@f-o-t/pdf 0.1.0

package/dist/index.js

@@ -0,0 +1,111 @@
+import {
+  CMYKColorSchema,
+  FONT_FAMILIES,
+  GrayColorSchema,
+  LineOptionsSchema,
+  PDFArraySchema,
+  PDFColorSchema,
+  PDFDictionarySchema,
+  PDFDocument,
+  PDFIndirectObjectSchema,
+  PDFMetadataSchema,
+  PDFNameSchema,
+  PDFObjectTypeSchema,
+  PDFPage,
+  PDFRefSchema,
+  PDFStreamSchema,
+  PDFValueSchema,
+  PDFVersionSchema,
+  PageSizeSchema,
+  RGBColorSchema,
+  RectOptionsSchema,
+  STANDARD_FONTS,
+  TextOptionsSchema,
+  getFontRefName,
+  isStandardFont,
+  serializeObject,
+  serializeStream,
+  serializeValue
+} from "./shared/chunk-37mjkw9w.js";
+import {
+  FontNotFoundError,
+  InvalidImageError,
+  InvalidPDFObjectError,
+  NotImplementedError,
+  PDFEncryptionError,
+  PDFError,
+  PDFGenerationError,
+  PDFLexer,
+  PDFParseError,
+  PDFParser,
+  PDFReader,
+  PDFSignatureError,
+  TokenType
+} from "./shared/chunk-10ftnz45.js";
+import {
+  createArray,
+  createDictionary,
+  createName,
+  createRef,
+  createStream,
+  isArray,
+  isDictionary,
+  isName,
+  isRef,
+  isStream
+} from "./shared/chunk-6dengthp.js";
+export {
+  serializeValue,
+  serializeStream,
+  serializeObject,
+  isStream,
+  isStandardFont,
+  isRef,
+  isName,
+  isDictionary,
+  isArray,
+  getFontRefName,
+  createStream,
+  createRef,
+  createName,
+  createDictionary,
+  createArray,
+  TokenType,
+  TextOptionsSchema,
+  STANDARD_FONTS,
+  RectOptionsSchema,
+  RGBColorSchema,
+  PageSizeSchema,
+  PDFVersionSchema,
+  PDFValueSchema,
+  PDFStreamSchema,
+  PDFSignatureError,
+  PDFRefSchema,
+  PDFReader,
+  PDFParser,
+  PDFParseError,
+  PDFPage,
+  PDFObjectTypeSchema,
+  PDFNameSchema,
+  PDFMetadataSchema,
+  PDFLexer,
+  PDFIndirectObjectSchema,
+  PDFGenerationError,
+  PDFError,
+  PDFEncryptionError,
+  PDFDocument,
+  PDFDictionarySchema,
+  PDFColorSchema,
+  PDFArraySchema,
+  NotImplementedError,
+  LineOptionsSchema,
+  InvalidPDFObjectError,
+  InvalidImageError,
+  GrayColorSchema,
+  FontNotFoundError,
+  FONT_FAMILIES,
+  CMYKColorSchema
+};
+
+//# debugId=EECFD06F56D594E564756E2164756E21
+//# sourceMappingURL=data:application/json;base64,ewogICJ2ZXJzaW9uIjogMywKICAic291cmNlcyI6IFtdLAogICJzb3VyY2VzQ29udGVudCI6IFsKICBdLAogICJtYXBwaW5ncyI6ICIiLAogICJkZWJ1Z0lkIjogIkVFQ0ZEMDZGNTZENTk0RTU2NDc1NkUyMTY0NzU2RTIxIiwKICAibmFtZXMiOiBbXQp9

package/dist/parsing/index.d.ts

@@ -0,0 +1,234 @@
+/**
+* PDF token types
+*/
+declare enum TokenType {
+	NUMBER = "NUMBER",
+	STRING = "STRING",
+	NAME = "NAME",
+	BOOLEAN = "BOOLEAN",
+	NULL = "NULL",
+	ARRAY_START = "ARRAY_START",
+	ARRAY_END = "ARRAY_END",
+	DICT_START = "DICT_START",
+	DICT_END = "DICT_END",
+	OBJ = "OBJ",
+	ENDOBJ = "ENDOBJ",
+	STREAM = "STREAM",
+	ENDSTREAM = "ENDSTREAM",
+	XREF = "XREF",
+	TRAILER = "TRAILER",
+	STARTXREF = "STARTXREF",
+	R = "R",
+	EOF = "EOF"
+}
+/**
+* PDF token
+*/
+interface Token {
+	type: TokenType;
+	value: any;
+	position: number;
+}
+/**
+* PDF Lexer
+*/
+declare class PDFLexer {
+	private data;
+	private position;
+	constructor(data: Uint8Array);
+	/**
+	* Get next token
+	*/
+	nextToken(): Token;
+	/**
+	* Peek at next character without consuming
+	*/
+	private peek;
+	/**
+	* Skip whitespace and comments
+	*/
+	private skipWhitespace;
+	/**
+	* Read a name token
+	*/
+	private readName;
+	/**
+	* Read a string token
+	*/
+	private readString;
+	/**
+	* Read a number token
+	*/
+	private readNumber;
+	/**
+	* Read a keyword token
+	*/
+	private readKeyword;
+	/**
+	* Check if character is delimiter
+	*/
+	private isDelimiter;
+	/**
+	* Check if byte is whitespace
+	*/
+	private isWhitespace;
+}
+/**
+* PDF reference to indirect object
+*/
+type PDFRef = {
+	readonly objectNumber: number;
+	readonly generation: number;
+};
+/**
+* PDF value types
+*/
+type PDFValue = boolean | number | string | PDFName | PDFArray | PDFDictionary | PDFStream | null | PDFRef;
+/**
+* PDF Name object
+*/
+type PDFName = {
+	readonly type: "name";
+	readonly value: string;
+};
+/**
+* PDF Array
+*/
+type PDFArray = PDFValue[];
+/**
+* PDF Dictionary
+*/
+type PDFDictionary = Record<string, PDFValue>;
+/**
+* PDF Stream
+*/
+type PDFStream = {
+	readonly dictionary: PDFDictionary;
+	readonly data: Uint8Array;
+};
+/**
+* PDF Parser
+*/
+declare class PDFParser {
+	private lexer;
+	private currentToken;
+	private nextToken;
+	private data;
+	constructor(data: Uint8Array);
+	/**
+	* Parse a PDF value
+	*/
+	parseValue(): PDFValue;
+	/**
+	* Parse number or reference (number number R)
+	*/
+	private parseNumberOrRef;
+	/**
+	* Parse string
+	*/
+	private parseString;
+	/**
+	* Parse name
+	*/
+	private parseName;
+	/**
+	* Parse boolean
+	*/
+	private parseBoolean;
+	/**
+	* Parse null
+	*/
+	private parseNull;
+	/**
+	* Parse array
+	*/
+	private parseArray;
+	/**
+	* Parse dictionary
+	*/
+	private parseDictionary;
+	/**
+	* Parse indirect object
+	*/
+	parseIndirectObject(): {
+		ref: PDFRef;
+		value: PDFValue;
+	};
+	/**
+	* Parse stream (dictionary already parsed)
+	*/
+	private parseStream;
+	/**
+	* Advance to next token
+	*/
+	private advance;
+	/**
+	* Check if more tokens available
+	*/
+	hasMore(): boolean;
+}
+/**
+* Parsed PDF Document
+*/
+interface ParsedPDF {
+	version: string;
+	catalog: PDFRef;
+	pages: PDFPage[];
+	objects: Map<number, any>;
+}
+/**
+* Parsed PDF Page
+*/
+interface PDFPage {
+	ref: PDFRef;
+	size: {
+		width: number;
+		height: number;
+	};
+	content: string;
+}
+/**
+* PDF Reader - reads and parses existing PDFs
+*/
+declare class PDFReader {
+	private data;
+	private objects;
+	constructor(data: Uint8Array);
+	/**
+	* Parse PDF file
+	*/
+	parse(): ParsedPDF;
+	/**
+	* Find startxref offset
+	*/
+	private findStartXRef;
+	/**
+	* Parse xref table
+	*/
+	private parseXRefTable;
+	/**
+	* Parse trailer dictionary
+	*/
+	private parseTrailer;
+	/**
+	* Read all objects from xref table
+	*/
+	private readObjects;
+	/**
+	* Parse PDF version from header
+	*/
+	private parseVersion;
+	/**
+	* Parse pages from catalog
+	*/
+	private parsePages;
+	/**
+	* Parse a single page
+	*/
+	private parsePage;
+	/**
+	* Extract text from content stream
+	*/
+	private extractText;
+}
+export { TokenType, Token, ParsedPDF, PDFReader, PDFParser, PDFPage, PDFLexer };

package/dist/parsing/index.js

@@ -0,0 +1,16 @@
+import {
+  PDFLexer,
+  PDFParser,
+  PDFReader,
+  TokenType
+} from "../shared/chunk-10ftnz45.js";
+import"../shared/chunk-6dengthp.js";
+export {
+  TokenType,
+  PDFReader,
+  PDFParser,
+  PDFLexer
+};
+
+//# debugId=1306B1E9F61CD14B64756E2164756E21
+//# sourceMappingURL=data:application/json;base64,ewogICJ2ZXJzaW9uIjogMywKICAic291cmNlcyI6IFtdLAogICJzb3VyY2VzQ29udGVudCI6IFsKICBdLAogICJtYXBwaW5ncyI6ICIiLAogICJkZWJ1Z0lkIjogIjEzMDZCMUU5RjYxQ0QxNEI2NDc1NkUyMTY0NzU2RTIxIiwKICAibmFtZXMiOiBbXQp9