@chainlesschain/personal-data-hub 0.4.7 → 0.4.23

package/lib/adapters/doc-baidu-netdisk/index.js

@@ -0,0 +1,91 @@
+/**
+ * §13+ — 百度网盘 (Baidu Netdisk, com.baidu.netdisk) adapter. §12.1 ROI ⭐⭐⭐
+ * "文件 + 外链".
+ *
+ * Thin wrapper over _document-base — a cloud-drive file list is the same shape
+ * as the doc-wps / doc-tencent-docs "own-document list". Baidu Netdisk exposes
+ * the owner's files via pan.baidu.com/api/list (BDUSS cookie); this adapter
+ * supplies the endpoint + field mapping, the base handles snapshot + cookie-api
+ * orchestration + normalize (event POST + item DOCUMENT). Endpoint best-effort +
+ * overridable via opts.listUrl (not field-verified — FAMILY-23 playbook).
+ */
+
+"use strict";
+
+const { createDocumentAdapter, parseTime, SNAPSHOT_SCHEMA_VERSION } = require("../_document-base");
+
+const NAME = "doc-baidu-netdisk";
+const VERSION = "0.1.0";
+
+// Best-effort Baidu Netdisk file-list endpoint. Overridable via opts.listUrl.
+const NETDISK_LIST_URL = "https://pan.baidu.com/api/list";
+
+// Baidu Netdisk `category` codes → normalized docType.
+const CATEGORY_MAP = {
+  1: "video",
+  2: "audio",
+  3: "image",
+  4: "doc",
+  5: "app",
+  6: "other",
+  7: "seed",
+};
+
+function mapNetdiskType(d) {
+  if (d.isdir === 1 || d.isdir === true) return "folder";
+  const cat = d.category != null ? d.category : d.file_category;
+  if (cat != null && CATEGORY_MAP[cat]) return CATEGORY_MAP[cat];
+  const name = String(d.server_filename || d.filename || "").toLowerCase();
+  if (/\.(mp4|mkv|avi|mov)$/.test(name)) return "video";
+  if (/\.(mp3|flac|wav|m4a)$/.test(name)) return "audio";
+  if (/\.(jpg|jpeg|png|gif|webp)$/.test(name)) return "image";
+  if (/\.(docx?|xlsx?|pptx?|pdf|txt)$/.test(name)) return "doc";
+  return "file";
+}
+
+function extractDocs(resp) {
+  if (!resp || typeof resp !== "object") return [];
+  if (Array.isArray(resp.list)) return resp.list;
+  if (Array.isArray(resp.data)) return resp.data;
+  if (resp.data && Array.isArray(resp.data.list)) return resp.data.list;
+  return [];
+}
+
+function mapDoc(d) {
+  if (!d || typeof d !== "object") return null;
+  const docId = d.fs_id || d.fsId || d.id || d.path;
+  if (!docId) return null;
+  return {
+    docId: String(docId),
+    title: d.server_filename || d.filename || d.title || "(未命名)",
+    docType: mapNetdiskType(d),
+    url: d.path || d.dlink || null,
+    createdMs: parseTime(d.server_ctime || d.local_ctime || d.ctime),
+    updatedMs: parseTime(d.server_mtime || d.local_mtime || d.mtime),
+    extra: {
+      size: d.size != null ? d.size : null,
+      isDir: d.isdir === 1 || d.isdir === true ? true : false,
+      path: d.path || null,
+      category: d.category != null ? d.category : null,
+    },
+  };
+}
+
+const BaiduNetdiskAdapter = createDocumentAdapter({
+  NAME,
+  VERSION,
+  platform: "baidu-netdisk",
+  defaultListUrl: NETDISK_LIST_URL,
+  extractDocs,
+  mapDoc,
+});
+
+module.exports = {
+  BaiduNetdiskAdapter,
+  extractDocs,
+  mapDoc,
+  CATEGORY_MAP,
+  NAME,
+  VERSION,
+  SNAPSHOT_SCHEMA_VERSION,
+};

package/lib/adapters/doc-camscanner/index.js

@@ -0,0 +1,102 @@
+/**
+ * §13+ — 扫描全能王 (CamScanner, com.intsig.camscanner) adapter. §12.1 ROI ⭐⭐
+ * "扫描文档归档".
+ *
+ * Thin wrapper over _document-base — CamScanner's scanned-document archive is
+ * the same shape as the doc-wps / doc-tencent-docs / doc-baidu-netdisk
+ * "own-document list": each scanned doc has a title, page count, create/modify
+ * time, and a PDF/jump url. CamScanner syncs the owner's docs to its cloud
+ * (intsig sync API, session cookie / sync token); this adapter supplies the
+ * endpoint + field mapping, the base handles snapshot + cookie-api orchestration
+ * + normalize (event POST + item DOCUMENT). Endpoint best-effort + overridable
+ * via opts.listUrl (not field-verified — FAMILY-23 playbook). A signProvider
+ * seam covers intsig's request signature; best-effort unsigned when absent.
+ */
+
+"use strict";
+
+const { createDocumentAdapter, parseTime, SNAPSHOT_SCHEMA_VERSION } = require("../_document-base");
+
+const NAME = "doc-camscanner";
+const VERSION = "0.1.0";
+
+// Best-effort CamScanner cloud doc-list endpoint. Overridable via opts.listUrl.
+const CAMSCANNER_LIST_URL = "https://sync.intsig.net/sync/list_docs";
+
+// CamScanner document type hints → normalized docType. A CamScanner "doc" is a
+// scanned bundle of pages exportable as PDF; certificate/book/excel are OCR
+// sub-modes the app offers.
+const TYPE_MAP = {
+  0: "scan",
+  1: "scan",
+  2: "certificate",
+  3: "book",
+  4: "excel",
+  5: "ppt",
+  pdf: "pdf",
+  doc: "scan",
+  certificate: "certificate",
+  book: "book",
+  excel: "excel",
+  ppt: "ppt",
+};
+
+function mapCamScannerType(d) {
+  const t = d.doc_type != null ? d.doc_type : d.type;
+  if (t != null && TYPE_MAP[t] != null) return TYPE_MAP[t];
+  const title = String(d.title || d.doc_title || d.pdf_name || "").toLowerCase();
+  if (/\.pdf$/.test(title)) return "pdf";
+  if (/\.(xlsx?|csv)$/.test(title)) return "excel";
+  if (/\.(pptx?)$/.test(title)) return "ppt";
+  return "scan";
+}
+
+function extractDocs(resp) {
+  if (!resp || typeof resp !== "object") return [];
+  if (Array.isArray(resp.docs)) return resp.docs;
+  if (Array.isArray(resp.list)) return resp.list;
+  if (Array.isArray(resp.data)) return resp.data;
+  if (resp.data && Array.isArray(resp.data.docs)) return resp.data.docs;
+  if (resp.data && Array.isArray(resp.data.list)) return resp.data.list;
+  return [];
+}
+
+function mapDoc(d) {
+  if (!d || typeof d !== "object") return null;
+  const docId = d.sync_doc_id || d.doc_id || d.docId || d.id || d.sid;
+  if (!docId) return null;
+  const pages = d.page_num != null ? d.page_num : d.pages != null ? d.pages : d.page_count;
+  return {
+    docId: String(docId),
+    title: d.title || d.doc_title || d.pdf_name || "(未命名扫描件)",
+    docType: mapCamScannerType(d),
+    url: d.pdf_url || d.url || d.jump_url || null,
+    createdMs: parseTime(d.create_time || d.upload_time || d.ctime || d.created),
+    updatedMs: parseTime(d.modify_time || d.last_modify_time || d.update_time || d.mtime),
+    extra: {
+      pageNum: Number.isFinite(Number(pages)) ? Number(pages) : null,
+      tags: Array.isArray(d.tags) ? d.tags : d.tag != null ? [d.tag] : [],
+      folder: d.dir_title || d.folder || null,
+    },
+  };
+}
+
+const CamScannerDocAdapter = createDocumentAdapter({
+  NAME,
+  VERSION,
+  platform: "camscanner",
+  defaultListUrl: CAMSCANNER_LIST_URL,
+  extractDocs,
+  mapDoc,
+});
+
+module.exports = {
+  CamScannerDocAdapter,
+  extractDocs,
+  mapDoc,
+  mapCamScannerType,
+  TYPE_MAP,
+  NAME,
+  VERSION,
+  SNAPSHOT_SCHEMA_VERSION,
+};

package/lib/adapters/doc-tencent-docs/index.js

@@ -0,0 +1,94 @@
+/**
+ * §13+ — 腾讯文档 (Tencent Docs) adapter. "自创文档列表" (§12.1, ROI ⭐⭐⭐).
+ *
+ * Thin wrapper over _document-base. 腾讯文档 exposes the owner's documents via
+ * docs.qq.com dop-api; this adapter supplies the endpoint + field mapping, the
+ * base handles snapshot + cookie-api orchestration + normalize. Endpoint is
+ * best-effort + overridable via opts.listUrl (docs.qq.com rotates its dop-api;
+ * some calls need a sign — opts.signProvider seam — FAMILY-23 playbook, not
+ * field-verified).
+ */
+
+"use strict";
+
+const { createDocumentAdapter, parseTime, SNAPSHOT_SCHEMA_VERSION } = require("../_document-base");
+
+const NAME = "doc-tencent-docs";
+const VERSION = "0.1.0";
+
+// Best-effort Tencent Docs "my documents" list. Overridable via opts.listUrl.
+const TENCENT_DOCS_LIST_URL = "https://docs.qq.com/dop-api/get/personal/files";
+
+// Tencent Docs type codes → normalized docType.
+const TYPE_MAP = {
+  doc: "doc",
+  document: "doc",
+  sheet: "sheet",
+  spreadsheet: "sheet",
+  slide: "slide",
+  presentation: "slide",
+  pdf: "pdf",
+  form: "form",
+  mind: "mind",
+  1: "doc",
+  2: "sheet",
+  3: "slide",
+};
+
+function mapTencentType(d) {
+  const raw = d.type != null ? d.type : d.docType != null ? d.docType : d.fileType;
+  const key = String(raw == null ? "" : raw).toLowerCase();
+  return TYPE_MAP[key] || TYPE_MAP[raw] || "doc";
+}
+
+function extractDocs(resp) {
+  if (!resp || typeof resp !== "object") return [];
+  if (Array.isArray(resp.files)) return resp.files;
+  if (Array.isArray(resp.list)) return resp.list;
+  const data = resp.data && typeof resp.data === "object" ? resp.data : null;
+  if (data) {
+    if (Array.isArray(data.files)) return data.files;
+    if (Array.isArray(data.list)) return data.list;
+    if (Array.isArray(data.records)) return data.records;
+  }
+  return [];
+}
+
+function mapDoc(d) {
+  if (!d || typeof d !== "object") return null;
+  const docId = d.id || d.fileId || d.file_id || d.docId || d.url;
+  if (!docId) return null;
+  return {
+    docId: String(docId),
+    title: d.title || d.name || d.fileName || "(无标题)",
+    docType: mapTencentType(d),
+    url:
+      d.url ||
+      (d.id ? `https://docs.qq.com/doc/${d.id}` : null),
+    createdMs: parseTime(d.createTime || d.create_time || d.gmtCreate),
+    updatedMs: parseTime(d.lastModifyTime || d.modifyTime || d.updateTime || d.gmtModify),
+    extra: {
+      ownerName: d.ownerName || d.creatorName || null,
+      starred: d.isStar != null ? d.isStar : undefined,
+    },
+  };
+}
+
+const TencentDocsAdapter = createDocumentAdapter({
+  NAME,
+  VERSION,
+  platform: "tencent-docs",
+  defaultListUrl: TENCENT_DOCS_LIST_URL,
+  extractDocs,
+  mapDoc,
+});
+
+module.exports = {
+  TencentDocsAdapter,
+  extractDocs,
+  mapDoc,
+  TYPE_MAP,
+  NAME,
+  VERSION,
+  SNAPSHOT_SCHEMA_VERSION,
+};

