ext.human_readable: more efficient implementation

plus unit tests and benchmark.

3 files changed, 120 insertions, 19 deletions

diff --git a/ranger/ext/human_readable.py b/ranger/ext/human_readable.py
index beeaf6d3..35dbc35e 100644
--- a/ranger/ext/human_readable.py
+++ b/ranger/ext/human_readable.py
@@ -13,24 +13,39 @@
 # You should have received a copy of the GNU General Public License
 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
 
-import math
-
-ONE_KB = 1024
-UNITS = 'BKMGTP'
-MAX_EXPONENT = len(UNITS) - 1
-
 def human_readable(byte, seperator=' '):
-	if not byte:
-		return '0'
-
-	exponent = int(math.log(byte, 2) / 10)
-	flt = round(float(byte) / (1 << (10 * exponent)), 2)
+	"""
+	Convert a large number of bytes to an easily readable format.
 
-	if exponent > MAX_EXPONENT:
-		return '>9000' # off scale
-
-	if int(flt) == flt:
-		return '%.0f%s%s' % (flt, seperator, UNITS[exponent])
-
-	else:
-		return '%.2f%s%s' % (flt, seperator, UNITS[exponent])
+	>>> human_readable(54)
+	"54 B"
+	>>> human_readable(1500)
+	"1.46 K"
+	>>> human_readable(2 ** 20 * 1023)
+	"1023 M"
+	"""
+	if byte <= 0:
+		return '0'
+	if byte < 2**10:
+		return '%d%sB'   % (byte, seperator)
+	if byte < 2**10 * 1000:
+		return '%.3g%sK' % (byte / 2**10.0, seperator)
+	if byte < 2**20:
+		return '%.4g%sK' % (byte / 2**10.0, seperator)
+	if byte < 2**20 * 1000:
+		return '%.3g%sM' % (byte / 2**20.0, seperator)
+	if byte < 2**30:
+		return '%.4g%sM' % (byte / 2**20.0, seperator)
+	if byte < 2**30 * 1000:
+		return '%.3g%sG' % (byte / 2**30.0, seperator)
+	if byte < 2**40:
+		return '%.4g%sG' % (byte / 2**30.0, seperator)
+	if byte < 2**40 * 1000:
+		return '%.3g%sT' % (byte / 2**40.0, seperator)
+	if byte < 2**50:
+		return '%.4g%sT' % (byte / 2**40.0, seperator)
+	if byte < 2**50 * 1000:
+		return '%.3g%sP' % (byte / 2**50.0, seperator)
+	if byte < 2**60:
+		return '%.4g%sP' % (byte / 2**50.0, seperator)
+	return '>9000'
diff --git a/test/bm_human_readable.py b/test/bm_human_readable.py
new file mode 100644
index 00000000..83f2a057
--- /dev/null
+++ b/test/bm_human_readable.py
@@ -0,0 +1,45 @@
+# Copyright (C) 2009, 2010  Roman Zimbelmann <romanz@lavabit.com>
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+from ranger.ext.human_readable import *
+
+# The version before 2010/06/24:
+import math
+UNITS = 'BKMGTP'
+MAX_EXPONENT = len(UNITS) - 1
+def human_readable_old(byte, seperator=' '):
+	if not byte:
+		return '0'
+
+	exponent = int(math.log(byte, 2) / 10)
+	flt = round(float(byte) / (1 << (10 * exponent)), 2)
+
+	if exponent > MAX_EXPONENT:
+		return '>9000' # off scale
+
+	if int(flt) == flt:
+		return '%.0f%s%s' % (flt, seperator, UNITS[exponent])
+
+	else:
+		return '%.2f%s%s' % (flt, seperator, UNITS[exponent])
+
+class benchmark_human_readable(object):
+	def bm_current(self, n):
+		for i in range(n):
+			human_readable((128 * i) % 2**50)
+
+	def bm_old(self, n):
+		for i in range(n):
+			human_readable_old((128 * i) % 2**50)
diff --git a/test/tc_human_readable.py b/test/tc_human_readable.py
new file mode 100644
index 00000000..50fc80a1
--- /dev/null
+++ b/test/tc_human_readable.py
@@ -0,0 +1,41 @@
+# Copyright (C) 2009, 2010  Roman Zimbelmann <romanz@lavabit.com>
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+import unittest
+from ranger.ext.human_readable import human_readable as hr
+
+class HumanReadableTest(unittest.TestCase):
+	def test_basic(self):
+		self.assertEqual("0", hr(0))
+		self.assertEqual("1 B", hr(1))
+		self.assertEqual("1 K", hr(2 ** 10))
+		self.assertEqual("1 M", hr(2 ** 20))
+		self.assertEqual("1 G", hr(2 ** 30))
+		self.assertEqual(">9000", hr(2 ** 100))
+
+	def test_big(self):
+		self.assertEqual("1023 G", hr(2 ** 30 * 1023))
+		self.assertEqual("1024 G", hr(2 ** 40 - 1))
+		self.assertEqual("1 T",    hr(2 ** 40))
+
+	def test_small(self):
+		self.assertEqual("1000 B", hr(1000))
+		self.assertEqual("1.66 M", hr(1.66 * 2 ** 20))
+		self.assertEqual("1.46 K", hr(1500))
+		self.assertEqual("1.5 K",  hr(2 ** 10 + 2 ** 9))
+		self.assertEqual("1.5 K",  hr(2 ** 10 + 2 ** 9 - 1))
+
+if __name__ == '__main__':
+	unittest.main()