Skip to content

Commit e07ba24

Browse files
Matt Carrollgcf-owl-bot[bot]
authored and
Shabirmean
committed
docs(samples): add OCR, form, quality, splitter and specialized processing samples (#680)
* docs(samples): add OCR, form, quality, splitter and specialized processing samples * 🦉 Updates from OwlBot See https://github.com/googleapis/repo-automation-bots/blob/main/packages/owl-bot/README.md Co-authored-by: Owl Bot <gcf-owl-bot[bot]@users.noreply.github.com>
1 parent 6445f9c commit e07ba24

14 files changed

+1023
-0
lines changed

‎document-ai/snippets/resources/document_quality_poor.pdf

616 KB
Binary file not shown.

‎document-ai/snippets/resources/handwritten_form.pdf

624 KB
Binary file not shown.

‎document-ai/snippets/resources/multi_document.pdf

3.01 MB
Binary file not shown.

‎document-ai/snippets/resources/us_driver_license.pdf

610 KB
Binary file not shown.

‎document-ai/snippets/src/main/java/documentai/v1beta3/ProcessFormDocument.java

Lines changed: 149 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,149 @@
1+
/*
2+
* Copyright 2020 Google LLC
3+
*
4+
* Licensed under the Apache License, Version 2.0 (the "License");
5+
* you may not use this file except in compliance with the License.
6+
* You may obtain a copy of the License at
7+
*
8+
* http://www.apache.org/licenses/LICENSE-2.0
9+
*
10+
* Unless required by applicable law or agreed to in writing, software
11+
* distributed under the License is distributed on an "AS IS" BASIS,
12+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13+
* See the License for the specific language governing permissions and
14+
* limitations under the License.
15+
*/
16+
17+
package documentai.v1beta3;
18+
19+
// [START documentai_process_form_document]
20+
21+
import com.google.cloud.documentai.v1beta3.Document;
22+
import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceClient;
23+
import com.google.cloud.documentai.v1beta3.ProcessRequest;
24+
import com.google.cloud.documentai.v1beta3.ProcessResponse;
25+
import com.google.cloud.documentai.v1beta3.RawDocument;
26+
import com.google.protobuf.ByteString;
27+
import java.io.IOException;
28+
import java.nio.file.Files;
29+
import java.nio.file.Paths;
30+
import java.util.List;
31+
import java.util.concurrent.ExecutionException;
32+
import java.util.concurrent.TimeoutException;
33+
34+
public class ProcessFormDocument {
35+
public static void processFormDocument()
36+
throws IOException, InterruptedException, ExecutionException, TimeoutException {
37+
// TODO(developer): Replace these variables before running the sample.
38+
String projectId = "your-project-id";
39+
String location = "your-project-location"; // Format is "us" or "eu".
40+
String processerId = "your-processor-id";
41+
String filePath = "path/to/input/file.pdf";
42+
processFormDocument(projectId, location, processerId, filePath);
43+
}
44+
45+
public static void processFormDocument(
46+
String projectId, String location, String processorId, String filePath)
47+
throws IOException, InterruptedException, ExecutionException, TimeoutException {
48+
// Initialize client that will be used to send requests. This client only needs to be created
49+
// once, and can be reused for multiple requests. After completing all of your requests, call
50+
// the "close" method on the client to safely clean up any remaining background resources.
51+
try (DocumentProcessorServiceClient client = DocumentProcessorServiceClient.create()) {
52+
// The full resource name of the processor, e.g.:
53+
// projects/project-id/locations/location/processor/processor-id
54+
// You must create new processors in the Cloud Console first
55+
String name =
56+
String.format("projects/%s/locations/%s/processors/%s", projectId, location, processorId);
57+
58+
// Read the file.
59+
byte[] imageFileData = Files.readAllBytes(Paths.get(filePath));
60+
61+
// Convert the image data to a Buffer and base64 encode it.
