summaryrefslogtreecommitdiffstats
path: root/cnmfmt/cnmfmt.go
blob: 1e5b6ee519cb9d19d9eccd6c210ebf392fafa4cc (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
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
// Package cnmfmt provides parsing and composition for CNMfmt formatting.
package cnmfmt // import "contnet.org/lib/cnm-go/cnmfmt"

import (
	"bytes"
	"io"
	"strings"

	"contnet.org/lib/cnm-go"
)

const (
	numFormats = 5 // emphasized, alternate, code, quote, link
)

func init() {
	cnm.RegisterTextContentParser("fmt", parseTextFmt)
}

// Text represents a paragraph of CNMfmt text.
type Text struct {
	// Spans are spans of formatted text.
	Spans []Span
}

// ParseParagraph parses a single CNMfmt text paragraph s.
func ParseParagraph(s string) Text {
	s = cnm.CollapseWhitespace(s)

	t := Text{}
	var buf bytes.Buffer
	format := Format{}
	last := rune(-1)
	url := false

	for _, r := range s {
		if url && format.Link == "" { // need URL for link
			if handleURL(r, &last, &format, &buf) {
				continue
			}
		}

		switch r {
		case '*', '_', '`', '"', '@':
			handleTag(r, &last, &t, &format, &buf, &url)

		case '\\':
			if last == '\\' {
				buf.WriteString("\\\\")
				last = -1
			} else {
				if last >= 0 {
					buf.WriteRune(last)
				}
				last = '\\'
			}

		default:
			if last >= 0 {
				buf.WriteRune(last)
			}
			buf.WriteRune(r)
			last = -1
		}
	}

	if url && format.Link == "" {
		if last >= 0 {
			buf.WriteRune(last)
		}
		format.Link = Unescape(buf.String())
		buf.Reset()
	} else if last >= 0 {
		buf.WriteRune(last)
	}
	last = -1
	handleTag(-1, &last, &t, &format, &buf, &url)

	t.trimUnescape()

	return t
}

func (t *Text) trimUnescape() {
	var spans []Span

	for _, span := range t.Spans {
		if span.Text != "" || span.Format.Link != "" {
			spans = append(spans, span)
		}
	}
	t.Spans, spans = spans, nil

	for i := len(t.Spans) - 1; i >= 0; i-- {
		span := t.Spans[i]
		if span.Text != "" || span.Format.Link != "" {
			spans = append(spans, span)
		}
	}
	for i := 0; i < len(spans)/2; i++ {
		spans[i], spans[len(spans)-1-i] = spans[len(spans)-1-i], spans[i]
	}
	t.Spans = spans

	for i := range t.Spans {
		t.Spans[i].Text = Unescape(t.Spans[i].Text)
	}
}

func (t *Text) appendSpan(format Format, txt string) {
	if txt != "" || format.Link != "" {
		t.Spans = append(t.Spans, Span{format, txt})
	}
}

func handleURL(r rune, last *rune, format *Format, buf *bytes.Buffer) bool {
	if r == '@' && *last == '@' { // end without text
		format.Link = Unescape(buf.String())
		buf.Reset()
		return false
	} else if *last == '\\' {
		buf.WriteByte('\\')
		buf.WriteRune(r)
		*last = -1
	} else if r == '\\' || r == '@' {
		*last = r
	} else if r != ' ' { // url
		buf.WriteRune(r)
	} else if buf.Len() > 0 { // space, then text
		format.Link = Unescape(buf.String())
		buf.Reset()
	} // else: prefix space
	return true
}

func handleTag(r rune, last *rune, txt *Text, format *Format, buf *bytes.Buffer, url *bool) {
	if *last == '\\' {
		buf.WriteRune(r)
		*last = -1
	} else if *last == r {
		txt.appendSpan(*format, buf.String())
		buf.Reset()
		switch r {
		case '*':
			format.Emphasized = !format.Emphasized
		case '_':
			format.Alternate = !format.Alternate
		case '`':
			format.Code = !format.Code
		case '"':
			format.Quote = !format.Quote
		case '@':
			format.Link = ""
			*url = !*url
		}
		*last = -1
	} else {
		switch *last {
		case '*', '_', '`', '"', '@':
			buf.WriteRune(*last)
		}
		*last = r
	}
}

