| set -e | |
| # select first CUDA device (in case there are multiple, which may fail due to [a recent Tensorflow problem](https://github.com/qurator-spk/eynollah/issues/99)) | |
| export CUDA_VISIBLE_DEVICES=0 | |
| # check we are not running into [this bug](https://github.com/shapely/shapely/issues/1598) | |
| python3 -c "from shapely.geometry import Polygon; import torch; torch.randn(10).cuda()" | |
| # validate CUDA support is working in TF and Torch (not an exhaustive test) | |
| python3 -c "import torch; print(torch.cuda.is_available())" |
| moved to https://github.com/mets/METS1to2 |
| #!/usr/bin/perl | |
| use strict; | |
| use utf8; | |
| use XML::LibXML; | |
| use XML::Quote; | |
| binmode STDOUT, ":utf8"; | |
| my $dom=XML::LibXML->load_xml(location=>$ARGV[0]); | |
| my $root=$dom->documentElement; |
| import {default as fetch} from 'node-fetch'; | |
| const { pdf } = require("pdf-to-img"); | |
| import {tmpdir} from "os"; | |
| import {createWriteStream, createReadStream} from 'fs'; | |
| import * as fsp from 'fs/promises' | |
| import * as archiver from 'archiver'; | |
| import {ArchiverError} from "archiver"; | |
| import * as path from "path"; | |
| import {Parser, Builder} from "xml2js"; |
| #! /usr/bin/env bash | |
| # see https://ryanfb.github.io/etc/2015/03/16/automatic_evaluation_of_ocr_quality.html | |
| # using https://github.com/saffsd/langid.py | |
| # install with pip install langid and add the scorelines.sh & ocrquality.rb scripts from the blog entry in the same directory | |
| # The PDF source files, which start with a DOI, adapt this for your case | |
| FILE_SELECTOR=/path/to/source/dir/*.pdf | |
| # The path to the directory to which the selected documents should be copied | |
| TARGET=/path/to/target/dir |
To estimate the impact of some changes to dinglehopper I used hyperfine to benchmark the behaviour.
The commands to run a docker container to execute the benchmarks are listed in performance-docker.sh.
The commands needed to prepare, execute and analyse the benchmark are listed in performance.sh.
| FROM python:3.7 | |
| RUN apt-get update \ | |
| && apt-get install -y --no-install-recommends libcairo2-dev libgtk-3-bin libgtk-3-dev libglib2.0-dev libgtksourceview-3.0-dev libgirepository1.0-dev gir1.2-webkit2-4.0 pkg-config cmake \ | |
| && pip3 install -U setuptools --use-feature=2020-resolver \ | |
| && pip3 install browse-ocrd --use-feature=2020-resolver | |
| ENV GDK_BACKEND broadway | |
| ENV BROADWAY_DISPLAY :5 |
| # -*- coding:utf-8 -*- | |
| from itertools import dropwhile | |
| import json | |
| import re | |
| import sys | |
| import matplotlib.pyplot as plt | |
| _jpageviewer_jar=~/opt/jpageviewer/JPageViewer.jar | |
| if [ -e "$_jpageviewer_jar" ]; then | |
| jpageviewer() { | |
| # --resolve-dir defaults to the file's directory | |
| _jpageviewer_resolve_dir=`dirname "$1"` | |
| # ... unless a mets.xml file exists one directory down (OCR-D workspace) | |
| if [ -e "$_jpageviewer_resolve_dir"/../mets.xml ]; then | |
| _jpageviewer_resolve_dir="$_jpageviewer_resolve_dir"/.. | |
| fi |
| <?xml version="1.0" encoding="UTF-8"?> | |
| <xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" | |
| xmlns:xs="http://www.w3.org/2001/XMLSchema" | |
| xmlns:saxon="http://saxon.sf.net/" | |
| xmlns:my="foo.bar" | |
| exclude-result-prefixes="xs my saxon uuid" | |
| xpath-default-namespace="http://www.w3.org/1999/xhtml" | |
| version="2.0" | |
| xmlns:uuid="java:java.util.UUID"> |