use comfy_table for output
This commit is contained in:
parent
6e2a978c01
commit
88499e3784
GPG key ID:
E333EC1335FFCCDB
3 changed files with 223 additions and 6 deletions
201
Cargo.lock
generated
201
Cargo.lock
generated
|
|
@ -2,6 +2,207 @@
|
|||
# It is not intended for manual editing.
|
||||
version = 4
|
||||
|
||||
[[package]]
|
||||
name = "bitflags"
|
||||
version = "2.11.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "c4512299f36f043ab09a583e57bceb5a5aab7a73db1805848e8fef3c9e8c78b3"
|
||||
|
||||
[[package]]
|
||||
name = "cfg-if"
|
||||
version = "1.0.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
|
||||
|
||||
[[package]]
|
||||
name = "comfy-table"
|
||||
version = "7.2.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "958c5d6ecf1f214b4c2bbbbf6ab9523a864bd136dcf71a7e8904799acfe1ad47"
|
||||
dependencies = [
|
||||
"crossterm",
|
||||
"unicode-segmentation",
|
||||
"unicode-width",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "crossterm"
|
||||
version = "0.29.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d8b9f2e4c67f833b660cdb0a3523065869fb35570177239812ed4c905aeff87b"
|
||||
dependencies = [
|
||||
"bitflags",
|
||||
"crossterm_winapi",
|
||||
"document-features",
|
||||
"parking_lot",
|
||||
"rustix",
|
||||
"winapi",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "crossterm_winapi"
|
||||
version = "0.9.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "acdd7c62a3665c7f6830a51635d9ac9b23ed385797f70a83bb8bafe9c572ab2b"
|
||||
dependencies = [
|
||||
"winapi",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "document-features"
|
||||
version = "0.2.12"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "d4b8a88685455ed29a21542a33abd9cb6510b6b129abadabdcef0f4c55bc8f61"
|
||||
dependencies = [
|
||||
"litrs",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "errno"
|
||||
version = "0.3.14"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
|
||||
dependencies = [
|
||||
"libc",
|
||||
"windows-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "libc"
|
||||
version = "0.2.185"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "52ff2c0fe9bc6cb6b14a0592c2ff4fa9ceb83eea9db979b0487cd054946a2b8f"
|
||||
|
||||
[[package]]
|
||||
name = "linux-raw-sys"
|
||||
version = "0.12.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "32a66949e030da00e8c7d4434b251670a91556f4144941d37452769c25d58a53"
|
||||
|
||||
[[package]]
|
||||
name = "litrs"
|
||||
version = "1.0.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "11d3d7f243d5c5a8b9bb5d6dd2b1602c0cb0b9db1621bafc7ed66e35ff9fe092"
|
||||
|
||||
[[package]]
|
||||
name = "lock_api"
|
||||
version = "0.4.14"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "224399e74b87b5f3557511d98dff8b14089b3dadafcab6bb93eab67d3aace965"
|
||||
dependencies = [
|
||||
"scopeguard",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "ngram-entropy"
|
||||
version = "0.1.0"
|
||||
dependencies = [
|
||||
"comfy-table",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "parking_lot"
|
||||
version = "0.12.5"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "93857453250e3077bd71ff98b6a65ea6621a19bb0f559a85248955ac12c45a1a"
|
||||
dependencies = [
|
||||
"lock_api",
|
||||
"parking_lot_core",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "parking_lot_core"
|
||||
version = "0.9.12"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "2621685985a2ebf1c516881c026032ac7deafcda1a2c9b7850dc81e3dfcb64c1"
|
||||
dependencies = [
|
||||
"cfg-if",
|
||||
"libc",
|
||||
"redox_syscall",
|
||||
"smallvec",
|
||||
"windows-link",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "redox_syscall"
