[svn-r20676] Purpose:

    - HDFFV-5928 - GMQS: h5diff problem and improvement on comparsing the same objects

Description:
    Fixed:
    1) adding h5tools_is_obj_same() function to check if two given IDs or paths point to the same object. This function can be very useful for other tools and applications.
    2) using h5tools_is_obj_same() at h5diff() and diff() in h5diff.c. If two paths point to the same object, there is no need to check the details of the object since we know there is no difference. The fix will increase the performance by skipping the content comparison. It also fixed the problem of reporting difference for some cases of comparing the same file, e.g. empty files or files with incomparable objects the same file.

    Test update:
    Updat prvious test cases (171, 172, 530) affected by this fix, so they
    still perfrom originally intended testing without bypassing.

Tested:
 jam (linux32-LE), koala (linux64-LE), heiwa (linuxppc64-BE), tejeda (mac32-LE), linew (solaris-BE), cmake

3 files changed, 116 insertions, 7 deletions

diff --git a/tools/lib/h5diff.c b/tools/lib/h5diff.c
index a4d8469..4f82906 100644
--- a/tools/lib/h5diff.c
+++ b/tools/lib/h5diff.c
@@ -932,6 +932,19 @@ hsize_t h5diff(const char *fname1,
     /* if both obj1 and obj2 are group */
     if (obj1type == H5TRAV_TYPE_GROUP && obj2type == H5TRAV_TYPE_GROUP)
     {
+
+        /* 
+         * Use h5tools_is_obj_same() to improve performance by skipping 
+         * comparing details of same objects. If verbose options is used,
+         * need to traverse thorugh the list of objects in the group and
+         * print out object information. Details of same objects will be 
+         * skipped at diff() function.
+         */
+         if(!(options->m_verbose || options->m_report)) {
+             if (h5tools_is_obj_same(file1_id,obj1fullname,file2_id,obj2fullname)!=0)
+                 goto out;
+         }
+
         /* 
          * traverse group1 
          */
@@ -1773,6 +1786,7 @@ hsize_t diff(hid_t file1_id,
     int     ret;
     int     is_dangle_link1 = 0;
     int     is_dangle_link2 = 0;
+    int     is_hard_link = 0;
     hsize_t nfound = 0;
 
 
@@ -1834,6 +1848,58 @@ hsize_t diff(hid_t file1_id,
     /* found dangling link */
     if (is_dangle_link1 || is_dangle_link2)
         goto out2;
+  
+    /* 
+     * Use h5tools_is_obj_same() to improve performance by skipping 
+     * comparing details of same objects,
+     * 
+     * check if two paths point to the same object for hard links or 
+     * the option of follow link is used. h5tools_is_obj_same() is not
+     * needed for other cases.
+     */
+    is_hard_link = (type==H5TRAV_TYPE_DATASET ||
+                    type==H5TRAV_TYPE_NAMED_DATATYPE ||
+                    type==H5TRAV_TYPE_GROUP);
+     if (options->follow_links || is_hard_link)
+     {
+        if (h5tools_is_obj_same(file1_id, path1, file2_id, path2)!=0)
+        {
+            /* print information is only verbose option is used */
+            if(options->m_verbose || options->m_report)
+            {
+                switch(type)
+                {
+                case H5TRAV_TYPE_DATASET:
+                    do_print_objname("dataset", path1, path2, options);
+                    break; 
+                case H5TRAV_TYPE_NAMED_DATATYPE:
+                    do_print_objname("datatype", path1, path2, options);
+                    break;
+                case H5TRAV_TYPE_GROUP:
+                    do_print_objname("group", path1, path2, options);
+                    break;
+                case H5TRAV_TYPE_LINK:
+                    do_print_objname("link", path1, path2, options);
+                    break;
+                case H5TRAV_TYPE_UDLINK:
+                    if(linkinfo1.linfo.type == H5L_TYPE_EXTERNAL && linkinfo2.linfo.type == H5L_TYPE_EXTERNAL)
+                        do_print_objname("external link", path1, path2, options);
+                    else
+                        do_print_objname ("user defined link", path1, path2, options);
+                    break; 
+                default:
+                    parallel_print("Comparison not supported: <%s> and <%s> are of type %s\n",
+                        path1, path2, get_type(type) );
+                    options->not_cmp = 1;
+                    break;
+                } /* switch(type)*/
+
+                print_found(nfound);
+            } /* if(options->m_verbose || options->m_report) */
+
+            goto out2;
+        } /* h5tools_is_obj_same */
+    }
 
     switch(type)
     {
diff --git a/tools/lib/h5tools.c b/tools/lib/h5tools.c
index bf85bc2..3e72bdd 100644
--- a/tools/lib/h5tools.c
+++ b/tools/lib/h5tools.c
@@ -626,11 +626,11 @@ h5tools_ncols(const char *s)
  *
  * Purpose: Recursive check for any variable length data in given type.
  *
- * Return: 
+ * Return:
  *    TRUE : type conatains any variable length data
  *    FALSE : type doesn't contain any variable length data
  *    Negative value: error occur
- * 
+ *
  * Programmer: Jonathan Kim  March 18, 2011
  *-------------------------------------------------------------------------
  */
@@ -658,7 +658,7 @@ done:
  *
  * Purpose: Recursive check for variable length string of a datatype.
  *
- * Return: 
+ * Return:
  *    TRUE : type conatains any variable length string
  *    FALSE : type doesn't contain any variable length string
  *    Negative value: error occur
@@ -848,7 +848,7 @@ h5tools_region_simple_prefix(FILE *stream, const h5tool_format_t *info,
     }
 
