Let hb_shape() guess script and direction...

- Rename HB_SCRIPT_INVALID_CODE to HB_SCRIPT_INVALID

- Add HB_DIRECTION_INVALID

- Make hb_script_get_horizontal_direction() public

- Make hb_shape() guess script from buffer text (first non-common
  non-inherit script) if buffer script is set to HB_SCRIPT_INVALID (this
  is NOT the default.)

- Make hb_shape() guess direction from buffer script if buffer direction
is set to HB_DIRECTION_INVALID (this is NOT the default.)

- Make hb-view.c set INVALID script and direction on the buffer.

The above changes are meant to make hb-view fairly useful for uni-script
uni-direction text.  The guessing behavior however is NOT the default of
hb_shape() and must be asked for explicitly.  This is intended, because
the guess is not a suitable substitute to full-fledged bidi and script
segmentation.  It's just a testing tool.

src/hb-common.h

@@ -78,7 +78,8 @@ typedef uint32_t hb_mask_t;
 typedef void (*hb_destroy_func_t) (void *user_data);
 
 typedef enum _hb_direction_t {
-  HB_DIRECTION_LTR,
+  HB_DIRECTION_INVALID = -1,
+  HB_DIRECTION_LTR = 0,
   HB_DIRECTION_RTL,
   HB_DIRECTION_TTB,
   HB_DIRECTION_BTT

src/hb-icu.c

@@ -118,7 +118,7 @@ hb_icu_get_script (hb_codepoint_t unicode)
 	U_ICU_VERSION_MAJOR_NUM > (major) || (U_ICU_VERSION_MAJOR_NUM == (major) && U_ICU_VERSION_MINOR_NUM >= (minor))
 #define MATCH_SCRIPT(C) case USCRIPT_##C: return HB_SCRIPT_##C
 #define MATCH_SCRIPT2(C1, C2) case USCRIPT_##C1: return HB_SCRIPT_##C2
-  MATCH_SCRIPT (INVALID_CODE);
+
   MATCH_SCRIPT (COMMON);             /* Zyyy */
   MATCH_SCRIPT (INHERITED);          /* Qaai */
   MATCH_SCRIPT (ARABIC);             /* Arab */

src/hb-ot-shape.cc

@@ -64,6 +64,7 @@ hb_ot_shape_collect_features (hb_ot_shape_plan_t       *plan,
       break;
     case HB_DIRECTION_TTB:
     case HB_DIRECTION_BTT:
+    case HB_DIRECTION_INVALID:
     default:
       break;
   }
@@ -170,7 +171,7 @@ hb_ensure_native_direction (hb_ot_shape_context_t *c)
 
   /* TODO vertical */
   if (HB_DIRECTION_IS_HORIZONTAL (direction) &&
-      direction != _hb_script_get_horizontal_direction (c->buffer->props.script))
+      direction != hb_script_get_horizontal_direction (c->buffer->props.script))
   {
     hb_buffer_reverse_clusters (c->buffer);
     c->buffer->props.direction = HB_DIRECTION_REVERSE (c->buffer->props.direction);

src/hb-shape.cc

@@ -39,8 +39,8 @@
 HB_BEGIN_DECLS
 
 
-void
-hb_shape (hb_font_t    *font,
+static void
+hb_shape_internal (hb_font_t    *font,
 		   hb_face_t    *face,
 		   hb_buffer_t  *buffer,
 		   hb_feature_t *features,
@@ -61,5 +61,45 @@ hb_shape (hb_font_t    *font,
   hb_ot_shape (font, face, buffer, features, num_features);
 }
 
+void
+hb_shape (hb_font_t    *font,
+	  hb_face_t    *face,
+	  hb_buffer_t  *buffer,
+	  hb_feature_t *features,
+	  unsigned int  num_features)
+{
+  hb_segment_properties_t orig_props;
+
+  orig_props = buffer->props;
+
+  /* If script is set to INVALID, guess from buffer contents */
+  if (buffer->props.script == HB_SCRIPT_INVALID) {
+    hb_unicode_get_script_func_t get_script = buffer->unicode->v.get_script;
+    unsigned int count = buffer->len;
+    for (unsigned int i = 0; i < count; i++) {
+      hb_script_t script = get_script (buffer->info[i].codepoint);
+      if (likely (script > HB_SCRIPT_INHERITED)) {
+        buffer->props.script = script;
+        break;
+      }
+    }
+  }
+
+  /* If direction is set to INVALID, guess from script */
+  if (buffer->props.direction == HB_DIRECTION_INVALID) {
+    buffer->props.direction = hb_script_get_horizontal_direction (buffer->props.script);
+  }
+
+  /* If language is not set, use default language from locale */
+  if (buffer->props.language == NULL) {
+    /* TODO get_default_for_script? using $LANGUAGE */
+    //buffer->props.language = hb_language_get_default ();
+  }
+
+  hb_shape_internal (font, face, buffer, features, num_features);
+
+  buffer->props = orig_props;
+}
+
 
 HB_END_DECLS

src/hb-unicode-private.h

@@ -55,10 +55,6 @@ struct _hb_unicode_funcs_t {
 extern HB_INTERNAL hb_unicode_funcs_t _hb_unicode_funcs_nil;
 
 
-HB_INTERNAL hb_direction_t
-_hb_script_get_horizontal_direction (hb_script_t script);
-
-
 HB_END_DECLS
 
 #endif /* HB_UNICODE_PRIVATE_H */

src/hb-unicode.c

@@ -352,7 +352,7 @@ const hb_direction_t horiz_dir[] =
 #undef RTL
 
 hb_direction_t
-_hb_script_get_horizontal_direction (hb_script_t script)
+hb_script_get_horizontal_direction (hb_script_t script)
 {
   if (unlikely ((unsigned int) script >= ARRAY_LENGTH (horiz_dir)))
     return HB_DIRECTION_LTR;

src/hb-unicode.h

@@ -70,7 +70,8 @@ typedef enum
 /* Unicode Script property */
 typedef enum
 {                               /* ISO 15924 code */
-  HB_SCRIPT_INVALID_CODE = -1,
+  HB_SCRIPT_INVALID = -1,
+
   HB_SCRIPT_COMMON       = 0,   /* Zyyy */
   HB_SCRIPT_INHERITED,          /* Qaai */
   HB_SCRIPT_ARABIC,             /* Arab */
@@ -289,6 +290,11 @@ hb_unicode_get_eastasian_width (hb_unicode_funcs_t *ufuncs,
 				hb_codepoint_t unicode);
 
 
+/* Misc functions */
+
+hb_direction_t
+hb_script_get_horizontal_direction (hb_script_t script);
+
 HB_END_DECLS
 
 #endif /* HB_UNICODE_H */

src/hb-view.c

@@ -184,8 +184,8 @@ _hb_cr_text_glyphs (cairo_t *cr,
   hb_buffer_set_unicode_funcs (hb_buffer, hb_glib_get_unicode_funcs ());
 
   hb_buffer_add_utf8 (hb_buffer, text, len, 0, len);
-  /* hb_buffer_set_script (hb_buffer, HB_SCRIPT_LATIN); */
-  /* hb_buffer_set_direction (hb_buffer, HB_DIRECTION_LTR); */
+  hb_buffer_set_script (hb_buffer, HB_SCRIPT_INVALID);
+  hb_buffer_set_direction (hb_buffer, HB_DIRECTION_INVALID);
   hb_buffer_set_language (hb_buffer, hb_language_from_string (language));
 
   hb_shape (hb_font, hb_face, hb_buffer, NULL, 0);