X-Git-Url: http://wagnertech.de/gitweb/gitweb.cgi/mfinanz.git/blobdiff_plain/8a635325ad558d18a2c6930a67e14f5312e91424..c46898c7a2328d211465818380178e25331d8f3c:/SL/Helper/Csv.pm

diff --git a/SL/Helper/Csv.pm b/SL/Helper/Csv.pm
index 092ba37e8..945758f5d 100644
--- a/SL/Helper/Csv.pm
+++ b/SL/Helper/Csv.pm
@@ -14,6 +14,7 @@ use Rose::Object::MakeMethods::Generic scalar => [ qw(
 ) ];
 
 use SL::Helper::Csv::Dispatcher;
+use SL::Helper::Csv::Error;
 
 # public interface
 
@@ -180,7 +181,7 @@ sub _guess_encoding {
 
 sub _push_error {
   my ($self, @errors) = @_;
-  my @new_errors = ($self->errors, @errors);
+  my @new_errors = ($self->errors, map { SL::Helper::Csv::Error->new(@$_) } @errors);
   $self->_errors(\@new_errors);
 }
 
@@ -203,15 +204,18 @@ SL::Helper::Csv - take care of csv file uploads
     file        => \$::form->{upload_file},
     encoding    => 'utf-8', # undef means utf8
     sep_char    => ',',     # default ';'
-    quote_char  => ''',     # default '"'
-    header      => [qw(id text sellprice word)] # see later
-    profile    => { sellprice => 'sellprice_as_number' }
+    quote_char  => '\'',    # default '"'
+    escape_char => '"',     # default '"'
+    header      => [qw(id text sellprice word)], # see later
+    profile     => { sellprice => 'sellprice_as_number' },
     class       => 'SL::DB::CsvLine',   # if present, map lines to this
-  )
+  );
 
   my $status  = $csv->parse;
   my $hrefs   = $csv->get_data;
-  my @objects = $scv->get_objects;
+  my @objects = $csv->get_objects;
+
+  my @errors  = $csv->errors;
 
 =head1 DESCRIPTION
 
@@ -221,8 +225,31 @@ Text::CSV offeres already good functions to get lines out of a csv file, but in
 most cases you will want those line to be parsed into hashes or even objects,
 so this model just skips ahead and gives you objects.
 
-Encoding autodetection is not easy, and should not be trusted. Try to avoid it
-if possible.
+Its basic assumptions are:
+
+=over 4
+
+=item You do know what you expect to be in that csv file.
+
+This means first and foremost you have knowledge about encoding, number and
+date format, csv parameters such as quoting and separation characters. You also
+know what content will be in that csv and what L<Rose::DB> is responsible for
+it. You provide valid header columns and their mapping to the objects.
+
+=item You do NOT know if the csv provider yields to your expectations.
+
+Stuff that does not work with what you expect should not crash anything, but
+give you a hint what went wrong. As a result, if you remeber to check for
+errors after each step, you should be fine.
+
+=item Data does not make sense. It's just data.
+
+Almost all data imports have some type of constraints. Some data needs to be
+unique, other data needs to be connected to existing data sets. This will not
+happen here. You will receive a plain mapping of the data into the class tree,
+nothing more.
+
+=back
 
 =head1 METHODS
 
@@ -248,7 +275,7 @@ Returns an arrayref of the raw lines as hashrefs.
 
 =item C<errors>
 
-Return all errors that came up druing parsing. See error handling for detailed
+Return all errors that came up during parsing. See error handling for detailed
 information.
 
 =back
@@ -265,7 +292,7 @@ scalar ref for memory data.
 =item C<encoding>
 
 Encoding of the CSV file. Note that this module does not do any encoding
-guessing.  Know what your data ist. Defaults to utf-8.
+guessing. Know what your data is. Defaults to utf-8.
 
 =item C<sep_char>
 
@@ -292,7 +319,7 @@ C<listprice> column.
 In case of a One-To-One relationsship these can also be set over
 relationsships by sparating the steps with a dot (C<.>). This will work:
 
-  { customer => customer.name }
+  { customer => 'customer.name' }
 
 And will result in something like this:
 
@@ -320,16 +347,13 @@ but deactivated by default.
 =head1 ERROR HANDLING
 
 After parsing a file all errors will be accumulated into C<errors>.
+Each entry is an object with the following attributes:
 
-Each entry is an arrayref with the following structure:
-
- [
- 0  offending raw input,
- 1  Text::CSV error code if T:C error, 0 else,
- 2  error diagnostics,
- 3  position in line,
- 4  estimated line in file,
- ]
+ raw_input:  offending raw input,
+ code:   Text::CSV error code if Text:CSV signalled an error, 0 else,
+ diag:   error diagnostics,
+ line:   position in line,
+ col:    estimated line in file,
 
 Note that the last entry can be off, but will give an estimate.