将 .srt 文件拆分为相等的块
Split .srt file into equal chunks
我是新手，我需要将 Srt（字幕文件）拆分成多个块。
例如：如果我有一个视频的字幕文件（60 分钟）。然后字幕文件应该分成6个字幕文件，每个字幕文件10分钟。
即 6 X 10 = 60 分钟
需要分6块不分分钟
使用这些每个字幕 time/duration，我必须将视频分成相同的块。
我正在尝试这段代码，你能帮我看看我如何计算时间并分成块吗，
我能够实现多少分钟的 chuck i needed.But 卡在如何从源文件中读取该 chunck 分钟并创建一个新文件。然后如何从下一个 10 开始下一个块源文件的分钟数。
import org.apache.commons.io.IOUtils;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.DataInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.sql.Timestamp;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.List;
import java.util.stream.Stream;
/**
* The class SyncSRTSubtitles reads a subtitles .SRT file and offsets all the
* timestamps with the same specific value in msec.
*
* The format of the .SRT file is like this:
*
* 123
* 00:11:23,456 --> 00:11:25,234
* subtitle #123 text here
*
*
* @author Sorinel CRISTESCU
*/
public class SyncSRTSubtitles {
/**
* Entry point in the program.
*
* @param args
* @throws IOException
*/
public static void main(String[] args) throws IOException {
/* INPUT: offset value: negative = less (-) ... positive = more (+). */
long delta = (22 * 1000L + 000); /* msec */
/* INPUT: source & destination files */
String srcFileNm = "/Users/meh/Desktop/avatar.srt";
String destFileNm = "/Users/meh/Desktop/avatar1.srt";
/* offset algorithm: START */
File outFile = new File(destFileNm);
outFile.createNewFile();
FileWriter ofstream = new FileWriter(outFile);
BufferedWriter out = new BufferedWriter(ofstream);
/* Open the file that is the first command line parameter */
FileInputStream fstream = new FileInputStream(srcFileNm);
DataInputStream in = new DataInputStream(fstream);
BufferedReader br = new BufferedReader(new InputStreamReader(in));
String strLine;
// List<String> doc = IOUtils.readLines(in, StandardCharsets.UTF_8);
String strEnd = null;
long diff = 0;
String line;
String startTS1;
try (Stream<String> lines = Files.lines(Paths.get(srcFileNm))) {
line = lines.skip(1).findFirst().get();
String[] atoms = line.split(" --> ");
startTS1 = atoms[0];
}
System.out.println("bolo:" +line);
System.out.println("startTS1:" +startTS1);
String startTS = null;
String endTS = null;
/* Read File Line By Line */
while ((strLine = br.readLine()) != null) {
String[] atoms = strLine.split(" --> ");
if (atoms.length == 1) {
//out.write(strLine + "\n");
}
else {
startTS = atoms[0];
endTS = atoms[1];
// out.write(offsetTime(startTS, delta) + " --> "
// + offsetTime(endTS, delta) + "\n");
strEnd = endTS;
}
}
try {
SimpleDateFormat dateFormat = new SimpleDateFormat("hh:mm:ss");
Date parsedendDate = dateFormat.parse(strEnd);
Date parsedStartDate = dateFormat.parse(startTS1);
diff = parsedendDate.getTime() - parsedStartDate.getTime();
} catch(Exception e) { //this generic but you can control another types of exception
// look the origin of excption
}
System.out.println("strEnd");
System.out.println(strEnd);
/* Close the input streams */
in.close();
out.close();
System.out.println(diff);
long diff1 =diff/6;
System.out.println(diff1);
long diff2= (diff1*6);
System.out.println(diff2);
System.out.println((diff / 3600000) + " hour/s " + (diff % 3600000) / 60000 + " minutes");
System.out.println((diff1 / 3600000) + " hour/s " + (diff1 % 3600000) / 60000 + " minutes");
System.out.println((diff2 / 3600000) + " hour/s " + (diff2 % 3600000) / 60000 + " minutes");
/* offset algorithm: END */
System.out.println("DONE! Check the rsult oin the file: " + destFileNm);
}
/**
* Computes the timestamp offset.
