List of usage examples for org.apache.pdfbox.cos COSDictionary keySet
public Set<COSName> keySet()
From source file:org.apache.padaf.preflight.font.Type3FontValidator.java
License:Apache License
/** * If the Resources entry is present, this method check its content. Only * fonts and Images are checked because this resource describes glyphs. REMARK * : The font and the image aren't validated because they will be validated by * an other ValidationHelper./*from w ww .ja v a2 s . co m*/ * * @return */ private boolean checkResources() throws ValidationException { if (this.resources == null) { // ---- No resources dictionary. return true; } COSDocument cDoc = this.handler.getDocument().getDocument(); COSDictionary dictionary = COSUtils.getAsDictionary(this.resources, cDoc); if (dictionary == null) { this.fontContainer.addError(new ValidationError(ERROR_FONTS_DICTIONARY_INVALID, "The Resources element isn't a dictionary")); return false; } COSBase cbImg = dictionary.getItem(COSName.getPDFName(DICTIONARY_KEY_XOBJECT)); COSBase cbFont = dictionary.getItem(COSName.getPDFName(DICTIONARY_KEY_FONT)); if (cbImg != null) { // ---- the referenced objects must be present in the PDF file COSDictionary dicImgs = COSUtils.getAsDictionary(cbImg, cDoc); Set<COSName> keyList = dicImgs.keySet(); for (Object key : keyList) { COSBase item = dictionary.getItem((COSName) key); COSDictionary xObjImg = COSUtils.getAsDictionary(item, cDoc); if (xObjImg == null) { this.fontContainer.addError(new ValidationError(ERROR_FONTS_DICTIONARY_INVALID, "The Resources dictionary of type 3 font is invalid")); return false; } if (!XOBJECT_DICTIONARY_VALUE_SUBTYPE_IMG .equals(xObjImg.getString(COSName.getPDFName(DICTIONARY_KEY_SUBTYPE)))) { this.fontContainer.addError(new ValidationError(ERROR_FONTS_DICTIONARY_INVALID, "The Resources dictionary of type 3 font is invalid")); return false; } } } if (cbFont != null) { // ---- the referenced object must be present in the PDF file COSDictionary dicFonts = COSUtils.getAsDictionary(cbFont, cDoc); Set<COSName> keyList = dicFonts.keySet(); for (Object key : keyList) { COSBase item = dictionary.getItem((COSName) key); COSDictionary xObjFont = COSUtils.getAsDictionary(item, cDoc); if (xObjFont == null) { this.fontContainer.addError(new ValidationError(ERROR_FONTS_DICTIONARY_INVALID, "The Resources dictionary of type 3 font is invalid")); return false; } if (!FONT_DICTIONARY_VALUE_FONT .equals(xObjFont.getString(COSName.getPDFName(DICTIONARY_KEY_TYPE)))) { this.fontContainer.addError(new ValidationError(ERROR_FONTS_DICTIONARY_INVALID, "The Resources dictionary of type 3 font is invalid")); return false; } try { PDFont aFont = PDFontFactory.createFont(xObjFont); // FontContainer aContainer = this.handler.retrieveFontContainer(aFont); AbstractFontContainer aContainer = this.handler.getFont(aFont.getCOSObject()); // ---- another font is used in the Type3, check if the font is valid. if (aContainer.isValid() != State.VALID) { this.fontContainer.addError(new ValidationError(ERROR_FONTS_TYPE3_DAMAGED, "The Resources dictionary of type 3 font contains invalid font")); return false; } } catch (IOException e) { throw new ValidationException("Unable to valid the Type3 : " + e.getMessage()); } } } List<ValidationError> errors = new ArrayList<ValidationError>(); ExtGStateContainer extGStates = new ExtGStateContainer(dictionary, cDoc); boolean res = extGStates.validateTransparencyRules(errors); for (ValidationError err : errors) { this.fontContainer.addError(err); } return res && validateShadingPattern(dictionary, errors); }
From source file:org.apache.pdflens.views.treeview.PDFTreeModel.java
License:Apache License
/** * Returns the child of <code>parent</code> at index <code>index</code> * in the parent's// w w w .j a v a 2s.co m * child array. <code>parent</code> must be a node previously obtained * from this data source. This should not return <code>null</code> * if <code>index</code> * is a valid index for <code>parent</code> (that is <code>index >= 0 && * index < getChildCount(parent</code>)). * * @param parent a node in the tree, obtained from this data source * @param index The index into the parent object to location the child object. * @return the child of <code>parent</code> at index <code>index</code> * */ public Object getChild(Object parent, int index) { Object retval = null; if (parent instanceof COSArray) { ArrayEntry entry = new ArrayEntry(); entry.setIndex(index); entry.setValue(((COSArray) parent).getObject(index)); retval = entry; } else if (parent instanceof COSDictionary) { COSDictionary dict = ((COSDictionary) parent); List<COSName> keys = new ArrayList<COSName>(dict.keySet()); Collections.sort(keys); Object key = keys.get(index); Object value = dict.getDictionaryObject((COSName) key); MapEntry entry = new MapEntry(); entry.setKey(key); entry.setValue(value); retval = entry; } else if (parent instanceof MapEntry) { retval = getChild(((MapEntry) parent).getValue(), index); } else if (parent instanceof ArrayEntry) { retval = getChild(((ArrayEntry) parent).getValue(), index); } else if (parent instanceof COSDocument) { retval = ((COSDocument) parent).getObjects().get(index); } else if (parent instanceof COSObject) { retval = ((COSObject) parent).getObject(); } else { throw new RuntimeException("Unknown COS type " + parent.getClass().getName()); } return retval; }
From source file:org.apache.pdflens.views.treeview.PDFTreeModel.java
License:Apache License
/** Returns the index of child in parent. If <code>parent</code> * is <code>null</code> or <code>child</code> is <code>null</code>, * returns -1.//from w w w . j a va 2 s. c om * * @param parent a note in the tree, obtained from this data source * @param child the node we are interested in * @return the index of the child in the parent, or -1 if either * <code>child</code> or <code>parent</code> are <code>null</code> * */ public int getIndexOfChild(Object parent, Object child) { int retval = -1; if (parent != null && child != null) { if (parent instanceof COSArray) { COSArray array = (COSArray) parent; if (child instanceof ArrayEntry) { ArrayEntry arrayEntry = (ArrayEntry) child; retval = arrayEntry.getIndex(); } else { retval = array.indexOf((COSBase) child); } } else if (parent instanceof COSDictionary) { MapEntry entry = (MapEntry) child; COSDictionary dict = (COSDictionary) parent; List<COSName> keys = new ArrayList<COSName>(dict.keySet()); Collections.sort(keys); for (int i = 0; retval == -1 && i < keys.size(); i++) { if (keys.get(i).equals(entry.getKey())) { retval = i; } } } else if (parent instanceof MapEntry) { retval = getIndexOfChild(((MapEntry) parent).getValue(), child); } else if (parent instanceof ArrayEntry) { retval = getIndexOfChild(((ArrayEntry) parent).getValue(), child); } else if (parent instanceof COSDocument) { retval = ((COSDocument) parent).getObjects().indexOf(child); } else if (parent instanceof COSObject) { retval = 0; } else { throw new RuntimeException("Unknown COS type " + parent.getClass().getName()); } } return retval; }
From source file:org.apache.tika.parser.pdf.EnhancedPDFParser.java
License:Apache License
@SuppressWarnings("deprecation") private void extractMetadata(PDDocument document, Metadata metadata) throws TikaException { XMPMetadata xmp = null;//from w ww .j a v a 2 s. c o m XMPSchemaDublinCore dcSchema = null; try { if (document.getDocumentCatalog().getMetadata() != null) { xmp = XMPMetadata.load(document.getDocumentCatalog().getMetadata().exportXMPMetadata()); } if (xmp != null) { dcSchema = xmp.getDublinCoreSchema(); } } catch (IOException e) { //swallow } PDDocumentInformation info = document.getDocumentInformation(); metadata.set(PagedText.N_PAGES, document.getNumberOfPages()); extractMultilingualItems(metadata, TikaCoreProperties.TITLE, info.getTitle(), dcSchema); extractDublinCoreListItems(metadata, TikaCoreProperties.CREATOR, info.getAuthor(), dcSchema); extractDublinCoreListItems(metadata, TikaCoreProperties.CONTRIBUTOR, null, dcSchema); addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator()); addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords()); addMetadata(metadata, "producer", info.getProducer()); extractMultilingualItems(metadata, TikaCoreProperties.DESCRIPTION, null, dcSchema); // TODO: Move to description in Tika 2.0 addMetadata(metadata, TikaCoreProperties.TRANSITION_SUBJECT_TO_OO_SUBJECT, info.getSubject()); addMetadata(metadata, "trapped", info.getTrapped()); // TODO Remove these in Tika 2.0 addMetadata(metadata, "created", info.getCreationDate()); addMetadata(metadata, TikaCoreProperties.CREATED, info.getCreationDate()); Calendar modified = info.getModificationDate(); addMetadata(metadata, Metadata.LAST_MODIFIED, modified); addMetadata(metadata, TikaCoreProperties.MODIFIED, modified); // All remaining metadata is custom // Copy this over as-is List<String> handledMetadata = Arrays.asList("Author", "Creator", "CreationDate", "ModDate", "Keywords", "Producer", "Subject", "Title", "Trapped"); for (COSName key : info.getDictionary().keySet()) { String name = key.getName(); if (!handledMetadata.contains(name)) { addMetadata(metadata, name, info.getDictionary().getDictionaryObject(key)); } } //try