@syncfusion/ej2-pdf-data-extract 30.1.41 → 30.2.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/ej2-pdf-data-extract.umd.min.js +1 -2
- package/dist/global/ej2-pdf-data-extract.min.js +1 -2
- package/dist/global/index.d.ts +1 -2
- package/package.json +14 -46
- package/dist/ts/index.d.ts +0 -20
- package/dist/ts/index.ts +0 -20
- package/dist/ts/pdf-data-extract/core/content-parser-helper.d.ts +0 -62
- package/dist/ts/pdf-data-extract/core/content-parser-helper.ts +0 -640
- package/dist/ts/pdf-data-extract/core/enum.d.ts +0 -6
- package/dist/ts/pdf-data-extract/core/enum.ts +0 -6
- package/dist/ts/pdf-data-extract/core/graphic-state.d.ts +0 -33
- package/dist/ts/pdf-data-extract/core/graphic-state.ts +0 -106
- package/dist/ts/pdf-data-extract/core/pdf-data-extractor.d.ts +0 -210
- package/dist/ts/pdf-data-extract/core/pdf-data-extractor.ts +0 -977
- package/dist/ts/pdf-data-extract/core/pdf-text-parser.d.ts +0 -67
- package/dist/ts/pdf-data-extract/core/pdf-text-parser.ts +0 -495
- package/dist/ts/pdf-data-extract/core/redaction/index.d.ts +0 -4
- package/dist/ts/pdf-data-extract/core/redaction/index.ts +0 -4
- package/dist/ts/pdf-data-extract/core/redaction/pdf-redaction-processor.d.ts +0 -55
- package/dist/ts/pdf-data-extract/core/redaction/pdf-redaction-processor.ts +0 -592
- package/dist/ts/pdf-data-extract/core/redaction/pdf-redaction-region.d.ts +0 -281
- package/dist/ts/pdf-data-extract/core/redaction/pdf-redaction-region.ts +0 -342
- package/dist/ts/pdf-data-extract/core/redaction/pdf-redactor.d.ts +0 -129
- package/dist/ts/pdf-data-extract/core/redaction/pdf-redactor.ts +0 -322
- package/dist/ts/pdf-data-extract/core/redaction/text-glyph-mapper.d.ts +0 -12
- package/dist/ts/pdf-data-extract/core/redaction/text-glyph-mapper.ts +0 -153
- package/dist/ts/pdf-data-extract/core/text-extraction/binary-cmap-reader.d.ts +0 -24
- package/dist/ts/pdf-data-extract/core/text-extraction/binary-cmap-reader.ts +0 -281
- package/dist/ts/pdf-data-extract/core/text-extraction/cmap.d.ts +0 -50
- package/dist/ts/pdf-data-extract/core/text-extraction/cmap.ts +0 -565
- package/dist/ts/pdf-data-extract/core/text-extraction/compact-font-parser.d.ts +0 -191
- package/dist/ts/pdf-data-extract/core/text-extraction/compact-font-parser.ts +0 -1928
- package/dist/ts/pdf-data-extract/core/text-extraction/encoding-utils.d.ts +0 -102
- package/dist/ts/pdf-data-extract/core/text-extraction/encoding-utils.ts +0 -5780
- package/dist/ts/pdf-data-extract/core/text-extraction/font-structure.d.ts +0 -167
- package/dist/ts/pdf-data-extract/core/text-extraction/font-structure.ts +0 -1842
- package/dist/ts/pdf-data-extract/core/text-extraction/font-tables.d.ts +0 -5
- package/dist/ts/pdf-data-extract/core/text-extraction/font-tables.ts +0 -16
- package/dist/ts/pdf-data-extract/core/text-extraction/font-utils.d.ts +0 -18
- package/dist/ts/pdf-data-extract/core/text-extraction/font-utils.ts +0 -630
- package/dist/ts/pdf-data-extract/core/text-extraction/glyph.d.ts +0 -93
- package/dist/ts/pdf-data-extract/core/text-extraction/glyph.ts +0 -622
- package/dist/ts/pdf-data-extract/core/text-extraction/index.d.ts +0 -10
- package/dist/ts/pdf-data-extract/core/text-extraction/index.ts +0 -10
- package/dist/ts/pdf-data-extract/core/text-extraction/matrix-helper.d.ts +0 -38
- package/dist/ts/pdf-data-extract/core/text-extraction/matrix-helper.ts +0 -150
- package/dist/ts/pdf-data-extract/core/text-extraction/metrics.d.ts +0 -16
- package/dist/ts/pdf-data-extract/core/text-extraction/metrics.ts +0 -2938
- package/dist/ts/pdf-data-extract/core/text-structure.d.ts +0 -628
- package/dist/ts/pdf-data-extract/core/text-structure.ts +0 -668
- package/dist/ts/pdf-data-extract/core/utils.d.ts +0 -99
- package/dist/ts/pdf-data-extract/core/utils.ts +0 -626
- package/dist/ts/pdf-data-extract/index.d.ts +0 -20
- package/dist/ts/pdf-data-extract/index.ts +0 -20
|
@@ -1,67 +0,0 @@
|
|
|
1
|
-
import { _PdfCrossReference, _PdfDictionary, PdfPage } from '@syncfusion/ej2-pdf';
|
|
2
|
-
import { _GraphicState, _TextState } from './graphic-state';
|
|
3
|
-
import { _FontStructure } from './text-extraction/font-structure';
|
|
4
|
-
