annotate backend/src/main/java/org/dive4elements/river/importer/common/AbstractParser.java @ 8991:c43d8c1a4455

Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
author mschaefer
date Tue, 10 Apr 2018 16:43:32 +0200
parents 2693bfaf503d
children abe069eb180c
rev   line source
8971
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
1 /* Copyright (C) 2017 by Bundesanstalt für Gewässerkunde
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
2 * Software engineering by
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
3 * Björnsen Beratende Ingenieure GmbH
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
4 * Dr. Schumacher Ingenieurbüro für Wasser und Umwelt
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
5 *
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
6 * This file is Free Software under the GNU AGPL (>=v3)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
7 * and comes with ABSOLUTELY NO WARRANTY! Check out the
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
8 * documentation coming with Dive4Elements River for details.
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
9 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
10
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
11 package org.dive4elements.river.importer.common;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
12
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
13 import java.io.File;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
14 import java.io.FileInputStream;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
15 import java.io.FilenameFilter;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
16 import java.io.IOException;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
17 import java.io.InputStreamReader;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
18 import java.io.LineNumberReader;
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8971
diff changeset
19 import java.math.BigDecimal;
8991
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
20 import java.text.DecimalFormat;
8971
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
21 import java.text.NumberFormat;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
22 import java.text.ParseException;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
23 import java.util.ArrayList;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
24 import java.util.List;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
25 import java.util.Locale;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
26 import java.util.TreeSet;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
27 import java.util.regex.Matcher;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
28 import java.util.regex.Pattern;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
29
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
30 import org.apache.log4j.Logger;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
31 import org.dive4elements.river.backend.utils.EpsilonComparator;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
32 import org.dive4elements.river.importer.ImportRiver;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
33
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
34 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
35 * Abstract base class for a parser of one FLYS csv data file.<br />
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
36 * The {@link parse} method creates a SERIES object for the meta data
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
37 * and a list of KMLINE objects for the km value lines read from the file.<br />
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
38 * The {@link store} method gets or creates the corresponding database objects
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
39 * by the hibernate binding classes DB_SERIES and DB_KMTUPLE,
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
40 * and updates or inserts them in the database.
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
41 * DB_SERIES has a one-to-many relationship with DB_KMTUPLE.<br />
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
42 * <br />
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
43 * The structure of the file is as follows:<br />
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
44 * <ul>
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
45 * <li>one or more comment lines (#) with the meta info of the data series</li>
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
46 * <li>the comment line with the column titles of values table, starting with the km column</li>
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
47 * <li>the rows of the values table, each one on its own line</li>
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
48 * </ul>
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
49 *
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
50 * @author Matthias Schäfer
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
51 *
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
52 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
53 public abstract class AbstractParser<DB_SERIES, DB_KMTUPLE, KMLINE extends AbstractKmLineImport<DB_SERIES, DB_KMTUPLE>, HEADER extends AbstractSeriesImport<DB_SERIES, DB_KMTUPLE, KMLINE>> implements ImportParser {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
54
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
55 /***** FIELDS *****/
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
56
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
57 public static final String ENCODING = "ISO-8859-1";
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
58
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
59 protected static final Locale DEFAULT_LOCALE = Locale.GERMAN;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
60
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
61 public static final String START_META_CHAR = "#";
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
62
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
63 protected static final String SEPARATOR_CHAR = ";";
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
64
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
65 protected static final Pattern META_RIVERNAME = Pattern.compile("^#\\s*((Gew.sser)|(Gewaesser)):\\s*(\\S[^;]*).*", Pattern.CASE_INSENSITIVE);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
66
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
67 protected static final Pattern META_KMRANGE_INFO = Pattern.compile("^#\\s*Strecke:\\s*(\\S[^;]*).*", Pattern.CASE_INSENSITIVE);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
68
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
69 protected static final Pattern META_COMMENTS = Pattern.compile("^#\\s*weitere Bemerkungen:\\s*(\\S[^;]*).*", Pattern.CASE_INSENSITIVE);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
70
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
71 private static final Pattern META_COLUMNTITLES = Pattern.compile("^#*\\s*Fluss.km\\s*;.+", Pattern.CASE_INSENSITIVE);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
72
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
73 private static final Pattern META_SUBGROUP = Pattern.compile("^##.*", Pattern.CASE_INSENSITIVE);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
74
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
75 private static NumberFormat numberFormat = NumberFormat.getInstance(Locale.ROOT);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
76
8991
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
77 private static DecimalFormat bigDecimalFormat;
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
78
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
79 static {
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
80 bigDecimalFormat = (DecimalFormat) NumberFormat.getInstance(Locale.ROOT);
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
81 bigDecimalFormat.setParseBigDecimal(true);
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
82 }
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
83
8971
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
84 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
85 * Path of the file or directory to import from
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
86 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
87 protected final File importPath;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
88
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
89 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
90 * Part of {@link importPath} without the river root dir
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
91 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
92 protected final File rootRelativePath;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
93
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
94 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
95 * River for which the import runs
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
