprintf("%s/token:%s", resEmail, resMatch)
data := fmt.Sprintf("%s/token:%s", string(resEmail), string(resMatch))
sEnc := b64.StdEncoding.EncodeToString([]byte(data))
req, err := http.NewRequestWithContext(ctx, "GET", "https://"+resDomain+"/api/v2/users.json", nil)
req, err := http.NewRequestWithContext(ctx, "GET", "https://"+string(resDomain)+"/api/v2/users.json", nil)
if err != nil {
continue
}
+7 -8
View File
@@ -1,10 +1,10 @@
package zenkitapi
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -25,25 +25,24 @@ var (
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zenkit"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zenkit")}
}
// FromData will find and optionally verify ZenkitAPI secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_ZenkitAPI,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -51,7 +50,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
req.Header.Add("Zenkit-API-Key", resMatch)
req.Header.Add("Zenkit-API-Key", string(resMatch))
res, err := client.Do(req)
if err == nil {
defer res.Body.Close()
+7 -15
View File
@@ -1,11 +1,11 @@
package zenrows
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,41 +14,34 @@ import (
type Scanner struct{}
// Ensure the Scanner satisfies the interface at compile time
var _ detectors.Detector = (*Scanner)(nil)
var (
client = common.SaneHttpClient()
// Make sure that your group is surrounded in boundary characters such as below to reduce false positives
keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zenrows"}) + `\b([0-9a-f]{40})\b`)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zenrows"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zenrows")}
}
// FromData will find and optionally verify ZenRows secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_ZenRows,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.zenrows.com/v1/?apikey=%s&url=https://httpbin.org/anything", resMatch), nil)
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.zenrows.com/v1/?apikey=%s&url=https://httpbin.org/anything", string(resMatch)), nil)
if err != nil {
continue
}
@@ -58,7 +51,6 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if res.StatusCode >= 200 && res.StatusCode < 300 {
s1.Verified = true
} else {
// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
continue
}
+8 -16
View File
@@ -1,11 +1,11 @@
package zenscrape
import (
"bytes"
"context"
"io"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,37 +14,30 @@ import (
type Scanner struct{}
// Ensure the Scanner satisfies the interface at compile time.
var _ detectors.Detector = (*Scanner)(nil)
var (
client = common.SaneHttpClient()
// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zenscrape"}) + `\b([0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})\b`)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zenscrape"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zenscrape")}
}
// FromData will find and optionally verify Zenscrape secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_Zenscrape,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -52,7 +45,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
req.Header.Add("apikey", resMatch)
req.Header.Add("apikey", string(resMatch))
res, err := client.Do(req)
if err == nil {
defer res.Body.Close()
@@ -60,9 +53,8 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
body := string(bodyBytes)
if !strings.Contains(body, "Not enough requests.") {
if !bytes.Contains(bodyBytes, []byte("Not enough requests.")) {
s1.Verified = true
} else {
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
+13 -14
View File
@@ -1,11 +1,11 @@
package zenserp
import (
"bytes"
"context"
"io"
"net/http"
"regexp"
"strings"
"time"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
@@ -27,47 +27,46 @@ var (
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zenserp"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zenserp")}
}
// FromData will find and optionally verify Zenserp secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_Zenserp,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", `https://app.zenserp.com/api/v2/search?q="test"&apikey=`+resMatch, nil)
req, err := http.NewRequestWithContext(ctx, "GET", `https://app.zenserp.com/api/v2/search?q="test"&apikey=`+string(resMatch), nil)
if err != nil {
continue
}
res, err := client.Do(req)
if err == nil {
defer res.Body.Close()
bodyBytes, err := io.ReadAll(res.Body)
if err != nil {
continue
}
body := string(bodyBytes)
if strings.Contains(body, "query") {
if bytes.Contains(bodyBytes, []byte("query")) {
s1.Verified = true
} else {
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
continue
}
}
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
continue
}
}
}
+7 -16
View File
@@ -1,11 +1,11 @@
package zeplin
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,37 +14,29 @@ import (
type Scanner struct{}
// Ensure the Scanner satisfies the interface at compile time.
