XNSIO
  About   Slides   Home  

 
Managed Chaos
Naresh Jain's Random Thoughts on Software Development and Adventure Sports
     
`
 
RSS Feed
Recent Thoughts
Tags
Recent Comments

Refactoring Teaser V

I have a treat for crappy code scavengers. Here is some code which has a Cyclomatic Complexity of 68 and NPath Complexity of 34,632 (this method is ONLY 189 lines long (154 NCSS)).

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
/*
 * Main reading method
 */
public void read(final ByteBuffer byteBuffer) throws Exception {
    invalidateBuffer();
    // Check that the buffer is not bigger than 1 Megabyte. For security reasons
    // we will abort parsing when 1 Mega of queued chars was found.
    if (buffer.length() > maxBufferSize)
        throw new Exception("Stopped parsing never ending stanza");
    CharBuffer charBuffer = encoder.decode(byteBuffer);
    char[] buf = charBuffer.array();
    int readByte = charBuffer.remaining();
 
    // Just return if nothing was read
    if (readByte == 0)
        return;
 
    // Verify if the last received byte is an incomplete double byte character
    char lastChar = buf[readByte - 1];
    if (lastChar >= 0xfff0) {
        // Rewind the position one place so the last byte stays in the buffer
        // The missing byte should arrive in the next iteration. Once we have both
        // of bytes we will have the correct character
        byteBuffer.position(byteBuffer.position() - 1);
        // Decrease the number of bytes read by one
        readByte--;
        // Just return if nothing was read
        if (readByte == 0)
            return;
    }
 
    buffer.append(buf, 0, readByte);
    // Do nothing if the buffer only contains white spaces
    if (buffer.charAt(0) <= ' ' && buffer.charAt(buffer.length() - 1) <= ' ')
        if ("".equals(buffer.toString().trim())) {
            // Empty the buffer so there is no memory leak
            buffer.delete(0, buffer.length());
            return;
        }
    // Robot.
    char ch;
    boolean isHighSurrogate = false;
    for (int i = 0; i < readByte; i++) {
        ch = buf[i];
        if (ch < 0x20 && ch != 0x9 && ch != 0xA && ch != 0xD && ch != 0x0)
            // Unicode characters in the range 0x0000-0x001F other than 9, A, and D are not allowed in XML
            // We need to allow the NULL character, however, for Flash XMLSocket clients to work.
            throw new Exception("Disallowed character");
        if (isHighSurrogate) {
            if (Character.isLowSurrogate(ch))
                // Everything is fine. Clean up traces for surrogates
                isHighSurrogate = false;
            else
                // Trigger error. Found high surrogate not followed by low surrogate
                throw new Exception("Found high surrogate not followed by low surrogate");
        } else if (Character.isHighSurrogate(ch))
            isHighSurrogate = true;
        else if (Character.isLowSurrogate(ch))
            // Trigger error. Found low surrogate char without a preceding high surrogate
            throw new Exception("Found low surrogate char without a preceding high surrogate");
        if (status == XMLLightweightParser.TAIL) {
            // Looking for the close tag
            if (depth < 1 && ch == head.charAt(tailCount)) {
                tailCount++;
                if (tailCount == head.length()) {
                    // Close stanza found!
                    // Calculate the correct start,end position of the message into the buffer
                    int end = buffer.length() - readByte + i + 1;
                    String msg = buffer.substring(startLastMsg, end);
                    // Add message to the list
                    foundMsg(msg);
                    startLastMsg = end;
                }
            } else {
                tailCount = 0;
                status = XMLLightweightParser.INSIDE;
            }
        } else if (status == XMLLightweightParser.PRETAIL) {
            if (ch == XMLLightweightParser.CDATA_START[cdataOffset]) {
                cdataOffset++;
                if (cdataOffset == XMLLightweightParser.CDATA_START.length) {
                    status = XMLLightweightParser.INSIDE_CDATA;
                    cdataOffset = 0;
                    continue;
                }
            } else {
                cdataOffset = 0;
                status = XMLLightweightParser.INSIDE;
            }
            if (ch == '/') {
                status = XMLLightweightParser.TAIL;
                depth--;
            } else if (ch == '!')
                // This is a <! (comment) so ignore it
                status = XMLLightweightParser.INSIDE;
            else
                depth++;
        } else if (status == XMLLightweightParser.VERIFY_CLOSE_TAG) {
            if (ch == '>') {
                depth--;
                status = XMLLightweightParser.OUTSIDE;
                if (depth < 1) {
                    // Found a tag in the form <tag />
                    int end = buffer.length() - readByte + i + 1;
                    String msg = buffer.substring(startLastMsg, end);
                    // Add message to the list
                    foundMsg(msg);
                    startLastMsg = end;
                }
            } else if (ch == '<') {
                status = XMLLightweightParser.PRETAIL;
                insideChildrenTag = true;
            } else
                status = XMLLightweightParser.INSIDE;
        } else if (status == XMLLightweightParser.INSIDE_PARAM_VALUE) {
 
