@fishdivinity/dsh-local-search 0.1.0 → 0.2.1

package/lib/anytxt.js

@@ -1,252 +1,272 @@
-import { EngineError } from './errors.js'
-
-const DEFAULT_URL = 'http://127.0.0.1:9920'
-const EXCLUDED = [/\\\$RECYCLE\.BIN\\/i, /\\System Volume Information\\/i]
-const RPC_TIMEOUT_MS = 15000
-
-/** Primary URL plus the 9921 fallback used by some Anytxt builds. */
-export function resolveAnytxtUrls(url = DEFAULT_URL) {
-  const base = String(url || DEFAULT_URL).replace(/\/+$/, '')
-  const urls = [base]
-  if (/:9920$/.test(base)) urls.push(base.replace(/:9920$/, ':9921'))
-  return urls
-}
-
-/** Quoted phrases use exact mode (st=1); other queries use advanced mode. */
-export function quoteAware(query) {
-  const trimmed = String(query ?? '').trim()
-  if (/^".*"$/s.test(trimmed)) {
-    return { pattern: trimmed.slice(1, -1), st: '1' }
-  }
-  return { pattern: trimmed, st: '2' }
-}
-
-/** Remove Anytxt's match highlight markers from snippets. */
-export function stripHighlights(text) {
-  return String(text ?? '').replace(/\*<<\*|\*>>\*/g, '')
-}
-
-function parseFileTuple(tuple) {
-  if (!Array.isArray(tuple) || tuple.length < 4) return undefined
-  const [fid, lastModify, size, file] = tuple
-  if (typeof file !== 'string' || EXCLUDED.some((re) => re.test(file))) return undefined
-  const numericSize = Number(size)
-  const numericModified = Number(lastModify)
-  const item = {
-    ref: String(fid),
-    path: file,
-  }
-  if (Number.isFinite(numericSize)) item.size = numericSize
-  if (Number.isFinite(numericModified) && numericModified > 0) {
-    item.modified = new Date(numericModified * 1000).toISOString()
-  }
-  return item
-}
-
-/** POST one JSON-RPC request and return `result.data.output`. */
-export async function anytxtRpc(url, method, input, { timeoutMs = RPC_TIMEOUT_MS, signal, fetchImpl = fetch } = {}) {
-  const timeoutSignal = AbortSignal.timeout(timeoutMs)
-  const combined = signal ? AbortSignal.any([signal, timeoutSignal]) : timeoutSignal
-  let response
-  try {
-    response = await fetchImpl(url, {
-      method: 'POST',
-      headers: { accept: 'application/json', 'content-type': 'application/json' },
-      body: JSON.stringify({ id: 1, jsonrpc: '2.0', method, params: { input } }),
-      signal: combined,
-    })
-  } catch (error) {
-    if (signal?.aborted) {
-      throw new EngineError('Anytxt request was aborted', 'ANYTXT_ABORTED', { cause: error })
-    }
-    if (error?.name === 'TimeoutError') {
-      throw new EngineError('Anytxt request timed out', 'ANYTXT_TIMEOUT', {
-        cause: error,
-        hint: 'Start Anytxt and retry; narrow the query if it is a large search.',
-      })
-    }
-    throw new EngineError('Anytxt JSON-RPC is unreachable', 'ANYTXT_DOWN', {
-      cause: error,
-      hint: `Start the Anytxt GUI (ATGUI.exe); the index service alone does not serve ${url}.`,
-    })
-  }
-  if (!response.ok) {
-    throw new EngineError(`Anytxt returned HTTP ${response.status}`, 'ANYTXT_HTTP', {
-      hint: `Check the Anytxt JSON-RPC endpoint at ${url}.`,
-    })
-  }
-  let data
-  try {
-    data = await response.json()
-  } catch (error) {
-    if (signal?.aborted) {
-      throw new EngineError('Anytxt request was aborted', 'ANYTXT_ABORTED', { cause: error })
-    }
-    if (error?.name === 'TimeoutError') {
-      throw new EngineError('Anytxt response timed out', 'ANYTXT_TIMEOUT', { cause: error })
-    }
-    throw new EngineError('Anytxt returned non-JSON', 'ANYTXT_BAD_OUTPUT', { cause: error })
-  }
-  if (!data || typeof data !== 'object') {
-    throw new EngineError('Anytxt returned a non-object JSON value', 'ANYTXT_BAD_OUTPUT')
-  }
-  if (data.error) {
-    throw new EngineError(`Anytxt RPC error: ${JSON.stringify(data.error)}`, 'ANYTXT_RPC', {
