Add unit tests for HTTP dissector (#767)

* Add unit tests for HTTP dissector

* Ignore some fields on test environment

* Remove Git patches

* Don't have indent in the expected JSONs

* Fix more issues and update expected JSONs

* Refactor the test environment lookup

* Add a Makefile

* Include HTTP tests into the CI

* Fix the linting errors

* Fix another linting error

* Update the expected JSONs

* Sort `PostData.Params` params as well

* Move expected JSONs into `expect/dissect`

* Add `TestAnalyze` method

* Add `TestRepresent` method

* Add `TestRegister`, `TestMacros` and `TestPing` methods

* Test extensions first

* Remove expected JSONs

* Remove `bin` directory and update `Makefile` rules

* Update `.gitignore`

* Fix skipping download functionality in the Makefile

* Run `go mod tidy`

* Fix the race condition in the tests

* Revert "Test extensions first"

This reverts commit b8350cf139.

* Make `TEST_UPDATE` env lookup one-liner

* Update .github/workflows/test.yml

Co-authored-by: gadotroee <55343099+gadotroee@users.noreply.github.com>

* Add a newline

* Replace `ls` with `find`

Co-authored-by: gadotroee <55343099+gadotroee@users.noreply.github.com>

.github/workflows/test.yml

@@ -27,19 +27,31 @@ jobs:
       - name: Check out code into the Go module directory
         uses: actions/checkout@v2
 
-      - shell: bash
+      - name: Install libpcap
+        shell: bash
         run: |
           sudo apt-get install libpcap-dev
 
+      - id: 'auth'
+        uses: 'google-github-actions/auth@v0'
+        with:
+          credentials_json: '${{ secrets.GCR_JSON_KEY }}'
+
+      - name: 'Set up Cloud SDK'
+        uses: 'google-github-actions/setup-gcloud@v0'
+
       - name: CLI Test
         run: make test-cli
 
       - name: Agent Test
         run: make test-agent
-      
+
       - name: Shared Test
         run: make test-shared
 
+      - name: Extensions Test
+        run: make test-extensions
+
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v2
 

.gitignore

@@ -44,3 +44,7 @@ cypress.env.json
 */cypress/screenshots
 */cypress/videos
 */cypress/support
+
+# Ignore test data in extensions
+tap/extensions/*/bin
+tap/extensions/*/expect

Makefile

@@ -101,5 +101,8 @@ test-agent:
 test-shared:
 	@echo "running shared tests"; cd shared && $(MAKE) test
 
+test-extensions:
+	@echo "running http tests"; cd tap/extensions/http && $(MAKE) test
+
 acceptance-test:
 	@echo "running acceptance tests"; cd acceptanceTests && $(MAKE) test

tap/api/api.go

@@ -8,12 +8,16 @@ import (
 	"fmt"
 	"io/ioutil"
 	"net/http"
+	"os"
+	"sort"
 	"sync"
 	"time"
 
 	"github.com/google/martian/har"
 )
 
+const mizuTestEnvVar = "MIZU_TEST"
+
 type Protocol struct {
 	Name            string   `json:"name"`
 	LongName        string   `json:"longName"`
@@ -262,27 +266,86 @@ type HTTPWrapper struct {
 }
 
