2020-07-19 16:15:03 +02:00
|
|
|
exports.name = 'masto_conversion';
|
|
|
|
const fs = require('fs');
|
2020-07-18 17:03:17 +02:00
|
|
|
|
2020-07-19 16:15:03 +02:00
|
|
|
class Conversion {
|
2020-07-20 12:39:01 +02:00
|
|
|
hello() {
|
|
|
|
console.log('hello from conversion');
|
2020-07-19 16:15:03 +02:00
|
|
|
}
|
2020-07-20 12:39:01 +02:00
|
|
|
|
|
|
|
likes() {
|
2020-07-19 16:15:03 +02:00
|
|
|
// read file likes
|
|
|
|
fs.readFile('source_data/likes.json',
|
|
|
|
// callback function that is called when reading file is done
|
|
|
|
function (err, data) {
|
|
|
|
// parse json
|
|
|
|
let jsonParsedLikes = JSON.parse(data);
|
|
|
|
// access elements
|
|
|
|
const lengthOfLikes = jsonParsedLikes.orderedItems.length;
|
|
|
|
console.log('likes length', lengthOfLikes);
|
|
|
|
return jsonParsedLikes;
|
|
|
|
});
|
|
|
|
}
|
2020-07-18 17:03:17 +02:00
|
|
|
|
2020-07-20 12:39:01 +02:00
|
|
|
filterToots(toots, options) {
|
|
|
|
let minchartoots;
|
2020-07-18 17:03:17 +02:00
|
|
|
|
2020-07-20 12:39:01 +02:00
|
|
|
if (options.filterBiggerTottsBeforeSlicing) {
|
2020-07-19 16:15:03 +02:00
|
|
|
minchartoots = toots.filter(item => {
|
|
|
|
return item['object'].content && item['object'].content.length > options.min_length;
|
|
|
|
});
|
|
|
|
minchartoots = minchartoots.slice(0, options.max_toots);
|
2020-07-20 12:39:01 +02:00
|
|
|
} else {
|
2020-07-19 16:15:03 +02:00
|
|
|
const slice = toots.slice(0, options.max_toots);
|
|
|
|
minchartoots = slice.filter(item => {
|
|
|
|
return item['object'].content && item['object'].content.length > options.min_length;
|
|
|
|
});
|
|
|
|
}
|
2020-07-20 12:39:01 +02:00
|
|
|
minchartoots.forEach(toot => {
|
|
|
|
toot = this.findMediaUrl(toot);
|
|
|
|
toot = this.removeLastChars(toot);
|
|
|
|
return toot;
|
|
|
|
});
|
|
|
|
|
|
|
|
return minchartoots;
|
2020-07-19 16:15:03 +02:00
|
|
|
}
|
2020-07-18 17:03:17 +02:00
|
|
|
|
2020-07-20 12:39:01 +02:00
|
|
|
//
|
|
|
|
/**
|
|
|
|
*
|
|
|
|
* @param toot
|
|
|
|
* @returns {*}
|
|
|
|
*/
|
|
|
|
findMediaUrl(toot) {
|
|
|
|
/**
|
|
|
|
* goal:
|
|
|
|
* https://mastodon.cipherbliss.com/system/media_attachments/files/000/858/113/original/74b370672892f884.jpg?1566230144
|
|
|
|
*
|
|
|
|
* input data:
|
|
|
|
* "attributedTo":"https://mastodon.cipherbliss.com/users/tykayn",
|
|
|
|
*
|
|
|
|
* "attachment":[{"type":"Document",
|
|
|
|
* "mediaType":"image/png","url":"media_attachments/files/000/872/910/original/c82b422f302b8ec9.png",
|
|
|
|
* "name":null,
|
|
|
|
* "blurhash":"UnSOjgo~ysWAVYWBkWjXu5axVrjckqoze?Rk"}],
|
|
|
|
*
|
|
|
|
* we use the attribuedTo property to find instance, and map the url to the instance url, and add this property to the attachment
|
|
|
|
*/
|
|
|
|
if (toot['object'].attributedTo) {
|
|
|
|
|
|
|
|
let splitted = toot['object'].attributedTo.split('/');
|
|
|
|
let instanceUrl = splitted[2];
|
|
|
|
|
|
|
|
toot.instanceUrl = 'https://' + instanceUrl;
|
|
|
|
