pg_query 2.0.3 → 2.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f19538f4d41c891a9b7704cd56becd762e44f5f766fba06c07f89b2e1d61b69f
-  data.tar.gz: df5a48fd5582bacd09098a5d37c21794a6f1caff82b16fe4597be2257bb0eaa1
+  metadata.gz: a47580d95bf78de051c96a5a4b260c9cf829ff74461dcea5fc99637467b86435
+  data.tar.gz: 8249f9d2c493f74cdafc99f69f8bb55e4f9504975f73cff2dfb504f5ae8987a8
 SHA512:
-  metadata.gz: 0326c810f5589b03d3a1809e98c199984c6bc013dfd93228cb6e35e5378cf39421ff0690c5dc67431f4b1501815fa80245d5e0cfcb1c75186054aa5d1300d684
-  data.tar.gz: 476514b25750f97ab9f27c55ccf6c221b6ab16687677178adc9f2ed219a85286dca983a36b25e703a3f0e9f080268ce6e82b69fbb932d4e50195bc711f434530
+  metadata.gz: 76a1633e48ac2c784510ef12a68ca7f6e4c43f134aa7bf7d82725138f95cd89564787e9bc862e50545ce99ca442f936d86bae6882156d7c52cd7b4acd1414699
+  data.tar.gz: 541bfbe7bc660ebbe34e79a54b2cfa1dee1bb59a8d9892113b8ea2ffe5fbda6734375c189ab5b62a98c280e6cf456327d89360fd0467d2b279b93bb504f67c19

data/CHANGELOG.md

@@ -5,6 +5,83 @@
 * ...
 
 
+## 2.1.3     2022-01-28
+
+* Track tables in EXCEPT and INTERSECT queries ([#239](https://github.com/pganalyze/pg_query/pull/239))
+* Get filter_columns working with UNION/EXCEPT/INTERSECT ([#240](https://github.com/pganalyze/pg_query/pull/240))
+* Update google-protobuf to address CVE scanner complaints
+  - Note that none of the CVEs apply to pg_query, but this avoids unnecessary errors when
+    the google-protobuf dependency is pulled in
+
+
+## 2.1.2     2021-11-12
+
+* Find tables in using clause of delete statement ([#234](https://github.com/pganalyze/pg_query/pull/234))
+* Find tables in case statements ([#235](https://github.com/pganalyze/pg_query/pull/235))
+* Correctly find nested tables in a subselect in a join condition ([#233](https://github.com/pganalyze/pg_query/pull/233))
+* Mark Postgres methods as visibility hidden, to avoid bloating dynamic symbol table ([#232](https://github.com/pganalyze/pg_query/pull/232))
+  - This is required on ELF platforms (i.e. Linux, etc) to avoid including all global
+    symbols in the shared library's symbol table, bloating the size, and causing
+    potential conflicts with other C libraries using the same symbol names.
+
+
+## 2.1.1     2021-10-13
+
+* Update to libpg_query 13-2.1.0 ([#230](https://github.com/pganalyze/pg_query/pull/230))
+  - Normalize: add funcname error object
+  - Normalize: Match GROUP BY against target list and re-use param refs
+  - PL/pgSQL: Setup namespace items for parameters, support RECORD types
+    - This significantly improves parsing for PL/pgSQL functions, to the extent
+      that most functions should now parse successfully
+  - Normalize: Don't modify constants in TypeName typmods/arrayBounds fields
+    - This matches how pg_stat_statement behaves, and avoids causing parsing
+      errors on the normalized statement
+  - Don't fail builds on systems that have strchrnul support (FreeBSD)
+* Fix build on FreeBSD ([#222](https://github.com/pganalyze/pg_query/pull/222))
+* Add workaround for Ruby garbage collection bug ([#227](https://github.com/pganalyze/pg_query/pull/227))
+  - The Ruby interpreter has a bug in `String#concat` where the appended
+    array may be garbage collected prematurely because the compiler
+    optimized out a Ruby stack variable. We now call `to_ary` on the
+    Protobuf object to ensure the array lands on the Ruby stack so the
+    garbage collector sees it.
