OfficeParserConfig.java
/*
* 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.tika.parser.microsoft;
import java.io.Serializable;
public class OfficeParserConfig implements Serializable {
private boolean extractMacros = false;
private boolean includeDeletedContent = false;
private boolean includeMoveFromContent = false;
private boolean includeShapeBasedContent = true;
private boolean includeHeadersAndFooters = true;
private boolean includeMissingRows = false;
private boolean includeSlideNotes = true;
private boolean includeSlideMasterContent = true;
private boolean concatenatePhoneticRuns = true;
private boolean useSAXDocxExtractor = false;
private boolean useSAXPptxExtractor = false;
private boolean preferAlternateContentChoice = true;
private boolean writeSelectHeadersInBody = false;
/**
* Maximum bytes per embedded object/pict when extracting from RTF within
* MSG files. Since embedded data is streamed to disk (not held in memory),
* the default is 2 GB. Set to -1 for unlimited.
*/
private int rtfEmbeddedMaxBytesInKb = 2 * 1024 * 1024; // 2 GB
private boolean includeGlossary = true;
private String dateOverrideFormat = null;
private int maxOverride = 0;//ignore
/**
* @return whether or not to extract macros
*/
public boolean isExtractMacros() {
return extractMacros;
}
/**
* Sets whether or not MSOffice parsers should extract macros.
* As of Tika 1.15, the default is <code>false</code>.
*
* @param extractMacros
*/
public void setExtractMacros(boolean extractMacros) {
this.extractMacros = extractMacros;
}
public boolean isIncludeDeletedContent() {
return includeDeletedContent;
}
/**
* Sets whether or not the parser should include deleted content.
* <p/>
* <b>This has only been implemented in the streaming docx parser
* ({@link org.apache.tika.parser.microsoft.ooxml.SXWPFWordExtractorDecorator} so far!!!</b>
*
* @param includeDeletedContent
*/
public void setIncludeDeletedContent(boolean includeDeletedContent) {
this.includeDeletedContent = includeDeletedContent;
}
public boolean isIncludeMoveFromContent() {
return includeMoveFromContent;
}
/**
* With track changes on, when a section is moved, the content
* is stored in both the "moveFrom" section and in the "moveTo" section.
* <p/>
* If you'd like to include the section both in its original location (moveFrom)
* and in its new location (moveTo), set this to <code>true</code>
* <p/>
* Default: <code>false</code>
* <p/>
* <b>This has only been implemented in the streaming docx parser
* ({@link org.apache.tika.parser.microsoft.ooxml.SXWPFWordExtractorDecorator} so far!!!</b>
*
* @param includeMoveFromContent
*/
public void setIncludeMoveFromContent(boolean includeMoveFromContent) {
this.includeMoveFromContent = includeMoveFromContent;
}
public boolean isIncludeShapeBasedContent() {
return includeShapeBasedContent;
}
/**
* In Excel and Word, there can be text stored within drawing shapes.
* (In PowerPoint everything is in a Shape)
* <p/>
* If you'd like to skip processing these to look for text, set this to
* <code>false</code>
* <p/>
* Default: <code>true</code>
*
* @param includeShapeBasedContent
*/
public void setIncludeShapeBasedContent(boolean includeShapeBasedContent) {
this.includeShapeBasedContent = includeShapeBasedContent;
}
public boolean isIncludeHeadersAndFooters() {
return includeHeadersAndFooters;
}
/**
* Whether or not to include headers and footers.
* <p/>
* This only operates on headers and footers in Word and Excel,
* not master slide content in Powerpoint.
* <p/>
* Default: <code>true</code>
*
* @param includeHeadersAndFooters
*/
public void setIncludeHeadersAndFooters(boolean includeHeadersAndFooters) {
this.includeHeadersAndFooters = includeHeadersAndFooters;
}
public boolean isUseSAXDocxExtractor() {
return useSAXDocxExtractor;
}
/**
* Use the experimental SAX-based streaming DOCX parser?
* If set to <code>false</code>, the classic parser will be used; if <code>true</code>,
* the new experimental parser will be used.
* <p/>
* Default: <code>false</code> (classic DOM parser)
*
* @param useSAXDocxExtractor
*/
public void setUseSAXDocxExtractor(boolean useSAXDocxExtractor) {
this.useSAXDocxExtractor = useSAXDocxExtractor;
}
public boolean isUseSAXPptxExtractor() {
return useSAXPptxExtractor;
}
/**
* Use the experimental SAX-based streaming DOCX parser?
* If set to <code>false</code>, the classic parser will be used; if <code>true</code>,
* the new experimental parser will be used.
* <p/>
* Default: <code>false</code> (classic DOM parser)
*
* @param useSAXPptxExtractor
*/
public void setUseSAXPptxExtractor(boolean useSAXPptxExtractor) {
this.useSAXPptxExtractor = useSAXPptxExtractor;
}
/**
* In OOXML, {@code mc:AlternateContent} wraps {@code mc:Choice} (newer/richer
* rendering, e.g. DrawingML text boxes) and {@code mc:Fallback} (degraded VML
* for older consumers). When {@code true} (default), the SAX parser processes
* the Choice branch and skips Fallback. When {@code false}, it processes
* Fallback and skips Choice (legacy behavior prior to Tika 4.x).
