file-identifier 0.1.0__tar.gz

file_identifier-0.1.0/LICENSE

@@ -0,0 +1,6 @@
+MIT License
+
+Copyright (c) 2026 Priyanshi Dwivedi
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software...

file_identifier-0.1.0/PKG-INFO

@@ -0,0 +1,12 @@
+Metadata-Version: 2.4
+Name: file-identifier
+Version: 0.1.0
+Summary: File Type Identifier using Magic Numbers
+Author-email: Author <author@example.com>
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file

file_identifier-0.1.0/README

@@ -0,0 +1,49 @@
+# 🔍 File Identifier
+
+Identify file types using **magic numbers (file signatures)** instead of file extensions.
+
+Works even if files have incorrect or fake extensions (e.g., `.pdf.exe`).
+
+---
+
+## 🚀 Installation
+
+```bash
+pip install file-identifier
+```
+
+---
+
+## 🛠 Usage
+
+```bash
+file-identifier <file_path>
+```
+
+### Example
+
+```bash
+file-identifier "C:\Users\YourName\Downloads\file.zip"
+```
+
+---
+
+## 📊 Output
+
+* File type
+* Likely extension
+* File size
+* Confidence level
+* Hex header
+
+---
+
+## 🧠 How it works
+
+Reads the first bytes of a file and matches them with known **magic signatures**.
+
+---
+
+## 📜 License
+
+MIT

file_identifier-0.1.0/file_identifier/__init__.py

@@ -0,0 +1,9 @@
+"""
+File Type Identifier using Magic Numbers
+Reads file headers (magic bytes) to identify file types - no extensions needed.
+"""
+
+from .core import identify_file, identify_many, read_header, print_report
+
+__version__ = "0.1.0"
+__all__ = ["identify_file", "identify_many", "read_header", "print_report"]

file_identifier-0.1.0/file_identifier/cli.py

@@ -0,0 +1,41 @@
+import sys
+import os
+import tempfile
+import argparse
+from .core import identify_file, print_report
+
+def main():
+    parser = argparse.ArgumentParser(description="File Type Identifier using Magic Numbers.")
+    parser.add_argument("files", nargs="*", help="List of files to identify")
+    args = parser.parse_args()
+
+    # If files are provided via CLI arguments
+    if args.files:
+        for fp in args.files:
+            print_report(identify_file(fp))
+    else:
+        # Default behavior with no arguments: Self-demo
+        print("\n🔍 File Type Identifier — Demo Mode")
+        print("Creating sample files with known magic bytes...\n")
+
+        samples = {
+            "sample.jpg":  b'\xff\xd8\xff\xe0\x00\x10JFIF',
+            "sample.png":  b'\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR',
+            "sample.pdf":  b'%PDF-1.4\n%\xe2\xe3\xcf\xd3',
+            "sample.gz":   b'\x1f\x8b\x08\x00\x00\x00\x00\x00',
+            "sample.exe":  b'MZ\x90\x00\x03\x00\x00\x00',
+            "sample.zip":  b'PK\x03\x04\x14\x00\x00\x00',
+            "sample.mp3":  b'ID3\x03\x00\x00\x00\x00',
+            "sample.txt":  b'Hello, world!\nThis is plain text.\n',
+            "sample.bin":  bytes(range(16)),
+        }
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            for name, data in samples.items():
+                fp = os.path.join(tmpdir, name)
+                with open(fp, 'wb') as f:
+                    f.write(data)
+                print_report(identify_file(fp))
+
+if __name__ == "__main__":
+    main()