to get the various versions //Caveats: // there is currently a fair amount of redundancy // TikaCoreProperties.FORMAT can be multivalued // There are also three potential pdf specific version keys: pdf:PDFVersion, pdfa:PDFVersion, pdf:PDFExtensionVersion metadata.set("pdf:PDFVersion", Float.toString(document.getDocument().getVersion())); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=" + Float.toString(document.getDocument().getVersion())); try { if (xmp != null) { xmp.addXMLNSMapping(XMPSchemaPDFAId.NAMESPACE, XMPSchemaPDFAId.class); XMPSchemaPDFAId pdfaxmp = (XMPSchemaPDFAId) xmp.getSchemaByClass(XMPSchemaPDFAId.class); if (pdfaxmp != null) { metadata.set("pdfaid:part", Integer.toString(pdfaxmp.getPart())); if (pdfaxmp.getConformance() != null) { metadata.set("pdfaid:conformance", pdfaxmp.getConformance()); String version = "A-" + pdfaxmp.getPart() + pdfaxmp.getConformance().toLowerCase(Locale.ROOT); metadata.set("pdfa:PDFVersion", version); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\"" + version + "\""); } } // TODO WARN if this XMP version is inconsistent with document header version? } } catch (IOException e) { metadata.set(TikaCoreProperties.TIKA_META_PREFIX + "pdf:metadata-xmp-parse-failed", "" + e); } //TODO: Let's try to move this into PDFBox. //Attempt to determine Adobe extension level, if present: COSDictionary root = document.getDocumentCatalog().getCOSObject(); COSDictionary extensions = (COSDictionary) root.getDictionaryObject(COSName.getPDFName("Extensions")); if (extensions != null) { for (COSName extName : extensions.keySet()) { // If it's an Adobe one, interpret it to determine the extension level: if (extName.equals(COSName.getPDFName("ADBE"))) { COSDictionary adobeExt = (COSDictionary) extensions.getDictionaryObject(extName); if (adobeExt != null) { String baseVersion = adobeExt.getNameAsString(COSName.getPDFName("BaseVersion")); int el = adobeExt.getInt(COSName.getPDFName("ExtensionLevel")); //-1 is sentinel value that something went wrong in getInt if (el != -1) { metadata.set("pdf:PDFExtensionVersion", baseVersion + " Adobe Extension Level " + el); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\"" + baseVersion + " Adobe Extension Level " + el + "\""); } } } else { // WARN that there is an Extension, but it's not Adobe's, and so is a 'new' format'. metadata.set("pdf:foundNonAdobeExtensionName", extName.getName()); } } } }
From source file:org.apache.tika.parser.pdf.PDFParser.java
License:Apache License
private void extractMetadata(PDDocument document, Metadata metadata) throws TikaException { //first extract AccessPermissions AccessPermission ap = document.getCurrentAccessPermission(); metadata.set(AccessPermissions.EXTRACT_FOR_ACCESSIBILITY, Boolean.toString(ap.canExtractForAccessibility())); metadata.set(AccessPermissions.EXTRACT_CONTENT, Boolean.toString(ap.canExtractContent())); metadata.set(AccessPermissions.ASSEMBLE_DOCUMENT, Boolean.toString(ap.canAssembleDocument())); metadata.set(AccessPermissions.FILL_IN_FORM, Boolean.toString(ap.canFillInForm())); metadata.set(AccessPermissions.CAN_MODIFY, Boolean.toString(ap.canModify())); metadata.set(AccessPermissions.CAN_MODIFY_ANNOTATIONS, Boolean.toString(ap.canModifyAnnotations())); metadata.set(AccessPermissions.CAN_PRINT, Boolean.toString(ap.canPrint())); metadata.set(AccessPermissions.CAN_PRINT_DEGRADED, Boolean.toString(ap.canPrintDegraded())); //now go for the XMP org.apache.jempbox.xmp.XMPMetadata xmp = null; XMPSchemaDublinCore dcSchema = null; XMPSchemaMediaManagement mmSchema = null; try {/*from www . ja v a 2 s .c om*/ if (document.getDocumentCatalog().getMetadata() != null) { xmp = document.getDocumentCatalog().getMetadata().exportXMPMetadata(); } } catch (IOException e) { } if (xmp != null) { try { dcSchema = xmp.getDublinCoreSchema(); } catch (IOException e) { } JempboxExtractor.extractXMPMM(xmp, metadata); } PDDocumentInformation info = document.getDocumentInformation(); metadata.set(PagedText.N_PAGES, document.getNumberOfPages()); extractMultilingualItems(metadata, TikaCoreProperties.TITLE, info.getTitle(), dcSchema); extractDublinCoreListItems(metadata, TikaCoreProperties.CREATOR, info.getAuthor(), dcSchema); extractDublinCoreListItems(metadata, TikaCoreProperties.CONTRIBUTOR, null, dcSchema); addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator()); addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords()); addMetadata(metadata, "producer", info.getProducer()); extractMultilingualItems(metadata, TikaCoreProperties.DESCRIPTION, null, dcSchema); // TODO: Move to description in Tika 2.0 addMetadata(metadata, TikaCoreProperties.TRANSITION_SUBJECT_TO_OO_SUBJECT, info.getSubject()); addMetadata(metadata, "trapped", info.getTrapped()); try { // TODO Remove these in Tika 2.0 addMetadata(metadata, "created", info.getCreationDate()); addMetadata(metadata, TikaCoreProperties.CREATED, info.getCreationDate()); } catch (IOException e) { // Invalid date format, just ignore } try { Calendar modified = info.getModificationDate(); addMetadata(metadata, Metadata.LAST_MODIFIED, modified); addMetadata(metadata, TikaCoreProperties.MODIFIED, modified); } catch (IOException e) { // Invalid date format, just ignore } // All remaining metadata is custom // Copy this over as-is List<String> handledMetadata = Arrays.asList("Author", "Creator", "CreationDate", "ModDate", "Keywords", "Producer", "Subject", "Title", "Trapped"); for (COSName key : info.getDictionary().keySet()) { String name = key.getName(); if (!handledMetadata.contains(name)) { addMetadata(metadata, name, info.getDictionary().getDictionaryObject(key)); } } //try to get the various versions //Caveats: // there is currently a fair amount of redundancy // TikaCoreProperties.FORMAT can be multivalued // There are also three potential pdf specific version keys: pdf:PDFVersion, pdfa:PDFVersion, pdf:PDFExtensionVersion metadata.set("pdf:PDFVersion", Float.toString(document.getDocument().getVersion())); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=" + Float.toString(document.getDocument().getVersion())); try { if (xmp != null) { xmp.addXMLNSMapping(XMPSchemaPDFAId.NAMESPACE, XMPSchemaPDFAId.class); XMPSchemaPDFAId pdfaxmp = (XMPSchemaPDFAId) xmp.getSchemaByClass(XMPSchemaPDFAId.class); if (pdfaxmp != null) { if (pdfaxmp.getPart() != null) { metadata.set("pdfaid:part", Integer.toString(pdfaxmp.getPart())); } if (pdfaxmp.getConformance() != null) { metadata.set("pdfaid:conformance", pdfaxmp.getConformance()); String version = "A-" + pdfaxmp.getPart() + pdfaxmp.getConformance().toLowerCase(Locale.ROOT); metadata.set("pdfa:PDFVersion", version); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\"" + version + "\""); } } // TODO WARN if this XMP version is inconsistent with document header version? } } catch (IOException e) { metadata.set(TikaCoreProperties.TIKA_META_PREFIX + "pdf:metadata-xmp-parse-failed", "" + e); } //TODO: Let's try to move this into PDFBox. //Attempt to determine Adobe extension level, if present: COSDictionary root = document.getDocumentCatalog().getCOSDictionary(); COSDictionary extensions = (COSDictionary) root.getDictionaryObject(COSName.getPDFName("Extensions")); if (extensions != null) { for (COSName extName : extensions.keySet()) { // If it's an Adobe one, interpret it to determine the extension level: if (extName.equals(COSName.getPDFName("ADBE"))) { COSDictionary adobeExt = (COSDictionary) extensions.getDictionaryObject(extName); if (adobeExt != null) { String baseVersion = adobeExt.getNameAsString(COSName.getPDFName("BaseVersion")); int el = adobeExt.getInt(COSName.getPDFName("ExtensionLevel")); //-1 is sentinel value that something went wrong in getInt if (el != -1) { metadata.set("pdf:PDFExtensionVersion", baseVersion + " Adobe Extension Level " + el); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\"" + baseVersion + " Adobe Extension Level " + el + "\""); } } } else { // WARN that there is an Extension, but it's not Adobe's, and so is a 'new' format'. metadata.set("pdf:foundNonAdobeExtensionName", extName.getName()); } } } }
From source file:org.apache.tika.parser.pdf.PDFPureJavaParser.java
License:Apache License
private void extractMetadata(PDDocument document, Metadata metadata, ParseContext context) throws TikaException { //first extract AccessPermissions AccessPermission ap = document.getCurrentAccessPermission(); metadata.set(AccessPermissions.EXTRACT_FOR_ACCESSIBILITY, Boolean.toString(ap.canExtractForAccessibility())); metadata.set(AccessPermissions.EXTRACT_CONTENT, Boolean.toString(ap.canExtractContent())); metadata.set(AccessPermissions.ASSEMBLE_DOCUMENT, Boolean.toString(ap.canAssembleDocument())); metadata.set(AccessPermissions.FILL_IN_FORM, Boolean.toString(ap.canFillInForm())); metadata.set(AccessPermissions.CAN_MODIFY, Boolean.toString(ap.canModify())); metadata.set(AccessPermissions.CAN_MODIFY_ANNOTATIONS, Boolean.toString(ap.canModifyAnnotations())); metadata.set(AccessPermissions.CAN_PRINT, Boolean.toString(ap.canPrint())); metadata.set(AccessPermissions.CAN_PRINT_DEGRADED, Boolean.toString(ap.canPrintDegraded())); //now go for