1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311
|
/*
* $Id: gwymoduleutils-file.c 23978 2021-08-13 14:48:02Z yeti-dn $
* Copyright (C) 2007-2016 David Necas (Yeti), Petr Klapetek.
* E-mail: yeti@gwyddion.net, klapetek@gwyddion.net.
*
* 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 2 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, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor,
* Boston, MA 02110-1301, USA.
*/
#include "config.h"
#include <stdarg.h>
#include <string.h>
#include <libgwyddion/gwymacros.h>
#include <libgwyddion/gwymath.h>
#include <libprocess/stats.h>
#include <libprocess/correct.h>
#include <libgwymodule/gwymodule-file.h>
#include <app/data-browser.h>
#include <app/settings.h>
#include <app/log.h>
#include <app/gwymoduleutils-file.h>
struct _GwyTextHeaderContext {
const GwyTextHeaderParser *parser;
GHashTable *hash;
GError *error;
gchar *section;
gpointer user_data;
guint lineno;
};
typedef void (*LogAddFunc)(GwyContainer *data,
gint previd,
gint newid,
const gchar *function,
...);
static void add_import_log(GwyContainer *data,
gint id,
LogAddFunc add_log,
const gchar *filetype,
const gchar *filename);
/**
* gwy_app_channel_check_nonsquare:
* @data: A data container.
* @id: Data channel id.
*
* Sets `realsquare' for a channel highly non-square pixels.
*
* The threshold for highly non-square is somewhat arbitrary.
* Fortunately, most files encoutered in practice have the measure ratio either
* very close to 1, larger or equal than 2.
*
* Returns: %TRUE if the channel was found to have highly non-square pixels
* and `realsquare' was set (otherwise it was unset).
*
* Since: 2.3
**/
gboolean
gwy_app_channel_check_nonsquare(GwyContainer *data,
gint id)
{
GwyDataField *dfield;
gdouble xmeasure, ymeasure, q;
gboolean nonsquare;
GQuark quark;
const gchar *key;
gchar *s;
quark = gwy_app_get_data_key_for_id(id);
dfield = GWY_DATA_FIELD(gwy_container_get_object(data, quark));
g_return_val_if_fail(GWY_IS_DATA_FIELD(dfield), FALSE);
xmeasure = gwy_data_field_get_xmeasure(dfield);
ymeasure = gwy_data_field_get_ymeasure(dfield);
q = xmeasure/ymeasure;
nonsquare = (q > G_SQRT2 || q < 1.0/G_SQRT2);
key = g_quark_to_string(quark);
s = g_strconcat(key, "/realsquare", NULL);
if (nonsquare)
gwy_container_set_boolean_by_name(data, s, TRUE);
else
gwy_container_remove_by_name(data, s);
g_free(s);
return nonsquare;
}
static const gchar*
guess_title_from_units(GwySIUnit *siunit)
{
static const struct {
const gchar *unit;
const gchar *title;
}
map[] = {
{ "m", "Topography", },
{ "A", "Current", },
{ "deg", "Phase", },
{ "V", "Voltage", },
{ "N", "Force", },
{ "s", "Time", },
};
GwySIUnit *test;
const gchar *title = NULL;
guint i;
test = gwy_si_unit_new(NULL);
for (i = 0; i < G_N_ELEMENTS(map); i++) {
gwy_si_unit_set_from_string(test, map[i].unit);
if (gwy_si_unit_equal(siunit, test)) {
title = map[i].title;
break;
}
}
g_object_unref(test);
return title;
}
/**
* gwy_app_channel_title_fall_back:
* @data: A data container.
* @id: Data channel id.
*
* Adds a channel title based on data field units.
*
* The guess is very simple, but probably better than `Unknown channel' in
* most cases. If there already is a title it is left intact, making use of
* this function as a fall-back easier.
*
* Returns: %TRUE if the title was set (either by this function or before).
*
* Since: 2.3
**/
gboolean
gwy_app_channel_title_fall_back(GwyContainer *data,
gint id)
{
GwyDataField *dfield;
const gchar *title;
GQuark quark;
quark = gwy_app_get_data_key_for_id(id);
dfield = gwy_container_get_object(data, quark);
g_return_val_if_fail(GWY_IS_DATA_FIELD(dfield), FALSE);
quark = gwy_app_get_data_title_key_for_id(id);
if (gwy_container_contains(data, quark))
return TRUE;
title = guess_title_from_units(gwy_data_field_get_si_unit_z(dfield));
if (title) {
gwy_container_set_const_string(data, quark, title);
return TRUE;
}
return FALSE;
}
/**
* gwy_app_xyz_title_fall_back:
* @data: A data container.
