feat: #127 skip ellipsis in arrays and objects

josdejong · May 15, 2024 · 019e509 · 019e509
1 parent e778b5e
commit 019e509
Show file tree

Hide file tree

Showing 4 changed files with 74 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -21,6 +21,7 @@ The following issues can be fixed:
 - Replace Python constants `None`, `True`, and `False` with `null`, `true`, and `false`
 - Strip trailing commas
 - Strip comments like `/* ... */` and `// ...`
+- Strip ellipsis in arrays and objects like `[1, 2, 3, ...]`
 - Strip JSONP notation like `callback({ ... })`
 - Strip escape characters from an escaped string like `{\"stringified\": \"content\"}`
 - Strip MongoDB data types like `NumberLong(2)` and `ISODate("2012-12-19T06:01:17.171Z")`

diff --git a/src/index.test.ts b/src/index.test.ts
@@ -151,6 +151,27 @@ describe.each(implementations)('jsonrepair [$name]', ({ jsonrepair }) => {
       expect(jsonrepair('{"message": "with, multiple, commma\'s, you see?')).toBe('{"message": "with, multiple, commma\'s, you see?"}')
     })
 
+    test('should repair ellipsis in an array', () => {
+      expect(jsonrepair('[1,2,3,...]')).toBe('[1,2,3]')
+      expect(jsonrepair('[1, 2, 3, ... ]')).toBe('[1, 2, 3  ]')
+      expect(jsonrepair('[1,2,3,/*comment1*/.../*comment2*/]')).toBe('[1,2,3]')
+      expect(jsonrepair('[\n  1,\n  2,\n  3,\n  /*comment1*/  .../*comment2*/\n]')).toBe('[\n  1,\n  2,\n  3\n    \n]')
+      expect(jsonrepair('{"array":[1,2,3,...]}')).toBe('{"array":[1,2,3]}')
+      expect(jsonrepair('[1,2,3,...,9]')).toBe('[1,2,3,9]')
+      expect(jsonrepair('[...,7,8,9]')).toBe('[7,8,9]')
+      expect(jsonrepair('[..., 7,8,9]')).toBe('[ 7,8,9]')
+    })
+
+    test('should repair ellipsis in an object', () => {
+      expect(jsonrepair('{"a":2,"b":3,...}')).toBe('{"a":2,"b":3}')
+      expect(jsonrepair('{"a":2,"b":3,/*comment1*/.../*comment2*/}')).toBe('{"a":2,"b":3}')
+      expect(jsonrepair('{\n  "a":2,\n  "b":3,\n  /*comment1*/.../*comment2*/\n}')).toBe('{\n  "a":2,\n  "b":3\n  \n}')
+      expect(jsonrepair('{"a":2,"b":3, ... }')).toBe('{"a":2,"b":3  }')
+      expect(jsonrepair('{"nested":{"a":2,"b":3, ... }}')).toBe('{"nested":{"a":2,"b":3  }}')
+      expect(jsonrepair('{"a":2,"b":3,...,"z":26}')).toBe('{"a":2,"b":3,"z":26}')
+      expect(jsonrepair('{"a":2,"b":3,...}')).toBe('{"a":2,"b":3}')
+    })
+
     test('should add missing start quote', () => {
       expect(jsonrepair('abc"')).toBe('"abc"')
       expect(jsonrepair('[a","b"]')).toBe('["a","b"]')

diff --git a/src/regular/jsonrepair.ts b/src/regular/jsonrepair.ts
@@ -216,6 +216,29 @@ export function jsonrepair(text: string): string {
     return skipCharacter(codeBackslash)
   }
 
+  /**
+   * Skip ellipsis like "[1,2,3,...]" or "[1,2,3,...,9]" or "[...,7,8,9]"
+   * or a similar construct in objects.
+   */
+  function skipEllipsis(): boolean {
+    parseWhitespaceAndSkipComments()
+
+    if (
+      text.charCodeAt(i) === codeDot &&
+      text.charCodeAt(i + 1) === codeDot &&
+      text.charCodeAt(i + 2) === codeDot
+    ) {
+      // repair: remove the ellipsis (three dots) and optionally a comma
+      i += 3
+      parseWhitespaceAndSkipComments()
+      skipCharacter(codeComma)
+
+      return true
+    }
+
+    return false
+  }
+
   /**
    * Parse an object like '{"key": "value"}'
    */
@@ -240,6 +263,8 @@ export function jsonrepair(text: string): string {
           initial = false
         }
 
+        skipEllipsis()
+
         const processedKey = parseString() || parseUnquotedString()
         if (!processedKey) {
           if (
@@ -314,6 +339,8 @@ export function jsonrepair(text: string): string {
           initial = false
         }
 
+        skipEllipsis()
+
         const processedValue = parseValue()
         if (!processedValue) {
           // repair trailing comma

diff --git a/src/streaming/core.ts b/src/streaming/core.ts
@@ -123,6 +123,7 @@ export function jsonrepairCore({
         switch (stack.caret) {
           case Caret.beforeKey:
             return (
+              skipEllipsis() ||
               parseObjectKey() ||
               parseUnexpectedColon() ||
               parseRepairTrailingComma() ||
@@ -140,7 +141,7 @@ export function jsonrepairCore({
       case StackType.array: {
         switch (stack.caret) {
           case Caret.beforeValue:
-            return parseValue() || parseRepairTrailingComma() || parseRepairArrayEnd()
+            return skipEllipsis() || parseValue() || parseRepairTrailingComma() || parseRepairArrayEnd()
           case Caret.afterValue:
             return (
               parseArrayComma() ||
@@ -524,6 +525,29 @@ export function jsonrepairCore({
     return skipCharacter(codeBackslash)
   }
 
+  /**
+   * Skip ellipsis like "[1,2,3,...]" or "[1,2,3,...,9]" or "[...,7,8,9]"
+   * or a similar construct in objects.
+   */
+  function skipEllipsis(): boolean {
+    parseWhitespaceAndSkipComments()
+
+    if (
+      input.charCodeAt(i) === codeDot &&
+      input.charCodeAt(i + 1) === codeDot &&
+      input.charCodeAt(i + 2) === codeDot
+    ) {
+      // repair: remove the ellipsis (three dots) and optionally a comma
+      i += 3
+      parseWhitespaceAndSkipComments()
+      skipCharacter(codeComma)
+
+      return true
+    }
+
+    return false
+  }
+
   /**
    * Parse a string enclosed by double quotes "...". Can contain escaped quotes
    * Repair strings enclosed in single quotes or special quotes