Update pdfioinfo example to support Acrobat Form dictionaries as well as indirect references (Issue #114 )

Move token buffers off the stack (Issue #117 )
Add PDFIO_MAX_STRING constant to control maximum allowed PDF strings (Issue #117 )
2025-04-05 08:26:46 +02:00 · 2025-04-04 21:24:42 -04:00 · 2025-04-04 21:20:23 -04:00 · 2025-04-04 19:27:03 -04:00 · 2025-04-04 19:12:16 -04:00 · 2025-04-04 19:11:54 -04:00
14 changed files with 733 additions and 165 deletions
--- a/CHANGES.md
+++ b/CHANGES.md
@ -1,6 +1,16 @@
 Changes in PDFio
 ================

+
+v1.5.2 - YYYY-MM-DD
+-------------------
+
+- Updated maximum allowed PDF string size to 64k (Issue #117)
+- Fixed form detection in `pdfioinfo` example code (Issue #114)
+- Fixed parsing of certain date/time values (Issue #115)
+- Fixed support for empty name values (Issue #116)
+
+
 v1.5.1 - 2025-03-28
 -------------------

--- a/203
+++ b/203
@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for pdfio 1.5.1.
+# Generated by GNU Autoconf 2.71 for pdfio 1.5.2.
 #
 # 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='1.5.1'
-PACKAGE_STRING='pdfio 1.5.1'
+PACKAGE_VERSION='1.5.2'
+PACKAGE_STRING='pdfio 1.5.2'
 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 1.5.1 to adapt to many kinds of systems.
+\`configure' configures pdfio 1.5.2 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 1.5.1:";;
+     short | recursive ) echo "Configuration of pdfio 1.5.2:";;
   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 1.5.1
+pdfio configure 1.5.2
 generated by GNU Autoconf 2.71

 Copyright (C) 2021 Free Software Foundation, Inc.
@ -1513,39 +1513,6 @@ fi

 } # ac_fn_c_try_compile

-# ac_fn_c_check_header_compile LINENO HEADER VAR INCLUDES
-# -------------------------------------------------------
-# Tests whether HEADER exists and can be compiled using the include files in
-# INCLUDES, setting the cache variable VAR accordingly.
-ac_fn_c_check_header_compile ()
-{
-  as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
-  { printf "%s\n" "$as_me:${as_lineno-$LINENO}: checking for $2" >&5
-printf %s "checking for $2... " >&6; }
-if eval test \${$3+y}
-then :
-  printf %s "(cached) " >&6
-else $as_nop
-  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
-/* end confdefs.h.  */
-$4
-#include <$2>
-_ACEOF
-if ac_fn_c_try_compile "$LINENO"
-then :
-  eval "$3=yes"
-else $as_nop
-  eval "$3=no"
-fi
-rm -f core conftest.err conftest.$ac_objext conftest.beam conftest.$ac_ext
-fi
-eval ac_res=\$$3
-	       { printf "%s\n" "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5
-printf "%s\n" "$ac_res" >&6; }
-  eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno
-
-} # ac_fn_c_check_header_compile
-
 # ac_fn_c_try_link LINENO
 # -----------------------
 # Try to link conftest.$ac_ext, and return whether this succeeded.
@ -1592,6 +1559,101 @@ fi
  as_fn_set_status $ac_retval

 } # ac_fn_c_try_link
+
+# ac_fn_c_check_func LINENO FUNC VAR
+# ----------------------------------
+# Tests whether FUNC exists, setting the cache variable VAR accordingly
+ac_fn_c_check_func ()
+{
+  as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+  { printf "%s\n" "$as_me:${as_lineno-$LINENO}: checking for $2" >&5
+printf %s "checking for $2... " >&6; }
+if eval test \${$3+y}
+then :
+  printf %s "(cached) " >&6
+else $as_nop
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+/* Define $2 to an innocuous variant, in case <limits.h> declares $2.
+   For example, HP-UX 11i <limits.h> declares gettimeofday.  */
+#define $2 innocuous_$2
+
+/* System header to define __stub macros and hopefully few prototypes,
+   which can conflict with char $2 (); below.  */
+
+#include <limits.h>
+#undef $2
+
+/* Override any GCC internal prototype to avoid an error.
+   Use char because int might match the return type of a GCC
+   builtin and then its argument prototype would still apply.  */
+#ifdef __cplusplus
+extern "C"
+#endif
+char $2 ();
+/* The GNU C library defines this for functions which it implements
+    to always fail with ENOSYS.  Some functions are actually named
+    something starting with __ and the normal name is an alias.  */
+#if defined __stub_$2 || defined __stub___$2
+choke me
+#endif
+
+int
+main (void)
+{
+return $2 ();
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"
+then :
+  eval "$3=yes"
+else $as_nop
+  eval "$3=no"
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.beam \
+    conftest$ac_exeext conftest.$ac_ext
+fi
+eval ac_res=\$$3
+	       { printf "%s\n" "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5
+printf "%s\n" "$ac_res" >&6; }
+  eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno
+
+} # ac_fn_c_check_func
+
+# ac_fn_c_check_header_compile LINENO HEADER VAR INCLUDES
+# -------------------------------------------------------
+# Tests whether HEADER exists and can be compiled using the include files in
+# INCLUDES, setting the cache variable VAR accordingly.
+ac_fn_c_check_header_compile ()
+{
+  as_lineno=${as_lineno-"$1"} as_lineno_stack=as_lineno_stack=$as_lineno_stack
+  { printf "%s\n" "$as_me:${as_lineno-$LINENO}: checking for $2" >&5
+printf %s "checking for $2... " >&6; }
+if eval test \${$3+y}
+then :
+  printf %s "(cached) " >&6
+else $as_nop
+  cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+$4
+#include <$2>
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"
+then :
+  eval "$3=yes"
+else $as_nop
+  eval "$3=no"
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.beam conftest.$ac_ext
+fi
+eval ac_res=\$$3
+	       { printf "%s\n" "$as_me:${as_lineno-$LINENO}: result: $ac_res" >&5
+printf "%s\n" "$ac_res" >&6; }
+  eval $as_lineno_stack; ${as_lineno_stack:+:} unset as_lineno
+
+} # ac_fn_c_check_header_compile
 ac_configure_args_raw=
 for ac_arg
 do
@ -1616,7 +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 1.5.1, which was
+It was created by pdfio $as_me 1.5.2, which was
 generated by GNU Autoconf 2.71.  Invocation command line was

  $ $0$ac_configure_args_raw
@ -2372,9 +2434,9 @@ ac_compiler_gnu=$ac_cv_c_compiler_gnu



-PDFIO_VERSION="1.5.1"
-PDFIO_VERSION_MAJOR="`echo 1.5.1 | awk -F. '{print $1}'`"
-PDFIO_VERSION_MINOR="`echo 1.5.1 | awk -F. '{printf("%d\n",$2);}'`"
+PDFIO_VERSION="1.5.2"
+PDFIO_VERSION_MAJOR="`echo 1.5.2 | awk -F. '{print $1}'`"
+PDFIO_VERSION_MINOR="`echo 1.5.2 | awk -F. '{printf("%d\n",$2);}'`"



@ -3877,6 +3939,56 @@ INSTALL="$(pwd)/install-sh"
 printf "%s\n" "using $INSTALL" >&6; }


