[crc32], [gl_crc32],
[Avoid making zlib call gnulib's crc32() instead of its own.])
-dnl Gnumeric support requires libxml2 and zlib.
+dnl Gnumeric and OpenDocument (read) support requires libxml2 and zlib.
if test $HAVE_LIBXML2 = yes && test $HAVE_ZLIB = yes; then
GNM_SUPPORT=yes
+ ODF_READ_SUPPORT=yes
AC_DEFINE(
[GNM_SUPPORT], [1],
[Define to 1 if building in support for reading Gnumeric files.])
+ AC_DEFINE(
+ [ODF_READ_SUPPORT], [1],
+ [Define to 1 if building in support for reading OpenDocument files.])
else
GNM_SUPPORT=no
+ ODF_READ_SUPPORT=no
fi
AC_SUBST([GNM_SUPPORT])
+AC_SUBST([ODF_READ_SUPPORT])
-dnl ODT support requires libxml2.
+dnl ODF support requires libxml2 (zlib is optional).
if test $HAVE_LIBXML2 = yes; then
AC_DEFINE(
- [ODT_SUPPORT], [1],
- [Define to 1 if building in support for writing ODT files.])
+ [ODF_WRITE_SUPPORT], [1],
+ [Define to 1 if building in support for writing OpenDocument files.])
fi
-AM_CONDITIONAL([ODT_SUPPORT], [test $HAVE_LIBXML2 = yes])
+AM_CONDITIONAL([ODF_WRITE_SUPPORT], [test $HAVE_LIBXML2 = yes])
AC_ARG_WITH(
gui_tools,
@display
GET DATA
- /TYPE=@{GNM,PSQL,TXT@}
+ /TYPE=@{GNM,ODS,PSQL,TXT@}
@dots{}additional subcommands depending on TYPE@dots{}
@end display
@item GNM
Spreadsheet files created by Gnumeric (@url{http://gnumeric.org}).
+@item ODS
+Spreadsheet files in OpenDocument format.
+
@item PSQL
Relations from PostgreSQL databases (@url{http://postgresql.org}).
separate sections below.
@menu
-* GET DATA /TYPE=GNM::
-* GET DATA /TYPE=PSQL::
-* GET DATA /TYPE=TXT::
+* GET DATA /TYPE=GNM/ODS:: Spreadsheets
+* GET DATA /TYPE=PSQL:: Databases
+* GET DATA /TYPE=TXT:: Delimited Text Files
@end menu
-@node GET DATA /TYPE=GNM
-@subsection Gnumeric Spreadsheet Files
+@node GET DATA /TYPE=GNM/ODS
+@subsection Spreadsheet Files
@display
-GET DATA /TYPE=GNM
+GET DATA /TYPE=@{GNM, ODS@}
/FILE=@{'file-name'@}
/SHEET=@{NAME 'sheet-name', INDEX n@}
/CELLRANGE=@{RANGE 'range', FULL@}
@end display
@cindex Gnumeric
+@cindex OpenDocument
@cindex spreadsheet files
-To use GET DATA to read a spreadsheet file created by Gnumeric
-(@url{http://gnumeric.org}), specify TYPE=GNM to indicate the file's
-format and use FILE to indicate the Gnumeric file to be read. All
-other subcommands are optional.
+
+Gnumeric spreadsheets (@url{http://gnumeric.org}), and spreadsheets
+in OpenDocument format
+(@url{http://libreplanet.org/wiki/Group:OpenDocument/Software})
+can be read using the GET DATA command.
+Use the TYPE subcommand to indicate the file's format.
+/TYPE=GNM indicates Gnumeric files,
+/TYPE=ODS indicates OpenDocument.
+The FILE subcommand is mandatory.
+Use it to specify the name file to be read.
+All other subcommands are optional.
The format of each variable is determined by the format of the spreadsheet
cell containing the first datum for the variable.
determined from the length of the string it contains, unless the
ASSUMEDVARWIDTH subcommand is given.
-
-The FILE subcommand is mandatory. Specify the name of the file
-to be read.
-
The SHEET subcommand specifies the sheet within the spreadsheet file to read.
There are two forms of the SHEET subcommand.
In the first form,
If @samp{/READNAMES=ON} is specified, then the contents of cells of
the first row are used as the names of the variables in which to store
-the data from subsequent rows.
-If the READNAMES command is omitted, or if @samp{/READNAMES=OFF} is
+the data from subsequent rows. This is the default.
+If @samp{/READNAMES=OFF} is
used, then the variables receive automatically assigned names.
The ASSUMEDVARWIDTH subcommand specifies the maximum width of string
src/data/make-file.h \
src/data/mrset.c \
src/data/mrset.h \
+ src/data/ods-reader.c \
+ src/data/ods-reader.h \
src/data/por-file-reader.c \
src/data/por-file-reader.h \
src/data/por-file-writer.c \
src/data/settings.h \
src/data/short-names.c \
src/data/short-names.h \
+ src/data/spreadsheet-reader.c \
+ src/data/spreadsheet-reader.h \
src/data/subcase.c \
src/data/subcase.h \
src/data/sys-file-encoding.c \
You should have received a copy of the GNU General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
-
-
#include <config.h>
#include "libpspp/message.h"
#define _(msgid) gettext (msgid)
#define N_(msgid) (msgid)
+#include "spreadsheet-reader.h"
#if !GNM_SUPPORT
struct casereader *
-gnumeric_open_reader (struct gnumeric_read_info *gri, struct dictionary **dict)
+gnumeric_open_reader (struct spreadsheet_read_info *gri, struct dictionary **dict)
{
- msg (ME, _("Support for Gnumeric files was not compiled into this installation of PSPP"));
+ msg (ME, _("Support for %s files was not compiled into this installation of PSPP"), "Gnumeric");
return NULL;
}
#include "gl/xalloc.h"
-/* Default width of string variables. */
-#define GNUMERIC_DEFAULT_WIDTH 8
-
static void gnm_file_casereader_destroy (struct casereader *, void *);
static struct ccase *gnm_file_casereader_read (struct casereader *, void *);
NULL,
};
-/* Convert a string, which is an integer encoded in base26
- IE, A=0, B=1, ... Z=25 to the integer it represents.
