atlas_rb 1.7.0 → 1.8.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1a9ee4ab4b57221618d8ad13ab874acbfce61a452efc8e9562559fcb0215bef8
-  data.tar.gz: 22c8c48404af609784177ba0f157380bc1cef435f9b6b37b76f6e65b95cef1a2
+  metadata.gz: a3d2bc949790f66ee7081de2e94d427f69869fcb301c45d4b9399c072f466820
+  data.tar.gz: 466abe63f27507e1845bc1126b739d2bfa396f7c79c447b1bf57e5be42352f4c
 SHA512:
-  metadata.gz: 68ddbb93d8ad4049f16d01786d860f3ccc7bd610e5f57144f79ba0e30dd1bb8e66fd4c98adf17e9847b8551e9b42265b649650acd6c23f3a6dad3ffa3479879b
-  data.tar.gz: bdfa9d364af363d50466158d13a944c3062b6d8649e5de57fdbb350d87e30e2c0fbf4dcc72c6ff515b536b40358456dc7359d449e1b2926149ff5f489f3ba9d5
+  metadata.gz: 87494a7060c9b9f192edb404ecffd98ea5b8f4859f4b507e25e7a8d66717d34af7c240f3d99df13163f5e822163d5d3f146df4e9898937a5cb0687b80d12cae1
+  data.tar.gz: 04b3221d9ae88ff6bd1b4586321dbd4eda20a4f6753cedfbf465ad4ad2d27214f5252a6e7dd4259e10a24b813eda4a966a7a39fd243244ad295b9c9a749cd5a6

data/.version

@@ -1 +1 @@
-1.7.0
+1.8.0

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 (1.8.0)
       faraday (~> 2.7)
       faraday-follow_redirects (~> 0.3.0)
       faraday-multipart (~> 1)

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

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: atlas_rb
 version: !ruby/object:Gem::Version
-  version: 1.7.0
+  version: 1.8.0
 platform: ruby
 authors:
 - David Cliff