From 69f155d4fc11f2f0e1dd1bfcd804192303ba1627 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Thu, 30 Apr 1998 16:57:48 +0000 Subject: Update. 1998-04-30 16:45 Ulrich Drepper * inet/ether_aton.c: Including netinet/if_ether.h is not necessary. * locale/Makefile (distribute): Add programs/repertoire.h. (localedef-modules): Add repertoire. (CPPFLAGS): Define REPERTOIREMAP_PATH. * locale/programs/repertoire.c: New file. * locale/programs/repertoire.h: New file. * locale/programs/charmap.c: Starting fixing character set handling to handle multi-byte encodings. * locale/programs/charset.c: Likewise. * locale/programs/charset.h: Likewise. * locale/programs/ld-collate.c: Likewise. * locale/programs/ld-ctype.c: Likewise. * locale/programs/linereader.c: Likewise. * locale/programs/localedef.c: Likewise. * locale/programs/locfile-kw.gperf: Likewise. * locale/programs/locfile-kw.h: Likewise. * locale/programs/locfile-token.h: Likewise. * locale/programs/locfile.h: Likewise. * locale/programs/stringtrans.c: Likewise. 1998-04-18 Philip Blundell * sysdeps/arm/memset.S: Fix off by one error. * sysdeps/unix/sysv/linux/arm/sysdep.h (PSEUDO): On error, call __syscall_error rather than syscall_error directly. 1998-04-17 Philip Blundell * sysdeps/unix/sysv/linux/arm/mmap.S: New file; implementation of mmap() syscall for ARM. * sysdeps/unix/arm/start.c: New file; startup code for ARM a.out binaries. --- ChangeLog | 38 + inet/ether_aton.c | 1 - linuxthreads/manager.c | 2 +- locale/Makefile | 8 +- locale/programs/charmap.c | 50 +- locale/programs/charset.c | 59 +- locale/programs/charset.h | 17 +- locale/programs/ld-collate.c | 16 +- locale/programs/ld-ctype.c | 38 +- locale/programs/linereader.c | 2 +- locale/programs/localedef.c | 17 +- locale/programs/locfile-kw.gperf | 3 +- locale/programs/locfile-kw.h | 160 +-- locale/programs/locfile-token.h | 5 +- locale/programs/locfile.h | 3 +- locale/programs/repertoire.c | 323 ++++++ locale/programs/repertoire.h | 38 + locale/programs/stringtrans.c | 5 +- localedata/ChangeLog | 7 + localedata/Makefile | 10 +- localedata/mnemonic.ds | 1967 --------------------------------- localedata/repertoiremaps/charids.894 | 511 +++++++++ localedata/repertoiremaps/mnemonic.ds | 1941 ++++++++++++++++++++++++++++++++ sysdeps/arm/memset.S | 1 - sysdeps/unix/arm/start.c | 85 ++ sysdeps/unix/sysv/linux/arm/mmap.S | 39 + sysdeps/unix/sysv/linux/arm/sysdep.h | 2 +- 27 files changed, 3201 insertions(+), 2147 deletions(-) create mode 100644 locale/programs/repertoire.c create mode 100644 locale/programs/repertoire.h delete mode 100644 localedata/mnemonic.ds create mode 100644 localedata/repertoiremaps/charids.894 create mode 100644 localedata/repertoiremaps/mnemonic.ds create mode 100644 sysdeps/unix/arm/start.c create mode 100644 sysdeps/unix/sysv/linux/arm/mmap.S diff --git a/ChangeLog b/ChangeLog index 39e4021024..e6af1a812d 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,41 @@ +1998-04-30 16:45 Ulrich Drepper + + * inet/ether_aton.c: Including netinet/if_ether.h is not necessary. + + * locale/Makefile (distribute): Add programs/repertoire.h. + (localedef-modules): Add repertoire. + (CPPFLAGS): Define REPERTOIREMAP_PATH. + * locale/programs/repertoire.c: New file. + * locale/programs/repertoire.h: New file. + * locale/programs/charmap.c: Starting fixing character set handling + to handle multi-byte encodings. + * locale/programs/charset.c: Likewise. + * locale/programs/charset.h: Likewise. + * locale/programs/ld-collate.c: Likewise. + * locale/programs/ld-ctype.c: Likewise. + * locale/programs/linereader.c: Likewise. + * locale/programs/localedef.c: Likewise. + * locale/programs/locfile-kw.gperf: Likewise. + * locale/programs/locfile-kw.h: Likewise. + * locale/programs/locfile-token.h: Likewise. + * locale/programs/locfile.h: Likewise. + * locale/programs/stringtrans.c: Likewise. + +1998-04-18 Philip Blundell + + * sysdeps/arm/memset.S: Fix off by one error. + + * sysdeps/unix/sysv/linux/arm/sysdep.h (PSEUDO): On error, call + __syscall_error rather than syscall_error directly. + +1998-04-17 Philip Blundell + + * sysdeps/unix/sysv/linux/arm/mmap.S: New file; implementation of + mmap() syscall for ARM. + + * sysdeps/unix/arm/start.c: New file; startup code for ARM a.out + binaries. + 1998-04-30 Ulrich Drepper * locale/programs/localedef.c: Recognize repertoire-map option. diff --git a/inet/ether_aton.c b/inet/ether_aton.c index 574800765a..4c80ec6bb8 100644 --- a/inet/ether_aton.c +++ b/inet/ether_aton.c @@ -18,7 +18,6 @@ Boston, MA 02111-1307, USA. */ #include -#include struct ether_addr * diff --git a/linuxthreads/manager.c b/linuxthreads/manager.c index 993df00eb4..81674399a1 100644 --- a/linuxthreads/manager.c +++ b/linuxthreads/manager.c @@ -313,6 +313,7 @@ static int pthread_handle_create(pthread_t *thread, const pthread_attr_t *attr, static void pthread_free(pthread_descr th) { + pthread_handle handle; pthread_descr t; /* Check that the thread th is still there -- pthread_reap_children @@ -324,7 +325,6 @@ static void pthread_free(pthread_descr th) } while (t != __pthread_main_thread); if (t != th) return; - pthread_handle handle; ASSERT(th->p_exited); /* Make the handle invalid */ handle = thread_handle(th->p_tid); diff --git a/locale/Makefile b/locale/Makefile index 57a5bc5715..b93298310b 100644 --- a/locale/Makefile +++ b/locale/Makefile @@ -1,4 +1,4 @@ -# Copyright (C) 1991, 1992, 1995, 1996, 1997 Free Software Foundation, Inc. +# Copyright (C) 1991, 92, 95, 96, 97, 98 Free Software Foundation, Inc. # This file is part of the GNU C Library. # The GNU C Library is free software; you can redistribute it and/or @@ -30,7 +30,8 @@ distribute = localeinfo.h categories.def iso-4217.def weight.h \ $(lib-modules:=.c) config.h simple-hash.h \ charmap-kw.gperf charmap-kw.h locfile-token.h \ locfile-kw.gperf locfile-kw.h linereader.h \ - locales.h locfile.h stringtrans.h charset.h) + locales.h locfile.h stringtrans.h charset.h \ + repertoire.h) routines = setlocale findlocale loadlocale localeconv nl_langinfo \ mb_cur_max codeset_name \ newlocale duplocale freelocale @@ -53,7 +54,7 @@ vpath %.h programs vpath %.gperf programs localedef-modules := $(categories:%=ld-%) charmap charset linereader \ - locfile stringtrans + locfile stringtrans repertoire locale-modules := locale-spec lib-modules := simple-hash xmalloc xstrdup @@ -77,6 +78,7 @@ CPPFLAGS := -DLOCALE_PATH='$(localepath)' \ -DLOCALEDIR='"$(localedir)"' \ -DLOCALE_ALIAS_PATH='"$(localedir):$(i18ndir)"' \ -DCHARMAP_PATH='"$(i18ndir)/charmaps"' \ + -DREPERTOIREMAP_PATH='"$(i18ndir)/repertoiremaps"' \ -DLOCSRCDIR='"$(i18ndir)/locales"' -DHAVE_CONFIG_H \ -Iprograms $(CPPFLAGS) diff --git a/locale/programs/charmap.c b/locale/programs/charmap.c index 0cd62fbfd4..7114a237a0 100644 --- a/locale/programs/charmap.c +++ b/locale/programs/charmap.c @@ -33,6 +33,8 @@ #include "error.h" #include "linereader.h" #include "charset.h" +#include "locfile.h" +#include "repertoire.h" /* Uncomment following line for production version. */ @@ -209,6 +211,8 @@ parse_charmap (const char *filename) memset (result, '\0', sizeof (struct charset_t)); /* The default DEFAULT_WIDTH is 1. */ result->width_default = 1; + /* Let the user overwrite the repertoire map we use. */ + result->repertoiremap = repertoiremap; #define obstack_chunk_alloc malloc #define obstack_chunk_free free @@ -265,6 +269,17 @@ parse_charmap (const char *filename) lr_ignore_rest (cmfile, 1); + /* Read the repertoire map now. */ + if (result->repertoiremap == NULL) + /* This is fatal. */ + error (4, 0, _("no repertoire map specified: cannot proceed")); + + result->repertoire = repertoire_read (result->repertoiremap); + if (result->repertoire == NULL) + /* This is also fatal. */ + error (4, errno, _("cannot read repertoire map `%s'"), + result->repertoiremap); + state = 2; continue; } @@ -273,7 +288,7 @@ parse_charmap (const char *filename) && nowtok != tok_mb_cur_min && nowtok != tok_escape_char && nowtok != tok_comment_char && nowtok != tok_g0esc && nowtok != tok_g1esc && nowtok != tok_g2esc - && nowtok != tok_g3esc) + && nowtok != tok_g3esc && nowtok != tok_repertoiremap) { lr_error (cmfile, _("syntax error in prolog: %s"), _("illegal definition")); @@ -305,6 +320,18 @@ parse_charmap (const char *filename) lr_ignore_rest (cmfile, 1); continue; + case tok_repertoiremap: + if (arg->tok != tok_ident) + goto badarg; + + if (result->repertoiremap == NULL) + result->repertoiremap = obstack_copy0 (&result->mem_pool, + arg->val.str.start, + arg->val.str.len); + + lr_ignore_rest (cmfile, 1); + continue; + case tok_mb_cur_max: case tok_mb_cur_min: if (arg->tok != tok_number) @@ -437,14 +464,14 @@ argument to <%s> must be a single character"), continue; } - if (nowtok == tok_charcode) - /* Write char value in table. */ - charset_new_char (cmfile, result, now->val.charcode.nbytes, - now->val.charcode.val, from_name, to_name); + if (now->val.charcode.nbytes < result->mb_cur_min) + lr_error (cmfile, _("too few bytes in character encoding")); + else if (now->val.charcode.nbytes > result->mb_cur_max) + lr_error (cmfile, _("too many bytes in character encoding")); else - /* Determine ISO 10646 value and write into table. */ - charset_new_unicode (cmfile, result, now->val.charcode.nbytes, - now->val.charcode.val, from_name, to_name); + charset_new_char (cmfile, &result->char_table, + now->val.charcode.nbytes, + now->val.charcode.val, from_name, to_name); /* Ignore trailing comment silently. */ lr_ignore_rest (cmfile, 0); @@ -466,8 +493,7 @@ argument to <%s> must be a single character"), continue; } - /* If the previous line was not completely correct free the - used memory. */ + /* Copy the to-name in a safe place. */ to_name = (char *) obstack_copy0 (&result->mem_pool, cmfile->token.val.str.start, cmfile->token.val.str.len); @@ -694,7 +720,7 @@ new_width (struct linereader *cmfile, struct charset_t *result, { unsigned int from_val, to_val; - from_val = charset_find_value (result, from, strlen (from)); + from_val = charset_find_value (&result->char_table, from, strlen (from)); if ((wchar_t) from_val == ILLEGAL_CHAR_VALUE) { lr_error (cmfile, _("unknown character `%s'"), from); @@ -705,7 +731,7 @@ new_width (struct linereader *cmfile, struct charset_t *result, to_val = from_val; else { - to_val = charset_find_value (result, to, strlen (to)); + to_val = charset_find_value (&result->char_table, to, strlen (to)); if ((wchar_t) to_val == ILLEGAL_CHAR_VALUE) { lr_error (cmfile, _("unknown character `%s'"), to); diff --git a/locale/programs/charset.c b/locale/programs/charset.c index fdacf25328..767fafb93a 100644 --- a/locale/programs/charset.c +++ b/locale/programs/charset.c @@ -1,4 +1,4 @@ -/* Copyright (C) 1996, 1997 Free Software Foundation, Inc. +/* Copyright (C) 1996, 1997, 1998 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Ulrich Drepper , 1996. @@ -23,6 +23,8 @@ #include #include +#include +#include #include #include #include @@ -31,49 +33,24 @@ #include "charset.h" -static void -insert_char (struct linereader *lr, struct charset_t *cs, int bytes, - unsigned int value, const char *from, const char *to); - - -void -charset_new_char (struct linereader *lr, struct charset_t *cs, int bytes, - unsigned int value, const char *from, const char *to) -{ - if (bytes < cs->mb_cur_min) - lr_error (lr, _("too few bytes in