Allow hyphens in ltree labels

Also increase the allowed length of labels to 1000 characters

Garen Torikian

Discussion: https://postgr.es/m/CAGXsc+-mNg9Gc0rp-ER0sv+zkZSZp2wE9-LX6XcoWSLVz22tZA@mail.gmail.com

diff --git a/contrib/ltree/expected/ltree.out b/contrib/ltree/expected/ltree.out
index b95be71c781b24d7f1a7641a394df58b4609282d..d2a53b9f0c15b79dc4860b87b6ba8e2a3fe3b45c 100644 (file)
--- a/contrib/ltree/expected/ltree.out
+++ b/contrib/ltree/expected/ltree.out
@@ -1,4 +1,6 @@
 CREATE EXTENSION ltree;
+-- max length for a label
+\set maxlbl 1000
 -- Check whether any of our opclasses fail amvalidate
 SELECT amname, opcname
 FROM pg_opclass opc LEFT JOIN pg_am am ON am.oid = opcmethod
@@ -25,6 +27,12 @@ SELECT '1.2'::ltree;
  1.2
 (1 row)
 
+SELECT '1.2.-3'::ltree;
+ ltree  
+--------
+ 1.2.-3
+(1 row)
+
 SELECT '1.2._3'::ltree;
  ltree  
 --------
@@ -45,15 +53,15 @@ ERROR:  ltree syntax error
 LINE 1: SELECT '1.2.'::ltree;
                ^
 DETAIL:  Unexpected end of input.
-SELECT repeat('x', 255)::ltree;
-                                                                                                                             repeat                                                                                                                              
------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
- xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+SELECT repeat('x', :maxlbl)::ltree;
+                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  repeat                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
 (1 row)
 
-SELECT repeat('x', 256)::ltree;
+SELECT repeat('x', :maxlbl + 1)::ltree;
 ERROR:  label string is too long
-DETAIL:  Label length is 256, must be at most 255, at character 257.
+DETAIL:  Label length is 1001, must be at most 1000, at character 1002.
 SELECT ltree2text('1.2.3.34.sdf');
   ltree2text  
 --------------
@@ -531,24 +539,24 @@ SELECT '1.2.3|@.4'::lquery;
 ERROR:  lquery syntax error at character 7
 LINE 1: SELECT '1.2.3|@.4'::lquery;
                ^
-SELECT (repeat('x', 255) || '*@@*')::lquery;
-                                                                                                                              lquery                                                                                                                               
--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
- xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx@*
+SELECT (repeat('x', :maxlbl) || '*@@*')::lquery;
+                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   lquery                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   
+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx@*
 (1 row)
 
-SELECT (repeat('x', 256) || '*@@*')::lquery;
+SELECT (repeat('x', :maxlbl + 1) || '*@@*')::lquery;
 ERROR:  label string is too long
-DETAIL:  Label length is 256, must be at most 255, at character 257.
-SELECT ('!' || repeat('x', 255))::lquery;
-                                                                                                                              lquery                                                                                                                              
-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
- !xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+DETAIL:  Label length is 1001, must be at most 1000, at character 1002.
+SELECT ('!' || repeat('x', :maxlbl))::lquery;
+                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  lquery                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ !xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
 (1 row)
 
-SELECT ('!' || repeat('x', 256))::lquery;
+SELECT ('!' || repeat('x', :maxlbl + 1))::lquery;
 ERROR:  label string is too long
-DETAIL:  Label length is 256, must be at most 255, at character 258.
+DETAIL:  Label length is 1001, must be at most 1000, at character 1003.
 SELECT nlevel('1.2.3.4');
  nlevel 
 --------
@@ -1195,6 +1203,12 @@ SELECT 'tree & aw_qw%*'::ltxtquery;
  tree & aw_qw%*
 (1 row)
 
+SELECT 'tree & aw-qw%*'::ltxtquery;
+   ltxtquery    
+----------------
+ tree & aw-qw%*
+(1 row)
+
 SELECT 'ltree.awdfg'::ltree @ '!tree & aWdf@*'::ltxtquery;
  ?column? 
 ----------

diff --git a/contrib/ltree/ltree.h b/contrib/ltree/ltree.h
index 2a80a02495ea4f1810c22c530aa0cd91b104aa20..5e0761641d32ac5db8e925a6c34d699eb21705ec 100644 (file)
--- a/contrib/ltree/ltree.h
+++ b/contrib/ltree/ltree.h
@@ -12,10 +12,10 @@
 