+  - The real fix in the interpreter is described in
+    https://bugs.ruby-lang.org/issues/18140#note-2, but most current Ruby
+    interpreters won't have this fix for some time.
+* Table/function extraction: Support subselects and LATERAL better ([#229](https://github.com/pganalyze/pg_query/pull/229))
+  - This reworks the parsing logic so we don't ignore certain kinds of
+    subselects.
+
+
+## 2.1.0     2021-07-04
+
+* Update to libpg_query 13-2.0.6
+  - Update to Postgres 13.3 patch release
+  - Normalize: Don't touch "GROUP BY 1" and "ORDER BY 1" expressions, keep original text 
+  - Fingerprint: Cache list item hashes to fingerprint complex queries faster
+  - Deparser: Emit the RangeVar catalogname if present
+  - Fix crash in pg_scan function when encountering backslash escapes
+* Support extracting functions from a parsed query ([#147](https://github.com/pganalyze/pg_query/pull/147))
+  - Adds new `functions`, `ddl_functions` and `call_functions` methods
+  - Note that functions are identified by their name only, not their full type definition,
+    since raw query parsetrees don't contain sufficient data to identify the types of
+    arguments when functions are called
+* Relax google-protobuf dependency ([#213](https://github.com/pganalyze/pg_query/pull/213))
+* Update google-protobuf to 3.17.1 ([#212](https://github.com/pganalyze/pg_query/pull/212))
+  - google-protobuf 3.15.x has a bug that causes a seg fault in Ruby under
+    certain conditions (https://github.com/protocolbuffers/protobuf/pull/8639). Use
+    google-protobuf 3.17.1 instead.
+* Use Protobuf definition for determining JSON field names
+  - Note you may see a breaking change if you were using `PgQuery::ParseResult.encode_json`
+    to map the protobuf result to JSON, since this now respects the intended JSON names
+    from the Proto3 definition (instead of the differently formatted Protobuf field names)
+* Rakefile: Fix "rake clean" by using CLEAN.include instead of CLEAN.<<
+* Find tables inside COALESCE/MIN/MAX functions, UPDATE FROM list
+* Extconf: Add library include path using $INCFLAGS, list it first
+  - This ensures any system installed libpg_query gets considered after
+    the bundled libpg_query, avoiding errors where the wrong header files
+    are used.
+
+
 ## 2.0.3     2021-04-05
 
 * Update to libpg_query 13-2.0.4

data/README.md

@@ -133,6 +133,18 @@ PgQuery.fingerprint("SELECT ?")
 => "50fde20626009aba"
 ```
 
+### Scanning a query into tokens
+
+```ruby
+PgQuery.scan('SELECT 1 --comment')
+
+=> [<PgQuery::ScanResult: version: 130002, tokens: [
+<PgQuery::ScanToken: start: 0, end: 6, token: :SELECT, keyword_kind: :RESERVED_KEYWORD>,
+<PgQuery::ScanToken: start: 7, end: 8, token: :ICONST, keyword_kind: :NO_KEYWORD>,
+<PgQuery::ScanToken: start: 9, end: 18, token: :SQL_COMMENT, keyword_kind: :NO_KEYWORD>]>,
