diff options
| author | Tom Lane <tgl@sss.pgh.pa.us> | 2006-05-21 20:06:18 +0000 |
|---|---|---|
| committer | Tom Lane <tgl@sss.pgh.pa.us> | 2006-05-21 20:06:18 +0000 |
| commit | 70794254a1cc8557e4bddafbfdc4ff2567c653ce (patch) | |
| tree | 258f3dbb8f56b7ede8a1ff5646722813e99f176f /src | |
| parent | 833e84621cf0ed48f1f5537aa5b569f333e02105 (diff) | |
| download | postgresql-70794254a1cc8557e4bddafbfdc4ff2567c653ce.tar.gz | |
Change the backend to reject strings containing invalidly-encoded multibyte
characters in all cases. Formerly we mostly just threw warnings for invalid
input, and failed to detect it at all if no encoding conversion was required.
The tighter check is needed to defend against SQL-injection attacks as per
CVE-2006-2313 (further details will be published after release). Embedded
zero (null) bytes will be rejected as well. The checks are applied during
input to the backend (receipt from client or COPY IN), so it no longer seems
necessary to check in textin() and related routines; any string arriving at
those functions will already have been validated. Conversion failure
reporting (for characters with no equivalent in the destination encoding)
has been cleaned up and made consistent while at it.
Also, fix a few longstanding errors in little-used encoding conversion
routines: win1251_to_iso, win866_to_iso, euc_tw_to_big5, euc_tw_to_mic,
mic_to_euc_tw were all broken to varying extents.
Patches by Tatsuo Ishii and Tom Lane. Thanks to Akio Ishida and Yasuo Ohgaki
for identifying the security issues.
Diffstat (limited to 'src')
34 files changed, 1323 insertions, 719 deletions
diff --git a/src/backend/commands/copy.c b/src/backend/commands/copy.c index 5db8856963..44077a3fb2 100644 --- a/src/backend/commands/copy.c +++ b/src/backend/commands/copy.c @@ -8,7 +8,7 @@ * * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/commands/copy.c,v 1.236.4.2 2005/10/03 23:43:29 tgl Exp $ + * $PostgreSQL: pgsql/src/backend/commands/copy.c,v 1.236.4.3 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -98,6 +98,7 @@ static bool fe_eof; /* true if detected end of copy data */ static EolType eol_type; /* EOL type of input */ static int client_encoding; /* remote side's character encoding */ static int server_encoding; /* local encoding */ +static int server_max_length; /* local encoding max length */ static bool embedded_line_warning; /* these are just for error messages, see copy_in_error_callback */ @@ -988,6 +989,7 @@ DoCopy(const CopyStmt *stmt) client_encoding = pg_get_client_encoding(); server_encoding = GetDatabaseEncoding(); + server_max_length = pg_database_encoding_max_length(); copy_dest = COPY_FILE; /* default */ copy_file = NULL; @@ -2010,7 +2012,8 @@ static bool CopyReadLine(void) { bool result; - bool change_encoding = (client_encoding != server_encoding); + bool change_encoding = (client_encoding != server_encoding || + server_max_length > 1); int c; int mblen; int j; diff --git a/src/backend/utils/adt/name.c b/src/backend/utils/adt/name.c index 1200ad9b34..211619ec15 100644 --- a/src/backend/utils/adt/name.c +++ b/src/backend/utils/adt/name.c @@ -14,7 +14,7 @@ * * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/adt/name.c,v 1.55 2004/12/31 22:01:22 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/adt/name.c,v 1.55.4.1 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -49,10 +49,7 @@ namein(PG_FUNCTION_ARGS) NameData *result; int len; - /* verify encoding */ len = strlen(s); - pg_verifymbstr(s, len, false); - len = pg_mbcliplen(s, len, NAMEDATALEN - 1); result = (NameData *) palloc0(NAMEDATALEN); diff --git a/src/backend/utils/adt/varchar.c b/src/backend/utils/adt/varchar.c index 40e771ffab..19b2de618a 100644 --- a/src/backend/utils/adt/varchar.c +++ b/src/backend/utils/adt/varchar.c @@ -8,7 +8,7 @@ * * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/adt/varchar.c,v 1.108.4.1 2005/12/22 22:50:14 tgl Exp $ + * $PostgreSQL: pgsql/src/backend/utils/adt/varchar.c,v 1.108.4.2 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -75,10 +75,7 @@ bpcharin(PG_FUNCTION_ARGS) int i; int charlen; /* number of charcters in the input string */ - /* verify encoding */ len = strlen(s); - pg_verifymbstr(s, len, false); - charlen = pg_mbstrlen(s); /* If typmod is -1 (or invalid), use the actual string length */ @@ -364,10 +361,7 @@ varcharin(PG_FUNCTION_ARGS) size_t len, maxlen; - /* verify encoding */ len = strlen(s); - pg_verifymbstr(s, len, false); - maxlen = atttypmod - VARHDRSZ; if (atttypmod >= (int32) VARHDRSZ && len > maxlen) diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c index f7f64add23..891c412d9e 100644 --- a/src/backend/utils/adt/varlena.c +++ b/src/backend/utils/adt/varlena.c @@ -8,7 +8,7 @@ * * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.118.4.1 2005/12/22 22:50:14 tgl Exp $ + * $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.118.4.2 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -260,10 +260,7 @@ textin(PG_FUNCTION_ARGS) text *result; int len; - /* verify encoding */ len = strlen(inputText); - pg_verifymbstr(inputText, len, false); - result = (text *) palloc(len + VARHDRSZ); VARATT_SIZEP(result) = len + VARHDRSZ; diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index c84d860e84..7997985b55 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -6,172 +6,81 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conv.c,v 1.51 2004/12/31 22:01:42 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conv.c,v 1.51.4.1 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ #include "postgres.h" #include "mb/pg_wchar.h" -/* - * convert bogus chars that cannot be represented in the current - * encoding system. - */ -void -pg_print_bogus_char(unsigned char **mic, unsigned char **p) -{ - char strbuf[16]; - int l = pg_mic_mblen(*mic); - - *(*p)++ = '('; - while (l--) - { - sprintf(strbuf, "%02x", *(*mic)++); - *(*p)++ = strbuf[0]; - *(*p)++ = strbuf[1]; - } - *(*p)++ = ')'; -} - -#ifdef NOT_USED - -/* - * GB18030 ---> MIC - * Added by Bill Huang <bhuang@redhat.com>,<bill_huanghb@ybb.ne.jp> - */ -static void -gb180302mic(unsigned char *gb18030, unsigned char *p, int len) -{ - int c1; - int c2; - - while (len > 0 && (c1 = *gb18030++)) - { - if (c1 < 0x80) - { /* should be ASCII */ - len--; - *p++ = c1; - } - else if (c1 >= 0x81 && c1 <= 0xfe) - { - c2 = *gb18030++; - - if (c2 >= 0x30 && c2 <= 0x69) - { - len -= 4; - *p++ = c1; - *p++ = c2; - *p++ = *gb18030++; - *p++ = *gb18030++; - *p++ = *gb18030++; - } - else if ((c2 >= 0x40 && c2 <= 0x7e) || (c2 >= 0x80 && c2 <= 0xfe)) - { - len -= 2; - *p++ = c1; - *p++ = c2; - *p++ = *gb18030++; - } - else - { /* throw the strange code */ - len--; - } - } - } - *p = '\0'; -} /* - * MIC ---> GB18030 - * Added by Bill Huang <bhuang@redhat.com>,<bill_huanghb@ybb.ne.jp> - */ -static void -mic2gb18030(unsigned char *mic, unsigned char *p, int len) -{ - int c1; - int c2; - - while (len > 0 && (c1 = *mic)) - { - len -= pg_mic_mblen(mic++); - - if (c1 <= 0x7f) /* ASCII */ - *p++ = c1; - else if (c1 >= 0x81 && c1 <= 0xfe) - { - c2 = *mic++; - - if ((c2 >= 0x40 && c2 <= 0x7e) || (c2 >= 0x80 && c2 <= 0xfe)) - { - *p++ = c1; - *p++ = c2; - } - else if (c2 >= 0x30 && c2 <= 0x39) - { - *p++ = c1; - *p++ = c2; - *p++ = *mic++; - *p++ = *mic++; - } - else - { - mic--; - pg_print_bogus_char(&mic, &p); - mic--; - pg_print_bogus_char(&mic, &p); - } - } - else - { - mic--; - pg_print_bogus_char(&mic, &p); - } - } - *p = '\0'; -} -#endif - -/* - * LATINn ---> MIC + * LATINn ---> MIC when the charset's local codes map directly to MIC + * + * l points to the source string of length len + * p is the output area (must be large enough!) + * lc is the mule character set id for the local encoding + * encoding is the PG identifier for the local encoding */ void -latin2mic(unsigned char *l, unsigned char *p, int len, int lc) +latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding) { int c1; - while (len-- > 0 && (c1 = *l++)) + while (len > 0) { - if (c1 > 0x7f) - { /* Latin? */ + c1 = *l; + if (c1 == 0) + report_invalid_encoding(encoding, (const char *) l, len); + if (IS_HIGHBIT_SET(c1)) *p++ = lc; - } *p++ = c1; + l++; + len--; } *p = '\0'; } /* - * MIC ---> LATINn + * MIC ---> LATINn when the charset's local codes map directly to MIC + * + * mic points to the source string of length len + * p is the output area (must be large enough!) + * lc is the mule character set id for the local encoding + * encoding is the PG identifier for the local encoding */ void -mic2latin(unsigned char *mic, unsigned char *p, int len, int lc) +mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding) { int c1; - while (len > 0 && (c1 = *mic)) + while (len > 0) { - len -= pg_mic_mblen(mic++); - - if (c1 == lc) - *p++ = *mic++; - else if (c1 > 0x7f) + c1 = *mic; + if (c1 == 0) + report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + if (!IS_HIGHBIT_SET(c1)) { - mic--; - pg_print_bogus_char(&mic, &p); + /* easy for ASCII */ + *p++ = c1; + mic++; + len--; } else - { /* should be ASCII */ - *p++ = c1; + { + int l = pg_mic_mblen(mic); + + if (len < l) + report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, + len); + if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1])) + report_untranslatable_char(PG_MULE_INTERNAL, encoding, + (const char *) mic, len); + *p++ = mic[1]; + mic += 2; + len -= 2; } } *p = '\0'; @@ -180,14 +89,25 @@ mic2latin(unsigned char *mic, unsigned char *p, int len, int lc) /* * ASCII ---> MIC + * + * While ordinarily SQL_ASCII encoding is forgiving of high-bit-set + * characters, here we must take a hard line because we don't know + * the appropriate MIC equivalent. */ void -pg_ascii2mic(unsigned char *l, unsigned char *p, int len) +pg_ascii2mic(const unsigned char *l, unsigned char *p, int len) { int c1; - while (len-- > 0 && (c1 = *l++)) - *p++ = (c1 & 0x7f); + while (len > 0) + { + c1 = *l; + if (c1 == 0 || IS_HIGHBIT_SET(c1)) + report_invalid_encoding(PG_SQL_ASCII, (const char *) l, len); + *p++ = c1; + l++; + len--; + } *p = '\0'; } @@ -195,19 +115,19 @@ pg_ascii2mic(unsigned char *l, unsigned char *p, int len) * MIC ---> ASCII */ void -pg_mic2ascii(unsigned char *mic, unsigned char *p, int len) +pg_mic2ascii(const unsigned char *mic, unsigned char *p, int len) { int c1; - while (len-- > 0 && (c1 = *mic)) + while (len > 0) { - if (c1 > 0x7f) - pg_print_bogus_char(&mic, &p); - else - { /* should be ASCII */ - *p++ = c1; - mic++; - } + c1 = *mic; + if (c1 == 0 || IS_HIGHBIT_SET(c1)) + report_untranslatable_char(PG_MULE_INTERNAL, PG_SQL_ASCII, + (const char *) mic, len); + *p++ = c1; + mic++; + len--; } *p = '\0'; } @@ -215,87 +135,103 @@ pg_mic2ascii(unsigned char *mic, unsigned char *p, int len) /* * latin2mic_with_table: a generic single byte charset encoding * conversion from a local charset to the mule internal code. - * with a encoding conversion table. - * the table is ordered according to the local charset, + * + * l points to the source string of length len + * p is the output area (must be large enough!) + * lc is the mule character set id for the local encoding + * encoding is the PG identifier for the local encoding + * tab holds conversion entries for the local charset * starting from 128 (0x80). each entry in the table * holds the corresponding code point for