nokogumbo 2.0.0.pre.alpha → 2.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +81 -10
- data/ext/nokogumbo/extconf.rb +6 -1
- data/ext/nokogumbo/nokogumbo.c +579 -233
- data/gumbo-parser/src/ascii.c +42 -0
- data/gumbo-parser/src/ascii.h +91 -7
- data/gumbo-parser/src/char_ref.c +5973 -4601
- data/gumbo-parser/src/char_ref.h +13 -28
- data/gumbo-parser/src/error.c +376 -120
- data/gumbo-parser/src/error.h +63 -125
- data/gumbo-parser/src/gumbo.h +47 -4
- data/gumbo-parser/src/parser.c +849 -709
- data/gumbo-parser/src/string_buffer.c +1 -1
- data/gumbo-parser/src/string_buffer.h +1 -1
- data/gumbo-parser/src/token_buffer.c +79 -0
- data/gumbo-parser/src/token_buffer.h +71 -0
- data/gumbo-parser/src/tokenizer.c +1426 -1261
- data/gumbo-parser/src/tokenizer.h +5 -5
- data/gumbo-parser/src/tokenizer_states.h +275 -23
- data/gumbo-parser/src/utf8.c +12 -59
- data/gumbo-parser/src/utf8.h +51 -16
- data/lib/nokogumbo.rb +0 -1
- data/lib/nokogumbo/html5.rb +2 -1
- data/lib/nokogumbo/html5/document.rb +12 -1
- data/lib/nokogumbo/html5/document_fragment.rb +35 -20
- data/lib/nokogumbo/{xml → html5}/node.rb +28 -13
- data/lib/nokogumbo/version.rb +1 -1
- metadata +16 -9
- data/CHANGELOG.md +0 -56
data/gumbo-parser/src/char_ref.h
CHANGED
@@ -1,40 +1,25 @@
|
|
1
1
|
#ifndef GUMBO_CHAR_REF_H_
|
2
2
|
#define GUMBO_CHAR_REF_H_
|
3
3
|
|
4
|
-
#include <
|
4
|
+
#include <stdlib.h>
|
5
5
|
|
6
6
|
#ifdef __cplusplus
|
7
7
|
extern "C" {
|
8
8
|
#endif
|
9
9
|
|
10
|
-
struct GumboInternalParser;
|
11
|
-
struct GumboInternalUtf8Iterator;
|
12
|
-
|
13
10
|
// Value that indicates no character was produced.
|
14
|
-
|
15
|
-
|
16
|
-
//
|
17
|
-
//
|
18
|
-
//
|
19
|
-
//
|
20
|
-
//
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
// Implements the "consume a character reference" section of the spec.
|
27
|
-
// This reads in characters from the input as necessary, and fills in a
|
28
|
-
// OneOrTwoCodepoints struct containing the characters read. It may add parse
|
29
|
-
// errors to the GumboParser's errors vector, if the spec calls for it. Pass a
|
30
|
-
// space for the "additional allowed char" when the spec says "with no
|
31
|
-
// additional allowed char". Returns false on parse error, true otherwise.
|
32
|
-
bool gumbo_consume_char_ref (
|
33
|
-
struct GumboInternalParser* parser,
|
34
|
-
struct GumboInternalUtf8Iterator* input,
|
35
|
-
int additional_allowed_char,
|
36
|
-
bool is_in_attribute,
|
37
|
-
OneOrTwoCodepoints* output
|
11
|
+
#define kGumboNoChar (-1)
|
12
|
+
|
13
|
+
// On input, str points to the start of the string to match and size is the
|
14
|
+
// size of the string.
|
15
|
+
//
|
16
|
+
// Returns the length of the match or 0 if there is no match.
|
17
|
+
// output[0] contains the first codepoint and output[1] contains the second if
|
18
|
+
// there are two, otherwise output[1] contains kGumboNoChar.
|
19
|
+
size_t match_named_char_ref (
|
20
|
+
const char *str,
|
21
|
+
size_t size,
|
22
|
+
int output[2]
|
38
23
|
);
|
39
24
|
|
40
25
|
#ifdef __cplusplus
|
data/gumbo-parser/src/error.c
CHANGED
@@ -19,6 +19,7 @@
|
|
19
19
|
#include <stdarg.h>
|
20
20
|
#include <stdio.h>
|
21
21
|
#include <string.h>
|
22
|
+
#include "ascii.h"
|
22
23
|
#include "error.h"
|
23
24
|
#include "gumbo.h"
|
24
25
|
#include "macros.h"
|
@@ -45,13 +46,13 @@ static int PRINTF(2) print_message (
|
|
45
46
|
args
|
46
47
|
);
|
47
48
|
va_end(args);
|
48
|
-
#
|
49
|
+
#if _MSC_VER && _MSC_VER < 1900
|
49
50
|
if (bytes_written == -1) {
|
50
|
-
// vsnprintf returns -1 on MSVC++ if there's not enough capacity,
|
51
|
-
// returning the number of bytes that would've been written had
|
52
|
-
// enough. In this case, we'll double the buffer size and hope
|
53
|
-
// we retry (letting it fail and returning 0 if it doesn't),
|
54
|
-
// no way to smartly resize the buffer.
