-
-
Save samebchase/0a0815866e3c6d887d13e67e977105e8 to your computer and use it in GitHub Desktop.
Quick and dirty way to generate Gemini files of my Twitter archive
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env raku | |
use JSON::Fast; | |
use Terminal::ANSIColor; | |
#use Grammar::Tracer; | |
grammar TwitterDate { | |
token TOP { <day-of-week> ' ' | |
<month> ' ' | |
<day> ' ' | |
<hh> ':' <mm> ':' <ss> ' ' | |
'+' <tz> ' ' | |
<yyyy> } | |
token day { \d ** 2 } | |
token day-of-week { 'Sun' | 'Mon' | 'Tue' | | |
'Wed' | 'Thu' | 'Fri' | | |
'Sat' } | |
token month { 'Jan' | 'Feb' | 'Mar' | 'Apr' | | |
'May' | 'Jun' | 'Jul' | 'Aug' | | |
'Sep' | 'Oct' | 'Nov' | 'Dec' } | |
token tz { \d ** 4 } | |
token hh { \d ** 2 } | |
token mm { \d ** 2 } | |
token ss { \d ** 2 } | |
token yyyy { \d ** 4 } | |
} | |
my %month-to-num = 'Jan' => 1, | |
'Feb' => 2, | |
'Mar' => 3, | |
'Apr' => 4, | |
'May' => 5, | |
'Jun' => 6, | |
'Jul' => 7, | |
'Aug' => 8, | |
'Sep' => 9, | |
'Oct' => 10, | |
'Nov' => 11, | |
'Dec' => 12; | |
sub is-reply(%tweet) { | |
so %tweet<tweet><in_reply_to_status_id>; | |
} | |
sub is-rt(%tweet) { | |
%tweet<tweet><full_text>.starts-with('RT'); | |
} | |
sub has-mentions(%tweet) { | |
%tweet<tweet><entities><user_mentions>.elems > 0 | |
or | |
%tweet<tweet><full_text>.starts-with('@') | |
} | |
sub has-hashtags(%tweet) { | |
%tweet<tweet><entities><hashtags>.elems > 0 | |
} | |
sub has-links(%tweet) { | |
%tweet<tweet><entities><urls>.elems > 0 | |
} | |
sub has-media(%tweet) { | |
so %tweet<tweet><entities><media> | |
} | |
sub created-at(%tweet) { | |
my $match = TwitterDate.parse(%tweet<tweet><created_at>); | |
return DateTime.new( | |
year => $match<yyyy>.Int, | |
month => %month-to-num{$match<month>.Str}, | |
day => $match<day>.Int, | |
hour => $match<hh>.Int, | |
minute => $match<mm>.Int, | |
second => $match<ss>.Int, | |
); | |
} | |
sub created-at-asc(%t1, %t2) { | |
created-at(%t1) <=> created-at(%t2); | |
} | |
sub created-at-desc(%t1, %t2) { | |
created-at(%t2) <=> created-at(%t1); | |
} | |
sub gen-tweet-stream($path) { | |
my $file-contents = slurp($path); | |
my @json-array = from-json $file-contents; | |
my $i = 1; | |
for @json-array.grep({ !is-reply($_) }) | |
.grep({ !is-rt($_) }) | |
.grep({ !has-mentions($_) }) | |
.grep({ !has-hashtags($_) }) | |
.grep({ !has-links($_) }) | |
.grep({ !has-media($_) }) | |
.sort({ created-at-asc $^a, $^b }) | |
.rotor(33) | |
-> @tweets { | |
my %first-tweet = @tweets.head; | |
my $first-tweet-created-at = created-at(%first-tweet); | |
my $batch-filename = "$i.gmi"; | |
my $file-contents = ''; | |
say colored("$i $batch-filename $first-tweet-created-at:", "bold blue on_black"); | |
for @tweets -> %tweet { | |
my $created-at = created-at(%tweet); | |
$file-contents ~= "### {$created-at.yyyy-mm-dd} {$created-at.hh-mm-ss}\n\n" ~ | |
"%tweet<tweet><full_text>\n\n"; | |
} | |
$file-contents ~= "=> gemini://gemini.samebchase.com/birdsite/{$i.succ}.gmi next\n"; | |
$file-contents ~= "=> gemini://gemini.samebchase.com/birdsite/{$i.pred}.gmi prev"; | |
spurt "generated/$batch-filename", $file-contents; | |
say "generated file $batch-filename"; | |
$i++; | |
} | |
} | |
sub MAIN() { | |
gen-tweet-stream('data/tweets.json'); | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment