/* PSPP - a program for statistical analysis.
- Copyright (C) 1997-9, 2000, 2006 Free Software Foundation, Inc.
+ Copyright (C) 1997-9, 2000, 2006, 2009 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
#include <data/casereader.h>
#include <data/dictionary.h>
#include <data/file-handle-def.h>
+#include <data/file-name.h>
#include <data/format.h>
#include <data/missing-values.h>
+#include <data/short-names.h>
#include <data/value-labels.h>
#include <data/variable.h>
-#include <libpspp/alloc.h>
#include <libpspp/compiler.h>
#include <libpspp/hash.h>
-#include <libpspp/magic.h>
#include <libpspp/message.h>
#include <libpspp/misc.h>
#include <libpspp/pool.h>
#include <libpspp/str.h>
+#include "minmax.h"
+#include "xalloc.h"
+
#include "gettext.h"
#define _(msgid) gettext (msgid)
+#define N_(msgid) (msgid)
/* portable_to_local[PORTABLE] translates the given portable
character into the local character set. */
jmp_buf bail_out; /* longjmp() target for error handling. */
struct file_handle *fh; /* File handle. */
+ struct fh_lock *lock; /* Read lock for file. */
FILE *file; /* File stream. */
+ int line_length; /* Number of characters so far on this line. */
char cc; /* Current character. */
char *trans; /* 256-byte character set translation table. */
int var_cnt; /* Number of variables. */
int weight_index; /* 0-based index of weight variable, or -1. */
- int *widths; /* Variable widths, 0 for numeric. */
- size_t value_cnt; /* Number of `value's per case. */
+ struct caseproto *proto; /* Format of output cases. */
bool ok; /* Set false on I/O error. */
};
-static struct casereader_class por_file_casereader_class;
+static const struct casereader_class por_file_casereader_class;
static void
error (struct pfm_reader *r, const char *msg,...)
va_list args;
ds_init_empty (&text);
- ds_put_format (&text, _("portable file %s corrupt at offset %ld: "),
+ ds_put_format (&text, _("portable file %s corrupt at offset 0x%lx: "),
fh_get_file_name (r->fh), ftell (r->file));
va_start (args, msg);
ds_put_vformat (&text, msg, args);
longjmp (r->bail_out, 1);
}
+/* Displays MSG as an warning for the current position in
+ portable file reader R. */
+static void
+warning (struct pfm_reader *r, const char *msg, ...)
+{
+ struct msg m;
+ struct string text;
+ va_list args;
+
+ ds_init_empty (&text);
+ ds_put_format (&text, _("reading portable file %s at offset 0x%lx: "),
+ fh_get_file_name (r->fh), ftell (r->file));
+ va_start (args, msg);
+ ds_put_vformat (&text, msg, args);
+ va_end (args);
+
+ m.category = MSG_GENERAL;
+ m.severity = MSG_WARNING;
+ m.where.file_name = NULL;
+ m.where.line_number = 0;
+ m.text = ds_cstr (&text);
+
+ msg_emit (&m);
+}
+
+/* Close and destroy R.
+ Returns false if an error was detected on R, true otherwise. */
+static bool
+close_reader (struct pfm_reader *r)
+{
+ bool ok;
+ if (r == NULL)
+ return true;
+
+ if (r->file)
+ {
+ if (fn_close (fh_get_file_name (r->fh), r->file) == EOF)
+ {
+ msg (ME, _("Error closing portable file \"%s\": %s."),
+ fh_get_file_name (r->fh), strerror (errno));
+ r->ok = false;
+ }
+ r->file = NULL;
+ }
+
+ fh_unlock (r->lock);
+ fh_unref (r->fh);
+
+ ok = r->ok;
+ pool_destroy (r->pool);
+
+ return ok;
+}
+
/* Closes portable file reader R, after we're done with it. */
static void
-por_file_casereader_destroy (struct casereader *reader UNUSED, void *r_)
+por_file_casereader_destroy (struct casereader *reader, void *r_)
{
struct pfm_reader *r = r_;
- pool_destroy (r->pool);
+ if (!close_reader (r))
+ casereader_force_error (reader);
}
/* Read a single character into cur_char. */
{
int c;
- while ((c = getc (r->file)) == '\r' || c == '\n')
- continue;
+ /* Read the next character from the file.
+ Ignore carriage returns entirely.
