File: HttpHeaderParserTest.java

package info (click to toggle)
openjdk-21 21.0.8%2B9-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 823,976 kB
  • sloc: java: 5,613,338; xml: 1,643,607; cpp: 1,296,296; ansic: 420,291; asm: 404,850; objc: 20,994; sh: 15,271; javascript: 11,245; python: 6,895; makefile: 2,362; perl: 357; awk: 351; sed: 172; jsp: 24; csh: 3
file content (498 lines) | stat: -rw-r--r-- 23,444 bytes parent folder | download | duplicates (13)
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
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498


/*
 * Copyright (c) 2022, Oracle and/or its affiliates. All rights reserved.
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * This code is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 only, as
 * published by the Free Software Foundation.
 *
 * This code is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
 * version 2 for more details (a copy is included in the LICENSE file that
 * accompanied this code).
 *
 * You should have received a copy of the GNU General Public License version
 * 2 along with this work; if not, write to the Free Software Foundation,
 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
 *
 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
 * or visit www.oracle.com if you need additional information or have any
 * questions.
 */

/* @test
 * @bug 8061729
 * @library /test/lib
 * @summary Sanity check that HttpHeaderParser works same as MessageHeader
 * @modules java.base/sun.net.www java.base/sun.net.www.protocol.http:open
 * @run testng/othervm HttpHeaderParserTest
 */

import java.io.ByteArrayInputStream;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.concurrent.atomic.AtomicBoolean;
import java.util.concurrent.atomic.AtomicInteger;

import static java.lang.String.format;
import static java.nio.charset.StandardCharsets.ISO_8859_1;
import static java.nio.charset.StandardCharsets.US_ASCII;
import jdk.test.lib.net.HttpHeaderParser;
import static org.testng.Assert.assertEquals;
import static org.testng.Assert.assertTrue;
import org.testng.annotations.DataProvider;
import org.testng.annotations.Test;
import sun.net.www.MessageHeader;

public class HttpHeaderParserTest {
    @DataProvider(name = "responses")
    public Object[][] responses() {
        List<String> responses = new ArrayList<>();

        String[] basic =
                { "HTTP/1.1 200 OK\r\n\r\n",

                        "HTTP/1.1 200 OK\r\n" +
                                "Date: Mon, 15 Jan 2001 12:18:21 GMT\r\n" +
                                "Server: Apache/1.3.14 (Unix)\r\n" +
                                "Connection: close\r\n" +
                                "Content-Type: text/html; charset=iso-8859-1\r\n" +
                                "Content-Length: 10\r\n\r\n" +
                                "123456789",

                        "HTTP/1.1 200 OK\r\n" +
                                "Content-Length: 9\r\n" +
                                "Content-Type: text/html; charset=UTF-8\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "X-Header: U\u00ffU\r\n" + // value with U+00FF - Extended Latin-1
                                "Content-Length: 9\r\n" +
                                "Content-Type: text/html; charset=UTF-8\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "Content-Length:   9\r\n" +
                                "Content-Type:   text/html; charset=UTF-8\r\n\r\n" +   // more than one SP after ':'
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "Content-Length:\t10\r\n" +
                                "Content-Type:\ttext/html; charset=UTF-8\r\n\r\n" +   // HT separator
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "Content-Length:\t\t10\r\n" +
                                "Content-Type:\t\ttext/html; charset=UTF-8\r\n\r\n" +   // more than one HT after ':'
                                "XXXXX",

                        "HTTP/1.1 407 Proxy Authorization Required\r\n" +
                                "Proxy-Authenticate: Basic realm=\"a fake realm\"\r\n\r\n",

                        "HTTP/1.1 401 Unauthorized\r\n" +
                                "WWW-Authenticate: Digest realm=\"wally land\" domain=/ " +
                                "nonce=\"2B7F3A2B\" qop=\"auth\"\r\n\r\n",

                        "HTTP/1.1 200 OK\r\n" +
                                "X-Foo:\r\n\r\n",      // no value

