[21411] | 1 | ###########################################################################
|
---|
| 2 | #
|
---|
| 3 | # dbutil::gdbmtxtgz -- utility functions for writing to gdbm-txtgz databases
|
---|
| 4 | #
|
---|
| 5 | # A component of the Greenstone digital library software
|
---|
| 6 | # from the New Zealand Digital Library Project at the
|
---|
| 7 | # University of Waikato, New Zealand.
|
---|
| 8 | #
|
---|
| 9 | # Copyright (C) 2009
|
---|
| 10 | #
|
---|
| 11 | # This program is free software; you can redistribute it and/or modify
|
---|
| 12 | # it under the terms of the GNU General Public License as published by
|
---|
| 13 | # the Free Software Foundation; either version 2 of the License, or
|
---|
| 14 | # (at your option) any later version.
|
---|
| 15 | #
|
---|
| 16 | # This program is distributed in the hope that it will be useful,
|
---|
| 17 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 18 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 19 | # GNU General Public License for more details.
|
---|
| 20 | #
|
---|
| 21 | # You should have received a copy of the GNU General Public License
|
---|
| 22 | # along with this program; if not, write to the Free Software
|
---|
| 23 | # Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
|
---|
| 24 | #
|
---|
| 25 | ###########################################################################
|
---|
| 26 |
|
---|
| 27 | package dbutil::gdbmtxtgz;
|
---|
| 28 |
|
---|
| 29 | use strict;
|
---|
| 30 |
|
---|
| 31 |
|
---|
| 32 |
|
---|
| 33 | # -----------------------------------------------------------------------------
|
---|
| 34 | # GDBM TXT-GZ IMPLEMENTATION
|
---|
| 35 | # -----------------------------------------------------------------------------
|
---|
| 36 |
|
---|
| 37 | sub open_infodb_write_handle
|
---|
| 38 | {
|
---|
| 39 | # Keep infodb in GDBM neutral form => save data as compressed text file,
|
---|
| 40 | # read for txt2db to be run on it later (i.e. by the runtime system,
|
---|
| 41 | # first time the collection is ever accessed). This makes it easier
|
---|
| 42 | # distribute pre-built collections to various architectures.
|
---|
| 43 | #
|
---|
| 44 | # NB: even if two architectures are little endian (e.g. Intel and
|
---|
| 45 | # ARM procesors) GDBM does *not* guarantee that the database generated on
|
---|
| 46 | # one will work on the other
|
---|
| 47 |
|
---|
| 48 | my $infodb_file_path = shift(@_);
|
---|
| 49 |
|
---|
| 50 | # Greenstone ships with gzip for windows, on $PATH
|
---|
| 51 |
|
---|
| 52 | my $infodb_file_handle = undef;
|
---|
| 53 | if (!open($infodb_file_handle, "| gzip - > \"$infodb_file_path\""))
|
---|
| 54 | {
|
---|
[22076] | 55 | print STDERR "Error: Failed to open pipe to gzip - > \"$infodb_file_path\"\n";
|
---|
| 56 | print STDERR " $!\n";
|
---|
| 57 | return undef;
|
---|
[21411] | 58 | }
|
---|
[23169] | 59 | binmode($infodb_file_handle,":utf8");
|
---|
[21411] | 60 | return $infodb_file_handle;
|
---|
| 61 | }
|
---|
| 62 |
|
---|
| 63 |
|
---|
| 64 | sub close_infodb_write_handle
|
---|
| 65 | {
|
---|
| 66 | my $infodb_handle = shift(@_);
|
---|
| 67 |
|
---|
| 68 | close($infodb_handle);
|
---|
| 69 | }
|
---|
| 70 |
|
---|
| 71 |
|
---|
| 72 | sub get_infodb_file_path
|
---|
| 73 | {
|
---|
| 74 | my $collection_name = shift(@_);
|
---|
| 75 | my $infodb_directory_path = shift(@_);
|
---|
| 76 |
|
---|
| 77 | my $infodb_file_name = &util::get_dirsep_tail($collection_name).".txt.gz";
|
---|
| 78 | return &util::filename_cat($infodb_directory_path, $infodb_file_name);
|
---|
| 79 | }
|
---|
| 80 |
|
---|
| 81 |
|
---|
| 82 | sub read_infodb_file
|
---|
| 83 | {
|
---|
| 84 | my $infodb_file_path = shift(@_);
|
---|
| 85 | my $infodb_map = shift(@_);
|
---|
| 86 |
|
---|
[23169] | 87 | my $cmd = "gzip --decompress --to-stdout \"$infodb_file_path\"";
|
---|
[21411] | 88 |
|
---|
| 89 | open (PIPEIN, "$cmd |")
|
---|
| 90 | || die "Error: Couldn't open pipe from gzip: $!\n $cmd\n";
|
---|
| 91 |
|
---|
[23169] | 92 | binmode(PIPEIN,":utf8");
|
---|
[21411] | 93 | my $infodb_line = "";
|
---|
| 94 | my $infodb_key = "";
|
---|
| 95 | my $infodb_value = "";
|
---|
