/src/libunistring/lib/unicase/u-casemap.h
Line  | Count  | Source (jump to first uncovered line)  | 
1  |  | /* Case mapping for UTF-8/UTF-16/UTF-32 strings (locale dependent).  | 
2  |  |    Copyright (C) 2009-2024 Free Software Foundation, Inc.  | 
3  |  |    Written by Bruno Haible <bruno@clisp.org>, 2009.  | 
4  |  |  | 
5  |  |    This file is free software.  | 
6  |  |    It is dual-licensed under "the GNU LGPLv3+ or the GNU GPLv2+".  | 
7  |  |    You can redistribute it and/or modify it under either  | 
8  |  |      - the terms of the GNU Lesser General Public License as published  | 
9  |  |        by the Free Software Foundation, either version 3, or (at your  | 
10  |  |        option) any later version, or  | 
11  |  |      - the terms of the GNU General Public License as published by the  | 
12  |  |        Free Software Foundation; either version 2, or (at your option)  | 
13  |  |        any later version, or  | 
14  |  |      - the same dual license "the GNU LGPLv3+ or the GNU GPLv2+".  | 
15  |  |  | 
16  |  |    This file is distributed in the hope that it will be useful,  | 
17  |  |    but WITHOUT ANY WARRANTY; without even the implied warranty of  | 
18  |  |    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU  | 
19  |  |    Lesser General Public License and the GNU General Public License  | 
20  |  |    for more details.  | 
21  |  |  | 
22  |  |    You should have received a copy of the GNU Lesser General Public  | 
23  |  |    License and of the GNU General Public License along with this  | 
24  |  |    program.  If not, see <https://www.gnu.org/licenses/>.  */  | 
25  |  |  | 
26  |  | UNIT *  | 
27  |  | FUNC (const UNIT *s, size_t n,  | 
28  |  |       casing_prefix_context_t prefix_context,  | 
29  |  |       casing_suffix_context_t suffix_context,  | 
30  |  |       const char *iso639_language,  | 
31  |  |       ucs4_t (*single_character_map) (ucs4_t),  | 
32  |  |       size_t offset_in_rule, /* offset in 'struct special_casing_rule' */  | 
33  |  |       uninorm_t nf,  | 
34  |  |       UNIT *resultbuf, size_t *lengthp)  | 
35  | 0  | { | 
36  |  |   /* The result being accumulated.  */  | 
37  | 0  |   UNIT *result;  | 
38  | 0  |   size_t length;  | 
39  | 0  |   size_t allocated;  | 
40  |  |  | 
41  |  |   /* Initialize the accumulator.  */  | 
42  | 0  |   if (nf != NULL || resultbuf == NULL)  | 
43  | 0  |     { | 
44  | 0  |       result = NULL;  | 
45  | 0  |       allocated = 0;  | 
46  | 0  |     }  | 
47  | 0  |   else  | 
48  | 0  |     { | 
49  | 0  |       result = resultbuf;  | 
50  | 0  |       allocated = *lengthp;  | 
51  | 0  |     }  | 
52  | 0  |   length = 0;  | 
53  |  | 
  | 
54  | 0  |   { | 
55  | 0  |     const UNIT *s_end = s + n;  | 
56  |  |  | 
57  |  |     /* Helper for evaluating the FINAL_SIGMA condition:  | 
58  |  |        Last character that was not case-ignorable.  */  | 
59  | 0  |     ucs4_t last_char_except_ignorable =  | 
60  | 0  |       prefix_context.last_char_except_ignorable;  | 
61  |  |  | 
62  |  |     /* Helper for evaluating the AFTER_SOFT_DOTTED and AFTER_I conditions:  | 
63  |  |        Last character that was of combining class 230 ("Above") or 0.  */ | 
64  | 0  |     ucs4_t last_char_normal_or_above =  | 
65  | 0  |       prefix_context.last_char_normal_or_above;  | 
66  |  | 
  | 
67  | 0  |     while (s < s_end)  | 
68  | 0  |       { | 
69  | 0  |         ucs4_t uc;  | 
70  | 0  |         int count = U_MBTOUC_UNSAFE (&uc, s, s_end - s);  | 
71  |  | 
  | 
72  | 0  |         ucs4_t mapped_uc[3];  | 
73  | 0  |         unsigned int mapped_count;  | 
74  |  | 
  | 
75  | 0  |         if (uc < 0x10000)  | 
76  | 0  |           { | 
77  |  |             /* Look first in the special-casing table.  */  | 
78  | 0  |             char code[3];  | 
79  |  | 
  | 
80  | 0  |             code[0] = (uc >> 8) & 0xff;  | 
81  | 0  |             code[1] = uc & 0xff;  | 
82  |  | 
  | 
83  | 0  |             for (code[2] = 0; ; code[2]++)  | 
84  | 0  |               { | 
85  | 0  |                 const struct special_casing_rule *rule =  | 
86  | 0  |                   gl_unicase_special_lookup (code, 3);  | 
87  |  | 
  | 
88  | 0  |                 if (rule == NULL)  | 
89  | 0  |                   break;  | 
90  |  |  | 
91  |  |                 /* Test if the condition applies.  */  | 
92  |  |                 /* Does the language apply?  */  | 
93  | 0  |                 if (rule->language[0] == '\0'  | 
94  | 0  |                     || (iso639_language != NULL  | 
95  | 0  |                         && iso639_language[0] == rule->language[0]  | 
96  | 0  |                         && iso639_language[1] == rule->language[1]))  | 
97  | 0  |                   { | 
98  |  |                     /* Does the context apply?  */  | 
99  | 0  |                     int context = rule->context;  | 
100  | 0  |                     bool applies;  | 
101  |  | 
  | 
102  | 0  |                     if (context < 0)  | 
103  | 0  |                       context = - context;  | 
104  | 0  |                     switch (context)  | 
105  | 0  |                       { | 
106  | 0  |                       case SCC_ALWAYS:  | 
107  | 0  |                         applies = true;  | 
108  | 0  |                         break;  | 
109  |  |  | 
110  | 0  |                       case SCC_FINAL_SIGMA:  | 
111  |  |                         /* "Before" condition: preceded by a sequence  | 
112  |  |                            consisting of a cased letter and a case-ignorable  | 
113  |  |                            sequence.  | 
114  |  |                            "After" condition: not followed by a sequence  | 
115  |  |                            consisting of a case-ignorable sequence and then a  | 
116  |  |                            cased letter.  */  | 
117  |  |                         /* Test the "before" condition.  */  | 
118  | 0  |                         applies = uc_is_cased (last_char_except_ignorable);  | 
119  |  |                         /* Test the "after" condition.  */  | 
120  | 0  |                         if (applies)  | 
121  | 0  |                           { | 
122  | 0  |                             const UNIT *s2 = s + count;  | 
123  | 0  |                             for (;;)  | 
124  | 0  |                               { | 
125  | 0  |                                 if (s2 < s_end)  | 
126  | 0  |                                   { | 
127  | 0  |                                     ucs4_t uc2;  | 
128  | 0  |                                     int count2 = U_MBTOUC_UNSAFE (&uc2, s2, s_end - s2);  | 
129  |  |                                     /* Our uc_is_case_ignorable function is  | 
130  |  |                                        known to return false for all cased  | 
131  |  |                                        characters.  So we can call  | 
132  |  |                                        uc_is_case_ignorable first.  */  | 
133  | 0  |                                     if (!uc_is_case_ignorable (uc2))  | 
134  | 0  |                                       { | 
135  | 0  |                                         applies = ! uc_is_cased (uc2);  | 
136  | 0  |                                         break;  | 
137  | 0  |                                       }  | 
138  | 0  |                                     s2 += count2;  | 
139  | 0  |                                   }  | 
140  | 0  |                                 else  | 
141  | 0  |                                   { | 
142  | 0  |                                     applies = ! uc_is_cased (suffix_context.first_char_except_ignorable);  | 
143  | 0  |                                     break;  | 
144  | 0  |                                   }  | 
145  | 0  |                               }  | 
146  | 0  |                           }  | 
147  | 0  |                         break;  | 
148  |  |  | 
149  | 0  |                       case SCC_AFTER_SOFT_DOTTED:  | 
150  |  |                         /* "Before" condition: There is a Soft_Dotted character  | 
151  |  |                            before it, with no intervening character of  | 
152  |  |                            combining class 0 or 230 (Above).  */  | 
153  |  |                         /* Test the "before" condition.  */  | 
154  | 0  |                         applies = uc_is_property_soft_dotted (last_char_normal_or_above);  | 
155  | 0  |                         break;  | 
156  |  |  | 
157  | 0  |                       case SCC_MORE_ABOVE:  | 
158  |  |                         /* "After" condition: followed by a character of  | 
159  |  |                            combining class 230 (Above) with no intervening  | 
160  |  |                            character of combining class 0 or 230 (Above).  */  | 
161  |  |                         /* Test the "after" condition.  */  | 
162  | 0  |                         { | 
