X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fdata%2Fsys-file-writer.c;h=1a65e3c067efc5688d912c0184d3e73be1fa59ed;hb=50f245ab3b7e42ae79ea4076ad7a2bbb97841cc6;hp=3e0d3499c9cd543450929e1b5dbb628552bc6640;hpb=51d8c9b54d65bd0aa3944b8fb9d4460875048e14;p=pspp-builds.git diff --git a/src/data/sys-file-writer.c b/src/data/sys-file-writer.c index 3e0d3499..1a65e3c0 100644 --- a/src/data/sys-file-writer.c +++ b/src/data/sys-file-writer.c @@ -1,5 +1,5 @@ /* PSPP - a program for statistical analysis. - Copyright (C) 1997-9, 2000, 2006, 2007 Free Software Foundation, Inc. + Copyright (C) 1997-9, 2000, 2006, 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 @@ -16,8 +16,8 @@ #include -#include "sys-file-writer.h" -#include "sys-file-private.h" +#include "data/sys-file-writer.h" +#include "data/sys-file-private.h" #include #include @@ -26,30 +26,33 @@ #include #include -#include -#include -#include -#include -#include -#include - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "minmax.h" -#include "unlocked-io.h" -#include "xalloc.h" +#include "data/attributes.h" +#include "data/case.h" +#include "data/casewriter-provider.h" +#include "data/casewriter.h" +#include "data/dictionary.h" +#include "data/file-handle-def.h" +#include "data/file-name.h" +#include "data/format.h" +#include "data/make-file.h" +#include "data/missing-values.h" +#include "data/mrset.h" +#include "data/settings.h" +#include "data/short-names.h" +#include "data/value-labels.h" +#include "data/variable.h" +#include "libpspp/float-format.h" +#include "libpspp/i18n.h" +#include "libpspp/integer-format.h" +#include "libpspp/message.h" +#include "libpspp/misc.h" +#include "libpspp/str.h" +#include "libpspp/version.h" + +#include "gl/xmemdup0.h" +#include "gl/minmax.h" +#include "gl/unlocked-io.h" +#include "gl/xalloc.h" #include "gettext.h" #define _(msgid) gettext (msgid) @@ -90,27 +93,40 @@ struct sfm_writer for long string variables. */ }; -static struct casewriter_class sys_file_casewriter_class; +static const struct casewriter_class sys_file_casewriter_class; static void write_header (struct sfm_writer *, const struct dictionary *); static void write_variable (struct sfm_writer *, const struct variable *); -static void write_value_labels (struct sfm_writer *, - struct variable *, int idx); +static void write_value_labels (struct sfm_writer *, struct variable *, + int idx); static void write_integer_info_record (struct sfm_writer *); static void write_float_info_record (struct sfm_writer *); static void write_longvar_table (struct sfm_writer *w, const struct dictionary *dict); +static void write_encoding_record (struct sfm_writer *w, + const struct dictionary *); + static void write_vls_length_table (struct sfm_writer *w, const struct dictionary *dict); +static void write_long_string_value_labels (struct sfm_writer *, + const struct dictionary *); + +static void write_mrsets (struct sfm_writer *, const struct dictionary *, + bool pre_v14); static void write_variable_display_parameters (struct sfm_writer *w, const struct dictionary *dict); static void write_documents (struct sfm_writer *, const struct dictionary *); +static void write_data_file_attributes (struct sfm_writer *, + const struct dictionary *); +static void write_variable_attributes (struct sfm_writer *, + const struct dictionary *); + static void write_int (struct sfm_writer *, int32_t); static inline void convert_double_to_output_format (double, uint8_t[8]); static void write_float (struct sfm_writer *, double); @@ -120,15 +136,16 @@ static void write_zeros (struct sfm_writer *, size_t); static void write_spaces (struct sfm_writer *, size_t); static void write_value (struct sfm_writer *, const union value *, int width); -static void write_case_uncompressed (struct sfm_writer *, struct ccase *); -static void write_case_compressed (struct sfm_writer *, struct ccase *); +static void write_case_uncompressed (struct sfm_writer *, + const struct ccase *); +static void write_case_compressed (struct sfm_writer *, const struct ccase *); static void flush_compressed (struct sfm_writer *); static void put_cmp_opcode (struct sfm_writer *, uint8_t); static void put_cmp_number (struct sfm_writer *, double); static