gheim 0.1.1 → 0.1.3

package/dist/esm/openai/index.js

@@ -1,5 +1,10 @@
-import { createRequire } from "node:module";
-var __require = /* @__PURE__ */ createRequire(import.meta.url);
+var __require = /* @__PURE__ */ ((x) => typeof require !== "undefined" ? require : typeof Proxy !== "undefined" ? new Proxy(x, {
+  get: (a, b) => (typeof require !== "undefined" ? require : a)[b]
+}) : x)(function(x) {
+  if (typeof require !== "undefined")
+    return require.apply(this, arguments);
+  throw Error('Dynamic require of "' + x + '" is not supported');
+});
 
 // src/core/sentinels.ts
 var LABEL_TO_TAG = {
@@ -228,8 +233,10 @@ class LocalDetector {
   chunkTokens;
   chunkOverlapTokens;
   batchSize;
+  actualDevice = null;
   _pipeline = null;
   _loadPromise = null;
+  _onProgress;
   constructor(opts = {}) {
     this.model = opts.model ?? DEFAULT_MODEL2;
     this.device = opts.device ?? "auto";
@@ -238,11 +245,13 @@ class LocalDetector {
     this.chunkTokens = opts.chunkTokens ?? DEFAULT_CHUNK_TOKENS;
     this.chunkOverlapTokens = opts.chunkOverlapTokens ?? DEFAULT_OVERLAP_TOKENS;
     this.batchSize = opts.batchSize ?? DEFAULT_BATCH_SIZE;
+    this._onProgress = opts.onProgress;
     if (this.chunkOverlapTokens >= this.chunkTokens) {
       throw new Error(`chunkOverlapTokens (${this.chunkOverlapTokens}) must be smaller than chunkTokens (${this.chunkTokens})`);
     }
     if (opts.pipelineInstance) {
       this._pipeline = opts.pipelineInstance;
+      this.actualDevice = this.device === "auto" ? null : this.device;
     }
   }
   async load() {
@@ -251,24 +260,70 @@ class LocalDetector {
     if (this._loadPromise)
       return this._loadPromise;
     this._loadPromise = (async () => {
-      let mod;
-      try {
-        mod = await import("@huggingface/transformers");
-      } catch (e) {
-        throw new Error("LocalDetector requires `@huggingface/transformers`. Install with: bun add @huggingface/transformers");
+      const mod = await loadTransformersJs();
+      const sequence = await this._planDeviceSequence();
+      let lastErr;
+      for (let i = 0;i < sequence.length; i++) {
+        const dev = sequence[i] ?? "wasm";
+        try {
+          const pipe = await mod.pipeline("token-classification", this.model, {
+            device: dev,
+            dtype: this.dtype,
+            progress_callback: this._onProgress ? (raw) => this._emitProgress(raw, dev) : undefined
+          });
+          this._pipeline = pipe;
+          this.actualDevice = dev;
+          return pipe;
+        } catch (e) {
+          lastErr = e;
+          if (i < sequence.length - 1)
+            continue;
+          throw e;
+        }
       }
-      const pipe = await mod.pipeline("token-classification", this.model, {
-        device: this.device,
-        dtype: this.dtype
-      });
-      this._pipeline = pipe;
-      return pipe;
+      throw lastErr ?? new Error("LocalDetector.load(): no candidate backends");
     })();
     return this._loadPromise;
   }
+  async _planDeviceSequence() {
+    if (this.device !== "auto")
+      return [this.device];
+    const seq = [];
+    const nav = typeof navigator !== "undefined" ? navigator : null;
+    if (nav?.gpu?.requestAdapter) {
+      try {
+        const adapter = await nav.gpu.requestAdapter();
+        if (adapter)
+          seq.push("webgpu");
+      } catch {}
+    }
+    seq.push("wasm");
+    return seq;
+  }
+  _emitProgress(raw, device) {
+    if (!this._onProgress)
+      return;
+    const event = {
+      phase: raw.status ?? "progress",
+      device
+    };
+    if (raw.file)
+      event.file = raw.file;
+    if (raw.status === "progress") {
+      if (raw.loaded != null)
+        event.loadedBytes = raw.loaded;
+      if (raw.total != null)
+        event.totalBytes = raw.total;
+      if (raw.progress != null) {
+        const norm = raw.progress > 1 ? raw.progress / 100 : raw.progress;
+        event.fraction = Math.max(0, Math.min(1, norm));
+      }
+    }
+    this._onProgress(event);
+  }
   async detect(text, opts) {
     if (opts?.model && opts.model !== this.model) {
-      throw new Error(`LocalDetector was constructed with model='${this.model}'; per-call model override ('${opts.model}') not supported.`);
+      throw new Error(`LocalDetector was constructed with model='${this.model}'; ` + `per-call model override ('${opts.model}') not supported.`);
     }
     if (!text)
       return [];
@@ -277,7 +332,7 @@ class LocalDetector {
   }
   async detectBatch(texts, opts) {
     if (opts?.model && opts.model !== this.model) {
-      throw new Error(`LocalDetector was constructed with model='${this.model}'; per-call model override ('${opts.model}') not supported.`);
+      throw new Error(`LocalDetector was constructed with model='${this.model}'; ` + `per-call model override ('${opts.model}') not supported.`);
     }
     if (texts.length === 0)
       return [];
@@ -438,102 +493,225 @@ function chunkByChars(text, chunkChars, overlapChars) {
 function normalizeWord(word) {
   return word.replace(/##/g, "").trim();
 }
-// src/detectors/index.ts
-function defaultDetector() {
-  const hasKey = typeof process !== "undefined" && Boolean(process.env?.GHEIM_API_KEY);
-  return hasKey ? new RemoteDetector : new LocalDetector;
-}
-
-// src/normalizers.ts
-import { createRequire as createRequire2 } from "node:module";
-var _require = null;
-var _requireResolved = false;
-function _getRequire() {
-  if (_requireResolved)
-    return _require;
-  _requireResolved = true;
+async function loadTransformersJs() {
   try {
-    _require = createRequire2(import.meta.url);
+    return await import("@huggingface/transformers");
   } catch {
-    _require = null;
+    throw new Error("LocalDetector requires `@huggingface/transformers`. Install with: bun add @huggingface/transformers");
   }
-  return _require;
 }
-function loadSync(name, errMsg) {
-  const req = _getRequire();
-  if (!req)
-    throw new Error(errMsg);
-  try {
-    return req(name);
-  } catch {
-    throw new Error(errMsg);
+// src/detectors/composite.ts
+function luhnOk(s) {
+  const digits = [];
+  for (const c of s) {
+    if (c >= "0" && c <= "9")
+      digits.push(Number(c));
+  }
+  if (digits.length < 13 || digits.length > 19)
+    return false;
+  let total = 0;
+  for (let i = 0;i < digits.length; i++) {
+    let d = digits[digits.length - 1 - i] ?? 0;
+    if (i % 2 === 1) {
+      d *= 2;
+      if (d > 9)
+        d -= 9;
+    }
+    total += d;
   }
+  return total % 10 === 0;
 }
-function loadPhoneLib() {
-  return loadSync("libphonenumber-js", "the e164 normalizer requires libphonenumber-js. " + "Install with: bun add libphonenumber-js");
+function ibanChOk(raw) {
+  const s = raw.replace(/[\s-]/g, "");
+  if (s.length !== 21 || !s.startsWith("CH") || !/^\d+$/.test(s.slice(2))) {
+    return false;
+  }
+  const rearranged = s.slice(4) + s.slice(0, 4);
+  let numeric = "";
+  for (const c of rearranged) {
+    numeric += c >= "A" && c <= "Z" ? String(c.charCodeAt(0) - 55) : c;
+  }
+  let rem = 0;
+  for (const ch of numeric) {
+    rem = (rem * 10 + Number(ch)) % 97;
+  }
+  return rem === 1;
 }
-function e164(opts = {}) {
-  const lib = loadPhoneLib();
-  return (s) => {
-    try {
-      const parsed = lib.parsePhoneNumberFromString(s, opts.region);
-      if (!parsed || !parsed.isValid())
-        return null;
-      return parsed.format("E.164");
-    } catch {
-      return null;
-    }
-  };
+function ahvOk(s) {
+  const digits = [];
+  for (const c of s) {
+    if (c >= "0" && c <= "9")
+      digits.push(Number(c));