163  | 0  |                           const UNIT *s2 = s + count;  | 
164  | 0  |                           applies = false;  | 
165  | 0  |                           for (;;)  | 
166  | 0  |                             { | 
167  | 0  |                               if (s2 < s_end)  | 
168  | 0  |                                 { | 
169  | 0  |                                   ucs4_t uc2;  | 
170  | 0  |                                   int count2 = U_MBTOUC_UNSAFE (&uc2, s2, s_end - s2);  | 
171  | 0  |                                   int ccc = uc_combining_class (uc2);  | 
172  | 0  |                                   if (ccc == UC_CCC_A)  | 
173  | 0  |                                     { | 
174  | 0  |                                       applies = true;  | 
175  | 0  |                                       break;  | 
176  | 0  |                                     }  | 
177  | 0  |                                   if (ccc == UC_CCC_NR)  | 
178  | 0  |                                     break;  | 
179  | 0  |                                   s2 += count2;  | 
180  | 0  |                                 }  | 
181  | 0  |                               else  | 
182  | 0  |                                 { | 
183  | 0  |                                   applies = ((suffix_context.bits & SCC_MORE_ABOVE_MASK) != 0);  | 
184  | 0  |                                   break;  | 
185  | 0  |                                 }  | 
186  | 0  |                             }  | 
187  | 0  |                         }  | 
188  | 0  |                         break;  | 
189  |  |  | 
190  | 0  |                       case SCC_BEFORE_DOT:  | 
191  |  |                         /* "After" condition: followed by COMBINING DOT ABOVE  | 
192  |  |                            (U+0307). Any sequence of characters with a  | 
193  |  |                            combining class that is neither 0 nor 230 may  | 
194  |  |                            intervene between the current character and the  | 
195  |  |                            combining dot above.  */  | 
196  |  |                         /* Test the "after" condition.  */  | 
197  | 0  |                         { | 
198  | 0  |                           const UNIT *s2 = s + count;  | 
199  | 0  |                           applies = false;  | 
200  | 0  |                           for (;;)  | 
201  | 0  |                             { | 
202  | 0  |                               if (s2 < s_end)  | 
203  | 0  |                                 { | 
204  | 0  |                                   ucs4_t uc2;  | 
205  | 0  |                                   int count2 = U_MBTOUC_UNSAFE (&uc2, s2, s_end - s2);  | 
206  | 0  |                                   if (uc2 == 0x0307) /* COMBINING DOT ABOVE */  | 
207  | 0  |                                     { | 
208  | 0  |                                       applies = true;  | 
209  | 0  |                                       break;  | 
210  | 0  |                                     }  | 
211  | 0  |                                   { | 
212  | 0  |                                     int ccc = uc_combining_class (uc2);  | 
213  | 0  |                                     if (ccc == UC_CCC_A || ccc == UC_CCC_NR)  | 
214  | 0  |                                       break;  | 
215  | 0  |                                   }  | 
216  | 0  |                                   s2 += count2;  | 
217  | 0  |                                 }  | 
218  | 0  |                               else  | 
219  | 0  |                                 { | 
220  | 0  |                                   applies = ((suffix_context.bits & SCC_BEFORE_DOT_MASK) != 0);  | 
221  | 0  |                                   break;  | 
222  | 0  |                                 }  | 
223  | 0  |                             }  | 
224  | 0  |                         }  | 
225  | 0  |                         break;  | 
226  |  |  | 
227  | 0  |                       case SCC_AFTER_I:  | 
228  |  |                         /* "Before" condition: There is an uppercase I before  | 
229  |  |                            it, and there is no intervening character of  | 
230  |  |                            combining class 0 or 230 (Above).  */  | 
231  |  |                         /* Test the "before" condition.  */  | 
232  | 0  |                         applies = (last_char_normal_or_above == 'I');  | 
233  | 0  |                         break;  | 
