Merge branch 'log-attr-things' into 'main'

break-thai: Fix up word break handling

See merge request GNOME/pango!434

6 files changed, 153 insertions, 76 deletions

diff --git a/docs/pango_rendering.md b/docs/pango_rendering.md
index 2745c0c0..4bec5176 100644
--- a/docs/pango_rendering.md
+++ b/docs/pango_rendering.md
@@ -15,18 +15,19 @@ various stages of this pipeline and the APIs that implement them.
 
 Itemization
 : breaks a piece of text into segments with consistent direction and shaping
-  properies. Among other things, this determines which font to use for each
+  properties. Among other things, this determines which font to use for each
   character. Use [func@Pango.itemize] or [func@Pango.itemize_with_base_dir]
   to itemize text.
 
 Shaping
 : converts characters into glyphs. Use [func@Pango.shape],
-  [func@Pango.shape_full] or [func@Pango.shape_with_flags] to shape text.
+  [func@Pango.shape_full] or [func@Pango.shape_item] to shape text.
 
 Line Breaking
 : determines where line breaks should be inserted into a sequence of glyphs.
-  The function [func@Pango.break] determines possible line breaks. The actual
-  line breaking is done by [class@Pango.Layout].
+  The functions [func@Pango.default_break], [func@Pango.tailor_break] and
+  [func@Pango.attr_break] determine possible line breaks. The actual line
+  breaking is done by [class@Pango.Layout].
 
 Justification
 : adjusts inter-word spacing to form lines of even length. This is done by
diff --git a/pango/break-thai.c b/pango/break-thai.c
index 871c0869..02a18cc5 100644
--- a/pango/break-thai.c
+++ b/pango/break-thai.c
@@ -92,15 +92,27 @@ break_thai (const char          *text,
   G_UNLOCK (thai_brk);
 
   for (cnt = 0; cnt < len; cnt++)
-    if (attrs[brk_pnts[cnt]].is_char_break)
     {
-      /* Only allow additional line breaks if line-breaking is NOT
-       * prohibited. (The alternative would be to set is_char_break to
-       * TRUE as well.  NOT setting it will break invariants that any
-       * line break opportunity is also a char break opportunity. */
-      attrs[brk_pnts[cnt]].is_line_break = TRUE;
-      attrs[brk_pnts[cnt]].is_word_start = TRUE;
-      attrs[brk_pnts[cnt]].is_word_end = TRUE;
+      if (!attrs[brk_pnts[cnt]].is_line_break)
+        {
+          /* Insert line breaks where there wasn't one.
+           * Satisfy invariants by marking it as char break too.
+           */
+          attrs[brk_pnts[cnt]].is_char_break = TRUE;
+          attrs[brk_pnts[cnt]].is_line_break = TRUE;
+        }
+      if (!(attrs[brk_pnts[cnt]].is_word_start ||
+            attrs[brk_pnts[cnt]].is_word_end))
+        {
+          /* If we find a break in the middle of a sequence
+           * of characters, end and start a word. We must
+           * be careful only to do that if default_break
+           * did not already find a word start or end,
+           * otherwise we mess up the sequence.
+           */
+          attrs[brk_pnts[cnt]].is_word_start = TRUE;
+          attrs[brk_pnts[cnt]].is_word_end = TRUE;
+        }
     }
 
   if (brk_pnts != brk_stack)
diff --git a/pango/break.c b/pango/break.c
index b2586da2..c55d5f22 100644
--- a/pango/break.c
+++ b/pango/break.c
@@ -139,29 +139,12 @@ typedef enum
   WordNumbers
 } WordType;
 
-
-/**
- * pango_default_break:
- * @text: text to break. Must be valid UTF-8
- * @length: length of text in bytes (may be -1 if @text is nul-terminated)
- * @analysis: (nullable): a `PangoAnalysis` structure for the @text
- * @attrs: logical attributes to fill in
- * @attrs_len: size of the array passed as @attrs
- *
- * This is the default break algorithm.
- *
- * It applies Unicode rules without language-specific
- * tailoring, therefore the @analyis argument is unused
- * and can be %NULL.
- *
- * See [func@Pango.tailor_break] for language-specific breaks.
- */
-void
-pango_default_break (const gchar   *text,
-		     gint           length,
-		     PangoAnalysis *analysis G_GNUC_UNUSED,
-		     PangoLogAttr  *attrs,
-		     int            attrs_len G_GNUC_UNUSED)
+static void
+default_break (const char    *text,
+               int            length,
+               PangoAnalysis *analysis G_GNUC_UNUSED,
+               PangoLogAttr  *attrs,
+               int            attrs_len G_GNUC_UNUSED)
 {
   /* The rationale for all this is in section 5.15 of the Unicode 3.0 book,
    * the line breaking stuff is also in TR14 on unicode.org
@@ -1639,7 +1622,7 @@ break_script (const char          *item_text,
 }
 
