XSLT 按触发值分组

Question

我想按触发器或标志值对 XML 进行分组。我只能使用 XSLT 1.0。原文XML：

<?xml version = "1.0" encoding = "utf-8"?>
<root>
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_2_1.tif"/>
        <field   level = "document" name = "groupId" value = "1"/>
        <field   level = "document" name = "scanDokumentPos" value = "1 "/>
    </image> 
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_2_2.tif"/>
        <field   level = "document" name = "groupId" value = "0"/>
        <field   level = "document" name = "scanDokumentPos" value = "1 "/>
    </image> 
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_2_3.tif"/>
        <field   level = "document" name = "groupId" value = "0"/>
        <field   level = "document" name = "scanDokumentPos" value = "1 "/>
    </image> 
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_3_1.tif"/>
        <field   level = "document" name = "groupId" value = "0"/>
        <field   level = "document" name = "scanDokumentPos" value = "2 "/>
    </image> 
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_3_2.tif"/>
        <field   level = "document" name = "groupId" value = "0"/>
        <field   level = "document" name = "scanDokumentPos" value = "2 "/>
    </image> 
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_7_1.tif"/>
        <field   level = "document" name = "groupId" value = "1"/>
        <field   level = "document" name = "scanDokumentPos" value = "6 "/>
    </image> 
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_7_2.tif"/>
        <field   level = "document" name = "groupId" value = "0"/>
        <field   level = "document" name = "scanDokumentPos" value = "6 "/>
    </image> 
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_8_1.tif"/>
        <field   level = "document" name = "groupId" value = "0"/>
        <field   level = "document" name = "scanDokumentPos" value = "7 "/>
    </image> 
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_8_2.tif"/>
        <field   level = "document" name = "groupId" value = "0"/>
        <field   level = "document" name = "scanDokumentPos" value = "7 "/>
    </image>
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_9_1.tif"/>
        <field   level = "document" name = "groupId" value = "1"/>
        <field   level = "document" name = "scanDokumentPos" value = "8 "/>
    </image> 
    <image> 
        <field   level = "system" name = "Image Filename" value = "Batch121_10_1.tif"/>
        <field   level = "document" name = "groupId" value = "1"/>
        <field   level = "document" name = "scanDokumentPos" value = "9 "/>
    </image> 
</root>

结果应该是：

<document>
    <childdocuments>
        <document GroupID=""> <!-- grouped because of groupId=1 -->
            <childdocuments>
                <document GroupID="1"> <!-- scanDokumentPos --> <!-- grouped because of groupId=0 and scanDokumentPos=1 -->
                    <pages> 
                        <page path="Batch121_2_1.tif"> <!-- Image Filename -->
                        <page path="Batch121_2_2.tif"> <!-- Image Filename -->
                        <page path="Batch121_2_3.tif"> <!-- Image Filename -->
                    </page>
                </document>
                <document GroupID="2"> <!-- scanDokumentPos --> <!-- grouped because of groupId=0 and scanDokumentPos=2 -->
                    <pages> 
                        <page path="Batch121_3_1.tif"> <!-- Image Filename -->
                        <page path="Batch121_3_2.tif"> <!-- Image Filename -->
                    </page>
                </document>             
            </childdocuments>
        </document>
        <document GroupID=""> <!-- start new document because of groupId=1 -->
            <childdocuments>
                <document GroupID="6"> <!-- scanDokumentPos --> <!-- grouped because of groupId=0 and scanDokumentPos=6 -->
                    <pages> 
                        <page path="Batch121_7_1.tif"> <!-- Image Filename -->
                        <page path="Batch121_7_2.tif"> <!-- Image Filename -->
                    </page>
                </document>
                <document GroupID="7"> <!-- scanDokumentPos --> <!-- grouped because of groupId=0 and scanDokumentPos=7 -->
                    <pages> 
                        <page path="Batch121_8_1.tif"> <!-- Image Filename -->
                        <page path="Batch121_8_2.tif"> <!-- Image Filename -->
                    </page>
                </document>     
            </childdocuments>
        </document>     
        <document GroupID=""> <!-- start new document because of groupId=1 -->
            <childdocuments>
                <document GroupID="8"> <!-- scanDokumentPos --> <!-- grouped because of groupId=0 and scanDokumentPos=8 -->
                    <pages> 
                        <page path="Batch121_9_1.tif"> <!-- Image Filename -->
                    </page>
                </document>     
            </childdocuments>
        </document>     
        <document GroupID=""> <!-- start new document because of groupId=1 -->
            <childdocuments>
                <document GroupID="9"> <!-- scanDokumentPos --> <!-- grouped because of groupId=0 and scanDokumentPos=9 -->
                    <pages> 
                        <page path="Batch121_10_1.tif"> <!-- Image Filename -->
                    </page>
                </document>     
            </childdocuments>
        </document>     
    </childdocuments>
</document>

