Refine memory allocation in ICU conversions

The simple calculations done to estimate the size of the output buffers
for ucnv_fromUChars() and ucnv_toUChars() could overflow int32_t for
large strings.  To avoid that, go the long way and run the function
first without an output buffer to get the correct output buffer size
requirement.

1 files changed, 20 insertions, 4 deletions

diff --git a/src/backend/utils/adt/pg_locale.c b/src/backend/utils/adt/pg_locale.c
index eae9fcb0de..12419fc8df 100644
--- a/src/backend/utils/adt/pg_locale.c
+++ b/src/backend/utils/adt/pg_locale.c
@@ -1511,14 +1511,22 @@ icu_to_uchar(UChar **buff_uchar, const char *buff, size_t nbytes)
 
 	init_icu_converter();
 
-	len_uchar = 2 * nbytes + 1; /* max length per docs */
-	*buff_uchar = palloc(len_uchar * sizeof(**buff_uchar));
 	status = U_ZERO_ERROR;
-	len_uchar = ucnv_toUChars(icu_converter, *buff_uchar, len_uchar,
+	len_uchar = ucnv_toUChars(icu_converter, NULL, 0,
+							  buff, nbytes, &status);
+	if (U_FAILURE(status) && status != U_BUFFER_OVERFLOW_ERROR)
+		ereport(ERROR,
+				(errmsg("ucnv_toUChars failed: %s", u_errorName(status))));
+
+	*buff_uchar = palloc((len_uchar + 1) * sizeof(**buff_uchar));
+
+	status = U_ZERO_ERROR;
+	len_uchar = ucnv_toUChars(icu_converter, *buff_uchar, len_uchar + 1,
 							  buff, nbytes, &status);
 	if (U_FAILURE(status))
 		ereport(ERROR,
 				(errmsg("ucnv_toUChars failed: %s", u_errorName(status))));
+
 	return len_uchar;
 }
 
@@ -1541,14 +1549,22 @@ icu_from_uchar(char **result, const UChar *buff_uchar, int32_t len_uchar)
 
 	init_icu_converter();
 
-	len_result = UCNV_GET_MAX_BYTES_FOR_STRING(len_uchar, ucnv_getMaxCharSize(icu_converter));
+	status = U_ZERO_ERROR;
+	len_result = ucnv_fromUChars(icu_converter, NULL, 0,
+								 buff_uchar, len_uchar, &status);
+	if (U_FAILURE(status) && status != U_BUFFER_OVERFLOW_ERROR)
+		ereport(ERROR,
+				(errmsg("ucnv_fromUChars failed: %s", u_errorName(status))));
+
 	*result = palloc(len_result + 1);
+
 	status = U_ZERO_ERROR;
 	len_result = ucnv_fromUChars(icu_converter, *result, len_result + 1,
 								 buff_uchar, len_uchar, &status);
 	if (U_FAILURE(status))
 		ereport(ERROR,
 				(errmsg("ucnv_fromUChars failed: %s", u_errorName(status))));
+
 	return len_result;
 }
 #endif							/* USE_ICU */