diff options
Diffstat (limited to 'ldap/clients/dsgw/utf8compare.c')
-rw-r--r-- | ldap/clients/dsgw/utf8compare.c | 2236 |
1 files changed, 2236 insertions, 0 deletions
diff --git a/ldap/clients/dsgw/utf8compare.c b/ldap/clients/dsgw/utf8compare.c new file mode 100644 index 00000000..59c85253 --- /dev/null +++ b/ldap/clients/dsgw/utf8compare.c @@ -0,0 +1,2236 @@ +/** + * PROPRIETARY/CONFIDENTIAL. Use of this product is subject to + * license terms. Copyright © 2001 Sun Microsystems, Inc. + * Some preexisting portions Copyright © 2001 Netscape Communications Corp. + * All rights reserved. + */ +#include <stdio.h> +#include <string.h> +#include <ctype.h> +#include "ldap.h" +#include "dsgw.h" + +typedef struct sUpperLowerTbl { + char *upper, *lower; + int tsz; /* target size */ +} UpperLowerTbl_t; + +/* + * dsgw_has8thBit: check the input string + * return 1 if the string contains 8-bit character + * return 0 otherwise + */ +int +dsgw_has8thBit(unsigned char *s) +{ + unsigned char *p, *tail; + tail = s + strlen((char *)s); + for (p = s; p < tail; p++) { + if (0x80 & *p) { + return 1; + } + } + return 0; +} + +/* + * UpperToLower Tables: sorted by upper characters + */ +UpperLowerTbl_t Upper2LowerTbl20[] = { + /* upper, lower */ + {"\303\200", "\303\240", 2}, + {"\303\201", "\303\241", 2}, + {"\303\202", "\303\242", 2}, + {"\303\203", "\303\243", 2}, + {"\303\204", "\303\244", 2}, + {"\303\205", "\303\245", 2}, + {"\303\206", "\303\246", 2}, + {"\303\207", "\303\247", 2}, + {"\303\210", "\303\250", 2}, + {"\303\211", "\303\251", 2}, + {"\303\212", "\303\252", 2}, + {"\303\213", "\303\253", 2}, + {"\303\214", "\303\254", 2}, + {"\303\215", "\303\255", 2}, + {"\303\216", "\303\256", 2}, + {"\303\217", "\303\257", 2}, + {"\303\220", "\303\260", 2}, + {"\303\221", "\303\261", 2}, + {"\303\222", "\303\262", 2}, + {"\303\223", "\303\263", 2}, + {"\303\224", "\303\264", 2}, + {"\303\225", "\303\265", 2}, + {"\303\226", "\303\266", 2}, + {"\303\230", "\303\270", 2}, + {"\303\231", "\303\271", 2}, + {"\303\232", "\303\272", 2}, + {"\303\233", "\303\273", 2}, + {"\303\234", "\303\274", 2}, + {"\303\235", "\303\275", 2}, + {"\303\236", "\303\276", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl21[] = { + {"\304\200", "\304\201", 2}, + {"\304\202", "\304\203", 2}, + {"\304\204", "\304\205", 2}, + {"\304\206", "\304\207", 2}, + {"\304\210", "\304\211", 2}, + {"\304\212", "\304\213", 2}, + {"\304\214", "\304\215", 2}, + {"\304\216", "\304\217", 2}, + {"\304\220", "\304\221", 2}, + {"\304\222", "\304\223", 2}, + {"\304\224", "\304\225", 2}, + {"\304\226", "\304\227", 2}, + {"\304\230", "\304\231", 2}, + {"\304\232", "\304\233", 2}, + {"\304\234", "\304\235", 2}, + {"\304\236", "\304\237", 2}, + {"\304\240", "\304\241", 2}, + {"\304\242", "\304\243", 2}, + {"\304\244", "\304\245", 2}, + {"\304\246", "\304\247", 2}, + {"\304\250", "\304\251", 2}, + {"\304\252", "\304\253", 2}, + {"\304\254", "\304\255", 2}, + {"\304\256", "\304\257", 2}, + {"\304\260", "\151", 1}, + {"\304\262", "\304\263", 2}, + {"\304\264", "\304\265", 2}, + {"\304\266", "\304\267", 2}, + {"\304\271", "\304\272", 2}, + {"\304\273", "\304\274", 2}, + {"\304\275", "\304\276", 2}, + {"\304\277", "\305\200", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl22[] = { + {"\305\201", "\305\202", 2}, + {"\305\203", "\305\204", 2}, + {"\305\205", "\305\206", 2}, + {"\305\207", "\305\210", 2}, + {"\305\212", "\305\213", 2}, + {"\305\214", "\305\215", 2}, + {"\305\216", "\305\217", 2}, + {"\305\220", "\305\221", 2}, + {"\305\222", "\305\223", 2}, + {"\305\224", "\305\225", 2}, + {"\305\226", "\305\227", 2}, + {"\305\230", "\305\231", 2}, + {"\305\232", "\305\233", 2}, + {"\305\234", "\305\235", 2}, + {"\305\236", "\305\237", 2}, + {"\305\240", "\305\241", 2}, + {"\305\242", "\305\243", 2}, + {"\305\244", "\305\245", 2}, + {"\305\246", "\305\247", 2}, + {"\305\250", "\305\251", 2}, + {"\305\252", "\305\253", 2}, + {"\305\254", "\305\255", 2}, + {"\305\256", "\305\257", 2}, + {"\305\260", "\305\261", 2}, + {"\305\262", "\305\263", 2}, + {"\305\264", "\305\265", 2}, + {"\305\266", "\305\267", 2}, + {"\305\270", "\303\277", 2}, + {"\305\271", "\305\272", 2}, + {"\305\273", "\305\274", 2}, + {"\305\275", "\305\276", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl23[] = { + {"\306\201", "\311\223", 2}, + {"\306\202", "\306\203", 2}, + {"\306\204", "\306\205", 2}, + {"\306\206", "\311\224", 2}, + {"\306\207", "\306\210", 2}, + {"\306\211", "\311\226", 2}, + {"\306\212", "\311\227", 2}, + {"\306\213", "\306\214", 2}, + {"\306\216", "\311\230", 2}, + {"\306\217", "\311\231", 2}, + {"\306\220", "\311\233", 2}, + {"\306\221", "\306\222", 2}, + {"\306\223", "\311\240", 2}, + {"\306\224", "\311\243", 2}, + {"\306\226", "\311\251", 2}, + {"\306\227", "\311\250", 2}, + {"\306\230", "\306\231", 2}, + {"\306\234", "\311\257", 2}, + {"\306\235", "\311\262", 2}, + {"\306\237", "\306\237", 2}, + {"\306\240", "\306\241", 2}, + {"\306\242", "\306\243", 2}, + {"\306\244", "\306\245", 2}, + {"\306\246", "\306\246", 2}, + {"\306\247", "\306\250", 2}, + {"\306\251", "\312\203", 2}, + {"\306\254", "\306\255", 2}, + {"\306\256", "\312\210", 2}, + {"\306\257", "\306\260", 2}, + {"\306\261", "\312\212", 2}, + {"\306\262", "\312\213", 2}, + {"\306\263", "\306\264", 2}, + {"\306\265", "\306\266", 2}, + {"\306\267", "\312\222", 2}, + {"\306\270", "\306\271", 2}, + {"\306\274", "\306\275", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl24[] = { + {"\307\204", "\307\205", 2}, + {"\307\205", "\307\204", 2}, + {"\307\207", "\307\210", 2}, + {"\307\210", "\307\207", 2}, + {"\307\212", "\307\213", 2}, + {"\307\213", "\307\212", 2}, + {"\307\215", "\307\216", 2}, + {"\307\217", "\307\220", 2}, + {"\307\221", "\307\222", 2}, + {"\307\223", "\307\224", 2}, + {"\307\225", "\307\226", 2}, + {"\307\227", "\307\230", 2}, + {"\307\231", "\307\232", 2}, + {"\307\233", "\307\234", 2}, + {"\307\236", "\307\237", 2}, + {"\307\240", "\307\241", 2}, + {"\307\242", "\307\243", 2}, + {"\307\244", "\307\245", 2}, + {"\307\246", "\307\247", 2}, + {"\307\250", "\307\251", 2}, + {"\307\252", "\307\253", 2}, + {"\307\254", "\307\255", 2}, + {"\307\256", "\307\257", 2}, + {"\307\261", "\307\262", 2}, + {"\307\262", "\307\261", 2}, + {"\307\264", "\307\265", 2}, + {"\307\272", "\307\273", 2}, + {"\307\274", "\307\275", 2}, + {"\307\276", "\307\277", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl25[] = { + {"\310\200", "\310\201", 2}, + {"\310\202", "\310\203", 2}, + {"\310\204", "\310\205", 2}, + {"\310\206", "\310\207", 2}, + {"\310\210", "\310\211", 2}, + {"\310\212", "\310\213", 2}, + {"\310\214", "\310\215", 2}, + {"\310\216", "\310\217", 2}, + {"\310\220", "\310\221", 2}, + {"\310\222", "\310\223", 2}, + {"\310\224", "\310\225", 2}, + {"\310\226", "\310\227", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl26[] = { + {"\316\206", "\316\254", 2}, + {"\316\210", "\316\255", 2}, + {"\316\211", "\316\256", 2}, + {"\316\212", "\316\257", 2}, + {"\316\214", "\317\214", 2}, + {"\316\216", "\317\215", 2}, + {"\316\217", "\317\216", 2}, + {"\316\221", "\316\261", 2}, + {"\316\222", "\316\262", 2}, + {"\316\223", "\316\263", 2}, + {"\316\224", "\316\264", 2}, + {"\316\225", "\316\265", 2}, + {"\316\226", "\316\266", 2}, + {"\316\227", "\316\267", 2}, + {"\316\230", "\316\270", 2}, + {"\316\231", "\316\271", 2}, + {"\316\232", "\316\272", 2}, + {"\316\233", "\316\273", 2}, + {"\316\234", "\316\274", 2}, + {"\316\235", "\316\275", 2}, + {"\316\236", "\316\276", 2}, + {"\316\237", "\316\277", 2}, + {"\316\240", "\317\200", 2}, + {"\316\241", "\317\201", 2}, + {"\316\243", "\317\203", 2}, + {"\316\244", "\317\204", 2}, + {"\316\245", "\317\205", 2}, + {"\316\246", "\317\206", 2}, + {"\316\247", "\317\207", 2}, + {"\316\250", "\317\210", 2}, + {"\316\251", "\317\211", 2}, + {"\316\252", "\317\212", 2}, + {"\316\253", "\317\213", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl27[] = { + {"\317\222", "\317\222", 2}, + {"\317\223", "\317\223", 2}, + {"\317\224", "\317\224", 2}, + {"\317\232", "\317\232", 2}, + {"\317\234", "\317\234", 2}, + {"\317\236", "\317\236", 2}, + {"\317\240", "\317\240", 2}, + {"\317\242", "\317\243", 2}, + {"\317\244", "\317\245", 2}, + {"\317\246", "\317\247", 2}, + {"\317\250", "\317\251", 