/usr/share/perl5/Spreadsheet/ParseExcel/Utility.pm is in libspreadsheet-parseexcel-perl 0.5800-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 | package Spreadsheet::ParseExcel::Utility;
###############################################################################
#
# Spreadsheet::ParseExcel::Utility - Utility functions for ParseExcel.
#
# Used in conjunction with Spreadsheet::ParseExcel.
#
# Copyright (c) 2009 John McNamara
# Copyright (c) 2006-2008 Gabor Szabo
# Copyright (c) 2000-2006 Kawai Takanori
#
# perltidy with standard settings.
#
# Documentation after __END__
#
use strict;
use warnings;
require Exporter;
use vars qw(@ISA @EXPORT_OK);
@ISA = qw(Exporter);
@EXPORT_OK = qw(ExcelFmt LocaltimeExcel ExcelLocaltime
col2int int2col sheetRef xls2csv);
our $VERSION = '0.58';
my $qrNUMBER = qr/(^[+-]?\d+(\.\d+)?$)|(^[+-]?\d+\.?(\d*)[eE][+-](\d+))$/;
###############################################################################
#
# ExcelFmt()
#
# This function takes an Excel style number format and converts a number into
# that format. for example: 'hh:mm:ss AM/PM' + 0.01023148 = '12:14:44 AM'.
#
# It does this with a type of templating mechanism. The format string is parsed
# to identify tokens that need to be replaced and their position within the
# string is recorded. These can be thought of as placeholders. The number is
# then converted to the required formats and substituted into the placeholders.
#
# Interested parties should refer to the Excel documentation on cell formats for
# more information: http://office.microsoft.com/en-us/excel/HP051995001033.aspx
# The Microsoft documentation for the Excel Binary File Format, [MS-XLS].pdf,
# also contains a ABNF grammar for number format strings.
#
# Maintainers notes:
# ==================
#
# Note on format subsections:
# A format string can contain 4 possible sub-sections separated by semi-colons:
# Positive numbers, negative numbers, zero values, and text.
# For example: _(* #,##0_);_(* (#,##0);_(* "-"_);_(@_)
#
# Note on conditional formats.
# A number format in Excel can have a conditional expression such as:
# [>9999999](000)000-0000;000-0000
# This is equivalent to the following in Perl:
# $format = $number > 9999999 ? '(000)000-0000' : '000-0000';
# Nested conditionals are also possible but we don't support them.
#
# Efficiency: The excessive use of substr() isn't very efficient. However,
# it probably doesn't merit rewriting this function with a parser or regular
# expressions and \G.
#
# TODO: I think the single quote handling may not be required. Check.
#
sub ExcelFmt {
my ( $format_str, $number, $is_1904, $number_type, $want_subformats ) = @_;
# Return text strings without further formatting.
return $number unless $number =~ $qrNUMBER;
# Handle OpenOffice.org GENERAL format.
$format_str = '@' if uc($format_str) eq "GENERAL";
# Check for a conditional at the start of the format. See notes above.
my $conditional;
if ( $format_str =~ /^\[([<>=][^\]]+)\](.*)$/ ) {
$conditional = $1;
$format_str = $2;
}
# Ignore the underscore token which is used to indicate a padding space.
$format_str =~ s/_/ /g;
# Split the format string into 4 possible sub-sections: positive numbers,
# negative numbers, zero values, and text. See notes above.
my @formats;
my $section = 0;
my $double_quote = 0;
my $single_quote = 0;
# Initial parsing of the format string to remove escape characters. This
# also handles quoted strings. See note about single quotes above.
CHARACTER:
for my $char ( split //, $format_str ) {
if ( $double_quote or $single_quote ) {
$formats[$section] .= $char;
$double_quote = 0 if $char eq '"';
$single_quote = 0;
next CHARACTER;
}
if ( $char eq ';' ) {
$section++;
next CHARACTER;
}
elsif ( $char eq '"' ) {
$double_quote = 1;
}
elsif ( $char eq '!' ) {
$single_quote = 1;
}
elsif ( $char eq '\\' ) {
$single_quote = 1;
}
elsif ( $char eq '(' ) {
next CHARACTER; # Ignore.
}
elsif ( $char eq ')' ) {
next CHARACTER; # Ignore.
}
# Convert upper case OpenOffice.org date/time formats to lowercase..
$char = lc($char) if $char =~ /[DMYHS]/;
$formats[$section] .= $char;
}
# Select the appropriate format from the 4 possible sub-sections:
# positive numbers, negative numbers, zero values, and text.
# We ignore the Text section since non-numeric values are returned
# unformatted at the start of the function.
my $format;
$section = 0;
if ( @formats == 1 ) {
$section = 0;
}
elsif ( @formats == 2 ) {
if ( $number < 0 ) {
$section = 1;
}
else {
$section = 0;
}
}
elsif ( @formats == 3 ) {
if ( $number == 0 ) {
$section = 2;
}
elsif ( $number < 0 ) {
$section = 1;
}
else {
$section = 0;
}
}
else {
$section = 0;
}
# Override the previous choice if the format is conditional.
if ($conditional) {
# TODO. Replace string eval with a function.
$section = eval "$number $conditional" ? 0 : 1;
}
# We now have the required format.
$format = $formats[$section];
# The format string can contain one of the following colours:
# [Black] [Blue] [Cyan] [Green] [Magenta] [Red] [White] [Yellow]
# or the string [ColorX] where x is a colour index from 1 to 56.
# We don't use the colour but we return it to the caller.
#
my $color = '';
if ( $format =~ s/^(\[[A-Z][a-z]{2,}(\d{1,2})?\])// ) {
$color = $1;
}
# Remove the locale, such as [$-409], from the format string.
my $locale = '';
if ( $format =~ s/^(\[\$?-\d+\])// ) {
$locale = $1;
}
# Replace currency locale, such as [$$-409], with $ in the format string.
# See the RT#60547 test cases in 21_number_format_user.t.
if ( $format =~ s/(\[\$([^-]+)(-\d+)?\])/$2/s ) {
$locale = $1;
}
# Remove leading # from '# ?/?', '# ??/??' fraction formats.
$format =~ s{# \?}{?}g;
# Parse the format string and create an AoA of placeholders that contain
# the parts of the string to be replaced. The format of the information
# stored is: [ $token, $start_pos, $end_pos, $option_info ].
#
my $format_mode = ''; # Either: '', 'number', 'date'
my $pos = 0; # Character position within format string.
my @placeholders = (); # Arefs with parts of the format to be replaced.
my $token = ''; # The actual format extracted from the total str.
my $start_pos; # A position variable. Initial parser position.
my $token_start = -1; # A position variable.
my $decimal_pos = -1; # Position of the punctuation char "." or ",".
my $comma_count = 0; # Count of the commas in the format.
my $is_fraction = 0; # Number format is a fraction.
my $is_currency = 0; # Number format is a currency.
my $is_percent = 0; # Number format is a percentage.
my $is_12_hour = 0; # Time format is using 12 hour clock.
my $seen_dot = 0; # Treat only the first "." as the decimal point.
