feat: add unicode property class support

CHANGELOG.md

@@ -2,6 +2,12 @@
 
 The changelog of the reregexp library.
 
+## [1.5.0] - 2021-05-19
+
+### Added
+
+- Support unicode property class syntax, e.g. `\p{Letter}`, more details have shown in README.
+
 ## [1.4.0] - 2021-05-16
 
 ### Added
@@ -13,4 +19,4 @@ The changelog of the reregexp library.
 - Optimize some regexp rules of the parser.
 - Change the default export library name from 'RegexpParser' to `ReRegExp` in browser.
 - Make the readme more clearly.
-- Upgrade the typescript and other tools dependencies versions.
+- Upgrade the typescript and other tools dependencies versions.

README.md

@@ -7,11 +7,14 @@ Generate a matched string with a given regular expression, it's useful if you wa
 
 ## Goals
 
-- Support named capture group, and set a configed string to override which will generated by the group.
+- Support named capture group, e.g. `(?<named>\w)\k<named>`, and also allowing to override it by expose a config field `namedGroupConf`.
+
+- Support unicode property class `\p{Lu}` by setting the static `UPCFactory` handle, see the example for more details.
 
 - Support `u` flag, so you can use unicode ranges.
 
 - Allow you get the capture group values.
+
 ## Installation
 
 ```bash
@@ -26,11 +29,11 @@ yarn add reregexp
 ```javascript
 const ReRegExp = require('reregexp').default;
 
-// You can use either a regex literal 
+// You can use either a regex literal
 // or a RegExp string
 // if you need use regex rules the browser not supported yet
-// such as named group, you need choose a RegExp string 
-// for the first constructor parameter.   
+// such as named group, you need choose a RegExp string
+// for the first constructor parameter.
 
 // Example 1:  use group reference
 const r1 = new ReRegExp(/([a-z0-9]{3})_\1/);
@@ -40,9 +43,9 @@ r1.build(); // => 'a2z_a2z' '13d_13d'
 const r2 = new ReRegExp(/(?<named>\w{1,2})_\1_\k<named>/);
 r2.build(); // => 'b5_b5_b5' '9_9_9'
 
-// Example 3: use named group and with `namedGroupConf` config 
+// Example 3: use named group and with `namedGroupConf` config
 // it will use the string in the config insteadof the string that will generated by the named group
-// of course, it will trigger an error if the string in config not match the rule of named group. 
+// of course, it will trigger an error if the string in config not match the rule of named group.
 const r3 = new ReRegExp('/(a)\\1(?<named>b)\\k<named>(?<override>\\w+)/', {
   namedGroupConf: {
     override: ['cc', 'dd'],
@@ -64,7 +67,7 @@ r6.build(); // => 'bZD' 'Poe'
 
 // Example 7: with the `u` flag, e.g. make some chinese characters.
 const r7 = new ReRegExp('/[\\u{4e00}-\\u{9fcc}]{5,10}/u');
-r7.build(); // => '偤豄酌菵呑', '孜垟与醽奚衜踆猠' 
+r7.build(); // => '偤豄酌菵呑', '孜垟与醽奚衜踆猠'
 
 // Example 8: set a global `maxRepeat` when use quantifier such as '*' and '+'.
 ReRegExp.maxRepeat = 10;
@@ -74,23 +77,42 @@ r8.build(); // => 'aaaaaaa', 'a' will repeated at most 10 times.
 // Example 9: use a `maxRepeat` in constructor config, it will override `maxRepeat` of the global.
 const r9 = new ReRegExp(/a*/, {
   maxRepeat: 20,
-}); 
+});
 r9.build(); // => 'aaaaaaaaaaaaaa', 'a' will repeated at most 20 times
 
-// Examples 10: use a `extractSetAverage` config for character sets.
+// Example 10: use a `extractSetAverage` config for character sets.
 const r10 = new ReRegExp(/[\Wa-z]/, {
-  // \W will extract as all the characters match \W, a-z now doesn't have the same chance as \W 
-  extractSetAverage: true, 
+  // \W will extract as all the characters match \W, a-z now doesn't have the same chance as \W
+  extractSetAverage: true,
 });
 