the XMP Document dom = loadDOM(document.getDocumentCatalog().getMetadata(), metadata, context); XMPMetadata xmp = null;// w ww . j a va 2 s . c om if (dom != null) { xmp = new XMPMetadata(dom); } XMPSchemaDublinCore dcSchema = null; /*if (xmp != null) { try { dcSchema = xmp.getDublinCoreSchema(); } catch (IOException e) {} JempboxExtractor.extractXMPMM(xmp, metadata); }*/ PDDocumentInformation info = document.getDocumentInformation(); metadata.set(PagedText.N_PAGES, document.getNumberOfPages()); extractMultilingualItems(metadata, TikaCoreProperties.TITLE, info.getTitle(), dcSchema); addMetadata(metadata, PDF.DOC_INFO_TITLE, info.getTitle()); extractDublinCoreListItems(metadata, TikaCoreProperties.CREATOR, info.getAuthor(), dcSchema); addMetadata(metadata, PDF.DOC_INFO_CREATOR, info.getAuthor()); extractDublinCoreListItems(metadata, TikaCoreProperties.CONTRIBUTOR, null, dcSchema); addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator()); addMetadata(metadata, PDF.DOC_INFO_CREATOR_TOOL, info.getCreator()); addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords()); addMetadata(metadata, PDF.DOC_INFO_KEY_WORDS, info.getKeywords()); addMetadata(metadata, "producer", info.getProducer()); addMetadata(metadata, PDF.DOC_INFO_PRODUCER, info.getProducer()); extractMultilingualItems(metadata, TikaCoreProperties.DESCRIPTION, null, dcSchema); addMetadata(metadata, PDF.DOC_INFO_SUBJECT, info.getSubject()); // TODO: Move to description in Tika 2.0 addMetadata(metadata, TikaCoreProperties.TRANSITION_SUBJECT_TO_OO_SUBJECT, info.getSubject()); addMetadata(metadata, "trapped", info.getTrapped()); addMetadata(metadata, PDF.DOC_INFO_TRAPPED, info.getTrapped()); // TODO Remove these in Tika 2.0 addMetadata(metadata, "created", info.getCreationDate()); addMetadata(metadata, PDF.DOC_INFO_CREATED, info.getCreationDate()); addMetadata(metadata, TikaCoreProperties.CREATED, info.getCreationDate()); Calendar modified = info.getModificationDate(); addMetadata(metadata, Metadata.LAST_MODIFIED, modified); addMetadata(metadata, TikaCoreProperties.MODIFIED, modified); addMetadata(metadata, PDF.DOC_INFO_MODIFICATION_DATE, info.getModificationDate()); // All remaining metadata is custom // Copy this over as-is List<String> handledMetadata = Arrays.asList("Author", "Creator", "CreationDate", "ModDate", "Keywords", "Producer", "Subject", "Title", "Trapped"); for (COSName key : info.getCOSObject().keySet()) { String name = key.getName(); if (!handledMetadata.contains(name)) { addMetadata(metadata, name, info.getCOSObject().getDictionaryObject(key)); addMetadata(metadata, PDF.PDF_DOC_INFO_CUSTOM_PREFIX + name, info.getCOSObject().getDictionaryObject(key)); } } //try to get the various versions //Caveats: // there is currently a fair amount of redundancy // TikaCoreProperties.FORMAT can be multivalued // There are also three potential pdf specific version keys: pdf:PDFVersion, pdfa:PDFVersion, pdf:PDFExtensionVersion metadata.set(PDF.PDF_VERSION, Float.toString(document.getDocument().getVersion())); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=" + Float.toString(document.getDocument().getVersion())); try { if (xmp != null) { xmp.addXMLNSMapping(XMPSchemaPDFAId.NAMESPACE, XMPSchemaPDFAId.class); XMPSchemaPDFAId pdfaxmp = (XMPSchemaPDFAId) xmp.getSchemaByClass(XMPSchemaPDFAId.class); if (pdfaxmp != null) { if (pdfaxmp.getPart() != null) { metadata.set(PDF.PDFAID_PART, Integer.toString(pdfaxmp.getPart())); } if (pdfaxmp.getConformance() != null) { metadata.set(PDF.PDFAID_CONFORMANCE, pdfaxmp.getConformance()); String version = "A-" + pdfaxmp.getPart() + pdfaxmp.getConformance().toLowerCase(Locale.ROOT); metadata.set(PDF.PDFA_VERSION, version); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\"" + version + "\""); } } // TODO WARN if this XMP version is inconsistent with document header version? } } catch (IOException e) { metadata.set(TikaCoreProperties.TIKA_META_PREFIX + "pdf:metadata-xmp-parse-failed", "" + e); } //TODO: Let's try to move this into PDFBox. //Attempt to determine Adobe extension level, if present: COSDictionary root = document.getDocumentCatalog().getCOSObject(); COSDictionary extensions = (COSDictionary) root.getDictionaryObject(COSName.getPDFName("Extensions")); if (extensions != null) { for (COSName extName : extensions.keySet()) { // If it's an Adobe one, interpret it to determine the extension level: if (extName.equals(COSName.getPDFName("ADBE"))) { COSDictionary adobeExt = (COSDictionary) extensions.getDictionaryObject(extName); if (adobeExt != null) { String baseVersion = adobeExt.getNameAsString(COSName.getPDFName("BaseVersion")); int el = adobeExt.getInt(COSName.getPDFName("ExtensionLevel")); //-1 is sentinel value that something went wrong in getInt if (el != -1) { metadata.set(PDF.PDF_EXTENSION_VERSION, baseVersion + " Adobe Extension Level " + el); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\"" + baseVersion + " Adobe Extension Level " + el + "\""); } } } else { // WARN that there is an Extension, but it's not Adobe's, and so is a 'new' format'. metadata.set("pdf:foundNonAdobeExtensionName", extName.getName()); } } } }