package/lib/adapters/doc-wps/index.js

@@ -0,0 +1,77 @@
+/**
+ * §13+ — WPS 云文档 (Kingsoft Office) adapter. "自创文档列表" (§12.1, ROI ⭐⭐⭐).
+ *
+ * Thin wrapper over _document-base. WPS exposes the owner's cloud documents via
+ * drive.wps.cn; this adapter supplies the endpoint + field mapping, the base
+ * handles snapshot + cookie-api orchestration + normalize (event POST + item
+ * DOCUMENT). Endpoint is best-effort + overridable via opts.listUrl (WPS rotates
+ * its drive API — FAMILY-23 playbook, not field-verified).
+ */
+
+"use strict";
+
+const { createDocumentAdapter, parseTime, SNAPSHOT_SCHEMA_VERSION } = require("../_document-base");
+
+const NAME = "doc-wps";
+const VERSION = "0.1.0";
+
+// Best-effort WPS cloud-drive file list. Overridable via opts.listUrl.
+const WPS_LIST_URL = "https://drive.wps.cn/api/v5/groups/special/files";
+
+// WPS doc-type codes/names → normalized docType.
+function mapWpsType(d) {
+  const t = String(d.fname || d.name || "").toLowerCase();
+  if (d.ftype && typeof d.ftype === "string") return d.ftype;
+  if (/\.(xlsx?|et|csv)$/.test(t)) return "sheet";
+  if (/\.(pptx?|dps)$/.test(t)) return "slide";
+  if (/\.pdf$/.test(t)) return "pdf";
+  if (/\.(docx?|wps)$/.test(t)) return "doc";
+  return "doc";
+}
+
+function extractDocs(resp) {
+  if (!resp || typeof resp !== "object") return [];
+  if (Array.isArray(resp.files)) return resp.files;
+  if (Array.isArray(resp.data)) return resp.data;
+  if (resp.data && Array.isArray(resp.data.files)) return resp.data.files;
+  if (Array.isArray(resp.list)) return resp.list;
+  return [];
+}
+
+function mapDoc(d) {
+  if (!d || typeof d !== "object") return null;
+  const docId = d.id || d.fileid || d.file_id || d.fid;
+  if (!docId) return null;
+  return {
+    docId: String(docId),
+    title: d.fname || d.name || d.title || "(无标题)",
+    docType: mapWpsType(d),
+    url:
+      d.url ||
+      (d.id ? `https://www.kdocs.cn/p/${d.id}` : null),
+    createdMs: parseTime(d.ctime || d.create_time || d.created),
+    updatedMs: parseTime(d.mtime || d.modify_time || d.updated || d.utime),
+    extra: {
+      size: d.fsize || d.size || null,
+      groupId: d.group_id || d.groupid || null,
+    },
+  };
+}
+
+const WpsDocAdapter = createDocumentAdapter({
+  NAME,
+  VERSION,
+  platform: "wps",
+  defaultListUrl: WPS_LIST_URL,
+  extractDocs,
+  mapDoc,
+});
+
+module.exports = {
+  WpsDocAdapter,
+  extractDocs,
+  mapDoc,
+  NAME,
+  VERSION,
+  SNAPSHOT_SCHEMA_VERSION,
+};