anki/ts/graphs/card-counts.ts
Damien Elmes 37151213cd Move more of the graph processing into the backend
The existing architecture serializes all cards and revlog entries in
the search range into a protobuf message, which the web frontend needs
to decode and then process. The thinking at the time was that this would
make it easier for add-ons to add extra graphs, but in the ~2.5 years
since the new graphs were introduced, no add-ons appear to have taken
advantage of it.

The cards and revlog entries can grow quite large on large collections -
on a collection I tested with approximately 2.5M reviews, the serialized
data is about 110MB, which is a lot to have to deserialize in JavaScript.

This commit shifts the preliminary processing of the data to the Rust end,
which means the data is able to be processed faster, and less needs to
be sent to the frontend. On the test collection above, this reduces the
serialized data from about 110MB to about 160KB, resulting in a more
than 2x performance improvement, and reducing frontend memory usage from
about 400MB to about 40MB.

This also makes #2043 more feasible - while it is still about 50-100%
slower than protobufjs, with the much smaller message size, the difference
is only about 10ms.
2022-12-16 21:42:17 +10:00

190 lines
5.4 KiB
TypeScript

// Copyright: Ankitects Pty Ltd and contributors
// License: GNU AGPL, version 3 or later; http://www.gnu.org/licenses/agpl.html
/* eslint
@typescript-eslint/no-explicit-any: "off",
*/
import * as tr from "@tslib/ftl";
import { localizedNumber } from "@tslib/i18n";
import type { Stats } from "@tslib/proto";
import {
arc,
cumsum,
interpolate,
pie,
scaleLinear,
schemeBlues,
schemeGreens,
schemeOranges,
schemeReds,
select,
sum,
} from "d3";
import type { GraphBounds } from "./graph-helpers";
type Count = [string, number, boolean, string];
export interface GraphData {
title: string;
counts: Count[];
totalCards: string;
}
const barColours = [
schemeBlues[5][2], /* new */
schemeOranges[5][2], /* learn */
schemeReds[5][2], /* relearn */
schemeGreens[5][2], /* young */
schemeGreens[5][3], /* mature */
"#FFDC41", /* suspended */
"grey", /* buried */
];
function countCards(data: Stats.GraphsResponse, separateInactive: boolean): Count[] {
const countData = separateInactive ? data.cardCounts!.excludingInactive! : data.cardCounts!.includingInactive!;
const extraQuery = separateInactive ? "AND -(\"is:buried\" OR \"is:suspended\")" : "";
const counts: Count[] = [
[tr.statisticsCountsNewCards(), countData.newCards, true, `"is:new"${extraQuery}`],
[
tr.statisticsCountsLearningCards(),
countData.learn,
true,
`(-"is:review" AND "is:learn")${extraQuery}`,
],
[
tr.statisticsCountsRelearningCards(),
countData.relearn,
true,
`("is:review" AND "is:learn")${extraQuery}`,
],
[
tr.statisticsCountsYoungCards(),
countData.young,
true,
`("is:review" AND -"is:learn") AND "prop:ivl<21"${extraQuery}`,
],
[
tr.statisticsCountsMatureCards(),
countData.mature,
true,
`("is:review" -"is:learn") AND "prop:ivl>=21"${extraQuery}`,
],
[
tr.statisticsCountsSuspendedCards(),
countData.suspended,
separateInactive,
"\"is:suspended\"",
],
[tr.statisticsCountsBuriedCards(), countData.buried, separateInactive, "\"is:buried\""],
];
return counts;
}
export function gatherData(
data: Stats.GraphsResponse,
separateInactive: boolean,
): GraphData {
const counts = countCards(data, separateInactive);
const totalCards = localizedNumber(sum(counts, e => e[1]));
return {
title: tr.statisticsCountsTitle(),
counts,
totalCards,
};
}
export interface SummedDatum {
label: string;
// count of this particular item
count: number;
// show up in the table
show: boolean;
query: string;
// running total
total: number;
}
export interface TableDatum {
label: string;
count: string;
query: string;
percent: string;
colour: string;
}
export function renderCards(
svgElem: SVGElement,
bounds: GraphBounds,
sourceData: GraphData,
): TableDatum[] {
const summed = cumsum(sourceData.counts, (d: Count) => d[1]);
const data = Array.from(summed).map((n, idx) => {
const count = sourceData.counts[idx];
return {
label: count[0],
count: count[1],
show: count[2],
query: count[3],
idx,
total: n,
} as SummedDatum;
});
// ensuring a non-zero range makes the percentages not break
// in an empty collection
const xMax = Math.max(1, summed.slice(-1)[0]);
const x = scaleLinear().domain([0, xMax]);
const svg = select(svgElem);
const paths = svg.select(".counts");
const pieData = pie()(sourceData.counts.map((d: Count) => d[1]));
const radius = bounds.height / 2 - bounds.marginTop - bounds.marginBottom;
const arcGen = arc().innerRadius(0).outerRadius(radius);
const trans = svg.transition().duration(600) as any;
paths
.attr("transform", `translate(${radius},${radius + bounds.marginTop})`)
.selectAll("path")
.data(pieData)
.join(
(enter) =>
enter
.append("path")
.attr("fill", (_d, idx) => {
return barColours[idx];
})
.attr("d", arcGen as any),
function(update) {
return update.call((d) =>
d.transition(trans).attrTween("d", (d) => {
const interpolator = interpolate(
{ startAngle: 0, endAngle: 0 },
d,
);
return (t): string => arcGen(interpolator(t) as any) as string;
})
);
},
);
x.range([bounds.marginLeft, bounds.width - bounds.marginRight]);
const tableData = data.flatMap((d: SummedDatum, idx: number) => {
const percent = localizedNumber((d.count / xMax) * 100, 2);
return d.show
? ({
label: d.label,
count: localizedNumber(d.count),
percent: `${percent}%`,
colour: barColours[idx],
query: d.query,
} as TableDatum)
: [];
});
return tableData;
}