character encoding")); - else if (bytes > cs->mb_cur_max) - lr_error (lr, _("too many bytes in character encoding")); - else - insert_char (lr, cs, bytes, value, from, to); -} - - -void -charset_new_unicode (struct linereader *lr, struct charset_t *cs, int bytes, - unsigned int value, const char *from, const char *to) -{ - /* For now: perhaps support will be removed again... */ - insert_char (lr, cs, bytes, value, from, to); -} - - unsigned int -charset_find_value (const struct charset_t *cs, const char *name, size_t len) +charset_find_value (const hash_table *ht, const char *name, size_t len) { void *result; - if (find_entry ((hash_table *) &cs->char_table, name, len, &result) < 0) + if (find_entry ((hash_table *) ht, name, len, &result) < 0) return ILLEGAL_CHAR_VALUE; return (unsigned int) ((unsigned long int) result); } -static void -insert_char (struct linereader *lr, struct charset_t *cs, int bytes, - unsigned int value, const char *from, const char *to) +void +charset_new_char (struct linereader *lr, hash_table *ht, int bytes, + unsigned int value, const char *from, const char *to) { + char *from_end; + char *to_end; const char *cp; char *buf; int prefix_len, len1, len2; @@ -81,7 +58,7 @@ insert_char (struct linereader *lr, struct charset_t *cs, int bytes, if (to == NULL) { - if (insert_entry (&cs->char_table, from, strlen (from), + if (insert_entry (ht, from, strlen (from), (void *) (unsigned long int) value) < 0) lr_error (lr, _("duplicate character name `%s'"), from); @@ -111,8 +88,16 @@ insert_char (struct linereader *lr, struct charset_t *cs, int bytes, if (cp == &from[len1 - 1] || strncmp (from, to, prefix_len) != 0) goto illegal_range; - from_nr = strtoul (&from[prefix_len], NULL, 10); - to_nr = strtoul (&to[prefix_len], NULL, 10); + errno = 0; + from_nr = strtoul (&from[prefix_len], &from_end, 10); + if (*from_end != '\0' || (from_nr == ULONG_MAX && errno == ERANGE) + || ((to_nr = strtoul (&to[prefix_len], &to_end, 10)) == ULONG_MAX + && errno == ERANGE) + || *to_end != '\0') + { + lr_error (lr, _("<%s> and <%s> are illegal names for range")); + return; + } if (from_nr > to_nr) { @@ -127,7 +112,7 @@ insert_char (struct linereader *lr, struct charset_t *cs, int bytes, { sprintf (&buf[prefix_len], "%0*d", len1 - prefix_len, cnt); - if (insert_entry (&cs->char_table, buf, len1, + if (insert_entry (ht, buf, len1, (void *) (unsigned long int) (value + (cnt - from_nr))) < 0) lr_error (lr, _("duplicate character name `%s'"), buf); diff --git a/locale/programs/charset.h b/locale/programs/charset.h index 82c4ef0c57..db93f16306 100644 --- a/locale/programs/charset.h +++ b/locale/programs/charset.h @@ -1,4 +1,4 @@ -/* Copyright (C) 1996, 1997 Free Software Foundation, Inc. +/* Copyright (C) 1996, 1997, 1998 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Ulrich Drepper , 1996. @@ -22,6 +22,7 @@ #include +#include "repertoire.h" #include "simple-hash.h" #include "linereader.h" @@ -36,6 +37,9 @@ struct width_rule struct charset_t { + const char *repertoiremap; + struct repertoire_t *repertoire; + const char *code_set_name; int mb_cur_min; int mb_cur_max; @@ -63,14 +67,11 @@ extern int be_quiet; struct charset_t *charmap_read (const char *filename); /* Prototypes for function to insert new character. */ -void charset_new_char (struct linereader *lr, struct charset_t *cs, int bytes, +void charset_new_char (struct linereader *lr, hash_table *ht, int bytes, unsigned int value, const char *from, const char *to); -void charset_new_unicode (struct linereader *lr, struct charset_t *cs, - int bytes, unsigned int value, const char *from, - const char *to); - -unsigned int charset_find_value (const struct charset_t *__cs, - const char *__name, size_t __len); +/* Return the value stored under the given key in the hashing table. */ +unsigned int charset_find_value (const hash_table *ht, + const char *name, size_t len); #endif /* charset.h */ diff --git a/locale/programs/ld-collate.c b/locale/programs/ld-collate.c index 57b97767af..a92ff1154a 100644 --- a/locale/programs/ld-collate.c +++ b/locale/programs/ld-collate.c @@ -212,7 +212,7 @@ collate_finish (struct localedef_t *locale, struct charset_t *charset) void *ptmp; unsigned int value = 0; - wch = charset_find_value (charset, patch->token, toklen); + wch = charset_find_value (&charset->char_table, patch->token, toklen); if (wch != ILLEGAL_CHAR_VALUE) { element_t *runp; @@ -1054,7 +1054,8 @@ collate_element_to (struct linereader *lr, struct localedef_t *locale, collate->combine_token = NULL; } - value = charset_find_value (charset, code->val.str.start, code->val.str.len); + value = charset_find_value (&charset->char_table, code->val.str.start, + code->val.str.len); if ((wchar_t) value != ILLEGAL_CHAR_VALUE) { lr_error (lr, _("symbol for multicharacter collating element " @@ -1181,7 +1182,8 @@ collate_symbol (struct linereader *lr, struct localedef_t *locale, wchar_t value; void *not_used; - value = charset_find_value (charset, code->val.str.start, code->val.str.len); + value = charset_find_value (&charset->char_table, code->val.str.start, + code->val.str.len); if (value != ILLEGAL_CHAR_VALUE) { lr_error (lr, _("symbol for multicharacter collating element " @@ -1268,7 +1270,7 @@ collate_order_elem (struct linereader *lr, struct localedef_t *locale, { case tok_bsymbol: /* We have a string to find in one of the three hashing tables. */ - value = charset_find_value (charset, code->val.str.start, + value = charset_find_value (&charset->char_table, code->val.str.start, code->val.str.len); if (value != ILLEGAL_CHAR_VALUE) { @@ -1533,7 +1535,8 @@ collate_weight_bsymbol (struct linereader *lr, struct localedef_t *locale, assert (code->tok == tok_bsymbol); - value = charset_find_value (charset, code->val.str.start, code->val.str.len); + value = charset_find_value (&charset->char_table, code->val.str.start, + code->val.str.len); if (value != ILLEGAL_CHAR_VALUE) { element_t *runp; @@ -1706,7 +1709,8 @@ collate_simple_weight (struct linereader *lr, struct localedef_t *locale, return -1; } - wch = charset_find_value (charset, startp, putp - startp); + wch = charset_find_value (&charset->char_table, startp, + putp - startp); if (wch != ILLEGAL_CHAR_VALUE) { element_t *pelem; diff --git a/locale/programs/ld-ctype.c b/locale/programs/ld-ctype.c index f2f32cc214..2f9a9a2caf 100644 --- a/locale/programs/ld-ctype.c +++ b/locale/programs/ld-ctype.c @@ -308,7 +308,7 @@ character %s'%s' in class `%s' must not be in class `%s'"), } /* ... and now test as a special case. */ - space_value = charset_find_value (charset, "SP", 2); + space_value = charset_find_value (&charset->char_table, "SP", 2); if ((wchar_t) space_value == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -634,7 +634,8 @@ ctype_class_from (struct linereader *lr, struct localedef_t *locale, struct locale_ctype_t *ctype = locale->categories[LC_CTYPE].ctype; unsigned int value; - value = charset_find_value (charset, code->val.str.start, code->val.str.len); + value = charset_find_value (&charset->char_table, code->val.str.start, + code->val.str.len); ctype->last_class_char = value; @@ -656,7 +657,8 @@ ctype_class_to (struct linereader *lr, struct localedef_t *locale, struct locale_ctype_t *ctype = locale->categories[LC_CTYPE].ctype; unsigned int value, cnt; - value = charset_find_value (charset, code->val.str.start, code->val.str.len); + value = charset_find_value (&charset->char_table, code->val.str.start, + code->val.str.len); /* In the LC_CTYPE category it is no error when a character is not found. This has to be ignored silently. */ @@ -750,7 +752,8 @@ ctype_map_from (struct linereader *lr, struct localedef_t *locale, struct locale_ctype_t *ctype = locale->categories[LC_CTYPE].ctype; unsigned int value; - value = charset_find_value (charset, code->val.str.start, code->val.str.len); + value = charset_find_value (&charset->char_table, code->val.str.start, + code->val.str.len); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) /* In the LC_CTYPE category it is no error when a character is @@ -770,7 +773,8 @@ ctype_map_to (struct linereader *lr, struct localedef_t *locale, struct locale_ctype_t *ctype = locale->categories[LC_CTYPE].ctype; unsigned int value; - value = charset_find_value (charset, code->val.str.start, code->val.str.len); + value = charset_find_value (&charset->char_table, code->val.str.start, + code->val.str.len); if ((wchar_t) ctype->from_map_char == ILLEGAL_CHAR_VALUE || (wchar_t) value == ILLEGAL_CHAR_VALUE) @@ -948,7 +952,7 @@ set_class_defaults (struct locale_ctype_t *ctype, struct charset_t *charset) unsigned int value; tmp[0] = ch; - value = charset_find_value (charset, tmp, 1); + value = charset_find_value (&charset->char_table, tmp, 1); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1013,7 +1017,7 @@ character `%s' not defined while needed as default value"), { unsigned int value; - value = charset_find_value (charset, "space", 5); + value = charset_find_value (&charset->char_table, "space", 5); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1024,7 +1028,7 @@ character `%s' not defined while needed as default value"), else ELEM (ctype, class_collection, , value) |= BIT (tok_space); - value = charset_find_value (charset, "form-feed", 9); + value = charset_find_value (&charset->char_table, "form-feed", 9); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1035,7 +1039,7 @@ character `%s' not defined while needed as default value"), else ELEM (ctype, class_collection, , value) |= BIT (tok_space); - value = charset_find_value (charset, "newline", 7); + value = charset_find_value (&charset->char_table, "newline", 7); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1046,7 +1050,7 @@ character `%s' not defined while needed as default value"), else ELEM (ctype, class_collection, , value) |= BIT (tok_space); - value = charset_find_value (charset, "carriage-return", 15); + value = charset_find_value (&charset->char_table, "carriage-return", 15); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1057,7 +1061,7 @@ character `%s' not defined while needed as default value"), else ELEM (ctype, class_collection, , value) |= BIT (tok_space); - value = charset_find_value (charset, "tab", 3); + value = charset_find_value (&charset->char_table, "tab", 3); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1068,7 +1072,7 @@ character `%s' not defined while needed as default value"), else ELEM (ctype, class_collection, , value) |= BIT (tok_space); - value = charset_find_value (charset, "vertical-tab", 12); + value = charset_find_value (&charset->char_table, "vertical-tab", 12); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1097,7 +1101,7 @@ character `%s' not defined while needed as default value"), { unsigned int value; - value = charset_find_value (charset, "space", 5); + value = charset_find_value (&charset->char_table, "space", 5); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1108,7 +1112,7 @@ character `%s' not defined while needed as default value"), else ELEM (ctype, class_collection, , value) |= BIT (tok_blank); - value = charset_find_value (charset, "tab", 3); + value = charset_find_value (&charset->char_table, "tab", 3); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1149,7 +1153,7 @@ character `%s' not defined while needed as default value"), if ((ctype->class_collection[cnt] & mask) != 