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
|
#pragma once
/* Document Markup Language (DML) v1.0 parser
* revision 0.03
*/
namespace nall { namespace {
struct DML {
auto& setAllowHTML(bool allowHTML) { settings.allowHTML = allowHTML; return *this; }
auto& setHost(const string& hostname) { settings.host = {hostname, "/"}; return *this; }
auto& setPath(const string& pathname) { settings.path = pathname; return *this; }
auto& setReader(const function<string (string)>& reader) { settings.reader = reader; return *this; }
auto& setSectioned(bool sectioned) { settings.sectioned = sectioned; return *this; }
auto parse(const string& filedata, const string& pathname) -> string;
auto parse(const string& filename) -> string;
private:
struct Settings {
bool allowHTML = true;
string host = "localhost/";
string path;
function<string (string)> reader;
bool sectioned = true;
} settings;
struct State {
string output;
uint sections = 0;
} state;
auto parseDocument(const string& filedata, const string& pathname, uint depth) -> bool;
auto parseBlock(string& block, const string& pathname, uint depth) -> bool;
auto count(const string& text, char value) -> uint;
auto escape(const string& text) -> string;
auto markup(const string& text) -> string;
};
auto DML::parse(const string& filedata, const string& pathname) -> string {
settings.path = pathname;
parseDocument(filedata, settings.path, 0);
return state.output;
}
auto DML::parse(const string& filename) -> string {
if(!settings.path) settings.path = pathname(filename);
string document = settings.reader ? settings.reader(filename) : string::read(filename);
parseDocument(document, settings.path, 0);
return state.output;
}
auto DML::parseDocument(const string& filedata, const string& pathname, uint depth) -> bool {
if(depth >= 100) return false; //attempt to prevent infinite recursion with reasonable limit
auto blocks = filedata.split("\n\n");
for(auto& block : blocks) parseBlock(block, pathname, depth);
if(settings.sectioned && state.sections && depth == 0) state.output.append("</section>\n");
return true;
}
auto DML::parseBlock(string& block, const string& pathname, uint depth) -> bool {
if(block.rstrip().empty()) return true;
auto lines = block.split("\n");
//include
if(block.beginsWith("<include ") && block.endsWith(">")) {
string filename{pathname, block.trim("<include ", ">", 1L).strip()};
string document = settings.reader ? settings.reader(filename) : string::read(filename);
parseDocument(document, nall::pathname(filename), depth + 1);
}
//html
else if(block.beginsWith("<html>\n") && settings.allowHTML) {
for(auto n : range(lines)) {
if(n == 0 || !lines[n].beginsWith(" ")) continue;
state.output.append(lines[n].ltrim(" ", 1L), "\n");
}
}
//section
else if(block.beginsWith("# ")) {
if(settings.sectioned) {
if(state.sections++) state.output.append("</section>");
state.output.append("<section>");
}
auto content = lines.takeFirst().ltrim("# ", 1L).split(" => ", 1L);
auto data = markup(content[0]);
auto name = escape(content(1, crc32(data)));
state.output.append("<header id=\"", name, "\">", data);
for(auto& line : lines) {
if(!line.beginsWith("# ")) continue;
state.output.append("<span>", line.ltrim("# ", 1L), "</span>");
}
state.output.append("</header>\n");
}
//header
else if(auto depth = count(block, '=')) {
auto content = slice(lines.takeFirst(), depth + 1).split(" => ", 1L);
auto data = markup(content[0]);
auto name = escape(content(1, crc32(data)));
if(depth <= 6) {
state.output.append("<h", depth, " id=\"", name, "\">", data);
for(auto& line : lines) {
if(count(line, '=') != depth) continue;
state.output.append("<span>", slice(line, depth + 1), "</span>");
}
state.output.append("</h", depth, ">\n");
}
}
//navigation
else if(count(block, '-')) {
state.output.append("<nav>\n");
uint level = 0;
for(auto& line : lines) {
if(auto depth = count(line, '-')) {
while(level < depth) level++, state.output.append("<ul>\n");
while(level > depth) level--, state.output.append("</ul>\n");
auto content = slice(line, depth + 1).split(" => ", 1L);
auto data = markup(content[0]);
auto name = escape(content(1, crc32(data)));