*
* @param ts
* String value of the timestamp in format: "hh:MM:ss,mmm"
* @param delta
* long value of the offset in msec (positive or negative).
* @return String with the new timestamp representation.
*/
private static String offsetTime(String ts, long delta) {
long tsMsec = 0;
String atoms[] = ts.split("\,");
if (atoms.length == 2) {
tsMsec += Integer.parseInt(atoms[1]);
}
atoms = atoms[0].split(":");
tsMsec += Integer.parseInt(atoms[2]) * 1000L; /* seconds */
tsMsec += Integer.parseInt(atoms[1]) * 60000L; /* minutes */
tsMsec += Integer.parseInt(atoms[0]) * 3600000L; /* hours */
tsMsec += delta; /* here we do the offset. */
long h = tsMsec / 3600000L;
System.out.println(h);
String result = get2digit(h, 2) + ":";
System.out.println(result);
long r = tsMsec % 3600000L;
System.out.println(r);
long m = r / 60000L;
System.out.println(m);
result += get2digit(m, 2) + ":";
System.out.println(result);
r = r % 60000L;
System.out.println(r);
long s = r / 1000L;
result += get2digit(s, 2) + ",";
result += get2digit(r % 1000L, 3);
System.out.println(result);
return result;
}
/**
* Gets the string representation of the number, adding the prefix '0' to
* have the required length.
*
* @param n
* long number to convert to string.
* @param digits
* int number of digits required.
* @return String with the required length string (3 for digits = 3 -->
* "003")
*/
private static String get2digit(long n, int digits) {
String result = "" + n;
while (result.length() < digits) {
result = "0" + result;
}
return result;
}
}
请建议我怎样才能做到这一点？
您需要解析文件两次：
- 读取最后一次结束时间
- 第二次处理所有行和
生成输出文件。
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.util.List;
import org.apache.commons.io.FileUtils;
public class SplitSRTFiles {
/**
* Splits a SRT file in multiple files each containing an equal time duration.
* @param args
* [0] number of wanted chunks
* [1] source file name
* @throws IOException
*/
public static void main(String[] args) throws IOException {
int nrOfChunks = Integer.parseInt(args[0]);
File srtFile = new File(args[1]);
System.out.println("Splitting "+srtFile.getAbsolutePath()+" into "+nrOfChunks+" files.");
List<String> srcLines = FileUtils.readLines(srtFile);
long fileEndTime = lastEndTime(srcLines);
long msecsPerChunkFile = fileEndTime / nrOfChunks;
int destFileCounter = 1;
String[] fileNameParts = srtFile.getName().split("\.");
File outFile = new File(fileNameParts[0] + destFileCounter + "." + fileNameParts[1]);
System.out.println("Writing to "+outFile.getAbsolutePath());
outFile.createNewFile();
FileWriter ofstream = new FileWriter(outFile);
BufferedWriter out = new BufferedWriter(ofstream);
for (String line : srcLines) {
String[] atoms = line.split(" --> ");
if (atoms.length > 1) {
long startTS = toMSec(atoms[0]);
// check if start time of this subtitle is after the current
// chunk
if (startTS > msecsPerChunkFile * destFileCounter) {
// close existing file ...