            if (ch == '"')
                status = XMLLightweightParser.INSIDE;
        } else if (status == XMLLightweightParser.INSIDE_CDATA) {
            if (ch == XMLLightweightParser.CDATA_END[cdataOffset]) {
                cdataOffset++;
                if (cdataOffset == XMLLightweightParser.CDATA_END.length) {
                    status = XMLLightweightParser.OUTSIDE;
                    cdataOffset = 0;
                }
            } else
                cdataOffset = 0;
        } else if (status == XMLLightweightParser.INSIDE) {
            if (ch == XMLLightweightParser.CDATA_START[cdataOffset]) {
                cdataOffset++;
                if (cdataOffset == XMLLightweightParser.CDATA_START.length) {
                    status = XMLLightweightParser.INSIDE_CDATA;
                    cdataOffset = 0;
                    continue;
                }
            } else {
                cdataOffset = 0;
                status = XMLLightweightParser.INSIDE;
            }
            if (ch == '"')
                status = XMLLightweightParser.INSIDE_PARAM_VALUE;
            else if (ch == '>') {
                status = XMLLightweightParser.OUTSIDE;
                if (insideRootTag
                        && ("stream:stream>".equals(head.toString()) || "?xml>".equals(head.toString()) || "flash:stream>".equals(head
                                .toString()))) {
                    // Found closing stream:stream
                    int end = buffer.length() - readByte + i + 1;
                    // Skip LF, CR and other "weird" characters that could appear
                    while (startLastMsg < end && '<' != buffer.charAt(startLastMsg))
                        startLastMsg++;
                    String msg = buffer.substring(startLastMsg, end);
                    foundMsg(msg);
                    startLastMsg = end;
                }
                insideRootTag = false;
            } else if (ch == '/')
                status = XMLLightweightParser.VERIFY_CLOSE_TAG;
        } else if (status == XMLLightweightParser.HEAD) {
            if (ch == ' ' || ch == '>') {
                // Append > to head to allow searching </tag>
                head.append(">");
                if (ch == '>')
                    status = XMLLightweightParser.OUTSIDE;
                else
                    status = XMLLightweightParser.INSIDE;
                insideRootTag = true;
                insideChildrenTag = false;
                continue;
            } else if (ch == '/' && head.length() > 0) {
                status = XMLLightweightParser.VERIFY_CLOSE_TAG;
                depth--;
            }
            head.append(ch);
 
        } else if (status == XMLLightweightParser.INIT) {
            if (ch == '<') {
                status = XMLLightweightParser.HEAD;
                depth = 1;
            } else
                startLastMsg++;
        } else if (status == XMLLightweightParser.OUTSIDE)
            if (ch == '<') {
                status = XMLLightweightParser.PRETAIL;
                cdataOffset = 1;
                insideChildrenTag = true;
            }
    }
    if (head.length() > 0 && ("/stream:stream>".equals(head.toString()) || "/flash:stream>".equals(head.toString())))
        // Found closing stream:stream
        foundMsg("</stream:stream>");
}

What does this code actually do?

This method is inside a LightWeightXMLParser. It reads data from a socket channel (java nio) and collects data until data is available on the channel. When a message is complete (fully formed XML), you can retrieve messages by invoking the getMsgs() method and you can invoke areThereMsgs() method to know if at least a message is presents.

86
87
88
89
90
91
92
93
94
95
96
/*
 * @return an array with all messages found
 */
public String[] getMsgs() {
    String[] res = new String[msgs.size()];
    for (int i = 0; i < res.length; i++)
        res[i] = msgs.get(i);
    msgs.clear();
    invalidateBuffer();
    return res;
}

Following Tests might help you understand the code slightly better:

16
17
18
19
20
21
22
23
    @Override
    protected void setUp() throws Exception {
        super.setUp();
        // Create parser
        parser = new LightWeightXMLParser(CHARSET);
        // Crete byte buffer and append text
        in = ByteBuffer.allocate(4096);
    }
25
26
27
28
29
30
    @Override
    protected void tearDown() throws Exception {
        super.tearDown();
        // Release byte buffer
        in.clear();
    }
32
33
34
35
36
37
38
39
40
41
    public void testHeader() throws Exception {
        String msg1 = "<stream:stream to=\"localhost\" xmlns=\"jabber:client\" xmlns:stream=\"http://etherx.jabber.org/streams\" version=\"1.0\">";
        in.put(msg1.getBytes());
        in.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in);
        // Make verifications
        assertTrue("Stream header is not being correctly parsed", parser.areThereMsgs());
        assertEquals("Wrong stanza was parsed", msg1, parser.getMsgs()[0]);
    }
43
44
45
46
47
48
49
50
51
52
53
54
55
56
    public void testHeaderWithXMLVersion() throws Exception {
        String msg1 = "<?xml version=\"1.0\"?>";
        String msg2 = "<stream:stream to=\"localhost\" xmlns=\"jabber:client\" xmlns:stream=\"http://etherx.jabber.org/streams\" version=\"1.0\">";
        in.put((msg1 + msg2).getBytes());
        in.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in);
        // Make verifications
        assertTrue("Stream header is not being correctly parsed", parser.areThereMsgs());
        String[] values = parser.getMsgs();
        assertEquals("Wrong number of parsed stanzas", 2, values.length);
        assertEquals("Wrong stanza was parsed", msg1, values[0]);
        assertEquals("Wrong stanza was parsed", msg2, values[1]);
    }
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
    public void testStanzas() throws Exception {
        String msg1 = "<stream:stream to=\"localhost\" xmlns=\"jabber:client\" xmlns:stream=\"http://etherx.jabber.org/streams\" version=\"1.0\">";
        String msg2 = "<starttls xmlns=\"urn:ietf:params:xml:ns:xmpp-tls\"/>";
        String msg3 = "<stream:stream to=\"localhost\" xmlns=\"jabber:client\" xmlns:stream=\"http://etherx.jabber.org/streams\" version=\"1.0\">";
        String msg4 = "<iq id=\"428qP-0\" to=\"localhost\" type=\"get\"><query xmlns=\"jabber:iq:register\"></query></iq>";
        String msg5 = "<stream:stream to=\"localhost\" xmlns=\"jabber:client\" xmlns:stream=\"http://etherx.jabber.org/streams\" version=\"1.0\">";
        String msg6 = "<presence id=\"428qP-5\"></presence>";
        in.put(msg1.getBytes());
        in.put(msg2.getBytes());
        in.put(msg3.getBytes());
        in.put(msg4.getBytes());
        in.put(msg5.getBytes());
        in.put(msg6.getBytes());
        in.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in);
        // Make verifications
        assertTrue("Stream header is not being correctly parsed", parser.areThereMsgs());
        String[] values = parser.getMsgs();
        assertEquals("Wrong number of parsed stanzas", 6, values.length);
        assertEquals("Wrong stanza was parsed", msg1, values[0]);
        assertEquals("Wrong stanza was parsed", msg2, values[1]);
        assertEquals("Wrong stanza was parsed", msg3, values[2]);
        assertEquals("Wrong stanza was parsed", msg4, values[3]);
        assertEquals("Wrong stanza was parsed", msg5, values[4]);
        assertEquals("Wrong stanza was parsed", msg6, values[5]);
    }
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
    public void testCompleteStanzas() throws Exception {
        String msg1 = "<stream:stream to=\"localhost\" xmlns=\"jabber:client\" xmlns:stream=\"http://etherx.jabber.org/streams\" version=\"1.0\">";
        String msg2 = "<starttls xmlns=\"urn:ietf:params:xml:ns:xmpp-tls\"/>";
        String msg3 = "<stream:stream to=\"localhost\" xmlns=\"jabber:client\" xmlns:stream=\"http://etherx.jabber.org/streams\" version=\"1.0\">";
        String msg4 = "<iq id=\"428qP-0\" to=\"localhost\" type=\"get\"><query xmlns=\"jabber:iq:register\"></query></iq>";
        String msg5 = "<stream:stream to=\"localhost\" xmlns=\"jabber:client\" xmlns:stream=\"http://etherx.jabber.org/streams\" version=\"1.0\">";
