From 34c215036f5fcdc7599b1ab0591b56dbb3811902 Mon Sep 17 00:00:00 2001
From: Behdad Esfahbod <behdad@behdad.org>
Date: Mon, 23 Jul 2012 23:51:29 -0400
Subject: [PATCH] [Indic] Improve Sinhala base algorithm and reph positioning

Sinhala does not have half forms.  And most (all?) consonants can be
base, except when preceded by ZWJ, which would request a subjoined form.
Hence switch the base algorithm to categorize with Khmer, start search
at start, and stop at a ZWJ.

Also, mark all pos=base consonants after base to be subjoined.  Mark
base itself to have pos=base.

Finally, adjust Sinhala's reph position to after-main.

Brings down Sinhala failures from 455 to 328 (0.120656%).
---
 src/hb-ot-shape-complex-indic.cc                       | 18 +++++++++++++++++-
 .../shaper-indic/indic/script-sinhala/misc/misc.txt    |  1 +
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/src/hb-ot-shape-complex-indic.cc b/src/hb-ot-shape-complex-indic.cc
index e7b70c8..83d7ab5 100644
--- a/src/hb-ot-shape-complex-indic.cc
+++ b/src/hb-ot-shape-complex-indic.cc
@@ -501,6 +501,7 @@ initial_reordering_consonant_syllable (const hb_ot_map_t *map, hb_buffer_t *buff
 
     switch ((hb_tag_t) buffer->props.script)
     {
+      case HB_SCRIPT_SINHALA:
       case HB_SCRIPT_KHMER:
 	base_pos = BASE_FIRST;
 	break;
@@ -557,6 +558,19 @@ initial_reordering_consonant_syllable (const hb_ot_map_t *map, hb_buffer_t *buff
 
       if (!has_reph)
 	base = limit;
+
+      /* Find the last base consonant that is not blocked by ZWJ.  If there is
+       * a ZWJ before a bse consonant, that would request a subjoined form. */
+      for (unsigned int i = limit; i < end; i++)
+        if (is_consonant (info[i]) && info[i].indic_position() == POS_BASE_C)
+	  base = i;
+	else if (info[i].indic_category() == OT_ZWJ)
+	  break;
+
+      /* Mark all subsequent consonants as below. */
+      for (unsigned int i = base + 1; i < end; i++)
+        if (is_consonant (info[i]) && info[i].indic_position() == POS_BASE_C)
+	  info[i].indic_position() = POS_BELOW_C;
     }
 
     if (base < start)
@@ -570,6 +584,8 @@ initial_reordering_consonant_syllable (const hb_ot_map_t *map, hb_buffer_t *buff
       has_reph = false;
     }
   }
+  if (base < end)
+    info[base].indic_position() = POS_BASE_C;
 
 
   /* 2. Decompose and reorder Matras:
@@ -931,6 +947,7 @@ final_reordering_syllable (hb_buffer_t *buffer,
      {
        case HB_SCRIPT_MALAYALAM:
        case HB_SCRIPT_ORIYA:
+       case HB_SCRIPT_SINHALA:
 	 reph_pos = REPH_AFTER_MAIN;
 	 break;
 
@@ -945,7 +962,6 @@ final_reordering_syllable (hb_buffer_t *buffer,
        default:
        case HB_SCRIPT_DEVANAGARI:
        case HB_SCRIPT_GUJARATI:
-       case HB_SCRIPT_SINHALA:
 	 reph_pos = REPH_BEFORE_POSTSCRIPT;
 	 break;
 
diff --git a/test/shaping/texts/in-tree/shaper-indic/indic/script-sinhala/misc/misc.txt b/test/shaping/texts/in-tree/shaper-indic/indic/script-sinhala/misc/misc.txt
index 03a0fae..c4f6b6b 100644
--- a/test/shaping/texts/in-tree/shaper-indic/indic/script-sinhala/misc/misc.txt
+++ b/test/shaping/texts/in-tree/shaper-indic/indic/script-sinhala/misc/misc.txt
@@ -30,3 +30,4 @@
 ශී‍්‍ර
 ස්ට්‍රේ
 ග්‍යෙ
+ර්‍ය්‍ය
-- 
2.7.4