+
+ac_fn_c_check_func "$LINENO" "timegm" "ac_cv_func_timegm"
+if test "x$ac_cv_func_timegm" = xyes
+then :
+
+
+printf "%s\n" "#define HAVE_TIMEGM 1" >>confdefs.h
+
+    CPPFLAGS="-DHAVE_TIMEGM=1 $CPPFLAGS"
+
+fi
+
+
+{ printf "%s\n" "$as_me:${as_lineno-$LINENO}: checking for tm_gmtoff member in tm structure" >&5
+printf %s "checking for tm_gmtoff member in tm structure... " >&6; }
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+    #include <time.h>
+int
+main (void)
+{
+
+        struct tm t;
+	int o = t.tm_gmtoff;
+
+  ;
+  return 0;
+}
+
+_ACEOF
+if ac_fn_c_try_compile "$LINENO"
+then :
+
+    { printf "%s\n" "$as_me:${as_lineno-$LINENO}: result: yes" >&5
+printf "%s\n" "yes" >&6; }
+
+printf "%s\n" "#define HAVE_TM_GMTOFF 1" >>confdefs.h
+
+    CPPFLAGS="-DHAVE_TM_GMTOFF=1 $CPPFLAGS"
+
+else $as_nop
+
+    { printf "%s\n" "$as_me:${as_lineno-$LINENO}: result: no" >&5
+printf "%s\n" "no" >&6; }
+
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.beam conftest.$ac_ext
+
+
 if test -n "$ac_tool_prefix"; then
  # Extract the first word of "${ac_tool_prefix}pkg-config", so it can be a program name with args.
 set dummy ${ac_tool_prefix}pkg-config; ac_word=$2
@ -3998,7 +4110,6 @@ PKGCONFIG_REQUIRES="zlib"

 { printf "%s\n" "$as_me:${as_lineno-$LINENO}: checking for zlib via pkg-config" >&5
 printf %s "checking for zlib via pkg-config... " >&6; }
-
 ac_header= ac_cache=
 for ac_item in $ac_header_c_list
 do
@ -4988,7 +5099,7 @@ cat >>$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 1.5.1, which was
+This file was extended by pdfio $as_me 1.5.2, which was
 generated by GNU Autoconf 2.71.  Invocation command line was

  CONFIG_FILES    = $CONFIG_FILES
@ -5044,7 +5155,7 @@ ac_cs_config_escaped=`printf "%s\n" "$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 1.5.1
+pdfio config.status 1.5.2
 configured by $0, generated by GNU Autoconf 2.71,
  with options \\"\$ac_cs_config\\"

--- a/configure.ac
+++ b/configure.ac
@ -21,7 +21,7 @@ AC_PREREQ([2.70])


 dnl Package name and version...
-AC_INIT([pdfio], [1.5.1], [https://github.com/michaelrsweet/pdfio/issues], [pdfio], [https://www.msweet.org/pdfio])
+AC_INIT([pdfio], [1.5.2], [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}'`"
@ -88,6 +88,27 @@ AC_SUBST([INSTALL])
 AC_MSG_RESULT([using $INSTALL])


+dnl Check for date/time functionality...
+AC_CHECK_FUNC([timegm], [
+    AC_DEFINE([HAVE_TIMEGM], [1], [Do we have the timegm function?])
+    CPPFLAGS="-DHAVE_TIMEGM=1 $CPPFLAGS"
+])
+
+AC_MSG_CHECKING([for tm_gmtoff member in tm structure])
+AC_COMPILE_IFELSE([
+    AC_LANG_PROGRAM([[#include <time.h>]], [[
+        struct tm t;
+	int o = t.tm_gmtoff;
+    ]])
+], [
+    AC_MSG_RESULT([yes])
+    AC_DEFINE([HAVE_TM_GMTOFF], [1], [Have tm_gmtoff member in struct tm?])
+    CPPFLAGS="-DHAVE_TM_GMTOFF=1 $CPPFLAGS"
+], [
+    AC_MSG_RESULT([no])
+])
+
+
 dnl Check for pkg-config, which is used for some other tests later on...
 AC_PATH_TOOL([PKGCONFIG], [pkg-config])

--- a/doc/pdfio.3
+++ b/doc/pdfio.3
@ -1,4 +1,4 @@
-.TH pdfio 3 "pdf read/write library" "2025-03-06" "pdf read/write library"
+.TH pdfio 3 "pdf read/write library" "2025-04-04" "pdf read/write library"
 .SH NAME
 pdfio \- pdf read/write library
 .SH Introduction
@ -1047,11 +1047,26 @@ The pdfioinfo.c example program opens a PDF file and prints the title, author, c
    {
      const char    *filename;              // PDF filename
      pdfio_file_t  *pdf;                   // PDF file
-      const char    *author;                // Author name
-      time_t        creation_date;          // Creation date
-      struct tm     *creation_tm;           // Creation date/time information
-      char          creation_text[256];     // Creation date/time as a string
-      const char    *title;                 // Title
+      pdfio_dict_t  *catalog;               // Catalog dictionary
+      const char    *author,                // Author name
+                    *creator,               // Creator name
+                    *producer,              // Producer name
+                    *title;                 // Title
+      time_t        creation_date,          // Creation date
+                    modification_date;      // Modification date
+      struct tm     *creation_tm,           // Creation date/time information
+                    *modification_tm;       // Modification date/time information
+      char          creation_text[256],     // Creation date/time as a string
+                    modification_text[256], // Modification date/time human fmt string
+                    range_text[255];        // Page range text
+      size_t        num_pages;              // PDF number of pages
+      bool          has_acroform;           // Does the file have an AcroForm?
+      pdfio_obj_t   *page;                  // Object
+      pdfio_dict_t  *page_dict;             // Object dictionary
+      size_t        cur,                    // Current page index
+                    prev;                   // Previous page index
+      pdfio_rect_t  cur_box,                // Current MediaBox
+                    prev_box;               // Previous MediaBox
    
    
      // Get the filename from the command\-line...
@ -1064,14 +1079,20 @@ The pdfioinfo.c example program opens a PDF file and prints the title, author, c
      filename = argv[1];
    
      // Open the PDF file with the default callbacks...
-      pdf = pdfioFileOpen(filename, /*password_cb*/NULL, /*password_cbdata*/NULL,
-                          /*error_cb*/NULL, /*error_cbdata*/NULL);
+      pdf = pdfioFileOpen(filename, /*password_cb*/NULL,
+                          /*password_cbdata*/NULL, /*error_cb*/NULL,
+                          /*error_cbdata*/NULL);
      if (pdf == NULL)
        return (1);
    
-      // Get the title and author...
-      author = pdfioFileGetAuthor(pdf);
-      title  = pdfioFileGetTitle(pdf);
+      // Get the title, author, etc...
+      catalog      = pdfioFileGetCatalog(pdf);
+      author       = pdfioFileGetAuthor(pdf);
+      creator      = pdfioFileGetCreator(pdf);
+      has_acroform = pdfioDictGetType(catalog, "AcroForm") != PDFIO_VALTYPE_NONE;
+      num_pages    = pdfioFileGetNumPages(pdf);
+      producer     = pdfioFileGetProducer(pdf);
+      title        = pdfioFileGetTitle(pdf);
    
      // Get the creation date and convert to a string...
      if ((creation_date = pdfioFileGetCreationDate(pdf)) > 0)
@ -1084,12 +1105,76 @@ The pdfioinfo.c example program opens a PDF file and prints the title, author, c
        snprintf(creation_text, sizeof(creation_text), "\-\- not set \-\-");
      }
    