- ... except that in this scheme, digits with an exponent
- greater than 1 are implicitly incremented by 1, so
- AA = 0 + 1*26, AB = 1 + 1*26,
- ABC = 2 + 2*26 + 1*26^2 ....
-*/
-static int
-pseudo_base26 (const char *str)
-{
- int i;
- int multiplier = 1;
- int result = 0;
- int len = strlen (str);
-
- for ( i = len - 1 ; i >= 0; --i)
- {
- int mantissa = (str[i] - 'A');
-
- if ( mantissa < 0 || mantissa > 25 )
- return -1;
-
- if ( i != len - 1)
- mantissa++;
-
- result += mantissa * multiplier;
-
- multiplier *= 26;
- }
-
- return result;
-}
-
-
-
-/* Convert a cell reference in the form "A1:B2", to
- integers. A1 means column zero, row zero.
- B1 means column 1 row 0. AA1 means column 26, row 0.
-*/
-static bool
-convert_cell_ref (const char *ref,
- int *col0, int *row0,
- int *coli, int *rowi)
-{
- char startcol[5];
- char stopcol [5];
-
- int startrow;
- int stoprow;
-
- int n = sscanf (ref, "%4[a-zA-Z]%d:%4[a-zA-Z]%d",
- startcol, &startrow,
- stopcol, &stoprow);
- if ( n != 4)
- return false;
-
- str_uppercase (startcol);
- *col0 = pseudo_base26 (startcol);
- str_uppercase (stopcol);
- *coli = pseudo_base26 (stopcol);
- *row0 = startrow - 1;
- *rowi = stoprow - 1 ;
-
- return true;
-}
-
-
enum reader_state
{
STATE_INIT = 0, /* Initial state */
static void process_node (struct gnumeric_reader *r);
-#define _xml(X) (CHAR_CAST (const xmlChar *, X))
-
-#define _xmlchar_to_int(X) (atoi(CHAR_CAST (const char *, X)))
static void
gnm_file_casereader_destroy (struct casereader *reader UNUSED, void *r_)
};
struct casereader *
-gnumeric_open_reader (struct gnumeric_read_info *gri, struct dictionary **dict)
+gnumeric_open_reader (struct spreadsheet_read_info *gri, struct dictionary **dict)
{
unsigned long int vstart = 0;
int ret;
if (-1 == var_spec [idx].width )
var_spec [idx].width = (gri->asw == -1) ?
- ROUND_UP (strlen(text), GNUMERIC_DEFAULT_WIDTH) : gri->asw;
+ ROUND_UP (strlen(text), SPREADSHEET_DEFAULT_WIDTH) : gri->asw;
}
free (value);
/* Probably no data exists for this variable, so allocate a
default width */
if ( var_spec[i].width == -1 )
- var_spec[i].width = GNUMERIC_DEFAULT_WIDTH;
+ var_spec[i].width = SPREADSHEET_DEFAULT_WIDTH;
name = dict_make_unique_var_name (r->dict, var_spec[i].name, &vstart);
dict_create_var (r->dict, name, var_spec[i].width);
#include <stdbool.h>
struct casereader;
-
-
-struct gnumeric_read_info
-{
- char *sheet_name ; /* In UTF-8. */
- char *file_name ; /* In filename encoding. */
- char *cell_range ; /* In UTF-8. */
- int sheet_index ;
- bool read_names ;
- int asw ;
-};
-
struct dictionary;
+struct spreadsheet_read_info;
-struct casereader * gnumeric_open_reader (struct gnumeric_read_info *, struct dictionary **);
+struct casereader * gnumeric_open_reader (struct spreadsheet_read_info *, struct dictionary **);
#endif
--- /dev/null
+/* PSPP - a program for statistical analysis.
+ Copyright (C) 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
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
+
+#include <config.h>
+
+#include "libpspp/message.h"
+#include "libpspp/misc.h"
+
+#include "data/data-in.h"
+
+#include "gl/minmax.h"
+
+#include "gettext.h"
+#define _(msgid) gettext (msgid)
+#define N_(msgid) (msgid)
+
+#include "ods-reader.h"
+#include "spreadsheet-reader.h"
+
+#if !ODF_READ_SUPPORT
+
+struct casereader *
+ods_open_reader (struct spreadsheet_read_info *gri, struct dictionary **dict)
+{
+ msg (ME, _("Support for %s files was not compiled into this installation of PSPP"), "OpenDocument");
+
+ return NULL;
+}
+
+#else
+
+#include "libpspp/zip-reader.h"
+
+
+#include <assert.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <libxml/xmlreader.h>
+#include <zlib.h>
+
+#include "data/format.h"
+#include "data/case.h"
+#include "data/casereader-provider.h"
+#include "data/dictionary.h"
+#include "data/identifier.h"
+#include "data/value.h"
+#include "data/variable.h"
+#include "libpspp/i18n.h"
+#include "libpspp/str.h"
+
+#include "gl/xalloc.h"
+
+static void ods_file_casereader_destroy (struct casereader *, void *);
+
+static struct ccase *ods_file_casereader_read (struct casereader *, void *);
+
+static const struct casereader_class ods_file_casereader_class =
+ {
+ ods_file_casereader_read,
+ ods_file_casereader_destroy,
+ NULL,
+ NULL,
+ };
+
+enum reader_state
+ {
+ STATE_INIT = 0, /* Initial state */
+ STATE_SPREADSHEET, /* Found the start of the spreadsheet doc */
+ STATE_TABLE, /* Found the sheet that we actually want */
+ STATE_ROW, /* Found the start of the cell array */
+ STATE_CELL, /* Found a cell */
+ STATE_CELL_CONTENT /* Found a the text within a cell */
+ };
+
+struct ods_reader
+{
+ xmlTextReaderPtr xtr;
+
+ enum reader_state state;
