diff contrib/simplemerge @ 4363:2e3c54fb79a3

actually port simplemerge to hg

- use bdiff instead of patiencediff;  this is a larger change, since
  bdiff works on 2 multi-line strings, while patiencediff works on 2
  lists;

- rename the main class from Merge3 to Merge3Text and add a Merge3
  class that derives from Merge3Text.  This new Merge3 class has
  the same interface from the original class, so that the tests
  still work;

  - Merge3 uses util.binary to detect binary data and raises
    util.Abort instead of a specific exception;

- don't use the @decorator syntax, to keep python2.3 compatibility;

- the test uses unittest, which likes to print how long it took to
  run.  This obviously doesn't play too well with hg's test suite,
  so we override time.time to fool unittest;

- one test has a different (but still valid) output because of the
  different diff algorithm used;

- the TestCase class used by bzr has some extras to help debugging.
  test-merge3.py used 2 of them:

  - log method to log some data

  - assertEqualDiff method to ease viewing diffs of diffs

  We add a dummy log method and use regular assertEquals instead of
  assertEqualDiff.

- make simplemerge executable and add "#!/usr/bin/env python" header

--- a/contrib/simplemerge	Mon Apr 16 20:17:39 2007 -0300
+++ b/contrib/simplemerge	Mon Apr 16 20:17:39 2007 -0300
@@ -1,3 +1,4 @@
+#!/usr/bin/env python
 # Copyright (C) 2004, 2005 Canonical Ltd
 #
 # This program is free software; you can redistribute it and/or modify
@@ -19,9 +20,12 @@
 # s: "i hate that."
 
 
-from bzrlib.errors import CantReprocessAndShowBase
-import bzrlib.patiencediff
-from bzrlib.textfile import check_text_lines
+from mercurial import util, mdiff
+from mercurial.i18n import _
+
+
+class CantReprocessAndShowBase(Exception):
+    pass
 
 
 def intersect(ra, rb):
@@ -61,16 +65,21 @@
 
 
 
-class Merge3(object):
+class Merge3Text(object):
     """3-way merge of texts.
 
-    Given BASE, OTHER, THIS, tries to produce a combined text
-    incorporating the changes from both BASE->OTHER and BASE->THIS.
-    All three will typically be sequences of lines."""
-    def __init__(self, base, a, b):
-        check_text_lines(base)
-        check_text_lines(a)
-        check_text_lines(b)
+    Given strings BASE, OTHER, THIS, tries to produce a combined text
+    incorporating the changes from both BASE->OTHER and BASE->THIS."""
+    def __init__(self, basetext, atext, btext, base=None, a=None, b=None):
+        self.basetext = basetext
+        self.atext = atext
+        self.btext = btext
+        if base is None:
+            base = mdiff.splitnewlines(basetext)
+        if a is None:
+            a = mdiff.splitnewlines(atext)
+        if b is None:
+            b = mdiff.splitnewlines(btext)
         self.base = base
         self.a = a
         self.b = b
@@ -300,8 +309,8 @@
             type, iz, zmatch, ia, amatch, ib, bmatch = region
             a_region = self.a[ia:amatch]
             b_region = self.b[ib:bmatch]
-            matches = bzrlib.patiencediff.PatienceSequenceMatcher(
-                    None, a_region, b_region).get_matching_blocks()
+            matches = mdiff.get_matching_blocks(''.join(a_region),
+                                                ''.join(b_region))
             next_a = ia
             next_b = ib
             for region_ia, region_ib, region_len in matches[:-1]:
@@ -319,10 +328,10 @@
                 yield reg
 
 
-    @staticmethod
     def mismatch_region(next_a, region_ia,  next_b, region_ib):
         if next_a < region_ia or next_b < region_ib:
             return 'conflict', None, None, next_a, region_ia, next_b, region_ib
+    mismatch_region = staticmethod(mismatch_region)
             
 
     def find_sync_regions(self):
@@ -333,10 +342,8 @@
         """
 
         ia = ib = 0
-        amatches = bzrlib.patiencediff.PatienceSequenceMatcher(
-                None, self.base, self.a).get_matching_blocks()
-        bmatches = bzrlib.patiencediff.PatienceSequenceMatcher(
-                None, self.base, self.b).get_matching_blocks()
+        amatches = mdiff.get_matching_blocks(self.basetext, self.atext)
+        bmatches = mdiff.get_matching_blocks(self.basetext, self.btext)
         len_a = len(amatches)
         len_b = len(bmatches)
 
@@ -392,10 +399,8 @@
 
     def find_unconflicted(self):
         """Return a list of ranges in base that are not conflicted."""
-        am = bzrlib.patiencediff.PatienceSequenceMatcher(
-                None, self.base, self.a).get_matching_blocks()
-        bm = bzrlib.patiencediff.PatienceSequenceMatcher(
-                None, self.base, self.b).get_matching_blocks()
+        am = mdiff.get_matching_blocks(self.basetext, self.atext)
+        bm = mdiff.get_matching_blocks(self.basetext, self.btext)
 
         unc = []
 
@@ -418,6 +423,22 @@
         return unc
 
 
+# bzr compatible interface, for the tests
+class Merge3(Merge3Text):
+    """3-way merge of texts.
+
+    Given BASE, OTHER, THIS, tries to produce a combined text
+    incorporating the changes from both BASE->OTHER and BASE->THIS.
+    All three will typically be sequences of lines."""
+    def __init__(self, base, a, b):
+        basetext = '\n'.join([i.strip('\n') for i in base] + [''])
+        atext = '\n'.join([i.strip('\n') for i in a] + [''])
+        btext = '\n'.join([i.strip('\n') for i in b] + [''])
+        if util.binary(basetext) or util.binary(atext) or util.binary(btext):
+            raise util.Abort(_("don't know how to merge binary files"))
+        Merge3Text.__init__(self, basetext, atext, btext, base, a, b)
+
+
 def main(argv):
     # as for diff3 and meld the syntax is "MINE BASE OTHER"
     a = file(argv[1], 'rt').readlines()