-      hint: 'Check the query syntax; Anytxt uses & | ! ( ) and "exact phrase".',
-    })
-  }
-  const output = data.result?.data?.output
-  if (output === undefined) {
-    throw new EngineError('Anytxt returned no result.data.output', 'ANYTXT_RPC')
-  }
-  return output
-}
-
-/** Try the primary URL, then the 9921 fallback only on connection failures. */
-async function rpcFirst(urls, method, input, options) {
-  let lastError
-  for (const url of urls) {
-    try {
-      return await anytxtRpc(url, method, input, options)
-    } catch (error) {
-      lastError = error
-      if (error.code === 'ANYTXT_DOWN' && url !== urls[urls.length - 1]) continue
-      throw error
-    }
-  }
-  throw lastError
-}
-
-/** Search document contents through Anytxt, one request pair per root. */
-export async function searchContent({
-  query,
-  roots,
-  ext,
-  limit = 20,
-  url = DEFAULT_URL,
-  timeoutMs = RPC_TIMEOUT_MS,
-  signal,
-  fetchImpl = fetch,
-} = {}) {
-  if (typeof query !== 'string' || query.trim().length === 0) {
-    throw new EngineError('query must be a non-empty string', 'INVALID_ARGUMENT')
-  }
-  if (!Number.isInteger(limit) || limit < 1) {
-    throw new EngineError('limit must be a positive integer', 'INVALID_ARGUMENT')
-  }
-  const urls = resolveAnytxtUrls(url)
-  const { pattern, st } = quoteAware(query)
-  const byRef = new Map()
-  let total = 0
-
-  for (const root of roots) {
-    const countOut = await rpcFirst(
-      urls,
-      'ATRpcServer.Searcher.V1.Search',
-      {
-        pattern,
-        filterDir: root,
-        filterExt: ext || '*',
-        lastModifyBegin: 0,
-        lastModifyEnd: 2147483647,
-        st,
-      },
-      { timeoutMs, signal, fetchImpl },
-    )
-    const count = typeof countOut.count === 'number' ? countOut.count : 0
-    total += count
-    if (count === 0) continue
-
-    const page = await rpcFirst(
-      urls,
-      'ATRpcServer.Searcher.V1.GetResult',
-      {
-        pattern,
-        filterDir: root,
-        filterExt: ext || '*',
-        lastModifyBegin: 0,
-        lastModifyEnd: 2147483647,
-        limit: String(limit),
-        offset: 0,
-        order: 0,
-        st,
-      },
-      { timeoutMs, signal, fetchImpl },
-    )
-    for (const tuple of page.files || []) {
-      const item = parseFileTuple(tuple)
-      if (item && !byRef.has(item.ref)) byRef.set(item.ref, item)
-    }
-  }
-
-  const items = [...byRef.values()].slice(0, limit)
-  return { items, total, truncated: total > items.length }
-}
-
-/** Snippets around a match in one indexed file. */
-export async function getFragments({
-  ref,
-  query,
-  url = DEFAULT_URL,
-  timeoutMs = RPC_TIMEOUT_MS,
-  signal,
-  fetchImpl = fetch,
-} = {}) {
-  if (!ref) throw new EngineError('ref must be a non-empty string', 'INVALID_ARGUMENT')
-  if (typeof query !== 'string' || query.trim().length === 0) {
-    throw new EngineError('query must be a non-empty string', 'INVALID_ARGUMENT')
-  }
-  const output = await rpcFirst(
-    resolveAnytxtUrls(url),
-    'ATRpcServer.Searcher.V1.GetFragmentAll',
-    { fid: ref, pattern: query },
-    { timeoutMs, signal, fetchImpl },
-  )
-  return (output.text || []).map(stripHighlights).filter(Boolean)
-}
-
-/** Full extracted text for one indexed file. */
-export async function getRawText({
-  ref,
-  url = DEFAULT_URL,
-  timeoutMs = RPC_TIMEOUT_MS,
-  signal,
-  fetchImpl = fetch,
-} = {}) {
-  if (!ref) throw new EngineError('ref must be a non-empty string', 'INVALID_ARGUMENT')
-  const output = await rpcFirst(
-    resolveAnytxtUrls(url),
-    'ATRpcServer.Searcher.V1.GetRawTextByFID',
-    { fid: ref },
-    { timeoutMs, signal, fetchImpl },
-  )
-  return typeof output.text === 'string' ? output.text : ''
-}
-
-/** Probe Anytxt without throwing. */
-export async function anytxtStatus({
