re2js 2.0.0 → 2.0.1

package/build/index.esm.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.esm.d.ts","sourceRoot":"","sources":["index.esm.js"],"names":[],"mappings":"AA0kCA;;;;;;;;;;;;;;;;;;;;;GAqBG;AACH;IACE;;;;;;;OAOG;IACH,6BAJW,MAAM,aACN,OAAO,GACL,MAAM,CA2BlB;IACD;;;;OAIG;IACH,qBAHW,KAAK,SACL,gBAAgB,GAAC,iBAAiB,GAAC,MAAM,EAAE,GAAC,MAAM,EA0B5D;IAnBC,oBAA2B;IAG3B,qBAAqB;IACrB,mBADW,MAAM,CACqC;IAEtD,uBAAuB;IACvB,QADW,MAAM,EAAE,CACH;IAChB,qCAAqC;IACrC,aADW,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CACC;IAClC,qBAAqB;IACrB,sBADW,MAAM,CACqC;IAUxD;;;OAGG;IACH,WAFa,KAAK,CAIjB;IAED;;;;OAIG;IACH,SAFa,OAAO,CAiBnB;IAbC,qBAAqB;IACrB,uCAAoD;IAEpD,qBAAqB;IACrB,8BAAkB;IAElB,8BAAqB;IAGrB,+BAAsB;IAEtB,+BAAmB;IAIrB;;;;OAIG;IACH,yBAHW,gBAAgB,GAAC,iBAAiB,GAChC,OAAO,CASnB;IAHC,+DAAyB;IAK3B;;;;;OAKG;IACH,cAHW,MAAM,GAAC,MAAM,GACX,MAAM,CAYlB;IAED;;;;;OAKG;IACH,YAHW,MAAM,GAAC,MAAM,GACX,MAAM,CAYlB;IAED;;;;;;;;;OASG;IACH,eAFa,MAAM,CAIlB;IAED;;;;OAIG;IACH,cAHW,MAAM,GAAC,MAAM,GACV,MAAM,OAAA,CAgBnB;IACD;;;;OAIG;IACH,cAFa,MAAM,CAIlB;IAED;;;;OAIG;IACH,kBAqBC;IAED;;;;;OAKG;IACH,WAFa,OAAO,CAInB;IAED;;;;;OAKG;IACH,aAFa,OAAO,CAInB;IAED;;;;;;;OAOG;IACH,aAJW,MAAM,GACJ,OAAO,CAoBnB;IAED;;;;;;OAMG;IACH,iBAWC;IAED;;;;;OAKG;IACH,iBAJW,MAAM,OACN,MAAM,GACJ,MAAM,CAOlB;IAED;;;OAGG;IACH,eAFa,MAAM,CAIlB;IAED;;;;;;;;;;;;;;;;;;;;OAoBG;IACH,0BAUC;IAED;;;;OAIG;IACH,sCA2DC;IAED;;;;OAIG;IACH,oCAiFC;IAED;;;;OAIG;IACH,cAFa,MAAM,CAIlB;IAED;;;;;;;;OAQG;IACH,wBALW,MAAM,aACN,OAAO,GACL,MAAM,CAKlB;IAED;;;;;;;;OAQG;IACH,0BALW,MAAM,aACN,OAAO,GACL,MAAM,CAKlB;IAED;;;;;;;OAOG;IACH,gBAWC;CACF;AAq5ID;;;;;;;;;GASG;AACH;IACE;;OAEG;IACH,gCAA4B;IAC5B;;OAEG;IACH,sBAAkB;IAClB;;;OAGG;IACH,yBAAqB;IACrB;;OAEG;IACH,sCAAkC;IAClC;;OAEG;IACH,6BAA0B;IAE1B;;;;;;;;;;OAUG;IACH,kBAHW,MAAM,GACJ,MAAM,CAIlB;IAED;;;;;;;;;OASG;IACH,6BAJW,MAAM,aACN,OAAO,GACL,MAAM,CAIlB;IAED;;;;;;;;;;OAUG;IACH,6BAHW,MAAM,GACJ,MAAM,CAIlB;IAED;;;;;OAKG;IACH,sBAJW,MAAM,UACN,MAAM,GACJ,KAAK,CAwBjB;IAED;;;;;;;OAOG;IACH,sBALW,MAAM,SACN,MAAM,GAAC,MAAM,EAAE,GACb,OAAO,CAKnB;IAED;;;OAGG;IACH,wBAWC;IAED;;;;OAIG;IACH,qBAHW,MAAM,SACN,MAAM,EAOhB;IAHC,qBAA2B;IAE3B,mBAAuB;IAGzB;;;OAGG;IACH,cAEC;IAED;;;OAGG;IACH,SAFa,MAAM,CAIlB;IAED;;;OAGG;IACH,WAFa,MAAM,CAIlB;IACD,WAEC;IAED;;;;;OAKG;IACH,eAHW,MAAM,GAAC,MAAM,EAAE,GACb,OAAO,CAInB;IAED;;;;;OAKG;IACH,eAHW,MAAM,GAAC,MAAM,EAAE,GACb,OAAO,CAOnB;IAED;;;;;;;;OAQG;IACH,YAHW,MAAM,GAAC,MAAM,EAAE,GACb,OAAO,CAUnB;IAED;;;;;;;;OAQG;IACH,iBAHW,MAAM,GAAC,MAAM,EAAE,GACb,OAAO,CAKnB;IAED;;;;;;;;;;;;OAYG;IACH,aAJW,MAAM,UACN,MAAM,GACJ,MAAM,EAAE,CAgDpB;IAED;;;OAGG;IACH,YAFa,MAAM,CAIlB;IAED;;;;;;;;;OASG;IACH,eAFa,MAAM,CAIlB;IAED;;;;;OAKG;IACH,cAFa,MAAM,CAIlB;IAED;;;;OAIG;IACH,eAFa,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAIlC;IAED;;;;OAIG;IACH,cAHW,GAAC,GACC,OAAO,CAUnB;CACF;AA10KD;;GAEG;AACH;CAMC;AAxDD;IACE,8BAA8B;IAC9B,qBADY,MAAM,EAIjB;CACF;AA+DD;;GAEG;AACH;CAMC;AApBD;;GAEG;AACH;CAMC;AA3DD;;GAEG;AACH;IACE;;;OAGG;IACH,mBAHW,MAAM,UACN,MAAM,GAAC,IAAI,EAcrB;IAJC,qBAAqB;IACrB,OADW,MAAM,CACC;IAClB,0BAA0B;IAC1B,OADW,MAAM,GAAC,IAAI,CACJ;IAGpB;;;OAGG;IACH,kBAFa,MAAM,CAIlB;IAED;;;OAGG;IACH,cAFa,MAAM,GAAC,IAAI,CAIvB;CACF;AAlTD;IACE,0BAGC;IADC,WAAkB;IAEpB,mBAEC;IACD;;;OAGG;IACH,kBAFa,MAAM,CAIlB;IAED;;;OAGG;IACH,WAFa,MAAM,EAAE,CAIpB;IAED;;;OAGG;IACH,UAFa,MAAM,CAIlB;CACF;AACD;IACE,iCAGC;IADC,kBAAgC;IAElC,mBAEC;IAED;;;OAGG;IACH,kBAFa,MAAM,CAIlB;IAED;;;OAGG;IACH,WAFa,MAAM,EAAE,CAIpB;IAED;;;OAGG;IACH,UAFa,MAAM,CAIlB;CACF;AAzFD;;GAEG;AACH;IACE,8BAAkD;IAClD,oBAEC;IAED;;;OAGG;IACH,kBAFa,OAAO,CAInB;IAED;;;OAGG;IACH,mBAFa,OAAO,CAInB;CACF"}
+{"version":3,"file":"index.esm.d.ts","sourceRoot":"","sources":["index.esm.js"],"names":[],"mappings":"AAwlCA;;;;;;;;;;;;;;;;;;;;;GAqBG;AACH;IACE;;;;;;;OAOG;IACH,6BAJW,MAAM,aACN,OAAO,GACL,MAAM,CA2BlB;IACD;;;;OAIG;IACH,qBAHW,KAAK,SACL,gBAAgB,GAAC,iBAAiB,GAAC,MAAM,EAAE,GAAC,MAAM,EA0B5D;IAnBC,oBAA2B;IAG3B,qBAAqB;IACrB,mBADW,MAAM,CACqC;IAEtD