* @id: XYZ surface data id.
*
* Adds a XYZ data title based on surface value units.
*
* The guess is very simple, but probably better than `Unknown channel' in
* most cases. If there already is a title it is left intact, making use of
* this function as a fall-back easier.
*
* Returns: %TRUE if the title was set (either by this function or before).
*
* Since: 2.45
**/
gboolean
gwy_app_xyz_title_fall_back(GwyContainer *data,
gint id)
{
GwySurface *surface;
const gchar *title;
GQuark quark;
quark = gwy_app_get_surface_key_for_id(id);
surface = gwy_container_get_object(data, quark);
g_return_val_if_fail(GWY_IS_SURFACE(surface), FALSE);
quark = gwy_app_get_surface_title_key_for_id(id);
if (gwy_container_contains(data, quark))
return TRUE;
title = guess_title_from_units(gwy_surface_get_si_unit_z(surface));
if (title) {
gwy_container_set_const_string(data, quark, title);
return TRUE;
}
return FALSE;
}
/**
* gwy_app_channel_remove_bad_data:
* @dfield: A data field. The values of bad data points are ignored and might
* be even left uninitialized.
* @mfield: A mask field containing 1.0 in place of good data points, 0.0 in
* place of bad points. It will be inverted to become the mask of
* bad points.
*
* Replaces bad data points with some neutral values.
*
* Since Gwyddion has no concept of bad data points, they are usually marked
* with a mask and replaced with some neutral values upon import, leaving the
* user to decide how to proceed further. This helper function performs such
* replacement.
*
* Returns: The number of bad data points replaced. If zero is returned, all
* points are good and there is no need for masking.
*
* Since: 2.14
**/
guint
gwy_app_channel_remove_bad_data(GwyDataField *dfield, GwyDataField *mfield)
{
gdouble *m = gwy_data_field_get_data(mfield);
guint i, mcount, n;
n = gwy_data_field_get_xres(dfield) * gwy_data_field_get_yres(dfield);
mcount = 0;
for (i = 0; i < n; i++) {
if (m[i] <= 0.0) {
m[i] = 1.0;
mcount++;
}
else
m[i] = 0.0;
}
if (mcount)
gwy_data_field_laplace_solve(dfield, mfield, -1, 0.25);
gwy_data_field_set_xreal(mfield, gwy_data_field_get_xreal(dfield));
gwy_data_field_set_yreal(mfield, gwy_data_field_get_yreal(dfield));
gwy_si_unit_assign(gwy_data_field_get_si_unit_xy(mfield),
gwy_data_field_get_si_unit_xy(dfield));
gwy_debug("mcount = %u", mcount);
return mcount;
}
/**
* gwy_app_channel_mask_of_nans:
* @dfield: A data field possibly containing NaNs and infinities.
* @removebad: Automatically remove the invalid values.
*
* Creates a mask corresponding to not-a-number and infinite values in a data
* field.
*
* NaNs and infinities are not normally allowed in Gwyddion so this function
* should be used upon import if the source file format can represent such
* values.
*
* The invalid values can be automatically removed using the same method as
* gwy_app_channel_remove_bad_data().
*
* Returns: A newly created data field with 1.0 in pixels corresponding to a
* NaN or infinity in @dfield. If no such pixels are present, %NULL
* is returned.
*
* Since: 2.38
**/
GwyDataField*
gwy_app_channel_mask_of_nans(GwyDataField *dfield,
gboolean removebad)
{
GwyDataField *mask = NULL;
guint k, n = dfield->xres*dfield->yres;
gdouble *d = dfield->data, *m = NULL;
for (k = 0; k < n; k++) {
if (gwy_isnan(d[k]) || gwy_isinf(d[k])) {
if (G_UNLIKELY(!mask)) {
mask = gwy_data_field_new_alike(dfield, TRUE);
m = gwy_data_field_get_data(mask);
gwy_si_unit_set_from_string(gwy_data_field_get_si_unit_z(mask),
NULL);
}
m[k] = 1.0;
}
}
if (!mask || !removebad)
return mask;
gwy_data_field_laplace_solve(dfield, mask, -1, 0.25);
return mask;
}
/**
* gwy_text_header_error_quark:
*
* Returns error domain for expression parsin and evaluation.
*
* See and use %GWY_TEXT_HEADER_ERROR.
