Feature: Highlight non-printable characters

Adds a new `-A`/`--show-all` option (in analogy to GNU Linux `cat`s option) that
highlights non-printable characters like space, tab or newline.

This works in two steps:
- **Preprocessing**: replace space by `•`, replace tab by `├──┤`, replace
newline by `␤`, etc.
- **Highlighting**: Use a newly written Sublime syntax to highlight
these special symbols.

Note: This feature is not technically a drop-in replacement for GNU `cat`s
`--show-all` but it has the same purpose.

1 files changed, 40 insertions, 1 deletions

diff --git a/src/preprocessor.rs b/src/preprocessor.rs
index 0a99e07d..a69f453e 100644
--- a/src/preprocessor.rs
+++ b/src/preprocessor.rs
@@ -1,7 +1,7 @@
 use console::AnsiCodeIterator;
 
 /// Expand tabs like an ANSI-enabled expand(1).
-pub fn expand(line: &str, width: usize, cursor: &mut usize) -> String {
+pub fn expand_tabs(line: &str, width: usize, cursor: &mut usize) -> String {
     let mut buffer = String::with_capacity(line.len() * 2);
 
     for chunk in AnsiCodeIterator::new(line) {
@@ -32,3 +32,42 @@ pub fn expand(line: &str, width: usize, cursor: &mut usize) -> String {
 
     buffer
 }
+
+pub fn replace_nonprintable(input: &mut Vec<u8>, output: &mut Vec<u8>, tab_width: usize) {
+    output.clear();
+
+    let tab_width = if tab_width == 0 {
+        4
+    } else if tab_width == 1 {
+        2
+    } else {
+        tab_width
+    };
+
+    for chr in input {
+        match *chr {
+            // space
+            b' ' => output.extend_from_slice("•".as_bytes()),
+            // tab
+            b'\t' => {
+                output.extend_from_slice("├".as_bytes());
+                output.extend_from_slice("─".repeat(tab_width - 2).as_bytes());
+                output.extend_from_slice("┤".as_bytes());
+            }
+            // new line
+            b'\n' => output.extend_from_slice("␤".as_bytes()),
+            // carriage return
+            b'\r' => output.extend_from_slice("␍".as_bytes()),
+            // null
+            0x00 => output.extend_from_slice("␀".as_bytes()),
+            // bell
+            0x07 => output.extend_from_slice("␇".as_bytes()),
+            // backspace
+            0x08 => output.extend_from_slice("␈".as_bytes()),
+            // escape
+            0x1B => output.extend_from_slice("␛".as_bytes()),
+            // anything else
+            _ => output.push(*chr),
+        }
+    }
+}