This commit comes as a continuation of the discussion that has led to
d522b05, as \v was handled inconsistently when parsing array values or
anything going through the parsers, and changing a parser behavior in
stable branches is a scary thing to do. The parsing of array values now
uses the more central scanner_isspace() and array_isspace() is removed.
As pointing out by Peter Eisentraut, fix a confusing reference to
horizontal space in the parsers with the term "horiz_space". \f was
included in this set since
3cfdd8f from 2000, but it is not horizontal.
"horiz_space" is renamed to "non_newline_space", to refer to all
whitespace characters except newlines.
The changes impact the parsers for the backend, psql, seg, cube, ecpg
and replication commands. Note that JSON should not escape \v, as per
RFC 7159, so these are not touched.
Reviewed-by: Peter Eisentraut, Tom Lane
Discussion: https://postgr.es/m/ZJKcjNwWHHvw9ksQ@paquier.xyz
\( cube_yylval = "("; return O_PAREN;
\) cube_yylval = ")"; return C_PAREN;
\, cube_yylval = ","; return COMMA;
-[ \t\n\r\f]+ /* discard spaces */
+[ \t\n\r\f\v]+ /* discard spaces */
. return yytext[0]; /* alert parser of the garbage */
%%
"keyąfoo"=>"valueą"
(1 row)
+-- More patterns that may depend on isspace() and locales, all discarded.
+SELECT E'key\u000A=>value\u000A'::hstore; -- \n
+ hstore
+----------------
+ "key"=>"value"
+(1 row)
+
+SELECT E'key\u0009=>value\u0009'::hstore; -- \t
+ hstore
+----------------
+ "key"=>"value"
+(1 row)
+
+SELECT E'key\u000D=>value\u000D'::hstore; -- \r
+ hstore
+----------------
+ "key"=>"value"
+(1 row)
+
+SELECT E'key\u000B=>value\u000B'::hstore; -- \v
+ hstore
+----------------
+ "key"=>"value"
+(1 row)
+
+SELECT E'key\u000C=>value\u000C'::hstore; -- \f
+ hstore
+----------------
+ "key"=>"value"
+(1 row)
+
SELECT 'keyą=>valueą'::hstore;
SELECT 'ą=>ą'::hstore;
SELECT 'keyąfoo=>valueą'::hstore;
+
+-- More patterns that may depend on isspace() and locales, all discarded.
+SELECT E'key\u000A=>value\u000A'::hstore; -- \n
+SELECT E'key\u0009=>value\u0009'::hstore; -- \t
+SELECT E'key\u000D=>value\u000D'::hstore; -- \r
+SELECT E'key\u000B=>value\u000B'::hstore; -- \v
+SELECT E'key\u000C=>value\u000C'::hstore; -- \f
\< seg_yylval.text = "<"; return EXTENSION;
\> seg_yylval.text = ">"; return EXTENSION;
\~ seg_yylval.text = "~"; return EXTENSION;
-[ \t\n\r\f]+ /* discard spaces */
+[ \t\n\r\f\v]+ /* discard spaces */
. return yytext[0]; /* alert parser of the garbage */
%%
ErrorContextCallback ptserrcontext;
/* make sure we give useful error for empty input */
- if (strspn(str, " \t\n\r\f") == strlen(str))
+ if (strspn(str, " \t\n\r\f\v") == strlen(str))
goto fail;
/*
* versions of Postgres failed to recognize -- as a comment if the input
* did not end with a newline.
*
- * XXX perhaps \f (formfeed) should be treated as a newline as well?
+ * non_newline_space tracks all the other space characters except newlines.
*
* XXX if you change the set of whitespace characters, fix scanner_isspace()
* to agree.
*/
-space [ \t\n\r\f]
-horiz_space [ \t\f]
-newline [\n\r]
-non_newline [^\n\r]
+space [ \t\n\r\f\v]
+non_newline_space [ \t\f\v]
+newline [\n\r]
+non_newline [^\n\r]
comment ("--"{non_newline}*)
*/
special_whitespace ({space}+|{comment}{newline})
-horiz_whitespace ({horiz_space}|{comment})
-whitespace_with_newline ({horiz_whitespace}*{newline}{special_whitespace}*)
+non_newline_whitespace ({non_newline_space}|{comment})
+whitespace_with_newline ({non_newline_whitespace}*{newline}{special_whitespace}*)
quote '
/* If we see {quote} then {quotecontinue}, the quoted string continues */
return '\r';
case 't':
return '\t';
+ case 'v':
+ return '\v';
default:
/* check for backslash followed by non-7-bit-ASCII */
if (c == '\0' || IS_HIGHBIT_SET(c))
ch == '\t' ||
ch == '\n' ||
ch == '\r' ||
+ ch == '\v' ||
ch == '\f')
return true;
return false;
%x xd
%x xq
-space [ \t\n\r\f]
+space [ \t\n\r\f\v]
quote '
quotestop {quote}
#include "nodes/nodeFuncs.h"
#include "nodes/supportnodes.h"
#include "optimizer/optimizer.h"
+#include "parser/scansup.h"
#include "port/pg_bitutils.h"
#include "utils/array.h"
#include "utils/arrayaccess.h"
int current_item; /* the item # we're at in the array */
} ArrayIteratorData;
-static bool array_isspace(char ch);
static int ArrayCount(const char *str, int *dim, char typdelim,
Node *escontext);
static bool ReadArrayStr(char *arrayStr, const char *origStr,
* Note: we currently allow whitespace between, but not within,
* dimension items.
