re2js 2.2.2 → 2.3.0

package/build/index.umd.js

@@ -2,7 +2,7 @@
  * re2js
  * RE2JS is the JavaScript port of RE2, a regular expression engine that provides linear time matching
  *
- * @version v2.2.2
+ * @version v2.3.0
  * @author Oleksii Vasyliev
  * @homepage https://github.com/le0pard/re2js#readme
  * @repository github:le0pard/re2js
@@ -100,7 +100,7 @@
   }
   class Codepoint {
     // codePointAt(0)
-    static CODES = new Map([['\x07', 7], ['\b', 8], ['\t', 9], ['\n', 10], ['\v', 11], ['\f', 12], ['\r', 13], [' ', 32], ['"', 34], ['$', 36], ['&', 38], ['(', 40], [')', 41], ['*', 42], ['+', 43], ['-', 45], ['.', 46], ['0', 48], ['1', 49], ['2', 50], ['3', 51], ['4', 52], ['5', 53], ['6', 54], ['7', 55], ['8', 56], ['9', 57], [':', 58], ['<', 60], ['>', 62], ['?', 63], ['A', 65], ['B', 66], ['C', 67], ['F', 70], ['P', 80], ['Q', 81], ['U', 85], ['Z', 90], ['[', 91], ['\\', 92], [']', 93], ['^', 94], ['_', 95], ['a', 97], ['b', 98], ['f', 102], ['i', 105], ['m', 109], ['n', 110], ['r', 114], ['s', 115], ['t', 116], ['v', 118], ['x', 120], ['z', 122], ['{', 123], ['|', 124], ['}', 125]]);
+    static CODES = new Map([['\x07', 7], ['\b', 8], ['\t', 9], ['\n', 10], ['\v', 11], ['\f', 12], ['\r', 13], [' ', 32], ['"', 34], ['$', 36], ['&', 38], ["'", 39], ['(', 40], [')', 41], ['*', 42], ['+', 43], ['-', 45], ['.', 46], ['0', 48], ['1', 49], ['2', 50], ['3', 51], ['4', 52], ['5', 53], ['6', 54], ['7', 55], ['8', 56], ['9', 57], [':', 58], ['<', 60], ['>', 62], ['?', 63], ['A', 65], ['B', 66], ['C', 67], ['F', 70], ['P', 80], ['Q', 81], ['U', 85], ['Z', 90], ['[', 91], ['\\', 92], [']', 93], ['^', 94], ['_', 95], ['`', 96], ['a', 97], ['b', 98], ['f', 102], ['i', 105], ['m', 109], ['n', 110], ['r', 114], ['s', 115], ['t', 116], ['v', 118], ['x', 120], ['z', 122], ['{', 123], ['|', 124], ['}', 125]]);
 
     // convert unicode codepoint to upper case codepoint
     // return same codepoint, if cannot do it (or codepoint not have upper variation)
@@ -154,10 +154,6 @@
     getStride(index) {
       return this.isStride1 ? 1 : this.data[index * this.SIZE + 2];
     }
-    get(index) {
-      const i = index * this.SIZE;
-      return [this.data[i], this.data[i + 1], this.getStride(index)];
-    }
     get length() {
       return this.data.length / this.SIZE;
     }
@@ -654,6 +650,9 @@
     static emptyInts() {
       return [];
     }
+    static isByteArray(input) {
+      return Array.isArray(input) || input instanceof Uint8Array;
+    }
 
     // Returns true iff |c| is an ASCII letter or decimal digit.
     static isalnum(c) {
@@ -955,7 +954,7 @@
      * @returns {number[]}
      */
     asBytes() {
-      return this.charSequence.toString().split('').map(s => s.codePointAt(0));
+      return Utils.stringToUtf8ByteArray(this.charSequence.toString());
     }
 
     /**
@@ -980,7 +979,7 @@
      * @returns {Utf8MatcherInput}
      */
     static utf8(input) {
-      if (Array.isArray(input)) {
+      if (Utils.isByteArray(input)) {
         return new Utf8MatcherInput(input);
       }
       return new Utf8MatcherInput(Utils.stringToUtf8ByteArray(input));
@@ -1112,10 +1111,10 @@
           if (start < this.start) {
             start = this.start;
           }
-          r1 = this.step(start) >> 3;
+          r1 = this.step(start - this.start) >> 3;
         }
       }
-      const r2 = pos < this.end ? this.step(pos) >> 3 : -1;
+      const r2 = pos < this.end ? this.step(pos - this.start) >> 3 : -1;
       return Utils.emptyOpContext(r1, r2);
     }
 
