Try to consistently use Latin1 for garmin format.
set(HEADERS
an1sym.h
cet.h
- cet/ansi_x3_4_1968.h
- cet/cp1252.h
- cet/iso_8859_8.h
cet_util.h
csv_util.h
defs.h
HEADERS = \
an1sym.h \
cet.h \
- cet/ansi_x3_4_1968.h \
- cet/cp1252.h \
- cet/iso_8859_8.h \
cet_util.h \
csv_util.h \
defs.h \
gbfile.h session.h src/core/datetime.h src/core/optional.h
cet_util.o: cet_util.cc defs.h config.h zlib/zlib.h zlib/zconf.h cet.h \
inifile.h gbfile.h session.h src/core/datetime.h src/core/optional.h \
- cet_util.h src/core/logging.h cet/ansi_x3_4_1968.h cet/cp1252.h \
- cet/iso_8859_8.h
+ cet_util.h src/core/logging.h
compegps.o: compegps.cc defs.h config.h zlib/zlib.h zlib/zconf.h cet.h \
inifile.h gbfile.h session.h src/core/datetime.h src/core/optional.h \
cet_util.h csv_util.h jeeps/gpsmath.h jeeps/gpsport.h
inifile.h gbfile.h session.h src/core/datetime.h src/core/optional.h
destinator.o: destinator.cc defs.h config.h zlib/zlib.h zlib/zconf.h \
cet.h inifile.h gbfile.h session.h src/core/datetime.h \
- src/core/optional.h cet_util.h garmin_fs.h jeeps/gps.h jeeps/../defs.h \
+ src/core/optional.h garmin_fs.h jeeps/gps.h jeeps/../defs.h \
jeeps/gpsport.h jeeps/gpsdevice.h jeeps/gpssend.h jeeps/gpsread.h \
jeeps/gpsutil.h jeeps/gpsapp.h jeeps/gpsprot.h jeeps/gpscom.h \
jeeps/gpsfmt.h jeeps/gpsmath.h jeeps/gpsmem.h jeeps/gpsrqst.h \
jeeps/gpsrqst.h
garmin_tables.o: garmin_tables.cc defs.h config.h zlib/zlib.h \
zlib/zconf.h cet.h inifile.h gbfile.h session.h src/core/datetime.h \
- src/core/optional.h garmin_tables.h garmin_icon_tables.h \
- jeeps/gpsmath.h jeeps/gpsport.h src/core/logging.h
+ src/core/optional.h garmin_tables.h jeeps/gpsmath.h jeeps/gpsport.h \
+ src/core/logging.h garmin_icon_tables.h
garmin_txt.o: garmin_txt.cc defs.h config.h zlib/zlib.h zlib/zconf.h \
cet.h inifile.h gbfile.h session.h src/core/datetime.h \
src/core/optional.h csv_util.h garmin_fs.h jeeps/gps.h jeeps/../defs.h \
inifile.h gbfile.h session.h src/core/datetime.h src/core/optional.h \
xmlgeneric.h
igo8.o: igo8.cc defs.h config.h zlib/zlib.h zlib/zconf.h cet.h inifile.h \
- gbfile.h session.h src/core/datetime.h src/core/optional.h cet_util.h
+ gbfile.h session.h src/core/datetime.h src/core/optional.h
ik3d.o: ik3d.cc defs.h config.h zlib/zlib.h zlib/zconf.h cet.h inifile.h \
gbfile.h session.h src/core/datetime.h src/core/optional.h \
xmlgeneric.h
inifile.h gbfile.h session.h src/core/datetime.h src/core/optional.h \
garmin_tables.h jeeps/gpsmath.h jeeps/gpsport.h
mkshort.o: mkshort.cc defs.h config.h zlib/zlib.h zlib/zconf.h cet.h \
- inifile.h gbfile.h session.h src/core/datetime.h src/core/optional.h \
- cet_util.h
+ inifile.h gbfile.h session.h src/core/datetime.h src/core/optional.h
mmo.o: mmo.cc defs.h config.h zlib/zlib.h zlib/zconf.h cet.h inifile.h \
gbfile.h session.h src/core/datetime.h src/core/optional.h
mtk_locus.o: mtk_locus.cc defs.h config.h zlib/zlib.h zlib/zconf.h cet.h \
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*/
+#include <string.h> // for strlen
+
#include "defs.h"
#include "cet.h"
/* %%% single character or value transmission %%% */
/* --------------------------------------------------------------------------- */
-/* %%% cet_char_to_ucs4 %%%
- *
- * single character to UCS-4 code %%%
- * return values: 0 if convertible character, otherwise 1
- */
-
-int
-cet_char_to_ucs4(const char src, const cet_cs_vec_t* vec, int* value)
-{
- int trash;
-
- int c = ((unsigned char)src & 0xFF);
- int* dest = (value != nullptr) ? value : &trash;
-
- *dest = c;
- c -= vec->ucs4_offset;
-
- if (c < 0) {
- return CET_SUCCESS;
- } else if ((c >= vec->ucs4_count) || (vec->ucs4_map[c] == -1)) {
- return CET_ERROR;
- } else {
- *dest = vec->ucs4_map[c];
- return CET_SUCCESS;
- }
-}
-
/* %%% cet_ucs4_to_utf8 %%%
*
* convert single UCS-4 value into UTF-8 sequence
return CET_ERROR; /* not valid */
}
-/* %%% cet_ucs4_to_char %%%
- *
- * convert single UCS-4 value to original character from CS
- *
- * return values: converted character or "CET_NOT_CONVERTABLE_DEFAULT"
- * if not possible
- */
-short
-cet_ucs4_to_char(const int value, const cet_cs_vec_t* vec)
-{
- const cet_ucs4_link_t* link;
-
- if ((link = vec->ucs4_link)) {
- int i = 0;
- int j = vec->ucs4_links - 1; /* validate ucs value against vec */
- while (i <= j) {
- int a = (i + j) >> 1;
- int x = link[a].value;
-
- if (x < value) {
- i = a + 1;
- } else if (x > value) {
- j = a - 1;
- } else {
- return link[a].origin;
- }
- }
- }
-
- if ((link = vec->ucs4_extra)) { /* can be NULL */
- int i = 0;
- int j = vec->ucs4_extras - 1;
- while (i <= j) {
- int a = (i + j) >> 1;
- int x = link[a].value;
-
- if (x < value) {
- i = a + 1;
- } else if (x > value) {
- j = a - 1;
- } else {
- return link[a].origin;
- }
- }
- }
-
- if (value < vec->ucs4_offset + vec->ucs4_count) {
- return (char)value & 0xFF;
- } else {
- if (vec->fallback && (vec->fallback != vec)) {
- return cet_ucs4_to_char(value, vec->fallback);
- } else {
- return CET_NOT_CONVERTABLE_DEFAULT;
- }
- }
-}
-
-/* %%% cet_utf8_to_char %%%
- *
- * Convert single UTF-8 sequence directly into associated characters
- * by given character set.
