This is new version of make_greater_string patch.
1. wchar.c:1532 pg_wchar_table: Restore the pg_wchar_table.
2. wchar.c:1371 pg_utf8_increment: Remove dangerous memcpy, but
one memcpy is left because it's safe. Remove code check after
increment.
3. wchar.c:1429 pg_eucjp_increment: Remove dangerous
memcpy. Remove code check after increment. Minor bug fix.
4. wchar.c:1654 pg_database_encoding_character_incrementer:
Select increment function by switch-select.
horiguchi.kyotaro> This is rebased patch of `Allow encoding specific character
horiguchi.kyotaro>
incrementer'(https://commitfest.postgresql.org/action/patch_view?id=602).
--
Kyotaro Horiguchi
NTT Open Source Software Center
diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
index 3e84679..593dba6 100644
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -5653,6 +5653,18 @@ pattern_selectivity(Const *patt, Pattern_Type ptype)
/*
+ * This function is "character increment" function for bytea used in
+ * make_greater_string() that has same interface with pg_wchar_tbl.charinc.
+ */
+static bool byte_increment(unsigned char *ptr, int len)
+{
+ if (*ptr >= 255) return false;
+
+ (*ptr)++;
+ return true;
+}
+
+/*
* Try to generate a string greater than the given string or any
* string it is a prefix of. If successful, return a palloc'd string
* in the form of a Const node; else return NULL.
@@ -5691,6 +5703,7 @@ make_greater_string(const Const *str_const, FmgrInfo *ltproc, Oid collation)
int len;
Datum cmpstr;
text *cmptxt = NULL;
+ character_incrementer charincfunc;
/*
* Get a modifiable copy of the prefix string in C-string format, and set
@@ -5752,27 +5765,38 @@ make_greater_string(const Const *str_const, FmgrInfo *ltproc, Oid collation)
}
}
+ if (datatype != BYTEAOID)
+ charincfunc = pg_database_encoding_character_incrementer();
+ else
+ charincfunc = &byte_increment;
+
while (len > 0)
{
- unsigned char *lastchar = (unsigned char *) (workstr + len - 1);
- unsigned char savelastchar = *lastchar;
+ int charlen;
+ unsigned char *lastchar;
+ unsigned char savelastbyte;
+ Const *workstr_const;
+
+ if (datatype == BYTEAOID)
+ charlen = 1;
+ else
+ charlen = len - pg_mbcliplen(workstr, len, len - 1);
+
+ lastchar = (unsigned char *) (workstr + len - charlen);
/*
- * Try to generate a larger string by incrementing the last byte.
+ * savelastbyte has meaning only for datatype == BYTEAOID
*/
- while (*lastchar < (unsigned char) 255)
- {
- Const *workstr_const;
+ savelastbyte = *lastchar;
- (*lastchar)++;
+ /*
+ * Try to generate a larger string by incrementing the last byte or
+ * character.
+ */
+ if (charincfunc(lastchar, charlen)) {
if (datatype != BYTEAOID)
- {
- /* do not generate invalid encoding sequences */
- if (!pg_verifymbstr(workstr, len, true))
- continue;
workstr_const = string_to_const(workstr, datatype);
- }
else
workstr_const = string_to_bytea_const(workstr, len);
@@ -5787,26 +5811,17 @@ make_greater_string(const Const *str_const, FmgrInfo *ltproc, Oid collation)
pfree(workstr);
return workstr_const;
}
-
+
/* No good, release unusable value and try again */
pfree(DatumGetPointer(workstr_const->constvalue));
pfree(workstr_const);
}
- /* restore last byte so we don't confuse pg_mbcliplen */
- *lastchar = savelastchar;
-
/*
- * Truncate off the last character, which might be more than 1 byte,
- * depending on the character encoding.
+ * Truncate off the last character or restore last byte for BYTEA.
*/
- if (datatype != BYTEAOID && pg_database_encoding_max_length() > 1)
- len = pg_mbcliplen(workstr, len, len - 1);
- else
- len -= 1;
-
- if (datatype != BYTEAOID)
- workstr[len] = '\0';
+ len -= charlen;
+ workstr[len] = (datatype != BYTEAOID ? '\0' : savelastbyte);
}
/* Failed... */
diff --git a/src/backend/utils/mb/wchar.c b/src/backend/utils/mb/wchar.c
index f23732f..d6dc717 100644
--- a/src/backend/utils/mb/wchar.c
+++ b/src/backend/utils/mb/wchar.c
@@ -1336,6 +1336,195 @@ pg_utf8_islegal(const unsigned char *source, int length)
/*
*-------------------------------------------------------------------
+ * character incrementer
+ *
+ * These functions accept "charptr", a pointer to the first byte of a
+ * maybe-multibyte character. Try `increment' the character and return true if
+ * successed. If these functions returns false, the character should be
+ * untouched. These functions must be implemented in correspondence with
+ * verifiers, in other words, the rewrited character by this function must pass
+ * the check by pg_*_verifier() if returns true. Returning the return value of
+ * pg_*_verifier() corresponding can finnaly avoid such a inconsistency when
+ * something wrong.