file_identifier-0.1.0/file_identifier/core.py

@@ -0,0 +1,144 @@
+"""
+File Type Identifier using Magic Numbers
+Reads file headers (magic bytes) to identify file types - no extensions needed.
+"""
+
+import struct
+from pathlib import Path
+
+MAGIC_SIGNATURES = [
+    # Images
+    (b'\xff\xd8\xff',                       "JPEG Image",           ".jpg"),
+    (b'\x89PNG\r\n\x1a\n',                  "PNG Image",            ".png"),
+    (b'GIF87a',                             "GIF Image (87a)",      ".gif"),
+    (b'GIF89a',                             "GIF Image (89a)",      ".gif"),
+    (b'BM',                                 "BMP Image",            ".bmp"),
+    (b'RIFF',                               "RIFF (WAV/AVI/WebP)",  ".riff"),
+    (b'\x00\x00\x01\x00',                   "ICO Icon",             ".ico"),
+    (b'\x49\x49\x2a\x00',                   "TIFF (little-endian)", ".tif"),
+    (b'\x4d\x4d\x00\x2a',                   "TIFF (big-endian)",    ".tif"),
+
+    # Documents
+    (b'%PDF',                               "PDF Document",         ".pdf"),
+    (b'\xd0\xcf\x11\xe0\xa1\xb1\x1a\xe1',  "MS Office (old)",      ".doc/.xls/.ppt"),
+    (b'PK\x03\x04',                         "ZIP / Office Open XML",".zip/.docx/.xlsx"),
+
+    # Audio / Video
+    (b'ID3',                                "MP3 Audio (ID3 tag)",  ".mp3"),
+    (b'\xff\xfb',                           "MP3 Audio",            ".mp3"),
+    (b'\xff\xf3',                           "MP3 Audio",            ".mp3"),
+    (b'fLaC',                               "FLAC Audio",           ".flac"),
+    (b'OggS',                               "OGG Container",        ".ogg"),
+    (b'\x1aE\xdf\xa3',                      "Matroska/WebM",        ".mkv/.webm"),
+    (b'\x00\x00\x00\x18ftypmp4',            "MP4 Video",            ".mp4"),
+    (b'\x00\x00\x00\x20ftyp',              "MP4 Video",            ".mp4"),
+
+    # Archives
+    (b'\x1f\x8b',                           "GZIP Archive",         ".gz"),
+    (b'BZh',                                "BZIP2 Archive",        ".bz2"),
+    (b'\xfd7zXZ\x00',                       "XZ Archive",           ".xz"),
+    (b'7z\xbc\xaf\x27\x1c',                "7-Zip Archive",        ".7z"),
+    (b'Rar!\x1a\x07\x00',                  "RAR Archive (v4)",     ".rar"),
+    (b'Rar!\x1a\x07\x01\x00',             "RAR Archive (v5)",     ".rar"),
+
+    # Executables / Binary
+    (b'MZ',                                 "Windows Executable",   ".exe/.dll"),
+    (b'\x7fELF',                            "ELF Executable (Linux)",".elf"),
+    (b'\xca\xfe\xba\xbe',                   "Java Class / Mach-O",  ".class"),
+    (b'\xfe\xed\xfa\xce',                   "Mach-O 32-bit",        ".macho"),
+    (b'\xfe\xed\xfa\xcf',                   "Mach-O 64-bit",        ".macho"),
+
+    # Text / Code (heuristic, checked last)
+    (b'#!/',                                "Shell Script",         ".sh"),
+    (b'<?xml',                              "XML Document",         ".xml"),
+    (b'<?php',                              "PHP Script",           ".php"),
+    (b'<html',                              "HTML Document",        ".html"),
+    (b'<HTML',                              "HTML Document",        ".html"),
+    (b'{\n',                                "JSON (likely)",        ".json"),
+    (b'{\r\n',                              "JSON (likely)",        ".json"),
+]
+
+MAX_HEADER = 32  # bytes to read from the file
+
+
+def read_header(filepath: str) -> bytes:
+    """Read the first MAX_HEADER bytes of a file."""
+    with open(filepath, 'rb') as f:
+        return f.read(MAX_HEADER)
+
+
+def identify_file(filepath: str) -> dict:
+    """
+    Identify a file's type by reading its magic bytes.
+
+    Returns a dict with:
+        path        - original filepath
+        hex_header  - hex dump of the first bytes
+        file_type   - human-readable type name
+        extension   - likely extension(s)
+        matched_sig - the raw signature that matched (hex)
+        confidence  - 'high' or 'low'
+    """
+    path = Path(filepath)
+    result = {
+        "path":        str(path),
+        "size_bytes":  path.stat().st_size if path.exists() else 0,
+        "file_type":   "Unknown",
+        "extension":   "?",
+        "hex_header":  "",
+        "matched_sig": "",
+        "confidence":  "low",
+    }
+
+    if not path.exists():
+        result["file_type"] = "File not found"
+        return result
+
+    if path.stat().st_size == 0:
+        result["file_type"] = "Empty file"
+        return result
+
+    header = read_header(filepath)
+    result["hex_header"] = " ".join(f"{b:02X}" for b in header)
+
+    for sig, name, ext in MAGIC_SIGNATURES:
+        if header[:len(sig)] == sig:
+            result["file_type"]   = name
+            result["extension"]   = ext
+            result["matched_sig"] = sig.hex(" ")
+            result["confidence"]  = "high" if len(sig) >= 4 else "medium"
+            return result
+
+    # Fallback: try to detect plain text (reject if null bytes present)
+    try:
+        decoded = header.decode('utf-8')
+        if '\x00' in decoded:
+            raise UnicodeDecodeError('utf-8', b'', 0, 1, 'null byte')
+        result["file_type"]  = "Plain Text (UTF-8)"
+        result["extension"]  = ".txt"
+        result["confidence"] = "medium"
+    except UnicodeDecodeError:
+        result["file_type"]  = "Unknown Binary"
+        result["extension"]  = ".bin"
+        result["confidence"] = "low"
+
+    return result
+
+
+def identify_many(filepaths: list[str]) -> list[dict]:
+    """Identify multiple files at once."""
+    return [identify_file(fp) for fp in filepaths]
+
+
+def print_report(result: dict) -> None:
+    """Pretty-print a single file identification result."""
+    print(f"\n{'='*55}")
+    print(f"  File    : {result['path']}")
+    print(f"  Type    : {result['file_type']}")
+    print(f"  Ext     : {result['extension']}")
+    print(f"  Size    : {result['size_bytes']:,} bytes")
+    print(f"  Confidence : {result['confidence']}")
+    print(f"  Header  : {result['hex_header']}")
+    if result['matched_sig']:
+        print(f"  Matched : {result['matched_sig']}")
+    print(f"{'='*55}")