the mule internal code. */ void -latin2mic_with_table( - unsigned char *l, /* local charset string (source) */ - unsigned char *p, /* pointer to store mule internal - * code (destination) */ - int len, /* length of l */ - int lc, /* leading character of p */ - unsigned char *tab /* code conversion table */ -) +latin2mic_with_table(const unsigned char *l, + unsigned char *p, + int len, + int lc, + int encoding, + const unsigned char *tab) { unsigned char c1, c2; - while (len-- > 0 && (c1 = *l++)) + while (len > 0) { - if (c1 < 128) + c1 = *l; + if (c1 == 0) + report_invalid_encoding(encoding, (const char *) l, len); + if (!IS_HIGHBIT_SET(c1)) *p++ = c1; else { - c2 = tab[c1 - 128]; + c2 = tab[c1 - HIGHBIT]; if (c2) { *p++ = lc; *p++ = c2; } else - { - *p++ = ' '; /* cannot convert */ - } + report_untranslatable_char(encoding, PG_MULE_INTERNAL, + (const char *) l, len); } + l++; + len--; } *p = '\0'; } /* * mic2latin_with_table: a generic single byte charset encoding - * conversion from the mule internal code to a local charset - * with a encoding conversion table. - * the table is ordered according to the second byte of the mule - * internal code starting from 128 (0x80). - * each entry in the table - * holds the corresponding code point for the local code. + * conversion from the mule internal code to a local charset. + * + * mic points to the source string of length len + * p is the output area (must be large enough!) + * lc is the mule character set id for the local encoding + * encoding is the PG identifier for the local encoding + * tab holds conversion entries for the mule internal code's + * second byte, starting from 128 (0x80). each entry in the table + * holds the corresponding code point for the local charset. */ void -mic2latin_with_table( - unsigned char *mic, /* mule internal code - * (source) */ - unsigned char *p, /* local code (destination) */ - int len, /* length of p */ - int lc, /* leading character */ - unsigned char *tab /* code conversion table */ -) +mic2latin_with_table(const unsigned char *mic, + unsigned char *p, + int len, + int lc, + int encoding, + const unsigned char *tab) { - unsigned char c1, c2; - while (len-- > 0 && (c1 = *mic++)) + while (len > 0) { - if (c1 < 128) - *p++ = c1; - else if (c1 == lc) + c1 = *mic; + if (c1 == 0) + report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); + if (!IS_HIGHBIT_SET(c1)) { - c1 = *mic++; + /* easy for ASCII */ + *p++ = c1; + mic++; len--; - c2 = tab[c1 - 128]; - if (c2) - *p++ = c2; - else - { - *p++ = ' '; /* cannot convert */ - } } else { - *p++ = ' '; /* bogus character */ + int l = pg_mic_mblen(mic); + + if (len < l) + report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, + len); + if (l != 2 || c1 != lc || !IS_HIGHBIT_SET(mic[1]) || + (c2 = tab[mic[1] - HIGHBIT]) == 0) + { + report_untranslatable_char(PG_MULE_INTERNAL, encoding, + (const char *) mic, len); + break; /* keep compiler quiet */ + } + *p++ = c2; + mic += 2; + len -= 2; } } *p = '\0'; @@ -332,27 +268,40 @@ compare2(const void *p1, const void *p2) } /* - * UTF-8 ---> local code + * UTF8 ---> local code * - * utf: input UTF-8 string. Its length is limited by "len" parameter - * or a null terminator. - * iso: pointer to the output. + * utf: input UTF8 string (need not be null-terminated). + * iso: pointer to the output area (must be large enough!) * map: the conversion map. * size: the size of the conversion map. + * encoding: the PG identifier for the local encoding. + * len: length of input string. */ void -UtfToLocal(unsigned char *utf, unsigned char *iso, - pg_utf_to_local *map, int size, int len) +UtfToLocal(const unsigned char *utf, unsigned char *iso, + const pg_utf_to_local *map, int size, int encoding, int len) { unsigned int iutf; int l; pg_utf_to_local *p; - for (; len > 0 && *utf; len -= l) + for (; len > 0; len -= l) { + /* "break" cases all represent errors */ + if (*utf == '\0') + break; + l = pg_utf_mblen(utf); + + if (len < l) + break; + + if (!pg_utf8_islegal(utf, l)) + break; + if (l == 1) { + /* ASCII case is easy */ *iso++ = *utf++; continue; } @@ -361,22 +310,27 @@ UtfToLocal(unsigned char *utf, unsigned char *iso, iutf = *utf++ << 8; iutf |= *utf++; } - else + else if (l == 3) { iutf = *utf++ << 16; iutf |= *utf++ << 8; iutf |= *utf++; } + else if (l == 4) + { + iutf = *utf++ << 24; + iutf |= *utf++ << 16; + iutf |= *utf++ << 8; + iutf |= *utf++; + } + p = bsearch(&iutf, map, size, sizeof(pg_utf_to_local), compare1); + if (p == NULL) - { - ereport(WARNING, - (errcode(ERRCODE_UNTRANSLATABLE_CHARACTER), - errmsg("ignoring unconvertible UTF-8 character 0x%04x", - iutf))); - continue; - } + report_untranslatable_char(PG_UTF8, encoding, + (const char *) (utf - l), len); + if (p->code & 0xff000000) *iso++ = p->code >> 24; if (p->code & 0x00ff0000) @@ -386,15 +340,26 @@ UtfToLocal(unsigned char *utf, unsigned char *iso, if (p->code & 0x000000ff) *iso++ = p->code & 0x000000ff; } + + if (len > 0) + report_invalid_encoding(PG_UTF8, (const char *) utf, len); + *iso = '\0'; } /* - * local code ---> UTF-8 + * local code ---> UTF8 + * + * iso: input local string (need not be null-terminated). + * utf: pointer to the output area (must be large enough!) + * map: the conversion map. + * size: the size of the conversion map. + * encoding: the PG identifier for the local encoding. + * len: length of input string. */ void -LocalToUtf(unsigned char *iso, unsigned char *utf, - pg_local_to_utf *map, int size, int encoding, int len) +LocalToUtf(const unsigned char *iso, unsigned char *utf, + const pg_local_to_utf *map, int size, int encoding, int len) { unsigned int iiso; int l; @@ -405,16 +370,23 @@ LocalToUtf(unsigned char *iso, unsigned char *utf, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("invalid encoding number: %d", encoding))); - for (; len > 0 && *iso; len -= l) + for (; len > 0; len -= l) { - if (*iso < 0x80) + /* "break" cases all represent errors */ + if (*iso == '\0') + break; + + if (!IS_HIGHBIT_SET(*iso)) { + /* ASCII case is easy */ *utf++ = *iso++; l = 1; continue; } - l = pg_encoding_mblen(encoding, iso); + l = pg_encoding_verifymb(encoding, (const char *) iso, len); + if (l < 0) + break; if (l == 1) iiso = *iso++; @@ -436,16 +408,13 @@ LocalToUtf(unsigned char *iso, unsigned char *utf, iiso |= *iso++ << 8; iiso |= *iso++; } + p = bsearch(&iiso, map, size, sizeof(pg_local_to_utf), compare2); if (p == NULL) - { - ereport(WARNING, - (errcode(ERRCODE_UNTRANSLATABLE_CHARACTER), - errmsg("ignoring unconvertible %s character 0x%04x", - (&pg_enc2name_tbl[encoding])->name, iiso))); - continue; - } + report_untranslatable_char(encoding, PG_UTF8, + (const char *) (iso - l), len); + if (p->utf & 0xff000000) *utf++ = p->utf >> 24; if (p->utf & 0x00ff0000) @@ -455,5 +424,9 @@ LocalToUtf(unsigned char *iso, unsigned char *utf, if (p->utf & 0x000000ff) *utf++ = p->utf & 0x000000ff; } + + if (len > 0) + report_invalid_encoding(encoding, (const char *) iso, len); + *utf = '\0'; } diff --git a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c index 436218fd7f..0ccf97cfab 100644 --- a/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c,v 1.9 2004/12/31 22:01:48 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c,v 1.9.4.1 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -70,14 +70,14 @@ extern Datum alt_to_iso(PG_FUNCTION_ARGS); * ---------- */ -static void koi8r2mic(unsigned char *l, unsigned char *p, int len); -static void mic2koi8r(unsigned char *mic, unsigned char *p, int len); -static void iso2mic(unsigned char *l, unsigned char *p, int len); -static void mic2iso(unsigned char *mic, unsigned char *p, int len); -static void win12512mic(unsigned char *l, unsigned char *p, int len); -static void mic2win1251(unsigned char *mic, unsigned char *p, int len); -static void alt2mic(unsigned char *l, unsigned char *p, int len); -static void mic2alt(unsigned char *mic, unsigned char *p, int len); +static void koi8r2mic(const unsigned char *l, unsigned char *p, int len); +static void mic2koi8r(const unsigned char *mic, unsigned char *p, int len); +static void iso2mic(const unsigned char *l, unsigned char *p, int len); +static void mic2iso(const unsigned char *mic, unsigned char *p, int len); +static void win12512mic(const unsigned char *l, unsigned char *p, int len); +static void mic2win1251(const unsigned char *mic, unsigned char *p, int len); +static void alt2mic(const unsigned char *l, unsigned char *p, int len); +static void mic2alt(const unsigned char *mic, unsigned char *p, int len); Datum koi8r_to_mic(PG_FUNCTION_ARGS) @@ -401,7 +401,7 @@ win1251_to_iso(PG_FUNCTION_ARGS) buf = palloc(len * ENCODING_GROWTH_RATE); win12512mic(src, buf, len); - mic2win1251(buf, dest, strlen(buf)); + mic2iso(buf, dest, strlen(buf)); pfree(buf); PG_RETURN_VOID(); @@ -441,7 +441,7 @@ alt_to_iso(PG_FUNCTION_ARGS) buf = palloc(len * ENCODING_GROWTH_RATE); alt2mic(src, buf, len); - mic2alt(buf, dest, strlen(buf)); + mic2iso(buf, dest, strlen(buf)); pfree(buf); PG_RETURN_VOID(); @@ -460,23 +460,23 @@ alt_to_iso(PG_FUNCTION_ARGS) /* koi8r2mic: KOI8-R to Mule internal code */ static void -koi8r2mic(unsigned char *l, unsigned char *p, int len) +koi8r2mic(const unsigned char *l, unsigned char *p, int len) { - latin2mic(l, p, len, LC_KOI8_R); + latin2mic(l, p, len, LC_KOI8_R, PG_KOI8R); } /* mic2koi8r: Mule internal code to KOI8-R */ static void -mic2koi8r(unsigned char *mic, unsigned char *p, int len) +mic2koi8r(const unsigned char *mic, unsigned char *p, int len) { - mic2latin(mic, p, len, LC_KOI8_R); + mic2latin(mic, p, len, LC_KOI8_R, PG_KOI8R); } /* iso2mic: ISO-8859-5 to Mule internal code */ static void -iso2mic(unsigned char *l, unsigned char *p, int len) +iso2mic(const unsigned char *l, unsigned char *p, int len) { - static unsigned char iso2koi[] = { + static const unsigned char iso2koi[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -495,14 +495,14 @@ iso2mic(unsigned char *l, unsigned char *p, int len) 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; - latin2mic_with_table(l, p, len, LC_KOI8_R, iso2koi); + latin2mic_with_table(l, p, len, LC_KOI8_R, PG_ISO_8859_5, iso2koi); } /* mic2iso: Mule internal code to ISO8859-5 */ static void -mic2iso(unsigned char *mic, unsigned char *p, int len) +mic2iso(const unsigned char *mic, unsigned char *p, int len) { - static unsigned char koi2iso[] = { + static const unsigned char koi2iso[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -521,14 +521,14 @@ mic2iso(unsigned char *mic, unsigned char *p, int len) 0xcc, 0xcb, 0xb7, 0xc8, 0xcd, 0xc9, 0xc7, 0xca }; - mic2latin_with_table(mic, p, len, LC_KOI8_R, koi2iso); + mic2latin_with_table(mic, p, len, LC_KOI8_R, PG_ISO_8859_5, koi2iso); } /* win2mic: CP1251 to Mule internal code */ static void -win12512mic(unsigned char *l, unsigned char *p, int len) +win12512mic(const unsigned char *l, unsigned char *p, int len) { - static unsigned char win2koi[] = { + static const unsigned char win2koi[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -547,14 +547,14 @@ win12512mic(unsigned char *l, unsigned char *p, int len) 0xdb, 0xdd, 0xdf, 0xd9, 0xd8, 0xdc, 0xc0, 0xd1 }; - latin2mic_with_table(l, p, len, LC_KOI8_R, win2koi); + latin2mic_with_table(l, p, len, LC_KOI8_R, PG_WIN1251, win2koi); } /* mic2win: Mule internal code