diff options
| -rw-r--r-- | doc/src/sgml/ref/psql-ref.sgml | 10 | ||||
| -rw-r--r-- | src/bin/psql/copy.c | 319 | ||||
| -rw-r--r-- | src/bin/psql/stringutils.c | 260 | ||||
| -rw-r--r-- | src/bin/psql/stringutils.h | 10 |
4 files changed, 372 insertions, 227 deletions
diff --git a/doc/src/sgml/ref/psql-ref.sgml b/doc/src/sgml/ref/psql-ref.sgml index d232ef895ac..6e3525d7687 100644 --- a/doc/src/sgml/ref/psql-ref.sgml +++ b/doc/src/sgml/ref/psql-ref.sgml @@ -1,5 +1,5 @@ <!-- -$Header: /cvsroot/pgsql/doc/src/sgml/ref/psql-ref.sgml,v 1.78 2002/10/11 23:03:48 petere Exp $ +$Header: /cvsroot/pgsql/doc/src/sgml/ref/psql-ref.sgml,v 1.79 2002/10/19 00:22:14 tgl Exp $ PostgreSQL documentation --> @@ -692,6 +692,7 @@ testdb=> <varlistentry> <term><literal>\copy <replaceable class="parameter">table</replaceable> + [ ( <replaceable class="parameter">column_list</replaceable> ) ] { <literal>from</literal> | <literal>to</literal> } <replaceable class="parameter">filename</replaceable> | stdin | stdout [ <literal>with</literal> ] @@ -705,11 +706,12 @@ testdb=> Performs a frontend (client) copy. This is an operation that runs an <acronym>SQL</acronym> <xref linkend="SQL-COPY" endterm="SQL-COPY-title"> command, but instead of the backend's - reading or writing the specified file, and consequently - requiring backend access and special user privilege, as well as - being bound to the file system accessible by the backend, + reading or writing the specified file, <application>psql</application> reads or writes the file and routes the data between the backend and the local file system. + This means that file accessibility and privileges are those + of the local user, not the server, and no SQL superuser + privileges are required. </para> <para> diff --git a/src/bin/psql/copy.c b/src/bin/psql/copy.c index 7e1b05d5fe8..b70519be159 100644 --- a/src/bin/psql/copy.c +++ b/src/bin/psql/copy.c @@ -3,7 +3,7 @@ * * Copyright 2000 by PostgreSQL Global Development Group * - * $Header: /cvsroot/pgsql/src/bin/psql/copy.c,v 1.27 2002/10/15 02:24:16 tgl Exp $ + * $Header: /cvsroot/pgsql/src/bin/psql/copy.c,v 1.28 2002/10/19 00:22:14 tgl Exp $ */ #include "postgres_fe.h" #include "copy.h" @@ -38,11 +38,15 @@ bool copy_in_state; * parse_slash_copy * -- parses \copy command line * - * Accepted syntax: \copy table|"table" [with oids] from|to filename|'filename' [with ] [ oids ] [ delimiter '<char>'] [ null as 'string' ] + * Accepted syntax: \copy table [(columnlist)] [with oids] from|to filename [with ] [ oids ] [ delimiter char] [ null as string ] * (binary is not here yet) * * Old syntax for backward compatibility: (2002-06-19): - * \copy table|"table" [with oids] from|to filename|'filename' [ using delimiters '<char>'] [ with null as 'string' ] + * \copy table [(columnlist)] [with oids] from|to filename [ using delimiters char] [ with null as string ] + * + * table name can be double-quoted and can have a schema part. + * column names can be double-quoted. + * filename, char, and string can be single-quoted like SQL literals. * * returns a malloc'ed structure with the options, or NULL on parsing error */ @@ -50,6 +54,7 @@ bool copy_in_state; struct copy_options { char *table; + char *column_list; char *file; /* NULL = stdin/stdout */ bool from; bool binary; @@ -65,6 +70,7 @@ free_copy_options(struct copy_options * ptr) if (!ptr) return; free(ptr->table); + free(ptr->column_list); free(ptr->file); free(ptr->delim); free(ptr->null); @@ -72,14 +78,32 @@ free_copy_options(struct copy_options * ptr) } +/* catenate "more" onto "var", freeing the original value of *var */ +static void +xstrcat(char **var, const char *more) +{ + char *newvar; + + newvar = (char *) malloc(strlen(*var) + strlen(more) + 1); + if (!newvar) + { + psql_error("out of memory\n"); + exit(EXIT_FAILURE); + } + strcpy(newvar, *var); + strcat(newvar, more); + free(*var); + *var = newvar; +} + + static struct copy_options * parse_slash_copy(const char *args) { struct copy_options *result; char *line; char *token; - bool error = false; - char quote; + const char *whitespace = " \t\n\r"; if (args) line = xstrdup(args); @@ -95,152 +119,183 @@ parse_slash_copy(const char *args) exit(EXIT_FAILURE); } - token = strtokx(line, " \t\n\r", "\"", '\\', "e, NULL, pset.encoding); + token = strtokx(line, whitespace, ".,()", "\"", + 0, false, pset.encoding); if (!token) - error = true; - else - { + goto error; + #ifdef NOT_USED - /* this is not implemented yet */ - if (!quote && strcasecmp(token, "binary") == 0) + /* this is not implemented yet */ + if (strcasecmp(token, "binary") == 0) + { + result->binary = true; + token = strtokx(NULL, whitespace, ".,()", "\"", + 0, false, pset.encoding); + if (!token) + goto error; + } +#endif + + result->table = xstrdup(token); + + token = strtokx(NULL, whitespace, ".,()", "\"", + 0, false, pset.encoding); + if (!token) + goto error; + + /* + * strtokx() will not have returned a multi-character token starting with + * '.', so we don't need strcmp() here. Likewise for '(', etc, below. + */ + if (token[0] == '.') + { + /* handle schema . table */ + xstrcat(&result->table, token); + token = strtokx(NULL, whitespace, ".,()", "\"", + 0, false, pset.encoding); + if (!token) + goto error; + xstrcat(&result->table, token); + token = strtokx(NULL, whitespace, ".,()", "\"", + 0, false, pset.encoding); + if (!token) + goto error; + } + + if (token[0] == '(') + { + /* handle parenthesized column list */ + result->column_list = xstrdup(token); + for (;;) { - result->binary = true; - token = strtokx(NULL, " \t\n\r", "\"", '\\', "e, NULL, pset.encoding); + token = strtokx(NULL, whitespace, ".,()", "\"", + 0, false, pset.encoding); + if (!token || strchr(".,()", token[0])) + goto error; + xstrcat(&result->column_list, token); + token = strtokx(NULL, whitespace, ".,()", "\"", + 0, false, pset.encoding); if (!token) - error = true; + goto error; + xstrcat(&result->column_list, token); + if (token[0] == ')') + break; + if (token[0] != ',') + goto error; } - if (token) -#endif - result->table = xstrdup(token); + token = strtokx(NULL, whitespace, ".,()", "\"", + 0, false, pset.encoding); + if (!token) + goto error; } -#ifdef USE_ASSERT_CHECKING - assert(error || result->table); -#endif - - if (!error) + /* + * Allows old COPY syntax for backward compatibility + * 2002-06-19 + */ + if (strcasecmp(token, "with") == 0) { - token = strtokx(NULL, " \t\n\r", NULL, '\\', NULL, NULL, pset.encoding); + token = strtokx(NULL, whitespace, NULL, NULL, + 0, false, pset.encoding); + if (!token || strcasecmp(token, "oids") != 0) + goto error; + result->oids = true; + + token = strtokx(NULL, whitespace, NULL, NULL, + 0, false, pset.encoding); if (!token) - error = true; - else - { - /* - * Allows old COPY syntax for backward compatibility - * 2002-06-19 - */ - if (strcasecmp(token, "with") == 0) - { - token = strtokx(NULL, " \t\n\r", NULL, '\\', NULL, NULL, pset.encoding); - if (!token || strcasecmp(token, "oids") != 0) - error = true; - else - result->oids = true; + goto error; + } - if (!error) - { - token = strtokx(NULL, " \t\n\r", NULL, '\\', NULL, NULL, pset.encoding); - if (!token) - error = true; - } - } + if (strcasecmp(token, "from") == 0) + result->from = true; + else if (strcasecmp(token, "to") == 0) + result->from = false; + else + goto error; - if (!error && strcasecmp(token, "from") == 