Merge pull request #212 from sharkdp/add-ascii-character-table

Add pure ASCII character table
sharkdp · Dec 11, 2023 · 7a9234c · 7a9234c
2 parents 711627b + 45fa72e
commit 7a9234c
Show file tree

Hide file tree

Showing 3 changed files with 79 additions and 12 deletions.
diff --git a/src/lib.rs b/src/lib.rs
@@ -26,6 +26,7 @@ pub enum ByteCategory {
 #[non_exhaustive]
 pub enum CharacterTable {
  Default,
+ Ascii,
  CP437,
 }
 
@@ -83,6 +84,14 @@ impl Byte {
  AsciiOther => '•',
  NonAscii => '×',
  },
+ CharacterTable::Ascii => match self.category() {
+ Null => '.',
+ AsciiPrintable => self.0 as char,
+ AsciiWhitespace if self.0 == 0x20 => ' ',
+ AsciiWhitespace => '.',
+ AsciiOther => '.',
+ NonAscii => '.',
+ },
  CharacterTable::CP437 => CP437[self.0 as usize],
  }
  }

diff --git a/src/main.rs b/src/main.rs
@@ -144,6 +144,21 @@ fn run() -> Result<()> {
  .action(ArgAction::SetTrue)
  .help("Show the character panel on the right. This is the default, unless --no-characters has been specified."),
  )
+ .arg(
+ Arg::new("character-table")
+ .long("character-table")
+ .value_name("FORMAT")
+ .value_parser(["default", "ascii", "codepage-437"])
+ .default_value("default")
+ .help(
+ "Defines how bytes are mapped to characters:\n \
+ \"default\": show printable ASCII characters as-is, '⋄' for NULL bytes, \
+ ' ' for space, '_' for other ASCII whitespace, \
+ '•' for other ASCII characters, and '×' for non-ASCII bytes.\n \
+ \"ascii\": show printable ASCII as-is, ' ' for space, '.' for everything else.\n \
+ \"codepage-437\": uses code page 437 (for non-ASCII bytes).\n"
+ ),
+ )
  .arg(
  Arg::new("no_position")
  .short('P')
@@ -213,18 +228,6 @@ fn run() -> Result<()> {
  .hide(true)
  .help("An alias for '--endianness=little'."),
  )
- .arg(
- Arg::new("character-table")
- .long("character-table")
- .value_name("FORMAT")
- .value_parser(["default", "codepage-437"])
- .default_value("default")
- .help(
- "The character table that should be used. 'default' \
- will show dots for non-ASCII characters, 'codepage-437' \
- will use code page 437 for those characters."
- ),
- )
  .arg(
  Arg::new("base")
  .short('b')
@@ -497,6 +500,7 @@ fn run() -> Result<()> {
  .as_ref()
  {
  "default" => CharacterTable::Default,
+ "ascii" => CharacterTable::Ascii,
  "codepage-437" => CharacterTable::CP437,
  _ => unreachable!(),
  };

diff --git a/tests/integration_tests.rs b/tests/integration_tests.rs
@@ -623,6 +623,60 @@ mod character_table {
  use super::hexyl;
  use super::PrettyAssert;
 