# Parse the format.
PARSER:
while ( $pos < length $format ) {
$start_pos = $pos;
my $char = substr( $format, $pos, 1 );
# Ignore control format characters such as '#0+-.?eE,%'. However,
# only ignore '.' if it is the first one encountered. RT 45502.
if ( ( !$seen_dot && $char !~ /[#0\+\-\.\?eE\,\%]/ )
|| $char !~ /[#0\+\-\?eE\,\%]/ )
{
if ( $token_start != -1 ) {
push @placeholders,
[
substr( $format, $token_start, $pos - $token_start ),
$decimal_pos, $pos - $token_start
];
$token_start = -1;
}
}
# Processing for quoted strings within the format. See notes above.
if ( $char eq '"' ) {
$double_quote = $double_quote ? 0 : 1;
$pos++;
next PARSER;
}
elsif ( $char eq '!' ) {
$single_quote = 1;
$pos++;
next PARSER;
}
elsif ( $char eq '\\' ) {
if ( $single_quote != 1 ) {
$single_quote = 1;
$pos++;
next PARSER;
}
}
if ( ( defined($double_quote) and ($double_quote) )
or ( defined($single_quote) and ($single_quote) )
or ( $seen_dot && $char eq '.' ) )
{
$single_quote = 0;
if (
( $format_mode ne 'date' )
and ( ( substr( $format, $pos, 2 ) eq "\x81\xA2" )
|| ( substr( $format, $pos, 2 ) eq "\x81\xA3" )
|| ( substr( $format, $pos, 2 ) eq "\xA2\xA4" )
|| ( substr( $format, $pos, 2 ) eq "\xA2\xA5" ) )
)
{
# The above matches are currency symbols.
push @placeholders,
[ substr( $format, $pos, 2 ), length($token), 2 ];
$is_currency = 1;
$pos += 2;
}
else {
$pos++;
}
}
elsif (
( $char =~ /[#0\+\.\?eE\,\%]/ )
|| ( ( $format_mode ne 'date' )
and ( ( $char eq '-' ) || ( $char eq '(' ) || ( $char eq ')' ) )
)
)
{
$format_mode = 'number' unless $format_mode;
if ( substr( $format, $pos, 1 ) =~ /[#0]/ ) {
if (
substr( $format, $pos ) =~
/^([#0]+[\.]?[0#]*[eE][\+\-][0#]+)/ )
{
push @placeholders, [ $1, $pos, length($1) ];
$pos += length($1);
}
else {
if ( $token_start == -1 ) {
$token_start = $pos;
$decimal_pos = length($token);
}
}
}
elsif ( substr( $format, $pos, 1 ) eq '?' ) {
# Look for a fraction format like ?/? or ??/??
if ( $token_start != -1 ) {
push @placeholders,
[
substr(
$format, $token_start, $pos - $token_start + 1
),
$decimal_pos,
$pos - $token_start + 1
];
}
$token_start = $pos;
# Find the end of the fraction format.
FRACTION:
while ( $pos < length($format) ) {
if ( substr( $format, $pos, 1 ) eq '/' ) {
$is_fraction = 1;
}
elsif ( substr( $format, $pos, 1 ) eq '?' ) {
$pos++;
next FRACTION;
}
else {
if ( $is_fraction
&& ( substr( $format, $pos, 1 ) =~ /[0-9]/ ) )
{
# TODO: Could invert if() logic and remove this.
$pos++;
next FRACTION;
}
else {
last FRACTION;
}
}
$pos++;
}
$pos--;
push @placeholders,
[
substr( $format, $token_start, $pos - $token_start + 1 ),
length($token), $pos - $token_start + 1
];
$token_start = -1;
}
elsif ( substr( $format, $pos, 3 ) =~ /^[eE][\+\-][0#]$/ ) {
if ( substr( $format, $pos ) =~ /([eE][\+\-][0#]+)/ ) {
push @placeholders, [ $1, $pos, length($1) ];
$pos += length($1);
}
$token_start = -1;
}
else {
if ( $token_start != -1 ) {
push @placeholders,
[
substr( $format, $token_start, $pos - $token_start ),
$decimal_pos, $pos - $token_start
];
$token_start = -1;
}
if ( substr( $format, $pos, 1 ) =~ /[\+\-]/ ) {
push @placeholders,
[ substr( $format, $pos, 1 ), length($token), 1 ];
$is_currency = 1;
}
elsif ( substr( $format, $pos, 1 ) eq '.' ) {
push @placeholders,
[ substr( $format, $pos, 1 ), length($token), 1 ];
$seen_dot = 1;
}
elsif ( substr( $format, $pos, 1 ) eq ',' ) {
$comma_count++;
push @placeholders,
[ substr( $format, $pos, 1 ), length($token), 1 ];
}
elsif ( substr( $format, $pos, 1 ) eq '%' ) {
$is_percent = 1;
}
elsif (( substr( $format, $pos, 1 ) eq '(' )
|| ( substr( $format, $pos, 1 ) eq ')' ) )
{
push @placeholders,
[ substr( $format, $pos, 1 ), length($token), 1 ];
$is_currency = 1;
}
}
$pos++;
}
elsif ( $char =~ /[ymdhsapg]/i ) {
$format_mode = 'date' unless $format_mode;
if ( substr( $format, $pos, 5 ) =~ /am\/pm/i ) {
push @placeholders, [ 'am/pm', length($token), 5 ];
$is_12_hour = 1;
$pos += 5;
}
elsif ( substr( $format, $pos, 3 ) =~ /a\/p/i ) {
push @placeholders, [ 'a/p', length($token), 3 ];
$is_12_hour = 1;
$pos += 3;
}
elsif ( substr( $format, $pos, 5 ) eq 'mmmmm' ) {
push @placeholders, [ 'mmmmm', length($token), 5 ];
$pos += 5;
}
elsif (( substr( $format, $pos, 4 ) eq 'mmmm' )
|| ( substr( $format, $pos, 4 ) eq 'dddd' )
|| ( substr( $format, $pos, 4 ) eq 'yyyy' )
|| ( substr( $format, $pos, 4 ) eq 'ggge' ) )
{
push @placeholders,
[ substr( $format, $pos, 4 ), length($token), 4 ];
$pos += 4;
}
elsif (( substr( $format, $pos, 3 ) eq 'ddd' )
|| ( substr( $format, $pos, 3 ) eq 'mmm' )
|| ( substr( $format, $pos, 3 ) eq 'yyy' ) )
{
push @placeholders,
[ substr( $format, $pos, 3 ), length($token), 3 ];
$pos += 3;
}
elsif (( substr( $format, $pos, 2 ) eq 'yy' )
|| ( substr( $format, $pos, 2 ) eq 'mm' )
|| ( substr( $format, $pos, 2 ) eq 'dd' )
|| ( substr( $format, $pos, 2 ) eq 'hh' )
|| ( substr( $format, $pos, 2 ) eq 'ss' )
|| ( substr( $format, $pos, 2 ) eq 'ge' ) )
{
if (
( substr( $format, $pos, 2 ) eq 'mm' )
&& (@placeholders)
&& ( ( $placeholders[-1]->[0] eq 'h' )
or ( $placeholders[-1]->[0] eq 'hh' ) )
)