var _ detectors.Detector = (*Scanner)(nil)
var (
client = common.SaneHttpClient()
// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zeplin"}) + `\b([a-zA-Z0-9-.]{350,400})\b`)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zeplin"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zeplin")}
}
// FromData will find and optionally verify Zeplin secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_Zeplin,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -52,14 +44,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", resMatch))
req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", string(resMatch)))
res, err := client.Do(req)
if err == nil {
defer res.Body.Close()
if res.StatusCode >= 200 && res.StatusCode < 300 {
s1.Verified = true
} else {
// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key.
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
continue
}
+7 -9
View File
@@ -1,6 +1,7 @@
package zerobounce
import (
"bytes"
"context"
"io"
"net/http"
@@ -26,29 +27,26 @@ var (
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zerobounce"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zerobounce")}
}
// FromData will find and optionally verify Zerobounce secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_Zerobounce,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", "https://api.zerobounce.net/v1/activity?email=testemail@email.com&api_key="+resMatch, nil)
req, err := http.NewRequestWithContext(ctx, "GET", "https://api.zerobounce.net/v1/activity?email=testemail@email.com&api_key="+string(resMatch), nil)
if err != nil {
continue
}
+14 -25
View File
@@ -1,12 +1,12 @@
package zipapi
import (
"bytes"
"context"
b64 "encoding/base64"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -15,57 +15,49 @@ import (
type Scanner struct{}
// Ensure the Scanner satisfies the interface at compile time.
var _ detectors.Detector = (*Scanner)(nil)
var (
client = common.SaneHttpClient()
// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zipapi"}) + `\b([0-9a-z]{32})\b`)
emailPat = regexp.MustCompile(`\b([a-zA-Z0-9._-]+@[a-zA-Z0-9._-]+\.[a-z]+)\b`)
pwordPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zipapi"}) + `\b([a-zA-Z0-9!=@#$%^]{7,})`)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zipapi"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zipapi")}
}
// FromData will find and optionally verify Zipapi secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
emailMatches := emailPat.FindAllStringSubmatch(dataStr, -1)
pwordMatches := pwordPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
emailMatches := emailPat.FindAllSubmatch(data, -1)
pwordMatches := pwordPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
for _, emailMatch := range emailMatches {
if len(emailMatch) != 2 {
continue
}
resEmail := strings.TrimSpace(emailMatch[1])
resEmail := bytes.TrimSpace(emailMatch[1])
for _, pwordMatch := range pwordMatches {
if len(pwordMatch) != 2 {
continue
}
resPword := strings.TrimSpace(pwordMatch[1])
resPword := bytes.TrimSpace(pwordMatch[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_ZipAPI,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
data := fmt.Sprintf("%s:%s", resEmail, resPword)
sEnc := b64.StdEncoding.EncodeToString([]byte(data))
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://service.zipapi.us/zipcode/90210/?X-API-KEY=%s", resMatch), nil)
data := append(resEmail, []byte(":")...)
data = append(data, resPword...)
sEnc := b64.StdEncoding.EncodeToString(data)
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://service.zipapi.us/zipcode/90210/?X-API-KEY=%s", string(resMatch)), nil)
if err != nil {
continue
}
@@ -77,19 +69,16 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if res.StatusCode >= 200 && res.StatusCode < 300 {
s1.Verified = true
} else {
// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key.
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
continue
}
}
}
}
results = append(results, s1)
}
}
}
return results, nil
}
+11 -19
View File
@@ -1,11 +1,11 @@
package zipbooks
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,48 +14,41 @@ import (
type Scanner struct{}
// Ensure the Scanner satisfies the interface at compile time.
