1 // Copyright 2010 Google Inc. All Rights Reserved.
2 //
3 // Licensed under the Apache License, Version 2.0 (the "License");
4 // you may not use this file except in compliance with the License.
5 // You may obtain a copy of the License at
6 //
7 // http://www.apache.org/licenses/LICENSE-2.0
8 //
9 // Unless required by applicable law or agreed to in writing, software
10 // distributed under the License is distributed on an "AS IS" BASIS,
11 // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
12 // See the License for the specific language governing permissions and
13 // limitations under the License.
14 //
15 // Author: jdtang@google.com (Jonathan Tang)
16
17 #include "string_buffer.h"
18
19 #include <assert.h>
20 #include <stdlib.h>
21 #include <string.h>
22 #include <strings.h>
23
24 #include "string_piece.h"
25 #include "util.h"
26
27 struct GumboInternalParser;
28
29 // Size chosen via statistical analysis of ~60K websites.
30 // 99% of text nodes and 98% of attribute names/values fit in this initial size.
31 static const size_t kDefaultStringBufferSize = 5;
32
maybe_resize_string_buffer(struct GumboInternalParser * parser,size_t additional_chars,GumboStringBuffer * buffer)33 static void maybe_resize_string_buffer(struct GumboInternalParser* parser,
34 size_t additional_chars, GumboStringBuffer* buffer) {
35 size_t new_length = buffer->length + additional_chars;
36 size_t new_capacity = buffer->capacity;
37 while (new_capacity < new_length) {
38 new_capacity *= 2;
39 }
40 if (new_capacity != buffer->capacity) {
41 char* new_data = gumbo_parser_allocate(parser, new_capacity);
42 memcpy(new_data, buffer->data, buffer->length);
43 gumbo_parser_deallocate(parser, buffer->data);
44 buffer->data = new_data;
45 buffer->capacity = new_capacity;
46 }
47 }
48
gumbo_string_buffer_init(struct GumboInternalParser * parser,GumboStringBuffer * output)49 void gumbo_string_buffer_init(
50 struct GumboInternalParser* parser, GumboStringBuffer* output) {
51 output->data = gumbo_parser_allocate(parser, kDefaultStringBufferSize);
52 output->length = 0;
53 output->capacity = kDefaultStringBufferSize;
54 }
55
gumbo_string_buffer_reserve(struct GumboInternalParser * parser,size_t min_capacity,GumboStringBuffer * output)56 void gumbo_string_buffer_reserve(struct GumboInternalParser* parser,
57 size_t min_capacity, GumboStringBuffer* output) {
58 maybe_resize_string_buffer(parser, min_capacity - output->length, output);
59 }
60
gumbo_string_buffer_append_codepoint(struct GumboInternalParser * parser,int c,GumboStringBuffer * output)61 void gumbo_string_buffer_append_codepoint(
62 struct GumboInternalParser* parser, int c, GumboStringBuffer* output) {
63 // num_bytes is actually the number of continuation bytes, 1 less than the
64 // total number of bytes. This is done to keep the loop below simple and
65 // should probably change if we unroll it.
66 int num_bytes, prefix;
67 if (c <= 0x7f) {
68 num_bytes = 0;
69 prefix = 0;
70 } else if (c <= 0x7ff) {
71 num_bytes = 1;
72 prefix = 0xc0;
73 } else if (c <= 0xffff) {
74 num_bytes = 2;
75 prefix = 0xe0;
76 } else {
77 num_bytes = 3;
78 prefix = 0xf0;
79 }
80 maybe_resize_string_buffer(parser, num_bytes + 1, output);
81 output->data[output->length++] = prefix | (c >> (num_bytes * 6));
82 for (int i = num_bytes - 1; i >= 0; --i) {
83 output->data[output->length++] = 0x80 | (0x3f & (c >> (i * 6)));
84 }
85 }
86
gumbo_string_buffer_append_string(struct GumboInternalParser * parser,GumboStringPiece * str,GumboStringBuffer * output)87 void gumbo_string_buffer_append_string(struct GumboInternalParser* parser,
88 GumboStringPiece* str, GumboStringBuffer* output) {
89 maybe_resize_string_buffer(parser, str->length, output);
90 memcpy(output->data + output->length, str->data, str->length);
91 output->length += str->length;
92 }
93
gumbo_string_buffer_to_string(struct GumboInternalParser * parser,GumboStringBuffer * input)94 char* gumbo_string_buffer_to_string(
95 struct GumboInternalParser* parser, GumboStringBuffer* input) {
96 char* buffer = gumbo_parser_allocate(parser, input->length + 1);
97 memcpy(buffer, input->data, input->length);
98 buffer[input->length] = '\0';
99 return buffer;
100 }
101
gumbo_string_buffer_clear(struct GumboInternalParser * parser,GumboStringBuffer * input)102 void gumbo_string_buffer_clear(
103 struct GumboInternalParser* parser, GumboStringBuffer* input) {
104 input->length = 0;
105 }
106
gumbo_string_buffer_destroy(struct GumboInternalParser * parser,GumboStringBuffer * buffer)107 void gumbo_string_buffer_destroy(
108 struct GumboInternalParser* parser, GumboStringBuffer* buffer) {
109 gumbo_parser_deallocate(parser, buffer->data);
110 }
111