From e5a675fe458ea8a8ce16554cf4994fe96f7783f0 Mon Sep 17 00:00:00 2001 From: Avril Date: Thu, 8 Oct 2020 04:23:01 +0100 Subject: [PATCH] Initial commit --- .gitignore | 2 + Cargo.lock | 252 ++++++++++++++++++++++++++++++++++++++++++++++++++++ Cargo.toml | 11 +++ README | 6 ++ src/main.rs | 47 ++++++++++ 5 files changed, 318 insertions(+) create mode 100644 .gitignore create mode 100644 Cargo.lock create mode 100644 Cargo.toml create mode 100644 README create mode 100644 src/main.rs diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..e2a3069 --- /dev/null +++ b/.gitignore @@ -0,0 +1,2 @@ +/target +*~ diff --git a/Cargo.lock b/Cargo.lock new file mode 100644 index 0000000..3d3df23 --- /dev/null +++ b/Cargo.lock @@ -0,0 +1,252 @@ +# This file is automatically @generated by Cargo. +# It is not intended for manual editing. +[[package]] +name = "autocfg" +version = "1.0.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cdb031dd78e28731d87d56cc8ffef4a8f36ca26c38fe2de700543e627f8a464a" + +[[package]] +name = "cfg-if" +version = "0.1.10" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4785bdd1c96b2a846b2bd7cc02e86b6b3dbf14e7e53446c4f54c92a361040822" + +[[package]] +name = "dtoa" +version = "0.4.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "134951f4028bdadb9b84baf4232681efbf277da25144b9b0ad65df75946c422b" + +[[package]] +name = "either" +version = "1.6.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e78d4f1cc4ae33bbfc157ed5d5a5ef3bc29227303d595861deb238fcec4e9457" + +[[package]] +name = "fixedbitset" +version = "0.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "37ab347416e802de484e4d03c7316c48f1ecb56574dfd4a46a80f173ce1de04d" + +[[package]] +name = "getopts" +version = "0.2.21" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "14dbbfd5c71d70241ecf9e6f13737f7b5ce823821063188d7e46c41d371eebd5" +dependencies = [ + "unicode-width", +] + +[[package]] +name = "getrandom" +version = "0.1.15" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc587bc0ec293155d5bfa6b9891ec18a1e330c234f896ea47fbada4cadbe47e6" +dependencies = [ + "cfg-if", + "libc", + "wasi", +] + +[[package]] +name = "hashbrown" +version = "0.9.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d7afe4a420e3fe79967a00898cc1f4db7c8a49a9333a29f8a4bd76a253d5cd04" + +[[package]] +name = "indexmap" +version = "1.6.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "55e2e4c765aa53a0424761bf9f41aa7a6ac1efa87238f59560640e27fca028f2" +dependencies = [ + "autocfg", + "hashbrown", +] + +[[package]] +name = "itertools" +version = "0.9.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "284f18f85651fe11e8a991b2adb42cb078325c996ed026d994719efcfca1d54b" +dependencies = [ + "either", +] + +[[package]] +name = "libc" +version = "0.2.79" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2448f6066e80e3bfc792e9c98bf705b4b0fc6e8ef5b43e5889aff0eaa9c58743" + +[[package]] +name = "linked-hash-map" +version = "0.5.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "8dd5a6d5999d9907cda8ed67bbd137d3af8085216c2ac62de5be860bd41f304a" + +[[package]] +name = "markov" +version = "0.1.1" +dependencies = [ + "markov 1.1.0", +] + +[[package]] +name = "markov" +version = "1.1.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fc6ad68e26d51a9558f65e93b9795c9422630d0932717a3235668bb9ab71e3fd" +dependencies = [ + "getopts", + "itertools", + "petgraph", + "rand", + "serde", + "serde_derive", + "serde_yaml", +] + +[[package]] +name = "petgraph" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "467d164a6de56270bd7c4d070df81d07beace25012d5103ced4e9ff08d6afdb7" +dependencies = [ + "fixedbitset", + "indexmap", +] + +[[package]] +name = "ppv-lite86" +version = "0.2.9" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c36fa947111f5c62a733b652544dd0016a43ce89619538a8ef92724a6f501a20" + +[[package]] +name = "proc-macro2" +version = "1.0.24" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1e0704ee1a7e00d7bb417d0770ea303c1bccbabf0ef1667dae92b5967f5f8a71" +dependencies = [ + "unicode-xid", +] + +[[package]] +name = "quote" +version = "1.0.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "aa563d17ecb180e500da1cfd2b028310ac758de548efdd203e18f283af693f37" +dependencies = [ + "proc-macro2", +] + +[[package]] +name = "rand" +version = "0.7.