file_identifier-0.1.0/file_identifier.egg-info/PKG-INFO

@@ -0,0 +1,12 @@
+Metadata-Version: 2.4
+Name: file-identifier
+Version: 0.1.0
+Summary: File Type Identifier using Magic Numbers
+Author-email: Author <author@example.com>
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Dynamic: license-file

file_identifier-0.1.0/file_identifier.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+LICENSE
+README
+pyproject.toml
+file_identifier/__init__.py
+file_identifier/cli.py
+file_identifier/core.py
+file_identifier.egg-info/PKG-INFO
+file_identifier.egg-info/SOURCES.txt
+file_identifier.egg-info/dependency_links.txt
+file_identifier.egg-info/entry_points.txt
+file_identifier.egg-info/top_level.txt

file_identifier-0.1.0/file_identifier.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

file_identifier-0.1.0/file_identifier.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+file-identifier = file_identifier.cli:main

file_identifier-0.1.0/file_identifier.egg-info/top_level.txt

@@ -0,0 +1 @@
+file_identifier

file_identifier-0.1.0/pyproject.toml

@@ -0,0 +1,23 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "file-identifier"
+version = "0.1.0"
+description = "File Type Identifier using Magic Numbers"
+readme = "README.md"
+requires-python = ">=3.8"
+
+authors = [
+  { name="Author", email="author@example.com" }
+]
+
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+
+[project.scripts]
+file-identifier = "file_identifier.cli:main"

file_identifier-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+