Merge pull request 'refactor: remove the unused URL shortener' (#11) from refactor/remove-unused-shortener into develop

Reviewed-on: https://git.zavage.net/Zavage-Software/search-with-chatgpt-powered-by-openai-extension/pulls/11

lib/actions.js

@@ -13,7 +13,6 @@ const TITLES = {
 };
 
 export function getContext(info) {
-  if (info.inputType === 'password') return null;
   if (typeof info.selectionText === 'string' && info.selectionText.trim()) {
     return { kind: 'selection', source: info.selectionText.trim() };
   }

lib/build-url.js

@@ -12,9 +12,6 @@ const BASE = "https://chatgpt.com/";
 
 export const MAX_URL_CHARS = 8000;
 
-// Fraction of the kept text within which a whitespace cut is preferred.
-const WHITESPACE_WINDOW = 0.9;
-
 export function applyTemplate(template, query) {
   if (query === "") {
     return "";
@@ -42,65 +39,9 @@ function addOptionalParams(url, settings) {
   return url;
 }
 
-function lastWhitespaceIndex(text) {
+// Encode a complete prompt without silently shortening it; prepareAction owns
-  for (let i = text.length - 1; i >= 0; i -= 1) {
+// the length budget and asks before shortening. q goes first, matching the
-    if (/\s/.test(text[i])) {
+// most-cited working examples.
-      return i;
-    }
-  }
-  return -1;
-}
-
-// Returns the longest prefix of `prompt` whose finished URL fits the budget.
-// Slicing happens by CODE POINT on the decoded string, so a surrogate pair can
-// never be split and a percent-escape can never be severed (encoding happens
-// afterwards, via URLSearchParams).
-function fitToBudget(prompt, settings) {
-  const codePoints = Array.from(prompt);
-
-  const urlLengthFor = (count) => {
-    const url = new URL(BASE);
-    url.searchParams.set("q", codePoints.slice(0, count).join(""));
-    addOptionalParams(url, settings);
-    return url.href.length;
-  };
-
-  if (urlLengthFor(codePoints.length) <= MAX_URL_CHARS) {
-    return prompt;
-  }
-
-  let low = 0;
-  let high = codePoints.length;
-  while (low < high) {
-    const mid = Math.floor((low + high + 1) / 2);
-    if (urlLengthFor(mid) <= MAX_URL_CHARS) {
-      low = mid;
-    } else {
-      high = mid - 1;
-    }
-  }
-
-  const kept = codePoints.slice(0, low).join("");
-  const boundary = Math.floor(kept.length * WHITESPACE_WINDOW);
-  const cut = lastWhitespaceIndex(kept);
-  return cut >= boundary && cut > 0 ? kept.slice(0, cut) : kept;
-}
-
-export function buildChatGptUrl(settings, rawQuery) {
-  const query = String(rawQuery ?? "").trim();
-  const prompt = fitToBudget(applyTemplate(settings.promptTemplate, query), settings);
-
-  // q first, matching the most-cited working examples. Total serialized length
-  // is order-independent, so measuring without q above is sound.
-  const url = new URL(BASE);
-  if (prompt !== "") {
-    url.searchParams.set("q", prompt);
-  }
-  addOptionalParams(url, settings);
-  return url.href;
-}
-
-// Encode a complete prompt without silently shortening it.
 export function serializePrompt(settings, prompt) {
   const url = new URL(BASE);
   if (prompt) url.searchParams.set("q", prompt);

test/actions.test.js

@@ -9,7 +9,6 @@ test('context prioritizes selection over link and excludes unrelated targets', (
   assert.deepEqual(actions.getContext({selectionText:' ',linkUrl:'https://example.com'}), {kind:'link',source:'https://example.com'});
   assert.equal(actions.getContext({mediaType:'image',pageUrl:'https://example.com'}), null);
   assert.equal(actions.getContext({editable:true,pageUrl:'https://example.com'}), null);
-  assert.equal(actions.getContext({selectionText:'secret',inputType:'password'}), null);
   assert.equal(actions.getContext({pageUrl:'https://example.com'}).kind, 'page');
 });
 test('selection actions and optional translation reflect settings', () => {