+ bool sheet_found;
+ int row;
+ int col;
+ int node_type;
+ int sheet_index;
+
+ const xmlChar *target_sheet;
+ int target_sheet_index;
+
+ int start_row;
+ int start_col;
+ int stop_row;
+ int stop_col;
+
+ struct caseproto *proto;
+ struct dictionary *dict;
+ struct ccase *first_case;
+ bool used_first_case;
+ bool read_names;
+
+ struct string ods_errs;
+ int span;
+};
+
+static void process_node (struct ods_reader *r);
+
+static void
+ods_file_casereader_destroy (struct casereader *reader UNUSED, void *r_)
+{
+ struct ods_reader *r = r_;
+ if ( r == NULL)
+ return ;
+
+ if (r->xtr)
+ xmlFreeTextReader (r->xtr);
+
+ if ( ! ds_is_empty (&r->ods_errs))
+ msg (ME, ds_cstr (&r->ods_errs));
+
+ ds_destroy (&r->ods_errs);
+
+ if ( ! r->used_first_case )
+ case_unref (r->first_case);
+
+ caseproto_unref (r->proto);
+
+ free (r);
+}
+
+static void
+process_node (struct ods_reader *r)
+{
+ xmlChar *name = xmlTextReaderName (r->xtr);
+ if (name == NULL)
+ name = xmlStrdup (_xml ("--"));
+
+ r->node_type = xmlTextReaderNodeType (r->xtr);
+
+ switch ( r->state)
+ {
+ case STATE_INIT:
+ if (0 == xmlStrcasecmp (name, _xml("office:spreadsheet")) &&
+ XML_READER_TYPE_ELEMENT == r->node_type)
+ {
+ r->state = STATE_SPREADSHEET;
+ }
+ break;
+ case STATE_SPREADSHEET:
+ if (0 == xmlStrcasecmp (name, _xml("table:table")))
+ {
+ if (XML_READER_TYPE_ELEMENT == r->node_type)
+ {
+ r->col = -1;
+ r->row = -1;
+ ++r->sheet_index;
+ if ( r->target_sheet != NULL)
+ {
+ xmlChar *value = xmlTextReaderGetAttribute (r->xtr, _xml ("table:name"));
+ if ( 0 == xmlStrcmp (value, r->target_sheet))
+ {
+ r->sheet_found = true;
+ r->state = STATE_TABLE;
+ }
+ free (value);
+ }
+ else if (r->target_sheet_index == r->sheet_index)
+ {
+ r->sheet_found = true;
+ r->state = STATE_TABLE;
+ }
+ else if ( r->target_sheet_index == -1)
+ r->state = STATE_TABLE;
+ }
+ }
+ else if (XML_READER_TYPE_END_ELEMENT == r->node_type
+ && r->sheet_found)
+ {
+ r->state = STATE_INIT;
+ }
+ break;
+ case STATE_TABLE:
+ if (0 == xmlStrcasecmp (name, _xml("table:table-row")) )
+ {
+ if ( XML_READER_TYPE_ELEMENT == r->node_type)
+ {
+ if (! xmlTextReaderIsEmptyElement (r->xtr))
+ {
+ r->state = STATE_ROW;
+ }
+ r->row++;
+ r->span = 1;
+ }
+ }
+ else if (XML_READER_TYPE_END_ELEMENT == r->node_type)
+ {
+ r->state = STATE_SPREADSHEET;
+ }
+ break;
+ case STATE_ROW:
+ if (0 == xmlStrcasecmp (name, _xml ("table:table-cell")))
+ {
+ if ( XML_READER_TYPE_ELEMENT == r->node_type)
+ {
+ xmlChar *value =
+ xmlTextReaderGetAttribute (r->xtr,
+ _xml ("table:number-columns-repeated"));
+ r->col += r->span;
+ r->span = value ? _xmlchar_to_int (value) : 1;
+ free (value);
+ if (! xmlTextReaderIsEmptyElement (r->xtr))
+ {
+ r->state = STATE_CELL;
+ }
+ }
+ }
+ else if (XML_READER_TYPE_END_ELEMENT == r->node_type)
+ {
+ r->state = STATE_TABLE;
+ r->col = -1;
+ /* Set the span back to the default */
+ r->span = 1;
+ }
+ break;
+ case STATE_CELL:
+ if (0 == xmlStrcasecmp (name, _xml("text:p")))
+ {
+ if ( XML_READER_TYPE_ELEMENT == r->node_type)
+ {
+ r->state = STATE_CELL_CONTENT;
+ }
+ }
+ else if (XML_READER_TYPE_END_ELEMENT == r->node_type)
+ {
+ r->state = STATE_ROW;
+ }
+ break;
+ case STATE_CELL_CONTENT:
+ if (XML_READER_TYPE_TEXT != r->node_type)
+ r->state = STATE_CELL;
+ break;
+ default:
+ break;
+ };
+
+ xmlFree (name);
+}
+
+/*
+ A struct containing the parameters of a cell's value
+ parsed from the xml
+*/
+struct xml_value
+{
+ xmlChar *type;
+ xmlChar *value;
+ xmlChar *text;
+};
+
+struct var_spec
+{
+ char *name;
+ struct xml_value firstval;
+};
+
+
+/* Determine the width that a xmv should probably have */
+static int
+xmv_to_width (const struct xml_value *xmv, int fallback)
+{
+ int width = SPREADSHEET_DEFAULT_WIDTH;
+
+ /* Non-strings always have zero width */
+ if (xmv->type != NULL && 0 != xmlStrcmp (xmv->type, _xml("string")))
+ return 0;
+
+ if ( fallback != -1)
+ return fallback;
+
+ if ( xmv->value )
+ width = ROUND_UP (xmlStrlen (xmv->value),
+ SPREADSHEET_DEFAULT_WIDTH);
+ else if ( xmv->text)
+ width = ROUND_UP (xmlStrlen (xmv->text),
+ SPREADSHEET_DEFAULT_WIDTH);
+
+ return width;
+}
+
+/*
+ Sets the VAR of case C, to the value corresponding to the xml data
+ */
+static void
+convert_xml_to_value (struct ccase *c, const struct variable *var,
+ const struct xml_value *xmv)
+{
+ union value *v = case_data_rw (c, var);
+
+ if (xmv->value == NULL && xmv->text == NULL)
+ value_set_missing (v, var_get_width (var));
+ else if ( var_is_alpha (var))
+ /* Use the text field, because it seems that there is no
+ value field for strings */
+ value_copy_str_rpad (v, var_get_width (var), xmv->text, ' ');
+ else
+ {
+ const struct fmt_spec *fmt = var_get_write_format (var);
