aboutsummaryrefslogtreecommitdiff
path: root/libbb/unicode.c
diff options
context:
space:
mode:
authorTomas Heinrich <heinrich.tomas@gmail.com>2010-03-26 13:13:24 +0100
committerDenys Vlasenko <vda.linux@googlemail.com>2010-03-26 13:13:24 +0100
commitaa167556cd2954bb9a9fb0a005178462087a4600 (patch)
tree241a779a20d302397bd5e59eefceb49ce78834e4 /libbb/unicode.c
parent385b4562e39e373761fd62b0990dce02ff96661f (diff)
downloadbusybox-w32-aa167556cd2954bb9a9fb0a005178462087a4600.tar.gz
busybox-w32-aa167556cd2954bb9a9fb0a005178462087a4600.tar.bz2
busybox-w32-aa167556cd2954bb9a9fb0a005178462087a4600.zip
unicode: optional table for better handling of neutral bidi chars
Off: function old new delta unicode_bidi_isrtl - 55 +55 isrtl_str 51 65 +14 unicode_isrtl 55 - -55 read_line_input 5003 4937 -66 ------------------------------------------------------------------------------ (add/remove: 1/4 grow/shrink: 1/1 up/down: 69/-121) Total: -52 bytes On: function old new delta static.neutral_b - 320 +320 static.neutral_p - 142 +142 unicode_bidi_isrtl - 55 +55 unicode_bidi_is_neutral_wchar - 55 +55 isrtl_str 51 59 +8 unicode_isrtl 55 - -55 read_line_input 5003 4937 -66 ------------------------------------------------------------------------------ (add/remove: 4/4 grow/shrink: 1/1 up/down: 580/-121) Total: 459 bytes Signed-off-by: Tomas Heinrich <heinrich.tomas@gmail.com> Signed-off-by: Denys Vlasenko <vda.linux@googlemail.com>
Diffstat (limited to 'libbb/unicode.c')
-rw-r--r--libbb/unicode.c348
1 files changed, 255 insertions, 93 deletions
diff --git a/libbb/unicode.c b/libbb/unicode.c
index 91667ea72..bc9714562 100644
--- a/libbb/unicode.c
+++ b/libbb/unicode.c
@@ -242,7 +242,7 @@ int FAST_FUNC iswpunct(wint_t wc)
242#include "unicode_wcwidth.c" 242#include "unicode_wcwidth.c"
243 243
244# if ENABLE_UNICODE_BIDI_SUPPORT 244# if ENABLE_UNICODE_BIDI_SUPPORT
245int FAST_FUNC unicode_isrtl(wint_t wc) 245int FAST_FUNC unicode_bidi_isrtl(wint_t wc)
246{ 246{
247 /* ranges taken from 247 /* ranges taken from
248 * http://www.unicode.org/Public/5.2.0/ucd/extracted/DerivedBidiClass.txt 248 * http://www.unicode.org/Public/5.2.0/ucd/extracted/DerivedBidiClass.txt
@@ -251,43 +251,44 @@ int FAST_FUNC unicode_isrtl(wint_t wc)
251 static const struct interval rtl_b[] = { 251 static const struct interval rtl_b[] = {
252# define BIG_(a,b) { a, b }, 252# define BIG_(a,b) { a, b },
253# define PAIR(a,b) 253# define PAIR(a,b)
254 PAIR(0x0590, 0x0590) 254# define ARRAY \
255 PAIR(0x05BE, 0x05BE) 255 PAIR(0x0590, 0x0590) \
