HTML DOM Element read

- DOM <table> element parsing (fixes #576 h/t @axolo) - removed InterfaceHdr check (fixes #209 h/t @Batistleman) - gitbook docs
2017-03-29 15:14:15 -04:00 · 2017-03-29 15:14:15 -04:00 · 65f1c7e58b
parent b89a876076
commit 65f1c7e58b
17 changed files with 307 additions and 5 deletions
--- a/.flowconfig
+++ b/.flowconfig
@ -8,6 +8,7 @@
 .*/ctest/.*
 .*/misc/.*
 .*/perf/.*
+.*/_book/.*

 .*/demo/browser.js
 .*/shim.js
--- a/.gitignore
+++ b/.gitignore
@ -1,5 +1,6 @@
 node_modules
 *.tgz
+_book/
 misc/coverage.html
 misc/prof.js
 v8.log
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@ -7,6 +7,9 @@ changes may not be included if they are not expected to break existing code.

 ## Unreleased

+
+## 0.9.7 (2017-03-28)
+
 * XLS legacy `!range` field removed
 * Hyperlink tooltip is stored in the `Tooltip` field

@ -15,7 +18,7 @@ changes may not be included if they are not expected to break existing code.
 * `sheet_to_json` now passes `null` values when `raw` is set to `true`
 * `sheet_to_json` treats `null` stub cells as values in conjunction with `raw`

-## 0.9.5 (2017-03-22) 
+## 0.9.5 (2017-03-22)

 * `cellDates` affects parsing in non-XLSX formats

--- a/5
+++ b/5
@ -173,6 +173,11 @@ README.md: $(READEPS)
 readme: README.md ## Update README Table of Contents
 	markdown-toc -i README.md

+.PHONY: book
+book: README.md ## Update summary for documentation
+	printf "# Summary\n\n- [xlsx](README.md#xlsx)\n" > misc/docs/SUMMARY.md
+	markdown-toc README.md | sed 's/(#/(README.md#/g'>> misc/docs/SUMMARY.md
+
 .PHONY: help
 help:
 	@grep -hE '(^[a-zA-Z_-][ a-zA-Z_-]*:.*?|^#[#*])' $(MAKEFILE_LIST) | bash misc/help.sh
--- a/README.md
+++ b/README.md
@ -43,6 +43,7 @@ with a unified JS representation, and ES3/ES5 browser compatibility back to IE6.
  * [Document Features](#document-features)
    + [Formulae](#formulae)
    + [Column Properties](#column-properties)
+    + [Hyperlinks](#hyperlinks)
 - [Parsing Options](#parsing-options)
  * [Input Type](#input-type)
  * [Guessing File Type](#guessing-file-type)
@ -51,6 +52,7 @@ with a unified JS representation, and ES3/ES5 browser compatibility back to IE6.
  * [Output Type](#output-type)
 - [Utility Functions](#utility-functions)
  * [Array of Arrays Input](#array-of-arrays-input)
+  * [HTML Table Input](#html-table-input)
  * [Formulae Output](#formulae-output)
  * [CSV and general DSV Output](#csv-and-general-dsv-output)
  * [JSON](#json)
@ -161,6 +163,13 @@ var workbook = XLSX.readFile('test.xlsx');
 /* DO SOMETHING WITH workbook HERE */
 ```

+- Browser DOM Table element:
+
+```js
+var worksheet = XLSX.utils.table_to_book(document.getElementById('tableau'));
+/* DO SOMETHING WITH workbook HERE */
+```
+
 - ajax (for a more complete example that works in older browsers, check the demo
  at <http://oss.sheetjs.com/js-xlsx/ajax.html>):

@ -449,7 +458,7 @@ for(var R = range.s.r; R <= range.e.r; ++R) {
 | `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)        |
+| `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
@ -688,6 +697,23 @@ follow the priority order:
 2) use `wpx` pixel width if available
 3) use `wch` character count if available

+#### Hyperlinks
+
+Hyperlinks are stored in the `l` key of cell objects.  The `Target` field of the
+hyperlink object is the target of the link, including the URI fragment. Tooltips
+are stored in the `Tooltip` field and are displayed when you move your mouse
+over the text.
+
+For example, the following snippet creates a link from cell `A3` to
+<http://sheetjs.com> with the tip `"Find us @ SheetJS.com!"`:
+
+```js
+ws['A3'].l = { Target:"http://sheetjs.com", Tooltip:"Find us @ SheetJS.com!" };
+```
+
+Note that Excel does not automatically style hyperlinks -- they will generally
+be displayed as normal text.
+
 ## Parsing Options

 The exported `read` and `readFile` functions accept an options argument:
@ -852,6 +878,33 @@ var ws = XLSX.utils.aoa_to_sheet([
 ]);
 ```

