summaryrefslogtreecommitdiffstats
path: root/Lib/CGIHTTPServer.py
blob: 13bfcdd22f031330d70ef3b73d521936cc9c2ef3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
"""CGI-savvy HTTP Server.

This module builds on SimpleHTTPServer by implementing GET and POST
requests to cgi-bin scripts.

If the os.fork() function is not present (e.g. on Windows),
os.popen2() is used as a fallback, with slightly altered semantics; if
that function is not present either (e.g. on Macintosh), only Python
scripts are supported, and they are executed by the current process.

In all cases, the implementation is intentionally naive -- all
requests are executed sychronously.

SECURITY WARNING: DON'T USE THIS CODE UNLESS YOU ARE INSIDE A FIREWALL
-- it may execute arbitrary Python code or external programs.

Note that status code 200 is sent prior to execution of a CGI script, so
scripts cannot send other status codes such as 302 (redirect).
"""


__version__ = "0.4"

__all__ = ["CGIHTTPRequestHandler"]

import os
import sys
import urllib
import BaseHTTPServer
import SimpleHTTPServer
import select


class CGIHTTPRequestHandler(SimpleHTTPServer.SimpleHTTPRequestHandler):

    """Complete HTTP server with GET, HEAD and POST commands.

    GET and HEAD also support running CGI scripts.

    The POST command is *only* implemented for CGI scripts.

    """

    # Determine platform specifics
    have_fork = hasattr(os, 'fork')
    have_popen2 = hasattr(os, 'popen2')
    have_popen3 = hasattr(os, 'popen3')

    # Make rfile unbuffered -- we need to read one line and then pass
    # the rest to a subprocess, so we can't use buffered input.
    rbufsize = 0

    def do_POST(self):
        """Serve a POST request.

        This is only implemented for CGI scripts.

        """

        if self.is_cgi():
            self.run_cgi()
        else:
            self.send_error(501, "Can only POST to CGI scripts")

    def send_head(self):
        """Version of send_head that support CGI scripts"""
        if self.is_cgi():
            return self.run_cgi()
        else:
            return SimpleHTTPServer.SimpleHTTPRequestHandler.send_head(self)

    def is_cgi(self):
        """Test whether self.path corresponds to a CGI script.

        Returns True and updates the cgi_info attribute to the tuple
        (dir, rest) if self.path requires running a CGI script.
        Returns False otherwise.

        The default implementation tests whether the normalized url
        path begins with one of the strings in self.cgi_directories
        (and the next character is a '/' or the end of the string).
        """
        splitpath = _url_collapse_path_split(self.path)
        if splitpath[0] in self.cgi_directories:
            self.cgi_info = splitpath
            return True
        return False

    cgi_directories = ['/cgi-bin', '/htbin']

    def is_executable(self, path):
        """Test whether argument path is an executable file."""
        return executable(path)

    def is_python(self, path):
        """Test whether argument path is a Python script."""
        head, tail = os.path.splitext(path)
        return tail.lower() in (".py", ".pyw")

    def run_cgi(self):
        """Execute a CGI script."""
        path = self.path
        dir, rest = self.cgi_info

        i = path.find('/', len(dir) + 1)
        while i >= 0:
            nextdir = path[:i]
            nextrest = path[i+1:]

            scriptdir = self.translate_path(nextdir)
            if os.path.isdir(scriptdir):
                dir, rest = nextdir, nextrest
                i = path.find('/', len(dir) + 1)
            else:
                break

        # find an explicit query string, if present.
        i = rest.rfind('?')
        if i >= 0:
            rest, query = rest[:i], rest[i+1:]
        else:
            query = ''

        # dissect the part after the directory name into a script name &
        # a possible additional path, to be stored in PATH_INFO.
        i = rest.find('/')
        if i >= 0:
            script, rest = rest[:i], rest[i:]
        else:
            script, rest = rest, ''

        scriptname = dir + '/' + script
        scriptfile = self.translate_path(scriptname)
        if not os.path.exists(scriptfile):
            self.send_error(404, "No such CGI script (%r)" % scriptname)
            return
        if not os.path.isfile(scriptfile):
            self.send_error(403, "CGI script is not a plain file (%r)" %
                            scriptname)
            return
        ispy = self.is_python(scriptname)
        if not ispy:
            if not (self.have_fork or self.have_popen2 or self.have_popen3):
                self.send_error(403, "CGI script is not a Python script (%r)" %
                                scriptname)
                return
            if not self.is_executable(scriptfile):
                self.send_error(403, "CGI script is not executable (%r)" %
                                scriptname)
                return

