@underactive/pi-topping 0.5.0 → 0.6.0

package/src/word-packs.ts

@@ -0,0 +1,119 @@
+import { getAgentDir } from "@earendil-works/pi-coding-agent";
+import { readdirSync, readFileSync } from "node:fs";
+import { fileURLToPath } from "node:url";
+import { join } from "node:path";
+import { isPlainObject, stripControlChars } from "./util.ts";
+import { WORDS, type WordEntry } from "./words.ts";
+
+const PACK_ID_PATTERN = /^[a-z][a-z0-9-]{0,63}$/;
+const RESERVED_BUNDLED_PACK_IDS = new Set(["simcity", "star-trek", "star-wars"]);
+
+export function isWordPackId(value: string): boolean { return PACK_ID_PATTERN.test(value); }
+const BUNDLED_PACK_DIRECTORY = fileURLToPath(new URL("../wordpacks/", import.meta.url));
+
+export interface WordPack {
+	id: string;
+	name: string;
+	description?: string;
+	attribution?: string;
+	words: readonly WordEntry[];
+	bundled: boolean;
+}
+
+export interface WorkingTextSelection {
+	text: string;
+	pastTense: string;
+}
+
+export function wordPacksPath(): string {
+	return join(getAgentDir(), "pi-topping", "word-packs.json");
+}
+
+function safeText(value: unknown): string | undefined {
+	if (typeof value !== "string") return undefined;
+	const text = stripControlChars(value).trim();
+	return text || undefined;
+}
+
+/** Validate a pack document, discarding invalid packs and entries. */
+export function parseWordPacks(value: unknown, bundled = false): WordPack[] {
+	if (!isPlainObject(value)) return [];
+	const rawPacks = Array.isArray(value.packs) ? value.packs : [value];
+	const packs: WordPack[] = [];
+	const ids = new Set<string>();
+	for (const rawPack of rawPacks) {
+		if (!isPlainObject(rawPack)) continue;
+		const id = safeText(rawPack.id);
+		const name = safeText(rawPack.name);
+		if (!id || !name || !isWordPackId(id) || ids.has(id) || (!bundled && RESERVED_BUNDLED_PACK_IDS.has(id))) continue;
+		const words: WordEntry[] = [];
+		if (Array.isArray(rawPack.words)) {
+			for (const rawWord of rawPack.words) {
+				if (!isPlainObject(rawWord)) continue;
+				const present_tense = safeText(rawWord.present_tense);
+				const past_tense = safeText(rawWord.past_tense);
+				if (present_tense && past_tense) words.push({ present_tense, past_tense });
+			}
+		}
+		if (!words.length) continue;
+		ids.add(id);
+		const description = safeText(rawPack.description);
+		const attribution = safeText(rawPack.attribution);
+		packs.push({ id, name, ...(description ? { description } : {}), ...(attribution ? { attribution } : {}), words, bundled });
+	}
+	return packs;
+}
+
+/** Load every shipped JSON pack. Missing or invalid bundled data is a package-integrity error. */
+export function loadBundledWordPacks(): WordPack[] {
+	const files = readdirSync(BUNDLED_PACK_DIRECTORY).filter((file) => file.endsWith(".json")).sort();
+	const packs: WordPack[] = [];
+	const ids = new Set<string>();
+	for (const file of files) {
+		let value: unknown;
+		try {
+			value = JSON.parse(readFileSync(join(BUNDLED_PACK_DIRECTORY, file), "utf8"));
+		} catch (error) {
+			throw new Error(`Invalid bundled word pack: ${file}`, { cause: error });
+		}
+		const parsed = parseWordPacks(value, true);
+		if (!parsed.length) throw new Error(`Invalid bundled word pack: ${file}`);
+		for (const pack of parsed) {
+			if (ids.has(pack.id)) throw new Error(`Duplicate bundled word pack ID: ${pack.id}`);
+			ids.add(pack.id);
+			packs.push(pack);
+		}
+	}
+	if (!packs.some((pack) => pack.id === "simcity")) throw new Error("Missing bundled SimCity word pack");
+	const bundledIds = new Set(packs.map((pack) => pack.id));
+	for (const id of RESERVED_BUNDLED_PACK_IDS) {
+		if (!bundledIds.has(id)) throw new Error(`Missing bundled word pack: ${id}`);
+	}
+	for (const id of bundledIds) {
+		if (!RESERVED_BUNDLED_PACK_IDS.has(id)) throw new Error(`Bundled word pack "${id}" must be listed in RESERVED_BUNDLED_PACK_IDS to prevent user-pack shadowing`);
+	}
+	return packs;
+}
+
+/** User pack failures are intentionally non-fatal. */
+export function loadUserWordPacks(): WordPack[] {
+	try {
+		return parseWordPacks(JSON.parse(readFileSync(wordPacksPath(), "utf8")));
+	} catch {
+		return [];
+	}
+}
+
+export function isWordPackEnabled(id: string, enabled: Record<string, boolean>): boolean {
+	return enabled[id] === true;
+}
+
+export function selectWorkingTextSelection(enabled: Record<string, boolean>, packs: readonly WordPack[], fraction: number): WorkingTextSelection {
