Initial Commit

.gitignore

@@ -0,0 +1,2 @@
+builds/*
+*.vim

.gitmodules

@@ -0,0 +1,9 @@
+[submodule "libs/tree-sitter-c"]
+	path = libs/tree-sitter-c
+	url = https://github.com/tree-sitter/tree-sitter-c
+[submodule "libs/tree-sitter"]
+	path = libs/tree-sitter
+	url = https://github.com/tree-sitter/tree-sitter.git
+[submodule "libs/tree-sitter-ruby"]
+	path = libs/tree-sitter-ruby
+	url = https://github.com/tree-sitter/tree-sitter-ruby.git

Makefile

@@ -0,0 +1,47 @@
+# Project settings
+TARGET   := cubit
+SRCDIR   := src
+BUILDDIR := builds
+UNIW     := libs/unicode_width/unicode_width.c
+GRAPHEME := libs/libgrapheme-2.0.2/src/*.c
+CJSON    := libs/cjson/cJSON.c
+TREE_SITTER_RUBY := libs/tree-sitter-ruby/libtree-sitter-ruby.a
+TREE_SITTER_C    := libs/tree-sitter-c/libtree-sitter-c.a
+TREE_SITTER      := libs/tree-sitter/libtree-sitter.a
+
+# Sources
+SRC := $(wildcard $(SRCDIR)/*.c) $(UNIW) $(GRAPHEME) $(CJSON)
+
+# Linker flags (libraries you want to link against)
+LIBS := $(TREE_SITTER) $(TREE_SITTER_RUBY) $(TREE_SITTER_C)
+
+# Compiler settings
+CC := gcc
+CFLAGS   := -Wall -Wextra
+DBGFLAGS := -O0 -g -fsanitize=address -fno-omit-frame-pointer
+OPTFLAGS := -O3 -march=native -flto -fomit-frame-pointer
+
+# Default target
+all: release
+
+# Debug/test build (with sanitizers, does NOT run automatically)
+test: $(BUILDDIR)/$(TARGET)-tst
+	@echo "Built test binary at $(BUILDDIR)/$(TARGET)-tst"
+
+$(BUILDDIR)/$(TARGET)-tst: $(SRC)
+	@mkdir -p $(BUILDDIR)
+	env ASAN_OPTIONS=verbosity=1:halt_on_error=1 $(CC) $(CFLAGS) $(DBGFLAGS) -o $@ $^ $(LIBS)
+
+# Release build (optimized, no sanitizers)
+release: $(BUILDDIR)/$(TARGET)
+
+$(BUILDDIR)/$(TARGET): $(SRC)
+	@mkdir -p $(BUILDDIR)
+	$(CC) $(CFLAGS) $(OPTFLAGS) -o $@ $^ $(LIBS)
+	strip $@
+
+# Clean
+clean:
+	rm -rf $(BUILDDIR)
+
+.PHONY: all test release clean

libs/cjson/cJSON.h

@@ -0,0 +1,395 @@
+/*
+  Copyright (c) 2009-2017 Dave Gamble and cJSON contributors
+
+  Permission is hereby granted, free of charge, to any person obtaining a copy
+  of this software and associated documentation files (the "Software"), to deal
+  in the Software without restriction, including without limitation the rights
+  to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+  copies of the Software, and to permit persons to whom the Software is
+  furnished to do so, subject to the following conditions:
+
+  The above copyright notice and this permission notice shall be included in
+  all copies or substantial portions of the Software.
+
+  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+  OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+  THE SOFTWARE.
+*/
+
+#ifndef cJSON__h
+#define cJSON__h
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#if !defined(__WINDOWS__) &&                                                   \
+    (defined(WIN32) || defined(WIN64) || defined(_MSC_VER) || defined(_WIN32))
+#define __WINDOWS__
+#endif
+
+#ifdef __WINDOWS__
+
+/* When compiling for windows, we specify a specific calling convention to avoid
+issues where we are being called from a project with a different default calling
+convention.  For windows you have 3 define options:
+
+CJSON_HIDE_SYMBOLS - Define this in the case where you don't want to ever
+dllexport symbols CJSON_EXPORT_SYMBOLS - Define this on library build when you
+want to dllexport symbols (default) CJSON_IMPORT_SYMBOLS - Define this if you
+want to dllimport symbol
+
+For *nix builds that support visibility attribute, you can define similar
+behavior by
+
+setting default visibility to hidden by adding
+-fvisibility=hidden (for gcc)
+or
+-xldscope=hidden (for sun cc)
+to CFLAGS
+
+then using the CJSON_API_VISIBILITY flag to "export" the same symbols the way
+CJSON_EXPORT_SYMBOLS does
+
+*/
+
+#define CJSON_CDECL __cdecl
+#define CJSON_STDCALL __stdcall
+
+/* export symbols by default, this is necessary for copy pasting the C and
+ * header file */
+#if !defined(CJSON_HIDE_SYMBOLS) && !defined(CJSON_IMPORT_SYMBOLS) &&          \
+    !defined(CJSON_EXPORT_SYMBOLS)
+#define CJSON_EXPORT_SYMBOLS
+#endif
+
+#if defined(CJSON_HIDE_SYMBOLS)
+#define CJSON_PUBLIC(type) type CJSON_STDCALL
+#elif defined(CJSON_EXPORT_SYMBOLS)
+#define CJSON_PUBLIC(type) __declspec(dllexport) type CJSON_STDCALL
+#elif defined(CJSON_IMPORT_SYMBOLS)
+#define CJSON_PUBLIC(type) __declspec(dllimport) type CJSON_STDCALL
+#endif
+#else /* !__WINDOWS__ */
+#define CJSON_CDECL
+#define CJSON_STDCALL
+
+#if (defined(__GNUC__) || defined(__SUNPRO_CC) || defined(__SUNPRO_C)) &&      \
+    defined(CJSON_API_VISIBILITY)
+#define CJSON_PUBLIC(type) __attribute__((visibility("default"))) type
+#else
+#define CJSON_PUBLIC(type) type
+#endif
+#endif
+
+/* project version */
+#define CJSON_VERSION_MAJOR 1
+#define CJSON_VERSION_MINOR 7
+#define CJSON_VERSION_PATCH 18
+
+#include <stddef.h>
+
+/* cJSON Types: */
+#define cJSON_Invalid (0)
+#define cJSON_False (1 << 0)
+#define cJSON_True (1 << 1)
+#define cJSON_NULL (1 << 2)
+#define cJSON_Number (1 << 3)
+#define cJSON_String (1 << 4)
+#define cJSON_Array (1 << 5)
+#define cJSON_Object (1 << 6)
+#define cJSON_Raw (1 << 7) /* raw json */
+
+#define cJSON_IsReference 256
+#define cJSON_StringIsConst 512
+
+/* The cJSON structure: */
+typedef struct cJSON {
+  /* next/prev allow you to walk array/object chains. Alternatively, use
+   * GetArraySize/GetArrayItem/GetObjectItem */
+  struct cJSON *next;
+  struct cJSON *prev;
+  /* An array or object item will have a child pointer pointing to a chain of
+   * the items in the array/object. */
+  struct cJSON *child;
+
+  /* The type of the item, as above. */
+  int type;
+
+  /* The item's string, if type==cJSON_String  and type == cJSON_Raw */
+  char *valuestring;
+  /* writing to valueint is DEPRECATED, use cJSON_SetNumberValue instead */
+  int valueint;
+  /* The item's number, if type==cJSON_Number */
+  double valuedouble;
+
+  /* The item's name string, if this item is the child of, or is in the list of
+   * subitems of an object. */
+  char *string;
+} cJSON;
+
+typedef struct cJSON_Hooks {
+  /* malloc/free are CDECL on Windows regardless of the default calling
+   * convention of the compiler, so ensure the hooks allow passing those
+   * functions directly. */
+  void *(CJSON_CDECL *malloc_fn)(size_t sz);
+  void(CJSON_CDECL *free_fn)(void *ptr);
+} cJSON_Hooks;
+
+typedef int cJSON_bool;
+
+/* Limits how deeply nested arrays/objects can be before cJSON rejects to parse
+ * them. This is to prevent stack overflows. */
+#ifndef CJSON_NESTING_LIMIT
+#define CJSON_NESTING_LIMIT 1000
+#endif
+
+/* Limits the length of circular references can be before cJSON rejects to parse
+ * them. This is to prevent stack overflows. */
+#ifndef CJSON_CIRCULAR_LIMIT
+#define CJSON_CIRCULAR_LIMIT 10000
+#endif
+
+/* returns the version of cJSON as a string */
+CJSON_PUBLIC(const char *) cJSON_Version(void);
+
+/* Supply malloc, realloc and free functions to cJSON */
+CJSON_PUBLIC(void) cJSON_InitHooks(cJSON_Hooks *hooks);
+
+/* Memory Management: the caller is always responsible to free the results from
+ * all variants of cJSON_Parse (with cJSON_Delete) and cJSON_Print (with stdlib
+ * free, cJSON_Hooks.free_fn, or cJSON_free as appropriate). The exception is
+ * cJSON_PrintPreallocated, where the caller has full responsibility of the
+ * buffer. */
+/* Supply a block of JSON, and this returns a cJSON object you can interrogate.
+ */
+CJSON_PUBLIC(cJSON *) cJSON_Parse(const char *value);
+CJSON_PUBLIC(cJSON *)
+cJSON_ParseWithLength(const char *value, size_t buffer_length);
+/* ParseWithOpts allows you to require (and check) that the JSON is null
+ * terminated, and to retrieve the pointer to the final byte parsed. */
+/* If you supply a ptr in return_parse_end and parsing fails, then
+ * return_parse_end will contain a pointer to the error so will match
+ * cJSON_GetErrorPtr(). */
+CJSON_PUBLIC(cJSON *)
+cJSON_ParseWithOpts(const char *value, const char **return_parse_end,
+                    cJSON_bool require_null_terminated);
+CJSON_PUBLIC(cJSON *)
+cJSON_ParseWithLengthOpts(const char *value, size_t buffer_length,
+                          const char **return_parse_end,
+                          cJSON_bool require_null_terminated);
+
+/* Render a cJSON entity to text for transfer/storage. */
+CJSON_PUBLIC(char *) cJSON_Print(const cJSON *item);
+/* Render a cJSON entity to text for transfer/storage without any formatting. */
+CJSON_PUBLIC(char *) cJSON_PrintUnformatted(const cJSON *item);
+/* Render a cJSON entity to text using a buffered strategy. prebuffer is a guess
+ * at the final size. guessing well reduces reallocation. fmt=0 gives
+ * unformatted, =1 gives formatted */
+CJSON_PUBLIC(char *)
+cJSON_PrintBuffered(const cJSON *item, int prebuffer, cJSON_bool fmt);
+/* Render a cJSON entity to text using a buffer already allocated in memory with
+ * given length. Returns 1 on success and 0 on failure. */
+/* NOTE: cJSON is not always 100% accurate in estimating how much memory it will
+ * use, so to be safe allocate 5 bytes more than you actually need */
+CJSON_PUBLIC(cJSON_bool)
+cJSON_PrintPreallocated(cJSON *item, char *buffer, const int length,
+                        const cJSON_bool format);
+/* Delete a cJSON entity and all subentities. */
+CJSON_PUBLIC(void) cJSON_Delete(cJSON *item);
+
+/* Returns the number of items in an array (or object). */
+CJSON_PUBLIC(int) cJSON_GetArraySize(const cJSON *array);
+/* Retrieve item number "index" from array "array". Returns NULL if
+ * unsuccessful. */
+CJSON_PUBLIC(cJSON *) cJSON_GetArrayItem(const cJSON *array, int index);
+/* Get item "string" from object. Case insensitive. */
+CJSON_PUBLIC(cJSON *)
+cJSON_GetObjectItem(const cJSON *const object, const char *const string);
+CJSON_PUBLIC(cJSON *)
+cJSON_GetObjectItemCaseSensitive(const cJSON *const object,
+                                 const char *const string);
+CJSON_PUBLIC(cJSON_bool)
+cJSON_HasObjectItem(const cJSON *object, const char *string);
+/* For analysing failed parses. This returns a pointer to the parse error.
+ * You'll probably need to look a few chars back to make sense of it. Defined
+ * when cJSON_Parse() returns 0. 0 when cJSON_Parse() succeeds. */
+CJSON_PUBLIC(const char *) cJSON_GetErrorPtr(void);
+
+/* Check item type and return its value */
+CJSON_PUBLIC(char *) cJSON_GetStringValue(const cJSON *const item);
+CJSON_PUBLIC(double) cJSON_GetNumberValue(const cJSON *const item);
+
+/* These functions check the type of an item */
+CJSON_PUBLIC(cJSON_bool) cJSON_IsInvalid(const cJSON *const item);
+CJSON_PUBLIC(cJSON_bool) cJSON_IsFalse(const cJSON *const item);
+CJSON_PUBLIC(cJSON_bool) cJSON_IsTrue(const cJSON *const item);
+CJSON_PUBLIC(cJSON_bool) cJSON_IsBool(const cJSON *const item);
+CJSON_PUBLIC(cJSON_bool) cJSON_IsNull(const cJSON *const item);
+CJSON_PUBLIC(cJSON_bool) cJSON_IsNumber(const cJSON *const item);
+CJSON_PUBLIC(cJSON_bool) cJSON_IsString(const cJSON *const item);
+CJSON_PUBLIC(cJSON_bool) cJSON_IsArray(const cJSON *const item);
+CJSON_PUBLIC(cJSON_bool) cJSON_IsObject(const cJSON *const item);
+CJSON_PUBLIC(cJSON_bool) cJSON_IsRaw(const cJSON *const item);
+
+/* These calls create a cJSON item of the appropriate type. */
+CJSON_PUBLIC(cJSON *) cJSON_CreateNull(void);
+CJSON_PUBLIC(cJSON *) cJSON_CreateTrue(void);
+CJSON_PUBLIC(cJSON *) cJSON_CreateFalse(void);
+CJSON_PUBLIC(cJSON *) cJSON_CreateBool(cJSON_bool boolean);
+CJSON_PUBLIC(cJSON *) cJSON_CreateNumber(double num);
+CJSON_PUBLIC(cJSON *) cJSON_CreateString(const char *string);
+/* raw json */
+CJSON_PUBLIC(cJSON *) cJSON_CreateRaw(const char *raw);
+CJSON_PUBLIC(cJSON *) cJSON_CreateArray(void);
+CJSON_PUBLIC(cJSON *) cJSON_CreateObject(void);
+
+/* Create a string where valuestring references a string so
+ * it will not be freed by cJSON_Delete */
+CJSON_PUBLIC(cJSON *) cJSON_CreateStringReference(const char *string);
+/* Create an object/array that only references it's elements so
+ * they will not be freed by cJSON_Delete */
+CJSON_PUBLIC(cJSON *) cJSON_CreateObjectReference(const cJSON *child);
+CJSON_PUBLIC(cJSON *) cJSON_CreateArrayReference(const cJSON *child);
+
+/* These utilities create an Array of count items.
+ * The parameter count cannot be greater than the number of elements in the
+ * number array, otherwise array access will be out of bounds.*/
+CJSON_PUBLIC(cJSON *) cJSON_CreateIntArray(const int *numbers, int count);
+CJSON_PUBLIC(cJSON *) cJSON_CreateFloatArray(const float *numbers, int count);
+CJSON_PUBLIC(cJSON *) cJSON_CreateDoubleArray(const double *numbers, int count);
+CJSON_PUBLIC(cJSON *)
+cJSON_CreateStringArray(const char *const *strings, int count);
+
+/* Append item to the specified array/object. */
+CJSON_PUBLIC(cJSON_bool) cJSON_AddItemToArray(cJSON *array, cJSON *item);
+CJSON_PUBLIC(cJSON_bool)
+cJSON_AddItemToObject(cJSON *object, const char *string, cJSON *item);
+/* Use this when string is definitely const (i.e. a literal, or as good as), and
+ * will definitely survive the cJSON object. WARNING: When this function was
+ * used, make sure to always check that (item->type & cJSON_StringIsConst) is
+ * zero before writing to `item->string` */
+CJSON_PUBLIC(cJSON_bool)
+cJSON_AddItemToObjectCS(cJSON *object, const char *string, cJSON *item);
+/* Append reference to item to the specified array/object. Use this when you
+ * want to add an existing cJSON to a new cJSON, but don't want to corrupt your
+ * existing cJSON. */
+CJSON_PUBLIC(cJSON_bool)
+cJSON_AddItemReferenceToArray(cJSON *array, cJSON *item);
+CJSON_PUBLIC(cJSON_bool)
+cJSON_AddItemReferenceToObject(cJSON *object, const char *string, cJSON *item);
+
+/* Remove/Detach items from Arrays/Objects. */
+CJSON_PUBLIC(cJSON *)
+cJSON_DetachItemViaPointer(cJSON *parent, cJSON *const item);
+CJSON_PUBLIC(cJSON *) cJSON_DetachItemFromArray(cJSON *array, int which);
+CJSON_PUBLIC(void) cJSON_DeleteItemFromArray(cJSON *array, int which);
+CJSON_PUBLIC(cJSON *)
+cJSON_DetachItemFromObject(cJSON *object, const char *string);
+CJSON_PUBLIC(cJSON *)
+cJSON_DetachItemFromObjectCaseSensitive(cJSON *object, const char *string);
+CJSON_PUBLIC(void)
+cJSON_DeleteItemFromObject(cJSON *object, const char *string);
+CJSON_PUBLIC(void)
+cJSON_DeleteItemFromObjectCaseSensitive(cJSON *object, const char *string);
+
+/* Update array items. */
+CJSON_PUBLIC(cJSON_bool)
+cJSON_InsertItemInArray(
+    cJSON *array, int which,
+    cJSON *newitem); /* Shifts pre-existing items to the right. */
+CJSON_PUBLIC(cJSON_bool)
+cJSON_ReplaceItemViaPointer(cJSON *const parent, cJSON *const item,
+                            cJSON *replacement);
+CJSON_PUBLIC(cJSON_bool)
+cJSON_ReplaceItemInArray(cJSON *array, int which, cJSON *newitem);
+CJSON_PUBLIC(cJSON_bool)
+cJSON_ReplaceItemInObject(cJSON *object, const char *string, cJSON *newitem);
+CJSON_PUBLIC(cJSON_bool)
+cJSON_ReplaceItemInObjectCaseSensitive(cJSON *object, const char *string,
+                                       cJSON *newitem);
+
+/* Duplicate a cJSON item */
+CJSON_PUBLIC(cJSON *) cJSON_Duplicate(const cJSON *item, cJSON_bool recurse);
+/* Duplicate will create a new, identical cJSON item to the one you pass, in new
+ * memory that will need to be released. With recurse!=0, it will duplicate any
+ * children connected to the item. The item->next and ->prev pointers are always
+ * zero on return from Duplicate. */
+/* Recursively compare two cJSON items for equality. If either a or b is NULL or
+ * invalid, they will be considered unequal. case_sensitive determines if object
+ * keys are treated case sensitive (1) or case insensitive (0) */
+CJSON_PUBLIC(cJSON_bool)
+cJSON_Compare(const cJSON *const a, const cJSON *const b,
+              const cJSON_bool case_sensitive);
+
+/* Minify a strings, remove blank characters(such as ' ', '\t', '\r', '\n') from
+ * strings. The input pointer json cannot point to a read-only address area,
+ * such as a string constant, but should point to a readable and writable
+ * address area. */
+CJSON_PUBLIC(void) cJSON_Minify(char *json);
+
+/* Helper functions for creating and adding items to an object at the same time.
+ * They return the added item or NULL on failure. */
+CJSON_PUBLIC(cJSON *)
+cJSON_AddNullToObject(cJSON *const object, const char *const name);
+CJSON_PUBLIC(cJSON *)
+cJSON_AddTrueToObject(cJSON *const object, const char *const name);
+CJSON_PUBLIC(cJSON *)
+cJSON_AddFalseToObject(cJSON *const object, const char *const name);
+CJSON_PUBLIC(cJSON *)
+cJSON_AddBoolToObject(cJSON *const object, const char *const name,
+                      const cJSON_bool boolean);
+CJSON_PUBLIC(cJSON *)
+cJSON_AddNumberToObject(cJSON *const object, const char *const name,
+                        const double number);
+CJSON_PUBLIC(cJSON *)
+cJSON_AddStringToObject(cJSON *const object, const char *const name,
+                        const char *const string);
+CJSON_PUBLIC(cJSON *)
+cJSON_AddRawToObject(cJSON *const object, const char *const name,
+                     const char *const raw);
+CJSON_PUBLIC(cJSON *)
+cJSON_AddObjectToObject(cJSON *const object, const char *const name);
+CJSON_PUBLIC(cJSON *)
+cJSON_AddArrayToObject(cJSON *const object, const char *const name);
+
+/* When assigning an integer value, it needs to be propagated to valuedouble
+ * too. */
+#define cJSON_SetIntValue(object, number)                                      \
+  ((object) ? (object)->valueint = (object)->valuedouble = (number) : (number))
+/* helper for the cJSON_SetNumberValue macro */
+CJSON_PUBLIC(double) cJSON_SetNumberHelper(cJSON *object, double number);
+#define cJSON_SetNumberValue(object, number)                                   \
+  ((object != NULL) ? cJSON_SetNumberHelper(object, (double)number) : (number))
+/* Change the valuestring of a cJSON_String object, only takes effect when type
+ * of object is cJSON_String */
+CJSON_PUBLIC(char *)
+cJSON_SetValuestring(cJSON *object, const char *valuestring);
+
+/* If the object is not a boolean type this does nothing and returns
+ * cJSON_Invalid else it returns the new type*/
+#define cJSON_SetBoolValue(object, boolValue)                                  \
+  ((object != NULL && ((object)->type & (cJSON_False | cJSON_True)))           \
+       ? (object)->type = ((object)->type & (~(cJSON_False | cJSON_True))) |   \
+                          ((boolValue) ? cJSON_True : cJSON_False)             \
+       : cJSON_Invalid)
+
+/* Macro for iterating over an array or object */
+#define cJSON_ArrayForEach(element, array)                                     \
+  for (element = (array != NULL) ? (array)->child : NULL; element != NULL;     \
+       element = element->next)
+
+/* malloc/free objects using the malloc/free functions that have been set with
+ * cJSON_InitHooks */
+CJSON_PUBLIC(void *) cJSON_malloc(size_t size);
+CJSON_PUBLIC(void) cJSON_free(void *object);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif

libs/libgrapheme-2.0.2/LICENSE

@@ -0,0 +1,15 @@
+ISC-License
+
+Copyright 2019-2022 Laslo Hunhold <dev@frign.de>
+
+Permission to use, copy, modify, and/or distribute this software for any
+purpose with or without fee is hereby granted, provided that the above
+copyright notice and this permission notice appear in all copies.
+
+THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.

