@syncfusion/ej2-pdf-data-extract 31.1.17 → 31.1.18

package/dist/ts/pdf-data-extract/core/graphic-state.d.ts

@@ -1,33 +0,0 @@
-export declare class _TextState {
-    _ctm: number[];
-    _fontName: string;
-    _fontSize: number;
-    _font: any;
-    _fontMatrix: number[];
-    _textMatrix: number[];
-    _textLineMatrix: number[];
-    _charSpacing: number;
-    _wordSpacing: number;
-    _leading: number;
-    _textHScale: number;
-    _textRise: number;
-    _identityMatrix: number[];
-    _fontIdentityMatrix: number[];
-    _textColor: number[];
-    constructor();
-    _setTextMatrix(a: number, b: number, c: number, d: number, e: number, f: number): void;
-    _setTextLineMatrix(a: number, b: number, c: number, d: number, e: number, f: number): void;
-    _translateTextMatrix(x: number, y: number): void;
-    _translateTextLineMatrix(x: number, y: number): void;
-    _carriageReturn(): void;
-    _clone(): any;
-}
-export declare class _GraphicState {
-    _state: _TextState;
-    _stateStack: any;
-    constructor(currentState?: _TextState);
-    _save(): void;
-    _restore(): void;
-    _transform(args: number[]): void;
-    _transformMatrix(m1: number[], m2: number[]): number[];
-}

package/dist/ts/pdf-data-extract/core/graphic-state.ts

@@ -1,106 +0,0 @@
-export class _TextState {
-    _ctm: number[];
-    _fontName: string;
-    _fontSize: number;
-    _font: any; //eslint-disable-line
-    _fontMatrix: number[];
-    _textMatrix: number[];
-    _textLineMatrix: number[];
-    _charSpacing: number;
-    _wordSpacing: number;
-    _leading: number;
-    _textHScale: number;
-    _textRise: number;
-    _identityMatrix: number[] = [1, 0, 0, 1, 0, 0];
-    _fontIdentityMatrix: number[] = [0.001, 0, 0, 0.001, 0, 0];
-    _textColor: number[] = [];
-    constructor() {
-        this._ctm = this._identityMatrix;
-        this._fontName = null;
-        this._fontSize = 0;
-        this._font = null;
-        this._fontMatrix = this._fontIdentityMatrix;
-        this._textMatrix = this._identityMatrix.slice();
-        this._textLineMatrix = this._identityMatrix.slice();
-        this._charSpacing = 0;
-        this._wordSpacing = 0;
-        this._leading = 0;
-        this._textHScale = 1;
-        this._textRise = 0;
-    }
-    _setTextMatrix(a: number, b: number, c: number, d: number, e: number, f: number): void {
-        const matrix: number[] = this._textMatrix;
-        matrix[0] = a;
-        matrix[1] = b;
-        matrix[2] = c;
-        matrix[3] = d;
-        matrix[4] = e;
-        matrix[5] = f;
-    }
-    _setTextLineMatrix(a: number, b: number, c: number, d: number, e: number, f: number): void {
-        const matrix: number[] = this._textLineMatrix;
-        matrix[0] = a;
-        matrix[1] = b;
-        matrix[2] = c;
-        matrix[3] = d;
-        matrix[4] = e;
-        matrix[5] = f;
-    }
-    _translateTextMatrix(x: number, y: number): void {
-        const matrix: number[] = this._textMatrix;
-        matrix[4] = matrix[0] * x + matrix[2] * y + matrix[4];
-        matrix[5] = matrix[1] * x + matrix[3] * y + matrix[5];
-    }
-    _translateTextLineMatrix(x: number, y: number): void {
-        const matrix: number[] = this._textLineMatrix;
-        matrix[4] = matrix[0] * x + matrix[2] * y + matrix[4];
-        matrix[5] = matrix[1] * x + matrix[3] * y + matrix[5];
-    }
-    _carriageReturn(): void {
-        this._translateTextLineMatrix(0, -this._leading);
-        this._textMatrix = this._textLineMatrix.slice();
-    }
-    _clone(): any { //eslint-disable-line
-        const clone: any = Object.create(this); //eslint-disable-line
-        clone._textMatrix = this._textMatrix.slice();
-        clone._textLineMatrix = this._textLineMatrix.slice();
-        clone._fontMatrix = this._fontMatrix.slice();
-        return clone;
-    }
-}
-export class _GraphicState {
-    _state: _TextState ;
-    _stateStack: any; //eslint-disable-line
-    constructor(currentState?: _TextState) {
-        if (!currentState) {
-            this._state = new _TextState();
-        } else {
-            this._state = currentState;
-        }
-        this._stateStack = [];
-    }
-    _save(): void {
-        const oldState: _TextState = this._state;
-        this._stateStack.push(this._state);
-        this._state = oldState._clone();
-    }
-    _restore(): void {
-        const prev: _TextState  = this._stateStack.pop();
-        if (prev) {
-            this._state = prev;
-        }
-    }
-    _transform(args: number[]): void {
-        this._state._ctm = this._transformMatrix(this._state._ctm, args);
-    }
-    _transformMatrix(m1: number[], m2: number[]): number[] {
-        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],
-            m1[0] * m2[4] + m1[2] * m2[5] + m1[4],
-            m1[1] * m2[4] + m1[3] * m2[5] + m1[5]
-        ];
-    }
-}