+	const pool = [...WORDS, ...packs.filter((pack) => isWordPackEnabled(pack.id, enabled)).flatMap((pack) => pack.words)];
+	const entry = pool[Math.min(pool.length - 1, Math.floor(fraction * pool.length))]!;
+	return { text: `${entry.present_tense}…`, pastTense: entry.past_tense };
+}
+
+export function pickWorkingTextSelection(enabled: Record<string, boolean>, packs: readonly WordPack[]): WorkingTextSelection {
+	return selectWorkingTextSelection(enabled, packs, Math.random());
+}

package/wordpacks/simcity.json

@@ -0,0 +1,432 @@
+{
+  "packs": [
+    {
+      "id": "simcity",
+      "name": "SimCity",
+      "description": "Classic city-simulation status phrases.",
+      "attribution": "Source: genact data/simcity.txt (MIT), Copyright 2020 Sven-Hendrik Haase. https://github.com/svenstaro/genact",
+      "words": [
+        {
+          "present_tense": "Adding hidden agendas",
+          "past_tense": "Added"
+        },
+        {
+          "present_tense": "Adjusting bell curves",
+          "past_tense": "Adjusted"
+        },
+        {
+          "present_tense": "Aesthesizing industrial areas",
+          "past_tense": "Aesthesized"
+        },
+        {
+          "present_tense": "Aligning covariance matrices",
+          "past_tense": "Aligned"
+        },
+        {
+          "present_tense": "Applying Feng Shui shaders",
+          "past_tense": "Applied"
+        },
+        {
+          "present_tense": "Applying theatre soda layer",
+          "past_tense": "Applied"
+        },
+        {
+          "present_tense": "Asserting packed exemplars",
+          "past_tense": "Asserted"
+        },
+        {
+          "present_tense": "Attempting to lock back-buffer",
+          "past_tense": "Attempted"
+        },
+        {
+          "present_tense": "Binding sapling root system",
+          "past_tense": "Bound"
+        },
+        {
+          "present_tense": "Breeding fauna",
+          "past_tense": "Bred"
+        },
+        {
+          "present_tense": "Building data trees",
+          "past_tense": "Built"
+        },
+        {
+          "present_tense": "Bureacritizing bureaucracies",
+          "past_tense": "Bureacritized"
+        },
+        {
+          "present_tense": "Calculating inverse probability matrices",
+          "past_tense": "Calculated"
+        },
+        {
+          "present_tense": "Calculating llama expectoration trajectory",
+          "past_tense": "Calculated"
+        },
+        {
+          "present_tense": "Calibrating blue skies",
+          "past_tense": "Calibrated"
+        },
+        {
+          "present_tense": "Charging ozone layer",
+          "past_tense": "Charged"
+        },
+        {
+          "present_tense": "Coalescing cloud formations",
+          "past_tense": "Coalesced"
+        },
+        {
+          "present_tense": "Cohorting exemplars",
+          "past_tense": "Cohorted"
+        },
+        {
+          "present_tense": "Collecting meteor particles",
+          "past_tense": "Collected"
+        },
+        {
+          "present_tense": "Compounding inert tessellations",
+          "past_tense": "Compounded"
+        },
+        {
+          "present_tense": "Compressing fish files",
+          "past_tense": "Compressed"
+        },
+        {
+          "present_tense": "Computing optimal bin packing",
+          "past_tense": "Computed"
+        },
+        {
+          "present_tense": "Concatenating sub-contractors",
+          "past_tense": "Concatenated"
+        },
+        {
+          "present_tense": "Containing existential buffer",
+          "past_tense": "Contained"
+        },
+        {
+          "present_tense": "Debarking ark ramp",
+          "past_tense": "Debarked"
+        },
+        {
+          "present_tense": "Debunching unionized commercial services",
+          "past_tense": "Debunched"
+        },
+        {
+          "present_tense": "Deciding what message to display next",
+          "past_tense": "Decided"
+        },
+        {
+          "present_tense": "Decomposing singular values",
+          "past_tense": "Decomposed"
+        },
+        {
+          "present_tense": "Decrementing tectonic plates",
+          "past_tense": "Decremented"
+        },
+        {
+          "present_tense": "Deleting ferry routes",
+          "past_tense": "Deleted"
+        },
+        {
+          "present_tense": "Depixelating inner mountain surface back faces",