- */
-
-short
-cet_utf8_to_char(const char* str, const cet_cs_vec_t* vec, /* out */ int* bytes, int* value)
-{
- int b, v;
-
- cet_utf8_to_ucs4(str, &b, &v); /* decode UTF-8 sequence */
-
- if (bytes != nullptr) {
- *bytes = b;
- }
- if (value != nullptr) {
- *value = v;
- }
-
- return cet_ucs4_to_char(v, vec);
-}
-
/* =========================================================================== */
/* %%% UTF-8 string manipulation functions %%% */
/* =========================================================================== */
return nullptr;
}
}
-
-/* =========================================================================== */
-/* %%% full string transformation %%% */
-/* =========================================================================== */
-
-/* %%% cet_str_utf8_to_any %%%
- *
- * Converts a UTF-8 string to given character set
- */
-char*
-cet_str_utf8_to_any(const char* src, const cet_cs_vec_t* vec)
-{
- const char* c = src;
- char* dest;
-
- if (c == nullptr) {
- return nullptr;
- }
- if (vec->ucs4_count == 0) {
- return xstrdup(src); /* UTF-8 -> UTF-8 */
- }
-
- int len = strlen(c);
- char* res = dest = (char*) xmalloc(len + 1); /* target will become smaller or equal length */
-
- const char* cend = c + len;
-
- while (c < cend) {
- int bytes;
- *dest++ = cet_utf8_to_char(c, vec, &bytes, nullptr);
- c += bytes;
- }
- *dest = '\0';
-
- return res;
-}
-
-
-/* %%% cet_str_any_to_utf8 %%%
- *
- * Converts a string from given character set to UTF-8
- */
-char*
-cet_str_any_to_utf8(const char* src, const cet_cs_vec_t* vec)
-{
- int value;
- char* cout;
- char temp = CET_NOT_CONVERTABLE_DEFAULT;
-
- const char* cin = src;
- if (cin == nullptr) {
- return nullptr;
- }
- if (vec->ucs4_count == 0) {
- return xstrdup(src); /* UTF-8 -> UTF-8 */
- }
-
- int len = 0;
- while (*cin != '\0') { /* determine length of resulting UTF-8 string */
- if (CET_ERROR == cet_char_to_ucs4(*cin++, vec, &value)) {
- cet_char_to_ucs4(temp, vec, &value);
- }
- len += cet_ucs4_to_utf8(nullptr, 6, value);
- }
-
- char* result = cout = (char*) xmalloc(len + 1);
- cin = src;
-
- while (*cin != '\0') {
- if (CET_ERROR == cet_char_to_ucs4(*cin++, vec, &value)) {
- cet_char_to_ucs4(temp, vec, &value);
- }
- cout += cet_ucs4_to_utf8(cout, 6, value);
- }
- *cout = '\0';
- return result;
-}
-
-/* %%% cet_str_uni_to_utf8 %%%
- *
- * Converts an unicode string to UTF-8
- */
-char*
-cet_str_uni_to_utf8(const short* src, const int length)
-{
- char* cout;
-
- if (src == nullptr) {
- return nullptr;
- }
-
- int len = 0;
- int i = length;
- unsigned short* cin = (unsigned short*)src;
-
- while (i-- > 0) {
- len += cet_ucs4_to_utf8(nullptr, 6, le_read16(cin++));
- }
-
- char* res = cout = (char*) xmalloc(len + 1);
- cin = (unsigned short*)src;
- i = length;
-
- while (i-- > 0) {
- cout += cet_ucs4_to_utf8(cout, 6, le_read16(cin++));
- }
-
- *cout = '\0';
-
- return res;
-}
-
-/* %%% cet_str_any_to_uni %%%
- *
- * Converts a string in given character set to a 'wide string' (unicode)
- */
-short*
-cet_str_any_to_uni(const char* src, const cet_cs_vec_t* vec, int* length)
-{
- char* utf8;
- short* sout;
-
- if (! src) {
- utf8 = xstrdup("");
- } else if (vec->ucs4_count == 0) {
- utf8 = cet_utf8_strdup(src); /* UTF-8 -> clean UTF-8 */
- } else {
- utf8 = cet_str_any_to_utf8(src, vec);
- }
-
- int len = cet_utf8_strlen(utf8);
- short* res = sout = (short int*) xcalloc(2, len + 1);
-
- if (len) {
- char* cin = utf8;
-
- while (*cin) {
- int bytes, value;
- if (CET_SUCCESS == cet_utf8_to_ucs4(cin, &bytes, &value)) {
- le_write16(sout, value);
- sout++;
- }
- cin += bytes;
- }
- }
-
- *sout = 0;
- if (length) {
- *length = len;
- }
- xfree(utf8);
-
- return res;
-}
#define CET_ERROR 1
#define CET_SUCCESS 0
-struct cet_ucs4_link_t {
- int value; /* UCS-4 value */
- short origin; /* associated character */
-};
-
-struct cet_cs_vec_t {
- const char* name; /* name of character set */
- const char** alias; /* alias table */
- cet_cs_vec_t* fallback; /* fallback character set */
- void* unused;
- const int* ucs4_map; /* char to UCS-4 value table */
- const int ucs4_offset; /* first non standard character */
- const int ucs4_count; /* values in table */
- const cet_ucs4_link_t* ucs4_link; /* UCS-4 to char backward links */
- const int ucs4_links; /* number of links */
- const cet_ucs4_link_t* ucs4_extra; /* Non standard UCS-4 to ... */
- const int ucs4_extras; /* number of extra links */
- cet_cs_vec_t* next;
-};
-
/* single char/value transmission */
int cet_utf8_to_ucs4(const char* str, int* bytes, int* value);
int cet_ucs4_to_utf8(char* dest, size_t dest_size, int value);
-/* single char/value transmission - vec based */
-
-int cet_char_to_ucs4(char src, const cet_cs_vec_t* vec, int* value);
-short cet_utf8_to_char(const char* str, const cet_cs_vec_t* vecint, int* bytes, int* value);
-short cet_ucs4_to_char(int value, const cet_cs_vec_t* vec);
-
-/* string to string - vector based */
-
-char* cet_str_utf8_to_any(const char* src, const cet_cs_vec_t* vec);
-char* cet_str_any_to_utf8(const char* src, const cet_cs_vec_t* vec);
-
-char* cet_str_uni_to_utf8(const short* src, int length);
-
/* UTF-8 string manipulation functions */
unsigned int cet_utf8_strlen(const char* str);
char* cet_utf8_strdup(const char* str);
char* cet_utf8_strndup(const char* str, int maxlen);
-/* unicode functions */
-
-short* cet_str_any_to_uni(const char* src, const cet_cs_vec_t* vec, int* length);
-
#endif
+++ /dev/null
-/*
-
- Data automatically generated from recode output:
-
- 'recode -lf "ANSI_X3.4-1968" 2>/dev/null'
-
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2 of the License, or
- (at your option) any later version.
-
- This program 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 General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
-
-*/
-
-#ifndef ansi_x3_4_1968_h
-#define ansi_x3_4_1968_h
-
-#define cet_cs_name_ansi_x3_4_1968 "US-ASCII"
-
-const char *cet_cs_alias_ansi_x3_4_1968[] =
-{
- "ANSI_X3.4-1968", "367", "ANSI_X3.4-1986", "ASCII",
- "CP367", "csASCII", "IBM367", "ISO646-US",
- "ISO646.1991-IRV", "iso-ir-6", "ISO_646.irv:1991", "us",
- nullptr
-};
-
-#define cet_ucs4_ofs_ansi_x3_4_1968 128
-#define cet_ucs4_cnt_ansi_x3_4_1968 1
-
-const int cet_ucs4_map_ansi_x3_4_1968[cet_ucs4_cnt_ansi_x3_4_1968] = {0};
-
-#define cet_ucs4_to_ansi_x3_4_1968_ct 1
-
-const cet_ucs4_link_t cet_ucs4_to_ansi_x3_4_1968_links[cet_ucs4_to_ansi_x3_4_1968_ct] = {{0, 0}};
-
-// #define cet_ucs4_to_ansi_x3_4_1968_extra_ct 200
-
-const cet_ucs4_link_t cet_ucs4_to_ansi_x3_4_1968_extra[] =
-/* ------------------------------------------*/
-/* !!! sorted by UCS-4 value !!! */
-/* ------------------------------------------*/
-{
- {0x00C0, (unsigned char) 'A'}, // latin capital letter a with grave
- {0x00C1, (unsigned char) 'A'}, // latin capital letter a with acute
- {0x00C2, (unsigned char) 'A'}, // latin capital letter a with circumflex
- {0x00C3, (unsigned char) 'A'}, // latin capital letter a with tilde
- {0x00C4, (unsigned char) 'A'}, // latin capital letter a with diaeresis
- {0x00C5, (unsigned char) 'A'}, // latin capital letter a with ring above
- {0x00C7, (unsigned char) 'C'}, // latin capital letter c with cedilla
- {0x00C8, (unsigned char) 'E'}, // latin capital letter e with grave
- {0x00C9, (unsigned char) 'E'}, // latin capital letter e with acute
- {0x00CA, (unsigned char) 'E'}, // latin capital letter e with circumflex
- {0x00CB, (unsigned char) 'E'}, // latin capital letter e with diaeresis
- {0x00CC, (unsigned char) 'I'}, // latin capital letter i with grave
- {0x00CD, (unsigned char) 'I'}, // latin capital letter i with acute
- {0x00CE, (unsigned char) 'I'}, // latin capital letter i with circumflex
- {0x00CF, (unsigned char) 'I'}, // latin capital letter i with diaeresis
- {0x00D1, (unsigned char) 'N'}, // latin capital letter n with tilde
- {0x00D2, (unsigned char) 'O'}, // latin capital letter o with grave
- {0x00D3, (unsigned char) 'O'}, // latin capital letter o with acute
- {0x00D4, (unsigned char) 'O'}, // latin capital letter o with circumflex
- {0x00D5, (unsigned char) 'O'}, // latin capital letter o with tilde
- {0x00D6, (unsigned char) 'O'}, // latin capital letter o with diaeresis
- {0x00D8, (unsigned char) 'O'}, // latin capital letter o with stroke
- {0x00D9, (unsigned char) 'U'}, // latin capital letter u with grave
- {0x00DA, (unsigned char) 'U'}, // latin capital letter u with acute
- {0x00DB, (unsigned char) 'U'}, // latin capital letter u with circumflex