2}, + {"\317\252", "\317\253", 2}, + {"\317\254", "\317\255", 2}, + {"\317\256", "\317\257", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl28[] = { + {"\320\201", "\321\221", 2}, + {"\320\202", "\321\222", 2}, + {"\320\203", "\321\223", 2}, + {"\320\204", "\321\224", 2}, + {"\320\205", "\321\225", 2}, + {"\320\206", "\321\226", 2}, + {"\320\207", "\321\227", 2}, + {"\320\210", "\321\230", 2}, + {"\320\211", "\321\231", 2}, + {"\320\212", "\321\232", 2}, + {"\320\213", "\321\233", 2}, + {"\320\214", "\321\234", 2}, + {"\320\216", "\321\236", 2}, + {"\320\217", "\321\237", 2}, + {"\320\220", "\320\260", 2}, + {"\320\221", "\320\261", 2}, + {"\320\222", "\320\262", 2}, + {"\320\223", "\320\263", 2}, + {"\320\224", "\320\264", 2}, + {"\320\225", "\320\265", 2}, + {"\320\226", "\320\266", 2}, + {"\320\227", "\320\267", 2}, + {"\320\230", "\320\270", 2}, + {"\320\231", "\320\271", 2}, + {"\320\232", "\320\272", 2}, + {"\320\233", "\320\273", 2}, + {"\320\234", "\320\274", 2}, + {"\320\235", "\320\275", 2}, + {"\320\236", "\320\276", 2}, + {"\320\237", "\320\277", 2}, + {"\320\240", "\321\200", 2}, + {"\320\241", "\321\201", 2}, + {"\320\242", "\321\202", 2}, + {"\320\243", "\321\203", 2}, + {"\320\244", "\321\204", 2}, + {"\320\245", "\321\205", 2}, + {"\320\246", "\321\206", 2}, + {"\320\247", "\321\207", 2}, + {"\320\250", "\321\210", 2}, + {"\320\251", "\321\211", 2}, + {"\320\252", "\321\212", 2}, + {"\320\253", "\321\213", 2}, + {"\320\254", "\321\214", 2}, + {"\320\255", "\321\215", 2}, + {"\320\256", "\321\216", 2}, + {"\320\257", "\321\217", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl29[] = { + {"\321\240", "\321\241", 2}, + {"\321\242", "\321\243", 2}, + {"\321\244", "\321\245", 2}, + {"\321\246", "\321\247", 2}, + {"\321\250", "\321\251", 2}, + {"\321\252", "\321\253", 2}, + {"\321\254", "\321\255", 2}, + {"\321\256", "\321\257", 2}, + {"\321\260", "\321\261", 2}, + {"\321\262", "\321\263", 2}, + {"\321\264", "\321\265", 2}, + {"\321\266", "\321\267", 2}, + {"\321\270", "\321\271", 2}, + {"\321\272", "\321\273", 2}, + {"\321\274", "\321\275", 2}, + {"\321\276", "\321\277", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl2a[] = { + {"\322\200", "\322\201", 2}, + {"\322\220", "\322\221", 2}, + {"\322\222", "\322\223", 2}, + {"\322\224", "\322\225", 2}, + {"\322\226", "\322\227", 2}, + {"\322\230", "\322\231", 2}, + {"\322\232", "\322\233", 2}, + {"\322\234", "\322\235", 2}, + {"\322\236", "\322\237", 2}, + {"\322\240", "\322\241", 2}, + {"\322\242", "\322\243", 2}, + {"\322\244", "\322\245", 2}, + {"\322\246", "\322\247", 2}, + {"\322\250", "\322\251", 2}, + {"\322\252", "\322\253", 2}, + {"\322\254", "\322\255", 2}, + {"\322\256", "\322\257", 2}, + {"\322\260", "\322\261", 2}, + {"\322\262", "\322\263", 2}, + {"\322\264", "\322\265", 2}, + {"\322\266", "\322\267", 2}, + {"\322\270", "\322\271", 2}, + {"\322\272", "\322\273", 2}, + {"\322\274", "\322\275", 2}, + {"\322\276", "\322\277", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl2b[] = { + {"\323\201", "\323\202", 2}, + {"\323\203", "\323\204", 2}, + {"\323\207", "\323\210", 2}, + {"\323\213", "\323\214", 2}, + {"\323\220", "\323\221", 2}, + {"\323\222", "\323\223", 2}, + {"\323\224", "\323\225", 2}, + {"\323\226", "\323\227", 2}, + {"\323\230", "\323\231", 2}, + {"\323\232", "\323\233", 2}, + {"\323\234", "\323\235", 2}, + {"\323\236", "\323\237", 2}, + {"\323\240", "\323\241", 2}, + {"\323\242", "\323\243", 2}, + {"\323\244", "\323\245", 2}, + {"\323\246", "\323\247", 2}, + {"\323\250", "\323\251", 2}, + {"\323\252", "\323\253", 2}, + {"\323\256", "\323\257", 2}, + {"\323\260", "\323\261", 2}, + {"\323\262", "\323\263", 2}, + {"\323\264", "\323\265", 2}, + {"\323\270", "\323\271", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl2c[] = { + {"\324\261", "\325\241", 2}, + {"\324\262", "\325\242", 2}, + {"\324\263", "\325\243", 2}, + {"\324\264", "\325\244", 2}, + {"\324\265", "\325\245", 2}, + {"\324\266", "\325\246", 2}, + {"\324\267", "\325\247", 2}, + {"\324\270", "\325\250", 2}, + {"\324\271", "\325\251", 2}, + {"\324\272", "\325\252", 2}, + {"\324\273", "\325\253", 2}, + {"\324\274", "\325\254", 2}, + {"\324\275", "\325\255", 2}, + {"\324\276", "\325\256", 2}, + {"\324\277", "\325\257", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl2d[] = { + {"\325\200", "\325\260", 2}, + {"\325\201", "\325\261", 2}, + {"\325\202", "\325\262", 2}, + {"\325\203", "\325\263", 2}, + {"\325\204", "\325\264", 2}, + {"\325\205", "\325\265", 2}, + {"\325\206", "\325\266", 2}, + {"\325\207", "\325\267", 2}, + {"\325\210", "\325\270", 2}, + {"\325\211", "\325\271", 2}, + {"\325\212", "\325\272", 2}, + {"\325\213", "\325\273", 2}, + {"\325\214", "\325\274", 2}, + {"\325\215", "\325\275", 2}, + {"\325\216", "\325\276", 2}, + {"\325\217", "\325\277", 2}, + {"\325\220", "\326\200", 2}, + {"\325\221", "\326\201", 2}, + {"\325\222", "\326\202", 2}, + {"\325\223", "\326\203", 2}, + {"\325\224", "\326\204", 2}, + {"\325\225", "\326\205", 2}, + {"\325\226", "\326\206", 2}, + {NULL, NULL, 0} + /* upper, lower */ +}; + +UpperLowerTbl_t Upper2LowerTbl30[] = { + /* upper, lower */ + {"\341\202\240", "\341\203\220", 3}, + {"\341\202\241", "\341\203\221", 3}, + {"\341\202\242", "\341\203\222", 3}, + {"\341\202\243", "\341\203\223", 3}, + {"\341\202\244", "\341\203\224", 3}, + {"\341\202\245", "\341\203\225", 3}, + {"\341\202\246", "\341\203\226", 3}, + {"\341\202\247", "\341\203\227", 3}, + {"\341\202\250", "\341\203\230", 3}, + {"\341\202\251", "\341\203\231", 3}, + {"\341\202\252", "\341\203\232", 3}, + {"\341\202\253", "\341\203\233", 3}, + {"\341\202\254", "\341\203\234", 3}, + {"\341\202\255", "\341\203\235", 3}, + {"\341\202\256", "\341\203\236", 3}, + {"\341\202\257", "\341\203\237", 3}, + {"\341\202\260", "\341\203\240", 3}, + {"\341\202\261", "\341\203\241", 3}, + {"\341\202\262", "\341\203\242", 3}, + {"\341\202\263", "\341\203\243", 3}, + {"\341\202\264", "\341\203\244", 3}, + {"\341\202\265", "\341\203\245", 3}, + {"\341\202\266", "\341\203\246", 3}, + {"\341\202\267", "\341\203\247", 3}, + {"\341\202\270", "\341\203\250", 3}, + {"\341\202\271", "\341\203\251", 3}, + {"\341\202\272", "\341\203\252", 3}, + {"\341\202\273", "\341\203\253", 3}, + {"\341\202\274", "\341\203\254", 3}, + {"\341\202\275", "\341\203\255", 3}, + {"\341\202\276", "\341\203\256", 3}, + {"\341\202\277", "\341\203\257", 3}, + {"\341\203\200", "\341\203\260", 3}, + {"\341\203\201", "\341\203\261", 3}, + {"\341\203\202", "\341\203\262", 3}, + {"\341\203\203", "\341\203\263", 3}, + {"\341\203\204", "\341\203\264", 3}, + {"\341\203\205", "\341\203\265", 3}, + {"\341\270\200", "\341\270\201", 3}, + {"\341\270\202", "\341\270\203", 3}, + {"\341\270\204", "\341\270\205", 3}, + {"\341\270\206", "\341\270\207", 3}, + {"\341\270\210", "\341\270\211", 3}, + {"\341\270\212", "\341\270\213", 3}, + {"\341\270\214", "\341\270\215", 3}, + {"\341\270\216", "\341\270\217", 3}, + {"\341\270\220", "\341\270\221", 3}, + {"\341\270\222", "\341\270\223", 3}, + {"\341\270\224", "\341\270\225", 3}, + {"\341\270\226", "\341\270\227", 3}, + {"\341\270\230", "\341\270\231", 3}, + {"\341\270\232", "\341\270\233", 3}, + {"\341\270\234", "\341\270\235", 3}, + {"\341\270\236", "\341\270\237", 3}, + {"\341\270\240", "\341\270\241", 3}, + {"\341\270\242", "\341\270\243", 3}, + {"\341\270\244", "\341\270\245", 3}, + {"\341\270\246", "\341\270\247", 3}, + {"\341\270\250", "\341\270\251", 3}, + {"\341\270\252", "\341\270\253", 3}, + {"\341\270\254", "\341\270\255", 3}, + {"\341\270\256", "\341\270\257", 3}, + {"\341\270\260", "\341\270\261", 3}, + {"\341\270\262", "\341\270\263", 3}, + {"\341\270\264", "\341\270\265", 3}, + {"\341\270\266", "\341\270\267", 3}, + {"\341\270\270", "\341\270\271", 3}, + {"\341\270\272", "\341\270\273", 3}, + {"\341\270\274", "\341\270\275", 3}, + {"\341\270\276", "\341\270\277", 3}, + {"\341\271\200", "\341\271\201", 3}, + {"\341\271\202", "\341\271\203", 3}, + {"\341\271\204", "\341\271\205", 3}, + {"\341\271\206", "\341\271\207", 3}, + {"\341\271\210", "\341\271\211", 3}, + {"\341\271\212", "\341\271\213", 3}, + {"\341\271\214", "\341\271\215", 3}, + {"\341\271\216", "\341\271\217", 3}, + {"\341\271\220", "\341\271\221", 3}, + {"\341\271\222", "\341\271\223", 