Last active
November 18, 2023 09:37
-
-
Save chuv1/9641abc8a5a1a9b3bb8c9177fb7ffa9e to your computer and use it in GitHub Desktop.
Test function to convert telegram message entities into HTML markup.
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
public function getHTML($without_cmd = false){ | |
if(empty($this->getEntities())){ | |
return $this->getText($without_cmd); | |
} | |
$text = $this->getText(); | |
$html = ''; | |
$entities_count = \count($this->getEntities())-1; | |
foreach($this->getEntities() as $k => $entity){ | |
if($k === 0){ | |
$html .= mb_substr($text, 0, $entity->getOffset()); | |
} | |
switch($entity->getType()){ | |
default: | |
case 'mention': | |
case 'hashtag': | |
case 'cashtag': | |
case 'bot_command': | |
case 'url': | |
case 'email': | |
case 'phone_number': | |
$html .= mb_substr($text, $entity->getOffset(), $entity->getLength()); | |
break; | |
case 'text_mention': | |
$html .= '<a href="tg://user?id='.$entity->getUser()->getId().'">'.mb_substr($text, $entity->getOffset(), $entity->getLength()).'</a>'; | |
break; | |
case 'text_link': | |
$html .= '<a href="'.$entity->getUrl().'">'.mb_substr($text, $entity->getOffset(), $entity->getLength()).'</a>'; | |
break; | |
case 'bold': | |
$html .= '<b>' . mb_substr($text, $entity->getOffset(), $entity->getLength()) . '</b>'; | |
break; | |
case 'italic': | |
$html .= '<i>' . mb_substr($text, $entity->getOffset(), $entity->getLength()) . '</i>'; | |
break; | |
case 'code': | |
$html .= '<code>' . mb_substr($text, $entity->getOffset(), $entity->getLength()) . '</code>'; | |
break; | |
case 'pre': | |
$html .= '<pre>' . mb_substr($text, $entity->getOffset(), $entity->getLength()) . '</pre>'; | |
break; | |
} | |
if($k === $entities_count){ | |
$html .= mb_substr($text, $entity->getOffset() + $entity->getLength()); | |
} | |
} | |
return $html; | |
} |
Thanks, @LeonidShastel , used your code and added typescript types to use with grammY
import type { Context } from 'grammy';
import type { MessageEntity } from 'grammy/out/types.node';
export const parseTelegramMessage = (ctx: Context) => {
const text = ctx.msg?.text;
const entities = ctx.msg?.entities;
if (!entities || !text) {
return text;
}
let tags: { index: number; tag: string | undefined }[] = [];
entities.forEach((entity) => {
const startTag = getTag(entity, text);
let searchTag = tags.filter((tag) => tag.index === entity.offset);
if (searchTag.length > 0 && startTag) searchTag[0].tag += startTag;
else
tags.push({
index: entity.offset,
tag: startTag
});
const closeTag = startTag?.indexOf('<a ') === 0 ? '</a>' : '</' + startTag?.slice(1);
searchTag = tags.filter((tag) => tag.index === entity.offset + entity.length);
if (searchTag.length > 0) searchTag[0].tag = closeTag + searchTag[0].tag;
else
tags.push({
index: entity.offset + entity.length,
tag: closeTag
});
});
let html = '';
for (let i = 0; i < text.length; i++) {
const tag = tags.filter((tag) => tag.index === i);
tags = tags.filter((tag) => tag.index !== i);
if (tag.length > 0) html += tag[0].tag;
html += text[i];
}
if (tags.length > 0) html += tags[0].tag;
return html;
};
const getTag = (entity: MessageEntity, text: string) => {
const entityText = text.slice(entity.offset, entity.offset + entity.length);
switch (entity.type) {
case 'bold':
return `<strong>`;
case 'text_link':
return `<a href="${entity.url}" target="_blank">`;
case 'url':
return `<a href="${entityText}" target="_blank">`;
case 'italic':
return `<em>`;
case 'code':
return `<code>`;
case 'strikethrough':
return `<s>`;
case 'underline':
return `<u>`;
case 'pre':
return `<pre>`;
case 'mention':
return `<a href="https://t.me/${entityText.replace('@', '')}" target="_blank">`;
case 'email':
return `<a href="mailto:${entityText}">`;
case 'phone_number':
return `<a href="tel:${entityText}">`;
}
};
Function for @mtproto/core, for parsing messages
export const parseTelegramMessage = function (msg) {
const text = msg.message || msg.caption;
const entities = msg.entities || msg.caption_entities;
if (!entities) {
return text;
}
let html = "";
entities.forEach((entity, index) => {
// Characters before entity
if (index === 0) {
html += text.slice(0, entity.offset);
}
// Handle entity transformation
const entityText = text.slice(
entity.offset,
entity.offset + entity.length
);
switch (entity._) {
case "messageEntityBold":
html += `<strong>${entityText}</strong>`;
break;
case "messageEntityPre":
html += `<pre>${entityText}</pre>`;
break;
case "messageEntityCode":
html += `<code>${entityText}</code>`;
break;
case "messageEntityStrike":
html += `<s>${entityText}</s>`;
break;
case "messageEntityUnderline":
html += `<u>${entityText}</u>`;
break;
case "messageEntitySpoiler":
html += `<span class="tg-spoiler">${entityText}</span>`;
break;
case "messageEntityUrl":
case "messageEntityTextUrl":
html += `<a href="${entity.url}" target="_blank">${entityText}</a>`;
break;
case "messageEntityItalic":
html += `<em>${entityText}</em>`;
break;
case "messageEntityMention":
html += `<a href="https://t.me/${entityText.replace(
"@",
""
)}" target="_blank">${entityText}</a>`;
break;
case "messageEntityEmail":
html += `<a href="mailto:${entityText}">${entityText}</a>`;
break;
case "messageEntityPhone":
html += `<a href="tel:${entityText}">${entityText}</a>`;
break;
default:
html += `${entityText}`;
}
// Characters after entity but before next entity
if (entities.length > index + 1) {
html += text.slice(
entity.offset + entity.length,
entities[index + 1].offset
);
}
// Last characters after last entity
if (entities.length === index + 1) {
html += text.slice(entity.offset + entity.length);
}
});
return html;
};
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Guys, your codes gave me basic ideas and I made my own Python3 solution. It works with nested entities too.
https://github.com/survtur/TelethonMessageToHtmlConverter