[MM-55052] Improve file extraction logging (#25036)

server/platform/services/docextractor/archive.go

@@ -18,6 +18,10 @@ type archiveExtractor struct {
 	SubExtractor Extractor
 }
 
+func (ae *archiveExtractor) Name() string {
+	return "archiveExtractor"
+}
+
 func (ae *archiveExtractor) Match(filename string) bool {
 	_, err := archiver.ByExtension(filename)
 	return err == nil

server/platform/services/docextractor/combine.go

@@ -10,9 +10,14 @@ import (
 )
 
 type combineExtractor struct {
+	logger        mlog.LoggerIFace
 	SubExtractors []Extractor
 }
 
+func (ce *combineExtractor) Name() string {
+	return "combineExtractor"
+}
+
 func (ce *combineExtractor) Add(extractor Extractor) {
 	ce.SubExtractors = append(ce.SubExtractors, extractor)
 }
@@ -32,7 +37,7 @@ func (ce *combineExtractor) Extract(filename string, r io.ReadSeeker) (string, e
 			r.Seek(0, io.SeekStart)
 			text, err := extractor.Extract(filename, r)
 			if err != nil {
-				mlog.Warn("unable to extract file content", mlog.Err(err))
+				ce.logger.Warn("Unable to extract file content", mlog.String("file_name", filename), mlog.String("extractor", extractor.Name()), mlog.Err(err))
 				continue
 			}
 			return text, nil

server/platform/services/docextractor/docextractor.go

@@ -5,6 +5,8 @@ package docextractor
 
 import (
 	"io"
+
+	"github.com/mattermost/mattermost/server/public/shared/mlog"
 )
 
 // ExtractSettings defines the features enabled/disable during the document text extraction.
@@ -15,13 +17,15 @@ type ExtractSettings struct {
 }
 
 // Extract extract the text from a document using the system default extractors
-func Extract(filename string, r io.ReadSeeker, settings ExtractSettings) (string, error) {
-	return ExtractWithExtraExtractors(filename, r, settings, []Extractor{})
+func Extract(logger mlog.LoggerIFace, filename string, r io.ReadSeeker, settings ExtractSettings) (string, error) {
+	return ExtractWithExtraExtractors(logger, filename, r, settings, []Extractor{})
 }
 
 // ExtractWithExtraExtractors extract the text from a document using the provided extractors beside the system default extractors.
-func ExtractWithExtraExtractors(filename string, r io.ReadSeeker, settings ExtractSettings, extraExtractors []Extractor) (string, error) {
-	enabledExtractors := &combineExtractor{}
+func ExtractWithExtraExtractors(logger mlog.LoggerIFace, filename string, r io.ReadSeeker, settings ExtractSettings, extraExtractors []Extractor) (string, error) {
+	enabledExtractors := &combineExtractor{
+		logger: logger,
+	}
 	for _, extraExtractor := range extraExtractors {
 		enabledExtractors.Add(extraExtractor)
 	}

server/platform/services/docextractor/docextractor_test.go

@@ -13,10 +13,13 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
+	"github.com/mattermost/mattermost/server/public/shared/mlog"
 	"github.com/mattermost/mattermost/server/v8/channels/utils/testutils"
 )
 
 func TestExtract(t *testing.T) {
+	logger := mlog.CreateConsoleTestLogger(t)
+
 	testCases := []struct {
 		Name         string
 		TestFileName string
@@ -127,7 +130,7 @@ func TestExtract(t *testing.T) {
 		t.Run(tc.Name, func(t *testing.T) {
 			data, err := testutils.ReadTestFile(tc.TestFileName)
 			require.NoError(t, err)
-			text, err := Extract(tc.TestFileName, bytes.NewReader(data), tc.Settings)
+			text, err := Extract(logger, tc.TestFileName, bytes.NewReader(data), tc.Settings)
 			if tc.ExpectError {
 				require.Error(t, err)
 			} else {
@@ -145,7 +148,7 @@ func TestExtract(t *testing.T) {
 	t.Run("Unsupported binary file", func(t *testing.T) {
 		data, err := testutils.ReadTestFile("testjpg.jpg")
 		require.NoError(t, err)
-		text, err := Extract("testjpg.jpg", bytes.NewReader(data), ExtractSettings{})
+		text, err := Extract(logger, "testjpg.jpg", bytes.NewReader(data), ExtractSettings{})
 		require.NoError(t, err)
 		require.Equal(t, "", text)
 	})
@@ -153,7 +156,7 @@ func TestExtract(t *testing.T) {
 	t.Run("Wrong docx extension", func(t *testing.T) {
 		data, err := testutils.ReadTestFile("sample-doc.pdf")
 		require.NoError(t, err)
-		text, err := Extract("sample-doc.docx", bytes.NewReader(data), ExtractSettings{})
+		text, err := Extract(logger, "sample-doc.docx", bytes.NewReader(data), ExtractSettings{})
 		require.NoError(t, err)
 		require.Equal(t, "", text)
 	})
@@ -161,6 +164,10 @@ func TestExtract(t *testing.T) {
 