+      // Get the modification date and convert to a string...
+      if ((modification_date = pdfioFileGetModificationDate(pdf)) > 0)
+      {
+        modification_tm = localtime(&modification_date);
+        strftime(modification_text, sizeof(modification_text), "%c", modification_tm);
+      }
+      else
+      {
+        snprintf(modification_text, sizeof(modification_text), "\-\- not set \-\-");
+      }
+    
      // Print file information to stdout...
      printf("%s:\\n", filename);
-      printf("         Title: %s\\n", title ? title : "\-\- not set \-\-");
-      printf("        Author: %s\\n", author ? author : "\-\- not set \-\-");
-      printf("    Created On: %s\\n", creation_text);
-      printf("  Number Pages: %u\\n", (unsigned)pdfioFileGetNumPages(pdf));
+      printf("           Title: %s\\n", title ? title : "\-\- not set \-\-");
+      printf("          Author: %s\\n", author ? author : "\-\- not set \-\-");
+      printf("         Creator: %s\\n", creator ? creator : "\-\- not set \-\-");
+      printf("        Producer: %s\\n", producer ? producer : "\-\- not set \-\-");
+      printf("      Created On: %s\\n", creation_text);
+      printf("     Modified On: %s\\n", modification_text);
+      printf("         Version: %s\\n", pdfioFileGetVersion(pdf));
+      printf("        AcroForm: %s\\n", has_acroform ? "Yes" : "No");
+      printf(" Number of Pages: %u\\n", (unsigned)num_pages);
+    
+      // Report the MediaBox for all of the pages
+      prev_box.x1 = prev_box.x2 = prev_box.y1 = prev_box.y2 = 0.0;
+    
+      for (cur = 0, prev = 0; cur < num_pages; cur ++)
+      {
+        // Find the MediaBox for this page in the page tree...
+        for (page = pdfioFileGetPage(pdf, cur);
+             page != NULL;
+             page = pdfioDictGetObj(page_dict, "Parent"))
+        {
+          cur_box.x1 = cur_box.x2 = cur_box.y1 = cur_box.y2 = 0.0;
+          page_dict  = pdfioObjGetDict(page);
+    
+          if (pdfioDictGetRect(page_dict, "MediaBox", &cur_box))
+            break;
+        }
+    
+        // If this MediaBox is different from the previous one, show the range of
+        // pages that have that size...
+        if (cur == 0 ||
+            fabs(cur_box.x1 \- prev_box.x1) > 0.01 ||
+            fabs(cur_box.y1 \- prev_box.y1) > 0.01 ||
+            fabs(cur_box.x2 \- prev_box.x2) > 0.01 ||
+            fabs(cur_box.y2 \- prev_box.y2) > 0.01)
+        {
+          if (cur > prev)
+          {
+            snprintf(range_text, sizeof(range_text), "Pages %u\-%u",
+                     (unsigned)(prev + 1), (unsigned)cur);
+            printf("%16s: [%g %g %g %g]\\n", range_text,
+                   prev_box.x1, prev_box.y1, prev_box.x2, prev_box.y2);
+          }
+    
+          // Start a new series of pages with the new size...
+          prev     = cur;
+          prev_box = cur_box;
+        }
+      }
+    
+      // Show the last range as needed...
+      if (cur > prev)
+      {
+        snprintf(range_text, sizeof(range_text), "Pages %u\-%u",
+                 (unsigned)(prev + 1), (unsigned)cur);
+        printf("%16s: [%g %g %g %g]\\n", range_text,
+               prev_box.x1, prev_box.y1, prev_box.x2, prev_box.y2);
+      }
    
      // Close the PDF file...
      pdfioFileClose(pdf);
@ -4590,6 +4675,10 @@ bool  pdfioStreamPrintf (
    ...
 );
 .fi
+.PP
+This function writes a formatted string to a stream.  In addition to the
+standard \fBprintf\fR format characters, you can use "%N" to format a PDF name
+value ("/Name") and "%S" to format a PDF string ("(String)") value.
 .SS pdfioStreamPutChar
 Write a single character to a stream.
 .PP
--- a/doc/pdfio.html
+++ b/doc/pdfio.html
@ -1,13 +1,13 @@
 <!DOCTYPE html>
 <html lang="en-US">
 <head>
-<title>PDFio Programming Manual v1.5.0</title>
+<title>PDFio Programming Manual v1.5.2</title>
 <meta http-equiv="Content-Type" content="text/html;charset=utf-8">
 <meta name="generator" content="codedoc v3.8">
 <meta name="author" content="Michael R Sweet">
 <meta name="language" content="en-US">
 <meta name="copyright" content="Copyright © 2021-2025 by Michael R Sweet">
-<meta name="version" content="1.5.0">
+<meta name="version" content="1.5.2">
 <style type="text/css"><!--
 body {
  background: white;
@ -251,7 +251,7 @@ span.string {
 <body>
 <div class="header">
 <p><img class="title" src="pdfio-512.png"></p>
-<h1 class="title">PDFio Programming Manual v1.5.0</h1>
+<h1 class="title">PDFio Programming Manual v1.5.2</h1>
 <p>Michael R Sweet</p>
 <p>Copyright © 2021-2025 by Michael R Sweet</p>
 </div>
@ -1165,11 +1165,26 @@ main(<span class="reserved">int</span>  argc,                         <span clas
 {
  <span class="reserved">const</span> <span class="reserved">char</span>    *filename;              <span class="comment">// PDF filename</span>
  pdfio_file_t  *pdf;                   <span class="comment">// PDF file</span>
-  <span class="reserved">const</span> <span class="reserved">char</span>    *author;                <span class="comment">// Author name</span>
-  time_t        creation_date;          <span class="comment">// Creation date</span>
-  <span class="reserved">struct</span> tm     *creation_tm;           <span class="comment">// Creation date/time information</span>
-  <span class="reserved">char</span>          creation_text[<span class="number">256</span>];     <span class="comment">// Creation date/time as a string</span>
-  <span class="reserved">const</span> <span class="reserved">char</span>    *title;                 <span class="comment">// Title</span>
+  pdfio_dict_t  *catalog;               <span class="comment">// Catalog dictionary</span>
+  <span class="reserved">const</span> <span class="reserved">char</span>    *author,                <span class="comment">// Author name</span>
+                *creator,               <span class="comment">// Creator name</span>
+                *producer,              <span class="comment">// Producer name</span>
+                *title;                 <span class="comment">// Title</span>
+  time_t        creation_date,          <span class="comment">// Creation date</span>
+                modification_date;      <span class="comment">// Modification date</span>
+  <span class="reserved">struct</span> tm     *creation_tm,           <span class="comment">// Creation date/time information</span>
+                *modification_tm;       <span class="comment">// Modification date/time information</span>
+  <span class="reserved">char</span>          creation_text[<span class="number">256</span>],     <span class="comment">// Creation date/time as a string</span>
+                modification_text[<span class="number">256</span>], <span class="comment">// Modification date/time human fmt string</span>
+                range_text[<span class="number">255</span>];        <span class="comment">// Page range text</span>
+  size_t        num_pages;              <span class="comment">// PDF number of pages</span>
+  <span class="reserved">bool</span>          has_acroform;           <span class="comment">// Does the file have an AcroForm?</span>
+  pdfio_obj_t   *page;                  <span class="comment">// Object</span>
+  pdfio_dict_t  *page_dict;             <span class="comment">// Object dictionary</span>
+  size_t        cur,                    <span class="comment">// Current page index</span>
+                prev;                   <span class="comment">// Previous page index</span>
+  pdfio_rect_t  cur_box,                <span class="comment">// Current MediaBox</span>
+                prev_box;               <span class="comment">// Previous MediaBox</span>


  <span class="comment">// Get the filename from the command-line...</span>
@ -1182,14 +1197,20 @@ main(<span class="reserved">int</span>  argc,                         <span clas
  filename = argv[<span class="number">1</span>];

  <span class="comment">// Open the PDF file with the default callbacks...</span>
-  pdf = pdfioFileOpen(filename, <span class="comment">/*password_cb*/</span>NULL, <span class="comment">/*password_cbdata*/</span>NULL,
-                      <span class="comment">/*error_cb*/</span>NULL, <span class="comment">/*error_cbdata*/</span>NULL);
+  pdf = pdfioFileOpen(filename, <span class="comment">/*password_cb*/</span>NULL,
+                      <span class="comment">/*password_cbdata*/</span>NULL, <span class="comment">/*error_cb*/</span>NULL,
+                      <span class="comment">/*error_cbdata*/</span>NULL);
  <span class="reserved">if</span> (pdf == NULL)
    <span class="reserved">return</span> (<span class="number">1</span>);