| 96 | while (defined ($infodb_line = <PIPEIN>))
|
---|
| 97 | {
|
---|
[28395] | 98 | $infodb_line =~ s/(\r\n)+$//; # more general than chomp
|
---|
| 99 |
|
---|
[21411] | 100 | if ($infodb_line =~ /^\[([^\]]+)\]$/)
|
---|
| 101 | {
|
---|
| 102 | $infodb_key = $1;
|
---|
| 103 | }
|
---|
| 104 | elsif ($infodb_line =~ /^-{70}$/)
|
---|
| 105 | {
|
---|
| 106 | $infodb_map->{$infodb_key} = $infodb_value;
|
---|
| 107 | $infodb_key = "";
|
---|
| 108 | $infodb_value = "";
|
---|
| 109 | }
|
---|
| 110 | else
|
---|
| 111 | {
|
---|
| 112 | $infodb_value .= $infodb_line;
|
---|
| 113 | }
|
---|
| 114 | }
|
---|
| 115 |
|
---|
| 116 | close (PIPEIN);
|
---|
| 117 | }
|
---|
| 118 |
|
---|
[22485] | 119 |
|
---|
| 120 | sub read_infodb_keys
|
---|
| 121 | {
|
---|
| 122 | my $infodb_file_path = shift(@_);
|
---|
| 123 | my $infodb_map = shift(@_);
|
---|
| 124 |
|
---|
[23169] | 125 | my $cmd = "gzip --decompress --to-stdout \"$infodb_file_path\"";
|
---|
[22485] | 126 |
|
---|
| 127 | open (PIPEIN, "$cmd |")
|
---|
| 128 | || die "Error: Couldn't open pipe from gzip: $!\n $cmd\n";
|
---|
| 129 |
|
---|
[23169] | 130 | binmode(PIPEIN,":utf8");
|
---|
[22485] | 131 | my $infodb_line = "";
|
---|
| 132 | my $infodb_key = "";
|
---|
| 133 | while (defined ($infodb_line = <PIPEIN>))
|
---|
| 134 | {
|
---|
[28395] | 135 | $infodb_line =~ s/(\r\n)+$//; # more general than chomp
|
---|
| 136 |
|
---|
[22485] | 137 | if ($infodb_line =~ /^\[([^\]]+)\]$/)
|
---|
| 138 | {
|
---|
| 139 | $infodb_key = $1;
|
---|
| 140 | }
|
---|
| 141 | elsif ($infodb_line =~ /^-{70}$/)
|
---|
| 142 | {
|
---|
| 143 | $infodb_map->{$infodb_key} = 1;
|
---|
| 144 | $infodb_key = "";
|
---|
| 145 | }
|
---|
| 146 | }
|
---|
| 147 |
|
---|
| 148 | close (PIPEIN);
|
---|
| 149 | }
|
---|
| 150 |
|
---|
[21411] | 151 |
|
---|
| 152 | sub write_infodb_entry
|
---|
| 153 | {
|
---|
| 154 |
|
---|
| 155 | my $infodb_handle = shift(@_);
|
---|
| 156 | my $infodb_key = shift(@_);
|
---|
| 157 | my $infodb_map = shift(@_);
|
---|
| 158 |
|
---|
| 159 | print $infodb_handle "[$infodb_key]\n";
|
---|
[27602] | 160 | foreach my $infodb_value_key (sort keys(%$infodb_map))
|
---|
[21411] | 161 | {
|
---|
| 162 | foreach my $infodb_value (@{$infodb_map->{$infodb_value_key}})
|
---|
| 163 | {
|
---|
| 164 | if ($infodb_value =~ /-{70,}/)
|
---|
| 165 | {
|
---|
| 166 | # if value contains 70 or more hyphens in a row we need to escape them
|
---|
| 167 | # to prevent txt2db from treating them as a separator
|
---|
| 168 | $infodb_value =~ s/-/&\#045;/gi;
|
---|
| 169 | }
|
---|
| 170 | print $infodb_handle "<$infodb_value_key>" . $infodb_value . "\n";
|
---|
| 171 | }
|
---|
| 172 | }
|
---|
| 173 | print $infodb_handle '-' x 70, "\n";
|
---|
| 174 | }
|
---|
| 175 |
|
---|
| 176 |
|
---|
[21856] | 177 |
|
---|
| 178 | sub write_infodb_rawentry
|
---|
| 179 | {
|
---|
| 180 |
|
---|
| 181 | my $infodb_handle = shift(@_);
|
---|
| 182 | my $infodb_key = shift(@_);
|
---|
| 183 | my $infodb_val = shift(@_);
|
---|
| 184 |
|
---|
| 185 | print $infodb_handle "[$infodb_key]\n";
|
---|
| 186 | print $infodb_handle "$infodb_val\n";
|
---|
| 187 | print $infodb_handle '-' x 70, "\n";
|
---|
| 188 | }
|
---|
| 189 |
|
---|
[23399] | 190 | sub set_infodb_entry
|
---|
| 191 | {
|
---|
| 192 | my $infodb_file_path = shift(@_);
|
---|
| 193 | my $infodb_key = shift(@_);
|
---|
| 194 | my $infodb_map = shift(@_);
|
---|
| 195 |
|
---|
| 196 | print STDERR "***** gdbmtxtgz::set_infodb_entry() not implemented yet!\n";
|
---|
| 197 | }
|
---|
[21856] | 198 |
|
---|
| 199 |
|
---|
[23399] | 200 |
|
---|
[21411] | 201 | sub delete_infodb_entry
|
---|
| 202 | {
|
---|
| 203 |
|
---|
| 204 | my $infodb_handle = shift(@_);
|
---|
| 205 | my $infodb_key = shift(@_);
|
---|
| 206 |
|
---|
| 207 |
|
---|
| 208 | # A minus at the end of a key (after the ]) signifies 'delete'
|
---|
| 209 | print $infodb_handle "[$infodb_key]-\n";
|
---|
| 210 |
|
---|
| 211 | # The 70 minus signs are also needed, to help make the parsing by db2txt simple
|
---|
| 212 | print $infodb_handle '-' x 70, "\n";
|
---|
| 213 | }
|
---|
| 214 |
|
---|
| 215 |
|
---|
| 216 |
|
---|
| 217 | 1;
|
---|