                        "HTTP/1.1 200 OK\r\n" +
                                "X-Foo:\r\n\r\n" +     // no value, with response body
                                "Some Response Body",

                        "HTTP/1.1 200 OK\r\n" +
                                "X-Foo:\r\n" +    // no value, followed by another header
                                "Content-Length: 10\r\n\r\n" +
                                "Some Response Body",

                        "HTTP/1.1 200 OK\r\n" +
                                "X-Foo:\r\n" +    // no value, followed by another header, with response body
                                "Content-Length: 10\r\n\r\n",

                        "HTTP/1.1 200 OK\r\n" +
                                "X-Foo: chegar\r\n" +
                                "X-Foo: dfuchs\r\n" +  // same header appears multiple times
                                "Content-Length: 0\r\n" +
                                "X-Foo: michaelm\r\n" +
                                "X-Foo: prappo\r\n\r\n",

                        "HTTP/1.1 200 OK\r\n" +
                                "X-Foo:\r\n" +    // no value, same header appears multiple times
                                "X-Foo: dfuchs\r\n" +
                                "Content-Length: 0\r\n" +
                                "X-Foo: michaelm\r\n" +
                                "X-Foo: prappo\r\n\r\n",

                        "HTTP/1.1 200 OK\r\n" +
                                "Accept-Ranges: bytes\r\n" +
                                "Cache-control: max-age=0, no-cache=\"set-cookie\"\r\n" +
                                "Content-Length: 132868\r\n" +
                                "Content-Type: text/html; charset=UTF-8\r\n" +
                                "Date: Sun, 05 Nov 2017 22:24:03 GMT\r\n" +
                                "Server: Apache/2.4.6 (Red Hat Enterprise Linux) OpenSSL/1.0.1e-fips Communique/4.2.2\r\n" +
                                "Set-Cookie: AWSELB=AF7927F5100F4202119876ED2436B5005EE;PATH=/;MAX-AGE=900\r\n" +
                                "Vary: Host,Accept-Encoding,User-Agent\r\n" +
                                "X-Mod-Pagespeed: 1.12.34.2-0\r\n" +
                                "Connection: keep-alive\r\n\r\n"
                };
        Arrays.stream(basic).forEach(responses::add);
        // add some tests where some of the CRLF are replaced
        // by a single LF
        Arrays.stream(basic)
                .map(HttpHeaderParserTest::mixedCRLF)
                .forEach(responses::add);

        String[] foldingTemplate =
                {  "HTTP/1.1 200 OK\r\n" +
                        "Content-Length: 9\r\n" +
                        "Content-Type: text/html;$NEWLINE" +  // folding field-value with '\n'|'\r'
                        " charset=UTF-8\r\n" +                // one preceding SP
                        "Connection: close\r\n\r\n" +
                        "XXYYZZAABBCCDDEE",

                        "HTTP/1.1 200 OK\r\n" +
                                "Content-Length: 19\r\n" +
                                "Content-Type: text/html;$NEWLINE" +  // folding field-value with '\n'|'\r
                                "   charset=UTF-8\r\n" +              // more than one preceding SP
                                "Connection: keep-alive\r\n\r\n" +
                                "XXYYZZAABBCCDDEEFFGG",

                        "HTTP/1.1 200 OK\r\n" +
                                "Content-Length: 999\r\n" +
                                "Content-Type: text/html;$NEWLINE" +  // folding field-value with '\n'|'\r
                                "\tcharset=UTF-8\r\n" +               // one preceding HT
                                "Connection: close\r\n\r\n" +
                                "XXYYZZAABBCCDDEE",

                        "HTTP/1.1 200 OK\r\n" +
                                "Content-Length: 54\r\n" +
                                "Content-Type: text/html;$NEWLINE" +  // folding field-value with '\n'|'\r
                                "\t\t\tcharset=UTF-8\r\n" +           // more than one preceding HT
                                "Connection: keep-alive\r\n\r\n" +
                                "XXYYZZAABBCCDDEEFFGG",

                        "HTTP/1.1 200 OK\r\n" +
                                "Content-Length: -1\r\n" +
                                "Content-Type: text/html;$NEWLINE" +  // folding field-value with '\n'|'\r
                                "\t \t \tcharset=UTF-8\r\n" +         // mix of preceding HT and SP
                                "Connection: keep-alive\r\n\r\n" +
                                "XXYYZZAABBCCDDEEFFGGHH",

                        "HTTP/1.1 200 OK\r\n" +
                                "Content-Length: 65\r\n" +
                                "Content-Type: text/html;$NEWLINE" +  // folding field-value with '\n'|'\r
                                " \t \t charset=UTF-8\r\n" +          // mix of preceding SP and HT
                                "Connection: keep-alive\r\n\r\n" +
                                "XXYYZZAABBCCDDEEFFGGHHII",

                        "HTTP/1.1 401 Unauthorized\r\n" +
                                "WWW-Authenticate: Digest realm=\"wally land\","
                                +"$NEWLINE    domain=/,"
                                +"$NEWLINE nonce=\"2B7F3A2B\","
                                +"$NEWLINE\tqop=\"auth\"\r\n\r\n",

                };
        for (String newLineChar : new String[] { "\n", "\r", "\r\n" }) {
            for (String template : foldingTemplate)
                responses.add(template.replace("$NEWLINE", newLineChar));
        }
        // add some tests where some of the CRLF are replaced
        // by a single LF
        for (String newLineChar : new String[] { "\n", "\r", "\r\n" }) {
            for (String template : foldingTemplate)
                responses.add(mixedCRLF(template).replace("$NEWLINE", newLineChar));
        }

        String[] bad = // much of this is to retain parity with legacy MessageHeaders
                { "HTTP/1.1 200 OK\r\n" +
                        "Connection:\r\n\r\n",   // empty value, no body

                        "HTTP/1.1 200 OK\r\n" +
                                "Connection:\r\n\r\n" +  // empty value, with body
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                ": no header\r\n\r\n",  // no/empty header-name, no body, no following header

                        "HTTP/1.1 200 OK\r\n" +
                                ": no; header\r\n" +  // no/empty header-name, no body, following header
                                "Content-Length: 65\r\n\r\n",

                        "HTTP/1.1 200 OK\r\n" +
                                ": no header\r\n" +  // no/empty header-name
                                "Content-Length: 65\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "X-foo: bar\r\n" +
                                " : no header\r\n" +  // fold, not a blank header-name
                                "Content-Length: 65\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "X-foo: bar\r\n" +
                                " \t : no header\r\n" +  // fold, not a blank header-name
                                "Content-Length: 65\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                ": no header\r\n\r\n" +  // no/empty header-name, followed by header
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "Conte\r" +
                                "nt-Length: 9\r\n" +    // fold/bad header name ??? without preceding space
                                "Content-Type: text/html; charset=UTF-8\r\n\r\n" +
                                "XXXXXYYZZ",

                        "HTTP/1.0 404 Not Found\r\n" +
                                "header-without-colon\r\n\r\n",

                        "HTTP/1.0 404 Not Found\r\n" +
                                "header-without-colon\r\n\r\n" +
                                "SOMEBODY",

                };
        Arrays.stream(bad).forEach(responses::add);

        return responses.stream().map(p -> new Object[] { p }).toArray(Object[][]::new);
    }

