add

atms-api/pom.xml

@@ -278,6 +278,24 @@
 			<version>3.9.1</version> <!-- Stay on 1.7.1 to support Java 6 -->
 			<scope>test</scope>
 		</dependency>
+
+		<dependency>
+			<groupId>org.apache.tika</groupId>
+			<artifactId>tika-core</artifactId>
+			<version>1.17</version>
+		</dependency>
+		<dependency>
+			<groupId>org.apache.tika</groupId>
+			<artifactId>tika-parsers</artifactId>
+			<version>1.17</version>
+		</dependency>
+		<dependency>
+			<groupId>com.javaaxp</groupId>
+			<artifactId>java-axp</artifactId>
+			<version>1.0</version>
+			<scope>system</scope>
+			<systemPath>${basedir}/lib/java-axp-1.0-SNAPSHOT.jar</systemPath>
+		</dependency>
 	</dependencies>
 	<build>
 		<finalName>atms-api</finalName>

atms-api/src/test/java/pwc/taxtech/atms/common/PDFTest.java

+package pwc.taxtech.atms.common;
+
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.pdf.PDFParser;
+import org.apache.tika.parser.pdf.PDFParserConfig;
+import org.apache.tika.sax.BodyContentHandler;
+
+import java.io.File;
+import java.io.FileInputStream;
+
+public class PDFTest {
+    public static void main(String[] args) {
+        try {
+            BodyContentHandler handler = new BodyContentHandler();
+
+            Metadata metadata = new Metadata();
+            FileInputStream inputstream = new FileInputStream(new File("C:\\woo\\test.pdf"));
+            ParseContext pcontext = new ParseContext();
+
+            PDFParser pdfparser = new PDFParser();
+            pdfparser.getPDFParserConfig().setSortByPosition(true);//参见底层实现
+//            pdfparser.getPDFParserConfig().setEnableAutoSpace(false);
+//            pdfparser.getPDFParserConfig().setAverageCharTolerance(1f);
+//            pdfparser.getPDFParserConfig().setSpacingTolerance(20f);
+            pdfparser.parse(inputstream, handler, metadata, pcontext);
+
+            System.out.println(handler.toString());
+
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+    }
+}

atms-api/src/test/java/pwc/taxtech/atms/common/POITest.java

+package pwc.taxtech.atms.common;
+
+import org.apache.poi.openxml4j.exceptions.InvalidFormatException;
+import org.apache.poi.ss.formula.eval.ValueEval;
+import org.apache.poi.ss.formula.functions.FreeRefFunction;
+import org.apache.poi.ss.formula.udf.AggregatingUDFFinder;
+import org.apache.poi.ss.formula.udf.DefaultUDFFinder;
+import org.apache.poi.ss.formula.udf.UDFFinder;
+import org.apache.poi.ss.usermodel.*;
+import org.apache.poi.ss.util.CellReference;
+
+import java.io.*;
+
+public class POITest {
+    public static void main(String[] args) {
+
+        File workbookFile = new File("C:\\source\\test - Copy.xlsx");
+
+        try {
+            FileInputStream fis = new FileInputStream(workbookFile);
+            Workbook workbook = WorkbookFactory.create(fis);
+
+            String[] functionNames = {"TmpFunction"};
+            FreeRefFunction[] functionImpls = {new TmpFunction()};
+
+            UDFFinder udfs = new DefaultUDFFinder(functionNames, functionImpls);
+            UDFFinder udfToolpack = new AggregatingUDFFinder(udfs);
+
+            workbook.addToolPack(udfToolpack);
+
+            FormulaEvaluator evaluator = workbook.getCreationHelper().createFormulaEvaluator();
+
+
+            int sheetNum = workbook.getNumberOfSheets();
+            Sheet st1 = workbook.getSheetAt(0);
+            st1.getRow(1).getCell(0).setCellType(CellType.NUMERIC);
+            st1.getRow(1).getCell(0).setCellValue(15);
+            evaluator.evaluateAll();
+            for (int i = 0; i < sheetNum; i++) {
+                Sheet tmpSheet = workbook.getSheetAt(i);
+                for (int r = tmpSheet.getFirstRowNum(); r <= tmpSheet.getLastRowNum(); r++) {
+                    Row row = tmpSheet.getRow(r);
+                    if (null == row) {
+                        continue;
+                    }
+                    for (int c = row.getFirstCellNum(); c <= row.getLastCellNum(); c++) {
+                        System.out.println("row :" + r + "  cell: " + c);
+                        Cell tmp = row.getCell(c);
+                        if (null != tmp && tmp.getCellTypeEnum().equals(CellType.FORMULA)) {
+//                            CellValue v = evaluator.evaluate(tmp);
+                            tmp.setCellType(CellType.NUMERIC);
+                            tmp.setCellValue(tmp.getNumericCellValue());
+                        }
+
+                    }
+                }
+
+            }
+
+            FileOutputStream excelFileOutPutStream = new FileOutputStream("C:\\source\\test - Copy.xlsx");
+
+            workbook.write(excelFileOutPutStream);
+
+            excelFileOutPutStream.flush();
+
+            excelFileOutPutStream.close();
+
+
+        } catch (FileNotFoundException e) {
+            e.printStackTrace();
+        } catch (InvalidFormatException e) {
+            e.printStackTrace();
+        } catch (IOException e) {
+            e.printStackTrace();
+        }
+    }
+
+
+}