libs/libgrapheme-2.0.2/Makefile

@@ -0,0 +1,327 @@
+# See LICENSE file for copyright and license details
+# libgrapheme - unicode string library
+.POSIX:
+.SUFFIXES:
+
+VERSION_MAJOR = 2
+VERSION_MINOR = 0
+VERSION_PATCH = 2
+UNICODE_VERSION = 15.0.0
+MAN_DATE = 2022-10-06
+
+include config.mk
+
+VERSION = $(VERSION_MAJOR).$(VERSION_MINOR).$(VERSION_PATCH)
+
+BENCHMARK =\
+	benchmark/case\
+	benchmark/character\
+	benchmark/sentence\
+	benchmark/line\
+	benchmark/utf8-decode\
+	benchmark/word\
+
+DATA =\
+	data/DerivedCoreProperties.txt\
+	data/EastAsianWidth.txt\
+	data/emoji-data.txt\
+	data/GraphemeBreakProperty.txt\
+	data/GraphemeBreakTest.txt\
+	data/LICENSE\
+	data/LineBreak.txt\
+	data/LineBreakTest.txt\
+	data/SentenceBreakProperty.txt\
+	data/SentenceBreakTest.txt\
+	data/SpecialCasing.txt\
+	data/UnicodeData.txt\
+	data/WordBreakProperty.txt\
+	data/WordBreakTest.txt\
+
+GEN =\
+	gen/case\
+	gen/character\
+	gen/character-test\
+	gen/line\
+	gen/line-test\
+	gen/sentence\
+	gen/sentence-test\
+	gen/word\
+	gen/word-test\
+
+SRC =\
+	src/case\
+	src/character\
+	src/line\
+	src/sentence\
+	src/utf8\
+	src/util\
+	src/word\
+
+TEST =\
+	test/case\
+	test/character\
+	test/line\
+	test/sentence\
+	test/utf8-decode\
+	test/utf8-encode\
+	test/word\
+
+MAN_TEMPLATE =\
+	man/template/is_case.sh\
+	man/template/next_break.sh\
+	man/template/to_case.sh\
+
+MAN3 =\
+	man/grapheme_decode_utf8\
+	man/grapheme_encode_utf8\
+	man/grapheme_is_character_break\
+	man/grapheme_is_uppercase\
+	man/grapheme_is_uppercase_utf8\
+	man/grapheme_is_lowercase\
+	man/grapheme_is_lowercase_utf8\
+	man/grapheme_is_titlecase\
+	man/grapheme_is_titlecase_utf8\
+	man/grapheme_next_character_break\
+	man/grapheme_next_line_break\
+	man/grapheme_next_sentence_break\
+	man/grapheme_next_word_break\
+	man/grapheme_next_character_break_utf8\
+	man/grapheme_next_line_break_utf8\
+	man/grapheme_next_sentence_break_utf8\
+	man/grapheme_next_word_break_utf8\
+	man/grapheme_to_uppercase\
+	man/grapheme_to_uppercase_utf8\
+	man/grapheme_to_lowercase\
+	man/grapheme_to_lowercase_utf8\
+	man/grapheme_to_titlecase\
+	man/grapheme_to_titlecase_utf8\
+
+MAN7 =\
+	man/libgrapheme\
+
+all: data/LICENSE $(MAN3:=.3) $(MAN7:=.7) libgrapheme.a $(SONAME)
+
+data/DerivedCoreProperties.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/DerivedCoreProperties.txt
+
+data/EastAsianWidth.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/EastAsianWidth.txt
+
+data/emoji-data.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/emoji/emoji-data.txt
+
+data/GraphemeBreakProperty.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/GraphemeBreakProperty.txt
+
+data/GraphemeBreakTest.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/GraphemeBreakTest.txt
+
+data/LICENSE:
+	wget -O $@ https://www.unicode.org/license.txt
+
+data/LineBreak.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/LineBreak.txt
+
+data/LineBreakTest.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/LineBreakTest.txt
+
+data/SentenceBreakProperty.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/SentenceBreakProperty.txt
+
+data/SentenceBreakTest.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/SentenceBreakTest.txt
+
+data/SpecialCasing.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/SpecialCasing.txt
+
+data/UnicodeData.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/UnicodeData.txt
+
+data/WordBreakProperty.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/WordBreakProperty.txt
+
+data/WordBreakTest.txt:
+	wget -O $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/auxiliary/WordBreakTest.txt
+
+benchmark/case.o: benchmark/case.c Makefile config.mk gen/word-test.h grapheme.h benchmark/util.h
+benchmark/character.o: benchmark/character.c Makefile config.mk gen/character-test.h grapheme.h benchmark/util.h
+benchmark/line.o: benchmark/line.c Makefile config.mk gen/line-test.h grapheme.h benchmark/util.h
+benchmark/utf8-decode.o: benchmark/utf8-decode.c Makefile config.mk gen/character-test.h grapheme.h benchmark/util.h
+benchmark/sentence.o: benchmark/sentence.c Makefile config.mk gen/sentence-test.h grapheme.h benchmark/util.h
+benchmark/util.o: benchmark/util.c Makefile config.mk benchmark/util.h
+benchmark/word.o: benchmark/word.c Makefile config.mk gen/word-test.h grapheme.h benchmark/util.h
+gen/case.o: gen/case.c Makefile config.mk gen/util.h
+gen/character.o: gen/character.c Makefile config.mk gen/util.h
+gen/character-test.o: gen/character-test.c Makefile config.mk gen/util.h
+gen/line.o: gen/line.c Makefile config.mk gen/util.h
+gen/line-test.o: gen/line-test.c Makefile config.mk gen/util.h
+gen/sentence.o: gen/sentence.c Makefile config.mk gen/util.h
+gen/sentence-test.o: gen/sentence-test.c Makefile config.mk gen/util.h
+gen/word.o: gen/word.c Makefile config.mk gen/util.h
+gen/word-test.o: gen/word-test.c Makefile config.mk gen/util.h
+gen/util.o: gen/util.c Makefile config.mk gen/util.h
+src/case.o: src/case.c Makefile config.mk gen/case.h grapheme.h src/util.h
+src/character.o: src/character.c Makefile config.mk gen/character.h grapheme.h src/util.h
+src/line.o: src/line.c Makefile config.mk gen/line.h grapheme.h src/util.h
+src/sentence.o: src/sentence.c Makefile config.mk gen/sentence.h grapheme.h src/util.h
+src/utf8.o: src/utf8.c Makefile config.mk grapheme.h
+src/util.o: src/util.c Makefile config.mk gen/types.h grapheme.h src/util.h
+src/word.o: src/word.c Makefile config.mk gen/word.h grapheme.h src/util.h
+test/case.o: test/case.c Makefile config.mk grapheme.h test/util.h
+test/character.o: test/character.c Makefile config.mk gen/character-test.h grapheme.h test/util.h
+test/line.o: test/line.c Makefile config.mk gen/line-test.h grapheme.h test/util.h
+test/sentence.o: test/sentence.c Makefile config.mk gen/sentence-test.h grapheme.h test/util.h
+test/utf8-encode.o: test/utf8-encode.c Makefile config.mk grapheme.h test/util.h
+test/utf8-decode.o: test/utf8-decode.c Makefile config.mk grapheme.h test/util.h
+test/util.o: test/util.c Makefile config.mk test/util.h
+test/word.o: test/word.c Makefile config.mk gen/word-test.h grapheme.h test/util.h
+
+benchmark/case: benchmark/case.o benchmark/util.o libgrapheme.a
+benchmark/character: benchmark/character.o benchmark/util.o libgrapheme.a
+benchmark/line: benchmark/line.o benchmark/util.o libgrapheme.a
+benchmark/sentence: benchmark/sentence.o benchmark/util.o libgrapheme.a
+benchmark/utf8-decode: benchmark/utf8-decode.o benchmark/util.o libgrapheme.a
+benchmark/word: benchmark/word.o benchmark/util.o libgrapheme.a
+gen/case: gen/case.o gen/util.o
+gen/character: gen/character.o gen/util.o
+gen/character-test: gen/character-test.o gen/util.o
+gen/line: gen/line.o gen/util.o
+gen/line-test: gen/line-test.o gen/util.o
+gen/sentence: gen/sentence.o gen/util.o
+gen/sentence-test: gen/sentence-test.o gen/util.o
+gen/word: gen/word.o gen/util.o
+gen/word-test: gen/word-test.o gen/util.o
+test/case: test/case.o test/util.o libgrapheme.a
+test/character: test/character.o test/util.o libgrapheme.a
+test/line: test/line.o test/util.o libgrapheme.a
+test/sentence: test/sentence.o test/util.o libgrapheme.a
+test/utf8-encode: test/utf8-encode.o test/util.o libgrapheme.a
+test/utf8-decode: test/utf8-decode.o test/util.o libgrapheme.a
+test/word: test/word.o test/util.o libgrapheme.a
+
+gen/case.h: data/DerivedCoreProperties.txt data/UnicodeData.txt data/SpecialCasing.txt gen/case
+gen/character.h: data/emoji-data.txt data/GraphemeBreakProperty.txt gen/character
+gen/character-test.h: data/GraphemeBreakTest.txt gen/character-test
+gen/line.h: data/emoji-data.txt data/EastAsianWidth.txt data/LineBreak.txt gen/line
+gen/line-test.h: data/LineBreakTest.txt gen/line-test
+gen/sentence.h: data/SentenceBreakProperty.txt gen/sentence
+gen/sentence-test.h: data/SentenceBreakTest.txt gen/sentence-test
+gen/word.h: data/WordBreakProperty.txt gen/word
+gen/word-test.h: data/WordBreakTest.txt gen/word-test
+
+man/grapheme_is_character_break.3: man/grapheme_is_character_break.sh Makefile config.mk
+man/grapheme_is_uppercase.3: man/grapheme_is_uppercase.sh man/template/is_case.sh Makefile config.mk
+man/grapheme_is_uppercase_utf8.3: man/grapheme_is_uppercase_utf8.sh man/template/is_case.sh Makefile config.mk
+man/grapheme_is_lowercase.3: man/grapheme_is_lowercase.sh man/template/is_case.sh Makefile config.mk
+man/grapheme_is_lowercase_utf8.3: man/grapheme_is_lowercase_utf8.sh man/template/is_case.sh Makefile config.mk
+man/grapheme_is_titlecase.3: man/grapheme_is_titlecase.sh man/template/is_case.sh Makefile config.mk
+man/grapheme_is_titlecase_utf8.3: man/grapheme_is_titlecase_utf8.sh man/template/is_case.sh Makefile config.mk
+man/grapheme_next_character_break.3: man/grapheme_next_character_break.sh man/template/next_break.sh Makefile config.mk
+man/grapheme_next_line_break.3: man/grapheme_next_line_break.sh man/template/next_break.sh Makefile config.mk
+man/grapheme_next_sentence_break.3: man/grapheme_next_sentence_break.sh man/template/next_break.sh Makefile config.mk
+man/grapheme_next_word_break.3: man/grapheme_next_word_break.sh man/template/next_break.sh Makefile config.mk
+man/grapheme_next_character_break_utf8.3: man/grapheme_next_character_break_utf8.sh man/template/next_break.sh Makefile config.mk
+man/grapheme_next_line_break_utf8.3: man/grapheme_next_line_break_utf8.sh man/template/next_break.sh Makefile config.mk
+man/grapheme_next_sentence_break_utf8.3: man/grapheme_next_sentence_break_utf8.sh man/template/next_break.sh Makefile config.mk
+man/grapheme_next_word_break_utf8.3: man/grapheme_next_word_break_utf8.sh man/template/next_break.sh Makefile config.mk
+man/grapheme_to_uppercase.3: man/grapheme_to_uppercase.sh man/template/to_case.sh Makefile config.mk
+man/grapheme_to_lowercase.3: man/grapheme_to_lowercase.sh man/template/to_case.sh Makefile config.mk
+man/grapheme_to_titlecase.3: man/grapheme_to_titlecase.sh man/template/to_case.sh Makefile config.mk
+man/grapheme_to_uppercase_utf8.3: man/grapheme_to_uppercase_utf8.sh man/template/to_case.sh Makefile config.mk
+man/grapheme_to_lowercase_utf8.3: man/grapheme_to_lowercase_utf8.sh man/template/to_case.sh Makefile config.mk
+man/grapheme_to_titlecase_utf8.3: man/grapheme_to_titlecase_utf8.sh man/template/to_case.sh Makefile config.mk
+man/grapheme_decode_utf8.3: man/grapheme_decode_utf8.sh Makefile config.mk
+man/grapheme_encode_utf8.3: man/grapheme_encode_utf8.sh Makefile config.mk
+
+man/libgrapheme.7: man/libgrapheme.sh Makefile config.mk
+
+$(GEN:=.o) gen/util.o:
+	$(BUILD_CC) -c -o $@ $(BUILD_CPPFLAGS) $(BUILD_CFLAGS) $(@:.o=.c)
+
+$(BENCHMARK:=.o) benchmark/util.o $(TEST:=.o) test/util.o:
+	$(CC) -c -o $@ $(CPPFLAGS) $(CFLAGS) $(@:.o=.c)
+
+$(SRC:=.o):
+	$(CC) -c -o $@ $(CPPFLAGS) $(CFLAGS) $(SHFLAGS) $(@:.o=.c)
+
+$(BENCHMARK):
+	$(CC) -o $@ $(LDFLAGS) $@.o benchmark/util.o libgrapheme.a -lutf8proc
+
+$(GEN):
+	$(BUILD_CC) -o $@ $(BUILD_LDFLAGS) $@.o gen/util.o
+
+$(TEST):
+	$(CC) -o $@ $(LDFLAGS) $@.o test/util.o libgrapheme.a
+
+$(GEN:=.h):
+	$(@:.h=) > $@
+
+libgrapheme.a: $(SRC:=.o)
+	$(AR) -rc $@ $?
+	$(RANLIB) $@
+
+$(SONAME): $(SRC:=.o)
+	$(CC) -o $@ $(SOFLAGS) $(LDFLAGS) $(SRC:=.o)
+
+$(MAN3:=.3):
+	SH="$(SH)" MAN_DATE="$(MAN_DATE)" UNICODE_VERSION="$(UNICODE_VERSION)" $(SH) $(@:.3=.sh) > $@
+
+$(MAN7:=.7):
+	SH="$(SH)" MAN_DATE="$(MAN_DATE)" UNICODE_VERSION="$(UNICODE_VERSION)" $(SH) $(@:.7=.sh) > $@
+
+benchmark: $(BENCHMARK)
+	for m in $(BENCHMARK); do ./$$m; done
+
+test: $(TEST)
+	for m in $(TEST); do ./$$m; done
+
+install: all
+	mkdir -p "$(DESTDIR)$(LIBPREFIX)"
+	mkdir -p "$(DESTDIR)$(INCPREFIX)"
+	mkdir -p "$(DESTDIR)$(MANPREFIX)/man3"
+	mkdir -p "$(DESTDIR)$(MANPREFIX)/man7"
+	cp -f $(MAN3:=.3) "$(DESTDIR)$(MANPREFIX)/man3"
+	cp -f $(MAN7:=.7) "$(DESTDIR)$(MANPREFIX)/man7"
+	cp -f libgrapheme.a "$(DESTDIR)$(LIBPREFIX)"
+	cp -f $(SONAME) "$(DESTDIR)$(LIBPREFIX)/$(SONAME)"
+	if [ "$(SOSYMLINK)" = "true" ]; then i=0; while [ "$$i" -le $(VERSION_MINOR) ]; do ln -sf "$(SONAME)" "$(DESTDIR)$(LIBPREFIX)/libgrapheme.so.$(VERSION_MAJOR).$$i"; i=$$((i+1)); done; fi
+	if [ "$(SOSYMLINK)" = "true" ]; then ln -sf "$(SONAME)" "$(DESTDIR)$(LIBPREFIX)/libgrapheme.so.$(VERSION_MAJOR)"; fi
+	if [ "$(SOSYMLINK)" = "true" ]; then ln -sf "$(SONAME)" "$(DESTDIR)$(LIBPREFIX)/libgrapheme.so"; fi
+	cp -f grapheme.h "$(DESTDIR)$(INCPREFIX)"
+	if ! [ -z "$(LDCONFIG)" ]; then $(SHELL) -c "$(LDCONFIG)"; fi
+	if ! [ -z "$(PCPREFIX)" ]; then mkdir -p "$(DESTDIR)$(PCPREFIX)"; printf "Name: libgrapheme\nDescription: Unicode string library\nURL: https://libs.suckless.org/libgrapheme/\nVersion: $(VERSION)\nCflags: -I$(INCPREFIX)\nLibs: -L$(LIBPREFIX) -lgrapheme\n" > "$(DESTDIR)$(PCPREFIX)/libgrapheme.pc"; fi
+
+uninstall:
+	for m in $(MAN3:=.3); do rm -f "$(DESTDIR)$(MANPREFIX)/man3/`basename $$m`"; done
+	for m in $(MAN7:=.7); do rm -f "$(DESTDIR)$(MANPREFIX)/man7/`basename $$m`"; done
+	rm -f "$(DESTDIR)$(LIBPREFIX)/libgrapheme.a"
+	rm -f "$(DESTDIR)$(LIBPREFIX)/$(SONAME)"
+	if [ "$(SOSYMLINK)" = "true" ]; then i=0; while [ "$$i" -le $(VERSION_MINOR) ]; do rm -f "$(DESTDIR)$(LIBPREFIX)/libgrapheme.so.$(VERSION_MAJOR).$$i"; i=$$((i+1)); done; fi
+	if [ "$(SOSYMLINK)" = "true" ]; then rm -f "$(DESTDIR)$(LIBPREFIX)/libgrapheme.so.$(VERSION_MAJOR)"; fi
+	if [ "$(SOSYMLINK)" = "true" ]; then rm -f "$(DESTDIR)$(LIBPREFIX)/libgrapheme.so"; fi
+	rm -f "$(DESTDIR)$(INCPREFIX)/grapheme.h"
+	if ! [ -z "$(LDCONFIG)" ]; then $(SHELL) -c "$(LDCONFIG)"; fi
+	if ! [ -z "$(PCPREFIX)" ]; then rm -f "$(DESTDIR)$(PCPREFIX)/libgrapheme.pc"; fi
+
+clean:
+	rm -f $(BENCHMARK:=.o) benchmark/util.o $(BENCHMARK) $(GEN:=.h) $(GEN:=.o) gen/util.o $(GEN) $(SRC:=.o) src/util.o $(TEST:=.o) test/util.o $(TEST) libgrapheme.a $(SONAME) $(MAN3:=.3) $(MAN7:=.7)
+
+clean-data:
+	rm -f $(DATA)
+
+dist:
+	rm -rf "libgrapheme-$(VERSION)"
+	mkdir "libgrapheme-$(VERSION)"
+	for m in benchmark data gen man man/template src test; do mkdir "libgrapheme-$(VERSION)/$$m"; done
+	cp config.mk configure grapheme.h LICENSE Makefile README "libgrapheme-$(VERSION)"
+	cp $(BENCHMARK:=.c) benchmark/util.c benchmark/util.h "libgrapheme-$(VERSION)/benchmark"
+	cp $(DATA) "libgrapheme-$(VERSION)/data"
+	cp $(GEN:=.c) gen/util.c gen/types.h gen/util.h "libgrapheme-$(VERSION)/gen"
+	cp $(MAN3:=.sh) $(MAN7:=.sh) "libgrapheme-$(VERSION)/man"
+	cp $(MAN_TEMPLATE) "libgrapheme-$(VERSION)/man/template"
+	cp $(SRC:=.c) src/util.h "libgrapheme-$(VERSION)/src"
+	cp $(TEST:=.c) test/util.c test/util.h "libgrapheme-$(VERSION)/test"
+	tar -cf - "libgrapheme-$(VERSION)" | gzip -c > "libgrapheme-$(VERSION).tar.gz"
+	rm -rf "libgrapheme-$(VERSION)"
+
+.PHONY: all benchmark test install uninstall clean clean-data dist

libs/libgrapheme-2.0.2/README

@@ -0,0 +1,64 @@
+libgrapheme
+===========
+
+libgrapheme is an extremely simple freestanding C99 library providing
+utilities for properly handling strings according to the latest Unicode
+standard 15.0.0. It offers fully Unicode compliant
+
+ - grapheme cluster (i.e. user-perceived character) segmentation
+ - word segmentation
+ - sentence segmentation
+ - detection of permissible line break opportunities
+ - case detection (lower-, upper- and title-case)
+ - case conversion (to lower-, upper- and title-case)
+
+on UTF-8 strings and codepoint arrays, which both can also be
+null-terminated.
+
+The necessary lookup-tables are automatically generated from the Unicode
+standard data (contained in the tarball) and heavily compressed. Over
+10,000 automatically generated conformance tests and over 150 unit tests
+ensure conformance and correctness.
+
+There is no complicated build-system involved and it's all done using one
+POSIX-compliant Makefile. All you need is a C99 compiler, given the
+lookup-table-generators and compressors are also written in C99. The
+resulting library is freestanding and thus not even dependent on a
+standard library to be present at runtime, making it a suitable choice
+for bare metal applications.
+
+It is also way smaller and much faster than the other established
+Unicode string libraries (ICU, GNU's libunistring, libutf8proc).
+
+Requirements
+------------
+A C99-compiler and POSIX make.
+
+Installation
+------------
+Run ./configure, which automatically edits config.mk to match your local
+setup. Edit config.mk by hand if necessary or desired for further
+customization.
+
+Afterwards enter the following command to build and install libgrapheme
+(if necessary as root):
+
+	make install
+
+Conformance
+-----------
+The libgrapheme library is compliant with the Unicode 15.0.0
+specification (September 2022). The tests can be run with
+
+	make test
+
+to check standard conformance and correctness.
+
+Usage
+-----
+Include the header grapheme.h in your code and link against libgrapheme
+with "-lgrapheme" either statically ("-static") or dynamically.
+
+Author
+------
+Laslo Hunhold <dev@frign.de>

libs/libgrapheme-2.0.2/benchmark/case.c

@@ -0,0 +1,55 @@
+/* See LICENSE file for copyright and license details. */
+#include <errno.h>
+#include <math.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../grapheme.h"
+#include "../gen/word-test.h"
+#include "util.h"
+
+#define NUM_ITERATIONS 10000
+
+struct break_benchmark_payload {
+	uint_least32_t *src;
+	size_t srclen;
+	uint_least32_t *dest;
+	size_t destlen;
+};
+
+void
+libgrapheme(const void *payload)
+{
+	const struct break_benchmark_payload *p = payload;
+
+	grapheme_to_uppercase(p->src, p->srclen, p->dest, p->destlen);
+}
+
+int
+main(int argc, char *argv[])
+{
+	struct break_benchmark_payload p;
+	double baseline = (double)NAN;
+
+	(void)argc;
+
+	if ((p.src = generate_cp_test_buffer(word_break_test,
+	                                     LEN(word_break_test),
+	                                     &(p.srclen))) == NULL) {
+		return 1;
+	}
+	if ((p.dest = calloc((p.destlen = 2 * p.srclen), sizeof(*(p.dest)))) == NULL) {
+		fprintf(stderr, "calloc: Out of memory\n");
+	}
+
+	printf("%s\n", argv[0]);
+	run_benchmark(libgrapheme, &p, "libgrapheme ", NULL, "codepoint",
+	              &baseline, NUM_ITERATIONS, p.srclen - 1);
+
+	free(p.src);
+	free(p.dest);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/benchmark/character.c