|
51
|
+
// vsnprintf returns -1 on older MSVC++ if there's not enough capacity,
|
52
|
+
// instead of returning the number of bytes that would've been written had
|
53
|
+
// there been enough. In this case, we'll double the buffer size and hope
|
54
|
+
// it fits when we retry (letting it fail and returning 0 if it doesn't),
|
55
|
+
// since there's no way to smartly resize the buffer.
|
55
56
|
gumbo_string_buffer_reserve(output->capacity * 2, output);
|
56
57
|
va_start(args, format);
|
57
58
|
int result = vsnprintf (
|
@@ -101,6 +102,214 @@ static void print_tag_stack (
|
|
101
102
|
gumbo_string_buffer_append_codepoint('.', output);
|
102
103
|
}
|
103
104
|
|
105
|
+
static void handle_tokenizer_error (
|
106
|
+
const GumboError* error,
|
107
|
+
GumboStringBuffer* output
|
108
|
+
) {
|
109
|
+
switch (error->type) {
|
110
|
+
case GUMBO_ERR_ABRUPT_CLOSING_OF_EMPTY_COMMENT:
|
111
|
+
print_message(output, "Empty comment abruptly closed by '%s', use '-->'.",
|
112
|
+
error->v.tokenizer.state == GUMBO_LEX_COMMENT_START? ">" : "->");
|
113
|
+
break;
|
114
|
+
case GUMBO_ERR_ABRUPT_DOCTYPE_PUBLIC_IDENTIFIER:
|
115
|
+
print_message (
|
116
|
+
output,
|
117
|
+
"DOCTYPE public identifier missing closing %s.",
|
118
|
+
error->v.tokenizer.state == GUMBO_LEX_DOCTYPE_PUBLIC_ID_DOUBLE_QUOTED?
|
119
|
+
"quotation mark (\")" : "apostrophe (')"
|
120
|
+
);
|
121
|
+
break;
|
122
|
+
case GUMBO_ERR_ABRUPT_DOCTYPE_SYSTEM_IDENTIFIER:
|
123
|
+
print_message (
|
124
|
+
output,
|
125
|
+
"DOCTYPE system identifier missing closing %s.",
|
126
|
+
error->v.tokenizer.state == GUMBO_LEX_DOCTYPE_SYSTEM_ID_DOUBLE_QUOTED?
|
127
|
+
"quotation mark (\")" : "apostrophe (')"
|
128
|
+
);
|
129
|
+
break;
|
130
|
+
case GUMBO_ERR_ABSENCE_OF_DIGITS_IN_NUMERIC_CHARACTER_REFERENCE:
|
131
|
+
print_message (
|
132
|
+
output,
|
133
|
+
"Numeric character reference '%.*s' does not contain any %sdigits.",
|
134
|
+
(int)error->original_text.length, error->original_text.data,
|
135
|
+
error->v.tokenizer.state == GUMBO_LEX_HEXADECIMAL_CHARACTER_REFERENCE_START? "hexadecimal " : ""
|
136
|
+
);
|
137
|
+
break;
|
138
|
+
case GUMBO_ERR_CDATA_IN_HTML_CONTENT:
|
139
|
+
print_message(output, "CDATA section outside foreign (SVG or MathML) content.");
|
140
|
+
break;
|
141
|
+
case GUMBO_ERR_CHARACTER_REFERENCE_OUTSIDE_UNICODE_RANGE:
|
142
|
+
print_message (
|
143
|
+
output,
|
144
|
+
"Numeric character reference '%.*s' references a code point that is outside the valid Unicode range.",
|
145
|
+
(int)error->original_text.length, error->original_text.data
|
146
|
+
);
|
147
|
+
break;
|
148
|
+
case GUMBO_ERR_CONTROL_CHARACTER_IN_INPUT_STREAM:
|
149
|
+
print_message (
|
150
|
+
output,
|
151
|
+
"Input contains prohibited control code point U+%04X.",
|
152
|
+
error->v.tokenizer.codepoint
|
153
|
+
);
|
154
|
+
break;
|
155
|
+
case GUMBO_ERR_CONTROL_CHARACTER_REFERENCE:
|
156
|
+
print_message (
|
157
|
+
output,
|
158
|
+
"Numeric character reference '%.*s' references prohibited control code point U+%04X.",
|
159
|
+
(int)error->original_text.length, error->original_text.data,
|
160
|
+
error->v.tokenizer.codepoint
|
161
|
+
);
|
162
|
+
break;
|
163
|
+
case GUMBO_ERR_END_TAG_WITH_ATTRIBUTES:
|
164
|
+
print_message(output, "End tag contains attributes.");
|
165
|
+
break;
|
166
|
+
case GUMBO_ERR_DUPLICATE_ATTRIBUTE:
|
167
|
+
print_message(output, "Tag contains multiple attributes with the same name.");
