Chilkat2-Python

Decompress Large Text File in Blocks

See more Compression Examples

Decompresses a large text file in blocks, and compares the restored (decompressed) file with the original to make sure it's correct. Chilkat2-Python

import sys
import chilkat2

success = False

# This example requires the Chilkat API to have been previously unlocked.
# See Global Unlock Sample for sample code.

# First, let's compress a text file.
# We'll then decompress in blocks, and compare the decompressed with the original file.

# Compress a text file:
compress = chilkat2.Compression()
compress.Algorithm = "deflate"

success = compress.CompressFile("qa_data/hamlet.xml","qa_data/hamlet_compressed.dat")
if (success == False):
    print(compress.LastErrorText)
    sys.exit()

fac = chilkat2.FileAccess()

# Examine the uncompressed and compressed sizes:
originalPath = "qa_data/hamlet.xml"
# Note: The FileSize method returns a signed 32-bit integer.  If the file is potentially larger than 2GB, call FileSizeStr instead to return
# the size of the file as a string, then convert to an integer value.
print("uncompressed size: " + str(fac.FileSize(originalPath)))
print("compressed size: " + str(fac.FileSize("qa_data/hamlet_compressed.dat")))

# Decompress in blocks..
facSrc = chilkat2.FileAccess()
facDest = chilkat2.FileAccess()

facSrc.OpenForRead("qa_data/hamlet_compressed.dat")

# If we compress in 32K chunks, find out how many blocks there will be.
blockSize = 32768
numBlocks = facSrc.GetNumBlocks(blockSize)

# Open an output file for the decompressed data.
restoredPath = "qa_output/hamlet_restored.xml"
success = facDest.OpenForWrite(restoredPath)
if (success == False):
    print(facDest.LastErrorText)
    sys.exit()

# Assuming numBlocks > 1
compress.FirstChunk = True
compress.LastChunk = False

i = 0
while i < numBlocks :
    # compressedBytes is a memoryview
    compressedBytes = facSrc.ReadBlock(i,blockSize)
    decompressedStr = compress.DecompressString(compressedBytes)

    facDest.AppendText(decompressedStr,"utf-8")

    i = i + 1

    compress.FirstChunk = False
    if (i == (numBlocks - 1)):
        compress.LastChunk = True

facSrc.FileClose()
facDest.FileClose()

# Examine the size of the restored file.
print("restored size: " + str(fac.FileSize(restoredPath)))

# Compare the contents of the original with the restored.
bEqualContents = fac.FileContentsEqual(restoredPath,originalPath)
print("Contents Equal: " + str(bEqualContents))