-  url = DEFAULT_URL,
-  root = process.env.SystemDrive ? `${process.env.SystemDrive}\\` : 'C:\\',
-  timeoutMs = 1500,
-  signal,
-  fetchImpl = fetch,
-} = {}) {
-  const urls = resolveAnytxtUrls(url)
-  try {
-    await rpcFirst(
-      urls,
-      'ATRpcServer.Searcher.V1.Search',
-      {
-        pattern: 'the',
-        filterDir: root,
-        filterExt: 'txt',
-        lastModifyBegin: 0,
-        lastModifyEnd: 2147483647,
-      },
-      { timeoutMs, signal, fetchImpl },
-    )
-    return { ok: true, url: urls[0] }
-  } catch (error) {
-    return { ok: false, code: error.code ?? 'ANYTXT_DOWN', message: error.message, url: urls[0] }
-  }
-}
+import { EngineError } from './errors.js'
+import { isLoopbackUrl } from './config.js'
+
+const DEFAULT_URL = 'http://127.0.0.1:9920'
+const EXCLUDED = [/\\\$RECYCLE\.BIN\\/i, /\\System Volume Information\\/i]
+const RPC_TIMEOUT_MS = 15000
+
+/**
+ * Primary URL plus the 9921 fallback used by some Anytxt builds.
+ *
+ * This is where the loopback rule lives: the endpoint is read per call, so a
+ * profile that still names another machine fails only the content search, with
+ * a code the model can explain — instead of failing activation and taking
+ * file-name search down with it.
+ * @param url - configured endpoint
+ * @returns the endpoints to try, in order
+ * @throws {EngineError} ANYTXT_ENDPOINT_REMOTE when the endpoint is not local
+ */
+export function resolveAnytxtUrls(url = DEFAULT_URL) {
+  const base = String(url || DEFAULT_URL).replace(/\/+$/, '')
+  if (!isLoopbackUrl(base)) {
+    throw new EngineError(`Anytxt endpoint must be local, not ${base}`, 'ANYTXT_ENDPOINT_REMOTE', {
+      hint: 'Both indexes describe this machine, so the endpoint must be 127.0.0.1, localhost or [::1].',
+    })
+  }
+  const urls = [base]
+  if (/:9920$/.test(base)) urls.push(base.replace(/:9920$/, ':9921'))
+  return urls
+}
+
+/** Quoted phrases use exact mode (st=1); other queries use advanced mode. */
+export function quoteAware(query) {
+  const trimmed = String(query ?? '').trim()
+  if (/^".*"$/s.test(trimmed)) {
+    return { pattern: trimmed.slice(1, -1), st: '1' }
+  }
+  return { pattern: trimmed, st: '2' }
+}
+
+/** Remove Anytxt's match highlight markers from snippets. */
+export function stripHighlights(text) {
+  return String(text ?? '').replace(/\*<<\*|\*>>\*/g, '')
+}
+
+function parseFileTuple(tuple) {
+  if (!Array.isArray(tuple) || tuple.length < 4) return undefined
+  const [fid, lastModify, size, file] = tuple
+  if (typeof file !== 'string' || EXCLUDED.some((re) => re.test(file))) return undefined
+  const numericSize = Number(size)
+  const numericModified = Number(lastModify)
+  const item = {
+    ref: String(fid),
+    path: file,
+  }
+  if (Number.isFinite(numericSize)) item.size = numericSize
+  if (Number.isFinite(numericModified) && numericModified > 0) {
+    item.modified = new Date(numericModified * 1000).toISOString()
+  }
+  return item
+}
+
+/** POST one JSON-RPC request and return `result.data.output`. */
+export async function anytxtRpc(url, method, input, { timeoutMs = RPC_TIMEOUT_MS, signal, fetchImpl = fetch } = {}) {
+  const timeoutSignal = AbortSignal.timeout(timeoutMs)
+  const combined = signal ? AbortSignal.any([signal, timeoutSignal]) : timeoutSignal
+  let response
+  try {
+    response = await fetchImpl(url, {
+      method: 'POST',
+      headers: { accept: 'application/json', 'content-type': 'application/json' },
+      body: JSON.stringify({ id: 1, jsonrpc: '2.0', method, params: { input } }),
+      signal: combined,
+      // A 307/308 would re-POST this body wherever the endpoint points, so a
+      // loopback service could bounce the request off-machine and have its
+      // answer trusted as index data.
