Mailing-List: contact commits-help@parquet.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@parquet.apache.org
Content-Type: text/plain; charset="us-ascii"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
From: blue@apache.org
To: commits@parquet.apache.org
Date: Fri, 28 Jul 2017 23:25:27 -0000
Message-Id: <1955db177fb54728b98a030942a9e18f@git.apache.org>
In-Reply-To: <baa6ecfdf1c74be9879ebda0c821fdfe@git.apache.org>
References: <baa6ecfdf1c74be9879ebda0c821fdfe@git.apache.org>
Subject: [2/4] parquet-mr git commit: PARQUET-777: Add Parquet CLI.
archived-at: Fri, 28 Jul 2017 23:25:30 -0000

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/java/org/apache/parquet/cli/util/Codecs.java
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/java/org/apache/parquet/cli/util/Codecs.java b/parquet-cli/src/main/java/org/apache/parquet/cli/util/Codecs.java
new file mode 100644
index 0000000..06f12fd
--- /dev/null
+++ b/parquet-cli/src/main/java/org/apache/parquet/cli/util/Codecs.java
@@ -0,0 +1,50 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.parquet.cli.util;
+
+import org.apache.avro.file.CodecFactory;
+import org.apache.parquet.hadoop.metadata.CompressionCodecName;
+
+import java.util.Locale;
+
+public class Codecs {
+  public static CompressionCodecName parquetCodec(String codec) {
+    try {
+      return CompressionCodecName.valueOf(codec.toUpperCase(Locale.ENGLISH));
+    } catch (IllegalArgumentException e) {
+      throw new IllegalArgumentException("Unknown compression codec: " + codec);
+    }
+  }
+
+  public static CodecFactory avroCodec(String codec) {
+    CompressionCodecName parquetCodec = parquetCodec(codec);
+    switch (parquetCodec) {
+      case UNCOMPRESSED:
+        return CodecFactory.nullCodec();
+      case SNAPPY:
+        return CodecFactory.snappyCodec();
+      case GZIP:
+        return CodecFactory.deflateCodec(9);
+      default:
+        throw new IllegalArgumentException(
+            "Codec incompatible with Avro: " + codec);
+    }
+  }
+}

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/java/org/apache/parquet/cli/util/Expressions.java
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/java/org/apache/parquet/cli/util/Expressions.java b/parquet-cli/src/main/java/org/apache/parquet/cli/util/Expressions.java
new file mode 100644
index 0000000..61f632a
--- /dev/null
+++ b/parquet-cli/src/main/java/org/apache/parquet/cli/util/Expressions.java
@@ -0,0 +1,391 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.parquet.cli.util;
+
+import com.google.common.base.Objects;
+import com.google.common.base.Preconditions;
+import com.google.common.collect.Lists;
+import org.apache.avro.Schema;
+import org.apache.avro.generic.GenericData;
+import org.apache.avro.generic.GenericRecord;
+import org.apache.avro.util.Utf8;
+import java.util.Collection;
+import java.util.List;
+import java.util.Map;
+import java.util.regex.Pattern;
+
+
+public class Expressions {
+  private static final Pattern NUMERIC_RE = Pattern.compile("^\\d+$");
+
+  public static Object select(Schema schema, Object datum, String path) {
+    return select(schema, datum, Lists.newArrayList(parse(path)));
+  }
+
+  @SuppressWarnings("unchecked")
+  private static Object select(Schema schema, Object datum, List<PathExpr> tokens) {
+    if (tokens.isEmpty()) {
+      return datum;
+    }
+
+    Preconditions.checkArgument(tokens.size() == 1, "Cannot return multiple values");
+    PathExpr token = tokens.get(0);
+
+    switch (schema.getType()) {
+      case RECORD:
+        if (!(datum instanceof GenericRecord) && "json".equals(schema.getName())) {
+          // skip the placeholder record schema
+          return select(schema.getField("value").schema(), datum, tokens);
+        }
+        Preconditions.checkArgument(token.type == PathExpr.Type.FIELD,
+            "Cannot dereference records");
+        Preconditions.checkArgument(datum instanceof GenericRecord,
+            "Not a record: %s", datum);
+        GenericRecord record = (GenericRecord) datum;
+        Schema.Field field = schema.getField(token.value);
+        Preconditions.checkArgument(field != null,
+            "No such field '%s' in schema: %s", token.value, schema);
+        return select(field.schema(), record.get(token.value), token.children);
+
+      case MAP:
+        Preconditions.checkArgument(datum instanceof Map,
+            "Not a map: %s", datum);
+        Map<Object, Object> map = (Map<Object, Object>) datum;
+        Object value = map.get(token.value);
+        if (value == null) {
+          // try with a Utf8
+          value = map.get(new Utf8(token.value));
+        }
+        return select(schema.getValueType(), value, token.children);
+
+      case ARRAY:
+        Preconditions.checkArgument(token.type == PathExpr.Type.DEREF,
+            "Cannot access fields of an array");
+        Preconditions.checkArgument(datum instanceof Collection,
+            "Not an array: %s", datum);
+        Preconditions.checkArgument(NUMERIC_RE.matcher(token.value).matches(),
+            "Not an array index: %s", token.value);
+        List<Object> list = (List<Object>) datum;
+        return select(schema.getElementType(), list.get(Integer.parseInt(token.value)),
+            token.children);
+
+      case UNION:
+        int branch = GenericData.get().resolveUnion(schema, datum);
+        return select(schema.getTypes().get(branch), datum, tokens);
+
+      default:
+        throw new IllegalArgumentException("Cannot access child of primitive value: " + datum);
+    }
+  }
+
+  /**
+   * a.2.b[3]["key"]
+   * * optional (union with null) should be ignored
+   * * unions should match by position number or short name (e.g. 2, user)
+   * * fields should match by name
+   * * arrays are dereferenced by position [n] =&gt; schema is the element schema
+   * * maps are dereferenced by key =&gt; schema is the value schema
+   */
+  public static Schema filterSchema(Schema schema, String... fieldPaths) {
+    return filterSchema(schema, Lists.newArrayList(fieldPaths));
+  }
+
+  public static Schema filterSchema(Schema schema, List<String> fieldPaths) {
+    if (fieldPaths == null) {
+      return schema;
+    }
+    List<PathExpr> paths = merge(Lists.newArrayList(fieldPaths));
+    return filter(schema, paths);
+  }
+
+  private static PathExpr parse(String path) {
+    PathExpr expr = null;
+    PathExpr last = null;
