WIP(document-ai): migrate Document AI Java samples and tests from v1beta3 to v1 GA

document-ai/src/main/java/documentai/v1beta3/ProcessFormDocument.java → document-ai/src/main/java/documentai/v1/ProcessFormDocument.java

@@ -14,16 +14,16 @@
  * limitations under the License.
  */
 
-package documentai.v1beta3;
+package documentai.v1;
 
 // [START documentai_process_form_document]
 
-import com.google.cloud.documentai.v1beta3.Document;
-import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceClient;
-import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceSettings;
-import com.google.cloud.documentai.v1beta3.ProcessRequest;
-import com.google.cloud.documentai.v1beta3.ProcessResponse;
-import com.google.cloud.documentai.v1beta3.RawDocument;
+import com.google.cloud.documentai.v1.Document;
+import com.google.cloud.documentai.v1.DocumentProcessorServiceClient;
+import com.google.cloud.documentai.v1.DocumentProcessorServiceSettings;
+import com.google.cloud.documentai.v1.ProcessRequest;
+import com.google.cloud.documentai.v1.ProcessResponse;
+import com.google.cloud.documentai.v1.RawDocument;
 import com.google.protobuf.ByteString;
 import java.io.IOException;
 import java.nio.file.Files;
@@ -153,4 +153,4 @@ private static String removeNewlines(String s) {
     return s.replace("\n", "").replace("\r", "");
   }
 }
-// [END documentai_process_form_document]
+// [END documentai_process_form_document]

document-ai/src/main/java/documentai/v1beta3/ProcessOcrDocument.java → document-ai/src/main/java/documentai/v1/ProcessOcrDocument.java

@@ -14,16 +14,16 @@
  * limitations under the License.
  */
 
-package documentai.v1beta3;
+package documentai.v1;
 
 // [START documentai_process_ocr_document]
 
-import com.google.cloud.documentai.v1beta3.Document;
-import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceClient;
-import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceSettings;
-import com.google.cloud.documentai.v1beta3.ProcessRequest;
-import com.google.cloud.documentai.v1beta3.ProcessResponse;
-import com.google.cloud.documentai.v1beta3.RawDocument;
+import com.google.cloud.documentai.v1.Document;
+import com.google.cloud.documentai.v1.DocumentProcessorServiceClient;
+import com.google.cloud.documentai.v1.DocumentProcessorServiceSettings;
+import com.google.cloud.documentai.v1.ProcessRequest;
+import com.google.cloud.documentai.v1.ProcessResponse;
+import com.google.cloud.documentai.v1.RawDocument;
 import com.google.protobuf.ByteString;
 import java.io.IOException;
 import java.nio.file.Files;
@@ -176,4 +176,4 @@ private static String escapeNewlines(String s) {
     return s.replace("\n", "\\n").replace("\r", "\\r");
   }
 }
-// [END documentai_process_ocr_document]
+// [END documentai_process_ocr_document]

document-ai/src/main/java/documentai/v1beta3/ProcessSpecializedDocument.java → document-ai/src/main/java/documentai/v1/ProcessSpecializedDocument.java

@@ -14,16 +14,16 @@
  * limitations under the License.
  */
 
-package documentai.v1beta3;
+package documentai.v1;
 
 // [START documentai_process_specialized_document]
 
-import com.google.cloud.documentai.v1beta3.Document;
-import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceClient;
-import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceSettings;
-import com.google.cloud.documentai.v1beta3.ProcessRequest;
-import com.google.cloud.documentai.v1beta3.ProcessResponse;
-import com.google.cloud.documentai.v1beta3.RawDocument;
+import com.google.cloud.documentai.v1.Document;
+import com.google.cloud.documentai.v1.DocumentProcessorServiceClient;
+import com.google.cloud.documentai.v1.DocumentProcessorServiceSettings;
+import com.google.cloud.documentai.v1.ProcessRequest;
+import com.google.cloud.documentai.v1.ProcessResponse;
+import com.google.cloud.documentai.v1.RawDocument;
 import com.google.protobuf.ByteString;
 import java.io.IOException;
 import java.nio.file.Files;
@@ -80,9 +80,9 @@ public static void processSpecializedDocument(
 
       System.out.println("Document processing complete.");
 
