https://www.xiaogenban1993.com/blog/24.10/js%E8%AF%AD%E6%B3%95%E7%9A%84awk

[giscus[bot]]

https://www.xiaogenban1993.com/blog/24.10/js%E8%AF%AD%E6%B3%95%E7%9A%84awk

Generated by FreeCoder

https://www.xiaogenban1993.com/blog/24.10/js%E8%AF%AD%E6%B3%95%E7%9A%84awk

[sunwu51]

flat的名字被占用了，改成jtxt了，地址：crates ， github

[sunwu51]

后经过多次测试发现变量赋值语句是性能的瓶颈，不仅使得处理大文件时候，内存爆炸，而且速度很慢。
后将赋值改为从上下文中set进去，而不是var语句解释赋值，性能和内存占用都有了改善，尤其是内存稳定在了100M左右。

use std::fs::File;
use std::io::{self, BufRead, BufReader};
use clap::{Arg, Command};
use deno_core::JsRuntime;
use deno_core::RuntimeOptions;
// use deno_core::serde_v8;
use deno_core::v8;

fn main() {
    // 定义参数形式为 jtxt [option] function [file]
    let matches = Command::new("jtxt")
        .version("1.0")
        .author("Your Name <sunwu51@126.com>")
        .about("Processes lines of input with JavaScript")
        .arg(Arg::new("begin")
            .short('b')
            .long("begin")
            .help("JavaScript code to execute before processing any lines")
            .value_parser(clap::builder::ValueParser::string()))
        .arg(Arg::new("end")
            .short('e')
            .long("end")
            .help("JavaScript code to execute after processing all lines")
            .value_parser(clap::builder::ValueParser::string()))
        .arg(Arg::new("function")
            .help("JavaScript code to process each line, l is the origin string")
            .required(true)
            .index(1))
        .arg(Arg::new("file")
            .help("Path to the input file. If not provided, reads from stdin.")
            .index(2))
        .get_matches();

    let begin_code = matches.get_one::<String>("begin");
    let end_code = matches.get_one::<String>("end").cloned();
    let js_function = matches.get_one::<String>("function").unwrap();
    let file_path = matches.get_one::<String>("file");

    // 创建JavaScript 执行上下文
    let mut runtime = JsRuntime::new(RuntimeOptions::default());

    // 创建全局变量
    runtime.execute_script("<anon>", "var ctx = {}, n1=0, n2=0, n3=0, s='', arr=[];").expect("Eval failed");
    // 执行begin的代码块，如果有的话
    if let Some(code) = begin_code {
        runtime.execute_script("<anon>", code.to_string()).expect("Eval failed");
    }

    // 逐行读取文件或者管道内容
    let input: Box<dyn BufRead> = if let Some(path) = file_path {
        Box::new(BufReader::new(File::open(path).expect("Failed to open file")))
    } else {
        Box::new(io::stdin().lock())
    };
    runtime.execute_script("<anon>", 
        format!("function process(){{ {} }}", js_function)).expect("Eval failed");
    for line in input.lines() {
        let line = line.unwrap();
        {
            // 创建一个 V8 值
            let scope = &mut runtime.handle_scope();
            let value = v8::String::new(scope, &line).unwrap();
            // 将 V8 值绑定到全局对象
            let global = scope.get_current_context().global(scope);
            let l = v8::String::new(scope, "l").unwrap().into();
            global.set(scope, l, value.into());
        }
        runtime.execute_script("<anon>", "process()").expect("Eval failed");
    }
    if let Some(code) = end_code {
        runtime.execute_script("<anon>", code).expect("Eval failed");
    }
}

对160M和10G文件统计字数，可以看到内存占用一直在100M以内，而160M文件处理速度是2s以内，10G是2min以内，已经和awk的40s非常接近了(awk测试下来是30-50s)。

# 内存占用一直在100M以内
$ top 
    PID USER      PR  NI    VIRT    RES    SHR S  %CPU  %MEM     TIME+ COMMAND                                                                                                 
  28640 gitpod    20   0   33.5g  62864  18428 R 101.0   0.1   0:27.12 jtxt 
  
gitpod /workspace/jtxt (base) $ time cargo run -r -- 'n1+=l.length' -e 'console.log(n1)' 100w.txt 
    Finished `release` profile [optimized] target(s) in 0.11s
     Running `target/release/jtxt n1+=l.length -e 'console.log(n1)' 100w.txt`
171980954

real    0m1.882s
user    0m1.745s
sys     0m0.149s

gitpod /workspace/jtxt (base) $ time cargo run -r -- 'n1+=l.length' -e 'console.log(n1)' largefile.txt 
    Finished `release` profile [optimized] target(s) in 0.09s
     Running `target/release/jtxt n1+=l.length -e 'console.log(n1)' largefile.txt`
10675354954

real    1m47.251s
user    1m43.004s
sys     0m3.177s