PDFio 1.5.4.

CHANGES.md

@@ -2,6 +2,15 @@ Changes in PDFio
 ================
 
 
+v1.5.4 - 2025-08-26
+-------------------
+
+- Updated indirect reference reading code to limit the range of generation
+  numbers.
+- Updated error messages for too large tokens (Issue #131)
+- Fixed a JPEG copy bug (Issue #132)
+
+
 v1.5.3 - 2025-05-03
 -------------------
 

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for pdfio 1.5.3.
+# Generated by GNU Autoconf 2.71 for pdfio 1.5.4.
 #
 # Report bugs to <https://github.com/michaelrsweet/pdfio/issues>.
 #
@@ -610,8 +610,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='pdfio'
 PACKAGE_TARNAME='pdfio'
-PACKAGE_VERSION='1.5.3'
-PACKAGE_STRING='pdfio 1.5.3'
+PACKAGE_VERSION='1.5.4'
+PACKAGE_STRING='pdfio 1.5.4'
 PACKAGE_BUGREPORT='https://github.com/michaelrsweet/pdfio/issues'
 PACKAGE_URL='https://www.msweet.org/pdfio'
 
@@ -1295,7 +1295,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures pdfio 1.5.3 to adapt to many kinds of systems.
+\`configure' configures pdfio 1.5.4 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1361,7 +1361,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of pdfio 1.5.3:";;
+     short | recursive ) echo "Configuration of pdfio 1.5.4:";;
    esac
   cat <<\_ACEOF
 
@@ -1460,7 +1460,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-pdfio configure 1.5.3
+pdfio configure 1.5.4
 generated by GNU Autoconf 2.71
 
 Copyright (C) 2021 Free Software Foundation, Inc.
@@ -1678,7 +1678,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by pdfio $as_me 1.5.3, which was
+It was created by pdfio $as_me 1.5.4, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -2434,9 +2434,9 @@ ac_compiler_gnu=$ac_cv_c_compiler_gnu
 
 
 
-PDFIO_VERSION="1.5.3"
-PDFIO_VERSION_MAJOR="`echo 1.5.3 | awk -F. '{print $1}'`"
-PDFIO_VERSION_MINOR="`echo 1.5.3 | awk -F. '{printf("%d\n",$2);}'`"
+PDFIO_VERSION="1.5.4"
+PDFIO_VERSION_MAJOR="`echo 1.5.4 | awk -F. '{print $1}'`"
+PDFIO_VERSION_MINOR="`echo 1.5.4 | awk -F. '{printf("%d\n",$2);}'`"
 
 
 
@@ -5099,7 +5099,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by pdfio $as_me 1.5.3, which was
+This file was extended by pdfio $as_me 1.5.4, which was
 generated by GNU Autoconf 2.71.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -5155,7 +5155,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-pdfio config.status 1.5.3
+pdfio config.status 1.5.4
 configured by $0, generated by GNU Autoconf 2.71,
   with options \\"\$ac_cs_config\\"
 

configure.ac

@@ -21,7 +21,7 @@ AC_PREREQ([2.70])
 
 
 dnl Package name and version...
-AC_INIT([pdfio], [1.5.3], [https://github.com/michaelrsweet/pdfio/issues], [pdfio], [https://www.msweet.org/pdfio])
+AC_INIT([pdfio], [1.5.4], [https://github.com/michaelrsweet/pdfio/issues], [pdfio], [https://www.msweet.org/pdfio])
 
 PDFIO_VERSION="AC_PACKAGE_VERSION"
 PDFIO_VERSION_MAJOR="`echo AC_PACKAGE_VERSION | awk -F. '{print $1}'`"

examples/md2pdf.c

@@ -1,7 +1,7 @@
 //
 // Simple markdown to PDF converter example for PDFio.
 //
-// Copyright © 2024 by Michael R Sweet.
+// Copyright © 2024-2025 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@@ -289,8 +289,8 @@ main(int  argc,				// I - Number of command-line arguments
   // Get the markdown file from the command-line...
   if (argc < 2 || argc > 3)
   {
-    fputs("Usage: md2pdf FILENANE.md [FILENAME.pdf]\n", stderr);
-    fputs("       md2pdf FILENANE.md >FILENAME.pdf\n", stderr);
+    fputs("Usage: md2pdf FILENAME.md [FILENAME.pdf]\n", stderr);
+    fputs("       md2pdf FILENAME.md >FILENAME.pdf\n", stderr);
     return (1);
   }
 

pdfio-content.c

@@ -2527,110 +2527,69 @@ copy_jpeg(pdfio_dict_t *dict,		// I - Dictionary
       bufend += bytes;
     }
 
