Feature: Highlight non-printable characters

assets/syntaxes/show-nonprintable.sublime-syntax

@@ -0,0 +1,27 @@
+%YAML 1.2
+---
+# http://www.sublimetext.com/docs/3/syntax.html
+name: Highlight non-printables
+file_extensions:
+    - show-nonprintable
+scope: whitespace
+contexts:
+  main:
+    - match: "•"
+      scope: support.function.show-nonprintable.space
+    - match: "├─*┤"
+      scope: constant.character.escape.show-nonprintable.tab
+    - match: "↹"
+      scope: constant.character.escape.show-nonprintable.tab
+    - match: "␊"
+      scope: keyword.operator.show-nonprintable.line-feed
+    - match: "␍"
+      scope: string.show-nonprintable.carriage-return
+    - match: "␀"
+      scope: entity.other.attribute-name.show-nonprintable.null
+    - match: "␇"
+      scope: entity.other.attribute-name.show-nonprintable.bell
+    - match: "␛"
+      scope: entity.other.attribute-name.show-nonprintable.escape
+    - match: "␈"
+      scope: entity.other.attribute-name.show-nonprintable.backspace

src/app.rs

@@ -37,6 +37,9 @@ pub struct Config<'a> {
     /// The explicitly configured language, if any
     pub language: Option<&'a str>,
 
+    /// Whether or not to show/replace non-printable characters like space, tab and newline.
+    pub show_nonprintable: bool,
+
     /// The character width of the terminal
     pub term_width: usize,
 
@@ -169,7 +172,14 @@ impl App {
 
         Ok(Config {
             true_color: is_truecolor_terminal(),
-            language: self.matches.value_of("language"),
+            language: self.matches.value_of("language").or_else(|| {
+                if self.matches.is_present("show-all") {
+                    Some("show-nonprintable")
+                } else {
+                    None
+                }
+            }),
+            show_nonprintable: self.matches.is_present("show-all"),
             output_wrap: if !self.interactive_output {
                 // We don't have the tty width when piping to another program.
                 // There's no point in wrapping when this is the case.

src/clap_app.rs

@@ -158,6 +158,18 @@ pub fn build_app(interactive_output: bool) -> ClapApp<'static, 'static> {
                      '--style=numbers'",
                 ),
         )
+        .arg(
+            Arg::with_name("show-all")
+                .long("show-all")
+                .alias("show-nonprintable")
+                .short("A")
+                .conflicts_with("language")
+                .help("Show non-printable characters (space, tab, newline, ..).")
+                .long_help(
+                    "Show non-printable characters like space, tab or newline. \
+                     Use '--tabs' to control the width of the tab-placeholders.",
+                ),
+        )
         .arg(
             Arg::with_name("line-range")
                 .long("line-range")

src/controller.rs

@@ -78,7 +78,6 @@ impl<'b> Controller<'b> {
         line_ranges: &LineRanges,
     ) -> Result<()> {
         let mut line_buffer = Vec::new();
-
         let mut line_number: usize = 1;
 
         while reader.read_line(&mut line_buffer)? {

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: &str, tab_width: usize) -> String {
+    let mut output = String::new();
+
+    let tab_width = if tab_width == 0 { 4 } else { tab_width };
+
+    for chr in input.chars() {
+        match chr {
+            // space
+            ' ' => output.push('•'),
+            // tab
+            '\t' => {
+                if tab_width == 1 {
+                    output.push('↹');
+                } else {
+                    output.push('├');
+                    output.push_str(&"─".repeat(tab_width - 2));
+                    output.push('┤');
+                }
+            }
+            // line feed
+            '\x0A' => output.push('␊'),
+            // carriage return
+            '\x0D' => output.push('␍'),
+            // null
+            '\x00' => output.push('␀'),
+            // bell
+            '\x07' => output.push('␇'),
+            // backspace
+            '\x08' => output.push('␈'),
+            // escape
+            '\x1B' => output.push('␛'),
+            // anything else
+            _ => output.push(chr),
+        }
+    }
+
+    output
+}

src/printer.rs

@@ -22,7 +22,7 @@ use diff::get_git_diff;
 use diff::LineChanges;
 use errors::*;
 use inputfile::{InputFile, InputFileReader};
-use preprocessor::expand;
+use preprocessor::{expand_tabs, replace_nonprintable};
 use style::OutputWrap;
 use terminal::{as_terminal_escaped, to_ansi_color};
 
@@ -177,7 +177,7 @@ impl<'a> InteractivePrinter<'a> {
 
     fn preprocess(&self, text: &str, cursor: &mut usize) -> String {
         if self.config.tab_width > 0 {
-            expand(text, self.config.tab_width, cursor)
+            expand_tabs(text, self.config.tab_width, cursor)
         } else {
             text.to_string()
         }
@@ -251,7 +251,7 @@ impl<'a> Printer for InteractivePrinter<'a> {
         line_number: usize,
         line_buffer: &[u8],
     ) -> Result<()> {
-        let line = match self.content_type {
+        let mut line = match self.content_type {
             ContentType::BINARY => {
                 return Ok(());
             }
@@ -263,6 +263,11 @@ impl<'a> Printer for InteractivePrinter<'a> {
                 .unwrap_or("Invalid UTF-16BE".into()),
             _ => String::from_utf8_lossy(&line_buffer).to_string(),
         };
+
+        if self.config.show_nonprintable {
+            line = replace_nonprintable(&mut line, self.config.tab_width);
+        }
+
         let regions = {
             let highlighter = match self.highlighter {
                 Some(ref mut highlighter) => highlighter,