+ Mostly ignore new-lines, but if a new-line occurs before the
+ line has reached 80 bytes in length, then treat the
+ "missing" bytes as spaces. */
+ for (;;)
+ {
+ while ((c = getc (r->file)) == '\r')
+ continue;
+ if (c != '\n')
+ break;
+
+ if (r->line_length < 80)
+ {
+ c = ' ';
+ ungetc ('\n', r->file);
+ break;
+ }
+ r->line_length = 0;
+ }
if (c == EOF)
error (r, _("unexpected end of file"));
if (r->trans != NULL)
c = r->trans[c];
r->cc = c;
+ r->line_length++;
}
/* Skip a single character if present, and return whether it was
static void read_version_data (struct pfm_reader *, struct pfm_read_info *);
static void read_variables (struct pfm_reader *, struct dictionary *);
static void read_value_label (struct pfm_reader *, struct dictionary *);
-void dump_dictionary (struct dictionary *);
+static void read_documents (struct pfm_reader *, struct dictionary *);
/* Reads the dictionary from file with handle H, and returns it in a
dictionary structure. This dictionary may be modified in order to
struct pfm_reader *volatile r = NULL;
*dict = dict_create ();
- if (!fh_open (fh, FH_REF_FILE, "portable file", "rs"))
- goto error;
/* Create and initialize reader. */
pool = pool_create ();
r = pool_alloc (pool, sizeof *r);
r->pool = pool;
- if (setjmp (r->bail_out))
- goto error;
- r->fh = fh;
- r->file = pool_fopen (r->pool, fh_get_file_name (r->fh), "rb");
+ r->fh = fh_ref (fh);
+ r->lock = NULL;
+ r->file = NULL;
+ r->line_length = 0;
r->weight_index = -1;
r->trans = NULL;
r->var_cnt = 0;
- r->widths = NULL;
- r->value_cnt = 0;
+ r->proto = NULL;
r->ok = true;
+ if (setjmp (r->bail_out))
+ goto error;
+
+ /* Lock file. */
+ /* TRANSLATORS: this fragment will be interpolated into
+ messages in fh_lock() that identify types of files. */
+ r->lock = fh_lock (fh, FH_REF_FILE, N_("portable file"), FH_ACC_READ, false);
+ if (r->lock == NULL)
+ goto error;
- /* Check that file open succeeded, prime reading. */
+ /* Open file. */
+ r->file = fn_open (fh_get_file_name (r->fh), "rb");
if (r->file == NULL)
{
msg (ME, _("An error occurred while opening \"%s\" for reading "
while (match (r, 'D'))
read_value_label (r, *dict);
+ /* Read documents. */
+ if (match (r, 'E'))
+ read_documents (r, *dict);
+
/* Check that we've made it to the data. */
if (!match (r, 'F'))
error (r, _("Data record expected."));
- r->value_cnt = dict_get_next_value_idx (*dict);
- return casereader_create_sequential (NULL, r->value_cnt, CASENUMBER_MAX,
+ r->proto = caseproto_ref_pool (dict_get_proto (*dict), r->pool);
+ return casereader_create_sequential (NULL, r->proto, CASENUMBER_MAX,
&por_file_casereader_class, r);
error:
- pool_destroy (r->pool);
+ close_reader (r);
dict_destroy (*dict);
*dict = NULL;
return NULL;
*buf = '\0';
}
+
+/* Reads a string into BUF, which must have room for 256
+ characters.
+ Returns the number of bytes read.
+*/
+static size_t
+read_bytes (struct pfm_reader *r, uint8_t *buf)
+{
+ int n = read_int (r);
+ if (n < 0 || n > 255)
+ error (r, _("Bad string length %d."), n);
+
+ while (n-- > 0)
+ {
+ *buf++ = r->cc;
+ advance (r);
+ }
+ return n;
+}
+
+
+
/* Reads a string and returns a copy of it allocated from R's
pool. */
static char *
static void
read_version_data (struct pfm_reader *r, struct pfm_read_info *info)
{
- static char empty_string[] = "";
- char *date, *time, *product, *author, *subproduct;
+ static const char empty_string[] = "";
+ char *date, *time;
+ const char *product, *author, *subproduct;
int i;
/* Read file. */
/* Validate file. */
if (strlen (date) != 8)
- error (r, _("Bad date string length %d."), (int) strlen (date));
+ error (r, _("Bad date string length %zu."), strlen (date));
if (strlen (time) != 6)
- error (r, _("Bad time string length %d."), (int) strlen (time));
+ error (r, _("Bad time string length %zu."), strlen (time));
/* Save file info. */
if (info != NULL)
checking that the format is appropriate for variable V. */
static struct fmt_spec
convert_format (struct pfm_reader *r, const int portable_format[3],
- struct variable *v)
+ struct variable *v, bool *report_error)
{
struct fmt_spec format;
bool ok;
if (!fmt_from_io (portable_format[0], &format.type))
- error (r, _("%s: Bad format specifier byte (%d)."),
- var_get_name (v), portable_format[0]);
+ {
+ if (*report_error)
+ warning (r, _("%s: Bad format specifier byte (%d). Variable "
+ "will be assigned a default format."),
+ var_get_name (v), portable_format[0]);
+ goto assign_default;
+ }
+
format.w = portable_format[1];
format.d = portable_format[2];
if (!ok)
{
- char fmt_string[FMT_STRING_LEN_MAX + 1];
- error (r, _("%s variable %s has invalid format specifier %s."),
- var_is_numeric (v) ? _("Numeric") : _("String"),
- var_get_name (v), fmt_to_string (&format, fmt_string));
- format = fmt_default_for_width (var_get_width (v));
+ if (*report_error)
+ {
+ char fmt_string[FMT_STRING_LEN_MAX + 1];
+ fmt_to_string (&format, fmt_string);
+ if (var_is_numeric (v))
+ warning (r, _("Numeric variable %s has invalid format "
+ "specifier %s."),
+ var_get_name (v), fmt_string);
+ else
+ warning (r, _("String variable %s with width %d has "
+ "invalid format specifier %s."),
+ var_get_name (v), var_get_width (v), fmt_string);
+ }
+ goto assign_default;
}
return format;
+
+assign_default:
+ *report_error = false;
+ return fmt_default_for_width (var_get_width (v));
}
-static union value parse_value (struct pfm_reader *, struct variable *);
+static void parse_value (struct pfm_reader *, int width, union value *);
/* Read information on all the variables. */
static void
error (r, _("Expected variable count record."));
r->var_cnt = read_int (r);
- if (r->var_cnt <= 0 || r->var_cnt == NOT_INT)
+ if (r->var_cnt <= 0)
error (r, _("Invalid number of variables %d."), r->var_cnt);
- r->widths = pool_nalloc (r->pool, r->var_cnt, sizeof *r->widths);
/* Purpose of this value is unknown. It is typically 161. */
read_int (r);
struct variable *v;
struct missing_values miss;
struct fmt_spec print, write;
+ bool report_error = true;
int j;
if (!match (r, '7'))
width = read_int (r);
if (width < 0)
error (r, _("Invalid variable width %d."), width);
- r->widths[i] = width;
read_string (r, name);
for (j = 0; j < 6; j++)
fmt[j] = read_int (r);
if (!var_is_valid_name (name, false) || *name == '#' || *name == '$')
- error (r, _("position %d: Invalid variable name `%s'."), i, name);
+ error (r, _("Invalid variable name `%s' in position %d."), name, i);
str_uppercase (name);
if (width < 0 || width > 255)
v = dict_create_var (dict, name, width);
if (v == NULL)
- error (r, _("Duplicate variable name %s."), name);
+ {
+ int i;
+ for (i = 1; i < 100000; i++)
+ {
+ char try_name[VAR_NAME_LEN + 1];
+ sprintf (try_name, "%.*s_%d", VAR_NAME_LEN - 6, name, i);
+ v = dict_create_var (dict, try_name, width);
+ if (v != NULL)
+ break;
+ }
+ if (v == NULL)
+ error (r, _("Duplicate variable name %s in position %d."), name, i);
+ warning (r, _("Duplicate variable name %s in position %d renamed "
+ "to %s."), name, i, var_get_name (v));
+ }
- print = convert_format (r, &fmt[0], v);
- write = convert_format (r, &fmt[3], v);
+ print = convert_format (r, &fmt[0], v, &report_error);
+ write = convert_format (r, &fmt[3], v, &report_error);
var_set_print_format (v, &print);
var_set_write_format (v, &write);
/* Range missing values. */
- mv_init (&miss, var_get_width (v));
+ mv_init (&miss, width);
if (match (r, 'B'))
{
double x = read_float (r);
double y = read_float (r);
- mv_add_num_range (&miss, x, y);
+ mv_add_range (&miss, x, y);
}
else if (match (r, 'A'))
- mv_add_num_range (&miss, read_float (r), HIGHEST);
+ mv_add_range (&miss, read_float (r), HIGHEST);
else if (match (r, '9'))
- mv_add_num_range (&miss, LOWEST, read_float (r));
+ mv_add_range (&miss, LOWEST, read_float (r));
/* Single missing values. */
while (match (r, '8'))
{
- union value value = parse_value (r, v);
+ int mv_width = MIN (width, 8);
+ union value value;
+
+ parse_value (r, mv_width, &value);
+ value_resize (&value, mv_width, width);
mv_add_value (&miss, &value);
+ value_destroy (&value, width);
}
var_set_missing_values (v, &miss);
+ mv_destroy (&miss);
if (match (r, 'C'))
{
}
}
-/* Parse a value for variable VV into value V. */
-static union value
-parse_value (struct pfm_reader *r, struct variable *vv)
+/* Parse a value of with WIDTH into value V. */
+static void
+parse_value (struct pfm_reader *r, int width, union value *v)
{
- union value v;
-
- if (var_is_alpha (vv))
+ value_init (v, width);
+ if (width > 0)
{
- char string[256];
- read_string (r, string);
- buf_copy_str_rpad (v.s, 8, string);
+ uint8_t buf[256];
+ size_t n_bytes = read_bytes (r, buf);
+ value_copy_buf_rpad (v, width, buf, n_bytes, ' ');
}
else
- v.f = read_float (r);
-
- return v;
+ v->f = read_float (r);
}
/* Parse a value label record and return success. */
if (v[i] == NULL)
error (r, _("Unknown variable %s while parsing value labels."), name);
- if (var_get_width (v[0]) != var_get_width (v[i]))
+ if (var_get_type (v[0]) != var_get_type (v[i]))
error (r, _("Cannot assign value labels to %s and %s, which "
- "have different variable types or widths."),
+ "have different variable types."),
var_get_name (v[0]), var_get_name (v[i]));
}
char label[256];
int j;
- val = parse_value (r, v[0]);
+ parse_value (r, var_get_width (v[0]), &val);
read_string (r, label);
- /* Assign the value_label's to each variable. */
+ /* Assign the value label to each variable. */
for (j = 0; j < nv; j++)
- {
- struct variable *var = v[j];
+ var_replace_value_label (v[j], &val, label);
- if (!var_add_value_label (var, &val, label))
- continue;
+ value_destroy (&val, var_get_width (v[0]));
+ }
+}
- if (var_is_numeric (var))
- error (r, _("Duplicate label for value %g for variable %s."),
- val.f, var_get_name (var));
- else
- error (r, _("Duplicate label for value `%.*s' for variable %s."),
- var_get_width (var), val.s, var_get_name (var));
- }
+/* Reads a set of documents from portable file R into DICT. */
+static void
+read_documents (struct pfm_reader *r, struct dictionary *dict)
+{
+ int line_cnt;
+ int i;
+
+ line_cnt = read_int (r);
+ for (i = 0; i < line_cnt; i++)
+ {
+ char line[256];
+ read_string (r, line);
+ dict_add_document_line (dict, line);
}
}
-/* Reads one case from portable file R into C. */
-static bool
-por_file_casereader_read (struct casereader *reader, void *r_, struct ccase *c)
+/* Reads and returns one case from portable file R. Returns a
+ null pointer on failure. */
+static struct ccase *
+por_file_casereader_read (struct casereader *reader, void *r_)
{
struct pfm_reader *r = r_;
+ struct ccase *volatile c;
size_t i;
- size_t idx;
- case_create (c, casereader_get_value_cnt (reader));
+ c = case_create (r->proto);
setjmp (r->bail_out);
if (!r->ok)
{
casereader_force_error (reader);
- case_destroy (c);
- return false;
+ case_unref (c);
+ return NULL;
}
/* Check for end of file. */
if (r->cc == 'Z')
{
- case_destroy (c);
- return false;
+ case_unref (c);
+ return NULL;
}
- idx = 0;
for (i = 0; i < r->var_cnt; i++)
{
- int width = r->widths[i];
+ int width = caseproto_get_width (r->proto, i);
if (width == 0)
- {
- case_data_rw_idx (c, idx)->f = read_float (r);
- idx++;
- }
+ case_data_rw_idx (c, i)->f = read_float (r);
else
{
- char string[256];
- read_string (r, string);
- buf_copy_str_rpad (case_data_rw_idx (c, idx)->s, width, string);
- idx += DIV_RND_UP (width, MAX_SHORT_STRING);
+ uint8_t buf[256];
+ size_t n_bytes = read_bytes (r, buf);
+ u8_buf_copy_rpad (case_str_rw_idx (c, i), width, buf, n_bytes, ' ');
}
}
- return true;
+ return c;
}
/* Returns true if FILE is an SPSS portable file,
{
unsigned char header[464];
char trans[256];
- int cooked_cnt, raw_cnt;
+ int cooked_cnt, raw_cnt, line_len;
int i;
cooked_cnt = raw_cnt = 0;
+ line_len = 0;
while (cooked_cnt < sizeof header)
{
int c = getc (file);
if (c == EOF || raw_cnt++ > 512)
return false;
- else if (c != '\n' && c != '\r')
- header[cooked_cnt++] = c;
+ else if (c == '\n')
+ {
+ while (line_len < 80 && cooked_cnt < sizeof header)
+ {
+ header[cooked_cnt++] = ' ';
+ line_len++;
+ }
+ line_len = 0;
+ }
+ else if (c != '\r')
+ {
+ header[cooked_cnt++] = c;
+ line_len++;
+ }
}
memset (trans, 0, 256);
return true;
}
-static struct casereader_class por_file_casereader_class =
+static const struct casereader_class por_file_casereader_class =
{
por_file_casereader_read,
por_file_casereader_destroy,
projects / pspp-builds.git / blobdiff