diff --git a/Cargo.lock b/Cargo.lock new file mode 100644 index 0000000..751a48f --- /dev/null +++ b/Cargo.lock @@ -0,0 +1,212 @@ +# This file is automatically @generated by Cargo. +# It is not intended for manual editing. +version = 3 + +[[package]] +name = "block-buffer" +version = "0.10.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3078c7629b62d3f0439517fa394996acacc5cbc91c5a20d8c658e77abd503a71" +dependencies = [ + "generic-array", +] + +[[package]] +name = "cfg-if" +version = "1.0.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd" + +[[package]] +name = "cpufeatures" +version = "0.2.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "53fe5e26ff1b7aef8bca9c6080520cfb8d9333c7568e1829cef191a9723e5504" +dependencies = [ + "libc", +] + +[[package]] +name = "crypto-common" +version = "0.1.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1bfb12502f3fc46cca1bb51ac28df9d618d813cdc3d2f25b9fe775a34af26bb3" +dependencies = [ + "generic-array", + "typenum", +] + +[[package]] +name = "digest" +version = "0.10.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292" +dependencies = [ + "block-buffer", + "crypto-common", +] + +[[package]] +name = "generic-array" +version = "0.14.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "85649ca51fd72272d7821adaf274ad91c288277713d9c18820d8499a7ff69e9a" +dependencies = [ + "typenum", + "version_check", +] + +[[package]] +name = "libc" +version = "0.2.152" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "13e3bf6590cbc649f4d1a3eefc9d5d6eb746f5200ffb04e5e142700b8faa56e7" + +[[package]] +name = "memchr" +version = "2.7.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "523dc4f511e55ab87b694dc30d0f820d60906ef06413f93d4d7a1385599cc149" + +[[package]] +name = "once_cell" +version = "1.19.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92" + +[[package]] +name = "pest" +version = "2.7.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1f200d8d83c44a45b21764d1916299752ca035d15ecd46faca3e9a2a2bf6ad06" +dependencies = [ + "memchr", + "thiserror", + "ucd-trie", +] + +[[package]] +name = "pest_derive" +version = "2.7.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "bcd6ab1236bbdb3a49027e920e693192ebfe8913f6d60e294de57463a493cfde" +dependencies = [ + "pest", + "pest_generator", +] + +[[package]] +name = "pest_generator" +version = "2.7.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2a31940305ffc96863a735bef7c7994a00b325a7138fdbc5bda0f1a0476d3275" +dependencies = [ + "pest", + "pest_meta", + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "pest_meta" +version = "2.7.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "a7ff62f5259e53b78d1af898941cdcdccfae7385cf7d793a6e55de5d05bb4b7d" +dependencies = [ + "once_cell", + "pest", + "sha2", +] + +[[package]] +name = "proc-macro2" +version = "1.0.76" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "95fc56cda0b5c3325f5fbbd7ff9fda9e02bb00bb3dac51252d2f1bfa1cb8cc8c" +dependencies = [ + "unicode-ident", +] + +[[package]] +name = "quote" +version = "1.0.35" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "291ec9ab5efd934aaf503a6466c5d5251535d108ee747472c3977cc5acc868ef" +dependencies = [ + "proc-macro2", +] + +[[package]] +name = "sha2" +version = "0.10.8" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "793db75ad2bcafc3ffa7c68b215fee268f537982cd901d132f89c6343f3a3dc8" +dependencies = [ + "cfg-if", + "cpufeatures", + "digest", +] + +[[package]] +name = "syn" +version = "2.0.48" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0f3531638e407dfc0814761abb7c00a5b54992b849452a0646b7f65c9f770f3f" +dependencies = [ + "proc-macro2", + "quote", + "unicode-ident", +] + +[[package]] +name = "tag" +version = "0.1.0" +dependencies = [ + "pest", + "pest_derive", +] + +[[package]] +name = "thiserror" +version = "1.0.56" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "d54378c645627613241d077a3a79db965db602882668f9136ac42af9ecb730ad" +dependencies = [ + "thiserror-impl", +] + +[[package]] +name = "thiserror-impl" +version = "1.0.56" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fa0faa943b50f3db30a20aa7e265dbc66076993efed8463e8de414e5d06d3471" +dependencies = [ + "proc-macro2", + "quote", + "syn", +] + +[[package]] +name = "typenum" +version = "1.17.