.gitignore

@@ -4,6 +4,7 @@
 results
 __pycache__
 *.pyc
+rum--*.sql
 tmp_install
 log
 

.travis.yml

@@ -1,4 +1,6 @@
-sudo: required
+os: linux
+
+dist: jammy
 
 language: c
 
@@ -21,13 +23,15 @@ notifications:
         on_failure: always
 
 env:
+    - PG_VERSION=17
+    - PG_VERSION=17 LEVEL=hardcore
+    - PG_VERSION=16
+    - PG_VERSION=16 LEVEL=hardcore
+    - PG_VERSION=15
+    - PG_VERSION=15 LEVEL=hardcore
     - PG_VERSION=14
     - PG_VERSION=14 LEVEL=hardcore
     - PG_VERSION=13
     - PG_VERSION=13 LEVEL=hardcore
     - PG_VERSION=12
     - PG_VERSION=12 LEVEL=hardcore
-    - PG_VERSION=11
-    - PG_VERSION=11 LEVEL=hardcore
-    - PG_VERSION=10
-    - PG_VERSION=10 LEVEL=hardcore

LICENSE

@@ -1,6 +1,6 @@
 RUM is released under the PostgreSQL License, a liberal Open Source license, similar to the BSD or MIT licenses.
 
-Portions Copyright (c) 2015-2019, Postgres Professional
+Portions Copyright (c) 2015-2024, Postgres Professional
 Portions Copyright (c) 1996-2017, PostgreSQL Global Development Group
 Portions Copyright (c) 1994, The Regents of the University of California
 

Makefile

@@ -11,14 +11,10 @@ OBJS = src/rumsort.o src/rum_ts_utils.o src/rumtsquery.o \
 	src/rumscan.o src/rumutil.o src/rumvacuum.o src/rumvalidate.o \
 	src/btree_rum.o src/rum_arr_utils.o $(WIN32RES)
 
-DATA_first = rum--1.0.sql
 DATA_updates = rum--1.0--1.1.sql rum--1.1--1.2.sql \
 			   rum--1.2--1.3.sql
 
-DATA = $(DATA_first) rum--$(EXTVERSION).sql $(DATA_updates)
-
-# Do not use DATA_built. It removes built files if clean target was used
-SQL_built = rum--$(EXTVERSION).sql $(DATA_updates)
+DATA_built = $(EXTENSION)--$(EXTVERSION).sql
 
 INCLUDES = rum.h rumsort.h
 RELATIVE_INCLUDES = $(addprefix src/, $(INCLUDES))
@@ -28,11 +24,26 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS = security rum rum_validate rum_hash ruminv timestamp orderby orderby_hash \
 	altorder altorder_hash limits \
 	int2 int4 int8 float4 float8 money oid \
-    time timetz date interval \
-    macaddr inet cidr text varchar char bytea bit varbit \
-	numeric rum_weight
+	time timetz date interval \
+	macaddr inet cidr text varchar char bytea bit varbit \
+	numeric rum_weight expr
+
+TAP_TESTS = 1
+
+ISOLATION = predicate-rum predicate-rum-2
+ISOLATION_OPTS = --load-extension=rum
+EXTRA_CLEAN = pglist_tmp
 
 ifdef USE_PGXS
+
+# We cannot run isolation test for versions 12,13 in PGXS case
+# because 'pg_isolation_regress' is not copied to install
+# directory, see src/test/isolation/Makefile
+ifeq ($(MAJORVERSION),$(filter 12% 13%,$(MAJORVERSION)))
+undefine ISOLATION
+undefine ISOLATION_OPTS
+endif
+
 PG_CONFIG = pg_config
 PGXS := $(shell $(PG_CONFIG) --pgxs)
 include $(PGXS)
@@ -43,26 +54,27 @@ include $(top_builddir)/src/Makefile.global
 include $(top_srcdir)/contrib/contrib-global.mk
 endif
 
+$(EXTENSION)--$(EXTVERSION).sql: rum_init.sql
+	cat $^ > $@
+
 ifeq ($(MAJORVERSION), 9.6)
 # arrays are not supported on 9.6
 else
 REGRESS += array
 endif
 
+# For 9.6-11 we have to make specific target with tap tests
+ifeq ($(MAJORVERSION), $(filter 9.6% 10% 11%, $(MAJORVERSION)))
 wal-check: temp-install
 	$(prove_check)
 
 check: wal-check
+endif
 
-all: $(SQL_built)
-
-#9.6 requires 1.3 file but 10.0 could live with update files
-rum--$(EXTVERSION).sql: $(DATA_first) $(DATA_updates)
-	cat $(DATA_first) $(DATA_updates) > rum--$(EXTVERSION).sql
-
-# rule for updates, e.g. rum--1.0--1.1.sql
-rum--%.sql: gen_rum_sql--%.pl
-	perl $< > $@
+#
+# Make conditional targets to save backward compatibility with PG11, PG10 and PG9.6.
+#
+ifeq ($(MAJORVERSION), $(filter 9.6% 10% 11%, $(MAJORVERSION)))
 
 install: installincludes
 
@@ -85,5 +97,6 @@ submake-rum:
 
 isolationcheck: | submake-isolation submake-rum temp-install
 	$(pg_isolation_regress_check) \
-	    --temp-config $(top_srcdir)/contrib/rum/logical.conf \
+		--temp-config $(top_srcdir)/contrib/rum/logical.conf \
 		$(ISOLATIONCHECKS)
+endif

