From 9c61aa3604af862a8c8217eee8d268b80ae06a2d Mon Sep 17 00:00:00 2001 From: Heikki Linnakangas Date: Mon, 14 Dec 2020 18:28:45 +0200 Subject: [PATCH 1/5] Add new mbverifystr() function for each encoding. This potentially makes pg_verify_mbstr() function faster, by allowing more efficient encoding-specific implementations. All of the implementations in this patch are pretty naive, though. --- src/backend/commands/extension.c | 2 +- src/backend/utils/mb/conv.c | 2 +- .../euc2004_sjis2004/euc2004_sjis2004.c | 4 +- .../euc_jp_and_sjis/euc_jp_and_sjis.c | 10 +- .../euc_kr_and_mic/euc_kr_and_mic.c | 4 +- .../euc_tw_and_big5/euc_tw_and_big5.c | 8 +- src/backend/utils/mb/mbutils.c | 31 +- src/common/wchar.c | 514 +++++++++++++++--- src/include/mb/pg_wchar.h | 10 +- 9 files changed, 491 insertions(+), 94 deletions(-) diff --git a/src/backend/commands/extension.c b/src/backend/commands/extension.c index b5630b4c8d9..82f1248dbf1 100644 --- a/src/backend/commands/extension.c +++ b/src/backend/commands/extension.c @@ -682,7 +682,7 @@ read_extension_script_file(const ExtensionControlFile *control, src_encoding = control->encoding; /* make sure that source string is valid in the expected encoding */ - pg_verify_mbstr_len(src_encoding, src_str, len, false); + (void) pg_verify_mbstr(src_encoding, src_str, len, false); /* * Convert the encoding to the database encoding. read_whole_file diff --git a/src/backend/utils/mb/conv.c b/src/backend/utils/mb/conv.c index 54dcf71fb75..192948caad2 100644 --- a/src/backend/utils/mb/conv.c +++ b/src/backend/utils/mb/conv.c @@ -653,7 +653,7 @@ LocalToUtf(const unsigned char *iso, int len, continue; } - l = pg_encoding_verifymb(encoding, (const char *) iso, len); + l = pg_encoding_verifymbchar(encoding, (const char *) iso, len); if (l < 0) break; diff --git a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c index 9ba6bd30405..3628e690aa1 100644 --- a/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c +++ b/src/backend/utils/mb/conversion_procs/euc2004_sjis2004/euc2004_sjis2004.c @@ -87,7 +87,7 @@ euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len) continue; } - l = pg_encoding_verifymb(PG_EUC_JIS_2004, (const char *) euc, len); + l = pg_encoding_verifymbchar(PG_EUC_JIS_2004, (const char *) euc, len); if (l < 0) report_invalid_encoding(PG_EUC_JIS_2004, @@ -238,7 +238,7 @@ shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len continue; } - l = pg_encoding_verifymb(PG_SHIFT_JIS_2004, (const char *) sjis, len); + l = pg_encoding_verifymbchar(PG_SHIFT_JIS_2004, (const char *) sjis, len); if (l < 0 || l > len) report_invalid_encoding(PG_SHIFT_JIS_2004, 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 4ca8e2126e4..ea05436596d 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 @@ -291,7 +291,7 @@ mic2sjis(const unsigned char *mic, unsigned char *p, int len) len--; continue; } - l = pg_encoding_verifymb(PG_MULE_INTERNAL, (const char *) mic, len); + l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); @@ -381,7 +381,7 @@ euc_jp2mic(const unsigned char *euc, unsigned char *p, int len) len--; continue; } - l = pg_encoding_verifymb(PG_EUC_JP, (const char *) euc, len); + l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); @@ -431,7 +431,7 @@ mic2euc_jp(const unsigned char *mic, unsigned char *p, int len) len--; continue; } - l = pg_encoding_verifymb(PG_MULE_INTERNAL, (const char *) mic, len); + l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); @@ -485,7 +485,7 @@ euc_jp2sjis(const unsigned char *euc, unsigned char *p, int len) len--; continue; } - l = pg_encoding_verifymb(PG_EUC_JP, (const char *) euc, len); + l = pg_encoding_verifymbchar(PG_EUC_JP, (const char *) euc, len); if (l < 0) report_invalid_encoding(PG_EUC_JP, (const char *) euc, len); @@ -580,7 +580,7 @@ sjis2euc_jp(const unsigned char *sjis, unsigned char *p, int len) len--; continue; } - l = pg_encoding_verifymb(PG_SJIS, (const char *) sjis, len); + l = pg_encoding_verifymbchar(PG_SJIS, (const char *) sjis, len); if (l < 0) report_invalid_encoding(PG_SJIS, (const char *) sjis, len); 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 4d7876a666e..600c5cbc5cd 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 @@ -76,7 +76,7 @@ euc_kr2mic(const unsigned char *euc, unsigned char *p, int len) c1 = *euc; if (IS_HIGHBIT_SET(c1)) { - l = pg_encoding_verifymb(PG_EUC_KR, (const char *) euc, len); + l = pg_encoding_verifymbchar(PG_EUC_KR, (const char *) euc, len); if (l != 2) report_invalid_encoding(PG_EUC_KR, (const char *) euc, len); @@ -122,7 +122,7 @@ mic2euc_kr(const unsigned char *mic, unsigned char *p, int len) len--; continue; } - l = pg_encoding_verifymb(PG_MULE_INTERNAL, (const char *) mic, len); + l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); 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 82a22b9bebf..7e4c2697b07 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 @@ -148,7 +148,7 @@ euc_tw2mic(const unsigned char *euc, unsigned char *p, int len) c1 = *euc; if (IS_HIGHBIT_SET(c1)) { - l = pg_encoding_verifymb(PG_EUC_TW, (const char *) euc, len); + l = pg_encoding_verifymbchar(PG_EUC_TW, (const char *) euc, len); if (l < 0) report_invalid_encoding(PG_EUC_TW, (const char *) euc, len); @@ -213,7 +213,7 @@ mic2euc_tw(const unsigned char *mic, unsigned char *p, int len) len--; continue; } - l = pg_encoding_verifymb(PG_MULE_INTERNAL, (const char *) mic, len); + l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); @@ -272,7 +272,7 @@ big52mic(const unsigned char *big5, unsigned char *p, int len) len--; continue; } - l = pg_encoding_verifymb(PG_BIG5, (const char *) big5, len); + l = pg_encoding_verifymbchar(PG_BIG5, (const char *) big5, len); if (l < 0) report_invalid_encoding(PG_BIG5, (const char *) big5, len); @@ -321,7 +321,7 @@ mic2big5(const unsigned char *mic, unsigned char *p, int len) len--; continue; } - l = pg_encoding_verifymb(PG_MULE_INTERNAL, (const char *) mic, len); + l = pg_encoding_verifymbchar(PG_MULE_INTERNAL, (const char *) mic, len); if (l < 0) report_invalid_encoding(PG_MULE_INTERNAL, (const char *) mic, len); diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c index a8e13cacfde..67d1c4fc19f 100644 --- a/src/backend/utils/mb/mbutils.c +++ b/src/backend/utils/mb/mbutils.c @@ -519,7 +519,7 @@ pg_convert(PG_FUNCTION_ARGS) /* make sure that source string is valid */ len = VARSIZE_ANY_EXHDR(string); src_str = VARDATA_ANY(string); - pg_verify_mbstr_len(src_encoding, src_str, len, false); + (void) pg_verify_mbstr(src_encoding, src_str, len, false); /* perform conversion */ dest_str = (char *) pg_do_encoding_conversion((unsigned char *) unconstify(char *, src_str), @@ -1215,10 +1215,10 @@ static bool pg_generic_charinc(unsigned char *charptr, int len) { unsigned char *lastbyte = charptr + len - 1; - mbverifier mbverify; + mbchar_verifier mbverify; /* We can just invoke the character verifier directly. */ - mbverify = pg_wchar_table[GetDatabaseEncoding()].mbverify; + mbverify = pg_wchar_table[GetDatabaseEncoding()].mbverifychar; while (*lastbyte < (unsigned char) 255) { @@ -1445,8 +1445,7 @@ pg_database_encoding_max_length(void) bool pg_verifymbstr(const char *mbstr, int len, bool noError) { - return - pg_verify_mbstr_len(GetDatabaseEncoding(), mbstr, len, noError) >= 0; + return pg_verify_mbstr(GetDatabaseEncoding(), mbstr, len, noError); } /* @@ -1456,7 +1455,18 @@ pg_verifymbstr(const char *mbstr, int len, bool noError) bool pg_verify_mbstr(int encoding, const char *mbstr, int len, bool noError) { - return