re2js 0.4.0 → 0.4.1

package/README.md

@@ -24,11 +24,14 @@ There are certain features of PCRE or Perl regular expressions that cannot be im
 To install RE2JS:
 
 ```bash
+# npm
 npm install re2js
-# or
+# yarn
 yarn add re2js
-# or
+# pnpm
 pnpm add re2js
+# bun
+bun add re2js
 ```
 
 ## Usage

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 v0.4.0
+ * @version v0.4.1
  * @author Alexey Vasiliev
  * @homepage https://github.com/le0pard/re2js#readme
  * @repository github:le0pard/re2js
@@ -716,8 +716,7 @@ class MatcherInputBase {
   }
 }
 class Utf8MatcherInput extends MatcherInputBase {
-  constructor() {
-    let bytes = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : null;
+  constructor(bytes = null) {
     super();
     this.bytes = bytes;
   }
@@ -749,8 +748,7 @@ class Utf8MatcherInput extends MatcherInputBase {
   }
 }
 class Utf16MatcherInput extends MatcherInputBase {
-  constructor() {
-    let charSequence = arguments.length > 0 && arguments[0] !== undefined ? arguments[0] : null;
+  constructor(charSequence = null) {
     super();
     this.charSequence = charSequence;
   }
@@ -874,7 +872,6 @@ class RE2JSFlagsException extends RE2JSException {
 /**
  * A stateful iterator that interprets a regex {@code RE2JS} on a specific input.
  *
- * <p>
  * Conceptually, a Matcher consists of four parts:
  * <ol>
  * <li>A compiled regular expression {@code RE2JS}, set at construction and fixed for the lifetime
@@ -1168,12 +1165,10 @@ class Matcher {
    * the form {@code $n}, where {@code n} is the group number in decimal. It advances the append
    * position to where the most recent match ended.
    *
-   * <p>
    * To embed a literal {@code $}, use \$ (actually {@code "\\$"} with string escapes). The escape
    * is only necessary when {@code $} is followed by a digit, but it is always allowed. Only
    * {@code $} and {@code \} need escaping, but any character can be escaped.
    *
-   * <p>
    * The group number {@code n} in {@code $n} is always at least one digit and expands to use more
    * digits as long as the resulting number is a valid group number for this pattern. To cut it off
    * earlier, escape the first digit that should not be used.
@@ -1431,9 +1426,7 @@ class MachineInputBase {
 // An implementation of MachineInput for UTF-8 byte arrays.
 // |pos| and |width| are byte indices.
 class MachineUTF8Input extends MachineInputBase {
-  constructor(bytes) {
-    let start = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 0;
-    let end = arguments.length > 2 && arguments[2] !== undefined ? arguments[2] : bytes.length;
+  constructor(bytes, start = 0, end = bytes.length) {
     super();
     this.bytes = bytes;
     this.start = start;
@@ -1516,8 +1509,7 @@ class MachineUTF8Input extends MachineInputBase {
 
   // Returns the index of the first occurrence of array |target| within
   // array |source| after |fromIndex|, or -1 if not found.
-  indexOf(source, target) {
-    let fromIndex = arguments.length > 2 && arguments[2] !== undefined ? arguments[2] : 0;
+  indexOf(source, target, fromIndex = 0) {
     let targetLength = target.length;
     if (targetLength === 0) {
       return -1;
@@ -1538,9 +1530,7 @@ class MachineUTF8Input extends MachineInputBase {
 
 // |pos| and |width| are in JS "char" units.
 class MachineUTF16Input extends MachineInputBase {
-  constructor(charSequence) {
-    let start = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 0;
-    let end = arguments.length > 2 && arguments[2] !== undefined ? arguments[2] : charSequence.length;
+  constructor(charSequence, start = 0, end = charSequence.length) {
     super();
     this.charSequence = charSequence;
     this.start = start;
@@ -1580,14 +1570,10 @@ class MachineUTF16Input extends MachineInputBase {
   }
 }
 class MachineInput {
-  static fromUTF8(bytes) {
-    let start = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 0;
-    let end = arguments.length > 2 && arguments[2] !== undefined ? arguments[2] : bytes.length;
+  static fromUTF8(bytes, start = 0, end = bytes.length) {
     return new MachineUTF8Input(bytes, start, end);
   }
-  static fromUTF16(charSequence) {
-    let start = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 0;
-    let end = arguments.length > 2 && arguments[2] !== undefined ? arguments[2] : charSequence.length;
+  static fromUTF16(charSequence, start = 0, end = charSequence.length) {
     return new MachineUTF16Input(charSequence, start, end);
   }
 }
@@ -1675,7 +1661,6 @@ class Regexp {
     this.name = null; // capturing name, for CAPTURE
     this.namedGroups = {}; // map of group name -> capturing index
   }
-
   reinit() {
     this.flags = 0;
     this.subs = Regexp.emptySubs();
@@ -4105,7 +4090,6 @@ class Parser {
     if (this.swapVerticalBar()) {
       this.pop(); // pop vertical bar
     }
-
     this.alternate();
     const n = this.stack.length;
     if (n !== 1) {
@@ -4279,7 +4263,6 @@ class Parser {
     if (this.swapVerticalBar()) {
       this.pop(); // pop vertical bar
     }
-
     this.alternate();
     const n = this.stack.length;
     if (n < 2) {
@@ -4865,10 +4848,8 @@ class AtomicReference {
  * An RE2 class instance is a compiled representation of an RE2 regular expression, independent of
  * the public Java-like Pattern/Matcher API.
  *
- * <p>
  * This class also contains various implementation helpers for RE2 regular expressions.
  *
- * <p>
  * Use the {@link #quoteMeta(String)} utility function to quote all regular expression
  * metacharacters in an arbitrary string.
  *
@@ -4890,7 +4871,6 @@ class RE2 {
    * Parses a regular expression and returns, if successful, an {@code RE2} instance that can be
    * used to match against text.
    *
-   * <p>
    * When matching against text, the regexp returns a match that begins as early as possible in the
    * input (leftmost), and among those it chooses the one that a backtracking search would have
    * found first. This so-called leftmost-first matching is the same semantics that Perl, Python,
@@ -4905,13 +4885,11 @@ class RE2 {
    * {@code compilePOSIX} is like {@link #compile} but restricts the regular expression to POSIX ERE
    * (egrep) syntax and changes the match semantics to leftmost-longest.
    *
-   * <p>
    * That is, when matching against text, the regexp returns a match that begins as early as
    * possible in the input (leftmost), and among those it chooses a match that is as long as
    * possible. This so-called leftmost-longest matching is the same semantics that early regular
    * expression implementations used and that POSIX specifies.
    *
-   * <p>
    * However, there can be multiple leftmost-longest matches, with different submatch choices, and
    * here this package diverges from POSIX. Among the possible leftmost-longest matches, this
    * package chooses the one that a backtracking search would have found first, while POSIX
@@ -4944,7 +4922,6 @@ class RE2 {
   /**
    * Returns true iff textual regular expression {@code pattern} matches string {@code s}.
    *
-   * <p>
    * More complicated queries need to use {@link #compile} and the full {@code RE2} interface.
    */
   // This is visible for testing.
@@ -5262,7 +5239,6 @@ class RE2 {
    * Returns an array holding the text of the leftmost match in {@code b} of this regular
    * expression.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5278,7 +5254,6 @@ class RE2 {
    * Returns a two-element array of integers defining the location of the leftmost match in
    * {@code b} of this regular expression. The match itself is at {@code b[loc[0]...loc[1]]}.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5294,7 +5269,6 @@ class RE2 {
    * Returns a string holding the text of the leftmost match in {@code s} of this regular
    * expression.
    *
-   * <p>
    * If there is no match, the return value is an empty string, but it will also be empty if the
    * regular expression successfully matches an empty string. Use {@link #findIndex} or
    * {@link #findSubmatch} if it is necessary to distinguish these cases.
@@ -5313,7 +5287,6 @@ class RE2 {
    * {@code s} of this regular expression. The match itself is at
    * {@code s.substring(loc[0], loc[1])}.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5326,7 +5299,6 @@ class RE2 {
    * {@code b} and the matches, if any, of its subexpressions, as defined by the <a
    * href='#submatch'>Submatch</a> description above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5349,7 +5321,6 @@ class RE2 {
    * expression in {@code b} and the matches, if any, of its subexpressions, as defined by the the
    * <a href='#submatch'>Submatch</a> and <a href='#index'>Index</a> descriptions above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5362,7 +5333,6 @@ class RE2 {
    * {@code s} and the matches, if any, of its subexpressions, as defined by the <a
    * href='#submatch'>Submatch</a> description above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5385,7 +5355,6 @@ class RE2 {
    * expression in {@code s} and the matches, if any, of its subexpressions, as defined by the <a
    * href='#submatch'>Submatch</a> description above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5398,7 +5367,6 @@ class RE2 {
    * list of up to {@code n} successive matches of the expression, as defined by the <a
    * href='#all'>All</a> description above.
    *
-   * <p>
    * A return value of null indicates no match.
    *
    * TODO(adonovan): think about defining a byte slice view class, like a read-only Go slice backed
@@ -5418,7 +5386,6 @@ class RE2 {
    * returns a list of up to {@code n} successive matches of the expression, as defined by the <a
    * href='#all'>All</a> description above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5435,7 +5402,6 @@ class RE2 {
    * to {@code n} successive matches of the expression, as defined by the <a href='#all'>All</a>
    * description above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5452,7 +5418,6 @@ class RE2 {
    * list of up to {@code n} successive matches of the expression, as defined by the <a
    * href='#all'>All</a> description above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5469,7 +5434,6 @@ class RE2 {
    * it returns a list of up to {@code n} successive matches of the expression, as defined by the <a
    * href='#all'>All</a> description above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5494,7 +5458,6 @@ class RE2 {
    * {@link #findUTF8SubmatchIndex}; it returns a list of up to {@code n} successive matches of the
    * expression, as defined by the <a href='#all'>All</a> description above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5511,7 +5474,6 @@ class RE2 {
    * returns a list of up to {@code n} successive matches of the expression, as defined by the <a
    * href='#all'>All</a> description above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5536,7 +5498,6 @@ class RE2 {
    * {@link #findSubmatchIndex}; it returns a list of up to {@code n} successive matches of the
    * expression, as defined by the <a href='#all'>All</a> description above.
    *
-   * <p>
    * A return value of null indicates no match.
    */
   // This is visible for testing.
@@ -5552,7 +5513,6 @@ class RE2 {
 /**
  * A compiled representation of an RE2 regular expression
  *
- * <p>
  * The matching functions take {@code String} arguments instead of the more general Java
  * {@code CharSequence} since the latter doesn't provide UTF-16 decoding.
  *
@@ -5586,10 +5546,9 @@ class RE2JS {
   /**
    * Returns a literal pattern string for the specified string.
    *
-   * <p>
    * This method produces a string that can be used to create a <code>RE2JS</code> that would
    * match the string <code>s</code> as if it were a literal pattern.
-   * </p>
+   *
    * Metacharacters or escape sequences in the input sequence will be given no special meaning.
    *
    * @param {string} str The string to be literalized
@@ -5605,8 +5564,7 @@ class RE2JS {
    * @param {number} [flags=0]
    * @returns {RE2JS}
    */
-  static compile(regex) {
-    let flags = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 0;
+  static compile(regex, flags = 0) {
     let fregex = regex;
     if ((flags & RE2JS.CASE_INSENSITIVE) !== 0) {
       fregex = `(?i)${fregex}`;
@@ -5725,7 +5683,6 @@ class RE2JS {
    * Splits input around instances of the regular expression. It returns an array giving the strings
    * that occur before, between, and after instances of the regular expression.
    *
-   * <p>
    * If {@code limit <= 0}, there is no limit on the size of the returned array. If
    * {@code limit == 0}, empty strings that would occur at the end of the array are omitted. If
    * {@code limit > 0}, at most limit strings are returned. The final string contains the remainder
@@ -5735,8 +5692,7 @@ class RE2JS {
    * @param {number} [limit=0] the limit
    * @returns {string[]} the split strings
    */
-  split(input) {
-    let limit = arguments.length > 1 && arguments[1] !== undefined ? arguments[1] : 0;
+  split(input, limit = 0) {
     const m = this.matcher(input);
     const result = [];
     let emptiesSkipped = 0;