1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
|
/* LanguageTool, a natural language style checker
* Copyright (C) 2005 Daniel Naber (http://www.danielnaber.de)
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301
* USA
*/
package de.danielnaber.languagetool.rules;
import java.util.ArrayList;
import java.util.List;
import java.util.ResourceBundle;
import de.danielnaber.languagetool.AnalyzedSentence;
import de.danielnaber.languagetool.AnalyzedTokenReadings;
import de.danielnaber.languagetool.Language;
/**
* Checks that a sentence starts with an uppercase letter.
*
* @author Daniel Naber
*/
public class UppercaseSentenceStartRule extends Rule {
private final Language language;
private String lastParagraphString = "";
public UppercaseSentenceStartRule(final ResourceBundle messages,
final Language language) {
super(messages);
super.setCategory(new Category(messages.getString("category_case")));
this.language = language;
}
public final String getId() {
return "UPPERCASE_SENTENCE_START";
}
public final String getDescription() {
return messages.getString("desc_uppercase_sentence");
}
public final RuleMatch[] match(final AnalyzedSentence text) {
final List<RuleMatch> ruleMatches = new ArrayList<RuleMatch>();
final AnalyzedTokenReadings[] tokens = text.getTokensWithoutWhitespace();
if (tokens.length < 2) {
return toRuleMatchArray(ruleMatches);
}
int matchTokenPos = 1; // 0 = SENT_START
final String firstToken = tokens[matchTokenPos].getToken();
String secondToken = null;
String thirdToken = null;
// ignore quote characters:
if (tokens.length >= 3
&& ("'".equals(firstToken) || "\"".equals(firstToken) || "„"
.equals(firstToken))) {
matchTokenPos = 2;
secondToken = tokens[matchTokenPos].getToken();
}
final String firstDutchToken = dutchSpecialCase(firstToken, secondToken,
tokens);
if (firstDutchToken != null) {
thirdToken = firstDutchToken;
matchTokenPos = 3;
}
String checkToken = firstToken;
if (thirdToken != null) {
checkToken = thirdToken;
} else if (secondToken != null) {
checkToken = secondToken;
}
final String lastToken = tokens[tokens.length - 1].getToken();
boolean noException = false;
//fix for lists; note - this will not always work for the last point in OOo,
//as OOo might serve paragraphs in any order.
if ((language == Language.RUSSIAN || language == Language.POLISH)
&& (";".equals(lastParagraphString) || ";".equals(lastToken)
|| ",".equals(lastParagraphString) || ",".equals(lastToken))) {
noException = true;
}
//fix for comma in last paragraph; note - this will not always work for the last point in OOo,
//as OOo might serve paragraphs in any order.
if ((language == Language.RUSSIAN || language == Language.ITALIAN
|| language == Language.POLISH || language == Language.GERMAN)
&& (",".equals(lastParagraphString))) {
noException = true;
}
lastParagraphString = lastToken;
if (checkToken.length() > 0) {
final char firstChar = checkToken.charAt(0);
if (Character.isLowerCase(firstChar) && (!noException)) {
final RuleMatch ruleMatch = new RuleMatch(this, tokens[matchTokenPos]
.getStartPos(), tokens[matchTokenPos].getStartPos()
+ tokens[matchTokenPos].getToken().length(), messages
.getString("incorrect_case"));
ruleMatch.setSuggestedReplacement(Character.toUpperCase(firstChar)
+ checkToken.substring(1));
ruleMatches.add(ruleMatch);
}
}
return toRuleMatchArray(ruleMatches);
}
private String dutchSpecialCase(final String firstToken,
final String secondToken, final AnalyzedTokenReadings[] tokens) {
if (language != Language.DUTCH) {
return null;
}
if (tokens.length >= 3 && firstToken.equals("'")
&& secondToken.matches("k|m|n|r|s|t")) {
return tokens[3].getToken();
}
return null;
}
public void reset() {
}
}
|