234  |  |  | 
235  | 0  |                       default:  | 
236  | 0  |                         abort ();  | 
237  | 0  |                       }  | 
238  | 0  |                     if (rule->context < 0)  | 
239  | 0  |                       applies = !applies;  | 
240  |  | 
  | 
241  | 0  |                     if (applies)  | 
242  | 0  |                       { | 
243  |  |                         /* The rule applies.  | 
244  |  |                            Look up the mapping (0 to 3 characters).  */  | 
245  | 0  |                         const unsigned short *mapped_in_rule =  | 
246  | 0  |                           (const unsigned short *)((const char *)rule + offset_in_rule);  | 
247  |  | 
  | 
248  | 0  |                         if (mapped_in_rule[0] == 0)  | 
249  | 0  |                           mapped_count = 0;  | 
250  | 0  |                         else  | 
251  | 0  |                           { | 
252  | 0  |                             mapped_uc[0] = mapped_in_rule[0];  | 
253  | 0  |                             if (mapped_in_rule[1] == 0)  | 
254  | 0  |                               mapped_count = 1;  | 
255  | 0  |                             else  | 
256  | 0  |                               { | 
257  | 0  |                                 mapped_uc[1] = mapped_in_rule[1];  | 
258  | 0  |                                 if (mapped_in_rule[2] == 0)  | 
259  | 0  |                                   mapped_count = 2;  | 
260  | 0  |                                 else  | 
261  | 0  |                                   { | 
262  | 0  |                                     mapped_uc[2] = mapped_in_rule[2];  | 
263  | 0  |                                     mapped_count = 3;  | 
264  | 0  |                                   }  | 
265  | 0  |                               }  | 
266  | 0  |                           }  | 
267  | 0  |                         goto found_mapping;  | 
268  | 0  |                       }  | 
269  | 0  |                   }  | 
270  |  |  | 
271  |  |                 /* Optimization: Save a hash table lookup in the next round.  */  | 
272  | 0  |                 if (!rule->has_next)  | 
273  | 0  |                   break;  | 
274  | 0  |               }  | 
275  | 0  |           }  | 
276  |  |  | 
277  |  |         /* No special-cased mapping.  So use the locale and context independent  | 
278  |  |            mapping.  */  | 
279  | 0  |         mapped_uc[0] = single_character_map (uc);  | 
280  | 0  |         mapped_count = 1;  | 
281  |  | 
  | 
282  | 0  |        found_mapping:  | 
283  |  |         /* Found the mapping: uc maps to mapped_uc[0..mapped_count-1].  */  | 
284  | 0  |         { | 
285  | 0  |           unsigned int i;  | 
286  |  | 
  | 
287  | 0  |           for (i = 0; i < mapped_count; i++)  | 
288  | 0  |             { | 
289  | 0  |               ucs4_t muc = mapped_uc[i];  | 
290  |  |  | 
291  |  |               /* Append muc to the result accumulator.  */  | 
292  | 0  |               if (length < allocated)  | 
293  | 0  |                 { | 
294  | 0  |                   int ret = U_UCTOMB (result + length, muc, allocated - length);  | 
295  | 0  |                   if (ret == -1)  | 
296  | 0  |                     { | 
297  | 0  |                       errno = EINVAL;  | 
298  | 0  |                       goto fail;  | 
299  | 0  |                     }  | 
300  | 0  |                   if (ret >= 0)  | 
301  | 0  |                     { | 
302  | 0  |                       length += ret;  | 
303  | 0  |                       goto done_appending;  | 
304  | 0  |                     }  | 
305  | 0  |                 }  | 
306  | 0  |               { | 
307  | 0  |                 size_t old_allocated = allocated;  | 
308  | 0  |                 size_t new_allocated = 2 * old_allocated;  | 
309  | 0  |                 if (new_allocated < 64)  | 
310  | 0  |                   new_allocated = 64;  | 
311  | 0  |                 if (new_allocated < old_allocated) /* integer overflow? */  | 
312  | 0  |                   abort ();  | 
313  | 0  |                 { | 
314  | 0  |                   UNIT *larger_result;  | 
315  | 0  |                   if (result == NULL)  | 
316  | 0  |                     { | 
317  | 0  |                       larger_result = (UNIT *) malloc (new_allocated * sizeof (UNIT));  | 
318  | 0  |                       if (larger_result == NULL)  | 
319  | 0  |                         { | 