+  }
+  if (digits.length !== 13)
+    return false;
+  if (digits[0] !== 7 || digits[1] !== 5 || digits[2] !== 6)
+    return false;
+  let total = 0;
+  for (let i = 0;i < 12; i++) {
+    total += (digits[i] ?? 0) * (i % 2 === 0 ? 1 : 3);
+  }
+  const check = (10 - total % 10) % 10;
+  return digits[12] === check;
 }
-function loadChrono(opts) {
-  const mod = loadSync("chrono-node", "the isoDate normalizer requires chrono-node. " + "Install with: bun add chrono-node");
-  if (opts.locale) {
-    const localeParser = mod[opts.locale];
-    if (localeParser)
-      return localeParser;
-  }
-  return mod;
+function vatCheOk(s) {
+  const digits = [];
+  for (const c of s) {
+    if (c >= "0" && c <= "9")
+      digits.push(Number(c));
+  }
+  if (digits.length < 9)
+    return false;
+  const weights = [5, 4, 3, 2, 7, 6, 5, 4];
+  let total = 0;
+  for (let i = 0;i < 8; i++) {
+    total += (digits[i] ?? 0) * (weights[i] ?? 0);
+  }
+  let expected = 11 - total % 11;
+  if (expected === 11)
+    expected = 0;
+  else if (expected === 10)
+    return false;
+  return digits[8] === expected;
 }
-function isoDate(opts = {}) {
-  const parser = loadChrono(opts);
-  return (s) => {
-    const d = parser.parseDate(s);
-    if (!d)
-      return null;
-    return d.toISOString().slice(0, 10);
-  };
+var REGEXES = [
+  {
+    label: "private_email",
+    pattern: /\b[\w._%+\-]+@[\w.\-]+\.[A-Za-z]{2,}\b/g
+  },
+  {
+    label: "private_url",
+    pattern: /https?:\/\/[^\s)>\]]+/g
+  },
+  {
+    label: "private_phone",
+    pattern: /(?:\+41|0041|0)\s?(?:\(0\)\s?)?\d{2}[\s\-/.]?\d{3}[\s\-/.]?\d{2}[\s\-/.]?\d{2}\b/g
+  },
+  {
+    label: "account_number",
+    pattern: /\bCH\d{2}(?:[\s-]?\d){17}\b/g,
+    validator: ibanChOk
+  },
+  {
+    label: "account_number",
+    pattern: /\b756\.\d{4}\.\d{4}\.\d{2}\b/g,
+    validator: ahvOk
+  },
+  {
+    label: "account_number",
+    pattern: /\b756\d{10}\b/g,
+    validator: ahvOk
+  },
+  {
+    label: "account_number",
+    pattern: /\bCHE-\d{3}\.\d{3}\.\d{3}(?:\s+(?:MWST|TVA|IVA))?\b/g,
+    validator: vatCheOk
+  },
+  {
+    label: "account_number",
+    pattern: /\b(?:\d[\s-]?){15,16}\d\b/g,
+    validator: luhnOk
+  },
+  {
+    label: "private_date",
+    pattern: /\b(?:\d{1,2}[./]\d{1,2}[./]\d{4}|\d{4}[./-]\d{1,2}[./-]\d{1,2})\b/g
+  },
+  {
+    label: "secret",
+    pattern: /\bsk-(?:proj-)?[A-Za-z0-9_\-]{20,}\b/g
+  },
+  {
+    label: "secret",
+    pattern: /\bghp_[A-Za-z0-9]{36}\b/g
+  },
+  {
+    label: "secret",
+    pattern: /\bAKIA[A-Z0-9]{16}\b/g
+  }
+];
+var URL_TRAIL_TRIM = '.,;:!?")>]';
+function trimUrl(text, start, end) {
+  while (end > start && URL_TRAIL_TRIM.includes(text[end - 1] ?? ""))
+    end--;
+  return [start, end];
 }
-function germanTransliteration() {
-  const table = {
-    ä: "ae",
-    Ä: "ae",
-    ö: "oe",
-    Ö: "oe",
-    ü: "ue",
-    Ü: "ue",
-    ß: "ss"
-  };
-  return (s) => {
-    let out = "";
-    for (const ch of s.normalize("NFKC")) {
-      out += table[ch] ?? ch;
+function findRegexSpans(text) {
+  const candidates = [];
+  for (const { label, pattern, validator } of REGEXES) {
+    pattern.lastIndex = 0;
+    let m;
+    while ((m = pattern.exec(text)) !== null) {
+      let start = m.index;
+      let end = m.index + m[0].length;
+      if (label === "private_url")
+        [start, end] = trimUrl(text, start, end);
+      const value = text.slice(start, end);
+      if (!value.trim())
+        continue;
+      if (validator && !validator(value))
+        continue;
+      candidates.push({
+        start,
+        end,
+        label,
+        text: value,
+        score: 1
+      });
     }
-    return out.toLowerCase().split(/\s+/).filter(Boolean).join(" ");
-  };
+  }
+  candidates.sort((a, b) => a.start !== b.start ? a.start - b.start : b.end - b.start - (a.end - a.start));