void put_cmp_string (struct sfm_writer *, const void *, size_t); -bool write_error (const struct sfm_writer *); -bool close_writer (struct sfm_writer *); +static bool write_error (const struct sfm_writer *); +static bool close_writer (struct sfm_writer *); /* Returns default options for writing a system file. */ struct sfm_write_options @@ -136,14 +153,13 @@ sfm_writer_default_options (void) { struct sfm_write_options opts; opts.create_writeable = true; - opts.compress = get_scompression (); + opts.compress = settings_get_scompression (); opts.version = 3; return opts; } /* Opens the system file designated by file handle FH for writing - cases from dictionary D according to the given OPTS. If - COMPRESS is nonzero, the system file will be compressed. + cases from dictionary D according to the given OPTS. No reference to D is retained, so it may be modified or destroyed at will after this function returns. D is not @@ -192,14 +208,14 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d, goto error; /* Create the file on disk. */ - mode = S_IRUSR | S_IRGRP | S_IROTH; + mode = 0444; if (opts.create_writeable) - mode |= S_IWUSR | S_IWGRP | S_IWOTH; + mode |= 0222; w->rf = replace_file_start (fh_get_file_name (fh), "wb", mode, &w->file, NULL); if (w->rf == NULL) { - msg (ME, _("Error opening \"%s\" for writing as a system file: %s."), + msg (ME, _("Error opening `%s' for writing as a system file: %s."), fh_get_file_name (fh), strerror (errno)); goto error; } @@ -228,6 +244,8 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d, write_integer_info_record (w); write_float_info_record (w); + write_mrsets (w, d, true); + write_variable_display_parameters (w, d); if (opts.version >= 3) @@ -235,18 +253,24 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d, write_vls_length_table (w, d); + write_long_string_value_labels (w, d); + + if (attrset_count (dict_get_attributes (d))) + write_data_file_attributes (w, d); + write_variable_attributes (w, d); + + write_mrsets (w, d, false); + + write_encoding_record (w, d); + /* Write end-of-headers record. */ write_int (w, 999); write_int (w, 0); if (write_error (w)) - { - close_writer (w); - return NULL; - } + goto error; - return casewriter_create (dict_get_next_value_idx (d), - &sys_file_casewriter_class, w); + return casewriter_create (dict_get_proto (d), &sys_file_casewriter_class, w); error: close_writer (w); @@ -333,7 +357,7 @@ write_header (struct sfm_writer *w, const struct dictionary *d) } else { - static const char *month_name[12] = + static const char *const month_name[12] = { "Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec", @@ -406,7 +430,7 @@ write_variable (struct sfm_writer *w, const struct variable *v) int width = var_get_width (v); int segment_cnt = sfm_width_to_segments (width); int seg0_width = sfm_segment_alloc_width (width, 0); - const struct missing_values *mv = var_get_missing_values (v); + struct missing_values mv; int i; /* Record type. */ @@ -421,7 +445,13 @@ write_variable (struct sfm_writer *w, const struct variable *v) /* Number of missing values. If there is a range, then the range counts as 2 missing values and causes the number to be negated. */ - write_int (w, mv_has_range (mv) ? 2 - mv_n_values (mv) : mv_n_values (mv)); + mv_copy (&mv, var_get_missing_values (v)); + if (mv_get_width (&mv) > 8) + mv_resize (&mv, 8); + if (mv_has_range (&mv)) + write_int (w, -2 - mv_n_values (&mv)); + else + write_int (w, mv_n_values (&mv)); /* Print and write formats. */ write_format (w, *var_get_print_format (v), seg0_width); @@ -435,26 +465,24 @@ write_variable (struct sfm_writer *w, const struct variable *v) /* Value label. */ if (var_has_label (v)) { - const char *label = var_get_label (v); - size_t padded_len = ROUND_UP (MIN (strlen (label), 255), 4); - write_int (w, padded_len); + char *label = recode_string (var_get_encoding (v), UTF8, var_get_label (v), -1); + size_t label_len = MIN (strlen (label), 255); + size_t padded_len = ROUND_UP (label_len, 4); + write_int (w, label_len); write_string (w, label, padded_len); + free (label); } /* Write the missing values, if any, range first. */ - if (mv_has_range (mv)) + if (mv_has_range (&mv)) { double x, y; - mv_peek_range (mv, &x, &y); + mv_get_range (&mv, &x, &y); write_float (w, x); write_float (w, y); } - for (i = 0; i < mv_n_values (mv); i++) - { - union value value; - mv_peek_value (mv, &value, i); - write_value (w, &value, seg0_width); - } + for (i = 0; i < mv_n_values (&mv); i++) + write_value (w, mv_get_value (&mv, i), mv_get_width (&mv)); write_variable_continuation_records (w, seg0_width); @@ -474,34 +502,45 @@ write_variable (struct sfm_writer *w, const struct variable *v) write_variable_continuation_records (w, seg_width); } + + mv_destroy (&mv); } /* Writes the value labels for variable V having system file - variable index IDX to system file W. */ + variable index IDX to system file W. + + Value labels for long string variables are written separately, + by write_long_string_value_labels. */ static void write_value_labels (struct sfm_writer *w, struct variable *v, int idx) { const struct val_labs *val_labs; - struct val_labs_iterator *i; - struct val_lab *vl; + const struct val_lab **labels; + size_t n_labels; + size_t i; val_labs = var_get_value_labels (v); - if (val_labs == NULL) + n_labels = val_labs_count (val_labs); + if (n_labels == 0 || var_get_width (v) > 8) return; /* Value label record. */ write_int (w, 3); /* Record type. */ write_int (w, val_labs_count (val_labs)); - for (vl = val_labs_first_sorted (val_labs, &i); vl != NULL; - vl = val_labs_next (val_labs, &i)) + labels = val_labs_sorted (val_labs); + for (i = 0; i < n_labels; i++) { - uint8_t len = MIN (strlen (vl->label), 255); + const struct val_lab *vl = labels[i]; + char *label = recode_string (var_get_encoding (v), UTF8, val_lab_get_label (vl), -1); + uint8_t len = MIN (strlen (label), 255); - write_value (w, &vl->value, var_get_width (v)); + write_value (w, val_lab_get_value (vl), var_get_width (v)); write_bytes (w, &len, 1); - write_bytes (w, vl->label, len); + write_bytes (w, label, len); write_zeros (w, REM_RND_UP (len + 1, 8)); + free (label); } + free (labels); /* Value label variable record. */ write_int (w, 4); /* Record type. */ @@ -520,6 +559,130 @@ write_documents (struct sfm_writer *w, const struct dictionary *d) write_bytes (w, dict_get_documents (d), line_cnt * DOC_LINE_LENGTH); } +static void +put_attrset (struct string *string, const struct attrset *attrs) +{ + const struct attribute *attr; + struct attrset_iterator i; + + for (attr = attrset_first (attrs, &i); attr != NULL; + attr = attrset_next (attrs, &i)) + { + size_t n_values = attribute_get_n_values (attr); + size_t j; + + ds_put_cstr (string, attribute_get_name (attr)); + ds_put_byte (string, '('); + for (j = 0; j < n_values; j++) + ds_put_format (string, "'%s'\n", attribute_get_value (attr, j)); + ds_put_byte (string, ')'); + } +} + +static void +write_attribute_record (struct sfm_writer *w, const struct string *content, + int subtype) +{ + write_int (w, 7); + write_int (w, subtype); + write_int (w, 1); + write_int (w, ds_length (content)); + write_bytes (w, ds_data (content), ds_length (content)); +} + +static void +write_data_file_attributes (struct sfm_writer *w, + const struct dictionary *d) +{ + struct string s = DS_EMPTY_INITIALIZER; + put_attrset (&s, dict_get_attributes (d)); + write_attribute_record (w, &s, 17); + ds_destroy (&s); +} + +static void +write_variable_attributes (struct sfm_writer *w, const struct dictionary *d) +{ + struct string s = DS_EMPTY_INITIALIZER; + size_t n_vars = dict_get_var_cnt (d); + size_t n_attrsets = 0; + size_t i; + + for (i = 0; i < n_vars; i++) + { + struct variable *v = dict_get_var (d, i); + struct attrset *attrs = var_get_attributes (v); + if (attrset_count (attrs)) + { + if (n_attrsets++) + ds_put_byte (&s, '/'); + ds_put_format (&s, "%s:", var_get_short_name (v, 0)); + put_attrset (&s, attrs); + } + } + if (n_attrsets) + write_attribute_record (w, &s, 18); + ds_destroy (&s); +} + +/* Write multiple response sets. If PRE_V14 is true, writes sets supported by + SPSS before release 14, otherwise writes sets supported only by later + versions. */ +static void +write_mrsets (struct sfm_writer *w, const struct dictionary *dict, + bool pre_v14) +{ + struct string s = DS_EMPTY_INITIALIZER; + size_t n_mrsets; + size_t i; + + n_mrsets = dict_get_n_mrsets (dict); + if (n_mrsets == 0) + return; + + for (i = 0; i < n_mrsets; i++) + { + const struct mrset *mrset = dict_get_mrset (dict, i); + const char *label; + size_t j; + + if ((mrset->type != MRSET_MD || mrset->cat_source != MRSET_COUNTEDVALUES) + != pre_v14) + continue; + + ds_put_format (&s, "%s=", mrset->name); + if (mrset->type == MRSET_MD) + { + char *counted; + + if (mrset->cat_source == MRSET_COUNTEDVALUES) + ds_put_format (&s, "E %d ", mrset->label_from_var_label ? 