var _ detectors.Detector = (*Scanner)(nil)
var (
client = common.SaneHttpClient()
// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
emailPat = regexp.MustCompile(`\b([a-zA-Z0-9._-]+@[a-zA-Z0-9._-]+\.[a-z]+)\b`)
pwordPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zipbooks", "password"}) + `\b([a-zA-Z0-9!=@#$%^]{8,})`)
pwordPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zipbooks", "password"}) + `\b([a-zA-Z0-9!=@#$%^]{8,})\b`)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zipbooks"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zipbooks")}
}
// FromData will find and optionally verify Zipbooks secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
emailMatches := emailPat.FindAllSubmatch(data, -1)
pwordMatches := pwordPat.FindAllSubmatch(data, -1)
matches := emailPat.FindAllStringSubmatch(dataStr, -1)
pwordMatches := pwordPat.FindAllStringSubmatch(dataStr, -1)
for _, match := range matches {
for _, match := range emailMatches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
for _, pwordMatch := range pwordMatches {
if len(pwordMatch) != 2 {
continue
}
resPword := strings.TrimSpace(pwordMatch[1])
resPword := bytes.TrimSpace(pwordMatch[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_ZipBooks,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
payload := strings.NewReader(fmt.Sprintf(`{"email": "%s", "password": "%s"}`, resMatch, resPword))
payload := bytes.NewReader([]byte(fmt.Sprintf(`{"email": "%s", "password": "%s"}`, string(resMatch), string(resPword))))
req, err := http.NewRequestWithContext(ctx, "POST", "https://api.zipbooks.com/v2/auth/login", payload)
if err != nil {
continue
@@ -67,7 +60,6 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if res.StatusCode >= 200 && res.StatusCode < 300 {
s1.Verified = true
} else {
// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key.
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
continue
}
+6 -7
View File
@@ -1,11 +1,11 @@
package zipcodeapi
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,25 +26,24 @@ var (
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zipcodeapi"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zipcodeapi")}
}
// FromData will find and optionally verify ZipCodeAPI secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_ZipCodeAPI,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
+7 -16
View File
@@ -1,10 +1,10 @@
package zipcodebase
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -13,37 +13,29 @@ import (
type Scanner struct{}
// Ensure the Scanner satisfies the interface at compile time
var _ detectors.Detector = (*Scanner)(nil)
var (
client = common.SaneHttpClient()
// Make sure that your group is surrounded in boundary characters such as below to reduce false positives
keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zipcodebase"}) + `\b([0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12})\b`)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zipcodebase"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zipcodebase")}
}
// FromData will find and optionally verify Zipcodebase secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_Zipcodebase,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -52,14 +44,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
continue
}
req.Header.Add("Accept", "application/vnd.zipcodebase+json; version=3")
req.Header.Add("apikey", resMatch)
req.Header.Add("apikey", string(resMatch))
res, err := client.Do(req)
if err == nil {
defer res.Body.Close()
if res.StatusCode >= 200 && res.StatusCode < 300 {
s1.Verified = true
} else {
// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
continue
}
+7 -15
View File
@@ -1,10 +1,10 @@
package zonkafeedback
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -13,37 +13,30 @@ import (
type Scanner struct{}
// Ensure the Scanner satisfies the interface at compile time.
var _ detectors.Detector = (*Scanner)(nil)
var (
client = common.SaneHttpClient()
// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zonka"}) + `\b([A-Za-z0-9]{36})\b`)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zonka"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zonka")}
}
// FromData will find and optionally verify ZonkaFeedback secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_ZonkaFeedback,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -51,14 +44,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
req.Header.Add("Z-API-TOKEN", resMatch)
req.Header.Add("Z-API-TOKEN", string(resMatch))
res, err := client.Do(req)
if err == nil {
defer res.Body.Close()
if res.StatusCode >= 200 && res.StatusCode < 300 {
s1.Verified = true
} else {
// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key.