atms-api/src/test/java/pwc/taxtech/atms/common/TikaTest.java

+package pwc.taxtech.atms.common;
+
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.sax.BodyContentHandler;
+import org.xml.sax.ContentHandler;
+
+import java.io.*;
+
+public class TikaTest {
+    public static void main(String[] args) {
+        try {
+//            Tika tika = new Tika();
+            File xpsFile = new File("C:\\woo\\海关稽核结果.xps");
+
+            InputStream inputStream = new FileInputStream(xpsFile);
+//            String FileName = xpsFile.getName();
+//            Metadata metadata = new Metadata();
+//            if (FileName != null && FileName.length() > 0)
+//                metadata.add(Metadata.RESOURCE_NAME_KEY, FileName);
+//            String MimeType = tika.detect(inputStream, metadata);
+//
+//            metadata.add(Metadata.CONTENT_TYPE, MimeType);
+//            inputStream.close();
+//            inputStream = new FileInputStream(xpsFile);
+//            Reader reader = tika.parse(inputStream, metadata);
+//            String content = IOUtils.toString(reader);
+//            inputStream.close();
+            Metadata metadata = new Metadata();
+            ContentHandler handler = new BodyContentHandler();
+            new TmpXPSParser().parse(inputStream, handler, metadata, new ParseContext());
+            String content = handler.toString();
+            System.out.println(content);
+        } catch (Exception e) {
+            e.printStackTrace();
+        }
+    }
+}

atms-api/src/test/java/pwc/taxtech/atms/common/TmpFunction.java

+package pwc.taxtech.atms.common;
+
+import org.apache.poi.ss.formula.OperationEvaluationContext;
+import org.apache.poi.ss.formula.eval.*;
+import org.apache.poi.ss.formula.functions.FreeRefFunction;
+import org.apache.poi.ss.util.CellReference;
+
+public class TmpFunction implements FreeRefFunction {
+    @Override
+    public ValueEval evaluate(ValueEval[] valueEvals, OperationEvaluationContext operationEvaluationContext) {
+//        if (valueEvals.length != 3) {
+//            return ErrorEval.VALUE_INVALID;
+//        }
+        try {
+            ValueEval v1 = OperandResolver.getSingleValue(valueEvals[0],
+                    operationEvaluationContext.getRowIndex(),
+                    operationEvaluationContext.getColumnIndex());
+            ValueEval v2 = OperandResolver.getSingleValue(valueEvals[1],
+                    operationEvaluationContext.getRowIndex(),
+                    operationEvaluationContext.getColumnIndex());
+
+            String val1 = OperandResolver.coerceValueToString(v1);
+            int val2 = OperandResolver.coerceValueToInt(v2);
+            CellReference reference = new CellReference(val1);
+
+
+            return new NumberEval(operationEvaluationContext.getWorkbook().getSheet(0)
+                    .getCell(reference.getRow(),reference.getCol()).getNumericCellValue() + val2);
+        } catch (EvaluationException e) {
+            e.printStackTrace();
+        }
+        return null;
+    }
+}

