=================================================================== RCS file: /cvs/pta/pta_import.pl,v retrieving revision 1.13 retrieving revision 1.25 diff -u -p -r1.13 -r1.25 --- pta/pta_import.pl 2020/11/18 21:32:16 1.13 +++ pta/pta_import.pl 2020/11/29 14:00:50 1.25 @@ -1,4 +1,4 @@ -#!/usr/bin/perl +#!/usr/bin/perl # Copyright (c) 2020 Freda Bundchen @@ -22,75 +22,26 @@ use Getopt::Std qw(getopts); our ($opt_I); my %banks = ( + "bbva_usa" => \&import_bbva_usa, + "capital_one_360" => \&import_capital_one_360, "capital_one_credit" => \&import_capital_one_credit, "chase_credit" => \&import_chase_credit, + "etrade_ira" => \&import_etrade_ira, "optum_hsa" => \&import_optum_hsa, "sparkasse_camt" => \&import_sparkasse_camt, + "wellsfargo" => \&import_wellsfargo, ); # === SUBROUTINES ===================================================== - -sub import_chase_credit ($$$) { - my ($account, $csv_account, $line) = @_; - my ($trans_date, $post_date, $description, $category, - $type, $amount) = split /,/, $line; - my ($debit, $credit); - $post_date =~ s#(\d+)/(\d+)/(\d+)#$3$1$2#; - ($amount, $debit, $credit) = - get_accounts_by_amount_sign($amount, $account, - $csv_account); - return ($post_date, $amount, $debit, $credit, $description); -} - -sub import_capital_one_credit ($$$) { - my ($account, $csv_account, $line) = @_; - my ($trans_date, $post_date, $card_num, - $description, $category, $csv_debit, - $csv_credit) = split /,/, $line; - $post_date =~ s/(\d+)-(\d+)-(\d+)/$1$2$3/; - my ($amount, $debit, $credit) = - get_accounts_by_csv_col($account, $csv_account, - $csv_debit, $csv_credit); - return ($post_date, $amount, $debit, $credit, $description); -} - -sub import_optum_hsa ($$$) { - my ($account, $csv_account, $line) = @_; - my ($date, $description, $amount, - $type) = split /,/, $line; - my ($debit, $credit); - $date =~ s/(\d+)-(\d+)-(\d+)/$1$2$3/; - $amount =~ s/\$//; - ($amount, $debit, $credit) = - get_accounts_by_amount_sign($amount, $account, - $csv_account); - return ($date, $amount, $debit, $credit, $description); -} - -sub import_sparkasse_camt ($$$) { - my ($account, $csv_account, $line) = @_; - my @fields; - $_ = $line; - push @fields, $1 while s/"([^"]*)";?//; - $_ eq "" or die "CAMT parse error before $_ in $line"; - @fields == 17 or die "not 17 but @fields fields: $line"; - $fields[1] =~ s/^(\d\d)\.(\d\d)\.(\d\d)$/20$3$2$1/ - or die "date parse error: $line"; - $fields[14] =~ s/,/./; - return $fields[1], - get_accounts_by_amount_sign($fields[14], $account, $csv_account), - (join ' ', $fields[11], $fields[4]); -} - sub get_accounts_by_amount_sign ($$$) { my ($amount, $account, $csv_account) = @_; my ($debit, $credit); if ($amount <= 0) { $amount = substr $amount, 1; - $credit = $csv_account; + $credit = $csv_account; $debit = $account; } else { - $debit = $csv_account; + $debit = $csv_account; $credit = $account; } return ($amount, $debit, $credit); @@ -118,20 +69,20 @@ sub usage () { # === MAIN PROGRAM ===================================================== -my ($csv_account, $fn, $in, $account_name, $delim, @compiled); - -# Parse command line arguments. getopts 'I:' or usage; -if ($opt_I) { - $account_name = $opt_I; - $banks{$account_name} or die "unknown accountname: $account_name"; - $fn = "import_" . $account_name . ".txt"; - open $in, $fn or die "$fn: $!"; -} else { +unless ($opt_I) { + warn "The option -I is required."; usage; } +my $account_name = $opt_I; +$banks{$account_name} or die "unknown accountname: $account_name"; # Parse the configuration file. +my $fn = "import/" . $account_name . ".txt"; +open my $in, '<', $fn