to CP1251 */ static void -mic2win1251(unsigned char *mic, unsigned char *p, int len) +mic2win1251(const unsigned char *mic, unsigned char *p, int len) { - static unsigned char koi2win[] = { + static const unsigned char koi2win[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -573,14 +573,14 @@ mic2win1251(unsigned char *mic, unsigned char *p, int len) 0xdc, 0xdb, 0xc7, 0xd8, 0xdd, 0xd9, 0xd7, 0xda }; - mic2latin_with_table(mic, p, len, LC_KOI8_R, koi2win); + mic2latin_with_table(mic, p, len, LC_KOI8_R, PG_WIN1251, koi2win); } /* alt2mic: CP866 to Mule internal code */ static void -alt2mic(unsigned char *l, unsigned char *p, int len) +alt2mic(const unsigned char *l, unsigned char *p, int len) { - static unsigned char alt2koi[] = { + static const unsigned char alt2koi[] = { 0xe1, 0xe2, 0xf7, 0xe7, 0xe4, 0xe5, 0xf6, 0xfa, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf2, 0xf3, 0xf4, 0xf5, 0xe6, 0xe8, 0xe3, 0xfe, @@ -599,14 +599,14 @@ alt2mic(unsigned char *l, unsigned char *p, int len) 0xb6, 0xa6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }; - latin2mic_with_table(l, p, len, LC_KOI8_R, alt2koi); + latin2mic_with_table(l, p, len, LC_KOI8_R, PG_ALT, alt2koi); } /* mic2alt: Mule internal code to CP866 */ static void -mic2alt(unsigned char *mic, unsigned char *p, int len) +mic2alt(const unsigned char *mic, unsigned char *p, int len) { - static unsigned char koi2alt[] = { + static const unsigned char koi2alt[] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, @@ -625,5 +625,5 @@ mic2alt(unsigned char *mic, unsigned char *p, int len) 0x9c, 0x9b, 0x87, 0x98, 0x9d, 0x99, 0x97, 0x9a }; - mic2latin_with_table(mic, p, len, LC_KOI8_R, koi2alt); + mic2latin_with_table(mic, p, len, LC_KOI8_R, PG_ALT, koi2alt); } diff --git a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c index 30d7bf7634..4d3bdfe2d1 100644 --- a/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c,v 1.9 2004/12/31 22:01:51 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_cn_and_mic/euc_cn_and_mic.c,v 1.9.4.1 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -32,8 +32,8 @@ extern Datum mic_to_euc_cn(PG_FUNCTION_ARGS); * ---------- */ -static void euc_cn2mic(unsigned char *euc, unsigned char *p, int len); -static void mic2euc_cn(unsigned char *mic, unsigned char *p, int len); +static void euc_cn2mic(const unsigned char *euc, unsigned char *p, int len); +static void mic2euc_cn(const unsigned char *mic, unsigned char *p, int len); Datum euc_cn_to_mic(PG_FUNCTION_ARGS) @@ -71,23 +71,30 @@ mic_to_euc_cn(PG_FUNCTION_ARGS) * EUC_CN ---> MIC */ static void -euc_cn2mic(unsigned char *euc, unsigned char *p, int len) +euc_cn2mic(const unsigned char *euc, unsigned char *p, int len) { int c1; - while (len >= 0 && (c1 = *euc++)) + while (len > 0) { - if (c1 & 0x80) + c1 = *euc; + if (IS_HIGHBIT_SET(c1)) { - len -= 2; + if (len < 2 || !IS_HIGHBIT_SET(euc[1])) + report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); *p++ = LC_GB2312_80; *p++ = c1; - *p++ = *euc++; + *p++ = euc[1]; + euc += 2; + len -= 2; } else { /* should be ASCII */ - len--; + if (c1 == 0) + report_invalid_encoding(PG_EUC_CN, (const char *) euc, len); *p++ = c1; + euc++; + len--; } } *p = '\0'; @@ -97,27 +104,34 @@ euc_cn2mic(unsigned char *euc, unsigned char *p, int len) * MIC ---> EUC_CN */ static void -mic2euc_cn(unsigned char *mic, unsigned char *p, int len) +mic2euc_cn(const unsigned char *mic, unsigned char *p, int len) { int c1; - while (len >= 0 && (c1 = *mic)) + while (len > 0) { - len -= pg_mic_mblen(mic++); - - if (c1 == LC_GB2312_80) + c1 = *mic; + if (IS_HIGHBIT_SET(c1)) { + if (c1 != LC_GB2312_80) + report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_CN, + (const char *) mic, len); + if (len < 3 || !IS_HIGHBIT_SET(mic[1]) || !IS_HIGHBIT_SET(mic[2])) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); + mic++; *p++ = *mic++; *p++ = *mic++; - } - else if (c1 > 0x7f) - { /* cannot convert to EUC_CN! */ - mic--; - pg_print_bogus_char(&mic, &p); + len -= 3; } else { /* should be ASCII */ + if (c1 == 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); *p++ = c1; + mic++; + len--; } } *p = '\0'; diff --git a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c index 0958af9cd7..6dba03b52f 100644 --- a/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c,v 1.9.4.3 2006/03/04 12:37:01 ishii Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_jp_and_sjis/euc_jp_and_sjis.c,v 1.9.4.4 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -22,9 +22,6 @@ #define PGSJISALTCODE 0x81ac #define PGEUCALTCODE 0xa2ae -#define ISSJISHEAD(c) ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xfc)) -#define ISSJISTAIL(c) ((c >= 0x40 && c <= 0x7e) || (c >= 0x80 && c <= 0xfc)) - /* * conversion table between SJIS UDC (IBM kanji) and EUC_JP */ @@ -57,10 +54,10 @@ extern Datum mic_to_sjis(PG_FUNCTION_ARGS); * ---------- */ -static void sjis2mic(unsigned char *sjis, unsigned char *p, int len); -static void mic2sjis(unsigned char *mic, unsigned char *p, int len); -static void euc_jp2mic(unsigned char *euc, unsigned char *p, int len); -static void mic2euc_jp(unsigned char *mic, unsigned char *p, int len); +static void sjis2mic(const unsigned char *sjis, unsigned char *p, int len); +static void mic2sjis(const unsigned char *mic, unsigned char *p, int len); +static void euc_jp2mic(const unsigned char *euc, unsigned char *p, int len); +static void mic2euc_jp(const unsigned char *mic, unsigned char *p, int len); Datum euc_jp_to_sjis(PG_FUNCTION_ARGS) @@ -170,38 +167,34 @@ mic_to_sjis(PG_FUNCTION_ARGS) * SJIS ---> MIC */ static void -sjis2mic(unsigned char *sjis, unsigned char *p, int len) +sjis2mic(const unsigned char *sjis, unsigned char *p, int len) { int c1, c2, -/* Eiji Tokuya patched begin */ i, k, k2; -/* Eiji Tokuya patched end */ - while (len >= 0 && (c1 = *sjis++)) + while (len > 0) { + c1 = *sjis; if (c1 >= 0xa1 && c1 <= 0xdf) { /* JIS X0201 (1 byte kana) */ - len--; *p++ = LC_JISX0201K; *p++ = c1; + sjis++; + len--; } - else if (c1 > 0x7f) + else if (IS_HIGHBIT_SET(c1)) { /* * JIS X0208, X0212, user defined extended characters */ - c2 = *sjis++; - if (!ISSJISHEAD(c1) || !ISSJISTAIL(c2)) - ereport(ERROR, - (errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE), - errmsg("invalid byte sequence for encoding \"SJIS\": 0x%02x%02x", - c1, c2))); + if (len < 2 || !ISSJISHEAD(c1) || !ISSJISTAIL(sjis[1])) + report_invalid_encoding(PG_SJIS, (const char *) sjis, len); + c2 = sjis[1]; k = (c1 << 8) + c2; -/* Eiji Tokuya patched begin */ if (k >= 0xed40 && k < 0xf040) { /* NEC selection IBM kanji */ @@ -220,19 +213,15 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len) } if (k < 0xeb3f) -/* Eiji Tokuya patched end */ { /* JIS X0208 */ - len -= 2; *p++ = LC_JISX0208; *p++ = ((c1 & 0x3f) << 1) + 0x9f + (c2 > 0x9e); *p++ = c2 + ((c2 > 0x9e) ? 2 : 0x60) + (c2 < 0x80); } -/* Eiji Tokuya patched begin */ else if ((k >= 0xeb40 && k < 0xf040) || (k >= 0xfc4c && k <= 0xfcfc)) { /* NEC selection IBM kanji - Other undecided justice */ -/* Eiji Tokuya patched end */ *p++ = LC_JISX0208; *p++ = PGEUCALTCODE >> 8; *p++ = PGEUCALTCODE & 0xff; @@ -243,7 +232,6 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len) * UDC1 mapping to X0208 85 ku - 94 ku JIS code 0x7521 - * 0x7e7e EUC 0xf5a1 - 0xfefe */ - len -= 2; *p++ = LC_JISX0208; c1 -= 0x6f; *p++ = ((c1 & 0x3f) << 1) + 0xf3 + (c2 > 0x9e); @@ -255,7 +243,6 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len) * UDC2 mapping to X0212 85 ku - 94 ku JIS code 0x7521 - * 0x7e7e EUC 0x8ff5a1 - 0x8ffefe */ - len -= 2; *p++ = LC_JISX0212; c1 -= 0x74; *p++ = ((c1 & 0x3f) << 1) + 0xf3 + (c2 > 0x9e); @@ -265,9 +252,7 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len) { /* * mapping IBM kanji to X0208 and X0212 - * */ - len -= 2; for (i = 0;; i++) { k2 = ibmkanji[i].sjis; @@ -291,11 +276,16 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len) } } } + sjis += 2; + len -= 2; } else { /* should be ASCII */ - len--; + if (c1 == 0) + report_invalid_encoding(PG_SJIS, (const char *) sjis, len); *p++ = c1; + sjis++; + len--; } } *p = '\0'; @@ -305,22 +295,37 @@ sjis2mic(unsigned char *sjis, unsigned char *p, int len) * MIC ---> SJIS */ static void -mic2sjis(unsigned char *mic, unsigned char *p, int len) +mic2sjis(const unsigned char *mic, unsigned char *p, int len) { int c1, c2, - k; + k, + l; - while (len >= 0 && (c1 = *mic)) + while (len > 0) { - len -= pg_mic_mblen(mic++); - + c1 = *mic; + if (!IS_HIGHBIT_SET(c1)) + { + /* ASCII */ + if (c1 == 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); + *p++ = c1; + mic++; + len--; + continue; + } + l = pg_encoding_verifymb(PG_MULE_INTERNAL, (const char *) mic, len); + if (l < 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); if (c1 == LC_JISX0201K) - *p++ = *mic++; + *p++ = mic[1]; else if (c1 == LC_JISX0208) { - c1 = *mic++; - c2 = *mic++; + c1 = mic[1]; + c2 = mic[2]; k = (c1 << 8) | (c2 & 0xff); if (k >= 0xf5a1) { @@ -337,8 +342,8 @@ mic2sjis(unsigned char *mic, unsigned char *p, int len) int i, k2; - c1 = *mic++; - c2 = *mic++; + c1 = mic[1]; + c2 = mic[2]; k = c1 << 8 | c2; if (k >= 0xf5a1) { @@ -369,16 +374,11 @@ mic2sjis(unsigned char *mic, unsigned char *p, int len) } } } - else if (c1 > 0x7f) - { - /* cannot convert to SJIS! */ - *p++ = PGSJISALTCODE >> 8; - *p++ = PGSJISALTCODE & 0xff; - } else - { /* should be ASCII */ - *p++ = c1; - } + report_untranslatable_char(PG_MULE_INTERNAL, PG_SJIS, + (const char *) mic, len); + mic += l; + len -= l; } *p = '\0'; } @@ -387,37 +387,48 @@ mic2sjis(unsigned char *mic, unsigned char *p, int len) * EUC_JP ---> MIC */ static void -euc_jp2mic(unsigned char *euc, unsigned char *p, int len) +euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) { int c1; + int l; - while (len >= 0 && (c1 = *euc++)) + while (len > 0) { + c1 = *euc; + if (!IS_HIGHBIT_SET(c1)) + { + /* ASCII */ + if (c1 == 0) + report_invalid_encoding(PG_EUC_JP, + (const char *) euc, len); + *p++ = c1; + euc++; + len--; + continue; + } + l = pg_encoding_verifymb(PG_EUC_JP, (const char *) euc, len); + if (l < 0) + report_invalid_encoding(PG_EUC_JP, + (const char *) euc, len); if (c1 == SS2) { /* 1 byte kana? */ - len -= 2; *p++ = LC_JISX0201K; - *p++ = *euc++; + *p++ = euc[1]; } else if (c1 == SS3) { /* JIS X0212 kanji? */ - len -= 3; *p++ = LC_JISX0212; - *p++ = *euc++; - *p++ = *euc++; + *p++ = euc[1]; + *p++ = euc[2]; } - else if (c1 & 0x80) + else { /* kanji? */ - len -= 2; *p++ = LC_JISX0208; *p++ = c1; - *p++ = *euc++; - } - else - { /* should be ASCII */ - len--; - *p++ = c1; + *p++ = euc[1]; } + euc += l; + len -= l; } *p = '\0'; } @@ -426,39 +437,50 @@ euc_jp2mic(unsigned char *euc, unsigned char *p, int len) * MIC ---> EUC_JP */ static void -mic2euc_jp(unsigned char *mic, unsigned char *p, int len) +mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) { int c1; + int l; - while (len >= 0 && (c1 = *mic)) + while (len > 0) { - len -= pg_mic_mblen(mic++); - + c1 = *mic; + if (!IS_HIGHBIT_SET(c1)) + { + /* ASCII */ + if (c1 == 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); + *p++ = c1; + mic++; + len--; + continue; + } + l = pg_encoding_verifymb(PG_MULE_INTERNAL, (const char *) mic, len); + if (l < 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); if (c1 == LC_JISX0201K) { *p++ = SS2; - *p++ = *mic++; + *p++ = mic[1]; } else if (c1 == LC_JISX0212) { *p++ = SS3; - *p++ = *mic++; - *p++ = *mic++; + *p++ = mic[1]; + *p++ = mic[2]; } else if (c1 == LC_JISX0208) { - *p++ = *mic++; - *p++ = *mic++; - } - else if (c1 > 0x7f) - { /* cannot convert to EUC_JP! */ - mic--; - pg_print_bogus_char(&mic, &p); + *p++ = mic[1]; + *p++ = mic[2]; } else - { /* should be ASCII */ - *p++ = c1; - } + report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_JP, + (const char *) mic, len); + mic += l; + len -= l; } *p = '\0'; } diff --git a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c index be7df0fc43..4ef0302cc8 100644 --- a/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c,v 1.9 2004/12/31 22:01:56 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_kr_and_mic/euc_kr_and_mic.c,v 1.9.4.1 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -32,8 +32,8 @@ extern Datum mic_to_euc_kr(PG_FUNCTION_ARGS); * ---------- */ -static void euc_kr2mic(unsigned char *euc, unsigned char *p, int len); -static void mic2euc_kr(unsigned char *mic, unsigned char *p, int len); +static void euc_kr2mic(const unsigned char *euc, unsigned char *p, int len); +static void mic2euc_kr(const unsigned char *mic, unsigned char *p, int len); Datum euc_kr_to_mic(PG_FUNCTION_ARGS) @@ -71,23 +71,34 @@ mic_to_euc_kr(PG_FUNCTION_ARGS) * EUC_KR ---> MIC */ static void -euc_kr2mic(unsigned char *euc, unsigned char *p, int len) +euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) { int c1; + int l; - while (len >= 0 && (c1 = *euc++)) + while (len > 0) { - if (c1 & 0x80) + c1 = *euc; + if (IS_HIGHBIT_SET(c1)) { - len -= 2; + l = pg_encoding_verifymb(PG_EUC_KR, (const char *) euc, len); + if (l != 2) + report_invalid_encoding(PG_EUC_KR, + (const char *) euc, len); *p++ = LC_KS5601; *p++ = c1; - *p++ = *euc++; + *p++ = euc[1]; + euc += 2; + len -= 2; } else { /* should be ASCII */ - len--; + if (c1 == 0) + report_invalid_encoding(PG_EUC_KR, + (const char *) euc, len); *p++ = c1; + euc++; + len--; } } *p = '\0'; @@ -97,28 +108,39 @@ euc_kr2mic(unsigned char *euc, unsigned char *p, int len) * MIC ---> EUC_KR */ static void -mic2euc_kr(unsigned char *mic, unsigned char *p, int len) +mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) { int c1; + int l; - while (len >= 0 && (c1 = *mic)) + while (len > 0) { - len -= pg_mic_mblen(mic++); - - if (c1 == LC_KS5601) + c1 = *mic; + if (!IS_HIGHBIT_SET(c1)) { - *p++ = *mic++; - *p++ = *mic++; + /* ASCII */ + if (c1 == 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); + *p++ = c1; + mic++; + len--; + continue; } - else if (c1 > 0x7f) - { /* cannot convert to EUC_KR! */ - mic--; - pg_print_bogus_char(&mic, &p); + l = pg_encoding_verifymb(PG_MULE_INTERNAL, (const char *) mic, len); + if (l < 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); + if (c1 == LC_KS5601) + { + *p++ = mic[1]; + *p++ = mic[2]; } else - { /* should be ASCII */ - *p++ = c1; - } + report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_KR, + (const char *) mic, len); + mic += l; + len -= l; } *p = '\0'; } diff --git a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c index 5cd6c0b763..8e3fd653c4 100644 --- a/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c,v 1.9 2004/12/31 22:02:07 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_tw_and_big5/euc_tw_and_big5.c,v 1.9.4.1 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -42,10 +42,10 @@ extern Datum mic_to_big5(PG_FUNCTION_ARGS); * ---------- */ -static void big52mic(unsigned char *big5, unsigned char *p, int len); -static void mic2big5(unsigned char *mic, unsigned char *p, int len); -static void euc_tw2mic(unsigned char *euc, unsigned char *p, int len); -static void mic2euc_tw(unsigned char *mic, unsigned char *p, int len); +static void big52mic(const unsigned char *big5, unsigned char *p, int len); +static void mic2big5(const unsigned char *mic, unsigned char *p, int len); +static void euc_tw2mic(const unsigned char *euc, unsigned char *p, int len); +static void mic2euc_tw(const unsigned char *mic, unsigned char *p, int len); Datum euc_tw_to_big5(PG_FUNCTION_ARGS) @@ -114,7 +114,7 @@ mic_to_euc_tw(PG_FUNCTION_ARGS) Assert(PG_GETARG_INT32(1) == PG_EUC_TW); Assert(len >= 0); - mic2big5(src, dest, len); + mic2euc_tw(src, dest, len); PG_RETURN_VOID(); } @@ -155,39 +155,52 @@ mic_to_big5(PG_FUNCTION_ARGS) * EUC_TW ---> MIC */ static void -euc_tw2mic(unsigned char *euc, unsigned char *p, int len) +euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) { int c1; + int l; - while (len >= 0 && (c1 = *euc++)) + while (len > 0) { - if (c1 == SS2) + c1 = *euc; + if (IS_HIGHBIT_SET(c1)) { - len -= 4; - c1 = *euc++; /* plane No. */ - if (c1 == 0xa1) - *p++ = LC_CNS11643_1; - else if (c1 == 0xa2) - *p++ = LC_CNS11643_2; - else + l = pg_encoding_verifymb(PG_EUC_TW, (const char *) euc, len); + if (l < 0) + report_invalid_encoding(PG_EUC_TW, + (const char *) euc, len); + if (c1 == SS2) { - *p++ = 0x9d; /* LCPRV2 */ - *p++ = 0xa3 - c1 + LC_CNS11643_3; + c1 = euc[1]; /* plane No. */ + if (c1 == 0xa1) + *p++ = LC_CNS11643_1; + else if (c1 == 0xa2) + *p++ = LC_CNS11643_2; + else + { + *p++ = 0x9d; /* LCPRV2 */ + *p++ = c1 - 0xa3 + LC_CNS11643_3; + } + *p++ = euc[2]; + *p++ = euc[3]; } - *p++ = *euc++; - *p++ = *euc++; - } - else if (c1 & 0x80) - { /* CNS11643-1 */ - len -= 2; - *p++ = LC_CNS11643_1; - *p++ = c1; - *p++ = *euc++; + else + { /* CNS11643-1 */ + *p++ = LC_CNS11643_1; + *p++ = c1; + *p++ = euc[1]; + } + euc += l; + len -= l; } else { /* should be ASCII */ - len--; + if (c1 == 0) + report_invalid_encoding(PG_EUC_TW, + (const char *) euc, len); *p++ = c1; + euc++; + len--; } } *p = '\0'; @@ -197,42 +210,54 @@ euc_tw2mic(unsigned char *euc, unsigned char *p, int len) * MIC ---> EUC_TW */ static void -mic2euc_tw(unsigned char *mic, unsigned char *p, int len) +mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) { int c1; + int l; - while (len >= 0 && (c1 = *mic)) + while (len > 0) { - len -= pg_mic_mblen(mic++); - + c1 = *mic; + if (!IS_HIGHBIT_SET(c1)) + { + /* ASCII */ + if (c1 == 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); + *p++ = c1; + mic++; + len--; + continue; + } + l = pg_encoding_verifymb(PG_MULE_INTERNAL, (const char *) mic, len); + if (l < 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); if (c1 == LC_CNS11643_1) { - *p++ = *mic++; - *p++ = *mic++; + *p++ = mic[1]; + *p++ = mic[2]; } else if (c1 == LC_CNS11643_2) { *p++ = SS2; *p++ = 0xa2; - *p++ = *mic++; - *p++ = *mic++; + *p++ = mic[1]; + *p++ = mic[2]; } - else if (c1 == 0x9d) + else if (c1 == 0x9d && + mic[1] >= LC_CNS11643_3 && mic[1] <= LC_CNS11643_7) { /* LCPRV2? */ *p++ = SS2; - *p++ = *mic++ - LC_CNS11643_3 + 0xa3; - *p++ = *mic++; - *p++ = *mic++; - } - else if (c1 > 0x7f) - { /* cannot convert to EUC_TW! */ - mic--; - pg_print_bogus_char(&mic, &p); + *p++ = mic[1] - LC_CNS11643_3 + 0xa3; + *p++ = mic[2]; + *p++ = mic[3]; } else - { /* should be ASCII */ - *p++ = c1; - } + report_untranslatable_char(PG_MULE_INTERNAL, PG_EUC_TW, + (const char *) mic, len); + mic += l; + len -= l; } *p = '\0'; } @@ -241,52 +266,49 @@ mic2euc_tw(unsigned char *mic, unsigned char *p, int len) * Big5 ---> MIC */ static void -big52mic(unsigned char *big5, unsigned char *p, int len) +big52mic(const unsigned char *big5, unsigned char *p, int len) { unsigned short c1; unsigned short big5buf, cnsBuf; unsigned char lc; - char bogusBuf[3]; - int i; + int l; - while (len >= 0 && (c1 = *big5++)) + while (len > 0) { - if (c1 <= 0x7fU) - { /* ASCII */ - len--; + c1 = *big5; + if (!IS_HIGHBIT_SET(c1)) + { + /* ASCII */ + if (c1 == 0) + report_invalid_encoding(PG_BIG5, + (const char *) big5, len); *p++ = c1; + big5++; + len--; + continue; } - else + l = pg_encoding_verifymb(PG_BIG5, (const char *) big5, len); + if (l < 0) + report_invalid_encoding(PG_BIG5, + (const char *) big5, len); + big5buf = (c1 << 8) | big5[1]; + cnsBuf = BIG5toCNS(big5buf, &lc); + if (lc != 0) { - len -= 2; - big5buf = c1 << 8; - c1 = *big5++; - big5buf |= c1; - cnsBuf = BIG5toCNS(big5buf, &lc); - if (lc != 0) + if (lc == LC_CNS11643_3 || lc == LC_CNS11643_4) { - if (lc == LC_CNS11643_3 || lc == LC_CNS11643_4) - { - *p++ = 0x9d; /* LCPRV2 */ - } - *p++ = lc; /* Plane No. */ - *p++ = (cnsBuf >> 8) & 0x00ff; - *p++ = cnsBuf & 0x00ff; - } - else - { /* cannot convert */ - big5 -= 2; - *p++ = '('; - for (i = 0; i < 2; i++) - { - sprintf(bogusBuf, "%02x", *big5++); - *p++ = bogusBuf[0]; - *p++ = bogusBuf[1]; - } - *p++ = ')'; + *p++ = 0x9d; /* LCPRV2 */ } + *p++ = lc; /* Plane No. */ + *p++ = (cnsBuf >> 8) & 0x00ff; + *p++ = cnsBuf & 0x00ff; } + else + report_untranslatable_char(PG_BIG5, PG_MULE_INTERNAL, + (const char *) big5, len); + big5 += l; + len -= l; } *p = '\0'; } @@ -295,46 +317,55 @@ big52mic(unsigned char *big5, unsigned char *p, int len) * MIC ---> Big5 */ static void -mic2big5(unsigned char *mic, unsigned char *p, int len) +mic2big5(const unsigned char *mic, unsigned char *p, int len) { - int l; unsigned short c1; unsigned short big5buf, cnsBuf; + int l; - while (len >= 0 && (c1 = *mic)) + while (len > 0) { - l = pg_mic_mblen(mic++); - len -= l; - + c1 = *mic; + if (!IS_HIGHBIT_SET(c1)) + { + /* ASCII */ + if (c1 == 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); + *p++ = c1; + mic++; + len--; + continue; + } + l = pg_encoding_verifymb(PG_MULE_INTERNAL, (const char *) mic, len); + if (l < 0) + report_invalid_encoding(PG_MULE_INTERNAL, + (const char *) mic, len); /* 0x9d means LCPRV2 */ if (c1 == LC_CNS11643_1 || c1 == LC_CNS11643_2 || c1 == 0x9d) { if (c1 == 0x9d) { - c1 = *mic++; /* get plane no. */ - } - cnsBuf = (*mic++) << 8; - cnsBuf |= (*mic++) & 0x00ff; - big5buf = CNStoBIG5(cnsBuf, c1); - if (big5buf == 0) - { /* cannot convert to Big5! */ - mic -= l; - pg_print_bogus_char(&mic, &p); + c1 = mic[1]; /* get plane no. */ + cnsBuf = (mic[2] << 8) | mic[3]; } else { - *p++ = (big5buf >> 8) & 0x00ff; - *p++ = big5buf & 0x00ff; + cnsBuf = (mic[1] << 8) | mic[2]; } + big5buf = CNStoBIG5(cnsBuf, c1); + if (big5buf == 0) + report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, + (const char *) mic, len); + *p++ = (big5buf >> 8) & 0x00ff; + *p++ = big5buf & 0x00ff; } - else if (c1 <= 0x7f) /* ASCII */ - *p++ = c1; else - { /* cannot convert to Big5! */ - mic--; - pg_print_bogus_char(&mic, &p); - } + report_untranslatable_char(PG_MULE_INTERNAL, PG_BIG5, + (const char *) mic, len); + mic += l; + len -= l; } *p = '\0'; } diff --git a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c index ec2da8bf9f..6f5bb71a38 100644 --- a/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c,v 1.9 2004/12/31 22:02:08 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/latin2_and_win1250/latin2_and_win1250.c,v 1.9.4.1 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -42,10 +42,10 @@ extern Datum win1250_to_latin2(PG_FUNCTION_ARGS); * ---------- */ -static void latin22mic(unsigned char *l, unsigned char *p, int len); -static void mic2latin2(unsigned char *mic, unsigned char *p, int len); -static void win12502mic(unsigned char *l, unsigned char *p, int len); -static void mic2win1250(unsigned char *mic, unsigned char *p, int len); +static void latin22mic(const unsigned char *l, unsigned char *p, int len); +static void mic2latin2(const unsigned char *mic, unsigned char *p, int len); +static void win12502mic(const unsigned char *l, unsigned char *p, int len); +static void mic2win1250(const unsigned char *mic, unsigned char *p, int len); Datum latin2_to_mic(PG_FUNCTION_ARGS) @@ -152,14 +152,15 @@ win1250_to_latin2(PG_FUNCTION_ARGS) } static void -latin22mic(unsigned char *l, unsigned char *p, int len) +latin22mic(const unsigned char *l, unsigned char *p, int len) { - latin2mic(l, p, len, LC_ISO8859_2); + latin2mic(l, p, len, LC_ISO8859_2, PG_LATIN2); } + static void -mic2latin2(unsigned char *mic, unsigned char *p, int len) +mic2latin2(const unsigned char *mic, unsigned char *p, int len) { - mic2latin(mic, p, len, LC_ISO8859_2); + mic2latin(mic, p, len, LC_ISO8859_2, PG_LATIN2); } /*----------------------------------------------------------------- @@ -167,9 +168,9 @@ mic2latin2(unsigned char *mic, unsigned char *p, int len) * Microsoft's CP1250(windows-1250) *-----------------------------------------------------------------*/ static void -win12502mic(unsigned char *l, unsigned char *p, int len) +win12502mic(const unsigned char *l, unsigned char *p, int len) { - static unsigned char win1250_2_iso88592[] = { + static const unsigned char win1250_2_iso88592[] = { 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0xA9, 0x8B, 0xA6, 0xAB, 0xAE, 0xAC, 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, @@ -188,12 +189,14 @@ win12502mic(unsigned char *l, unsigned char *p, int len) 0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF }; - latin2mic_with_table(l, p, len, LC_ISO8859_2, win1250_2_iso88592); + latin2mic_with_table(l, p, len, LC_ISO8859_2, PG_WIN1250, + win1250_2_iso88592); } + static void -mic2win1250(unsigned char *mic, unsigned char *p, int len) +mic2win1250(const unsigned char *mic, unsigned char *p, int len) { - static unsigned char iso88592_2_win1250[] = { + static const unsigned char iso88592_2_win1250[] = { 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x00, 0x8B, 0x00, 0x00, 0x00, 0x00, 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, @@ -212,5 +215,6 @@ mic2win1250(unsigned char *mic, unsigned char *p, int len) 0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF }; - mic2latin_with_table(mic, p, len, LC_ISO8859_2, iso88592_2_win1250); + mic2latin_with_table(mic, p, len, LC_ISO8859_2, PG_WIN1250, + iso88592_2_win1250); } diff --git a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c index f0435da45d..097975f952 100644 --- a/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c +++ b/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c,v 1.9 2004/12/31 22:02:10 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/latin_and_mic/latin_and_mic.c,v 1.9.4.1 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -40,12 +40,12 @@ extern Datum mic_to_latin4(PG_FUNCTION_ARGS); * ---------- */ -static void latin12mic(unsigned char *l, unsigned char *p, int len); -static void mic2latin1(unsigned char *mic, unsigned char *p, int len); -static void latin32mic(unsigned char *l, unsigned char *p, int len); -static void mic2latin3(unsigned char *mic, unsigned char *p, int len); -static void latin42mic(unsigned char *l, unsigned char *p, int len); -static void mic2latin4(unsigned char *mic, unsigned char *p, int len); +static void latin12mic(const unsigned char *l, unsigned char *p, int len); +static void mic2latin1(const unsigned char *mic, unsigned char *p, int len); +static void latin32mic(const unsigned char *l, unsigned char *p, int len); +static void mic2latin3(const unsigned char *mic, unsigned char *p, int len); +static void latin42mic(const unsigned char *l, unsigned char *p, int len); +static void mic2latin4(const unsigned char *mic, unsigned char *p, int len); Datum latin1_to_mic(PG_FUNCTION_ARGS) @@ -144,32 +144,37 @@ mic_to_latin4(PG_FUNCTION_ARGS) } static void -latin12mic(unsigned char *l, unsigned char *p, int len) +latin12mic(const unsigned char *l, unsigned char *p, int len) { - latin2mic(l, p, len, LC_ISO8859_1); + latin2mic(l, p, len, LC_ISO8859_1, PG_LATIN1); } + static void -mic2latin1(unsigned char *mic, unsigned char *p, int len) +mic2latin1(const unsigned char *mic, unsigned char *p, int len) { - mic2latin(mic, p, len, LC_ISO8859_1); + mic2latin(mic, p, len, LC_ISO8859_1, PG_LATIN1); } + static void -latin32mic(unsigned char *l, unsigned char *p, int len) +latin32mic(const unsigned char *l, unsigned char *p, int len) { - latin2mic(l, p, len, LC_ISO8859_3); + latin2mic(l, p, len, LC_ISO8859_3, PG_LATIN3); } + static void -mic2latin3(unsigned char *mic, unsigned char *p, int len) +mic2latin3(const unsigned char *mic, unsigned char *p, int len) { - mic2latin(mic, p, len, LC_ISO8859_3); + mic2latin(mic, p, len, LC_ISO8859_3, PG_LATIN3); } + static void -latin42mic(unsigned char *l, unsigned char *p, int len) +latin42mic(const unsigned char *l, unsigned char *p, int len) { - latin2mic(l, p, len, LC_ISO8859_4); + latin2mic(l, p, len, LC_ISO8859_4, PG_LATIN4); } + static void -mic2latin4(unsigned char *mic, unsigned char *p, int len) +mic2latin4(const unsigned char *mic, unsigned char *p, int len) { - mic2latin(mic, p, len, LC_ISO8859_4); + mic2latin(mic, p, len, LC_ISO8859_4, PG_LATIN4); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c b/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c index 93ce77377b..78d0b3ca83 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c,v 1.9 2004/12/31 22:02:11 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c,v 1.9.4.1 2006/05/21 20:06:16 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -43,6 +43,7 @@ ascii_to_utf8(PG_FUNCTION_ARGS) Assert(PG_GETARG_INT32(1) == PG_UTF8); Assert(len >= 0); + /* this looks wrong, but basically we're just rejecting high-bit-set */ pg_ascii2mic(src, dest, len); PG_RETURN_VOID(); @@ -59,6 +60,7 @@ utf8_to_ascii(PG_FUNCTION_ARGS) Assert(PG_GETARG_INT32(1) == PG_SQL_ASCII); Assert(len >= 0); + /* this looks wrong, but basically we're just rejecting high-bit-set */ pg_mic2ascii(src, dest, len); PG_RETURN_VOID(); diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c index 31b5b5f3e2..ea923b66fa 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c,v 1.9 2004/12/31 22:02:13 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_big5(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapBIG5, - sizeof(ULmapBIG5) / sizeof(pg_utf_to_local), len); + sizeof(ULmapBIG5) / sizeof(pg_utf_to_local), PG_BIG5, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c index 81dc25f361..ec91c41f8a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c,v 1.9 2004/12/31 22:02:14 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -58,7 +58,7 @@ utf8_to_koi8r(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmap_KOI8R, - sizeof(ULmap_KOI8R) / sizeof(pg_utf_to_local), len); + sizeof(ULmap_KOI8R) / sizeof(pg_utf_to_local), PG_KOI8R, len); PG_RETURN_VOID(); } @@ -92,7 +92,7 @@ utf8_to_win1251(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmap_WIN1251, - sizeof(ULmap_WIN1251) / sizeof(pg_utf_to_local), len); + sizeof(ULmap_WIN1251) / sizeof(pg_utf_to_local), PG_WIN1251, len); PG_RETURN_VOID(); } @@ -126,7 +126,7 @@ utf8_to_alt(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmap_ALT, - sizeof(ULmap_ALT) / sizeof(pg_utf_to_local), len); + sizeof(ULmap_ALT) / sizeof(pg_utf_to_local), PG_ALT, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c index 59dfe9d0a7..25f4ce6252 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c,v 1.9 2004/12/31 22:02:16 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapEUC_CN, - sizeof(ULmapEUC_CN) / sizeof(pg_utf_to_local), len); + sizeof(ULmapEUC_CN) / sizeof(pg_utf_to_local), PG_EUC_CN, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c index d438148d31..38c8827789 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c,v 1.9 2004/12/31 22:02:17 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapEUC_JP, - sizeof(ULmapEUC_JP) / sizeof(pg_utf_to_local), len); + sizeof(ULmapEUC_JP) / sizeof(pg_utf_to_local), PG_EUC_JP, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c index 0f8668546f..4ce2feeeb0 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c,v 1.9 2004/12/31 22:02:19 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapEUC_KR, - sizeof(ULmapEUC_KR) / sizeof(pg_utf_to_local), len); + sizeof(ULmapEUC_KR) / sizeof(pg_utf_to_local), PG_EUC_KR, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c index 8ceb89140c..c008632229 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c,v 1.9 2004/12/31 22:02:20 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapEUC_TW, - sizeof(ULmapEUC_TW) / sizeof(pg_utf_to_local), len); + sizeof(ULmapEUC_TW) / sizeof(pg_utf_to_local), PG_EUC_TW, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c index ae06726158..7d532591fd 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c,v 1.9 2004/12/31 22:02:23 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_gb18030(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapGB18030, - sizeof(ULmapGB18030) / sizeof(pg_utf_to_local), len); + sizeof(ULmapGB18030) / sizeof(pg_utf_to_local), PG_GB18030, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c index 04524c8497..463fedba2a 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c,v 1.9 2004/12/31 22:02:26 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_gbk(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapGBK, - sizeof(ULmapGBK) / sizeof(pg_utf_to_local), len); + sizeof(ULmapGBK) / sizeof(pg_utf_to_local), PG_GBK, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c index 1bb101d4da..edd8cfbd6d 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c,v 1.11 2004/12/31 22:02:27 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c,v 1.11.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -151,7 +151,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS) Assert(PG_GETARG_INT32(0) == PG_UTF8); Assert(len >= 0); - UtfToLocal(src, dest, maps[encoding].map2, maps[encoding].size2, len); + UtfToLocal(src, dest, maps[encoding].map2, maps[encoding].size2, encoding, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c index 8b5812eead..8accfb4bf6 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c,v 1.10 2004/12/31 22:02:29 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c,v 1.10.