256 PAIR(0x05C0, 0x05C0) 256 PAIR(0x05BE, 0x05BE) \
257 PAIR(0x05C3, 0x05C3) 257 PAIR(0x05C0, 0x05C0) \
258 PAIR(0x05C6, 0x05C6) 258 PAIR(0x05C3, 0x05C3) \
259 BIG_(0x05C8, 0x05FF) 259 PAIR(0x05C6, 0x05C6) \
260 PAIR(0x0604, 0x0605) 260 BIG_(0x05C8, 0x05FF) \
261 PAIR(0x0608, 0x0608) 261 PAIR(0x0604, 0x0605) \
262 PAIR(0x060B, 0x060B) 262 PAIR(0x0608, 0x0608) \
263 PAIR(0x060D, 0x060D) 263 PAIR(0x060B, 0x060B) \
264 BIG_(0x061B, 0x064A) 264 PAIR(0x060D, 0x060D) \
265 PAIR(0x065F, 0x065F) 265 BIG_(0x061B, 0x064A) \
266 PAIR(0x066D, 0x066F) 266 PAIR(0x065F, 0x065F) \
267 BIG_(0x0671, 0x06D5) 267 PAIR(0x066D, 0x066F) \
268 PAIR(0x06E5, 0x06E6) 268 BIG_(0x0671, 0x06D5) \
269 PAIR(0x06EE, 0x06EF) 269 PAIR(0x06E5, 0x06E6) \
270 BIG_(0x06FA, 0x070E) 270 PAIR(0x06EE, 0x06EF) \
271 PAIR(0x0710, 0x0710) 271 BIG_(0x06FA, 0x070E) \
272 BIG_(0x0712, 0x072F) 272 PAIR(0x0710, 0x0710) \
273 BIG_(0x074B, 0x07A5) 273 BIG_(0x0712, 0x072F) \
274 BIG_(0x07B1, 0x07EA) 274 BIG_(0x074B, 0x07A5) \
275 PAIR(0x07F4, 0x07F5) 275 BIG_(0x07B1, 0x07EA) \
276 BIG_(0x07FA, 0x0815) 276 PAIR(0x07F4, 0x07F5) \
277 PAIR(0x081A, 0x081A) 277 BIG_(0x07FA, 0x0815) \
278 PAIR(0x0824, 0x0824) 278 PAIR(0x081A, 0x081A) \
279 PAIR(0x0828, 0x0828) 279 PAIR(0x0824, 0x0824) \
280 BIG_(0x082E, 0x08FF) 280 PAIR(0x0828, 0x0828) \
281 PAIR(0x200F, 0x200F) 281 BIG_(0x082E, 0x08FF) \
282 PAIR(0x202B, 0x202B) 282 PAIR(0x200F, 0x200F) \
283 PAIR(0x202E, 0x202E) 283 PAIR(0x202B, 0x202B) \
284 BIG_(0xFB1D, 0xFB1D) 284 PAIR(0x202E, 0x202E) \
285 BIG_(0xFB1F, 0xFB28) 285 BIG_(0xFB1D, 0xFB1D) \
286 BIG_(0xFB2A, 0xFD3D) 286 BIG_(0xFB1F, 0xFB28) \
287 BIG_(0xFD40, 0xFDCF) 287 BIG_(0xFB2A, 0xFD3D) \
288 BIG_(0xFDC8, 0xFDCF) 288 BIG_(0xFD40, 0xFDCF) \
289 BIG_(0xFDF0, 0xFDFC) 289 BIG_(0xFDC8, 0xFDCF) \
290 BIG_(0xFDFE, 0xFDFF) 290 BIG_(0xFDF0, 0xFDFC) \
291 BIG_(0xFDFE, 0xFDFF) \
291 BIG_(0xFE70, 0xFEFE) 292 BIG_(0xFE70, 0xFEFE)
292 /* Probably not necessary 293 /* Probably not necessary
293 {0x10800, 0x1091E}, 294 {0x10800, 0x1091E},
@@ -302,68 +303,21 @@ int FAST_FUNC unicode_isrtl(wint_t wc)
302 {0x10E7F, 0x10FFF}, 303 {0x10E7F, 0x10FFF},
303 {0x1E800, 0x1EFFF} 304 {0x1E800, 0x1EFFF}
304 */ 305 */
306 ARRAY
305# undef BIG_ 307# undef BIG_
306# undef PAIR 308# undef PAIR
307 }; 309 };
308
309 static const uint16_t rtl_p[] = {
310# define BIG_(a,b) 310# define BIG_(a,b)
311# define PAIR(a,b) (a << 2) | (b-a), 311# define PAIR(a,b) (a << 2) | (b-a),
312 /* Exact copy-n-paste of the above: */ 312 static const uint16_t rtl_p[] = { ARRAY };
313 PAIR(0x0590, 0x0590)
