fix: special characters issues with filenames (#736)

2026-08-08 00:22:14 +01:00 · 2023-12-05 16:34:35 +01:00
parent 66142b1dd8
commit 130b94aa8c
5 changed files with 174 additions and 31 deletions
--- a/go.mod
+++ b/go.mod
@@ -5,13 +5,13 @@ go 1.21
 require (
 	github.com/alexliesenfeld/health v0.8.0
 	github.com/andybalholm/brotli v1.0.6 // indirect
-	github.com/chromedp/cdproto v0.0.0-20231114014204-3e458d5176f9
+	github.com/chromedp/cdproto v0.0.0-20231205062650-00455a960d61
 	github.com/chromedp/chromedp v0.9.3
 	github.com/golang/snappy v0.0.4 // indirect
 	github.com/google/uuid v1.4.0
 	github.com/hashicorp/go-cleanhttp v0.5.2 // indirect
 	github.com/hashicorp/go-retryablehttp v0.7.5
-	github.com/klauspost/compress v1.17.3 // indirect
+	github.com/klauspost/compress v1.17.4 // indirect
 	github.com/klauspost/pgzip v1.2.6 // indirect
 	github.com/labstack/echo/v4 v4.11.3
 	github.com/labstack/gommon v0.4.1
@@ -27,12 +27,12 @@ require (
 	github.com/ulikunitz/xz v0.5.11 // indirect
 	go.uber.org/multierr v1.11.0
 	go.uber.org/zap v1.26.0
-	golang.org/x/crypto v0.15.0 // indirect
+	golang.org/x/crypto v0.16.0 // indirect
 	golang.org/x/image v0.14.0 // indirect
-	golang.org/x/net v0.18.0
+	golang.org/x/net v0.19.0
 	golang.org/x/sync v0.5.0
-	golang.org/x/sys v0.14.0 // indirect
-	golang.org/x/term v0.14.0
+	golang.org/x/sys v0.15.0 // indirect
+	golang.org/x/term v0.15.0
 	golang.org/x/text v0.14.0
 )