0) - result->from = true; - else if (!error && strcasecmp(token, "to") == 0) - result->from = false; - else - error = true; - } - } + token = strtokx(NULL, whitespace, NULL, "'", + '\\', true, pset.encoding); + if (!token) + goto error; + + if (strcasecmp(token, "stdin") == 0 || + strcasecmp(token, "stdout") == 0) + result->file = NULL; + else + result->file = xstrdup(token); + + token = strtokx(NULL, whitespace, NULL, NULL, + 0, false, pset.encoding); - if (!error) + /* + * Allows old COPY syntax for backward compatibility + * 2002-06-19 + */ + if (token && strcasecmp(token, "using") == 0) { - token = strtokx(NULL, " \t\n\r", "'", '\\', "e, NULL, pset.encoding); + token = strtokx(NULL, whitespace, NULL, NULL, + 0, false, pset.encoding); + if (!(token && strcasecmp(token, "delimiters") == 0)) + goto error; + token = strtokx(NULL, whitespace, NULL, "'", + '\\', false, pset.encoding); if (!token) - error = true; - else if (!quote && (strcasecmp(token, "stdin") == 0 || strcasecmp(token, "stdout") == 0)) - result->file = NULL; - else - result->file = xstrdup(token); + goto error; + result->delim = xstrdup(token); + token = strtokx(NULL, whitespace, NULL, NULL, + 0, false, pset.encoding); } - if (!error) + if (token) { - token = strtokx(NULL, " \t\n\r", NULL, '\\', NULL, NULL, pset.encoding); - if (token) + if (strcasecmp(token, "with") != 0) + goto error; + while ((token = strtokx(NULL, whitespace, NULL, NULL, + 0, false, pset.encoding)) != NULL) { - /* - * Allows old COPY syntax for backward compatibility - * 2002-06-19 - */ - if (strcasecmp(token, "using") == 0) + if (strcasecmp(token, "delimiter") == 0) { - token = strtokx(NULL, " \t\n\r", NULL, '\\', NULL, NULL, pset.encoding); - if (token && strcasecmp(token, "delimiters") == 0) - { - token = strtokx(NULL, " \t\n\r", "'", '\\', NULL, NULL, pset.encoding); - if (token) - { - result->delim = xstrdup(token); - token = strtokx(NULL, " \t\n\r", NULL, '\\', NULL, NULL, pset.encoding); - } - else - error = true; - } + token = strtokx(NULL, whitespace, NULL, "'", + '\\', false, pset.encoding); + if (token && strcasecmp(token, "as") == 0) + token = strtokx(NULL, whitespace, NULL, "'", + '\\', false, pset.encoding); + if (token) + result->delim = xstrdup(token); else - error = true; + goto error; } - } - } - - if (!error && token) - { - if (strcasecmp(token, "with") == 0) - { - while (!error && (token = strtokx(NULL, " \t\n\r", NULL, '\\', NULL, NULL, pset.encoding))) + else if (strcasecmp(token, "null") == 0) { - if (strcasecmp(token, "delimiter") == 0) - { - token = strtokx(NULL, " \t\n\r", "'", '\\', NULL, NULL, pset.encoding); - if (token && strcasecmp(token, "as") == 0) - token = strtokx(NULL, " \t\n\r", "'", '\\', NULL, NULL, pset.encoding); - if (token) - result->delim = xstrdup(token); - else - error = true; - } - else if (strcasecmp(token, "null") == 0) - { - token = strtokx(NULL, " \t\n\r", "'", '\\', NULL, NULL, pset.encoding); - if (token && strcasecmp(token, "as") == 0) - token = strtokx(NULL, " \t\n\r", "'", '\\', NULL, NULL, pset.encoding); - if (token) - result->null = xstrdup(token); - else - error = true; - } + token = strtokx(NULL, whitespace, NULL, "'", + '\\', false, pset.encoding); + if (token && strcasecmp(token, "as") == 0) + token = strtokx(NULL, whitespace, NULL, "'", + '\\', false, pset.encoding); + if (token) + result->null = xstrdup(token); else - error = true; + goto error; } + else + goto error; } - else - error = true; } free(line); - if (error) - { - if (token) - psql_error("\\copy: parse error at '%s'\n", token); - else - psql_error("\\copy: parse error at end of line\n"); - free_copy_options(result); - return NULL; - } + return