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
|
package xlsx
import (
"archive/zip"
"bytes"
"encoding/xml"
"errors"
"fmt"
"io"
"path"
"strconv"
"strings"
)
const (
sheetEnding = `</sheetData></worksheet>`
fixedCellRefChar = "$"
cellRangeChar = ":"
externalSheetBangChar = "!"
)
// XLSXReaderError is the standard error type for otherwise undefined
// errors in the XSLX reading process.
type XLSXReaderError struct {
Err string
}
// Error returns a string value from an XLSXReaderError struct in order
// that it might comply with the builtin.error interface.
func (e *XLSXReaderError) Error() string {
return e.Err
}
// getRangeFromString is an internal helper function that converts
// XLSX internal range syntax to a pair of integers. For example,
// the range string "1:3" yield the upper and lower integers 1 and 3.
func getRangeFromString(rangeString string) (lower int, upper int, error error) {
var parts []string
parts = strings.SplitN(rangeString, cellRangeChar, 2)
if parts[0] == "" {
error = errors.New(fmt.Sprintf("Invalid range '%s'\n", rangeString))
}
if parts[1] == "" {
error = errors.New(fmt.Sprintf("Invalid range '%s'\n", rangeString))
}
lower, error = strconv.Atoi(parts[0])
if error != nil {
error = errors.New(fmt.Sprintf("Invalid range (not integer in lower bound) %s\n", rangeString))
}
upper, error = strconv.Atoi(parts[1])
if error != nil {
error = errors.New(fmt.Sprintf("Invalid range (not integer in upper bound) %s\n", rangeString))
}
return lower, upper, error
}
// ColLettersToIndex is used to convert a character based column
// reference to a zero based numeric column identifier.
func ColLettersToIndex(letters string) int {
sum, mul, n := 0, 1, 0
for i := len(letters) - 1; i >= 0; i, mul, n = i-1, mul*26, 1 {
c := letters[i]
switch {
case 'A' <= c && c <= 'Z':
n += int(c - 'A')
case 'a' <= c && c <= 'z':
n += int(c - 'a')
}
sum += n * mul
}
return sum
}
// Get the largestDenominator that is a multiple of a basedDenominator
// and fits at least once into a given numerator.
func getLargestDenominator(numerator, multiple, baseDenominator, power int) (int, int) {
if numerator/multiple == 0 {
return 1, power
}
next, nextPower := getLargestDenominator(
numerator, multiple*baseDenominator, baseDenominator, power+1)
if next > multiple {
return next, nextPower
}
return multiple, power
}
// Convers a list of numbers representing a column into a alphabetic
// representation, as used in the spreadsheet.
func formatColumnName(colId []int) string {
lastPart := len(colId) - 1
result := ""
for n, part := range colId {
if n == lastPart {
// The least significant number is in the
// range 0-25, all other numbers are 1-26,
// hence we use a differente offset for the
// last part.
result += string(part + 65)
} else {
// Don't output leading 0s, as there is no
// representation of 0 in this format.
if part > 0 {
result += string(part + 64)
}
}
}
return result
}
func smooshBase26Slice(b26 []int) []int {
// Smoosh values together, eliminating 0s from all but the
// least significant part.
lastButOnePart := len(b26) - 2
for i := lastButOnePart; i > 0; i-- {
part := b26[i]
if part == 0 {
greaterPart := b26[i-1]
if greaterPart > 0 {
b26[i-1] = greaterPart - 1
b26[i] = 26
}
}
}
return b26
}
func intToBase26(x int) (parts []int) {
// Excel column codes are pure evil - in essence they're just
// base26, but they don't represent the number 0.
b26Denominator, _ := getLargestDenominator(x, 1, 26, 0)
// This loop terminates because integer division of 1 / 26
// returns 0.
for d := b26Denominator; d > 0; d = d / 26 {
value := x / d
remainder := x % d
parts = append(parts, value)
x = remainder
}
return parts
}
// ColIndexToLetters is used to convert a zero based, numeric column
// indentifier into a character code.
func ColIndexToLetters(colRef int) string {
parts := intToBase26(colRef)
return formatColumnName(smooshBase26Slice(parts))
}
// RowIndexToString is used to convert a zero based, numeric row
// indentifier into its string representation.
