pdf2json 0.1.0

data/pdf2json-0.52-source/xpdf/Page.h

@@ -0,0 +1,187 @@
+//========================================================================
+//
+// Page.h
+//
+// Copyright 1996-2003 Glyph & Cog, LLC
+//
+//========================================================================
+
+#ifndef PAGE_H
+#define PAGE_H
+
+#include <aconf.h>
+
+#ifdef USE_GCC_PRAGMAS
+#pragma interface
+#endif
+
+#include "Object.h"
+
+class Dict;
+class XRef;
+class OutputDev;
+class Links;
+class Catalog;
+
+//------------------------------------------------------------------------
+
+class PDFRectangle {
+public:
+  double x1, y1, x2, y2;
+
+  PDFRectangle() { x1 = y1 = x2 = y2 = 0; }
+  PDFRectangle(double x1A, double y1A, double x2A, double y2A)
+    { x1 = x1A; y1 = y1A; x2 = x2A; y2 = y2A; }
+  GBool isValid() { return x1 != 0 || y1 != 0 || x2 != 0 || y2 != 0; }
+  void clipTo(PDFRectangle *rect);
+};
+
+//------------------------------------------------------------------------
+// PageAttrs
+//------------------------------------------------------------------------
+
+class PageAttrs {
+public:
+
+  // Construct a new PageAttrs object by merging a dictionary
+  // (of type Pages or Page) into another PageAttrs object.  If
+  // <attrs> is NULL, uses defaults.
+  PageAttrs(PageAttrs *attrs, Dict *dict);
+
+  // Destructor.
+  ~PageAttrs();
+
+  // Accessors.
+  PDFRectangle *getMediaBox() { return &mediaBox; }
+  PDFRectangle *getCropBox() { return &cropBox; }
+  GBool isCropped() { return haveCropBox; }
+  PDFRectangle *getBleedBox() { return &bleedBox; }
+  PDFRectangle *getTrimBox() { return &trimBox; }
+  PDFRectangle *getArtBox() { return &artBox; }
+  int getRotate() { return rotate; }
+  GString *getLastModified()
+    { return lastModified.isString()
+	? lastModified.getString() : (GString *)NULL; }
+  Dict *getBoxColorInfo()
+    { return boxColorInfo.isDict() ? boxColorInfo.getDict() : (Dict *)NULL; }
+  Dict *getGroup()
+    { return group.isDict() ? group.getDict() : (Dict *)NULL; }
+  Stream *getMetadata()
+    { return metadata.isStream() ? metadata.getStream() : (Stream *)NULL; }
+  Dict *getPieceInfo()
+    { return pieceInfo.isDict() ? pieceInfo.getDict() : (Dict *)NULL; }
+  Dict *getSeparationInfo()
+    { return separationInfo.isDict()
+	? separationInfo.getDict() : (Dict *)NULL; }
+  Dict *getResourceDict()
+    { return resources.isDict() ? resources.getDict() : (Dict *)NULL; }
+
+private:
+
+  GBool readBox(Dict *dict, char *key, PDFRectangle *box);
+
+  PDFRectangle mediaBox;
+  PDFRectangle cropBox;
+  GBool haveCropBox;
+  PDFRectangle bleedBox;
+  PDFRectangle trimBox;
+  PDFRectangle artBox;
+  int rotate;
+  Object lastModified;
+  Object boxColorInfo;
+  Object group;
+  Object metadata;
+  Object pieceInfo;
+  Object separationInfo;
+  Object resources;
+};
+
+//------------------------------------------------------------------------
+// Page
+//------------------------------------------------------------------------
+
+class Page {
+public:
+
+  // Constructor.
+  Page(XRef *xrefA, int numA, Dict *pageDict, PageAttrs *attrsA);
+
+  // Destructor.
+  ~Page();
+
+  // Is page valid?
+  GBool isOk() { return ok; }
+
+  // Get page parameters.
+  int getNum() { return num; }
+  PDFRectangle *getMediaBox() { return attrs->getMediaBox(); }
+  PDFRectangle *getCropBox() { return attrs->getCropBox(); }
+  GBool isCropped() { return attrs->isCropped(); }
+  double getMediaWidth() 
+    { return attrs->getMediaBox()->x2 - attrs->getMediaBox()->x1; }
+  double getMediaHeight()
+    { return attrs->getMediaBox()->y2 - attrs->getMediaBox()->y1; }
+  double getCropWidth() 
+    { return attrs->getCropBox()->x2 - attrs->getCropBox()->x1; }
+  double getCropHeight()
+    { return attrs->getCropBox()->y2 - attrs->getCropBox()->y1; }
+  PDFRectangle *getBleedBox() { return attrs->getBleedBox(); }
+  PDFRectangle *getTrimBox() { return attrs->getTrimBox(); }
+  PDFRectangle *getArtBox() { return attrs->getArtBox(); }
+  int getRotate() { return attrs->getRotate(); }
+  GString *getLastModified() { return attrs->getLastModified(); }
+  Dict *getBoxColorInfo() { return attrs->getBoxColorInfo(); }
+  Dict *getGroup() { return attrs->getGroup(); }
+  Stream *getMetadata() { return attrs->getMetadata(); }
+  Dict *getPieceInfo() { return attrs->getPieceInfo(); }
+  Dict *getSeparationInfo() { return attrs->getSeparationInfo(); }
+
+  // Get resource dictionary.
+  Dict *getResourceDict() { return attrs->getResourceDict(); }
+
+  // Get annotations array.
+  Object *getAnnots(Object *obj) { return annots.fetch(xref, obj); }
+
+  // Return a list of links.
+  Links *getLinks(Catalog *catalog);
+
+  // Get contents.
+  Object *getContents(Object *obj) { return contents.fetch(xref, obj); }
+
+  // Display a page.
+  void display(OutputDev *out, double hDPI, double vDPI,
+	       int rotate, GBool useMediaBox, GBool crop,
+	       Links *links, GBool printing, Catalog *catalog,
+	       GBool (*abortCheckCbk)(void *data) = NULL,
+	       void *abortCheckCbkData = NULL);
+
+  // Display part of a page.
+  void displaySlice(OutputDev *out, double hDPI, double vDPI,
+		    int rotate, GBool useMediaBox, GBool crop,
+		    int sliceX, int sliceY, int sliceW, int sliceH,
+		    Links *links, GBool printing, Catalog *catalog,
+		    GBool (*abortCheckCbk)(void *data) = NULL,
+		    void *abortCheckCbkData = NULL);
+
+  void makeBox(double hDPI, double vDPI, int rotate,
+	       GBool useMediaBox, GBool upsideDown,
+	       double sliceX, double sliceY, double sliceW, double sliceH,
+	       PDFRectangle *box, GBool *crop);
+
+  void processLinks(OutputDev *out, Catalog *catalog);
+
+  // Get the page's default CTM.