{
# For this case 'm' is minutes not months.
push @placeholders, [ 'mm', length($token), 2, 'minutes' ];
}
else {
push @placeholders,
[ substr( $format, $pos, 2 ), length($token), 2 ];
}
if ( ( substr( $format, $pos, 2 ) eq 'ss' )
&& ( @placeholders > 1 ) )
{
if ( ( $placeholders[-2]->[0] eq 'm' )
|| ( $placeholders[-2]->[0] eq 'mm' ) )
{
# For this case 'm' is minutes not months.
push( @{ $placeholders[-2] }, 'minutes' );
}
}
$pos += 2;
}
elsif (( substr( $format, $pos, 1 ) eq 'm' )
|| ( substr( $format, $pos, 1 ) eq 'd' )
|| ( substr( $format, $pos, 1 ) eq 'h' )
|| ( substr( $format, $pos, 1 ) eq 's' ) )
{
if (
( substr( $format, $pos, 1 ) eq 'm' )
&& (@placeholders)
&& ( ( $placeholders[-1]->[0] eq 'h' )
or ( $placeholders[-1]->[0] eq 'hh' ) )
)
{
# For this case 'm' is minutes not months.
push @placeholders, [ 'm', length($token), 1, 'minutes' ];
}
else {
push @placeholders,
[ substr( $format, $pos, 1 ), length($token), 1 ];
}
if ( ( substr( $format, $pos, 1 ) eq 's' )
&& ( @placeholders > 1 ) )
{
if ( ( $placeholders[-2]->[0] eq 'm' )
|| ( $placeholders[-2]->[0] eq 'mm' ) )
{
# For this case 'm' is minutes not months.
push( @{ $placeholders[-2] }, 'minutes' );
}
}
$pos += 1;
}
}
elsif ( ( substr( $format, $pos, 3 ) eq '[h]' ) ) {
$format_mode = 'date' unless $format_mode;
push @placeholders, [ '[h]', length($token), 3 ];
$pos += 3;
}
elsif ( ( substr( $format, $pos, 4 ) eq '[mm]' ) ) {
$format_mode = 'date' unless $format_mode;
push @placeholders, [ '[mm]', length($token), 4 ];
$pos += 4;
}
elsif ( $char eq '@' ) {
push @placeholders, [ '@', length($token), 1 ];
$pos++;
}
elsif ( $char eq '*' ) {
push @placeholders,
[ substr( $format, $pos, 1 ), length($token), 1 ];
}
else {
$pos++;
}
$pos++ if ( $pos == $start_pos ); #No Format match
$token .= substr( $format, $start_pos, $pos - $start_pos );
} # End of parsing.
# Copy the located format string to a result string that we will perform
# the substitutions on and return to the user.
my $result = $token;
# Add a placeholder between the decimal/comma and end of the token, if any.
if ( $token_start != -1 ) {
push @placeholders,
[
substr( $format, $token_start, $pos - $token_start + 1 ),
$decimal_pos, $pos - $token_start + 1
];
}
#
# In the next sections we process date, number and text formats. We take a
# format such as yyyy/mm/dd and replace it with something like 2008/12/25.
#
if ( ( $format_mode eq 'date' ) && ( $number =~ $qrNUMBER ) ) {
# The maximum allowable date in Excel is 9999-12-31T23:59:59.000 which
# equates to 2958465.999+ in the 1900 epoch and 2957003.999+ in the
# 1904 epoch. We use 0 as the minimum in both epochs. The 1904 system
# actually supports negative numbers but that isn't worth the effort.
my $min_date = 0;
my $max_date = 2958466;
$max_date = 2957004 if $is_1904;
if ( $number < $min_date || $number >= $max_date ) {
return $number; # Return unformatted number.
}
# Process date formats.
my @time = ExcelLocaltime( $number, $is_1904 );
# 0 1 2 3 4 5 6 7
my ( $sec, $min, $hour, $day, $month, $year, $wday, $msec ) = @time;
$month++; # localtime() zero indexed month.
$year += 1900; # localtime() year.
my @full_month_name = qw(
None January February March April May June July
August September October November December
);
my @short_month_name = qw(
None Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
);
my @full_day_name = qw(
Sunday Monday Tuesday Wednesday Thursday Friday Saturday
);
my @short_day_name = qw(
Sun Mon Tue Wed Thu Fri Sat
);
# Replace the placeholders in the template such as yyyy mm dd with
# actual numbers or strings.
my $replacement;
for ( my $i = @placeholders - 1 ; $i >= 0 ; $i-- ) {
my $placeholder = $placeholders[$i];
if ( $placeholder->[-1] eq 'minutes' ) {
# For this case 'm/mm' is minutes not months.
if ( $placeholder->[0] eq 'mm' ) {
$replacement = sprintf( "%02d", $min );
}
else {
$replacement = sprintf( "%d", $min );