第一个分组键是groupId。如果 1 在级别 1 上开始新文档。那么 groupId=1 之后直到下一个 groupId=1 或文件末尾的所有元素都属于一个组。第二个分组键是 scanDokumentPos。将所有页面分组为一个具有相同 scanDokumentPos 的文档。

测试：http://xsltransform.net/3N7GxDx/3

Answer 1

如评论中所述，XSLT 1.0 中的分组最好使用 Muenchian Grouping 完成。

给出的示例 () 是一个很好的示例，但与您的问题不同的是，您的第一个分组更像是“group-starting-with”，而不仅仅是按值进行分组。

我要做的是创建 2 个密钥。

第一个选择 image 个 groupId 不为“1”的元素，该元素基于第一个 groupId 为“1”的前一个兄弟生成的 id。

第二个根据生成的 ID（见上文）和“scanDokumentPos”值的组合选择 image groupId 不为“1”的元素。

这是一个例子。我没有处理 image 元素的处理。我只显示分组。图像元素的处理应该是微不足道的。

<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
  <xsl:output indent="yes"/>
  <xsl:strip-space elements="*"/>
  
  <xsl:key name="doc_group" match="image[not(field[@name='groupId']/@value='1')]" 
    use="generate-id(preceding-sibling::image[field[@name='groupId']/@value='1'][1])"/>
  
  <xsl:key name="doc_pos_group" match="image[not(field[@name='groupId']/@value='1')]" 
    use="concat(generate-id(preceding-sibling::image[field[@name='groupId']/@value='1'][1]),'|',
    field[@name='scanDokumentPos']/@value)"/>
  
  <xsl:template match="@*|node()">
    <xsl:copy>
      <xsl:apply-templates select="@*|node()"/>
    </xsl:copy>
  </xsl:template>
  
  <xsl:template match="/*">
    <document>
      <childdocuments>
        <xsl:for-each select="image[field[@name='groupId']/@value='1']">
          <xsl:variable name="curr_image" select="."/>
          <xsl:variable name="curr_id" select="generate-id()"/>
          <document GroupID="">
            <childdocuments>
              <xsl:if test="1 >= count(key('doc_group',$curr_id))">
                <document GroupID="{normalize-space(field[@name='scanDokumentPos']/@value)}">
                  <pages>
                    <xsl:apply-templates select="$curr_image"/>
                  </pages>
                </document>
              </xsl:if>
              <xsl:for-each select="key('doc_group',$curr_id)[count(.|key('doc_pos_group', 
                concat($curr_id,'|',field[@name='scanDokumentPos']/@value))[1])=1]">
                <xsl:variable name="doc_pos" select="field[@name='scanDokumentPos']/@value"/>
                <document GroupID="{normalize-space($doc_pos)}">
                  <pages>
                    <xsl:apply-templates 
                      select="$curr_image[field[@name='scanDokumentPos']/@value=$doc_pos]|
                      key('doc_pos_group',concat($curr_id,'|',$doc_pos))"/>
                  </pages>
                </document>
              </xsl:for-each>
            </childdocuments>
          </document>
        </xsl:for-each>
      </childdocuments>
    </document>
  </xsl:template>
  
</xsl:stylesheet>

Fiddle: http://xsltfiddle.liberty-development.net/a9HjZV/4

XSLT 按触发值分组

XSLT grouping by a trigger value

xml

xslt

xpath

xslt-grouping