diff --git a/README.md b/README.md
index 142a20a..c934e6f 100644
--- a/README.md
+++ b/README.md
@@ -29,8 +29,10 @@ with a unified JS representation, and ES3/ES5 browser compatibility back to IE6.
* [Optional Modules](#optional-modules)
* [ECMAScript 5 Compatibility](#ecmascript-5-compatibility)
- [Parsing Workbooks](#parsing-workbooks)
+ * [Note on Streaming Read](#note-on-streaming-read)
- [Working with the Workbook](#working-with-the-workbook)
- [Writing Workbooks](#writing-workbooks)
+ * [Streaming Write](#streaming-write)
- [Interface](#interface)
* [Parsing functions](#parsing-functions)
* [Writing functions](#writing-functions)
@@ -298,6 +300,39 @@ function handleFile(e) {
input_dom_element.addEventListener('change', handleFile, false);
```
+**Complete examples:**
+
+- 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
+
+### Note on Streaming Read
+
+The most common and interesting formats (XLS, XLSX/M, XLSB, ODS) are ultimately
+ZIP or CFB containers of files. Neither format puts the directory structure at
+the beginning of the file: ZIP files place the Central Directory records at the
+end of the logical file, while CFB files can place the FAT structure anywhere in
+the file! As a result, to properly handle these formats, a streaming function
+would have to buffer the entire file before commencing. That belies the
+expectations of streaming, so we do not provide any streaming read API. If you
+really want to stream, there are node modules like `concat-stream` that will do
+the buffering for you.
+
## Working with the Workbook
The full object format is described later in this README.
@@ -320,25 +355,6 @@ var desired_value = (desired_cell ? desired_cell.v : undefined);
**Complete examples:**
-- 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
@@ -392,6 +408,12 @@ saveAs(new Blob([s2ab(wbout)],{type:"application/octet-stream"}), "test.xlsx");
- writing an array of arrays in nodejs
- exporting an HTML table
+### Streaming Write
+
+`XLSX.stream.to_csv` is the streaming version of `XLSX.utils.sheet_to_csv`. It
+takes the same arguments but returns a readable stream.
+
+ pipes CSV write stream to nodejs response.
## Interface
`XLSX` is the exposed variable in the browser and the exported node variable
@@ -769,7 +791,7 @@ 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`:
+first cell specifies the formula. Consider `D1:D3=A1:A3*B1:B3`:
```js
worksheet['D1'] = { t:'n', F:"D1:D3", f:"A1:A3*B1:B3" };
@@ -977,7 +999,8 @@ Plaintext format guessing follows the priority order:
| Format | Test |
|:-------|:--------------------------------------------------------------------|
-| XML | starts with < |
+| HTML | starts with \\/]+)=((?:")([^"]*)(?:")|(?:')([^']*)(?:'))/g;
+var attregexg=/([^"\s?>\/]+)=((?:")([^"]*)(?:")|(?:')([^']*)(?:')|([^'">\s]+))/g;
var tagregex=/<[^>]*>/g;
var nsregex=/<\w*:/, nsregex2 = /<(\/?)\w+:/;
function parsexmltag(tag/*:string*/, skip_root/*:?boolean*/)/*:any*/ {
@@ -7,11 +7,13 @@ function parsexmltag(tag/*:string*/, skip_root/*:?boolean*/)/*:any*/ {
for(; eq !== tag.length; ++eq) if((c = tag.charCodeAt(eq)) === 32 || c === 10 || c === 13) break;
if(!skip_root) z[0] = tag.substr(0, eq);
if(eq === tag.length) return z;
- var m = tag.match(attregexg), j=0, v="", i=0, q="", cc="";
+ var m = tag.match(attregexg), j=0, v="", i=0, q="", cc="", quot = 1;
if(m) for(i = 0; i != m.length; ++i) {
cc = m[i];
for(c=0; c != cc.length; ++c) if(cc.charCodeAt(c) === 61) break;
- q = cc.substr(0,c); v = cc.substring(c+2, cc.length-1);
+ q = cc.substr(0,c);
+ quot = ((eq=cc.charCodeAt(c+1)) == 34 || eq == 39) ? 1 : 0;
+ v = cc.substring(c+1+quot, cc.length-quot);
for(j=0;j!=q.length;++j) if(q.charCodeAt(j) === 58) break;
if(j===q.length) {
if(q.indexOf("_") > 0) q = q.substr(0, q.indexOf("_")); // from ods
@@ -54,9 +56,10 @@ function escapexml(text/*:string*/, xml/*:?boolean*/)/*:string*/{
}
function escapexmltag(text/*:string*/)/*:string*/{ return escapexml(text).replace(/ /g,"_x0020_"); }
+var htmlcharegex = /[\u0000-\u001f]/g;
function escapehtml(text){
var s = text + '';
- return s.replace(decregex, function(y) { return rencoding[y]; });
+ return s.replace(decregex, function(y) { return rencoding[y]; }).replace(htmlcharegex,function(s) { return "&#x" + ("000"+s.charCodeAt(0).toString(16)).slice(-4) + ";"; });
}
/* TODO: handle codepages */
diff --git a/bits/41_lotus.js b/bits/41_lotus.js
index 1bf7f5b..8b66deb 100644
--- a/bits/41_lotus.js
+++ b/bits/41_lotus.js
@@ -28,7 +28,7 @@ var WK_ = (function() {
if(!d) return d;
var o = opts || {};
if(DENSE != null && o.dense == null) o.dense = DENSE;
- var s = (o.dense ? [] : {}), n = "Sheet1", sidx = 0;
+ var s/*:Worksheet*/ = ((o.dense ? [] : {})/*:any*/), n = "Sheet1", sidx = 0;
var sheets = {}, snames = [n];
var refguess = {s: {r:0, c:0}, e: {r:0, c:0} };
diff --git a/bits/43_sstbin.js b/bits/43_sstbin.js
index a084bea..9d158ac 100644
--- a/bits/43_sstbin.js
+++ b/bits/43_sstbin.js
@@ -22,8 +22,8 @@ function parse_sst_bin(data, opts)/*:SST*/ {
pass = false; break;
default:
- if(R_n.indexOf("Begin") > 0) state.push(R_n);
- else if(R_n.indexOf("End") > 0) state.pop();
+ if(R_n.indexOf("Begin") > 0){}
+ else if(R_n.indexOf("End") > 0){}
if(!pass || opts.WTF) throw new Error("Unexpected record " + RT + " " + R_n);
}
});
diff --git a/bits/61_fcommon.js b/bits/61_fcommon.js
index 1694626..a23bb9a 100644
--- a/bits/61_fcommon.js
+++ b/bits/61_fcommon.js
@@ -1,7 +1,7 @@
/* TODO: it will be useful to parse the function str */
var rc_to_a1 = (function(){
var rcregex = /(^|[^A-Za-z])R(\[?)(-?\d+|)\]?C(\[?)(-?\d+|)\]?/g;
- var rcbase;
+ var rcbase/*:Cell*/ = ({r:0,c:0}/*:any*/);
function rcfunc($$,$1,$2,$3,$4,$5) {
var R = $3.length>0?parseInt($3,10)|0:0, C = $5.length>0?parseInt($5,10)|0:0;
if(C<0 && $4.length === 0) C=0;
@@ -10,7 +10,7 @@ var rc_to_a1 = (function(){
if($2.length > 0 || $3.length == 0) rRel = true; if(rRel) R += rcbase.r; else --R;
return $1 + (cRel ? "" : "$") + encode_col(C) + (rRel ? "" : "$") + encode_row(R);
}
- return function rc_to_a1(fstr, base) {
+ return function rc_to_a1(fstr/*:string*/, base/*:Cell*/)/*:string*/ {
rcbase = base;
return fstr.replace(rcregex, rcfunc);
};
diff --git a/bits/72_wbxml.js b/bits/72_wbxml.js
index b08a69e..a45302b 100644
--- a/bits/72_wbxml.js
+++ b/bits/72_wbxml.js
@@ -160,6 +160,8 @@ function write_wb_xml(wb/*:Workbook*/, opts/*:?WriteOpts*/)/*:string*/ {
var o = [XML_HEADER];
o[o.length] = WB_XML_ROOT;
+ var write_names = (wb.Workbook && (wb.Workbook.Names||[]).length > 0);
+
/* fileVersion */
/* fileSharing */
@@ -185,9 +187,9 @@ function write_wb_xml(wb/*:Workbook*/, opts/*:?WriteOpts*/)/*:string*/ {
/* functionGroups */
/* externalReferences */
- if(wb.Workbook && (wb.Workbook.Names||[]).length > 0) {
+ if(write_names) {
o[o.length] = "";
- wb.Workbook.Names.forEach(function(n) {
+ if(wb.Workbook && wb.Workbook.Names) wb.Workbook.Names.forEach(function(n) {
var d = {name:n.Name};