--- a/go.sum
+++ b/go.sum
@@ -10,8 +10,8 @@ github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6r
 github.com/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
 github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/chromedp/cdproto v0.0.0-20231011050154-1d073bb38998/go.mod h1:GKljq0VrfU4D5yc+2qA6OVr8pmO/MBbPEWqWQ/oqGEs=
-github.com/chromedp/cdproto v0.0.0-20231114014204-3e458d5176f9 h1:e3tMnG8i9SfKOilykpprojNk3a49O4dn+wqZsam1qYQ=
-github.com/chromedp/cdproto v0.0.0-20231114014204-3e458d5176f9/go.mod h1:GKljq0VrfU4D5yc+2qA6OVr8pmO/MBbPEWqWQ/oqGEs=
+github.com/chromedp/cdproto v0.0.0-20231205062650-00455a960d61 h1:XD280QPATe9jaz20dylKe3vBsNcH1w3mkssGY0lidn8=
+github.com/chromedp/cdproto v0.0.0-20231205062650-00455a960d61/go.mod h1:GKljq0VrfU4D5yc+2qA6OVr8pmO/MBbPEWqWQ/oqGEs=
 github.com/chromedp/chromedp v0.9.3 h1:Wq58e0dZOdHsxaj9Owmfcf+ibtpYN1N0FWVbaxa/esg=
 github.com/chromedp/chromedp v0.9.3/go.mod h1:NipeUkUcuzIdFbBP8eNNvl9upcceOfWzoJn6cRe4ksA=
 github.com/chromedp/sysutil v1.0.0 h1:+ZxhTpfpZlmchB58ih/LBHX52ky7w2VhQVKQMucy3Ic=
@@ -53,8 +53,8 @@ github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8Hm
 github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
 github.com/klauspost/compress v1.4.1/go.mod h1:RyIbtBH6LamlWaDj8nUwkbUhJ87Yi3uG0guNDohfE1A=
 github.com/klauspost/compress v1.11.4/go.mod h1:aoV0uJVorq1K+umq18yTdKaF57EivdYsUV+/s2qKfXs=
-github.com/klauspost/compress v1.17.3 h1:qkRjuerhUU1EmXLYGkSH6EZL+vPSxIrYjLNAK4slzwA=
-github.com/klauspost/compress v1.17.3/go.mod h1:/dCuZOvVtNoHsyb+cuJD3itjs3NbnF6KH9zAO4BDxPM=
+github.com/klauspost/compress v1.17.4 h1:Ej5ixsIri7BrIjBkRZLTo6ghwrEtHFk7ijlczPW4fZ4=
+github.com/klauspost/compress v1.17.4/go.mod h1:/dCuZOvVtNoHsyb+cuJD3itjs3NbnF6KH9zAO4BDxPM=
 github.com/klauspost/cpuid v1.2.0/go.mod h1:Pj4uuM528wm8OyEC2QMXAi2YiTZ96dNQPGgoMS4s3ek=
 github.com/klauspost/pgzip v1.2.5/go.mod h1:Ch1tH69qFZu15pkjo5kYi6mth2Zzwzt50oCQKQE9RUs=
 github.com/klauspost/pgzip v1.2.6 h1:8RXeL5crjEUFnR2/Sn6GJNWtSQ3Dk8pq4CL3jvdDyjU=
@@ -136,20 +136,20 @@ go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
 go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
 go.uber.org/zap v1.26.0 h1:sI7k6L95XOKS281NhVKOFCUNIvv9e0w4BF8N3u+tCRo=
 go.uber.org/zap v1.26.0/go.mod h1:dtElttAiwGvoJ/vj4IwHBS/gXsEu/pZ50mUIRWuG0so=
-golang.org/x/crypto v0.15.0 h1:frVn1TEaCEaZcn3Tmd7Y2b5KKPaZ+I32Q2OA3kYp5TA=
-golang.org/x/crypto v0.15.0/go.mod h1:4ChreQoLWfG3xLDer1WdlH5NdlQ3+mwnQq1YTKY+72g=
+golang.org/x/crypto v0.16.0 h1:mMMrFzRSCF0GvB7Ne27XVtVAaXLrPmgPC7/v0tkwHaY=
+golang.org/x/crypto v0.16.0/go.mod h1:gCAAfMLgwOJRpTjQ2zCCt2OcSfYMTeZVSRtQlPC7Nq4=
 golang.org/x/image v0.14.0 h1:tNgSxAFe3jC4uYqvZdTr84SZoM1KfwdC9SKIFrLjFn4=
 golang.org/x/image v0.14.0/go.mod h1:HUYqC05R2ZcZ3ejNQsIHQDQiwWM4JBqmm6MKANTp4LE=
-golang.org/x/net v0.18.0 h1:mIYleuAkSbHh0tCv7RvjL3F6ZVbLjq4+R7zbOn3Kokg=
-golang.org/x/net v0.18.0/go.mod h1:/czyP5RqHAH4odGYxBJ1qz0+CE5WZ+2j1YgoEo8F2jQ=
+golang.org/x/net v0.19.0 h1:zTwKpTd2XuCqf8huc7Fo2iSy+4RHPd10s4KzeTnVr1c=
+golang.org/x/net v0.19.0/go.mod h1:CfAk/cbD4CthTvqiEl8NpboMuiuOYsAr/7NOjZJtv1U=
 golang.org/x/sync v0.5.0 h1:60k92dhOjHxJkrqnwsfl8KuaHbn/5dl0lUPUklKo3qE=
 golang.org/x/sync v0.5.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.14.0 h1:Vz7Qs629MkJkGyHxUlRHizWJRG2j8fbQKjELVSNhy7Q=
-golang.org/x/sys v0.14.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/term v0.14.0 h1:LGK9IlZ8T9jvdy6cTdfKUCltatMFOehAQo9SRC46UQ8=
-golang.org/x/term v0.14.0/go.mod h1:TySc+nGkYR6qt8km8wUhuFRTVSMIX3XPR58y2lC8vww=
+golang.org/x/sys v0.15.0 h1:h48lPFYpsTvQJZF4EKyI4aLHaev3CxivZmv7yZig9pc=
+golang.org/x/sys v0.15.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/term v0.15.0 h1:y/Oo/a/q3IXu26lQgl04j/gjuBDOBlx7X6Om1j2CPW4=
+golang.org/x/term v0.15.0/go.mod h1:BDl952bC7+uMoWR75FIrCDx79TPU9oHkTZ9yRbYOrX0=
 golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
--- a/pkg/modules/api/context.go
+++ b/pkg/modules/api/context.go
@@ -12,14 +12,11 @@ import (
 	"path/filepath"
 	"strings"
 	"time"
-	"unicode"