pg_verify_mbstr_len(encoding, mbstr, len, noError) >= 0; + int oklen; + + Assert(PG_VALID_ENCODING(encoding)); + + oklen = pg_wchar_table[encoding].mbverifystr((const unsigned char *) mbstr, len); + if (oklen != len) + { + if (noError) + return false; + report_invalid_encoding(encoding, mbstr + oklen, len - oklen); + } + return true; } /* @@ -1469,11 +1479,14 @@ pg_verify_mbstr(int encoding, const char *mbstr, int len, bool noError) * If OK, return length of string in the encoding. * If a problem is found, return -1 when noError is * true; when noError is false, ereport() a descriptive message. + * + * Note: We cannot use the faster encoding-specific mbverifystr() function + * here, because we need to count the number of characters in the string. */ int pg_verify_mbstr_len(int encoding, const char *mbstr, int len, bool noError) { - mbverifier mbverify; + mbchar_verifier mbverifychar; int mb_len; Assert(PG_VALID_ENCODING(encoding)); @@ -1493,7 +1506,7 @@ pg_verify_mbstr_len(int encoding, const char *mbstr, int len, bool noError) } /* fetch function pointer just once */ - mbverify = pg_wchar_table[encoding].mbverify; + mbverifychar = pg_wchar_table[encoding].mbverifychar; mb_len = 0; @@ -1516,7 +1529,7 @@ pg_verify_mbstr_len(int encoding, const char *mbstr, int len, bool noError) report_invalid_encoding(encoding, mbstr, len); } - l = (*mbverify) ((const unsigned char *) mbstr, len); + l = (*mbverifychar) ((const unsigned char *) mbstr, len); if (l < 0) { diff --git a/src/common/wchar.c b/src/common/wchar.c index efaf1c155bb..5ab29bcbc39 100644 --- a/src/common/wchar.c +++ b/src/common/wchar.c @@ -19,7 +19,7 @@ * Operations on multi-byte encodings are driven by a table of helper * functions. * - * To add an encoding support, define mblen(), dsplen() and verifier() for + * To add an encoding support, define mblen(), dsplen(), verifychar() and verifystr() for * the encoding. For server-encodings, also define mb2wchar() and wchar2mb() * conversion functions. * @@ -1087,29 +1087,47 @@ pg_gb18030_dsplen(const unsigned char *s) *------------------------------------------------------------------- * multibyte sequence validators * - * These functions accept "s", a pointer to the first byte of a string, + * The verifychar 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 + * The verifychar 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". + * + * The verifystr functions also accept "s", a pointer to a string and "len", + * the remaining length of the string. It tries to verify the whole string, and + * returns the number of input bytes (<= len) that are valid. If there is an + * encoding error, the return value is < len, and len points to the first invalid + * byte. + * + * The verifystr functions must test for and reject zeroes in the input. *------------------------------------------------------------------- */ - static int -pg_ascii_verifier(const unsigned char *s, int len) +pg_ascii_verifychar(const unsigned char *s, int len) { return 1; } +static int +pg_ascii_verifystr(const unsigned char *s, int len) +{ + const unsigned char *nullpos = memchr(s, 0, len); + + if (nullpos == NULL) + return len; + { + return nullpos - s; + } +} + #define IS_EUC_RANGE_VALID(c) ((c) >= 0xa1 && (c) <= 0xfe) static int -pg_eucjp_verifier(const unsigned char *s, int len) +pg_eucjp_verifychar(const unsigned char *s, int len) { int l; unsigned char c1, @@ -1164,7 +1182,36 @@ pg_eucjp_verifier(const unsigned char *s, int len) } static int -pg_euckr_verifier(const unsigned char *s, int len) +pg_eucjp_verifystr(const unsigned char *s, int len) +{ + const unsigned char *start = s; + + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_eucjp_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + +static int +pg_euckr_verifychar(const unsigned