From source file:org.apache.tika.parser.pdf18.PDFParser.java
License:Apache License
private void extractMetadata(PDDocument document, Metadata metadata) throws TikaException { //first extract AccessPermissions AccessPermission ap = document.getCurrentAccessPermission(); metadata.set(AccessPermissions.EXTRACT_FOR_ACCESSIBILITY, Boolean.toString(ap.canExtractForAccessibility())); metadata.set(AccessPermissions.EXTRACT_CONTENT, Boolean.toString(ap.canExtractContent())); metadata.set(AccessPermissions.ASSEMBLE_DOCUMENT, Boolean.toString(ap.canAssembleDocument())); metadata.set(AccessPermissions.FILL_IN_FORM, Boolean.toString(ap.canFillInForm())); metadata.set(AccessPermissions.CAN_MODIFY, Boolean.toString(ap.canModify())); metadata.set(AccessPermissions.CAN_MODIFY_ANNOTATIONS, Boolean.toString(ap.canModifyAnnotations())); metadata.set(AccessPermissions.CAN_PRINT, Boolean.toString(ap.canPrint())); metadata.set(AccessPermissions.CAN_PRINT_DEGRADED, Boolean.toString(ap.canPrintDegraded())); //now go for the XMP org.apache.jempbox.xmp.XMPMetadata xmp = null; XMPSchemaDublinCore dcSchema = null; XMPSchemaMediaManagement mmSchema = null; try {// w w w . j av a 2s .co m if (document.getDocumentCatalog().getMetadata() != null) { xmp = document.getDocumentCatalog().getMetadata().exportXMPMetadata(); } } catch (IOException e) { } if (xmp != null) { try { dcSchema = xmp.getDublinCoreSchema(); } catch (IOException e) { } JempboxExtractor.extractXMPMM(xmp, metadata); } PDDocumentInformation info = document.getDocumentInformation(); metadata.set(PagedText.N_PAGES, document.getNumberOfPages()); extractMultilingualItems(metadata, TikaCoreProperties.TITLE, info.getTitle(), dcSchema); extractDublinCoreListItems(metadata, TikaCoreProperties.CREATOR, info.getAuthor(), dcSchema); extractDublinCoreListItems(metadata, TikaCoreProperties.CONTRIBUTOR, null, dcSchema); addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator()); addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords()); addMetadata(metadata, "producer", info.getProducer()); extractMultilingualItems(metadata, TikaCoreProperties.DESCRIPTION, null, dcSchema); // TODO: Move to description in Tika 2.0 addMetadata(metadata, TikaCoreProperties.TRANSITION_SUBJECT_TO_OO_SUBJECT, info.getSubject()); addMetadata(metadata, "trapped", info.getTrapped()); try { // TODO Remove these in Tika 2.0 addMetadata(metadata, "created", info.getCreationDate()); addMetadata(metadata, TikaCoreProperties.CREATED, info.getCreationDate()); } catch (IOException e) { // Invalid date format, just ignore } try { Calendar modified = info.getModificationDate(); addMetadata(metadata, Metadata.LAST_MODIFIED, modified); addMetadata(metadata, TikaCoreProperties.MODIFIED, modified); } catch (IOException e) { // Invalid date format, just ignore } // All remaining metadata is custom // Copy this over as-is List<String> handledMetadata = Arrays.asList("Author", "Creator", "CreationDate", "ModDate", "Keywords", "Producer", "Subject", "Title", "Trapped"); for (COSName key : info.getDictionary().keySet()) { String name = key.getName(); if (!handledMetadata.contains(name)) { addMetadata(metadata, name, info.getDictionary().getDictionaryObject(key)); } } //try to get the various versions //Caveats: // there is currently a fair amount of redundancy // TikaCoreProperties.FORMAT can be multivalued // There are also three potential pdf specific version keys: pdf:PDFVersion, pdfa:PDFVersion, pdf:PDFExtensionVersion metadata.set("pdf:PDFVersion", Float.toString(document.getDocument().getVersion())); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=" + Float.toString(document.getDocument().getVersion())); try { if (xmp != null) { xmp.addXMLNSMapping(XMPSchemaPDFAId.NAMESPACE, XMPSchemaPDFAId.class); XMPSchemaPDFAId pdfaxmp = (XMPSchemaPDFAId) xmp.getSchemaByClass(XMPSchemaPDFAId.class); if (pdfaxmp != null) { if (pdfaxmp.getPart() != null) { metadata.set("pdfaid:part", Integer.toString(pdfaxmp.getPart())); } if (pdfaxmp.getConformance() != null) { metadata.set("pdfaid:conformance", pdfaxmp.getConformance()); String version = "A-" + pdfaxmp.getPart() + pdfaxmp.getConformance().toLowerCase(Locale.ROOT); metadata.set("pdfa:PDFVersion", version); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\"" + version + "\""); } } // TODO WARN if this XMP version is inconsistent with document header version? } } catch (IOException e) { metadata.set(TikaCoreProperties.TIKA_META_PREFIX + "pdf:metadata-xmp-parse-failed", "" + e); } //TODO: Let's try to move this into PDFBox. //Attempt to determine Adobe extension level, if present: COSDictionary root = document.getDocumentCatalog().getCOSDictionary(); COSDictionary extensions = (COSDictionary) root.getDictionaryObject(COSName.getPDFName("Extensions")); if (extensions != null) { for (COSName extName : extensions.keySet()) { // If it's an Adobe one, interpret it to determine the extension level: if (extName.equals(COSName.getPDFName("ADBE"))) { COSDictionary adobeExt = (COSDictionary) extensions.getDictionaryObject(extName); if (adobeExt != null) { String baseVersion = adobeExt.getNameAsString(COSName.getPDFName("BaseVersion")); int el = adobeExt.getInt(COSName.getPDFName("ExtensionLevel")); //-1 is sentinel value that something went wrong in getInt if (el != -1) { metadata.set("pdf:PDFExtensionVersion", baseVersion + " Adobe Extension Level " + el); metadata.add(TikaCoreProperties.FORMAT.getName(), MEDIA_TYPE.toString() + "; version=\"" + baseVersion + " Adobe Extension Level " + el + "\""); } } } else { // WARN that there is an Extension, but it's not Adobe's, and so is a 'new' format'. metadata.set("pdf:foundNonAdobeExtensionName", extName.getName()); } } } }
From source file:org.xmlcml.font.NonStandardFontManager.java
License:Apache License
private AMIFont lookupOrCreateFont(int level, COSDictionary dict) { /**/* w w w .j a va 2s .c o m*/ Type = COSName{Font} Subtype = COSName{Type1} BaseFont = COSName{Times-Roman} Name = COSName{arXivStAmP} LastChar = COSInt{32} Widths = COSArray{[COSInt{19}]} FirstChar = COSInt{32} FontMatrix = COSArray{[COSFloat{0.0121}, COSInt{0}, COSInt{0}, COSFloat{-0.0121}, COSInt{0}, COSInt{0}]} ToUnicode = COSDictionary{(COSName{Length}:COSInt{212}) (COSName{Filter}:COSName{FlateDecode}) } FontBBox = COSArray{[COSInt{0}, COSInt{0}, COSInt{1}, COSInt{1}]} Resources = COSDictionary{(COSName{ProcSet}:COSArray{[COSName{PDF}, COSName{ImageB}]}) } Encoding = COSDictionary{(COSName{Differences}:COSArray{[COSInt{32}, COSName{space}]}) (COSName{Type}:COSName{Encoding}) } CharProcs = COSDictionary{(COSName{space}:COSDictionary{(COSName{Length}:COSInt{67}) (COSName{Filter}:COSName{FlateDecode}) }) }*/ AMIFont amiFont = null; String fontName = AMIFont.getFontName(dict); String typeS = null; amiFont = getAmiFontByFontName(fontName); if (amiFont == null) { // some confusion here between fontName and fontFamilyName amiFont = new AMIFont(fontName, null, typeS, dict); amiFont.setFontName(fontName); amiFontByFontNameMap.put(fontName, amiFont); String indent = ""; for (int i = 0; i < level; i++) { indent += " "; } LOG.debug(String.format("%s****************** level %d font dict:", indent, level)); level++; indent += " "; for (COSName key : dict.keySet()) { String keyName = key.getName(); Object object = dict.getDictionaryObject(key); LOG.debug(String.format("%s****************** %s = %s", indent, keyName, object)); } COSArray array = (COSArray) dict.getDictionaryObject(COSName.DESCENDANT_FONTS); if (array != null) { LOG.debug(String.format("%s****************** descendant fonts (%d):", indent, array.size())); amiFont = lookupOrCreateFont(level, (COSDictionary) array.getObject(0)); } } return amiFont; }
From source file:org.xmlcml.pdf2svg.AMIFont.java
License:Apache License
public static String getFontName(COSDictionary dict) { String fontName = null;/*from w w w . j a v a 2 s . c o m*/ String baseFontS = null; for (COSName key : dict.keySet()) { String keyName = key.getName(); if (keyName == null) { LOG.error("Null key"); continue; } else if (!(key instanceof COSName)) { LOG.error("key not COSName"); continue; } String cosNameName = null; COSBase cosBase = dict.getDictionaryObject(key); if (cosBase instanceof COSName) { COSName cosName = (COSName) cosBase; cosNameName = cosName.getName(); LOG.trace("Name:" + cosNameName); } else if (cosBase instanceof COSInteger) { COSInteger cosInteger = (COSInteger) cosBase; LOG.trace("Integer: " + cosInteger.intValue()); } else if (cosBase instanceof COSArray) { COSArray cosArray = (COSArray) cosBase; LOG.trace("Array: " + cosArray.size() + " / " + cosArray); } else if (cosBase instanceof COSDictionary) { COSDictionary cosDictionary = (COSDictionary) cosBase; LOG.trace("Dictionary: " + cosDictionary); } else { LOG.error("COS " + cosBase); } if (cosNameName != null && keyName.equals(N_NAME)) { fontName = cosNameName; } else if (cosNameName != null && keyName.equals(N_BASE_FONT)) { baseFontS = cosNameName; } } if (fontName == null) { fontName = baseFontS; } return fontName; }
