README cleanup in anticipation of node fetch
parent
3cbe83c855
commit
6c436ae277
@ -1,21 +1,21 @@
|
||||
var CT_VBA = "application/vnd.ms-office.vbaProject";
|
||||
function make_vba_xls(cfb/*:CFBContainer*/) {
|
||||
var newcfb = CFB.utils.cfb_new({root:"R"});
|
||||
cfb.FullPaths.forEach(function(p, i) {
|
||||
if(p.slice(-1) === "/" || !p.match(/_VBA_PROJECT_CUR/)) return;
|
||||
var newpath = p.replace(/^[^\/]*/,"R").replace(/\/_VBA_PROJECT_CUR\u0000*/, "");
|
||||
CFB.utils.cfb_add(newcfb, newpath, cfb.FileIndex[i].content);
|
||||
});
|
||||
return CFB.write(newcfb);
|
||||
function make_vba_xls(cfb) {
|
||||
var newcfb = CFB.utils.cfb_new({ root: "R" });
|
||||
cfb.FullPaths.forEach(function(p, i) {
|
||||
if (p.slice(-1) === "/" || !p.match(/_VBA_PROJECT_CUR/))
|
||||
return;
|
||||
var newpath = p.replace(/^[^\/]*/, "R").replace(/\/_VBA_PROJECT_CUR\u0000*/, "");
|
||||
CFB.utils.cfb_add(newcfb, newpath, cfb.FileIndex[i].content);
|
||||
});
|
||||
return CFB.write(newcfb);
|
||||
}
|
||||
|
||||
function fill_vba_xls(cfb/*:CFBContainer*/, vba/*:CFBContainer*/)/*:void*/ {
|
||||
vba.FullPaths.forEach(function(p, i) {
|
||||
if(i == 0) return;
|
||||
var newpath = p.replace(/[^\/]*[\/]/, "/_VBA_PROJECT_CUR/");
|
||||
if(newpath.slice(-1) !== "/") CFB.utils.cfb_add(cfb, newpath, vba.FileIndex[i].content);
|
||||
});
|
||||
function fill_vba_xls(cfb, vba) {
|
||||
vba.FullPaths.forEach(function(p, i) {
|
||||
if (i == 0)
|
||||
return;
|
||||
var newpath = p.replace(/[^\/]*[\/]/, "/_VBA_PROJECT_CUR/");
|
||||
if (newpath.slice(-1) !== "/")
|
||||
CFB.utils.cfb_add(cfb, newpath, vba.FileIndex[i].content);
|
||||
});
|
||||
}
|
||||
|
||||
var VBAFMTS = [ "xlsb", "xlsm", "xlam", "biff8", "xla" ];
|
||||
|
||||
var VBAFMTS = ["xlsb", "xlsm", "xlam", "biff8", "xla"];
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -1,67 +0,0 @@
|
||||
### Streaming Read
|
||||
|
||||
<details>
|
||||
<summary><b>Why is there no Streaming Read API?</b> (click to show)</summary>
|
||||
|
||||
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 storage info 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.
|
||||
|
||||
</details>
|
||||
|
||||
When dealing with Readable Streams, the easiest approach is to buffer the stream
|
||||
and process the whole thing at the end. This can be done with a temporary file
|
||||
or by explicitly concatenating the stream:
|
||||
|
||||
<details>
|
||||
<summary><b>Explicitly concatenating streams</b> (click to show)</summary>
|
||||
|
||||
```js
|
||||
var fs = require('fs');
|
||||
var XLSX = require('xlsx');
|
||||
function process_RS(stream/*:ReadStream*/, cb/*:(wb:Workbook)=>void*/)/*:void*/{
|
||||
var buffers = [];
|
||||
stream.on('data', function(data) { buffers.push(data); });
|
||||
stream.on('end', function() {
|
||||
var buffer = Buffer.concat(buffers);
|
||||
var workbook = XLSX.read(buffer, {type:"buffer"});
|
||||
|
||||
/* DO SOMETHING WITH workbook IN THE CALLBACK */
|
||||
cb(workbook);
|
||||
});
|
||||
}
|
||||
```
|
||||
|
||||
More robust solutions are available using modules like `concat-stream`.
