Add :character-info command (#4000)

3 files changed, 192 insertions, 0 deletions

diff --git a/book/src/generated/typable-cmd.md b/book/src/generated/typable-cmd.md
index 66e6ac03..0ff501a3 100644
--- a/book/src/generated/typable-cmd.md
+++ b/book/src/generated/typable-cmd.md
@@ -43,6 +43,7 @@
 | `:change-current-directory`, `:cd` | Change the current working directory. |
 | `:show-directory`, `:pwd` | Show the current working directory. |
 | `:encoding` | Set encoding. Based on `https://encoding.spec.whatwg.org`. |
+| `:character-info`, `:char` | Get info about the character under the primary cursor. |
 | `:reload` | Discard changes and reload from the source file. |
 | `:reload-all` | Discard changes and reload all documents from the source files. |
 | `:update` | Write changes only if the file has been modified. |
diff --git a/helix-term/src/commands/typed.rs b/helix-term/src/commands/typed.rs
index f2495d8c..1fd11b65 100644
--- a/helix-term/src/commands/typed.rs
+++ b/helix-term/src/commands/typed.rs
@@ -4,6 +4,7 @@ use crate::job::Job;
 
 use super::*;
 
+use helix_core::encoding;
 use helix_view::editor::{Action, CloseError, ConfigEvent};
 use ui::completers::{self, Completer};
 
@@ -1033,6 +1034,131 @@ fn set_encoding(
     }
 }
 
+/// Shows info about the character under the primary cursor.
+fn get_character_info(
+    cx: &mut compositor::Context,
+    _args: &[Cow<str>],
+    event: PromptEvent,
+) -> anyhow::Result<()> {
+    if event != PromptEvent::Validate {
+        return Ok(());
+    }
+
+    let (view, doc) = current_ref!(cx.editor);
+    let text = doc.text().slice(..);
+
+    let grapheme_start = doc.selection(view.id).primary().cursor(text);
+    let grapheme_end = graphemes::next_grapheme_boundary(text, grapheme_start);
+
+    if grapheme_start == grapheme_end {
+        return Ok(());
+    }
+
+    let grapheme = text.slice(grapheme_start..grapheme_end).to_string();
+    let encoding = doc.encoding();
+
+    let printable = grapheme.chars().fold(String::new(), |mut s, c| {
+        match c {
+            '\0' => s.push_str("\\0"),
+            '\t' => s.push_str("\\t"),
+            '\n' => s.push_str("\\n"),
+            '\r' => s.push_str("\\r"),
+            _ => s.push(c),
+        }
+
+        s
+    });
+
+    // Convert to Unicode codepoints if in UTF-8
+    let unicode = if encoding == encoding::UTF_8 {
+        let mut unicode = " (".to_owned();
+
+        for (i, char) in grapheme.chars().enumerate() {
+            if i != 0 {
+                unicode.push(' ');
+            }
+
+            unicode.push_str("U+");
+
+            let codepoint: u32 = if char.is_ascii() {
+                char.into()
+            } else {
+                // Not ascii means it will be multi-byte, so strip out the extra
+                // bits that encode the length & mark continuation bytes
+
+                let s = String::from(char);
+                let bytes = s.as_bytes();
+
+                // First byte starts with 2-4 ones then a zero, so strip those off
+                let first = bytes[0];
+                let codepoint = first & (0xFF >> (first.leading_ones() + 1));
+                let mut codepoint = u32::from(codepoint);
+
+                // Following bytes start with 10
+                for byte in bytes.iter().skip(1) {
+                    codepoint <<= 6;
+                    codepoint += u32::from(*byte) & 0x3F;
+                }
+
+                codepoint
+            };
+
+            unicode.push_str(&format!("{codepoint:0>4x}"));
+        }
+
+        unicode.push(')');
+        unicode
+    } else {
+        String::new()
+    };
+
+    // Give the decimal value for ascii characters
+    let dec = if encoding.is_ascii_compatible() && grapheme.len() == 1 {
+        format!(" Dec {}", grapheme.as_bytes()[0])
+    } else {
+        String::new()
+    };
+
+    let hex = {
+        let mut encoder = encoding.new_encoder();
+        let max_encoded_len = encoder
+            .max_buffer_length_from_utf8_without_replacement(grapheme.len())
+            .unwrap();
+        let mut bytes = Vec::with_capacity(max_encoded_len);
+        let mut current_byte = 0;
+        let mut hex = String::new();
+
+        for (i, char) in grapheme.chars().enumerate() {
+            if i != 0 {
+                hex.push_str(" +");
+            }
+
+            let (result, _input_bytes_read) = encoder.encode_from_utf8_to_vec_without_replacement(
+                &char.to_string(),
+                &mut bytes,
+                true,
+            );
+
+            if let encoding::EncoderResult::Unmappable(char) = result {
+                bail!("{char:?} cannot be mapped to {}", encoding.name());
+            }
+
+            for byte in &bytes[current_byte..] {
+                hex.push_str(&format!(" {byte:0>2x}"));
+            }
+
+            current_byte = bytes.len();
+        }
+
+        hex
+    };
+
+    cx.editor
+        .set_status(format!("\"{printable}\"{unicode}{dec} Hex{hex}"));
+
+    Ok(())
+}
+
 /// Reload the [`Document`] from its source file.
 fn reload(
     cx: &mut compositor::Context,
@@ -2132,6 +2258,13 @@ pub const TYPABLE_COMMAND_LIST: &[TypableCommand] = &[
             completer: None,
         },
         TypableCommand {
+            name: "character-info",
+            aliases: &["char"],
+            doc: "Get info about the character under the primary cursor.",
+            fun: get_character_info,
+            completer: None,
+        },
+        TypableCommand {
             name: "reload",
             aliases: &[],
             doc: "Discard changes and reload from the source file.",
diff --git a/helix-term/tests/test/commands.rs b/helix-term/tests/test/commands.rs
index 6e7275f5..da2e020e 100644
--- a/helix-term/tests/test/commands.rs
+++ b/helix-term/tests/test/commands.rs
@@ -354,3 +354,61 @@ async fn test_extend_line() -> anyhow::Result<()> {
 
