update ingest-attachment to use Tika 1.17 and newer deps

plugins/ingest-attachment/licenses/apache-mime4j-core-0.8.1.jar.sha1

@@ -0,0 +1 @@
+c62dfe18a3b827a2c626ade0ffba44562ddf3f61

plugins/ingest-attachment/licenses/apache-mime4j-dom-0.8.1.jar.sha1

@@ -0,0 +1 @@
+f2d653c617004193f3350330d907f77b60c88c56

plugins/ingest-attachment/licenses/commons-io-2.5.jar.sha1

@@ -0,0 +1 @@
+2852e6e05fbb95076fc091f6d1780f1f8fe35e0f

plugins/ingest-attachment/licenses/fontbox-2.0.8.jar.sha1

@@ -0,0 +1 @@
+52f852fcfc7481d45efdffd224eb78b85981b17b

plugins/ingest-attachment/licenses/jempbox-1.8.13.jar.sha1

@@ -0,0 +1 @@
+a874cef0ed0e2a8c4cc5ed52c23ba3e6d78eca4e

plugins/ingest-attachment/licenses/pdfbox-2.0.8.jar.sha1

@@ -0,0 +1 @@
+17bdf273d66f3afe41eedb9d3ab6a7b819c44a0c

plugins/ingest-attachment/licenses/poi-3.17.jar.sha1

@@ -0,0 +1 @@
+0ae92292a2043888b40d418da97dc0b669fde326

plugins/ingest-attachment/licenses/poi-ooxml-3.17.jar.sha1

@@ -0,0 +1 @@
+07d8c44407178b73246462842bf1e206e99c8e0a

plugins/ingest-attachment/licenses/poi-ooxml-schemas-3.17.jar.sha1

@@ -0,0 +1 @@
+890114bfa82f5b6380ea0e9b0bf49b0af797b414

plugins/ingest-attachment/licenses/poi-scratchpad-3.17.jar.sha1

@@ -0,0 +1 @@
+85d86a0e26c7f5c0db4ee63e8c7728e51c5d64ce

plugins/ingest-attachment/licenses/tika-core-1.17.jar.sha1

@@ -0,0 +1 @@
+b450102c2aee98107474d2f92661d947b9cef183

plugins/ingest-attachment/licenses/tika-parsers-1.17.jar.sha1

@@ -0,0 +1 @@
+4277c54fcaed542fbc8a0001fdb4c23baccc0132

plugins/ingest-attachment/src/main/java/org/elasticsearch/ingest/attachment/AttachmentProcessor.java

@@ -19,6 +19,7 @@
 
 package org.elasticsearch.ingest.attachment;
 
+import org.apache.tika.exception.ZeroByteFileException;
 import org.apache.tika.language.LanguageIdentifier;
 import org.apache.tika.metadata.Metadata;
 import org.apache.tika.metadata.TikaCoreProperties;
@@ -81,68 +82,72 @@ public void execute(IngestDocument ingestDocument) {
             throw new IllegalArgumentException("field [" + field + "] is null, cannot parse.");
         }
 
+        Metadata metadata = new Metadata();
+        String parsedContent = "";
         try {
-            Metadata metadata = new Metadata();
-            String parsedContent = TikaImpl.parse(input, metadata, indexedChars);
+            parsedContent = TikaImpl.parse(input, metadata, indexedChars);
+        } catch (ZeroByteFileException e) {
+            // tika 1.17 throws an exception when the InputStream has 0 bytes.
+            // previously, it did not mind. This is here to preserve that behavior.
+        } catch (Exception e) {
+            throw new ElasticsearchParseException("Error parsing document in field [{}]", e, field);
+        }
 
-            if (properties.contains(Property.CONTENT) && Strings.hasLength(parsedContent)) {
-                // somehow tika seems to append a newline at the end automatically, lets remove that again
-                additionalFields.put(Property.CONTENT.toLowerCase(), parsedContent.trim());
-            }
+        if (properties.contains(Property.CONTENT) && Strings.hasLength(parsedContent)) {
+            // somehow tika seems to append a newline at the end automatically, lets remove that again
+            additionalFields.put(Property.CONTENT.toLowerCase(), parsedContent.trim());
+        }
 