0) ctype->class_collection[cnt] |= BIT (tok_print); - space = charset_find_value (charset, "space", 5); + space = charset_find_value (&charset->char_table, "space", 5); if (space == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1178,7 +1182,7 @@ character `%s' not defined while needed as default value"), tmp[1] = (char) ch; - value_from = charset_find_value (charset, &tmp[1], 1); + value_from = charset_find_value (&charset->char_table, &tmp[1], 1); if ((wchar_t) value_from == ILLEGAL_CHAR_VALUE) { if (!be_quiet) @@ -1190,7 +1194,7 @@ character `%s' not defined while needed as default value"), /* This conversion is implementation defined. */ tmp[1] = (char) (ch + ('A' - 'a')); - value_to = charset_find_value (charset, &tmp[1], 1); + value_to = charset_find_value (&charset->char_table, &tmp[1], 1); if ((wchar_t) value_to == ILLEGAL_CHAR_VALUE) { if (!be_quiet) diff --git a/locale/programs/linereader.c b/locale/programs/linereader.c index 6692164b60..4406e1ab72 100644 --- a/locale/programs/linereader.c +++ b/locale/programs/linereader.c @@ -524,7 +524,7 @@ get_string (struct linereader *lr, const struct charset_t *charset) if (lr->translate_strings) { - value = charset_find_value (charset, &buf[startidx], + value = charset_find_value (&charset->char_table, &buf[startidx], bufact - startidx); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) illegal_string = 1; diff --git a/locale/programs/localedef.c b/locale/programs/localedef.c index 32437c12f5..831c36e429 100644 --- a/locale/programs/localedef.c +++ b/locale/programs/localedef.c @@ -81,8 +81,8 @@ static const char *charmap_file; /* Name of the locale definition file. */ static const char *input_file; -/* Name of the UCS file. */ -static const char *ucs_csn; +/* Name of the repertoire map file. */ +const char *repertoiremap; /* Name and version of program. */ @@ -99,9 +99,7 @@ static const struct argp_option options[] = { "charmap", 'f', "FILE", 0, N_("Symbolic character names defined in FILE") }, { "inputfile", 'i', "FILE", 0, N_("Source definitions are found in FILE") }, - { "code-set-name", 'u', "NAME", OPTION_HIDDEN, - N_("Specify code set for mapping ISO 10646 elements") }, - { "repertoire-map", 'u', NAME, 0, + { "repertoire-map", 'u', "FILE", 0, N_("file containing mapping from symbolic names to UCS4 values") }, { NULL, 0, NULL, 0, N_("Output control:") }, @@ -355,7 +353,7 @@ parse_opt (int key, char *arg, struct argp_state *state) input_file = arg; break; case 'u': - ucs_csn = arg; + repertoiremap = arg; break; case 'v': verbose = 1; @@ -377,10 +375,11 @@ more_help (int key, const char *text, void *input) case ARGP_KEY_HELP_EXTRA: /* We print some extra information. */ asprintf (&cp, gettext ("\ -System's directory for character maps: %s\n\ - locale files : %s\n\ +System's directory for character maps : %s\n\ + repertoire maps: %s\n\ + locale path : %s\n\ %s"), - CHARMAP_PATH, LOCALE_PATH, gettext ("\ + CHARMAP_PATH, REPERTOIREMAP_PATH, LOCALE_PATH, gettext ("\ Report bugs using the `glibcbug' script to .\n")); return cp; default: diff --git a/locale/programs/locfile-kw.gperf b/locale/programs/locfile-kw.gperf index 38150ad46b..991e9dd6f9 100644 --- a/locale/programs/locfile-kw.gperf +++ b/locale/programs/locfile-kw.gperf @@ -1,5 +1,5 @@ %{ -/* Copyright (C) 1996, 1997 Free Software Foundation, Inc. +/* Copyright (C) 1996, 1997, 1998 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Ulrich Drepper , 1996. @@ -26,6 +26,7 @@ struct keyword_t ; %% escape_char, tok_escape_char, 0 comment_char, tok_comment_char, 0 +repertoiremap, tok_repertoiremap, 0 LC_CTYPE, tok_lc_ctype, 0 END, tok_end, 0 copy, tok_copy, 0 diff --git a/locale/programs/locfile-kw.h b/locale/programs/locfile-kw.h index 0fb0b5ca5f..bd80618e77 100644 --- a/locale/programs/locfile-kw.h +++ b/locale/programs/locfile-kw.h @@ -1,6 +1,6 @@ /* C code produced by gperf version 2.5 (GNU C++ version) */ /* Command-line: gperf -acCgopt -k1,2,5,$ -N locfile_hash programs/locfile-kw.gperf */ -/* Copyright (C) 1996, 1997 Free Software Foundation, Inc. +/* Copyright (C) 1996, 1997, 1998 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Ulrich Drepper , 1996. @@ -24,12 +24,12 @@ #include "locfile-token.h" struct keyword_t ; -#define TOTAL_KEYWORDS 73 +#define TOTAL_KEYWORDS 74 #define MIN_WORD_LENGTH 3 #define MAX_WORD_LENGTH 17 #define MIN_HASH_VALUE 3 -#define MAX_HASH_VALUE 132 -/* maximum key range = 130, duplicates = 0 */ +#define MAX_HASH_VALUE 178 +/* maximum key range = 176, duplicates = 0 */ #ifdef __GNUC__ inline @@ -39,19 +39,19 @@ hash (register const char *str, register int len) { static const unsigned char asso_values[] = { - 133, 133, 133, 133, 133, 133, 133, 133, 133, 133, - 133, 133, 133, 133, 133, 133, 133, 133, 133, 133, - 133, 133, 133, 133, 133, 133, 133, 133, 133, 133, - 133, 133, 133, 133, 133, 133, 133, 133, 133, 133, - 133, 133, 133, 133, 133, 133, 133, 133, 133, 133, - 133, 133, 133, 133, 133, 133, 133, 133, 133, 133, - 133, 133, 133, 133, 133, 133, 133, 0, 0, 0, - 0, 0, 133, 0, 133, 133, 0, 133, 0, 20, - 133, 133, 0, 0, 0, 5, 133, 133, 133, 5, - 133, 133, 133, 133, 133, 5, 133, 0, 60, 0, - 15, 10, 20, 40, 5, 20, 133, 0, 45, 40, - 10, 0, 0, 133, 15, 50, 0, 30, 0, 10, - 15, 15, 133, 133, 133, 133, 133, 133, + 179, 179, 179, 179, 179, 179, 179, 179, 179, 179, + 179, 179, 179, 179, 179, 179, 179, 179, 179, 179, + 179, 179, 179, 179, 179, 179, 179, 179, 179, 179, + 179, 179, 179, 179, 179, 179, 179, 179, 179, 179, + 179, 179, 179, 179, 179, 179, 179, 179, 179, 179, + 179, 179, 179, 179, 179, 179, 179, 179, 179, 179, + 179, 179, 179, 179, 179, 179, 179, 0, 0, 0, + 0, 0, 179, 0, 179, 179, 0, 179, 0, 45, + 179, 179, 0, 0, 0, 5, 179, 179, 179, 10, + 179, 179, 179, 179, 179, 5, 179, 0, 5, 0, + 15, 20, 5, 20, 40, 20, 179, 25, 15, 50, + 10, 0, 0, 179, 45, 50, 0, 30, 0, 5, + 10, 60, 179, 179, 179, 179, 179, 179, }; register int hval = len; @@ -88,102 +88,110 @@ locfile_hash (register const char *str, register int len) {"",}, {"t_fmt", tok_t_fmt, 0}, {"LC_MESSAGES", tok_lc_messages, 0}, - {"",}, - {"charconv", tok_charconv, 0}, + {"",}, {"",}, {"UNDEFINED", tok_undefined, 0}, {"LC_NUMERIC", tok_lc_numeric, 0}, {"",}, {"collating-element", tok_collating_element, 0}, {"position", tok_position, 0}, - {"copy", tok_copy, 0}, - {"print", tok_print, 0}, {"",}, - {"toupper", tok_toupper, 0}, + {"alpha", tok_alpha, 0}, + {"",}, {"",}, {"positive_sign", tok_positive_sign, 0}, {"",}, {"d_fmt", tok_d_fmt, 0}, + {"",}, + {"forward", tok_forward, 0}, {"",}, {"",}, - {"era", tok_era, 0}, - {"p_sep_by_space", tok_p_sep_by_space, 0}, - {"LC_COLLATE", tok_lc_collate, 0}, - {"noexpr", tok_noexpr, 0}, - {"tolower", tok_tolower, 0}, - {"day", tok_day, 0}, - {"era_t_fmt", tok_era_t_fmt, 0}, + {"abmon", tok_abmon, 0}, + {"collating-symbol", tok_collating_symbol, 0}, + {"d_t_fmt", tok_d_t_fmt, 0}, + {"backward", tok_backward, 0}, + {"",}, {"punct", tok_punct, 0}, - {"LC_MONETARY", tok_lc_monetary, 0}, - {"comment_char", tok_comment_char, 0}, + {"",}, {"",}, {"",}, + {"p_sep_by_space", tok_p_sep_by_space, 0}, + {"digit", tok_digit, 0}, + {"",}, {"",}, {"",}, {"",}, + {"cntrl", tok_cntrl, 0}, + {"p_sign_posn", tok_p_sign_posn, 0}, {"",}, + {"charconv", tok_charconv, 0}, {"n_sep_by_space", tok_n_sep_by_space, 0}, - {"digit", tok_digit, 0}, - {"order_start", tok_order_start, 0}, - {"forward", tok_forward, 0}, + {"print", tok_print, 0}, + {"xdigit", tok_xdigit, 0}, + {"toupper", tok_toupper, 0}, {"negative_sign", tok_negative_sign, 0}, {"",}, - {"nostr", tok_nostr, 0}, - {"yesstr", tok_yesstr, 0}, - {"d_t_fmt", tok_d_t_fmt, 0}, - {"",}, - {"era_d_fmt", tok_era_d_fmt, 0}, - {"alpha", tok_alpha, 0}, - {"era_d_t_fmt", tok_era_d_t_fmt, 0}, + {"LC_COLLATE", tok_lc_collate, 0}, + {"n_sign_posn", tok_n_sign_posn, 0}, + {"tolower", tok_tolower, 0}, + {"",}, {"",}, + {"int_curr_symbol", tok_int_curr_symbol, 0}, + {"noexpr", tok_noexpr, 0}, {"",}, {"mon", tok_mon, 0}, - {"order_end", tok_order_end, 0}, + {"copy", tok_copy, 0}, {"t_fmt_ampm", tok_t_fmt_ampm, 0}, - {"xdigit", tok_xdigit, 0}, + {"LC_MONETARY", tok_lc_monetary, 0}, {"mon_thousands_sep", tok_mon_thousands_sep, 0}, - {"",}, {"",}, {"",}, - {"collating-symbol", tok_collating_symbol, 0}, - {"yesexpr", tok_yesexpr, 0}, - {"era_year", tok_era_year, 0}, - {"charclass", tok_charclass, 0}, - {"upper", tok_upper, 0}, - {"p_sign_posn", tok_p_sign_posn, 0}, + {"era", tok_era, 0}, + {"",}, {"",}, {"",}, {"",}, + {"p_cs_precedes", tok_p_cs_precedes, 0}, + {"era_t_fmt", tok_era_t_fmt, 0}, + {"blank", tok_blank, 0}, {"",}, - {"thousands_sep", tok_thousands_sep, 0}, + {"comment_char", tok_comment_char, 0}, + {"day", tok_day, 0}, {"",}, - {"graph", tok_graph, 0}, + {"currency_symbol", tok_currency_symbol, 0}, {"",}, {"mon_decimal_point", tok_mon_decimal_point, 0}, - {"p_cs_precedes", tok_p_cs_precedes, 0}, + {"n_cs_precedes", tok_n_cs_precedes, 0}, + {"",}, {"",}, {"",}, {"",}, {"",}, + {"era_d_fmt", tok_era_d_fmt, 0}, + {"alt_digits", tok_alt_digits, 0}, + {"era_d_t_fmt", tok_era_d_t_fmt, 0}, {"",}, - {"space", tok_space, 0}, - {"n_sign_posn", tok_n_sign_posn, 0}, + {"grouping", tok_grouping, 0}, {"",}, + {"space", tok_space, 0}, + {"",}, {"",}, {"decimal_point", tok_decimal_point, 0}, + {"charclass", tok_charclass, 0}, + {"int_frac_digits", tok_int_frac_digits, 0}, + {"order_start", tok_order_start, 0}, + {"mon_grouping", tok_mon_grouping, 0}, + {"thousands_sep", tok_thousands_sep, 0}, {"from", tok_from, 0}, + {"nostr", tok_nostr, 0}, + {"",}, {"",}, {"",}, {"",}, {"lower", tok_lower, 0}, - {"",}, {"",}, - {"n_cs_precedes", tok_n_cs_precedes, 0}, + {"",}, {"",}, {"",}, + {"order_end", tok_order_end, 0}, {"",}, - {"abmon", tok_abmon, 0}, - {"escape_char", tok_escape_char, 0}, + {"frac_digits", tok_frac_digits, 0}, {"",}, {"",}, {"",}, - {"int_curr_symbol", tok_int_curr_symbol, 0}, + {"alnum", tok_alnum, 0}, {"",}, {"",}, - {"backward", tok_backward, 0}, + {"repertoiremap", tok_repertoiremap, 0}, {"",}, + {"upper", tok_upper, 0}, + {"escape_char", tok_escape_char, 0}, + {"",}, {"",}, {"",}, {"abday", tok_abday, 0}, - {"",}, {"",}, {"",}, {"",}, - {"currency_symbol", tok_currency_symbol, 0}, - {"frac_digits", tok_frac_digits, 0}, - {"",}, - {"grouping", tok_grouping, 0}, + {"yesstr", tok_yesstr, 0}, + {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, - {"cntrl", tok_cntrl, 0}, - {"",}, {"",}, {"",}, {"",}, - {"blank", tok_blank, 0}, - {"",}, {"",}, {"",}, {"",}, - {"int_frac_digits", tok_int_frac_digits, 0}, - {"",}, {"",}, {"",}, {"",}, - {"alt_digits", tok_alt_digits, 0}, + {"yesexpr", tok_yesexpr, 0}, + {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, + {"graph", tok_graph, 0}, {"",}, {"",}, {"",}, {"",}, {"am_pm", tok_am_pm, 0}, + {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, + {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, {"",}, - {"alnum", tok_alnum, 0}, - {"",}, - {"mon_grouping", tok_mon_grouping, 0}, + {"era_year", tok_era_year, 0}, }; if (len <= MAX_WORD_LENGTH && len >= MIN_WORD_LENGTH) diff --git a/locale/programs/locfile-token.h b/locale/programs/locfile-token.h index 6d1543c320..7845b4ba76 100644 --- a/locale/programs/locfile-token.h +++ b/locale/programs/locfile-token.h @@ -1,4 +1,4 @@ -/* Copyright (C) 1996, 1997 Free Software Foundation, Inc. +/* Copyright (C) 1996, 1997, 1998 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Ulrich Drepper , 1996. @@ -49,6 +49,8 @@ enum token_t tok_g2esc, tok_g3esc, + tok_charids, + tok_code_set_name, tok_mb_cur_max, tok_mb_cur_min, @@ -56,6 +58,7 @@ enum token_t tok_width, tok_width_variable, tok_width_default, + tok_repertoiremap, tok_lc_ctype, tok_copy, diff --git a/locale/programs/locfile.h b/locale/programs/locfile.h index 604e726e20..697af64979 100644 --- a/locale/programs/locfile.h +++ b/locale/programs/locfile.h @@ -1,4 +1,4 @@ -/* Copyright (C) 1996, 1997 Free Software Foundation, Inc. +/* Copyright (C) 1996, 1997, 1998 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Ulrich Drepper , 1996. @@ -55,6 +55,7 @@ struct localedef_t /* Declared in localedef.c. */ extern int be_quiet; +extern const char *repertoiremap; /* Found in localedef.c. */ void def_to_process (const char *name, int category); diff --git a/locale/programs/repertoire.c b/locale/programs/repertoire.c new file mode 100644 index 0000000000..1f219ec81f --- /dev/null +++ b/locale/programs/repertoire.c @@ -0,0 +1,323 @@ +/* Copyright (C) 1998 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Ulrich Drepper , 1998. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Library General Public License as + published by the Free Software Foundation; either version 2 of the + License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with the GNU C Library; see the file COPYING.LIB. If not, + write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, + Boston, MA 02111-1307, USA. */ + +#ifdef HAVE_CONFIG_H +# include +#endif + +#include +#include +#include +#include +#include +#include + +#include "linereader.h" +#include "charset.h" +#include "repertoire.h" +#include "simple-hash.h" + + +extern void *xmalloc (size_t __n); + + +/* Simple keyword hashing for the repertoiremap. */ +static struct repertoire_t *parse_repertoiremap (const char *filename); +static const struct keyword_t *repertoiremap_hash (const char *str, int len); + + +struct repertoire_t * +repertoire_read (const char *filename) +{ + const char *pathnfile; + struct repertoire_t *result = NULL; + + if (euidaccess (filename, R_OK) >= 0) + pathnfile = filename; + else if (filename[0] != '/') + { + char *cp = xmalloc (strlen (filename) + sizeof CHARMAP_PATH + 1); + stpcpy (stpcpy (stpcpy (cp, CHARMAP_PATH), "/"), filename); + + pathnfile = (const char *) cp; + } + else + pathnfile = NULL; + + if (pathnfile != NULL) + { + result = parse_repertoiremap (pathnfile); + + if (result == NULL && !be_quiet) + error (0, errno, _("repertoire map file `%s' not found"), filename); + } + + return result; +} + + +static struct repertoire_t * +parse_repertoiremap (const char *filename) +{ + struct linereader *cmfile; + struct repertoire_t *result; + int state; + char *from_name = NULL; + char *to_name = NULL; + + /* Determine path. */ + cmfile = lr_open (filename, repertoiremap_hash); + if (cmfile == NULL) + { + if (strchr (filename, '/') == NULL) + { + /* Look in the systems charmap directory. */ + char *buf = xmalloc (strlen (filename) + 1 + + sizeof (REPERTOIREMAP_PATH)); + + stpcpy (stpcpy (stpcpy (buf, REPERTOIREMAP_PATH), "/"), filename); + cmfile = lr_open (buf, repertoiremap_hash); + + if (cmfile == NULL) + free (buf); + } + + if (cmfile == NULL) + return NULL; + } + + /* Allocate room for result. */ + result = (struct repertoire_t *) xmalloc (sizeof (struct repertoire_t)); + memset (result, '\0', sizeof (struct repertoire_t)); + +#define obstack_chunk_alloc malloc +#define obstack_chunk_free free + obstack_init (&result->mem_pool); + + if (init_hash (&result->char_table, 256)) + { + free (result); + return NULL; + } + + /* We use a state machine to describe the charmap description file + format. */ + state = 1; + while (1) + { + /* What's on? */ + struct token *now = lr_token (cmfile, NULL); + enum token_t nowtok = now->tok; + struct token *arg; + + if (nowtok == tok_eof) + break; + + switch (state) + { + case 1: + /* We haven't yet read any character definition. This is where + we accept escape_char and comment_char definitions. */ + if (nowtok == tok_eol) + /* Ignore empty lines. */ + continue; + + if (nowtok == tok_escape_char || nowtok == tok_comment_char) + { + /* We know that we need an argument. */ + arg = lr_token (cmfile, NULL); + + if (arg->tok != tok_ident) + { + lr_error (cmfile, _("syntax error in prolog: %s"), + _("bad argument")); + + lr_ignore_rest (cmfile, 0); + continue; + } + + if (arg->val.str.len != 1) + { + lr_error (cmfile, _("\ +argument to <%s> must be a single character"), + nowtok == tok_escape_char ? "escape_char" + : "comment_char"); + + lr_ignore_rest (cmfile, 0); + continue; + } + + if (nowtok == tok_escape_char) + cmfile->escape_char = *arg->val.str.start; + else + cmfile->comment_char = *arg->val.str.start; + + lr_ignore_rest (cmfile, 1); + continue; + } + + if (nowtok == tok_charids) + { + lr_ignore_rest (cmfile, 1); + + state = 2; + continue; + } + + /* Otherwise we start reading the character definitions. */ + state = 2; + /* FALLTHROUGH */ + + case 2: + /* We are now are in the body. Each line + must have the format "%s %s %s\n" or "%s...%s %s %s\n". */ + if (nowtok == tok_eol) + /* Ignore empty lines. */ + continue; + + if (nowtok == tok_end) + { + state = 90; + continue; + } + + if (nowtok != tok_bsymbol) + { + lr_error (cmfile, + _("syntax error in repertoire map definition: %s"), + _("no symbolic name given")); + + lr_ignore_rest (cmfile, 0); + continue; + } + + /* If the previous line was not completely correct free the + used memory. */ + if (from_name != NULL) + obstack_free (&result->mem_pool, from_name); + + from_name = (char *) obstack_copy0 (&result->mem_pool, + now->val.str.start, + now->val.str.len); + to_name = NULL; + + state = 3; + continue; + + case 3: + /* We have two possibilities: We can see an ellipsis or an + encoding value. */ + if (nowtok == tok_ellipsis) + { + state = 4; + continue; + } + /* FALLTHROUGH */ + + case 5: + /* We expect a value of the form or where + the xxx mean a hexadecimal value. */ + state = 2; + + errno = 0; + if (nowtok != tok_ucs2 && nowtok != tok_ucs4) + { + lr_error (cmfile, + _("syntax error in repertoire map definition: %s"), + _("no or value given")); + + lr_ignore_rest (cmfile, 0); + continue; + } + + /* We've found a new valid definition. */ + charset_new_char (cmfile, &result->char_table, 4, + now->val.charcode.val, from_name, to_name); + + /* Ignore the rest of the line. */ + lr_ignore_rest (cmfile, 0); + + from_name = NULL; + to_name = NULL; + + continue; + + case 4: + if (nowtok != tok_bsymbol) + { + lr_error (cmfile, + _("syntax error in repertoire map definition: %s"), + _("no symbolic name given for end of range")); + + lr_ignore_rest (cmfile, 0); + state = 2; + continue; + } + + /* Copy the to-name in a safe place. */ + to_name = (char *) obstack_copy0 (&result->mem_pool, + cmfile->token.val.str.start, + cmfile->token.val.str.len); + + state = 5; + continue; + + case 90: + if (nowtok != tok_charids) + lr_error (cmfile, _("\ +`%1$s' definition does not end with `END %1$s'"), "CHARIDS"); + + lr_ignore_rest (cmfile, nowtok == tok_charids); + break; + } + + break; + } + + if (state != 2 && state != 90 && !be_quiet) + error (0, 0, _("%s: premature end of file"), cmfile->fname); + + lr_close (cmfile); + + return result; +} + + +static const struct keyword_t * +repertoiremap_hash (const char *str, int len) +{ + static const struct keyword_t wordlist[0] = + { + {"escape_char", tok_escape_char, 1}, + {"comment_char", tok_comment_char, 1}, + {"CHARIDS", tok_charids, 0}, + {"END", tok_end, 0}, + }; + + if (len == 11 && memcmp (wordlist[0].name, str, 11) == 0) + return &wordlist[0]; + if (len == 12 && memcmp (wordlist[1].name, str, 12) == 0) + return &wordlist[1]; + if (len == 7 && memcmp (wordlist[2].name, str, 7) == 0) + return &wordlist[2]; + if (len == 3 && memcmp (wordlist[3].name, str, 3) == 0) + return &wordlist[3]; + + return NULL; +} diff --git a/locale/programs/repertoire.h b/locale/programs/repertoire.h new file mode 100644 index 0000000000..7befeb4e0d --- /dev/null +++ b/locale/programs/repertoire.h @@ -0,0 +1,38 @@ +/* Copyright (C) 1998 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Ulrich Drepper , 1998. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Library General Public License as + published by the Free Software Foundation; either version 2 of the + License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Library General Public License for more details. + + You should have received a copy of the GNU Library General Public + License along with the GNU C Library; see the file COPYING.LIB. If not, + write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, + Boston, MA 02111-1307, USA. */ + +#ifndef _REPERTOIREMAP_H +#define _REPERTOIREMAP_H 1 + +#include + +#include "simple-hash.h" +#include "linereader.h" + +struct repertoire_t +{ + struct obstack mem_pool; + hash_table char_table; +}; + + +/* Prototypes for repertoire map handling functions. */ +struct repertoire_t *repertoire_read (const char *filename); + +#endif /* repertoiremap.h */ diff --git a/locale/programs/stringtrans.c b/locale/programs/stringtrans.c index 34b107e295..b810129678 100644 --- a/locale/programs/stringtrans.c +++ b/locale/programs/stringtrans.c @@ -1,4 +1,4 @@ -/* Copyright (C) 1996, 1997 Free Software Foundation, Inc. +/* Copyright (C) 1996, 1997, 1998 Free Software Foundation, Inc. This file is part of the GNU C Library. Contributed by Ulrich Drepper , 1996. @@ -92,7 +92,8 @@ translate_string (char *str, struct charset_t *charset) return NULL; } - value = charset_find_value (charset, str + 1, tp - (str + 1)); + value = charset_find_value (&charset->char_table, str + 1, + tp - (str + 1)); if ((wchar_t) value == ILLEGAL_CHAR_VALUE) { free (buf); diff --git a/localedata/ChangeLog b/localedata/ChangeLog index 7a74d1f089..8ec112fb74 100644 --- a/localedata/ChangeLog +++ b/localedata/ChangeLog @@ -1,3 +1,10 @@ +1998-04-30 Ulrich Drepper + + * Makefile: Install repertoire maps. + * localedata/mnemonic.ds: Moved into repertoiremaps subdir. + * localedata/repertoiremaps/charids.894: New file. + * localedata/repertoiremaps/mnemonic.ds: New file. + 1998-04-29 Ulrich Drepper * tst-locale.sh: Add comment for when multi-byte charsets in diff --git a/localedata/Makefile b/localedata/Makefile index 9be179abed..c4370d8082 100644 --- a/localedata/Makefile +++ b/localedata/Makefile @@ -30,6 +30,10 @@ charmaps := $(filter-out $(addprefix charmaps/, CVS RCS %~), \ locales := $(filter-out $(addprefix locales/, CVS RCS %~), \ $(wildcard locales/*)) +# List of repertoire maps. +repertoires := $(filter-out $(addprefix repertoiremaps/, CVS RCS %~), \ + $(wildcard repertoiremaps/*)) + test-srcs := collate-test xfrm-test tst-fmon tst-rpmatch test-input := de_DE.ISO-8859-1 da_DK.ISO-8859-1 fr_CA,2.13.ISO-8859-1 test-output := $(foreach s, .out .xout, \ @@ -42,7 +46,7 @@ ld-test-srcs := $(addprefix tests/,$(addsuffix .cm,$(ld-test-names)) \ $(addsuffix .def,$(ld-test-names))) distribute := CHECKSUMS tst-fmon.sh tst-fmon.data ChangeLog sort-test.sh \ - README mnemonic.ds fr_CA,2.13.in de_DE.in da_DK.in \ + README fr_CA,2.13.in de_DE.in da_DK.in $(repertoiremaps) \ $(charmaps) $(locales) $(ld-test-srcs) tst-rpmatch.sh \ SUPPORTED tst-locale.sh @@ -50,13 +54,15 @@ distribute := CHECKSUMS