9 |
use Socialtext::Resting; |
use Socialtext::Resting; |
10 |
use Encode; |
use Encode; |
11 |
use HTTP::Date; |
use HTTP::Date; |
12 |
|
use POSIX qw/strftime/; |
13 |
|
use File::Slurp; |
14 |
|
use File::MMagic::XS; |
15 |
|
use Getopt::Long; |
16 |
use Data::Dump qw/dump/; |
use Data::Dump qw/dump/; |
17 |
|
|
18 |
|
my $debug = 0; |
19 |
my $max = 999; |
my $max = 999; |
20 |
|
my $attachments = 0; |
21 |
|
|
22 |
|
GetOptions( |
23 |
|
'debug+' => \$debug, |
24 |
|
'max=i' => \$max, |
25 |
|
'attachments' => \$attachments, |
26 |
|
); |
27 |
|
|
28 |
my $page; |
my $page; |
29 |
my $page_date; |
my $page_date; |
30 |
|
|
31 |
my @page_names; |
my @page_names; |
32 |
|
|
33 |
|
print "Importing $max pages", $attachments ? " with attachments" : "", "...\n"; |
34 |
|
|
35 |
find({ |
find({ |
36 |
wanted => sub { |
wanted => sub { |
37 |
my $path = $File::Find::name; |
my $path = $File::Find::name; |
38 |
return unless -f $path; |
return unless -f $path; |
39 |
|
|
40 |
warn "# $path\n"; |
warn "+ $path\n"; |
41 |
my $ref = XMLin( $path ) || die "can't open $path: $!"; |
my $ref = XMLin( $path, |
42 |
|
KeyAttr => { |
43 |
|
'attachment' => '+name', |
44 |
|
'meta' => 'name', |
45 |
|
}, |
46 |
|
ForceArray => [ 'attachment', 'meta', 'widget' ], |
47 |
|
) || die "can't open $path: $!"; |
48 |
|
|
49 |
|
warn "## $path = ",dump( $ref ) if $debug; |
50 |
|
|
51 |
my $name = $ref->{name} || die "no name in $path"; |
my $name = $ref->{name} || die "no name in $path"; |
52 |
|
|
53 |
return if $name =~ m/^TamSystem/; |
return if $name =~ m/^TamSystem/; |
54 |
|
|
55 |
my $date = $ref->{meta}->{LastModified}; |
my $date = $ref->{meta}->{LastModified}->{value}; |
56 |
if ( ! $date ) { |
if ( ! $date ) { |
57 |
warn "SKIP: no LastModified in $path $name"; |
warn "SKIP: no LastModified in $path $name"; |
58 |
return; |
return; |
59 |
} |
} |
|
my $data = |
|
|
$ref->{widgets}->{widget}->{data} || |
|
|
$ref->{widgets}->{widget}->{Body}->{data} || |
|
|
die "no data in $path ",dump( $ref ); |
|
60 |
|
|
61 |
$page->{ $name } = [ $data, $date ]; |
my $data; |
62 |
|
|
63 |
|
foreach my $w ( @{ $ref->{widgets}->{widget} } ) { |
64 |
|
|
65 |
|
warn "## w = ",dump( $w ) if $debug; |
66 |
|
|
67 |
|
$data .= "\n----\n" if $data; |
68 |
|
$data .= $w->{data} || die "no data?"; |
69 |
|
} |
70 |
|
|
71 |
|
my $attachments; |
72 |
|
|
73 |
|
if ( my $a = $ref->{attachment} ) { |
74 |
|
foreach my $name ( keys %$a ) { |
75 |
|
my $full_path = $path; |
76 |
|
$full_path =~ s,pages/,attachments/,; |
77 |
|
$full_path .= '.' . $name; |
78 |
|
die "$full_path doesn't exist" unless -e $full_path; |
79 |
|
push @$attachments, { |
80 |
|
full_path => $full_path, |
81 |
|