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
continue
}
+13 -20
View File
@@ -1,11 +1,11 @@
package zulipchat
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -14,61 +14,55 @@ import (
type Scanner struct{}
// Ensure the Scanner satisfies the interface at compile time.
var _ detectors.Detector = (*Scanner)(nil)
var (
client = common.SaneHttpClient()
// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zulipchat"}) + common.BuildRegex(common.AlphaNumPattern, "", 32))
idPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zulipchat"}) + common.EmailPattern)
domainPat = regexp.MustCompile(detectors.PrefixRegex([]string{"zulipchat", "domain"}) + common.SubDomainPattern)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"zulipchat"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("zulipchat")}
}
// FromData will find and optionally verify ZulipChat secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
idMatches := idPat.FindAllStringSubmatch(dataStr, -1)
domainMatches := domainPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
idMatches := idPat.FindAllSubmatch(data, -1)
domainMatches := domainPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
for _, idMatch := range idMatches {
// getting the last word of the string
resIdMatch := strings.TrimSpace(idMatch[0][strings.LastIndex(idMatch[0], " ")+1:])
resIdMatch := bytes.TrimSpace(idMatch[0][bytes.LastIndex(idMatch[0], []byte(" "))+1:])
for _, domainMatch := range domainMatches {
if len(domainMatch) != 2 {
continue
}
resDomainMatch := strings.TrimSpace(domainMatch[1])
resDomainMatch := bytes.TrimSpace(domainMatch[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_ZulipChat,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://%s.zulipchat.com/api/v1/users", resDomainMatch), nil)
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://%s.zulipchat.com/api/v1/users", string(resDomainMatch)), nil)
if err != nil {
continue
}
req.Header.Add("Content-Type", "application/json")
req.SetBasicAuth(resIdMatch, resMatch)
req.SetBasicAuth(string(resIdMatch), string(resMatch))
res, err := client.Do(req)
if err == nil {
@@ -76,7 +70,6 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if res.StatusCode >= 200 && res.StatusCode < 300 {
s1.Verified = true
} else {
// This function will check false positives for common test words, but also it will make sure the key appears 'random' enough to be a real key.
if detectors.IsKnownFalsePositive(resIdMatch, detectors.DefaultFalsePositives, true) {
continue
}
+1 -9
View File
@@ -2,10 +2,6 @@ package engine
import (
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/envoyapikey"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/huggingface"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/salesforce"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/snowflake"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/trufflehogenterprise"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/abbysale"
@@ -291,7 +287,6 @@ import (
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/getresponse"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/getsandbox"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/github"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/github_oauth2"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/github_old"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/githubapp"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/gitlab"
@@ -561,6 +556,7 @@ import (
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/satismeterwritekey"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/saucelabs"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/scalewaykey"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/github_oauth2"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/scalr"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/scrapeowl"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors/scraperapi"
@@ -1536,10 +1532,6 @@ func DefaultDetectors() []detectors.Detector {
couchbase.Scanner{},
envoyapikey.Scanner{},
github_oauth2.Scanner{},
snowflake.Scanner{},
huggingface.Scanner{},
trufflehogenterprise.Scanner{},
salesforce.Scanner{},
}
}
+5 -5
View File
@@ -308,18 +308,18 @@ func Start(ctx context.Context, options ...EngineOption) (*Engine, error) {
// build ahocorasick prefilter for efficient string matching
// on keywords
keywords := []string{}
var keywords [][]byte
for _, d := range e.detectors[false] {
for _, kw := range d.Keywords() {
keywords = append(keywords, strings.ToLower(kw))
keywords = append(keywords, bytes.ToLower(kw))
}
}
for _, d := range e.detectors[true] {
for _, kw := range d.Keywords() {
keywords = append(keywords, strings.ToLower(kw))
keywords = append(keywords, bytes.ToLower(kw))
}
}
e.prefilter = *ahocorasick.NewTrieBuilder().AddStrings(keywords).Build()
e.prefilter = *ahocorasick.NewTrieBuilder().AddPatterns(keywords).Build()
ctx.Logger().V(3).Info("loaded decoders", "count", len(e.decoders))
ctx.Logger().V(3).Info("loaded detectors",
@@ -466,7 +466,7 @@ func (e *Engine) detectorWorker(ctx context.Context) {
for _, detector := range detectorsSet {
chunkContainsKeyword := false
for _, kw := range detector.Keywords() {
if _, ok := matchedKeywords[strings.ToLower(kw)]; ok {
if _, ok := matchedKeywords[strings.ToLower(string(kw))]; ok {
chunkContainsKeyword = true
break
}
+23 -24
View File
@@ -29,8 +29,6 @@ var (
maxDepth = 5
maxSize = 250 * 1024 * 1024 // 20MB
maxTimeout = time.Duration(30) * time.Second
defaultBufferSize = 512
)
// Ensure the Archive satisfies the interfaces at compile time.