|
168
|
+
break;
|
169
|
+
case GUMBO_ERR_END_TAG_WITH_TRAILING_SOLIDUS:
|
170
|
+
print_message(output, "End tag ends with '/>', use '>'.");
|
171
|
+
break;
|
172
|
+
case GUMBO_ERR_EOF_BEFORE_TAG_NAME:
|
173
|
+
print_message(output, "End of input where a tag name is expected.");
|
174
|
+
break;
|
175
|
+
case GUMBO_ERR_EOF_IN_CDATA:
|
176
|
+
print_message(output, "End of input in CDATA section.");
|
177
|
+
break;
|
178
|
+
case GUMBO_ERR_EOF_IN_COMMENT:
|
179
|
+
print_message(output, "End of input in comment.");
|
180
|
+
break;
|
181
|
+
case GUMBO_ERR_EOF_IN_DOCTYPE:
|
182
|
+
print_message(output, "End of input in DOCTYPE.");
|
183
|
+
break;
|
184
|
+
case GUMBO_ERR_EOF_IN_SCRIPT_HTML_COMMENT_LIKE_TEXT:
|
185
|
+
print_message(output, "End of input in text that resembles an HTML comment inside script element content.");
|
186
|
+
break;
|
187
|
+
case GUMBO_ERR_EOF_IN_TAG:
|
188
|
+
print_message(output, "End of input in tag.");
|
189
|
+
break;
|
190
|
+
case GUMBO_ERR_INCORRECTLY_CLOSED_COMMENT:
|
191
|
+
print_message(output, "Comment closed incorrectly by '--!>', use '-->'.");
|
192
|
+
break;
|
193
|
+
case GUMBO_ERR_INCORRECTLY_OPENED_COMMENT:
|
194
|
+
print_message(output, "Comment, DOCTYPE, or CDATA opened incorrectly, use '<!--', '<!DOCTYPE', or '<![CDATA['.");
|
195
|
+
break;
|
196
|
+
case GUMBO_ERR_INVALID_CHARACTER_SEQUENCE_AFTER_DOCTYPE_NAME:
|
197
|
+
print_message(output, "Invalid character sequence after DOCTYPE name, expected 'PUBLIC', 'SYSTEM', or '>'.");
|
198
|
+
break;
|
199
|
+
case GUMBO_ERR_INVALID_FIRST_CHARACTER_OF_TAG_NAME:
|
200
|
+
if (gumbo_ascii_isascii(error->v.tokenizer.codepoint)
|
201
|
+
&& !gumbo_ascii_iscntrl(error->v.tokenizer.codepoint))
|
202
|
+
print_message(output, "Invalid first character of tag name '%c'.", error->v.tokenizer.codepoint);
|
203
|
+
else
|
204
|
+
print_message(output, "Invalid first code point of tag name U+%04X.", error->v.tokenizer.codepoint);
|
205
|
+
break;
|
206
|
+
case GUMBO_ERR_MISSING_ATTRIBUTE_VALUE:
|
207
|
+
print_message(output, "Missing attribute value.");
|
208
|
+
break;
|
209
|
+
case GUMBO_ERR_MISSING_DOCTYPE_NAME:
|
210
|
+
print_message(output, "Missing DOCTYPE name.");
|
211
|
+
break;
|
212
|
+
case GUMBO_ERR_MISSING_DOCTYPE_PUBLIC_IDENTIFIER:
|
213
|
+
print_message(output, "Missing DOCTYPE public identifier.");
|
214
|
+
break;
|
215
|
+
case GUMBO_ERR_MISSING_DOCTYPE_SYSTEM_IDENTIFIER:
|
216
|
+
print_message(output, "Missing DOCTYPE system identifier.");
|
217
|
+
break;
|
218
|
+
case GUMBO_ERR_MISSING_END_TAG_NAME:
|
219
|
+
print_message(output, "Missing end tag name.");
|
220
|
+
break;
|
221
|
+
case GUMBO_ERR_MISSING_QUOTE_BEFORE_DOCTYPE_PUBLIC_IDENTIFIER:
|
222
|
+
print_message(output, "Missing quote before DOCTYPE public identifier.");
|
223
|
+
break;
|
224
|
+
case GUMBO_ERR_MISSING_QUOTE_BEFORE_DOCTYPE_SYSTEM_IDENTIFIER:
|
225
|
+
print_message(output, "Missing quote before DOCTYPE system identifier.");
|
226
|
+
break;
|
227
|
+
case GUMBO_ERR_MISSING_SEMICOLON_AFTER_CHARACTER_REFERENCE:
|
228
|
+
print_message(output, "Missing semicolon after character reference '%.*s'.",
|
229
|
+
(int)error->original_text.length, error->original_text.data);
|
230
|
+
break;
|
231
|
+
case GUMBO_ERR_MISSING_WHITESPACE_AFTER_DOCTYPE_PUBLIC_KEYWORD:
|
232
|
+
print_message(output, "Missing whitespace after 'PUBLIC' keyword.");
|
233
|
+
break;
|
234
|
+
