atlas_rb 1.7.0 → 1.8.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1a9ee4ab4b57221618d8ad13ab874acbfce61a452efc8e9562559fcb0215bef8
-  data.tar.gz: 22c8c48404af609784177ba0f157380bc1cef435f9b6b37b76f6e65b95cef1a2
+  metadata.gz: de8129aceabcd06af713b7bddf2e4be8ff259bc3f8095af41d9e63cc2f03c17b
+  data.tar.gz: 9a45c13597c30c4b0c09c9dfb0bf199edb7d919d050f10faaadc32cc2024af3b
 SHA512:
-  metadata.gz: 68ddbb93d8ad4049f16d01786d860f3ccc7bd610e5f57144f79ba0e30dd1bb8e66fd4c98adf17e9847b8551e9b42265b649650acd6c23f3a6dad3ffa3479879b
-  data.tar.gz: bdfa9d364af363d50466158d13a944c3062b6d8649e5de57fdbb350d87e30e2c0fbf4dcc72c6ff515b536b40358456dc7359d449e1b2926149ff5f489f3ba9d5
+  metadata.gz: ee4d49599431a9052c3f3bc55d2d336bb967fedc61edb2815dda42cee74d2250b6700a51ea88c5b74a959fe2f562923e4486831bba66ceb7d5b0236fa74b054c
+  data.tar.gz: 75e2208c86cc1d3e6e13a1bcde956d2d821a7e6e5a141004b2bc2743b550778bd621bcc70aed2528122fabcb931f60a2bc356ed99226a9ece39b125b4d3a3f09

data/.version

@@ -1 +1 @@
-1.7.0
+1.8.1

data/CHANGELOG.md

@@ -1,5 +1,16 @@
 # Changelog
 
+## 1.8.0
+
+### Added — `Work.set_full_text` (full-text search seam)
+
+`Work.set_full_text(id, text:)` → `PATCH /works/:id/full_text`. Hands Atlas the
+Work-level aggregate of Cerberus-extracted document text; Atlas stores it as the
+Work's derived `full_text` and projects it onto the Work's Solr doc
+(`all_text_timv`) for body-text search and the "Full Text Match" snippet. Same
+"machine-set derived metadata" family as `set_thumbnails` / `set_image_derivatives`
+— a regenerable search aid re-sent on any re-ingest, not user-authored content.
+
 ## 1.7.0
 
 ### Added — binary version read surface (`Blob.versions` / `version_content` / `rollback`)

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    atlas_rb (1.7.0)
+    atlas_rb (1.8.1)
       faraday (~> 2.7)
       faraday-follow_redirects (~> 0.3.0)
       faraday-multipart (~> 1)