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><b>Writing to filesystem first</b> (click to show)</summary>
|
||||
|
||||
This example uses [`tempfile`](https://npm.im/tempfile) to generate file names:
|
||||
|
||||
```js
|
||||
var fs = require('fs'), tempfile = require('tempfile');
|
||||
var XLSX = require('xlsx');
|
||||
function process_RS(stream/*:ReadStream*/, cb/*:(wb:Workbook)=>void*/)/*:void*/{
|
||||
var fname = tempfile('.sheetjs');
|
||||
console.log(fname);
|
||||
var ostream = fs.createWriteStream(fname);
|
||||
stream.pipe(ostream);
|
||||
ostream.on('finish', function() {
|
||||
var workbook = XLSX.readFile(fname);
|
||||
fs.unlinkSync(fname);
|
||||
|
||||
/* DO SOMETHING WITH workbook IN THE CALLBACK */
|
||||
cb(workbook);
|
||||
});
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
@ -0,0 +1,182 @@
|
||||
### Processing JSON and JS Data
|
||||
|
||||
JSON and JS data tend to represent single worksheets. This section will use a
|
||||
few utility functions to generate workbooks:
|
||||
|
||||
_Create a new Worksheet_
|
||||
|
||||
```js
|
||||
var workbook = XLSX.utils.book_new();
|
||||
```
|
||||
|
||||
The `book_new` utility function creates an empty workbook with no worksheets.
|
||||
|
||||
|
||||
_Append a Worksheet to a Workbook_
|
||||
|
||||
```js
|
||||
XLSX.utils.book_append_sheet(workbook, worksheet, sheet_name);
|
||||
```
|
||||
|
||||
The `book_append_sheet` utility function appends a worksheet to the workbook.
|
||||
The third argument specifies the desired worksheet name. Multiple worksheets can
|
||||
be added to a workbook by calling the function multiple times.
|
||||
|
||||
|
||||
#### API
|
||||
|
||||
_Create a worksheet from an array of arrays of JS values_
|
||||
|
||||
```js
|
||||
var worksheet = XLSX.utils.aoa_to_sheet(aoa, opts);
|
||||
```
|
||||
|
||||
The `aoa_to_sheet` utility function walks an "array of arrays" in row-major
|
||||
order, generating a worksheet object. The following snippet generates a sheet
|
||||
with cell `A1` set to the string `A1`, cell `B1` set to `B2`, etc:
|
||||
|
||||
```js
|
||||
var worksheet = XLSX.utils.aoa_to_sheet([
|
||||
["A1", "B1", "C1"],
|
||||
["A2", "B2", "C2"],
|
||||
["A3", "B3", "C3"]
|
||||
])
|
||||
```
|
||||
|
||||
["Array of Arrays Input"](#array-of-arrays-input) describes the function and the
|
||||
optional `opts` argument in more detail.
|
||||
|
||||
|
||||
_Create a worksheet from an array of JS objects_
|
||||
|
||||
```js
|
||||
var worksheet = XLSX.utils.json_to_sheet(jsa, opts);
|
||||
```
|
||||
|
||||
The `json_to_sheet` utility function walks an array of JS objects in order,
|
||||
generating a worksheet object. By default, it will generate a header row and
|
||||
one row per object in the array. The optional `opts` argument has settings to
|
||||
control the column order and header output.
|
||||
|
||||
["Array of Objects Input"](#array-of-arrays-input) describes the function and
|
||||
the optional `opts` argument in more detail.
|
||||
|
||||
#### Examples
|
||||
|
||||
["Zen of SheetJS"](#the-zen-of-sheetjs) contains a detailed example "Get Data
|
||||
from a JSON Endpoint and Generate a Workbook"
|
||||
|
||||
The [`database` demo](/demos/database/) includes examples of working with
|
||||
databases and query results.