tst-fmon.sh tst-fmon.data ChangeLog sort-test.sh \ include ../Makeconfig # Files to install. -install-others := $(addprefix $(inst_i18ndir)/, $(charmaps) $(locales)) +install-others := $(addprefix $(inst_i18ndir)/, $(charmaps) $(locales) \ + $(repertoiremaps)) include ../Rules # Install the source files in the appropriate directories. $(inst_i18ndir)/charmaps/%: charmaps/% $(+force); $(do-install) $(inst_i18ndir)/locales/%: locales/% $(+force); $(do-install) +$(inst_i18ndir)/repertoiremaps/%: repertoiremaps/% $(+force); $(do-install) ifeq (no,$(cross-compiling)) diff --git a/localedata/mnemonic.ds b/localedata/mnemonic.ds deleted file mode 100644 index abeab6b4b9..0000000000 --- a/localedata/mnemonic.ds +++ /dev/null @@ -1,1967 +0,0 @@ -escape_char / - NULL (NUL) - START OF HEADING (SOH) - START OF TEXT (STX) - END OF TEXT (ETX) - END OF TRANSMISSION (EOT) - ENQUIRY (ENQ) - ACKNOWLEDGE (ACK) - BELL (BEL) - BELL (BEL) - BACKSPACE (BS) - CHARACTER TABULATION (HT) - LINE FEED (LF) - LINE TABULATION (VT) - FORM FEED (FF) - CARRIAGE RETURN (CR) - DATALINK ESCAPE (DLE) - DEVICE CONTROL ONE (DC1) - DEVICE CONTROL TWO (DC2) - DEVICE CONTROL THREE (DC3) - DEVICE CONTROL FOUR (DC4) - NEGATIVE ACKNOWLEDGE (NAK) - SYNCRONOUS IDLE (SYN) - END OF TRANSMISSION BLOCK (ETB) - CANCEL (CAN) - SUBSTITUTE (SUB) - ESCAPE (ESC) - FILE SEPARATOR (IS4) - GROUP SEPARATOR (IS3) - GROUP SEPARATOR (IS3) - RECORD SEPARATOR (IS2) - UNIT SEPARATOR (IS1) - DELETE (DEL) - SPACE - EXCLAMATION MARK - QUOTATION MARK - NUMBER SIGN - DOLLAR SIGN - PERCENT SIGN - AMPERSAND - APOSTROPHE - LEFT PARENTHESIS - RIGHT PARENTHESIS - ASTERISK - PLUS SIGN - COMMA - HYPHEN-MINUS - HYPHEN-MINUS - FULL STOP - FULL STOP - SOLIDUS - SOLIDUS - DIGIT ZERO - DIGIT ONE - DIGIT TWO - DIGIT THREE - DIGIT FOUR - DIGIT FIVE - DIGIT SIX - DIGIT SEVEN - DIGIT EIGHT - DIGIT NINE - COLON - SEMICOLON - LESS-THAN SIGN - EQUALS SIGN - GREATER-THAN SIGN - QUESTION MARK - COMMERCIAL AT - LEFT SQUARE BRACKET - REVERSE SOLIDUS - REVERSE SOLIDUS - RIGHT SQUARE BRACKET - CIRCUMFLEX ACCENT - CIRCUMFLEX ACCENT - LOW LINE - LOW LINE - GRAVE ACCENT - LEFT CURLY BRACKET - LEFT CURLY BRACKET - VERTICAL LINE - RIGHT CURLY BRACKET - RIGHT CURLY BRACKET - TILDE - SPACE - EXCLAMATION MARK -<"> QUOTATION MARK - NUMBER SIGN - DOLLAR SIGN -<%> PERCENT SIGN -<&> AMPERSAND -<'> APOSTROPHE -<(> LEFT PARENTHESIS -<)> RIGHT PARENTHESIS -<*> ASTERISK -<+> PLUS SIGN -<,> COMMA -<-> HYPHEN-MINUS -<.> FULL STOP - SOLIDUS -<0> DIGIT ZERO -<1> DIGIT ONE -<2> DIGIT TWO -<3> DIGIT THREE -<4> DIGIT FOUR -<5> DIGIT FIVE -<6> DIGIT SIX -<7> DIGIT SEVEN -<8> DIGIT EIGHT -<9> DIGIT NINE -<:> COLON -<;> SEMICOLON -<<> LESS-THAN SIGN -<=> EQUALS SIGN -> GREATER-THAN SIGN - QUESTION MARK - COMMERCIAL AT - LATIN CAPITAL LETTER A - LATIN CAPITAL LETTER B - LATIN CAPITAL LETTER C - LATIN CAPITAL LETTER D - LATIN CAPITAL LETTER E - LATIN CAPITAL LETTER F - LATIN CAPITAL LETTER G - LATIN CAPITAL LETTER H - LATIN CAPITAL LETTER I - LATIN CAPITAL LETTER J - LATIN CAPITAL LETTER K - LATIN CAPITAL LETTER L - LATIN CAPITAL LETTER M - LATIN CAPITAL LETTER N - LATIN CAPITAL LETTER O -

LATIN SMALL LETTER P - LATIN SMALL LETTER Q - LATIN SMALL LETTER R - LATIN SMALL LETTER S - LATIN SMALL LETTER T - LATIN SMALL LETTER U - LATIN SMALL LETTER V - LATIN SMALL LETTER W - LATIN SMALL LETTER X - LATIN SMALL LETTER Y - LATIN SMALL LETTER Z -<(!> LEFT CURLY BRACKET - VERTICAL LINE - RIGHT CURLY BRACKET -<'?> TILDE - NO-BREAK SPACE - INVERTED EXCLAMATION MARK - CENT SIGN - POUND SIGN - CURRENCY SIGN - YEN SIGN - BROKEN BAR - SECTION SIGN -<':> DIAERESIS - COPYRIGHT SIGN -<-a> FEMININE ORDINAL INDICATOR -<<<> LEFT-POINTING DOUBLE ANGLE QUOTATION MARK - NOT SIGN -<--> SOFT HYPHEN - REGISTERED SIGN -<'m> MACRON - DEGREE SIGN -<+-> PLUS-MINUS SIGN -<2S> SUPERSCRIPT TWO -<3S> SUPERSCRIPT THREE -<''> ACUTE ACCENT - MICRO SIGN - PILCROW SIGN -<.M> MIDDLE DOT -<',> CEDILLA -<1S> SUPERSCRIPT ONE -<-o> MASCULINE ORDINAL INDICATOR -/>> RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK -<14> VULGAR FRACTION ONE QUARTER -<12> VULGAR FRACTION ONE HALF -<34> VULGAR FRACTION THREE QUARTERS - INVERTED QUESTION MARK - LATIN CAPITAL LETTER A WITH GRAVE - LATIN CAPITAL LETTER A WITH ACUTE -> LATIN CAPITAL LETTER A WITH CIRCUMFLEX - LATIN CAPITAL LETTER A WITH TILDE - LATIN CAPITAL LETTER A WITH DIAERESIS - LATIN CAPITAL LETTER A WITH RING ABOVE - LATIN CAPITAL LETTER AE - LATIN CAPITAL LETTER C WITH CEDILLA - LATIN CAPITAL LETTER E WITH GRAVE - LATIN CAPITAL LETTER E WITH ACUTE -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX - LATIN CAPITAL LETTER E WITH DIAERESIS - LATIN CAPITAL LETTER I WITH GRAVE - LATIN CAPITAL LETTER I WITH ACUTE -> LATIN CAPITAL LETTER I WITH CIRCUMFLEX - LATIN CAPITAL LETTER I WITH DIAERESIS - LATIN CAPITAL LETTER ETH (Icelandic) - LATIN CAPITAL LETTER N WITH TILDE - LATIN CAPITAL LETTER O WITH GRAVE - LATIN CAPITAL LETTER O WITH ACUTE -> LATIN CAPITAL LETTER O WITH CIRCUMFLEX - LATIN CAPITAL LETTER O WITH TILDE - LATIN CAPITAL LETTER O WITH DIAERESIS -<*X> MULTIPLICATION SIGN - LATIN CAPITAL LETTER O WITH STROKE - LATIN CAPITAL LETTER U WITH GRAVE - LATIN CAPITAL LETTER U WITH ACUTE -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX - LATIN CAPITAL LETTER U WITH DIAERESIS - LATIN CAPITAL LETTER Y WITH ACUTE - LATIN CAPITAL LETTER THORN (Icelandic) - LATIN SMALL LETTER SHARP S (German) - LATIN SMALL LETTER A WITH GRAVE - LATIN SMALL LETTER A WITH ACUTE -> LATIN SMALL LETTER A WITH CIRCUMFLEX - LATIN SMALL LETTER A WITH TILDE - LATIN SMALL LETTER A WITH DIAERESIS - LATIN SMALL LETTER A WITH RING ABOVE - LATIN SMALL LETTER AE - LATIN SMALL LETTER C WITH CEDILLA - LATIN SMALL LETTER E WITH GRAVE - LATIN SMALL LETTER E WITH ACUTE -> LATIN SMALL LETTER E WITH CIRCUMFLEX - LATIN SMALL LETTER E WITH DIAERESIS - LATIN SMALL LETTER I WITH GRAVE - LATIN SMALL LETTER I WITH ACUTE -> LATIN SMALL LETTER I WITH CIRCUMFLEX - LATIN SMALL LETTER I WITH DIAERESIS - LATIN SMALL LETTER ETH (Icelandic) - LATIN SMALL LETTER N WITH TILDE - LATIN SMALL LETTER O WITH GRAVE - LATIN SMALL LETTER O WITH ACUTE -> LATIN SMALL LETTER O WITH CIRCUMFLEX - LATIN SMALL LETTER O WITH TILDE - LATIN SMALL LETTER O WITH DIAERESIS -<-:> DIVISION SIGN - LATIN SMALL LETTER O WITH STROKE - LATIN SMALL LETTER U WITH GRAVE - LATIN SMALL LETTER U WITH ACUTE -> LATIN SMALL LETTER U WITH CIRCUMFLEX - LATIN SMALL LETTER U WITH DIAERESIS - LATIN SMALL LETTER Y WITH ACUTE - LATIN SMALL LETTER THORN (Icelandic) - LATIN SMALL LETTER Y WITH DIAERESIS - LATIN CAPITAL LETTER A WITH MACRON - LATIN SMALL LETTER A WITH MACRON - LATIN CAPITAL LETTER A WITH BREVE - LATIN SMALL LETTER A WITH BREVE - LATIN CAPITAL LETTER A WITH OGONEK - LATIN SMALL LETTER A WITH OGONEK - LATIN CAPITAL LETTER C WITH ACUTE - LATIN SMALL LETTER C WITH ACUTE -> LATIN CAPITAL LETTER C WITH CIRCUMFLEX -> LATIN SMALL LETTER C WITH CIRCUMFLEX - LATIN CAPITAL LETTER C WITH DOT ABOVE - LATIN SMALL LETTER C WITH DOT ABOVE - LATIN CAPITAL LETTER C WITH CARON - LATIN SMALL LETTER C WITH CARON - LATIN CAPITAL LETTER D WITH CARON - LATIN SMALL LETTER D WITH CARON - LATIN CAPITAL LETTER D WITH STROKE - LATIN SMALL LETTER D WITH STROKE - LATIN CAPITAL LETTER E WITH MACRON - LATIN SMALL LETTER E WITH MACRON - LATIN CAPITAL LETTER E WITH BREVE - LATIN SMALL LETTER E WITH BREVE - LATIN CAPITAL LETTER E WITH DOT ABOVE - LATIN SMALL LETTER E WITH DOT ABOVE - LATIN CAPITAL LETTER E WITH OGONEK - LATIN SMALL LETTER E WITH OGONEK - LATIN CAPITAL LETTER E WITH CARON - LATIN SMALL LETTER E WITH CARON -> LATIN CAPITAL LETTER G WITH CIRCUMFLEX -> LATIN SMALL LETTER G WITH CIRCUMFLEX - LATIN CAPITAL LETTER G WITH BREVE - LATIN SMALL LETTER G WITH BREVE - LATIN CAPITAL LETTER G WITH DOT ABOVE - LATIN SMALL LETTER G WITH DOT ABOVE - LATIN CAPITAL LETTER G WITH CEDILLA - LATIN SMALL LETTER G WITH CEDILLA -> LATIN CAPITAL LETTER H WITH CIRCUMFLEX -> LATIN SMALL LETTER H WITH CIRCUMFLEX - LATIN CAPITAL LETTER H WITH STROKE - LATIN SMALL LETTER H WITH STROKE - LATIN CAPITAL LETTER I WITH TILDE - LATIN SMALL LETTER I WITH TILDE - LATIN CAPITAL LETTER I WITH MACRON - LATIN SMALL LETTER I WITH MACRON - LATIN CAPITAL LETTER I WITH BREVE - LATIN SMALL LETTER I WITH BREVE - LATIN CAPITAL LETTER I WITH OGONEK - LATIN SMALL LETTER I WITH OGONEK - LATIN CAPITAL LETTER I WITH DOT ABOVE - LATIN SMALL LETTER DOTLESS I - LATIN CAPITAL LIGATURE IJ - LATIN SMALL LIGATURE IJ -> LATIN CAPITAL LETTER J WITH CIRCUMFLEX -> LATIN SMALL LETTER J WITH CIRCUMFLEX - LATIN CAPITAL LETTER K WITH CEDILLA - LATIN SMALL LETTER K WITH CEDILLA - LATIN SMALL LETTER KRA (Greenlandic) - LATIN CAPITAL LETTER L WITH ACUTE - LATIN SMALL LETTER L WITH ACUTE - LATIN CAPITAL LETTER L WITH CEDILLA - LATIN SMALL LETTER L WITH CEDILLA - LATIN CAPITAL LETTER L WITH CARON - LATIN SMALL LETTER L WITH CARON - LATIN CAPITAL LETTER L WITH MIDDLE DOT - LATIN SMALL LETTER L WITH MIDDLE DOT - LATIN CAPITAL LETTER L WITH STROKE - LATIN SMALL LETTER L WITH STROKE - LATIN CAPITAL LETTER N WITH ACUTE - LATIN SMALL LETTER N WITH ACUTE - LATIN CAPITAL LETTER N WITH CEDILLA - LATIN SMALL LETTER N WITH CEDILLA - LATIN CAPITAL LETTER N WITH CARON - LATIN SMALL LETTER N WITH CARON -<'n> LATIN SMALL LETTER N PRECEDED BY APOSTROPHE - LATIN CAPITAL LETTER ENG (Sami) - LATIN SMALL LETTER ENG (Sami) - LATIN CAPITAL LETTER O WITH MACRON - LATIN SMALL LETTER O WITH MACRON - LATIN CAPITAL LETTER O WITH BREVE - LATIN SMALL LETTER O WITH BREVE - LATIN CAPITAL LETTER O WITH DOUBLE ACUTE - LATIN SMALL LETTER O WITH DOUBLE ACUTE - LATIN CAPITAL LIGATURE OE - LATIN SMALL LIGATURE OE - LATIN CAPITAL LETTER R WITH ACUTE - LATIN SMALL LETTER R WITH ACUTE - LATIN CAPITAL LETTER R WITH CEDILLA - LATIN SMALL LETTER R WITH CEDILLA - LATIN CAPITAL LETTER R WITH CARON - LATIN SMALL LETTER R WITH CARON - LATIN CAPITAL LETTER S WITH ACUTE - LATIN SMALL LETTER S WITH ACUTE -> LATIN CAPITAL LETTER S WITH CIRCUMFLEX -> LATIN SMALL LETTER S WITH CIRCUMFLEX - LATIN CAPITAL LETTER S WITH CEDILLA - LATIN SMALL LETTER S WITH CEDILLA - LATIN CAPITAL LETTER S WITH CARON - LATIN SMALL LETTER S WITH CARON - LATIN CAPITAL LETTER T WITH CEDILLA - LATIN SMALL LETTER T WITH CEDILLA - LATIN CAPITAL LETTER T WITH CARON - LATIN SMALL LETTER T WITH CARON - LATIN CAPITAL LETTER T WITH STROKE - LATIN SMALL LETTER T WITH STROKE - LATIN CAPITAL LETTER U WITH TILDE - LATIN SMALL LETTER U WITH TILDE - LATIN CAPITAL LETTER U WITH MACRON - LATIN SMALL LETTER U WITH MACRON - LATIN CAPITAL LETTER U WITH BREVE - LATIN SMALL LETTER U WITH BREVE - LATIN CAPITAL LETTER U WITH RING ABOVE - LATIN SMALL LETTER U WITH RING ABOVE - LATIN CAPITAL LETTER U WITH DOUBLE ACUTE - LATIN SMALL LETTER U WITH DOUBLE ACUTE - LATIN CAPITAL LETTER U WITH OGONEK - LATIN SMALL LETTER U WITH OGONEK -> LATIN CAPITAL LETTER W WITH CIRCUMFLEX -> LATIN SMALL LETTER W WITH CIRCUMFLEX -> LATIN CAPITAL LETTER Y WITH CIRCUMFLEX -> LATIN SMALL LETTER Y WITH CIRCUMFLEX - LATIN CAPITAL LETTER Y WITH DIAERESIS - LATIN CAPITAL LETTER Z WITH ACUTE - LATIN SMALL LETTER Z WITH ACUTE - LATIN CAPITAL LETTER Z WITH DOT ABOVE - LATIN SMALL LETTER Z WITH DOT ABOVE - LATIN CAPITAL LETTER Z WITH CARON - LATIN SMALL LETTER Z WITH CARON - LATIN SMALL LETTER LONG S - LATIN CAPITAL LETTER C WITH HOOK - LATIN SMALL LETTER C WITH HOOK - LATIN CAPITAL LETTER F WITH HOOK - LATIN SMALL LETTER F WITH