if(n.Comment) d.comment = n.Comment;
if(n.Sheet != null) d.localSheetId = ""+n.Sheet;
diff --git a/bits/75_xlml.js b/bits/75_xlml.js
index eef9ed5..c91a228 100644
--- a/bits/75_xlml.js
+++ b/bits/75_xlml.js
@@ -171,7 +171,7 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ {
make_ssf(SSF);
var str = debom(xlml_normalize(d));
if(opts && opts.type == 'binary' && typeof cptable !== 'undefined') str = cptable.utils.decode(65001, char_codes(str));
- if(str.substr(0,1000).indexOf("= 0) return parse_html(str, opts);
+ if(str.substr(0,1000).indexOf("= 0) return HTML_.to_workbook(str, opts);
var Rn;
var state = [], tmp;
if(DENSE != null && opts.dense == null) opts.dense = DENSE;
diff --git a/bits/79_html.js b/bits/79_html.js
index 428b51c..3c48b89 100644
--- a/bits/79_html.js
+++ b/bits/79_html.js
@@ -1,46 +1,93 @@
/* TODO: in browser attach to DOM; in node use an html parser */
-function parse_html(str/*:string*/, _opts)/*:Workbook*/ {
- var opts = _opts || {};
- if(DENSE != null && opts.dense == null) opts.dense = DENSE;
- var ws/*:Worksheet*/ = opts.dense ? ([]/*:any*/) : ({}/*:any*/);
- var o/*:Workbook*/ = { SheetNames: ["Sheet1"], Sheets: {Sheet1:ws} };
- var i = str.indexOf(" / pair");
- var rows = str.slice(i, j).split(/]*>/);
- var R = 0, C = 0;
- var range = {s:{r:10000000, c:10000000},e:{r:0,c:0}};
- for(i = 0; i < rows.length; ++i) {
- if(rows[i].substr(0,3) != "");
- for(j = 0; j < cells.length; ++j) {
- if(cells[j].substr(0,3) != "")) > -1) m = m.slice(cc+1);
- while(m.indexOf(">") > -1) m = m.slice(0, m.lastIndexOf("<"));
- /* TODO: generate stub cells */
- if(!m.length) continue;
- if(range.s.r > R) range.s.r = R;
- if(range.e.r < R) range.e.r = R;
- if(range.s.c > C) range.s.c = C;
- if(range.e.c < C) range.e.c = C;
- if(opts.dense) {
- if(!ws[R]) ws[R] = [];
- if(Number(m) == Number(m)) ws[R][C] = {t:'n', v:+m};
- else ws[R][C] = {t:'s', v:m};
- } else {
- var coord/*:string*/ = encode_cell({r:R, c:C});
- /* TODO: value parsing */
- if(Number(m) == Number(m)) ws[coord] = {t:'n', v:+m};
- else ws[coord] = {t:'s', v:m};
+var HTML_ = (function() {
+ function html_to_sheet(str/*:string*/, _opts)/*:Workbook*/ {
+ var opts = _opts || {};
+ if(DENSE != null && opts.dense == null) opts.dense = DENSE;
+ var ws/*:Worksheet*/ = opts.dense ? ([]/*:any*/) : ({}/*:any*/);
+ var i = str.indexOf(" / pair");
+ var rows = str.slice(i, j).split(/(:?]*>)/);
+ var R = -1, C = 0, RS = 0, CS = 0;
+ var range = {s:{r:10000000, c:10000000},e:{r:0,c:0}};
+ var merges = [], midx = 0;
+ for(i = 0; i < rows.length; ++i) {
+ var row = rows[i].trim();
+ if(row.substr(0,3) == "");
+ for(j = 0; j < cells.length; ++j) {
+ var cell = cells[j].trim();
+ if(cell.substr(0,3) != "")) > -1) m = m.slice(cc+1);
+ while(m.indexOf(">") > -1) m = m.slice(0, m.lastIndexOf("<"));
+ var tag = parsexmltag(cell.slice(0, cell.indexOf(">")));
+ CS = tag.colspan ? +tag.colspan : 1;
+ if((RS = +tag.rowspan)>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
+ /* TODO: generate stub cells */
+ if(!m.length) { C += CS; continue; }
+ m = unescapexml(m).replace(/[\r\n]/g,"");
+ if(range.s.r > R) range.s.r = R;
+ if(range.e.r < R) range.e.r = R;
+ if(range.s.c > C) range.s.c = C;
+ if(range.e.c < C) range.e.c = C;
+ if(opts.dense) {
+ if(!ws[R]) ws[R] = [];
+ if(Number(m) == Number(m)) ws[R][C] = {t:'n', v:+m};
+ else ws[R][C] = {t:'s', v:m};
+ } else {
+ var coord/*:string*/ = encode_cell({r:R, c:C});
+ /* TODO: value parsing */
+ if(Number(m) == Number(m)) ws[coord] = {t:'n', v:+m};
+ else ws[coord] = {t:'s', v:m};
+ }
+ C += CS;
}
}
- ++R; C = 0;
+ ws['!ref'] = encode_range(range);
+ return ws;
}
- ws['!ref'] = encode_range(range);
- return o;
-}
+ function html_to_book(str/*:string*/, opts)/*:Workbook*/ {
+ return sheet_to_workbook(html_to_sheet(str, opts), opts);
+ }
+ function sheet_to_html(ws/*:Worksheet*/, opts)/*:string*/ {
+ var o/*:Array*/ = [];
+ var r = decode_range(ws['!ref']), cell/*:Cell*/;
+ var dense = Array.isArray(ws);
+ var M = (ws['!merges'] ||[]);
+ for(var R = r.s.r; R <= r.e.r; ++R) {
+ var oo = [];
+ for(var C = r.s.c; C <= r.e.c; ++C) {
+ var RS = 0, CS = 0;
+ for(var j = 0; j < M.length; ++j) {
+ if(M[j].s.r > R || M[j].s.c > C) continue;
+ if(M[j].e.r < R || M[j].e.c < C) continue;
+ if(M[j].s.r < R || M[j].s.c < C) { RS = -1; break; }
+ RS = M[j].e.r - M[j].s.r + 1; CS = M[j].e.c - M[j].s.c + 1; break;
+ }
+ if(RS < 0) continue;
+ var coord = encode_cell({r:R,c:C});
+ cell = dense ? (ws[R]||[])[C] : ws[coord];
+ if(!cell || cell.v == null) { oo.push(" | "); continue; }
+ /* TODO: html entities */
+ var w = cell.h || escapexml(cell.w || (format_cell(cell), cell.w) || "");
+ var sp = {};
+ if(RS > 1) sp.rowspan = RS;
+ if(CS > 1) sp.colspan = CS;
+ oo.push(writextag('td', w, sp));
+ }
+ o.push("" + oo.join("") + "
");
+ }
+ return "";
+ }
+
+ return {
+ to_workbook: html_to_book,
+ to_sheet: html_to_sheet,
+ from_sheet: sheet_to_html
+ };
+})();
function parse_dom_table(table/*:HTMLElement*/, _opts/*:?any*/)/*:Worksheet*/ {
var opts = _opts || {};
@@ -61,7 +108,7 @@ function parse_dom_table(table/*:HTMLElement*/, _opts/*:?any*/)/*:Worksheet*/ {
}
/* TODO: figure out how to extract nonstandard mso- style */
CS = +elt.getAttribute("colspan") || 1;
- if((RS = +elt.getAttribute("rowspan"))>0) merges.push({s:{r:R,c:C},e:{r:R + RS - 1, c:C + CS - 1}});
+ if((RS = +elt.getAttribute("rowspan"))>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
var o = {t:'s', v:v};
if(v != null && v.length && !isNaN(Number(v))) o = {t:'n', v:Number(v)};
if(opts.dense) { if(!ws[R]) ws[R] = []; ws[R][C] = o; }
diff --git a/bits/82_sheeter.js b/bits/82_sheeter.js
index ba8e6f0..ab908ea 100644
--- a/bits/82_sheeter.js
+++ b/bits/82_sheeter.js
@@ -8,6 +8,7 @@ function write_obj_str(factory/*:WriteObjStrFactory*/) {
};
}
+var write_htm_str = write_obj_str(HTML_);
var write_csv_str = write_obj_str({from_sheet:sheet_to_csv});
var write_slk_str = write_obj_str(SYLK);
var write_dif_str = write_obj_str(DIF);
diff --git a/bits/88_write.js b/bits/88_write.js
index ab5561d..0423f5c 100644
--- a/bits/88_write.js
+++ b/bits/88_write.js
@@ -64,6 +64,7 @@ function writeSync(wb/*:Workbook*/, opts/*:?WriteOpts*/) {
case 'xlml': return write_string_type(write_xlml(wb, o), o);
case 'slk':
case 'sylk': return write_string_type(write_slk_str(wb, o), o);
+ case 'html': return write_string_type(write_htm_str(wb, o), o);
case 'txt': return write_bstr_type(write_txt_str(wb, o), o);
case 'csv': return write_string_type(write_csv_str(wb, o), o);
case 'dif': return write_string_type(write_dif_str(wb, o), o);
@@ -86,6 +87,7 @@ function resolve_book_type(o/*?WriteFileOpts*/) {
case '.fods': o.bookType = 'fods'; break;
case '.xlml': o.bookType = 'xlml'; break;
case '.sylk': o.bookType = 'sylk'; break;
+ case '.html': o.bookType = 'html'; break;
case '.xls': o.bookType = 'biff2'; break;
case '.xml': o.bookType = 'xml'; break;
case '.ods': o.bookType = 'ods'; break;
