Create a GUC variable REGEX_FLAVOR to control the type of regular

expression accepted by the regex operators, per discussion yesterday.

Along the way, reduce deadlock_timeout from PGC_POSTMASTER to PGC_SIGHUP
category.  It is probably best to insist that all backends share the same
setting, but that doesn't mean it has to be frozen at startup.

diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index baeef81618134d7e3047dd0a8d7bdc71cf0503aa..a3e66eabc34a701d04be5a9d5df9a46b5dfb6fe3 100644 (file)
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -1,5 +1,5 @@
 
 
@@ -2665,10 +2665,24 @@ SUBSTRING('foobar' FROM 'o(.)b')   o
     due to their availability in programming languages such as Perl and Tcl.
     REs using these non-POSIX extensions are called
     advanced REs or AREs
-    in this documentation.  We first describe the ERE/ARE flavor and then
-    mention the restrictions of the BRE form.
+    in this documentation.  AREs are almost an exact superset of EREs,
+    but BREs have several notational incompatibilities (as well as being
+    much more limited).
+    We first describe the ARE and ERE forms, noting features that apply
+    only to AREs, and then describe how BREs differ.
    
 
+   
+    
+     The form of regular expressions accepted by PostgreSQL
+     can be chosen by setting the REGEX_FLAVOR run-time parameter
+     (described in the &cite-admin;).  The usual setting is
+     advanced, but one might choose extended for
+     maximum backwards compatibility with pre-7.4 releases of
+     PostgreSQL.
+    
+   
+
    
     A regular expression is defined as one or more
     branches, separated by
@@ -2784,7 +2798,7 @@ SUBSTRING('foobar' FROM 'o(.)b')   o
      meaning in PostgreSQL string literals.
      To write a pattern constant that contains a backslash,
      you must write two backslashes in the query.
-   
+    
    
 
    
@@ -3392,11 +3406,11 @@ SUBSTRING('foobar' FROM 'o(.)b')   o
    
 
    
-    Normally the flavor of RE being used is specified by
-    application-dependent means.
-    However, this can be overridden by a director.
+    Normally the flavor of RE being used is determined by
+    REGEX_FLAVOR.
+    However, this can be overridden by a director prefix.
     If an RE of any flavor begins with ***:,
-    the rest of the RE is an ARE.
+    the rest of the RE is taken as an ARE.
     If an RE of any flavor begins with ***=,
     the rest of the RE is taken to be a literal string,
     with all characters considered ordinary characters.
@@ -3407,8 +3421,8 @@ SUBSTRING('foobar' FROM 'o(.)b')   o
     a sequence (?xyz)
     (where xyz is one or more alphabetic characters)
     specifies options affecting the rest of the RE.
-    These supplement, and can override,
-    any options specified externally.
+    These options override any previously determined options (including
+    both the RE flavor and case sensitivity).
     The available option letters are
     shown in .
    
@@ -3432,7 +3446,7 @@ SUBSTRING('foobar' FROM 'o(.)b')   o
 
        
         c 
-        case-sensitive matching (usual default) 
+        case-sensitive matching (overrides operator type) 
        
 
        
@@ -3443,7 +3457,7 @@ SUBSTRING('foobar' FROM 'o(.)b')   o
        
         i 
         case-insensitive matching (see
-       ) 
+       ) (overrides operator type) 
        
 
        
@@ -3471,12 +3485,12 @@ SUBSTRING('foobar' FROM 'o(.)b')   o
 
        
         s 
-        non-newline-sensitive matching (usual default) 
+        non-newline-sensitive matching (default) 
        
 
        
         t 
-        tight syntax (usual default; see below) 
+        tight syntax (default; see below) 
        
 
        
@@ -3696,7 +3710,7 @@ SUBSTRING('foobar' FROM 'o(.)b')   o
    
 
    
-    Two significant incompatibilites exist between AREs and the ERE syntax
+    Two significant incompatibilities exist between AREs and the ERE syntax
     recognized by pre-7.4 releases of PostgreSQL:
 
     
@@ -3717,6 +3731,10 @@ SUBSTRING('foobar' FROM 'o(.)b')   o
       
      
     
+
+    While these differences are unlikely to create a problem for most
+    applications, you can avoid them if necessary by
+    setting REGEX_FLAVOR to extended.
    
