Rooba
/
Diskernet
mirror of https://github.com/crisdosyago/Diskernet.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

"Up todo - time to test up-to-date text implementation"

This commit is contained in:
Cris Stringfellow 2021-12-30 00:58:39 +08:00
parent b4299f7d10
commit d98fd94534
3 changed files with 85 additions and 33 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
docs/todo
View File

@ -1,6 +1,3 @@
- sometimes snippets do not appear (e.g. avenger endgame google search result for hemsworth query)
- this is because text is too short. So let's combine this with other issue.
- [COMBINE] ensure we are getting the page text to index once it is actually loaded (we should call again later, or add mutation observer and update on mutate) then send console message to the controller ({textChanged}), to trigger indexURL again
- complete snippet generation
- improve trigram segmenter: lower max segment length, increase fore and aft context
- Index.json is randomly getting clobbered sometimes. Investigate and fix. Important because this breaks the whole archive.

86
public/injection.js
View File

@ -1,6 +1,6 @@
import {DEBUG as debug} from '../src/common.js';
const DEBUG = debug || true;
const DEBUG = debug || false;
export function getInjection({sessionId}) {
// Notes:
@ -80,10 +80,10 @@ export function getInjection({sessionId}) {
}
function beginTextNotifications() {
// listen for {textChanged:true} messages
// listen for {textChange:true} messages
// throttle them
// on leading throttle edge send message to controller with
// console.info(JSON.stringify({textChanged:true}));
// console.info(JSON.stringify({textChange:...}));
self.addEventListener('message', messageParser);
console.log('Begun notifying of text changes.');
@ -91,23 +91,23 @@ export function getInjection({sessionId}) {
function messageParser({data, origin}) {
let source;
try {
({source} = data.frameTextChangedNotification);
({source} = data.frameTextChangeNotification);
if ( count > MAX_NOTIFICATIONS ) {
self.removeEventListener('message', messageParser);
return;
}
count++;
handler({textChanged:{source}});
handler({textChange:{source}});
} catch(e) {
DEBUG && console.warn('could not parse message', data, e);
}
}
}
function handleFrameMessage({textChanged}) {
const {source} = textChanged;
function handleFrameMessage({textChange}) {
const {source} = textChange;
console.log('Telling controller that text changed');
say({textChanged:true, source, count});
say({textChange:{source, sessionId, count}});
}
}
@ -117,7 +117,7 @@ export function getInjection({sessionId}) {
// create mutation observer for text
// throttle output
const observer = new MutationObserver(check, /*throttle(check, MIN_CHECK_TEXT)*/);
const observer = new MutationObserver(throttle(check, MIN_CHECK_TEXT));
observer.observe(document.documentElement || document, OBSERVER_OPTS);
console.log('Begun observing text changes.');
@ -128,23 +128,67 @@ export function getInjection({sessionId}) {
if ( textMutated ) {
DEBUG && console.log('Text changed');
lastInnerText = document.documentElement.innerText;
Top.postMessage({frameTextChangedNotification:{source:location.href}}, '*');
Top.postMessage({frameTextChangeNotification:{source:location.href}}, '*');
}
}
}
// javascript throttle function
// source: https://stackoverflow.com/a/59378445
function throttle(func, timeFrame) {
var lastTime = 0;
return function (...args) {
var now = new Date();
if (now - lastTime >= timeFrame) {
func.apply(this, args);
lastTime = now;
}
};
}
// source: https://stackoverflow.com/a/59378445
/*
function throttle(func, timeFrame) {
var lastTime = 0;
return function (...args) {
var now = new Date();
if (now - lastTime >= timeFrame) {
func.apply(this, args);
lastTime = now;
}
};
}
*/
// alternate throttle function with trailing edge call
// source: https://stackoverflow.com/a/27078401
///*
// Notes
// Returns a function, that, when invoked, will only be triggered at most once
// during a given window of time. Normally, the throttled function will run
// as much as it can, without ever going more than once per \`wait\` duration;
// but if you'd like to disable the execution on the leading edge, pass
// \`{leading: false}\`. To disable execution on the trailing edge, ditto.
function throttle(func, wait, options) {
var context, args, result;
var timeout = null;
var previous = 0;
if (!options) options = {};
var later = function() {
previous = options.leading === false ? 0 : Date.now();
timeout = null;
result = func.apply(context, args);
if (!timeout) context = args = null;
};
return function() {
var now = Date.now();
if (!previous && options.leading === false) previous = now;
var remaining = wait - (now - previous);
context = this;
args = arguments;
if (remaining <= 0 || remaining > wait) {
if (timeout) {
clearTimeout(timeout);
timeout = null;
}
previous = now;
result = func.apply(context, args);
if (!timeout) context = args = null;
} else if (!timeout && options.trailing !== false) {
timeout = setTimeout(later, remaining);
}
return result;
};
}
//*/
}
`;
}

29
src/archivist.js
View File

@ -246,13 +246,16 @@ export default Archivist;
try {
const val = JSON.parse(strVal);
// possible messages
const {install, titleChange} = val;
const {install, titleChange, textChange} = val;
switch(true) {
case !!install: {
confirmInstall({install});
} break;
case !!titleChange: {
reindexOnTitleChange({titleChange});
reindexOnContentChange({titleChange});
} break;
case !!textChanged: {
reindexOnContentChange({textChanged});
} break;
default: {
if ( DEBUG ) {
@ -274,13 +277,21 @@ export default Archivist;
}
}
async function reindexOnTitleChange({titleChange}) {
const {currentTitle, sessionId} = titleChange;
DEBUG && console.log('Received titleChange', titleChange);
const latestTargetInfo = clone(await untilHas(Targets, sessionId));
latestTargetInfo.title = currentTitle;
Targets.set(sessionId, latestTargetInfo);
DEBUG && console.log('Updated stored target info', latestTargetInfo);
async function reindexOnContentChange({titleChange, textChange}) {
let latestTargetInfo;
if ( titleChange ) {
const {currentTitle, sessionId} = titleChange;
DEBUG && console.log('Received titleChange', titleChange);
latestTargetInfo = clone(await untilHas(Targets, sessionId));
latestTargetInfo.title = currentTitle;
Targets.set(sessionId, latestTargetInfo);
DEBUG && console.log('Updated stored target info', latestTargetInfo);
} else if ( textChange ) {
const DEBUG = true;
const {sessionId} = textChange;
latestTargetInfo = clone(await untilHas(Targets, sessionId));
DEBUG && console.log(`Will reindex because we were told text content maybe changed.`);
}
indexURL({targetInfo:latestTargetInfo});
}