        String msg6 = "<presence id=\"428qP-5\"></presence>";
        String msg7 = "</stream:stream>";
        in.put(msg1.getBytes());
        in.put(msg2.getBytes());
        in.put(msg3.getBytes());
        in.put(msg4.getBytes());
        in.put(msg5.getBytes());
        in.put(msg6.getBytes());
        in.put(msg7.getBytes());
        in.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in);
        // Make verifications
        assertTrue("Stream header is not being correctly parsed", parser.areThereMsgs());
        String[] values = parser.getMsgs();
        assertEquals("Wrong number of parsed stanzas", 7, values.length);
        assertEquals("Wrong stanza was parsed", msg1, values[0]);
        assertEquals("Wrong stanza was parsed", msg2, values[1]);
        assertEquals("Wrong stanza was parsed", msg3, values[2]);
        assertEquals("Wrong stanza was parsed", msg4, values[3]);
        assertEquals("Wrong stanza was parsed", msg5, values[4]);
        assertEquals("Wrong stanza was parsed", msg6, values[5]);
        assertEquals("Wrong stanza was parsed", msg7, values[6]);
    }
117
118
119
120
121
122
123
124
125
126
127
    public void testIQ() throws Exception {
        String iq = "<iq type=\"set\" to=\"lachesis\" from=\"0sups/Connection Worker - 1\" id=\"360-22348\"><session xmlns=\"http://jabber.org/protocol/connectionmanager\" id=\"0sups87b1694\"><close/></session></iq>";
        in.put(iq.getBytes());
        in.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in);
        // Make verifications
        assertTrue("Stream header is not being correctly parsed", parser.areThereMsgs());
        String parsedIQ = parser.getMsgs()[0];
        assertEquals("Wrong stanza was parsed", iq, parsedIQ);
    }
129
130
131
132
133
134
135
136
137
138
139
140
    public void testNestedElements() throws Exception {
        String msg1 = "<message><message xmlns=\"e\">1</message></message>";
        in.put(msg1.getBytes());
        in.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in);
        // Make verifications
        assertTrue("Stream header is not being correctly parsed", parser.areThereMsgs());
        String[] values = parser.getMsgs();
        assertEquals("Wrong number of parsed stanzas", 1, values.length);
        assertEquals("Wrong stanza was parsed", msg1, values[0]);
    }
142
143
144
145
146
147
148
149
150
    public void testIncompleteStanza() throws Exception {
        String msg1 = "<message><something xmlns=\"http://idetalk.com/namespace\">12";
        in.put(msg1.getBytes());
        in.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in);
        // Make verifications
        assertFalse("Found messages in incomplete stanza", parser.areThereMsgs());
    }
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
    public void testStanzaWithSpecialChars() throws Exception {
        String msg1 = "<message><something xmlns=\"http://idetalk.com/namespace\">12/</something></message>";
        String msg2 = "<message><something xmlns=\"http://idetalk.com/namespace\">12///</something></message>";
        String msg3 = "<message><something xmlns=\"http://idetalk.com/namespace\">12/\\/</something></message>";
        String msg4 = "<message><something xmlns=\"http://idetalk.com/namespace\">http://idetalk.com/namespace/</something></message>";
        in.put(msg1.getBytes());
        in.put(msg2.getBytes());
        in.put(msg3.getBytes());
        in.put(msg4.getBytes());
        in.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in);
        // Make verifications
        assertTrue("No messages were found in stanza", parser.areThereMsgs());
        String[] values = parser.getMsgs();
        assertEquals("Wrong number of parsed stanzas", 4, values.length);
        assertEquals("Wrong stanza was parsed", msg1, values[0]);
        assertEquals("Wrong stanza was parsed", msg2, values[1]);
        assertEquals("Wrong stanza was parsed", msg3, values[2]);
        assertEquals("Wrong stanza was parsed", msg4, values[3]);
    }
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
    public void testCompletedStanza() throws Exception {
        String msg1 = "<message><something xmlns=\"http://idetalk.com/namespace\">12";
        in.put(msg1.getBytes());
        in.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in);
        // Make verifications
        assertFalse("Found messages in incomplete stanza", parser.areThereMsgs());
 
