Tabs are 8 spaces, as the Python docs dictate. Fixes issue #31.

6 files changed, 37 insertions, 12 deletions

diff --git a/CHANGES.txt b/CHANGES.txt
index 55f4f0af..d630b76b 100644
--- a/CHANGES.txt
+++ b/CHANGES.txt
@@ -5,10 +5,11 @@ Change history for Coverage.py
 Version 3.2b2

 -------------

 

-- Fixed some problems syntax coloring sources with line continuations:

-  `issue 30`_.

+- Fixed some problems syntax coloring sources with line continuations and

+  source with tabs: `issue 30`_ and `issue 31`_.

   

 .. _issue 30: http://bitbucket.org/ned/coveragepy/issue/30

+.. _issue 31: http://bitbucket.org/ned/coveragepy/issue/31

 

 

 Version 3.2b1, 10 November 2009

diff --git a/coverage/html.py b/coverage/html.py
index 98d32cdc..8c274728 100644
--- a/coverage/html.py
+++ b/coverage/html.py
@@ -60,7 +60,7 @@ class HtmlReporter(Reporter):
     def html_file(self, cu, analysis):
         """Generate an HTML file for one source file."""
         
-        source = cu.source_file().read().expandtabs(4)
+        source = cu.source_file().read()
 
         nums = analysis.numbers        
 
diff --git a/coverage/phystokens.py b/coverage/phystokens.py
index 7eebb8ad..2862490f 100644
--- a/coverage/phystokens.py
+++ b/coverage/phystokens.py
@@ -71,7 +71,7 @@ def source_token_lines(source):
     ws_tokens = [token.INDENT, token.DEDENT, token.NEWLINE, tokenize.NL]
     line = []
     col = 0
-    tokgen = tokenize.generate_tokens(StringIO(source).readline)
+    tokgen = tokenize.generate_tokens(StringIO(source.expandtabs(8)).readline)
     for ttype, ttext, (_, scol), (_, ecol), _ in phys_tokens(tokgen):
         mark_start = True
         for part in re.split('(\n)', ttext):
diff --git a/test/farm/html/run_tabbed.py b/test/farm/html/run_tabbed.py
index 88ffcaef..e7e60cec 100644
--- a/test/farm/html/run_tabbed.py
+++ b/test/farm/html/run_tabbed.py
@@ -10,12 +10,14 @@ def html_it():
 runfunc(html_it, rundir="src")
 
 # Editors like to change things, make sure our source file still has tabs.
-contains("src/tabbed.py", "\tif x:\t\t\t\t\t\t# look nice")
+contains("src/tabbed.py", "\tif x:\t\t\t\t\t# look nice")
 
 contains("html/tabbed.html",
-    ">&nbsp; &nbsp; <span class='key'>if</span> <span class='nam'>x</span>"
-    "<span class='op'>:</span>&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;"
-    " &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; <span class='com'># look nice</span>"
+    ">&nbsp; &nbsp; &nbsp; &nbsp; <span class='key'>if</span> "
+    "<span class='nam'>x</span><span class='op'>:</span>"
+    "&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; "
+    "&nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp;&nbsp; "
+    "<span class='com'># look nice</span>"   
     )
 
 doesnt_contain("html/tabbed.html", "\t")
diff --git a/test/farm/html/src/tabbed.py b/test/farm/html/src/tabbed.py
index fe426115..bc6bb456 100644
--- a/test/farm/html/src/tabbed.py
+++ b/test/farm/html/src/tabbed.py
@@ -2,7 +2,7 @@
 x = 1
 if x:
 	a = "Tabbed"				# Aligned comments
-	if x:						# look nice
+	if x:					# look nice
 		b = "No spaces"			# when they 
-	c = "Done"					# line up.
+	c = "Done"				# line up.
 
diff --git a/test/test_phystokens.py b/test/test_phystokens.py
index 64316034..ccbdb5a0 100644
--- a/test/test_phystokens.py
+++ b/test/test_phystokens.py
@@ -14,8 +14,15 @@ def foo():
   say('two = %d' % 2)
 """
 
+MIXED_WS = """\
+def hello():
+        a="Hello world!"
+\tb="indented"
+"""
+
 HERE = os.path.split(__file__)[0]
 
+
 class PhysTokensTest(CoverageTest):
     """Tests for Coverage.py's improver tokenizer."""
 
@@ -51,14 +58,29 @@ class PhysTokensTest(CoverageTest):
                 [('ws', '  '), ('nam', 'say'), ('op', '('),
                             ('str', "'two = %d'"), ('ws', ' '), ('op', '%'),
                             ('ws', ' '), ('num', '2'), ('op', ')')]
-            ]
-            )
+            ])
         self.check_tokenization(SIMPLE)
 
+    def test_tab_indentation(self):
+        # Mixed tabs and spaces...
+        self.assertEqual(list(source_token_lines(MIXED_WS)),
+            [
+                [('key', 'def'), ('ws', ' '), ('nam', 'hello'), ('op', '('),
+                            ('op', ')'), ('op', ':')],
+                [('ws', '        '), ('nam', 'a'), ('op', '='),
+                            ('str', '"Hello world!"')],
+                [('ws', '        '), ('nam', 'b'), ('op', '='),
+                            ('str', '"indented"')],
+            ])
+
     def test_tokenize_real_file(self):
+        # Check the tokenization of a real file (large, btw).
         real_file = os.path.join(HERE, "test_coverage.py")
         self.check_file_tokenization(real_file)
 
     def test_stress(self):
+        # Check the tokenization of a stress-test file.
         stress = os.path.join(HERE, "stress_phystoken.txt")
         self.check_file_tokenization(stress)
+
+        
\ No newline at end of file