Columns in a row are separated by the delimiter character.
The column values themselves are strings generated by the
output function, or acceptable to the input function, of each
- attribute's data type. The specified null-value string is used in
+ attribute's data type. The specified null string is used in
place of columns that are null.
COPY FROM will raise an error if any line of the
input file contains more or fewer columns than are expected.
newline, carriage return, and the current delimiter character.
+ The specified null string is sent by COPY TO without
+ adding any backslashes; conversely, COPY FROM matches
+ the input against the null string before removing backslashes. Therefore,
+ a null string such as \N cannot be confused with
+ the actual data value \N (which would be represented
+ as \\N).
+
+
The following special backslash sequences are recognized by
COPY FROM:
- Never put a backslash before a data character N or period
- (.). Such pairs will be mistaken for the default null string
- or the end-of-data marker, respectively. Any other backslashed character
- that is not mentioned in the above table will be taken to represent itself.
+ Any other backslashed character that is not mentioned in the above table
+ will be taken to represent itself. However, beware of adding backslashes
+ unnecessarily, since that might accidentally produce a string matching the
+ end-of-data marker (\.) or the null string (\N by
+ default). These strings will be recognized before any other backslash
+ processing is done.
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/commands/copy.c,v 1.212 2003/09/29 22:06:40 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/commands/copy.c,v 1.213 2003/10/06 02:38:53 tgl Exp $
*
*-------------------------------------------------------------------------
*/
* to server encoding, and then extract individual attribute fields into
* attribute_buf. (We used to have CopyReadAttribute read the input source
* directly, but that caused a lot of encoding issues and unnecessary logic
- * complexity).
+ * complexity.)
*/
static StringInfoData line_buf;
static bool line_buf_converted;
static void CopyFrom(Relation rel, List *attnumlist, bool binary, bool oids,
char *delim, char *null_print);
static bool CopyReadLine(void);
-static char *CopyReadAttribute(const char *delim, CopyReadResult *result);
+static char *CopyReadAttribute(const char *delim, const char *null_print,
+ CopyReadResult *result, bool *isnull);
static Datum CopyReadBinaryAttribute(int column_no, FmgrInfo *flinfo,
Oid typelem, bool *isnull);
static void CopyAttributeOut(char *string, char *delim);
tmp = 0;
CopySendInt32(tmp);
}
+ else
+ {
+ /*
+ * For non-binary copy, we need to convert null_print to client
+ * encoding, because it will be sent directly with CopySendString.
+ */
+ if (server_encoding != client_encoding)
+ null_print = (char *)
+ pg_server_to_client((unsigned char *) null_print,
+ strlen(null_print));
+ }
mySnapshot = CopyQuerySnapshot();
if (file_has_oids)
{
- string = CopyReadAttribute(delim, &result);
+ string = CopyReadAttribute(delim, null_print,
+ &result, &isnull);
- if (strcmp(string, null_print) == 0)
+ if (isnull)
ereport(ERROR,
(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
errmsg("null OID in COPY data")));
errmsg("missing data for column \"%s\"",
NameStr(attr[m]->attname))));
- string = CopyReadAttribute(delim, &result);
+ string = CopyReadAttribute(delim, null_print,
+ &result, &isnull);
- if (strcmp(string, null_print) == 0)
+ if (isnull)
{
/* we read an SQL NULL, no need to do anything */
}
return result;
}
-/*
+/*----------
* Read the value of a single attribute, performing de-escaping as needed.
*
+ * delim is the column delimiter string (must be just one byte for now).
+ * null_print is the null marker string. Note that this is compared to
+ * the pre-de-escaped input string.
+ *
* *result is set to indicate what terminated the read:
* NORMAL_ATTR: column delimiter
* END_OF_LINE: end of line
* In either case, the string read up to the terminator is returned.
*
- * Note: This function does not care about SQL NULL values -- it
- * is the caller's responsibility to check if the returned string
- * matches what the user specified for the SQL NULL value.
- *
- * delim is the column delimiter string.
+ * *isnull is set true or false depending on whether the input matched
+ * the null marker. Note that the caller cannot check this since the
+ * returned string will be the post-de-escaping equivalent, which may
+ * look the same as some valid data string.
+ *----------
*/
static char *
-CopyReadAttribute(const char *delim, CopyReadResult *result)
+CopyReadAttribute(const char *delim, const char *null_print,
+ CopyReadResult *result, bool *isnull)
{
char c;
char delimc = delim[0];
+ int start_cursor = line_buf.cursor;
+ int end_cursor;
+ int input_len;
/* reset attribute_buf to empty */
attribute_buf.len = 0;
for (;;)
{
+ end_cursor = line_buf.cursor;
if (line_buf.cursor >= line_buf.len)
break;
c = line_buf.data[line_buf.cursor++];
c = val & 0377;
}
break;
-
- /*
- * This is a special hack to parse `\N' as
- * rather then just 'N' to provide
- * compatibility with the default NULL output. -- pe
- */
- case 'N':
- appendStringInfoCharMacro(&attribute_buf, '\\');
- c = 'N';
- break;
case 'b':
c = '\b';
break;
appendStringInfoCharMacro(&attribute_buf, c);
}
+ /* check whether raw input matched null marker */
+ input_len = end_cursor - start_cursor;
+ if (input_len == strlen(null_print) &&
+ strncmp(&line_buf.data[start_cursor], null_print, input_len) == 0)
+ *isnull = true;
+ else
+ *isnull = false;
+
return attribute_buf.data;
}
projects / postgresql.git / commitdiff