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
//! Unicode normalization for Urdu text.
//!
//! `کتاب` typed on an Urdu keyboard and `كتاب` typed on an Arabic keyboard look
//! identical on screen. They are not the same bytes: the third letter is
//! `U+06A9` in one and `U+0643` in the other. So `a == b` is `false`, your
//! search box returns nothing, and your deduplication misses half the corpus.
//!
//! This crate folds those shape-identical duplicates together, strips the marks
//! that carry no meaning, and expands the pre-shaped glyphs that PDF extraction
//! leaves behind.
//!
//! ```
//! use urdu_text::{eq_normalized, normalize};
//!
//! // Arabic kaf vs Urdu keheh — same word, different bytes.
//! assert!(eq_normalized("كتاب", "کتاب"));
//!
//! // Tatweel is decoration for line justification; it means nothing.
//! assert_eq!(normalize("کتـــاب"), "کتاب");
//!
//! // A lam-alef ligature out of a PDF, expanded back into two letters.
//! assert_eq!(normalize("\u{FEFB}ہور"), "لاہور");
//! ```
//!
//! # What this crate refuses to do
//!
//! Urdu is written in a Perso-Arabic script, so it is tempting to reach for an
//! Arabic normalizer. Every general-purpose Arabic normalizer gets at least one
//! of the following wrong, and each mistake silently changes what the text says:
//!
//! | Fold | Arabic normalizers | This crate | Why |
//! |------|--------------------|------------|-----|
//! | `آ` → `ا` | applied | **never** | `آم` "mango" ≠ `ام` |
//! | `ے` → `ی` | applied | **never** | `کے` "of" ≠ `کی` "whose" |
//! | `ھ` → `ہ` | applied | **never** | `تھا` "was" → `تہا`, not a word |
//! | strip hamza `U+0654` | applied | **never** | `کوئی` "someone" → `کوی`, not a word |
//!
//! In Arabic, `آ` really is alef with a maddah stacked on it, and folding it is
//! defensible. In Urdu it is its own letter with its own place in the alphabet.
//! Hamza is worse: `U+0654` sits inside the Unicode combining-marks range, so
//! "strip all combining marks" removes it — and in Urdu, hamza is spelling.
//!
//! # Configuring
//!
//! [`normalize`] applies a default preset. For anything else, build an
//! [`Options`] and call [`normalize_with`]:
//!
//! ```
//! use urdu_text::{normalize_with, Options};
//!
//! // Everything on, plus ASCII digits (off in the default preset).
//! let indexing = Options { ascii_digits: true, ..Options::default() };
//! assert_eq!(normalize_with("۲۰۲۴ء", &indexing), "2024ء");
//!
//! // Or start from nothing and switch on exactly one thing. Here the tatweel
//! // goes but the Arabic kaf U+0643 is deliberately left as it was.
//! let gentle = Options { strip_tatweel: true, ..Options::none() };
//! assert_eq!(normalize_with("\u{0643}ت\u{0640}اب", &gentle), "\u{0643}تاب");
//! ```
//!
//! [`Options`] is deliberately *not* `#[non_exhaustive]`, so `..Options::default()`
//! works from outside the crate. The trade-off is that adding a field is a
//! breaking change — which is the honest signal, because adding a normalization
//! step changes everyone's output anyway.
//!
//! # Properties
//!
//! - **Idempotent.** `normalize(normalize(s)) == normalize(s)` for every preset.
//! - **Single pass, one allocation.** No intermediate `String`s.
//! - **Zero dependencies**, `#![no_std]` (needs `alloc`), `#![forbid(unsafe_code)]`.
//!
//! # Where the decisions live
//!
//! Every character table is in `src/tables.rs`, one judgement call per comment.
//! The README lists the calls a native speaker should second-guess.
extern crate alloc;
use String;
pub use ;
use is_format_mark;
/// Which normalization steps to apply.
///
/// Every field defaults to `true` except [`ascii_digits`](Options::ascii_digits).
