From 245dd7fd8251e7c9094643d42d2680efc3f8d62b Mon Sep 17 00:00:00 2001 From: SheetJS Date: Mon, 20 Mar 2017 05:02:25 -0400 Subject: [PATCH] Documentation improvements - multiformat column widths (fixes #591 h/t @sheeeeep) - skip nested BIFF files --- .npmignore | 2 +- Makefile | 6 +- README.md | 141 +++++++++++++++++++++++++++++----- bits/20_jsutils.js | 2 +- bits/39_xlsbiff.js | 34 ++++++--- bits/45_styutils.js | 42 +++++++++-- bits/67_wsxml.js | 16 ++-- bits/68_wsbin.js | 17 ++++- bits/75_xlml.js | 16 +++- bits/76_xls.js | 34 +++++++-- bits/77_parsetab.js | 2 +- docbits/00_intro.md | 19 +++++ docbits/01_toc.md | 4 + docbits/10_install.md | 70 +++++++++++++++++ docbits/20_import.md | 119 +++++++++++++++++++++++++++++ docbits/25_manip.md | 53 +++++++++++++ docbits/30_export.md | 41 ++++++++++ docbits/40_interface.md | 45 +++++++++++ docbits/50_csf.md | 23 ++++++ docbits/51_cell.md | 24 ++++++ docbits/52_datatype.md | 39 ++++++++++ docbits/53_wsobject.md | 34 +++++++++ docbits/54_wbobject.md | 17 +++++ docbits/60_features.md | 7 ++ docbits/61_formulae.md | 79 +++++++++++++++++++ docbits/62_columns.md | 31 ++++++++ docbits/80_parseopts.md | 72 ++++++++++++++++++ docbits/81_writeopts.md | 52 +++++++++++++ docbits/82_util.md | 124 ++++++++++++++++++++++++++++++ docbits/85_filetype.md | 93 +++++++++++++++++++++++ docbits/90_test.md | 62 +++++++++++++++ docbits/95_contrib.md | 21 ++++++ docbits/97_license.md | 6 ++ docbits/98_reference.md | 30 ++++++++ docbits/99_badges.md | 17 +++++ misc/flow.js | 7 ++ test.js | 49 ++++++++++++ test_files | 2 +- xlsx.flow.js | 163 ++++++++++++++++++++++++++++++---------- xlsx.js | 163 ++++++++++++++++++++++++++++++---------- 40 files changed, 1637 insertions(+), 141 deletions(-) create mode 100644 docbits/00_intro.md create mode 100644 docbits/01_toc.md create mode 100644 docbits/10_install.md create mode 100644 docbits/20_import.md create mode 100644 docbits/25_manip.md create mode 100644 docbits/30_export.md create mode 100644 docbits/40_interface.md create mode 100644 docbits/50_csf.md create mode 100644 docbits/51_cell.md create mode 100644 docbits/52_datatype.md create mode 100644 docbits/53_wsobject.md create mode 100644 docbits/54_wbobject.md create mode 100644 docbits/60_features.md create mode 100644 docbits/61_formulae.md create mode 100644 docbits/62_columns.md create mode 100644 docbits/80_parseopts.md create mode 100644 docbits/81_writeopts.md create mode 100644 docbits/82_util.md create mode 100644 docbits/85_filetype.md create mode 100644 docbits/90_test.md create mode 100644 docbits/95_contrib.md create mode 100644 docbits/97_license.md create mode 100644 docbits/98_reference.md create mode 100644 docbits/99_badges.md diff --git a/.npmignore b/.npmignore index d89b36d..7aa78ea 100644 --- a/.npmignore +++ b/.npmignore @@ -37,5 +37,5 @@ test.js .flowconfig *.flow.js bits/ -odsbits/ +docbits/ tests/ diff --git a/Makefile b/Makefile index db8eeb7..6ffdb53 100644 --- a/Makefile +++ b/Makefile @@ -144,8 +144,12 @@ misc/coverage.html: $(TARGET) test.js coveralls: ## Coverage Test + Send to coveralls.io mocha --require blanket --reporter mocha-lcov-reporter -t 20000 | node ./node_modules/coveralls/bin/coveralls.js +READEPS=$(sort $(wildcard docbits/*.md)) +README.md: $(READEPS) + awk 'FNR==1{p=0}/#/{p=1}p' $^ | tr -d '\15\32' > $@ + .PHONY: readme -readme: ## Update README Table of Contents +readme: README.md ## Update README Table of Contents markdown-toc -i README.md .PHONY: help diff --git a/README.md b/README.md index 047820a..d35ee05 100644 --- a/README.md +++ b/README.md @@ -35,10 +35,12 @@ with a unified JS representation, and ES3/ES5 browser compatibility back to IE6. - [Workbook / Worksheet / Cell Object Description](#workbook--worksheet--cell-object-description) * [General Structures](#general-structures) * [Cell Object](#cell-object) - * [Data Types](#data-types) - * [Formulae](#formulae) + + [Data Types](#data-types) * [Worksheet Object](#worksheet-object) * [Workbook Object](#workbook-object) + * [Document Features](#document-features) + + [Formulae](#formulae) + + [Column Properties](#column-properties) - [Parsing Options](#parsing-options) * [Input Type](#input-type) * [Guessing File Type](#guessing-file-type) @@ -443,7 +445,7 @@ text from the number format (`cell.z`) and the raw value if possible. The actual array formula is stored in the `f` field of the first cell in the array range. Other cells in the range will omit the `f` field. -### Data Types +#### Data Types The raw value is stored in the `v` field, interpreted based on the `t` field. @@ -482,21 +484,6 @@ Type `z` represents blank stub cells. These do not have any data or type, and are not processed by any of the core library functions. By default these cells will not be generated; the parser `sheetStubs` option must be set to `true`. -### Formulae - -The A1-style formula string is stored in the `f` field. Even though different -file formats store the formulae in different ways, the formats are translated. - -Shared formulae are decompressed and each cell has the correct formula. - -Array formulae are stored in the top-left cell of the array block. All cells -of an array formula have a `F` field corresponding to the range. A single-cell -formula can be distinguished from a plain formula by the presence of `F` field. - -The `sheet_to_formulae` method generates one line per formula or array formula. -Array formulae are rendered in the form `range=formula` while plain cells are -rendered in the form `cell=formula or value`. - ### Worksheet Object Each key that does not start with `!` maps to a cell (using `A-1` notation) @@ -548,6 +535,123 @@ standard, XLS parsing stores core properties in both places. . The workbook's epoch can be determined by examining the workbook's `wb.WBProps.date1904` property. +### Document Features + +Even for basic features like date storage, the official Excel formats store the +same content in different ways. The parsers are expected to convert from the +underlying file format representation to the Common Spreadsheet Format. Writers +are expected to convert from CSF back to the underlying file format. + +#### Formulae + +The A1-style formula string is stored in the `f` field. Even though different +file formats store the formulae in different ways, the formats are translated. +Even though some formats store formulae with a leading equal sign, CSF formulae +do not start with `=`. + +The worksheet representation of A1=1, A2=2, A3=A1+A2: + +```js +{ + "!ref": "A1:A3", + A1: { t:'n', v:1 }, + A2: { t:'n', v:2 }, + A3: { t:'n', v:3, f:'A1+A2' } +} +``` + +Shared formulae are decompressed and each cell has the formula corresponding to +its cell. Writers generally do not attempt to generate shared formulae. + +Cells with formula entries but no value will be serialized in a way that Excel +and other spreadsheet tools will recognize. This library will not automatically +compute formula results! For example, to compute `BESSELJ` in a worksheet: + +```js +{ + "!ref": "A1:A3", + A1: { t:'n', v:3.14159 }, + A2: { t:'n', v:2 }, + A3: { t:'n', f:'BESSELJ(A1,A2)' } +} +``` + +**Array Formulae** + +Array formulae are stored in the top-left cell of the array block. All cells +of an array formula have a `F` field corresponding to the range. A single-cell +formula can be distinguished from a plain formula by the presence of `F` field. + +For example, setting the cell `C1` to the array formula `{=SUM(A1:A3*B1:B3)}`: + +```js +worksheet['C1'] = { t:'n', f: "SUM(A1:A3*B1:B3)", F:"C1:C1" }; +``` + +For a multi-cell array formula, every cell has the same array range but only the +first cell has content. Consider `D1:D3=A1:A3*B1:B3`: + +```js +worksheet['D1'] = { t:'n', F:"D1:D3", f:"A1:A3*B1:B3" }; +worksheet['D2'] = { t:'n', F:"D1:D3" }; +worksheet['D3'] = { t:'n', F:"D1:D3" }; +``` + +Utilities and writers are expected to check for the presence of a `F` field and +ignore any possible formula element `f` in cells other than the starting cell. +They are not expected to perform validation of the formulae! + +**Formula Output** + +The `sheet_to_formulae` method generates one line per formula or array formula. +Array formulae are rendered in the form `range=formula` while plain cells are +rendered in the form `cell=formula or value`. Note that string literals are +prefixed with an apostrophe `'`, consistent with Excel's formula bar display. + +**Formulae File Format Details** + +| Storage Representation | Formats | Read | Write | +|:-----------------------|:-------------------------|:-----:|:-----:| +| A1-style strings | XLSX | :o: | :o: | +| RC-style strings | XLML and plaintext | :o: | :o: | +| BIFF Parsed formulae | XLSB and all XLS formats | :o: | | +| OpenFormula formulae | ODS/FODS/UOS | :o: | :o: | + +Since Excel prohibits named cells from colliding with names of A1 or RC style +cell references, a (not-so-simple) regex conversion is possible. BIFF Parsed +formulae have to be explicitly unwound. OpenFormula formulae can be converted +with regexes for the most part. +#### Column Properties + +Excel internally stores column widths in a nebulous "Max Digit Width" form. The +Max Digit Width is the width of the largest digit when rendered. The internal +width must be an integer multiple of the the width divided by 256. ECMA-376 +describes a formula for converting between pixels and the internal width. + +Given the constraints, it is possible to determine the MDW without actually +inspecting the font! The parsers guess the pixel width by converting from width +to pixels and back, repeating for all possible MDW and selecting the MDW that +minimizes the error. XLML actually stores the pixel width, so the guess works +in the opposite direction. + +The `!cols` array in each worksheet, if present, is a collection of `ColInfo` +objects which have the following properties: + +```typescript +type ColInfo = { + MDW?:number; // Excel's "Max Digit Width" unit, always integral + width:number; // width in Excel's "Max Digit Width", width*256 is integral + wpx?:number; // width in screen pixels + wch?:number; // intermediate character calculation +}; +``` + +Even though all of the information is made available, writers are expected to +follow the priority order: + +1) use `width` field if available +2) use `wpx` pixel width if available +2) use `wch` character count if available ## Parsing Options The exported `read` and `readFile` functions accept an options argument: @@ -1001,6 +1105,7 @@ OSP-covered specifications: - [MS-XLDM]: Spreadsheet Data Model File Format - [MS-EXSPXML3]: Excel Calculation Version 2 Web Service XML Schema - [XLS]: Microsoft Office Excel 97-2007 Binary File Format Specification + - [MS-OI29500]: Office Implementation Information for ISO/IEC 29500 Standards Support Open Document Format for Office Applications Version 1.2 (29 September 2011) diff --git a/bits/20_jsutils.js b/bits/20_jsutils.js index 2289e1d..601ed32 100644 --- a/bits/20_jsutils.js +++ b/bits/20_jsutils.js @@ -75,7 +75,7 @@ function str2cc(str) { } function dup(o/*:any*/)/*:any*/ { - if(typeof JSON != 'undefined') return JSON.parse(JSON.stringify(o)); + if(typeof JSON != 'undefined' && !Array.isArray(o)) return JSON.parse(JSON.stringify(o)); if(typeof o != 'object' || o == null) return o; var out = {}; for(var k in o) if(o.hasOwnProperty(k)) out[k] = dup(o[k]); diff --git a/bits/39_xlsbiff.js b/bits/39_xlsbiff.js index 2ded65b..5ca34e1 100644 --- a/bits/39_xlsbiff.js +++ b/bits/39_xlsbiff.js @@ -239,10 +239,11 @@ function parse_RecalcId(blob, length) { } /* 2.4.87 */ -function parse_DefaultRowHeight (blob, length) { - var f = length == 4 ? blob.read_shift(2) : 0, miyRw; - miyRw = blob.read_shift(2); // flags & 0x02 -> hidden, else empty +function parse_DefaultRowHeight(blob, length) { + var f = blob.read_shift(2); var fl = {Unsynced:f&1,DyZero:(f&2)>>1,ExAsc:(f&4)>>2,ExDsc:(f&8)>>3}; + /* char is misleading, miyRw and miyRwHidden overlap */ + var miyRw = blob.read_shift(2); return [fl, miyRw]; } @@ -328,12 +329,13 @@ function parse_MulBlank(blob, length) { } /* 2.5.20 2.5.249 TODO: interpret values here */ -function parse_CellStyleXF(blob, length, style) { +function parse_CellStyleXF(blob, length, style, opts) { var o = {}; var a = blob.read_shift(4), b = blob.read_shift(4); var c = blob.read_shift(4), d = blob.read_shift(2); o.patternType = XLSFillPattern[c >> 26]; + if(!opts.cellStyles) return o; o.alc = a & 0x07; o.fWrap = (a >> 3) & 0x01; o.alcV = (a >> 4) & 0x07; @@ -367,16 +369,16 @@ function parse_CellStyleXF(blob, length, style) { o.fsxButton = (d >> 14) & 0x01; return o; } -function parse_CellXF(blob, length) {return parse_CellStyleXF(blob,length,0);} -function parse_StyleXF(blob, length) {return parse_CellStyleXF(blob,length,1);} +function parse_CellXF(blob, length, opts) {return parse_CellStyleXF(blob,length,0, opts);} +function parse_StyleXF(blob, length, opts) {return parse_CellStyleXF(blob,length,1, opts);} /* 2.4.353 TODO: actually do this right */ -function parse_XF(blob, length) { +function parse_XF(blob, length, opts) { var o = {}; o.ifnt = blob.read_shift(2); o.ifmt = blob.read_shift(2); o.flags = blob.read_shift(2); o.fStyle = (o.flags >> 2) & 0x01; length -= 6; - o.data = parse_CellStyleXF(blob, length, o.fStyle); + o.data = parse_CellStyleXF(blob, length, o.fStyle, opts); return o; } @@ -626,12 +628,24 @@ function parse_XFCRC(blob, length) { return o; } +/* 2.4.53 TODO: parse flags */ +/* [MS-XLSB] 2.4.323 TODO: parse flags */ +function parse_ColInfo(blob, length, opts) { + if(!opts.cellStyles) return parsenoop(blob, length); + var w = opts && opts.biff >= 12 ? 