[svn-r1697] Changes since 19990915

----------------------

./src/H5public.h
	We undefine a bunch of things that could get redefined in the config
	file because some customers have applications that include headers
	from multiple packages, all of which might be using autoconf.

	Include <stdint.h> for the C9x types.

./test/h5test.h
	More flushing of stdout for when testing is redirected down a pipe.

./tools/h5ls.c
	Added a `-S' or `--simple' switch which causes the output to be
	simplified somewhat for easier parsing by other scripts. For instance,
	characters are escaped using a very simple mechanism instead of C's
	more complicated backslash notation, data doesn't have `{}' or `[]'
	characters interspersed for compound and array types, and data is
	printed with exactly one element per line.  This switch is now used by
	an HDF5-to-HTML CGI script being developed for the DMF people.

./tools/h5tools.c
./tools/h5tools.h
	The repeat threshold which controls how strings are printed when a
	character repeats a bunch of times is now settable at runtime instead
	of compile time. The default is to show all characters, like

	   "abceeeeeeeeeeeeeeeeeeeeeeeeeeeeeefgh"

	But if you set it to something like 5 then any sequence of 5 or more
	characters is replaced by something shorter, like:

	   "abc" 'e'x30 "fgh"	  or

	Added an `str_locale' property which describes how to escape special
	characters in strings. The default is C-like escapes but an
	alternative is ESCAPE_HTML which replaces all non-alphanumeric
	characters with a 3-character HTML escape of the form `%XX'

	Fixed a bug where empty strings didn't even have the quote characters
	printed. Now empty strings show up as `""' instead of absolutely
	nothing.

	Added a `per_line' property which controls the maximum number of
	elements which will appear per line of output. The default is infinity
	but in practice the right margin causes line breaks. By setting the
	`per_line' value to one and the right margin to a very large value one
	can achieve output with exactly one element per line.

3 files changed, 166 insertions, 91 deletions

diff --git a/tools/h5ls.c b/tools/h5ls.c
index 191445a..4d4d978 100644
--- a/tools/h5ls.c
+++ b/tools/h5ls.c
@@ -41,6 +41,7 @@ static hbool_t recursive_g = FALSE;	/*recursive descent listing	     */
 static hbool_t grp_literal_g = FALSE;	/*list group, not contents	     */
 static hbool_t hexdump_g = FALSE;	/*show data as raw hexadecimal	     */
 static hbool_t show_errors_g = FALSE;	/*print HDF5 error messages	     */
+static hbool_t simple_output_g = FALSE;	/*make output more machine-readable  */
 
 /* Info to pass to the iteration functions */
 typedef struct iter_t {
@@ -108,6 +109,7 @@ usage: %s [OPTIONS] [OBJECTS...]\n\
       -l, --label      Label members of compound datasets\n\
       -r, --recursive  List all groups recursively, avoiding cycles\n\
       -s, --string     Print 1-byte integer datasets as ASCII\n\
+      -S, --simple     Use a machine-readable output format\n\
       -wN, --width=N   Set the number of columns of output\n\
       -v, --verbose    Generate more verbose output\n\
       -V, --version    Print version number and exit\n\
@@ -1098,7 +1100,9 @@ display_type(hid_t type, int ind)
  *              Tuesday, July 21, 1998
  *
  * Modifications:
- *
+ *		Robb Matzke, 1999-09-27
+ *		Understands the simple_output_g switch which causes data to
+ *		be displayed in a more machine-readable format.
  *-------------------------------------------------------------------------
  */
 static void
@@ -1107,21 +1111,41 @@ dump_dataset_values(hid_t dset)
     hid_t		f_type = H5Dget_type(dset);
     size_t		size = H5Tget_size(f_type);
     h5dump_t		info;
-
+    char		string_prefix[64];
+	
     /* Set to all default values and then override */
     memset(&info, 0, sizeof info);
-    info.idx_fmt = "(%s)";
-    info.line_ncols = width_g;
-    info.line_multi_new = 1;
-    if (label_g) info.cmpd_name = "%s=";
-    
-    /*
-     * If a compound datatype is split across multiple lines then indent
-     * the continuation line.
-     */
-    info.line_pre  = "        %s ";
-    info.line_cont = "        %s  ";
 
+    if (simple_output_g) {
+	info.idx_fmt = "";
+	info.line_ncols = 65535; /*something big*/
+	info.line_per_line = 1;
+	info.line_multi_new = 0;
+	info.line_pre  = "        ";
+	info.line_cont = "         ";
+	
+	info.arr_pre = "";
+	info.arr_suf = "";
+	info.arr_sep = " ";
+
+	info.cmpd_pre = "";
+	info.cmpd_suf = "";
+	info.cmpd_sep = " ";
+	if (label_g) info.cmpd_name = "%s=";
+	
+	info.elmt_suf1 = " ";
+	info.str_locale = ESCAPE_HTML;
+	
+    } else {
+	info.idx_fmt = "(%s)";
+	info.line_ncols = width_g;
+	info.line_multi_new = 1;
+	if (label_g) info.cmpd_name = "%s=";
+	info.line_pre  = "        %s ";
+	info.line_cont = "        %s  ";
+	info.str_repeat = 8;
+    }
+    
     if (hexdump_g) {
 	/*
 	 * Print all data in hexadecimal format if the `-x' or `--hexdump'
@@ -1136,7 +1160,9 @@ dump_dataset_values(hid_t dset)
 	info.ascii = TRUE;
 	info.elmt_suf1 = "";
 	info.elmt_suf2 = "";
-	info.line_pre ="        %s \"";
+	strcpy(string_prefix, info.line_pre);
+	strcat(string_prefix, "\"");
+	info.line_pre = string_prefix;
 	info.line_suf = "\"";
     }
     
@@ -1211,12 +1237,14 @@ list_attr (hid_t obj, const char *attr_name, void UNUSED *op_data)
 	    info.line_1st  = "        Data:  ";
 	    info.line_pre  = "               ";
 	    info.line_cont = "                ";
+	    info.str_repeat = 8;
 	    
 	} else {
 	    printf("        Data:\n");
 	    info.idx_fmt = "(%s)";
 	    info.line_pre  = "            %s ";
 	    info.line_cont = "            %s  ";
+	    info.str_repeat = 8;
 	}
 	info.line_ncols = width_g;
 	if (label_g) info.cmpd_name = "%s=";
@@ -1924,6 +1952,8 @@ main (int argc, char *argv[])
 	} else if (!strcmp(argv[argno], "--recursive")) {
 	    recursive_g = TRUE;
 	    fullname_g = TRUE;
+	} else if (!strcmp(argv[argno], "--simple")) {
+	    simple_output_g = TRUE;
 	} else if (!strcmp(argv[argno], "--string")) {
 	    string_g = TRUE;
 	} else if (!strncmp(argv[argno], "--width=", 8)) {
@@ -1996,6 +2026,9 @@ main (int argc, char *argv[])
 		    recursive_g = TRUE;
 		    fullname_g = TRUE;
 		    break;
+		case 'S':	/* --simple */
+		    simple_output_g = TRUE;
+		    break;
 		case 's':	/* --string */
 		    string_g = TRUE;
 		    break;
diff --git a/tools/h5tools.c b/tools/h5tools.c
index 36ce038..5dbb7ff 100644
--- a/tools/h5tools.c
+++ b/tools/h5tools.c
@@ -61,12 +61,6 @@ int print_data(hid_t oid, hid_t _p_type, int obj_data);
 #define REPEAT_VERBOSE
 
