/usr/share/khmerconverter/modules/legacyReorder.py is in khmerconverter 1.4-1.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 | #!/usr/bin/python
# -*- coding: utf8 -*-
# Khmer Lnicode fonts to Khmer Legacy Conversion
# (c) 2006 The WordForge Foundation, all rights reserved.
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public License
# as published by the Free Software Foundation; either version 2.1
# of the License, or (at your option) any later version.
#
# See the LICENSE file for more details.
#
# Developed by:
# Hok Kakada (hokkakada@khmeros.info)
# Keo Sophon (keosophon@khmeros.info)
# San Titvirak (titvirak@khmeros.info)
# Seth Chanratha (sethchanratha@khmeros.info)
#
# This module reorder unicode string accordding unicode order
import unittest
# important character to test in order to form a cluster
SRAAA = unichr(0x17B6)
SRAE = unichr(0x17C1)
SRAOE = unichr(0x17BE)
SRAOO = unichr(0x17C4)
SRAYA = unichr(0x17BF)
SRAIE = unichr(0x17C0)
SRAAU = unichr(0x17C5)
SRAII = unichr(0x17B8)
SRAU = unichr(0x17BB)
TRIISAP = unichr(0x17CA)
MUUSIKATOAN = unichr(0x17C9)
SAMYOKSANNYA = unichr(0x17D0)
LA = unichr(0x17A1)
NYO = unichr(0x1789)
BA = unichr(0x1794)
YO = unichr(0x1799)
SA = unichr(0x179F)
COENG = unichr(0x17D2)
CORO = unichr(0x17D2) + unichr(0x179A)
CONYO = unichr(0x17D2) + unichr(0x1789)
SRAOM = unichr(0x17C6)
MARK = unichr(0x17EA)
#TODO: think about another relacement for the dotted circle;
DOTCIRCLE = u''
# possible combination for sra E
sraEcombining = {
SRAOE:SRAII,
SRAYA:SRAYA,
SRAIE:SRAIE,
SRAOO:SRAAA,
SRAAU:SRAAU
}
CC_RESERVED = 0
CC_CONSONANT = 1 # Consonant of type 1 or independent vowel
CC_CONSONANT2 = 2 # Consonant of type 2
CC_CONSONANT3 = 3 # Consonant of type 3
CC_ZERO_WIDTH_NJ_MARK = 4 # Zero Width non joiner character (0x200C)
CC_CONSONANT_SHIFTER = 5
CC_ROBAT = 6 # Khmer special diacritic accent -treated differently in state table
CC_COENG = 7 # Subscript consonant combining character
CC_DEPENDENT_VOWEL = 8
CC_SIGN_ABOVE = 9
CC_SIGN_AFTER = 10
CC_ZERO_WIDTH_J_MARK = 11 # Zero width joiner character
CC_COUNT = 12 # This is the number of character classes
CF_CLASS_MASK = 0x0000FFFF
CF_CONSONANT = 0x01000000 # flag to speed up comparing
CF_SPLIT_VOWEL = 0x02000000 # flag for a split vowel -> the first part is added in front of the syllable
CF_DOTTED_CIRCLE = 0x04000000 # add a dotted circle if a character with this flag is the first in a
# syllable
CF_COENG = 0x08000000 # flag to speed up comparing
CF_SHIFTER = 0x10000000 # flag to speed up comparing
CF_ABOVE_VOWEL = 0x20000000 # flag to speed up comparing
# position flags
CF_POS_BEFORE = 0x00080000