4 : 2; + var colFirst = blob.read_shift(w); + var colLast = blob.read_shift(w); + var coldx = blob.read_shift(w); + var ixfe = blob.read_shift(w); + var flags = blob.read_shift(2); + if(w == 2) blob.l += 2; + return {s:colFirst, e:colLast, w:coldx, ixfe:ixfe, flags:flags}; +} + var parse_Style = parsenoop; var parse_StyleExt = parsenoop; -var parse_ColInfo = parsenoop; - var parse_Window2 = parsenoop; diff --git a/bits/45_styutils.js b/bits/45_styutils.js index 60ef307..ec1a17a 100644 --- a/bits/45_styutils.js +++ b/bits/45_styutils.js @@ -50,17 +50,43 @@ function rgb_tint(hex, tint) { } /* 18.3.1.13 width calculations */ +/* [MS-OI29500] 2.1.595 Column Width & Formatting */ var DEF_MDW = 7, MAX_MDW = 15, MIN_MDW = 1, MDW = DEF_MDW; -function width2px(width) { return (( width + ((128/MDW)|0)/256 )* MDW )|0; } -function px2char(px) { return (((px - 5)/MDW * 100 + 0.5)|0)/100; } -function char2width(chr) { return (((chr * MDW + 5)/MDW*256)|0)/256; } +function width2px(width) { return Math.floor(( width + (Math.round(128/MDW))/256 )* MDW ); } +function px2char(px) { return (Math.floor((px - 5)/MDW * 100 + 0.5))/100; } +function char2width(chr) { return (Math.round((chr * MDW + 5)/MDW*256))/256; } +function px2char_(px) { return (((px - 5)/MDW * 100 + 0.5))/100; } +function char2width_(chr) { return (((chr * MDW + 5)/MDW*256))/256; } function cycle_width(collw) { return char2width(px2char(width2px(collw))); } -function find_mdw(collw, coll) { - if(cycle_width(collw) != collw) { - for(MDW=DEF_MDW; MDW>MIN_MDW; --MDW) if(cycle_width(collw) === collw) break; - if(MDW === MIN_MDW) for(MDW=DEF_MDW+1; MDW 0.5) guess--; + if(Math.abs(guess) < delta) { delta = Math.abs(guess); _MDW = MDW; } } + MDW = _MDW; +} + +function process_col(coll/*:ColInfo*/) { + if(coll.width) { + coll.wpx = width2px(coll.width); + coll.wch = px2char(coll.wpx); + coll.MDW = MDW; + } else if(coll.wpx) { + coll.wch = px2char(coll.wpx); + coll.width = char2width(coll.wch); + coll.MDW = MDW; + } + if(coll.customWidth) delete coll.customWidth; } /* [MS-EXSPXML3] 2.4.54 ST_enmPattern */ diff --git a/bits/67_wsxml.js b/bits/67_wsxml.js index 1ee57cb..ae6320b 100644 --- a/bits/67_wsxml.js +++ b/bits/67_wsxml.js @@ -98,14 +98,10 @@ function parse_ws_xml_cols(columns, cols) { for(var coli = 0; coli != cols.length; ++coli) { var coll = parsexmltag(cols[coli], true); var colm=parseInt(coll.min, 10)-1, colM=parseInt(coll.max,10)-1; - delete coll.min; delete coll.max; - if(!seencol && coll.width) { seencol = true; find_mdw(+coll.width, coll); } - if(coll.width) { - coll.wpx = width2px(+coll.width); - coll.wch = px2char(coll.wpx); - coll.MDW = MDW; - } - while(colm <= colM) columns[colm++] = coll; + delete coll.min; delete coll.max; coll.width = +coll.width; + if(!seencol && coll.width) { seencol = true; find_mdw_colw(coll.width); } + process_col(coll); + while(colm <= colM) columns[colm++] = dup(coll); } } @@ -116,7 +112,9 @@ function write_ws_xml_cols(ws, cols)/*:string*/ { var p = ({min:i+1,max:i+1}/*:any*/); /* wch (chars), wpx (pixels) */ width = -1; - if(col.wpx) width = px2char(col.wpx); + if(col.MDW) MDW = col.MDW; + if(col.width); + else if(col.wpx) width = px2char(col.wpx); else if(col.wch) width = col.wch; if(width > -1) { p.width = char2width(width); p.customWidth= 1; } o[o.length] = (writextag('col', null, p)); diff --git a/bits/68_wsbin.js b/bits/68_wsbin.js index b2524bf..0232b05 100644 --- a/bits/68_wsbin.js +++ b/bits/68_wsbin.js @@ -282,6 +282,10 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles)/*:Worksheet*/ { for(var i = 0; i < wb.Names['!names'].length; ++i) supbooks[0][i+1] = wb.Names[wb.Names['!names'][i]]; + var colinfo = [], rowinfo = []; + var defwidth = 0, defheight = 0; // twips / MDW respectively + var seencol = false; + recordhopper(data, function ws_parse(val, Record) { if(end) return; switch(Record.n) { @@ -369,6 +373,16 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles)/*:Worksheet*/ { s[encode_col(C) + rr].f = stringify_formula(val[1], refguess, {r:row.r, c:C}, supbooks, opts); break; + /* identical to 'ColInfo' in XLS */ + case 'BrtColInfo': { + if(!opts.cellStyles) break; + while(val.e >= val.s) { + colinfo[val.e--] = { width: val.w/256 }; + if(!seencol) { seencol = true; find_mdw_colw(val.w/256); } + process_col(colinfo[val.e+1]); + } + } break; + case 'BrtBeginSheet': break; case 'BrtWsProp': break; // TODO case 'BrtSheetCalcProp': break; // TODO @@ -384,7 +398,6 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles)/*:Worksheet*/ { case 'BrtWsFmtInfoEx14': break; // TODO case 'BrtWsFmtInfo': break; // TODO case 'BrtBeginColInfos': break; // TODO - case 'BrtColInfo': break; // TODO case 'BrtEndColInfos': break; // TODO case 'BrtBeginSheetData': break; // TODO case 'BrtEndSheetData': break; // TODO @@ -497,6 +510,8 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles)/*:Worksheet*/ { } } if(mergecells.length > 0) s["!merges"] = mergecells; + if(colinfo.length > 0) s["!cols"] = colinfo; + if(rowinfo.length > 0) s["!rows"] = rowinfo; return s; } diff --git a/bits/75_xlml.js b/bits/75_xlml.js index 992c9a8..aadb14a 100644 --- a/bits/75_xlml.js +++ b/bits/75_xlml.js @@ -178,8 +178,9 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ { var mergecells = []; var Props = {}, Custprops = {}, pidx = 0, cp = {}; var comments = [], comment = {}; - var cstys = [], csty; + var cstys = [], csty, seencol = false; var arrayf = []; + var rowinfo = []; xlmlregex.lastIndex = 0; str = str.replace(//mg,""); while((Rn = xlmlregex.exec(str))) switch(Rn[3]) { @@ -241,6 +242,8 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ { sheetnames.push(sheetname); if(refguess.s.r <= refguess.e.r && refguess.s.c <= refguess.e.c) cursheet["!ref"] = encode_range(refguess); if(mergecells.length) cursheet["!merges"] = mergecells; + if(cstys.length > 0) cursheet["!cols"] = cstys; + if(rowinfo.length > 0) cursheet["!rows"] = rowinfo; sheets[sheetname] = cursheet; } else { refguess = {s: {r:2000000, c:2000000}, e: {r:0, c:0} }; @@ -251,6 +254,7 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ { cursheet = {}; mergecells = []; arrayf = []; + rowinfo = []; } break; case 'Table': @@ -259,7 +263,7 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ { else { table = xlml_parsexmltag(Rn[0]); state.push([Rn[3], false]); - cstys = []; + cstys = []; seencol = false; } break; @@ -275,8 +279,14 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ { case 'Column': if(state[state.length-1][0] !== 'Table') break; csty = xlml_parsexmltag(Rn[0]); + csty.wpx = parseInt(csty.Width, 10); + if(!seencol && csty.wpx > 10) { + seencol = true; find_mdw_wpx(csty.wpx); + for(var _col = 0; _col < cstys.length; ++_col) if(cstys[_col]) process_col(cstys[_col]); + } + if(seencol) process_col(csty); cstys[(csty.Index-1||cstys.length)] = csty; - for(var i = 0; i < +csty.Span; ++i) cstys[cstys.length] = csty; + for(var i = 0; i < +csty.Span; ++i) cstys[cstys.length] = dup(csty); break; case 'NamedRange': break; diff --git a/bits/76_xls.js b/bits/76_xls.js index 00bf734..0e4a8f4 100644 --- a/bits/76_xls.js +++ b/bits/76_xls.js @@ -100,9 +100,9 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { if(icv < 64) return palette[icv-8] || XLSIcv[icv]; return XLSIcv[icv]; }; - var process_cell_style = function pcs(cell, line/*:any*/) { + var process_cell_style = function pcs(cell, line/*:any*/, options) { var xfd = line.XF.data; - if(!xfd || !xfd.patternType) return; + if(!xfd || !xfd.patternType || !options || !options.cellStyles) return; line.s = ({}/*:any*/); line.s.patternType = xfd.patternType; var t; @@ -110,8 +110,9 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { if((t = rgb2Hex(get_rgb(xfd.icvBack)))) { line.s.bgColor = {rgb:t}; } }; var addcell = function addcell(cell/*:any*/, line/*:any*/, options/*:any*/) { + if(file_depth > 1) return; if(!cell_valid) return; - if(options.cellStyles && line.XF && line.XF.data) process_cell_style(cell, line); + if(options.cellStyles && line.XF && line.XF.data) process_cell_style(cell, line, options); lastcell = cell; last_cell = encode_cell(cell); if(range.s) { @@ -149,11 +150,15 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { biff: 8, // BIFF version codepage: 0, // CP from CodePage record winlocked: 0, // fLockWn from WinProtect + cellStyles: !!options && !!options.cellStyles, WTF: !!options && !!options.wtf }/*:any*/); if(options.password) opts.password = options.password; var mergecells = []; var objects = []; + var colinfo = [], rowinfo = []; + var defwidth = 0, defheight = 0; // twips / MDW respectively + var seencol = false; var supbooks = ([[]]/*:any*/); // 1-indexed, will hold extern names var sbc = 0, sbci = 0, sbcli = 0; supbooks.SheetNames = opts.snames; @@ -260,6 +265,8 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { } if(mergecells.length > 0) out["!merges"] = mergecells; if(objects.length > 0) out["!objects"] = objects; + if(colinfo.length > 0) out["!cols"] = colinfo; + if(rowinfo.length > 0) out["!rows"] = rowinfo; } if(cur_sheet === "") Preamble = out; else Sheets[cur_sheet] = out; out = {}; @@ -288,6 +295,9 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { mergecells = []; objects = []; array_formulae = []; opts.arrayf = array_formulae; + colinfo = []; rowinfo = []; + defwidth = defheight = 0; + seencol = false; } break; case 'Number': case 'BIFF2NUM': case 'BIFF2INT': { @@ -436,6 +446,19 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { case 'ClrtClient': break; case 'XFExt': update_xfext(XFs[val.ixfe], val.ext); break; + case 'DefColWidth': defwidth = val; break; + case 'DefaultRowHeight': defheight = val[1]; break; // TODO: flags + + case 'ColInfo': { + if(!opts.cellStyles) break; + while(val.e >= val.s) { + colinfo[val.e--] = { width: val.w/256 }; + if(!seencol) { seencol = true; find_mdw_colw(val.w/256); } + process_col(colinfo[val.e+1]); + } + } break; + case 'Row': break; // TODO + case 'NameCmt': break; case 'Header': break; // TODO case 'Footer': break; // TODO @@ -443,11 +466,8 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { case 'VCenter': break; // TODO case 'Pls': break; // TODO case 'Setup': break; // TODO - case 'DefColWidth': break; // TODO case 'GCW': break; case 'LHRecord': break; - case 'ColInfo': break; // TODO - case 'Row': break; // TODO case 'DBCell': break; // TODO case 'EntExU2': break; // TODO case 'SxView': break; // TODO @@ -465,7 +485,7 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { case 'Feature11': case 'Feature12': case 'List12': break; case 'Country': country = val; break; case 'RecalcId': break; - case 'DefaultRowHeight': case 'DxGCol': break; // TODO: htmlify + case 'DxGCol': break; // TODO: htmlify case 'Fbi': case 'Fbi2': case 'GelFrame': break; case 'Font': break; // TODO case 'XFCRC': break; // TODO diff --git a/bits/77_parsetab.js b/bits/77_parsetab.js index 8bcd2c0..b820f4a 100644 --- a/bits/77_parsetab.js +++ b/bits/77_parsetab.js @@ -53,7 +53,7 @@ var XLSBRecordEnum = { /*::[*/0x0039/*::]*/: { n:"BrtEndMdxTuple", f:parsenoop }, /*::[*/0x003A/*::]*/: { n:"BrtMdxMbrIstr", f:parsenoop }, /*::[*/0x003B/*::]*/: { n:"BrtStr", f:parsenoop }, - /*::[*/0x003C/*::]*/: { n:"BrtColInfo", f:parsenoop }, + /*::[*/0x003C/*::]*/: { n:"BrtColInfo", f:parse_ColInfo }, /*::[*/0x003E/*::]*/: { n:"BrtCellRString", f:parsenoop }, /*::[*/0x003F/*::]*/: { n:"BrtCalcChainItem$", f:parse_BrtCalcChainItem$ }, /*::[*/0x0040/*::]*/: { n:"BrtDVal", f:parsenoop }, diff --git a/docbits/00_intro.md b/docbits/00_intro.md new file mode 100644 index 0000000..e2ef709 --- /dev/null +++ b/docbits/00_intro.md @@ -0,0 +1,19 @@ +# xlsx + +Parser and writer for various spreadsheet formats. Pure-JS cleanroom +implementation from official specifications, related documents, and test files. +Emphasis on parsing and writing robustness, cross-format feature compatibility +with a unified JS representation, and ES3/ES5 browser compatibility back to IE6. + +[**In-Browser Demo**](http://oss.sheetjs.com/js-xlsx) + +[**Source Code**](http://git.io/xlsx) + +[**Commercial Support**](http://sheetjs.com/reinforcements) + +[**File format support for known spreadsheet data formats:**](#file-formats) + +![circo graph of format support](formats.png) + + + diff --git a/docbits/01_toc.md b/docbits/01_toc.md new file mode 100644 index 0000000..69d6596 --- /dev/null +++ b/docbits/01_toc.md @@ -0,0 +1,4 @@ +## Table of Contents + + + diff --git a/docbits/10_install.md b/docbits/10_install.md new file mode 100644 index 0000000..88878e2 --- /dev/null +++ b/docbits/10_install.md @@ -0,0 +1,70 @@ +## Installation + +With [npm](https://www.npmjs.org/package/xlsx): + +```bash +$ npm install xlsx +``` + +In the browser: + +```html + +``` + +With [bower](http://bower.io/search/?q=js-xlsx): + +```bash +$ bower install js-xlsx +``` + +CDNjs automatically pulls the latest version and makes all versions available at + + +### JS Ecosystem Demos + +The `demos` directory includes sample projects for: + +- [`browserify`](http://browserify.org/) +- [`requirejs`](http://requirejs.org/) +- [`webpack`](https://webpack.js.org/) + +### Optional Modules + +The node version automatically requires modules for additional features. Some +of these modules are rather large in size and are only needed in special +circumstances, so they do not ship with the core. For browser use, they must +be included directly: + +```html + + +``` + +An appropriate version for each dependency is included in the dist/ directory. + +The complete single-file version is generated at `dist/xlsx.full.min.js` + +Webpack and browserify builds include optional modules by default. Webpack can +be configured to remove support with `resolve.alias`: + +```js + /* uncomment the lines below to remove support */ + resolve: { + alias: { "./dist/cpexcel.js": "" } // <-- omit international support + } +``` + + +### ECMAScript 5 Compatibility + +Since xlsx.js uses ES5 functions like `Array#forEach`, older browsers require +[Polyfills](http://git.io/QVh77g). This repo and the gh-pages branch include +[a shim](https://github.com/SheetJS/js-xlsx/blob/master/shim.js) + +To use the shim, add the shim before the script tag that loads xlsx.js: + +```html + +``` + diff --git a/docbits/20_import.md b/docbits/20_import.md new file mode 100644 index 0000000..05d8b7e --- /dev/null +++ b/docbits/20_import.md @@ -0,0 +1,119 @@ +## Parsing Workbooks + +For parsing, the first step is to read the file. This involves acquiring the +data and feeding it into the library. Here are a few common scenarios: + +- node readFile: + +```js +if(typeof require !== 'undefined') XLSX = require('xlsx'); +var workbook = XLSX.readFile('test.xlsx'); +/* DO SOMETHING WITH workbook HERE */ +``` + +- ajax (for a more complete example that works in older browsers, check the demo + at ): + +```js +/* set up XMLHttpRequest */ +var url = "test_files/formula_stress_test_ajax.xlsx"; +var oReq = new XMLHttpRequest(); +oReq.open("GET", url, true); +oReq.responseType = "arraybuffer"; + +oReq.onload = function(e) { + var arraybuffer = oReq.response; + + /* convert data to binary string */ + var data = new Uint8Array(arraybuffer); + var arr = new Array(); + for(var i = 0; i != data.length; ++i) arr[i] = String.fromCharCode(data[i]); + var bstr = arr.join(""); + + /* Call XLSX */ + var workbook = XLSX.read(bstr, {type:"binary"}); + + /* DO SOMETHING WITH workbook HERE */ +} + +oReq.send(); +``` + +- HTML5 drag-and-drop using readAsBinaryString or readAsArrayBuffer: + note: readAsBinaryString and readAsArrayBuffer may not be available in every + browser. Use dynamic feature tests to determine which method to use. + +```js +/* processing array buffers, only required for readAsArrayBuffer */ +function fixdata(data) { + var o = "", l = 0, w = 10240; + for(; l HTML5 File API / Base64 Text / Web Workers + +Note that older versions of IE do not support HTML5 File API, so the base64 mode +is used for testing. On OSX you can get the base64 encoding with: + +```bash +$ certutil -encode target_file target_file.b64 +``` + +(note: You have to open the file and remove the header and footer lines) + +- XMLHttpRequest + +- node + +The node version installs a command line tool `xlsx` which can read spreadsheet +files and output the contents in various formats. The source is available at +`xlsx.njs` in the bin directory. + +Some helper functions in `XLSX.utils` generate different views of the sheets: + +- `XLSX.utils.sheet_to_csv` generates CSV +- `XLSX.utils.sheet_to_json` generates an array of objects +- `XLSX.utils.sheet_to_formulae` generates a list of formulae + diff --git a/docbits/30_export.md b/docbits/30_export.md new file mode 100644 index 0000000..d1e5c85 --- /dev/null +++ b/docbits/30_export.md @@ -0,0 +1,41 @@ +## Writing Workbooks + +For writing, the first step is to generate output data. The helper functions +`write` and `writeFile` will produce the data in various formats suitable for +dissemination. The second step is to actual share the data with the end point. +Assuming `workbook` is a workbook object: + +- nodejs write to file: + +```js +/* output format determined by filename */ +XLSX.writeFile(workbook, 'out.xlsx'); +/* at this point, out.xlsx is a file that you can distribute */ +``` + +- browser generate binary blob and "download" to client + (using [FileSaver.js](https://github.com/eligrey/FileSaver.js/) for download): + +```js +/* bookType can be 'xlsx' or 'xlsm' or 'xlsb' or 'ods' */ +var wopts = { bookType:'xlsx', bookSST:false, type:'binary' }; + +var wbout = XLSX.write(workbook,wopts); + +function s2ab(s) { + var buf = new ArrayBuffer(s.length); + var view = new Uint8Array(buf); + for (var i=0; i!=s.length; ++i) view[i] = s.charCodeAt(i) & 0xFF; + return buf; +} + +/* the saveAs call downloads a file on the local machine */ +saveAs(new Blob([s2ab(wbout)],{type:"application/octet-stream"}), "test.xlsx"); +``` + +**Complete examples:** + +- generates a simple file +- writing an array of arrays in nodejs +- exporting an HTML table + diff --git a/docbits/40_interface.md b/docbits/40_interface.md new file mode 100644 index 0000000..44ca6c3 --- /dev/null +++ b/docbits/40_interface.md @@ -0,0 +1,45 @@ +## Interface + +`XLSX` is the exposed variable in the browser and the exported node variable + +`XLSX.version` is the version of the library (added by the build script). + +`XLSX.SSF` is an embedded version of the [format library](http://git.io/ssf). + +### Parsing functions + +`XLSX.read(data, read_opts)` attempts to parse `data`. + +`XLSX.readFile(filename, read_opts)` attempts to read `filename` and parse. + +Parse options are described in the [Parsing Options](#parsing-options) section. + +### Writing functions + +`XLSX.write(wb, write_opts)` attempts to write the workbook `wb` + +`XLSX.writeFile(wb, filename, write_opts)` attempts to write `wb` to `filename` + +Write options are described in the [Writing Options](#writing-options) section. + +### Utilities + +Utilities are available in the `XLSX.utils` object: + +**Exporting:** + +- `sheet_to_json` converts a worksheet object to an array of JSON objects. + `sheet_to_row_object_array` is an alias that will be removed in the future. +- `sheet_to_csv` generates delimiter-separated-values output. +- `sheet_to_formulae` generates a list of the formulae (with value fallbacks). + +Exporters are described in the [Utility Functions](#utility-functions) section. + + +**Cell and cell address manipulation:** + +- `format_cell` generates the text value for a cell (using number formats) +- `{en,de}code_{row,col}` convert between 0-indexed rows/cols and A1 forms. +- `{en,de}code_cell` converts cell addresses +- `{en,de}code_range` converts cell ranges + diff --git a/docbits/50_csf.md b/docbits/50_csf.md new file mode 100644 index 0000000..e365c13 --- /dev/null +++ b/docbits/50_csf.md @@ -0,0 +1,23 @@ +## Workbook / Worksheet / Cell Object Description + +js-xlsx conforms to the Common Spreadsheet Format (CSF): + +### General Structures + +Cell address objects are stored as `{c:C, r:R}` where `C` and `R` are 0-indexed +column and row numbers, respectively. For example, the cell address `B5` is +represented by the object `{c:1, r:4}`. + +Cell range objects are stored as `{s:S, e:E}` where `S` is the first cell and +`E` is the last cell in the range. The ranges are inclusive. For example, the +range `A3:B7` is represented by the object `{s:{c:0, r:2}, e:{c:1, r:6}}`. Utils +use the following pattern to walk each of the cells in a range: + +```js +for(var R = range.s.r; R <= range.e.r; ++R) { + for(var C = range.s.c; C <= range.e.c; ++C) { + var cell_address = {c:C, r:R}; + } +} +``` + diff --git a/docbits/51_cell.md b/docbits/51_cell.md new file mode 100644 index 0000000..0b8b951 --- /dev/null +++ b/docbits/51_cell.md @@ -0,0 +1,24 @@ +### Cell Object + +| Key | Description | +| --- | ---------------------------------------------------------------------- | +| `v` | raw value (see Data Types section for more info) | +| `w` | formatted text (if applicable) | +| `t` | cell type: `b` Boolean, `n` Number, `e` error, `s` String, `d` Date | +| `f` | cell formula encoded as an A1-style string (if applicable) | +| `F` | range of enclosing array if formula is array formula (if applicable) | +| `r` | rich text encoding (if applicable) | +| `h` | HTML rendering of the rich text (if applicable) | +| `c` | comments associated with the cell | +| `z` | number format string associated with the cell (if requested) | +| `l` | cell hyperlink object (.Target holds link, .tooltip is tooltip) | +| `s` | the style/theme of the cell (if applicable) | + +Built-in export utilities (such as the CSV exporter) will use the `w` text if it +is available. To change a value, be sure to delete `cell.w` (or set it to +`undefined`) before attempting to export. The utilities will regenerate the `w` +text from the number format (`cell.z`) and the raw value if possible. + +The actual array formula is stored in the `f` field of the first cell in the +array range. Other cells in the range will omit the `f` field. + diff --git a/docbits/52_datatype.md b/docbits/52_datatype.md new file mode 100644 index 0000000..48690ee --- /dev/null +++ b/docbits/52_datatype.md @@ -0,0 +1,39 @@ +#### Data Types + +The raw value is stored in the `v` field, interpreted based on the `t` field. + +Type `b` is the Boolean type. `v` is interpreted according to JS truth tables. + +Type `e` is the Error type. `v` holds the number and `w` holds the common name: + +| Value | Error Meaning | +| -----: | :-------------- | +| `0x00` | `#NULL!` | +| `0x07` | `#DIV/0!` | +| `0x0F` | `#VALUE!` | +| `0x17` | `#REF!