From source file:uk.bl.wa.tika.parser.pdf.pdfbox.PDFParser.java
License:Apache License
private void extractMetadata(PDDocument document, Metadata metadata) throws TikaException { PDDocumentInformation info = document.getDocumentInformation(); metadata.set(PagedText.N_PAGES, document.getNumberOfPages()); addMetadata(metadata, Metadata.TITLE, info.getTitle()); addMetadata(metadata, Metadata.AUTHOR, info.getAuthor()); addMetadata(metadata, Metadata.KEYWORDS, info.getKeywords()); addMetadata(metadata, "pdf:creator", info.getCreator()); addMetadata(metadata, "pdf:producer", info.getProducer()); addMetadata(metadata, Metadata.SUBJECT, info.getSubject()); addMetadata(metadata, "trapped", info.getTrapped()); addMetadata(metadata, "created", info.getCreationDate()); addMetadata(metadata, Metadata.CREATION_DATE, info.getCreationDate()); Calendar modified = info.getModificationDate(); addMetadata(metadata, Metadata.LAST_MODIFIED, modified); // All remaining metadata is custom // Copy this over as-is List<String> handledMetadata = Arrays.asList(new String[] { "Author", "Creator", "CreationDate", "ModDate", "Keywords", "Producer", "Subject", "Title", "Trapped" }); if (info.getCOSObject() != null && info.getCOSObject().keySet() != null) { for (COSName key : info.getCOSObject().keySet()) { String name = key.getName(); if (!handledMetadata.contains(name)) { addMetadata(metadata, name, info.getCOSObject().getDictionaryObject(key)); }// w w w . ja v a 2 s .c o m } } // ANJ Extensions: // // // Add other data of interest: metadata.set("pdf:version", "" + document.getDocument().getVersion()); metadata.set("pdf:numPages", "" + document.getNumberOfPages()); //metadata.set("pdf:cryptoMode", ""+getCryptoModeAsString(reader)); //metadata.set("pdf:openedWithFullPermissions", ""+reader.isOpenedWithFullPermissions()); metadata.set("pdf:encrypted", "" + document.isEncrypted()); //metadata.set("pdf:metadataEncrypted", ""+document.isMetadataEncrypted()); //metadata.set("pdf:128key", ""+reader.is128Key()); //metadata.set("pdf:tampered", ""+reader.isTampered()); try { if (document.getDocumentCatalog().getMetadata() != null) { XMPMetadata xmp = XMPMetadata.load(document.getDocumentCatalog().getMetadata().exportXMPMetadata()); // There is a special class for grabbing data in the PDF schema - not sure it will add much here: // Could parse xmp:CreatorTool and pdf:Producer etc. etc. out of here. XMPSchemaPDF pdfxmp = xmp.getPDFSchema(); // Added a PDF/A schema class: xmp.addXMLNSMapping(XMPSchemaPDFA.NAMESPACE, XMPSchemaPDFA.class); XMPSchemaPDFA pdfaxmp = (XMPSchemaPDFA) xmp.getSchemaByClass(XMPSchemaPDFA.class); if (pdfaxmp != null) { metadata.set("pdfaid:part", pdfaxmp.getPart()); metadata.set("pdfaid:conformance", pdfaxmp.getConformance()); String version = "A-" + pdfaxmp.getPart() + pdfaxmp.getConformance().toLowerCase(); //metadata.set("pdfa:version", version ); metadata.set("pdf:version", version); } // TODO WARN if this XMP version is inconsistent with document header version? } } catch (IOException e) { log.error("XMP Parsing failed: " + e); metadata.set("pdf:metadata-xmp-parse-failed", "" + e); } // Attempt to determine Adobe extension level, if present: COSDictionary root = document.getDocumentCatalog().getCOSObject(); COSDictionary extensions = (COSDictionary) root.getDictionaryObject(COSName.getPDFName("Extensions")); if (extensions != null) { for (COSName extName : extensions.keySet()) { // If it's an Adobe one, interpret it to determine the extension level: if (extName.equals(COSName.getPDFName("ADBE"))) { COSDictionary adobeExt = (COSDictionary) extensions.getDictionaryObject(extName); if (adobeExt != null) { String baseVersion = adobeExt.getNameAsString(COSName.getPDFName("BaseVersion")); int el = adobeExt.getInt(COSName.getPDFName("ExtensionLevel")); metadata.set("pdf:version", baseVersion + " Adobe Extension Level " + el); } // TODO WARN if this embedded version is inconsistent with document header version? } else { // WARN that there is an Extension, but it's not Adobe's, and so is a 'new' format'. metadata.set("pdf:foundNonAdobeExtensionName", extName.getName()); } } } // End Of ANJ Extensions. }