-    if (*bufptr == _PDFIO_JPEG_MARKER)
+    if (*bufptr != _PDFIO_JPEG_MARKER)
     {
-      // Start of a marker in the file...
-      bufptr ++;
+      _pdfioFileError(dict->pdf, "Invalid JPEG data: <%02X>", *bufptr);
+      goto finish;
+    }
 
-      marker = *bufptr;
-      length = (size_t)((bufptr[1] << 8) | bufptr[2]);
-      bufptr += 3;
+    // Start of a marker in the file...
+    bufptr ++;
 
-      if (marker == _PDFIO_JPEG_MARKER)
-	continue;
-      else if (marker == _PDFIO_JPEG_EOI || marker == _PDFIO_JPEG_SOS || length < 2)
-        break;
+    marker = *bufptr;
+    length = (size_t)((bufptr[1] << 8) | bufptr[2]);
+    bufptr += 3;
 
-      PDFIO_DEBUG("copy_jpeg: JPEG X'FF%02X' (length %u)\n", marker, (unsigned)length);
+    PDFIO_DEBUG("copy_jpeg: JPEG X'FF%02X' (length %u)\n", marker, (unsigned)length);
 
-      length -= 2;
+    if (marker == _PDFIO_JPEG_EOI || marker == _PDFIO_JPEG_SOS || length < 2)
+      break;
 
-      if ((marker >= _PDFIO_JPEG_SOF0 && marker <= _PDFIO_JPEG_SOF3) || (marker >= _PDFIO_JPEG_SOF5 && marker <= _PDFIO_JPEG_SOF7) || (marker >= _PDFIO_JPEG_SOF9 && marker <= _PDFIO_JPEG_SOF11) || (marker >= _PDFIO_JPEG_SOF13 && marker <= _PDFIO_JPEG_SOF15))
+    length -= 2;
+
+    if ((marker >= _PDFIO_JPEG_SOF0 && marker <= _PDFIO_JPEG_SOF3) || (marker >= _PDFIO_JPEG_SOF5 && marker <= _PDFIO_JPEG_SOF7) || (marker >= _PDFIO_JPEG_SOF9 && marker <= _PDFIO_JPEG_SOF11) || (marker >= _PDFIO_JPEG_SOF13 && marker <= _PDFIO_JPEG_SOF15))
+    {
+      // SOFn marker, look for dimensions...
+      //
+      // Byte(s)  Description
+      // -------  -------------------
+      // 0        Bits per component
+      // 1-2      Height
+      // 3-4      Width
+      // 5        Number of colors
+      if (bufptr[0] != 8)
       {
-        // SOFn marker, look for dimensions...
-        //
-        // Byte(s)  Description
-        // -------  -------------------
-        // 0        Bits per component
-        // 1-2      Height
-        // 3-4      Width
-        // 5        Number of colors
-        if (bufptr[0] != 8)
-        {
-          _pdfioFileError(dict->pdf, "Unable to load %d-bit JPEG image.", bufptr[0]);
-	  goto finish;
-        }
-
-	width      = (unsigned)((bufptr[3] << 8) | bufptr[4]);
-	height     = (unsigned)((bufptr[1] << 8) | bufptr[2]);
-	num_colors = bufptr[5];
-      }
-      else if (marker == _PDFIO_JPEG_APP2 && length > 14 && memcmp(bufptr, "ICC_PROFILE", 12))
-      {
-        // Portion of ICC profile
-        int	n = bufptr[12],		// Chunk number in profile (1-based)
-		count = bufptr[13];	// Number of chunks
-        unsigned char *icc_temp;	// New ICC buffer
-
-        // Discard "ICC_PROFILE\0" and chunk number/count...
-        bufptr += 14;
-        length -= 14;
-
-        // Expand our ICC buffer...
-        if ((icc_temp = realloc(icc_data, icc_datalen + length)) == NULL)
-          return (NULL);
-        else
-          icc_data = icc_temp;
-
-        // Read the chunk into the ICC buffer...
-        do
-        {
-	  if (bufptr >= bufend)
-	  {
-	    // Read more of the marker...
-	    if ((bytes = read(fd, buffer, sizeof(buffer))) <= 0)
-	    {
-	      _pdfioFileError(dict->pdf, "Unable to read JPEG data - %s", strerror(errno));
-	      goto finish;
-	    }
-
-            bufptr = buffer;
-	    bufend = buffer + bytes;
-	  }
-
-          // Copy from the file buffer to the ICC buffer
-          if ((bytes = bufend - bufptr) > (ssize_t)length)
-	    bytes = (ssize_t)length;
-
-	  memcpy(icc_data + icc_datalen, bufptr, bytes);
-	  icc_datalen += (size_t)bytes;
-	  bufptr      += bytes;
-	  length      -= (size_t)bytes;
-	}
-	while (length > 0);
-
-        if (n == count && width > 0 && height > 0 && num_colors > 0)
-        {
-          // Have everything we need...
-          break;
-        }
-        else
-        {
-          // Continue reading...
-          continue;
-        }
+	_pdfioFileError(dict->pdf, "Unable to load %d-bit JPEG image.", bufptr[0]);
+	goto finish;
       }
 