 /* }}} */
-/* {{{ Attribute-based tailoring */
+/* {{{ Attribute-based customization */
 
 static gboolean
 break_attrs (const char   *text,
@@ -1707,11 +1690,11 @@ break_attrs (const char   *text,
 
 static gboolean
 tailor_break (const char    *text,
-	      int            length,
-	      PangoAnalysis *analysis,
+              int            length,
+              PangoAnalysis *analysis,
               int            item_offset,
-	      PangoLogAttr  *attrs,
-	      int            attrs_len)
+              PangoLogAttr  *attrs,
+              int            attrs_len)
 {
   gboolean res;
 
@@ -1732,6 +1715,34 @@ tailor_break (const char    *text,
 /* {{{ Public API */
 
 /**
+ * pango_default_break:
+ * @text: text to break. Must be valid UTF-8
+ * @length: length of text in bytes (may be -1 if @text is nul-terminated)
+ * @analysis: (nullable): a `PangoAnalysis` structure for the @text
+ * @attrs: logical attributes to fill in
+ * @attrs_len: size of the array passed as @attrs
+ *
+ * This is the default break algorithm.
+ *
+ * It applies Unicode rules without language-specific
+ * tailoring, therefore the @analyis argument is unused
+ * and can be %NULL.
+ *
+ * See [func@Pango.tailor_break] for language-specific breaks.
+ *
+ * See [func@Pango.attr_break] for attribute-based customization.
+ */
+void
+pango_default_break (const char    *text,
+                     int            length,
+                     PangoAnalysis *analysis G_GNUC_UNUSED,
+                     PangoLogAttr  *attrs,
+                     int            attrs_len G_GNUC_UNUSED)
+{
+  default_break (text, length, analysis, attrs, attrs_len);
+}
+
+/**
  * pango_break:
  * @text: the text to process. Must be valid UTF-8
  * @length: length of @text in bytes (may be -1 if @text is nul-terminated)
@@ -1745,11 +1756,11 @@ tailor_break (const char    *text,
  * For most purposes you may want to use
  * [func@Pango.get_log_attrs].
  *
- * Deprecated: 1.44: Use [func@Pango.default_break] and
- *   [func@Pango.tailor_break]
+ * Deprecated: 1.44: Use [func@Pango.default_break],
+ *   [func@Pango.tailor_break] and func@Pango.attr_break].
  */
 void
-pango_break (const gchar   *text,
+pango_break (const char    *text,
              gint           length,
              PangoAnalysis *analysis,
              PangoLogAttr  *attrs,
@@ -1758,7 +1769,7 @@ pango_break (const gchar   *text,
   g_return_if_fail (analysis != NULL);
   g_return_if_fail (attrs != NULL);
 
-  pango_default_break (text, length, analysis, attrs, attrs_len);
+  default_break (text, length, analysis, attrs, attrs_len);
   tailor_break (text, length, analysis, -1, attrs, attrs_len);
 }
 
@@ -1769,12 +1780,11 @@ pango_break (const gchar   *text,
  * @analysis: `PangoAnalysis` for @text
  * @offset: Byte offset of @text from the beginning of the
  *   paragraph, or -1 to ignore attributes from @analysis
- * @log_attrs: (array length=log_attrs_len): array with one `PangoLogAttr`
+ * @attrs: (array length=attrs_len): array with one `PangoLogAttr`
  *   per character in @text, plus one extra, to be filled in
- * @log_attrs_len: length of @log_attrs array
+ * @attrs_len: length of @attrs array
  *
- * Apply language-specific tailoring to the breaks
- * in @log_attrs.
+ * Apply language-specific tailoring to the breaks in @attrs.
  *
  * The line breaks are assumed to have been produced
  * by [func@Pango.default_break].
@@ -1782,6 +1792,10 @@ pango_break (const gchar   *text,
  * If @offset is not -1, it is used to apply attributes
  * from @analysis that are relevant to line breaking.
  *
+ * Note that it is better to pass -1 for @offset and
+ * use [func@Pango.attr_break] to apply attributes to
+ * the whole paragraph.
+ *
  * Since: 1.44
  */
 void
@@ -1789,13 +1803,13 @@ pango_tailor_break (const char    *text,
                     int            length,
                     PangoAnalysis *analysis,
                     int            offset,
-                    PangoLogAttr  *log_attrs,
-                    int            log_attrs_len)
+                    PangoLogAttr  *attrs,
+                    int            attrs_len)
 {
-  PangoLogAttr *start = log_attrs;
+  PangoLogAttr *start = attrs;
   PangoLogAttr attr_before = *start;
 