-            if (properties.contains(Property.LANGUAGE) && Strings.hasLength(parsedContent)) {
-                LanguageIdentifier identifier = new LanguageIdentifier(parsedContent);
-                String language = identifier.getLanguage();
-                additionalFields.put(Property.LANGUAGE.toLowerCase(), language);
-            }
+        if (properties.contains(Property.LANGUAGE) && Strings.hasLength(parsedContent)) {
+            LanguageIdentifier identifier = new LanguageIdentifier(parsedContent);
+            String language = identifier.getLanguage();
+            additionalFields.put(Property.LANGUAGE.toLowerCase(), language);
+        }
 
-            if (properties.contains(Property.DATE)) {
-                String createdDate = metadata.get(TikaCoreProperties.CREATED);
-                if (createdDate != null) {
-                    additionalFields.put(Property.DATE.toLowerCase(), createdDate);
-                }
+        if (properties.contains(Property.DATE)) {
+            String createdDate = metadata.get(TikaCoreProperties.CREATED);
+            if (createdDate != null) {
+                additionalFields.put(Property.DATE.toLowerCase(), createdDate);
             }
+        }
 
-            if (properties.contains(Property.TITLE)) {
-                String title = metadata.get(TikaCoreProperties.TITLE);
-                if (Strings.hasLength(title)) {
-                    additionalFields.put(Property.TITLE.toLowerCase(), title);
-                }
+        if (properties.contains(Property.TITLE)) {
+            String title = metadata.get(TikaCoreProperties.TITLE);
+            if (Strings.hasLength(title)) {
+                additionalFields.put(Property.TITLE.toLowerCase(), title);
             }
+        }
 
-            if (properties.contains(Property.AUTHOR)) {
-                String author = metadata.get("Author");
-                if (Strings.hasLength(author)) {
-                    additionalFields.put(Property.AUTHOR.toLowerCase(), author);
-                }
+        if (properties.contains(Property.AUTHOR)) {
+            String author = metadata.get("Author");
+            if (Strings.hasLength(author)) {
+                additionalFields.put(Property.AUTHOR.toLowerCase(), author);
             }
+        }
 
-            if (properties.contains(Property.KEYWORDS)) {
-                String keywords = metadata.get("Keywords");
-                if (Strings.hasLength(keywords)) {
-                    additionalFields.put(Property.KEYWORDS.toLowerCase(), keywords);
-                }
+        if (properties.contains(Property.KEYWORDS)) {
+            String keywords = metadata.get("Keywords");
+            if (Strings.hasLength(keywords)) {
+                additionalFields.put(Property.KEYWORDS.toLowerCase(), keywords);
             }
+        }
 
-            if (properties.contains(Property.CONTENT_TYPE)) {
-                String contentType = metadata.get(Metadata.CONTENT_TYPE);
-                if (Strings.hasLength(contentType)) {
-                    additionalFields.put(Property.CONTENT_TYPE.toLowerCase(), contentType);
-                }
+        if (properties.contains(Property.CONTENT_TYPE)) {
+            String contentType = metadata.get(Metadata.CONTENT_TYPE);
+            if (Strings.hasLength(contentType)) {
+                additionalFields.put(Property.CONTENT_TYPE.toLowerCase(), contentType);
             }
+        }
 
-            if (properties.contains(Property.CONTENT_LENGTH)) {
-                String contentLength = metadata.get(Metadata.CONTENT_LENGTH);
-                long length;
-                if (Strings.hasLength(contentLength)) {
-                    length = Long.parseLong(contentLength);
-                } else {
-                    length = parsedContent.length();
-                }
-                additionalFields.put(Property.CONTENT_LENGTH.toLowerCase(), length);
+        if (properties.contains(Property.CONTENT_LENGTH)) {
+            String contentLength = metadata.get(Metadata.CONTENT_LENGTH);
+            long length;
+            if (Strings.hasLength(contentLength)) {
+                length = Long.parseLong(contentLength);
+            } else {
+                length = parsedContent.length();
             }
-        } catch (Exception e) {
-            throw new ElasticsearchParseException("Error parsing document in field [{}]", e, field);
+            additionalFields.put(Property.CONTENT_LENGTH.toLowerCase(), length);
         }
 
         ingestDocument.setFieldValue(targetField, additionalFields);