result; + +error: + if (token) + psql_error("\\copy: parse error at '%s'\n", token); else - return result; + psql_error("\\copy: parse error at end of line\n"); + free_copy_options(result); + free(line); + + return NULL; } @@ -272,7 +327,11 @@ do_copy(const char *args) if (options->binary) appendPQExpBuffer(&query, "BINARY "); - appendPQExpBuffer(&query, "\"%s\" ", options->table); + appendPQExpBuffer(&query, "%s ", options->table); + + if (options->column_list) + appendPQExpBuffer(&query, "%s ", options->column_list); + /* Uses old COPY syntax for backward compatibility 2002-06-19 */ if (options->oids) appendPQExpBuffer(&query, "WITH OIDS "); @@ -285,10 +344,22 @@ do_copy(const char *args) /* Uses old COPY syntax for backward compatibility 2002-06-19 */ if (options->delim) - appendPQExpBuffer(&query, " USING DELIMITERS '%s'", options->delim); + { + if (options->delim[0] == '\'') + appendPQExpBuffer(&query, " USING DELIMITERS %s", + options->delim); + else + appendPQExpBuffer(&query, " USING DELIMITERS '%s'", + options->delim); + } if (options->null) - appendPQExpBuffer(&query, " WITH NULL AS '%s'", options->null); + { + if (options->null[0] == '\'') + appendPQExpBuffer(&query, " WITH NULL AS %s", options->null); + else + appendPQExpBuffer(&query, " WITH NULL AS '%s'", options->null); + } if (options->from) { diff --git a/src/bin/psql/stringutils.c b/src/bin/psql/stringutils.c index 8ff58c46430..0401c92718c 100644 --- a/src/bin/psql/stringutils.c +++ b/src/bin/psql/stringutils.c @@ -1,45 +1,61 @@ /* * psql - the PostgreSQL interactive terminal * - * Copyright 2000 by PostgreSQL Global Development Group + * Copyright 2000-2002 by PostgreSQL Global Development Group * - * $Header: /cvsroot/pgsql/src/bin/psql/stringutils.c,v 1.30 2002/08/27 20:16:49 petere Exp $ + * $Header: /cvsroot/pgsql/src/bin/psql/stringutils.c,v 1.31 2002/10/19 00:22:14 tgl Exp $ */ #include "postgres_fe.h" -#include "stringutils.h" -#include "settings.h" -#include <ctype.h> #include <assert.h> +#include <ctype.h> #include "libpq-fe.h" +#include "settings.h" +#include "stringutils.h" - -static void unescape_quotes(char *source, int quote, int escape); +static void strip_quotes(char *source, char quote, char escape, int encoding); /* * Replacement for strtok() (a.k.a. poor man's flex) * - * The calling convention is similar to that of strtok. + * Splits a string into tokens, returning one token per call, then NULL + * when no more tokens exist in the given string. + * + * The calling convention is similar to that of strtok, but with more + * frammishes. + * * s - string to parse, if NULL continue parsing the last string - * delim - set of characters that delimit tokens (usually whitespace) - * quote - set of characters that quote stuff, they're not part of the token - * escape - character than can quote quotes - * was_quoted - if not NULL, stores the quoting character if any was encountered - * token_pos - if not NULL, receives a count to the start of the token in the - * parsed string + * whitespace - set of whitespace characters that separate tokens + * delim - set of non-whitespace separator characters (or NULL) + * quote - set of characters that can quote a token (NULL if none) + * escape - character that can quote quotes (0 if none) + * del_quotes - if TRUE, strip quotes from the returned token, else return + * it exactly as found in the string + * encoding - the active character-set encoding + * + * Characters in 'delim', if any, will be returned as single-character + * tokens unless part of a quoted token. + * + * Double occurences of the quoting character are always taken to represent + * a single quote character in the data. If escape