From ef4bce5a1d9c63f9ae8b1eba2796fa99c2d85ab2 Mon Sep 17 00:00:00 2001 From: veradec Date: Fri, 11 Sep 2026 00:36:52 +0530 Subject: fix: restructuring for more readability and metadata to push to crates.io --- Cargo.toml | 5 ++ src/main.rs | 233 ++++++++++++++++++++++++++++++------------------------------ 2 files changed, 122 insertions(+), 116 deletions(-) diff --git a/Cargo.toml b/Cargo.toml index 0e5f267..f4c0985 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -1,5 +1,10 @@ [package] name = "okaml-rs" +description = "Rust Parser for Okaml Markup Language" +readme = "README.md" +repository = "https://github.com/lang-okaml/okaml-rs" +license = "MIT" +authors = ["Venkata Rao Dechiraju", "verade@duck.com"] version = "0.1.0" edition = "2024" diff --git a/src/main.rs b/src/main.rs index 944b405..4a0886b 100644 --- a/src/main.rs +++ b/src/main.rs @@ -19,36 +19,103 @@ struct Okml { value: OkmlType, } -fn parse_list(tokens: Vec<&str>, mut index: usize) -> (Vec, usize) { - let mut parent: Vec = Default::default(); - index = index +2; - let mut current = tokens.get(index).unwrap(); - if current == &"}" { - return (parent, index) +impl Okml { + fn read_from_file(file_path: &str) -> Vec{ + let extension = &file_path[file_path.len()-4..file_path.len()]; + + if extension != "okml" { + error!("File is not in .okml {extension}"); + std::process::exit(-1); + } + info!("Okml File Loaded: {}", file_path); + + let mut content = fs::read_to_string(file_path) + .expect("Should've read the file"); + + let mut processed_content = pre_process(content.clone()); + + let re = Regex::new(r"[ \t\n]+").unwrap(); + let tokens: Vec<&str> = re.split(&processed_content).filter(|s| !s.is_empty()).collect(); + let (parsed_ast, _) = parse(tokens, 0); + parsed_ast + } + fn read_from_string(content: &str) -> Vec { + let mut processed_content = pre_process(content.to_string()); + let re = Regex::new(r"[ \t\n]+").unwrap(); + let tokens: Vec<&str> = re.split(&processed_content).filter(|s| !s.is_empty()).collect(); + let (parsed_ast, _) = parse(tokens, 0); + parsed_ast } - let mut value = tokens.get(index+1).unwrap(); - while current != &"}" { - current = tokens.get(index).unwrap(); - value = tokens.get(index+1).unwrap(); - if current == &"}" || value == &"}" { - break; +} + +fn pre_process(mut content: String) -> String{ + let mut chars: Vec = content.chars().collect(); + let mut result = Vec::with_capacity(chars.len()); + let mut next_char: Option<&char>; + for (index, ¤t_char) in chars.iter().enumerate() { + next_char = chars.get(index+1); + if current_char == ' ' && next_char == Some(&':') { + continue; + } + + if current_char == ':' + && next_char != Some(&' ') + && chars.get(index.wrapping_sub(1)) != Some(&'\\') + { + result.push(current_char); + result.push(' '); + } else if current_char == '{' && chars.get(index-1) != Some(&' '){ + result.push(' '); + result.push(current_char); + } else if current_char == '`' && (next_char != Some(&'`')) { + result.push(current_char); + result.push('\n'); + } else if current_char == '`' && (chars.get(index-1) != Some(&'\n')) { + // result.push('\n'); + result.push(current_char); + } + else { + result.push(current_char); } + } + + chars = result; + + let mut rc: String = chars.into_iter().collect(); + return rc; +} + + +fn parse(tokens: Vec<&str>, index: usize) -> (Vec, usize) { + let token_len = tokens.len(); + let mut parent: Vec = Default::default(); + let count_braces: u64 = 0; + let mut index = 0; + while index < token_len-1 { + let current = tokens.get(index).unwrap(); + let mut value = tokens.get(index+1).unwrap(); + // parse (sub_list_key { ) if value == &"{" { - let mut new_index: usize = 0; let mut child: Vec = Default::default(); + let mut new_index = 0; (child, new_index) = parse_list(tokens.clone(), index); - parent.push(Okml { + let mut child_to_push: Okml = Okml { key: current.to_string(), value: OkmlType::SubList(child) - }); + }; + parent.push(child_to_push); index = new_index-1; - } else { - // println!("{} => {} ", current, value); + continue; + } + + + // parse (key: value) + if let Some(':') = current.chars().last() { if value == &"```" { let mut _current: &str; let mut result: String = Default::default(); - while index < tokens.len(){ + while index < token_len{ index = index+1; _current = tokens.get(index+1).unwrap(); if _current == "```" { @@ -62,8 +129,8 @@ fn parse_list(tokens: Vec<&str>, mut index: usize) -> (Vec, usize) { key: current.to_string(), value: OkmlType::String(result.clone()) }); - // info!