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -44,15 +44,20 @@ iso8859_1_to_utf8(PG_FUNCTION_ARGS) Assert(PG_GETARG_INT32(1) == PG_UTF8); Assert(len >= 0); - while (len-- > 0 && (c = *src++)) + while (len > 0) { - if (c < 0x80) + c = *src; + if (c == 0) + report_invalid_encoding(PG_LATIN1, (const char *) src, len); + if (!IS_HIGHBIT_SET(c)) *dest++ = c; else { *dest++ = (c >> 6) | 0xc0; *dest++ = (c & 0x003f) | 0x80; } + src++; + len--; } *dest = '\0'; @@ -66,30 +71,44 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS) unsigned char *dest = PG_GETARG_CSTRING(3); int len = PG_GETARG_INT32(4); unsigned short c, - c1, - c2; + c1; Assert(PG_GETARG_INT32(0) == PG_UTF8); Assert(PG_GETARG_INT32(1) == PG_LATIN1); Assert(len >= 0); - while (len >= 0 && (c = *src++)) + while (len > 0) { - if ((c & 0xe0) == 0xc0) + c = *src; + if (c == 0) + report_invalid_encoding(PG_UTF8, (const char *) src, len); + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(c)) { - c1 = c & 0x1f; - c2 = *src++ & 0x3f; - *dest = c1 << 6; - *dest++ |= c2; - len -= 2; + *dest++ = c; + src++; + len--; } - else if ((c & 0xe0) == 0xe0) - elog(ERROR, "could not convert UTF-8 character 0x%04x to ISO8859-1", - c); else { - *dest++ = c; - len--; + int l = pg_utf_mblen(src); + + if (l > len || !pg_utf8_islegal(src, l)) + report_invalid_encoding(PG_UTF8, (const char *) src, len); + if (l != 2) + report_untranslatable_char(PG_UTF8, PG_LATIN1, + (const char *) src, len); + c1 = src[1] & 0x3f; + c = ((c & 0x1f) << 6) | c1; + if (c >= 0x80 && c <= 0xff) + { + *dest++ = (unsigned char) c; + src += 2; + len -= 2; + } + else + report_untranslatable_char(PG_UTF8, PG_LATIN1, + (const char *) src, len); } } *dest = '\0'; diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c index 3083d397ce..97bd44c3fb 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c,v 1.9 2004/12/31 22:02:31 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_johab(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapJOHAB, - sizeof(ULmapJOHAB) / sizeof(pg_utf_to_local), len); + sizeof(ULmapJOHAB) / sizeof(pg_utf_to_local), PG_JOHAB, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c index 3d3f805f1f..852ca98a56 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c,v 1.9 2004/12/31 22:02:33 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_sjis(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapSJIS, - sizeof(ULmapSJIS) / sizeof(pg_utf_to_local), len); + sizeof(ULmapSJIS) / sizeof(pg_utf_to_local), PG_SJIS, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/utf8_and_tcvn.c b/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/utf8_and_tcvn.c index 4894d3fee8..a3d7b3b398 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/utf8_and_tcvn.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/utf8_and_tcvn.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/utf8_and_tcvn.c,v 1.9 2004/12/31 22:02:35 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/utf8_and_tcvn.c,v 1.9.4.1 2006/05/21 20:06:18 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_tcvn(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapTCVN, - sizeof(ULmapTCVN) / sizeof(pg_utf_to_local), len); + sizeof(ULmapTCVN) / sizeof(pg_utf_to_local), PG_TCVN, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c index c995ebc59a..33f6e59b05 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c,v 1.9 2004/12/31 22:02:36 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -62,7 +62,7 @@ utf8_to_uhc(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapUHC, - sizeof(ULmapUHC) / sizeof(pg_utf_to_local), len); + sizeof(ULmapUHC) / sizeof(pg_utf_to_local), PG_UHC, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c b/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c index 3b260a0e64..403edc27a8 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c,v 1.9 2004/12/31 22:02:38 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -46,7 +46,7 @@ utf_to_win1250(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapWIN1250, - sizeof(ULmapWIN1250) / sizeof(pg_utf_to_local), len); + sizeof(ULmapWIN1250) / sizeof(pg_utf_to_local), PG_WIN1250, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c b/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c index 1001e19e75..fcdd418fac 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c,v 1.9 2004/12/31 22:02:39 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -46,7 +46,7 @@ utf_to_win1256(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapWIN1256, - sizeof(ULmapWIN1256) / sizeof(pg_utf_to_local), len); + sizeof(ULmapWIN1256) / sizeof(pg_utf_to_local), PG_WIN1256, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c b/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c index c37c5c495b..21432c0b5f 100644 --- a/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c +++ b/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c @@ -6,7 +6,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c,v 1.9 2004/12/31 22:02:41 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c,v 1.9.4.1 2006/05/21 20:06:17 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -46,7 +46,7 @@ utf_to_win874(PG_FUNCTION_ARGS) Assert(len >= 0); UtfToLocal(src, dest, ULmapWIN874, - sizeof(ULmapWIN874) / sizeof(pg_utf_to_local), len); + sizeof(ULmapWIN874) / sizeof(pg_utf_to_local), PG_WIN874, len); PG_RETURN_VOID(); } diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index 9718e7e73e..da5f8e66c5 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -4,7 +4,7 @@ * (currently mule internal code (mic) is used) * Tatsuo Ishii * - * $PostgreSQL: pgsql/src/backend/utils/mb/mbutils.c,v 1.48 2004/10/13 01:25:12 neilc Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/mbutils.c,v 1.48.4.1 2006/05/21 20:06:16 tgl Exp $ */ #include "postgres.h" @@ -370,8 +370,49 @@ pg_client_to_server(unsigned char *s, int len) Assert(DatabaseEncoding); Assert(ClientEncoding); - if (ClientEncoding->encoding == DatabaseEncoding->encoding) + if (len <= 0) + return s; + + if (ClientEncoding->encoding == DatabaseEncoding->encoding || + ClientEncoding->encoding == PG_SQL_ASCII) + { + /* + * No conversion is needed, but we must still validate the data. + */ + (void) pg_verify_mbstr(DatabaseEncoding->encoding, s, len, false); return s; + } + + if (DatabaseEncoding->encoding == PG_SQL_ASCII) + { + /* + * No conversion is possible, but we must still validate the data, + * because the client-side code might have done string escaping + * using the selected client_encoding. If the client encoding is + * ASCII-safe then we just do a straight validation under that + * encoding. For an ASCII-unsafe encoding we have a problem: + * we dare not pass such data to the parser but we have no way + * to convert it. We compromise by rejecting the data if it + * contains any non-ASCII characters. + */ + if (PG_VALID_BE_ENCODING(ClientEncoding->encoding)) + (void) pg_verify_mbstr(ClientEncoding->encoding, s, len, false); + else + { + int i; + + for (i = 0; i < len; i++) + { + if (s[i] == '\0' || IS_HIGHBIT_SET(s[i])) + ereport(ERROR, + (errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE), + errmsg("invalid byte value for encoding \"%s\": 0x%02x", + pg_enc2name_tbl[PG_SQL_ASCII].name, + (unsigned char) s[i]))); + } + } + return s; + } return perform_default_encoding_conversion(s, len, true); } @@ -385,9 +426,14 @@ pg_server_to_client(unsigned char *s, int len) Assert(DatabaseEncoding); Assert(ClientEncoding); - if (ClientEncoding->encoding == DatabaseEncoding->encoding) + if (len <= 0) return s; + if (ClientEncoding->encoding == DatabaseEncoding->encoding || + ClientEncoding->encoding == PG_SQL_ASCII || + DatabaseEncoding->encoding == PG_SQL_ASCII) + return s; /* assume data is valid */ + return perform_default_encoding_conversion(s, len, false); } @@ -406,9 +452,6 @@ perform_default_encoding_conversion(unsigned char *src, int len, bool is_client_ dest_encoding; FmgrInfo *flinfo; - if (len <= 0) - return src; - if (is_client_to_server) { src_encoding = ClientEncoding->encoding; @@ -425,12 +468,6 @@ perform_default_encoding_conversion(unsigned char *src, int len, bool is_client_ if (flinfo == NULL) return src; - if (src_encoding == dest_encoding) - return src; - - if (src_encoding == PG_SQL_ASCII || dest_encoding == PG_SQL_ASCII) - return src; - result = palloc(len * 4 + 1); FunctionCall5(flinfo, diff --git a/src/backend/utils/mb/wchar.c b/src/backend/utils/mb/wchar.c index 3adf4481e8..96a2688695 100644 --- a/src/backend/utils/mb/wchar.c +++ b/src/backend/utils/mb/wchar.c @@ -1,7 +1,7 @@ /* * conversion functions between pg_wchar and multibyte streams. * Tatsuo Ishii - * $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.40.4.1 2005/12/24 10:11:32 ishii Exp $ + * $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.40.4.2 2006/05/21 20:06:16 tgl Exp $ * * WIN1250 client encoding updated by Pavel Behal * @@ -96,7 +96,7 @@ static int pg_euc2wchar_with_len return (cnt); } -static int +static inline int pg_euc_mblen(const unsigned char *s) { int len; @@ -112,7 +112,7 @@ pg_euc_mblen(const unsigned char *s) return (len); } -static int +static inline int pg_euc_dsplen(const unsigned char *s) { int len; @@ -714,53 +714,433 @@ pg_gb18030_dsplen(const unsigned char *s) return (len); } +/* + *------------------------------------------------------------------- + * multibyte sequence validators + * + * These functions accept "s", a pointer to the first byte of a string, + * and "len", the remaining length of the string. If there is a validly + * encoded character beginning at *s, return its length in bytes; else + * return -1. + * + * The functions can assume that len > 0 and that *s != '\0', but they must + * test for and reject zeroes in any additional bytes of a multibyte character. + * + * Note that this definition allows the function for a single-byte + * encoding to be just "return 1". + *------------------------------------------------------------------- + */ + +static int +pg_ascii_verifier(const unsigned char *s, int len) +{ + return 1; +} + +#define IS_EUC_RANGE_VALID(c) ((c) >= 0xa1 && (c) <= 0xfe) + +static int +pg_eucjp_verifier(const unsigned char *s, int len) +{ + int l; + unsigned char c1, c2; + + c1 = *s++; + + switch (c1) + { + case SS2: /* JIS X 0201 */ + l = 2; + if (l > len) + return -1; + c2 = *s++; + if (c2 < 0xa1 || c2 > 0xdf) + return -1; + break; + + case SS3: /* JIS X 0212 */ + l = 3; + if (l > len) + return -1; + c2 = *s++; + if (!IS_EUC_RANGE_VALID(c2)) + return -1; + c2 = *s++; + if (!IS_EUC_RANGE_VALID(c2)) + return -1; + break; + + default: + if (IS_HIGHBIT_SET(c1)) /* JIS X 0208? */ + { + l = 2; + if (l > len) + return -1; + if (!IS_EUC_RANGE_VALID(c1)) + return -1; + c2 = *s++; + if (!IS_EUC_RANGE_VALID(c2)) + return -1; + } + else /* must be ASCII */ + { + l = 1; + } + break; + } + + return l; +} + +static int +pg_euckr_verifier(const unsigned char *s, int len) +{ + int l; + unsigned char c1, c2; + + c1 = *s++; + + if (IS_HIGHBIT_SET(c1)) + { + l = 2; + if (l > len) + return -1; + if (!IS_EUC_RANGE_VALID(c1)) + return -1; + c2 = *s++; + if (!IS_EUC_RANGE_VALID(c2)) + return -1; + } + else /* must be ASCII */ + { + l = 1; + } + + return l; +} + +/* EUC-CN byte sequences are exactly same as EUC-KR */ +#define pg_euccn_verifier pg_euckr_verifier + +static int +pg_euctw_verifier(const unsigned char *s, int len) +{ + int l; + unsigned char c1, c2; + + c1 = *s++; + + switch (c1) + { + case SS2: /* CNS 11643 Plane 1-7 */ + l = 4; + if (l > len) + return -1; + c2 = *s++; + if (c2 < 0xa1 || c2 > 0xa7) + return -1; + c2 = *s++; + if (!IS_EUC_RANGE_VALID(c2)) + return -1; + c2 = *s++; + if (!IS_EUC_RANGE_VALID(c2)) + return -1; + break; + + case SS3: /* unused */ + return -1; + + default: + if (IS_HIGHBIT_SET(c1)) /* CNS 11643 Plane 1 */ + { + l = 2; + if (l > len) + return -1; + /* no further range check on c1? */ + c2 = *s++; + if (!IS_EUC_RANGE_VALID(c2)) + return -1; + } + else /* must be ASCII */ + { + l = 1; + } + break; + } + return l; +} + +static int +pg_johab_verifier(const unsigned char *s, int len) +{ + int l, mbl; + unsigned char c; + + l = mbl = pg_johab_mblen(s); + + if (len < l) + return -1; + + if (!IS_HIGHBIT_SET(*s)) + return mbl; + + while (--l > 0) + { + c = *++s; + if (!IS_EUC_RANGE_VALID(c)) + return -1; + } + return mbl; +} + +static int +pg_mule_verifier(const unsigned char *s, int len) +{ + int l, mbl; + unsigned char c; + + l = mbl = pg_mule_mblen(s); + + if (len < l) + return -1; + + while (--l > 0) + { + c = *++s; + if (!IS_HIGHBIT_SET(c)) + return -1; + } + return mbl; +} + +static int +pg_latin1_verifier(const unsigned char *s, int len) +{ + return 1; +} + +static int +pg_sjis_verifier(const unsigned char *s, int len) +{ + int l, mbl; + unsigned char c1, c2; + + l = mbl = pg_sjis_mblen(s); + + if (len < l) + return -1; + + if (l == 1) /* pg_sjis_mblen already verified it */ + return mbl; + + c1 = *s++; + c2 = *s; + if (!ISSJISHEAD(c1) || !ISSJISTAIL(c2)) + return -1; + return mbl; +} + +static int +pg_big5_verifier(const unsigned char *s, int len) +{ + int l, mbl; + + l = mbl = pg_big5_mblen(s); + + if (len < l) + return -1; + + while (--l > 0) + { + if (*++s == '\0') + return -1; + } + + return mbl; +} + +static int +pg_gbk_verifier(const unsigned char *s, int len) +{ + int l, mbl; + + l = mbl = pg_gbk_mblen(s); + + if (len < l) + return -1; + + while (--l > 0) + { + if (*++s == '\0') + return -1; + } + + return mbl; +} + +static int +pg_uhc_verifier(const unsigned char *s, int len) +{ + int l, mbl; + + l = mbl = pg_uhc_mblen(s); + + if (len < l) + return -1; + + while (--l > 0) + { + if (*++s == '\0') + return -1; + } + + return mbl; +} + +static int +pg_gb18030_verifier(const unsigned char *s, int len) +{ + int l, mbl; + + l = mbl = pg_gb18030_mblen(s); + + if (len < l) + return -1; + + while (--l > 0) + { + if (*++s == '\0') + return -1; + } + + return mbl; +} + +static int +pg_utf8_verifier(const unsigned char *s, int len) +{ + int l = pg_utf_mblen(s); + + if (len < l) + return -1; + + if (!pg_utf8_islegal(s, l)) + return -1; + return l; +} + +/* + * Check for validity of a single UTF-8 encoded character + * + * This directly implements the rules in RFC3629, modified to restrict + * us to 16-bit Unicode code points (hence, at most 3 bytes in UTF8). + * The bizarre-looking + * restrictions on the second byte are meant to ensure that there isn't + * more than one encoding of a given Unicode character point; that is, + * you may not use a longer-than-necessary byte sequence with high order + * zero bits to represent a character that would fit in fewer bytes. + * To do otherwise is to create security hazards (eg, create an apparent + * non-ASCII character that decodes to plain ASCII). + * + * length is assumed to have been obtained by pg_utf_mblen(), and the + * caller must have checked that that many bytes are present in the buffer. + */ +bool +pg_utf8_islegal(const unsigned char *source, int length) +{ + unsigned char a; + + switch (length) + { + default: + /* reject lengths 4, 5 and 6 for now */ + return false; + case 3: + a = source[2]; + if (a < 0x80 || a > 0xBF) + return false; + /* FALL THRU */ + case 2: + a = source[1]; + switch (*source) + { + case 0xE0: + if (a < 0xA0 || a > 0xBF) + return false; + break; + case 0xED: + if (a < 0x80 || a > 0x9F) + return false; + break; + default: + if (a < 0x80 || a > 0xBF) + return false; + break; + } + /* FALL THRU */ + case 1: + a = *source; + if (a >= 0x80 && a < 0xC2) + return false; + if (a > 0xEF) + return false; + break; + } + return true; +} + +/* + *------------------------------------------------------------------- + * encoding info table + *------------------------------------------------------------------- + */ pg_wchar_tbl pg_wchar_table[] = { - {pg_ascii2wchar_with_len, pg_ascii_mblen, pg_ascii_dsplen, 1}, /* 0; PG_SQL_ASCII */ - {pg_eucjp2wchar_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, 3}, /* 1; PG_EUC_JP */ - {pg_euccn2wchar_with_len, pg_euccn_mblen, pg_euccn_dsplen, 3}, /* 2; PG_EUC_CN */ - {pg_euckr2wchar_with_len, pg_euckr_mblen, pg_euckr_dsplen, 3}, /* 3; PG_EUC_KR */ - {pg_euctw2wchar_with_len, pg_euctw_mblen, pg_euctw_dsplen, 3}, /* 4; PG_EUC_TW */ - {pg_johab2wchar_with_len, pg_johab_mblen, pg_johab_dsplen, 3}, /* 5; PG_JOHAB */ - {pg_utf2wchar_with_len, pg_utf_mblen, pg_utf_dsplen, 3}, /* 6; PG_UNICODE */ - {pg_mule2wchar_with_len, pg_mule_mblen, pg_mule_dsplen, 3}, /* 7; PG_MULE_INTERNAL */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 8; PG_LATIN1 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 9; PG_LATIN2 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 10; PG_LATIN3 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 11; PG_LATIN4 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 12; PG_LATIN5 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 13; PG_LATIN6 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 14; PG_LATIN7 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 15; PG_LATIN8 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 16; PG_LATIN9 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 17; PG_LATIN10 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 18; PG_WIN1256 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 19; PG_TCVN */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 20; PG_WIN874 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 21; PG_KOI8 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 22; PG_WIN1251 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 23; PG_ALT */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 24; ISO-8859-5 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 25; ISO-8859-6 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 26; ISO-8859-7 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 27; ISO-8859-8 */ - {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 28; PG_WIN1250 */ - {0, pg_sjis_mblen, pg_sjis_dsplen, 2}, /* 29; PG_SJIS */ - {0, pg_big5_mblen, pg_big5_dsplen, 2}, /* 30; PG_BIG5 */ - {0, pg_gbk_mblen, pg_gbk_dsplen, 2}, /* 31; PG_GBK */ - {0, pg_uhc_mblen, pg_uhc_dsplen, 2}, /* 32; PG_UHC */ - {0, pg_gb18030_mblen, pg_gb18030_dsplen, 2} /* 33; PG_GB18030 */ + {pg_ascii2wchar_with_len, pg_ascii_mblen, pg_ascii_dsplen, pg_ascii_verifier, 1}, /* 0; PG_SQL_ASCII */ + {pg_eucjp2wchar_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifier, 3}, /* 1; PG_EUC_JP */ + {pg_euccn2wchar_with_len, pg_euccn_mblen, pg_euccn_dsplen, pg_euccn_verifier, 3}, /* 2; PG_EUC_CN */ + {pg_euckr2wchar_with_len, pg_euckr_mblen, pg_euckr_dsplen, pg_euckr_verifier, 3}, /* 3; PG_EUC_KR */ + {pg_euctw2wchar_with_len, pg_euctw_mblen, pg_euctw_dsplen, pg_euctw_verifier, 3}, /* 4; PG_EUC_TW */ + {pg_johab2wchar_with_len, pg_johab_mblen, pg_johab_dsplen, pg_johab_verifier, 3}, /* 5; PG_JOHAB */ + {pg_utf2wchar_with_len, pg_utf_mblen, pg_utf_dsplen, pg_utf8_verifier, 3}, /* 6; PG_UNICODE */ + {pg_mule2wchar_with_len, pg_mule_mblen, pg_mule_dsplen, pg_mule_verifier, 3}, /* 7; PG_MULE_INTERNAL */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 8; PG_LATIN1 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 9; PG_LATIN2 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 10; PG_LATIN3 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 11; PG_LATIN4 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 12; PG_LATIN5 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 13; PG_LATIN6 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 14; PG_LATIN7 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 15; PG_LATIN8 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 16; PG_LATIN9 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 17; PG_LATIN10 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 18; PG_WIN1256 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 19; PG_TCVN */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 20; PG_WIN874 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 21; PG_KOI8 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 22; PG_WIN1251 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 23; PG_ALT */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 24; ISO-8859-5 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 25; ISO-8859-6 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 26; ISO-8859-7 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 27; ISO-8859-8 */ + {pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* 28; PG_WIN1250 */ + {0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifier, 2}, /* 29; PG_SJIS */ + {0, pg_big5_mblen, pg_big5_dsplen, pg_big5_verifier, 2}, /* 30; PG_BIG5 */ + {0, pg_gbk_mblen, pg_gbk_dsplen, pg_gbk_verifier, 2}, /* 31; PG_GBK */ + {0, pg_uhc_mblen, pg_uhc_dsplen, pg_uhc_verifier, 2}, /* 32; PG_UHC */ + {0, pg_gb18030_mblen, pg_gb18030_dsplen, pg_gb18030_verifier, 2} /* 33; PG_GB18030 */ }; /* returns the byte length of a word for mule internal code */ int pg_mic_mblen(const unsigned char *mbstr) { - return (pg_mule_mblen(mbstr)); + return pg_mule_mblen(mbstr); } /* - * Returns the byte length of a multibyte word. + * Returns the byte length of a multibyte character. */ int pg_encoding_mblen(int encoding, const unsigned char *mbstr) @@ -769,12 +1149,12 @@ pg_encoding_mblen(int encoding, const unsigned char *mbstr) return ((encoding >= 0 && encoding < sizeof(pg_wchar_table) / sizeof(pg_wchar_tbl)) ? - ((*pg_wchar_table[encoding].mblen) (mbstr)) : - ((*pg_wchar_table[PG_SQL_ASCII].mblen) (mbstr))); + ((*pg_wchar_table[encoding].mblen) ((const unsigned char *) mbstr)) : + ((*pg_wchar_table[PG_SQL_ASCII].mblen) ((const unsigned char *) mbstr))); } /* - * Returns the display length of a multibyte word. + * Returns the display length of a multibyte character. */ int pg_encoding_dsplen(int encoding, const unsigned char *mbstr) @@ -783,12 +1163,28 @@ pg_encoding_dsplen(int encoding, const unsigned char *mbstr) return ((encoding >= 0 && encoding < sizeof(pg_wchar_table) / sizeof(pg_wchar_tbl)) ? - ((*pg_wchar_table[encoding].dsplen) (mbstr)) : - ((*pg_wchar_table[PG_SQL_ASCII].dsplen) (mbstr))); + ((*pg_wchar_table[encoding].dsplen) ((const unsigned char *) mbstr)) : + ((*pg_wchar_table[PG_SQL_ASCII].dsplen) ((const unsigned char *) mbstr))); +} + +/* + * Verify the first multibyte character of the given string. + * Return its byte length if good, -1 if bad. (See comments above for + * full details of the mbverify API.) + */ +int +pg_encoding_verifymb(int encoding, const char *mbstr, int len) +{ + Assert(PG_VALID_ENCODING(encoding)); + + return ((encoding >= 0 && + encoding < sizeof(pg_wchar_table) / sizeof(pg_wchar_tbl)) ? + ((*pg_wchar_table[encoding].mbverify) ((const unsigned char *) mbstr, len)) : + ((*pg_wchar_table[PG_SQL_ASCII].mbverify) ((const unsigned char *) mbstr, len))); } /* - * fetch maximum length of a char encoding + * fetch maximum length of a given encoding */ int pg_encoding_max_length(int encoding) @@ -801,83 +1197,147 @@ pg_encoding_max_length(int encoding) #ifndef FRONTEND /* - * Verify mbstr to make sure that it has a valid character sequence. - * mbstr is not necessarily NULL terminated; length of mbstr is + * fetch maximum length of the encoding for the current database + */ +int +pg_database_encoding_max_length(void) +{ + return pg_wchar_table[GetDatabaseEncoding()].maxmblen; +} + +/* + * Verify mbstr to make sure that it is validly encoded in the current + * database encoding. Otherwise same as pg_verify_mbstr(). + */ +bool +pg_verifymbstr(const char *mbstr, int len, bool noError) +{ + return pg_verify_mbstr(GetDatabaseEncoding(), mbstr, len, noError); +} + +/* + * Verify