 func (h HTTPPayload) MarshalJSON() ([]byte, error) {
+	_, testEnvEnabled := os.LookupEnv(mizuTestEnvVar)
 	switch h.Type {
 	case TypeHttpRequest:
 		harRequest, err := har.NewRequest(h.Data.(*http.Request), true)
 		if err != nil {
 			return nil, errors.New("Failed converting request to HAR")
 		}
+		sort.Slice(harRequest.Headers, func(i, j int) bool {
+			if harRequest.Headers[i].Name < harRequest.Headers[j].Name {
+				return true
+			}
+			if harRequest.Headers[i].Name > harRequest.Headers[j].Name {
+				return false
+			}
+			return harRequest.Headers[i].Value < harRequest.Headers[j].Value
+		})
+		sort.Slice(harRequest.QueryString, func(i, j int) bool {
+			if harRequest.QueryString[i].Name < harRequest.QueryString[j].Name {
+				return true
+			}
+			if harRequest.QueryString[i].Name > harRequest.QueryString[j].Name {
+				return false
+			}
+			return harRequest.QueryString[i].Value < harRequest.QueryString[j].Value
+		})
+		if harRequest.PostData != nil {
+			sort.Slice(harRequest.PostData.Params, func(i, j int) bool {
+				if harRequest.PostData.Params[i].Name < harRequest.PostData.Params[j].Name {
+					return true
+				}
+				if harRequest.PostData.Params[i].Name > harRequest.PostData.Params[j].Name {
+					return false
+				}
+				return harRequest.PostData.Params[i].Value < harRequest.PostData.Params[j].Value
+			})
+		}
+		if testEnvEnabled {
+			harRequest.URL = ""
+		}
+		var reqWrapper *HTTPRequestWrapper
+		if !testEnvEnabled {
+			reqWrapper = &HTTPRequestWrapper{Request: h.Data.(*http.Request)}
+		}
 		return json.Marshal(&HTTPWrapper{
 			Method:     harRequest.Method,
 			Details:    harRequest,
-			RawRequest: &HTTPRequestWrapper{Request: h.Data.(*http.Request)},
+			RawRequest: reqWrapper,
 		})
 	case TypeHttpResponse:
 		harResponse, err := har.NewResponse(h.Data.(*http.Response), true)
 		if err != nil {
 			return nil, errors.New("Failed converting response to HAR")
 		}
+		sort.Slice(harResponse.Headers, func(i, j int) bool {
+			if harResponse.Headers[i].Name < harResponse.Headers[j].Name {
+				return true
+			}
+			if harResponse.Headers[i].Name > harResponse.Headers[j].Name {
+				return false
+			}
+			return harResponse.Headers[i].Value < harResponse.Headers[j].Value
+		})
+		sort.Slice(harResponse.Cookies, func(i, j int) bool {
+			if harResponse.Cookies[i].Name < harResponse.Cookies[j].Name {
+				return true
+			}
+			if harResponse.Cookies[i].Name > harResponse.Cookies[j].Name {
+				return false
+			}
+			return harResponse.Cookies[i].Value < harResponse.Cookies[j].Value
+		})
+		var resWrapper *HTTPResponseWrapper
+		if !testEnvEnabled {
+			resWrapper = &HTTPResponseWrapper{Response: h.Data.(*http.Response)}
+		}
 		return json.Marshal(&HTTPWrapper{
 			Method:      "",
 			Url:         "",
 			Details:     harResponse,
-			RawResponse: &HTTPResponseWrapper{Response: h.Data.(*http.Response)},
+			RawResponse: resWrapper,
 		})
 	default:
 		panic(fmt.Sprintf("HTTP payload cannot be marshaled: %v", h.Type))

tap/extensions/http/Makefile

@@ -0,0 +1,16 @@
+skipbin := $$(find bin -mindepth 1 -maxdepth 1)
+skipexpect := $$(find expect -mindepth 1 -maxdepth 1)
+
+test: test-pull-bin test-pull-expect
+	@MIZU_TEST=1 go test -v ./... -coverpkg=./... -race -coverprofile=coverage.out -covermode=atomic
+
+test-update: test-pull-bin
+	@MIZU_TEST=1 TEST_UPDATE=1 go test -v ./... -coverpkg=./... -coverprofile=coverage.out -covermode=atomic
+
+test-pull-bin:
+	@mkdir -p bin
+	@[ "${skipbin}" ] && echo "Skipping downloading BINs" || gsutil -m cp gs://static.up9.io/mizu/test-pcap/bin/http/\*.bin bin
+
+test-pull-expect:
+	@mkdir -p expect
+	@[ "${skipexpect}" ] && echo "Skipping downloading expected JSONs" || gsutil -m cp -r gs://static.up9.io/mizu/test-pcap/expect/http/\* expect

tap/extensions/http/go.mod

@@ -4,13 +4,17 @@ go 1.17
 
 require (
 	github.com/beevik/etree v1.1.0
+	github.com/stretchr/testify v1.7.0
 	github.com/up9inc/mizu/tap/api v0.0.0
 	golang.org/x/net v0.0.0-20220127200216-cd36cc0744dd
 )
 
