Skip to content

Commit

Permalink
ODS read/write number formats
Browse files Browse the repository at this point in the history
  • Loading branch information
@SheetJSDev
SheetJSDev committed Jun 8, 2022
1 parent 4cc0412 commit 08f5678
Show file tree
Hide file tree
Showing 2 changed files with 432 additions and 35 deletions.
271 changes: 249 additions & 22 deletions bits/80_parseods.js
View file
Original file line number Diff line number Diff line change
Expand Up @@ -27,14 +27,236 @@ var number_formats_ods = {
quarter: ["\\Qm", "m\\\"th quarter\""]
};

/* Note: ODS can stick styles in content.xml or styles.xml, FODS blurs lines */
function parse_ods_styles(d/*:string*/, _opts, _nfm) {
var number_format_map = _nfm || {};
var str = xlml_normalize(d);
xlmlregex.lastIndex = 0;
str = str.replace(/<!--([\s\S]*?)-->/mg,"").replace(/<!DOCTYPE[^\[]*\[[^\]]*\]>/gm,"");
var Rn, NFtag, NF = "", tNF = "", y, etpos = 0, tidx = -1, infmt = false, payload = "";
while((Rn = xlmlregex.exec(str))) {
switch((Rn[3]=Rn[3].replace(/_.*$/,""))) {
/* Number Format Definitions */
case 'number-style': // <number:number-style> 16.29.2
case 'currency-style': // <number:currency-style> 16.29.8
case 'percentage-style': // <number:percentage-style> 16.29.10
case 'date-style': // <number:date-style> 16.29.11
case 'time-style': // <number:time-style> 16.29.19
case 'text-style': // <number:text-style> 16.29.26
if(Rn[1]==='/') {
infmt = false;
if(NFtag['truncate-on-overflow'] == "false") {
if(NF.match(/h/)) NF = NF.replace(/h+/, "[$&]");
else if(NF.match(/m/)) NF = NF.replace(/m+/, "[$&]");
else if(NF.match(/s/)) NF = NF.replace(/s+/, "[$&]");
}
number_format_map[NFtag.name] = NF;
NF = "";
} else if(Rn[0].charAt(Rn[0].length-2) !== '/') {
infmt = true;
NF = "";
NFtag = parsexmltag(Rn[0], false);
} break;

// LibreOffice bug https://bugs.documentfoundation.org/show_bug.cgi?id=149484
case 'boolean-style': // <number:boolean-style> 16.29.24
if(Rn[1]==='/') {
infmt = false;
number_format_map[NFtag.name] = "General";
NF = "";
} else if(Rn[0].charAt(Rn[0].length-2) !== '/') {
infmt = true;
NF = "";
NFtag = parsexmltag(Rn[0], false);
} break;

/* Number Format Elements */
case 'boolean': // <number:boolean> 16.29.25
NF += "General"; // ODF spec is unfortunately underspecified here
break;

case 'text': // <number:text> 16.29.27
if(Rn[1]==='/') {
payload = str.slice(tidx, xlmlregex.lastIndex - Rn[0].length);
// NOTE: Excel has a different interpretation of "%%" and friends
if(payload == "%" && NFtag[0] == '<number:percentage-style') NF += "%";
else NF += '"' + payload.replace(/"/g, '""') + '"';
} else if(Rn[0].charAt(Rn[0].length-2) !== '/') {
tidx = xlmlregex.lastIndex;
} break;


case 'day': { // <number:day> 16.29.12
y = parsexmltag(Rn[0], false);
switch(y["style"]) {
case "short": NF += "d"; break;
case "long": NF += "dd"; break;
default: NF += "dd"; break; // TODO: error condition
}
} break;

case 'day-of-week': { // <number:day-of-week> 16.29.16
y = parsexmltag(Rn[0], false);
switch(y["style"]) {
case "short": NF += "ddd"; break;
case "long": NF += "dddd"; break;
default: NF += "ddd"; break;
}
} break;

case 'era': { // <number:era> 16.29.15 TODO: proper mapping
y = parsexmltag(Rn[0], false);
switch(y["style"]) {
case "short": NF += "ee"; break;
case "long": NF += "eeee"; break;
default: NF += "eeee"; break; // TODO: error condition
}
} break;

case 'hours': { // <number:hours> 16.29.20
y = parsexmltag(Rn[0], false);
switch(y["style"]) {
case "short": NF += "h"; break;
case "long": NF += "hh"; break;
default: NF += "hh"; break; // TODO: error condition
}
} break;

case 'minutes': { // <number:minutes> 16.29.21
y = parsexmltag(Rn[0], false);
switch(y["style"]) {
case "short": NF += "m"; break;
case "long": NF += "mm"; break;
default: NF += "mm"; break; // TODO: error condition
}
} break;