case GUMBO_ERR_MISSING_WHITESPACE_AFTER_DOCTYPE_SYSTEM_KEYWORD:
|
235
|
+
print_message(output, "Missing whitespace after 'SYSTEM' keyword.");
|
236
|
+
break;
|
237
|
+
case GUMBO_ERR_MISSING_WHITESPACE_BEFORE_DOCTYPE_NAME:
|
238
|
+
print_message(output, "Missing whitespace between 'DOCTYPE' keyword and DOCTYPE name.");
|
239
|
+
break;
|
240
|
+
case GUMBO_ERR_MISSING_WHITESPACE_BETWEEN_ATTRIBUTES:
|
241
|
+
print_message(output, "Missing whitespace between attributes.");
|
242
|
+
break;
|
243
|
+
case GUMBO_ERR_MISSING_WHITESPACE_BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS:
|
244
|
+
print_message(output, "Missing whitespace between DOCTYPE public and system identifiers.");
|
245
|
+
break;
|
246
|
+
case GUMBO_ERR_NESTED_COMMENT:
|
247
|
+
print_message(output, "Nested comment.");
|
248
|
+
break;
|
249
|
+
case GUMBO_ERR_NONCHARACTER_CHARACTER_REFERENCE:
|
250
|
+
print_message (
|
251
|
+
output,
|
252
|
+
"Numeric character reference '%.*s' references noncharacter U+%04X.",
|
253
|
+
(int)error->original_text.length, error->original_text.data,
|
254
|
+
error->v.tokenizer.codepoint
|
255
|
+
);
|
256
|
+
break;
|
257
|
+
case GUMBO_ERR_NONCHARACTER_IN_INPUT_STREAM:
|
258
|
+
print_message(output, "Input contains noncharacter U+%04X.", error->v.tokenizer.codepoint);
|
259
|
+
break;
|
260
|
+
case GUMBO_ERR_NON_VOID_HTML_ELEMENT_START_TAG_WITH_TRAILING_SOLIDUS:
|
261
|
+
print_message(output, "Start tag of nonvoid HTML element ends with '/>', use '>'.");
|
262
|
+
break;
|
263
|
+
case GUMBO_ERR_NULL_CHARACTER_REFERENCE:
|
264
|
+
print_message(output, "Numeric character reference '%.*s' references U+0000.",
|
265
|
+
(int)error->original_text.length, error->original_text.data);
|
266
|
+
break;
|
267
|
+
case GUMBO_ERR_SURROGATE_CHARACTER_REFERENCE:
|
268
|
+
print_message (
|
269
|
+
output,
|
270
|
+
"Numeric character reference '%.*s' references surrogate U+%4X.",
|
271
|
+
(int)error->original_text.length, error->original_text.data,
|
272
|
+
error->v.tokenizer.codepoint
|
273
|
+
);
|
274
|
+
break;
|
275
|
+
case GUMBO_ERR_SURROGATE_IN_INPUT_STREAM:
|
276
|
+
print_message(output, "Input contains surrogate U+%04X.", error->v.tokenizer.codepoint);
|
277
|
+
break;
|
278
|
+
case GUMBO_ERR_UNEXPECTED_CHARACTER_AFTER_DOCTYPE_SYSTEM_IDENTIFIER:
|
279
|
+
print_message(output, "Unexpected character after DOCTYPE system identifier.");
|
280
|
+
break;
|
281
|
+
case GUMBO_ERR_UNEXPECTED_CHARACTER_IN_ATTRIBUTE_NAME:
|
282
|
+
print_message(output, "Unexpected character (%c) in attribute name.", error->v.tokenizer.codepoint);
|
283
|
+
break;
|
284
|
+
case GUMBO_ERR_UNEXPECTED_CHARACTER_IN_UNQUOTED_ATTRIBUTE_VALUE:
|
285
|
+
print_message(output, "Unexpected character (%c) in unquoted attribute value.", error->v.tokenizer.codepoint);
|
286
|
+
break;
|
287
|
+
case GUMBO_ERR_UNEXPECTED_EQUALS_SIGN_BEFORE_ATTRIBUTE_NAME:
|
288
|
+
print_message(output, "Unexpected '=' before an attribute name.");
|
289
|
+
break;
|
290
|
+
case GUMBO_ERR_UNEXPECTED_NULL_CHARACTER:
|
291
|
+
print_message(output, "Input contains unexpected U+0000.");
|
292
|
+
break;
|
293
|
+
case GUMBO_ERR_UNEXPECTED_QUESTION_MARK_INSTEAD_OF_TAG_NAME:
|
294
|
+
print_message(output, "Unexpected '?' where start tag name is expected.");
|
295
|
+
break;
|
296
|
+
case GUMBO_ERR_UNEXPECTED_SOLIDUS_IN_TAG:
|
297
|
+
print_message(output, "Unexpected '/' in tag.");
|
298
|
+
break;
|
299
|
+
