Compare commits

..

1 Commits

Author SHA1 Message Date
Ahrav Dutta 31ce55f6fc PR 0 of 40 2023-08-25 21:39:47 -07:00
37 changed files with 206 additions and 369 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
+8 -3
View File
@@ -8,11 +8,12 @@ import (
"regexp"
"strings"
"golang.org/x/sync/errgroup"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
"github.com/trufflesecurity/trufflehog/v3/pkg/pb/custom_detectorspb"
"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
"golang.org/x/sync/errgroup"
)
// The maximum number of matches from one chunk. This const is used when
@@ -180,8 +181,12 @@ func (c *customRegexWebhook) createResults(ctx context.Context, match map[string
}
}
func (c *customRegexWebhook) Keywords() []string {
return c.GetKeywords()
func (c *customRegexWebhook) Keywords() [][]byte {
keywords := make([][]byte, 0, len(c.GetKeywords()))
for _, keyword := range c.GetKeywords() {
keywords = append(keywords, []byte(keyword))
}
return keywords
}
// productIndices produces a permutation of indices for each length. Example:
+7 -10
View File
@@ -1,10 +1,10 @@
package abbysale
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -25,25 +25,23 @@ 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{"abbysale"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("abbysale")}
}
// FromData will find and optionally verify Abbysale 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_Abbysale,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -51,14 +49,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
req.Header.Add("x-api-key", resMatch)
req.Header.Add("x-api-key", 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 -10
View File
@@ -1,11 +1,11 @@
package abstract
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,29 +26,27 @@ 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{"abstract"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("abstract")}
}
// FromData will find and optionally verify Abstract 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_Abstract,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://exchange-rates.abstractapi.com/v1/live/?api_key=%s&base=USD", resMatch), nil)
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://exchange-rates.abstractapi.com/v1/live/?api_key=%s&base=USD", string(resMatch)), nil)
if err != nil {
continue
}
@@ -59,7 +57,6 @@ 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
}
+9 -13
View File
@@ -1,12 +1,12 @@
package abuseipdb
import (
"bytes"
"context"
"io"
"net/http"
// "log"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -27,25 +27,23 @@ 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{"abuseipdb"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("abuseipdb")}
}
// FromData will find and optionally verify AbuseIPDB 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_AbuseIPDB,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -53,14 +51,12 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
req.Header.Add("Key", resMatch)
req.Header.Add("Key", string(resMatch))
res, err := client.Do(req)
if err == nil {
bodyBytes, err := io.ReadAll(res.Body)
if err == nil {
bodyString := string(bodyBytes)
validResponse := strings.Contains(bodyString, `ipAddress`)
// errCode := strings.Contains(bodyString, `AbuseIPDB APIv2 Server.`)
validResponse := bytes.Contains(bodyBytes, []byte(`ipAddress`))
defer res.Body.Close()
if res.StatusCode >= 200 && res.StatusCode < 300 {
@@ -70,7 +66,6 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
s1.Verified = false
}
} 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
}
@@ -78,6 +73,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
}
}
}
results = append(results, s1)
}
+7 -10
View File
@@ -1,10 +1,10 @@
package accuweather
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -25,29 +25,27 @@ 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{"accuweather"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("accuweather")}
}
// FromData will find and optionally verify Accuweather 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_Accuweather,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", "https://dataservice.accuweather.com/locations/v1/cities/autocomplete?apikey="+resMatch+"&q=----&language=en-us", nil)
req, err := http.NewRequestWithContext(ctx, "GET", "https://dataservice.accuweather.com/locations/v1/cities/autocomplete?apikey="+string(resMatch)+"&q=----&language=en-us", nil)
if err != nil {
continue
}
@@ -57,7 +55,6 @@ 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
}
+7 -10
View File
@@ -1,10 +1,10 @@
package adafruitio
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -25,29 +25,27 @@ 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{"aio_"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("aio_")}
}
// FromData will find and optionally verify AdafruitIO 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_AdafruitIO,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", "https://io.adafruit.com/api/v2/ladybugtest/feeds/?x-aio-key="+resMatch, nil)
