peaeater

[
	{ "keys": ["ctrl+\\","a","`"], "command": "insert", "args": {"characters": "à"} },
	{ "keys": ["ctrl+\\","a","^"], "command": "insert", "args": {"characters": "â"} },
	{ "keys": ["ctrl+\\","e","'"], "command": "insert", "args": {"characters": "é"} },
	{ "keys": ["ctrl+\\","e","`"], "command": "insert", "args": {"characters": "è"} },
	{ "keys": ["ctrl+\\","e","^"], "command": "insert", "args": {"characters": "ê"} },
	{ "keys": ["ctrl+\\","e",":"], "command": "insert", "args": {"characters": "ë"} },
	{ "keys": ["ctrl+\\","i",":"], "command": "insert", "args": {"characters": "ï"} },
	{ "keys": ["ctrl+\\","i","^"], "command": "insert", "args": {"characters": "î"} },
	{ "keys": ["ctrl+\\","o","^"], "command": "insert", "args": {"characters": "ô"} },

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

# 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

# convert pngs to jpgs
# requires imagemagick

Param(
    [int]$size = 1000,
    [string]$indir = ".",
    [string]$outdir = $indir
    )

if (!(test-path $outdir)) {

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

# ocr tif/png to hocr (html)
# requires tesseract

Param(
    [string]$ext = "tif",
    [string]$indir = ".",
    [string]$outdir = $indir
)

if (!(test-path $outdir)) {

peaeater

<#
 Processes raw source pdfs, producing per page: 1 txt, 1 hocr, 1 jpg.
 Requires imagemagick w/ ghostscript, tesseract.
 
 Subscripts: pdf2png.ps1, ocr.ps1, hocr.ps1, png2jpg.ps1
#>

param(
    [string]$indir = ".",
    [string]$outbase = $indir

peaeater

<entity 
    name="sample"
    transformer="RegexTransformer,TemplateTransformer">

    <field column="test_ignored" template="BLAH" />
    <field column="test_ignored" sourceColName="id" regex="(.+)" />

    <!-- 
    test_ignored will equal 'BLAH' because TemplateTransformer acts last,
    even though it is written first.

peaeater

<#
    Peter Tyrrell, 2015
    Convert Harvest time report to Quickbooks import format in Windows-1252.
#>

param (
    [string]$indir = ".",
    [string]$outdir = $indir
)

peaeater

# restarts named app pool if stopped, writes restart event to the Application Event Log
# Peter Tyrrell, May 13 2013

param(
    [string[]]$names = (,"ISAPI Webpublisher")
)

# If OS < Server 2008 R2, install Powershell snap-in for IIS and uncomment:
#Add-PSSnapin WebAdministration