    static final AtomicInteger index = new AtomicInteger();
    static final AtomicInteger limit = new AtomicInteger(1);
    static final AtomicBoolean useCRLF = new AtomicBoolean();
    // A small method to replace part of the CRLF present in a string
    // with simple LF. The method uses a deterministic algorithm based
    // on current values of static index/limit/useCRLF counters.
    // These counters are used to produce a stream of substitutes that
    // looks like this:
    // LF CRLF LF LF CRLF CRLF LF LF LF CRLF CRLF CRLF (then repeat from start)
    static final String mixedCRLF(String headers) {
        int next;
        int start = 0;
        int last = headers.lastIndexOf("\r\n");
        String prev = "";
        StringBuilder res = new StringBuilder();
        while ((next = headers.indexOf("\r\n", start)) > 0) {
            res.append(headers.substring(start, next));
            if ("\n".equals(prev) && next == last) {
                // for some reason the legacy MessageHeader parser will
                // not consume the final LF if the headers are terminated
                // by <LF><CRLF> instead of <CRLF><CRLF>. It consume
                // <LF><CR> but leaves the last <LF> in the stream.
                // Here we just make sure to avoid using <LF><CRLF>
                // as that would cause the legacy parser to consume
                // 1 byte less than the Http1HeadersParser - which
                // does consume the last <LF>, as it should.
                // if this is the last CRLF and the previous one
                // was replaced by LF then use LF.
                res.append(prev);
            } else {
                prev = useCRLF.get() ? "\r\n" : "\n";
                res.append(prev);
            }
            // skip CRLF
            start = next + 2;

            // The idea is to substitute some of the CRLF with LF.
            // Rather than doing this randomly, always use the following
            // sequence:
            // LF CRLF LF LF CRLF CRLF LF LF LF CRLF CRLF CRLF
            index.incrementAndGet();
            if (index.get() == limit.get()) {
                index.set(0);
                if (useCRLF.get()) limit.incrementAndGet();
                if (limit.get() > 3) limit.set(1);
                useCRLF.set(!useCRLF.get());
            }
        }
        res.append(headers.substring(start));
        return res.toString();
    }


    @Test(dataProvider = "responses")
    public void verifyHeaders(String respString) throws Exception {
        System.out.println("\ntesting:\n\t" + respString
                .replace("\r\n", "<CRLF>")
                .replace("\r", "<CR>")
                .replace("\n","<LF>")
                .replace("LF>", "LF>\n\t"));
        byte[] bytes = respString.getBytes(ISO_8859_1);
        ByteArrayInputStream bais = new ByteArrayInputStream(bytes);
        MessageHeader m = new MessageHeader(bais);
        Map<String,List<String>> messageHeaderMap = m.getHeaders();
        int availableBytes = bais.available();

        HttpHeaderParser decoder = new HttpHeaderParser();
        ByteArrayInputStream headerStream = new ByteArrayInputStream(bytes);
        int initialBytes = headerStream.available();
        decoder.parse(headerStream);
        System.out.printf("HttpHeaderParser parsed %d bytes out of %d%n", initialBytes - headerStream.available(), bytes.length);
        Map<String,List<String>> decoderMap1 = decoder.getHeaderMap();


        // assert status-line
        String statusLine1 = messageHeaderMap.get(null).get(0);
        String statusLine2 = decoder.getRequestDetails();
        if (statusLine1.startsWith("HTTP")) {// skip the case where MH's messes up the status-line
            assertEquals(statusLine2, statusLine1, "Status-line not equal");
        } else {
            assertTrue(statusLine2.startsWith("HTTP/1."), "Status-line not HTTP/1.");
        }

        // remove the null'th entry with is the status-line
        Map<String,List<String>> map = new HashMap<>();
        for (Map.Entry<String,List<String>> e : messageHeaderMap.entrySet()) {
            if (e.getKey() != null) {
                map.put(e.getKey(), e.getValue());
            }
        }
        messageHeaderMap = map;

        assertHeadersEqual(messageHeaderMap, decoderMap1,
                "messageHeaderMap not equal to decoderMap1");

        assertEquals(availableBytes, headerStream.available(),
                String.format("stream available (%d) not equal to remaining (%d)",
                        availableBytes, headerStream.available()));
    }

    @DataProvider(name = "errors")
    public Object[][] errors() {
        List<String> responses = new ArrayList<>();

        // These responses are parsed, somewhat, by MessageHeaders but give
        // nonsensible results. They, correctly, fail with the Http1HeaderParser.
        String[] bad =
                {// "HTTP/1.1 402 Payment Required\r\n" +
                        // "Content-Length: 65\r\n\r",   // missing trailing LF   //TODO: incomplete