+  void getDefaultCTM(double *ctm, double hDPI, double vDPI,
+		     int rotate, GBool useMediaBox, GBool upsideDown);
+
+private:
+
+  XRef *xref;			// the xref table for this PDF file
+  int num;			// page number
+  PageAttrs *attrs;		// page attributes
+  Object annots;		// annotations array
+  Object contents;		// page contents
+  GBool ok;			// true if page is valid
+};
+
+#endif

data/pdf2json-0.52-source/xpdf/Parser.cc

@@ -0,0 +1,227 @@
+//========================================================================
+//
+// Parser.cc
+//
+// Copyright 1996-2003 Glyph & Cog, LLC
+//
+//========================================================================
+
+#include <aconf.h>
+
+#ifdef USE_GCC_PRAGMAS
+#pragma implementation
+#endif
+
+#include <stddef.h>
+#include "Object.h"
+#include "Array.h"
+#include "Dict.h"
+#include "Decrypt.h"
+#include "Parser.h"
+#include "XRef.h"
+#include "Error.h"
+
+Parser::Parser(XRef *xrefA, Lexer *lexerA, GBool allowStreamsA) {
+  xref = xrefA;
+  lexer = lexerA;
+  inlineImg = 0;
+  allowStreams = allowStreamsA;
+  lexer->getObj(&buf1);
+  lexer->getObj(&buf2);
+}
+
+Parser::~Parser() {
+  buf1.free();
+  buf2.free();
+  delete lexer;
+}
+
+Object *Parser::getObj(Object *obj, Guchar *fileKey,
+		       CryptAlgorithm encAlgorithm, int keyLength,
+		       int objNum, int objGen) {
+  char *key;
+  Stream *str;
+  Object obj2;
+  int num;
+  DecryptStream *decrypt;
+  GString *s, *s2;
+  int c;
+
+  // refill buffer after inline image data
+  if (inlineImg == 2) {
+    buf1.free();
+    buf2.free();
+    lexer->getObj(&buf1);
+    lexer->getObj(&buf2);
+    inlineImg = 0;
+  }
+
+  // array
+  if (buf1.isCmd("[")) {
+    shift();
+    obj->initArray(xref);
+    while (!buf1.isCmd("]") && !buf1.isEOF())
+      obj->arrayAdd(getObj(&obj2, fileKey, encAlgorithm, keyLength,
+			   objNum, objGen));
+    if (buf1.isEOF())
+      error(getPos(), "End of file inside array");
+    shift();
+
+  // dictionary or stream
+  } else if (buf1.isCmd("<<")) {
+    shift();
+    obj->initDict(xref);
+    while (!buf1.isCmd(">>") && !buf1.isEOF()) {
+      if (!buf1.isName()) {
+	error(getPos(), "Dictionary key must be a name object");
+	shift();
+      } else {
+	key = copyString(buf1.getName());
+	shift();
+	if (buf1.isEOF() || buf1.isError()) {
+	  gfree(key);
+	  break;
+	}
+	obj->dictAdd(key, getObj(&obj2, fileKey, encAlgorithm, keyLength,
+				 objNum, objGen));
+      }
+    }
+    if (buf1.isEOF())
+      error(getPos(), "End of file inside dictionary");
+    // stream objects are not allowed inside content streams or
+    // object streams
+    if (allowStreams && buf2.isCmd("stream")) {
+      if ((str = makeStream(obj, fileKey, encAlgorithm, keyLength,
+			    objNum, objGen))) {
+	obj->initStream(str);
+      } else {
+	obj->free();
+	obj->initError();
+      }
+    } else {
+      shift();
+    }
+
+  // indirect reference or integer
+  } else if (buf1.isInt()) {
+    num = buf1.getInt();
+    shift();
+    if (buf1.isInt() && buf2.isCmd("R")) {
+      obj->initRef(num, buf1.getInt());
+      shift();
+      shift();
+    } else {
+      obj->initInt(num);
+    }
+
+  // string
+  } else if (buf1.isString() && fileKey) {
+    s = buf1.getString();
+    s2 = new GString();
+    obj2.initNull();
+    decrypt = new DecryptStream(new MemStream(s->getCString(), 0,
+					      s->getLength(), &obj2),
+				fileKey, encAlgorithm, keyLength,
+				objNum, objGen);
+    decrypt->reset();
+    while ((c = decrypt->getChar()) != EOF) {
+      s2->append((char)c);
+    }
+    delete decrypt;
+    obj->initString(s2);
+    shift();
+
+  // simple object
+  } else {
+    buf1.copy(obj);
