reverse-engineering-anything/src/domain/analysisView/environmentStateWriteComposed.ts

import type { JsonValue } from "../jsonValue.js";
import {
  ownMember,
  same,
  scalarText,
  type JsonObject,
} from "./environmentStateRules.js";
import { COPY_MIN_LENGTH } from "./environmentStateWriteCopies.js";
import { GENERATED } from "./environmentStateWriteGenerated.js";
import type { ComposedPart, FieldRule } from "./environmentStateWriteRules.js";
import {
  joinsAfter,
  joinsBefore,
  readClock,
  slugOf,
  slugSpellings,
  zoneMinutesForFormat,
} from "./environmentStateWriteValues.js";
import {
  CLOCK_PATTERNS,
  clockDigits,
} from "./environmentStateWriteClockFormats.js";

type SourcePart = Exclude<ComposedPart, { readonly text: string }>;

/** Text a field's value offers a composed string, and the part that spells it. */
interface Candidate {
  readonly token: string;
  readonly part: SourcePart;
}

/** Rules whose field holds a value the call or serving decides, which a created composed string may show. */
const SOURCES: ReadonlySet<FieldRule["rule"]> = new Set([
  ...GENERATED,
  "echo",
  "copy",
  "path",
  "slug",
  "clock",
]);

/** The text a part spells from written fields; undefined when its field holds nothing it can spell. */
export const composedPartText = (
  part: ComposedPart,
  fields: JsonObject,
): string | undefined => {
  if ("text" in part) return part.text;
  const value = ownMember(fields, part.from);
  if (part.as === "clock") return clockDigits(value, part.pattern);
  if (part.as === "value") return scalarText(value);
  return typeof value === "string" ? slugOf(value, part.ampersand) : undefined;
};

/** A composed string spelled from written fields, or undefined when a part has nothing to spell. */
export const composedValue = (
  parts: readonly ComposedPart[],
  fields: JsonObject,
): string | undefined => {
  let text = "";
  for (const part of parts) {
    const spelled = composedPartText(part, fields);
    if (spelled === undefined) return undefined;
    text += spelled;
  }
  return text;
};

/** The texts a field's value offers: itself and its slug when long enough to show it, and a clock's calendar digits. */
const candidatesOf = (
  field: string,
  value: JsonValue | undefined,
  shortest: number,
): Candidate[] => {
  const candidates: Candidate[] = [];
  const text = scalarText(value);
  if (text !== undefined && text.length >= shortest)
    candidates.push({ token: text, part: { from: field, as: "value" } });
  if (typeof value === "string")
    for (const { slug, ampersand } of slugSpellings(value))
      if (slug !== value && slug.length >= COPY_MIN_LENGTH)
        candidates.push({
          token: slug,
          part: {
            from: field,
            as: "slug",
            ...(ampersand === undefined ? {} : { ampersand }),
          },
        });
  if (readClock(value) !== undefined)
    for (const pattern of CLOCK_PATTERNS) {
      const digits = clockDigits(value, pattern);
      if (digits !== undefined)
        candidates.push({
          token: digits,
          part: { from: field, as: "clock", pattern },
        });
    }
  return candidates;
};

/** Candidates by their text, and the lengths those texts take, longest first: looked up per position rather than searched. */
interface CandidateIndex {
  readonly byToken: ReadonlyMap<string, readonly Candidate[]>;
  readonly lengths: readonly number[];
}

const indexed = (candidates: readonly Candidate[]): CandidateIndex => {
  const byToken = new Map<string, Candidate[]>();
  for (const candidate of candidates) {
    const same = byToken.get(candidate.token);
    if (same === undefined) byToken.set(candidate.token, [candidate]);
    else same.push(candidate);
  }
  const lengths = [...new Set(candidates.map(({ token }) => token.length))];
  return { byToken, lengths: lengths.sort((left, right) => right - left) };
};

/** The longest candidates whose text starts at a position and ends at a delimiter. */
const matchesAt = (
  text: string,
  at: number,
  index: CandidateIndex,
): readonly Candidate[] => {
  if (joinsBefore(text, at)) return [];
  for (const length of index.lengths) {
    if (at + length > text.length || joinsAfter(text, at + length)) continue;
    const matches = index.byToken.get(text.slice(at, at + length));
    if (matches !== undefined) return matches;
  }
  return [];
};

/** Parts with each slug of a source holding no `&` spelling it as the word, or undefined when no such slug part exists. */
const ampersandWord = (
  parts: readonly ComposedPart[],
  entity: JsonObject,
): ComposedPart[] | undefined => {
  let changed = false;
  const spelled = parts.map((part): ComposedPart => {
    if (!("as" in part) || part.as !== "slug" || part.ampersand !== undefined)
      return part;
    const source = ownMember(entity, part.from);
    if (typeof source === "string" && source.includes("&")) return part;
    changed = true;
    return { ...part, ampersand: "and" };
  });
  return changed ? spelled : undefined;
};

/** More ways to read one string than this leave it unexplained. */
const MAX_SEGMENTATIONS = 8;

