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
|
// GoToSocial
// Copyright (C) GoToSocial Authors admin@gotosocial.org
// SPDX-License-Identifier: AGPL-3.0-or-later
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
package text
import (
"fmt"
"strings"
"github.com/superseriousbusiness/gotosocial/internal/regexes"
"github.com/yuin/goldmark/ast"
"github.com/yuin/goldmark/parser"
"github.com/yuin/goldmark/text"
)
/*
MENTION PARSER STUFF
*/
// mention fulfils the goldmark
// ast.Node interface.
type mention struct {
ast.BaseInline
Segment text.Segment
}
var kindMention = ast.NewNodeKind("Mention")
func (n *mention) Kind() ast.NodeKind {
return kindMention
}
func (n *mention) Dump(source []byte, level int) {
fmt.Printf("%sMention: %s\n", strings.Repeat(" ", level), string(n.Segment.Value(source)))
}
// newMention creates a goldmark ast.Node
// from a text.Segment. The contained segment
// is used in rendering.
func newMention(s text.Segment) *mention {
return &mention{
BaseInline: ast.BaseInline{},
Segment: s,
}
}
// mentionParser fulfils the goldmark
// parser.InlineParser interface.
type mentionParser struct{}
// Mention parsing is triggered by the `@` symbol
// which appears at the beginning of a mention.
func (p *mentionParser) Trigger() []byte {
return []byte{'@'}
}
func (p *mentionParser) Parse(
_ ast.Node,
block text.Reader,
_ parser.Context,
) ast.Node {
// If preceding character is not a valid boundary
// character, then this cannot be a valid mention.
if !isMentionBoundary(block.PrecendingCharacter()) {
return nil
}
line, segment := block.PeekLine()
// Ascertain location of mention in the line
// that starts with the trigger character.
loc := regexes.MentionFinder.FindIndex(line)
if loc == nil || loc[0] != 0 {
// Noop if not found or
// not found at start.
return nil
}
// Advance the block to
// the end of the mention.
block.Advance(loc[1])
// mention ast.Node spans from the
// beginning of this segment up to
// the last character of the mention.
return newMention(
segment.WithStop(
segment.Start + loc[1],
),
)
}
/*
HASHTAG PARSER STUFF
*/
// hashtag fulfils the goldmark
// ast.Node interface.
type hashtag struct {
ast.BaseInline
Segment text.Segment
}
var kindHashtag = ast.NewNodeKind("Hashtag")
func (n *hashtag) Kind() ast.NodeKind {
return kindHashtag
}
func (n *hashtag) Dump(source []byte, level int) {
fmt.Printf("%sHashtag: %s\n", strings.Repeat(" ", level), string(n.Segment.Value(source)))
}
// newHashtag creates a goldmark ast.Node
// from a text.Segment. The contained segment
// is used in rendering.
func newHashtag(s text.Segment) *hashtag {
return &hashtag{
BaseInline: ast.BaseInline{},
Segment: s,
}
}
type hashtagParser struct{}
// Hashtag parsing is triggered by a '#' symbol
// which appears at the beginning of a hashtag.
func (p *hashtagParser) Trigger() []byte {
return []byte{'#'}
}
func (p *hashtagParser) Parse(
_ ast.Node,
block text.Reader,
_ parser.Context,
) ast.Node {
// If preceding character is not a valid boundary
// character, then this cannot be a valid hashtag.
if !isHashtagBoundary(block.PrecendingCharacter()) {
return nil
}
var (
line, segment = block.PeekLine()
lineStr = string(line)
lineStrLen = len(lineStr)
)
if lineStrLen <= 1 {
// This is probably just
// a lonely '#' char.
return nil
}
// Iterate through the runes in the detected
// hashtag string until we reach either:
// - A weird character (bad).
// - The end of the hashtag (ok).
// - The end of the string (also ok).
for i, r := range lineStr {
switch {
case r == '#' && i == 0:
// Ignore initial '#'.
continue
case !isPermittedInHashtag(r) &&
!isHashtagBoundary(r):
// Weird non-boundary character
// in the hashtag. Don't trust it.
return nil
case isHashtagBoundary(r):
// Reached closing hashtag
// boundary. Advance block
// to the end of the hashtag.
block.Advance(i)
// hashtag ast.Node spans from
// the beginning of this segment
// up to the boundary character.
return newHashtag(
segment.WithStop(
segment.Start + i,
),
)
}
}
// No invalid or boundary characters before the
// end of the line: it's all hashtag, baby 😎
//
// Advance block to the end of the segment.
block.Advance(segment.Len())
// hashtag ast.Node spans
// the entire segment.
return newHashtag(segment)
}
/*
EMOJI PARSER STUFF
*/
// emoji fulfils the goldmark
// ast.Node interface.
type emoji struct {
ast.BaseInline
Segment text.Segment
}
var kindEmoji = ast.NewNodeKind("Emoji")
func (n *emoji) Kind() ast.NodeKind {
return kindEmoji
}
func (n *emoji) Dump(source []byte, level int) {
fmt.Printf("%sEmoji: %s\n", strings.Repeat(" ", level), string(n.Segment.Value(source)))
}
// newEmoji creates a goldmark ast.Node
// from a text.Segment. The contained
// segment is used in rendering.
func newEmoji(s text.Segment) *emoji {
return &emoji{
BaseInline: ast.BaseInline{},
Segment: s,
}
}
type emojiParser struct{}
// Emoji parsing is triggered by a ':' char
// which appears at the start of the emoji.
func (p *emojiParser) Trigger() []byte {
return []byte{':'}
}
func (p *emojiParser) Parse(
_ ast.Node,
block text.Reader,
_ parser.Context,
) ast.Node {
line, segment := block.PeekLine()
// Ascertain location of emoji in the line
// that starts with the trigger character.
loc := regexes.EmojiFinder.FindIndex(line)
if loc == nil || loc[0] != 0 {
// Noop if not found or
// not found at start.
return nil
}
// Advance the block to
// the end of the emoji.
block.Advance(loc[1])
// emoji ast.Node spans from the
// beginning of this segment up to
// the last character of the emoji.
return newEmoji(
segment.WithStop(
segment.Start + loc[1],
),
)
}
|