CF_POS_BELOW = 0x00040000
CF_POS_ABOVE = 0x00020000
CF_POS_AFTER = 0x00010000
CF_POS_MASK = 0x000f0000
# simple classes, they are used in the state table (in this file) to control the length of a syllable
# they are also used to know where a character should be placed (location in reference to the base character)
# and also to know if a character, when independently displayed, should be displayed with a dotted-circle to
# indicate error in syllable construction
_xx = CC_RESERVED
_sa = CC_SIGN_ABOVE | CF_DOTTED_CIRCLE | CF_POS_ABOVE
_sp = CC_SIGN_AFTER | CF_DOTTED_CIRCLE| CF_POS_AFTER
_c1 = CC_CONSONANT | CF_CONSONANT
_c2 = CC_CONSONANT2 | CF_CONSONANT
_c3 = CC_CONSONANT3 | CF_CONSONANT
_rb = CC_ROBAT | CF_POS_ABOVE | CF_DOTTED_CIRCLE
_cs = CC_CONSONANT_SHIFTER | CF_DOTTED_CIRCLE | CF_SHIFTER
_dl = CC_DEPENDENT_VOWEL | CF_POS_BEFORE | CF_DOTTED_CIRCLE
_db = CC_DEPENDENT_VOWEL | CF_POS_BELOW | CF_DOTTED_CIRCLE
_da = CC_DEPENDENT_VOWEL | CF_POS_ABOVE | CF_DOTTED_CIRCLE | CF_ABOVE_VOWEL
_dr = CC_DEPENDENT_VOWEL | CF_POS_AFTER | CF_DOTTED_CIRCLE
_co = CC_COENG | CF_COENG | CF_DOTTED_CIRCLE
# split vowel
_va = _da | CF_SPLIT_VOWEL
_vr = _dr | CF_SPLIT_VOWEL
# Character class tables
# _xx character does not combine into syllable, such as numbers, puntuation marks, non-Khmer signs...
# _sa Sign placed above the base
# _sp Sign placed after the base
# _c1 Consonant of type 1 or independent vowel (independent vowels behave as type 1 consonants)
# _c2 Consonant of type 2 (only RO)
# _c3 Consonant of type 3
# _rb Khmer sign robat u17CC. combining mark for subscript consonants
# _cd Consonant-shifter
# _dl Dependent vowel placed before the base (left of the base)
# _db Dependent vowel placed below the base
# _da Dependent vowel placed above the base
# _dr Dependent vowel placed behind the base (right of the base)
# _co Khmer combining mark COENG u17D2, combines with the consonant or independent vowel following
# it to create a subscript consonant or independent vowel
# _va Khmer split vowel in wich the first part is before the base and the second one above the base
# _vr Khmer split vowel in wich the first part is before the base and the second one behind (right of) the base
khmerCharClasses = [
_c1, _c1, _c1, _c3, _c1, _c1, _c1, _c1, _c3, _c1, _c1, _c1, _c1, _c3, _c1, _c1, # 1780 - 178F
_c1, _c1, _c1, _c1, _c3, _c1, _c1, _c1, _c1, _c3, _c2, _c1, _c1, _c1, _c3, _c3, # 1790 - 179F
_c1, _c3, _c1, _c1, _c1, _c1, _c1, _c1, _c1, _c1, _c1, _c1, _c1, _c1, _c1, _c1, # 17A0 - 17AF
_c1, _c1, _c1, _c1, _dr, _dr, _dr, _da, _da, _da, _da, _db, _db, _db, _va, _vr, # 17B0 - 17BF
_vr, _dl, _dl, _dl, _vr, _vr, _sa, _sp, _sp, _cs, _cs, _sa, _rb, _sa, _sa, _sa, # 17C0 - 17CF