func RowIndexToString(rowRef int) string {
return strconv.Itoa(rowRef + 1)
}
// letterOnlyMapF is used in conjunction with strings.Map to return
// only the characters A-Z and a-z in a string
func letterOnlyMapF(rune rune) rune {
switch {
case 'A' <= rune && rune <= 'Z':
return rune
case 'a' <= rune && rune <= 'z':
return rune - 32
}
return -1
}
// intOnlyMapF is used in conjunction with strings.Map to return only
// the numeric portions of a string.
func intOnlyMapF(rune rune) rune {
if rune >= 48 && rune < 58 {
return rune
}
return -1
}
// GetCoordsFromCellIDString returns the zero based cartesian
// coordinates from a cell name in Excel format, e.g. the cellIDString
// "A1" returns 0, 0 and the "B3" return 1, 2.
func GetCoordsFromCellIDString(cellIDString string) (x, y int, error error) {
var letterPart string = strings.Map(letterOnlyMapF, cellIDString)
y, error = strconv.Atoi(strings.Map(intOnlyMapF, cellIDString))
if error != nil {
return x, y, error
}
y -= 1 // Zero based
x = ColLettersToIndex(letterPart)
return x, y, error
}
// GetCellIDStringFromCoords returns the Excel format cell name that
// represents a pair of zero based cartesian coordinates.
func GetCellIDStringFromCoords(x, y int) string {
return GetCellIDStringFromCoordsWithFixed(x, y, false, false)
}
// GetCellIDStringFromCoordsWithFixed returns the Excel format cell name that
// represents a pair of zero based cartesian coordinates.
// It can specify either value as fixed.
func GetCellIDStringFromCoordsWithFixed(x, y int, xFixed, yFixed bool) string {
xStr := ColIndexToLetters(x)
if xFixed {
xStr = fixedCellRefChar + xStr
}
yStr := RowIndexToString(y)
if yFixed {
yStr = fixedCellRefChar + yStr
}
return xStr + yStr
}
// getMaxMinFromDimensionRef return the zero based cartesian maximum
// and minimum coordinates from the dimension reference embedded in a
// XLSX worksheet. For example, the dimension reference "A1:B2"
// returns "0,0", "1,1".
func getMaxMinFromDimensionRef(ref string) (minx, miny, maxx, maxy int, err error) {
var parts []string
parts = strings.Split(ref, cellRangeChar)
minx, miny, err = GetCoordsFromCellIDString(parts[0])
if err != nil {
return -1, -1, -1, -1, err
}
maxx, maxy, err = GetCoordsFromCellIDString(parts[1])
if err != nil {
return -1, -1, -1, -1, err
}
return
}
// calculateMaxMinFromWorkSheet works out the dimensions of a spreadsheet
// that doesn't have a DimensionRef set. The only case currently
// known where this is true is with XLSX exported from Google Docs.
// This is also true for XLSX files created through the streaming APIs.
func calculateMaxMinFromWorksheet(worksheet *xlsxWorksheet) (minx, miny, maxx, maxy int, err error) {
// Note, this method could be very slow for large spreadsheets.
var x, y int
var maxVal int
maxVal = int(^uint(0) >> 1)
minx = maxVal
miny = maxVal
maxy = 0
maxx = 0
for _, row := range worksheet.SheetData.Row {
for _, cell := range row.C {
x, y, err = GetCoordsFromCellIDString(cell.R)
if err != nil {
return -1, -1, -1, -1, err
}
if x < minx {
minx = x
}
if x > maxx {
maxx = x
}
if y < miny {
miny = y
}
if y > maxy {
maxy = y
}
}
}
if minx == maxVal {
minx = 0
}
if miny == maxVal {
miny = 0
}
return
}
// makeRowFromSpan will, when given a span expressed as a string,
// return an empty Row large enough to encompass that span and
// populate it with empty cells. All rows start from cell 1 -
// regardless of the lower bound of the span.
func makeRowFromSpan(spans string, sheet *Sheet) *Row {
var error error
var upper int
var row *Row
var cell *Cell
row = new(Row)
row.Sheet = sheet
_, upper, error = getRangeFromString(spans)
if error != nil {
panic(error)
}
error = nil
row.Cells = make([]*Cell, upper)
for i := 0; i < upper; i++ {
cell = new(Cell)
cell.Value = ""
row.Cells[i] = cell
}
return row
}
// makeRowFromRaw returns the Row representation of the xlsxRow.