- {0x00DC, (unsigned char) 'U'}, // latin capital letter u with diaeresis
- {0x00DD, (unsigned char) 'Y'}, // latin capital letter y with acute
- {0x00E0, (unsigned char) 'a'}, // latin small letter a with grave
- {0x00E1, (unsigned char) 'a'}, // latin small letter a with acute
- {0x00E2, (unsigned char) 'a'}, // latin small letter a with circumflex
- {0x00E3, (unsigned char) 'a'}, // latin small letter a with tilde
- {0x00E4, (unsigned char) 'a'}, // latin small letter a with diaeresis
- {0x00E5, (unsigned char) 'a'}, // latin small letter a with ring above
- {0x00E7, (unsigned char) 'c'}, // latin small letter c with cedilla
- {0x00E8, (unsigned char) 'e'}, // latin small letter e with grave
- {0x00E9, (unsigned char) 'e'}, // latin small letter e with acute
- {0x00EA, (unsigned char) 'e'}, // latin small letter e with circumflex
- {0x00EB, (unsigned char) 'e'}, // latin small letter e with diaeresis
- {0x00EC, (unsigned char) 'i'}, // latin small letter i with grave
- {0x00ED, (unsigned char) 'i'}, // latin small letter i with acute
- {0x00EE, (unsigned char) 'i'}, // latin small letter i with circumflex
- {0x00EF, (unsigned char) 'i'}, // latin small letter i with diaeresis
- {0x00F1, (unsigned char) 'n'}, // latin small letter n with tilde
- {0x00F2, (unsigned char) 'o'}, // latin small letter o with grave
- {0x00F3, (unsigned char) 'o'}, // latin small letter o with acute
- {0x00F4, (unsigned char) 'o'}, // latin small letter o with circumflex
- {0x00F5, (unsigned char) 'o'}, // latin small letter o with tilde
- {0x00F6, (unsigned char) 'o'}, // latin small letter o with diaeresis
- {0x00F8, (unsigned char) 'o'}, // latin small letter o with stroke
- {0x00F9, (unsigned char) 'u'}, // latin small letter u with grave
- {0x00FA, (unsigned char) 'u'}, // latin small letter u with acute
- {0x00FB, (unsigned char) 'u'}, // latin small letter u with circumflex
- {0x00FC, (unsigned char) 'u'}, // latin small letter u with diaeresis
- {0x00FD, (unsigned char) 'y'}, // latin small letter y with acute
- {0x00FF, (unsigned char) 'y'}, // latin small letter y with diaeresis
- {0x0100, (unsigned char) 'A'}, // latin capital letter a with macron
- {0x0101, (unsigned char) 'a'}, // latin small letter a with macron
- {0x0102, (unsigned char) 'A'}, // latin capital letter a with breve
- {0x0103, (unsigned char) 'a'}, // latin small letter a with breve
- {0x0104, (unsigned char) 'A'}, // latin capital letter a with ogonek
- {0x0105, (unsigned char) 'a'}, // latin small letter a with ogonek
- {0x0106, (unsigned char) 'C'}, // latin capital letter c with acute
- {0x0107, (unsigned char) 'c'}, // latin small letter c with acute
- {0x0108, (unsigned char) 'C'}, // latin capital letter c with circumflex
- {0x0109, (unsigned char) 'c'}, // latin small letter c with circumflex
- {0x010A, (unsigned char) 'C'}, // latin capital letter c with dot above
- {0x010B, (unsigned char) 'c'}, // latin small letter c with dot above
- {0x010C, (unsigned char) 'C'}, // latin capital letter c with caron
- {0x010D, (unsigned char) 'c'}, // latin small letter c with caron
- {0x010E, (unsigned char) 'D'}, // latin capital letter d with caron
- {0x010F, (unsigned char) 'd'}, // latin small letter d with caron
- {0x0110, (unsigned char) 'D'}, // latin capital letter d with stroke
- {0x0111, (unsigned char) 'd'}, // latin small letter d with stroke
- {0x0112, (unsigned char) 'E'}, // latin capital letter e with macron
- {0x0113, (unsigned char) 'e'}, // latin small letter e with macron
- {0x0114, (unsigned char) 'E'}, // latin capital letter e with breve
- {0x0115, (unsigned char) 'e'}, // latin small letter e with breve
- {0x0116, (unsigned char) 'E'}, // latin capital letter e with dot above
- {0x0117, (unsigned char) 'e'}, // latin small letter e with dot above
- {0x0118, (unsigned char) 'E'}, // latin capital letter e with ogonek
- {0x0119, (unsigned char) 'e'}, // latin small letter e with ogonek
- {0x011A, (unsigned char) 'E'}, // latin capital letter e with caron
- {0x011B, (unsigned char) 'e'}, // latin small letter e with caron
- {0x011C, (unsigned char) 'G'}, // latin capital letter g with circumflex
- {0x011D, (unsigned char) 'g'}, // latin small letter g with circumflex
- {0x011E, (unsigned char) 'G'}, // latin capital letter g with breve
- {0x011F, (unsigned char) 'g'}, // latin small letter g with breve
- {0x0120, (unsigned char) 'G'}, // latin capital letter g with dot above
- {0x0121, (unsigned char) 'g'}, // latin small letter g with dot above
- {0x0122, (unsigned char) 'G'}, // latin capital letter g with cedilla
- {0x0123, (unsigned char) 'g'}, // latin small letter g with cedilla
- {0x0124, (unsigned char) 'H'}, // latin capital letter h with circumflex
- {0x0125, (unsigned char) 'h'}, // latin small letter h with circumflex
- {0x0126, (unsigned char) 'H'}, // latin capital letter h with stroke
- {0x0127, (unsigned char) 'h'}, // latin small letter h with stroke
- {0x0128, (unsigned char) 'I'}, // latin capital letter i with tilde
- {0x0129, (unsigned char) 'i'}, // latin small letter i with tilde
- {0x012A, (unsigned char) 'I'}, // latin capital letter i with macron
- {0x012B, (unsigned char) 'i'}, // latin small letter i with macron
- {0x012C, (unsigned char) 'I'}, // latin capital letter i with breve
- {0x012D, (unsigned char) 'i'}, // latin small letter i with breve
- {0x012E, (unsigned char) 'I'}, // latin capital letter i with ogonek
- {0x012F, (unsigned char) 'i'}, // latin small letter i with ogonek
- {0x0130, (unsigned char) 'I'}, // latin capital letter i with dot above
- {0x0131, (unsigned char) 'i'}, // latin small letter dotless i
- {0x0134, (unsigned char) 'J'}, // latin capital letter j with circumflex
- {0x0135, (unsigned char) 'j'}, // latin small letter j with circumflex
- {0x0136, (unsigned char) 'K'}, // latin capital letter k with cedilla
- {0x0137, (unsigned char) 'k'}, // latin small letter k with cedilla
- {0x0139, (unsigned char) 'L'}, // latin capital letter l with acute
- {0x013A, (unsigned char) 'l'}, // latin small letter l with acute
- {0x013B, (unsigned char) 'L'}, // latin capital letter l with cedilla
- {0x013C, (unsigned char) 'l'}, // latin small letter l with cedilla
- {0x013D, (unsigned char) 'L'}, // latin capital letter l with caron
- {0x013E, (unsigned char) 'l'}, // latin small letter l with caron
- {0x0141, (unsigned char) 'L'}, // latin capital letter l with stroke
- {0x0142, (unsigned char) 'l'}, // latin small letter l with stroke
- {0x0143, (unsigned char) 'N'}, // latin capital letter n with acute
- {0x0144, (unsigned char) 'n'}, // latin small letter n with acute
- {0x0145, (unsigned char) 'N'}, // latin capital letter n with cedilla
- {0x0146, (unsigned char) 'n'}, // latin small letter n with cedilla
- {0x0147, (unsigned char) 'N'}, // latin capital letter n with caron
- {0x0148, (unsigned char) 'n'}, // latin small letter n with caron
- {0x014C, (unsigned char) 'O'}, // latin capital letter o with macron
- {0x014D, (unsigned char) 'o'}, // latin small letter o with macron
- {0x014E, (unsigned char) 'O'}, // latin capital letter o with breve
- {0x014F, (unsigned char) 'o'}, // latin small letter o with breve
- {0x0150, (unsigned char) 'O'}, // latin capital letter o with double acute
- {0x0151, (unsigned char) 'o'}, // latin small letter o with double acute
- {0x0152, (unsigned char) 'O'}, // latin capital ligature oe
- {0x0153, (unsigned char) 'o'}, // latin small ligature oe
- {0x0154, (unsigned char) 'R'}, // latin capital letter r with acute
- {0x0155, (unsigned char) 'r'}, // latin small letter r with acute
- {0x0156, (unsigned char) 'R'}, // latin capital letter r with cedilla
- {0x0157, (unsigned char) 'r'}, // latin small letter r with cedilla
- {0x0158, (unsigned char) 'R'}, // latin capital letter r with caron
- {0x0159, (unsigned char) 'r'}, // latin small letter r with caron
- {0x015A, (unsigned char) 'S'}, // latin capital letter s with acute
- {0x015B, (unsigned char) 's'}, // latin small letter s with acute
- {0x015C, (unsigned char) 'S'}, // latin capital letter s with circumflex
- {0x015D, (unsigned char) 's'}, // latin small letter s with circumflex
- {0x015E, (unsigned char) 'S'}, // latin capital letter s with cedilla
- {0x015F, (unsigned char) 's'}, // latin small letter s with cedilla
- {0x0160, (unsigned char) 'S'}, // latin capital letter s with caron
- {0x0161, (unsigned char) 's'}, // latin small letter s with caron
- {0x0162, (unsigned char) 'T'}, // latin capital letter t with cedilla