*
* Returns: The error domain.
*
* Since: 2.18
**/
GQuark
gwy_text_header_error_quark(void)
{
static GQuark error_domain = 0;
if (!error_domain)
error_domain = g_quark_from_static_string("gwy-text-header-error-quark");
return error_domain;
}
static inline guint
chomp(gchar *line,
guint len)
{
while (len && g_ascii_isspace(line[len-1]))
line[--len] = '\0';
return len;
}
static inline gchar*
strip(gchar *line,
guint len)
{
while (len && g_ascii_isspace(*line)) {
line++;
len--;
}
while (len && g_ascii_isspace(line[len-1]))
line[--len] = '\0';
return line;
}
static void
check_fatal_error(GwyTextHeaderContext *context)
{
if (!context->parser->error
|| !context->parser->error(context, context->error, context->user_data))
g_clear_error(&context->error);
}
static void
make_noise(GwyTextHeaderContext *context,
GwyTextHeaderError code,
const gchar *format,
...)
{
gchar *s;
va_list ap;
if (!context->parser->error)
return;
va_start(ap, format);
s = g_strdup_vprintf(format, ap);
va_end(ap);
g_set_error(&context->error, GWY_TEXT_HEADER_ERROR, code, "%s", s);
g_free(s);
check_fatal_error(context);
}
/**
* gwy_text_header_parse:
* @header: Text header to parse. It must be %NULL-terminated and writable.
* Its contents will be modified to directly embed the hash keys
* and/or values. It must not be freed while the returned hash
* table is in use.
* @parser: Parser specification.
* @user_data: User data passed to parser callbacks.
* @error: Error to set on fatal errors.
*
* Parses a line-oriented text header into a hash table.
*
* See #GwyTextHeaderParser for details of memory and error handling.
*
* Lines consisting only of whitespace are ignored.
*
* Returns: A newly created hash table with values indexed by they keys found
* in the header.
*
* Since: 2.18
**/
GHashTable*
gwy_text_header_parse(gchar *header,
const GwyTextHeaderParser *parser,
gpointer user_data,
GError **error)
{
GwyTextHeaderContext context;
gchar *line, *header_start;
const gchar *section_prefix = NULL, *section_suffix = NULL,
*endsect_prefix = NULL, *endsect_suffix = NULL,
**comments = NULL;
guint section_prefix_len = 0, section_suffix_len = 0,
endsect_prefix_len = 0, endsect_suffix_len = 0,
comment_prefix_len = 0, line_prefix_len = 0;
gchar equal_sign_char = 0;
guint j, ncomments = 0;
gboolean free_keys = FALSE;
g_return_val_if_fail(header, NULL);
g_return_val_if_fail(parser, NULL);
g_return_val_if_fail(parser->section_template
|| !parser->endsection_template,
NULL);
g_return_val_if_fail(!parser->section_template == !parser->section_accessor,
NULL);
g_return_val_if_fail(parser->item || !parser->destroy_key, NULL);
g_return_val_if_fail(parser->item || !parser->destroy_value, NULL);
header_start = header;
/* Split section templates to prefix and suffix. */
if (parser->section_template) {
gchar *p;
p = strchr(parser->section_template, '\x1a');
g_return_val_if_fail(p, NULL);
section_prefix = parser->section_template;
section_prefix_len = p - parser->section_template;
section_suffix = section_prefix + (p+1 - parser->section_template);
section_suffix_len = strlen(section_suffix);
free_keys = TRUE;
}
if (parser->endsection_template) {
gchar *p;
if ((p = strchr(parser->endsection_template, '\x1a'))) {
endsect_prefix = parser->endsection_template;
endsect_prefix_len = p - parser->endsection_template;
endsect_suffix = endsect_prefix + (p+1 - parser->endsection_template);
endsect_suffix_len = strlen(endsect_suffix);
}
}
if (parser->comment_prefix) {
comment_prefix_len = strlen(parser->comment_prefix);
if (strchr(parser->comment_prefix, '\n')) {
const gchar *p;
for (j = 0, p = parser->comment_prefix-1;
p;
p = strchr(p+1, '\n'), j++)
;
ncomments = j;
comments = g_new(const gchar*, j+1);
comments[0] = parser->comment_prefix;
j = 1;
do {
if ((p = strchr(comments[j-1], '\n')))
comments[j++] = p+1;
} while (p);
comments[j] = parser->comment_prefix + comment_prefix_len + 1;
}
}
if (parser->line_prefix)
line_prefix_len = strlen(parser->line_prefix);
if (parser->key_value_separator && strlen(parser->key_value_separator) == 1)
equal_sign_char = parser->key_value_separator[0];
/* Build the hash table */
context.lineno = 0;
context.section = NULL;
context.error = NULL;
context.parser = parser;
context.user_data = user_data;
context.hash = g_hash_table_new_full(g_str_hash, g_str_equal,
parser->destroy_key
? parser->destroy_key
: (free_keys ? g_free : NULL),
parser->destroy_value
? parser->destroy_value : NULL);
for (line = gwy_str_next_line(&header);
line && !context.error;