@@ -94,6 +96,7 @@ function resolve_book_type(o/*?WriteFileOpts*/) {
case '.dif': o.bookType = 'dif'; break;
case '.prn': o.bookType = 'prn'; break;
case '.slk': o.bookType = 'sylk'; break;
+ case '.htm': o.bookType = 'html'; break;
}
}
diff --git a/bits/90_utils.js b/bits/90_utils.js
index 0c50d26..fd6d84f 100644
--- a/bits/90_utils.js
+++ b/bits/90_utils.js
@@ -154,42 +154,47 @@ function sheet_to_json(sheet/*:Worksheet*/, opts/*:?Sheet2JSONOpts*/){
return out;
}
-function sheet_to_csv(sheet/*:Worksheet*/, opts/*:?Sheet2CSVOpts*/) {
- var out = "", txt = "", qreg = /"/g;
+var qreg = /"/g;
+function make_csv_row(sheet/*:Worksheet*/, r/*:Range*/, R/*:number*/, cols/*:Array*/, fs/*:number*/, rs/*:number*/, FS/*:string*/, o/*:Sheet2CSVOpts*/)/*:?string*/ {
+ var isempty = true;
+ var row = "", txt = "", rr = encode_row(R);
+ for(var C = r.s.c; C <= r.e.c; ++C) {
+ var val = o.dense ? (sheet[R]||[])[C]: sheet[cols[C] + rr];
+ if(val == null) txt = "";
+ else if(val.v != null) {
+ isempty = false;
+ txt = ''+format_cell(val, null, o);
+ for(var i = 0, cc = 0; i !== txt.length; ++i) if((cc = txt.charCodeAt(i)) === fs || cc === rs || cc === 34) {
+ txt = "\"" + txt.replace(qreg, '""') + "\""; break; }
+ } else if(val.f != null && !val.F) {
+ isempty = false;
+ txt = '=' + val.f; if(txt.indexOf(",") >= 0) txt = '"' + txt.replace(qreg, '""') + '"';
+ } else txt = "";
+ /* NOTE: Excel CSV does not support array formulae */
+ row += (C === r.s.c ? "" : FS) + txt;
+ }
+ if(o.blankrows === false && isempty) return null;
+ return row;
+}
+
+function sheet_to_csv(sheet/*:Worksheet*/, opts/*:?Sheet2CSVOpts*/)/*:string*/ {
+ var out = "";
var o = opts == null ? {} : opts;
if(sheet == null || sheet["!ref"] == null) return "";
var r = safe_decode_range(sheet["!ref"]);
var FS = o.FS !== undefined ? o.FS : ",", fs = FS.charCodeAt(0);
var RS = o.RS !== undefined ? o.RS : "\n", rs = RS.charCodeAt(0);
var endregex = new RegExp((FS=="|" ? "\\|" : FS)+"+$");
- var row = "", rr = "", cols = [];
- var i = 0, cc = 0, val;
- var R = 0, C = 0;
- var dense = Array.isArray(sheet);
- for(C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
- for(R = r.s.r; R <= r.e.r; ++R) {
- var isempty = true;
- row = "";
- rr = encode_row(R);
- for(C = r.s.c; C <= r.e.c; ++C) {
- val = dense ? (sheet[R]||[])[C]: sheet[cols[C] + rr];
- if(val == null) txt = "";
- else if(val.v != null) {
- isempty = false;
- txt = ''+format_cell(val, null, o);
- for(i = 0, cc = 0; i !== txt.length; ++i) if((cc = txt.charCodeAt(i)) === fs || cc === rs || cc === 34) {
- txt = "\"" + txt.replace(qreg, '""') + "\""; break; }
- } else if(val.f != null && !val.F) {
- isempty = false;
- txt = '=' + val.f; if(txt.indexOf(",") >= 0) txt = '"' + txt.replace(qreg, '""') + '"';
- } else txt = "";
- /* NOTE: Excel CSV does not support array formulae */
- row += (C === r.s.c ? "" : FS) + txt;
- }
- if(o.blankrows === false && isempty) continue;
+ var row = "", cols = [];
+ o.dense = Array.isArray(sheet);
+ for(var C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
+ for(var R = r.s.r; R <= r.e.r; ++R) {
+ row = make_csv_row(sheet, r, R, cols, fs, rs, FS, o);
+ if(row == null) { continue; }
if(o.strip) row = row.replace(endregex,"");
out += row + RS;
}
+ delete o.dense;
return out;
}
diff --git a/bits/97_node.js b/bits/97_node.js
index 91a64e6..46e5b65 100644
--- a/bits/97_node.js
+++ b/bits/97_node.js
@@ -3,45 +3,26 @@ if(has_buf && typeof require != 'undefined') (function() {
var write_csv_stream = function(sheet/*:Worksheet*/, opts/*:?Sheet2CSVOpts*/) {
var stream = Readable();
- var out = "", txt = "", qreg = /"/g;
+ var out = "";
var o = opts == null ? {} : opts;
if(sheet == null || sheet["!ref"] == null) { stream.push(null); return stream; }
var r = safe_decode_range(sheet["!ref"]);
var FS = o.FS !== undefined ? o.FS : ",", fs = FS.charCodeAt(0);
var RS = o.RS !== undefined ? o.RS : "\n", rs = RS.charCodeAt(0);
var endregex = new RegExp((FS=="|" ? "\\|" : FS)+"+$");
- var row = "", rr = "", cols = [];
- var i = 0, cc = 0, val;
- var R = 0, C = 0;
- var dense = Array.isArray(sheet);
- for(C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
- R = r.s.r;
+ var row = "", cols = [];
+ o.dense = Array.isArray(sheet);
+ for(var C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
+ var R = r.s.r;
stream._read = function() {
if(R > r.e.r) return stream.push(null);
- while(true) {
- var isempty = true;
- row = "";
- rr = encode_row(R);
- for(C = r.s.c; C <= r.e.c; ++C) {
- val = dense ? (sheet[R]||[])[C]: sheet[cols[C] + rr];
- if(val == null) txt = "";
- else if(val.v != null) {
- isempty = false;
- txt = ''+format_cell(val, null, o);
- for(i = 0, cc = 0; i !== txt.length; ++i) if((cc = txt.charCodeAt(i)) === fs || cc === rs || cc === 34) {
- txt = "\"" + txt.replace(qreg, '""') + "\""; break; }
- } else if(val.f != null && !val.F) {
- isempty = false;
- txt = '=' + val.f; if(txt.indexOf(",") >= 0) txt = '"' + txt.replace(qreg, '""') + '"';
- } else txt = "";
- /* NOTE: Excel CSV does not support array formulae */
- row += (C === r.s.c ? "" : FS) + txt;
- }
- if(o.blankrows === false && isempty) { ++R; continue; }
- if(o.strip) row = row.replace(endregex,"");
- stream.push(row + RS);
- ++R;
- break;
+ while(R <= r.e.r) {
+ row = make_csv_row(sheet, r, R, cols, fs, rs, FS, o);
+ if(row == null) { ++R; continue; }
+ if(o.strip) row = row.replace(endregex,"");
+ stream.push(row + RS);
+ ++R;
+ break;
}
};
return stream;
diff --git a/docbits/20_import.md b/docbits/20_import.md
index 26ac49f..9c42ef5 100644
--- a/docbits/20_import.md
+++ b/docbits/20_import.md
@@ -124,3 +124,24 @@ function handleFile(e) {
input_dom_element.addEventListener('change', handleFile, false);
```
+**Complete examples:**
+
+- HTML5 File API / Base64 Text / Web Workers
+
+Note that older versions of IE do not support HTML5 File API, so the base64 mode
+is used for testing. On OSX you can get the base64 encoding with:
+
+```bash
+$ certutil -encode target_file target_file.b64
+```
+
+(note: You have to open the file and remove the header and footer lines)
+
+- XMLHttpRequest
+
diff --git a/docbits/21_readstream.md b/docbits/21_readstream.md
new file mode 100644
index 0000000..0528a20
--- /dev/null
+++ b/docbits/21_readstream.md
@@ -0,0 +1,12 @@
+### Note on Streaming Read
+
+The most common and interesting formats (XLS, XLSX/M, XLSB, ODS) are ultimately
+ZIP or CFB containers of files. Neither format puts the directory structure at
+the beginning of the file: ZIP files place the Central Directory records at the
+end of the logical file, while CFB files can place the FAT structure anywhere in
+the file! As a result, to properly handle these formats, a streaming function
+would have to buffer the entire file before commencing. That belies the
+expectations of streaming, so we do not provide any streaming read API. If you
+really want to stream, there are node modules like `concat-stream` that will do
+the buffering for you.