- {0x0163, (unsigned char) 't'}, // latin small letter t with cedilla
- {0x0164, (unsigned char) 'T'}, // latin capital letter t with caron
- {0x0165, (unsigned char) 't'}, // latin small letter t with caron
- {0x0166, (unsigned char) 'T'}, // latin capital letter t with stroke
- {0x0167, (unsigned char) 't'}, // latin small letter t with stroke
- {0x0168, (unsigned char) 'U'}, // latin capital letter u with tilde
- {0x0169, (unsigned char) 'u'}, // latin small letter u with tilde
- {0x016A, (unsigned char) 'U'}, // latin capital letter u with macron
- {0x016B, (unsigned char) 'u'}, // latin small letter u with macron
- {0x016C, (unsigned char) 'U'}, // latin capital letter u with breve
- {0x016D, (unsigned char) 'u'}, // latin small letter u with breve
- {0x016E, (unsigned char) 'U'}, // latin capital letter u with ring above
- {0x016F, (unsigned char) 'u'}, // latin small letter u with ring above
- {0x0170, (unsigned char) 'U'}, // latin capital letter u with double acute
- {0x0171, (unsigned char) 'u'}, // latin small letter u with double acute
- {0x0172, (unsigned char) 'U'}, // latin capital letter u with ogonek
- {0x0173, (unsigned char) 'u'}, // latin small letter u with ogonek
- {0x0174, (unsigned char) 'W'}, // latin capital letter w with circumflex
- {0x0175, (unsigned char) 'w'}, // latin small letter w with circumflex
- {0x0176, (unsigned char) 'Y'}, // latin capital letter y with circumflex
- {0x0177, (unsigned char) 'y'}, // latin small letter y with circumflex
- {0x0178, (unsigned char) 'Y'}, // latin capital letter y with diaeresis
- {0x0179, (unsigned char) 'Z'}, // latin capital letter z with acute
- {0x017A, (unsigned char) 'z'}, // latin small letter z with acute
- {0x017B, (unsigned char) 'Z'}, // latin capital letter z with dot above
- {0x017C, (unsigned char) 'z'}, // latin small letter z with dot above
- {0x017D, (unsigned char) 'Z'}, // latin capital letter z with caron
- {0x017E, (unsigned char) 'z'}, // latin small letter z with caron
- {0x0180, (unsigned char) 'b'}, // latin small letter b with stroke
- {0x0189, (unsigned char) 'D'}, // latin capital letter african d
- {0x0191, (unsigned char) 'F'}, // latin capital letter f with hook
- {0x0192, (unsigned char) 'f'}, // latin small letter f with hook
- {0x0197, (unsigned char) 'I'}, // latin capital letter i with stroke
- {0x019A, (unsigned char) 'l'}, // latin small letter l with bar
- {0x019F, (unsigned char) 'O'}, // latin capital letter o with middle tilde
- {0x01A0, (unsigned char) 'O'}, // latin capital letter o with horn
- {0x01A1, (unsigned char) 'o'}, // latin small letter o with horn
- {0x01AB, (unsigned char) 't'}, // latin small letter t with palatal hook
- {0x01AE, (unsigned char) 'T'}, // latin capital letter t with retroflex hook
- {0x01AF, (unsigned char) 'U'}, // latin capital letter u with horn
- {0x01B0, (unsigned char) 'u'}, // latin small letter u with horn
- {0x01B6, (unsigned char) 'z'}, // latin small letter z with stroke
- {0x01C0, (unsigned char) '|'}, // latin letter dental click
- {0x01C3, (unsigned char) '!'}, // latin letter retroflex click
- {0x01CD, (unsigned char) 'A'}, // latin capital letter a with caron
- {0x01CE, (unsigned char) 'a'}, // latin small letter a with caron
- {0x01CF, (unsigned char) 'I'}, // latin capital letter i with caron
- {0x01D0, (unsigned char) 'i'}, // latin small letter i with caron
- {0x01D1, (unsigned char) 'O'}, // latin capital letter o with caron
- {0x01D2, (unsigned char) 'o'}, // latin small letter o with caron
- {0x01D3, (unsigned char) 'U'}, // latin capital letter u with caron
- {0x01D4, (unsigned char) 'u'}, // latin small letter u with caron
- {0x01D5, (unsigned char) 'U'}, // latin capital letter u with diaeresis and macron
- {0x01D6, (unsigned char) 'u'}, // latin small letter u with diaeresis and macron
- {0x01D7, (unsigned char) 'U'}, // latin capital letter u with diaeresis and acute
- {0x01D8, (unsigned char) 'u'}, // latin small letter u with diaeresis and acute
- {0x01D9, (unsigned char) 'U'}, // latin capital letter u with diaeresis and caron
- {0x01DA, (unsigned char) 'u'}, // latin small letter u with diaeresis and caron
- {0x01DB, (unsigned char) 'U'}, // latin capital letter u with diaeresis and grave
- {0x01DC, (unsigned char) 'u'}, // latin small letter u with diaeresis and grave
- {0x01DE, (unsigned char) 'A'}, // latin capital letter a with diaeresis and macron
- {0x01DF, (unsigned char) 'a'}, // latin small letter a with diaeresis and macron
- {0x01E4, (unsigned char) 'G'}, // latin capital letter g with stroke
- {0x01E5, (unsigned char) 'g'}, // latin small letter g with stroke
- {0x01E6, (unsigned char) 'G'}, // latin capital letter g with caron
- {0x01E7, (unsigned char) 'g'}, // latin small letter g with caron
- {0x01E8, (unsigned char) 'K'}, // latin capital letter k with caron
- {0x01E9, (unsigned char) 'k'}, // latin small letter k with caron
- {0x01EA, (unsigned char) 'O'}, // latin capital letter o with ogonek
- {0x01EB, (unsigned char) 'o'}, // latin small letter o with ogonek
- {0x01EC, (unsigned char) 'O'}, // latin capital letter o with ogonek and macron
- {0x01ED, (unsigned char) 'o'}, // latin small letter o with ogonek and macron
- {0x01F0, (unsigned char) 'j'}, // latin small letter j with caron
- {0x0261, (unsigned char) 'g'}, // latin small letter script g
- {0x02B9, (unsigned char) '\''}, // modifier letter prime
- {0x02BA, (unsigned char) '"'}, // modifier letter double prime
- {0x02BC, (unsigned char) '\''}, // modifier letter apostrophe
- {0x02C4, (unsigned char) '^'}, // modifier letter up arrowhead
- {0x02C6, (unsigned char) '^'}, // modifier letter circumflex accent
- {0x02C7, (unsigned char) '^'}, // caron
- {0x02C8, (unsigned char) '\''}, // modifier letter vertical line
- {0x02CB, (unsigned char) '`'}, // modifier letter grave accent
- {0x02CD, (unsigned char) '_'}, // modifier letter low macron
- {0x02D8, (unsigned char) '^'}, // circumflex accent
- {0x02D9, (unsigned char) '\''}, // dot above
- {0x02DC, (unsigned char) '~'}, // small tilde
- {0x0300, (unsigned char) '`'}, // combining grave accent
- {0x0302, (unsigned char) '^'}, // combining circumflex accent
- {0x0303, (unsigned char) '~'}, // combining tilde
- {0x030E, (unsigned char) '"'}, // combining double vertical line above
- {0x0331, (unsigned char) '_'}, // combining macron below
- {0x0332, (unsigned char) '_'}, // combining low line
- {0x037E, (unsigned char) ';'}, // greek question mark
- {0x0393, (unsigned char) 'G'}, // greek capital letter gamma
- {0x0398, (unsigned char) 'T'}, // greek capital letter theta
- {0x03A3, (unsigned char) 'S'}, // greek capital letter sigma
- {0x03A6, (unsigned char) 'F'}, // greek capital letter phi
- {0x03A9, (unsigned char) 'O'}, // greek capital letter omega
- {0x03B1, (unsigned char) 'a'}, // greek small letter alpha
- {0x03B4, (unsigned char) 'd'}, // greek small letter delta
- {0x03B5, (unsigned char) 'e'}, // greek small letter epsilon
- {0x03C0, (unsigned char) 'p'}, // greek small letter pi
- {0x03C3, (unsigned char) 's'}, // greek small letter sigma
- {0x03C4, (unsigned char) 't'}, // greek small letter tau
- {0x03C6, (unsigned char) 'f'}, // greek small letter phi
- {0x04BB, (unsigned char) 'h'}, // cyrillic small letter shha
- {0x0589, (unsigned char) ':'}, // armenian full stop
- {0x066A, (unsigned char) '%'}, // arabic percent sign
- {0x1E02, (unsigned char) 'B'}, // latin capital letter b with dot above
- {0x1E03, (unsigned char) 'b'}, // latin small letter b with dot above
- {0x1E0A, (unsigned char) 'D'}, // latin capital letter d with dot above
- {0x1E0B, (unsigned char) 'd'}, // latin small letter d with dot above
- {0x1E1E, (unsigned char) 'F'}, // latin capital letter f with dot above
- {0x1E1F, (unsigned char) 'f'}, // latin small letter f with dot above
- {0x1E40, (unsigned char) 'M'}, // latin capital letter m with dot above
- {0x1E41, (unsigned char) 'm'}, // latin small letter m with dot above
- {0x1E56, (unsigned char) 'P'}, // latin capital letter p with dot above
- {0x1E57, (unsigned char) 'p'}, // latin small letter p with dot above
- {0x1E60, (unsigned char) 'S'}, // latin capital letter s with dot above
- {0x1E61, (unsigned char) 's'}, // latin small letter s with dot above
- {0x1E6A, (unsigned char) 'T'}, // latin capital letter t with dot above
- {0x1E6B, (unsigned char) 't'}, // latin small letter t with dot above
- {0x1E80, (unsigned char) 'W'}, // latin capital letter w with grave
