postgresql/src/bin/scripts/createdb.c

283 lines
7.3 KiB
C
Raw Normal View History

/*-------------------------------------------------------------------------
*
* createdb
*
* Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
2010-09-20 22:08:53 +02:00
* src/bin/scripts/createdb.c
*
*-------------------------------------------------------------------------
*/
#include "postgres_fe.h"
Fix the inadvertent libpq ABI breakage discovered by Martin Pitt: the renumbering of encoding IDs done between 8.2 and 8.3 turns out to break 8.2 initdb and psql if they are run with an 8.3beta1 libpq.so. For the moment we can rearrange the order of enum pg_enc to keep the same number for everything except PG_JOHAB, which isn't a problem since there are no direct references to it in the 8.2 programs anyway. (This does force initdb unfortunately.) Going forward, we want to fix things so that encoding IDs can be changed without an ABI break, and this commit includes the changes needed to allow libpq's encoding IDs to be treated as fully independent of the backend's. The main issue is that libpq clients should not include pg_wchar.h or otherwise assume they know the specific values of libpq's encoding IDs, since they might encounter version skew between pg_wchar.h and the libpq.so they are using. To fix, have libpq officially export functions needed for encoding name<=>ID conversion and validity checking; it was doing this anyway unofficially. It's still the case that we can't renumber backend encoding IDs until the next bump in libpq's major version number, since doing so will break the 8.2-era client programs. However the code is now prepared to avoid this type of problem in future. Note that initdb is no longer a libpq client: we just pull in the two source files we need directly. The patch also fixes a few places that were being sloppy about checking for an unrecognized encoding name.
2007-10-13 22:18:42 +02:00
#include "common.h"
#include "common/logging.h"
#include "fe_utils/string_utils.h"
static void help(const char *progname);
int
main(int argc, char *argv[])
{
static struct option long_options[] = {
{"host", required_argument, NULL, 'h'},
{"port", required_argument, NULL, 'p'},
{"username", required_argument, NULL, 'U'},
{"no-password", no_argument, NULL, 'w'},
{"password", no_argument, NULL, 'W'},
{"echo", no_argument, NULL, 'e'},
{"owner", required_argument, NULL, 'O'},
{"tablespace", required_argument, NULL, 'D'},
{"template", required_argument, NULL, 'T'},
{"encoding", required_argument, NULL, 'E'},
{"lc-collate", required_argument, NULL, 1},
{"lc-ctype", required_argument, NULL, 2},
{"locale", required_argument, NULL, 'l'},
{"maintenance-db", required_argument, NULL, 3},
{NULL, 0, NULL, 0}
};
const char *progname;
int optindex;
int c;
const char *dbname = NULL;
const char *maintenance_db = NULL;
char *comment = NULL;
char *host = NULL;
char *port = NULL;
char *username = NULL;
enum trivalue prompt_password = TRI_DEFAULT;
bool echo = false;
char *owner = NULL;
char *tablespace = NULL;
char *template = NULL;
char *encoding = NULL;
char *lc_collate = NULL;
char *lc_ctype = NULL;
char *locale = NULL;
PQExpBufferData sql;
PGconn *conn;
PGresult *result;
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_logging_init(argv[0]);
progname = get_progname(argv[0]);
set_pglocale_pgservice(argv[0], PG_TEXTDOMAIN("pgscripts"));
handle_help_version_opts(argc, argv, "createdb", help);
while ((c = getopt_long(argc, argv, "h:p:U:wWeO:D:T:E:l:", long_options, &optindex)) != -1)
{
switch (c)
{
case 'h':
host = pg_strdup(optarg);
break;
case 'p':
port = pg_strdup(optarg);
break;
case 'U':
username = pg_strdup(optarg);
break;
case 'w':
prompt_password = TRI_NO;
break;
case 'W':
prompt_password = TRI_YES;
break;
case 'e':
echo = true;
break;
case 'O':
owner = pg_strdup(optarg);
break;
case 'D':
tablespace = pg_strdup(optarg);
break;
case 'T':
template = pg_strdup(optarg);
break;
case 'E':
encoding = pg_strdup(optarg);
break;
case 1:
lc_collate = pg_strdup(optarg);
break;
case 2:
lc_ctype = pg_strdup(optarg);
break;
case 'l':
locale = pg_strdup(optarg);
break;
case 3:
maintenance_db = pg_strdup(optarg);
break;
default:
fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
exit(1);
}
}
switch (argc - optind)
{
case 0:
break;
case 1:
dbname = argv[optind];
break;
case 2:
dbname = argv[optind];
comment = argv[optind + 1];
break;
default:
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("too many command-line arguments (first is \"%s\")",
argv[optind + 2]);
fprintf(stderr, _("Try \"%s --help\" for more information.\n"), progname);
exit(1);
}
if (locale)
{
if (lc_ctype)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("only one of --locale and --lc-ctype can be specified");
exit(1);
}
if (lc_collate)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("only one of --locale and --lc-collate can be specified");
exit(1);
}
lc_ctype = locale;
lc_collate = locale;
}
if (encoding)
{
if (pg_char_to_encoding(encoding) < 0)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("\"%s\" is not a valid encoding name", encoding);
exit(1);
}
}
if (dbname == NULL)
{
if (getenv("PGDATABASE"))
dbname = getenv("PGDATABASE");
else if (getenv("PGUSER"))
dbname = getenv("PGUSER");
else
dbname = get_user_name_or_exit(progname);
}
/* No point in trying to use postgres db when creating postgres db. */
if (maintenance_db == NULL && strcmp(dbname, "postgres") == 0)
maintenance_db = "template1";
conn = connectMaintenanceDatabase(maintenance_db, host, port, username,
prompt_password, progname, echo);
initPQExpBuffer(&sql);
