001/*
002 * Licensed to the Apache Software Foundation (ASF) under one or more
003 * contributor license agreements.  See the NOTICE file distributed with
004 * this work for additional information regarding copyright ownership.
005 * The ASF licenses this file to You under the Apache License, Version 2.0
006 * (the "License"); you may not use this file except in compliance with
007 * the License.  You may obtain a copy of the License at
008 *
009 *      http://www.apache.org/licenses/LICENSE-2.0
010 *
011 * Unless required by applicable law or agreed to in writing, software
012 * distributed under the License is distributed on an "AS IS" BASIS,
013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
014 * See the License for the specific language governing permissions and
015 * limitations under the License.
016 */
017
018package org.apache.commons.csv;
019
020import java.io.Serializable;
021import java.util.Arrays;
022import java.util.Iterator;
023import java.util.LinkedHashMap;
024import java.util.List;
025import java.util.Map;
026import java.util.stream.Collectors;
027import java.util.stream.Stream;
028
029/**
030 * A CSV record parsed from a CSV file.
031 *
032 * <p>
033 * Note: Support for {@link Serializable} is scheduled to be removed in version 2.0.
034 * In version 1.8 the mapping between the column header and the column index was
035 * removed from the serialised state. The class maintains serialization compatibility
036 * with versions pre-1.8 for the record values; these must be accessed by index
037 * following deserialization. There will be loss of any functionally linked to the header
038 * mapping when transferring serialised forms pre-1.8 to 1.8 and vice versa.
039 * </p>
040 */
041public final class CSVRecord implements Serializable, Iterable<String> {
042
043    private static final long serialVersionUID = 1L;
044
045    private final long characterPosition;
046
047    /** The accumulated comments (if any) */
048    private final String comment;
049
050    /** The record number. */
051    private final long recordNumber;
052
053    /** The values of the record */
054    private final String[] values;
055
056    /** The parser that originates this record. This is not serialized. */
057    private final transient CSVParser parser;
058
059    CSVRecord(final CSVParser parser, final String[] values, final String comment, final long recordNumber,
060            final long characterPosition) {
061        this.recordNumber = recordNumber;
062        this.values = values != null ? values : Constants.EMPTY_STRING_ARRAY;
063        this.parser = parser;
064        this.comment = comment;
065        this.characterPosition = characterPosition;
066    }
067
068    /**
069     * Returns a value by {@link Enum}.
070     *
071     * @param e
072     *            an enum
073     * @return the String at the given enum String
074     */
075    public String get(final Enum<?> e) {
076        return get(e == null ? null : e.name());
077    }
078
079    /**
080     * Returns a value by index.
081     *
082     * @param i
083     *            a column index (0-based)
084     * @return the String at the given index
085     */
086    public String get(final int i) {
087        return values[i];
088    }
089
090    /**
091     * Returns a value by name.
092     *
093     * <p>
094     * Note: This requires a field mapping obtained from the original parser.
095     * A check using {@link #isMapped(String)} should be used to determine if a
096     * mapping exists from the provided {@code name} to a field index. In this case an
097     * exception will only be thrown if the record does not contain a field corresponding
098     * to the mapping, that is the record length is not consistent with the mapping size.
099     * </p>
100     *
101     * @param name
102     *            the name of the column to be retrieved.
103     * @return the column value, maybe null depending on {@link CSVFormat#getNullString()}.
104     * @throws IllegalStateException
105     *             if no header mapping was provided
106     * @throws IllegalArgumentException
107     *             if {@code name} is not mapped or if the record is inconsistent
108     * @see #isMapped(String)
109     * @see #isConsistent()
110     * @see #getParser()
111     * @see CSVFormat.Builder#setNullString(String)
112     */
113    public String get(final String name) {
114        final Map<String, Integer> headerMap = getHeaderMapRaw();
115        if (headerMap == null) {
116            throw new IllegalStateException(
117                "No header mapping was specified, the record values can't be accessed by name");
118        }
119        final Integer index = headerMap.get(name);
120        if (index == null) {
121            throw new IllegalArgumentException(String.format("Mapping for %s not found, expected one of %s", name,
122                headerMap.keySet()));
123        }
124        try {
125            return values[index.intValue()];
126        } catch (final ArrayIndexOutOfBoundsException e) {
127            throw new IllegalArgumentException(String.format(
128                "Index for header '%s' is %d but CSVRecord only has %d values!", name, index,
129                Integer.valueOf(values.length)));
130        }
131    }
132
133    /**
134     * Returns the start position of this record as a character position in the source stream. This may or may not
135     * correspond to the byte position depending on the character set.
136     *
137     * @return the position of this record in the source stream.
138     */
139    public long getCharacterPosition() {
140        return characterPosition;
141    }
142
143    /**
144     * Returns the comment for this record, if any.
145     * Note that comments are attached to the following record.
146     * If there is no following record (i.e. the comment is at EOF)
147     * the comment will be ignored.
148     *
149     * @return the comment for this record, or null if no comment for this record is available.
