From 675644189d80257a028d2bf3b5de95dfa0ed6106 Mon Sep 17 00:00:00 2001
From: Ethanfel <ethan.fel@ts-pc.fr>
Date: Tue, 7 Apr 2026 14:55:27 +0200
Subject: [PATCH] feat: add SelVA Dataset Browser node

Companion node for inspecting dataset.json entries by integer index.
Outputs video (.mp4), audio (.wav/.flac), features (.npz), frames dir,
mask dir, label, and max_index for constraining the index widget range.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 nodes/__init__.py              |  1 +
 nodes/selva_dataset_browser.py | 99 ++++++++++++++++++++++++++++++++++
 2 files changed, 100 insertions(+)
 create mode 100644 nodes/selva_dataset_browser.py

diff --git a/nodes/__init__.py b/nodes/__init__.py
index 4914aa2..f965e29 100644
--- a/nodes/__init__.py
+++ b/nodes/__init__.py
@@ -8,6 +8,7 @@ _NODES = {
     "SelvaLoraLoader":       (".selva_lora_loader",       "SelvaLoraLoader",       "SelVA LoRA Loader"),
     "SelvaLoraTrainer":      (".selva_lora_trainer",      "SelvaLoraTrainer",      "SelVA LoRA Trainer"),
     "SelvaLoraScheduler":    (".selva_lora_scheduler",    "SelvaLoraScheduler",    "SelVA LoRA Scheduler"),
+    "SelvaDatasetBrowser":   (".selva_dataset_browser",   "SelvaDatasetBrowser",   "SelVA Dataset Browser"),
 }
 
 for key, (module_path, class_name, display_name) in _NODES.items():
diff --git a/nodes/selva_dataset_browser.py b/nodes/selva_dataset_browser.py
new file mode 100644
index 0000000..33c502c
--- /dev/null
+++ b/nodes/selva_dataset_browser.py
@@ -0,0 +1,99 @@
+import json
+from pathlib import Path
+
+import folder_paths
+
+from .utils import SELVA_CATEGORY
+
+
+class SelvaDatasetBrowser:
+    """Browse a dataset.json file entry by entry using an integer index.
+
+    Each entry in the JSON is expected to have:
+      - "path"  : base path (no extension) — directory that holds frame images
+      - "label" : text description of the clip
+
+    Derived outputs:
+      - video_path  : path + ".mp4"
+      - audio_path  : path + ".wav"
+      - frames_dir  : path  (the directory itself, for image-sequence loaders)
+      - label       : entry["label"]
+      - count       : total number of entries in the file
+    """
+
+    @classmethod
+    def INPUT_TYPES(cls):
+        return {
+            "required": {
+                "dataset_json": ("STRING", {
+                    "default": "",
+                    "tooltip": "Absolute or ComfyUI-relative path to a dataset.json file.",
+                }),
+                "index": ("INT", {
+                    "default": 0,
+                    "min": 0,
+                    "max": 9999,
+                    "step": 1,
+                    "tooltip": "Zero-based index of the entry to inspect.",
+                }),
+            },
+        }
+
+    RETURN_TYPES  = ("STRING", "STRING", "STRING", "STRING", "STRING", "STRING", "STRING", "INT")
+    RETURN_NAMES  = ("video_path", "audio_wav", "audio_flac", "features_path", "frames_dir", "mask_dir", "label", "max_index")
+    OUTPUT_TOOLTIPS = (
+        "path + '.mp4'",
+        "path + '.wav'",
+        "path + '.flac'",
+        "path + '.npz'  (pre-extracted SelVA features)",
+        "path  (image-sequence directory)",
+        "path + '_mask'  (mask image-sequence directory)",
+        "Text label for this clip",
+        "count - 1 — wire to a primitive INT's max to constrain the index widget",
+    )
+    FUNCTION  = "browse"
+    CATEGORY  = SELVA_CATEGORY
+    DESCRIPTION = (
+        "Reads a dataset.json produced by the SelVA dataset preparation pipeline "
+        "and exposes one entry at a time via an integer index. "
+        "Outputs the video path, audio path, frames directory, label, and total entry count."
+    )
+
+    # Re-read the file every call so edits are picked up without restarting ComfyUI.
+    IS_CHANGED = classmethod(lambda cls, **_: float("nan"))
+
+    def browse(self, dataset_json: str, index: int):
+        p = Path(dataset_json.strip())
+        if not p.is_absolute():
+            p = Path(folder_paths.base_path) / p
+        if not p.exists():
+            raise FileNotFoundError(f"[SelVA Dataset Browser] File not found: {p}")
+
+        with p.open("r", encoding="utf-8") as f:
+            data = json.load(f)
+
+        if not isinstance(data, list) or len(data) == 0:
+            raise ValueError(f"[SelVA Dataset Browser] Expected a non-empty JSON array in {p}")
+
+        count = len(data)
+        index = max(0, min(index, count - 1))   # clamp silently
+        entry = data[index]
+
+        base  = entry["path"]
+        label = entry.get("label", "")
+
+        print(
+            f"[SelVA Dataset Browser] {index + 1}/{count}  label='{label}'  base={base}",
+            flush=True,
+        )
+
+        return (
+            base + ".mp4",
+            base + ".wav",
+            base + ".flac",
+            base + ".npz",
+            base,
+            base + "_mask",
+            label,
+            count - 1,
+        )