Patch #914575: difflib side by side diff support, diff.py s/b/s HTML option.

Doc/lib/libdifflib.tex

@@ -52,6 +52,79 @@
   characters.
 \end{classdesc*}
 
+\begin{classdesc*}{HtmlDiff}
+
+  This class can be used to create an HTML table (or a complete HTML file
+  containing the table) showing a side by side, line by line comparision
+  of text with inter-line and intra-line change highlights.  The table can 
+  be generated in either full or contextual difference mode.
+
+  The constructor for this class is:
+
+  \begin{funcdesc}{__init__}{
+    \optional{, tabsize
+    \optional{, wrapcolumn
+    \optional{, linejunk
+    \optional{, charjunk}}}}}
+
+    Initializes instance of \class{HtmlDiff}.  
+
+    \var{tabsize} is an optional keyword argument to specify tab stop spacing 
+    and defaults to \code{8}.
+
+    \var{wrapcolumn} is an optional keyword to specify column number where 
+    lines are broken and wrapped, defaults to \code{None} where lines are not 
+    wrapped.
+
+    \var{linejunk} and \var{charjunk} are optional keyword arguments passed 
+    into \code{ndiff()} (used to by \class{HtmlDiff} to generate the 
+    side by side HTML differences).  See \code{ndiff()} documentation for 
+    argument default values and descriptions.
+  \end{funcdesc}  
+
+  The following methods are public:
+
+  \begin{funcdesc}{make_file}{fromlines, tolines
+    \optional{, fromdesc
+    \optional{, todesc
+    \optional{, context
+    \optional{, numlines}}}}}
+    Compares \var{fromlines} and \var{tolines} (lists of strings) and returns
+    a string which is a complete HTML file containing a table showing line by
+    line differences with inter-line and intra-line changes highlighted.
+    
+    \var{fromdesc} and \var{todesc} are optional keyword arguments to specify 
+    from/to file column header strings (both default to an empty string).  
+    
+    \var{context} and \var{numlines} are both optional keyword arguments.
+    Set \var{context} to \code{True} when contextual differences are to be 
+    shown, else the default is \code{False} to show the full files.  
+    \var{numlines} defaults to \code{5}.  When \var{context} is \code{True}
+    \var{numlines} controls the number of context lines which surround the 
+    difference highlights.  When \var{context} is \code{False} \var{numlines}
+    controls the number of lines which are shown before a difference 
+    highlight when using the "next" hyperlinks (setting to zero would cause
+    the "next" hyperlinks to place the next difference highlight at the top of
+    the browser without any leading context).
+  \end{funcdesc}  
+
+  \begin{funcdesc}{make_table}{fromlines, tolines
+    \optional{, fromdesc
+    \optional{, todesc
+    \optional{, context}}}}
+    Compares \var{fromlines} and \var{tolines} (lists of strings) and returns
+    a string which is a complete HTML table showing line by line differences
+    with inter-line and intra-line changes highlighted.
+    
+    The arguments of this method are a subset of those for the 
+    \code{make_file} method.  Refer to the \code{make_file} method 
+    documentation.
+  \end{funcdesc}  
+
+  \file{Tools/scripts/ndiff.py} is a command-line front-end to this class
+  and contains a good example of its use.
+\end{classdesc*}
+
 \begin{funcdesc}{context_diff}{a, b\optional{, fromfile\optional{, tofile
 	\optional{, fromfiledate\optional{, tofiledate\optional{, n
 	\optional{, lineterm}}}}}}}

Lib/test/test_difflib.py

 import difflib
-from test import test_support
+from test.test_support import run_unittest, findfile
 import unittest
 import doctest
 
@@ -19,6 +19,130 @@ class TestSFbugs(unittest.TestCase):
         diff_gen = difflib.unified_diff([], [])
         self.assertRaises(StopIteration, diff_gen.next)
 