+### HTML Table Input
+
+`XLSX.utils.table_to_sheet` takes a table DOM element and returns a worksheet
+resembling the input table.  Numbers are parsed.  All other data will be stored
+as strings.
+
+`XLSX.utils.table_to_book` produces a minimal workbook based on the worksheet.
+
+To generate the example sheet, start with the HTML table:
+
+```html
+<table id="sheetjs">
+<tr><td>S</td><td>h</td><td>e</td><td>e</td><td>t</td><td>J</td><td>S</td></tr>
+<tr><td>1</td><td>2</td><td>3</td><td>4</td><td>5</td><td>6</td><td>7</td></tr>
+<tr><td>2</td><td>3</td><td>4</td><td>5</td><td>6</td><td>7</td><td>8</td></tr>
+</table>
+```
+
+To process the table:
+
+```js
+var tbl = document.getElementById('sheetjs');
+var wb = XLSX.utils.table_to_book(tbl);
+```
+
+Note: `XLSX.read` can handle HTML represented as strings.
+
 ### Formulae Output

 `XLSX.utils.sheet_to_formulae` generates an array of commands that represent
--- a/bits/39_xlsbiff.js
+++ b/bits/39_xlsbiff.js
@ -158,7 +158,7 @@ function parse_BOF(blob, length) {
 function parse_InterfaceHdr(blob, length) {
 	if(length === 0) return 0x04b0;
 	var q;
-	if((q=blob.read_shift(2))!==0x04b0) throw new Error("InterfaceHdr codePage " + q);
+	if((q=blob.read_shift(2))!==0x04b0){}
 	return 0x04b0;
 }