// WriteIndent writes the formatted text indented by n tabs.
func (t Text) WriteIndent(w io.Writer, n int) error {
	var state [numFormats]byte
	si := 0
	format := Format{}
	spans := EscapeSpans(t.Spans)
	var line []string
	for _, span := range spans {
		order := tagOrder(state[:si], format, span.Format)
		for _, f := range order {
			switch f {
			case '*':
				format.Emphasized = !format.Emphasized
				line = append(line, "**")
			case '_':
				format.Alternate = !format.Alternate
				line = append(line, "__")
			case '`':
				format.Code = !format.Code
				line = append(line, "``")
			case '"':
				format.Quote = !format.Quote
				line = append(line, "\"\"")
			case '@':
				if format.Link != "" {
					line = append(line, "@@")
				}
				if span.Format.Link != "" {
					pad := ""
					if span.Text != "" {
						pad = " "
					}
					line = append(line, "@@", cnm.Escape(span.Format.Link), pad)
				}
			}
		}
		line = append(line, span.Text)
		si = cleanupTags(state[:], order, span.Format)
		format = span.Format
	}
	return cnm.WriteIndent(w, strings.Join(line, ""), n)
}

func tagOrder(state []byte, old, new Format) []byte {
	ldiff := ""
	if old.Link != new.Link {
		ldiff = "1"
	}
	diff := Format{
		Emphasized: old.Emphasized != new.Emphasized,
		Alternate:  old.Alternate != new.Alternate,
		Code:       old.Code != new.Code,
		Quote:      old.Quote != new.Quote,
		Link:       ldiff,
	}

	// close formats
	var order [numFormats]byte
	oi := 0
	for i := len(state) - 1; i >= 0; i-- {
		switch state[i] {
		case '*':
			if diff.Emphasized {
				order[oi] = '*'
				oi++
				diff.Emphasized = false
			}
		case '_':
			if diff.Alternate {
				order[oi] = '_'
				oi++
				diff.Alternate = false
			}
		case '`':
			if diff.Code {
				order[oi] = '`'
				oi++
				diff.Code = false
			}
		case '"':
			if diff.Quote {
				order[oi] = '"'
				oi++
				diff.Quote = false
			}
		case '@':
			if diff.Link != "" {
				order[oi] = '@'
				oi++
				diff.Link = ""
			}
		}
	}

	// open formats
	if diff.Emphasized {
		order[oi] = '*'
		oi++
	}
	if diff.Alternate {
		order[oi] = '_'
		oi++
	}
	if diff.Code {
		order[oi] = '`'
		oi++
	}
	if diff.Quote {
		order[oi] = '"'
		oi++
	}
	if diff.Link != "" {
		order[oi] = '@'
		oi++
	}

	return order[:oi]
}

func cleanupTags(state []byte, order []byte, format Format) int {
	var newState [2 * numFormats]byte

	// take care of both state and order
	copy(newState[:numFormats], state)
	copy(newState[numFormats:], order)

	// remove formats that are off
	for i := range newState {
		switch newState[i] {
		case '*':
			if !format.Emphasized {
				newState[i] = 0
			}
		case '_':
			if !format.Alternate {
				newState[i] = 0
			}
		case '`':
			if !format.Code {
				newState[i] = 0
			}
		case '"':
			if !format.Quote {
				newState[i] = 0
			}
		case '@':
			if format.Link == "" {
				newState[i] = 0
			}
		}
	}

	si := 0
	for _, f := range newState {
		if f > 0 {
			state[si] = f
			si++
		}
	}

	// clean up unused state
	for i := si; i < numFormats; i++ {
		state[i] = 0
	}

	return si
}

// Span represents a span of text with a format.
type Span struct {
	// Format is the format of the text.
	Format Format

	// Text is the text content of the span.
	Text string
}

// Format represents a state of CNMfmt formatting.
type Format struct {
	// Emphasized text.
	Emphasized bool

	// Text in an alternate voice.
	Alternate bool

	// Text is code.
	Code bool

	// Quoted text.
	Quote bool

	// Hyperlink URL (if non-empty).
	Link string
}

// Escape escapes CNMfmt and CNM text special characters.
func Escape(s string) string {
	return EscapeFmt(cnm.Escape(s))
}

// EscapeSpans escapes CNMfmt and CNM text within spans.
//
// This function will not needlessly escape spaces at the start or end of a
// span if the sibling span contains nonspaces.
func EscapeSpans(spans []Span) []Span {
	// XXX: this is an ugly solution
	esc := make([]Span, len(spans))
	for i := range spans {
		start := false
		end := false
		span := spans[i]
		if i+1 < len(spans) {
			s := spans[i+1].Text
			if len(s) > 0 && s[0] != ' ' {
				span.Text = span.Text + "x"
				end = true
			}
		}
		if i > 0 {
			s := spans[i-1].Text
			if len(s) > 0 && s[len(s)-1] != ' ' {
				span.Text = "x" + span.Text
				start = true
			}
		}
		span.Text = Escape(span.Text)
		if start {
			span.Text = span.Text[1:]
		}
		if end {
			span.Text = span.Text[:len(span.Text)-1]
		}
		esc[i] = span
	}
	return esc
}

var escapeReplacer = strings.NewReplacer(
	`*`, `\*`,
	`_`, `\_`,
	"`", "\\`",
	`"`, `\"`,
	`@`, `\@`,
)

// EscapeFmt escapes only CNMfmt format toggle characters.
func EscapeFmt(s string) string {
	return escapeReplacer.Replace(s)
}

// Unescape resolves CNM text and CNMfmt escape sequences in s.
func Unescape(s string) string {
	return cnm.Unescape(UnescapeFmt(s))
}

var unescapeReplacer = strings.NewReplacer(
	`\*`, `*`,
	`\_`, `_`,
	"\\`", "`",
	`\"`, `"`,
	`\@`, `@`,
)

// UnescapeFmt resolves only CNMfmt escape sequences in s.
func UnescapeFmt(s string) string {
	return unescapeReplacer.Replace(s)
}

// TextFmtContents represents CNM `text fmt` contents.
type TextFmtContents struct {
	Paragraphs []Text
}

// NewTextFmtBlock creates a new `text fmt` block containing provided CNMfmt
// paragraphs.
func NewTextFmtBlock(paragraphs []Text) *cnm.TextBlock {
	return cnm.NewTextBlock("fmt", TextFmtContents{paragraphs})
}

// WriteIndent writes the formatted text contents indented by n tabs.
func (tf TextFmtContents) WriteIndent(w io.Writer, n int) error {
	for i, p := range tf.Paragraphs {
		if i != 0 {
			if err := cnm.WriteIndent(w, "", 0); err != nil {
				return err
			}
		}
		if err := p.WriteIndent(w, n); err != nil {
			return err
		}
	}
	return nil
}

// Parse parses paragraphs of CNMfmt text.
func Parse(paragraphs string) []Text {
	var txt []Text
	var paragraph []string

	for _, line := range strings.Split(paragraphs, "\n") {
		end := false
		if line != "" {
			if strings.Trim(line, "\n\r\t\f ") == "" {
				end = true
			} else {
				paragraph = append(paragraph, line)
			}
		} else if len(paragraph) > 0 {
			end = true
		}
		if end {
			txt = append(txt, ParseParagraph(strings.Join(paragraph, " ")))
			paragraph = nil
		}
	}
	if len(paragraph) > 0 {
		txt = append(txt, ParseParagraph(strings.Join(paragraph, " ")))
	}

	return txt
}

func parseTextFmt(p *cnm.Parser, block *cnm.TokenBlock) (cnm.TextContents, error) {
	txt := TextFmtContents{}
	var paragraph []string
	var err error
	for err == nil {
		if !p.Empty() && p.Indent() <= block.Indent() {
			break
		}

		token := p.RawText()
		end := false
		if text, ok := token.(*cnm.TokenRawText); ok {
			if strings.Trim(text.Text, "\n\r\t\f ") == "" {
				end = true
			} else {
				paragraph = append(paragraph, text.Text)
			}
		} else if _, ok := token.(*cnm.TokenEmptyLine); ok && len(paragraph) > 0 {
			end = true
		}
		if end {
			txt.Paragraphs = append(txt.Paragraphs, ParseParagraph(strings.Join(paragraph, " ")))
			paragraph = nil
		}
		err = p.Next()
	}
	if len(paragraph) > 0 {
		txt.Paragraphs = append(txt.Paragraphs, ParseParagraph(strings.Join(paragraph, " ")))
	}
	return txt, err
}