-// Examples 11: use a `capture` config if cared about the capture data
+// Example 11: use a `capture` config if cared about the capture data
 const r11 = new ReRegExp(/(aa?)b(?<named>\w)/), {
   capture: true, // if you cared about the group capture data, set the `capture` config true
 });
 r11.build(); // => 'abc'
 console.log(r11.$1); // => 'a'
 console.log(r11.$2); // => 'c'
 console.log(r11.groups); // => {named: 'c'}
+
+// Example 12: use the unicode property class by setting the `UPCFactory`
+ReRegExp.UPCFactory = (data: UPCData) => {
+  /*
+  UPCData: {
+    negate: boolean; // if the symbol is 'P'
+    short: boolean; // take '\pL' as a short for '\p{Letter}'
+    key?: string; // if has a unicode property name, such as `Script`
+    value: string; // unicode property value, binary or non-binary
+  }
+  */
+  return {
+    generate(){
+      return 'x'; // return an object that has a `generate` method.
+    }
+  }
+};
+const r12 = new ReRegExp('/\\p{Lu}/u');
+console.log(r12.build()); // => 'x', should handle in the `UPCFactory` method.
 ```
 
 ## Config
@@ -140,7 +162,6 @@ get a regexp parsed queues, flags, lastRule after remove named captures.
 ## Build precautions,do not use any regexp anchors.
 
 1. `^` `$` the start,end anchors will be ignored.
-
 2. `(?=)` `(?!)` `(?<=)` `(?<!)` the regexp lookhead,lookbehind will throw an error when run `build()`.
 
 3. `\b` `\B` will be ignored.
@@ -159,10 +180,9 @@ get a regexp parsed queues, flags, lastRule after remove named captures.
 
 6. `/[^\w\W]/` for the negative charsets, if all the characters are eliminated, the `build()` will throw an error. the same such as `/[^a-zA-Z0-9_\W]/`、`/[^\s\S]/`...
 
-
 ## Questions & Bugs?
 
-Welcome to report to us with [issue](https://github.com/suchjs/reregexp/issues) if you meet any question or bug. 
+Welcome to report to us with [issue](https://github.com/suchjs/reregexp/issues) if you meet any question or bug.
 
 ## License
 

__tests__/index.test.ts

@@ -1,8 +1,4 @@
-import ReRegExp, {
-  ParserConf,
-  CharsetHelper,
-  UnicodeCategoryData,
-} from '../src/index';
+import ReRegExp, { ParserConf, CharsetHelper, UPCData } from '../src/index';
 type Rule = RegExp | string;
 const validParser = (rule: Rule) => {
   return () => {
@@ -477,8 +473,8 @@ describe('Test regexp parser', () => {
     }).toThrowError();
     // set the factory
     expect(() => {
-      ReRegExp.unicodeCategoryFactory = function (data: UnicodeCategoryData) {
-        if (data.reverse) {
+      ReRegExp.UPCFactory = function (data: UPCData) {
+        if (data.negate) {
           return {
             generate() {
               return '_';
@@ -511,7 +507,7 @@ describe('Test regexp parser', () => {
       const r5 = new ReRegExp('/\\P{Letter}{2}/u');
       expect(r5.build()).toEqual('__');
       // delete the factory
-      delete ReRegExp.unicodeCategoryFactory;
+      delete ReRegExp.UPCFactory;
     }).not.toThrowError();
   });
   // test last info

package.json

@@ -1,7 +1,7 @@
 {
   "name": "reregexp",
-  "version": "1.4.0",
-  "description": "Generate a random string match a given regular expression, useful for mocking strings.",
+  "version": "1.5.0",
+  "description": "Generate a random string match a given regular expression, suitable for mocking strings.",
   "main": "./lib/index.js",
   "typings": "./lib/index.d.ts",
   "author": "[email protected]",

src/index.ts

@@ -83,18 +83,16 @@ export type Result = Pick<
   queues: RegexpPart[];
 };
 
-export type UnicodeCategoryData = {
-  reverse: boolean;
+export type UPCData = {
+  negate: boolean;
   short: boolean;
   key?: string;
-  value?: string;
+  value: string;
 };
 
-export type UnicodeCategoryFactory = (
-  data: UnicodeCategoryData,
-) => UnicodeCategoryInstance | never;
+export type UPCFactory = (data: UPCData) => UPCInstance | never;
 
-export interface UnicodeCategoryInstance {
+export interface UPCInstance {
   generate(): string;
 }
 
@@ -306,7 +304,7 @@ export default class ReRegExp {
   // static maxRepeat config
   public static maxRepeat = 5;
   // static handle for unicode categories
-  public static unicodeCategoryFactory?: UnicodeCategoryFactory;
+  public static UPCFactory?: UPCFactory;
   // regexp input, without flags
   public readonly context: string = '';
   // flags
@@ -553,9 +551,9 @@ export default class ReRegExp {
             // unicode categories/script/block
             if (hasFlagU) {
               // must have `u` flag
-              if (typeof ReRegExp.unicodeCategoryFactory !== 'function') {
+              if (typeof ReRegExp.UPCFactory !== 'function') {
                 throw new Error(
-                  `You must set the ReRegExp.unicodeCategoryFactory before you use the unicode category.`,
+                  `You must set the ReRegExp.UPCFactory before you use the unicode category.`,
                 );
               }
               target = new RegexpUnicodeCategory(next);
@@ -1637,9 +1635,9 @@ export class RegexpASCII extends RegexpHexCode {
 
 export class RegexpUnicodeCategory extends RegexpPart {
   public type = 'unicode-category';
-  protected data: UnicodeCategoryData;
+  protected data: UPCData;
   protected rule = /^([A-Z]|\{(?:(?:([a-zA-Z_]+)=)?([A-Za-z_]+))})/;
-  protected generator: UnicodeCategoryInstance;
+  protected generator: UPCInstance;
   // constructor
   public constructor(private readonly symbol: string) {
     super();
@@ -1649,12 +1647,12 @@ export class RegexpUnicodeCategory extends RegexpPart {
     if (this.rule.test(context)) {
       const { $1: all, $2: key, $3: value } = RegExp;
       const { symbol } = this;
-      const reverse = symbol === 'P';
-      let data: UnicodeCategoryData;
+      const negate = symbol === 'P';
+      let data: UPCData;
       if (value) {
         data = {
           short: false,
-          reverse,
+          negate,
           value,
         };
         if (key) {
@@ -1663,12 +1661,12 @@ export class RegexpUnicodeCategory extends RegexpPart {
       } else {
         data = {
           short: true,
-          reverse,
+          negate,
           value: all,
         };
       }
       this.data = data;
-      const factory = ReRegExp.unicodeCategoryFactory;
+      const factory = ReRegExp.UPCFactory;
       this.generator = factory(data);
       this.input = `\\${symbol}${all}`;
       return all.length;