+    shift();
+  }
+
+  return obj;
+}
+
+Stream *Parser::makeStream(Object *dict, Guchar *fileKey,
+			   CryptAlgorithm encAlgorithm, int keyLength,
+			   int objNum, int objGen) {
+  Object obj;
+  BaseStream *baseStr;
+  Stream *str;
+  Guint pos, endPos, length;
+
+  // get stream start position
+  lexer->skipToNextLine();
+  pos = lexer->getPos();
+
+  // get length
+  dict->dictLookup("Length", &obj);
+  if (obj.isInt()) {
+    length = (Guint)obj.getInt();
+    obj.free();
+  } else {
+    error(getPos(), "Bad 'Length' attribute in stream");
+    obj.free();
+    return NULL;
+  }
+
+  // check for length in damaged file
+  if (xref && xref->getStreamEnd(pos, &endPos)) {
+    length = endPos - pos;
+  }
+
+  // in badly damaged PDF files, we can run off the end of the input
+  // stream immediately after the "stream" token
+  if (!lexer->getStream()) {
+    return NULL;
+  }
+  baseStr = lexer->getStream()->getBaseStream();
+
+  // skip over stream data
+  lexer->setPos(pos + length);
+
+  // refill token buffers and check for 'endstream'
+  shift();  // kill '>>'
+  shift();  // kill 'stream'
+  if (buf1.isCmd("endstream")) {
+    shift();
+  } else {
+    error(getPos(), "Missing 'endstream'");
+    // kludge for broken PDF files: just add 5k to the length, and
+    // hope its enough
+    length += 5000;
+  }
+
+  // make base stream
+  str = baseStr->makeSubStream(pos, gTrue, length, dict);
+
+  // handle decryption
+  if (fileKey) {
+    str = new DecryptStream(str, fileKey, encAlgorithm, keyLength,
+			    objNum, objGen);
+  }
+
+  // get filters
+  str = str->addFilters(dict);
+
+  return str;
+}
+
+void Parser::shift() {
+  if (inlineImg > 0) {
+    if (inlineImg < 2) {
+      ++inlineImg;
+    } else {
+      // in a damaged content stream, if 'ID' shows up in the middle
+      // of a dictionary, we need to reset
+      inlineImg = 0;
+    }
+  } else if (buf2.isCmd("ID")) {
+    lexer->skipChar();		// skip char after 'ID' command
+    inlineImg = 1;
+  }
+  buf1.free();
+  buf1 = buf2;
+  if (inlineImg > 0)		// don't buffer inline image data
+    buf2.initNull();
+  else
+    lexer->getObj(&buf2);
+}

data/pdf2json-0.52-source/xpdf/Parser.h

@@ -0,0 +1,59 @@
+//========================================================================
+//
+// Parser.h
+//
+// Copyright 1996-2003 Glyph & Cog, LLC
+//
+//========================================================================
+
+#ifndef PARSER_H
+#define PARSER_H
+
+#include <aconf.h>
+
+#ifdef USE_GCC_PRAGMAS
+#pragma interface
+#endif
+
+#include "Lexer.h"
+
+//------------------------------------------------------------------------
+// Parser
+//------------------------------------------------------------------------
+
+class Parser {
+public:
+
+  // Constructor.
+  Parser(XRef *xrefA, Lexer *lexerA, GBool allowStreamsA);
+
+  // Destructor.
+  ~Parser();
+
+  // Get the next object from the input stream.
+  Object *getObj(Object *obj, Guchar *fileKey = NULL,
+		 CryptAlgorithm encAlgorithm = cryptRC4, int keyLength = 0,
+		 int objNum = 0, int objGen = 0);
+
+  // Get stream.
+  Stream *getStream() { return lexer->getStream(); }
+
+  // Get current position in file.
+  int getPos() { return lexer->getPos(); }
+
+private:
+
+  XRef *xref;			// the xref table for this PDF file
+  Lexer *lexer;			// input stream
+  GBool allowStreams;		// parse stream objects?
+  Object buf1, buf2;		// next two tokens
+  int inlineImg;		// set when inline image data is encountered
+
+  Stream *makeStream(Object *dict, Guchar *fileKey,
+		     CryptAlgorithm encAlgorithm, int keyLength,
+		     int objNum, int objGen);
+  void shift();
+};
+
+#endif
+