char *s, int len) { int l; unsigned char c1, @@ -1192,11 +1239,41 @@ pg_euckr_verifier(const unsigned char *s, int len) return l; } +static int +pg_euckr_verifystr(const unsigned char *s, int len) +{ + const unsigned char *start = s; + + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_euckr_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + /* EUC-CN byte sequences are exactly same as EUC-KR */ -#define pg_euccn_verifier pg_euckr_verifier +#define pg_euccn_verifychar pg_euckr_verifychar +#define pg_euccn_verifystr pg_euckr_verifystr static int -pg_euctw_verifier(const unsigned char *s, int len) +pg_euctw_verifychar(const unsigned char *s, int len) { int l; unsigned char c1, @@ -1246,7 +1323,36 @@ pg_euctw_verifier(const unsigned char *s, int len) } static int -pg_johab_verifier(const unsigned char *s, int len) +pg_euctw_verifystr(const unsigned char *s, int len) +{ + const unsigned char *start = s; + + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_euctw_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + +static int +pg_johab_verifychar(const unsigned char *s, int len) { int l, mbl; @@ -1270,7 +1376,36 @@ pg_johab_verifier(const unsigned char *s, int len) } static int -pg_mule_verifier(const unsigned char *s, int len) +pg_johab_verifystr(const unsigned char *s, int len) +{ + const unsigned char *start = s; + + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_johab_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + +static int +pg_mule_verifychar(const unsigned char *s, int len) { int l, mbl; @@ -1291,13 +1426,54 @@ pg_mule_verifier(const unsigned char *s, int len) } static int -pg_latin1_verifier(const unsigned char *s, int len) +pg_mule_verifystr(const unsigned char *s, int len) +{ + const unsigned char *start = s; + + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_mule_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + +static int +pg_latin1_verifychar(const unsigned char *s, int len) { return 1; } static int -pg_sjis_verifier(const unsigned char *s, int len) +pg_latin1_verifystr(const unsigned char *s, int len) +{ + const unsigned char *nullpos = memchr(s, 0, len); + + if (nullpos == NULL) + return len; + { + return nullpos - s; + } +} + +static int +pg_sjis_verifychar(const unsigned char *s, int len) { int l, mbl; @@ -1320,7 +1496,36 @@ pg_sjis_verifier(const unsigned char *s, int len) } static int -pg_big5_verifier(const unsigned char *s, int len) +pg_sjis_verifystr(const unsigned char *s, int len) +{ + const unsigned char *start = s; + + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_sjis_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + +static int +pg_big5_verifychar(const unsigned char *s, int len) { int l, mbl; @@ -1340,7 +1545,36 @@ pg_big5_verifier(const unsigned char *s, int len) } static int -pg_gbk_verifier(const unsigned char *s, int len) +pg_big5_verifystr(const unsigned char *s, int len) +{ + const unsigned char *start = s; + + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_big5_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + +static int +pg_gbk_verifychar(const unsigned char *s, int len) { int l, mbl; @@ -1360,7 +1594,36 @@ pg_gbk_verifier(const unsigned char *s, int len) } static int -pg_uhc_verifier(const unsigned char *s, int len) +pg_gbk_verifystr(const unsigned char *s, int len) +{ + const unsigned char *start = s; + + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_gbk_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + +static int +pg_uhc_verifychar(const unsigned char *s, int len) { int l, mbl; @@ -1380,7 +1643,36 @@ pg_uhc_verifier(const unsigned char *s, int len) } static int -pg_gb18030_verifier(const unsigned char *s, int len) +pg_uhc_verifystr(const unsigned char *s, int len) +{ + const unsigned