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 31import logging 32import re 33 34 35_regexp_compile_cache = {} 36 37 38def match(pattern, string): 39 """Matches the string with the pattern, caching the compiled regexp.""" 40 if not pattern in _regexp_compile_cache: 41 _regexp_compile_cache[pattern] = re.compile(pattern) 42 return _regexp_compile_cache[pattern].match(string) 43 44 45def git_diff_to_svn_diff(line): 46 """Converts a git formatted diff line to a svn formatted line. 47 48 Args: 49 line: A string representing a line of the diff. 50 """ 51 conversion_patterns = (("^diff --git a/(.+) b/(?P<FilePath>.+)", lambda matched: "Index: " + matched.group('FilePath') + "\n"), 52 ("^new file.*", lambda matched: "\n"), 53 ("^index [0-9a-f]{7}\.\.[0-9a-f]{7} [0-9]{6}", lambda matched: "===================================================================\n"), 54 ("^--- a/(?P<FilePath>.+)", lambda matched: "--- " + matched.group('FilePath') + "\n"), 55 ("^\+\+\+ b/(?P<FilePath>.+)", lambda matched: "+++ " + matched.group('FilePath') + "\n")) 56 57 for pattern, conversion in conversion_patterns: 58 matched = match(pattern, line) 59 if matched: 60 return conversion(matched) 61 return line 62 63 64def get_diff_converter(first_diff_line): 65 """Gets a converter function of diff lines. 66 67 Args: 68 first_diff_line: The first filename line of a diff file. 69 If this line is git formatted, we'll return a 70 converter from git to SVN. 71 """ 72 if match(r"^diff --git a/", first_diff_line): 73 return git_diff_to_svn_diff 74 return lambda input: input 75 76 77_INITIAL_STATE = 1 78_DECLARED_FILE_PATH = 2 79_PROCESSING_CHUNK = 3 80 81 82class DiffFile: 83 """Contains the information for one file in a patch. 84 85 The field "lines" is a list which contains tuples in this format: 86 (deleted_line_number, new_line_number, line_string) 87 If deleted_line_number is zero, it means this line is newly added. 88 If new_line_number is zero, it means this line is deleted. 89 """ 90 91 def __init__(self, filename): 92 self.filename = filename 93 self.lines = [] 94 95 def add_new_line(self, line_number, line): 96 self.lines.append((0, line_number, line)) 97 98 def add_deleted_line(self, line_number, line): 99 self.lines.append((line_number, 0, line)) 100 101 def add_unchanged_line(self, deleted_line_number, new_line_number, line): 102 self.lines.append((deleted_line_number, new_line_number, line)) 103 104 105class DiffParser: 106 """A parser for a patch file. 107 108 The field "files" is a dict whose key is the filename and value is 109 a DiffFile object. 110 """ 111 112 def __init__(self, diff_input): 113 """Parses a diff. 114 115 Args: 116 diff_input: An iterable object. 117 """ 118 state = _INITIAL_STATE 119 120 self.files = {} 121 current_file = None 122 old_diff_line = None 123 new_diff_line = None 124 for line in diff_input: 125 line = line.rstrip("\n") 126 if state == _INITIAL_STATE: 127 transform_line = get_diff_converter(line) 128 line = transform_line(line) 129 130 file_declaration = match(r"^Index: (?P<FilePath>.+)", line) 131 if file_declaration: 132 filename = file_declaration.group('FilePath') 133 current_file = DiffFile(filename) 134 self.files[filename] = current_file 135 state = _DECLARED_FILE_PATH 136 continue 137 138 lines_changed = match(r"^@@ -(?P<OldStartLine>\d+)(,\d+)? \+(?P<NewStartLine>\d+)(,\d+)? @@", line) 139 if lines_changed: 140 if state != _DECLARED_FILE_PATH and state != _PROCESSING_CHUNK: 141 logging.error('Unexpected line change without file path declaration: %r' % line) 142 old_diff_line = int(lines_changed.group('OldStartLine')) 143 new_diff_line = int(lines_changed.group('NewStartLine')) 144 state = _PROCESSING_CHUNK 145 continue 146 147 if state == _PROCESSING_CHUNK: 148 if line.startswith('+'): 149 current_file.add_new_line(new_diff_line, line[1:]) 150 new_diff_line += 1 151 elif line.startswith('-'): 152 current_file.add_deleted_line(old_diff_line, line[1:]) 153 old_diff_line += 1 154 elif line.startswith(' '): 155 current_file.add_unchanged_line(old_diff_line, new_diff_line, line[1:]) 156 old_diff_line += 1 157 new_diff_line += 1 158 elif line == '\\ No newline at end of file': 159 # Nothing to do. We may still have some added lines. 160 pass 161 else: 162 logging.error('Unexpected diff format when parsing a chunk: %r' % line) 163