Improvements and tests for eml conversion (#4644)

<!-- PR description-->

---

#### Does this PR need a docs update or release note?

- [ ] ✅ Yes, it's included
- [x] 🕐 Yes, but in a later PR
- [ ] ⛔ No

#### Type of change

<!--- Please check the type of change your PR introduces: --->
- [ ] 🌻 Feature
- [ ] 🐛 Bugfix
- [ ] 🗺️ Documentation
- [x] 🤖 Supportability/Tests
- [ ] 💻 CI/Deployment
- [ ] 🧹 Tech Debt/Cleanup

#### Issue(s)

<!-- Can reference multiple issues. Use one of the following "magic words" - "closes, fixes" to auto-close the Github issue. -->
* https://github.com/alcionai/corso/issues/3893

#### Test Plan

<!-- How will this be tested prior to merging.-->
- [ ] 💪 Manual
- [x] ⚡ Unit test
- [ ] 💚 E2E

CHANGELOG.md

@@ -7,6 +7,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased] (beta)
 
+### Added
+- Added export support for emails in exchange backups as `.eml` files
+
 ### Changed
 - Change file extension of messages export to json to match the content
 

src/cmd/converter/converter.go

@@ -7,7 +7,6 @@ import (
 	"os"
 
 	"github.com/alcionai/corso/src/internal/converters/eml"
-	"github.com/alcionai/corso/src/pkg/services/m365/api"
 )
 
 func main() {
@@ -31,12 +30,7 @@ func main() {
 	case "msg":
 		switch to {
 		case "eml":
-			msg, err := api.BytesToMessageable(body)
+			out, err = eml.FromJSON(context.Background(), body)
-			if err != nil {
-				log.Fatal(err)
-			}
-
-			out, err = eml.ToEml(context.Background(), msg)
 			if err != nil {
 				log.Fatal(err)
 			}

src/internal/converters/eml/eml.go

@@ -13,26 +13,31 @@ import (
 	"fmt"
 
 	"github.com/alcionai/clues"
-	"github.com/microsoftgraph/msgraph-sdk-go/models"
 	mail "github.com/xhit/go-simple-mail/v2"
 
 	"github.com/alcionai/corso/src/internal/common/ptr"
 	"github.com/alcionai/corso/src/pkg/logger"
+	"github.com/alcionai/corso/src/pkg/services/m365/api"
 )
 
 const (
-	fromFormat = "%s <%s>"
+	addressFormat = "%s <%s>"
-	dateFormat = "2006-01-02 15:04:05 MST" // from xhit/go-simple-mail
+	dateFormat    = "2006-01-02 15:04:05 MST" // from xhit/go-simple-mail
 )
 
-// ToEml converts a Messageable to .eml format
+// FromJSON converts a Messageable (as json) to .eml format
-func ToEml(ctx context.Context, data models.Messageable) (string, error) {
+func FromJSON(ctx context.Context, body []byte) (string, error) {
+	data, err := api.BytesToMessageable(body)
+	if err != nil {
+		return "", clues.Wrap(err, "converting to messageble")
+	}
+
 	email := mail.NewMSG()
 
 	if data.GetFrom() != nil {
 		email.SetFrom(
 			fmt.Sprintf(
-				fromFormat,
+				addressFormat,
 				ptr.Val(data.GetFrom().GetEmailAddress().GetName()),
 				ptr.Val(data.GetFrom().GetEmailAddress().GetAddress())))
 	}
@@ -41,7 +46,7 @@ func ToEml(ctx context.Context, data models.Messageable) (string, error) {
 		for _, recipient := range data.GetToRecipients() {
 			email.AddTo(
 				fmt.Sprintf(
-					fromFormat,
+					addressFormat,
 					ptr.Val(recipient.GetEmailAddress().GetName()),
 					ptr.Val(recipient.GetEmailAddress().GetAddress())))
 		}
@@ -51,7 +56,7 @@ func ToEml(ctx context.Context, data models.Messageable) (string, error) {
 		for _, recipient := range data.GetCcRecipients() {
 			email.AddCc(
 				fmt.Sprintf(
-					fromFormat,
+					addressFormat,
 					ptr.Val(recipient.GetEmailAddress().GetName()),
 					ptr.Val(recipient.GetEmailAddress().GetAddress())))
 		}
@@ -61,7 +66,7 @@ func ToEml(ctx context.Context, data models.Messageable) (string, error) {
 		for _, recipient := range data.GetBccRecipients() {
 			email.AddBcc(
 				fmt.Sprintf(
-					fromFormat,
+					addressFormat,
 					ptr.Val(recipient.GetEmailAddress().GetName()),
 					ptr.Val(recipient.GetEmailAddress().GetAddress())))
 		}
@@ -77,7 +82,7 @@ func ToEml(ctx context.Context, data models.Messageable) (string, error) {
 		} else if len(rts) != 0 {
 			email.SetReplyTo(
 				fmt.Sprintf(
-					fromFormat,
+					addressFormat,
 					ptr.Val(rts[0].GetEmailAddress().GetName()),
 					ptr.Val(rts[0].GetEmailAddress().GetAddress())))
 		}

