re2js 0.3.3 → 0.4.0

package/README.md

@@ -205,6 +205,7 @@ You can access the named groups in a pattern using the `namedGroups()` function
 import { RE2JS } from 're2js'
 
 RE2JS.compile('(?P<foo>\\d{2})').namedGroups() // { foo: 1 }
+RE2JS.compile('(?<bar>\\d{2})').namedGroups() // { bar: 1 }
 RE2JS.compile('\\d{2}').namedGroups() // {}
 RE2JS.compile('(?P<foo>.*)(?P<bar>.*)').namedGroups() // { foo: 1, bar: 2 }
 ```
@@ -234,6 +235,7 @@ The `group()` method retrieves the content matched by a specific name of capturi
 ```js
 import { RE2JS } from 're2js'
 
+// example with `(?P<name>expr)`
 const p = RE2JS.compile(
   '(?P<baz>f(?P<foo>b*a(?P<another>r+)){0,10})(?P<bag>bag)?(?P<nomatch>zzz)?'
 )
@@ -245,6 +247,16 @@ if (matchString.matches()) {
   matchString.group('bag') // 'bag'
   matchString.group('nomatch') // null
 }
+
+// example with `(?<name>expr)`
+const m = RE2JS.compile(
+  '(?<baz>f(?<foo>b*a))'
+)
+const mString = m.matcher('fbba')
+if (mString.matches()) {
+  mString.group('baz') // 'fbba'
+  mString.group('foo') // 'bba'
+}
 ```
 
 ### Replacing Matches

package/build/index.cjs.cjs

@@ -2,7 +2,7 @@
  * re2js
  * RE2JS is the JavaScript port of RE2, a regular expression engine that provides linear time matching
  *
- * @version v0.3.3
+ * @version v0.4.0
  * @author Alexey Vasiliev
  * @homepage https://github.com/le0pard/re2js#readme
  * @repository github:le0pard/re2js
@@ -419,6 +419,8 @@ class Unicode {
   // equalsIgnoreCase performs case-insensitive equality comparison
   // on the given runes |r1| and |r2|, with special consideration
   // for the likely scenario where both runes are ASCII characters.
+  // If non-ASCII, Unicode case folding will be performed on |r1|
+  // to compare it to |r2|.
   // -1 is interpreted as the end-of-file mark.
   static equalsIgnoreCase(r1, r2) {
     // Runes already match, or one of them is EOF
@@ -677,9 +679,7 @@ class Utils {
 // example
 // Encoding[(Encoding['UTF_16'] = 0)] = 'UTF_16'
 // Encoding[(Encoding['UTF_8'] = 1)] = 'UTF_8'
-const createEnum = function () {
-  let values = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : [];
-  let initNum = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 0;
+const createEnum = (values = [], initNum = 0) => {
   const enumObject = {};
   for (let i = 0; i < values.length; i++) {
     const val = values[i];
@@ -814,8 +814,7 @@ class RE2JSException extends Error {
  * An exception thrown by the parser if the pattern was invalid.
  */
 class RE2JSSyntaxException extends RE2JSException {
-  constructor(error) {
-    let input = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : null;
+  constructor(error, input = null) {
     let message = `error parsing regexp: ${error}`;
     if (input) {
       message += `: \`${input}\``;
@@ -988,8 +987,7 @@ class Matcher {
    * @param {string|number} [group=0]
    * @returns {string}
    */
-  start() {
-    let group = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : 0;
+  start(group = 0) {
     if (typeof group === 'string') {
       const groupInt = this.namedGroups[group];
       if (!Number.isFinite(groupInt)) {
@@ -1007,8 +1005,7 @@ class Matcher {
    * @param {string|number} [group=0]
    * @returns {string}
    */
-  end() {
-    let group = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : 0;
+  end(group = 0) {
     if (typeof group === 'string') {
       const groupInt = this.namedGroups[group];
       if (!Number.isFinite(groupInt)) {
@@ -1025,8 +1022,7 @@ class Matcher {
    * @param {string|number} [group=0]
    * @returns {string}
    */
-  group() {
-    let group = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : 0;
+  group(group = 0) {
     if (typeof group === 'string') {
       const groupInt = this.namedGroups[group];
       if (!Number.isFinite(groupInt)) {
@@ -1106,8 +1102,7 @@ class Matcher {
    * @returns {boolean} if it finds a match
    * @throws IndexOutOfBoundsException if start is not a valid input position
    */
-  find() {
-    let start = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : null;
+  find(start = null) {
     if (start !== null) {
       if (start < 0 || start > this.matcherInputLength) {
         throw new RE2JSGroupException(`start index out of bounds: ${start}`);
@@ -1190,8 +1185,7 @@ class Matcher {
    * @throws IndexOutOfBoundsException if replacement refers to an invalid group
    * @private
    */
-  appendReplacement(replacement) {
-    let perlMode = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : false;
+  appendReplacement(replacement, perlMode = false) {
     let res = '';
     const s = this.start();
     const e = this.end();
@@ -1375,8 +1369,7 @@ class Matcher {
    * @returns {string} the input string with the matches replaced
    * @throws IndexOutOfBoundsException if replacement refers to an invalid group and perlMode is false
    */
-  replaceAll(replacement) {
-    let perlMode = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : false;
+  replaceAll(replacement, perlMode = false) {
     return this.replace(replacement, true, perlMode);
   }
 
@@ -1389,8 +1382,7 @@ class Matcher {
    * @returns {string} the input string with the first match replaced