+          "past_tense": "Depixelated"
+        },
+        {
+          "present_tense": "Depositing slush funds",
+          "past_tense": "Deposited"
+        },
+        {
+          "present_tense": "Destabilizing economic indicators",
+          "past_tense": "Destabilized"
+        },
+        {
+          "present_tense": "Determining width of blast fronts",
+          "past_tense": "Determined"
+        },
+        {
+          "present_tense": "Deunionizing bulldozers",
+          "past_tense": "Deunionized"
+        },
+        {
+          "present_tense": "Dicing models",
+          "past_tense": "Diced"
+        },
+        {
+          "present_tense": "Diluting livestock nutrition variables",
+          "past_tense": "Diluted"
+        },
+        {
+          "present_tense": "Downloading satellite terrain data",
+          "past_tense": "Downloaded"
+        },
+        {
+          "present_tense": "Exposing flash variables to streak system",
+          "past_tense": "Exposed"
+        },
+        {
+          "present_tense": "Extracting resources",
+          "past_tense": "Extracted"
+        },
+        {
+          "present_tense": "Factoring pay scale",
+          "past_tense": "Factored"
+        },
+        {
+          "present_tense": "Fixing election outcome matrix",
+          "past_tense": "Fixed"
+        },
+        {
+          "present_tense": "Flood-filling ground water",
+          "past_tense": "Flood-Filled"
+        },
+        {
+          "present_tense": "Flushing pipe network",
+          "past_tense": "Flushed"
+        },
+        {
+          "present_tense": "Gathering particle sources",
+          "past_tense": "Gathered"
+        },
+        {
+          "present_tense": "Generating jobs",
+          "past_tense": "Generated"
+        },
+        {
+          "present_tense": "Gesticulating mimes",
+          "past_tense": "Gesticulated"
+        },
+        {
+          "present_tense": "Graphing whale migration",
+          "past_tense": "Graphed"
+        },
+        {
+          "present_tense": "Hiding Willio Webnet mask",
+          "past_tense": "Hid"
+        },
+        {
+          "present_tense": "Implementing impeachment routine",
+          "past_tense": "Implemented"
+        },
+        {
+          "present_tense": "Increasing accuracy of RCI simulators",
+          "past_tense": "Increased"
+        },
+        {
+          "present_tense": "Increasing magmafacation",
+          "past_tense": "Increased"
+        },
+        {
+          "present_tense": "Initializing my Sim tracking mechanism",
+          "past_tense": "Initialized"
+        },
+        {
+          "present_tense": "Initializing rhinoceros breeding timetable",
+          "past_tense": "Initialized"
+        },
+        {
+          "present_tense": "Initializing robotic click-path AI",
+          "past_tense": "Initialized"
+        },
+        {
+          "present_tense": "Inserting sublimated messages",
+          "past_tense": "Inserted"
+        },
+        {
+          "present_tense": "Integrating curves",
+          "past_tense": "Integrated"
+        },
+        {
+          "present_tense": "Integrating illumination form factors",
+          "past_tense": "Integrated"
+        },
+        {
+          "present_tense": "Integrating population graphs",
+          "past_tense": "Integrated"
+        },
+        {
+          "present_tense": "Iterating cellular automata",
+          "past_tense": "Iterated"
+        },
+        {
+          "present_tense": "Lecturing errant subsystems",
+          "past_tense": "Lectured"
+        },
+        {
+          "present_tense": "Mixing genetic pool",
+          "past_tense": "Mixed"
+        },
+        {
+          "present_tense": "Modeling object components",
+          "past_tense": "Modeled"
+        },
+        {
+          "present_tense": "Mopping occupant leaks",
+          "past_tense": "Mopped"
+        },
+        {
+          "present_tense": "Normalizing power",
+          "past_tense": "Normalized"
+        },
+        {
+          "present_tense": "Obfuscating Quigley matrix",
+          "past_tense": "Obfuscated"
+        },
+        {
+          "present_tense": "Overconstraining dirty industry calculations",
+          "past_tense": "Overconstrained"
+        },
+        {
+          "present_tense": "Partitioning city grid singularities",
