Merge pull request #46 from volo-zyko/parse_patch_info_lines

Implement parsing of lines with extended patch info

tests/samples/git.diff

@@ -20,7 +20,7 @@ index c7921f5..8946660 100644
 +This is now updated.
 +
 +This is a new line.
-
+ 
  This will stay.
 \ No newline at end of file
 diff --git a/removed_file b/removed_file

tests/samples/sample5.diff

@@ -0,0 +1,29 @@
+=== modified file 'modified_file1'
+--- modified_file1	2013-10-13 23:53:13 +0000
++++ modified_file1	2013-10-13 23:53:26 +0000
+@@ -1,5 +1,7 @@
+ This is the original content.
+
+-This should be updated.
++This is now updated.
++
++This is a new line.
+
+ This will stay.
+\ No newline at end of file
+
+=== modified file 'modified_file2'
+--- modified_file2	2013-10-13 23:53:13 +0000
++++ modified_file2	2013-10-13 23:53:26 +0000
+@@ -1,5 +1,7 @@
+ This is the original content.
+
+-This should be updated.
++This is now updated.
++
++This is a new line.
+
+ This will stay.
+\ No newline at end of file
+
+

tests/samples/sample6.diff

@@ -0,0 +1,38 @@
+--- /path/to/original	''timestamp''
++++ /path/to/new	''timestamp''
+@@ -1,3 +1,9 @@
++This is an important
++notice! It should
++therefore be located at
++the beginning of this
++document!
++
+ This part of the
+ document has stayed the
+ same from version to
+@@ -5,16 +11,13 @@
+ be shown if it doesn't
+ change.  Otherwise, that
+ would not be helping to
+-compress the size of the
+-changes.
+-
+-This paragraph contains
+-text that is outdated.
+-It will be deleted in the
+-near future.
++compress anything.
+
+ It is important to spell
+-check this dokument. On
++check this document. On
+ the other hand, a
+ misspelled word isn't
+ the end of the world.
+ this paragraph needs to
+ be changed. Things can
+ be added after it.
++
++This paragraph contains
++important new additions
++to this document.

tests/samples/sample7.diff

@@ -0,0 +1,29 @@
+--- /path/to/original	''timestamp''
++++ /path/to/new	''timestamp''
+@@ -1,3 +1,9 @@
++This is an important
++notice! It should
++therefore be located at
++the beginning of this
++document!
++
+ This part of the
+ document has stayed the
+ same from version to
+@@ -5,16 +11,13 @@
+ be shown if it doesn't
+ change.  Otherwise, that
+ would not be helping to
+-compress the size of the
+-changes.
+-
+-This paragraph contains
+-text that is outdated.
++compress anything.
+
+ It is important to spell
+-check this dokument. On
++check this document. On
+ the other hand, a
+ misspelled word isn't
+ the end of the world.

tests/test_parser.py

@@ -92,12 +92,27 @@ def test_preserve_dos_line_endings(self):
         added_unicode_line = res.added_files[0][0][1]
         self.assertEqual(added_unicode_line.value, 'holá mundo!\r\n')
 
+    def test_preserve_dos_line_endings_empty_line_type(self):
+        utf8_file = os.path.join(self.samples_dir, 'samples/sample5.diff')
+        with open(utf8_file, 'rb') as diff_file:
+            res = PatchSet(diff_file, encoding='utf-8')
+
+        # 2 files updated by diff
+        self.assertEqual(len(res), 2)
+        modified_unicode_line = res.modified_files[0][0][6]
+        self.assertEqual(modified_unicode_line.value, '\r\n')
+        self.assertEqual(modified_unicode_line.line_type, ' ')
+
+        modified_unicode_line = res.modified_files[1][0][6]
+        self.assertEqual(modified_unicode_line.value, '\n')
+        self.assertEqual(modified_unicode_line.line_type, ' ')
+
     def test_print_hunks_without_gaps(self):
         with codecs.open(self.sample_file, 'r', encoding='utf-8') as diff_file:
             res = PatchSet(diff_file)
         lines = unicode(res).splitlines()
-        self.assertEqual(lines[12], '@@ -5,16 +11,10 @@ ')
-        self.assertEqual(lines[31], '@@ -22,3 +22,7 @@ ')
+        self.assertEqual(lines[12], '@@ -5,16 +11,10 @@')
+        self.assertEqual(lines[31], '@@ -22,3 +22,7 @@')
 