96 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
97 protected final ImportRiver river;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
98
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
99 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
100 * Reader during parse
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
101 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
102 protected LineNumberReader in;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
103
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
104 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
105 * Last line read from in
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
106 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
107 protected String currentLine;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
108
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
109 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
110 * State of the header lines parse loop
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
111 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
112 protected ParsingState headerParsingState;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
113
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
114 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
115 * Series header of the stations table, with the imported meta info.
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
116 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
117 protected HEADER seriesHeader;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
118
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
119 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
120 * List of meta info Pattern matched during {@link handleMetaLine}
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
121 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
122 protected final List<Pattern> metaPatternsMatched;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
123
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
124 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
125 * Column titles of the stations table, starting with the km column.
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
126 * All strings have been trimmed.
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
127 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
128 protected final List<String> columnTitles;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
129
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
130 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
131 * List of the km value tuples imported, no duplicate km
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
132 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
133 protected final List<KMLINE> values;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
134
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
135 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
136 * Ordered list with the imported km to check for duplicates.
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
137 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
138 protected final TreeSet<Double> kmExists;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
139
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
140
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
141 /***** CONSTRUCTORS *****/
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
142
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
143 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
144 * Constructs a parser for an import file
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
145 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
146 public AbstractParser(final File importPath, final File rootRelativePath, final ImportRiver river) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
147 this.importPath = importPath;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
148 this.rootRelativePath = rootRelativePath;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
149 this.river = river;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
150 this.metaPatternsMatched = new ArrayList<>();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
151 this.kmExists = new TreeSet<>(EpsilonComparator.CMP);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
152 this.columnTitles = new ArrayList<>();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
153 this.values = new ArrayList<>();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
154 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
155
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
156
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
157 /***** METHODS *****/
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
158
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
159 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
160 * Lists all files from a directory having a type extension (starting with dot)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
161 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
162 protected static List<File> listFiles(final File importDir, final String extension) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
163 final File[] files = importDir.listFiles(new FilenameFilter() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
164 @Override
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
165 public boolean accept(final File dir, final String name) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
166 return name.toLowerCase().endsWith(extension);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
167 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
168 });
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
169 final List<File> fl = new ArrayList<>();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
170 if (files != null)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
171 for (final File file : files)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
172 fl.add(file);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
173 return fl;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
174 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
175
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
176 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
177 * Parses a file and adds series and values to the parser's collection
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
178 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
179 @Override
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
180 public void parse() throws IOException {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
181 logStartInfo();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
182 this.seriesHeader = createSeriesImport(this.importPath.getName().replaceAll("\\.csv", ""));
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
183 this.metaPatternsMatched.clear();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
184 this.kmExists.clear();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
185 this.headerParsingState = ParsingState.CONTINUE;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
186 try {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
187 try {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
188 this.in = new LineNumberReader(new InputStreamReader(new FileInputStream(this.importPath), ENCODING));
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
189 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
190 catch (final Exception e) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
191 logError("Could not open (" + e.getMessage() + ")");
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
192 this.headerParsingState = ParsingState.STOP;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
193 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
194 this.currentLine = null;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
195 while (this.headerParsingState != ParsingState.STOP) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
196 this.currentLine = this.in.readLine();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
197 if (this.currentLine == null)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
198 break;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
199 this.currentLine = this.currentLine.trim();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
200 if (this.currentLine.isEmpty())
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
201 continue;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
202 if (this.headerParsingState == ParsingState.CONTINUE)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
203 handleMetaLine();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
204 else
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
205 handleDataLine();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
206 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
207 if (this.headerParsingState != ParsingState.STOP)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
