Handle non ASCII characters in PDF name objects (#429)

Hopding · Apr 29, 2020 · 0bc4f7b · 0bc4f7b
1 parent f7f9304
commit 0bc4f7b
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 8 deletions.
diff --git a/src/core/parser/PDFObjectParser.ts b/src/core/parser/PDFObjectParser.ts
@@ -140,14 +140,7 @@ class PDFObjectParser extends BaseParser {
     let name = '';
     while (!this.bytes.done()) {
       const byte = this.bytes.peek();
-      if (
-        byte < CharCodes.ExclamationPoint ||
-        byte > CharCodes.Tilde ||
-        IsWhitespace[byte] ||
-        IsDelimiter[byte]
-      ) {
-        break;
-      }
+      if (IsWhitespace[byte] || IsDelimiter[byte]) break;
       name += charFromCode(byte);
       this.bytes.next();
     }

diff --git a/tests/core/parser/PDFObjectParser.spec.ts b/tests/core/parser/PDFObjectParser.spec.ts
@@ -306,6 +306,10 @@ describe(`PDFObjectParser`, () => {
       expect(parser.parseObject()).toBe(PDFName.of('Bing'));
       expect(parser.parseObject()).toBe(PDFName.of('Bang'));
     });
+
+    it(`handles names containing non-ASCII characters`, () => {
+      expectParse('/ABCDEE+»ªÎÄÖÐËÎ').toBe(PDFName.of('ABCDEE+»ªÎÄÖÐËÎ'));
+    });
   });
 
   describe(`when parsing arrays`, () => {