+
diff --git a/docbits/25_manip.md b/docbits/25_manip.md
index d9f5048..b9b78f6 100644
--- a/docbits/25_manip.md
+++ b/docbits/25_manip.md
@@ -20,25 +20,6 @@ var desired_value = (desired_cell ? desired_cell.v : undefined);
**Complete examples:**
-- 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
diff --git a/docbits/31_writestream.md b/docbits/31_writestream.md
new file mode 100644
index 0000000..d9cae3d
--- /dev/null
+++ b/docbits/31_writestream.md
@@ -0,0 +1,6 @@
+### Streaming Write
+
+`XLSX.stream.to_csv` is the streaming version of `XLSX.utils.sheet_to_csv`. It
+takes the same arguments but returns a readable stream.
+
+ pipes CSV write stream to nodejs response.
diff --git a/docbits/61_formulae.md b/docbits/61_formulae.md
index a2e8ae1..35df471 100644
--- a/docbits/61_formulae.md
+++ b/docbits/61_formulae.md
@@ -45,7 +45,7 @@ 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`:
+first cell specifies the formula. Consider `D1:D3=A1:A3*B1:B3`:
```js
worksheet['D1'] = { t:'n', F:"D1:D3", f:"A1:A3*B1:B3" };
diff --git a/docbits/80_parseopts.md b/docbits/80_parseopts.md
index 2d7890b..1056919 100644
--- a/docbits/80_parseopts.md
+++ b/docbits/80_parseopts.md
@@ -77,7 +77,8 @@ Plaintext format guessing follows the priority order:
| Format | Test |
|:-------|:--------------------------------------------------------------------|
-| XML | starts with < |
+| HTML | starts with \ txt
dbf -> csf
html -> csf
+ csf -> html
}
}
diff --git a/formats.png b/formats.png
index 145c98e..af17b09 100644
Binary files a/formats.png and b/formats.png differ
diff --git a/misc/docs/SUMMARY.md b/misc/docs/SUMMARY.md
index 57b5bf7..613f855 100644
--- a/misc/docs/SUMMARY.md
+++ b/misc/docs/SUMMARY.md
@@ -6,8 +6,10 @@
* [Optional Modules](README.md#optional-modules)
* [ECMAScript 5 Compatibility](README.md#ecmascript-5-compatibility)
- [Parsing Workbooks](README.md#parsing-workbooks)
+ * [Note on Streaming Read](README.md#note-on-streaming-read)
- [Working with the Workbook](README.md#working-with-the-workbook)
- [Writing Workbooks](README.md#writing-workbooks)
+ * [Streaming Write](README.md#streaming-write)
- [Interface](README.md#interface)
* [Parsing functions](README.md#parsing-functions)
* [Writing functions](README.md#writing-functions)
diff --git a/test.js b/test.js
index 2b8e928..eafe902 100644
--- a/test.js
+++ b/test.js
@@ -961,7 +961,7 @@ describe('parse features', function() {
var bef = (function() {
ws = X.utils.aoa_to_sheet([
["a","b","c"],
- ["&","<",">"]
+ ["&","<",">","\n"]
]);
wb = {SheetNames:["Sheet1"],Sheets:{Sheet1:ws}};
});
@@ -972,6 +972,7 @@ describe('parse features', function() {
assert.equal(get_cell(wb2.Sheets.Sheet1, "A2").h, "&");
assert.equal(get_cell(wb2.Sheets.Sheet1, "B2").h, "<");
assert.equal(get_cell(wb2.Sheets.Sheet1, "C2").h, ">");
+ assert.equal(get_cell(wb2.Sheets.Sheet1, "D2").h, "
");
}); });
});
@@ -1135,6 +1136,15 @@ describe('write features', function() {
}); });
});
});
+ describe('HTML', function() {
+ it('should use `h` value when present', function() {
+ var sheet = X.utils.aoa_to_sheet([["abc"]]);
+ get_cell(sheet, "A1").h = "abc";
+ var wb = {SheetNames:["Sheet1"], Sheets:{Sheet1:sheet}};
+ var str = X.write(wb, {bookType:"html", type:"binary"});
+ assert(str.indexOf("abc") > 0);
+ });
+ });
});
function seq(end, start) {
diff --git a/xlsx.flow.js b/xlsx.flow.js
index a6ecf85..68c0a85 100644
--- a/xlsx.flow.js
+++ b/xlsx.flow.js
@@ -1549,7 +1549,7 @@ function resolve_path(path/*:string*/, base/*:string*/)/*:string*/ {
}
return result.join('/');
}
-var attregexg=/([^\s?>\/]+)=((?:")([^"]*)(?:")|(?:')([^']*)(?:'))/g;
+var attregexg=/([^"\s?>\/]+)=((?:")([^"]*)(?:")|(?:')([^']*)(?:')|([^'">\s]+))/g;
var tagregex=/<[^>]*>/g;
var nsregex=/<\w*:/, nsregex2 = /<(\/?)\w+:/;
function parsexmltag(tag/*:string*/, skip_root/*:?boolean*/)/*:any*/ {
@@ -1558,11 +1558,13 @@ function parsexmltag(tag/*:string*/, skip_root/*:?boolean*/)/*:any*/ {
for(; eq !== tag.length; ++eq) if((c = tag.charCodeAt(eq)) === 32 || c === 10 || c === 13) break;
if(!skip_root) z[0] = tag.substr(0, eq);
if(eq === tag.length) return z;
- var m = tag.match(attregexg), j=0, v="", i=0, q="", cc="";
+ var m = tag.match(attregexg), j=0, v="", i=0, q="", cc="", quot = 1;
if(m) for(i = 0; i != m.length; ++i) {
cc = m[i];
for(c=0; c != cc.length; ++c) if(cc.charCodeAt(c) === 61) break;
- q = cc.substr(0,c); v = cc.substring(c+2, cc.length-1);
+ q = cc.substr(0,c);
+ quot = ((eq=cc.charCodeAt(c+1)) == 34 || eq == 39) ? 1 : 0;
+ v = cc.substring(c+1+quot, cc.length-quot);
for(j=0;j!=q.length;++j) if(q.charCodeAt(j) === 58) break;
if(j===q.length) {
if(q.indexOf("_") > 0) q = q.substr(0, q.indexOf("_")); // from ods
@@ -1605,9 +1607,10 @@ function escapexml(text/*:string*/, xml/*:?boolean*/)/*:string*/{
}
function escapexmltag(text/*:string*/)/*:string*/{ return escapexml(text).replace(/ /g,"_x0020_"); }
+var htmlcharegex = /[\u0000-\u001f]/g;
function escapehtml(text){
var s = text + '';
- return s.replace(decregex, function(y) { return rencoding[y]; });
+ return s.replace(decregex, function(y) { return rencoding[y]; }).replace(htmlcharegex,function(s) { return "&#x" + ("000"+s.charCodeAt(0).toString(16)).slice(-4) + ";"; });
}
/* TODO: handle codepages */
@@ -5332,7 +5335,7 @@ var WK_ = (function() {
if(!d) return d;
var o = opts || {};
if(DENSE != null && o.dense == null) o.dense = DENSE;
- var s = (o.dense ? [] : {}), n = "Sheet1", sidx = 0;
+ var s/*:Worksheet*/ = ((o.dense ? [] : {})/*:any*/), n = "Sheet1", sidx = 0;
var sheets = {}, snames = [n];
var refguess = {s: {r:0, c:0}, e: {r:0, c:0} };
@@ -5862,8 +5865,8 @@ function parse_sst_bin(data, opts)/*:SST*/ {
pass = false; break;
default:
- if(R_n.indexOf("Begin") > 0) state.push(R_n);
- else if(R_n.indexOf("End") > 0) state.pop();
+ if(R_n.indexOf("Begin") > 0){}
+ else if(R_n.indexOf("End") > 0){}
if(!pass || opts.WTF) throw new Error("Unexpected record " + RT + " " + R_n);
}
});
@@ -7462,7 +7465,7 @@ function parse_ms_xml() { return {'!type':'macro'}; }
/* TODO: it will be useful to parse the function str */
var rc_to_a1 = (function(){
var rcregex = /(^|[^A-Za-z])R(\[?)(-?\d+|)\]?C(\[?)(-?\d+|)\]?/g;
- var rcbase;
+ var rcbase/*:Cell*/ = ({r:0,c:0}/*:any*/);
function rcfunc($$,$1,$2,$3,$4,$5) {
var R = $3.length>0?parseInt($3,10)|0:0, C = $5.length>0?parseInt($5,10)|0:0;
if(C<0 && $4.length === 0) C=0;
@@ -7471,7 +7474,7 @@ var rc_to_a1 = (function(){
if($2.length > 0 || $3.length == 0) rRel = true; if(rRel) R += rcbase.r; else --R;
return $1 + (cRel ? "" : "$") + encode_col(C) + (rRel ? "" : "$") + encode_row(R);
}
- return function rc_to_a1(fstr, base) {
+ return function rc_to_a1(fstr/*:string*/, base/*:Cell*/)/*:string*/ {
rcbase = base;