_sa, _sa, _co, _sa, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _xx, _sa, _xx, _xx, # 17D0 - 17DF
]
#khmerStateTable[][CC_COUNT] =
khmerStateTable = [
# xx c1 c2 c3 zwnj cs rb co dv sa sp zwj
[ 1, 2, 2, 2, 1, 1, 1, 6, 1, 1, 1, 2], # 0 - ground state
[-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1], # 1 - exit state (or sign to the right of the
# syllable)
[-1, -1, -1, -1, 3, 4, 5, 6, 16, 17, 1, -1], # 2 - Base consonant
[-1, -1, -1, -1, -1, 4, -1, -1, 16, -1, -1, -1], # 3 - First ZWNJ before a register shifter
# It can only be followed by a shifter or a vowel
[-1, -1, -1, -1, 15, -1, -1, 6, 16, 17, 1, 14], # 4 - First register shifter
[-1, -1, -1, -1, -1, -1, -1, -1, 20, -1, 1, -1], # 5 - Robat
[-1, 7, 8, 9, -1, -1, -1, -1, -1, -1, -1, -1], # 6 - First Coeng
[-1, -1, -1, -1, 12, 13, -1, 10, 16, 17, 1, 14], # 7 - First consonant of type 1 after coeng
[-1, -1, -1, -1, 12, 13, -1, -1, 16, 17, 1, 14], # 8 - First consonant of type 2 after coeng
[-1, -1, -1, -1, 12, 13, -1, 10, 16, 17, 1, 14], # 9 - First consonant or type 3 after ceong
[-1, 11, 11, 11, -1, -1, -1, -1, -1, -1, -1, -1], # 10 - Second Coeng (no register shifter before)
[-1, -1, -1, -1, 15, -1, -1, -1, 16, 17, 1, 14], # 11 - Second coeng consonant (or ind. vowel) no
# register shifter before
[-1, -1, -1, -1, -1, 13, -1, -1, 16, -1, -1, -1], # 12 - Second ZWNJ before a register shifter
[-1, -1, -1, -1, 15, -1, -1, -1, 16, 17, 1, 14], # 13 - Second register shifter
[-1, -1, -1, -1, -1, -1, -1, -1, 16, -1, -1, -1], # 14 - ZWJ before vowel
[-1, -1, -1, -1, -1, -1, -1, -1, 16, -1, -1, -1], # 15 - ZWNJ before vowel
[-1, -1, -1, -1, -1, -1, -1, -1, -1, 17, 1, 18], # 16 - dependent vowel
[-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 1, 18], # 17 - sign above
[-1, -1, -1, -1, -1, -1, -1, 19, -1, -1, -1, -1], # 18 - ZWJ after vowel
[-1, 1, -1, 1, -1, -1, -1, -1, -1, -1, -1, -1], # 19 - Third coeng
[-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 1, -1] # 20 - dependent vowel after a Robat
]
def getCharClass(uniChar):
"""
input one unicode character;
output an integer which is the Khmer type of the character or 0
"""
if (type(uniChar) != unicode):
raise TypeError('only accept unicode character')
if (len(uniChar) != 1):
raise TypeError('only accept one character, but ' + str(len(uniChar)) + ' chars found.')
ch = ord(uniChar[0])
if (ch >= 0x1780):
ch -= 0x1780
if (ch < len(khmerCharClasses)):
return khmerCharClasses[ch]
return 0
def reorder(sin):
"""
Given an input string of unicode cluster to reorder.
The return is the visual based cluster (legacy style) string.
