More emoji

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "deunicode"
-version = "1.3.1"
+version = "1.3.2"
 authors = ["Kornel Lesinski <kornel@geekhood.net>", "Amit Chowdhury <amitc97@gmail.com>"]
 description = "Convert Unicode strings to pure ASCII by intelligently transliterating them. Suppors Emoji and Chinese."
 documentation = "https://docs.rs/deunicode"
@@ -9,7 +9,7 @@ homepage = "https://lib.rs/crates/deunicode"
 repository = "https://github.com/kornelski/deunicode/"
 readme = "README.md"
 include = ["src/*", "Cargo.toml", "README.md"]
-edition = "2018"
+edition = "2021"
 
 keywords = [
   "unidecode",
@@ -26,6 +26,7 @@ alloc = []
 
 [badges]
 travis-ci = { repository = "kornelski/deunicode" }
+maintenance = { status = "actively-developed" }
 
 [package.metadata.docs.rs]
 targets = ["x86_64-unknown-linux-gnu"]

README.md

@@ -49,6 +49,7 @@ Unicode data
 ------------
  * [`Text::Unidecode`](http://search.cpan.org/~sburke/Text-Unidecode-1.30/lib/Text/Unidecode.pm) by Sean M. Burke
  * [Unicodey](https://unicodey.com) by Cal Henderson
+ * [gh emoji](https://lib.rs/gh-emoji)
  * [any_ascii](https://anyascii.com/)
 
 For a detailed explanation on the rationale behind the original

scripts/Cargo.toml

@@ -2,7 +2,7 @@
 name = "unidecode-compress"
 version = "0.1.0"
 authors = ["Kornel <kornel@geekhood.net>"]
-edition = "2018"
+edition = "2021"
 
 [[bin]]
 name = "compress"
@@ -13,3 +13,4 @@ serde = "1.0.104"
 serde_json = "1.0.48"
 serde_derive = "1.0.104"
 any_ascii = "0.2.0"
+emojis = "0.4.0"

scripts/compress.rs

@@ -82,21 +82,47 @@ fn main() {
         if ch != "[?] " && ch != "[?]" {ch} else {UNKNOWN_CHAR}
     }).collect();
 
+    if all_codepoints.len() < 140000 { all_codepoints.resize(140000, UNKNOWN_CHAR); }
+
     all_codepoints['术' as usize] = "Shu ";
     all_codepoints['价' as usize] = "Jia ";
     all_codepoints['旅' as usize] = "Lv ";
     all_codepoints['什' as usize] = "Shen ";
     all_codepoints['么' as usize] = "Me ";
+    all_codepoints['❗' as usize] = "!";
+    all_codepoints['❕' as usize] = "!";
+    all_codepoints['❓' as usize] = "?";
+    all_codepoints['❔' as usize] = "?";
+    all_codepoints['➕' as usize] = "+";
+    all_codepoints['➖' as usize] = "-";
+    all_codepoints['➗' as usize] = "/";
+    all_codepoints['🟰' as usize] = "=";
+    all_codepoints['💲' as usize] = "$";
+    all_codepoints['💵' as usize] = "$";
+    all_codepoints['🌟' as usize] = "*";
+    all_codepoints['⭐' as usize] = "*";
 
     for &(ch, ref name) in gemoji.iter().chain(emoji1.iter()).chain(emoji2.iter()) {
-        while all_codepoints.len() <= ch {
-            all_codepoints.push(UNKNOWN_CHAR);
+        if all_codepoints.len() <= ch {
+            all_codepoints.resize(ch as usize+1, UNKNOWN_CHAR);
         }
         if "" == all_codepoints[ch] || "[?]" == all_codepoints[ch] || UNKNOWN_CHAR == all_codepoints[ch] || name.len() < all_codepoints[ch].len() {
             all_codepoints[ch] = name;
         }
     }
 
+    for (mut name, ch) in emojis::iter().filter(|e| e.as_str().chars().count() == 1)
+        .filter_map(|e| Some((e.shortcode().unwrap_or(e.name()), e.as_str().chars().next()? as usize))) {
+        if all_codepoints.len() <= ch {
+            all_codepoints.resize(ch as usize+1, UNKNOWN_CHAR);
+        }
+        if "" == all_codepoints[ch] || "[?]" == all_codepoints[ch] || UNKNOWN_CHAR == all_codepoints[ch] {
+            let new_name = format!("{} ", name.trim().replace('_', " ")).into_boxed_str();
+            name = Box::leak(new_name);
+            all_codepoints[ch] = name;
+        }
+    }
+
     for (i, ch) in all_codepoints.iter_mut().enumerate().skip(255) {
         if *ch == UNKNOWN_CHAR {
             let any = std::char::from_u32(i as u32)