commit -- why not...

5 files changed, 238 insertions, 0 deletions

diff --git a/Demo/comparisons/README b/Demo/comparisons/README
new file mode 100644
index 0000000..111667c
--- /dev/null
+++ b/Demo/comparisons/README
@@ -0,0 +1,60 @@
+Subject: Re: What language would you use?
+From: Tom Christiansen <tchrist@mox.perl.com>
+Date: 6 Nov 1994 15:14:51 GMT
+Newsgroups: comp.lang.python,comp.lang.tcl,comp.lang.scheme,comp.lang.misc,comp.lang.perl
+Message-Id: <39irtb$3t4@csnews.cs.Colorado.EDU>
+References: <39b7ha$j9v@zeno.nscf.org> <39hhjp$lgn@csnews.cs.Colorado.EDU> <39hvsu$dus@mathserv.mps.ohio-state.edu>
+
+[...]
+If you're really into benchmarks, I'd love it if someone were to code up
+the following problems in tcl, python, and scheme (and whatever else you'd
+like).  Separate versions (one optimized for speed, one for beauty :-) are
+ok.  Post your code so we can time it on our own systems.
+
+0)  Factorial Test  (numerics and function calls)
+
+        (we did this already)
+
+1)  Regular Expressions Test
+
+    Read a file of (extended per egrep) regular expressions (one per line), 
+    and apply those to all files whose names are listed on the command line.
+    Basically, an 'egrep -f' simulator.  Test it with 20 "vt100" patterns
+    against a five /etc/termcap files.  Tests using more elaborate patters
+    would also be interesting.  Your code should not break if given hundreds
+    of regular expressions or binary files to scan.  
+
+2)  Sorting Test
+
+    Sort an input file that consists of lines like this
+
+        var1=23 other=14 ditto=23 fred=2
+
+    such that each output line is sorted WRT to the number.  Order
+    of output lines does not change.  Resolve collisions using the
+    variable name.   e.g.
+
+        fred=2 other=14 ditto=23 var1=23 
+
+    Lines may be up to several kilobytes in length and contain
+    zillions of variables.
+
+3)  System Test
+
+    Given a list of directories, report any bogus symbolic links contained
+    anywhere in those subtrees.  A bogus symbolic link is one that cannot
+    be resolved because it points to a nonexistent or otherwise
+    unresolvable file.  Do *not* use an external find executable.
+    Directories may be very very deep.  Print a warning immediately if the
+    system you're running on doesn't support symbolic links.
+
+
+I'll post perl solutions if people post the others.
+
+
+--tom
+-- 
+Tom Christiansen      Perl Consultant, Gamer, Hiker      tchrist@mox.perl.com
+
+ "But Billy! A *small* allowance prepares you for a lifetime of small
+ salaries and for your Social Security payments."    --Family Circus
diff --git a/Demo/comparisons/patterns b/Demo/comparisons/patterns
new file mode 100755
index 0000000..f4da846
--- /dev/null
+++ b/Demo/comparisons/patterns
@@ -0,0 +1,4 @@
+^def 
+^class 
+^import 
+^from 
diff --git a/Demo/comparisons/regextest.py b/Demo/comparisons/regextest.py
new file mode 100755
index 0000000..35ee9ee
--- /dev/null
+++ b/Demo/comparisons/regextest.py
@@ -0,0 +1,50 @@
+#! /usr/local/bin/python
+
+# 1)  Regular Expressions Test
+# 
+#     Read a file of (extended per egrep) regular expressions (one per line), 
+#     and apply those to all files whose names are listed on the command line.
+#     Basically, an 'egrep -f' simulator.  Test it with 20 "vt100" patterns
+#     against a five /etc/termcap files.  Tests using more elaborate patters
+#     would also be interesting.  Your code should not break if given hundreds
+#     of regular expressions or binary files to scan.  