/// Use `..Options::default()` to change one thing, or [`Options::none()`] to
/// start from all-off.
///
/// ```
/// use urdu_text::Options;
///
/// let o = Options { collapse_whitespace: false, ..Options::default() };
/// assert!(o.fold_letters);
/// assert!(!o.collapse_whitespace);
/// ```
/// Normalize Urdu text with the default preset.
///
/// Equivalent to `normalize_with(input, &Options::default())`: presentation
/// forms expanded, letters folded, aerab and tatweel and invisible marks
/// stripped, whitespace collapsed, digits left as they are.
///
/// # Examples
///
/// ```
/// use urdu_text::normalize;
///
/// // Arabic kaf U+0643 folds to Urdu keheh U+06A9.
/// assert_eq!(normalize("كتاب"), "کتاب");
///
/// // Aerab removed, hamza kept — both the combining and precomposed forms.
/// assert_eq!(normalize("\u{06CC}\u{0654}"), "\u{06CC}\u{0654}");
/// assert_eq!(normalize("کِتاب"), "کتاب");
/// assert_eq!(normalize("کوئی"), "کوئی");
///
/// // Whitespace collapsed and trimmed.
/// assert_eq!(normalize(" اردو زبان "), "اردو زبان");
///
/// // Digits are left alone by default.
/// assert_eq!(normalize("۲۰۲۴"), "۲۰۲۴");
/// ```
/// Normalize Urdu text with an explicit [`Options`].
///
/// Runs in a single pass over `input` with one allocation.
///
/// # Examples
///
/// ```
/// use urdu_text::{normalize_with, Options};
///
/// let searchable = Options { ascii_digits: true, ..Options::default() };
/// assert_eq!(normalize_with("سن ۱۹۴۷", &searchable), "سن 1947");
///
/// // Keep the diacritics, fix everything else.
/// let keep_aerab = Options { strip_aerab: false, ..Options::default() };
/// assert_eq!(normalize_with("كِتاب", &keep_aerab), "کِتاب");
/// ```
/// Apply the per-character steps and append, if anything survives.
///
/// `pending_space` implements whitespace collapsing without a second pass: a
/// run of whitespace only sets the flag, and the flag is only spent when a real
/// character follows. Leading whitespace never sets it (`out` is still empty)
/// and trailing whitespace never spends it, so trimming falls out for free.
/// Are these two strings the same once normalized?
///
/// This is what you want instead of `a == b` when comparing Urdu that came from
/// more than one source.
///
/// # Examples
///
/// ```
/// use urdu_text::eq_normalized;
///
/// assert!(eq_normalized("كتاب", "کتاب")); // Arabic kaf vs Urdu keheh
/// assert!(eq_normalized("کتـــاب", "کتاب")); // tatweel
///
/// // Still different words, and still compare as such.
/// assert!(!eq_normalized("کے", "کی"));
/// assert!(!eq_normalized("آم", "ام"));
/// assert!(!eq_normalized("تھا", "تہا"));
/// ```
/// Remove tatweel (`U+0640`) and nothing else.
///
/// ```
/// use urdu_text::strip_tatweel;
///
/// assert_eq!(strip_tatweel("کتـــاب"), "کتاب");
/// // Nothing else is touched — the Arabic kaf survives.
/// assert_eq!(strip_tatweel("\u{0643}ـ"), "\u{0643}");
/// ```
/// Remove aerab (diacritics) and nothing else.
///
/// Hamza (`U+0654`, `U+0655`) is **kept** — see [`is_aerab_char`].
///
/// ```
/// use urdu_text::strip_aerab;
///
/// assert_eq!(strip_aerab("کِتاب"), "کتاب");
/// // A combining hamza survives, because removing it would change the word.
/// assert_eq!(strip_aerab("\u{06CC}\u{0654}"), "\u{06CC}\u{0654}");
/// // ...and so does the precomposed letter U+0626 ئ.
/// assert_eq!(strip_aerab("کوئی"), "کوئی");
/// ```