isn't 0, then escape + * followed by anything (except \0) is a data character too. * * Note that the string s is _not_ overwritten in this implementation. + * + * NB: it's okay to vary delim, quote, and escape from one call to the + * next on a single source string, but changing whitespace is a bad idea + * since you might lose data. */ char * strtokx(const char *s, + const char *whitespace, const char *delim, const char *quote, - int escape, - char *was_quoted, - unsigned int *token_pos, + char escape, + bool del_quotes, int encoding) { static char *storage = NULL;/* store the local copy of the users @@ -50,23 +66,32 @@ strtokx(const char *s, /* variously abused variables: */ unsigned int offset; char *start; - char *cp = NULL; + char *p; if (s) { free(storage); - storage = strdup(s); + /* + * We may need extra space to insert delimiter nulls for adjacent + * tokens. 2X the space is a gross overestimate, but it's + * unlikely that this code will be used on huge strings anyway. + */ + storage = (char *) malloc(2 * strlen(s) + 1); + if (!storage) + return NULL; /* really "out of memory" */ + strcpy(storage, s); string = storage; } if (!storage) return NULL; - /* skip leading "whitespace" */ - offset = strspn(string, delim); + /* skip leading whitespace */ + offset = strspn(string, whitespace); + start = &string[offset]; - /* end of string reached */ - if (string[offset] == '\0') + /* end of string reached? */ + if (*start == '\0') { /* technically we don't need to free here, but we're nice */ free(storage); @@ -75,118 +100,165 @@ strtokx(const char *s, return NULL; } - /* test if quoting character */ - if (quote) - cp = strchr(quote, string[offset]); - - if (cp) + /* test if delimiter character */ + if (delim && strchr(delim, *start)) { - /* okay, we have a quoting character, now scan for the closer */ - char *p; + /* + * If not at end of string, we need to insert a null to terminate + * the returned token. We can just overwrite the next character + * if it happens to be in the whitespace set ... otherwise move over + * the rest of the string to make room. (This is why we allocated + * extra space above). + */ + p = start + 1; + if (*p != '\0') + { + if (!strchr(whitespace, *p)) + memmove(p + 1, p, strlen(p) + 1); + *p = '\0'; + string = p + 1; + } + else + { + /* at end of string, so no extra work */ + string = p; + } - start = &string[offset + 1]; + return start; + } - if (token_pos) - *token_pos = start - storage; + /* test if quoting character */ + if (quote && strchr(quote, *start)) + { + /* okay, we have a quoted token, now scan for the closer */ + char thisquote = *start; - for (p = start; - *p && (*p != *cp || *(p - 1) == escape); - p += PQmblen(p, encoding) - ); + for (p = start + 1; *p; p += PQmblen(p, encoding)) + { + if (*p == escape && p[1] != '\0') + p++; /* process escaped anything */ + else if (*p == thisquote && p[1] == thisquote) + p++; /* process doubled quote */ + else if (*p == thisquote) + { + p++; /* skip trailing quote */ + break; + } + } - /* not yet end of string? */ + /* + * If not at end of string, we need to insert a null to terminate + * the returned token. See notes above. + */ if (*p != '\0') { + if (!strchr(whitespace, *p)) + memmove(p + 1, p, strlen(p) + 1); *p = '\0'; string = p + 1; - if (was_quoted) - *was_quoted = *cp; - unescape_quotes(start, *cp, escape); - return start; } else { - if (was_quoted) - *was_quoted = *cp; + /* at end of string, so no extra work */ string = p; - - unescape_quotes(start, *cp, escape); - return start; } + + /* Clean up the token if caller wants that */ + if (del_quotes) + strip_quotes(start, thisquote, escape, encoding); + + return