Reorganized modules, made rules a separate struct
Rules are now a separate struct, and the `rules` member of `settings::Settings` is now a `Vec<settings::rule::Rule`. Several elements were made private, now can be accessed through dedicated methods
This commit is contained in:
parent
dbbb1616dd
commit
5f30c6d636
@ -19,6 +19,7 @@ use log::{info, warn};
|
|||||||
use simplelog::*;
|
use simplelog::*;
|
||||||
|
|
||||||
pub mod settings;
|
pub mod settings;
|
||||||
|
mod utils;
|
||||||
|
|
||||||
/// Initializes the crate
|
/// Initializes the crate
|
||||||
///
|
///
|
||||||
|
@ -6,16 +6,15 @@ use serde::{Deserialize, Serialize};
|
|||||||
extern crate log;
|
extern crate log;
|
||||||
use log::{debug, error, info};
|
use log::{debug, error, info};
|
||||||
|
|
||||||
pub mod utils;
|
use crate::utils::{self, SettingsType};
|
||||||
use utils::SettingsType;
|
|
||||||
|
|
||||||
pub mod regex_wrapper;
|
mod rule;
|
||||||
use regex_wrapper::Regex;
|
use rule::Rule;
|
||||||
|
|
||||||
/// Current version of the ruleset. It will help determine if the ruleset is
|
/// Current version of the ruleset. It will help determine if the ruleset is
|
||||||
/// outdated or from a more recent version of the software than the one being in
|
/// outdated or from a more recent version of the software than the one being in
|
||||||
/// use.
|
/// use.
|
||||||
pub const RULESET_CURRENT_VERSION: i32 = 1;
|
const RULESET_CURRENT_VERSION: i32 = 1;
|
||||||
|
|
||||||
/// Encode a [`Settings`] struct to a filetype, returns a
|
/// Encode a [`Settings`] struct to a filetype, returns a
|
||||||
/// `std::result::Result<std::string::String, std::io::Error>`
|
/// `std::result::Result<std::string::String, std::io::Error>`
|
||||||
@ -42,7 +41,6 @@ pub const RULESET_CURRENT_VERSION: i32 = 1;
|
|||||||
/// ```
|
/// ```
|
||||||
///
|
///
|
||||||
/// [`Settings`]: ./settings/struct.Settings.html
|
/// [`Settings`]: ./settings/struct.Settings.html
|
||||||
#[macro_export(local_inner_macros)]
|
|
||||||
macro_rules! encode_settings {
|
macro_rules! encode_settings {
|
||||||
($funcrate:ident, $content:expr) => {
|
($funcrate:ident, $content:expr) => {
|
||||||
match $funcrate::to_string($content) {
|
match $funcrate::to_string($content) {
|
||||||
@ -75,7 +73,6 @@ macro_rules! encode_settings {
|
|||||||
/// ```
|
/// ```
|
||||||
///
|
///
|
||||||
/// [`Settings`]: ./settings/struct.Settings.html
|
/// [`Settings`]: ./settings/struct.Settings.html
|
||||||
#[macro_export(local_inner_macros)]
|
|
||||||
macro_rules! decode_settings {
|
macro_rules! decode_settings {
|
||||||
($funcrate:ident, $content:expr) => {
|
($funcrate:ident, $content:expr) => {
|
||||||
match $funcrate::from_str($content) {
|
match $funcrate::from_str($content) {
|
||||||
@ -105,7 +102,7 @@ pub struct Settings {
|
|||||||
/// loaded ruleset comes from a newer version of lang_evolve_core
|
/// loaded ruleset comes from a newer version of lang_evolve_core
|
||||||
/// than the one used by the user.
|
/// than the one used by the user.
|
||||||
#[serde(default = "Settings::get_ruleset_version")]
|
#[serde(default = "Settings::get_ruleset_version")]
|
||||||
pub version: String,
|
version: String,
|
||||||
|
|
||||||
/// Categories of phonemes
|
/// Categories of phonemes
|
||||||
///
|
///
|
||||||
@ -117,7 +114,7 @@ pub struct Settings {
|
|||||||
/// phonemes. It is currently not possible to have more than one
|
/// phonemes. It is currently not possible to have more than one
|
||||||
/// character to be considered as one sound.
|
/// character to be considered as one sound.
|
||||||
#[serde(default)]
|
#[serde(default)]
|
||||||
pub categories: HashMap<String, String>,
|
categories: HashMap<String, String>,
|
||||||
|
|
||||||
/// Soundchange rules
|
/// Soundchange rules
|
||||||
///
|
///
|
||||||
@ -125,7 +122,7 @@ pub struct Settings {
|
|||||||
/// a regex to be matched while the second represents the change
|
/// a regex to be matched while the second represents the change
|
||||||
/// to be made to the input data.
|
/// to be made to the input data.
|
||||||
#[serde(default)]
|
#[serde(default)]
|
||||||
pub rules: Vec<(Regex, String)>,
|
rules: Vec<Rule>,
|
||||||
}
|
}
|
||||||
|
|
||||||
/// Representation inside the crate of LangEvolve’s settings.
|
/// Representation inside the crate of LangEvolve’s settings.
|
||||||
@ -182,10 +179,9 @@ impl Settings {
|
|||||||
/// [`utils::SettingsTYpe`]: ./utils/enum.SettingsType.html
|
/// [`utils::SettingsTYpe`]: ./utils/enum.SettingsType.html
|
||||||
/// [`Settings.version`]: ./struct.Settings.html#structfield.version
|
/// [`Settings.version`]: ./struct.Settings.html#structfield.version
|
||||||
pub fn import(path: &std::path::Path) -> std::io::Result<Self> {
|
pub fn import(path: &std::path::Path) -> std::io::Result<Self> {
|
||||||
use utils::SettingsType::{Json, Yaml};
|
use SettingsType::{Json, Yaml};
|
||||||
let file_type = utils::get_file_type(&path);
|
let file_type = utils::get_file_type(&path);
|
||||||
let content = utils::read_file(&path)?;
|
let content = utils::read_file(&path)?;
|
||||||
|
|
||||||
let settings: Settings = match file_type {
|
let settings: Settings = match file_type {
|
||||||
Yaml => decode_settings!(serde_yaml, &content),
|
Yaml => decode_settings!(serde_yaml, &content),
|
||||||
Json => decode_settings!(serde_json, &content),
|
Json => decode_settings!(serde_json, &content),
|
||||||
@ -236,6 +232,26 @@ impl Settings {
|
|||||||
Self::import(&path).unwrap()
|
Self::import(&path).unwrap()
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/// Add a new rule to the current settings
|
||||||
|
///
|
||||||
|
/// # Arguments
|
||||||
|
///
|
||||||
|
/// * `from` - Regex that should match the text to be replaced
|
||||||
|
/// * `to` - Regex that should replace some text
|
||||||
|
pub fn add_rule(&mut self, from: &str, to: &str) {
|
||||||
|
self.rules.push(Rule::new(from, to))
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Add a new category of phonemes to the current settings
|
||||||
|
///
|
||||||
|
/// # Arguments
|
||||||
|
///
|
||||||
|
/// * `name` - Name of the category
|
||||||
|
/// * `content` - Content of the category, phonemes
|
||||||
|
pub fn add_category(&mut self, name: &str, content: &str) {
|
||||||
|
self.categories.insert(String::from(name), String::from(content));
|
||||||
|
}
|
||||||
|
|
||||||
/// Export current settings to a file.
|
/// Export current settings to a file.
|
||||||
///
|
///
|
||||||
/// The allowed file formats are described in the [`SettingsType`] enum.
|
/// The allowed file formats are described in the [`SettingsType`] enum.
|
||||||
@ -284,35 +300,12 @@ impl Settings {
|
|||||||
RULESET_CURRENT_VERSION.to_string()
|
RULESET_CURRENT_VERSION.to_string()
|
||||||
}
|
}
|
||||||
|
|
||||||
fn update_rules(&self) -> std::result::Result<Vec<(Regex, String)>, String> {
|
fn update_rules(&self) -> std::result::Result<Vec<Rule>, String> {
|
||||||
let mut rules = self.rules.clone();
|
let rules = self.rules.clone();
|
||||||
|
let rules: Vec<Rule> = rules
|
||||||
// TODO break categories in different rules
|
.iter()
|
||||||
for (from, to) in rules.iter_mut() {
|
.map(|x| x.update(&self.categories).unwrap())
|
||||||
let re = Regex::new("%\\D");
|
.collect();
|
||||||
let from_match = re.is_match(from.as_str());
|
|
||||||
let to_match = re.is_match(to);
|
|
||||||
if from_match || to_match {
|
|
||||||
for (category, content) in &self.categories {
|
|
||||||
if from_match {
|
|
||||||
*from = Regex::new(
|
|
||||||
from.to_string()
|
|
||||||
.replace(
|
|
||||||
format!("%{}", category).as_str(),
|
|
||||||
format!("[{}]", content).as_str(),
|
|
||||||
)
|
|
||||||
.as_str()
|
|
||||||
);
|
|
||||||
}
|
|
||||||
if to_match {
|
|
||||||
*to = to.to_string().replace(
|
|
||||||
format!("%{}", category).as_str(),
|
|
||||||
format!("[{}]", content).as_str()
|
|
||||||
);
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
}
|
|
||||||
Ok(rules)
|
Ok(rules)
|
||||||
}
|
}
|
||||||
|
|
||||||
@ -345,10 +338,17 @@ impl Settings {
|
|||||||
let rules = self.update_rules().unwrap();
|
let rules = self.update_rules().unwrap();
|
||||||
let mut s = s.clone();
|
let mut s = s.clone();
|
||||||
debug!("===============================================");
|
debug!("===============================================");
|
||||||
for (from, to) in rules {
|
for rule in rules {
|
||||||
debug!("from: {}\tto: {}", from.to_string(), to);
|
debug!(
|
||||||
|
"from: {}\tto: {}",
|
||||||
|
rule.get_from().to_string(),
|
||||||
|
rule.get_to()
|
||||||
|
);
|
||||||
debug!("old: {}", s);
|
debug!("old: {}", s);
|
||||||
s = from.replace_all(&s, to.as_str()).to_string();
|
s = rule
|
||||||
|
.get_from()
|
||||||
|
.replace_all(&s, rule.get_to().as_str())
|
||||||
|
.to_string();
|
||||||
debug!("new: {}", s);
|
debug!("new: {}", s);
|
||||||
}
|
}
|
||||||
Ok(s)
|
Ok(s)
|
||||||
|
94
src/settings/rule/mod.rs
Normal file
94
src/settings/rule/mod.rs
Normal file
@ -0,0 +1,94 @@
|
|||||||
|
extern crate serde;
|
||||||
|
extern crate serde_json;
|
||||||
|
extern crate serde_yaml;
|
||||||
|
use serde::{Deserialize, Serialize};
|
||||||
|
|
||||||
|
mod regex_wrapper;
|
||||||
|
use regex_wrapper::Regex;
|
||||||
|
|
||||||
|
/// Representation of a rule in LangEvolveRs
|
||||||
|
#[derive(Debug, Serialize, Deserialize, Clone)]
|
||||||
|
pub struct Rule {
|
||||||
|
/// Regex that should match the input text
|
||||||
|
from: Regex,
|
||||||
|
/// Text to replace matched text
|
||||||
|
to: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
impl Rule {
|
||||||
|
/// Create new rule
|
||||||
|
///
|
||||||
|
/// # Arguments
|
||||||
|
///
|
||||||
|
/// * `from` - literal string that represents the regex that should match
|
||||||
|
/// the input text
|
||||||
|
/// * `to` - literal string that represents the regex text that should
|
||||||
|
/// replaced the text matched by `from`
|
||||||
|
pub fn new(from: &str, to: &str) -> Self {
|
||||||
|
Rule {
|
||||||
|
from: Regex::new(from),
|
||||||
|
to: String::from(to),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// TODO break categories in different rules
|
||||||
|
pub fn update(
|
||||||
|
&self,
|
||||||
|
categories: &std::collections::HashMap<String, String>,
|
||||||
|
) -> std::result::Result<Rule, String> {
|
||||||
|
let mut rule = self.clone();
|
||||||
|
let re = Regex::new("%\\D");
|
||||||
|
let from_match = re.is_match(&self.from.as_str());
|
||||||
|
let to_match = re.is_match(&self.to.as_str());
|
||||||
|
if from_match && !to_match {
|
||||||
|
for (category, content) in categories {
|
||||||
|
rule.from = Regex::new(
|
||||||
|
rule.from
|
||||||
|
.to_string()
|
||||||
|
.replace(
|
||||||
|
format!("%{}", category).as_str(),
|
||||||
|
format!("[{}]", content).as_str(),
|
||||||
|
)
|
||||||
|
.as_str(),
|
||||||
|
);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
Ok(rule)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn get_from(&self) -> &Regex {
|
||||||
|
&self.from
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn get_to(&self) -> String {
|
||||||
|
self.to.clone()
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
impl From<String> for Rule {
|
||||||
|
fn from(source: String) -> Self {
|
||||||
|
let components: Vec<&str> = source.split_terminator(">").collect();
|
||||||
|
Self {
|
||||||
|
from: Regex::new(components[0]),
|
||||||
|
to: String::from(components[1]),
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
impl PartialEq for Rule {
|
||||||
|
fn eq(&self, other: &Self) -> bool {
|
||||||
|
self.from == other.from && self.to == other.to
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
impl Eq for Rule {}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn rule_new() {
|
||||||
|
let rule1 = Rule::new("([ae]+)i", "${1}i");
|
||||||
|
let rule2 = Rule {
|
||||||
|
from: Regex::new("([ae]+)i"),
|
||||||
|
to: String::from("${1}i"),
|
||||||
|
};
|
||||||
|
assert_eq!(rule1, rule2);
|
||||||
|
}
|
@ -1,17 +1,3 @@
|
|||||||
// extern crate serde;
|
|
||||||
// extern crate regex;
|
|
||||||
// use serde::{Deserialize, Serialize};
|
|
||||||
|
|
||||||
// #[derive(Clone, Debug, Deserialize, Serialize)]
|
|
||||||
// #[serde(transparent)]
|
|
||||||
// pub struct Regex(regex::Regex);
|
|
||||||
|
|
||||||
// #[derive(Clone, Debug, Deserialize, Serialize)]
|
|
||||||
// #[serde(remote = "regex::Regex")]
|
|
||||||
// pub struct RegexDef{
|
|
||||||
// #[serde(getter = "regex::Regex::to_string")]
|
|
||||||
// r: String
|
|
||||||
// }
|
|
||||||
use std::{fmt, ops};
|
use std::{fmt, ops};
|
||||||
|
|
||||||
#[derive(Clone, Debug)]
|
#[derive(Clone, Debug)]
|
Loading…
Reference in New Issue
Block a user