req, err := http.NewRequestWithContext(ctx, "GET", "https://io.adafruit.com/api/v2/ladybugtest/feeds/?x-aio-key="+string(resMatch), nil)
if err != nil {
continue
}
@@ -57,7 +55,6 @@ 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
}
+12 -14
View File
@@ -1,10 +1,10 @@
package adobeio
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,32 +26,31 @@ 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{"adobe"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("adobe")}
}
// FromData will find and optionally verify AdobeIO 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)
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
matches := keyPat.FindAllSubmatch(data, -1)
idMatches := idPat.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 {
if len(idMatch) != 2 {
continue
}
resIdMatch := strings.TrimSpace(idMatch[1])
resIdMatch := bytes.TrimSpace(idMatch[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_AdobeIO,
Raw: []byte(resMatch),
RawV2: []byte(resMatch + resIdMatch),
Raw: resMatch,
RawV2: append(resMatch, resIdMatch...),
}
if verify {
@@ -59,15 +58,14 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
req.Header.Add("x-api-key", resMatch)
req.Header.Add("x-product", resIdMatch)
req.Header.Add("x-api-key", string(resMatch))
req.Header.Add("x-product", string(resIdMatch))
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
}
+11 -12
View File
@@ -1,11 +1,11 @@
package adzuna
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -27,36 +27,35 @@ 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{"adzuna"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("adzuna")}
}
// FromData will find and optionally verify Adzuna 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)
matches := keyPat.FindAllSubmatch(data, -1)
idMatches := idPat.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 {
if len(idMatch) != 2 {
continue
}
resIdMatch := strings.TrimSpace(idMatch[1])
resIdMatch := bytes.TrimSpace(idMatch[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_Adzuna,
Raw: []byte(resMatch),
RawV2: []byte(resMatch + resIdMatch),
Raw: resMatch,
RawV2: append(resMatch, resIdMatch...),
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.adzuna.com/v1/api/jobs/gb/search/1?app_id=%s&app_key=%s", resIdMatch, resMatch), nil)
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.adzuna.com/v1/api/jobs/gb/search/1?app_id=%s&app_key=%s", string(resIdMatch), string(resMatch)), nil)
if err != nil {
continue
}
@@ -66,7 +65,6 @@ 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
}
@@ -76,6 +74,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
results = append(results, s1)
}
}
return results, nil
+11 -14
View File
@@ -1,10 +1,10 @@
package aeroworkflow
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,49 +26,46 @@ 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{"aeroworkflow"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("aeroworkflow")}
}
// FromData will find and optionally verify Aeroworkflow 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)
matches := keyPat.FindAllSubmatch(data, -1)
idmatches := idPat.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 {
if len(idmatch) != 2 {
continue
}
resIdMatch := strings.TrimSpace(idmatch[1])
resIdMatch := bytes.TrimSpace(idmatch[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_Aeroworkflow,
Raw: []byte(resMatch),
RawV2: []byte(resMatch + resIdMatch),
Raw: resMatch,
RawV2: append(resMatch, resIdMatch...),
}
if verify {
req, err := http.NewRequest("GET", "https://api.aeroworkflow.com/api/"+resIdMatch+"/v1/AeroAppointments", nil)
req, err := http.NewRequest("GET", "https://api.aeroworkflow.com/api/"+string(resIdMatch)+"/v1/AeroAppointments", nil)
if err != nil {
continue
}
req.Header.Add("Accept", "application/json")
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
}
+10 -13
View File
@@ -1,10 +1,10 @@
package agora
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,34 +26,31 @@ 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{"agora"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("agora")}
}
// FromData will find and optionally verify Agora 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)
secretMatches := secretPat.FindAllStringSubmatch(dataStr, -1)
matches := keyPat.FindAllSubmatch(data, -1)
secretMatches := secretPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
resMatch := bytes.TrimSpace(match[1])
for _, secret := range secretMatches {
if len(secret) != 2 {
continue
}
resSecret := strings.TrimSpace(secret[1])
resSecret := bytes.TrimSpace(secret[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_Agora,
Raw: []byte(resMatch),
RawV2: []byte(resMatch + resSecret),
Raw: resMatch,
RawV2: append(resMatch, resSecret...),
}
if verify {
@@ -61,7 +58,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