import { TextGlyph, TextLine, TextWord } from './text-structure';
|
|
5
|
-
import { _MatrixHelper } from './text-extraction/matrix-helper';
|
|
6
|
-
import { _PdfContentParserHelper } from './content-parser-helper';
|
|
7
|
-
export declare class _PdfTextParser {
|
|
8
|
-
_textGlyph: TextGlyph[];
|
|
9
|
-
_textWord: TextWord[];
|
|
10
|
-
_textLine: TextLine[];
|
|
11
|
-
_extractedText: string;
|
|
12
|
-
_width: number;
|
|
13
|
-
_height: number;
|
|
14
|
-
_index: number;
|
|
15
|
-
_fontSize: number;
|
|
16
|
-
_encodedText: string[];
|
|
17
|
-
_previousRect: {
|
|
18
|
-
x: number;
|
|
19
|
-
y: number;
|
|
20
|
-
width: number;
|
|
21
|
-
height: number;
|
|
22
|
-
};
|
|
23
|
-
_boundingRectangle: {
|
|
24
|
-
x: number;
|
|
25
|
-
y: number;
|
|
26
|
-
width: number;
|
|
27
|
-
height: number;
|
|
28
|
-
};
|
|
29
|
-
_translateTextMatrix(x: number, y: number, textMatrix: _MatrixHelper): _MatrixHelper;
|
|
30
|
-
_getCharacterWidth(width: number, currentFont: _FontStructure): number;
|
|
31
|
-
_setNewLineWithLeading(textState: _TextState): void;
|
|
32
|
-
_setTextMatrix(element: string[], textState: _TextState): void;
|
|
33
|
-
_beginText(textState: _TextState, identityMatrix: number[]): void;
|
|
34
|
-
_setFont(element: string[], textState: _TextState): void;
|
|
35
|
-
_moveTextPlacementAndSetLeading(element: string[], textState: _TextState): void;
|
|
36
|
-
_setTextRise(element: string[], textState: _TextState): void;
|
|
37
|
-
_setCharSpacing(element: string[], textState: _TextState): void;
|
|
38
|
-
_setWordSpacing(element: string[], textState: _TextState): void;
|
|
39
|
-
_setTextHorizontalScale(element: string[], textState: _TextState): void;
|
|
40
|
-
_updateTextLeading(element: string[], textState: _TextState): void;
|
|
41
|
-
_moveTextPlacement(element: string[], textState: _TextState): void;
|
|
42
|
-
_getCurrentTransform(font: _FontStructure, fontMatrix: number[], textState: _TextState): number[];
|
|
43
|
-
_isFoundText(x: number, y: number, page: PdfPage, redactBounds: {
|
|
44
|
-
x: number;
|
|
45
|
-
y: number;
|
|
46
|
-
width: number;
|
|
47
|
-
height: number;
|
|
48
|
-
}[]): boolean;
|
|
49
|
-
_getRelativeLocation(x: number, y: number, page: PdfPage): number[];
|
|
50
|
-
_transform(m1: number[], m2: number[]): number[];
|
|
51
|
-
_getCropOrMediaBox(page: PdfPage): number[];
|
|
52
|
-
_getSplitText(encodedText: string, font: _FontStructure, inputText: string[], isForRedaction?: boolean): {
|
|
53
|
-
decodedList: string[];
|
|
54
|
-
inputType?: string[];
|
|
55
|
-
};
|
|
56
|
-
_getPageRotation(textState: _TextState): number;
|
|
57
|
-
_splitHexString(hexString: string): string[];
|
|
58
|
-
_getFallBackFontDictionary(crossReference: _PdfCrossReference): _PdfDictionary;
|
|
59
|
-
_processCommand(token: string, element: string[], state: _GraphicState): void;
|
|
60
|
-
_getTextFont(fontCollection: Map<string, _FontStructure>, textState: _TextState, crossReference: _PdfCrossReference): _FontStructure;
|
|
61
|
-
_getTextContentItem(currentFont: _FontStructure, text: string, extraSpacing: number, textState: _TextState, page: PdfPage, tempString: string, previousRect: {
|
|
62
|
-
x: number;
|
|
63
|
-
y: number;
|
|
64
|
-
width: number;
|
|
65
|
-
height: number;
|
|
66
|
-
}, extractedText: string, parser?: _PdfContentParserHelper, textGlyphs?: TextGlyph[], hex?: string[], index?: number, encodedText?: string[]): any;
|
|
67
|
-
}
|
|
@@ -1,495 +0,0 @@
|
|
|
1
|
-
import { _PdfCrossReference, _PdfDictionary, _PdfName, PdfPage, PdfRotationAngle } from '@syncfusion/ej2-pdf';
|
|
2
|
-
import { _GraphicState, _TextState } from './graphic-state';
|
|
3
|
-
import { _getLiteralString, _hexToChar, _isArrayEqual, _skipEscapeSequence } from './utils';
|
|
4
|
-
import { _FontStructure } from './text-extraction/font-structure';
|
|
5
|
-
import { TextGlyph, TextLine, TextWord } from './text-structure';
|
|
6
|
-
import { _MatrixHelper } from './text-extraction/matrix-helper';
|
|
7
|
-
import { _PdfContentParserHelper } from './content-parser-helper';
|
|
8
|
-
|
|
9
|
-
export class _PdfTextParser {
|
|
10
|
-
_textGlyph: TextGlyph[] = [];
|
|
11
|
-
_textWord: TextWord[] = [];
|
|
12
|
-