+    boolean inDeref = false;
+    boolean afterDeref = false;
+    int valueStart = 0;
+    for (int i = 0; i < path.length(); i += 1) {
+      switch (path.charAt(i)) {
+        case '.':
+          Preconditions.checkState(valueStart != i || afterDeref, "Empty reference: ''");
+          if (!inDeref) {
+            if (valueStart != i) {
+              PathExpr current = PathExpr.field(path.substring(valueStart, i));
+              if (last != null) {
+                last.children.add(current);
+              } else {
+                expr = current;
+              }
+              last = current;
+            }
+            valueStart = i + 1;
+            afterDeref = false;
+          }
+          break;
+        case '[':
+          Preconditions.checkState(!inDeref, "Cannot nest [ within []");
+          Preconditions.checkState(valueStart != i || afterDeref, "Empty reference: ''");
+          if (valueStart != i) {
+            PathExpr current = PathExpr.field(path.substring(valueStart, i));
+            if (last != null) {
+              last.children.add(current);
+            } else {
+              expr = current;
+            }
+            last = current;
+          }
+          valueStart = i + 1;
+          inDeref = true;
+          afterDeref = false;
+          break;
+        case ']':
+          Preconditions.checkState(inDeref, "Cannot use ] without a starting [");
+          Preconditions.checkState(valueStart != i, "Empty reference: ''");
+          PathExpr current = PathExpr.deref(path.substring(valueStart, i));
+          if (last != null) {
+            last.children.add(current);
+          } else {
+            expr = current;
+          }
+          last = current;
+          valueStart = i + 1;
+          inDeref = false;
+          afterDeref = true;
+          break;
+        default:
+          Preconditions.checkState(!afterDeref, "Fields after [] must start with .");
+      }
+    }
+    Preconditions.checkState(!inDeref, "Fields after [ must end with ]");
+    if (valueStart < path.length()) {
+      PathExpr current = PathExpr.field(path.substring(valueStart, path.length()));
+      if (last != null) {
+        last.children.add(current);
+      } else {
+        expr = current;
+      }
+    }
+    return expr;
+  }
+
+  private static List<PathExpr> merge(List<String> fields) {
+    List<PathExpr> paths = Lists.newArrayList();
+    for (String field : fields) {
+      merge(paths, parse(field));
+    }
+    return paths;
+  }
+
+  private static List<PathExpr> merge(List<PathExpr> tokens, PathExpr toAdd) {
+    boolean merged = false;
+    for (PathExpr token : tokens) {
+      if ((token.type == toAdd.type) &&
+          (token.type == PathExpr.Type.DEREF || token.value.equals(toAdd.value))) {
+        for (PathExpr child : toAdd.children) {
+          merge(token.children, child);
+        }
+        merged = true;
+      }
+    }
+    if (!merged) {
+      tokens.add(toAdd);
+    }
+    return tokens;
+  }
+
+  private static Schema filter(Schema schema, List<PathExpr> exprs) {
+    if (exprs.isEmpty()) {
+      return schema;
+    }
+
+    switch (schema.getType()) {
+      case RECORD:
+        List<Schema.Field> fields = Lists.newArrayList();
+        for (PathExpr expr : exprs) {
+          Schema.Field field = schema.getField(expr.value);
+          Preconditions.checkArgument(field != null,
+              "Cannot find field '%s' in schema: %s", expr.value, schema);
+          fields.add(new Schema.Field(expr.value, filter(field.schema(), expr.children),
+              field.doc(), field.defaultVal(), field.order()));
+        }
+        return Schema.createRecord(schema.getName(),
+            schema.getDoc(), schema.getNamespace(), schema.isError(), fields);
+
+      case UNION:
+        // Ignore schemas that are a union with null because there is another token
+        if (schema.getTypes().size() == 2) {
+          if (schema.getTypes().get(0).getType() == Schema.Type.NULL) {
+            return filter(schema.getTypes().get(1), exprs);
+          } else if (schema.getTypes().get(1).getType() == Schema.Type.NULL) {
+            return filter(schema.getTypes().get(0), exprs);
+          }
+        }
+
+        List<Schema> schemas = Lists.newArrayList();
+        for (PathExpr expr : exprs) {
+          schemas.add(filter(schema, expr));
+        }
+
+        if (schemas.size() > 1) {
+          return Schema.createUnion(schemas);
+        } else {
+          return schemas.get(0);
+        }
+
+      case MAP:
+        Preconditions.checkArgument(exprs.size() == 1,
+            "Cannot find multiple children of map schema: %s", schema);
+        return filter(schema, exprs.get(0));
+
+      case ARRAY:
+        Preconditions.checkArgument(exprs.size() == 1,
+            "Cannot find multiple children of array schema: %s", schema);
+        return filter(schema, exprs.get(0));
+
+      default:
+        throw new IllegalArgumentException(String.format(
+            "Cannot find child of primitive schema: %s", schema));
+    }
+  }
+
+  private static Schema filter(Schema schema, PathExpr expr) {
+    if (expr == null) {
+      return schema;
+    }
+
+    switch (schema.getType()) {
+      case RECORD:
+        Preconditions.checkArgument(expr.type == PathExpr.Type.FIELD,
+            "Cannot index a record: [%s]", expr.value);
+        Schema.Field field = schema.getField(expr.value);
+        if (field != null) {
+          return filter(field.schema(), expr.children);
+        } else {
+          throw new IllegalArgumentException(String.format(
+              "Cannot find field '%s' in schema: %s", expr.value, schema.toString(true)));
+        }
+
+      case MAP:
+        return Schema.createMap(filter(schema.getValueType(), expr.children));
+
+      case ARRAY:
+        Preconditions.checkArgument(expr.type == PathExpr.Type.DEREF,
+            "Cannot find field '%s' in an array", expr.value);
+        Preconditions.checkArgument(NUMERIC_RE.matcher(expr.value).matches(),
+            "Cannot index array by non-numeric value '%s'", expr.value);
+        return Schema.createArray(filter(schema.getElementType(), expr.children));
+
+      case UNION:
+        // TODO: this should only return something if the type can match rather than explicitly
+        // accessing parts of a union. when selecting data, unions are ignored.