-  <span class="comment">// Get the title and author...</span>
-  author = pdfioFileGetAuthor(pdf);
-  title  = pdfioFileGetTitle(pdf);
+  <span class="comment">// Get the title, author, etc...</span>
+  catalog      = pdfioFileGetCatalog(pdf);
+  author       = pdfioFileGetAuthor(pdf);
+  creator      = pdfioFileGetCreator(pdf);
+  has_acroform = pdfioDictGetType(catalog, <span class="string">&quot;AcroForm&quot;</span>) != PDFIO_VALTYPE_NONE;
+  num_pages    = pdfioFileGetNumPages(pdf);
+  producer     = pdfioFileGetProducer(pdf);
+  title        = pdfioFileGetTitle(pdf);

  <span class="comment">// Get the creation date and convert to a string...</span>
  <span class="reserved">if</span> ((creation_date = pdfioFileGetCreationDate(pdf)) &gt; <span class="number">0</span>)
@ -1202,12 +1223,76 @@ main(<span class="reserved">int</span>  argc,                         <span clas
    snprintf(creation_text, <span class="reserved">sizeof</span>(creation_text), <span class="string">&quot;-- not set --&quot;</span>);
  }

+  <span class="comment">// Get the modification date and convert to a string...</span>
+  <span class="reserved">if</span> ((modification_date = pdfioFileGetModificationDate(pdf)) &gt; <span class="number">0</span>)
+  {
+    modification_tm = localtime(&amp;modification_date);
+    strftime(modification_text, <span class="reserved">sizeof</span>(modification_text), <span class="string">&quot;%c&quot;</span>, modification_tm);
+  }
+  <span class="reserved">else</span>
+  {
+    snprintf(modification_text, <span class="reserved">sizeof</span>(modification_text), <span class="string">&quot;-- not set --&quot;</span>);
+  }
+
  <span class="comment">// Print file information to stdout...</span>
  printf(<span class="string">&quot;%s:\n&quot;</span>, filename);
-  printf(<span class="string">&quot;         Title: %s\n&quot;</span>, title ? title : <span class="string">&quot;-- not set --&quot;</span>);
-  printf(<span class="string">&quot;        Author: %s\n&quot;</span>, author ? author : <span class="string">&quot;-- not set --&quot;</span>);
-  printf(<span class="string">&quot;    Created On: %s\n&quot;</span>, creation_text);
-  printf(<span class="string">&quot;  Number Pages: %u\n&quot;</span>, (<span class="reserved">unsigned</span>)pdfioFileGetNumPages(pdf));
+  printf(<span class="string">&quot;           Title: %s\n&quot;</span>, title ? title : <span class="string">&quot;-- not set --&quot;</span>);
+  printf(<span class="string">&quot;          Author: %s\n&quot;</span>, author ? author : <span class="string">&quot;-- not set --&quot;</span>);
+  printf(<span class="string">&quot;         Creator: %s\n&quot;</span>, creator ? creator : <span class="string">&quot;-- not set --&quot;</span>);
+  printf(<span class="string">&quot;        Producer: %s\n&quot;</span>, producer ? producer : <span class="string">&quot;-- not set --&quot;</span>);
+  printf(<span class="string">&quot;      Created On: %s\n&quot;</span>, creation_text);
+  printf(<span class="string">&quot;     Modified On: %s\n&quot;</span>, modification_text);
+  printf(<span class="string">&quot;         Version: %s\n&quot;</span>, pdfioFileGetVersion(pdf));
+  printf(<span class="string">&quot;        AcroForm: %s\n&quot;</span>, has_acroform ? <span class="string">&quot;Yes&quot;</span> : <span class="string">&quot;No&quot;</span>);
+  printf(<span class="string">&quot; Number of Pages: %u\n&quot;</span>, (<span class="reserved">unsigned</span>)num_pages);
+
+  <span class="comment">// Report the MediaBox for all of the pages</span>
+  prev_box.x1 = prev_box.x2 = prev_box.y1 = prev_box.y2 = <span class="number">0.0</span>;
+
+  <span class="reserved">for</span> (cur = <span class="number">0</span>, prev = <span class="number">0</span>; cur &lt; num_pages; cur ++)
+  {
+    <span class="comment">// Find the MediaBox for this page in the page tree...</span>
+    <span class="reserved">for</span> (page = pdfioFileGetPage(pdf, cur);
+         page != NULL;
+         page = pdfioDictGetObj(page_dict, <span class="string">&quot;Parent&quot;</span>))
+    {
+      cur_box.x1 = cur_box.x2 = cur_box.y1 = cur_box.y2 = <span class="number">0.0</span>;
+      page_dict  = pdfioObjGetDict(page);
+
+      <span class="reserved">if</span> (pdfioDictGetRect(page_dict, <span class="string">&quot;MediaBox&quot;</span>, &amp;cur_box))
+        <span class="reserved">break</span>;
+    }
+
+    <span class="comment">// If this MediaBox is different from the previous one, show the range of</span>
+    <span class="comment">// pages that have that size...</span>
+    <span class="reserved">if</span> (cur == <span class="number">0</span> ||
+        fabs(cur_box.x1 - prev_box.x1) &gt; <span class="number">0.01</span> ||
+        fabs(cur_box.y1 - prev_box.y1) &gt; <span class="number">0.01</span> ||
+        fabs(cur_box.x2 - prev_box.x2) &gt; <span class="number">0.01</span> ||
+        fabs(cur_box.y2 - prev_box.y2) &gt; <span class="number">0.01</span>)
+    {
+      <span class="reserved">if</span> (cur &gt; prev)
+      {
+        snprintf(range_text, <span class="reserved">sizeof</span>(range_text), <span class="string">&quot;Pages %u-%u&quot;</span>,
+                 (<span class="reserved">unsigned</span>)(prev + <span class="number">1</span>), (<span class="reserved">unsigned</span>)cur);
+        printf(<span class="string">&quot;%16s: [%g %g %g %g]\n&quot;</span>, range_text,
+               prev_box.x1, prev_box.y1, prev_box.x2, prev_box.y2);
+      }
+
+      <span class="comment">// Start a new series of pages with the new size...</span>
+      prev     = cur;
+      prev_box = cur_box;
+    }
+  }
+
+  <span class="comment">// Show the last range as needed...</span>
+  <span class="reserved">if</span> (cur &gt; prev)
+  {
+    snprintf(range_text, <span class="reserved">sizeof</span>(range_text), <span class="string">&quot;Pages %u-%u&quot;</span>,
+             (<span class="reserved">unsigned</span>)(prev + <span class="number">1</span>), (<span class="reserved">unsigned</span>)cur);
+    printf(<span class="string">&quot;%16s: [%g %g %g %g]\n&quot;</span>, range_text,
+           prev_box.x1, prev_box.y1, prev_box.x2, prev_box.y2);
+  }

  <span class="comment">// Close the PDF file...</span>
  pdfioFileClose(pdf);
@ -5081,6 +5166,10 @@ ssize_t pdfioStreamPeek(<a href="#pdfio_stream_t">pdfio_stream_t</a> *st, <span
 </tbody></table>
 <h4 class="returnvalue">Return Value</h4>
 <p class="description"><code>true</code> on success, <code>false</code> on failure</p>
+<h4 class="discussion">Discussion</h4>
+<p class="discussion">This function writes a formatted string to a stream.  In addition to the
+standard <code>printf</code> format characters, you can use &quot;%N&quot; to format a PDF name
+value (&quot;/Name&quot;) and &quot;%S&quot; to format a PDF string (&quot;(String)&quot;) value.</p>
 <h3 class="function"><a id="pdfioStreamPutChar">pdfioStreamPutChar</a></h3>
 <p class="description">Write a single character to a stream.</p>
 <p class="code">
--- a/doc/pdfio.md
+++ b/doc/pdfio.md
@ -889,11 +889,26 @@ main(int  argc,                         // I - Number of command-line arguments
 {
  const char    *filename;              // PDF filename
  pdfio_file_t  *pdf;                   // PDF file
-  const char    *author;                // Author name
-  time_t        creation_date;          // Creation date
-  struct tm     *creation_tm;           // Creation date/time information
-  char          creation_text[256];     // Creation date/time as a string
-  const char    *title;                 // Title
+  pdfio_dict_t  *catalog;               // Catalog dictionary
+  const char    *author,                // Author name
+                *creator,               // Creator name
+                *producer,              // Producer name
+                *title;                 // Title
+  time_t        creation_date,          // Creation date
+                modification_date;      // Modification date
+  struct tm     *creation_tm,           // Creation date/time information
+                *modification_tm;       // Modification date/time information
+  char          creation_text[256],     // Creation date/time as a string
+                modification_text[256], // Modification date/time human fmt string
+                range_text[255];        // Page range text
+  size_t        num_pages;              // PDF number of pages
+  bool          has_acroform;           // Does the file have an AcroForm?
+  pdfio_obj_t   *page;                  // Object
+  pdfio_dict_t  *page_dict;             // Object dictionary
+  size_t        cur,                    // Current page index
+                prev;                   // Previous page index
+  pdfio_rect_t  cur_box,                // Current MediaBox
+                prev_box;               // Previous MediaBox