     def test_parse_sample(self):
         """Parse sample file."""
@@ -181,20 +196,32 @@ def test_patchset_from_bytes_string(self):
         self.assertEqual(ps1, ps2)
 
     def test_patchset_string_input(self):
-            with codecs.open(self.sample_file, 'r', encoding='utf-8') as diff_file:
-                diff_data = diff_file.read()
-                ps1 = PatchSet(diff_data)
+        with codecs.open(self.sample_file, 'r', encoding='utf-8') as diff_file:
+            diff_data = diff_file.read()
+            ps1 = PatchSet(diff_data)
 
-            with codecs.open(self.sample_file, 'r', encoding='utf-8') as diff_file:
-                ps2 = PatchSet(diff_file)
+        with codecs.open(self.sample_file, 'r', encoding='utf-8') as diff_file:
+            ps2 = PatchSet(diff_file)
 
-            self.assertEqual(ps1, ps2)
+        self.assertEqual(ps1, ps2)
 
     def test_parse_malformed_diff(self):
         """Parse malformed file."""
         with open(self.sample_bad_file) as diff_file:
             self.assertRaises(UnidiffParseError, PatchSet, diff_file)
 
+    def test_parse_malformed_diff_longer_than_expected(self):
+        """Parse malformed file with non-terminated hunk."""
+        utf8_file = os.path.join(self.samples_dir, 'samples/sample6.diff')
+        with open(utf8_file, 'r') as diff_file:
+            self.assertRaises(UnidiffParseError, PatchSet, diff_file)
+
+    def test_parse_malformed_diff_shorter_than_expected(self):
+        """Parse malformed file with non-terminated hunk."""
+        utf8_file = os.path.join(self.samples_dir, 'samples/sample7.diff')
+        with open(utf8_file, 'r') as diff_file:
+            self.assertRaises(UnidiffParseError, PatchSet, diff_file)
+
     def test_diff_lines_linenos(self):
         with open(self.sample_file, 'rb') as diff_file:
             res = PatchSet(diff_file, encoding='utf-8')
@@ -295,3 +322,8 @@ def test_samples(self):
 
             self.assertEqual(res.added, 7)
             self.assertEqual(res.removed, 4)
+
+            # check that original diffs and those produced
+            # by unidiff are the same
+            with codecs.open(file_path, 'r', encoding='utf-8') as diff_file:
+                self.assertEqual(diff_file.read(), str(res))

unidiff/constants.py

@@ -44,7 +44,9 @@
 # -  deleted line
 # \  No newline case
 RE_HUNK_BODY_LINE = re.compile(
-    r'^(?P<line_type>[- \n\+\\])(?P<value>.*)', re.DOTALL)
+    r'^(?P<line_type>[- \+\\])(?P<value>.*)', re.DOTALL)
+RE_HUNK_EMPTY_BODY_LINE = re.compile(
+    r'^(?P<line_type>[- \+\\]?)(?P<value>[\r\n]{1,2})', re.DOTALL)
 
 RE_NO_NEWLINE_MARKER = re.compile(r'^\\ No newline at end of file')
 
@@ -53,6 +55,6 @@
 LINE_TYPE_ADDED = '+'
 LINE_TYPE_REMOVED = '-'
 LINE_TYPE_CONTEXT = ' '
-LINE_TYPE_EMPTY = '\n'
+LINE_TYPE_EMPTY = ''
 LINE_TYPE_NO_NEWLINE = '\\'
 LINE_VALUE_NO_NEWLINE = ' No newline at end of file'