|
||||
version = "0.5.18"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ed2bf2547551a7053d6fdfafda3f938979645c44812fbfcda098faae3f1a362d"
|
||||
dependencies = [
|
||||
"bitflags",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "rustix"
|
||||
version = "1.1.4"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b6fe4565b9518b83ef4f91bb47ce29620ca828bd32cb7e408f0062e9930ba190"
|
||||
dependencies = [
|
||||
"bitflags",
|
||||
"errno",
|
||||
"libc",
|
||||
"linux-raw-sys",
|
||||
"windows-sys",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "scopeguard"
|
||||
version = "1.2.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "94143f37725109f92c262ed2cf5e59bce7498c01bcc1502d7b9afe439a4e9f49"
|
||||
|
||||
[[package]]
|
||||
name = "smallvec"
|
||||
version = "1.15.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "67b1b7a3b5fe4f1376887184045fcf45c69e92af734b7aaddc05fb777b6fbd03"
|
||||
|
||||
[[package]]
|
||||
name = "unicode-segmentation"
|
||||
version = "1.13.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "9629274872b2bfaf8d66f5f15725007f635594914870f65218920345aa11aa8c"
|
||||
|
||||
[[package]]
|
||||
name = "unicode-width"
|
||||
version = "0.2.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
|
||||
|
||||
[[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-x86_64-pc-windows-gnu"
|
||||
version = "0.4.0"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "712e227841d057c1ee1cd2fb22fa7e5a5461ae8e48fa2ca79ec42cfc1931183f"
|
||||
|
||||
[[package]]
|
||||
name = "windows-link"
|
||||
version = "0.2.1"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
|
||||
|
||||
[[package]]
|
||||
name = "windows-sys"
|
||||
version = "0.61.2"
|
||||
source = "registry+https://github.com/rust-lang/crates.io-index"
|
||||
checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
|
||||
dependencies = [
|
||||
"windows-link",
|
||||
]
|
||||
|
|
|
|||
|
|
@ -4,3 +4,4 @@ version = "0.1.0"
|
|||
edition = "2024"
|
||||
|
||||
[dependencies]
|
||||
comfy-table = "7.2.2"
|
||||
|
|
|
|||
27
src/main.rs
27
src/main.rs
|
|
@ -6,6 +6,8 @@ use std::{
|
|||
process,
|
||||
};
|
||||
|
||||
use comfy_table::{CellAlignment, ContentArrangement, Table, presets::UTF8_FULL};
|
||||
|
||||
const USAGE: &str = "\
|
||||
usage: (ngram-entropy) | (ngram-entropy N) | (ngram-entropy MIN MAX)\
|
||||
";
|
||||
|
|
@ -37,16 +39,29 @@ fn main() {
|
|||
let mut src = Vec::new();
|
||||
io::stdin().read_to_end(&mut src).unwrap();
|
||||
|
||||
let mut table: HashMap<&[u8], u64> = HashMap::new();
|
||||
let mut table = Table::new();
|
||||
table
|
||||
.load_preset(UTF8_FULL)
|
||||
.apply_modifier(comfy_table::modifiers::UTF8_SOLID_INNER_BORDERS)
|
||||
.set_content_arrangement(ContentArrangement::Dynamic)
|
||||
.set_header(["n", "bits", "bits/byte", "unique ngrams"]);
|
||||
for column in table.column_iter_mut() {
|
||||
column.set_cell_alignment(CellAlignment::Right);
|
||||
}
|
||||
|
||||
let mut counts: HashMap<&[u8], u64> = HashMap::new();
|
||||
|
||||
for n in min..=max {
|
||||
let (ngrams, freqs) = ngram_freqs(n, &src, &mut table);
|
||||
let (ngrams, freqs) = ngram_freqs(n, &src, &mut counts);
|
||||
let bits = entropy(freqs);
|
||||
println!(
|
||||
"{n:2}: {bits:6.3} bits, {:.3} bits/byte ({ngrams} unique ngrams)",
|
||||
bits / n as f64
|
||||
);
|
||||
table.add_row([
|
||||
n.to_string(),
|
||||
format!("{bits:.3}"),
|
||||
format!("{:.3}", bits / n as f64),
|
||||
ngrams.to_string(),
|
||||
]);
|
||||
}
|
||||
println!("{table}");
|
||||
}
|
||||
|
||||
fn ngram_freqs<'a>(
|
||||
|
|
|
|||
Loading…
Reference in a new issue