summaryrefslogtreecommitdiff
path: root/src/pkg/bufio/scan_test.go
blob: 0db7cad2047545926756ac573a6720d5e37b275b (plain)
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
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
// Copyright 2013 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 bufio_test

import (
	. "bufio"
	"bytes"
	"errors"
	"io"
	"strings"
	"testing"
	"unicode"
	"unicode/utf8"
)

// Test white space table matches the Unicode definition.
func TestSpace(t *testing.T) {
	for r := rune(0); r <= utf8.MaxRune; r++ {
		if IsSpace(r) != unicode.IsSpace(r) {
			t.Fatalf("white space property disagrees: %#U should be %t", r, unicode.IsSpace(r))
		}
	}
}

var scanTests = []string{
	"",
	"a",
	"¼",
	"☹",
	"\x81",   // UTF-8 error
	"\uFFFD", // correctly encoded RuneError
	"abcdefgh",
	"abc def\n\t\tgh    ",
	"abc¼☹\x81\uFFFD日本語\x82abc",
}

func TestScanByte(t *testing.T) {
	for n, test := range scanTests {
		buf := strings.NewReader(test)
		s := NewScanner(buf)
		s.Split(ScanBytes)
		var i int
		for i = 0; s.Scan(); i++ {
			if b := s.Bytes(); len(b) != 1 || b[0] != test[i] {
				t.Errorf("#%d: %d: expected %q got %q", n, i, test, b)
			}
		}
		if i != len(test) {
			t.Errorf("#%d: termination expected at %d; got %d", n, len(test), i)
		}
		err := s.Err()
		if err != nil {
			t.Errorf("#%d: %v", n, err)
		}
	}
}

// Test that the rune splitter returns same sequence of runes (not bytes) as for range string.
func TestScanRune(t *testing.T) {
	for n, test := range scanTests {
		buf := strings.NewReader(test)
		s := NewScanner(buf)
		s.Split(ScanRunes)
		var i, runeCount int
		var expect rune
		// Use a string range loop to validate the sequence of runes.
		for i, expect = range string(test) {
			if !s.Scan() {
				break
			}
			runeCount++
			got, _ := utf8.DecodeRune(s.Bytes())
			if got != expect {
				t.Errorf("#%d: %d: expected %q got %q", n, i, expect, got)
			}
		}
		if s.Scan() {
			t.Errorf("#%d: scan ran too long, got %q", n, s.Text())
		}
		testRuneCount := utf8.RuneCountInString(test)
		if runeCount != testRuneCount {
			t.Errorf("#%d: termination expected at %d; got %d", n, testRuneCount, runeCount)
		}
		err := s.Err()
		if err != nil {
			t.Errorf("#%d: %v", n, err)
		}
	}
}

var wordScanTests = []string{
	"",
	" ",
	"\n",
	"a",
	" a ",
	"abc def",
	" abc def ",
	" abc\tdef\nghi\rjkl\fmno\vpqr\u0085stu\u00a0\n",
}

// Test that the word splitter returns the same data as strings.Fields.
func TestScanWords(t *testing.T) {
	for n, test := range wordScanTests {
		buf := strings.NewReader(test)
		s := NewScanner(buf)
		s.Split(ScanWords)
		words := strings.Fields(test)
		var wordCount int
		for wordCount = 0; wordCount < len(words); wordCount++ {
			if !s.Scan() {
				break
			}
			got := s.Text()
			if got != words[wordCount] {
				t.Errorf("#%d: %d: expected %q got %q", n, wordCount, words[wordCount], got)
			}
		}
		if s.Scan() {
			t.Errorf("#%d: scan ran too long, got %q", n, s.Text())
		}
		if wordCount != len(words) {
			t.Errorf("#%d: termination expected at %d; got %d", n, len(words), wordCount)
		}
		err := s.Err()
		if err != nil {
			t.Errorf("#%d: %v", n, err)
		}
	}
}

// slowReader is a reader that returns only a few bytes at a time, to test the incremental
// reads in Scanner.Scan.
type slowReader struct {
	max int
	buf io.Reader
}

func (sr *slowReader) Read(p []byte) (n int, err error) {
	if len(p) > sr.max {
		p = p[0:sr.max]
	}
	return sr.buf.Read(p)
}