+  const out = [];
+  let lastEnd = -1;
+  for (const sp of candidates) {
+    if (sp.start < lastEnd)
+      continue;
+    out.push(sp);
+    lastEnd = sp.end;
+  }
+  return out;
 }
-var BUILTINS = {
-  e164: () => e164(),
-  iso_date: () => isoDate(),
-  german: () => germanTransliteration()
-};
-function resolveNormalizer(spec) {
-  if (typeof spec === "function")
-    return spec;
-  const factory = BUILTINS[spec];
-  if (!factory) {
-    throw new Error(`unknown built-in normalizer: ${JSON.stringify(spec)}. ` + `Available: ${Object.keys(BUILTINS).join(", ")}, or pass a callable.`);
-  }
-  return factory();
+function maskSpans(text, spans) {
+  if (spans.length === 0)
+    return text;
+  const chars = [...text];
+  for (const sp of spans) {
+    for (let i = sp.start;i < sp.end && i < chars.length; i++) {
+      chars[i] = " ";
+    }
+  }
+  return chars.join("");
+}
+
+class CompositeDetector {
+  model;
+  constructor(opts) {
+    if (!opts || !opts.model) {
+      throw new Error("CompositeDetector requires { model: Detector } — pass any object with " + "a .detect(text) method (e.g. new LocalDetector({...})).");
+    }
+    this.model = opts.model;
+  }
+  async detect(text, opts) {
+    if (!text)
+      return [];
+    const regexSpans = findRegexSpans(text);
+    const masked = maskSpans(text, regexSpans);
+    const modelSpans = await this.model.detect(masked, opts);
+    const out = [...regexSpans];
+    const regexRanges = regexSpans.map((s) => [s.start, s.end]);
+    for (const sp of modelSpans) {
+      const overlaps = regexRanges.some(([rs, re]) => sp.start < re && rs < sp.end);
+      if (overlaps)
+        continue;
+      out.push(sp);
+    }
+    out.sort((a, b) => a.start !== b.start ? a.start - b.start : b.end - b.start - (a.end - a.start));
+    return out;
+  }
+}
+// src/detectors/index.ts
+function defaultDetector() {
+  const hasKey = typeof process !== "undefined" && Boolean(process.env?.GHEIM_API_KEY);
+  return hasKey ? new RemoteDetector : new LocalDetector;
 }
 
 // src/core/session.ts
@@ -548,8 +726,8 @@ class Session {
   resolvedNormalizers = {};
   constructor(opts = {}) {
     if (opts.normalizers) {
-      for (const [label, spec] of Object.entries(opts.normalizers)) {
-        this.resolvedNormalizers[label] = resolveNormalizer(spec);
+      for (const [label, fn] of Object.entries(opts.normalizers)) {
+        this.resolvedNormalizers[label] = fn;
       }
     }
   }
@@ -573,8 +751,11 @@ class Session {
     return sentinel;
   }
   applySpans(text, spans) {
+    return this.applySpansDetailed(text, spans).redacted;
+  }
+  applySpansDetailed(text, spans) {
     if (spans.length === 0)
-      return text;
+      return { redacted: text, merged: [] };
     const sorted = [...spans].sort((a, b) => a.start - b.start || b.end - b.start - (a.end - a.start));
     const merged = mergeAdjacent(text, sorted);
     const out = [];
@@ -590,7 +771,7 @@ class Session {
       cursor = end;
     }
     out.push(text.slice(cursor));
-    return out.join("");
+    return { redacted: out.join(""), merged };
   }
   restore(text) {
     if (Object.keys(this.mapping).length === 0)
@@ -823,6 +1004,16 @@ function restoreChatResponse(response, session) {
     if (msg && typeof msg.content === "string") {
       msg.content = session.restore(msg.content);
     }
+    if (msg && typeof msg.reasoning === "string") {
+      msg.reasoning = session.restore(msg.reasoning);
+    }
+    if (msg && Array.isArray(msg.reasoning_details)) {
+      for (const r of msg.reasoning_details) {
+        if (r && typeof r.text === "string") {
+          r.text = session.restore(r.text);
+        }
+      }
+    }
     for (const tc of msg?.tool_calls ?? []) {
       const fn = tc.function;