` | +| `0x1D` | `#NAME?` | +| `0x24` | `#NUM!` | +| `0x2A` | `#N/A` | +| `0x2B` | `#GETTING_DATA` | + +Type `n` is the Number type. This includes all forms of data that Excel stores +as numbers, such as dates/times and Boolean fields. Excel exclusively uses data +that can be fit in an IEEE754 floating point number, just like JS Number, so the +`v` field holds the raw number. The `w` field holds formatted text. Dates are +stored as numbers by default and converted with `XLSX.SSF.parse_date_code`. + +Type `d` is the Date type, generated only when the option `cellDates` is passed. +Since JSON does not have a natural Date type, parsers are generally expected to +store ISO 8601 Date strings like you would get from `date.toISOString()`. On +the other hand, writers and exporters should be able to handle date strings and +JS Date objects. Note that Excel disregards timezone modifiers and treats all +dates in the local timezone. js-xlsx does not correct for this error. + +Type `s` is the String type. `v` should be explicitly stored as a string to +avoid possible confusion. + +Type `z` represents blank stub cells. These do not have any data or type, and +are not processed by any of the core library functions. By default these cells +will not be generated; the parser `sheetStubs` option must be set to `true`. + diff --git a/docbits/53_wsobject.md b/docbits/53_wsobject.md new file mode 100644 index 0000000..753793f --- /dev/null +++ b/docbits/53_wsobject.md @@ -0,0 +1,34 @@ +### Worksheet Object + +Each key that does not start with `!` maps to a cell (using `A-1` notation) + +`worksheet[address]` returns the cell object for the specified address. + +Special worksheet keys (accessible as `worksheet[key]`, each starting with `!`): + +- `ws['!ref']`: A-1 based range representing the worksheet range. Functions that + work with sheets should use this parameter to determine the range. Cells that + are assigned outside of the range are not processed. In particular, when + writing a worksheet by hand, be sure to update the range. For a longer + discussion, see + + Functions that handle worksheets should test for the presence of `!ref` field. + If the `!ref` is omitted or is not a valid range, functions are free to treat + the sheet as empty or attempt to guess the range. The standard utilities that + ship with this library treat sheets as empty (for example, the CSV output is + empty string). + + When reading a worksheet with the `sheetRows` property set, the ref parameter + will use the restricted range. The original range is set at `ws['!fullref']` + +- `ws['!cols']`: array of column properties objects. Column widths are actually + stored in files in a normalized manner, measured in terms of the "Maximum + Digit Width" (the largest width of the rendered digits 0-9, in pixels). When + parsed, the column objects store the pixel width in the `wpx` field, character + width in the `wch` field, and the maximum digit width in the `MDW` field. + +- `ws['!merges']`: array of range objects corresponding to the merged cells in + the worksheet. Plaintext utilities are unaware of merge cells. CSV export + will write all cells in the merge range if they exist, so be sure that only + the first cell (upper-left) in the range is set. + diff --git a/docbits/54_wbobject.md b/docbits/54_wbobject.md new file mode 100644 index 0000000..e0687e7 --- /dev/null +++ b/docbits/54_wbobject.md @@ -0,0 +1,17 @@ +### Workbook Object + +`workbook.SheetNames` is an ordered list of the sheets in the workbook + +`wb.Sheets[sheetname]` returns an object representing the worksheet. + +`wb.Props` is an object storing the standard properties. `wb.Custprops` stores +custom properties. Since the XLS standard properties deviate from the XLSX +standard, XLS parsing stores core properties in both places. . + +`wb.WBProps` includes more workbook-level properties: + +- Excel supports two epochs (January 1 1900 and January 1 1904), see + [1900 vs. 1904 Date System](http://support2.microsoft.com/kb/180162). + The workbook's epoch can be determined by examining the workbook's + `wb.WBProps.date1904` property. + diff --git a/docbits/60_features.md b/docbits/60_features.md new file mode 100644 index 0000000..e300ac4 --- /dev/null +++ b/docbits/60_features.md @@ -0,0 +1,7 @@ +### Document Features + +Even for basic features like date storage, the official Excel formats store the +same content in different ways. The parsers are expected to convert from the +underlying file format representation to the Common Spreadsheet Format. Writers +are expected to convert from CSF back to the underlying file format. + diff --git a/docbits/61_formulae.md b/docbits/61_formulae.md new file mode 100644 index 0000000..a2e8ae1 --- /dev/null +++ b/docbits/61_formulae.md @@ -0,0 +1,79 @@ +#### Formulae + +The A1-style formula string is stored in the `f` field. Even though different +file formats store the formulae in different ways, the formats are translated. +Even though some formats store formulae with a leading equal sign, CSF formulae +do not start with `=`. + +The worksheet representation of A1=1, A2=2, A3=A1+A2: + +```js +{ + "!ref": "A1:A3", + A1: { t:'n', v:1 }, + A2: { t:'n', v:2 }, + A3: { t:'n', v:3, f:'A1+A2' } +} +``` + +Shared formulae are decompressed and each cell has the formula corresponding to +its cell. Writers generally do not attempt to generate shared formulae. + +Cells with formula entries but no value will be serialized in a way that Excel +and other spreadsheet tools will recognize. This library will not automatically +compute formula results! For example, to compute `BESSELJ` in a worksheet: + +```js +{ + "!ref": "A1:A3", + A1: { t:'n', v:3.14159 }, + A2: { t:'n', v:2 }, + A3: { t:'n', f:'BESSELJ(A1,A2)' } +} +``` + +**Array Formulae** + +Array formulae are stored in the top-left cell of the array block. All cells +of an array formula have a `F` field corresponding to the range. A single-cell +formula can be distinguished from a plain formula by the presence of `F` field. + +For example, setting the cell `C1` to the array formula `{=SUM(A1:A3*B1:B3)}`: + +```js +worksheet['C1'] = { t:'n', f: "SUM(A1:A3*B1:B3)", F:"C1:C1" }; +``` + +For a multi-cell array formula, every cell has the same array range but only the +first cell has content. Consider `D1:D3=A1:A3*B1:B3`: + +```js +worksheet['D1'] = { t:'n', F:"D1:D3", f:"A1:A3*B1:B3" }; +worksheet['D2'] = { t:'n', F:"D1:D3" }; +worksheet['D3'] = { t:'n', F:"D1:D3" }; +``` + +Utilities and writers are expected to check for the presence of a `F` field and +ignore any possible formula element `f` in cells other than the starting cell. +They are not expected to perform validation of the formulae! + +**Formula Output** + +The `sheet_to_formulae` method generates one line per formula or array formula. +Array formulae are rendered in the form `range=formula` while plain cells are +rendered in the form `cell=formula or value`. Note that string literals are +prefixed with an apostrophe `'`, consistent with Excel's formula bar display. + +**Formulae File Format Details** + +| Storage Representation | Formats | Read | Write | +|:-----------------------|:-------------------------|:-----:|:-----:| +| A1-style strings | XLSX | :o: | :o: | +| RC-style strings | XLML and plaintext | :o: | :o: | +| BIFF Parsed formulae | XLSB and all XLS formats | :o: | | +| OpenFormula formulae | ODS/FODS/UOS | :o: | :o: | + +Since Excel prohibits named cells from colliding with names of A1 or RC style +cell references, a (not-so-simple) regex conversion is possible. BIFF Parsed +formulae have to be explicitly unwound. OpenFormula formulae can be converted +with regexes for the most part. diff --git a/docbits/62_columns.md b/docbits/62_columns.md new file mode 100644 index 0000000..4613e10 --- /dev/null +++ b/docbits/62_columns.md @@ -0,0 +1,31 @@ +#### Column Properties + +Excel internally stores column widths in a nebulous "Max Digit Width" form. The +Max Digit Width is the width of the largest digit when rendered. The internal +width must be an integer multiple of the the width divided by 256. ECMA-376 +describes a formula for converting between pixels and the internal width. + +Given the constraints, it is possible to determine the MDW without actually +inspecting the font! The parsers guess the pixel width by converting from width +to pixels and back, repeating for all possible MDW and selecting the MDW that +minimizes the error. XLML actually stores the pixel width, so the guess works +in the opposite direction. + +The `!cols` array in each worksheet, if present, is a collection of `ColInfo` +objects which have the following properties: + +```typescript +type ColInfo = { + MDW?:number; // Excel's "Max Digit Width" unit, always integral + width:number; // width in Excel's "Max Digit Width", width*256 is integral + wpx?:number; // width in screen pixels + wch?:number; // intermediate character calculation +}; +``` + +Even though all of the information is made available, writers are expected to +follow the priority order: + +1) use `width` field if available +2) use `wpx` pixel width if available +2) use `wch` character count if available diff --git a/docbits/80_parseopts.md b/docbits/80_parseopts.md new file mode 100644 index 0000000..a4ef4f9 --- /dev/null +++ b/docbits/80_parseopts.md @@ -0,0 +1,72 @@ +## Parsing Options + +The exported `read` and `readFile` functions accept an options argument: + +| Option Name | Default | Description | +| :---------- | ------: | :--------------------------------------------------- | +| type | | Input data encoding (see Input Type below) | +| cellFormula | true | Save formulae to the .f field ** | +| cellHTML | true | Parse rich text and save HTML to the .h field | +| cellNF | false | Save number format string to the .z field | +| cellStyles | false | Save style/theme info to the .s field | +| cellDates | false | Store dates as type `d` (default is `n`) ** | +| sheetStubs | false | Create cell objects of type `z` for stub cells | +| sheetRows | 0 | If >0, read the first `sheetRows` rows ** | +| bookDeps | false | If true, parse calculation chains | +| bookFiles | false | If true, add raw files to book object ** | +| bookProps | false | If true, only parse enough to get book metadata ** | +| bookSheets | false | If true, only parse enough to get the sheet names | +| bookVBA | false | If true, expose vbaProject.bin to `vbaraw` field ** | +| password | "" | If defined and file is encrypted, use password ** | +| WTF | false | If true, throw errors on unexpected file features ** | + +- `cellFormula` option only applies to formats that require extra processing to + parse formulae (XLS/XLSB). +- Even if `cellNF` is false, formatted text will be generated and saved to `.w` +- In some cases, sheets may be parsed even if `bookSheets` is false. +- `bookSheets` and `bookProps` combine to give both sets of information +- `Deps` will be an empty object if `bookDeps` is falsy +- `bookFiles` behavior depends on file type: + * `keys` array (paths in the ZIP) for ZIP-based formats + * `files` hash (mapping paths to objects representing the files) for ZIP + * `cfb` object for formats using CFB containers +- `sheetRows-1` rows will be generated when looking at the JSON object output + (since the header row is counted as a row when parsing the data) +- `bookVBA` merely exposes the raw vba object. It does not parse the data. +- `cellDates` currently does not convert numerical dates to JS dates. +- Currently only XOR encryption is supported. Unsupported error will be thrown + for files employing other encryption methods. +- WTF is mainly for development. By default, the parser will suppress read + errors on single worksheets, allowing you to read from the worksheets that do + parse properly. Setting `WTF:1` forces those errors to be thrown. + +The defaults are enumerated in bits/84\_defaults.js + +### Input Type + +Strings can be interpreted in multiple ways. The `type` parameter for `read` +tells the library how to parse the data argument: + +| `type` | expected input | +|------------|-----------------------------------------------------------------| +| `"base64"` | string: base64 encoding of the file | +| `"binary"` | string: binary string (`n`-th byte is `data.charCodeAt(n)`) | +| `"buffer"` | nodejs Buffer | +| `"array"` | array: array of 8-bit unsigned int (`n`-th byte is `data[n]`) | +| `"file"` | string: filename that will be read and processed (nodejs only) | + +### Guessing File Type + +Excel and other spreadsheet tools read the first few bytes and apply other +heuristics to determine a file type. This enables file type punning: renaming +files with the `.xls` extension will tell your computer to use Excel to open the +file but Excel will know how to handle it. This library applies similar logic: + +| Byte 0 | Raw File Type | Spreadsheet Types | +|:-------|:--------------|:----------------------------------------------------| +| `0xD0` | CFB Container | BIFF 5/8 or password-protected XLSX/XLSB | +| `0x09` | BIFF Stream | BIFF 2/3/4/5 | +| `0x3C` | XML/HTML | SpreadsheetML or Flat ODS or UOS1 or HTML | +| `0x50` | ZIP Archive | XLSB or XLSX/M or ODS or UOS2 | +| `0xFE` | UTF8 Text | SpreadsheetML or Flat ODS or UOS1 | + diff --git a/docbits/81_writeopts.md b/docbits/81_writeopts.md new file mode 100644 index 0000000..205af24 --- /dev/null +++ b/docbits/81_writeopts.md @@ -0,0 +1,52 @@ +## Writing Options + +The exported `write` and `writeFile` functions accept an options argument: + +| Option Name | Default | Description | +| :---------- | -------: | :-------------------------------------------------- | +| type | | Output data encoding (see Output Type below) | +| cellDates | `false` | Store dates as type `d` (default is `n`) | +| bookSST | `false` | Generate Shared String Table ** | +| bookType | `"xlsx"` | Type of Workbook (see below for supported formats) | +| sheet | `""` | Name of Worksheet for single-sheet formats ** | +| compression | `false` | Use ZIP compression for ZIP-based formats ** | + +- `bookSST` is slower and more memory intensive, but has better compatibility + with older versions of iOS Numbers +- The raw data is the only thing guaranteed to be saved. Formulae, formatting, + and other niceties may not be serialized (pending CSF standardization) +- `cellDates` only applies to XLSX output and is not guaranteed to work with + third-party readers. Excel itself does not usually write cells with type `d` + so non-Excel tools may ignore the data or blow up in the presence of dates. + +### Supported Output Formats + +For broad compatibility with third-party tools, this library supports many +output formats. The specific file type is controlled with `bookType` option: + +| bookType | file ext | container | sheets | Description | +| :------- | -------: | :-------: | :----- |:--------------------------------- | +| `xlsx` | `.xlsx` | ZIP | multi | Excel 2007+ XML Format | +| `xlsm` | `.xlsm` | ZIP | multi | Excel 2007+ Macro XML Format | +| `xlsb` | `.xlsb` | ZIP | multi | Excel 2007+ Binary Format | +| `ods` | `.ods` | ZIP | multi | OpenDocument Spreadsheet | +| `biff2` | `.xls` | none | single | Excel 2.0 Worksheet format | +| `fods` | `.fods` | none | multi | Flat OpenDocument Spreadsheet | +| `csv` | `.csv` | none | single | Comma Separated Values | + +- `compression` only applies to formats with ZIP containers. +- Formats that only support a single sheet require a `sheet` option specifying + the worksheet. If the string is empty, the first worksheet is used. + +### Output Type + +The `type` argument for `write` mirrors the `type` argument for `read`: + +| `type` | output | +|------------|-----------------------------------------------------------------| +| `"base64"` | string: base64 encoding of the file | +| `"binary"` | string: binary string (`n`-th byte is `data.charCodeAt(n)`) | +| `"buffer"` | nodejs Buffer | +| `"file"` | string: name of file to be written (nodejs only) | + + diff --git a/docbits/82_util.md b/docbits/82_util.md new file mode 100644 index 0000000..2a26720 --- /dev/null +++ b/docbits/82_util.md @@ -0,0 +1,124 @@ +## Utility Functions + +The `sheet_to_*` functions accept a worksheet and an optional options object. + +The examples are based on the following worksheet: + +``` +XXX| A | B | C | D | E | F | G | +---+---+---+---+---+---+---+---+ + 1 | S | h | e | e | t | J | S | + 2 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | + 3 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | +``` + +### Formulae Output + +`XLSX.utils.sheet_to_formulae` generates an array of commands that represent +how a person would enter data into an application. Each entry is of the form +`A1-cell-address=formula-or-value`. String literals are prefixed with a `'` in +accordance with Excel. For the example sheet: + +```js +> var o = XLSX.utils.sheet_to_formulae(ws); +> o.filter(function(v, i) { return i % 5 === 0; }); +[ 'A1=\'S', 'F1=\'J', 'D2=4', 'B3=3', 'G3=8' ] +``` + +### CSV and general DSV Output + +As an alternative to the `writeFile` CSV type, `XLSX.utils.sheet_to_csv` also +produces CSV output. The function takes an options argument: + +| Option Name | Default | Description | +| :---------- | :------: | :-------------------------------------------------- | +| FS | `","` | "Field Separator" delimiter between fields | +| RS | `"\n"` | "Record Separator" delimiter between rows | + +For the example sheet: + +```js +> console.log(XLSX.utils.sheet_to_csv(ws)); +S,h,e,e,t,J,S +1,2,3,4,5,6,7 +2,3,4,5,6,7,8 +> console.log(XLSX.utils.sheet_to_csv(ws, {FS:"\t"})); +S h e e t J S +1 2 3 4 5 6 7 +2 3 4 5 6 7 8 +> console.log(X.utils.sheet_to_csv(_ws,{FS:":",RS:"|"})); +S:h:e:e:t:J:S|1:2:3:4:5:6:7|2:3:4:5:6:7:8| +``` + +### JSON + +`XLSX.utils.sheet_to_json` and the alias `XLSX.utils.sheet_to_row_object_array` +generate different types of JS objects. The function takes an options argument: + +| Option Name | Default | Description | +| :---------- | :------: | :-------------------------------------------------- | +| raw | `false` | Use raw values (true) or formatted strings (false) | +| range | from WS | Override Range (see table below) | +| header | | Control output format (see table below) | + +- `raw` only affects cells which have a format code (`.z`) field or a formatted + text (`.w`) field. +- If `header` is specified, the first row is considered a data row; if `header` + is not specified, the first row is the header row and not considered data. +- When `header` is not specified, the conversion will automatically disambiguate + header entries by affixing `_` and a count starting at `1`. For example, if + three columns have header `foo` the output fields are `foo`, `foo_1`, `foo_2` + +`range` is expected to be one of: + +| `range` | Description | +| :--------------- | :-------------------------------------------------------- | +| (number) | Use worksheet range but set starting row to the value | +| (string) | Use specified range (A1-style bounded range string) | +| (default) | Use worksheet range (`ws['!ref']`) | + +`header` is expected to be one of: + +| `header` | Description | +| :--------------- | :-------------------------------------------------------- | +| `1` | Generate an array of arrays | +| `"A"` | Row object keys are literal column labels | +| array of strings | Use specified strings as keys in row objects | +| (default) | Read and disambiguate first row as keys | + +For the example sheet: + +```js +> console.log(X.utils.sheet_to_json(_ws)); +[ { S: 1, h: 2, e: 3, e_1: 4, t: 5, J: 6, S_1: 7 }, + { S: 2, h: 3, e: 4, e_1: 5, t: 6, J: 7, S_1: 8 } ] + +> console.log(X.utils.sheet_to_json(_ws, {header:1})); +[ [ 'S', 'h', 'e', 'e', 't', 'J', 'S' ], + [ 1, 2, 3, 4, 5, 6, 7 ], + [ 2, 3, 4, 5, 6, 7, 8 ] ] + +> console.log(X.utils.sheet_to_json(_ws, {header:"A"})); +[ { A: 'S', B: 'h', C: 'e', D: 'e', E: 't', F: 'J', G: 'S' }, + { A: 1, B: 2, C: 3, D: 4, E: 5, F: 6, G: 7 }, + { A: 2, B: 3, C: 4, D: 5, E: 6, F: 7, G: 8 } ] +> console.log(X.utils.sheet_to_json(_ws, {header:["A","E","I","O","U","6","9"]})); +[ { '6': 'J', '9': 'S', A: 'S', E: 'h', I: 'e', O: 'e', U: 't' }, + { '6': 6, '9': 7, A: 1, E: 2, I: 3, O: 4, U: 5 }, + { '6': 7, '9': 8, A: 2, E: 3, I: 4, O: 5, U: 6 } ] +``` + +Example showing the effect of `raw`: + +```js +> _ws['A2'].w = "1"; // set A2 formatted string value +> console.log(X.utils.sheet_to_json(_ws, {header:1})); +[ [ 'S', 'h', 'e', 'e', 't', 'J', 'S' ], + [ '1', 2, 3, 4, 5, 6, 7 ], // <-- A2 uses the formatted string + [ 2, 3, 4, 5, 6, 7, 8 ] ] +> console.log(X.utils.sheet_to_json(_ws, {header:1, raw:true})); +[ [ 'S', 'h', 'e', 'e', 't', 'J', 'S' ], + [ 1, 2, 3, 4, 5, 6, 7 ], // <-- A2 uses the raw value + [ 2, 3, 4, 5, 6, 7, 8 ] ] +``` + diff --git a/docbits/85_filetype.md b/docbits/85_filetype.md new file mode 100644 index 0000000..ca12816 --- /dev/null +++ b/docbits/85_filetype.md @@ -0,0 +1,93 @@ +## File Formats + +Despite the library name `xlsx`, it supports numerous spreadsheet file formats: + +| Format | Read | Write | +|:-------------------------------------------------------------|:-----:|:-----:| +| **Excel Worksheet/Workbook Formats** |:-----:|:-----:| +| Excel 2007+ XML Formats (XLSX/XLSM) | :o: | :o: | +| Excel 2007+ Binary Format (XLSB BIFF12) | :o: | :o: | +| Excel 2003-2004 XML Format (XML "SpreadsheetML") | :o: | :o: | +| Excel 97-2004 (XLS BIFF8) | :o: | | +| Excel 5.0/95 (XLS BIFF5) | :o: | | +| Excel 4.0 (XLS/XLW BIFF4) | :o: | | +| Excel 3.0 (XLS BIFF3) | :o: | | +| Excel 2.0/2.1 (XLS BIFF2) | :o: | :o: | +| **Excel Supported Text Formats** |:-----:|:-----:| +| Delimiter-Separated Values (CSV/TSV/DSV) | | :o: | +| **Other Workbook/Worksheet Formats** |:-----:|:-----:| +| OpenDocument Spreadsheet (ODS) | :o: | :o: | +| Flat XML ODF Spreadsheet (FODS) | :o: | :o: | +| Uniform Office Format Spreadsheet (标文通 UOS1/UOS2) | :o: | | +| **Other Common Spreadsheet Output Formats** |:-----:|:-----:| +| HTML Tables | :o: | | + +### Excel 2007+ XML (XLSX/XLSM) + +XLSX and XLSM files are ZIP containers containing a series of XML files in +accordance with the Open Packaging Conventions (OPC). The XLSM filetype, almost +identical to XLSX, is used for files containing macros. + +The format is standardized in ECMA-376 and later in ISO/IEC 29500. Excel does +not follow the specification, and there are additional documents discussing how +Excel deviates from the specification. + +### Excel 2.0-95 (BIFF2/BIFF3/BIFF4/BIFF5) + +BIFF 2/3 XLS are single-sheet streams of binary records. Excel 4 introduced +the concept of a workbook (`XLW` files) but also had single-sheet `XLS` format. +The structure is largely similar to the Lotus 1-2-3 file formats. BIFF5/8/12 +extended the format in various ways but largely stuck to the same record format. + +There is no official specification for any of these formats. Excel 95 can write +files in these formats, so record lengths and fields were backsolved by writing +in all of the supported formats and comparing files. Excel 2016 can generate +BIFF5 files, enabling a full suite of file tests starting from XLSX or BIFF2. + +### Excel 97-2004 Binary (BIFF8) + +BIFF8 exclusively uses the Compound File Binary container format, splitting some +content into streams within the file. At its core, it still uses an extended +version of the binary record format from older versions of BIFF. + +The `MS-XLS` specification covers the basics of the file format, and other +specifications expand on serialization of features like properties. + +### Excel 2003-2004 (SpreadsheetML) + +Predating XLSX, SpreadsheetML files are simple XML files. There is no official +and comprehensive specification, although MS has released whitepapers on the +format. Since Excel 2016 can generate SpreadsheetML files, backsolving is +pretty straightforward. + +### Excel 2007+ Binary (XLSB, BIFF12) + +Introduced in parallel with XLSX, the XLSB filetype combines BIFF architecture +with the content separation and ZIP container of XLSX. For the most part nodes +in an XLSX sub-file can be mapped to XLSB records in a corresponding sub-file. + +The `MS-XLSB` specification covers the basics of the file format, and other +specifications expand on serialization of features like properties. + +### OpenDocument Spreadsheet (ODS/FODS) and Uniform Office Spreadsheet (UOS1/2) + +ODS is an XML-in-ZIP format akin to XLSX while FODS is an XML format akin to +SpreadsheetML. Both are detailed in the OASIS standard, but tools like LO/OO +add undocumented extensions. + +UOS is a very similar format, and it comes in 2 varieties corresponding to ODS +and FODS respectively. For the most part, the difference between the formats +lies in the names of tags and attributes. + +### Comma-Separated Values + +Excel CSV deviates from RFC4180 in a number of important ways. The generated +CSV files should generally work in Excel although they may not work in RFC4180 +compatible readers. + +### HTML + +Excel HTML worksheets include special metadata encoded in styles. For example, +`mso-number-format` is a localized string containing the number format. Despite +the metadata the output is valid HTML, although it does accept bare `&` symbols. + diff --git a/docbits/90_test.md b/docbits/90_test.md new file mode 100644 index 0000000..ab23fa7 --- /dev/null +++ b/docbits/90_test.md @@ -0,0 +1,62 @@ +## Testing + +`make test` will run the node-based tests. By default it runs tests on files in +every supported format. To test a specific file type, set `FMTS` to the format +you want to test. Feature-specific tests are avaialble with `make test_misc` + +```bash +$ make test # run full tests +$ make test_xls # only use the XLS test files +$ make test_xlsx # only use the XLSX test files +$ make test_xlsb # only use the XLSB test files +$ make test_xml # only use the XLSB test files +$ make test_ods # only use the XLSB test files +``` + +To enable all errors, set the environment variable `WTF=1`: + +```bash +$ make test # run full tests +$ WTF=1 make test # enable all error messages +``` + +Flow and JSHint/JSCS checks are available: + +```bash +$ make lint # JSHint and JSCS checks +$ make flow # make lint + Flow checking +``` + +To run the in-browser tests, clone the repo for +[oss.sheetjs.com](https://github.com/SheetJS/SheetJS.github.io) and replace +the xlsx.js file (then fire up the browser and go to `stress.html`): + +```bash +$ cp xlsx.js ../SheetJS.github.io +$ cd ../SheetJS.github.io +$ simplehttpserver # or "python -mSimpleHTTPServer" or "serve" +$ open -a Chromium.app http://localhost:8000/stress.html +``` +### Tested Environments + + - NodeJS 0.8, 0.9, 0.10, 0.11, 0.12, 4.x, 5.x, 6.x, 7.x + - IE 6/7/8/9/10/11 (IE6-9 browsers require shims for interacting with client) + - Chrome 24+ + - Safari 6+ + - FF 18+ + +Tests utilize the mocha testing framework. Travis-CI and Sauce Labs links: + + - for XLSX module in nodejs + - for XLSX module in nodejs + - for XLS\* modules + - for XLS\* modules using Sauce Labs + +### Test Files + +Test files are housed in [another repo](https://github.com/SheetJS/test_files). + +Running `make init` will refresh the `test_files` submodule and get the files. + + + diff --git a/docbits/95_contrib.md b/docbits/95_contrib.md new file mode 100644 index 0000000..97b7c66 --- /dev/null +++ b/docbits/95_contrib.md @@ -0,0 +1,21 @@ +## Contributing + +Due to the precarious nature of the Open Specifications Promise, it is very +important to ensure code is cleanroom. Consult CONTRIBUTING.md + +The xlsx.js file is constructed from the files in the `bits` subdirectory. The +build script (run `make`) will concatenate the individual bits to produce the +script. Before submitting a contribution, ensure that running make will produce +the xlsx.js file exactly. The simplest way to test is to add the script: + +```bash +$ git add xlsx.js +$ make clean +$ make +$ git diff xlsx.js +``` + +To produce the dist files, run `make dist`. The dist files are updated in each +version release and *should not be committed between versions*. + + diff --git a/docbits/97_license.md b/docbits/97_license.md new file mode 100644 index 0000000..a13d311 --- /dev/null +++ b/docbits/97_license.md @@ -0,0 +1,6 @@ +## License + +Please consult the attached LICENSE file for details. All rights not explicitly +granted by the Apache 2.0 License are reserved by the Original Author. + + diff --git a/docbits/98_reference.md b/docbits/98_reference.md new file mode 100644 index 0000000..0bd1daf --- /dev/null +++ b/docbits/98_reference.md @@ -0,0 +1,30 @@ +## References + +ISO/IEC 29500:2012(E) "Information technology — Document description and processing languages — Office Open XML File Formats" + +OSP-covered specifications: + + - [MS-XLSB]: Excel (.xlsb) Binary File Format + - [MS-XLSX]: Excel (.xlsx) Extensions to the Office Open XML SpreadsheetML File Format + - [MS-OE376]: Office Implementation Information for ECMA-376 Standards Support + - [MS-CFB]: Compound File Binary File Format + - [MS-XLS]: Excel Binary File Format (.xls) Structure Specification + - [MS-ODATA]: Open Data Protocol (OData) + - [MS-OFFCRYPTO]: Office Document Cryptography Structure + - [MS-OLEDS]: Object Linking and Embedding (OLE) Data Structures + - [MS-OLEPS]: Object Linking and Embedding (OLE) Property Set Data Structures + - [MS-OSHARED]: Office Common Data Types and Objects Structures + - [MS-ODRAW]: Office Drawing Binary File Format + - [MS-ODRAWXML]: Office Drawing Extensions to Office Open XML Structure + - [MS-OVBA]: Office VBA File Format Structure + - [MS-CTXLS]: Excel Custom Toolbar Binary File Format + - [MS-XLDM]: Spreadsheet Data Model File Format + - [MS-EXSPXML3]: Excel Calculation Version 2 Web Service XML Schema + - [XLS]: Microsoft Office Excel 97-2007 Binary File Format Specification + - [MS-OI29500]: Office Implementation Information for ISO/IEC 29500 Standards Support + +Open Document Format for Office Applications Version 1.2 (29 September 2011) + +Worksheet File Format (From Lotus) December 1984 + + diff --git a/docbits/99_badges.md b/docbits/99_badges.md new file mode 100644 index 0000000..615917c --- /dev/null +++ b/docbits/99_badges.md @@ -0,0 +1,17 @@ +## Badges + +[![Build Status](https://saucelabs.com/browser-matrix/xlsx.svg)](https://saucelabs.com/u/xlsx) + +[![Build Status](https://travis-ci.org/SheetJS/js-xlsx.svg?branch=master)](https://travis-ci.org/SheetJS/js-xlsx) + +[![Build Status](https://semaphoreci.com/api/v1/sheetjs/js-xlsx/branches/master/shields_badge.svg)](https://semaphoreci.com/sheetjs/js-xlsx) + +[![Coverage Status](http://img.shields.io/coveralls/SheetJS/js-xlsx/master.svg)](https://coveralls.io/r/SheetJS/js-xlsx?branch=master) + +[![NPM Downloads](https://img.shields.io/npm/dt/xlsx.svg)](https://npmjs.org/package/xlsx) + +[![Dependencies Status](https://david-dm.org/sheetjs/js-xlsx/status.svg)](https://david-dm.org/sheetjs/js-xlsx) + +[![ghit.me](https://ghit.me/badge.svg?repo=sheetjs/js-xlsx)](https://ghit.me/repo/sheetjs/js-xlsx) + +[![Analytics](https://ga-beacon.appspot.com/UA-36810333-1/SheetJS/js-xlsx?pixel)](https://github.com/SheetJS/js-xlsx) diff --git a/misc/flow.js b/misc/flow.js index dc78ed1..feeb605 100644 --- a/misc/flow.js +++ b/misc/flow.js @@ -59,4 +59,11 @@ type SST = { }; type Comment = any; + +type ColInfo = { + MDW?:number; // Excel's "Max Digit Width" unit, always integral + width:number; // width in Excel's "Max Digit Width", width*256 is integral + wpx?:number; // width in screen pixels + wch?:number; // intermediate character calculation +}; */ diff --git a/test.js b/test.js index 23b7ceb..62ac8aa 100644 --- a/test.js +++ b/test.js @@ -66,6 +66,12 @@ var paths = { nfxlsb: dir + 'number_format.xlsb', dtxlsx: dir + 'xlsx-stream-d-date-cell.xlsx', dtxlsb: dir + 'xlsx-stream-d-date-cell.xlsb', + cwxls: dir + 'column_width.xlsx', + cwxls5: dir + 'column_width.biff5', + cwxml: dir + 'column_width.xml', + cwxlsx: dir + 'column_width.xlsx', + cwxlsb: dir + 'column_width.xlsx', + dtxlsb: dir + 'xlsx-stream-d-date-cell.xlsb', swcxls: dir + 'apachepoi_SimpleWithComments.xls', swcxml: dir + '2011/apachepoi_SimpleWithComments.xls.xml', swcxlsx: dir + 'apachepoi_SimpleWithComments.xlsx', @@ -680,6 +686,49 @@ describe('parse features', function() { }); }); + describe('column properties', function() { + var wb1, wb2, wb3, wb4, wb5; + var bef = (function() { + X = require(modp); + wb1 = X.readFile(paths.cwxlsx, {cellStyles:true}); + wb2 = X.readFile(paths.cwxlsb, {cellStyles:true}); + wb3 = X.readFile(paths.cwxls, {cellStyles:true}); + wb4 = X.readFile(paths.cwxls5, {cellStyles:true}); + wb5 = X.readFile(paths.cwxml, {cellStyles:true}); + }); + if(typeof before != 'undefined') before(bef); + else it('before', bef); + it('should have "!cols"', function() { + assert(wb1.Sheets.Sheet1['!cols']); + assert(wb2.Sheets.Sheet1['!cols']); + assert(wb3.Sheets.Sheet1['!cols']); + assert(wb4.Sheets.Sheet1['!cols']); + assert(wb5.Sheets.Sheet1['!cols']); + }); + it('should have correct widths', function() { + [wb1, wb2, wb3, wb4, wb5].map(function(x) { return x.Sheets.Sheet1['!cols']; }).forEach(function(x) { + assert.equal(x[1].width, 0.1640625); + assert.equal(x[2].width, 16.6640625); + assert.equal(x[3].width, 1.6640625); + assert.equal(x[4].width, 4.83203125); + assert.equal(x[5].width, 8.83203125); + assert.equal(x[6].width, 12.83203125); + assert.equal(x[7].width, 16.83203125); + }); + }); + it('should have correct pixels', function() { + [wb1, wb2, wb3, wb4, wb5].map(function(x) { return x.Sheets.Sheet1['!cols']; }).forEach(function(x) { + assert.equal(x[1].wpx, 1); + assert.equal(x[2].wpx, 100); + assert.equal(x[3].wpx, 10); + assert.equal(x[4].wpx, 29); + assert.equal(x[5].wpx, 53); + assert.equal(x[6].wpx, 77); + assert.equal(x[7].wpx, 101); + }); + }); + }); + describe('merge cells',function() { var wb1, wb2, wb3, wb4, wb5; var bef = (function() { diff --git a/test_files b/test_files index 664ad78..7fe887f 160000 --- a/test_files +++ b/test_files @@ -1 +1 @@ -Subproject commit 664ad78895cb8dad33e8e993614555baf7d999ae +Subproject commit 7fe887ff7b26b233db24f3d4df513319c493efc8 diff --git a/xlsx.flow.js b/xlsx.flow.js index 95f8e80..fd09e05 100644 --- a/xlsx.flow.js +++ b/xlsx.flow.js @@ -1398,7 +1398,7 @@ function str2cc(str) { } function dup(o/*:any*/)/*:any*/ { - if(typeof JSON != 'undefined') return JSON.parse(JSON.stringify(o)); + if(typeof JSON != 'undefined' && !Array.isArray(o)) return JSON.parse(JSON.stringify(o)); if(typeof o != 'object' || o == null) return o; var out = {}; for(var k in o) if(o.hasOwnProperty(k)) out[k] = dup(o[k]); @@ -3786,10 +3786,11 @@ function parse_RecalcId(blob, length) { } /* 2.4.87 */ -function parse_DefaultRowHeight (blob, length) { - var f = length == 4 ? blob.read_shift(2) : 0, miyRw; - miyRw = blob.read_shift(2); // flags & 0x02 -> hidden, else empty +function parse_DefaultRowHeight(blob, length) { + var f = blob.read_shift(2); var fl = {Unsynced:f&1,DyZero:(f&2)>>1,ExAsc:(f&4)>>2,ExDsc:(f&8)>>3}; + /* char is misleading, miyRw and miyRwHidden overlap */ + var miyRw = blob.read_shift(2); return [fl, miyRw]; } @@ -3875,12 +3876,13 @@ function parse_MulBlank(blob, length) { } /* 2.5.20 2.5.249 TODO: interpret values here */ -function parse_CellStyleXF(blob, length, style) { +function parse_CellStyleXF(blob, length, style, opts) { var o = {}; var a = blob.read_shift(4), b = blob.read_shift(4); var c = blob.read_shift(4), d = blob.read_shift(2); o.patternType = XLSFillPattern[c >> 26]; + if(!opts.cellStyles) return o; o.alc = a & 0x07; o.fWrap = (a >> 3) & 0x01; o.alcV = (a >> 4) & 0x07; @@ -3914,16 +3916,16 @@ function parse_CellStyleXF(blob, length, style) { o.fsxButton = (d >> 14) & 0x01; return o; } -function parse_CellXF(blob, length) {return parse_CellStyleXF(blob,length,0);} -function parse_StyleXF(blob, length) {return parse_CellStyleXF(blob,length,1);} +function parse_CellXF(blob, length, opts) {return parse_CellStyleXF(blob,length,0, opts);} +function parse_StyleXF(blob, length, opts) {return parse_CellStyleXF(blob,length,1, opts);} /* 2.4.353 TODO: actually do this right */ -function parse_XF(blob, length) { +function parse_XF(blob, length, opts) { var o = {}; o.ifnt = blob.read_shift(2); o.ifmt = blob.read_shift(2); o.flags = blob.read_shift(2); o.fStyle = (o.flags >> 2) & 0x01; length -= 6; - o.data = parse_CellStyleXF(blob, length, o.fStyle); + o.data = parse_CellStyleXF(blob, length, o.fStyle, opts); return o; } @@ -4173,12 +4175,24 @@ function parse_XFCRC(blob, length) { return o; } +/* 2.4.53 TODO: parse flags */ +/* [MS-XLSB] 2.4.323 TODO: parse flags */ +function parse_ColInfo(blob, length, opts) { + if(!opts.cellStyles) return parsenoop(blob, length); + var w = opts && opts.biff >= 12 ? 