derivative-rodeo 0.3.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: dc2eed3e32c7a4558d55e9d530b6790a5b876dcdfc4ced421cfa4894aa977d44
-  data.tar.gz: 6e16e4bd7b9d38a1a19b1768a5cdb021c6aa946287f430c6a6c62fa26a215ca6
+  metadata.gz: bee0908ac5d045db1948b062d3a4e1569fff41b4a5a0f1521f31b620c15c53a6
+  data.tar.gz: 328de6f1cde3bcdadca31a361821b2c573425d15bfddbea5bf85d9475a8a3d0e
 SHA512:
-  metadata.gz: 0ac19d20f92490eed508949b18df66ce61d0850a22a2b8b1e514673ddd447afb578e8090d4234dc0a179b85c25a145e44bce6a1e71cfe2f67d2e3b438cb4b9ff
-  data.tar.gz: 6f503dd265243982bc9163b7fb6da42211eca3eb647b1ee9491fcbc06b373c6822222ee6d72c190f2e1bbd7ca63c8126102acd841b1e8f0240434a1af3a69a4f
+  metadata.gz: 2d8ba019ef30666d9633b73e90fe599b53d5f6698de0400b43a25c37a06470542962db8f61d74ed6a444f1ecc5ffbd604d2c0891dffcf5fa86d9dce87ace1bb5
+  data.tar.gz: b682377ce08e4379f1323bfdb6c6b8f46c97d45ebb392bb1dc7f5bc27f5b01701731880dc08f96cb5ef2b0da8ad39349b4534a63b4039e78616331b93bd9516c

data/lib/derivative_rodeo/generators/base_generator.rb

@@ -39,7 +39,6 @@ module DerivativeRodeo
       #        {Services::ConvertUriViaTemplateService} with the given
       #        :preprocessed_location_template.
       def initialize(input_uris:, output_location_template:, preprocessed_location_template: nil)
-        # NOTE: Are we using this preprocessed_location_template?  Wondering?
         @input_uris = Array.wrap(input_uris)
         @output_location_template = output_location_template
         @preprocessed_location_template = preprocessed_location_template

data/lib/derivative_rodeo/generators/pdf_split_generator.rb

@@ -52,7 +52,7 @@ module DerivativeRodeo
       # @see #existing_page_locations
       # @see .filename_for_a_derived_page_from_a_pdf?
       def image_file_basename_template(basename:)
-        "#{basename}/pages/#{basename}--page-%d.#{output_extension}"
+        "#{basename}--page-%d.#{output_extension}"
       end
 
       ##
@@ -62,21 +62,21 @@ module DerivativeRodeo
       # @param input_location [StorageLocations::BaseLocation]
       #
       # @return [Enumerable<StorageLocations::BaseLocation>] the files at the given :input_location
-      #         with :tail_glob.
+      #         with :tail_regexp.
       #
       # @note There is relation to {Generators::BaseGenerator#destination} and this method.
       #
       # @note The tail_glob is in relation to the {#image_file_basename_template}
       def existing_page_locations(input_location:)
         # See image_file_basename_template
-        tail_glob = "#{input_location.file_basename}/pages/*.#{output_extension}"
+        tail_regexp = %r{#{input_location.file_basename}--page-\d+\.#{output_extension}$}
 
-        output_locations = input_location.derived_file_from(template: output_location_template).globbed_tail_locations(tail_glob: tail_glob)
+        output_locations = input_location.derived_file_from(template: output_location_template).matching_locations_in_file_dir(tail_regexp: tail_regexp)
         return output_locations if output_locations.count.positive?
 
         return [] if preprocessed_location_template.blank?
 
-        input_location.derived_file_from(template: preprocessed_location_template).globbed_tail_loations(tail_glob: tail_glob)
+        input_location.derived_file_from(template: preprocessed_location_template).globbed_tail_loations(tail_regexp: tail_regexp)
       end
 
       ##
@@ -101,20 +101,22 @@ module DerivativeRodeo
       def with_each_requisite_location_and_tmp_file_path
         input_files.each do |input_location|
           input_location.with_existing_tmp_path do |input_tmp_file_path|
-            ## We want a single call for a directory listing of the image_file_basename_template
-            generated_files = existing_page_locations(input_location: input_location)
+            existing_locations = existing_page_locations(input_location: input_location)
 
