forked from sheetjs/docs.sheetjs.com
188 lines
4.7 KiB
Markdown
188 lines
4.7 KiB
Markdown
|
---
|
||
|
title: Perl + JE
|
||
|
pagination_prev: demos/cli
|
||
|
pagination_next: demos/clipboard
|
||
|
---
|
||
|
|
||
|
:::warning
|
||
|
|
||
|
In a production application, it is strongly recommended to use a binding for a
|
||
|
C engine like [`JavaScript::Duktape`](/docs/demos/engines/duktape)
|
||
|
|
||
|
:::
|
||
|
|
||
|
JE is a pure-Perl JavaScript engine.
|
||
|
|
||
|
The [Extendscript build](/docs/getting-started/installation/extendscript) can be
|
||
|
parsed and evaluated in a JE context.
|
||
|
|
||
|
|
||
|
## Integration Details
|
||
|
|
||
|
The engine deviates from ES3. Modifying prototypes can fix some behavior:
|
||
|
|
||
|
```js
|
||
|
/* String#charCodeAt is missing */
|
||
|
var string = "";
|
||
|
for(var i = 0; i < 256; ++i) string += String.fromCharCode(i);
|
||
|
String.prototype.charCodeAt = function(n) {
|
||
|
var result = string.indexOf(this.charAt(n));
|
||
|
if(result == -1) throw this.charAt(n);
|
||
|
return result;
|
||
|
};
|
||
|
|
||
|
/* workaround for String split bug */
|
||
|
Number.prototype.charCodeAt = function(n) { return this + 48; };
|
||
|
|
||
|
/* String#match bug with empty results */
|
||
|
String.prototype.old_match = String.prototype.match;
|
||
|
String.prototype.match = function(p) {
|
||
|
var result = this.old_match(p);
|
||
|
return (Array.isArray(result) && result.length == 0) ? null : result;
|
||
|
};
|
||
|
```
|
||
|
|
||
|
When loading the ExtendScript build, the BOM must be removed:
|
||
|
|
||
|
```perl
|
||
|
## Load SheetJS source
|
||
|
my $src = read_file('xlsx.extendscript.js', { binmode => ':raw' });
|
||
|
$src =~ s/^\xEF\xBB\xBF//; ## remove UTF8 BOM
|
||
|
my $XLSX = $je->eval($src);
|
||
|
```
|
||
|
|
||
|
### Reading Files
|
||
|
|
||
|
Data should be passed as Base64 strings:
|
||
|
|
||
|
```perl
|
||
|
use File::Slurp;
|
||
|
use MIME::Base64 qw( encode_base64 );
|
||
|
|
||
|
## Set up conversion method
|
||
|
$je->eval(<<'EOF');
|
||
|
function sheetjsparse(data) { try {
|
||
|
return XLSX.read(String(data), {type: "base64", WTF:1});
|
||
|
} catch(e) { return String(e); } }
|
||
|
EOF
|
||
|
|
||
|
## Read file
|
||
|
my $raw_data = encode_base64(read_file($ARGV[0], { binmode => ':raw' }), "");
|
||
|
|
||
|
## Call method with data
|
||
|
$return_val = $je->method(sheetjsparse => $raw_data);
|
||
|
```
|
||
|
|
||
|
### Writing Files
|
||
|
|
||
|
Due to bugs in data interchange, it is strongly recommended to use a simple
|
||
|
format like `.fods`:
|
||
|
|
||
|
```perl
|
||
|
use File::Slurp;
|
||
|
|
||
|
## Set up conversion method
|
||
|
$je->eval(<<'EOF');
|
||
|
function sheetjswrite(wb) { try {
|
||
|
return XLSX.write(wb, { WTF:1, bookType: "fods", type: "string" });
|
||
|
} catch(e) { return String(e); } }
|
||
|
EOF
|
||
|
|
||
|
## Generate file
|
||
|
my $fods = $je->method(sheetjswrite => $workbook);
|
||
|
|
||
|
## Write to filesystem
|
||
|
write_file("SheetJE.fods", $fods);
|
||
|
```
|
||
|
|
||
|
## Complete Example
|
||
|
|
||
|
:::note
|
||
|
|
||
|
This demo was tested on 2023 February 12 against JE 0.066
|
||
|
|
||
|
:::
|
||
|
|
||
|
1) Install `JE` through CPAN:
|
||
|
|
||
|
```bash
|
||
|
cpan install JE
|
||
|
```
|
||
|
|
||
|
2) Download the [ExtendScript build](/docs/getting-started/installation/extendscript):
|
||
|
|
||
|
```bash
|
||
|
curl -LO https://cdn.sheetjs.com/xlsx-latest/package/dist/xlsx.extendscript.js
|
||
|
```
|
||
|
|
||
|
3) Save the following to `SheetJE.pl`:
|
||
|
|
||
|
```perl title="SheetJE.pl"
|
||
|
use JE;
|
||
|
use File::Slurp;
|
||
|
use MIME::Base64 qw( encode_base64 );
|
||
|
|
||
|
## Initialize
|
||
|
say STDERR "Initializing Engine";
|
||
|
my $je = new JE;
|
||
|
$je->eval("var global = (function(){ return this; }).call(null);");
|
||
|
$je->eval(<<'EOF');
|
||
|
Number.prototype.charCodeAt = function(n) { return this + 48; };
|
||
|
var string = ""; for(var i = 0; i < 256; ++i) string += String.fromCharCode(i);
|
||
|
String.prototype.charCodeAt = function(n) {
|
||
|
var result = string.indexOf(this.charAt(n));
|
||
|
if(result == -1) throw this.charAt(n);
|
||
|
return result;
|
||
|
};
|
||
|
String.prototype.old_match = String.prototype.match;
|
||
|
String.prototype.match = function(p) {
|
||
|
var result = this.old_match(p);
|
||
|
return (Array.isArray(result) && result.length == 0) ? null : result;
|
||
|
};
|
||
|
EOF
|
||
|
|
||
|
## Load SheetJS source
|
||
|
say STDERR "Loading SheetJS Library";
|
||
|
my $src = read_file('xlsx.extendscript.js', { binmode => ':raw' });
|
||
|
$src =~ s/^\xEF\xBB\xBF//;
|
||
|
my $XLSX = $je->eval($src);
|
||
|
|
||
|
## Set up conversion method
|
||
|
$je->eval(<<'EOF');
|
||
|
function sheetjsparse(data) { try {
|
||
|
return XLSX.read(String(data), {type: "base64", WTF:1});
|
||
|
} catch(e) { return String(e); } }
|
||
|
function sheetjscsv(wb) { try {
|
||
|
var ws = wb.Sheets[wb.SheetNames[0]];
|
||
|
return XLSX.utils.sheet_to_csv(ws);
|
||
|
} catch(e) { return String(e); } }
|
||
|
function sheetjswrite(wb) { try {
|
||
|
return XLSX.write(wb, { WTF:1, bookType: "fods", type: "string" });
|
||
|
} catch(e) { return String(e); } }
|
||
|
EOF
|
||
|
|
||
|
## Read file
|
||
|
say STDERR "Parsing " . $ARGV[0];
|
||
|
my $raw_data = encode_base64(read_file($ARGV[0], { binmode => ':raw' }), "");
|
||
|
$workbook = $je->method(sheetjsparse => $raw_data);
|
||
|
|
||
|
## Convert to CSV
|
||
|
say STDERR "Converting to CSV";
|
||
|
my $csv_data = $je->method(sheetjscsv => $workbook);
|
||
|
print $csv_data;
|
||
|
|
||
|
## Write to SheetJE.fods
|
||
|
say STDERR "Writing to SheetJE.fods";
|
||
|
my $fods = $je->method(sheetjswrite => $workbook);
|
||
|
write_file("SheetJE.fods", $fods);
|
||
|
```
|
||
|
|
||
|
4) Download a test file and run:
|
||
|
|
||
|
```bash
|
||
|
curl -LO https://sheetjs.com/data/cd.xls
|
||
|
perl SheetJE.pl cd.xls
|
||
|
```
|
||
|
|
||
|
After a short wait, the contents will be displayed in CSV form. It will also
|
||
|
write a file `SheetJE.fods` that can be opened in LibreOffice.
|