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
|
package model.html;
import java.util.*;
import org.javatuples.*;
import org.json.JSONObject;
import persistance.JsonAble;
/**
* This class represents the state of and implements an LL(1) HTML parser.
* For convenience, the following (defo wrong) context-free grammar for HTML is below.
* <br>
* HTML ::= '<!DOCTYPE html>' (NODE)*
* NODE ::= '<'TAG (' ' WORD '=' ('"'TEXT'"' | TEXT))* '>' (NODE)* '<\/' TAG '>'
* | '<'SELF_CLOSING_TAG (' ' WORD '=' ('"'TEXT'"' | TEXT))* ('>'|'/>')
* | (TEXT | NODE)*
* TEXT ::= UNICODE - {'"'} + {'\"'}
* TAG ::= 'body' | 'div' | ...
* SELF_CLOSING_TAG ::= 'img' | ...
* (note that \forall T \in SELF_CLOSING_TAG, T \notin TAG)
*/
public class HtmlParser implements JsonAble {
/**
* HTML is not nice to parse. We manage to get away with a relatively small number of parser states regardless.
*/
private enum ParserState {
HTML, IGNORED,
OPENING_TAG, KEY, VALUE, // TAG::OPENING_TAG, TAG::KEY, TAG::VALUE
SINGLE_QUOTES, DOUBLE_QUOTES, // VALUE::SINGLE_QUOTES, VALUE::DOUBLE_QUOTES
UNKNOWN_TAG, CLOSING_TAG,
}
// HTML documents are uniquely a list of Nodes rather than a Node themselves
private ArrayList<Node> result;
// a bunch of useful buffers. see CssParser for commentary.
private ArrayDeque<ElementNode> unfinished;
private String currentTag;
private ArrayList<Pair<String, String>> currentAttributes;
private String currentKey;
private String currentValue;
private String currentText;
// important for quote escapes, and multiple whitespace chars
private char previousChar;
private ParserState state;
// EFFECTS: constructs a new HTML parser.
// MODIFIES: this
public HtmlParser() {
result = new ArrayList<>();
unfinished = new ArrayDeque<>();
currentTag = "";
currentAttributes = new ArrayList<>();
currentKey = "";
currentValue = "";
currentText = "";
previousChar = '\0';
// We safely? assume to start outside of all nodes.
state = ParserState.HTML;
}
public ArrayList<Node> parseHtml(String input) {
for (char c : input.toCharArray()) {
// System.out.print(state);
// System.out.println(" " + c + " " + currentText);
switch (state) {
case HTML: caseHtml(c);
break;
case UNKNOWN_TAG: caseUnknownTag(c);
break; // FOOTGUN LANGUAGE DESIGN STRIKES AGAIN
case IGNORED: caseIgnored(c);
break;
case OPENING_TAG: caseOpeningTag(c);
break;
case CLOSING_TAG: caseClosingTag(c);
break;
case KEY: caseKey(c);
break;
case VALUE: caseValue(c);
break;
case SINGLE_QUOTES: caseSingleQuotes(c);
break;
case DOUBLE_QUOTES: caseDoubleQuotes(c);
break;
}
}
return result;
}
/**
* EFFECTS: Handles and updates parser state/buffers for a single character while in the HTML state.
* MODIFIES: this
*/
private void caseHtml(char c) {
switch (c) {
case '<':
state = ParserState.UNKNOWN_TAG;
if (!currentText.equals("")) {
addNewTextNode();
}
break; // FOOTGUN LANGUAGE DESIGN
case ' ': case '\n':
if (previousChar != ' ') {
currentText += ' ';
}
previousChar = ' ';
break;
default:
currentText += c;
previousChar = c;
break;
}
}
/**
* EFFECTS: Handles and updates parser state/buffers for a single character while in the UNKNOWN_TAG state.
* MODIFIES: this
*/
private void caseUnknownTag(char c) {
switch (c) {
case '/':
state = ParserState.CLOSING_TAG;
break;
case '>': // Why would you put <> in your HTML??? go away
state = ParserState.HTML;
currentText += "<>";
break;
// For now, we'll straight-up ignore anything matching the <!...> syntax:
// i.e. comments, and <!DOCTYPE html>
case '!':
state = ParserState.IGNORED;
break;
default:
state = ParserState.OPENING_TAG;
currentTag += c;
break;
}
}
/**
* EFFECTS: Handles and updates parser state/buffers for a single character while in the IGNORED state.
* MODIFIES: this
*/
private void caseIgnored(char c) {
switch (c) {
case '>':
state = ParserState.HTML;
break;
default:
break;
}
}
/**
* EFFECTS: Handles and updates parser state/buffers for a single character while in the OPENING_TAG state.
* MODIFIES: this
*/
private void caseOpeningTag(char c) {
switch (c) {
case '>':
addNewElementNode();
break;
case ' ': case '\n':
state = ParserState.KEY;
break;
default:
currentTag += c;
break;
}
}
/**
* EFFECTS: Handles and updates parser state/buffers for a single character while in the CLOSING_TAG state.
* MODIFIES: this
*/
private void caseClosingTag(char c) {
switch (c) {
case '>':
state = ParserState.HTML;
// IMPORTANT: we don't validate that closing tags correspond to an open tag
if (!isSelfClosingTag(currentTag)) {
if (unfinished.size() != 0) {
unfinished.removeLast();
}
}
currentTag = "";
break;
case ' ': case '\n':
break;
default:
currentTag += c;
break;
}
}
/**
* EFFECTS: Handles and updates parser state/buffers for a single character while in the KEY state.