line = gwy_str_next_line(&header), context.lineno++) {
gchar *key, *value;
guint len;
/* Chomp whitespace at the end */
if (!(len = chomp(line, strlen(line))))
continue;
/* Header end marker */
if (parser->terminator
&& gwy_strequal(line, parser->terminator))
break;
/* Section ends -- before section starts beause they might look
* similar. */
if (endsect_prefix
&& len > endsect_prefix_len + endsect_suffix_len
&& strncmp(line, endsect_prefix, endsect_prefix_len) == 0
&& gwy_strequal(line + len - endsect_suffix_len, endsect_suffix)) {
gchar *endsection;
len -= endsect_suffix_len;
line[len] = '\0';
endsection = strip(line + endsect_prefix_len,
len - endsect_prefix_len);
if (!context.section) {
make_noise(&context, GWY_TEXT_HEADER_ERROR_SECTION_END,
_("Section %s ended at line %u but it has "
"never started."),
endsection, context.lineno);
continue;
}
if (!gwy_strequal(endsection, context.section)) {
make_noise(&context, GWY_TEXT_HEADER_ERROR_SECTION_END,
_("Section %s ended at line %u instead of %s."),
endsection, context.lineno, context.section);
continue;
}
if (parser->endsection
&& !parser->endsection(&context, context.section, user_data,
&context.error))
check_fatal_error(&context);
context.section = NULL;
continue;
}
else if (parser->endsection_template
&& gwy_strequal(line, parser->endsection_template)) {
if (parser->endsection
&& !parser->endsection(&context, context.section, user_data,
&context.error))
check_fatal_error(&context);
context.section = NULL;
continue;
}
/* Sections starts */
if (section_prefix
&& len > section_prefix_len + section_suffix_len
&& strncmp(line, parser->section_template, section_prefix_len) == 0
&& gwy_strequal(line + len - section_suffix_len, section_suffix)) {
gchar *newsection;
len -= section_suffix_len;
line[len] = '\0';
newsection = strip(line + section_prefix_len,
len - section_prefix_len);
if (parser->endsection_template && context.section) {
make_noise(&context, GWY_TEXT_HEADER_ERROR_SECTION_START,
_("Section %s started at line %u before %s ended."),
newsection, context.lineno, context.section);
}
if (!*newsection) {
make_noise(&context, GWY_TEXT_HEADER_ERROR_SECTION_NAME,
_("Empty section name at header line %u."),
context.lineno);
continue;
}
context.section = newsection;
if (parser->section
&& !parser->section(&context, context.section, user_data,
&context.error))
check_fatal_error(&context);
continue;
}
/* Comments */
if (comments) {
for (j = 0; j < ncomments; j++) {
if (strncmp(line, comments[j],
comments[j+1] - comments[j] - 1) == 0)
break;
}
if (j < ncomments)
continue;
}
else if (parser->comment_prefix
&& strncmp(line, parser->comment_prefix,
comment_prefix_len) == 0)
continue;
/* Line prefixes */
if (parser->line_prefix) {
if (strncmp(line, parser->line_prefix, line_prefix_len) == 0) {
line += line_prefix_len;
len -= line_prefix_len;
}
else {
make_noise(&context, GWY_TEXT_HEADER_ERROR_PREFIX,
_("Header line %u lacks prefix %s."),
context.lineno, parser->line_prefix);
continue;
}
}
while (g_ascii_isspace(*line)) {
line++;
len--;
}
/* Keys and values */
if (equal_sign_char)
value = strchr(line, equal_sign_char);
else if (parser->key_value_separator)
value = strstr(line, parser->key_value_separator);
else {
for (value = line; !g_ascii_isspace(*value); value++) {
if (!*value) {
value = NULL;
break;
}
}
}
if (!value) {
make_noise(&context, GWY_TEXT_HEADER_ERROR_GARBAGE,
_("Header line %u lacks key-value separator."),
context.lineno);
continue;
}
*(value++) = '\0';
if (!chomp(line, value - line - 1)) {
make_noise(&context, GWY_TEXT_HEADER_ERROR_KEY,
_("Key at header line %u is empty."), context.lineno);
continue;
}
key = line;
value = strip(value, len - (value - line));
if (parser->section_template) {
if (context.section)
key = g_strconcat(context.section, parser->section_accessor,
key, NULL);
else
key = g_strdup(key);
}
if (parser->item) {
if (!parser->item(&context, context.hash, key, value,
context.user_data, &context.error))
check_fatal_error(&context);
}
else
g_hash_table_replace(context.hash, key, value);
}
g_free(comments);
if (parser->terminator && !line && !context.error)
make_noise(&context, GWY_TEXT_HEADER_ERROR_TERMINATOR,
_("Header suddenly ended at line %u; end of header marker "
"is missing"),
context.lineno);
if (context.error) {
g_propagate_error(error, context.error);
g_hash_table_destroy(context.hash);
return NULL;
}
if (parser->end)
parser->end(&context, header - header_start, context.user_data);
return context.hash;
}
/**
* gwy_text_header_context_get_section:
* @context: Header parsing context.
