1 # Copyright (C) 2009 Google Inc. All rights reserved.

     2 #

     3 # Redistribution and use in source and binary forms, with or without

     4 # modification, are permitted provided that the following conditions are

     5 # met:

     6 #

     7 #    * Redistributions of source code must retain the above copyright

     8 # notice, this list of conditions and the following disclaimer.

     9 #    * Redistributions in binary form must reproduce the above

    10 # copyright notice, this list of conditions and the following disclaimer

    11 # in the documentation and/or other materials provided with the

    12 # distribution.

    13 #    * Neither the name of Google Inc. nor the names of its

    14 # contributors may be used to endorse or promote products derived from

    15 # this software without specific prior written permission.

    16 #

    17 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS

    18 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT

    19 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR

    20 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT

    21 # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,

    22 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT

    23 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,

    24 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY

    25 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT

    26 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE

    27 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

    28 

    29 """WebKit's Python module for interacting with patches."""

    30 

    31 import logging

    32 import re

    33 

    34 _log = logging.getLogger("webkitpy.common.checkout.diff_parser")

    35 

    36 _regexp_compile_cache = {}

    37 

    38 

    39 def match(pattern, string):

    40     """Matches the string with the pattern, caching the compiled regexp."""

    41     if not pattern in _regexp_compile_cache:

    42         _regexp_compile_cache[pattern] = re.compile(pattern)

    43     return _regexp_compile_cache[pattern].match(string)

    44 

    45 

    46 def git_diff_to_svn_diff(line):

    47     """Converts a git formatted diff line to a svn formatted line.

    48 

    49     Args:

    50       line: A string representing a line of the diff.

    51     """

    52     conversion_patterns = (("^diff --git \w/(.+) \w/(?P<FilePath>.+)", lambda matched: "Index: " + matched.group('FilePath') + "\n"),

    53                            ("^new file.*", lambda matched: "\n"),

    54                            ("^index [0-9a-f]{7}\.\.[0-9a-f]{7} [0-9]{6}", lambda matched: "===================================================================\n"),

    55                            ("^--- \w/(?P<FilePath>.+)", lambda matched: "--- " + matched.group('FilePath') + "\n"),

    56                            ("^\+\+\+ \w/(?P<FilePath>.+)", lambda matched: "+++ " + matched.group('FilePath') + "\n"))

    57 

    58     for pattern, conversion in conversion_patterns:

    59         matched = match(pattern, line)

    60         if matched:

    61             return conversion(matched)

    62     return line

    63 

    64 

    65 def get_diff_converter(first_diff_line):

    66     """Gets a converter function of diff lines.

    67 

    68     Args:

    69       first_diff_line: The first filename line of a diff file.

    70                        If this line is git formatted, we'll return a

    71                        converter from git to SVN.

    72     """

    73     if match(r"^diff --git \w/", first_diff_line):

    74         return git_diff_to_svn_diff

    75     return lambda input: input

    76 

    77 

    78 _INITIAL_STATE = 1

    79 _DECLARED_FILE_PATH = 2

    80 _PROCESSING_CHUNK = 3

    81 

    82 

    83 class DiffFile:

    84     """Contains the information for one file in a patch.

    85 

    86     The field "lines" is a list which contains tuples in this format:

    87        (deleted_line_number, new_line_number, line_string)

    88     If deleted_line_number is zero, it means this line is newly added.

    89     If new_line_number is zero, it means this line is deleted.

    90     """

    91 

    92     def __init__(self, filename):

    93         self.filename = filename

    94         self.lines = []

    95 

    96     def add_new_line(self, line_number, line):

    97         self.lines.append((0, line_number, line))

    98 

    99     def add_deleted_line(self, line_number, line):

   100         self.lines.append((line_number, 0, line))

   101 

   102     def add_unchanged_line(self, deleted_line_number, new_line_number, line):

   103         self.lines.append((deleted_line_number, new_line_number, line))

   104 

   105 

   106 class DiffParser:

   107     """A parser for a patch file.

   108 

   109     The field "files" is a dict whose key is the filename and value is

   110     a DiffFile object.

   111     """

   112 

   113     def __init__(self, diff_input):

   114         """Parses a diff.

   115 

   116         Args:

   117           diff_input: An iterable object.

   118         """

   119         state = _INITIAL_STATE

   120 

   121         self.files = {}

   122         current_file = None

   123         old_diff_line = None

   124         new_diff_line = None

   125         for line in diff_input:

   126             line = line.rstrip("\n")

   127             if state == _INITIAL_STATE:

   128                 transform_line = get_diff_converter(line)

   129             line = transform_line(line)

   130 

   131             file_declaration = match(r"^Index: (?P<FilePath>.+)", line)

   132             if file_declaration:

   133                 filename = file_declaration.group('FilePath')

   134                 current_file = DiffFile(filename)

   135                 self.files[filename] = current_file

   136                 state = _DECLARED_FILE_PATH

   137                 continue

   138 

   139             lines_changed = match(r"^@@ -(?P<OldStartLine>\d+)(,\d+)? \+(?P<NewStartLine>\d+)(,\d+)? @@", line)

   140             if lines_changed:

   141                 if state != _DECLARED_FILE_PATH and state != _PROCESSING_CHUNK:

   142                     _log.error('Unexpected line change without file path '

   143                                'declaration: %r' % line)

   144                 old_diff_line = int(lines_changed.group('OldStartLine'))

   145                 new_diff_line = int(lines_changed.group('NewStartLine'))

   146                 state = _PROCESSING_CHUNK

   147                 continue

   148 

   149             if state == _PROCESSING_CHUNK:

   150                 if line.startswith('+'):

   151                     current_file.add_new_line(new_diff_line, line[1:])

   152                     new_diff_line += 1

   153                 elif line.startswith('-'):

   154                     current_file.add_deleted_line(old_diff_line, line[1:])

   155                     old_diff_line += 1

   156                 elif line.startswith(' '):

   157                     current_file.add_unchanged_line(old_diff_line, new_diff_line, line[1:])

   158                     old_diff_line += 1

   159                     new_diff_line += 1

   160                 elif line == '\\ No newline at end of file':

   161                     # Nothing to do.  We may still have some added lines.

   162                     pass

   163                 else:

   164                     _log.error('Unexpected diff format when parsing a '

   165                                'chunk: %r' % line)