Improved compression by only appending count if the count is more than 2

This commit is contained in:
Ashhar Hasan 2015-10-30 03:06:17 +05:30
parent 6276624914
commit ef77603f9b
2 changed files with 84 additions and 46 deletions

View File

@ -18,7 +18,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## Problem: Compress a string such that 'AAABCCDDDD' becomes 'A3B1C2D4'. Only compress the string if it saves space.\n",
"## Problem: Compress a string such that 'AAABCCDDDD' becomes 'A3BCCD4'. Only compress the string if it saves space.\n",
"\n",
"* [Constraints](#Constraints)\n",
"* [Test Cases](#Test-Cases)\n",
@ -51,7 +51,7 @@
"* None -> None\n",
"* '' -> ''\n",
"* 'AABBCC' -> 'AABBCC'\n",
"* 'AAABCCDDDD' -> 'A3B1C2D4'"
"* 'AAABCCDDDD' -> 'A3BCCD4'"
]
},
{
@ -69,10 +69,20 @@
" * For each char in string\n",
" * If char is the same as last_char, increment count\n",
" * Else\n",
" * Append last_char to compressed_string\n",
" * append count to compressed_string\n",
" * count = 1\n",
" * last_char = char\n",
" * If the count is more than 2\n",
" * Append last_char to compressed_string\n",
" * append count to compressed_string\n",
" * count = 1\n",
" * last_char = char\n",
" * If count is 1\n",
" * Append last_char to compressed_string\n",
" * count = 1\n",
" * last_char = char\n",
" * If count is 2\n",
" * Append last_char to compressed_string\n",
" * Append last_char to compressed_string once more\n",
" * count = 1\n",
" * last_char = char\n",
" * Append last_char to compressed_string\n",
" * Append count to compressed_string\n",
" * Return compressed_string\n",
@ -91,47 +101,66 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 14,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"def compress_string(string):\n",
" if string is None or len(string) == 0:\n",
" return string\n",
"\tif string is None or len(string) == 0:\n",
"\t\treturn string\n",
"\n",
" # Calculate the size of the compressed string\n",
" size = 0\n",
" last_char = string[0]\n",
" for char in string:\n",
" if char != last_char:\n",
" size += 2\n",
" last_char = char\n",
" size += 2\n",
"\t# Calculate the size of the compressed string\n",
"\tsize = 0\n",
"\tlast_char = string[0]\n",
"\tfor char in string:\n",
"\t\tif char != last_char:\n",
"\t\t\tsize += 2\n",
"\t\t\tlast_char = char\n",
"\tsize += 2\n",
"\n",
" # If the compressed string size is greater than\n",
" # or equal to string size, return original string\n",
" if size >= len(string):\n",
" return string\n",
"\t# If the compressed string size is greater than\n",
"\t# or equal to string size, return original string\n",
"\tif size >= len(string):\n",
"\t\treturn string\n",
"\n",
" # Create compressed_string\n",
" compressed_string = list()\n",
" count = 0\n",
" last_char = string[0]\n",
" for char in string:\n",
" if char == last_char:\n",
" count += 1\n",
" else:\n",
" compressed_string.append(last_char)\n",
" compressed_string.append(str(count))\n",
" count = 1\n",
" last_char = char\n",
" compressed_string.append(last_char)\n",
" compressed_string.append(str(count))\n",
"\t# Create compressed_string\n",
"\t# New objective:\n",
"\t\t# Single characters are to be left as is\n",
"\t\t# Double characters are to be left as are\n",
"\tcompressed_string = list()\n",
"\tcount = 0\n",
"\tlast_char = string[0]\n",
"\tfor char in string:\n",
"\t\tif char == last_char:\n",
"\t\t\tcount += 1\n",
"\t\telse:\n",
"\t\t\t# Do the old compression tricks only if count exceeds two\n",
"\t\t\tif count > 2:\n",
"\t\t\t\tcompressed_string.append(last_char)\n",
"\t\t\t\tcompressed_string.append(str(count))\n",
"\t\t\t\tcount = 1\n",
"\t\t\t\tlast_char = char\n",
"\t\t\t# If count is either 1 or 2 (or 0?)\n",
"\t\t\t# FIXME: CAN COUNT BE 0?\n",
"\t\t\telse:\n",
"\t\t\t\t# If count is 1, leave the char as is\n",
"\t\t\t\tif count == 1:\n",
"\t\t\t\t\tcompressed_string.append(last_char)\n",
"\t\t\t\t\tcount = 1\n",
"\t\t\t\t\tlast_char = char\n",
"\t\t\t\t# If count is 2, append the character twice\n",
"\t\t\t\telse:\n",
"\t\t\t\t\tcompressed_string.append(last_char)\n",
"\t\t\t\t\tcompressed_string.append(last_char)\n",
"\t\t\t\t\tcount = 1\n",
"\t\t\t\t\tlast_char = char\n",
"\tcompressed_string.append(last_char)\n",
"\tcompressed_string.append(str(count))\n",
"\n",
" # Convert the characters in the list to a string\n",
" return \"\".join(compressed_string)"
"\t# Convert the characters in the list to a string\n",
"\treturn \"\".join(compressed_string)"
]
},
{
@ -143,7 +172,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 15,
"metadata": {
"collapsed": false
},
@ -167,7 +196,7 @@
" assert_equal(func(None), None)\n",
" assert_equal(func(''), '')\n",
" assert_equal(func('AABBCC'), 'AABBCC')\n",
" assert_equal(func('AAABCCDDDD'), 'A3B1C2D4')\n",
" assert_equal(func('AAABCCDDDD'), 'A3BCCD4')\n",
" print('Success: test_compress')\n",
"\n",
"\n",
@ -182,7 +211,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 16,
"metadata": {
"collapsed": false
},
@ -198,25 +227,34 @@
"source": [
"%run -i test_compress.py"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"display_name": "Python 3",
"language": "python",
"name": "python2"
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.10"
"pygments_lexer": "ipython3",
"version": "3.4.3"
}
},
"nbformat": 4,

View File

@ -7,7 +7,7 @@ class TestCompress(object):
assert_equal(func(None), None)
assert_equal(func(''), '')
assert_equal(func('AABBCC'), 'AABBCC')
assert_equal(func('AAABCCDDDD'), 'A3B1C2D4')
assert_equal(func('AAABCCDDDD'), 'A3BCCD4')
print('Success: test_compress')