+ #[test]
+ fn ascii() {
+ hexyl()
+ .arg("hello_world_elf64")
+ .arg("--color=never")
+ .arg("--character-table=ascii")
+ .assert()
+ .success()
+ .pretty_stdout(
+ "┌────────┬─────────────────────────┬─────────────────────────┬────────┬────────┐
+│00000000│ 7f 45 4c 46 02 01 01 00 ┊ 00 00 00 00 00 00 00 00 │.ELF....┊........│
+│00000010│ 02 00 3e 00 01 00 00 00 ┊ 00 10 40 00 00 00 00 00 │..>.....┊..@.....│
+│00000020│ 40 00 00 00 00 00 00 00 ┊ 28 20 00 00 00 00 00 00 │@.......┊( ......│
+│00000030│ 00 00 00 00 40 00 38 00 ┊ 03 00 40 00 04 00 03 00 │[email protected].┊..@.....│
+│00000040│ 01 00 00 00 04 00 00 00 ┊ 00 00 00 00 00 00 00 00 │........┊........│
+│00000050│ 00 00 40 00 00 00 00 00 ┊ 00 00 40 00 00 00 00 00 │..@.....┊..@.....│
+│00000060│ e8 00 00 00 00 00 00 00 ┊ e8 00 00 00 00 00 00 00 │........┊........│
+│00000070│ 00 10 00 00 00 00 00 00 ┊ 01 00 00 00 05 00 00 00 │........┊........│
+│00000080│ 00 10 00 00 00 00 00 00 ┊ 00 10 40 00 00 00 00 00 │........┊..@.....│
+│00000090│ 00 10 40 00 00 00 00 00 ┊ 1d 00 00 00 00 00 00 00 │..@.....┊........│
+│000000a0│ 1d 00 00 00 00 00 00 00 ┊ 00 10 00 00 00 00 00 00 │........┊........│
+│000000b0│ 01 00 00 00 06 00 00 00 ┊ 00 20 00 00 00 00 00 00 │........┊. ......│
+│000000c0│ 00 20 40 00 00 00 00 00 ┊ 00 20 40 00 00 00 00 00 │. @.....┊. @.....│
+│000000d0│ 0e 00 00 00 00 00 00 00 ┊ 0e 00 00 00 00 00 00 00 │........┊........│
+│000000e0│ 00 10 00 00 00 00 00 00 ┊ 00 00 00 00 00 00 00 00 │........┊........│
+│000000f0│ 00 00 00 00 00 00 00 00 ┊ 00 00 00 00 00 00 00 00 │........┊........│
+│* │ ┊ │ ┊ │
+│00001000│ ba 0e 00 00 00 b9 00 20 ┊ 40 00 bb 01 00 00 00 b8 │....... ┊@.......│
+│00001010│ 04 00 00 00 cd 80 b8 01 ┊ 00 00 00 cd 80 00 00 00 │........┊........│
+│00001020│ 00 00 00 00 00 00 00 00 ┊ 00 00 00 00 00 00 00 00 │........┊........│
+│* │ ┊ │ ┊ │
+│00002000│ 48 65 6c 6c 6f 2c 20 77 ┊ 6f 72 6c 64 21 0a 00 2e │Hello, w┊orld!...│
+│00002010│ 73 68 73 74 72 74 61 62 ┊ 00 2e 74 65 78 74 00 2e │shstrtab┊..text..│
+│00002020│ 64 61 74 61 00 00 00 00 ┊ 00 00 00 00 00 00 00 00 │data....┊........│
+│00002030│ 00 00 00 00 00 00 00 00 ┊ 00 00 00 00 00 00 00 00 │........┊........│
+│* │ ┊ │ ┊ │
+│00002060│ 00 00 00 00 00 00 00 00 ┊ 0b 00 00 00 01 00 00 00 │........┊........│
+│00002070│ 06 00 00 00 00 00 00 00 ┊ 00 10 40 00 00 00 00 00 │........┊..@.....│
+│00002080│ 00 10 00 00 00 00 00 00 ┊ 1d 00 00 00 00 00 00 00 │........┊........│
+│00002090│ 00 00 00 00 00 00 00 00 ┊ 10 00 00 00 00 00 00 00 │........┊........│
+│000020a0│ 00 00 00 00 00 00 00 00 ┊ 11 00 00 00 01 00 00 00 │........┊........│
+│000020b0│ 03 00 00 00 00 00 00 00 ┊ 00 20 40 00 00 00 00 00 │........┊. @.....│
+│000020c0│ 00 20 00 00 00 00 00 00 ┊ 0e 00 00 00 00 00 00 00 │. ......┊........│
+│000020d0│ 00 00 00 00 00 00 00 00 ┊ 04 00 00 00 00 00 00 00 │........┊........│
+│000020e0│ 00 00 00 00 00 00 00 00 ┊ 01 00 00 00 03 00 00 00 │........┊........│
+│000020f0│ 00 00 00 00 00 00 00 00 ┊ 00 00 00 00 00 00 00 00 │........┊........│
+│00002100│ 0e 20 00 00 00 00 00 00 ┊ 17 00 00 00 00 00 00 00 │. ......┊........│
+│00002110│ 00 00 00 00 00 00 00 00 ┊ 01 00 00 00 00 00 00 00 │........┊........│
+│00002120│ 00 00 00 00 00 00 00 00 ┊ │........┊ │
+└────────┴─────────────────────────┴─────────────────────────┴────────┴────────┘
+",
+ );
+ }
+
  #[test]
  fn codepage_437() {
  hexyl()