+patch914575_from1 = """
+   1. Beautiful is beTTer than ugly.
+   2. Explicit is better than implicit.
+   3. Simple is better than complex.
+   4. Complex is better than complicated.
+"""
+
+patch914575_to1 = """
+   1. Beautiful is better than ugly.
+   3.   Simple is better than complex.
+   4. Complicated is better than complex.
+   5. Flat is better than nested.
+"""
+
+patch914575_from2 = """
+\t\tLine 1: preceeded by from:[tt] to:[ssss]
+  \t\tLine 2: preceeded by from:[sstt] to:[sssst]
+  \t \tLine 3: preceeded by from:[sstst] to:[ssssss]
+Line 4:  \thas from:[sst] to:[sss] after :
+Line 5: has from:[t] to:[ss] at end\t
+"""
+
+patch914575_to2 = """
+    Line 1: preceeded by from:[tt] to:[ssss]
+    \tLine 2: preceeded by from:[sstt] to:[sssst]
+      Line 3: preceeded by from:[sstst] to:[ssssss]
+Line 4:   has from:[sst] to:[sss] after :
+Line 5: has from:[t] to:[ss] at end  
+"""
+
+patch914575_from3 = """line 0
+1234567890123456789012345689012345
+line 1
+line 2
+line 3
+line 4   changed 
+line 5   changed 
+line 6   changed 
+line 7
+line 8  subtracted
+line 9
+1234567890123456789012345689012345
+short line
+just fits in!!
+just fits in two lines yup!!
+the end"""
+
+patch914575_to3 = """line 0
+1234567890123456789012345689012345
+line 1
+line 2    added
+line 3
+line 4   chanGEd 
+line 5a  chanGed 
+line 6a  changEd 
+line 7
+line 8
+line 9
+1234567890
+another long line that needs to be wrapped
+just fitS in!!
+just fits in two lineS yup!!
+the end"""
+
+class TestSFpatches(unittest.TestCase):
+
+    def test_html_diff(self):
+        # Check SF patch 914575 for generating HTML differences
+        f1a = ((patch914575_from1 + '123\n'*10)*3)
+        t1a = (patch914575_to1 + '123\n'*10)*3
+        f1b = '456\n'*10 + f1a
+        t1b = '456\n'*10 + t1a
+        f1a = f1a.splitlines()
+        t1a = t1a.splitlines()
+        f1b = f1b.splitlines()
+        t1b = t1b.splitlines()
+        f2 = patch914575_from2.splitlines()
+        t2 = patch914575_to2.splitlines()
+        f3 = patch914575_from3
+        t3 = patch914575_to3
+        i = difflib.HtmlDiff()
+        j = difflib.HtmlDiff(tabsize=2)
+        k = difflib.HtmlDiff(wrapcolumn=14)
+        
+        full = i.make_file(f1a,t1a,'from','to',context=False,numlines=5)
+        tables = '\n'.join(
+            [
+             '<h2>Context (first diff within numlines=5(default))</h2>', 
+             i.make_table(f1a,t1a,'from','to',context=True),
+             '<h2>Context (first diff after numlines=5(default))</h2>', 
+             i.make_table(f1b,t1b,'from','to',context=True),
+             '<h2>Context (numlines=6)</h2>', 
+             i.make_table(f1a,t1a,'from','to',context=True,numlines=6),
+             '<h2>Context (numlines=0)</h2>', 
+             i.make_table(f1a,t1a,'from','to',context=True,numlines=0),
+             '<h2>Same Context</h2>', 
+             i.make_table(f1a,f1a,'from','to',context=True),
+             '<h2>Same Full</h2>', 
+             i.make_table(f1a,f1a,'from','to',context=False),
+             '<h2>Empty Context</h2>',
+             i.make_table([],[],'from','to',context=True),
+             '<h2>Empty Full</h2>',
+             i.make_table([],[],'from','to',context=False),
+             '<h2>tabsize=2</h2>',
+             j.make_table(f2,t2),
+             '<h2>tabsize=default</h2>',
+             i.make_table(f2,t2),
+             '<h2>Context (wrapcolumn=14,numlines=0)</h2>',
+             k.make_table(f3.splitlines(),t3.splitlines(),context=True,numlines=0),
+             '<h2>wrapcolumn=14,splitlines()</h2>',
+             k.make_table(f3.splitlines(),t3.splitlines()),
+             '<h2>wrapcolumn=14,splitlines(True)</h2>',
+             k.make_table(f3.splitlines(True),t3.splitlines(True)),
+             ])
+        actual = full.replace('</body>','\n%s\n</body>' % tables)
+        # temporarily uncomment next three lines to baseline this test
+        #f = open('test_difflib_expect.html','w')
+        #f.write(actual)
+        #f.close()
+        expect = open(findfile('test_difflib_expect.html')).read()
+        
+                          
+        self.assertEqual(actual,expect)
+
 Doctests = doctest.DocTestSuite(difflib)
 
-test_support.run_unittest(TestSFbugs, Doctests)
+run_unittest(TestSFpatches, TestSFbugs, Doctests)

Misc/ACKS

@@ -201,6 +201,7 @@ Raymund Galvin
 Nitin Ganatra
 Fred Gansevles
 Lars Marius Garshol
+Dan Gass
 Andrew Gaul
 Stephen M. Gava
 Harry Henry Gebel

Misc/NEWS

@@ -47,6 +47,8 @@ Core and builtins
 Extension modules
 -----------------
 
+- difflib now supports HTML side-by-side diff.
+
 - os.urandom has been added for systems that support sources of random
   data.
 
@@ -63,6 +65,8 @@ Extension modules
 Library
 -------
 
+- difflib and diff.py can now generate HTML.
+
 - bdist_rpm now includes version and release in the BuildRoot, and
   replaces - by ``_`` in version and release.
 

Tools/scripts/diff.py

-""" Command line interface to difflib.py providing diffs in three formats:
+""" Command line interface to difflib.py providing diffs in four formats:
 
 * ndiff:    lists every line and highlights interline changes.
-* context:  highlights clusters of changes in a before/after format
+* context:  highlights clusters of changes in a before/after format.
 * unified:  highlights clusters of changes in an inline format.
+* html:     generates side by side comparison with change highlights.
 
 """
 
@@ -14,6 +15,7 @@ def main():
     parser = optparse.OptionParser(usage)
     parser.add_option("-c", action="store_true", default=False, help='Produce a context format diff (default)')
     parser.add_option("-u", action="store_true", default=False, help='Produce a unified format diff')
+    parser.add_option("-m", action="store_true", default=False, help='Produce HTML side by side diff (can use -c and -l in conjunction)')
     parser.add_option("-n", action="store_true", default=False, help='Produce a ndiff format diff')
     parser.add_option("-l", "--lines", type="int", default=3, help='Set number of context lines (default 3)')
     (options, args) = parser.parse_args()
@@ -36,6 +38,8 @@ def main():
         diff = difflib.unified_diff(fromlines, tolines, fromfile, tofile, fromdate, todate, n=n)
     elif options.n:
         diff = difflib.ndiff(fromlines, tolines)
+    elif options.m:
+        diff = difflib.HtmlDiff().make_file(fromlines,tolines,fromfile,tofile,context=options.c,numlines=n)
     else:
         diff = difflib.context_diff(fromlines, tolines, fromfile, tofile, fromdate, todate, n=n)