@@ -64,7 +62,7 @@ func SetArchiveMaxTimeout(timeout time.Duration) {
// FromFile extracts the files from an archive.
func (a *Archive) FromFile(originalCtx context.Context, data io.Reader) chan []byte {
archiveChan := make(chan []byte, defaultBufferSize)
archiveChan := make(chan []byte, 512)
go func() {
ctx, cancel := context.WithTimeout(originalCtx, maxTimeout)
logger := logContext.AddLogger(ctx).Logger()
@@ -185,28 +183,29 @@ func (a *Archive) ReadToMax(ctx context.Context, reader io.Reader) (data []byte,
logger.Error(err, "Panic occurred when reading archive")
}
}()
if common.IsDone(ctx) {
return nil, ctx.Err()
fileContent := bytes.Buffer{}
logger.V(5).Info("Remaining buffer capacity", "bytes", maxSize-a.size)
for i := 0; i <= maxSize/512; i++ {
if common.IsDone(ctx) {
return nil, ctx.Err()
}
fileChunk := make([]byte, 512)
bRead, err := reader.Read(fileChunk)
if err != nil && !errors.Is(err, io.EOF) {
return []byte{}, err
}
a.size += bRead
if len(fileChunk) > 0 {
fileContent.Write(fileChunk[0:bRead])
}
if bRead < 512 {
return fileContent.Bytes(), nil
}
if a.size >= maxSize && bRead == 512 {
logger.V(2).Info("Max archive size reached.")
return fileContent.Bytes(), nil
}
}
var fileContent bytes.Buffer
// Create a limited reader to ensure we don't read more than the max size.
lr := io.LimitReader(reader, int64(maxSize))
// Using io.CopyBuffer for performance advantages. Though buf is mandatory
// for the method, due to the internal implementation of io.CopyBuffer, when
// *bytes.Buffer implements io.WriterTo or io.ReaderFrom, the provided buf
// is simply ignored. Thus, we can pass nil for the buf parameter.
_, err = io.CopyBuffer(&fileContent, lr, nil)
if err != nil && !errors.Is(err, io.EOF) {
return nil, err
}
if fileContent.Len() == maxSize {
logger.V(2).Info("Max archive size reached.")
}
return fileContent.Bytes(), nil
}
-53
View File
@@ -1,7 +1,6 @@
package handlers
import (
"bytes"
"context"
"io"
"net/http"
@@ -127,58 +126,6 @@ func TestHandleFile(t *testing.T) {
assert.Equal(t, 1, len(ch))
}
func TestReadToMax(t *testing.T) {
tests := []struct {
name string
input []byte
expected []byte
}{
{
name: "read full content within maxSize",
input: []byte("abcdefg"),
expected: []byte("abcdefg"),
},
{
name: "read content larger than maxSize",
input: make([]byte, maxSize+10), // this creates a byte slice 10 bytes larger than maxSize
expected: make([]byte, maxSize),
},
{
name: "empty input",
input: []byte(""),
expected: []byte(""),
},
}
a := &Archive{}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
reader := bytes.NewReader(tt.input)
output, err := a.ReadToMax(context.Background(), reader)
assert.Nil(t, err)
assert.Equal(t, tt.expected, output)
})
}
}
func BenchmarkReadToMax(b *testing.B) {
data := bytes.Repeat([]byte("a"), 1024*1000) // 1MB of data.
reader := bytes.NewReader(data)
a := &Archive{}
b.ResetTimer()
for i := 0; i < b.N; i++ {
b.StartTimer()
_, _ = a.ReadToMax(context.Background(), reader)
b.StopTimer()
_, _ = reader.Seek(0, 0) // Reset the reader position.
a.size = 0 // Reset archive size.
