X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Fdata%2Fsys-file-writer.c;h=c1ff9a83a212fac17bf2767cadbc92ef1feb1581;hb=6b562f8a8263930b8d1ed1862efec76f2511ed08;hp=aa539a51364fb6804aa1ddfc2b14d2ee545ebbc3;hpb=c3ac5a8af9c449072c7e872ca70a78c1755ae309;p=pspp-builds.git diff --git a/src/data/sys-file-writer.c b/src/data/sys-file-writer.c index aa539a51..c1ff9a83 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 @@ -103,9 +103,14 @@ 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); @@ -126,8 +131,9 @@ 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); @@ -241,10 +247,14 @@ 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); @@ -255,8 +265,7 @@ sfm_open_writer (struct file_handle *fh, struct dictionary *d, return NULL; } - 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); @@ -487,31 +496,39 @@ write_variable (struct sfm_writer *w, const struct variable *v) } /* 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]; + const char *label = val_lab_get_label (vl); + 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 (labels); /* Value label variable record. */ write_int (w, 4); /* Record type. */ @@ -659,6 +676,89 @@ 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) @@ -747,7 +847,7 @@ sys_file_casewriter_write (struct casewriter *writer, void *w_, if (ferror (w->file)) { casewriter_force_error (writer); - case_destroy (c); + case_unref (c); return; } @@ -758,7 +858,7 @@ 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. */ @@ -836,7 +936,7 @@ static const 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; @@ -844,12 +944,12 @@ 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); } } @@ -857,7 +957,7 @@ 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; @@ -865,7 +965,7 @@ 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) @@ -889,7 +989,7 @@ 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); @@ -1012,13 +1112,13 @@ 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)