history-collector/extension/service-worker.js

import { CONFIG } from "./config.js";

const HOST = "si.komelt.local_history_archive";
const LEGACY_QUEUE_KEY = "pendingVisits";
const LOCAL_QUEUE_KEY = "pendingLocalVisits";
const REMOTE_QUEUE_KEY = "pendingRemoteVisits";
const MAX_QUEUE = 2000;
const MAX_REMOTE_URL_LENGTH = 2083;

let operationTail = Promise.resolve();
let runtimeSettings = CONFIG;
let flushInProgress = false;
let flushRequested = false;
let activeFlush = null;

async function refreshRuntimeSettings() {
  try {
    const managed = await chrome.storage.managed.get(["collectorUrl", "apiToken", "deviceId"]);
    runtimeSettings = {
      collectorUrl: typeof managed.collectorUrl === "string" ? managed.collectorUrl : CONFIG.collectorUrl,
      apiToken: typeof managed.apiToken === "string" ? managed.apiToken : CONFIG.apiToken,
      deviceId: typeof managed.deviceId === "string" ? managed.deviceId : CONFIG.deviceId
    };
  } catch (error) {
    console.warn("Managed extension settings unavailable", error?.message || error);
  }
}

function runSerialized(operation) {
  const next = operationTail.then(operation, operation);
  operationTail = next.catch((error) => {
    console.warn("Queued operation failed", error?.message || error);
  });
  return next;
}

function capped(visits) {
  return visits.slice(-MAX_QUEUE);
}

async function readQueues() {
  const values = await chrome.storage.local.get([
    LEGACY_QUEUE_KEY,
    LOCAL_QUEUE_KEY,
    REMOTE_QUEUE_KEY
  ]);
  return {
    legacy: Array.isArray(values[LEGACY_QUEUE_KEY]) ? values[LEGACY_QUEUE_KEY] : [],
    local: Array.isArray(values[LOCAL_QUEUE_KEY]) ? values[LOCAL_QUEUE_KEY] : [],
    remote: Array.isArray(values[REMOTE_QUEUE_KEY]) ? values[REMOTE_QUEUE_KEY] : []
  };
}

async function snapshotQueues() {
  return runSerialized(async () => {
    const { legacy, local, remote } = await readQueues();
    const localVisits = capped(legacy.length ? [...legacy, ...local] : local);
    const remoteVisits = capped(
      legacy.length && remoteEnabled()
        ? [...legacy.filter(isRemoteVisit), ...remote]
        : remote
    );

    if (
      legacy.length
      || localVisits.length !== local.length
      || remoteVisits.length !== remote.length
    ) {
      const update = {
        [LOCAL_QUEUE_KEY]: localVisits,
        [REMOTE_QUEUE_KEY]: remoteVisits
      };
      if (legacy.length) update[LEGACY_QUEUE_KEY] = [];
      await chrome.storage.local.set(update);
    }

    return { localVisits, remoteVisits };
  });
}

function sameQueueItem(left, right) {
  return JSON.stringify(left) === JSON.stringify(right);
}

function deliveredItemsStillQueued(current, snapshot, offset, deliveredCount) {
  const confirmed = snapshot.slice(offset, offset + deliveredCount);
  if (confirmed.length !== deliveredCount || current.length < deliveredCount) return 0;
  for (let index = 0; index < deliveredCount; index += 1) {
    if (!sameQueueItem(current[index], confirmed[index])) return 0;
  }
  return deliveredCount;
}

async function acknowledgeQueuePrefix(key, snapshot, offset, deliveredCount) {
  if (!deliveredCount) return;
  try {
    await runSerialized(async () => {
      const { [key]: current = [] } = await chrome.storage.local.get(key);
      const visits = Array.isArray(current) ? current : [];
      const removeCount = deliveredItemsStillQueued(visits, snapshot, offset, deliveredCount);
      if (removeCount) {
        await chrome.storage.local.set({ [key]: capped(visits.slice(removeCount)) });
      }
    });
  } catch (error) {
    console.warn("Could not acknowledge queued visits", error?.message || error);
  }
}

function remoteEnabled() {
  return Boolean(runtimeSettings.collectorUrl && runtimeSettings.apiToken);
}
function isRemoteVisit(visit) {
  return isHttpUrl(visit?.url) && visit.url.length <= MAX_REMOTE_URL_LENGTH;
}

async function enqueueVisit(visit) {
  await refreshRuntimeSettings();
  try {
    await runSerialized(async () => {
      const { legacy, local, remote } = await readQueues();
      const localVisits = [...(legacy.length ? legacy : []), ...local, visit];
      const remoteVisits = [
        ...(legacy.length && remoteEnabled() ? legacy.filter(isRemoteVisit) : []),
        ...remote
      ];
      if (remoteEnabled() && isRemoteVisit(visit)) remoteVisits.push(visit);