@@ -0,0 +1,86 @@
+/* See LICENSE file for copyright and license details. */
+#include <errno.h>
+#include <math.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../grapheme.h"
+#include "../gen/character-test.h"
+#include "util.h"
+
+#include <utf8proc.h>
+
+#define NUM_ITERATIONS 100000
+
+struct break_benchmark_payload {
+	uint_least32_t *buf;
+	utf8proc_int32_t *buf_utf8proc;
+	size_t buflen;
+};
+
+void
+libgrapheme(const void *payload)
+{
+	uint_least16_t state = 0;
+	const struct break_benchmark_payload *p = payload;
+	size_t i;
+
+	for (i = 0; i + 1 < p->buflen; i++) {
+		(void)grapheme_is_character_break(p->buf[i], p->buf[i+1],
+		                                  &state);
+	}
+}
+
+void
+libutf8proc(const void *payload)
+{
+	utf8proc_int32_t state = 0;
+	const struct break_benchmark_payload *p = payload;
+	size_t i;
+
+	for (i = 0; i + 1 < p->buflen; i++) {
+		(void)utf8proc_grapheme_break_stateful(p->buf_utf8proc[i],
+		                                       p->buf_utf8proc[i+1],
+		                                       &state);
+	}
+}
+
+int
+main(int argc, char *argv[])
+{
+	struct break_benchmark_payload p;
+	double baseline = (double)NAN;
+	size_t i;
+
+	(void)argc;
+
+	if ((p.buf = generate_cp_test_buffer(character_break_test,
+	                                     LEN(character_break_test),
+	                                     &(p.buflen))) == NULL) {
+		return 1;
+	}
+	if ((p.buf_utf8proc = malloc(p.buflen * sizeof(*(p.buf_utf8proc)))) == NULL) {
+		fprintf(stderr, "malloc: %s\n", strerror(errno));
+		exit(1);
+	}
+	for (i = 0; i < p.buflen; i++) {
+		/*
+		 * there is no overflow, as we know that the maximum
+		 * codepoint is 0x10FFFF, which is way below 2^31
+		 */
+		p.buf_utf8proc[i] = (utf8proc_int32_t)p.buf[i];
+	}
+
+	printf("%s\n", argv[0]);
+	run_benchmark(libgrapheme, &p, "libgrapheme ", NULL, "comparison",
+	              &baseline, NUM_ITERATIONS, p.buflen - 1);
+	run_benchmark(libutf8proc, &p, "libutf8proc ", NULL, "comparison",
+	              &baseline, NUM_ITERATIONS, p.buflen - 1);
+
+	free(p.buf);
+	free(p.buf_utf8proc);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/benchmark/line.c

@@ -0,0 +1,52 @@
+/* See LICENSE file for copyright and license details. */
+#include <errno.h>
+#include <math.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../grapheme.h"
+#include "../gen/line-test.h"
+#include "util.h"
+
+#define NUM_ITERATIONS 10000
+
+struct break_benchmark_payload {
+	uint_least32_t *buf;
+	size_t buflen;
+};
+
+void
+libgrapheme(const void *payload)
+{
+	const struct break_benchmark_payload *p = payload;
+	size_t off;
+
+	for (off = 0; off < p->buflen; ) {
+		off += grapheme_next_line_break(p->buf + off, p->buflen - off);
+	}
+}
+
+int
+main(int argc, char *argv[])
+{
+	struct break_benchmark_payload p;
+	double baseline = (double)NAN;
+
+	(void)argc;
+
+	if ((p.buf = generate_cp_test_buffer(line_break_test,
+	                                     LEN(line_break_test),
+	                                     &(p.buflen))) == NULL) {
+		return 1;
+	}
+
+	printf("%s\n", argv[0]);
+	run_benchmark(libgrapheme, &p, "libgrapheme ", NULL, "codepoint",
+	              &baseline, NUM_ITERATIONS, p.buflen - 1);
+
+	free(p.buf);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/benchmark/sentence.c

@@ -0,0 +1,52 @@
+/* See LICENSE file for copyright and license details. */
+#include <errno.h>
+#include <math.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../grapheme.h"
+#include "../gen/sentence-test.h"
+#include "util.h"
+
+#define NUM_ITERATIONS 100000
+
+struct break_benchmark_payload {
+	uint_least32_t *buf;
+	size_t buflen;
+};
+
+void
+libgrapheme(const void *payload)
+{
+	const struct break_benchmark_payload *p = payload;
+	size_t off;
+
+	for (off = 0; off < p->buflen; ) {
+		off += grapheme_next_sentence_break(p->buf + off, p->buflen - off);
+	}
+}
+
+int
+main(int argc, char *argv[])
+{
+	struct break_benchmark_payload p;
+	double baseline = (double)NAN;
+
+	(void)argc;
+
+	if ((p.buf = generate_cp_test_buffer(sentence_break_test,
+	                                     LEN(sentence_break_test),
+	                                     &(p.buflen))) == NULL) {
+		return 1;
+	}
+
+	printf("%s\n", argv[0]);
+	run_benchmark(libgrapheme, &p, "libgrapheme ", NULL, "codepoint",
+	              &baseline, NUM_ITERATIONS, p.buflen - 1);
+
+	free(p.buf);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/benchmark/utf8-decode.c

@@ -0,0 +1,95 @@
+/* See LICENSE file for copyright and license details. */
+#include <errno.h>
+#include <math.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../grapheme.h"
+#include "../gen/character-test.h"
+#include "util.h"
+
+#include <utf8proc.h>
+
+#define NUM_ITERATIONS 100000
+
+struct utf8_benchmark_payload {
+	char *buf;
+	utf8proc_uint8_t *buf_utf8proc;
+	size_t buflen;
+};
+
+void
+libgrapheme(const void *payload)
+{
+	const struct utf8_benchmark_payload *p = payload;
+	uint_least32_t cp;
+	size_t ret, off;
+
+	for (off = 0; off < p->buflen; off += ret) {
+		if ((ret = grapheme_decode_utf8(p->buf + off,
+		                                p->buflen - off, &cp)) >
+		    (p->buflen - off)) {
+			break;
+		}
+		(void)cp;
+	}
+}
+
+void
+libutf8proc(const void *payload)
+{
+	const struct utf8_benchmark_payload *p = payload;
+	utf8proc_int32_t cp;
+	utf8proc_ssize_t ret;
+	size_t off;
+
+	for (off = 0; off < p->buflen; off += (size_t)ret) {
+		if ((ret = utf8proc_iterate(p->buf_utf8proc + off,
+		                            (utf8proc_ssize_t)(p->buflen - off),
+				            &cp)) < 0) {
+			break;
+		}
+		(void)cp;
+	}
+}
+
+int
+main(int argc, char *argv[])
+{
+	struct utf8_benchmark_payload p;
+	size_t i;
+	double baseline = (double)NAN;
+
+	(void)argc;
+
+	p.buf = generate_utf8_test_buffer(character_break_test,
+	                                  LEN(character_break_test),
+	                                  &(p.buflen));
+
+	/* convert cp-buffer to stupid custom libutf8proc-uint8-type */
+	if ((p.buf_utf8proc = malloc(p.buflen)) == NULL) {
+		fprintf(stderr, "malloc: %s\n", strerror(errno));
+		exit(1);
+	}
+	for (i = 0; i < p.buflen; i++) {
+		/* 
+		 * even if char is larger than 8 bit, it will only have
+		 * any of the first 8 bits set (by construction).
+		 */
+		p.buf_utf8proc[i] = (utf8proc_uint8_t)p.buf[i];
+	}
+
+	printf("%s\n", argv[0]);
+	run_benchmark(libgrapheme, &p, "libgrapheme ", NULL,
+	              "byte", &baseline, NUM_ITERATIONS, p.buflen);
+	run_benchmark(libutf8proc, &p, "libutf8proc ",
+	              "but unsafe (does not detect overlong encodings)",
+	              "byte", &baseline, NUM_ITERATIONS, p.buflen);
+
+	free(p.buf);
+	free(p.buf_utf8proc);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/benchmark/util.c

@@ -0,0 +1,115 @@
+/* See LICENSE file for copyright and license details. */
+#include <math.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <time.h>
+
+#include "../gen/types.h"
+#include "../grapheme.h"
+#include "util.h"
+
+uint_least32_t *
+generate_cp_test_buffer(const struct break_test *test, size_t testlen,
+                        size_t *buflen)
+{
+	size_t i, j, off;
+	uint_least32_t *buf;
+
+	/* allocate and generate buffer */
+	for (i = 0, *buflen = 0; i < testlen; i++) {
+		*buflen += test[i].cplen;
+	}
+	if (!(buf = calloc(*buflen, sizeof(*buf)))) {
+		fprintf(stderr, "generate_test_buffer: calloc: Out of memory.\n");
+		exit(1);
+	}
+	for (i = 0, off = 0; i < testlen; i++) {
+		for (j = 0; j < test[i].cplen; j++) {
+			buf[off + j] = test[i].cp[j];
+		}
+		off += test[i].cplen;
+	}
+
+	return buf;
+}
+
+char *
+generate_utf8_test_buffer(const struct break_test *test, size_t testlen,
+                          size_t *buflen)
+{
+	size_t i, j, off, ret;
+	char *buf;
+
+	/* allocate and generate buffer */
+	for (i = 0, *buflen = 0; i < testlen; i++) {
+		for (j = 0; j < test[i].cplen; j++) {
+			*buflen += grapheme_encode_utf8(test[i].cp[j], NULL, 0);
+		}
+	}
+	(*buflen)++; /* terminating NUL-byte */
+	if (!(buf = malloc(*buflen))) {
+		fprintf(stderr, "generate_test_buffer: malloc: Out of memory.\n");
+		exit(1);
+	}
+	for (i = 0, off = 0; i < testlen; i++) {
+		for (j = 0; j < test[i].cplen; j++, off += ret) {
+			if ((ret = grapheme_encode_utf8(test[i].cp[j],
+			                                buf + off,
+			                                *buflen - off)) >
+			    (*buflen - off)) {
+				/* shouldn't happen */
+				fprintf(stderr, "generate_utf8_test_buffer: "
+				        "Buffer too small.\n");
+				exit(1);
+			}
+		}
+	}
+	buf[*buflen - 1] = '\0';
+
+	return buf;
+}
+
+static double
+time_diff(struct timespec *a, struct timespec *b)
+{
+	return (double)(b->tv_sec - a->tv_sec) +
+	       (double)(b->tv_nsec - a->tv_nsec) * 1E-9;
+}
+
+void
+run_benchmark(void (*func)(const void *), const void *payload,
+              const char *name, const char *comment, const char *unit,
+              double *baseline, size_t num_iterations,
+              size_t units_per_iteration)
+{
+	struct timespec start, end;
+	size_t i;
+	double diff;
+
+	printf("\t%s ", name);
+	fflush(stdout);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	for (i = 0; i < num_iterations; i++) {
+		func(payload);
+
+		if (i % (num_iterations / 10) == 0) {
+			printf(".");
+			fflush(stdout);
+		}
+	}
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	diff = time_diff(&start, &end) / (double)num_iterations /
+	       (double)units_per_iteration;
+
+	if (isnan(*baseline)) {
+		*baseline = diff;
+		printf(" avg. %.3es/%s (baseline)\n", diff, unit);
+	} else {
+		printf(" avg. %.3es/%s (%.2f%% %s%s%s)\n", diff, unit,
+		       fabs(1.0 - diff / *baseline) * 100,
+		       (diff < *baseline) ? "faster" : "slower",
+		       comment ? ", " : "",
+		       comment ? comment : "");
+	}
+}

libs/libgrapheme-2.0.2/benchmark/util.h

@@ -0,0 +1,23 @@
+/* See LICENSE file for copyright and license details. */
+#ifndef UTIL_H
+#define UTIL_H
+
+#include "../gen/types.h"
+
+#define LEN(x) (sizeof(x) / sizeof(*(x)))
+
+#ifdef __has_attribute
+	#if __has_attribute(optnone)
+		void libgrapheme(const void *) __attribute__((optnone));
+		void libutf8proc(const void *) __attribute__((optnone));
+	#endif
+#endif
+
+uint_least32_t *generate_cp_test_buffer(const struct break_test *, size_t,
+                                        size_t *);
+char *generate_utf8_test_buffer(const struct break_test *, size_t, size_t *);
+
+void run_benchmark(void (*func)(const void *), const void *, const char *,
+                   const char *, const char *, double *, size_t, size_t);
+
+#endif /* UTIL_H */

libs/libgrapheme-2.0.2/benchmark/word.c

@@ -0,0 +1,52 @@
+/* See LICENSE file for copyright and license details. */
+#include <errno.h>
+#include <math.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "../grapheme.h"
+#include "../gen/word-test.h"
+#include "util.h"
+
+#define NUM_ITERATIONS 10000
+
+struct break_benchmark_payload {
+	uint_least32_t *buf;
+	size_t buflen;
+};
+
+void
+libgrapheme(const void *payload)
+{
+	const struct break_benchmark_payload *p = payload;
+	size_t off;
+
+	for (off = 0; off < p->buflen; ) {
+		off += grapheme_next_word_break(p->buf + off, p->buflen - off);
+	}
+}
+
+int
+main(int argc, char *argv[])
+{
+	struct break_benchmark_payload p;
+	double baseline = (double)NAN;
+
+	(void)argc;
+
+	if ((p.buf = generate_cp_test_buffer(word_break_test,
+	                                     LEN(word_break_test),
+	                                     &(p.buflen))) == NULL) {
+		return 1;
+	}
+
+	printf("%s\n", argv[0]);
+	run_benchmark(libgrapheme, &p, "libgrapheme ", NULL, "codepoint",
+	              &baseline, NUM_ITERATIONS, p.buflen - 1);
+
+	free(p.buf);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/config.mk

@@ -0,0 +1,32 @@
+# Customize below to fit your system (run ./configure for automatic presets)
+
+# paths (unset $PCPREFIX to not install a pkg-config-file)
+DESTDIR   =
+PREFIX    = /usr/local
+INCPREFIX = $(PREFIX)/include
+LIBPREFIX = $(PREFIX)/lib
+MANPREFIX = $(PREFIX)/share/man
+PCPREFIX  = $(LIBPREFIX)/pkgconfig
+
+# flags
+CPPFLAGS = -D_DEFAULT_SOURCE
+CFLAGS   = -std=c99 -Os -Wall -Wextra -Wpedantic
+LDFLAGS  = -s
+
+BUILD_CPPFLAGS = $(CPPFLAGS)
+BUILD_CFLAGS   = $(CFLAGS)
+BUILD_LDFLAGS  = $(LDFLAGS)
+
+SHFLAGS   = -fPIC -ffreestanding
+
+SOFLAGS   = -shared -nostdlib -Wl,--soname=libgrapheme.so.$(VERSION_MAJOR).$(VERSION_MINOR)
+SONAME    = libgrapheme.so.$(VERSION_MAJOR).$(VERSION_MINOR).$(VERSION_PATCH)
+SOSYMLINK = true
+
+# tools (unset $LDCONFIG to not call ldconfig(1) after install/uninstall)
+CC       = cc
+BUILD_CC = $(CC)
+AR       = ar
+RANLIB   = ranlib
+LDCONFIG = ldconfig
+SH       = sh

libs/libgrapheme-2.0.2/configure

@@ -0,0 +1,39 @@
+#!/bin/sh
+# See LICENSE file for copyright and license details.
+
+replace_line()
+{
+	VAR=$1
+	ALIGNMENT=$2
+	VALUE=$3
+	awk "/^${VAR}[ ]*=/ { print \"${VAR}${ALIGNMENT} = ${VALUE}\"; next }; { print; }" config.mk > config.mk.tmp
+	mv config.mk.tmp config.mk
+}
+
+case $(uname) in
+	DragonFly|FreeBSD|Linux|MidnightBSD|NetBSD)
+		# the default
+		replace_line 'SOFLAGS'   '  '  '-shared -nostdlib -Wl,--soname=libgrapheme.so.$(VERSION_MAJOR).$(VERSION_MINOR)'
+		replace_line 'SONAME'    '   ' 'libgrapheme.so.$(VERSION_MAJOR).$(VERSION_MINOR).$(VERSION_PATCH)'
+		replace_line 'SOSYMLINK' ''    'true'
+		replace_line 'LDCONFIG'  ''    'ldconfig'
+		;;
+	OpenBSD)
+		replace_line 'SOFLAGS'   '  '  '-shared -nostdlib'
+		replace_line 'SONAME'    '   ' 'libgrapheme.so.$(VERSION_MAJOR).$(VERSION_MINOR)'
+		replace_line 'SOSYMLINK' ''    'false'
+		replace_line 'LDCONFIG'  ''    ''
+		;;
+	Darwin)
+		replace_line 'SOFLAGS'   '  '  '-dynamiclib -install_name libgrapheme.$(VERSION_MAJOR).dylib -current_version $(VERSION_MAJOR).$(VERSION_MINOR).$(VERSION_PATCH) -compatibility_version $(VERSION_MAJOR).$(VERSION_MINOR).0'
+		replace_line 'SONAME'    '   ' 'libgrapheme.$(VERSION_MAJOR).dylib'
+		replace_line 'SOSYMLINK' ''    'false'
+		replace_line 'LDCONFIG'  ''    ''
+		;;
+	*)
+		echo "Your system does not have a preset. Edit config.mk and send a patch please! :)"
+		exit 1
+		;;
+esac
+
+exit 0

