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    /**
074     * An empty immutable {@code FTPFile} array.
075     */
076    private static final FTPFile[] EMPTY_FTP_FILE_ARRAY = {};
077    private List<String> entries = new LinkedList<>();
078
079    private ListIterator<String> internalIterator = entries.listIterator();
080    private final FTPFileEntryParser parser;
081
082    // Should invalid files (parse failures) be allowed?
083    private final boolean saveUnparseableEntries;
084
085    /**
086     * Constructs a new instance.
087     *
088     * @param parser How to parse file entries.
089     */
090    public FTPListParseEngine(final FTPFileEntryParser parser) {
091        this(parser, null);
092    }
093
094    /**
095     * Intended for use by FTPClient only
096     *
097     * @since 3.4
098     */
099    FTPListParseEngine(final FTPFileEntryParser parser, final FTPClientConfig configuration) {
100        this.parser = parser;
101        this.saveUnparseableEntries = configuration != null && configuration.getUnparseableEntries();
102    }
103
104    /**
105     * 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
106     * before being added to the array.
107     *
108     * @param filter FTPFileFilter, must not be {@code null}.
109     * @return a list of FTPFile objects containing the whole list of files returned by the server as read by this object's parser.
110     *         <p>
111     *         <strong> NOTE:</strong> This array may contain null members if any of the individual file listings failed to parse. The caller should check each
112     *         entry for null before referencing it, or use a filter such as {@link FTPFileFilters#NON_NULL} which does not allow null entries.
113     * @since 3.9.0
114     */
115    public List<FTPFile> getFileList(final FTPFileFilter filter) {
116        return entries.stream().map(e -> {
117            final FTPFile file = parser.parseFTPEntry(e);
118            return file == null && saveUnparseableEntries ? new FTPFile(e) : file;
119        }).filter(filter::accept).collect(Collectors.toList());
120    }
121
122    /**
123     * Gets an array of FTPFile objects containing the whole list of files returned by the server as read by this object's parser.
124     *
125     * @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
126     *         be null
127     * @throws IOException - not ever thrown, may be removed in a later release
128     */
129    // TODO remove; not actually thrown
130    public FTPFile[] getFiles() throws IOException {
131        return getFiles(FTPFileFilters.NON_NULL);
132    }
133
134    /**
135     * 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
136     * before being added to the array.
137     *
138     * @param filter FTPFileFilter, must not be {@code null}.
139     * @return an array of FTPFile objects containing the whole list of files returned by the server as read by this object's parser.
140     *         <p>
141     *         <strong> NOTE:</strong> This array may contain null members if any of the individual file listings failed to parse. The caller should check each
142     *         entry for null before referencing it, or use a filter such as {@link FTPFileFilters#NON_NULL} which does not allow null entries.
143     * @throws IOException - not ever thrown, may be removed in a later release
144     * @since 2.2
145     */
146    // TODO remove; not actually thrown
147    public FTPFile[] getFiles(final FTPFileFilter filter) throws IOException {
148        return getFileList(filter).toArray(EMPTY_FTP_FILE_ARRAY);
149    }
150
151    /**
152     * Gets an array of at most {@code quantityRequested} FTPFile objects starting at this object's internal iterator's current position. If fewer than
153     * {@code quantityRequested} such elements are available, the returned array will have a length equal to the number of entries at and after the current
154     * position. If no such entries are found, this array will have a length of 0.
155     *
156     * 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.
157     *
158     * @param quantityRequested the maximum number of entries we want to get.
159     * @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
160     *         number of elements which exist in the list at and after its current position.
161     *         <p>
162     *         <strong> NOTE:</strong> This array may contain null members if any of the individual file listings failed to parse. The caller should check each
163     *         entry for null before referencing it.