out.close();
ofstream.close();
// ... and start a new file
destFileCounter++;
outFile = new File(srtFile.getParent(), fileNameParts[0] + destFileCounter + "." + fileNameParts[1]);
System.out.println("Writing to "+outFile.getAbsolutePath());
outFile.createNewFile();
ofstream = new FileWriter(outFile);
out = new BufferedWriter(ofstream);
}
}
out.write(line + "/n");
}
out.close();
ofstream.close();
System.out.println("Done.");
}
/**
* Calculates the time in msec of the end time of the last subtitle of the
* file
*
* @param lines
* read from file
* @return end time in milliseconds of the last subtitle
*/
public static long lastEndTime(List lines) throws IOException {
String endTS = null;
for (String line : lines) {
String[] atoms = line.split(" --> ");
if (atoms.length > 1) {
endTS = atoms[1];
}
}
return endTS == null ? 0L : toMSec(endTS);
}
public static long toMSec(String time) {
long tsMsec = 0;
String atoms[] = time.split("\,");
if (atoms.length == 2) {
tsMsec += Integer.parseInt(atoms[1]);
}
atoms = atoms[0].split(":");
tsMsec += Integer.parseInt(atoms[2]) * 1000L; /* seconds */
tsMsec += Integer.parseInt(atoms[1]) * 60000L; /* minutes */
tsMsec += Integer.parseInt(atoms[0]) * 3600000L; /* hours */
return tsMsec;
}
}
我想出了一个将文件分成块的方法，
public static void main(String args[]) throws IOException {
String FilePath = "/Users/meh/Desktop/escapeplan.srt";
FileInputStream fin = new FileInputStream(FilePath);
System.out.println("size: " +fin.getChannel().size());
long abc = 0l;
abc = (fin.getChannel().size())/3;
System.out.println("6: " +abc);
System.out.println("abc: " +abc);
//FilePath = args[1];
File filename = new File(FilePath);
long splitFileSize = 0,bytefileSize=0;
if (filename.exists()) {
try {
//bytefileSize = Long.parseLong(args[2]);
splitFileSize = abc;
Splitme spObj = new Splitme();
spObj.split(FilePath, (long) splitFileSize);
spObj = null;
} catch (Exception e) {
e.printStackTrace();
}
} else {
System.out.println("File Not Found....");
}
}
public void split(String FilePath, long splitlen) {
long leninfile = 0, leng = 0;
int count = 1, data;
try {
File filename = new File(FilePath);
InputStream infile = new BufferedInputStream(new FileInputStream(filename));
data = infile.read();
System.out.println("data");
System.out.println(data);
while (data != -1) {
filename = new File("/Users/meh/Documents/srt" + count + ".srt");
//RandomAccessFile outfile = new RandomAccessFile(filename, "rw");
OutputStream outfile = new BufferedOutputStream(new FileOutputStream(filename));
while (data != -1 && leng < splitlen) {
outfile.write(data);
leng++;
data = infile.read();
}
leninfile += leng;
leng = 0;
outfile.close();
changeTimeStamp(filename, count);
count++;
}
} catch (Exception e) {
e.printStackTrace();
}
}
我是新手，我需要将 Srt（字幕文件）拆分成多个块。
例如：如果我有一个视频的字幕文件（60 分钟）。然后字幕文件应该分成6个字幕文件，每个字幕文件10分钟。
即 6 X 10 = 60 分钟
需要分6块不分分钟
使用这些每个字幕 time/duration，我必须将视频分成相同的块。
我正在尝试这段代码，你能帮我看看我如何计算时间并分成块吗，
我能够实现多少分钟的 chuck i needed.But 卡在如何从源文件中读取该 chunck 分钟并创建一个新文件。然后如何从下一个 10 开始下一个块源文件的分钟数。
import org.apache.commons.io.IOUtils;
import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.DataInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.sql.Timestamp;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.List;
import java.util.stream.Stream;
/**
* The class SyncSRTSubtitles reads a subtitles .SRT file and offsets all the
* timestamps with the same specific value in msec.
*
* The format of the .SRT file is like this:
*
* 123
* 00:11:23,456 --> 00:11:25,234
* subtitle #123 text here
*
*
* @author Sorinel CRISTESCU
*/
public class SyncSRTSubtitles {
/**
* Entry point in the program.
