X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fdata-io%2Fget-data.c;h=10d59aa374aa06cd29b30c3ea3e58bf528187099;hb=2814862a2c45a39f9822cf4c64ca3884822d064d;hp=eeb3827a58924dfa13eedd6bf2d2c2df43ffd8b5;hpb=691c25e36fd1ee722dd35419d6110e3876b99f9c;p=pspp diff --git a/src/language/data-io/get-data.c b/src/language/data-io/get-data.c index eeb3827a58..10d59aa374 100644 --- a/src/language/data-io/get-data.c +++ b/src/language/data-io/get-data.c @@ -1,5 +1,5 @@ /* PSPP - a program for statistical analysis. - Copyright (C) 2007, 2008, 2009, 2010 Free Software Foundation, Inc. + Copyright (C) 2007, 2008, 2009, 2010, 2011, 2012 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 @@ -18,35 +18,43 @@ #include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "xalloc.h" +#include + +#include "data/dataset.h" +#include "data/dictionary.h" +#include "data/format.h" +#include "data/gnumeric-reader.h" +#include "data/ods-reader.h" +#include "data/spreadsheet-reader.h" +#include "data/psql-reader.h" +#include "data/settings.h" +#include "language/command.h" +#include "language/data-io/data-parser.h" +#include "language/data-io/data-reader.h" +#include "language/data-io/file-handle.h" +#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" + +#include "gl/xalloc.h" #include "gettext.h" #define _(msgid) gettext (msgid) #define N_(msgid) (msgid) -static int parse_get_gnm (struct lexer *lexer, struct dataset *); +static struct spreadsheet_read_info *parse_spreadsheet (struct lexer *lexer); +static void destroy_spreadsheet_read_info (struct spreadsheet_read_info *); + static int parse_get_txt (struct lexer *lexer, struct dataset *); static int parse_get_psql (struct lexer *lexer, struct dataset *); int cmd_get_data (struct lexer *lexer, struct dataset *ds) { + char *tok = NULL; lex_force_match (lexer, T_SLASH); if (!lex_force_match_id (lexer, "TYPE")) @@ -54,14 +62,44 @@ cmd_get_data (struct lexer *lexer, struct dataset *ds) lex_force_match (lexer, T_EQUALS); - if (lex_match_id (lexer, "GNM")) - return parse_get_gnm (lexer, ds); - else if (lex_match_id (lexer, "TXT")) - return parse_get_txt (lexer, ds); + tok = strdup (lex_tokcstr (lexer)); + if (lex_match_id (lexer, "TXT")) + { + return parse_get_txt (lexer, ds); + } else if (lex_match_id (lexer, "PSQL")) - return parse_get_psql (lexer, ds); + { + return parse_get_psql (lexer, ds); + } + 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) + goto error; + + if ( 0 == strncasecmp (tok, "GNM", 3)) + reader = gnumeric_open_reader (sri, &dict); + else if (0 == strncasecmp (tok, "ODS", 3)) + reader = ods_open_reader (sri, &dict); + + if (reader) + { + dataset_set_dict (ds, dict); + dataset_set_source (ds, reader); + destroy_spreadsheet_read_info (sri); + free (tok); + return CMD_SUCCESS; + } + destroy_spreadsheet_read_info (sri); + } + else + msg (SE, _("Unsupported TYPE %s."), tok); - msg (SE, _("Unsupported TYPE %s"), lex_tokid (lexer)); + error: + free (tok); return CMD_FAILURE; } @@ -85,7 +123,7 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds) if (!lex_force_string (lexer)) goto error; - psql.conninfo = xstrdup (ds_cstr (lex_tokstr (lexer))); + psql.conninfo = ss_xstrdup (lex_tokss (lexer)); lex_get (lexer); @@ -113,7 +151,7 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds) if ( ! lex_force_string (lexer) ) goto error; - ds_put_substring (&psql.sql, lex_tokstr (lexer)->ss); + ds_put_substring (&psql.sql, lex_tokss (lexer)); lex_get (lexer); } } @@ -122,7 +160,10 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds) struct casereader *reader = psql_open_reader (&psql, &dict); if ( reader ) - proc_set_active_file (ds, reader, dict); + { + dataset_set_dict (ds, dict); + dataset_set_source (ds, reader); + } } ds_destroy (&psql.sql); @@ -138,10 +179,13 @@ parse_get_psql (struct lexer *lexer, struct dataset *ds) return CMD_FAILURE; } -static int -parse_get_gnm (struct lexer *lexer, struct dataset *ds) +static struct spreadsheet_read_info * +parse_spreadsheet (struct lexer *lexer) { - struct gnumeric_read_info gri = {NULL, NULL, NULL, 1, true, -1}; + struct spreadsheet_read_info *sri = xzalloc (sizeof *sri); + sri->sheet_index = 1; + sri->read_names = true; + sri->asw = -1; lex_force_match (lexer, T_SLASH); @@ -153,7 +197,7 @@ parse_get_gnm (struct lexer *lexer, struct dataset *ds) if (!lex_force_string (lexer)) goto error; - gri.file_name = xstrdup (ds_cstr (lex_tokstr (lexer))); + sri->file_name = utf8_to_filename (lex_tokcstr (lexer)); lex_get (lexer); @@ -162,7 +206,8 @@ parse_get_gnm (struct lexer *lexer, struct dataset *ds) if ( lex_match_id (lexer, "ASSUMEDSTRWIDTH")) { lex_match (lexer, T_EQUALS); - gri.asw = lex_integer (lexer); + sri->asw = lex_integer (lexer); + lex_get (lexer); } else if (lex_match_id (lexer, "SHEET")) { @@ -172,12 +217,15 @@ parse_get_gnm (struct lexer *lexer, struct dataset *ds) if ( ! lex_force_string (lexer) ) goto error; - gri.sheet_name = xstrdup (ds_cstr (lex_tokstr (lexer))); - gri.sheet_index = -1; + sri->sheet_name = ss_xstrdup (lex_tokss (lexer)); + sri->sheet_index = -1; + + lex_get (lexer); } else if (lex_match_id (lexer, "INDEX")) { - gri.sheet_index = lex_integer (lexer); + sri->sheet_index = lex_integer (lexer); + lex_get (lexer); } else goto error; @@ -188,15 +236,15 @@ parse_get_gnm (struct lexer *lexer, struct dataset *ds) if (lex_match_id (lexer, "FULL")) { - gri.cell_range = NULL; - lex_put_back (lexer, T_ID); + sri->cell_range = NULL; } else if (lex_match_id (lexer, "RANGE")) { if ( ! lex_force_string (lexer) ) goto error; - gri.cell_range = xstrdup (ds_cstr (lex_tokstr (lexer))); + sri->cell_range = ss_xstrdup (lex_tokss (lexer)); + lex_get (lexer); } else goto error; @@ -207,44 +255,30 @@ parse_get_gnm (struct lexer *lexer, struct dataset *ds) if ( lex_match_id (lexer, "ON")) { - gri.read_names = true; + sri->read_names = true; } else if (lex_match_id (lexer, "OFF")) { - gri.read_names = false; + sri->read_names = false; } else goto error; - lex_put_back (lexer, T_ID); } else { + lex_error (lexer, NULL); goto error; } - lex_get (lexer); } - { - struct dictionary *dict = NULL; - struct casereader *reader = gnumeric_open_reader (&gri, &dict); - - if ( reader ) - proc_set_active_file (ds, reader, dict); - } - - free (gri.file_name); - free (gri.sheet_name); - free (gri.cell_range); - return CMD_SUCCESS; + return sri; error: - - free (gri.file_name); - free (gri.sheet_name); - free (gri.cell_range); - return CMD_FAILURE; + destroy_spreadsheet_read_info (sri); + return NULL; } + static bool set_type (struct data_parser *parser, const char *subcommand, enum data_parser_type type, bool *has_type) @@ -270,9 +304,11 @@ static int parse_get_txt (struct lexer *lexer, struct dataset *ds) { struct data_parser *parser = NULL; - struct dictionary *dict = dict_create (); + 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; @@ -283,7 +319,7 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) if (!lex_force_match_id (lexer, "FILE")) goto error; lex_force_match (lexer, T_EQUALS); - fh = fh_parse (lexer, FH_REF_FILE | FH_REF_INLINE); + fh = fh_parse (lexer, FH_REF_FILE | FH_REF_INLINE, NULL); if (fh == NULL) goto error; @@ -299,7 +335,18 @@ 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; @@ -311,7 +358,7 @@ 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", NULL_SENTINEL); goto error; } if (!ok) @@ -349,7 +396,7 @@ 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", NULL_SENTINEL); goto error; } } @@ -415,7 +462,8 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) if (!lex_force_string (lexer)) goto error; - s = ds_ss (lex_tokstr (lexer)); + /* XXX should support multibyte UTF-8 characters */ + s = lex_tokss (lexer); if (ss_match_string (&s, ss_cstr ("\\t"))) ds_put_cstr (&hard_seps, "\t"); if (ss_match_string (&s, ss_cstr ("\\\\"))) @@ -440,15 +488,16 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) if (!lex_force_string (lexer)) goto error; + /* XXX should support multibyte UTF-8 characters */ if (settings_get_syntax () == COMPATIBLE - && ds_length (lex_tokstr (lexer)) != 1) + && ss_length (lex_tokss (lexer)) != 1) { msg (SE, _("In compatible syntax mode, the QUALIFIER string " "must contain exactly one character.")); goto error; } - data_parser_set_quotes (parser, ds_ss (lex_tokstr (lexer))); + data_parser_set_quotes (parser, lex_tokss (lexer)); lex_get (lexer); } else if (settings_get_syntax () == ENHANCED @@ -458,21 +507,19 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) break; else { - lex_error (lexer, _("expecting %s"), "VARIABLES"); + lex_error_expecting (lexer, "VARIABLES", NULL_SENTINEL); goto error; } } lex_match (lexer, T_EQUALS); - record = 1; type = data_parser_get_type (parser); do { - char name[VAR_NAME_LEN + 1]; struct fmt_spec input, output; - int fc, lc; struct variable *v; + int fc, lc; while (type == DP_FIXED && lex_match (lexer, T_SLASH)) { @@ -499,9 +546,10 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) lex_get (lexer); } - if (!lex_force_id (lexer)) + if (!lex_force_id (lexer) + || !dict_id_is_valid (dict, lex_tokcstr (lexer), true)) goto error; - strcpy (name, lex_tokid (lexer)); + name = xstrdup (lex_tokcstr (lexer)); lex_get (lexer); if (type == DP_DELIMITED) @@ -509,19 +557,46 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) if (!parse_format_specifier (lexer, &input) || !fmt_check_input (&input)) goto error; + + output = fmt_for_output_from_input (&input); } else { + char fmt_type_name[FMT_TYPE_LEN_MAX + 1]; + enum fmt_type fmt_type; + int w, d; + if (!parse_column_range (lexer, 0, &fc, &lc, NULL)) goto error; - if (!parse_format_specifier_name (lexer, &input.type)) + + /* Accept a format (e.g. F8.2) or just a type name (e.g. DOLLAR). */ + if (!parse_abstract_format_specifier (lexer, fmt_type_name, &w, &d)) goto error; + if (!fmt_from_name (fmt_type_name, &fmt_type)) + { + 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) + { + output.type = fmt_type; + output.w = w; + output.d = d; + if (!fmt_check_output (&output)) + goto error; + } + else + output = fmt_for_output_from_input (&input); } - output = fmt_for_output_from_input (&input); v = dict_create_var (dict, name, fmt_var_width (&input)); if (v == NULL) @@ -538,20 +613,38 @@ parse_get_txt (struct lexer *lexer, struct dataset *ds) else data_parser_add_fixed_field (parser, &input, var_get_case_index (v), name, record, fc); + free (name); + name = NULL; } 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); fh_unref (fh); + free (encoding); return CMD_SUCCESS; error: data_parser_destroy (parser); dict_destroy (dict); fh_unref (fh); + free (name); + free (encoding); return CMD_CASCADING_FAILURE; } + + +static void +destroy_spreadsheet_read_info (struct spreadsheet_read_info *sri) +{ + if ( NULL == sri) + return; + + free (sri->sheet_name); + free (sri->cell_range); + free (sri->file_name); + free (sri); +}