3}, + {"\341\271\224", "\341\271\225", 3}, + {"\341\271\226", "\341\271\227", 3}, + {"\341\271\230", "\341\271\231", 3}, + {"\341\271\232", "\341\271\233", 3}, + {"\341\271\234", "\341\271\235", 3}, + {"\341\271\236", "\341\271\237", 3}, + {"\341\271\240", "\341\271\241", 3}, + {"\341\271\242", "\341\271\243", 3}, + {"\341\271\244", "\341\271\245", 3}, + {"\341\271\246", "\341\271\247", 3}, + {"\341\271\250", "\341\271\251", 3}, + {"\341\271\252", "\341\271\253", 3}, + {"\341\271\254", "\341\271\255", 3}, + {"\341\271\256", "\341\271\257", 3}, + {"\341\271\260", "\341\271\261", 3}, + {"\341\271\262", "\341\271\263", 3}, + {"\341\271\264", "\341\271\265", 3}, + {"\341\271\266", "\341\271\267", 3}, + {"\341\271\270", "\341\271\271", 3}, + {"\341\271\272", "\341\271\273", 3}, + {"\341\271\274", "\341\271\275", 3}, + {"\341\271\276", "\341\271\277", 3}, + {"\341\272\200", "\341\272\201", 3}, + {"\341\272\202", "\341\272\203", 3}, + {"\341\272\204", "\341\272\205", 3}, + {"\341\272\206", "\341\272\207", 3}, + {"\341\272\210", "\341\272\211", 3}, + {"\341\272\212", "\341\272\213", 3}, + {"\341\272\214", "\341\272\215", 3}, + {"\341\272\216", "\341\272\217", 3}, + {"\341\272\220", "\341\272\221", 3}, + {"\341\272\222", "\341\272\223", 3}, + {"\341\272\224", "\341\272\225", 3}, + {"\341\272\240", "\341\272\241", 3}, + {"\341\272\242", "\341\272\243", 3}, + {"\341\272\244", "\341\272\245", 3}, + {"\341\272\246", "\341\272\247", 3}, + {"\341\272\250", "\341\272\251", 3}, + {"\341\272\252", "\341\272\253", 3}, + {"\341\272\254", "\341\272\255", 3}, + {"\341\272\256", "\341\272\257", 3}, + {"\341\272\260", "\341\272\261", 3}, + {"\341\272\262", "\341\272\263", 3}, + {"\341\272\264", "\341\272\265", 3}, + {"\341\272\266", "\341\272\267", 3}, + {"\341\272\270", "\341\272\271", 3}, + {"\341\272\272", "\341\272\273", 3}, + {"\341\272\274", "\341\272\275", 3}, + {"\341\272\276", "\341\272\277", 3}, + {"\341\273\200", "\341\273\201", 3}, + {"\341\273\202", "\341\273\203", 3}, + {"\341\273\204", "\341\273\205", 3}, + {"\341\273\206", "\341\273\207", 3}, + {"\341\273\210", "\341\273\211", 3}, + {"\341\273\212", "\341\273\213", 3}, + {"\341\273\214", "\341\273\215", 3}, + {"\341\273\216", "\341\273\217", 3}, + {"\341\273\220", "\341\273\221", 3}, + {"\341\273\222", "\341\273\223", 3}, + {"\341\273\224", "\341\273\225", 3}, + {"\341\273\226", "\341\273\227", 3}, + {"\341\273\230", "\341\273\231", 3}, + {"\341\273\232", "\341\273\233", 3}, + {"\341\273\234", "\341\273\235", 3}, + {"\341\273\236", "\341\273\237", 3}, + {"\341\273\240", "\341\273\241", 3}, + {"\341\273\242", "\341\273\243", 3}, + {"\341\273\244", "\341\273\245", 3}, + {"\341\273\246", "\341\273\247", 3}, + {"\341\273\250", "\341\273\251", 3}, + {"\341\273\252", "\341\273\253", 3}, + {"\341\273\254", "\341\273\255", 3}, + {"\341\273\256", "\341\273\257", 3}, + {"\341\273\260", "\341\273\261", 3}, + {"\341\273\262", "\341\273\263", 3}, + {"\341\273\264", "\341\273\265", 3}, + {"\341\273\266", "\341\273\267", 3}, + {"\341\273\270", "\341\273\271", 3}, + {"\341\274\210", "\341\274\200", 3}, + {"\341\274\211", "\341\274\201", 3}, + {"\341\274\212", "\341\274\202", 3}, + {"\341\274\213", "\341\274\203", 3}, + {"\341\274\214", "\341\274\204", 3}, + {"\341\274\215", "\341\274\205", 3}, + {"\341\274\216", "\341\274\206", 3}, + {"\341\274\217", "\341\274\207", 3}, + {"\341\274\230", "\341\274\220", 3}, + {"\341\274\231", "\341\274\221", 3}, + {"\341\274\232", "\341\274\222", 3}, + {"\341\274\233", "\341\274\223", 3}, + {"\341\274\234", "\341\274\224", 3}, + {"\341\274\235", "\341\274\225", 3}, + {"\341\274\250", "\341\274\240", 3}, + {"\341\274\251", "\341\274\241", 3}, + {"\341\274\252", "\341\274\242", 3}, + {"\341\274\253", "\341\274\243", 3}, + {"\341\274\254", "\341\274\244", 3}, + {"\341\274\255", "\341\274\245", 3}, + {"\341\274\256", "\341\274\246", 3}, + {"\341\274\257", "\341\274\247", 3}, + {"\341\274\270", "\341\274\260", 3}, + {"\341\274\271", "\341\274\261", 3}, + {"\341\274\272", "\341\274\262", 3}, + {"\341\274\273", "\341\274\263", 3}, + {"\341\274\274", "\341\274\264", 3}, + {"\341\274\275", "\341\274\265", 3}, + {"\341\274\276", "\341\274\266", 3}, + {"\341\274\277", "\341\274\267", 3}, + {"\341\275\210", "\341\275\200", 3}, + {"\341\275\211", "\341\275\201", 3}, + {"\341\275\212", "\341\275\202", 3}, + {"\341\275\213", "\341\275\203", 3}, + {"\341\275\214", "\341\275\204", 3}, + {"\341\275\215", "\341\275\205", 3}, + {"\341\275\231", "\341\275\221", 3}, + {"\341\275\233", "\341\275\223", 3}, + {"\341\275\235", "\341\275\225", 3}, + {"\341\275\237", "\341\275\227", 3}, + {"\341\275\250", "\341\275\240", 3}, + {"\341\275\251", "\341\275\241", 3}, + {"\341\275\252", "\341\275\242", 3}, + {"\341\275\253", "\341\275\243", 3}, + {"\341\275\254", "\341\275\244", 3}, + {"\341\275\255", "\341\275\245", 3}, + {"\341\275\256", "\341\275\246", 3}, + {"\341\275\257", "\341\275\247", 3}, + {"\341\276\210", "\341\276\200", 3}, + {"\341\276\211", "\341\276\201", 3}, + {"\341\276\212", "\341\276\202", 3}, + {"\341\276\213", "\341\276\203", 3}, + {"\341\276\214", "\341\276\204", 3}, + {"\341\276\215", "\341\276\205", 3}, + {"\341\276\216", "\341\276\206", 3}, + {"\341\276\217", "\341\276\207", 3}, + {"\341\276\230", "\341\276\220", 3}, + {"\341\276\231", "\341\276\221", 3}, + {"\341\276\232", "\341\276\222", 3}, + {"\341\276\233", "\341\276\223", 3}, + {"\341\276\234", "\341\276\224", 3}, + {"\341\276\235", "\341\276\225", 3}, + {"\341\276\236", "\341\276\226", 3}, + {"\341\276\237", "\341\276\227", 3}, + {"\341\276\250", "\341\276\240", 3}, + {"\341\276\251", "\341\276\241", 3}, + {"\341\276\252", "\341\276\242", 3}, + {"\341\276\253", "\341\276\243", 3}, + {"\341\276\254", "\341\276\244", 3}, + {"\341\276\255", "\341\276\245", 3}, + {"\341\276\256", "\341\276\246", 3}, + {"\341\276\257", "\341\276\247", 3}, + {"\341\276\270", "\341\276\260", 3}, + {"\341\276\271", "\341\276\261", 3}, + {"\341\276\272", "\341\275\260", 3}, + {"\341\276\273", "\341\275\261", 3}, + {"\341\276\274", "\341\276\263", 3}, + {"\341\276\276", "\341\276\276", 3}, + {"\341\277\210", "\341\275\262", 3}, + {"\341\277\211", "\341\275\263", 3}, + {"\341\277\212", "\341\275\264", 3}, + {"\341\277\213", "\341\275\265", 3}, + {"\341\277\214", "\341\277\203", 3}, + {"\341\277\230", "\341\277\220", 3}, + {"\341\277\231", "\341\277\221", 3}, + {"\341\277\232", "\341\275\266", 3}, + {"\341\277\233", "\341\275\267", 3}, + {"\341\277\250", "\341\277\240", 3}, + {"\341\277\251", "\341\277\241", 3}, + {"\341\277\252", "\341\275\272", 3}, + {"\341\277\253", "\341\275\273", 3}, + {"\341\277\254", "\341\277\245", 3}, + {"\341\277\270", "\341\275\270", 3}, + {"\341\277\271", "\341\275\271", 3}, + {"\341\277\272", "\341\275\274", 3}, + {"\341\277\273", "\341\275\275", 3}, + {"\341\277\274", "\341\277\263", 3}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Upper2LowerTbl31[] = { + {"\357\274\241", "\357\275\201", 3}, + {"\357\274\242", "\357\275\202", 3}, + {"\357\274\243", "\357\275\203", 3}, + {"\357\274\244", "\357\275\204", 3}, + {"\357\274\245", "\357\275\205", 3}, + {"\357\274\246", "\357\275\206", 3}, + {"\357\274\247", "\357\275\207", 3}, + {"\357\274\250", "\357\275\210", 3}, + {"\357\274\251", "\357\275\211", 3}, + {"\357\274\252", "\357\275\212", 3}, + {"\357\274\253", "\357\275\213", 3}, + {"\357\274\254", "\357\275\214", 3}, + {"\357\274\255", "\357\275\215", 3}, + {"\357\274\256", "\357\275\216", 3}, + {"\357\274\257", "\357\275\217", 3}, + {"\357\274\260", "\357\275\220", 3}, + {"\357\274\261", "\357\275\221", 3}, + {"\357\274\262", "\357\275\222", 3}, + {"\357\274\263", "\357\275\223", 3}, + {"\357\274\264", "\357\275\224", 3}, + {"\357\274\265", "\357\275\225", 3}, + {"\357\274\266", "\357\275\226", 3}, + {"\357\274\267", "\357\275\227", 3}, + {"\357\274\270", "\357\275\230", 3}, + {"\357\274\271", "\357\275\231", 3}, + {"\357\274\272", "\357\275\232", 3}, + {NULL, NULL, 0} + /* upper, lower */ +}; + +UpperLowerTbl_t *Upper2LowerTbl2[] = { + Upper2LowerTbl20, /* \303 */ + Upper2LowerTbl21, /* \304 */ + Upper2LowerTbl22, /* \305 */ + Upper2LowerTbl23, /* \306 */ + Upper2LowerTbl24, /* \307 */ + Upper2LowerTbl25, /* \310 */ + NULL, /* \311 */ + NULL, /* \312 */ + NULL, /* \313 */ + NULL, /* \314 */ + NULL, /* \315 */ + Upper2LowerTbl26, /* \316 */ + Upper2LowerTbl27, /* \317 */ + Upper2LowerTbl28, /* \320 */ + Upper2LowerTbl29, /* \321 */ + Upper2LowerTbl2a, /* \322 */ + Upper2LowerTbl2b, /* \323 */ + Upper2LowerTbl2c, /* \324 */ + Upper2LowerTbl2d /* \325 */ +}; + +UpperLowerTbl_t *Upper2LowerTbl3[] = { + Upper2LowerTbl30, /* \341 */ + NULL, /* \342 */ + NULL, /* \343 */ + NULL, /* \344 */ + NULL, /* \345 */ + NULL, /* \346 */ + NULL, /* \347 */ + NULL, /* \350 */ + NULL, /* \351 */ + NULL, /* \352 */ + NULL, /* \353 */ + NULL, /* \354 */ + NULL, /* \355 */ + NULL, /* \356 */ + Upper2LowerTbl31 /* \357 */ +}; + +#define UL2S (unsigned char)'\303' +#define UL2E (unsigned char)'\325' +#define UL3S (unsigned char)'\341' +#define UL3E (unsigned char)'\357' + +/* + * dsgw_utf8StrToLower: translate upper-case string to lower-case + * + * input: a null terminated UTF-8 string + * output: a null terminated UTF-8 string which characters are + * converted to lower-case; characters which are not + * upper-case are copied as is. If it's not considered + * a UTF-8 string, NULL is returned. + * + * Notes: This function takes a string (made of multiple UTF-8 characters) + * for the input (not one character as in "tolower"). + * Output string is allocated in this function, which needs to be + * released when it's not needed any more. + */ +unsigned char * +dsgw_utf8StrToLower(unsigned char *s) +{ + UpperLowerTbl_t *ultp; + unsigned char *p, *np, *tail; + unsigned char *lp, *lphead; + int len, sz; + + if (s == NULL || *s == '\0') { + return s; + } + len = strlen((char *)s); + tail = s + len; + lphead = lp = (unsigned char *)dsgw_ch_malloc(len + 1); + p = s; + while ((np = (unsigned char *)ldap_utf8next((char *)p)) <= tail) { + switch(sz = np - p) { + case 1: + sprintf((char *)lp, "%c", tolower(*p)); + break; + case 2: + if (*p < UL2S || *p > UL2E) { /* out of range */ + memcpy(lp, p, sz); + break; + } + for (ultp = Upper2LowerTbl2[*p - UL2S]; + ultp && ultp->upper && memcmp(p, ultp->upper, sz); + ultp++) + ; + if (!ultp) { /* out of range */ + memcpy(lp, p, sz); + } if (ultp->upper) { /* matched */ + memcpy(lp, ultp->lower, ultp->tsz); + sz = ultp->tsz; + } else { + memcpy(lp, p, sz); + } + break; + case 3: + if (*p != UL3S && *p != UL3E) { /* out of range */ + memcpy(lp, p, sz); + break; + } + for (ultp = Upper2LowerTbl3[*p - UL3S]; + ultp && ultp->upper && memcmp(p, ultp->upper, sz); + ultp++) + ; + if (!ultp) { /* out of range */ + memcpy(lp, p, sz); + } if (ultp->upper) { /* matched */ + memcpy(lp, ultp->lower, sz); + } else { + memcpy(lp, p, sz); + } + break; + case 4: + memcpy(lp, p, sz); + break; + default: /* not UTF-8 */ + free(lphead); + return NULL; + } + lp += sz; + p = np; + if (p == tail) { + break; + } + } + *lp = '\0'; + return lphead; +} + +/* + * dsgw_utf8ToLower: translate upper-case character to lower-case + * + * input: a UTF-8 character (s) + * output: a UTF-8 character which is converted to lower-case (d) + * length (in bytes) of input character (ssz) and + * output character (dsz) + * + * Notes: This function takes a UTF-8 character (could be multiple bytes) + * for the input. Memory for the output character is NOT allocated + * in this function, caller should have allocated it (d). + * "memmove" is used since (s) and (d) are overlapped. + */ +void +dsgw_utf8ToLower(unsigned char *s, unsigned char *d, int *ssz, int *dsz) +{ + UpperLowerTbl_t *ultp; + unsigned char *tail; + + if (s == NULL || *s == '\0') { + *ssz = *dsz = 0; + return; + } + if (!(*s & 0x80)) { /* ASCII */ + *dsz = *ssz = 1; + *d = tolower(*s); + return; + } + tail = (unsigned char *)ldap_utf8next((char *)s); + *dsz = *ssz = tail - s; + switch(*ssz) { + case 1: /* ASCII */ + *d = tolower(*s); + break; + case 2: /* 2 bytes */ + if (*s < UL2S || *s > UL2E) { /* out of range */ + memmove(d, s, *ssz); + break; + } + for (ultp = Upper2LowerTbl2[*s - UL2S]; + ultp && ultp->upper && memcmp(s, ultp->upper, *ssz); + ultp++) + ; + if (!ultp) { /* out of range */ + memmove(d, s, *ssz); + } else if (ultp->upper) { /* matched */ + memmove(d, ultp->lower, ultp->tsz); + *dsz = ultp->tsz; + } else { + memmove(d, s, *ssz); + } + break; + case 3: /* 3 bytes */ + if (*s != UL3S && *s != UL3E) { /* out of range */ + memmove(d, s, *ssz); + break; + } + for (ultp = Upper2LowerTbl3[*s - UL3S]; + ultp && ultp->upper && memcmp(s, ultp->upper, *ssz); + ultp++) + ; + if (!ultp) { /* out of range */ + memmove(d, s, *ssz); + } else if (ultp->upper) { /* matched */ + memmove(d, ultp->lower, *ssz); + } else { + memmove(d, s, *ssz); + } + break; + } + return; +} + +/* + * dsgw_utf8isUpper: tests for a character that is a upper-case letter in + * UTF-8 + * + * input: a UTF-8 character (could be multi-byte) + * output: 1 if the character is a upper-case letter + * 0 if the character is not a upper-case letter + */ +int +dsgw_utf8isUpper(unsigned char *s) +{ + UpperLowerTbl_t *ultp; + unsigned char *next; + int sz; + + if (s == NULL || *s == '\0') { + return 0; + } + if (!(*s & 0x80)) { /* ASCII */ + return isupper(*s); + } + next = (unsigned char *)ldap_utf8next((char *)s); + switch(sz = next - s) { + case 1: /* ASCII */ + return isupper(*s); + case 2: + if (*s < UL2S || *s > UL2E) { /* out of range */ + return 0; + } + for (ultp = Upper2LowerTbl2[*s - UL2S]; + ultp && ultp->upper && memcmp(s, ultp->upper, sz); + ultp++) + ; + if (!ultp) { /* out of range */ + return 0; + } if (ultp->upper) { /* matched */ + return 1; + } else { + return 0; + } + case 3: + if (*s < UL3S || *s > UL3E) { /* out of range */ + return 0; + } + for (ultp = Upper2LowerTbl3[*s - UL3S]; + ultp && ultp->upper && memcmp(s, ultp->upper, sz); + ultp++) + ; + if (!ultp) { /* out of range */ + return 0; + } if (ultp->upper) { /* matched */ + return 1; + } else { + return 0; + } + default: + return 0; + } +} + +/* + * Lower2Upper Tables: sorted by lower characters + */ +UpperLowerTbl_t Lower2UpperTbl20[] = { + /* upper, lower */ + {"\303\200", "\303\240", 2}, + {"\303\201", "\303\241", 2}, + {"\303\202", "\303\242", 2}, + {"\303\203", "\303\243", 2}, + {"\303\204", "\303\244", 2}, + {"\303\205", "\303\245", 2}, + {"\303\206", "\303\246", 2}, + {"\303\207", "\303\247", 2}, + {"\303\210", "\303\250", 2}, + {"\303\211", "\303\251", 2}, + {"\303\212", "\303\252", 2}, + {"\303\213", "\303\253", 2}, + {"\303\214", "\303\254", 2}, + {"\303\215", "\303\255", 2}, + {"\303\216", "\303\256", 2}, + {"\303\217", "\303\257", 2}, + {"\303\220", "\303\260", 2}, + {"\303\221", "\303\261", 2}, + {"\303\222", "\303\262", 2}, + {"\303\223", "\303\263", 2}, + {"\303\224", "\303\264", 2}, + {"\303\225", "\303\265", 2}, + {"\303\226", "\303\266", 2}, + {"\303\230", "\303\270", 2}, + {"\303\231", "\303\271", 2}, + {"\303\232", "\303\272", 2}, + {"\303\233", "\303\273", 2}, + {"\303\234", "\303\274", 2}, + {"\303\235", "\303\275", 2}, + {"\303\236", "\303\276", 2}, + {"\305\270", "\303\277", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl21[] = { + {"\304\200", "\304\201", 2}, + {"\304\202", "\304\203", 2}, + {"\304\204", "\304\205", 2}, + {"\304\206", "\304\207", 2}, + {"\304\210", "\304\211", 2}, + {"\304\212", "\304\213", 2}, + {"\304\214", "\304\215", 2}, + {"\304\216", "\304\217", 2}, + {"\304\220", "\304\221", 2}, + {"\304\222", "\304\223", 2}, + {"\304\224", "\304\225", 2}, + {"\304\226", "\304\227", 2}, + {"\304\230", "\304\231", 2}, + {"\304\232", "\304\233", 2}, + {"\304\234", "\304\235", 2}, + {"\304\236", "\304\237", 2}, + {"\304\240", "\304\241", 2}, + {"\304\242", "\304\243", 2}, + {"\304\244", "\304\245", 2}, + {"\304\246", "\304\247", 2}, + {"\304\250", "\304\251", 2}, + {"\304\252", "\304\253", 2}, + {"\304\254", "\304\255", 2}, + {"\304\256", "\304\257", 2}, + {"\111", "\304\261", 1}, + {"\304\262", "\304\263", 2}, + {"\304\264", "\304\265", 2}, + {"\304\266", "\304\267", 2}, + {"\304\271", "\304\272", 2}, + {"\304\273", "\304\274", 2}, + {"\304\275", "\304\276", 2}, + {NULL, NULL} +}; + +UpperLowerTbl_t Lower2UpperTbl22[] = { + {"\304\277", "\305\200", 2}, + {"\305\201", "\305\202", 2}, + {"\305\203", "\305\204", 2}, + {"\305\205", "\305\206", 2}, + {"\305\207", "\305\210", 2}, + {"\305\212", "\305\213", 2}, + {"\305\214", "\305\215", 2}, + {"\305\216", "\305\217", 2}, + {"\305\220", "\305\221", 2}, + {"\305\222", "\305\223", 