feat: Implement Crypto Algorithms (SHA256 and ChaCha20)

AUTHORS

@@ -11,4 +11,5 @@ Pratik Goyal <[email protected]>
 Jay Thorat <[email protected]>
 Rajveer Singh Bharadwaj <[email protected]>
 Kishan Ved <[email protected]>
-Arvinder Singh Dhoul <[email protected]>
+Arvinder Singh Dhoul <[email protected]>
+Parasa V Prajwal <[email protected]>

docs/source/pydatastructs/strings/algorithms.rst

@@ -1,4 +1,6 @@
 Algorithms
 ==========
 
-.. autofunction:: pydatastructs.find
+.. autofunction:: pydatastructs.find
+
+.. autoclass:: pydatastructs.Crypto

pydatastructs/strings/__init__.py

@@ -12,7 +12,8 @@
 __all__.extend(trie.__all__)
 
 from .algorithms import (
-    find
+    find,
+    Crypto
 )
 
 __all__.extend(algorithms.__all__)

pydatastructs/strings/algorithms.py

@@ -2,9 +2,11 @@
     DynamicOneDimensionalArray, OneDimensionalArray)
 from pydatastructs.utils.misc_util import (
     Backend, raise_if_backend_is_not_python)
+import struct
 
 __all__ = [
-    'find'
+    'find',
+    'Crypto'
 ]
 
 PRIME_NUMBER, MOD = 257, 1000000007
@@ -245,3 +247,188 @@ def _z_function(text, query):
             positions.append(pos)
 
