1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196
//!
//! This crate provides a demo of using [fi_night] crate for implementation
//! of a simple parser capable of indexing nested bracketed segments of text.
//! The parser distinguishes sentences separated by '.' and ```[bracketed]``` text
//! segments.
//! The automaton implementation can be seen in modules
//! parser_pda.rs and parser_nondet_pda.rs which implement two
//! versions providing the same functionality.
//!
//! Here is an example:
//!```rust
//! use parser_pda::{create_parser_pda_instance} ;
//! use parser_pda::parser_pda::{LittleParser, LittleParserTrait, LittleParserStates::*, LittleParserSignals::*,
//! LITTLE_PARSER_GEN_CODE};
//!
//! fn main() {
//! let mut parser = create_parser_pda_instance();
//!
//! fsm_code_to_file("parser_automaton", "target/fsm", LITTLE_PARSER_GEN_CODE);
//!
//! let text = "Fif[teen] men on a dead man's [[chest]]. []]Yo [[ho [[ho. And [the [bottle] ]of [[[RUM]]] ";
//!
//! parser.start();
//!
//! for ch in text.chars() {
//! match ch {
//! '[' => parser.next(&LeftBracket),
//! ']' => parser.next(&RightBracket),
//! '.' => parser.next(&EndOfSentence),
//! ch @ _ => parser.next(&Letter(ch)),
//! }
//! }
//! parser.stop();
//!
//! display_output(&text, &mut parser);
//!
//! fn display_output(text: &str, parser: &mut LittleParser) {
//! use substring::Substring;
//! println!("input: {}\n", text);
//! while let Some(seg) = parser.data_mut().segments.pop() {
//! let tabbed = "\t".repeat(seg.rank);
//!
//! println!("{} {}[{} {}) -> {}", tabbed, seg.tp, seg.seg.0, seg.seg.1,
//! text.substring(seg.seg.0, seg.seg.1));
//! }
//! }
//! }
//!
//! use std::fs::{File, create_dir};
//! use std::io::{Seek, Write};
//!
//! fn fsm_code_to_file(fname: &str, path: &str, gen_code: &str) {
//!
//! let _ = create_dir(path);
//!
//! File::create(&format!("{}/{}.rs", path, fname))
//! .and_then(|mut file| {
//! file.seek(std::io::SeekFrom::End(0))?;
//! file.write_all(gen_code.to_string().as_bytes())?;
//! file.flush()
//! });
//! }
//! ```
//!
//! The code running stores the rust code of the automaton under
//! /target/fsm/parser_automaton.rs
//! and emits the following output:
//! ```text
//! input: Fif[teen] men on a dead man's [[chest]]. []]Yo [[ho [[ho. And [the [bottle] ]of [[[RUM]]]
//!
//! Sentence[0 39) -> Fif[teen] men on a dead man's [[chest]]
//! Plain[0 30) -> Fif[teen] men on a dead man's
//! Plain[0 3) -> Fif
//! Bracketed[4 8) -> teen
//! Bracketed[31 38) -> [chest]
//! Bracketed[32 37) -> chest
//! InvalidSentence[40 56) -> []]Yo [[ho [[ho
//! Plain[40 43) -> []
//! Plain[40 41) ->
//! Bracketed[42 42) ->
//! UnbalancedRightSth[43 56) -> ]Yo [[ho [[ho
//! Tail[57 90) -> And [the [bottle] ]of [[[RUM]]]
//! Plain[57 80) -> And [the [bottle] ]of
//! Plain[57 62) -> And
//! Bracketed[63 76) -> the [bottle]
//! Bracketed[68 74) -> bottle
//! Bracketed[81 88) -> [[RUM]]
//! Bracketed[82 87) -> [RUM]
//! Bracketed[83 86) -> RUM
//!```
#[macro_use]
extern crate fi_night;
pub mod defs;
pub mod parser_pda;
pub mod parser_nondet_pda;
use crate::defs::{ ParserCtx, fsm_code_to_file };
pub fn create_parser_pda_instance() -> crate::parser_pda::LittleParser {
crate::parser_pda::LittleParser::new(
crate::parser_pda::LittleParserStates::Idle,
ParserCtx {
segments: std::collections::BinaryHeap::new(),
index: 0,
})
}
pub fn create_parser_nondet_pda_instance() -> crate::parser_nondet_pda::ParserNonDetPDA {
crate::parser_nondet_pda::ParserNonDetPDA::new(
crate::parser_nondet_pda::ParserNonDetPDAStates::Idle,
ParserCtx {
segments: std::collections::BinaryHeap::new(),
index: 0,
})
}
pub fn parser_pda_test() {
use crate::parser_pda::{LittleParser, LittleParserTrait, LittleParserStates::*, LittleParserSignals::*,
LITTLE_PARSER_GEN_CODE};
crate::fsm_code_to_file("parser_pda", "target/fsm", LITTLE_PARSER_GEN_CODE);
let mut parser = crate::parser_pda::LittleParser::new(
Idle,
ParserCtx {
segments: std::collections::BinaryHeap::new(),
index: 0,
});
let text = "Fif[teen] men on a dead man's [[chest]]. []]Yo [[ho [[ho. And [the [bottle] ]of [[[RUM]]] ";
parser.start();
for ch in text.chars() {
match ch {
'[' => parser.next(&LeftBracket),
']' => parser.next(&RightBracket),
'.' => parser.next(&EndOfSentence),
ch @ _ => parser.next(&Letter(ch)),
}
}
parser.stop();
display_output(&text, &mut parser);
fn display_output(text: &str, parser: &mut LittleParser) {
use substring::Substring;
println!("input: {}\n", text);
while let Some(seg) = parser.data_mut().segments.pop() {
let tabbed = "\t".repeat(seg.rank);
println!("{} {}[{} {}) -> {}", tabbed, seg.tp, seg.seg.0, seg.seg.1,
text.substring(seg.seg.0, seg.seg.1));
}
}
}
pub fn parser_nondet_pda_test() {
use crate::parser_nondet_pda::{ParserNonDetPDA, ParserNonDetPDATrait, ParserNonDetPDAStates::*, ParserNonDetPDASignals::*,
PARSER_NON_DET_PDA_GEN_CODE};
crate::fsm_code_to_file("parser_nondet_pda", "target/fsm", PARSER_NON_DET_PDA_GEN_CODE);
let mut parser = crate::parser_nondet_pda::ParserNonDetPDA::new(
Idle,
ParserCtx {
segments: std::collections::BinaryHeap::new(),
index: 0,
});
let text = "Fif[teen] men on a dead man's [[chest]]. []]Yo [[ho [[ho. And [the [bottle] ]of [[[RUM]]] ";
parser.start();
for ch in text.chars() {
match ch {
'[' => parser.next(&LeftBracket),
']' => parser.next(&RightBracket),
'.' => parser.next(&EndOfSentence),
ch @ _ => parser.next(&Letter(ch)),
}
}
parser.stop();
display_output(&text, &mut parser);
fn display_output(text: &str, parser: &mut ParserNonDetPDA) {
use substring::Substring;
println!("input: {}\n", text);
while let Some(seg) = parser.data_mut().segments.pop() {
let tabbed = "\t".repeat(seg.rank);
println!("{} {}[{} {}) -> {}", tabbed, seg.tp, seg.seg.0, seg.seg.1,
text.substring(seg.seg.0, seg.seg.1));
}
}
}