+ []]
+```
+
 ## Differences from Upstream PostgreSQL
 
 This gem is based on [libpg_query](https://github.com/pganalyze/libpg_query),

data/Rakefile

@@ -5,8 +5,8 @@ require 'rspec/core/rake_task'
 require 'rubocop/rake_task'
 require 'open-uri'
 
-LIB_PG_QUERY_TAG = '13-2.0.4'.freeze
-LIB_PG_QUERY_SHA256SUM = 'a67ef3e3b6c9cb1297f362888d6660dac165d3b020f78d23afe4293b8ceaf190'.freeze
+LIB_PG_QUERY_TAG = '13-2.1.0'.freeze
+LIB_PG_QUERY_SHA256SUM = 'a01329ae5bac19b10b8ddf8012bd663a20f85f180d6d7b900c1a1ca8444d19a5'.freeze
 
 Rake::ExtensionTask.new 'pg_query' do |ext|
   ext.lib_dir = 'lib/pg_query'
@@ -21,9 +21,9 @@ task default: %i[spec lint]
 task test: :spec
 task lint: :rubocop
 
-CLEAN << 'tmp/**/*'
-CLEAN << 'ext/pg_query/*.o'
-CLEAN << 'lib/pg_query/pg_query.bundle'
+CLEAN.include 'tmp/**/*'
+CLEAN.include 'ext/pg_query/*.o'
+CLEAN.include 'lib/pg_query/pg_query.bundle'
 
 task :update_source do
   workdir = File.join(__dir__, 'tmp')
@@ -86,18 +86,4 @@ task :update_source do
   system("cp -a #{libdir}/testdata/* #{testfilesdir}")
   # Copy back the custom ext files
   system("cp -a #{extbakdir}/pg_query_ruby.{c,sym} #{extbakdir}/extconf.rb #{extdir}")
-
-  # Generate JSON field name helper (workaround until https://github.com/protocolbuffers/protobuf/pull/8356 is merged)
-  str = "module PgQuery\n  INTERNAL_PROTO_FIELD_NAME_TO_JSON_NAME = {\n"
-  cur_type = nil
-  File.read(File.join(libdir, 'protobuf/pg_query.proto')).each_line do |line|
-    if line[/^message (\w+)/]
-      cur_type = $1
-      next
-    end
-    next unless line[/(repeated )?\w+ (\w+) = \d+( \[json_name="(\w+)"\])?;/]
-    str += format("    [%s, :%s] => '%s',\n", cur_type, $2, $4 || $2)
-  end
-  str += "  }\nend\n"
-  File.write(File.join(__dir__, 'lib/pg_query/json_field_names.rb'), str)
 end

data/ext/pg_query/extconf.rb

@@ -7,7 +7,9 @@ require 'pathname'
 
 $objs = Dir.glob(File.join(__dir__, '*.c')).map { |f| Pathname.new(f).sub_ext('.o').to_s }
 
-$CFLAGS << " -I#{File.join(__dir__, 'include')} -O3 -Wall -fno-strict-aliasing -fwrapv -fstack-protector -Wno-unused-function -Wno-unused-variable -g"
+$CFLAGS << " -fvisibility=hidden -O3 -Wall -fno-strict-aliasing -fwrapv -fstack-protector -Wno-unused-function -Wno-unused-variable -Wno-clobbered -Wno-sign-compare -Wno-discarded-qualifiers -g"
+
+$INCFLAGS = "-I#{File.join(__dir__, 'include')} " + $INCFLAGS
 
 SYMFILE = File.join(__dir__, 'pg_query_ruby.sym')
 if RUBY_PLATFORM =~ /darwin/

data/ext/pg_query/include/c.h

@@ -110,6 +110,18 @@
 #define pg_attribute_unused()
 #endif
 
+/*
+ * Place this macro before functions that should be allowed to make misaligned
+ * accesses.  Think twice before using it on non-x86-specific code!
+ * Testing can be done with "-fsanitize=alignment -fsanitize-trap=alignment"
+ * on clang, or "-fsanitize=alignment -fno-sanitize-recover=alignment" on gcc.
