regex_literal/

lib.rs

/*!
regex-literal - regex literal enclosed by delimiters
===============================================================================
This crate provides a quick approach of creating regular expression [`Regex`] 
and sequence [`ReSequence`] from delimited literals at runtime. Its aim is to 
formalize regex literal in Rust computing.

## Background
In Rust Reference[^1], primitive types (boolean, numeric and textual) have own 
literal expressions that are evaluated as single tokens in source code at 
compile time. But it is not the case for regular expression (abbr. regex).

In many scripting languages that implement PCRE library[^2], a regex pattern 
is enclosed by a pair of delimiters, for example,`/pattern/im` in JavaScript. 
Regex engines in [Rust crate regex-automata](https://crates.io/crates/regex-automata), 
can only receive a general literal (&str) in building a one-pattern regex. 
In the interface of [Regex::new_many](https://docs.rs/regex-automata/latest/regex_automata/meta/struct.Regex.html#method.new_many), 
an array of many pattern strings is required, as there is no syntax 
for one string literal representing a compound regex.

## Features
The crate delivers literal formats for regex and regex sets with the 
following punctuations:

* `//` (a pair of forward slashes) as the default delimiters that enclose a 
pattern. 
 
* `[]` (a pair of square brackets) that hold a union of multiple patterns 
(abbr. as 'ReU').

* `<>` (a pair of angle brackets) that hold a sequence of regex patterns and/or
 pattern unions (abbr. as 'ReS') that iterates over consecutive matchings.

* `,` (comma) serves as seperator in between regex pattern literals, while any 
whitespace unicode character[^3] is skipped in parsing.

### Samples of regex literals
1. a simple pattern : `r#"/ab+c/"#`
2. a regex union literal: `r#"[/(?i)ab+c/,/(?u)\s{2}D+/]"#`
3. a regex sequence literal:  `r#"</(?i)ab+c/,/(?u)\s{2}D+/>"#`
4. another regex sequence literal: `r#"<[/(?i)ab+c/,/(?u)\s{2}D+/],/\s*\w+/>"#`

Note that [`crate::delimited::set_delimiter()`] allows choosing a customized 
delimiter from [`crate::delimited::DELIMITER_CHARS`](static@DELIMITER_CHARS).
In addition, [`crate::util`] module provides public functions of text 
convertion between undelimited and delimited patterns.

## Building Regex structs from regex-literal
The regular expression structs can be constructed via either 
[`crate::XRegex::try_from`],[`crate::XRegex::from_str`]  or 
[`crate::XRegex::new`]. The former two use the default regex literal delimiter 
("/" transcoded in [`crate::delimited::DELIMITER`]); the latter allows a 
customised delimiter. An easy alternative is to use macro 
`xregex!` [`crate::xregex`] when constructing XRegex with literals.

### Examples

```rust
use regex_literal::{XRegex,FromStr,Regex,Match,PatternID,Input,Anchored,xregex};

//example 0: create a XRegex structs from a one-pattern literal by xregex!()
let text = "abc123";
//construct XRegex
let xre = xregex!(r"/^[a-z]+\d{3}$/"); 
// equivalent to the following variances - (1) XRegex::try_from(br"/^[a-z]+\d{3}$/").unwrap() (2) XRegex::from_str(r"/^[a-z]+\d{3}$/").unwrap() (3) XRegex::new(r"/^[a-z]+\d{3}$/",b"/").unwrap()
//get regex reference from XRegex struct
let re = xre.as_regex().unwrap();
//check if the one pattern regex matches with the target text
assert!(re.is_match(text));

//example 1: create a XRegex struct from a one-pattern literal
let text0 = "abc123";
//create one-pattern literal
let re0 = r#"/^[a-z]+\d{3}$/"#;
//construct XRegex
let x = re0.parse::<XRegex>().unwrap();//let x = XRegex::from_str(re0).unwrap();
//get Regex from XRegex struct
let x_one_pattern = x.as_regex().unwrap();
//check if the one pattern regex matches with the target text
assert!(x_one_pattern.is_match(text0));
//find the first match if it exists
let m = x_one_pattern.find(text0);
assert_eq!(m,Some(Match::must(0,0..6)));

//example 2: create a XRegex struct from a one-pattern literal
let text1 = "ABBBC abc123";
let re1 = "!!!!(?i)ab+c!!!!";
//construct XRegex
let y = XRegex::new(re1,b"!!!!").unwrap();
//get Regex from XRegex struct
let y_one_pattern = y.as_regex().unwrap();
// check if this one pattern regex matches with the input
assert!(y_one_pattern.is_match(text1));
//find all non-overlapping leftmost matches
let matches:Vec<Match> = y_one_pattern.find_iter(text1).collect();
assert_eq!(matches,vec![Match::must(0,0..5),Match::must(0,6..9),]);

//example 3: create a XRegex struct from a multiple-pattern literal
let reu = r"[/(?i)ab+c/,/\w+/]";
let mut m1 = XRegex::from_str(reu).unwrap();
//get Regex from XRegex struct
let m_patterns = m1.get_regex().unwrap();
assert!(m_patterns.is_match(text1));
let m_matches:Vec<Match> = m_patterns.find_iter(text1).collect();
assert_eq!(m_matches,vec![Match::must(0,0..5),Match::must(0,6..9),Match::must(1,9..12)]); //non-overlapping leftmost matches

let expected = Some(Match::must(1,0..7));
let input = Input::new("23ABBBC abc&").anchored(Anchored::Pattern(PatternID::must(1)));//choose the specific pattern for input
let n_patterns = XRegex::from_str(reu).unwrap().get_regex().unwrap();
let mut caps = n_patterns.create_captures();
n_patterns.search_captures(&input,&mut caps);
assert_eq!(expected, caps.get_match());

//example 4: create a XRegex struct from a regex sequence literal
let rel = br#"</(?i)ab+c/,/^\w+?\d+$/>"#;
let xre2= XRegex::try_from(&rel[..]).unwrap();
let seq_slice = xre2.as_slice().unwrap();
let child_regex = &seq_slice[1];
assert!(child_regex.is_match("abc333"));

