mirrors/postgres
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Change regex \D and \W shorthands to always match newlines.

Browse Source 
Newline is certainly not a digit, nor a word character, so it is
sensible that it should match these complemented character classes.
Previously, \D and \W acted that way by default, but in
newline-sensitive mode ('n' or 'p' flag) they did not match newlines.

This behavior was previously forced because explicit complemented
character classes don't match newlines in newline-sensitive mode;
but as of the previous commit that implementation constraint no
longer exists.  It seems useful to change this because the primary
real-world use for newline-sensitive mode seems to be to match the
default behavior of other regex engines such as Perl and Javascript
... and their default behavior is that these match newlines.

The old behavior can be kept by writing an explicit complemented
character class, i.e. [^[:digit:]] or [^[:word:]].  (This means
that \D and \W are not exactly equivalent to those strings, but
they weren't anyway.)

Discussion: https://postgr.es/m/3220564.1613859619@sss.pgh.pa.us
This commit is contained in:
Tom Lane 2021-02-25 13:29:06 -05:00
parent 2a0af7fe46
commit 7dc13a0f08
4 changed files with 36 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
doc/src/sgml/func.sgml
View File

@ -6323,32 +6323,38 @@ SELECT foo FROM regexp_split_to_table('the quick brown fox', '\s*') AS foo;
<tbody>
<row>
<entry> <literal>\d</literal> </entry>
<entry> <literal>[[:digit:]]</literal> </entry>
<entry> matches any digit, like
<literal>[[:digit:]]</literal> </entry>
</row>
<row>
<entry> <literal>\s</literal> </entry>
<entry> <literal>[[:space:]]</literal> </entry>
<entry> matches any whitespace character, like
<literal>[[:space:]]</literal> </entry>
</row>
<row>
<entry> <literal>\w</literal> </entry>
<entry> <literal>[[:word:]]</literal> </entry>
<entry> matches any word character, like
<literal>[[:word:]]</literal> </entry>
</row>
<row>
<entry> <literal>\D</literal> </entry>
<entry> <literal>[^[:digit:]]</literal> </entry>
<entry> matches any non-digit, like
<literal>[^[:digit:]]</literal> </entry>
</row>
<row>
<entry> <literal>\S</literal> </entry>
<entry> <literal>[^[:space:]]</literal> </entry>
<entry> matches any non-whitespace character, like
<literal>[^[:space:]]</literal> </entry>
</row>
<row>
<entry> <literal>\W</literal> </entry>
<entry> <literal>[^[:word:]]</literal> </entry>
<entry> matches any non-word character, like
<literal>[^[:word:]]</literal> </entry>
</row>
</tbody>
</tgroup>
@ -6813,14 +6819,20 @@ SELECT regexp_match('abc01234xyz', '(?:(.*?)(\d+)(.*)){1,1}');
If newline-sensitive matching is specified, <literal>.</literal>
and bracket expressions using <literal>^</literal>
will never match the newline character
(so that matches will never cross newlines unless the RE
explicitly arranges it)
(so that matches will not cross lines unless the RE
explicitly includes a newline)
and <literal>^</literal> and <literal>$</literal>
will match the empty string after and before a newline
respectively, in addition to matching at beginning and end of string
respectively.
But the ARE escapes <literal>\A</literal> and <literal>\Z</literal>
continue to match beginning or end of string <emphasis>only</emphasis>.
Also, the character class shorthands <literal>\D</literal>
and <literal>\W</literal> will match a newline regardless of this mode.
(Before <productname>PostgreSQL</productname> 14, they did not match
newlines when in newline-sensitive mode.
Write <literal>[^[:digit:]]</literal>
or <literal>[^[:word:]]</literal> to get the old behavior.)
</para>
<para>

7
src/backend/regex/re_syntax.n
View File

@ -804,7 +804,7 @@ and bracket expressions using
\fB^\fR
will never match the newline character
(so that matches will never cross newlines unless the RE
explicitly arranges it)
explicitly includes a newline)
and
\fB^\fR
and
@ -817,6 +817,11 @@ ARE
and
\fB\eZ\fR
continue to match beginning or end of string \fIonly\fR.
Also, the character class shorthands
\fB\eD\fR
and
\fB\eW\fR
will match a newline regardless of this mode.
.PP
If partial newline-sensitive matching is specified,
this affects \fB.\fR

6
src/backend/regex/regcomp.c
View File

@ -1407,10 +1407,6 @@ charclasscomplement(struct vars *v,
/* build arcs for char class; this may cause color splitting */
subcolorcvec(v, cv, cstate, cstate);
/* in NLSTOP mode, ensure newline is not part of the result set */
if (v->cflags & REG_NLSTOP)
newarc(v->nfa, PLAIN, v->nlcolor, cstate, cstate);
NOERR();
/* clean up any subcolors in the arc set */
@ -1612,6 +1608,8 @@ cbracket(struct vars *v,
NOERR();
bracket(v, left, right);
/* in NLSTOP mode, ensure newline is not part of the result set */
if (v->cflags & REG_NLSTOP)
newarc(v->nfa, PLAIN, v->nlcolor, left, right);
NOERR();

12
src/test/modules/test_regex/expected/test_regex.out
View File

@ -2144,7 +2144,8 @@ select * from test_regex('\D+', E'abc\ndef345', 'nLP');
test_regex
-------------------------------
{0,REG_UNONPOSIX,REG_ULOCALE}
{abc}
{"abc +
def"}
(2 rows)
select * from test_regex('[\D]+', E'abc\ndef345', 'LPE');
@ -2159,7 +2160,8 @@ select * from test_regex('[\D]+', E'abc\ndef345', 'nLPE');
test_regex
----------------------------------------
{0,REG_UBBS,REG_UNONPOSIX,REG_ULOCALE}
{abc}
{"abc +
def"}
(2 rows)
select * from test_regex('\w+', E'abc_012\ndef', 'LP');
@ -2202,7 +2204,8 @@ select * from test_regex('\W+', E'***\n@@@___', 'nLP');
test_regex
-------------------------------
{0,REG_UNONPOSIX,REG_ULOCALE}
{***}
{"*** +
@@@"}
(2 rows)
select * from test_regex('[\W]+', E'***\n@@@___', 'LPE');
@ -2217,7 +2220,8 @@ select * from test_regex('[\W]+', E'***\n@@@___', 'nLPE');
test_regex
----------------------------------------
{0,REG_UBBS,REG_UNONPOSIX,REG_ULOCALE}
{***}
{"*** +
@@@"}
(2 rows)
-- doing 13 "escapes"