314 PAIR(0x05BE, 0x05BE)
315 PAIR(0x05C0, 0x05C0)
316 PAIR(0x05C3, 0x05C3)
317 PAIR(0x05C6, 0x05C6)
318 BIG_(0x05C8, 0x05FF)
319 PAIR(0x0604, 0x0605)
320 PAIR(0x0608, 0x0608)
321 PAIR(0x060B, 0x060B)
322 PAIR(0x060D, 0x060D)
323 BIG_(0x061B, 0x064A)
324 PAIR(0x065F, 0x065F)
325 PAIR(0x066D, 0x066F)
326 BIG_(0x0671, 0x06D5)
327 PAIR(0x06E5, 0x06E6)
328 PAIR(0x06EE, 0x06EF)
329 BIG_(0x06FA, 0x070E)
330 PAIR(0x0710, 0x0710)
331 BIG_(0x0712, 0x072F)
332 BIG_(0x074B, 0x07A5)
333 BIG_(0x07B1, 0x07EA)
334 PAIR(0x07F4, 0x07F5)
335 BIG_(0x07FA, 0x0815)
336 PAIR(0x081A, 0x081A)
337 PAIR(0x0824, 0x0824)
338 PAIR(0x0828, 0x0828)
339 BIG_(0x082E, 0x08FF)
340 PAIR(0x200F, 0x200F)
341 PAIR(0x202B, 0x202B)
342 PAIR(0x202E, 0x202E)
343 BIG_(0xFB1D, 0xFB1D)
344 BIG_(0xFB1F, 0xFB28)
345 BIG_(0xFB2A, 0xFD3D)
346 BIG_(0xFD40, 0xFDCF)
347 BIG_(0xFDC8, 0xFDCF)
348 BIG_(0xFDF0, 0xFDFC)
349 BIG_(0xFDFE, 0xFDFF)
350 BIG_(0xFE70, 0xFEFE)
351 /* Probably not necessary
352 {0x10800, 0x1091E},
353 {0x10920, 0x10A00},
354 {0x10A04, 0x10A04},
355 {0x10A07, 0x10A0B},
356 {0x10A10, 0x10A37},
357 {0x10A3B, 0x10A3E},
358 {0x10A40, 0x10A7F},
359 {0x10B36, 0x10B38},
360 {0x10B40, 0x10E5F},
361 {0x10E7F, 0x10FFF},
362 {0x1E800, 0x1EFFF}
363 */
364# undef BIG_ 313# undef BIG_
365# undef PAIR 314# undef PAIR
366 }; 315# define BIG_(a,b) char big_##a[b < 0x4000 && b-a <= 3 ? -1 : 1];
316# define PAIR(a,b) char pair##a[b >= 0x4000 || b-a > 3 ? -1 : 1];
317 struct CHECK { ARRAY };
318# undef BIG_
319# undef PAIR
320# undef ARRAY
367 321
368 if (in_interval_table(wc, rtl_b, ARRAY_SIZE(rtl_b) - 1)) 322 if (in_interval_table(wc, rtl_b, ARRAY_SIZE(rtl_b) - 1))
369 return 1; 323 return 1;
@@ -371,6 +325,214 @@ int FAST_FUNC unicode_isrtl(wint_t wc)
371 return 1; 325 return 1;
372 return 0; 326 return 0;
373} 327}
328
329# if ENABLE_UNICODE_NEUTRAL_TABLE
330int FAST_FUNC unicode_bidi_is_neutral_wchar(wint_t wc)
331{
332 /* ranges taken from
333 * http://www.unicode.org/Public/5.2.0/ucd/extracted/DerivedBidiClass.txt
334 * Bidi_Classes: Paragraph_Separator, Segment_Separator,
335 * White_Space, Other_Neutral, European_Number, European_Separator,
336 * European_Terminator, Arabic_Number, Common_Separator
337 */
338 static const struct interval neutral_b[] = {
339# define BIG_(a,b) { a, b },
340# define PAIR(a,b)
341# define ARRAY \
342 BIG_(0x0009, 0x000D) \
343 BIG_(0x001C, 0x0040) \
344 BIG_(0x005B, 0x0060) \
345 PAIR(0x007B, 0x007E) \
346 PAIR(0x0085, 0x0085) \
347 BIG_(0x00A0, 0x00A9) \
348 PAIR(0x00AB, 0x00AC) \
349 BIG_(0x00AE, 0x00B4) \