data/lib/atlas_rb/blob.rb

@@ -39,6 +39,49 @@ module AtlasRb
       ))['blob']
     end
 
+    # Resolve a content Blob to its parent FileSet and containing Work noids.
+    #
+    # Wraps `GET /files/<id>/ancestry`. The download path is keyed only by the
+    # blob id, so a consumer recording a download/stream impression against the
+    # containing Work resolves it here — instead of threading the work noid
+    # through the download URL. Reads on the Blob floor (no admin gate). An
+    # unknown id yields a `404` (raw Faraday response); either value is `nil`
+    # when unresolvable (e.g. an orphan blob with no FileSet parent).
+    #
+    # @param id [String] the Blob ID.
+    # @param nuid [String, nil] optional acting user's NUID. On the relay-signing
+    #   path it is signed into the assertion `sub`; on the BYO-JWT (`ATLAS_JWT`)
+    #   path it is ignored (identity lives in the token).
+    # @param on_behalf_of [String, nil] optional NUID for the `On-Behalf-Of`
+    #   header. Falls through to {AtlasRb.config}.default_on_behalf_of when
+    #   omitted.
+    # @return [AtlasRb::Mash] `{ "file_set" => "<noid>", "work" => "<noid>" }`
+    #   (either value `nil` when unresolvable).
+    #
+    # @example
+    #   AtlasRb::Blob.ancestry("b-321")
+    #   # => { "file_set" => "fs-654", "work" => "w-789" }
+    def self.ancestry(id, nuid: nil, on_behalf_of: nil)
+      AtlasRb::Mash.new(JSON.parse(
+        connection({}, nuid, on_behalf_of: on_behalf_of).get("#{ROUTE}#{id}/ancestry")&.body
+      ))
+    end
+
+    # Convenience over {.ancestry}: the containing Work's noid for a content
+    # Blob (or `nil` when unresolvable). The shape Cerberus's impression-capture
+    # job wants — roll a download up to its Work from the blob id alone.
+    #
+    # @param id [String] the Blob ID.
+    # @param nuid [String, nil] optional acting user's NUID (see {.ancestry}).
+    # @param on_behalf_of [String, nil] optional `On-Behalf-Of` NUID (see {.ancestry}).
+    # @return [String, nil] the containing Work's noid, or `nil` when unresolvable.
+    #
+    # @example
+    #   AtlasRb::Blob.work("b-321") # => "w-789"
+    def self.work(id, nuid: nil, on_behalf_of: nil)
+      ancestry(id, nuid: nuid, on_behalf_of: on_behalf_of)['work']
+    end
+
     # Stream the Blob's binary content through a caller-supplied block.
     #
     # The body is **not** buffered — each chunk Faraday receives is yielded

data/lib/atlas_rb/work.rb

@@ -344,6 +344,42 @@ module AtlasRb
       ))
     end
 
+    # Store a Work's derived full-document text for search indexing.
+    #
+    # Purpose-specific PATCH in the same "machine-set derived metadata" family
+    # as {.set_thumbnails} / {.set_image_derivatives}. Hand Atlas the Work-level
+    # aggregate of the extracted body text (the concatenation of the Work's
+    # content FileSets' text); Atlas stores it as the Work's derived `full_text`
+    # and its `FullTextIndexer` projects it onto the Work's Solr doc
+    # (`all_text_timv`) for body-text search + the "Full Text Match" snippet.
+    #
+    # Distinct from {.metadata} — this is a machine-extracted search aid
+    # (pdftotext / Tika in a Cerberus job), not user-authored descriptive
+    # content, and is re-sent on any re-ingest. Empty/blank text clears it.
+    #
+    # @param id [String] the Work ID.
+    # @param text [String] the extracted plain text (Work-level aggregate).
+    # @param nuid [String, nil] optional acting user's NUID. On the relay-signing
+    #   path it is signed into the assertion `sub`; on the BYO-JWT (`ATLAS_JWT`)
+    #   path it is ignored (identity lives in the token).
+    # @param on_behalf_of [String, nil] optional NUID for the `On-Behalf-Of`
+    #   header. Falls through to {AtlasRb.config}.default_on_behalf_of when
+    #   omitted.
+    # @return [AtlasRb::Mash] the parsed JSON response (the Work; the stored text
+    #   is not echoed back — it's read only through Solr).
+    # @raise [AtlasRb::StaleResourceError] if Atlas reports an optimistic-lock
+    #   conflict that exhausted its internal retry budget (HTTP 409 with
+    #   `error: "stale_resource"`).
+    #
+    # @example
+    #   AtlasRb::Work.set_full_text("w-789", text: extracted_pdf_text)
+    def self.set_full_text(id, text:, nuid: nil, on_behalf_of: nil)
+      AtlasRb::Mash.new(JSON.parse(
+        connection({}, nuid, on_behalf_of: on_behalf_of)
+          .patch(ROUTE + id + '/full_text', JSON.dump(text: text))&.body
+      ))
+    end
+
     # List the assets attached to a Work — {Blob}s and {Delegate}s alike.
     #
     # Useful for building download UIs — the response includes enough to

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: atlas_rb
 version: !ruby/object:Gem::Version
-  version: 1.7.0
+  version: 1.8.1
 platform: ruby
 authors:
 - David Cliff
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2026-06-24 00:00:00.000000000 Z
+date: 2026-06-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: faraday