11 : 1); + else + ds_put_byte (&s, 'D'); + + if (mrset->width == 0) + counted = xasprintf ("%.0f", mrset->counted.f); + else + counted = xmemdup0 (value_str (&mrset->counted, mrset->width), + mrset->width); + ds_put_format (&s, "%zu %s", strlen (counted), counted); + free (counted); + } + else + ds_put_byte (&s, 'C'); + ds_put_byte (&s, ' '); + + label = mrset->label && !mrset->label_from_var_label ? mrset->label : ""; + ds_put_format (&s, "%zu %s", strlen (label), label); + + for (j = 0; j < mrset->n_vars; j++) + ds_put_format (&s, " %s", var_get_short_name (mrset->vars[j], 0)); + ds_put_byte (&s, '\n'); + } + write_attribute_record (w, &s, pre_v14 ? 7 : 19); + ds_destroy (&s); +} + /* Write the alignment, width and scale values. */ static void write_variable_display_parameters (struct sfm_writer *w, @@ -583,6 +746,89 @@ write_vls_length_table (struct sfm_writer *w, ds_destroy (&map); } + +static void +write_long_string_value_labels (struct sfm_writer *w, + const struct dictionary *dict) +{ + size_t n_vars = dict_get_var_cnt (dict); + size_t size, i; + off_t start UNUSED; + + /* Figure out the size in advance. */ + size = 0; + for (i = 0; i < n_vars; i++) + { + struct variable *var = dict_get_var (dict, i); + const struct val_labs *val_labs = var_get_value_labels (var); + int width = var_get_width (var); + const struct val_lab *val_lab; + + if (val_labs_count (val_labs) == 0 || width < 9) + continue; + + size += 12 + strlen (var_get_name (var)); + for (val_lab = val_labs_first (val_labs); val_lab != NULL; + val_lab = val_labs_next (val_labs, val_lab)) + size += 8 + width + strlen (val_lab_get_label (val_lab)); + } + if (size == 0) + return; + + write_int (w, 7); /* Record type. */ + write_int (w, 21); /* Record subtype */ + write_int (w, 1); /* Data item (byte) size. */ + write_int (w, size); /* Number of data items. */ + + start = ftello (w->file); + for (i = 0; i < n_vars; i++) + { + struct variable *var = dict_get_var (dict, i); + const struct val_labs *val_labs = var_get_value_labels (var); + const char *var_name = var_get_name (var); + int width = var_get_width (var); + const struct val_lab *val_lab; + + if (val_labs_count (val_labs) == 0 || width < 9) + continue; + + write_int (w, strlen (var_name)); + write_bytes (w, var_name, strlen (var_name)); + write_int (w, width); + write_int (w, val_labs_count (val_labs)); + for (val_lab = val_labs_first (val_labs); val_lab != NULL; + val_lab = val_labs_next (val_labs, val_lab)) + { + const char *label = val_lab_get_label (val_lab); + size_t label_length = strlen (label); + + write_int (w, width); + write_bytes (w, value_str (val_lab_get_value (val_lab), width), + width); + write_int (w, label_length); + write_bytes (w, label, label_length); + } + } + assert (ftello (w->file) == start + size); +} + +static void +write_encoding_record (struct sfm_writer *w, + const struct dictionary *d) +{ + const char *enc = dict_get_encoding (d); + + if ( NULL == enc) + return; + + write_int (w, 7); /* Record type. */ + write_int (w, 20); /* Record subtype. */ + write_int (w, 1); /* Data item (char) size. */ + write_int (w, strlen (enc)); /* Number of data items. */ + write_string (w, enc, strlen (enc)); +} + + /* Writes the long variable name table. */ static void write_longvar_table (struct sfm_writer *w, const struct dictionary *dict) @@ -594,11 +840,13 @@ write_longvar_table (struct sfm_writer *w, const struct dictionary *dict) for (i = 0; i < dict_get_var_cnt (dict); i++) { struct variable *v = dict_get_var (dict, i); + char *longname = recode_string (dict_get_encoding (dict), UTF8, var_get_name (v), -1); if (i) - ds_put_char (&map, '\t'); + ds_put_byte (&map, '\t'); ds_put_format (&map, "%s=%s", - var_get_short_name (v, 