HOOK - LATIN CAPITAL LETTER K WITH HOOK - LATIN SMALL LETTER K WITH HOOK - LATIN CAPITAL LETTER O WITH HORN - LATIN SMALL LETTER O WITH HORN - LATIN CAPITAL LETTER OI - LATIN SMALL LETTER OI - LATIN LETTER YR - LATIN CAPITAL LETTER U WITH HORN - LATIN SMALL LETTER U WITH HORN - LATIN CAPITAL LETTER Z WITH STROKE - LATIN SMALL LETTER Z WITH STROKE - LATIN CAPITAL LETTER EZH - LATIN CAPITAL LETTER A WITH CARON - LATIN SMALL LETTER A WITH CARON - LATIN CAPITAL LETTER I WITH CARON - LATIN SMALL LETTER I WITH CARON - LATIN CAPITAL LETTER O WITH CARON - LATIN SMALL LETTER O WITH CARON - LATIN CAPITAL LETTER U WITH CARON - LATIN SMALL LETTER U WITH CARON - LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON - LATIN SMALL LETTER U WITH DIAERESIS AND MACRON - LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE - LATIN SMALL LETTER U WITH DIAERESIS AND ACUTE - LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON - LATIN SMALL LETTER U WITH DIAERESIS AND CARON - LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE - LATIN SMALL LETTER U WITH DIAERESIS AND GRAVE - LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON - LATIN SMALL LETTER A WITH DIAERESIS AND MACRON - LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON - LATIN SMALL LETTER A WITH DOT ABOVE AND MACRON - LATIN CAPITAL LETTER AE WITH MACRON - LATIN SMALL LETTER AE WITH MACRON - LATIN CAPITAL LETTER G WITH STROKE - LATIN SMALL LETTER G WITH STROKE - LATIN CAPITAL LETTER G WITH CARON - LATIN SMALL LETTER G WITH CARON - LATIN CAPITAL LETTER K WITH CARON - LATIN SMALL LETTER K WITH CARON - LATIN CAPITAL LETTER O WITH OGONEK - LATIN SMALL LETTER O WITH OGONEK - LATIN CAPITAL LETTER O WITH OGONEK AND MACRON - LATIN SMALL LETTER O WITH OGONEK AND MACRON - LATIN CAPITAL LETTER EZH WITH CARON - LATIN SMALL LETTER EZH WITH CARON - LATIN CAPITAL LETTER G WITH ACUTE - LATIN SMALL LETTER G WITH ACUTE - LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE - LATIN SMALL LETTER A WITH RING ABOVE AND ACUTE - LATIN CAPITAL LETTER AE WITH ACUTE - LATIN SMALL LETTER AE WITH ACUTE - LATIN CAPITAL LETTER O WITH STROKE AND ACUTE - LATIN SMALL LETTER O WITH STROKE AND ACUTE - LATIN CAPITAL LETTER A WITH DOUBLE GRAVE - LATIN SMALL LETTER A WITH DOUBLE GRAVE - LATIN CAPITAL LETTER A WITH INVERTED BREVE - LATIN SMALL LETTER A WITH INVERTED BREVE - LATIN CAPITAL LETTER E WITH DOUBLE GRAVE - LATIN SMALL LETTER E WITH DOUBLE GRAVE - LATIN CAPITAL LETTER E WITH INVERTED BREVE - LATIN SMALL LETTER E WITH INVERTED BREVE - LATIN CAPITAL LETTER I WITH DOUBLE GRAVE - LATIN SMALL LETTER I WITH DOUBLE GRAVE - LATIN CAPITAL LETTER I WITH INVERTED BREVE - LATIN SMALL LETTER I WITH INVERTED BREVE - LATIN CAPITAL LETTER O WITH DOUBLE GRAVE - LATIN SMALL LETTER O WITH DOUBLE GRAVE - LATIN CAPITAL LETTER O WITH INVERTED BREVE - LATIN SMALL LETTER O WITH INVERTED BREVE - LATIN CAPITAL LETTER R WITH DOUBLE GRAVE - LATIN SMALL LETTER R WITH DOUBLE GRAVE - LATIN CAPITAL LETTER R WITH INVERTED BREVE - LATIN SMALL LETTER R WITH INVERTED BREVE - LATIN CAPITAL LETTER U WITH DOUBLE GRAVE - LATIN SMALL LETTER U WITH DOUBLE GRAVE - LATIN CAPITAL LETTER U WITH INVERTED BREVE - LATIN SMALL LETTER U WITH INVERTED BREVE - LATIN SMALL LETTER EZH -<;S> MODIFIER LETTER TURNED COMMA -<1/>> MODIFIER LETTER CIRCUMFLEX ACCENT -<'<> CARON (Mandarin Chinese third tone) -<1!> MODIFIER LETTER GRAVE ACCENT -<'(> BREVE -<'.> DOT ABOVE (Mandarin Chinese light tone) -<'0> RING ABOVE -<';> OGONEK -<1?> SMALL TILDE -<'"> DOUBLE ACUTE ACCENT -<'G> GREEK NUMERAL SIGN (Dexia keraia) -<,G> GREEK LOWER NUMERAL SIGN (Aristeri keraia) - GREEK YPOGEGRAMMENI - GREEK QUESTION MARK (Erotimatiko) -<'*> GREEK TONOS -<'%> GREEK DIALYTIKA TONOS - GREEK CAPITAL LETTER ALPHA WITH TONOS -<.*> GREEK ANO TELEIA - GREEK CAPITAL LETTER EPSILON WITH TONOS - GREEK CAPITAL LETTER ETA WITH TONOS - GREEK CAPITAL LETTER IOTA WITH TONOS - GREEK CAPITAL LETTER OMICRON WITH TONOS - GREEK CAPITAL LETTER UPSILON WITH TONOS - GREEK CAPITAL LETTER OMEGA WITH TONOS - GREEK SMALL LETTER IOTA WITH DIALYTICA AND TONOS - GREEK CAPITAL LETTER ALPHA - GREEK CAPITAL LETTER BETA - GREEK CAPITAL LETTER GAMMA - GREEK CAPITAL LETTER DELTA - GREEK CAPITAL LETTER EPSILON - GREEK CAPITAL LETTER ZETA - GREEK CAPITAL LETTER ETA - GREEK CAPITAL LETTER THETA - GREEK CAPITAL LETTER IOTA - GREEK CAPITAL LETTER KAPPA - GREEK CAPITAL LETTER LAMDA - GREEK CAPITAL LETTER MU - GREEK CAPITAL LETTER NU - GREEK CAPITAL LETTER XI - GREEK CAPITAL LETTER OMICRON - GREEK CAPITAL LETTER PI - GREEK CAPITAL LETTER RHO - GREEK CAPITAL LETTER SIGMA - GREEK CAPITAL LETTER TAU - GREEK CAPITAL LETTER UPSILON - GREEK CAPITAL LETTER PHI - GREEK CAPITAL LETTER CHI - GREEK CAPITAL LETTER PSI - GREEK CAPITAL LETTER OMEGA - GREEK CAPITAL LETTER IOTA WITH DIALYTIKA - GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA - GREEK SMALL LETTER ALPHA WITH TONOS - GREEK SMALL LETTER EPSILON WITH TONOS - GREEK SMALL LETTER ETA WITH TONOS - GREEK SMALL LETTER IOTA WITH TONOS - GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS - GREEK SMALL LETTER ALPHA - GREEK SMALL LETTER BETA - GREEK SMALL LETTER GAMMA - GREEK SMALL LETTER DELTA - GREEK SMALL LETTER EPSILON - GREEK SMALL LETTER ZETA - GREEK SMALL LETTER ETA - GREEK SMALL LETTER THETA - GREEK SMALL LETTER IOTA - GREEK SMALL LETTER KAPPA - GREEK SMALL LETTER LAMDA - GREEK SMALL LETTER MU - GREEK SMALL LETTER NU - GREEK SMALL LETTER XI - GREEK SMALL LETTER OMICRON - GREEK SMALL LETTER PI - GREEK SMALL LETTER RHO -<*s> GREEK SMALL LETTER FINAL SIGMA - GREEK SMALL LETTER SIGMA - GREEK SMALL LETTER TAU - GREEK SMALL LETTER UPSILON - GREEK SMALL LETTER PHI - GREEK SMALL LETTER CHI - GREEK SMALL LETTER PSI - GREEK SMALL LETTER OMEGA - GREEK SMALL LETTER IOTA WITH DIALYTIKA - GREEK SMALL LETTER UPSILON WITH DIALYTIKA - GREEK SMALL LETTER OMICRON WITH TONOS - GREEK SMALL LETTER UPSILON WITH TONOS - GREEK SMALL LETTER OMEGA WITH TONOS - GREEK BETA SYMBOL - CYRILLIC CAPITAL LETTER IO - CYRILLIC CAPITAL LETTER DJE (Serbocroatian) - CYRILLIC CAPITAL LETTER GJE - CYRILLIC CAPITAL LETTER UKRAINIAN IE - CYRILLIC CAPITAL LETTER DZE - CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I - CYRILLIC CAPITAL LETTER YI (Ukrainian) - CYRILLIC CAPITAL LETTER JE - CYRILLIC CAPITAL LETTER LJE - CYRILLIC CAPITAL LETTER NJE - CYRILLIC CAPITAL LETTER TSHE (Serbocroatian) - CYRILLIC CAPITAL LETTER KJE - CYRILLIC CAPITAL LETTER SHORT U (Byelorussian) - CYRILLIC CAPITAL LETTER DZHE - CYRILLIC CAPITAL LETTER A - CYRILLIC CAPITAL LETTER BE - CYRILLIC CAPITAL LETTER VE - CYRILLIC CAPITAL LETTER GHE - CYRILLIC CAPITAL LETTER DE - CYRILLIC CAPITAL LETTER IE - CYRILLIC CAPITAL LETTER ZHE - CYRILLIC CAPITAL LETTER ZE - CYRILLIC CAPITAL LETTER I - CYRILLIC CAPITAL LETTER SHORT I - CYRILLIC CAPITAL LETTER KA - CYRILLIC CAPITAL LETTER EL - CYRILLIC CAPITAL LETTER EM - CYRILLIC CAPITAL LETTER EN - CYRILLIC CAPITAL LETTER O - CYRILLIC CAPITAL LETTER PE - CYRILLIC CAPITAL LETTER ER - CYRILLIC CAPITAL LETTER ES - CYRILLIC CAPITAL LETTER TE - CYRILLIC CAPITAL LETTER U - CYRILLIC CAPITAL LETTER EF - CYRILLIC CAPITAL LETTER HA - CYRILLIC CAPITAL LETTER TSE - CYRILLIC CAPITAL LETTER CHE - CYRILLIC CAPITAL LETTER SHA - CYRILLIC CAPITAL LETTER SHCHA -<="> CYRILLIC CAPITAL LETTER HARD SIGN - CYRILLIC CAPITAL LETTER YERU -<%"> CYRILLIC CAPITAL LETTER SOFT SIGN - CYRILLIC CAPITAL LETTER E - CYRILLIC CAPITAL LETTER YU - CYRILLIC CAPITAL LETTER YA - CYRILLIC SMALL LETTER A - CYRILLIC SMALL LETTER BE - CYRILLIC SMALL LETTER VE - CYRILLIC SMALL LETTER GHE - CYRILLIC SMALL LETTER DE - CYRILLIC SMALL LETTER IE - CYRILLIC SMALL LETTER ZHE - CYRILLIC SMALL LETTER ZE - CYRILLIC SMALL LETTER I - CYRILLIC SMALL LETTER SHORT I - CYRILLIC SMALL LETTER KA - CYRILLIC SMALL LETTER EL - CYRILLIC SMALL LETTER EM - CYRILLIC SMALL LETTER EN - CYRILLIC SMALL LETTER O - CYRILLIC SMALL LETTER PE - CYRILLIC SMALL LETTER ER - CYRILLIC SMALL LETTER ES - CYRILLIC SMALL LETTER TE - CYRILLIC SMALL LETTER U - CYRILLIC SMALL LETTER EF - CYRILLIC SMALL LETTER HA - CYRILLIC SMALL LETTER TSE - CYRILLIC SMALL LETTER CHE - CYRILLIC SMALL LETTER SHA - CYRILLIC SMALL LETTER SHCHA -<='> CYRILLIC SMALL LETTER HARD SIGN - CYRILLIC SMALL LETTER YERU -<%'> CYRILLIC SMALL LETTER SOFT SIGN - CYRILLIC SMALL LETTER E - CYRILLIC SMALL LETTER YU - CYRILLIC SMALL LETTER YA - CYRILLIC SMALL LETTER IO - CYRILLIC SMALL LETTER DJE (Serbocroatian) - CYRILLIC SMALL LETTER GJE - CYRILLIC SMALL LETTER UKRAINIAN IE - CYRILLIC SMALL LETTER DZE - CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I - CYRILLIC SMALL LETTER YI (Ukrainian) - CYRILLIC SMALL LETTER JE - CYRILLIC SMALL LETTER LJE - CYRILLIC SMALL LETTER NJE - CYRILLIC SMALL LETTER TSHE (Serbocroatian) - CYRILLIC SMALL LETTER KJE - CYRILLIC SMALL LETTER SHORT U (Byelorussian) - CYRILLIC SMALL LETTER DZHE - CYRILLIC CAPITAL LETTER YAT - CYRILLIC SMALL LETTER YAT - CYRILLIC CAPITAL LETTER BIG YUS - CYRILLIC SMALL LETTER BIG YUS - CYRILLIC CAPITAL LETTER FITA - CYRILLIC SMALL LETTER FITA - CYRILLIC CAPITAL LETTER IZHITSA - CYRILLIC SMALL LETTER IZHITSA - CYRILLIC CAPITAL LETTER KOPPA - CYRILLIC SMALL LETTER KOPPA - CYRILLIC CAPITAL LETTER GHE WITH UPTURN - CYRILLIC SMALL LETTER GHE WITH UPTURN - HEBREW LETTER ALEF - HEBREW LETTER BET - HEBREW LETTER GIMEL - HEBREW LETTER DALET - HEBREW LETTER HE - HEBREW LETTER VAV - HEBREW LETTER ZAYIN - HEBREW LETTER HET - HEBREW LETTER TET - HEBREW LETTER YOD - HEBREW LETTER FINAL KAF - HEBREW LETTER KAF - HEBREW LETTER LAMED - HEBREW LETTER FINAL MEM - HEBREW LETTER MEM - HEBREW LETTER FINAL NUN - HEBREW LETTER NUN - HEBREW LETTER SAMEKH - HEBREW LETTER AYIN - HEBREW LETTER FINAL PE - HEBREW LETTER PE - HEBREW LETTER FINAL TSADI - HEBREW LETTER TSADI - HEBREW LETTER QOF - HEBREW LETTER RESH - HEBREW LETTER SHIN - HEBREW LETTER TAV -<,+> ARABIC COMMA -<;+> ARABIC SEMICOLON - ARABIC QUESTION MARK - ARABIC LETTER HAMZA - ARABIC LETTER ALEF WITH MADDA ABOVE - ARABIC LETTER ALEF WITH HAMZA ABOVE - ARABIC LETTER WAW WITH HAMZA ABOVE - ARABIC LETTER ALEF WITH HAMZA BELOW - ARABIC LETTER YEH WITH HAMZA ABOVE - ARABIC LETTER ALEF - ARABIC LETTER BEH - ARABIC LETTER TEH MARBUTA - ARABIC LETTER TEH - ARABIC LETTER THEH - ARABIC LETTER JEEM - ARABIC LETTER HAH - ARABIC LETTER KHAH - ARABIC LETTER DAL - ARABIC LETTER THAL - ARABIC LETTER REH - ARABIC LETTER ZAIN - ARABIC LETTER SEEN - ARABIC LETTER SHEEN - ARABIC LETTER SAD -

