Add test alto XML workflow

.gitmodules

@@ -0,0 +1,4 @@
+[submodule "open-oni"]
+	path = open-oni
+	url = [email protected]:codemyriad/open-oni.git
+        branch = masca

create_awardee_title.py

@@ -0,0 +1,16 @@
+import datetime
+from core.models import Title, Language, Country, Awardee
+
+Awardee.objects.get_or_create(org_code="lamasca", name="La Masca")
+Title.objects.all().delete()
+title = Title.objects.create(
+    lccn = "sn00000001",    # This needs to be unique across the platform
+    lccn_orig = "sn00000001",
+    name = "La masca",
+    name_normal = "la-masca",
+    start_year = "1994",
+    end_year = "1994",
+    country = Country.objects.get(code="it"),
+    version = datetime.datetime.now()
+)
+title.languages.set([Language.objects.get(code="ita")])

docker-compose.yml

@@ -0,0 +1,64 @@
+services:
+  rdbms:
+    image: mariadb:10.6
+    environment:
+      - MYSQL_ROOT_PASSWORD=123456
+      - MYSQL_DATABASE=openoni
+      - MYSQL_USER=openoni
+      - MYSQL_PASSWORD=openoni
+    volumes:
+      - ./conf/mysql/:/etc/mysql/conf.d:Z
+      - data-mariadb:/var/lib/mysql
+    command: ['--character-set-server=utf8mb4', '--collation-server=utf8mb4_unicode_ci']
+  solr:
+    image: solr:8-slim
+    volumes:
+      - data-solr:/var/solr
+    command:
+      - solr-precreate
+      - openoni
+  rais:
+    image: uolibraries/rais:4
+    environment:
+      - RAIS_IIIFWEBPATH=/images/iiif
+      - RAIS_IIIFBASEURL=${ONI_BASE_URL:-http://localhost}
+      - RAIS_TILECACHELEN=250
+      - RAIS_TILEPATH=/opt/openoni/data/batches
+    volumes:
+      # Image files must be available at RAIS_TILEPATH
+      - ./test_batches:/opt/openoni/data/batches:z
+  web:
+    image: ghcr.io/codemyriad/lamasca-open-oni-web:latest
+    volumes:
+      - ./open-oni:/opt/openoni:z
+      - ./create_awardee_title.py:/opt/create_awardee_title.py
+      - ./test_batches:/opt/openoni/data/batches:z
+    depends_on:
+      - rdbms
+    links:
+      - rdbms
+      - solr
+      - rais
+    environment:
+      - APACHE_LOG_LEVEL=${APACHE_LOG_LEVEL:-warn}
+      - ONI_BASE_URL
+      - ONI_CHRONAM_API_THROTTLE
+      - ONI_DB_HOST
+      - ONI_DB_PORT
+      - ONI_DB_NAME
+      - ONI_DB_USER
+      - ONI_DB_PASSWORD
+      - ONI_DEBUG
+      - ONI_HSTS_SECONDS
+      - ONI_IIIF_URL
+      - ONI_LOG_LEVEL
+      - ONI_LOG_SQL
+      - ONI_LOG_TO_FILE
+      - ONI_SECRET_KEY
+      - ONI_SOLR_URL
+    ports:
+      - ${HTTPPORT:-80}:80
+
+volumes:
+  data-mariadb: {}
+  data-solr: {}

how-to-test-alto-xml.md

@@ -0,0 +1,18 @@
+# How to test an Alto XML file
+
+Setup Open ONI as submodule. This is needed since the open-oni folder will be mounted in the `web` container.
+
+    `git submodule --init --checkout`
+
+Than you should be able to test an XML Alto file with:
+
+    `bash test_alto_batch.sh <path_to_alto_XML_file>`
+
+The script will lookup for a .jp2 and .tif image in the same directory and with the same name as the Alto XML file.
+
+    e.g.
+
+    test_alto
+        |-- 0001.xml
+        |-- 0001.jp2
+        |-- 0001.tif