*
* Gets the currently open section.
*
* This function may be called if no sectioning is defined. It simply
* returns %NULL then.
*
* Returns: The name of the currently open section, %NULL if there is none.
*
* Since: 2.18
**/
const gchar*
gwy_text_header_context_get_section(const GwyTextHeaderContext *context)
{
return context->section;
}
/**
* gwy_text_header_context_get_lineno:
* @context: Header parsing context.
*
* Gets the current header line.
*
* Returns: The current line number, starting from zero.
*
* Since: 2.18
**/
guint
gwy_text_header_context_get_lineno(const GwyTextHeaderContext *context)
{
return context->lineno;
}
/**
* gwy_file_channel_import_log_add:
* @data: A data container.
* @id: Data channel id.
* @filetype: File type, i.e. the name of the function importing the data
* (without any "file::" prefix). Since 2.38 it is possible to
* pass %NULL to fill the name of the currently running file type
* function automatically.
* @filename: Name of the imported file. If it is not valid UTF-8, it will be
* converted to UTF-8 using g_filename_to_utf8(). Failing even
* that, non-ASCII characters will be escaped.
*
* Logs the import of a channel from third-party file.
*
* This is a convenience wrapper for gwy_app_channel_log_add(). The source id
* will be set to -1. The file name will be added to function arguments.
*
* Since: 2.35
**/
void
gwy_file_channel_import_log_add(GwyContainer *data,
gint id,
const gchar *filetype,
const gchar *filename)
{
add_import_log(data, id, gwy_app_channel_log_add, filetype, filename);
}
/**
* gwy_file_volume_import_log_add:
* @data: A data container.
* @id: Volume data id.
* @filetype: File type, i.e. the name of the function importing the data
* (without any "file::" prefix). Since 2.38 it is possible to
* pass %NULL to fill the name of the currently running file type
* function automatically.
* @filename: Name of the imported file. If it is not valid UTF-8, it will be
* converted to UTF-8 using g_filename_to_utf8(). Failing even
* that, non-ASCII characters will be escaped.
*
* Logs the import of volume data from third-party file.
*
* This is a convenience wrapper for gwy_app_volume_log_add(). The source id
* will be set to -1. The file name will be added to function arguments.
*
* Since: 2.35
**/
void
gwy_file_volume_import_log_add(GwyContainer *data,
gint id,
const gchar *filetype,
const gchar *filename)
{
add_import_log(data, id, gwy_app_volume_log_add, filetype, filename);
}
/**
* gwy_file_xyz_import_log_add:
* @data: A data container.
* @id: XYZ surface data id.
* @filetype: File type, i.e. the name of the function importing the data
* (without any "file::" prefix). It is possible to
* pass %NULL to fill the name of the currently running file type
* function automatically.
* @filename: Name of the imported file. If it is not valid UTF-8, it will be
* converted to UTF-8 using g_filename_to_utf8(). Failing even
* that, non-ASCII characters will be escaped.
*
* Logs the import of xyz data from third-party file.
*
* This is a convenience wrapper for gwy_app_xyz_log_add(). The source id
* will be set to -1. The file name will be added to function arguments.