     Ok(())
 }
+
+#[tokio::test(flavor = "multi_thread")]
+async fn test_character_info() -> anyhow::Result<()> {
+    // UTF-8, single byte
+    test_key_sequence(
+        &mut helpers::AppBuilder::new().build()?,
+        Some("ih<esc>h:char<ret>"),
+        Some(&|app| {
+            assert_eq!(
+                r#""h" (U+0068) Dec 104 Hex 68"#,
+                app.editor.get_status().unwrap().0
+            );
+        }),
+        false,
+    )
+    .await?;
+
+    // UTF-8, multi-byte
+    test_key_sequence(
+        &mut helpers::AppBuilder::new().build()?,
+        Some("ië<esc>h:char<ret>"),
+        Some(&|app| {
+            assert_eq!(
+                r#""ë" (U+0065 U+0308) Hex 65 + cc 88"#,
+                app.editor.get_status().unwrap().0
+            );
+        }),
+        false,
+    )
+    .await?;
+
+    // Multiple characters displayed as one, escaped characters
+    test_key_sequence(
+        &mut helpers::AppBuilder::new().build()?,
+        Some(":line<minus>ending crlf<ret>:char<ret>"),
+        Some(&|app| {
+            assert_eq!(
+                r#""\r\n" (U+000d U+000a) Hex 0d + 0a"#,
+                app.editor.get_status().unwrap().0
+            );
+        }),
+        false,
+    )
+    .await?;
+
+    // Non-UTF-8
+    test_key_sequence(
+        &mut helpers::AppBuilder::new().build()?,
+        Some(":encoding ascii<ret>ih<esc>h:char<ret>"),
+        Some(&|app| {
+            assert_eq!(r#""h" Dec 104 Hex 68"#, app.editor.get_status().unwrap().0);
+        }),
+        false,
+    )
+    .await?;
+
+    Ok(())
+}