let $raw-values :=
for $book in collection("abc")/(gbook|set)[@type='oeb']
return
element { "book" }
{
for $value in distinct-values($book//node()/@class)
return element { "class" } { $value }
}
for $item in distinct-values($raw-values//class)
order by $item
return element { "uniques" } { $item }
xquery version "1.0-ml";
import module namespace search = "http://marklogic.com/appservices/search"
at "/MarkLogic/appservices/search/search.xqy";
declare namespace my="http://www.my-web-site.com/xquery";
declare variable $options-title :=
<options xmlns="http://marklogic.com/appservices/search">
<searchable-expression>
collection("abc123")//(div)
</searchable-expression>
<transform-results apply="snippet">
<per-match-tokens>30</per-match-tokens>
<max-matches>1</max-matches>
<max-snippet-chars>200</max-snippet-chars>
<preferred-elements/>
</transform-results>
</options>;
declare function my:do-search()
{
search:search("food", $options-title, (), 25)
};
my:do-search()
C:\Program Files\Saxon.NET>bin\Transform SaxonTest.xml SaxonTest.xsl
// Create a Processor instance.
Processor p = new Processor();
// Load the source document.
XdmNode node = p.NewDocumentBuilder().Build(new Uri(file));
// Create a transformer for the stylesheet.
XsltTransformer transformer = p.NewXsltCompiler().Compile(myStream).Load();
// Set the root node of the source document to be the initial context node.
transformer.InitialContextNode = node;
// BaseOutputUri is only necessary for xsl:result-document.
transformer.BaseOutputUri = new Uri(file);
// Create a serializer.
Serializer serializer = new Serializer();
transformer.Run(serializer);
<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet
version="2.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:fo="http://www.w3.org/1999/XSL/Format"
xmlns:xs="http://www.w3.org/2001/XMLSchema"
xmlns:fn="http://www.w3.org/2005/xpath-functions"
exclude-result-prefixes="fo xs fn">
<xsl:output method="xml" indent="yes" encoding="UTF-8" name="xmlFormat"/>
<xsl:template match="text()" />
<xsl:template match="/">
<xsl:for-each select="//node()[@fragment='true']">
<xsl:variable name="filename" select="concat( /gpg-book/@local-id, '/', @local-id, '.xml' )"/>
<xsl:result-document href="{$filename}" format="xmlFormat">
<pcu-gpg-book>
<xsl:copy-of select="/gpg-book/taxonomy_pcu"/>
<xsl:copy-of select="/gpg-book/content-metadata"/>
<xsl:copy-of select="/gpg-book/print-pub-metadata"/>
<xsl:copy-of select="parent::node()"/>
</pcu-gpg-book>
</xsl:result-document>
</xsl:for-each>
</xsl:template>
</xsl:stylesheet>
SELECT entryid, Count(entryid) AS ecount
FROM filelocation
GROUP BY entryid
HAVING (Count(entryid) > 1) -- This runs after the aggregate count() function
<Subject>Value 1|Value 2</Subject>I wanted two things out of that series of elements: unique strings and the value before the |. As I type this, I realize there may be a bit of a bug here, but I'll have to test it out. Here's what I did for the series of subject elements. Can you spot the bug? ;-)
<Subject>Value 1|Value 2</Subject>
<Subject>Value 1|Value 2</Subject>
<Time>Time Value 1</Time>
<Time>Time Value 1</Time>
<Time>Time Value 1</Time>
<Subject>Value 3|Value 4</Subject>
<Subject>Value 3|Value 4</Subject>
<Subject>Value 3|Value 4</Subject>
<Time>Time Value 2</Time>
<Time>Time Value 2</Time>
<Time>Time Value 2</Time>
<xsl:variable name="subjects" select="/fragment/index-only-subjects//Subject[not(text()=preceding-sibling::Subject/text())]/text()"/>I'm pretty sure there's a way to do this with xsl:keys / key(), but I got this solution working first.
<xsl:for-each select="$subjects">
<xsl:sort select="." data-type="text"/>
<subject>
<xsl:choose>
<xsl:when test="contains(.,'|')">
<xsl:value-of select="substring-before(.,'|')"/>
</xsl:when>
<xsl:otherwise>
<xsl:value-of select="."/>
</xsl:otherwise>
</xsl:choose>
</subject>
</xsl:for-each>
bodyalign:center / margin: 0 auto are for IE/FF.
