import hashlib

import io

import struct

import sys

import tarfile

import unittest

import zstandard as zstd

from .common import (

    make_cffi,

    OpCountingBytesIO,

)

if sys.version_info[0] >= 3:

    next = lambda it: it.__next__()

else:

    next = lambda it: it.next()

def multithreaded_chunk_size(level, source_size=0):

    params = zstd.ZstdCompressionParameters.from_level(level,

                                                       source_size=source_size)

    return 1 << (params.window_log + 2)

@make_cffi

class TestCompressor(unittest.TestCase):

    def test_level_bounds(self):

        with self.assertRaises(ValueError):

            zstd.ZstdCompressor(level=23)

    def test_memory_size(self):

        cctx = zstd.ZstdCompressor(level=1)

        self.assertGreater(cctx.memory_size(), 100)

@make_cffi

class TestCompressor_compress(unittest.TestCase):

    def test_compress_empty(self):

        cctx = zstd.ZstdCompressor(level=1, write_content_size=False)

        result = cctx.compress(b'')

        self.assertEqual(result, b'\x28\xb5\x2f\xfd\x00\x48\x01\x00\x00')

        params = zstd.get_frame_parameters(result)

        self.assertEqual(params.content_size, zstd.CONTENTSIZE_UNKNOWN)

        self.assertEqual(params.window_size, 524288)

        self.assertEqual(params.dict_id, 0)

        self.assertFalse(params.has_checksum, 0)

        cctx = zstd.ZstdCompressor()

        result = cctx.compress(b'')

        self.assertEqual(result, b'\x28\xb5\x2f\xfd\x20\x00\x01\x00\x00')

        params = zstd.get_frame_parameters(result)

        self.assertEqual(params.content_size, 0)

    def test_input_types(self):

        cctx = zstd.ZstdCompressor(level=1, write_content_size=False)

        expected = b'\x28\xb5\x2f\xfd\x00\x00\x19\x00\x00\x66\x6f\x6f'

        mutable_array = bytearray(3)

        mutable_array[:] = b'foo'

        sources = [

            memoryview(b'foo'),

            bytearray(b'foo'),

            mutable_array,

        ]

        for source in sources:

            self.assertEqual(cctx.compress(source), expected)

    def test_compress_large(self):

        chunks = []

        for i in range(255):

            chunks.append(struct.Struct('>B').pack(i) * 16384)

        cctx = zstd.ZstdCompressor(level=3, write_content_size=False)

        result = cctx.compress(b''.join(chunks))

        self.assertEqual(len(result), 999)

        self.assertEqual(result[0:4], b'\x28\xb5\x2f\xfd')

        # This matches the test for read_to_iter() below.

        cctx = zstd.ZstdCompressor(level=1, write_content_size=False)

        result = cctx.compress(b'f' * zstd.COMPRESSION_RECOMMENDED_INPUT_SIZE + b'o')

        self.assertEqual(result, b'\x28\xb5\x2f\xfd\x00\x40\x54\x00\x00'

                                 b'\x10\x66\x66\x01\x00\xfb\xff\x39\xc0'

                                 b'\x02\x09\x00\x00\x6f')

    def test_negative_level(self):

        cctx = zstd.ZstdCompressor(level=-4)

        result = cctx.compress(b'foo' * 256)

    def test_no_magic(self):

        params = zstd.ZstdCompressionParameters.from_level(

            1, format=zstd.FORMAT_ZSTD1)

        cctx = zstd.ZstdCompressor(compression_params=params)

        magic = cctx.compress(b'foobar')

        params = zstd.ZstdCompressionParameters.from_level(

            1, format=zstd.FORMAT_ZSTD1_MAGICLESS)

        cctx = zstd.ZstdCompressor(compression_params=params)

        no_magic = cctx.compress(b'foobar')

        self.assertEqual(magic[0:4], b'\x28\xb5\x2f\xfd')

        self.assertEqual(magic[4:], no_magic)

    def test_write_checksum(self):

        cctx = zstd.ZstdCompressor(level=1)

        no_checksum = cctx.compress(b'foobar')

        cctx = zstd.ZstdCompressor(level=1, write_checksum=True)

        with_checksum = cctx.compress(b'foobar')

        self.assertEqual(len(with_checksum), len(no_checksum) + 4)

        no_params = zstd.get_frame_parameters(no_checksum)

        with_params = zstd.get_frame_parameters(with_checksum)

        self.assertFalse(no_params.has_checksum)

        self.assertTrue(with_params.has_checksum)

    def test_write_content_size(self):

        cctx = zstd.ZstdCompressor(level=1)

        with_size = cctx.compress(b'foobar' * 256)

        cctx = zstd.ZstdCompressor(level=1, write_content_size=False)

