add command line option to show full category name

This patch adds `clap` as a dependency for command-line argument
parsing, and introduces a `-f` flag to allow toggling whether or not the
full names of character classes are displayed.

Cargo.lock

@@ -2,24 +2,117 @@
 # It is not intended for manual editing.
 version = 3
 
+[[package]]
+name = "atty"
+version = "0.2.14"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d9b39be18770d11421cdb1b9947a45dd3f37e93092cbf377614828a319d5fee8"
+dependencies = [
+ "hermit-abi",
+ "libc",
+ "winapi",
+]
+
+[[package]]
+name = "autocfg"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d468802bab17cbc0cc575e9b053f41e72aa36bfa6b7f55e3529ffa43161b97fa"
+
+[[package]]
+name = "bitflags"
+version = "1.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bef38d45163c2f1dde094a7dfd33ccf595c92905c8f8f4fdc18d06fb1037718a"
+
 [[package]]
 name = "bytecount"
 version = "0.6.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2c676a478f63e9fa2dd5368a42f28bba0d6c560b775f38583c8bbaa7fcd67c9c"
 
+[[package]]
+name = "clap"
+version = "3.2.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "86447ad904c7fb335a790c9d7fe3d0d971dc523b8ccd1561a520de9a85302750"
+dependencies = [
+ "atty",
+ "bitflags",
+ "clap_derive",
+ "clap_lex",
+ "indexmap",
+ "once_cell",
+ "strsim",
+ "termcolor",
+ "textwrap",
+]
+
+[[package]]
+name = "clap_derive"
+version = "3.2.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ea0c8bce528c4be4da13ea6fead8965e95b6073585a2f05204bd8f4119f82a65"
+dependencies = [
+ "heck",
+ "proc-macro-error",
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "clap_lex"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2850f2f5a82cbf437dd5af4d49848fbdfc27c157c3d010345776f952765261c5"
+dependencies = [
+ "os_str_bytes",
+]
+
 [[package]]
 name = "fnv"
 version = "1.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3f9eec918d3f24069decb9af1554cad7c880e2da24a9afd88aca000531ab82c1"
 
+[[package]]
+name = "hashbrown"
+version = "0.12.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8a9ee70c43aaf417c914396645a0fa852624801b24ebb7ae78fe8272889ac888"
+
 [[package]]
 name = "heck"
 version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "2540771e65fc8cb83cd6e8a237f70c319bd5c29f78ed1084ba5d50eeac86f7f9"
 
+[[package]]
+name = "hermit-abi"
+version = "0.1.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "62b467343b94ba476dcb2500d242dadbb39557df889310ac77c5d99100aaac33"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "indexmap"
+version = "1.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "10a35a97730320ffe8e2d410b5d3b69279b98d2c14bdb8b70ea89ecf7888d41e"
+dependencies = [
+ "autocfg",
+ "hashbrown",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.132"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8371e4e5341c3a96db127eb2465ac681ced4c433e01dd0e938adbef26ba93ba5"
+
 [[package]]
 name = "libshire"
 version = "0.1.0"
@@ -28,6 +121,18 @@ dependencies = [
  "serde",
 ]
 
+[[package]]
+name = "once_cell"
+version = "1.14.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2f7254b99e31cad77da24b08ebf628882739a608578bb1bcdfc1f9c21260d7c0"
+
+[[package]]
+name = "os_str_bytes"
+version = "6.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9ff7415e9ae3fff1225851df9e0d9e4e5479f947619774677a63572e55e80eff"
+
 [[package]]
 name = "papergrid"
 version = "0.5.1"
@@ -87,6 +192,12 @@ version = "1.0.144"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0f747710de3dcd43b88c9168773254e809d8ddbdf9653b84e2554ab219f17860"
 
+[[package]]
+name = "strsim"
+version = "0.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73473c0e59e6d5812c5dfe2a064a6444949f089e20eec9a2e5506596494e4623"
+
 [[package]]
 name = "syn"
 version = "1.0.99"
@@ -122,6 +233,21 @@ dependencies = [
  "syn",
 ]
 