_textLine: TextLine[] = [];
|
|
13
|
-
_extractedText: string = '';
|
|
14
|
-
_width: number = 0;
|
|
15
|
-
_height: number = 0;
|
|
16
|
-
_index: number = 0;
|
|
17
|
-
_fontSize: number = 0;
|
|
18
|
-
_encodedText: string[] = [];
|
|
19
|
-
_previousRect: { x: number, y: number, width: number, height: number } = {x: 0, y: 0, width: 0 , height: 0};
|
|
20
|
-
_boundingRectangle: { x: number, y: number, width: number, height: number } = {x: 0, y: 0, width: 0 , height: 0};
|
|
21
|
-
_translateTextMatrix(x: number, y: number, textMatrix: _MatrixHelper): _MatrixHelper {
|
|
22
|
-
const matrix: _MatrixHelper = new _MatrixHelper(textMatrix._m11, textMatrix._m12, textMatrix._m21, textMatrix._m22,
|
|
23
|
-
textMatrix._m11 * x + textMatrix._m21 * y + textMatrix._offsetX,
|
|
24
|
-
textMatrix._m12 * x + textMatrix._m22 * y + textMatrix._offsetY);
|
|
25
|
-
return matrix;
|
|
26
|
-
}
|
|
27
|
-
_getCharacterWidth(width: number, currentFont: _FontStructure): number {
|
|
28
|
-
let advancedWidth: number;
|
|
29
|
-
if (currentFont._type === 'TrueType') {
|
|
30
|
-
advancedWidth = width;
|
|
31
|
-
} else {
|
|
32
|
-
advancedWidth = 1 ;
|
|
33
|
-
}
|
|
34
|
-
return advancedWidth;
|
|
35
|
-
}
|
|
36
|
-
_setNewLineWithLeading(textState: _TextState): void {
|
|
37
|
-
textState._carriageReturn();
|
|
38
|
-
}
|
|
39
|
-
_setTextMatrix(element: string[], textState: _TextState): void {
|
|
40
|
-
textState._setTextMatrix(
|
|
41
|
-
parseFloat(element[0]), parseFloat(element[1]), parseFloat(element[2]),
|
|
42
|
-
parseFloat(element[3]), parseFloat(element[4]), parseFloat(element[5])
|
|
43
|
-
);
|
|
44
|
-
textState._setTextLineMatrix(
|
|
45
|
-
parseFloat(element[0]), parseFloat(element[1]), parseFloat(element[2]),
|
|
46
|
-
parseFloat(element[3]), parseFloat(element[4]), parseFloat(element[5])
|
|
47
|
-
);
|
|
48
|
-
}
|
|
49
|
-
_beginText(textState: _TextState, identityMatrix: number[]): void {
|
|
50
|
-
textState._textMatrix = identityMatrix.slice();
|
|
51
|
-
textState._textLineMatrix = identityMatrix.slice();
|
|
52
|
-
}
|
|
53
|
-
_setFont(element: string[], textState: _TextState): void {
|
|
54
|
-
for (let j: number = 0; j < element.length; j++) {
|
|
55
|
-
if (element[Number.parseInt(j.toString(), 10)].indexOf('/') !== -1) {
|
|
56
|
-
textState._font = element[Number.parseInt(j.toString(), 10)].replace('/', '');
|
|
57
|
-
break;
|
|
58
|
-
}
|
|
59
|
-
}
|
|
60
|
-
textState._fontSize = Number(element[1]);
|
|
61
|
-
}
|
|
62
|
-
_moveTextPlacementAndSetLeading(element: string[], textState: _TextState): void {
|
|
63
|
-
textState._leading = -Number(element[1]);
|
|
64
|
-
textState._translateTextLineMatrix(Number(element[0]), Number(element[1]));
|
|
65
|
-
textState._textMatrix = textState._textLineMatrix.slice();
|
|
66
|
-
}
|
|
67
|
-
_setTextRise(element: string[], textState: _TextState): void {
|
|
68
|
-
textState._textRise = Number(element[0]);
|
|
69
|
-
}
|
|
70
|
-
_setCharSpacing(element: string[], textState: _TextState): void {
|
|
71
|
-
textState._charSpacing = Number(element[0]);
|
|
72
|
-
}
|
|
73
|
-
_setWordSpacing(element: string[], textState: _TextState): void {
|
|
74
|
-
textState._wordSpacing = Number(element[0]);
|
|
75
|
-
}
|
|
76
|
-
_setTextHorizontalScale(element: string[], textState: _TextState): void {
|
|
77
|
-
textState._textHScale = Number(element[0]) / 100;
|
|
78
|
-
}
|
|
79
|
-
_updateTextLeading(element: string[], textState: _TextState): void {
|
|
80
|
-
textState._leading = Number(element[0]);
|
|
81
|
-
}
|
|
82
|
-
_moveTextPlacement(element: string[], textState: _TextState): void {
|
|
83
|
-
textState._translateTextLineMatrix(Number(element[0]), Number(element[1]));
|
|
84
|
-
textState._textMatrix = textState._textLineMatrix.slice();
|
|
85
|
-
}
|
|
86
|
-
_getCurrentTransform(font: _FontStructure, fontMatrix: number[], textState: _TextState): number[] {
|
|
87
|
-
const tsm: number[] = [textState._fontSize * textState._textHScale, 0, 0, textState._fontSize, 0, textState._textRise];
|
|
88
|
-
if (font._isType3Font && textState._fontSize <= 1 && !_isArrayEqual(fontMatrix, [0.001, 0, 0, 0.001, 0, 0])) {
|
|
89
|
-