libs/libgrapheme-2.0.2/data/GraphemeBreakTest.txt

@@ -0,0 +1,630 @@
+# GraphemeBreakTest-15.0.0.txt
+# Date: 2022-02-26, 00:38:37 GMT
+# © 2022 Unicode®, Inc.
+# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
+# For terms of use, see https://www.unicode.org/terms_of_use.html
+#
+# Unicode Character Database
+#   For documentation, see https://www.unicode.org/reports/tr44/
+#
+# Default Grapheme_Cluster_Break Test
+#
+# Format:
+# <string> (# <comment>)?
+#  <string> contains hex Unicode code points, with
+#	÷ wherever there is a break opportunity, and
+#	× wherever there is not.
+#  <comment> the format can change, but currently it shows:
+#	- the sample character name
+#	- (x) the Grapheme_Cluster_Break property value for the sample character
+#	- [x] the rule that determines whether there is a break or not,
+#	   as listed in the Rules section of GraphemeBreakTest.html
+#
+# These samples may be extended or changed in the future.
+#
+÷ 0020 ÷ 0020 ÷	#  ÷ [0.2] SPACE (Other) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 0020 × 0308 ÷ 0020 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 0020 ÷ 000D ÷	#  ÷ [0.2] SPACE (Other) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0020 × 0308 ÷ 000D ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0020 ÷ 000A ÷	#  ÷ [0.2] SPACE (Other) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0020 × 0308 ÷ 000A ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0020 ÷ 0001 ÷	#  ÷ [0.2] SPACE (Other) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0020 × 0308 ÷ 0001 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0020 × 034F ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0020 × 0308 × 034F ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0020 ÷ 1F1E6 ÷	#  ÷ [0.2] SPACE (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0020 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0020 ÷ 0600 ÷	#  ÷ [0.2] SPACE (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0020 × 0308 ÷ 0600 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0020 × 0903 ÷	#  ÷ [0.2] SPACE (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0020 × 0308 × 0903 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0020 ÷ 1100 ÷	#  ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0020 × 0308 ÷ 1100 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0020 ÷ 1160 ÷	#  ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0020 × 0308 ÷ 1160 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0020 ÷ 11A8 ÷	#  ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0020 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0020 ÷ AC00 ÷	#  ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0020 × 0308 ÷ AC00 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0020 ÷ AC01 ÷	#  ÷ [0.2] SPACE (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0020 × 0308 ÷ AC01 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0020 ÷ 231A ÷	#  ÷ [0.2] SPACE (Other) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0020 × 0308 ÷ 231A ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0020 × 0300 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0020 × 0308 × 0300 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0020 × 200D ÷	#  ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0020 × 0308 × 200D ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0020 ÷ 0378 ÷	#  ÷ [0.2] SPACE (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 0020 × 0308 ÷ 0378 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 000D ÷ 0020 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] SPACE (Other) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 0020 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 000D ÷ 000D ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 000D ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 000D × 000A ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 000A ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 000D ÷ 0001 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 0001 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 000D ÷ 034F ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 000D ÷ 0308 × 034F ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 000D ÷ 1F1E6 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 000D ÷ 0600 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 0600 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 000D ÷ 0903 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 000D ÷ 0308 × 0903 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 000D ÷ 1100 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 1100 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 000D ÷ 1160 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 1160 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 000D ÷ 11A8 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 11A8 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 000D ÷ AC00 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ AC00 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 000D ÷ AC01 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ AC01 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 000D ÷ 231A ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] WATCH (ExtPict) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 231A ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 000D ÷ 0300 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 000D ÷ 0308 × 0300 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 000D ÷ 200D ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 000D ÷ 0308 × 200D ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 000D ÷ 0378 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 000D ÷ 0308 ÷ 0378 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 000A ÷ 0020 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] SPACE (Other) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 0020 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 000A ÷ 000D ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 000D ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 000A ÷ 000A ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 000A ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 000A ÷ 0001 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 0001 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 000A ÷ 034F ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 000A ÷ 0308 × 034F ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 000A ÷ 1F1E6 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 000A ÷ 0600 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 0600 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 000A ÷ 0903 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 000A ÷ 0308 × 0903 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 000A ÷ 1100 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 1100 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 000A ÷ 1160 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 1160 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 000A ÷ 11A8 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 11A8 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 000A ÷ AC00 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ AC00 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 000A ÷ AC01 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ AC01 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 000A ÷ 231A ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] WATCH (ExtPict) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 231A ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 000A ÷ 0300 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 000A ÷ 0308 × 0300 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 000A ÷ 200D ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 000A ÷ 0308 × 200D ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 000A ÷ 0378 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 000A ÷ 0308 ÷ 0378 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 0001 ÷ 0020 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] SPACE (Other) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 0020 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 0001 ÷ 000D ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 000D ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0001 ÷ 000A ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 000A ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0001 ÷ 0001 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 0001 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0001 ÷ 034F ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0001 ÷ 0308 × 034F ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0001 ÷ 1F1E6 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0001 ÷ 0600 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 0600 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0001 ÷ 0903 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0001 ÷ 0308 × 0903 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0001 ÷ 1100 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 1100 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0001 ÷ 1160 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 1160 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0001 ÷ 11A8 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 11A8 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0001 ÷ AC00 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ AC00 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0001 ÷ AC01 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ AC01 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0001 ÷ 231A ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 231A ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0001 ÷ 0300 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0001 ÷ 0308 × 0300 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0001 ÷ 200D ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0001 ÷ 0308 × 200D ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0001 ÷ 0378 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 0001 ÷ 0308 ÷ 0378 ÷	#  ÷ [0.2] <START OF HEADING> (Control) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 034F ÷ 0020 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 034F × 0308 ÷ 0020 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 034F ÷ 000D ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 034F × 0308 ÷ 000D ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 034F ÷ 000A ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 034F × 0308 ÷ 000A ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 034F ÷ 0001 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 034F × 0308 ÷ 0001 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 034F × 034F ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 034F × 0308 × 034F ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 034F ÷ 1F1E6 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 034F × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 034F ÷ 0600 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 034F × 0308 ÷ 0600 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 034F × 0903 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 034F × 0308 × 0903 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 034F ÷ 1100 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 034F × 0308 ÷ 1100 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 034F ÷ 1160 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 034F × 0308 ÷ 1160 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 034F ÷ 11A8 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 034F × 0308 ÷ 11A8 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 034F ÷ AC00 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 034F × 0308 ÷ AC00 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 034F ÷ AC01 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 034F × 0308 ÷ AC01 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 034F ÷ 231A ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 034F × 0308 ÷ 231A ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 034F × 0300 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 034F × 0308 × 0300 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 034F × 200D ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 034F × 0308 × 200D ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 034F ÷ 0378 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 034F × 0308 ÷ 0378 ÷	#  ÷ [0.2] COMBINING GRAPHEME JOINER (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 1F1E6 ÷ 0020 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 0020 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 1F1E6 ÷ 000D ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 000D ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 1F1E6 ÷ 000A ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 000A ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 1F1E6 ÷ 0001 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 0001 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 1F1E6 × 034F ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 1F1E6 × 0308 × 034F ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 1F1E6 × 1F1E6 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [12.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 1F1E6 ÷ 0600 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 0600 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 1F1E6 × 0903 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 1F1E6 × 0308 × 0903 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 1F1E6 ÷ 1100 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 1100 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 1F1E6 ÷ 1160 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 1160 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 1F1E6 ÷ 11A8 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 1F1E6 ÷ AC00 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ AC00 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 1F1E6 ÷ AC01 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ AC01 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 1F1E6 ÷ 231A ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 231A ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 1F1E6 × 0300 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 1F1E6 × 0308 × 0300 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 1F1E6 × 200D ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 1F1E6 × 0308 × 200D ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 1F1E6 ÷ 0378 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 1F1E6 × 0308 ÷ 0378 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 0600 × 0020 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] SPACE (Other) ÷ [0.3]
+÷ 0600 × 0308 ÷ 0020 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 0600 ÷ 000D ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0600 × 0308 ÷ 000D ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0600 ÷ 000A ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0600 × 0308 ÷ 000A ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0600 ÷ 0001 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0600 × 0308 ÷ 0001 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0600 × 034F ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0600 × 0308 × 034F ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0600 × 1F1E6 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0600 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0600 × 0600 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0600 × 0308 ÷ 0600 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0600 × 0903 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0600 × 0308 × 0903 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0600 × 1100 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0600 × 0308 ÷ 1100 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0600 × 1160 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0600 × 0308 ÷ 1160 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0600 × 11A8 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0600 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0600 × AC00 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0600 × 0308 ÷ AC00 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0600 × AC01 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0600 × 0308 ÷ AC01 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0600 × 231A ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] WATCH (ExtPict) ÷ [0.3]
+÷ 0600 × 0308 ÷ 231A ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0600 × 0300 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0600 × 0308 × 0300 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0600 × 200D ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0600 × 0308 × 200D ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0600 × 0378 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.2] <reserved-0378> (Other) ÷ [0.3]
+÷ 0600 × 0308 ÷ 0378 ÷	#  ÷ [0.2] ARABIC NUMBER SIGN (Prepend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 0903 ÷ 0020 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 0903 × 0308 ÷ 0020 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 0903 ÷ 000D ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0903 × 0308 ÷ 000D ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0903 ÷ 000A ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0903 × 0308 ÷ 000A ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0903 ÷ 0001 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0903 × 0308 ÷ 0001 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0903 × 034F ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0903 × 0308 × 034F ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0903 ÷ 1F1E6 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0903 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0903 ÷ 0600 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0903 × 0308 ÷ 0600 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0903 × 0903 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0903 × 0308 × 0903 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0903 ÷ 1100 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0903 × 0308 ÷ 1100 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0903 ÷ 1160 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0903 × 0308 ÷ 1160 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0903 ÷ 11A8 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0903 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0903 ÷ AC00 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0903 × 0308 ÷ AC00 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0903 ÷ AC01 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0903 × 0308 ÷ AC01 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0903 ÷ 231A ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0903 × 0308 ÷ 231A ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0903 × 0300 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0903 × 0308 × 0300 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0903 × 200D ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0903 × 0308 × 200D ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0903 ÷ 0378 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 0903 × 0308 ÷ 0378 ÷	#  ÷ [0.2] DEVANAGARI SIGN VISARGA (SpacingMark) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 1100 ÷ 0020 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 1100 × 0308 ÷ 0020 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 1100 ÷ 000D ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 1100 × 0308 ÷ 000D ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 1100 ÷ 000A ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 1100 × 0308 ÷ 000A ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 1100 ÷ 0001 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 1100 × 0308 ÷ 0001 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 1100 × 034F ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 1100 × 0308 × 034F ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 1100 ÷ 1F1E6 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 1100 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 1100 ÷ 0600 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 1100 × 0308 ÷ 0600 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 1100 × 0903 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 1100 × 0308 × 0903 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 1100 × 1100 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 1100 × 0308 ÷ 1100 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 1100 × 1160 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 1100 × 0308 ÷ 1160 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 1100 ÷ 11A8 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 1100 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 1100 × AC00 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 1100 × 0308 ÷ AC00 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 1100 × AC01 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 1100 × 0308 ÷ AC01 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 1100 ÷ 231A ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 1100 × 0308 ÷ 231A ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 1100 × 0300 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 1100 × 0308 × 0300 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 1100 × 200D ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 1100 × 0308 × 200D ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 1100 ÷ 0378 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 1100 × 0308 ÷ 0378 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 1160 ÷ 0020 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 1160 × 0308 ÷ 0020 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 1160 ÷ 000D ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 1160 × 0308 ÷ 000D ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 1160 ÷ 000A ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 1160 × 0308 ÷ 000A ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 1160 ÷ 0001 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 1160 × 0308 ÷ 0001 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 1160 × 034F ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 1160 × 0308 × 034F ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 1160 ÷ 1F1E6 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 1160 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 1160 ÷ 0600 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 1160 × 0308 ÷ 0600 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 1160 × 0903 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 1160 × 0308 × 0903 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 1160 ÷ 1100 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 1160 × 0308 ÷ 1100 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 1160 × 1160 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [7.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 1160 × 0308 ÷ 1160 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 1160 × 11A8 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [7.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 1160 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 1160 ÷ AC00 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 1160 × 0308 ÷ AC00 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 1160 ÷ AC01 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 1160 × 0308 ÷ AC01 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 1160 ÷ 231A ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 1160 × 0308 ÷ 231A ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 1160 × 0300 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 1160 × 0308 × 0300 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 1160 × 200D ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 1160 × 0308 × 200D ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 1160 ÷ 0378 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 1160 × 0308 ÷ 0378 ÷	#  ÷ [0.2] HANGUL JUNGSEONG FILLER (V) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 11A8 ÷ 0020 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 0020 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 11A8 ÷ 000D ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 000D ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 11A8 ÷ 000A ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 000A ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 11A8 ÷ 0001 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 0001 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 11A8 × 034F ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 11A8 × 0308 × 034F ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 11A8 ÷ 1F1E6 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 11A8 ÷ 0600 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 0600 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 11A8 × 0903 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 11A8 × 0308 × 0903 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 11A8 ÷ 1100 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 1100 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 11A8 ÷ 1160 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 1160 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 11A8 × 11A8 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [8.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 11A8 ÷ AC00 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 11A8 × 0308 ÷ AC00 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 11A8 ÷ AC01 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 11A8 × 0308 ÷ AC01 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 11A8 ÷ 231A ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 231A ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 11A8 × 0300 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 11A8 × 0308 × 0300 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 11A8 × 200D ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 11A8 × 0308 × 200D ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 11A8 ÷ 0378 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 11A8 × 0308 ÷ 0378 ÷	#  ÷ [0.2] HANGUL JONGSEONG KIYEOK (T) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ AC00 ÷ 0020 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ AC00 × 0308 ÷ 0020 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ AC00 ÷ 000D ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ AC00 × 0308 ÷ 000D ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ AC00 ÷ 000A ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ AC00 × 0308 ÷ 000A ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ AC00 ÷ 0001 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ AC00 × 0308 ÷ 0001 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ AC00 × 034F ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ AC00 × 0308 × 034F ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ AC00 ÷ 1F1E6 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ AC00 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ AC00 ÷ 0600 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ AC00 × 0308 ÷ 0600 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ AC00 × 0903 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ AC00 × 0308 × 0903 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ AC00 ÷ 1100 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ AC00 × 0308 ÷ 1100 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ AC00 × 1160 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [7.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ AC00 × 0308 ÷ 1160 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ AC00 × 11A8 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [7.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ AC00 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ AC00 ÷ AC00 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ AC00 × 0308 ÷ AC00 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ AC00 ÷ AC01 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ AC00 × 0308 ÷ AC01 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ AC00 ÷ 231A ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ AC00 × 0308 ÷ 231A ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ AC00 × 0300 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ AC00 × 0308 × 0300 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ AC00 × 200D ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ AC00 × 0308 × 200D ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ AC00 ÷ 0378 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ AC00 × 0308 ÷ 0378 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ AC01 ÷ 0020 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ AC01 × 0308 ÷ 0020 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ AC01 ÷ 000D ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ AC01 × 0308 ÷ 000D ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ AC01 ÷ 000A ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ AC01 × 0308 ÷ 000A ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ AC01 ÷ 0001 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ AC01 × 0308 ÷ 0001 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ AC01 × 034F ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ AC01 × 0308 × 034F ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ AC01 ÷ 1F1E6 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ AC01 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ AC01 ÷ 0600 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ AC01 × 0308 ÷ 0600 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ AC01 × 0903 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ AC01 × 0308 × 0903 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ AC01 ÷ 1100 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ AC01 × 0308 ÷ 1100 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ AC01 ÷ 1160 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ AC01 × 0308 ÷ 1160 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ AC01 × 11A8 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [8.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ AC01 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ AC01 ÷ AC00 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ AC01 × 0308 ÷ AC00 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ AC01 ÷ AC01 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ AC01 × 0308 ÷ AC01 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ AC01 ÷ 231A ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ AC01 × 0308 ÷ 231A ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ AC01 × 0300 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ AC01 × 0308 × 0300 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ AC01 × 200D ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ AC01 × 0308 × 200D ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ AC01 ÷ 0378 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ AC01 × 0308 ÷ 0378 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 231A ÷ 0020 ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 231A × 0308 ÷ 0020 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 231A ÷ 000D ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 231A × 0308 ÷ 000D ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 231A ÷ 000A ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 231A × 0308 ÷ 000A ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 231A ÷ 0001 ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 231A × 0308 ÷ 0001 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 231A × 034F ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 231A × 0308 × 034F ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 231A ÷ 1F1E6 ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 231A × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 231A ÷ 0600 ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 231A × 0308 ÷ 0600 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 231A × 0903 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 231A × 0308 × 0903 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 231A ÷ 1100 ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 231A × 0308 ÷ 1100 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 231A ÷ 1160 ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 231A × 0308 ÷ 1160 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 231A ÷ 11A8 ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 231A × 0308 ÷ 11A8 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 231A ÷ AC00 ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 231A × 0308 ÷ AC00 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 231A ÷ AC01 ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 231A × 0308 ÷ AC01 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 231A ÷ 231A ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 231A × 0308 ÷ 231A ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 231A × 0300 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 231A × 0308 × 0300 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 231A × 200D ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 231A × 0308 × 200D ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 231A ÷ 0378 ÷	#  ÷ [0.2] WATCH (ExtPict) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 231A × 0308 ÷ 0378 ÷	#  ÷ [0.2] WATCH (ExtPict) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 0300 ÷ 0020 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 0300 × 0308 ÷ 0020 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 0300 ÷ 000D ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0300 × 0308 ÷ 000D ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0300 ÷ 000A ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0300 × 0308 ÷ 000A ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0300 ÷ 0001 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0300 × 0308 ÷ 0001 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0300 × 034F ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0300 × 0308 × 034F ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0300 ÷ 1F1E6 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0300 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0300 ÷ 0600 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0300 × 0308 ÷ 0600 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0300 × 0903 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0300 × 0308 × 0903 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0300 ÷ 1100 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0300 × 0308 ÷ 1100 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0300 ÷ 1160 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0300 × 0308 ÷ 1160 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0300 ÷ 11A8 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0300 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0300 ÷ AC00 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0300 × 0308 ÷ AC00 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0300 ÷ AC01 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0300 × 0308 ÷ AC01 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0300 ÷ 231A ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0300 × 0308 ÷ 231A ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0300 × 0300 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0300 × 0308 × 0300 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0300 × 200D ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0300 × 0308 × 200D ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0300 ÷ 0378 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 0300 × 0308 ÷ 0378 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 200D ÷ 0020 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 200D × 0308 ÷ 0020 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 200D ÷ 000D ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 200D × 0308 ÷ 000D ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 200D ÷ 000A ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 200D × 0308 ÷ 000A ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 200D ÷ 0001 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 200D × 0308 ÷ 0001 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 200D × 034F ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 200D × 0308 × 034F ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 200D ÷ 1F1E6 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 200D × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 200D ÷ 0600 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 200D × 0308 ÷ 0600 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 200D × 0903 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 200D × 0308 × 0903 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 200D ÷ 1100 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 200D × 0308 ÷ 1100 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 200D ÷ 1160 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 200D × 0308 ÷ 1160 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 200D ÷ 11A8 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 200D × 0308 ÷ 11A8 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 200D ÷ AC00 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 200D × 0308 ÷ AC00 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 200D ÷ AC01 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 200D × 0308 ÷ AC01 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 200D ÷ 231A ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 200D × 0308 ÷ 231A ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 200D × 0300 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 200D × 0308 × 0300 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 200D × 200D ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 200D × 0308 × 200D ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 200D ÷ 0378 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 200D × 0308 ÷ 0378 ÷	#  ÷ [0.2] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 0378 ÷ 0020 ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 0378 × 0308 ÷ 0020 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 0378 ÷ 000D ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0378 × 0308 ÷ 000D ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0378 ÷ 000A ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0378 × 0308 ÷ 000A ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0378 ÷ 0001 ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0378 × 0308 ÷ 0001 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [5.0] <START OF HEADING> (Control) ÷ [0.3]
+÷ 0378 × 034F ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0378 × 0308 × 034F ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAPHEME JOINER (Extend) ÷ [0.3]
+÷ 0378 ÷ 1F1E6 ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0378 × 0308 ÷ 1F1E6 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) ÷ [0.3]
+÷ 0378 ÷ 0600 ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0378 × 0308 ÷ 0600 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) ÷ [0.3]
+÷ 0378 × 0903 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0378 × 0308 × 0903 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [0.3]
+÷ 0378 ÷ 1100 ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0378 × 0308 ÷ 1100 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 0378 ÷ 1160 ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0378 × 0308 ÷ 1160 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JUNGSEONG FILLER (V) ÷ [0.3]
+÷ 0378 ÷ 11A8 ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0378 × 0308 ÷ 11A8 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL JONGSEONG KIYEOK (T) ÷ [0.3]
+÷ 0378 ÷ AC00 ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0378 × 0308 ÷ AC00 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GA (LV) ÷ [0.3]
+÷ 0378 ÷ AC01 ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0378 × 0308 ÷ AC01 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] HANGUL SYLLABLE GAG (LVT) ÷ [0.3]
+÷ 0378 ÷ 231A ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0378 × 0308 ÷ 231A ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] WATCH (ExtPict) ÷ [0.3]
+÷ 0378 × 0300 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0378 × 0308 × 0300 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] COMBINING GRAVE ACCENT (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0378 × 200D ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0378 × 0308 × 200D ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0378 ÷ 0378 ÷	#  ÷ [0.2] <reserved-0378> (Other) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 0378 × 0308 ÷ 0378 ÷	#  ÷ [0.2] <reserved-0378> (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] <reserved-0378> (Other) ÷ [0.3]
+÷ 000D × 000A ÷ 0061 ÷ 000A ÷ 0308 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Other) ÷ [5.0] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0061 × 0308 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [0.3]
+÷ 0020 × 200D ÷ 0646 ÷	#  ÷ [0.2] SPACE (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] ARABIC LETTER NOON (Other) ÷ [0.3]
+÷ 0646 × 200D ÷ 0020 ÷	#  ÷ [0.2] ARABIC LETTER NOON (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] SPACE (Other) ÷ [0.3]
+÷ 1100 × 1100 ÷	#  ÷ [0.2] HANGUL CHOSEONG KIYEOK (L) × [6.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ AC00 × 11A8 ÷ 1100 ÷	#  ÷ [0.2] HANGUL SYLLABLE GA (LV) × [7.0] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ AC01 × 11A8 ÷ 1100 ÷	#  ÷ [0.2] HANGUL SYLLABLE GAG (LVT) × [8.0] HANGUL JONGSEONG KIYEOK (T) ÷ [999.0] HANGUL CHOSEONG KIYEOK (L) ÷ [0.3]
+÷ 1F1E6 × 1F1E7 ÷ 1F1E8 ÷ 0062 ÷	#  ÷ [0.2] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [12.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
+÷ 0061 ÷ 1F1E6 × 1F1E7 ÷ 1F1E8 ÷ 0062 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
+÷ 0061 ÷ 1F1E6 × 1F1E7 × 200D ÷ 1F1E8 ÷ 0062 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
+÷ 0061 ÷ 1F1E6 × 200D ÷ 1F1E7 × 1F1E8 ÷ 0062 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
+÷ 0061 ÷ 1F1E6 × 1F1E7 ÷ 1F1E8 × 1F1E9 ÷ 0062 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER A (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER B (RI) ÷ [999.0] REGIONAL INDICATOR SYMBOL LETTER C (RI) × [13.0] REGIONAL INDICATOR SYMBOL LETTER D (RI) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
+÷ 0061 × 200D ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [0.3]
+÷ 0061 × 0308 ÷ 0062 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
+÷ 0061 × 0903 ÷ 0062 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.1] DEVANAGARI SIGN VISARGA (SpacingMark) ÷ [999.0] LATIN SMALL LETTER B (Other) ÷ [0.3]
+÷ 0061 ÷ 0600 × 0062 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) ÷ [999.0] ARABIC NUMBER SIGN (Prepend) × [9.2] LATIN SMALL LETTER B (Other) ÷ [0.3]
+÷ 1F476 × 1F3FF ÷ 1F476 ÷	#  ÷ [0.2] BABY (ExtPict) × [9.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend) ÷ [999.0] BABY (ExtPict) ÷ [0.3]
+÷ 0061 × 1F3FF ÷ 1F476 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend) ÷ [999.0] BABY (ExtPict) ÷ [0.3]
+÷ 0061 × 1F3FF ÷ 1F476 × 200D × 1F6D1 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend) ÷ [999.0] BABY (ExtPict) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [11.0] OCTAGONAL SIGN (ExtPict) ÷ [0.3]
+÷ 1F476 × 1F3FF × 0308 × 200D × 1F476 × 1F3FF ÷	#  ÷ [0.2] BABY (ExtPict) × [9.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend) × [9.0] COMBINING DIAERESIS (Extend_ExtCccZwj) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [11.0] BABY (ExtPict) × [9.0] EMOJI MODIFIER FITZPATRICK TYPE-6 (Extend) ÷ [0.3]
+÷ 1F6D1 × 200D × 1F6D1 ÷	#  ÷ [0.2] OCTAGONAL SIGN (ExtPict) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [11.0] OCTAGONAL SIGN (ExtPict) ÷ [0.3]
+÷ 0061 × 200D ÷ 1F6D1 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] OCTAGONAL SIGN (ExtPict) ÷ [0.3]
+÷ 2701 × 200D × 2701 ÷	#  ÷ [0.2] UPPER BLADE SCISSORS (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) × [11.0] UPPER BLADE SCISSORS (Other) ÷ [0.3]
+÷ 0061 × 200D ÷ 2701 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Other) × [9.0] ZERO WIDTH JOINER (ZWJ_ExtCccZwj) ÷ [999.0] UPPER BLADE SCISSORS (Other) ÷ [0.3]
+#
+# Lines: 602
+#
+# EOF

libs/libgrapheme-2.0.2/data/LICENSE

@@ -0,0 +1,46 @@
+UNICODE, INC. LICENSE AGREEMENT - DATA FILES AND SOFTWARE
+
+See Terms of Use <https://www.unicode.org/copyright.html>
+for definitions of Unicode Inc.’s Data Files and Software.
+
+NOTICE TO USER: Carefully read the following legal agreement.
+BY DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING UNICODE INC.'S
+DATA FILES ("DATA FILES"), AND/OR SOFTWARE ("SOFTWARE"),
+YOU UNEQUIVOCALLY ACCEPT, AND AGREE TO BE BOUND BY, ALL OF THE
+TERMS AND CONDITIONS OF THIS AGREEMENT.
+IF YOU DO NOT AGREE, DO NOT DOWNLOAD, INSTALL, COPY, DISTRIBUTE OR USE
+THE DATA FILES OR SOFTWARE.
+
+COPYRIGHT AND PERMISSION NOTICE
+
+Copyright © 1991-2022 Unicode, Inc. All rights reserved.
+Distributed under the Terms of Use in https://www.unicode.org/copyright.html.
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of the Unicode data files and any associated documentation
+(the "Data Files") or Unicode software and any associated documentation
+(the "Software") to deal in the Data Files or Software
+without restriction, including without limitation the rights to use,
+copy, modify, merge, publish, distribute, and/or sell copies of
+the Data Files or Software, and to permit persons to whom the Data Files
+or Software are furnished to do so, provided that either
+(a) this copyright and permission notice appear with all copies
+of the Data Files or Software, or
+(b) this copyright and permission notice appear in associated
+Documentation.
+
+THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF
+ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
+WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT OF THIRD PARTY RIGHTS.
+IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS
+NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL
+DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
+DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
+PERFORMANCE OF THE DATA FILES OR SOFTWARE.
+
+Except as contained in this notice, the name of a copyright holder
+shall not be used in advertising or otherwise to promote the sale,
+use or other dealings in these Data Files or Software without prior
+written authorization of the copyright holder.

libs/libgrapheme-2.0.2/data/SentenceBreakTest.txt

@@ -0,0 +1,530 @@
+# SentenceBreakTest-15.0.0.txt
+# Date: 2022-02-26, 00:39:00 GMT
+# © 2022 Unicode®, Inc.
+# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
+# For terms of use, see https://www.unicode.org/terms_of_use.html
+#
+# Unicode Character Database
+#   For documentation, see https://www.unicode.org/reports/tr44/
+#
+# Default Sentence_Break Test
+#
+# Format:
+# <string> (# <comment>)?
+#  <string> contains hex Unicode code points, with
+#	÷ wherever there is a break opportunity, and
+#	× wherever there is not.
+#  <comment> the format can change, but currently it shows:
+#	- the sample character name
+#	- (x) the Sentence_Break property value for the sample character
+#	- [x] the rule that determines whether there is a break or not,
+#	   as listed in the Rules section of SentenceBreakTest.html
+#
+# These samples may be extended or changed in the future.
+#
+÷ 0001 × 0001 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0001 × 0308 × 0001 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0001 × 000D ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0001 × 0308 × 000D ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0001 × 000A ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0001 × 0308 × 000A ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0001 × 0085 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0001 × 0308 × 0085 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0001 × 0009 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0001 × 0308 × 0009 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0001 × 0061 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0001 × 0308 × 0061 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0001 × 0041 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0001 × 0308 × 0041 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0001 × 01BB ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0001 × 0308 × 01BB ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0001 × 0030 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0001 × 0308 × 0030 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0001 × 002E ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0001 × 0308 × 002E ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0001 × 0021 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0001 × 0308 × 0021 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0001 × 0022 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0001 × 0308 × 0022 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0001 × 002C ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0001 × 0308 × 002C ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0001 × 00AD ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0001 × 0308 × 00AD ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0001 × 0300 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0001 × 0308 × 0300 ÷	#  ÷ [0.2] <START OF HEADING> (Other) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 000D ÷ 0001 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 000D ÷ 0308 × 0001 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 000D ÷ 000D ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 000D ÷ 0308 × 000D ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 000D × 000A ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 000D ÷ 0308 × 000A ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 000D ÷ 0085 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 000D ÷ 0308 × 0085 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 000D ÷ 0009 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 000D ÷ 0308 × 0009 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 000D ÷ 0061 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 000D ÷ 0308 × 0061 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 000D ÷ 0041 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 000D ÷ 0308 × 0041 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 000D ÷ 01BB ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 000D ÷ 0308 × 01BB ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 000D ÷ 0030 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 000D ÷ 0308 × 0030 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 000D ÷ 002E ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 000D ÷ 0308 × 002E ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 000D ÷ 0021 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 000D ÷ 0308 × 0021 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 000D ÷ 0022 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 000D ÷ 0308 × 0022 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 000D ÷ 002C ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMMA (SContinue) ÷ [0.3]
+÷ 000D ÷ 0308 × 002C ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 000D ÷ 00AD ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 000D ÷ 0308 × 00AD ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 000D ÷ 0300 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 000D ÷ 0308 × 0300 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 000A ÷ 0001 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 000A ÷ 0308 × 0001 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 000A ÷ 000D ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 000A ÷ 0308 × 000D ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 000A ÷ 000A ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 000A ÷ 0308 × 000A ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 000A ÷ 0085 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 000A ÷ 0308 × 0085 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 000A ÷ 0009 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 000A ÷ 0308 × 0009 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 000A ÷ 0061 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 000A ÷ 0308 × 0061 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 000A ÷ 0041 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 000A ÷ 0308 × 0041 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 000A ÷ 01BB ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 000A ÷ 0308 × 01BB ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 000A ÷ 0030 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 000A ÷ 0308 × 0030 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 000A ÷ 002E ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 000A ÷ 0308 × 002E ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 000A ÷ 0021 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 000A ÷ 0308 × 0021 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 000A ÷ 0022 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 000A ÷ 0308 × 0022 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 000A ÷ 002C ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMMA (SContinue) ÷ [0.3]
+÷ 000A ÷ 0308 × 002C ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 000A ÷ 00AD ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 000A ÷ 0308 × 00AD ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 000A ÷ 0300 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 000A ÷ 0308 × 0300 ÷	#  ÷ [0.2] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0085 ÷ 0001 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0085 ÷ 0308 × 0001 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0085 ÷ 000D ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0085 ÷ 0308 × 000D ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0085 ÷ 000A ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0085 ÷ 0308 × 000A ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0085 ÷ 0085 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0085 ÷ 0308 × 0085 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0085 ÷ 0009 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0085 ÷ 0308 × 0009 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0085 ÷ 0061 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0085 ÷ 0308 × 0061 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0085 ÷ 0041 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0085 ÷ 0308 × 0041 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0085 ÷ 01BB ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0085 ÷ 0308 × 01BB ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0085 ÷ 0030 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0085 ÷ 0308 × 0030 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0085 ÷ 002E ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0085 ÷ 0308 × 002E ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0085 ÷ 0021 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0085 ÷ 0308 × 0021 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0085 ÷ 0022 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0085 ÷ 0308 × 0022 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0085 ÷ 002C ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMMA (SContinue) ÷ [0.3]
+÷ 0085 ÷ 0308 × 002C ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0085 ÷ 00AD ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0085 ÷ 0308 × 00AD ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0085 ÷ 0300 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0085 ÷ 0308 × 0300 ÷	#  ÷ [0.2] <NEXT LINE (NEL)> (Sep) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0009 × 0001 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0009 × 0308 × 0001 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0009 × 000D ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0009 × 0308 × 000D ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0009 × 000A ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0009 × 0308 × 000A ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0009 × 0085 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0009 × 0308 × 0085 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0009 × 0009 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0009 × 0308 × 0009 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0009 × 0061 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0009 × 0308 × 0061 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0009 × 0041 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0009 × 0308 × 0041 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0009 × 01BB ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0009 × 0308 × 01BB ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0009 × 0030 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0009 × 0308 × 0030 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0009 × 002E ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0009 × 0308 × 002E ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0009 × 0021 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0009 × 0308 × 0021 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0009 × 0022 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0009 × 0308 × 0022 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0009 × 002C ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0009 × 0308 × 002C ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0009 × 00AD ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0009 × 0308 × 00AD ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0009 × 0300 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0009 × 0308 × 0300 ÷	#  ÷ [0.2] <CHARACTER TABULATION> (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0061 × 0001 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0061 × 0308 × 0001 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0061 × 000D ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0061 × 0308 × 000D ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0061 × 000A ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0061 × 0308 × 000A ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0061 × 0085 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0061 × 0308 × 0085 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0061 × 0009 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0061 × 0308 × 0009 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0061 × 0061 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0061 × 0308 × 0061 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0061 × 0041 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0061 × 0308 × 0041 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0061 × 01BB ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0061 × 0308 × 01BB ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0061 × 0030 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0061 × 0308 × 0030 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0061 × 002E ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0061 × 0308 × 002E ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0061 × 0021 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0061 × 0308 × 0021 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0061 × 0022 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0061 × 0308 × 0022 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0061 × 002C ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0061 × 0308 × 002C ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0061 × 00AD ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0061 × 0308 × 00AD ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0061 × 0300 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0061 × 0308 × 0300 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0041 × 0001 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0041 × 0308 × 0001 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0041 × 000D ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0041 × 0308 × 000D ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0041 × 000A ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0041 × 0308 × 000A ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0041 × 0085 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0041 × 0308 × 0085 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0041 × 0009 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0041 × 0308 × 0009 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0041 × 0061 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0041 × 0308 × 0061 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0041 × 0041 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0041 × 0308 × 0041 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0041 × 01BB ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0041 × 0308 × 01BB ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0041 × 0030 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0041 × 0308 × 0030 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0041 × 002E ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0041 × 0308 × 002E ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0041 × 0021 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0041 × 0308 × 0021 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0041 × 0022 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0041 × 0308 × 0022 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0041 × 002C ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0041 × 0308 × 002C ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0041 × 00AD ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0041 × 0308 × 00AD ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0041 × 0300 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0041 × 0308 × 0300 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 01BB × 0001 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 01BB × 0308 × 0001 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 01BB × 000D ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 01BB × 0308 × 000D ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 01BB × 000A ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 01BB × 0308 × 000A ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 01BB × 0085 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 01BB × 0308 × 0085 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 01BB × 0009 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 01BB × 0308 × 0009 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 01BB × 0061 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 01BB × 0308 × 0061 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 01BB × 0041 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 01BB × 0308 × 0041 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 01BB × 01BB ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 01BB × 0308 × 01BB ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 01BB × 0030 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 01BB × 0308 × 0030 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 01BB × 002E ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 01BB × 0308 × 002E ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 01BB × 0021 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 01BB × 0308 × 0021 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 01BB × 0022 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 01BB × 0308 × 0022 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 01BB × 002C ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 01BB × 0308 × 002C ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 01BB × 00AD ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 01BB × 0308 × 00AD ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 01BB × 0300 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 01BB × 0308 × 0300 ÷	#  ÷ [0.2] LATIN LETTER TWO WITH STROKE (OLetter) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0030 × 0001 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0030 × 0308 × 0001 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0030 × 000D ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0030 × 0308 × 000D ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0030 × 000A ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0030 × 0308 × 000A ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0030 × 0085 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0030 × 0308 × 0085 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0030 × 0009 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0030 × 0308 × 0009 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0030 × 0061 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0030 × 0308 × 0061 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0030 × 0041 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0030 × 0308 × 0041 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0030 × 01BB ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0030 × 0308 × 01BB ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0030 × 0030 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0030 × 0308 × 0030 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0030 × 002E ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0030 × 0308 × 002E ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0030 × 0021 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0030 × 0308 × 0021 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0030 × 0022 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0030 × 0308 × 0022 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0030 × 002C ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0030 × 0308 × 002C ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0030 × 00AD ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0030 × 0308 × 00AD ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0030 × 0300 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0030 × 0308 × 0300 ÷	#  ÷ [0.2] DIGIT ZERO (Numeric) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 002E ÷ 0001 ÷	#  ÷ [0.2] FULL STOP (ATerm) ÷ [11.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 002E × 0308 ÷ 0001 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 002E × 000D ÷	#  ÷ [0.2] FULL STOP (ATerm) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 002E × 0308 × 000D ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 002E × 000A ÷	#  ÷ [0.2] FULL STOP (ATerm) × [9.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 002E × 0308 × 000A ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 002E × 0085 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [9.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 002E × 0308 × 0085 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 002E × 0009 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [9.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 002E × 0308 × 0009 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 002E × 0061 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [8.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 002E × 0308 × 0061 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 002E ÷ 0041 ÷	#  ÷ [0.2] FULL STOP (ATerm) ÷ [11.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 002E × 0308 ÷ 0041 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 002E ÷ 01BB ÷	#  ÷ [0.2] FULL STOP (ATerm) ÷ [11.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 002E × 0308 ÷ 01BB ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 002E × 0030 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [6.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 002E × 0308 × 0030 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [6.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 002E × 002E ÷	#  ÷ [0.2] FULL STOP (ATerm) × [8.1] FULL STOP (ATerm) ÷ [0.3]
+÷ 002E × 0308 × 002E ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] FULL STOP (ATerm) ÷ [0.3]
+÷ 002E × 0021 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [8.1] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 002E × 0308 × 0021 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 002E × 0022 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [9.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 002E × 0308 × 0022 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 002E × 002C ÷	#  ÷ [0.2] FULL STOP (ATerm) × [8.1] COMMA (SContinue) ÷ [0.3]
+÷ 002E × 0308 × 002C ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] COMMA (SContinue) ÷ [0.3]
+÷ 002E × 00AD ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 002E × 0308 × 00AD ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 002E × 0300 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 002E × 0308 × 0300 ÷	#  ÷ [0.2] FULL STOP (ATerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0021 ÷ 0001 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) ÷ [11.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0021 × 0308 ÷ 0001 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0021 × 000D ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0021 × 0308 × 000D ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0021 × 000A ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0021 × 0308 × 000A ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0021 × 0085 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0021 × 0308 × 0085 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0021 × 0009 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0021 × 0308 × 0009 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0021 ÷ 0061 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) ÷ [11.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0021 × 0308 ÷ 0061 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0021 ÷ 0041 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) ÷ [11.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0021 × 0308 ÷ 0041 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0021 ÷ 01BB ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) ÷ [11.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0021 × 0308 ÷ 01BB ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0021 ÷ 0030 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) ÷ [11.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0021 × 0308 ÷ 0030 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0021 × 002E ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [8.1] FULL STOP (ATerm) ÷ [0.3]
+÷ 0021 × 0308 × 002E ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] FULL STOP (ATerm) ÷ [0.3]
+÷ 0021 × 0021 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [8.1] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0021 × 0308 × 0021 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0021 × 0022 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0021 × 0308 × 0022 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [9.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0021 × 002C ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [8.1] COMMA (SContinue) ÷ [0.3]
+÷ 0021 × 0308 × 002C ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.1] COMMA (SContinue) ÷ [0.3]
+÷ 0021 × 00AD ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0021 × 0308 × 00AD ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0021 × 0300 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0021 × 0308 × 0300 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0022 × 0001 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0022 × 0308 × 0001 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0022 × 000D ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0022 × 0308 × 000D ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0022 × 000A ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0022 × 0308 × 000A ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0022 × 0085 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0022 × 0308 × 0085 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0022 × 0009 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0022 × 0308 × 0009 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0022 × 0061 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0022 × 0308 × 0061 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0022 × 0041 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0022 × 0308 × 0041 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0022 × 01BB ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0022 × 0308 × 01BB ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0022 × 0030 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0022 × 0308 × 0030 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0022 × 002E ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0022 × 0308 × 002E ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0022 × 0021 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0022 × 0308 × 0021 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0022 × 0022 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0022 × 0308 × 0022 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0022 × 002C ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0022 × 0308 × 002C ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0022 × 00AD ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0022 × 0308 × 00AD ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0022 × 0300 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0022 × 0308 × 0300 ÷	#  ÷ [0.2] QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 002C × 0001 ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 002C × 0308 × 0001 ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 002C × 000D ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 002C × 0308 × 000D ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 002C × 000A ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 002C × 0308 × 000A ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 002C × 0085 ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 002C × 0308 × 0085 ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 002C × 0009 ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 002C × 0308 × 0009 ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 002C × 0061 ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 002C × 0308 × 0061 ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 002C × 0041 ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 002C × 0308 × 0041 ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 002C × 01BB ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 002C × 0308 × 01BB ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 002C × 0030 ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 002C × 0308 × 0030 ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 002C × 002E ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 002C × 0308 × 002E ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 002C × 0021 ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 002C × 0308 × 0021 ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 002C × 0022 ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 002C × 0308 × 0022 ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 002C × 002C ÷	#  ÷ [0.2] COMMA (SContinue) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 002C × 0308 × 002C ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 002C × 00AD ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 002C × 0308 × 00AD ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 002C × 0300 ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 002C × 0308 × 0300 ÷	#  ÷ [0.2] COMMA (SContinue) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 00AD × 0001 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 00AD × 0308 × 0001 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 00AD × 000D ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 00AD × 0308 × 000D ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 00AD × 000A ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 00AD × 0308 × 000A ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 00AD × 0085 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 00AD × 0308 × 0085 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 00AD × 0009 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 00AD × 0308 × 0009 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 00AD × 0061 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 00AD × 0308 × 0061 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 00AD × 0041 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 00AD × 0308 × 0041 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 00AD × 01BB ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 00AD × 0308 × 01BB ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 00AD × 0030 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 00AD × 0308 × 0030 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 00AD × 002E ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 00AD × 0308 × 002E ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 00AD × 0021 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 00AD × 0308 × 0021 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 00AD × 0022 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 00AD × 0308 × 0022 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 00AD × 002C ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 00AD × 0308 × 002C ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 00AD × 00AD ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 00AD × 0308 × 00AD ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 00AD × 0300 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 00AD × 0308 × 0300 ÷	#  ÷ [0.2] SOFT HYPHEN (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0300 × 0001 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0300 × 0308 × 0001 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <START OF HEADING> (Other) ÷ [0.3]
+÷ 0300 × 000D ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0300 × 0308 × 000D ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CARRIAGE RETURN (CR)> (CR) ÷ [0.3]
+÷ 0300 × 000A ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0300 × 0308 × 000A ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <LINE FEED (LF)> (LF) ÷ [0.3]
+÷ 0300 × 0085 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0300 × 0308 × 0085 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <NEXT LINE (NEL)> (Sep) ÷ [0.3]
+÷ 0300 × 0009 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0300 × 0308 × 0009 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] <CHARACTER TABULATION> (Sp) ÷ [0.3]
+÷ 0300 × 0061 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0300 × 0308 × 0061 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN SMALL LETTER A (Lower) ÷ [0.3]
+÷ 0300 × 0041 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0300 × 0308 × 0041 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER A (Upper) ÷ [0.3]
+÷ 0300 × 01BB ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0300 × 0308 × 01BB ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN LETTER TWO WITH STROKE (OLetter) ÷ [0.3]
+÷ 0300 × 0030 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0300 × 0308 × 0030 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] DIGIT ZERO (Numeric) ÷ [0.3]
+÷ 0300 × 002E ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0300 × 0308 × 002E ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0300 × 0021 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0300 × 0308 × 0021 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] EXCLAMATION MARK (STerm) ÷ [0.3]
+÷ 0300 × 0022 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0300 × 0308 × 0022 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] QUOTATION MARK (Close) ÷ [0.3]
+÷ 0300 × 002C ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0300 × 0308 × 002C ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [998.0] COMMA (SContinue) ÷ [0.3]
+÷ 0300 × 00AD ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0300 × 0308 × 00AD ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] SOFT HYPHEN (Format_FE) ÷ [0.3]
+÷ 0300 × 0300 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 0300 × 0308 × 0300 ÷	#  ÷ [0.2] COMBINING GRAVE ACCENT (Extend_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) ÷ [0.3]
+÷ 000D × 000A ÷ 0061 × 000A ÷ 0308 ÷	#  ÷ [0.2] <CARRIAGE RETURN (CR)> (CR) × [3.0] <LINE FEED (LF)> (LF) ÷ [4.0] LATIN SMALL LETTER A (Lower) × [998.0] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) ÷ [0.3]
+÷ 0061 × 0308 ÷	#  ÷ [0.2] LATIN SMALL LETTER A (Lower) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [0.3]
+÷ 0020 × 200D × 0646 ÷	#  ÷ [0.2] SPACE (Sp) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [998.0] ARABIC LETTER NOON (OLetter) ÷ [0.3]
+÷ 0646 × 200D × 0020 ÷	#  ÷ [0.2] ARABIC LETTER NOON (OLetter) × [5.0] ZERO WIDTH JOINER (Extend_FE) × [998.0] SPACE (Sp) ÷ [0.3]
+÷ 0028 × 0022 × 0047 × 006F × 002E × 0022 × 0029 × 0020 ÷ 0028 × 0048 × 0065 × 0020 × 0064 × 0069 × 0064 × 002E × 0029 ÷	#  ÷ [0.2] LEFT PARENTHESIS (Close) × [998.0] QUOTATION MARK (Close) × [998.0] LATIN CAPITAL LETTER G (Upper) × [998.0] LATIN SMALL LETTER O (Lower) × [998.0] FULL STOP (ATerm) × [9.0] QUOTATION MARK (Close) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] SPACE (Sp) ÷ [11.0] LEFT PARENTHESIS (Close) × [998.0] LATIN CAPITAL LETTER H (Upper) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] SPACE (Sp) × [998.0] LATIN SMALL LETTER D (Lower) × [998.0] LATIN SMALL LETTER I (Lower) × [998.0] LATIN SMALL LETTER D (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) ÷ [0.3]
+÷ 0028 × 201C × 0047 × 006F × 003F × 201D × 0029 × 0020 ÷ 0028 × 0048 × 0065 × 0020 × 0064 × 0069 × 0064 × 002E × 0029 ÷	#  ÷ [0.2] LEFT PARENTHESIS (Close) × [998.0] LEFT DOUBLE QUOTATION MARK (Close) × [998.0] LATIN CAPITAL LETTER G (Upper) × [998.0] LATIN SMALL LETTER O (Lower) × [998.0] QUESTION MARK (STerm) × [9.0] RIGHT DOUBLE QUOTATION MARK (Close) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] SPACE (Sp) ÷ [11.0] LEFT PARENTHESIS (Close) × [998.0] LATIN CAPITAL LETTER H (Upper) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] SPACE (Sp) × [998.0] LATIN SMALL LETTER D (Lower) × [998.0] LATIN SMALL LETTER I (Lower) × [998.0] LATIN SMALL LETTER D (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) ÷ [0.3]
+÷ 0055 × 002E × 0053 × 002E × 0041 × 0300 × 002E × 0020 × 0069 × 0073 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER U (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER S (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) × [8.0] SPACE (Sp) × [8.0] LATIN SMALL LETTER I (Lower) × [998.0] LATIN SMALL LETTER S (Lower) ÷ [0.3]
+÷ 0055 × 002E × 0053 × 002E × 0041 × 0300 × 003F × 0020 ÷ 0048 × 0065 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER U (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER S (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] QUESTION MARK (STerm) × [9.0] SPACE (Sp) ÷ [11.0] LATIN CAPITAL LETTER H (Upper) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
+÷ 0055 × 002E × 0053 × 002E × 0041 × 0300 × 002E ÷	#  ÷ [0.2] LATIN CAPITAL LETTER U (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER S (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) ÷ [0.3]
+÷ 0033 × 002E × 0034 ÷	#  ÷ [0.2] DIGIT THREE (Numeric) × [998.0] FULL STOP (ATerm) × [6.0] DIGIT FOUR (Numeric) ÷ [0.3]
+÷ 0063 × 002E × 0064 ÷	#  ÷ [0.2] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.0] LATIN SMALL LETTER D (Lower) ÷ [0.3]
+÷ 0043 × 002E × 0064 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER C (Upper) × [998.0] FULL STOP (ATerm) × [8.0] LATIN SMALL LETTER D (Lower) ÷ [0.3]
+÷ 0063 × 002E × 0044 ÷	#  ÷ [0.2] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER D (Upper) ÷ [0.3]
+÷ 0043 × 002E × 0044 ÷	#  ÷ [0.2] LATIN CAPITAL LETTER C (Upper) × [998.0] FULL STOP (ATerm) × [7.0] LATIN CAPITAL LETTER D (Upper) ÷ [0.3]
+÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 × 0074 × 0068 × 0065 ÷	#  ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.0] RIGHT PARENTHESIS (Close) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [8.0] NO-BREAK SPACE (Sp) × [8.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
+÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 ÷ 0054 × 0068 × 0065 ÷	#  ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [9.0] NO-BREAK SPACE (Sp) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
+÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 × 2018 × 0028 × 0074 × 0068 × 0065 ÷	#  ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.0] RIGHT PARENTHESIS (Close) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [8.0] NO-BREAK SPACE (Sp) × [8.0] LEFT SINGLE QUOTATION MARK (Close) × [998.0] LEFT PARENTHESIS (Close) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
+÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 ÷ 2018 × 0028 × 0054 × 0068 × 0065 ÷	#  ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [9.0] NO-BREAK SPACE (Sp) ÷ [11.0] LEFT SINGLE QUOTATION MARK (Close) × [998.0] LEFT PARENTHESIS (Close) × [998.0] LATIN CAPITAL LETTER T (Upper) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
+÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 × 0308 × 0074 × 0068 × 0065 ÷	#  ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.0] RIGHT PARENTHESIS (Close) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [8.0] NO-BREAK SPACE (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
+÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 00A0 × 0308 ÷ 0054 × 0068 × 0065 ÷	#  ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [9.0] NO-BREAK SPACE (Sp) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
+÷ 0065 × 0074 × 0063 × 002E × 0029 × 2019 × 0308 ÷ 0054 × 0068 × 0065 ÷	#  ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
+÷ 0065 × 0074 × 0063 × 002E × 0029 × 000A ÷ 0308 × 0054 × 0068 × 0065 ÷	#  ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [9.0] RIGHT PARENTHESIS (Close) × [9.0] <LINE FEED (LF)> (LF) ÷ [4.0] COMBINING DIAERESIS (Extend_FE) × [998.0] LATIN CAPITAL LETTER T (Upper) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
+÷ 0074 × 0068 × 0065 × 0020 × 0072 × 0065 × 0073 × 0070 × 002E × 0020 × 006C × 0065 × 0061 × 0064 × 0065 × 0072 × 0073 × 0020 × 0061 × 0072 × 0065 ÷	#  ÷ [0.2] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER H (Lower) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] SPACE (Sp) × [998.0] LATIN SMALL LETTER R (Lower) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER S (Lower) × [998.0] LATIN SMALL LETTER P (Lower) × [998.0] FULL STOP (ATerm) × [8.0] SPACE (Sp) × [8.0] LATIN SMALL LETTER L (Lower) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER A (Lower) × [998.0] LATIN SMALL LETTER D (Lower) × [998.0] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER R (Lower) × [998.0] LATIN SMALL LETTER S (Lower) × [998.0] SPACE (Sp) × [998.0] LATIN SMALL LETTER A (Lower) × [998.0] LATIN SMALL LETTER R (Lower) × [998.0] LATIN SMALL LETTER E (Lower) ÷ [0.3]
+÷ 5B57 × 002E ÷ 5B57 ÷	#  ÷ [0.2] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [998.0] FULL STOP (ATerm) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) ÷ [0.3]
+÷ 0065 × 0074 × 0063 × 002E ÷ 5B83 ÷	#  ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) ÷ [0.3]
+÷ 0065 × 0074 × 0063 × 002E × 3002 ÷	#  ÷ [0.2] LATIN SMALL LETTER E (Lower) × [998.0] LATIN SMALL LETTER T (Lower) × [998.0] LATIN SMALL LETTER C (Lower) × [998.0] FULL STOP (ATerm) × [8.1] IDEOGRAPHIC FULL STOP (STerm) ÷ [0.3]
+÷ 5B57 × 3002 ÷ 5B83 ÷	#  ÷ [0.2] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [998.0] IDEOGRAPHIC FULL STOP (STerm) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) ÷ [0.3]
+÷ 0021 × 0020 × 0020 ÷	#  ÷ [0.2] EXCLAMATION MARK (STerm) × [9.0] SPACE (Sp) × [10.0] SPACE (Sp) ÷ [0.3]
+÷ 2060 × 0028 × 2060 × 0022 × 2060 × 0047 × 2060 × 006F × 2060 × 002E × 2060 × 0022 × 2060 × 0029 × 2060 × 0020 × 2060 ÷ 0028 × 2060 × 0048 × 2060 × 0065 × 2060 × 0020 × 2060 × 0064 × 2060 × 0069 × 2060 × 0064 × 2060 × 002E × 2060 × 0029 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER G (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER O (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0028 × 2060 × 201C × 2060 × 0047 × 2060 × 006F × 2060 × 003F × 2060 × 201D × 2060 × 0029 × 2060 × 0020 × 2060 ÷ 0028 × 2060 × 0048 × 2060 × 0065 × 2060 × 0020 × 2060 × 0064 × 2060 × 0069 × 2060 × 0064 × 2060 × 002E × 2060 × 0029 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LEFT DOUBLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER G (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER O (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] QUESTION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT DOUBLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0055 × 2060 × 002E × 2060 × 0053 × 2060 × 002E × 2060 × 0041 × 2060 × 0300 × 002E × 2060 × 0020 × 2060 × 0069 × 2060 × 0073 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER U (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER S (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER I (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER S (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0055 × 2060 × 002E × 2060 × 0053 × 2060 × 002E × 2060 × 0041 × 2060 × 0300 × 003F × 2060 × 0020 × 2060 ÷ 0048 × 2060 × 0065 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER U (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER S (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] QUESTION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LATIN CAPITAL LETTER H (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0055 × 2060 × 002E × 2060 × 0053 × 2060 × 002E × 2060 × 0041 × 2060 × 0300 × 002E × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER U (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER S (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER A (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING GRAVE ACCENT (Extend_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0033 × 2060 × 002E × 2060 × 0034 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] DIGIT THREE (Numeric) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [6.0] DIGIT FOUR (Numeric) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0063 × 2060 × 002E × 2060 × 0064 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0043 × 2060 × 002E × 2060 × 0064 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER C (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0063 × 2060 × 002E × 2060 × 0044 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER D (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0043 × 2060 × 002E × 2060 × 0044 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER C (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [7.0] LATIN CAPITAL LETTER D (Upper) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 × 0074 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 ÷ 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 × 2018 × 2060 × 0028 × 2060 × 0074 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LEFT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 ÷ 2018 × 2060 × 0028 × 2060 × 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] LEFT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LEFT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 × 0308 × 0074 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [8.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [8.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 00A0 × 2060 × 0308 ÷ 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] NO-BREAK SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 2019 × 2060 × 0308 ÷ 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT SINGLE QUOTATION MARK (Close) × [5.0] WORD JOINER (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) ÷ [11.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 0029 × 2060 × 000A ÷ 2060 × 0308 × 2060 × 0054 × 2060 × 0068 × 2060 × 0065 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [9.0] RIGHT PARENTHESIS (Close) × [5.0] WORD JOINER (Format_FE) × [9.0] <LINE FEED (LF)> (LF) ÷ [4.0] WORD JOINER (Format_FE) × [5.0] COMBINING DIAERESIS (Extend_FE) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN CAPITAL LETTER T (Upper) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0074 × 2060 × 0068 × 2060 × 0065 × 2060 × 0020 × 2060 × 0072 × 2060 × 0065 × 2060 × 0073 × 2060 × 0070 × 2060 × 002E × 2060 × 0020 × 2060 × 006C × 2060 × 0065 × 2060 × 0061 × 2060 × 0064 × 2060 × 0065 × 2060 × 0072 × 2060 × 0073 × 2060 × 0020 × 2060 × 0061 × 2060 × 0072 × 2060 × 0065 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER H (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER R (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER S (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER P (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [8.0] LATIN SMALL LETTER L (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER A (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER D (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER R (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER S (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER A (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER R (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 5B57 × 2060 × 002E × 2060 ÷ 5B57 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 ÷ 5B83 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0065 × 2060 × 0074 × 2060 × 0063 × 2060 × 002E × 2060 × 3002 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER E (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER T (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] LATIN SMALL LETTER C (Lower) × [5.0] WORD JOINER (Format_FE) × [998.0] FULL STOP (ATerm) × [5.0] WORD JOINER (Format_FE) × [8.1] IDEOGRAPHIC FULL STOP (STerm) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 5B57 × 2060 × 3002 × 2060 ÷ 5B83 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] CJK UNIFIED IDEOGRAPH-5B57 (OLetter) × [5.0] WORD JOINER (Format_FE) × [998.0] IDEOGRAPHIC FULL STOP (STerm) × [5.0] WORD JOINER (Format_FE) ÷ [11.0] CJK UNIFIED IDEOGRAPH-5B83 (OLetter) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+÷ 2060 × 0021 × 2060 × 0020 × 2060 × 0020 × 2060 × 2060 ÷	#  ÷ [0.2] WORD JOINER (Format_FE) × [998.0] EXCLAMATION MARK (STerm) × [5.0] WORD JOINER (Format_FE) × [9.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [10.0] SPACE (Sp) × [5.0] WORD JOINER (Format_FE) × [5.0] WORD JOINER (Format_FE) ÷ [0.3]
+#
+# Lines: 502
+#
+# EOF

libs/libgrapheme-2.0.2/data/SpecialCasing.txt

@@ -0,0 +1,281 @@
+# SpecialCasing-15.0.0.txt
+# Date: 2022-02-02, 23:35:52 GMT
+# © 2022 Unicode®, Inc.
+# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
+# For terms of use, see https://www.unicode.org/terms_of_use.html
+#
+# Unicode Character Database
+#   For documentation, see https://www.unicode.org/reports/tr44/
+#
+# Special Casing
+#
+# This file is a supplement to the UnicodeData.txt file. It does not define any
+# properties, but rather provides additional information about the casing of
+# Unicode characters, for situations when casing incurs a change in string length
+# or is dependent on context or locale. For compatibility, the UnicodeData.txt
+# file only contains simple case mappings for characters where they are one-to-one
+# and independent of context and language. The data in this file, combined with
+# the simple case mappings in UnicodeData.txt, defines the full case mappings
+# Lowercase_Mapping (lc), Titlecase_Mapping (tc), and Uppercase_Mapping (uc).
+#
+# Note that the preferred mechanism for defining tailored casing operations is
+# the Unicode Common Locale Data Repository (CLDR). For more information, see the
+# discussion of case mappings and case algorithms in the Unicode Standard.
+#
+# All code points not listed in this file that do not have a simple case mappings
+# in UnicodeData.txt map to themselves.
+# ================================================================================
+# Format
+# ================================================================================
+# The entries in this file are in the following machine-readable format:
+#
+# <code>; <lower>; <title>; <upper>; (<condition_list>;)? # <comment>
+#
+# <code>, <lower>, <title>, and <upper> provide the respective full case mappings
+# of <code>, expressed as character values in hex. If there is more than one character,
+# they are separated by spaces. Other than as used to separate elements, spaces are
+# to be ignored.
+#
+# The <condition_list> is optional. Where present, it consists of one or more language IDs
+# or casing contexts, separated by spaces. In these conditions:
+# - A condition list overrides the normal behavior if all of the listed conditions are true.
+# - The casing context is always the context of the characters in the original string,
+#   NOT in the resulting string.
+# - Case distinctions in the condition list are not significant.
+# - Conditions preceded by "Not_" represent the negation of the condition.
+# The condition list is not represented in the UCD as a formal property.
+#
+# A language ID is defined by BCP 47, with '-' and '_' treated equivalently.
+#
+# A casing context for a character is defined by Section 3.13 Default Case Algorithms
+# of The Unicode Standard.
+#
+# Parsers of this file must be prepared to deal with future additions to this format:
+#  * Additional contexts
+#  * Additional fields
+# ================================================================================
+
+# ================================================================================
+# Unconditional mappings
+# ================================================================================
+
+# The German es-zed is special--the normal mapping is to SS.
+# Note: the titlecase should never occur in practice. It is equal to titlecase(uppercase(<es-zed>))
+
+00DF; 00DF; 0053 0073; 0053 0053; # LATIN SMALL LETTER SHARP S
+
+# Preserve canonical equivalence for I with dot. Turkic is handled below.
+
+0130; 0069 0307; 0130; 0130; # LATIN CAPITAL LETTER I WITH DOT ABOVE
+
+# Ligatures
+
+FB00; FB00; 0046 0066; 0046 0046; # LATIN SMALL LIGATURE FF
+FB01; FB01; 0046 0069; 0046 0049; # LATIN SMALL LIGATURE FI
+FB02; FB02; 0046 006C; 0046 004C; # LATIN SMALL LIGATURE FL
+FB03; FB03; 0046 0066 0069; 0046 0046 0049; # LATIN SMALL LIGATURE FFI
+FB04; FB04; 0046 0066 006C; 0046 0046 004C; # LATIN SMALL LIGATURE FFL
+FB05; FB05; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE LONG S T
+FB06; FB06; 0053 0074; 0053 0054; # LATIN SMALL LIGATURE ST
+
+0587; 0587; 0535 0582; 0535 0552; # ARMENIAN SMALL LIGATURE ECH YIWN
+FB13; FB13; 0544 0576; 0544 0546; # ARMENIAN SMALL LIGATURE MEN NOW
+FB14; FB14; 0544 0565; 0544 0535; # ARMENIAN SMALL LIGATURE MEN ECH
+FB15; FB15; 0544 056B; 0544 053B; # ARMENIAN SMALL LIGATURE MEN INI
+FB16; FB16; 054E 0576; 054E 0546; # ARMENIAN SMALL LIGATURE VEW NOW
+FB17; FB17; 0544 056D; 0544 053D; # ARMENIAN SMALL LIGATURE MEN XEH
+
+# No corresponding uppercase precomposed character
+
+0149; 0149; 02BC 004E; 02BC 004E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE
+0390; 0390; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS
+03B0; 03B0; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS
+01F0; 01F0; 004A 030C; 004A 030C; # LATIN SMALL LETTER J WITH CARON
+1E96; 1E96; 0048 0331; 0048 0331; # LATIN SMALL LETTER H WITH LINE BELOW
+1E97; 1E97; 0054 0308; 0054 0308; # LATIN SMALL LETTER T WITH DIAERESIS
+1E98; 1E98; 0057 030A; 0057 030A; # LATIN SMALL LETTER W WITH RING ABOVE
+1E99; 1E99; 0059 030A; 0059 030A; # LATIN SMALL LETTER Y WITH RING ABOVE
+1E9A; 1E9A; 0041 02BE; 0041 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING
+1F50; 1F50; 03A5 0313; 03A5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI
+1F52; 1F52; 03A5 0313 0300; 03A5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA
+1F54; 1F54; 03A5 0313 0301; 03A5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA
+1F56; 1F56; 03A5 0313 0342; 03A5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI
+1FB6; 1FB6; 0391 0342; 0391 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI
+1FC6; 1FC6; 0397 0342; 0397 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI
+1FD2; 1FD2; 0399 0308 0300; 0399 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA
+1FD3; 1FD3; 0399 0308 0301; 0399 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA
+1FD6; 1FD6; 0399 0342; 0399 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI
+1FD7; 1FD7; 0399 0308 0342; 0399 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI
+1FE2; 1FE2; 03A5 0308 0300; 03A5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA
+1FE3; 1FE3; 03A5 0308 0301; 03A5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA
+1FE4; 1FE4; 03A1 0313; 03A1 0313; # GREEK SMALL LETTER RHO WITH PSILI
+1FE6; 1FE6; 03A5 0342; 03A5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI
+1FE7; 1FE7; 03A5 0308 0342; 03A5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI
+1FF6; 1FF6; 03A9 0342; 03A9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI
+
+# IMPORTANT-when iota-subscript (0345) is uppercased or titlecased,
+#  the result will be incorrect unless the iota-subscript is moved to the end
+#  of any sequence of combining marks. Otherwise, the accents will go on the capital iota.
+#  This process can be achieved by first transforming the text to NFC before casing.
+#  E.g. <alpha><iota_subscript><acute> is uppercased to <ALPHA><acute><IOTA>
+
+# The following cases are already in the UnicodeData.txt file, so are only commented here.
+
+# 0345; 0345; 0399; 0399; # COMBINING GREEK YPOGEGRAMMENI
+
+# All letters with YPOGEGRAMMENI (iota-subscript) or PROSGEGRAMMENI (iota adscript)
+# have special uppercases.
+# Note: characters with PROSGEGRAMMENI are actually titlecase, not uppercase!
+
+1F80; 1F80; 1F88; 1F08 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI
+1F81; 1F81; 1F89; 1F09 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI
+1F82; 1F82; 1F8A; 1F0A 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI
+1F83; 1F83; 1F8B; 1F0B 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI
+1F84; 1F84; 1F8C; 1F0C 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI
+1F85; 1F85; 1F8D; 1F0D 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI
+1F86; 1F86; 1F8E; 1F0E 0399; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
+1F87; 1F87; 1F8F; 1F0F 0399; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
+1F88; 1F80; 1F88; 1F08 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI
+1F89; 1F81; 1F89; 1F09 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI
+1F8A; 1F82; 1F8A; 1F0A 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI
+1F8B; 1F83; 1F8B; 1F0B 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI
+1F8C; 1F84; 1F8C; 1F0C 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI
+1F8D; 1F85; 1F8D; 1F0D 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI
+1F8E; 1F86; 1F8E; 1F0E 0399; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
+1F8F; 1F87; 1F8F; 1F0F 0399; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
+1F90; 1F90; 1F98; 1F28 0399; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI
+1F91; 1F91; 1F99; 1F29 0399; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI
+1F92; 1F92; 1F9A; 1F2A 0399; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI
+1F93; 1F93; 1F9B; 1F2B 0399; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI
+1F94; 1F94; 1F9C; 1F2C 0399; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI
+1F95; 1F95; 1F9D; 1F2D 0399; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI
+1F96; 1F96; 1F9E; 1F2E 0399; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
+1F97; 1F97; 1F9F; 1F2F 0399; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
+1F98; 1F90; 1F98; 1F28 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI
+1F99; 1F91; 1F99; 1F29 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI
+1F9A; 1F92; 1F9A; 1F2A 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI
+1F9B; 1F93; 1F9B; 1F2B 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI
+1F9C; 1F94; 1F9C; 1F2C 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI
+1F9D; 1F95; 1F9D; 1F2D 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI
+1F9E; 1F96; 1F9E; 1F2E 0399; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
+1F9F; 1F97; 1F9F; 1F2F 0399; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
+1FA0; 1FA0; 1FA8; 1F68 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI
+1FA1; 1FA1; 1FA9; 1F69 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI
+1FA2; 1FA2; 1FAA; 1F6A 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI
+1FA3; 1FA3; 1FAB; 1F6B 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI
+1FA4; 1FA4; 1FAC; 1F6C 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI
+1FA5; 1FA5; 1FAD; 1F6D 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI
+1FA6; 1FA6; 1FAE; 1F6E 0399; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI
+1FA7; 1FA7; 1FAF; 1F6F 0399; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI
+1FA8; 1FA0; 1FA8; 1F68 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI
+1FA9; 1FA1; 1FA9; 1F69 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI
+1FAA; 1FA2; 1FAA; 1F6A 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI
+1FAB; 1FA3; 1FAB; 1F6B 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI
+1FAC; 1FA4; 1FAC; 1F6C 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI
+1FAD; 1FA5; 1FAD; 1F6D 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI
+1FAE; 1FA6; 1FAE; 1F6E 0399; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI
+1FAF; 1FA7; 1FAF; 1F6F 0399; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI
+1FB3; 1FB3; 1FBC; 0391 0399; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI
+1FBC; 1FB3; 1FBC; 0391 0399; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI
+1FC3; 1FC3; 1FCC; 0397 0399; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI
+1FCC; 1FC3; 1FCC; 0397 0399; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI
+1FF3; 1FF3; 1FFC; 03A9 0399; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI
+1FFC; 1FF3; 1FFC; 03A9 0399; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI
+
+# Some characters with YPOGEGRAMMENI also have no corresponding titlecases
+
+1FB2; 1FB2; 1FBA 0345; 1FBA 0399; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI
+1FB4; 1FB4; 0386 0345; 0386 0399; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI
+1FC2; 1FC2; 1FCA 0345; 1FCA 0399; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI
+1FC4; 1FC4; 0389 0345; 0389 0399; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI
+1FF2; 1FF2; 1FFA 0345; 1FFA 0399; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI
+1FF4; 1FF4; 038F 0345; 038F 0399; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI
+
+1FB7; 1FB7; 0391 0342 0345; 0391 0342 0399; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI
+1FC7; 1FC7; 0397 0342 0345; 0397 0342 0399; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI
+1FF7; 1FF7; 03A9 0342 0345; 03A9 0342 0399; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI
+
+# ================================================================================
+# Conditional Mappings
+# The remainder of this file provides conditional casing data used to produce
+# full case mappings.
+# ================================================================================
+# Language-Insensitive Mappings
+# These are characters whose full case mappings do not depend on language, but do
+# depend on context (which characters come before or after). For more information
+# see the header of this file and the Unicode Standard.
+# ================================================================================
+
+# Special case for final form of sigma
+
+03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
+
+# Note: the following cases for non-final are already in the UnicodeData.txt file.
+
+# 03A3; 03C3; 03A3; 03A3; # GREEK CAPITAL LETTER SIGMA
+# 03C3; 03C3; 03A3; 03A3; # GREEK SMALL LETTER SIGMA
+# 03C2; 03C2; 03A3; 03A3; # GREEK SMALL LETTER FINAL SIGMA
+
+# Note: the following cases are not included, since they would case-fold in lowercasing
+
+# 03C3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK SMALL LETTER SIGMA
+# 03C2; 03C3; 03A3; 03A3; Not_Final_Sigma; # GREEK SMALL LETTER FINAL SIGMA
+
+# ================================================================================
+# Language-Sensitive Mappings
+# These are characters whose full case mappings depend on language and perhaps also
+# context (which characters come before or after). For more information
+# see the header of this file and the Unicode Standard.
+# ================================================================================
+
+# Lithuanian
+
+# Lithuanian retains the dot in a lowercase i when followed by accents.
+
+# Remove DOT ABOVE after "i" with upper or titlecase
+
+0307; 0307; ; ; lt After_Soft_Dotted; # COMBINING DOT ABOVE
+
+# Introduce an explicit dot above when lowercasing capital I's and J's
+# whenever there are more accents above.
+# (of the accents used in Lithuanian: grave, acute, tilde above, and ogonek)
+
+0049; 0069 0307; 0049; 0049; lt More_Above; # LATIN CAPITAL LETTER I
+004A; 006A 0307; 004A; 004A; lt More_Above; # LATIN CAPITAL LETTER J
+012E; 012F 0307; 012E; 012E; lt More_Above; # LATIN CAPITAL LETTER I WITH OGONEK
+00CC; 0069 0307 0300; 00CC; 00CC; lt; # LATIN CAPITAL LETTER I WITH GRAVE
+00CD; 0069 0307 0301; 00CD; 00CD; lt; # LATIN CAPITAL LETTER I WITH ACUTE
+0128; 0069 0307 0303; 0128; 0128; lt; # LATIN CAPITAL LETTER I WITH TILDE
+
+# ================================================================================
+
+# Turkish and Azeri
+
+# I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
+# The following rules handle those cases.
+
+0130; 0069; 0130; 0130; tr; # LATIN CAPITAL LETTER I WITH DOT ABOVE
+0130; 0069; 0130; 0130; az; # LATIN CAPITAL LETTER I WITH DOT ABOVE
+
+# When lowercasing, remove dot_above in the sequence I + dot_above, which will turn into i.
+# This matches the behavior of the canonically equivalent I-dot_above
+
+0307; ; 0307; 0307; tr After_I; # COMBINING DOT ABOVE
+0307; ; 0307; 0307; az After_I; # COMBINING DOT ABOVE
+
+# When lowercasing, unless an I is before a dot_above, it turns into a dotless i.
+
+0049; 0131; 0049; 0049; tr Not_Before_Dot; # LATIN CAPITAL LETTER I
+0049; 0131; 0049; 0049; az Not_Before_Dot; # LATIN CAPITAL LETTER I
+
+# When uppercasing, i turns into a dotted capital I
+
+0069; 0069; 0130; 0130; tr; # LATIN SMALL LETTER I
+0069; 0069; 0130; 0130; az; # LATIN SMALL LETTER I
+
+# Note: the following case is already in the UnicodeData.txt file.
+
+# 0131; 0131; 0049; 0049; tr; # LATIN SMALL LETTER DOTLESS I
+
+# EOF
+

libs/libgrapheme-2.0.2/gen/case.c

@@ -0,0 +1,318 @@
+/* See LICENSE file for copyright and license details. */
+#include <errno.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "util.h"
+
+#define FILE_DCP "data/DerivedCoreProperties.txt"
+
+static const struct property_spec case_property[] = {
+	{
+		.enumname = "OTHER",
+		.file     = NULL,
+		.ucdname  = NULL,
+	},
+	{
+		.enumname = "BOTH_CASED_CASE_IGNORABLE",
+		.file     = NULL,
+		.ucdname  = NULL,
+	},
+	{	
+		.enumname = "CASED",
+		.file     = FILE_DCP,
+		.ucdname  = "Cased",
+	},
+	{
+		.enumname = "CASE_IGNORABLE",
+		.file     = FILE_DCP,
+		.ucdname  = "Case_Ignorable",
+	},
+	{
+		.enumname = "UNCASED",
+		.file     = FILE_DCP,
+		.ucdname  = "Uncased",
+	},
+};
+
+static uint_least8_t
+handle_conflict(uint_least32_t cp, uint_least8_t prop1, uint_least8_t prop2)
+{
+	uint_least8_t result;
+
+	(void)cp;
+
+	if ((!strcmp(case_property[prop1].enumname, "CASED") &&
+	     !strcmp(case_property[prop2].enumname, "CASE_IGNORABLE")) ||
+	    (!strcmp(case_property[prop1].enumname, "CASE_IGNORABLE") &&
+	     !strcmp(case_property[prop2].enumname, "CASED"))) {
+		for (result = 0; result < LEN(case_property); result++) {
+			if (!strcmp(case_property[result].enumname,
+			            "BOTH_CASED_CASE_IGNORABLE")) {
+				break;
+			}
+		}
+		if (result == LEN(case_property)) {
+			fprintf(stderr, "handle_conflict: Internal error.\n");
+			exit(1);
+		}
+	} else {
+		fprintf(stderr, "handle_conflict: Cannot handle conflict.\n");
+		exit(1);
+	}
+
+	return result;
+}
+
+static struct properties *prop_upper = NULL, *prop_lower, *prop_title;
+static struct special_case {
+	struct {
+		uint_least32_t *cp;
+		size_t cplen;
+	} upper, lower, title;
+} *sc = NULL;
+static size_t sclen = 0;
+
+static int
+unicodedata_callback(const char *file, char **field, size_t nfields,
+                     char *comment, void *payload)
+{
+	uint_least32_t cp, upper, lower, title;
+
+	(void)file;
+	(void)comment;
+	(void)payload;
+
+	hextocp(field[0], strlen(field[0]), &cp);
+
+	upper = lower = title = cp;
+
+	if ((strlen(field[12]) > 0 && hextocp(field[12], strlen(field[12]), &upper))                 ||
+	    (strlen(field[13]) > 0 && hextocp(field[13], strlen(field[13]), &lower))                 ||
+	    (nfields >= 15 && strlen(field[14]) > 0 && hextocp(field[14], strlen(field[14]), &title))) {
+		return 1;
+	}
+
+	prop_upper[cp].property = (int_least32_t)upper - (int_least32_t)cp;
+	prop_lower[cp].property = (int_least32_t)lower - (int_least32_t)cp;
+	prop_title[cp].property = (int_least32_t)title - (int_least32_t)cp;
+
+	return 0;
+}
+
+static int
+parse_cp_list(const char *str, uint_least32_t **cp, size_t *cplen)
+{
+	size_t count, i;
+	const char *tmp1 = NULL, *tmp2 = NULL;
+
+	/* count the number of spaces in the string and infer list length */
+	for (count = 1, tmp1 = str; (tmp2 = strchr(tmp1, ' ')) != NULL; count++, tmp1 = tmp2 + 1)
+		;
+
+	/* allocate resources */
+	if (!(*cp = calloc((*cplen = count), sizeof(**cp)))) {
+		fprintf(stderr, "calloc: %s\n", strerror(errno));
+		exit(1);
+	}
+
+	/* go through the string again, parsing the numbers */
+	for (i = 0, tmp1 = tmp2 = str; tmp2 != NULL; i++) {
+		tmp2 = strchr(tmp1, ' ');
+		if (hextocp(tmp1, tmp2 ? (size_t)(tmp2 - tmp1) : strlen(tmp1), &((*cp)[i]))) {
+			return 1;
+		}
+		if (tmp2 != NULL) {
+			tmp1 = tmp2 + 1;
+		}
+	}
+
+	return 0;
+}
+
+static int
+specialcasing_callback(const char *file, char **field, size_t nfields,
+                       char *comment, void *payload)
+{
+	uint_least32_t cp;
+
+	(void)file;
+	(void)comment;
+	(void)payload;
+
+	if (nfields > 4 && strlen(field[4]) > 0) {
+		/*
+		 * we have more than 4 fields, i.e. the rule has a
+		 * condition (language-sensitive, etc.) and is discarded
+		 */
+		return 0;
+	}
+
+	/* parse affected codepoint */
+	hextocp(field[0], strlen(field[0]), &cp);
+
+	/* extend special case array */
+	if (!(sc = realloc(sc, (++sclen) * sizeof(*sc)))) {
+		fprintf(stderr, "realloc: %s\n", strerror(errno));
+		exit(1);	
+	}
+
+	/* parse field data */
+	parse_cp_list(field[3], &(sc[sclen - 1].upper.cp),
+	              &(sc[sclen - 1].upper.cplen));
+	parse_cp_list(field[1], &(sc[sclen - 1].lower.cp),
+	              &(sc[sclen - 1].lower.cplen));
+	parse_cp_list(field[2], &(sc[sclen - 1].title.cp),
+	              &(sc[sclen - 1].title.cplen));
+
+	/*
+	 * overwrite value in "single mapping" property table by the
+	 * special value 0x110000 + (offset in special case array),
+	 * even if the special case has length 1
+	 */
+	prop_upper[cp].property = (int_least64_t)(UINT32_C(0x110000) + (sclen - 1));
+	prop_lower[cp].property = (int_least64_t)(UINT32_C(0x110000) + (sclen - 1));
+	prop_title[cp].property = (int_least64_t)(UINT32_C(0x110000) + (sclen - 1));
+
+	return 0;
+}
+
+static int_least64_t
+get_value(const struct properties *prop, size_t offset)
+{
+	return prop[offset].property;
+}
+
+int
+main(int argc, char *argv[])
+{
+	struct properties_compressed comp_upper, comp_lower, comp_title;
+	struct properties_major_minor mm_upper, mm_lower, mm_title;
+	size_t i, j;
+
+	(void)argc;
+
+	/* generate case property table from the specification */
+	properties_generate_break_property(case_property,
+	                                   LEN(case_property),
+	                                   handle_conflict, NULL, "case",
+	                                   argv[0]);
+
+	/*
+	 * allocate property buffers for all 0x110000 codepoints
+	 *
+	 * the buffers contain the offset from the "base" character
+	 * to the respective case mapping. By callocing we set all fields
+	 * to zero, which is also the Unicode "default" in the sense that
+	 * there is no case mapping by default (unless we fill it in)
+	 */
+	if (!(prop_upper = calloc(UINT32_C(0x110000), sizeof(*prop_upper))) ||
+	    !(prop_lower = calloc(UINT32_C(0x110000), sizeof(*prop_lower))) ||
+	    !(prop_title = calloc(UINT32_C(0x110000), sizeof(*prop_title)))) {
+		fprintf(stderr, "calloc: %s\n", strerror(errno));
+		exit(1);
+	}
+	parse_file_with_callback("data/UnicodeData.txt", unicodedata_callback,
+	                         NULL);
+	parse_file_with_callback("data/SpecialCasing.txt", specialcasing_callback,
+	                         NULL);
+
+	/* compress properties */
+	properties_compress(prop_upper, &comp_upper);
+	properties_compress(prop_lower, &comp_lower);
+	properties_compress(prop_title, &comp_title);
+
+	fprintf(stderr, "%s: LUT compression-ratios: upper=%.2f%%, lower=%.2f%%, title=%.2f%%\n",
+	        argv[0], properties_get_major_minor(&comp_upper, &mm_upper),
+	        properties_get_major_minor(&comp_lower, &mm_lower),
+	        properties_get_major_minor(&comp_title, &mm_title));
+
+	/* print tables */
+	printf("/* Automatically generated by %s */\n#include <stdint.h>\n#include <stddef.h>\n\n", argv[0]);
+
+	printf("struct special_case {\n\tuint_least32_t *cp;\n\tsize_t cplen;\n};\n\n");
+
+	properties_print_lookup_table("upper_major", mm_upper.major, 0x1100);
+	printf("\n");
+	properties_print_derived_lookup_table("upper_minor", "int_least32_t", mm_upper.minor,
+	                                      mm_upper.minorlen, get_value, comp_upper.data);
+	printf("\n");
+	properties_print_lookup_table("lower_major", mm_lower.major, 0x1100);
+	printf("\n");
+	properties_print_derived_lookup_table("lower_minor", "int_least32_t", mm_lower.minor,
+	                                      mm_lower.minorlen, get_value, comp_lower.data);
+	printf("\n");
+	properties_print_lookup_table("title_major", mm_title.major, 0x1100);
+	printf("\n");
+	properties_print_derived_lookup_table("title_minor", "int_least32_t", mm_title.minor,
+	                                      mm_title.minorlen, get_value, comp_title.data);
+	printf("\n");
+
+	printf("static const struct special_case upper_special[] = {\n");
+	for (i = 0; i < sclen; i++) {
+		printf("\t{\n");
+
+		printf("\t\t.cp     = (uint_least32_t[]){");
+		for (j = 0; j < sc[i].upper.cplen; j++) {
+			printf(" UINT32_C(0x%06X)", sc[i].upper.cp[j]);
+			if (j + 1 < sc[i].upper.cplen) {
+				putchar(',');
+			}
+		}
+		printf(" },\n");
+		printf("\t\t.cplen  = %zu,\n", sc[i].upper.cplen);
+		printf("\t},\n");
+	}
+	printf("};\n\n");
+
+	printf("static const struct special_case lower_special[] = {\n");
+	for (i = 0; i < sclen; i++) {
+		printf("\t{\n");
+
+		printf("\t\t.cp     = (uint_least32_t[]){");
+		for (j = 0; j < sc[i].lower.cplen; j++) {
+			printf(" UINT32_C(0x%06X)", sc[i].lower.cp[j]);
+			if (j + 1 < sc[i].lower.cplen) {
+				putchar(',');
+			}
+		}
+		printf(" },\n");
+		printf("\t\t.cplen  = %zu,\n", sc[i].lower.cplen);
+		printf("\t},\n");
+	}
+	printf("};\n\n");
+
+	printf("static const struct special_case title_special[] = {\n");
+	for (i = 0; i < sclen; i++) {
+		printf("\t{\n");
+
+		printf("\t\t.cp     = (uint_least32_t[]){");
+		for (j = 0; j < sc[i].title.cplen; j++) {
+			printf(" UINT32_C(0x%06X)", sc[i].title.cp[j]);
+			if (j + 1 < sc[i].title.cplen) {
+				putchar(',');
+			}
+		}
+		printf(" },\n");
+		printf("\t\t.cplen  = %zu,\n", sc[i].title.cplen);
+		printf("\t},\n");
+	}
+	printf("};\n\n");
+
+	free(comp_lower.data);
+	free(comp_lower.offset);
+	free(comp_title.data);
+	free(comp_title.offset);
+	free(comp_upper.data);
+	free(comp_upper.offset);
+	free(mm_lower.major);
+	free(mm_lower.minor);
+	free(mm_title.major);
+	free(mm_title.minor);
+	free(mm_upper.major);
+	free(mm_upper.minor);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/gen/character-test.c

@@ -0,0 +1,19 @@
+/* See LICENSE file for copyright and license details. */
+#include <stddef.h>
+
+#include "util.h"
+
+int
+main(int argc, char *argv[])
+{
+	struct break_test *test = NULL;
+	size_t testlen = 0;
+
+	(void)argc;
+
+	break_test_list_parse("data/GraphemeBreakTest.txt", &test, &testlen);
+	break_test_list_print(test, testlen, "character_break_test", argv[0]);
+	break_test_list_free(test, testlen);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/gen/character.c

@@ -0,0 +1,97 @@
+/* See LICENSE file for copyright and license details. */
+#include <stddef.h>
+
+#include "util.h"
+
+#define FILE_EMOJI    "data/emoji-data.txt"
+#define FILE_GRAPHEME "data/GraphemeBreakProperty.txt"
+
+static const struct property_spec char_break_property[] = {
+	{
+		.enumname = "OTHER",
+		.file     = NULL,
+		.ucdname  = NULL,
+	},
+	{
+		.enumname = "CONTROL",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "Control",
+	},
+	{
+		.enumname = "CR",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "CR",
+	},
+	{
+		.enumname = "EXTEND",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "Extend",
+	},
+	{
+		.enumname = "EXTENDED_PICTOGRAPHIC",
+		.file     = FILE_EMOJI,
+		.ucdname  = "Extended_Pictographic",
+	},
+	{
+		.enumname = "HANGUL_L",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "L",
+	},
+	{
+		.enumname = "HANGUL_V",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "V",
+	},
+	{
+		.enumname = "HANGUL_T",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "T",
+	},
+	{
+		.enumname = "HANGUL_LV",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "LV",
+	},
+	{
+		.enumname = "HANGUL_LVT",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "LVT",
+	},
+	{
+		.enumname = "LF",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "LF",
+	},
+	{
+		.enumname = "PREPEND",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "Prepend",
+	},
+	{
+		.enumname = "REGIONAL_INDICATOR",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "Regional_Indicator",
+	},
+	{
+		.enumname = "SPACINGMARK",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "SpacingMark",
+	},
+	{
+		.enumname = "ZWJ",
+		.file     = FILE_GRAPHEME,
+		.ucdname  = "ZWJ",
+	},
+};
+
+int
+main(int argc, char *argv[])
+{
+	(void)argc;
+
+	properties_generate_break_property(char_break_property,
+	                                   LEN(char_break_property),
+	                                   NULL, NULL, "char_break", argv[0]);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/gen/line-test.c

@@ -0,0 +1,19 @@
+/* See LICENSE file for copyright and license details. */
+#include <stddef.h>
+
+#include "util.h"
+
+int
+main(int argc, char *argv[])
+{
+	struct break_test *test = NULL;
+	size_t testlen = 0;
+
+	(void)argc;
+
+	break_test_list_parse("data/LineBreakTest.txt", &test, &testlen);
+	break_test_list_print(test, testlen, "line_break_test", argv[0]);
+	break_test_list_free(test, testlen);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/gen/line.c

@@ -0,0 +1,456 @@
+/* See LICENSE file for copyright and license details. */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "util.h"
+
+#define FILE_EAW   "data/EastAsianWidth.txt"
+#define FILE_EMOJI "data/emoji-data.txt"
+#define FILE_LINE  "data/LineBreak.txt"
+
+static const struct property_spec line_break_property[] = {
+	{
+		.enumname = "AL",
+		.file     = FILE_LINE,
+		.ucdname  = "AL",
+	},
+	/*
+	 * Both extended pictographic and cn are large classes,
+	 * but we are only interested in their intersection for LB30b,
+	 * so we have the following two temporary classes. At first
+	 * the extpict-class is filled, then the cn-class, which leads
+	 * to conflicts (that we handle by putting them in the "proper"
+	 * class BOTH_CN_EXTPICT). We make use of the fact that there
+	 * is no intersection between AL and Cn.
+	 *
+	 * Any consecutive conflicts are permitted to overwrite
+	 * TMP_EXTENDED_PICTOGRAPHIC and TMP_CN, because we don't need
+	 * them, and in the final postprocessing we "reset" all
+	 * remaining matches (that then didn't fit any of the other
+	 * classes) to the generic class AL.
+	 */
+	{
+		.enumname = "TMP_CN",
+		.file     = FILE_LINE,
+		.ucdname  = "Cn",
+	},
+	{
+		.enumname = "TMP_EXTENDED_PICTOGRAPHIC",
+		.file     = FILE_EMOJI,
+		.ucdname  = "Extended_Pictographic",
+	},
+	/* end of special block */
+	{
+		.enumname = "B2",
+		.file     = FILE_LINE,
+		.ucdname  = "B2",
+	},
+	{
+		.enumname = "BA",
+		.file     = FILE_LINE,
+		.ucdname  = "BA",
+	},
+	{
+		.enumname = "BB",
+		.file     = FILE_LINE,
+		.ucdname  = "BB",
+	},
+	{
+		.enumname = "BK",
+		.file     = FILE_LINE,
+		.ucdname  = "BK",
+	},
+	{
+		.enumname = "BOTH_CN_EXTPICT",
+		.file     = NULL,
+		.ucdname  = NULL,
+	},
+	{
+		.enumname = "CB",
+		.file     = FILE_LINE,
+		.ucdname  = "CB",
+	},
+	{
+		.enumname = "CL",
+		.file     = FILE_LINE,
+		.ucdname  = "CL",
+	},
+	{
+		.enumname = "CM",
+		.file     = FILE_LINE,
+		.ucdname  = "CM",
+	},
+	{
+		.enumname = "CP_WITHOUT_EAW_HWF",
+		.file     = FILE_LINE,
+		.ucdname  = "CP",
+	},
+	{
+		.enumname = "CP_WITH_EAW_HWF",
+		.file     = NULL,
+		.ucdname  = NULL,
+	},
+	{
+		.enumname = "CR",
+		.file     = FILE_LINE,
+		.ucdname  = "CR",
+	},
+	{
+		.enumname = "EB",
+		.file     = FILE_LINE,
+		.ucdname  = "EB",
+	},
+	{
+		.enumname = "EM",
+		.file     = FILE_LINE,
+		.ucdname  = "EM",
+	},
+	{
+		.enumname = "EX",
+		.file     = FILE_LINE,
+		.ucdname  = "EX",
+	},
+	{
+		.enumname = "GL",
+		.file     = FILE_LINE,
+		.ucdname  = "GL",
+	},
+	{
+		.enumname = "H2",
+		.file     = FILE_LINE,
+		.ucdname  = "H2",
+	},
+	{
+		.enumname = "H3",
+		.file     = FILE_LINE,
+		.ucdname  = "H3",
+	},
+	{
+		.enumname = "HL",
+		.file     = FILE_LINE,
+		.ucdname  = "HL",
+	},
+	{
+		.enumname = "HY",
+		.file     = FILE_LINE,
+		.ucdname  = "HY",
+	},
+	{
+		.enumname = "ID",
+		.file     = FILE_LINE,
+		.ucdname  = "ID",
+	},
+	{
+		.enumname = "IN",
+		.file     = FILE_LINE,
+		.ucdname  = "IN",
+	},
+	{
+		.enumname = "IS",
+		.file     = FILE_LINE,
+		.ucdname  = "IS",
+	},
+	{
+		.enumname = "JL",
+		.file     = FILE_LINE,
+		.ucdname  = "JL",
+	},
+	{
+		.enumname = "JT",
+		.file     = FILE_LINE,
+		.ucdname  = "JT",
+	},
+	{
+		.enumname = "JV",
+		.file     = FILE_LINE,
+		.ucdname  = "JV",
+	},
+	{
+		.enumname = "LF",
+		.file     = FILE_LINE,
+		.ucdname  = "LF",
+	},
+	{
+		.enumname = "NL",
+		.file     = FILE_LINE,
+		.ucdname  = "NL",
+	},
+	{
+		.enumname = "NS",
+		.file     = FILE_LINE,
+		.ucdname  = "NS",
+	},
+	{
+		.enumname = "NU",
+		.file     = FILE_LINE,
+		.ucdname  = "NU",
+	},
+	{
+		.enumname = "OP_WITHOUT_EAW_HWF",
+		.file     = FILE_LINE,
+		.ucdname  = "OP",
+	},
+	{
+		.enumname = "OP_WITH_EAW_HWF",
+		.file     = NULL,
+		.ucdname  = NULL,
+	},
+	{
+		.enumname = "PO",
+		.file     = FILE_LINE,
+		.ucdname  = "PO",
+	},
+	{
+		.enumname = "PR",
+		.file     = FILE_LINE,
+		.ucdname  = "PR",
+	},
+	{
+		.enumname = "QU",
+		.file     = FILE_LINE,
+		.ucdname  = "QU",
+	},
+	{
+		.enumname = "RI",
+		.file     = FILE_LINE,
+		.ucdname  = "RI",
+	},
+	{
+		.enumname = "SP",
+		.file     = FILE_LINE,
+		.ucdname  = "SP",
+	},
+	{
+		.enumname = "SY",
+		.file     = FILE_LINE,
+		.ucdname  = "SY",
+	},
+	{
+		.enumname = "WJ",
+		.file     = FILE_LINE,
+		.ucdname  = "WJ",
+	},
+	{
+		.enumname = "ZW",
+		.file     = FILE_LINE,
+		.ucdname  = "ZW",
+	},
+	{
+		.enumname = "ZWJ",
+		.file     = FILE_LINE,
+		.ucdname  = "ZWJ",
+	},
+	{
+		.enumname = "TMP_AI",
+		.file     = FILE_LINE,
+		.ucdname  = "AI",
+	},
+	{
+		.enumname = "TMP_CJ",
+		.file     = FILE_LINE,
+		.ucdname  = "CJ",
+	},
+	{
+		.enumname = "TMP_XX",
+		.file     = NULL,
+		.ucdname  = NULL,
+	},
+	{
+		.enumname = "TMP_MN",
+		.file     = FILE_LINE,
+		.ucdname  = "Mn",
+	},
+	{
+		.enumname = "TMP_MC",
+		.file     = FILE_LINE,
+		.ucdname  = "Mc",
+	},
+	{
+		.enumname = "TMP_SA_WITHOUT_MN_OR_MC",
+		.file     = FILE_LINE,
+		.ucdname  = "SA",
+	},
+	{
+		.enumname = "TMP_SA_WITH_MN_OR_MC",
+		.file     = FILE_LINE,
+		.ucdname  = "SA",
+	},
+	{
+		.enumname = "TMP_SG",
+		.file     = FILE_LINE,
+		.ucdname  = "SG",
+	},
+	{
+		.enumname = "TMP_EAW_H",
+		.file     = FILE_EAW,
+		.ucdname  = "H",
+	},
+	{
+		.enumname = "TMP_EAW_W",
+		.file     = FILE_EAW,
+		.ucdname  = "W",
+	},
+	{
+		.enumname = "TMP_EAW_F",
+		.file     = FILE_EAW,
+		.ucdname  = "F",
+	},
+};
+
+static uint_least8_t
+handle_conflict(uint_least32_t cp, uint_least8_t prop1, uint_least8_t prop2)
+{
+	uint_least8_t result = prop2;
+	char *target = NULL;
+
+	(void)cp;
+
+	if ((!strcmp(line_break_property[prop1].enumname, "TMP_EAW_H")  ||
+	     !strcmp(line_break_property[prop1].enumname, "TMP_EAW_W")  ||
+	     !strcmp(line_break_property[prop1].enumname, "TMP_EAW_F")) ||
+	    (!strcmp(line_break_property[prop2].enumname, "TMP_EAW_H") ||
+	     !strcmp(line_break_property[prop2].enumname, "TMP_EAW_W") ||
+	     !strcmp(line_break_property[prop2].enumname, "TMP_EAW_F"))) {
+		if (!strcmp(line_break_property[prop1].enumname, "CP_WITHOUT_EAW_HWF") ||
+		    !strcmp(line_break_property[prop2].enumname, "CP_WITHOUT_EAW_HWF")) {
+			target = "CP_WITH_EAW_HWF";
+		} else if (!strcmp(line_break_property[prop1].enumname, "OP_WITHOUT_EAW_HWF") ||
+		    !strcmp(line_break_property[prop2].enumname, "OP_WITHOUT_EAW_HWF")) {
+			target = "OP_WITH_EAW_HWF";
+		} else {
+			/* ignore EAW for the rest */
+			if ((!strcmp(line_break_property[prop1].enumname, "TMP_EAW_H") ||
+			     !strcmp(line_break_property[prop1].enumname, "TMP_EAW_W") ||
+			     !strcmp(line_break_property[prop1].enumname, "TMP_EAW_F"))) {
+				result = prop2;
+			} else {
+				result = prop1;
+			}
+		}
+	} else if ((!strcmp(line_break_property[prop1].enumname, "TMP_MN") ||
+	            !strcmp(line_break_property[prop1].enumname, "TMP_MC")) ||
+		   (!strcmp(line_break_property[prop2].enumname, "TMP_MN") ||
+		    !strcmp(line_break_property[prop2].enumname, "TMP_MC"))) {
+		if (!strcmp(line_break_property[prop1].enumname, "SA_WITHOUT_MN_OR_MC") ||
+		    !strcmp(line_break_property[prop2].enumname, "SA_WITHOUT_MN_OR_MC")) {
+			target = "SA_WITH_MN_OR_MC";
+		} else {
+			/* ignore Mn and Mc for the rest */
+			if ((!strcmp(line_break_property[prop1].enumname, "TMP_MN") ||
+			     !strcmp(line_break_property[prop1].enumname, "TMP_MC"))) {
+				result = prop2;
+			} else {
+				result = prop1;
+			}
+		}
+	} else if (!strcmp(line_break_property[prop1].enumname, "TMP_CN") ||
+	           !strcmp(line_break_property[prop2].enumname, "TMP_CN")) {
+		if (!strcmp(line_break_property[prop1].enumname, "TMP_EXTENDED_PICTOGRAPHIC") ||
+		    !strcmp(line_break_property[prop2].enumname, "TMP_EXTENDED_PICTOGRAPHIC")) {
+			target = "BOTH_CN_EXTPICT";
+		} else {
+			/* ignore Cn for all the other properties */
+			if (!strcmp(line_break_property[prop1].enumname, "TMP_CN")) {
+				result = prop2;
+			} else {
+				result = prop1;
+			}
+		}
+	} else if (!strcmp(line_break_property[prop1].enumname, "TMP_EXTENDED_PICTOGRAPHIC") ||
+	           !strcmp(line_break_property[prop2].enumname, "TMP_EXTENDED_PICTOGRAPHIC")) {
+		if (!strcmp(line_break_property[prop1].enumname, "TMP_CN") ||
+		    !strcmp(line_break_property[prop2].enumname, "TMP_CN")) {
+			target = "BOTH_CN_EXTPICT";
+		} else {
+			/* ignore Extended_Pictographic for all the other properties */
+			if (!strcmp(line_break_property[prop1].enumname, "TMP_EXTENDED_PICTOGRAPHIC")) {
+				result = prop2;
+			} else {
+				result = prop1;
+			}
+		}
+	} else {
+		fprintf(stderr, "handle_conflict: Cannot handle conflict %s <- %s.\n",
+		        line_break_property[prop1].enumname, line_break_property[prop2].enumname);
+		exit(1);
+	}
+
+	if (target) {
+		for (result = 0; result < LEN(line_break_property); result++) {
+			if (!strcmp(line_break_property[result].enumname,
+			            target)) {
+				break;
+			}
+		}
+		if (result == LEN(line_break_property)) {
+			fprintf(stderr, "handle_conflict: Internal error.\n");
+			exit(1);
+		}
+	}
+
+	return result;
+}
+
+static uint_least8_t
+post_process(uint_least8_t prop)
+{
+	const char *target = NULL;
+	uint_least8_t result;
+
+	/* LB1 */
+	if (!strcmp(line_break_property[prop].enumname, "TMP_AI") ||
+	    !strcmp(line_break_property[prop].enumname, "TMP_SG") ||
+	    !strcmp(line_break_property[prop].enumname, "TMP_XX")) {
+		/* map AI, SG and XX to AL */
+		target = "AL";
+	} else if (!strcmp(line_break_property[prop].enumname, "TMP_SA_WITH_MN_OR_MC")) {
+		/* map SA (with General_Category Mn or Mc) to CM */
+		target = "CM";
+	} else if (!strcmp(line_break_property[prop].enumname, "TMP_SA_WITHOUT_MN_OR_MC")) {
+		/* map SA (without General_Category Mn or Mc) to AL */
+		target = "AL";
+	} else if (!strcmp(line_break_property[prop].enumname, "TMP_CJ")) {
+		/* map CJ to NS */
+		target = "NS";
+	} else if (!strcmp(line_break_property[prop].enumname, "TMP_CN") ||
+	           !strcmp(line_break_property[prop].enumname, "TMP_EXTENDED_PICTOGRAPHIC") ||
+	           !strcmp(line_break_property[prop].enumname, "TMP_MN") ||
+	           !strcmp(line_break_property[prop].enumname, "TMP_MC") ||
+	           !strcmp(line_break_property[prop].enumname, "TMP_EAW_H") ||
+	           !strcmp(line_break_property[prop].enumname, "TMP_EAW_W") ||
+	           !strcmp(line_break_property[prop].enumname, "TMP_EAW_F")) {
+		/* map all the temporary classes "residue" to AL */
+		target = "AL";
+	}
+
+	if (target) {
+		for (result = 0; result < LEN(line_break_property); result++) {
+			if (!strcmp(line_break_property[result].enumname,
+			            target)) {
+				break;
+			}
+		}
+		if (result == LEN(line_break_property)) {
+			fprintf(stderr, "handle_conflict: Internal error.\n");
+			exit(1);
+		}
+
+		return result;
+	} else {
+		return prop;
+	}
+}
+
+int
+main(int argc, char *argv[])
+{
+	(void)argc;
+
+	properties_generate_break_property(line_break_property,
+	                                   LEN(line_break_property),
+	                                   handle_conflict, post_process,
+	                                   "line_break", argv[0]);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/gen/sentence-test.c

