summaryrefslogtreecommitdiffstats
path: root/core/java/android/text/util/Rfc822Tokenizer.java
blob: 69cf93cf35fccef3bafe7c1ed8d5aaeb77e38273 (plain)
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
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
/*
 * Copyright (C) 2008 The Android Open Source Project
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *      http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package android.text.util;

import android.widget.MultiAutoCompleteTextView;

import java.util.ArrayList;
import java.util.Collection;

/**
 * This class works as a Tokenizer for MultiAutoCompleteTextView for
 * address list fields, and also provides a method for converting
 * a string of addresses (such as might be typed into such a field)
 * into a series of Rfc822Tokens.
 */
public class Rfc822Tokenizer implements MultiAutoCompleteTextView.Tokenizer {

    /**
     * This constructor will try to take a string like
     * "Foo Bar (something) <foo\@google.com>,
     * blah\@google.com (something)"
     * and convert it into one or more Rfc822Tokens, output into the supplied
     * collection.
     *
     * It does *not* decode MIME encoded-words; charset conversion
     * must already have taken place if necessary.
     * It will try to be tolerant of broken syntax instead of
     * returning an error.
     *
     */
    public static void tokenize(CharSequence text, Collection<Rfc822Token> out) {
        StringBuilder name = new StringBuilder();
        StringBuilder address = new StringBuilder();
        StringBuilder comment = new StringBuilder();

        int i = 0;
        int cursor = text.length();

        while (i < cursor) {
            char c = text.charAt(i);

            if (c == ',' || c == ';') {
                i++;

                while (i < cursor && text.charAt(i) == ' ') {
                    i++;
                }

                crunch(name);

                if (address.length() > 0) {
                    out.add(new Rfc822Token(name.toString(),
                                            address.toString(),
                                            comment.toString()));
                } else if (name.length() > 0) {
                    out.add(new Rfc822Token(null,
                                            name.toString(),
                                            comment.toString()));
                }

                name.setLength(0);
                address.setLength(0);
                comment.setLength(0);
            } else if (c == '"') {
                i++;

                while (i < cursor) {
                    c = text.charAt(i);

                    if (c == '"') {
                        i++;
                        break;
                    } else if (c == '\\') {
                        if (i + 1 < cursor) {
                            name.append(text.charAt(i + 1));
                        }
                        i += 2;
                    } else {
                        name.append(c);
                        i++;
                    }
                }
            } else if (c == '(') {
                int level = 1;
                i++;

                while (i < cursor && level > 0) {
                    c = text.charAt(i);

                    if (c == ')') {
                        if (level > 1) {
                            comment.append(c);
                        }

                        level--;
                        i++;
                    } else if (c == '(') {
                        comment.append(c);
                        level++;
                        i++;
                    } else if (c == '\\') {
                        if (i + 1 < cursor) {
                            comment.append(text.charAt(i + 1));
                        }
                        i += 2;
                    } else {
                        comment.append(c);
                        i++;
                    }
                }
            } else if (c == '<') {
                i++;

                while (i < cursor) {
                    c = text.charAt(i);

                    if (c == '>') {
                        i++;
                        break;
                    } else {
                        address.append(c);
                        i++;
                    }
                }
            } else if (c == ' ') {
                name.append('\0');
                i++;
            } else {
                name.append(c);
                i++;
            }
        }

        crunch(name);

        if (address.length() > 0) {
            out.add(new Rfc822Token(name.toString(),
                                    address.toString(),
                                    comment.toString()));
        } else if (name.length() > 0) {
            out.add(new Rfc822Token(null,
                                    name.toString(),
                                    comment.toString()));
        }
    }

    /**
     * This method will try to take a string like
     * "Foo Bar (something) &lt;foo\@google.com&gt;,
     * blah\@google.com (something)"
     * and convert it into one or more Rfc822Tokens.
     * It does *not* decode MIME encoded-words; charset conversion
     * must already have taken place if necessary.
     * It will try to be tolerant of broken syntax instead of
     * returning an error.
     */
    public static Rfc822Token[] tokenize(CharSequence text) {
        ArrayList<Rfc822Token> out = new ArrayList<Rfc822Token>();
        tokenize(text, out);
        return out.toArray(new Rfc822Token[out.size()]);
    }

    private static void crunch(StringBuilder sb) {
        int i = 0;
        int len = sb.length();

        while (i < len) {
            char c = sb.charAt(i);

            if (c == '\0') {
                if (i == 0 || i == len - 1 ||
                    sb.charAt(i - 1) == ' ' ||
                    sb.charAt(i - 1) == '\0' ||
                    sb.charAt(i + 1) == ' ' ||
                    sb.charAt(i + 1) == '\0') {
                    sb.deleteCharAt(i);
                    len--;
                } else {
                    i++;
                }
            } else {
                i++;
            }
        }

        for (i = 0; i < len; i++) {
            if (sb.charAt(i) == '\0') {
                sb.setCharAt(i, ' ');
            }
        }
    }

    /**
     * {@inheritDoc}
     */
    public int findTokenStart(CharSequence text, int cursor) {
        /*
         * It's hard to search backward, so search forward until
         * we reach the cursor.
         */

        int best = 0;
        int i = 0;

        while (i < cursor) {
            i = findTokenEnd(text, i);

            if (i < cursor) {
                i++; // Skip terminating punctuation

                while (i < cursor && text.charAt(i) == ' ') {
                    i++;
                }

                if (i < cursor) {
                    best = i;
                }
            }
        }

        return best;
    }

    /**
     * {@inheritDoc}
     */
    public int findTokenEnd(CharSequence text, int cursor) {
        int len = text.length();
        int i = cursor;

        while (i < len) {
            char c = text.charAt(i);

            if (c == ',' || c == ';') {
                return i;
            } else if (c == '"') {
                i++;

                while (i < len) {
                    c = text.charAt(i);

                    if (c == '"') {
                        i++;
                        break;
                    } else if (c == '\\') {
                        i += 2;
                    } else {
                        i++;
                    }
                }
            } else if (c == '(') {
                int level = 1;
                i++;

                while (i < len && level > 0) {
                    c = text.charAt(i);

                    if (c == ')') {
                        level--;
                        i++;
                    } else if (c == '(') {
                        level++;
                        i++;
                    } else if (c == '\\') {
                        i += 2;
                    } else {
                        i++;
                    }
                }
            } else if (c == '<') {
                i++;

                while (i < len) {
                    c = text.charAt(i);

                    if (c == '>') {
                        i++;
                        break;
                    } else {
                        i++;
                    }
                }
            } else {
                i++;
            }
        }

        return i;
    }

    /**
     * Terminates the specified address with a comma and space.
     * This assumes that the specified text already has valid syntax.
     * The Adapter subclass's convertToString() method must make that
     * guarantee.
     */
    public CharSequence terminateToken(CharSequence text) {
        return text + ", ";
    }
}