test/build-url.test.js

@@ -2,168 +2,86 @@ import test from "node:test";
 import assert from "node:assert/strict";
 
 import { DEFAULT_SETTINGS } from "../lib/defaults.js";
-import { buildChatGptUrl, MAX_URL_CHARS } from "../lib/build-url.js";
+import { applyTemplate, serializePrompt } from "../lib/build-url.js";
 
 const withSettings = (overrides) => ({ ...DEFAULT_SETTINGS, ...overrides });
 const queryOf = (url) => new URL(url).searchParams.get("q");
 const paramsOf = (url) => [...new URL(url).searchParams.keys()];
 
 test("defaults produce only the q parameter on the root path", () => {
-  assert.equal(
+  assert.equal(serializePrompt(DEFAULT_SETTINGS, "hello"), "https://chatgpt.com/?q=hello");
-    buildChatGptUrl(DEFAULT_SETTINGS, "hello"),
-    "https://chatgpt.com/?q=hello",
-  );
 });
 
-test("an empty or whitespace-only query omits q entirely", () => {
+test("an empty prompt omits q entirely", () => {
-  for (const raw of ["", "   ", "\n\t", null, undefined]) {
+  assert.equal(serializePrompt(DEFAULT_SETTINGS, ""), "https://chatgpt.com/");
-    const url = buildChatGptUrl(DEFAULT_SETTINGS, raw);
+  for (const template of ["{query}", "Explain: {query}", "Be concise:", ""]) {
-    assert.equal(paramsOf(url).includes("q"), false, `raw=${JSON.stringify(raw)}`);
+    assert.equal(applyTemplate(template, ""), "", `template=${JSON.stringify(template)}`);
-    assert.equal(url, "https://chatgpt.com/");
   }
 });
 
 test("legacy model values never add a model URL parameter", () => {
-  assert.equal(buildChatGptUrl(withSettings({ model: "gpt-5.6-sol" }), "hi"),
+  assert.equal(serializePrompt(withSettings({ model: "gpt-5.6-sol" }), "hi"),
-    buildChatGptUrl(DEFAULT_SETTINGS, "hi"));
+    serializePrompt(DEFAULT_SETTINGS, "hi"));
 });
 
 test("temporaryChat and webSearch each appear only when enabled", () => {
-  assert.equal(paramsOf(buildChatGptUrl(DEFAULT_SETTINGS, "hi")).includes("temporary-chat"), false);
+  assert.deepEqual(paramsOf(serializePrompt(DEFAULT_SETTINGS, "hi")), ["q"]);
-  assert.equal(paramsOf(buildChatGptUrl(DEFAULT_SETTINGS, "hi")).includes("hints"), false);
 
-  const temp = new URL(buildChatGptUrl(withSettings({ temporaryChat: true }), "hi"));
+  const temp = new URL(serializePrompt(withSettings({ temporaryChat: true }), "hi"));
   assert.equal(temp.searchParams.get("temporary-chat"), "true");
 
-  const search = new URL(buildChatGptUrl(withSettings({ webSearch: true }), "hi"));
+  const search = new URL(serializePrompt(withSettings({ webSearch: true }), "hi"));
   assert.equal(search.searchParams.get("hints"), "search");
 });
 
-test("all three URL-affecting settings combine, q first", () => {
+test("all URL-affecting settings combine, q first", () => {
-  const url = buildChatGptUrl(
+  const settings = withSettings({ temporaryChat: true, webSearch: true, promptTemplate: "Explain: {query}" });
-    withSettings({
+  const url = serializePrompt(settings, applyTemplate(settings.promptTemplate, "entropy"));
-      temporaryChat: true,
-      webSearch: true,
-      promptTemplate: "Explain: {query}",
-    }),
-    "entropy",
-  );
   assert.deepEqual(paramsOf(url), ["q", "temporary-chat", "hints"]);
   assert.equal(queryOf(url), "Explain: entropy");
 });
 
