join: add support for non-unicode field separators

This allows for `-t` to take invalid unicode (but still single-byte) values
on unix-like platforms. Other platforms, which as of the time of this commit
do not support `OsStr::as_bytes()`, could possibly be supported in the future,
but would require design decisions as to what that means.

src/uu/join/src/join.rs

@@ -14,6 +14,8 @@ use clap::{crate_version, App, AppSettings, Arg};
 use std::cmp::Ordering;
 use std::fs::File;
 use std::io::{stdin, stdout, BufRead, BufReader, Split, Stdin, Write};
+#[cfg(unix)]
+use std::os::unix::ffi::OsStrExt;
 use uucore::display::Quotable;
 use uucore::error::{set_exit_code, UResult, USimpleError};
 
@@ -532,8 +534,19 @@ pub fn uumain(args: impl uucore::Args) -> UResult<()> {
     settings.key1 = get_field_number(keys, key1)?;
     settings.key2 = get_field_number(keys, key2)?;
 
-    if let Some(value_str) = matches.value_of("t") {
-        let value = value_str.as_bytes();
+    if let Some(value_os) = matches.value_of_os("t") {
+        #[cfg(unix)]
+        let value = value_os.as_bytes();
+        #[cfg(not(unix))]
+        let value = match value_os.to_str() {
+            Some(value) => value.as_bytes(),
+            None => {
+                return Err(USimpleError::new(
+                    1,
+                    "unprintable field separators are only supported on unix-like platforms",
+                ))
+            }
+        };
         settings.separator = match value.len() {
             0 => Sep::Line,
             1 => Sep::Char(value[0]),
@@ -541,7 +554,7 @@ pub fn uumain(args: impl uucore::Args) -> UResult<()> {
             _ => {
                 return Err(USimpleError::new(
                     1,
-                    format!("multi-character tab {}", value_str),
+                    format!("multi-character tab {}", value_os.to_string_lossy()),
                 ))
             }
         };
@@ -655,6 +668,7 @@ FILENUM is 1 or 2, corresponding to FILE1 or FILE2",
                 .short('t')
                 .takes_value(true)
                 .value_name("CHAR")
+                .allow_invalid_utf8(true)
                 .help("use CHAR as input and output field separator"),
         )
         .arg(

tests/by-util/test_join.rs

@@ -1,6 +1,10 @@
 // spell-checker:ignore (words) autoformat
 
 use crate::common::util::*;
+#[cfg(unix)]
+use std::{ffi::OsStr, os::unix::ffi::OsStrExt};
+#[cfg(windows)]
+use std::{ffi::OsString, os::windows::ffi::OsStringExt};
 
 #[test]
 fn empty_files() {
@@ -364,6 +368,32 @@ fn non_unicode() {
         .arg("non-unicode_2.bin")
         .succeeds()
         .stdout_only_fixture("non-unicode.expected");
+
+    #[cfg(unix)]
+    {
+        let invalid_utf8: u8 = 167;
+        new_ucmd!()
+            .arg("-t")
+            .arg(OsStr::from_bytes(&[invalid_utf8]))
+            .arg("non-unicode_1.bin")
+            .arg("non-unicode_2.bin")
+            .succeeds()
+            .stdout_only_fixture("non-unicode_sep.expected");
+    }
+
+    #[cfg(windows)]
+    {
+        let invalid_utf16: OsString = OsStringExt::from_wide(&[0xD800]);
+        new_ucmd!()
+            .arg("-t")
+            .arg(&invalid_utf16)
+            .arg("non-unicode_1.bin")
+            .arg("non-unicode_2.bin")
+            .fails()
+            .stderr_is(
+                "join: unprintable field separators are only supported on unix-like platforms",
+            );
+    }
 }
 
 #[test]