2 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
3 * Copyright (C) $$Year-Rel$$ The Jalview Authors
5 * This file is part of Jalview.
7 * Jalview is free software: you can redistribute it and/or
8 * modify it under the terms of the GNU General Public License
9 * as published by the Free Software Foundation, either version 3
10 * of the License, or (at your option) any later version.
12 * Jalview is distributed in the hope that it will be useful, but
13 * WITHOUT ANY WARRANTY; without even the implied warranty
14 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
15 * PURPOSE. See the GNU General Public License for more details.
17 * You should have received a copy of the GNU General Public License
18 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
19 * The Jalview Authors are detailed in the 'AUTHORS' file.
23 import jalview.api.AlignExportSettingsI;
24 import jalview.api.AlignViewportI;
25 import jalview.api.AlignmentViewPanel;
26 import jalview.api.FeatureSettingsModelI;
27 import jalview.util.MessageManager;
29 import java.io.BufferedInputStream;
30 import java.io.BufferedReader;
31 import java.io.ByteArrayInputStream;
33 import java.io.FileInputStream;
34 import java.io.FileReader;
35 import java.io.IOException;
36 import java.io.InputStream;
37 import java.io.InputStreamReader;
38 import java.io.Reader;
39 import java.io.StringReader;
40 import java.net.HttpURLConnection;
41 import java.net.MalformedURLException;
43 import java.net.URLConnection;
44 import java.util.zip.GZIPInputStream;
46 import jalview.util.Platform;
49 * implements a random access wrapper around a particular datasource, for
50 * passing to identifyFile and AlignFile objects.
52 public class FileParse
54 protected static final String SPACE = " ";
56 protected static final String TAB = "\t";
59 * text specifying source of data. usually filename or url.
61 private String dataName = "unknown source";
63 public File inFile = null;
65 private byte[] bytes; // from JavaScript
67 public byte[] getBytes()
73 * a viewport associated with the current file operation. May be null. May
74 * move to different object.
76 private AlignViewportI viewport;
79 * specific settings for exporting data from the current context
81 private AlignExportSettingsI exportSettings;
84 * sequence counter for FileParse object created from same data source
89 * separator for extracting specific 'frame' of a datasource for formats that
90 * support multiple records (e.g. BLC, Stockholm, etc)
92 protected char suffixSeparator = '#';
95 * character used to write newlines
97 protected String newline = System.getProperty("line.separator");
99 public void setNewlineString(String nl)
104 public String getNewlineString()
110 * '#' separated string tagged on to end of filename or url that was clipped
111 * off to resolve to valid filename
113 protected String suffix = null;
115 protected DataSourceType dataSourceType = null;
117 protected BufferedReader dataIn = null;
119 protected String errormessage = "UNINITIALISED SOURCE";
121 protected boolean error = true;
123 protected String warningMessage = null;
126 * size of readahead buffer used for when initial stream position is marked.
128 final int READAHEAD_LIMIT = 2048;
135 * Create a new FileParse instance reading from the same datasource starting
136 * at the current position. WARNING! Subsequent reads from either object will
137 * affect the read position of the other, but not the error state.
141 public FileParse(FileParse from) throws IOException
145 throw new Error(MessageManager
146 .getString("error.implementation_error_null_fileparse"));
152 index = ++from.index;
153 inFile = from.inFile;
154 suffixSeparator = from.suffixSeparator;
155 suffix = from.suffix;
156 errormessage = from.errormessage; // inherit potential error messages
157 error = false; // reset any error condition.
158 dataSourceType = from.dataSourceType;
159 dataIn = from.dataIn;
164 dataName = from.dataName;
168 * Attempt to open a file as a datasource. Sets error and errormessage if
169 * fileStr was invalid.
172 * @return this.error (true if the source was invalid)
174 private boolean checkFileSource(String fileStr) throws IOException
177 this.inFile = new File(fileStr);
178 // check to see if it's a Jar file in disguise.