164     */
165    public FTPFile[] getNext(final int quantityRequested) {
166        final List<FTPFile> tmpResults = new LinkedList<>();
167        int count = quantityRequested;
168        while (count > 0 && internalIterator.hasNext()) {
169            final String entry = internalIterator.next();
170            FTPFile temp = parser.parseFTPEntry(entry);
171            if (temp == null && saveUnparseableEntries) {
172                temp = new FTPFile(entry);
173            }
174            tmpResults.add(temp);
175            count--;
176        }
177        return tmpResults.toArray(EMPTY_FTP_FILE_ARRAY);
178
179    }
180
181    /**
182     * Gets an array of at most {@code quantityRequested} FTPFile objects starting at this object's internal iterator's current position, and working back
183     * toward the beginning.
184     *
185     * 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
186     * the current position. If no such entries are found, this array will have a length of 0.
187     *
188     * 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.
189     *
190     * @param quantityRequested the maximum number of entries we want to get.
191     * @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
192     *         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
193     *         reversed).
194     *         <p>
195     *         <strong> NOTE:</strong> This array may contain null members if any of the individual file listings failed to parse. The caller should check each
196     *         entry for null before referencing it.
197     */
198    public FTPFile[] getPrevious(final int quantityRequested) {
199        final List<FTPFile> tmpResults = new LinkedList<>();
200        int count = quantityRequested;
201        while (count > 0 && internalIterator.hasPrevious()) {
202            final String entry = internalIterator.previous();
203            FTPFile temp = parser.parseFTPEntry(entry);
204            if (temp == null && saveUnparseableEntries) {
205                temp = new FTPFile(entry);
206            }
207            tmpResults.add(0, temp);
208            count--;
209        }
210        return tmpResults.toArray(EMPTY_FTP_FILE_ARRAY);
211    }
212
213    /**
214     * convenience method to allow clients to know whether this object's internal iterator's current position is at the end of the list.
215     *
216     * @return true if internal iterator is not at end of list, false otherwise.
217     */
218    public boolean hasNext() {
219        return internalIterator.hasNext();
220    }
221
222    /**
223     * convenience method to allow clients to know whether this object's internal iterator's current position is at the beginning of the list.
224     *
225     * @return true if internal iterator is not at beginning of list, false otherwise.
226     */
227    public boolean hasPrevious() {
228        return internalIterator.hasPrevious();
229    }
230
231    /**
232     * Internal method for reading (and closing) the input into the {@code entries} list. After this method has completed, {@code entries} will contain a
233     * collection of entries (as defined by {@code FTPFileEntryParser.readNextEntry()}), but this may contain various non-entry preliminary lines from the
234     * server output, duplicates, and other data that will not be part of the final listing.
235     *
236     * @param inputStream The socket stream on which the input will be read.
237     * @param charsetName The encoding to use.
238     * @throws IOException thrown on any failure to read the stream
239     */
240    private void read(final InputStream inputStream, final String charsetName) throws IOException {
241        try (BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream, Charsets.toCharset(charsetName)))) {
242            String line = parser.readNextEntry(reader);
243            while (line != null) {
244                entries.add(line);
245                line = parser.readNextEntry(reader);
246            }
247        }
248    }
249
250    /**
251     * Do not use.
252     *
253     * @param inputStream the stream from which to read
254     * @throws IOException on error
255     * @deprecated Use {@link #readServerList(InputStream, String)} instead
256     */
257    @Deprecated
258    public void readServerList(final InputStream inputStream) throws IOException {
259        readServerList(inputStream, null);
260    }
261
262    /**
263     * 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
264     * list of unparsed entries (Strings) each referring to a unique file on the server.
265     *
266     * @param inputStream input stream provided by the server socket.
267     * @param charsetName the encoding to be used for reading the stream
268     * @throws IOException thrown on any failure to read from the sever.
269     */
270    public void readServerList(final InputStream inputStream, final String charsetName) throws IOException {
271        entries = new LinkedList<>();
272        read(inputStream, charsetName);
273        parser.preParse(entries);
274        resetIterator();
275    }
276
277    /**
278     * resets this object's internal iterator to the beginning of the list.
279     */
280    public void resetIterator() {
281        internalIterator = entries.listIterator();
282    }
283
284}