/
extract.go
338 lines (288 loc) · 8.26 KB
/
extract.go
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
/*
Copyright 2018 The pdfcpu Authors.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
*/
package pdfcpu
import (
"bytes"
"io"
"strings"
"github.com/pdfcpu/pdfcpu/pkg/filter"
"github.com/pdfcpu/pdfcpu/pkg/log"
"github.com/pkg/errors"
)
// Image is a Reader representing an image resource.
type Image struct {
io.Reader
Name string // Resource name
Type string // File type
}
// ImageObjNrs returns all image dict objNrs for pageNr.
// Requires an optimized context.
func (ctx *Context) ImageObjNrs(pageNr int) []int {
// TODO Exclude SMask image objects.
objNrs := []int{}
for k, v := range ctx.Optimize.PageImages[pageNr-1] {
if v {
objNrs = append(objNrs, k)
}
}
return objNrs
}
// ExtractImage extracts an image from image dict referenced by objNr.
// Supported imgTypes: FlateDecode, DCTDecode, JPXDecode
func (ctx *Context) ExtractImage(objNr int) (*Image, error) {
imageObj := ctx.Optimize.ImageObjects[objNr]
imageDict := imageObj.ImageDict
fpl := imageDict.FilterPipeline
if fpl == nil {
return nil, nil
}
var s []string
for _, filter := range fpl {
s = append(s, filter.Name)
}
filters := strings.Join(s, ",")
// Ignore filter chains with length > 1
if len(fpl) > 1 {
log.Info.Printf("ExtractImage(%d): skip img with more than 1 filter: %s\n", objNr, filters)
return nil, nil
}
f := fpl[0].Name
// We do not extract imageMasks with the exception of CCITTDecoded images
if im := imageDict.BooleanEntry("ImageMask"); im != nil && *im {
if f != filter.CCITTFax {
log.Info.Printf("ExtractImage(%d): skip img with imageMask\n", objNr)
return nil, nil
}
}
// Ignore if image has a soft mask defined.
// if sm, _ := imageDict.Find("SMask"); sm != nil {
// log.Info.Printf("extractImageData: ignore obj# %d, unsupported \"SMask\"\n", objNr)
// return nil, nil
// }
// Ignore if image has a Mask defined.
if sm, _ := imageDict.Find("Mask"); sm != nil {
log.Info.Printf("ExtractImage(%d): skip image, unsupported \"Mask\"\n", objNr)
return nil, nil
}
// CCITTDecoded images sometimes don't have a ColorSpace attribute.
if f == filter.CCITTFax {
_, err := ctx.DereferenceDictEntry(imageDict.Dict, "ColorSpace")
if err != nil {
imageDict.InsertName("ColorSpace", DeviceGrayCS)
}
}
switch f {
case filter.Flate, filter.CCITTFax:
// If color space is CMYK then write .tif else write .png
if err := imageDict.Decode(); err != nil {
return nil, err
}
case filter.DCT:
//imageObj.Extension = "jpg"
case filter.JPX:
//imageObj.Extension = "jpx"
default:
log.Debug.Printf("ExtractImage(%d): skip img, filter %s unsupported\n", objNr, filters)
return nil, nil
}
resourceName := imageObj.ResourceNames[0]
return RenderImage(ctx.XRefTable, imageDict, resourceName, objNr)
}
// ExtractPageImages extracts all images used by pageNr.
func (ctx *Context) ExtractPageImages(pageNr int) ([]Image, error) {
ii := []Image{}
for _, objNr := range ctx.ImageObjNrs(pageNr) {
i, err := ctx.ExtractImage(objNr)
if err != nil {
return nil, err
}
if i != nil {
ii = append(ii, *i)
}
}
return ii, nil
}
// Font is a Reader representing an embedded font.
type Font struct {
io.Reader
Name string
Type string
}
// FontObjNrs returns all font dict objNrs for pageNr.
// Requires an optimized context.
func (ctx *Context) FontObjNrs(pageNr int) []int {
objNrs := []int{}
for k, v := range ctx.Optimize.PageFonts[pageNr-1] {
if v {
objNrs = append(objNrs, k)
}
}
return objNrs
}
// ExtractFont extracts a font from font dict by objNr.
func (ctx *Context) ExtractFont(objNr int) (*Font, error) {
fontObject := ctx.Optimize.FontObjects[objNr]
// Only embedded fonts have binary data.
