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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
|
/* 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.fr;
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.rules.Category;
import de.danielnaber.languagetool.rules.RuleMatch;
import de.danielnaber.languagetool.tools.StringTools;
/**
* A rule that matches spaces before ?,:,; and ! (required for correct French
* punctuation).
*
* @author Marcin Miłkowski
*/
public class QuestionWhitespaceRule extends FrenchRule {
public QuestionWhitespaceRule(final ResourceBundle messages) {
// super(messages);
super.setCategory(new Category(messages.getString("category_misc")));
}
@Override
public String getId() {
return "FRENCH_WHITESPACE";
}
@Override
public String getDescription() {
return "Insertion des espaces fines insécables";
}
@Override
public RuleMatch[] match(final AnalyzedSentence text) {
final List<RuleMatch> ruleMatches = new ArrayList<RuleMatch>();
final AnalyzedTokenReadings[] tokens = text.getTokens();
String prevToken = "";
int pos = 0;
for (int i = 1; i < tokens.length; i++) {
final String token = tokens[i].getToken();
final boolean isWhiteBefore = tokens[i].isWhitespaceBefore();
pos += token.length();
String msg = null;
final int fixPos = 0;
int fixLen = 0;
String suggestionText = null;
if (isWhiteBefore) {
if (token.equals("?")) {
msg = "Point d'interrogation est précédé d'une espace fine insécable.";
// non-breaking space
suggestionText = " ?";
fixLen = 1;
} else if (token.equals("!")) {
msg = "Point d'exclamation est précédé d'une espace fine insécable.";
// non-breaking space
suggestionText = " !";
fixLen = 1;
} else if (token.equals("»")) {
msg = "Le guillemet fermant est précédé d'une espace fine insécable.";
// non-breaking space
suggestionText = " »";
fixLen = 1;
} else if (token.equals(";")) {
msg = "Point-virgule est précédé d'une espace fine insécable.";
// non-breaking space
suggestionText = " ;";
fixLen = 1;
} else if (token.equals(":")) {
msg = "Deux-points sont précédé d'une espace fine insécable.";
// non-breaking space
suggestionText = " :";
fixLen = 1;
}
} else {
if (token.equals("?") && !prevToken.equals("!")
&& !prevToken.equals("\u00a0")) {
msg = "Point d'interrogation est précédé d'une espace fine insécable.";
// non-breaking space
suggestionText = prevToken + " ?";
fixLen = 1;
} else if (token.equals("!") && !prevToken.equals("?")
&& !prevToken.equals("\u00a0")) {
msg = "Point d'exclamation est précédé d'une espace fine insécable.";
// non-breaking space
suggestionText = prevToken + " !";
fixLen = 1;
} else if (token.equals(";") && !prevToken.equals("\u00a0")) {
msg = "Point-virgule est précédé d'une espace fine insécable.";
// non-breaking space
suggestionText = prevToken + " ;";
fixLen = 1;
} else if (token.equals(":") && !prevToken.equals("\u00a0")) {
msg = "Deux-points précédés d'une espace fine insécable.";
// non-breaking space
suggestionText = prevToken + " :";
fixLen = 1;
} else if (token.equals("»") && !prevToken.equals("\u00a0")) {
msg = "Le guillemet fermant est précédé d'une espace fine insécable.";
// non-breaking space
suggestionText = prevToken + " »";
fixLen = 1;
}
}
if (StringTools.isEmpty(token) && prevToken.equals("«")) {
msg = "Le guillemet ouvrant est suivi d'une espace fine insécable.";
// non-breaking space
suggestionText = "« ";
fixLen = 1;
} else if (!StringTools.isEmpty(token) && !token.equals("\u00a0")
&& prevToken.equals("«")) {
msg = "Le guillemet ouvrant est suivi d'une espace fine insécable.";
// non-breaking space
suggestionText = "« ";
fixLen = 0;
}
if (msg != null) {
final int fromPos = tokens[i - 1].getStartPos() + fixPos;
final int toPos = tokens[i - 1].getStartPos() + fixPos + fixLen
+ tokens[i - 1].getToken().length();
final RuleMatch ruleMatch = new RuleMatch(this, fromPos, toPos, msg,
"Insérer un espace insécable");
if (suggestionText != null) {
ruleMatch.setSuggestedReplacement(suggestionText);
}
ruleMatches.add(ruleMatch);
}
prevToken = token;
}
return toRuleMatchArray(ruleMatches);
}
@Override
public void reset() {
// nothing
}
}
|