--- a/bits/79_html.js
+++ b/bits/79_html.js
@ -33,3 +33,35 @@ function parse_html(str/*:string*/, opts)/*:Workbook*/ {
 	ws['!ref'] = encode_range(range);
 	return o;
 }
+
+function parse_dom_table(table/*:HTMLElement*/, opts/*:?any*/)/*:Worksheet*/ {
+	var ws/*:Worksheet*/ = ({}/*:any*/);
+	var rows = table.getElementsByTagName('tr');
+	var range = {s:{r:0,c:0},e:{r:rows.length - 1,c:0}};
+	var merges = [], midx = 0;
+	var R = 0, _C = 0, C = 0, RS = 0, CS = 0;
+	for(; R < rows.length; ++R) {
+		var row = rows[R];
+		var elts = row.children;
+		for(_C = C = 0; _C < elts.length; ++_C) {
+			var elt = elts[_C], v = elts[_C].innerText;
+			for(midx = 0; midx < merges.length; ++midx) {
+				var m = merges[midx];
+				if(m.s.c == C && m.s.r <= R && R <= m.e.r) { C = m.e.c+1; midx = -1; }
+			}
+			/* 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}});
+			var o = {t:'s', v:v};
+			if(!isNaN(Number(v))) o = {t:'n', v:Number(v)};
+			ws[encode_cell({c:C, r:R})] = o;
+			C += CS;
+		}
+	}
+	ws['!merges'] = merges;
+	return ws;
+}
+
+function table_to_book(table/*:HTMLElement*/, opts/*:?any*/)/*:Workbook*/ {
+	return sheet_to_workbook(parse_dom_table(table, opts), opts);
+}
--- a/bits/90_utils.js
+++ b/bits/90_utils.js
@ -240,6 +240,8 @@ var utils = {
 	make_json: sheet_to_json,
 	make_formulae: sheet_to_formulae,
 	aoa_to_sheet: aoa_to_sheet,
+	table_to_sheet: parse_dom_table,
+	table_to_book: table_to_book,
 	sheet_to_csv: sheet_to_csv,
 	sheet_to_json: sheet_to_json,
 	sheet_to_formulae: sheet_to_formulae,
--- a/book.json
+++ b/book.json
@ -0,0 +1,27 @@
+{
+	"root": "./misc/docs",
+	"title": "SheetJS js-xlsx",
+	"author": "sheetjs",
+	"gitbook": "3.2.2",
+	"plugins": ["anchorjs", "ga", "sidebar-ad", "-sharing", "advanced-emoji"],
+	"pluginsConfig": {
+		"anchorjs": {
+			"icon": "#",
+			"placement": "left",
+			"visible": "always"
+		},
+		"ga": {
+			"token": "UA-36810333-1"
+		},
+		"sidebar-ad": {
+			"imageUrl": "http://oss.sheetjs.com/assets/img/logo.png",
+			"url": "http://sheetjs.com"
+		},
+		"theme-default": {
+			"showLevel": false,
+			"styles": {
+				"website": "style.css"
+			}
+		}
+	}
+}
--- a/docbits/20_import.md
+++ b/docbits/20_import.md
@ -11,6 +11,13 @@ var workbook = XLSX.readFile('test.xlsx');
 /* DO SOMETHING WITH workbook HERE */
 ```

+- Browser DOM Table element:
+
+```js
+var worksheet = XLSX.utils.table_to_book(document.getElementById('tableau'));
+/* DO SOMETHING WITH workbook HERE */
+```
+
 - ajax (for a more complete example that works in older browsers, check the demo
  at <http://oss.sheetjs.com/js-xlsx/ajax.html>):

--- a/docbits/82_util.md
+++ b/docbits/82_util.md
@ -38,6 +38,33 @@ var ws = XLSX.utils.aoa_to_sheet([
 ]);
 ```

+### HTML Table Input
+
+`XLSX.utils.table_to_sheet` takes a table DOM element and returns a worksheet
+resembling the input table.  Numbers are parsed.  All other data will be stored
+as strings.
+
+`XLSX.utils.table_to_book` produces a minimal workbook based on the worksheet.
+
+To generate the example sheet, start with the HTML table:
+
+```html
+<table id="sheetjs">
+<tr><td>S</td><td>h</td><td>e</td><td>e</td><td>t</td><td>J</td><td>S</td></tr>
+<tr><td>1</td><td>2</td><td>3</td><td>4</td><td>5</td><td>6</td><td>7</td></tr>
+<tr><td>2</td><td>3</td><td>4</td><td>5</td><td>6</td><td>7</td><td>8</td></tr>
+</table>
+```
+
+To process the table:
+
+```js
+var tbl = document.getElementById('sheetjs');
+var wb = XLSX.utils.table_to_book(tbl);
+```
+
+Note: `XLSX.read` can handle HTML represented as strings.
+
 ### Formulae Output