const glyphHeight: number = font._boundingBox[3] - font._boundingBox[1];
|
|
90
|
-
if (glyphHeight > 0) {
|
|
91
|
-
tsm[3] *= glyphHeight * fontMatrix[3];
|
|
92
|
-
}
|
|
93
|
-
}
|
|
94
|
-
return this._transform(textState._ctm, this._transform(textState._textMatrix, tsm));
|
|
95
|
-
}
|
|
96
|
-
_isFoundText(x: number, y: number, page: PdfPage, redactBounds: {x: number, y: number, width: number, height: number}[]): boolean {
|
|
97
|
-
let isFound: boolean = false;
|
|
98
|
-
let location: number[] = [];
|
|
99
|
-
if (y < 0) {
|
|
100
|
-
y = -y;
|
|
101
|
-
}
|
|
102
|
-
const rectValue: {x: number, y: number, width: number, height: number} = {x: 0, y: 0, width: 0, height: 0};
|
|
103
|
-
const redactionBounds: {x: number, y: number, width: number, height: number}[] = redactBounds;
|
|
104
|
-
location = this._getRelativeLocation(x, y, page);
|
|
105
|
-
let yPosition: number = Math.floor(location[1]);
|
|
106
|
-
const count: number = redactionBounds.length;
|
|
107
|
-
for (let i: number = 0; i < count; i++) {
|
|
108
|
-
const bounds: {x: number, y: number, width: number, height: number} = redactionBounds[Number.parseInt(i.toString(), 10)];
|
|
109
|
-
const ypos: number = Math.floor(redactionBounds[Number.parseInt(i.toString(), 10)].y);
|
|
110
|
-
if (ypos === yPosition || (ypos === (yPosition - 1)) || (ypos === (yPosition + 1))) {
|
|
111
|
-
isFound = true;
|
|
112
|
-
break;
|
|
113
|
-
}
|
|
114
|
-
if ((bounds.y >= yPosition && yPosition >= (bounds.y - bounds.height)) || (bounds.y <= yPosition && yPosition <= (bounds.y
|
|
115
|
-
+ bounds.height))) {
|
|
116
|
-
isFound = true;
|
|
117
|
-
break;
|
|
118
|
-
}
|
|
119
|
-
const size: number[] = page.size;
|
|
120
|
-
yPosition = Math.floor(size[1] - y);
|
|
121
|
-
if ((bounds.y >= yPosition && yPosition >= (bounds.y - bounds.height)) || (bounds.y <= yPosition && yPosition <= (bounds.y +
|
|
122
|
-
bounds.height))) {
|
|
123
|
-
isFound = true;
|
|
124
|
-
break;
|
|
125
|
-
}
|
|
126
|
-
if (rectValue.y !== 0) {
|
|
127
|
-
if (rectValue.y < 0) {
|
|
128
|
-
rectValue.y = -rectValue.y;
|
|
129
|
-
}
|
|
130
|
-
yPosition = Math.floor(y + rectValue.y);
|
|
131
|
-
if ((bounds.y >= yPosition && yPosition >= (bounds.y - bounds.height)) || (bounds.y <= yPosition && yPosition <= (bounds.y +
|
|
132
|
-
bounds.height))) {
|
|
133
|
-
isFound = true;
|
|
134
|
-
break;
|
|
135
|
-
}
|
|
136
|
-
if (rectValue.height < 0) {
|
|
137
|
-
rectValue.height = -rectValue.height;
|
|
138
|
-
}
|
|
139
|
-
yPosition = Math.floor(rectValue.height - yPosition);
|
|
140
|
-
if ((bounds.y >= yPosition && yPosition >= (bounds.y - bounds.height)) || (bounds.y <= yPosition && yPosition <= (bounds.y +
|
|
141
|
-
bounds.height))) {
|
|
142
|
-
isFound = true;
|
|
143
|
-
break;
|
|
144
|
-
}
|
|
145
|
-
}
|
|
146
|
-
}
|
|
147
|
-
return isFound;
|
|
148
|
-
}
|
|
149
|
-
_getRelativeLocation(x: number, y: number , page: PdfPage): number[] {
|
|
150
|
-
const location: number[] = [x, y];
|
|
151
|
-
if (page.rotation === PdfRotationAngle.angle90) {
|
|
152
|
-
location[0] = page.size[1] - y;
|
|
153
|
-
location[1] = x;
|
|
154
|
-
} else if (page.rotation === PdfRotationAngle.angle270) {
|
|
155
|
-
location[0] = page.size[0] - x;
|
|
156
|
-
location[1] = y;
|
|
157
|
-
}
|
|
158
|
-
return location;
|
|
159
|
-
}
|
|
160
|
-
_transform(m1: number[], m2: number[]): number[] {
|
|
161
|
-
return [m1[0] * m2[0] + m1[2] * m2[1], m1[1] * m2[0] + m1[3] * m2[1], m1[0] * m2[2] + m1[2] * m2[3], m1[1] * m2[2] + m1[3] * m2[3]
|
|
162
|
-
, m1[0] * m2[4] + m1[2] * m2[5] + m1[4], m1[1] * m2[4] + m1[3] * m2[5] + m1[5]];
|
|
163
|
-
}
|
|
164
|
-
_getCropOrMediaBox(page: PdfPage): number[] {
|
|
165
|
-
const cropOrMediaBox: number[] = [];
|
|
166
|
-
if (page.cropBox[0] !== 0 || page.cropBox[3] !== 0) {
|
|
167
|
-
cropOrMediaBox[0] = page.cropBox[0];
|
|
168
|
-
cropOrMediaBox[1] = page.cropBox[2];
|
|
169
|
-
cropOrMediaBox[2] = page.cropBox[3];
|
|
170
|
-
} else if (page.mediaBox[0] !== 0 || page.mediaBox[3] !== 0) {
|
|
171
|
-
cropOrMediaBox[0] = page.mediaBox[0];
|
|
172
|
-
cropOrMediaBox[1] = page.mediaBox[2];
|
|
173
|
-
cropOrMediaBox[2] = page.mediaBox[3];
|
|
174
|
-
}
|
|
175
|
-
return cropOrMediaBox;