-  if (tailor_break (text, length, analysis, offset, log_attrs, log_attrs_len))
+  if (tailor_break (text, length, analysis, offset, attrs, attrs_len))
     {
       /* if tailored, we enforce some of the attrs from before
        * tailoring at the boundary
@@ -1810,18 +1824,50 @@ pango_tailor_break (const char    *text,
 }
 
 /**
+ * pango_attr_break:
+ * @text: text to break. Must be valid UTF-8
+ * @length: length of text in bytes (may be -1 if @text is nul-terminated)
+ * @attr_list: `PangoAttrList` to apply
+ * @offset: Byte offset of @text from the beginning of the paragraph
+ * @attrs: (array length=attrs_len): array with one `PangoLogAttr`
+ *   per character in @text, plus one extra, to be filled in
+ * @attrs_len: length of @attrs array
+ *
+ * Apply customization from attributes to the breaks in @attrs.
+ *
+ * The line breaks are assumed to have been produced
+ * by [func@Pango.default_break] and [func@Pango.tailor_break].
+ *
+ * Since: 1.50
+ */
+void
+pango_attr_break (const char    *text,
+                  int            length,
+                  PangoAttrList *attr_list,
+                  int            offset,
+                  PangoLogAttr  *attrs,
+                  int            attrs_len)
+{
+  GSList *attributes;
+
+  attributes = pango_attr_list_get_attributes (attr_list);
+  break_attrs (text, length, attributes, offset, attrs, attrs_len);
+  g_slist_free_full (attributes, (GDestroyNotify)pango_attribute_destroy);
+}
+
+/**
  * pango_get_log_attrs:
  * @text: text to process. Must be valid UTF-8
  * @length: length in bytes of @text
  * @level: embedding level, or -1 if unknown
  * @language: language tag
- * @log_attrs: (array length=attrs_len): array with one `PangoLogAttr`
+ * @attrs: (array length=attrs_len): array with one `PangoLogAttr`
  *   per character in @text, plus one extra, to be filled in
- * @attrs_len: length of @log_attrs array
+ * @attrs_len: length of @attrs array
  *
  * Computes a `PangoLogAttr` for each character in @text.
  *
- * The @log_attrs array must have one `PangoLogAttr` for
+ * The @attrs array must have one `PangoLogAttr` for
  * each position in @text; if @text contains N characters,
  * it has N+1 positions, including the last position at the
  * end of the text. @text should be an entire paragraph;
@@ -1834,7 +1880,7 @@ pango_get_log_attrs (const char    *text,
                      int            length,
                      int            level,
                      PangoLanguage *language,
-                     PangoLogAttr  *log_attrs,
+                     PangoLogAttr  *attrs,
                      int            attrs_len)
 {
   int chars_broken;
@@ -1842,12 +1888,12 @@ pango_get_log_attrs (const char    *text,
   PangoScriptIter iter;
 
   g_return_if_fail (length == 0 || text != NULL);
-  g_return_if_fail (log_attrs != NULL);
+  g_return_if_fail (attrs != NULL);
 
   analysis.level = level;
   analysis.language = language;
 
-  pango_default_break (text, length, &analysis, log_attrs, attrs_len);
+  pango_default_break (text, length, &analysis, attrs, attrs_len);
 
   chars_broken = 0;
 
@@ -1867,7 +1913,7 @@ pango_get_log_attrs (const char    *text,
                           run_end - run_start,
                           &analysis,
                           -1,
-                          log_attrs + chars_broken,
+                          attrs + chars_broken,
                           chars_in_range + 1);
 
       chars_broken += chars_in_range;
@@ -1881,4 +1927,6 @@ pango_get_log_attrs (const char    *text,
                attrs_len);
 }
 
-/* }}} */
+ /* }}} */
+
+/* vim:set foldmethod=marker expandtab: */
diff --git a/pango/pango-break.h b/pango/pango-break.h
index 81526e9a..a8e6c5b9 100644
--- a/pango/pango-break.h
+++ b/pango/pango-break.h
@@ -105,7 +105,7 @@ void                    pango_get_log_attrs     (const char    *text,
                                                  int            length,
                                                  int            level,
                                                  PangoLanguage *language,
-                                                 PangoLogAttr  *log_attrs,
+                                                 PangoLogAttr  *attrs,
                                                  int            attrs_len);
 