+        Preconditions.checkArgument(expr.type == PathExpr.Type.DEREF,
+            "Cannot find field '%s' in a union", expr.value);
+        List<Schema> options = schema.getTypes();
+        if (NUMERIC_RE.matcher(expr.value).matches()) {
+          // look up the option by position
+          int i = Integer.parseInt(expr.value);
+          if (i < options.size()) {
+            return filter(options.get(i), expr.children);
+          }
+        } else {
+          // look up the option by name
+          for (Schema option : options) {
+            if (expr.value.equalsIgnoreCase(option.getName())) {
+              return filter(option, expr.children);
+            }
+          }
+        }
+        throw new IllegalArgumentException(String.format(
+            "Invalid union index '%s' for schema: %s", expr.value, schema));
+
+      default:
+        throw new IllegalArgumentException(String.format(
+            "Cannot find '%s' in primitive schema: %s", expr.value, schema));
+    }
+  }
+
+  private static class PathExpr {
+    enum Type {
+      DEREF,
+      FIELD
+    }
+
+    static PathExpr deref(String value) {
+      return new PathExpr(Type.DEREF, value);
+    }
+
+    static PathExpr deref(String value, PathExpr child) {
+      return new PathExpr(Type.DEREF, value, Lists.newArrayList(child));
+    }
+
+    static PathExpr field(String value) {
+      return new PathExpr(Type.FIELD, value);
+    }
+
+    static PathExpr field(String value, PathExpr child) {
+      return new PathExpr(Type.FIELD, value, Lists.newArrayList(child));
+    }
+
+    private final Type type;
+    private final String value;
+    private final List<PathExpr> children;
+
+    PathExpr(Type type, String value) {
+      this.type = type;
+      this.value = value;
+      this.children = Lists.newArrayList();
+    }
+
+    PathExpr(Type type, String value, List<PathExpr> children) {
+      this.type = type;
+      this.value = value;
+      this.children = children;
+    }
+
+    @Override
+    public boolean equals(Object o) {
+      if (this == o) return true;
+      if (o == null || getClass() != o.getClass()) return false;
+
+      PathExpr pathExpr = (PathExpr) o;
+
+      if (type != pathExpr.type) return false;
+      if (value != null ? !value.equals(pathExpr.value) : pathExpr.value != null) return false;
+      return children != null ? children.equals(pathExpr.children) : pathExpr.children == null;
+    }
+
+    @Override
+    public int hashCode() {
+      int result = type != null ? type.hashCode() : 0;
+      result = 31 * result + (value != null ? value.hashCode() : 0);
+      result = 31 * result + (children != null ? children.hashCode() : 0);
+      return result;
+    }
+
+    @Override
+    public String toString() {
+      return Objects.toStringHelper(this)
+          .add("type", type)
+          .add("value", value)
+          .add("children", children)
+          .toString();
+    }
+  }
+}

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/java/org/apache/parquet/cli/util/Formats.java
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/java/org/apache/parquet/cli/util/Formats.java b/parquet-cli/src/main/java/org/apache/parquet/cli/util/Formats.java
new file mode 100644
index 0000000..6895182
--- /dev/null
+++ b/parquet-cli/src/main/java/org/apache/parquet/cli/util/Formats.java
@@ -0,0 +1,47 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.parquet.cli.util;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.Arrays;
+
+public class Formats {
+  public enum Format {
+    PARQUET,
+    AVRO,
+    SEQUENCE,
+    TEXT
+  }
+
+  public static Format detectFormat(InputStream stream) throws IOException {
+    byte[] first3 = new byte[3];
+    stream.read(first3);
+    if (Arrays.equals(first3, new byte[]{'P', 'A', 'R'})) {
+      return Format.PARQUET;
+    } else if (Arrays.equals(first3, new byte[]{'O', 'b', 'j'})) {
+      return Format.AVRO;
+    } else if (Arrays.equals(first3, new byte[]{'S', 'E', 'Q'})) {
+      return Format.SEQUENCE;
+    } else {
+      return Format.TEXT;
+    }
+  }
+}

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/java/org/apache/parquet/cli/util/GetClassLoader.java
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/java/org/apache/parquet/cli/util/GetClassLoader.java b/parquet-cli/src/main/java/org/apache/parquet/cli/util/GetClassLoader.java
new file mode 100644
index 0000000..1cacbd5
--- /dev/null
+++ b/parquet-cli/src/main/java/org/apache/parquet/cli/util/GetClassLoader.java
@@ -0,0 +1,39 @@
+/*
+ *  Licensed to the Apache Software Foundation (ASF) under one
+ *  or more contributor license agreements.  See the NOTICE file
+ *  distributed with this work for additional information
+ *  regarding copyright ownership.  The ASF licenses this file
+ *  to you under the Apache License, Version 2.0 (the
+ *  "License"); you may not use this file except in compliance
+ *  with the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ *  Unless required by applicable law or agreed to in writing,
+ *  software distributed under the License is distributed on an
+ *  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ *  KIND, either express or implied.  See the License for the
+ *  specific language governing permissions and limitations
+ *  under the License.
+ */
+
+package org.apache.parquet.cli.util;
+
+import java.net.URL;
+import java.net.URLClassLoader;
+import java.security.PrivilegedAction;
+import java.util.List;
+
+public class GetClassLoader implements PrivilegedAction<ClassLoader> {
+  private final URL[] urls;
+
+  public GetClassLoader(List<URL> urls) {
+    this.urls = urls.toArray(new URL[urls.size()]);
+  }
+
+  @Override
+  public ClassLoader run() {
+    return new URLClassLoader(
+        urls, Thread.currentThread().getContextClassLoader());
+  }
+}

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/java/org/apache/parquet/cli/util/RecordException.java
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/java/org/apache/parquet/cli/util/RecordException.java b/parquet-cli/src/main/java/org/apache/parquet/cli/util/RecordException.java
new file mode 100644
index 0000000..f7e7b6c
--- /dev/null
+++ b/parquet-cli/src/main/java/org/apache/parquet/cli/util/RecordException.java
@@ -0,0 +1,53 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.parquet.cli.util;
+
+/**
+ * Exception to signal that a record could not be read or written.
+ */
+public class RecordException extends RuntimeException {
+  public RecordException(String message) {
+    super(message);
+  }
+
+  public RecordException(String message, Throwable cause) {
+    super(message, cause);
+  }
+
+  /**
+   * Precondition-style validation that throws a {@link RecordException}.
+   *
+   * @param isValid
+   *          {@code true} if valid, {@code false} if an exception should be
+   *          thrown
+   * @param message
+   *          A String message for the exception.
+   */
+  public static void check(boolean isValid, String message, Object... args) {
+    if (!isValid) {
+      String[] argStrings = new String[args.length];
+      for (int i = 0; i < args.length; i += 1) {
+        argStrings[i] = String.valueOf(args[i]);
+      }
+      throw new RecordException(
+          String.format(String.valueOf(message), (Object[]) argStrings));
+    }
+  }
+}

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/java/org/apache/parquet/cli/util/RuntimeIOException.java
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/java/org/apache/parquet/cli/util/RuntimeIOException.java b/parquet-cli/src/main/java/org/apache/parquet/cli/util/RuntimeIOException.java
new file mode 100644
index 0000000..e723319
--- /dev/null
+++ b/parquet-cli/src/main/java/org/apache/parquet/cli/util/RuntimeIOException.java
@@ -0,0 +1,31 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.parquet.cli.util;
+
+import java.io.IOException;
+
+/**
+ * RuntimeException wrapper for IOExceptions
+ */
+public class RuntimeIOException extends RuntimeException {
+  public RuntimeIOException(String message, IOException cause) {
+    super(message, cause);
+  }
+}

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/java/org/apache/parquet/cli/util/Schemas.java
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/java/org/apache/parquet/cli/util/Schemas.java b/parquet-cli/src/main/java/org/apache/parquet/cli/util/Schemas.java
new file mode 100644
index 0000000..877c7cc
--- /dev/null
+++ b/parquet-cli/src/main/java/org/apache/parquet/cli/util/Schemas.java
@@ -0,0 +1,498 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.parquet.cli.util;
+
+import com.google.common.base.Objects;
+import com.google.common.base.Preconditions;
+import com.google.common.collect.ImmutableList;
+import com.google.common.collect.Lists;
+import com.google.common.collect.Sets;
+import com.google.common.io.Closeables;
+import org.apache.parquet.cli.json.AvroJson;
+import org.apache.avro.Schema;
+import org.apache.avro.file.DataFileStream;
+import org.apache.avro.generic.GenericDatumReader;
+import org.apache.avro.generic.GenericRecord;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.parquet.avro.AvroSchemaConverter;
+import org.apache.parquet.hadoop.ParquetFileReader;
+import org.apache.parquet.hadoop.metadata.ParquetMetadata;
+import org.codehaus.jackson.node.NullNode;
+import java.io.IOException;
+import java.io.InputStream;
+import java.net.URI;
+import java.util.Collection;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Set;
+
+public class Schemas {
+
+  public static Schema fromAvsc(InputStream in) throws IOException {
+    // the parser has state, so use a new one each time
+    return new Schema.Parser().parse(in);
+  }
+
+  public static Schema fromAvro(InputStream in) throws IOException {
+    GenericDatumReader<GenericRecord> datumReader =
+        new GenericDatumReader<GenericRecord>();
+    DataFileStream<GenericRecord> stream = null;
+    boolean threw = true;
+
+    try {
+      stream = new DataFileStream<>(in, datumReader);
+      Schema schema = stream.getSchema();
+      threw = false;
+      return schema;
+    } finally {
+      Closeables.close(stream, threw);
+    }
+  }
+
+  public static Schema fromParquet(Configuration conf, URI location) throws IOException {
+    Path path = new Path(location);
+    FileSystem fs = path.getFileSystem(conf);
+
+    ParquetMetadata footer = ParquetFileReader.readFooter(fs.getConf(), path);
+
+    String schemaString = footer.getFileMetaData()
+        .getKeyValueMetaData().get("parquet.avro.schema");
+    if (schemaString == null) {
+      // try the older property
+      schemaString = footer.getFileMetaData()
+          .getKeyValueMetaData().get("avro.schema");
+    }
+
+    if (schemaString != null) {
+      return new Schema.Parser().parse(schemaString);
+    } else {
+      return new AvroSchemaConverter()
+          .convert(footer.getFileMetaData().getSchema());
+    }
+  }
+
+  public static Schema fromJSON(String name, InputStream in) throws IOException {
+    return AvroJson.inferSchema(in, name, 20);
+  }
+
+  /**
+   * Returns whether null is allowed by the schema.
