Andrew Dunstan wrote:
Tom Lane wrote:
Andrew Dunstan <[EMAIL PROTECTED]> writes:
I've just been looking at the state machine in wparser_def.c. I
think the processing for entities is also a few bob short in the
pound. It recognises decimal numeric character references, but nor
hexadecimal numeric character references. That's fairly silly since
the HTML spec specifically says the latter are "particularly
useful". The rules for named entities are also deficient w.r.t.
digits, just like the case of tags that Tom noticed. This isn't
academic: HTML features a number of named entities with digits in
the name (sup2, frac14 for example).
In XML at least, legal names are defined by the following rules from
the spec:
...
[A-Za-z:_][A-Za-z0-9:_.-]*
I suggest we use that or something very close to it as the rule for
names in these patterns.
No objections here. Who wants to patch wparser_def?
I can get to it some time in the next week. - rather snowed under
right now.
BTW, I'm also suspicious of the clause that allows <?xml ... it
appears that it will allow <?xfoo and <?XFOO also, which seems quite
odd, especially the latter.
Here's a patch that fixes the patterns for numeric entities, tag names,
and removes the upper case 'X' case in the special case for an XML
prolog. There are still some oddities, but I decided against making
heroic efforts to fix them. It's probably less important if the patterns
are slightly too liberal (e.g. accepting <a href="qwe<qwe>"> ) than if
they don't recognize what they are alleged to recognize.
cheers
andrew
Index: doc/src/sgml/textsearch.sgml
===================================================================
RCS file: /cvsroot/pgsql/doc/src/sgml/textsearch.sgml,v
retrieving revision 1.36
diff -c -r1.36 textsearch.sgml
*** doc/src/sgml/textsearch.sgml 16 Nov 2007 03:23:07 -0000 1.36
--- doc/src/sgml/textsearch.sgml 19 Nov 2007 13:22:11 -0000
***************
*** 1862,1873 ****
</row>
<row>
<entry><literal>tag</></entry>
! <entry>HTML tag</entry>
<entry><literal><A HREF="dictionaries.html"></literal></entry>
</row>
<row>
<entry><literal>entity</></entry>
! <entry>HTML entity</entry>
<entry><literal>&amp;</literal></entry>
</row>
<row>
--- 1862,1873 ----
</row>
<row>
<entry><literal>tag</></entry>
! <entry>HTML-type tag</entry>
<entry><literal><A HREF="dictionaries.html"></literal></entry>
</row>
<row>
<entry><literal>entity</></entry>
! <entry>HTML-type entity</entry>
<entry><literal>&amp;</literal></entry>
</row>
<row>
Index: src/backend/tsearch/wparser_def.c
===================================================================
RCS file: /cvsroot/pgsql/src/backend/tsearch/wparser_def.c,v
retrieving revision 1.10
diff -c -r1.10 wparser_def.c
*** src/backend/tsearch/wparser_def.c 15 Nov 2007 22:25:16 -0000 1.10
--- src/backend/tsearch/wparser_def.c 19 Nov 2007 13:22:11 -0000
***************
*** 95,101 ****
"Hyphenated word part, all letters",
"Hyphenated word part, all ASCII",
"Space symbols",
! "HTML tag",
"Protocol head",
"Hyphenated word, letters and digits",
"Hyphenated word, all ASCII",
--- 95,101 ----
"Hyphenated word part, all letters",
"Hyphenated word part, all ASCII",
"Space symbols",
! "HTML-type tag",
"Protocol head",
"Hyphenated word, letters and digits",
"Hyphenated word, all ASCII",
***************
*** 105,111 ****
"Decimal notation",