func makeRowFromRaw(rawrow xlsxRow, sheet *Sheet) *Row {
var upper int
var row *Row
var cell *Cell
row = new(Row)
row.Sheet = sheet
upper = -1
for _, rawcell := range rawrow.C {
if rawcell.R != "" {
x, _, error := GetCoordsFromCellIDString(rawcell.R)
if error != nil {
panic(fmt.Sprintf("Invalid Cell Coord, %s\n", rawcell.R))
}
if x > upper {
upper = x
}
continue
}
upper++
}
upper++
row.OutlineLevel = rawrow.OutlineLevel
row.Cells = make([]*Cell, upper)
for i := 0; i < upper; i++ {
cell = new(Cell)
cell.Value = ""
row.Cells[i] = cell
}
return row
}
func makeEmptyRow(sheet *Sheet) *Row {
row := new(Row)
row.Cells = make([]*Cell, 0)
row.Sheet = sheet
return row
}
type sharedFormula struct {
x, y int
formula string
}
func formulaForCell(rawcell xlsxC, sharedFormulas map[int]sharedFormula) string {
var res string
f := rawcell.F
if f == nil {
return ""
}
if f.T == "shared" {
x, y, err := GetCoordsFromCellIDString(rawcell.R)
if err != nil {
res = f.Content
} else {
if f.Ref != "" {
res = f.Content
sharedFormulas[f.Si] = sharedFormula{x, y, res}
} else {
sharedFormula := sharedFormulas[f.Si]
dx := x - sharedFormula.x
dy := y - sharedFormula.y
orig := []byte(sharedFormula.formula)
var start, end int
var stringLiteral bool
for end = 0; end < len(orig); end++ {
c := orig[end]
if c == '"' {
stringLiteral = !stringLiteral
}
if stringLiteral {
continue // Skip characters in quotes
}
if c >= 'A' && c <= 'Z' || c == '$' {
res += string(orig[start:end])
start = end
end++
foundNum := false
for ; end < len(orig); end++ {
idc := orig[end]
if idc >= '0' && idc <= '9' || idc == '$' {
foundNum = true
} else if idc >= 'A' && idc <= 'Z' {
if foundNum {
break
}
} else {
break
}
}
if foundNum {
cellID := string(orig[start:end])
res += shiftCell(cellID, dx, dy)
start = end
}
}
}
if start < len(orig) {
res += string(orig[start:])
}
}
}
} else {
res = f.Content
}
return strings.Trim(res, " \t\n\r")
}
// shiftCell returns the cell shifted according to dx and dy taking into consideration of absolute
// references with dollar sign ($)
func shiftCell(cellID string, dx, dy int) string {
fx, fy, _ := GetCoordsFromCellIDString(cellID)
// Is fixed column?
fixedCol := strings.Index(cellID, fixedCellRefChar) == 0
// Is fixed row?
fixedRow := strings.LastIndex(cellID, fixedCellRefChar) > 0
if !fixedCol {
// Shift column
fx += dx
}
if !fixedRow {
// Shift row
fy += dy
}
// New shifted cell
shiftedCellID := GetCellIDStringFromCoords(fx, fy)
if !fixedCol && !fixedRow {
return shiftedCellID
}
// There are absolute references, need to put the $ back into the formula.
letterPart := strings.Map(letterOnlyMapF, shiftedCellID)
numberPart := strings.Map(intOnlyMapF, shiftedCellID)
result := ""
if fixedCol {
result += "$"
}
result += letterPart
if fixedRow {
result += "$"
}
result += numberPart
return result
}
// fillCellData attempts to extract a valid value, usable in
// CSV form from the raw cell value. Note - this is not actually
// general enough - we should support retaining tabs and newlines.
func fillCellData(rawCell xlsxC, refTable *RefTable, sharedFormulas map[int]sharedFormula, cell *Cell) {
val := strings.Trim(rawCell.V, " \t\n\r")
cell.formula = formulaForCell(rawCell, sharedFormulas)
switch rawCell.T {
case "s": // Shared String
cell.cellType = CellTypeString
if val != "" {
ref, err := strconv.Atoi(val)
if err != nil {
panic(err)
}
cell.Value = refTable.ResolveSharedString(ref)
}
case "inlineStr":
cell.cellType = CellTypeInline
fillCellDataFromInlineString(rawCell, cell)
case "b": // Boolean
cell.Value = val
cell.cellType = CellTypeBool
case "e": // Error
cell.Value = val
cell.cellType = CellTypeError
case "str":
// String Formula (special type for cells with formulas that return a string value)
// Unlike the other string cell types, the string is stored directly in the value.