 type customTestPdfExtractor struct{}
 
+func (te *customTestPdfExtractor) Name() string {
+	return "customTestPdfExtractor"
+}
+
 func (te *customTestPdfExtractor) Match(filename string) bool {
 	return strings.HasSuffix(filename, ".pdf")
 }
@@ -171,6 +178,10 @@ func (te *customTestPdfExtractor) Extract(filename string, r io.ReadSeeker) (str
 
 type failingExtractor struct{}
 
+func (te *failingExtractor) Name() string {
+	return "failingExtractor"
+}
+
 func (te *failingExtractor) Match(filename string) bool {
 	return true
 }
@@ -180,11 +191,12 @@ func (te *failingExtractor) Extract(filename string, r io.ReadSeeker) (string, e
 }
 
 func TestExtractWithExtraExtractors(t *testing.T) {
+	logger := mlog.CreateConsoleTestLogger(t)
 	t.Run("override existing extractor", func(t *testing.T) {
 		data, err := testutils.ReadTestFile("sample-doc.pdf")
 		require.NoError(t, err)
 
-		text, err := ExtractWithExtraExtractors("sample-doc.pdf", bytes.NewReader(data), ExtractSettings{}, []Extractor{&customTestPdfExtractor{}})
+		text, err := ExtractWithExtraExtractors(logger, "sample-doc.pdf", bytes.NewReader(data), ExtractSettings{}, []Extractor{&customTestPdfExtractor{}})
 		require.NoError(t, err)
 		require.Equal(t, text, "this is a text generated content")
 	})
@@ -193,7 +205,7 @@ func TestExtractWithExtraExtractors(t *testing.T) {
 		data, err := testutils.ReadTestFile("sample-doc.pdf")
 		require.NoError(t, err)
 
-		text, err := ExtractWithExtraExtractors("sample-doc.pdf", bytes.NewReader(data), ExtractSettings{}, []Extractor{&failingExtractor{}})
+		text, err := ExtractWithExtraExtractors(logger, "sample-doc.pdf", bytes.NewReader(data), ExtractSettings{}, []Extractor{&failingExtractor{}})
 		require.NoError(t, err)
 		assert.Contains(t, text, "simple")
 		assert.Contains(t, text, "document")

server/platform/services/docextractor/documents.go

@@ -26,6 +26,10 @@ var doconvConverterByExtensions = map[string]func(io.Reader) (string, map[string
 	"pdf": docconv.ConvertPDF,
 }
 
+func (de *documentExtractor) Name() string {
+	return "documentExtractor"
+}
+
 func (de *documentExtractor) Match(filename string) bool {
 	extension := strings.TrimPrefix(path.Ext(filename), ".")
 	_, ok := doconvConverterByExtensions[extension]

server/platform/services/docextractor/interface.go

@@ -11,4 +11,5 @@ import (
 type Extractor interface {
 	Match(filename string) bool
 	Extract(filename string, file io.ReadSeeker) (string, error)
+	Name() string
 }

server/platform/services/docextractor/mmpreview.go

@@ -36,6 +36,10 @@ func newMMPreviewExtractor(url string, secret string, pdfExtractor pdfExtractor)
 	return &mmPreviewExtractor{url: url, secret: secret, pdfExtractor: pdfExtractor}
 }
 
+func (mpe *mmPreviewExtractor) Name() string {
+	return "mmPreviewExtractor"
+}
+
 func (mpe *mmPreviewExtractor) Match(filename string) bool {
 	extension := strings.TrimPrefix(path.Ext(filename), ".")
 	return mmpreviewSupportedExtensions[extension]

server/platform/services/docextractor/pdf.go

@@ -17,6 +17,10 @@ import (
 
 type pdfExtractor struct{}
 
+func (pe *pdfExtractor) Name() string {
+	return "pdfExtractor"
+}
+
 func (pe *pdfExtractor) Match(filename string) bool {
 	supportedExtensions := map[string]bool{
 		"pdf": true,

server/platform/services/docextractor/plain.go

@@ -11,6 +11,10 @@ import (
 
 type plainExtractor struct{}
 
+func (pe *plainExtractor) Name() string {
+	return "plainExtractor"
+}
+
 func (pe *plainExtractor) Match(filename string) bool {
 	return true
 }