fix(tokenizer): Fix onattribend's endIndex (#1540)

fb55 · Jul 16, 2023 · 685ccb6 · 685ccb6
1 parent 1b25141
commit 685ccb6
Show file tree

Hide file tree

Showing 5 changed files with 197 additions and 58 deletions.
diff --git a/src/Tokenizer.spec.ts b/src/Tokenizer.spec.ts
@@ -47,6 +47,21 @@ describe("Tokenizer", () => {
         });
     });
 
+    describe("should correctly mark attributes", () => {
+        it("for no value attribute", () => {
+            expect(tokenize("<div aaaaaaa >")).toMatchSnapshot();
+        });
+        it("for no quotes attribute", () => {
+            expect(tokenize("<div aaa=aaa >")).toMatchSnapshot();
+        });
+        it("for single quotes attribute", () => {
+            expect(tokenize("<div aaa='a' >")).toMatchSnapshot();
+        });
+        it("for double quotes attribute", () => {
+            expect(tokenize('<div aaa="a" >')).toMatchSnapshot();
+        });
+    });
+
     describe("should not break after special tag followed by an entity", () => {
         it("for normal special tag", () => {
             expect(tokenize("<style>a{}</style>&apos;<br/>")).toMatchSnapshot();

diff --git a/src/Tokenizer.ts b/src/Tokenizer.ts
@@ -464,7 +464,7 @@ export default class Tokenizer {
     private stateInAttributeName(c: number): void {
         if (c === CharCodes.Eq || isEndOfTagSection(c)) {
             this.cbs.onattribname(this.sectionStart, this.index);
-            this.sectionStart = -1;
+            this.sectionStart = this.index;
             this.state = State.AfterAttributeName;
             this.stateAfterAttributeName(c);
         }
@@ -473,11 +473,12 @@ export default class Tokenizer {
         if (c === CharCodes.Eq) {
             this.state = State.BeforeAttributeValue;
         } else if (c === CharCodes.Slash || c === CharCodes.Gt) {
-            this.cbs.onattribend(QuoteType.NoValue, this.index);
+            this.cbs.onattribend(QuoteType.NoValue, this.sectionStart);
+            this.sectionStart = -1;
             this.state = State.BeforeAttributeName;
             this.stateBeforeAttributeName(c);
         } else if (!isWhitespace(c)) {
-            this.cbs.onattribend(QuoteType.NoValue, this.index);
+            this.cbs.onattribend(QuoteType.NoValue, this.sectionStart);
             this.state = State.InAttributeName;
             this.sectionStart = this.index;
         }
@@ -506,7 +507,7 @@ export default class Tokenizer {
                 quote === CharCodes.DoubleQuote
                     ? QuoteType.Double
                     : QuoteType.Single,
-                this.index,
+                this.index + 1,
             );
             this.state = State.BeforeAttributeName;
         } else if (this.decodeEntities && c === CharCodes.Amp) {

diff --git a/src/__snapshots__/Tokenizer.spec.ts.snap b/src/__snapshots__/Tokenizer.spec.ts.snap
@@ -1,5 +1,128 @@
 // Jest Snapshot v1, https://goo.gl/fbAQLP
 
+exports[`Tokenizer should correctly mark attributes for double quotes attribute 1`] = `
+[
+  [
+    "onopentagname",
+    1,
+    4,
+  ],
+  [
+    "onattribname",
+    5,
+    8,
+  ],
+  [
+    "onattribdata",
+    10,
+    11,
+  ],
+  [
+    "onattribend",
+    3,
+    12,
+  ],
+  [
+    "onopentagend",
+    13,
+  ],
+  [
+    "onend",
+  ],
+]
+`;
+
+exports[`Tokenizer should correctly mark attributes for no quotes attribute 1`] = `
+[
+  [
+    "onopentagname",
+    1,
+    4,
+  ],
+  [
+    "onattribname",
+    5,
+    8,
+  ],
+  [
+    "onattribdata",
+    9,
+    12,
+  ],
+  [
+    "onattribend",
+    1,
+    12,
+  ],
+  [
+    "onopentagend",
+    13,
+  ],
+  [
+    "onend",
+  ],
+]
+`;
+
+exports[`Tokenizer should correctly mark attributes for no value attribute 1`] = `
+[
+  [
+    "onopentagname",
+    1,
+    4,
+  ],
+  [
+    "onattribname",
+    5,
+    12,
+  ],
+  [
+    "onattribend",
+    0,
+    12,
+  ],
+  [
+    "onopentagend",
+    13,
+  ],
+  [
+    "onend",
+  ],
+]
+`;
+
+exports[`Tokenizer should correctly mark attributes for single quotes attribute 1`] = `
+[
+  [
+    "onopentagname",
+    1,
+    4,
+  ],
+  [
+    "onattribname",
+    5,
+    8,
+  ],
+  [
+    "onattribdata",
+    10,
+    11,
+  ],
+  [
+    "onattribend",
+    2,
+    12,
+  ],
+  [
+    "onopentagend",
+    13,
+  ],
+  [
+    "onend",
+  ],
+]
+`;
+
 exports[`Tokenizer should handle entities for XML entities 1`] = `
 [
   [
@@ -82,7 +205,7 @@ exports[`Tokenizer should handle entities for entities in attributes (#276) 1`]
   [
     "onattribend",
     3,
-    41,
+    42,
   ],
   [
     "onselfclosingtag",