cell.Value = val
cell.cellType = CellTypeStringFormula
case "d": // Date: Cell contains a date in the ISO 8601 format.
cell.Value = val
cell.cellType = CellTypeDate
case "": // Numeric is the default
fallthrough
case "n": // Numeric
cell.Value = val
cell.cellType = CellTypeNumeric
default:
panic(errors.New("invalid cell type"))
}
}
// fillCellDataFromInlineString attempts to get inline string data and put it into a Cell.
func fillCellDataFromInlineString(rawcell xlsxC, cell *Cell) {
cell.Value = ""
if rawcell.Is != nil {
if rawcell.Is.T != "" {
cell.Value = strings.Trim(rawcell.Is.T, " \t\n\r")
} else {
for _, r := range rawcell.Is.R {
cell.Value += r.T
}
}
}
}
// readRowsFromSheet is an internal helper function that extracts the
// rows from a XSLXWorksheet, populates them with Cells and resolves
// the value references from the reference table and stores them in
// the rows and columns.
func readRowsFromSheet(Worksheet *xlsxWorksheet, file *File, sheet *Sheet, rowLimit int) ([]*Row, []*Col, int, int) {
var rows []*Row
var cols []*Col
var row *Row
var minCol, maxCol, maxRow, colCount, rowCount int
var reftable *RefTable
var err error
var insertRowIndex, insertColIndex int
sharedFormulas := map[int]sharedFormula{}
if len(Worksheet.SheetData.Row) == 0 {
return nil, nil, 0, 0
}
reftable = file.referenceTable
if len(Worksheet.Dimension.Ref) > 0 && len(strings.Split(Worksheet.Dimension.Ref, cellRangeChar)) == 2 && rowLimit == NoRowLimit {
minCol, _, maxCol, maxRow, err = getMaxMinFromDimensionRef(Worksheet.Dimension.Ref)
} else {
minCol, _, maxCol, maxRow, err = calculateMaxMinFromWorksheet(Worksheet)
}
if err != nil {
panic(err.Error())
}
rowCount = maxRow + 1
colCount = maxCol + 1
rows = make([]*Row, rowCount)
cols = make([]*Col, colCount)
for i := range cols {
cols[i] = &Col{
Hidden: false,
}
}
if Worksheet.Cols != nil {
// Columns can apply to a range, for convenience we expand the
// ranges out into individual column definitions.
for _, rawcol := range Worksheet.Cols.Col {
// Note, below, that sometimes column definitions can
// exist outside the defined dimensions of the
// spreadsheet - we deliberately exclude these
// columns.
for i := rawcol.Min; i <= rawcol.Max && i <= colCount; i++ {
col := &Col{
Min: rawcol.Min,
Max: rawcol.Max,
Hidden: rawcol.Hidden,
Width: rawcol.Width,
OutlineLevel: rawcol.OutlineLevel}
cols[i-1] = col
if file.styles != nil {
col.style = file.styles.getStyle(rawcol.Style)
col.numFmt, col.parsedNumFmt = file.styles.getNumberFormat(rawcol.Style)
}
}
}
}
numRows := len(rows)
for rowIndex := 0; rowIndex < len(Worksheet.SheetData.Row); rowIndex++ {
rawrow := Worksheet.SheetData.Row[rowIndex]
// Some spreadsheets will omit blank rows from the
// stored data
for rawrow.R > (insertRowIndex + 1) {
// Put an empty Row into the array
if insertRowIndex < numRows {
rows[insertRowIndex] = makeEmptyRow(sheet)
}
insertRowIndex++
}
// range is not empty and only one range exist
if len(rawrow.Spans) != 0 && strings.Count(rawrow.Spans, cellRangeChar) == 1 {
row = makeRowFromSpan(rawrow.Spans, sheet)
} else {
row = makeRowFromRaw(rawrow, sheet)
}
row.Hidden = rawrow.Hidden
height, err := strconv.ParseFloat(rawrow.Ht, 64)
if err == nil {
row.Height = height
}
row.isCustom = rawrow.CustomHeight
row.OutlineLevel = rawrow.OutlineLevel
insertColIndex = minCol
for _, rawcell := range rawrow.C {
h, v, err := Worksheet.MergeCells.getExtent(rawcell.R)
if err != nil {
panic(err.Error())
}
x, _, _ := GetCoordsFromCellIDString(rawcell.R)
// K1000000: Prevent panic when the range specified in the spreadsheet
// view exceeds the actual number of columns in the dataset.