{
text-align: center;
align: center;
}
#container
{
text-align: left;
margin: 0 auto;
}
CREATE PROCEDURE p_RecreateFT_Articles
AS
ALTER TABLE [dbo].[Articles] WITH NOCHECK ADD
CONSTRAINT [PK_Articles] PRIMARY KEY CLUSTERED
(
[Article_ID]
) ON [PRIMARY]
IF EXISTS (SELECT * FROM dbo.sysfulltextcatalogs WHERE NAME = 'FT_Articles')
EXEC sp_fulltext_catalog 'FT_Articles', 'drop'
-- Create the catalog if it doesn't already exist.
IF NOT EXISTS (SELECT * FROM dbo.sysfulltextcatalogs WHERE NAME = 'FT_Articles')
EXEC sp_fulltext_catalog 'FT_Articles', 'create'
-- Add the full text index to the table
EXEC sp_fulltext_table '[dbo].[Articles]', 'create', 'FT_Articles', 'PK_Articles'
-- Add the columns to the full text index
EXEC sp_fulltext_column '[dbo].[Articles]', 'ArticleTitle', 'add'
EXEC sp_fulltext_column '[dbo].[Articles]', 'ArticleBody', 'add'
-- Activate the index
EXEC sp_fulltext_table '[dbo].[Articles]', 'activate'
-- Start population
EXEC sp_fulltext_catalog 'FT_Articles', 'start_full'
GO
INSERT INTO ProductSubjects (ID, ProductID, SubjectID)
SELECT NEWID(), '52EB01B6-B768-4F9B-8F60-1A695A13D945', Subjects.ID
FROM Subjects
SELECT
ID,
CASE
WHEN Subject2 IS NULL THEN
Subject1
WHEN Subject2 IS NOT NULL AND Subject3 IS NULL THEN
Subject1 + ' : ' + Subject2
ELSE Subject1 + ' : ' + Subject2 + ' : ' + Subject3
END AS TheSubject
FROM Subjects
ORDER BY TheSubject
<html>
<head>
<title>Highlight</title>
<style type="text/css">
.highlight { background-color:#ffff00; }
</style>
</head>
<body>
<div id="div1">Row one <a href="javascript:changeHighlight('div1');">HIGHLIGHT</a></div>
<div id="div2">Row two <a href="javascript:changeHighlight('div2');">HIGHLIGHT</a></div>
<div id="div3">Row three <a href="javascript:changeHighlight('div3');">HIGHLIGHT</a></div>
<input type="hidden" id="currentDiv" />
<script language="javascript" type="text/javascript">
function changeHighlight(myElement)
{
document.getElementById(myElement).className = 'highlight';
var lastHighlight = document.getElementById('currentDiv').value;
if(lastHighlight != '')
{
document.getElementById(lastHighlight).className = '';
}
document.getElementById("currentDiv").value = myElement;
}
</script>
</body>
</html>
...
using org.pdfbox.pdmodel;
using org.pdfbox.util;
using System.IO;
...
static void Main(string[] args)
{
// All the error catching is left for you to do.
string[] files = {
@"C:\9780791093757.pdf",
@"C:\9780791095850.pdf",
@"C:\9780816048526.pdf"
};
bool UseIndividualPages = false;
foreach (string s in files)
{
string textFileDocument = Path.GetDirectoryName(s) + Path.DirectorySeparatorChar +
Path.GetFileNameWithoutExtension(s) + ".txt";
PDDocument pdfDocument = PDDocument.load(s);
PDFTextStripper pdfStripper = new PDFTextStripper();
pdfStripper.setPageSeparator(Environment.NewLine + Environment.NewLine);
if (UseIndividualPages) // Extracts one file per page in the PDF
{
for (int i = 1; i <= pdfDocument.getNumberOfPages(); i++)
// getNumberOfPages() is 1-based.
{
pdfStripper.setStartPage(i);
pdfStripper.setEndPage(i);
string textFilePage = Path.GetDirectoryName(s) + Path.DirectorySeparatorChar +
Path.GetFileNameWithoutExtension(s) + " " + i.ToString() + ".txt";
ExtractText(pdfStripper, pdfDocument, textFilePage);
}
}
else // Extracts one file for the entire PDF
{
ExtractText(pdfStripper, pdfDocument, textFileDocument);
}
pdfDocument.close();
}
Console.ReadLine();
}
static void ExtractText(PDFTextStripper textStripper, PDDocument document,
string outputFile)
{
if (File.Exists(outputFile)) File.Delete(outputFile);
using (StreamWriter sw = new StreamWriter(outputFile))
{
sw.Write(textStripper.getText(document));
Console.WriteLine(outputFile);
}
}
Here are some comments on when you can connect at various stations:
