Repository: any23 Updated Branches: refs/heads/master 40619343d -> 5a2613b84
ANY23-364 resolved POI deprecation warnings Project: http://git-wip-us.apache.org/repos/asf/any23/repo Commit: http://git-wip-us.apache.org/repos/asf/any23/commit/5a2613b8 Tree: http://git-wip-us.apache.org/repos/asf/any23/tree/5a2613b8 Diff: http://git-wip-us.apache.org/repos/asf/any23/diff/5a2613b8 Branch: refs/heads/master Commit: 5a2613b848b317c54381bcc8d7b23ca1e27e3725 Parents: 4061934 Author: Hans <firedrak...@gmail.com> Authored: Wed Jul 11 15:10:46 2018 -0500 Committer: Hans <firedrak...@gmail.com> Committed: Wed Jul 11 15:10:46 2018 -0500 ---------------------------------------------------------------------- .../plugin/officescraper/ExcelExtractor.java | 42 +++++++++++--------- .../main/java/org/apache/any23/vocab/Excel.java | 9 ++--- 2 files changed, 28 insertions(+), 23 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/any23/blob/5a2613b8/plugins/office-scraper/src/main/java/org/apache/any23/plugin/officescraper/ExcelExtractor.java ---------------------------------------------------------------------- diff --git a/plugins/office-scraper/src/main/java/org/apache/any23/plugin/officescraper/ExcelExtractor.java b/plugins/office-scraper/src/main/java/org/apache/any23/plugin/officescraper/ExcelExtractor.java index 4c8826c..d4e7918 100644 --- a/plugins/office-scraper/src/main/java/org/apache/any23/plugin/officescraper/ExcelExtractor.java +++ b/plugins/office-scraper/src/main/java/org/apache/any23/plugin/officescraper/ExcelExtractor.java @@ -27,6 +27,7 @@ import org.apache.any23.rdf.RDFUtils; import org.apache.any23.vocab.Excel; import org.apache.poi.hssf.usermodel.HSSFWorkbook; import org.apache.poi.ss.usermodel.Cell; +import org.apache.poi.ss.usermodel.CellType; import org.apache.poi.ss.usermodel.Row; import org.apache.poi.ss.usermodel.Sheet; import org.apache.poi.ss.usermodel.Workbook; @@ -87,9 +88,9 @@ public class ExcelExtractor implements Extractor.ContentExtractor { // TODO: this should be done by Tika, the extractors should be split. private Workbook createWorkbook(IRI document, InputStream is) throws IOException { final String documentIRI = document.toString(); - if(documentIRI.endsWith(".xlsx")) { + if (documentIRI.endsWith(".xlsx")) { return new XSSFWorkbook(is); - } else if(documentIRI.endsWith("xls")) { + } else if (documentIRI.endsWith("xls")) { return new HSSFWorkbook(is); } else { throw new IllegalArgumentException("Unsupported extension for resource [" + documentIRI + "]"); @@ -121,7 +122,7 @@ public class ExcelExtractor implements Extractor.ContentExtractor { final int lastRowNum = sheet.getLastRowNum(); er.writeTriple(sheetIRI, excel.sheetName, RDFUtils.literal(sheetName)); er.writeTriple(sheetIRI, excel.firstRow, RDFUtils.literal(firstRowNum)); - er.writeTriple(sheetIRI, excel.lastRow , RDFUtils.literal(lastRowNum )); + er.writeTriple(sheetIRI, excel.lastRow, RDFUtils.literal(lastRowNum)); } private void writeRowMetadata(IRI rowIRI, Row row, ExtractionResult er) { @@ -132,8 +133,9 @@ public class ExcelExtractor implements Extractor.ContentExtractor { } private void writeCell(IRI rowIRI, Cell cell, ExtractionResult er) { - final IRI cellType = cellTypeToType(cell.getCellType()); - if(cellType == null) return; // Skip unsupported cells. + final IRI cellType = cellTypeToType(cell.getCellTypeEnum()); + if (cellType == null) + return; // Skip unsupported cells. final IRI cellIRI = getCellIRI(rowIRI, cell); er.writeTriple(rowIRI, excel.containsCell, cellIRI); er.writeTriple(cellIRI, RDF.TYPE, excel.cell); @@ -157,20 +159,24 @@ public class ExcelExtractor implements Extractor.ContentExtractor { String.format("/%d/", cell.getColumnIndex())); } - private IRI cellTypeToType(int cellType) { + private IRI cellTypeToType(CellType cellType) { final String postfix; - switch (cellType) { - case Cell.CELL_TYPE_STRING: - postfix = "string"; - break; - case Cell.CELL_TYPE_BOOLEAN: - postfix = "boolean"; - break; - case Cell.CELL_TYPE_NUMERIC: - postfix = "numeric"; - break; - default: - postfix = null; + if (cellType == null) { + postfix = null; + } else { + switch (cellType) { + case STRING: + postfix = "string"; + break; + case BOOLEAN: + postfix = "boolean"; + break; + case NUMERIC: + postfix = "numeric"; + break; + default: + postfix = null; + } } return postfix == null ? null : RDFUtils.iri(excel.getNamespace().toString() + postfix); } http://git-wip-us.apache.org/repos/asf/any23/blob/5a2613b8/plugins/office-scraper/src/main/java/org/apache/any23/vocab/Excel.java ---------------------------------------------------------------------- diff --git a/plugins/office-scraper/src/main/java/org/apache/any23/vocab/Excel.java b/plugins/office-scraper/src/main/java/org/apache/any23/vocab/Excel.java index 2ce8874..3295469 100644 --- a/plugins/office-scraper/src/main/java/org/apache/any23/vocab/Excel.java +++ b/plugins/office-scraper/src/main/java/org/apache/any23/vocab/Excel.java @@ -109,13 +109,12 @@ public class Excel extends Vocabulary { */ public static final String NS = "http://any23.apache.org/excel/"; - private static Excel instance; + private static final class InstanceHolder { + private static final Excel instance = new Excel(); + } public static Excel getInstance() { - if (instance == null) { - instance = new Excel(); - } - return instance; + return InstanceHolder.instance; } public IRI createResource(String localName) {