case GUMBO_ERR_UNKNOWN_NAMED_CHARACTER_REFERENCE:
|
300
|
+
print_message(output, "Unknown named character reference '%.*s'.",
|
301
|
+
(int)error->original_text.length, error->original_text.data);
|
302
|
+
break;
|
303
|
+
case GUMBO_ERR_UTF8_INVALID:
|
304
|
+
print_message(output, "Invalid UTF8 encoding.");
|
305
|
+
break;
|
306
|
+
case GUMBO_ERR_UTF8_TRUNCATED:
|
307
|
+
print_message(output, "UTF8 character truncated.");
|
308
|
+
break;
|
309
|
+
case GUMBO_ERR_PARSER:
|
310
|
+
assert(0 && "Unreachable.");
|
311
|
+
}
|
312
|
+
}
|
104
313
|
static void handle_parser_error (
|
105
314
|
const GumboParserError* error,
|
106
315
|
GumboStringBuffer* output
|
@@ -111,7 +320,7 @@ static void handle_parser_error (
|
|
111
320
|
) {
|
112
321
|
print_message (
|
113
322
|
output,
|
114
|
-
"
|
323
|
+
"Expected a doctype token"
|
115
324
|
);
|
116
325
|
return;
|
117
326
|
}
|
@@ -191,122 +400,155 @@ GumboError* gumbo_add_error(GumboParser* parser) {
|
|
191
400
|
return error;
|
192
401
|
}
|
193
402
|
|
194
|
-
|
403
|
+
GumboSourcePosition gumbo_error_position(const GumboError* error) {
|
404
|
+
return error->position;
|
405
|
+
}
|
406
|
+
|
407
|
+
const char* gumbo_error_code(const GumboError* error) {
|
408
|
+
switch (error->type) {
|
409
|
+
// Defined tokenizer errors.
|
410
|
+
case GUMBO_ERR_ABRUPT_CLOSING_OF_EMPTY_COMMENT:
|
411
|
+
return "abrupt-closing-of-empty-comment";
|
412
|
+
case GUMBO_ERR_ABRUPT_DOCTYPE_PUBLIC_IDENTIFIER:
|
413
|
+
return "abrupt-doctype-public-identifier";
|
414
|
+
case GUMBO_ERR_ABRUPT_DOCTYPE_SYSTEM_IDENTIFIER:
|
415
|
+
return "abrupt-doctype-system-identifier";
|
416
|
+
case GUMBO_ERR_ABSENCE_OF_DIGITS_IN_NUMERIC_CHARACTER_REFERENCE:
|
417
|
+
return "absence-of-digits-in-numeric-character-reference";
|
418
|
+
case GUMBO_ERR_CDATA_IN_HTML_CONTENT:
|
419
|
+
return "cdata-in-html-content";
|
420
|
+
case GUMBO_ERR_CHARACTER_REFERENCE_OUTSIDE_UNICODE_RANGE:
|
421
|
+
return "character-reference-outside-unicode-range";
|
422
|
+
case GUMBO_ERR_CONTROL_CHARACTER_IN_INPUT_STREAM:
|
423
|
+
return "control-character-in-input-stream";
|
424
|
+
case GUMBO_ERR_CONTROL_CHARACTER_REFERENCE:
|
425
|
+
return "control-character-reference";
|
426
|
+
case GUMBO_ERR_END_TAG_WITH_ATTRIBUTES:
|
427
|
+
return "end-tag-with-attributes";
|
428
|
+
case GUMBO_ERR_DUPLICATE_ATTRIBUTE:
|
429
|
+
return "duplicate-attribute";
|
430
|
+
case GUMBO_ERR_END_TAG_WITH_TRAILING_SOLIDUS:
|
431
|
+
return "end-tag-with-trailing-solidus";
|
432
|
+
case GUMBO_ERR_EOF_BEFORE_TAG_NAME:
|
433
|
+
return "eof-before-tag-name";
|
434
|
+
case GUMBO_ERR_EOF_IN_CDATA:
|
435
|
+
return "eof-in-cdata";
|
436
|
+
case GUMBO_ERR_EOF_IN_COMMENT:
|
437
|
+
return "eof-in-comment";
|
438
|
+
case GUMBO_ERR_EOF_IN_DOCTYPE:
|
439
|
+
return "eof-in-doctype";
|
440
|
+
case GUMBO_ERR_EOF_IN_SCRIPT_HTML_COMMENT_LIKE_TEXT:
|
441
|
+
return "eof-in-script-html-comment-like-text";
|
442
|
+
case GUMBO_ERR_EOF_IN_TAG:
|
443
|
+
return "eof-in-tag";
|
444
|
+
case GUMBO_ERR_INCORRECTLY_CLOSED_COMMENT:
|
445
|
+
return "incorrectly-closed-comment";
|
446
|
+
case GUMBO_ERR_INCORRECTLY_OPENED_COMMENT:
|
447
|
+
return "incorrectly-opened-comment";
|
448
|
+
case GUMBO_ERR_INVALID_CHARACTER_SEQUENCE_AFTER_DOCTYPE_NAME:
|
449
|
+
return "invalid-character-sequence-after-doctype-name";
|
450
|
+
case GUMBO_ERR_INVALID_FIRST_CHARACTER_OF_TAG_NAME:
|
451
|
+
return "invalid-first-character-of-tag-name";