+      redirect: 'error',
+    })
+  } catch (error) {
+    if (signal?.aborted) {
+      throw new EngineError('Anytxt request was aborted', 'ANYTXT_ABORTED', { cause: error })
+    }
+    if (error?.name === 'TimeoutError') {
+      throw new EngineError('Anytxt request timed out', 'ANYTXT_TIMEOUT', {
+        cause: error,
+        hint: 'Start Anytxt and retry; narrow the query if it is a large search.',
+      })
+    }
+    throw new EngineError('Anytxt JSON-RPC is unreachable', 'ANYTXT_DOWN', {
+      cause: error,
+      hint: `Start the Anytxt GUI (ATGUI.exe); the index service alone does not serve ${url}.`,
+    })
+  }
+  if (!response.ok) {
+    throw new EngineError(`Anytxt returned HTTP ${response.status}`, 'ANYTXT_HTTP', {
+      hint: `Check the Anytxt JSON-RPC endpoint at ${url}.`,
+    })
+  }
+  let data
+  try {
+    data = await response.json()
+  } catch (error) {
+    if (signal?.aborted) {
+      throw new EngineError('Anytxt request was aborted', 'ANYTXT_ABORTED', { cause: error })
+    }
+    if (error?.name === 'TimeoutError') {
+      throw new EngineError('Anytxt response timed out', 'ANYTXT_TIMEOUT', { cause: error })
+    }
+    throw new EngineError('Anytxt returned non-JSON', 'ANYTXT_BAD_OUTPUT', { cause: error })
+  }
+  if (!data || typeof data !== 'object') {
+    throw new EngineError('Anytxt returned a non-object JSON value', 'ANYTXT_BAD_OUTPUT')
+  }
+  if (data.error) {
+    throw new EngineError(`Anytxt RPC error: ${JSON.stringify(data.error)}`, 'ANYTXT_RPC', {
+      hint: 'Check the query syntax; Anytxt uses & | ! ( ) and "exact phrase".',
+    })
+  }
+  const output = data.result?.data?.output
+  if (output === undefined) {
+    throw new EngineError('Anytxt returned no result.data.output', 'ANYTXT_RPC')
+  }
+  return output
+}
+
+/** Try the primary URL, then the 9921 fallback only on connection failures. */
+async function rpcFirst(urls, method, input, options) {
+  let lastError
+  for (const url of urls) {
+    try {
+      return await anytxtRpc(url, method, input, options)
+    } catch (error) {
+      lastError = error
+      if (error.code === 'ANYTXT_DOWN' && url !== urls[urls.length - 1]) continue
+      throw error
+    }
+  }
+  throw lastError
+}
+
+/** Search document contents through Anytxt, one request pair per root. */
+export async function searchContent({
+  query,
+  roots,
+  ext,
+  limit = 20,
+  url = DEFAULT_URL,
+  timeoutMs = RPC_TIMEOUT_MS,
+  signal,
+  fetchImpl = fetch,
+} = {}) {
+  if (typeof query !== 'string' || query.trim().length === 0) {
+    throw new EngineError('query must be a non-empty string', 'INVALID_ARGUMENT')
+  }
+  if (!Number.isInteger(limit) || limit < 1) {
+    throw new EngineError('limit must be a positive integer', 'INVALID_ARGUMENT')
+  }
+  const urls = resolveAnytxtUrls(url)
+  const { pattern, st } = quoteAware(query)
+  const byRef = new Map()
+  let total = 0
+
+  for (const root of roots) {
+    const countOut = await rpcFirst(
+      urls,