|
|
176
|
-
}
|
|
177
|
-
_getSplitText(encodedText: string, font: _FontStructure, inputText: string[], isForRedaction: boolean = false): { decodedList:
|
|
178
|
-
string[], inputType?: string[] } {
|
|
179
|
-
const decodedList: string[] = [];
|
|
180
|
-
let key: string = '';
|
|
181
|
-
const encoding: string = font._encoding;
|
|
182
|
-
const inputType: string[] = isForRedaction ? [] : undefined;
|
|
183
|
-
let tempString: string = '';
|
|
184
|
-
let splittedText: string[];
|
|
185
|
-
let isHex: boolean = false;
|
|
186
|
-
let isWidth: boolean;
|
|
187
|
-
switch (encodedText[0]) {
|
|
188
|
-
case '(':
|
|
189
|
-
encodedText = encodedText.substring(1, encodedText.length - 1);
|
|
190
|
-
if (encodedText.indexOf('\\\n') !== -1 || encodedText.indexOf('\\(') !== -1 || encodedText.indexOf('\\)') !== -1) {
|
|
191
|
-
if (encodedText.indexOf('\\\n') !== -1) {
|
|
192
|
-
encodedText = encodedText.replace(/\\\n/g, '');
|
|
193
|
-
}
|
|
194
|
-
if (encodedText.indexOf('\\(') !== -1) {
|
|
195
|
-
encodedText = encodedText.replace(/\\\(/g, '(');
|
|
196
|
-
}
|
|
197
|
-
if (encodedText.indexOf('\\)') !== -1) {
|
|
198
|
-
encodedText = encodedText.replace(/\\\)/g, ')');
|
|
199
|
-
}
|
|
200
|
-
}
|
|
201
|
-
if (encodedText.indexOf('\\n') !== -1) {
|
|
202
|
-
encodedText = encodedText.replace(/\\n/g, '\n');
|
|
203
|
-
}
|
|
204
|
-
if (encodedText.indexOf('\\r') !== -1) {
|
|
205
|
-
encodedText = encodedText.replace(/\\r/g, '\r');
|
|
206
|
-
}
|
|
207
|
-
encodedText = _getLiteralString(encodedText, encoding);
|
|
208
|
-
encodedText = _skipEscapeSequence(encodedText);
|
|
209
|
-
key = encodedText + 's';
|
|
210
|
-
decodedList.push(key);
|
|
211
|
-
if (isForRedaction) {
|
|
212
|
-
inputType.push(' ');
|
|
213
|
-
}
|
|
214
|
-
break;
|
|
215
|
-
case '[':
|
|
216
|
-
splittedText = inputText;
|
|
217
|
-
isHex = false;
|
|
218
|
-
for (let i: number = 0; i < splittedText.length; i++) {
|
|
219
|
-
let input: string = splittedText[Number.parseInt(i.toString(), 10)];
|
|
220
|
-
isWidth = false;
|
|
221
|
-
if (input.indexOf('\\\n') !== -1) {
|
|
222
|
-
input = input.replace(/\\\n/g, '');
|
|
223
|
-
}
|
|
224
|
-
if (input[0] === '<') {
|
|
225
|
-
isHex = true;
|
|
226
|
-
if (isForRedaction) {
|
|
227
|
-
inputType.push(input);
|
|
228
|
-
}
|
|
229
|
-
input = input.slice(1, -1);
|
|
230
|
-
} else if (input[0] === '(') {
|
|
231
|
-
input = input.slice(1, -1);
|
|
232
|
-
} else if (input.length > 0){
|
|
233
|
-
input = input.replace('\n', '');
|
|
234
|
-
decodedList.push(input);
|
|
235
|
-
if (isForRedaction) {
|
|
236
|
-
inputType.push(' ');
|
|
237
|
-
}
|
|
238
|
-
continue;
|
|
239
|
-
}
|
|
240
|
-
if (isHex) {
|
|
241
|
-
tempString = _hexToChar(input);
|
|
242
|
-
} else {
|
|
243
|
-
tempString = _getLiteralString(input, encoding);
|
|
244
|
-
if (tempString.indexOf('\\') !== -1) {
|
|
245
|
-
tempString = _skipEscapeSequence(tempString);
|
|
246
|
-
}
|
|
247
|
-
}
|
|
248
|
-
if (!isWidth && input.length > 0) {
|
|
249
|
-
key = tempString + 's';
|
|
250
|
-
decodedList.push(key);
|
|
251
|
-
key = '';
|
|
252
|
-
if (isForRedaction && !isHex) {
|
|
253
|
-
inputType.push(' ');
|
|
254
|
-
}
|
|
255
|
-
isHex = false;
|
|
256
|
-
}
|
|
257
|
-
}
|
|
258
|
-
break;
|
|
259
|
-
case '<':
|
|
260
|
-
encodedText = encodedText.substring(1, encodedText.length - 1);
|
|
261
|
-
tempString = _hexToChar(encodedText);
|
|
262
|
-
key = tempString + 's';
|
|
263
|
-
decodedList.push(key);
|
|
264
|
-
break;
|
|
265
|
-
}
|
|
266
|
-
return isForRedaction ? { decodedList, inputType } : { decodedList };
|
|
267
|
-
}
|
|
268
|
-
_getPageRotation(textState: _TextState): number {
|
|
269
|
-
let rotation: number = 0;
|
|
270
|
-
if (textState._textMatrix[0] === 0 && textState._textMatrix[1] > 0 && textState._textMatrix[2] < 0 &&
|
|
271
|
-
textState._textMatrix[3] >= 0) {
|
|
272
|
-
rotation = 90;
|
|
273
|
-
} else if (textState._textMatrix[0] === 0 && textState._textMatrix[1] < 0 && textState._textMatrix[2] > 0
|
|
274
|
-
&& textState._textMatrix[3] === 0) {
|
|
275
|
-
rotation = 270;
|
|
276
|
-
}
|
|
277
|
-
return rotation;
|
|
278
|
-
}
|
|
279
|
-
_splitHexString(hexString: string): string[] {
