tohuuuuu

#!/usr/bin/env python3
import re
import pandas
from airium import Airium

dataframe = pandas.read_csv("part_000000.csv", delimiter=",")
dataset = dataframe.values

a = Airium()

tohuuuuu

"""
We need the Pypi regex module instead of the builtin "re", since the builtin implementation
doesn't allow Lookbehinds with flexible width which we need here.
See https://stackoverflow.com/q/20089922/342546 and https://stackoverflow.com/q/78772454/342546
"""
import regex as re

"""
Regex für BVerfGE-Zitate (nur Band/Startseite, nicht auch zitierte Seite). Basismuster
sind zwei Zifferngruppen, die durch ein Komma getrennt sind.

tohuuuuu

for i in *.pdf
do
  ocrmypdf -l deu -i "$i" "${i/%.pdf/_ocr.pdf}"
done

tohuuuuu

ssh -f <user>@<host> -L <localport>:<remoteserver>:443 -N

tohuuuuu

start-process -NoNewWindow powershell `
 {ssh -f <user>@<host> `
      -L 10443:127.0.0.1:443 `
      -N }

tohuuuuu

export storepass="mystorepassword"
export keypass="mykeypassword"
for i in ./*.jar; do jarsigner -storepass:env storepass -keypass:env keypass "$i" key_alias;done

tohuuuuu

java -cp /usr/share/java/saxonb.jar net.sf.saxon.Transform -ext:on videodata.xml transform_vsmeta.xslt

tohuuuuu

<xsl:stylesheet
    version="2.0"
    xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
    xmlns:xhtml="http://www.w3.org/1999/xhtml"
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
    <!-- Sets the root directory for the output -->
    <xsl:variable
        name="outpathprefix"
        select="'/tmp/videodata-nfo-out'" />
    <xsl:template match="/videodata_tmp/row">

tohuuuuu

CREATE TEMP TABLE "videodata_tmp" AS
        SELECT 
                v.mapper_id as id, 
                'home'||v.mapper_id as uniqueid,
                right(v.path, position('/' in reverse(v.path)) - 1) as filename, 
                v.path, 
                g2.genre, 
                h.title, 
                h.record_time, 
                s.summary