@@ -1197,14 +1196,17 @@
     index(re2, pos) {
       pos += this.start;
       const i = this.charSequence.indexOf(re2.prefix, pos);
-      return i < 0 ? i : i - pos;
+      if (i < 0 || i > this.end - re2.prefix.length) {
+        return -1;
+      }
+      return i - pos;
     }
 
     // Returns a bitmask of EMPTY_* flags.
     context(pos) {
       pos += this.start;
-      const r1 = pos > 0 && pos <= this.charSequence.length ? this.charSequence.codePointAt(pos - 1) : -1;
-      const r2 = pos < this.charSequence.length ? this.charSequence.codePointAt(pos) : -1;
+      const r1 = pos > this.start && pos <= this.end ? this.charSequence.codePointAt(pos - 1) : -1;
+      const r2 = pos < this.end ? this.charSequence.codePointAt(pos) : -1;
       return Utils.emptyOpContext(r1, r2);
     }
     prefixLength(re2) {
@@ -1333,6 +1335,11 @@
    *
    * @author rsc@google.com (Russ Cox)
    */
+
+  /**
+   * @typedef {import('./index').RE2JS} RE2JS_Pattern
+   */
+
   class Matcher {
     /**
      * Quotes '\' and '$' in {@code s}, so that the returned string could be used in
@@ -1370,14 +1377,17 @@
     }
     /**
      *
-     * @param {RE2JS} pattern
-     * @param {Utf8MatcherInput|Utf16MatcherInput|number[]|string} input
+     * @param {RE2JS_Pattern} pattern
+     * @param {Uint8Array|number[]|string} input
      */
     constructor(pattern, input) {
       if (pattern === null) {
         throw new Error('pattern is null');
       }
-      // The pattern being matched.
+      /**
+       * The pattern being matched.
+       * @type {RE2JS_Pattern}
+       */
       this.patternInput = pattern;
       const re2 = this.patternInput.re2();
       // The number of submatches (groups) in the pattern.
@@ -1392,7 +1402,7 @@
       this.numberOfInstructions = re2.numberOfInstructions();
       if (input instanceof MatcherInputBase) {
         this.resetMatcherInput(input);
-      } else if (Array.isArray(input)) {
+      } else if (Utils.isByteArray(input)) {
         this.resetMatcherInput(MatcherInput.utf8(input));
       } else {
         this.resetMatcherInput(MatcherInput.utf16(input));
@@ -1401,7 +1411,7 @@
 
     /**
      * Returns the {@code RE2JS} associated with this {@code Matcher}.
-     * @returns {RE2JS}
+     * @returns {RE2JS_Pattern}
      */
     pattern() {
       return this.patternInput;
@@ -1431,7 +1441,7 @@
 
