annotate backend/src/main/java/org/dive4elements/river/importer/parsers/MorphologicalWidthParser.java @ 9650:a2a42a6bac6b

Importer (s/u-info) extensions: outer try/catch for parse and log of line no, catching parsing exception if not enough value fields, parsing error and warning log messages with line number, detecting and rejecting duplicate data series, better differentiation between error and warning log messages
author mschaefer
date Mon, 23 Mar 2020 14:57:03 +0100
parents c43d8c1a4455
children
rev   line source
5844
4dd33b86dc61 Added header to river backend.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5838
diff changeset
1 /* Copyright (C) 2011, 2012, 2013 by Bundesanstalt für Gewässerkunde
4dd33b86dc61 Added header to river backend.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5838
diff changeset
2 * Software engineering by Intevation GmbH
4dd33b86dc61 Added header to river backend.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5838
diff changeset
3 *
5992
4c3ccf2b0304 Removed trailing whitespace.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5844
diff changeset
4 * This file is Free Software under the GNU AGPL (>=v3)
5844
4dd33b86dc61 Added header to river backend.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5838
diff changeset
5 * and comes with ABSOLUTELY NO WARRANTY! Check out the
5992
4c3ccf2b0304 Removed trailing whitespace.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5844
diff changeset
6 * documentation coming with Dive4Elements River for details.
5844
4dd33b86dc61 Added header to river backend.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5838
diff changeset
7 */
4dd33b86dc61 Added header to river backend.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5838
diff changeset
8
5829
18619c1e7c2a Repaired internal references.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5828
diff changeset
9 package org.dive4elements.river.importer.parsers;
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
10
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
11 import java.math.BigDecimal;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
12 import java.text.NumberFormat;
8991
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
13 import java.text.ParseException;
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
14 import java.util.ArrayList;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
15 import java.util.List;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
16 import java.util.regex.Matcher;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
17 import java.util.regex.Pattern;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
18
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
19 import org.apache.log4j.Logger;
5829
18619c1e7c2a Repaired internal references.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5828
diff changeset
20 import org.dive4elements.river.importer.ImportMorphWidth;
18619c1e7c2a Repaired internal references.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5828
diff changeset
21 import org.dive4elements.river.importer.ImportMorphWidthValue;
18619c1e7c2a Repaired internal references.
Sascha L. Teichmann <teichmann@intevation.de>
parents: 5828
diff changeset
22 import org.dive4elements.river.importer.ImportUnit;
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
23 import org.dive4elements.river.importer.common.AbstractParser;
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
24
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
25
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
26 public class MorphologicalWidthParser extends LineParser {
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
27
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
28 private static final Logger log =
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
29 Logger.getLogger(MorphologicalWidthParser.class);
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
30
8856
5e38e2924c07 Fix code style.
Tom Gottfried <tom@intevation.de>
parents: 5992
diff changeset
31 public static final NumberFormat nf = NumberFormat.getInstance(
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
32 DEFAULT_LOCALE);
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
33
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
34 public static final Pattern META_UNIT =
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
35 Pattern.compile("^Einheit: \\[(.*)\\].*");
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
36
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
37 protected List<ImportMorphWidth> morphWidths;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
38
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
39 protected ImportMorphWidth current;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
40
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
41
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
42 public MorphologicalWidthParser() {
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
43 this.morphWidths = new ArrayList<>();
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
44 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
45
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
46
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
47 @Override
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
48 protected void reset() {
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
49 this.current = new ImportMorphWidth();
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
50 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
51
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
52
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
53 @Override
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
54 protected void finish() {
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
55 if (this.current != null) {
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
56 this.morphWidths.add(this.current);
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
57 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
58 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
59
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
60
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
61 @Override
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
62 protected void handleLine(final int lineNum, final String line) {
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
63 if (line.startsWith(START_META_CHAR)) {
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
64 handleMetaLine(stripMetaLine(line));
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
65 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
66 else {
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
67 handleDataLine(line);
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
68 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
69 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
70
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
71
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
72 protected void handleMetaLine(final String line) {
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
73 if (handleMetaUnit(line)) {
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
74 return;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
75 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
76 else {
3662
0d27d02b1208 backend: Completed the error messages of the importer.
Sascha L. Teichmann <sascha.teichmann@intevation.de>
parents: 2821
diff changeset
77 log.warn("MWP: Unknown meta line: '" + line + "'");
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
78 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
79 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
80
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
81
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
82 protected boolean handleMetaUnit(final String line) {
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
83 final Matcher m = META_UNIT.matcher(line);
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
84
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
85 if (m.matches()) {
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
86 final String unit = m.group(1);
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
87
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
88 this.current.setUnit(new ImportUnit(unit));
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
89
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
90 return true;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
91 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
92
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
93 return false;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
94 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
95
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
96
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
97 protected void handleDataLine(final String line) {
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
98 final String[] vals = line.split(SEPERATOR_CHAR);
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
99
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
100 if (vals == null || vals.length < 2) {
3662
0d27d02b1208 backend: Completed the error messages of the importer.
Sascha L. Teichmann <sascha.teichmann@intevation.de>
parents: 2821
diff changeset
101 log.warn("MWP: skip invalid data line: '" + line + "'");
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
102 return;
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
103 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
104
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
105 try {
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
106 final BigDecimal km = AbstractParser.parseDecimal(vals[0]);
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
107 final BigDecimal width = AbstractParser.parseDecimal(vals[1]);
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
108
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
109 final String desc = vals.length > 2 ? vals[2] : null;
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
110
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
111 this.current.addValue(new ImportMorphWidthValue(
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
112 km,
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
113 width,
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
114 desc
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
115 ));
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
116 }
8991
c43d8c1a4455 Parse via decimalformat instead of bigdecimal constructor (to cope with strings with chars after the actual number)
mschaefer
parents: 8989
diff changeset
117 catch (final ParseException pe) {
5490
b3dd14fc13a6 Parsers: do not call warnings error
Tom Gottfried <tom.gottfried@intevation.de>
parents: 5016
diff changeset
118 log.warn("MWP: unparseable number in data row: " + line);
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
119 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
120 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
121
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
122
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
123 public List<ImportMorphWidth> getMorphologicalWidths() {
8989
2693bfaf503d Fixed several BigDecimal(double) creations by BigDecimal(String) parsing to avoid unnecessary decimal digits
mschaefer
parents: 8856
diff changeset
124 return this.morphWidths;
2821
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
125 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
126 }
0a536eb5d668 Added parser for parsing morphological widths.
Ingo Weinzierl <ingo.weinzierl@intevation.de>
parents:
diff changeset
127 // vim:set ts=4 sw=4 si et sta sts=4 fenc=utf8 :

http://dive4elements.wald.intevation.org