peaeater

<#
  Split csv files with or without header rows, multiline columns with newlines ok.
#>

param (
  [string]$in,
  [string]$outdir = [System.IO.Path]::GetDirectoryName($in),
  [int]$count = 1000,
  [string]$delimiter = ',',
  [string[]]$header = @()

peaeater

    <fieldType name="text_suggest_edge" class="solr.TextField">
      <analyzer type="index">
        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
        <tokenizer class="solr.KeywordTokenizerFactory"/>
        <filter class="solr.LowerCaseFilterFactory"/>
        <filter class="solr.PatternReplaceFilterFactory" pattern="([\.,;:-_])" replacement=" " replace="all"/>
        <filter class="solr.EdgeNGramFilterFactory" maxGramSize="30" minGramSize="1"/>
        <filter class="solr.PatternReplaceFilterFactory" pattern="([^\w\d\*æøåÆØÅ ])" replacement="" replace="all"/>
      </analyzer>
      <analyzer type="query">

peaeater

# Creates new self-signed certificate for testing purposes
new-selfsignedcertificate -dnsname "*.domain.local" -friendlyname "*.domain.local Development Certificate" -certstorelocation "cert:\LocalMachine\My" -notafter (get-date).AddYears(100)

peaeater

<#
    Downsample PDF and convert to gray if necessary.
    Requires Ghostscript (gswin64c).
#>

param (
    [string]$indir,
    [string]$outdir = $indir,
    [string]$gs = "gswin64c",
    [string]$dpi = "150"

peaeater

# convert pdf to png
# requires imagemagick w/ ghostscript

param (
    [Parameter(Mandatory=$true,ValueFromPipeline=$true,Position=0)]
    [ValidateScript({[System.IO.Path]::GetExtension($_) -eq ".pdf"})]
    [string]$in,
    [string]$magick = "C:\utils\imagemagick\ImageMagick-7.1.1-Q16-HDRI\magick.exe"
)

peaeater

# ocr tif/png to txt
# requires tesseract

Param(
    [string]$ext = "tif",
    [string]$indir = ".",
    [string]$outdir = $indir,
    [string]$tesseract = "C:\utils\tesseract\tesseract.exe"
)

peaeater

<#
  sqlps dependency
  If module sqlps does not exist, install from:
    Microsoft SQL Server 2016 Feature Pack (https://www.microsoft.com/en-us/download/details.aspx?id=52676)
    - SQLSysClrTypes.msi
    - SharedManagementObjects.msi
    - PowershellTools.msi
#>

param(

peaeater

<#
    Sync a directory to remote server in FTP mode

    Peter Tyrrell
#>


param(
    [Parameter(Mandatory = $false, Position = 0)]
    [string]$logsrc = "",

peaeater

<fieldType name="alphaNumericSort" class="solr.TextField" sortMissingLast="false" omitNorms="true">
  <analyzer>
    <!-- KeywordTokenizer does no actual tokenizing, so the entire
         input string is preserved as a single token
      -->
    <tokenizer class="solr.KeywordTokenizerFactory"/>
    <!-- The LowerCase TokenFilter does what you expect, which can be
         when you want your sorting to be case insensitive
      -->
    <filter class="solr.LowerCaseFilterFactory" />

peaeater

<#
    1. Leaf
    Given a text file of PDF filenames, extract content from PDFs recursively
    and create mirror directory structure for text file outputs.

    * Handles filenames with entry separators.
    * Ignores PDF older than its text file mirror unless -force param is used.
    * Requires poppler pdftotext.exe

    .\text-mirror.ps1 -in C:\dev\abc\extract\extracted\pdfs\abc-pdfs-1.txt `