return fstr.replace(rcregex, rcfunc);
};
@@ -11527,6 +11530,8 @@ function write_wb_xml(wb/*:Workbook*/, opts/*:?WriteOpts*/)/*:string*/ {
var o = [XML_HEADER];
o[o.length] = WB_XML_ROOT;
+ var write_names = (wb.Workbook && (wb.Workbook.Names||[]).length > 0);
+
/* fileVersion */
/* fileSharing */
@@ -11552,9 +11557,9 @@ function write_wb_xml(wb/*:Workbook*/, opts/*:?WriteOpts*/)/*:string*/ {
/* functionGroups */
/* externalReferences */
- if(wb.Workbook && (wb.Workbook.Names||[]).length > 0) {
+ if(write_names) {
o[o.length] = "";
- wb.Workbook.Names.forEach(function(n) {
+ if(wb.Workbook && wb.Workbook.Names) wb.Workbook.Names.forEach(function(n) {
var d = {name:n.Name};
if(n.Comment) d.comment = n.Comment;
if(n.Sheet != null) d.localSheetId = ""+n.Sheet;
@@ -12080,7 +12085,7 @@ function parse_xlml_xml(d, opts)/*:Workbook*/ {
make_ssf(SSF);
var str = debom(xlml_normalize(d));
if(opts && opts.type == 'binary' && typeof cptable !== 'undefined') str = cptable.utils.decode(65001, char_codes(str));
- if(str.substr(0,1000).indexOf("= 0) return parse_html(str, opts);
+ if(str.substr(0,1000).indexOf("= 0) return HTML_.to_workbook(str, opts);
var Rn;
var state = [], tmp;
if(DENSE != null && opts.dense == null) opts.dense = DENSE;
@@ -15054,48 +15059,95 @@ function write_biff_buf(wb/*:Workbook*/, opts/*:WriteOpts*/) {
return ba.end();
}
/* TODO: in browser attach to DOM; in node use an html parser */
-function parse_html(str/*:string*/, _opts)/*:Workbook*/ {
- var opts = _opts || {};
- if(DENSE != null && opts.dense == null) opts.dense = DENSE;
- var ws/*:Worksheet*/ = opts.dense ? ([]/*:any*/) : ({}/*:any*/);
- var o/*:Workbook*/ = { SheetNames: ["Sheet1"], Sheets: {Sheet1:ws} };
- var i = str.indexOf(" / pair");
- var rows = str.slice(i, j).split(/]*>/);
- var R = 0, C = 0;
- var range = {s:{r:10000000, c:10000000},e:{r:0,c:0}};
- for(i = 0; i < rows.length; ++i) {
- if(rows[i].substr(0,3) != "");
- for(j = 0; j < cells.length; ++j) {
- if(cells[j].substr(0,3) != "")) > -1) m = m.slice(cc+1);
- while(m.indexOf(">") > -1) m = m.slice(0, m.lastIndexOf("<"));
- /* TODO: generate stub cells */
- if(!m.length) continue;
- if(range.s.r > R) range.s.r = R;
- if(range.e.r < R) range.e.r = R;
- if(range.s.c > C) range.s.c = C;
- if(range.e.c < C) range.e.c = C;
- if(opts.dense) {
- if(!ws[R]) ws[R] = [];
- if(Number(m) == Number(m)) ws[R][C] = {t:'n', v:+m};
- else ws[R][C] = {t:'s', v:m};
- } else {
- var coord/*:string*/ = encode_cell({r:R, c:C});
- /* TODO: value parsing */
- if(Number(m) == Number(m)) ws[coord] = {t:'n', v:+m};
- else ws[coord] = {t:'s', v:m};
+var HTML_ = (function() {
+ function html_to_sheet(str/*:string*/, _opts)/*:Workbook*/ {
+ var opts = _opts || {};
+ if(DENSE != null && opts.dense == null) opts.dense = DENSE;
+ var ws/*:Worksheet*/ = opts.dense ? ([]/*:any*/) : ({}/*:any*/);
+ var i = str.indexOf(" / pair");
+ var rows = str.slice(i, j).split(/(:?]*>)/);
+ var R = -1, C = 0, RS = 0, CS = 0;
+ var range = {s:{r:10000000, c:10000000},e:{r:0,c:0}};
+ var merges = [], midx = 0;
+ for(i = 0; i < rows.length; ++i) {
+ var row = rows[i].trim();
+ if(row.substr(0,3) == "");
+ for(j = 0; j < cells.length; ++j) {
+ var cell = cells[j].trim();
+ if(cell.substr(0,3) != "")) > -1) m = m.slice(cc+1);
+ while(m.indexOf(">") > -1) m = m.slice(0, m.lastIndexOf("<"));
+ var tag = parsexmltag(cell.slice(0, cell.indexOf(">")));
+ CS = tag.colspan ? +tag.colspan : 1;
+ if((RS = +tag.rowspan)>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
+ /* TODO: generate stub cells */
+ if(!m.length) { C += CS; continue; }
+ m = unescapexml(m).replace(/[\r\n]/g,"");
+ if(range.s.r > R) range.s.r = R;
+ if(range.e.r < R) range.e.r = R;
+ if(range.s.c > C) range.s.c = C;
+ if(range.e.c < C) range.e.c = C;
+ if(opts.dense) {
+ if(!ws[R]) ws[R] = [];
+ if(Number(m) == Number(m)) ws[R][C] = {t:'n', v:+m};
+ else ws[R][C] = {t:'s', v:m};
+ } else {
+ var coord/*:string*/ = encode_cell({r:R, c:C});
+ /* TODO: value parsing */
+ if(Number(m) == Number(m)) ws[coord] = {t:'n', v:+m};
+ else ws[coord] = {t:'s', v:m};
+ }
+ C += CS;
}
}
- ++R; C = 0;
+ ws['!ref'] = encode_range(range);
+ return ws;
}
- ws['!ref'] = encode_range(range);
- return o;
-}
+ function html_to_book(str/*:string*/, opts)/*:Workbook*/ {
+ return sheet_to_workbook(html_to_sheet(str, opts), opts);
+ }
+ function sheet_to_html(ws/*:Worksheet*/, opts)/*:string*/ {
+ var o/*:Array*/ = [];
+ var r = decode_range(ws['!ref']), cell/*:Cell*/;
+ var dense = Array.isArray(ws);
+ var M = (ws['!merges'] ||[]);
+ for(var R = r.s.r; R <= r.e.r; ++R) {
+ var oo = [];
+ for(var C = r.s.c; C <= r.e.c; ++C) {
+ var RS = 0, CS = 0;
+ for(var j = 0; j < M.length; ++j) {
+ if(M[j].s.r > R || M[j].s.c > C) continue;
+ if(M[j].e.r < R || M[j].e.c < C) continue;
+ if(M[j].s.r < R || M[j].s.c < C) { RS = -1; break; }
+ RS = M[j].e.r - M[j].s.r + 1; CS = M[j].e.c - M[j].s.c + 1; break;
+ }
+ if(RS < 0) continue;
+ var coord = encode_cell({r:R,c:C});
+ cell = dense ? (ws[R]||[])[C] : ws[coord];
+ if(!cell || cell.v == null) { oo.push(" | "); continue; }
+ /* TODO: html entities */
+ var w = cell.h || escapexml(cell.w || (format_cell(cell), cell.w) || "");
+ var sp = {};
+ if(RS > 1) sp.rowspan = RS;
+ if(CS > 1) sp.colspan = CS;
+ oo.push(writextag('td', w, sp));
+ }
+ o.push("" + oo.join("") + "
");
+ }
+ return "";
+ }
+
+ return {
+ to_workbook: html_to_book,
+ to_sheet: html_to_sheet,
+ from_sheet: sheet_to_html
+ };
+})();
function parse_dom_table(table/*:HTMLElement*/, _opts/*:?any*/)/*:Worksheet*/ {
var opts = _opts || {};
@@ -15116,7 +15168,7 @@ function parse_dom_table(table/*:HTMLElement*/, _opts/*:?any*/)/*:Worksheet*/ {
}
/* TODO: figure out how to extract nonstandard mso- style */
CS = +elt.getAttribute("colspan") || 1;
- if((RS = +elt.getAttribute("rowspan"))>0) merges.push({s:{r:R,c:C},e:{r:R + RS - 1, c:C + CS - 1}});
+ if((RS = +elt.getAttribute("rowspan"))>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
var o = {t:'s', v:v};
if(v != null && v.length && !isNaN(Number(v))) o = {t:'n', v:Number(v)};
if(opts.dense) { if(!ws[R]) ws[R] = []; ws[R][C] = o; }
@@ -15652,6 +15704,7 @@ function write_obj_str(factory/*:WriteObjStrFactory*/) {
};
}
+var write_htm_str = write_obj_str(HTML_);
var write_csv_str = write_obj_str({from_sheet:sheet_to_csv});
var write_slk_str = write_obj_str(SYLK);
var write_dif_str = write_obj_str(DIF);
@@ -16213,6 +16266,7 @@ function writeSync(wb/*:Workbook*/, opts/*:?WriteOpts*/) {
case 'xlml': return write_string_type(write_xlml(wb, o), o);
case 'slk':
case 'sylk': return write_string_type(write_slk_str(wb, o), o);
+ case 'html': return write_string_type(write_htm_str(wb, o), o);
case 'txt': return write_bstr_type(write_txt_str(wb, o), o);
