file_types.py revision 11508:46e5f3bf7f17 
1# Copyright (c) 2010 The Hewlett-Packard Development Company
2# All rights reserved.
3#
4# Redistribution and use in source and binary forms, with or without
5# modification, are permitted provided that the following conditions are
6# met: redistributions of source code must retain the above copyright
7# notice, this list of conditions and the following disclaimer;
8# redistributions in binary form must reproduce the above copyright
9# notice, this list of conditions and the following disclaimer in the
10# documentation and/or other materials provided with the distribution;
11# neither the name of the copyright holders nor the names of its
12# contributors may be used to endorse or promote products derived from
13# this software without specific prior written permission.
14#
15# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
16# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
17# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
18# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
19# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
20# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
21# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
22# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
23# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
25# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26#
27# Authors: Nathan Binkert
28
29import os
30
31# lanuage type for each file extension
32lang_types = {
33    '.c'     : "C",
34    '.cl'    : "C",
35    '.h'     : "C",
36    '.cc'    : "C++",
37    '.hh'    : "C++",
38    '.cxx'   : "C++",
39    '.hxx'   : "C++",
40    '.cpp'   : "C++",
41    '.hpp'   : "C++",
42    '.C'     : "C++",
43    '.H'     : "C++",
44    '.i'     : "swig",
45    '.py'    : "python",
46    '.pl'    : "perl",
47    '.pm'    : "perl",
48    '.s'     : "asm",
49    '.S'     : "asm",
50    '.l'     : "lex",
51    '.ll'    : "lex",
52    '.y'     : "yacc",
53    '.yy'    : "yacc",
54    '.isa'   : "isa",
55    '.sh'    : "shell",
56    '.slicc' : "slicc",
57    '.sm'    : "slicc",
58    '.awk'   : "awk",
59    '.el'    : "lisp",
60    '.txt'   : "text",
61    '.tex'   : "tex",
62    '.mk'    : "make",
63    }
64
65# languages based on file prefix
66lang_prefixes = (
67    ('SCons',    'scons'),
68    ('Make',     'make'),
69    ('make',     'make'),
70    ('Doxyfile', 'doxygen'),
71    )
72
73# languages based on #! line of first file
74hash_bang = (
75    ('python', 'python'),
76    ('perl',   'perl'),
77    ('sh',     'shell'),
78    )
79
80# the list of all languages that we detect
81all_languages = frozenset(lang_types.itervalues())
82all_languages |= frozenset(lang for start,lang in lang_prefixes)
83all_languages |= frozenset(lang for start,lang in hash_bang)
84
85def lang_type(filename, firstline=None, openok=True):
86    '''identify the language of a given filename and potentially the
87    firstline of the file.  If the firstline of the file is not
88    provided and openok is True, open the file and read the first line
89    if necessary'''
90
91    basename = os.path.basename(filename)
92    name,extension = os.path.splitext(basename)
93
94    # first try to detect language based on file extension
95    try:
96        return lang_types[extension]
97    except KeyError:
98        pass
99
100    # now try to detect language based on file prefix
101    for start,lang in lang_prefixes:
102        if basename.startswith(start):
103            return lang
104
105    # if a first line was not provided but the file is ok to open,
106    # grab the first line of the file.
107    if firstline is None and openok:
108        handle = file(filename, 'r')
109        firstline = handle.readline()
110        handle.close()
111
112    # try to detect language based on #! in first line
113    if firstline and firstline.startswith('#!'):
114        for string,lang in hash_bang:
115            if firstline.find(string) > 0:
116                return lang
117
118    # sorry, we couldn't detect the language
119    return None
120
121# directories and files to ignore by default
122default_dir_ignore = frozenset(('.hg', '.svn', 'build', 'ext'))
123default_file_ignore = frozenset(('parsetab.py', ))
124
125def find_files(base, languages=all_languages,
126               dir_ignore=default_dir_ignore,
127               file_ignore=default_file_ignore):
128    '''find all files in a directory and its subdirectories based on a
129    set of languages, ignore directories specified in dir_ignore and
130    files specified in file_ignore'''
131    if base[-1] != '/':
132        base += '/'
133
134    def update_dirs(dirs):
135        '''strip the ignored directories out of the provided list'''
136        index = len(dirs) - 1
137        for i,d in enumerate(reversed(dirs)):
138            if d in dir_ignore:
139                del dirs[index - i]
140
141    # walk over base
142    for root,dirs,files in os.walk(base):
143        root = root.replace(base, '', 1)
144
145        # strip ignored directories from the list
146        update_dirs(dirs)
147
148        for filename in files:
149            if filename in file_ignore:
150                # skip ignored files
151                continue
152
153            # try to figure out the language of the specified file
154            fullpath = os.path.join(base, root, filename)
155            language = lang_type(fullpath)
156
157            # if the file is one of the langauges that we want return
158            # its name and the language
159            if language in languages:
160                yield fullpath, language
161
162def update_file(dst, src, language, mutator):
163    '''update a file of the specified language with the provided
164    mutator generator.  If inplace is provided, update the file in
165    place and return the handle to the updated file.  If inplace is
166    false, write the updated file to cStringIO'''
167
168    # if the source and destination are the same, we're updating in place
169    inplace = dst == src
170
171    if isinstance(src, str):
172        # if a filename was provided, open the file
173        if inplace:
174            mode = 'r+'
175        else:
176            mode = 'r'
177        src = file(src, mode)
178
179    orig_lines = []
180
181    # grab all of the lines of the file and strip them of their line ending
182    old_lines = list(line.rstrip('\r\n') for line in src.xreadlines())
183    new_lines = list(mutator(old_lines, src.name, language))
184
185    for line in src.xreadlines():
186        line = line
187
188    if inplace:
189        # if we're updating in place and the file hasn't changed, do nothing
190        if old_lines == new_lines:
191            return
192
193        # otherwise, truncate the file and seek to the beginning.
194        dst = src
195        dst.truncate(0)
196        dst.seek(0)
197    elif isinstance(dst, str):
198        # if we're not updating in place and a destination file name
199        # was provided, create a file object
200        dst = file(dst, 'w')
201
202    for line in new_lines:
203        dst.write(line)
204        dst.write('\n')
205