// genLine writes to buf a predictable but non-trivial line of text of length
// n, including the terminal newline and an occasional carriage return.
// If addNewline is false, the \r and \n are not emitted.
func genLine(buf *bytes.Buffer, lineNum, n int, addNewline bool) {
	buf.Reset()
	doCR := lineNum%5 == 0
	if doCR {
		n--
	}
	for i := 0; i < n-1; i++ { // Stop early for \n.
		c := 'a' + byte(lineNum+i)
		if c == '\n' || c == '\r' { // Don't confuse us.
			c = 'N'
		}
		buf.WriteByte(c)
	}
	if addNewline {
		if doCR {
			buf.WriteByte('\r')
		}
		buf.WriteByte('\n')
	}
	return
}

// Test the line splitter, including some carriage returns but no long lines.
func TestScanLongLines(t *testing.T) {
	const smallMaxTokenSize = 256 // Much smaller for more efficient testing.
	// Build a buffer of lots of line lengths up to but not exceeding smallMaxTokenSize.
	tmp := new(bytes.Buffer)
	buf := new(bytes.Buffer)
	lineNum := 0
	j := 0
	for i := 0; i < 2*smallMaxTokenSize; i++ {
		genLine(tmp, lineNum, j, true)
		if j < smallMaxTokenSize {
			j++
		} else {
			j--
		}
		buf.Write(tmp.Bytes())
		lineNum++
	}
	s := NewScanner(&slowReader{1, buf})
	s.Split(ScanLines)
	s.MaxTokenSize(smallMaxTokenSize)
	j = 0
	for lineNum := 0; s.Scan(); lineNum++ {
		genLine(tmp, lineNum, j, false)
		if j < smallMaxTokenSize {
			j++
		} else {
			j--
		}
		line := tmp.String() // We use the string-valued token here, for variety.
		if s.Text() != line {
			t.Errorf("%d: bad line: %d %d\n%.100q\n%.100q\n", lineNum, len(s.Bytes()), len(line), s.Text(), line)
		}
	}
	err := s.Err()
	if err != nil {
		t.Fatal(err)
	}
}

// Test that the line splitter errors out on a long line.
func TestScanLineTooLong(t *testing.T) {
	const smallMaxTokenSize = 256 // Much smaller for more efficient testing.
	// Build a buffer of lots of line lengths up to but not exceeding smallMaxTokenSize.
	tmp := new(bytes.Buffer)
	buf := new(bytes.Buffer)
	lineNum := 0
	j := 0
	for i := 0; i < 2*smallMaxTokenSize; i++ {
		genLine(tmp, lineNum, j, true)
		j++
		buf.Write(tmp.Bytes())
		lineNum++
	}
	s := NewScanner(&slowReader{3, buf})
	s.Split(ScanLines)
	s.MaxTokenSize(smallMaxTokenSize)
	j = 0
	for lineNum := 0; s.Scan(); lineNum++ {
		genLine(tmp, lineNum, j, false)
		if j < smallMaxTokenSize {
			j++
		} else {
			j--
		}
		line := tmp.Bytes()
		if !bytes.Equal(s.Bytes(), line) {
			t.Errorf("%d: bad line: %d %d\n%.100q\n%.100q\n", lineNum, len(s.Bytes()), len(line), s.Bytes(), line)
		}
	}
	err := s.Err()
	if err != ErrTooLong {
		t.Fatalf("expected ErrTooLong; got %s", err)
	}
}

// Test that the line splitter handles a final line without a newline.
func testNoNewline(text string, lines []string, t *testing.T) {
	buf := strings.NewReader(text)
	s := NewScanner(&slowReader{7, buf})
	s.Split(ScanLines)
	for lineNum := 0; s.Scan(); lineNum++ {
		line := lines[lineNum]
		if s.Text() != line {
			t.Errorf("%d: bad line: %d %d\n%.100q\n%.100q\n", lineNum, len(s.Bytes()), len(line), s.Bytes(), line)
		}
	}
	err := s.Err()
	if err != nil {
		t.Fatal(err)
	}
}

var noNewlineLines = []string{
	"abcdefghijklmn\nopqrstuvwxyz",
}

// Test that the line splitter handles a final line without a newline.
func TestScanLineNoNewline(t *testing.T) {
	const text = "abcdefghijklmn\nopqrstuvwxyz"
	lines := []string{
		"abcdefghijklmn",
		"opqrstuvwxyz",
	}
	testNoNewline(text, lines, t)
}

// Test that the line splitter handles a final line with a carriage return but no newline.
func TestScanLineReturnButNoNewline(t *testing.T) {
	const text = "abcdefghijklmn\nopqrstuvwxyz\r"
	lines := []string{
		"abcdefghijklmn",
		"opqrstuvwxyz",
	}
	testNoNewline(text, lines, t)
}

// Test that the line splitter handles a final empty line.
func TestScanLineEmptyFinalLine(t *testing.T) {
	const text = "abcdefghijklmn\nopqrstuvwxyz\n\n"
	lines := []string{
		"abcdefghijklmn",
		"opqrstuvwxyz",
		"",
	}
	testNoNewline(text, lines, t)
}

// Test that the line splitter handles a final empty line with a carriage return but no newline.
func TestScanLineEmptyFinalLineWithCR(t *testing.T) {
	const text = "abcdefghijklmn\nopqrstuvwxyz\n\r"
	lines := []string{
		"abcdefghijklmn",
		"opqrstuvwxyz",
		"",
	}
	testNoNewline(text, lines, t)
}

var testError = errors.New("testError")

// Test the correct error is returned when the split function errors out.
func TestSplitError(t *testing.T) {
	// Create a split function that delivers a little data, then a predictable error.
	numSplits := 0
	const okCount = 7
	errorSplit := func(data []byte, atEOF bool) (advance int, token []byte, err error) {
		if atEOF {
			panic("didn't get enough data")
		}
		if numSplits >= okCount {
			return 0, nil, testError
		}
		numSplits++
		return 1, data[0:1], nil
	}
	// Read the data.
	const text = "abcdefghijklmnopqrstuvwxyz"
	buf := strings.NewReader(text)
	s := NewScanner(&slowReader{1, buf})
	s.Split(errorSplit)
	var i int
	for i = 0; s.Scan(); i++ {
		if len(s.Bytes()) != 1 || text[i] != s.Bytes()[0] {
			t.Errorf("#%d: expected %q got %q", i, text[i], s.Bytes()[0])
		}
	}
	// Check correct termination location and error.
	if i != okCount {
		t.Errorf("unexpected termination; expected %d tokens got %d", okCount, i)
	}
	err := s.Err()
	if err != testError {
		t.Fatalf("expected %q got %v", testError, err)
	}
}

// Test that an EOF is overridden by a user-generated scan error.
func TestErrAtEOF(t *testing.T) {
	s := NewScanner(strings.NewReader("1 2 33"))
	// This spitter will fail on last entry, after s.err==EOF.
	split := func(data []byte, atEOF bool) (advance int, token []byte, err error) {
		advance, token, err = ScanWords(data, atEOF)
		if len(token) > 1 {
			if s.ErrOrEOF() != io.EOF {
				t.Fatal("not testing EOF")
			}
			err = testError
		}
		return
	}
	s.Split(split)
	for s.Scan() {
	}
	if s.Err() != testError {
		t.Fatal("wrong error:", s.Err())
	}
}

// Test for issue 5268.
type alwaysError struct{}

func (alwaysError) Read(p []byte) (int, error) {
	return 0, io.ErrUnexpectedEOF
}

func TestNonEOFWithEmptyRead(t *testing.T) {
	scanner := NewScanner(alwaysError{})
	for scanner.Scan() {
		t.Fatal("read should fail")
	}
	err := scanner.Err()
	if err != io.ErrUnexpectedEOF {
		t.Errorf("unexpected error: %v", err)
	}
}

// Test that Scan finishes if we have endless empty reads.
type endlessZeros struct{}

func (endlessZeros) Read(p []byte) (int, error) {
	return 0, nil
}

func TestBadReader(t *testing.T) {
	scanner := NewScanner(endlessZeros{})
	for scanner.Scan() {
		t.Fatal("read should fail")
	}
	err := scanner.Err()
	if err != io.ErrNoProgress {
		t.Errorf("unexpected error: %v", err)
	}
}