"Signed integer",
"Unsigned integer",
! "HTML entity"
};
--- 105,111 ----
"Decimal notation",
"Signed integer",
"Unsigned integer",
! "HTML-type entity"
};
***************
*** 136,141 ****
--- 136,143 ----
TPS_InHTMLEntity,
TPS_InHTMLEntityNumFirst,
TPS_InHTMLEntityNum,
+ TPS_InHTMLEntityHexNumFirst,
+ TPS_InHTMLEntityHexNum,
TPS_InHTMLEntityEnd,
TPS_InTagFirst,
TPS_InXMLBegin,
***************
*** 815,836 ****
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
{p_iseqC, '#', A_NEXT, TPS_InHTMLEntityNumFirst, 0, NULL},
{p_isasclet, 0, A_NEXT, TPS_InHTMLEntity, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
static const TParserStateActionItem actionTPS_InHTMLEntity[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
! {p_isasclet, 0, A_NEXT, TPS_InHTMLEntity, 0, NULL},
{p_iseqC, ';', A_NEXT, TPS_InHTMLEntityEnd, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
static const TParserStateActionItem actionTPS_InHTMLEntityNumFirst[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InHTMLEntityNum, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
static const TParserStateActionItem actionTPS_InHTMLEntityNum[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InHTMLEntityNum, 0, NULL},
--- 817,852 ----
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
{p_iseqC, '#', A_NEXT, TPS_InHTMLEntityNumFirst, 0, NULL},
{p_isasclet, 0, A_NEXT, TPS_InHTMLEntity, 0, NULL},
+ {p_iseqC, ':', A_NEXT, TPS_InHTMLEntity, 0, NULL},
+ {p_iseqC, '_', A_NEXT, TPS_InHTMLEntity, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
static const TParserStateActionItem actionTPS_InHTMLEntity[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
! {p_isalnum, 0, A_NEXT, TPS_InHTMLEntity, 0, NULL},
! {p_iseqC, ':', A_NEXT, TPS_InHTMLEntity, 0, NULL},
! {p_iseqC, '_', A_NEXT, TPS_InHTMLEntity, 0, NULL},
! {p_iseqC, ':', A_NEXT, TPS_InHTMLEntity, 0, NULL},
! {p_iseqC, '.', A_NEXT, TPS_InHTMLEntity, 0, NULL},
! {p_iseqC, '-', A_NEXT, TPS_InHTMLEntity, 0, NULL},
{p_iseqC, ';', A_NEXT, TPS_InHTMLEntityEnd, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
static const TParserStateActionItem actionTPS_InHTMLEntityNumFirst[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
+ {p_iseqC, 'x', A_NEXT, TPS_InHTMLEntityHexNumFirst, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InHTMLEntityNum, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
+ static const TParserStateActionItem actionTPS_InHTMLEntityHexNumFirst[] = {
+ {p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
+ {p_isxdigit, 0, A_NEXT, TPS_InHTMLEntityHexNum, 0, NULL},
+ {NULL, 0, A_POP, TPS_Null, 0, NULL}
+ };
+
static const TParserStateActionItem actionTPS_InHTMLEntityNum[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
{p_isdigit, 0, A_NEXT, TPS_InHTMLEntityNum, 0, NULL},
***************
*** 838,843 ****
--- 854,866 ----
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
+ static const TParserStateActionItem actionTPS_InHTMLEntityHexNum[] = {
+ {p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
+ {p_isxdigit, 0, A_NEXT, TPS_InHTMLEntityHexNum, 0, NULL},
+ {p_iseqC, ';', A_NEXT, TPS_InHTMLEntityEnd, 0, NULL},
+ {NULL, 0, A_POP, TPS_Null, 0, NULL}
+ };
+
static const TParserStateActionItem actionTPS_InHTMLEntityEnd[] = {