("{} => {}", current, result); } else { + let mut return_value: OkmlType; match value { &"true" | &"yes" => return_value = OkmlType::Boolean(true), @@ -85,44 +152,45 @@ fn parse_list(tokens: Vec<&str>, mut index: usize) -> (Vec, usize) { value: (return_value) }); } - } - index = index+2; - } + } + index +=1 + } - - (parent, index) + return (parent, index) } -fn parse(tokens: Vec<&str>, index: usize) -> (Vec, usize) { - let token_len = tokens.len(); + +fn parse_list(tokens: Vec<&str>, mut index: usize) -> (Vec, usize) { let mut parent: Vec = Default::default(); - let count_braces: u64 = 0; - let mut index = 0; - while index < token_len-1 { - let current = tokens.get(index).unwrap(); - let mut value = tokens.get(index+1).unwrap(); - // parse (sub_list_key { ) + index = index +2; + let mut current = tokens.get(index).unwrap(); + if current == &"}" { + return (parent, index) + } + let mut value = tokens.get(index+1).unwrap(); + while current != &"}" { + current = tokens.get(index).unwrap(); + value = tokens.get(index+1).unwrap(); + if current == &"}" || value == &"}" { + break; + } + if value == &"{" { + let mut new_index: usize = 0; let mut child: Vec = Default::default(); - let mut new_index = 0; (child, new_index) = parse_list(tokens.clone(), index); - let mut child_to_push: Okml = Okml { + parent.push(Okml { key: current.to_string(), value: OkmlType::SubList(child) - }; - parent.push(child_to_push); + }); index = new_index-1; - continue; - } - - - // parse (key: value) - if let Some(':') = current.chars().last() { + } else { + // println!("{} => {} ", current, value); if value == &"```" { let mut _current: &str; let mut result: String = Default::default(); - while index < token_len{ + while index < tokens.len(){ index = index+1; _current = tokens.get(index+1).unwrap(); if _current == "```" { @@ -136,9 +204,7 @@ fn parse(tokens: Vec<&str>, index: usize) -> (Vec, usize) { key: current.to_string(), value: OkmlType::String(result.clone()) }); - info!("{} => {}", current, result); } else { - let mut return_value: OkmlType; match value { &"true" | &"yes" => return_value = OkmlType::Boolean(true), @@ -159,83 +225,18 @@ fn parse(tokens: Vec<&str>, index: usize) -> (Vec, usize) { key: current.to_string(), value: (return_value) }); - info!("{} => {}", current, value); } - } else { - info!("{}", current); } - index +=1 - } - - return (parent, index) -} + index = index+2; + } -fn pre_process(mut content: String) -> String{ - let mut chars: Vec = content.chars().collect(); - let mut result = Vec::with_capacity(chars.len()); - let mut next_char: Option<&char>; - for (index, ¤t_char) in chars.iter().enumerate() { - next_char = chars.get(index+1); - if current_char == ' ' && next_char == Some(&':') { - continue; - } - - if current_char == ':' - && next_char != Some(&' ') - && chars.get(index.wrapping_sub(1)) != Some(&'\\') - { - result.push(current_char); - result.push(' '); - } else if current_char == '{' && chars.get(index-1) != Some(&' '){ - result.push(' '); - result.push(current_char); - } else if current_char == '`' && (next_char != Some(&'`')) { - result.push(current_char); - result.push('\n'); - } else if current_char == '`' && (chars.get(index-1) != Some(&'\n')) { - // result.push('\n'); - result.push(current_char); - } - else { - result.push(current_char); - } - } - chars = result; - - - // for c in chars { - // print!("{c}", ); - // } - - let mut rc: String = chars.into_iter().collect(); - return rc; + (parent, index) } -fn load_from_file(file_path: &str) { - let extension = &file_path[file_path.len()-4..file_path.len()]; - - if extension != "okml" { - error!("File is not in .okml {extension}"); - std::process::exit(-1); - } - info!("File: {}", file_path); - - let mut content = fs::read_to_string(file_path) - .expect("Should've read the file"); - - let mut processed_content = pre_process(content.clone()); - - let re = Regex::new(r"[ \t\n]+").unwrap(); - let tokens: Vec<&str> = re.split(&processed_content).filter(|s| !s.is_empty()).collect(); - let (parsed_ast, _) = parse(tokens, 0); - println!("{:#?}", parsed_ast); -} fn main() { - env_logger::init(); - - let args: Vec = std::env::args().collect(); - let file_path = &args[1]; - load_from_file(file_path); + let file_path = "../example/syntax.okml"; + let parsed_ast:Vec = Okml::read_from_file(file_path); + println!("{:?}", parsed_ast); } -- cgit v1.2.3