+   *
+   * @param schema a Schema
+   * @return true if schema allows the value to be null
+   */
+  public static boolean nullOk(Schema schema) {
+    if (Schema.Type.NULL == schema.getType()) {
+      return true;
+    } else if (Schema.Type.UNION == schema.getType()) {
+      for (Schema possible : schema.getTypes()) {
+        if (nullOk(possible)) {
+          return true;
+        }
+      }
+    }
+    return false;
+  }
+
+  /**
+   * Merges {@link Schema} instances if they are compatible.
+   * <p>
+   * Schemas are incompatible if:
+   * <ul>
+   * <li>The {@link Schema.Type} does not match.</li>
+   * <li>For record schemas, the record name does not match</li>
+   * <li>For enum schemas, the enum name does not match</li>
+   * </ul>
+   * <p>
+   * Map value, array element, and record field types types will use unions if
+   * necessary, and union schemas are merged recursively.
+   *
+   * @param schemas a set of {@code Schema} instances to merge
+   * @return a merged {@code Schema}
+   * @throws IllegalStateException if the schemas are not compatible
+   */
+  public static Schema merge(Iterable<Schema> schemas) {
+    Iterator<Schema> iter = schemas.iterator();
+    if (!iter.hasNext()) {
+      return null;
+    }
+    Schema result = iter.next();
+    while (iter.hasNext()) {
+      result = merge(result, iter.next());
+    }
+    return result;
+  }
+
+  /**
+   * Merges {@link Schema} instances and creates a union of schemas if any are
+   * incompatible.
+   * <p>
+   * Schemas are incompatible if:
+   * <ul>
+   * <li>The {@link Schema.Type} does not match.</li>
+   * <li>For record schemas, the record name does not match</li>
+   * <li>For enum schemas, the enum name does not match</li>
+   * </ul>
+   * <p>
+   * Map value, array element, and record field types types will use unions if
+   * necessary, and union schemas are merged recursively.
+   *
+   * @param schemas a set of {@code Schema} instances to merge
+   * @return a combined {@code Schema}
+   */
+  public static Schema mergeOrUnion(Iterable<Schema> schemas) {
+    Iterator<Schema> iter = schemas.iterator();
+    if (!iter.hasNext()) {
+      return null;
+    }
+    Schema result = iter.next();
+    while (iter.hasNext()) {
+      result = mergeOrUnion(result, iter.next());
+    }
+    return result;
+  }
+
+  /**
+   * Merges two {@link Schema} instances if they are compatible.
+   * <p>
+   * Two schemas are incompatible if:
+   * <ul>
+   * <li>The {@link Schema.Type} does not match.</li>
+   * <li>For record schemas, the record name does not match</li>
+   * <li>For enum schemas, the enum name does not match</li>
+   * </ul>
+   * <p>
+   * Map value and array element types will use unions if necessary, and union
+   * schemas are merged recursively.
+   *
+   * @param left a {@code Schema}
+   * @param right a {@code Schema}
+   * @return a merged {@code Schema}
+   * @throws IllegalStateException if the schemas are not compatible
+   */
+  public static Schema merge(Schema left, Schema right) {
+    Schema merged = mergeOnly(left, right);
+    Preconditions.checkState(merged != null,
+        "Cannot merge %s and %s", left, right);
+    return merged;
+  }
+
+  /**
+   * Merges two {@link Schema} instances or returns {@code null}.
+   * <p>
+   * The two schemas are merged if they are the same type. Records are merged
+   * if the two records have the same name or have no names but have a
+   * significant number of shared fields.
+   * <p>
+   * @see {@link #mergeOrUnion} to return a union when a merge is not possible.
+   *
+   * @param left a {@code Schema}
+   * @param right a {@code Schema}
+   * @return a {@code Schema} for both types
+   */
+  private static Schema mergeOrUnion(Schema left, Schema right) {
+    Schema merged = mergeOnly(left, right);
+    if (merged != null) {
+      return merged;
+    }
+    return union(left, right);
+  }
+
+  /**
+   * Creates a union of two {@link Schema} instances.
+   * <p>
+   * If either {@code Schema} is a union, this will attempt to merge the other
+   * schema with the types contained in that union before adding more types to
+   * the union that is produced.
+   * <p>
+   * If both schemas are not unions, no merge is attempted.
+   *
+   * @param left a {@code Schema}
+   * @param right a {@code Schema}
+   * @return a UNION schema of the to {@code Schema} instances
+   */
+  private static Schema union(Schema left, Schema right) {
+    if (left.getType() == Schema.Type.UNION) {
+      if (right.getType() == Schema.Type.UNION) {
+        // combine the unions by adding each type in right individually
+        Schema combined = left;
+        for (Schema type : right.getTypes()) {
+          combined = union(combined, type);
+        }
+        return combined;
+
+      } else {
+        boolean notMerged = true;
+        // combine a union with a non-union by checking if each type will merge
+        List<Schema> types = Lists.newArrayList();
+        Iterator<Schema> schemas = left.getTypes().iterator();
+        // try to merge each type and stop when one succeeds
+        while (schemas.hasNext()) {
+          Schema next = schemas.next();
+          Schema merged = mergeOnly(next, right);
+          if (merged != null) {
+            types.add(merged);
+            notMerged = false;
+            break;
+          } else {
+            // merge didn't work, add the type
+            types.add(next);
+          }
+        }
+        // add the remaining types from the left union
+        while (schemas.hasNext()) {
+          types.add(schemas.next());
+        }
+
+        if (notMerged) {
+          types.add(right);
+        }
+
+        return Schema.createUnion(types);
+      }
+    } else if (right.getType() == Schema.Type.UNION) {
+      return union(right, left);
+    }
+
+    return Schema.createUnion(ImmutableList.of(left, right));
+  }
+
+  /**
+   * Merges two {@link Schema} instances or returns {@code null}.