}
}
func TestExtractDebContent(t *testing.T) {
// Open the sample .deb file from the testdata folder.
file, err := os.Open("testdata/test.deb")
+1 -1
View File
@@ -133,7 +133,7 @@ func BranchHeads(repo *gogit.Repository) (map[string]*object.Commit, error) {
}
headCommit, err := repo.CommitObject(*headHash)
if err != nil {
logger.Error(err, "unable to get commit", "head_hash", headHash.String())
logger.Error(err, "unable to get commit", "commit", headCommit.String())
return nil
}
branches[branchName] = headCommit
+1 -1
View File
@@ -20,7 +20,7 @@ const (
// Chunker takes a chunk and splits it into chunks of ChunkSize.
func Chunker(originalChunk *Chunk) chan *Chunk {
chunkChan := make(chan *Chunk, 1)
chunkChan := make(chan *Chunk)
go func() {
defer close(chunkChan)
if len(originalChunk.Data) <= TotalChunkSize {
-1
View File
@@ -238,7 +238,6 @@ func (s *Source) chunkAction(ctx context.Context, proj project, bld build, act a
SourceType: s.Type(),
SourceName: s.name,
SourceID: s.SourceID(),
JobID: s.JobID(),
Data: removeCircleSha1Line(data.Bytes()),
SourceMetadata: &source_metadatapb.MetaData{
Data: &source_metadatapb.MetaData_Circleci{
-1
View File
@@ -174,7 +174,6 @@ func (s *Source) Chunks(ctx context.Context, chunksChan chan *sources.Chunk) err
SourceType: s.Type(),
SourceName: s.name,
SourceID: s.SourceID(),
JobID: s.JobID(),
Data: file.Bytes(),
SourceMetadata: &source_metadatapb.MetaData{
Data: &source_metadatapb.MetaData_Docker{
-2
View File
@@ -161,7 +161,6 @@ func (s *Source) scanFile(ctx context.Context, path string, chunksChan chan *sou
SourceType: s.Type(),
SourceName: s.name,
SourceID: s.SourceID(),
JobID: s.JobID(),
SourceMetadata: &source_metadatapb.MetaData{
Data: &source_metadatapb.MetaData_Filesystem{
Filesystem: &source_metadatapb.Filesystem{
@@ -192,7 +191,6 @@ func (s *Source) scanFile(ctx context.Context, path string, chunksChan chan *sou
SourceType: s.Type(),
SourceName: s.name,
SourceID: s.SourceID(),
JobID: s.JobID(),
Data: data.Bytes(),
SourceMetadata: &source_metadatapb.MetaData{
Data: &source_metadatapb.MetaData_Filesystem{
-1
View File
@@ -324,7 +324,6 @@ func (s *Source) processObject(ctx context.Context, o object) error {
chunkSkel := &sources.Chunk{
SourceName: s.name,
SourceType: s.Type(),
JobID: s.JobID(),
SourceID: s.sourceId,
Verify: s.verify,
SourceMetadata: &source_metadatapb.MetaData{
-7
View File
@@ -446,7 +446,6 @@ func (s *Git) ScanCommits(ctx context.Context, repo *git.Repository, path string
chunkSkel := &sources.Chunk{
SourceName: s.sourceName,
SourceID: s.sourceID,
JobID: s.jobID,
SourceType: s.sourceType,
SourceMetadata: metadata,
Verify: s.verify,
@@ -465,7 +464,6 @@ func (s *Git) ScanCommits(ctx context.Context, repo *git.Repository, path string
chunksChan <- &sources.Chunk{
SourceName: s.sourceName,
SourceID: s.sourceID,
JobID: s.jobID,
SourceType: s.sourceType,
SourceMetadata: metadata,
Data: diff.Content.Bytes(),
@@ -492,7 +490,6 @@ func (s *Git) gitChunk(ctx context.Context, diff gitparse.Diff, fileName, email,
chunksChan <- &sources.Chunk{
SourceName: s.sourceName,
SourceID: s.sourceID,
JobID: s.jobID,
SourceType: s.sourceType,
SourceMetadata: metadata,
