0.10.5: UTF-8 Tokenizer Fix

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "parallel"
-version = "0.10.4"
+version = "0.10.5"
 authors = ["Michael Aaron Murphy <mmstickman@gmail.com>"]
 license = "MIT"
 description = "Command-line CPU load balancer for executing jobs in parallel"
@@ -10,7 +10,7 @@ readme = "README.md"
 
 [dependencies]
 itoa         = "0.1"
-numtoa       = "0.0.3"
+numtoa       = "0.0.5"
 num_cpus     = "1.2"
 permutate    = "0.2"
 arrayvec     = "0.3"

README.md

@@ -1,7 +1,7 @@
 # MIT/Rust Parallel: A Command-line CPU Load Balancer Written in Rust
-[![Crates.io](https://img.shields.io/crates/v/parallel.svg)](https://github.com/mmstick/parallel)
+[![Crates.io](https://img.shields.io/crates/v/parallel.svg)](https://crates.io/crates/parallel)
 [![Tokei SLoC Count](https://tokei.rs/b1/github/mmstick/parallel)](https://github.com/mmstick/parallel)
-[![AUR](https://img.shields.io/aur/version/parallel-rust.svg)](https://github.com/mmstick/parallel)
+[![AUR](https://img.shields.io/aur/version/parallel-rust.svg)](https://aur.archlinux.org/packages/parallel-rust/)
 [![OpenHub Statistics](https://www.openhub.net/p/rust-parallel/widgets/project_thin_badge?format=gif&ref=Thin+badge)](https://www.openhub.net/p/rust-parallel/)
 
 This is an attempt at recreating the functionality of [GNU Parallel](https://www.gnu.org/software/parallel/), a work-stealer for the command-line, in Rust under a MIT license. The end goal will be to support much of the functionality of `GNU Parallel` and then to extend the functionality further for the next generation of command-line utilities written in Rust. While functionality is important, with the application being developed in Rust, the goal is to also be as fast and efficient as possible.

src/arguments/mod.rs

@@ -263,7 +263,7 @@ impl Args {
 fn write_stdin_to_disk(max_args: usize, mut unprocessed_path: PathBuf) -> Result<usize, ParseErr> {
     println!("parallel: reading inputs from standard input");
     unprocessed_path.push("unprocessed");
-    let disk_buffer = fs::OpenOptions::new().write(true).create(true).open(&unprocessed_path)
+    let disk_buffer = fs::OpenOptions::new().truncate(true).write(true).create(true).open(&unprocessed_path)
         .map_err(|why| ParseErr::File(FileErr::Open(unprocessed_path.clone(), why)))?;
     let mut disk_buffer = BufWriter::new(disk_buffer);
     let mut number_of_arguments = 0;
@@ -314,7 +314,7 @@ fn write_inputs_to_disk(lists: Vec<Vec<String>>, current_inputs: Vec<String>, ma
     mut unprocessed_path: PathBuf) -> Result<usize, ParseErr>
 {
     unprocessed_path.push("unprocessed");
-    let disk_buffer = fs::OpenOptions::new().write(true).create(true).open(&unprocessed_path)
+    let disk_buffer = fs::OpenOptions::new().truncate(true).write(true).create(true).open(&unprocessed_path)
         .map_err(|why| ParseErr::File(FileErr::Open(unprocessed_path.to_owned(), why)))?;
     let mut disk_buffer = BufWriter::new(disk_buffer);
     let mut number_of_arguments = 0;

src/execute/receive.rs

@@ -93,7 +93,7 @@ pub fn receive_messages(input_rx: Receiver<State>, args: Args, base: &str, proce
     let processed_file = fs::OpenOptions::new().create(true).write(true).open(processed_path).unwrap();
     let mut processed_file = BufWriter::new(processed_file);
     // An opened disk buffer pointing to the error file.
-    let error_file = fs::OpenOptions::new().create(true).write(true).open(errors_path).unwrap();
+    let error_file = fs::OpenOptions::new().truncate(true).create(true).write(true).open(errors_path).unwrap();
     let mut error_file = BufWriter::new(error_file);
     // Obtaining the number of digits in the total number of inputs is required for padding purposes.
     let mut id_pad_length = args.ninputs.digits();

src/tokenizer/mod.rs

@@ -87,7 +87,8 @@ pub fn tokenize(tokens: &mut ArrayVec<[Token; 128]>, template: &'static str, pat
     // Mark the index where the argument's first character begins.
     let mut argument_start = 0;
 
-    for (id, character) in template.chars().enumerate() {
+    let mut id = 0;
+    for character in template.chars() {
         match (character, pattern_matching) {
             // This condition initiates the pattern matching
             ('{', false) => {
@@ -126,6 +127,7 @@ pub fn tokenize(tokens: &mut ArrayVec<[Token; 128]>, template: &'static str, pat
             },
             (_, _) => ()
         }
+        id += character.len_utf8();
     }
 
     // In the event that there is leftover data that was not matched, this will add the final