README.md

@@ -8,38 +8,38 @@
 
 ## Introduction
 
-The **rum** module provides access method to work with `RUM` index. It is based
-on the `GIN` access methods code.
+The **rum** module provides an access method to work with a `RUM` index. It is based
+on the `GIN` access method's code.
 
-`GIN` index allows to perform fast full text search using `tsvector` and
-`tsquery` types. But full text search with GIN index has several problems:
+A `GIN` index allows performing fast full-text search using `tsvector` and
+`tsquery` types. But full-text search with a GIN index has several problems:
 
-- Slow ranking. It is need position information about lexems to ranking. `GIN`
-index doesn't store positions of lexems. So after index scan we need additional
-heap scan to retrieve lexems positions.
-- Slow phrase search with `GIN` index. This problem relates with previous
-problem. It is need position information to perform phrase search.
-- Slow ordering by timestamp. `GIN` index can't store some related information
-in index with lexemes. So it is necessary to perform additional heap scan.
+- Slow ranking. It needs positional information about lexemes to do ranking. A `GIN`
+index doesn't store positions of lexemes. So after index scanning, we need an
+additional heap scan to retrieve lexeme positions.
+- Slow phrase search with a `GIN` index. This problem relates to the previous
+problem. It needs positional information to perform phrase search.
+- Slow ordering by timestamp. A `GIN` index can't store some related information
+in the index with lexemes. So it is necessary to perform an additional heap scan.
 
-`RUM` solves this problems by storing additional information in posting tree.
+`RUM` solves these problems by storing additional information in a posting tree.
 For example, positional information of lexemes or timestamps. You can get an
-idea of `RUM` by the following picture:
+idea of `RUM` with the following diagram:
 
 ![How RUM stores additional information](img/gin_rum.png)
 
-Drawback of `RUM` is that it has slower build and insert time than `GIN`.
-It is because we need to store additional information besides keys and because
-`RUM` uses generic WAL records.
+A drawback of `RUM` is that it has slower build and insert times than `GIN`.
+This is because we need to store additional information besides keys and because
+`RUM` uses generic Write-Ahead Log (WAL) records.
 
 ## License
 
-This module available under the [license](LICENSE) similar to
+This module is available under the [license](LICENSE) similar to
 [PostgreSQL](http://www.postgresql.org/about/licence/).
 
 ## Installation
 
-Before build and install **rum** you should ensure following:
+Before building and installing **rum**, you should ensure following are installed:
 
 * PostgreSQL version is 9.6+.
 
@@ -60,9 +60,29 @@ Typical installation procedure may look like this:
 
 > **Important:** Don't forget to set the `PG_CONFIG` variable in case you want to test `RUM` on a custom build of PostgreSQL. Read more [here](https://wiki.postgresql.org/wiki/Building_and_Installing_PostgreSQL_Extension_Modules).
 
+## Tests
+
+$ make check
+
+This command runs:
+- regression tests;
+- isolation tests;
+- tap tests.
+
+    One of the tap tests downloads a 1GB archive and then unpacks it
+    into a file weighing almost 3GB. It is disabled by default.
+
+    To run this test, you need to set an environment variable:
+
+        $ export PG_TEST_EXTRA=big_values
+
+    The way to turn it off again:
+
+        $ export -n PG_TEST_EXTRA
+
 ## Common operators and functions
 
-**rum** module provides next operators.
+The **rum** module provides next operators.
 
 |       Operator       | Returns |                 Description
 | -------------------- | ------- | ----------------------------------------------
@@ -71,19 +91,19 @@ Typical installation procedure may look like this:
 | timestamp <=| timestamp | float8 | Returns distance only for left timestamps.
 | timestamp |=> timestamp | float8 | Returns distance only for right timestamps.
 
-Last three operations also works for types timestamptz, int2, int4, int8, float4, float8,
+The last three operations also work for types timestamptz, int2, int4, int8, float4, float8,
 money and oid.
 
 ## Operator classes
 
-**rum** provides next operator classes.
+**rum** provides the following operator classes.
 
 ### rum_tsvector_ops
 
 For type: `tsvector`
 
-This operator class stores `tsvector` lexemes with positional information. Supports
-ordering by `<=>` operator and prefix search. There is the example.
+This operator class stores `tsvector` lexemes with positional information. It supports
+ordering by the `<=>` operator and prefix search. See the example below.
 