       if (fn && typeof fn.arguments === "string") {
@@ -837,6 +1028,16 @@ function patchChatChunk(chunk, buf) {
     if (typeof delta.content === "string") {
       delta.content = buf.feed(delta.content);
     }
+    if (typeof delta.reasoning === "string") {
+      delta.reasoning = buf.feed(delta.reasoning);
+    }
+    if (Array.isArray(delta.reasoning_details)) {
+      for (const r of delta.reasoning_details) {
+        if (r && typeof r.text === "string") {
+          r.text = buf.feed(r.text);
+        }
+      }
+    }
   }
 }
 function makeChatTailChunk(template, content) {
@@ -1163,9 +1364,20 @@ class OpenAI {
   gheimStrict;
   _clientPromise;
   constructor(opts = {}) {
-    const detector = opts.gheimDetector ?? defaultDetector();
-    this.gheimStrict = opts.gheimStrict ?? true;
-    this._clientPromise = opts.openaiClient ? Promise.resolve(opts.openaiClient) : loadOpenAI(opts.clientOptions);
+    const {
+      gheimDetector,
+      gheimStrict,
+      openaiClient,
+      clientOptions,
+      ...passthrough
+    } = opts;
+    const detector = gheimDetector ?? defaultDetector();
+    this.gheimStrict = gheimStrict ?? true;
+    const innerOpts = {
+      ...clientOptions ?? {},
+      ...passthrough
+    };
+    this._clientPromise = openaiClient ? Promise.resolve(openaiClient) : loadOpenAI(innerOpts);
     this._clientPromise.then((c) => {
       this.raw = c;
     });

package/dist/types/core/session.d.ts

@@ -1,15 +1,24 @@
 /** Session state — mirrors gheim-py's Session. */
 import type { Span } from "../detectors/base.ts";
-import type { Normalizer } from "../normalizers.ts";
+/** A surface canonicaliser. Maps a raw surface to a canonical key, or
+ *  null to fall back to the default NFKC + lowercase key. Re-declared
+ *  locally so this module doesn't pull in `gheim/normalizers` (which
+ *  uses Node's `createRequire` and breaks browser bundlers). */
+export type Normalizer = (s: string) => string | null;
 /** Constructor options for Session. */
 export interface SessionOptions {
     /**
      * Optional per-label canonical-form normalizers. Maps a label name
-     * (e.g. "private_phone") to either a built-in name ("e164" /
-     * "iso_date") or a callable Normalizer. Surfaces that fail to parse
-     * fall back to the default NFKC+lowercase key. See ./normalizers.ts.
+     * (e.g. "private_phone") to a callable Normalizer. Surfaces that fail
+     * to parse fall back to the default NFKC+lowercase key.
+     *
+     * Built-in factories (e164, isoDate, germanTransliteration) live in
+     * the `gheim/normalizers` subpath — they pull in optional peer deps
+     * (`libphonenumber-js`, `chrono-node`) so they're not loaded by
+     * default to keep the browser bundle small and avoid Node-only
+     * imports leaking into the main entry.
      */
-    normalizers?: Record<string, string | Normalizer>;
+    normalizers?: Record<string, Normalizer>;
 }
 export declare class Session {
     /** Sentinel string ("<PERSON_1>") → original surface form. */
@@ -19,7 +28,19 @@ export declare class Session {
     private resolvedNormalizers;
     constructor(opts?: SessionOptions);
     allocate(label: string, surface: string): string;
-    applySpans(text: string, spans: Span[]): string;
+    applySpans(text: string, spans: readonly (Span | MergedSpan)[]): string;
+    /**
+     * Like {@link applySpans} but also returns the post-merge span list. UI
+     * consumers (segment rendering, bar overlays) typically need both the
+     * redacted text and the merged spans so they can highlight the redacted
+     * runs at their original character positions; without this method they'd
+     * have to call {@link mergeAdjacent} again on the same input. Pure
+     * convenience — no extra cost over `applySpans`.
