summaryrefslogtreecommitdiff
path: root/indexing/zhmakeindex/style.go
blob: 2b480bf1935f0850ec8f3b032e497abccb485e6e (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
package main

import (
	"path/filepath"
	"bufio"
	"log"
	"os"
	"strconv"
	"strings"
	"unicode"
	"unicode/utf8"

	"golang.org/x/text/transform"

	"github.com/leo-liu/zhmakeindex/kpathsea"
)

// 输入格式
// 这里使用简单 struct 实现,需要大量分情况讨论。
// 也可以用 map 实现,代码可能会简短并易于扩展,但要动态处理类型
type InputStyle struct {
	keyword         string
	arg_open        rune
	arg_close       rune
	actual          rune
	encap           rune
	escape          rune
	level           rune
	quote           rune
	page_compositor string
	range_open      rune
	range_close     rune
	comment         rune
}

func NewInputStyle() *InputStyle {
	in := &InputStyle{
		keyword:         "\\indexentry",
		arg_open:        '{',
		arg_close:       '}',
		actual:          '@',
		encap:           '|',
		escape:          '\\',
		level:           '!',
		quote:           '"',
		page_compositor: "-",
		range_open:      '(',
		range_close:     ')',
		comment:         '%',
	}
	return in
}

type OutputStyle struct {
	preamble                  string
	postamble                 string
	setpage_prefix            string
	setpage_suffix            string
	group_skip                string
	headings_flag             int
	heading_prefix            string
	heading_suffix            string
	symhead_positive          string
	symhead_negative          string
	numhead_positive          string
	numhead_negative          string
	stroke_prefix             string
	stroke_suffix             string
	radical_prefix            string
	radical_suffix            string
	radical_simplified_flag   int
	radical_simplified_prefix string
	radical_simplified_suffix string
	item_0                    string
	item_1                    string
	item_2                    string
	item_01                   string
	item_x1                   string
	item_12                   string
	item_x2                   string
	delim_0                   string
	delim_1                   string
	delim_2                   string
	delim_n                   string
	delim_r                   string
	delim_t                   string
	encap_prefix              string
	encap_infix               string
	encap_suffix              string
	page_precedence           string
	line_max                  int
	indent_space              string
	indent_length             int
	suffix_2p                 string
	suffix_3p                 string
	suffix_mp                 string
}

func NewOutputStyle() *OutputStyle {
	out := &OutputStyle{
		preamble:                  "\\begin{theindex}\n",
		postamble:                 "\n\n\\end{theindex}\n",
		setpage_prefix:            "\n  \\setcounter{page}{",
		setpage_suffix:            "}\n",
		group_skip:                "\n\n  \\indexspace\n",
		headings_flag:             0,
		heading_prefix:            "",
		heading_suffix:            "",
		symhead_positive:          "Symbols",
		symhead_negative:          "symbols",
		numhead_positive:          "Numbers",
		numhead_negative:          "numbers",
		stroke_prefix:             "",
		stroke_suffix:             " 画",
		radical_prefix:            "",
		radical_suffix:            "部",
		radical_simplified_flag:   1,
		radical_simplified_prefix: "(",
		radical_simplified_suffix: ")",
		item_0:          "\n  \\item ",
		item_1:          "\n    \\subitem ",
		item_2:          "\n      \\subsubitem ",
		item_01:         "\n    \\subitem ",
		item_x1:         "\n    \\subitem ",
		item_12:         "\n      \\subsubitem ",
		item_x2:         "\n      \\subsubitem ",
		delim_0:         ", ",
		delim_1:         ", ",
		delim_2:         ", ",
		delim_n:         ", ",
		delim_r:         "--",
		delim_t:         "",
		encap_prefix:    "\\",
		encap_infix:     "{",
		encap_suffix:    "}",
		page_precedence: "rnaRA",
		line_max:        72,
		indent_space:    "\t\t",
		indent_length:   16,
		suffix_2p:       "",
		suffix_3p:       "",
		suffix_mp:       "",
	}
	return out
}

func NewStyles(o *StyleOptions) (*InputStyle, *OutputStyle) {
	in := NewInputStyle()
	out := NewOutputStyle()