     /**
      * Resets the {@code Matcher} and changes the input.
-     * @param {Utf8MatcherInput|Utf16MatcherInput} input
+     * @param {import('./MatcherInput').MatcherInputBase} input
      * @returns {Matcher} the {@code Matcher} itself, for chained method calls
      */
     resetMatcherInput(input) {
@@ -1496,7 +1506,7 @@
     /**
      * Returns the named group of the most recent match, or {@code null} if the group was not matched.
      * @param {string|number} [group=0]
-     * @returns {?string}
+     * @returns {string|null}
      */
     group(group = 0) {
       if (typeof group === 'string') {
@@ -1554,10 +1564,7 @@
       if (group === 0 || this.hasGroups) {
         return;
       }
-      let end = this.groups[1] + 1;
-      if (end > this.matcherInputLength) {
-        end = this.matcherInputLength;
-      }
+      const end = this.matcherInputLength;
       const res = this.patternInput.re2().matchMachineInput(this.matcherInput, this.groups[0], end, this.anchorFlag, 1 + this.patternGroupCount);
       const ok = res[0];
       if (!ok) {
@@ -1591,7 +1598,7 @@
      * Matches the input against the pattern (unanchored), starting at a specified position. If there
      * is a match, {@code find} sets the match state to describe it.
      *
-     * @param {number} [start=null] the input position where the search begins
+     * @param {number|null} [start=null] the input position where the search begins
      * @returns {boolean} if it finds a match
      * @throws IndexOutOfBoundsException if start is not a valid input position
      */
@@ -1753,7 +1760,10 @@
               throw new RE2JSGroupException("named capture group is missing trailing '}'");
             }
             const groupName = replacement.substring(i + 1, j);
-            res += this.group(groupName);
+            const groupVal = this.group(groupName);
+            if (groupVal !== null) {
+              res += groupVal;
+            }
             last = j + 1;
             i = j;
             continue;
@@ -1799,6 +1809,22 @@
             i++;
             last = i + 1;
             continue;
+          } else if (Codepoint.CODES.get('`') === c) {
+            if (last < i) {
+              res += replacement.substring(last, i);
+            }
+            res += this.substring(0, this.start(0));
+            i++;
+            last = i + 1;
+            continue;
+          } else if (Codepoint.CODES.get("'") === c) {
+            if (last < i) {
+              res += replacement.substring(last, i);
+            }
+            res += this.substring(this.end(0), this.matcherInputLength);
+            i++;
+            last = i + 1;
+            continue;
           } else if (Codepoint.CODES.get('1') <= c && c <= Codepoint.CODES.get('9')) {
             let n = c - Codepoint.CODES.get('0');
             if (last < i) {
@@ -1841,7 +1867,10 @@
             }
             const groupName = replacement.substring(i + 1, j);
             if (Object.prototype.hasOwnProperty.call(this.namedGroups, groupName)) {
-              res += this.group(groupName);
+              const groupVal = this.group(groupName);
+              if (groupVal !== null) {
+                res += groupVal;
+              }
             } else {
               res += `$<${groupName}>`;
             }
@@ -4343,13 +4372,6 @@
     // start every program with a fail instruction, so we'll never want to point
     // at its output link.
 
-    next(l) {
-      const i = this.inst[l >> 1];
-      if ((l & 1) === 0) {
-        return i.out;
-      }
-      return i.arg;
-    }
     patch(l, val) {
       let head = l.head;
       while (head !== 0) {
@@ -5679,6 +5701,7 @@
         case Codepoint.CODES.get('6'):
         case Codepoint.CODES.get('7'):
           {
+            // Single non-zero digit is a backreference; not supported
             if (!t.more() || t.peek() < Codepoint.CODES.get('0') || t.peek() > Codepoint.CODES.get('7')) {
               break;
             }
@@ -5686,6 +5709,7 @@
         // eslint-disable-next-line no-fallthrough
         case Codepoint.CODES.get('0'):
           {
+            // Consume up to three octal digits; already have one.
             let r = c - Codepoint.CODES.get('0');
             for (let i = 1; i < 3; i++) {
               if (!t.more() || t.peek() < Codepoint.CODES.get('0') || t.peek() > Codepoint.CODES.get('7')) {
@@ -7466,7 +7490,11 @@
      */
     matchWithGroup(input, start, end, anchor, ngroup) {
       if (!(input instanceof MatcherInputBase)) {
-        input = MatcherInput.utf16(input);
+        if (Utils.isByteArray(input)) {
+          input = MatcherInput.utf8(input);
+        } else {
+          input = MatcherInput.utf16(input);
+        }
       }
       return this.matchMachineInput(input, start, end, anchor, ngroup);
     }
@@ -7921,9 +7949,18 @@
   }
 
