X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fdata-io%2Finpt-pgm.c;h=0301d7d057aa77ca000a36abc51937ab638d982e;hb=693ac90cdac91d29870f303b88763a3685b3f341;hp=c2e5dc0f721438a7af412fc936e19cb20a99b1d1;hpb=cc57a28ef6796ae9a64ef80d453f72126956d49d;p=pspp diff --git a/src/language/data-io/inpt-pgm.c b/src/language/data-io/inpt-pgm.c index c2e5dc0f72..0301d7d057 100644 --- a/src/language/data-io/inpt-pgm.c +++ b/src/language/data-io/inpt-pgm.c @@ -1,5 +1,5 @@ /* PSPP - a program for statistical analysis. - Copyright (C) 1997-9, 2000, 2009 Free Software Foundation, Inc. + Copyright (C) 1997-9, 2000, 2009, 2010, 2011, 2012, 2013 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 @@ -16,61 +16,46 @@ #include -#include - #include #include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "xalloc.h" +#include "data/case.h" +#include "data/caseinit.h" +#include "data/casereader-provider.h" +#include "data/dataset.h" +#include "data/dictionary.h" +#include "data/session.h" +#include "data/transformations.h" +#include "data/variable.h" +#include "language/command.h" +#include "language/data-io/data-reader.h" +#include "language/data-io/file-handle.h" +#include "language/data-io/inpt-pgm.h" +#include "language/expressions/public.h" +#include "language/lexer/lexer.h" +#include "libpspp/assertion.h" +#include "libpspp/compiler.h" +#include "libpspp/message.h" +#include "libpspp/misc.h" +#include "libpspp/str.h" + +#include "gl/xalloc.h" #include "gettext.h" #define _(msgid) gettext (msgid) -/* Private result codes for use within INPUT PROGRAM. */ -enum cmd_result_extensions - { - CMD_END_INPUT_PROGRAM = CMD_PRIVATE_FIRST, - CMD_END_CASE - }; - /* Indicates how a `union value' should be initialized. */ -enum value_init_type - { - INP_NUMERIC = 01, /* Numeric. */ - INP_STRING = 0, /* String. */ - - INP_INIT_ONCE = 02, /* Initialize only once. */ - INP_REINIT = 0, /* Reinitialize for each iteration. */ - }; - struct input_program_pgm { + struct session *session; + struct dataset *ds; struct trns_chain *trns_chain; enum trns_result restart; casenumber case_nr; /* Incremented by END CASE transformation. */ struct caseinit *init; - size_t value_cnt; + struct caseproto *proto; }; static void destroy_input_program (struct input_program_pgm *); @@ -103,60 +88,85 @@ cmd_input_program (struct lexer *lexer, struct dataset *ds) { struct input_program_pgm *inp; bool saw_END_CASE = false; + bool saw_END_FILE = false; + bool saw_DATA_LIST = false; - proc_discard_active_file (ds); - if (lex_token (lexer) != '.') + if (!lex_match (lexer, T_ENDCMD)) return lex_end_of_command (lexer); inp = xmalloc (sizeof *inp); + inp->session = session_create (dataset_session (ds)); + inp->ds = dataset_create (inp->session, "INPUT PROGRAM"); inp->trns_chain = NULL; inp->init = NULL; + inp->proto = NULL; inside_input_program = true; - for (;;) + while (!lex_match_phrase (lexer, "END INPUT PROGRAM")) { - enum cmd_result result = cmd_parse_in_state (lexer, ds, CMD_STATE_INPUT_PROGRAM); - if (result == CMD_END_INPUT_PROGRAM) - break; - else if (result == CMD_END_CASE) + enum cmd_result result; + + result = cmd_parse_in_state (lexer, inp->ds, CMD_STATE_INPUT_PROGRAM); + switch (result) { - emit_END_CASE (ds, inp); + case CMD_DATA_LIST: + saw_DATA_LIST = true; + break; + + case CMD_END_CASE: + emit_END_CASE (inp->ds, inp); saw_END_CASE = true; - } - else if (cmd_result_is_failure (result) && result != CMD_FAILURE) - { - if (result == CMD_EOF) - msg (SE, _("Unexpected end-of-file within INPUT PROGRAM.")); - inside_input_program = false; - proc_discard_active_file (ds); - destroy_input_program (inp); - return result; + break; + + case CMD_END_FILE: + saw_END_FILE = true; + break; + + case CMD_FAILURE: + break; + + default: + if (cmd_result_is_failure (result) + && lex_get_error_mode (lexer) != LEX_ERROR_TERMINAL) + { + if (result == CMD_EOF) + msg (SE, _("Unexpected end-of-file within INPUT PROGRAM.")); + inside_input_program = false; + destroy_input_program (inp); + return result; + } } } if (!saw_END_CASE) - emit_END_CASE (ds, inp); + emit_END_CASE (inp->ds, inp); inside_input_program = false; - if (dict_get_next_value_idx (dataset_dict (ds)) == 0) + if (!saw_DATA_LIST && !saw_END_FILE) + { + msg (SE, _("Input program must contain DATA LIST or END FILE.")); + destroy_input_program (inp); + return