 Let us assume we have the table:
 
@@ -140,8 +160,8 @@ SELECT t, a <=> to_tsquery('english', 'place | situation') AS rank
 
 For type: `tsvector`
 
-This operator class stores hash of `tsvector` lexemes with positional information.
-Supports ordering by `<=>` operator. But **doesn't** support prefix search.
+This operator class stores a hash of `tsvector` lexemes with positional information.
+It supports ordering by the `<=>` operator. It **doesn't** support prefix search.
 
 ### rum_TYPE_ops
 
@@ -153,17 +173,18 @@ Supported operations: `<`, `<=`, `=`, `>=`, `>` for all types and
 `<=>`, `<=|` and `|=>` for int2, int4, int8, float4, float8, money, oid,
 timestamp and timestamptz types.
 
-Supports ordering by `<=>`, `<=|` and `|=>` operators. Can be used with
+This operator supports ordering by the `<=>`, `<=|` and `|=>` operators. It can be used with
 `rum_tsvector_addon_ops`, `rum_tsvector_hash_addon_ops' and `rum_anyarray_addon_ops` operator classes.
 
 ### rum_tsvector_addon_ops
 
 For type: `tsvector`
 
-This operator class stores `tsvector` lexems with any supported by module
-field. There is the example.
+This operator class stores `tsvector` lexemes with any supported by module
+field. See the example below.
 
 Let us assume we have the table:
+
 ```sql
 CREATE TABLE tsts (id int, t tsvector, d timestamp);
 
@@ -202,16 +223,16 @@ SELECT id, d, d <=> '2016-05-16 14:21:25' FROM tsts WHERE t @@ 'wr&qh' ORDER BY
 
 For type: `tsvector`
 
-This operator class stores hash of `tsvector` lexems with any supported by module
+This operator class stores a hash of `tsvector` lexemes with any supported by module
 field.
 
-**Doesn't** support prefix search.
+It **doesn't** support prefix search.
 
 ### rum_tsquery_ops
 
 For type: `tsquery`
 
-Stores branches of query tree in additional information. For example we have the table:
+It stores branches of query tree in additional information. For example, we have the table:
 ```sql
 CREATE TABLE query (q tsquery, tag text);
 
@@ -240,8 +261,8 @@ SELECT * FROM query
 For type: `anyarray`
 
 This operator class stores `anyarray` elements with length of the array.
-Supports operators `&&`, `@>`, `<@`, `=`, `%` operators. Supports ordering by `<=>` operator.
-For example we have the table:
+It supports operators `&&`, `@>`, `<@`, `=`, `%` operators. It also supports ordering by `<=>` operator.
+For example, we have the table:
 
 ```sql
 CREATE TABLE test_array (i int2[]);

expected/altorder.out

@@ -1,3 +1,12 @@
+/*
+ * ------------------------------------
+ *  NOTE: This test behaves differenly
+ * ------------------------------------
+ *
+ * altorder.out - test output for 64-bit systems and
+ * altorder_1.out - test output for 32-bit systems.
+ *
+ */
 CREATE TABLE atsts (id int, t tsvector, d timestamp);
 \copy atsts from 'data/tsts.data'
 -- PGPRO-2537: We need more data to test rumsort.c with logtape.c

expected/altorder_1.out

@@ -1,3 +1,12 @@
+/*
+ * ------------------------------------
+ *  NOTE: This test behaves differenly
+ * ------------------------------------
+ *
+ * altorder.out - test output for 64-bit systems and
+ * altorder_1.out - test output for 32-bit systems.
+ *
+ */
 CREATE TABLE atsts (id int, t tsvector, d timestamp);
 \copy atsts from 'data/tsts.data'
 -- PGPRO-2537: We need more data to test rumsort.c with logtape.c

expected/altorder_hash.out

@@ -1,3 +1,12 @@
+/*
+ * ------------------------------------
+ *  NOTE: This test behaves differenly
+ * ------------------------------------
+ *
+ * altorder_hash.out - test output for 64-bit systems and
+ * altorder_hash_1.out - test output for 32-bit systems.
+ *
+ */
 CREATE TABLE atstsh (id int, t tsvector, d timestamp);
 \copy atstsh from 'data/tsts.data'
 CREATE INDEX atstsh_idx ON atstsh USING rum (t rum_tsvector_hash_addon_ops, d)

expected/altorder_hash_1.out

@@ -1,3 +1,12 @@
+/*
+ * ------------------------------------
+ *  NOTE: This test behaves differenly
+ * ------------------------------------
+ *
+ * altorder_hash.out - test output for 64-bit systems and
+ * altorder_hash_1.out - test output for 32-bit systems.
+ *
+ */
 CREATE TABLE atstsh (id int, t tsvector, d timestamp);
 \copy atstsh from 'data/tsts.data'
 CREATE INDEX atstsh_idx ON atstsh USING rum (t rum_tsvector_hash_addon_ops, d)