62+
ByteString content = ByteString.copyFrom(imageFileData);
63+
64+
RawDocument document =
65+
RawDocument.newBuilder().setContent(content).setMimeType("application/pdf").build();
66+
67+
// Configure the process request.
68+
ProcessRequest request =
69+
ProcessRequest.newBuilder().setName(name).setRawDocument(document).build();
70+
71+
// Recognizes text entities in the PDF document
72+
ProcessResponse result = client.processDocument(request);
73+
Document documentResponse = result.getDocument();
74+
75+
System.out.println("Document processing complete.");
76+
77+
// Read the text recognition output from the processor
78+
// For a full list of Document object attributes,
79+
// please reference this page:
80+
// https://googleapis.dev/java/google-cloud-document-ai/latest/index.html
81+
82+
// Get all of the document text as one big string
83+
String text = documentResponse.getText();
84+
System.out.printf("Full document text: '%s'\n", removeNewlines(text));
85+
86+
// Read the text recognition output from the processor
87+
List<Document.Page> pages = documentResponse.getPagesList();
88+
System.out.printf("There are %s page(s) in this document.\n", pages.size());
89+
90+
for (Document.Page page : pages) {
91+
System.out.printf("\n\n**** Page %d ****\n", page.getPageNumber());
92+
93+
List<Document.Page.Table> tables = page.getTablesList();
94+
System.out.printf("Found %d table(s):\n", tables.size());
95+
for (Document.Page.Table table : tables) {
96+
printTableInfo(table, text);
97+
}
98+
99+
List<Document.Page.FormField> formFields = page.getFormFieldsList();
100+
System.out.printf("Found %d form fields:\n", formFields.size());
101+
for (Document.Page.FormField formField : formFields) {
102+
String fieldName = getLayoutText(formField.getFieldName().getTextAnchor(), text);
103+
String fieldValue = getLayoutText(formField.getFieldValue().getTextAnchor(), text);
104+
System.out.printf(
105+
" * '%s': '%s'\n", removeNewlines(fieldName), removeNewlines(fieldValue));
106+
}
107+
}
108+
}
109+
}
110+
111+
private static void printTableInfo(Document.Page.Table table, String text) {
112+
Document.Page.Table.TableRow firstBodyRow = table.getBodyRows(0);
113+
int columnCount = firstBodyRow.getCellsCount();
114+
System.out.printf(
115+
" Table with %d columns and %d rows:\n", columnCount, table.getBodyRowsCount());
116+
117+
Document.Page.Table.TableRow headerRow = table.getHeaderRows(0);
118+
StringBuilder headerRowText = new StringBuilder();
119+
for (Document.Page.Table.TableCell cell : headerRow.getCellsList()) {
120+
String columnName = getLayoutText(cell.getLayout().getTextAnchor(), text);
121+
headerRowText.append(String.format("%s | ", removeNewlines(columnName)));
122+
}
123+
headerRowText.setLength(headerRowText.length() - 3);
124+
System.out.printf(" Collumns: %s\n", headerRowText.toString());
125+
126+
StringBuilder firstRowText = new StringBuilder();
127+
for (Document.Page.Table.TableCell cell : firstBodyRow.getCellsList()) {
128+
String cellText = getLayoutText(cell.getLayout().getTextAnchor(), text);
129+
firstRowText.append(String.format("%s | ", removeNewlines(cellText)));
130+
}
131+
firstRowText.setLength(firstRowText.length() - 3);
132+
System.out.printf(" First row data: %s\n", firstRowText.toString());
133+
}
134+
135+
// Extract shards from the text field
136+
private static String getLayoutText(Document.TextAnchor textAnchor, String text) {
137+
if (textAnchor.getTextSegmentsList().size() > 0) {
138+
int startIdx = (int) textAnchor.getTextSegments(0).getStartIndex();
139+
int endIdx = (int) textAnchor.getTextSegments(0).getEndIndex();
140+
return text.substring(startIdx, endIdx);
141+
}
142+
return "[NO TEXT]";
143+
}
144+
145+
private static String removeNewlines(String s) {
146+
return s.replace("\n", "").replace("\r", "");
147+
}
148+
}
149+
// [END documentai_process_form_document]