 /*
- * This is the original value of the repeat_threshold in the h5dump_sprint
- * function.
- */
-#define H5DEFAULT_REPEAT_THRESHOLD 8
-
-/*
  * The output functions need a temporary buffer to hold a piece of the
  * dataset while it's being printed.  This constant sets the limit on the
  * size of that temporary buffer in bytes.  For efficiency's sake, choose the
@@ -97,6 +91,7 @@ typedef struct h5dump_str_t {
 /* Output variables */
 typedef struct h5dump_context_t {
     size_t		cur_column;	/*current column for output	*/
+    size_t		cur_elmt;	/*current element/output line	*/
     int			need_prefix;	/*is line prefix needed?	*/
     int			ndims;		/*dimensionality		*/
     hsize_t		p_min_idx[H5S_MAX_RANK]; /*min selected index	*/
@@ -613,11 +608,6 @@ h5dump_sprint(h5dump_str_t *str/*in,out*/, const h5dump_t *info,
     static char	fmt_llong[8], fmt_ullong[8];
     H5T_str_t 	pad;
     H5G_stat_t	sb;
-    int		repeat_threshold = H5DEFAULT_REPEAT_THRESHOLD;
-
-	if (programtype == H5DUMP){
-		repeat_threshold = -1; /*-1 means any amount of repeat allowed*/
-    }
     
     /* Build default formats for long long types */
     if (!fmt_llong[0]) {
@@ -645,37 +635,45 @@ h5dump_sprint(h5dump_str_t *str/*in,out*/, const h5dump_t *info,
     } else if (info->ascii &&
 	       (H5Tequal(type, H5T_NATIVE_SCHAR) ||
 		H5Tequal(type, H5T_NATIVE_UCHAR))) {
-	switch (*((char*)vp)) {
-	case '"':
-	    h5dump_str_append(str, "\\\"");
-	    break;
-	case '\\':
-	    h5dump_str_append(str, "\\\\");
-	    break;
-	case '\b':
-	    h5dump_str_append(str, "\\b");
-	    break;
-	case '\f':
-	    h5dump_str_append(str, "\\f");
-	    break;
-	case '\n':
-	    h5dump_str_append(str, "\\n");
-	    break;
-	case '\r':
-	    h5dump_str_append(str, "\\r");
-	    break;
-	case '\t':
-	    h5dump_str_append(str, "\\t");
-	    break;
-	default:
-	    if (isprint((int)(*((char*)vp)))) {
-		h5dump_str_append(str, "%c", *((char*)vp));
+	if (ESCAPE_HTML==info->str_locale) {
+	    if (*((char*)vp)<=' ' || *((char*)vp)>'~') {
+		h5dump_str_append(str, "%%%02X", *((unsigned char*)vp));
 	    } else {
-		h5dump_str_append(str, "\\%03o", *((unsigned char*)vp));
+		h5dump_str_append(str, "%c", *((char*)vp));
+	    }
+	} else {
+	    switch (*((char*)vp)) {
+	    case '"':
+		h5dump_str_append(str, "\\\"");
+		break;
+	    case '\\':
+		h5dump_str_append(str, "\\\\");
+		break;
+	    case '\b':
+		h5dump_str_append(str, "\\b");
+		break;
+	    case '\f':
+		h5dump_str_append(str, "\\f");
+		break;
+	    case '\n':
+		h5dump_str_append(str, "\\n");
+		break;
+	    case '\r':
+		h5dump_str_append(str, "\\r");
+		break;
+	    case '\t':
+		h5dump_str_append(str, "\\t");
+		break;
+	    default:
+		if (isprint(*((char*)vp))) {
+		    h5dump_str_append(str, "%c", *((char*)vp));
+		} else {
+		    h5dump_str_append(str, "\\%03o", *((unsigned char*)vp));
+		}
+		break;
 	    }
-	    break;
 	}
-	
+
     } else if (H5T_STRING==H5Tget_class(type)) {
 	size = H5Tget_size(type);
 	quote = '\0';
@@ -687,14 +685,12 @@ h5dump_sprint(h5dump_str_t *str/*in,out*/, const h5dump_t *info,
 			
 	    /*
 	     * Count how many times the next character repeats. If the
-	     * threshold is negative then that means it can repeat any number
+	     * threshold is zero then that means it can repeat any number
 	     * of times.
 	     */
-	    if (repeat_threshold >= 0) {
-		j=1;
+	    j=1;
+	    if (info->str_repeat>0) {
 		while (i+j<size && ((char*)vp)[i]==((char*)vp)[i+j]) j++;
-	    } else {
-		j = repeat_threshold - 1;
 	    }
 	    