-            if generated_files.count.zero?
-              generated_files = Services::PdfSplitter.call(
+            if existing_locations.count.positive?
+              existing_locations.each do |location|
+                yield(location, location.file_path)
+              end
+            else
+              # We're going to need to create the files and "cast" them to locations.
+              Services::PdfSplitter.call(
                 input_tmp_file_path,
                 image_extension: output_extension,
                 image_file_basename_template: image_file_basename_template(basename: input_location.file_basename)
-              )
-            end
-
-            generated_files.each do |image_path|
-              image_location = StorageLocations::FileLocation.new("file://#{image_path}")
-              yield(image_location, image_path)
+              ).each do |image_path|
+                image_location = StorageLocations::FileLocation.new("file://#{image_path}")
+                yield(image_location, image_path)
+              end
             end
           end
         end

data/lib/derivative_rodeo/storage_locations/base_location.rb

@@ -210,18 +210,18 @@ module DerivativeRodeo
 
       ##
       # When you have a known location and want to check for files that are within that location,
-      # use the {#globbed_tail_locations} method.  In the case of {Generators::PdfSplitGenerator} we
+      # use the {#matching_locations_in_file_dir} method.  In the case of {Generators::PdfSplitGenerator} we
       # need to know the path to all of the image files we "split" off of the given PDF.
       #
       # We can use the :file_path as the prefix the given :tail_glob as the suffix for a "fully
       # qualified" Dir.glob type search.
       #
-      # @param tail_glob [String]
+      # @param tail_regexp [Regexp]
       #
       # @return [Enumerable<StorageLocations::BaseLocation>] the locations of the files; an empty
       #         array when there are none.
-      def globbed_tail_locations(tail_glob:)
-        raise NotImplementedError, "#{self.class}#globbed_locations"
+      def matching_locations_in_file_dir(tail_regexp:)
+        raise NotImplementedError, "#{self.class}#matching_locations_in_file_dir"
       end
 
       ##

data/lib/derivative_rodeo/storage_locations/file_location.rb

@@ -35,8 +35,16 @@ module DerivativeRodeo
         file_uri
       end
 
-      def globbed_tail_locations(tail_glob:)
-        Dir.glob(File.join(file_dir, tail_glob))
+      ##
+      # @return [Enumerable<DerivativeRodeo::StorageLocations::FileLocation>]
+      #
+      # @see Generators::PdfSplitGenerator#image_file_basename_template
+      #
+      # @param tail_regexp [Regexp]
+      def matching_locations_in_file_dir(tail_regexp:)
+        Dir.glob(File.join(file_dir, "*")).each_with_object([]) do |filename, accumulator|
+          accumulator << derived_file_from(template: "file://#{filename}") if tail_regexp.match(filename)
+        end
       end
     end
   end

data/lib/derivative_rodeo/storage_locations/s3_location.rb

@@ -65,31 +65,19 @@ module DerivativeRodeo
       ##
       # @return [Enumerable<DerivativeRodeo::StorageLocations::S3Location>]
       #
-      # @note S3 allows searching on a prefix but does not allow for "wildcard" searches.  We can
-      #       use the components of the file_path to fake that behavior.
+      # @note S3 allows searching on a prefix but does not allow for "wildcard" searches.
       #
       # @see Generators::PdfSplitGenerator#image_file_basename_template
-      def globbed_tail_locations(tail_glob:)
-        # file_path = "s3://blah/1234/hello-world/pages/*.tiff"
-        #
-        # NOTE: Should we be storing our files as such?  The pattern we need is
-        # :parent_identifier/:file_set_identifier/files There are probably cases where a work has
-        # more than one PDF (that we intend to split); we don't want to trample on those split files
-        # and miscolate two PDFs.
-        #
-        # file_path = "s3://blah/1234/hello-world/hello-world.pdf
-        globname = File.join(file_dir, tail_glob)
-        regexp = %r{#{File.extname(globname)}$}
-
-        # NOTE: We're making some informed guesses, needing to include the fully qualified template
-        # based on both the key of the item in the bucket as well as the bucket's host.
+      #
+      # @param tail_regexp [Regexp]
+      def matching_locations_in_file_dir(tail_regexp:)
         uri = URI.parse(file_uri)
         scheme_and_host = "#{uri.scheme}://#{uri.host}"
 
-        bucket.objects(prefix: File.dirname(globname)).flat_map do |object|
-          if object.key.match(regexp)
+        bucket.objects(prefix: file_dir).each_with_object([]) do |object, accumulator|
+          if tail_regexp.match(object.key)
             template = File.join(scheme_and_host, object.key)
-            derived_file_from(template: template)
+            accumulator << derived_file_from(template: template)
           end
         end
       end

data/lib/derivative_rodeo/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module DerivativeRodeo
-  VERSION = '0.3.0'
+  VERSION = '0.4.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: derivative-rodeo
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Rob Kaufman
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-06-05 00:00:00.000000000 Z
+date: 2023-06-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -337,7 +337,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.1.6
 signing_key:
 specification_version: 4
 summary: An ETL Ecosystem for Derivative Processing.