Github user olegz commented on a diff in the pull request:
https://github.com/apache/nifi/pull/397#discussion_r65247502
--- Diff:
nifi-nar-bundles/nifi-ocr-bundle/nifi-ocr-processors/src/main/java/org/apache/nifi/processors/ocr/TesseractOCRProcessor.java
---
@@ -0,0 +1,359 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.nifi.processors.ocr;
+
+import java.awt.image.BufferedImage;
+import java.io.File;
+import java.io.FileFilter;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.OutputStream;
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+import java.util.concurrent.atomic.AtomicBoolean;
+
+import javax.imageio.ImageIO;
+
+import org.apache.commons.lang3.StringUtils;
+import org.apache.nifi.annotation.behavior.InputRequirement;
+import org.apache.nifi.annotation.documentation.CapabilityDescription;
+import org.apache.nifi.annotation.documentation.Tags;
+import org.apache.nifi.annotation.lifecycle.OnScheduled;
+import org.apache.nifi.components.AllowableValue;
+import org.apache.nifi.components.PropertyDescriptor;
+import org.apache.nifi.components.ValidationContext;
+import org.apache.nifi.components.ValidationResult;
+import org.apache.nifi.components.Validator;
+import org.apache.nifi.flowfile.FlowFile;
+import org.apache.nifi.processor.AbstractProcessor;
+import org.apache.nifi.processor.ProcessContext;
+import org.apache.nifi.processor.ProcessSession;
+import org.apache.nifi.processor.Relationship;
+import org.apache.nifi.processor.exception.ProcessException;
+import org.apache.nifi.processor.io.StreamCallback;
+import org.apache.nifi.processor.util.StandardValidators;
+
+import net.sourceforge.tess4j.ITesseract;
+import net.sourceforge.tess4j.Tesseract;
+import net.sourceforge.tess4j.TesseractException;
+
+@Tags({"ocr", "tesseract", "image", "text"})
+@InputRequirement(InputRequirement.Requirement.INPUT_REQUIRED)
+@CapabilityDescription("Extracts text from images using Optical Character
Recognition (OCR). The images are pulled from the incoming" +
+ " Flowfile's content. Supported image types are TIFF, JPEG, GIF,
PNG, BMP, and PDF. Any Flowfile that doesn't contain" +
+ " a supported image type in its content body will be routed to the
'unsupported image format' relationship and no OCR will be performed." +
+ " This processor uses Tesseract to perform its duties and part of
that requires that a valid Tesseract data (Tessdata) directory" +
+ " be specified in the 'Tessdata Directory' Property. This
processor considers a valid Tessdata directory to be an existing directory on
the" +
+ " local NiFi instance that contains one or more files ending with
the '.traineddata' extension. The list of supported languages" +
+ " is built from the Tessdata directory configured by listing all
files ending with '.traineddata' and considering those" +
+ " Tesseract language models. You can create you own Tesseract
language models and place them in your Tessedata directory" +
+ " and the processor will display it in the dropdown list of
languages available. All valid Tesseract configuration values" +
+ " may be passed to this processor by use of the 'Tesseract
configuration values' which accepts a comma separated list" +
+ " of key=value pairs representing Tesseract configurations.
'Tesseract configuration values' is where all of your tuning" +
+ " values can be passed in to help increase the accuracy of your
OCR operations based on your expected input images." +
+ " TesseractOCRProcessor only supports installations of Tesseract
version 3.0 and greater.")
+public class TesseractOCRProcessor extends AbstractProcessor {
+
+ public static Set<String> SUPPORTED_LANGUAGES;
+ private static final String TESS_LANG_EXTENSION = ".traineddata";
+ private static List<AllowableValue> PAGE_SEGMENTATION_MODES;
+ private static volatile ITesseract tesseract;
--- End diff --
I am not sure this should be static. Any reason?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