char *start = s; + + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_uhc_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + +static int +pg_gb18030_verifychar(const unsigned char *s, int len) { int l; @@ -1411,11 +1703,55 @@ pg_gb18030_verifier(const unsigned char *s, int len) } static int -pg_utf8_verifier(const unsigned char *s, int len) +pg_gb18030_verifystr(const unsigned char *s, int len) { - int l = pg_utf_mblen(s); + const unsigned char *start = s; - if (len < l) + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_gb18030_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + +static int +pg_utf8_verifychar(const unsigned char *s, int len) +{ + int l; + + if ((*s & 0x80) == 0) + { + if (*s == '\0') + return -1; + return 1; + } + else if ((*s & 0xe0) == 0xc0) + l = 2; + else if ((*s & 0xf0) == 0xe0) + l = 3; + else if ((*s & 0xf8) == 0xf0) + l = 4; + else + l = 1; + + if (l > len) return -1; if (!pg_utf8_islegal(s, l)) @@ -1424,6 +1760,35 @@ pg_utf8_verifier(const unsigned char *s, int len) return l; } +static int +pg_utf8_verifystr(const unsigned char *s, int len) +{ + const unsigned char *start = s; + + while (len > 0) + { + int l; + + /* fast path for ASCII-subset characters */ + if (!IS_HIGHBIT_SET(*s)) + { + if (*s == '\0') + break; + l = 1; + } + else + { + l = pg_utf8_verifychar(s, len); + if (l == -1) + break; + } + s += l; + len -= l; + } + + return s - start; +} + /* * Check for validity of a single UTF-8 encoded character * @@ -1503,48 +1868,48 @@ pg_utf8_islegal(const unsigned char *source, int length) *------------------------------------------------------------------- */ const pg_wchar_tbl pg_wchar_table[] = { - {pg_ascii2wchar_with_len, pg_wchar2single_with_len, pg_ascii_mblen, pg_ascii_dsplen, pg_ascii_verifier, 1}, /* PG_SQL_ASCII */ - {pg_eucjp2wchar_with_len, pg_wchar2euc_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifier, 3}, /* PG_EUC_JP */ - {pg_euccn2wchar_with_len, pg_wchar2euc_with_len, pg_euccn_mblen, pg_euccn_dsplen, pg_euccn_verifier, 2}, /* PG_EUC_CN */ - {pg_euckr2wchar_with_len, pg_wchar2euc_with_len, pg_euckr_mblen, pg_euckr_dsplen, pg_euckr_verifier, 3}, /* PG_EUC_KR */ - {pg_euctw2wchar_with_len, pg_wchar2euc_with_len, pg_euctw_mblen, pg_euctw_dsplen, pg_euctw_verifier, 4}, /* PG_EUC_TW */ - {pg_eucjp2wchar_with_len, pg_wchar2euc_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifier, 3}, /* PG_EUC_JIS_2004 */ - {pg_utf2wchar_with_len, pg_wchar2utf_with_len, pg_utf_mblen, pg_utf_dsplen, pg_utf8_verifier, 4}, /* PG_UTF8 */ - {pg_mule2wchar_with_len, pg_wchar2mule_with_len, pg_mule_mblen, pg_mule_dsplen, pg_mule_verifier, 4}, /* PG_MULE_INTERNAL */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_LATIN1 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_LATIN2 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_LATIN3 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_LATIN4 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_LATIN5 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_LATIN6 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_LATIN7 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_LATIN8 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_LATIN9 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_LATIN10 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN1256 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN1258 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN866 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN874 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_KOI8R */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN1251 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN1252 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* ISO-8859-5 