*
* Since: 2.45
**/
void
gwy_file_xyz_import_log_add(GwyContainer *data,
gint id,
const gchar *filetype,
const gchar *filename)
{
add_import_log(data, id, gwy_app_xyz_log_add, filetype, filename);
}
/**
* gwy_file_curve_map_import_log_add:
* @data: A data container.
* @id: Volume data id.
* @filetype: File type, i.e. the name of the function importing the data
* (without any "file::" prefix). Since 2.38 it is possible to
* pass %NULL to fill the name of the currently running file type
* function automatically.
* @filename: Name of the imported file. If it is not valid UTF-8, it will be
* converted to UTF-8 using g_filename_to_utf8(). Failing even
* that, non-ASCII characters will be escaped.
*
* Logs the import of volume data from third-party file.
*
* This is a convenience wrapper for gwy_app_curve_map_log_add(). The source id
* will be set to -1. The file name will be added to function arguments.
*
* Since: 2.60
**/
void
gwy_file_curve_map_import_log_add(GwyContainer *data,
gint id,
const gchar *filetype,
const gchar *filename)
{
add_import_log(data, id, gwy_app_curve_map_log_add, filetype, filename);
}
static void
add_import_log(GwyContainer *data,
gint id,
LogAddFunc add_log,
const gchar *filetype,
const gchar *filename)
{
/* There should not be any settings key called
* "/module/<filetype>/filename".
* But just in case there is one, preserve it. */
GwyContainer *settings;
GValue savedval;
GQuark quark;
gchar *myfilename = NULL, *fskey, *qualname;
if (!filetype)
filetype = gwy_file_func_current();
g_return_if_fail(filename);
g_return_if_fail(filetype);
g_return_if_fail(data);
if (g_utf8_validate(filename, -1, NULL))
myfilename = g_strdup(filename);
if (!myfilename)
myfilename = g_filename_to_utf8(filename, -1, NULL, NULL, NULL);
if (!myfilename)
myfilename = g_strescape(filename, NULL);
fskey = g_strdup_printf("/module/%s/filename", filetype);
quark = g_quark_from_string(fskey);
g_free(fskey);
gwy_clear(&savedval, 1);
settings = gwy_app_settings_get();
if (gwy_container_contains(settings, quark))
savedval = gwy_container_get_value(settings, quark);
/* Eats myfilename. */
gwy_container_set_string(settings, quark, myfilename);
qualname = g_strconcat("file::", filetype, NULL);
add_log(data, -1, id, qualname, NULL);
g_free(qualname);
if (G_VALUE_TYPE(&savedval)) {
gwy_container_set_value(settings, quark, &savedval);
g_value_unset(&savedval);
}
else
gwy_container_remove(settings, quark);
}
/************************** Documentation ****************************/
/**
* SECTION:gwymoduleutils-file
* @title: file module utils
* @short_description: Utility functions for file modules
* @include: app/gwymoduleutils-file.h
*
* Functions gwy_app_channel_check_nonsquare() and
* gwy_app_channel_title_fall_back() perform common tasks improving the
* imported of channels from foreign data files. Typically one calls them on
* all imported channel ids after storing the data fields the the container,
* if they are useful for a given file type.
*
* The group of functions gwy_get_gint16_le(), gwy_get_gint16_be(), etc.
* is intended to portably read packed binary data structures that are commonly
* found in SPM files. They all work identically: the binary data value is
* read from the buffer, converted if necessary, and the provided
* buffer pointer is moved to point after the value to faciliate sequential
* reading.
*
* As no buffer size is passed, obviously no buffer size checking is performed.
* The caller has to ensure the buffer is large enough -- it is expected the
* caller checks the total buffer size before starting to parse it.
*
* For example to portably read the following packed struct stored
* in big-endian byte order:
* <informalexample><programlisting>
* struct {
* guint16 xres;
* guint16 yres;
* gfloat measure;
* } header;
* </programlisting></informalexample>
* one can do (after checking the buffer size):
* <informalexample><programlisting>
* const guchar *p = buffer;
* header.xres = gwy_get_guint16_be(&p);
* header.yres = gwy_get_guint16_be(&p);
* header.measure = gwy_get_gfloat_be(&p);
* </programlisting></informalexample>
* and @p will point after @measure in @buffer after this snippet is finished.
*
* The data types used in @header do not matter (provided they are large
* enough to hold the values), the exact types are determined by the functions
* used. Therefore the reading would work identically if @header was defined
* using common types:
* <informalexample><programlisting>
* struct {
* gint xres;
* gint yres;
* gdouble measure;
* } header;
* </programlisting></informalexample>
**/
/**
* gwy_get_gboolean8:
* @ppv: Pointer to a pointer to boolean (stored as a signle byte)
* in a memory buffer.
