我听说过Lucene.Net我听说过Apache Tika .问题是 - 我如何使用 C# vs Java 索引这些文档？我认为问题在于没有与 Tika 等效的 .Net 从这些文档类型中提取相关文本。
更新 - 2011 年 2 月 5 日
根据给定的回复，目前似乎不是 原生 .Net 相当于 Tika。提到了 2 个有趣的项目，每个项目本身都很有趣:
鉴于上述 2 个项目，我看到了几个选项。要提取文本，我可以 a) 使用 Omega 使用的相同组件，或者 b) 使用 IKVM 运行 Tika。对我来说，选项 b) 似乎更干净，因为只有 2 个依赖项。
有趣的是，现在有几个搜索引擎可能可以从 .Net 中使用。有 Xapian、Lucene.Net 甚至 Lucene(使用 IKVM)。
更新 - 2011 年 2 月 7 日
另一个答案是建议我检查 ifilters。事实证明，这是 MS 用于 Windows 搜索的，因此 Office ifilter 很容易获得。此外，还有一些 PDF ifilter。缺点是它们是在非托管代码中实现的，因此需要 COM 互操作才能使用它们。我在 DotLucene.NET 存档中找到了以下代码片段(不再是事件项目):
using System;
using System.Diagnostics;
using System.Runtime.InteropServices;
using System.Text;
namespace IFilter
{
[Flags]
public enum IFILTER_INIT : uint
{
NONE = 0,
CANON_PARAGRAPHS = 1,
HARD_LINE_BREAKS = 2,
CANON_HYPHENS = 4,
CANON_SPACES = 8,
APPLY_INDEX_ATTRIBUTES = 16,
APPLY_CRAWL_ATTRIBUTES = 256,
APPLY_OTHER_ATTRIBUTES = 32,
INDEXING_ONLY = 64,
SEARCH_LINKS = 128,
FILTER_OWNED_VALUE_OK = 512
}
public enum CHUNK_BREAKTYPE
{
CHUNK_NO_BREAK = 0,
CHUNK_EOW = 1,
CHUNK_EOS = 2,
CHUNK_EOP = 3,
CHUNK_EOC = 4
}
[Flags]
public enum CHUNKSTATE
{
CHUNK_TEXT = 0x1,
CHUNK_VALUE = 0x2,
CHUNK_FILTER_OWNED_VALUE = 0x4
}
[StructLayout(LayoutKind.Sequential)]
public struct PROPSPEC
{
public uint ulKind;
public uint propid;
public IntPtr lpwstr;
}
[StructLayout(LayoutKind.Sequential)]
public struct FULLPROPSPEC
{
public Guid guidPropSet;
public PROPSPEC psProperty;
}
[StructLayout(LayoutKind.Sequential)]
public struct STAT_CHUNK
{
public uint idChunk;
[MarshalAs(UnmanagedType.U4)] public CHUNK_BREAKTYPE breakType;
[MarshalAs(UnmanagedType.U4)] public CHUNKSTATE flags;
public uint locale;
[MarshalAs(UnmanagedType.Struct)] public FULLPROPSPEC attribute;
public uint idChunkSource;
public uint cwcStartSource;
public uint cwcLenSource;
}
[StructLayout(LayoutKind.Sequential)]
public struct FILTERREGION
{
public uint idChunk;
public uint cwcStart;
public uint cwcExtent;
}
[ComImport]
[Guid("89BCB740-6119-101A-BCB7-00DD010655AF")]
[InterfaceType(ComInterfaceType.InterfaceIsIUnknown)]
public interface IFilter
{
[PreserveSig]
int Init([MarshalAs(UnmanagedType.U4)] IFILTER_INIT grfFlags, uint cAttributes, [MarshalAs(UnmanagedType.LPArray, SizeParamIndex=1)] FULLPROPSPEC[] aAttributes, ref uint pdwFlags);
[PreserveSig]
int GetChunk(out STAT_CHUNK pStat);
[PreserveSig]
int GetText(ref uint pcwcBuffer, [MarshalAs(UnmanagedType.LPWStr)] StringBuilder buffer);
void GetValue(ref UIntPtr ppPropValue);
void BindRegion([MarshalAs(UnmanagedType.Struct)] FILTERREGION origPos, ref Guid riid, ref UIntPtr ppunk);
}
[ComImport]
[Guid("f07f3920-7b8c-11cf-9be8-00aa004b9986")]
public class CFilter
{
}
public class IFilterConstants
{
public const uint PID_STG_DIRECTORY = 0x00000002;
public const uint PID_STG_CLASSID = 0x00000003;
public const uint PID_STG_STORAGETYPE = 0x00000004;
public const uint PID_STG_VOLUME_ID = 0x00000005;
public const uint PID_STG_PARENT_WORKID = 0x00000006;
public const uint PID_STG_SECONDARYSTORE = 0x00000007;
public const uint PID_STG_FILEINDEX = 0x00000008;
public const uint PID_STG_LASTCHANGEUSN = 0x00000009;
public const uint PID_STG_NAME = 0x0000000a;
public const uint PID_STG_PATH = 0x0000000b;
public const uint PID_STG_SIZE = 0x0000000c;
public const uint PID_STG_ATTRIBUTES = 0x0000000d;
public const uint PID_STG_WRITETIME = 0x0000000e;
public const uint PID_STG_CREATETIME = 0x0000000f;
public const uint PID_STG_ACCESSTIME = 0x00000010;
public const uint PID_STG_CHANGETIME = 0x00000011;
public const uint PID_STG_CONTENTS = 0x00000013;
public const uint PID_STG_SHORTNAME = 0x00000014;
public const int FILTER_E_END_OF_CHUNKS = (unchecked((int) 0x80041700));
public const int FILTER_E_NO_MORE_TEXT = (unchecked((int) 0x80041701));
public const int FILTER_E_NO_MORE_VALUES = (unchecked((int) 0x80041702));
public const int FILTER_E_NO_TEXT = (unchecked((int) 0x80041705));
public const int FILTER_E_NO_VALUES = (unchecked((int) 0x80041706));
public const int FILTER_S_LAST_TEXT = (unchecked((int) 0x00041709));
}
///
/// IFilter return codes
///
public enum IFilterReturnCodes : uint
{
///
/// Success
///
S_OK = 0,
///
/// The function was denied access to the filter file.
///
E_ACCESSDENIED = 0x80070005,
///
/// The function encountered an invalid handle, probably due to a low-memory situation.
///
E_HANDLE = 0x80070006,
///
/// The function received an invalid parameter.
///
E_INVALIDARG = 0x80070057,
///
/// Out of memory
///
E_OUTOFMEMORY = 0x8007000E,
///
/// Not implemented
///
E_NOTIMPL = 0x80004001,
///
/// Unknown error
///
E_FAIL = 0x80000008,
///
/// File not filtered due to password protection
///
FILTER_E_PASSWORD = 0x8004170B,
///
/// The document format is not recognised by the filter
///
FILTER_E_UNKNOWNFORMAT = 0x8004170C,
///
/// No text in current chunk
///
FILTER_E_NO_TEXT = 0x80041705,
///
/// No more chunks of text available in object
///
FILTER_E_END_OF_CHUNKS = 0x80041700,
///
/// No more text available in chunk
///
FILTER_E_NO_MORE_TEXT = 0x80041701,
///
/// No more property values available in chunk
///
FILTER_E_NO_MORE_VALUES = 0x80041702,
///
/// Unable to access object
///
FILTER_E_ACCESS = 0x80041703,
///
/// Moniker doesn't cover entire region
///
FILTER_W_MONIKER_CLIPPED = 0x00041704,
///
/// Unable to bind IFilter for embedded object
///
FILTER_E_EMBEDDING_UNAVAILABLE = 0x80041707,
///
/// Unable to bind IFilter for linked object
///
FILTER_E_LINK_UNAVAILABLE = 0x80041708,
///
/// This is the last text in the current chunk
///
FILTER_S_LAST_TEXT = 0x00041709,
///
/// This is the last value in the current chunk
///
FILTER_S_LAST_VALUES = 0x0004170A
}
///
/// Convenience class which provides static methods to extract text from files using installed IFilters
///
public class DefaultParser
{
public DefaultParser()
{
}
[DllImport("query.dll", CharSet = CharSet.Unicode)]
private extern static int LoadIFilter(string pwcsPath, [MarshalAs(UnmanagedType.IUnknown)] object pUnkOuter, ref IFilter ppIUnk);
private static IFilter loadIFilter(string filename)
{
object outer = null;
IFilter filter = null;
// Try to load the corresponding IFilter
int resultLoad = LoadIFilter(filename, outer, ref filter);
if (resultLoad != (int) IFilterReturnCodes.S_OK)
{
return null;
}
return filter;
}
public static bool IsParseable(string filename)
{
return loadIFilter(filename) != null;
}
public static string Extract(string path)
{
StringBuilder sb = new StringBuilder();
IFilter filter = null;
try
{
filter = loadIFilter(path);
if (filter == null)
return String.Empty;
uint i = 0;
STAT_CHUNK ps = new STAT_CHUNK();
IFILTER_INIT iflags =
IFILTER_INIT.CANON_HYPHENS |
IFILTER_INIT.CANON_PARAGRAPHS |
IFILTER_INIT.CANON_SPACES |
IFILTER_INIT.APPLY_CRAWL_ATTRIBUTES |
IFILTER_INIT.APPLY_INDEX_ATTRIBUTES |
IFILTER_INIT.APPLY_OTHER_ATTRIBUTES |
IFILTER_INIT.HARD_LINE_BREAKS |
IFILTER_INIT.SEARCH_LINKS |
IFILTER_INIT.FILTER_OWNED_VALUE_OK;
if (filter.Init(iflags, 0, null, ref i) != (int) IFilterReturnCodes.S_OK)
throw new Exception("Problem initializing an IFilter for:\n" + path + " \n\n");
while (filter.GetChunk(out ps) == (int) (IFilterReturnCodes.S_OK))
{
if (ps.flags == CHUNKSTATE.CHUNK_TEXT)
{
IFilterReturnCodes scode = 0;
while (scode == IFilterReturnCodes.S_OK || scode == IFilterReturnCodes.FILTER_S_LAST_TEXT)
{
uint pcwcBuffer = 65536;
System.Text.StringBuilder sbBuffer = new System.Text.StringBuilder((int)pcwcBuffer);
scode = (IFilterReturnCodes) filter.GetText(ref pcwcBuffer, sbBuffer);
if (pcwcBuffer > 0 && sbBuffer.Length > 0)
{
if (sbBuffer.Length < pcwcBuffer) // Should never happen, but it happens !
pcwcBuffer = (uint)sbBuffer.Length;
sb.Append(sbBuffer.ToString(0, (int) pcwcBuffer));
sb.Append(" "); // "\r\n"
}
}
}
}
}
finally
{
if (filter != null) {
Marshal.ReleaseComObject (filter);
System.GC.Collect();
System.GC.WaitForPendingFinalizers();
}
}
return sb.ToString();
}
}
}
目前，这似乎是在 Windows 服务器上使用 .NET 平台从文档中提取文本的最佳方式。谢谢大家的帮助。
更新 - 2011 年 3 月 8 日
虽然我仍然认为 ifilter 是一个不错的选择，但我认为如果您希望使用 .NET 中的 Lucene 来索引文档，一个很好的选择是使用 Solr .当我第一次开始研究这个主题时，我从未听说过 Solr。所以，对于那些还没有的人，Solr 是一个独立的搜索服务，在 Lucene 之上用 Java 编写。这个想法是您可以在防火墙机器上启动 Solr，并通过 HTTP 从您的 .NET 应用程序与其通信。 Solr 真的像服务一样编写，可以做 Lucene 可以做的所有事情，(包括使用 Tika 从 .PDF、.XLS、.DOC、.PPT 等中提取文本)等等。 Solr 似乎也有一个非常活跃的社区，关于 Lucene.NET，这是我不确定的一件事。
最佳答案
您还可以查看 ifilters - 如果您搜索 asp.net ifilters，则有许多资源:
当然，如果您将其分发到客户端系统会增加麻烦，因为您需要在您的分发中包含 ifilter 并将它们与您的应用程序一起安装在他们的机器上，或者他们将无法从任何文件中提取文本他们没有 ifilters 。
关于.net - 使用 Lucene.NET 索引 .PDF、.XLS、.DOC、.PPT，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/4905271/