                        "HTTP/1.1 402 Payment Required\r\n" +
                                "Content-Length: 65\r\n\rT\r\n\r\nGGGGGG",

                        "HTTP/1.1 200OK\r\n\rT",

                        "HTTP/1.1 200OK\rT",

                        "HTTP/1.0 FOO\r\n",

                        "HTTP/1.1 BAR\r\n",

                        "HTTP/1.1 +99\r\n",

                        "HTTP/1.1 -22\r\n",

                        "HTTP/1.1 -20 \r\n",

                        "HTTP/1.1 200 OK\r\n" +
                                "X-fo\u00ffo: foo\r\n" +     // invalid char in name
                                "Content-Length: 5\r\n" +
                                "Content-Type: text/html; charset=UTF-8\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "HTTP/1.1 200 OK\r\n" +
                                "X-foo : bar\r\n" +          //  trim space after name
                                "Content-Length: 5\r\n" +
                                "Content-Type: text/html; charset=UTF-8\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                " X-foo: bar\r\n" +          // trim space before name
                                "Content-Length: 5\r\n" +
                                "Content-Type: text/html; charset=UTF-8\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "X foo: bar\r\n" +           // invalid space in name
                                "Content-Length: 5\r\n" +
                                "Content-Type: text/html; charset=UTF-8\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "Content-Length: 5\r\n" +
                                "Content Type: text/html; charset=UTF-8\r\n\r\n" + // invalid space in name
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                "Conte\r" +
                                " nt-Length: 9\r\n" +    // fold results in space in header name
                                "Content-Type: text/html; charset=UTF-8\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                " : no header\r\n" +  // all blank header-name (not fold)
                                "Content-Length: 65\r\n\r\n" +
                                "XXXXX",

                        "HTTP/1.1 200 OK\r\n" +
                                " \t : no header\r\n" +  // all blank header-name (not fold)
                                "Content-Length: 65\r\n\r\n" +
                                "XXXXX",

                };
        Arrays.stream(bad).forEach(responses::add);

        return responses.stream().map(p -> new Object[] { p }).toArray(Object[][]::new);
    }

    @Test(dataProvider = "errors", expectedExceptions = IOException.class)
    public void errors(String respString) throws IOException {
        byte[] bytes = respString.getBytes(US_ASCII);
        HttpHeaderParser decoder = new HttpHeaderParser();
        ByteArrayInputStream bais = new ByteArrayInputStream(bytes);
        decoder.parse(bais);
    }

    void assertHeadersEqual(Map<String,List<String>> expected,
                            Map<String,List<String>> actual,
                            String msg) {

        if (expected.equals(actual))
            return;

        assertEquals(expected.size(), actual.size(),
                format("%s. Expected size %d, actual size %s. %nexpected= %s,%n actual=%s.",
                        msg, expected.size(), actual.size(), mapToString(expected), mapToString(actual)));

        for (Map.Entry<String,List<String>> e : expected.entrySet()) {
            String key = e.getKey();
            List<String> values = e.getValue();

            boolean found = false;
            for (Map.Entry<String,List<String>> other: actual.entrySet()) {
                if (key.equalsIgnoreCase(other.getKey())) {
                    found = true;
                    List<String> otherValues = other.getValue();
                    assertEquals(values.size(), otherValues.size(),
                            format("%s. Expected list size %d, actual size %s",
                                    msg, values.size(), otherValues.size()));
                    if (!(values.containsAll(otherValues) && otherValues.containsAll(values)))
                        assertTrue(false, format("Lists are unequal [%s] [%s]", values, otherValues));
                    break;
                }
            }
            assertTrue(found, format("header name, %s, not found in %s", key, actual));
        }
    }

    static String mapToString(Map<String,List<String>> map) {
        StringBuilder sb = new StringBuilder();
        List<String> sortedKeys = new ArrayList(map.keySet());
        Collections.sort(sortedKeys);
        for (String key : sortedKeys) {
            List<String> values = map.get(key);
            sb.append("\n\t" + key + " | " + values);
        }
        return sb.toString();
    }
}