-      // Skip past this marker...
-      while (length > 0)
+      width      = (unsigned)((bufptr[3] << 8) | bufptr[4]);
+      height     = (unsigned)((bufptr[1] << 8) | bufptr[2]);
+      num_colors = bufptr[5];
+    }
+    else if (marker == _PDFIO_JPEG_APP2 && length > 14 && memcmp(bufptr, "ICC_PROFILE", 12))
+    {
+      // Portion of ICC profile
+      int	n = bufptr[12],		// Chunk number in profile (1-based)
+	      count = bufptr[13];	// Number of chunks
+      unsigned char *icc_temp;	// New ICC buffer
+
+      // Discard "ICC_PROFILE\0" and chunk number/count...
+      bufptr += 14;
+      length -= 14;
+
+      // Expand our ICC buffer...
+      if ((icc_temp = realloc(icc_data, icc_datalen + length)) == NULL)
+	return (NULL);
+      else
+	icc_data = icc_temp;
+
+      // Read the chunk into the ICC buffer...
+      do
       {
-        bytes = bufend - bufptr;
-
-        if (length > (size_t)bytes)
-        {
-          // Consume everything we have and grab more...
-          length -= (size_t)bytes;
-
+	if (bufptr >= bufend)
+	{
+	  // Read more of the marker...
 	  if ((bytes = read(fd, buffer, sizeof(buffer))) <= 0)
 	  {
 	    _pdfioFileError(dict->pdf, "Unable to read JPEG data - %s", strerror(errno));
@@ -2640,12 +2599,54 @@ copy_jpeg(pdfio_dict_t *dict,		// I - Dictionary
 	  bufptr = buffer;
 	  bufend = buffer + bytes;
 	}
-	else
+
+	// Copy from the file buffer to the ICC buffer
+	if ((bytes = bufend - bufptr) > (ssize_t)length)
+	  bytes = (ssize_t)length;
+
+	memcpy(icc_data + icc_datalen, bufptr, bytes);
+	icc_datalen += (size_t)bytes;
+	bufptr      += bytes;
+	length      -= (size_t)bytes;
+      }
+      while (length > 0);
+
+      if (n == count && width > 0 && height > 0 && num_colors > 0)
+      {
+	// Have everything we need...
+	break;
+      }
+      else
+      {
+	// Continue reading...
+	continue;
+      }
+    }
+
+    // Skip past this marker...
+    while (length > 0)
+    {
+      bytes = bufend - bufptr;
+
+      if (length > (size_t)bytes)
+      {
+	// Consume everything we have and grab more...
+	length -= (size_t)bytes;
+
+	if ((bytes = read(fd, buffer, sizeof(buffer))) <= 0)
 	{
-	  // Enough at the end of the buffer...
-	  bufptr += length;
-	  length = 0;
+	  _pdfioFileError(dict->pdf, "Unable to read JPEG data - %s", strerror(errno));
+	  goto finish;
 	}
+
+	bufptr = buffer;
+	bufend = buffer + bytes;
+      }
+      else
+      {
+	// Enough at the end of the buffer...
+	bufptr += length;
+	length = 0;
       }
     }
   }