179 if (!inFile.exists())
181 errormessage = "FILE NOT FOUND";
184 if (!inFile.canRead())
186 errormessage = "FILE CANNOT BE OPENED FOR READING";
189 if (inFile.isDirectory())
191 // this is really a 'complex' filetype - but we don't handle directory
193 errormessage = "FILE IS A DIRECTORY";
200 dataIn = checkForGzipStream(new FileInputStream(fileStr));
202 } catch (Exception x)
204 warningMessage = "Failed to resolve " + fileStr
205 + " as a data source. (" + x.getMessage() + ")";
206 // x.printStackTrace();
215 * Recognise the 2-byte magic header for gzip streams
217 * https://recalll.co/ask/v/topic/java-How-to-check-if-InputStream-is-Gzipped/555aadd62bd27354438b90f6
219 * @param bytes - at least two bytes
222 private static boolean isGzipStream(byte[] bytes) {
223 int head = ((int) bytes[0] & 0xff) | ((bytes[1] << 8) & 0xff00);
224 return (GZIPInputStream.GZIP_MAGIC == head);
228 * Returns a Reader for the given input after wrapping it in a buffered input
229 * stream, and then checking if it needs to be wrapped by a GZipInputStream
234 private BufferedReader checkForGzipStream(InputStream input) throws Exception {
236 // NB: stackoverflow https://stackoverflow.com/questions/4818468/how-to-check-if-inputstream-is-gzipped
237 // could use a PushBackInputStream rather than a BufferedInputStream
239 BufferedInputStream bufinput;
240 if (!input.markSupported()) {
241 bufinput= new BufferedInputStream(input,16);
245 byte[] bytes=input.readNBytes(2);
247 if (bytes.length==2 && isGzipStream(bytes)) {
248 return getGzipReader(input);
250 // return a buffered reader for the stream.
251 InputStreamReader isReader= new InputStreamReader(input);
252 BufferedReader toReadFrom=new BufferedReader(isReader);
256 * Returns a {@code BufferedReader} which wraps the input stream with a
257 * GZIPInputStream. Throws a {@code ZipException} if a GZIP format error
258 * occurs or the compression method used is unsupported.
264 private BufferedReader getGzipReader(InputStream inputStream)
267 BufferedReader inData = new BufferedReader(
268 new InputStreamReader(new GZIPInputStream(inputStream)));
276 * Tries to read from the given URL. If successful, saves a reader to the
277 * response in field {@code dataIn}, otherwise (on exception, or HTTP response
278 * status not 200), throws an exception.
280 * If the response status includes
283 * Content-Type : application/x-gzip
286 * then tries to read as gzipped content.
289 * @throws IOException
290 * @throws MalformedURLException
292 private void checkURLSource(String urlStr)
293 throws IOException, MalformedURLException
295 errormessage = "URL NOT FOUND";
296 URL url = new URL(urlStr);
297 URLConnection _conn = url.openConnection();
298 if (_conn instanceof HttpURLConnection)
300 HttpURLConnection conn = (HttpURLConnection) _conn;
301 int rc = conn.getResponseCode();
302 if (rc != HttpURLConnection.HTTP_OK)
304 throw new IOException(
305 "Response status from " + urlStr + " was " + rc);
309 dataIn = checkForGzipStream(_conn.getInputStream());
311 } catch (IOException ex)
313 throw new IOException("Failed to handle non-HTTP URI stream",ex);
314 } catch (Exception ex)
316 throw new IOException("Failed to determine type of input stream for given URI",ex);
320 String encoding = _conn.getContentEncoding();
321 String contentType = _conn.getContentType();
322 boolean isgzipped = "application/x-gzip".equalsIgnoreCase(contentType)
323 || "gzip".equals(encoding);
325 InputStream inputStream = _conn.getInputStream();
330 dataIn = getGzipReader(inputStream);
332 } catch (Exception e1)
334 throw new IOException(MessageManager
335 .getString("exception.failed_to_resolve_gzip_stream"), e);
340 dataIn = new BufferedReader(new InputStreamReader(inputStream));
346 * sets the suffix string (if any) and returns remainder (if suffix was
350 * @return truncated fileStr or null
352 private String extractSuffix(String fileStr)
354 // first check that there wasn't a suffix string tagged on.
355 int sfpos = fileStr.lastIndexOf(suffixSeparator);
356 if (sfpos > -1 && sfpos < fileStr.length() - 1)
358 suffix = fileStr.substring(sfpos + 1);
359 // System.err.println("DEBUG: Found Suffix:"+suffix);
360 return fileStr.substring(0, sfpos);
366 * not for general use, creates a fileParse object for an existing reader with
367 * configurable values for the origin and the type of the source
369 public FileParse(BufferedReader source, String originString,
370 DataSourceType sourceType)
372 dataSourceType = sourceType;
375 dataName = originString;
379 if (dataIn.markSupported())
381 dataIn.mark(READAHEAD_LIMIT);
383 } catch (IOException q)
390 * Create a datasource for input to Jalview. See AppletFormatAdapter for the
391 * types of sources that are handled.
394 * - datasource locator/content as File or String
396 * - protocol of source
397 * @throws MalformedURLException
398 * @throws IOException
400 public FileParse(Object file, DataSourceType sourceType)
401 throws MalformedURLException, IOException
403 if (file instanceof File)
405 parse((File) file, ((File) file).getPath(), sourceType, true);
409 parse(null, file.toString(), sourceType, false);
413 private void parse(File file, String fileStr, DataSourceType sourceType,
414 boolean isFileObject) throws IOException
416 bytes = Platform.getFileBytes(file);
417 dataSourceType = sourceType;
420 if (sourceType == DataSourceType.FILE)
425 // this will be from JavaScript
427 dataIn = new BufferedReader(
428 new InputStreamReader(new ByteArrayInputStream(bytes)));
431 else if (checkFileSource(fileStr))
433 String suffixLess = extractSuffix(fileStr);
434 if (suffixLess != null)
436 if (checkFileSource(suffixLess))
438 throw new IOException(MessageManager.formatMessage(
439 "exception.problem_opening_file_also_tried",
441 { inFile.getName(), suffixLess, errormessage }));
446 throw new IOException(MessageManager.formatMessage(
447 "exception.problem_opening_file", new String[]
448 { inFile.getName(), errormessage }));
452 else if (sourceType == DataSourceType.RELATIVE_URL)
454 // BH 2018 hack for no support for access-origin
455 bytes = Platform.getFileAsBytes(fileStr);
456 dataIn = new BufferedReader(
457 new InputStreamReader(new ByteArrayInputStream(bytes)));
461 else if (sourceType == DataSourceType.URL)
467 checkURLSource(fileStr);
468 if (suffixSeparator == '#')
470 extractSuffix(fileStr); // URL lref is stored for later reference.
472 } catch (IOException e)
474 String suffixLess = extractSuffix(fileStr);
475 if (suffixLess == null)
483 checkURLSource(suffixLess);
484 } catch (IOException e2)
486 errormessage = "BAD URL WITH OR WITHOUT SUFFIX";
487 throw (e); // just pass back original - everything was wrong.