"""
if (type(sin) != unicode):
raise TypeError('only accept unicode string')
cursor = 0
state = 0
charCount = len(sin)
result = u''
while (cursor < charCount):
reserved = ''
signAbove = ''
signAfter = ''
base = ''
robat = ''
shifter = ''
vowelBefore = ''
vowelBelow = ''
vowelAbove = ''
vowelAfter = ''
coeng = False
cluster = ''
coeng1 = ''
coeng2 = ''
shifterAfterCoeng = False
while (cursor < charCount):
curChar = sin[cursor]
kChar = getCharClass(curChar)
charClass = kChar & CF_CLASS_MASK
state = khmerStateTable[state][charClass]
if (state < 0):
break
## collect variable for cluster here
if (kChar == _xx):
reserved = curChar
elif (kChar == _sa): # Sign placed above the base
signAbove = curChar
elif (kChar == _sp): # Sign placed after the base
signAfter = curChar
elif (kChar == _c1) or (kChar == _c2) or (kChar == _c3): # Consonant
if (coeng):
if (not coeng1):
coeng1 = COENG + curChar
else:
coeng2 = COENG + curChar
coeng = False
else:
base = curChar
elif (kChar == _rb): # Khmer sign robat u17CC
robat = curChar
elif (kChar == _cs): # Consonant-shifter
if (coeng1):
shifterAfterCoeng = True
shifter = curChar
elif (kChar == _dl): # Dependent vowel placed before the base
vowelBefore = curChar
elif (kChar == _db): # Dependent vowel placed below the base
vowelBelow = curChar
elif (kChar == _da): # Dependent vowel placed above the base
vowelAbove = curChar
elif (kChar == _dr): # Dependent vowel placed behind the base
vowelAfter = curChar
elif (kChar == _co): # Khmer combining mark COENG
coeng = True
elif (kChar == _va): # Khmer split vowel, see _da
vowelBefore = SRAE
vowelAbove = sraEcombining[curChar]
elif (kChar == _vr): # Khmer split vowel, see _dr
vowelBefore = SRAE
vowelAfter = sraEcombining[curChar]
cursor += 1
# end of while (a cluster has found)
# logic of vowel
# determine if right side vowel should be marked
if (coeng1 and vowelBelow):
vowelBelow = MARK + vowelBelow
elif ((base == LA or base == NYO) and vowelBelow):
vowelBelow = MARK + vowelBelow
elif (coeng1 and vowelBefore and vowelAfter):
vowelAfter = MARK + vowelAfter
# logic when cluster has coeng
# should coeng be located on left side
coengBefore = ''
if (coeng1 == CORO):
coengBefore = coeng1
coeng1 = ''
elif (coeng2 == CORO):
coengBefore = MARK + coeng2
coeng2 = ''
if (coeng1 or coeng2):
# NYO must change to other form when there is coeng
if (base == NYO):
base = MARK + base
# coeng NYO must be marked
if (coeng1 == CONYO):
coeng1 = MARK + coeng1
if (coeng1 and coeng2):
coeng2 = MARK + coeng2
# logic of shifter with base character
if (base and shifter):
# special case apply to BA only
if (vowelAbove) and (base == BA) and (shifter == TRIISAP):
vowelAbove = MARK + vowelAbove
elif (vowelAbove):
shifter = MARK + shifter
elif (signAbove == SAMYOKSANNYA) and (shifter == MUUSIKATOAN):
shifter = MARK + shifter
elif (signAbove and vowelAfter):
shifter = MARK + shifter
elif (signAbove):
signAbove = MARK + signAbove
# add another mark to shifter
if (coeng1) and (vowelAbove or signAbove):
shifter = MARK + shifter
if (base == LA or base == NYO):
shifter = MARK + shifter