+   * <p>
+   * The two schemas are merged if they are the same type. Records are merged
+   * if the two records have the same name or have no names but have a
+   * significant number of shared fields.
+   * <p>
+   * @see {@link #mergeOrUnion} to return a union when a merge is not possible.
+   *
+   * @param left a {@code Schema}
+   * @param right a {@code Schema}
+   * @return a merged {@code Schema} or {@code null} if merging is not possible
+   */
+  private static Schema mergeOnly(Schema left, Schema right) {
+    if (Objects.equal(left, right)) {
+      return left;
+    }
+
+    // handle primitive type promotion; doesn't promote integers to floats
+    switch (left.getType()) {
+      case INT:
+        if (right.getType() == Schema.Type.LONG) {
+          return right;
+        }
+        break;
+      case LONG:
+        if (right.getType() == Schema.Type.INT) {
+          return left;
+        }
+        break;
+      case FLOAT:
+        if (right.getType() == Schema.Type.DOUBLE) {
+          return right;
+        }
+        break;
+      case DOUBLE:
+        if (right.getType() == Schema.Type.FLOAT) {
+          return left;
+        }
+    }
+
+    // any other cases where the types don't match must be combined by a union
+    if (left.getType() != right.getType()) {
+      return null;
+    }
+
+    switch (left.getType()) {
+      case UNION:
+        return union(left, right);
+      case RECORD:
+        if (left.getName() == null && right.getName() == null &&
+            fieldSimilarity(left, right) < SIMILARITY_THRESH) {
+          return null;
+        } else if (!Objects.equal(left.getName(), right.getName())) {
+          return null;
+        }
+
+        Schema combinedRecord = Schema.createRecord(
+            coalesce(left.getName(), right.getName()),
+            coalesce(left.getDoc(), right.getDoc()),
+            coalesce(left.getNamespace(), right.getNamespace()),
+            false
+        );
+        combinedRecord.setFields(mergeFields(left, right));
+
+        return combinedRecord;
+
+      case MAP:
+        return Schema.createMap(
+            mergeOrUnion(left.getValueType(), right.getValueType()));
+
+      case ARRAY:
+        return Schema.createArray(
+            mergeOrUnion(left.getElementType(), right.getElementType()));
+
+      case ENUM:
+        if (!Objects.equal(left.getName(), right.getName())) {
+          return null;
+        }
+        Set<String> symbols = Sets.newLinkedHashSet();
+        symbols.addAll(left.getEnumSymbols());
+        symbols.addAll(right.getEnumSymbols());
+        return Schema.createEnum(
+            left.getName(),
+            coalesce(left.getDoc(), right.getDoc()),
+            coalesce(left.getNamespace(), right.getNamespace()),
+            ImmutableList.copyOf(symbols)
+        );
+
+      default:
+        // all primitives are handled before the switch by the equality check.
+        // schemas that reach this point are not primitives and also not any of
+        // the above known types.
+        throw new UnsupportedOperationException(
+            "Unknown schema type: " + left.getType());
+    }
+  }
+
+  private static final Schema NULL = Schema.create(Schema.Type.NULL);
+  private static final NullNode NULL_DEFAULT = NullNode.getInstance();
+
+  /**
+   * Returns a union {@link Schema} of NULL and the given {@code schema}.
+   * <p>
+   * A NULL schema is always the first type in the union so that a null default
+   * value can be set.
+   *
+   * @param schema a {@code Schema}
+   * @return a union of null and the given schema
+   */
+  private static Schema nullableForDefault(Schema schema) {
+    if (schema.getType() == Schema.Type.NULL) {
+      return schema;
+    }
+
+    if (schema.getType() != Schema.Type.UNION) {
+      return Schema.createUnion(ImmutableList.of(NULL, schema));
+    }
+
+    if (schema.getTypes().get(0).getType() == Schema.Type.NULL) {
+      return schema;
+    }
+
+    List<Schema> types = Lists.newArrayList();
+    types.add(NULL);
+    for (Schema type : schema.getTypes()) {
+      if (type.getType() != Schema.Type.NULL) {
+        types.add(type);
+      }
+    }
+
+    return Schema.createUnion(types);
+  }
+
+  private static List<Schema.Field> mergeFields(Schema left, Schema right) {
+    List<Schema.Field> fields = Lists.newArrayList();
+    for (Schema.Field leftField : left.getFields()) {
+      Schema.Field rightField = right.getField(leftField.name());
+      if (rightField != null) {
+        fields.add(new Schema.Field(
+            leftField.name(),
+            mergeOrUnion(leftField.schema(), rightField.schema()),
+            coalesce(leftField.doc(), rightField.doc()),
+            coalesce(leftField.defaultValue(), rightField.defaultValue())
+        ));
+      } else {
+        if (leftField.defaultValue() != null) {
+          fields.add(copy(leftField));
+        } else {
+          fields.add(new Schema.Field(
+              leftField.name(), nullableForDefault(leftField.schema()),
+              leftField.doc(), NULL_DEFAULT
+          ));
+        }
+      }
+    }
+
+    for (Schema.Field rightField : right.getFields()) {
+      if (left.getField(rightField.name()) == null) {
+        if (rightField.defaultValue() != null) {
+          fields.add(copy(rightField));
+        } else {
+          fields.add(new Schema.Field(
+              rightField.name(), nullableForDefault(rightField.schema()),
+              rightField.doc(), NULL_DEFAULT
+          ));
+        }
+      }
+    }
+
+    return fields;
+  }
+
+  /**
+   * Creates a new field with the same name, schema, doc, and default value as
+   * the incoming schema.
+   * <p>
+   * Fields cannot be used in more than one record (not Immutable?).
+   */
+  public static Schema.Field copy(Schema.Field field) {
+    return new Schema.Field(
+        field.name(), field.schema(), field.doc(), field.defaultValue());
+  }
+
+  private static float fieldSimilarity(Schema left, Schema right) {
+    // check whether the unnamed records appear to be the same record
+    Set<String> leftNames = names(left.getFields());
+    Set<String> rightNames = names(right.getFields());
+    int common = Sets.intersection(leftNames, rightNames).size();
+    float leftRatio = ((float) common) / ((float) leftNames.size());
+    float rightRatio = ((float) common) / ((float) rightNames.size());
+    return hmean(leftRatio, rightRatio);
+  }
+
+  private static Set<String> names(Collection<Schema.Field> fields) {
+    Set<String> names = Sets.newHashSet();
+    for (Schema.Field field : fields) {
+      names.add(field.name());
+    }
+    return names;
+  }
+
+  private static float SIMILARITY_THRESH = 0.3f;
+  private static float hmean(float left, float right) {
+    return (2.0f * left * right) / (left + right);
+  }
+
+  /**
+   * Returns the first non-null object that is passed in.
