perf: improve text node checking speed

We used to carve a fragment out of the node and check that, but it was clostly to do. We now keep track of an index instead.
lddubeau · Aug 15, 2018 · f270e8b · f270e8b
1 parent 7cfa4e2
commit f270e8b
Showing 1 changed file with 19 additions and 23 deletions.
diff --git a/lib/saxes.js b/lib/saxes.js
@@ -83,9 +83,9 @@ exports.EVENTS = [
 ];
 
 const buffers = [
-  "comment", "openWakaBang", "textNode", "textFragments", "tagName", "doctype",
-  "piTarget", "piBody", "entity", "attribName", "attribValue", "cdata",
-  "xmlDeclName", "xmlDeclValue",
+  "comment", "openWakaBang", "textNode", "tagName", "doctype", "piTarget",
+  "piBody", "entity", "attribName", "attribValue", "cdata", "xmlDeclName",
+  "xmlDeclValue",
 ];
 
 const NL = 0xA;
@@ -267,6 +267,10 @@ class SaxesParser {
     this.requiredSeparator = undefined;
     this.entityBufferName = undefined;
     this.entityReturnState = undefined;
+    // This records the index before which we don't have to check for the
+    // presence of ]]]>. The text before that index has been checked already,
+    // and should not be checked twice.
+    this.textNodeCheckedBefore = 0;
 
     // namespaces form a prototype chain.
     // it always points at the current tag,
@@ -626,27 +630,19 @@ class SaxesParser {
         this.reportedTextBeforeRoot = true;
       }
       this.textNode = String.fromCodePoint(c);
+      this.textNodeCheckedBefore = 0;
       this.state = S_TEXT;
       this.xmlDeclPossible = false;
     }
   }
 
   /** @private */
   sText(chunkState) {
-    const start = this.textNode.length;
     const c = this.captureWhile(chunkState,
                                 cx => cx !== LESS && cx !== AMP,
                                 "textNode");
 
-    const fragment = this.textNode.slice(start);
-
-    // textFragments is a buffer we use to check for the precence of a
-    // literal "]]>" in text nodes. We cannot do the check against textNode
-    // itself because textNode will contain resolved entities so "]]&gt;"
-    // would turn to "]]>" in textNode and raise a false error.
-    this.textFragments += fragment;
-
-    if (!this.inRoot && /\S/.test(fragment)) {
+    if (!this.inRoot && /\S/.test(this.textNode)) {
       // We use the reportedTextBeforeRoot and reportedTextAfterRoot flags
       // to avoid reporting errors for every single character that is out of
       // place.
@@ -661,20 +657,19 @@ class SaxesParser {
       }
     }
 
-    // We also have to check the end of textFragments because some cases may
-    // slip through otherwise. For instance, if client code writes
-    // char-by-char. Then fragment will never contain ]]> but instead we'll have
-    // 3 fragments one with "]", a second with "]" and a third with ">".
-    if (this.textFragments.includes("]]>")) {
-      this.textFragments = "";
+    if (this.textNode.includes("]]>", this.textNodeCheckedBefore)) {
       this.fail("the string \"]]>\" is disallowed in char data.");
     }
 
+    // We have to go back two spaces so that we can catch the case where on a
+    // previous write call, the textNode buffer ended on ``]]`` and we started
+    // with ``>`` this time around.
+    this.textNodeCheckedBefore = this.textNode.length - 2;
+
     switch (c) {
     case LESS:
       this.state = S_OPEN_WAKA;
       this.startTagPosition = this.position;
-      this.textFragments = "";
       break;
     case AMP:
       // We use the reportedTextBeforeRoot and reportedTextAfterRoot flags to
@@ -692,9 +687,6 @@ class SaxesParser {
       this.state = S_ENTITY;
       this.entityBufferName = "textNode";
       this.entityReturnState = S_TEXT;
-      // If we run into an entity, then necessarily we do not have a "]]>"
-      // literal. So we flush this.textFragments.
-      this.textFragments = "";
       break;
     default:
     }
@@ -1472,6 +1464,9 @@ class SaxesParser {
     }
     else if (c === SEMICOLON) {
       this[this.entityBufferName] += this.parseEntity();
+      if (this.entityBufferName === "textNode") {
+        this.textNodeCheckedBefore = this.textNode.length;
+      }
       this.entity = "";
       this.state = this.entityReturnState;
     }
@@ -1522,6 +1517,7 @@ class SaxesParser {
       this.ontext(this.textNode);
     }
     this.textNode = "";
+    this.textNodeCheckedBefore = 0;
   }
 
   /**