name => ( $name || $a->{$name}->{desc} || 'noname' ), |
82 |
|
}; |
83 |
|
} |
84 |
|
} |
85 |
|
|
86 |
|
$page->{ $name } = { |
87 |
|
content => convert_markup( $data ), |
88 |
|
original => $data, |
89 |
|
date => convert_date( $date ), |
90 |
|
attachments => $attachments, |
91 |
|
}; |
92 |
|
|
|
# strip path from page name |
|
93 |
$name =~ s,^.+/([^/]+)$,$1,; |
$name =~ s,^.+/([^/]+)$,$1,; |
94 |
push @page_names, $name; |
push @page_names, $name; |
95 |
|
|
|
#warn dump( $ref ); |
|
96 |
}, |
}, |
97 |
|
no_chdir=>1, |
98 |
}, shift @ARGV || '.'); |
}, shift @ARGV || '.'); |
99 |
|
|
100 |
my @pages = ( keys %$page ); |
my @pages = ( keys %$page ); |
107 |
username => 'tamtam', |
username => 'tamtam', |
108 |
password => 'import', |
password => 'import', |
109 |
server => 'http://saturn.ffzg.hr/', |
server => 'http://saturn.ffzg.hr/', |
110 |
|
workspace => 'razmjenavjestina', |
111 |
); |
); |
|
$Rester->workspace('razmjenavjestina'); |
|
112 |
$Rester->put_workspacetag('TamTam'); |
$Rester->put_workspacetag('TamTam'); |
113 |
|
|
114 |
|
sub convert_date { |
115 |
|
my $date = shift; |
116 |
|
# return time2str( $date ); |
117 |
|
return strftime('%F %T %z', gmtime( $date )); |
118 |
|
} |
119 |
|
|
120 |
sub header { |
sub header { |
121 |
my $h = shift; |
my $h = shift; |
122 |
if ( $h =~ m/^(=+)\s+(.+?)\s+\1$/ ) { |
if ( $h =~ m/^(=+)\s+(.+?)\s+\1$/ ) { |
132 |
return $with . $what . $with; |
return $with . $what . $with; |
133 |
} |
} |
134 |
|
|
135 |
my $count = 0; |
sub pre { |
136 |
|
my $text = shift; |
137 |
foreach my $name ( keys %$page ) { |
$text =~ s/^{{{\s*//s; |
138 |
last if $count++ == $max; |
$text =~ s/\s*}}}$//s; |
139 |
|
return "\n.pre\n" . $text . "\n.pre\n"; |
140 |
|
} |
141 |
|
|
142 |
my ( $body, $date ) = @{ $page->{$name} }; |
sub convert_markup { |
143 |
$date = time2str( $date ); |
my $body = shift; |
144 |
|
|
145 |
$body =~ s/\Q[[TableOfContents]]\E/{toc}/gs; |
$body =~ s/\Q[[TableOfContents]]\E/{toc}/gs; |
146 |
$body =~ s/\Q[[BR]]\E/\n/gs; |
$body =~ s/\Q[[BR]]\E/\n/gs; |
148 |
$body =~ s/''''(.+?)''''/surround('`',$1)/gse; |
$body =~ s/''''(.+?)''''/surround('`',$1)/gse; |
149 |
$body =~ s/'''(.+?)'''/surround('*',$1)/gse; |
$body =~ s/'''(.+?)'''/surround('*',$1)/gse; |
150 |
$body =~ s/''(.+?)''/surround('_',$1)/gse; |
$body =~ s/''(.+?)''/surround('_',$1)/gse; |
151 |
|
$body =~ s/$RE{balanced}{-begin => "{{{"}{-end => "}}}"}{-keep}/pre($1)/gse; |
152 |
|
|
153 |
# fix bullets |
# fix bullets |
154 |
$body =~ s/^\s+([\*])/$1/gm; |
$body =~ s/^\s+([\*])/$1/gm; |
157 |
$body =~ s/\["([^"]+)"\]/[$1]/gs; |
$body =~ s/\["([^"]+)"\]/[$1]/gs; |
158 |
$body =~ s,\[(http://\S+)\s+([^\]]+)\],"$2"<$1>,gs; |
