datagrok-tools 6.2.5 → 6.2.6

package/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Datagrok-tools changelog
 
+## 6.2.6 (2026-05-26)
+
+* `grok s tables upload` — accepts `.d42` binary blobs in addition to `.csv`. Content-Type is auto-detected from the file extension (`application/octet-stream` for d42, `text/csv` otherwise); server content-negotiates and persists either form against the same `/public/v1/tables/{name}` endpoint.
+
 ## 6.2.5 (2026-05-21)
 
 * `grok report read` — renamed `--extract-actions` to `--extract-client-log`; sidecar is now `<stem>_client_log.json`. The old flag is no longer accepted.

package/GROK_S.md

@@ -27,7 +27,7 @@ browser or a logged-in session.
 | Run a registered function                                   | `grok s functions run 'Pkg:fn(arg1,arg2)'`             |
 | List functions with rich filters                            | `grok s functions list --type script --language python --package Chem` |
 | List / browse files in a file share                         | `grok s files list "System:AppData" -r`                |
-| Upload / download a table (CSV)                             | `grok s tables upload <name> file.csv` / `tables download <name> -O out.csv` |
+| Upload / download a table (CSV or d42)                      | `grok s tables upload <name> file.csv\|file.d42` / `tables download <name> -O out.csv` |
 | Check whether a package is deployed                         | `grok s packages list --filter "MyPlugin"`             |
 | Hit any undocumented endpoint                               | `grok s raw GET /api/users/current`                    |
 | Check server + per-module health                            | `grok s healthcheck [--module <name>]`                 |
@@ -205,21 +205,26 @@ the `source` before sending).
 
 ## Tables
 
-CSV-level table I/O — the shell counterpart to Python's `grok.tables.upload/download`.
+Table I/O — the shell counterpart to Python's `grok.tables.upload/download`.
 Unlike `files put`, this registers a proper Datagrok table entity (returns `{ID, ...}`).
 
 ```bash
 grok s tables upload MyTable ./data.csv                         # CSV → table
+grok s tables upload MyTable ./data.d42                         # d42 binary → table
 grok s tables upload MyTable ./data.csv --output json           # get ID and markup back
 grok s tables download MyTable                                  # CSV to stdout (pipe-friendly)
 grok s tables download MyTable -O ./data.csv                    # CSV to a local file
 grok s tables download <uuid>                                   # UUID or namespace:name both work
 ```
 
-Upload streams raw bytes with `Content-Type: text/csv` so it handles large tables
-without loading the whole file into a JSON envelope. `-O` / `--output-file` avoids
-colliding with the format flag (`--output table|json|csv|quiet`), which still controls
-how the upload result is printed.
+Upload streams raw bytes — `Content-Type: text/csv` for `.csv` and
+`application/octet-stream` for `.d42` (auto-detected from the file extension). Both
+formats handle large tables without loading the whole file into a JSON envelope.
+`-O` / `--output-file` avoids colliding with the format flag (`--output
+table|json|csv|quiet`), which still controls how the upload result is printed.
+
+Download is CSV-only — the server reads the stored d42 blob and converts. If you
+need the raw d42 bytes, hit `/tables/data/<id>` directly via `grok s raw`.
 
 ## Server health
 

package/bin/commands/server.js

@@ -8,6 +8,7 @@ exports.parseFuncCall = parseFuncCall;
 exports.resolveManifestSources = resolveManifestSources;
 exports.server = server;
 var fs = _interopRequireWildcard(require("fs"));
+var path = _interopRequireWildcard(require("path"));
 var _nodeDapi = require("../utils/node-dapi");
 var _serverClient = require("../utils/server-client");
 var _serverOutput = require("../utils/server-output");
@@ -169,14 +170,15 @@ async function handleTablesDownload(dapi, rest, argv, output) {
 async function handleTablesUpload(dapi, rest, output) {
   const [name, localPath] = rest;
   if (!name || !localPath) {
-    (0, _serverOutput.printError)(new Error('Usage: grok s tables upload <name> <file.csv>'));
+    (0, _serverOutput.printError)(new Error('Usage: grok s tables upload <name> <file.csv|file.d42>'));
     return false;
   }
   if (!fs.existsSync(localPath)) {
     (0, _serverOutput.printError)(new Error(`Local file not found: ${localPath}`));
     return false;
   }
-  const result = await dapi.tables.upload(name, localPath);
+  const ct = path.extname(localPath).toLowerCase() === '.d42' ? 'application/octet-stream' : 'text/csv';
+  const result = await dapi.tables.upload(name, localPath, ct);
   if (output === 'quiet') console.log(result?.ID ?? result?.id ?? '');else (0, _serverOutput.printOutput)(result, output);
   return true;
 }
@@ -611,7 +613,7 @@ Special commands:
   grok s groups list-memberships <group> [--admin]    List parent groups
   grok s users block <id-or-login>                    Block a user from the platform
   grok s users unblock <id-or-login>                  Unblock a previously blocked user
-  grok s tables upload <name> <file.csv>              Upload a CSV as a Datagrok table
+  grok s tables upload <name> <file.csv|file.d42>     Upload a CSV or d42 binary as a Datagrok table
   grok s tables download <name-or-id> [-O <file>]     Download a table as CSV (stdout by default)
   grok s batch <entity> <verb> arg1 [arg2 ...]        Batch operation (one round-trip)
   grok s batch <entity> <verb> --json params.json     Batch from JSON array

package/bin/utils/node-dapi.js

@@ -502,12 +502,16 @@ class NodeTablesDataSource {
     return result;
   }
 
-  /** POST /public/v1/tables/{name} with raw CSV bytes. Returns `{ID, Grok name, Markup, URL}`. */
-  async upload(name, localPath) {
+  /**
+   * POST /public/v1/tables/{name} with raw bytes. Returns `{ID, Grok name, Markup, URL}`.
+   * Defaults to `text/csv`; pass `application/octet-stream` to upload a `.d42`
+   * binary blob — the server content-negotiates on the header and persists either form.
+   */
+  async upload(name, localPath, contentType = 'text/csv') {
     const fs = require('fs');
     const bytes = fs.readFileSync(localPath);
     const seg = encodeURIComponent(name.replace(/:/g, '.'));
-    return this.client.putBytes(`/public/v1/tables/${seg}`, bytes, 'text/csv');
+    return this.client.putBytes(`/public/v1/tables/${seg}`, bytes, contentType);
   }
 }
 exports.NodeTablesDataSource = NodeTablesDataSource;

package/download-demo-datasets.R

@@ -0,0 +1,67 @@
+# tools/download-demo-datasets.R
+#
+# Выгружает три демо-датасета для ANOVA UI:
+#   - InsectSprays (R datasets package) → CSV
+#   - ToothGrowth  (R datasets package) → CSV
+#   - SiRstv       (NIST StRD)          → CSV
+#
+# Запуск из корня репозитория:
+#   Rscript tools/download-demo-datasets.R
+#
+# Результат сохраняется в packages/EDA/demo-data/.
+
+OUT_DIR <- "packages/EDA/demo-data"
+dir.create(OUT_DIR, showWarnings = FALSE, recursive = TRUE)
+
+# ─── 1. InsectSprays ──────────────────────────────────────────────────
+data(InsectSprays)
+write.csv(InsectSprays,
+          file.path(OUT_DIR, "insect-sprays.csv"),
+          row.names = FALSE,
+          fileEncoding = "UTF-8")
+cat("Wrote insect-sprays.csv (", nrow(InsectSprays), "rows )\n")
+
+# ─── 2. ToothGrowth ───────────────────────────────────────────────────
+data(ToothGrowth)
+write.csv(ToothGrowth,
+          file.path(OUT_DIR, "tooth-growth.csv"),
+          row.names = FALSE,
+          fileEncoding = "UTF-8")
+cat("Wrote tooth-growth.csv (", nrow(ToothGrowth), "rows )\n")
+
+# ─── 3. SiRstv (NIST StRD) ────────────────────────────────────────────
+# NIST .dat файл имеет большой текстовый header; данные идут после
+# строки "Data:  Instrument   Resistance" (заголовок встроен в маркер).
+nist_url <- "https://www.itl.nist.gov/div898/strd/anova/SiRstv.dat"
+# На Windows libcurl падает на NIST SSL (CRYPT_E_NO_REVOCATION_CHECK).
+# wininet использует системный HTTP-стек и работает; на других ОС — стандартный путь.
+read_nist <- function(u) {
+  if (.Platform$OS.type == "windows") {
+    tmp <- tempfile()
+    suppressWarnings(download.file(u, tmp, quiet = TRUE, method = "wininet"))
+    readLines(tmp)
+  } else {
+    readLines(url(u))
+  }
+}
+lines <- read_nist(nist_url)
+data_start <- grep("^\\s*Data:\\s+Instrument", lines)
+if (length(data_start) != 1)
+  stop("Cannot locate 'Data: Instrument' marker in SiRstv.dat")
+
+# Пропустить только строку "Data:..." — следующая уже содержит данные.
+data_lines <- lines[(data_start + 1):length(lines)]
+data_lines <- data_lines[nzchar(trimws(data_lines))]
+
+# В каждой строке два числа через whitespace: Instrument Resistance
+sirstv <- read.table(text = data_lines,
+                     col.names = c("Instrument", "Resistance"))
+sirstv$Instrument <- as.integer(sirstv$Instrument)
+
+write.csv(sirstv,
+          file.path(OUT_DIR, "silicon-resistivity.csv"),
+          row.names = FALSE,
+          fileEncoding = "UTF-8")
+cat("Wrote silicon-resistivity.csv (", nrow(sirstv), "rows )\n")
+
+cat("\nAll three demo datasets written to", OUT_DIR, "\n")

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "datagrok-tools",
-  "version": "6.2.5",
+  "version": "6.2.6",
   "description": "Utility to upload and publish packages to Datagrok",
   "homepage": "https://github.com/datagrok-ai/public/tree/master/tools#readme",
   "dependencies": {