CMD_FAILURE; + } + if (dict_get_next_value_idx (dataset_dict (inp->ds)) == 0) { msg (SE, _("Input program did not create any variables.")); - proc_discard_active_file (ds); destroy_input_program (inp); return CMD_FAILURE; } - inp->trns_chain = proc_capture_transformations (ds); + inp->trns_chain = proc_capture_transformations (inp->ds); trns_chain_finalize (inp->trns_chain); inp->restart = TRNS_CONTINUE; /* Figure out how to initialize each input case. */ inp->init = caseinit_create (); - caseinit_mark_for_init (inp->init, dataset_dict (ds)); - inp->value_cnt = dict_get_next_value_idx (dataset_dict (ds)); + caseinit_mark_for_init (inp->init, dataset_dict (inp->ds)); + inp->proto = caseproto_ref (dict_get_proto (dataset_dict (inp->ds))); - proc_set_active_file_data ( - ds, casereader_create_sequential (NULL, inp->value_cnt, CASENUMBER_MAX, + dataset_set_dict (ds, dict_clone (dataset_dict (inp->ds))); + dataset_set_source ( + ds, casereader_create_sequential (NULL, inp->proto, CASENUMBER_MAX, &input_program_casereader_class, inp)); return CMD_SUCCESS; @@ -165,8 +175,12 @@ cmd_input_program (struct lexer *lexer, struct dataset *ds) int cmd_end_input_program (struct lexer *lexer UNUSED, struct dataset *ds UNUSED) { - assert (in_input_program ()); - return CMD_END_INPUT_PROGRAM; + /* Inside INPUT PROGRAM, this should get caught at the top of the loop in + cmd_input_program(). + + Outside of INPUT PROGRAM, the command parser should reject this + command. */ + NOT_REACHED (); } /* Returns true if STATE is valid given the transformations that @@ -187,7 +201,7 @@ static struct ccase * input_program_casereader_read (struct casereader *reader UNUSED, void *inp_) { struct input_program_pgm *inp = inp_; - struct ccase *c = case_create (inp->value_cnt); + struct ccase *c = case_create (inp->proto); do { @@ -215,8 +229,10 @@ destroy_input_program (struct input_program_pgm *pgm) { if (pgm != NULL) { + session_destroy (pgm->session); trns_chain_destroy (pgm->trns_chain); caseinit_destroy (pgm->init); + caseproto_unref (pgm->proto); free (pgm); } } @@ -243,9 +259,9 @@ int cmd_end_case (struct lexer *lexer, struct dataset *ds UNUSED) { assert (in_input_program ()); - if (lex_token (lexer) == '.') + if (lex_token (lexer) == T_ENDCMD) return CMD_END_CASE; - return lex_end_of_command (lexer); + return CMD_SUCCESS; } /* Outputs the current case */ @@ -272,52 +288,65 @@ cmd_reread (struct lexer *lexer, struct dataset *ds) struct file_handle *fh; /* File to be re-read. */ struct expression *e; /* Expression for column to set. */ struct reread_trns *t; /* Created transformation. */ + char *encoding = NULL; fh = fh_get_default_handle (); e = NULL; - while (lex_token (lexer) != '.') + while (lex_token (lexer) != T_ENDCMD) { if (lex_match_id (lexer, "COLUMN")) { - lex_match (lexer, '='); + lex_match (lexer, T_EQUALS); if (e) { - msg (SE, _("COLUMN subcommand multiply specified.")); - expr_free (e); - return CMD_CASCADING_FAILURE; + lex_sbc_only_once ("COLUMN"); + goto error; } e = expr_parse (lexer, ds, EXPR_NUMBER); if (!e) - return CMD_CASCADING_FAILURE; + goto error; } else if (lex_match_id (lexer, "FILE")) { - lex_match (lexer, '='); + lex_match (lexer, T_EQUALS); fh_unref (fh); - fh = fh_parse (lexer, FH_REF_FILE | FH_REF_INLINE); + fh = fh_parse (lexer, FH_REF_FILE | FH_REF_INLINE, NULL); if (fh == NULL) - { - expr_free (e); - return CMD_CASCADING_FAILURE; - } + goto error; + } + else 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 { lex_error (lexer, NULL); - expr_free (e); - return CMD_CASCADING_FAILURE; + goto error; } } t = xmalloc (sizeof *t); - t->reader = dfm_open_reader (fh, lexer); + t->reader = dfm_open_reader (fh, lexer, encoding); t->column = e; add_transformation (ds, reread_trns_proc, reread_trns_free, t); fh_unref (fh); + free (encoding); return CMD_SUCCESS; + +error: + expr_free (e); + free (encoding); + return CMD_CASCADING_FAILURE; } /* Executes a REREAD transformation. */ @@ -356,13 +385,13 @@ reread_trns_free (void *t_) /* Parses END FILE command. */ int -cmd_end_file (struct lexer *lexer, struct dataset *ds) +cmd_end_file (struct lexer *lexer UNUSED, struct dataset *ds) { assert (in_input_program ()); add_transformation (ds, end_file_trns_proc, NULL, NULL); - return lex_end_of_command (lexer); + return CMD_END_FILE; } /* Executes an END FILE transformation. */