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 *      https://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.net.ftp;
019
020import java.io.BufferedReader;
021import java.io.IOException;
022import java.io.InputStream;
023import java.io.InputStreamReader;
024import java.util.LinkedList;
025import java.util.List;
026import java.util.ListIterator;
027import java.util.stream.Collectors;
028
029import org.apache.commons.io.Charsets;
030
031
032/**
033 * This class handles the entire process of parsing a listing of file entries from the server.
034 * <p>
035 * This object defines a two-part parsing mechanism.
036 * </p>
037 * <p>
038 * The first part consists of reading the raw input into an internal list of strings. Every item in this list corresponds to an actual file. All extraneous
039 * matter emitted by the server will have been removed by the end of this phase. This is accomplished in conjunction with the FTPFileEntryParser associated with
040 * this engine, by calling its methods {@code readNextEntry()} - which handles the issue of what delimits one entry from another, usually but not always a line
041 * feed and {@code preParse()} - which handles removal of extraneous matter such as the preliminary lines of a listing, removal of duplicates on versioning
042 * systems, etc.
043 * </p>
044 * <p>
045 * The second part is composed of the actual parsing, again in conjunction with the particular parser used by this engine. This is controlled by an iterator
046 * over the internal list of strings. This may be done either in block mode, by calling the {@code getNext()} and {@code getPrevious()} methods to provide
047 * "paged" output of less than the whole list at one time, or by calling the {@code getFiles()} method to return the entire list.
048 * </p>
049 * <p>
050 * Examples:
051 * </p>
052 * <p>
053 * Paged access:
054 * </p>
055 * <pre>
056 * FTPClient f = FTPClient();
057 * f.connect(server);
058 * f.login(user, password);
059 * FTPListParseEngine engine = f.initiateListParsing(directory);
060 *
061 * while (engine.hasNext()) {
062 *     FTPFile[] files = engine.getNext(25); // "page size" you want
063 *     // do whatever you want with these files, display them, etc.
064 *     // expensive FTPFile objects not created until needed.
065 * }
066 * </pre>
067 * <p>
068 * For unpaged access, simply use FTPClient.listFiles(). That method uses this class transparently.
069 * </p>
070 */
071public class FTPListParseEngine {
072    /**
073     * An empty immutable {@code FTPFile} array.
074     */
075    private static final FTPFile[] EMPTY_FTP_FILE_ARRAY = {};
076    private List<String> entries = new LinkedList<>();
077
078    private ListIterator<String> internalIterator = entries.listIterator();
079    private final FTPFileEntryParser parser;
080
081    // Should invalid files (parse failures) be allowed?
082    private final boolean saveUnparseableEntries;
083
084    /**
085     * Constructs a new instance.
086     *
087     * @param parser How to parse file entries.
088     */
089    public FTPListParseEngine(final FTPFileEntryParser parser) {
090        this(parser, null);
091    }
092
093    /**
094     * Intended for use by FTPClient only
095     *
096     * @since 3.4
097     */
098    FTPListParseEngine(final FTPFileEntryParser parser, final FTPClientConfig configuration) {
099        this.parser = parser;
100        this.saveUnparseableEntries = configuration != null && configuration.getUnparseableEntries();
101    }
102
103    /**
104     * Gets a list of FTPFile objects containing the whole list of files returned by the server as read by this object's parser. The files are filtered
105     * before being added to the array.
106     *
107     * @param filter FTPFileFilter, must not be {@code null}.
108     * @return a list of FTPFile objects containing the whole list of files returned by the server as read by this object's parser.
109     *         <p>
110     *         <strong> NOTE:</strong> This array may contain null members if any of the individual file listings failed to parse. The caller should check each
111     *         entry for null before referencing it, or use a filter such as {@link FTPFileFilters#NON_NULL} which does not allow null entries.
112     * @since 3.9.0
113     */
114    public List<FTPFile> getFileList(final FTPFileFilter filter) {
115        return entries.stream().map(e -> {
116            final FTPFile file = parser.parseFTPEntry(e);
117            return file == null && saveUnparseableEntries ? new FTPFile(e) : file;
118        }).filter(filter::accept).collect(Collectors.toList());
119    }
120
121    /**
122     * Gets an array of FTPFile objects containing the whole list of files returned by the server as read by this object's parser.
123     *
124     * @return an array of FTPFile objects containing the whole list of files returned by the server as read by this object's parser. None of the entries will
125     *         be null
126     * @throws IOException - not ever thrown, may be removed in a later release
127     */
128    // TODO remove; not actually thrown
129    public FTPFile[] getFiles() throws IOException {
130        return getFiles(FTPFileFilters.NON_NULL);
131    }
132
133    /**
134     * Gets an array of FTPFile objects containing the whole list of files returned by the server as read by this object's parser. The files are filtered
135     * before being added to the array.
136     *
137     * @param filter FTPFileFilter, must not be {@code null}.
138     * @return an array of FTPFile objects containing the whole list of files returned by the server as read by this object's parser.
139     *         <p>
140     *         <strong> NOTE:</strong> This array may contain null members if any of the individual file listings failed to parse. The caller should check each
141     *         entry for null before referencing it, or use a filter such as {@link FTPFileFilters#NON_NULL} which does not allow null entries.
