Java 从CSV文件缓慢读取
我正在尝试读取csv文件,但速度很慢。下面是大致解释的代码:Java 从CSV文件缓慢读取,java,csv,Java,Csv,我正在尝试读取csv文件,但速度很慢。下面是大致解释的代码: private static Film[] readMoviesFromCSV() { // Regex to split by comma without splitting in double quotes. // https://regexr.com/3s3me <- example on this data var pattern = Pattern.compile(",(?=(?:[^\\\"]
private static Film[] readMoviesFromCSV() {
// Regex to split by comma without splitting in double quotes.
// https://regexr.com/3s3me <- example on this data
var pattern = Pattern.compile(",(?=(?:[^\\\"]*\\\"[^\\\"]*\\\")*[^\\\"]*$)");
Film[] films = null;
try (var br = new BufferedReader(new FileReader(FILENAME))) {
var start = System.currentTimeMillis();
var temparr = br.lines().skip(1).collect(Collectors.toList()); // skip first line and read into List
films = temparr.stream().parallel()
.map(pattern::split)
.filter(x -> x.length == 24 && x[7].equals("en")) // all fields(total 24) and english speaking movies
.filter(x -> (x[14].length() > 0)) // check if it has x[14] (date)
.map(movieData -> new Film(movieData[8], movieData[9], movieData[14], movieData[22], movieData[23], movieData[7]))
// movieData[8] = String title, movieData[9] = String overview
// movieData[14] = String date (constructor parses it to LocalDate object)
// movieData[22] = String avgRating
.toArray(Film[]::new);
System.out.println(MessageFormat.format("Execution time: {0}", (System.currentTimeMillis() - start)));
System.out.println(films.length);
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return films;
}
private static Film[]readMoviesFromCSV(){
//正则表达式以逗号分隔,不以双引号分隔。
// https://regexr.com/3s3me 这里是univocity parsers库的作者。您可以通过如下方式重写您在编辑中发布的代码,从而进一步加快代码的速度:
//initialize an arraylist with a good size to avoid reallocation
final ArrayList<Film> films = new ArrayList<Film>(20000);
CsvParserSettings parserSettings = new CsvParserSettings();
parserSettings.setLineSeparatorDetectionEnabled(true);
parserSettings.setHeaderExtractionEnabled(true);
//don't generate strings for columns you don't want
parserSettings.selectIndexes(7, 8, 9, 14, 22, 23);
//keep generating rows with the same number of columns found in the input
//indexes not selected will have nulls as they are not processed.
parserSettings.setColumnReorderingEnabled(false);
parserSettings.setProcessor(new AbstractRowProcessor(){
@Override
public void rowProcessed(String[] row, ParsingContext context) {
if(row.length == 24 && "en".equals(row[7]) && row[14] != null){
films.add(new Film(row[8], row[9], row[14], row[22], row[23], row[7]));
}
}
});
CsvParser parser = new CsvParser(parserSettings);
long start = System.currentTimeMillis();
try {
parser.parse(new File(FILENAME), "UTF-8");
} catch (FileNotFoundException e) {
e.printStackTrace();
}
System.out.printf(MessageFormat.format("Time: {0}",(System.currentTimeMillis()-start)));
return films.toArray(new Film[0]);
//使用合适的大小初始化arraylist以避免重新分配
最终ArrayList影片=新ArrayList(20000);
CsvParserSettings parserSettings=新的CsvParserSettings();
已启用parserSettings.setLineSeparatorDetectionEnabled(true);
parserSettings.setHeaderExtractionEnabled(true);
//不要为不需要的列生成字符串
选择索引(7、8、9、14、22、23);
//继续生成与输入中找到的列数相同的行
//未选择的索引将具有空值,因为它们未被处理。
parserSettings.setColumnReorderingEnabled(false);
setProcessor(新的AbstractRowProcessor(){
@凌驾
public void rowProcessed(字符串[]行,ParsingContext上下文){
if(row.length==24&&“en”.equals(row[7])&&row[14]!=null){
添加(新胶片(第[8]行、第[9]行、第[14]行、第[22]行、第[23]行、第[7]行));
}
}
});
CsvParser parser=新的CsvParser(parserSettings);
长启动=System.currentTimeMillis();
试一试{
parser.parse(新文件(文件名),“UTF-8”);
}catch(filenotfounde异常){
e、 printStackTrace();
}
printf(MessageFormat.format(“Time:{0}”,(System.currentTimeMillis()-start));
返回电影。toArray(新电影[0]);
为了方便起见,如果你必须把东西分成不同的类,你也可以在你的电影
类中
希望这有帮助。如果删除.parallel()
?不确定是否有帮助here@azro同样的,如果没有并行,可能会慢一点,但它的计时不正确,所以我不能确定。我将尝试使用一些库来读取它。要更精确地计算时间,请使用.nanoTime()更准确^^请注意,您不是在测量读取文件所需的时间。您是在测量读取文件和处理文件所需的时间。很可能是读取文件速度快,但处理速度慢。正则表达式的速度不快,逗号的“手动”搜索速度更快(可能是)
//initialize an arraylist with a good size to avoid reallocation
final ArrayList<Film> films = new ArrayList<Film>(20000);
CsvParserSettings parserSettings = new CsvParserSettings();
parserSettings.setLineSeparatorDetectionEnabled(true);
parserSettings.setHeaderExtractionEnabled(true);
//don't generate strings for columns you don't want
parserSettings.selectIndexes(7, 8, 9, 14, 22, 23);
//keep generating rows with the same number of columns found in the input
//indexes not selected will have nulls as they are not processed.
parserSettings.setColumnReorderingEnabled(false);
parserSettings.setProcessor(new AbstractRowProcessor(){
@Override
public void rowProcessed(String[] row, ParsingContext context) {
if(row.length == 24 && "en".equals(row[7]) && row[14] != null){
films.add(new Film(row[8], row[9], row[14], row[22], row[23], row[7]));
}
}
});
CsvParser parser = new CsvParser(parserSettings);
long start = System.currentTimeMillis();
try {
parser.parse(new File(FILENAME), "UTF-8");
} catch (FileNotFoundException e) {
e.printStackTrace();
}
System.out.printf(MessageFormat.format("Time: {0}",(System.currentTimeMillis()-start)));
return films.toArray(new Film[0]);