database/postgres
database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-06-05 23:56:58 +03:00
Code

Our code had:

Browse Source 
if (c == '\\' && cstate->line_buf.len == 0)

The problem with that is the because of the input and _output_
buffering, cstate->line_buf.len could be zero even if we are not on the
first character of a line.  In fact, for a typical line, it is zero for
all characters on the line.  The proper solution is to introduce a
boolean, first_char_in_line, that we set as we enter the loop and clear
once we process a character.

I have restructured the line-reading code in copy.c by:

        o  merging the CSV/non-CSV functions into a single function
        o  used macros to centralize and clarify the buffering code
        o  updated comments
        o  renamed client_encoding_only to encoding_embeds_ascii
        o  added a high-bit test to the encoding_embeds_ascii test for
           performance
        o  in CSV mode, allow a backslash followed by a non-period to
           continue being processed as a data value

There should be no performance impact from this patch because it is
functionally equivalent.  If you apply the patch you will see copy.c is
much clearer in this area now and might suggest additional
optimizations.

I have also attached a 8.1-only patch to fix the CSV \. handling bug
with no code restructuring.
This commit is contained in:
Bruce Momjian 2005-12-27 18:10:57 +00:00
parent ab2d8c41ff
commit 3f99c2d5a7
1 changed files with 25 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
src/backend/commands/copy.c
View File

@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
* $PostgreSQL: pgsql/src/backend/commands/copy.c,v 1.254.2.1 2005/11/22 18:23:07 momjian Exp $
* $PostgreSQL: pgsql/src/backend/commands/copy.c,v 1.254.2.2 2005/12/27 18:10:57 momjian Exp $
*
*-------------------------------------------------------------------------
*/
@ -2338,6 +2338,7 @@ CopyReadLineCSV(CopyState cstate)
bool need_data;
bool hit_eof;
char s[2];
bool first_char_in_line = true;
bool in_quote = false,
last_was_esc = false;
char quotec = cstate->quote[0];
@ -2531,7 +2532,7 @@ CopyReadLineCSV(CopyState cstate)
/*
* In CSV mode, we only recognize \. at start of line
*/
if (c == '\\' && cstate->line_buf.len == 0)
if (c == '\\' && first_char_in_line)
{
char c2;
@ -2577,13 +2578,15 @@ CopyReadLineCSV(CopyState cstate)
/* if hit_eof, c2 will become '\0' */
c2 = copy_raw_buf[raw_buf_ptr++];
if (c2 == '\n')
ereport(ERROR,
(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
errmsg("end-of-copy marker does not match previous newline style")));
{
raw_buf_ptr = prev_raw_ptr + 1;
goto not_end_of_copy;
}
if (c2 != '\r')
ereport(ERROR,
(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
errmsg("end-of-copy marker corrupt")));
{
raw_buf_ptr = prev_raw_ptr + 1;
goto not_end_of_copy;
}
}
if (raw_buf_ptr >= copy_buf_len && !hit_eof)
{
@ -2594,16 +2597,16 @@ CopyReadLineCSV(CopyState cstate)
/* if hit_eof, c2 will become '\0' */
c2 = copy_raw_buf[raw_buf_ptr++];
if (c2 != '\r' && c2 != '\n')
ereport(ERROR,
(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
errmsg("end-of-copy marker corrupt")));
{
raw_buf_ptr = prev_raw_ptr + 1;
goto not_end_of_copy;
}
if ((cstate->eol_type == EOL_NL && c2 != '\n') ||
(cstate->eol_type == EOL_CRNL && c2 != '\n') ||
(cstate->eol_type == EOL_CR && c2 != '\r'))
ereport(ERROR,
(errcode(ERRCODE_BAD_COPY_FILE_FORMAT),
errmsg("end-of-copy marker does not match previous newline style")));
/*
* Transfer only the data before the \. into line_buf, then
* discard the data and the \. sequence.
@ -2618,11 +2621,15 @@ CopyReadLineCSV(CopyState cstate)
}
/*
* Do we need to be careful about trailing bytes of multibyte
* characters? (See note above about client_only_encoding)
*
* We assume here that pg_encoding_mblen only looks at the first byte
* of the character!
* This label is for CSV cases where \. appears at the start of a line,
* but there is more text after it, meaning it was a data value.
* We are more strict for \. in CSV mode because \. could be a data
* value, while in non-CSV mode, \. cannot be a data value.
*/
not_end_of_copy:
/*
* Process all bytes of a multi-byte character as a group.
*/
if (cstate->client_only_encoding)
{
@ -2645,6 +2652,7 @@ CopyReadLineCSV(CopyState cstate)
}
raw_buf_ptr += mblen - 1;
}
first_char_in_line = false;
} /* end of outer loop */
/*