 `XLSX.utils.sheet_to_formulae` generates an array of commands that represent
--- a/misc/docs/README.md
+++ b/misc/docs/README.md
@ -0,0 +1 @@
+../../README.md
--- a/misc/docs/SUMMARY.md
+++ b/misc/docs/SUMMARY.md
@ -0,0 +1,55 @@
+# Summary
+
+- [xlsx](README.md#xlsx)
+- [Installation](README.md#installation)
+  * [JS Ecosystem Demos](README.md#js-ecosystem-demos)
+  * [Optional Modules](README.md#optional-modules)
+  * [ECMAScript 5 Compatibility](README.md#ecmascript-5-compatibility)
+- [Parsing Workbooks](README.md#parsing-workbooks)
+- [Working with the Workbook](README.md#working-with-the-workbook)
+- [Writing Workbooks](README.md#writing-workbooks)
+- [Interface](README.md#interface)
+  * [Parsing functions](README.md#parsing-functions)
+  * [Writing functions](README.md#writing-functions)
+  * [Utilities](README.md#utilities)
+- [Workbook / Worksheet / Cell Object Description](README.md#workbook--worksheet--cell-object-description)
+  * [General Structures](README.md#general-structures)
+  * [Cell Object](README.md#cell-object)
+    + [Data Types](README.md#data-types)
+    + [Dates](README.md#dates)
+  * [Worksheet Object](README.md#worksheet-object)
+  * [Chartsheet Object](README.md#chartsheet-object)
+  * [Workbook Object](README.md#workbook-object)
+  * [Document Features](README.md#document-features)
+    + [Formulae](README.md#formulae)
+    + [Column Properties](README.md#column-properties)
+    + [Hyperlinks](README.md#hyperlinks)
+- [Parsing Options](README.md#parsing-options)
+  * [Input Type](README.md#input-type)
+  * [Guessing File Type](README.md#guessing-file-type)
+- [Writing Options](README.md#writing-options)
+  * [Supported Output Formats](README.md#supported-output-formats)
+  * [Output Type](README.md#output-type)
+- [Utility Functions](README.md#utility-functions)
+  * [Array of Arrays Input](README.md#array-of-arrays-input)
+  * [HTML Table Input](README.md#html-table-input)
+  * [Formulae Output](README.md#formulae-output)
+  * [CSV and general DSV Output](README.md#csv-and-general-dsv-output)
+  * [JSON](README.md#json)
+- [File Formats](README.md#file-formats)
+  * [Excel 2007+ XML (XLSX/XLSM)](README.md#excel-2007-xml-xlsxxlsm)
+  * [Excel 2.0-95 (BIFF2/BIFF3/BIFF4/BIFF5)](README.md#excel-20-95-biff2biff3biff4biff5)
+  * [Excel 97-2004 Binary (BIFF8)](README.md#excel-97-2004-binary-biff8)
+  * [Excel 2003-2004 (SpreadsheetML)](README.md#excel-2003-2004-spreadsheetml)
+  * [Excel 2007+ Binary (XLSB, BIFF12)](README.md#excel-2007-binary-xlsb-biff12)
+  * [OpenDocument Spreadsheet (ODS/FODS) and Uniform Office Spreadsheet (UOS1/2)](README.md#opendocument-spreadsheet-odsfods-and-uniform-office-spreadsheet-uos12)
+  * [dBASE and Visual FoxPro (DBF)](README.md#dbase-and-visual-foxpro-dbf)
+  * [Comma-Separated Values](README.md#comma-separated-values)
+  * [HTML](README.md#html)
+- [Testing](README.md#testing)
+  * [Tested Environments](README.md#tested-environments)
+  * [Test Files](README.md#test-files)
+- [Contributing](README.md#contributing)
+- [License](README.md#license)
+- [References](README.md#references)
+- [Badges](README.md#badges)
--- a/misc/docs/formats.png
+++ b/misc/docs/formats.png
@ -0,0 +1 @@
+../../formats.png
--- a/misc/docs/style.css
+++ b/misc/docs/style.css
@ -0,0 +1,19 @@
+a.anchorjs-link {
+    color: rgba(65, 131, 196, 0.1);
+    font-weight: 400;
+    text-decoration: none;
+    transition: color 100ms ease-out;
+    z-index: 999;
+}
+
+a.anchorjs-link:hover {
+    color: rgba(65, 131, 196, 1);
+}
+
+.gitbook-link {
+    display: none !important;
+}
+
+#book-search-input {
+    display: none !important;
+}
--- a/xlsx.flow.js
+++ b/xlsx.flow.js
@ -3859,7 +3859,7 @@ function parse_BOF(blob, length) {
 function parse_InterfaceHdr(blob, length) {
 	if(length === 0) return 0x04b0;
 	var q;
-	if((q=blob.read_shift(2))!==0x04b0) throw new Error("InterfaceHdr codePage " + q);
+	if((q=blob.read_shift(2))!==0x04b0){}
 	return 0x04b0;
 }