 PANGO_AVAILABLE_IN_ALL
@@ -120,8 +120,16 @@ void                    pango_tailor_break      (const char    *text,
                                                  int            length,
                                                  PangoAnalysis *analysis,
                                                  int            offset,
-                                                 PangoLogAttr  *log_attrs,
-                                                 int            log_attrs_len);
+                                                 PangoLogAttr  *attrs,
+                                                 int            attrs_len);
+
+PANGO_AVAILABLE_IN_1_50
+void                    pango_attr_break        (const char    *text,
+                                                 int            length,
+                                                 PangoAttrList *attr_list,
+                                                 int            offset,
+                                                 PangoLogAttr  *attrs,
+                                                 int            attrs_len);
 
 G_END_DECLS
 
diff --git a/pango/pango-layout.c b/pango/pango-layout.c
index f78d7daf..b6e0c217 100644
--- a/pango/pango-layout.c
+++ b/pango/pango-layout.c
@@ -4214,12 +4214,13 @@ process_line (PangoLayout    *layout,
 }
 
 static void
-get_items_log_attrs (const char   *text,
-                     int           start,
-                     int           length,
-                     GList        *items,
-                     PangoLogAttr *log_attrs,
-                     int           log_attrs_len)
+get_items_log_attrs (const char    *text,
+                     int            start,
+                     int            length,
+                     GList         *items,
+                     PangoAttrList *attrs,
+                     PangoLogAttr  *log_attrs,
+                     int            log_attrs_len)
 {
   int offset = 0;
   GList *l;
@@ -4235,12 +4236,18 @@ get_items_log_attrs (const char   *text,
       pango_tailor_break (text + item->offset,
                           item->length,
                           &item->analysis,
-                          item->offset,
+                          -1,
                           log_attrs + offset,
                           item->num_chars + 1);
 
       offset += item->num_chars;
     }
+
+  if (attrs && items)
+    {
+      PangoItem *item = items->data;
+      pango_attr_break (text + start, length, attrs, item->offset, log_attrs, log_attrs_len);
+    }
 }
 
 static PangoAttrList *
@@ -4517,6 +4524,7 @@ pango_layout_check_lines (PangoLayout *layout)
                              start - layout->text,
                              delimiter_index + delim_len,
                              state.items,
+                             shape_attrs,
                              layout->log_attrs + start_offset,
                              layout->n_chars + 1 - start_offset);
 
diff --git a/tests/breaks/four.expected b/tests/breaks/four.expected
index ce58e10b..2f29d778 100644
--- a/tests/breaks/four.expected
+++ b/tests/breaks/four.expected
@@ -1,6 +1,6 @@
-Text:         ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ไ⁩ ⁦ท⁩ ⁦ย⁩  [ ]   ⁦ห⁩ ⁦ร⁩⁦ื⁩ ⁦อ⁩  [ ]   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ไ⁩ ⁦ท⁩ ⁦ย⁩   ⁦ก⁩ ⁦ล⁩ ⁦า⁩ ⁦ง⁩  [ ]   ⁦เ⁩ ⁦ป⁩⁦็⁩ ⁦น⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ร⁩ ⁦า⁩ ⁦ช⁩ ⁦ก⁩ ⁦า⁩ ⁦ร⁩   ⁦แ⁩ ⁦ล⁩ ⁦ะ⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ป⁩ ⁦ร⁩ ⁦ะ⁩ ⁦จ⁩ ⁦ำ⁩   ⁦ช⁩ ⁦า⁩ ⁦ต⁩⁦ิ⁩   ⁦ข⁩ ⁦อ⁩ ⁦ง⁩   ⁦ป⁩ ⁦ร⁩ ⁦ะ⁩ ⁦เ⁩ ⁦ท⁩ ⁦ศ⁩   ⁦ไ⁩ ⁦ท⁩ ⁦ย⁩  [ ]   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ไ⁩ ⁦ท⁩ ⁦ย⁩   ⁦เ⁩ ⁦ป⁩⁦็⁩ ⁦น⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ใ⁩ ⁦น⁩   ⁦ก⁩ ⁦ล⁩⁦ุ⁩⁦่⁩ ⁦ม⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ไ⁩ ⁦ท⁩   ⁦ซ⁩⁦ึ⁩⁦่⁩ ⁦ง⁩   ⁦เ⁩ ⁦ป⁩⁦็⁩ ⁦น⁩   ⁦ก⁩ ⁦ล⁩⁦ุ⁩⁦่⁩ ⁦ม⁩   ⁦ย⁩⁦่⁩ ⁦อ⁩ ⁦ย⁩   ⁦ข⁩ ⁦อ⁩ ⁦ง⁩   ⁦ต⁩ ⁦ร⁩ ⁦ะ⁩ ⁦ก⁩⁦ู⁩ ⁦ล⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ข⁩ ⁦ร⁩⁦้⁩ ⁦า⁩  [ ]   ⁦ไ⁩ ⁦ท⁩  [ ]   ⁦ส⁩⁦ั⁩ ⁦น⁩ ⁦น⁩⁦ิ⁩ ⁦ษ⁩ ⁦ฐ⁩ ⁦า⁩ ⁦น⁩   ⁦ว⁩⁦่⁩ ⁦า⁩  [ ]   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ใ⁩ ⁦น⁩   ⁦ต⁩ ⁦ร⁩ ⁦ะ⁩ ⁦ก⁩⁦ู⁩ ⁦ล⁩   ⁦น⁩⁦ี⁩⁦้⁩   ⁦ม⁩⁦ี⁩   ⁦ถ⁩⁦ิ⁩⁦่⁩ ⁦น⁩   ⁦ก⁩ ⁦ำ⁩ ⁦เ⁩ ⁦น⁩⁦ิ⁩ ⁦ด⁩   ⁦จ⁩ ⁦า⁩ ⁦ก⁩   ⁦ท⁩ ⁦า⁩ ⁦ง⁩   ⁦ต⁩ ⁦อ⁩ ⁦น⁩   ⁦ใ⁩ ⁦ต⁩⁦้⁩   ⁦ข⁩ ⁦อ⁩ ⁦ง⁩   ⁦ป⁩ ⁦ร⁩ ⁦ะ⁩ ⁦เ⁩ ⁦ท⁩ ⁦ศ⁩   ⁦จ⁩⁦ี⁩ ⁦น⁩  [ ]   ⁦แ⁩ ⁦ล⁩ ⁦ะ⁩   ⁦น⁩⁦ั⁩ ⁦ก⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩ ⁦ศ⁩ ⁦า⁩ ⁦ส⁩ ⁦ต⁩ ⁦ร⁩⁦์⁩   ⁦บ⁩ ⁦า⁩ ⁦ง⁩   ⁦ส⁩⁦่⁩ ⁦ว⁩ ⁦น⁩   ⁦เ⁩ ⁦ส⁩ ⁦น⁩ ⁦อ⁩   ⁦ว⁩⁦่⁩ ⁦า⁩  [ ]   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ไ⁩ ⁦ท⁩ ⁦ย⁩   ⁦น⁩⁦่⁩ ⁦า⁩   ⁦จ⁩ ⁦ะ⁩   ⁦ม⁩⁦ี⁩   ⁦ค⁩ ⁦ว⁩ ⁦า⁩ ⁦ม⁩   ⁦เ⁩ ⁦ช⁩⁦ื⁩⁦่⁩ ⁦อ⁩ ⁦ม⁩   ⁦โ⁩ ⁦ย⁩ ⁦ง⁩   ⁦ก⁩⁦ั⁩ ⁦บ⁩   ⁦ต⁩ ⁦ร⁩ ⁦ะ⁩ ⁦ก⁩⁦ู⁩ ⁦ล⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦อ⁩ ⁦อ⁩   ⁦ส⁩ ⁦โ⁩ ⁦ต⁩ ⁦ร⁩  [ ]   ⁦เ⁩ ⁦อ⁩ ⁦เ⁩ ⁦ช⁩⁦ี⁩ ⁦ย⁩   ⁦ต⁩⁦ิ⁩ ⁦ก⁩  [ ]   ⁦ต⁩ ⁦ร⁩ ⁦ะ⁩ ⁦ก⁩⁦ู⁩ ⁦ล⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦อ⁩ ⁦อ⁩   ⁦ส⁩ ⁦โ⁩ ⁦ต⁩ ⁦ร⁩ ⁦น⁩⁦ี⁩ ⁦เ⁩ ⁦ซ⁩⁦ี⁩ ⁦ย⁩ ⁦น⁩  [ ]   ⁦แ⁩ ⁦ล⁩ ⁦ะ⁩   ⁦ต⁩ ⁦ร⁩ ⁦ะ⁩ ⁦ก⁩⁦ู⁩ ⁦ล⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦จ⁩⁦ี⁩ ⁦น⁩  [ ]   ⁦ท⁩⁦ิ⁩ ⁦เ⁩ ⁦บ⁩ ⁦ต⁩  [0x0a] 
-Breaks:     c  c c c lc  c c c    lc  c  c c    lc  c c c lc  c c lc  c c c c    lc  c  c lc  c c c lc  c c c c c lc  c c lc  c c c lc  c c c c lc  c c  lc  c c lc  c c c c c lc  c c c    lc  c c c lc  c c lc  c  c lc  c c c lc  c lc  c   c lc  c c c lc  c lc    c lc  c  c lc  c   c lc   c c lc  c c lc  c c c  c lc  c c c lc  c  c c    lc  c c    lc   c c  c c c c lc   c c    lc  c c c lc  c lc  c c c  c lc    lc   lc    c lc  c c c  c lc  c c lc  c c lc  c c lc  c  lc  c c lc  c c c c c lc   c c    lc  c c lc   c lc  c c c c c c c c  lc  c c lc   c c lc  c c c lc   c c    lc  c c c lc  c c lc   c lc  c lc   lc  c c c lc  c   c c lc  c c lc   c lc  c c c  c lc  c c c lc  c lc  c c c c    lc  c c c  c lc   c c    lc  c c c  c lc  c c c lc  c lc  c c c c  c c  c c c    lc  c c lc  c c c  c lc  c c c lc   c c    lc   c c c c       c
-Whitespace:                  x             x                                x                                                                                                          x                                                                                                                                                     x          x                             x                                                                                                                             x                                                                          x                                                                                                                    x                        x                                                       x                                          x               w       w
-Sentences:  bs                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  e       b
-Words:      bs b b b bse b b be   bse b  b be   bse b b b bse b b bse b b b be   bse b  b bse b b b bse b b b b b bse b b bse b b b bse b b b b bse b b  bse b b bse b b b b b bse b b be   bse b b b bse b b bse b  b bse b b b bse b bse b   b bse b b b bse b bse   b bse b  b bse b   b bse  b b bse b b bse b b b  b bse b b b bse b  b be   bse b be   bse  b b  b b b b bse  b be   bse b b b bse b bse b b b  b bse   bse  bse   b bse b b b  b bse b b bse b b bse b b bse b  bse b b bse b b b b b bse  b be   bse b b bse  b bse b b b b b b b b  bse b b bse  b b bse b b b bse  b be   bse b b b bse b b bse  b bse b bse  bse b b b bse b   b b bse b b bse  b bse b b b  b bse b b b bse b bse b b b be   bse b b b  b bse  b be   bse b b b  b bse b b b bse b bse b b b b  b b  b b be   bse b b bse b b b  b bse b b b bse  b be   bse  b b b be      b
-Graphemes:  b  b b b b   b b b    b   b  b b    b   b b b b   b b b   b b b b    b   b  b b   b b b b   b b b b b b   b b b   b b b b   b b b b b   b b  b   b b b   b b b b b b   b b b    b   b b b b   b b b   b  b b   b b b b   b b   b   b b   b b b b   b b     b b   b  b b   b   b b    b b b   b b b   b b b  b b   b b b b   b  b b    b   b b    b    b b  b b b b b    b b    b   b b b b   b b   b b b  b b     b    b     b b   b b b  b b   b b b   b b b   b b b   b  b   b b b   b b b b b b    b b    b   b b b    b b   b b b b b b b b  b   b b b    b b b   b b b b    b b    b   b b b b   b b b    b b   b b    b   b b b b   b   b b b   b b b    b b   b b b  b b   b b b b   b b   b b b b    b   b b b  b b    b b    b   b b b  b b   b b b b   b b   b b b b  b b  b b b    b   b b b   b b b  b b   b b b b    b b    b    b b b b       b