 /*
  * We want the maximum length of a label to be encoding-independent, so
- * set it somewhat arbitrarily at 255 characters (not bytes), while using
+ * set it somewhat arbitrarily at 1000 characters (not bytes), while using
  * uint16 fields to hold the byte length.
  */
-#define LTREE_LABEL_MAX_CHARS 255
+#define LTREE_LABEL_MAX_CHARS 1000
 
 /*
  * LOWER_NODE used to be defined in the Makefile via the compile flags.
@@ -126,7 +126,8 @@ typedef struct
 
 #define LQUERY_HASNOT      0x01
 
-#define ISALNUM(x) ( t_isalnum(x) || t_iseq(x, '_') )
+/* valid label chars are alphanumerics, underscores and hyphens */
+#define ISLABEL(x) ( t_isalnum(x) || t_iseq(x, '_') || t_iseq(x, '-') )
 
 /* full text query */
 

diff --git a/contrib/ltree/ltree_io.c b/contrib/ltree/ltree_io.c
index f0dd3df5115f414722116d5079d9583b77cc4a11..56533172e320eab83efc3425871c1399968247b4 100644 (file)
--- a/contrib/ltree/ltree_io.c
+++ b/contrib/ltree/ltree_io.c
@@ -74,7 +74,7 @@ parse_ltree(const char *buf, struct Node *escontext)
        switch (state)
        {
            case LTPRS_WAITNAME:
-               if (ISALNUM(ptr))
+               if (ISLABEL(ptr))
                {
                    lptr->start = ptr;
                    lptr->wlen = 0;
@@ -92,7 +92,7 @@ parse_ltree(const char *buf, struct Node *escontext)
                    lptr++;
                    state = LTPRS_WAITNAME;
                }
-               else if (!ISALNUM(ptr))
+               else if (!ISLABEL(ptr))
                    UNCHAR;
                break;
            default:
@@ -316,7 +316,7 @@ parse_lquery(const char *buf, struct Node *escontext)
        switch (state)
        {
            case LQPRS_WAITLEVEL:
-               if (ISALNUM(ptr))
+               if (ISLABEL(ptr))
                {
                    GETVAR(curqlevel) = lptr = (nodeitem *) palloc0(sizeof(nodeitem) * (numOR + 1));
                    lptr->start = ptr;
@@ -339,7 +339,7 @@ parse_lquery(const char *buf, struct Node *escontext)
                    UNCHAR;
                break;
            case LQPRS_WAITVAR:
-               if (ISALNUM(ptr))
+               if (ISLABEL(ptr))
                {
                    lptr++;
                    lptr->start = ptr;
@@ -385,7 +385,7 @@ parse_lquery(const char *buf, struct Node *escontext)
                    state = LQPRS_WAITLEVEL;
                    curqlevel = NEXTLEV(curqlevel);
                }
-               else if (ISALNUM(ptr))
+               else if (ISLABEL(ptr))
                {
                    /* disallow more chars after a flag */
                    if (lptr->flag)

diff --git a/contrib/ltree/ltxtquery_io.c b/contrib/ltree/ltxtquery_io.c
index a16e577303a54e7b61761d096895d5476d774cc5..c95f94df810e5f22f4c7577f4a9f0f5f4ab3b4d0 100644 (file)
--- a/contrib/ltree/ltxtquery_io.c
+++ b/contrib/ltree/ltxtquery_io.c
@@ -80,7 +80,7 @@ gettoken_query(QPRS_STATE *state, int32 *val, int32 *lenval, char **strval, uint
                    (state->buf)++;
                    return OPEN;
                }
-               else if (ISALNUM(state->buf))
+               else if (ISLABEL(state->buf))
                {
                    state->state = INOPERAND;
                    *strval = state->buf;
@@ -93,7 +93,7 @@ gettoken_query(QPRS_STATE *state, int32 *val, int32 *lenval, char **strval, uint
                             errmsg("operand syntax error")));
                break;
            case INOPERAND:
-               if (ISALNUM(state->buf))
+               if (ISLABEL(state->buf))
                {
                    if (*flag)
                        ereturn(state->escontext, ERR,

diff --git a/contrib/ltree/sql/ltree.sql b/contrib/ltree/sql/ltree.sql
index eabef4f851ce8c485ff203e11bdab6d1cdf6348e..4a6e6266c31b34a506d27d4de735079dd431009e 100644 (file)
--- a/contrib/ltree/sql/ltree.sql
+++ b/contrib/ltree/sql/ltree.sql
@@ -1,5 +1,8 @@
 CREATE EXTENSION ltree;
 
