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
use HashMap;
use crate::;
/// A builder for constructing a [`SimpleMatcher`].
///
/// This builder provides a convenient and ergonomic API for constructing a [`SimpleMatcher`]
/// without needing to manually build and nest HashMaps. It allows adding words incrementally,
/// grouped by their intended text processing pipeline.
///
/// # Detailed Explanation / Algorithm
/// The builder collects word patterns into a nested map structure: `HashMap<ProcessType, HashMap<word_id, word_pattern>>`.
/// When `build()` is called, this structure is passed to `SimpleMatcher::new`, which then:
/// 1. Parses logical operators (`&`, `~`) in each pattern.
/// 2. Deduplicates sub-patterns across different process types.
/// 3. Compiles an optimized Aho-Corasick automaton for efficient matching.
///
/// # Type Parameters
/// * `'a` - The lifetime of the word patterns and strings.
///
/// # Fields
/// * `word_map` - A nested hash map storing words grouped by their [`ProcessType`] and uniquely identified by a `word_id`.
///
/// # Examples
/// ```rust
/// use matcher_rs::{SimpleMatcherBuilder, ProcessType};
///
/// let matcher = SimpleMatcherBuilder::new()
/// .add_word(ProcessType::None, 1, "hello")
/// .add_word(ProcessType::None, 2, "world")
/// .add_word(ProcessType::Fanjian, 3, "你好")
/// .build();
/// ```
/// A builder for constructing a single [`MatchTable`].
///
/// This builder provides a fluent, ergonomic API for building a [`MatchTable`]
/// without having to construct the struct literal directly. The two required
/// fields — `table_id` and `match_table_type` — are supplied upfront in
/// [`MatchTableBuilder::new`]; everything else is optional and can be added
/// incrementally before calling [`build`](MatchTableBuilder::build).
///
/// # Detailed Explanation / Algorithm
/// The builder accumulates configuration for a single match table:
/// 1. A unique `table_id` for tracking.
/// 2. A [`MatchTableType`] defining the engine and preprocessing to use.
/// 3. Lists of match patterns and optional exemption patterns.
///
/// When `build()` is called, these are bundled into a [`MatchTable`] struct which
/// can then be added to a [`MatcherBuilder`].
///
/// # Type Parameters
/// * `'a` - The lifetime of the word patterns and strings.
///
/// # Fields
/// * `table_id` - A unique identifier for the specific matching table.
/// * `match_table_type` - The specific matching strategy and configuration used for this table.
/// * `word_list` - A list of words to be used in the matching process.
/// * `exemption_process_type` - The text processing rules to be applied to exemption words.
/// * `exemption_word_list` - A list of words that trigger exemptions from matching.
///
/// # Examples
/// ```rust
/// use matcher_rs::{MatchTableBuilder, MatchTableType, ProcessType, MatcherBuilder};
///
/// let table = MatchTableBuilder::new(1, MatchTableType::Simple { process_type: ProcessType::None })
/// .add_word("hello")
/// .add_word("world")
/// .add_exemption_word("goodbye")
/// .build();
///
/// let matcher = MatcherBuilder::new()
/// .add_table(1, table)
/// .build();
/// ```
/// A builder for constructing a [`Matcher`].
///
/// This builder provides a convenient way to construct a [`Matcher`]
/// by adding complete [`MatchTable`] entries iteratively.
///
/// # Detailed Explanation / Algorithm
/// The `MatcherBuilder` groups [`MatchTable`]s under rule-level identifiers (`match_id`).
/// When `build()` is called, it constructs a complex [`Matcher`] that:
/// 1. Combines all [`MatchTable`] entries.
/// 2. Deduplicates text processing workflows across tables.
/// 3. Initializes the internal engines (`SimpleMatcher`, `RegexMatcher`, `SimMatcher`) for each table category.
///
/// # Type Parameters
/// * `'a` - The lifetime of the word patterns and strings inside the tables.
///
/// # Fields
/// * `table_map` - A map grouping [`MatchTable`] instances under rule-level identifiers (`match_id`).
///
/// # Examples
/// ```rust
/// use matcher_rs::{MatcherBuilder, MatchTable, MatchTableType, ProcessType};
///
/// let table = MatchTable {
/// table_id: 1,
/// match_table_type: MatchTableType::Simple { process_type: ProcessType::None },
/// word_list: vec!["hello"],
/// exemption_process_type: ProcessType::None,
/// exemption_word_list: vec![],
/// };
///
/// let matcher = MatcherBuilder::new()
/// .add_table(1, table)
/// .build();
/// ```