copy of i343

Dockerfile

@@ -46,6 +46,11 @@ RUN wget https://github.com/ImageMagick/ImageMagick/archive/refs/tags/7.1.0-57.t
     && rm -rf ImageMagick* \
     && rm -rf /var/cache/apk/*
 
+# Install "best" training data for Tesseract
+RUN echo "📚 Installing Tesseract Best (training data)!" && \
+    cd /usr/share/tessdata/ && \
+    wget https://github.com/tesseract-ocr/tessdata_best/blob/main/eng.traineddata?raw=true -O eng_best.traineddata
+
 ARG VIPS_VERSION=8.11.3
 
 RUN set -x -o pipefail \

Gemfile.lock

@@ -219,7 +219,7 @@ GIT
 
 GIT
   remote: https://github.com/scientist-softserv/iiif_print.git
-  revision: 122e86634f17c8f40d9ae4d59d2d7deca00f1694
+  revision: cee97520f95e90a9e75d4dbcf159db337676e3c6
   branch: main
   specs:
     iiif_print (1.0.0)

app/services/iiif_print/tenant_config.rb

@@ -100,6 +100,11 @@ module PdfSplitter
       mattr_accessor :iiif_print_splitter
       self.iiif_print_splitter = ::IiifPrint::SplitPdfs::PagesToJpgsSplitter
 
+      ##
+      def self.never_split_pdfs?
+        !TenantConfig.use_iiif_print?
+      end
+
       ##
       # @api public
       def self.call(*args)
@@ -147,6 +152,12 @@ def service
     # In Hyrax::WorkShowPresenter we're only looking at the underlying file_sets.  But IiifPrint
     # needs to look at multiple places.
     module WorkShowPresenterDecorator
+      ##
+      # @return [Boolean] Identifies whether IiifPrint PDF splitting is active for this work's tenant
+      def split_pdfs?
+        TenantConfig.use_iiif_print?
+      end
+
       ##
       # @return [Array<Symbol>] predicate methods (e.g. ending in "?") that reflect the types
       #         of files we want to consider for showing in the IIIF Viewer.

config/initializers/iiif_print.rb

@@ -22,4 +22,5 @@
   #   config.sort_iiif_manifest_canvases_by = :date_published
   config.default_iiif_manifest_version = 3
   config.persistence_adapter = IiifPrint::PersistenceLayer::ValkyrieAdapter
+  config.additional_tesseract_options = "-l eng_best"
 end

db/migrate/20240214005253_add_model_details_to_iiif_print_pending_relationships.iiif_print.rb

@@ -1,8 +1,8 @@
 # This migration comes from iiif_print (originally 20231110163052)
 class AddModelDetailsToIiifPrintPendingRelationships < ActiveRecord::Migration[5.2]
   def change
-    add_column :iiif_print_pending_relationships, :parent_model, :string
-    add_column :iiif_print_pending_relationships, :child_model, :string
-    add_column :iiif_print_pending_relationships, :file_id, :string
+    add_column :iiif_print_pending_relationships, :parent_model, :string unless column_exists?(:iif_print_pending_relationships, :parent_model)
+    add_column :iiif_print_pending_relationships, :child_model, :string  unless column_exists?(:iif_print_pending_relationships, :child_model)
+    add_column :iiif_print_pending_relationships, :file_id, :string  unless column_exists?(:iif_print_pending_relationships, :file_id)
   end
 end