X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fdata-io%2Fget-data.c;h=0c60bd3d63bb2c84104a28442e331499a088c30d;hb=2a76184b55a8c229adc0b31d3436d29076de0ef8;hp=9b878c553a92bf1a16e37f5985506e025db924c6;hpb=32ee0e0402d6d56674f53a47d879ec5c07dabe09;p=pspp diff --git a/src/language/data-io/get-data.c b/src/language/data-io/get-data.c index 9b878c553a..0c60bd3d63 100644 --- a/src/language/data-io/get-data.c +++ b/src/language/data-io/get-data.c @@ -1,5 +1,6 @@ /* PSPP - a program for statistical analysis. - Copyright (C) 2007, 2008, 2009, 2010, 2011 Free Software Foundation, Inc. + Copyright (C) 2007, 2008, 2009, 2010, 2011, 2012, + 2013, 2015, 2016 Free Software Foundation, Inc. This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -35,6 +36,7 @@ #include "language/data-io/placement-parser.h" #include "language/lexer/format-parser.h" #include "language/lexer/lexer.h" +#include "libpspp/cast.h" #include "libpspp/i18n.h" #include "libpspp/message.h" @@ -44,8 +46,10 @@ #define _(msgid) gettext (msgid) #define N_(msgid) (msgid) -static struct spreadsheet_read_info *parse_spreadsheet (struct lexer *lexer); -static void destroy_spreadsheet_read_info (struct spreadsheet_read_info *); +static bool parse_spreadsheet (struct lexer *lexer, char **filename, + struct spreadsheet_read_options *opts); + +static void destroy_spreadsheet_read_info (struct spreadsheet_read_options *); static int parse_get_txt (struct lexer *lexer, struct dataset *); static int parse_get_psql (struct lexer *lexer, struct dataset *); @@ -54,50 +58,77 @@ int cmd_get_data (struct lexer *lexer, struct dataset *ds) { char *tok = NULL; - lex_force_match (lexer, T_SLASH); + struct spreadsheet_read_options opts; + + opts.sheet_name = NULL; + opts.sheet_index = -1; + opts.cell_range = NULL; + opts.read_names = false; + opts.asw = -1; + + if (! lex_force_match (lexer, T_SLASH)) + goto error; if (!lex_force_match_id (lexer, "TYPE")) - return CMD_FAILURE; + goto error; - lex_force_match (lexer, T_EQUALS); + if (!lex_force_match (lexer, T_EQUALS)) + goto error; + + const char *s = lex_tokcstr (lexer); + + if (s) + tok = strdup (s); - tok = strdup (lex_tokcstr (lexer)); if (lex_match_id (lexer, "TXT")) { + free (tok); return parse_get_txt (lexer, ds); } else if (lex_match_id (lexer, "PSQL")) { + free (tok); return parse_get_psql (lexer, ds); } - else if (lex_match_id (lexer, "GNM") || + else if (lex_match_id (lexer, "GNM") || lex_match_id (lexer, "ODS")) { - struct casereader *reader = NULL; - struct dictionary *dict = NULL; - struct spreadsheet_read_info *sri = parse_spreadsheet (lexer); - if (NULL == sri) + char *filename = NULL; + if (!parse_spreadsheet (lexer, &filename, &opts)) goto error; - if ( 0 == strncasecmp (tok, "GNM", 3)) - reader = gnumeric_open_reader (sri, &dict); + struct spreadsheet *spreadsheet = NULL; + if (0 == strncasecmp (tok, "GNM", 3)) + spreadsheet = gnumeric_probe (filename, true); else if (0 == strncasecmp (tok, "ODS", 3)) - reader = ods_open_reader (sri, &dict); + spreadsheet = ods_probe (filename, true); + + if (spreadsheet == NULL) + { + msg (SE, _("error reading file `%s'"), filename); + free (filename); + goto error; + } + free (filename); + struct casereader *reader = spreadsheet_make_reader (spreadsheet, &opts); if (reader) { - dataset_set_dict (ds, dict); + dataset_set_dict (ds, dict_clone (spreadsheet->dict)); dataset_set_source (ds, reader); - destroy_spreadsheet_read_info (sri); free (tok); + destroy_spreadsheet_read_info (&opts); + spreadsheet_unref (spreadsheet); return CMD_SUCCESS; } - destroy_spreadsheet_read_info (sri); + spreadsheet_unref (spreadsheet); } else msg (SE, _("Unsupported TYPE %s."), tok); + error: + destroy_spreadsheet_read_info (&opts); free (tok); return CMD_FAILURE; } @@ -112,12 +143,14 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds) psql.bsize = -1; ds_init_empty (&psql.sql); - lex_force_match (lexer, T_SLASH); + if (! lex_force_match (lexer, T_SLASH)) + goto error; if (!lex_force_match_id (lexer, "CONNECT")) goto error; - lex_force_match (lexer, T_EQUALS); + if (! lex_force_match (lexer, T_EQUALS)) + goto error; if (!lex_force_string (lexer)) goto error; @@ -126,28 +159,34 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds) lex_get (lexer); - while (lex_match (lexer, T_SLASH) ) + while (lex_match (lexer, T_SLASH)) { - if ( lex_match_id (lexer, "ASSUMEDSTRWIDTH")) + if (lex_match_id (lexer, "ASSUMEDSTRWIDTH")) { lex_match (lexer, T_EQUALS); - psql.str_width = lex_integer (lexer); - lex_get (lexer); + if (lex_force_int_range (lexer, "ASSUMEDSTRWIDTH", 1, 32767)) + { + psql.str_width = lex_integer (lexer); + lex_get (lexer); + } } - else if ( lex_match_id (lexer, "BSIZE")) + else if (lex_match_id (lexer, "BSIZE")) { lex_match (lexer, T_EQUALS); - psql.bsize = lex_integer (lexer); - lex_get (lexer); + if (lex_force_int_range (lexer, "BSIZE", 1, INT_MAX)) + { + psql.bsize = lex_integer (lexer); + lex_get (lexer); + } } - else if ( lex_match_id (lexer, "UNENCRYPTED")) + else if (lex_match_id (lexer, "UNENCRYPTED")) { psql.allow_clear = true; } else if (lex_match_id (lexer, "SQL")) { lex_match (lexer, T_EQUALS); - if ( ! lex_force_string (lexer) ) + if (! lex_force_string (lexer)) goto error; ds_put_substring (&psql.sql, lex_tokss (lexer)); @@ -158,7 +197,7 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds) struct dictionary *dict = NULL; struct casereader *reader = psql_open_reader (&psql, &dict); - if ( reader ) + if (reader) { dataset_set_dict (ds, dict); dataset_set_source (ds, reader); @@ -178,56 +217,69 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds) return CMD_FAILURE; } -static struct spreadsheet_read_info * -parse_spreadsheet (struct lexer *lexer) +static bool +parse_spreadsheet (struct lexer *lexer, char **filename, + struct spreadsheet_read_options *opts) { - struct spreadsheet_read_info *sri = xzalloc (sizeof *sri); - sri->sheet_index = 1; - sri->read_names = true; - sri->asw = -1; + opts->sheet_index = 1; + opts->sheet_name = NULL; + opts->cell_range = NULL; + opts->read_names = true; + opts->asw = -1; - lex_force_match (lexer, T_SLASH); + if (! lex_force_match (lexer, T_SLASH)) + goto error; if (!lex_force_match_id (lexer, "FILE")) goto error; - lex_force_match (lexer, T_EQUALS); + if (! lex_force_match (lexer, T_EQUALS)) + goto error; if (!lex_force_string (lexer)) goto error; - sri->file_name = utf8_to_filename (lex_tokcstr (lexer)); + *filename = utf8_to_filename (lex_tokcstr (lexer)); lex_get (lexer); - while (lex_match (lexer, T_SLASH) ) + while (lex_match (lexer, T_SLASH)) { - if ( lex_match_id (lexer, "ASSUMEDSTRWIDTH")) + if (lex_match_id (lexer, "ASSUMEDSTRWIDTH")) { lex_match (lexer, T_EQUALS); - sri->asw = lex_integer (lexer); - lex_get (lexer); + if (lex_force_int_range (lexer, "ASSUMEDSTRWIDTH", 1, 32767)) + { + opts->asw = lex_integer (lexer); + lex_get (lexer); + } } else if (lex_match_id (lexer, "SHEET")) { lex_match (lexer, T_EQUALS); if (lex_match_id (lexer, "NAME")) { - if ( ! lex_force_string (lexer) ) + if (! lex_force_string (lexer)) goto error; - sri->sheet_name = ss_xstrdup (lex_tokss (lexer)); - sri->sheet_index = -1; + opts->sheet_name = ss_xstrdup (lex_tokss (lexer)); + opts->sheet_index = -1; lex_get (lexer); } else if (lex_match_id (lexer, "INDEX")) { - sri->sheet_index = lex_integer (lexer); + if (!lex_force_int_range (lexer, "INDEX", 1, INT_MAX)) + goto error; + opts->sheet_index = lex_integer (lexer); lex_get (lexer); } else - goto error; + { + msg (SE, _("%s must be followed by either \"%s\" or \"%s\"."), + "/SHEET", "NAME", "INDEX"); + goto error; + } } else if (lex_match_id (lexer, "CELLRANGE")) { @@ -235,33 +287,41 @@ parse_spreadsheet (struct lexer *lexer) if (lex_match_id (lexer, "FULL")) { - sri->cell_range = NULL; + opts->cell_range = NULL; } else if (lex_match_id (lexer, "RANGE")) { - if ( ! lex_force_string (lexer) ) + if (! lex_force_string (lexer)) goto error; - sri->cell_range = ss_xstrdup (lex_tokss (lexer)); + opts->cell_range = ss_xstrdup (lex_tokss (lexer)); lex_get (lexer); } else - goto error; + { + msg (SE, _("%s must be followed by either \"%s\" or \"%s\"."), + "/CELLRANGE", "FULL", "RANGE"); + goto error; + } } else if (lex_match_id (lexer, "READNAMES")) { lex_match (lexer, T_EQUALS); - if ( lex_match_id (lexer, "ON")) + if (lex_match_id (lexer, "ON")) { - sri->read_names = true; + opts->read_names = true; } else if (lex_match_id (lexer, "OFF")) { - sri->read_names = false; + opts->read_names = false; } else - goto error; + { + msg (SE, _("%s must be followed by either \"%s\" or \"%s\"."), + "/READNAMES", "ON", "OFF"); + goto error; + } } else { @@ -270,11 +330,10 @@ parse_spreadsheet (struct lexer *lexer) } } - return sri; + return true; error: - destroy_spreadsheet_read_info (sri); - return NULL; + return false; } @@ -306,26 +365,30 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) struct dictionary *dict = dict_create (get_default_encoding ()); struct file_handle *fh = NULL; struct dfm_reader *reader = NULL; + char *encoding = NULL; char *name = NULL; int record; enum data_parser_type type; bool has_type; - lex_force_match (lexer, T_SLASH); + if (! lex_force_match (lexer, T_SLASH)) + goto error; if (!lex_force_match_id (lexer, "FILE")) goto error; - lex_force_match (lexer, T_EQUALS); + if (! lex_force_match (lexer, T_EQUALS)) + goto error; fh = fh_parse (lexer, FH_REF_FILE | FH_REF_INLINE, NULL); if (fh == NULL) goto error; - parser = data_parser_create (dict); + parser = data_parser_create (); has_type = false; data_parser_set_type (parser, DP_DELIMITED); data_parser_set_span (parser, false); data_parser_set_quotes (parser, ss_empty ()); + data_parser_set_quote_escape (parser, true); data_parser_set_empty_line_has_field (parser, true); for (;;) @@ -333,7 +396,18 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) if (!lex_force_match (lexer, T_SLASH)) goto