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
|
// Copyright 2019 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package span_test
import (
"strings"
"testing"
"golang.org/x/tools/internal/span"
)
// The funny character below is 4 bytes long in UTF-8; two UTF-16 code points
var funnyString = []byte("š23\nš45")
var toUTF16Tests = []struct {
scenario string
input []byte
line int // 1-indexed count
col int // 1-indexed byte position in line
offset int // 0-indexed byte offset into input
resUTF16col int // 1-indexed UTF-16 col number
pre string // everything before the cursor on the line
post string // everything from the cursor onwards
err string // expected error string in call to ToUTF16Column
issue *bool
}{
{
scenario: "cursor missing content",
input: nil,
err: "ToUTF16Column: point is missing position",
},
{
scenario: "cursor missing position",
input: funnyString,
line: -1,
col: -1,
err: "ToUTF16Column: point is missing position",
},
{
scenario: "cursor missing offset",
input: funnyString,
line: 1,
col: 1,
offset: -1,
err: "ToUTF16Column: point is missing offset",
},
{
scenario: "zero length input; cursor at first col, first line",
input: []byte(""),
line: 1,
col: 1,
offset: 0,
resUTF16col: 1,
},
{
scenario: "cursor before funny character; first line",
input: funnyString,
line: 1,
col: 1,
offset: 0,
resUTF16col: 1,
pre: "",
post: "š23",
},
{
scenario: "cursor after funny character; first line",
input: funnyString,
line: 1,
col: 5, // 4 + 1 (1-indexed)
offset: 4,
resUTF16col: 3, // 2 + 1 (1-indexed)
pre: "š",
post: "23",
},
{
scenario: "cursor after last character on first line",
input: funnyString,
line: 1,
col: 7, // 4 + 1 + 1 + 1 (1-indexed)
offset: 6, // 4 + 1 + 1
resUTF16col: 5, // 2 + 1 + 1 + 1 (1-indexed)
pre: "š23",
post: "",
},
{
scenario: "cursor before funny character; second line",
input: funnyString,
line: 2,
col: 1,
offset: 7, // length of first line
resUTF16col: 1,
pre: "",
post: "š45",
},
{
scenario: "cursor after funny character; second line",
input: funnyString,
line: 1,
col: 5, // 4 + 1 (1-indexed)
offset: 11, // 7 (length of first line) + 4
resUTF16col: 3, // 2 + 1 (1-indexed)
pre: "š",
post: "45",
},
{
scenario: "cursor after last character on second line",
input: funnyString,
line: 2,
col: 7, // 4 + 1 + 1 + 1 (1-indexed)
offset: 13, // 7 (length of first line) + 4 + 1 + 1
resUTF16col: 5, // 2 + 1 + 1 + 1 (1-indexed)
pre: "š45",
post: "",
},
{
scenario: "cursor beyond end of file",
input: funnyString,
line: 2,
col: 8, // 4 + 1 + 1 + 1 + 1 (1-indexed)
offset: 14, // 4 + 1 + 1 + 1
err: "ToUTF16Column: offsets 7-14 outside file contents (13)",
},
}
var fromUTF16Tests = []struct {
scenario string
input []byte
line int // 1-indexed line number (isn't actually used)
offset int // 0-indexed byte offset to beginning of line
utf16col int // 1-indexed UTF-16 col number
resCol int // 1-indexed byte position in line
resOffset int // 0-indexed byte offset into input
pre string // everything before the cursor on the line
post string // everything from the cursor onwards
err string // expected error string in call to ToUTF16Column
}{
{
scenario: "zero length input; cursor at first col, first line",
input: []byte(""),
line: 1,
offset: 0,
utf16col: 1,
resCol: 1,
resOffset: 0,
pre: "",
post: "",
},
{
scenario: "missing offset",
input: funnyString,
line: 1,
offset: -1,
err: "FromUTF16Column: point is missing offset",
},
{
scenario: "cursor before funny character",
input: funnyString,
line: 1,
utf16col: 1,
resCol: 1,
resOffset: 0,