|
|
280
|
-
const hexList: string[] = [];
|
|
281
|
-
if (typeof(hexString) === 'undefined') {
|
|
282
|
-
return hexList;
|
|
283
|
-
}
|
|
284
|
-
hexString = hexString.slice(1, -1);
|
|
285
|
-
const size: number = hexString.startsWith('0') ? 4 : 2;
|
|
286
|
-
for (let i: number = 0; i < hexString.length; i += size) {
|
|
287
|
-
let chunk: string = hexString.substring(i, i + size);
|
|
288
|
-
if (chunk.indexOf('\n') !== -1) {
|
|
289
|
-
const extraChar: string = hexString.charAt(i + size);
|
|
290
|
-
chunk += extraChar;
|
|
291
|
-
i++;
|
|
292
|
-
}
|
|
293
|
-
hexList.push(chunk);
|
|
294
|
-
}
|
|
295
|
-
return hexList;
|
|
296
|
-
}
|
|
297
|
-
_getFallBackFontDictionary(crossReference: _PdfCrossReference): _PdfDictionary {
|
|
298
|
-
const dictionary: _PdfDictionary = new _PdfDictionary(crossReference);
|
|
299
|
-
dictionary.set('BaseFont', new _PdfName('Helvetica'));
|
|
300
|
-
dictionary.set('Type', new _PdfName('FallbackType'));
|
|
301
|
-
dictionary.set('Subtype', new _PdfName('FallbackType'));
|
|
302
|
-
dictionary.set('Encoding', new _PdfName('WinAnsiEncoding'));
|
|
303
|
-
return dictionary;
|
|
304
|
-
}
|
|
305
|
-
_processCommand(token: string, element: string[], state: _GraphicState): void {
|
|
306
|
-
let args: number[] = [];
|
|
307
|
-
switch (token) {
|
|
308
|
-
case 'q':
|
|
309
|
-
state._save();
|
|
310
|
-
break;
|
|
311
|
-
case 'Q':
|
|
312
|
-
state._restore();
|
|
313
|
-
break;
|
|
314
|
-
case 'cm':
|
|
315
|
-
args = [parseFloat(element[0]), parseFloat(element[1]), parseFloat(
|
|
316
|
-
element[2]), parseFloat(element[3]), parseFloat(element[4]), parseFloat(element[5])];
|
|
317
|
-
state._transform(args);
|
|
318
|
-
}
|
|
319
|
-
}
|
|
320
|
-
_getTextFont(fontCollection: Map<string, _FontStructure>, textState: _TextState, crossReference: _PdfCrossReference): _FontStructure {
|
|
321
|
-
let currentFont: _FontStructure;
|
|
322
|
-
if (fontCollection.get(textState._font)) {
|
|
323
|
-
currentFont = fontCollection.get(textState._font);
|
|
324
|
-
} else {
|
|
325
|
-
const dictionary: _PdfDictionary = this._getFallBackFontDictionary(crossReference);
|
|
326
|
-
currentFont = new _FontStructure(dictionary, crossReference);
|
|
327
|
-
}
|
|
328
|
-
return currentFont;
|
|
329
|
-
}
|
|
330
|
-
_getTextContentItem(currentFont: _FontStructure, text: string, extraSpacing: number, textState: _TextState, page: PdfPage,
|
|
331
|
-
tempString: string, previousRect: { x: number, y: number, width: number, height: number }, extractedText: string, parser?: _PdfContentParserHelper, textGlyphs?: TextGlyph[], hex?: string[], index?: number, encodedText?: string[]): any { // eslint-disable-line
|
|
332
|
-
text = text.slice(0, -1 );
|
|
333
|
-
let fontSize: number = 0;
|
|
334
|
-
let isHex: boolean = false;
|
|
335
|
-
let textBounds: { x: number, y: number, width: number, height: number } = {x: 0, y: 0, width: 0 , height: 0};
|
|
336
|
-
if (typeof(hex) !== 'undefined' && hex.length > 0) {
|
|
337
|
-
isHex = true;
|
|
338
|
-
}
|
|
339
|
-
let glyphs: any = currentFont._charsToGlyphs(text); // eslint-disable-line
|
|
340
|
-
const ii: number = glyphs.length;
|
|
341
|
-
let scale: number = 0;
|
|
342
|
-
if (currentFont. _fontMatrix) {
|
|
343
|
-
scale = currentFont._fontMatrix[0];
|
|
344
|
-
} else {
|
|
345
|
-
currentFont._fontMatrix = [0.001, 0, 0, 0.001, 0, 0];
|
|
346
|
-
scale = 0.001;
|
|
347
|
-
}
|
|
348
|
-
const rotation: number = this._getPageRotation(textState);
|
|
349
|
-
for (let i: number = 0; i < ii; i++) {
|
|
350
|
-
const glyph: any = glyphs[Number.parseInt(i.toString(), 10)]; // eslint-disable-line
|
|
351
|
-
// this._resultantText += glyph._unicode;
|
|
352
|
-
let width: number;
|
|
353
|
-
let charSpacing: number = textState._charSpacing + (i + 1 === ii ? extraSpacing : 0);
|
|
354
|
-
let glyphWidth: number = glyph._width;
|
|
355
|
-
if (currentFont._vertical) {
|
|
356
|
-
glyphWidth = glyph.vmetric ? glyph.vmetric[0] : -glyphWidth;
|
|
357
|
-
}
|
|
358
|
-
let scaledDim: number = glyphWidth * scale * textState._fontSize;
|
|
359
|
-
width = scale * glyphWidth;
|
|
360
|
-
let height: number = 0;
|
|
361
|
-
