判斷java檔案型別TikaToolKit的例項
阿新 • • 發佈:2020-10-20
引入依賴
<dependency> <groupId>org.apache.tika</groupId> <artifactId>tika-core</artifactId> <version>1.20</version> </dependency>
或
compile 'org.apache.tika:tika-core:1.20'
工具類
import lombok.AllArgsConstructor; import lombok.Getter; import lombok.extern.slf4j.Slf4j; import org.apache.tika.metadata.HttpHeaders; import org.apache.tika.metadata.Metadata; import org.apache.tika.metadata.TikaMetadataKeys; import org.apache.tika.parser.AutoDetectParser; import org.apache.tika.parser.ParseContext; import org.xml.sax.helpers.DefaultHandler; import java.io.File; import java.io.FileInputStream; import java.io.InputStream; import java.util.HashMap; import java.util.regex.Matcher; import java.util.regex.Pattern; /** * tika * * @author zhy */ @Slf4j public class TikaToolUtil { /** * 獲取型別 * * @param file 檔案 * @return String */ public static String getMimeType(File file) { if (file.isDirectory()) { return "the target is a directory"; } AutoDetectParser parser = new AutoDetectParser(); parser.setParsers(new HashMap<>()); Metadata metadata = new Metadata(); metadata.add(TikaMetadataKeys.RESOURCE_NAME_KEY,file.getName()); try (InputStream stream = new FileInputStream(file)) { parser.parse(stream,new DefaultHandler(),metadata,new ParseContext()); } catch (Exception e) { log.error(e.getMessage()); } return metadata.get(HttpHeaders.CONTENT_TYPE); } /** * 判斷是否是圖片 * * @param file 檔案 * @return boolean */ public static boolean isImage(File file) { String type = getMimeType(file); System.out.println(type); Pattern p = Pattern.compile(Type.IMAGE.name); Matcher m = p.matcher(type); return m.matches(); } /** * 判斷是否是zip * * @param file 檔案 * @return boolean */ public static boolean isZip(File file) { String type = getMimeType(file); System.out.println(type); Pattern p = Pattern.compile(Type.ZIP.name); Matcher m = p.matcher(type); return m.matches(); } /** * 判斷是否是dicom * * @param file 檔案 * @return boolean */ public static boolean isDicom(File file) { String type = getMimeType(file); Pattern p = Pattern.compile(Type.DCM.name); Matcher m = p.matcher(type); return m.matches(); } /** * 型別列舉 */ @Getter @AllArgsConstructor public enum Type { /** * dcm */ DCM("application/dicom"),/** * zip */ ZIP("application/zip"),/** * 圖片 */ IMAGE("image/.*"),/** * 視訊 */ VIDEO("video/*"); private String name; } public static void main(String[] args) { boolean image = isImage(new File("C:\\Users\\zhy\\Desktop\\dcm\\123.dcm")); System.out.println("zhy:" + image); } }
補充知識:java根據檔案流判斷檔案型別(字尾名)
我就廢話不多說了,大家還是直接看程式碼吧~
import java.io.FileInputStream; public class FileType{ public static String bytesToHexString(byte[] src) { StringBuilder stringBuilder = new StringBuilder(); if (src == null || src.length <= 0) { return null; } for (int i = 0; i < src.length; i++) { int v = src[i] & 0xFF; String hv = Integer.toHexString(v); if (hv.length() < 2) { stringBuilder.append(0); } stringBuilder.append(hv); } return stringBuilder.toString(); } /** * @param args */ public static void main(String[] args) throws Exception { FileInputStream is = new FileInputStream("F:\\相簿\\微信圖片\\03.jpg"); byte[] b = new byte[3]; is.read(b,b.length); String xxx = bytesToHexString(b); xxx = xxx.toUpperCase(); System.out.println("標頭檔案是:" + xxx); String ooo = TypeDict.checkType(xxx); System.out.println("字尾名是:" + ooo); } }
public class TypeDict { /** 常用檔案的檔案頭如下:(以前六位為準) JPEG (jpg),檔案頭:FFD8FF PNG (png),檔案頭:89504E47 GIF (gif),檔案頭:47494638 TIFF (tif),檔案頭:49492A00 Windows Bitmap (bmp),檔案頭:424D CAD (dwg),檔案頭:41433130 Adobe Photoshop (psd),檔案頭:38425053 Rich Text Format (rtf),檔案頭:7B5C727466 XML (xml),檔案頭:3C3F786D6C HTML (html),檔案頭:68746D6C3E Email [thorough only] (eml),檔案頭:44656C69766572792D646174653A Outlook Express (dbx),檔案頭:CFAD12FEC5FD746F Outlook (pst),檔案頭:2142444E MS Word/Excel (xls.or.doc),檔案頭:D0CF11E0 MS Access (mdb),檔案頭:5374616E64617264204A WordPerfect (wpd),檔案頭:FF575043 Postscript (eps.or.ps),檔案頭:252150532D41646F6265 Adobe Acrobat (pdf),檔案頭:255044462D312E Quicken (qdf),檔案頭:AC9EBD8F Windows Password (pwl),檔案頭:E3828596 ZIP Archive (zip),檔案頭:504B0304 RAR Archive (rar),檔案頭:52617221 Wave (wav),檔案頭:57415645 AVI (avi),檔案頭:41564920 Real Audio (ram),檔案頭:2E7261FD Real Media (rm),檔案頭:2E524D46 MPEG (mpg),檔案頭:000001BA MPEG (mpg),檔案頭:000001B3 Quicktime (mov),檔案頭:6D6F6F76 Windows Media (asf),檔案頭:3026B2758E66CF11 MIDI (mid),檔案頭:4D546864 */ public static String checkType(String xxxx) { switch (xxxx) { case "FFD8FF": return "jpg"; case "89504E": return "png"; case "474946": return "jif"; default: return "0000"; } } }
以上這篇判斷java檔案型別TikaToolKit的例項就是小編分享給大家的全部內容了,希望能給大家一個參考,也希望大家多多支援我們。