}
}
elsif ( $placeholder->[0] eq 'yyyy' ) {
# 4 digit Year. 2000 -> 2000.
$replacement = sprintf( '%04d', $year );
}
elsif ( $placeholder->[0] eq 'yy' ) {
# 2 digit Year. 2000 -> 00.
$replacement = sprintf( '%02d', $year % 100 );
}
elsif ( $placeholder->[0] eq 'mmmmm' ) {
# First character of the month name. 1 -> J.
$replacement = substr( $short_month_name[$month], 0, 1 );
}
elsif ( $placeholder->[0] eq 'mmmm' ) {
# Full month name. 1 -> January.
$replacement = $full_month_name[$month];
}
elsif ( $placeholder->[0] eq 'mmm' ) {
# Short month name. 1 -> Jan.
$replacement = $short_month_name[$month];
}
elsif ( $placeholder->[0] eq 'mm' ) {
# 2 digit month. 1 -> 01.
$replacement = sprintf( '%02d', $month );
}
elsif ( $placeholder->[0] eq 'm' ) {
# 1 digit month. 1 -> 1.
$replacement = sprintf( '%d', $month );
}
elsif ( $placeholder->[0] eq 'dddd' ) {
# Full day name. Wednesday (for example.)
$replacement = $full_day_name[$wday];
}
elsif ( $placeholder->[0] eq 'ddd' ) {
# Short day name. Wed (for example.)
$replacement = $short_day_name[$wday];
}
elsif ( $placeholder->[0] eq 'dd' ) {
# 2 digit day. 1 -> 01.
$replacement = sprintf( '%02d', $day );
}
elsif ( $placeholder->[0] eq 'd' ) {
# 1 digit day. 1 -> 1.
$replacement = sprintf( '%d', $day );
}
elsif ( $placeholder->[0] eq 'hh' ) {
# 2 digit hour.
if ($is_12_hour) {
my $hour_tmp = $hour % 12;
$hour_tmp = 12 if $hour % 12 == 0;
$replacement = sprintf( '%d', $hour_tmp );
}
else {
$replacement = sprintf( '%02d', $hour );
}
}
elsif ( $placeholder->[0] eq 'h' ) {
# 1 digit hour.
if ($is_12_hour) {
my $hour_tmp = $hour % 12;
$hour_tmp = 12 if $hour % 12 == 0;
$replacement = sprintf( '%2d', $hour_tmp );
}
else {
$replacement = sprintf( '%d', $hour );
}
}
elsif ( $placeholder->[0] eq 'ss' ) {
# 2 digit seconds.
$replacement = sprintf( '%02d', $sec );
}
elsif ( $placeholder->[0] eq 's' ) {
# 1 digit seconds.
$replacement = sprintf( '%d', $sec );
}
elsif ( $placeholder->[0] eq 'am/pm' ) {
# AM/PM.
$replacement = ( $hour >= 12 ) ? 'PM' : 'AM';
}
elsif ( $placeholder->[0] eq 'a/p' ) {
# AM/PM.
$replacement = ( $hour >= 12 ) ? 'P' : 'A';
}
elsif ( $placeholder->[0] eq '.' ) {
# Decimal point for seconds.
$replacement = '.';
}
elsif ( $placeholder->[0] =~ /(^0+$)/ ) {
# Milliseconds. For example h:ss.000.
my $length = length($1);
$replacement =
substr( sprintf( "%.${length}f", $msec / 1000 ), 2, $length );
}
elsif ( $placeholder->[0] eq '[h]' ) {
# Hours modulus 24. 25 displays as 25 not as 1.
$replacement = sprintf( '%d', int($number) * 24 + $hour );
}
elsif ( $placeholder->[0] eq '[mm]' ) {
# Mins modulus 60. 72 displays as 72 not as 12.
$replacement =
sprintf( '%d', ( int($number) * 24 + $hour ) * 60 + $min );
}
elsif ( $placeholder->[0] eq 'ge' ) {
require Spreadsheet::ParseExcel::FmtJapan;
# Japanese Nengo (aka Gengo) in initialism (abbr. name)
$replacement =
Spreadsheet::ParseExcel::FmtJapan::CnvNengo( abbr_name => @time );
}
elsif ( $placeholder->[0] eq 'ggge' ) {
require Spreadsheet::ParseExcel::FmtJapan;
# Japanese Nengo (aka Gengo) in Kanji (full name)
$replacement =
Spreadsheet::ParseExcel::FmtJapan::CnvNengo( name => @time );
}
elsif ( $placeholder->[0] eq '@' ) {
# Text format.
$replacement = $number;
}
# Substitute the replacement string back into the template.
substr( $result, $placeholder->[1], $placeholder->[2],
$replacement );
}
}
elsif ( ( $format_mode eq 'number' ) && ( $number =~ $qrNUMBER ) ) {
# Process non date formats.
if (@placeholders) {
while ( $placeholders[-1]->[0] eq ',' ) {
$comma_count--;
substr(
$result,
$placeholders[-1]->[1],
$placeholders[-1]->[2], ''
);
$number /= 1000;
pop @placeholders;
}
my $number_format = join( '', map { $_->[0] } @placeholders );
my $number_result;
my $str_length = 0;
my $engineering = 0;
my $is_decimal = 0;
my $is_integer = 0;
my $after_decimal = undef;
for my $token ( split //, $number_format ) {
if ( $token eq '.' ) {
$str_length++;
$is_decimal = 1;
}
elsif ( ( $token eq 'E' ) || ( $token eq 'e' ) ) {
$engineering = 1;
}
elsif ( $token eq '0' ) {
$str_length++;
$after_decimal++ if $is_decimal;
$is_integer = 1;
}
elsif ( $token eq '#' ) {
$after_decimal++ if $is_decimal;
$is_integer = 1;
}
elsif ( $token eq '?' ) {
$after_decimal++ if $is_decimal;
}
}
$number *= 100.0 if $is_percent;
my $data = ($is_currency) ? abs($number) : $number + 0;
if ($is_fraction) {
$number_result = sprintf( "%0${str_length}d", int($data) );
}
else {
if ($is_decimal) {
if ( defined $after_decimal ) {
$number_result =
sprintf "%0${str_length}.${after_decimal}f", $data;
}
else {
$number_result = sprintf "%0${str_length}f", $data;