+-- max length for a label
+\set maxlbl 1000
+
 -- Check whether any of our opclasses fail amvalidate
 SELECT amname, opcname
 FROM pg_opclass opc LEFT JOIN pg_am am ON am.oid = opcmethod
@@ -8,6 +11,7 @@ WHERE opc.oid >= 16384 AND NOT amvalidate(opc.oid);
 SELECT ''::ltree;
 SELECT '1'::ltree;
 SELECT '1.2'::ltree;
+SELECT '1.2.-3'::ltree;
 SELECT '1.2._3'::ltree;
 
 -- empty labels not allowed
@@ -15,8 +19,8 @@ SELECT '.2.3'::ltree;
 SELECT '1..3'::ltree;
 SELECT '1.2.'::ltree;
 
-SELECT repeat('x', 255)::ltree;
-SELECT repeat('x', 256)::ltree;
+SELECT repeat('x', :maxlbl)::ltree;
+SELECT repeat('x', :maxlbl + 1)::ltree;
 
 SELECT ltree2text('1.2.3.34.sdf');
 SELECT text2ltree('1.2.3.34.sdf');
@@ -111,10 +115,10 @@ SELECT '1.!.3'::lquery;
 SELECT '1.2.!'::lquery;
 SELECT '1.2.3|@.4'::lquery;
 
-SELECT (repeat('x', 255) || '*@@*')::lquery;
-SELECT (repeat('x', 256) || '*@@*')::lquery;
-SELECT ('!' || repeat('x', 255))::lquery;
-SELECT ('!' || repeat('x', 256))::lquery;
+SELECT (repeat('x', :maxlbl) || '*@@*')::lquery;
+SELECT (repeat('x', :maxlbl + 1) || '*@@*')::lquery;
+SELECT ('!' || repeat('x', :maxlbl))::lquery;
+SELECT ('!' || repeat('x', :maxlbl + 1))::lquery;
 
 SELECT nlevel('1.2.3.4');
 SELECT nlevel(('1' || repeat('.1', 65534))::ltree);
@@ -233,6 +237,8 @@ SELECT 'QWER_GY'::ltree ~ 'q_t%@*';
 --ltxtquery
 SELECT '!tree & aWdf@*'::ltxtquery;
 SELECT 'tree & aw_qw%*'::ltxtquery;
+SELECT 'tree & aw-qw%*'::ltxtquery;
+
 SELECT 'ltree.awdfg'::ltree @ '!tree & aWdf@*'::ltxtquery;
 SELECT 'tree.awdfg'::ltree @ '!tree & aWdf@*'::ltxtquery;
 SELECT 'tree.awdfg'::ltree @ '!tree | aWdf@*'::ltxtquery;

diff --git a/doc/src/sgml/ltree.sgml b/doc/src/sgml/ltree.sgml
index 508f404ae8117be77fbd56ee98e880f73b8c00d1..edea1eadb8832e38523ad44e2aad670c81769845 100644 (file)
--- a/doc/src/sgml/ltree.sgml
+++ b/doc/src/sgml/ltree.sgml
@@ -23,10 +23,11 @@
   <title>Definitions</title>
 
   <para>
-   A <firstterm>label</firstterm> is a sequence of alphanumeric characters
-   and underscores (for example, in C locale the characters
-   <literal>A-Za-z0-9_</literal> are allowed).
-   Labels must be less than 256 characters long.
+   A <firstterm>label</firstterm> is a sequence of alphanumeric characters,
+   underscores, and hyphens. Valid alphanumeric character ranges are
+   dependent on the database locale. For example, in C locale, the characters
+   <literal>A-Za-z0-9_-</literal> are allowed.
+   Labels must be no more than 1000 characters long.
   </para>
 
   <para>