load_alto_batch.sh

@@ -0,0 +1,63 @@
+#!/bin/bash
+
+# Check if input file is provided
+if [ $# -eq 0 ]; then
+    echo "Usage: $0 <alto_xml_file>"
+    exit 1
+fi
+
+# Input Alto XML file
+ALTO_XML_FILE=$(realpath "$1")
+
+# Create temporary batch directory structure
+BATCH_DIR=$(mktemp -d)
+BATCH_NAME=$(basename "${ALTO_XML_FILE%.*}")
+
+# Create Open ONI batch directory structure
+mkdir -p "${BATCH_DIR}/${BATCH_NAME}/alto"
+mkdir -p "${BATCH_DIR}/${BATCH_NAME}/jp2"
+mkdir -p "${BATCH_DIR}/${BATCH_NAME}/tiff"
+
+# Copy Alto XML to batch directory
+cp "$ALTO_XML_FILE" "${BATCH_DIR}/${BATCH_NAME}/alto/"
+
+# Create a dummy mets.xml file (required for Open ONI batch)
+cat << EOF > "${BATCH_DIR}/${BATCH_NAME}/mets.xml"
+<?xml version="1.0" encoding="UTF-8"?>
+<mets:mets xmlns:mets="http://www.loc.gov/METS/" xmlns:xlink="http://www.w3.org/1999/xlink">
+    <mets:dmdSec ID="dmdSec_1">
+        <mets:mdWrap MDTYPE="DC">
+            <mets:xmlData>
+                <dc:title xmlns:dc="http://purl.org/dc/elements/1.1/">${BATCH_NAME}</dc:title>
+            </mets:xmlData>
+        </mets:mdWrap>
+    </mets:dmdSec>
+</mets:mets>
+EOF
+
+# Create a dummy image to satisfy Open ONI requirements
+convert -size 2000x3000 xc:white "${BATCH_DIR}/${BATCH_NAME}/jp2/${BATCH_NAME}_0001.jp2"
+convert -size 2000x3000 xc:white "${BATCH_DIR}/${BATCH_NAME}/tiff/${BATCH_NAME}_0001.tif"
+
+# Path to Open ONI docker-compose file (adjust as needed)
+DOCKER_COMPOSE_PATH="/path/to/open-oni/docker-compose.yml"
+
+# Ensure docker-compose file exists
+if [ ! -f "$DOCKER_COMPOSE_PATH" ]; then
+    echo "Docker Compose file not found at $DOCKER_COMPOSE_PATH"
+    exit 1
+fi
+
+# Stop any existing Open ONI containers
+docker-compose -f "$DOCKER_COMPOSE_PATH" down
+
+# Start Docker Compose with batch mounted
+docker-compose -f "$DOCKER_COMPOSE_PATH" up -d
+
+# Wait for the container to fully start
+sleep 15
+
+# Load the batch into Open ONI
+docker-compose -f "$DOCKER_COMPOSE_PATH" exec -T web python manage.py load_batch /opt/newspaper_batches/"$BATCH_NAME"
+
+echo "Batch ${BATCH_NAME} loaded successfully!"