  // Get the filename from the command-line...
@ -906,14 +921,20 @@ main(int  argc,                         // I - Number of command-line arguments
  filename = argv[1];

  // Open the PDF file with the default callbacks...
-  pdf = pdfioFileOpen(filename, /*password_cb*/NULL, /*password_cbdata*/NULL,
-                      /*error_cb*/NULL, /*error_cbdata*/NULL);
+  pdf = pdfioFileOpen(filename, /*password_cb*/NULL,
+                      /*password_cbdata*/NULL, /*error_cb*/NULL,
+                      /*error_cbdata*/NULL);
  if (pdf == NULL)
    return (1);

-  // Get the title and author...
-  author = pdfioFileGetAuthor(pdf);
-  title  = pdfioFileGetTitle(pdf);
+  // Get the title, author, etc...
+  catalog      = pdfioFileGetCatalog(pdf);
+  author       = pdfioFileGetAuthor(pdf);
+  creator      = pdfioFileGetCreator(pdf);
+  has_acroform = pdfioDictGetType(catalog, "AcroForm") != PDFIO_VALTYPE_NONE;
+  num_pages    = pdfioFileGetNumPages(pdf);
+  producer     = pdfioFileGetProducer(pdf);
+  title        = pdfioFileGetTitle(pdf);

  // Get the creation date and convert to a string...
  if ((creation_date = pdfioFileGetCreationDate(pdf)) > 0)
@ -926,12 +947,76 @@ main(int  argc,                         // I - Number of command-line arguments
    snprintf(creation_text, sizeof(creation_text), "-- not set --");
  }

+  // Get the modification date and convert to a string...
+  if ((modification_date = pdfioFileGetModificationDate(pdf)) > 0)
+  {
+    modification_tm = localtime(&modification_date);
+    strftime(modification_text, sizeof(modification_text), "%c", modification_tm);
+  }
+  else
+  {
+    snprintf(modification_text, sizeof(modification_text), "-- not set --");
+  }
+
  // Print file information to stdout...
  printf("%s:\n", filename);
-  printf("         Title: %s\n", title ? title : "-- not set --");
-  printf("        Author: %s\n", author ? author : "-- not set --");
-  printf("    Created On: %s\n", creation_text);
-  printf("  Number Pages: %u\n", (unsigned)pdfioFileGetNumPages(pdf));
+  printf("           Title: %s\n", title ? title : "-- not set --");
+  printf("          Author: %s\n", author ? author : "-- not set --");
+  printf("         Creator: %s\n", creator ? creator : "-- not set --");
+  printf("        Producer: %s\n", producer ? producer : "-- not set --");
+  printf("      Created On: %s\n", creation_text);
+  printf("     Modified On: %s\n", modification_text);
+  printf("         Version: %s\n", pdfioFileGetVersion(pdf));
+  printf("        AcroForm: %s\n", has_acroform ? "Yes" : "No");
+  printf(" Number of Pages: %u\n", (unsigned)num_pages);
+
+  // Report the MediaBox for all of the pages
+  prev_box.x1 = prev_box.x2 = prev_box.y1 = prev_box.y2 = 0.0;
+
+  for (cur = 0, prev = 0; cur < num_pages; cur ++)
+  {
+    // Find the MediaBox for this page in the page tree...
+    for (page = pdfioFileGetPage(pdf, cur);
+         page != NULL;
+         page = pdfioDictGetObj(page_dict, "Parent"))
+    {
+      cur_box.x1 = cur_box.x2 = cur_box.y1 = cur_box.y2 = 0.0;
+      page_dict  = pdfioObjGetDict(page);
+
+      if (pdfioDictGetRect(page_dict, "MediaBox", &cur_box))
+        break;
+    }
+
+    // If this MediaBox is different from the previous one, show the range of
+    // pages that have that size...
+    if (cur == 0 ||
+        fabs(cur_box.x1 - prev_box.x1) > 0.01 ||
+        fabs(cur_box.y1 - prev_box.y1) > 0.01 ||
+        fabs(cur_box.x2 - prev_box.x2) > 0.01 ||
+        fabs(cur_box.y2 - prev_box.y2) > 0.01)
+    {
+      if (cur > prev)
+      {
+        snprintf(range_text, sizeof(range_text), "Pages %u-%u",
+                 (unsigned)(prev + 1), (unsigned)cur);
+        printf("%16s: [%g %g %g %g]\n", range_text,
+               prev_box.x1, prev_box.y1, prev_box.x2, prev_box.y2);
+      }
+
+      // Start a new series of pages with the new size...
+      prev     = cur;
+      prev_box = cur_box;
+    }
+  }
+
+  // Show the last range as needed...
+  if (cur > prev)
+  {
+    snprintf(range_text, sizeof(range_text), "Pages %u-%u",
+             (unsigned)(prev + 1), (unsigned)cur);
+    printf("%16s: [%g %g %g %g]\n", range_text,
+           prev_box.x1, prev_box.y1, prev_box.x2, prev_box.y2);
+  }

  // Close the PDF file...
  pdfioFileClose(pdf);
--- a/examples/pdfioinfo.c
+++ b/examples/pdfioinfo.c
@ -68,7 +68,7 @@ main(int  argc,				// I - Number of command-line arguments
  catalog      = pdfioFileGetCatalog(pdf);
  author       = pdfioFileGetAuthor(pdf);
  creator      = pdfioFileGetCreator(pdf);
-  has_acroform = pdfioDictGetObj(catalog, "AcroForm") != NULL ? true : false;
+  has_acroform = pdfioDictGetType(catalog, "AcroForm") != PDFIO_VALTYPE_NONE;
  num_pages    = pdfioFileGetNumPages(pdf);
  producer     = pdfioFileGetProducer(pdf);
  title        = pdfioFileGetTitle(pdf);
--- a/pdfio-content.c
+++ b/pdfio-content.c
@ -1833,8 +1833,6 @@ pdfioFileCreateFontObjFromFile(
        {
          if ((w1 = ttfGetWidth(font, (int)i)) == w0 && i < 65530)
          {
-            size_t j;			// Look-ahead
-
            for (j = 1; j < 4; j ++)
            {
              if (ttfGetWidth(font, (int)(i + j)) != w0)
--- a/pdfio-file.c
+++ b/pdfio-file.c
@ -110,6 +110,8 @@ pdfioFileClose(pdfio_file_t *pdf)	// I - PDF file
 {
  bool		ret = true;		// Return value
  size_t	i;			// Looping var
+  _pdfio_strbuf_t *current,		// Current string buffer
+		*next;			// Next string buffer


  // Range check input
@ -152,6 +154,12 @@ pdfioFileClose(pdfio_file_t *pdf)	// I - PDF file
    free(pdf->strings[i]);
  free(pdf->strings);