req.SetBasicAuth(resSecret, resMatch)
req.SetBasicAuth(string(resSecret), string(resMatch))
res, err := client.Do(req)
if err == nil {
+7 -9
View File
@@ -1,11 +1,11 @@
package aha
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,25 +26,23 @@ 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{"aha"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("aha")}
}
// FromData will find and optionally verify Aha 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_Aha,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -53,7 +51,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
continue
}
req.Header.Add("Accept", "application/vnd.aha+json; version=3")
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()
@@ -1,6 +1,7 @@
package airbrakeprojectkey
import (
"bytes"
"context"
"net/http"
"regexp"
@@ -26,40 +27,36 @@ 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{"airbrake"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("airbrake")}
}
// FromData will find and optionally verify AirbrakeProjectKey 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)
matches := keyPat.FindAllSubmatch(data, -1)
idMatches := idPat.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 {
if len(idMatch) != 2 {
continue
}
resIdMatch := strings.TrimSpace(idMatch[1])
resIdMatch := bytes.TrimSpace(idMatch[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_AirbrakeProjectKey,
Raw: []byte(resMatch),
RawV2: []byte(resMatch + resIdMatch),
Raw: resMatch,
RawV2: append(resMatch, resIdMatch...),
}
if verify {
payload := strings.NewReader(`{"environment":"production","username":"john","email":"john@smith.com","repository":"https://github.com/airbrake/airbrake","revision":"38748467ea579e7ae64f7815452307c9d05e05c5","version":"v2.0"}`)
req, err := http.NewRequestWithContext(ctx, "POST", "https://api.airbrake.io/api/v4/projects/"+resIdMatch+"/deploys?key="+resMatch, payload)
req, err := http.NewRequestWithContext(ctx, "POST", "https://api.airbrake.io/api/v4/projects/"+string(resIdMatch)+"/deploys?key="+string(resMatch), payload)
if err != nil {
continue
}
@@ -74,15 +71,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
}
if !s1.Verified {
if detectors.IsKnownFalsePositive(string(s1.Raw), detectors.DefaultFalsePositives, true) {
if detectors.IsKnownFalsePositive(resMatch, detectors.DefaultFalsePositives, true) {
continue
}
}
results = append(results, s1)
}
}
return results, nil
@@ -1,10 +1,10 @@
package airbrakeuserkey
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -25,29 +25,27 @@ 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{"airbrake"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("airbrake")}
}
// FromData will find and optionally verify AirbrakeUserKey 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_AirbrakeUserKey,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", "https://api.airbrake.io/api/v4/projects?key="+resMatch, nil)
req, err := http.NewRequestWithContext(ctx, "GET", "https://api.airbrake.io/api/v4/projects?key="+string(resMatch), nil)
if err != nil {
continue
}
+7 -9
View File
@@ -1,11 +1,11 @@
package airship
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,25 +26,23 @@ 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{"airship"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("airship")}
}
// FromData will find and optionally verify Airship 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_Airship,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -53,7 +51,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
continue
}
req.Header.Add("Accept", "application/vnd.urbanairship+json; version=3")
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()
+12 -14
View File
@@ -1,11 +1,11 @@
package airtableapikey
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,42 +26,40 @@ 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{"airtable"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("airtable")}
}
// FromData will find and optionally verify AirtableApiKey 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)
appMatches := appPat.FindAllStringSubmatch(dataStr, -1)
keyMatches := keyPat.FindAllStringSubmatch(dataStr, -1)
appMatches := appPat.FindAllSubmatch(data, -1)
keyMatches := keyPat.FindAllSubmatch(data, -1)
for _, keyMatch := range keyMatches {
if len(keyMatch) != 2 {
continue
}
keyRes := strings.TrimSpace(keyMatch[1])
keyRes := bytes.TrimSpace(keyMatch[1])
for _, appMatch := range appMatches {
if len(appMatch) != 2 {
continue
}
appRes := strings.TrimSpace(appMatch[1])
appRes := bytes.TrimSpace(appMatch[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_AirtableApiKey,
Redacted: appRes,
Raw: []byte(keyRes),
RawV2: []byte(keyRes + appRes),
Redacted: string(appRes),
Raw: keyRes,
RawV2: append(keyRes, appRes...),
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", "https://api.airtable.com/v0/"+appRes+"/Projects", nil)
