X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fdata-io%2Fdata-parser.c;h=aea3bbd0374693ca6bd1846aaa96ce9cfb041ca3;hb=61eeaf756db35a5d25fff81c607d977f000409a1;hp=800ae57b50db3e027a82396ce243e4604cf45f5f;hpb=38993354cabb6fc37bb882be92f9a49e9aeb4c88;p=pspp-builds.git diff --git a/src/language/data-io/data-parser.c b/src/language/data-io/data-parser.c index 800ae57b..aea3bbd0 100644 --- a/src/language/data-io/data-parser.c +++ b/src/language/data-io/data-parser.c @@ -1,5 +1,5 @@ /* PSPP - a program for statistical analysis. - Copyright (C) 2007, 2009, 2010 Free Software Foundation, Inc. + Copyright (C) 2007, 2009, 2010, 2011 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 @@ -16,24 +16,24 @@ #include -#include +#include "language/data-io/data-parser.h" #include #include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include +#include "data/casereader-provider.h" +#include "data/data-in.h" +#include "data/dataset.h" +#include "data/dictionary.h" +#include "data/format.h" +#include "data/file-handle-def.h" +#include "data/settings.h" +#include "language/data-io/data-reader.h" +#include "libpspp/message.h" +#include "libpspp/str.h" +#include "output/tab.h" -#include "xalloc.h" +#include "gl/xalloc.h" #include "gettext.h" #define _(msgid) gettext (msgid) @@ -395,7 +395,6 @@ data_parser_parse (struct data_parser *parser, struct dfm_reader *reader, && dfm_get_percent_read (reader) >= parser->percent_cases) return false; - dfm_push (reader); if (parser->type == DP_DELIMITED) { if (parser->span) @@ -405,7 +404,6 @@ data_parser_parse (struct data_parser *parser, struct dfm_reader *reader, } else retval = parse_fixed (parser, reader, c); - dfm_pop (reader); return retval; } @@ -452,19 +450,19 @@ cut_field (const struct data_parser *parser, struct dfm_reader *reader, } *first_column = dfm_column_start (reader); - if (ss_find_char (parser->quotes, ss_first (p)) != SIZE_MAX) + if (ss_find_byte (parser->quotes, ss_first (p)) != SIZE_MAX) { /* Quoted field. */ - int quote = ss_get_char (&p); + int quote = ss_get_byte (&p); if (!ss_get_until (&p, quote, field)) msg (SW, _("Quoted string extends beyond end of line.")); if (parser->quote_escape && ss_first (p) == quote) { ds_assign_substring (tmp, *field); - while (ss_match_char (&p, quote)) + while (ss_match_byte (&p, quote)) { struct substring ss; - ds_put_char (tmp, quote); + ds_put_byte (tmp, quote); if (!ss_get_until (&p, quote, &ss)) msg (SW, _("Quoted string extends beyond end of line.")); ds_put_substring (tmp, ss); @@ -477,17 +475,17 @@ cut_field (const struct data_parser *parser, struct dfm_reader *reader, if present. */ ss_ltrim (&p, parser->soft_seps); if (!ss_is_empty (p) - && ss_find_char (parser->hard_seps, ss_first (p)) != SIZE_MAX) + && ss_find_byte (parser->hard_seps, ss_first (p)) != SIZE_MAX) ss_advance (&p, 1); } else { /* Regular field. */ - ss_get_chars (&p, ss_cspan (p, ds_ss (&parser->any_sep)), field); + ss_get_bytes (&p, ss_cspan (p, ds_ss (&parser->any_sep)), field); *last_column = *first_column + ss_length (*field); if (!ss_ltrim (&p, parser->soft_seps) || ss_is_empty (p) - || ss_find_char (parser->hard_seps, p.string[0]) != SIZE_MAX) + || ss_find_byte (parser->hard_seps, p.string[0]) != SIZE_MAX) { /* Advance past a trailing hard separator, regardless of whether one actually existed. If @@ -502,6 +500,26 @@ cut_field (const struct data_parser *parser, struct dfm_reader *reader, return true; } +static void +parse_error (const struct dfm_reader *reader, const struct field *field, + int first_column, int last_column, char *error) +{ + struct msg m; + + m.category = MSG_C_DATA; + m.severity = MSG_S_WARNING; + m.file_name = CONST_CAST (char *, dfm_get_file_name (reader)); + m.first_line = dfm_get_line_number (reader); + m.last_line = m.first_line + 1; + m.first_column = first_column; + m.last_column = last_column; + m.text = xasprintf (_("Data for variable %s is not valid as format %s: %s"), + field->name, fmt_name (field->format.type), error); + msg_emit (&m); + + free (error); +} + /* Reads a case from READER into C, parsing it according to fixed-format syntax rules in PARSER. Returns true if successful, false at end of file or on I/O error. */ @@ -536,13 +554,16 @@ parse_fixed (const struct data_parser *parser, struct dfm_reader *reader, struct substring s = ss_substr (line, f->first_column - 1, f->format.w); union value *value = case_data_rw_idx (c, f->case_idx); - - data_in (s, input_encoding, f->format.type, - f->first_column, f->first_column + f->format.w, - value, fmt_var_width (&f->format), output_encoding); - - data_in_imply_decimals (s, input_encoding, f->format.type, - f->format.d, value); + char *error = data_in (s, input_encoding, f->format.type, + value, fmt_var_width (&f->format), + output_encoding); + + if (error == NULL) + data_in_imply_decimals (s, input_encoding, f->format.type, + f->format.d, value); + else + parse_error (reader, f, f->first_column, + f->first_column + f->format.w, error); } dfm_forward_record (reader); @@ -567,6 +588,7 @@ parse_delimited_span (const struct data_parser *parser, { struct substring s; int first_column, last_column; + char *error; /* Cut out a field and read in a new record if necessary. */ while (!cut_field (parser, reader, @@ -584,9 +606,11 @@ parse_delimited_span (const struct data_parser *parser, } } - data_in (s, input_encoding, f->format.type, first_column, last_column, - case_data_rw_idx (c, f->case_idx), - fmt_var_width (&f->format), output_encoding); + error = data_in (s, input_encoding, f->format.type, + case_data_rw_idx (c, f->case_idx), + fmt_var_width (&f->format), output_encoding); + if (error != NULL) + parse_error (reader, f, first_column, last_column, error); } ds_destroy (&tmp); return true; @@ -612,6 +636,8 @@ parse_delimited_no_span (const struct data_parser *parser, for (f = parser->fields; f < end; f++) { int first_column, last_column; + char *error; + if (!cut_field (parser, reader, &first_column, &last_column, &tmp, &s)) { if (f < end - 1 && settings_get_undefined ()) @@ -625,9 +651,11 @@ parse_delimited_no_span (const struct data_parser *parser, goto exit; } - data_in (s, input_encoding, f->format.type, first_column, last_column, - case_data_rw_idx (c, f->case_idx), - fmt_var_width (&f->format), output_encoding); + error = data_in (s, input_encoding, f->format.type, + case_data_rw_idx (c, f->case_idx), + fmt_var_width (&f->format), output_encoding); + if (error != NULL) + parse_error (reader, f, first_column, last_column, error); } s = dfm_get_record (reader); @@ -734,7 +762,7 @@ struct data_parser_casereader static const struct casereader_class data_parser_casereader_class; -/* Replaces DS's active file by an input program that reads data +/* Replaces DS's active dataset by an input program that reads data from READER according to the rules in PARSER, using DICT as the underlying dictionary. Ownership of PARSER and READER is transferred to the input program, and ownership of DICT is @@ -754,7 +782,8 @@ data_parser_make_active_file (struct data_parser *parser, struct dataset *ds, casereader = casereader_create_sequential (NULL, r->proto, CASENUMBER_MAX, &data_parser_casereader_class, r); - proc_set_active_file (ds, casereader, dict); + dataset_set_dict (ds, dict); + dataset_set_source (ds, casereader); } static struct ccase *