2}, + {"\305\224", "\305\225", 2}, + {"\305\226", "\305\227", 2}, + {"\305\230", "\305\231", 2}, + {"\305\232", "\305\233", 2}, + {"\305\234", "\305\235", 2}, + {"\305\236", "\305\237", 2}, + {"\305\240", "\305\241", 2}, + {"\305\242", "\305\243", 2}, + {"\305\244", "\305\245", 2}, + {"\305\246", "\305\247", 2}, + {"\305\250", "\305\251", 2}, + {"\305\252", "\305\253", 2}, + {"\305\254", "\305\255", 2}, + {"\305\256", "\305\257", 2}, + {"\305\260", "\305\261", 2}, + {"\305\262", "\305\263", 2}, + {"\305\264", "\305\265", 2}, + {"\305\266", "\305\267", 2}, + {"\305\271", "\305\272", 2}, + {"\305\273", "\305\274", 2}, + {"\305\275", "\305\276", 2}, + {"\123", "\305\277", 1}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl23[] = { + {"\306\202", "\306\203", 2}, + {"\306\204", "\306\205", 2}, + {"\306\207", "\306\210", 2}, + {"\306\213", "\306\214", 2}, + {"\306\221", "\306\222", 2}, + {"\306\230", "\306\231", 2}, + {"\306\240", "\306\241", 2}, + {"\306\242", "\306\243", 2}, + {"\306\244", "\306\245", 2}, + {"\306\247", "\306\250", 2}, + {"\306\254", "\306\255", 2}, + {"\306\257", "\306\260", 2}, + {"\306\263", "\306\264", 2}, + {"\306\265", "\306\266", 2}, + {"\306\270", "\306\271", 2}, + {"\306\274", "\306\275", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl24[] = { + {"\307\204", "\307\206", 2}, + {"\307\207", "\307\211", 2}, + {"\307\212", "\307\214", 2}, + {"\307\215", "\307\216", 2}, + {"\307\217", "\307\220", 2}, + {"\307\221", "\307\222", 2}, + {"\307\223", "\307\224", 2}, + {"\307\225", "\307\226", 2}, + {"\307\227", "\307\230", 2}, + {"\307\231", "\307\232", 2}, + {"\307\233", "\307\234", 2}, + {"\307\236", "\307\237", 2}, + {"\307\240", "\307\241", 2}, + {"\307\242", "\307\243", 2}, + {"\307\244", "\307\245", 2}, + {"\307\246", "\307\247", 2}, + {"\307\250", "\307\251", 2}, + {"\307\252", "\307\253", 2}, + {"\307\254", "\307\255", 2}, + {"\307\256", "\307\257", 2}, + {"\307\261", "\307\263", 2}, + {"\307\264", "\307\265", 2}, + {"\307\272", "\307\273", 2}, + {"\307\274", "\307\275", 2}, + {"\307\276", "\307\277", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl25[] = { + {"\310\200", "\310\201", 2}, + {"\310\202", "\310\203", 2}, + {"\310\204", "\310\205", 2}, + {"\310\206", "\310\207", 2}, + {"\310\210", "\310\211", 2}, + {"\310\212", "\310\213", 2}, + {"\310\214", "\310\215", 2}, + {"\310\216", "\310\217", 2}, + {"\310\220", "\310\221", 2}, + {"\310\222", "\310\223", 2}, + {"\310\224", "\310\225", 2}, + {"\310\226", "\310\227", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl26[] = { + {"\306\201", "\311\223", 2}, + {"\306\206", "\311\224", 2}, + {"\306\211", "\311\226", 2}, + {"\306\212", "\311\227", 2}, + {"\306\216", "\311\230", 2}, + {"\306\217", "\311\231", 2}, + {"\306\220", "\311\233", 2}, + {"\306\223", "\311\240", 2}, + {"\306\224", "\311\243", 2}, + {"\306\227", "\311\250", 2}, + {"\306\226", "\311\251", 2}, + {"\306\234", "\311\257", 2}, + {"\306\235", "\311\262", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl27[] = { + {"\306\251", "\312\203", 2}, + {"\306\256", "\312\210", 2}, + {"\306\261", "\312\212", 2}, + {"\306\262", "\312\213", 2}, + {"\306\267", "\312\222", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl28[] = { + {"\316\206", "\316\254", 2}, + {"\316\210", "\316\255", 2}, + {"\316\211", "\316\256", 2}, + {"\316\212", "\316\257", 2}, + {"\316\221", "\316\261", 2}, + {"\316\222", "\316\262", 2}, + {"\316\223", "\316\263", 2}, + {"\316\224", "\316\264", 2}, + {"\316\225", "\316\265", 2}, + {"\316\226", "\316\266", 2}, + {"\316\227", "\316\267", 2}, + {"\316\230", "\316\270", 2}, + {"\316\231", "\316\271", 2}, + {"\316\232", "\316\272", 2}, + {"\316\233", "\316\273", 2}, + {"\316\234", "\316\274", 2}, + {"\316\235", "\316\275", 2}, + {"\316\236", "\316\276", 2}, + {"\316\237", "\316\277", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl29[] = { + {"\316\240", "\317\200", 2}, + {"\316\241", "\317\201", 2}, + {"\316\243", "\317\202", 2}, + {"\316\243", "\317\203", 2}, + {"\316\244", "\317\204", 2}, + {"\316\245", "\317\205", 2}, + {"\316\246", "\317\206", 2}, + {"\316\247", "\317\207", 2}, + {"\316\250", "\317\210", 2}, + {"\316\251", "\317\211", 2}, + {"\316\252", "\317\212", 2}, + {"\316\253", "\317\213", 2}, + {"\316\214", "\317\214", 2}, + {"\316\216", "\317\215", 2}, + {"\316\217", "\317\216", 2}, + {"\316\222", "\317\220", 2}, + {"\316\230", "\317\221", 2}, + {"\316\246", "\317\225", 2}, + {"\316\240", "\317\226", 2}, + {"\317\242", "\317\243", 2}, + {"\317\244", "\317\245", 2}, + {"\317\246", "\317\247", 2}, + {"\317\250", "\317\251", 2}, + {"\317\252", "\317\253", 2}, + {"\317\254", "\317\255", 2}, + {"\317\256", "\317\257", 2}, + {"\316\232", "\317\260", 2}, + {"\316\241", "\317\261", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl2a[] = { + {"\320\220", "\320\260", 2}, + {"\320\221", "\320\261", 2}, + {"\320\222", "\320\262", 2}, + {"\320\223", "\320\263", 2}, + {"\320\224", "\320\264", 2}, + {"\320\225", "\320\265", 2}, + {"\320\226", "\320\266", 2}, + {"\320\227", "\320\267", 2}, + {"\320\230", "\320\270", 2}, + {"\320\231", "\320\271", 2}, + {"\320\232", "\320\272", 2}, + {"\320\233", "\320\273", 2}, + {"\320\234", "\320\274", 2}, + {"\320\235", "\320\275", 2}, + {"\320\236", "\320\276", 2}, + {"\320\237", "\320\277", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl2b[] = { + {"\320\240", "\321\200", 2}, + {"\320\241", "\321\201", 2}, + {"\320\242", "\321\202", 2}, + {"\320\243", "\321\203", 2}, + {"\320\244", "\321\204", 2}, + {"\320\245", "\321\205", 2}, + {"\320\246", "\321\206", 2}, + {"\320\247", "\321\207", 2}, + {"\320\250", "\321\210", 2}, + {"\320\251", "\321\211", 2}, + {"\320\252", "\321\212", 2}, + {"\320\253", "\321\213", 2}, + {"\320\254", "\321\214", 2}, + {"\320\255", "\321\215", 2}, + {"\320\256", "\321\216", 2}, + {"\320\257", "\321\217", 2}, + {"\320\201", "\321\221", 2}, + {"\320\202", "\321\222", 2}, + {"\320\203", "\321\223", 2}, + {"\320\204", "\321\224", 2}, + {"\320\205", "\321\225", 2}, + {"\320\206", "\321\226", 2}, + {"\320\207", "\321\227", 2}, + {"\320\210", "\321\230", 2}, + {"\320\211", "\321\231", 2}, + {"\320\212", "\321\232", 2}, + {"\320\213", "\321\233", 2}, + {"\320\214", "\321\234", 2}, + {"\320\216", "\321\236", 2}, + {"\320\217", "\321\237", 2}, + {"\321\240", "\321\241", 2}, + {"\321\242", "\321\243", 2}, + {"\321\244", "\321\245", 2}, + {"\321\246", "\321\247", 2}, + {"\321\250", "\321\251", 2}, + {"\321\252", "\321\253", 2}, + {"\321\254", "\321\255", 2}, + {"\321\256", "\321\257", 2}, + {"\321\260", "\321\261", 2}, + {"\321\262", "\321\263", 2}, + {"\321\264", "\321\265", 2}, + {"\321\266", "\321\267", 2}, + {"\321\270", "\321\271", 2}, + {"\321\272", "\321\273", 2}, + {"\321\274", "\321\275", 2}, + {"\321\276", "\321\277", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl2c[] = { + {"\322\200", "\322\201", 2}, + {"\322\220", "\322\221", 2}, + {"\322\222", "\322\223", 2}, + {"\322\224", "\322\225", 2}, + {"\322\226", "\322\227", 2}, + {"\322\230", "\322\231", 2}, + {"\322\232", "\322\233", 2}, + {"\322\234", "\322\235", 2}, + {"\322\236", "\322\237", 2}, + {"\322\240", "\322\241", 2}, + {"\322\242", "\322\243", 2}, + {"\322\244", "\322\245", 2}, + {"\322\246", "\322\247", 2}, + {"\322\250", "\322\251", 2}, + {"\322\252", "\322\253", 2}, + {"\322\254", "\322\255", 2}, + {"\322\256", "\322\257", 2}, + {"\322\260", "\322\261", 2}, + {"\322\262", "\322\263", 2}, + {"\322\264", "\322\265", 2}, + {"\322\266", "\322\267", 2}, + {"\322\270", "\322\271", 2}, + {"\322\272", "\322\273", 2}, + {"\322\274", "\322\275", 2}, + {"\322\276", "\322\277", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl2d[] = { + {"\323\201", "\323\202", 2}, + {"\323\203", "\323\204", 2}, + {"\323\207", "\323\210", 2}, + {"\323\213", "\323\214", 2}, + {"\323\220", "\323\221", 2}, + {"\323\222", "\323\223", 2}, + {"\323\224", "\323\225", 2}, + {"\323\226", "\323\227", 2}, + {"\323\230", "\323\231", 2}, + {"\323\232", "\323\233", 2}, + {"\323\234", "\323\235", 2}, + {"\323\236", "\323\237", 2}, + {"\323\240", "\323\241", 2}, + {"\323\242", "\323\243", 2}, + {"\323\244", "\323\245", 2}, + {"\323\246", "\323\247", 2}, + {"\323\250", "\323\251", 2}, + {"\323\252", "\323\253", 2}, + {"\323\256", "\323\257", 2}, + {"\323\260", "\323\261", 