Detangle ASCII and multi-byte code for case-insenstive UTF-8 searches.

This avoids some work for the common case of ASCII text, which can reduce time
taken for search in text that is ASCII or almost-all ASCII by 30%.
Ensures that the bytes variable is always initialized.
There are a small gains possible by making other minor changes but they would
increase code length and add complexity.
Add performance test for UTF-8 search in almost-all ASCII document.
Increase size of test cases for more consistent results on faster computers.

1 files changed, 24 insertions, 5 deletions

diff --git a/test/performanceTests.py b/test/performanceTests.py
index eb7c0c096..a3df73465 100644
--- a/test/performanceTests.py
+++ b/test/performanceTests.py
@@ -26,7 +26,7 @@ class TestPerformance(unittest.TestCase):
 	def testAddLine(self):
 		data = (string.ascii_letters + string.digits + "\n").encode('utf-8')
 		start = timer()
-		for i in range(1000):
+		for i in range(2000):
 			self.ed.AddText(len(data), data)
 			self.assertEquals(self.ed.LineCount, i + 2)
 		end = timer()
@@ -38,7 +38,7 @@ class TestPerformance(unittest.TestCase):
 	def testAddLineMiddle(self):
 		data = (string.ascii_letters + string.digits + "\n").encode('utf-8')
 		start = timer()
-		for i in range(1000):
+		for i in range(2000):
 			self.ed.AddText(len(data), data)
 			self.assertEquals(self.ed.LineCount, i + 2)
 		end = timer()
@@ -64,7 +64,7 @@ class TestPerformance(unittest.TestCase):
 		insert = (string.digits + "\n").encode('utf-8')
 		self.ed.AddText(len(data), data)
 		start = timer()
-		for i in range(1000):
+		for i in range(2000):
 			self.ed.InsertText(0, insert)
 		end = timer()
 		duration = end - start
@@ -96,7 +96,7 @@ class TestPerformance(unittest.TestCase):
 		self.ed.AddText(len(manyLines), manyLines)
 		searchString = "φ".encode('utf-8')
 		start = timer()
-		for i in range(10):
+		for i in range(1000):
 			self.ed.TargetStart = 0
 			self.ed.TargetEnd = self.ed.Length-1
 			self.ed.SearchFlags = self.ed.SCFIND_MATCHCASE
@@ -115,7 +115,7 @@ class TestPerformance(unittest.TestCase):
 		self.ed.AddText(len(manyLines), manyLines)
 		searchString = "φ".encode('utf-8')
 		start = timer()
-		for i in range(10):
+		for i in range(20):
 			self.ed.TargetStart = 0
 			self.ed.TargetEnd = self.ed.Length-1
 			self.ed.SearchFlags = 0
@@ -126,5 +126,24 @@ class TestPerformance(unittest.TestCase):
 		print("%6.3f testUTF8Searches" % duration)
 		self.xite.DoEvents()
 
+	def testUTF8AsciiSearches(self):
+		self.ed.SetCodePage(65001)
+		oneLine = "Fold Margin=NagasakiOsakaHiroshimaHanedaKyoto(&F)\n".encode('utf-8')
+		manyLines = oneLine * 100000
+		manyLines = manyLines + "φ\n".encode('utf-8')
+		self.ed.AddText(len(manyLines), manyLines)
+		searchString = "φ".encode('utf-8')
+		start = timer()
+		for i in range(20):
+			self.ed.TargetStart = 0
+			self.ed.TargetEnd = self.ed.Length-1
+			self.ed.SearchFlags = 0
+			pos = self.ed.SearchInTarget(len(searchString), searchString)
+			self.assert_(pos > 0)
+		end = timer()
+		duration = end - start
+		print("%6.3f testUTF8AsciiSearches" % duration)
+		self.xite.DoEvents()
+
 if __name__ == '__main__':
 	Xite.main("performanceTests")