test_alto_batch.sh

@@ -0,0 +1,78 @@
+#!/bin/bash
+
+set -e
+
+# Check if input file is provided
+if [ $# -eq 0 ]; then
+    echo "Usage: $0 <alto_xml_file>"
+    exit 1
+fi
+
+# Input Alto XML file
+ALTO_XML_FILE=$(realpath "$1")
+ALTO_XML_FILENAME=$(basename "${ALTO_XML_FILE%.*}")
+
+# Create temporary batch directory structure
+BATCH_DIR=./test_batches
+BATCH_NAME="batch_lamasca_${ALTO_XML_FILENAME}_ver01"
+BATCH_DATE=1994011201
+
+echo "Creating test batch in ${BATCH_DIR}/${BATCH_NAME}"
+
+# Create Open ONI batch directory structure
+mkdir -p "${BATCH_DIR}/${BATCH_NAME}/data/sn00000001/001/${BATCH_DATE}"
+
+# Copy Alto XML to batch directory
+cp "$ALTO_XML_FILE" "${BATCH_DIR}/${BATCH_NAME}/data/sn00000001/001/${BATCH_DATE}/0001.xml"
+cp "$ALTO_XML_FILENAME.jp2" "${BATCH_DIR}/${BATCH_NAME}/data/sn00000001/001/${BATCH_DATE}/0001.jp2"
+cp "$ALTO_XML_FILENAME.tif" "${BATCH_DIR}/${BATCH_NAME}/data/sn00000001/001/${BATCH_DATE}/0001.tif"
+
+# Create a dummy batch_xml file (required for Open ONI batch)
+cat << EOF > "${BATCH_DIR}/${BATCH_NAME}/data/batch.xml"
+<?xml version="1.0" ?>
+<batch xmlns="http://www.loc.gov/ndnp" name="${ALTO_XML_FILENAME}" awardee="lamasca" awardYear="1994">
+	<issue editionOrder="01" issueDate="1994-01-12" lccn="sn00000001">./sn00000001/001/${BATCH_DATE}/${BATCH_DATE}.xml</issue>
+</batch>
+EOF
+
+# Copy default mets file
+cp test_batches/default_mets.xml ${BATCH_DIR}/${BATCH_NAME}/data/sn00000001/001/${BATCH_DATE}/${BATCH_DATE}.xml
+
+# Path to Open ONI docker-compose file (adjust as needed)
+DOCKER_COMPOSE_PATH="./docker-compose.yml"
+
+# Ensure docker-compose file exists
+if [ ! -f "$DOCKER_COMPOSE_PATH" ]; then
+    echo "Docker Compose file not found at $DOCKER_COMPOSE_PATH"
+    exit 1
+fi
+
+# Stop any existing Open ONI containers
+docker compose -f "$DOCKER_COMPOSE_PATH" down
+
+# Start Docker Compose with batch mounted
+docker compose -f "$DOCKER_COMPOSE_PATH" up -d
+
+# Wait for the container to fully start
+sleep 15
+
+# Create Awardee and Title objects if they don't exists
+docker compose -f "$DOCKER_COMPOSE_PATH" exec -T web bash -c "source ENV/bin/activate && python manage.py shell < /opt/create_awardee_title.py"
+
+# Purge the batch if it exists in Open ONI
+docker compose -f "$DOCKER_COMPOSE_PATH" exec -T web bash -c "source ENV/bin/activate && python manage.py purge_batch $BATCH_NAME"
+
+# Load the batch into Open ONI
+docker compose -f "$DOCKER_COMPOSE_PATH" exec -T web bash -c "source ENV/bin/activate && python manage.py load_batch /opt/openoni/data/batches/$BATCH_NAME"
+
+docker compose -f "$DOCKER_COMPOSE_PATH" exec -T web bash -c "curl -s http://localhost/lccn/sn00000001/1994-01-12/ed-1/seq-1/"
+
+# Change permissions for the django cache
+docker compose -f "$DOCKER_COMPOSE_PATH" exec -T web bash -c "chown -R www-data:www-data /var/tmp/django_cache"
+
+echo "Batch ${BATCH_NAME} loaded successfully!"
+
+echo "You should be able to see your page at http://localhost/lccn/sn00000001/1994-01-12/ed-1/seq-1/"
+echo "Useful links:"
+echo "OCR: http://localhost/lccn/sn00000001/1994-01-12/ed-1/seq-1/ocr/"
+echo "Text coordinates: http://localhost/lccn/sn00000001/1994-01-12/ed-1/seq-1/coordinates/"