// Some spreadsheets will omit blank cells
// from the data.
for x > insertColIndex {
// Put an empty Cell into the array
if insertColIndex < len(row.Cells) {
row.Cells[insertColIndex] = new(Cell)
}
insertColIndex++
}
cellX := insertColIndex
if cellX < len(row.Cells) {
cell := row.Cells[cellX]
cell.HMerge = h
cell.VMerge = v
fillCellData(rawcell, reftable, sharedFormulas, cell)
if file.styles != nil {
cell.style = file.styles.getStyle(rawcell.S)
cell.NumFmt, cell.parsedNumFmt = file.styles.getNumberFormat(rawcell.S)
}
cell.date1904 = file.Date1904
// Cell is considered hidden if the row or the column of this cell is hidden
cell.Hidden = rawrow.Hidden || (len(cols) > cellX && cols[cellX].Hidden)
insertColIndex++
}
}
if len(rows) > insertRowIndex {
rows[insertRowIndex] = row
}
insertRowIndex++
}
// insert trailing empty rows for the rest of the file
for ; insertRowIndex < rowCount; insertRowIndex++ {
rows[insertRowIndex] = makeEmptyRow(sheet)
}
return rows, cols, colCount, rowCount
}
type indexedSheet struct {
Index int
Sheet *Sheet
Error error
}
func readSheetViews(xSheetViews xlsxSheetViews) []SheetView {
if xSheetViews.SheetView == nil || len(xSheetViews.SheetView) == 0 {
return nil
}
sheetViews := []SheetView{}
for _, xSheetView := range xSheetViews.SheetView {
sheetView := SheetView{}
if xSheetView.Pane != nil {
xlsxPane := xSheetView.Pane
pane := &Pane{}
pane.XSplit = xlsxPane.XSplit
pane.YSplit = xlsxPane.YSplit
pane.TopLeftCell = xlsxPane.TopLeftCell
pane.ActivePane = xlsxPane.ActivePane
pane.State = xlsxPane.State
sheetView.Pane = pane
}
sheetViews = append(sheetViews, sheetView)
}
return sheetViews
}
// readSheetFromFile is the logic of converting a xlsxSheet struct
// into a Sheet struct. This work can be done in parallel and so
// readSheetsFromZipFile will spawn an instance of this function per
// sheet and get the results back on the provided channel.
func readSheetFromFile(sc chan *indexedSheet, index int, rsheet xlsxSheet, fi *File, sheetXMLMap map[string]string, rowLimit int) (errRes error) {
result := &indexedSheet{Index: index, Sheet: nil, Error: nil}
defer func() {
if e := recover(); e != nil {
switch e.(type) {
case error:
result.Error = e.(error)
errRes = e.(error)
default:
result.Error = errors.New("unexpected error")
}
// The only thing here, is if one close the channel. but its not the case
sc <- result
}
}()
worksheet, err := getWorksheetFromSheet(rsheet, fi.worksheets, sheetXMLMap, rowLimit)
if err != nil {
result.Error = err
sc <- result
return err
}
sheet := new(Sheet)
sheet.File = fi
sheet.Rows, sheet.Cols, sheet.MaxCol, sheet.MaxRow = readRowsFromSheet(worksheet, fi, sheet, rowLimit)
sheet.Hidden = rsheet.State == sheetStateHidden || rsheet.State == sheetStateVeryHidden
sheet.SheetViews = readSheetViews(worksheet.SheetViews)
sheet.SheetFormat.DefaultColWidth = worksheet.SheetFormatPr.DefaultColWidth
sheet.SheetFormat.DefaultRowHeight = worksheet.SheetFormatPr.DefaultRowHeight
sheet.SheetFormat.OutlineLevelCol = worksheet.SheetFormatPr.OutlineLevelCol
sheet.SheetFormat.OutlineLevelRow = worksheet.SheetFormatPr.OutlineLevelRow
if nil != worksheet.DataValidations {
for _, dd := range worksheet.DataValidations.DataValidation {
sqrefArr := strings.Split(dd.Sqref, " ")
for _, sqref := range sqrefArr {
parts := strings.Split(sqref, cellRangeChar)
minCol, minRow, err := GetCoordsFromCellIDString(parts[0])
if nil != err {
