From 7f6ffcda2234960c75ce76d1c1cfc4a7738cbb95 Mon Sep 17 00:00:00 2001
From: Michael R Sweet <msweet@msweet.org>
Date: Fri, 6 Oct 2023 10:46:30 -0400
Subject: [PATCH] Fix a couple issues with parsing PDF files produced by
 Microsoft Reporting Services (Issue #46)

- Odd cross-reference stream containing 3-byte generation number field for this
  16-bit value
- Odd empty hex strings
---
 CHANGES.md    |  2 ++
 pdfio-file.c  | 19 +++++++++++++++++--
 pdfio-token.c |  7 +++++++
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/CHANGES.md b/CHANGES.md
index 32713bf..6a1f4ef 100644
--- a/CHANGES.md
+++ b/CHANGES.md
@@ -7,6 +7,8 @@ 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)
+- Fixed an issue with PDF files produced by Microsoft Reporting Services
+  (Issue #46)
 
 
 v1.1.1 (March 20, 2023)
diff --git a/pdfio-file.c b/pdfio-file.c
index a95378c..e045230 100644
--- a/pdfio-file.c
+++ b/pdfio-file.c
@@ -1759,9 +1759,9 @@ load_xref(
       w_2     = w[0];
       w_3     = w[0] + w[1];
 
-      if (w[1] == 0 || w[2] > 2 || w[0] > sizeof(buffer) || w[1] > sizeof(buffer) || w[2] > sizeof(buffer) || w_total > sizeof(buffer))
+      if (w[1] == 0 || w[2] > 4 || w[0] > sizeof(buffer) || w[1] > sizeof(buffer) || w[2] > sizeof(buffer) || w_total > sizeof(buffer))
       {
-	_pdfioFileError(pdf, "Cross-reference stream has invalid W key.");
+	_pdfioFileError(pdf, "Cross-reference stream has invalid W key [%u %u %u].", (unsigned)w[0], (unsigned)w[1], (unsigned)w[2]);
 	return (false);
       }
 
@@ -1801,9 +1801,11 @@ load_xref(
 	    }
 	  }
 
+          // Offset
 	  for (i = 1, offset = buffer[w_2]; i < w[1]; i ++)
 	    offset = (offset << 8) | buffer[w_2 + i];
 
+          // Generation number
 	  switch (w[2])
 	  {
 	    default :
@@ -1815,6 +1817,19 @@ load_xref(
 	    case 2 :
 		generation = (buffer[w_3] << 8) | buffer[w_3 + 1];
 		break;
+	    case 3 :
+	        // Issue #46: Stupid Microsoft PDF generator using 3 bytes to
+	        // encode 16-bit generation numbers == 0 (probably a lazy coder
+	        // stuffing things into an array of 64-bit unsigned integers)
+		generation = (buffer[w_3] << 16) | (buffer[w_3 + 1] << 8) | buffer[w_3 + 2];
+		if (generation > 65535)
+		  generation = 65535;
+		break;
+	    case 4 : // Even stupider :)
+		generation = (buffer[w_3] << 24) | (buffer[w_3 + 1] << 16) | (buffer[w_3 + 2] << 8) | buffer[w_3 + 3];
+		if (generation > 65535)
+		  generation = 65535;
+		break;
 	  }
 
 	  // Create a placeholder for the object in memory...
diff --git a/pdfio-token.c b/pdfio-token.c
index 559a7ff..437bd9c 100644
--- a/pdfio-token.c
+++ b/pdfio-token.c
@@ -495,6 +495,13 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  *bufptr++ = (char)ch;
 	  break;
 	}
+	else if (ch == '>')
+	{
+	  // Issue #46: Empty hex string from Microsoft PDF generator; treat as
+	  // empty literal string...
+	  *buffer = '(';
+	  break;
+	}
 	else if (!isspace(ch & 255) && !isxdigit(ch & 255))
 	{
 	  _pdfioFileError(tb->pdf, "Syntax error: '<%c'", ch);