+
+# This implementation:
+# - combines all patterns into a single one using ( ... | ... | ... )
+# - reads patterns from stdin, scans files given as command line arguments
+# - produces output in the format <file>:<lineno>:<line>
+# - is only about 2.5 times as slow as egrep (though I couldn't run
+#   Tom's test -- this system, a vanilla SGI, only has /etc/terminfo)
+
+import string
+import sys
+import regex
+from regex_syntax import *
+
+regex.set_syntax(RE_SYNTAX_EGREP)
+
+def main():
+	pats = map(chomp, sys.stdin.readlines())
+	bigpat = '(' + string.joinfields(pats, '|') + ')'
+	prog = regex.compile(bigpat)
+	
+	for file in sys.argv[1:]:
+		try:
+			fp = open(file, 'r')
+		except IOError, msg:
+			print "%s: %s" % (file, msg)
+			continue
+		lineno = 0
+		while 1:
+			line = fp.readline()
+			if not line:
+				break
+			lineno = lineno + 1
+			if prog.search(line) >= 0:
+				print "%s:%s:%s" % (file, lineno, line),
+
+def chomp(s):
+	if s[-1:] == '\n': return s[:-1]
+	else: return s
+
+main()
diff --git a/Demo/comparisons/sortingtest.py b/Demo/comparisons/sortingtest.py
new file mode 100755
index 0000000..1de683b
--- /dev/null
+++ b/Demo/comparisons/sortingtest.py
@@ -0,0 +1,50 @@
+#! /usr/local/bin/python
+
+# 2)  Sorting Test
+# 
+#     Sort an input file that consists of lines like this
+# 
+#         var1=23 other=14 ditto=23 fred=2
+# 
+#     such that each output line is sorted WRT to the number.  Order
+#     of output lines does not change.  Resolve collisions using the
+#     variable name.   e.g.
+# 
+#         fred=2 other=14 ditto=23 var1=23 
+# 
+#     Lines may be up to several kilobytes in length and contain
+#     zillions of variables.
+
+# This implementation:
+# - Reads stdin, writes stdout
+# - Uses any amount of whitespace to separate fields
+# - Allows signed numbers
+# - Treats illegally formatted fields as field=0
+# - Outputs the sorted fields with exactly one space between them
+# - Handles blank input lines correctly
+
+import regex
+import string
+import sys
+
+def main():
+	prog = regex.compile('^\(.*\)=\([-+]?[0-9]+\)')
+	def makekey(item, prog=prog):
+		if prog.match(item) >= 0:
+			var, num = prog.group(1, 2)
+			return string.atoi(num), var
+		else:
+			# Bad input -- pretend it's a var with value 0
+			return 0, item
+	while 1:
+		line = sys.stdin.readline()
+		if not line:
+			break
+		items = string.split(line)
+		items = map(makekey, items)
+		items.sort()
+		for num, var in items:
+			print "%s=%s" % (var, num),
+		print
+
+main()
diff --git a/Demo/comparisons/systemtest.py b/Demo/comparisons/systemtest.py
new file mode 100755
index 0000000..26d9f54
--- /dev/null
+++ b/Demo/comparisons/systemtest.py
@@ -0,0 +1,74 @@
+#! /usr/local/bin/python
+
+# 3)  System Test
+# 
+#     Given a list of directories, report any bogus symbolic links contained
+#     anywhere in those subtrees.  A bogus symbolic link is one that cannot
+#     be resolved because it points to a nonexistent or otherwise
+#     unresolvable file.  Do *not* use an external find executable.
+#     Directories may be very very deep.  Print a warning immediately if the
+#     system you're running on doesn't support symbolic links.
+
+# This implementation:
+# - takes one optional argument, using the current directory as default
+# - uses chdir to increase performance
+# - sorts the names per directory
+# - prints output lines of the form "path1 -> path2" as it goes
+# - prints error messages about directories it can't list or chdir into
+
+import os
+import sys
+from stat import *
+
+def main():
+	try:
+		# Note: can't test for presence of lstat -- it's always there
+		dummy = os.readlink
+	except AttributeError:
+		print "This system doesn't have symbolic links"
+		sys.exit(0)
+	if sys.argv[1:]:
+		prefix = sys.argv[1]
+	else:
+		prefix = ''
+	if prefix:
+		os.chdir(prefix)
+		if prefix[-1:] != '/': prefix = prefix + '/'
+		reportboguslinks(prefix)
+	else:
+		reportboguslinks('')
+
+def reportboguslinks(prefix):
+	try:
+		names = os.listdir('.')
+	except os.error, msg:
+		print "%s%s: can't list: %s" % (prefix, '.', msg)
+		return
+	names.sort()
+	for name in names:
+		if name == os.curdir or name == os.pardir:
+			continue
+		try:
+			mode = os.lstat(name)[ST_MODE]
+		except os.error:
+			print "%s%s: can't stat: %s" % (prefix, name, msg)
+			continue
+		if S_ISLNK(mode):
+			try:
+				os.stat(name)
+			except os.error:
+				print "%s%s -> %s" % \
+				      (prefix, name, os.readlink(name))
+		elif S_ISDIR(mode):
+			try:
+				os.chdir(name)
+			except os.error, msg:
+				print "%s%s: can't chdir: %s" % \
+				      (prefix, name, msg)
+				continue
+			try:
+				reportboguslinks(prefix + name + '/')
+			finally:
+				os.chdir('..')
+
+main()