*
* @param args
* @throws IOException
*/
public static void main(String[] args) throws IOException {
/* INPUT: offset value: negative = less (-) ... positive = more (+). */
long delta = (22 * 1000L + 000); /* msec */
/* INPUT: source & destination files */
String srcFileNm = "/Users/meh/Desktop/avatar.srt";
String destFileNm = "/Users/meh/Desktop/avatar1.srt";
/* offset algorithm: START */
File outFile = new File(destFileNm);
outFile.createNewFile();
FileWriter ofstream = new FileWriter(outFile);
BufferedWriter out = new BufferedWriter(ofstream);
/* Open the file that is the first command line parameter */
FileInputStream fstream = new FileInputStream(srcFileNm);
DataInputStream in = new DataInputStream(fstream);
BufferedReader br = new BufferedReader(new InputStreamReader(in));
String strLine;
// List<String> doc = IOUtils.readLines(in, StandardCharsets.UTF_8);
String strEnd = null;
long diff = 0;
String line;
String startTS1;
try (Stream<String> lines = Files.lines(Paths.get(srcFileNm))) {
line = lines.skip(1).findFirst().get();
String[] atoms = line.split(" --> ");
startTS1 = atoms[0];
}
System.out.println("bolo:" +line);
System.out.println("startTS1:" +startTS1);
String startTS = null;
String endTS = null;
/* Read File Line By Line */
while ((strLine = br.readLine()) != null) {
String[] atoms = strLine.split(" --> ");
if (atoms.length == 1) {
//out.write(strLine + "\n");
}
else {
startTS = atoms[0];
endTS = atoms[1];
// out.write(offsetTime(startTS, delta) + " --> "
// + offsetTime(endTS, delta) + "\n");
strEnd = endTS;
}
}
try {
SimpleDateFormat dateFormat = new SimpleDateFormat("hh:mm:ss");
Date parsedendDate = dateFormat.parse(strEnd);
Date parsedStartDate = dateFormat.parse(startTS1);
diff = parsedendDate.getTime() - parsedStartDate.getTime();
} catch(Exception e) { //this generic but you can control another types of exception
// look the origin of excption
}
System.out.println("strEnd");
System.out.println(strEnd);
/* Close the input streams */
in.close();
out.close();
System.out.println(diff);
long diff1 =diff/6;
System.out.println(diff1);
long diff2= (diff1*6);
System.out.println(diff2);
System.out.println((diff / 3600000) + " hour/s " + (diff % 3600000) / 60000 + " minutes");
System.out.println((diff1 / 3600000) + " hour/s " + (diff1 % 3600000) / 60000 + " minutes");
System.out.println((diff2 / 3600000) + " hour/s " + (diff2 % 3600000) / 60000 + " minutes");
/* offset algorithm: END */
System.out.println("DONE! Check the rsult oin the file: " + destFileNm);
}
/**
* Computes the timestamp offset.
*
* @param ts
* String value of the timestamp in format: "hh:MM:ss,mmm"
* @param delta
* long value of the offset in msec (positive or negative).
* @return String with the new timestamp representation.
*/
private static String offsetTime(String ts, long delta) {
long tsMsec = 0;
String atoms[] = ts.split("\,");
if (atoms.length == 2) {
tsMsec += Integer.parseInt(atoms[1]);
}
atoms = atoms[0].split(":");
tsMsec += Integer.parseInt(atoms[2]) * 1000L; /* seconds */
tsMsec += Integer.parseInt(atoms[1]) * 60000L; /* minutes */
tsMsec += Integer.parseInt(atoms[0]) * 3600000L; /* hours */
tsMsec += delta; /* here we do the offset. */
long h = tsMsec / 3600000L;
System.out.println(h);
String result = get2digit(h, 2) + ":";
System.out.println(result);
long r = tsMsec % 3600000L;
System.out.println(r);
long m = r / 60000L;
System.out.println(m);
result += get2digit(m, 2) + ":";
System.out.println(result);
r = r % 60000L;
System.out.println(r);
long s = r / 1000L;
result += get2digit(s, 2) + ",";
result += get2digit(r % 1000L, 3);
System.out.println(result);
return result;
}
/**
* Gets the string representation of the number, adding the prefix '0' to
* have the required length.
*
* @param n
* long number to convert to string.
* @param digits
* int number of digits required.
* @return String with the required length string (3 for digits = 3 -->
* "003")
*/
private static String get2digit(long n, int digits) {
String result = "" + n;
while (result.length() < digits) {
result = "0" + result;
}
return result;
}
}
请建议我怎样才能做到这一点？
您需要解析文件两次：
- 读取最后一次结束时间
- 第二次处理所有行和 生成输出文件。
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.util.List;
import org.apache.commons.io.FileUtils;
public class SplitSRTFiles {
/**
* Splits a SRT file in multiple files each containing an equal time duration.