2}, + {"\323\262", "\323\263", 2}, + {"\323\264", "\323\265", 2}, + {"\323\270", "\323\271", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl2e[] = { + {"\324\261", "\325\241", 2}, + {"\324\262", "\325\242", 2}, + {"\324\263", "\325\243", 2}, + {"\324\264", "\325\244", 2}, + {"\324\265", "\325\245", 2}, + {"\324\266", "\325\246", 2}, + {"\324\267", "\325\247", 2}, + {"\324\270", "\325\250", 2}, + {"\324\271", "\325\251", 2}, + {"\324\272", "\325\252", 2}, + {"\324\273", "\325\253", 2}, + {"\324\274", "\325\254", 2}, + {"\324\275", "\325\255", 2}, + {"\324\276", "\325\256", 2}, + {"\324\277", "\325\257", 2}, + {"\325\200", "\325\260", 2}, + {"\325\201", "\325\261", 2}, + {"\325\202", "\325\262", 2}, + {"\325\203", "\325\263", 2}, + {"\325\204", "\325\264", 2}, + {"\325\205", "\325\265", 2}, + {"\325\206", "\325\266", 2}, + {"\325\207", "\325\267", 2}, + {"\325\210", "\325\270", 2}, + {"\325\211", "\325\271", 2}, + {"\325\212", "\325\272", 2}, + {"\325\213", "\325\273", 2}, + {"\325\214", "\325\274", 2}, + {"\325\215", "\325\275", 2}, + {"\325\216", "\325\276", 2}, + {"\325\217", "\325\277", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl2f[] = { + {"\325\220", "\326\200", 2}, + {"\325\221", "\326\201", 2}, + {"\325\222", "\326\202", 2}, + {"\325\223", "\326\203", 2}, + {"\325\224", "\326\204", 2}, + {"\325\225", "\326\205", 2}, + {"\325\226", "\326\206", 2}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl30[] = { + {"\341\202\240", "\341\203\220", 3}, + {"\341\202\241", "\341\203\221", 3}, + {"\341\202\242", "\341\203\222", 3}, + {"\341\202\243", "\341\203\223", 3}, + {"\341\202\244", "\341\203\224", 3}, + {"\341\202\245", "\341\203\225", 3}, + {"\341\202\246", "\341\203\226", 3}, + {"\341\202\247", "\341\203\227", 3}, + {"\341\202\250", "\341\203\230", 3}, + {"\341\202\251", "\341\203\231", 3}, + {"\341\202\252", "\341\203\232", 3}, + {"\341\202\253", "\341\203\233", 3}, + {"\341\202\254", "\341\203\234", 3}, + {"\341\202\255", "\341\203\235", 3}, + {"\341\202\256", "\341\203\236", 3}, + {"\341\202\257", "\341\203\237", 3}, + {"\341\202\260", "\341\203\240", 3}, + {"\341\202\261", "\341\203\241", 3}, + {"\341\202\262", "\341\203\242", 3}, + {"\341\202\263", "\341\203\243", 3}, + {"\341\202\264", "\341\203\244", 3}, + {"\341\202\265", "\341\203\245", 3}, + {"\341\202\266", "\341\203\246", 3}, + {"\341\202\267", "\341\203\247", 3}, + {"\341\202\270", "\341\203\250", 3}, + {"\341\202\271", "\341\203\251", 3}, + {"\341\202\272", "\341\203\252", 3}, + {"\341\202\273", "\341\203\253", 3}, + {"\341\202\274", "\341\203\254", 3}, + {"\341\202\275", "\341\203\255", 3}, + {"\341\202\276", "\341\203\256", 3}, + {"\341\202\277", "\341\203\257", 3}, + {"\341\203\200", "\341\203\260", 3}, + {"\341\203\201", "\341\203\261", 3}, + {"\341\203\202", "\341\203\262", 3}, + {"\341\203\203", "\341\203\263", 3}, + {"\341\203\204", "\341\203\264", 3}, + {"\341\203\205", "\341\203\265", 3}, + {"\341\270\200", "\341\270\201", 3}, + {"\341\270\202", "\341\270\203", 3}, + {"\341\270\204", "\341\270\205", 3}, + {"\341\270\206", "\341\270\207", 3}, + {"\341\270\210", "\341\270\211", 3}, + {"\341\270\212", "\341\270\213", 3}, + {"\341\270\214", "\341\270\215", 3}, + {"\341\270\216", "\341\270\217", 3}, + {"\341\270\220", "\341\270\221", 3}, + {"\341\270\222", "\341\270\223", 3}, + {"\341\270\224", "\341\270\225", 3}, + {"\341\270\226", "\341\270\227", 3}, + {"\341\270\230", "\341\270\231", 3}, + {"\341\270\232", "\341\270\233", 3}, + {"\341\270\234", "\341\270\235", 3}, + {"\341\270\236", "\341\270\237", 3}, + {"\341\270\240", "\341\270\241", 3}, + {"\341\270\242", "\341\270\243", 3}, + {"\341\270\244", "\341\270\245", 3}, + {"\341\270\246", "\341\270\247", 3}, + {"\341\270\250", "\341\270\251", 3}, + {"\341\270\252", "\341\270\253", 3}, + {"\341\270\254", "\341\270\255", 3}, + {"\341\270\256", "\341\270\257", 3}, + {"\341\270\260", "\341\270\261", 3}, + {"\341\270\262", "\341\270\263", 3}, + {"\341\270\264", "\341\270\265", 3}, + {"\341\270\266", "\341\270\267", 3}, + {"\341\270\270", "\341\270\271", 3}, + {"\341\270\272", "\341\270\273", 3}, + {"\341\270\274", "\341\270\275", 3}, + {"\341\270\276", "\341\270\277", 3}, + {"\341\271\200", "\341\271\201", 3}, + {"\341\271\202", "\341\271\203", 3}, + {"\341\271\204", "\341\271\205", 3}, + {"\341\271\206", "\341\271\207", 3}, + {"\341\271\210", "\341\271\211", 3}, + {"\341\271\212", "\341\271\213", 3}, + {"\341\271\214", "\341\271\215", 3}, + {"\341\271\216", "\341\271\217", 3}, + {"\341\271\220", "\341\271\221", 3}, + {"\341\271\222", "\341\271\223", 3}, + {"\341\271\224", "\341\271\225", 3}, + {"\341\271\226", "\341\271\227", 3}, + {"\341\271\230", "\341\271\231", 3}, + {"\341\271\232", "\341\271\233", 3}, + {"\341\271\234", "\341\271\235", 3}, + {"\341\271\236", "\341\271\237", 3}, + {"\341\271\240", "\341\271\241", 3}, + {"\341\271\242", "\341\271\243", 3}, + {"\341\271\244", "\341\271\245", 3}, + {"\341\271\246", "\341\271\247", 3}, + {"\341\271\250", "\341\271\251", 3}, + {"\341\271\252", "\341\271\253", 3}, + {"\341\271\254", "\341\271\255", 3}, + {"\341\271\256", "\341\271\257", 3}, + {"\341\271\260", "\341\271\261", 3}, + {"\341\271\262", "\341\271\263", 3}, + {"\341\271\264", "\341\271\265", 3}, + {"\341\271\266", "\341\271\267", 3}, + {"\341\271\270", "\341\271\271", 3}, + {"\341\271\272", "\341\271\273", 3}, + {"\341\271\274", "\341\271\275", 3}, + {"\341\271\276", "\341\271\277", 3}, + {"\341\272\200", "\341\272\201", 3}, + {"\341\272\202", "\341\272\203", 3}, + {"\341\272\204", "\341\272\205", 3}, + {"\341\272\206", "\341\272\207", 3}, + {"\341\272\210", "\341\272\211", 3}, + {"\341\272\212", "\341\272\213", 3}, + {"\341\272\214", "\341\272\215", 3}, + {"\341\272\216", "\341\272\217", 3}, + {"\341\272\220", "\341\272\221", 3}, + {"\341\272\222", "\341\272\223", 3}, + {"\341\272\224", "\341\272\225", 3}, + {"\341\272\240", "\341\272\241", 3}, + {"\341\272\242", "\341\272\243", 3}, + {"\341\272\244", "\341\272\245", 3}, + {"\341\272\246", "\341\272\247", 3}, + {"\341\272\250", "\341\272\251", 3}, + {"\341\272\252", "\341\272\253", 3}, + {"\341\272\254", "\341\272\255", 3}, + {"\341\272\256", "\341\272\257", 3}, + {"\341\272\260", "\341\272\261", 3}, + {"\341\272\262", "\341\272\263", 3}, + {"\341\272\264", "\341\272\265", 3}, + {"\341\272\266", "\341\272\267", 3}, + {"\341\272\270", "\341\272\271", 3}, + {"\341\272\272", "\341\272\273", 3}, + {"\341\272\274", "\341\272\275", 3}, + {"\341\272\276", "\341\272\277", 3}, + {"\341\273\200", "\341\273\201", 3}, + {"\341\273\202", "\341\273\203", 3}, + {"\341\273\204", "\341\273\205", 3}, + {"\341\273\206", "\341\273\207", 3}, + {"\341\273\210", "\341\273\211", 3}, + {"\341\273\212", "\341\273\213", 3}, + {"\341\273\214", "\341\273\215", 3}, + {"\341\273\216", "\341\273\217", 3}, + {"\341\273\220", "\341\273\221", 3}, + {"\341\273\222", "\341\273\223", 3}, + {"\341\273\224", "\341\273\225", 3}, + {"\341\273\226", "\341\273\227", 3}, + {"\341\273\230", "\341\273\231", 3}, + {"\341\273\232", "\341\273\233", 3}, + {"\341\273\234", "\341\273\235", 3}, + {"\341\273\236", "\341\273\237", 3}, + {"\341\273\240", "\341\273\241", 3}, + {"\341\273\242", "\341\273\243", 3}, + {"\341\273\244", "\341\273\245", 3}, + {"\341\273\246", "\341\273\247", 3}, + {"\341\273\250", "\341\273\251", 3}, + {"\341\273\252", "\341\273\253", 3}, + {"\341\273\254", "\341\273\255", 3}, + {"\341\273\256", "\341\273\257", 3}, + {"\341\273\260", "\341\273\261", 3}, + {"\341\273\262", "\341\273\263", 3}, + {"\341\273\264", "\341\273\265", 3}, + {"\341\273\266", "\341\273\267", 3}, + {"\341\273\270", "\341\273\271", 3}, + {"\341\274\210", "\341\274\200", 3}, + {"\341\274\211", "\341\274\201", 3}, + {"\341\274\212", "\341\274\202", 3}, + {"\341\274\213", "\341\274\203", 3}, + {"\341\274\214", "\341\274\204", 3}, + {"\341\274\215", "\341\274\205", 3}, + {"\341\274\216", "\341\274\206", 3}, + {"\341\274\217", "\341\274\207", 3}, + {"\341\274\230", "\341\274\220", 3}, + {"\341\274\231", "\341\274\221", 3}, + {"\341\274\232", "\341\274\222", 3}, + {"\341\274\233", "\341\274\223", 3}, + {"\341\274\234", "\341\274\224", 3}, + {"\341\274\235", "\341\274\225", 3}, + {"\341\274\250", "\341\274\240", 3}, + {"\341\274\251", "\341\274\241", 3}, + {"\341\274\252", "\341\274\242", 