update

Author: maxxbw

lib/utils/CSVUtil.java

@@ -1,7 +1,6 @@
 package javaToolkit.lib.utils;
 
 import java.io.FileWriter;
-import java.io.Writer;
 import java.nio.file.Path;
 import java.util.ArrayList;
 import java.util.List;

lib/utils/CollectionUtil.java

@@ -4,31 +4,39 @@
 
 public class CollectionUtil {
 
-    /**
-     * https://stackoverflow.com/a/109389/4315608
-     *
-     * @param map
-     * @param <K>
-     * @param <V>
-     * @return
-     */
-    public static <K, V> Map<K, V> sortByValue(Map<K, V> map) {
-        List<Map.Entry<K, V>> list = new LinkedList<>(map.entrySet());
-        Collections.sort(list, new Comparator<Object>() {
-            @SuppressWarnings("unchecked")
-            public int compare(Object o1, Object o2) {
-                return ((Comparable<V>) ((Map.Entry<K, V>) (o1)).getValue()).compareTo(((Map.Entry<K, V>) (o2)).getValue());
-            }
-        });
+	/**
+	 * https://stackoverflow.com/a/109389/4315608
+	 *
+	 * @param map
+	 * @param <K>
+	 * @param <V>
+	 * @return
+	 */
+	public static <K, V> Map<K, V> sortByValue(Map<K, V> map) {
+		List<Map.Entry<K, V>> list = new LinkedList<>(map.entrySet());
+		Collections.sort(list, new Comparator<Object>() {
+			@SuppressWarnings("unchecked")
+			public int compare(Object o1, Object o2) {
+				return ((Comparable<V>) ((Map.Entry<K, V>) (o1)).getValue())
+						.compareTo(((Map.Entry<K, V>) (o2)).getValue());
+			}
+		});
 
-        Map<K, V> result = new LinkedHashMap<>();
-        for (Iterator<Map.Entry<K, V>> it = list.iterator(); it.hasNext(); ) {
-            Map.Entry<K, V> entry = (Map.Entry<K, V>) it.next();
-            result.put(entry.getKey(), entry.getValue());
-        }
+		Map<K, V> result = new LinkedHashMap<>();
+		for (Iterator<Map.Entry<K, V>> it = list.iterator(); it.hasNext();) {
+			Map.Entry<K, V> entry = (Map.Entry<K, V>) it.next();
+			result.put(entry.getKey(), entry.getValue());
+		}
 
-        return result;
-    }
+		return result;
+	}
 
+	public static Set<Object> mergeMultipleSet(List<Set<Object>> multiSet) {
+		Set<Object> mergeSet = new HashSet<>();
+		for (Set<Object> set : multiSet) {
+			mergeSet.addAll(set);
+		}
+		return mergeSet;
+	}
 
 }

lib/utils/GitUtil.java

@@ -3,10 +3,31 @@
 import java.nio.file.Path;
 import java.nio.file.Paths;
 import java.util.Arrays;
+import java.util.Date;
+import java.util.HashSet;
 import java.util.List;
+import java.util.Set;
 
 public class GitUtil {
 
+	public static void main(String[] args) {
+		Path repoDir = Paths.get("/data/bowen/data/PTBench-Data/data/2019/quarkusio#gizmo/raw_github");
+		Set<String> mergeSet = new HashSet<>();
+		Set<String> bugComs = new HashSet<String>(getComsWithSingleWordMatch(repoDir, "bug"));
+		System.out.println("# bug coms " + String.valueOf(bugComs.size()));
+		mergeSet.addAll(bugComs);
+		Set<String> BugComs = new HashSet<String>(getComsWithSingleWordMatch(repoDir, "Bug"));
+		System.out.println("# Bug coms " + String.valueOf(BugComs.size()));
+		mergeSet.addAll(BugComs);
+		Set<String> fixComs = new HashSet<String>(getComsWithSingleWordMatch(repoDir, "fix"));
+		System.out.println("# fix coms " + String.valueOf(fixComs.size()));
+		mergeSet.addAll(fixComs);
+		Set<String> FixComs = new HashSet<String>(getComsWithSingleWordMatch(repoDir, "Fix"));
+		System.out.println("# Fix coms " + String.valueOf(FixComs.size()));
+		mergeSet.addAll(FixComs);
+		System.out.println("# merge coms " + String.valueOf(mergeSet.size()));
+	}
+
 	public static Boolean clone(String repoName, String usrName, Path targetDir) {
 
 		if (targetDir.toFile().exists()) {
@@ -32,9 +53,28 @@ public static Boolean clone(String repoName, String usrName, Path targetDir) {
 	public static List<String> getAllCommitsSha(Path repoDir) {
 
 		String cmd = "timeout 300 git --no-pager log --all --pretty=format:\"%H\"";
-		
+
+		ProcessUtil.ProcessReporter pr = ProcessUtil.executeCMD(cmd, null, repoDir, 0);
+		if (pr.exitCode == 0) {
+			return Arrays.asList(pr.out.replace("\"", "").split("\n"));
+		} else {
+			FileUtil.writeStr2File(pr.out, Paths.get(repoDir.toString(), "getAllCommitsSha_out.txt"));
+			FileUtil.writeStr2File(pr.err, Paths.get(repoDir.toString(), "getAllCommitsSha_err.txt"));
+			// System.out.println("cmd " + cmd + "\n");
+			// System.out.println("report \n" + pr.toString());
+			return null;
+		}
+	}
+
+	public static List<String> getComsWithSingleWordMatch(Path repoDir, String word) {
+
+		String cmd = "timeout 300 git --no-pager log --all --pretty=format:\"%H\" --grep=" + word.trim();
+
 		ProcessUtil.ProcessReporter pr = ProcessUtil.executeCMD(cmd, null, repoDir, 0);
 		if (pr.exitCode == 0) {
+			if ("".equals(pr.out.trim())) {
+				return null;
+			}
 			return Arrays.asList(pr.out.replace("\"", "").split("\n"));
 		} else {
 			FileUtil.writeStr2File(pr.out, Paths.get(repoDir.toString(), "getAllCommitsSha_out.txt"));