        # Reference: http://hoohoo.ncsa.uiuc.edu/cgi/env.html
        # XXX Much of the following could be prepared ahead of time!
        env = {}
        env['SERVER_SOFTWARE'] = self.version_string()
        env['SERVER_NAME'] = self.server.server_name
        env['GATEWAY_INTERFACE'] = 'CGI/1.1'
        env['SERVER_PROTOCOL'] = self.protocol_version
        env['SERVER_PORT'] = str(self.server.server_port)
        env['REQUEST_METHOD'] = self.command
        uqrest = urllib.unquote(rest)
        env['PATH_INFO'] = uqrest
        env['PATH_TRANSLATED'] = self.translate_path(uqrest)
        env['SCRIPT_NAME'] = scriptname
        if query:
            env['QUERY_STRING'] = query
        host = self.address_string()
        if host != self.client_address[0]:
            env['REMOTE_HOST'] = host
        env['REMOTE_ADDR'] = self.client_address[0]
        authorization = self.headers.getheader("authorization")
        if authorization:
            authorization = authorization.split()
            if len(authorization) == 2:
                import base64, binascii
                env['AUTH_TYPE'] = authorization[0]
                if authorization[0].lower() == "basic":
                    try:
                        authorization = base64.decodestring(authorization[1])
                    except binascii.Error:
                        pass
                    else:
                        authorization = authorization.split(':')
                        if len(authorization) == 2:
                            env['REMOTE_USER'] = authorization[0]
        # XXX REMOTE_IDENT
        if self.headers.typeheader is None:
            env['CONTENT_TYPE'] = self.headers.type
        else:
            env['CONTENT_TYPE'] = self.headers.typeheader
        length = self.headers.getheader('content-length')
        if length:
            env['CONTENT_LENGTH'] = length
        referer = self.headers.getheader('referer')
        if referer:
            env['HTTP_REFERER'] = referer
        accept = []
        for line in self.headers.getallmatchingheaders('accept'):
            if line[:1] in "\t\n\r ":
                accept.append(line.strip())
            else:
                accept = accept + line[7:].split(',')
        env['HTTP_ACCEPT'] = ','.join(accept)
        ua = self.headers.getheader('user-agent')
        if ua:
            env['HTTP_USER_AGENT'] = ua
        co = filter(None, self.headers.getheaders('cookie'))
        if co:
            env['HTTP_COOKIE'] = ', '.join(co)
        # XXX Other HTTP_* headers
        # Since we're setting the env in the parent, provide empty
        # values to override previously set values
        for k in ('QUERY_STRING', 'REMOTE_HOST', 'CONTENT_LENGTH',
                  'HTTP_USER_AGENT', 'HTTP_COOKIE', 'HTTP_REFERER'):
            env.setdefault(k, "")
        os.environ.update(env)

        self.send_response(200, "Script output follows")

        decoded_query = query.replace('+', ' ')

        if self.have_fork:
            # Unix -- fork as we should
            args = [script]
            if '=' not in decoded_query:
                args.append(decoded_query)
            nobody = nobody_uid()
            self.wfile.flush() # Always flush before forking
            pid = os.fork()
            if pid != 0:
                # Parent
                pid, sts = os.waitpid(pid, 0)
                # throw away additional data [see bug #427345]
                while select.select([self.rfile], [], [], 0)[0]:
                    if not self.rfile.read(1):
                        break
                if sts:
                    self.log_error("CGI script exit status %#x", sts)
                return
            # Child
            try:
                try:
                    os.setuid(nobody)
                except os.error:
                    pass
                os.dup2(self.rfile.fileno(), 0)
                os.dup2(self.wfile.fileno(), 1)
                os.execve(scriptfile, args, os.environ)
            except:
                self.server.handle_error(self.request, self.client_address)
                os._exit(127)