0), var_get_name (v)); + var_get_short_name (v, 0), longname); + free (longname); } write_int (w, 7); /* Record type. */ @@ -671,7 +919,7 @@ sys_file_casewriter_write (struct casewriter *writer, void *w_, if (ferror (w->file)) { casewriter_force_error (writer); - case_destroy (c); + case_unref (c); return; } @@ -682,7 +930,7 @@ sys_file_casewriter_write (struct casewriter *writer, void *w_, else write_case_compressed (w, c); - case_destroy (c); + case_unref (c); } /* Destroys system file writer W. */ @@ -695,7 +943,7 @@ sys_file_casewriter_destroy (struct casewriter *writer, void *w_) } /* Returns true if an I/O error has occurred on WRITER, false otherwise. */ -bool +static bool write_error (const struct sfm_writer *writer) { return ferror (writer->file); @@ -703,7 +951,7 @@ write_error (const struct sfm_writer *writer) /* Closes a system file after we're done with it. Returns true if successful, false if an I/O error occurred. */ -bool +static bool close_writer (struct sfm_writer *w) { bool ok; @@ -724,7 +972,7 @@ close_writer (struct sfm_writer *w) /* Seek back to the beginning and update the number of cases. This is just a courtesy to later readers, so there's no need to check return values or report errors. */ - if (ok && w->case_cnt <= INT32_MAX && !fseek (w->file, 80, SEEK_SET)) + if (ok && w->case_cnt <= INT32_MAX && !fseeko (w->file, 80, SEEK_SET)) { write_int (w, w->case_cnt); clearerr (w->file); @@ -734,7 +982,7 @@ close_writer (struct sfm_writer *w) ok = false; if (!ok) - msg (ME, _("An I/O error occurred writing system file \"%s\"."), + msg (ME, _("An I/O error occurred writing system file `%s'."), fh_get_file_name (w->fh)); if (ok ? !replace_file_commit (w->rf) : !replace_file_abort (w->rf)) @@ -751,7 +999,7 @@ close_writer (struct sfm_writer *w) } /* System file writer casewriter class. */ -static struct casewriter_class sys_file_casewriter_class = +static const struct casewriter_class sys_file_casewriter_class = { sys_file_casewriter_write, sys_file_casewriter_destroy, @@ -760,7 +1008,7 @@ static struct casewriter_class sys_file_casewriter_class = /* Writes case C to system file W, without compressing it. */ static void -write_case_uncompressed (struct sfm_writer *w, struct ccase *c) +write_case_uncompressed (struct sfm_writer *w, const struct ccase *c) { size_t i; @@ -768,12 +1016,12 @@ write_case_uncompressed (struct sfm_writer *w, struct ccase *c) { struct sfm_var *v = &w->sfm_vars[i]; - if (v->width == 0) + if (v->var_width == 0) write_float (w, case_num_idx (c, v->case_index)); else { write_bytes (w, case_str_idx (c, v->case_index) + v->offset, - v->width); + v->segment_width); write_spaces (w, v->padding); } } @@ -781,7 +1029,7 @@ write_case_uncompressed (struct sfm_writer *w, struct ccase *c) /* Writes case C to system file W, with compression. */ static void -write_case_compressed (struct sfm_writer *w, struct ccase *c) +write_case_compressed (struct sfm_writer *w, const struct ccase *c) { size_t i; @@ -789,7 +1037,7 @@ write_case_compressed (struct sfm_writer *w, struct ccase *c) { struct sfm_var *v = &w->sfm_vars[i]; - if (v->width == 0) + if (v->var_width == 0) { double d = case_num_idx (c, v->case_index); if (d == SYSMIS) @@ -813,7 +1061,7 @@ write_case_compressed (struct sfm_writer *w, struct ccase *c) multiple of 8, by ensuring that the final partial oct (8 byte unit) is treated as padded with spaces on the right. */ - for (width = v->width; width > 0; width -= 8, offset += 8) + for (width = v->segment_width; width > 0; width -= 8, offset += 8) { const void *data = case_str_idx (c, v->case_index) + offset; int chunk_size = MIN (width, 8); @@ -936,13 +1184,13 @@ write_value (struct sfm_writer *w, const union value *value, int width) write_float (w, value->f); else { - write_bytes (w, value->s, width); + write_bytes (w, value_str (value, width), width); write_zeros (w, 8 - width); } } /* Writes null-terminated STRING in a field of the given WIDTH to - W. If WIDTH is longer than WIDTH, it is truncated; if WIDTH + W. If STRING is longer than WIDTH, it is truncated; if WIDTH is narrowed, it is padded on the right with spaces. */ static void write_string (struct sfm_writer *w, const char *string, size_t width)