• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# Copyright (C) 2009 Google Inc. All rights reserved.
2# Copyright (C) 2010 Chris Jerdonek (chris.jerdonek@gmail.com)
3# Copyright (C) 2010 ProFUSION embedded systems
4#
5# Redistribution and use in source and binary forms, with or without
6# modification, are permitted provided that the following conditions are
7# met:
8#
9#     * Redistributions of source code must retain the above copyright
10# notice, this list of conditions and the following disclaimer.
11#     * Redistributions in binary form must reproduce the above
12# copyright notice, this list of conditions and the following disclaimer
13# in the documentation and/or other materials provided with the
14# distribution.
15#     * Neither the name of Google Inc. nor the names of its
16# contributors may be used to endorse or promote products derived from
17# this software without specific prior written permission.
18#
19# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30
31"""Supports reading and processing text files."""
32
33import codecs
34import logging
35import os
36import sys
37
38
39_log = logging.getLogger(__name__)
40
41
42class TextFileReader(object):
43
44    """Supports reading and processing text files.
45
46       Attributes:
47         file_count: The total number of files passed to this instance
48                     for processing, including non-text files and files
49                     that should be skipped.
50         delete_only_file_count: The total number of files that are not
51                                 processed this instance actually because
52                                 the files don't have any modified lines
53                                 but should be treated as processed.
54
55    """
56
57    def __init__(self, processor):
58        """Create an instance.
59
60        Arguments:
61          processor: A ProcessorBase instance.
62
63        """
64        self._processor = processor
65        self.file_count = 0
66        self.delete_only_file_count = 0
67
68    def _read_lines(self, file_path):
69        """Read the file at a path, and return its lines.
70
71        Raises:
72          IOError: If the file does not exist or cannot be read.
73
74        """
75        # Support the UNIX convention of using "-" for stdin.
76        if file_path == '-':
77            file = codecs.StreamReaderWriter(sys.stdin,
78                                             codecs.getreader('utf8'),
79                                             codecs.getwriter('utf8'),
80                                             'replace')
81        else:
82            # We do not open the file with universal newline support
83            # (codecs does not support it anyway), so the resulting
84            # lines contain trailing "\r" characters if we are reading
85            # a file with CRLF endings.
86            file = codecs.open(file_path, 'r', 'utf8', 'replace')
87
88        try:
89            contents = file.read()
90        finally:
91            file.close()
92
93        lines = contents.split('\n')
94        return lines
95
96    def process_file(self, file_path, **kwargs):
97        """Process the given file by calling the processor's process() method.
98
99        Args:
100          file_path: The path of the file to process.
101          **kwargs: Any additional keyword parameters that should be passed
102                    to the processor's process() method.  The process()
103                    method should support these keyword arguments.
104
105        Raises:
106          SystemExit: If no file at file_path exists.
107
108        """
109        self.file_count += 1
110
111        if not os.path.exists(file_path) and file_path != "-":
112            _log.error("File does not exist: '%s'" % file_path)
113            sys.exit(1)
114
115        if not self._processor.should_process(file_path):
116            _log.debug("Skipping file: '%s'" % file_path)
117            return
118        _log.debug("Processing file: '%s'" % file_path)
119
120        try:
121            lines = self._read_lines(file_path)
122        except IOError, err:
123            message = ("Could not read file. Skipping: '%s'\n  %s"
124                       % (file_path, err))
125            _log.warn(message)
126            return
127
128        self._processor.process(lines, file_path, **kwargs)
129
130    def _process_directory(self, directory):
131        """Process all files in the given directory, recursively.
132
133        Args:
134          directory: A directory path.
135
136        """
137        for dir_path, dir_names, file_names in os.walk(directory):
138            for file_name in file_names:
139                file_path = os.path.join(dir_path, file_name)
140                self.process_file(file_path)
141
142    def process_paths(self, paths):
143        """Process the given file and directory paths.
144
145        Args:
146          paths: A list of file and directory paths.
147
148        """
149        for path in paths:
150            if os.path.isdir(path):
151                self._process_directory(directory=path)
152            else:
153                self.process_file(path)
154
155    def count_delete_only_file(self):
156        """Count up files that contains only deleted lines.
157
158        Files which has no modified or newly-added lines don't need
159        to check style, but should be treated as checked. For that
160        purpose, we just count up the number of such files.
161        """
162        self.delete_only_file_count += 1
163