case 'month': { // <number:month> 16.29.13
y = parsexmltag(Rn[0], false);
if(y["textual"]) NF += "mm";
switch(y["style"]) {
case "short": NF += "m"; break;
case "long": NF += "mm"; break;
default: NF += "m"; break;
}
} break;

case 'seconds': { // <number:seconds> 16.29.22
y = parsexmltag(Rn[0], false);
switch(y["style"]) {
case "short": NF += "s"; break;
case "long": NF += "ss"; break;
default: NF += "ss"; break; // TODO: error condition
}
if(y["decimal-places"]) NF += "." + fill("0", +y["decimal-places"]);
} break;

case 'year': { // <number:year> 16.29.14
y = parsexmltag(Rn[0], false);
switch(y["style"]) {
case "short": NF += "yy"; break;
case "long": NF += "yyyy"; break;
default: NF += "yy"; break; // TODO: error condition
}
} break;

case 'am-pm': // <number:am-pm> 16.29.23
NF += "AM/PM"; // LO autocorrects A/P -> AM/PM
break;

case 'week-of-year': // <number:week-of-year> 16.29.17
case 'quarter': // <number:quarter> 16.29.18
console.error("Excel does not support ODS format token " + Rn[3]);
break;

case 'fill-character': // <number:fill-character> 16.29.5
if(Rn[1]==='/') {
payload = str.slice(tidx, xlmlregex.lastIndex - Rn[0].length);
// NOTE: Excel has a different interpretation of "%%" and friends
NF += '"' + payload.replace(/"/g, '""') + '"*';
} else if(Rn[0].charAt(Rn[0].length-2) !== '/') {
tidx = xlmlregex.lastIndex;
} break;

case 'scientific-number': // <number:scientific-number> 16.29.6
// TODO: find a mapping for all parameters
y = parsexmltag(Rn[0], false);
NF += "0." + fill("0", +y["min-decimal-places"] || +y["decimal-places"] || 2) + fill("?", +y["decimal-places"] - +y["min-decimal-places"] || 0) + "E" + (parsexmlbool(y["forced-exponent-sign"]) ? "+" : "") + fill("0", +y["min-exponent-digits"] || 2);
break;

case 'fraction': // <number:fraction> 16.29.7
// TODO: find a mapping for all parameters
y = parsexmltag(Rn[0], false);
if(!+y["min-integer-digits"]) NF += "#";
else NF += fill("0", +y["min-integer-digits"]);
NF += " ";
NF += fill("?", +y["min-numerator-digits"] || 1);
NF += "/";
if(+y["denominator-value"]) NF += y["denominator-value"];
else NF += fill("?", +y["min-denominator-digits"] || 1);
break;

case 'currency-symbol': // <number:currency-symbol> 16.29.9
// TODO: localization with [$-...]
if(Rn[1]==='/') {
NF += '"' + str.slice(tidx, xlmlregex.lastIndex - Rn[0].length).replace(/"/g, '""') + '"';
} else if(Rn[0].charAt(Rn[0].length-2) !== '/') {
tidx = xlmlregex.lastIndex;
} else NF += "$";
break;

case 'text-properties': // <style:text-properties> 16.29.29
y = parsexmltag(Rn[0], false);
switch((y["color"]||"").toLowerCase().replace("#", "")) {
case "ff0000": case "red": NF = "[Red]" + NF; break;
}
break;

case 'text-content': // <number:text-content> 16.29.28
NF += "@";
break;

case 'map': // <style:map> 16.3
// TODO: handle more complex maps
y = parsexmltag(Rn[0], false);
if(unescapexml(y["condition"]) == "value()>=0") NF = number_format_map[y["apply-style-name"]] + ";" + NF;
else console.error("ODS number format may be incorrect: " + y["condition"]);
break;

case 'number': // <number:number> 16.29.3
// TODO: handle all the attributes
if(Rn[1]==='/') break;
y = parsexmltag(Rn[0], false);
tNF = "";
tNF += fill("0", +y["min-integer-digits"] || 1);
if(parsexmlbool(y["grouping"])) tNF = commaify(fill("#", Math.max(0, 4 - tNF.length)) + tNF);
if(+y["min-decimal-places"] || +y["decimal-places"]) tNF += ".";
if(+y["min-decimal-places"]) tNF += fill("0", +y["min-decimal-places"] || 1);
if(+y["decimal-places"] - (+y["min-decimal-places"]||0)) tNF += fill("#", +y["decimal-places"] - (+y["min-decimal-places"]||0));
NF += tNF;
break;

case 'embedded-text': // <number:embedded-text> 16.29.4
// TODO: verify interplay with grouping et al
if(Rn[1]==='/') {
if(etpos == 0) NF += '"' + str.slice(tidx, xlmlregex.lastIndex - Rn[0].length).replace(/"/g, '""') + '"';
else NF = NF.slice(0, etpos) + '"' + str.slice(tidx, xlmlregex.lastIndex - Rn[0].length).replace(/"/g, '""') + '"' + NF.slice(etpos);
} else if(Rn[0].charAt(Rn[0].length-2) !== '/') {
tidx = xlmlregex.lastIndex;
etpos = -+parsexmltag(Rn[0], false)["position"] || 0;
} break;