if !fontObject.Embedded() {
log.Debug.Printf("ExtractFont: ignoring obj#%d - non embedded font: %s\n", objNr, fontObject.FontName)
return nil, nil
}
d, err := fontDescriptor(ctx.XRefTable, fontObject.FontDict, objNr)
if err != nil {
return nil, err
}
if d == nil {
log.Debug.Printf("ExtractFont: ignoring obj#%d - no fontDescriptor available for font: %s\n", objNr, fontObject.FontName)
return nil, nil
}
ir := fontDescriptorFontFileIndirectObjectRef(d)
if ir == nil {
log.Debug.Printf("ExtractFont: ignoring obj#%d - no font file available for font: %s\n", objNr, fontObject.FontName)
return nil, nil
}
var f *Font
fontType := fontObject.SubType()
switch fontType {
case "TrueType":
// ttf ... true type file
// ttc ... true type collection
sd, _, err := ctx.DereferenceStreamDict(*ir)
if err != nil {
return nil, err
}
if sd == nil {
return nil, errors.Errorf("extractFontData: corrupt font obj#%d for font: %s\n", objNr, fontObject.FontName)
}
// Decode streamDict if used filter is supported only.
err = sd.Decode()
if err == filter.ErrUnsupportedFilter {
return nil, nil
}
if err != nil {
return nil, err
}
f = &Font{bytes.NewReader(sd.Content), fontObject.FontName, "ttf"}
default:
log.Info.Printf("extractFontData: ignoring obj#%d - unsupported fonttype %s - font: %s\n", objNr, fontType, fontObject.FontName)
return nil, nil
}
return f, nil
}
// ExtractPageFonts extracts all fonts used by pageNr.
func (ctx *Context) ExtractPageFonts(pageNr int) ([]Font, error) {
ff := []Font{}
for _, i := range ctx.FontObjNrs(pageNr) {
f, err := ctx.ExtractFont(i)
if err != nil {
return nil, err
}
if f != nil {
ff = append(ff, *f)
}
}
return ff, nil
}
// ExtractPage extracts pageNr into a new single page context.
func (ctx *Context) ExtractPage(pageNr int) (*Context, error) {
return ctx.ExtractPages([]int{pageNr}, false)
}
// ExtractPages extracts pageNrs into a new single page context.
func (ctx *Context) ExtractPages(pageNrs []int, usePgCache bool) (*Context, error) {
ctxDest, err := CreateContextWithXRefTable(nil, PaperSize["A4"])
if err != nil {
return nil, err
}
if err := AddPages(ctx, ctxDest, pageNrs, usePgCache); err != nil {
return nil, err
}
return ctxDest, nil
}
// ExtractPageContent extracts the consolidated page content stream for pageNr.
func (ctx *Context) ExtractPageContent(pageNr int) (io.Reader, error) {
consolidateRes := false
d, _, err := ctx.PageDict(pageNr, consolidateRes)
if err != nil {
return nil, err
}
bb, err := ctx.PageContent(d)
if err != nil && err != errNoContent {
return nil, err
}
return bytes.NewReader(bb), nil
}
// Metadata is a Reader representing a metadata dict.
type Metadata struct {
io.Reader // metadata
ObjNr int // metadata dict objNr
ParentObjNr int // container object number
ParentType string // container dict type
}
func extractMetadataFromDict(ctx *Context, d Dict, parentObjNr int) (*Metadata, error) {
o, found := d.Find("Metadata")
if !found || o == nil {
return nil, nil
}
sd, _, err := ctx.DereferenceStreamDict(o)
if err != nil {
return nil, err
}
if sd == nil {
return nil, nil
}
// Get metadata dict object number.
ir, _ := o.(IndirectRef)
mdObjNr := ir.ObjectNumber.Value()
// Get container dict type.
dt := "unknown"
if d.Type() != nil {
dt = *d.Type()
}
// Decode streamDict for supported filters only.
if err = sd.Decode(); err == filter.ErrUnsupportedFilter {
return nil, nil
}
if err != nil {
return nil, err
}
return &Metadata{bytes.NewReader(sd.Content), mdObjNr, parentObjNr, dt}, nil
}
// ExtractMetadata returns all metadata of ctx.
func (ctx *Context) ExtractMetadata() ([]Metadata, error) {
mm := []Metadata{}
for k, v := range ctx.Table {
if v.Free || v.Compressed {
continue
}
switch d := v.Object.(type) {
case Dict:
md, err := extractMetadataFromDict(ctx, d, k)
if err != nil {
return nil, err
}
if md == nil {
continue
}
mm = append(mm, *md)
case StreamDict:
md, err := extractMetadataFromDict(ctx, d.Dict, k)
if err != nil {
return nil, err
}
if md == nil {
continue
}
mm = append(mm, *md)
}
}
return mm, nil
}