208 getLog().info("Number of values found: " + this.seriesHeader.getValueCount());
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
209 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
210 finally {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
211 if (this.in != null) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
212 this.in.close();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
213 this.in = null;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
214 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
215 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
216 if (this.headerParsingState == ParsingState.STOP)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
217 logError("Parsing of the file stopped due to a severe error");
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
218 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
219
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
220 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
221 * Writes the parse start info to the log
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
222 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
223 protected void logStartInfo() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
224 getLog().info("Start parsing:;'" + this.rootRelativePath + "'");
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
225 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
226
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
227 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
228 * Stores the parsed series and values in the database
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
229 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
230 @Override
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
231 public void store() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
232 if (this.headerParsingState != ParsingState.STOP) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
233 this.seriesHeader.store(this.river.getPeer());
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
234 final String counts = String.format("parse=%d, insert=%d, update/ignore=%d", this.seriesHeader.getValueCount(),
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
235 this.seriesHeader.getValueStoreCount(StoreMode.INSERT), this.seriesHeader.getValueStoreCount(StoreMode.UPDATE));
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
236 if (this.seriesHeader.getValueCount() > this.seriesHeader.getValueStoreCount(StoreMode.INSERT))
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
237 logWarning("Number of value inserts less than number parsed: " + counts);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
238 else
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
239 getLog().info("Number of values records: " + counts);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
240 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
241 else
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
242 logWarning("Severe parsing errors, not storing series '" + this.seriesHeader.getFilename() + "'");
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
243 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
244
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
245 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
246 * Strips separator chars from a meta info text, and trims leading and trailing whitespace
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
247 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
248 public static String parseMetaInfo(final String text) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
249 return text.replace(SEPARATOR_CHAR, "").trim();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
250 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
251
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
252 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
253 * Parses a number string with dot or comma as decimal char, and returning null in case of an error
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
254 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
255 public static Number parseDoubleWithNull(final String text) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
256 try {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
257 return parseDouble(text);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
258 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
259 catch (final Exception e) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
260 return null;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
261 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
262 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
263
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
264 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
265 * Parses a number string with dot or comma as decimal char
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
266 *
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
267 * @throws ParseException
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
268 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
269 public static Number parseDouble(final String text) throws ParseException {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
270 return numberFormat.parse(text.replace(',', '.'));
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
271 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
272
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
273 /**
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8971
diff changeset
274 * Parses a number string as a BigDecimal, replacing a comma with a dot first
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8971
diff changeset
275 */
8991
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
276 public static BigDecimal parseDecimal(final String text) throws ParseException {
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
277 return (BigDecimal) bigDecimalFormat.parse(text.replace(',', '.'));
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8971
diff changeset
278 }
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8971
diff changeset
279
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8971
diff changeset
280 /**
8971
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
281 * Gets the class's logger
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
282 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
283 protected abstract Logger getLog();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
284
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
285 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
286 * Logs an error message, appending the relative file path
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
287 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
288 protected void logError(final String message) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
289 getLog().error(message + ";" + this.rootRelativePath);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
290 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
291
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
292 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
293 * Logs a warning message, appending the relative file path
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
294 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
295 protected void logWarning(final String message) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
296 getLog().warn(message + ";" + this.rootRelativePath);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
297 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
298
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
299 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
300 * Creates a new series import object
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
301 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
302 protected abstract HEADER createSeriesImport(final String filename);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
303
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
304 protected void handleMetaLine() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
305 if (META_SUBGROUP.matcher(this.currentLine).matches())
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
306 return;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
307 else if (handleMetaRivername())
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
308 return;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
309 else if (handleMetaKmrange_info())
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
310 return;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
311 else if (handleMetaComment())
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
312 return;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
313 else if (handleMetaOther())
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
314 return;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