3}, + {"\341\274\253", "\341\274\243", 3}, + {"\341\274\254", "\341\274\244", 3}, + {"\341\274\255", "\341\274\245", 3}, + {"\341\274\256", "\341\274\246", 3}, + {"\341\274\257", "\341\274\247", 3}, + {"\341\274\270", "\341\274\260", 3}, + {"\341\274\271", "\341\274\261", 3}, + {"\341\274\272", "\341\274\262", 3}, + {"\341\274\273", "\341\274\263", 3}, + {"\341\274\274", "\341\274\264", 3}, + {"\341\274\275", "\341\274\265", 3}, + {"\341\274\276", "\341\274\266", 3}, + {"\341\274\277", "\341\274\267", 3}, + {"\341\275\210", "\341\275\200", 3}, + {"\341\275\211", "\341\275\201", 3}, + {"\341\275\212", "\341\275\202", 3}, + {"\341\275\213", "\341\275\203", 3}, + {"\341\275\214", "\341\275\204", 3}, + {"\341\275\215", "\341\275\205", 3}, + {"\341\275\231", "\341\275\221", 3}, + {"\341\275\233", "\341\275\223", 3}, + {"\341\275\235", "\341\275\225", 3}, + {"\341\275\237", "\341\275\227", 3}, + {"\341\275\250", "\341\275\240", 3}, + {"\341\275\251", "\341\275\241", 3}, + {"\341\275\252", "\341\275\242", 3}, + {"\341\275\253", "\341\275\243", 3}, + {"\341\275\254", "\341\275\244", 3}, + {"\341\275\255", "\341\275\245", 3}, + {"\341\275\256", "\341\275\246", 3}, + {"\341\275\257", "\341\275\247", 3}, + {"\341\276\272", "\341\275\260", 3}, + {"\341\276\273", "\341\275\261", 3}, + {"\341\277\210", "\341\275\262", 3}, + {"\341\277\211", "\341\275\263", 3}, + {"\341\277\212", "\341\275\264", 3}, + {"\341\277\213", "\341\275\265", 3}, + {"\341\277\232", "\341\275\266", 3}, + {"\341\277\233", "\341\275\267", 3}, + {"\341\277\270", "\341\275\270", 3}, + {"\341\277\271", "\341\275\271", 3}, + {"\341\277\252", "\341\275\272", 3}, + {"\341\277\253", "\341\275\273", 3}, + {"\341\277\272", "\341\275\274", 3}, + {"\341\277\273", "\341\275\275", 3}, + {"\341\276\210", "\341\276\200", 3}, + {"\341\276\211", "\341\276\201", 3}, + {"\341\276\212", "\341\276\202", 3}, + {"\341\276\213", "\341\276\203", 3}, + {"\341\276\214", "\341\276\204", 3}, + {"\341\276\215", "\341\276\205", 3}, + {"\341\276\216", "\341\276\206", 3}, + {"\341\276\217", "\341\276\207", 3}, + {"\341\276\230", "\341\276\220", 3}, + {"\341\276\231", "\341\276\221", 3}, + {"\341\276\232", "\341\276\222", 3}, + {"\341\276\233", "\341\276\223", 3}, + {"\341\276\234", "\341\276\224", 3}, + {"\341\276\235", "\341\276\225", 3}, + {"\341\276\236", "\341\276\226", 3}, + {"\341\276\237", "\341\276\227", 3}, + {"\341\276\250", "\341\276\240", 3}, + {"\341\276\251", "\341\276\241", 3}, + {"\341\276\252", "\341\276\242", 3}, + {"\341\276\253", "\341\276\243", 3}, + {"\341\276\254", "\341\276\244", 3}, + {"\341\276\255", "\341\276\245", 3}, + {"\341\276\256", "\341\276\246", 3}, + {"\341\276\257", "\341\276\247", 3}, + {"\341\276\270", "\341\276\260", 3}, + {"\341\276\271", "\341\276\261", 3}, + {"\341\276\274", "\341\276\263", 3}, + {"\341\277\214", "\341\277\203", 3}, + {"\341\277\230", "\341\277\220", 3}, + {"\341\277\231", "\341\277\221", 3}, + {"\341\277\250", "\341\277\240", 3}, + {"\341\277\251", "\341\277\241", 3}, + {"\341\277\254", "\341\277\245", 3}, + {"\341\277\274", "\341\277\263", 3}, + {NULL, NULL, 0} +}; + +UpperLowerTbl_t Lower2UpperTbl31[] = { + {"\357\274\241", "\357\275\201", 3}, + {"\357\274\242", "\357\275\202", 3}, + {"\357\274\243", "\357\275\203", 3}, + {"\357\274\244", "\357\275\204", 3}, + {"\357\274\245", "\357\275\205", 3}, + {"\357\274\246", "\357\275\206", 3}, + {"\357\274\247", "\357\275\207", 3}, + {"\357\274\250", "\357\275\210", 3}, + {"\357\274\251", "\357\275\211", 3}, + {"\357\274\252", "\357\275\212", 3}, + {"\357\274\253", "\357\275\213", 3}, + {"\357\274\254", "\357\275\214", 3}, + {"\357\274\255", "\357\275\215", 3}, + {"\357\274\256", "\357\275\216", 3}, + {"\357\274\257", "\357\275\217", 3}, + {"\357\274\260", "\357\275\220", 3}, + {"\357\274\261", "\357\275\221", 3}, + {"\357\274\262", "\357\275\222", 3}, + {"\357\274\263", "\357\275\223", 3}, + {"\357\274\264", "\357\275\224", 3}, + {"\357\274\265", "\357\275\225", 3}, + {"\357\274\266", "\357\275\226", 3}, + {"\357\274\267", "\357\275\227", 3}, + {"\357\274\270", "\357\275\230", 3}, + {"\357\274\271", "\357\275\231", 3}, + {"\357\274\272", "\357\275\232", 3}, + {NULL, NULL, 0} + /* upper, lower */ +}; + +UpperLowerTbl_t *Lower2UpperTbl2[] = { + Lower2UpperTbl20, /* \303 */ + Lower2UpperTbl21, /* \304 */ + Lower2UpperTbl22, /* \305 */ + Lower2UpperTbl23, /* \306 */ + Lower2UpperTbl24, /* \307 */ + Lower2UpperTbl25, /* \310 */ + Lower2UpperTbl26, /* \311 */ + Lower2UpperTbl27, /* \312 */ + NULL, /* \313 */ + NULL, /* \314 */ + NULL, /* \315 */ + Lower2UpperTbl28, /* \316 */ + Lower2UpperTbl29, /* \317 */ + Lower2UpperTbl2a, /* \320 */ + Lower2UpperTbl2b, /* \321 */ + Lower2UpperTbl2c, /* \322 */ + Lower2UpperTbl2d, /* \323 */ + NULL, /* \324 */ + Lower2UpperTbl2e, /* \325 */ + Lower2UpperTbl2f /* \326 */ +}; + +UpperLowerTbl_t *Lower2UpperTbl3[] = { + Lower2UpperTbl30, /* \341 */ + NULL, /* \342 */ + NULL, /* \343 */ + NULL, /* \344 */ + NULL, /* \345 */ + NULL, /* \346 */ + NULL, /* \347 */ + NULL, /* \350 */ + NULL, /* \351 */ + NULL, /* \352 */ + NULL, /* \353 */ + NULL, /* \354 */ + NULL, /* \355 */ + NULL, /* \356 */ + Lower2UpperTbl31 /* \357 */ +}; + +#define LU2S (unsigned char)'\303' +#define LU2E (unsigned char)'\326' +#define LU3S (unsigned char)'\341' +#define LU3E (unsigned char)'\357' + +/* + * dsgw_utf8StrToUpper: translate lower-case string to upper-case + * + * input: a null terminated UTF-8 string + * output: a null terminated UTF-8 string which characters are + * converted to upper-case; characters which are not + * lower-case are copied as is. If it's not considered + * a UTF-8 string, NULL is returned. + * + * Notes: This function takes a string (made of multiple UTF-8 characters) + * for the input (not one character as in "toupper"). + * Output string is allocated in this function, which needs to be + * released when it's not needed any more. + */ +unsigned char * +dsgw_utf8StrToUpper(unsigned char *s) +{ + UpperLowerTbl_t *ultp; + unsigned char *p, *np, *tail; + unsigned char *up, *uphead; + int len, sz; + + if (s == NULL || *s == '\0') { + return s; + } + len = strlen((char *)s); + tail = s + len; + uphead = up = (unsigned char *)dsgw_ch_malloc(len + 1); + p = s; + while ((np = (unsigned char *)ldap_utf8next((char *)p)) <= tail) { + switch(sz = np - p) { + case 1: /* ASCII */ + sprintf((char *)up, "%c", toupper(*p)); + break; + case 2: /* 2 bytes */ + if (*p < LU2S || *p > LU2E) { /* out of range */ + memcpy(up, p, sz); + break; + } + for (ultp = Lower2UpperTbl2[*p - LU2S]; + ultp && ultp->lower && memcmp(p, ultp->lower, sz); + ultp++) + ; + if (!ultp) { /* out of range */ + memcpy(up, p, sz); + } if (ultp->lower) { /* matched */ + memcpy(up, ultp->upper, ultp->tsz); + sz = ultp->tsz; + } else { + memcpy(up, p, sz); + } + break; + case 3: /* 3 bytes */ + if (*p != LU3S && *p != LU3E) { /* out of range */ + memcpy(up, p, sz); + break; + } + for (ultp = Lower2UpperTbl3[*p - LU3S]; + ultp && ultp->lower && memcmp(p, ultp->lower, sz); + ultp++) + ; + if (!ultp) { /* out of range */ + memcpy(up, p, sz); + } if (ultp->lower) { /* matched */ + memcpy(up, ultp->upper, sz); + } else { + memcpy(up, p, sz); + } + break; + case 4: + memcpy(up, p, sz); + break; + default: /* not UTF-8 */ + free(uphead); + return NULL; + } + up += sz; + p = np; + if (p == tail) { + break; + } + } + *up = '\0'; + return uphead; +} + +/* + * dsgw_utf8ToUpper: translate lower-case character to upper-case + * + * input: a UTF-8 character (s) + * output: a UTF-8 character which is converted to upper-case (d) + * length (in bytes) of input character (ssz) and + * output character (dsz) + * + * Notes: This function takes a UTF-8 character (could be multiple bytes) + * for the input. Memory for the output character is NOT allocated + * in this function, caller should have allocated it (d). + * "memmove" is used since (s) and (d) are overlapped. + */ +void +dsgw_utf8ToUpper(unsigned char *s, unsigned char *d, int *ssz, int *dsz) +{ + UpperLowerTbl_t *ultp; + unsigned char *tail; + + if (s == NULL || *s == '\0') { + *ssz = *dsz = 0; + return; + } + if (!