Ra = 16;
CM = 17;
Symbol= 18;
+CS = 19;
c = (C | Ra); # is_consonant
n = ((ZWNJ?.RS)? (N.N?)?); # is_consonant_modifier
halant_or_matra_group = (final_halant_group | (h.ZWJ)? matra_group{0,4}) (Coeng (cn|V))?;
-consonant_syllable = Repha? (cn.halant_group){0,4} cn medial_group halant_or_matra_group syllable_tail;
+consonant_syllable = (Repha|CS)? (cn.halant_group){0,4} cn medial_group halant_or_matra_group syllable_tail;
vowel_syllable = reph? V.n? (ZWJ | (halant_group.cn){0,4} medial_group halant_or_matra_group syllable_tail);
-standalone_cluster = (Repha? PLACEHOLDER | reph? DOTTEDCIRCLE).n? (halant_group.cn){0,4} medial_group halant_or_matra_group syllable_tail;
+standalone_cluster = ((Repha|CS)? PLACEHOLDER | reph? DOTTEDCIRCLE).n? (halant_group.cn){0,4} medial_group halant_or_matra_group syllable_tail;
symbol_cluster = symbol syllable_tail;
broken_cluster = reph? n? (halant_group.cn){0,4} medial_group halant_or_matra_group syllable_tail;
other = any;
OT_Repha = 15, /* Atomically-encoded logical or visual repha. */
OT_Ra = 16,
OT_CM = 17, /* Consonant-Medial. */
- OT_Symbol = 18 /* Avagraha, etc that take marks (SM,A,VD). */
+ OT_Symbol = 18, /* Avagraha, etc that take marks (SM,A,VD). */
+ OT_CS = 19
};
#define MEDIAL_FLAGS (FLAG (OT_CM))
* We treat Vowels and placeholders as if they were consonants. This is safe because Vowels
* cannot happen in a consonant syllable. The plus side however is, we can call the
* consonant syllable logic from the vowel syllable function and get it all right! */
-#define CONSONANT_FLAGS (FLAG (OT_C) | FLAG (OT_Ra) | MEDIAL_FLAGS | FLAG (OT_V) | FLAG (OT_PLACEHOLDER) | FLAG (OT_DOTTEDCIRCLE))
+#define CONSONANT_FLAGS (FLAG (OT_C) | FLAG (OT_CS) | FLAG (OT_Ra) | MEDIAL_FLAGS | FLAG (OT_V) | FLAG (OT_PLACEHOLDER) | FLAG (OT_DOTTEDCIRCLE))
#define JOINER_FLAGS (FLAG (OT_ZWJ) | FLAG (OT_ZWNJ))
#define HALANT_OR_COENG_FLAGS (FLAG (OT_H) | FLAG (OT_Coeng))
INDIC_SYLLABIC_CATEGORY_CONSONANT_PREFIXED = OT_X, /* Don't care. */
INDIC_SYLLABIC_CATEGORY_CONSONANT_SUBJOINED = OT_CM,
INDIC_SYLLABIC_CATEGORY_CONSONANT_SUCCEEDING_REPHA = OT_N,
- INDIC_SYLLABIC_CATEGORY_CONSONANT_WITH_STACKER = OT_C,
+ INDIC_SYLLABIC_CATEGORY_CONSONANT_WITH_STACKER = OT_CS,
INDIC_SYLLABIC_CATEGORY_GEMINATION_MARK = OT_SM,
INDIC_SYLLABIC_CATEGORY_INVISIBLE_STACKER = OT_Coeng,
INDIC_SYLLABIC_CATEGORY_JOINER = OT_ZWJ,
A = 10;
As = 18;
C = 1;
-D = 19;
+D = 32;
D0 = 20;
DB = 3;
GB = 11;
ZWNJ = 5;
Ra = 16;
P = 31;
+CS = 19;
j = ZWJ|ZWNJ; # Joiners
k = (Ra As H); # Kinzi
complex_syllable_tail = As* medial_group main_vowel_group post_vowel_group* pwo_tone_group* V* j?;
syllable_tail = (H | complex_syllable_tail);
-consonant_syllable = k? (c|IV|D|GB).VS? (H (c|IV).VS?)* syllable_tail;
+consonant_syllable = (k|CS)? (c|IV|D|GB).VS? (H (c|IV).VS?)* syllable_tail;
punctuation_cluster = P V;
broken_cluster = k? VS? syllable_tail;
other = any;
/* Note: This enum is duplicated in the -machine.rl source file.
* Not sure how to avoid duplication. */
enum myanmar_category_t {
- OT_As = 18, /* Asat */
- OT_D = 19, /* Digits except zero */
+ OT_As = 18, /* Asat */
OT_D0 = 20, /* Digit zero */
OT_DB = OT_N, /* Dot below */
OT_GB = OT_PLACEHOLDER,
OT_VPre = 28,
OT_VPst = 29,
OT_VS = 30, /* Variation selectors */
- OT_P = 31 /* Punctuation */
+ OT_P = 31, /* Punctuation */
+ OT_D = 32, /* Digits except zero */
};