|
452
|
+
case GUMBO_ERR_MISSING_ATTRIBUTE_VALUE:
|
453
|
+
return "missing-attribute-value";
|
454
|
+
case GUMBO_ERR_MISSING_DOCTYPE_NAME:
|
455
|
+
return "missing-doctype-name";
|
456
|
+
case GUMBO_ERR_MISSING_DOCTYPE_PUBLIC_IDENTIFIER:
|
457
|
+
return "missing-doctype-public-identifier";
|
458
|
+
case GUMBO_ERR_MISSING_DOCTYPE_SYSTEM_IDENTIFIER:
|
459
|
+
return "missing-doctype-system-identifier";
|
460
|
+
case GUMBO_ERR_MISSING_END_TAG_NAME:
|
461
|
+
return "missing-end-tag-name";
|
462
|
+
case GUMBO_ERR_MISSING_QUOTE_BEFORE_DOCTYPE_PUBLIC_IDENTIFIER:
|
463
|
+
return "missing-quote-before-doctype-public-identifier";
|
464
|
+
case GUMBO_ERR_MISSING_QUOTE_BEFORE_DOCTYPE_SYSTEM_IDENTIFIER:
|
465
|
+
return "missing-quote-before-doctype-system-identifier";
|
466
|
+
case GUMBO_ERR_MISSING_SEMICOLON_AFTER_CHARACTER_REFERENCE:
|
467
|
+
return "missing-semicolon-after-character-reference";
|
468
|
+
case GUMBO_ERR_MISSING_WHITESPACE_AFTER_DOCTYPE_PUBLIC_KEYWORD:
|
469
|
+
return "missing-whitespace-after-doctype-public-keyword";
|
470
|
+
case GUMBO_ERR_MISSING_WHITESPACE_AFTER_DOCTYPE_SYSTEM_KEYWORD:
|
471
|
+
return "missing-whitespace-after-doctype-system-keyword";
|
472
|
+
case GUMBO_ERR_MISSING_WHITESPACE_BEFORE_DOCTYPE_NAME:
|
473
|
+
return "missing-whitespace-before-doctype-name";
|
474
|
+
case GUMBO_ERR_MISSING_WHITESPACE_BETWEEN_ATTRIBUTES:
|
475
|
+
return "missing-whitespace-between-attributes";
|
476
|
+
case GUMBO_ERR_MISSING_WHITESPACE_BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS:
|
477
|
+
return "missing-whitespace-between-doctype-public-and-system-identifiers";
|
478
|
+
case GUMBO_ERR_NESTED_COMMENT:
|
479
|
+
return "nested-comment";
|
480
|
+
case GUMBO_ERR_NONCHARACTER_CHARACTER_REFERENCE:
|
481
|
+
return "noncharacter-character-reference";
|
482
|
+
case GUMBO_ERR_NONCHARACTER_IN_INPUT_STREAM:
|
483
|
+
return "noncharacter-in-input-stream";
|
484
|
+
case GUMBO_ERR_NON_VOID_HTML_ELEMENT_START_TAG_WITH_TRAILING_SOLIDUS:
|
485
|
+
return "non-void-html-element-start-tag-with-trailing-solidus";
|
486
|
+
case GUMBO_ERR_NULL_CHARACTER_REFERENCE:
|
487
|
+
return "null-character-reference";
|
488
|
+
case GUMBO_ERR_SURROGATE_CHARACTER_REFERENCE:
|
489
|
+
return "surrogate-character-reference";
|
490
|
+
case GUMBO_ERR_SURROGATE_IN_INPUT_STREAM:
|
491
|
+
return "surrogate-in-input-stream";
|
492
|
+
case GUMBO_ERR_UNEXPECTED_CHARACTER_AFTER_DOCTYPE_SYSTEM_IDENTIFIER:
|
493
|
+
return "unexpected-character-after-doctype-system-identifier";
|
494
|
+
case GUMBO_ERR_UNEXPECTED_CHARACTER_IN_ATTRIBUTE_NAME:
|
495
|
+
return "unexpected-character-in-attribute-name";
|
496
|
+
case GUMBO_ERR_UNEXPECTED_CHARACTER_IN_UNQUOTED_ATTRIBUTE_VALUE:
|
497
|
+
return "unexpected-character-in-unquoted-attribute-value";
|
498
|
+
case GUMBO_ERR_UNEXPECTED_EQUALS_SIGN_BEFORE_ATTRIBUTE_NAME:
|
499
|
+
return "unexpected-equals-sign-before-attribute-name";
|
500
|
+
case GUMBO_ERR_UNEXPECTED_NULL_CHARACTER:
|
501
|
+
return "unexpected-null-character";
|
502
|
+
case GUMBO_ERR_UNEXPECTED_QUESTION_MARK_INSTEAD_OF_TAG_NAME:
|
503
|
+
return "unexpected-question-mark-instead-of-tag-name";
|
504
|
+
case GUMBO_ERR_UNEXPECTED_SOLIDUS_IN_TAG:
|
505
|
+
return "unexpected-solidus-in-tag";
|
506
|
+
case GUMBO_ERR_UNKNOWN_NAMED_CHARACTER_REFERENCE:
|
507
|
+
return "unknown-named-character-reference";
|
508
|
+
|
509
|
+
// Encoding errors.