 require (
+	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/google/martian v2.1.0+incompatible // indirect
+	github.com/pmezard/go-difflib v1.0.0 // indirect
 	golang.org/x/text v0.3.7 // indirect
+	gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b // indirect
 )
 
 replace github.com/up9inc/mizu/tap/api v0.0.0 => ../../api

tap/extensions/http/go.sum

@@ -1,7 +1,15 @@
 github.com/beevik/etree v1.1.0 h1:T0xke/WvNtMoCqgzPhkX2r4rjY3GDZFi+FjpRZY2Jbs=
 github.com/beevik/etree v1.1.0/go.mod h1:r8Aw8JqVegEf0w2fDnATrX9VpkMcyFeM0FhwO62wh+A=
+github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
+github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/google/martian v2.1.0+incompatible h1:/CP5g8u/VJHijgedC/Legn3BAbAaWPgecwXBIDzw5no=
 github.com/google/martian v2.1.0+incompatible/go.mod h1:9I4somxYTbIHy5NJKHRl3wXiIaQGbYVAs8BPL6v8lEs=
+github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
+github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/testify v1.7.0 h1:nwc3DEeHmmLAfoZucVR881uASk0Mfjw8xYJ99tb5CcY=
+github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 golang.org/x/net v0.0.0-20220127200216-cd36cc0744dd h1:O7DYs+zxREGLKzKoMQrtrEacpb0ZVXA5rIwylE2Xchk=
 golang.org/x/net v0.0.0-20220127200216-cd36cc0744dd/go.mod h1:CfG3xpIq0wQ8r1q4Su4UZFWDARRcnwPjda9FqA0JpMk=
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
@@ -10,3 +18,8 @@ golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuX
 golang.org/x/text v0.3.7 h1:olpwvP2KacW1ZWvsR7uQhoyTYvKAupfQrRGBFM352Gk=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405 h1:yhCVgyC4o1eVCa2tZl7eS0r+SDo693bJlVdllGtEeKM=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b h1:h8qDotaEPuJATrMmW04NCwg7v22aHH28wwpauUhK9Oo=
+gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

tap/extensions/http/helpers.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 	"reflect"
+	"sort"
 	"strconv"
 
 	"github.com/up9inc/mizu/tap/api"
@@ -39,6 +40,10 @@ func mapSliceMergeRepeatedKeys(mapSlice []interface{}) (newMapSlice []interface{
 		newMapSlice = append(newMapSlice, h)
 	}
 
+	sort.Slice(newMapSlice, func(i, j int) bool {
+		return newMapSlice[i].(map[string]interface{})["name"].(string) < newMapSlice[j].(map[string]interface{})["name"].(string)
+	})
+
 	return
 }
 