     /* Calculate new prefix */
-    h5tools_str_region_prefix(&prefix, info, elmtno, ptdata, ctx->ndims, 
+    h5tools_str_region_prefix(&prefix, info, elmtno, ptdata, ctx->ndims,
             ctx->p_max_idx, ctx);
 
     /* Write new prefix to output */
@@ -2419,7 +2419,7 @@ h5tools_dump_simple_subset(FILE *stream, const h5tool_format_t *info, hid_t dset
     /* Terminate the output */
     if (ctx.cur_column) {
         fputs(OPT(info->line_suf, ""), stdout);
-        putc('\n', stdout); 
+        putc('\n', stdout);
         fputs(OPT(info->line_sep, ""), stdout);
     }
 
@@ -2527,7 +2527,7 @@ h5tools_dump_simple_dset(FILE *stream, const h5tool_format_t *info,
         vl_data = TRUE;
     if (H5Tdetect_class(p_type, H5T_VLEN) == TRUE)
         vl_data = TRUE;
- 
+
     /*
      * Determine the strip mine size and allocate a buffer. The strip mine is
      * a hyperslab whose size is manageable.
@@ -2545,7 +2545,7 @@ h5tools_dump_simple_dset(FILE *stream, const h5tool_format_t *info,
         }
     }
 
-    if(!sm_nbytes) 
+    if(!sm_nbytes)
         goto done;
 
     assert(sm_nbytes == (hsize_t)((size_t)sm_nbytes)); /*check for overflow*/
@@ -4323,3 +4323,45 @@ hbool_t h5tools_is_zero(const void *_mem, size_t size)
     return TRUE;
 }
 
+/*-------------------------------------------------------------------------
+ * Function:    h5tools_is_obj_same
+ *
+ * Purpose: Check if two given object IDs or link names point to the same object.
+ *
+ * Parameters:
+ *             hid_t loc_id1: location of the first object
+ *             char *name1:   link name of the first object.
+ *                             Use "." or NULL if loc_id1 is the object to be compared.
+ *             hid_t loc_id2: location of the second object
+ *             char *name1:   link name of the first object.
+ *                             Use "." or NULL if loc_id2 is the object to be compared.
+ *
+ * Return:  TRUE if it is the same object; FALSE otherwise.
+ *
+ * Programmer: Peter Cao
+ *             4/27/2011
+  *
+ *-------------------------------------------------------------------------
+ */
+hbool_t h5tools_is_obj_same(hid_t loc_id1, const char *name1,
+		                    hid_t loc_id2, const char *name2)
+{
+    H5O_info_t oinfo1,  oinfo2;
+    hbool_t ret_val = 0;
+
+    if ( name1 && strcmp(name1, "."))
+    	H5Oget_info_by_name(loc_id1, name1, &oinfo1, H5P_DEFAULT);
+    else
+    	H5Oget_info(loc_id1, &oinfo1);
+
+    if ( name2 && strcmp(name2, "."))
+    	H5Oget_info_by_name(loc_id2, name2, &oinfo2, H5P_DEFAULT);
+    else
+    	H5Oget_info(loc_id2, &oinfo2);
+
+    if (oinfo1.fileno == oinfo2.fileno && oinfo1.addr==oinfo2.addr)
+    	ret_val = 1;
+
+    return ret_val;
+}
+
diff --git a/tools/lib/h5tools.h b/tools/lib/h5tools.h
index d08edf7..89e07fa 100644
--- a/tools/lib/h5tools.h
+++ b/tools/lib/h5tools.h
@@ -555,6 +555,7 @@ H5TOOLS_DLL hid_t    h5tools_get_big_endian_type(hid_t type);
 
 H5TOOLS_DLL htri_t   h5tools_detect_vlen(hid_t tid);
 H5TOOLS_DLL htri_t   h5tools_detect_vlen_str(hid_t tid);
+H5TOOLS_DLL hbool_t   h5tools_is_obj_same(hid_t loc_id1, const char *name1, hid_t loc_id2, const char *name2);
 
 H5TOOLS_DLL void     h5tools_dump_simple_data(FILE *stream, const h5tool_format_t *info, hid_t container,
                          h5tools_context_t *ctx/*in,out*/, unsigned flags,