*
* Reads a boolean value stored as a signle byte from a
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gboolean value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_gint16_le:
* @ppv: Pointer to a pointer to a little-endian signed 16bit integer
* in a memory buffer.
*
* Reads a signed 16bit integer value from a little-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gint16 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_gint16_be:
* @ppv: Pointer to a pointer to a big-endian signed 16bit integer
* in a memory buffer.
*
* Reads a signed 16bit integer value from a big-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gint16 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_guint16_le:
* @ppv: Pointer to a pointer to a little-endian unsigned 16bit integer
* in a memory buffer.
*
* Reads an unsigned 16bit integer value from a little-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #guint16 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_guint16_be:
* @ppv: Pointer to a pointer to a big-endian unsigned 16bit integer
* in a memory buffer.
*
* Reads an unsigned 16bit integer value from a big-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #guint16 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_gint32_le:
* @ppv: Pointer to a pointer to a little-endian signed 32bit integer
* in a memory buffer.
*
* Reads a signed 32bit integer value from a little-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gint32 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_gint32_be:
* @ppv: Pointer to a pointer to a big-endian signed 32bit integer
* in a memory buffer.
*
* Reads a signed 32bit integer value from a big-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gint32 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_guint32_le:
* @ppv: Pointer to a pointer to a little-endian unsigned 32bit integer
* in a memory buffer.
*
* Reads an unsigned 32bit integer value from a little-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #guint32 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_guint32_be:
* @ppv: Pointer to a pointer to a big-endian unsigned 32bit integer
* in a memory buffer.
*
* Reads an unsigned 32bit integer value from a big-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #guint32 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_gint64_le:
* @ppv: Pointer to a pointer to a little-endian signed 64bit integer
* in a memory buffer.
*
* Reads a signed 64bit integer value from a little-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gint64 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_gint64_be:
* @ppv: Pointer to a pointer to a big-endian signed 64bit integer
* in a memory buffer.
*
* Reads a signed 64bit integer value from a big-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gint64 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_guint64_le:
* @ppv: Pointer to a pointer to a little-endian unsigned 64bit integer
* in a memory buffer.
*
* Reads an unsigned 64bit integer value from a little-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #guint64 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_guint64_be:
* @ppv: Pointer to a pointer to a big-endian unsigned 64bit integer
* in a memory buffer.
*
* Reads an unsigned 64bit integer value from a big-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #guint64 value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_gfloat_le:
* @ppv: Pointer to a pointer to a little-endian single-precision IEEE float
* in a memory buffer.
*
* Reads a single-precision IEEE float value from a little-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gfloat value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_gfloat_be:
* @ppv: Pointer to a pointer to a big-endian single-precision IEEE float
* in a memory buffer.
*
* Reads a single-precision IEEE float value from a big-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gfloat value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_gdouble_le:
* @ppv: Pointer to a pointer to a little-endian double-precision IEEE float
* in a memory buffer.
*
* Reads a double-precision IEEE float value from a little-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gdouble value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_gdouble_be:
* @ppv: Pointer to a pointer to a big-endian double-precision IEEE float
* in a memory buffer.
*
* Reads a double-precision IEEE float value from a big-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The #gdouble value read from the buffer.
*
* Since: 2.3
**/
/**
* gwy_get_pascal_real_le:
* @ppv: Pointer to a pointer to a little-endian six-byte Pascal Real
* in a memory buffer.
*
* Reads a six-byte Pascale Real value from a little-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The floating point value read from the buffer as a #gdouble.
*
* Since: 2.3
**/
/**
* gwy_get_pascal_real_be:
* @ppv: Pointer to a pointer to a big-endian six-byte Pascal Real
* in a memory buffer.
*
* Reads a six-byte Pascale Real value from a big-endian
* binary data buffer, moving the buffer pointer to point just after the value.
*
* Returns: The floating point value read from the buffer as a #gdouble.
*
* Since: 2.3
**/
/**
* GWY_TEXT_HEADER_ERROR:
*
* Error domain for text header parsing. Errors in this domain will be from the
* #GwyTextHeaderError enumeration. See #GError for information on error
* domains.
*
* Since: 2.18
**/
/**
* GwyTextHeaderError:
* @GWY_TEXT_HEADER_ERROR_SECTION_NAME: Section name is invalid. It is raised
* by the parser only for an empty section
* name.