315 else if (handleMetaColumnTitles()) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
316 if (this.headerParsingState != ParsingState.STOP)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
317 this.headerParsingState = ParsingState.DONE;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
318 return;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
319 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
320 else {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
321 if (this.currentLine.startsWith(START_META_CHAR)) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
322 if (this.headerParsingState != ParsingState.IGNORE)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
323 logWarning("Not matching any known meta type in line " + this.in.getLineNumber() + ", ignored");
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
324 else
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
325 this.headerParsingState = ParsingState.CONTINUE;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
326 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
327 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
328 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
329
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
330 private boolean handleMetaRivername() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
331 if (META_RIVERNAME.matcher(this.currentLine).matches()) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
332 this.metaPatternsMatched.add(META_RIVERNAME);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
333 return true;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
334 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
335 else
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
336 return false;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
337 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
338
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
339 private boolean handleMetaKmrange_info() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
340 final Matcher m = META_KMRANGE_INFO.matcher(this.currentLine);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
341 if (m.matches()) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
342 this.metaPatternsMatched.add(META_KMRANGE_INFO);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
343 this.seriesHeader.setKmrange_info(parseMetaInfo(m.group(1)));
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
344 return true;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
345 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
346 return false;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
347 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
348
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
349 private boolean handleMetaComment() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
350 final Matcher m = META_COMMENTS.matcher(this.currentLine);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
351 if (m.matches()) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
352 this.metaPatternsMatched.add(META_COMMENTS);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
353 this.seriesHeader.setComment(parseMetaInfo(m.group(1)));
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
354 return true;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
355 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
356 return false;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
357 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
358
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
359 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
360 * Parses currentLine for non-default meta info
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
361 *
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
362 * @return Whether the line has been handled
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
363 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
364 protected boolean handleMetaOther() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
365 return false;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
366 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
367
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
368 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
369 * Parses a header line for the km table column header line
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
370 *
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
371 * @return Whether the line has been handled and we are ready for reading the km values lines
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
372 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
373 protected boolean handleMetaColumnTitles() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
374 if (META_COLUMNTITLES.matcher(this.currentLine).matches()) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
375 this.metaPatternsMatched.add(META_COLUMNTITLES);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
376 this.columnTitles.clear();
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
377 final String[] titles = this.currentLine.split(SEPARATOR_CHAR, 0);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
378 for (int i = 0; i <= titles.length - 1; i++)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
379 this.columnTitles.add(titles[i].trim());
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
380 return true;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
381 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
382 return false;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
383 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
384
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
385 private void handleDataLine() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
386 final String[] values = this.currentLine.split(SEPARATOR_CHAR, 0);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
387 // Skip import line without data or only km
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
388 if (values.length < 2)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
389 return;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
390 Double km;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
391 try {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
392 km = Double.valueOf(parseDouble(values[0]).doubleValue());
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
393 if (kmMustBeUnique()) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
394 if (this.kmExists.contains(km)) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
395 logWarning("Ignoring duplicate station '" + values[0] + "' in line " + this.in.getLineNumber());
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
396 return;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
397 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
398 this.kmExists.add(km);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
399 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
400 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
401 catch (final Exception e) {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
402 logError("Not parseable km in line " + this.in.getLineNumber() + ": " + e.getMessage());
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
403 return;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
404 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
405 final KMLINE value = createKmLineImport(km, values);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
406 if (value != null)
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
407 this.seriesHeader.addValue(value);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
408 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
409
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
410 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
411 * Whether {@link handleDataLine} shall check for and reject km duplicates
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
412 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
413 protected boolean kmMustBeUnique() {
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
414 return true;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
415 }
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
416
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
417 /**
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
418 * Creates a value import item with the km and other fields of the current line;
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
419 * the km has been validated
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
420 *
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
421 * @return value item, or null if parse error
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
422 */
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
423 protected abstract KMLINE createKmLineImport(final Double km, final String[] values);
50416a0df385 Importer for the Schifffahrt (S-INFO) and Oekologie (U-INFO) files
mschaefer
parents:
diff changeset
424 }

http://dive4elements.wald.intevation.org