mbstr to make sure that it is validly encoded in the specified + * encoding. + * + * mbstr is not necessarily zero terminated; length of mbstr is * specified by len. * * If OK, return TRUE. If a problem is found, return FALSE when noError is * true; when noError is false, ereport() a descriptive message. */ bool -pg_verifymbstr(const unsigned char *mbstr, int len, bool noError) +pg_verify_mbstr(int encoding, const char *mbstr, int len, bool noError) { - int l; - int i; - int encoding; + mbverifier mbverify; + + Assert(PG_VALID_ENCODING(encoding)); - /* we do not need any check in single-byte encodings */ - if (pg_database_encoding_max_length() <= 1) - return true; + /* + * In single-byte encodings, we need only reject nulls (\0). + */ + if (pg_encoding_max_length(encoding) <= 1) + { + const char *nullpos = memchr(mbstr, 0, len); - encoding = GetDatabaseEncoding(); + if (nullpos == NULL) + return true; + if (noError) + return false; + report_invalid_encoding(encoding, nullpos, 1); + } - while (len > 0 && *mbstr) + /* fetch function pointer just once */ + mbverify = pg_wchar_table[encoding].mbverify; + + while (len > 0) { - /* special UTF-8 check */ - if (encoding == PG_UTF8 && (*mbstr & 0xf8) == 0xf0) + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*mbstr)) { + if (*mbstr != '\0') + { + mbstr++; + len--; + continue; + } if (noError) return false; - ereport(ERROR, - (errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE), - errmsg("Unicode characters greater than or equal to 0x10000 are not supported"))); + report_invalid_encoding(encoding, mbstr, len); } - l = pg_mblen(mbstr); + l = (*mbverify) ((const unsigned char *) mbstr, len); - for (i = 1; i < l; i++) + if (l < 0) { - /* - * we expect that every multibyte char consists of bytes - * having the 8th bit set - */ - if (i >= len || (mbstr[i] & 0x80) == 0) - { - char buf[8 * 2 + 1]; - char *p = buf; - int j, - jlimit; - - if (noError) - return false; - - jlimit = Min(l, len); - jlimit = Min(jlimit, 8); /* prevent buffer overrun */ - - for (j = 0; j < jlimit; j++) - p += sprintf(p, "%02x", mbstr[j]); - - ereport(ERROR, - (errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE), - errmsg("invalid byte sequence for encoding \"%s\": 0x%s", - GetDatabaseEncodingName(), buf))); - } + if (noError) + return false; + report_invalid_encoding(encoding, mbstr, len); } - len -= l; mbstr += l; + len -= l; } - return true; } /* - * fetch maximum length of a char encoding for the current database + * report_invalid_encoding: complain about invalid multibyte character + * + * note: len is remaining length of string, not length of character; + * len must be greater than zero, as we always examine the first byte. */ -int -pg_database_encoding_max_length(void) +void +report_invalid_encoding(int encoding, const char *mbstr, int len) { - return pg_wchar_table[GetDatabaseEncoding()].maxmblen; + int l = pg_encoding_mblen(encoding, mbstr); + char buf[8 * 2 + 1]; + char *p = buf; + int j, + jlimit; + + jlimit = Min(l, len); + jlimit = Min(jlimit, 8); /* prevent buffer overrun */ + + for (j = 0; j < jlimit; j++) + p += sprintf(p, "%02x", (unsigned char) mbstr[j]); + + ereport(ERROR, + (errcode(ERRCODE_CHARACTER_NOT_IN_REPERTOIRE), + errmsg("invalid byte sequence for encoding \"%s\": 0x%s", + pg_enc2name_tbl[encoding].name, + buf))); +} + +/* + * report_untranslatable_char: complain about untranslatable character + * + * note: len is remaining length of string, not length of character; + * len must be greater than zero, as we always examine the first byte. + */ +void +report_untranslatable_char(int src_encoding, int dest_encoding, + const char *mbstr, int len) +{ + int l = pg_encoding_mblen(src_encoding, mbstr); + char buf[8 * 2 + 1]; + char *p = buf; + int j, + jlimit; + + jlimit = Min(l, len); + jlimit = Min(jlimit, 8); /* prevent buffer overrun */ + + for (j = 0; j < jlimit; j++) + p += sprintf(p, "%02x", (unsigned char) mbstr[j]); + + ereport(ERROR, + (errcode(ERRCODE_UNTRANSLATABLE_CHARACTER), + errmsg("character 0x%s of encoding \"%s\" has no equivalent in \"%s\"", + buf, + pg_enc2name_tbl[src_encoding].name, + pg_enc2name_tbl[dest_encoding].name))); } #endif diff --git a/src/include/c.h b/src/include/c.h index 08ce6dd243..9bdbcd8184 100644 --- a/src/include/c.h +++ b/src/include/c.h @@ -12,7 +12,7 @@ * Portions Copyright (c) 1996-2005, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * - * $PostgreSQL: pgsql/src/include/c.h,v 1.178.4.1 2005/07/18 15:53:46 tgl Exp $ + * $PostgreSQL: pgsql/src/include/c.h,v 1.178.4.2 2006/05/21 20:06:18 tgl Exp $ * *------------------------------------------------------------------------- */ @@ -670,6 +670,8 @@ typedef NameData *Name; /* msb for char */ #define CSIGNBIT (0x80) +#define HIGHBIT (0x80) +#define IS_HIGHBIT_SET(ch) ((unsigned char)(ch) & HIGHBIT) #define STATUS_OK (0) #define STATUS_ERROR (-1) diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 568679bf44..17e68edf6c 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -1,4 +1,4 @@ -/* $PostgreSQL: pgsql/src/include/mb/pg_wchar.h,v 1.56 2004/12/04 18:19:33 momjian Exp $ */ +/* $PostgreSQL: pgsql/src/include/mb/pg_wchar.h,v 1.56.4.1 2006/05/21 20:06:18 tgl Exp $ */ #ifndef PG_WCHAR_H #define PG_WCHAR_H @@ -24,10 +24,16 @@ typedef unsigned int pg_wchar; #define SS3 0x8f /* single shift 3 (JIS0212) */ /* + * SJIS validation macros + */ +#define ISSJISHEAD(c) (((c) >= 0x81 && (c) <= 0x9f) || ((c) >= 0xe0 && (c) <= 0xfc)) +#define ISSJISTAIL(c) (((c) >= 0x40 && (c) <= 0x7e) || ((c) >= 0x80 && (c) <= 0xfc)) + +/* * Leading byte types or leading prefix byte for MULE internal code. * See http://www.xemacs.org for more details. (there is a doc titled * "XEmacs Internals Manual", "MULE Character Sets and Encodings" - * section. + * section.) */ /* * Is a leading byte for "official" single byte encodings? @@ -64,7 +70,7 @@ typedef unsigned int pg_wchar; #define LC_ISO8859_8 0x88 /* Hebrew (not supported yet) */ #define LC_JISX0201K 0x89 /* Japanese 1 byte kana */ #define LC_JISX0201R 0x8a /* Japanese 1 byte Roman */ -/* Note that 0x8b seems to be unused in as of Emacs 20.7. +/* Note that 0x8b seems to be unused as of Emacs 20.7. * However, there might be a chance that 0x8b could be used * in later version of Emacs. */ @@ -137,13 +143,13 @@ typedef unsigned int pg_wchar; /* #define FREE 0xff free (unused) */ /* - * Encoding numeral identificators + * PostgreSQL encoding identifiers * * WARNING: the order of this table must be same as order * in the pg_enc2name[] (mb/encnames.c) array! * - * If you add some encoding don'y forget check - * PG_ENCODING_[BE|FE]_LAST macros. + * If you add some encoding don't forget to check + * PG_ENCODING_BE_LAST macro. * * The PG_SQL_ASCII is default encoding and must be = 0. */ @@ -199,14 +205,13 @@ typedef enum pg_enc #define PG_VALID_BE_ENCODING(_enc) \ ((_enc) >= 0 && (_enc) <= PG_ENCODING_BE_LAST) -#define PG_ENCODING_IS_CLIEN_ONLY(_enc) \ - (((_enc) > PG_ENCODING_BE_LAST && (_enc) <= PG_ENCODING_FE_LAST) +#define PG_ENCODING_IS_CLIENT_ONLY(_enc) \ + ((_enc) > PG_ENCODING_BE_LAST && (_enc) <= PG_ENCODING_FE_LAST) #define PG_VALID_ENCODING(_enc) \ ((_enc) >= 0 && (_enc) < _PG_LAST_ENCODING_) -/* On FE are possible all encodings - */ +/* On FE are possible all encodings */ #define PG_VALID_FE_ENCODING(_enc) PG_VALID_ENCODING(_enc) /* @@ -246,18 +251,21 @@ extern const char *pg_encoding_to_char(int encoding); typedef int (*mb2wchar_with_len_converter) (const unsigned char *from, pg_wchar *to, int len); + typedef int (*mblen_converter) (const unsigned char *mbstr); typedef int (*mbdisplaylen_converter) (const unsigned char *mbstr); +typedef int (*mbverifier) (const unsigned char *mbstr, int len); + typedef struct { mb2wchar_with_len_converter mb2wchar_with_len; /* convert a multibyte * string to a wchar */ - mblen_converter mblen; /* returns the length of a multibyte char */ - mbdisplaylen_converter dsplen; /* returns the lenghth of a - * display length */ - int maxmblen; /* max bytes for a char in this charset */ + mblen_converter mblen; /* get byte length of a char */ + mbdisplaylen_converter dsplen; /* get display width of a char */ + mbverifier mbverify; /* verify multibyte sequence */ + int maxmblen; /* max bytes for a char in this encoding */ } pg_wchar_tbl; extern pg_wchar_tbl pg_wchar_table[]; @@ -290,6 +298,7 @@ extern int pg_mblen(const unsigned char *mbstr); extern int pg_dsplen(const unsigned char *mbstr); extern int pg_encoding_mblen(int encoding, const unsigned char *mbstr); extern int pg_encoding_dsplen(int encoding, const unsigned char *mbstr); +extern int pg_encoding_verifymb(int encoding, const char *mbstr, int len); extern int pg_mule_mblen(const unsigned char *mbstr); extern int pg_mic_mblen(const unsigned char *mbstr); extern int pg_mbstrlen(const unsigned char *mbstr); @@ -323,20 +332,33 @@ extern unsigned char *pg_server_to_client(unsigned char *s, int len); extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc); extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc); -extern void LocalToUtf(unsigned char *iso, unsigned char *utf, - pg_local_to_utf *map, int size, int encoding, int len); - -extern void UtfToLocal(unsigned char *utf, unsigned char *iso, - pg_utf_to_local *map, int size, int len); - -extern bool pg_verifymbstr(const unsigned char *mbstr, int len, bool noError); - -extern void pg_ascii2mic(unsigned char *src, unsigned char *dest, int len); -extern void pg_mic2ascii(unsigned char *src, unsigned char *dest, int len); -extern void pg_print_bogus_char(unsigned char **mic, unsigned char **p); -extern void latin2mic(unsigned char *l, unsigned char *p, int len, int lc); -extern void mic2latin(unsigned char *mic, unsigned char *p, int len, int lc); -extern void latin2mic_with_table(unsigned char *l, unsigned char *p, int len, int lc, unsigned char *tab); -extern void mic2latin_with_table(unsigned char *mic, unsigned char *p, int len, int lc, unsigned char *tab); +extern void LocalToUtf(const unsigned char *iso, unsigned char *utf, + const pg_local_to_utf *map, int size, int encoding, int len); + +extern void UtfToLocal(const unsigned char *utf, unsigned char *iso, + const pg_utf_to_local *map, int size, int encoding, int len); + +extern bool pg_verifymbstr(const char *mbstr, int len, bool noError); +extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len, + bool noError); + +extern void report_invalid_encoding(int encoding, const char *mbstr, int len); +extern void report_untranslatable_char(int src_encoding, int dest_encoding, + const char *mbstr, int len); + +extern void pg_ascii2mic(const unsigned char *l, unsigned char *p, int len); +extern void pg_mic2ascii(const unsigned char *mic, unsigned char *p, int len); +extern void latin2mic(const unsigned char *l, unsigned char *p, int len, + int lc, int encoding); +extern void mic2latin(const unsigned char *mic, unsigned char *p, int len, + int lc, int encoding); +extern void latin2mic_with_table(const unsigned char *l, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab); +extern void mic2latin_with_table(const unsigned char *mic, unsigned char *p, + int len, int lc, int encoding, + const unsigned char *tab); + +extern bool pg_utf8_islegal(const unsigned char *source, int length); #endif /* PG_WCHAR_H */ |