toot.attachment = toot['object'].attachment.map(att => {
|
|
|
|
att.href = toot.instanceUrl + '/system/' + att.url;
|
|
|
|
return att;
|
|
|
|
});
|
|
|
|
}
|
|
|
|
return toot;
|
|
|
|
}
|
|
|
|
|
|
|
|
removeLastChars(toot) {
|
|
|
|
toot['object'].content = toot['object'].content.trim();
|
|
|
|
return toot;
|
|
|
|
}
|
|
|
|
|
|
|
|
makeStatsForToots(tootArray) {
|
|
|
|
let stats = {
|
|
|
|
recievers: {},
|
|
|
|
hashtags : {},
|
|
|
|
};
|
|
|
|
// make statistics on who do we talk to, based on the cc field
|
|
|
|
tootArray.forEach(elem => {
|
|
|
|
|
|
|
|
// stats on hashtags
|
|
|
|
if (elem['object'].tag) {
|
|
|
|
elem['object'].tag.forEach(tag => {
|
|
|
|
if (tag.type === 'Hashtag') {
|
|
|
|
if (!stats.hashtags[tag.name]) {
|
|
|
|
stats.hashtags[tag.name] = {
|
|
|
|
name : tag.name,
|
|
|
|
href : tag.href,
|
2020-07-19 16:15:03 +02:00
|
|
|
counter: 0,
|
|
|
|
};
|
|
|
|
}
|
2020-07-20 12:39:01 +02:00
|
|
|
stats.hashtags[tag.name].counter++;
|
|
|
|
}
|
|
|
|
});
|
|
|
|
}
|
|
|
|
// stats on recievers of toots
|
|
|
|
if (elem['object'].cc) {
|
|
|
|
elem['object'].cc.forEach(copyFolk => {
|
|
|
|
if (!stats.recievers[copyFolk]) {
|
|
|
|
stats.recievers[copyFolk] = {
|
|
|
|
user : this.urlToUser(copyFolk),
|
|
|
|
name : copyFolk,
|
|
|
|
counter : 0,
|
|
|
|
counterContentLength: 0,
|
|
|
|
};
|
|
|
|
}
|
|
|
|
stats.recievers[copyFolk].counter++;
|
|
|
|
stats.recievers[copyFolk].counterContentLength += elem['object'].content.length;
|
|
|
|
});
|
|
|
|
}
|
|
|
|
});
|
2020-07-19 16:46:34 +02:00
|
|
|
|
2020-07-20 12:39:01 +02:00
|
|
|
console.log('stats.hashtags', stats.hashtags[0]);
|
|
|
|
stats = {
|
|
|
|
recievers: this.sortTootsByLength(stats.recievers),
|
|
|
|
hashtags : this.sortTootsByLength(stats.hashtags),
|
|
|
|
};
|
|
|
|
return stats;
|
2020-07-19 16:15:03 +02:00
|
|
|
}
|
2020-07-18 17:03:17 +02:00
|
|
|
|
2020-07-20 12:39:01 +02:00
|
|
|
sortTootsByLength(stats) {
|
2020-07-19 16:15:03 +02:00
|
|
|
const statKeys = Object.keys(stats);
|
|
|
|
const arrayToSort = [];
|
|
|
|
statKeys.forEach(elem => {
|
|
|
|
arrayToSort.push(
|
|
|
|
stats[elem],
|
|
|
|
);
|
|
|
|
});
|
2020-07-20 12:39:01 +02:00
|
|
|
arrayToSort.sort((a, b) => {
|
|
|
|
return b.counter - a.counter;
|
2020-07-19 16:15:03 +02:00
|
|
|
});
|
|
|
|
return arrayToSort;
|
|
|
|
}
|
2020-07-20 12:39:01 +02:00
|
|
|
|
|
|
|
urlToUser(url) {
|
|
|
|
let sliceOfSlashes = url.split('/');
|
|
|
|
let userObject = {
|
|
|
|
url : url,
|
|
|
|
username: sliceOfSlashes[sliceOfSlashes.length - 1],
|
|
|
|
};
|
|
|
|
return userObject;
|
|
|
|
}
|
|
|
|
|
|
|
|
filterOnlyTootsWithMedias(tootList) {
|
|
|
|
console.log('filterOnlyTootsWithMedias')
|
|
|
|
return tootList.filter(toot => {
|
|
|
|
return toot['object'].attachment && toot['object'].attachment.length
|
|
|
|
});
|
|
|
|
}
|
|
|
|
|
2020-07-19 16:15:03 +02:00
|
|
|
}
|
2020-07-20 12:39:01 +02:00
|
|
|
|
2020-07-19 16:15:03 +02:00
|
|
|
exports.conversion = new Conversion();
|