350 PAIR(0x00B6, 0x00B9) \
351 BIG_(0x00BB, 0x00BF) \
352 PAIR(0x00D7, 0x00D7) \
353 PAIR(0x00F7, 0x00F7) \
354 PAIR(0x02B9, 0x02BA) \
355 BIG_(0x02C2, 0x02CF) \
356 BIG_(0x02D2, 0x02DF) \
357 BIG_(0x02E5, 0x02FF) \
358 PAIR(0x0374, 0x0375) \
359 PAIR(0x037E, 0x037E) \
360 PAIR(0x0384, 0x0385) \
361 PAIR(0x0387, 0x0387) \
362 PAIR(0x03F6, 0x03F6) \
363 PAIR(0x058A, 0x058A) \
364 PAIR(0x0600, 0x0603) \
365 PAIR(0x0606, 0x0607) \
366 PAIR(0x0609, 0x060A) \
367 PAIR(0x060C, 0x060C) \
368 PAIR(0x060E, 0x060F) \
369 BIG_(0x0660, 0x066C) \
370 PAIR(0x06DD, 0x06DD) \
371 PAIR(0x06E9, 0x06E9) \
372 BIG_(0x06F0, 0x06F9) \
373 PAIR(0x07F6, 0x07F9) \
374 PAIR(0x09F2, 0x09F3) \
375 PAIR(0x09FB, 0x09FB) \
376 PAIR(0x0AF1, 0x0AF1) \
377 BIG_(0x0BF3, 0x0BFA) \
378 BIG_(0x0C78, 0x0C7E) \
379 PAIR(0x0CF1, 0x0CF2) \
380 PAIR(0x0E3F, 0x0E3F) \
381 PAIR(0x0F3A, 0x0F3D) \
382 BIG_(0x1390, 0x1400) \
383 PAIR(0x1680, 0x1680) \
384 PAIR(0x169B, 0x169C) \
385 PAIR(0x17DB, 0x17DB) \
386 BIG_(0x17F0, 0x17F9) \
387 BIG_(0x1800, 0x180A) \
388 PAIR(0x180E, 0x180E) \
389 PAIR(0x1940, 0x1940) \
390 PAIR(0x1944, 0x1945) \
391 BIG_(0x19DE, 0x19FF) \
392 PAIR(0x1FBD, 0x1FBD) \
393 PAIR(0x1FBF, 0x1FC1) \
394 PAIR(0x1FCD, 0x1FCF) \
395 PAIR(0x1FDD, 0x1FDF) \
396 PAIR(0x1FED, 0x1FEF) \
397 PAIR(0x1FFD, 0x1FFE) \
398 BIG_(0x2000, 0x200A) \
399 BIG_(0x2010, 0x2029) \
400 BIG_(0x202F, 0x205F) \
401 PAIR(0x2070, 0x2070) \
402 BIG_(0x2074, 0x207E) \
403 BIG_(0x2080, 0x208E) \
404 BIG_(0x20A0, 0x20B8) \
405 PAIR(0x2100, 0x2101) \
406 PAIR(0x2103, 0x2106) \
407 PAIR(0x2108, 0x2109) \
408 PAIR(0x2114, 0x2114) \
409 PAIR(0x2116, 0x2118) \
410 BIG_(0x211E, 0x2123) \
411 PAIR(0x2125, 0x2125) \
412 PAIR(0x2127, 0x2127) \
413 PAIR(0x2129, 0x2129) \
414 PAIR(0x212E, 0x212E) \
415 PAIR(0x213A, 0x213B) \
416 BIG_(0x2140, 0x2144) \
417 PAIR(0x214A, 0x214D) \
418 BIG_(0x2150, 0x215F) \
419 PAIR(0x2189, 0x2189) \
420 BIG_(0x2190, 0x2335) \
421 BIG_(0x237B, 0x2394) \
422 BIG_(0x2396, 0x23E8) \
423 BIG_(0x2400, 0x2426) \
424 BIG_(0x2440, 0x244A) \
425 BIG_(0x2460, 0x249B) \
426 BIG_(0x24EA, 0x26AB) \
427 BIG_(0x26AD, 0x26CD) \
428 BIG_(0x26CF, 0x26E1) \
429 PAIR(0x26E3, 0x26E3) \
430 BIG_(0x26E8, 0x26FF) \
431 PAIR(0x2701, 0x2704) \
432 PAIR(0x2706, 0x2709) \
433 BIG_(0x270C, 0x2727) \
434 BIG_(0x2729, 0x274B) \
435 PAIR(0x274D, 0x274D) \
436 PAIR(0x274F, 0x2752) \
437 BIG_(0x2756, 0x275E) \
438 BIG_(0x2761, 0x2794) \
439 BIG_(0x2798, 0x27AF) \
440 BIG_(0x27B1, 0x27BE) \
441 BIG_(0x27C0, 0x27CA) \
442 PAIR(0x27CC, 0x27CC) \
443 BIG_(0x27D0, 0x27FF) \
