dbieber/Arxiv PDF Title Updater for Hypothesis Pages.js

## Arxiv PDF Title Updater for Hypothesis Pages.js
// ==UserScript==
// @name         Arxiv PDF Title Updater for Hypothesis Pages
// @namespace    http://tampermonkey.net/
// @version      1.2
// @description  Update Arxiv PDF links titles on Hypothesis pages
// @author       David Bieber + GPT-4
// @match        *://*.hypothes.is/*
// @grant        GM_xmlhttpRequest
// ==/UserScript==

(async function() {
    'use strict';

    // Utility function to extract ArxivIDs
    function extractArxivIDs(links) {
        const arxivIDs = [];
        const arxivIDRegex = /(\d+\.\d+)(v\d+)?\.pdf/;

        for (const link of links) {
            const match = link.textContent.match(arxivIDRegex);
            if (match) {
                arxivIDs.push(match[1]);
            }
        }

        console.log('ArxivIDs found on Hypothesis page:', arxivIDs);
        return arxivIDs;
    }

    // Utility function to query the Arxiv API
    async function queryArxivAPI(ids) {
        return new Promise((resolve, reject) => {
            const arxivAPI = `http://export.arxiv.org/api/query?id_list=${ids.join(',')}`;

            GM_xmlhttpRequest({
                method: 'GET',
                url: arxivAPI,
                onload: function(response) {
                    if (response.status >= 200 && response.status < 400) {
                        resolve(response.responseText);
                    } else {
                        reject(new Error('Error querying the Arxiv API'));
                    }
                },
                onerror: function() {
                    reject(new Error('Error querying the Arxiv API'));
                },
            });
        });
    }

    // Utility function to split an array into chunks
    function chunkArray(array, size) {
        const chunks = [];
        for (let i = 0; i < array.length; i += size) {
            chunks.push(array.slice(i, i + size));
        }
        return chunks;
    }

    // Utility function to update the link titles on the Hypothesis page
    function updateLinkTitles(links, titles) {
        for (const link of links) {
            const match = link.textContent.match(/(\d+\.\d+)(v\d+)?\.pdf/);
            if (match) {
                const arxivID = match[1];
                if (titles.hasOwnProperty(arxivID)) {
                    link.textContent = titles[arxivID];
                }
            }
        }
    }

    // Get all the links on the Hypothesis page
    const links = document.querySelectorAll('a[data-ref="title"]');

    // Extract the ArxivIDs
    const arxivIDs = extractArxivIDs(links);

    // Query the Arxiv API and update the link titles
    if (arxivIDs.length > 0) {
        try {
            const titles = {};
            const arxivIDChunks = chunkArray(arxivIDs, 10);

            for (const chunk of arxivIDChunks) {
                const responseText = await queryArxivAPI(chunk);
                const parser = new DOMParser();
                const xmlDoc = parser.parseFromString(responseText, 'application/xml');
                const entries = xmlDoc.getElementsByTagName('entry');

                for (const entry of entries) {
                    const idElement = entry.querySelector('id');
                    const titleElement = entry.querySelector('title');

                    if (idElement && titleElement) {
                        let arxivID = idElement.textContent.split('/').pop();
                        // Remove version suffix (e.g., "v1")
                        arxivID = arxivID.replace(/v\d+$/, '');
                        const title = titleElement.textContent.trim();
                        titles[arxivID] = title;
                    }
                }
            }

            console.log('Arxiv titles fetched:', titles);
            updateLinkTitles(links, titles);
        } catch (error) {
            console.error('Failed to update Arxiv PDF link titles:', error);
        }
    }
})();
	// ==UserScript==
	// @name Arxiv PDF Title Updater for Hypothesis Pages
	// @namespace http://tampermonkey.net/
	// @version 1.2
	// @description Update Arxiv PDF links titles on Hypothesis pages
	// @author David Bieber + GPT-4
	// @match ://.hypothes.is/*
	// @grant GM_xmlhttpRequest
	// ==/UserScript==

	(async function() {
	'use strict';

	// Utility function to extract ArxivIDs
	function extractArxivIDs(links) {
	const arxivIDs = [];
	const arxivIDRegex = /(\d+\.\d+)(v\d+)?\.pdf/;

	for (const link of links) {
	const match = link.textContent.match(arxivIDRegex);
	if (match) {
	arxivIDs.push(match[1]);
	}
	}

	console.log('ArxivIDs found on Hypothesis page:', arxivIDs);
	return arxivIDs;
	}

	// Utility function to query the Arxiv API
	async function queryArxivAPI(ids) {
	return new Promise((resolve, reject) => {
	const arxivAPI = `http://export.arxiv.org/api/query?id_list=${ids.join(',')}`;

	GM_xmlhttpRequest({
	method: 'GET',
	url: arxivAPI,
	onload: function(response) {
	if (response.status >= 200 && response.status < 400) {
	resolve(response.responseText);
	} else {
	reject(new Error('Error querying the Arxiv API'));
	}
	},
	onerror: function() {
	reject(new Error('Error querying the Arxiv API'));
	},
	});
	});
	}

	// Utility function to split an array into chunks
	function chunkArray(array, size) {
	const chunks = [];
	for (let i = 0; i < array.length; i += size) {
	chunks.push(array.slice(i, i + size));
	}
	return chunks;
	}

	// Utility function to update the link titles on the Hypothesis page
	function updateLinkTitles(links, titles) {
	for (const link of links) {
	const match = link.textContent.match(/(\d+\.\d+)(v\d+)?\.pdf/);
	if (match) {
	const arxivID = match[1];
	if (titles.hasOwnProperty(arxivID)) {
	link.textContent = titles[arxivID];
	}
	}
	}
	}

	// Get all the links on the Hypothesis page
	const links = document.querySelectorAll('a[data-ref="title"]');

	// Extract the ArxivIDs
	const arxivIDs = extractArxivIDs(links);

	// Query the Arxiv API and update the link titles
	if (arxivIDs.length > 0) {
	try {
	const titles = {};
	const arxivIDChunks = chunkArray(arxivIDs, 10);

	for (const chunk of arxivIDChunks) {
	const responseText = await queryArxivAPI(chunk);
	const parser = new DOMParser();
	const xmlDoc = parser.parseFromString(responseText, 'application/xml');
	const entries = xmlDoc.getElementsByTagName('entry');

	for (const entry of entries) {
	const idElement = entry.querySelector('id');
	const titleElement = entry.querySelector('title');

	if (idElement && titleElement) {
	let arxivID = idElement.textContent.split('/').pop();
	// Remove version suffix (e.g., "v1")
	arxivID = arxivID.replace(/v\d+$/, '');
	const title = titleElement.textContent.trim();
	titles[arxivID] = title;
	}
	}
	}

	console.log('Arxiv titles fetched:', titles);
	updateLinkTitles(links, titles);
	} catch (error) {
	console.error('Failed to update Arxiv PDF link titles:', error);
	}
	}
	})();