* @param args
* [0] number of wanted chunks
* [1] source file name
* @throws IOException
*/
public static void main(String[] args) throws IOException {
int nrOfChunks = Integer.parseInt(args[0]);
File srtFile = new File(args[1]);
System.out.println("Splitting "+srtFile.getAbsolutePath()+" into "+nrOfChunks+" files.");
List<String> srcLines = FileUtils.readLines(srtFile);
long fileEndTime = lastEndTime(srcLines);
long msecsPerChunkFile = fileEndTime / nrOfChunks;
int destFileCounter = 1;
String[] fileNameParts = srtFile.getName().split("\.");
File outFile = new File(fileNameParts[0] + destFileCounter + "." + fileNameParts[1]);
System.out.println("Writing to "+outFile.getAbsolutePath());
outFile.createNewFile();
FileWriter ofstream = new FileWriter(outFile);
BufferedWriter out = new BufferedWriter(ofstream);
for (String line : srcLines) {
String[] atoms = line.split(" --> ");
if (atoms.length > 1) {
long startTS = toMSec(atoms[0]);
// check if start time of this subtitle is after the current
// chunk
if (startTS > msecsPerChunkFile * destFileCounter) {
// close existing file ...
out.close();
ofstream.close();
// ... and start a new file
destFileCounter++;
outFile = new File(srtFile.getParent(), fileNameParts[0] + destFileCounter + "." + fileNameParts[1]);
System.out.println("Writing to "+outFile.getAbsolutePath());
outFile.createNewFile();
ofstream = new FileWriter(outFile);
out = new BufferedWriter(ofstream);
}
}
out.write(line + "/n");
}
out.close();
ofstream.close();
System.out.println("Done.");
}
/**
* Calculates the time in msec of the end time of the last subtitle of the
* file
*
* @param lines
* read from file
* @return end time in milliseconds of the last subtitle
*/
public static long lastEndTime(List lines) throws IOException {
String endTS = null;
for (String line : lines) {
String[] atoms = line.split(" --> ");
if (atoms.length > 1) {
endTS = atoms[1];
}
}
return endTS == null ? 0L : toMSec(endTS);
}
public static long toMSec(String time) {
long tsMsec = 0;
String atoms[] = time.split("\,");
if (atoms.length == 2) {
tsMsec += Integer.parseInt(atoms[1]);
}
atoms = atoms[0].split(":");
tsMsec += Integer.parseInt(atoms[2]) * 1000L; /* seconds */
tsMsec += Integer.parseInt(atoms[1]) * 60000L; /* minutes */
tsMsec += Integer.parseInt(atoms[0]) * 3600000L; /* hours */
return tsMsec;
}
}
我想出了一个将文件分成块的方法，
public static void main(String args[]) throws IOException {
String FilePath = "/Users/meh/Desktop/escapeplan.srt";
FileInputStream fin = new FileInputStream(FilePath);
System.out.println("size: " +fin.getChannel().size());
long abc = 0l;
abc = (fin.getChannel().size())/3;
System.out.println("6: " +abc);
System.out.println("abc: " +abc);
//FilePath = args[1];
File filename = new File(FilePath);
long splitFileSize = 0,bytefileSize=0;
if (filename.exists()) {
try {
//bytefileSize = Long.parseLong(args[2]);
splitFileSize = abc;
Splitme spObj = new Splitme();
spObj.split(FilePath, (long) splitFileSize);
spObj = null;
} catch (Exception e) {
e.printStackTrace();
}
} else {
System.out.println("File Not Found....");
}
}
public void split(String FilePath, long splitlen) {
long leninfile = 0, leng = 0;
int count = 1, data;
try {
File filename = new File(FilePath);
InputStream infile = new BufferedInputStream(new FileInputStream(filename));
data = infile.read();
System.out.println("data");
System.out.println(data);
while (data != -1) {
filename = new File("/Users/meh/Documents/srt" + count + ".srt");
//RandomAccessFile outfile = new RandomAccessFile(filename, "rw");
OutputStream outfile = new BufferedOutputStream(new FileOutputStream(filename));
while (data != -1 && leng < splitlen) {
outfile.write(data);
leng++;
data = infile.read();
}
leninfile += leng;
leng = 0;
outfile.close();
changeTimeStamp(filename, count);
count++;
}
} catch (Exception e) {
e.printStackTrace();
}
}