pre: "",
post: "š23",
},
{
scenario: "cursor after funny character",
input: funnyString,
line: 1,
utf16col: 3,
resCol: 5,
resOffset: 4,
pre: "š",
post: "23",
},
{
scenario: "cursor after last character on line",
input: funnyString,
line: 1,
utf16col: 5,
resCol: 7,
resOffset: 6,
pre: "š23",
post: "",
},
{
scenario: "cursor beyond last character on line",
input: funnyString,
line: 1,
offset: 0,
utf16col: 6,
resCol: 7,
resOffset: 6,
pre: "š23",
post: "",
},
{
scenario: "cursor before funny character; second line",
input: funnyString,
line: 2,
offset: 7, // length of first line
utf16col: 1,
resCol: 1,
resOffset: 7,
pre: "",
post: "š45",
},
{
scenario: "cursor after funny character; second line",
input: funnyString,
line: 2,
offset: 7, // length of first line
utf16col: 3, // 2 + 1 (1-indexed)
resCol: 5, // 4 + 1 (1-indexed)
resOffset: 11, // 7 (length of first line) + 4
pre: "š",
post: "45",
},
{
scenario: "cursor after last character on second line",
input: funnyString,
line: 2,
offset: 7, // length of first line
utf16col: 5, // 2 + 1 + 1 + 1 (1-indexed)
resCol: 7, // 4 + 1 + 1 + 1 (1-indexed)
resOffset: 13, // 7 (length of first line) + 4 + 1 + 1
pre: "š45",
post: "",
},
{
scenario: "cursor beyond end of file",
input: funnyString,
line: 2,
offset: 7,
utf16col: 6, // 2 + 1 + 1 + 1 + 1(1-indexed)
resCol: 8, // 4 + 1 + 1 + 1 + 1 (1-indexed)
resOffset: 14, // 7 (length of first line) + 4 + 1 + 1 + 1
err: "FromUTF16Column: chr goes beyond the content",
},
{
scenario: "offset beyond end of file",
input: funnyString,
line: 2,
offset: 14,
utf16col: 2,
err: "FromUTF16Column: offset (14) greater than length of content (13)",
},
}
func TestToUTF16(t *testing.T) {
for _, e := range toUTF16Tests {
t.Run(e.scenario, func(t *testing.T) {
if e.issue != nil && !*e.issue {
t.Skip("expected to fail")
}
p := span.NewPoint(e.line, e.col, e.offset)
got, err := span.ToUTF16Column(p, e.input)
if err != nil {
if err.Error() != e.err {
t.Fatalf("expected error %v; got %v", e.err, err)
}
return
}
if e.err != "" {
t.Fatalf("unexpected success; wanted %v", e.err)
}
if got != e.resUTF16col {
t.Fatalf("expected result %v; got %v", e.resUTF16col, got)
}
pre, post := getPrePost(e.input, p.Offset())
if string(pre) != e.pre {
t.Fatalf("expected #%d pre %q; got %q", p.Offset(), e.pre, pre)
}
if string(post) != e.post {
t.Fatalf("expected #%d, post %q; got %q", p.Offset(), e.post, post)
}
})
}
}
func TestFromUTF16(t *testing.T) {
for _, e := range fromUTF16Tests {
t.Run(e.scenario, func(t *testing.T) {
p := span.NewPoint(e.line, 1, e.offset)
p, err := span.FromUTF16Column(p, e.utf16col, []byte(e.input))
if err != nil {
if err.Error() != e.err {
t.Fatalf("expected error %v; got %v", e.err, err)
}
return
}
if e.err != "" {
t.Fatalf("unexpected success; wanted %v", e.err)
}
if p.Column() != e.resCol {
t.Fatalf("expected resulting col %v; got %v", e.resCol, p.Column())
}
if p.Offset() != e.resOffset {
t.Fatalf("expected resulting offset %v; got %v", e.resOffset, p.Offset())
}
pre, post := getPrePost(e.input, p.Offset())
if string(pre) != e.pre {
t.Fatalf("expected #%d pre %q; got %q", p.Offset(), e.pre, pre)
}
if string(post) != e.post {
t.Fatalf("expected #%d post %q; got %q", p.Offset(), e.post, post)
}
})
}
}
func getPrePost(content []byte, offset int) (string, string) {
pre, post := string(content)[:offset], string(content)[offset:]
if i := strings.LastIndex(pre, "\n"); i >= 0 {
pre = pre[i+1:]
}
if i := strings.IndexRune(post, '\n'); i >= 0 {
post = post[:i]
}
return pre, post
}
|