error; - if (lex_match_id (lexer, "ARRANGEMENT")) + if (lex_match_id (lexer, "ENCODING")) + { + lex_match (lexer, T_EQUALS); + if (!lex_force_string (lexer)) + goto error; + + free (encoding); + encoding = ss_xstrdup (lex_tokss (lexer)); + + lex_get (lexer); + } + else if (lex_match_id (lexer, "ARRANGEMENT")) { bool ok; @@ -345,7 +419,7 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) DP_DELIMITED, &has_type); else { - lex_error (lexer, _("expecting %s or %s"), "FIXED", "DELIMITED"); + lex_error_expecting (lexer, "FIXED", "DELIMITED"); goto error; } if (!ok) @@ -354,13 +428,8 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) else if (lex_match_id (lexer, "FIRSTCASE")) { lex_match (lexer, T_EQUALS); - if (!lex_force_int (lexer)) + if (!lex_force_int_range (lexer, "FIRSTCASE", 1, INT_MAX)) goto error; - if (lex_integer (lexer) < 1) - { - msg (SE, _("Value of FIRSTCASE must be 1 or greater.")); - goto error; - } data_parser_set_skip (parser, lex_integer (lexer) - 1); lex_get (lexer); } @@ -383,7 +452,7 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) } else { - lex_error (lexer, _("expecting %s or %s"), "LINE", "VARIABLES"); + lex_error_expecting (lexer, "LINE", "VARIABLES"); goto error; } } @@ -392,13 +461,8 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) if (!set_type (parser, "FIXCASE", DP_FIXED, &has_type)) goto error; lex_match (lexer, T_EQUALS); - if (!lex_force_int (lexer)) + if (!lex_force_int_range (lexer, "FIXCASE", 1, INT_MAX)) goto error; - if (lex_integer (lexer) < 1) - { - msg (SE, _("Value of FIXCASE must be at least 1.")); - goto error; - } data_parser_set_records (parser, lex_integer (lexer)); lex_get (lexer); } @@ -407,33 +471,22 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) lex_match (lexer, T_EQUALS); if (lex_match (lexer, T_ALL)) { - data_parser_set_case_limit (parser, -1); - data_parser_set_case_percent (parser, 100); + /* Nothing to do. */ } else if (lex_match_id (lexer, "FIRST")) { if (!lex_force_int (lexer)) goto error; - if (lex_integer (lexer) < 1) - { - msg (SE, _("Value of FIRST must be at least 1.")); - goto error; - } - data_parser_set_case_limit (parser, lex_integer (lexer)); lex_get (lexer); } else if (lex_match_id (lexer, "PERCENT")) { if (!lex_force_int (lexer)) goto error; - if (lex_integer (lexer) < 1 || lex_integer (lexer) > 100) - { - msg (SE, _("Value of PERCENT must be between 1 and 100.")); - goto error; - } - data_parser_set_case_percent (parser, lex_integer (lexer)); lex_get (lexer); } + msg (SW, _("Ignoring obsolete IMPORTCASES subcommand. (N OF CASES " + "or SAMPLE may be used to substitute.)")); } else if (lex_match_id_n (lexer, "DELIMITERS", 4)) { @@ -487,14 +540,11 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) data_parser_set_quotes (parser, lex_tokss (lexer)); lex_get (lexer); } - else if (settings_get_syntax () == ENHANCED - && lex_match_id (lexer, "ESCAPE")) - data_parser_set_quote_escape (parser, true); else if (lex_match_id (lexer, "VARIABLES")) break; else { - lex_error (lexer, _("expecting %s"), "VARIABLES"); + lex_error_expecting (lexer, "VARIABLES"); goto error; } } @@ -510,48 +560,42 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) while (type == DP_FIXED && lex_match (lexer, T_SLASH)) { - if (!lex_force_int (lexer)) + if (!lex_force_int_range (lexer, NULL, record, + data_parser_get_records (parser))) goto error; - if (lex_integer (lexer) < record) - { - msg (SE, _("The record number specified, %ld, is at or " - "before the previous record, %d. Data " - "fields must be listed in order of " - "increasing record number."), - lex_integer (lexer), record); - goto error; - } - if (lex_integer (lexer) > data_parser_get_records (parser)) - { - msg (SE, _("The record number specified, %ld, exceeds " - "the number of records per case specified " - "on FIXCASE, %d."), - lex_integer (lexer), data_parser_get_records (parser)); - goto error; - } record = lex_integer (lexer); lex_get (lexer); } + const char * tstr = lex_tokcstr (lexer); + if (tstr == NULL) + { + lex_error (lexer, NULL); + goto error; + } + name = xstrdup (tstr); if (!lex_force_id (lexer) - || !dict_id_is_valid (dict, lex_tokcstr (lexer), true)) - goto error; - name = xstrdup (lex_tokcstr (lexer)); + || !dict_id_is_valid (dict, name, true)) + { + goto error; + } lex_get (lexer); - if (type == DP_DELIMITED) { if (!parse_format_specifier (lexer, &input) - || !fmt_check_input (&input)) - goto error; - - output = fmt_for_output_from_input (&input); + || !fmt_check_input (&input)) + { + goto error; + } + output = fmt_for_output_from_input (&input, + settings_get_fmt_settings ()); } else { char fmt_type_name[FMT_TYPE_LEN_MAX + 1]; enum fmt_type fmt_type; - int w, d; + uint16_t w; + uint8_t d; if (!parse_column_range (lexer, 0, &fc, &lc, NULL)) goto error; @@ -564,14 +608,12 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) msg (SE, _("Unknown format type `%s'."), fmt_type_name); goto error; } - /* Compose input format. */ input.type = fmt_type; input.w = lc - fc + 1; input.d = 0; if (!fmt_check_input (&input)) goto error; - /* Compose output format. */ if (w != 0) { @@ -582,9 +624,9 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) goto error; } else - output = fmt_for_output_from_input (&input); + output = fmt_for_output_from_input (&input, + settings_get_fmt_settings ()); } - v = dict_create_var (dict, name, fmt_var_width (&input)); if (v == NULL) { @@ -592,7 +634,6 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) goto error; } var_set_both_formats (v, &output); - if (type == DP_DELIMITED) data_parser_add_delimited_field (parser, &input, var_get_case_index (v), @@ -605,31 +646,28 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) } while (lex_token (lexer) != T_ENDCMD); - reader = dfm_open_reader (fh, lexer); + reader = dfm_open_reader (fh, lexer, encoding); if (reader == NULL) goto error; - data_parser_make_active_file (parser, ds, reader, dict); + data_parser_make_active_file (parser, ds, reader, dict, NULL, NULL); fh_unref (fh); + free (encoding); return CMD_SUCCESS; error: data_parser_destroy (parser); - dict_destroy (dict); + dict_unref (dict); fh_unref (fh); free (name); + free (encoding); return CMD_CASCADING_FAILURE; } -static void -destroy_spreadsheet_read_info (struct spreadsheet_read_info *sri) +static void +destroy_spreadsheet_read_info (struct spreadsheet_read_options *opts) { - if ( NULL == sri) - return; - - free (sri->sheet_name); - free (sri->cell_range); - free (sri->file_name); - free (sri); + free (opts->cell_range); + free (opts->sheet_name); }