# uncomplete coeng
if (coeng and not coeng1):
coeng1 = COENG
elif (coeng and not coeng2):
coeng2 = MARK + COENG
# render DOTCIRCLE for standalone sign or vowel
if (not base) and (vowelBefore or coengBefore or robat or shifter or coeng1 or coeng2 or vowelAfter or vowelBelow or vowelAbove or signAbove or signAfter):
base = DOTCIRCLE
# place of shifter
shifter1 = ''
shifter2 = ''
if (shifterAfterCoeng):
shifter2 = shifter
else:
shifter1 = shifter
specialCaseBA = False
if (base == BA) and ((vowelAfter == SRAAA) or (vowelAfter == SRAAU) or (vowelAfter == MARK + SRAAA) or (vowelAfter == MARK + SRAAU)):
# SRAAA or SRAAU will get a MARK if there is coeng, redefine to last char
vowelAfter = vowelAfter[-1]
specialCaseBA = True
if (coeng1) and (coeng1[-1] in [BA, YO, SA]):
specialCaseBA = False
# cluster formation
if (specialCaseBA):
cluster = vowelBefore + coengBefore + base + vowelAfter + robat + shifter1 + coeng1 + coeng2 + shifter2 + vowelBelow + vowelAbove + signAbove + signAfter
else:
cluster = vowelBefore + coengBefore + base + robat + shifter1 + coeng1 + coeng2 + shifter2 + vowelBelow + vowelAbove + vowelAfter + signAbove + signAfter
result += cluster + reserved
state = 0
# end of while
return result
class TestReordering(unittest.TestCase):
def testKhmerType(self):
# make sure the types are correct
self.assertEqual(getCharClass(unichr(0x177F)), 0)
self.assertEqual(getCharClass(unichr(0x1780)), _c1)
self.assertEqual(getCharClass(unichr(0x1790)), _c1)
self.assertEqual(getCharClass(unichr(0x17A0)), _c1)
self.assertEqual(getCharClass(unichr(0x17B0)), _c1)
self.assertEqual(getCharClass(unichr(0x17C0)), _vr)
self.assertEqual(getCharClass(unichr(0x17D0)), _sa)
self.assertEqual(getCharClass(unichr(0x17D4)), 0)
self.assertEqual(getCharClass(unichr(0x17ff)), 0)
def testReordering(self):
# low vowel under coeng go deeper
self.assertEqual(reorder(u'ខ្នុ'), u'ខ្ន' + MARK + u'ុ')
self.assertEqual(reorder(u'ត្រូ'), u'្រត' + MARK + u'ូ')
self.assertEqual(reorder(u'ព្យួ'), u'ព្យ' + MARK + u'ួ')
# vowel under LA or NYO go deeper
self.assertEqual(reorder(u'ឡូ'), u'ឡ' + MARK + u'ូ')
self.assertEqual(reorder(u'ញួ'), u'ញ' + MARK + u'ួ')
# mark vowel after when there is coeng
self.assertEqual(reorder(u'ក្បៀ'), u'េក្ប' + MARK + u'ៀ')
# coeng RO must on left side
self.assertEqual(reorder(u'ក្រ'), u'្រក')
self.assertEqual(reorder(u'ស្ត្រ'), MARK + u'្រស្ត')
# mark NYO when there is coeng
self.assertEqual(reorder(u'ញ្ជ'), MARK + u'ញ្ជ')
# coeng NYO under NYO is marked
self.assertEqual(reorder(u'ញ្ញ'), MARK + u'ញ' + MARK + u'្ញ')
# coeng NYO under other is normal
self.assertEqual(reorder(u'ជ្ញ'), u'ជ្ញ')
# coeng1 and coeng2, mark coeng2
self.assertEqual(reorder(u'ក្ស្ម'), u'ក្ស' + MARK + u'្ម')
# PA has no modification
self.assertEqual(reorder(u'ប៉'), u'ប៉')
# special case BA TRISSAP, mark vowel above
self.assertEqual(reorder(u'ប៊ី'), u'ប៊' + MARK + u'ី')
# base and shifter and vowel above, mark shifter
self.assertEqual(reorder(u'ប៉ី'), u'ប' + MARK + u'៉ី')
self.assertEqual(reorder(u'ស៊ី'), u'ស' + MARK + u'៊ី')