}}
return number_format_map;
}

function parse_content_xml(d/*:string*/, _opts)/*:Workbook*/ {
function parse_content_xml(d/*:string*/, _opts, _nfm)/*:Workbook*/ {
var opts = _opts || {};
if(DENSE != null && opts.dense == null) opts.dense = DENSE;
var str = xlml_normalize(d);
var state/*:Array<any>*/ = [], tmp;
var tag/*:: = {}*/;
var NFtag = {name:""}, NF = "", pidx = 0;
var nfidx, NF = "", pidx = 0;
var sheetag/*:: = {name:"", '名称':""}*/;
var rowtag/*:: = {'行号':""}*/;
var Sheets = {}, SheetNames/*:Array<string>*/ = [];
Expand All @@ -45,7 +267,7 @@ function parse_content_xml(d/*:string*/, _opts)/*:Workbook*/ {
var textR = [];
var R = -1, C = -1, range = {s: {r:1000000,c:10000000}, e: {r:0, c:0}};
var row_ol = 0;
var number_format_map = {};
var number_format_map = _nfm || {}, styles = {};
var merges/*:Array<Range>*/ = [], mrange = {}, mR = 0, mC = 0;
var rowinfo/*:Array<RowInfo>*/ = [], rowpeat = 1, colpeat = 1;
var arrayf/*:Array<[Range, string]>*/ = [];
Expand All @@ -56,7 +278,7 @@ function parse_content_xml(d/*:string*/, _opts)/*:Workbook*/ {
var creator = "", creatoridx = 0;
var isstub = false, intable = false;
var i = 0;
var baddate = 1;
var baddate = 0;
xlmlregex.lastIndex = 0;
str = str.replace(/<!--([\s\S]*?)-->/mg,"").replace(/<!DOCTYPE[^\[]*\[[^\]]*\]>/gm,"");
while((Rn = xlmlregex.exec(str))) switch((Rn[3]=Rn[3].replace(/_.*$/,""))) {
Expand Down Expand Up @@ -114,6 +336,7 @@ function parse_content_xml(d/*:string*/, _opts)/*:Workbook*/ {
colpeat = parseInt(ctag['number-columns-repeated']||"1", 10);
q = ({t:'z', v:null/*:: , z:null, w:"",c:[]*/}/*:any*/);
if(ctag.formula && opts.cellFormula != false) q.f = ods_to_csf_formula(unescapexml(ctag.formula));
if(ctag["style-name"] && styles[ctag["style-name"]]) q.z = styles[ctag["style-name"]];
if((ctag['数据类型'] || ctag['value-type']) == "string") {
q.t = "s"; q.v = unescapexml(ctag['string-value'] || "");
if(opts.dense) {
Expand All @@ -136,6 +359,7 @@ function parse_content_xml(d/*:string*/, _opts)/*:Workbook*/ {
ctag = parsexmltag(Rn[0], false);
comments = []; comment = ({}/*:any*/);
q = ({t:ctag['数据类型'] || ctag['value-type'], v:null/*:: , z:null, w:"",c:[]*/}/*:any*/);
if(ctag["style-name"] && styles[ctag["style-name"]]) q.z = styles[ctag["style-name"]];
if(opts.cellFormula) {
if(ctag.formula) ctag.formula = unescapexml(ctag.formula);
if(ctag['number-matrix-columns-spanned'] && ctag['number-matrix-rows-spanned']) {
Expand Down Expand Up @@ -163,16 +387,16 @@ function parse_content_xml(d/*:string*/, _opts)/*:Workbook*/ {