 	    /*
@@ -703,7 +699,7 @@ h5dump_sprint(h5dump_str_t *str/*in,out*/, const h5dump_t *info,
 	     * the characters, then make sure the character to be repeated is
 	     * in it's own quote.
 	     */
-	    if (j>repeat_threshold) {
+	    if (info->str_repeat>0 && j>info->str_repeat) {
 		if (quote) h5dump_str_append(str, "%c", quote);
 		quote = '\'';
 		h5dump_str_append(str, "%s%c", i?" ":"", quote);
@@ -713,39 +709,48 @@ h5dump_sprint(h5dump_str_t *str/*in,out*/, const h5dump_t *info,
 	    }
 			
 	    /* Print the character */
-	    switch (((char*)vp)[i]) {
-	    case '"':
-		h5dump_str_append(str, "\\\"");
-		break;
-	    case '\\':
-		h5dump_str_append(str, "\\\\");
-		break;
-	    case '\b':
-		h5dump_str_append(str, "\\b");
-		break;
-	    case '\f':
-		h5dump_str_append(str, "\\f");
-		break;
-	    case '\n':
-		h5dump_str_append(str, "\\n");
-		break;
-	    case '\r':
-		h5dump_str_append(str, "\\r");
-		break;
-	    case '\t':
-		h5dump_str_append(str, "\\t");
-		break;
-	    default:
-		if (isprint((int)((char*)vp)[i])) {
-		    h5dump_str_append(str, "%c", ((char*)vp)[i]);
+	    if (ESCAPE_HTML==info->str_locale) {
+		if (((char*)vp)[i]<=' ' || ((char*)vp)[i]>'~') {
+		    h5dump_str_append(str, "%%%02X", ((unsigned char*)vp)[i]);
 		} else {
-		    h5dump_str_append(str, "\\%03o", ((unsigned char*)vp)[i]);
+		    h5dump_str_append(str, "%c", ((char*)vp)[i]);
+		}
+	    } else {
+		switch (((char*)vp)[i]) {
+		case '"':
+		    h5dump_str_append(str, "\\\"");
+		    break;
+		case '\\':
+		    h5dump_str_append(str, "\\\\");
+		    break;
+		case '\b':
+		    h5dump_str_append(str, "\\b");
+		    break;
+		case '\f':
+		    h5dump_str_append(str, "\\f");
+		    break;
+		case '\n':
+		    h5dump_str_append(str, "\\n");
+		    break;
+		case '\r':
+		    h5dump_str_append(str, "\\r");
+		    break;
+		case '\t':
+		    h5dump_str_append(str, "\\t");
+		    break;
+		default:
+		    if (isprint(((char*)vp)[i])) {
+			h5dump_str_append(str, "%c", ((char*)vp)[i]);
+		    } else {
+			h5dump_str_append(str, "\\%03o",
+					  ((unsigned char*)vp)[i]);
+		    }
+		    break;
 		}
-		break;
 	    }
-			
+	    
 	    /* Print the repeat count */
-	    if (j>repeat_threshold) {
+	    if (info->str_repeat && j>info->str_repeat) {
 #ifdef REPEAT_VERBOSE
 		h5dump_str_append(str, "%c repeats %d times", quote, j-1);
 #else
@@ -756,6 +761,11 @@ h5dump_sprint(h5dump_str_t *str/*in,out*/, const h5dump_t *info,
 	    }
 	}
 	if (quote) h5dump_str_append(str, "%c", quote);
+
+	if (0==i) {
+	    h5dump_str_append(str, "\"\"");	/*empty string*/
+	}
+	
 		
     } else if (H5Tequal(type, H5T_NATIVE_INT)) {
 	h5dump_str_append(str, OPT(info->fmt_int, "%d"),
@@ -1001,7 +1011,9 @@ h5dump_ncols(const char *s)
  *              Monday, April 26, 1999
  *
  * Modifications:
- *
+ *		Robb Matzke, 1999-09-29
+ *		If a new prefix is printed then the current element number is
+ *		set back to zero.
  *-------------------------------------------------------------------------
  */
 static void
@@ -1036,6 +1048,7 @@ h5dump_simple_prefix(FILE *stream, const h5dump_t *info,
 	      stream);
     }
     ctx->cur_column = ctx->prev_prefix_len = h5dump_str_len(&prefix);
+    ctx->cur_elmt = 0;
     ctx->need_prefix = 0;
 