tap/extensions/http/main_test.go

@@ -0,0 +1,300 @@
+package http
+
+import (
+	"bufio"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"io/ioutil"
+	"log"
+	"os"
+	"path"
+	"path/filepath"
+	"sort"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/up9inc/mizu/tap/api"
+)
+
+const (
+	binDir          = "bin"
+	patternBin      = "*_req.bin"
+	patternDissect  = "*.json"
+	msgDissecting   = "Dissecting:"
+	msgAnalyzing    = "Analyzing:"
+	msgRepresenting = "Representing:"
+	respSuffix      = "_res.bin"
+	expectDir       = "expect"
+	dissectDir      = "dissect"
+	analyzeDir      = "analyze"
+	representDir    = "represent"
+	testUpdate      = "TEST_UPDATE"
+)
+
+func TestRegister(t *testing.T) {
+	dissector := NewDissector()
+	extension := &api.Extension{}
+	dissector.Register(extension)
+	assert.Equal(t, "http", extension.Protocol.Name)
+	assert.NotNil(t, extension.MatcherMap)
+}
+
+func TestMacros(t *testing.T) {
+	expectedMacros := map[string]string{
+		"http":  `proto.name == "http" and proto.version.startsWith("1")`,
+		"http2": `proto.name == "http" and proto.version == "2.0"`,
+		"grpc":  `proto.name == "http" and proto.version == "2.0" and proto.macro == "grpc"`,
+	}
+	dissector := NewDissector()
+	macros := dissector.Macros()
+	assert.Equal(t, expectedMacros, macros)
+}
+
+func TestPing(t *testing.T) {
+	dissector := NewDissector()
+	dissector.Ping()
+}
+
+func TestDissect(t *testing.T) {
+	_, testUpdateEnabled := os.LookupEnv(testUpdate)
+
+	expectDirDissect := path.Join(expectDir, dissectDir)
+
+	if testUpdateEnabled {
+		os.RemoveAll(expectDirDissect)
+		err := os.MkdirAll(expectDirDissect, 0775)
+		assert.Nil(t, err)
+	}
+
+	dissector := NewDissector()
+	paths, err := filepath.Glob(path.Join(binDir, patternBin))
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	options := &api.TrafficFilteringOptions{
+		IgnoredUserAgents: []string{},
+	}
+
+	for _, _path := range paths {
+		basePath := _path[:len(_path)-8]
+
+		// Channel to verify the output
+		itemChannel := make(chan *api.OutputChannelItem)
+		var emitter api.Emitter = &api.Emitting{
+			AppStats:      &api.AppStats{},
+			OutputChannel: itemChannel,
+		}
+
+		var items []*api.OutputChannelItem
+		stop := make(chan bool)
+
+		go func() {
+			for {
+				select {
+				case <-stop:
+					return
+				case item := <-itemChannel:
+					items = append(items, item)
+				}
+			}
+		}()
+
+		// Stream level
+		counterPair := &api.CounterPair{
+			Request:  0,
+			Response: 0,
+		}
+		superIdentifier := &api.SuperIdentifier{}
+
+		// Request
+		pathClient := _path
+		fmt.Printf("%s %s\n", msgDissecting, pathClient)
+		fileClient, err := os.Open(pathClient)
+		assert.Nil(t, err)
+
+		bufferClient := bufio.NewReader(fileClient)
+		tcpIDClient := &api.TcpID{
+			SrcIP:   "1",
+			DstIP:   "2",
+			SrcPort: "1",
+			DstPort: "2",
+		}
+		err = dissector.Dissect(bufferClient, true, tcpIDClient, counterPair, &api.SuperTimer{}, superIdentifier, emitter, options)
+		if err != nil && err != io.EOF && err != io.ErrUnexpectedEOF {
+			panic(err)
+		}
+
+		// Response
+		pathServer := basePath + respSuffix
+		fmt.Printf("%s %s\n", msgDissecting, pathServer)
+		fileServer, err := os.Open(pathServer)
+		assert.Nil(t, err)
+
+		bufferServer := bufio.NewReader(fileServer)
+		tcpIDServer := &api.TcpID{
+			SrcIP:   "2",
+			DstIP:   "1",
+			SrcPort: "2",
+			DstPort: "1",
+		}
+		err = dissector.Dissect(bufferServer, false, tcpIDServer, counterPair, &api.SuperTimer{}, superIdentifier, emitter, options)
+		if err != nil && err != io.EOF && err != io.ErrUnexpectedEOF {
+			panic(err)
+		}
+
+		fileClient.Close()
+		fileServer.Close()
+
+		pathExpect := path.Join(expectDirDissect, fmt.Sprintf("%s.json", basePath[4:]))
