tonyair/silverstripe-textextraction
1
0
Fork 0
mirror of https://github.com/silverstripe/silverstripe-textextraction synced 2024-10-22 11:06:00 +02:00
Code Issues Projects Releases Wiki Activity

fix(PDFTextExtractor): Added support for Windows, but only if 'binary_location' is defined. Updated documentation to inform the user of this.

Browse Source
This commit is contained in:
Jake Bentvelzen 2016-05-13 15:07:33 +10:00
parent bde4cf4536
commit 75ffe7b56a
2 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -89,7 +89,7 @@ FileTextCache_SSCache:
PDFs require special handling, for example through the [XPDF](http://www.foolabs.com/xpdf/) PDFs require special handling, for example through the [XPDF](http://www.foolabs.com/xpdf/)
commandline utility. Follow their installation instructions, its presence will be automatically commandline utility. Follow their installation instructions, its presence will be automatically
detected. You can optionally set the binary path in `mysite/_config/config.yml`: detected for *nix operating systems. You can optionally set the binary path (required for Windows) in `mysite/_config/config.yml`
```yml ```yml
PDFTextExtractor: PDFTextExtractor:

7
code/extractors/PDFTextExtractor.php
View File

@ -71,6 +71,9 @@ class PDFTextExtractor extends FileTextExtractor
if(file_exists($path)) { if(file_exists($path)) {
return $path; return $path;
} }
if (file_exists($path.'.exe')) {
return $path.'.exe';
}
} }
// Not found // Not found
@ -100,6 +103,10 @@ class PDFTextExtractor extends FileTextExtractor
} }
exec(sprintf('%s %s - 2>&1', $this->bin('pdftotext'), escapeshellarg($path)), $content, $err); exec(sprintf('%s %s - 2>&1', $this->bin('pdftotext'), escapeshellarg($path)), $content, $err);
if ($err) { if ($err) {
if (!is_array($err) && $err == 1) {
// For Windows compatibility
$err = $content;
}
throw new FileTextExtractor_Exception(sprintf( throw new FileTextExtractor_Exception(sprintf(
'PDFTextExtractor->getContent() failed for %s: %s', 'PDFTextExtractor->getContent() failed for %s: %s',
$path, $path,