|
||||
|
||||
### Processing HTML Tables
|
||||
|
||||
#### API
|
||||
|
||||
_Create a worksheet by scraping an HTML TABLE in the page_
|
||||
|
||||
```js
|
||||
var worksheet = XLSX.utils.table_to_sheet(dom_element, opts);
|
||||
```
|
||||
|
||||
The `table_to_sheet` utility function takes a DOM TABLE element and iterates
|
||||
through the rows to generate a worksheet. The `opts` argument is optional.
|
||||
["HTML Table Input"](#html-table-input) describes the function in more detail.
|
||||
|
||||
|
||||
|
||||
_Create a workbook by scraping an HTML TABLE in the page_
|
||||
|
||||
```js
|
||||
var workbook = XLSX.utils.table_to_book(dom_element, opts);
|
||||
```
|
||||
|
||||
The `table_to_book` utility function follows the same logic as `table_to_sheet`.
|
||||
After generating a worksheet, it creates a blank workbook and appends the
|
||||
spreadsheet.
|
||||
|
||||
The options argument supports the same options as `table_to_sheet`, with the
|
||||
addition of a `sheet` property to control the worksheet name. If the property
|
||||
is missing or no options are specified, the default name `Sheet1` is used.
|
||||
|
||||
#### Examples
|
||||
|
||||
Here are a few common scenarios (click on each subtitle to see the code):
|
||||
|
||||
<details>
|
||||
<summary><b>HTML TABLE element in a webpage</b> (click to show)</summary>
|
||||
|
||||
```html
|
||||
<!-- include the standalone script and shim. this uses the UNPKG CDN -->
|
||||
<script src="https://unpkg.com/xlsx/dist/shim.min.js"></script>
|
||||
<script src="https://unpkg.com/xlsx/dist/xlsx.full.min.js"></script>
|
||||
|
||||
<!-- example table with id attribute -->
|
||||
<table id="tableau">
|
||||
<tr><td>Sheet</td><td>JS</td></tr>
|
||||
<tr><td>12345</td><td>67</td></tr>
|
||||
</table>
|
||||
|
||||
<!-- this block should appear after the table HTML and the standalone script -->
|
||||
<script type="text/javascript">
|
||||
var workbook = XLSX.utils.table_to_book(document.getElementById("tableau"));
|
||||
|
||||
/* DO SOMETHING WITH workbook HERE */
|
||||
</script>
|
||||
```
|
||||
|
||||
Multiple tables on a web page can be converted to individual worksheets:
|
||||
|
||||
```js
|
||||
/* create new workbook */
|
||||
var workbook = XLSX.utils.book_new();
|
||||
|
||||
/* convert table "table1" to worksheet named "Sheet1" */
|
||||
var sheet1 = XLSX.utils.table_to_sheet(document.getElementById("table1"));
|
||||
XLSX.utils.book_append_sheet(workbook, sheet1, "Sheet1");
|
||||
|
||||
/* convert table "table2" to worksheet named "Sheet2" */
|
||||
var sheet2 = XLSX.utils.table_to_sheet(document.getElementById("table2"));
|
||||
XLSX.utils.book_append_sheet(workbook, sheet2, "Sheet2");
|
||||
|
||||
/* workbook now has 2 worksheets */
|
||||
```
|
||||
|
||||
Alternatively, the HTML code can be extracted and parsed:
|
||||
|
||||
```js
|
||||
var htmlstr = document.getElementById("tableau").outerHTML;
|
||||
var workbook = XLSX.read(htmlstr, {type:"string"});
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><b>Chrome/Chromium Extension</b> (click to show)</summary>
|
||||
|
||||
The [`chrome` demo](demos/chrome/) shows a complete example and details the
|
||||
required permissions and other settings.
