re2js 2.2.2 → 2.2.3

package/README.md

@@ -473,6 +473,8 @@ Parameters:
   - `$1, $2, ...` refer to the corresponding capture groups in the pattern
   - `$$` inserts a literal `$`
   - `$<name>` can be used to reference named capture groups
+  - `` $` `` inserts the portion of the string that precedes the matched substring
+  - `$'` inserts the portion of the string that follows the matched substring
   - on invalid group - ignore it
 - `javaMode (Boolean)`: If set to `true`, the replacement follows Java's rules for replacement. Defaults to `false`. If `javaMode = true`, changed rules for capture groups and special characters:
   - `$0` refers to the entire matched substring

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 v2.2.2
+ * @version v2.2.3
  * @author Oleksii Vasyliev
  * @homepage https://github.com/le0pard/re2js#readme
  * @repository github:le0pard/re2js
@@ -96,7 +96,7 @@ for (let i = 0; i < ASCII_SIZE; i++) {
 }
 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)
@@ -150,10 +150,6 @@ class UnicodeRangeTable {
   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;
   }
@@ -650,6 +646,9 @@ class Utils {
   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) {
@@ -951,7 +950,7 @@ class Utf16MatcherInput extends MatcherInputBase {
    * @returns {number[]}
    */
   asBytes() {
-    return this.charSequence.toString().split('').map(s => s.codePointAt(0));
+    return Utils.stringToUtf8ByteArray(this.charSequence.toString());
   }
 
   /**
@@ -976,7 +975,7 @@ class MatcherInput {
    * @returns {Utf8MatcherInput}
    */
   static utf8(input) {
-    if (Array.isArray(input)) {
+    if (Utils.isByteArray(input)) {
       return new Utf8MatcherInput(input);
     }
     return new Utf8MatcherInput(Utils.stringToUtf8ByteArray(input));
@@ -1108,10 +1107,10 @@ class MachineUTF8Input extends MachineInputBase {
         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);
   }
 
@@ -1193,14 +1192,17 @@ class MachineUTF16Input extends MachineInputBase {
   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) {
@@ -1388,7 +1390,7 @@ class Matcher {
     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));
@@ -1550,10 +1552,7 @@ class Matcher {
     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) {
@@ -1749,7 +1748,10 @@ class Matcher {
             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;
@@ -1795,6 +1797,22 @@ class Matcher {
           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) {
@@ -1837,7 +1855,10 @@ class Matcher {
           }
           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}>`;
           }
@@ -4339,13 +4360,6 @@ class Prog {
   // 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) {
@@ -5675,6 +5689,7 @@ class Parser {
       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;
           }
@@ -5682,6 +5697,7 @@ class Parser {
       // 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')) {
@@ -7462,7 +7478,11 @@ class RE2 {
    */
   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);
   }
@@ -7968,7 +7988,7 @@ class RE2Set {
   }
   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;
@@ -8025,45 +8045,50 @@ class TranslateRegExpString {
               {
                 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)) {
-                        break;
-                      }
-                      result += nextCh;
-                    }
-                    result += '}';
-                    changed = true;
-                    continue;
-                  } else if (nextCh === '{') {
+                  if (nextCh === '{') {
                     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 += '\\u';
+                result += 'u';
                 i += 2;
+                changed = true;
                 continue;
               }
             default:
@@ -8298,7 +8323,7 @@ class RE2JS {
    * @returns {Matcher}
    */
   matcher(input) {
-    if (Array.isArray(input)) {
+    if (Utils.isByteArray(input)) {
       input = MatcherInput.utf8(input);
     }
     return new Matcher(this, input);
@@ -8314,7 +8339,7 @@ class RE2JS {
    * @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);
     }
@@ -8333,7 +8358,7 @@ class RE2JS {
    * @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;
   }