req, err := http.NewRequestWithContext(ctx, "GET", "https://api.airtable.com/v0/"+string(appRes)+"/Projects", nil)
if err != nil {
continue
}
req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", keyRes))
req.Header.Add("Authorization", fmt.Sprintf("Bearer %s", string(keyRes)))
res, err := client.Do(req)
if err == nil {
defer res.Body.Close()
+8 -10
View File
@@ -1,11 +1,11 @@
package airvisual
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,34 +26,32 @@ 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{"airvisual"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("airvisual")}
}
// FromData will find and optionally verify AirVisual 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_AirVisual,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.airvisual.com/v2/countries?key=%s", resMatch), nil)
req, err := http.NewRequestWithContext(ctx, "GET", fmt.Sprintf("https://api.airvisual.com/v2/countries?key=%s", string(resMatch)), nil)
if err != nil {
continue
}
req.Header.Add("Accept", "application/vnd.airvisual+json; version=3")
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()
+7 -9
View File
@@ -1,11 +1,11 @@
package aiven
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,25 +26,23 @@ 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{"aiven"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("aiven")}
}
// FromData will find and optionally verify Aiven 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_Aiven,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -52,7 +50,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
req.Header.Add("Authorization", fmt.Sprintf("aivenv1 %s", resMatch))
req.Header.Add("Authorization", fmt.Sprintf("aivenv1 %s", string(resMatch)))
res, err := client.Do(req)
if err == nil {
defer res.Body.Close()
+7 -9
View File
@@ -1,11 +1,11 @@
package alchemy
import (
"bytes"
"context"
"fmt"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -27,25 +27,23 @@ 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{"alchemy"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("alchemy")}
}
// FromData will find and optionally verify Alchemy 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_Alchemy,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
@@ -53,7 +51,7 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if client == nil {
client = defaultClient
}
req, err := http.NewRequestWithContext(ctx, "GET", "https://eth-mainnet.g.alchemy.com/v2/"+resMatch+"/getNFTs/?owner=vitalik.eth", nil)
req, err := http.NewRequestWithContext(ctx, "GET", "https://eth-mainnet.g.alchemy.com/v2/"+string(resMatch)+"/getNFTs/?owner=vitalik.eth", nil)
if err != nil {
continue
}
+8 -10
View File
@@ -1,12 +1,12 @@
package alconost
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"
@@ -27,30 +27,28 @@ 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{"alconost"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("alconost")}
}
// FromData will find and optionally verify Alconost 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_Alconost,
Raw: []byte(resMatch),
Raw: resMatch,
}
if verify {
data := fmt.Sprintf("%s:", resMatch)
sEnc := b64.StdEncoding.EncodeToString([]byte(data))
data := append(resMatch, ':')
sEnc := b64.StdEncoding.EncodeToString(data)
req, err := http.NewRequestWithContext(ctx, "GET", "https://nitro.alconost.com/api/v1/account", nil)
if err != nil {
continue
+10 -13
View File
@@ -1,10 +1,10 @@
package alegra
import (
"bytes"
"context"
"net/http"
"regexp"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
@@ -26,34 +26,32 @@ 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{"alegra"}
func (s Scanner) Keywords() [][]byte {
return [][]byte{[]byte("alegra")}
}
// FromData will find and optionally verify Alegra 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)
matches := keyPat.FindAllSubmatch(data, -1)
idMatches := idPat.FindAllSubmatch(data, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
tokenPatMatch := strings.TrimSpace(match[1])
tokenPatMatch := bytes.TrimSpace(match[1])
for _, idMatch := range idMatches {
if len(idMatch) != 2 {
continue
}
userPatMatch := strings.TrimSpace(idMatch[1])
userPatMatch := bytes.TrimSpace(idMatch[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_Alegra,
Raw: []byte(tokenPatMatch),
RawV2: []byte(tokenPatMatch + userPatMatch),
Raw: tokenPatMatch,
RawV2: append(tokenPatMatch, userPatMatch...),
}
if verify {
@@ -61,14 +59,13 @@ func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (result
if err != nil {
continue
}
req.SetBasicAuth(userPatMatch, tokenPatMatch)
req.SetBasicAuth(string(userPatMatch), string(tokenPatMatch))
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(tokenPatMatch, detectors.DefaultFalsePositives, true) {
continue
}
+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
+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{},
}
}
+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,