pdfreader.java

一个java操作pdf文件的开发包,很好用的.

        tokens.seek(tokens.getStartxref());
        tokens.nextToken();
        if (!tokens.getStringValue().equals("startxref"))
            throw new IOException("startxref not found.");
        tokens.nextToken();
        if (tokens.getTokenType() != PRTokeniser.TK_NUMBER)
            throw new IOException("startxref is not followed by a number.");
        int startxref = tokens.intValue();
        tokens.seek(startxref);
        int ch;
        do {
            ch = tokens.read();
        } while (ch != -1 && ch != 't');
        if (ch == -1)
            throw new IOException("Unexpected end of file.");
        tokens.backOnePosition();
        tokens.nextValidToken();
        if (!tokens.getStringValue().equals("trailer"))
            throw new IOException("trailer not found.");
        trailer = (PdfDictionary)readPRObject();
        if (trailer.get(PdfName.ENCRYPT) != null) {
            encrypted = true;
            throw new IOException("Encrypted files are not supported.");
        }
        PdfNumber xrefSize = (PdfNumber)trailer.get(PdfName.SIZE);
        xref = new int[xrefSize.intValue()];
        tokens.seek(startxref);
        readXrefSection();
        PdfDictionary trailer2 = trailer;
        while (true) {
            PdfNumber prev = (PdfNumber)trailer2.get(PdfName.PREV);
            if (prev == null)
                break;
            tokens.seek(prev.intValue());
            readXrefSection();
            trailer2 = (PdfDictionary)readPRObject();
        }
    }
    
    protected void readXrefSection() throws IOException {
        tokens.nextValidToken();
        if (!tokens.getStringValue().equals("xref"))
            tokens.throwError("xref subsection not found");
        int start = 0;
        int end = 0;
        int pos = 0;
        int gen = 0;
        while (true) {
            tokens.nextValidToken();
            if (tokens.getStringValue().equals("trailer"))
                break;
            if (tokens.getTokenType() != PRTokeniser.TK_NUMBER)
                tokens.throwError("Object number of the first object in this xref subsection not found");
            start = tokens.intValue();
            tokens.nextValidToken();
            if (tokens.getTokenType() != PRTokeniser.TK_NUMBER)
                tokens.throwError("Number of entries in this xref subsection not found");
            end = tokens.intValue() + start;
            if (start == 1) { // fix incorrect start number
                int back = tokens.getFilePointer();
                tokens.nextValidToken();
                pos = tokens.intValue();
                tokens.nextValidToken();
                gen = tokens.intValue();
                if (pos == 0 && gen == 65535) {
                    --start;
                    --end;
                }
                tokens.seek(back);
            }
            if (xref.length < end) { // fix incorrect size
                int xref2[] = new int[end];
                System.arraycopy(xref, 0, xref2, 0, xref.length);
                xref = xref2;
            }
            for (int k = start; k < end; ++k) {
                tokens.nextValidToken();
                pos = tokens.intValue();
                tokens.nextValidToken();
                gen = tokens.intValue();
                tokens.nextValidToken();
                if (tokens.getStringValue().equals("n")) {
                    if (xref[k] == 0)
                        xref[k] = pos;
                }
                else if (tokens.getStringValue().equals("f")) {
                    if (xref[k] == 0)
                        xref[k] = -1;
                }
                else
                    tokens.throwError("Invalid cross-reference entry in this xref subsection");
            }
        }
    }

    protected void rebuildXref() throws IOException {
        tokens.seek(0);
        int xr[][] = new int[1024][];
        int top = 0;
        trailer = null;
        byte line[] = new byte[64];
        for (;;) {
            int pos = tokens.getFilePointer();
            if (!tokens.readLineSegment(line))
                break;
            if (line[0] == 't') {
                if (!PdfEncodings.convertToString(line, null).startsWith("trailer"))
                    continue;
                pos = tokens.getFilePointer();
                try {
                    PdfDictionary dic = (PdfDictionary)readPRObject();
                    if (dic.get(PdfName.ROOT) != null)
                        trailer = dic;
                    else
                        tokens.seek(pos);
                }
                catch (Exception e) {
                    tokens.seek(pos);
                }
            }
            else if (line[0] >= '0' && line[0] <= '9') {
                int obj[] = PRTokeniser.checkObjectStart(line);
                if (obj == null)
                    continue;
                int num = obj[0];
                int gen = obj[1];
                if (num >= xr.length) {
                    int newLength = num * 2;
                    int xr2[][] = new int[newLength][];
                    System.arraycopy(xr, 0, xr2, 0, top);
                    xr = xr2;
                }
                if (num >= top)
                    top = num + 1;
                if (xr[num] == null || gen >= xr[num][1]) {
                    obj[0] = pos;
                    xr[num] = obj;
                }
            }
        }
        if (trailer == null)
            throw new IOException("trailer not found.");
        if (trailer.get(PdfName.ENCRYPT) != null)
            throw new IOException("Encrypted files are not supported.");
        xref = new int[top];
        for (int k = 0; k < top; ++k) {
            int obj[] = xr[k];
            if (obj != null)
                xref[k] = obj[0];
        }
    }

    protected PdfDictionary readDictionary() throws IOException {
        PdfDictionary dic = new PdfDictionary();
        while (true) {
            tokens.nextValidToken();
            if (tokens.getTokenType() == PRTokeniser.TK_END_DIC)
                break;
            if (tokens.getTokenType() != PRTokeniser.TK_NAME)
                tokens.throwError("Dictionary key is not a name.");
            PdfName name = new PdfName(tokens.getStringValue());
            PdfObject obj = readPRObject();
            int type = obj.type();
            if (-type == PRTokeniser.TK_END_DIC)
                tokens.throwError("Unexpected '>>'");
            if (-type == PRTokeniser.TK_END_ARRAY)
                tokens.throwError("Unexpected ']'");
            dic.put(name, obj);
        }
        return dic;
    }
    