# base and muusikatoan and samyok-sannya, mark shifter
self.assertEqual(reorder(u'នំប៉័ង'), u'នំប' + MARK + u'៉' + u'័ង')
# shifter and sign above and vowel after, mark shifter
self.assertEqual(reorder(u'ស៊ាំ'), u'ស' + MARK + u'៊' + u'ាំ')
# shifter and sign above, mark sign
self.assertEqual(reorder(u'អ៊ំ'), u'អ៊' + MARK + u'ំ')
# double mark shifter when there is ceong and sign or vowel above
self.assertEqual(reorder(u'ប្ប៉័ង'), u'ប្ប' + MARK + MARK + u'៉' + u'័ង')
# uncomplete coeng is still keep
self.assertEqual(reorder(u'ក្'), u'ក្')
self.assertEqual(reorder(u'ក្ក្'), u'ក្ក' + MARK + u'្')
# render standalone vowel or sign with DOTCIRCLE
self.assertEqual(reorder(u'ា'), DOTCIRCLE + u'ា')
self.assertEqual(reorder(u'េ'), u'េ' + DOTCIRCLE)
self.assertEqual(reorder(u'ើ'), u'េ' + DOTCIRCLE + u'ី')
self.assertEqual(reorder(u'ំ'), DOTCIRCLE + u'ំ')
self.assertEqual(reorder(u'ោះ'), u'េ' + DOTCIRCLE + u'ា' + DOTCIRCLE + u'ះ')
# shifter is after ceong
self.assertEqual(reorder(u'ន្ស៊ី'), u'ន្ស' + MARK + MARK + u'៊ី')
# special case BA and sra A, get alway near to each other
self.assertEqual(reorder(u'ប្រា'), u'្របា')
self.assertEqual(reorder(u'ប្ដា'), u'បា្ដ')
self.assertEqual(reorder(u'ប៉ា'), u'បា៉')
self.assertEqual(reorder(u'ប្រៅ'), u'េ្របៅ')
self.assertEqual(reorder(u'ប្ដៅ'), u'េបៅ្ដ')
self.assertEqual(reorder(u'ប៉ៅ'), u'េបៅ៉')
# except there is coeng between them
self.assertEqual(reorder(u'ប្បា'), u'ប្បា')
# other test of prevention
# simple rendering
self.assertEqual(reorder(u'គេ'), u'េគ')
self.assertEqual(reorder(u'គោ'), u'េគា')
self.assertEqual(reorder(u'កៅ'), u'េកៅ')
self.assertEqual(reorder(u'លើ'), u'េលី')
self.assertEqual(reorder(u'បៀ'), u'េបៀ')
self.assertEqual(reorder(u'តឿ'), u'េតឿ')
self.assertEqual(reorder(u'កាំ'), u'កាំ')
# reorder of more than one cluster
self.assertEqual(reorder(u'កាប់គោ'), u'កាប់េគា')
self.assertEqual(reorder(u'ខាងលើ'), u'ខាងេលី')
self.assertEqual(reorder(u'ចំពោះ'), u'ចំេពាះ')
# mix with english text
self.assertEqual(reorder(u'កកុះwelcomeកុម្ភៈ'), u'កកុះwelcomeកុម្ភៈ')
# two shifter or 3 vowel or 4 sign
self.assertEqual(reorder(u'៊៊'), DOTCIRCLE + u'៊' + DOTCIRCLE + u'៊')
self.assertEqual(reorder(u'ាិី'), DOTCIRCLE + u'ា' + DOTCIRCLE + u'ិ' + DOTCIRCLE + u'ី')
self.assertEqual(reorder(u'ំះ័'), DOTCIRCLE + u'ំ' + DOTCIRCLE + u'ះ' + DOTCIRCLE + u'័')
# muusikatoan not convert when vowel is not high
self.assertEqual(reorder(u'ម៉្ងៃ'), u'ៃម៉្ង')
# two coengs with vowel that place on left and right (some bigger than normal)
self.assertEqual(reorder(u'កញ្ច្រៀវ'), u'កេ' + MARK + u'្រ' + MARK + u'ញ្ច' + MARK + u'ៀវ')
self.assertEqual(reorder(u'កញ្ច្រោង'), u'កេ' + MARK + u'្រ' + MARK + u'ញ្ច' + MARK + u'ាង')
# vowel which under coeng go one step deeper
self.assertEqual(reorder(u'ប្ដូ'), u'ប្ដ' + MARK + u'ូ')
# don't break the sign
self.assertEqual(reorder(u'ចុះ'), u'ចុះ')
self.assertEqual(reorder(u'នុ៎ះ'), u'នុ៎ះ')
# change sign OM, not shifter
self.assertEqual(reorder(u'អ៊ុំ'), u'អ៊ុ' + MARK + u'ំ' )
# this is two cluster
self.assertEqual(reorder(u'ាក'), DOTCIRCLE + u'ាក')
if __name__ == '__main__':
unittest.main()
|