/* 19.385 office:value-type */
switch(q.t) {
case 'boolean': q.t = 'b'; q.v = parsexmlbool(ctag['boolean-value']); break;
case 'boolean': q.t = 'b'; q.v = parsexmlbool(ctag['boolean-value']) || (+ctag['boolean-value'] >= 1); break;
case 'float': q.t = 'n'; q.v = parseFloat(ctag.value); break;
case 'percentage': q.t = 'n'; q.v = parseFloat(ctag.value); break;
case 'currency': q.t = 'n'; q.v = parseFloat(ctag.value); break;
case 'date': q.t = 'd'; q.v = parseDate(ctag['date-value']);
if(!opts.cellDates) { q.t = 'n'; q.v = datenum(q.v, WB.WBProps.date1904) - baddate; }
q.z = 'm/d/yy'; break;
if(!q.z) q.z = 'm/d/yy'; break;
case 'time': q.t = 'n'; q.v = parse_isodur(ctag['time-value'])/86400;
if(opts.cellDates) { q.t = 'd'; q.v = numdate(q.v); }
q.z = 'HH:MM:SS'; break;
if(!q.z) q.z = 'HH:MM:SS'; break;
case 'number': q.t = 'n'; q.v = parseFloat(ctag['数据数值']); break;
default:
if(q.t === 'string' || q.t === 'text' || !q.t) {
Expand Down Expand Up @@ -267,23 +491,24 @@ function parse_content_xml(d/*:string*/, _opts)/*:Workbook*/ {
textp = ""; textpidx = 0; textR = [];
break;

case 'scientific-number': // TODO: <number:scientific-number>
break;
case 'currency-symbol': // TODO: <number:currency-symbol>
break;
case 'currency-style': // TODO: <number:currency-style>
case 'scientific-number': // <number:scientific-number>
case 'currency-symbol': // <number:currency-symbol>
case 'fill-character': // 16.29.5 <number:fill-character>
break;

case 'text-style': // 16.27.25 <number:text-style>
case 'boolean-style': // 16.27.23 <number:boolean-style>
case 'number-style': // 16.27.2 <number:number-style>
case 'currency-style': // 16.29.8 <number:currency-style>
case 'percentage-style': // 16.27.9 <number:percentage-style>
case 'date-style': // 16.27.10 <number:date-style>
case 'time-style': // 16.27.18 <number:time-style>
if(Rn[1]==='/'){
number_format_map[NFtag.name] = NF;
if((tmp=state.pop())[0]!==Rn[3]) throw "Bad state: "+tmp;
var xlmlidx = xlmlregex.lastIndex;
parse_ods_styles(str.slice(nfidx, xlmlregex.lastIndex), _opts, number_format_map);
xlmlregex.lastIndex = xlmlidx;
} else if(Rn[0].charAt(Rn[0].length-2) !== '/') {
NF = "";
NFtag = parsexmltag(Rn[0], false);
state.push([Rn[3], true]);
nfidx = xlmlregex.lastIndex - Rn[0].length;
} break;

case 'script': break; // 3.13 <office:script>
Expand All @@ -292,8 +517,10 @@ function parse_content_xml(d/*:string*/, _opts)/*:Workbook*/ {

case 'default-style': // TODO: <style:default-style>
case 'page-layout': break; // TODO: <style:page-layout>
case 'style': // 16.2 <style:style>
break;
case 'style': { // 16.2 <style:style>
var styletag = parsexmltag(Rn[0], false);
if(styletag["family"] == "table-cell" && number_format_map[styletag["data-style-name"]]) styles[styletag["name"]] = number_format_map[styletag["data-style-name"]];
} break;
case 'map': break; // 16.3 <style:map>
case 'font-face': break; // 16.21 <style:font-face>

Expand Down Expand Up @@ -331,9 +558,7 @@ function parse_content_xml(d/*:string*/, _opts)/*:Workbook*/ {
NF += number_formats_ods[Rn[3]][tag.style==='long'?1:0]; break;
} break;

case 'boolean-style': break; // 16.27.23 <number:boolean-style>
case 'boolean': break; // 16.27.24 <number:boolean>
case 'text-style': break; // 16.27.25 <number:text-style>
case 'text': // 16.27.26 <number:text>
if(Rn[0].slice(-2) === "/>") break;
else if(Rn[1]==="/") switch(state[state.length-1][0]) {
Expand Down Expand Up @@ -564,9 +789,11 @@ function parse_content_xml(d/*:string*/, _opts)/*:Workbook*/ {
function parse_ods(zip/*:ZIPFile*/, opts/*:?ParseOpts*/)/*:Workbook*/ {
opts = opts || ({}/*:any*/);
if(safegetzipfile(zip, 'META-INF/manifest.xml')) parse_manifest(getzipdata(zip, 'META-INF/manifest.xml'), opts);
var styles = getzipstr(zip, 'styles.xml');
var Styles = styles && parse_ods_styles(utf8read(styles), opts);
var content = getzipstr(zip, 'content.xml');
if(!content) throw new Error("Missing content.xml in ODS / UOF file");
var wb = parse_content_xml(utf8read(content), opts);
var wb = parse_content_xml(utf8read(content), opts, Styles);
if(safegetzipfile(zip, 'meta.xml')) wb.Props = parse_core_props(getzipdata(zip, 'meta.xml'));
return wb;
}
Expand Down
Loading

0 comments on commit 08f5678

Please sign in to comment.