|
510
|
+
case GUMBO_ERR_UTF8_INVALID:
|
511
|
+
return "utf8-invalid";
|
512
|
+
case GUMBO_ERR_UTF8_TRUNCATED:
|
513
|
+
return "utf8-truncated";
|
514
|
+
|
515
|
+
// Generic parser error.
|
516
|
+
case GUMBO_ERR_PARSER:
|
517
|
+
return "generic-parser";
|
518
|
+
}
|
519
|
+
// Silence warning about control reaching end of non-void function.
|
520
|
+
// All errors _should_ be handled in the switch statement.
|
521
|
+
return "generic-parser";
|
522
|
+
}
|
523
|
+
|
524
|
+
static void error_to_string (
|
195
525
|
const GumboError* error,
|
196
526
|
GumboStringBuffer* output
|
197
527
|
) {
|
198
|
-
|
199
|
-
output
|
200
|
-
|
201
|
-
error->
|
202
|
-
|
203
|
-
|
204
|
-
|
205
|
-
|
206
|
-
|
207
|
-
|
208
|
-
|
209
|
-
|
210
|
-
);
|
211
|
-
break;
|
212
|
-
case GUMBO_ERR_UTF8_TRUNCATED:
|
213
|
-
print_message (
|
214
|
-
output,
|
215
|
-
"Input stream ends with a truncated UTF8 character 0x%" PRIx32,
|
216
|
-
error->v.codepoint
|
217
|
-
);
|
218
|
-
break;
|
219
|
-
case GUMBO_ERR_UTF8_NULL:
|
220
|
-
print_message (
|
221
|
-
output,
|
222
|
-
"Unexpected NULL character in the input stream"
|
223
|
-
);
|
224
|
-
break;
|
225
|
-
case GUMBO_ERR_NUMERIC_CHAR_REF_NO_DIGITS:
|
226
|
-
print_message (
|
227
|
-
output,
|
228
|
-
"No digits after &# in numeric character reference"
|
229
|
-
);
|
230
|
-
break;
|
231
|
-
case GUMBO_ERR_NUMERIC_CHAR_REF_WITHOUT_SEMICOLON:
|
232
|
-
print_message (
|
233
|
-
output,
|
234
|
-
"The numeric character reference &#%" PRIu32 " should be followed "
|
235
|
-
"by a semicolon",
|
236
|
-
error->v.codepoint
|
237
|
-
);
|
238
|
-
break;
|
239
|
-
case GUMBO_ERR_NUMERIC_CHAR_REF_INVALID:
|
240
|
-
print_message (
|
241
|
-
output,
|
242
|
-
"The numeric character reference &#%" PRIu32 "; encodes an invalid "
|
243
|
-
"unicode codepoint",
|
244
|
-
error->v.codepoint
|
245
|
-
);
|
246
|
-
break;
|
247
|
-
case GUMBO_ERR_NAMED_CHAR_REF_WITHOUT_SEMICOLON:
|
248
|
-
// The textual data came from one of the literal strings in the table, and
|
249
|
-
// so it'll be null-terminated.
