Mercurial > dive4elements > river

comparison backend/src/main/java/org/dive4elements/river/importer/parsers/AnnotationsParser.java @ 5838:5aa05a7a34b7

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Rename modules to more fitting names.
author Sascha L. Teichmann <teichmann@intevation.de>
date Thu, 25 Apr 2013 15:23:37 +0200
parents flys-backend/src/main/java/org/dive4elements/river/importer/parsers/AnnotationsParser.java@18619c1e7c2a
children 4dd33b86dc61
comparison
equal deleted inserted replaced
5837:d9901a08d0a6 5838:5aa05a7a34b7
1 package org.dive4elements.river.importer.parsers;
2
3 import java.util.HashMap;
4 import java.util.TreeSet;
5 import java.util.List;
6 import java.util.ArrayList;
7
8 import java.io.IOException;
9 import java.io.File;
10 import java.io.LineNumberReader;
11 import java.io.InputStreamReader;
12 import java.io.FileInputStream;
13
14 import java.math.BigDecimal;
15
16 import org.apache.log4j.Logger;
17
18 import org.dive4elements.artifacts.common.utils.FileTools;
19
20 import org.dive4elements.river.importer.ImportAnnotation;
21 import org.dive4elements.river.importer.ImportRange;
22 import org.dive4elements.river.importer.ImportEdge;
23 import org.dive4elements.river.importer.ImportAnnotationType;
24 import org.dive4elements.river.importer.ImportAttribute;
25 import org.dive4elements.river.importer.ImportPosition;
26
27 public class AnnotationsParser
28 {
29 private static Logger log = Logger.getLogger(AnnotationsParser.class);
30
31 public static final String ENCODING = "ISO-8859-1";
32
33 public static final String [] TO_SCAN = {
34 "Basisdaten",
35 "Streckendaten",
36 ".." + File.separator +
37 "Morphologie" + File.separator + "Streckendaten"
38 };
39
40 protected HashMap<String, ImportAttribute> attributes;
41 protected HashMap<String, ImportPosition> positions;
42 protected TreeSet<ImportAnnotation> annotations;
43 protected AnnotationClassifier classifier;
44
45 public AnnotationsParser() {
46 this(null);
47 }
48
49 public AnnotationsParser(AnnotationClassifier classifier) {
50 attributes = new HashMap<String, ImportAttribute>();
51 positions = new HashMap<String, ImportPosition>();
52 annotations = new TreeSet<ImportAnnotation>();
53 this.classifier = classifier;
54 }
55
56 public void parseFile(File file) throws IOException {
57 log.info("parsing km file: '" + file + "'");
58
59 ImportAnnotationType defaultIAT = null;
60
61 if (classifier != null) {
62 defaultIAT = classifier.classifyFile(
63 file.getName(),
64 classifier.getDefaultType());
65 }
66
67 LineNumberReader in = null;
68 try {
69 in =
70 new LineNumberReader(
71 new InputStreamReader(
72 new FileInputStream(file), ENCODING));
73
74 String line = null;
75 while ((line = in.readLine()) != null) {
76 if ((line = line.trim()).length() == 0
77 || line.startsWith("*")) {
78 continue;
79 }
80
81 String [] parts = line.split("\\s*;\\s*");
82
83 if (parts.length < 3) {
84 log.warn("ANN: not enough columns in line "
85 + in.getLineNumber());
86 continue;
87 }
88
89 ImportPosition position = positions.get(parts[0]);
90 if (position == null) {
91 position = new ImportPosition(parts[0]);
92 positions.put(parts[0], position);
93 }
94
95 ImportAttribute attribute = attributes.get(parts[1]);
96 if (attribute == null) {
97 attribute = new ImportAttribute(parts[1]);
98 attributes.put(parts[1], attribute);
99 }
100
101 String [] r = parts[2].replace(",", ".").split("\\s*#\\s*");
102
103 BigDecimal from, to;
104
105 try {
106 from = new BigDecimal(r[0]);
107 to = r.length < 2 ? null : new BigDecimal(r[1]);
108 if (to != null && from.compareTo(to) > 0) {
109 BigDecimal t = from; from = to; to = t;
110 }
111 }
112 catch (NumberFormatException nfe) {
113 log.warn("ANN: invalid number in line " + in.getLineNumber());
114 continue;
115 }
116
117 ImportEdge edge = null;
118
119 if (parts.length == 4) { // Only 'Unterkante'
120 try {
121 edge = new ImportEdge(
122 null,
123 new BigDecimal(parts[3].trim().replace(',', '.')));
124 }
125 catch (NumberFormatException nfe) {
126 log.warn("ANN: cannot parse 'Unterkante' in line " +
127 in.getLineNumber());
128 }
129 }
130 else if (parts.length > 4) { // 'Unterkante' and 'Oberkante'
131 String bottom = parts[3].trim().replace(',', '.');
132 String top = parts[4].trim().replace(',', '.');
133 try {
134 BigDecimal b = bottom.length() == 0
135 ? null
136 : new BigDecimal(bottom);
137 BigDecimal t = top.length() == 0
138 ? null
139 : new BigDecimal(top);
140 edge = new ImportEdge(t, b);
141 }
142 catch (NumberFormatException nfe) {
143 log.warn(
144 "ANN: cannot parse 'Unterkante' or 'Oberkante' in line "
145 + in.getLineNumber());
146 }
147 }
148
149 ImportRange range = new ImportRange(from, to);
150
151 ImportAnnotationType type = classifier != null
152 ? classifier.classifyDescription(line, defaultIAT)
153 : null;
154
155 ImportAnnotation annotation = new ImportAnnotation(
156 attribute, position, range, edge, type);
157
158 if (!annotations.add(annotation)) {
159 log.info("ANN: duplicated annotation '" + parts[0] +
160 "' in line " + in.getLineNumber());
161 }
162 }
163 }
164 finally {
165 if (in != null) {
166 in.close();
167 }
168 }
169 }
170
171 public void parse(File root) throws IOException {
172
173 for (String toScan: TO_SCAN) {
174 File directory = FileTools.repair(new File(root, toScan));
175 if (!directory.isDirectory()) {
176 log.warn("ANN: '" + directory + "' is not a directory.");
177 continue;
178 }
179 File [] files = directory.listFiles();
180 if (files == null) {
181 log.warn("ANN: cannot list directory '" + directory + "'");
182 continue;
183 }
184
185 for (File file: files) {
186 if (file.isFile() && file.canRead()
187 && file.getName().toLowerCase().endsWith(".km")) {
188 parseFile(file);
189 }
190 }
191 } // for all directories to scan
192 }
193
194 public List<ImportAnnotation> getAnnotations() {
195 return new ArrayList<ImportAnnotation>(annotations);
196 }
197 }
198 // vim:set ts=4 sw=4 si et sta sts=4 fenc=utf8 :
http://dive4elements.wald.intevation.org