   class RE2Set {
+    /** @type {number} */
     static UNANCHORED = RE2Flags.UNANCHORED;
+    /** @type {number} */
     static ANCHOR_START = RE2Flags.ANCHOR_START;
+    /** @type {number} */
     static ANCHOR_BOTH = RE2Flags.ANCHOR_BOTH;
+
+    /**
+     * Constructs a new RE2Set with the specified anchor mode and flags.
+     * @param {number} [anchor=RE2Set.UNANCHORED] - The anchoring mode (e.g., RE2Set.UNANCHORED).
+     * @param {number} [flags=0] - The public flags to apply to all patterns in the set.
+     */
     constructor(anchor = RE2Set.UNANCHORED, flags = 0) {
       this.anchor = anchor;
       this.jsFlags = flags;
@@ -7940,6 +7977,14 @@
       this.dfa = null;
       this.dummyRe2 = null;
     }
+
+    /**
+     * Adds a new regular expression pattern to the set.
+     * Patterns cannot be added after the set has been compiled.
+     * @param {string} pattern - The regular expression pattern to add.
+     * @returns {number} The integer index assigned to the added pattern.
+     * @throws {RE2JSCompileException} If patterns are added after compilation.
+     */
     add(pattern) {
       if (this.prog) {
         throw new RE2JSCompileException('Cannot add patterns after compile');
@@ -7958,6 +8003,12 @@
       this.regexps.push(Simplify.simplify(re));
       return this.regexps.length - 1;
     }
+
+    /**
+     * Compiles the added patterns into a single state machine.
+     * This is automatically called on the first match if not called explicitly.
+     * @returns {void}
+     */
     compile() {
       if (this.prog) return;
       this.prog = Compiler.compileSet(this.regexps);
@@ -7970,9 +8021,15 @@
         longest: false
       };
     }
+
+    /**
+     * Matches the input against the compiled set of regular expressions.
+     * @param {string|number[]|Uint8Array} input - The input string or UTF-8 byte array to match against.
+     * @returns {number[]} An array of indices representing the patterns that successfully matched the input.
+     */
     match(input) {
       if (!this.prog) this.compile();
-      const machineInput = Array.isArray(input) ? MachineInput.fromUTF8(input) : MachineInput.fromUTF16(input);
+      const machineInput = Utils.isByteArray(input) ? MachineInput.fromUTF8(input) : MachineInput.fromUTF16(input);
       let internalAnchor = RE2Flags.UNANCHORED;
       if (this.anchor === RE2Set.ANCHOR_START) {
         internalAnchor = RE2Flags.ANCHOR_START;
@@ -7995,13 +8052,19 @@
    * Transform JS regex string to RE2 regex string
    */
   class TranslateRegExpString {
-    static isUpperCaseAlpha(ch) {
-      return 'A' <= ch && ch <= 'Z';
-    }
     static isHexadecimal(ch) {
       return '0' <= ch && ch <= '9' || 'A' <= ch && ch <= 'F' || 'a' <= ch && ch <= 'f';
     }
     static translate(data) {
+      let prefixFlags = '';
+      if (data instanceof RegExp) {
+        if (data.ignoreCase) prefixFlags += 'i';
+        if (data.multiline) prefixFlags += 'm';
+        if (data.dotAll) prefixFlags += 's';
+
+        // execution flags ('g', 'y') are safely ignored here.
+        data = data.source;
+      }
       if (typeof data !== 'string') {
         return data;
       }
@@ -8012,6 +8075,7 @@
         result = '(?:)';
         changed = true;
       }
+      let inCharClass = false;
       let i = 0;
       while (i < size) {
         let ch = data[i];
@@ -8029,54 +8093,160 @@
                 {
                   if (i + 2 < size) {
                     let nextCh = data[i + 2];
-                    if (TranslateRegExpString.isUpperCaseAlpha(nextCh)) {
+                    let code = nextCh.charCodeAt(0);
+                    if (code >= 65 && code <= 90 || code >= 97 && code <= 122) {
+                      let val = code % 32;
                       result += '\\x';
-                      result += (nextCh.charCodeAt(0) - 64 >> 4).toString(16).toUpperCase();
-                      result += (nextCh.charCodeAt(0) - 64 & 15).toString(16).toUpperCase();
+                      result += (val >> 4).toString(16).toUpperCase();
+                      result += (val & 15).toString(16).toUpperCase();
                       i += 3;
                       changed = true;
                       continue;
                     }
                   }
-                  result += '\\c';
+                  result += 'c';
                   i += 2;
+                  changed = true;
                   continue;
                 }
               case 'u':
                 {
                   if (i + 2 < size) {
                     let nextCh = data[i + 2];
-                    if (TranslateRegExpString.isHexadecimal(nextCh)) {
-                      result += '\\x{' + nextCh;
-                      i += 3;
-                      for (let j = 0; j < 3 && i < size; ++i, ++j) {
-                        nextCh = data[i];
-                        if (!TranslateRegExpString.isHexadecimal(nextCh)) {
+                    if (nextCh === '{') {
+                      // Must have a closing brace and at least one valid hex digit inside
+                      let j = i + 3;
+                      let hasHex = false;
+                      let closed = false;
+                      while (j < size) {
+                        const hexChar = data[j];
+                        if (hexChar === '}') {
+                          closed = true;
+                          break;
+                        }
+                        if (!TranslateRegExpString.isHexadecimal(hexChar)) {
                           break;
                         }
-                        result += nextCh;
+                        hasHex = true;
+                        j++;
+                      }
+                      if (closed && hasHex) {
+                        result += '\\x';
+                        i += 2;
+                        changed = true;
+                        continue;
+                      }
+                    } else if (i + 5 < size) {
+                      let isHex4 = true;
+                      for (let j = 0; j < 4; j++) {
+                        if (!TranslateRegExpString.isHexadecimal(data[i + 2 + j])) {
+                          isHex4 = false;
+                          break;
+                        }
+                      }
+                      if (isHex4) {
+                        result += '\\x{' + data.substring(i + 2, i + 6) + '}';
+                        i += 6;
+                        changed = true;
+                        continue;
                       }
-                      result += '}';
-                      changed = true;
-                      continue;
-                    } else if (nextCh === '{') {
-                      result += '\\x';
-                      i += 2;
-                      changed = true;
-                      continue;
                     }
                   }
-                  result += '\\u';
+
+                  // Graceful degradation for invalid/unclosed \u sequences
+                  result += 'u';
+                  i += 2;
+                  changed = true;
+                  continue;
+                }
+              case 'x':
+                {
+                  let isValidHex = false;
+                  if (i + 2 < size && data[i + 2] === '{') {
+                    // Must have a closing brace and at least one valid hex digit inside
+                    let j = i + 3;
+                    let hasHex = false;
+                    let closed = false;
+                    while (j < size) {
+                      const hexChar = data[j];
+                      if (hexChar === '}') {
+                        closed = true;
+                        break;
+                      }
+                      if (!TranslateRegExpString.isHexadecimal(hexChar)) {
+                        break;
+                      }
+                      hasHex = true;
+                      j++;
+                    }
+                    if (closed && hasHex) {
+                      isValidHex = true;
+                    }
+                  } else if (i + 3 < size && TranslateRegExpString.isHexadecimal(data[i + 2]) && TranslateRegExpString.isHexadecimal(data[i + 3])) {
+                    isValidHex = true;
+                  }
+                  if (isValidHex) {
+                    result += '\\x';
+                    i += 2;
+                  } else {
+                    result += 'x';
+                    i += 2;
+                    changed = true;
+                  }
+                  continue;
+                }
+              // Whitelist of valid RE2/JS alphanumeric escapes
+              case 'n':
+              case 'r':
+              case 't':
+              case 'a':
+              case 'f':
+              case 'v':
+              case 'd':
+              case 'D':
+              case 's':
+              case 'S':
+              case 'w':
+              case 'W':
+              case 'b':
+              case 'B':
+              case 'p':
+              case 'P':
+              case 'A':
+              case 'z':
+              case 'Q':
+              case 'E':
+              case '0':
+              case '1':
+              case '2':
+              case '3':
+              case '4':
+              case '5':
+              case '6':
+              case '7':
+                {
+                  result += '\\' + ch;
                   i += 2;
                   continue;
                 }
               default:
                 {
-                  result += '\\';
                   let cp = data.codePointAt(i + 1);
-                  let symSize = Utils.charCount(cp);
-                  result += data.substring(i + 1, i + 1 + symSize);
-                  i += symSize + 1;
+                  let isAlphaNum = cp >= 48 && cp <= 57 || cp >= 65 && cp <= 90 || cp >= 97 && cp <= 122;
+                  if (isAlphaNum) {
+                    // Invalid JS alphanumeric escape sequence (e.g. \8, \9, \e, \K)
+                    // Gracefully degrade to the literal character to prevent RE2 syntax crashes
+                    let symSize = Utils.charCount(cp);
+                    result += data.substring(i + 1, i + 1 + symSize);
+                    i += symSize + 1;
+                    changed = true;
+                  } else {
+                    // Escaped symbol (e.g. \., \*, \])
+                    result += '\\';
+                    let symSize = Utils.charCount(cp);
+                    result += data.substring(i + 1, i + 1 + symSize);
+                    i += symSize + 1;
+                  }
                   continue;
                 }
             }
@@ -8086,7 +8256,13 @@
           i += 1;
           changed = true;
           continue;
-        } else if (ch === '(' && i + 2 < size && data[i + 1] === '?' && data[i + 2] === '<') {
+        } else if (ch === '[') {
+          // Track entry into a character class (protects syntax inside)
+          inCharClass = true;
+        } else if (ch === ']') {
+          // Track exit of a character class
+          inCharClass = false;
+        } else if (!inCharClass && ch === '(' && i + 2 < size && data[i + 1] === '?' && data[i + 2] === '<') {
           if (i + 3 < size && !'=!>)'.includes(data[i + 3])) {
             result += '(?P<';
             i += 3;
@@ -8099,7 +8275,13 @@
         result += data.substring(i, i + symSize);
         i += symSize;
       }
-      return changed ? result : data;
+      const finalResult = changed ? result : data;
+
+      // Append any extracted inline flags
+      if (prefixFlags.length > 0) {
+        return `(?${prefixFlags})${finalResult}`;
+      }
+      return finalResult;
     }
   }
 