+Text:         ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ไ⁩ ⁦ท⁩ ⁦ย⁩  [ ]  ⁦ห⁩ ⁦ร⁩⁦ื⁩ ⁦อ⁩  [ ]  ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ไ⁩ ⁦ท⁩ ⁦ย⁩   ⁦ก⁩ ⁦ล⁩ ⁦า⁩ ⁦ง⁩  [ ]  ⁦เ⁩ ⁦ป⁩⁦็⁩ ⁦น⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ร⁩ ⁦า⁩ ⁦ช⁩ ⁦ก⁩ ⁦า⁩ ⁦ร⁩   ⁦แ⁩ ⁦ล⁩ ⁦ะ⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ป⁩ ⁦ร⁩ ⁦ะ⁩ ⁦จ⁩ ⁦ำ⁩   ⁦ช⁩ ⁦า⁩ ⁦ต⁩⁦ิ⁩   ⁦ข⁩ ⁦อ⁩ ⁦ง⁩   ⁦ป⁩ ⁦ร⁩ ⁦ะ⁩ ⁦เ⁩ ⁦ท⁩ ⁦ศ⁩   ⁦ไ⁩ ⁦ท⁩ ⁦ย⁩  [ ]  ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ไ⁩ ⁦ท⁩ ⁦ย⁩   ⁦เ⁩ ⁦ป⁩⁦็⁩ ⁦น⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ใ⁩ ⁦น⁩   ⁦ก⁩ ⁦ล⁩⁦ุ⁩⁦่⁩ ⁦ม⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ไ⁩ ⁦ท⁩   ⁦ซ⁩⁦ึ⁩⁦่⁩ ⁦ง⁩   ⁦เ⁩ ⁦ป⁩⁦็⁩ ⁦น⁩   ⁦ก⁩ ⁦ล⁩⁦ุ⁩⁦่⁩ ⁦ม⁩   ⁦ย⁩⁦่⁩ ⁦อ⁩ ⁦ย⁩   ⁦ข⁩ ⁦อ⁩ ⁦ง⁩   ⁦ต⁩ ⁦ร⁩ ⁦ะ⁩ ⁦ก⁩⁦ู⁩ ⁦ล⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ข⁩ ⁦ร⁩⁦้⁩ ⁦า⁩  [ ]  ⁦ไ⁩ ⁦ท⁩  [ ]  ⁦ส⁩⁦ั⁩ ⁦น⁩ ⁦น⁩⁦ิ⁩ ⁦ษ⁩ ⁦ฐ⁩ ⁦า⁩ ⁦น⁩   ⁦ว⁩⁦่⁩ ⁦า⁩  [ ]  ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ใ⁩ ⁦น⁩   ⁦ต⁩ ⁦ร⁩ ⁦ะ⁩ ⁦ก⁩⁦ู⁩ ⁦ล⁩   ⁦น⁩⁦ี⁩⁦้⁩   ⁦ม⁩⁦ี⁩   ⁦ถ⁩⁦ิ⁩⁦่⁩ ⁦น⁩   ⁦ก⁩ ⁦ำ⁩ ⁦เ⁩ ⁦น⁩⁦ิ⁩ ⁦ด⁩   ⁦จ⁩ ⁦า⁩ ⁦ก⁩   ⁦ท⁩ ⁦า⁩ ⁦ง⁩   ⁦ต⁩ ⁦อ⁩ ⁦น⁩   ⁦ใ⁩ ⁦ต⁩⁦้⁩   ⁦ข⁩ ⁦อ⁩ ⁦ง⁩   ⁦ป⁩ ⁦ร⁩ ⁦ะ⁩ ⁦เ⁩ ⁦ท⁩ ⁦ศ⁩   ⁦จ⁩⁦ี⁩ ⁦น⁩  [ ]  ⁦แ⁩ ⁦ล⁩ ⁦ะ⁩   ⁦น⁩⁦ั⁩ ⁦ก⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩ ⁦ศ⁩ ⁦า⁩ ⁦ส⁩ ⁦ต⁩ ⁦ร⁩⁦์⁩   ⁦บ⁩ ⁦า⁩ ⁦ง⁩   ⁦ส⁩⁦่⁩ ⁦ว⁩ ⁦น⁩   ⁦เ⁩ ⁦ส⁩ ⁦น⁩ ⁦อ⁩   ⁦ว⁩⁦่⁩ ⁦า⁩  [ ]  ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦ไ⁩ ⁦ท⁩ ⁦ย⁩   ⁦น⁩⁦่⁩ ⁦า⁩   ⁦จ⁩ ⁦ะ⁩   ⁦ม⁩⁦ี⁩   ⁦ค⁩ ⁦ว⁩ ⁦า⁩ ⁦ม⁩   ⁦เ⁩ ⁦ช⁩⁦ื⁩⁦่⁩ ⁦อ⁩ ⁦ม⁩   ⁦โ⁩ ⁦ย⁩ ⁦ง⁩   ⁦ก⁩⁦ั⁩ ⁦บ⁩   ⁦ต⁩ ⁦ร⁩ ⁦ะ⁩ ⁦ก⁩⁦ู⁩ ⁦ล⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦อ⁩ ⁦อ⁩   ⁦ส⁩ ⁦โ⁩ ⁦ต⁩ ⁦ร⁩  [ ]  ⁦เ⁩ ⁦อ⁩ ⁦เ⁩ ⁦ช⁩⁦ี⁩ ⁦ย⁩   ⁦ต⁩⁦ิ⁩ ⁦ก⁩  [ ]  ⁦ต⁩ ⁦ร⁩ ⁦ะ⁩ ⁦ก⁩⁦ู⁩ ⁦ล⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦อ⁩ ⁦อ⁩   ⁦ส⁩ ⁦โ⁩ ⁦ต⁩ ⁦ร⁩ ⁦น⁩⁦ี⁩ ⁦เ⁩ ⁦ซ⁩⁦ี⁩ ⁦ย⁩ ⁦น⁩  [ ]  ⁦แ⁩ ⁦ล⁩ ⁦ะ⁩   ⁦ต⁩ ⁦ร⁩ ⁦ะ⁩ ⁦ก⁩⁦ู⁩ ⁦ล⁩   ⁦ภ⁩ ⁦า⁩ ⁦ษ⁩ ⁦า⁩   ⁦จ⁩⁦ี⁩ ⁦น⁩  [ ]  ⁦ท⁩⁦ิ⁩ ⁦เ⁩ ⁦บ⁩ ⁦ต⁩  [0x0a] 
+Breaks:     c  c c c lc  c c c    lc c  c c    lc c c c lc  c c lc  c c c c    lc c  c lc  c c c lc  c c c c c lc  c c lc  c c c lc  c c c c lc  c c  lc  c c lc  c c c c c lc  c c c    lc c c c lc  c c lc  c  c lc  c c c lc  c lc  c   c lc  c c c lc  c lc    c lc  c  c lc  c   c lc   c c lc  c c lc  c c c  c lc  c c c lc  c  c c    lc c c    lc  c c  c c c c lc   c c    lc c c c lc  c lc  c c c  c lc    lc   lc    c lc  c c c  c lc  c c lc  c c lc  c c lc  c  lc  c c lc  c c c c c lc   c c    lc c c lc   c lc  c c c c c c c c  lc  c c lc   c c lc  c c c lc   c c    lc c c c lc  c c lc   c lc  c lc   lc  c c c lc  c   c c lc  c c lc   c lc  c c c  c lc  c c c lc  c lc  c c c c    lc c c c  c lc   c c    lc c c c  c lc  c c c lc  c lc  c c c c  c c  c c c    lc c c lc  c c c  c lc  c c c lc   c c    lc  c c c c       c