or die "$fn: $!"; +my ($cost_center_field, $csv_account, $date_field, $date_format, + $delim, $header, $quantity_field, $quote, @amount_fields, + @compiled, @description_fields, @ignored); while (<$in>) { chomp; next if /^(?:#|$)/; @@ -141,11 +92,48 @@ while (<$in>) { $csv_account = $1; next; } + if (s/^AMOUNT\s+//) { + push @amount_fields, $1 - 1 while s/(\d+)\s*//; + $_ eq '' or die "trailing garbage: AMOUNT ... $_"; + next; + } + if (/^COSTCENTER\s+(\d+)/) { + $cost_center_field = $1 - 1; + next; + } + if (/^DATE\s+(\d+)\s+(\S+)/) { + $date_field = $1 - 1; + $date_format = $2; + next; + } if (/^DELIM\s+(\S)$/) { $delim and die "duplicate DELIM line: $1"; $delim = $1; next; } + if (s/^DESCRIPTION\s+//) { + push @description_fields, $1 - 1 while s/(\d+)\s*//; + $_ eq '' or die "trailing garbage: DESCRIPTION ... $_"; + next; + } + if (/^HEADER\s+(.*)$/) { + $header and die "duplicate HEADER line: $1"; + $header = $1; + next; + } + if (/^IGNORE\s+(.*)/) { + push @ignored, qr/$1/; + next; + } + if (/^QUANTITY\s+(\d+)/) { + $quantity_field = $1 - 1; + next; + } + if (/^QUOTE\s+(\S)$/) { + $quote and die "duplicate QUOTE line: $1"; + $quote = $1; + next; + } $delim or die "no DELIM line in $fn"; s/^(.*)$delim\s+(\d+)\s+(\S+)// or die "$fn import parse error: $line"; @@ -159,12 +147,29 @@ close $in; $csv_account or die "no ACCOUNT line in $fn"; # Parse the CSV file from the bank. -chomp(my $header = <>); -while (<>) { +if (@ARGV) { + open STDIN, '<', $ARGV[0] or die "$ARGV[0]: $!"; +} +LINE: while () { chomp; next if (/^$/); + foreach my $ignore (@ignored) { + next LINE if /$ignore/; + } my $line = $_; - my @fields = split /$delim/, $line; + if ($header) { + $line eq $header + or die "expected HEADER $header\nbut got $line"; + undef $header; + next; + } + my $copy_line = $line; + my @fields; + if ($quote) { + push @fields, $1 while $copy_line =~ s/$quote([^$quote]*)$quote$delim?//; + } else { + @fields = split /$delim/, $line; + } my $matches = 0; my ($account, $booking); foreach my $selector (@compiled) { @@ -181,10 +186,45 @@ while (<>) { } } $matches or die "unmatched CSV line: $line"; - my ($date, $amount, $debit, $credit, $description) = - $banks{$account_name}->($account, $csv_account, $line); + my $date = $fields[$date_field] or + die "date parse error: $line"; + if ($date_format eq "MM/DD/YYYY") { + $date =~ s#(\d+)/(\d+)/(\d+)#$3$1$2#; + } elsif ($date_format eq "MM/DD/YY") { + $date =~ s#(\d+)/(\d+)/(\d+)#20$3$1$2#; + } elsif ($date_format eq "YYYY-MM-DD") { + $date =~ s#(\d+)-(\d+)-(\d+)#$1$2$3#; + } elsif ($date_format eq "DD.MM.YY") { + $date =~ s#(\d+)\.(\d+)\.(\d+)#20$3$2$1#; + } else { + die "unhandled date format: $line"; + } + foreach my $i (@amount_fields) { + if (defined($fields[$i])) { + $fields[$i] =~ s/,/./; + $fields[$i] =~ s/\$//; + $fields[$i] = "-$1" if $fields[$i] =~ /^\((\d+\.\d+)\)/; + } + } + my $description = join ' ', @fields[@description_fields]; + my ($amount, $credit, $debit); + if ($#amount_fields) { + ($amount, $debit, $credit) = + get_accounts_by_csv_col($account, + $csv_account, $fields[$amount_fields[0]], + $fields[$amount_fields[1]]); + } else { + ($amount, $debit, $credit) = + get_accounts_by_amount_sign( + $fields[$amount_fields[0]], + $account, $csv_account); + } $date && $amount && $debit && $credit && $description or die "import parse error: $line"; $description =~ s/#//g; + $description .= " [$fields[$cost_center_field]]" + if $cost_center_field; + $description .= " quantity $fields[$quantity_field]" + if $quantity_field; print "$date $booking $debit $credit $amount $description\n"; }