      const update = {
        [LOCAL_QUEUE_KEY]: capped(localVisits),
        [REMOTE_QUEUE_KEY]: capped(remoteVisits)
      };
      if (legacy.length) update[LEGACY_QUEUE_KEY] = [];
      await chrome.storage.local.set(update);
    });
    requestFlush();
  } catch (error) {
    console.warn("Could not queue visit", error?.message || error);
  }
}

async function archiveLocally(visits) {
  if (!visits.length) return true;
  try {
    const reply = await chrome.runtime.sendNativeMessage(HOST, { type: "visits", visits });
    return reply?.ok === true;
  } catch (error) {
    console.warn("Local archive unavailable", error.message);
    return false;
  }
}
function isHttpUrl(url) {
  if (typeof url !== "string") return false;
  try {
    const protocol = new URL(url).protocol;
    return protocol === "http:" || protocol === "https:";
  } catch {
    return false;
  }
}
async function sendToCollector(visits, onChunkDelivered) {
  // Empty settings deliberately disable sending; the local SQLite archive still works.
  if (!remoteEnabled()) return false;
  const remoteVisits = visits
    .filter(isRemoteVisit)
    .map((visit) => ({
      ...visit,
      title: String(visit.title ?? "").slice(0, 1000)
    }));
  try {
    for (let offset = 0; offset < remoteVisits.length; offset += 100) {
      const chunk = remoteVisits.slice(offset, offset + 100);
      const response = await fetch(runtimeSettings.collectorUrl, {
        method: "POST",
        headers: {
          "Content-Type": "application/json",
          "Authorization": `Bearer ${runtimeSettings.apiToken}`
        },
        body: JSON.stringify({
          device_id: runtimeSettings.deviceId,
          visits: chunk
        })
      });
      if (!response.ok) {
        const detail = (await response.text()).trim().slice(0, 1000);
        throw new Error(`HTTP ${response.status}${detail ? `: ${detail}` : ""}`);
      }
      if (onChunkDelivered) await onChunkDelivered(offset, chunk.length);
    }
    return true;
  } catch (error) {
    console.warn("Collector unavailable", error.message);
    return false;
  }
}

async function flushOnce() {
  await refreshRuntimeSettings();
  const { localVisits, remoteVisits } = await snapshotQueues();
  if (!localVisits.length && !remoteVisits.length) return;

  const [localOk, remoteOk] = await Promise.all([
    archiveLocally(localVisits),
    sendToCollector(
      remoteVisits,
      (offset, deliveredCount) => acknowledgeQueuePrefix(
        REMOTE_QUEUE_KEY,
        remoteVisits,
        offset,
        deliveredCount
      )
    )
  ]);
  if (localOk && localVisits.length) {
    await acknowledgeQueuePrefix(LOCAL_QUEUE_KEY, localVisits, 0, localVisits.length);
  }
  if (remoteOk && remoteVisits.length) {
    await acknowledgeQueuePrefix(REMOTE_QUEUE_KEY, remoteVisits, 0, remoteVisits.length);
  }
}

async function flushLoop() {
  while (flushRequested) {
    flushRequested = false;
    try {
      await flushOnce();
    } catch (error) {
      console.warn("Queue flush failed", error?.message || error);
    }
  }
}

function requestFlush() {
  flushRequested = true;
  if (flushInProgress) return activeFlush;

  flushInProgress = true;
  activeFlush = flushLoop().catch((error) => {
    console.warn("Queue flush loop failed", error?.message || error);
  }).then(() => {
    flushInProgress = false;
    if (flushRequested) return requestFlush();
    return undefined;
  });
  return activeFlush;
}
chrome.history.onVisited.addListener((item) => {
  return enqueueVisit({
    url: item.url, title: item.title || "",
    visit_time: new Date(item.lastVisitTime || Date.now()).toISOString(),
    transition: "observed", source: "chrome-extension"
  });
});
chrome.downloads.onCreated.addListener((item) => {
  if (!isHttpUrl(item?.url)) return;
  const startTime = new Date(item.startTime || Date.now());
  return enqueueVisit({
    url: item.url,
    title: "",
    visit_time: Number.isNaN(startTime.getTime()) ? new Date().toISOString() : startTime.toISOString(),
    transition: "download",
    source: "chrome-extension"
  });
});
chrome.runtime.onStartup.addListener(() => requestFlush());
chrome.runtime.onInstalled.addListener(() => requestFlush());
chrome.alarms.create("local-history-archive-flush", { periodInMinutes: 1 });
chrome.alarms.onAlarm.addListener(() => requestFlush());