case 'csv': return write_string_type(write_csv_str(wb, o), o);
case 'dif': return write_string_type(write_dif_str(wb, o), o);
@@ -16235,6 +16289,7 @@ function resolve_book_type(o/*?WriteFileOpts*/) {
case '.fods': o.bookType = 'fods'; break;
case '.xlml': o.bookType = 'xlml'; break;
case '.sylk': o.bookType = 'sylk'; break;
+ case '.html': o.bookType = 'html'; break;
case '.xls': o.bookType = 'biff2'; break;
case '.xml': o.bookType = 'xml'; break;
case '.ods': o.bookType = 'ods'; break;
@@ -16243,6 +16298,7 @@ function resolve_book_type(o/*?WriteFileOpts*/) {
case '.dif': o.bookType = 'dif'; break;
case '.prn': o.bookType = 'prn'; break;
case '.slk': o.bookType = 'sylk'; break;
+ case '.htm': o.bookType = 'html'; break;
}
}
@@ -16417,42 +16473,47 @@ function sheet_to_json(sheet/*:Worksheet*/, opts/*:?Sheet2JSONOpts*/){
return out;
}
-function sheet_to_csv(sheet/*:Worksheet*/, opts/*:?Sheet2CSVOpts*/) {
- var out = "", txt = "", qreg = /"/g;
+var qreg = /"/g;
+function make_csv_row(sheet/*:Worksheet*/, r/*:Range*/, R/*:number*/, cols/*:Array*/, fs/*:number*/, rs/*:number*/, FS/*:string*/, o/*:Sheet2CSVOpts*/)/*:?string*/ {
+ var isempty = true;
+ var row = "", txt = "", rr = encode_row(R);
+ for(var C = r.s.c; C <= r.e.c; ++C) {
+ var val = o.dense ? (sheet[R]||[])[C]: sheet[cols[C] + rr];
+ if(val == null) txt = "";
+ else if(val.v != null) {
+ isempty = false;
+ txt = ''+format_cell(val, null, o);
+ for(var i = 0, cc = 0; i !== txt.length; ++i) if((cc = txt.charCodeAt(i)) === fs || cc === rs || cc === 34) {
+ txt = "\"" + txt.replace(qreg, '""') + "\""; break; }
+ } else if(val.f != null && !val.F) {
+ isempty = false;
+ txt = '=' + val.f; if(txt.indexOf(",") >= 0) txt = '"' + txt.replace(qreg, '""') + '"';
+ } else txt = "";
+ /* NOTE: Excel CSV does not support array formulae */
+ row += (C === r.s.c ? "" : FS) + txt;
+ }
+ if(o.blankrows === false && isempty) return null;
+ return row;
+}
+
+function sheet_to_csv(sheet/*:Worksheet*/, opts/*:?Sheet2CSVOpts*/)/*:string*/ {
+ var out = "";
var o = opts == null ? {} : opts;
if(sheet == null || sheet["!ref"] == null) return "";
var r = safe_decode_range(sheet["!ref"]);
var FS = o.FS !== undefined ? o.FS : ",", fs = FS.charCodeAt(0);
var RS = o.RS !== undefined ? o.RS : "\n", rs = RS.charCodeAt(0);
var endregex = new RegExp((FS=="|" ? "\\|" : FS)+"+$");
- var row = "", rr = "", cols = [];
- var i = 0, cc = 0, val;
- var R = 0, C = 0;
- var dense = Array.isArray(sheet);
- for(C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
- for(R = r.s.r; R <= r.e.r; ++R) {
- var isempty = true;
- row = "";
- rr = encode_row(R);
- for(C = r.s.c; C <= r.e.c; ++C) {
- val = dense ? (sheet[R]||[])[C]: sheet[cols[C] + rr];
- if(val == null) txt = "";
- else if(val.v != null) {
- isempty = false;
- txt = ''+format_cell(val, null, o);
- for(i = 0, cc = 0; i !== txt.length; ++i) if((cc = txt.charCodeAt(i)) === fs || cc === rs || cc === 34) {
- txt = "\"" + txt.replace(qreg, '""') + "\""; break; }
- } else if(val.f != null && !val.F) {
- isempty = false;
- txt = '=' + val.f; if(txt.indexOf(",") >= 0) txt = '"' + txt.replace(qreg, '""') + '"';
- } else txt = "";
- /* NOTE: Excel CSV does not support array formulae */
- row += (C === r.s.c ? "" : FS) + txt;
- }
- if(o.blankrows === false && isempty) continue;
+ var row = "", cols = [];
+ o.dense = Array.isArray(sheet);
+ for(var C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
+ for(var R = r.s.r; R <= r.e.r; ++R) {
+ row = make_csv_row(sheet, r, R, cols, fs, rs, FS, o);
+ if(row == null) { continue; }
if(o.strip) row = row.replace(endregex,"");
out += row + RS;
}
+ delete o.dense;
return out;
}
@@ -16528,45 +16589,26 @@ if(has_buf && typeof require != 'undefined') (function() {
var write_csv_stream = function(sheet/*:Worksheet*/, opts/*:?Sheet2CSVOpts*/) {
var stream = Readable();
- var out = "", txt = "", qreg = /"/g;
+ var out = "";
var o = opts == null ? {} : opts;
if(sheet == null || sheet["!ref"] == null) { stream.push(null); return stream; }
var r = safe_decode_range(sheet["!ref"]);
var FS = o.FS !== undefined ? o.FS : ",", fs = FS.charCodeAt(0);
var RS = o.RS !== undefined ? o.RS : "\n", rs = RS.charCodeAt(0);
var endregex = new RegExp((FS=="|" ? "\\|" : FS)+"+$");
- var row = "", rr = "", cols = [];
- var i = 0, cc = 0, val;
- var R = 0, C = 0;
- var dense = Array.isArray(sheet);
- for(C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
- R = r.s.r;
+ var row = "", cols = [];
+ o.dense = Array.isArray(sheet);
+ for(var C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
+ var R = r.s.r;
stream._read = function() {
if(R > r.e.r) return stream.push(null);
- while(true) {
- var isempty = true;
- row = "";
- rr = encode_row(R);
- for(C = r.s.c; C <= r.e.c; ++C) {
- val = dense ? (sheet[R]||[])[C]: sheet[cols[C] + rr];
- if(val == null) txt = "";
- else if(val.v != null) {
- isempty = false;
- txt = ''+format_cell(val, null, o);
- for(i = 0, cc = 0; i !== txt.length; ++i) if((cc = txt.charCodeAt(i)) === fs || cc === rs || cc === 34) {
- txt = "\"" + txt.replace(qreg, '""') + "\""; break; }
- } else if(val.f != null && !val.F) {
- isempty = false;
- txt = '=' + val.f; if(txt.indexOf(",") >= 0) txt = '"' + txt.replace(qreg, '""') + '"';
- } else txt = "";
- /* NOTE: Excel CSV does not support array formulae */
- row += (C === r.s.c ? "" : FS) + txt;
- }
- if(o.blankrows === false && isempty) { ++R; continue; }
- if(o.strip) row = row.replace(endregex,"");
- stream.push(row + RS);
- ++R;
- break;
+ while(R <= r.e.r) {
+ row = make_csv_row(sheet, r, R, cols, fs, rs, FS, o);
+ if(row == null) { ++R; continue; }
+ if(o.strip) row = row.replace(endregex,"");
+ stream.push(row + RS);
+ ++R;
+ break;
}
};
return stream;
diff --git a/xlsx.js b/xlsx.js
index e56cf7c..a0e786b 100644
--- a/xlsx.js
+++ b/xlsx.js
@@ -1498,7 +1498,7 @@ function resolve_path(path, base) {
}
return result.join('/');
}
-var attregexg=/([^\s?>\/]+)=((?:")([^"]*)(?:")|(?:')([^']*)(?:'))/g;
+var attregexg=/([^"\s?>\/]+)=((?:")([^"]*)(?:")|(?:')([^']*)(?:')|([^'">\s]+))/g;
var tagregex=/<[^>]*>/g;
var nsregex=/<\w*:/, nsregex2 = /<(\/?)\w+:/;
function parsexmltag(tag, skip_root) {
@@ -1507,11 +1507,13 @@ function parsexmltag(tag, skip_root) {
for(; eq !== tag.length; ++eq) if((c = tag.charCodeAt(eq)) === 32 || c === 10 || c === 13) break;
if(!skip_root) z[0] = tag.substr(0, eq);
if(eq === tag.length) return z;
- var m = tag.match(attregexg), j=0, v="", i=0, q="", cc="";
+ var m = tag.match(attregexg), j=0, v="", i=0, q="", cc="", quot = 1;
if(m) for(i = 0; i != m.length; ++i) {
cc = m[i];
for(c=0; c != cc.length; ++c) if(cc.charCodeAt(c) === 61) break;
- q = cc.substr(0,c); v = cc.substring(c+2, cc.length-1);
+ q = cc.substr(0,c);
+ quot = ((eq=cc.charCodeAt(c+1)) == 34 || eq == 39) ? 1 : 0;
+ v = cc.substring(c+1+quot, cc.length-quot);
for(j=0;j!=q.length;++j) if(q.charCodeAt(j) === 58) break;
if(j===q.length) {
if(q.indexOf("_") > 0) q = q.substr(0, q.indexOf("_")); // from ods
@@ -1554,9 +1556,10 @@ function escapexml(text, xml){
}
function escapexmltag(text){ return escapexml(text).replace(/ /g,"_x0020_"); }
+var htmlcharegex = /[\u0000-\u001f]/g;
function escapehtml(text){
var s = text + '';
- return s.replace(decregex, function(y) { return rencoding[y]; });
+ return s.replace(decregex, function(y) { return rencoding[y]; }).replace(htmlcharegex,function(s) { return "&#x" + ("000"+s.charCodeAt(0).toString(16)).slice(-4) + ";"; });
}
/* TODO: handle codepages */
@@ -5276,7 +5279,7 @@ var WK_ = (function() {
if(!d) return d;
var o = opts || {};
if(DENSE != null && o.dense == null) o.dense = DENSE;
- var s = (o.dense ? [] : {}), n = "Sheet1", sidx = 0;
+ var s = ((o.dense ? [] : {})), n = "Sheet1", sidx = 0;
var sheets = {}, snames = [n];
var refguess = {s: {r:0, c:0}, e: {r:0, c:0} };
@@ -5806,8 +5809,8 @@ function parse_sst_bin(data, opts) {
pass = false; break;
default:
- if(R_n.indexOf("Begin") > 0) state.push(R_n);
- else if(R_n.indexOf("End") > 0) state.pop();
+ if(R_n.indexOf("Begin") > 0){}
+ else if(R_n.indexOf("End") > 0){}
if(!pass || opts.WTF) throw new Error("Unexpected record " + RT + " " + R_n);
}
});
@@ -7406,7 +7409,7 @@ function parse_ms_xml() { return {'!type':'macro'}; }
/* TODO: it will be useful to parse the function str */
var rc_to_a1 = (function(){
var rcregex = /(^|[^A-Za-z])R(\[?)(-?\d+|)\]?C(\[?)(-?\d+|)\]?/g;
- var rcbase;
+ var rcbase = ({r:0,c:0});
function rcfunc($$,$1,$2,$3,$4,$5) {
var R = $3.length>0?parseInt($3,10)|0:0, C = $5.length>0?parseInt($5,10)|0:0;
if(C<0 && $4.length === 0) C=0;
@@ -11470,6 +11473,8 @@ function write_wb_xml(wb, opts) {
var o = [XML_HEADER];
o[o.length] = WB_XML_ROOT;
+ var write_names = (wb.Workbook && (wb.Workbook.Names||[]).length > 0);
+
/* fileVersion */
/* fileSharing */
@@ -11495,9 +11500,9 @@ function write_wb_xml(wb, opts) {
/* functionGroups */
/* externalReferences */
- if(wb.Workbook && (wb.Workbook.Names||[]).length > 0) {
+ if(write_names) {
o[o.length] = "";
- wb.Workbook.Names.forEach(function(n) {
+ if(wb.Workbook && wb.Workbook.Names) wb.Workbook.Names.forEach(function(n) {
var d = {name:n.Name};
if(n.Comment) d.comment = n.Comment;
if(n.Sheet != null) d.localSheetId = ""+n.Sheet;
@@ -12021,7 +12026,7 @@ function parse_xlml_xml(d, opts) {
make_ssf(SSF);
var str = debom(xlml_normalize(d));
if(opts && opts.type == 'binary' && typeof cptable !== 'undefined') str = cptable.utils.decode(65001, char_codes(str));
- if(str.substr(0,1000).indexOf("= 0) return parse_html(str, opts);
+ if(str.substr(0,1000).indexOf("= 0) return HTML_.to_workbook(str, opts);
var Rn;
var state = [], tmp;
if(DENSE != null && opts.dense == null) opts.dense = DENSE;
@@ -14993,48 +14998,95 @@ function write_biff_buf(wb, opts) {
return ba.end();
}
/* TODO: in browser attach to DOM; in node use an html parser */
-function parse_html(str, _opts) {
- var opts = _opts || {};
- if(DENSE != null && opts.dense == null) opts.dense = DENSE;
- var ws = opts.dense ? ([]) : ({});
- var o = { SheetNames: ["Sheet1"], Sheets: {Sheet1:ws} };
- var i = str.indexOf(" / pair");
- var rows = str.slice(i, j).split(/]*>/);
- var R = 0, C = 0;
- var range = {s:{r:10000000, c:10000000},e:{r:0,c:0}};
- for(i = 0; i < rows.length; ++i) {
- if(rows[i].substr(0,3) != "");
- for(j = 0; j < cells.length; ++j) {
- if(cells[j].substr(0,3) != "")) > -1) m = m.slice(cc+1);
- while(m.indexOf(">") > -1) m = m.slice(0, m.lastIndexOf("<"));
- /* TODO: generate stub cells */
- if(!m.length) continue;
- if(range.s.r > R) range.s.r = R;
- if(range.e.r < R) range.e.r = R;
- if(range.s.c > C) range.s.c = C;
- if(range.e.c < C) range.e.c = C;
- if(opts.dense) {
- if(!ws[R]) ws[R] = [];
- if(Number(m) == Number(m)) ws[R][C] = {t:'n', v:+m};
- else ws[R][C] = {t:'s', v:m};
- } else {
- var coord = encode_cell({r:R, c:C});
- /* TODO: value parsing */
- if(Number(m) == Number(m)) ws[coord] = {t:'n', v:+m};
- else ws[coord] = {t:'s', v:m};
+var HTML_ = (function() {
+ function html_to_sheet(str, _opts) {
+ var opts = _opts || {};
+ if(DENSE != null && opts.dense == null) opts.dense = DENSE;
+ var ws = opts.dense ? ([]) : ({});
+ var i = str.indexOf(" / pair");
+ var rows = str.slice(i, j).split(/(:?]*>)/);
+ var R = -1, C = 0, RS = 0, CS = 0;
+ var range = {s:{r:10000000, c:10000000},e:{r:0,c:0}};
+ var merges = [], midx = 0;
+ for(i = 0; i < rows.length; ++i) {
+ var row = rows[i].trim();
+ if(row.substr(0,3) == "");
+ for(j = 0; j < cells.length; ++j) {
+ var cell = cells[j].trim();
+ if(cell.substr(0,3) != "")) > -1) m = m.slice(cc+1);
+ while(m.indexOf(">") > -1) m = m.slice(0, m.lastIndexOf("<"));
+ var tag = parsexmltag(cell.slice(0, cell.indexOf(">")));
+ CS = tag.colspan ? +tag.colspan : 1;
+ if((RS = +tag.rowspan)>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
+ /* TODO: generate stub cells */
+ if(!m.length) { C += CS; continue; }
+ m = unescapexml(m).replace(/[\r\n]/g,"");
+ if(range.s.r > R) range.s.r = R;
+ if(range.e.r < R) range.e.r = R;
+ if(range.s.c > C) range.s.c = C;
+ if(range.e.c < C) range.e.c = C;
+ if(opts.dense) {
+ if(!ws[R]) ws[R] = [];
+ if(Number(m) == Number(m)) ws[R][C] = {t:'n', v:+m};
+ else ws[R][C] = {t:'s', v:m};
+ } else {
+ var coord = encode_cell({r:R, c:C});
+ /* TODO: value parsing */
+ if(Number(m) == Number(m)) ws[coord] = {t:'n', v:+m};
+ else ws[coord] = {t:'s', v:m};
+ }
+ C += CS;
}
}
- ++R; C = 0;
+ ws['!ref'] = encode_range(range);
+ return ws;
}
- ws['!ref'] = encode_range(range);
- return o;
-}
+ function html_to_book(str, opts) {
+ return sheet_to_workbook(html_to_sheet(str, opts), opts);
+ }
+ function sheet_to_html(ws, opts) {
+ var o = [];
+ var r = decode_range(ws['!ref']), cell;
+ var dense = Array.isArray(ws);
+ var M = (ws['!merges'] ||[]);
+ for(var R = r.s.r; R <= r.e.r; ++R) {
+ var oo = [];
+ for(var C = r.s.c; C <= r.e.c; ++C) {
+ var RS = 0, CS = 0;
+ for(var j = 0; j < M.length; ++j) {
+ if(M[j].s.r > R || M[j].s.c > C) continue;
+ if(M[j].e.r < R || M[j].e.c < C) continue;
+ if(M[j].s.r < R || M[j].s.c < C) { RS = -1; break; }
+ RS = M[j].e.r - M[j].s.r + 1; CS = M[j].e.c - M[j].s.c + 1; break;
+ }
+ if(RS < 0) continue;
+ var coord = encode_cell({r:R,c:C});
+ cell = dense ? (ws[R]||[])[C] : ws[coord];
+ if(!cell || cell.v == null) { oo.push(" | "); continue; }
+ /* TODO: html entities */
+ var w = cell.h || escapexml(cell.w || (format_cell(cell), cell.w) || "");
+ var sp = {};
+ if(RS > 1) sp.rowspan = RS;
+ if(CS > 1) sp.colspan = CS;
+ oo.push(writextag('td', w, sp));
+ }
+ o.push("" + oo.join("") + "