```

## Conversion of regex literals
1. [`crate::util::delimit`] and [`crate::util::undelimit`] provide regex 
literal conversion between undelimited and delimited forms.

### Examples

``` rust
# use regex_literal::util::{delimit,undelimit};
 
let delimiter = "/";
// a regex literal that includes delimiter(forward slash `/`)
let re1 = r"\d{2}/\d{2}/\d{4}";
let delimited1 = delimit(re1,delimiter);
let string1 = r"/\d{2}\/\d{2}\/\d{4}/";
assert_eq!(&delimited1[..],string1);

let undelimited = undelimit(&delimited1[..],delimiter).unwrap();
assert_eq!(&undelimited[..], re1);

```

2. [`crate::assembly::into_reu`] and [`crate::assembly::into_res`] annotate 
patterns with default delimiters into delimited literals of regular expression 
union and sequence accordingly. Note the transformations require feature "w".

### Examples

``` rust
# use regex_literal::assembly::into_reu;
let re1 = "(?i)ab+c";
let re2 = r"\w+";
let re_set = [re1,re2];
let reu = into_reu(&re_set);
assert_eq!(reu,r"[/(?i)ab+c/,/\w+/]".to_owned());

```


## Acknowledgements
[`regex-literal`] has adopted PCRE-style delimiters on top of regex engines in Rust crate regex-automata.

[^1]: [literal expressions](https://doc.rust-lang.org/reference/expressions/literal-expr.html)

[^2]: [PCRE flavor](https://pcre.org/original/doc/html/pcretest.html)

[^3]: [Unicode characters with property White_Space=yes](https://en.wikipedia.org/wiki/Whitespace_character#Unicode)

---



*/

//includes the changlog markdown file for documenting everything into one 

#![doc = include_str!("../CHANGELOG.md")]

#![allow(unused)]
extern crate alloc;
mod error;
pub mod util;

pub mod delimited;
pub use alloc::str::FromStr;//trait implemented in XRegex 
pub use delimited::*;

/// construct XRegex with the following arguments: $l - regex string literal, $d_bytes - the byte string literal of delimiter
#[macro_export]
macro_rules! xregex {
	($l:literal) => {
		$l.parse::<$crate::XRegex>().unwrap() //XRegex::from_str(literal).unwrap()
	};
	($l:literal,$d_bytes:literal) => {
		$crate::XRegex::new($l,$d_bytes).unwrap()	
	};
}

//https://doc.rust-lang.org/cargo/reference/features.html
///feature `w` - "wiring"
#[cfg(any(test, feature = "w"))]
pub mod assembly; 
/// feature `c` - "correlation"
#[cfg(any(test,feature = "c"))]
pub mod correlation;

//the #[cfg(test)] annotation on the tests module tells Rust to compile and run the test code only when you run cargo test, not when you run cargo build
#[cfg(test)] 
mod tests {
	use super::*;
	#[test]
	fn regex_from_single_pattern_literal()  {
		 let re_str =  "/(?i)ab+c/";
		 let mut re = XRegex::from_str(re_str).unwrap();
		 //test literal field
		 assert_eq!(re.literal.0 as u8, b'/');
		 assert_eq!(re.literal.1, "/(?i)ab+c/".to_owned());
		 let my_re = re.get_regex().unwrap();
		 assert!(my_re.is_match("ABBBC"));	
	}
	#[test]
	fn regex_from_pattern_union_str()  {
		let reunion_str =  "[/(?i)ab+c/,/(?u)\\s{2}D+/]";
		let mut re = XRegex::from_str(reunion_str).unwrap();
		let my_re_set = re.get_regex().unwrap();
		assert!(my_re_set.is_match("ABBBC"));
		assert!(my_re_set.is_match("  DD"));
	}