+ */
+#if __clang_major__ >= 7 || __GNUC__ >= 8
+#define pg_attribute_no_sanitize_alignment() __attribute__((no_sanitize("alignment")))
+#else
+#define pg_attribute_no_sanitize_alignment()
+#endif
+
 /*
  * Append PG_USED_FOR_ASSERTS_ONLY to definitions of variables that are only
  * used in assert-enabled builds, to avoid compiler warnings about unused

data/ext/pg_query/include/executor/executor.h

@@ -271,6 +271,12 @@ extern ProjectionInfo *ExecBuildProjectionInfo(List *targetList,
 											   TupleTableSlot *slot,
 											   PlanState *parent,
 											   TupleDesc inputDesc);
+extern ProjectionInfo *ExecBuildProjectionInfoExt(List *targetList,
+												  ExprContext *econtext,
+												  TupleTableSlot *slot,
+												  bool assignJunkEntries,
+												  PlanState *parent,
+												  TupleDesc inputDesc);
 extern ExprState *ExecPrepareExpr(Expr *node, EState *estate);
 extern ExprState *ExecPrepareQual(List *qual, EState *estate);
 extern ExprState *ExecPrepareCheck(List *qual, EState *estate);

data/ext/pg_query/include/nodes/execnodes.h

@@ -395,12 +395,15 @@ typedef struct OnConflictSetState
  * relation, and perhaps also fire triggers.  ResultRelInfo holds all the
  * information needed about a result relation, including indexes.
  *
- * Normally, a ResultRelInfo refers to a table that is in the query's
- * range table; then ri_RangeTableIndex is the RT index and ri_RelationDesc
- * is just a copy of the relevant es_relations[] entry.  But sometimes,
- * in ResultRelInfos used only for triggers, ri_RangeTableIndex is zero
- * and ri_RelationDesc is a separately-opened relcache pointer that needs
- * to be separately closed.  See ExecGetTriggerResultRel.
+ * Normally, a ResultRelInfo refers to a table that is in the query's range
+ * table; then ri_RangeTableIndex is the RT index and ri_RelationDesc is
+ * just a copy of the relevant es_relations[] entry.  However, in some
+ * situations we create ResultRelInfos for relations that are not in the
+ * range table, namely for targets of tuple routing in a partitioned table,
+ * and when firing triggers in tables other than the target tables (See
+ * ExecGetTriggerResultRel).  In these situations, ri_RangeTableIndex is 0
+ * and ri_RelationDesc is a separately-opened relcache pointer that needs to
+ * be separately closed.
  */
 typedef struct ResultRelInfo
 {

data/ext/pg_query/include/nodes/pathnodes.h

@@ -912,7 +912,7 @@ typedef struct StatisticExtInfo
 
 	Oid			statOid;		/* OID of the statistics row */
 	RelOptInfo *rel;			/* back-link to statistic's table */
-	char		kind;			/* statistic kind of this entry */
+	char		kind;			/* statistics kind of this entry */
 	Bitmapset  *keys;			/* attnums of the columns covered */
 } StatisticExtInfo;
 

data/ext/pg_query/include/optimizer/paths.h

@@ -135,6 +135,14 @@ extern EquivalenceClass *get_eclass_for_sort_expr(PlannerInfo *root,
 												  Index sortref,
 												  Relids rel,
 												  bool create_it);
+extern EquivalenceMember *find_ec_member_matching_expr(EquivalenceClass *ec,
+													   Expr *expr,
+													   Relids relids);
+extern EquivalenceMember *find_computable_ec_member(PlannerInfo *root,
+													EquivalenceClass *ec,
+													List *exprs,
+													Relids relids,
+													bool require_parallel_safe);
 extern Expr *find_em_expr_for_rel(EquivalenceClass *ec, RelOptInfo *rel);