    
 

diff --git a/doc/src/sgml/runtime.sgml b/doc/src/sgml/runtime.sgml
index cf8a648ba84bf5e6d4a5fa676d315e7be5dc78d3..cd171c41d280e77ea782a7a0e3874edd13ce820e 100644 (file)
--- a/doc/src/sgml/runtime.sgml
+++ b/doc/src/sgml/runtime.sgml
@@ -1,5 +1,5 @@
 
 
 
@@ -1447,8 +1447,7 @@ env PGOPTIONS='-c geqo=off' psql
         practice. On a heavily loaded server you might want to raise it.
         Ideally the setting should exceed your typical transaction time,
         so as to improve the odds that the lock will be released before
-        the waiter decides to check for deadlock. This option can only
-        be set at server start.
+        the waiter decides to check for deadlock.
        
       
      
@@ -1781,6 +1780,20 @@ dynamic_library_path = '/usr/local/lib/postgresql:/home/my_project/lib:$libdir'
       
      
 
+     
+      REGEX_FLAVOR (string)
+      regular expressions
+      
+       
+        The regular expression flavor can be set to
+   advanced, extended, or basic.
+   The usual default is advanced.  The extended
+   setting may be useful for exact backwards compatibility with
+   pre-7.4 releases of PostgreSQL.
+       
+      
+     
+
      
       SEARCH_PATH (string)
       search_path

diff --git a/src/backend/utils/adt/regexp.c b/src/backend/utils/adt/regexp.c
index 604e55d4145f9f71bb2508602b2742128bacb767..56f78422bcc293f9e3b28cd0b9c9a542eed531cf 100644 (file)
--- a/src/backend/utils/adt/regexp.c
+++ b/src/backend/utils/adt/regexp.c
@@ -8,7 +8,7 @@
  *
  *
  * IDENTIFICATION
- *   $Header: /cvsroot/pgsql/src/backend/utils/adt/regexp.c,v 1.44 2003/02/05 17:41:32 tgl Exp $
+ *   $Header: /cvsroot/pgsql/src/backend/utils/adt/regexp.c,v 1.45 2003/02/06 20:25:33 tgl Exp $
  *
  *     Alistair Crooks added the code for the regex caching
  *     agc - cached the regular expressions used - there's a good chance
@@ -34,6 +34,10 @@
 #include "utils/builtins.h"
 
 
+/* GUC-settable flavor parameter */
+static int regex_flavor = REG_ADVANCED;
+
+
 /*
  * We cache precompiled regular expressions using a "self organizing list"
  * structure, in which recently-used items tend to be near the front.
@@ -216,6 +220,34 @@ RE_compile_and_execute(text *text_re, unsigned char *dat, int dat_len,
 }
 
 
+/*
+ * assign_regex_flavor - GUC hook to validate and set REGEX_FLAVOR
+ */
+const char *
+assign_regex_flavor(const char *value,
+                   bool doit, bool interactive)
+{
+   if (strcasecmp(value, "advanced") == 0)
+   {
+       if (doit)
+           regex_flavor = REG_ADVANCED;
+   }
+   else if (strcasecmp(value, "extended") == 0)
+   {
+       if (doit)
+           regex_flavor = REG_EXTENDED;
+   }
+   else if (strcasecmp(value, "basic") == 0)
+   {
+       if (doit)
+           regex_flavor = REG_BASIC;
+   }
+   else
+       return NULL;            /* fail */
+   return value;               /* OK */
+}
+
+
 /*
  * interface routines called by the function manager
  */
@@ -229,7 +261,7 @@ nameregexeq(PG_FUNCTION_ARGS)
    PG_RETURN_BOOL(RE_compile_and_execute(p,
                                          (unsigned char *) NameStr(*n),
                                          strlen(NameStr(*n)),
-                                         REG_ADVANCED,
+                                         regex_flavor,
                                          0, NULL));
 }
 
@@ -242,7 +274,7 @@ nameregexne(PG_FUNCTION_ARGS)
    PG_RETURN_BOOL(!RE_compile_and_execute(p,
                                           (unsigned char *) NameStr(*n),
                                           strlen(NameStr(*n)),
-                                          REG_ADVANCED,
+                                          regex_flavor,
                                           0, NULL));
 }
 
@@ -255,7 +287,7 @@ textregexeq(PG_FUNCTION_ARGS)
    PG_RETURN_BOOL(RE_compile_and_execute(p,
                                          (unsigned char *) VARDATA(s),
                                          VARSIZE(s) - VARHDRSZ,
-                                         REG_ADVANCED,
+                                         regex_flavor,
                                          0, NULL));
 }
 
@@ -268,7 +300,7 @@ textregexne(PG_FUNCTION_ARGS)
    PG_RETURN_BOOL(!RE_compile_and_execute(p,
                                           (unsigned char *) VARDATA(s),
                                           VARSIZE(s) - VARHDRSZ,
-                                          REG_ADVANCED,
+                                          regex_flavor,
                                           0, NULL));
 }
 