 	"github.com/google/uuid"
 	"github.com/labstack/echo/v4"
 	"github.com/mholt/archiver/v3"
 	"go.uber.org/zap"
-	"golang.org/x/text/runes"
-	"golang.org/x/text/transform"
 	"golang.org/x/text/unicode/norm"

 	"github.com/gotenberg/gotenberg/v7/pkg/gotenberg"
@@ -124,15 +121,6 @@ func newContext(echoCtx echo.Context, logger *zap.Logger, fs *gotenberg.FileSyst
 	ctx.files = make(map[string]string)

 	copyToDisk := func(fh *multipart.FileHeader) error {
-		// Avoid directory traversal and normalize filename.
-		// See https://github.com/gotenberg/gotenberg/issues/104.
-		t := transform.Chain(norm.NFD, runes.Remove(runes.In(unicode.Mn)), norm.NFC)
-
-		filename, _, err := transform.String(t, filepath.Base(fh.Filename))
-		if err != nil {
-			return fmt.Errorf("transform filename: %w", err)
-		}
-
 		in, err := fh.Open()
 		if err != nil {
 			return fmt.Errorf("open multipart file: %w", err)
@@ -145,6 +133,10 @@ func newContext(echoCtx echo.Context, logger *zap.Logger, fs *gotenberg.FileSyst
 			}
 		}()

+		// Avoid directory traversal and make sure filename characters are
+		// normalized.
+		// See: https://github.com/gotenberg/gotenberg/issues/662.
+		filename := norm.NFC.String(filepath.Base(fh.Filename))
 		path := fmt.Sprintf("%s/%s", ctx.dirPath, filename)

 		out, err := os.Create(path)
--- a/pkg/modules/libreoffice/api/libreoffice.go
+++ b/pkg/modules/libreoffice/api/libreoffice.go
@@ -4,12 +4,15 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"io"
 	"net"
 	"os"
+	"path/filepath"
 	"sync"
 	"sync/atomic"
 	"time"

+	"github.com/google/uuid"
 	"go.uber.org/zap"

 	"github.com/gotenberg/gotenberg/v7/pkg/gotenberg"
@@ -290,6 +293,11 @@ func (p *libreOfficeProcess) pdf(ctx context.Context, logger *zap.Logger, inputP
 		)
 	}

+	inputPath, err := nonBasicLatinCharactersGuard(logger, inputPath)
+	if err != nil {
+		return fmt.Errorf("non-basic latin characters guard: %w", err)
+	}
+
 	args = append(args, "--output", outputPath, inputPath)

 	cmd, err := gotenberg.CommandContext(ctx, logger, p.arguments.unoBinPath, args...)
@@ -321,6 +329,65 @@ func (p *libreOfficeProcess) pdf(ctx context.Context, logger *zap.Logger, inputP
 	return fmt.Errorf("convert to PDF: %w", err)
 }