*/
- while (array_isspace(*p))
+ while (scanner_isspace(*p))
p++;
if (*p != '[')
break; /* no more dimension items */
errdetail("Missing \"%s\" after array dimensions.",
ASSGN)));
p += strlen(ASSGN);
- while (array_isspace(*p))
+ while (scanner_isspace(*p))
p++;
/*
PG_RETURN_ARRAYTYPE_P(retval);
}
-/*
- * array_isspace() --- a non-locale-dependent isspace()
- *
- * We used to use isspace() for parsing array values, but that has
- * undesirable results: an array value might be silently interpreted
- * differently depending on the locale setting. Now we just hard-wire
- * the traditional ASCII definition of isspace().
- */
-static bool
-array_isspace(char ch)
-{
- if (ch == ' ' ||
- ch == '\t' ||
- ch == '\n' ||
- ch == '\r' ||
- ch == '\v' ||
- ch == '\f')
- return true;
- return false;
-}
-
/*
* ArrayCount
* Determines the dimensions for an array string.
itemdone = true;
nelems[nest_level - 1]++;
}
- else if (!array_isspace(*ptr))
+ else if (!scanner_isspace(*ptr))
{
/*
* Other non-space characters must be after a
/* only whitespace is allowed after the closing brace */
while (*ptr)
{
- if (!array_isspace(*ptr++))
+ if (!scanner_isspace(*ptr++))
ereturn(escontext, -1,
(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
errmsg("malformed array literal: \"%s\"", str),
indx[ndim - 1]++;
srcptr++;
}
- else if (array_isspace(*srcptr))
+ else if (scanner_isspace(*srcptr))
{
/*
* If leading space, drop it immediately. Else, copy
overall_length += 1;
}
else if (ch == '{' || ch == '}' || ch == typdelim ||
- array_isspace(ch))
+ scanner_isspace(ch))
needquote = true;
}
}
/*
* Assorted character class definitions that should match psqlscan.l.
*/
-space [ \t\n\r\f]
+space [ \t\n\r\f\v]
quote '
xeoctesc [\\][0-7]{1,3}
xehexesc [\\]x[0-9A-Fa-f]{1,2}
* versions of Postgres failed to recognize -- as a comment if the input
* did not end with a newline.
*
- * XXX perhaps \f (formfeed) should be treated as a newline as well?
+ * non_newline_space tracks all space characters except newlines.
*
* XXX if you change the set of whitespace characters, fix scanner_isspace()
* to agree.
*/
-space [ \t\n\r\f]
-horiz_space [ \t\f]
-newline [\n\r]
-non_newline [^\n\r]
+space [ \t\n\r\f\v]
+non_newline_space [ \t\f\v]
+newline [\n\r]
+non_newline [^\n\r]
comment ("--"{non_newline}*)
*/
special_whitespace ({space}+|{comment}{newline})
-horiz_whitespace ({horiz_space}|{comment})
-whitespace_with_newline ({horiz_whitespace}*{newline}{special_whitespace}*)
+non_newline_whitespace ({non_newline_space}|{comment})
+whitespace_with_newline ({non_newline_whitespace}*{newline}{special_whitespace}*)
quote '
/* If we see {quote} then {quotecontinue}, the quoted string continues */
if (ch == '"' || ch == '\\' ||
ch == '{' || ch == '}' || ch == ',' ||
- /* these match array_isspace(): */
+ /* these match scanner_isspace(): */
ch == ' ' || ch == '\t' || ch == '\n' ||
ch == '\r' || ch == '\v' || ch == '\f')
{
* versions of Postgres failed to recognize -- as a comment if the input
* did not end with a newline.
*
- * XXX perhaps \f (formfeed) should be treated as a newline as well?
+ * non_newline_space tracks all space characters except newlines.
*
* XXX if you change the set of whitespace characters, fix ecpg_isspace()
* to agree.
*/
-space [ \t\n\r\f]
-horiz_space [ \t\f]
-newline [\n\r]
-non_newline [^\n\r]
+space [ \t\n\r\f\v]
+non_newline_space [ \t\f\v]
+newline [\n\r]
+non_newline [^\n\r]
comment ("--"{non_newline}*)
* it, whereas {whitespace} should generally have a * after it...
*/
-horiz_whitespace ({horiz_space}|{comment})
-whitespace_with_newline ({horiz_whitespace}*{newline}{whitespace}*)
+non_newline_whitespace ({non_newline_space}|{comment})
+whitespace_with_newline ({non_newline_whitespace}*{newline}{whitespace}*)
quote '
/* If we see {quote} then {quotecontinue}, the quoted string continues */
ch == '\t' ||
ch == '\n' ||
ch == '\r' ||
- ch == '\f')
+ ch == '\f' ||
+ ch == '\v')
return true;
return false;
}
projects / users / rhaas / postgres.git / commitdiff