Data: append([]byte{}, newChunkBuffer.Bytes()...),
@@ -507,7 +504,6 @@ func (s *Git) gitChunk(ctx context.Context, diff gitparse.Diff, fileName, email,
chunksChan <- &sources.Chunk{
SourceName: s.sourceName,
SourceID: s.sourceID,
JobID: s.jobID,
SourceType: s.sourceType,
SourceMetadata: metadata,
Data: line,
@@ -527,7 +523,6 @@ func (s *Git) gitChunk(ctx context.Context, diff gitparse.Diff, fileName, email,
chunksChan <- &sources.Chunk{
SourceName: s.sourceName,
SourceID: s.sourceID,
JobID: s.jobID,
SourceType: s.sourceType,
SourceMetadata: metadata,
Data: append([]byte{}, newChunkBuffer.Bytes()...),
@@ -593,7 +588,6 @@ func (s *Git) ScanStaged(ctx context.Context, repo *git.Repository, path string,
chunkSkel := &sources.Chunk{
SourceName: s.sourceName,
SourceID: s.sourceID,
JobID: s.jobID,
SourceType: s.sourceType,
SourceMetadata: metadata,
Verify: s.verify,
@@ -608,7 +602,6 @@ func (s *Git) ScanStaged(ctx context.Context, repo *git.Repository, path string,
chunksChan <- &sources.Chunk{
SourceName: s.sourceName,
SourceID: s.sourceID,
JobID: s.jobID,
SourceType: s.sourceType,
SourceMetadata: metadata,
Data: diff.Content.Bytes(),
+2 -7
View File
@@ -149,16 +149,14 @@ func (s *Source) newFilteredRepoCache(c cache.Cache, include, exclude []string)
for _, ig := range include {
g, err := glob.Compile(ig)
if err != nil {
s.log.V(1).Info("invalid include glob", "include_value", ig, "err", err)
continue
s.log.V(1).Info("invalid include glob", "glob", g, "err", err)
}
includeGlobs = append(includeGlobs, g)
}
for _, eg := range exclude {
g, err := glob.Compile(eg)
if err != nil {
s.log.V(1).Info("invalid exclude glob", "exclude_value", eg, "err", err)
continue
s.log.V(1).Info("invalid exclude glob", "glob", g, "err", err)
}
excludeGlobs = append(excludeGlobs, g)
}
@@ -1225,7 +1223,6 @@ func (s *Source) chunkIssueComments(ctx context.Context, repo, repoPath string,
chunk := &sources.Chunk{
SourceName: s.name,
SourceID: s.SourceID(),
JobID: s.JobID(),
SourceType: s.Type(),
SourceMetadata: &source_metadatapb.MetaData{
Data: &source_metadatapb.MetaData_Github{
@@ -1259,7 +1256,6 @@ func (s *Source) chunkPullRequestComments(ctx context.Context, repo string, comm
SourceName: s.name,
SourceID: s.SourceID(),
SourceType: s.Type(),
JobID: s.JobID(),
SourceMetadata: &source_metadatapb.MetaData{
Data: &source_metadatapb.MetaData_Github{
Github: &source_metadatapb.Github{
@@ -1291,7 +1287,6 @@ func (s *Source) chunkGistComments(ctx context.Context, gistUrl string, comments
SourceName: s.name,
SourceID: s.SourceID(),
SourceType: s.Type(),
JobID: s.JobID(),
SourceMetadata: &source_metadatapb.MetaData{
Data: &source_metadatapb.MetaData_Github{
Github: &source_metadatapb.Github{
-1
View File
@@ -376,7 +376,6 @@ func (s *Source) pageChunker(ctx context.Context, client *s3.S3, chunksChan chan
SourceType: s.Type(),
SourceName: s.name,
SourceID: s.SourceID(),
JobID: s.JobID(),
SourceMetadata: &source_metadatapb.MetaData{
Data: &source_metadatapb.MetaData_S3{
S3: &source_metadatapb.S3{
+2 -20
View File
@@ -36,10 +36,7 @@ type SourceManager struct {
handles map[handle]sourceInfo
handlesLock sync.Mutex
// Pool limiting the amount of concurrent sources running.