* MODIFIES: this
*/
private void caseKey(char c) {
switch (c) {
case '>':
addNewElementNode();
break;
case '=':
state = ParserState.VALUE;
break;
case ' ': case '\n':
break;
default:
currentKey += c;
break;
}
}
/**
* EFFECTS: Handles and updates parser state/buffers for a single character while in the VALUE state.
* MODIFIES: this
*/
private void caseValue(char c) {
switch (c) {
case '\'': state = ParserState.SINGLE_QUOTES;
break;
case '\"': state = ParserState.DOUBLE_QUOTES;
break;
case ' ': case '\n':
state = ParserState.KEY;
currentAttributes.add(new Pair<>(currentKey, currentValue));
currentKey = "";
currentValue = "";
break; // THE FOOTGUN DESIGN STRIKES AGAIN
case '>':
if (!currentKey.equals("") || !currentValue.equals("")) {
currentAttributes.add(new Pair<>(currentKey, currentValue));
currentKey = "";
currentValue = "";
}
addNewElementNode();
break;
default:
currentValue += c;
break;
}
}
/**
* EFFECTS: Handles and updates parser state/buffers for a single character while in the SINGLE_QUOTES state.
* MODIFIES: this
*/
private void caseSingleQuotes(char c) {
switch (c) {
case '\'':
if (previousChar != '\\') {
state = ParserState.VALUE;
previousChar = '\0';
} else {
currentValue = currentValue.substring(0, currentValue.length() - 1);
currentValue += c;
previousChar = c;
}
break;
default:
currentValue += c;
previousChar = c;
break;
}
}
/**
* EFFECTS: Handles and updates parser state/buffers for a single character while in the DOUBLE_QUOTES state.
* MODIFIES: this
*/
private void caseDoubleQuotes(char c) {
switch (c) {
case '\"':
if (previousChar != '\\') {
state = ParserState.VALUE;
previousChar = '\0';
} else {
currentValue = currentValue.substring(0, currentValue.length() - 1);
currentValue += c;
previousChar = c;
}
break; // FOOTGUN LANGUAGE DESIGN
default:
currentValue += c;
previousChar = c;
break;
}
}
/**
* Helper function to remove code duplication.
* EFFECTS: Creates and adds a new ElementNode from the current buffers to the unfinished and result stacks
* MODIFIES: this
*/
private void addNewElementNode() {
state = ParserState.HTML;
ElementNode node = new ElementNode(currentTag, currentAttributes);
if (unfinished.size() != 0) {
unfinished.getLast().addChild(node);
if (!isSelfClosingTag(currentTag)) {
unfinished.add(node);
}
} else {
result.add(node);
if (!isSelfClosingTag(currentTag)) {
unfinished.add((ElementNode) result.get(result.size() - 1));
}
}
currentTag = "";
currentAttributes = new ArrayList<>();
}
/**
* Helper function to check method length boxes.
* EFFECTS: Creates and adds a new TextNode from the current buffers to the unfinished and result stacks
* MODIFIES: this
*/
private void addNewTextNode() {
if (unfinished.size() != 0) {
unfinished.getLast().addChild(new TextNode(currentText));
} else {
result.add(new TextNode(currentText));
}
currentText = "";
previousChar = '\0';
}
/**
* Simple helper function to check if a tag is self-closing.
* EFFECTS: Returns whether a String tag is a self-closing tag.
*/
private static boolean isSelfClosingTag(String tag) {
switch (tag) {
case "input": case "param":
case "br": case "hr": case "wbr":
case "img": case "embed": case "area":
case "meta": case "base": case "link":
case "source": case "track": case "col":
return true;
default:
return false;
}
}
public JSONObject serialize() {
return new JSONObject(this);
}
}
/*
<!DOCTYPE html>
<html>
<head>
<title>j-james</title>
<meta charset="utf-8"/>
<meta name="viewport" content="width=device-width"/>
<link rel="icon" type="image/jpg" href="assets/compass.jpg"/>
<link rel="stylesheet" href="css/normalize.css"/>
<link rel="stylesheet" href="css/style.css"/>
</head>
<body>
<header>
<h1>
<a href="https://j-james.me">j-james</a>
</h1>
<nav>
<a href="https://j-james.me/about">about</a>
<a href="https://j-james.me/resume">resume</a>
<a href="https://j-james.me/posts">posts</a>
<a href="https://j-james.me/writeups">writeups</a>
</nav>
</header>
<main>
<div id="intro">
<img id="face" src="assets/compass.jpg"/>
</div>
<div id="details">
<h2>Projects</h2>
<p> Lorem ipsum dolor sit amet, consectetur adipiscing elit,
sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris
nisi ut aliquip ex ea commodo consequat.
Duis aute irure dolor in reprehenderit in voluptate velit esse cillum
dolore eu fugiat nulla pariatur.
Excepteur sint occaecat cupidatat non proident, sunt in culpa
qui officia deserunt mollit anim id est laborum. </p>
<!-- <h2>Posts</h2>
<p> Lorem ipsum dolor sit amet, consectetur adipiscing elit,
sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris
nisi ut aliquip ex ea commodo consequat.
Duis aute irure dolor in reprehenderit in voluptate velit esse cillum
dolore eu fugiat nulla pariatur.
Excepteur sint occaecat cupidatat non proident, sunt in culpa
qui officia deserunt mollit anim id est laborum. </p> -->
</div>
</main>
<footer>
<span><img src="assets/copyleft.svg" width="12" height="12"/> 2020-2022 j-james </span>
</footer>
</body>
</html>
*/
|