(*s & 0x80)) { /* ASCII */ + *dsz = *ssz = 1; + *d = toupper(*s); + return; + } + tail = (unsigned char *)ldap_utf8next((char *)s); + *dsz = *ssz = tail - s; + switch(*ssz) { + case 1: /* ASCII */ + *d = toupper(*s); + break; + case 2: /* 2 bytes */ + if (*s < LU2S || *s > LU2E) { /* out of range */ + memmove(d, s, *ssz); + break; + } + for (ultp = Lower2UpperTbl2[*s - LU2S]; + ultp && ultp->lower && memcmp(s, ultp->lower, *ssz); + ultp++) + ; + if (!ultp) { /* out of range */ + memmove(d, s, *ssz); + } else if (ultp->lower) { /* matched */ + memmove(d, ultp->upper, ultp->tsz); + *dsz = ultp->tsz; + } else { + memmove(d, s, *ssz); + } + break; + case 3: /* 3 bytes */ + if (*s != LU3S && *s != LU3E) { /* out of range */ + memmove(d, s, *ssz); + break; + } + for (ultp = Lower2UpperTbl3[*s - LU3S]; + ultp && ultp->lower && memcmp(s, ultp->lower, *ssz); + ultp++) + ; + if (!ultp) { /* out of range */ + memmove(d, s, *ssz); + } else if (ultp->lower) { /* matched */ + memmove(d, ultp->upper, *ssz); + } else { + memmove(d, s, *ssz); + } + break; + } + return; +} + +/* + * dsgw_utf8isLower: tests for a character that is a lower-case letter in + * UTF-8 + * + * input: a UTF-8 character (could be multi-byte) + * output: 1 if the character is a lower-case letter + * 0 if the character is not a lower-case letter + */ +int +dsgw_utf8isLower(unsigned char *s) +{ + UpperLowerTbl_t *ultp; + unsigned char *next; + int sz; + + if (s == NULL || *s == '\0') { + return 0; + } + if (!(*s & 0x80)) { /* ASCII */ + return islower(*s); + } + next = (unsigned char *)ldap_utf8next((char *)s); + switch(sz = next - s) { + case 1: /* ASCII */ + return islower(*s); + case 2: + if (*s < LU2S || *s > LU2E) { /* out of range */ + return 0; + } + for (ultp = Lower2UpperTbl2[*s - LU2S]; + ultp && ultp->lower && memcmp(s, ultp->lower, sz); + ultp++) + ; + if (!ultp) { /* out of range */ + return 0; + } if (ultp->lower) { /* matched */ + return 1; + } else { + return 0; + } + case 3: + if (*s < LU3S || *s > LU3E) { /* out of range */ + return 0; + } + for (ultp = Lower2UpperTbl3[*s - LU3S]; + ultp && ultp->lower && memcmp(s, ultp->lower, sz); + ultp++) + ; + if (!ultp) { /* out of range */ + return 0; + } if (ultp->lower) { /* matched */ + return 1; + } else { + return 0; + } + default: + return 0; + } +} + +/* + * dsgw_utf8casecmp: case-insensitive string compare for UTF-8 strings + * + * input: two UTF-8 strings (s0, s1) to be compared + * output: positive number, if s0 is after s1 + * 0, if the two strings are identical ignoring the case + * negative number, if s1 is after s0 + * + * Rules: If both UTF-8 strings are NULL or 0-length, 0 is returned. + * If one of the strings is NULL or 0-length, the NULL/0-length + * string is smaller. + * If one or both of the strings are not UTF-8, system provided + * strcasecmp is used. + * If one of the two strings contains no 8-bit characters, + * strcasecmp is used. + * The strings are compared after converted to lower-case UTF-8. + * Each character is compared from the beginning. + * Evaluation goes in this order: + * If the length of one character is shorter then the other, + * the difference of the two lengths is returned. + * If the length of the corresponsing characters is same, + * each byte in the characters is compared. + * If there's a difference between two bytes, + * the diff is returned. + * If one string is shorter then the other, the diff is returned. + * + * Notes: Don't use this function for collation + * 1) there's no notion of locale in this function. + * 2) it's UTF-8 code order, which is different from the locale + * based collation. + */ +int +dsgw_utf8casecmp(unsigned char *s0, unsigned char *s1) +{ + unsigned char *d0, *d1; /* store lower-case strings */ + unsigned char *p0, *p1; /* current UTF-8 char */ + unsigned char *n0, *n1; /* next UTF-8 char */ + unsigned char *t0, *t1; /* tail of the strings */ + unsigned char *x0, *x1; /* current byte in a char */ + int i0, i1; /* length of characters */ + int l0, l1; /* length of leftover */ + int rval; + int has8_s0; + int has8_s1; + + d0 = d1 = NULL; + if (s0 == NULL || *s0 == '\0') { + if (s1 == NULL || *s1 == '\0') { + rval = 0; + } else { + rval = -1; /* regardless s1, s0 < s1 */ + } + goto end; + } else if (s1 == NULL || *s1 == '\0') { + rval = 1; /* regardless s0, s0 > s1 */ + goto end; + } + + has8_s0 = dsgw_has8thBit(s0); + has8_s1 = dsgw_has8thBit(s1); + if (has8_s0 == has8_s1) { /* both has-8th-bit or both do not */ + if (has8_s0 == 0) { /* neither has-8th-bit */ + rval = strcasecmp((char *)s0, (char *)s1); + goto end; + } + } else { /* one has and the other do not */ + rval = strcasecmp((char *)s0, (char *)s1); + goto end; + } + + d0 = dsgw_utf8StrToLower(s0); + d1 = dsgw_utf8StrToLower(s1); + if (d0 == NULL || d1 == NULL || /* either is not a UTF-8 string */ + (d0 && *d0 == '\0') || (d1 && *d1 == '\0')) { + rval = strcasecmp((char *)s0, (char *)s1); + goto end; + } + + p0 = d0; + p1 = d1; + + t0 = d0 + strlen((char *)d0); + t1 = d1 + strlen((char *)d1); + + rval = 0; + while (1) { + n0 = (unsigned char *)ldap_utf8next((char *)p0); + n1 = (unsigned char *)ldap_utf8next((char *)p1); + if (n0 > t0 || n1 > t1) { + break; + } + + i0 = n0 - p0; + i1 = n1 - p1; + rval = i0 - i1; + if (rval) { /* length is different */ + goto end; + } + + /* i0 == i1: same length */ + for (x0 = p0, x1 = p1; x0 < n0; x0++, x1++) { + rval = *x0 - *x1; + if (rval) { + goto end; + } + } + + p0 = n0; p1 = n1; /* goto next */ + } + /* finished scanning the shared part and check the leftover */ + l0 = t0 - n0; + l1 = t1 - n1; + rval = l0 - l1; + +end: + if (d0) + free(d0); + if (d1) + free(d1); + + return rval; +} + +/* + * dsgw_utf8ncasecmp: case-insensitive string compare (n chars) for UTF-8 + * strings + * + * input: two UTF-8 strings (s0, s1) to be compared + * number or characters + * output: positive number, if s0 is after s1 + * 0, if the two strings are identical ignoring the case + * negative number, if s1 is after s0 + * + * Rules: Same as dsgw_utf8casecmp except the n characters limit. + * + * Notes: Don't use this function for collation + * 1) there's no notion of locale in this function. + * 2) it's UTF-8 code order, which is different from the locale + * based collation. + * n characters, NOT n bytes + */ +int +dsgw_utf8ncasecmp(unsigned char *s0, unsigned char *s1, int n) +{ + unsigned char *d0, *d1; /* store lower-case strings */ + unsigned char *p0, *p1; /* current UTF-8 char */ + unsigned char *n0, *n1; /* next UTF-8 char */ + unsigned char *t0, *t1; /* tail of the strings */ + unsigned char *x0, *x1; /* current byte in a char */ + int i0, i1; /* length of characters */ + int l0, l1; /* length of leftover */ + int cnt; + int rval; + int has8_s0; + int has8_s1; + + d0 = d1 = NULL; + if (s0 == NULL || *s0 == '\0') { + if (s1 == NULL || *s1 == '\0') { + rval = 0; + } else { + rval = -1; /* regardless s1, s0 < s1 */ + } + goto end; + } else if (s1 == NULL || *s1 == '\0') { + rval = 1; /* regardless s0, s0 > s1 */ + goto end; + } + + has8_s0 = dsgw_has8thBit(s0); + has8_s1 = dsgw_has8thBit(s1); + if (has8_s0 == has8_s1) { /* both has-8th-bit or both do not */ + if (has8_s0 == 0) { /* neither has-8th-bit */ + rval = strncasecmp((char *)s0, (char *)s1, n); + goto end; + } + } else { /* one has and the other do not */ + rval = strncasecmp((char *)s0, (char *)s1, n); + goto end; + } + + d0 = dsgw_utf8StrToLower(s0); + d1 = dsgw_utf8StrToLower(s1); + if (d0 == NULL || d1 == NULL || /* either is not a UTF-8 string */ + (d0 && *d0 == '\0') || (d1 && *d1 == '\0')) { + rval = strncasecmp((char *)s0, (char *)s1, n); + goto end; + } + + p0 = d0; + p1 = d1; + + t0 = d0 + strlen((char *)d0); + t1 = d1 + strlen((char *)d1); + + rval = 0; + cnt = 0; + while (1) { + n0 = (unsigned char *)ldap_utf8next((char *)p0); + n1 = (unsigned char *)ldap_utf8next((char *)p1); + if (n0 > t0 || n1 > t1 || cnt == n) { + break; + } + + i0 = n0 - p0; + i1 = n1 - p1; + rval = i0 - i1; + if (rval) /* length is different */ + goto end; + + /* i0 == i1: same length */ + for (x0 = p0, x1 = p1; x0 < n0; x0++, x1++) { + rval = *x0 - *x1; + if (rval) + goto end; + } + + p0 = n0; p1 = n1; /* goto next */ + cnt++; + } + if (cnt == n) + rval = 0; + else { + /* finished scanning the shared part and check the leftover */ + l0 = t0 - n0; + l1 = t1 - n1; + rval = l0 - l1; + } + +end: + if (d0) + free(d0); + if (d1) + free(d1); + + return rval; +} + |