|
||||
|
||||
In an extension, it is recommended to generate the workbook in a content script
|
||||
and pass the object back to the extension:
|
||||
|
||||
```js
|
||||
/* in the worker script */
|
||||
chrome.runtime.onMessage.addListener(function(msg, sender, cb) {
|
||||
/* pass a message like { sheetjs: true } from the extension to scrape */
|
||||
if(!msg || !msg.sheetjs) return;
|
||||
/* create a new workbook */
|
||||
var workbook = XLSX.utils.book_new();
|
||||
/* loop through each table element */
|
||||
var tables = document.getElementsByTagName("table")
|
||||
for(var i = 0; i < tables.length; ++i) {
|
||||
var worksheet = XLSX.utils.table_to_sheet(tables[i]);
|
||||
XLSX.utils.book_append_sheet(workbook, worksheet, "Table" + i);
|
||||
}
|
||||
/* pass back to the extension */
|
||||
return cb(workbook);
|
||||
});
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,21 @@
|
||||
var CT_VBA = "application/vnd.ms-office.vbaProject";
|
||||
function make_vba_xls(cfb) {
|
||||
var newcfb = CFB.utils.cfb_new({ root: "R" });
|
||||
cfb.FullPaths.forEach(function(p, i) {
|
||||
if (p.slice(-1) === "/" || !p.match(/_VBA_PROJECT_CUR/))
|
||||
return;
|
||||
var newpath = p.replace(/^[^\/]*/, "R").replace(/\/_VBA_PROJECT_CUR\u0000*/, "");
|
||||
CFB.utils.cfb_add(newcfb, newpath, cfb.FileIndex[i].content);
|
||||
});
|
||||
return CFB.write(newcfb);
|
||||
}
|
||||
function fill_vba_xls(cfb, vba) {
|
||||
vba.FullPaths.forEach(function(p, i) {
|
||||
if (i == 0)
|
||||
return;
|
||||
var newpath = p.replace(/[^\/]*[\/]/, "/_VBA_PROJECT_CUR/");
|
||||
if (newpath.slice(-1) !== "/")
|
||||
CFB.utils.cfb_add(cfb, newpath, vba.FileIndex[i].content);
|
||||
});
|
||||
}
|
||||
var VBAFMTS = ["xlsb", "xlsm", "xlam", "biff8", "xla"];
|
||||
@ -0,0 +1,24 @@
|
||||
import * as CFBModule from 'cfb';
|
||||
type CFBType = typeof CFBModule;
|
||||
declare var CFB: CFBType;
|
||||
|
||||
var CT_VBA = "application/vnd.ms-office.vbaProject";
|
||||
function make_vba_xls(cfb: CFBModule.CFB$Container) {
|
||||
var newcfb = CFB.utils.cfb_new({root:"R"});
|
||||
cfb.FullPaths.forEach(function(p, i) {
|
||||
if(p.slice(-1) === "/" || !p.match(/_VBA_PROJECT_CUR/)) return;
|
||||
var newpath = p.replace(/^[^\/]*/,"R").replace(/\/_VBA_PROJECT_CUR\u0000*/, "");
|
||||
CFB.utils.cfb_add(newcfb, newpath, cfb.FileIndex[i].content);
|
||||
});
|
||||
return CFB.write(newcfb);
|
||||
}
|
||||
|
||||
function fill_vba_xls(cfb: CFBModule.CFB$Container, vba: CFBModule.CFB$Container): void {
|
||||
vba.FullPaths.forEach(function(p, i) {
|
||||
if(i == 0) return;
|
||||
var newpath = p.replace(/[^\/]*[\/]/, "/_VBA_PROJECT_CUR/");
|
||||
if(newpath.slice(-1) !== "/") CFB.utils.cfb_add(cfb, newpath, vba.FileIndex[i].content);
|
||||
});
|
||||
}
|
||||
|
||||
var VBAFMTS: string[] = [ "xlsb", "xlsm", "xlam", "biff8", "xla" ];
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue