ifilter - 用于 docx 解析器错误的 word ifilter

Question

.Docx 文档似乎没有被索引。

我在 .docx 中使用了唯一的字符串，但当我搜索“one”时，未返回 .docx。

例如，以下文本:

“这是第一行的文本，这是第二行的文本。”

将通过 iFilter 提取为:

“这是第一行的文本，这是第二行的文本。”

因此，当 Ifilter 解析 .docx 时，他会删除换行符分隔符并尝试解析“oneand here”... .

看来 .docx 的 Word ifilter 将一行的最后一个单词与下一行的第一个单词连接起来。

任何人都可以提供一些如何解决此问题的想法吗？

提前致谢。

Answer 1

好的，我现在明白了。基本上 64 位 IFilter 无法正常工作。它合并由换行符分隔的单词，并且不将它们贯穿。我用过Ionic.zip使用 DocxToText 的稍微修改版本来访问 docx zip 存档并解析重要的 xml 文件。现在效果很好。

这是最初由 Jevgenij Pankov 创建的修改后的代码

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using Ionic.Zip;
using System.IO;
using System.Xml;

public class DocxToText
{
    private const string ContentTypeNamespace =
        @"http://schemas.openxmlformats.org/package/2006/content-types";

    private const string WordprocessingMlNamespace =
        @"http://schemas.openxmlformats.org/wordprocessingml/2006/main";

    private const string DocumentXmlXPath =
        "/t:Types/t:Override[@ContentType=\"" +
        "application/vnd.openxmlformats-officedocument." +
        "wordprocessingml.document.main+xml\"]";

    private const string BodyXPath = "/w:document/w:body";

    private string docxFile = "";
    private string docxFileLocation = "";

    public DocxToText(string fileName)
    {
        docxFile = fileName;
    }

    #region ExtractText()
    /// 

    /// Extracts text from the Docx file.

    /// 

    /// Extracted text.

    public string ExtractText()
    {
        if (string.IsNullOrEmpty(docxFile))
            throw new Exception("Input file not specified.");

        // Usually it is "/word/document.xml"


        docxFileLocation = FindDocumentXmlLocation();

        if (string.IsNullOrEmpty(docxFileLocation))
            throw new Exception("It is not a valid Docx file.");

        return ReadDocumentXml();
    }
    #endregion

    #region FindDocumentXmlLocation()
    /// 

    /// Gets location of the "document.xml" zip entry.

    /// 

    /// Location of the "document.xml".

    private string FindDocumentXmlLocation()
    {
        using (ZipFile zip = new ZipFile(docxFile))
        {
            foreach (ZipEntry entry in zip)
            {
                // Find "[Content_Types].xml" zip entry
                if (string.Compare(entry.FileName, "[Content_Types].xml", true) == 0)
                {
                    XmlDocument xmlDoc = new XmlDocument();
                    using (var stream = new MemoryStream())
                    {

                        entry.Extract(stream);
                        stream.Position = 0;

                        xmlDoc.PreserveWhitespace = true;
                        xmlDoc.Load(stream);
                    }

                    //Create an XmlNamespaceManager for resolving namespaces


                    XmlNamespaceManager nsmgr =
                        new XmlNamespaceManager(xmlDoc.NameTable);
                    nsmgr.AddNamespace("t", ContentTypeNamespace);

                    // Find location of "document.xml"


                    XmlNode node = xmlDoc.DocumentElement.SelectSingleNode(
                        DocumentXmlXPath, nsmgr);

                    if (node != null)
                    {
                        string location =
                            ((XmlElement)node).GetAttribute("PartName");
                        return location.TrimStart(new char[] { '/' });
                    }
                    break;
                }
            }
        }
        return null;
    }
    #endregion

    #region ReadDocumentXml()
    /// 

    /// Reads "document.xml" zip entry.

    /// 

    /// Text containing in the document.

    private string ReadDocumentXml()
    {
        StringBuilder sb = new StringBuilder();

        using (ZipFile zip = new ZipFile(docxFile))
        {
            foreach (ZipEntry entry in zip)
            {
                if (string.Compare(entry.FileName, docxFileLocation, true) == 0)
                {
                    XmlDocument xmlDoc = new XmlDocument();
                    using (var stream = new MemoryStream())
                    {

                        entry.Extract(stream);
                        stream.Position = 0;

                        xmlDoc.PreserveWhitespace = true;
                        xmlDoc.Load(stream);
                    }

                    XmlNamespaceManager nsmgr =
                        new XmlNamespaceManager(xmlDoc.NameTable);
                    nsmgr.AddNamespace("w", WordprocessingMlNamespace);

                    XmlNode node =
                        xmlDoc.DocumentElement.SelectSingleNode(BodyXPath, nsmgr);

                    if (node == null)
                        return string.Empty;

                    sb.Append(ReadNode(node));

                    break;
                }
            }
        }
        return sb.ToString();
    }
    #endregion

    #region ReadNode()
    /// 

    /// Reads content of the node and its nested childs.

    /// 

    /// XmlNode.

    /// Text containing in the node.

    private string ReadNode(XmlNode node)
    {
        if (node == null || node.NodeType != XmlNodeType.Element)
            return string.Empty;

        StringBuilder sb = new StringBuilder();
        foreach (XmlNode child in node.ChildNodes)
        {
            if (child.NodeType != XmlNodeType.Element) continue;

            switch (child.LocalName)
            {
                case "t": // Text

                    sb.Append(child.InnerText.TrimEnd());

                    string space =
                        ((XmlElement)child).GetAttribute("xml:space");
                    if (!string.IsNullOrEmpty(space) &&
                        space == "preserve")
                        sb.Append(' ');

                    break;

                case "cr":                          // Carriage return

                case "br":                          // Page break

                    sb.Append(Environment.NewLine);
                    break;

                case "tab":                         // Tab

                    sb.Append("\t");
                    break;

                case "p":                           // Paragraph

                    sb.Append(ReadNode(child));
                    sb.Append(Environment.NewLine);
                    sb.Append(Environment.NewLine);
                    break;

                default:
                    sb.Append(ReadNode(child));
                    break;
            }
        }
        return sb.ToString();
    }
    #endregion
}

这是这段代码的用法...

DocxToText dtt = new DocxToText(filepath);
string docxText = dtt.ExtractText();