src/internal/converters/eml/eml_test.go

@@ -1,12 +1,15 @@
 package eml
 
 import (
+	"fmt"
 	"testing"
+	"time"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"github.com/stretchr/testify/suite"
 
+	"github.com/alcionai/corso/src/internal/common/ptr"
 	"github.com/alcionai/corso/src/internal/converters/eml/testdata"
 	"github.com/alcionai/corso/src/internal/tester"
 	"github.com/alcionai/corso/src/pkg/services/m365/api"
@@ -26,11 +29,57 @@ func (suite *EMLUnitSuite) TestConvert_messageble_to_eml() {
 	ctx, flush := tester.NewContext(t)
 	defer flush()
 
-	msg, err := api.BytesToMessageable([]byte(testdata.EmailWithAttachments))
+	body := []byte(testdata.EmailWithAttachments)
+
+	out, err := FromJSON(ctx, body)
+	assert.NoError(t, err, "converting to eml")
+
+	msg, err := api.BytesToMessageable(body)
 	require.NoError(t, err, "creating message")
 
-	_, err = ToEml(ctx, msg)
+	assert.Contains(t, out, fmt.Sprintf("Subject: %s", ptr.Val(msg.GetSubject())))
-	// TODO(meain): add more tests on the generated content
+	assert.Contains(t, out, fmt.Sprintf("Date: %s", msg.GetSentDateTime().Format(time.RFC1123Z)))
-	// Cannot test output directly as it contains a random boundary
+	assert.Contains(
-	assert.NoError(t, err, "converting to eml")
+		t,
+		out,
+		fmt.Sprintf(
+			`From: "%s" <%s>`,
+			ptr.Val(msg.GetFrom().GetEmailAddress().GetName()),
+			ptr.Val(msg.GetFrom().GetEmailAddress().GetAddress())))
+
+	for _, addr := range msg.GetToRecipients() {
+		assert.Contains(
+			t,
+			out,
+			fmt.Sprintf(
+				`To: "%s" <%s>`,
+				ptr.Val(addr.GetEmailAddress().GetName()),
+				ptr.Val(addr.GetEmailAddress().GetAddress())))
+	}
+
+	for _, addr := range msg.GetCcRecipients() {
+		assert.Contains(
+			t,
+			out,
+			fmt.Sprintf(
+				`Cc: "%s" <%s>`,
+				ptr.Val(addr.GetEmailAddress().GetName()),
+				ptr.Val(addr.GetEmailAddress().GetAddress())))
+	}
+
+	for _, addr := range msg.GetBccRecipients() {
+		assert.Contains(
+			t,
+			out,
+			fmt.Sprintf(
+				`Bcc: "%s" <%s>`,
+				ptr.Val(addr.GetEmailAddress().GetName()),
+				ptr.Val(addr.GetEmailAddress().GetAddress())))
+	}
+
+	// Only fist 30 chars as the .eml generator can introduce a
+	// newline in between the text to limit the column width of the
+	// output. It does not affect the data, but can break our tests and
+	// so using 30 as a safe limit to test.
+	assert.Contains(t, out, ptr.Val(msg.GetBody().GetContent())[:30], "body")
 }

src/internal/m365/collection/exchange/export.go

@@ -13,7 +13,6 @@ import (
 	"github.com/alcionai/corso/src/pkg/export"
 	"github.com/alcionai/corso/src/pkg/fault"
 	"github.com/alcionai/corso/src/pkg/path"
-	"github.com/alcionai/corso/src/pkg/services/m365/api"
 )
 
 func NewExportCollection(
@@ -65,17 +64,7 @@ func streamItems(
 				continue
 			}
 
-			msg, err := api.BytesToMessageable(content)
+			email, err := eml.FromJSON(ctx, content)
-			if err != nil {
-				ch <- export.Item{
-					ID:    id,
-					Error: clues.Wrap(err, "parsing email"),
-				}
-
-				continue
-			}
-
-			email, err := eml.ToEml(ctx, msg)
 			if err != nil {
 				ch <- export.Item{
 					ID:    id,