491 } catch (Exception e)
493 errormessage = "CANNOT ACCESS DATA AT URL '" + fileStr + "' ("
494 + e.getMessage() + ")";
498 else if (sourceType == DataSourceType.PASTE)
500 errormessage = "PASTE INACCESSIBLE!";
501 dataIn = new BufferedReader(new StringReader(fileStr));
504 else if (sourceType == DataSourceType.CLASSLOADER)
506 errormessage = "RESOURCE CANNOT BE LOCATED";
507 InputStream is = getClass().getResourceAsStream("/" + fileStr);
510 String suffixLess = extractSuffix(fileStr);
511 if (suffixLess != null)
513 is = getClass().getResourceAsStream("/" + suffixLess);
518 dataIn = new BufferedReader(new InputStreamReader(is));
528 errormessage = "PROBABLE IMPLEMENTATION ERROR : Datasource Type given as '"
529 + (sourceType != null ? sourceType : "null") + "'";
532 if (dataIn == null || error)
534 // pass up the reason why we have no source to read from
535 throw new IOException(MessageManager.formatMessage(
536 "exception.failed_to_read_data_from_source", new String[]
540 dataIn.mark(READAHEAD_LIMIT);
544 * mark the current position in the source as start for the purposes of it
545 * being analysed by IdentifyFile().identify
547 * @throws IOException
549 public void mark() throws IOException
553 dataIn.mark(READAHEAD_LIMIT);
557 throw new IOException(
558 MessageManager.getString("exception.no_init_source_stream"));
562 public String nextLine() throws IOException
566 return dataIn.readLine();
568 throw new IOException(MessageManager
569 .formatMessage("exception.invalid_source_stream", new String[]
575 * @return true if this FileParse is configured for Export only
577 public boolean isExporting()
579 return !error && dataIn == null;
584 * @return true if the data source is valid
586 public boolean isValid()
592 * closes the datasource and tidies up. source will be left in an error state
594 public void close() throws IOException
596 errormessage = "EXCEPTION ON CLOSE";
600 errormessage = "SOURCE IS CLOSED";
604 * Rewinds the datasource to the marked point if possible
609 public void reset(int bytesRead) throws IOException
611 if (bytesRead >= READAHEAD_LIMIT)
613 System.err.println(String.format(
614 "File reset error: read %d bytes but reset limit is %d",
615 bytesRead, READAHEAD_LIMIT));
617 if (dataIn != null && !error)
623 throw new IOException(MessageManager.getString(
624 "error.implementation_error_reset_called_for_invalid_source"));
630 * @return true if there is a warning for the user
632 public boolean hasWarningMessage()
634 return (warningMessage != null && warningMessage.length() > 0);
639 * @return empty string or warning message about file that was just parsed.
641 public String getWarningMessage()
643 return warningMessage;
646 public String getInFile()
650 return inFile.getAbsolutePath() + " (" + index + ")";
654 return "From Paste + (" + index + ")";
659 * @return the dataName
661 public String getDataName()
667 * set the (human readable) name or URI for this datasource
671 protected void setDataName(String dataname)
677 * get the underlying bufferedReader for this data source.
679 * @return null if no reader available
680 * @throws IOException
682 public Reader getReader()
684 if (dataIn != null) // Probably don't need to test for readiness &&
692 public AlignViewportI getViewport()
697 public void setViewport(AlignViewportI viewport)
699 this.viewport = viewport;
703 * @return the currently configured exportSettings for writing data.
705 public AlignExportSettingsI getExportSettings()
707 return exportSettings;
711 * Set configuration for export of data.
713 * @param exportSettings
714 * the exportSettings to set
716 public void setExportSettings(AlignExportSettingsI exportSettings)
718 this.exportSettings = exportSettings;
722 * method overridden by complex file exporter/importers which support
723 * exporting visualisation and layout settings for a view
727 public void configureForView(AlignmentViewPanel avpanel)
731 setViewport(avpanel.getAlignViewport());
733 // could also set export/import settings
737 * Returns the preferred feature colour configuration if there is one, else
742 public FeatureSettingsModelI getFeatureColourScheme()
747 public DataSourceType getDataSourceType()
749 return dataSourceType;
753 * Returns a buffered reader for the input object. Returns null, or throws
754 * IOException, on failure.
757 * a File, or a String which is a name of a file
760 * @throws IOException
762 public BufferedReader getBufferedReader(Object file,
763 DataSourceType sourceType) throws IOException
765 BufferedReader in = null;
771 if (file instanceof String)
773 return new BufferedReader(new FileReader((String) file));
775 bytes = Platform.getFileBytes((File) file);
778 return new BufferedReader(
779 new InputStreamReader(new ByteArrayInputStream(bytes)));
781 return new BufferedReader(new FileReader((File) file));
783 URL url = new URL(file.toString());
784 in = new BufferedReader(new InputStreamReader(url.openStream()));
786 case RELATIVE_URL: // JalviewJS only
787 bytes = Platform.getFileAsBytes(file.toString());
790 in = new BufferedReader(
791 new InputStreamReader(new ByteArrayInputStream(bytes)));
795 in = new BufferedReader(new StringReader(file.toString()));
798 InputStream is = getClass().getResourceAsStream("/" + file);
801 in = new BufferedReader(new InputStreamReader(is));