start; } - /* otherwise no quoting character. scan till next delimiter */ - start = &string[offset]; + /* + * Otherwise no quoting character. Scan till next whitespace, + * delimiter or quote. NB: at this point, *start is known not to be + * '\0', whitespace, delim, or quote, so we will consume at least + * one character. + */ + offset = strcspn(start, whitespace); - if (token_pos) - *token_pos = start - storage; + if (delim) + { + unsigned int offset2 = strcspn(start, delim); - offset = strcspn(start, delim); - if (was_quoted) - *was_quoted = 0; + if (offset > offset2) + offset = offset2; + } - if (start[offset] != '\0') + if (quote) { - start[offset] = '\0'; - string = &start[offset] + 1; + unsigned int offset2 = strcspn(start, quote); - return start; + if (offset > offset2) + offset = offset2; + } + + p = start + offset; + + /* + * If not at end of string, we need to insert a null to terminate + * the returned token. See notes above. + */ + if (*p != '\0') + { + if (!strchr(whitespace, *p)) + memmove(p + 1, p, strlen(p) + 1); + *p = '\0'; + string = p + 1; } else { - string = &start[offset]; - return start; + /* at end of string, so no extra work */ + string = p; } -} - + return start; +} /* - * unescape_quotes + * strip_quotes * - * Resolves escaped quotes. Used by strtokx above. + * Remove quotes from the string at *source. Leading and trailing occurrences + * of 'quote' are removed; embedded double occurrences of 'quote' are reduced + * to single occurrences; if 'escape' is not 0 then 'escape' removes special + * significance of next character. + * + * Note that the source string is overwritten in-place. */ static void -unescape_quotes(char *source, int quote, int escape) +strip_quotes(char *source, char quote, char escape, int encoding) { - char *p; - char *destination, - *tmp; + char *src; + char *dst; #ifdef USE_ASSERT_CHECKING assert(source); + assert(quote); #endif - destination = calloc(1, strlen(source) + 1); - if (!destination) - { - perror("calloc"); - exit(EXIT_FAILURE); - } + src = dst = source; - tmp = destination; + if (*src && *src == quote) + src++; /* skip leading quote */ - for (p = source; *p; p++) + while (*src) { - char c; - - if (*p == escape && *(p + 1) && quote == *(p + 1)) - { - c = *(p + 1); - p++; - } - else - c = *p; - - *tmp = c; - tmp++; + char c = *src; + int i; + + if (c == quote && src[1] == '\0') + break; /* skip trailing quote */ + else if (c == quote && src[1] == quote) + src++; /* process doubled quote */ + else if (c == escape && src[1] != '\0') + src++; /* process escaped character */ + + i = PQmblen(src, encoding); + while (i--) + *dst++ = *src++; } - /* Terminating null character */ - *tmp = '\0'; - - strcpy(source, destination); - - free(destination); + *dst = '\0'; } diff --git a/src/bin/psql/stringutils.h b/src/bin/psql/stringutils.h index faafc606d5e..62c8ba9e3af 100644 --- a/src/bin/psql/stringutils.h +++ b/src/bin/psql/stringutils.h @@ -1,9 +1,9 @@ /* * psql - the PostgreSQL interactive terminal * - * Copyright 2000 by PostgreSQL Global Development Group + * Copyright 2000-2002 by PostgreSQL Global Development Group * - * $Header: /cvsroot/pgsql/src/bin/psql/stringutils.h,v 1.17 2001/11/05 17:46:31 momjian Exp $ + * $Id: stringutils.h,v 1.18 2002/10/19 00:22:14 tgl Exp $ */ #ifndef STRINGUTILS_H #define STRINGUTILS_H @@ -11,11 +11,11 @@ /* The cooler version of strtok() which knows about quotes and doesn't * overwrite your input */ extern char *strtokx(const char *s, + const char *whitespace, const char *delim, const char *quote, - int escape, - char *was_quoted, - unsigned int *token_pos, + char escape, + bool del_quotes, int encoding); #endif /* STRINGUTILS_H */ |