+  for (current = pdf->strbuffers; current; current = next)
+  {
+    next = current->next;
+    free(current);
+  }
+
  free(pdf);

  return (ret);
--- a/pdfio-private.h
+++ b/pdfio-private.h
@ -94,6 +94,7 @@
 //

 #  define PDFIO_MAX_DEPTH	32	// Maximum nesting depth for values
+#  define PDFIO_MAX_STRING	65536	// Maximum length of string

 typedef void (*_pdfio_extfree_t)(void *);
 					// Extension data free function
@ -224,6 +225,14 @@ typedef struct _pdfio_objmap_s		// PDF object map
  size_t	src_number;		// Source object number
 } _pdfio_objmap_t;

+typedef struct _pdfio_strbuf_s		// PDF string buffer
+{
+  struct _pdfio_strbuf_s *next;		// Next string buffer
+  bool		bufused;		// Is this string buffer being used?
+  char		buffer[PDFIO_MAX_STRING + 32];
+					// String buffer
+} _pdfio_strbuf_t;
+
 struct _pdfio_file_s			// PDF file structure
 {
  char		*filename;		// Filename
@ -283,6 +292,7 @@ struct _pdfio_file_s			// PDF file structure
  size_t	num_strings,		// Number of strings
 		alloc_strings;		// Allocated strings
  char		**strings;		// Nul-terminated strings
+  _pdfio_strbuf_t *strbuffers;		// String buffers
 };

 struct _pdfio_obj_s			// Object
@ -390,6 +400,8 @@ extern bool		_pdfioObjWriteHeader(pdfio_obj_t *obj) _PDFIO_INTERNAL;
 extern pdfio_stream_t	*_pdfioStreamCreate(pdfio_obj_t *obj, pdfio_obj_t *length_obj, size_t cbsize, pdfio_filter_t compression) _PDFIO_INTERNAL;
 extern pdfio_stream_t	*_pdfioStreamOpen(pdfio_obj_t *obj, bool decode) _PDFIO_INTERNAL;

+extern char		*_pdfioStringAllocBuffer(pdfio_file_t *pdf);
+extern void		_pdfioStringFreeBuffer(pdfio_file_t *pdf, char *buffer);
 extern bool		_pdfioStringIsAllocated(pdfio_file_t *pdf, const char *s) _PDFIO_INTERNAL;

 extern void		_pdfioTokenClear(_pdfio_token_t *tb) _PDFIO_INTERNAL;
--- a/pdfio-string.c
+++ b/pdfio-string.c
@ -532,6 +532,41 @@ _pdfio_vsnprintf(pdfio_file_t *pdf,	// I - PDF file
 }


+//
+// '_pdfioStringAllocBuffer()' - Allocate a string buffer.
+//
+
+char *					// O - Buffer or `NULL` on error
+_pdfioStringAllocBuffer(
+    pdfio_file_t *pdf)			// I - PDF file
+{
+  _pdfio_strbuf_t	*current;	// Current string buffer
+
+
+  // See if we have an available string buffer...
+  for (current = pdf->strbuffers; current; current = current->next)
+  {
+    if (!current->bufused)
+    {
+      current->bufused = true;
+      return (current->buffer);
+    }
+  }
+
+  // Didn't find one, allocate a new one...
+  if ((current = calloc(1, sizeof(_pdfio_strbuf_t))) == NULL)
+    return (NULL);
+
+  // Add to the linked list of string buffers...
+  current->next    = pdf->strbuffers;
+  current->bufused = true;
+
+  pdf->strbuffers = current;
+
+  return (current->buffer);
+}
+
+
 //
 // 'pdfioStringCreate()' - Create a durable literal string.
 //
@ -642,6 +677,29 @@ pdfioStringCreatef(
 }


+//
+// '_pdfioStringFreeBuffer()' - Free a string buffer.
+//
+
+void
+_pdfioStringFreeBuffer(
+    pdfio_file_t *pdf,			// I - PDF file
+    char         *buffer)		// I - String buffer
+{
+  _pdfio_strbuf_t	*current;	// Current string buffer
+
+
+  for (current = pdf->strbuffers; current; current = current->next)
+  {
+    if (current->buffer == buffer)
+    {
+      current->bufused = false;
+      break;
+    }
+  }
+}
+
+
 //
 // '_pdfioStringIsAllocated()' - Check whether a string has been allocated.
 //
--- a/pdfio-token.c
+++ b/pdfio-token.c
@ -1,7 +1,7 @@
 //
 // PDF token parsing functions for PDFio.
 //
-// Copyright © 2021-2023 by Michael R Sweet.
+// Copyright © 2021-2025 by Michael R Sweet.
 //
 // Licensed under Apache License v2.0.  See the file "LICENSE" for more
 // information.
@ -528,13 +528,6 @@ _pdfioTokenRead(_pdfio_token_t *tb,	// I - Token buffer/stack
 	    return (false);
 	  }
 	}
-
-	if (bufptr == (buffer + 1))
-	{
-	  _pdfioFileError(tb->pdf, "Empty name.");
-	  *bufptr = '\0';
-	  return (false);
-	}
 	break;

    case '<' : // Potential hex string
--- a/pdfio-value.c
+++ b/pdfio-value.c
@ -125,7 +125,7 @@ _pdfioValueDecrypt(pdfio_file_t   *pdf,	// I - PDF file
  _pdfio_crypto_ctx_t	ctx;		// Decryption context
  _pdfio_crypto_cb_t	cb;		// Decryption callback
  size_t		ivlen;		// Number of initialization vector bytes
-  uint8_t		temp[32768];	// Temporary buffer for decryption
+  uint8_t		*temp = NULL;	// Temporary buffer for decryption
  size_t		templen;	// Number of actual data bytes
  time_t		timeval;	// Date/time value

@ -152,11 +152,16 @@ _pdfioValueDecrypt(pdfio_file_t   *pdf,	// I - PDF file

    case PDFIO_VALTYPE_BINARY :
 	// Decrypt the binary string...
-	if (v->value.binary.datalen > (sizeof(temp) - 32))
+	if (v->value.binary.datalen > PDFIO_MAX_STRING)
 	{
 	  _pdfioFileError(pdf, "Unable to read encrypted binary string - too long.");
 	  return (false);
 	}
+	else if ((temp = (uint8_t *)_pdfioStringAllocBuffer(pdf)) == NULL)
+	{
+	  _pdfioFileError(pdf, "Unable to read encrypted binary string - out of memory.");
+	  return (false);
+	}

 	ivlen = v->value.binary.datalen;
 	if ((cb = _pdfioCryptoMakeReader(pdf, obj, &ctx, v->value.binary.data, &ivlen)) == NULL)
@ -171,6 +176,8 @@ _pdfioValueDecrypt(pdfio_file_t   *pdf,	// I - PDF file
 	  v->value.binary.datalen = templen - temp[templen - 1];
 	else
 	  v->value.binary.datalen = templen;
+
+        _pdfioStringFreeBuffer(pdf, (char *)temp);
 	break;

    case PDFIO_VALTYPE_STRING :
@ -300,7 +307,9 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
                _pdfio_value_t *v,	// I - Value
                size_t         depth)	// I - Depth of value
 {
-  char		token[32768];		// Token buffer
+  _pdfio_value_t *ret = NULL;		// Return value
+  char		*token = _pdfioStringAllocBuffer(pdf);
+					// Token buffer
  time_t	timeval;		// Date/time value
 #ifdef DEBUG
  static const char * const valtypes[] =
@ -322,8 +331,11 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file

  PDFIO_DEBUG("_pdfioValueRead(pdf=%p, obj=%p, v=%p)\n", pdf, obj, v);