atms-api/src/test/java/pwc/taxtech/atms/common/TmpXPSParser.java

+package pwc.taxtech.atms.common;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.Collections;
+import java.util.List;
+import java.util.Set;
+
+import javaaxp.core.service.IXPSAccess;
+import javaaxp.core.service.IXPSPageAccess;
+import javaaxp.core.service.XPSError;
+import javaaxp.core.service.impl.XPSServiceImpl;
+import javaaxp.core.service.impl.document.jaxb.CTCanvas;
+import javaaxp.core.service.impl.document.jaxb.CTGlyphs;
+import javaaxp.core.service.impl.document.jaxb.CTPath;
+import javaaxp.core.service.model.document.page.IFixedPage;
+
+import org.apache.tika.exception.TikaException;
+import org.apache.tika.metadata.Metadata;
+import org.apache.tika.mime.MediaType;
+import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.Parser;
+import org.apache.tika.sax.XHTMLContentHandler;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.SAXException;
+
+
+public class TmpXPSParser implements Parser {
+
+    private double currentXPosition = 0;
+
+    /**
+     *
+     */
+    private static final long serialVersionUID = -3528366722867144747L;
+
+    private static final Set<MediaType> SUPPORTED_TYPES =
+            Collections.singleton(MediaType.application("vnd.ms-xpsdocument"));
+
+    private static final String XPS_MIME_TYPE = "application/vnd.ms-xpsdocument";
+
+    private XHTMLContentHandler fileXHTML;
+
+    public Set<MediaType> getSupportedTypes(ParseContext context) {
+        return SUPPORTED_TYPES;
+    }
+
+    public void parse(
+            InputStream stream, ContentHandler handler,
+            Metadata metadata, ParseContext context)
+            throws IOException, SAXException, TikaException {
+        metadata.set(Metadata.CONTENT_TYPE, XPS_MIME_TYPE);
+
+        fileXHTML = new XHTMLContentHandler(handler, metadata);
+        try {
+            parseXPS(stream);
+        } catch (XPSError e) {
+            throw new IOException(e);
+        }
+        stream.close();
+    }
+
+    private void parseXPS(InputStream inputStream) throws XPSError, SAXException {
+        IXPSAccess xpsAccess = XPSServiceImpl.getInstance().getXPSAccess(inputStream);
+        xhtmlStartDocument();
+        int firstDocNum = xpsAccess.getDocumentAccess().getFirstDocNum();
+        int lastDocNum = xpsAccess.getDocumentAccess().getLastDocNum();
+        for (int i = firstDocNum; i <= lastDocNum; i++) {
+            IXPSPageAccess xpsPageAccess = xpsAccess.getPageAccess(i);
+            int firstPageNum = xpsPageAccess.getFirstPageNum();
+            int lastPageNum = xpsPageAccess.getLastPageNum();
+            for (int j = firstPageNum; j <= lastPageNum; j++) {
+                IFixedPage fixedPage = xpsPageAccess.getPage(j);
+                parseObjs(fixedPage.getPathOrGlyphsOrCanvas());
+            }
+        }
+        xhtmlEndDocument();
+    }
+
+    private void parseObjs(List<Object> objs) throws XPSError, SAXException {
+        for (Object o : objs)
+            parseObj(o);
+    }
+
+    private void parseObj(Object xpsObj) throws XPSError, SAXException {
+        if (xpsObj instanceof CTCanvas) {
+            CTCanvas c = (CTCanvas) xpsObj;
+            xhtmlStartCanvas();
+            parseObjs(c.getPathOrGlyphsOrCanvas());
+            xhtmlEndCanvas();
+        } else if (xpsObj instanceof CTGlyphs) {
+            CTGlyphs c = (CTGlyphs) xpsObj;
+            if (c.getOriginX() < currentXPosition) {
+                fileXHTML.startElement("div");
+                fileXHTML.characters(" ");
+                fileXHTML.endElement("div");
+            }
+            String text = c.getUnicodeString();
+            xhtmlParagraph(text);
+            currentXPosition = c.getOriginX();
+        } else if (xpsObj instanceof CTPath) {
+        } else {
+            System.out.println("Unhandled type : " + xpsObj.getClass().getCanonicalName());
+        }
+    }
+
+    private void xhtmlStartDocument() throws SAXException {
+        fileXHTML.startDocument();
+    }
+
+    private void xhtmlEndDocument() throws SAXException {
+        fileXHTML.endDocument();
+    }
+
+    private void xhtmlStartCanvas() throws SAXException {
+        fileXHTML.startElement("div");
+    }
+
+    private void xhtmlEndCanvas() throws SAXException {
+        fileXHTML.endElement("div");
+    }
+
+    private void xhtmlParagraph(String text) throws SAXException {
+        fileXHTML.startElement("span");
+        fileXHTML.characters(text);
+        fileXHTML.endElement("span");
+    }
+
+    /**
+     * @deprecated This method will be removed in Apache Tika 1.0.
+     */
+    public void parse(
+            InputStream stream, ContentHandler handler, Metadata metadata)
+            throws IOException, SAXException, TikaException {
+        parse(stream, handler, metadata, new ParseContext());
+    }
+
+}