    protected PdfArray readArray() throws IOException {
        PdfArray array = new PdfArray();
        while (true) {
            PdfObject obj = readPRObject();
            int type = obj.type();
            if (-type == PRTokeniser.TK_END_ARRAY)
                break;
            if (-type == PRTokeniser.TK_END_DIC)
                tokens.throwError("Unexpected '>>'");
            array.add(obj);
        }
        return array;
    }
    
    protected PdfObject readPRObject() throws IOException {
        tokens.nextValidToken();
        int type = tokens.getTokenType();
        switch (type) {
            case PRTokeniser.TK_START_DIC:
            {
                PdfDictionary dic = readDictionary();
                int pos = tokens.getFilePointer();
		// be careful in the trailer. May not be a "next" token.
                if (tokens.nextToken() && tokens.getStringValue().equals("stream")) {
                    int ch = tokens.read();
                    if (ch == '\r')
                        ch = tokens.read();
                    if (ch != '\n')
                        tokens.backOnePosition();
                    PRStream stream = new PRStream(this, tokens.getFilePointer());
                    stream.putAll(dic);
                    return stream;
                }
                else {
                    tokens.seek(pos);
                    return dic;
                }
            }
            case PRTokeniser.TK_START_ARRAY:
                return readArray();
            case PRTokeniser.TK_NUMBER:
                return new PdfNumber(tokens.getStringValue());
            case PRTokeniser.TK_STRING:
                return new PdfString(tokens.getStringValue(), null);
            case PRTokeniser.TK_NAME:
                return new PdfName(tokens.getStringValue());
            case PRTokeniser.TK_REF:
                return new PRIndirectReference(this, tokens.getReference(), tokens.getGeneration());
            default:
                return new PdfLiteral(-type, tokens.getStringValue());
        }
    }

    public static byte[] FlateDecode(byte in[]) {
        byte b[] = FlateDecode(in, true);
        if (b == null)
            return FlateDecode(in, false);
        return b;
    }
    
    public static byte[] FlateDecode(byte in[], boolean strict) {
        ByteArrayInputStream stream = new ByteArrayInputStream(in);
        InflaterInputStream zip = new InflaterInputStream(stream);
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        byte b[] = new byte[strict ? 4092 : 1];
        try {
            int n;
            while ((n = zip.read(b)) >= 0) {
                out.write(b, 0, n);
            }
            zip.close();
            out.close();
            return out.toByteArray();
        }
        catch (Exception e) {
            if (strict)
                return null;
            return out.toByteArray();
        }
    }

    public static byte[] ASCIIHexDecode(byte in[]) {
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        boolean first = true;
        int n1 = 0;
        for (int k = 0; k < in.length; ++k) {
            int ch = in[k] & 0xff;
            if (ch == '>')
                break;
            if (PRTokeniser.isWhitespace(ch))
                continue;
            int n = PRTokeniser.getHex(ch);
            if (n == -1)
                throw new RuntimeException("Illegal character in ASCIIHexDecode.");
            if (first)
                n1 = n;
            else
                out.write((byte)((n1 << 4) + n));
            first = !first;
        }
        if (!first)
            out.write((byte)(n1 << 4));
        return out.toByteArray();
    }

    public static byte[] ASCII85Decode(byte in[]) {
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        int state = 0;
        int chn[] = new int[5];
        for (int k = 0; k < in.length; ++k) {
            int ch = in[k] & 0xff;
            if (ch == '~')
                break;
            if (PRTokeniser.isWhitespace(ch))
                continue;
            if (ch == 'z' && state == 0) {
                out.write(0);
                out.write(0);
                out.write(0);
                out.write(0);
                continue;
            }
            if (ch < '!' || ch > 'u')
                throw new RuntimeException("Illegal character in ASCII85Decode.");
            chn[state] = ch - '!';
            ++state;
            if (state == 5) {
                state = 0;
                int r = 0;
                for (int j = 0; j < 5; ++j)
                    r = r * 85 + chn[j];
                out.write((byte)(r >> 24));
                out.write((byte)(r >> 16));
                out.write((byte)(r >> 8));
                out.write((byte)r);
            }
        }
        int r = 0;
        if (state == 1)
            throw new RuntimeException("Illegal length in ASCII85Decode.");
        if (state == 2) {
            r = chn[0] * 85 + chn[1];
            out.write((byte)r);
        }
        else if (state == 3) {
            r = chn[0] * 85 * 85 + chn[1] * 85 + chn[2];
            out.write((byte)(r >> 8));
            out.write((byte)r);
        }
        else if (state == 4) {
            r = chn[0] * 85 * 85 * 85 + chn[1] * 85 * 85 + chn[2] * 85 + chn[3];
            out.write((byte)(r >> 16));
            out.write((byte)(r >> 8));
            out.write((byte)r);
        }
        return out.toByteArray();
    }

    public static byte[] LZWDecode(byte in[]) {
        ByteArrayOutputStream out = new ByteArrayOutputStream();
        LZWDecoder lzw = new LZWDecoder();
        lzw.decode(in, out);
        return out.toByteArray();
    }
    
    /** Checks if the document had errors and was rebuilt.
     * @return true if rebuilt.
     *
     */
    public boolean isRebuilt() {
        return this.rebuilt;
    }

    public PdfDictionary getPageN(int pageNum)
    {
        if (pageNum > pages.length) return null;
        return pages[pageNum - 1];


    }

    public PRIndirectReference getPageOrigRef(int pageNum)
    {
        if (pageNum > pageRefs.length) return null;
        return pageRefs[pageNum - 1];
    }
    
}