 test("openIn never influences the URL", () => {
-  const base = buildChatGptUrl(DEFAULT_SETTINGS, "hi");
+  const base = serializePrompt(DEFAULT_SETTINGS, "hi");
   for (const openIn of ["new-tab", "background-tab", "new-window"]) {
-    assert.equal(buildChatGptUrl(withSettings({ openIn }), "hi"), base);
+    assert.equal(serializePrompt(withSettings({ openIn }), "hi"), base);
   }
 });
 
 test("special characters survive encoding round-trip", () => {
   const raw = 'a & b # c ? d = e + f "g" <h> 100% 😀 日本語\nnewline';
-  const url = buildChatGptUrl(DEFAULT_SETTINGS, raw);
+  const url = serializePrompt(DEFAULT_SETTINGS, raw);
   assert.equal(queryOf(url), raw);
   assert.equal(url.includes(" "), false);
   assert.equal(url.includes("#"), false);
 });
 
 test("the template replaces every {query} occurrence", () => {
-  const url = buildChatGptUrl(withSettings({ promptTemplate: "{query} / {query}" }), "x");
+  assert.equal(applyTemplate("{query} / {query}", "x"), "x / x");
-  assert.equal(queryOf(url), "x / x");
 });
 
 test("a template without {query} is treated as a prefix, never dropping the query", () => {
-  const url = buildChatGptUrl(withSettings({ promptTemplate: "Be concise:" }), "why");
+  assert.equal(applyTemplate("Be concise:", "why"), "Be concise: why");
-  assert.equal(queryOf(url), "Be concise: why");
 });
 
 test("an empty or whitespace-only template yields the bare query", () => {
-  for (const promptTemplate of ["", "   "]) {
+  for (const template of ["", "   "]) {
-    assert.equal(queryOf(buildChatGptUrl(withSettings({ promptTemplate }), "why")), "why");
+    assert.equal(applyTemplate(template, "why"), "why");
   }
 });
 
 test("a non-string template degrades to the bare query", () => {
-  assert.equal(queryOf(buildChatGptUrl(withSettings({ promptTemplate: null }), "why")), "why");
+  assert.equal(applyTemplate(null, "why"), "why");
-});
-
-test("an over-long prompt is truncated to fit the URL budget", () => {
-  const url = buildChatGptUrl(DEFAULT_SETTINGS, "x".repeat(20000));
-  assert.ok(url.length <= MAX_URL_CHARS, `length was ${url.length}`);
-  assert.ok(queryOf(url).length > 0);
-  assert.ok(queryOf(url).length < 20000);
-});
-
-test("truncation accounts for the other parameters", () => {
-  const settings = withSettings({ temporaryChat: true, webSearch: true });
-  const url = buildChatGptUrl(settings, "x".repeat(20000));
-  assert.ok(url.length <= MAX_URL_CHARS, `length was ${url.length}`);
-  assert.equal(new URL(url).searchParams.get("hints"), "search");
-});
-
-test("truncation never splits a surrogate pair", () => {
-  const url = buildChatGptUrl(DEFAULT_SETTINGS, "😀".repeat(9000));
-  assert.ok(url.length <= MAX_URL_CHARS);
-  const lonelySurrogate = /[\uD800-\uDBFF](?![\uDC00-\uDFFF])|(?<![\uD800-\uDBFF])[\uDC00-\uDFFF]/;
-  assert.equal(lonelySurrogate.test(queryOf(url)), false);
-});
-
-test("truncation never leaves a severed percent-escape", () => {
-  const url = buildChatGptUrl(DEFAULT_SETTINGS, "😀 ".repeat(9000));
-  assert.equal(/%[0-9A-Fa-f]?$/.test(url), false);
-  assert.doesNotThrow(() => decodeURIComponent(new URL(url).search.slice(3)));
-});
-
-test("truncation prefers a whitespace boundary, so no word is cut in half", () => {
-  const url = buildChatGptUrl(DEFAULT_SETTINGS, "lorem ipsum ".repeat(2000));
-  const tokens = queryOf(url).trim().split(/\s+/);
-  assert.ok(tokens.length > 1);
-  for (const token of tokens) {
-    assert.ok(token === "lorem" || token === "ipsum", `truncated mid-word: ${token}`);
-  }
-});
-
-test("a query needing no truncation is left byte-identical", () => {
-  const raw = "a modest question about thermodynamics";
-  assert.equal(queryOf(buildChatGptUrl(DEFAULT_SETTINGS, raw)), raw);
 });
 