}
# Fix for Perl and sprintf not rounding up like Excel.
# http://rt.cpan.org/Public/Bug/Display.html?id=45626
if ( $data =~ /^${number_result}5/ ) {
$number_result =
sprintf "%0${str_length}.${after_decimal}f",
$data . '1';
}
}
else {
$number_result = sprintf( "%0${str_length}.0f", $data );
}
}
$number_result = AddComma($number_result) if $comma_count > 0;
my $number_length = length($number_result);
my $decimal_pos = -1;
my $replacement;
for ( my $i = @placeholders - 1 ; $i >= 0 ; $i-- ) {
my $placeholder = $placeholders[$i];
if ( $placeholder->[0] =~
/([#0]*)([\.]?)([0#]*)([eE])([\+\-])([0#]+)/ )
{
substr( $result, $placeholder->[1], $placeholder->[2],
MakeE( $placeholder->[0], $number ) );
}
elsif ( $placeholder->[0] =~ /\// ) {
substr( $result, $placeholder->[1], $placeholder->[2],
MakeFraction( $placeholder->[0], $number, $is_integer )
);
}
elsif ( $placeholder->[0] eq '.' ) {
$number_length--;
$decimal_pos = $number_length;
}
elsif ( $placeholder->[0] eq '+' ) {
substr( $result, $placeholder->[1], $placeholder->[2],
( $number > 0 )
? '+'
: ( ( $number == 0 ) ? '+' : '-' ) );
}
elsif ( $placeholder->[0] eq '-' ) {
substr( $result, $placeholder->[1], $placeholder->[2],
( $number > 0 )
? ''
: ( ( $number == 0 ) ? '' : '-' ) );
}
elsif ( $placeholder->[0] eq '@' ) {
substr( $result, $placeholder->[1], $placeholder->[2],
$number );
}
elsif ( $placeholder->[0] eq '*' ) {
substr( $result, $placeholder->[1], $placeholder->[2], '' );
}
elsif (( $placeholder->[0] eq "\xA2\xA4" )
or ( $placeholder->[0] eq "\xA2\xA5" )
or ( $placeholder->[0] eq "\x81\xA2" )
or ( $placeholder->[0] eq "\x81\xA3" ) )
{
substr(
$result, $placeholder->[1],
$placeholder->[2], $placeholder->[0]
);
}
elsif (( $placeholder->[0] eq '(' )
or ( $placeholder->[0] eq ')' ) )
{
substr(
$result, $placeholder->[1],
$placeholder->[2], $placeholder->[0]
);
}
else {
if ( $number_length > 0 ) {
if ( $i <= 0 ) {
$replacement =
substr( $number_result, 0, $number_length );
$number_length = 0;
}
else {
my $real_part_length = length( $placeholder->[0] );
if ( $decimal_pos >= 0 ) {
my $format = $placeholder->[0];
$format =~ s/^#+//;
$real_part_length = length $format;
$real_part_length =
( $number_length <= $real_part_length )
? $number_length
: $real_part_length;
}
else {
$real_part_length =
( $number_length <= $real_part_length )
? $number_length
: $real_part_length;
}
$replacement =
substr( $number_result,
$number_length - $real_part_length,
$real_part_length );
$number_length -= $real_part_length;
}
}
else {
$replacement = '';
}
substr( $result, $placeholder->[1], $placeholder->[2],
"\x00" . $replacement );
}
}
$replacement =
( $number_length > 0 )
? substr( $number_result, 0, $number_length )
: '';
$result =~ s/\x00/$replacement/;
$result =~ s/\x00//g;
}
}
else {
# Process text formats
my $is_text = 0;
for ( my $i = @placeholders - 1 ; $i >= 0 ; $i-- ) {
my $placeholder = $placeholders[$i];
if ( $placeholder->[0] eq '@' ) {
substr( $result, $placeholder->[1], $placeholder->[2],
$number );
$is_text++;
}
else {
substr( $result, $placeholder->[1], $placeholder->[2], '' );
}
}
$result = $number unless $is_text;
} # End of placeholder substitutions.
# Trim the leading and trailing whitespace from the results.
$result =~ s/^\s+//;
$result =~ s/\s+$//;
# Fix for negative currency.
$result =~ s/^\$\-/\-\$/;
$result =~ s/^\$ \-/\-\$ /;
# Return color and locale strings if required.
if ($want_subformats) {
return ( $result, $color, $locale );
}
else {
return $result;
}
}
#------------------------------------------------------------------------------
# AddComma (for Spreadsheet::ParseExcel::Utility)
#------------------------------------------------------------------------------
sub AddComma {
my ($sNum) = @_;
if ( $sNum =~ /^([^\d]*)(\d\d\d\d+)(\.*.*)$/ ) {
my ( $sPre, $sObj, $sAft ) = ( $1, $2, $3 );
for ( my $i = length($sObj) - 3 ; $i > 0 ; $i -= 3 ) {
substr( $sObj, $i, 0, ',' );
}
return $sPre . $sObj . $sAft;
}
else {
return $sNum;
}
}
#------------------------------------------------------------------------------
# MakeFraction (for Spreadsheet::ParseExcel::Utility)
#------------------------------------------------------------------------------
sub MakeFraction {
my ( $sFmt, $iData, $iFlg ) = @_;
my $iBunbo;
my $iShou;
#1. Init
# print "FLG: $iFlg\n";
if ($iFlg) {
$iShou = $iData - int($iData);
return '' if ( $iShou == 0 );
}
else {
$iShou = $iData;
}
$iShou = abs($iShou);
my $sSWk;
#2.Calc BUNBO
#2.1 BUNBO defined
if ( $sFmt =~ /\/(\d+)$/ ) {
$iBunbo = $1;
return sprintf( "%d/%d", $iShou * $iBunbo, $iBunbo );
}
else {
#2.2 Calc BUNBO
$sFmt =~ /\/(\?+)$/;
my $iKeta = length($1);
my $iSWk = 1;
my $sSWk = '';
my $iBunsi;
for ( my $iBunbo = 2 ; $iBunbo < 10**$iKeta ; $iBunbo++ ) {
$iBunsi = int( $iShou * $iBunbo + 0.5 );
my $iCmp = abs( $iShou - ( $iBunsi / $iBunbo ) );
if ( $iCmp < $iSWk ) {
$iSWk = $iCmp;
$sSWk = sprintf( "%d/%d", $iBunsi, $iBunbo );
last if ( $iSWk == 0 );
}
}
return $sSWk;
}
}
#------------------------------------------------------------------------------
# MakeE (for Spreadsheet::ParseExcel::Utility)
#------------------------------------------------------------------------------
sub MakeE {
my ( $sFmt, $iData ) = @_;
$sFmt =~ /(([#0]*)[\.]?[#0]*)([eE])([\+\-][0#]+)/;
my ( $sKari, $iKeta, $sE, $sSisu ) = ( $1, length($2), $3, $4 );
$iKeta = 1 if ( $iKeta <= 0 );
my $iLog10 = 0;
$iLog10 = ( $iData == 0 ) ? 0 : ( log( abs($iData) ) / log(10) );
$iLog10 = (
int( $iLog10 / $iKeta ) +
( ( ( $iLog10 - int( $iLog10 / $iKeta ) ) < 0 ) ? -1 : 0 ) ) * $iKeta;
my $sUe = ExcelFmt( $sKari, $iData * ( 10**( $iLog10 * -1 ) ), 0 );
my $sShita = ExcelFmt( $sSisu, $iLog10, 0 );
return $sUe . $sE . $sShita;
}
#------------------------------------------------------------------------------
# LeapYear (for Spreadsheet::ParseExcel::Utility)
#------------------------------------------------------------------------------
sub LeapYear {
my ($iYear) = @_;
return 1 if ( $iYear == 1900 ); #Special for Excel
return ( ( ( $iYear % 4 ) == 0 )
&& ( ( $iYear % 100 ) || ( $iYear % 400 ) == 0 ) )
? 1
: 0;
}
#------------------------------------------------------------------------------
# LocaltimeExcel (for Spreadsheet::ParseExcel::Utility)
#------------------------------------------------------------------------------
sub LocaltimeExcel {
my ( $iSec, $iMin, $iHour, $iDay, $iMon, $iYear, $iwDay, $iMSec, $flg1904 )
= @_;
#0. Init
$iMon++;
$iYear += 1900;
#1. Calc Time
my $iTime;
$iTime = $iHour;
$iTime *= 60;
$iTime += $iMin;
$iTime *= 60;
$iTime += $iSec;
$iTime += $iMSec / 1000.0 if ( defined($iMSec) );
$iTime /= 86400.0; #3600*24(1day in seconds)
my $iY;
my $iYDays;
#2. Calc Days
if ($flg1904) {
$iY = 1904;
$iTime--; #Start from Jan 1st
$iYDays = 366;
}
else {
$iY = 1900;
$iYDays = 366; #In Excel 1900 is leap year (That's not TRUE!)
}
while ( $iY < $iYear ) {
$iTime += $iYDays;
$iY++;
$iYDays = ( LeapYear($iY) ) ? 366 : 365;
}
for ( my $iM = 1 ; $iM < $iMon ; $iM++ ) {
if ( $iM == 1
|| $iM == 3
|| $iM == 5
|| $iM == 7
|| $iM == 8
|| $iM == 10
|| $iM == 12 )
{
$iTime += 31;
}
elsif ( $iM == 4 || $iM == 6 || $iM == 9 || $iM == 11 ) {
$iTime += 30;
}
elsif ( $iM == 2 ) {
$iTime += ( LeapYear($iYear) ) ? 29 : 28;
}
}
$iTime += $iDay;
return $iTime;
}
#------------------------------------------------------------------------------
# ExcelLocaltime (for Spreadsheet::ParseExcel::Utility)
#------------------------------------------------------------------------------
sub ExcelLocaltime {
my ( $dObj, $flg1904 ) = @_;
my ( $iSec, $iMin, $iHour, $iDay, $iMon, $iYear, $iwDay, $iMSec );
my ( $iDt, $iTime, $iYDays );
$iDt = int($dObj);
$iTime = $dObj - $iDt;
#1. Calc Days
if ($flg1904) {
$iYear = 1904;
$iDt++; #Start from Jan 1st
$iYDays = 366;
$iwDay = ( ( $iDt + 4 ) % 7 );
}
else {
$iYear = 1900;
$iYDays = 366; #In Excel 1900 is leap year (That's not TRUE!)
$iwDay = ( ( $iDt + 6 ) % 7 );
}
while ( $iDt > $iYDays ) {
$iDt -= $iYDays;
$iYear++;
$iYDays =
( ( ( $iYear % 4 ) == 0 )
&& ( ( $iYear % 100 ) || ( $iYear % 400 ) == 0 ) ) ? 366 : 365;
}
$iYear -= 1900; # Localtime year is relative to 1900.
for ( $iMon = 1 ; $iMon < 12 ; $iMon++ ) {
my $iMD;
if ( $iMon == 1
|| $iMon == 3
|| $iMon == 5
|| $iMon == 7
|| $iMon == 8
|| $iMon == 10
|| $iMon == 12 )
{
$iMD = 31;
}
elsif ( $iMon == 4 || $iMon == 6 || $iMon == 9 || $iMon == 11 ) {
$iMD = 30;
}
elsif ( $iMon == 2 ) {
$iMD = ( ( $iYear % 4 ) == 0 ) ? 29 : 28;
}
last if ( $iDt <= $iMD );
$iDt -= $iMD;
}
$iMon -= 1; # Localtime month is 0 based.
#2. Calc Time
$iDay = $iDt;
$iTime += ( 0.0005 / 86400.0 );
$iTime *= 24.0;
$iHour = int($iTime);
$iTime -= $iHour;
$iTime *= 60.0;
$iMin = int($iTime);
$iTime -= $iMin;
$iTime *= 60.0;
$iSec = int($iTime);
$iTime -= $iSec;
$iTime *= 1000.0;
$iMSec = int($iTime);
return ( $iSec, $iMin, $iHour, $iDay, $iMon, $iYear, $iwDay, $iMSec );
}
# -----------------------------------------------------------------------------
# col2int (for Spreadsheet::ParseExcel::Utility)
#------------------------------------------------------------------------------
# converts a excel row letter into an int for use in an array
sub col2int {
my $result = 0;
my $str = shift;
my $incr = 0;
for ( my $i = length($str) ; $i > 0 ; $i-- ) {
my $char = substr( $str, $i - 1 );
my $curr += ord( lc($char) ) - ord('a') + 1;
$curr *= $incr if ($incr);
$result += $curr;
$incr += 26;
}
# this is one out as we range 0..x-1 not 1..x
$result--;
return $result;
}
# -----------------------------------------------------------------------------
# int2col (for Spreadsheet::ParseExcel::Utility)
#------------------------------------------------------------------------------
### int2col
# convert a column number into column letters
# @note this is quite a brute force coarse method
# does not manage values over 701 (ZZ)
# @arg number, to convert
# @returns string, column name
#
sub int2col {
my $out = "";
my $val = shift;
do {
$out .= chr( ( $val % 26 ) + ord('A') );
$val = int( $val / 26 ) - 1;
} while ( $val >= 0 );
return scalar reverse $out;
}
# -----------------------------------------------------------------------------
# sheetRef (for Spreadsheet::ParseExcel::Utility)
#------------------------------------------------------------------------------
# -----------------------------------------------------------------------------
### sheetRef
# convert an excel letter-number address into a useful array address
# @note that also Excel uses X-Y notation, we normally use Y-X in arrays
# @args $str, excel coord eg. A2
# @returns an array - 2 elements - column, row, or undefined
#
sub sheetRef {
my $str = shift;
my @ret;
$str =~ m/^(\D+)(\d+)$/;
if ( $1 && $2 ) {
push( @ret, $2 - 1, col2int($1) );
}
if ( $ret[0] < 0 ) {
undef @ret;
}
return @ret;
}
# -----------------------------------------------------------------------------
# xls2csv (for Spreadsheet::ParseExcel::Utility)
#------------------------------------------------------------------------------
### xls2csv
# convert a chunk of an excel file into csv text chunk
# @args $param, sheet-colrow:colrow (1-A1:B2 or A1:B2 for sheet 1
# @args $rotate, 0 or 1 decides if output should be rotated or not
# @returns string containing a chunk of csv
#
sub xls2csv {
my ( $filename, $regions, $rotate ) = @_;
my $sheet = 0;
# We need Text::CSV_XS for proper CSV handling.
require Text::CSV_XS;
# extract any sheet number from the region string
$regions =~ m/^(\d+)-(.*)/;
if ($2) {
$sheet = $1 - 1;
$regions = $2;
}
# now extract the start and end regions
$regions =~ m/(.*):(.*)/;
if ( !$1 || !$2 ) {
print STDERR "Bad Params";
return "";
}
my @start = sheetRef($1);
my @end = sheetRef($2);
if ( !@start ) {
print STDERR "Bad coorinates - $1";
return "";
}
if ( !@end ) {
print STDERR "Bad coorinates - $2";
return "";
}
if ( $start[1] > $end[1] ) {
print STDERR "Bad COLUMN ordering\n";
print STDERR "Start column " . int2col( $start[1] );
print STDERR " after end column " . int2col( $end[1] ) . "\n";
return "";
}
if ( $start[0] > $end[0] ) {
print STDERR "Bad ROW ordering\n";
print STDERR "Start row " . ( $start[0] + 1 );
print STDERR " after end row " . ( $end[0] + 1 ) . "\n";
exit;
}
# start the excel object now
my $oExcel = new Spreadsheet::ParseExcel;
my $oBook = $oExcel->Parse($filename);
# open the sheet
my $oWkS = $oBook->{Worksheet}[$sheet];
# now check that the region exists in the file
# if not truncate to the possible region
# output a warning msg
if ( $start[1] < $oWkS->{MinCol} ) {
print STDERR int2col( $start[1] )
. " < min col "
. int2col( $oWkS->{MinCol} )
. " Resetting\n";
$start[1] = $oWkS->{MinCol};
}
if ( $end[1] > $oWkS->{MaxCol} ) {
print STDERR int2col( $end[1] )
. " > max col "
. int2col( $oWkS->{MaxCol} )
. " Resetting\n";
$end[1] = $oWkS->{MaxCol};
}
if ( $start[0] < $oWkS->{MinRow} ) {
print STDERR ""
. ( $start[0] + 1 )
. " < min row "
. ( $oWkS->{MinRow} + 1 )
. " Resetting\n";
$start[0] = $oWkS->{MinCol};
}
if ( $end[0] > $oWkS->{MaxRow} ) {
print STDERR ""
. ( $end[0] + 1 )
. " > max row "
. ( $oWkS->{MaxRow} + 1 )
. " Resetting\n";
$end[0] = $oWkS->{MaxRow};
}
my $x1 = $start[1];
my $y1 = $start[0];
my $x2 = $end[1];
my $y2 = $end[0];
my @cell_data;
my $row = 0;
if ( !$rotate ) {
for ( my $y = $y1 ; $y <= $y2 ; $y++ ) {
for ( my $x = $x1 ; $x <= $x2 ; $x++ ) {
my $cell = $oWkS->{Cells}[$y][$x];
my $value;
if ( defined $cell ) {
$value .= $cell->value();
}
else {
$value = '';
}
push @{ $cell_data[$row] }, $value;
}
$row++;
}
}
else {
for ( my $x = $x1 ; $x <= $x2 ; $x++ ) {
for ( my $y = $y1 ; $y <= $y2 ; $y++ ) {
my $cell = $oWkS->{Cells}[$y][$x];
my $value;
if ( defined $cell ) {
$value .= $cell->value();
}
else {
$value = '';
}
push @{ $cell_data[$row] }, $value;
}
$row++;
}
}
# Create the CSV output string.
my $csv = Text::CSV_XS->new( { binary => 1, eol => $/ } );
my $output = "";
for my $row (@cell_data) {
$csv->combine(@$row);
$output .= $csv->string();
}
return $output;
}
1;
__END__
=pod
=head1 NAME
Spreadsheet::ParseExcel::Utility - Utility functions for Spreadsheet::ParseExcel.
=head1 SYNOPSIS
use Spreadsheet::ParseExcel::Utility qw(ExcelFmt ExcelLocaltime LocaltimeExcel);
# Convert localtime to Excel time
my $datetime = LocaltimeExcel(11, 10, 12, 23, 2, 64); # 1964-3-23 12:10:11
print $datetime, "\n"; # 23459.5070717593 (Excel date/time format)
# Convert Excel Time to localtime
my @time = ExcelLocaltime($datetime);
print join(":", @time), "\n"; # 11:10:12:23:2:64:1:0
# Formatting
print ExcelFmt('yyyy-mm-dd', $datetime), "\n"; # 1964-3-23
print ExcelFmt('m-d-yy', $datetime), "\n"; # 3-23-64
print ExcelFmt('#,##0', $datetime), "\n"; # 23,460
print ExcelFmt('#,##0.00', $datetime), "\n"; # 23,459.51
=head1 DESCRIPTION
The C<Spreadsheet::ParseExcel::Utility> module provides utility functions for working with ParseExcel and Excel data.
=head1 Functions
C<Spreadsheet::ParseExcel::Utility> can export the following functions:
ExcelFmt
ExcelLocaltime
LocaltimeExcel
col2int
int2col
sheetRef
xls2csv
These functions must be imported implicitly:
# Just one function.
use Spreadsheet::ParseExcel::Utility 'col2int';
# More than one.
use Spreadsheet::ParseExcel::Utility qw(ExcelFmt ExcelLocaltime LocaltimeExcel);
=head2 ExcelFmt($format_string, $number, $is_1904)
Excel stores data such as dates and currency values as numbers. The way these numbers are displayed is controlled by the number format string for the cell. For example a cell with a number format of C<'$#,##0.00'> for currency and a value of 1234.567 would be displayed as follows:
'$#,##0.00' + 1234.567 = '$1,234.57'.
The C<ExcelFmt()> function tries to emulate this formatting so that the user can convert raw numbers returned by C<Spreadsheet::ParseExel> to a desired format. For example:
print ExcelFmt('$#,##0.00', 1234.567); # $1,234.57.
The syntax of the function is:
my $text = ExcelFmt($format_string, $number, $is_1904);
Where C<$format_string> is an Excel number format string, C<$number> is a real or integer number and C<is_1904> is an optional flag to indicate that dates should use Excel's 1904 epoch instead of the default 1900 epoch.
C<ExcelFmt()> is also used internally to convert numbers returned by the C<Cell::unformatted()> method to the formatted value returned by the C<Cell::value()> method:
my $cell = $worksheet->get_cell( 0, 0 );
print $cell->unformatted(), "\n"; # 1234.567
print $cell->value(), "\n"; # $1,234.57
The most common usage for C<ExcelFmt> is to convert numbers to dates. Dates and times in Excel are represented by real numbers, for example "1 Jan 2001 12:30 PM" is represented by the number 36892.521. The integer part of the number stores the number of days since the epoch and the fractional part stores the percentage of the day. By applying an Excel number format the number is converted to the desired string representation:
print ExcelFmt('d mmm yyyy h:mm AM/PM', 36892.521); # 1 Jan 2001 12:30 PM
C<$is_1904> is an optional flag to indicate that dates should use Excel's 1904 epoch instead of the default 1900 epoch. Excel for Windows generally uses 1900 and Excel for Mac OS uses 1904. The C<$is1904> flag isn't required very often by a casual user and can usually be ignored.
=head2 ExcelLocaltime($excel_datetime, $is_1904)
The C<ExcelLocaltime()> function converts from an Excel date/time number to a C<localtime()>-like array of values:
my @time = ExcelLocaltime($excel_datetime);
# 0 1 2 3 4 5 6 7
my ( $sec, $min, $hour, $day, $month, $year, $wday, $msec ) = @time;
The array elements from C<(0 .. 6)> are the same as Perl's C<localtime()>. The last element C<$msec> is milliseconds. In particular it should be noted that, in common with C<localtime()>, the month is zero indexed and the year is the number of years since 1900. This means that you will usually need to do the following:
$month++;
$year += 1900;
See also Perl's documentation for L<localtime()|perlfunc>:
The C<$is_1904> flag is an optional. It is used to indicate that dates should use Excel's 1904 epoch instead of the default 1900 epoch.
=head2 LocaltimeExcel($sec, $min, $hour, $day, $month, $year, $wday, $msec, $is_1904)
The C<LocaltimeExcel()> function converts from a C<localtime()>-like array of values to an Excel date/time number:
$excel_datetime = LocaltimeExcel($sec, $min, $hour, $day, $month, $year, $wday, $msec);
The array elements from C<(0 .. 6)> are the same as Perl's C<localtime()>. The last element C<$msec> is milliseconds. In particular it should be noted that, in common with C<localtime()>, the month is zero indexed and the year is the number of years since 1900. See also Perl's documentation for L<localtime()|perlfunc>:
The C<$wday> and C<$msec> elements are usually optional. This time elements can also be zeroed if they aren't of interest:
# sec, min, hour, day, month, year
$excel_datetime = LocaltimeExcel( 0, 0, 0, 1, 0, 101 );
print ExcelFmt('d mmm yyyy', $excel_datetime); # 1 Jan 2001
The C<$is_1904> flag is also optional. It is used to indicate that dates should use Excel's 1904 epoch instead of the default 1900 epoch.
=head2 col2int($column)
The C<col2int()> function converts an Excel column letter to an zero-indexed column number:
print col2int('A'); # 0
print col2int('AA'); # 26
This function was contributed by Kevin Mulholland.
=head2 int2col($column_number)
The C<int2col()> function converts an zero-indexed Excel column number to a column letter:
print int2col(0); # 'A'
print int2col(26); # 'AA'
This function was contributed by Kevin Mulholland.
=head2 sheetRef($cell_string)
The C<sheetRef()> function converts an Excel cell reference in 'A1' notation to a zero-indexed C<(row, col)> pair.
my ($row, $col) = sheetRef('A1'); # ( 0, 0 )
my ($row, $col) = sheetRef('C2'); # ( 1, 2 )
This function was contributed by Kevin Mulholland.
=head2 xls2csv($filename, $region, $rotate)
The C<xls2csv()> function converts a section of an Excel file into a CSV text string.
$csv_text = xls2csv($filename, $region, $rotate);
Where:
$region = "sheet-colrow:colrow"
For example '1-A1:B2' means 'A1:B2' for sheet 1.
and
$rotate = 0 or 1 (output is rotated/transposed or not)
This function requires C<Text::CSV_XS> to be installed. It was contributed by Kevin Mulholland along with the C<xls2csv> script in the C<sample> directory of the distro.
See also the following xls2csv utilities: Ken Prows' C<xls2csv>: http://search.cpan.org/~ken/xls2csv/script/xls2csv and H.Merijn Brand's C<xls2csv> (which is part of Spreadsheet::Read): http://search.cpan.org/~hmbrand/Spreadsheet-Read/
=head1 AUTHOR
Maintainer 0.40+: John McNamara jmcnamara@cpan.org
Maintainer 0.27-0.33: Gabor Szabo szabgab@cpan.org
Original author: Kawai Takanori kwitknr@cpan.org
=head1 COPYRIGHT
Copyright (c) 2009-2010 John McNamara
Copyright (c) 2006-2008 Gabor Szabo
Copyright (c) 2000-2006 Kawai Takanori
All rights reserved.
You may distribute under the terms of either the GNU General Public License or the Artistic License, as specified in the Perl README file.
=cut
|