OrgGo/unipdf
1
0
Fork 0
mirror of https://github.com/unidoc/unipdf.git synced 2025-05-07 19:29:16 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #363 from adrg/image-extract-opts

Browse Source 
Add image extraction options
This commit is contained in:
Gunnsteinn Hall 2019-03-08 19:54:09 +00:00 committed by GitHub
commit c41dd7e028
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 30 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
pdf/extractor/image.go
View File

@ -12,10 +12,21 @@ import (
"github.com/unidoc/unidoc/pdf/model" "github.com/unidoc/unidoc/pdf/model"
) )
// ImageExtractOptions contains options for controlling image extraction from
// PDF pages.
type ImageExtractOptions struct {
IncludeInlineStencilMasks bool
}
// ExtractPageImages returns the image contents of the page extractor, including data // ExtractPageImages returns the image contents of the page extractor, including data
// and position, size information for each image. // and position, size information for each image.
func (e *Extractor) ExtractPageImages() (*PageImages, error) { // A set of options to control page image extraction can be passed in. The options
ctx := &imageExtractContext{} // parameter can be nil for the default options. By default, inline stencil masks
// are not extracted.
func (e *Extractor) ExtractPageImages(options *ImageExtractOptions) (*PageImages, error) {
ctx := &imageExtractContext{
options: options,
}
err := ctx.extractContentStreamImages(e.contents, e.resources) err := ctx.extractContentStreamImages(e.contents, e.resources)
if err != nil { if err != nil {
@ -59,6 +70,9 @@ type imageExtractContext struct {
// Cache to avoid processing same image many times. // Cache to avoid processing same image many times.
cacheXObjectImages map[*core.PdfObjectStream]*cachedImage cacheXObjectImages map[*core.PdfObjectStream]*cachedImage
// Extract options.
options *ImageExtractOptions
} }
type cachedImage struct { type cachedImage struct {
@ -76,6 +90,9 @@ func (ctx *imageExtractContext) extractContentStreamImages(contents string, reso
if ctx.cacheXObjectImages == nil { if ctx.cacheXObjectImages == nil {
ctx.cacheXObjectImages = map[*core.PdfObjectStream]*cachedImage{} ctx.cacheXObjectImages = map[*core.PdfObjectStream]*cachedImage{}
} }
if ctx.options == nil {
ctx.options = &ImageExtractOptions{}
}
processor := contentstream.NewContentStreamProcessor(*operations) processor := contentstream.NewContentStreamProcessor(*operations)
processor.AddHandler(contentstream.HandlerConditionEnumAllOperands, "", processor.AddHandler(contentstream.HandlerConditionEnumAllOperands, "",
@ -95,6 +112,12 @@ func (ctx *imageExtractContext) processOperand(op *contentstream.ContentStreamOp
return nil return nil
} }
if isImageMask, ok := core.GetBoolVal(iimg.ImageMask); ok {
if isImageMask && !ctx.options.IncludeInlineStencilMasks {
return nil
}
}
return ctx.extractInlineImage(iimg, gs, resources) return ctx.extractInlineImage(iimg, gs, resources)
} else if op.Operand == "Do" && len(op.Params) == 1 { } else if op.Operand == "Do" && len(op.Params) == 1 {
// Do: XObject. // Do: XObject.

10
pdf/extractor/image_test.go
View File

@ -87,7 +87,7 @@ func TestImageExtractionBasic(t *testing.T) {
pageExtractor, err := New(page) pageExtractor, err := New(page)
require.NoError(t, err) require.NoError(t, err)
pageImages, err := pageExtractor.ExtractPageImages() pageImages, err := pageExtractor.ExtractPageImages(nil)
require.NoError(t, err) require.NoError(t, err)
assert.Equal(t, len(tcase.Expected), len(pageImages.Images)) assert.Equal(t, len(tcase.Expected), len(pageImages.Images))
@ -177,7 +177,7 @@ func TestImageExtractionNestedCM(t *testing.T) {
pageExtractor, err := New(page) pageExtractor, err := New(page)
require.NoError(t, err) require.NoError(t, err)
pageImages, err := pageExtractor.ExtractPageImages() pageImages, err := pageExtractor.ExtractPageImages(nil)
require.NoError(t, err) require.NoError(t, err)
assert.Equal(t, len(tcase.Expected), len(pageImages.Images)) assert.Equal(t, len(tcase.Expected), len(pageImages.Images))
@ -222,7 +222,7 @@ func TestImageExtractionMulti(t *testing.T) {
pageExtractor, err := New(page) pageExtractor, err := New(page)
require.NoError(t, err) require.NoError(t, err)
pageImages, err := pageExtractor.ExtractPageImages() pageImages, err := pageExtractor.ExtractPageImages(nil)
require.NoError(t, err) require.NoError(t, err)
assert.Equal(t, tcase.NumImages, len(pageImages.Images)) assert.Equal(t, tcase.NumImages, len(pageImages.Images))
@ -303,7 +303,7 @@ func TestImageExtractionRealWorld(t *testing.T) {
pageExtractor, err := New(page) pageExtractor, err := New(page)
require.NoError(t, err) require.NoError(t, err)
pageImages, err := pageExtractor.ExtractPageImages() pageImages, err := pageExtractor.ExtractPageImages(nil)
require.NoError(t, err) require.NoError(t, err)
if len(tcase.Expected) == 0 { if len(tcase.Expected) == 0 {
@ -328,7 +328,7 @@ func BenchmarkImageExtraction(b *testing.B) {
pageExtractor, err := New(page) pageExtractor, err := New(page)
require.NoError(b, err) require.NoError(b, err)
pageImages, err := pageExtractor.ExtractPageImages() pageImages, err := pageExtractor.ExtractPageImages(nil)
require.NoError(b, err) require.NoError(b, err)
cnt += len(pageImages.Images) cnt += len(pageImages.Images)