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "42ff0bf0c66b8238c6f3b578df37d0b7848e55df8577b3f74f92a69acceeb825" + +[[package]] +name = "ucd-trie" +version = "0.1.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ed646292ffc8188ef8ea4d1e0e0150fb15a5c2e12ad9b8fc191ae7a8a7f3c4b9" + +[[package]] +name = "unicode-ident" +version = "1.0.12" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "3354b9ac3fae1ff6755cb6db53683adb661634f67557942dea4facebec0fee4b" + +[[package]] +name = "version_check" +version = "0.9.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "49874b5167b65d7193b8aba1567f5c7d93d001cafc34600cee003eda787e483f" diff --git a/Cargo.toml b/Cargo.toml index 3381189..71fd8d5 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -6,3 +6,5 @@ edition = "2021" # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html [dependencies] +pest = "2.7.6" +pest_derive = "2.7.6" diff --git a/src/lib.rs b/src/lib.rs new file mode 100644 index 0000000..079be18 --- /dev/null +++ b/src/lib.rs @@ -0,0 +1,2 @@ +/// parsers contains the relevant grammar parsers +pub mod parsers; diff --git a/src/parsers.rs b/src/parsers.rs new file mode 100644 index 0000000..7387d80 --- /dev/null +++ b/src/parsers.rs @@ -0,0 +1,83 @@ +use pest_derive::Parser; + +#[derive(Parser)] +#[grammar = "tagline.pest"] +/// TaglineParser is responsible for parsing the taglines at the start of each searched file. +pub struct TaglineParser; + +#[cfg(test)] +mod tests { + use pest::Parser; + + use super::*; + + #[test] + fn test_tagline_parser() { + struct TestCase<'a> { + name: &'a str, + input: &'a str, + expected_tags: Vec<&'a str>, + expected_error: bool, + } + + let test_cases = [ + TestCase { + name: "success_with_space", + input: "tags: [#1 #2 #3]", + expected_tags: vec!["#1", "#2", "#3"], + expected_error: false, + }, + TestCase { + name: "success_without_space", + input: "tags:[#1#asdf#something-idk]", + expected_tags: vec!["#1", "#asdf", "#something-idk"], + expected_error: false, + }, + TestCase { + name: "success_with_newline", + input: "tags:\n[\n\t#something_else\n]", + expected_tags: vec!["#something_else"], + expected_error: false, + }, + TestCase { + name: "fail_no_brackets", + input: "tags:#1#2#3", + expected_tags: vec![], + expected_error: true, + }, + TestCase { + name: "fail_no_tags", + input: "[#1#2#3]", + expected_tags: vec![], + expected_error: true, + }, + TestCase { + name: "fail_wrong_tag", + input: "tags:[##]", + expected_tags: vec![], + expected_error: true, + }, + ]; + + test_cases.iter().for_each(|test_case| { + println!("Testing {}", test_case.name); + + let res = TaglineParser::parse(Rule::tagline, test_case.input); + if res.is_err() { + assert!(test_case.expected_error); + return; + } + + assert!(!test_case.expected_error); + + for (i, tag) in res.unwrap().next().unwrap().into_inner().enumerate() { + match tag.as_rule() { + Rule::tag => { + assert!(tag.as_str() == test_case.expected_tags[i]) + } + _ => unreachable!(), + } + } + }) + } +} diff --git a/tagline.pest b/tagline.pest new file mode 100644 index 0000000..4448ea1 --- /dev/null +++ b/tagline.pest @@ -0,0 +1,6 @@ +tag = {"#" ~ (LETTER|NUMBER|CONNECTOR_PUNCTUATION|DASH_PUNCTUATION)+} +taglist = _{"[" ~ tag* ~ "]"} +tagline = _{"tags:" ~ taglist} + +WHITESPACE = _{" " | "\t" | NEWLINE} +