150     */
151    public String getComment() {
152        return comment;
153    }
154
155    private Map<String, Integer> getHeaderMapRaw() {
156        return parser == null ? null : parser.getHeaderMapRaw();
157    }
158
159    /**
160     * Returns the parser.
161     *
162     * <p>
163     * Note: The parser is not part of the serialized state of the record. A null check
164     * should be used when the record may have originated from a serialized form.
165     * </p>
166     *
167     * @return the parser.
168     * @since 1.7
169     */
170    public CSVParser getParser() {
171        return parser;
172    }
173
174    /**
175     * Returns the number of this record in the parsed CSV file.
176     *
177     * <p>
178     * <strong>ATTENTION:</strong> If your CSV input has multi-line values, the returned number does not correspond to
179     * the current line number of the parser that created this record.
180     * </p>
181     *
182     * @return the number of this record.
183     * @see CSVParser#getCurrentLineNumber()
184     */
185    public long getRecordNumber() {
186        return recordNumber;
187    }
188
189    /**
190     * Checks whether this record has a comment, false otherwise.
191     * Note that comments are attached to the following record.
192     * If there is no following record (i.e. the comment is at EOF)
193     * the comment will be ignored.
194     *
195     * @return true if this record has a comment, false otherwise
196     * @since 1.3
197     */
198    public boolean hasComment() {
199        return comment != null;
200    }
201
202    /**
203     * Tells whether the record size matches the header size.
204     *
205     * <p>
206     * Returns true if the sizes for this record match and false if not. Some programs can export files that fail this
207     * test but still produce parsable files.
208     * </p>
209     *
210     * @return true of this record is valid, false if not
211     */
212    public boolean isConsistent() {
213        final Map<String, Integer> headerMap = getHeaderMapRaw();
214        return headerMap == null || headerMap.size() == values.length;
215    }
216
217    /**
218     * Checks whether a given column is mapped, i.e. its name has been defined to the parser.
219     *
220     * @param name
221     *            the name of the column to be retrieved.
222     * @return whether a given column is mapped.
223     */
224    public boolean isMapped(final String name) {
225        final Map<String, Integer> headerMap = getHeaderMapRaw();
226        return headerMap != null && headerMap.containsKey(name);
227    }
228
229    /**
230     * Checks whether a column with given index has a value.
231     *
232     * @param index
233     *         a column index (0-based)
234     * @return whether a column with given index has a value
235     */
236    public boolean isSet(final int index) {
237        return 0 <= index && index < values.length;
238    }
239
240    /**
241     * Checks whether a given columns is mapped and has a value.
242     *
243     * @param name
244     *            the name of the column to be retrieved.
245     * @return whether a given columns is mapped and has a value
246     */
247    public boolean isSet(final String name) {
248        return isMapped(name) && getHeaderMapRaw().get(name).intValue() < values.length;
249    }
250
251    /**
252     * Returns an iterator over the values of this record.
253     *
254     * @return an iterator over the values of this record.
255     */
256    @Override
257    public Iterator<String> iterator() {
258        return toList().iterator();
259    }
260
261    /**
262     * Puts all values of this record into the given Map.
263     *
264     * @param <M> the map type
265     * @param map The Map to populate.
266     * @return the given map.
267     * @since 1.9.0
268     */
269    public <M extends Map<String, String>> M putIn(final M map) {
270        if (getHeaderMapRaw() == null) {
271            return map;
272        }
273        getHeaderMapRaw().forEach((key, value) -> {
274            if (value < values.length) {
275                map.put(key, values[value]);
276            }
277        });
278        return map;
279    }
280
281    /**
282     * Returns the number of values in this record.
283     *
284     * @return the number of values.
285     */
286    public int size() {
287        return values.length;
288    }
289
290    /**
291     * Returns a sequential ordered stream whose elements are the values.
292     *
293     * @return the new stream.
294     * @since 1.9.0
295     */
296    public Stream<String> stream() {
297        return Stream.of(values);
298    }
299
300    /**
301     * Converts the values to a new List.
302     * <p>
303     * Editing the list does not update this instance.
304     * </p>
305     *
306     * @return a new List
307     * @since 1.9.0
308     */
309    public List<String> toList() {
310        return stream().collect(Collectors.toList());
311    }
312
313    /**
314     * Copies this record into a new Map of header name to record value.
315     * <p>
316     * Editing the map does not update this instance.
317     * </p>
318     *
319     * @return A new Map. The map is empty if the record has no headers.
320     */
321    public Map<String, String> toMap() {
322        return putIn(new LinkedHashMap<>(values.length));
323    }
324
325    /**
326     * Returns a string representation of the contents of this record. The result is constructed by comment, mapping,
327     * recordNumber and by passing the internal values array to {@link Arrays#toString(Object[])}.
328     *
329     * @return a String representation of this record.
330     */
331    @Override
332    public String toString() {
333        return "CSVRecord [comment='" + comment + "', recordNumber=" + recordNumber + ", values=" +
334            Arrays.toString(values) + "]";
335    }
336
337    /**
338     * Gets the values for this record. This is not a copy.
339     *
340     * @return the values for this record.
341     * @since 1.10.0
342     */
343    public String[] values() {
344        return values;
345    }
346
347}