‎document-ai/snippets/src/main/java/documentai/v1beta3/ProcessOcrDocument.java

Lines changed: 172 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,172 @@
1+
/*
2+
* Copyright 2020 Google LLC
3+
*
4+
* Licensed under the Apache License, Version 2.0 (the "License");
5+
* you may not use this file except in compliance with the License.
6+
* You may obtain a copy of the License at
7+
*
8+
* http://www.apache.org/licenses/LICENSE-2.0
9+
*
10+
* Unless required by applicable law or agreed to in writing, software
11+
* distributed under the License is distributed on an "AS IS" BASIS,
12+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13+
* See the License for the specific language governing permissions and
14+
* limitations under the License.
15+
*/
16+
17+
package documentai.v1beta3;
18+
19+
// [START documentai_process_ocr_document]
20+
21+
import com.google.cloud.documentai.v1beta3.Document;
22+
import com.google.cloud.documentai.v1beta3.DocumentProcessorServiceClient;
23+
import com.google.cloud.documentai.v1beta3.ProcessRequest;
24+
import com.google.cloud.documentai.v1beta3.ProcessResponse;
25+
import com.google.cloud.documentai.v1beta3.RawDocument;
26+
import com.google.protobuf.ByteString;
27+
import java.io.IOException;
28+
import java.nio.file.Files;
29+
import java.nio.file.Paths;
30+
import java.util.List;
31+
import java.util.concurrent.ExecutionException;
32+
import java.util.concurrent.TimeoutException;
33+
34+
public class ProcessOcrDocument {
35+
public static void processOcrDocument()
36+
throws IOException, InterruptedException, ExecutionException, TimeoutException {
37+
// TODO(developer): Replace these variables before running the sample.
38+
String projectId = "your-project-id";
39+
String location = "your-project-location"; // Format is "us" or "eu".
40+
String processerId = "your-processor-id";
41+
String filePath = "path/to/input/file.pdf";
42+
processOcrDocument(projectId, location, processerId, filePath);
43+
}
44+
45+
public static void processOcrDocument(
46+
String projectId, String location, String processorId, String filePath)
47+
throws IOException, InterruptedException, ExecutionException, TimeoutException {
48+
// Initialize client that will be used to send requests. This client only needs to be created
49+
// once, and can be reused for multiple requests. After completing all of your requests, call
50+
// the "close" method on the client to safely clean up any remaining background resources.
51+
try (DocumentProcessorServiceClient client = DocumentProcessorServiceClient.create()) {
52+
// The full resource name of the processor, e.g.:
53+
// projects/project-id/locations/location/processor/processor-id
54+
// You must create new processors in the Cloud Console first
55+
String name =
56+
String.format("projects/%s/locations/%s/processors/%s", projectId, location, processorId);
57+
58+
// Read the file.
59+
byte[] imageFileData = Files.readAllBytes(Paths.get(filePath));
60+
61+
// Convert the image data to a Buffer and base64 encode it.
62+
ByteString content = ByteString.copyFrom(imageFileData);
63+
64+
RawDocument document =
65+
RawDocument.newBuilder().setContent(content).setMimeType("application/pdf").build();
66+
67+
// Configure the process request.
68+
ProcessRequest request =
69+
ProcessRequest.newBuilder().setName(name).setRawDocument(document).build();
70+
71+
// Recognizes text entities in the PDF document
72+
ProcessResponse result = client.processDocument(request);
73+
Document documentResponse = result.getDocument();
74+
75+
System.out.println("Document processing complete.");
76+
77+
// Read the text recognition output from the processor
78+
// For a full list of Document object attributes,
79+
// please reference this page:
80+
// https://googleapis.dev/java/google-cloud-document-ai/latest/index.html
81+
82+
// Get all of the document text as one big string
83+
String text = documentResponse.getText();
84+
System.out.printf("Full document text: '%s'\n", escapeNewlines(text));
85+
86+
// Read the text recognition output from the processor
87+
List<Document.Page> pages = documentResponse.getPagesList();
88+
System.out.printf("There are %s page(s) in this document.\n", pages.size());
89+
90+
for (Document.Page page : pages) {
91+
