X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fdata%2Fsys-file-writer.c;h=3fed2e05445135ec2ebcc300ce23c4855d0f41df;hb=20d1a04f1af4d67583bfd97658447ee7a135dfad;hp=6b4344a79d779a1bed28c0ea58c42f9f8dd6854d;hpb=679e253a4777564db48ccec70b8ce2f6e5b7e46b;p=pspp-builds.git diff --git a/src/data/sys-file-writer.c b/src/data/sys-file-writer.c index 6b4344a7..3fed2e05 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 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 @@ -21,28 +21,28 @@ #include #include -#include #include #include #include #include -#include -#include #include #include -#include #include #include #include +#include #include +#include #include #include #include #include #include +#include #include +#include #include #include #include @@ -51,9 +51,11 @@ #include "minmax.h" #include "unlocked-io.h" +#include "xalloc.h" #include "gettext.h" #define _(msgid) gettext (msgid) +#define N_(msgid) (msgid) /* Compression bias used by PSPP. Values between (1 - COMPRESSION_BIAS) and (251 - COMPRESSION_BIAS) inclusive can be @@ -64,7 +66,9 @@ struct sfm_writer { struct file_handle *fh; /* File handle. */ + struct fh_lock *lock; /* Mutual exclusion for file. */ FILE *file; /* File stream. */ + struct replace_file *rf; /* Ticket for replacing output file. */ bool compress; /* 1=compressed, 0=not compressed. */ casenumber case_cnt; /* Number of cases written so far. */ @@ -88,27 +92,37 @@ 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_variable (struct sfm_writer *, const struct variable *, const struct dictionary *); static void write_value_labels (struct sfm_writer *, - struct variable *, int idx); + struct variable *, int idx, const struct dictionary *); 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_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); @@ -118,8 +132,9 @@ 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); @@ -134,7 +149,7 @@ 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; } @@ -150,9 +165,8 @@ struct casewriter * sfm_open_writer (struct file_handle *fh, struct dictionary *d, struct sfm_write_options opts) { - struct sfm_writer *w = NULL; + struct sfm_writer *w; mode_t mode; - int fd; int idx; int i; @@ -164,22 +178,12 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d, opts.version = 3; } - /* Create file. */ - mode = S_IRUSR | S_IRGRP | S_IROTH; - if (opts.create_writeable) - mode |= S_IWUSR | S_IWGRP | S_IWOTH; - fd = open (fh_get_file_name (fh), O_WRONLY | O_CREAT | O_TRUNC, mode); - if (fd < 0) - goto open_error; - - /* Open file handle. */ - if (!fh_open (fh, FH_REF_FILE, "system file", "we")) - goto error; - /* Create and initialize writer. */ w = xmalloc (sizeof *w); - w->fh = fh; - w->file = fdopen (fd, "w"); + w->fh = fh_ref (fh); + w->lock = NULL; + w->file = NULL; + w->rf = NULL; w->compress = opts.compress; w->case_cnt = 0; @@ -193,11 +197,24 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d, w->segment_cnt = sfm_dictionary_to_sfm_vars (d, &w->sfm_vars, &w->sfm_var_cnt); - /* Check that file create succeeded. */ - if (w->file == NULL) + /* Open file handle as an exclusive writer. */ + /* TRANSLATORS: this fragment will be interpolated into + messages in fh_lock() that identify types of files. */ + w->lock = fh_lock (fh, FH_REF_FILE, N_("system file"), FH_ACC_WRITE, true); + if (w->lock == NULL) + goto error; + + /* Create the file on disk. */ + mode = S_IRUSR | S_IRGRP | S_IROTH; + if (opts.create_writeable) + mode |= S_IWUSR | S_IWGRP | S_IWOTH; + w->rf = replace_file_start (fh_get_file_name (fh), "wb", mode, + &w->file, NULL); + if (w->rf == NULL) { - close (fd); - goto open_error; + msg (ME, _("Error opening \"%s\" for writing as a system file: %s."), + fh_get_file_name (fh), strerror (errno)); + goto error; } /* Write the file header. */ @@ -206,7 +223,7 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d, /* Write basic variable info. */ short_names_assign (d); for (i = 0; i < dict_get_var_cnt (d); i++) - write_variable (w, dict_get_var (d, i)); + write_variable (w, dict_get_var (d, i), d); /* Write out value labels. */ idx = 0; @@ -214,7 +231,7 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d, { struct variable *v = dict_get_var (d, i); - write_value_labels (w, v, idx); + write_value_labels (w, v, idx, d); idx += sfm_width_to_octs (var_get_width (v)); } @@ -231,23 +248,29 @@ 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_encoding_record (w, d); + /* Write end-of-headers record. */ write_int (w, 999); write_int (w, 0); if (write_error (w)) - goto error; + { + close_writer (w); + return NULL; + } - return casewriter_create (&sys_file_casewriter_class, w); + return casewriter_create (dict_get_proto (d), &sys_file_casewriter_class, w); - error: +error: close_writer (w); return NULL; - - open_error: - msg (ME, _("Error opening \"%s\" for writing as a system file: %s."), - fh_get_file_name (fh), strerror (errno)); - goto error; } /* Returns value of X truncated to two least-significant digits. */ @@ -330,7 +353,7 @@ 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", @@ -398,12 +421,12 @@ write_variable_continuation_records (struct sfm_writer *w, int width) /* Write the variable record(s) for variable V to system file W. */ static void -write_variable (struct sfm_writer *w, const struct variable *v) +write_variable (struct sfm_writer *w, const struct variable *v, const struct dictionary *dict) { 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. */ @@ -418,7 +441,13 @@ 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); @@ -433,25 +462,23 @@ write_variable (struct sfm_writer *w, const struct variable *v) if (var_has_label (v)) { const char *label = var_get_label (v); - size_t padded_len = ROUND_UP (MIN (strlen (label), 255), 4); + char *l = recode_string (dict_get_encoding (dict), UTF8, label, -1); + size_t padded_len = ROUND_UP (MIN (strlen (l), 255), 4); write_int (w, padded_len); - write_string (w, label, padded_len); + write_string (w, l, padded_len); + free (l); } /* 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); @@ -471,34 +498,45 @@ 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) +write_value_labels (struct sfm_writer *w, struct variable *v, int idx, const struct dictionary *dict) { 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 (dict_get_encoding (dict), 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. */ @@ -517,6 +555,72 @@ 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_char (string, '('); + for (j = 0; j < n_values; j++) + ds_put_format (string, "'%s'\n", attribute_get_value (attr, j)); + ds_put_char (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_char (&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 the alignment, width and scale values. */ static void write_variable_display_parameters (struct sfm_writer *w, @@ -580,6 +684,89 @@ 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) @@ -591,11 +778,13 @@ 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_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. */ @@ -668,7 +857,7 @@ sys_file_casewriter_write (struct casewriter *writer, void *w_, if (ferror (w->file)) { casewriter_force_error (writer); - case_destroy (c); + case_unref (c); return; } @@ -679,7 +868,7 @@ 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. */ @@ -733,9 +922,13 @@ close_writer (struct sfm_writer *w) if (!ok) 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)) + ok = false; } - fh_close (w->fh, "system file", "we"); + fh_unlock (w->lock); + fh_unref (w->fh); free (w->sfm_vars); free (w); @@ -744,7 +937,7 @@ 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, @@ -753,7 +946,7 @@ 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; @@ -761,12 +954,12 @@ 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); } } @@ -774,7 +967,7 @@ 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; @@ -782,7 +975,7 @@ 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) @@ -806,7 +999,7 @@ 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); @@ -929,13 +1122,13 @@ 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)