+          "past_tense": "Partitioned"
+        },
+        {
+          "present_tense": "Perturbing matrices",
+          "past_tense": "Perturbed"
+        },
+        {
+          "present_tense": "Pixelating nude patch",
+          "past_tense": "Pixelated"
+        },
+        {
+          "present_tense": "Polishing water highlights",
+          "past_tense": "Polished"
+        },
+        {
+          "present_tense": "Populating lot templates",
+          "past_tense": "Populated"
+        },
+        {
+          "present_tense": "Preparing sprites for random walks",
+          "past_tense": "Prepared"
+        },
+        {
+          "present_tense": "Prioritizing landmarks",
+          "past_tense": "Prioritized"
+        },
+        {
+          "present_tense": "Projecting law enforcement pastry intake",
+          "past_tense": "Projected"
+        },
+        {
+          "present_tense": "Realigning alternate time frames",
+          "past_tense": "Realigned"
+        },
+        {
+          "present_tense": "Reconfiguring user mental processes",
+          "past_tense": "Reconfigured"
+        },
+        {
+          "present_tense": "Relaxing splines",
+          "past_tense": "Relaxed"
+        },
+        {
+          "present_tense": "Removing road network speed bumps",
+          "past_tense": "Removed"
+        },
+        {
+          "present_tense": "Removing texture gradients",
+          "past_tense": "Removed"
+        },
+        {
+          "present_tense": "Removing vehicle avoidance behavior",
+          "past_tense": "Removed"
+        },
+        {
+          "present_tense": "Resolving GUID conflict",
+          "past_tense": "Resolved"
+        },
+        {
+          "present_tense": "Reticulating splines",
+          "past_tense": "Reticulated"
+        },
+        {
+          "present_tense": "Retracting Phong shader",
+          "past_tense": "Retracted"
+        },
+        {
+          "present_tense": "Retrieving from back store",
+          "past_tense": "Retrieved"
+        },
+        {
+          "present_tense": "Reverse engineering image consultant",
+          "past_tense": "Engineered"
+        },
+        {
+          "present_tense": "Routing neural network infrastructure",
+          "past_tense": "Routed"
+        },
+        {
+          "present_tense": "Scattering rhino food sources",
+          "past_tense": "Scattered"
+        },
+        {
+          "present_tense": "Scrubbing terrain",
+          "past_tense": "Scrubbed"
+        },
+        {
+          "present_tense": "Searching for llamas",
+          "past_tense": "Searched"
+        },
+        {
+          "present_tense": "Seeding architecture simulation parameters",
+          "past_tense": "Seeded"
+        },
+        {
+          "present_tense": "Sequencing particles",
+          "past_tense": "Sequenced"
+        },
+        {
+          "present_tense": "Setting advisor moods",
+          "past_tense": "Set"
+        },
+        {
+          "present_tense": "Setting inner deity indicators",
+          "past_tense": "Set"
+        },
+        {
+          "present_tense": "Setting universal physical constants",
+          "past_tense": "Set"
+        },
+        {
+          "present_tense": "Sonically enhancing occupant-free timber",
+          "past_tense": "Enhanced"
+        },
+        {
+          "present_tense": "Speculating stock market indices",
+          "past_tense": "Speculated"
+        },
+        {
+          "present_tense": "Splatting transforms",
+          "past_tense": "Splatted"
+        },
+        {
+          "present_tense": "Stratifying ground layers",
+          "past_tense": "Stratified"
+        },
+        {
+          "present_tense": "Sub-sampling water data",
+          "past_tense": "Sub-Sampled"
+        },
+        {
+          "present_tense": "Synthesizing gravity",
+          "past_tense": "Synthesized"
+        },
+        {
+          "present_tense": "Synthesizing wavelets",
+          "past_tense": "Synthesized"
+        },
+        {
+          "present_tense": "Time-compressing simulator clock",
+          "past_tense": "Time-Compressed"
+        },
+        {
+          "present_tense": "Weathering buildings",
+          "past_tense": "Weathered"
+        },
+        {
+          "present_tense": "Zeroing crime network",
+          "past_tense": "Zeroed"
+        }
+      ]
+    }
+  ]
+}