* @GWY_TEXT_HEADER_ERROR_SECTION_END: Section ended when a different section
* or no section was open. Note that
* gwy_text_header_context_get_section()
* returns the section being closed at the
* time this error is raised.
* @GWY_TEXT_HEADER_ERROR_SECTION_START: Section started before the previous
* ended. This is raised only if
* @endsection_template is set.
* @GWY_TEXT_HEADER_ERROR_PREFIX: Line lacks the mandatory prefix.
* @GWY_TEXT_HEADER_ERROR_GARBAGE: Line cannot be parsed into a key-value pair.
* @GWY_TEXT_HEADER_ERROR_KEY: Key name is invalid, namely empty.
* @GWY_TEXT_HEADER_ERROR_VALUE: Value is invalid. This is never raised by
* the parser.
* @GWY_TEXT_HEADER_ERROR_TERMINATOR: The text header has ended without being
* terminated by specified terminator.
*
* Error codes returned by text header parsing.
*
* Some errors, in particular %GWY_TEXT_HEADER_ERROR_KEY and
* %GWY_TEXT_HEADER_ERROR_VALUE are expected to be raised by user callbacks
* (they are not restricted to these codes though).
*
* Since: 2.18
**/
/**
* GwyTextHeaderContext:
*
* #GwyTextHeaderContext represents the parsing state. It is an opaque data
* structure and should be only manipulated with the functions below.
*
* Since: 2.18
**/
/**
* GwyTextHeaderParser:
* @comment_prefix: Prefix denoting comment lines. It is possible to specify
* multiple prefixes by separating them with newline ("\n").
* @section_template: Section start template. It must contain the character
* "\x1a" in the place where the section name apprears.
* For example, "[Section \x1a]".
* @endsection_template: Section end template. It may or may not contain the
* substitute character "\x1a" depending on whether the
* section end markers contain the section name. It is
* invalid to set @endsection_template without setting
* @section_template. Example: "[Section \x1a End]".
* @section_accessor: Glue to put between the section name and key when
* constructing hash table keys. It is invalid to set
* @section_accessor without setting @section_template.
* Typically, "::" is used.
* @line_prefix: Mandatory prefix of each line. Note this applies only to
* key-value lines. The templates, such comments, sections and
* terminators, must still include @line_prefix if they start
* with it.
* @key_value_separator: The string separating keys and values on each line.
* Typically, "=" or ":" is used. When left %NULL,
* whitespace plays the role of the separator. Of
* course, keys cannot contain whitespace then.
* @terminator: Line that marks end of the header. It is mandatory if
* specified, @GWY_TEXT_HEADER_ERROR_TERMINATOR is raised when
* the header ends sooner than @terminator is found.
* @item: Callback called when a key-value pair is found. If set it is
* responsible for inserting the pair to the hash table with
* g_hash_table_replace(). It is free to insert a different pair or
* nothing. It must return %FALSE if it raises an error.
* @section: Callback called when a section starts. It must return %FALSE if
* it raises an error.
* @endsection: Callback called when a section end. It must return %FALSE if
* it raises an error.
* @end: Callback called when the parsing finishes successfully, @length
* contains the length of parsed text in bytes.
* @error: Callback called when an error occurs, including errors raised by
* other user callbacks. If it returns %TRUE the error is considered
* fatal and the parsing terminates immediately. If it is left unset
* no errors are fatal hence no errors are reported to the caller.
* @destroy_key: Function to destroy keys, passed to g_hash_table_new_full().
* It is invalid to set @destroy_key if @item callback is not
* set.
* @destroy_value: Function to destroy values, passed to
* g_hash_table_new_full(). It is invalid to set
* @destroy_value if @item callback is not set.
*
* Text header parser specification.
*
* Memory considerations: In general, the parser attempts to reuse the contents
* of @header directly for the hash keys and values. There are two cases when
* it cannot: sectioning implies that keys must be constructed dynamically
* and the use of @item callback means the parser has no control on what is
* inserted into the hash table.
*
* This means that the @item callback must free @key if sectioning is used and
* it is not going to actually use it as the hash table key. And, of course,
* suitable @destroy_key and @destroy_value functions must be set.
*
* Since: 2.18
**/
/* vim: set cin et ts=4 sw=4 cino=>1s,e0,n0,f0,{0,}0,^0,\:1s,=0,g1s,h0,t0,+1s,c3,(0,u0 : */
|