     /* Free string */
@@ -1065,6 +1078,10 @@ h5dump_simple_prefix(FILE *stream, const h5dump_t *info,
  *		The `container' argument is the optional dataset for
  *		reference types.
  *
+ * 		Robb Matzke, 1999-09-29
+ *		Understands the `per_line' property which indicates that
+ *		every Nth element should begin a new line.
+ *
  *-------------------------------------------------------------------------
  */
 static void
@@ -1087,7 +1104,7 @@ h5dump_simple_data(FILE *stream, const h5dump_t *info, hid_t container,
     if (info->line_ncols>0) ncols = info->line_ncols;
     h5dump_simple_prefix(stream, info, ctx, 0, 0);
     
-    for (i=0; i<nelmts; i++) {
+    for (i=0; i<nelmts; i++, ctx->cur_elmt++) {
 	
 	/* Render the element */
 	h5dump_str_reset(&buffer);
@@ -1135,6 +1152,14 @@ h5dump_simple_data(FILE *stream, const h5dump_t *info, hid_t container,
 	     strlen(OPT(info->line_suf, ""))) > ncols) {
 	    ctx->need_prefix = TRUE;
 	}
+
+	/*
+	 * If too many elements have already been printed then we need to
+	 * start a new line.
+	 */
+	if (info->line_per_line>0 && ctx->cur_elmt>=info->line_per_line) {
+	    ctx->need_prefix = TRUE;
+	}
 	
 	/*
 	 * Each OPTIONAL_LINE_BREAK embedded in the rendered string can cause
diff --git a/tools/h5tools.h b/tools/h5tools.h
index da63be0..d962cee 100644
--- a/tools/h5tools.h
+++ b/tools/h5tools.h
@@ -13,6 +13,8 @@
 #include <hdf5.h>
 #include <stdio.h>
 
+#define ESCAPE_HTML	1
+
 /*
  * Information about how to format output.
  */
@@ -77,6 +79,15 @@ typedef struct h5dump_t {
      *		     escape.  If `ascii' is zero then then 1-byte integers are
      *		     printed as numeric values.  The default is zero.
      *
+     *	 str_locale: Determines how strings are printed. If zero then strings
+     *		     are printed like in C except. If set to ESCAPE_HTML then
+     *		     strings are printed using HTML encoding where each
+     *		     character not in the class [a-zA-Z0-9] is substituted
+     *		     with `%XX' where `X' is a hexadecimal digit.
+     *
+     *	 str_repeat: If set to non-zero then any character value repeated N
+     *		     or more times is printed as 'C'*N
+     *
      * Numeric data is also subject to the formats for individual elements.
      */
     hbool_t	raw;
@@ -94,6 +105,8 @@ typedef struct h5dump_t {
     const char	*fmt_double;
     const char	*fmt_float;
     int		ascii;
+    int		str_locale;
+    int		str_repeat;
 
     /*
      * Fields associated with compound array members.
@@ -178,7 +191,10 @@ typedef struct h5dump_t {
     /*
      * Fields associated with entire lines.
      *
-     *   ncols:	    Number of columns per line defaults to 80.
+     *	 ncols:	    Number of columns per line defaults to 80.
+     *
+     *	 per_line:  If this field has a positive value then every Nth element
+     *	 	    will be printed at the beginning of a line.
      *
      *	 pre:       Each line of output contains an optional prefix area
      *		    before the data. This area can contain the index for the
@@ -224,6 +240,7 @@ typedef struct h5dump_t {
      *		    unless it wouldn't fit.
      */
     int		line_ncols;		/*columns of output		*/
+    size_t	line_per_line;		/*max elements per line		*/
     const char	*line_pre;		/*prefix at front of each line	*/
     const char	*line_1st;		/*alternate pre. on first line	*/
     const char	*line_cont;		/*alternate pre. on continuation*/