1 /*
2 * Copyright (c) 2001-2017, Zoltan Farkas All Rights Reserved.
3 *
4 * This library is free software; you can redistribute it and/or
5 * modify it under the terms of the GNU Lesser General Public
6 * License as published by the Free Software Foundation; either
7 * version 2.1 of the License, or (at your option) any later version.
8 *
9 * This library is distributed in the hope that it will be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 * GNU General Public License for more details.
13 *
14 * You should have received a copy of the GNU Lesser General Public
15 * License along with this program; if not, write to the Free Software
16 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
17 *
18 * Additionally licensed with:
19 *
20 * Licensed under the Apache License, Version 2.0 (the "License");
21 * you may not use this file except in compliance with the License.
22 * You may obtain a copy of the License at
23 *
24 * http://www.apache.org/licenses/LICENSE-2.0
25 *
26 * Unless required by applicable law or agreed to in writing, software
27 * distributed under the License is distributed on an "AS IS" BASIS,
28 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
29 * See the License for the specific language governing permissions and
30 * limitations under the License.
31 */
32 package org.spf4j.io.csv;
33
34 import java.io.IOException;
35 import java.util.Iterator;
36 import java.util.function.Consumer;
37 import javax.annotation.Nonnull;
38
39 /**
40 * Char separated value file Reader.
41 * A newly created reader will initially be positioned at START_DOCUMENT. (current())
42 * A example Token sequence will be:
43 * START_DOCUMENT, ELEMENT, ELEMENT, END_ROW, ELEMENT, ELEMENT, END_ROW, END_DOCUMENT
44 *
45 * @author zoly
46 */
47 public interface CsvReader {
48
49 enum TokenType {
50 START_DOCUMENT, ELEMENT, END_ROW, END_DOCUMENT
51 }
52
53 /**
54 * read next CSV element, and return its type.
55 *
56 * @return return CSV element type.
57 * @throws IOException exception is something goes wrong.
58 */
59 @Nonnull
60 TokenType next() throws IOException, CsvParseException;
61
62 /**
63 * @return the currently parsed token type, null if no current token is available (next has never been called)
64 * @throws IOException
65 * @throws CsvParseException
66 */
67 @Nonnull
68 TokenType current();
69
70 /**
71 * the CSV element string. the underlying instance is reused, so you will need to make a copy of this if planning to
72 * use it.
73 *
74 * @return CharSequence representing a csv cell.
75 */
76 CharSequence getElement();
77
78 /**
79 * Current CSV line number.
80 * @return
81 */
82 long currentLineNumber();
83
84 default int skipRow() throws IOException, CsvParseException {
85 int skipped = 0;
86 TokenType current = current();
87 if (current == TokenType.START_DOCUMENT) { // beginning of file.
88 next();
89 }
90 while ((current = current()) != CsvReader.TokenType.END_ROW
91 && current != CsvReader.TokenType.END_DOCUMENT) {
92 next();
93 skipped++;
94 }
95 if (current != CsvReader.TokenType.END_DOCUMENT) {
96 next();
97 }
98 return skipped;
99 }
100
101 default void readRow(final Consumer<CharSequence> consumer) throws IOException, CsvParseException {
102 TokenType current = current();
103 if (current == TokenType.START_DOCUMENT) { // beginning of file.
104 next();
105 }
106 while ((current = current()) != CsvReader.TokenType.END_ROW
107 && current != CsvReader.TokenType.END_DOCUMENT) {
108 consumer.accept(getElement());
109 next();
110 }
111 if (current != CsvReader.TokenType.END_DOCUMENT) {
112 next();
113 }
114 }
115
116
117 static CsvReader toReader(final Iterator<? extends CharSequence> it) {
118 return new IterableCsvReader(it);
119 }
120 }