@@ -288,7 +320,7 @@ nameicregexeq(PG_FUNCTION_ARGS)
    PG_RETURN_BOOL(RE_compile_and_execute(p,
                                          (unsigned char *) NameStr(*n),
                                          strlen(NameStr(*n)),
-                                         REG_ICASE | REG_ADVANCED,
+                                         regex_flavor | REG_ICASE,
                                          0, NULL));
 }
 
@@ -301,7 +333,7 @@ nameicregexne(PG_FUNCTION_ARGS)
    PG_RETURN_BOOL(!RE_compile_and_execute(p,
                                           (unsigned char *) NameStr(*n),
                                           strlen(NameStr(*n)),
-                                          REG_ICASE | REG_ADVANCED,
+                                          regex_flavor | REG_ICASE,
                                           0, NULL));
 }
 
@@ -314,7 +346,7 @@ texticregexeq(PG_FUNCTION_ARGS)
    PG_RETURN_BOOL(RE_compile_and_execute(p,
                                          (unsigned char *) VARDATA(s),
                                          VARSIZE(s) - VARHDRSZ,
-                                         REG_ICASE | REG_ADVANCED,
+                                         regex_flavor | REG_ICASE,
                                          0, NULL));
 }
 
@@ -327,7 +359,7 @@ texticregexne(PG_FUNCTION_ARGS)
    PG_RETURN_BOOL(!RE_compile_and_execute(p,
                                           (unsigned char *) VARDATA(s),
                                           VARSIZE(s) - VARHDRSZ,
-                                          REG_ICASE | REG_ADVANCED,
+                                          regex_flavor | REG_ICASE,
                                           0, NULL));
 }
 
@@ -353,7 +385,7 @@ textregexsubstr(PG_FUNCTION_ARGS)
    match = RE_compile_and_execute(p,
                                   (unsigned char *) VARDATA(s),
                                   VARSIZE(s) - VARHDRSZ,
-                                  REG_ADVANCED,
+                                  regex_flavor,
                                   2, pmatch);
 
    /* match? then return the substring matching the pattern */

diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index aeb044f7d17f094f1ea26ce1a2dc3296117275d6..2f99d3d5f41c56f0b350c6d90a04953766baf960 100644 (file)
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -5,7 +5,7 @@
  * command, configuration file, and command line options.
  * See src/backend/utils/misc/README for more information.
  *
- * $Header: /cvsroot/pgsql/src/backend/utils/misc/guc.c,v 1.113 2003/01/28 18:04:02 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/utils/misc/guc.c,v 1.114 2003/02/06 20:25:33 tgl Exp $
  *
  * Copyright 2000 by PostgreSQL Global Development Group
  * Written by Peter Eisentraut .
@@ -127,6 +127,7 @@ static double phony_random_seed;
 static char *client_encoding_string;
 static char *datestyle_string;
 static char *default_iso_level_string;
+static char *regex_flavor_string;
 static char *server_encoding_string;
 static char *session_authorization_string;
 static char *timezone_string;
@@ -568,7 +569,7 @@ static struct config_int
    },
 
    {
-       {"deadlock_timeout", PGC_POSTMASTER}, &DeadlockTimeout,
+       {"deadlock_timeout", PGC_SIGHUP}, &DeadlockTimeout,
        1000, 0, INT_MAX, NULL, NULL
    },
 
@@ -818,6 +819,11 @@ static struct config_string
        "C", locale_time_assign, NULL
    },
 
+   {
+       {"regex_flavor", PGC_USERSET}, ®ex_flavor_string,
+       "advanced", assign_regex_flavor, NULL
+   },
+
    {
        {"search_path", PGC_USERSET, GUC_LIST_INPUT | GUC_LIST_QUOTE},
        &namespace_search_path,

diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index 2e7d63024b7f9305ba80b6cf1c5114cea8931c3c..f40c2a00355843a436a2799d454da01e95233203 100644 (file)
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -208,6 +208,7 @@
 #max_expr_depth = 10000        # min 10
 #max_files_per_process = 1000  # min 25
 #password_encryption = true
+#regex_flavor = advanced   # advanced, extended, or basic
 #sql_inheritance = true
 #transform_null_equals = false
 #statement_timeout = 0     # 0 is disabled, in milliseconds

diff --git a/src/bin/psql/tab-complete.c b/src/bin/psql/tab-complete.c
index efebd2f6b6fe2f114f0882f8296d52ab95497bd9..60d682c58a6d084ad108e0ce8efe8c859604e360 100644 (file)
--- a/src/bin/psql/tab-complete.c
+++ b/src/bin/psql/tab-complete.c
@@ -3,7 +3,7 @@
  *
  * Copyright 2000-2002 by PostgreSQL Global Development Group
  *
- * $Header: /cvsroot/pgsql/src/bin/psql/tab-complete.c,v 1.72 2003/01/25 23:10:30 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/bin/psql/tab-complete.c,v 1.73 2003/02/06 20:25:33 tgl Exp $
  */
 