     return positions
+
+class Crypto:
+
+    @staticmethod
+    def _right_rotate(value, shift, size=32):
+        return (value >> shift) | (value << (size - shift)) & (2**size - 1)
+
+    @staticmethod
+    def sha256_encrypt(text) -> str:
+        """
+        Finds the SHA256 ciphertext of the given plaintext
+
+        Parameters
+        ==========
+
+        text: str
+            The string on which SHA256 encryption is to be performed.
+
+        Returns
+        =======
+
+        text: str
+            The SHA256 encoded ciphertext
+
+        Examples
+        ========
+
+        >>> from pydatastructs import Crypto
+        >>> text = "PyDataStructs"
+        >>> ciphertext = Crypto.sha256_encrypt(text)
+        >>> print(ciphertext)
+        777a305fe4f1cfc7ce270891ec50651331e2ab6d09312b906740a5ea413bd057
+
+        References
+        ==========
+
+        .. [1] https://en.wikipedia.org/wiki/SHA-2
+        .. [2] https://github.com/TheAlgorithms/Python/blob/master/hashes/sha256.py
+
+        """
+        # SHA-256 Constants
+        k = [
+            0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
+            0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, 0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
+            0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc, 0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
+            0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7, 0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
+            0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13, 0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
+            0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3, 0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
+            0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5, 0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
+            0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208, 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
+        ]
+
+        h = [
+            0x6a09e667, 0xbb67ae85, 0x3c6ef372, 0xa54ff53a,
+            0x510e527f, 0x9b05688c, 0x1f83d9ab, 0x5be0cd19
+        ]
+
+        message = bytearray(text, 'utf-8')
+        length = len(message) * 8
+        message.append(0x80)
+        while (len(message) * 8) % 512 != 448:
+            message.append(0)
+        message += struct.pack('>Q', length)
+
+        for i in range(0, len(message), 64):
+            chunk = message[i:i+64]
+            w = list(struct.unpack('>16L', chunk)) + [0] * 48
+            for j in range(16, 64):
+                s0 = (Crypto._right_rotate(w[j-15], 7) ^ Crypto._right_rotate(w[j-15], 18) ^ (w[j-15] >> 3))
+                s1 = (Crypto._right_rotate(w[j-2], 17) ^ Crypto._right_rotate(w[j-2], 19) ^ (w[j-2] >> 10))
+                w[j] = (w[j-16] + s0 + w[j-7] + s1) & 0xFFFFFFFF
+
+            a, b, c, d, e, f, g, h0 = h
+
+            for j in range(64):
+                S1 = Crypto._right_rotate(e, 6) ^ Crypto._right_rotate(e, 11) ^ Crypto._right_rotate(e, 25)
+                ch = (e & f) ^ (~e & g)
+                temp1 = (h0 + S1 + ch + k[j] + w[j]) & 0xFFFFFFFF
+                S0 = Crypto._right_rotate(a, 2) ^ Crypto._right_rotate(a, 13) ^ Crypto._right_rotate(a, 22)
+                maj = (a & b) ^ (a & c) ^ (b & c)
+                temp2 = (S0 + maj) & 0xFFFFFFFF
+
+                h0, g, f, e, d, c, b, a = (g, f, e, (d + temp1) & 0xFFFFFFFF, c, b, a, (temp1 + temp2) & 0xFFFFFFFF)
+
+            h = [(x + y) & 0xFFFFFFFF for x, y in zip(h, [a, b, c, d, e, f, g, h0])]
+
+        return ''.join(f'{value:08x}' for value in h)
+
+    @staticmethod
+    def yield_chacha20_xor_stream(key, iv, position=0):
+        """Generate the xor stream with the ChaCha20 cipher."""
+        if not isinstance(position, int):
+            raise TypeError
+        if position & ~0xFFFFFFFF:
+            raise ValueError("Position is not uint32.")
+        if not isinstance(key, bytes):
+            raise TypeError
+        if not isinstance(iv, bytes):
+            raise TypeError
+        if len(key) != 32:
+            raise ValueError
+        if len(iv) != 8:
+            raise ValueError
+
+        def rotate(v, c):
+            return ((v << c) & 0xFFFFFFFF) | v >> (32 - c)
+
+        def quarter_round(x, a, b, c, d):
+            x[a] = (x[a] + x[b]) & 0xFFFFFFFF
+            x[d] = rotate(x[d] ^ x[a], 16)
+            x[c] = (x[c] + x[d]) & 0xFFFFFFFF
+            x[b] = rotate(x[b] ^ x[c], 12)
+            x[a] = (x[a] + x[b]) & 0xFFFFFFFF
+            x[d] = rotate(x[d] ^ x[a], 8)
+            x[c] = (x[c] + x[d]) & 0xFFFFFFFF
+            x[b] = rotate(x[b] ^ x[c], 7)
+
+        ctx = [0] * 16
+        ctx[:4] = (1634760805, 857760878, 2036477234, 1797285236)
+        ctx[4:12] = struct.unpack("<8L", key)
+        ctx[12] = ctx[13] = position
+        ctx[14:16] = struct.unpack("<LL", iv)
+        while 1:
+            x = list(ctx)
+            for i in range(10):
+                quarter_round(x, 0, 4, 8, 12)
+                quarter_round(x, 1, 5, 9, 13)
+                quarter_round(x, 2, 6, 10, 14)
+                quarter_round(x, 3, 7, 11, 15)
+                quarter_round(x, 0, 5, 10, 15)
+                quarter_round(x, 1, 6, 11, 12)
+                quarter_round(x, 2, 7, 8, 13)
+                quarter_round(x, 3, 4, 9, 14)
+            for c in struct.pack(
+                "<16L", *((x[i] + ctx[i]) & 0xFFFFFFFF for i in range(16))
+            ):
+                yield c
+            ctx[12] = (ctx[12] + 1) & 0xFFFFFFFF
+            if ctx[12] == 0:
+                ctx[13] = (ctx[13] + 1) & 0xFFFFFFFF
+
+    @staticmethod
+    def chacha20(data:bytes, key:bytes, nonce=None, position=0):
+        """
+        Encrypt (or decrypt) data using the ChaCha20 stream cipher.
+
+        Parameters
+        ==========
+        data : bytes
+            Input data to encrypt/decrypt
+        key : bytes
+            32-byte encryption key. Shorter keys will be padded by repetition.
+        nonce : bytes, optional
+            8-byte nonce
+
+        Returns
+        =======
+        bytes
+            Processed output
+
+        Notes
+        =====
+        Chacha20 is symmetric - same operation encrypts and decrypts.
+
+        References
+        ==========
+
+        .. [1] https://en.wikipedia.org/wiki/ChaCha20-Poly1305
+        .. [2] https://github.com/pts/chacha20/blob/master/chacha20_python3.py
+
+        """
+
+        if nonce is None:
+            nonce = b"\0" * 8
+
+        if not key:
+            raise ValueError("Key is empty.")
+        if len(key) < 32:
+            key = (key * (32 // len(key) + 1))[:32]
+        if len(key) > 32:
+            key = key[:32]
+
+        return bytes(
+            a ^ b for a, b in zip(data, Crypto.yield_chacha20_xor_stream(key, nonce, position))
+        )

