Allow extra whitespace/newlines after stream tokens (Issue #40)

michaelrsweet · Oct 2, 2023 · a83f7f5 · a83f7f5
1 parent 6a4ce57
commit a83f7f5
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 2 deletions.
diff --git a/CHANGES.md b/CHANGES.md
@@ -2,6 +2,13 @@ Changes in PDFio
 ================
 
 
+v1.1.2 (TBD)
+------------
+
+- Fixed an issue with broken PDF files containing extra CR and/or LF separators
+  after the object stream token (Issue #40)
+
+
 v1.1.1 (March 20, 2023)
 -----------------------
 

diff --git a/Makefile b/Makefile
@@ -29,7 +29,7 @@ DSONAME		=
 LDFLAGS		=
 LIBS		=	-lm -lz
 RANLIB		=	ranlib
-VERSION		=	1.1.1
+VERSION		=	1.1.2
 prefix		=	/usr/local
 
 

diff --git a/pdfio-object.c b/pdfio-object.c
@@ -420,6 +420,9 @@ _pdfioObjLoad(pdfio_obj_t *obj)		// I - Object
   }
 
   ptr += 3;
+  while (*ptr && isspace(*ptr & 255))
+    ptr ++;
+
   _pdfioFileConsume(obj->pdf, (size_t)(ptr - line));
 
   // Then grab the object value...
@@ -438,11 +441,14 @@ _pdfioObjLoad(pdfio_obj_t *obj)		// I - Object
     return (false);
   }
 
+  if (tb.bufptr && tb.bufptr < tb.bufend && (*(tb.bufptr) == 0x0d || *(tb.bufptr) == 0x0a))
+    tb.bufptr ++;			// Skip trailing CR or LF after token
+
   _pdfioTokenFlush(&tb);
 
   if (!strcmp(line, "stream"))
   {
-    // Yes, save its location...
+    // Yes, this is an embedded stream so save its location...
     obj->stream_offset = _pdfioFileTell(obj->pdf);
     PDFIO_DEBUG("_pdfioObjLoad: stream_offset=%lu.\n", (unsigned long)obj->stream_offset);
   }