pool errgroup.Group
poolLimit int
currentRunningCount int32
// Max number of units to scan concurrently per source.
pool errgroup.Group
concurrentUnits int
// Run the sources using source unit enumeration / chunking if available.
useSourceUnits bool
@@ -71,10 +68,7 @@ func WithReportHook(hook JobProgressHook) func(*SourceManager) {
// WithConcurrentSources limits the concurrent number of sources a manager can run.
func WithConcurrentSources(concurrency int) func(*SourceManager) {
return func(mgr *SourceManager) {
mgr.pool.SetLimit(concurrency)
mgr.poolLimit = concurrency
}
return func(mgr *SourceManager) { mgr.pool.SetLimit(concurrency) }
}
// WithBufferedOutput sets the size of the buffer used for the Chunks() channel.
@@ -173,8 +167,6 @@ func (s *SourceManager) asyncRun(ctx context.Context, handle handle) (JobProgres
ctx, cancel := context.WithCancel(ctx)
progress := NewJobProgress(jobID, int64(handle), sourceName, WithHooks(s.hooks...), WithCancel(cancel))
s.pool.Go(func() error {
atomic.AddInt32(&s.currentRunningCount, 1)
defer atomic.AddInt32(&s.currentRunningCount, -1)
ctx := context.WithValues(ctx,
"job_id", jobID,
"source_manager_worker_id", common.RandomID(5),
@@ -215,16 +207,6 @@ func (s *SourceManager) ScanChunk(chunk *Chunk) {
s.outputChunks <- chunk
}
// AvailableCapacity returns the number of concurrent jobs the manager can
// accommodate at this time. If there is no limit, -1 is returned.
func (s *SourceManager) AvailableCapacity() int {
if s.poolLimit == 0 {
return -1
}
runCount := atomic.LoadInt32(&s.currentRunningCount)
return s.poolLimit - int(runCount)
}
// preflightChecks is a helper method to check the Manager or the context isn't
// done and that the handle is valid.
func (s *SourceManager) preflightChecks(ctx context.Context, handle handle) error {
-21
View File
@@ -317,24 +317,3 @@ func TestSourceManagerCancelRun(t *testing.T) {
assert.Error(t, ref.Snapshot().FatalError())
assert.True(t, errors.Is(ref.Snapshot().FatalError(), returnedErr))
}
func TestSourceManagerAvailableCapacity(t *testing.T) {
mgr := NewManager(WithConcurrentSources(1337))
start, end := make(chan struct{}), make(chan struct{})
handle, err := enrollDummy(mgr, callbackChunker{func(context.Context, chan *Chunk) error {
start <- struct{}{} // Send start signal.
<-end // Wait for end signal.
return nil
}})
assert.NoError(t, err)
assert.Equal(t, 1337, mgr.AvailableCapacity())
ref, err := mgr.ScheduleRun(context.Background(), handle)
assert.NoError(t, err)
<-start // Wait for start signal.
assert.Equal(t, 1336, mgr.AvailableCapacity())
end <- struct{}{} // Send end signal.
<-ref.Done() // Wait for the job to finish.
assert.Equal(t, 1337, mgr.AvailableCapacity())
}
-2
View File
@@ -272,7 +272,6 @@ func (s *Source) monitorConnection(ctx context.Context, conn net.Conn, chunksCha
SourceName: s.syslog.sourceName,
SourceID: s.syslog.sourceID,
SourceType: s.syslog.sourceType,
JobID: s.JobID(),
SourceMetadata: metadata,
Data: input,
Verify: s.verify,
@@ -314,7 +313,6 @@ func (s *Source) acceptUDPConnections(ctx context.Context, netListener net.Packe
chunksChan <- &sources.Chunk{
SourceName: s.syslog.sourceName,
SourceID: s.syslog.sourceID,
JobID: s.JobID(),
SourceType: s.syslog.sourceType,
SourceMetadata: metadata,
Data: input,