* <p>
* For text extraction, Choice typically contains equal or more content than
* Fallback.
* <p>
* Default: {@code true}
*
* @return whether to prefer mc:Choice over mc:Fallback
*/
public boolean isPreferAlternateContentChoice() {
return preferAlternateContentChoice;
}
/**
* @param preferAlternateContentChoice whether to prefer mc:Choice over mc:Fallback
* @see #isPreferAlternateContentChoice()
*/
public void setPreferAlternateContentChoice(boolean preferAlternateContentChoice) {
this.preferAlternateContentChoice = preferAlternateContentChoice;
}
public boolean isConcatenatePhoneticRuns() {
return concatenatePhoneticRuns;
}
/**
* Microsoft Excel files can sometimes contain phonetic (furigana) strings.
* See <a href="https://support.office.com/en-us/article/PHONETIC-function-9a329dac-0c0f-42f8-9a55-639086988554">PHONETIC</a>.
* This sets whether or not the parser will concatenate the phonetic runs to the original text.
* <p>
* This is currently only supported by the xls and xlsx parsers (not the xlsb parser),
* and the default is <code>true</code>.
* </p>
*
* @param concatenatePhoneticRuns
*/
public void setConcatenatePhoneticRuns(boolean concatenatePhoneticRuns) {
this.concatenatePhoneticRuns = concatenatePhoneticRuns;
}
public boolean isIncludeGlossary() {
return includeGlossary;
}
/**
* Whether or not to include the glossary (building blocks / AutoText) document
* from docx files. The glossary can contain template content such as form field
* placeholders that may duplicate content already present in the main body.
* <p/>
* Default: <code>true</code>
*
* @param includeGlossary whether or not to include glossary content
*/
public void setIncludeGlossary(boolean includeGlossary) {
this.includeGlossary = includeGlossary;
}
public boolean isIncludeMissingRows() {
return includeMissingRows;
}
/**
* For table-like formats, and tables within other formats, should
* missing rows in sparse tables be output where detected?
* The default is to only output rows defined within the file, which
* avoid lots of blank lines, but means layout isn't preserved.
*/
public void setIncludeMissingRows(boolean includeMissingRows) {
this.includeMissingRows = includeMissingRows;
}
public boolean isIncludeSlideNotes() {
return includeSlideNotes;
}
/**
* Whether or not to process slide notes content. If set
* to <code>false</code>, the parser will skip the text content
* and all embedded objects from the slide notes in ppt and ppt[xm].
* The default is <code>true</code>.
*
* @param includeSlideNotes whether or not to process slide notes
* @since 1.19.1
*/
public void setIncludeSlideNotes(boolean includeSlideNotes) {
this.includeSlideNotes = includeSlideNotes;
}
/**
* @return whether or not to process content in slide masters
* @since 1.19.1
*/
public boolean isIncludeSlideMasterContent() {
return includeSlideMasterContent;
}
/**
* Whether or not to include contents from any of the three
* types of masters -- slide, notes, handout -- in a .ppt or ppt[xm] file.
* If set to <code>false</code>, the parser will not extract
* text or embedded objects from any of the masters.
*
* @param includeSlideMasterContent
* @since 1.19.1
*/
public void setIncludeSlideMasterContent(boolean includeSlideMasterContent) {
this.includeSlideMasterContent = includeSlideMasterContent;
}
public String getDateFormatOverride() {
return dateOverrideFormat;
}
/**
* A user may wish to override the date formats in xls and xlsx files.
* For example, a user might prefer 'yyyy-mm-dd' to 'mm/dd/yy'.
* <p>
* Note: these formats are "Excel formats" not Java's SimpleDateFormat
*
* @param format
*/
public void setDateOverrideFormat(String format) {
this.dateOverrideFormat = format;
}
public void setMaxOverride(int maxOverride) {
this.maxOverride = maxOverride;
}
public int getMaxOverride() {
return this.maxOverride;
}
/**
* The default changed to <code>false</code> in 4.x. For legacy 3.x behavior,
* set this to <code>true</code>.
* @return
*/
public boolean isWriteSelectHeadersInBody() {
return writeSelectHeadersInBody;
}
public void setWriteSelectHeadersInBody(boolean writeSelectHeadersInBody) {
this.writeSelectHeadersInBody = writeSelectHeadersInBody;
}
/**
* Maximum bytes (in KB) per embedded object/pict when extracting from RTF
* within MSG files. Data is streamed to disk, so the default is 2 GB.
* Set to -1 for unlimited.
*/
public int getRtfEmbeddedMaxBytesInKb() {
return rtfEmbeddedMaxBytesInKb;
}
public void setRtfEmbeddedMaxBytesInKb(int rtfEmbeddedMaxBytesInKb) {
this.rtfEmbeddedMaxBytesInKb = rtfEmbeddedMaxBytesInKb;
}
}