4 : 2; + var colFirst = blob.read_shift(w); + var colLast = blob.read_shift(w); + var coldx = blob.read_shift(w); + var ixfe = blob.read_shift(w); + var flags = blob.read_shift(2); + if(w == 2) blob.l += 2; + return {s:colFirst, e:colLast, w:coldx, ixfe:ixfe, flags:flags}; +} + var parse_Style = parsenoop; var parse_StyleExt = parsenoop; -var parse_ColInfo = parsenoop; - var parse_Window2 = parsenoop; @@ -5039,17 +5053,43 @@ function rgb_tint(hex, tint) { } /* 18.3.1.13 width calculations */ +/* [MS-OI29500] 2.1.595 Column Width & Formatting */ var DEF_MDW = 7, MAX_MDW = 15, MIN_MDW = 1, MDW = DEF_MDW; -function width2px(width) { return (( width + ((128/MDW)|0)/256 )* MDW )|0; } -function px2char(px) { return (((px - 5)/MDW * 100 + 0.5)|0)/100; } -function char2width(chr) { return (((chr * MDW + 5)/MDW*256)|0)/256; } +function width2px(width) { return Math.floor(( width + (Math.round(128/MDW))/256 )* MDW ); } +function px2char(px) { return (Math.floor((px - 5)/MDW * 100 + 0.5))/100; } +function char2width(chr) { return (Math.round((chr * MDW + 5)/MDW*256))/256; } +function px2char_(px) { return (((px - 5)/MDW * 100 + 0.5))/100; } +function char2width_(chr) { return (((chr * MDW + 5)/MDW*256))/256; } function cycle_width(collw) { return char2width(px2char(width2px(collw))); } -function find_mdw(collw, coll) { - if(cycle_width(collw) != collw) { - for(MDW=DEF_MDW; MDW>MIN_MDW; --MDW) if(cycle_width(collw) === collw) break; - if(MDW === MIN_MDW) for(MDW=DEF_MDW+1; MDW 0.5) guess--; + if(Math.abs(guess) < delta) { delta = Math.abs(guess); _MDW = MDW; } } + MDW = _MDW; +} + +function process_col(coll/*:ColInfo*/) { + if(coll.width) { + coll.wpx = width2px(coll.width); + coll.wch = px2char(coll.wpx); + coll.MDW = MDW; + } else if(coll.wpx) { + coll.wch = px2char(coll.wpx); + coll.width = char2width(coll.wch); + coll.MDW = MDW; + } + if(coll.customWidth) delete coll.customWidth; } /* [MS-EXSPXML3] 2.4.54 ST_enmPattern */ @@ -8552,14 +8592,10 @@ function parse_ws_xml_cols(columns, cols) { for(var coli = 0; coli != cols.length; ++coli) { var coll = parsexmltag(cols[coli], true); var colm=parseInt(coll.min, 10)-1, colM=parseInt(coll.max,10)-1; - delete coll.min; delete coll.max; - if(!seencol && coll.width) { seencol = true; find_mdw(+coll.width, coll); } - if(coll.width) { - coll.wpx = width2px(+coll.width); - coll.wch = px2char(coll.wpx); - coll.MDW = MDW; - } - while(colm <= colM) columns[colm++] = coll; + delete coll.min; delete coll.max; coll.width = +coll.width; + if(!seencol && coll.width) { seencol = true; find_mdw_colw(coll.width); } + process_col(coll); + while(colm <= colM) columns[colm++] = dup(coll); } } @@ -8570,7 +8606,9 @@ function write_ws_xml_cols(ws, cols)/*:string*/ { var p = ({min:i+1,max:i+1}/*:any*/); /* wch (chars), wpx (pixels) */ width = -1; - if(col.wpx) width = px2char(col.wpx); + if(col.MDW) MDW = col.MDW; + if(col.width); + else if(col.wpx) width = px2char(col.wpx); else if(col.wch) width = col.wch; if(width > -1) { p.width = char2width(width); p.customWidth= 1; } o[o.length] = (writextag('col', null, p)); @@ -9074,6 +9112,10 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles)/*:Worksheet*/ { for(var i = 0; i < wb.Names['!names'].length; ++i) supbooks[0][i+1] = wb.Names[wb.Names['!names'][i]]; + var colinfo = [], rowinfo = []; + var defwidth = 0, defheight = 0; // twips / MDW respectively + var seencol = false; + recordhopper(data, function ws_parse(val, Record) { if(end) return; switch(Record.n) { @@ -9161,6 +9203,16 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles)/*:Worksheet*/ { s[encode_col(C) + rr].f = stringify_formula(val[1], refguess, {r:row.r, c:C}, supbooks, opts); break; + /* identical to 'ColInfo' in XLS */ + case 'BrtColInfo': { + if(!opts.cellStyles) break; + while(val.e >= val.s) { + colinfo[val.e--] = { width: val.w/256 }; + if(!seencol) { seencol = true; find_mdw_colw(val.w/256); } + process_col(colinfo[val.e+1]); + } + } break; + case 'BrtBeginSheet': break; case 'BrtWsProp': break; // TODO case 'BrtSheetCalcProp': break; // TODO @@ -9176,7 +9228,6 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles)/*:Worksheet*/ { case 'BrtWsFmtInfoEx14': break; // TODO case 'BrtWsFmtInfo': break; // TODO case 'BrtBeginColInfos': break; // TODO - case 'BrtColInfo': break; // TODO case 'BrtEndColInfos': break; // TODO case 'BrtBeginSheetData': break; // TODO case 'BrtEndSheetData': break; // TODO @@ -9289,6 +9340,8 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles)/*:Worksheet*/ { } } if(mergecells.length > 0) s["!merges"] = mergecells; + if(colinfo.length > 0) s["!cols"] = colinfo; + if(rowinfo.length > 0) s["!rows"] = rowinfo; return s; } @@ -10121,8 +10174,9 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ { var mergecells = []; var Props = {}, Custprops = {}, pidx = 0, cp = {}; var comments = [], comment = {}; - var cstys = [], csty; + var cstys = [], csty, seencol = false; var arrayf = []; + var rowinfo = []; xlmlregex.lastIndex = 0; str = str.replace(//mg,""); while((Rn = xlmlregex.exec(str))) switch(Rn[3]) { @@ -10184,6 +10238,8 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ { sheetnames.push(sheetname); if(refguess.s.r <= refguess.e.r && refguess.s.c <= refguess.e.c) cursheet["!ref"] = encode_range(refguess); if(mergecells.length) cursheet["!merges"] = mergecells; + if(cstys.length > 0) cursheet["!cols"] = cstys; + if(rowinfo.length > 0) cursheet["!rows"] = rowinfo; sheets[sheetname] = cursheet; } else { refguess = {s: {r:2000000, c:2000000}, e: {r:0, c:0} }; @@ -10194,6 +10250,7 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ { cursheet = {}; mergecells = []; arrayf = []; + rowinfo = []; } break; case 'Table': @@ -10202,7 +10259,7 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ { else { table = xlml_parsexmltag(Rn[0]); state.push([Rn[3], false]); - cstys = []; + cstys = []; seencol = false; } break; @@ -10218,8 +10275,14 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ { case 'Column': if(state[state.length-1][0] !== 'Table') break; csty = xlml_parsexmltag(Rn[0]); + csty.wpx = parseInt(csty.Width, 10); + if(!seencol && csty.wpx > 10) { + seencol = true; find_mdw_wpx(csty.wpx); + for(var _col = 0; _col < cstys.length; ++_col) if(cstys[_col]) process_col(cstys[_col]); + } + if(seencol) process_col(csty); cstys[(csty.Index-1||cstys.length)] = csty; - for(var i = 0; i < +csty.Span; ++i) cstys[cstys.length] = csty; + for(var i = 0; i < +csty.Span; ++i) cstys[cstys.length] = dup(csty); break; case 'NamedRange': break; @@ -10891,9 +10954,9 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { if(icv < 64) return palette[icv-8] || XLSIcv[icv]; return XLSIcv[icv]; }; - var process_cell_style = function pcs(cell, line/*:any*/) { + var process_cell_style = function pcs(cell, line/*:any*/, options) { var xfd = line.XF.data; - if(!xfd || !xfd.patternType) return; + if(!xfd || !xfd.patternType || !options || !options.cellStyles) return; line.s = ({}/*:any*/); line.s.patternType = xfd.patternType; var t; @@ -10901,8 +10964,9 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { if((t = rgb2Hex(get_rgb(xfd.icvBack)))) { line.s.bgColor = {rgb:t}; } }; var addcell = function addcell(cell/*:any*/, line/*:any*/, options/*:any*/) { + if(file_depth > 1) return; if(!cell_valid) return; - if(options.cellStyles && line.XF && line.XF.data) process_cell_style(cell, line); + if(options.cellStyles && line.XF && line.XF.data) process_cell_style(cell, line, options); lastcell = cell; last_cell = encode_cell(cell); if(range.s) { @@ -10940,11 +11004,15 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { biff: 8, // BIFF version codepage: 0, // CP from CodePage record winlocked: 0, // fLockWn from WinProtect + cellStyles: !!options && !!options.cellStyles, WTF: !!options && !!options.wtf }/*:any*/); if(options.password) opts.password = options.password; var mergecells = []; var objects = []; + var colinfo = [], rowinfo = []; + var defwidth = 0, defheight = 0; // twips / MDW respectively + var seencol = false; var supbooks = ([[]]/*:any*/); // 1-indexed, will hold extern names var sbc = 0, sbci = 0, sbcli = 0; supbooks.SheetNames = opts.snames; @@ -11051,6 +11119,8 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { } if(mergecells.length > 0) out["!merges"] = mergecells; if(objects.length > 0) out["!objects"] = objects; + if(colinfo.length > 0) out["!cols"] = colinfo; + if(rowinfo.length > 0) out["!rows"] = rowinfo; } if(cur_sheet === "") Preamble = out; else Sheets[cur_sheet] = out; out = {}; @@ -11079,6 +11149,9 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { mergecells = []; objects = []; array_formulae = []; opts.arrayf = array_formulae; + colinfo = []; rowinfo = []; + defwidth = defheight = 0; + seencol = false; } break; case 'Number': case 'BIFF2NUM': case 'BIFF2INT': { @@ -11227,6 +11300,19 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { case 'ClrtClient': break; case 'XFExt': update_xfext(XFs[val.ixfe], val.ext); break; + case 'DefColWidth': defwidth = val; break; + case 'DefaultRowHeight': defheight = val[1]; break; // TODO: flags + + case 'ColInfo': { + if(!opts.cellStyles) break; + while(val.e >= val.s) { + colinfo[val.e--] = { width: val.w/256 }; + if(!seencol) { seencol = true; find_mdw_colw(val.w/256); } + process_col(colinfo[val.e+1]); + } + } break; + case 'Row': break; // TODO + case 'NameCmt': break; case 'Header': break; // TODO case 'Footer': break; // TODO @@ -11234,11 +11320,8 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { case 'VCenter': break; // TODO case 'Pls': break; // TODO case 'Setup': break; // TODO - case 'DefColWidth': break; // TODO case 'GCW': break; case 'LHRecord': break; - case 'ColInfo': break; // TODO - case 'Row': break; // TODO case 'DBCell': break; // TODO case 'EntExU2': break; // TODO case 'SxView': break; // TODO @@ -11256,7 +11339,7 @@ function parse_workbook(blob, options/*:ParseOpts*/)/*:Workbook*/ { case 'Feature11': case 'Feature12': case 'List12': break; case 'Country': country = val; break; case 'RecalcId': break; - case 'DefaultRowHeight': case 'DxGCol': break; // TODO: htmlify + case 'DxGCol': break; // TODO: htmlify case 'Fbi': case 'Fbi2': case 'GelFrame': break; case 'Font': break; // TODO case 'XFCRC': break; // TODO @@ -11576,7 +11659,7 @@ var XLSBRecordEnum = { /*::[*/0x0039/*::]*/: { n:"BrtEndMdxTuple", f:parsenoop }, /*::[*/0x003A/*::]*/: { n:"BrtMdxMbrIstr", f:parsenoop }, /*::[*/0x003B/*::]*/: { n:"BrtStr", f:parsenoop }, - /*::[*/0x003C/*::]*/: { n:"BrtColInfo", f:parsenoop }, + /*::[*/0x003C/*::]*/: { n:"BrtColInfo", f:parse_ColInfo }, /*::[*/0x003E/*::]*/: { n:"BrtCellRString", f:parsenoop }, /*::[*/0x003F/*::]*/: { n:"BrtCalcChainItem$", f:parse_BrtCalcChainItem$ }, /*::[*/0x0040/*::]*/: { n:"BrtDVal", f:parsenoop }, diff --git a/xlsx.js b/xlsx.js index dcc7a8d..e85cba0 100644 --- a/xlsx.js +++ b/xlsx.js @@ -1352,7 +1352,7 @@ function str2cc(str) { } function dup(o) { - if(typeof JSON != 'undefined') return JSON.parse(JSON.stringify(o)); + if(typeof JSON != 'undefined' && !Array.isArray(o)) return JSON.parse(JSON.stringify(o)); if(typeof o != 'object' || o == null) return o; var out = {}; for(var k in o) if(o.hasOwnProperty(k)) out[k] = dup(o[k]); @@ -3734,10 +3734,11 @@ function parse_RecalcId(blob, length) { } /* 2.4.87 */ -function parse_DefaultRowHeight (blob, length) { - var f = length == 4 ? blob.read_shift(2) : 0, miyRw; - miyRw = blob.read_shift(2); // flags & 0x02 -> hidden, else empty +function parse_DefaultRowHeight(blob, length) { + var f = blob.read_shift(2); var fl = {Unsynced:f&1,DyZero:(f&2)>>1,ExAsc:(f&4)>>2,ExDsc:(f&8)>>3}; + /* char is misleading, miyRw and miyRwHidden overlap */ + var miyRw = blob.read_shift(2); return [fl, miyRw]; } @@ -3823,12 +3824,13 @@ function parse_MulBlank(blob, length) { } /* 2.5.20 2.5.249 TODO: interpret values here */ -function parse_CellStyleXF(blob, length, style) { +function parse_CellStyleXF(blob, length, style, opts) { var o = {}; var a = blob.read_shift(4), b = blob.read_shift(4); var c = blob.read_shift(4), d = blob.read_shift(2); o.patternType = XLSFillPattern[c >> 26]; + if(!opts.cellStyles) return o; o.alc = a & 0x07; o.fWrap = (a >> 3) & 0x01; o.alcV = (a >> 4) & 0x07; @@ -3862,16 +3864,16 @@ function parse_CellStyleXF(blob, length, style) { o.fsxButton = (d >> 14) & 0x01; return o; } -function parse_CellXF(blob, length) {return parse_CellStyleXF(blob,length,0);} -function parse_StyleXF(blob, length) {return parse_CellStyleXF(blob,length,1);} +function parse_CellXF(blob, length, opts) {return parse_CellStyleXF(blob,length,0, opts);} +function parse_StyleXF(blob, length, opts) {return parse_CellStyleXF(blob,length,1, opts);} /* 2.4.353 TODO: actually do this right */ -function parse_XF(blob, length) { +function parse_XF(blob, length, opts) { var o = {}; o.ifnt = blob.read_shift(2); o.ifmt = blob.read_shift(2); o.flags = blob.read_shift(2); o.fStyle = (o.flags >> 2) & 0x01; length -= 6; - o.data = parse_CellStyleXF(blob, length, o.fStyle); + o.data = parse_CellStyleXF(blob, length, o.fStyle, opts); return o; } @@ -4121,12 +4123,24 @@ function parse_XFCRC(blob, length) { return o; } +/* 2.4.53 TODO: parse flags */ +/* [MS-XLSB] 2.4.323 TODO: parse flags */ +function parse_ColInfo(blob, length, opts) { + if(!opts.cellStyles) return parsenoop(blob, length); + var w = opts && opts.biff >= 12 ? 4 : 2; + var colFirst = blob.read_shift(w); + var colLast = blob.read_shift(w); + var coldx = blob.read_shift(w); + var ixfe = blob.read_shift(w); + var flags = blob.read_shift(2); + if(w == 2) blob.l += 2; + return {s:colFirst, e:colLast, w:coldx, ixfe:ixfe, flags:flags}; +} + var parse_Style = parsenoop; var parse_StyleExt = parsenoop; -var parse_ColInfo = parsenoop; - var parse_Window2 = parsenoop; @@ -4987,17 +5001,43 @@ function rgb_tint(hex, tint) { } /* 18.3.1.13 width calculations */ +/* [MS-OI29500] 2.1.595 Column Width & Formatting */ var DEF_MDW = 7, MAX_MDW = 15, MIN_MDW = 1, MDW = DEF_MDW; -function width2px(width) { return (( width + ((128/MDW)|0)/256 )* MDW )|0; } -function px2char(px) { return (((px - 5)/MDW * 100 + 0.5)|0)/100; } -function char2width(chr) { return (((chr * MDW + 5)/MDW*256)|0)/256; } +function width2px(width) { return Math.floor(( width + (Math.round(128/MDW))/256 )* MDW ); } +function px2char(px) { return (Math.floor((px - 5)/MDW * 100 + 0.5))/100; } +function char2width(chr) { return (Math.round((chr * MDW + 5)/MDW*256))/256; } +function px2char_(px) { return (((px - 5)/MDW * 100 + 0.5))/100; } +function char2width_(chr) { return (((chr * MDW + 5)/MDW*256))/256; } function cycle_width(collw) { return char2width(px2char(width2px(collw))); } -function find_mdw(collw, coll) { - if(cycle_width(collw) != collw) { - for(MDW=DEF_MDW; MDW>MIN_MDW; --MDW) if(cycle_width(collw) === collw) break; - if(MDW === MIN_MDW) for(MDW=DEF_MDW+1; MDW 0.5) guess--; + if(Math.abs(guess) < delta) { delta = Math.abs(guess); _MDW = MDW; } } + MDW = _MDW; +} + +function process_col(coll) { + if(coll.width) { + coll.wpx = width2px(coll.width); + coll.wch = px2char(coll.wpx); + coll.MDW = MDW; + } else if(coll.wpx) { + coll.wch = px2char(coll.wpx); + coll.width = char2width(coll.wch); + coll.MDW = MDW; + } + if(coll.customWidth) delete coll.customWidth; } /* [MS-EXSPXML3] 2.4.54 ST_enmPattern */ @@ -8499,14 +8539,10 @@ function parse_ws_xml_cols(columns, cols) { for(var coli = 0; coli != cols.length; ++coli) { var coll = parsexmltag(cols[coli], true); var colm=parseInt(coll.min, 10)-1, colM=parseInt(coll.max,10)-1; - delete coll.min; delete coll.max; - if(!seencol && coll.width) { seencol = true; find_mdw(+coll.width, coll); } - if(coll.width) { - coll.wpx = width2px(+coll.width); - coll.wch = px2char(coll.wpx); - coll.MDW = MDW; - } - while(colm <= colM) columns[colm++] = coll; + delete coll.min; delete coll.max; coll.width = +coll.width; + if(!seencol && coll.width) { seencol = true; find_mdw_colw(coll.width); } + process_col(coll); + while(colm <= colM) columns[colm++] = dup(coll); } } @@ -8517,7 +8553,9 @@ function write_ws_xml_cols(ws, cols) { var p = ({min:i+1,max:i+1}); /* wch (chars), wpx (pixels) */ width = -1; - if(col.wpx) width = px2char(col.wpx); + if(col.MDW) MDW = col.MDW; + if(col.width); + else if(col.wpx) width = px2char(col.wpx); else if(col.wch) width = col.wch; if(width > -1) { p.width = char2width(width); p.customWidth= 1; } o[o.length] = (writextag('col', null, p)); @@ -9021,6 +9059,10 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles) { for(var i = 0; i < wb.Names['!names'].length; ++i) supbooks[0][i+1] = wb.Names[wb.Names['!names'][i]]; + var colinfo = [], rowinfo = []; + var defwidth = 0, defheight = 0; // twips / MDW respectively + var seencol = false; + recordhopper(data, function ws_parse(val, Record) { if(end) return; switch(Record.n) { @@ -9108,6 +9150,16 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles) { s[encode_col(C) + rr].f = stringify_formula(val[1], refguess, {r:row.r, c:C}, supbooks, opts); break; + /* identical to 'ColInfo' in XLS */ + case 'BrtColInfo': { + if(!opts.cellStyles) break; + while(val.e >= val.s) { + colinfo[val.e--] = { width: val.w/256 }; + if(!seencol) { seencol = true; find_mdw_colw(val.w/256); } + process_col(colinfo[val.e+1]); + } + } break; + case 'BrtBeginSheet': break; case 'BrtWsProp': break; // TODO case 'BrtSheetCalcProp': break; // TODO @@ -9123,7 +9175,6 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles) { case 'BrtWsFmtInfoEx14': break; // TODO case 'BrtWsFmtInfo': break; // TODO case 'BrtBeginColInfos': break; // TODO - case 'BrtColInfo': break; // TODO case 'BrtEndColInfos': break; // TODO case 'BrtBeginSheetData': break; // TODO case 'BrtEndSheetData': break; // TODO @@ -9236,6 +9287,8 @@ function parse_ws_bin(data, opts, rels, wb, themes, styles) { } } if(mergecells.length > 0) s["!merges"] = mergecells; + if(colinfo.length > 0) s["!cols"] = colinfo; + if(rowinfo.length > 0) s["!rows"] = rowinfo; return s; } @@ -10066,8 +10119,9 @@ function parse_xlml_xml(d, opts) { var mergecells = []; var Props = {}, Custprops = {}, pidx = 0, cp = {}; var comments = [], comment = {}; - var cstys = [], csty; + var cstys = [], csty, seencol = false; var arrayf = []; + var rowinfo = []; xlmlregex.lastIndex = 0; str = str.replace(//mg,""); while((Rn = xlmlregex.exec(str))) switch(Rn[3]) { @@ -10128,6 +10182,8 @@ for(var cma = c; cma <= cc; ++cma) { sheetnames.push(sheetname); if(refguess.s.r <= refguess.e.r && refguess.s.c <= refguess.e.c) cursheet["!ref"] = encode_range(refguess); if(mergecells.length) cursheet["!merges"] = mergecells; + if(cstys.length > 0) cursheet["!cols"] = cstys; + if(rowinfo.length > 0) cursheet["!rows"] = rowinfo; sheets[sheetname] = cursheet; } else { refguess = {s: {r:2000000, c:2000000}, e: {r:0, c:0} }; @@ -10138,6 +10194,7 @@ for(var cma = c; cma <= cc; ++cma) { cursheet = {}; mergecells = []; arrayf = []; + rowinfo = []; } break; case 'Table': @@ -10146,7 +10203,7 @@ for(var cma = c; cma <= cc; ++cma) { else { table = xlml_parsexmltag(Rn[0]); state.push([Rn[3], false]); - cstys = []; + cstys = []; seencol = false; } break; @@ -10162,8 +10219,14 @@ for(var cma = c; cma <= cc; ++cma) { case 'Column': if(state[state.length-1][0] !== 'Table') break; csty = xlml_parsexmltag(Rn[0]); + csty.wpx = parseInt(csty.Width, 10); + if(!seencol && csty.wpx > 10) { + seencol = true; find_mdw_wpx(csty.wpx); + for(var _col = 0; _col < cstys.length; ++_col) if(cstys[_col]) process_col(cstys[_col]); + } + if(seencol) process_col(csty); cstys[(csty.Index-1||cstys.length)] = csty; - for(var i = 0; i < +csty.Span; ++i) cstys[cstys.length] = csty; + for(var i = 0; i < +csty.Span; ++i) cstys[cstys.length] = dup(csty); break; case 'NamedRange': break; @@ -10834,9 +10897,9 @@ function parse_workbook(blob, options) { if(icv < 64) return palette[icv-8] || XLSIcv[icv]; return XLSIcv[icv]; }; - var process_cell_style = function pcs(cell, line) { + var process_cell_style = function pcs(cell, line, options) { var xfd = line.XF.data; - if(!xfd || !xfd.patternType) return; + if(!xfd || !xfd.patternType || !options || !options.cellStyles) return; line.s = ({}); line.s.patternType = xfd.patternType; var t; @@ -10844,8 +10907,9 @@ function parse_workbook(blob, options) { if((t = rgb2Hex(get_rgb(xfd.icvBack)))) { line.s.bgColor = {rgb:t}; } }; var addcell = function addcell(cell, line, options) { + if(file_depth > 1) return; if(!cell_valid) return; - if(options.cellStyles && line.XF && line.XF.data) process_cell_style(cell, line); + if(options.cellStyles && line.XF && line.XF.data) process_cell_style(cell, line, options); lastcell = cell; last_cell = encode_cell(cell); if(range.s) { @@ -10883,11 +10947,15 @@ function parse_workbook(blob, options) { biff: 8, // BIFF version codepage: 0, // CP from CodePage record winlocked: 0, // fLockWn from WinProtect + cellStyles: !!options && !!options.cellStyles, WTF: !!options && !!options.wtf }); if(options.password) opts.password = options.password; var mergecells = []; var objects = []; + var colinfo = [], rowinfo = []; + var defwidth = 0, defheight = 0; // twips / MDW respectively + var seencol = false; var supbooks = ([[]]); // 1-indexed, will hold extern names var sbc = 0, sbci = 0, sbcli = 0; supbooks.SheetNames = opts.snames; @@ -10994,6 +11062,8 @@ function parse_workbook(blob, options) { } if(mergecells.length > 0) out["!merges"] = mergecells; if(objects.length > 0) out["!objects"] = objects; + if(colinfo.length > 0) out["!cols"] = colinfo; + if(rowinfo.length > 0) out["!rows"] = rowinfo; } if(cur_sheet === "") Preamble = out; else Sheets[cur_sheet] = out; out = {}; @@ -11022,6 +11092,9 @@ function parse_workbook(blob, options) { mergecells = []; objects = []; array_formulae = []; opts.arrayf = array_formulae; + colinfo = []; rowinfo = []; + defwidth = defheight = 0; + seencol = false; } break; case 'Number': case 'BIFF2NUM': case 'BIFF2INT': { @@ -11170,6 +11243,19 @@ function parse_workbook(blob, options) { case 'ClrtClient': break; case 'XFExt': update_xfext(XFs[val.ixfe], val.ext); break; + case 'DefColWidth': defwidth = val; break; + case 'DefaultRowHeight': defheight = val[1]; break; // TODO: flags + + case 'ColInfo': { + if(!opts.cellStyles) break; + while(val.e >= val.s) { + colinfo[val.e--] = { width: val.w/256 }; + if(!seencol) { seencol = true; find_mdw_colw(val.w/256); } + process_col(colinfo[val.e+1]); + } + } break; + case 'Row': break; // TODO + case 'NameCmt': break; case 'Header': break; // TODO case 'Footer': break; // TODO @@ -11177,11 +11263,8 @@ function parse_workbook(blob, options) { case 'VCenter': break; // TODO case 'Pls': break; // TODO case 'Setup': break; // TODO - case 'DefColWidth': break; // TODO case 'GCW': break; case 'LHRecord': break; - case 'ColInfo': break; // TODO - case 'Row': break; // TODO case 'DBCell': break; // TODO case 'EntExU2': break; // TODO case 'SxView': break; // TODO @@ -11199,7 +11282,7 @@ function parse_workbook(blob, options) { case 'Feature11': case 'Feature12': case 'List12': break; case 'Country': country = val; break; case 'RecalcId': break; - case 'DefaultRowHeight': case 'DxGCol': break; // TODO: htmlify + case 'DxGCol': break; // TODO: htmlify case 'Fbi': case 'Fbi2': case 'GelFrame': break; case 'Font': break; // TODO case 'XFCRC': break; // TODO @@ -11519,7 +11602,7 @@ var XLSBRecordEnum = { 0x0039: { n:"BrtEndMdxTuple", f:parsenoop }, 0x003A: { n:"BrtMdxMbrIstr", f:parsenoop }, 0x003B: { n:"BrtStr", f:parsenoop }, -0x003C: { n:"BrtColInfo", f:parsenoop }, +0x003C: { n:"BrtColInfo", f:parse_ColInfo }, 0x003E: { n:"BrtCellRString", f:parsenoop }, 0x003F: { n:"BrtCalcChainItem$", f:parse_BrtCalcChainItem$ }, 0x0040: { n:"BrtDVal", f:parsenoop },