    * @throws IndexOutOfBoundsException if replacement refers to an invalid group and perlMode is false
    */
-  replaceFirst(replacement) {
-    let perlMode = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : false;
+  replaceFirst(replacement, perlMode = false) {
     return this.replace(replacement, false, perlMode);
   }
 
@@ -1402,9 +1394,7 @@ class Matcher {
    * @returns {string}
    * @private
    */
-  replace(replacement) {
-    let all = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : true;
-    let perlMode = arguments.length > 2 && arguments[2] !== undefined ? arguments[2] : false;
+  replace(replacement, all = true, perlMode = false) {
     let res = '';
     this.reset();
     while (this.find()) {
@@ -2000,6 +1990,10 @@ class Inst {
     // class.
     if (this.runes.length === 1) {
       const r0 = this.runes[0];
+      // If this pattern is case-insensitive, apply Unicode case folding to compare the two runes.
+      // Note that this may result in a case-folding loop when executed,
+      // so attempt to reduce the chance of that occurring
+      // by performing case folding on |r0| from the pattern rather than |r| from the input.
       if ((this.arg & RE2Flags.FOLD_CASE) !== 0) {
         return Unicode.equalsIgnoreCase(r0, r);
       }
@@ -2231,10 +2225,7 @@ class Prog {
  * @class
  */
 class Frag {
-  constructor() {
-    let i = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : 0;
-    let out = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 0;
-    let nullable = arguments.length > 2 && arguments[2] !== undefined ? arguments[2] : false;
+  constructor(i = 0, out = 0, nullable = false) {
     this.i = i; // an instruction address (pc).
     this.out = out; // a patch list; see explanation in Prog.js
     this.nullable = nullable; // whether the fragment can match the empty string
@@ -2727,8 +2718,7 @@ class CharClass {
       CharClass.qsortIntPair(array, i, right);
     }
   }
-  constructor() {
-    let r = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : Utils.emptyInts();
+  constructor(r = Utils.emptyInts()) {
     this.r = r; // inclusive ranges, pairs of [lo,hi].  r.length is even.
     this.len = r.length; // prefix of |r| that is defined.  Even.
   }
@@ -3402,8 +3392,7 @@ class Parser {
   static concatRunes(x, y) {
     return [...x, ...y];
   }
-  constructor(wholeRegexp) {
-    let flags = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 0;
+  constructor(wholeRegexp, flags = 0) {
     this.wholeRegexp = wholeRegexp;
     // Flags control the behavior of the parser and record information about
     // regexp context.
@@ -4145,21 +4134,22 @@ class Parser {
     // support all three as well.  EcmaScript 4 uses only the Python form.
     //
     // In both the open source world (via Code Search) and the
-    // Google source tree, (?P<expr>name) is the dominant form,
-    // so that's the one we implement.  One is enough.
+    // Google source tree, (?P<name>expr) and (?<name>expr) are the
+    // dominant forms of named captures and both are supported.
     const s = t.rest();
-    if (s.startsWith('(?P<')) {
+    if (s.startsWith('(?P<') || s.startsWith('(?<')) {
       // Pull out name.
+      const begin = s.charAt(2) === 'P' ? 4 : 3;
       const end = s.indexOf('>');
       if (end < 0) {
         throw new RE2JSSyntaxException(Parser.ERR_INVALID_NAMED_CAPTURE, s);
       }
-      const name = s.substring(4, end); // "name"
+      const name = s.substring(begin, end); // "name"
       t.skipString(name);
-      t.skip(5); // "(?P<>"
+      t.skip(begin + 1); // "(?P<>" or "(?<>"
       if (!Parser.isValidCaptureName(name)) {
         // "(?P<name>"
-        throw new RE2JSSyntaxException(Parser.ERR_INVALID_NAMED_CAPTURE, s.substring(0, end));
+        throw new RE2JSSyntaxException(Parser.ERR_INVALID_NAMED_CAPTURE, s.substring(0, end + 1)); // "(?P<name>" or "(?<name>"
       }
       // Like ordinary capture, but named.
       const re = this.op(Regexp.Op.LEFT_PAREN);
@@ -4631,8 +4621,7 @@ class Machine {
   }
 
   // Frees all threads on the thread queue, returning them to the free pool.
-  freeQueue(queue) {
-    let from = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 0;
+  freeQueue(queue, from = 0) {
     const numberOfThread = queue.size - from;
     const requiredPoolLength = this.poolSize + numberOfThread;
     if (this.pool.length < requiredPoolLength) {
@@ -4962,9 +4951,7 @@ class RE2 {
   static match(pattern, s) {
     return RE2.compile(pattern).match(s);
   }
-  constructor(expr, prog) {
-    let numSubexp = arguments.length > 2 && arguments[2] !== undefined ? arguments[2] : 0;
-    let longest = arguments.length > 3 && arguments[3] !== undefined ? arguments[3] : 0;
+  constructor(expr, prog, numSubexp = 0, longest = 0) {
     this.expr = expr; // as passed to Compile
     this.prog = prog; // compiled program
     this.numSubexp = numSubexp;
@@ -5198,8 +5185,7 @@ class RE2 {
   }
 
   // Find matches in input.
-  allMatches(input, n) {
-    let deliverFun = arguments.length > 2 && arguments[2] !== undefined ? arguments[2] : v => v;
+  allMatches(input, n, deliverFun = v => v) {
     let result = [];
     const end = input.endPos();
     if (n < 0) {