let tempFontSize: number = 0;
|
|
362
|
-
const transform: number[] = this._getCurrentTransform(currentFont, currentFont._fontMatrix, textState);
|
|
363
|
-
const cropOrMediaBox: number[] = this._getCropOrMediaBox(page);
|
|
364
|
-
let x: number = transform[4];
|
|
365
|
-
let y: number = 0;
|
|
366
|
-
if (page.rotation === PdfRotationAngle.angle180 || page.rotation === PdfRotationAngle.angle270) {
|
|
367
|
-
x = cropOrMediaBox[1] - x;
|
|
368
|
-
} else {
|
|
369
|
-
x = x - cropOrMediaBox[0];
|
|
370
|
-
}
|
|
371
|
-
if (page.rotation === PdfRotationAngle.angle90 || page.rotation === PdfRotationAngle.angle180) {
|
|
372
|
-
y = transform[5];
|
|
373
|
-
} else {
|
|
374
|
-
y = cropOrMediaBox[2] - transform[5];
|
|
375
|
-
}
|
|
376
|
-
if (!currentFont._vertical) {
|
|
377
|
-
height = Math.hypot(transform[2], transform[3]);
|
|
378
|
-
} else {
|
|
379
|
-
width = Math.hypot(transform[0], transform[1]);
|
|
380
|
-
}
|
|
381
|
-
if (transform[0] > 0) {
|
|
382
|
-
tempFontSize = transform[0];
|
|
383
|
-
} else if (transform[1] !== 0 && transform[2] !== 0) {
|
|
384
|
-
if (transform[1] < 0) {
|
|
385
|
-
tempFontSize = -transform[1];
|
|
386
|
-
} else {
|
|
387
|
-
tempFontSize = transform[1];
|
|
388
|
-
}
|
|
389
|
-
}
|
|
390
|
-
if (glyph._unicode === ' ') {
|
|
391
|
-
if (!currentFont._vertical) {
|
|
392
|
-
charSpacing += scaledDim + textState._wordSpacing;
|
|
393
|
-
textState._translateTextMatrix(charSpacing * (textState._textHScale), 0);
|
|
394
|
-
width *= tempFontSize;
|
|
395
|
-
if (rotation === 90) {
|
|
396
|
-
y = y - width;
|
|
397
|
-
x = x - height + height / 4 ;
|
|
398
|
-
} else if (page.rotation === PdfRotationAngle.angle90 || page.rotation === PdfRotationAngle.angle180) {
|
|
399
|
-
y = y - height + (height / 1.3333333333333333);
|
|
400
|
-
} else {
|
|
401
|
-
y = y - height / 1.3333333333333333;
|
|
402
|
-
}
|
|
403
|
-
} else {
|
|
404
|
-
charSpacing += -scaledDim + textState._wordSpacing;
|
|
405
|
-
textState._translateTextMatrix(0, -charSpacing);
|
|
406
|
-
height += tempFontSize;
|
|
407
|
-
x = x - width / 2;
|
|
408
|
-
}
|
|
409
|
-
}
|
|
410
|
-
if (glyph._unicode !== ' ') {
|
|
411
|
-
if (!currentFont._vertical) {
|
|
412
|
-
scaledDim *= textState._textHScale;
|
|
413
|
-
textState._translateTextMatrix(scaledDim, 0);
|
|
414
|
-
width *= tempFontSize;
|
|
415
|
-
if (rotation === 90) {
|
|
416
|
-
y = y - width;
|
|
417
|
-
x = x - height + height / 4 ;
|
|
418
|
-
} else if (page.rotation === PdfRotationAngle.angle90 || page.rotation === PdfRotationAngle.angle180) {
|
|
419
|
-
y = y - height + (height / 1.3333333333333333);
|
|
420
|
-
} else {
|
|
421
|
-
y = y - (height / 1.3333333333333333);
|
|
422
|
-
}
|
|
423
|
-
} else {
|
|
424
|
-
textState._translateTextMatrix(0, scaledDim);
|
|
425
|
-
scaledDim = Math.abs(scaledDim);
|
|
426
|
-
height += scaledDim + tempFontSize;
|
|
427
|
-
x = x - width / 2;
|
|
428
|
-
}
|
|
429
|
-
}
|
|
430
|
-
if (page.rotation === PdfRotationAngle.angle0 && rotation === 90) {
|
|
431
|
-
textBounds = {x: x, y: y, width: height, height: width};
|
|
432
|
-
} else if (page.rotation === PdfRotationAngle.angle90) {
|
|
433
|
-
textBounds = {x: y, y: x, width: height, height: width};
|
|
434
|
-
} else if (page.rotation === PdfRotationAngle.angle180) {
|
|
435
|
-
textBounds = {x: x - width, y: y, width: width, height: height};
|
|
436
|
-
} else if (page.rotation === PdfRotationAngle.angle270) {
|
|
437
|
-
textBounds = {x: y, y: x - width, width: height, height: width};
|
|
438
|
-
} else {
|
|
439
|
-
textBounds = {x: x, y: y, width: width, height: height};
|
|
440
|
-
}
|
|
441
|
-
extractedText += glyph._unicode;
|
|
442
|
-
if (typeof(textGlyphs) !== 'undefined') {
|
|
443
|
-
const bounds: { x: number, y: number, width: number, height: number } = textBounds;
|
|
444
|
-
const textGlyph: TextGlyph = new TextGlyph();
|
|
445
|
-
if (isHex && hex.length >= i) {
|
|
446
|
-
textGlyph._isHex = true;
|
|
447
|
-
encodedText[Number.parseInt(index.toString(), 10)] = hex[Number.parseInt(i.toString(), 10)];
|
|
448
|
-
} else {
|
|
449
|
-
encodedText[Number.parseInt(index.toString(), 10)] = glyph._fontCharacter;
|
|
450
|
-
}
|
|