+ enum fmt_category fc = fmt_get_category (fmt->type);
+
+ assert ( fc != FMT_CAT_STRING);
+
+ const char *text = xmv->value ? CHAR_CAST (const char *, xmv->value):
+ CHAR_CAST (const char *, xmv->text);
+
+ data_in (ss_cstr (text), "UTF-8",
+ fmt->type,
+ v,
+ var_get_width (var),
+ "UTF-8");
+ }
+}
+
+
+struct casereader *
+ods_open_reader (struct spreadsheet_read_info *gri, struct dictionary **dict)
+{
+ int ret = 0;
+ xmlChar *type = NULL;
+ unsigned long int vstart = 0;
+ casenumber n_cases = CASENUMBER_MAX;
+ int i;
+ struct var_spec *var_spec = NULL;
+ int n_var_specs = 0;
+
+ struct ods_reader *r = xzalloc (sizeof *r);
+
+ r->read_names = gri->read_names;
+ ds_init_empty (&r->ods_errs);
+
+ struct zip_reader *zreader = zip_reader_create (gri->file_name, &r->ods_errs);
+ struct zip_member *content = NULL;
+
+ if ( NULL == zreader)
+ {
+ msg (ME, _("Error opening `%s' for reading as a OpenDocument spreadsheet file: %s."),
+ gri->file_name, ds_cstr (&r->ods_errs));
+
+ goto error;
+ }
+
+ content = zip_member_open (zreader, "content.xml");
+ if ( NULL == content)
+ {
+ msg (ME, _("Could not extract OpenDocument spreadsheet from file `%s': %s."),
+ gri->file_name, ds_cstr (&r->ods_errs));
+
+ goto error;
+ }
+
+ zip_member_ref (content);
+
+ r->xtr = xmlReaderForIO ((xmlInputReadCallback) zip_member_read,
+ (xmlInputCloseCallback) zip_member_finish,
+ content, NULL, NULL, XML_PARSE_RECOVER);
+
+ if ( r->xtr == NULL)
+ {
+ goto error;
+ }
+
+ if ( gri->cell_range )
+ {
+ if ( ! convert_cell_ref (gri->cell_range,
+ &r->start_col, &r->start_row,
+ &r->stop_col, &r->stop_row))
+ {
+ msg (SE, _("Invalid cell range `%s'"),
+ gri->cell_range);
+ goto error;
+ }
+ }
+ else
+ {
+ r->start_col = 0;
+ r->start_row = 0;
+ r->stop_col = -1;
+ r->stop_row = -1;
+ }
+
+ r->state = STATE_INIT;
+ r->target_sheet = BAD_CAST gri->sheet_name;
+ r->target_sheet_index = gri->sheet_index;
+ r->row = r->col = -1;
+ r->sheet_index = 0;
+
+
+ /* If CELLRANGE was given, then we know how many variables should be read */
+ if ( r->stop_col != -1 )
+ {
+ n_var_specs = r->stop_col - r->start_col + 1;
+ var_spec = xrealloc (var_spec, sizeof (*var_spec) * n_var_specs);
+ }
+
+
+ /* Advance to the start of the cells for the target sheet */
+ while ( (r->row < r->start_row ))
+ {
+ if (1 != (ret = xmlTextReaderRead (r->xtr)))
+ break;
+
+ process_node (r);
+ }
+
+ if (ret < 1)
+ {
+ msg (MW, _("Selected sheet or range of spreadsheet `%s' is empty."),
+ gri->file_name);
+ goto error;
+ }
+
+ if ( gri->read_names)
+ {
+ while (1 == (ret = xmlTextReaderRead (r->xtr)))
+ {
+ int idx;
+ process_node (r);
+ if ( r->row > r->start_row)
+ break;
+
+ if (r->col == -1 && r->row == r->start_row)
+ break;
+
+ if ( r->col < r->start_col)
+ continue;
+
+ idx = r->col - r->start_col;
+
+ if (r->state == STATE_CELL_CONTENT
+ &&
+ XML_READER_TYPE_TEXT == r->node_type)
+ {
+ xmlChar *value = xmlTextReaderValue (r->xtr);
+ if ( idx >= n_var_specs)
+ {
+
+ var_spec = xrealloc (var_spec, sizeof (*var_spec) * (idx + 1));
+
+ /* xrealloc (unlike realloc) doesn't initialise its memory to 0 */
+ memset (var_spec + n_var_specs * sizeof (*var_spec),
+ 0,
+ (n_var_specs - idx + 1) * sizeof (*var_spec));
+ n_var_specs = idx + 1;
+ }
+ var_spec[idx].firstval.text = 0;
+ var_spec[idx].firstval.value = 0;
+ var_spec[idx].firstval.type = 0;
+
+ var_spec [idx].name = strdup (CHAR_CAST (const char *, value));
+ free (value);
+ value = NULL;
+ }
+ }
+ }
+
+ xmlChar *val_string = NULL;
+ /* Read in the first row of data */
+ while (1 == xmlTextReaderRead (r->xtr))
+ {
+ int idx;
+ process_node (r);
+ if ( r->row >= r->start_row + 1 + gri->read_names)
+ break;
+
+ if ( r->col < r->start_col)
+ continue;
+
+ if ( r->col - r->start_col + 1 > n_var_specs)
+ continue;
+
+ idx = r->col - r->start_col;
+
+ if ( r->state == STATE_CELL &&
+ XML_READER_TYPE_ELEMENT == r->node_type)
+ {
+ type = xmlTextReaderGetAttribute (r->xtr, _xml ("office:value-type"));
+ val_string = xmlTextReaderGetAttribute (r->xtr, _xml ("office:value"));
+ }
+
+ if ( r->state == STATE_CELL_CONTENT &&
+ XML_READER_TYPE_TEXT == r->node_type)
+ {
+ var_spec [idx].firstval.type = type;
+ var_spec [idx].firstval.text = xmlTextReaderValue (r->xtr);
+ var_spec [idx].firstval.value = val_string;
+ val_string = NULL;
+ type = NULL;
+ }
+ }
+
+ /* Create the dictionary and populate it */
+ *dict = r->dict = dict_create (
+ CHAR_CAST (const char *, xmlTextReaderConstEncoding (r->xtr)));
+
+ for (i = 0 ; i < n_var_specs ; ++i )
+ {
+ struct fmt_spec fmt;
+ struct variable *var = NULL;
+ char *name = dict_make_unique_var_name (r->dict, var_spec[i].name, &vstart);
+ int width = xmv_to_width (&var_spec[i].firstval, gri->asw);
+ dict_create_var (r->dict, name, width);
+ free (name);
+
+ var = dict_get_var (r->dict, i);
+
+ if ( 0 == xmlStrcmp (var_spec[i].firstval.type, _xml("date")))
+ {
+ fmt.type = FMT_DATE;
+ fmt.d = 0;
+ fmt.w = 20;
+ }
+ else
+ fmt = fmt_default_for_width (width);
+
+ var_set_both_formats (var, &fmt);
+ }
+
+ /* Create the first case, and cache it */
+ r->used_first_case = false;
+
+ if ( n_var_specs == 0 )
+ {
+ msg (MW, _("Selected sheet or range of spreadsheet `%s' is empty."),
+ gri->file_name);
+ goto error;
+ }
+
+ r->proto = caseproto_ref (dict_get_proto (r->dict));
+ r->first_case = case_create (r->proto);
+ case_set_missing (r->first_case);
+
+ for ( i = 0 ; i < n_var_specs ; ++i )
+ {
+ const struct variable *var = dict_get_var (r->dict, i);
+
+ convert_xml_to_value (r->first_case, var, &var_spec[i].firstval);
+ }
+
+ zip_reader_destroy (zreader);
+
+ for ( i = 0 ; i < n_var_specs ; ++i )
+ {
+ free (var_spec[i].firstval.type);
+ free (var_spec[i].firstval.value);
+ free (var_spec[i].firstval.text);
+ free (var_spec[i].name);
+ }
+
+ free (var_spec);
+
+ return casereader_create_sequential
+ (NULL,
+ r->proto,
+ n_cases,
+ &ods_file_casereader_class, r);
+
+ error:
+
+ zip_reader_destroy (zreader);
+
+ for ( i = 0 ; i < n_var_specs ; ++i )
+ {
+ free (var_spec[i].firstval.type);
+ free (var_spec[i].firstval.value);
+ free (var_spec[i].firstval.text);
+ free (var_spec[i].name);
+ }
+
+ free (var_spec);
+
+ return NULL;
+}
+
+
+/* Reads and returns one case from READER's file. Returns a null
+ pointer on failure. */
+static struct ccase *
+ods_file_casereader_read (struct casereader *reader UNUSED, void *r_)
+{
+ struct ccase *c = NULL;
+ xmlChar *val_string = NULL;
+ struct ods_reader *r = r_;
+ int current_row = r->row;
+
+ if ( r->row == -1)
+ return NULL;
+
+ if ( !r->used_first_case )
+ {
+ r->used_first_case = true;
+ return r->first_case;
+ }
+
+
+ if ( r->state > STATE_INIT)
+ {
+ c = case_create (r->proto);
+ case_set_missing (c);
+ }
+
+ while (1 == xmlTextReaderRead (r->xtr))
+ {
+ process_node (r);
+ if ( r->row > current_row)
+ {
+ break;
+ }
+ if ( r->col < r->start_col || (r->stop_col != -1 && r->col > r->stop_col))
+ {
+ continue;
+ }
+ if ( r->col - r->start_col >= caseproto_get_n_widths (r->proto))
+ {
+ continue;
+ }
+ if ( r->stop_row != -1 && r->row > r->stop_row)
+ {
+ continue;
+ }
+ if ( r->state == STATE_CELL &&
+ r->node_type == XML_READER_TYPE_ELEMENT )
+ {
+ val_string = xmlTextReaderGetAttribute (r->xtr, _xml ("office:value"));
+ }
+
+ if ( r->state == STATE_CELL_CONTENT && r->node_type == XML_READER_TYPE_TEXT )
+ {
+ int col;
+ struct xml_value *xmv = xzalloc (sizeof *xmv);
+ xmv->text = xmlTextReaderValue (r->xtr);
+ xmv->value = val_string;
+ val_string = NULL;
+
+ for (col = 0; col < r->span ; ++col)
+ {
+ const int idx = r->col + col - r->start_col;
+
+ const struct variable *var = dict_get_var (r->dict, idx);
+
+ convert_xml_to_value (c, var, xmv);
+ }
+ free (xmv->text);
+ free (xmv->value);
+ free (xmv);
+ }
+
+ if ( r->state < STATE_TABLE)
+ break;
+ }
+
+ if (NULL == c || (r->stop_row != -1 && r->row > r->stop_row + 1))
+ {
+ case_unref (c);
+ return NULL;
+ }
+ else
+ {
+ return c;
+ }
+}
+#endif
--- /dev/null
+/* PSPP - a program for statistical analysis.
+ Copyright (C) 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
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
+
+#ifndef ODS_READ_H
+#define ODS_READ_H 1
+
+struct casereader;
+struct dictionary;
+struct spreadsheet_read_info;
+
+struct casereader * ods_open_reader (struct spreadsheet_read_info *, struct dictionary **);
+
+
+#endif
--- /dev/null
+/* PSPP - a program for statistical analysis.
+ 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
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
+
+#include <config.h>
+
+#include "spreadsheet-reader.h"
+
+#include <libpspp/str.h>
+#include <stdio.h>
+#include <string.h>
+
+/* Convert a string, which is an integer encoded in base26
+ IE, A=0, B=1, ... Z=25 to the integer it represents.
+ ... except that in this scheme, digits with an exponent
+ greater than 1 are implicitly incremented by 1, so
+ AA = 0 + 1*26, AB = 1 + 1*26,
+ ABC = 2 + 2*26 + 1*26^2 ....
+*/
+int
+pseudo_base26 (const char *str)
+{
+ int i;
+ int multiplier = 1;
+ int result = 0;
+ int len = strlen (str);
+
+ for ( i = len - 1 ; i >= 0; --i)
+ {
+ int mantissa = (str[i] - 'A');
+
+ if ( mantissa < 0 || mantissa > 25 )
+ return -1;
+
+ if ( i != len - 1)
+ mantissa++;
+
+ result += mantissa * multiplier;
+
+ multiplier *= 26;
+ }
+
+ return result;
+}
+
+
+/* Convert a cell reference in the form "A1:B2", to
+ integers. A1 means column zero, row zero.
+ B1 means column 1 row 0. AA1 means column 26, row 0.
+*/
+bool
+convert_cell_ref (const char *ref,
+ int *col0, int *row0,
+ int *coli, int *rowi)
+{
+ char startcol[5];
+ char stopcol [5];
+
+ int startrow;
+ int stoprow;
+
+ int n = sscanf (ref, "%4[a-zA-Z]%d:%4[a-zA-Z]%d",
+ startcol, &startrow,
+ stopcol, &stoprow);
+ if ( n != 4)
+ return false;
+
+ str_uppercase (startcol);
+ *col0 = pseudo_base26 (startcol);
+ str_uppercase (stopcol);
+ *coli = pseudo_base26 (stopcol);
+ *row0 = startrow - 1;
+ *rowi = stoprow - 1 ;
+
+ return true;
+}
+
--- /dev/null
+/* PSPP - a program for statistical analysis.
+ Copyright (C) 2007, 2010 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
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version.
+
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU General Public License for more details.
+
+ You should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
+
+#ifndef SPREADSHEET_READ_H
+#define SPREADSHEET_READ_H 1
+
+#include <stdbool.h>
+
+/* Default width of string variables. */
+#define SPREADSHEET_DEFAULT_WIDTH 8
+
+struct spreadsheet_read_info
+{
+ char *sheet_name ; /* In UTF-8. */
+ char *file_name ; /* In filename encoding. */
+ char *cell_range ; /* In UTF-8. */
+ int sheet_index ;
+ bool read_names ;
+ int asw ;
+};
+
+int pseudo_base26 (const char *str);
+
+bool convert_cell_ref (const char *ref,
+ int *col0, int *row0,
+ int *coli, int *rowi);
+
+
+#define _xml(X) (CHAR_CAST (const xmlChar *, X))
+
+#define _xmlchar_to_int(X) (atoi(CHAR_CAST (const char *, X)))
+
+
+#endif
#include <stdlib.h>
+#include <string.h>
+
#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"
#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"))
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_tokcstr (lexer));
+ error:
+ free (tok);
return CMD_FAILURE;
}
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);
if (!lex_force_string (lexer))
goto error;
- gri.file_name = utf8_to_filename (lex_tokcstr (lexer));
+ sri->file_name = utf8_to_filename (lex_tokcstr (lexer));
lex_get (lexer);
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"))
if ( ! lex_force_string (lexer) )
goto error;
- gri.sheet_name = ss_xstrdup (lex_tokss (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
if (lex_match_id (lexer, "FULL"))
{
- gri.cell_range = NULL;
+ sri->cell_range = NULL;
}
else if (lex_match_id (lexer, "RANGE"))
{
if ( ! lex_force_string (lexer) )
goto error;
- gri.cell_range = ss_xstrdup (lex_tokss (lexer));
+ sri->cell_range = ss_xstrdup (lex_tokss (lexer));
lex_get (lexer);
}
else
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;
}
}
- {
- struct dictionary *dict = NULL;
- struct casereader *reader = gnumeric_open_reader (&gri, &dict);
-
- if ( reader )
- {
- dataset_set_dict (ds, dict);
- dataset_set_source (ds, reader);
- }
- }
-
- 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)
free (name);
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);
+}
src/output/charts/roc-chart-cairo.c \
src/output/charts/scree-cairo.c
endif
-if ODT_SUPPORT
+if ODF_WRITE_SUPPORT
src_output_liboutput_la_SOURCES += src/output/odt.c
endif
# Variables used internally by the testsuite.
EXEEXT='@EXEEXT@'
GNM_SUPPORT='@GNM_SUPPORT@'
+ODF_READ_SUPPORT='@ODF_READ_SUPPORT@'
PERL='@PERL@'
WITH_PERL_MODULE='@WITH_PERL_MODULE@'
host='@host@'
tests/data/num-out.expected.cmp.gz \
tests/data/v13.sav \
tests/data/v14.sav \
- tests/language/data-io/Book1.gnm.unzipped
+ tests/language/data-io/Book1.gnm.unzipped \
+ tests/language/data-io/test.ods
CLEANFILES += *.save pspp.* foo*
tests/language/data-io/data-reader.at \
tests/language/data-io/dataset.at \
tests/language/data-io/file-handle.at \
- tests/language/data-io/get-data-gnm.at \
+ tests/language/data-io/get-data-spreadsheet.at \
tests/language/data-io/get-data-psql.at \
tests/language/data-io/get-data-txt.at \
tests/language/data-io/get.at \
+++ /dev/null
-AT_BANNER([GET DATA /TYPE=GNM])
-
-AT_SETUP([GET DATA /TYPE=GNM with CELLRANGE])
-AT_SKIP_IF([test "$GNM_SUPPORT" = no])
-AT_CHECK([gzip -c $top_srcdir/tests/language/data-io/Book1.gnm.unzipped > Book1.gnumeric])
-AT_DATA([get-data.sps], [dnl
-GET DATA /TYPE=gnm /FILE='Book1.gnumeric' /READNAMES=off /SHEET=name 'This' /CELLRANGE=range 'g9:i13' .
-DISPLAY VARIABLES.
-LIST.
-])
-AT_CHECK([pspp -o pspp.csv get-data.sps])
-AT_CHECK([cat pspp.csv], [0], [dnl
-Variable,Description,,Position
-VAR001,Format: F8.2,,1
-,Measure: Scale,,
-,Display Alignment: Right,,
-,Display Width: 8,,
-VAR002,Format: A8,,2
-,Measure: Nominal,,
-,Display Alignment: Left,,
-,Display Width: 8,,
-VAR003,Format: F8.2,,3
-,Measure: Scale,,
-,Display Alignment: Right,,
-,Display Width: 8,,
-
-Table: Data List
-VAR001,VAR002,VAR003
-.00,fred ,20.00
-1.00,11 ,21.00
-2.00,twelve ,22.00
-3.00,13 ,23.00
-4.00,14 ,24.00
-])
-AT_CLEANUP
-
-AT_SETUP([GET DATA /TYPE=GNM with CELLRANGE and READNAMES])
-AT_SKIP_IF([test "$GNM_SUPPORT" = no])
-AT_CHECK([gzip -c $top_srcdir/tests/language/data-io/Book1.gnm.unzipped > Book1.gnumeric])
-AT_DATA([get-data.sps], [dnl
-GET DATA /TYPE=gnm /FILE='Book1.gnumeric' /READNAMES=on /SHEET=name 'This' /CELLRANGE=range 'g8:i13' .