444 BIG_(0x2900, 0x2B4C) \
445 BIG_(0x2B50, 0x2B59) \
446 BIG_(0x2CE5, 0x2CEA) \
447 BIG_(0x2CF9, 0x2CFF) \
448 BIG_(0x2E00, 0x2E99) \
449 BIG_(0x2E9B, 0x2EF3) \
450 BIG_(0x2F00, 0x2FD5) \
451 BIG_(0x2FF0, 0x2FFB) \
452 BIG_(0x3000, 0x3004) \
453 BIG_(0x3008, 0x3020) \
454 PAIR(0x3030, 0x3030) \
455 PAIR(0x3036, 0x3037) \
456 PAIR(0x303D, 0x303D) \
457 PAIR(0x303E, 0x303F) \
458 PAIR(0x309B, 0x309C) \
459 PAIR(0x30A0, 0x30A0) \
460 PAIR(0x30FB, 0x30FB) \
461 BIG_(0x31C0, 0x31E3) \
462 PAIR(0x321D, 0x321E) \
463 BIG_(0x3250, 0x325F) \
464 PAIR(0x327C, 0x327E) \
465 BIG_(0x32B1, 0x32BF) \
466 PAIR(0x32CC, 0x32CF) \
467 PAIR(0x3377, 0x337A) \
468 PAIR(0x33DE, 0x33DF) \
469 PAIR(0x33FF, 0x33FF) \
470 BIG_(0x4DC0, 0x4DFF) \
471 BIG_(0xA490, 0xA4C6) \
472 BIG_(0xA60D, 0xA60F) \
473 BIG_(0xA673, 0xA673) \
474 BIG_(0xA67E, 0xA67F) \
475 BIG_(0xA700, 0xA721) \
476 BIG_(0xA788, 0xA788) \
477 BIG_(0xA828, 0xA82B) \
478 BIG_(0xA838, 0xA839) \
479 BIG_(0xA874, 0xA877) \
480 BIG_(0xFB29, 0xFB29) \
481 BIG_(0xFD3E, 0xFD3F) \
482 BIG_(0xFDFD, 0xFDFD) \
483 BIG_(0xFE10, 0xFE19) \
484 BIG_(0xFE30, 0xFE52) \
485 BIG_(0xFE54, 0xFE66) \
486 BIG_(0xFE68, 0xFE6B) \
487 BIG_(0xFF01, 0xFF20) \
488 BIG_(0xFF3B, 0xFF40) \
489 BIG_(0xFF5B, 0xFF65) \
490 BIG_(0xFFE0, 0xFFE6) \
491 BIG_(0xFFE8, 0xFFEE) \
492 BIG_(0xFFF9, 0xFFFD)
493 /*
494 {0x10101, 0x10101},
495 {0x10140, 0x1019B},
496 {0x1091F, 0x1091F},
497 {0x10B39, 0x10B3F},
498 {0x10E60, 0x10E7E},
499 {0x1D200, 0x1D241},
500 {0x1D245, 0x1D245},
501 {0x1D300, 0x1D356},
502 {0x1D6DB, 0x1D6DB},
503 {0x1D715, 0x1D715},
504 {0x1D74F, 0x1D74F},
505 {0x1D789, 0x1D789},
506 {0x1D7C3, 0x1D7C3},
507 {0x1D7CE, 0x1D7FF},
508 {0x1F000, 0x1F02B},
509 {0x1F030, 0x1F093},
510 {0x1F100, 0x1F10A}
511 */
512 ARRAY
513# undef BIG_
514# undef PAIR
515 };
516# define BIG_(a,b)
517# define PAIR(a,b) (a << 2) | (b-a),
518 static const uint16_t neutral_p[] = { ARRAY };
519# undef BIG_
520# undef PAIR
521# define BIG_(a,b) char big_##a[b < 0x4000 && b-a <= 3 ? -1 : 1];
522# define PAIR(a,b) char pair##a[b >= 0x4000 || b-a > 3 ? -1 : 1];
523 struct CHECK { ARRAY };
524# undef BIG_
525# undef PAIR
526# undef ARRAY
527
528 if (in_interval_table(wc, neutral_b, ARRAY_SIZE(neutral_b) - 1))
529 return 1;
530 if (in_uint16_table(wc, neutral_p, ARRAY_SIZE(neutral_p) - 1))
531 return 1;
532 return 0;
533}
534# endif
535
374# endif /* UNICODE_BIDI_SUPPORT */ 536# endif /* UNICODE_BIDI_SUPPORT */
375 537
376#endif /* Homegrown Unicode support */ 538#endif /* Homegrown Unicode support */