state.output.append("<li><a href=\"#", name, "\">", data, "</a></li>\n");
}
}
while(level--) state.output.append("</ul>\n");
state.output.append("</nav>\n");
}
//list
else if(count(block, '*')) {
uint level = 0;
for(auto& line : lines) {
if(auto depth = count(line, '*')) {
while(level < depth) level++, state.output.append("<ul>\n");
while(level > depth) level--, state.output.append("</ul>\n");
auto data = markup(slice(line, depth + 1));
state.output.append("<li>", data, "</li>\n");
}
}
while(level--) state.output.append("</ul>\n");
}
//quote
else if(count(block, '>')) {
uint level = 0;
for(auto& line : lines) {
if(auto depth = count(line, '>')) {
while(level < depth) level++, state.output.append("<blockquote>\n");
while(level > depth) level--, state.output.append("</blockquote>\n");
auto data = markup(slice(line, depth + 1));
state.output.append(data, "\n");
}
}
while(level--) state.output.append("</blockquote>\n");
}
//code
else if(block.beginsWith(" ")) {
state.output.append("<pre>");
for(auto& line : lines) {
if(!line.beginsWith(" ")) continue;
state.output.append(escape(line.ltrim(" ", 1L)), "\n");
}
state.output.rtrim("\n", 1L).append("</pre>\n");
}
//divider
else if(block.equals("---")) {
state.output.append("<hr>\n");
}
//paragraph
else {
state.output.append("<p>", markup(block), "</p>\n");
}
return true;
}
auto DML::count(const string& text, char value) -> uint {
for(uint n = 0; n < text.size(); n++) {
if(text[n] != value) {
if(text[n] == ' ') return n;
break;
}
}
return 0;
}
auto DML::escape(const string& text) -> string {
string output;
for(auto c : text) {
if(c == '&') { output.append("&"); continue; }
if(c == '<') { output.append("<"); continue; }
if(c == '>') { output.append(">"); continue; }
if(c == '"') { output.append("""); continue; }
output.append(c);
}
return output;
}
auto DML::markup(const string& text) -> string {
string output;
char match = 0;
uint offset = 0;
for(uint n = 0; n < text.size();) {
char a = n ? text[n - 1] : 0;
char b = text[n];
char c = text[n++ + 1];
bool d = !a || a == ' ' || a == '\t' || a == '\r' || a == '\n'; //is previous character whitespace?
bool e = !c || c == ' ' || c == '\t' || c == '\r' || c == '\n'; //is next character whitespace?
bool f = (c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z') || (c >= '0' && c <= '9'); //is next character alphanumeric?
if(!match && d && !e) {
if(b == '*') { match = '*'; offset = n; continue; }
if(b == '/') { match = '/'; offset = n; continue; }
if(b == '_') { match = '_'; offset = n; continue; }
if(b == '~') { match = '~'; offset = n; continue; }
if(b == '|') { match = '|'; offset = n; continue; }
if(b == '[') { match = ']'; offset = n; continue; }
if(b == '{') { match = '}'; offset = n; continue; }
}
//if we reach the end of the string without a match; force a match so the content is still output
if(match && b != match && !c) { b = match; f = 0; n++; }
if(match && b == match && !f) {
match = 0;
auto content = slice(text, offset, n - offset - 1);
if(b == '*') { output.append("<strong>", escape(content), "</strong>"); continue; }
if(b == '/') { output.append("<em>", escape(content), "</em>"); continue; }
if(b == '_') { output.append("<ins>", escape(content), "</ins>"); continue; }
if(b == '~') { output.append("<del>", escape(content), "</del>"); continue; }
if(b == '|') { output.append("<code>", escape(content), "</code>"); continue; }
if(b == ']') {
auto p = content.split(" => ", 1L);
p[0].replace("@/", settings.host);
output.append("<a href=\"", escape(p[0]), "\">", escape(p(1, p[0])), "</a>");
continue;
}
if(b == '}') {
auto p = content.split(" => ", 1L);
p[0].replace("@/", settings.host);
output.append("<img src=\"", escape(p[0]), "\" alt=\"", escape(p(1, "")), "\">");
continue;
}
continue;
}
if(match) continue;
if(b == '\\' && c) { output.append(c); n++; continue; } //character escaping
if(b == '&') { output.append("&"); continue; } //entity escaping
if(b == '<') { output.append("<"); continue; } //...
if(b == '>') { output.append(">"); continue; } //...
if(b == '"') { output.append("""); continue; } //...
output.append(b);
}
return output;
}
}}
|