+     */
+    applySpansDetailed(text: string, spans: readonly (Span | MergedSpan)[]): {
+        redacted: string;
+        merged: MergedSpan[];
+    };
     restore(text: string): string;
     toJSON(): {
         mapping: Record<string, string>;
@@ -28,4 +49,19 @@ export declare class Session {
         mapping: Record<string, string>;
     }, opts?: SessionOptions): Session;
 }
+/** A span after merge: same shape as input, but no `text`/`score` carried. */
+export interface MergedSpan {
+    start: number;
+    end: number;
+    label: string;
+}
+/** Merge runs of adjacent same-label spans (BPE-split surface fix).
+ *
+ * Two same-label spans separated by ≤ MERGE_GAP characters of pure
+ * whitespace (or directly touching) collapse into one. Models tokenize
+ * a phone like "+41 44 268 12 34" into many single-space-separated
+ * pieces with the same label; merging recovers the original entity so
+ * the demo and SDK both see one PHONE span instead of five.
+ */
+export declare function mergeAdjacent(text: string, spans: readonly (Span | MergedSpan)[]): MergedSpan[];
 //# sourceMappingURL=session.d.ts.map

package/dist/types/core/session.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"session.d.ts","sourceRoot":"","sources":["../../../src/core/session.ts"],"names":[],"mappings":"AAAA,kDAAkD;AAClD,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,sBAAsB,CAAC;AAEjD,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAmBpD,uCAAuC;AACvC,MAAM,WAAW,cAAc;IAC7B;;;;;OAKG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,GAAG,UAAU,CAAC,CAAC;CACnD;AAED,qBAAa,OAAO;IAClB,8DAA8D;IAC9D,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAM;IACrC,OAAO,CAAC,QAAQ,CAAkC;IAClD,OAAO,CAAC,QAAQ,CAAkC;IAClD,OAAO,CAAC,mBAAmB,CAAkC;gBAEjD,IAAI,GAAE,cAAmB;IAQrC,QAAQ,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,MAAM;IAiBhD,UAAU,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,IAAI,EAAE,GAAG,MAAM;IAoB/C,OAAO,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM;IAK7B,MAAM,IAAI;QAAE,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;KAAE;IAI7C,MAAM,CAAC,QAAQ,CACb,GAAG,EAAE;QAAE,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;KAAE,EACxC,IAAI,GAAE,cAAmB,GACxB,OAAO;CAqBX"}
+{"version":3,"file":"session.d.ts","sourceRoot":"","sources":["../../../src/core/session.ts"],"names":[],"mappings":"AAAA,kDAAkD;AAClD,OAAO,KAAK,EAAE,IAAI,EAAE,MAAM,sBAAsB,CAAC;AAGjD;;;gEAGgE;AAChE,MAAM,MAAM,UAAU,GAAG,CAAC,CAAC,EAAE,MAAM,KAAK,MAAM,GAAG,IAAI,CAAC;AAkBtD,uCAAuC;AACvC,MAAM,WAAW,cAAc;IAC7B;;;;;;;;;;OAUG;IACH,WAAW,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,UAAU,CAAC,CAAC;CAC1C;AAED,qBAAa,OAAO;IAClB,8DAA8D;IAC9D,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAM;IACrC,OAAO,CAAC,QAAQ,CAAkC;IAClD,OAAO,CAAC,QAAQ,CAAkC;IAClD,OAAO,CAAC,mBAAmB,CAAkC;gBAEjD,IAAI,GAAE,cAAmB;IAQrC,QAAQ,CAAC,KAAK,EAAE,MAAM,EAAE,OAAO,EAAE,MAAM,GAAG,MAAM;IAiBhD,UAAU,CAAC,IAAI,EAAE,MAAM,EAAE,KAAK,EAAE,SAAS,CAAC,IAAI,GAAG,UAAU,CAAC,EAAE,GAAG,MAAM;IAIvE;;;;;;;OAOG;IACH,kBAAkB,CAChB,IAAI,EAAE,MAAM,EACZ,KAAK,EAAE,SAAS,CAAC,IAAI,GAAG,UAAU,CAAC,EAAE,GACpC;QAAE,QAAQ,EAAE,MAAM,CAAC;QAAC,MAAM,EAAE,UAAU,EAAE,CAAA;KAAE;IAoB7C,OAAO,CAAC,IAAI,EAAE,MAAM,GAAG,MAAM;IAK7B,MAAM,IAAI;QAAE,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;KAAE;IAI7C,MAAM,CAAC,QAAQ,CACb,GAAG,EAAE;QAAE,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;KAAE,EACxC,IAAI,GAAE,cAAmB,GACxB,OAAO;CAqBX;AAID,8EAA8E;AAC9E,MAAM,WAAW,UAAU;IACzB,KAAK,EAAE,MAAM,CAAC;IACd,GAAG,EAAE,MAAM,CAAC;IACZ,KAAK,EAAE,MAAM,CAAC;CACf;AAED;;;;;;;GAOG;AACH,wBAAgB,aAAa,CAC3B,IAAI,EAAE,MAAM,EACZ,KAAK,EAAE,SAAS,CAAC,IAAI,GAAG,UAAU,CAAC,EAAE,GACpC,UAAU,EAAE,CAqBd"}

package/dist/types/detectors/composite.d.ts

@@ -0,0 +1,58 @@
+/**
+ * Composite detector: regex front-end + model on the remainder.