142     * @throws IOException - not ever thrown, may be removed in a later release
143     * @since 2.2
144     */
145    // TODO remove; not actually thrown
146    public FTPFile[] getFiles(final FTPFileFilter filter) throws IOException {
147        return getFileList(filter).toArray(EMPTY_FTP_FILE_ARRAY);
148    }
149
150    /**
151     * Gets an array of at most {@code quantityRequested} FTPFile objects starting at this object's internal iterator's current position. If fewer than
152     * {@code quantityRequested} such elements are available, the returned array will have a length equal to the number of entries at and after the current
153     * position. If no such entries are found, this array will have a length of 0.
154     *
155     * After this method is called this object's internal iterator is advanced by a number of positions equal to the size of the array returned.
156     *
157     * @param quantityRequested the maximum number of entries we want to get.
158     * @return an array of at most {@code quantityRequested} FTPFile objects starting at the current position of this iterator within its list and at least the
159     *         number of elements which exist in the list at and after its current position.
160     *         <p>
161     *         <strong> NOTE:</strong> This array may contain null members if any of the individual file listings failed to parse. The caller should check each
162     *         entry for null before referencing it.
163     */
164    public FTPFile[] getNext(final int quantityRequested) {
165        final List<FTPFile> tmpResults = new LinkedList<>();
166        int count = quantityRequested;
167        while (count > 0 && internalIterator.hasNext()) {
168            final String entry = internalIterator.next();
169            FTPFile temp = parser.parseFTPEntry(entry);
170            if (temp == null && saveUnparseableEntries) {
171                temp = new FTPFile(entry);
172            }
173            tmpResults.add(temp);
174            count--;
175        }
176        return tmpResults.toArray(EMPTY_FTP_FILE_ARRAY);
177
178    }
179
180    /**
181     * Gets an array of at most {@code quantityRequested} FTPFile objects starting at this object's internal iterator's current position, and working back
182     * toward the beginning.
183     *
184     * If fewer than {@code quantityRequested} such elements are available, the returned array will have a length equal to the number of entries at and after
185     * the current position. If no such entries are found, this array will have a length of 0.
186     *
187     * After this method is called this object's internal iterator is moved back by a number of positions equal to the size of the array returned.
188     *
189     * @param quantityRequested the maximum number of entries we want to get.
190     * @return an array of at most {@code quantityRequested} FTPFile objects starting at the current position of this iterator within its list and at least the
191     *         number of elements which exist in the list at and after its current position. This array will be in the same order as the underlying list (not
192     *         reversed).
193     *         <p>
194     *         <strong> NOTE:</strong> This array may contain null members if any of the individual file listings failed to parse. The caller should check each
195     *         entry for null before referencing it.
196     */
197    public FTPFile[] getPrevious(final int quantityRequested) {
198        final List<FTPFile> tmpResults = new LinkedList<>();
199        int count = quantityRequested;
200        while (count > 0 && internalIterator.hasPrevious()) {
201            final String entry = internalIterator.previous();
202            FTPFile temp = parser.parseFTPEntry(entry);
203            if (temp == null && saveUnparseableEntries) {
204                temp = new FTPFile(entry);
205            }
206            tmpResults.add(0, temp);
207            count--;
208        }
209        return tmpResults.toArray(EMPTY_FTP_FILE_ARRAY);
210    }
211
212    /**
213     * convenience method to allow clients to know whether this object's internal iterator's current position is at the end of the list.
214     *
215     * @return true if internal iterator is not at end of list, false otherwise.
216     */
217    public boolean hasNext() {
218        return internalIterator.hasNext();
219    }
220
221    /**
222     * convenience method to allow clients to know whether this object's internal iterator's current position is at the beginning of the list.
223     *
224     * @return true if internal iterator is not at beginning of list, false otherwise.
225     */
226    public boolean hasPrevious() {
227        return internalIterator.hasPrevious();
228    }
229
230    /**
231     * Internal method for reading (and closing) the input into the {@code entries} list. After this method has completed, {@code entries} will contain a
232     * collection of entries (as defined by {@code FTPFileEntryParser.readNextEntry()}), but this may contain various non-entry preliminary lines from the
233     * server output, duplicates, and other data that will not be part of the final listing.
234     *
235     * @param inputStream The socket stream on which the input will be read.
236     * @param charsetName The encoding to use.
237     * @throws IOException thrown on any failure to read the stream
238     */
239    private void read(final InputStream inputStream, final String charsetName) throws IOException {
240        try (BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream, Charsets.toCharset(charsetName)))) {
241            String line = parser.readNextEntry(reader);
242            while (line != null) {
243                entries.add(line);
244                line = parser.readNextEntry(reader);
245            }
246        }
247    }
248
249    /**
250     * Do not use.
251     *
252     * @param inputStream the stream from which to read
253     * @throws IOException on error
254     * @deprecated use {@link #readServerList(InputStream, String)} instead
255     */
256    @Deprecated
257    public void readServerList(final InputStream inputStream) throws IOException {
258        readServerList(inputStream, null);
259    }
260
261    /**
262     * Reads (and closes) the initial reading and preparsing of the list returned by the server. After this method has completed, this object will contain a
263     * list of unparsed entries (Strings) each referring to a unique file on the server.
264     *
265     * @param inputStream input stream provided by the server socket.
266     * @param charsetName the encoding to be used for reading the stream
267     * @throws IOException thrown on any failure to read from the sever.
268     */
269    public void readServerList(final InputStream inputStream, final String charsetName) throws IOException {
270        entries = new LinkedList<>();
271        read(inputStream, charsetName);
272        parser.preParse(entries);
273        resetIterator();
274    }
275
276    /**
277     * resets this object's internal iterator to the beginning of the list.
278     */
279    public void resetIterator() {
280        internalIterator = entries.listIterator();
281    }
282
283}