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
|
package fzf
import (
"regexp"
"sort"
"strings"
)
const UPPERCASE = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
// fuzzy
// 'exact
// ^exact-prefix
// exact-suffix$
// !not-fuzzy
// !'not-exact
// !^not-exact-prefix
// !not-exact-suffix$
type TermType int
const (
TERM_FUZZY TermType = iota
TERM_EXACT
TERM_PREFIX
TERM_SUFFIX
)
type Term struct {
typ TermType
inv bool
text []rune
origText []rune
}
type Pattern struct {
mode Mode
caseSensitive bool
text []rune
terms []Term
hasInvTerm bool
delimiter *regexp.Regexp
nth []Range
procFun map[TermType]func(bool, *string, []rune) (int, int)
}
var (
_patternCache map[string]*Pattern
_splitRegex *regexp.Regexp
_cache ChunkCache
)
func init() {
// We can uniquely identify the pattern for a given string since
// mode and caseMode do not change while the program is running
_patternCache = make(map[string]*Pattern)
_splitRegex = regexp.MustCompile("\\s+")
_cache = NewChunkCache()
}
func clearPatternCache() {
_patternCache = make(map[string]*Pattern)
}
func BuildPattern(mode Mode, caseMode Case,
nth []Range, delimiter *regexp.Regexp, runes []rune) *Pattern {
var asString string
switch mode {
case MODE_EXTENDED, MODE_EXTENDED_EXACT:
asString = strings.Trim(string(runes), " ")
default:
asString = string(runes)
}
cached, found := _patternCache[asString]
if found {
return cached
}
caseSensitive, hasInvTerm := true, false
terms := []Term{}
switch caseMode {
case CASE_SMART:
if !strings.ContainsAny(asString, UPPERCASE) {
runes, caseSensitive = []rune(strings.ToLower(asString)), false
}
case CASE_IGNORE:
runes, caseSensitive = []rune(strings.ToLower(asString)), false
}
switch mode {
case MODE_EXTENDED, MODE_EXTENDED_EXACT:
terms = parseTerms(mode, string(runes))
for _, term := range terms {
if term.inv {
hasInvTerm = true
}
}
}
ptr := &Pattern{
mode: mode,
caseSensitive: caseSensitive,
text: runes,
terms: terms,
hasInvTerm: hasInvTerm,
nth: nth,
delimiter: delimiter,
procFun: make(map[TermType]func(bool, *string, []rune) (int, int))}
ptr.procFun[TERM_FUZZY] = FuzzyMatch
ptr.procFun[TERM_EXACT] = ExactMatchNaive
ptr.procFun[TERM_PREFIX] = PrefixMatch
ptr.procFun[TERM_SUFFIX] = SuffixMatch
_patternCache[asString] = ptr
return ptr
}
func parseTerms(mode Mode, str string) []Term {
tokens := _splitRegex.Split(str, -1)
terms := []Term{}
for _, token := range tokens {
typ, inv, text := TERM_FUZZY, false, token
origText := []rune(text)
if mode == MODE_EXTENDED_EXACT {
typ = TERM_EXACT
}
if strings.HasPrefix(text, "!") {
inv = true
text = text[1:]
}
if strings.HasPrefix(text, "'") {
if mode == MODE_EXTENDED {
typ = TERM_EXACT
text = text[1:]
}
} else if strings.HasPrefix(text, "^") {
typ = TERM_PREFIX
text = text[1:]
} else if strings.HasSuffix(text, "$") {
typ = TERM_SUFFIX
text = text[:len(text)-1]
}
if len(text) > 0 {
terms = append(terms, Term{
typ: typ,
inv: inv,
text: []rune(text),
origText: origText})
}
}
return terms
}
func (p *Pattern) IsEmpty() bool {
if p.mode == MODE_FUZZY {
return len(p.text) == 0
} else {
return len(p.terms) == 0
}
}
func (p *Pattern) AsString() string {
return string(p.text)
}
func (p *Pattern) CacheKey() string {
if p.mode == MODE_FUZZY {
return p.AsString()
}
cacheableTerms := []string{}
for _, term := range p.terms {
if term.inv {
continue
}
cacheableTerms = append(cacheableTerms, string(term.origText))
}
sort.Strings(cacheableTerms)
return strings.Join(cacheableTerms, " ")
}
func (p *Pattern) Match(chunk *Chunk) []*Item {
space := chunk
// ChunkCache: Exact match
cacheKey := p.CacheKey()
if !p.hasInvTerm { // Because we're excluding Inv-term from cache key
if cached, found := _cache.Find(chunk, cacheKey); found {
return cached
}
}
// ChunkCache: Prefix match
foundPrefixCache := false
for idx := len(cacheKey) - 1; idx > 0; idx-- {
if cached, found := _cache.Find(chunk, cacheKey[:idx]); found {
cachedChunk := Chunk(cached)
space = &cachedChunk
foundPrefixCache = true
break
}
}
// ChunkCache: Suffix match
if !foundPrefixCache {
for idx := 1; idx < len(cacheKey); idx++ {
if cached, found := _cache.Find(chunk, cacheKey[idx:]); found {
cachedChunk := Chunk(cached)
space = &cachedChunk
break
}
}
}
var matches []*Item
if p.mode == MODE_FUZZY {
matches = p.fuzzyMatch(space)
} else {
matches = p.extendedMatch(space)
}
if !p.hasInvTerm {
_cache.Add(chunk, cacheKey, matches)
}
return matches
}
func (p *Pattern) fuzzyMatch(chunk *Chunk) []*Item {
matches := []*Item{}
for _, item := range *chunk {
input := p.prepareInput(item)
if sidx, eidx := p.iter(FuzzyMatch, input, p.text); sidx >= 0 {
matches = append(matches, &Item{
text: item.text,
index: item.index,
offsets: []Offset{Offset{sidx, eidx}},
rank: NilRank})
}
}
return matches
}
func (p *Pattern) extendedMatch(chunk *Chunk) []*Item {
matches := []*Item{}
for _, item := range *chunk {
input := p.prepareInput(item)
offsets := []Offset{}
Loop:
for _, term := range p.terms {
pfun := p.procFun[term.typ]
if sidx, eidx := p.iter(pfun, input
|