appendPQExpBuffer(&sql, "CREATE DATABASE %s",
fmtId(dbname));
if (owner)
appendPQExpBuffer(&sql, " OWNER %s", fmtId(owner));
if (tablespace)
appendPQExpBuffer(&sql, " TABLESPACE %s", fmtId(tablespace));
if (encoding)
{
appendPQExpBufferStr(&sql, " ENCODING ");
appendStringLiteralConn(&sql, encoding, conn);
}
if (template)
appendPQExpBuffer(&sql, " TEMPLATE %s", fmtId(template));
if (lc_collate)
{
appendPQExpBufferStr(&sql, " LC_COLLATE ");
appendStringLiteralConn(&sql, lc_collate, conn);
}
if (lc_ctype)
{
appendPQExpBufferStr(&sql, " LC_CTYPE ");
appendStringLiteralConn(&sql, lc_ctype, conn);
}
appendPQExpBufferChar(&sql, ';');
if (echo)
printf("%s\n", sql.data);
result = PQexec(conn, sql.data);
if (PQresultStatus(result) != PGRES_COMMAND_OK)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("database creation failed: %s", PQerrorMessage(conn));
PQfinish(conn);
exit(1);
}
PQclear(result);
if (comment)
{
printfPQExpBuffer(&sql, "COMMENT ON DATABASE %s IS ", fmtId(dbname));
appendStringLiteralConn(&sql, comment, conn);
appendPQExpBufferChar(&sql, ';');
if (echo)
printf("%s\n", sql.data);
result = PQexec(conn, sql.data);
if (PQresultStatus(result) != PGRES_COMMAND_OK)
{
Unified logging system for command-line programs This unifies the various ad hoc logging (message printing, error printing) systems used throughout the command-line programs. Features: - Program name is automatically prefixed. - Message string does not end with newline. This removes a common source of inconsistencies and omissions. - Additionally, a final newline is automatically stripped, simplifying use of PQerrorMessage() etc., another common source of mistakes. - I converted error message strings to use %m where possible. - As a result of the above several points, more translatable message strings can be shared between different components and between frontends and backend, without gratuitous punctuation or whitespace differences. - There is support for setting a "log level". This is not meant to be user-facing, but can be used internally to implement debug or verbose modes. - Lazy argument evaluation, so no significant overhead if logging at some level is disabled. - Some color in the messages, similar to gcc and clang. Set PG_COLOR=auto to try it out. Some colors are predefined, but can be customized by setting PG_COLORS. - Common files (common/, fe_utils/, etc.) can handle logging much more simply by just using one API without worrying too much about the context of the calling program, requiring callbacks, or having to pass "progname" around everywhere. - Some programs called setvbuf() to make sure that stderr is unbuffered, even on Windows. But not all programs did that. This is now done centrally. Soft goals: - Reduces vertical space use and visual complexity of error reporting in the source code. - Encourages more deliberate classification of messages. For example, in some cases it wasn't clear without analyzing the surrounding code whether a message was meant as an error or just an info. - Concepts and terms are vaguely aligned with popular logging frameworks such as log4j and Python logging. This is all just about printing stuff out. Nothing affects program flow (e.g., fatal exits). The uses are just too varied to do that. Some existing code had wrappers that do some kind of print-and-exit, and I adapted those. I tried to keep the output mostly the same, but there is a lot of historical baggage to unwind and special cases to consider, and I might not always have succeeded. One significant change is that pg_rewind used to write all error messages to stdout. That is now changed to stderr. Reviewed-by: Donald Dong <xdong@csumb.edu> Reviewed-by: Arthur Zakirov <a.zakirov@postgrespro.ru> Discussion: https://www.postgresql.org/message-id/flat/6a609b43-4f57-7348-6480-bd022f924310@2ndquadrant.com
2019-04-01 14:24:37 +02:00
pg_log_error("comment creation failed (database was created): %s",
PQerrorMessage(conn));
PQfinish(conn);
exit(1);
}
PQclear(result);
}
PQfinish(conn);
exit(0);
}
static void
help(const char *progname)
{
printf(_("%s creates a PostgreSQL database.\n\n"), progname);
printf(_("Usage:\n"));
printf(_(" %s [OPTION]... [DBNAME] [DESCRIPTION]\n"), progname);
printf(_("\nOptions:\n"));
printf(_(" -D, --tablespace=TABLESPACE default tablespace for the database\n"));
printf(_(" -e, --echo show the commands being sent to the server\n"));
printf(_(" -E, --encoding=ENCODING encoding for the database\n"));
printf(_(" -l, --locale=LOCALE locale settings for the database\n"));
printf(_(" --lc-collate=LOCALE LC_COLLATE setting for the database\n"));
printf(_(" --lc-ctype=LOCALE LC_CTYPE setting for the database\n"));
printf(_(" -O, --owner=OWNER database user to own the new database\n"));
printf(_(" -T, --template=TEMPLATE template database to copy\n"));
printf(_(" -V, --version output version information, then exit\n"));
printf(_(" -?, --help show this help, then exit\n"));
printf(_("\nConnection options:\n"));
printf(_(" -h, --host=HOSTNAME database server host or socket directory\n"));
printf(_(" -p, --port=PORT database server port\n"));
printf(_(" -U, --username=USERNAME user name to connect as\n"));
printf(_(" -w, --no-password never prompt for password\n"));
printf(_(" -W, --password force password prompt\n"));
printf(_(" --maintenance-db=DBNAME alternate maintenance database\n"));
printf(_("\nBy default, a database with the same name as the current user is created.\n"));
printf(_("\nReport bugs to <%s>.\n"), PACKAGE_BUGREPORT);
printf(_("%s home page: <%s>\n"), PACKAGE_NAME, PACKAGE_URL);
}