@ -13545,6 +13545,38 @@ function parse_html(str/*:string*/, opts)/*:Workbook*/ {
 	ws['!ref'] = encode_range(range);
 	return o;
 }
+
+function parse_dom_table(table/*:HTMLElement*/, opts/*:?any*/)/*:Worksheet*/ {
+	var ws/*:Worksheet*/ = ({}/*:any*/);
+	var rows = table.getElementsByTagName('tr');
+	var range = {s:{r:0,c:0},e:{r:rows.length - 1,c:0}};
+	var merges = [], midx = 0;
+	var R = 0, _C = 0, C = 0, RS = 0, CS = 0;
+	for(; R < rows.length; ++R) {
+		var row = rows[R];
+		var elts = row.children;
+		for(_C = C = 0; _C < elts.length; ++_C) {
+			var elt = elts[_C], v = elts[_C].innerText;
+			for(midx = 0; midx < merges.length; ++midx) {
+				var m = merges[midx];
+				if(m.s.c == C && m.s.r <= R && R <= m.e.r) { C = m.e.c+1; midx = -1; }
+			}
+			/* 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}});
+			var o = {t:'s', v:v};
+			if(!isNaN(Number(v))) o = {t:'n', v:Number(v)};
+			ws[encode_cell({c:C, r:R})] = o;
+			C += CS;
+		}
+	}
+	ws['!merges'] = merges;
+	return ws;
+}
+
+function table_to_book(table/*:HTMLElement*/, opts/*:?any*/)/*:Workbook*/ {
+	return sheet_to_workbook(parse_dom_table(table, opts), opts);
+}
 var parse_content_xml = (function() {

 	var parse_text_p = function(text, tag) {
@ -14762,6 +14794,8 @@ var utils = {
 	make_json: sheet_to_json,
 	make_formulae: sheet_to_formulae,
 	aoa_to_sheet: aoa_to_sheet,
+	table_to_sheet: parse_dom_table,
+	table_to_book: table_to_book,
 	sheet_to_csv: sheet_to_csv,
 	sheet_to_json: sheet_to_json,
 	sheet_to_formulae: sheet_to_formulae,
--- a/xlsx.js
+++ b/xlsx.js
@ -3805,7 +3805,7 @@ function parse_BOF(blob, length) {
 function parse_InterfaceHdr(blob, length) {
 	if(length === 0) return 0x04b0;
 	var q;
-	if((q=blob.read_shift(2))!==0x04b0) throw new Error("InterfaceHdr codePage " + q);
+	if((q=blob.read_shift(2))!==0x04b0){}
 	return 0x04b0;
 }

@ -13486,6 +13486,38 @@ function parse_html(str, opts) {
 	ws['!ref'] = encode_range(range);
 	return o;
 }
+
+function parse_dom_table(table, opts) {
+	var ws = ({});
+	var rows = table.getElementsByTagName('tr');
+	var range = {s:{r:0,c:0},e:{r:rows.length - 1,c:0}};
+	var merges = [], midx = 0;
+	var R = 0, _C = 0, C = 0, RS = 0, CS = 0;
+	for(; R < rows.length; ++R) {
+		var row = rows[R];
+		var elts = row.children;
+		for(_C = C = 0; _C < elts.length; ++_C) {
+			var elt = elts[_C], v = elts[_C].innerText;
+			for(midx = 0; midx < merges.length; ++midx) {
+				var m = merges[midx];
+				if(m.s.c == C && m.s.r <= R && R <= m.e.r) { C = m.e.c+1; midx = -1; }
+			}
+			/* 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}});
+			var o = {t:'s', v:v};
+			if(!isNaN(Number(v))) o = {t:'n', v:Number(v)};
+			ws[encode_cell({c:C, r:R})] = o;
+			C += CS;
+		}
+	}
+	ws['!merges'] = merges;
+	return ws;
+}
+
+function table_to_book(table, opts) {
+	return sheet_to_workbook(parse_dom_table(table, opts), opts);
+}
 var parse_content_xml = (function() {

 	var parse_text_p = function(text, tag) {
@ -14694,6 +14726,8 @@ var utils = {
 	make_json: sheet_to_json,
 	make_formulae: sheet_to_formulae,
 	aoa_to_sheet: aoa_to_sheet,
+	table_to_sheet: parse_dom_table,
+	table_to_book: table_to_book,
 	sheet_to_csv: sheet_to_csv,
 	sheet_to_json: sheet_to_json,
 	sheet_to_formulae: sheet_to_formulae,