package/dist/ts/pdf-data-extract/core/pdf-data-extractor.d.ts

@@ -1,210 +0,0 @@
-import { _MatrixHelper, _TransformationStack } from './text-extraction/matrix-helper';
-import { TextGlyph, TextLine, TextWord } from './text-structure';
-import { _PdfContentParserHelper } from './content-parser-helper';
-import { _GraphicState } from './graphic-state';
-import { _FontStructure } from './text-extraction';
-import { _PdfCrossReference, _PdfRecord, PdfDocument, PdfFontStyle, PdfPage } from '@syncfusion/ej2-pdf';
-import { _PdfTextParser } from './pdf-text-parser';
-/**
- * Represents a utility for extracting data from a PDF document.
- * ```typescript
- * // Load an existing PDF document
- * let document: PdfDocument = new PdfDocument(data, password);
- * // Initialize a new instance of the `PdfDataExtractor` class
- * let extractor: PdfDataExtractor = new PdfDataExtractor(document);
- * // Extract `TextLine` from the PDF document.
- * let textLines: Array<TextLine> = extractor.extractTextLines({ startPageIndex: 0, endPageIndex: document.pageCount-1});
- * // Save the document
- * document.save('output.pdf');
- * // Destroy the document
- * document.destroy();
- * ```
- */
-export declare class PdfDataExtractor {
-    _document: PdfDocument;
-    _rotation: number;
-    _textMatrix: _MatrixHelper;
-    _textLeading: number;
-    _textColor: number[];
-    _textLineMatrix: _MatrixHelper;
-    _extractedText: string;
-    _hasLeading: boolean;
-    _hasNoSpacing: boolean;
-    _textLines: TextLine[];
-    _transformations: _TransformationStack;
-    _identityMatrix: number[];
-    _currentLocation: number[];
-    _currentFont: string;
-    _tempBoundingRectangle: {
-        x: number;
-        y: number;
-        width: number;
-        height: number;
-    };
-    _boundingRectangle: {
-        x: number;
-        y: number;
-        width: number;
-        height: number;
-    };
-    _previousRect: {
-        x: number;
-        y: number;
-        width: number;
-        height: number;
-    };
-    _fontSize: number;
-    _textHorizontalScaling: number;
-    _previousTextMatrix: _MatrixHelper;
-    _previousFontSize: number;
-    _previousExtractText: string;
-    _arise: number;
-    _isTextMatrix: boolean;
-    _currentTextMatrix: _MatrixHelper;
-    _text: string;
-    _hasTj: boolean;
-    _hasTm: boolean;
-    _hasET: boolean;
-    _characterSpacing: number;
-    _wordSpacing: number;
-    _hasBeginMarkedContent: boolean;
-    _differenceX: number;
-    _textScale: number;
-    _textRise: number;
-    _width: number;
-    _height: number;
-    _crossReference: _PdfCrossReference;
-    _resultantText: string;
-    _currentExtractedText: string;
-    _initialTransForm: _MatrixHelper;
-    _textGlyph: TextGlyph[];
-    _textWord: TextWord[];
-    _textLine: TextLine[];
-    _textExtraction: string[];
-    _fontCollection: Map<string, _FontStructure>;
-    _ctm: _MatrixHelper;
-    _objects: _MatrixHelper[];
-    _isLayout: boolean;
-    _isRotatePage: boolean;
-    _isExtractTextLines: boolean;
-    _contentParser: _PdfContentParserHelper;
-    _parser: _PdfTextParser;
-    /**
-     * Initialize a new instance of the `PdfDataExtractor` class
-     *
-     * @param {PdfDocument} document PDF document
-     * ```typescript
-     * // Load an existing PDF document
-     * let document: PdfDocument = new PdfDocument(data1);
-     * // Initialize a new instance of the `PdfDataExtractor` class
-     * let extractor: PdfDataExtractor = new PdfDataExtractor(document);
-     * // Extracts text from the PDF Page based on its layout
-     * let text: string = extractor.extractText({isLayout: true});
-     * // Save the output PDF
-     * document.save(‘Output.pdf’);
-     * // Destroy the documents
-     * document.destroy();
-     * ```
-     */
-    constructor(document: PdfDocument);
-    /**
-     * Extract text from the PDF document
-     *
-     * @returns {string} The extracted text
-     *
-     * ```typescript
-     * // Load an existing PDF document
-     * let document: PdfDocument = new PdfDocument(data1);
-     * // Initialize a new instance of the `PdfDataExtractor` class
-     * let extractor: PdfDataExtractor = new PdfDataExtractor(document);
-     * // Extract text content from the PDF document.