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6a6b1679d49b24bbfe0c803429aa1874472f50d9b363131f0e89fc356b544d03" +dependencies = [ + "getrandom", + "libc", + "rand_chacha", + "rand_core", + "rand_hc", +] + +[[package]] +name = "rand_chacha" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f4c8ed856279c9737206bf725bf36935d8666ead7aa69b52be55af369d193402" +dependencies = [ + "ppv-lite86", + "rand_core", +] + +[[package]] +name = "rand_core" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "90bde5296fc891b0cef12a6d03ddccc162ce7b2aff54160af9338f8d40df6d19" +dependencies = [ + "getrandom", +] + +[[package]] +name = "rand_hc" +version = "0.2.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ca3129af7b92a17112d59ad498c6f81eaf463253766b90396d39ea7a39d6613c" +dependencies = [ + "rand_core", +] + +[[package]] +name = "serde" +version = "1.0.116" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "96fe57af81d28386a513cbc6858332abc6117cfdb5999647c6444b8f43a370a5" + +[[package]] +name = "serde_derive" +version = "1.0.116" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f630a6370fd8e457873b4bd2ffdae75408bc291ba72be773772a4c2a065d9ae8" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "serde_yaml" +version = "0.8.13" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ae3e2dd40a7cdc18ca80db804b7f461a39bb721160a85c9a1fa30134bf3c02a5" +dependencies = [ + "dtoa", + "linked-hash-map", + "serde", + "yaml-rust", +] + +[[package]] +name = "syn" +version = "1.0.42" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9c51d92969d209b54a98397e1b91c8ae82d8c87a7bb87df0b29aa2ad81454228" +dependencies = [ + "proc-macro2", + "quote", + "unicode-xid", +] + +[[package]] +name = "unicode-width" +version = "0.1.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9337591893a19b88d8d87f2cec1e73fad5cdfd10e5a6f349f498ad6ea2ffb1e3" + +[[package]] +name = "unicode-xid" +version = "0.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f7fe0bb3479651439c9112f72b6c505038574c9fbb575ed1bf3b797fa39dd564" + +[[package]] +name = "wasi" +version = "0.9.0+wasi-snapshot-preview1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cccddf32554fecc6acb585f82a32a72e28b48f8c4c1883ddfeeeaa96f7d8e519" + +[[package]] +name = "yaml-rust" +version = "0.4.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "39f0c922f1a334134dc2f7a8b67dc5d25f0735263feec974345ff706bcf20b0d" +dependencies = [ + "linked-hash-map", +] diff --git a/Cargo.toml b/Cargo.toml new file mode 100644 index 0000000..7a76f0b --- /dev/null +++ b/Cargo.toml @@ -0,0 +1,11 @@ +[package] +name = "markov" +version = "0.1.1" +description = "Generate string of text from Markov chain fed by stdin" +authors = ["Avril "] +edition = "2018" + +# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html + +[dependencies] +chain = {package = "markov", version = "1.1.0"} \ No newline at end of file diff --git a/README b/README new file mode 100644 index 0000000..5c0318f --- /dev/null +++ b/README @@ -0,0 +1,6 @@ +Generate strings from markov chain of stdin + +Usage: + +$ cat corpus | markov +$ cat corpus | markov diff --git a/src/main.rs b/src/main.rs new file mode 100644 index 0000000..22f352d --- /dev/null +++ b/src/main.rs @@ -0,0 +1,47 @@ +use chain::{ + Chain, +}; +use std::{ + io::{ + BufRead, + self, + }, +}; + +fn buffered_read_all_lines io::Result<()>>(input: &mut T, mut then: F) -> io::Result +{ + let mut buffer = String::new(); + let mut read; + let mut total=0; + while {read = input.read_line(&mut buffer)?; read!=0} { + then(&buffer[..])?; + buffer.clear(); + total += read; + } + Ok(total) +} + +fn main() { + let stdin = io::stdin(); + let mut stdin = stdin.lock(); + let mut chain = Chain::new(); + + buffered_read_all_lines(&mut stdin, |string| { + chain.feed(&string.split_whitespace() + .filter(|word| !word.is_empty()) + .map(|s| s.to_owned()).collect::>()); + + Ok(()) + }).expect("Failed to read from stdin"); + + if !chain.is_empty() { + if let Some(num) = std::env::args().skip(1).next() { + let sz: usize = num.parse().expect("Cannot parse number of tokens to generate"); + for string in chain.str_iter_for(sz) { + println!("{}", string); + } + } else { + println!("{}", chain.generate_str()); + } + } +}