{NULL, 0, A_BINGO | A_CLEAR, TPS_Base, HTMLENTITY, NULL}
};
***************
*** 854,861 ****
static const TParserStateActionItem actionTPS_InXMLBegin[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
/* <?xml ... */
{p_iseqC, 'x', A_NEXT, TPS_InTag, 0, NULL},
- {p_iseqC, 'X', A_NEXT, TPS_InTag, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
--- 877,884 ----
static const TParserStateActionItem actionTPS_InXMLBegin[] = {
{p_isEOF, 0, A_POP, TPS_Null, 0, NULL},
/* <?xml ... */
+ /* XXX do we wants states for the m and l ? Right now this accepts <?xZ */
{p_iseqC, 'x', A_NEXT, TPS_InTag, 0, NULL},
{NULL, 0, A_POP, TPS_Null, 0, NULL}
};
***************
*** 1282,1287 ****
--- 1305,1312 ----
TPARSERSTATEACTION(TPS_InHTMLEntity),
TPARSERSTATEACTION(TPS_InHTMLEntityNumFirst),
TPARSERSTATEACTION(TPS_InHTMLEntityNum),
+ TPARSERSTATEACTION(TPS_InHTMLEntityHexNumFirst),
+ TPARSERSTATEACTION(TPS_InHTMLEntityHexNum),
TPARSERSTATEACTION(TPS_InHTMLEntityEnd),
TPARSERSTATEACTION(TPS_InTagFirst),
TPARSERSTATEACTION(TPS_InXMLBegin),
Index: src/test/regress/expected/tsearch.out
===================================================================
RCS file: /cvsroot/pgsql/src/test/regress/expected/tsearch.out,v
retrieving revision 1.8
diff -c -r1.8 tsearch.out
*** src/test/regress/expected/tsearch.out 27 Oct 2007 19:03:45 -0000 1.8
--- src/test/regress/expected/tsearch.out 19 Nov 2007 13:22:12 -0000
***************
*** 222,228 ****
10 | hword_part | Hyphenated word part, all letters
11 | hword_asciipart | Hyphenated word part, all ASCII
12 | blank | Space symbols
! 13 | tag | HTML tag
14 | protocol | Protocol head
15 | numhword | Hyphenated word, letters and digits
16 | asciihword | Hyphenated word, all ASCII
--- 222,228 ----
10 | hword_part | Hyphenated word part, all letters
11 | hword_asciipart | Hyphenated word part, all ASCII
12 | blank | Space symbols
! 13 | tag | HTML-type tag
14 | protocol | Protocol head
15 | numhword | Hyphenated word, letters and digits
16 | asciihword | Hyphenated word, all ASCII
***************
*** 232,238 ****
20 | float | Decimal notation
21 | int | Signed integer
22 | uint | Unsigned integer
! 23 | entity | HTML entity
(23 rows)
SELECT * FROM ts_parse('default', '345 [EMAIL PROTECTED] '' http://www.com/ http://aew.werc.ewr/?ad=qwe&dw 1aew.werc.ewr/?ad=qwe&dw 2aew.werc.ewr http://3aew.werc.ewr/?ad=qwe&dw http://4aew.werc.ewr http://5aew.werc.ewr:8100/? ad=qwe&dw 6aew.werc.ewr:8100/?ad=qwe&dw 7aew.werc.ewr:8100/?ad=qwe&dw=%20%32 +4.0e-10 qwe qwe qwqwe 234.435 455 5.005 [EMAIL PROTECTED] qwe-wer asdf <fr>qwer jf sdjk<we hjwer <werrwe> ewr1> ewri2 <a href="qwe<qwe>">
--- 232,238 ----
20 | float | Decimal notation
21 | int | Signed integer
22 | uint | Unsigned integer
! 23 | entity | HTML-type entity
(23 rows)
SELECT * FROM ts_parse('default', '345 [EMAIL PROTECTED] '' http://www.com/ http://aew.werc.ewr/?ad=qwe&dw 1aew.werc.ewr/?ad=qwe&dw 2aew.werc.ewr http://3aew.werc.ewr/?ad=qwe&dw http://4aew.werc.ewr http://5aew.werc.ewr:8100/? ad=qwe&dw 6aew.werc.ewr:8100/?ad=qwe&dw 7aew.werc.ewr:8100/?ad=qwe&dw=%20%32 +4.0e-10 qwe qwe qwqwe 234.435 455 5.005 [EMAIL PROTECTED] qwe-wer asdf <fr>qwer jf sdjk<we hjwer <werrwe> ewr1> ewri2 <a href="qwe<qwe>">
---------------------------(end of broadcast)---------------------------
TIP 6: explain analyze is your friend