+
+		time.Sleep(10 * time.Millisecond)
+
+		stop <- true
+
+		sort.Slice(items, func(i, j int) bool {
+			iMarshaled, err := json.Marshal(items[i])
+			assert.Nil(t, err)
+			jMarshaled, err := json.Marshal(items[j])
+			assert.Nil(t, err)
+			return len(iMarshaled) < len(jMarshaled)
+		})
+
+		marshaled, err := json.Marshal(items)
+		assert.Nil(t, err)
+
+		if testUpdateEnabled {
+			if len(items) > 0 {
+				err = os.WriteFile(pathExpect, marshaled, 0644)
+				assert.Nil(t, err)
+			}
+		} else {
+			if _, err := os.Stat(pathExpect); errors.Is(err, os.ErrNotExist) {
+				assert.Len(t, items, 0)
+			} else {
+				expectedBytes, err := ioutil.ReadFile(pathExpect)
+				assert.Nil(t, err)
+
+				assert.JSONEq(t, string(expectedBytes), string(marshaled))
+			}
+		}
+	}
+}
+
+func TestAnalyze(t *testing.T) {
+	_, testUpdateEnabled := os.LookupEnv(testUpdate)
+
+	expectDirDissect := path.Join(expectDir, dissectDir)
+	expectDirAnalyze := path.Join(expectDir, analyzeDir)
+
+	if testUpdateEnabled {
+		os.RemoveAll(expectDirAnalyze)
+		err := os.MkdirAll(expectDirAnalyze, 0775)
+		assert.Nil(t, err)
+	}
+
+	dissector := NewDissector()
+	paths, err := filepath.Glob(path.Join(expectDirDissect, patternDissect))
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	for _, _path := range paths {
+		fmt.Printf("%s %s\n", msgAnalyzing, _path)
+
+		bytes, err := ioutil.ReadFile(_path)
+		assert.Nil(t, err)
+
+		var items []*api.OutputChannelItem
+		err = json.Unmarshal(bytes, &items)
+		assert.Nil(t, err)
+
+		var entries []*api.Entry
+		for _, item := range items {
+			entry := dissector.Analyze(item, "", "")
+			entries = append(entries, entry)
+		}
+
+		pathExpect := path.Join(expectDirAnalyze, filepath.Base(_path))
+
+		marshaled, err := json.Marshal(entries)
+		assert.Nil(t, err)
+
+		if testUpdateEnabled {
+			if len(entries) > 0 {
+				err = os.WriteFile(pathExpect, marshaled, 0644)
+				assert.Nil(t, err)
+			}
+		} else {
+			if _, err := os.Stat(pathExpect); errors.Is(err, os.ErrNotExist) {
+				assert.Len(t, items, 0)
+			} else {
+				expectedBytes, err := ioutil.ReadFile(pathExpect)
+				assert.Nil(t, err)
+
+				assert.JSONEq(t, string(expectedBytes), string(marshaled))
+			}
+		}
+	}
+}
+
+func TestRepresent(t *testing.T) {
+	_, testUpdateEnabled := os.LookupEnv(testUpdate)
+
+	expectDirAnalyze := path.Join(expectDir, analyzeDir)
+	expectDirRepresent := path.Join(expectDir, representDir)
+
+	if testUpdateEnabled {
+		os.RemoveAll(expectDirRepresent)
+		err := os.MkdirAll(expectDirRepresent, 0775)
+		assert.Nil(t, err)
+	}
+
+	dissector := NewDissector()
+	paths, err := filepath.Glob(path.Join(expectDirAnalyze, patternDissect))
+	if err != nil {
+		log.Fatal(err)
+	}
+
+	for _, _path := range paths {
+		fmt.Printf("%s %s\n", msgRepresenting, _path)
+
+		bytes, err := ioutil.ReadFile(_path)
+		assert.Nil(t, err)
+
+		var entries []*api.Entry
+		err = json.Unmarshal(bytes, &entries)
+		assert.Nil(t, err)
+
+		var objects []string
+		for _, entry := range entries {
+			object, _, err := dissector.Represent(entry.Request, entry.Response)
+			assert.Nil(t, err)
+			objects = append(objects, string(object))
+		}
+
+		pathExpect := path.Join(expectDirRepresent, filepath.Base(_path))
+
+		marshaled, err := json.Marshal(objects)
+		assert.Nil(t, err)
+
+		if testUpdateEnabled {
+			if len(objects) > 0 {
+				err = os.WriteFile(pathExpect, marshaled, 0644)
+				assert.Nil(t, err)
+			}
+		} else {
+			if _, err := os.Stat(pathExpect); errors.Is(err, os.ErrNotExist) {
+				assert.Len(t, objects, 0)
+			} else {
+				expectedBytes, err := ioutil.ReadFile(pathExpect)
+				assert.Nil(t, err)
+
+				assert.JSONEq(t, string(expectedBytes), string(marshaled))
+			}
+		}
+	}
+}