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 parsing and modifying ChangeLog files 30 31import codecs 32import fileinput # inplace file editing for set_reviewer_in_changelog 33import os.path 34import re 35import textwrap 36 37from webkitpy.common.system.deprecated_logging import log 38from webkitpy.common.config.committers import CommitterList 39from webkitpy.common.net.bugzilla import parse_bug_id_from_changelog 40 41 42class ChangeLogEntry(object): 43 # e.g. 2009-06-03 Eric Seidel <eric@webkit.org> 44 date_line_regexp = r'^(?P<date>\d{4}-\d{2}-\d{2})\s+(?P<name>.+?)\s+<(?P<email>[^<>]+)>$' 45 46 # e.g. == Rolled over to ChangeLog-2011-02-16 == 47 rolled_over_regexp = r'^== Rolled over to ChangeLog-\d{4}-\d{2}-\d{2} ==$' 48 49 def __init__(self, contents, committer_list=CommitterList()): 50 self._contents = contents 51 self._committer_list = committer_list 52 self._parse_entry() 53 54 def _parse_entry(self): 55 match = re.match(self.date_line_regexp, self._contents, re.MULTILINE) 56 if not match: 57 log("WARNING: Creating invalid ChangeLogEntry:\n%s" % self._contents) 58 59 # FIXME: group("name") does not seem to be Unicode? Probably due to self._contents not being unicode. 60 self._author_name = match.group("name") if match else None 61 self._author_email = match.group("email") if match else None 62 63 match = re.search("^\s+Reviewed by (?P<reviewer>.*?)[\.,]?\s*$", self._contents, re.MULTILINE) # Discard everything after the first period 64 self._reviewer_text = match.group("reviewer") if match else None 65 66 self._reviewer = self._committer_list.committer_by_name(self._reviewer_text) 67 self._author = self._committer_list.committer_by_email(self._author_email) or self._committer_list.committer_by_name(self._author_name) 68 69 def author_name(self): 70 return self._author_name 71 72 def author_email(self): 73 return self._author_email 74 75 def author(self): 76 return self._author # Might be None 77 78 # FIXME: Eventually we would like to map reviwer names to reviewer objects. 79 # See https://bugs.webkit.org/show_bug.cgi?id=26533 80 def reviewer_text(self): 81 return self._reviewer_text 82 83 def reviewer(self): 84 return self._reviewer # Might be None 85 86 def contents(self): 87 return self._contents 88 89 def bug_id(self): 90 return parse_bug_id_from_changelog(self._contents) 91 92 93# FIXME: Various methods on ChangeLog should move into ChangeLogEntry instead. 94class ChangeLog(object): 95 96 def __init__(self, path): 97 self.path = path 98 99 _changelog_indent = " " * 8 100 101 @staticmethod 102 def parse_latest_entry_from_file(changelog_file): 103 """changelog_file must be a file-like object which returns 104 unicode strings. Use codecs.open or StringIO(unicode()) 105 to pass file objects to this class.""" 106 date_line_regexp = re.compile(ChangeLogEntry.date_line_regexp) 107 rolled_over_regexp = re.compile(ChangeLogEntry.rolled_over_regexp) 108 entry_lines = [] 109 # The first line should be a date line. 110 first_line = changelog_file.readline() 111 assert(isinstance(first_line, unicode)) 112 if not date_line_regexp.match(first_line): 113 return None 114 entry_lines.append(first_line) 115 116 for line in changelog_file: 117 # If we've hit the next entry, return. 118 if date_line_regexp.match(line) or rolled_over_regexp.match(line): 119 # Remove the extra newline at the end 120 return ChangeLogEntry(''.join(entry_lines[:-1])) 121 entry_lines.append(line) 122 return None # We never found a date line! 123 124 def latest_entry(self): 125 # ChangeLog files are always UTF-8, we read them in as such to support Reviewers with unicode in their names. 126 changelog_file = codecs.open(self.path, "r", "utf-8") 127 try: 128 return self.parse_latest_entry_from_file(changelog_file) 129 finally: 130 changelog_file.close() 131 132 # _wrap_line and _wrap_lines exist to work around 133 # http://bugs.python.org/issue1859 134 135 def _wrap_line(self, line): 136 return textwrap.fill(line, 137 width=70, 138 initial_indent=self._changelog_indent, 139 # Don't break urls which may be longer than width. 140 break_long_words=False, 141 subsequent_indent=self._changelog_indent) 142 143 # Workaround as suggested by guido in 144 # http://bugs.python.org/issue1859#msg60040 145 146 def _wrap_lines(self, message): 147 lines = [self._wrap_line(line) for line in message.splitlines()] 148 return "\n".join(lines) 149 150 def update_with_unreviewed_message(self, message): 151 reviewed_by_regexp = re.compile( 152 "%sReviewed by NOBODY \(OOPS!\)\." % self._changelog_indent) 153 removing_boilerplate = False 154 # inplace=1 creates a backup file and re-directs stdout to the file 155 for line in fileinput.FileInput(self.path, inplace=1): 156 if reviewed_by_regexp.search(line): 157 message_lines = self._wrap_lines(message) 158 print reviewed_by_regexp.sub(message_lines, line), 159 # Remove all the ChangeLog boilerplate between the Reviewed by 160 # line and the first changed file. 161 removing_boilerplate = True 162 elif removing_boilerplate: 163 if line.find('*') >= 0: # each changed file is preceded by a * 164 removing_boilerplate = False 165 166 if not removing_boilerplate: 167 print line, 168 169 def set_reviewer(self, reviewer): 170 # inplace=1 creates a backup file and re-directs stdout to the file 171 for line in fileinput.FileInput(self.path, inplace=1): 172 # Trailing comma suppresses printing newline 173 print line.replace("NOBODY (OOPS!)", reviewer.encode("utf-8")), 174 175 def set_short_description_and_bug_url(self, short_description, bug_url): 176 message = "%s\n %s" % (short_description, bug_url) 177 for line in fileinput.FileInput(self.path, inplace=1): 178 print line.replace("Need a short description and bug URL (OOPS!)", message.encode("utf-8")), 179