        String msg2 = "</something></message>";
        ByteBuffer in2 = ByteBuffer.allocate(4096);
        in2.put(msg2.getBytes());
        in2.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in2);
        in2.clear();
        assertTrue("Stream header is not being correctly parsed", parser.areThereMsgs());
        String[] values = parser.getMsgs();
        assertEquals("Wrong number of parsed stanzas", 1, values.length);
        assertEquals("Wrong stanza was parsed", msg1 + msg2, values[0]);
    }
196
197
198
199
200
201
202
203
204
205
206
207
    public void testStanzaWithComments() throws Exception {
        String msg1 = "<iq from=\"[email protected]/spark\"><query xmlns=\"jabber:iq:privacy\"><!-- silly comment --></query></iq>";
        in.put(msg1.getBytes());
        in.flip();
        // Fill parser with byte buffer content and parse it
        parser.read(in);
        // Make verifications
        assertTrue("No messages were found in stanza", parser.areThereMsgs());
        String[] values = parser.getMsgs();
        assertEquals("Wrong number of parsed stanzas", 1, values.length);
        assertEquals("Wrong stanza was parsed", msg1, values[0]);
    }
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
    public void testWeirdoContent() throws Exception {
        final String[] testStanzas = { "<?xml version=\"1.0\"?>",
                "<stream:stream xmlns:stream=\"http://etherx.jabber.org/streams\" xmlns=\"jabber:client\" to=\"localhost\" >",
                "<emppartag test=\"1\"/>", "<cdatatest><![CDATA[just<ignore everything& >>here<<<<< /> />]]&gt;]]></cdatatest>",
                "<esctest param=\"1\"> this \" is / a test /> test /> </esctest>",
                "<comtest>this <!-- comment --> is a comment</comtest>", "<emptag/>",
                "<iq type=\"get\" id=\"aab1a\" ><query xmlns=\"jabber:iq:roster\"/> <tag> text </tag></iq>",
                "<iq type=\"get\" id=\"aab1a\" ><query xmlns=\"jabber:iq:roster\"/> </iq>",
                "<message><body xmlns=\"http://idetalk.com/namespace\">12\"</body></message>",
                "<message to=\"[email protected]\" id=\"XRk8p-X\"><body> /> /> </body></message>", };
        String testMsg = "";
        for (String s : testStanzas)
            testMsg += s;
        ByteBuffer mybuffer = ByteBuffer.wrap(testMsg.getBytes());
        parser.read(mybuffer);
 
        String[] msgs = parser.getMsgs();
        for (int i = 0; i < testStanzas.length; i++) {
            assertTrue(i < msgs.length);
            assertEquals(testStanzas[i], msgs[i]);
        }
    }
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
    public void testRead() {
        try {
            LightWeightXMLParser parser = new LightWeightXMLParser("UTF-8");
            String xml1 = "<ab>\u1000</a";
            String xml2 = "b>";
            ByteBuffer buffer1 = ByteBuffer.wrap(xml1.getBytes("UTF-8"));
            ByteBuffer buffer2 = ByteBuffer.wrap(xml2.getBytes("UTF-8"));
 
            parser.read(buffer1);
            parser.read(buffer2);
 
            if (!parser.areThereMsgs())
                Assert.fail("No messages found");
 
            String msgs[] = parser.getMsgs();
            if (msgs.length > 1)
                Assert.fail("More than one message found");
            else
                Assert.assertEquals(xml1 + xml2, msgs[0]);
        } catch (Exception e) {
            Assert.fail(e.getMessage());
        }
    }

Feel free to download the full project source code.


    Licensed under
Creative Commons License