|
250
|
-
print_message (
|
251
|
-
output,
|
252
|
-
"The named character reference &%.*s should be followed by a "
|
253
|
-
"semicolon",
|
254
|
-
(int) error->v.text.length,
|
255
|
-
error->v.text.data
|
256
|
-
);
|
257
|
-
break;
|
258
|
-
case GUMBO_ERR_NAMED_CHAR_REF_INVALID:
|
259
|
-
print_message (
|
260
|
-
output,
|
261
|
-
"The named character reference &%.*s; is not a valid entity name",
|
262
|
-
(int) error->v.text.length,
|
263
|
-
error->v.text.data
|
264
|
-
);
|
265
|
-
break;
|
266
|
-
case GUMBO_ERR_DUPLICATE_ATTR:
|
267
|
-
print_message (
|
268
|
-
output,
|
269
|
-
"Attribute %s occurs multiple times, at positions %u and %u",
|
270
|
-
error->v.duplicate_attr.name,
|
271
|
-
error->v.duplicate_attr.original_index,
|
272
|
-
error->v.duplicate_attr.new_index
|
273
|
-
);
|
274
|
-
break;
|
275
|
-
case GUMBO_ERR_DASHES_OR_DOCTYPE:
|
276
|
-
print_message (
|
277
|
-
output,
|
278
|
-
"Incorrectly opened comment; expected '--', 'DOCTYPE', or '[CDATA['"
|
279
|
-
);
|
280
|
-
break;
|
281
|
-
case GUMBO_ERR_PARSER:
|
282
|
-
handle_parser_error(&error->v.parser, output);
|
283
|
-
break;
|
284
|
-
case GUMBO_ERR_UNACKNOWLEDGED_SELF_CLOSING_TAG:
|
285
|
-
case GUMBO_ERR_SELF_CLOSING_END_TAG:
|
286
|
-
print_message (
|
287
|
-
output,
|
288
|
-
"Tag cannot be self-closing");
|
289
|
-
break;
|
290
|
-
default:
|
291
|
-
print_message (
|
292
|
-
output,
|
293
|
-
"Tokenizer error with an unimplemented error message"
|
294
|
-
);
|
295
|
-
break;
|
296
|
-
}
|
297
|
-
gumbo_string_buffer_append_codepoint('.', output);
|
528
|
+
if (error->type < GUMBO_ERR_PARSER)
|
529
|
+
handle_tokenizer_error(error, output);
|
530
|
+
else
|
531
|
+
handle_parser_error(&error->v.parser, output);
|
532
|
+
}
|
533
|
+
|
534
|
+
size_t gumbo_error_to_string(const GumboError* error, char** output) {
|
535
|
+
GumboStringBuffer sb;
|
536
|
+
gumbo_string_buffer_init(&sb);
|
537
|
+
error_to_string(error, &sb);
|
538
|
+
*output = sb.data;
|
539
|
+
return sb.length;
|
298
540
|
}
|
299
541
|
|
300
|
-
void
|
542
|
+
void caret_diagnostic_to_string (
|
301
543
|
const GumboError* error,
|
302
544
|
const char* source_text,
|
303
545
|
size_t source_length,
|
304
546
|
GumboStringBuffer* output
|
305
547
|
) {
|
306
|
-
|
548
|
+
error_to_string(error, output);
|
307
549
|
|
308
|
-
const char* line_start = find_prev_newline(source_text, error->original_text);
|
309
|
-
const char* line_end = find_next_newline(source_text + source_length, error->original_text);
|
550
|
+
const char* line_start = find_prev_newline(source_text, error->original_text.data);
|
551
|
+
const char* line_end = find_next_newline(source_text + source_length, error->original_text.data);
|
310
552
|
GumboStringPiece original_line;
|
311
553
|
original_line.data = line_start;
|
312
554
|
original_line.length = line_end - line_start;
|
@@ -324,6 +566,19 @@ void gumbo_caret_diagnostic_to_string (
|
|
324
566
|
gumbo_string_buffer_append_codepoint('\n', output);
|
325
567
|
}
|
326
568
|
|
569
|
+
size_t gumbo_caret_diagnostic_to_string (
|
570
|
+
const GumboError* error,
|
571
|
+
const char* source_text,
|
572
|
+
size_t source_length,
|
573
|
+
char **output
|
574
|
+
) {
|
575
|
+
GumboStringBuffer sb;
|
576
|
+
gumbo_string_buffer_init(&sb);
|
577
|
+
caret_diagnostic_to_string(error, source_text, source_length, &sb);
|
578
|
+
*output = sb.data;
|
579
|
+
return sb.length;
|
580
|
+
}
|
581
|
+
|
327
582
|
void gumbo_print_caret_diagnostic (
|
328
583
|
const GumboError* error,
|
329
584
|
const char* source_text,
|
@@ -331,20 +586,21 @@ void gumbo_print_caret_diagnostic (
|
|
331
586
|
) {
|
332
587
|
GumboStringBuffer text;
|
333
588
|
gumbo_string_buffer_init(&text);
|
334
|
-
|
589
|
+
print_message (
|
590
|
+
&text,
|
591
|
+
"%lu:%lu: ",
|
592
|
+
(unsigned long)error->position.line,
|
593
|
+
(unsigned long)error->position.column
|
594
|
+
);
|
595
|
+
|
596
|
+
caret_diagnostic_to_string(error, source_text, source_length, &text);
|
335
597
|
printf("%.*s", (int) text.length, text.data);
|
336
598
|
gumbo_string_buffer_destroy(&text);
|
337
599
|
}
|
338
600
|
|
339
601
|
void gumbo_error_destroy(GumboError* error) {
|
340
|
-
if (
|
341
|
-
error->type == GUMBO_ERR_PARSER
|
342
|
-
|| error->type == GUMBO_ERR_UNACKNOWLEDGED_SELF_CLOSING_TAG
|
343
|
-
|| error->type == GUMBO_ERR_SELF_CLOSING_END_TAG
|
344
|
-
) {
|
602
|
+
if (error->type == GUMBO_ERR_PARSER) {
|
345
603
|
gumbo_vector_destroy(&error->v.parser.tag_stack);
|
346
|
-
} else if (error->type == GUMBO_ERR_DUPLICATE_ATTR) {
|
347
|
-
gumbo_free((void*) error->v.duplicate_attr.name);
|
348
604
|
}
|
349
605
|
gumbo_free(error);
|
350
606
|
}
|