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* ISO-8859-6 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* ISO-8859-7 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* ISO-8859-8 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN1250 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN1253 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN1254 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN1255 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_WIN1257 */ - {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1}, /* PG_KOI8U */ - {0, 0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifier, 2}, /* PG_SJIS */ - {0, 0, pg_big5_mblen, pg_big5_dsplen, pg_big5_verifier, 2}, /* PG_BIG5 */ - {0, 0, pg_gbk_mblen, pg_gbk_dsplen, pg_gbk_verifier, 2}, /* PG_GBK */ - {0, 0, pg_uhc_mblen, pg_uhc_dsplen, pg_uhc_verifier, 2}, /* PG_UHC */ - {0, 0, pg_gb18030_mblen, pg_gb18030_dsplen, pg_gb18030_verifier, 4}, /* PG_GB18030 */ - {0, 0, pg_johab_mblen, pg_johab_dsplen, pg_johab_verifier, 3}, /* PG_JOHAB */ - {0, 0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifier, 2} /* PG_SHIFT_JIS_2004 */ + {pg_ascii2wchar_with_len, pg_wchar2single_with_len, pg_ascii_mblen, pg_ascii_dsplen, pg_ascii_verifychar, pg_ascii_verifystr, 1}, /* PG_SQL_ASCII */ + {pg_eucjp2wchar_with_len, pg_wchar2euc_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifychar, pg_eucjp_verifystr, 3}, /* PG_EUC_JP */ + {pg_euccn2wchar_with_len, pg_wchar2euc_with_len, pg_euccn_mblen, pg_euccn_dsplen, pg_euccn_verifychar, pg_euccn_verifystr, 2}, /* PG_EUC_CN */ + {pg_euckr2wchar_with_len, pg_wchar2euc_with_len, pg_euckr_mblen, pg_euckr_dsplen, pg_euckr_verifychar, pg_euckr_verifystr, 3}, /* PG_EUC_KR */ + {pg_euctw2wchar_with_len, pg_wchar2euc_with_len, pg_euctw_mblen, pg_euctw_dsplen, pg_euctw_verifychar, pg_euctw_verifystr, 4}, /* PG_EUC_TW */ + {pg_eucjp2wchar_with_len, pg_wchar2euc_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifychar, pg_eucjp_verifystr, 3}, /* PG_EUC_JIS_2004 */ + {pg_utf2wchar_with_len, pg_wchar2utf_with_len, pg_utf_mblen, pg_utf_dsplen, pg_utf8_verifychar, pg_utf8_verifystr, 4}, /* PG_UTF8 */ + {pg_mule2wchar_with_len, pg_wchar2mule_with_len, pg_mule_mblen, pg_mule_dsplen, pg_mule_verifychar, pg_mule_verifystr, 4}, /* PG_MULE_INTERNAL */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_LATIN1 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_LATIN2 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_LATIN3 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_LATIN4 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_LATIN5 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_LATIN6 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_LATIN7 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_LATIN8 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_LATIN9 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_LATIN10 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN1256 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN1258 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN866 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN874 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_KOI8R */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN1251 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN1252 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* ISO-8859-5 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* ISO-8859-6 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* ISO-8859-7 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* ISO-8859-8 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN1250 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN1253 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN1254 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN1255 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_WIN1257 */ + {pg_latin12wchar_with_len, pg_wchar2single_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifychar, pg_latin1_verifystr, 1}, /* PG_KOI8U */ + {0, 0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifychar, pg_sjis_verifystr, 2}, /* PG_SJIS */ + {0, 0, pg_big5_mblen, pg_big5_dsplen, pg_big5_verifychar, pg_big5_verifystr, 2}, /* PG_BIG5 */ + {0, 0, pg_gbk_mblen, pg_gbk_dsplen, pg_gbk_verifychar, pg_gbk_verifystr, 2}, /* PG_GBK */ + {0, 0, pg_uhc_mblen, pg_uhc_dsplen, pg_uhc_verifychar, pg_uhc_verifystr, 2}, /* PG_UHC */ + {0, 0, pg_gb18030_mblen, pg_gb18030_dsplen, pg_gb18030_verifychar, pg_gb18030_verifystr, 4}, /* PG_GB18030 */ + {0, 0, pg_johab_mblen, pg_johab_dsplen, pg_johab_verifychar, pg_johab_verifystr, 3}, /* PG_JOHAB */ + {0, 0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifychar, pg_sjis_verifystr, 2} /* PG_SHIFT_JIS_2004 */ }; /* @@ -1572,14 +1937,29 @@ pg_encoding_dsplen(int encoding, const 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.) + * full details of the mbverifychar API.) + */ +int +pg_encoding_verifymbchar(int encoding, const char *mbchar, int len) +{ + return (PG_VALID_ENCODING(encoding) ? + pg_wchar_table[encoding].mbverifychar((const unsigned char *) mbchar, len) : + pg_wchar_table[PG_SQL_ASCII].mbverifychar((const unsigned char *) mbchar, len)); +} + +/* + * Verify that a string is valid for the given encoding. + * + * Returns the number of input bytes (<= len) that form a valid string. If + * it equals 'len', the whole input is valid. Otherwise it is the index of + * the first invalid input byte. */ int -pg_encoding_verifymb(int encoding, const char *mbstr, int len) +pg_encoding_verifymbstr(int encoding, const char *mbstr, int len) { return (PG_VALID_ENCODING(encoding) ? - pg_wchar_table[encoding].mbverify((const unsigned char *) mbstr, len) : - pg_wchar_table[PG_SQL_ASCII].mbverify((const unsigned char *) mbstr, len)); + pg_wchar_table[encoding].mbverifystr((const unsigned char *) mbstr, len) : + pg_wchar_table[PG_SQL_ASCII].mbverifystr((const unsigned char *) mbstr, len)); } /* diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h index 494aefc7fab..549f2dd045d 100644 --- a/src/include/mb/pg_wchar.h +++ b/src/include/mb/pg_wchar.h @@ -371,7 +371,9 @@ typedef int (*mbdisplaylen_converter) (const unsigned char *mbstr); typedef bool (*mbcharacter_incrementer) (unsigned char *mbstr, int len); -typedef int (*mbverifier) (const unsigned char *mbstr, int len); +typedef int (*mbchar_verifier) (const unsigned char *mbstr, int len); + +typedef int (*mbstr_verifier) (const unsigned char *mbstr, int len); typedef struct { @@ -381,7 +383,8 @@ typedef struct * to a multibyte */ mblen_converter mblen; /* get byte length of a char */ mbdisplaylen_converter dsplen; /* get display width of a char */ - mbverifier mbverify; /* verify multibyte sequence */ + mbchar_verifier mbverifychar; /* verify multibyte character */ + mbstr_verifier mbverifystr; /* verify multibyte string */ int maxmblen; /* max bytes for a char in this encoding */ } pg_wchar_tbl; @@ -554,7 +557,8 @@ extern int pg_valid_server_encoding_id(int encoding); */ extern int pg_encoding_mblen(int encoding, const char *mbstr); extern int pg_encoding_dsplen(int encoding, const char *mbstr); -extern int pg_encoding_verifymb(int encoding, const char *mbstr, int len); +extern int pg_encoding_verifymbchar(int encoding, const char *mbchar, int len); +extern int pg_encoding_verifymbstr(int encoding, const char *mbstr, int len); extern int pg_encoding_max_length(int encoding); extern int pg_valid_client_encoding(const char *name); extern int pg_valid_server_encoding(const char *name); -- 2.20.1