Update date/time parsing (Issue #115)

CHANGES.md

@@ -5,6 +5,7 @@ Changes in PDFio
 v1.5.2 - YYYY-MM-DD
 -------------------
 
+- Fixed parsing of certain date/time values (Issue #115)
 - Fixed support for empty name values (Issue #116)
 
 

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.71 for pdfio 1.5.1.
+# 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_VERSION='1.5.2'
-PACKAGE_STRING='pdfio 1.5.1'
+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="1.5.2"
-PDFIO_VERSION_MAJOR="`echo 1.5.1 | awk -F. '{print $1}'`"
+PDFIO_VERSION_MAJOR="`echo 1.5.2 | awk -F. '{print $1}'`"
-PDFIO_VERSION_MINOR="`echo 1.5.1 | awk -F. '{printf("%d\n",$2);}'`"
+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\\"
 

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])
 

pdfio-value.c

@@ -351,7 +351,7 @@ _pdfioValueRead(pdfio_file_t   *pdf,	// I - PDF file
     if ((v->value.dict = _pdfioDictRead(pdf, obj, tb, depth + 1)) == NULL)
       return (NULL);
   }
-  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;
@@ -707,31 +707,59 @@ _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:YYYYMMDDhhmmssZ
-  //   (D:YYYYMMDDhhmmss+HH'mm)
+  //   D:YYYYMMDDhhmmss+HH'mm
-  //   (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 +770,20 @@ 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 +794,24 @@ get_date_time(const char *s)		// I - PDF date/time value
     return (0);
   }
 
-  // Date value...
+  // Convert date value to time_t...
-  memset(&dateval, 0, sizeof(dateval));
+#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;
+#  if defined(HAVE_TM_GMTOFF)
-  dateval.tm_mon  = (s[6] - '0') * 10 + s[7] - '0' - 1;
+  localtime_r(&t, &dateval);
-  dateval.tm_mday = (s[8] - '0') * 10 + s[9] - '0';
+  t -= dateval.tm_gmtoff;
-  dateval.tm_hour = (s[10] - '0') * 10 + s[11] - '0';
+#  else
-  dateval.tm_min  = (s[12] - '0') * 10 + s[13] - '0';
+  t -= timezone;
-  dateval.tm_sec  = (s[14] - '0') * 10 + s[15] - '0';
+#  endif // HAVE_TM_GMTOFF
+#endif // _WIN32
 
-  if (s[16] == 'Z')
+  return (t + offset);
-  {
-    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);
 }