451
|
-
textGlyph._text = glyph._unicode;
|
|
452
|
-
textGlyph._bounds = [bounds.x, bounds.y, bounds.width, bounds.height];
|
|
453
|
-
textGlyph._fontName = currentFont._name;
|
|
454
|
-
textGlyph._fontStyle = currentFont._fontStyle;
|
|
455
|
-
textGlyph._fontSize = textState._fontSize;
|
|
456
|
-
textGlyph._color = textState._textColor;
|
|
457
|
-
textGlyph._width = glyph._width;
|
|
458
|
-
textGlyph._charSpacing = textState._charSpacing;
|
|
459
|
-
textGlyph._wordSpacing = textState._wordSpacing;
|
|
460
|
-
index++;
|
|
461
|
-
if (page.rotation !== PdfRotationAngle.angle0) {
|
|
462
|
-
textGlyph._isRotated = true;
|
|
463
|
-
} else {
|
|
464
|
-
textGlyph._isRotated = false;
|
|
465
|
-
}
|
|
466
|
-
textGlyphs.push(textGlyph);
|
|
467
|
-
} else {
|
|
468
|
-
fontSize = textState._fontSize;
|
|
469
|
-
const result: any = parser._splitWords(glyph._unicode, tempString, currentFont._name,// eslint-disable-line
|
|
470
|
-
currentFont._fontStyle, page, rotation, textState._textColor, textState._fontSize,
|
|
471
|
-
textBounds, previousRect);
|
|
472
|
-
previousRect = result.previousRect;
|
|
473
|
-
tempString = result.tempString;
|
|
474
|
-
if (previousRect) {
|
|
475
|
-
previousRect = {x: textBounds.x, y: textBounds.y,
|
|
476
|
-
width: textBounds.width, height: textBounds.height};
|
|
477
|
-
} else {
|
|
478
|
-
previousRect = {x: 0, y: 0, width: 0 , height: 0};
|
|
479
|
-
}
|
|
480
|
-
}
|
|
481
|
-
if (charSpacing && glyph._unicode !== ' ') {
|
|
482
|
-
if (!currentFont._vertical) {
|
|
483
|
-
textState._translateTextMatrix(charSpacing * textState._textHScale, 0);
|
|
484
|
-
} else {
|
|
485
|
-
textState._translateTextMatrix(0, -charSpacing);
|
|
486
|
-
}
|
|
487
|
-
}
|
|
488
|
-
}
|
|
489
|
-
if (typeof(textGlyphs) !== 'undefined') {
|
|
490
|
-
return {textGlyphs, extractedText, encodedText, index};
|
|
491
|
-
} else {
|
|
492
|
-
return {tempString, extractedText, fontSize, previousRect};
|
|
493
|
-
}
|
|
494
|
-
}
|
|
495
|
-
}
|
|
@@ -1,55 +0,0 @@
|
|
|
1
|
-
import { _PdfAnnotationType, _PdfContentStream, _PdfDictionary, PdfDocument, PdfPage } from '@syncfusion/ej2-pdf';
|
|
2
|
-
import { PdfRedactionRegion } from './pdf-redaction-region';
|
|
3
|
-
export declare class _PdfRedactionProcessor {
|
|
4
|
-
_updateContentStream(page: PdfPage, stream: _PdfContentStream, options: PdfRedactionRegion[], document: PdfDocument): void;
|
|
5
|
-
_processFormFields(page: PdfPage, options: PdfRedactionRegion[], document: PdfDocument): void;
|
|
6
|
-
_isFound(values: number[], redactionBounds: {
|
|
7
|
-
x: number;
|
|
8
|
-
y: number;
|
|
9
|
-
width: number;
|
|
10
|
-
height: number;
|
|
11
|
-
}): boolean;
|
|
12
|
-
_intersectsWith(rect1: {
|
|
13
|
-
x: number;
|
|
14
|
-
y: number;
|
|
15
|
-
width: number;
|
|
16
|
-
height: number;
|
|
17
|
-
}, rect2: {
|
|
18
|
-
x: number;
|
|
19
|
-
y: number;
|
|
20
|
-
width: number;
|
|
21
|
-
height: number;
|
|
22
|
-
}): boolean;
|
|
23
|
-
_isEmptyRectangle(width: number, height: number): boolean;
|
|
24
|
-
_toRectangle(x: number, y: number, width: number, height: number): number[];
|
|
25
|
-
_isKidInSamePage(kid: _PdfDictionary, page: PdfPage): boolean;
|
|
26
|
-
_processAnnotation(page: PdfPage, options: PdfRedactionRegion[]): void;
|
|
27
|
-
_getBoundsFromPoints(points: number[], loadedPage: PdfPage): {
|
|
28
|
-
bounds: {
|
|
29
|
-
x: number;
|
|
30
|
-
y: number;
|
|
31
|
-
width: number;
|
|
32
|
-
height: number;
|
|
33
|
-
};
|
|
34
|
-
isValidAnnotation: boolean;
|
|
35
|
-
};
|
|
36
|
-
_isLineIntersectRectangle(redactBounds: {
|
|
37
|
-
x: number;
|
|
38
|
-
y: number;
|
|
39
|
-
width: number;
|
|
40
|
-
height: number;
|
|
41
|
-
}, p1X: number, p1Y: number, p2X: number, p2Y: number): boolean;
|
|
42
|
-
_isBoundsEqual(bounds1: {
|
|
43
|
-
x: number;
|
|
44
|
-
y: number;
|
|
45
|
-
width: number;
|
|
46
|
-
height: number;
|
|
47
|
-
}, bounds2: {
|
|
48
|
-
x: number;
|
|
49
|
-
y: number;
|
|
50
|
-
width: number;
|
|
51
|
-
height: number;
|
|
52
|
-
}): boolean;
|
|
53
|
-
_getAnnotationType(dictionary: _PdfDictionary): _PdfAnnotationType;
|
|
54
|
-
_findAnnotation(array: any[]): boolean;
|
|
55
|
-
}
|