+   */
+  @SafeVarargs
+  private static <E> E coalesce(E... objects) {
+    for (E object : objects) {
+      if (object != null) {
+        return object;
+      }
+    }
+    return null;
+  }
+}

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/java/org/apache/parquet/cli/util/SeekableFSDataInputStream.java
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/java/org/apache/parquet/cli/util/SeekableFSDataInputStream.java b/parquet-cli/src/main/java/org/apache/parquet/cli/util/SeekableFSDataInputStream.java
new file mode 100644
index 0000000..8a8b41e
--- /dev/null
+++ b/parquet-cli/src/main/java/org/apache/parquet/cli/util/SeekableFSDataInputStream.java
@@ -0,0 +1,76 @@
+/*
+ *  Licensed to the Apache Software Foundation (ASF) under one
+ *  or more contributor license agreements.  See the NOTICE file
+ *  distributed with this work for additional information
+ *  regarding copyright ownership.  The ASF licenses this file
+ *  to you under the Apache License, Version 2.0 (the
+ *  "License"); you may not use this file except in compliance
+ *  with the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ *  Unless required by applicable law or agreed to in writing,
+ *  software distributed under the License is distributed on an
+ *  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ *  KIND, either express or implied.  See the License for the
+ *  specific language governing permissions and limitations
+ *  under the License.
+ */
+
+package org.apache.parquet.cli.util;
+
+import org.apache.avro.file.SeekableInput;
+import org.apache.hadoop.fs.FSDataInputStream;
+import org.apache.hadoop.fs.FileStatus;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import java.io.IOException;
+import java.io.InputStream;
+
+/**
+ * A wrapper for FSDataInputStream that implements Avro's SeekableInput.
+ */
+public class SeekableFSDataInputStream extends InputStream implements SeekableInput {
+  private final FSDataInputStream in;
+  private final FileStatus stat;
+
+  public SeekableFSDataInputStream(FileSystem fs, Path file) throws IOException {
+    this.in = fs.open(file);
+    this.stat = fs.getFileStatus(file);
+  }
+
+  @Override
+  public void seek(long p) throws IOException {
+    in.seek(p);
+  }
+
+  @Override
+  public long tell() throws IOException {
+    return in.getPos();
+  }
+
+  @Override
+  public long length() throws IOException {
+    return stat.getLen();
+  }
+
+  @Override
+  public int read(byte[] b) throws IOException {
+    return in.read(b);
+  }
+
+  @Override
+  public int read() throws IOException {
+    return in.read();
+  }
+
+  @Override
+  public int read(byte[] b, int off, int len) throws IOException {
+    return in.read(b, off, len);
+  }
+
+  @Override
+  public void close() throws IOException {
+    in.close();
+  }
+}

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/resources/META-INF/LICENSE
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/resources/META-INF/LICENSE b/parquet-cli/src/main/resources/META-INF/LICENSE
new file mode 100644
index 0000000..2b581f8
--- /dev/null
+++ b/parquet-cli/src/main/resources/META-INF/LICENSE
@@ -0,0 +1,348 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+--------------------------------------------------------------------------------
+
+This product depends on Apache Thrift and includes it in this binary artifact.
+
+Copyright: 2006-2010 The Apache Software Foundation.
+Home page: https://thrift.apache.org/
+License: http://www.apache.org/licenses/LICENSE-2.0
+
+--------------------------------------------------------------------------------
+
+This product depends on SLF4J and includes SLF4J in this binary artifact. SLF4J
+is a simple logging facade for Java.
+
+Copyright: 2004-2013 QOS.ch.
+Home page: http://www.slf4j.org/
+License: http://slf4j.org/license.html (MIT license)
+
+The following is the SLF4J license (MIT):
+
+  Copyright (c) 2004-2013 QOS.ch
+  All rights reserved.
+
+  Permission is hereby granted, free  of charge, to any person obtaining
+  a  copy  of this  software  and  associated  documentation files  (the
+  "Software"), to  deal in  the Software without  restriction, including
+  without limitation  the rights to  use, copy, modify,  merge, publish,
+  distribute,  sublicense, and/or sell  copies of  the Software,  and to
+  permit persons to whom the Software  is furnished to do so, subject to
+  the following conditions:
+
+  The  above  copyright  notice  and  this permission  notice  shall  be
+  included in all copies or substantial portions of the Software.
+
+  THE  SOFTWARE IS  PROVIDED  "AS  IS", WITHOUT  WARRANTY  OF ANY  KIND,
+  EXPRESS OR  IMPLIED, INCLUDING  BUT NOT LIMITED  TO THE  WARRANTIES OF
+  MERCHANTABILITY,    FITNESS    FOR    A   PARTICULAR    PURPOSE    AND
+  NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+  LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+  OF CONTRACT, TORT OR OTHERWISE,  ARISING FROM, OUT OF OR IN CONNECTION
+  WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+
+--------------------------------------------------------------------------------
+
+This project includes code from Daniel Lemire's JavaFastPFOR project in this
+binary artifact. The "Lemire" bit packing classes produced by parquet-generator
+are derived from the JavaFastPFOR project.
+
+Copyright: 2013 Daniel Lemire
+Home page: http://lemire.me/en/
+Project page: https://github.com/lemire/JavaFastPFOR
+License: Apache License Version 2.0 http://www.apache.org/licenses/LICENSE-2.0
+
+--------------------------------------------------------------------------------
+
+This product depends on Apache Avro and includes it in this binary artifact.
+
+Copyright: 2010-2016 The Apache Software Foundation.
+Home page: https://avro.apache.org/
+License: http://www.apache.org/licenses/LICENSE-2.0
+
+--------------------------------------------------------------------------------
+
+This product depends on fastutil and includes it in this binary artifact.
+Fastutil provides type-specific collection implementations.
+
+Copyright: 2002-2014 Sebastiano Vigna
+Home page: http://fasutil.di.unimi.it/
+License: http://www.apache.org/licenses/LICENSE-2.0.html
+
+--------------------------------------------------------------------------------
+
+This product depends on Jackson and includes it in this binary artifact.
+Jackson is a high-performance JSON processor.
+
+Copyright: 2007-2015 Tatu Saloranta and other contributors
+Home page: http://jackson.codehaus.org/
+Home page: http://wiki.fasterxml.com/JacksonHome
+License: http://www.apache.org/licenses/LICENSE-2.0.txt
+
+--------------------------------------------------------------------------------
+
+This product depends on snappy-java and includes it in this binary artifact.
+Snappy is a fast compression codec that aims for high speeds and reasonable
+compression, developed by Google.
+
+Copyright: 2011 Taro L. Saito and other contributors
+Home page: http://www.xerial.org/
+License: http://www.apache.org/licenses/LICENSE-2.0.txt
+
+--------------------------------------------------------------------------------
+
+This product depends on Apache Commons and includes commons-codec,
+commons-pool, and commons-compress in this binary artifact.
+
+Copyright: 2002-2015 The Apache Software Foundation.
+Home page: https://commons.apache.org/proper/commons-codec/
+Home page: https://commons.apache.org/proper/commons-pool/
+License: http://www.apache.org/licenses/LICENSE-2.0
+
+Commons Compress includes files derived from the LZMA SDK, version 9.20 (C/ and
+CPP/7zip/), in the package org.apache.commons.compress.archivers.sevenz:
+
+| LZMA SDK is placed in the public domain. (http://www.7-zip.org/sdk.html)
+
+--------------------------------------------------------------------------------
+
+This product depends on Google guava and includes it in this binary artifact.
+
+Copyright: 2010-2015 The Guava Authors
+Home page: https://github.com/google/guava
+License: http://www.apache.org/licenses/LICENSE-2.0
+
+--------------------------------------------------------------------------------
+
+This product depends on JCommander and includes it in this binary artifact.
+
+Copyright: Copyright 2012, Cedric Beust and contributors
+Home page: http://jcommander.org
+License: https://github.com/cbeust/jcommander/blob/master/license.txt
+
+--------------------------------------------------------------------------------
+
+This product depends on OpenCSV and includes it in this binary artifact.
+
+Copyright: 2006 Glen Smith and contributors
+Home page: http://opencsv.sourceforge.net/
+License: http://www.apache.org/licenses/LICENSE-2.0
+
+----------------------------------------------------------------------
+
+License for paranamer, included in this binary artifact:
+
+Copyright (c) 2006 Paul Hammant & ThoughtWorks Inc
+All rights reserved.
+
+| Redistribution and use in source and binary forms, with or without
+| modification, are permitted provided that the following conditions
+| are met:
+| 1. Redistributions of source code must retain the above copyright
+|    notice, this list of conditions and the following disclaimer.
+| 2. Redistributions in binary form must reproduce the above copyright
+|    notice, this list of conditions and the following disclaimer in the
+|    documentation and/or other materials provided with the distribution.
+| 3. Neither the name of the copyright holders nor the names of its
+|    contributors may be used to endorse or promote products derived from
+|    this software without specific prior written permission.
+|
+| THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+| AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+| IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+| ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+| LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+| CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+| SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+| INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+| CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+| ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF
+| THE POSSIBILITY OF SUCH DAMAGE.
+
+----------------------------------------------------------------------
+
+License for xz compression, included in this binary artifact:
+
+Home page: http://tukaani.org/xz/java.html
+
+| This Java implementation of XZ has been put into the public domain, thus you
+| can do whatever you want with it. All the files in the package have been
+| written by Lasse Collin, but some files are heavily based on public domain code
+| written by Igor Pavlov.
+

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/resources/META-INF/NOTICE
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/resources/META-INF/NOTICE b/parquet-cli/src/main/resources/META-INF/NOTICE
new file mode 100644
index 0000000..f90733d
--- /dev/null
+++ b/parquet-cli/src/main/resources/META-INF/NOTICE
@@ -0,0 +1,45 @@
+
+Apache Parquet MR
+Copyright 2016 The Apache Software Foundation
+
+This product includes software developed at
+The Apache Software Foundation (http://www.apache.org/).
+
+--------------------------------------------------------------------------------
+
+This project includes code from Kite, developed at Cloudera, Inc. with
+the following copyright notice:
+
+| Copyright 2013 Cloudera Inc.
+|
+| Licensed under the Apache License, Version 2.0 (the "License");
+| you may not use this file except in compliance with the License.
+| You may obtain a copy of the License at
+|
+|   http://www.apache.org/licenses/LICENSE-2.0
+|
+| Unless required by applicable law or agreed to in writing, software
+| distributed under the License is distributed on an "AS IS" BASIS,
+| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+| See the License for the specific language governing permissions and
+| limitations under the License.
+
+--------------------------------------------------------------------------------
+
+This project includes code from Netflix, Inc. with the following copyright
+notice:
+
+| Copyright 2016 Netflix, Inc.
+|
+| Licensed under the Apache License, Version 2.0 (the "License");
+| you may not use this file except in compliance with the License.
+| You may obtain a copy of the License at
+|
+|   http://www.apache.org/licenses/LICENSE-2.0
+|
+| Unless required by applicable law or agreed to in writing, software
+| distributed under the License is distributed on an "AS IS" BASIS,
+| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+| See the License for the specific language governing permissions and
+| limitations under the License.
+

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-cli/src/main/resources/cli-logging.properties
----------------------------------------------------------------------
diff --git a/parquet-cli/src/main/resources/cli-logging.properties b/parquet-cli/src/main/resources/cli-logging.properties
new file mode 100644
index 0000000..7391985
--- /dev/null
+++ b/parquet-cli/src/main/resources/cli-logging.properties
@@ -0,0 +1,51 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+
+# debug log4j configuration
+#log4j.debug=true
+
+# by default, log anything but cli console to component logger
+log4j.rootLogger = WARN, component
+
+# Set the appender named console to be a ConsoleAppender
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+
+# CLI console output
+log4j.logger.org.apache.parquet.cli=INFO, console
+log4j.additivity.org.apache.parquet.cli=false
+
+# Define the layout for console appender
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%m%n
+
+# Change to turn on component logging
+log4j.appender.component=org.apache.log4j.varia.NullAppender
+
+# Define the layout for component appender
+log4j.appender.component.layout=org.apache.log4j.PatternLayout
+log4j.appender.component.layout.ConversionPattern=%d{yyyy-MM-dd HH:mm:ss} %-5p :: %m [%C]%n
+
+# silence native code warnings
+log4j.logger.org.apache.hadoop.util.NativeCodeLoader=ERROR
+
+log4j.logger.org.apache.parquet.CorruptStatistics=ERROR
+
+# set up logging levels for MR
+log4j.logger.org.apache.hadoop.mapred.LocalJobRunner=WARN, console
+log4j.logger.org.apache.hadoop.mapreduce.Job=INFO, console

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-common/src/main/java/org/apache/parquet/Exceptions.java
----------------------------------------------------------------------
diff --git a/parquet-common/src/main/java/org/apache/parquet/Exceptions.java b/parquet-common/src/main/java/org/apache/parquet/Exceptions.java
new file mode 100644
index 0000000..bdd531c
--- /dev/null
+++ b/parquet-common/src/main/java/org/apache/parquet/Exceptions.java
@@ -0,0 +1,34 @@
+/*
+ *  Licensed to the Apache Software Foundation (ASF) under one
+ *  or more contributor license agreements.  See the NOTICE file
+ *  distributed with this work for additional information
+ *  regarding copyright ownership.  The ASF licenses this file
+ *  to you under the Apache License, Version 2.0 (the
+ *  "License"); you may not use this file except in compliance
+ *  with the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ *  Unless required by applicable law or agreed to in writing,
+ *  software distributed under the License is distributed on an
+ *  "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ *  KIND, either express or implied.  See the License for the
+ *  specific language governing permissions and limitations
+ *  under the License.
+ */
+
+package org.apache.parquet;
+
+public class Exceptions {
+  /**
+   * If the given throwable is an instance of E, throw it as an E.
+   */
+  public static <E extends Exception> void throwIfInstance(Throwable t,
+                                                           Class<E> excClass)
+      throws E {
+    if (excClass.isAssignableFrom(t.getClass())) {
+      // the throwable is already an exception, so return it
+      throw excClass.cast(t);
+    }
+  }
+}

http://git-wip-us.apache.org/repos/asf/parquet-mr/blob/ddbeb4dd/parquet-common/src/main/java/org/apache/parquet/util/DynConstructors.java
----------------------------------------------------------------------
diff --git a/parquet-common/src/main/java/org/apache/parquet/util/DynConstructors.java b/parquet-common/src/main/java/org/apache/parquet/util/DynConstructors.java
new file mode 100644
index 0000000..e1dddf1
--- /dev/null
+++ b/parquet-common/src/main/java/org/apache/parquet/util/DynConstructors.java
@@ -0,0 +1,273 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *   http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied.  See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.parquet.util;
+
+import org.apache.parquet.Preconditions;
+import java.lang.reflect.Constructor;
+import java.lang.reflect.InvocationTargetException;
+import java.security.AccessController;
+import java.security.PrivilegedAction;
+import java.util.HashMap;
+import java.util.Map;
+
+import static org.apache.parquet.Exceptions.throwIfInstance;
+
+public class DynConstructors {
+  public static class Ctor<C> extends DynMethods.UnboundMethod {
+    private final Constructor<C> ctor;
+    private final Class<? extends C> constructed;
+
+    private Ctor(Constructor<C> constructor, Class<? extends C> constructed) {
+      super(null, "newInstance");
+      this.ctor = constructor;
+      this.constructed = constructed;
+    }
+
+    public Class<? extends C> getConstructedClass() {
+      return constructed;
+    }
+
+    public C newInstanceChecked(Object... args) throws Exception {
+      try {
+        return ctor.newInstance(args);
+      } catch (InstantiationException e) {
+        throw e;
+      } catch (IllegalAccessException e) {
+        throw e;
+      } catch (InvocationTargetException e) {
+        throwIfInstance(e.getCause(), Exception.class);
+        throwIfInstance(e.getCause(), RuntimeException.class);
+        throw new RuntimeException(e.getCause());
+      }
+    }
+
+    public C newInstance(Object... args) {
+      try {
+        return newInstanceChecked(args);
+      } catch (Exception e) {
+        throwIfInstance(e, RuntimeException.class);
+        throw new RuntimeException(e);
+      }
+    }
+
+    @Override
+    @SuppressWarnings("unchecked")
+    public <R> R invoke(Object target, Object... args) {
+      Preconditions.checkArgument(target == null,
+          "Invalid call to constructor: target must be null");
+      return (R) newInstance(args);
+    }
+
+    @Override
+    @SuppressWarnings("unchecked")
+    public <R> R invokeChecked(Object target, Object... args) throws Exception {
+      Preconditions.checkArgument(target == null,
+          "Invalid call to constructor: target must be null");
+      return (R) newInstanceChecked(args);
+    }
+
+    @Override
+    public DynMethods.BoundMethod bind(Object receiver) {
+      throw new IllegalStateException("Cannot bind constructors");
+    }
+
+    @Override
+    public boolean isStatic() {
+      return true;
+    }
+
+    @Override
+    public String toString() {
+      return getClass().getSimpleName() +
+          "(constructor=" + ctor + ", class=" + constructed + ")";
+    }
+  }
+
+  public static class Builder {
+    private final Class<?> baseClass;
+    private ClassLoader loader = Thread.currentThread().getContextClassLoader();
+    private Ctor ctor = null;
+    private Map<String, Throwable> problems = new HashMap<String, Throwable>();
+
+    public Builder(Class<?> baseClass) {
+      this.baseClass = baseClass;
+    }
+
+    public Builder() {
+      this.baseClass = null;
+    }
+
+    /**
+     * Set the {@link ClassLoader} used to lookup classes by name.
+     * <p>
+     * If not set, the current thread's ClassLoader is used.
+     *
+     * @param loader a ClassLoader
+     * @return this Builder for method chaining
+     */
+    public Builder loader(ClassLoader loader) {
+      this.loader = loader;
+      return this;
+    }
+
+    public Builder impl(String className, Class<?>... types) {
+      // don't do any work if an implementation has been found
+      if (ctor != null) {
+        return this;
+      }
+
+      try {
+        Class<?> targetClass = Class.forName(className, true, loader);
+        impl(targetClass, types);
+      } catch (NoClassDefFoundError e) {
+        // cannot load this implementation
+        problems.put(className, e);
+      } catch (ClassNotFoundException e) {
+        // not the right implementation
+        problems.put(className, e);
+      }
+      return this;
+    }
+
+    public <T> Builder impl(Class<T> targetClass, Class<?>... types) {
+      // don't do any work if an implementation has been found
+      if (ctor != null) {
+        return this;
+      }
+
+      try {
+        ctor = new Ctor<T>(targetClass.getConstructor(types), targetClass);
+      } catch (NoSuchMethodException e) {
+        // not the right implementation
+        problems.put(methodName(targetClass, types), e);
+      }
+      return this;
+    }
+
+    public Builder hiddenImpl(Class<?>... types) {
+      hiddenImpl(baseClass, types);
+      return this;
+    }
+
+    @SuppressWarnings("unchecked")
+    public Builder hiddenImpl(String className, Class<?>... types) {
+      // don't do any work if an implementation has been found
+      if (ctor != null) {
+        return this;
+      }
+
+      try {
+        Class targetClass = Class.forName(className, true, loader);
+        hiddenImpl(targetClass, types);
+      } catch (NoClassDefFoundError e) {
+        // cannot load this implementation
+        problems.put(className, e);
+      } catch (ClassNotFoundException e) {
+        // not the right implementation
+        problems.put(className, e);
+      }
+      return this;
+    }
+
+    public <T> Builder hiddenImpl(Class<T> targetClass, Class<?>... types) {
+      // don't do any work if an implementation has been found
+      if (ctor != null) {
+        return this;
+      }
+
+      try {
+        Constructor<T> hidden = targetClass.getDeclaredConstructor(types);
+        AccessController.doPrivileged(new MakeAccessible(hidden));
+        ctor = new Ctor<T>(hidden, targetClass);
+      } catch (SecurityException e) {
+        // unusable
+        problems.put(methodName(targetClass, types), e);
+      } catch (NoSuchMethodException e) {
+        // not the right implementation
+        problems.put(methodName(targetClass, types), e);
+      }
+      return this;
+    }
+
+    @SuppressWarnings("unchecked")
+    public <C> Ctor<C> buildChecked() throws NoSuchMethodException {
+      if (ctor != null) {
+        return ctor;
+      }
+      throw new NoSuchMethodException("Cannot find constructor for " +
+          baseClass + "\n" + formatProblems(problems));
+    }
+
+    @SuppressWarnings("unchecked")
+    public <C> Ctor<C> build() {
+      if (ctor != null) {
+        return ctor;
+      }
+      throw new RuntimeException("Cannot find constructor for " +
+          baseClass + "\n" + formatProblems(problems));
+    }
+  }
+
+  private static class MakeAccessible implements PrivilegedAction<Void> {
+    private Constructor<?> hidden;
+
+    public MakeAccessible(Constructor<?> hidden) {
+      this.hidden = hidden;
+    }
+
+    @Override
+    public Void run() {
+      hidden.setAccessible(true);
+      return null;
+    }
+  }
+
+  private static String formatProblems(Map<String, Throwable> problems) {
+    StringBuilder sb = new StringBuilder();
+    boolean first = true;
+    for (Map.Entry<String, Throwable> problem : problems.entrySet()) {
+      if (first) {
+        first = false;
+      } else {
+        sb.append("\n");
+      }
+      sb.append("\tMissing ").append(problem.getKey()).append(" [")
+          .append(problem.getValue().getClass().getName()).append(": ")
+          .append(problem.getValue().getMessage()).append("]");
+    }
+    return sb.toString();
+  }
+
+  private static String methodName(Class<?> targetClass, Class<?>... types) {
+    StringBuilder sb = new StringBuilder();
+    sb.append(targetClass.getName()).append("(");
+    boolean first = true;
+    for (Class<?> type : types) {
+      if (first) {
+        first = false;
+      } else {
+        sb.append(",");
+      }
+      sb.append(type.getName());
+    }
+    sb.append(")");
+    return sb.toString();
+  }
+}