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_log = logging.getLogger("webkitpy.common.checkout.diff_parser") 35 36 37# FIXME: This is broken. We should compile our regexps up-front 38# instead of using a custom cache. 39_regexp_compile_cache = {} 40 41 42# FIXME: This function should be removed. 43def match(pattern, string): 44 """Matches the string with the pattern, caching the compiled regexp.""" 45 if not pattern in _regexp_compile_cache: 46 _regexp_compile_cache[pattern] = re.compile(pattern) 47 return _regexp_compile_cache[pattern].match(string) 48 49 50# FIXME: This belongs on DiffParser (e.g. as to_svn_diff()). 51def git_diff_to_svn_diff(line): 52 """Converts a git formatted diff line to a svn formatted line. 53 54 Args: 55 line: A string representing a line of the diff. 56 """ 57 # FIXME: This list should be a class member on DiffParser. 58 # These regexp patterns should be compiled once instead of every time. 59 conversion_patterns = (("^diff --git \w/(.+) \w/(?P<FilePath>.+)", lambda matched: "Index: " + matched.group('FilePath') + "\n"), 60 ("^new file.*", lambda matched: "\n"), 61 ("^index [0-9a-f]{7}\.\.[0-9a-f]{7} [0-9]{6}", lambda matched: "===================================================================\n"), 62 ("^--- \w/(?P<FilePath>.+)", lambda matched: "--- " + matched.group('FilePath') + "\n"), 63 ("^\+\+\+ \w/(?P<FilePath>.+)", lambda matched: "+++ " + matched.group('FilePath') + "\n")) 64 65 for pattern, conversion in conversion_patterns: 66 matched = match(pattern, line) 67 if matched: 68 return conversion(matched) 69 return line 70 71 72# FIXME: This method belongs on DiffParser 73def get_diff_converter(first_diff_line): 74 """Gets a converter function of diff lines. 75 76 Args: 77 first_diff_line: The first filename line of a diff file. 78 If this line is git formatted, we'll return a 79 converter from git to SVN. 80 """ 81 if match(r"^diff --git \w/", first_diff_line): 82 return git_diff_to_svn_diff 83 return lambda input: input 84 85 86_INITIAL_STATE = 1 87_DECLARED_FILE_PATH = 2 88_PROCESSING_CHUNK = 3 89 90 91class DiffFile(object): 92 """Contains the information for one file in a patch. 93 94 The field "lines" is a list which contains tuples in this format: 95 (deleted_line_number, new_line_number, line_string) 96 If deleted_line_number is zero, it means this line is newly added. 97 If new_line_number is zero, it means this line is deleted. 98 """ 99 # FIXME: Tuples generally grow into classes. We should consider 100 # adding a DiffLine object. 101 102 def added_or_modified_line_numbers(self): 103 # This logic was moved from patchreader.py, but may not be 104 # the right API for this object long-term. 105 return [line[1] for line in self.lines if not line[0]] 106 107 def __init__(self, filename): 108 self.filename = filename 109 self.lines = [] 110 111 def add_new_line(self, line_number, line): 112 self.lines.append((0, line_number, line)) 113 114 def add_deleted_line(self, line_number, line): 115 self.lines.append((line_number, 0, line)) 116 117 def add_unchanged_line(self, deleted_line_number, new_line_number, line): 118 self.lines.append((deleted_line_number, new_line_number, line)) 119 120 121# If this is going to be called DiffParser, it should be a re-useable parser. 122# Otherwise we should rename it to ParsedDiff or just Diff. 123class DiffParser(object): 124 """A parser for a patch file. 125 126 The field "files" is a dict whose key is the filename and value is 127 a DiffFile object. 128 """ 129 130 def __init__(self, diff_input): 131 """Parses a diff. 132 133 Args: 134 diff_input: An iterable object. 135 """ 136 self.files = self._parse_into_diff_files(diff_input) 137 138 # FIXME: This function is way too long and needs to be broken up. 139 def _parse_into_diff_files(self, diff_input): 140 files = {} 141 state = _INITIAL_STATE 142 current_file = None 143 old_diff_line = None 144 new_diff_line = None 145 for line in diff_input: 146 line = line.rstrip("\n") 147 if state == _INITIAL_STATE: 148 transform_line = get_diff_converter(line) 149 line = transform_line(line) 150 151 file_declaration = match(r"^Index: (?P<FilePath>.+)", line) 152 if file_declaration: 153 filename = file_declaration.group('FilePath') 154 current_file = DiffFile(filename) 155 files[filename] = current_file 156 state = _DECLARED_FILE_PATH 157 continue 158 159 lines_changed = match(r"^@@ -(?P<OldStartLine>\d+)(,\d+)? \+(?P<NewStartLine>\d+)(,\d+)? @@", line) 160 if lines_changed: 161 if state != _DECLARED_FILE_PATH and state != _PROCESSING_CHUNK: 162 _log.error('Unexpected line change without file path ' 163 'declaration: %r' % line) 164 old_diff_line = int(lines_changed.group('OldStartLine')) 165 new_diff_line = int(lines_changed.group('NewStartLine')) 166 state = _PROCESSING_CHUNK 167 continue 168 169 if state == _PROCESSING_CHUNK: 170 if line.startswith('+'): 171 current_file.add_new_line(new_diff_line, line[1:]) 172 new_diff_line += 1 173 elif line.startswith('-'): 174 current_file.add_deleted_line(old_diff_line, line[1:]) 175 old_diff_line += 1 176 elif line.startswith(' '): 177 current_file.add_unchanged_line(old_diff_line, new_diff_line, line[1:]) 178 old_diff_line += 1 179 new_diff_line += 1 180 elif line == '\\ No newline at end of file': 181 # Nothing to do. We may still have some added lines. 182 pass 183 else: 184 _log.error('Unexpected diff format when parsing a ' 185 'chunk: %r' % line) 186 return files 187