return fmt.Errorf("data validation %s", err.Error())
}
if 2 == len(parts) {
maxCol, maxRow, err := GetCoordsFromCellIDString(parts[1])
if nil != err {
return fmt.Errorf("data validation %s", err.Error())
}
if minCol == maxCol && minRow == maxRow {
newDD := new(xlsxCellDataValidation)
*newDD = *dd
newDD.Sqref = ""
sheet.Cell(minRow, minCol).SetDataValidation(newDD)
} else {
// one col mutli dd , error todo
for i := minCol; i <= maxCol; i++ {
newDD := new(xlsxCellDataValidation)
*newDD = *dd
newDD.Sqref = ""
sheet.Col(i).SetDataValidation(dd, minRow, maxRow)
}
}
} else {
newDD := new(xlsxCellDataValidation)
*newDD = *dd
newDD.Sqref = ""
sheet.Cell(minRow, minCol).SetDataValidation(dd)
}
}
}
}
result.Sheet = sheet
sc <- result
return nil
}
// readSheetsFromZipFile is an internal helper function that loops
// over the Worksheets defined in the XSLXWorkbook and loads them into
// Sheet objects stored in the Sheets slice of a xlsx.File struct.
func readSheetsFromZipFile(f *zip.File, file *File, sheetXMLMap map[string]string, rowLimit int) (map[string]*Sheet, []*Sheet, error) {
var workbook *xlsxWorkbook
var err error
var rc io.ReadCloser
var decoder *xml.Decoder
var sheetCount int
workbook = new(xlsxWorkbook)
rc, err = f.Open()
if err != nil {
return nil, nil, err
}
decoder = xml.NewDecoder(rc)
err = decoder.Decode(workbook)
if err != nil {
return nil, nil, err
}
file.Date1904 = workbook.WorkbookPr.Date1904
for entryNum := range workbook.DefinedNames.DefinedName {
file.DefinedNames = append(file.DefinedNames, &workbook.DefinedNames.DefinedName[entryNum])
}
// Only try and read sheets that have corresponding files.
// Notably this excludes chartsheets don't right now
var workbookSheets []xlsxSheet
for _, sheet := range workbook.Sheets.Sheet {
if f := worksheetFileForSheet(sheet, file.worksheets, sheetXMLMap); f != nil {
workbookSheets = append(workbookSheets, sheet)
}
}
sheetCount = len(workbookSheets)
sheetsByName := make(map[string]*Sheet, sheetCount)
sheets := make([]*Sheet, sheetCount)
sheetChan := make(chan *indexedSheet, sheetCount)
go func() {
defer close(sheetChan)
err = nil
for i, rawsheet := range workbookSheets {
if err := readSheetFromFile(sheetChan, i, rawsheet, file, sheetXMLMap, rowLimit); err != nil {
return
}
}
}()
for j := 0; j < sheetCount; j++ {
sheet := <-sheetChan
if sheet.Error != nil {
return nil, nil, sheet.Error
}
sheetName := workbookSheets[sheet.Index].Name
sheetsByName[sheetName] = sheet.Sheet
sheet.Sheet.Name = sheetName
sheets[sheet.Index] = sheet.Sheet
}
return sheetsByName, sheets, nil
}
// readSharedStringsFromZipFile() is an internal helper function to
// extract a reference table from the sharedStrings.xml file within
// the XLSX zip file.
func readSharedStringsFromZipFile(f *zip.File) (*RefTable, error) {
var sst *xlsxSST
var error error
var rc io.ReadCloser
var decoder *xml.Decoder
var reftable *RefTable
// In a file with no strings it's possible that
// sharedStrings.xml doesn't exist. In this case the value
// passed as f will be nil.
if f == nil {
return nil, nil
}
rc, error = f.Open()
if error != nil {
return nil, error
}
sst = new(xlsxSST)
decoder = xml.NewDecoder(rc)
error = decoder.Decode(sst)
if error != nil {
return nil, error
}
reftable = MakeSharedStringRefTable(sst)
return reftable, nil
}
// readStylesFromZipFile() is an internal helper function to
// extract a style table from the style.xml file within
// the XLSX zip file.