-DISPLAY VARIABLES.
-LIST.
-])
-AT_CHECK([pspp -o pspp.csv get-data.sps])
-AT_CHECK([cat pspp.csv], [0], [dnl
-Variable,Description,,Position
-V1,Format: F8.2,,1
-,Measure: Scale,,
-,Display Alignment: Right,,
-,Display Width: 8,,
-V2,Format: A8,,2
-,Measure: Nominal,,
-,Display Alignment: Left,,
-,Display Width: 8,,
-VAR001,Format: F8.2,,3
-,Measure: Scale,,
-,Display Alignment: Right,,
-,Display Width: 8,,
-
-Table: Data List
-V1,V2,VAR001
-.00,fred ,20.00
-1.00,11 ,21.00
-2.00,twelve ,22.00
-3.00,13 ,23.00
-4.00,14 ,24.00
-])
-AT_CLEANUP
-
-AT_SETUP([GET DATA /TYPE=GNM without CELLRANGE])
-AT_SKIP_IF([test "$GNM_SUPPORT" = no])
-AT_CHECK([gzip -c $top_srcdir/tests/language/data-io/Book1.gnm.unzipped > Book1.gnumeric])
-AT_DATA([get-data.sps], [dnl
-GET DATA /TYPE=gnm /FILE='Book1.gnumeric' /SHEET=index 3.
-DISPLAY VARIABLES.
-LIST.
-])
-AT_CHECK([pspp -o pspp.csv get-data.sps])
-AT_CHECK([cat pspp.csv], [0], [dnl
-Variable,Description,,Position
-name,Format: A8,,1
-,Measure: Nominal,,
-,Display Alignment: Left,,
-,Display Width: 8,,
-id,Format: F8.2,,2
-,Measure: Scale,,
-,Display Alignment: Right,,
-,Display Width: 8,,
-height,Format: F8.2,,3
-,Measure: Scale,,
-,Display Alignment: Right,,
-,Display Width: 8,,
-
-Table: Data List
-name,id,height
-fred ,.00,23.40
-bert ,1.00,.56
-charlie ,2.00,. @&t@
-dick ,3.00,-34.09
-])
-AT_CLEANUP
-
-AT_SETUP([GET DATA /TYPE=GNM with missing data])
-AT_SKIP_IF([test "$GNM_SUPPORT" = no])
-AT_CHECK([gzip -c $top_srcdir/tests/language/data-io/Book1.gnm.unzipped > Book1.gnumeric])
-AT_DATA([get-data.sps], [dnl
-* This sheet has no data in one of its variables
-GET DATA /TYPE=gnm /FILE='Book1.gnumeric' /READNAMES=on /SHEET=index 5.
-DISPLAY VARIABLES.
-LIST.
-])
-AT_CHECK([pspp -o pspp.csv get-data.sps])
-AT_CHECK([cat pspp.csv], [0], [dnl
-Variable,Description,,Position
-vone,Format: F8.2,,1
-,Measure: Scale,,
-,Display Alignment: Right,,
-,Display Width: 8,,
-vtwo,Format: F8.2,,2
-,Measure: Scale,,
-,Display Alignment: Right,,
-,Display Width: 8,,
-vthree,Format: A8,,3
-,Measure: Nominal,,
-,Display Alignment: Left,,
-,Display Width: 8,,
-v4,Format: F8.2,,4
-,Measure: Scale,,
-,Display Alignment: Right,,
-,Display Width: 8,,
-
-Table: Data List
-vone,vtwo,vthree,v4
-1.00,3.00,,5.00
-2.00,4.00,,6.00
-])
-AT_CLEANUP
-
-AT_SETUP([GET DATA /TYPE=GNM with empty sheet])
-AT_SKIP_IF([test "$GNM_SUPPORT" = no])
-AT_CHECK([gzip -c $top_srcdir/tests/language/data-io/Book1.gnm.unzipped > Book1.gnumeric])
-AT_DATA([get-data.sps], [dnl
-* This sheet is empty
-GET DATA /TYPE=gnm /FILE='Book1.gnumeric' /SHEET=name 'Empty'.
-])
-AT_CHECK([pspp -o pspp.csv get-data.sps], [0], [dnl
-warning: Selected sheet or range of spreadsheet `Book1.gnumeric' is empty.
-])
-AT_CLEANUP
-
-AT_SETUP([GET DATA /TYPE=GNM with nonexistent sheet])
-AT_SKIP_IF([test "$GNM_SUPPORT" = no])
-AT_CHECK([gzip -c $top_srcdir/tests/language/data-io/Book1.gnm.unzipped > Book1.gnumeric])
-AT_DATA([get-data.sps], [dnl
-* This sheet doesnt exist.
-GET DATA /TYPE=gnm /FILE='Book1.gnumeric' /SHEET=name 'foobarxx'.
-])
-AT_CHECK([pspp -o pspp.csv get-data.sps], [0], [dnl
-warning: Selected sheet or range of spreadsheet `Book1.gnumeric' is empty.
-])
-AT_CLEANUP
--- /dev/null
+
+m4_define([SPREADSHEET_TEST_PREP],[dnl
+ m4_if($1,[GNM],[dnl
+ AT_CHECK([gzip -c $top_srcdir/tests/language/data-io/Book1.gnm.unzipped > Book1.gnumeric])dnl
+ m4_define([testsheet],[Book1.gnumeric])dnl
+ AT_SKIP_IF([test n$GNM_SUPPORT != nyes])dnl
+ ]) dnl
+ m4_if($1,[ODS],[dnl
+ AT_CHECK([cp $top_srcdir/tests/language/data-io/test.ods test.ods])dnl
+ m4_define([testsheet],[test.ods])dnl
+ AT_SKIP_IF([test n$ODF_READ_SUPPORT != nyes])dnl
+ ])dnl
+])
+
+m4_define([CHECK_SPREADSHEET_READER],
+ [dnl
+AT_SETUP([GET DATA /TYPE=$1 with CELLRANGE])
+SPREADSHEET_TEST_PREP($1)
+AT_DATA([get-data.sps], [dnl
+GET DATA /TYPE=$1 /FILE='testsheet' /READNAMES=off /SHEET=name 'This' /CELLRANGE=range 'g9:i13' .