        no_size = cctx.compress(b'foobar' * 256)

        self.assertEqual(len(with_size), len(no_size) + 1)

        no_params = zstd.get_frame_parameters(no_size)

        with_params = zstd.get_frame_parameters(with_size)

        self.assertEqual(no_params.content_size, zstd.CONTENTSIZE_UNKNOWN)

        self.assertEqual(with_params.content_size, 1536)

    def test_no_dict_id(self):

        samples = []

        for i in range(128):

            samples.append(b'foo' * 64)

            samples.append(b'bar' * 64)

            samples.append(b'foobar' * 64)

        d = zstd.train_dictionary(1024, samples)

        cctx = zstd.ZstdCompressor(level=1, dict_data=d)

        with_dict_id = cctx.compress(b'foobarfoobar')

        cctx = zstd.ZstdCompressor(level=1, dict_data=d, write_dict_id=False)

        no_dict_id = cctx.compress(b'foobarfoobar')

        self.assertEqual(len(with_dict_id), len(no_dict_id) + 4)

        no_params = zstd.get_frame_parameters(no_dict_id)

        with_params = zstd.get_frame_parameters(with_dict_id)

        self.assertEqual(no_params.dict_id, 0)

        self.assertEqual(with_params.dict_id, 1387616518)

    def test_compress_dict_multiple(self):

        samples = []

        for i in range(128):

            samples.append(b'foo' * 64)

            samples.append(b'bar' * 64)

            samples.append(b'foobar' * 64)

        d = zstd.train_dictionary(8192, samples)

        cctx = zstd.ZstdCompressor(level=1, dict_data=d)

        for i in range(32):

            cctx.compress(b'foo bar foobar foo bar foobar')

    def test_dict_precompute(self):

        samples = []

        for i in range(128):

            samples.append(b'foo' * 64)

            samples.append(b'bar' * 64)

            samples.append(b'foobar' * 64)

        d = zstd.train_dictionary(8192, samples)

        d.precompute_compress(level=1)

        cctx = zstd.ZstdCompressor(level=1, dict_data=d)

        for i in range(32):

            cctx.compress(b'foo bar foobar foo bar foobar')

    def test_multithreaded(self):

        chunk_size = multithreaded_chunk_size(1)

        source = b''.join([b'x' * chunk_size, b'y' * chunk_size])

        cctx = zstd.ZstdCompressor(level=1, threads=2)

        compressed = cctx.compress(source)

        params = zstd.get_frame_parameters(compressed)

        self.assertEqual(params.content_size, chunk_size * 2)

        self.assertEqual(params.dict_id, 0)

        self.assertFalse(params.has_checksum)

        dctx = zstd.ZstdDecompressor()

        self.assertEqual(dctx.decompress(compressed), source)

    def test_multithreaded_dict(self):

        samples = []

        for i in range(128):

            samples.append(b'foo' * 64)

            samples.append(b'bar' * 64)

            samples.append(b'foobar' * 64)

        d = zstd.train_dictionary(1024, samples)

        cctx = zstd.ZstdCompressor(dict_data=d, threads=2)

        result = cctx.compress(b'foo')

        params = zstd.get_frame_parameters(result);

        self.assertEqual(params.content_size, 3);

        self.assertEqual(params.dict_id, d.dict_id())

        self.assertEqual(result,

                         b'\x28\xb5\x2f\xfd\x23\x06\x59\xb5\x52\x03\x19\x00\x00'

                         b'\x66\x6f\x6f')

    def test_multithreaded_compression_params(self):

        params = zstd.ZstdCompressionParameters.from_level(0, threads=2)

        cctx = zstd.ZstdCompressor(compression_params=params)

        result = cctx.compress(b'foo')

        params = zstd.get_frame_parameters(result);

        self.assertEqual(params.content_size, 3);

        self.assertEqual(result,

                         b'\x28\xb5\x2f\xfd\x20\x03\x19\x00\x00\x66\x6f\x6f')

@make_cffi

class TestCompressor_compressobj(unittest.TestCase):

    def test_compressobj_empty(self):

        cctx = zstd.ZstdCompressor(level=1, write_content_size=False)

        cobj = cctx.compressobj()

        self.assertEqual(cobj.compress(b''), b'')

        self.assertEqual(cobj.flush(),

                         b'\x28\xb5\x2f\xfd\x00\x48\x01\x00\x00')

    def test_input_types(self):

        expected = b'\x28\xb5\x2f\xfd\x00\x48\x19\x00\x00\x66\x6f\x6f'

        cctx = zstd.ZstdCompressor(level=1, write_content_size=False)

        mutable_array = bytearray(3)

        mutable_array[:] = b'foo'

