mirror of
https://github.com/gotenberg/gotenberg.git
synced 2026-08-13 10:52:15 +01:00
feat(pdfengines): add split feature
This commit is contained in:
@@ -2,6 +2,7 @@
|
||||
// interface using the pdfcpu command-line tool. This package allows for:
|
||||
//
|
||||
// 1. The merging of PDF files.
|
||||
// 2. The splitting of PDF files.
|
||||
//
|
||||
// See: https://github.com/pdfcpu/pdfcpu.
|
||||
package pdfcpu
|
||||
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
|
||||
"go.uber.org/zap"
|
||||
|
||||
@@ -70,6 +71,38 @@ func (engine *PdfCpu) Merge(ctx context.Context, logger *zap.Logger, inputPaths
|
||||
return fmt.Errorf("merge PDFs with pdfcpu: %w", err)
|
||||
}
|
||||
|
||||
// Split splits a given PDF file.
|
||||
func (engine *PdfCpu) Split(ctx context.Context, logger *zap.Logger, mode gotenberg.SplitMode, inputPath, outputDirPath string) ([]string, error) {
|
||||
var args []string
|
||||
|
||||
switch mode.Mode {
|
||||
case gotenberg.SplitModeIntervals:
|
||||
args = append(args, "split", "-mode", "span", inputPath, outputDirPath, mode.Span)
|
||||
case gotenberg.SplitModePages:
|
||||
outputPath := fmt.Sprintf("%s/%s", outputDirPath, filepath.Base(inputPath))
|
||||
args = append(args, "trim", "-pages", mode.Span, inputPath, outputPath)
|
||||
default:
|
||||
return nil, fmt.Errorf("split PDFs using mode '%s' with pdfcpu: %w", mode.Mode, gotenberg.ErrPdfSplitModeNotSupported)
|
||||
}
|
||||
|
||||
cmd, err := gotenberg.CommandContext(ctx, logger, engine.binPath, args...)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("create command: %w", err)
|
||||
}
|
||||
|
||||
_, err = cmd.Exec()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("split PDFs with pdfcpu: %w", err)
|
||||
}
|
||||
|
||||
outputPaths, err := gotenberg.WalkDir(outputDirPath, ".pdf")
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("walk directory to find resulting PDFs from split with pdfcpu: %w", err)
|
||||
}
|
||||
|
||||
return outputPaths, nil
|
||||
}
|
||||
|
||||
// Convert is not available in this implementation.
|
||||
func (engine *PdfCpu) Convert(ctx context.Context, logger *zap.Logger, formats gotenberg.PdfFormats, inputPath, outputPath string) error {
|
||||
return fmt.Errorf("convert PDF to '%+v' with pdfcpu: %w", formats, gotenberg.ErrPdfEngineMethodNotSupported)
|
||||
|
||||
@@ -116,7 +116,7 @@ func TestPdfCpu_Merge(t *testing.T) {
|
||||
t.Fatalf("expected error but got: %v", err)
|
||||
}
|
||||
|
||||
fs := gotenberg.NewFileSystem()
|
||||
fs := gotenberg.NewFileSystem(new(gotenberg.OsMkdirAll))
|
||||
outputDir, err := fs.MkdirAll()
|
||||
if err != nil {
|
||||
t.Fatalf("expected error but got: %v", err)
|
||||
@@ -142,6 +142,95 @@ func TestPdfCpu_Merge(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestPdfCpu_Split(t *testing.T) {
|
||||
for _, tc := range []struct {
|
||||
scenario string
|
||||
ctx context.Context
|
||||
mode gotenberg.SplitMode
|
||||
inputPath string
|
||||
expectError bool
|
||||
expectedError error
|
||||
expectOutputPathsCount int
|
||||
}{
|
||||
{
|
||||
scenario: "ErrPdfSplitModeNotSupported",
|
||||
expectError: true,
|
||||
expectedError: gotenberg.ErrPdfSplitModeNotSupported,
|
||||
expectOutputPathsCount: 0,
|
||||
},
|
||||
{
|
||||
scenario: "invalid context",
|
||||
ctx: nil,
|
||||
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModeIntervals, Span: "1"},
|
||||
expectError: true,
|
||||
expectOutputPathsCount: 0,
|
||||
},
|
||||
{
|
||||
scenario: "invalid input path",
|
||||
ctx: context.TODO(),
|
||||
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModeIntervals, Span: "1"},
|
||||
inputPath: "",
|
||||
expectError: true,
|
||||
expectOutputPathsCount: 0,
|
||||
},
|
||||
{
|
||||
scenario: "success (intervals)",
|
||||
ctx: context.TODO(),
|
||||
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModeIntervals, Span: "1"},
|
||||
inputPath: "/tests/test/testdata/pdfengines/sample1.pdf",
|
||||
expectError: false,
|
||||
expectOutputPathsCount: 3,
|
||||
},
|
||||
{
|
||||
scenario: "success (pages)",
|
||||
ctx: context.TODO(),
|
||||
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1"},
|
||||
inputPath: "/tests/test/testdata/pdfengines/sample1.pdf",
|
||||
expectError: false,
|
||||
expectOutputPathsCount: 1,
|
||||
},
|
||||
} {
|
||||
t.Run(tc.scenario, func(t *testing.T) {
|
||||
engine := new(PdfCpu)
|
||||
err := engine.Provision(nil)
|
||||
if err != nil {
|
||||
t.Fatalf("expected error but got: %v", err)
|
||||
}
|
||||
|
||||
fs := gotenberg.NewFileSystem(new(gotenberg.OsMkdirAll))
|
||||
outputDir, err := fs.MkdirAll()
|
||||
if err != nil {
|
||||
t.Fatalf("expected error but got: %v", err)
|
||||
}
|
||||
|
||||
defer func() {
|
||||
err = os.RemoveAll(fs.WorkingDirPath())
|
||||
if err != nil {
|
||||
t.Fatalf("expected no error while cleaning up but got: %v", err)
|
||||
}
|
||||
}()
|
||||
|
||||
outputPaths, err := engine.Split(tc.ctx, zap.NewNop(), tc.mode, tc.inputPath, outputDir)
|
||||
|
||||
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.expectedError != nil && !errors.Is(err, tc.expectedError) {
|
||||
t.Fatalf("expected error %v but got: %v", tc.expectedError, err)
|
||||
}
|
||||
|
||||
if tc.expectOutputPathsCount != len(outputPaths) {
|
||||
t.Errorf("expected %d output paths but got %d", tc.expectOutputPathsCount, len(outputPaths))
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestPdfCpu_Convert(t *testing.T) {
|
||||
mod := new(PdfCpu)
|
||||
err := mod.Convert(context.TODO(), zap.NewNop(), gotenberg.PdfFormats{}, "", "")
|
||||
|
||||
Reference in New Issue
Block a user