+DISPLAY VARIABLES.
+LIST.
+])
+AT_CHECK([pspp -o pspp.csv get-data.sps])
+AT_CHECK([cat pspp.csv], [0], [dnl
+Variable,Description,,Position
+VAR001,Format: F8.2,,1
+,Measure: Scale,,
+,Display Alignment: Right,,
+,Display Width: 8,,
+VAR002,Format: A8,,2
+,Measure: Nominal,,
+,Display Alignment: Left,,
+,Display Width: 8,,
+VAR003,Format: F8.2,,3
+,Measure: Scale,,
+,Display Alignment: Right,,
+,Display Width: 8,,
+
+Table: Data List
+VAR001,VAR002,VAR003
+.00,fred ,20.00
+1.00,11 ,21.00
+2.00,twelve ,22.00
+3.00,13 ,23.00
+4.00,14 ,24.00
+])
+AT_CLEANUP
+
+AT_SETUP([GET DATA /TYPE=$1 with CELLRANGE and READNAMES])
+SPREADSHEET_TEST_PREP($1)
+AT_DATA([get-data.sps], [dnl
+GET DATA /TYPE=$1 /FILE='testsheet' /READNAMES=on /SHEET=name 'This' /CELLRANGE=range 'g8:i13' .
+DISPLAY VARIABLES.
+LIST.
+])
+AT_CHECK([pspp -o pspp.csv get-data.sps])
+AT_CHECK([cat pspp.csv], [0], [dnl
+Variable,Description,,Position
+V1,Format: F8.2,,1
+,Measure: Scale,,
+,Display Alignment: Right,,
+,Display Width: 8,,
+V2,Format: A8,,2
+,Measure: Nominal,,
+,Display Alignment: Left,,
+,Display Width: 8,,
+VAR001,Format: F8.2,,3
+,Measure: Scale,,
+,Display Alignment: Right,,
+,Display Width: 8,,
+
+Table: Data List
+V1,V2,VAR001
+.00,fred ,20.00
+1.00,11 ,21.00
+2.00,twelve ,22.00
+3.00,13 ,23.00
+4.00,14 ,24.00
+])
+AT_CLEANUP
+
+AT_SETUP([GET DATA /TYPE=$1 without CELLRANGE])
+SPREADSHEET_TEST_PREP($1)
+AT_DATA([get-data.sps], [dnl
+GET DATA /TYPE=$1 /FILE='testsheet' /SHEET=index 3.
+DISPLAY VARIABLES.
+LIST.
+])
+AT_CHECK([pspp -o pspp.csv get-data.sps])
+AT_CHECK([cat pspp.csv], [0], [dnl
+Variable,Description,,Position
+name,Format: A8,,1
+,Measure: Nominal,,
+,Display Alignment: Left,,
+,Display Width: 8,,
+id,Format: F8.2,,2
+,Measure: Scale,,
+,Display Alignment: Right,,
+,Display Width: 8,,
+height,Format: F8.2,,3
+,Measure: Scale,,
+,Display Alignment: Right,,
+,Display Width: 8,,
+
+Table: Data List
+name,id,height
+fred ,.00,23.40
+bert ,1.00,.56
+charlie ,2.00,. @&t@
+dick ,3.00,-34.09
+])
+AT_CLEANUP
+
+AT_SETUP([GET DATA /TYPE=$1 with missing data])
+SPREADSHEET_TEST_PREP($1)
+AT_DATA([get-data.sps], [dnl
+* This sheet has no data in one of its variables
+GET DATA /TYPE=$1 /FILE='testsheet' /READNAMES=on /SHEET=index 5.
+DISPLAY VARIABLES.
+LIST.
+])
+AT_CHECK([pspp -o pspp.csv get-data.sps])
+AT_CHECK([cat pspp.csv], [0], [dnl
+Variable,Description,,Position
+vone,Format: F8.2,,1
+,Measure: Scale,,
+,Display Alignment: Right,,
+,Display Width: 8,,
+vtwo,Format: F8.2,,2
+,Measure: Scale,,
+,Display Alignment: Right,,
+,Display Width: 8,,
+vthree,Format: A8,,3
+,Measure: Nominal,,
+,Display Alignment: Left,,
+,Display Width: 8,,
+v4,Format: F8.2,,4
+,Measure: Scale,,
+,Display Alignment: Right,,
+,Display Width: 8,,
+
+Table: Data List
+vone,vtwo,vthree,v4
+1.00,3.00,,5.00
+2.00,4.00,,6.00
+])
+AT_CLEANUP
+
+AT_SETUP([GET DATA /TYPE=$1 with empty sheet])
+SPREADSHEET_TEST_PREP($1)
+AT_DATA([get-data.sps], [dnl
+* This sheet is empty
+GET DATA /TYPE=$1 /FILE='testsheet' /SHEET=name 'Empty'.
+])
+AT_CHECK([pspp -o pspp.csv get-data.sps], [0], [dnl
+warning: Selected sheet or range of spreadsheet `testsheet' is empty.
+])
+AT_CLEANUP
+
+AT_SETUP([GET DATA /TYPE=$1 with nonexistent sheet])
+SPREADSHEET_TEST_PREP($1)
+AT_DATA([get-data.sps], [dnl
+* This sheet doesnt exist.
+GET DATA /TYPE=$1 /FILE='testsheet' /SHEET=name 'foobarxx'.
+])
+AT_CHECK([pspp -o pspp.csv get-data.sps], [0], [dnl
+warning: Selected sheet or range of spreadsheet `testsheet' is empty.
+])
+AT_CLEANUP
+])
+
+
+AT_BANNER([GET DATA Spreadsheet /TYPE=GNM])
+
+CHECK_SPREADSHEET_READER([GNM])
+
+AT_BANNER([GET DATA Spreadsheet /TYPE=ODS])
+
+CHECK_SPREADSHEET_READER([ODS])
+
projects / pspp / commitdiff