-     * let text: string = extractor.extractText();
-     * // Save the output PDF
-     * document.save(‘Output.pdf’);
-     * // Destroy the documents
-     * document.destroy();
-     * ```
-     */
-    extractText(): string;
-    /**
-     * Extract text from the page ranges specified by start and end page number
-     *
-     * @param {object} options Options to specify the page range to be selected and to extract the text.
-     * @returns {string} The extracted text
-     *
-     * ```typescript
-     * // Load an existing PDF document
-     * let document: PdfDocument = new PdfDocument(data1);
-     * // Initialize a new instance of the `PdfDataExtractor` class
-     * let extractor: PdfDataExtractor = new PdfDataExtractor(document);
-     * // Extract text content from the PDF document.
-     * let text: string = extractor.extractText({ startPageIndex: 0, endPageIndex: document.pageCount - 1 });
-     * // Save the output PDF
-     * document.save(‘Output.pdf’);
-     * // Destroy the documents
-     * document.destroy();
-     * ```
-     */
-    extractText(options: {
-        isLayout?: boolean;
-        startPageIndex?: number;
-        endPageIndex?: number;
-    }): string;
-    _renderTextAsLayOut(recordCollection: _PdfRecord[], page: PdfPage, fontCollection: Map<string, _FontStructure>, xObjectCollection: Map<string, any>): any;
-    _renderText(page: PdfPage, fontCollection: Map<string, _FontStructure>, xObjectCollection: Map<string, any>, graphicState: _GraphicState): any;
-    _setTextLeading(textLeading: number): void;
-    _moveToNextLine(tx: number, ty: number, textLineMatrix: _MatrixHelper): void;
-    _updateTextMatrix(tj: number): _MatrixHelper;
-    _updateTextLineMatrix(char: string, width: number): void;
-    _renderTextElementFromTJ(elements: string[], page: PdfPage, fontCollection: Map<string, _FontStructure>): string;
-    _getTextHeight(font: _FontStructure, textMatrix: _MatrixHelper): number;
-    _transform(m1: number[], m2: number[]): number[];
-    _buildTextContentStream(elements: string[], page: PdfPage, fontCollection: Map<string, _FontStructure>): void;
-    _getTextWidth(text: string, extraSpacing: number, currentFont: _FontStructure, page: PdfPage, tempString: string): string;
-    _splitWords(glyph: string, tempString: string, fontName: string, fontStyle: PdfFontStyle, page: PdfPage, rotation?: number, textColor?: number[]): string;
-    _getTextRenderingMatrix(): _MatrixHelper;
-    _renderFont(fontElements: string[]): void;
-    /**
-     * Extract `TextLine` collection from the PDF document.
-     *
-     * @returns {TextLine[]} The extracted textLines
-     *
-     * ```typescript
-     * // Load an existing PDF document
-     * let document: PdfDocument = new PdfDocument(data1);
-     * // Initialize a new instance of the `PdfDataExtractor` class
-     * let extractor: PdfDataExtractor = new PdfDataExtractor(document);
-     * // Extract `TextLine` from the PDF document.
-     * let textCollection: TextLine[] = extractor.extractTextLines();
-     * // Save the output PDF
-     * document.save(‘Output.pdf’);
-     * // Destroy the documents
-     * document.destroy();
-     * ```
-     */
-    extractTextLines(): TextLine[];
-    /**
-     * Extract `TextLine` from the PDF document.
-     *
-     * @param {object} options The options to specify the page range to be selected.
-     * @returns {TextLine[]} The extracted textLines
-     *
-     * ```typescript
-     * // Load an existing PDF document
-     * let document: PdfDocument = new PdfDocument(data1);
-     * // Initialize a new instance of the `PdfDataExtractor` class
-     * let extractor: PdfDataExtractor = new PdfDataExtractor(document);
-     * // Extract `TextLine` from the PDF document.
-     * let textCollection: TextLine[] = extractor.extractTextLines({ startPageIndex: 0, endPageIndex: document.pageCount - 1});
-     * // Save the output PDF
-     * document.save(‘Output.pdf’);
-     * // Destroy the documents
-     * document.destroy();
-     * ```
-     */
-    extractTextLines(options: {
-        startPageIndex?: number;
-        endPageIndex?: number;
-    }): TextLine[];
-    _processPages(startIndex: number, endIndex: number): void;
-}