HDDS-11546. Add regex operation to filter option of ldb scan command. (…

…apache#7289)

(cherry picked from commit 256aad9)

hadoop-ozone/dist/src/main/smoketest/debug/ozone-debug-ldb.robot

@@ -110,6 +110,16 @@ Test ozone debug ldb scan with filter option success
                         Should not contain      ${output}       testfile1
                         Should not contain      ${output}       testfile2
                         Should not contain      ${output}       testfile3
+    # test filter option with regex matching numbers
+    ${output} =         Execute                 ozone debug ldb --db=/data/metadata/om.db scan --cf=keyTable --filter="dataSize:regex:^1[0-2]{3}$"
+                        Should contain          ${output}       testfile1
+                        Should not contain      ${output}       testfile2
+                        Should not contain      ${output}       testfile3
+    # test filter option with regex matching string
+    ${output} =         Execute                 ozone debug ldb --db=/data/metadata/om.db scan --cf=keyTable --filter="keyName:regex:^test.*[0-1]$"
+                        Should contain          ${output}       testfile1
+                        Should not contain      ${output}       testfile2
+                        Should not contain      ${output}       testfile3
 
 Test ozone debug ldb scan with filter option failure
     # test filter option with invalid operator

hadoop-ozone/integration-test/src/test/java/org/apache/hadoop/ozone/debug/TestLDBCli.java

@@ -120,6 +120,7 @@ public void shutdown() throws IOException {
   /**
    * Defines ldb tool test cases.
    */
+  @SuppressWarnings({"methodlength"})
   private static Stream<Arguments> scanTestCases() {
     return Stream.of(
         Arguments.of(
@@ -206,6 +207,19 @@ private static Stream<Arguments> scanTestCases() {
             Named.of("Filter dataSize>2000", Arrays.asList("--filter", "dataSize:greater:2000")),
             Named.of("Expect empty result", null)
         ),
+        Arguments.of(
+            Named.of(KEY_TABLE, Pair.of(KEY_TABLE, false)),
+            Named.of("Default", Pair.of(0, "")),
+            Named.of("Filter key3 regex", Arrays.asList("--filter", "keyName:regex:^.*3$")),
+            Named.of("Expect key3", Pair.of("key3", "key4"))
+        ),
+        Arguments.of(
+            Named.of(KEY_TABLE, Pair.of(KEY_TABLE, false)),
+            Named.of("Default", Pair.of(0, "")),
+            Named.of("Filter keys whose dataSize digits start with 5 using regex",
+                Arrays.asList("--filter", "dataSize:regex:^5.*$")),
+            Named.of("Expect empty result", null)
+        ),
         Arguments.of(
             Named.of(BLOCK_DATA + " V3", Pair.of(BLOCK_DATA, true)),
             Named.of("Default", Pair.of(0, "")),

hadoop-ozone/tools/src/main/java/org/apache/hadoop/ozone/debug/DBScanner.java

@@ -74,6 +74,8 @@
 import java.util.concurrent.ThreadPoolExecutor;
 import java.util.concurrent.TimeUnit;
 import java.util.concurrent.atomic.AtomicLong;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
 
 import static java.nio.charset.StandardCharsets.UTF_8;
 
@@ -132,9 +134,11 @@ public class DBScanner implements Callable<Void>, SubcommandWithParent {
   @CommandLine.Option(names = {"--filter"},
       description = "Comma-separated list of \"<field>:<operator>:<value>\" where " +
           "<field> is any valid field of the record, " +
-          "<operator> is (EQUALS,LESSER or GREATER) and " +
-          "<value> is the value of the field. " +
-          "eg.) \"dataSize:equals:1000\" for showing records having the value 1000 for dataSize")
+          "<operator> is [EQUALS,LESSER, GREATER or REGEX]. (EQUALS compares the exact string, " +
+          "REGEX compares with a valid regular expression passed, and LESSER/GREATER works with numeric values), " +
+          "<value> is the value of the field. \n" +
+          "eg.) \"dataSize:equals:1000\" for showing records having the value 1000 for dataSize, \n" +
+          "     \"keyName:regex:^key.*$\" for showing records having keyName that matches the given regex.")
   private String filter;
 
   @CommandLine.Option(names = {"--dnSchema", "--dn-schema", "-d"},
@@ -396,7 +400,6 @@ private boolean checkFilteredObject(Object obj, Class<?> clazz, Map<String, Filt
           throw new IOException("Invalid filter passed");
         } else if (fieldValue.getNextLevel() == null) {
           // reached the end of fields hierarchy, check if they match the filter
-          // Currently, only equals operation is supported
           try {
             switch (fieldValue.getOperator()) {
             case EQUALS:
@@ -416,8 +419,15 @@ private boolean checkFilteredObject(Object obj, Class<?> clazz, Map<String, Filt
                 return false;
               }
               break;
+            case REGEX:
+              Pattern p = Pattern.compile(String.valueOf(fieldValue.getValue()));
+              Matcher m = p.matcher(String.valueOf(valueObject));
+              if (!m.find()) {
+                return false;
+              }
+              break;
             default:
-              err().println("Only EQUALS/LESSER/GREATER operator is supported currently.");
+              err().println("Only EQUALS/LESSER/GREATER/REGEX operator is supported currently.");
               throw new IOException("Invalid filter passed");
             }
           } catch (NumberFormatException ex) {

hadoop-ozone/tools/src/main/java/org/apache/hadoop/ozone/utils/Filter.java

@@ -86,6 +86,8 @@ public FilterOperator getFilterOperator(String op) {
       return FilterOperator.GREATER;
     } else if (op.equalsIgnoreCase("LESSER")) {
       return FilterOperator.LESSER;
+    } else if (op.equalsIgnoreCase("REGEX")) {
+      return FilterOperator.REGEX;
     } else {
       return null;
     }
@@ -102,6 +104,7 @@ public String toString() {
   public enum FilterOperator {
     EQUALS,
     LESSER,
-    GREATER;
+    GREATER,
+    REGEX;
   }
 }