feat: [contentwarehouse] Make Layout Parser generally available in V1

packages/google-cloud-contentwarehouse/protos/google/cloud/documentai/v1/document.proto

@@ -893,6 +893,160 @@ message Document {
     repeated Provenance provenance = 3 [deprecated = true];
   }
 
+  // Represents the parsed layout of a document as a collection of blocks that
+  // the document is divided into.
+  message DocumentLayout {
+    // Represents a block. A block could be one of the various types (text,
+    // table, list) supported.
+    message DocumentLayoutBlock {
+      // Represents where the block starts and ends in the document.
+      message LayoutPageSpan {
+        // Page where block starts in the document.
+        int32 page_start = 1;
+
+        // Page where block ends in the document.
+        int32 page_end = 2;
+      }
+
+      // Represents a text type block.
+      message LayoutTextBlock {
+        // Text content stored in the block.
+        string text = 1;
+
+        // Type of the text in the block. Available options are: `paragraph`,
+        // `subtitle`, `heading-1`, `heading-2`, `heading-3`, `heading-4`,
+        // `heading-5`, `header`, `footer`.
+        string type = 2;
+
+        // A text block could further have child blocks.
+        // Repeated blocks support further hierarchies and nested blocks.
+        repeated DocumentLayoutBlock blocks = 3;
+      }
+
+      // Represents a table type block.
+      message LayoutTableBlock {
+        // Header rows at the top of the table.
+        repeated LayoutTableRow header_rows = 1;
+
+        // Body rows containing main table content.
+        repeated LayoutTableRow body_rows = 2;
+
+        // Table caption/title.
+        string caption = 3;
+      }
+
+      // Represents a row in a table.
+      message LayoutTableRow {
+        // A table row is a list of table cells.
+        repeated LayoutTableCell cells = 1;
+      }
+
+      // Represents a cell in a table row.
+      message LayoutTableCell {
+        // A table cell is a list of blocks.
+        // Repeated blocks support further hierarchies and nested blocks.
+        repeated DocumentLayoutBlock blocks = 1;
+
+        // How many rows this cell spans.
+        int32 row_span = 2;
+
+        // How many columns this cell spans.
+        int32 col_span = 3;
+      }
+
+      // Represents a list type block.
+      message LayoutListBlock {
+        // List entries that constitute a list block.
+        repeated LayoutListEntry list_entries = 1;
+
+        // Type of the list_entries (if exist). Available options are `ordered`
+        // and `unordered`.
+        string type = 2;
+      }
+
+      // Represents an entry in the list.
+      message LayoutListEntry {
+        // A list entry is a list of blocks.
+        // Repeated blocks support further hierarchies and nested blocks.
+        repeated DocumentLayoutBlock blocks = 1;
+      }
+
+      oneof block {
+        // Block consisting of text content.
+        LayoutTextBlock text_block = 2;
+
+        // Block consisting of table content/structure.
+        LayoutTableBlock table_block = 3;
+
+        // Block consisting of list content/structure.
+        LayoutListBlock list_block = 4;
+      }
+
+      // ID of the block.
+      string block_id = 1;
+
+      // Page span of the block.
+      LayoutPageSpan page_span = 5;
+    }
+
+    // List of blocks in the document.
+    repeated DocumentLayoutBlock blocks = 1;
+  }
+
+  // Represents the chunks that the document is divided into.
+  message ChunkedDocument {
+    // Represents a chunk.
+    message Chunk {
+      // Represents where the chunk starts and ends in the document.
+      message ChunkPageSpan {
+        // Page where chunk starts in the document.
+        int32 page_start = 1;
+
+        // Page where chunk ends in the document.
+        int32 page_end = 2;
+      }
+
+      // Represents the page header associated with the chunk.
+      message ChunkPageHeader {
+        // Header in text format.
+        string text = 1;
+
+        // Page span of the header.
+        ChunkPageSpan page_span = 2;
+      }
+
+      // Represents the page footer associated with the chunk.
+      message ChunkPageFooter {
+        // Footer in text format.
+        string text = 1;
+
+        // Page span of the footer.
+        ChunkPageSpan page_span = 2;
+      }
+
+      // ID of the chunk.
+      string chunk_id = 1;
+
+      // Unused.
+      repeated string source_block_ids = 2;
+
+      // Text content of the chunk.
+      string content = 3;
+
+      // Page span of the chunk.
+      ChunkPageSpan page_span = 4;
+
+      // Page headers associated with the chunk.
+      repeated ChunkPageHeader page_headers = 5;
+
+      // Page footers associated with the chunk.
+      repeated ChunkPageFooter page_footers = 6;
+    }
+
+    // List of chunks.
+    repeated Chunk chunks = 1;
+  }
+
   // Original source document from the user.
   oneof source {
     // Optional. Currently supports Google Cloud Storage URI of the form
@@ -944,4 +1098,10 @@ message Document {
 
   // Placeholder. Revision history of this document.
   repeated Revision revisions = 13;
+
+  // Parsed layout of the document.
+  DocumentLayout document_layout = 17;
+
+  // Document chunked based on chunking config.
+  ChunkedDocument chunked_document = 18;
 }

packages/google-cloud-contentwarehouse/protos/google/cloud/documentai/v1/document_processor_service.proto

@@ -328,6 +328,23 @@ service DocumentProcessorService {
 
 // Options for Process API
 message ProcessOptions {
+  // Serving config for layout parser processor.
+  message LayoutConfig {
+    // Serving config for chunking.
+    message ChunkingConfig {
+      // Optional. The chunk sizes to use when splitting documents, in order of
+      // level.
+      int32 chunk_size = 1 [(google.api.field_behavior) = OPTIONAL];
+
+      // Optional. Whether or not to include ancestor headings when splitting.
+      bool include_ancestor_headings = 2
+          [(google.api.field_behavior) = OPTIONAL];
+    }
+
+    // Optional. Config for chunking in layout parser processor.
+    ChunkingConfig chunking_config = 1 [(google.api.field_behavior) = OPTIONAL];
+  }
+
   // A list of individual page numbers.
   message IndividualPageSelector {
     // Optional. Indices of the pages (starting from 1).
@@ -356,6 +373,10 @@ message ProcessOptions {
   // Returns error if set on other processor types.
   OcrConfig ocr_config = 1;
 
+  // Optional. Only applicable to `LAYOUT_PARSER_PROCESSOR`.
+  // Returns error if set on other processor types.
+  LayoutConfig layout_config = 9 [(google.api.field_behavior) = OPTIONAL];
+
   // Optional. Override the schema of the
   // [ProcessorVersion][google.cloud.documentai.v1.ProcessorVersion]. Will
   // return an Invalid Argument error if this field is set when the underlying

packages/google-cloud-contentwarehouse/protos/google/cloud/documentai/v1/processor.proto

@@ -128,6 +128,12 @@ message ProcessorVersion {
 
   // Output only. The model type of this processor version.
   ModelType model_type = 15 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 16 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 17 [(google.api.field_behavior) = OUTPUT_ONLY];
 }
 
 // Contains the alias and the aliased resource name of processor version.
@@ -224,4 +230,10 @@ message Processor {
   // The [KMS key](https://cloud.google.com/security-key-management) used for
   // encryption and decryption in CMEK scenarios.
   string kms_key_name = 8;
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzs = 12 [(google.api.field_behavior) = OUTPUT_ONLY];
+
+  // Output only. Reserved for future use.
+  bool satisfies_pzi = 13 [(google.api.field_behavior) = OUTPUT_ONLY];
 }