 /*----------------------------------------------------------------------
@@ -215,14 +215,11 @@ psql_completion(char *text, int start, int end)
        "TRANSACTION",
 
        /*
-        * the rest should match USERSET entries in
-        * backend/utils/misc/guc.c
+        * the rest should match USERSET and possibly SUSET entries in
+        * backend/utils/misc/guc.c.
         */
        "australian_timezones",
-       "authentication_timeout",
        "autocommit",
-       "checkpoint_segments",
-       "checkpoint_timeout",
        "client_encoding",
        "client_min_messages",
        "commit_delay",
@@ -231,7 +228,6 @@ psql_completion(char *text, int start, int end)
        "cpu_operator_cost",
        "cpu_tuple_cost",
        "DateStyle",
-       "db_user_namespace",
        "deadlock_timeout",
        "debug_pretty_print",
        "debug_print_parse",
@@ -239,19 +235,19 @@ psql_completion(char *text, int start, int end)
        "debug_print_rewritten",
        "default_statistics_target",
        "default_transaction_isolation",
+       "default_transaction_read_only",
        "dynamic_library_path",
        "effective_cache_size",
+       "enable_hashagg",
        "enable_hashjoin",
        "enable_indexscan",
        "enable_mergejoin",
        "enable_nestloop",
        "enable_seqscan",
        "enable_sort",
-       "enable_hashagg",
        "enable_tidscan",
        "explain_pretty_print",
        "extra_float_digits",
-       "fixbtree",
        "from_collapse_limit",
        "fsync",
        "geqo",
@@ -262,18 +258,19 @@ psql_completion(char *text, int start, int end)
        "geqo_selection_bias",
        "geqo_threshold",
        "join_collapse_limit",
-       "log_hostname",
        "krb_server_keyfile",
        "lc_messages",
        "lc_monetary",
        "lc_numeric",
        "lc_time",
-       "log_connections",
        "log_duration",
+       "log_executor_stats",
        "log_min_error_statement",
-       "log_pid",
+       "log_min_messages",
+       "log_parser_stats",
+       "log_planner_stats",
        "log_statement",
-       "log_timestamp",
+       "log_statement_stats",
        "max_connections",
        "max_expr_depth",
        "max_files_per_process",
@@ -282,19 +279,12 @@ psql_completion(char *text, int start, int end)
        "max_locks_per_transaction",
        "password_encryption",
        "port",
-       "pre_auth_delay",
        "random_page_cost",
+       "regex_flavor",
        "search_path",
-       "log_min_messages",
        "shared_buffers",
-       "log_executor_stats",
-       "log_parser_stats",
-       "log_planner_stats",
-       "log_source_port",
-       "log_statement_stats",
        "seed",
        "server_encoding",
-       "silent_mode",
        "sort_mem",
        "sql_inheritance",
        "ssl",
@@ -316,7 +306,6 @@ psql_completion(char *text, int start, int end)
        "unix_socket_group",
        "unix_socket_permissions",
        "vacuum_mem",
-       "virtual_hostt",
        "wal_buffers",
        "wal_debug",
        "wal_sync_method",

diff --git a/src/include/utils/builtins.h b/src/include/utils/builtins.h
index 6a781dab61bd0080fed2f4fb834fb7a9cd6aa350..df20f4ad499a1ce093e6c7dc937cfcdfcf45524d 100644 (file)
--- a/src/include/utils/builtins.h
+++ b/src/include/utils/builtins.h
@@ -7,7 +7,7 @@
  * Portions Copyright (c) 1996-2002, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $Id: builtins.h,v 1.206 2002/12/06 05:20:28 momjian Exp $
+ * $Id: builtins.h,v 1.207 2003/02/06 20:25:33 tgl Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -377,6 +377,8 @@ extern Datum texticregexeq(PG_FUNCTION_ARGS);
 extern Datum texticregexne(PG_FUNCTION_ARGS);
 extern Datum textregexsubstr(PG_FUNCTION_ARGS);
 extern Datum similar_escape(PG_FUNCTION_ARGS);
+extern const char *assign_regex_flavor(const char *value,
+                                      bool doit, bool interactive);
 
 /* regproc.c */
 extern Datum regprocin(PG_FUNCTION_ARGS);