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 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

<#
    Requires Stanford NER, Java 1.8+
    formats = slashTags, inlineXML, xml, tsv, tabbedEntities 
#>


param(
    [Parameter(Mandatory=$true,Position=0)]
    [string]$file,
    [Parameter(Mandatory=$true,Position=1)]

peaeater

<#
    parse tsv
    Categories: person, location, organization, misc, money, percent, date, time (depending on classifier used to produce the tsv)
    Outfile: Results written to console if outfile not provided. If all categories, outfile is used as a filename template.

#>

param(
    [Parameter(Mandatory=$true,Position=0)]

peaeater

   <!-- suggest fields -->
   <copyField source="title" dest="title_suggest" />
   <copyField source="title" dest="title_suggest_edge" />
   <copyField source="title" dest="title_suggest_ngram" />
   <copyField source="title" dest="title_s" />
   <copyField source="collection" dest="collection_suggest" />
   <copyField source="collection" dest="collection_suggest_edge" />
   <copyField source="collection" dest="collection_suggest_ngram" />
   <copyField source="collection" dest="collection_s" />
   <copyField source="universe" dest="universe_suggest" />

peaeater

<!-- request handler to return typeahead suggestions -->
<requestHandler name="/suggest" class="solr.SearchHandler">
  <lst name="defaults">
    <str name="echoParams">explicit</str>
    <str name="defType">edismax</str>
    <str name="rows">10</str>
    <str name="fl">universe,collection,title,score</str>
    <str name="qf">title_suggest^30 title_suggest_ngram^50.0 collection_suggest^15 collection_suggest_ngram^25.0</str>
    <str name="pf">title_suggest_edge^50.0 collection_suggest_edge^25.0</str>
    <str name="group">true</str>

peaeater

    <!-- text_suggest : Matches whole terms in the suggest text  -->
    <fieldType name="text_suggest" class="solr.TextField" positionIncrementGap="100">
      <analyzer type="index">
        <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-ISOLatin1Accent.txt"/>
        <tokenizer class="solr.StandardTokenizerFactory"/>
        <filter class="solr.WordDelimiterFilterFactory" 
              generateWordParts="1" 
              generateNumberParts="1"
              catenateWords="1"
              catenateNumbers="1"