@@ -8177,7 +8359,7 @@
      * RE2JS-compatible syntax, and handling Unicode sequences properly. It ensures that the
      * resulting regex is safe and properly formatted before compilation.
      *
-     * @param {string} expr - The regular expression string to be translated.
+     * @param {string|RegExp} expr - The regular expression string to be translated.
      * @returns {string} - The transformed regular expression string, ready for compilation.
      */
     static translateRegExp(expr) {
@@ -8221,7 +8403,7 @@
      * Matches a string against a regular expression.
      *
      * @param {string} regex the regular expression
-     * @param {string|number[]} input the input
+     * @param {string|number[]|Uint8Array} input the input
      * @returns {boolean} true if the regular expression matches the entire input
      * @throws RE2JSSyntaxException if the regular expression is malformed
      */
@@ -8288,7 +8470,7 @@
     /**
      * Matches a string against a regular expression.
      *
-     * @param {string|number[]} input the input
+     * @param {string|number[]|Uint8Array} input the input
      * @returns {boolean} true if the regular expression matches the entire input
      */
     matches(input) {
@@ -8298,11 +8480,11 @@
     /**
      * Creates a new {@code Matcher} matching the pattern against the input.
      *
-     * @param {string|number[]} input the input string
+     * @param {string|number[]|Uint8Array} input the input string
      * @returns {Matcher}
      */
     matcher(input) {
-      if (Array.isArray(input)) {
+      if (Utils.isByteArray(input)) {
         input = MatcherInput.utf8(input);
       }
       return new Matcher(this, input);
@@ -8314,11 +8496,11 @@
      * a boolean and does not extract capture groups, it bypasses the `Matcher` overhead
      * and guarantees execution on the high-speed DFA engine whenever possible.
      *
-     * @param {string|number[]} input - The input string or UTF-8 byte array to test against.
+     * @param {string|number[]|Uint8Array} input - The input string or UTF-8 byte array to test against.
      * @returns {boolean} `true` if the pattern is found anywhere in the input, `false` otherwise.
      */
     test(input) {
-      if (Array.isArray(input)) {
+      if (Utils.isByteArray(input)) {
         // Reuse the existing UTF-8 fast-path method
         return this.re2Input.matchUTF8(input);
       }
@@ -8333,11 +8515,11 @@
      * faster because it does not request capture group data. By requesting 0 capture groups,
      * it securely routes execution through the DFA fast-path.
      *
-     * @param {string|number[]} input - The input string or UTF-8 byte array to test against.
+     * @param {string|number[]|Uint8Array} input - The input string or UTF-8 byte array to test against.
      * @returns {boolean} `true` if the exact input string fully matches the pattern, `false` otherwise.
      */
     testExact(input) {
-      const machineInput = Array.isArray(input) ? MachineInput.fromUTF8(input) : MachineInput.fromUTF16(input);
+      const machineInput = Utils.isByteArray(input) ? MachineInput.fromUTF8(input) : MachineInput.fromUTF16(input);
       return this.re2Input.executeEngine(machineInput, 0, RE2Flags.ANCHOR_BOTH, 0) !== null;
     }