Protobuf-net反序列化开放街道地图

时间:2011-01-11 22:20:43

标签: protobuf-net openstreetmap

对于我的生活,我无法从Open Street Maps反序列化protobuf文件。

我正在尝试反序列化以下提取:http://download.geofabrik.de/osm/north-america/us-northeast.osm.pbf以获取节点,我使用http://code.google.com/p/protobuf-net/作为库。我试图反序列化一堆不同的对象,但它们都是空的。

可以在此处找到原型文件:http://trac.openstreetmap.org/browser/applications/utils/export/osm2pgsql/protobuf

有什么建议吗?

4 个答案:

答案 0 :(得分:8)

答案 1 :(得分:1)

在马克的大纲设置之后,我通过查看http://git.openstreetmap.nl/index.cgi/pbf2osm.git/tree/src/main.c?h=35116112eb0066c7729a963b292faa608ddc8ad7

找出了最后一部分

这是最终的代码。

using System;
using System.Diagnostics;
using System.IO;
using crosby.binary;
using OSMPBF;
using PerlLLC.Tools;
using ProtoBuf;
using zlib;

namespace OpenStreetMapOperations
{
    class OpenStreetMapParser
    {
        static void Main()
        {
            using (var file = File.OpenRead(StaticTools.AssemblyDirectory + @"\us-pacific.osm.pbf"))
            {
                // from http://wiki.openstreetmap.org/wiki/ProtocolBufBinary:
                //A file contains a header followed by a sequence of fileblocks. The design is intended to allow future random-access to the contents of the file and skipping past not-understood or unwanted data.
                //The format is a repeating sequence of:
                //int4: length of the BlockHeader message in network byte order
                //serialized BlockHeader message
                //serialized Blob message (size is given in the header)

                int length, blockCount = 0;
                while (Serializer.TryReadLengthPrefix(file, PrefixStyle.Fixed32, out length))
                {
                    // I'm just being lazy and re-using something "close enough" here
                    // note that v2 has a big-endian option, but Fixed32 assumes little-endian - we
                    // actually need the other way around (network byte order):
                    length = IntLittleEndianToBigEndian((uint)length);

                    BlockHeader header;
                    // again, v2 has capped-streams built in, but I'm deliberately
                    // limiting myself to v1 features
                    using (var tmp = new LimitedStream(file, length))
                    {
                        header = Serializer.Deserialize<BlockHeader>(tmp);
                    }
                    Blob blob;
                    using (var tmp = new LimitedStream(file, header.datasize))
                    {
                        blob = Serializer.Deserialize<Blob>(tmp);
                    }
                    if (blob.zlib_data == null) throw new NotSupportedException("I'm only handling zlib here!");

                    HeaderBlock headerBlock;
                    PrimitiveBlock primitiveBlock;

                    using (var ms = new MemoryStream(blob.zlib_data))
                    using (var zlib = new ZLibStream(ms))
                    {
                        if (header.type == "OSMHeader")
                            headerBlock = Serializer.Deserialize<HeaderBlock>(zlib);

                        if (header.type == "OSMData")
                            primitiveBlock = Serializer.Deserialize<PrimitiveBlock>(zlib);
                    }
                    blockCount++;
                    Trace.WriteLine("Read block " + blockCount.ToString());


                }
                Trace.WriteLine("all done");
            }
        }

        // 4-byte number
        static int IntLittleEndianToBigEndian(uint i)
        {
            return (int)(((i & 0xff) << 24) + ((i & 0xff00) << 8) + ((i & 0xff0000) >> 8) + ((i >> 24) & 0xff));
        }
    }

    abstract class InputStream : Stream
    {
        protected abstract int ReadNextBlock(byte[] buffer, int offset, int count);
        public sealed override int Read(byte[] buffer, int offset, int count)
        {
            int bytesRead, totalRead = 0;
            while (count > 0 && (bytesRead = ReadNextBlock(buffer, offset, count)) > 0)
            {
                count -= bytesRead;
                offset += bytesRead;
                totalRead += bytesRead;
                pos += bytesRead;
            }
            return totalRead;
        }
        long pos;
        public override void Write(byte[] buffer, int offset, int count)
        {
            throw new NotImplementedException();
        }
        public override void SetLength(long value)
        {
            throw new NotImplementedException();
        }
        public override long Position
        {
            get
            {
                return pos;
            }
            set
            {
                if (pos != value) throw new NotImplementedException();
            }
        }
        public override long Length
        {
            get { throw new NotImplementedException(); }
        }
        public override void Flush()
        {
            throw new NotImplementedException();
        }
        public override bool CanWrite
        {
            get { return false; }
        }
        public override bool CanRead
        {
            get { return true; }
        }
        public override bool CanSeek
        {
            get { return false; }
        }
        public override long Seek(long offset, SeekOrigin origin)
        {
            throw new NotImplementedException();
        }
    }
    class ZLibStream : InputStream
    {   // uses ZLIB.NET: http://www.componentace.com/download/download.php?editionid=25
        private ZInputStream reader; // seriously, why isn't this a stream?
        public ZLibStream(Stream stream)
        {
            reader = new ZInputStream(stream);
        }
        public override void Close()
        {
            reader.Close();
            base.Close();
        }
        protected override int ReadNextBlock(byte[] buffer, int offset, int count)
        {
            // OMG! reader.Read is the base-stream, reader.read is decompressed! yeuch
            return reader.read(buffer, offset, count);
        }

    }
    // deliberately doesn't dispose the base-stream    
    class LimitedStream : InputStream
    {
        private Stream stream;
        private long remaining;
        public LimitedStream(Stream stream, long length)
        {
            if (length < 0) throw new ArgumentOutOfRangeException("length");
            if (stream == null) throw new ArgumentNullException("stream");
            if (!stream.CanRead) throw new ArgumentException("stream");
            this.stream = stream;
            this.remaining = length;
        }
        protected override int ReadNextBlock(byte[] buffer, int offset, int count)
        {
            if (count > remaining) count = (int)remaining;
            int bytesRead = stream.Read(buffer, offset, count);
            if (bytesRead > 0) remaining -= bytesRead;
            return bytesRead;
        }
    }
}

答案 2 :(得分:1)

是的,它来自Fileformat.cs中的protogen(基于OSM Fileformat.proto文件..代码如下。)

package OSM_PROTO;
  message Blob {
    optional bytes raw = 1;
    optional int32 raw_size = 2; 
    optional bytes zlib_data = 3;
    optional bytes lzma_data = 4;
    optional bytes bzip2_data = 5;
  }

  message BlockHeader {
    required string type = 1;
    optional bytes indexdata = 2;
    required int32 datasize = 3;
  }

以下是生成文件中BlockHeader的声明:

public sealed partial class BlockHeader : pb::GeneratedMessage<BlockHeader, BlockHeader.Builder> {...}

- &GT;使用pb = global :: Google.ProtocolBuffers;

(ProtocolBuffers.dll)附带此软件包:

http://code.google.com/p/protobuf-csharp-port/downloads/detail?name=protobuf-csharp-port-2.4.1.473-full-binaries.zip&can=2&q=

答案 3 :(得分:0)

您是否尝试过更小的区域?例如us-pacific.osm.pbf

最终发布错误消息会很有用。