pdfio-token.c

@@ -380,7 +380,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  else
 	  {
 	    // Out of space
-	    _pdfioFileError(tb->pdf, "Token too large.");
+	    _pdfioFileError(tb->pdf, "String token too large.");
 	    *bufptr = '\0';
 	    return (false);
 	  }
@@ -408,7 +408,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
           if ((2 * (bytes + 1)) > bufsize)
           {
 	    // Out of space...
-	    _pdfioFileError(tb->pdf, "Token too large.");
+	    _pdfioFileError(tb->pdf, "Binary string token too large.");
 	    *bufptr = '\0';
 	    return (false);
           }
@@ -442,7 +442,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  else
 	  {
 	    // Out of space...
-	    _pdfioFileError(tb->pdf, "Token too large.");
+	    _pdfioFileError(tb->pdf, "Keyword token too large.");
 	    *bufptr = '\0';
 	    return (false);
 	  }
@@ -474,7 +474,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  else
 	  {
 	    // Out of space...
-	    _pdfioFileError(tb->pdf, "Token too large.");
+	    _pdfioFileError(tb->pdf, "Number token too large.");
 	    *bufptr = '\0';
 	    return (false);
 	  }
@@ -523,7 +523,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	  else
 	  {
 	    // Out of space
-	    _pdfioFileError(tb->pdf, "Token too large.");
+	    _pdfioFileError(tb->pdf, "Name token too large.");
 	    *bufptr = '\0';
 	    return (false);
 	  }
@@ -566,7 +566,7 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	    else
 	    {
 	      // Too large
-	      _pdfioFileError(tb->pdf, "Token too large.");
+	      _pdfioFileError(tb->pdf, "Hex string token too large.");
 	      *bufptr = '\0';
 	      return (false);
 	    }

pdfio-value.c

@@ -515,7 +515,7 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
         // Integer...
         long generation = 0;		// Generation number
 
-        while (tempptr < tb->bufend && isdigit(*tempptr & 255))
+        while (tempptr < tb->bufend && generation < 65536 && isdigit(*tempptr & 255))
         {
           generation = generation * 10 + *tempptr - '0';
           tempptr ++;

pdfio.h

@@ -23,7 +23,7 @@ extern "C" {
 // Version numbers...
 //
 
-#  define PDFIO_VERSION		"1.5.3"
+#  define PDFIO_VERSION		"1.5.4"
 #  define PDFIO_VERSION_MAJOR	1
 #  define PDFIO_VERSION_MINOR	5
 

pdfio_native.nuspec

@@ -3,7 +3,7 @@
     <metadata>
         <id>pdfio_native</id>
         <title>PDFio Library for VS2019+</title>
-        <version>1.5.3</version>
+        <version>1.5.4</version>
         <authors>Michael R Sweet</authors>
         <owners>michaelrsweet</owners>
         <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>
@@ -16,7 +16,7 @@
         <copyright>Copyright © 2019-2025 by Michael R Sweet</copyright>
         <tags>pdf file native</tags>
 	<dependencies>
-	    <dependency id="pdfio_native.redist" version="1.5.3" />
+	    <dependency id="pdfio_native.redist" version="1.5.4" />
 	    <dependency id="libpng_native.redist" version="1.6.30" />
 	    <dependency id="zlib_native.redist" version="1.2.11" />
 	</dependencies>

pdfio_native.redist.nuspec

@@ -3,7 +3,7 @@
     <metadata>
         <id>pdfio_native.redist</id>
         <title>PDFio Library for VS2019+</title>
-        <version>1.5.3</version>
+        <version>1.5.4</version>
         <authors>Michael R Sweet</authors>
         <owners>michaelrsweet</owners>
         <projectUrl>https://github.com/michaelrsweet/pappl</projectUrl>