-  if (!_pdfioTokenGet(tb, token, sizeof(token)))
-    return (NULL);
+  if (!token)
+    goto done;
+
+  if (!_pdfioTokenGet(tb, token, PDFIO_MAX_STRING))
+    goto done;

  if (!strcmp(token, "["))
  {
@ -331,12 +343,14 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
    if (depth >= PDFIO_MAX_DEPTH)
    {
      _pdfioFileError(pdf, "Too many nested arrays.");
-      return (NULL);
+      goto done;
    }

    v->type = PDFIO_VALTYPE_ARRAY;
    if ((v->value.array = _pdfioArrayRead(pdf, obj, tb, depth + 1)) == NULL)
-      return (NULL);
+      goto done;
+
+    ret = v;
  }
  else if (!strcmp(token, "<<"))
  {
@ -344,29 +358,34 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
    if (depth >= PDFIO_MAX_DEPTH)
    {
      _pdfioFileError(pdf, "Too many nested dictionaries.");
-      return (NULL);
+      goto done;
    }

    v->type = PDFIO_VALTYPE_DICT;
    if ((v->value.dict = _pdfioDictRead(pdf, obj, tb, depth + 1)) == NULL)
-      return (NULL);
+      goto done;
+
+    ret = v;
  }
-  else if (!strncmp(token, "(D:", 3) && (timeval = get_date_time(token + 1)) != 0)
+  else if ((timeval = get_date_time(token + 1)) != 0)
  {
    v->type       = PDFIO_VALTYPE_DATE;
    v->value.date = timeval;
+    ret           = v;
  }
  else if (token[0] == '(')
  {
    // String
    v->type         = PDFIO_VALTYPE_STRING;
    v->value.string = pdfioStringCreate(pdf, token + 1);
+    ret           = v;
  }
  else if (token[0] == '/')
  {
    // Name
    v->type       = PDFIO_VALTYPE_NAME;
    v->value.name = pdfioStringCreate(pdf, token + 1);
+    ret           = v;
  }
  else if (token[0] == '<')
  {
@ -379,7 +398,7 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
    if ((v->value.binary.data = (unsigned char *)malloc(v->value.binary.datalen)) == NULL)
    {
      _pdfioFileError(pdf, "Out of memory for hex string.");
-      return (NULL);
+      goto done;
    }

    // Convert hex to binary...
@ -406,6 +425,8 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file

      *dataptr++ = (unsigned char)d;
    }
+
+    ret = v;
  }
  else if (strchr("0123456789-+.", token[0]) != NULL)
  {
@ -493,7 +514,8 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file

 	  PDFIO_DEBUG("_pdfioValueRead: Returning indirect value %lu %u R.\n", (unsigned long)v->value.indirect.number, v->value.indirect.generation);

-	  return (v);
+	  ret = v;
+	  goto done;
 	}
      }
    }
@ -501,27 +523,41 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
    // If we get here, we have a number...
    v->type         = PDFIO_VALTYPE_NUMBER;
    v->value.number = _pdfio_strtod(pdf, token);
+    ret             = v;
  }
  else if (!strcmp(token, "true") || !strcmp(token, "false"))
  {
    // Boolean value
    v->type          = PDFIO_VALTYPE_BOOLEAN;
    v->value.boolean = !strcmp(token, "true");
+    ret              = v;
  }
  else if (!strcmp(token, "null"))
  {
    // null value
    v->type = PDFIO_VALTYPE_NULL;
+    ret     = v;
  }
  else
  {
    _pdfioFileError(pdf, "Unexpected '%s' token seen.", token);
-    return (NULL);
  }

-  PDFIO_DEBUG("_pdfioValueRead: Returning %s value.\n", valtypes[v->type]);
+  done:

-  return (v);
+  if (token)
+    _pdfioStringFreeBuffer(pdf, token);
+
+  if (ret)
+  {
+    PDFIO_DEBUG("_pdfioValueRead: Returning %s value.\n", valtypes[ret->type]);
+    return (ret);
+  }
+  else
+  {
+    PDFIO_DEBUG("_pdfioValueRead: Returning NULL.\n");
+    return (NULL);
+  }
 }


@ -546,8 +582,10 @@ _pdfioValueWrite(pdfio_file_t   *pdf,	// I - PDF file
    case PDFIO_VALTYPE_BINARY :
        {
          size_t	databytes;	// Bytes to write
-          uint8_t	temp[32768],	// Temporary buffer for encryption
+          uint8_t	*temp = NULL,	// Temporary buffer for encryption
 			*dataptr;	// Pointer into data
+          bool          ret = false;	// Return value
+

          if (obj && pdf->encryption)
          {
@ -556,11 +594,16 @@ _pdfioValueWrite(pdfio_file_t   *pdf,	// I - PDF file
 	    _pdfio_crypto_cb_t cb;	// Encryption callback
 	    size_t	ivlen;		// Number of initialization vector bytes

-            if (v->value.binary.datalen > (sizeof(temp) - 32))
+            if (v->value.binary.datalen > PDFIO_MAX_STRING)
            {
 	      _pdfioFileError(pdf, "Unable to write encrypted binary string - too long.");
 	      return (false);
            }
+            else if ((temp = (uint8_t *)_pdfioStringAllocBuffer(pdf)) == NULL)
+            {
+	      _pdfioFileError(pdf, "Unable to write encrypted binary string - out of memory.");
+	      return (false);
+            }

 	    cb        = _pdfioCryptoMakeWriter(pdf, obj, &ctx, temp, &ivlen);
 	    databytes = (cb)(&ctx, temp + ivlen, v->value.binary.data, v->value.binary.datalen) + ivlen;
@ -573,18 +616,25 @@ _pdfioValueWrite(pdfio_file_t   *pdf,	// I - PDF file
          }

          if (!_pdfioFilePuts(pdf, "<"))
-            return (false);
+            goto bindone;

          for (; databytes > 1; databytes -= 2, dataptr += 2)
          {
            if (!_pdfioFilePrintf(pdf, "%02X%02X", dataptr[0], dataptr[1]))
-              return (false);
+              goto bindone;
          }

-          if (databytes > 0)
-            return (_pdfioFilePrintf(pdf, "%02X>", dataptr[0]));
-          else
-            return (_pdfioFilePuts(pdf, ">"));
+          if (databytes > 0 && !_pdfioFilePrintf(pdf, "%02X", dataptr[0]))
+            goto bindone;
+
+	  ret = _pdfioFilePuts(pdf, ">");
+
+          bindone:
+
+          if (temp)
+            _pdfioStringFreeBuffer(pdf, (char *)temp);
+
+          return (ret);
        }

    case PDFIO_VALTYPE_BOOLEAN :
@ -609,7 +659,7 @@ _pdfioValueWrite(pdfio_file_t   *pdf,	// I - PDF file
 	  if (obj && pdf->encryption)
 	  {
 	    // Write encrypted string...
-	    uint8_t	temp[32768],	// Encrypted bytes
+	    uint8_t	temp[64],	// Encrypted bytes
 			*tempptr;	// Pointer into encrypted bytes
 	    _pdfio_crypto_ctx_t ctx;	// Encryption context
 	    _pdfio_crypto_cb_t cb;	// Encryption callback
@ -660,7 +710,7 @@ _pdfioValueWrite(pdfio_file_t   *pdf,	// I - PDF file
        if (obj && pdf->encryption)
        {
          // Write encrypted string...
-          uint8_t	temp[32768],	// Encrypted bytes
+          uint8_t	*temp = NULL,	// Encrypted bytes
 			*tempptr;	// Pointer into encrypted bytes
          _pdfio_crypto_ctx_t ctx;	// Encryption context
          _pdfio_crypto_cb_t cb;	// Encryption callback
@ -668,29 +718,41 @@ _pdfioValueWrite(pdfio_file_t   *pdf,	// I - PDF file
 					// Length of value
 			ivlen,		// Number of initialization vector bytes
 			tempbytes;	// Number of output bytes
+	  bool		ret = false;	// Return value

