{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"vscode-thecalendre-data-file-viewer","slug":"data-file-viewer","name":"Data File Viewer","type":"extension","url":"https://marketplace.visualstudio.com/items?itemName=thecalendre.data-file-viewer","page_url":"https://unfragile.ai/data-file-viewer","categories":["data-analysis"],"tags":["arrow","avro","data science","data visualization","file viewer","hdf5","machine learning","matlab","ml","netcdf","numpy","parquet","pickle"],"pricing":{"model":"freemium","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"vscode-thecalendre-data-file-viewer__cap_0","uri":"capability://data.processing.analysis.multi.format.binary.data.deserialization.and.in.editor.preview","name":"multi-format binary data deserialization and in-editor preview","description":"Automatically intercepts file opens for 13+ binary data formats (.pkl, .h5, .parquet, .feather, .joblib, .npy, .npz, .msgpack, .arrow, .avro, .nc, .mat) and deserializes them into a navigable tree structure within VS Code's custom viewer panel. Uses format-specific parsers (Python pickle, HDF5 libraries, Apache Arrow, etc.) running in an isolated Python environment to convert binary data into JSON-serializable structures for display, replacing the default hex dump view.","intents":["I want to quickly inspect the contents of a pickle or HDF5 file without writing a Python script","I need to explore nested data structures in parquet or arrow files directly from my editor","I want to verify that a joblib model file contains the expected data before loading it in code","I need to browse NumPy arrays and understand their shape and contents without running Python"],"best_for":["Data scientists and ML engineers working in VS Code who frequently inspect serialized model files and datasets","Python developers prototyping ML pipelines who need quick data validation without context switching","Teams migrating data workflows to VS Code and needing native binary file inspection"],"limitations":["Very large files (>1GB) experience significant load time delays; no streaming or chunked loading implemented","Custom pickle objects that don't serialize to JSON will fail to display; only standard Python types are guaranteed to work","Read-only access — cannot modify or re-serialize data back to the original format through the viewer","Pickle and joblib deserialization executes arbitrary Python code during parsing, creating code execution risk if files are from untrusted sources","No sandboxing of Python code execution during deserialization — relies entirely on user trust"],"requires":["Visual Studio Code 1.50+ or Cursor editor","Python 3.7+ installed on system PATH","Supported binary file format (.pkl, .h5, .parquet, .feather, .joblib, .npy, .npz, .msgpack, .arrow, .avro, .nc, .mat)","~2-3 minutes for initial isolated Python environment setup on first use"],"input_types":["binary file (.pkl, .h5, .parquet, .feather, .joblib, .npy, .npz, .msgpack, .arrow, .avro, .nc, .mat)"],"output_types":["JSON tree structure","formatted text display with type annotations","copyable JSON string to clipboard"],"categories":["data-processing-analysis","file-viewer"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-thecalendre-data-file-viewer__cap_1","uri":"capability://data.processing.analysis.hierarchical.json.tree.navigation.with.collapse.expand.and.syntax.highlighting","name":"hierarchical json tree navigation with collapse/expand and syntax highlighting","description":"Renders deserialized binary data as an interactive, collapsible JSON tree structure within the editor panel, allowing users to expand and collapse nested objects, arrays, and data structures. Implements syntax highlighting to visually distinguish data types (strings, numbers, booleans, null, objects) and provides a simplified vs. detailed view toggle to reduce cognitive load when exploring large nested structures. Tree navigation is stateful — collapsed/expanded state persists during the current viewing session.","intents":["I want to drill down into a deeply nested data structure without seeing all levels at once","I need to quickly identify the type of each field in a complex object (string vs number vs array)","I want to toggle between a high-level summary view and a detailed view of the same data"],"best_for":["Data scientists exploring unfamiliar dataset schemas before writing processing code","ML engineers validating model checkpoint structures (weights, metadata, hyperparameters)","Developers debugging data pipeline outputs by inspecting intermediate serialized states"],"limitations":["No search or filtering within the tree — must manually navigate to find specific fields","No sorting or reordering of keys — display order is determined by the original data structure","Tree state is not persisted across file close/reopen — must re-expand sections on next view","Performance degrades with very deep nesting (>50 levels) due to DOM rendering overhead"],"requires":["Visual Studio Code 1.50+","Successfully deserialized binary file (output from multi-format deserialization capability)"],"input_types":["JSON tree structure from deserialized binary data"],"output_types":["interactive HTML tree view","syntax-highlighted text representation"],"categories":["data-processing-analysis","visualization"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-thecalendre-data-file-viewer__cap_2","uri":"capability://data.processing.analysis.clipboard.export.of.json.representation","name":"clipboard export of json representation","description":"Provides a one-click mechanism to copy the entire deserialized data structure (or selected subtree) as a JSON string to the system clipboard. This enables users to paste the data into other tools (Python REPL, text editors, documentation, etc.) without manually re-serializing or writing export code. The export respects the current view state (simplified vs. detailed) and includes all type information.","intents":["I want to copy a data structure from a .pkl file and paste it into a Python script for testing","I need to document the schema of a model file by copying its JSON representation into a markdown file","I want to share a snapshot of a dataset's structure with a teammate via Slack or email"],"best_for":["Data scientists who frequently move between inspection and coding workflows","Teams documenting data schemas and model structures","Developers creating test fixtures from real serialized data"],"limitations":["Export is JSON-only — cannot export back to original binary format (.pkl, .h5, etc.)","Large data structures (>10MB JSON) may cause clipboard performance issues or system memory pressure","No selective export of subtrees — must copy entire structure or manually edit after paste","Formatting is minified JSON by default; no pretty-print option documented"],"requires":["Visual Studio Code 1.50+","Successfully deserialized and displayed binary file","System clipboard access (standard for VS Code extensions)"],"input_types":["JSON tree structure from deserialized binary data"],"output_types":["JSON string (minified or formatted) in system clipboard"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-thecalendre-data-file-viewer__cap_3","uri":"capability://automation.workflow.isolated.python.environment.management.with.zero.configuration.setup","name":"isolated python environment management with zero-configuration setup","description":"Automatically creates and manages a dedicated Python virtual environment for the extension on first use, installing all required binary format parsers (pickle, h5py, pandas, pyarrow, scipy, etc.) without affecting the user's global Python installation or project dependencies. The environment is created once, persists across VS Code sessions, and is completely removed if the extension is uninstalled. Setup is fully automated and requires no user configuration — users are not exposed to pip commands, requirements files, or dependency management.","intents":["I want to use this extension without worrying about breaking my project's Python dependencies","I need the extension to work immediately after installation without manual setup steps","I want to ensure the extension uses a clean, isolated Python environment"],"best_for":["Data scientists and ML engineers who want zero-friction tool installation","Teams with strict dependency management policies who need isolated tool environments","Users with complex project environments who cannot afford dependency conflicts"],"limitations":["Initial setup takes 2-3 minutes on first use while dependencies are downloaded and installed","Isolated environment adds ~50-100MB disk space overhead per installation","No user control over which versions of parsers are installed — versions are pinned by extension maintainer","If Python 3.7+ is not on system PATH, extension will fail silently with unclear error messaging","Environment recreation is required if Python installation is moved or deleted"],"requires":["Python 3.7+ installed and accessible on system PATH","Visual Studio Code 1.50+","~100MB free disk space for isolated environment","Network access for initial pip dependency download (one-time)"],"input_types":["system Python installation"],"output_types":["isolated virtual environment with installed parsers"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-thecalendre-data-file-viewer__cap_4","uri":"capability://data.processing.analysis.format.auto.detection.and.routing.to.appropriate.parser","name":"format auto-detection and routing to appropriate parser","description":"Automatically detects the binary file format based on file extension and magic bytes (file header signatures) and routes the deserialization request to the appropriate format-specific parser. This enables seamless handling of 13+ different formats without requiring users to specify format type or choose a parser manually. Detection happens transparently when a file is opened, and unsupported formats are silently ignored (file opens in default binary viewer).","intents":["I want to open any data science file and have it automatically display correctly without choosing a format","I need the extension to handle files with non-standard extensions or ambiguous formats","I want to work with multiple file formats in the same project without manual configuration"],"best_for":["Data science teams working with heterogeneous data formats across projects","Developers who want plug-and-play functionality without format configuration","Users who frequently switch between different serialization formats"],"limitations":["Detection relies on file extension as primary signal — files with wrong extensions may fail to parse","Magic byte detection is not documented — unclear which formats use header-based detection vs. extension-only","No user