	if o.style == "" {
		return in, out
	}
	if filepath.Ext(o.style) == "" {
		o.style += ".ist"
	}
	// 读取格式文件,处理格式
	o.style = kpathsea.FindFile(o.style, kpathsea.IST_FORMAT, false)
	if o.style == "" {
		log.Fatalln("找不到格式文件。")
	}
	styleFile, err := os.Open(o.style)
	if err != nil {
		log.Fatalln(err.Error())
	}
	defer styleFile.Close()
	scanner := bufio.NewScanner(transform.NewReader(styleFile, o.style_decoder))
	scanner.Split(ScanStyleTokens)
	for scanner.Scan() {
		if err := scanner.Err(); err != nil {
			log.Println(err.Error())
		}
		key := scanner.Text()
		if !scanner.Scan() {
			log.Println("格式文件不完整")
		}
		if err := scanner.Err(); err != nil {
			log.Println(err.Error())
		}
		value := scanner.Text()
		switch key {
		// 输入参数
		case "keyword":
			in.keyword = unquote(value)
		case "arg_open":
			in.arg_open = unquoteChar(value)
		case "arg_close":
			in.arg_close = unquoteChar(value)
		case "actual":
			in.actual = unquoteChar(value)
		case "encap":
			in.encap = unquoteChar(value)
		case "escape":
			in.escape = unquoteChar(value)
		case "level":
			in.level = unquoteChar(value)
		case "quote":
			in.quote = unquoteChar(value)
		case "page_compositor":
			in.page_compositor = unquote(value)
		case "range_open":
			in.range_open = unquoteChar(value)
		case "range_close":
			in.range_close = unquoteChar(value)
		case "comment":
			in.comment = unquoteChar(value)
		// 输出参数
		case "preamble":
			out.preamble = unquote(value)
		case "postamble":
			out.postamble = unquote(value)
		case "setpage_prefix":
			out.setpage_prefix = unquote(value)
		case "setpage_suffix":
			out.setpage_suffix = unquote(value)
		case "group_skip":
			out.group_skip = unquote(value)
		case "headings_flag", "lethead_flag":
			out.headings_flag = parseInt(value)
		case "heading_prefix", "lethead_prefix":
			out.heading_prefix = unquote(value)
		case "heading_suffix", "lethead_suffix":
			out.heading_suffix = unquote(value)
		case "symhead_positive":
			out.symhead_positive = unquote(value)
		case "symhead_negative":
			out.symhead_negative = unquote(value)
		case "numhead_positive":
			out.numhead_positive = unquote(value)
		case "numhead_negative":
			out.numhead_negative = unquote(value)
		case "stroke_prefix":
			out.stroke_prefix = unquote(value)
		case "stroke_suffix":
			out.stroke_suffix = unquote(value)
		case "radical_prefix":
			out.radical_prefix = unquote(value)
		case "radical_suffix":
			out.radical_suffix = unquote(value)
		case "radical_simplify_flag":
			out.radical_simplified_flag = parseInt(value)
		case "radical_simplified_prefix":
			out.radical_simplified_prefix = unquote(value)
		case "radical_simplified_suffix":
			out.radical_simplified_suffix = unquote(value)
		case "item_0":
			out.item_0 = unquote(value)
		case "item_1":
			out.item_1 = unquote(value)
		case "item_2":
			out.item_2 = unquote(value)
		case "item_01":
			out.item_01 = unquote(value)
		case "item_x1":
			out.item_x1 = unquote(value)
		case "item_12":
			out.item_12 = unquote(value)
		case "item_x2":
			out.item_x2 = unquote(value)
		case "delim_0":
			out.delim_0 = unquote(value)
		case "delim_1":
			out.delim_1 = unquote(value)
		case "delim_2":
			out.delim_2 = unquote(value)
		case "delim_n":
			out.delim_n = unquote(value)
		case "delim_r":
			out.delim_r = unquote(value)
		case "delim_t":
			out.delim_t = unquote(value)
		case "encap_prefix":
			out.encap_prefix = unquote(value)
		case "encap_infix":
			out.encap_infix = unquote(value)
		case "encap_suffix":
			out.encap_suffix = unquote(value)
		case "line_max":
			out.line_max = parseInt(value)
		case "indent_space":
			out.indent_space = unquote(value)
		case "indent_length":
			out.indent_length = parseInt(value)
		case "suffix_2p":
			out.suffix_2p = unquote(value)
		case "suffix_3p":
			out.suffix_3p = unquote(value)
		case "suffix_mp":
			out.suffix_mp = unquote(value)
		// 其他
		default:
			log.Printf("忽略未知格式 %s\n", key)
		}
	}
	return in, out
}

func unquote(src string) string {
	// 处理双引号中有换行符的串
	if src[0] == '"' {
		src = strings.Replace(src, "\n", "\\n", -1)
	}
	dst, err := strconv.Unquote(src)
	if err != nil {
		log.Println(err.Error())
	}
	return dst
}

func unquoteChar(src string) rune {
	src = unquote(src)
	dst, _, tail, err := strconv.UnquoteChar(src, 0)
	if tail != "" {
		err = strconv.ErrSyntax
	}
	if err != nil {
		log.Println(err.Error())
	}
	return dst
}

func parseInt(src string) int {
	i, err := strconv.ParseInt(src, 0, 0)
	if err != nil {
		log.Println(err.Error())
	}
	return int(i)
}

// bufio.SplitFunc 的实例
// 查找标识符、数字、单引号内的 rune、双引号或反引号内的串;跳过以 % 开头的注释(未完成)
// 实现参考了 bufio.ScanWords
func ScanStyleTokens(data []byte, atEOF bool) (advance int, token []byte, err error) {
	// 跳过空白和注释
	start := 0
	in_comment := false
	for width := 0; start < len(data); start += width {
		var r rune
		r, width = utf8.DecodeRune(data[start:])
		if !in_comment && r == '%' {
			in_comment = true
		} else if in_comment && r == '\n' {
			in_comment = false
		} else if !in_comment && !unicode.IsSpace(r) {
			break
		}
		// 其他情况跳过:注释中未遇到换行符,或者注释外遇到空白符
	}
	if atEOF && len(data) == 0 {
		return 0, nil, nil
	}
	// 首先读出第一个字符,按不同类型扫描 token
	switch first, firstwidth := utf8.DecodeRune(data[start:]); first {
	// 读引号内的 rune 或串,从引号后开始扫描
	case '\'', '"', '`':
		for width, i := 0, start+firstwidth; i < len(data); i += width {
			var r rune
			r, width = utf8.DecodeRune(data[i:])
			if r == '\\' { // 跳过转义符
				_, newwidth := utf8.DecodeRune(data[i+width:])
				width += newwidth
			} else if r == first { // 找到终点
				return i + width, data[start : i+width], nil
			}
		}
	// 读标识符、数字等,读到空格或注释符为止
	default:
		for width, i := 0, start; i < len(data); i += width {
			var r rune
			r, width = utf8.DecodeRune(data[i:])
			if unicode.IsSpace(r) || r == '%' {
				return i, data[start:i], nil
			}
		}
	}
	// 进入 EOF,剩下的部分全是一个 token(规则不足)
	if atEOF && len(data) > start {
		return len(data), data[start:], nil
	}
	// 要求更长的数据
	return 0, nil, nil
}