+      'ATRpcServer.Searcher.V1.Search',
+      {
+        pattern,
+        filterDir: root,
+        filterExt: ext || '*',
+        lastModifyBegin: 0,
+        lastModifyEnd: 2147483647,
+        st,
+      },
+      { timeoutMs, signal, fetchImpl },
+    )
+    const count = typeof countOut.count === 'number' ? countOut.count : 0
+    total += count
+    if (count === 0) continue
+
+    const page = await rpcFirst(
+      urls,
+      'ATRpcServer.Searcher.V1.GetResult',
+      {
+        pattern,
+        filterDir: root,
+        filterExt: ext || '*',
+        lastModifyBegin: 0,
+        lastModifyEnd: 2147483647,
+        limit: String(limit),
+        offset: 0,
+        order: 0,
+        st,
+      },
+      { timeoutMs, signal, fetchImpl },
+    )
+    for (const tuple of page.files || []) {
+      const item = parseFileTuple(tuple)
+      if (item && !byRef.has(item.ref)) byRef.set(item.ref, item)
+    }
+  }
+
+  const items = [...byRef.values()].slice(0, limit)
+  return { items, total, truncated: total > items.length }
+}
+
+/** Snippets around a match in one indexed file. */
+export async function getFragments({
+  ref,
+  query,
+  url = DEFAULT_URL,
+  timeoutMs = RPC_TIMEOUT_MS,
+  signal,
+  fetchImpl = fetch,
+} = {}) {
+  if (!ref) throw new EngineError('ref must be a non-empty string', 'INVALID_ARGUMENT')
+  if (typeof query !== 'string' || query.trim().length === 0) {
+    throw new EngineError('query must be a non-empty string', 'INVALID_ARGUMENT')
+  }
+  const output = await rpcFirst(
+    resolveAnytxtUrls(url),
+    'ATRpcServer.Searcher.V1.GetFragmentAll',
+    { fid: ref, pattern: query },
+    { timeoutMs, signal, fetchImpl },
+  )
+  return (output.text || []).map(stripHighlights).filter(Boolean)
+}
+
+/** Full extracted text for one indexed file. */
+export async function getRawText({
+  ref,
+  url = DEFAULT_URL,
+  timeoutMs = RPC_TIMEOUT_MS,
+  signal,
+  fetchImpl = fetch,
+} = {}) {
+  if (!ref) throw new EngineError('ref must be a non-empty string', 'INVALID_ARGUMENT')
+  const output = await rpcFirst(
+    resolveAnytxtUrls(url),
+    'ATRpcServer.Searcher.V1.GetRawTextByFID',
+    { fid: ref },
+    { timeoutMs, signal, fetchImpl },
+  )
+  return typeof output.text === 'string' ? output.text : ''
+}
+
+/** Probe Anytxt without throwing. */
+export async function anytxtStatus({
+  url = DEFAULT_URL,
+  root = process.env.SystemDrive ? `${process.env.SystemDrive}\\` : 'C:\\',
+  timeoutMs = 1500,
+  signal,
+  fetchImpl = fetch,
+} = {}) {
+  const urls = resolveAnytxtUrls(url)
+  try {
+    await rpcFirst(
+      urls,
+      'ATRpcServer.Searcher.V1.Search',
+      {
+        pattern: 'the',
+        filterDir: root,
+        filterExt: 'txt',
+        lastModifyBegin: 0,
+        lastModifyEnd: 2147483647,
+      },
+      { timeoutMs, signal, fetchImpl },
+    )
+    return { ok: true, url: urls[0] }
+  } catch (error) {
+    return { ok: false, code: error.code ?? 'ANYTXT_DOWN', message: error.message, url: urls[0] }
+  }
+}