Fix parsing of ignored operators in websearch_to_tsquery().

The manual says clearly that punctuation in the input of
websearch_to_tsquery() is ignored, except for the special cases
of dashes and quotes.  However, this failed for cases like
"(foo bar) or something", or in general an ISOPERATOR character
in front of the "or".  We'd switch back to WAITOPERAND state,
then ignore the operator character while remaining in that state,
and then reach the "or" in WAITOPERAND state which (intentionally)
makes us treat it as data.

The fix is simple enough: if we see an ISOPERATOR character while in
WAITOPERATOR state, we have to skip it while staying in that state.
(We don't need to worry about other punctuation characters: those will
be consumed as though they were words, but then rejected by lexizing.)

In v14 and up (since commit eb086056f) we can simplify the code a bit
more too, because there is no longer a reason for the WAITOPERAND
state to distinguish between quoted and unquoted operands.

Per bug #18479 from Manos Emmanouilidis.  Back-patch to all supported
branches.

Discussion: https://postgr.es/m/18479-d9b46e2fc242c33e@postgresql.org

diff --git a/src/backend/utils/adt/tsquery.c b/src/backend/utils/adt/tsquery.c
index f54f2988149f5d0fd5dc184255ea52e75c259daf..2bb3d0fc3f399118af8a0626e23a58a237847cce 100644 (file)
--- a/src/backend/utils/adt/tsquery.c
+++ b/src/backend/utils/adt/tsquery.c
@@ -420,7 +420,7 @@ gettoken_query_websearch(TSQueryParserState state, int8 *operator,
                                }
                                else if (ISOPERATOR(state->buf))
                                {
-                                       /* or else gettoken_tsvector() will raise an error */
+                                       /* ignore, else gettoken_tsvector() will raise an error */
                                        state->buf++;
                                        state->state = WAITOPERAND;
                                        continue;
@@ -452,15 +452,9 @@ gettoken_query_websearch(TSQueryParserState state, int8 *operator,
                                break;
 
                        case WAITOPERATOR:
-                               if (t_iseq(state->buf, '"'))
+                               if (*state->buf == '\0')
                                {
-                                       /*
-                                        * put implicit AND after an operand and handle this quote
-                                        * in WAITOPERAND
-                                        */
-                                       state->state = WAITOPERAND;
-                                       *operator = OP_AND;
-                                       return PT_OPR;
+                                       return PT_END;
                                }
                                else if (parse_or_operator(state))
                                {
@@ -468,15 +462,17 @@ gettoken_query_websearch(TSQueryParserState state, int8 *operator,
                                        *operator = OP_OR;
                                        return PT_OPR;
                                }
-                               else if (*state->buf == '\0')
+                               else if (ISOPERATOR(state->buf))
                                {
-                                       return PT_END;
+                                       /* ignore other operators in this state too */
+                                       state->buf++;
+                                       continue;
                                }
                                else if (!t_isspace(state->buf))
                                {
-                                       /* put implicit AND after an operand */
-                                       *operator = OP_AND;
+                                       /* insert implicit AND between operands */
                                        state->state = WAITOPERAND;
+                                       *operator = OP_AND;
                                        return PT_OPR;
                                }
                                break;

diff --git a/src/test/regress/expected/tsearch.out b/src/test/regress/expected/tsearch.out
index 85113703389fb7506ac247b75cee05403f08b405..5d3d9d6250be2904800b23e7a0f8cca07c0aba65 100644 (file)
--- a/src/test/regress/expected/tsearch.out
+++ b/src/test/regress/expected/tsearch.out
@@ -2549,12 +2549,19 @@ select websearch_to_tsquery('simple', 'abc <-> def');
  'abc' & 'def'
 (1 row)
 
+-- parens are ignored, too
 select websearch_to_tsquery('simple', 'abc (pg or class)');
   websearch_to_tsquery  
 ------------------------
  'abc' & 'pg' | 'class'
 (1 row)
 
+select websearch_to_tsquery('simple', '(foo bar) or (ding dong)');
+      websearch_to_tsquery       
+---------------------------------
+ 'foo' & 'bar' | 'ding' & 'dong'
+(1 row)
+
 -- NOT is ignored in quotes
 select websearch_to_tsquery('english', 'My brand new smartphone');
      websearch_to_tsquery      

diff --git a/src/test/regress/sql/tsearch.sql b/src/test/regress/sql/tsearch.sql
index ca5226128ca345532a092cf08a48efc68ef378c9..c931f1a06f3a0caf688c6ca4a4d2724502e53edc 100644 (file)
--- a/src/test/regress/sql/tsearch.sql
+++ b/src/test/regress/sql/tsearch.sql
@@ -741,7 +741,10 @@ select websearch_to_tsquery('simple', ':');
 select websearch_to_tsquery('simple', 'abc & def');
 select websearch_to_tsquery('simple', 'abc | def');
 select websearch_to_tsquery('simple', 'abc <-> def');
+
+-- parens are ignored, too
 select websearch_to_tsquery('simple', 'abc (pg or class)');
+select websearch_to_tsquery('simple', '(foo bar) or (ding dong)');
 
 -- NOT is ignored in quotes
 select websearch_to_tsquery('english', 'My brand new smartphone');