override mechanism — if auto-detection fails, no way to manually specify format","Ambiguous formats (e.g., .h5 could be HDF5 or custom binary) may route to wrong parser","Unsupported formats silently fall back to default binary viewer with no user notification"],"requires":["Visual Studio Code 1.50+","File with recognized extension (.pkl, .h5, .parquet, .feather, .joblib, .npy, .npz, .msgpack, .arrow, .avro, .nc, .mat)"],"input_types":["binary file with recognized extension"],"output_types":["routed to appropriate format-specific parser"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"vscode-thecalendre-data-file-viewer__cap_5","uri":"capability://data.processing.analysis.pickle.and.joblib.code.execution.with.security.warning","name":"pickle and joblib code execution with security warning","description":"Enables deserialization of Python pickle (.pkl) and joblib (.joblib) files, which inherently requires executing arbitrary Python code embedded in the serialized data during the unpickling process. The extension displays a security warning to users before opening pickle files, informing them that opening untrusted pickle files can execute malicious code. However, there is no sandboxing or code execution prevention — the warning is purely informational, and users must manually verify file trustworthiness.","intents":["I want to inspect a pickle file that I created or received from a trusted source","I need to verify that a joblib model file contains the expected structure before loading it in code","I want to understand what code will be executed when I unpickle a file"],"best_for":["Data scientists working with their own pickle files or files from trusted team members","ML engineers validating model checkpoints from known sources","Developers who understand pickle security implications and can assess file trustworthiness"],"limitations":["No sandboxing — arbitrary Python code in pickle files executes with full user permissions","No code inspection or static analysis — users cannot see what code will execute before opening the file","Security warning is informational only — does not prevent file opening or code execution","No option to deserialize pickle files in a restricted/safe mode","Joblib files have identical security properties to pickle but may not be as widely understood as a security risk","No audit logging of which pickle files were opened or what code was executed"],"requires":["Visual Studio Code 1.50+","Python 3.7+ with pickle module (standard library)","User understanding of pickle security risks","Trust in the source of the pickle file"],"input_types":["pickle file (.pkl, .pickle)","joblib file (.joblib)"],"output_types":["deserialized Python object as JSON tree"],"categories":["data-processing-analysis","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":39,"verified":false,"data_access_risk":"high","permissions":["Visual Studio Code 1.50+ or Cursor editor","Python 3.7+ installed on system PATH","Supported binary file format (.pkl, .h5, .parquet, .feather, .joblib, .npy, .npz, .msgpack, .arrow, .avro, .nc, .mat)","~2-3 minutes for initial isolated Python environment setup on first use","Visual Studio Code 1.50+","Successfully deserialized binary file (output from multi-format deserialization capability)","Successfully deserialized and displayed binary file","System clipboard access (standard for VS Code extensions)","Python 3.7+ installed and accessible on system PATH","~100MB free disk space for isolated environment"],"failure_modes":["Very large files (>1GB) experience significant load time delays; no streaming or chunked loading implemented","Custom pickle objects that don't serialize to JSON will fail to display; only standard Python types are guaranteed to work","Read-only access — cannot modify or re-serialize data back to the original format through the viewer","Pickle and joblib deserialization executes arbitrary Python code during parsing, creating code execution risk if files are from untrusted sources","No sandboxing of Python code execution during deserialization — relies entirely on user trust","No search or filtering within the tree — must manually navigate to find specific fields","No sorting or reordering of keys — display order is determined by the original data structure","Tree state is not persisted across file close/reopen — must re-expand sections on next view","Performance degrades with very deep nesting (>50 levels) due to DOM rendering overhead","Export is JSON-only — cannot export back to original binary format (.pkl, .h5, etc.)","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.31,"quality":0.37,"ecosystem":0.35000000000000003,"match_graph":0.25,"freshness":0.9,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.15,"match_graph":0.23,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:34.803Z","last_scraped_at":"2026-05-03T15:20:36.253Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=data-file-viewer","compare_url":"https://unfragile.ai/compare?artifact=data-file-viewer"}},"signature":"s9HapFwtsj76SfByrgfMsxBqfT5amD8kteJyeJO7I9ZlF0rR6ITnk7ASKhm2aHbISYYX4UQUdbWQ6maYOAzaBw==","signedAt":"2026-06-16T07:54:49.365Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/data-file-viewer","artifact":"https://unfragile.ai/data-file-viewer","verify":"https://unfragile.ai/api/v1/verify?slug=data-file-viewer","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}