feat(split): add splitUnify form field

This commit is contained in:
Julien Neuhart
2024-12-21 12:14:23 +01:00
parent 51a913a5e4
commit 8bc29ad92d
9 changed files with 106 additions and 64 deletions

View File

@@ -43,6 +43,10 @@ type SplitMode struct {
// Span is either the intervals or the page ranges to extract, depending on
// the selected mode.
Span string
// Unify specifies whether to put extracted pages into a single file or as
// many files as there are page ranges. Only works with "pages" mode.
Unify bool
}
const (

View File

@@ -79,8 +79,12 @@ func (engine *PdfCpu) Split(ctx context.Context, logger *zap.Logger, mode gotenb
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)
if mode.Unify {
outputPath := fmt.Sprintf("%s/%s", outputDirPath, filepath.Base(inputPath))
args = append(args, "trim", "-pages", mode.Span, inputPath, outputPath)
break
}
args = append(args, "extract", "-mode", "page", "-pages", mode.Span, inputPath, outputDirPath)
default:
return nil, fmt.Errorf("split PDFs using mode '%s' with pdfcpu: %w", mode.Mode, gotenberg.ErrPdfSplitModeNotSupported)
}

View File

@@ -189,6 +189,14 @@ func TestPdfCpu_Split(t *testing.T) {
expectError: false,
expectOutputPathsCount: 1,
},
{
scenario: "success (pages & unify)",
ctx: context.TODO(),
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2", Unify: true},
inputPath: "/tests/test/testdata/pdfengines/sample1.pdf",
expectError: false,
expectOutputPathsCount: 1,
},
} {
t.Run(tc.scenario, func(t *testing.T) {
engine := new(PdfCpu)

View File

@@ -18,8 +18,9 @@ import (
// FormDataPdfSplitMode creates a [gotenberg.SplitMode] from the form data.
func FormDataPdfSplitMode(form *api.FormData, mandatory bool) gotenberg.SplitMode {
var (
mode string
span string
mode string
span string
unify bool
)
splitModeFunc := func(value string) error {
@@ -66,9 +67,19 @@ func FormDataPdfSplitMode(form *api.FormData, mandatory bool) gotenberg.SplitMod
})
}
form.
Bool("splitUnify", &unify, false).
Custom("splitUnify", func(value string) error {
if value != "" && unify && mode != gotenberg.SplitModePages {
return fmt.Errorf("unify is not available for split mode '%s'", mode)
}
return nil
})
return gotenberg.SplitMode{
Mode: mode,
Span: span,
Mode: mode,
Span: span,
Unify: unify,
}
}
@@ -160,16 +171,20 @@ func SplitPdfStub(ctx *api.Context, engine gotenberg.PdfEngine, mode gotenberg.S
return nil, fmt.Errorf("split PDF '%s': %w", inputPath, err)
}
if mode.Mode == gotenberg.SplitModePages {
return paths, nil
}
// Keep the original filename.
for i, path := range paths {
newPath := fmt.Sprintf(
"%s/%s_%d.pdf",
outputDirPath, filenameNoExt, i,
)
var newPath string
if mode.Unify && mode.Mode == gotenberg.SplitModePages {
newPath = fmt.Sprintf(
"%s/%s.pdf",
outputDirPath, filenameNoExt,
)
} else {
newPath = fmt.Sprintf(
"%s/%s_%d.pdf",
outputDirPath, filenameNoExt, i,
)
}
err = ctx.Rename(path, newPath)
if err != nil {
@@ -177,6 +192,10 @@ func SplitPdfStub(ctx *api.Context, engine gotenberg.PdfEngine, mode gotenberg.S
}
outputPaths = append(outputPaths, newPath)
if mode.Unify && mode.Mode == gotenberg.SplitModePages {
break
}
}
}

View File

@@ -93,6 +93,27 @@ func TestFormDataPdfSplitMode(t *testing.T) {
expectedSplitMode: gotenberg.SplitMode{Mode: gotenberg.SplitModeIntervals},
expectValidationError: true,
},
{
scenario: "invalid splitUnify (intervals)",
ctx: func() *api.ContextMock {
ctx := &api.ContextMock{Context: new(api.Context)}
ctx.SetValues(map[string][]string{
"splitMode": {
"intervals",
},
"splitSpan": {
"1",
},
"splitUnify": {
"true",
},
})
return ctx
}(),
mandatory: false,
expectedSplitMode: gotenberg.SplitMode{Mode: gotenberg.SplitModeIntervals, Span: "1", Unify: true},
expectValidationError: true,
},
{
scenario: "valid form fields (intervals)",
ctx: func() *api.ContextMock {
@@ -122,11 +143,14 @@ func TestFormDataPdfSplitMode(t *testing.T) {
"splitSpan": {
"1-2",
},
"splitUnify": {
"true",
},
})
return ctx
}(),
mandatory: false,
expectedSplitMode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2"},
expectedSplitMode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2", Unify: true},
expectValidationError: false,
},
{
@@ -442,7 +466,7 @@ func TestSplitPdfStub(t *testing.T) {
},
{
scenario: "success (pages)",
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2"},
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2", Unify: true},
ctx: func() *api.ContextMock {
ctx := &api.ContextMock{Context: new(api.Context)}
ctx.SetMkdirAll(&gotenberg.MkdirAllMock{MkdirAllMock: func(path string, perm os.FileMode) error {
@@ -940,7 +964,7 @@ func TestSplitHandler(t *testing.T) {
expectOutputPathsCount: 0,
},
{
scenario: "success (intervals)",
scenario: "success",
ctx: func() *api.ContextMock {
ctx := &api.ContextMock{Context: new(api.Context)}
ctx.SetFiles(map[string]string{
@@ -978,45 +1002,6 @@ func TestSplitHandler(t *testing.T) {
expectOutputPathsCount: 2,
expectOutputPaths: []string{"/file/file_0.pdf", "/file/file_1.pdf"},
},
{
scenario: "success (pages)",
ctx: func() *api.ContextMock {
ctx := &api.ContextMock{Context: new(api.Context)}
ctx.SetFiles(map[string]string{
"file.pdf": "/file.pdf",
})
ctx.SetValues(map[string][]string{
"splitMode": {
gotenberg.SplitModePages,
},
"splitSpan": {
"1-2",
},
"pdfua": {
"true",
},
"metadata": {
"{\"Creator\": \"foo\", \"Producer\": \"bar\" }",
},
})
return ctx
}(),
engine: &gotenberg.PdfEngineMock{
SplitMock: func(ctx context.Context, logger *zap.Logger, mode gotenberg.SplitMode, inputPath, outputDirPath string) ([]string, error) {
return []string{"/file/file.pdf"}, nil
},
ConvertMock: func(ctx context.Context, logger *zap.Logger, formats gotenberg.PdfFormats, inputPath, outputPath string) error {
return nil
},
WriteMetadataMock: func(ctx context.Context, logger *zap.Logger, metadata map[string]interface{}, inputPath string) error {
return nil
},
},
expectError: false,
expectHttpError: false,
expectOutputPathsCount: 1,
expectOutputPaths: []string{"/file/file.pdf"},
},
} {
t.Run(tc.scenario, func(t *testing.T) {
tc.ctx.SetLogger(zap.NewNop())

View File

@@ -59,6 +59,9 @@ func (engine *PdfTk) Split(ctx context.Context, logger *zap.Logger, mode gotenbe
switch mode.Mode {
case gotenberg.SplitModePages:
if !mode.Unify {
return nil, fmt.Errorf("split PDFs using mode '%s' without unify with PDFtk: %w", mode.Mode, gotenberg.ErrPdfSplitModeNotSupported)
}
args = append(args, inputPath, "cat", mode.Span, "output", outputPath)
default:
return nil, fmt.Errorf("split PDFs using mode '%s' with PDFtk: %w", mode.Mode, gotenberg.ErrPdfSplitModeNotSupported)

View File

@@ -159,25 +159,33 @@ func TestPdfCpu_Split(t *testing.T) {
expectedError: gotenberg.ErrPdfSplitModeNotSupported,
expectOutputPathsCount: 0,
},
{
scenario: "ErrPdfSplitModeNotSupported (no unify with pages)",
ctx: context.TODO(),
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1", Unify: false},
expectError: true,
expectedError: gotenberg.ErrPdfSplitModeNotSupported,
expectOutputPathsCount: 0,
},
{
scenario: "invalid context",
ctx: nil,
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2"},
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2", Unify: true},
expectError: true,
expectOutputPathsCount: 0,
},
{
scenario: "invalid input path",
ctx: context.TODO(),
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2"},
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2", Unify: true},
inputPath: "",
expectError: true,
expectOutputPathsCount: 0,
},
{
scenario: "success (pages)",
scenario: "success (pages & unify)",
ctx: context.TODO(),
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2"},
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2", Unify: true},
inputPath: "/tests/test/testdata/pdfengines/sample1.pdf",
expectError: false,
expectOutputPathsCount: 1,

View File

@@ -59,6 +59,9 @@ func (engine *QPdf) Split(ctx context.Context, logger *zap.Logger, mode gotenber
switch mode.Mode {
case gotenberg.SplitModePages:
if !mode.Unify {
return nil, fmt.Errorf("split PDFs using mode '%s' without unify with QPDF: %w", mode.Mode, gotenberg.ErrPdfSplitModeNotSupported)
}
args = append(args, inputPath, "--pages", ".", mode.Span, "--", outputPath)
default:
return nil, fmt.Errorf("split PDFs using mode '%s' with QPDF: %w", mode.Mode, gotenberg.ErrPdfSplitModeNotSupported)

View File

@@ -159,25 +159,33 @@ func TestQPdf_Split(t *testing.T) {
expectedError: gotenberg.ErrPdfSplitModeNotSupported,
expectOutputPathsCount: 0,
},
{
scenario: "ErrPdfSplitModeNotSupported (no unify with pages)",
ctx: context.TODO(),
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1", Unify: false},
expectError: true,
expectedError: gotenberg.ErrPdfSplitModeNotSupported,
expectOutputPathsCount: 0,
},
{
scenario: "invalid context",
ctx: nil,
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2"},
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2", Unify: true},
expectError: true,
expectOutputPathsCount: 0,
},
{
scenario: "invalid input path",
ctx: context.TODO(),
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2"},
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2", Unify: true},
inputPath: "",
expectError: true,
expectOutputPathsCount: 0,
},
{
scenario: "success (pages)",
scenario: "success (pages & unify)",
ctx: context.TODO(),
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2"},
mode: gotenberg.SplitMode{Mode: gotenberg.SplitModePages, Span: "1-2", Unify: true},
inputPath: "/tests/test/testdata/pdfengines/sample1.pdf",
expectError: false,
expectOutputPathsCount: 1,