 extern Expr *find_em_expr_usable_for_sorting_rel(PlannerInfo *root,
 												 EquivalenceClass *ec,

data/ext/pg_query/include/pg_config.h

@@ -757,7 +757,7 @@
 #define PACKAGE_NAME "PostgreSQL"
 
 /* Define to the full name and version of this package. */
-#define PACKAGE_STRING "PostgreSQL 13.2"
+#define PACKAGE_STRING "PostgreSQL 13.3"
 
 /* Define to the one symbol short name of this package. */
 #define PACKAGE_TARNAME "postgresql"
@@ -766,7 +766,7 @@
 #define PACKAGE_URL "https://www.postgresql.org/"
 
 /* Define to the version of this package. */
-#define PACKAGE_VERSION "13.2"
+#define PACKAGE_VERSION "13.3"
 
 /* Define to the name of a signed 128-bit integer type. */
 #define PG_INT128_TYPE __int128
@@ -785,7 +785,7 @@
 #define PG_MAJORVERSION_NUM 13
 
 /* PostgreSQL minor version number */
-#define PG_MINORVERSION_NUM 2
+#define PG_MINORVERSION_NUM 3
 
 /* Define to best printf format archetype, usually gnu_printf if available. */
 #define PG_PRINTF_ATTRIBUTE printf
@@ -794,13 +794,13 @@
 #define PG_USE_STDBOOL 1
 
 /* PostgreSQL version as a string */
-#define PG_VERSION "13.2"
+#define PG_VERSION "13.3"
 
 /* PostgreSQL version as a number */
-#define PG_VERSION_NUM 130002
+#define PG_VERSION_NUM 130003
 
 /* A string containing the version number, platform, and C compiler */
-#define PG_VERSION_STR "PostgreSQL 13.2 on x86_64-apple-darwin19.6.0, compiled by Apple clang version 12.0.0 (clang-1200.0.32.29), 64-bit"
+#define PG_VERSION_STR "PostgreSQL 13.3 on x86_64-apple-darwin19.6.0, compiled by Apple clang version 12.0.0 (clang-1200.0.32.29), 64-bit"
 
 /* Define to 1 to allow profiling output to be saved separately for each
    process. */
@@ -987,3 +987,6 @@
 #undef HAVE_EXECINFO_H
 #undef HAVE_BACKTRACE_SYMBOLS
 #undef HAVE__GET_CPUID
+#ifdef __FreeBSD__
+#define HAVE_STRCHRNUL
+#endif

data/ext/pg_query/include/pg_config_manual.h

@@ -135,6 +135,13 @@
 #define EXEC_BACKEND
 #endif
 
+/*
+ * Define this if your operating system supports link()
+ */
+#if !defined(WIN32) && !defined(__CYGWIN__)
+#define HAVE_WORKING_LINK 1
+#endif
+
 /*
  * USE_POSIX_FADVISE controls whether Postgres will attempt to use the
  * posix_fadvise() kernel call.  Usually the automatic configure tests are

data/ext/pg_query/include/pg_query.h

@@ -106,9 +106,9 @@ void pg_query_free_fingerprint_result(PgQueryFingerprintResult result);
 void pg_query_exit(void);
 
 // Postgres version information
-#define PG_VERSION "13.2"
+#define PG_VERSION "13.3"
 #define PG_MAJORVERSION "13"
-#define PG_VERSION_NUM 130002
+#define PG_VERSION_NUM 130003
 
 // Deprecated APIs below
 

data/ext/pg_query/include/pg_query_outfuncs_defs.c

@@ -2270,6 +2270,7 @@ _outTableLikeClause(OUT_TYPE(TableLikeClause, TableLikeClause) out, const TableL
 {
   WRITE_SPECIFIC_NODE_PTR_FIELD(RangeVar, range_var, relation, relation, relation);
   WRITE_UINT_FIELD(options, options, options);
+  WRITE_UINT_FIELD(relation_oid, relationOid, relationOid);
 }
 
 static void

data/ext/pg_query/include/pg_query_readfuncs_defs.c

@@ -2674,6 +2674,7 @@ _readTableLikeClause(OUT_TYPE(TableLikeClause, TableLikeClause) msg)
   TableLikeClause *node = makeNode(TableLikeClause);
   READ_SPECIFIC_NODE_PTR_FIELD(RangeVar, range_var, relation, relation, relation);
   READ_UINT_FIELD(options, options, options);
+  READ_UINT_FIELD(relation_oid, relationOid, relationOid);
   return node;
 }