	
	#[test]
	fn resequence_from_literal() {
		//let seq_str =  r"</(?u)[\u4e00-\u9fa5]{4}/,/\d{3}/>";
		let seq_str = r"</\s+/,/(\p{script=Han}+)(\d{3})/>";
		let mut xregex = XRegex::from_str(seq_str).unwrap();
		let input = "  天下一家1234";
		assert_eq!(xregex.data.matching_indices(input).unwrap(),vec![0,1]);
		
		let seq = xregex.as_slice().unwrap();
		assert_eq!(seq.len(),2);
		
		
		let regex_ws = &seq[0];
		let m1 = regex_ws.find(input);
		assert_eq!(m1,Some(Match::must(0,0..2)));
		let regex_words = &seq[1];
		//assert!(regex_words.is_match(input));
		let mut caps = regex_words.create_captures();
		regex_words.captures(input,&mut caps);
		let chinese_span = caps.get_group(1).unwrap();
		
		assert_eq!("天下一家",&input[chinese_span.start..chinese_span.end]);
		
		
		/*
		let mut captures = vec![];
		for (full,[chinese,digits]) in regex_words.captures_iter(&input).map(|c| c.extract()) {
			captures.push((chinese, digits.parse::<u16>()?));
		}
		//see Captures from https://docs.rs/regex-automata/latest/regex_automata/util/captures/struct.Captures.html#method.extract

		assert_eq!(captures,vec![("天下一家",1234)]);
		*/
		
	}

		#[test]	
		fn test_macro_xregex(){
			let mut x = xregex!("/(?i)ab+c/",b"/");
			let my_re = x.get_regex().unwrap();
			assert!(my_re.is_match("ABBBC"));	
		}
	
}


//this test succeed when run: cargo build --features "w" && cargo test ; https://doc.rust-lang.org/cargo/reference/features.html#command-line-feature-options
//reference: https://doc.rust-lang.org/cargo/commands/cargo-build.html
#[cfg(test)] 
mod tests_on_w_feature{
	use super::*;
	use assembly::{assemble_reu,assemble_res,into_reu,into_res};
	#[test]
	fn test_assemble_reu(){
			let reu = r"[/(?i)ab+c/,/\w+/]";
			let m1 = XRegex::from_str(reu).unwrap();
			
			let re1 = "/(?i)ab+c/";
			let re2 = r"/\w+/";
			let arr_re = [re1,re2];
			let assembled = assemble_reu(&arr_re).unwrap();
			assert_eq!(reu.to_owned(),assembled);
			let m2 = XRegex::from_str(&assembled).unwrap();
			assert_eq!(m1,m2);		
	}

	#[test]
	fn test_assemble_res(){
			let res = r"</(?i)ab+c/,/\w+/>";
			let m1 = XRegex::from_str(res).unwrap();
			
			let re1 = "/(?i)ab+c/";
			let re2 = r"/\w+/";
			let arr_re = [re1,re2];
			let assembled = assemble_res(&arr_re).unwrap();
			assert_eq!(res.to_owned(),assembled);
			let m2 = XRegex::from_str(&assembled).unwrap();
			assert_eq!(m1,m2);		
	}

	#[test]
		fn test_into_reu(){
			let re1 = "(?i)ab+c";
			let re2 = r"\w+";
			let re_set = [re1,re2];
			let reu = into_reu(&re_set);
			assert_eq!(reu,r"[/(?i)ab+c/,/\w+/]".to_owned());
			
		}
	#[test]
		fn test_into_res(){
			let re1 = "(?i)ab+c";
			let re2 = r"\w+";
			let re_set = [re1,re2];
			let res = into_res(&re_set);
			assert_eq!(res,r"</(?i)ab+c/,/\w+/>".to_owned());
			
		}

}

#[cfg(test)] 
mod tests_on_c_feature{
	use super::*;
	use correlation::par_matching_indices;

	#[test]
	fn test_parallel_matching(){
		let seq_str = r"</\s+/,/(\p{script=Han}+)(\d{3})/>";
		let mut xregex = XRegex::from_str(seq_str).unwrap();
		let input = "  天下一家1234";
		let seq = xregex.as_slice().unwrap();
		assert_eq!(par_matching_indices(seq,input).unwrap(),vec![0,1]);
	}

}