- {0x1E81, (unsigned char) 'w'}, // latin small letter w with grave
- {0x1E82, (unsigned char) 'W'}, // latin capital letter w with acute
- {0x1E83, (unsigned char) 'w'}, // latin small letter w with acute
- {0x1E84, (unsigned char) 'W'}, // latin capital letter w with diaeresis
- {0x1E85, (unsigned char) 'w'}, // latin small letter w with diaeresis
- {0x1E94, (unsigned char) 'u'},
- {0x1EF2, (unsigned char) 'Y'}, // latin capital letter y with grave
- {0x1EF3, (unsigned char) 'y'}, // latin small letter y with grave
- {0x2000, (unsigned char) ' '}, // en quad
- {0x2001, (unsigned char) ' '}, // em quad
- {0x2002, (unsigned char) ' '}, // en space
- {0x2003, (unsigned char) ' '}, // em space
- {0x2004, (unsigned char) ' '}, // three-per-em space
- {0x2005, (unsigned char) ' '}, // four-per-em space
- {0x2006, (unsigned char) ' '}, // six-per-em space
- {0x2010, (unsigned char) '-'}, // hyphen
- {0x2011, (unsigned char) '-'}, // non-breaking hyphen
- {0x2013, (unsigned char) '-'}, // en dash
- {0x2014, (unsigned char) '-'}, // em dash
- {0x2017, (unsigned char) '='}, // double low line
- {0x2018, (unsigned char) '`'}, // left single quotation mark
- {0x2019, (unsigned char) '\''}, // right single quotation mark
- {0x201C, (unsigned char) '"'},
- {0x201D, (unsigned char) '"'},
- {0x2032, (unsigned char) '\''}, // prime
- {0x2035, (unsigned char) '`'}, // reversed prime
- {0x203C, (unsigned char) '!'}, // double exclamation mark
- {0x2044, (unsigned char) '/'}, // fraction slash
- {0x2074, (unsigned char) '4'}, // superscript four
- {0x2075, (unsigned char) '5'}, // superscript five
- {0x2076, (unsigned char) '6'}, // superscript six
- {0x2077, (unsigned char) '7'}, // superscript seven
- {0x2078, (unsigned char) '8'}, // superscript eight
- {0x207F, (unsigned char) 'n'}, // superscript latin small letter n
- {0x2080, (unsigned char) '0'}, // subscript zero
- {0x2081, (unsigned char) '1'}, // subscript one
- {0x2082, (unsigned char) '2'}, // subscript two
- {0x2083, (unsigned char) '3'}, // subscript three
- {0x2084, (unsigned char) '4'}, // subscript four
- {0x2085, (unsigned char) '5'}, // subscript five
- {0x2086, (unsigned char) '6'}, // subscript six
- {0x2087, (unsigned char) '7'}, // subscript seven
- {0x2088, (unsigned char) '8'}, // subscript eight
- {0x2089, (unsigned char) '9'}, // subscript nine
- {0x20A7, (unsigned char) 'P'}, // peseta sign
- {0x2102, (unsigned char) 'C'}, // double-struck capital c
- {0x2107, (unsigned char) 'E'}, // euler constant
- {0x210A, (unsigned char) 'g'}, // script small g
- {0x210B, (unsigned char) 'H'}, // script capital h
- {0x210C, (unsigned char) 'H'}, // black-letter capital h
- {0x210D, (unsigned char) 'H'}, // double-struck capital h
- {0x210E, (unsigned char) 'h'}, // planck constant
- {0x2110, (unsigned char) 'I'}, // script capital i
- {0x2111, (unsigned char) 'I'}, // black-letter capital i
- {0x2112, (unsigned char) 'L'}, // script capital l
- {0x2113, (unsigned char) 'l'}, // script small l
- {0x2115, (unsigned char) 'N'}, // double-struck capital n
- {0x2118, (unsigned char) 'P'}, // script capital p
- {0x2119, (unsigned char) 'P'}, // double-struck capital p
- {0x211A, (unsigned char) 'Q'}, // double-struck capital q
- {0x211B, (unsigned char) 'R'}, // script capital r
- {0x211C, (unsigned char) 'R'}, // black-letter capital r
- {0x211D, (unsigned char) 'R'}, // double-struck capital r
- {0x2124, (unsigned char) 'Z'}, // double-struck capital z
- {0x2128, (unsigned char) 'Z'}, // black-letter capital z
- {0x212A, (unsigned char) 'K'}, // kelvin sign
- {0x212C, (unsigned char) 'B'}, // script capital b
- {0x212D, (unsigned char) 'C'}, // black-letter capital c
- {0x212E, (unsigned char) 'e'}, // estimated symbol
- {0x212F, (unsigned char) 'e'}, // script small e
- {0x2130, (unsigned char) 'E'}, // script capital e
- {0x2131, (unsigned char) 'F'}, // script capital f
- {0x2133, (unsigned char) 'M'}, // script capital m
- {0x2134, (unsigned char) 'o'}, // script small o
- {0x2190, (unsigned char) '<'}, // leftwards arrow
- {0x2191, (unsigned char) '^'}, // upwards arrow
- {0x2192, (unsigned char) '>'}, // rightwards arrow
- {0x2193, (unsigned char) 'v'}, // downwards arrow
- {0x2194, (unsigned char) '-'}, // left right arrow
- {0x2195, (unsigned char) '|'}, // up down arrow
- {0x21A8, (unsigned char) '|'}, // up down arrow with base
- {0x2212, (unsigned char) '-'}, // minus sign
- {0x2215, (unsigned char) '/'}, // division slash
- {0x2216, (unsigned char) '\\'}, // set minus
- {0x2217, (unsigned char) '*'}, // asterisk operator
- {0x221A, (unsigned char) 'v'}, // square root
- {0x221E, (unsigned char) '8'}, // infinity
- {0x221F, (unsigned char) 'L'}, // right angle
- {0x2223, (unsigned char) '|'}, // divides
- {0x2229, (unsigned char) 'n'}, // intersection
- {0x2236, (unsigned char) ':'}, // ratio
- {0x223C, (unsigned char) '~'}, // tilde operator
- {0x2261, (unsigned char) '='}, // identical to
- {0x2264, (unsigned char) '='}, // less-than or equal to
- {0x2265, (unsigned char) '='}, // greater-than or equal to
- {0x2303, (unsigned char) '^'}, // up arrowhead
- {0x2320, (unsigned char) '('}, // top half integral
- {0x2321, (unsigned char) ')'}, // bottom half integral
- {0x2329, (unsigned char) '<'}, // left-pointing angle bracket
- {0x232A, (unsigned char) '>'}, // right-pointing angle bracket
- {0x25AC, (unsigned char) '-'}, // black rectangle
- {0x25B2, (unsigned char) '^'}, // black up-pointing triangle
- {0x25BA, (unsigned char) '>'}, // black right-pointing pointer
- {0x25C4, (unsigned char) '<'}, // black left-pointing pointer
- {0x25CB, (unsigned char) '0'}, // white circle
- {0x25D9, (unsigned char) '0'}, // inverse white circle
- {0x263A, (unsigned char) 'O'}, // white smiling face
- {0x263B, (unsigned char) 'O'}, // black smiling face
- {0x263C, (unsigned char) '0'}, // white sun with rays
- {0x2640, (unsigned char) '+'}, // female sign
- {0x2642, (unsigned char) '>'}, // male sign
- {0x266A, (unsigned char) 'd'}, // eighth note
- {0x266B, (unsigned char) 'd'}, // beamed eighth notes
- {0x2758, (unsigned char) '|'}, // light vertical bar
- {0x3000, (unsigned char) ' '}, // ideographic space
- {0x3008, (unsigned char) '<'}, // left angle bracket
- {0x3009, (unsigned char) '>'}, // right angle bracket
- {0x301A, (unsigned char) '['}, // left white square bracket
- {0x301B, (unsigned char) ']'}, // right white square bracket
- {0x301D, (unsigned char) '"'}, // reversed double prime quotation mark
- {0x301E, (unsigned char) '"'} // double prime quotation mark
-};
-
-cet_cs_vec_t cet_cs_vec_ansi_x3_4_1968 = /* defined in cet.h */
-{
- cet_cs_name_ansi_x3_4_1968, /* name of character set */
- cet_cs_alias_ansi_x3_4_1968, /* alias table */
-
- nullptr, /* fallback character set */
- nullptr, /* unused */
-
- cet_ucs4_map_ansi_x3_4_1968, /* char to UCS-4 value table */
- cet_ucs4_ofs_ansi_x3_4_1968, /* first non standard character */
- cet_ucs4_cnt_ansi_x3_4_1968, /* number of values in table */
-
- cet_ucs4_to_ansi_x3_4_1968_links, /* UCS-4 to char links */
- cet_ucs4_to_ansi_x3_4_1968_ct, /* number of links */
-
- cet_ucs4_to_ansi_x3_4_1968_extra, /* hand made UCS-4 links */
- sizeof(cet_ucs4_to_ansi_x3_4_1968_extra) / sizeof(cet_ucs4_to_ansi_x3_4_1968_extra[0]), /* number of extra links */
-
- nullptr /* for internal use */
-};
-
-
-/*
-const int ansi_x3_4_1968_ucs4_full_map[] =
-{
- 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
- 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
- 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017,
- 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f,
- 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
- 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
- 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
- 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f,
- 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
- 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
- 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
- 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f,
- 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
- 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f,
- 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
- 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1
-};
-*/
-
-#endif
+++ /dev/null
-/*
-
- Data automatically generated from recode output:
-
- 'recode -lf "CP1252" 2>/dev/null'
-
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2 of the License, or
- (at your option) any later version.
-
- This program 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 General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
-
-*/
-
-#ifndef cp1252_h
-#define cp1252_h
-
-#define cet_cs_name_cp1252 "CP1252"
-
-const char *cet_cs_alias_cp1252[] =
-{
- "CP1252", "1252", "ms-ansi", "windows-1252", "WIN-CP1252",
- nullptr
-};
-
-#define cet_ucs4_ofs_cp1252 128
-#define cet_ucs4_cnt_cp1252 128
-
-const int cet_ucs4_map_cp1252[cet_ucs4_cnt_cp1252] =
-{
- 0x20ac, -1, 0x201a, 0x0192, 0x201e, 0x2026, 0x2020, 0x2021,
- 0x02c6, 0x2030, 0x0160, 0x2039, 0x0152, -1, 0x017d, -1,
- -1, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
- 0x02dc, 0x2122, 0x0161, 0x203a, 0x0153, -1, 0x017e, 0x0178,
- 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7,
- 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af,
- 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
- 0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf,
- 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7,
- 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf,
- 0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7,
- 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df,
- 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7,
- 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef,
- 0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7,
- 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff
-};
-
-#define cet_ucs4_to_cp1252_ct 27
-
-const cet_ucs4_link_t cet_ucs4_to_cp1252_links[cet_ucs4_to_cp1252_ct] =
-{
- {0x0152, 0x8c} /* capital ligature oe */,
- {0x0153, 0x9c} /* small ligature oe */,
- {0x0160, 0x8a} /* capital letter s with caron */,
- {0x0161, 0x9a} /* small letter s with caron */,
- {0x0178, 0x9f} /* capital letter y with diaeresis */,
- {0x017d, 0x8e} /* capital letter z with caron */,
- {0x017e, 0x9e} /* small letter z with caron */,
- {0x0192, 0x83} /* minuscule latine f hameçon */,
- {0x02c6, 0x88} /* modificative accent circonflexe */,
- {0x02dc, 0x98} /* tilde */,
- {0x2013, 0x96} /* dash */,
- {0x2014, 0x97} /* dash */,
- {0x2018, 0x91} /* single quotation mark */,
- {0x2019, 0x92} /* single quotation mark */,
- {0x201a, 0x82} /* low-9 quotation mark */,
- {0x201c, 0x93} /* double quotation mark */,
- {0x201d, 0x94} /* double quotation mark */,
- {0x201e, 0x84} /* low-9 quotation mark */,
- {0x2020, 0x86} /* dagger */,
- {0x2021, 0x87} /* dagger */,
- {0x2022, 0x95} /* puce */,
- {0x2026, 0x85} /* horizontal ellipsis */,
- {0x2030, 0x89} /* mille sign */,
- {0x2039, 0x8b} /* left-pointing angle quotation mark */,
- {0x203a, 0x9b} /* right-pointing angle quotation mark */,
- {0x20ac, 0x80} /* euro */,
- {0x2122, 0x99} /* mark sign */
-};
-
-/* Extra table was generated from bestfit1252.txt located at
- ftp.unicode.org:/Public/MAPPINGS/VENDORS/MICSFT/WindowsBestFit/ */
-
-const cet_ucs4_link_t cet_ucs4_to_cp1252_extra[] =
-{
- {0x0110, 0xd0} /* latin capital letter d with stroke */,
- {0x0189, 0xd0} /* latin capital letter african d */,
- {0x0191, 0x83} /* latin capital letter f with hook */,
- {0x02c9, 0xaf} /* modifier letter macron */,
- {0x02ca, 0xb4} /* modifier letter acute accent */,
- {0x02da, 0xb0} /* ring above */,
- {0x0301, 0xb4} /* combining acute accent */,
- {0x0304, 0xaf} /* combining macron */,
- {0x0305, 0xaf} /* combining overline */,
- {0x0308, 0xa8} /* combining diaeresis */,
- {0x030a, 0xb0} /* combining ring above */,
- {0x0327, 0xb8} /* combining cedilla */,
- {0x03b2, 0xdf} /* greek small letter beta */,
- {0x03bc, 0xb5} /* greek small letter mu */,
- {0x2024, 0xb7} /* one dot leader */,
- {0x2070, 0xb0} /* superscript zero */,
- {0x20a1, 0xa2} /* colon sign */,
- {0x20a4, 0xa3} /* lira sign */,
- {0x212b, 0xc5} /* angstrom sign */,
- {0x2205, 0xd8} /* empty set */,
- {0x2213, 0xb1} /* minus-or-plus sign */,
- {0x2218, 0xb0} /* ring operator */,
- {0x2219, 0xb7} /* bullet operator */,
- {0x2248, 0x98} /* almost equal to */,
- {0x226a, 0xab} /* much less-than */,
- {0x226b, 0xbb} /* much greater-than */,
- {0x22c5, 0xb7} /* dot operator */,
- {0x2302, 0xa6} /* house */,
- {0x2310, 0xac} /* reversed not sign */,
- {0x2502, 0xa6} /* box drawings light vertical */,
- {0x2524, 0xa6} /* box drawings light vertical and left */,
- {0x2551, 0xa6} /* box drawings double vertical */,
- {0x255e, 0xa6} /* box drawings vertical single and right double */,
- {0x255f, 0xa6} /* box drawings vertical double and right single */,
- {0x2560, 0xa6} /* box drawings double vertical and right */,
- {0x2561, 0xa6} /* box drawings vertical single and left double */,
- {0x2562, 0xa6} /* box drawings vertical double and left single */,
- {0x2563, 0xa6} /* box drawings double vertical and left */,
- {0x2580, 0xaf} /* upper half block */,
- {0x2588, 0xa6} /* full block */,
- {0x258c, 0xa6} /* left half block */,
- {0x2590, 0xa6} /* right half block */,
- {0x2591, 0xa6} /* light shade */,
- {0x2592, 0xa6} /* medium shade */,
- {0x2593, 0xa6} /* dark shade */,
- {0x25a0, 0xa6} /* black square */,
- {0x263c, 0xa4} /* white sun with rays */,
- {0x300a, 0xab} /* left double angle bracket */,
- {0x300b, 0xbb} /* right double angle bracket */,
- {0x30fb, 0xb7} /* katakana middle dot */
-};
-
-#define cet_ucs4_to_cp1252_extra_ct sizeof(cet_ucs4_to_cp1252_extra) / sizeof(cet_ucs4_to_cp1252_extra[0])
-
-cet_cs_vec_t cet_cs_vec_cp1252 = /* defined in cet.h */
-{
- cet_cs_name_cp1252, /* name of character set */
- cet_cs_alias_cp1252, /* alias table */
-
- nullptr, /* ... to UCS-4 converter (multi-byte) */
- nullptr, /* UCS-4 to ... converter (multi-byte) */
-
- cet_ucs4_map_cp1252, /* char to UCS-4 value table */
- cet_ucs4_ofs_cp1252, /* first non standard character */
- cet_ucs4_cnt_cp1252, /* number of values in table */
-
- cet_ucs4_to_cp1252_links, /* UCS-4 to char links */
- cet_ucs4_to_cp1252_ct, /* number of links */
-
- cet_ucs4_to_cp1252_extra, /* hand made UCS-4 links */
- cet_ucs4_to_cp1252_extra_ct, /* number of extra links */
-
- nullptr /* for internal use */
-};
-
-
-/*
-const int cp1252_ucs4_full_map[] =
-{
- 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
- 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
- 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017,
- 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f,
- 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
- 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
- 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
- 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f,
- 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
- 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
- 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
- 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f,
- 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
- 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f,
- 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
- 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f,
- 0x20ac, -1, 0x201a, 0x0192, 0x201e, 0x2026, 0x2020, 0x2021,
- 0x02c6, 0x2030, 0x0160, 0x2039, 0x0152, -1, 0x017d, 0x017e,
- -1, 0x2018, 0x2019, 0x201c, 0x201d, 0x2022, 0x2013, 0x2014,
- 0x02dc, 0x2122, 0x0161, 0x203a, 0x0153, -1, -1, 0x0178,
- 0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7,
- 0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af,
- 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
- 0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf,
- 0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7,
- 0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf,
- 0x00d0, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7,
- 0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x00dd, 0x00de, 0x00df,
- 0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7,
- 0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef,
- 0x00f0, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7,
- 0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x00fd, 0x00fe, 0x00ff
-};
-*/
-
-#endif
+++ /dev/null
-/*
-
- Data automatically generated from recode output:
-
- 'recode -lf "ISO-8859-8" 2>/dev/null'
-
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation; either version 2 of the License, or
- (at your option) any later version.
-
- This program 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 General Public License for more details.
-
- You should have received a copy of the GNU General Public License
- along with this program; if not, write to the Free Software
- Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
-
-*/
-
-#ifndef iso_8859_8_h
-#define iso_8859_8_h
-
-#define cet_cs_name_iso_8859_8 "ISO-8859-8"
-
-const char *cet_cs_alias_iso_8859_8[] =
-{
- "ISO-8859-8", "csISOLatinHebrew", "hebrew", "ISO8859-8",
- "iso-ir-138", "ISO_8859-8", "ISO_8859-8:1988", nullptr
-};
-
-#define cet_ucs4_ofs_iso_8859_8 161
-#define cet_ucs4_cnt_iso_8859_8 90
-
-const int cet_ucs4_map_iso_8859_8[cet_ucs4_cnt_iso_8859_8] =
-{
- -1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7, 0x00a8,
- 0x00a9, 0x00d7, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x203e, 0x00b0,
- 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7, 0x00b8,
- 0x00b9, 0x00f7, 0x00bb, 0x00bc, 0x00bd, 0x00be, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, 0x2017, 0x05d0,
- 0x05d1, 0x05d2, 0x05d3, 0x05d4, 0x05d5, 0x05d6, 0x05d7, 0x05d8,
- 0x05d9, 0x05da, 0x05db, 0x05dc, 0x05dd, 0x05de, 0x05df, 0x05e0,
- 0x05e1, 0x05e2, 0x05e3, 0x05e4, 0x05e5, 0x05e6, 0x05e7, 0x05e8,
- 0x05e9, 0x05ea
-};
-
-#define cet_ucs4_to_iso_8859_8_ct 31
-
-const cet_ucs4_link_t cet_ucs4_to_iso_8859_8_links[cet_ucs4_to_iso_8859_8_ct] =
-{
- {0x00d7, 0xaa} /* sign */,
- {0x00f7, 0xba} /* sign */,
- {0x05d0, 0xe0} /* letter alef */,
- {0x05d1, 0xe1} /* letter bet */,
- {0x05d2, 0xe2} /* letter gimel */,
- {0x05d3, 0xe3} /* letter dalet */,
- {0x05d4, 0xe4} /* letter he */,
- {0x05d5, 0xe5} /* letter vav */,
- {0x05d6, 0xe6} /* letter zayin */,
- {0x05d7, 0xe7} /* letter het */,
- {0x05d8, 0xe8} /* letter tet */,
- {0x05d9, 0xe9} /* letter yod */,
- {0x05da, 0xea} /* letter final kaf */,
- {0x05db, 0xeb} /* letter kaf */,
- {0x05dc, 0xec} /* letter lamed */,
- {0x05dd, 0xed} /* letter final mem */,
- {0x05de, 0xee} /* letter mem */,
- {0x05df, 0xef} /* letter final nun */,
- {0x05e0, 0xf0} /* letter nun */,
- {0x05e1, 0xf1} /* letter samekh */,
- {0x05e2, 0xf2} /* letter ayin */,
- {0x05e3, 0xf3} /* letter final pe */,
- {0x05e4, 0xf4} /* letter pe */,
- {0x05e5, 0xf5} /* letter final tsadi */,
- {0x05e6, 0xf6} /* letter tsadi */,
- {0x05e7, 0xf7} /* letter qof */,
- {0x05e8, 0xf8} /* letter resh */,
- {0x05e9, 0xf9} /* letter shin */,
- {0x05ea, 0xfa} /* letter tav */,
- {0x2017, 0xdf} /* low line */,
- {0x203e, 0xaf} /* overline */
-};
-
-/*
-#define cet_ucs4_to_iso_8859_8_extra_ct 0
-const cet_ucs4_link_t cet_ucs4_to_iso_8859_8_extra[cet_ucs4_to_iso_8859_8_extra_ct] = {};
-*/
-
-cet_cs_vec_t cet_cs_vec_iso_8859_8 = /* defined in cet.h */
-{
- cet_cs_name_iso_8859_8, /* name of character set */
- cet_cs_alias_iso_8859_8, /* alias table */
-
- nullptr, /* ... to UCS-4 converter (multi-byte) */
- nullptr, /* UCS-4 to ... converter (multi-byte) */
-
- cet_ucs4_map_iso_8859_8, /* char to UCS-4 value table */
- cet_ucs4_ofs_iso_8859_8, /* first non standard character */
- cet_ucs4_cnt_iso_8859_8, /* number of values in table */
-
- cet_ucs4_to_iso_8859_8_links, /* UCS-4 to char links */
- cet_ucs4_to_iso_8859_8_ct, /* number of links */
-
- nullptr, /* hand made UCS-4 links */
- 0, /* number of extra links */
-
- nullptr /* for internal use */
-};
-
-
-/*
-const int iso_8859_8_ucs4_full_map[] =
-{
- 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007,
- 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f,
- 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017,
- 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f,
- 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027,
- 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
- 0x0030, 0x0031, 0x0032, 0x0033, 0x0034, 0x0035, 0x0036, 0x0037,
- 0x0038, 0x0039, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f,
- 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047,
- 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f,
- 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057,
- 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f,
- 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067,
- 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f,
- 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077,
- 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f,
- 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087,
- 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f,
- 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097,
- 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f,
- 0x00a0, -1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7,
- 0x00a8, 0x00a9, 0x00d7, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x203e,
- 0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
- 0x00b8, 0x00b9, 0x00f7, 0x00bb, 0x00bc, 0x00bd, 0x00be, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, -1,
- -1, -1, -1, -1, -1, -1, -1, 0x2017,
- 0x05d0, 0x05d1, 0x05d2, 0x05d3, 0x05d4, 0x05d5, 0x05d6, 0x05d7,
- 0x05d8, 0x05d9, 0x05da, 0x05db, 0x05dc, 0x05dd, 0x05de, 0x05df,
- 0x05e0, 0x05e1, 0x05e2, 0x05e3, 0x05e4, 0x05e5, 0x05e6, 0x05e7,
- 0x05e8, 0x05e9, 0x05ea, -1, -1, -1, -1, -1
-};
-*/
-
-#endif
Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*/
-#include <cstdio> // for printf, snprintf
-#include <cstdlib> // for qsort
-
#include <QtCore/QByteArray> // for QByteArray
#include <QtCore/QDebug> // for QDebug
#include <QtCore/QTextCodec> // for QTextCodec
#include "defs.h"
-#include "cet.h" // for cet_cs_vec_t, cet_str_any_to_utf8, cet_str_utf8_to_any, cet_str_any_to_uni
#include "cet_util.h"
#include "src/core/logging.h" // for Fatal
#define MYNAME "cet_util"
-static cet_cs_vec_t* cet_cs_vec_root = nullptr;
-
-struct cet_cs_alias_t {
- char* name;
- cet_cs_vec_t* vec;
-};
-
-static cet_cs_alias_t* cet_cs_alias;
-static int cet_cs_alias_ct = 0;
-static int cet_cs_vec_ct = 0;
-
-/* %%% fixed inbuild character sets %%% */
-
-#include "cet/ansi_x3_4_1968.h" // for cet_cs_vec_ansi_x3_4_1968, cet_cs_name_ansi_x3_4_1968
-#include "cet/cp1252.h" // for cet_cs_name_cp1252, cet_cs_vec_cp1252
-#include "cet/iso_8859_8.h" // for cet_cs_name_iso_8859_8, cet_cs_vec_iso_8859_8
-
-
-/* %%% short hand strings transmission for main character sets %%% */
-
-short*
-cet_str_utf8_to_uni(const char* src, int* length)
-{
- return cet_str_any_to_uni(src, &cet_cs_vec_utf8, length);
-}
-
-/* %%% cet_str_any_to_any %%%
- *
- * -->> for use in mkshort */
-
-char*
-cet_str_any_to_any(const char* src, const cet_cs_vec_t* src_vec, const cet_cs_vec_t* dest_vec)
-{
- const cet_cs_vec_t* v_in = (src_vec != nullptr) ? src_vec : &cet_cs_vec_ansi_x3_4_1968;
- const cet_cs_vec_t* v_out = (dest_vec != nullptr) ? dest_vec : &cet_cs_vec_ansi_x3_4_1968;
-
- if (src == nullptr) {
- return nullptr;
- } else if ((*src == '\0') || (v_in == v_out)) {
- return xstrdup(src);
- }
-
- char* c0 = (v_in == &cet_cs_vec_utf8) ? xstrdup(src) : cet_str_any_to_utf8(src, v_in);
- char* c1 = (v_out == &cet_cs_vec_utf8) ? xstrdup(c0) : cet_str_utf8_to_any(c0, v_out);
- xfree(c0);
-
- return c1;
-}
-
-static signed int
-cet_cs_alias_qsort_cb(const void* a, const void* b)
-{
- const auto* va = (const cet_cs_alias_t*) a;
- const auto* vb = (const cet_cs_alias_t*) b;
- return case_ignore_strcmp(va->name, vb->name);
-}
-
-void
-cet_register_cs(cet_cs_vec_t* vec)
-{
- if (vec->next == nullptr) {
- vec->next = cet_cs_vec_root;
- cet_cs_vec_root = vec;
- cet_cs_vec_ct++;
- }
-}
-
-/* Dummy vector for our native character set */
-
-const char* cet_cs_utf8_alias[] = {
- "utf8", nullptr
-};
-
-cet_cs_vec_t cet_cs_vec_utf8 = {
- CET_CHARSET_UTF8,
- cet_cs_utf8_alias,
- nullptr,
- nullptr,
- nullptr,
- 0,
- 0,
- nullptr,
- 0,
- nullptr,
- 0,
- nullptr,
-};
-
-void
-cet_register()
-{
- int i, c;
-
- if (cet_cs_vec_root != nullptr) {
- return;
- }
-
- cet_cs_vec_ct = 0;
- cet_register_cs(&cet_cs_vec_utf8); /* internal place holder */
- // Alias for "US-ASCII".
-#ifdef cet_cs_name_ansi_x3_4_1968
- cet_register_cs(&cet_cs_vec_ansi_x3_4_1968);
-#endif
-#ifdef cet_cs_name_cp1252
- cet_register_cs(&cet_cs_vec_cp1252);
-#endif
-#ifdef cet_cs_name_iso_8859_8
- cet_register_cs(&cet_cs_vec_iso_8859_8);
-#endif
-
-
- if (cet_cs_vec_ct > 0) {
- cet_cs_vec_t* p;
- c = 0;
-
- /* enumerate count of all names and aliases */
-
- for (p = cet_cs_vec_root; p != nullptr; p = p->next) {
- c++;
- if (p->alias != nullptr) {
- const char** a = p->alias;
- while ((*a) != nullptr) {
- a++;
- c++;
- }
- }
- }
- /* create name to vec table */
-
- cet_cs_alias_t* list = (cet_cs_alias_t*) xcalloc(c, sizeof(*list));
- i = 0;
- for (p = cet_cs_vec_root; p != nullptr; p = p->next) {
- if (p->alias != nullptr) {
- const char** a = p->alias;
-
- list[i].name = xstrdup(p->name);
- list[i].vec = p;
- i++;
- while (*a != nullptr) {
- list[i].name = xstrdup(*a);
- list[i].vec = p;
- i++;
- a++;
- }
- }
- }
- qsort(list, c, sizeof(*list), cet_cs_alias_qsort_cb);
- cet_cs_alias = list;
- cet_cs_alias_ct = c;
-
- /* install fallback for ascii-like (first 128 ch.) character sets */
- for (i = 1250; i <= 1258; i++) {
- char name[16];
- cet_cs_vec_t* vec;
-
- snprintf(name, sizeof(name), "WIN-CP%d", i);
- if ((vec = cet_find_cs_by_name(name))) {
- vec->fallback = &cet_cs_vec_ansi_x3_4_1968;
- }
- }
- for (i = 1; i <= 15; i++) {
- char name[16];
- cet_cs_vec_t* vec;
-
- snprintf(name, sizeof(name), "ISO-8859-%d", i);
- if ((vec = cet_find_cs_by_name(name))) {
- vec->fallback = &cet_cs_vec_ansi_x3_4_1968;
- }
- }
- }
-#ifdef CET_DEBUG
- printf("We have registered %d character sets with %d aliases\n", cet_cs_vec_ct, cet_cs_alias_ct);
-#endif
-}
-
-cet_cs_vec_t*
-cet_find_cs_by_name(const QString& name)
-{
- cet_register();
-
- if (cet_cs_alias == nullptr) {
- return nullptr;
- }
-
- int i = 0;
- int j = cet_cs_alias_ct - 1;
-
- while (i <= j) {
- int a = (i + j) >> 1;
- auto n = &cet_cs_alias[a];
- int x = case_ignore_strcmp(name, n->name);
- if (x == 0) {
- return n->vec;
- } else if (x < 0) {
- j = a - 1;
- } else {
- i = a + 1;
- }
- }
- return nullptr;
-}
-
-void
-cet_deregister()
-{
- int j = cet_cs_alias_ct;
- cet_cs_alias_t* p = cet_cs_alias;
-
- if (p == nullptr) {
- return;
- }
-
- cet_cs_alias_ct = 0;
- cet_cs_alias = nullptr;
-
- for (int i = 0; i < j; i++) {
- xfree(p[i].name);
- }
- xfree(p);
-}
-
/* gpsbabel additions */
-int
-cet_validate_cs(const QString& cs, cet_cs_vec_t** vec, QString* cs_name)
-{
- if (cs.isEmpty()) { /* set default us-ascii */
- *vec = &cet_cs_vec_ansi_x3_4_1968;
- *cs_name = CET_CHARSET_ASCII;
- return 1;
- }
-
- cet_cs_vec_t* v = cet_find_cs_by_name(cs);
- if (v != nullptr) {
- // TODO: make v->name into q QString and replace this...
- char* tmp = xstrdup(v->name);
- *cs_name = strupper(tmp);
- xfree(tmp);
- *vec = v;
- return 1;
- } else {
- cs_name->clear();
- *vec = nullptr;
- return 0;
- }
-}
-
void
cet_convert_deinit()
{
- global_opts.charset = nullptr;
global_opts.codec = nullptr;
}
void
cet_convert_init(const QString& cs_name, const int force)
{
- if ((force != 0) || (global_opts.charset == nullptr)) {
+ if ((force != 0) || (global_opts.codec == nullptr)) {
cet_convert_deinit();
- if (0 == cet_validate_cs(cs_name, &global_opts.charset, &global_opts.charset_name)) {
- Fatal() << "Unsupported character set \"" << cs_name << ".";
- }
if (cs_name.isEmpty()) { /* set default us-ascii */
global_opts.codec = QTextCodec::codecForName(CET_CHARSET_ASCII);
} else {
- QByteArray ba = CSTR(cs_name);
- global_opts.codec = QTextCodec::codecForName(ba);
+ global_opts.codec = QTextCodec::codecForName(CSTR(cs_name));
}
if (!global_opts.codec) {
Fatal() << "Unsupported character set \"" << cs_name << ".";
#ifndef CET_UTIL_H_INCLUDED_
#define CET_UTIL_H_INCLUDED_
-#if HAVE_CONFIG_H
-#include "config.h"
-#endif
-
#include <QtCore/QString>
-#include "cet.h"
#include "defs.h"
-cet_cs_vec_t* cet_find_cs_by_name(const QString& name);
-void cet_register();
-void cet_deregister();
-
-extern cet_cs_vec_t cet_cs_vec_cp1252;
-
-extern cet_cs_vec_t cet_cs_vec_ansi_x3_4_1968;
-
-short* cet_str_utf8_to_uni(const char* src, int* length);
-
-extern cet_cs_vec_t cet_cs_vec_utf8;
-
-
-/* helpers */
-
-[[deprecated]] char* cet_str_any_to_any(const char* src, const cet_cs_vec_t* src_vec, const cet_cs_vec_t* dest_vec);
/* gpsbabel extensions */
int verbose_status; /* set by GUI wrappers for status */
int smart_icons;
int smart_names;
- cet_cs_vec_t* charset;
- QString charset_name;
inifile_t* inifile;
QTextCodec* codec;
};
}
- // If a user has specified a non-default character set, we'll trust
- // them to sort our the wreckage of violating the Garmin protocol and
- // ship characters to the device in that character set.
- if (global_opts.charset != &cet_cs_vec_utf8) {
- receiver_charset = xstrdup(global_opts.charset_name);
- }
if (global_opts.debug_level > 0) {
fprintf(stderr, "Waypoint type: %d\n"
"Chosen waypoint length %d\n",
}
}
- // Allow override of sent character set for internationalized GPSes.
- if (global_opts.charset != &cet_cs_vec_utf8) {
- receiver_charset = xstrdup(global_opts.charset_name);
- }
-
/*
* If the user provided a short_length, override the calculated value.
*/
setshort_mustupper(mkshort_handle, receiver_must_upper);
+ /*
+ * This used to mean something when we used cet, but these days this
+ * format either use implicit QString conversions (utf8) which is
+ * likely a bug, or we have hard coded QString::fromLatin1 or CSTRc.
+ * So all the above detection of receiver_charset is for naught.
+ * But perhaps we will use an appropriate codec based on receiver_charset
+ * someday.
+ */
if (receiver_charset) {
cet_convert_init(receiver_charset, 1);
}
if (trk_head == nullptr || array[i]->ishdr) {
trk_head = route_head_alloc();
trk_head->rte_num = trk_num;
- trk_head->rte_name = trk_name;
+ trk_head->rte_name = QString::fromLatin1(trk_name);
trk_num++;
track_add_head(trk_head);
}
rte_head = route_head_alloc();
route_add_head(rte_head);
if (csrc) {
- rte_head->rte_name = csrc;
+ rte_head->rte_name = QString::fromLatin1(csrc);
}
} else {
if (array[i]->islink) {
#endif
#include "defs.h"
-#include "cet_util.h" // for cet_convert_init, cet_convert_deinit, cet_deregister, cet_register, cet_cs_vec_utf8
+#include "cet_util.h" // for cet_convert_init, cet_convert_deinit
#include "csv_util.h" // for csv_linesplit
#include "filter.h" // for Filter
#include "filter_vecs.h" // for FilterVecs
global_opts.objective = wptdata;
global_opts.masked_objective = NOTHINGMASK; /* this makes the default mask behaviour slightly different */
- global_opts.charset_name.clear();
global_opts.inifile = nullptr;
gpsbabel_time = current_time().toTime_t(); /* frozen in testmode */
Vecs::Instance().init_vecs();
FilterVecs::Instance().init_filter_vecs();
- cet_register();
session_init();
waypt_init();
route_init();
rc = run(prog_name);
- cet_deregister();
waypt_flush_all();
route_deinit();
session_exit();
projects / gpsbabel.git / commitdiff