+[[package]]
+name = "termcolor"
+version = "1.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bab24d30b911b2376f3a13cc2cd443142f0c81dda04c118693e35b3835757755"
+dependencies = [
+ "winapi-util",
+]
+
+[[package]]
+name = "textwrap"
+version = "0.15.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "949517c0cf1bf4ee812e2e07e08ab448e3ae0d23472aee8a06c985f0c8815b16"
+
 [[package]]
 name = "unicode-ident"
 version = "1.0.4"
@@ -138,6 +264,7 @@ checksum = "c0edd1e5b14653f783770bce4a4dabb4a5108a5370a5f5d8cfe8710c361f6c8b"
 name = "utfdump"
 version = "0.1.0"
 dependencies = [
+ "clap",
  "libshire",
  "tabled",
  "utfdump_core",
@@ -152,3 +279,34 @@ name = "version_check"
 version = "0.9.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f"
+
+[[package]]
+name = "winapi"
+version = "0.3.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5c839a674fcd7a98952e593242ea400abe93992746761e38641405d28b00f419"
+dependencies = [
+ "winapi-i686-pc-windows-gnu",
+ "winapi-x86_64-pc-windows-gnu",
+]
+
+[[package]]
+name = "winapi-i686-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ac3b87c63620426dd9b991e5ce0329eff545bccbbb34f3be09ff6fb6ab51b7b6"
+
+[[package]]
+name = "winapi-util"
+version = "0.1.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "70ec6ce85bb158151cae5e5c87f95a8e97d2c0c4b001223f33a334e3ce5de178"
+dependencies = [
+ "winapi",
+]
+
+[[package]]
+name = "winapi-x86_64-pc-windows-gnu"
+version = "0.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"

utfdump_bin/Cargo.toml

@@ -7,6 +7,7 @@ edition = "2021"
 utfdump_core = { path = "../utfdump_core" }
 libshire = { git = "https://github.com/pantonshire/libshire", branch = "main" }
 tabled = "0.8.0"
+clap = { version = "3.2.22", features = ["derive"] }
 
 [build-dependencies]
 utfdump_core = { path = "../utfdump_core" }

utfdump_bin/src/main.rs

@@ -1,5 +1,6 @@
 use std::{fmt, io::{self, Read}};
 
+use clap::Parser;
 use libshire::strings::CappedString;
 use tabled::{Tabled, Table, Style};
 
@@ -7,7 +8,16 @@ use utfdump_core::{chardata::Category, encoded::Data};
 
 const UNICODE_DATA: &[u8] = include_bytes!(concat!(env!("OUT_DIR"), "/unicode_data_encoded"));
 
+#[derive(Parser)]
+#[clap(author, version, about, long_about = None)]
+struct Args {
+    #[clap(short, long, action)]
+    full_category_names: bool,
+}
+
 fn main() {
+    let args = Args::parse();
+
     let data = Data::<'static>::from_bytes(UNICODE_DATA).unwrap();
 
     let input = {
@@ -32,7 +42,10 @@ fn main() {
 
             if let Some(char_data) = data.get(c as u32) {
                 name = Optional::Some(char_data.name());
-                category = Optional::Some(char_data.category());
+                category = Optional::Some(DisplayCategory {
+                    category: char_data.category(),
+                    full_name: args.full_category_names,
+                });
 
                 let ccc = char_data.ccc();
                 char_combining_class = Optional::Some(ccc);
@@ -68,14 +81,14 @@ fn main() {
 struct OutRow {
     #[tabled(rename = "")]
     display_char: CappedString<8>, 
-    #[tabled(rename = "Codepoint")]
+    #[tabled(rename = "Code")]
     codepoint: Codepoint,
     #[tabled(rename = "UTF-8")]
     utf_8_bytes: Utf8Bytes,
     #[tabled(rename = "Name")]
     name: Optional<&'static str>,
     #[tabled(rename = "Category")]
-    category: Optional<Category>,
+    category: Optional<DisplayCategory>,
     #[tabled(rename = "Combining")]
     char_combining_class: Optional<u8>,
 }
@@ -124,3 +137,20 @@ impl fmt::Display for Utf8Bytes {
         Ok(())
     }
 }
+
+#[derive(Debug)]
+struct DisplayCategory {
+    category: Category,
+    full_name: bool,
+}
+
+impl fmt::Display for DisplayCategory {
+    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
+        if self.full_name {
+            write!(f, "{}", self.category.full_name())
+        } else {
+            write!(f, "{}", self.category.abbr())
+        }
+    }
+}
+

utfdump_core/src/chardata.rs

@@ -231,7 +231,7 @@ impl Category {
 
 impl fmt::Display for Category {
     fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
-        write!(f, "{}: {}", self.abbr(), self.full_name())
+        write!(f, "{}", self.abbr())
     }
 }