Configuration

EDocIAS configuration is specified in the config.php file.

Below is a sample version of config.php, much of copied from my local setup.

<?php
// Location of a temporary directory that will be used when processing files
$tempDir = "/tmp";

// Array of directories to scan
// Although this example lists a single directory, more than one directory can
// be specified.
$dirs = array ( "/Users/cknudsen/Documents" );

// Array of folder names to skip
$skipFolders = array (
  'My Music', // not interested in my MP3/AAC files being searchable
  'My Pictures', // not interested in searching for pictures (but maybe you are)
  'Backups', // contains db backups in tar.gz format
  'GnuCash',
  'GmailBackup',
);

// Database settings
$db_host = 'localhost';
$db_login = 'mydatabasename';
$db_password = 'mydatabaselogin';
$db_database = 'mydbpwd';
// At this point, only 'mysql' has been tested, but other databases should
// also work if you create the correct SQL for creating the edm_doc table.
// See dbi4php.php for supported db types (oracle, postgresql, ms sql server, etc.)
$db_type = 'mysql';
$db_persistent = '1';
$phpdbiVerbose = true; // show db/sql errors to end user?

// Location of various tools for converting binary files to plain text
// %FILE% will be replaced with the full path to the binary file.
// Note that icons will be based on the 'type' and should be in the
// "icons" subdirectory.  For example, the "image/jpeg" mime type will
// use "icons/image-icon.png" icon.
$fileSpecs = array (
  array (
    "type" => 'text',
    "mime" => 'text/plain',
    "regex" => 'txt',
    "command" => 'cp "%FILE%" textout.txt' ),
  array (
    "type" => 'image',
    "mime" => 'image/jpeg',
    "regex" => '(jpg|jpeg)',
    "command" => '/usr/local/bin/tesseract "%FILE%" textout' ),
  array (
    "type" => 'image',
    "mime" => 'image/png',
    "regex" => 'png',
    "command" => '/usr/local/bin/tesseract "%FILE%" textout' ),
  array (
    "type" => 'image',
    "mime" => 'image/gif',
    "regex" => 'gif',
    "command" => '/usr/local/bin/tesseract "%FILE%" textout' ),
  array (
    "type" => 'pdf',
    "mime" => 'application/pdf',
    "regex" => 'pdf',
    "command" => '/opt/local/bin/xpdf-pdftotext "%FILE%" textout.txt' ),
  array (
    "type" => 'word',
    "mime" => 'application/ms-word',
    "regex" => 'doc',
    "command" => '/usr/local/bin/antiword "%FILE%" > textout.txt' ),
  array (
    "type" => 'excel',
    "mime" => 'application/ms-excel',
    "regex" => 'xls',
    "command" =>
      '/usr/bin/perl /Applications/MAMP/htdocs/edm/xls2txt.pl "%FILE%" textout.txt' ),

);

?>