perf: improve performance of text handling

lddubeau · Sep 12, 2019 · 9c13099 · 9c13099
1 parent b19edfa
commit 9c13099
Showing 1 changed file with 21 additions and 20 deletions.
diff --git a/lib/saxes.js b/lib/saxes.js
@@ -948,22 +948,28 @@ class SaxesParser {
     //
     const { chunk, limit, i: start } = this;
     let { forbiddenState } = this;
-    let c;
     // eslint-disable-next-line no-labels, no-restricted-syntax
     scanLoop:
-    while (this.i < limit) {
+    // eslint-disable-next-line no-constant-condition
+    while (true) {
+      if (this.i >= limit) {
+        this.text += chunk.substring(start);
+        break;
+      }
       const code = this.getCode();
       switch (code) {
       case LESS:
         this.state = S_OPEN_WAKA;
-        c = code;
+        // This is faster than adding codepoints one by one.
+        this.text += chunk.substring(start, this.i - 1);
         forbiddenState = FORBIDDEN_START;
         // eslint-disable-next-line no-labels
         break scanLoop;
       case AMP:
         this.state = S_ENTITY;
         this.entityReturnState = S_TEXT;
-        c = code;
+        // This is faster than adding codepoints one by one.
+        this.text += chunk.substring(start, this.i - 1);
         forbiddenState = FORBIDDEN_START;
         // eslint-disable-next-line no-labels
         break scanLoop;
@@ -992,11 +998,6 @@ class SaxesParser {
       }
     }
     this.forbiddenState = forbiddenState;
-
-    // This is faster than adding codepoints one by one.
-    this.text += chunk.substring(start,
-                                 c === undefined ? undefined :
-                                 (this.i - (c <= 0xFFFF ? 1 : 2)));
   }
 
   /** @private */
@@ -1012,21 +1013,27 @@ class SaxesParser {
     //
     const { chunk, limit, i: start } = this;
     let nonSpace = false;
-    let c;
     // eslint-disable-next-line no-labels, no-restricted-syntax
     outRootLoop:
-    while (this.i < limit) {
+    // eslint-disable-next-line no-constant-condition
+    while (true) {
+      if (this.i >= limit) {
+        this.text += chunk.substring(start);
+        break;
+      }
       const code = this.getCode();
       switch (code) {
       case LESS:
         this.state = S_OPEN_WAKA;
-        c = code;
+        // This is faster than adding codepoints one by one.
+        this.text += chunk.substring(start, this.i - 1);
         // eslint-disable-next-line no-labels
         break outRootLoop;
       case AMP:
         this.state = S_ENTITY;
         this.entityReturnState = S_TEXT;
-        c = code;
+        // This is faster than adding codepoints one by one.
+        this.text += chunk.substring(start, this.i - 1);
         nonSpace = true;
         // eslint-disable-next-line no-labels
         break outRootLoop;
@@ -1037,11 +1044,6 @@ class SaxesParser {
       }
     }
 
-    // This is faster than adding codepoints one by one.
-    this.text += chunk.substring(start,
-                                 c === undefined ? undefined :
-                                 (this.i - (c <= 0xFFFF ? 1 : 2)));
-
     if (!nonSpace) {
       return;
     }
@@ -1786,8 +1788,7 @@ class SaxesParser {
       const code = this.getCode();
       if (code === q || code === AMP || code === LESS) {
         // This is faster than adding codepoints one by one.
-        const slice = chunk.substring(start,
-                                      this.i - (code <= 0xFFFF ? 1 : 2));
+        const slice = chunk.substring(start, this.i - 1);
         switch (code) {
         case q:
           this.pushAttrib(this.name, this.text + slice);