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.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.net.util.Charsets;
030
031/**
032 * This class handles the entire process of parsing a listing of file entries from the server.
033 * <p>
034 * This object defines a two-part parsing mechanism.
035 * <p>
036 * 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
037 * 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
038 * this engine, by calling its methods <code>readNextEntry()</code> - which handles the issue of what delimits one entry from another, usually but not always a
039 * line feed and <code>preParse()</code> - which handles removal of extraneous matter such as the preliminary lines of a listing, removal of duplicates on
040 * versioning systems, etc.
041 * <p>
042 * 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
043 * over the internal list of strings. This may be done either in block mode, by calling the <code>getNext()</code> and <code>getPrevious()</code> methods to
044 * provide "paged" output of less than the whole list at one time, or by calling the <code>getFiles()</code> method to return the entire list.
045 * <p>
046 * Examples:
047 * <p>
048 * Paged access:
049 *
050 * <pre>
051 * FTPClient f = FTPClient();
052 * f.connect(server);
053 * f.login(user, password);
054 * FTPListParseEngine engine = f.initiateListParsing(directory);
055 *
056 * while (engine.hasNext()) {
057 *     FTPFile[] files = engine.getNext(25); // "page size" you want
058 *     // do whatever you want with these files, display them, etc.
059 *     // expensive FTPFile objects not created until needed.
060 * }
061 * </pre>
062 * <p>
063 * For unpaged access, simply use FTPClient.listFiles(). That method uses this class transparently.
064 */
065public class FTPListParseEngine {
066    /**
067     * An empty immutable {@code FTPFile} array.
068     */
069    private static final FTPFile[] EMPTY_FTP_FILE_ARRAY = {};
070    private List<String> entries = new LinkedList<>();
071
072    private ListIterator<String> internalIterator = entries.listIterator();
073    private final FTPFileEntryParser parser;
074
075    // Should invalid files (parse failures) be allowed?
076    private final boolean saveUnparseableEntries;
077
078    public FTPListParseEngine(final FTPFileEntryParser parser) {
079        this(parser, null);
080    }
081
082    /**
083     * Intended for use by FTPClient only
084     *
085     * @since 3.4
086     */
087    FTPListParseEngine(final FTPFileEntryParser parser, final FTPClientConfig configuration) {
088        this.parser = parser;
089        if (configuration != null) {
090            this.saveUnparseableEntries = configuration.getUnparseableEntries();
091        } else {
092            this.saveUnparseableEntries = false;
093        }
094    }
095
096    /**
097     * Returns 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
098     * before being added to the array.
099     *
100     * @param filter FTPFileFilter, must not be <code>null</code>.
101     *
102     * @return a list of FTPFile objects containing the whole list of files returned by the server as read by this object's parser.
103     *         <p>
104     *         <b> NOTE:</b> This array may contain null members if any of the individual file listings failed to parse. The caller should check each entry for
105     *         null before referencing it, or use a filter such as {@link FTPFileFilters#NON_NULL} which does not allow null entries.
106     * @since 3.9.0
107     */
108    public List<FTPFile> getFileList(final FTPFileFilter filter) {
109        return entries.stream().map(e -> {
110            final FTPFile file = parser.parseFTPEntry(e);
111            return file == null && saveUnparseableEntries ? new FTPFile(e) : file;
112        }).filter(filter::accept).collect(Collectors.toList());
113    }
114
115    /**
116     * Returns an array of FTPFile objects containing the whole list of files returned by the server as read by this object's parser.
117     *
118     * @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
119     *         be null
120     * @throws IOException - not ever thrown, may be removed in a later release
121     */
122    public FTPFile[] getFiles() throws IOException // TODO remove; not actually thrown
123    {
124        return getFiles(FTPFileFilters.NON_NULL);
125    }
126
127    /**
128     * Returns 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
129     * before being added to the array.
130     *
131     * @param filter FTPFileFilter, must not be <code>null</code>.
132     *
133     * @return an array of FTPFile objects containing the whole list of files returned by the server as read by this object's parser.
134     *         <p>
135     *         <b> NOTE:</b> This array may contain null members if any of the individual file listings failed to parse. The caller should check each entry for
136     *         null before referencing it, or use a filter such as {@link FTPFileFilters#NON_NULL} which does not allow null entries.
137     * @since 2.2
138     * @throws IOException - not ever thrown, may be removed in a later release
139     */
140    public FTPFile[] getFiles(final FTPFileFilter filter) throws IOException // TODO remove; not actually thrown
141    {
142        return getFileList(filter).toArray(EMPTY_FTP_FILE_ARRAY);
143    }
144
145    /**
146     * Returns an array of at most <code>quantityRequested</code> FTPFile objects starting at this object's internal iterator's current position. If fewer than
147     * <code>quantityRequested</code> such elements are available, the returned array will have a length equal to the number of entries at and after the
148     * current position. If no such entries are found, this array will have a length of 0.