        sources = [

            memoryview(b'foo'),

            bytearray(b'foo'),

            mutable_array,

        ]

        for source in sources:

            cobj = cctx.compressobj()

            self.assertEqual(cobj.compress(source), b'')

            self.assertEqual(cobj.flush(), expected)

    def test_compressobj_large(self):

        chunks = []

        for i in range(255):

            chunks.append(struct.Struct('>B').pack(i) * 16384)

        cctx = zstd.ZstdCompressor(level=3)

        cobj = cctx.compressobj()

        result = cobj.compress(b''.join(chunks)) + cobj.flush()

        self.assertEqual(len(result), 999)

        self.assertEqual(result[0:4], b'\x28\xb5\x2f\xfd')

        params = zstd.get_frame_parameters(result)

        self.assertEqual(params.content_size, zstd.CONTENTSIZE_UNKNOWN)

        self.assertEqual(params.window_size, 1048576)

        self.assertEqual(params.dict_id, 0)

        self.assertFalse(params.has_checksum)

    def test_write_checksum(self):

        cctx = zstd.ZstdCompressor(level=1)

        cobj = cctx.compressobj()

        no_checksum = cobj.compress(b'foobar') + cobj.flush()

        cctx = zstd.ZstdCompressor(level=1, write_checksum=True)

        cobj = cctx.compressobj()

        with_checksum = cobj.compress(b'foobar') + cobj.flush()

        no_params = zstd.get_frame_parameters(no_checksum)

        with_params = zstd.get_frame_parameters(with_checksum)

        self.assertEqual(no_params.content_size, zstd.CONTENTSIZE_UNKNOWN)

        self.assertEqual(with_params.content_size, zstd.CONTENTSIZE_UNKNOWN)

        self.assertEqual(no_params.dict_id, 0)

        self.assertEqual(with_params.dict_id, 0)

        self.assertFalse(no_params.has_checksum)

        self.assertTrue(with_params.has_checksum)

        self.assertEqual(len(with_checksum), len(no_checksum) + 4)

    def test_write_content_size(self):

        cctx = zstd.ZstdCompressor(level=1)

        cobj = cctx.compressobj(size=len(b'foobar' * 256))

        with_size = cobj.compress(b'foobar' * 256) + cobj.flush()

        cctx = zstd.ZstdCompressor(level=1, write_content_size=False)

        cobj = cctx.compressobj(size=len(b'foobar' * 256))

        no_size = cobj.compress(b'foobar' * 256) + cobj.flush()

        no_params = zstd.get_frame_parameters(no_size)

        with_params = zstd.get_frame_parameters(with_size)

        self.assertEqual(no_params.content_size, zstd.CONTENTSIZE_UNKNOWN)

        self.assertEqual(with_params.content_size, 1536)

        self.assertEqual(no_params.dict_id, 0)

        self.assertEqual(with_params.dict_id, 0)

        self.assertFalse(no_params.has_checksum)

        self.assertFalse(with_params.has_checksum)

        self.assertEqual(len(with_size), len(no_size) + 1)

    def test_compress_after_finished(self):

        cctx = zstd.ZstdCompressor()

        cobj = cctx.compressobj()

        cobj.compress(b'foo')

        cobj.flush()

        with self.assertRaisesRegexp(zstd.ZstdError, 'cannot call compress\(\) after compressor'):

            cobj.compress(b'foo')

        with self.assertRaisesRegexp(zstd.ZstdError, 'compressor object already finished'):

            cobj.flush()

    def test_flush_block_repeated(self):

        cctx = zstd.ZstdCompressor(level=1)

        cobj = cctx.compressobj()

        self.assertEqual(cobj.compress(b'foo'), b'')

        self.assertEqual(cobj.flush(zstd.COMPRESSOBJ_FLUSH_BLOCK),

                         b'\x28\xb5\x2f\xfd\x00\x48\x18\x00\x00foo')

        self.assertEqual(cobj.compress(b'bar'), b'')

        # 3 byte header plus content.

        self.assertEqual(cobj.flush(), b'\x19\x00\x00bar')

    def test_flush_empty_block(self):

        cctx = zstd.ZstdCompressor(write_checksum=True)

        cobj = cctx.compressobj()

        cobj.compress(b'foobar')

        cobj.flush(zstd.COMPRESSOBJ_FLUSH_BLOCK)

        # No-op if no block is active (this is internal to zstd).

        self.assertEqual(cobj.flush(zstd.COMPRESSOBJ_FLUSH_BLOCK), b'')

        trailing = cobj.flush()

        # 3 bytes block header + 4 bytes frame checksum

        self.assertEqual(len(trailing), 7)

        header = trailing[0:3]

        self.assertEqual(header, b'\x01\x00\x00')

    def test_multithreaded(self):