+// LibreOffice cannot convert a file with a name containing non-basic Latin
+// characters.
+// See:
+// https://github.com/gotenberg/gotenberg/issues/104
+// https://github.com/gotenberg/gotenberg/issues/730
+func nonBasicLatinCharactersGuard(logger *zap.Logger, inputPath string) (string, error) {
+	hasNonBasicLatinChars := func(str string) bool {
+		for _, r := range str {
+			// Check if the character is outside basic Latin.
+			if r != '.' && (r < ' ' || r > '~') {
+				return true
+			}
+		}
+		return false
+	}
+
+	filename := filepath.Base(inputPath)
+	if !hasNonBasicLatinChars(filename) {
+		logger.Debug("no non-basic latin characters in filename, skip copy")
+		return inputPath, nil
+	}
+
+	logger.Warn("non-basic latin characters in filename, copy to a file with a valid filename")
+	basePath := filepath.Dir(inputPath)
+	ext := filepath.Ext(inputPath)
+	newInputPath := filepath.Join(basePath, fmt.Sprintf("%s%s", uuid.NewString(), ext))
+
+	in, err := os.Open(inputPath)
+	if err != nil {
+		return "", fmt.Errorf("open file: %w", err)
+	}
+
+	defer func() {
+		err := in.Close()
+		if err != nil {
+			logger.Error(fmt.Sprintf("close file: %s", err))
+		}
+	}()
+
+	out, err := os.Create(newInputPath)
+	if err != nil {
+		return "", fmt.Errorf("create new file: %w", err)
+	}
+
+	defer func() {
+		err := out.Close()
+		if err != nil {
+			logger.Error(fmt.Sprintf("close new file: %s", err))
+		}
+	}()
+
+	_, err = io.Copy(out, in)
+	if err != nil {
+		return "", fmt.Errorf("copy file to new file: %w", err)
+	}
+
+	return newInputPath, nil
+}
+
 // Interface guards.
 var (
 	_ gotenberg.Process = (*libreOfficeProcess)(nil)
--- a/pkg/modules/libreoffice/api/libreoffice_test.go
+++ b/pkg/modules/libreoffice/api/libreoffice_test.go
@@ -545,7 +545,7 @@ func TestLibreOfficeProcess_pdf(t *testing.T) {
 			err := tc.libreOffice.pdf(
 				ctx,
 				logger,
-				fmt.Sprintf("file://%s/document.txt", tc.fs.WorkingDirPath()),
+				fmt.Sprintf("%s/document.txt", tc.fs.WorkingDirPath()),
 				fmt.Sprintf("%s/%s.pdf", tc.fs.WorkingDirPath(), uuid.NewString()),
 				tc.options,
 			)
@@ -564,3 +564,87 @@ func TestLibreOfficeProcess_pdf(t *testing.T) {
 		})
 	}
 }
+
+func TestNonBasicLatinCharactersGuard(t *testing.T) {
+	for _, tc := range []struct {
+		scenario            string
+		fs                  *gotenberg.FileSystem
+		filename            string
+		expectSameInputPath bool
+		expectError         bool
+	}{
+		{
+			scenario: "basic latin characters",
+			fs: func() *gotenberg.FileSystem {
+				fs := gotenberg.NewFileSystem()
+
+				err := os.MkdirAll(fs.WorkingDirPath(), 0o755)
+				if err != nil {
+					t.Fatalf(fmt.Sprintf("expected no error but got: %v", err))
+				}
+
+				err = os.WriteFile(fmt.Sprintf("%s/document.txt", fs.WorkingDirPath()), []byte("Basic latin characters"), 0o755)
+				if err != nil {
+					t.Fatalf("expected no error but got: %v", err)
+				}
+
+				return fs
+			}(),
+			filename:            "document.txt",
+			expectSameInputPath: true,
+			expectError:         false,
+		},
+		{
+			scenario: "non-basic latin characters",
+			fs: func() *gotenberg.FileSystem {
+				fs := gotenberg.NewFileSystem()
+
+				err := os.MkdirAll(fs.WorkingDirPath(), 0o755)
+				if err != nil {
+					t.Fatalf(fmt.Sprintf("expected no error but got: %v", err))
+				}
+
+				err = os.WriteFile(fmt.Sprintf("%s/éèßàùä.txt", fs.WorkingDirPath()), []byte("Non-basic latin characters"), 0o755)
+				if err != nil {
+					t.Fatalf("expected no error but got: %v", err)
+				}
+
+				return fs
+			}(),
+			filename:            "éèßàùä.txt",
+			expectSameInputPath: false,
+			expectError:         false,
+		},
+	} {
+		t.Run(tc.scenario, func(t *testing.T) {
+			defer func() {
+				err := os.RemoveAll(tc.fs.WorkingDirPath())
+				if err != nil {
+					t.Fatalf("expected no error while cleaning up, but got: %v", err)
+				}
+			}()
+
+			inputPath := fmt.Sprintf("%s/%s", tc.fs.WorkingDirPath(), tc.filename)
+			newInputPath, err := nonBasicLatinCharactersGuard(
+				zap.NewNop(),
+				inputPath,
+			)
+
+			if !tc.expectError && err != nil {
+				t.Fatalf("expected no error but got: %v", err)
+			}
+
+			if tc.expectError && err == nil {
+				t.Fatal("expected error but got none")
+			}
+
+			if tc.expectSameInputPath && newInputPath != inputPath {
+				t.Fatalf("expected same input path, but got '%s'", newInputPath)
+			}
+
+			if !tc.expectSameInputPath && newInputPath == inputPath {
+				t.Fatalf("expected different input path, but got same '%s'", newInputPath)
+			}
+		})
+	}
+}