pydatastructs/strings/tests/test_algorithms.py

@@ -1,4 +1,4 @@
-from pydatastructs.strings import find
+from pydatastructs.strings import find, Crypto
 
 import random, string
 
@@ -74,3 +74,40 @@ def gen_random_string(length):
         if text != query:
             positions = find(text, query, algorithm)
             assert positions.size == 0
+
+def _test_sha256_encrypt():
+
+    test_cases = [
+        "HelloWorld",
+        "1234567890",
+        "abcdefABCDEF",
+        "",
+        "The quick brown fox jumps over the lazy dog",
+        "Pydatastructs"
+    ]
+
+    expected_hashes = [
+        "872e4e50ce9990d8b041330c47c9ddd11bec6b503ae9386a99da8584e9bb12c4",
+        "c775e7b757ede630cd0aa1113bd102661ab38829ca52a6422ab782862f268646",
+        "4a098074bfa74c04454ebbc7d286d085c420934c27ab11e9c00cc53247d9959e",
+        "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
+        "d7a8fbb307d7809469ca9abcb0082e4f8d5651e46d3cdb762d02d0bf37c9e592",
+        "1b5b22944c188c3e90d126ebd27e10d7497fbf5924f23c05775fa2dd9e1d8c86"
+    ]
+
+    for text, expected in zip(test_cases, expected_hashes):
+        assert Crypto.sha256_encrypt(text) == expected
+
+def _test_chacha20():
+    import binascii
+    cnvt = lambda x: binascii.unhexlify(bytes(x, 'ascii'))
+    test_cases = [
+        ('76b8e0ada0f13d90405d6ae55386bd28bdd219b8a08ded1aa836efcc8b770dc7da41597c5157488d7724e03fb8d84a376a43b8f41518a11cc387b669', '0000000000000000000000000000000000000000000000000000000000000000', '0000000000000000'),
+        ('4540f05a9f1fb296d7736e7b208e3c96eb4fe1834688d2604f450952ed432d41bbe2a0b6ea7566d2a5d1e7e20d42af2c53d792b1c43fea817e9ad275', '0000000000000000000000000000000000000000000000000000000000000001', '0000000000000000'),
+        ('de9cba7bf3d69ef5e786dc63973f653a0b49e015adbff7134fcb7df137821031e85a050278a7084527214f73efc7fa5b5277062eb7a0433e445f41e3', '0000000000000000000000000000000000000000000000000000000000000000', '0000000000000001'),
+        ('ef3fdfd6c61578fbf5cf35bd3dd33b8009631634d21e42ac33960bd138e50d32111e4caf237ee53ca8ad6426194a88545ddc497a0b466e7d6bbdb004', '0000000000000000000000000000000000000000000000000000000000000000', '0100000000000000'),
+        ('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', '000102030405060708090a0b0c0d0e0f101112131415161718191a1b1c1d1e1f', '0001020304050607')
+    ]
+
+    for i, (ciphertext, key, iv) in enumerate(map(lambda t: tuple(map(cnvt, t)), test_cases)):
+        assert Crypto.chacha20_encrypt(b'\0' * len(ciphertext), key, iv) == ciphertext