+Whitespace:                  x            x                               x                                                                                                         x                                                                                                                                                    x         x                            x                                                                                                                            x                                                                         x                                                                                                                   x                       x                                                      x                                         x              w       w
+Sentences:  bs                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     e       b
+Words:      bs b b b bse b b be   bs b  b be   bs b b b bse b b bse b b b be   bs b  b bse b b b bse b b b b b bse b b bse b b b bse b b b b bse b b  bse b b bse b b b b b bse b b be   bs b b b bse b b bse b  b bse b b b bse b bse b   b bse b b b bse b bse   b bse b  b bse b   b bse  b b bse b b bse b b b  b bse b b b bse b  b be   bs b be   bs  b b  b b b b bse  b be   bs b b b bse b bse b b b  b bse   bse  bse   b bse b b b  b bse b b bse b b bse b b bse b  bse b b bse b b b b b bse  b be   bs b b bse  b bse b b b b b b b b  bse b b bse  b b bse b b b bse  b be   bs b b b bse b b bse  b bse b bse  bse b b b bse b   b b bse b b bse  b bse b b b  b bse b b b bse b bse b b b be   bs b b b  b bse  b be   bs b b b  b bse b b b bse b bse b b b b  b b  b b be   bs b b bse b b b  b bse b b b bse  b be   bs  b b b be      b
+Graphemes:  b  b b b b   b b b    b  b  b b    b  b b b b   b b b   b b b b    b  b  b b   b b b b   b b b b b b   b b b   b b b b   b b b b b   b b  b   b b b   b b b b b b   b b b    b  b b b b   b b b   b  b b   b b b b   b b   b   b b   b b b b   b b     b b   b  b b   b   b b    b b b   b b b   b b b  b b   b b b b   b  b b    b  b b    b   b b  b b b b b    b b    b  b b b b   b b   b b b  b b     b    b     b b   b b b  b b   b b b   b b b   b b b   b  b   b b b   b b b b b b    b b    b  b b b    b b   b b b b b b b b  b   b b b    b b b   b b b b    b b    b  b b b b   b b b    b b   b b    b   b b b b   b   b b b   b b b    b b   b b b  b b   b b b b   b b   b b b b    b  b b b  b b    b b    b  b b b  b b   b b b b   b b   b b b b  b b  b b b    b  b b b   b b b  b b   b b b b    b b    b   b b b b       b