ARABIC LETTER DAD - ARABIC LETTER TAH - ARABIC LETTER ZAH - ARABIC LETTER AIN - ARABIC LETTER GHAIN -<++> ARABIC TATWEEL - ARABIC LETTER FEH - ARABIC LETTER QAF - ARABIC LETTER KAF - ARABIC LETTER LAM - ARABIC LETTER MEEM - ARABIC LETTER NOON - ARABIC LETTER HEH - ARABIC LETTER WAW - ARABIC LETTER ALEF MAKSURA - ARABIC LETTER YEH -<:+> ARABIC FATHATAN -<"+> ARABIC DAMMATAN -<=+> ARABIC KASRATAN - ARABIC FATHA -<'+> ARABIC DAMMA -<1+> ARABIC KASRA -<3+> ARABIC SHADDA -<0+> ARABIC SUKUN -<0a> ARABIC-INDIC DIGIT ZERO -<1a> ARABIC-INDIC DIGIT ONE -<2a> ARABIC-INDIC DIGIT TWO -<3a> ARABIC-INDIC DIGIT THREE -<4a> ARABIC-INDIC DIGIT FOUR -<5a> ARABIC-INDIC DIGIT FIVE -<6a> ARABIC-INDIC DIGIT SIX -<7a> ARABIC-INDIC DIGIT SEVEN -<8a> ARABIC-INDIC DIGIT EIGHT -<9a> ARABIC-INDIC DIGIT NINE - ARABIC LETTER SUPERSCRIPT ALEF - ARABIC LETTER PEH - ARABIC LETTER HAH WITH HAMZA ABOVE - ARABIC LETTER TCHEH - ARABIC LETTER JEH - ARABIC LETTER VEH - ARABIC LETTER GAF - LATIN CAPITAL LETTER A WITH RING BELOW - LATIN SMALL LETTER A WITH RING BELOW - LATIN CAPITAL LETTER B WITH DOT ABOVE - LATIN SMALL LETTER B WITH DOT ABOVE - LATIN CAPITAL LETTER B WITH DOT BELOW - LATIN SMALL LETTER B WITH DOT BELOW - LATIN CAPITAL LETTER B WITH LINE BELOW - LATIN SMALL LETTER B WITH LINE BELOW - LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE - LATIN SMALL LETTER C WITH CEDILLA AND ACUTE - LATIN CAPITAL LETTER D WITH DOT ABOVE - LATIN SMALL LETTER D WITH DOT ABOVE - LATIN CAPITAL LETTER D WITH DOT BELOW - LATIN SMALL LETTER D WITH DOT BELOW - LATIN CAPITAL LETTER D WITH LINE BELOW - LATIN SMALL LETTER D WITH LINE BELOW - LATIN CAPITAL LETTER D WITH CEDILLA - LATIN SMALL LETTER D WITH CEDILLA -> LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW -> LATIN SMALL LETTER D WITH CIRCUMFLEX BELOW - LATIN CAPITAL LETTER E WITH MACRON AND GRAVE - LATIN SMALL LETTER E WITH MACRON AND GRAVE - LATIN CAPITAL LETTER E WITH MACRON AND ACUTE - LATIN SMALL LETTER E WITH MACRON AND ACUTE -> LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW -> LATIN SMALL LETTER E WITH CIRCUMFLEX BELOW - LATIN CAPITAL LETTER E WITH TILDE BELOW - LATIN SMALL LETTER E WITH TILDE BELOW - LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE - LATIN SMALL LETTER E WITH CEDILLA AND BREVE - LATIN CAPITAL LETTER F WITH DOT ABOVE - LATIN SMALL LETTER F WITH DOT ABOVE - LATIN CAPITAL LETTER G WITH MACRON - LATIN SMALL LETTER G WITH MACRON - LATIN CAPITAL LETTER H WITH DOT ABOVE - LATIN SMALL LETTER H WITH DOT ABOVE - LATIN CAPITAL LETTER H WITH DOT BELOW - LATIN SMALL LETTER H WITH DOT BELOW - LATIN CAPITAL LETTER H WITH DIAERESIS - LATIN SMALL LETTER H WITH DIAERESIS - LATIN CAPITAL LETTER H WITH CEDILLA - LATIN SMALL LETTER H WITH CEDILLA - LATIN CAPITAL LETTER H WITH BREVE BELOW - LATIN SMALL LETTER H WITH BREVE BELOW - LATIN CAPITAL LETTER I WITH TILDE BELOW - LATIN SMALL LETTER I WITH TILDE BELOW - LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE - LATIN SMALL LETTER I WITH DIAERESIS AND ACUTE - LATIN CAPITAL LETTER K WITH ACUTE - LATIN SMALL LETTER K WITH ACUTE - LATIN CAPITAL LETTER K WITH DOT BELOW - LATIN SMALL LETTER K WITH DOT BELOW - LATIN CAPITAL LETTER K WITH LINE BELOW - LATIN SMALL LETTER K WITH LINE BELOW - LATIN CAPITAL LETTER L WITH DOT BELOW - LATIN SMALL LETTER L WITH DOT BELOW - LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON - LATIN SMALL LETTER L WITH DOT BELOW AND MACRON - LATIN CAPITAL LETTER L WITH LINE BELOW - LATIN SMALL LETTER L WITH LINE BELOW -> LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW -> LATIN SMALL LETTER L WITH CIRCUMFLEX BELOW - LATIN CAPITAL LETTER M WITH ACUTE - LATIN SMALL LETTER M WITH ACUTE - LATIN CAPITAL LETTER M WITH DOT ABOVE - LATIN SMALL LETTER M WITH DOT ABOVE - LATIN CAPITAL LETTER M WITH DOT BELOW - LATIN SMALL LETTER M WITH DOT BELOW - LATIN CAPITAL LETTER N WITH DOT ABOVE - LATIN SMALL LETTER N WITH DOT ABOVE - LATIN CAPITAL LETTER N WITH DOT BELOW - LATIN SMALL LETTER N WITH DOT BELOW - LATIN CAPITAL LETTER N WITH LINE BELOW - LATIN SMALL LETTER N WITH LINE BELOW -> LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW -> LATIN SMALL LETTER N WITH CIRCUMFLEX BELOW - LATIN CAPITAL LETTER O WITH TILDE AND ACUTE - LATIN SMALL LETTER O WITH TILDE AND ACUTE - LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS - LATIN SMALL LETTER O WITH TILDE AND DIAERESIS - LATIN CAPITAL LETTER O WITH MACRON AND GRAVE - LATIN SMALL LETTER O WITH MACRON AND GRAVE - LATIN CAPITAL LETTER O WITH MACRON AND ACUTE - LATIN SMALL LETTER O WITH MACRON AND ACUTE - LATIN CAPITAL LETTER P WITH ACUTE - LATIN SMALL LETTER P WITH ACUTE - LATIN CAPITAL LETTER P WITH DOT ABOVE - LATIN SMALL LETTER P WITH DOT ABOVE - LATIN CAPITAL LETTER R WITH DOT ABOVE - LATIN SMALL LETTER R WITH DOT ABOVE - LATIN CAPITAL LETTER R WITH DOT BELOW - LATIN SMALL LETTER R WITH DOT BELOW - LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON - LATIN SMALL LETTER R WITH DOT BELOW AND MACRON - LATIN CAPITAL LETTER R WITH LINE BELOW - LATIN SMALL LETTER R WITH LINE BELOW - LATIN CAPITAL LETTER S WITH DOT ABOVE - LATIN SMALL LETTER S WITH DOT ABOVE - LATIN CAPITAL LETTER S WITH DOT BELOW - LATIN SMALL LETTER S WITH DOT BELOW - LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE - LATIN SMALL LETTER S WITH ACUTE AND DOT ABOVE - LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE - LATIN SMALL LETTER S WITH CARON AND DOT ABOVE - LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE - LATIN SMALL LETTER S WITH DOT BELOW AND DOT ABOVE - LATIN CAPITAL LETTER T WITH DOT ABOVE - LATIN SMALL LETTER T WITH DOT ABOVE - LATIN CAPITAL LETTER T WITH DOT BELOW - LATIN SMALL LETTER T WITH DOT BELOW - LATIN CAPITAL LETTER T WITH LINE BELOW - LATIN SMALL LETTER T WITH LINE BELOW -> LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW -> LATIN SMALL LETTER T WITH CIRCUMFLEX BELOW - LATIN CAPITAL LETTER U WITH DIAERESIS BELOW - LATIN SMALL LETTER U WITH DIAERESIS BELOW - LATIN CAPITAL LETTER U WITH TILDE BELOW - LATIN SMALL LETTER U WITH TILDE BELOW -> LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW -> LATIN SMALL LETTER U WITH CIRCUMFLEX BELOW - LATIN CAPITAL LETTER U WITH TILDE AND ACUTE - LATIN SMALL LETTER U WITH TILDE AND ACUTE - LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS - LATIN SMALL LETTER U WITH MACRON AND DIAERESIS - LATIN CAPITAL LETTER V WITH TILDE - LATIN SMALL LETTER V WITH TILDE - LATIN CAPITAL LETTER V WITH DOT BELOW - LATIN SMALL LETTER V WITH DOT BELOW - LATIN CAPITAL LETTER W WITH GRAVE - LATIN SMALL LETTER W WITH GRAVE - LATIN CAPITAL LETTER W WITH ACUTE - LATIN SMALL LETTER W WITH ACUTE - LATIN CAPITAL LETTER W WITH DIAERESIS - LATIN SMALL LETTER W WITH DIAERESIS - LATIN CAPITAL LETTER W WITH DOT ABOVE - LATIN SMALL LETTER W WITH DOT ABOVE - LATIN CAPITAL LETTER W WITH DOT BELOW - LATIN SMALL LETTER W WITH DOT BELOW - LATIN CAPITAL LETTER X WITH DOT ABOVE - LATIN SMALL LETTER X WITH DOT ABOVE - LATIN CAPITAL LETTER X WITH DIAERESIS - LATIN SMALL LETTER X WITH DIAERESIS - LATIN CAPITAL LETTER Y WITH DOT ABOVE - LATIN SMALL LETTER Y WITH DOT ABOVE -> LATIN CAPITAL LETTER Z WITH CIRCUMFLEX -> LATIN SMALL LETTER Z WITH CIRCUMFLEX - LATIN CAPITAL LETTER Z WITH DOT BELOW - LATIN SMALL LETTER Z WITH DOT BELOW - LATIN CAPITAL LETTER Z WITH LINE BELOW - LATIN SMALL LETTER Z WITH LINE BELOW - LATIN CAPITAL LETTER A WITH DOT BELOW - LATIN SMALL LETTER A WITH DOT BELOW - LATIN CAPITAL LETTER A WITH HOOK ABOVE - LATIN SMALL LETTER A WITH HOOK ABOVE -'> LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE -'> LATIN SMALL LETTER A WITH CIRCUMFLEX AND ACUTE -!> LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE -!> LATIN SMALL LETTER A WITH CIRCUMFLEX AND GRAVE -2> LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE -2> LATIN SMALL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE -?> LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE -?> LATIN SMALL LETTER A WITH CIRCUMFLEX AND TILDE --.> LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW --.> LATIN SMALL LETTER A WITH CIRCUMFLEX AND DOT BELOW - LATIN CAPITAL LETTER A WITH BREVE AND ACUTE - LATIN SMALL LETTER A WITH BREVE AND ACUTE - LATIN CAPITAL LETTER A WITH BREVE AND GRAVE - LATIN SMALL LETTER A WITH BREVE AND GRAVE - LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE - LATIN SMALL LETTER A WITH BREVE AND HOOK ABOVE - LATIN CAPITAL LETTER A WITH BREVE AND TILDE - LATIN SMALL LETTER A WITH BREVE AND TILDE - LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW - LATIN SMALL LETTER A WITH BREVE AND DOT BELOW - LATIN CAPITAL LETTER E WITH DOT BELOW - LATIN SMALL LETTER E WITH DOT BELOW - LATIN CAPITAL LETTER E WITH HOOK ABOVE - LATIN SMALL LETTER E WITH HOOK ABOVE - LATIN CAPITAL LETTER E WITH TILDE - LATIN SMALL LETTER E WITH TILDE -'> LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE -'> LATIN SMALL LETTER E WITH CIRCUMFLEX AND ACUTE -!> LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE -!> LATIN SMALL LETTER E WITH CIRCUMFLEX AND GRAVE -2> LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE -2> LATIN SMALL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE -?> LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE -?> LATIN SMALL LETTER E WITH CIRCUMFLEX AND TILDE --.> LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW --.> LATIN SMALL LETTER E WITH CIRCUMFLEX AND DOT BELOW - LATIN CAPITAL LETTER I WITH HOOK ABOVE - LATIN SMALL LETTER I WITH HOOK ABOVE - LATIN CAPITAL LETTER I WITH DOT BELOW - LATIN SMALL LETTER I WITH DOT BELOW - LATIN CAPITAL LETTER O WITH DOT BELOW - LATIN SMALL LETTER O WITH DOT BELOW - LATIN CAPITAL LETTER O WITH HOOK ABOVE - LATIN SMALL LETTER O WITH HOOK ABOVE -'> LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE -'> LATIN SMALL LETTER O WITH CIRCUMFLEX AND ACUTE -!> LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE -!> LATIN SMALL LETTER O WITH CIRCUMFLEX AND GRAVE -2> LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE -2> LATIN SMALL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE -?> LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE -?> LATIN SMALL LETTER O WITH CIRCUMFLEX AND TILDE --.> LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW --.> LATIN SMALL LETTER O WITH CIRCUMFLEX AND DOT BELOW - LATIN CAPITAL LETTER O WITH HORN AND ACUTE - LATIN SMALL LETTER O WITH HORN AND ACUTE - LATIN CAPITAL LETTER O WITH HORN AND GRAVE - LATIN SMALL LETTER O WITH HORN AND GRAVE - LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE - LATIN SMALL LETTER O WITH HORN AND HOOK ABOVE - LATIN CAPITAL LETTER O WITH HORN AND TILDE - LATIN SMALL LETTER O WITH HORN AND TILDE - LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW - LATIN SMALL LETTER O WITH HORN AND DOT BELOW - LATIN CAPITAL LETTER U WITH DOT BELOW - LATIN SMALL LETTER U WITH DOT BELOW - LATIN CAPITAL LETTER U WITH HOOK ABOVE - LATIN SMALL LETTER U WITH HOOK ABOVE - LATIN CAPITAL LETTER U WITH HORN AND ACUTE - LATIN SMALL LETTER U WITH HORN AND ACUTE - LATIN CAPITAL LETTER U WITH HORN AND GRAVE - LATIN SMALL LETTER U WITH HORN AND GRAVE - LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE - LATIN SMALL LETTER U WITH HORN AND HOOK ABOVE - LATIN CAPITAL LETTER U WITH HORN AND TILDE - LATIN SMALL LETTER U WITH HORN AND TILDE - LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW - LATIN SMALL LETTER U WITH HORN AND DOT BELOW - LATIN CAPITAL LETTER Y WITH GRAVE - LATIN SMALL LETTER Y WITH GRAVE - LATIN CAPITAL LETTER Y WITH DOT BELOW - LATIN SMALL LETTER Y WITH DOT BELOW - LATIN CAPITAL LETTER Y WITH HOOK ABOVE - LATIN SMALL LETTER Y WITH HOOK ABOVE - LATIN CAPITAL LETTER Y WITH TILDE - LATIN SMALL LETTER Y WITH TILDE -<,,> GREEK PSILI - GREEK PERISPOMENI - GREEK DIALYTIKA AND PERISPOMENI -<,!> GREEK PSILI AND VARIA -<,'> GREEK PSILI AND OXIA - GREEK PSILI AND PERISPOMENI -<;!> GREEK DASIA AND VARIA -<;'> GREEK DASIA AND OXIA - GREEK DASIA AND PERISPOMENI - GREEK DIALYTIKA AND VARIA - GREEK VARIA -<;;> GREEK DASIA -<1N> EN SPACE -<1M> EM SPACE -<3M> THREE-PER-EM SPACE -<4M> FOUR-PER-EM SPACE -<6M> SIX-PER-EM SPACE - LEFT-TO-RIGHT MARK - RIGHT-TO-LEFT MARK -<1T> THIN SPACE -<1H> HAIR SPACE -<-1> HYPHEN -<-N> EN DASH -<-M> EM DASH -<-3> HORIZONTAL BAR - DOUBLE VERTICAL LINE -<=2> DOUBLE LOW LINE -<'6> LEFT SINGLE QUOTATION MARK -<'9> RIGHT SINGLE QUOTATION MARK -<.9> SINGLE LOW-9 QUOTATION MARK -<9'> SINGLE HIGH-REVERSED-9 QUOTATION MARK -<"6> LEFT DOUBLE QUOTATION MARK -<"9> RIGHT DOUBLE QUOTATION MARK -<:9> DOUBLE LOW-9 QUOTATION MARK -<9"> DOUBLE HIGH-REVERSED-9 QUOTATION MARK - DAGGER - DOUBLE DAGGER - BULLET -<..> TWO DOT LEADER -<.3> HORIZONTAL ELLIPSIS -<%0> PER MILLE SIGN -<1'> PRIME -<2'> DOUBLE PRIME -<3'> TRIPLE PRIME -<1"> REVERSED PRIME -<2"> REVERSED DOUBLE PRIME -<3"> REVERSED TRIPLE PRIME - CARET -<<1> SINGLE LEFT-POINTING ANGLE QUOTATION MARK -1> SINGLE RIGHT-POINTING ANGLE QUOTATION MARK -<:X> REFERENCE MARK - DOUBLE EXCLAMATION MARK -<'-> OVERLINE -<0S> SUPERSCRIPT ZERO -<4S> SUPERSCRIPT FOUR -<5S> SUPERSCRIPT FIVE -<6S> SUPERSCRIPT SIX -<7S> SUPERSCRIPT SEVEN -<8S> SUPERSCRIPT EIGHT -<9S> SUPERSCRIPT NINE -<+S> SUPERSCRIPT PLUS SIGN -<-S> SUPERSCRIPT MINUS -<=S> SUPERSCRIPT EQUALS SIGN -<(S> SUPERSCRIPT LEFT PARENTHESIS -<)S> SUPERSCRIPT RIGHT PARENTHESIS - SUPERSCRIPT LATIN SMALL LETTER N -<0s> SUBSCRIPT ZERO -<1s> SUBSCRIPT ONE -<2s> SUBSCRIPT TWO -<3s> SUBSCRIPT THREE -<4s> SUBSCRIPT FOUR -<5s> SUBSCRIPT FIVE -<6s> SUBSCRIPT SIX -<7s> SUBSCRIPT SEVEN -<8s> SUBSCRIPT EIGHT -<9s> SUBSCRIPT NINE -<+s> SUBSCRIPT PLUS SIGN -<-s> SUBSCRIPT MINUS -<=s> SUBSCRIPT EQUALS SIGN -<(s> SUBSCRIPT LEFT PARENTHESIS -<)s> SUBSCRIPT RIGHT PARENTHESIS - FRENCH FRANK SIGN -
  • LIRA SIGN - PESETA SIGN - WON SIGN - DEGREE CELSIUS - CARE OF - DEGREE FAHRENHEIT - NUMERO SIGN - SOUND RECORDING COPYRIGHT - PRESCRIPTION TAKE - SERVICE MARK - TRADE MARK SIGN - OHM SIGN - ANGSTROM SIGN -<13> VULGAR FRACTION ONE THIRD -<23> VULGAR FRACTION TWO THIRDS -<15> VULGAR FRACTION ONE FIFTH -<25> VULGAR FRACTION TWO FIFTHS -<35> VULGAR FRACTION THREE FIFTHS -<45> VULGAR FRACTION FOUR FIFTHS -<16> VULGAR FRACTION ONE SIXTH -<56> VULGAR FRACTION FIVE SIXTHS -<18> VULGAR FRACTION ONE EIGHTH -<38> VULGAR FRACTION THREE EIGHTHS -<58> VULGAR FRACTION FIVE EIGHTHS -<78> VULGAR FRACTION SEVEN EIGHTHS -<1R> ROMAN NUMERAL ONE -<2R> ROMAN NUMERAL TWO -<3R> ROMAN NUMERAL THREE -<4R> ROMAN NUMERAL FOUR -<5R> ROMAN NUMERAL FIVE -<6R> ROMAN NUMERAL SIX -<7R> ROMAN NUMERAL SEVEN -<8R> ROMAN NUMERAL EIGHT -<9R> ROMAN NUMERAL NINE - ROMAN NUMERAL TEN -
    ROMAN NUMERAL ELEVEN - ROMAN NUMERAL TWELVE -<50R> ROMAN NUMERAL FIFTY -<100R> ROMAN NUMERAL ONE HUNDRED -<500R> ROMAN NUMERAL FIVE HUNDRED -<1000R> ROMAN NUMERAL ONE THOUSAND -<1r> SMALL ROMAN NUMERAL ONE -<2r> SMALL ROMAN NUMERAL TWO -<3r> SMALL ROMAN NUMERAL THREE -<4r> SMALL ROMAN NUMERAL FOUR -<5r> SMALL ROMAN NUMERAL FIVE -<6r> SMALL ROMAN NUMERAL SIX -<7r> SMALL ROMAN NUMERAL SEVEN -<8r> SMALL ROMAN NUMERAL EIGHT -<9r> SMALL ROMAN NUMERAL NINE - SMALL ROMAN NUMERAL TEN -
    SMALL ROMAN NUMERAL ELEVEN - SMALL ROMAN NUMERAL TWELVE -<50r> SMALL ROMAN NUMERAL FIFTY -<100r> SMALL ROMAN NUMERAL ONE HUNDRED -<500r> SMALL ROMAN NUMERAL FIVE HUNDRED -<1000r> SMALL ROMAN NUMERAL ONE THOUSAND -<1000RCD> ROMAN NUMERAL ONE THOUSAND C D -<5000R> ROMAN NUMERAL FIVE THOUSAND -<10000R> ROMAN NUMERAL TEN THOUSAND -<<-> LEFTWARDS ARROW -<-!> UPWARDS ARROW -<-/>> RIGHTWARDS ARROW -<-v> DOWNWARDS ARROW -<> LEFT RIGHT ARROW - UP DOWN ARROW -< NORTH WEST ARROW -> NORTH EAST ARROW -> SOUTH EAST ARROW -< SOUTH WEST ARROW - UP DOWN ARROW WITH BASE -V> RIGHTWARDS HARPOON WITH BARB UPWARDS -<<=> LEFTWARDS DOUBLE ARROW -<=/>> RIGHTWARDS DOUBLE ARROW -<==> LEFT RIGHT DOUBLE ARROW - FOR ALL - PARTIAL DIFFERENTIAL - THERE EXISTS - EMPTY SET - INCREMENT - NABLA -<(-> ELEMENT OF -<-)> CONTAINS AS MEMBER -<*P> N-ARY PRODUCT -<+Z> N-ARY SUMMATION -<-2> MINUS SIGN -<-+> MINUS-OR-PLUS SIGN -<.+> DOT PLUS - DIVISION SLASH -<*-> ASTERISK OPERATOR - RING OPERATOR - BULLET OPERATOR - SQUARE ROOT -<0(> PROPORTIONAL TO -<00> INFINITY -<-L> RIGHT ANGLE -<-V> ANGLE - PARALLEL TO - LOGICAL AND - LOGICAL OR -<(U> INTERSECTION -<)U> UNION - INTEGRAL - DOUBLE INTEGRAL - CONTOUR INTEGRAL -<.:> THEREFORE -<:.> BECAUSE -<:R> RATIO -<::> PROPORTION - TILDE OPERATOR - INVERTED LAZY S - ASYMPTOTICALLY EQUAL TO - APPROXIMATELY EQUAL TO - ALMOST EQUAL TO -<=?> ALL EQUAL TO - IMAGE OF OR APPROXIMATELY EQUAL TO - NOT EQUAL TO -<=3> IDENTICAL TO -<=<> LESS-THAN OR EQUAL TO -=> GREATER-THAN OR EQUAL TO -<<*> MUCH LESS-THAN -<*/>> MUCH GREATER-THAN - NOT LESS-THAN -> NOT GREATER-THAN -<(C> SUBSET OF -<)C> SUPERSET OF -<(_> SUBSET OF OR EQUAL TO -<)_> SUPERSET OF OR EQUAL TO -<0.> CIRCLED DOT OPERATOR -<02> CIRCLED RING OPERATOR -<-T> UP TACK -<.P> DOT OPERATOR -<:3> VERTICAL ELLIPSIS - HOUSE -<<7> LEFT CEILING -7> RIGHT CEILING -<7<> LEFT FLOOR -<7/>> RIGHT FLOOR - REVERSED NOT SIGN -<(A> ARC - TELEPHONE RECORDER - TOP HALF INTEGRAL - BOTTOM HALF INTEGRAL -< LEFT-POINTING ANGLE BRACKET -> RIGHT-POINTING ANGLE BRACKET - OPEN BOX -<1h> OCR HOOK -<3h> OCR CHAIR -<2h> OCR FORK -<4h> OCR INVERTED FORK -<1j> OCR BRANCH BANK IDENTIFICATION -<2j> OCR AMOUNT OF CHECK -<3j> OCR DASH -<4j> OCR CUSTOMER ACCOUNT NUMBER -<1-o> CIRCLED DIGIT ONE -<2-o> CIRCLED DIGIT TWO -<3-o> CIRCLED DIGIT THREE -<4-o> CIRCLED DIGIT FOUR -<5-o> CIRCLED DIGIT FIVE -<6-o> CIRCLED DIGIT SIX -<7-o> CIRCLED DIGIT SEVEN -<8-o> CIRCLED DIGIT EIGHT -<9-o> CIRCLED DIGIT NINE -<10-o> CIRCLED NUMBER TEN -<11-o> CIRCLED NUMBER ELEVEN -<12-o> CIRCLED NUMBER TWELVE -<13-o> CIRCLED NUMBER THIRTEEN -<14-o> CIRCLED NUMBER FOURTEEN -<15-o> CIRCLED NUMBER FIFTEEN -<16-o> CIRCLED NUMBER SIXTEEN -<17-o> CIRCLED NUMBER SEVENTEEN -<18-o> CIRCLED NUMBER EIGHTEEN -<19-o> CIRCLED NUMBER NINETEEN -<20-o> CIRCLED NUMBER TWENTY -<(1)> PARENTHESIZED DIGIT ONE -<(2)> PARENTHESIZED DIGIT TWO -<(3)> PARENTHESIZED DIGIT THREE -<(4)> PARENTHESIZED DIGIT FOUR -<(5)> PARENTHESIZED DIGIT FIVE -<(6)> PARENTHESIZED DIGIT SIX -<(7)> PARENTHESIZED DIGIT SEVEN -<(8)> PARENTHESIZED DIGIT EIGHT -<(9)> PARENTHESIZED DIGIT NINE -<(10)> PARENTHESIZED NUMBER TEN -<(11)> PARENTHESIZED NUMBER ELEVEN -<(12)> PARENTHESIZED NUMBER TWELVE -<(13)> PARENTHESIZED NUMBER THIRTEEN -<(14)> PARENTHESIZED NUMBER FOURTEEN -<(15)> PARENTHESIZED NUMBER FIFTEEN -<(16)> PARENTHESIZED NUMBER SIXTEEN -<(17)> PARENTHESIZED NUMBER SEVENTEEN -<(18)> PARENTHESIZED NUMBER EIGHTEEN -<(19)> PARENTHESIZED NUMBER NINETEEN -<(20)> PARENTHESIZED NUMBER TWENTY -<1.> DIGIT ONE FULL STOP -<2.> DIGIT TWO FULL STOP -<3.> DIGIT THREE FULL STOP -<4.> DIGIT FOUR FULL STOP -<5.> DIGIT FIVE FULL STOP -<6.> DIGIT SIX FULL STOP -<7.> DIGIT SEVEN FULL STOP -<8.> DIGIT EIGHT FULL STOP -<9.> DIGIT NINE FULL STOP -<10.> NUMBER TEN FULL STOP -<11.> NUMBER ELEVEN FULL STOP -<12.> NUMBER TWELVE FULL STOP -<13.> NUMBER THIRTEEN FULL STOP -<14.> NUMBER FOURTEEN FULL STOP -<15.> NUMBER FIFTEEN FULL STOP -<16.> NUMBER SIXTEEN FULL STOP -<17.> NUMBER SEVENTEEN FULL STOP -<18.> NUMBER EIGHTEEN FULL STOP -<19.> NUMBER NINETEEN FULL STOP -<20.> NUMBER TWENTY FULL STOP -<(a)> PARENTHESIZED LATIN SMALL LETTER A -<(b)> PARENTHESIZED LATIN SMALL LETTER B -<(c)> PARENTHESIZED LATIN SMALL LETTER C -<(d)> PARENTHESIZED LATIN SMALL LETTER D -<(e)> PARENTHESIZED LATIN SMALL LETTER E -<(f)> PARENTHESIZED LATIN SMALL LETTER F -<(g)> PARENTHESIZED LATIN SMALL LETTER G -<(h)> PARENTHESIZED LATIN SMALL LETTER H -<(i)> PARENTHESIZED LATIN SMALL LETTER I -<(j)> PARENTHESIZED LATIN SMALL LETTER J -<(k)> PARENTHESIZED LATIN SMALL LETTER K -<(l)> PARENTHESIZED LATIN SMALL LETTER L -<(m)> PARENTHESIZED LATIN SMALL LETTER M -<(n)> PARENTHESIZED LATIN SMALL LETTER N -<(o)> PARENTHESIZED LATIN SMALL LETTER O -<(p)> PARENTHESIZED LATIN SMALL LETTER P -<(q)> PARENTHESIZED LATIN SMALL LETTER Q -<(r)> PARENTHESIZED LATIN SMALL LETTER R -<(s)> PARENTHESIZED LATIN SMALL LETTER S -<(t)> PARENTHESIZED LATIN SMALL LETTER T -<(u)> PARENTHESIZED LATIN SMALL LETTER U -<(v)> PARENTHESIZED LATIN SMALL LETTER V -<(w)> PARENTHESIZED LATIN SMALL LETTER W -<(x)> PARENTHESIZED LATIN SMALL LETTER X -<(y)> PARENTHESIZED LATIN SMALL LETTER Y -<(z)> PARENTHESIZED LATIN SMALL LETTER Z - CIRCLED LATIN CAPITAL LETTER A - CIRCLED LATIN CAPITAL LETTER B - CIRCLED LATIN CAPITAL LETTER C - CIRCLED LATIN CAPITAL LETTER D - CIRCLED LATIN CAPITAL LETTER E - CIRCLED LATIN CAPITAL LETTER F - CIRCLED LATIN CAPITAL LETTER G - CIRCLED LATIN CAPITAL LETTER H - CIRCLED LATIN CAPITAL LETTER I - CIRCLED LATIN CAPITAL LETTER J - CIRCLED LATIN CAPITAL LETTER K - CIRCLED LATIN CAPITAL LETTER L - CIRCLED LATIN CAPITAL LETTER M - CIRCLED LATIN CAPITAL LETTER N - CIRCLED LATIN CAPITAL LETTER O - CIRCLED LATIN CAPITAL LETTER P - CIRCLED LATIN CAPITAL LETTER Q - CIRCLED LATIN CAPITAL LETTER R - CIRCLED LATIN CAPITAL LETTER S - CIRCLED LATIN CAPITAL LETTER T - CIRCLED LATIN CAPITAL LETTER U - CIRCLED LATIN CAPITAL LETTER V - CIRCLED LATIN CAPITAL LETTER W - CIRCLED LATIN CAPITAL LETTER X - CIRCLED LATIN CAPITAL LETTER Y - CIRCLED LATIN CAPITAL LETTER Z - CIRCLED LATIN SMALL LETTER A - CIRCLED LATIN SMALL LETTER B - CIRCLED LATIN SMALL LETTER C - CIRCLED LATIN SMALL LETTER D - CIRCLED LATIN SMALL LETTER E - CIRCLED LATIN SMALL LETTER F - CIRCLED LATIN SMALL LETTER G - CIRCLED LATIN SMALL LETTER H - CIRCLED LATIN SMALL LETTER I - CIRCLED LATIN SMALL LETTER J - CIRCLED LATIN SMALL LETTER K - CIRCLED LATIN SMALL LETTER L - CIRCLED LATIN SMALL LETTER M - CIRCLED LATIN SMALL LETTER N - CIRCLED LATIN SMALL LETTER O - CIRCLED LATIN SMALL LETTER P - CIRCLED LATIN SMALL LETTER Q - CIRCLED LATIN SMALL LETTER R - CIRCLED LATIN SMALL LETTER S - CIRCLED LATIN SMALL LETTER T - CIRCLED LATIN SMALL LETTER U - CIRCLED LATIN SMALL LETTER V - CIRCLED LATIN SMALL LETTER W - CIRCLED LATIN SMALL LETTER X - CIRCLED LATIN SMALL LETTER Y - CIRCLED LATIN SMALL LETTER Z -<0-o> CIRCLED DIGIT ZERO - BOX DRAWINGS LIGHT HORIZONTAL - BOX DRAWINGS HEAVY HORIZONTAL - BOX DRAWINGS LIGHT VERTICAL - BOX DRAWINGS HEAVY VERTICAL -<3-> BOX DRAWINGS LIGHT TRIPLE DASH HORIZONTAL -<3_> BOX DRAWINGS HEAVY TRIPLE DASH HORIZONTAL -<3!> BOX DRAWINGS LIGHT TRIPLE DASH VERTICAL -<3//> BOX DRAWINGS HEAVY TRIPLE DASH VERTICAL -<4-> BOX DRAWINGS LIGHT QUADRUPLE DASH HORIZONTAL -<4_> BOX DRAWINGS HEAVY QUADRUPLE DASH HORIZONTAL -<4!> BOX DRAWINGS LIGHT QUADRUPLE DASH VERTICAL -<4//> BOX DRAWINGS HEAVY QUADRUPLE DASH VERTICAL - BOX DRAWINGS LIGHT DOWN AND RIGHT - BOX DRAWINGS DOWN LIGHT AND RIGHT HEAVY - BOX DRAWINGS DOWN HEAVY AND RIGHT LIGHT - BOX DRAWINGS HEAVY DOWN AND RIGHT -
    BOX DRAWINGS LIGHT DOWN AND LEFT -
    BOX DRAWINGS DOWN LIGHT AND LEFT HEAVY -
    BOX DRAWINGS DOWN HEAVY AND LEFT LIGHT - BOX DRAWINGS HEAVY DOWN AND LEFT - BOX DRAWINGS LIGHT UP AND RIGHT - BOX DRAWINGS UP LIGHT AND RIGHT HEAVY - BOX DRAWINGS UP HEAVY AND RIGHT LIGHT - BOX DRAWINGS HEAVY UP AND RIGHT -

    • LATIN CAPITAL LETTER P - LATIN CAPITAL LETTER Q - LATIN CAPITAL LETTER R - LATIN CAPITAL LETTER S - LATIN CAPITAL LETTER T - LATIN CAPITAL LETTER U - LATIN CAPITAL LETTER V - LATIN CAPITAL LETTER W - LATIN CAPITAL LETTER X - LATIN CAPITAL LETTER Y - LATIN CAPITAL LETTER Z -<<(> LEFT SQUARE BRACKET - REVERSE SOLIDUS -<)/>> RIGHT SQUARE BRACKET -<'/>> CIRCUMFLEX ACCENT -<_> LOW LINE -<'!> GRAVE ACCENT - LATIN SMALL LETTER A - LATIN SMALL LETTER B - LATIN SMALL LETTER C - LATIN SMALL LETTER D - LATIN SMALL LETTER E - LATIN SMALL LETTER F - LATIN SMALL LETTER G - LATIN SMALL LETTER H - LATIN SMALL LETTER I - LATIN SMALL LETTER J - LATIN SMALL LETTER K - LATIN SMALL LETTER L - LATIN SMALL LETTER M - LATIN SMALL LETTER N - LATIN SMALL LETTER O -