        elif self.have_popen2 or self.have_popen3:
            # Windows -- use popen2 or popen3 to create a subprocess
            import shutil
            if self.have_popen3:
                popenx = os.popen3
            else:
                popenx = os.popen2
            cmdline = scriptfile
            if self.is_python(scriptfile):
                interp = sys.executable
                if interp.lower().endswith("w.exe"):
                    # On Windows, use python.exe, not pythonw.exe
                    interp = interp[:-5] + interp[-4:]
                cmdline = "%s -u %s" % (interp, cmdline)
            if '=' not in query and '"' not in query:
                cmdline = '%s "%s"' % (cmdline, query)
            self.log_message("command: %s", cmdline)
            try:
                nbytes = int(length)
            except (TypeError, ValueError):
                nbytes = 0
            files = popenx(cmdline, 'b')
            fi = files[0]
            fo = files[1]
            if self.have_popen3:
                fe = files[2]
            if self.command.lower() == "post" and nbytes > 0:
                data = self.rfile.read(nbytes)
                fi.write(data)
            # throw away additional data [see bug #427345]
            while select.select([self.rfile._sock], [], [], 0)[0]:
                if not self.rfile._sock.recv(1):
                    break
            fi.close()
            shutil.copyfileobj(fo, self.wfile)
            if self.have_popen3:
                errors = fe.read()
                fe.close()
                if errors:
                    self.log_error('%s', errors)
            sts = fo.close()
            if sts:
                self.log_error("CGI script exit status %#x", sts)
            else:
                self.log_message("CGI script exited OK")

        else:
            # Other O.S. -- execute script in this process
            save_argv = sys.argv
            save_stdin = sys.stdin
            save_stdout = sys.stdout
            save_stderr = sys.stderr
            try:
                save_cwd = os.getcwd()
                try:
                    sys.argv = [scriptfile]
                    if '=' not in decoded_query:
                        sys.argv.append(decoded_query)
                    sys.stdout = self.wfile
                    sys.stdin = self.rfile
                    execfile(scriptfile, {"__name__": "__main__"})
                finally:
                    sys.argv = save_argv
                    sys.stdin = save_stdin
                    sys.stdout = save_stdout
                    sys.stderr = save_stderr
                    os.chdir(save_cwd)
            except SystemExit, sts:
                self.log_error("CGI script exit status %s", str(sts))
            else:
                self.log_message("CGI script exited OK")


# TODO(gregory.p.smith): Move this into an appropriate library.
def _url_collapse_path_split(path):
    """
    Given a URL path, remove extra '/'s and '.' path elements and collapse
    any '..' references.

    Implements something akin to RFC-2396 5.2 step 6 to parse relative paths.

    Returns: A tuple of (head, tail) where tail is everything after the final /
    and head is everything before it.  Head will always start with a '/' and,
    if it contains anything else, never have a trailing '/'.

    Raises: IndexError if too many '..' occur within the path.
    """
    # Similar to os.path.split(os.path.normpath(path)) but specific to URL
    # path semantics rather than local operating system semantics.
    path_parts = []
    for part in path.split('/'):
        if part == '.':
            path_parts.append('')
        else:
            path_parts.append(part)
    # Filter out blank non trailing parts before consuming the '..'.
    path_parts = [part for part in path_parts[:-1] if part] + path_parts[-1:]
    if path_parts:
        tail_part = path_parts.pop()
    else:
        tail_part = ''
    head_parts = []
    for part in path_parts:
        if part == '..':
            head_parts.pop()
        else:
            head_parts.append(part)
    if tail_part and tail_part == '..':
        head_parts.pop()
        tail_part = ''
    return ('/' + '/'.join(head_parts), tail_part)


nobody = None

def nobody_uid():
    """Internal routine to get nobody's uid"""
    global nobody
    if nobody:
        return nobody
    try:
        import pwd
    except ImportError:
        return -1
    try:
        nobody = pwd.getpwnam('nobody')[2]
    except KeyError:
        nobody = 1 + max(map(lambda x: x[2], pwd.getpwall()))
    return nobody


def executable(path):
    """Test for executable file."""
    try:
        st = os.stat(path)
    except os.error:
        return False
    return st.st_mode & 0111 != 0


def test(HandlerClass = CGIHTTPRequestHandler,
         ServerClass = BaseHTTPServer.HTTPServer):
    SimpleHTTPServer.test(HandlerClass, ServerClass)


if __name__ == '__main__':
    test()