+ *
+ * Production-ready Swiss PII detector that combines two complementary
+ * strategies — a port of the Python sibling
+ * (`gheim.detectors.composite.CompositeDetector`) with parity-tested
+ * regexes and checksum validators.
+ *
+ * 1. Deterministic regex front-end for structured PII categories where
+ *    shape is unambiguous and checksums verify identity:
+ *    - IBAN-CH (mod-97-10), AHV (EAN-13 mod-10), VAT-CHE (mod-11-10),
+ *      Visa/Mastercard (Luhn)
+ *    - Email, URL, Swiss phone (+41 / 0041 / 0...), explicit dates
+ *      (DD.MM.YYYY, YYYY-MM-DD)
+ *    - API tokens (sk-, ghp_, AKIA...)
+ *
+ *    Spans found here are "trusted" — checksums catch most surface-form
+ *    imitations; the model is never asked.
+ *
+ * 2. The fine-tuned model on whatever's left after regex masking.
+ *    Persons, addresses, and edge-case dates fall here. The model's
+ *    "single-category mode" failure (where an IBAN/phone-shaped
+ *    sequence suppresses person/date detection in the same input) is
+ *    bypassed because the regex already absorbed those tokens — the
+ *    model sees them as whitespace.
+ *
+ * Wraps the same `Detector` interface (`detect(text) → Span[]`) as
+ * `LocalDetector` so it drops into any code path that already accepts a
+ * detector.
+ */
+import type { Detector, Span } from "./base.ts";
+/** Options for {@link CompositeDetector}. */
+export interface CompositeDetectorOptions {
+    /** Inner detector — usually a {@link LocalDetector}. Anything with
+     *  a `detect(text) → Promise<Span[]>` method works. */
+    model: Detector;
+}
+/** Regex front-end (with checksum validation) + model on the remainder.
+ *
+ * @example
+ * import { LocalDetector, CompositeDetector } from "gheim";
+ * const composite = new CompositeDetector({
+ *   model: new LocalDetector({ dtype: "q8" }),
+ * });
+ * const spans = await composite.detect(swissLetter);
+ * // → IBAN/phone/email caught by regex (checksum-validated);
+ * //   person/address/dates caught by the model on the masked remainder.
+ */
+export declare class CompositeDetector implements Detector {
+    readonly model: Detector;
+    constructor(opts: CompositeDetectorOptions);
+    /** Two-pass detection: regex first (with checksum), then model on
+     *  the masked remainder. Returns a single overlap-resolved span list. */
+    detect(text: string, opts?: {
+        model?: string;
+    }): Promise<Span[]>;
+}
+//# sourceMappingURL=composite.d.ts.map

package/dist/types/detectors/composite.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"composite.d.ts","sourceRoot":"","sources":["../../../src/detectors/composite.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AACH,OAAO,KAAK,EAAE,QAAQ,EAAE,IAAI,EAAE,MAAM,WAAW,CAAC;AAiNhD,6CAA6C;AAC7C,MAAM,WAAW,wBAAwB;IACvC;2DACuD;IACvD,KAAK,EAAE,QAAQ,CAAC;CACjB;AAED;;;;;;;;;;GAUG;AACH,qBAAa,iBAAkB,YAAW,QAAQ;IAChD,QAAQ,CAAC,KAAK,EAAE,QAAQ,CAAC;gBAEb,IAAI,EAAE,wBAAwB;IAU1C;6EACyE;IACnE,MAAM,CAAC,IAAI,EAAE,MAAM,EAAE,IAAI,CAAC,EAAE;QAAE,KAAK,CAAC,EAAE,MAAM,CAAA;KAAE,GAAG,OAAO,CAAC,IAAI,EAAE,CAAC;CAmBvE"}