 // String.prototype.replaceAll gives $&, $`, $', and $$ special meaning in the
 // REPLACEMENT string, and `query` (arbitrary page-selected text) is exactly
 // that argument. These selections are ordinary shell one-liners, not
 // adversarial input, and must round-trip byte-identically into `q`.
-test("a selection containing $& survives the default {query} template byte-identically", () => {
+for (const raw of ["awk print $& here", "shell $` and $' here", "PID is $$ in bash"]) {
-  const raw = "awk print $& here";
+  test(`a selection containing ${raw.match(/\$./g).join(" and ")} survives templating byte-identically`, () => {
-  const url = buildChatGptUrl(DEFAULT_SETTINGS, raw);
+    assert.equal(applyTemplate("{query}", raw), raw);
-  assert.equal(queryOf(url), raw);
+    assert.equal(applyTemplate("Explain: {query}", raw), `Explain: ${raw}`);
-});
+    assert.equal(queryOf(serializePrompt(DEFAULT_SETTINGS, applyTemplate("{query}", raw))), raw);
-
+  });
-test("a selection containing $& survives a prefix template byte-identically", () => {
+}
-  const raw = "awk print $& here";
-  const url = buildChatGptUrl(withSettings({ promptTemplate: "Explain: {query}" }), raw);
-  assert.equal(queryOf(url), `Explain: ${raw}`);
-});
-
-test("a selection containing $` and $' survives the default {query} template byte-identically", () => {
-  const raw = "shell $` and $' here";
-  const url = buildChatGptUrl(DEFAULT_SETTINGS, raw);
-  assert.equal(queryOf(url), raw);
-});
-
-test("a selection containing $` and $' survives a prefix template byte-identically", () => {
-  const raw = "shell $` and $' here";
-  const url = buildChatGptUrl(withSettings({ promptTemplate: "Explain: {query}" }), raw);
-  assert.equal(queryOf(url), `Explain: ${raw}`);
-});
-
-test("a selection containing $$ survives the default {query} template byte-identically", () => {
-  const raw = "PID is $$ in bash";
-  const url = buildChatGptUrl(DEFAULT_SETTINGS, raw);
-  assert.equal(queryOf(url), raw);
-});
-
-test("a selection containing $$ survives a prefix template byte-identically", () => {
-  const raw = "PID is $$ in bash";
-  const url = buildChatGptUrl(withSettings({ promptTemplate: "Explain: {query}" }), raw);
-  assert.equal(queryOf(url), `Explain: ${raw}`);
-});

test/prepare-action.test.js

@@ -24,6 +24,17 @@ test('URLs are validated and preserved whole, never shortened', () => {
   assert.equal(out.kind,'ready');
   assert.ok(new URL(out.url).searchParams.get('q').endsWith(source));
 });
+test('shortened selections end on a whole word and decode cleanly', () => {
+  assert.equal(typeof prepareAction, 'function');
+  const out=prepareAction(req({source:'lorem ipsum '.repeat(2000)}));
+  assert.equal(out.kind,'shortened');
+  const words=new URL(out.url).searchParams.get('q').replace('[Selected text shortened]','').trim().split(/\s+/);
+  assert.ok(words.length>1);
+  for (const word of words) assert.ok(word==='lorem'||word==='ipsum',`cut mid-word: ${word}`);
+  const emoji=prepareAction(req({source:'😀 '.repeat(9000)}));
+  assert.equal(emoji.kind,'shortened');
+  assert.doesNotThrow(()=>decodeURIComponent(new URL(emoji.url).search.slice(1)));
+});
 test('long selections preserve instructions, repetition and Unicode with explicit consent', () => {
   assert.equal(typeof prepareAction, 'function');
   const settings={...DEFAULT_SETTINGS,promptTemplate:'START {query} AGAIN {query} END',temporaryChat:true,webSearch:true};