+ * -------------------------------------------------------------------
+ */
+
+#ifndef FRONTEND
+static bool pg_generic_charinc(unsigned char *charptr, int len)
+{
+ unsigned char *lastchar = (unsigned char *) (charptr + len - 1);
+ unsigned char savelastchar = *lastchar;
+ const char *const_charptr = (const char *)charptr;
+
+ while (*lastchar < (unsigned char) 255)
+ {
+ (*lastchar)++;
+ if (!pg_verifymbstr(const_charptr, len, true))
+ continue;
+ return true;
+ }
+
+ *lastchar = savelastchar;
+ return false;
+}
+
+static bool
+pg_utf8_increment(unsigned char *charptr, int length)
+{
+ unsigned char a;
+ unsigned char bak[4];
+ bool success;
+
+ switch (length)
+ {
+ default:
+ /* reject lengths 5 and 6 for now */
+ return false;
+ case 4:
+ bak[3] = charptr[3];
+ a = charptr[3];
+ if (a < 0xBF)
+ {
+ charptr[3]++;
+ break;
+ }
+ charptr[3] = 0x80;
+ /* FALL THRU */
+ case 3:
+ bak[2] = charptr[2];
+ a = charptr[2];
+ if (a < 0xBF)
+ {
+ charptr[2]++;
+ break;
+ }
+ charptr[2] = 0x80;
+ /* FALL THRU */
+ case 2:
+ bak[1] = charptr[1];
+ a = charptr[1];
+ if ((*charptr == 0xed && a < 0x9F) || a < 0xBF)
+ {
+ charptr[1]++;
+ break;
+ }
+ charptr[1] = 0x80;
+ /* FALL THRU */
+ case 1:
+ bak[0] = *charptr;
+ a = *charptr;
+ if (a == 0x7F || a == 0xDF || a == 0xEF || a == 0xF7) {
+ /* Rewinding modified bytes and return fail. length is
+ * confirmed to be between 1 and 4 here. */
+ memcpy(charptr, bak, length);
+ return false;
+ }
+ charptr[0]++;
+ break;
+ }
+
+ return true;
+}
+
+static bool
+pg_eucjp_increment(unsigned char *charptr, int length)
+{
+ unsigned char bak[3];
+ bool success;
+ unsigned char c1, c2;
+ signed int i;
+
+ c1 = *charptr;
+
+ switch (c1)
+ {
+ case SS2: /* JIS X 0201 */
+ if (length != 2) return false;
+
+ c2 = charptr[1];
+
+ if (c2 > 0xde)
+ charptr[0] = charptr[1] = 0xa1;
+ else if (c2 < 0xa1)
+ charptr[1] = 0xa1;
+ else
+ charptr[1]++;
+
+ break;
+
+ case SS3: /* JIS X 0212 */
+ if (length != 3) return false;
+
+ for (i = 2 ; i > 0 ; i--)
+ {
+ bak[i] = charptr[i];
+ c2 = charptr[i];
+ if (c2 < 0xa1)
+ {
+ charptr[i] = 0xa1;
+ return true;
+ }
+ else if (c2 < 0xfe)
+ {
+ charptr[i]++;
+ break;
+ }
+ charptr[i] = 0xa1;
+ }
+
+
+ if (i == 0) /* Out of 3-byte code region */
+ {
+ charptr[1] = bak[1];
+ charptr[2] = bak[2];
+ return false;
+ }
+
+ break;
+
+ default:
+ if (IS_HIGHBIT_SET(c1)) /* JIS X 0208? */
+ {
+ if (length != 2) return false;
+
+ for (i = 1 ; i >= 0 ; i--) /* i must be signed */
+ {
+ bak[i] = charptr[i];
+ c2 = charptr[i];
+ if (c2 < 0xa1)
+ {
+ charptr[i] = 0xa1;
+ return true;
+ }
+ else if (c2 < 0xfe)
+ {
+ charptr[i]++;
+ break;
+ }
+ charptr[i] = 0xa1;
+ }
+
+ if (i < 0) /* Out of 2 byte code region */
+ {
+ charptr[0] = bak[0];
+ charptr[1] = bak[1];
+ return false;
+ }
+ }
+ else
+ { /* ASCII, single byte */
+ if (c1 > 0x7e)
+ return false;
+ (*charptr)++;
+ }
+ }
+
+ return true;
+}
+#endif
+
+/*
+ *-------------------------------------------------------------------
* encoding info table
* XXX must be sorted by the same order as enum pg_enc (in mb/pg_wchar.h)
*-------------------------------------------------------------------
@@ -1459,6 +1648,24 @@ pg_database_encoding_max_length(void)
}
/*
+ * give the character incrementer for the encoding for the current database
+ */
+character_incrementer
+pg_database_encoding_character_incrementer(void)
+{
+ switch (GetDatabaseEncoding()) {
+ case PG_UTF8:
+ return pg_utf8_increment;
+
+ case PG_EUC_JP:
+ return pg_eucjp_increment;
+
+ default:
+ return pg_generic_charinc;
+ }
+}
+
+/*
* Verify mbstr to make sure that it is validly encoded in the current
* database encoding. Otherwise same as pg_verify_mbstr().
*/
diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h
index 826c7af..728175c 100644
--- a/src/include/mb/pg_wchar.h
+++ b/src/include/mb/pg_wchar.h
@@ -284,6 +284,8 @@ typedef int (*mblen_converter) (const unsigned char *mbstr);
typedef int (*mbdisplaylen_converter) (const unsigned char *mbstr);
+typedef bool (*character_incrementer) (unsigned char *mbstr, int len);
+
typedef int (*mbverifier) (const unsigned char *mbstr, int len);
typedef struct
@@ -389,6 +391,7 @@ extern int pg_encoding_mbcliplen(int encoding, const char *mbstr,
extern int pg_mbcharcliplen(const char *mbstr, int len, int imit);
extern int pg_encoding_max_length(int encoding);
extern int pg_database_encoding_max_length(void);
+extern character_incrementer pg_database_encoding_character_incrementer(void);
extern int PrepareClientEncoding(int encoding);
extern int SetClientEncoding(int encoding);
--
Sent via pgsql-hackers mailing list (pgsql-hackers@postgresql.org)
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-hackers