$body =~ s,\[(http://\S+)\s+([^\]]+)\],"$2"<$1>,gs; |
159 |
$body =~ s,\[(http://[^\]]+)\],$1,gs; |
$body =~ s,\[(http://[^\]]+)\],$1,gs; |
|
$body =~ s,$page_link_re,[$1],gs; |
|
160 |
|
|
161 |
Encode::_utf8_off( $body ); |
# fix hr |
162 |
|
$body =~ s,(\S+)----,$1\n----,gs; |
163 |
|
$body =~ s,----(\S+),----\n$1,gs; |
164 |
|
|
165 |
|
# attachments |
166 |
|
$body =~ s,\[attachment:([^\]]+)(gif|png|jpg|jpeg)\],{image: $1$2},gis; |
167 |
|
$body =~ s,\[attachment:([^\]]+)\],{file: $1},gs; |
168 |
|
|
169 |
|
return $body; |
170 |
|
} |
171 |
|
|
172 |
|
my $count = 0; |
173 |
|
|
174 |
|
my $m = File::MMagic::XS->new; |
175 |
|
|
176 |
|
foreach my $name ( keys %$page ) { |
177 |
|
last if $count++ == $max; |
178 |
|
|
179 |
|
my $p = $page->{$name}; |
180 |
|
|
181 |
|
warn "## $name = ",dump( $p ) if $debug; |
182 |
|
|
183 |
|
my $body = $p->{content} || die "no content?"; |
184 |
|
my $date = $p->{date} || die "no date?"; |
185 |
|
|
186 |
my @tags = ( 'TamTam' ); |
my @tags = ( 'TamTam' ); |
187 |
|
|
188 |
|
my $full_name = $name; |
189 |
|
|
190 |
if ( $name =~ m!/! ) { |
if ( $name =~ m!/! ) { |
191 |
my @page_tags = split(m!/!, $name); |
my @page_tags = split(m!/!, $name); |
192 |
$name = pop @page_tags; # remove page name |
$name = pop @page_tags; # remove page name |
193 |
push @tags, @page_tags; |
push @tags, @page_tags; |
194 |
} |
} |
195 |
|
|
196 |
$Rester->put_page( $name, { |
# link named pages |
197 |
content => $body, |
$body =~ s,\b$page_link_re\b,[$1],gs; |
198 |
date => $date, |
$body =~ s,``,,gs; |
199 |
}); |
|
200 |
print "+ $name\n"; |
$body .= qq{ |
201 |
|
|
202 |
|
---- |
203 |
|
|
204 |
|
"original"<http://www.razmjenavjestina.org/$full_name> {date: $date} |
205 |
|
}; |
206 |
|
|
207 |
|
Encode::_utf8_off( $body ); |
208 |
|
|
209 |
|
print "$name $date\n"; |
210 |
|
|
211 |
|
# original markup |
212 |
|
$Rester->put_page( $name, { content => $p->{original}, date => $date }); |
213 |
|
|
214 |
foreach ( @tags ) { |
foreach ( @tags ) { |
215 |
$Rester->put_pagetag( $name, $_ ); |
$Rester->put_pagetag( $name, $_, { date => $date } ); |
216 |
print "+ $name [$_]\n"; |
print "+ tag $_\n"; |
217 |
} |
} |
218 |
|
|
219 |
|
if ( $attachments ) { |
220 |
|
foreach my $a ( @{ $p->{attachments} } ) { |
221 |
|
my $type = $m->get_mime( $a->{full_path} ); |
222 |
|
my $content = read_file( $a->{full_path} ); |
223 |
|
print "+ attachment ", $a->{name}," $type ", length($content), " bytes\n"; |
224 |
|
$Rester->post_attachment($name, $a->{name}, $content, $type ); |
225 |
|
} |
226 |
|
} |
227 |
|
|
228 |
|
# converted page |
229 |
|
$Rester->put_page( $name, { content => $body, date => $date }); |
230 |
|
|
231 |
} |
} |
232 |
|
|