1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
| #!/usr/bin/perl
use strict;
use warnings;
use File::Find;
use HTML::TreeBuilder;
use Getopt::Long;
my $octopress_root;
my $options_read = GetOptions("dir=s", \$octopress_root);
############################################################
unless ($options_read && $octopress_root) {
print "\n";
print "\n";
print "usage: tagify.pl --dir d\n";
print "\n";
print "where d is the root octopress directory\n";
print " - the parent of source, public, etc.\n";
print "\n";
exit 1;
}
# The tag cloud HTML gets saved into this file.
# This file is included by two others:
# a) The file used for the sidebar aside
# b) The page used to display all tags
# (accessible as /tags/index.html)
#
my $custom_file = "$octopress_root/source/_includes".
"/custom/tag_cloud.html";
# This is the data structure that contains all the tag
# data parsed by the HTML files.
# It's key is the tag name (not case-normalized).
# The value is another hash. That hash has 2 keys:
# count - number of pages with that tag
# range_num - a number from 1 - 10 indicating
# popularity (see below)
# pages - an array of hashes
#
# Each hash in the pages array has 3 keys:
# title - the HTML title of the post
# file - the full file name of the HTML file
# categories - yet another hash
#
# The categories hash has two keys:
# href - the url to the category page (as determined
# by OctoPress)
# text - the name of the category (as displayed by
# Octopress)
#
my $tag_data = { };
# This function populates the tag_data data structure
#
find(\&getTags, "$octopress_root/public/blog");
# Find the number of times the most popular tag is used
#
my $max = 1; # start with 1, not 0 to prevent a
# divide-by-zero error later
# if none of the posts have tags
foreach my $tag (keys %$tag_data) {
$tag_data->{$tag}->{count} = scalar(@{$tag_data->{$tag}->{pages}});
if ($tag_data->{$tag}->{count} > $max) {
$max = $tag_data->{$tag}->{count};
}
}
# Assign each tag a range number from 1 - 10
# based on popularity. This range number will
# be used along with CSS to print tags with
# the appropriate size.
#
foreach my $tag (keys %$tag_data) {
$tag_data->{$tag}->{range_num} =
int(($tag_data->{$tag}->{count} / $max)
* 10
+ 0.5); # nearest whole number
if ($tag_data->{$tag}->{range_num} == 0) {
$tag_data->{$tag}->{range_num} = 1;
# we want 1-10, not 0-10
}
}
# Write the tag cloud file
#
open (O, ">$custom_file") || die;
print O "<div id='tag_cloud'>\n";
# sort by tag name, case insensitive
#
foreach my $tag (sort { lc($a) cmp lc($b)}
keys %$tag_data) {
# give each tag anchor a title,
# for screen readers and the like
#
my $plural = "y";
if ($tag_data->{$tag}->{count} > 1) {
$plural = 'ies';
}
print O qq[<a href="/blog/tags/$tag/" ];
print O qq[title="$tag_data->{$tag}->{count} entr$plural" ];
print O qq[class="tag_$tag_data->{$tag}->{range_num}">];
print O qq[$tag];
print O qq[</a>\n];
}
print O "</div>\n";
close O;
# Now save the individual tag files
# First, clear out the directory because we're gonna
# regenerate all the files.
#
my $tag_dir = "$octopress_root/source/blog/tags";
# If source/tags exists but is a file
#
die "source/blog/tags is a file" if (-f $tag_dir);
# Create the directory if it doesn't exist
#
if (!-d $tag_dir) {
mkdir $tag_dir;
createTagsIndexMarkdown($tag_dir);
}
else {
# Delete all directories under source/tags.
# We don't want to delete everything because we
# need to preserve tags/index.markdown in case
# something was modified there.
#
my $dirs = `find $tag_dir/* -type d`;
my @dirs = split(/[\r\n]+/, $dirs);
foreach my $dir (@dirs) {
`/bin/rm -rf $dir`;
}
}
# Make a file for each tag.
#
foreach my $tag (keys %$tag_data) {
makeTagFile($tag);
}
## ####################################################
## Functions
## ####################################################
sub makeTagFile {
my $tag = shift;
mkdir "source/blog/tags/$tag"
||
die "Couldn't make directory source/blog/tags/$tag";
open (O, "> source/blog/tags/$tag/index.markdown")
||
die "Can't open source/blog/tags/$tag/index.markdown";
print O qq^---
layout: page
title: Tag: $tag
footer: false
---
<div id="blog-archives" class="category">
^;
my $year = 0;
# Sort by file name descending
# This is the same as sorting by date descending
#
foreach my $file (
sort { $b->{file} cmp $a->{file} }
@{$tag_data->{$tag}->{pages}}) {
# Get the year month and date
#
my ($yyyy, $mm, $dd) = $file->{file} =~
m!(\d\d\d\d)/(\d\d)/(\d\d)/!;
# The HTML and associated logic here mimics
# the HTML of the category pages - print
# a H2 for every new year
#
if ($yyyy != $year) {
$year = $yyyy;
print O "<h2>$year</h2>\n";
}
# Construct the URL & date string
#
my $url = $file->{file};
$url =~ s/^$octopress_root\/public//;
my $title = $file->{title};
my @months = qw ( x Jan Feb Mar Apr May Jun
Jul Aug Sep Oct Nov Dec );
my $mon = $months[$mm * 1];
print O qq[
<article>
<h1><a href="$url">$title</a></h1>
<time datetime="$yyyy-$mm-${dd}T00:00:00-06:00" pubdate><span class='month'>$mon</span> <span class='day'>$dd</span> <span class='year'>$yyyy</span></time>
<footer>
<span class="categories">posted in
];
# Print each category, separated by commas
#
print O join(", ",
map { "<a href='$_->{href}'>$_->{text}</a>" }
@{$file->{categories}}
);
print O qq[</span>
</footer>
</article>
];
}
print O "</div>\n";
close O;
}
sub getTags {
my $file = $File::Find::name;
# Only parse files that look like posts
#
return unless $file =~ /\.html$/;
return unless $file =~
/^$octopress_root\/public\/blog\/\d{4}\/\d{2}\/\d{2}\//;
# Read the contents of the HTML file
#
open (HTML, $_) || die "Can't open $file";
my $contents = join("", <HTML>);
close HTML;
my $tree = HTML::TreeBuilder->new();
$tree->parse($contents);
# Get the title
#
my $title = $tree->look_down(_tag => "h1",
class => "entry-title");
$title = $title->as_trimmed_text();
# Get the categories
#
my $category_ent = $tree->look_down(_tag => "span",
class => "categories");
my @as = $category_ent->look_down(_tag => "a",
class => "category");
my @categories = ();
foreach my $a (@as) {
push(@categories,
{ href => $a->attr('href'),
text => $a->as_trimmed_text
});
}
# Get the tags
#
my $ul = $tree->look_down("_tag", "ul",
"id" , "tags_ul");
if ($ul) {
my @items = $ul->look_down("_tag" => "li");
foreach my $item (@items) {
my $tag = $item->as_trimmed_text();
# Finally, populate the data structure
#
push (@{$tag_data->{$tag}->{pages}},
{ title => $title,
file => $file,
categories => \@categories
} );
}
}
else {
# no tags in this document
}
$tree->delete();
}
# This function creates a default
# source/tags/index.markdown
#
sub createTagsIndexMarkdown {
my $tag_dir = shift;
open (O, ">$tag_dir/index.markdown");
print O qq[---
layout: page
title: Tags
footer: false
---
<div class="tag_page">
{% include custom/tag_cloud.html %}
</div>
];
close O;
}
|