System.out.printf("Page %d:\n", page.getPageNumber());
92+
printPageDimensions(page.getDimension());
93+
printDetectedLanguages(page.getDetectedLanguagesList());
94+
printParagraphs(page.getParagraphsList(), text);
95+
printBlocks(page.getBlocksList(), text);
96+
printLines(page.getLinesList(), text);
97+
printTokens(page.getTokensList(), text);
98+
}
99+
}
100+
}
101+
102+
private static void printPageDimensions(Document.Page.Dimension dimension) {
103+
String unit = dimension.getUnit();
104+
System.out.printf(" Width: %.1f %s\n", dimension.getWidth(), unit);
105+
System.out.printf(" Height: %.1f %s\n", dimension.getHeight(), unit);
106+
}
107+
108+
private static void printDetectedLanguages(
109+
List<Document.Page.DetectedLanguage> detectedLangauges) {
110+
System.out.println(" Detected languages:");
111+
for (Document.Page.DetectedLanguage detectedLanguage : detectedLangauges) {
112+
String languageCode = detectedLanguage.getLanguageCode();
113+
float confidence = detectedLanguage.getConfidence();
114+
System.out.printf(" %s (%.2f%%)\n", languageCode, confidence * 100.0);
115+
}
116+
}
117+
118+
private static void printParagraphs(List<Document.Page.Paragraph> paragraphs, String text) {
119+
System.out.printf(" %d paragraphs detected:\n", paragraphs.size());
120+
Document.Page.Paragraph firstParagraph = paragraphs.get(0);
121+
String firstParagraphText = getLayoutText(firstParagraph.getLayout().getTextAnchor(), text);
122+
System.out.printf(" First paragraph text: %s\n", escapeNewlines(firstParagraphText));
123+
Document.Page.Paragraph lastParagraph = paragraphs.get(paragraphs.size() - 1);
124+
String lastParagraphText = getLayoutText(lastParagraph.getLayout().getTextAnchor(), text);
125+
System.out.printf(" Last paragraph text: %s\n", escapeNewlines(lastParagraphText));
126+
}
127+
128+
private static void printBlocks(List<Document.Page.Block> blocks, String text) {
129+
System.out.printf(" %d blocks detected:\n", blocks.size());
130+
Document.Page.Block firstBlock = blocks.get(0);
131+
String firstBlockText = getLayoutText(firstBlock.getLayout().getTextAnchor(), text);
132+
System.out.printf(" First block text: %s\n", escapeNewlines(firstBlockText));
133+
Document.Page.Block lastBlock = blocks.get(blocks.size() - 1);
134+
String lastBlockText = getLayoutText(lastBlock.getLayout().getTextAnchor(), text);
135+
System.out.printf(" Last block text: %s\n", escapeNewlines(lastBlockText));
136+
}
137+
138+
private static void printLines(List<Document.Page.Line> lines, String text) {
139+
System.out.printf(" %d lines detected:\n", lines.size());
140+
Document.Page.Line firstLine = lines.get(0);
141+
String firstLineText = getLayoutText(firstLine.getLayout().getTextAnchor(), text);
142+
System.out.printf(" First line text: %s\n", escapeNewlines(firstLineText));
143+
Document.Page.Line lastLine = lines.get(lines.size() - 1);
144+
String lastLineText = getLayoutText(lastLine.getLayout().getTextAnchor(), text);
145+
System.out.printf(" Last line text: %s\n", escapeNewlines(lastLineText));
146+
}
147+
148+
private static void printTokens(List<Document.Page.Token> tokens, String text) {
149+
System.out.printf(" %d tokens detected:\n", tokens.size());
150+
Document.Page.Token firstToken = tokens.get(0);
151+
String firstTokenText = getLayoutText(firstToken.getLayout().getTextAnchor(), text);
152+
System.out.printf(" First token text: %s\n", escapeNewlines(firstTokenText));
153+
Document.Page.Token lastToken = tokens.get(tokens.size() - 1);
154+
String lastTokenText = getLayoutText(lastToken.getLayout().getTextAnchor(), text);
155+
System.out.printf(" Last token text: %s\n", escapeNewlines(lastTokenText));
156+
}
157+
158+
// Extract shards from the text field
159+
private static String getLayoutText(Document.TextAnchor textAnchor, String text) {
160+
if (textAnchor.getTextSegmentsList().size() > 0) {
161+
int startIdx = (int) textAnchor.getTextSegments(0).getStartIndex();
162+
int endIdx = (int) textAnchor.getTextSegments(0).getEndIndex();
163+
return text.substring(startIdx, endIdx);
164+
}
165+
return "[NO TEXT]";
166+
}
167+
168+
private static String escapeNewlines(String s) {
169+
return s.replace("\n", "\\n").replace("\r", "\\r");
170+
}
171+
}
172+
// [END documentai_process_ocr_document]

0 commit comments

Comments
 (0)