Timings misc (#1945)

scripts/early-multi-language-timings/catrust2.rs

@@ -0,0 +1,14 @@
+//use std::fs::File;
+use std::io::{self, prelude::*, BufReader};
+
+fn main() -> io::Result<()> {
+    //let file = File::open("foo.txt")?;
+    let file = io::stdin();
+    let reader = BufReader::new(file);
+
+    for line in reader.lines() {
+        println!("{}", line?);
+    }
+
+    Ok(())
+}

scripts/early-multi-language-timings/ff1.rs

@@ -0,0 +1,24 @@
+// Claude
+
+use std::fs::File;
+use std::io::{self, BufRead, BufReader};
+
+// Method 1: Using BufReader with lines() - Good balance of speed and memory
+fn read_lines_buf_reader(path: &str) -> io::Result<()> {
+    let file = File::open(path)?;
+    let reader = BufReader::new(file);
+
+    let mut n = 0;
+    for line in reader.lines() {
+        let _line = line?;
+        // Process line here
+        n += 1;
+    }
+    println!("line count {}", n);
+
+    Ok(())
+}
+
+fn main() {
+  let _ = read_lines_buf_reader("/Users/kerl/tmp/big");
+}

scripts/early-multi-language-timings/ff2.rs

@@ -0,0 +1,21 @@
+// Claude
+
+use std::fs::File;
+use std::io::{self, BufRead, BufReader};
+
+// Method 2: Using BufReader with read_line - More control, similar performance
+fn read_lines_manual(path: &str) -> io::Result<()> {
+    let file = File::open(path)?;
+    let mut reader = BufReader::new(file);
+    let mut line = String::new();
+    
+    while reader.read_line(&mut line)? > 0 {
+        // Process line here
+        line.clear(); // Reuse the string buffer
+    }
+    Ok(())
+}
+
+fn main() {
+  let _ = read_lines_manual("/Users/kerl/tmp/big");
+}

scripts/early-multi-language-timings/ff3.rs

@@ -0,0 +1,21 @@
+// Claude
+
+use std::fs::File;
+use std::io::{self, BufRead, BufReader};
+
+// Method 3: Using custom buffer size for larger files
+fn read_lines_custom_buffer(path: &str) -> io::Result<()> {
+    const BUFFER_SIZE: usize = 128 * 1024; // 128KB buffer
+    let file = File::open(path)?;
+    let reader = BufReader::with_capacity(BUFFER_SIZE, file);
+    
+    for line in reader.lines() {
+        let _line = line?;
+        // Process line here
+    }
+    Ok(())
+}
+
+fn main() {
+  let _ = read_lines_custom_buffer("/Users/kerl/tmp/big");
+}

scripts/early-multi-language-timings/ff4.rs

@@ -0,0 +1,24 @@
+// Claude
+
+use std::fs::File;
+use std::io::{self, BufRead, BufReader};
+
+// Method 4: Memory mapped files for very large files
+fn read_lines_memmap(path: &str) -> io::Result<()> {
+    use memmap2::Mmap;
+    
+    let file = File::open(path)?;
+    let mmap = unsafe { Mmap::map(&file)? };
+    
+    // Convert memory map to string and iterate over lines
+    if let Ok(contents) = std::str::from_utf8(&mmap) {
+        for line in contents.lines() {
+            // Process line here
+        }
+    }
+    Ok(())
+}
+
+fn main() {
+  let _ = read_lines_custom_buffer("/Users/kerl/tmp/big");
+}

scripts/early-multi-language-timings/new-timings.sh

@@ -0,0 +1,9 @@
+justtime ./catc < ~/tmp/big > /dev/null
+justtime ./catc0 < ~/tmp/big > /dev/null
+justtime ./catm < ~/tmp/big > /dev/null
+justtime ./catrust < ~/tmp/big > /dev/null
+justtime ./catrust2 < ~/tmp/big > /dev/null
+justtime ./ff1 < ~/tmp/big > /dev/null
+justtime ./ff2 < ~/tmp/big > /dev/null
+justtime ./ff3 < ~/tmp/big > /dev/null
+justtime ./catgo < ~/tmp/big > /dev/null

scripts/early-multi-language-timings/new-timings.txt

@@ -0,0 +1,24 @@
+
+bash ./new-timings.sh
+TIME IN SECONDS 9.691 -- ./catc
+TIME IN SECONDS 8.137 -- ./catc0
+TIME IN SECONDS 0.005 -- ./catm
+TIME IN SECONDS 12.975 -- ./catrust
+TIME IN SECONDS 52.282 -- ./catrust2
+TIME IN SECONDS 7.488 -- ./ff1
+TIME IN SECONDS 4.646 -- ./ff2
+TIME IN SECONDS 6.932 -- ./ff3
+TIME IN SECONDS 6.412 -- ./catgo
+
+TIME IN SECONDS 0.005 -- ./catm
+TIME IN SECONDS 4.646 -- ./ff2
+TIME IN SECONDS 6.412 -- ./catgo
+TIME IN SECONDS 6.932 -- ./ff3
+TIME IN SECONDS 7.488 -- ./ff1
+TIME IN SECONDS 8.137 -- ./catc0
+TIME IN SECONDS 9.691 -- ./catc
+TIME IN SECONDS 12.975 -- ./catrust
+TIME IN SECONDS 52.282 -- ./catrust2
+
+$ justtime mlr cat ~/tmp/big > /dev/null
+TIME IN SECONDS 79.106 -- mlr cat /Users/kerl/tmp/big