149     *
150     * 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.
151     *
152     * @param quantityRequested the maximum number of entries we want to get.
153     *
154     * @return an array of at most <code>quantityRequested</code> FTPFile objects starting at the current position of this iterator within its list and at least
155     *         the number of elements which exist in the list at and after its current position.
156     *         <p>
157     *         <b> NOTE:</b> This array may contain null members if any of the individual file listings failed to parse. The caller should check each entry for
158     *         null before referencing it.
159     */
160    public FTPFile[] getNext(final int quantityRequested) {
161        final List<FTPFile> tmpResults = new LinkedList<>();
162        int count = quantityRequested;
163        while (count > 0 && this.internalIterator.hasNext()) {
164            final String entry = this.internalIterator.next();
165            FTPFile temp = this.parser.parseFTPEntry(entry);
166            if (temp == null && saveUnparseableEntries) {
167                temp = new FTPFile(entry);
168            }
169            tmpResults.add(temp);
170            count--;
171        }
172        return tmpResults.toArray(EMPTY_FTP_FILE_ARRAY);
173
174    }
175
176    /**
177     * Returns an array of at most <code>quantityRequested</code> FTPFile objects starting at this object's internal iterator's current position, and working
178     * back toward the beginning.
179     *
180     * If fewer than <code>quantityRequested</code> such elements are available, the returned array will have a length equal to the number of entries at and
181     * after the current position. If no such entries are found, this array will have a length of 0.
182     *
183     * 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.
184     *
185     * @param quantityRequested the maximum number of entries we want to get.
186     *
187     * @return an array of at most <code>quantityRequested</code> FTPFile objects starting at the current position of this iterator within its list and at least
188     *         the 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
189     *         (not reversed).
190     *         <p>
191     *         <b> NOTE:</b> This array may contain null members if any of the individual file listings failed to parse. The caller should check each entry for
192     *         null before referencing it.
193     */
194    public FTPFile[] getPrevious(final int quantityRequested) {
195        final List<FTPFile> tmpResults = new LinkedList<>();
196        int count = quantityRequested;
197        while (count > 0 && this.internalIterator.hasPrevious()) {
198            final String entry = this.internalIterator.previous();
199            FTPFile temp = this.parser.parseFTPEntry(entry);
200            if (temp == null && saveUnparseableEntries) {
201                temp = new FTPFile(entry);
202            }
203            tmpResults.add(0, temp);
204            count--;
205        }
206        return tmpResults.toArray(EMPTY_FTP_FILE_ARRAY);
207    }
208
209    /**
210     * convenience method to allow clients to know whether this object's internal iterator's current position is at the end of the list.
211     *
212     * @return true if internal iterator is not at end of list, false otherwise.
213     */
214    public boolean hasNext() {
215        return internalIterator.hasNext();
216    }
217
218    /**
219     * convenience method to allow clients to know whether this object's internal iterator's current position is at the beginning of the list.
220     *
221     * @return true if internal iterator is not at beginning of list, false otherwise.
222     */
223    public boolean hasPrevious() {
224        return internalIterator.hasPrevious();
225    }
226
227    /**
228     * Internal method for reading (and closing) the input into the <code>entries</code> list. After this method has completed, <code>entries</code> will
229     * contain a collection of entries (as defined by <code>FTPFileEntryParser.readNextEntry()</code>), but this may contain various non-entry preliminary lines
230     * from the server output, duplicates, and other data that will not be part of the final listing.
231     *
232     * @param inputStream The socket stream on which the input will be read.
233     * @param charsetName The encoding to use.
234     *
235     * @throws IOException thrown on any failure to read the stream
236     */
237    private void read(final InputStream inputStream, final String charsetName) throws IOException {
238        try (final BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream, Charsets.toCharset(charsetName)))) {
239
240            String line = this.parser.readNextEntry(reader);
241
242            while (line != null) {
243                this.entries.add(line);
244                line = this.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     *
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        this.entries = new LinkedList<>();
272        read(inputStream, charsetName);
273        this.parser.preParse(this.entries);
274        resetIterator();
275    }
276
277    // DEPRECATED METHODS - for API compatibility only - DO NOT USE
278
279    /**
280     * resets this object's internal iterator to the beginning of the list.
281     */
282    public void resetIterator() {
283        this.internalIterator = this.entries.listIterator();
284    }
285
286}