,uBAAuB;IACvB,QADW,MAAM,EAAE,CACH;IAChB,qCAAqC;IACrC,aADW,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CACC;IAClC,qBAAqB;IACrB,sBADW,MAAM,CACqC;IAUxD;;;OAGG;IACH,WAFa,KAAK,CAIjB;IAED;;;;OAIG;IACH,SAFa,OAAO,CAiBnB;IAbC,qBAAqB;IACrB,uCAAoD;IAEpD,qBAAqB;IACrB,8BAAkB;IAElB,8BAAqB;IAGrB,+BAAsB;IAEtB,+BAAmB;IAIrB;;;;OAIG;IACH,yBAHW,gBAAgB,GAAC,iBAAiB,GAChC,OAAO,CASnB;IAHC,+DAAyB;IAK3B;;;;;OAKG;IACH,cAHW,MAAM,GAAC,MAAM,GACX,MAAM,CAYlB;IAED;;;;;OAKG;IACH,YAHW,MAAM,GAAC,MAAM,GACX,MAAM,CAYlB;IAED;;;;;;;;;OASG;IACH,eAFa,MAAM,CAIlB;IAED;;;;OAIG;IACH,cAHW,MAAM,GAAC,MAAM,GACV,MAAM,OAAA,CAgBnB;IACD;;;;OAIG;IACH,cAFa,MAAM,CAIlB;IAED;;;;OAIG;IACH,kBAqBC;IAED;;;;;OAKG;IACH,WAFa,OAAO,CAInB;IAED;;;;;OAKG;IACH,aAFa,OAAO,CAInB;IAED;;;;;;;OAOG;IACH,aAJW,MAAM,GACJ,OAAO,CAoBnB;IAED;;;;;;OAMG;IACH,iBAWC;IAED;;;;;OAKG;IACH,iBAJW,MAAM,OACN,MAAM,GACJ,MAAM,CAOlB;IAED;;;OAGG;IACH,eAFa,MAAM,CAIlB;IAED;;;;;;;;;;;;;;;;;;;;OAoBG;IACH,0BAUC;IAED;;;;OAIG;IACH,sCA2DC;IAED;;;;OAIG;IACH,oCAiFC;IAED;;;;OAIG;IACH,cAFa,MAAM,CAIlB;IAED;;;;;;;;OAQG;IACH,wBALW,MAAM,aACN,OAAO,GACL,MAAM,CAKlB;IAED;;;;;;;;OAQG;IACH,0BALW,MAAM,aACN,OAAO,GACL,MAAM,CAKlB;IAED;;;;;;;OAOG;IACH,gBAWC;CACF;AAq5ID;;;;;;;;;GASG;AACH;IACE;;OAEG;IACH,gCAA4B;IAC5B;;OAEG;IACH,sBAAkB;IAClB;;;OAGG;IACH,yBAAqB;IACrB;;OAEG;IACH,sCAAkC;IAClC;;OAEG;IACH,6BAA0B;IAE1B;;;;;;;;;;OAUG;IACH,kBAHW,MAAM,GACJ,MAAM,CAIlB;IAED;;;;;;;;;OASG;IACH,6BAJW,MAAM,aACN,OAAO,GACL,MAAM,CAIlB;IAED;;;;;;;;;;OAUG;IACH,6BAHW,MAAM,GACJ,MAAM,CAIlB;IAED;;;;;OAKG;IACH,sBAJW,MAAM,UACN,MAAM,GACJ,KAAK,CAwBjB;IAED;;;;;;;OAOG;IACH,sBALW,MAAM,SACN,MAAM,GAAC,MAAM,EAAE,GACb,OAAO,CAKnB;IAED;;;OAGG;IACH,wBAWC;IAED;;;;OAIG;IACH,qBAHW,MAAM,SACN,MAAM,EAOhB;IAHC,qBAA2B;IAE3B,mBAAuB;IAGzB;;;OAGG;IACH,cAEC;IAED;;;OAGG;IACH,SAFa,MAAM,CAIlB;IAED;;;OAGG;IACH,WAFa,MAAM,CAIlB;IACD,WAEC;IAED;;;;;OAKG;IACH,eAHW,MAAM,GAAC,MAAM,EAAE,GACb,OAAO,CAInB;IAED;;;;;OAKG;IACH,eAHW,MAAM,GAAC,MAAM,EAAE,GACb,OAAO,CAOnB;IAED;;;;;;;;OAQG;IACH,YAHW,MAAM,GAAC,MAAM,EAAE,GACb,OAAO,CAUnB;IAED;;;;;;;;OAQG;IACH,iBAHW,MAAM,GAAC,MAAM,EAAE,GACb,OAAO,CAKnB;IAED;;;;;;;;;;;;OAYG;IACH,aAJW,MAAM,UACN,MAAM,GACJ,MAAM,EAAE,CAgDpB;IAED;;;OAGG;IACH,YAFa,MAAM,CAIlB;IAED;;;;;;;;;OASG;IACH,eAFa,MAAM,CAIlB;IAED;;;;;OAKG;IACH,cAFa,MAAM,CAIlB;IAED;;;;OAIG;IACH,eAFa,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAIlC;IAED;;;;OAIG;IACH,cAHW,GAAC,GACC,OAAO,CAUnB;CACF;AA10KD;;GAEG;AACH;CAMC;AAxDD;IACE,8BAA8B;IAC9B,qBADY,MAAM,EAIjB;CACF;AA+DD;;GAEG;AACH;CAMC;AApBD;;GAEG;AACH;CAMC;AA3DD;;GAEG;AACH;IACE;;;OAGG;IACH,mBAHW,MAAM,UACN,MAAM,GAAC,IAAI,EAcrB;IAJC,qBAAqB;IACrB,OADW,MAAM,CACC;IAClB,0BAA0B;IAC1B,OADW,MAAM,GAAC,IAAI,CACJ;IAGpB;;;OAGG;IACH,kBAFa,MAAM,CAIlB;IAED;;;OAGG;IACH,cAFa,MAAM,GAAC,IAAI,CAIvB;CACF;AA3TD;IACE,0BAGC;IADC,WAAkB;IAEpB,mBAEC;IACD;;;OAGG;IACH,kBAFa,MAAM,CAIlB;IAED;;;OAGG;IACH,WAFa,MAAM,EAAE,CAIpB;IAED;;;OAGG;IACH,UAFa,MAAM,CAIlB;CACF;AACD;IACE,iCAGC;IADC,kBAAgC;IAElC,mBAEC;IAED;;;OAGG;IACH,kBAFa,MAAM,CAIlB;IAED;;;OAGG;IACH,WAFa,MAAM,EAAE,CAIpB;IAED;;;OAGG;IACH,UAFa,MAAM,CAIlB;CACF;AAzFD;;GAEG;AACH;IACE,8BAAkD;IAClD,oBAEC;IAED;;;OAGG;IACH,kBAFa,OAAO,CAInB;IAED;;;OAGG;IACH,mBAFa,OAAO,CAInB;CACF"}

package/build/index.esm.js

@@ -2,7 +2,7 @@
  * re2js
  * RE2JS is the JavaScript port of RE2, a regular expression engine that provides linear time matching
  *
- * @version v2.0.0
+ * @version v2.0.1
  * @author Alexey Vasiliev
  * @homepage https://github.com/le0pard/re2js#readme
  * @repository github:le0pard/re2js
@@ -359,6 +359,11 @@ class Unicode {
   // Checked during test.
   static MIN_FOLD = 0x0041;
   static MAX_FOLD = 0x1e943;
+  static MIN_HIGH_SURROGATE = 0xd800;
+  static MAX_HIGH_SURROGATE = 0xdbff;
+  static MIN_LOW_SURROGATE = 0xdc00;
+  static MAX_LOW_SURROGATE = 0xdfff;
+  static MIN_SUPPLEMENTARY_CODE_POINT = 0x10000;
 
   // is32 uses binary search to test whether rune is in the specified
   // slice of 32-bit ranges.
@@ -665,9 +670,9 @@ class Utils {
         } else if (c < 2048) {
           out[p++] = c >> 6 | 192;
           out[p++] = c & 63 | 128;
-        } else if ((c & 0xfc00) === 0xd800 && i + 1 < str.length && (str.charCodeAt(i + 1) & 0xfc00) === 0xdc00) {
+        } else if ((c & 0xfc00) === Unicode.MIN_HIGH_SURROGATE && i + 1 < str.length && (str.charCodeAt(i + 1) & 0xfc00) === Unicode.MIN_LOW_SURROGATE) {
           // Surrogate Pair
-          c = 0x10000 + ((c & 0x03ff) << 10) + (str.charCodeAt(++i) & 0x03ff);
+          c = Unicode.MIN_SUPPLEMENTARY_CODE_POINT + ((c & 0x03ff) << 10) + (str.charCodeAt(++i) & 0x03ff);
           out[p++] = c >> 18 | 240;
           out[p++] = c >> 12 & 63 | 128;
           out[p++] = c >> 6 & 63 | 128;
@@ -701,9 +706,9 @@ class Utils {
           let c2 = bytes[pos++];
           let c3 = bytes[pos++];
           let c4 = bytes[pos++];
-          let u = ((c1 & 7) << 18 | (c2 & 63) << 12 | (c3 & 63) << 6 | c4 & 63) - 0x10000;
-          out[c++] = String.fromCharCode(0xd800 + (u >> 10));
-          out[c++] = String.fromCharCode(0xdc00 + (u & 1023));
+          let u = ((c1 & 7) << 18 | (c2 & 63) << 12 | (c3 & 63) << 6 | c4 & 63) - Unicode.MIN_SUPPLEMENTARY_CODE_POINT;
+          out[c++] = String.fromCharCode(Unicode.MIN_HIGH_SURROGATE + (u >> 10));
+          out[c++] = String.fromCharCode(Unicode.MIN_LOW_SURROGATE + (u & 1023));
         } else {
           let c2 = bytes[pos++];
           let c3 = bytes[pos++];
@@ -877,38 +882,34 @@ class MachineUTF8Input extends MachineInputBase {
   // the lower 3 bits, and the rune (Unicode code point) in the high
   // bits.  Never negative, except for EOF which is represented as -1
   // << 3 | 0.
-  step(i) {
-    i += this.start;
-    if (i >= this.end) {
+  step(pos) {
+    pos += this.start;
+    if (pos >= this.end) {
       return MachineInputBase.EOF();
     }
-    let x = this.bytes[i++] & 255;
-    if ((x & 128) === 0) {
-      return x << 3 | 1;
-    } else if ((x & 224) === 192) {
-      x = x & 31;
-      if (i >= this.end) {
-        return MachineInputBase.EOF();
-      }
-      x = x << 6 | this.bytes[i++] & 63;
-      return x << 3 | 2;
-    } else if ((x & 240) === 224) {
-      x = x & 15;
-      if (i + 1 >= this.end) {
-        return MachineInputBase.EOF();
-      }
-      x = x << 6 | this.bytes[i++] & 63;
-      x = x << 6 | this.bytes[i++] & 63;
-      return x << 3 | 3;
+
+    // Read UTF-8 bytes to extract the Rune and its width
+    const c = this.bytes[pos] & 0xff;
+    if (c < 0x80) {
+      return c << 3 | 1;
+    } else if (c >= 0xc2 && c <= 0xdf && pos + 1 < this.end) {
+      const c1 = this.bytes[pos + 1] & 0xff;
+      const rune = (c & 0x1f) << 6 | c1 & 0x3f;
+      return rune << 3 | 2;
+    } else if (c >= 0xe0 && c <= 0xef && pos + 2 < this.end) {
+      const c1 = this.bytes[pos + 1] & 0xff;
+      const c2 = this.bytes[pos + 2] & 0xff;
+      const rune = (c & 0x0f) << 12 | (c1 & 0x3f) << 6 | c2 & 0x3f;
+      return rune << 3 | 3;
+    } else if (c >= 0xf0 && c <= 0xf4 && pos + 3 < this.end) {
+      const c1 = this.bytes[pos + 1] & 0xff;
+      const c2 = this.bytes[pos + 2] & 0xff;
+      const c3 = this.bytes[pos + 3] & 0xff;
+      const rune = (c & 0x07) << 18 | (c1 & 0x3f) << 12 | (c2 & 0x3f) << 6 | c3 & 0x3f;
+      return rune << 3 | 4;
     } else {
-      x = x & 7;
-      if (i + 2 >= this.end) {
-        return MachineInputBase.EOF();
-      }
-      x = x << 6 | this.bytes[i++] & 63;
-      x = x << 6 | this.bytes[i++] & 63;
-      x = x << 6 | this.bytes[i++] & 63;
-      return x << 3 | 4;
+      // Invalid sequence fallback
+      return c << 3 | 1;
     }
   }
 
@@ -983,12 +984,25 @@ class MachineUTF16Input extends MachineInputBase {
   // << 3 | 0.
   step(pos) {
     pos += this.start;
-    if (pos < this.end) {
-      const rune = this.charSequence.codePointAt(pos);
-      return rune << 3 | Utils.charCount(rune);
-    } else {
+    if (pos >= this.end) {
       return MachineInputBase.EOF();
     }
+    const c1 = this.charSequence.charCodeAt(pos);
+
+    // Fast path: standard BMP character (not a high surrogate)
+    if (c1 < Unicode.MIN_HIGH_SURROGATE || c1 > Unicode.MAX_HIGH_SURROGATE || pos + 1 >= this.end) {
+      return c1 << 3 | 1;
+    }
+
+    // Slow path: Calculate surrogate pair manually
+    const c2 = this.charSequence.charCodeAt(pos + 1);
+    if (c2 >= Unicode.MIN_LOW_SURROGATE && c2 <= Unicode.MAX_LOW_SURROGATE) {
+      const rune = (c1 - Unicode.MIN_HIGH_SURROGATE) * 0x400 + (c2 - Unicode.MIN_LOW_SURROGATE) + Unicode.MIN_SUPPLEMENTARY_CODE_POINT;
+      return rune << 3 | 2;
+    }
+
+    // Invalid surrogate pair fallback
+    return c1 << 3 | 1;
   }
 
   // Returns the index relative to |pos| at which |re2.prefix| is found
@@ -1736,7 +1750,7 @@ class Inst {
     let lo = 0;
     let hi = this.runes.length / 2 | 0;
     while (lo < hi) {
-      const m = lo + ((hi - lo) / 2 | 0);
+      const m = lo + hi >> 1; // native cpu instruction for "lo + (((hi - lo) / 2) | 0)"
       const c = this.runes[2 * m];
       if (c <= r) {
         if (r <= this.runes[2 * m + 1]) {
@@ -1797,10 +1811,10 @@ class Thread {
 // A queue is a 'sparse array' holding pending threads of execution.  See:
 // research.swtch.com/2008/03/using-uninitialized-memory-for-fun-and.html
 class Queue {
-  constructor() {
-    this.sparse = []; // may contain stale but in-bounds values.
-    this.densePcs = []; // may contain stale pc in slots >= size
-    this.denseThreads = []; // may contain stale Thread in slots >= size
+  constructor(numInst) {
+    this.sparse = new Int32Array(numInst); // may contain stale but in-bounds values.
+    this.densePcs = new Int32Array(numInst); // may contain stale pc in slots >= size
+    this.denseThreads = new Array(numInst); // may contain stale Thread in slots >= size
     this.size = 0;
   }
   contains(pc) {
@@ -2301,7 +2315,7 @@ class DFA {
       if (width === 0) {
         break;
       }
-      currentState = this.step(currentState, rune, anchor);
+      currentState = anchor === RE2Flags.UNANCHORED && rune <= Unicode.MAX_ASCII && currentState.nextAscii[rune] || this.step(currentState, rune, anchor);
 
       // If we hit an unrecoverable DFA error or bailout, signal fallback
       if (currentState === null) return null;