-          if (len > (sizeof(temp) - 32))
+          if (len > PDFIO_MAX_STRING)
          {
            _pdfioFileError(pdf, "Unable to write encrypted string - too long.");
            return (false);
          }
+          else if ((temp = (uint8_t *)_pdfioStringAllocBuffer(pdf)) == NULL)
+          {
+            _pdfioFileError(pdf, "Unable to write encrypted string - out of memory.");
+            return (false);
+          }

          cb        = _pdfioCryptoMakeWriter(pdf, obj, &ctx, temp, &ivlen);
          tempbytes = (cb)(&ctx, temp + ivlen, (const uint8_t *)v->value.string, len) + ivlen;

          if (!_pdfioFilePuts(pdf, "<"))
-            return (false);
+            goto strdone;

          for (tempptr = temp; tempbytes > 1; tempbytes -= 2, tempptr += 2)
          {
            if (!_pdfioFilePrintf(pdf, "%02X%02X", tempptr[0], tempptr[1]))
-              return (false);
+              goto strdone;
          }

-          if (tempbytes > 0)
-            return (_pdfioFilePrintf(pdf, "%02X>", *tempptr));
-          else
-	    return (_pdfioFilePuts(pdf, ">"));
+          if (tempbytes > 0 && !_pdfioFilePrintf(pdf, "%02X", *tempptr))
+            goto strdone;
+
+	  ret = _pdfioFilePuts(pdf, ">");
+
+          strdone :
+
+          _pdfioStringFreeBuffer(pdf, (char *)temp);
+
+          return (ret);
        }
        else
        {
@ -707,31 +769,59 @@ _pdfioValueWrite(pdfio_file_t   *pdf,	// I - PDF file
 // 'get_date_time()' - Convert PDF date/time value to time_t.
 //

-static time_t				// O - Time in seconds
+static time_t				// O - Time in seconds or `0` for none
 get_date_time(const char *s)		// I - PDF date/time value
 {
  int		i;			// Looping var
  struct tm	dateval;		// Date value
-  int		offset;			// Date offset
+  int		offset = 0;		// Date offset in seconds
+  time_t	t;			// Time value


  PDFIO_DEBUG("get_date_time(s=\"%s\")\n", s);

  // Possible date value of the form:
  //
-  //   (D:YYYYMMDDhhmmssZ)
-  //   (D:YYYYMMDDhhmmss+HH'mm)
-  //   (D:YYYYMMDDhhmmss-HH'mm)
+  //   D:YYYYMMDDhhmmssZ
+  //   D:YYYYMMDDhhmmss+HH'mm
+  //   D:YYYYMMDDhhmmss-HH'mm
  //

+  if (strncmp(s, "D:", 2))
+    return (0);
+
  for (i = 2; i < 16; i ++)
  {
+    // Look for date/time digits...
    if (!isdigit(s[i] & 255) || !s[i])
      break;
  }

-  if (i >= 16)
+  if (i < 6 || (i & 1))
  {
+    // Short year or missing digit...
+    return (0);
+  }
+
+  memset(&dateval, 0, sizeof(dateval));
+
+  dateval.tm_year = (s[2] - '0') * 1000 + (s[3] - '0') * 100 + (s[4] - '0') * 10 + s[5] - '0' - 1900;
+  if (i > 6)
+    dateval.tm_mon  = (s[6] - '0') * 10 + s[7] - '0' - 1;
+  if (i > 8)
+    dateval.tm_mday = (s[8] - '0') * 10 + s[9] - '0';
+  else
+    dateval.tm_mday = 1;
+  if (i > 10)
+    dateval.tm_hour = (s[10] - '0') * 10 + s[11] - '0';
+  if (i > 12)
+    dateval.tm_min  = (s[12] - '0') * 10 + s[13] - '0';
+  if (i > 14)
+    dateval.tm_sec  = (s[14] - '0') * 10 + s[15] - '0';
+
+  if (i >= 16 && s[i])
+  {
+    // Get zone info...
    if (s[i] == 'Z')
    {
      // UTC...
@ -742,14 +832,20 @@ get_date_time(const char *s)		// I - PDF date/time value
      // Timezone offset from UTC...
      if (isdigit(s[i + 1] & 255) && isdigit(s[i + 2] & 255) && s[i + 3] == '\'' && isdigit(s[i + 4] & 255) && isdigit(s[i + 5] & 255))
      {
+	offset = (s[i + 1] - '0') * 36000 + (s[i + 2] - '0') * 3600 + (s[i + 4] - '0') * 600 + (s[i + 5] - '0') * 60;
+	if (s[i] == '-')
+	  offset = -offset;
+
 	i += 6;
+
+	// Accept trailing quote, per PDF spec...
 	if (s[i] == '\'')
 	  i ++;
      }
    }
-    else if (!s[i])
+    else
    {
-      // Missing zone info, invalid date string...
+      // Random zone info, invalid date string...
      return (0);
    }
  }
@ -760,26 +856,24 @@ get_date_time(const char *s)		// I - PDF date/time value
    return (0);
  }

-  // Date value...
-  memset(&dateval, 0, sizeof(dateval));
+  // Convert date value to time_t...
+#if _WIN32
+  if ((t = _mkgmtime(&dateval)) < 0)
+    return (0);
+#elif defined(HAVE_TIMEGM)
+  if ((t = timegm(&dateval)) < 0)
+    return (0);
+#else
+  if ((t = mktime(&dateval)) < 0)
+    return (0);

-  dateval.tm_year = (s[2] - '0') * 1000 + (s[3] - '0') * 100 + (s[4] - '0') * 10 + s[5] - '0' - 1900;
-  dateval.tm_mon  = (s[6] - '0') * 10 + s[7] - '0' - 1;
-  dateval.tm_mday = (s[8] - '0') * 10 + s[9] - '0';
-  dateval.tm_hour = (s[10] - '0') * 10 + s[11] - '0';
-  dateval.tm_min  = (s[12] - '0') * 10 + s[13] - '0';
-  dateval.tm_sec  = (s[14] - '0') * 10 + s[15] - '0';
+#  if defined(HAVE_TM_GMTOFF)
+  localtime_r(&t, &dateval);
+  t -= dateval.tm_gmtoff;
+#  else
+  t -= timezone;
+#  endif // HAVE_TM_GMTOFF
+#endif // _WIN32

-  if (s[16] == 'Z')
-  {
-    offset = 0;
-  }
-  else
-  {
-    offset = (s[17] - '0') * 600 + (s[18] - '0') * 60 + (s[19] - '0') * 10 + s[20] - '0';
-    if (s[16] == '-')
-      offset = -offset;
-  }
-
-  return (mktime(&dateval) + offset);
+  return (t + offset);
 }
--- a/pdfio.h
+++ b/pdfio.h
@ -23,7 +23,7 @@ extern "C" {
 // Version numbers...
 //

-#  define PDFIO_VERSION		"1.5.1"
+#  define PDFIO_VERSION		"1.5.2"
 #  define PDFIO_VERSION_MAJOR	1
 #  define PDFIO_VERSION_MINOR	5
Author	SHA1	Message	Date
Michael R Sweet	130cef8702	Update pdfioinfo example to support Acrobat Form dictionaries as well as indirect references (Issue #114 )	2025-04-04 21:24:42 -04:00
Michael R Sweet	0bd9edc845	Move token buffers off the stack (Issue #117 )	2025-04-04 21:20:23 -04:00
Michael R Sweet	fe755eac3d	Add PDFIO_MAX_STRING constant to control maximum allowed PDF strings (Issue #117 )	2025-04-04 19:27:03 -04:00
Michael R Sweet	8cca645835	Update date/time parsing (Issue #115 )	2025-04-04 19:12:16 -04:00
Michael R Sweet	b8ea9ea064	Bump version.	2025-04-04 19:11:54 -04:00
Michael R Sweet	2874022aa4	Allow empty name tokens (Issue #116 )	2025-04-04 18:26:35 -04:00
Michael R Sweet	3befcf2fd5	Fix warning about shadowed loop variable.	2025-04-04 18:17:04 -04:00