func readStylesFromZipFile(f *zip.File, theme *theme) (*xlsxStyleSheet, error) {
var style *xlsxStyleSheet
var error error
var rc io.ReadCloser
var decoder *xml.Decoder
rc, error = f.Open()
if error != nil {
return nil, error
}
style = newXlsxStyleSheet(theme)
decoder = xml.NewDecoder(rc)
error = decoder.Decode(style)
if error != nil {
return nil, error
}
buildNumFmtRefTable(style)
return style, nil
}
func buildNumFmtRefTable(style *xlsxStyleSheet) {
for _, numFmt := range style.NumFmts.NumFmt {
// We do this for the side effect of populating the NumFmtRefTable.
style.addNumFmt(numFmt)
}
}
func readThemeFromZipFile(f *zip.File) (*theme, error) {
rc, err := f.Open()
if err != nil {
return nil, err
}
var themeXml xlsxTheme
err = xml.NewDecoder(rc).Decode(&themeXml)
if err != nil {
return nil, err
}
return newTheme(themeXml), nil
}
type WorkBookRels map[string]string
func (w *WorkBookRels) MakeXLSXWorkbookRels() xlsxWorkbookRels {
relCount := len(*w)
xWorkbookRels := xlsxWorkbookRels{}
xWorkbookRels.Relationships = make([]xlsxWorkbookRelation, relCount+3)
for k, v := range *w {
index, err := strconv.Atoi(k[3:])
if err != nil {
panic(err.Error())
}
xWorkbookRels.Relationships[index-1] = xlsxWorkbookRelation{
Id: k,
Target: v,
Type: "http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet"}
}
relCount++
sheetId := fmt.Sprintf("rId%d", relCount)
xWorkbookRels.Relationships[relCount-1] = xlsxWorkbookRelation{
Id: sheetId,
Target: "sharedStrings.xml",
Type: "http://schemas.openxmlformats.org/officeDocument/2006/relationships/sharedStrings"}
relCount++
sheetId = fmt.Sprintf("rId%d", relCount)
xWorkbookRels.Relationships[relCount-1] = xlsxWorkbookRelation{
Id: sheetId,
Target: "theme/theme1.xml",
Type: "http://schemas.openxmlformats.org/officeDocument/2006/relationships/theme"}
relCount++
sheetId = fmt.Sprintf("rId%d", relCount)
xWorkbookRels.Relationships[relCount-1] = xlsxWorkbookRelation{
Id: sheetId,
Target: "styles.xml",
Type: "http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles"}
return xWorkbookRels
}
// readWorkbookRelationsFromZipFile is an internal helper function to
// extract a map of relationship ID strings to the name of the
// worksheet.xml file they refer to. The resulting map can be used to
// reliably derefence the worksheets in the XLSX file.
func readWorkbookRelationsFromZipFile(workbookRels *zip.File) (WorkBookRels, error) {
var sheetXMLMap WorkBookRels
var wbRelationships *xlsxWorkbookRels
var rc io.ReadCloser
var decoder *xml.Decoder
var err error
rc, err = workbookRels.Open()
if err != nil {
return nil, err
}
decoder = xml.NewDecoder(rc)
wbRelationships = new(xlsxWorkbookRels)
err = decoder.Decode(wbRelationships)
if err != nil {
return nil, err
}
sheetXMLMap = make(WorkBookRels)
for _, rel := range wbRelationships.Relationships {
if strings.HasSuffix(rel.Target, ".xml") && rel.Type == "http://schemas.openxmlformats.org/officeDocument/2006/relationships/worksheet" {
_, filename := path.Split(rel.Target)
sheetXMLMap[rel.Id] = strings.Replace(filename, ".xml", "", 1)
}
}
return sheetXMLMap, nil
}
// ReadZip() takes a pointer to a zip.ReadCloser and returns a
// xlsx.File struct populated with its contents. In most cases
// ReadZip is not used directly, but is called internally by OpenFile.
func ReadZip(f *zip.ReadCloser) (*File, error) {
return ReadZipWithRowLimit(f, NoRowLimit)
}
// ReadZipWithRowLimit() takes a pointer to a zip.ReadCloser and returns a
// xlsx.File struct populated with its contents. In most cases
// ReadZip is not used directly, but is called internally by OpenFile.
func ReadZipWithRowLimit(f *zip.ReadCloser, rowLimit int) (*File, error) {
defer f.Close()
return ReadZipReaderWithRowLimit(&f.Reader, rowLimit)
}
// ReadZipReader() can be used to read an XLSX in memory without
// touching the filesystem.
func ReadZipReader(r *zip.Reader) (*File, error) {
return ReadZipReaderWithRowLimit(r, NoRowLimit)
}
// ReadZipReaderWithRowLimit() can be used to read an XLSX in memory without
// touching the filesystem.
// rowLimit is the number of rows that should be read from the file. If rowLimit is -1, no limit is applied.
// You can specify this with the constant NoRowLimit.
func ReadZipReaderWithRowLimit(r *zip.Reader, rowLimit int) (*File, error) {
var err error
var file *File
var reftable *RefTable
var sharedStrings *zip.File
var sheetXMLMap map[string]string
var sheetsByName map[string]*Sheet
var sheets []*Sheet
var style *xlsxStyleSheet
var styles *zip.File
var themeFile *zip.File
var v *zip.File
var workbook *zip.File
var workbookRels *zip.File
var worksheets map[string]*zip.File
file = NewFile()
// file.numFmtRefTable = make(map[int]xlsxNumFmt, 1)
worksheets = make(map[string]*zip.File, len(r.File))
for _, v = range r.File {
switch v.Name {
case "xl/sharedStrings.xml":
sharedStrings = v
case "xl/workbook.xml":
workbook = v
case "xl/_rels/workbook.xml.rels":
workbookRels = v
case "xl/styles.xml":
styles = v
case "xl/theme/theme1.xml":
themeFile = v
default:
if len(v.Name) > 17 {
if v.Name[0:13] == "xl/worksheets" {
worksheets[v.Name[14:len(v.Name)-4]] = v
}
}
}
}
if workbookRels == nil {
return nil, fmt.Errorf("xl/_rels/workbook.xml.rels not found in input xlsx.")
}
sheetXMLMap, err = readWorkbookRelationsFromZipFile(workbookRels)
if err != nil {
return nil, err
}
if len(worksheets) == 0 {
return nil, fmt.Errorf("Input xlsx contains no worksheets.")
}
file.worksheets = worksheets
reftable, err = readSharedStringsFromZipFile(sharedStrings)
if err != nil {
return nil, err
}
file.referenceTable = reftable
if themeFile != nil {
theme, err := readThemeFromZipFile(themeFile)
if err != nil {
return nil, err
}
file.theme = theme
}
if styles != nil {
style, err = readStylesFromZipFile(styles, file.theme)
if err != nil {
return nil, err
}
file.styles = style
}
sheetsByName, sheets, err = readSheetsFromZipFile(workbook, file, sheetXMLMap, rowLimit)
if err != nil {
return nil, err
}
if sheets == nil {
readerErr := new(XLSXReaderError)
readerErr.Err = "No sheets found in XLSX File"
return nil, readerErr
}
file.Sheet = sheetsByName
file.Sheets = sheets
return file, nil
}
// truncateSheetXML will take in a reader to an XML sheet file and will return a reader that will read an equivalent
// XML sheet file with only the number of rows specified. This greatly speeds up XML unmarshalling when only
// a few rows need to be read from a large sheet.
// When sheets are truncated, all formatting present after the sheetData tag will be lost, but all of this formatting
// is related to printing and visibility, and is out of scope for most purposes of this library.
func truncateSheetXML(r io.Reader, rowLimit int) (io.Reader, error) {
var rowCount int
var token xml.Token
var readErr error
output := new(bytes.Buffer)
r = io.TeeReader(r, output)
decoder := xml.NewDecoder(r)
for {
token, readErr = decoder.Token()
if readErr == io.EOF {
break
} else if readErr != nil {
return nil, readErr
}
end, ok := token.(xml.EndElement)
if ok && end.Name.Local == "row" {
rowCount++
if rowCount >= rowLimit {
break
}
}
}
offset := decoder.InputOffset()
output.Truncate(int(offset))
if readErr != io.EOF {
_, err := output.Write([]byte(sheetEnding))
if err != nil {
return nil, err
}
}
return output, nil
}
|