-      // Read fields specificly from the specalized US drivers license processor:
+      // Read fields specifically from the specialized US drivers license processor:
       // https://cloud.google.com/document-ai/docs/processors-list#processor_us-driver-license-parser
-      // retriving data from other specalized processors follow a similar pattern.
+      // retrieving data from other specialized processors follow a similar pattern.
       // For a complete list of processors see:
       // https://cloud.google.com/document-ai/docs/processors-list
       //
@@ -94,9 +94,9 @@ public static void processSpecializedDocument(
         // the processor documentation:
         // https://cloud.google.com/document-ai/docs/processors-list
         String entityType = entity.getType();
-        // some other value formats in addition to text are availible
+        // some other value formats in addition to text are available
         // e.g. dates: `entity.getNormalizedValue().getDateValue().getYear()`
-        // check for normilized value with `entity.hasNormalizedValue()`
+        // check for normalized value with `entity.hasNormalizedValue()`
         String entityTextValue = escapeNewlines(entity.getTextAnchor().getContent());
         float entityConfidence = entity.getConfidence();
         System.out.printf(
@@ -110,4 +110,4 @@ private static String escapeNewlines(String s) {
     return s.replace("\n", "\\n").replace("\r", "\\r");
   }
 }
-// [END documentai_process_specialized_document]
+// [END documentai_process_specialized_document]

document-ai/src/main/java/documentai/v1beta3/ProcessSplitterDocument.java → document-ai/src/main/java/documentai/v1/ProcessSplitterDocument.java

@@ -14,16 +14,16 @@
  * limitations under the License.
  */
 
-package documentai.v1beta3;
+package documentai.v1;
 
 // [START documentai_process_splitter_document]
 
-import com.google.cloud.documentai.v1beta3.Document;
-import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceClient;
-import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceSettings;
-import com.google.cloud.documentai.v1beta3.ProcessRequest;
-import com.google.cloud.documentai.v1beta3.ProcessResponse;
-import com.google.cloud.documentai.v1beta3.RawDocument;
+import com.google.cloud.documentai.v1.Document;
+import com.google.cloud.documentai.v1.DocumentProcessorServiceClient;
+import com.google.cloud.documentai.v1.DocumentProcessorServiceSettings;
+import com.google.cloud.documentai.v1.ProcessRequest;
+import com.google.cloud.documentai.v1.ProcessResponse;
+import com.google.cloud.documentai.v1.RawDocument;
 import com.google.protobuf.ByteString;
 import java.io.IOException;
 import java.nio.file.Files;
@@ -86,7 +86,7 @@ public static void processSplitterDocument(
       // This processor only provides text for the document and information on how
       // to split the document on logical boundaries. To identify and extract text,
       // form elements, and entities please see other processors like the OCR, form,
-      // and specalized processors.
+      // and specialized processors.
       List<Document.Entity> entities = documentResponse.getEntitiesList();
       System.out.printf("Found %d subdocuments:\n", entities.size());
       for (Document.Entity entity : entities) {
@@ -116,4 +116,4 @@ private static String pageRefsToString(List<Document.PageAnchor.PageRef> pageRef
     }
   }
 }
-// [END documentai_process_splitter_document]
+// [END documentai_process_splitter_document]

document-ai/src/test/java/documentai/v1beta3/ProcessFormDocumentTest.java → document-ai/src/test/java/documentai/v1/ProcessFormDocumentTest.java

@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package documentai.v1beta3;
+package documentai.v1;
 
 import static com.google.common.truth.Truth.assertThat;
 import static org.junit.Assert.assertNotNull;
@@ -30,7 +30,9 @@
 
 public class ProcessFormDocumentTest {
   private static final String PROJECT_ID = System.getenv("GOOGLE_CLOUD_PROJECT");
-  private static final String PROCESSOR_ID = "88541adc6eeec481";
+  private static final String PROCESSOR_ID = System.getenv("DOCAI_FORM_PROCESSOR_ID") != null
+      ? System.getenv("DOCAI_FORM_PROCESSOR_ID")
+      : "88541adc6eeec481";
   private static final String FILE_PATH = "resources/invoice.pdf";
 
   private ByteArrayOutputStream bout;
@@ -60,19 +62,19 @@ public void setUp() {
   @Test
   public void testProcessFormDocument()
       throws InterruptedException, ExecutionException, IOException, TimeoutException {
-    // parse the GCS invoice as a form.
+    // parse the invoice as a form.
     ProcessFormDocument.processFormDocument(PROJECT_ID, "us", PROCESSOR_ID, FILE_PATH);
     String got = bout.toString();
 
     assertThat(got).contains("There are 1 page(s) in this document.");
-    assertThat(got).contains("Table with 4 columns and 6 rows");
+    assertThat(got).contains("Table with 4 columns and 3 rows");
     assertThat(got).contains("Found 13 form fields");
-    assertThat(got).contains("'BALANCE DUE': '$2140.00'");
+    assertThat(got).contains("BALANCE DUE");
   }
 
   @After
   public void tearDown() {
     System.out.flush();
     System.setOut(originalPrintStream);
   }
-}
+}

document-ai/src/test/java/documentai/v1beta3/ProcessOcrDocumentTest.java → document-ai/src/test/java/documentai/v1/ProcessOcrDocumentTest.java

@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package documentai.v1beta3;
+package documentai.v1;
 
 import static com.google.common.truth.Truth.assertThat;
 import static org.junit.Assert.assertNotNull;
@@ -30,7 +30,9 @@
 
 public class ProcessOcrDocumentTest {
   private static final String PROJECT_ID = System.getenv("GOOGLE_CLOUD_PROJECT");
-  private static final String PROCESSOR_ID = "f9018d35bc5edc1e";
+  private static final String PROCESSOR_ID = System.getenv("DOCAI_OCR_PROCESSOR_ID") != null
+      ? System.getenv("DOCAI_OCR_PROCESSOR_ID")
+      : "f9018d35bc5edc1e";
   private static final String FILE_PATH = "resources/handwritten_form.pdf";
 
   private ByteArrayOutputStream bout;
@@ -60,7 +62,7 @@ public void setUp() {
   @Test
   public void testProcessOcrDocument()
       throws InterruptedException, ExecutionException, IOException, TimeoutException {
-    // parse the GCS invoice as a form.
+    // parse the document with OCR.
     ProcessOcrDocument.processOcrDocument(PROJECT_ID, "us", PROCESSOR_ID, FILE_PATH);
     String got = bout.toString();
 
@@ -74,4 +76,4 @@ public void tearDown() {
     System.out.flush();
     System.setOut(originalPrintStream);
   }
-}
+}

document-ai/src/test/java/documentai/v1beta3/ProcessSpecializedDocumentTest.java → document-ai/src/test/java/documentai/v1/ProcessSpecializedDocumentTest.java

@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package documentai.v1beta3;
+package documentai.v1;
 
 import static com.google.common.truth.Truth.assertThat;
 import static org.junit.Assert.assertNotNull;
@@ -30,7 +30,9 @@
 
 public class ProcessSpecializedDocumentTest {
   private static final String PROJECT_ID = System.getenv("GOOGLE_CLOUD_PROJECT");
-  private static final String PROCESSOR_ID = "ae8bc99f01b36b5e";
+  private static final String PROCESSOR_ID = System.getenv("DOCAI_SPECIALIZED_PROCESSOR_ID") != null
+      ? System.getenv("DOCAI_SPECIALIZED_PROCESSOR_ID")
+      : "ae8bc99f01b36b5e";
   private static final String FILE_PATH = "resources/us_driver_license.pdf";
 
   private ByteArrayOutputStream bout;
@@ -60,7 +62,7 @@ public void setUp() {
   @Test
   public void testProcessSpecializedDocument()
       throws InterruptedException, ExecutionException, IOException, TimeoutException {
-    // parse the GCS invoice as a form.
+    // parse the specialized document.
     ProcessSpecializedDocument.processSpecializedDocument(
         PROJECT_ID, "us", PROCESSOR_ID, FILE_PATH);
     String got = bout.toString();
@@ -74,4 +76,4 @@ public void tearDown() {
     System.out.flush();
     System.setOut(originalPrintStream);
   }
-}
+}

document-ai/src/test/java/documentai/v1beta3/ProcessSplitterDocumentTest.java → document-ai/src/test/java/documentai/v1/ProcessSplitterDocumentTest.java

@@ -14,7 +14,7 @@
  * limitations under the License.
  */
 
-package documentai.v1beta3;
+package documentai.v1;
 
 import static com.google.common.truth.Truth.assertThat;
 import static org.junit.Assert.assertNotNull;
@@ -26,11 +26,14 @@
 import java.util.concurrent.TimeoutException;
 import org.junit.After;
 import org.junit.Before;
+import org.junit.Ignore;
 import org.junit.Test;
 
 public class ProcessSplitterDocumentTest {
   private static final String PROJECT_ID = System.getenv("GOOGLE_CLOUD_PROJECT");
-  private static final String PROCESSOR_ID = "7cb010d65184a4d";
+  private static final String PROCESSOR_ID = System.getenv("DOCAI_SPLITTER_PROCESSOR_ID") != null
+      ? System.getenv("DOCAI_SPLITTER_PROCESSOR_ID")
+      : "7cb010d65184a4d";
   private static final String FILE_PATH = "resources/multi_document.pdf";
 
   private ByteArrayOutputStream bout;
@@ -46,7 +49,7 @@ private static void requireEnvVar(String varName) {
   @Before
   public void checkRequirements() {
     requireEnvVar("GOOGLE_CLOUD_PROJECT");
-    requireEnvVar("GOOGLE_APPLICATION_CREDENTIALS");
+    // requireEnvVar("GOOGLE_APPLICATION_CREDENTIALS");
   }
 
   @Before
@@ -58,9 +61,10 @@ public void setUp() {
   }
 
   @Test
+  @Ignore("ProcessorType DOCUMENT_SPLIT_PROCESSOR is deprecated by Google Cloud.")
   public void testProcessSplitterDocument()
       throws InterruptedException, ExecutionException, IOException, TimeoutException {
-    // parse the GCS invoice as a form.
+    // parse the multi-document with splitter processor.
     ProcessSplitterDocument.processSplitterDocument(PROJECT_ID, "us", PROCESSOR_ID, FILE_PATH);
     String got = bout.toString();
 
@@ -74,4 +78,4 @@ public void tearDown() {
     System.out.flush();
     System.setOut(originalPrintStream);
   }
-}
+}