320  | 0  |                           errno = ENOMEM;  | 
321  | 0  |                           goto fail;  | 
322  | 0  |                         }  | 
323  | 0  |                     }  | 
324  | 0  |                   else if (result == resultbuf)  | 
325  | 0  |                     { | 
326  | 0  |                       larger_result = (UNIT *) malloc (new_allocated * sizeof (UNIT));  | 
327  | 0  |                       if (larger_result == NULL)  | 
328  | 0  |                         { | 
329  | 0  |                           errno = ENOMEM;  | 
330  | 0  |                           goto fail;  | 
331  | 0  |                         }  | 
332  | 0  |                       U_CPY (larger_result, resultbuf, length);  | 
333  | 0  |                     }  | 
334  | 0  |                   else  | 
335  | 0  |                     { | 
336  | 0  |                       larger_result =  | 
337  | 0  |                         (UNIT *) realloc (result, new_allocated * sizeof (UNIT));  | 
338  | 0  |                       if (larger_result == NULL)  | 
339  | 0  |                         { | 
340  | 0  |                           errno = ENOMEM;  | 
341  | 0  |                           goto fail;  | 
342  | 0  |                         }  | 
343  | 0  |                     }  | 
344  | 0  |                   result = larger_result;  | 
345  | 0  |                   allocated = new_allocated;  | 
346  | 0  |                   { | 
347  | 0  |                     int ret = U_UCTOMB (result + length, muc, allocated - length);  | 
348  | 0  |                     if (ret == -1)  | 
349  | 0  |                       { | 
350  | 0  |                         errno = EINVAL;  | 
351  | 0  |                         goto fail;  | 
352  | 0  |                       }  | 
353  | 0  |                     if (ret < 0)  | 
354  | 0  |                       abort ();  | 
355  | 0  |                     length += ret;  | 
356  | 0  |                     goto done_appending;  | 
357  | 0  |                   }  | 
358  | 0  |                 }  | 
359  | 0  |               }  | 
360  | 0  |              done_appending: ;  | 
361  | 0  |             }  | 
362  | 0  |         }  | 
363  |  |  | 
364  | 0  |         if (!uc_is_case_ignorable (uc))  | 
365  | 0  |           last_char_except_ignorable = uc;  | 
366  |  | 
  | 
367  | 0  |         { | 
368  | 0  |           int ccc = uc_combining_class (uc);  | 
369  | 0  |           if (ccc == UC_CCC_A || ccc == UC_CCC_NR)  | 
370  | 0  |             last_char_normal_or_above = uc;  | 
371  | 0  |         }  | 
372  |  | 
  | 
373  | 0  |         s += count;  | 
374  | 0  |       }  | 
375  | 0  |   }  | 
376  |  |  | 
377  | 0  |   if (nf != NULL)  | 
378  | 0  |     { | 
379  |  |       /* Finally, normalize the result.  */  | 
380  | 0  |       UNIT *normalized_result;  | 
381  |  | 
  | 
382  | 0  |       normalized_result = U_NORMALIZE (nf, result, length, resultbuf, lengthp);  | 
383  | 0  |       if (normalized_result == NULL)  | 
384  | 0  |         goto fail;  | 
385  |  |  | 
386  | 0  |       free (result);  | 
387  | 0  |       return normalized_result;  | 
388  | 0  |     }  | 
389  |  |  | 
390  | 0  |   if (length == 0)  | 
391  | 0  |     { | 
392  | 0  |       if (result == NULL)  | 
393  | 0  |         { | 
394  |  |           /* Return a non-NULL value.  NULL means error.  */  | 
395  | 0  |           result = (UNIT *) malloc (1);  | 
396  | 0  |           if (result == NULL)  | 
397  | 0  |             { | 
398  | 0  |               errno = ENOMEM;  | 
399  | 0  |               goto fail;  | 
400  | 0  |             }  | 
401  | 0  |         }  | 
402  | 0  |     }  | 
403  | 0  |   else if (result != resultbuf && length < allocated)  | 
404  | 0  |     { | 
405  |  |       /* Shrink the allocated memory if possible.  */  | 
406  | 0  |       UNIT *memory;  | 
407  |  | 
  | 
408  | 0  |       memory = (UNIT *) realloc (result, length * sizeof (UNIT));  | 
409  | 0  |       if (memory != NULL)  | 
410  | 0  |         result = memory;  | 
411  | 0  |     }  | 
412  |  |  | 
413  | 0  |   *lengthp = length;  | 
414  | 0  |   return result;  | 
415  |  |  | 
416  | 0  |  fail:  | 
417  | 0  |   if (result != resultbuf)  | 
418  | 0  |     { | 
419  | 0  |       int saved_errno = errno;  | 
420  | 0  |       free (result);  | 
421  | 0  |       errno = saved_errno;  | 
422  | 0  |     }  | 
423  | 0  |   return NULL;  | 
424  | 0  | }  |