/**
 * Literal text around the longest delimited candidate at each position, left to right: one reading per choice where
 * sources serving could tell apart spell the same text, which other entities then tell apart. Empty when no candidate
 * shows, or the choices exceed `MAX_SEGMENTATIONS`. `alike` names parts serving fills with one value.
 */
const segmentations = (
  text: string,
  index: CandidateIndex,
  alike: (left: SourcePart, right: SourcePart) => boolean,
): ComposedPart[][] => {
  let readings: ComposedPart[][] = [[]];
  let literal = "";
  let shown = false;
  for (let at = 0; at < text.length;) {
    const matches = matchesAt(text, at, index);
    if (matches.length === 0) {
      literal += text[at];
      at += 1;
      continue;
    }
    // Stop at the cap before comparing or allocating more, however many sources spell the text.
    const choices: SourcePart[] = [];
    for (const { part } of matches)
      if (!choices.some((choice) => alike(choice, part))) {
        choices.push(part);
        if (readings.length * choices.length > MAX_SEGMENTATIONS) return [];
      }
    const lead: ComposedPart[] = literal === "" ? [] : [{ text: literal }];
    readings = readings.flatMap((parts) =>
      choices.map((choice) => [...parts, ...lead, choice]),
    );
    literal = "";
    shown = true;
    at += matches[0]!.token.length;
  }
  if (!shown) return [];
  return literal === ""
    ? readings
    : readings.map((parts) => [...parts, { text: literal }]);
};

const samePart = (left: SourcePart, right: SourcePart): boolean =>
  left.from === right.from &&
  left.as === right.as &&
  (left.as !== "clock" ||
    right.as !== "clock" ||
    left.pattern === right.pattern) &&
  (left.as !== "slug" ||
    right.as !== "slug" ||
    left.ampersand === right.ampersand);

/** How many entities holding the field and what its parts read spell it as the parts do, or undefined when one holds it otherwise, a non-string value included. */
const heldSpellings = (
  parts: readonly ComposedPart[],
  field: string,
  held: readonly JsonObject[],
): number | undefined => {
  let agreeing = 0;
  for (const entity of held) {
    if (!Object.hasOwn(entity, field)) continue;
    const spelled = composedValue(parts, entity);
    if (spelled === undefined) continue;
    if (spelled !== entity[field]) return undefined;
    agreeing += 1;
  }
  return agreeing;
};

/**
 * For a created entity, each string field rebuilt from literal text and the fields other rules write, when it shows
 * at least one and the type's other entities spell it the same way, at least one of them: one call alone cannot show
 * which text is literal.
 */
export const createdComposer = (
  entity: JsonObject,
  rules: readonly FieldRule[],
  held: readonly JsonObject[],
): ((field: string) => FieldRule | undefined) => {
  // Serving stamps every clock a create writes with the one write clock, so their digits in one zone are one source.
  const zones = new Map(
    rules.flatMap((rule) =>
      rule.rule === "clock"
        ? [
            [
              rule.field,
              rule.format.kind === "iso"
                ? zoneMinutesForFormat(rule.format.zone)
                : 0,
            ] as const,
          ]
        : [],
    ),
  );
  const alike = (left: SourcePart, right: SourcePart): boolean =>
    samePart(left, right) ||
    (left.as === "clock" &&
      right.as === "clock" &&
      left.pattern === right.pattern &&
      zones.has(left.from) &&
      zones.get(left.from) === zones.get(right.from));
  let index: CandidateIndex | undefined;
  return (field) => {
    const text = ownMember(entity, field);
    if (typeof text !== "string") return undefined;
    index ??= indexed(
      rules.flatMap((rule) =>
        SOURCES.has(rule.rule)
          ? candidatesOf(
              rule.field,
              ownMember(entity, rule.field),
              // A generated value is short and still the call's own, as a template's is.
              GENERATED.has(rule.rule) ? 1 : COPY_MIN_LENGTH,
            )
          : [],
      ),
    );
    const fits = segmentations(text, index, alike).flatMap((parts) => {
      if (parts.some((part) => "from" in part && part.from === field))
        return [];
      // A slug whose source here holds no `&` spells it as the held entities do.
      const spelled = [parts, ampersandWord(parts, entity)].find(
        (candidate) =>
          candidate !== undefined &&
          (heldSpellings(candidate, field, held) ?? 0) > 0,
      );
      return spelled === undefined ? [] : [spelled];
    });
    return fits.length === 1
      ? { field, rule: "composed", parts: fits[0]! }
      : undefined;
  };
};

/**
 * An unsent string field an update rebuilt from literal text and fields serving knows, members stored as sent and those
 * the call left as they were: the same parts spell it before the call and on the type's other entities.
 */
export const composedChange = (
  field: string,
  entity: {
    readonly before: JsonObject;
    readonly after: JsonObject;
    readonly sent: JsonObject;
    readonly idField: string;
    readonly others: readonly JsonObject[];
  },
): FieldRule | undefined => {
  const { before, after, sent, idField } = entity;
  const text = ownMember(after, field);
  if (typeof text !== "string" || typeof ownMember(before, field) !== "string")
    return undefined;
  const known = Object.keys(after).filter(
    (other) =>
      other !== field &&
      (Object.hasOwn(sent, other)
        ? same(sent[other], after[other])
        : Object.hasOwn(before, other) && same(before[other], after[other])),
  );
  const index = indexed(
    known.flatMap((other) =>
      candidatesOf(
        other,
        ownMember(after, other),
        other === idField ? 1 : COPY_MIN_LENGTH,
      ),
    ),
  );
  const fits = segmentations(text, index, samePart).filter(
    (parts) =>
      composedValue(parts, before) === ownMember(before, field) &&
      heldSpellings(parts, field, entity.others) !== undefined,
  );
  return fits.length === 1
    ? { field, rule: "composed", parts: fits[0]! }
    : undefined;
};