");
+ }
+ return "";
+ }
+
+ return {
+ to_workbook: html_to_book,
+ to_sheet: html_to_sheet,
+ from_sheet: sheet_to_html
+ };
+})();
function parse_dom_table(table, _opts) {
var opts = _opts || {};
@@ -15055,7 +15107,7 @@ function parse_dom_table(table, _opts) {
}
/* TODO: figure out how to extract nonstandard mso- style */
CS = +elt.getAttribute("colspan") || 1;
- if((RS = +elt.getAttribute("rowspan"))>0) merges.push({s:{r:R,c:C},e:{r:R + RS - 1, c:C + CS - 1}});
+ if((RS = +elt.getAttribute("rowspan"))>0 || CS>1) merges.push({s:{r:R,c:C},e:{r:R + (RS||1) - 1, c:C + CS - 1}});
var o = {t:'s', v:v};
if(v != null && v.length && !isNaN(Number(v))) o = {t:'n', v:Number(v)};
if(opts.dense) { if(!ws[R]) ws[R] = []; ws[R][C] = o; }
@@ -15591,6 +15643,7 @@ function write_obj_str(factory) {
};
}
+var write_htm_str = write_obj_str(HTML_);
var write_csv_str = write_obj_str({from_sheet:sheet_to_csv});
var write_slk_str = write_obj_str(SYLK);
var write_dif_str = write_obj_str(DIF);
@@ -16148,6 +16201,7 @@ function writeSync(wb, opts) {
case 'xlml': return write_string_type(write_xlml(wb, o), o);
case 'slk':
case 'sylk': return write_string_type(write_slk_str(wb, o), o);
+ case 'html': return write_string_type(write_htm_str(wb, o), o);
case 'txt': return write_bstr_type(write_txt_str(wb, o), o);
case 'csv': return write_string_type(write_csv_str(wb, o), o);
case 'dif': return write_string_type(write_dif_str(wb, o), o);
@@ -16170,6 +16224,7 @@ function resolve_book_type(o/*?WriteFileOpts*/) {
case '.fods': o.bookType = 'fods'; break;
case '.xlml': o.bookType = 'xlml'; break;
case '.sylk': o.bookType = 'sylk'; break;
+ case '.html': o.bookType = 'html'; break;
case '.xls': o.bookType = 'biff2'; break;
case '.xml': o.bookType = 'xml'; break;
case '.ods': o.bookType = 'ods'; break;
@@ -16178,6 +16233,7 @@ function resolve_book_type(o/*?WriteFileOpts*/) {
case '.dif': o.bookType = 'dif'; break;
case '.prn': o.bookType = 'prn'; break;
case '.slk': o.bookType = 'sylk'; break;
+ case '.htm': o.bookType = 'html'; break;
}
}
@@ -16347,42 +16403,47 @@ function sheet_to_json(sheet, opts){
return out;
}
+var qreg = /"/g;
+function make_csv_row(sheet, r, R, cols, fs, rs, FS, o) {
+ var isempty = true;
+ var row = "", txt = "", rr = encode_row(R);
+ for(var C = r.s.c; C <= r.e.c; ++C) {
+ var val = o.dense ? (sheet[R]||[])[C]: sheet[cols[C] + rr];
+ if(val == null) txt = "";
+ else if(val.v != null) {
+ isempty = false;
+ txt = ''+format_cell(val, null, o);
+ for(var i = 0, cc = 0; i !== txt.length; ++i) if((cc = txt.charCodeAt(i)) === fs || cc === rs || cc === 34) {
+ txt = "\"" + txt.replace(qreg, '""') + "\""; break; }
+ } else if(val.f != null && !val.F) {
+ isempty = false;
+ txt = '=' + val.f; if(txt.indexOf(",") >= 0) txt = '"' + txt.replace(qreg, '""') + '"';
+ } else txt = "";
+ /* NOTE: Excel CSV does not support array formulae */
+ row += (C === r.s.c ? "" : FS) + txt;
+ }
+ if(o.blankrows === false && isempty) return null;
+ return row;
+}
+
function sheet_to_csv(sheet, opts) {
- var out = "", txt = "", qreg = /"/g;
+ var out = "";
var o = opts == null ? {} : opts;
if(sheet == null || sheet["!ref"] == null) return "";
var r = safe_decode_range(sheet["!ref"]);
var FS = o.FS !== undefined ? o.FS : ",", fs = FS.charCodeAt(0);
var RS = o.RS !== undefined ? o.RS : "\n", rs = RS.charCodeAt(0);
var endregex = new RegExp((FS=="|" ? "\\|" : FS)+"+$");
- var row = "", rr = "", cols = [];
- var i = 0, cc = 0, val;
- var R = 0, C = 0;
- var dense = Array.isArray(sheet);
- for(C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
- for(R = r.s.r; R <= r.e.r; ++R) {
- var isempty = true;
- row = "";
- rr = encode_row(R);
- for(C = r.s.c; C <= r.e.c; ++C) {
- val = dense ? (sheet[R]||[])[C]: sheet[cols[C] + rr];
- if(val == null) txt = "";
- else if(val.v != null) {
- isempty = false;
- txt = ''+format_cell(val, null, o);
- for(i = 0, cc = 0; i !== txt.length; ++i) if((cc = txt.charCodeAt(i)) === fs || cc === rs || cc === 34) {
- txt = "\"" + txt.replace(qreg, '""') + "\""; break; }
- } else if(val.f != null && !val.F) {
- isempty = false;
- txt = '=' + val.f; if(txt.indexOf(",") >= 0) txt = '"' + txt.replace(qreg, '""') + '"';
- } else txt = "";
- /* NOTE: Excel CSV does not support array formulae */
- row += (C === r.s.c ? "" : FS) + txt;
- }
- if(o.blankrows === false && isempty) continue;
+ var row = "", cols = [];
+ o.dense = Array.isArray(sheet);
+ for(var C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
+ for(var R = r.s.r; R <= r.e.r; ++R) {
+ row = make_csv_row(sheet, r, R, cols, fs, rs, FS, o);
+ if(row == null) { continue; }
if(o.strip) row = row.replace(endregex,"");
out += row + RS;
}
+ delete o.dense;
return out;
}
@@ -16458,45 +16519,26 @@ if(has_buf && typeof require != 'undefined') (function() {
var write_csv_stream = function(sheet, opts) {
var stream = Readable();
- var out = "", txt = "", qreg = /"/g;
+ var out = "";
var o = opts == null ? {} : opts;
if(sheet == null || sheet["!ref"] == null) { stream.push(null); return stream; }
var r = safe_decode_range(sheet["!ref"]);
var FS = o.FS !== undefined ? o.FS : ",", fs = FS.charCodeAt(0);
var RS = o.RS !== undefined ? o.RS : "\n", rs = RS.charCodeAt(0);
var endregex = new RegExp((FS=="|" ? "\\|" : FS)+"+$");
- var row = "", rr = "", cols = [];
- var i = 0, cc = 0, val;
- var R = 0, C = 0;
- var dense = Array.isArray(sheet);
- for(C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
- R = r.s.r;
+ var row = "", cols = [];
+ o.dense = Array.isArray(sheet);
+ for(var C = r.s.c; C <= r.e.c; ++C) cols[C] = encode_col(C);
+ var R = r.s.r;
stream._read = function() {
if(R > r.e.r) return stream.push(null);
- while(true) {
- var isempty = true;
- row = "";
- rr = encode_row(R);
- for(C = r.s.c; C <= r.e.c; ++C) {
- val = dense ? (sheet[R]||[])[C]: sheet[cols[C] + rr];
- if(val == null) txt = "";
- else if(val.v != null) {
- isempty = false;
- txt = ''+format_cell(val, null, o);
- for(i = 0, cc = 0; i !== txt.length; ++i) if((cc = txt.charCodeAt(i)) === fs || cc === rs || cc === 34) {
- txt = "\"" + txt.replace(qreg, '""') + "\""; break; }
- } else if(val.f != null && !val.F) {
- isempty = false;
- txt = '=' + val.f; if(txt.indexOf(",") >= 0) txt = '"' + txt.replace(qreg, '""') + '"';
- } else txt = "";
- /* NOTE: Excel CSV does not support array formulae */
- row += (C === r.s.c ? "" : FS) + txt;
- }
- if(o.blankrows === false && isempty) { ++R; continue; }
- if(o.strip) row = row.replace(endregex,"");
- stream.push(row + RS);
- ++R;
- break;
+ while(R <= r.e.r) {
+ row = make_csv_row(sheet, r, R, cols, fs, rs, FS, o);
+ if(row == null) { ++R; continue; }
+ if(o.strip) row = row.replace(endregex,"");
+ stream.push(row + RS);
+ ++R;
+ break;
}
};
return stream;