@@ -0,0 +1,19 @@
+/* See LICENSE file for copyright and license details. */
+#include <stddef.h>
+
+#include "util.h"
+
+int
+main(int argc, char *argv[])
+{
+	struct break_test *test = NULL;
+	size_t testlen = 0;
+
+	(void)argc;
+
+	break_test_list_parse("data/SentenceBreakTest.txt", &test, &testlen);
+	break_test_list_print(test, testlen, "sentence_break_test", argv[0]);
+	break_test_list_free(test, testlen);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/gen/sentence.c

@@ -0,0 +1,94 @@
+/* See LICENSE file for copyright and license details. */
+#include "util.h"
+
+#define FILE_SENTENCE "data/SentenceBreakProperty.txt"
+
+static const struct property_spec sentence_break_property[] = {
+	{
+		.enumname = "OTHER",
+		.file     = NULL,
+		.ucdname  = NULL,
+	},
+	{
+		.enumname = "CR",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "CR",
+	},
+	{
+		.enumname = "LF",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "LF",
+	},
+	{
+		.enumname = "EXTEND",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "Extend",
+	},
+	{
+		.enumname = "SEP",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "Sep",
+	},
+	{
+		.enumname = "FORMAT",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "Format",
+	},
+	{
+		.enumname = "SP",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "Sp",
+	},
+	{
+		.enumname = "LOWER",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "Lower",
+	},
+	{
+		.enumname = "UPPER",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "Upper",
+	},
+	{
+		.enumname = "OLETTER",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "OLetter",
+	},
+	{
+		.enumname = "NUMERIC",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "Numeric",
+	},
+	{
+		.enumname = "ATERM",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "ATerm",
+	},
+	{
+		.enumname = "SCONTINUE",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "SContinue",
+	},
+	{
+		.enumname = "STERM",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "STerm",
+	},
+	{
+		.enumname = "CLOSE",
+		.file     = FILE_SENTENCE,
+		.ucdname  = "Close",
+	},
+};
+
+int
+main(int argc, char *argv[])
+{
+	(void)argc;
+
+	properties_generate_break_property(sentence_break_property,
+	                                   LEN(sentence_break_property),
+	                                   NULL, NULL, "sentence_break", argv[0]);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/gen/types.h

@@ -0,0 +1,16 @@
+/* See LICENSE file for copyright and license details. */
+#ifndef TYPES_H
+#define TYPES_H
+
+#include <stddef.h>
+#include <stdint.h>
+
+struct break_test {
+	uint_least32_t *cp;
+	size_t cplen;
+	size_t *len;
+	size_t lenlen;
+	char *descr;
+};
+
+#endif /* TYPES_H */

libs/libgrapheme-2.0.2/gen/util.c

@@ -0,0 +1,704 @@
+/* See LICENSE file for copyright and license details. */
+#include <stdbool.h>
+#include <ctype.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+
+#include "util.h"
+
+struct range {
+	uint_least32_t lower;
+	uint_least32_t upper;
+};
+
+struct properties_payload {
+	struct properties *prop;
+	const struct property_spec *spec;
+	uint_least8_t speclen;
+	int (*set_value)(struct properties_payload *, uint_least32_t, int_least64_t);
+	uint_least8_t (*handle_conflict)(uint_least32_t, uint_least8_t, uint_least8_t);
+};
+
+struct break_test_payload
+{
+	struct break_test **test;
+	size_t *testlen;
+};
+
+static void *
+reallocate_array(void *p, size_t len, size_t size)
+{
+	if (len > 0 && size > SIZE_MAX / len) {
+		errno = ENOMEM;
+		return NULL;
+	}
+
+	return realloc(p, len * size);
+}
+
+int
+hextocp(const char *str, size_t len, uint_least32_t *cp)
+{
+	size_t i;
+	int off;
+	char relative;
+
+	/* the maximum valid codepoint is 0x10FFFF */
+	if (len > 6) {
+		fprintf(stderr, "hextocp: '%.*s' is too long.\n",
+		        (int)len, str);
+		return 1;
+	}
+
+	for (i = 0, *cp = 0; i < len; i++) {
+		if (str[i] >= '0' && str[i] <= '9') {
+			relative = '0';
+			off = 0;
+		} else if (str[i] >= 'a' && str[i] <= 'f') {
+			relative = 'a';
+			off = 10;
+		} else if (str[i] >= 'A' && str[i] <= 'F') {
+			relative = 'A';
+			off = 10;
+		} else {
+			fprintf(stderr, "hextocp: '%.*s' is not hexadecimal.\n",
+			        (int)len, str);
+			return 1;
+		}
+
+		*cp += ((uint_least32_t)1 << (4 * (len - i - 1))) *
+		       (uint_least32_t)(str[i] - relative + off);
+	}
+
+	if (*cp > UINT32_C(0x10FFFF)) {
+		fprintf(stderr, "hextocp: '%.*s' is too large.\n",
+		        (int)len, str);
+		return 1;
+	}
+
+	return 0;
+}
+
+static int
+range_parse(const char *str, struct range *range)
+{
+	char *p;
+
+	if ((p = strstr(str, "..")) == NULL) {
+		/* input has the form "XXXXXX" */
+		if (hextocp(str, strlen(str), &range->lower)) {
+			return 1;
+		}
+		range->upper = range->lower;
+	} else {
+		/* input has the form "XXXXXX..XXXXXX" */
+		if (hextocp(str, (size_t)(p - str), &range->lower) ||
+		    hextocp(p + 2, strlen(p + 2), &range->upper)) {
+			return 1;
+		}
+	}
+
+	return 0;
+}
+
+void
+parse_file_with_callback(const char *fname, int (*callback)(const char *,
+                         char **, size_t, char *, void *), void *payload)
+{
+	FILE *fp;
+	char *line = NULL, **field = NULL, *comment;
+	size_t linebufsize = 0, i, fieldbufsize = 0, j, nfields;
+	ssize_t len;
+
+	/* open file */
+	if (!(fp = fopen(fname, "r"))) {
+		fprintf(stderr, "parse_file_with_callback: fopen '%s': %s.\n",
+		        fname, strerror(errno));
+		exit(1);
+	}
+
+	while ((len = getline(&line, &linebufsize, fp)) >= 0) {
+		/* remove trailing newline */
+		if (len > 0 && line[len - 1] == '\n') {
+			line[len - 1] = '\0';
+			len--;
+		}
+
+		/* skip empty lines and comment lines */
+		if (len == 0 || line[0] == '#') {
+			continue;
+		}
+
+		/* tokenize line into fields */
+		for (i = 0, nfields = 0, comment = NULL; i < (size_t)len; i++) {
+			/* skip leading whitespace */
+			while (line[i] == ' ') {
+				i++;
+			}
+
+			/* check if we crashed into the comment */
+			if (line[i] != '#') {
+				/* extend field buffer, if necessary */
+				if (++nfields > fieldbufsize) {
+					if ((field = realloc(field, nfields *
+					      sizeof(*field))) == NULL) {
+						fprintf(stderr, "parse_file_with_"
+						        "callback: realloc: %s.\n",
+						        strerror(errno));
+						exit(1);
+					}
+					fieldbufsize = nfields;
+				}
+
+				/* set current position as field start */
+				field[nfields - 1] = &line[i];
+
+				/* continue until we reach ';' or '#' or end */
+				while (line[i] != ';' && line[i] != '#' &&
+				       line[i] != '\0') {
+					i++;
+				}
+			}
+
+			if (line[i] == '#') {
+				/* set comment-variable for later */
+				comment = &line[i + 1];
+			}
+
+			/* go back whitespace and terminate field there */
+			if (i > 0) {
+				for (j = i - 1; line[j] == ' '; j--)
+					;
+				line[j + 1] = '\0';
+			} else {
+				line[i] = '\0';
+			}
+
+			/* if comment is set, we are done */
+			if (comment != NULL) {
+				break;
+			}
+		}
+
+		/* skip leading whitespace in comment */
+		while (comment != NULL && comment[0] == ' ') {
+			comment++;
+		}
+
+		/* call callback function */
+		if (callback(fname, field, nfields, comment, payload)) {
+			fprintf(stderr, "parse_file_with_callback: "
+			        "Malformed input.\n");
+			exit(1);
+		}
+	}
+
+	free(line);
+	free(field);
+}
+
+static int
+properties_callback(const char *file, char **field, size_t nfields,
+                    char *comment, void *payload)
+{
+	/* prop always has the length 0x110000 */
+	struct properties_payload *p = (struct properties_payload *)payload;
+	struct range r;
+	uint_least8_t i;
+	uint_least32_t cp;
+
+	(void)comment;
+
+	if (nfields < 2) {
+		return 1;
+	}
+
+	for (i = 0; i < p->speclen; i++) {
+		/* identify fitting file and identifier */
+		if (p->spec[i].file &&
+		    !strcmp(p->spec[i].file, file) &&
+		    (!strcmp(p->spec[i].ucdname, field[1]) ||
+		     (comment != NULL && !strncmp(p->spec[i].ucdname, comment, strlen(p->spec[i].ucdname)) &&
+		      comment[strlen(p->spec[i].ucdname)] == ' '))) {
+			/* parse range in first field */
+			if (range_parse(field[0], &r)) {
+				return 1;
+			}
+
+			/* apply to all codepoints in the range */
+			for (cp = r.lower; cp <= r.upper; cp++) {
+				if (p->set_value(payload, cp, i)) {
+					exit(1);
+				}
+			}
+			break;
+		}
+	}
+
+	return 0;
+}
+
+void
+properties_compress(const struct properties *prop,
+                    struct properties_compressed *comp)
+{
+	uint_least32_t cp, i;
+
+	/* initialization */
+	if (!(comp->offset = malloc((size_t)UINT32_C(0x110000) * sizeof(*(comp->offset))))) {
+		fprintf(stderr, "malloc: %s\n", strerror(errno));
+		exit(1);
+	}
+	comp->data = NULL;
+	comp->datalen = 0;
+
+	for (cp = 0; cp < UINT32_C(0x110000); cp++) {
+		for (i = 0; i < comp->datalen; i++) {
+			if (!memcmp(&(prop[cp]), &(comp->data[i]), sizeof(*prop))) {
+				/* found a match! */
+				comp->offset[cp] = i;
+				break;
+			}
+		}
+		if (i == comp->datalen) {
+			/*
+			 * found no matching properties-struct, so
+			 * add current properties to data and add the
+			 * offset in the offset-table
+			 */
+			if (!(comp->data = reallocate_array(comp->data,
+			                                    ++(comp->datalen),
+			                                    sizeof(*(comp->data))))) {
+				fprintf(stderr, "reallocate_array: %s\n",
+				        strerror(errno));
+				exit(1);
+			}
+			memcpy(&(comp->data[comp->datalen - 1]), &(prop[cp]),
+			       sizeof(*prop));
+			comp->offset[cp] = comp->datalen - 1;
+		}
+	}
+}
+
+double
+properties_get_major_minor(const struct properties_compressed *comp,
+                           struct properties_major_minor *mm)
+{
+	size_t i, j, compression_count = 0;
+
+	/*
+	 * we currently have an array comp->offset which maps the
+	 * codepoints 0..0x110000 to offsets into comp->data.
+	 * To improve cache-locality instead and allow a bit of
+	 * compressing, instead of directly mapping a codepoint
+	 * 0xAAAABB with comp->offset, we generate two arrays major
+	 * and minor such that
+	 *    comp->offset(0xAAAABB) == minor[major[0xAAAA] + 0xBB]
+	 * This yields a major-array of length 2^16 and a minor array
+	 * of variable length depending on how many common subsequences
+	 * can be filtered out.
+	 */
+
+	/* initialize */
+	if (!(mm->major = malloc((size_t)0x1100 * sizeof(*(mm->major))))) {
+		fprintf(stderr, "malloc: %s\n", strerror(errno));
+		exit(1);
+	}
+	mm->minor = NULL;
+	mm->minorlen = 0;
+
+	for (i = 0; i < (size_t)0x1100; i++) {
+		/*
+		 * we now look at the cp-range (i << 8)..(i << 8 + 0xFF)
+		 * and check if its corresponding offset-data already
+		 * exists in minor (because then we just point there
+		 * and need less storage)
+		 */
+		for (j = 0; j + 0xFF < mm->minorlen; j++) {
+			if (!memcmp(&(comp->offset[i << 8]),
+			            &(mm->minor[j]),
+			            sizeof(*(comp->offset)) * 0x100)) {
+				break;
+			}
+		}
+		if (j + 0xFF < mm->minorlen) {
+			/* found an index */
+			compression_count++;
+			mm->major[i] = j;
+		} else {
+			/*
+			 * add "new" sequence to minor and point to it
+			 * in major
+			 */
+			mm->minorlen += 0x100;
+			if (!(mm->minor = reallocate_array(mm->minor,
+			                                   mm->minorlen,
+			                                   sizeof(*(mm->minor))))) {
+				fprintf(stderr, "reallocate_array: %s\n",
+				        strerror(errno));
+				exit(1);
+			}
+			memcpy(&(mm->minor[mm->minorlen - 0x100]),
+			       &(comp->offset[i << 8]),
+			       sizeof(*(mm->minor)) * 0x100);
+			mm->major[i] = mm->minorlen - 0x100;
+		}
+	}
+
+	/* return compression ratio */
+	return (double)compression_count / 0x1100 * 100;
+}
+
+void
+properties_print_lookup_table(char *name, size_t *data, size_t datalen)
+{
+	char *type;
+	size_t i, maxval;
+
+	for (i = 0, maxval = 0; i < datalen; i++) {
+		if (data[i] > maxval) {
+			maxval = data[i];
+		}
+	}
+
+	type = (maxval <= UINT_LEAST8_MAX)  ? "uint_least8_t"  :
+	       (maxval <= UINT_LEAST16_MAX) ? "uint_least16_t" :
+	       (maxval <= UINT_LEAST32_MAX) ? "uint_least32_t" :
+	                                      "uint_least64_t";
+
+	printf("static const %s %s[] = {\n\t", type, name);
+	for (i = 0; i < datalen; i++) {
+		printf("%zu", data[i]);
+		if (i + 1 == datalen) {
+			printf("\n");
+		} else if ((i + 1) % 8 != 0) {
+			printf(", ");
+		} else {
+			printf(",\n\t");
+		}
+
+	}
+	printf("};\n");
+}
+
+void
+properties_print_derived_lookup_table(char *name, char *type, size_t *offset, size_t offsetlen,
+                                      int_least64_t (*get_value)(const struct properties *,
+                                      size_t), const void *payload)
+{
+	size_t i;
+
+	printf("static const %s %s[] = {\n\t", type, name);
+	for (i = 0; i < offsetlen; i++) {
+		printf("%"PRIiLEAST64, get_value(payload, offset[i]));
+		if (i + 1 == offsetlen) {
+			printf("\n");
+		} else if ((i + 1) % 8 != 0) {
+			printf(", ");
+		} else {
+			printf(",\n\t");
+		}
+
+	}
+	printf("};\n");
+}
+
+static void
+properties_print_enum(const struct property_spec *spec, size_t speclen,
+                      const char *enumname, const char *enumprefix)
+{
+	size_t i;
+
+	printf("enum %s {\n", enumname);
+	for (i = 0; i < speclen; i++) {
+		printf("\t%s_%s,\n", enumprefix, spec[i].enumname);
+	}
+	printf("\tNUM_%sS,\n};\n\n", enumprefix);
+}
+
+static int
+set_value_bp(struct properties_payload *payload, uint_least32_t cp,
+             int_least64_t value)
+{
+	if (payload->prop[cp].property != 0) {
+		if (payload->handle_conflict == NULL) {
+			fprintf(stderr, "set_value_bp: "
+	                        "Unhandled character break property "
+			        "overwrite for 0x%06X (%s <- %s).\n",
+		                cp, payload->spec[payload->prop[cp].
+			        property].enumname,
+			        payload->spec[value].enumname);
+			return 1;
+		} else {
+			value = payload->handle_conflict(cp,
+			        (uint_least8_t)payload->prop[cp].property,
+			        (uint_least8_t)value);
+		}
+	}
+	payload->prop[cp].property = value;
+
+	return 0;
+}
+
+static int_least64_t
+get_value_bp(const struct properties *prop, size_t offset)
+{
+	return (uint_least8_t)prop[offset].property;
+}
+
+void
+properties_generate_break_property(const struct property_spec *spec,
+                                   uint_least8_t speclen,
+                                   uint_least8_t (*handle_conflict)(
+                                   uint_least32_t, uint_least8_t,
+                                   uint_least8_t), uint_least8_t
+                                   (*post_process)(uint_least8_t),
+                                   const char *prefix, const char *argv0)
+{
+	struct properties_compressed comp;
+	struct properties_major_minor mm;
+	struct properties_payload payload;
+	struct properties *prop;
+	size_t i, j, prefixlen = strlen(prefix);
+	char buf1[64], prefix_uc[64], buf2[64], buf3[64], buf4[64];
+
+	/* allocate property buffer for all 0x110000 codepoints */
+	if (!(prop = calloc(UINT32_C(0x110000), sizeof(*prop)))) {
+		fprintf(stderr, "calloc: %s\n", strerror(errno));
+		exit(1);
+	}
+
+	/* generate data */
+	payload.prop = prop;
+	payload.spec = spec;
+	payload.speclen = speclen;
+	payload.set_value = set_value_bp;
+	payload.handle_conflict = handle_conflict;
+
+	/* parse each file exactly once and ignore NULL-fields */
+	for (i = 0; i < speclen; i++) {
+		for (j = 0; j < i; j++) {
+			if (spec[i].file && spec[j].file &&
+			    !strcmp(spec[i].file, spec[j].file)) {
+				/* file has already been parsed */
+				break;
+			}
+		}
+		if (i == j && spec[i].file) {
+			/* file has not been processed yet */
+			parse_file_with_callback(spec[i].file,
+			                         properties_callback,
+			                         &payload);
+		}
+	}
+
+	/* post-processing */
+	if (post_process != NULL) {
+		for (i = 0; i < UINT32_C(0x110000); i++) {
+			payload.prop[i].property =
+				post_process((uint_least8_t)payload.prop[i].property);
+		}
+	}
+
+	/* compress data */
+	printf("/* Automatically generated by %s */\n#include <stdint.h>\n\n", argv0);
+	properties_compress(prop, &comp);
+
+	fprintf(stderr, "%s: %s-LUT compression-ratio: %.2f%%\n", argv0,
+	        prefix, properties_get_major_minor(&comp, &mm));
+
+	/* prepare names */
+	if ((size_t)snprintf(buf1, LEN(buf1), "%s_property", prefix) >= LEN(buf1)) {
+		fprintf(stderr, "snprintf: String truncated.\n");
+		exit(1);
+	}
+	if (LEN(prefix_uc) + 1 < prefixlen) {
+		fprintf(stderr, "snprintf: Buffer too small.\n");
+		exit(1);
+	}
+	for (i = 0; i < prefixlen; i++) {
+		prefix_uc[i] = (char)toupper(prefix[i]);
+	}
+	prefix_uc[prefixlen] = '\0';
+	if ((size_t)snprintf(buf2, LEN(buf2), "%s_PROP", prefix_uc) >= LEN(buf2) ||
+	    (size_t)snprintf(buf3, LEN(buf3), "%s_major", prefix) >= LEN(buf3)   ||
+	    (size_t)snprintf(buf4, LEN(buf4), "%s_minor", prefix) >= LEN(buf4)) {
+		fprintf(stderr, "snprintf: String truncated.\n");
+		exit(1);
+	}
+
+	/* print data */
+	properties_print_enum(spec, speclen, buf1, buf2);
+	properties_print_lookup_table(buf3, mm.major, 0x1100);
+	printf("\n");
+	properties_print_derived_lookup_table(buf4, "uint_least8_t", mm.minor, mm.minorlen,
+	                                      get_value_bp, comp.data);
+
+	/* free data */
+	free(prop);
+	free(comp.data);
+	free(comp.offset);
+	free(mm.major);
+	free(mm.minor);
+}
+
+static int
+break_test_callback(const char *fname, char **field, size_t nfields,
+                      char *comment, void *payload)
+{
+	struct break_test *t,
+		**test = ((struct break_test_payload *)payload)->test;
+	size_t i, *testlen = ((struct break_test_payload *)payload)->testlen;
+	char *token;
+
+	(void)fname;
+
+	if (nfields < 1) {
+		return 1;
+	}
+
+	/* append new testcase and initialize with zeroes */
+	if ((*test = realloc(*test, ++(*testlen) * sizeof(**test))) == NULL) {
+		fprintf(stderr, "break_test_callback: realloc: %s.\n",
+		        strerror(errno));
+		return 1;
+	}
+	t = &(*test)[*testlen - 1];
+	memset(t, 0, sizeof(*t));
+
+	/* parse testcase "<÷|×> <cp> <÷|×> ... <cp> <÷|×>" */
+	for (token = strtok(field[0], " "), i = 0; token != NULL; i++,
+	     token = strtok(NULL, " ")) {
+		if (i % 2 == 0) {
+			/* delimiter or start of sequence */
+			if (i == 0 || !strncmp(token, "\xC3\xB7", 2)) { /* UTF-8 */
+				/*
+				 * '÷' indicates a breakpoint,
+				 * the current length is done; allocate
+				 * a new length field and set it to 0
+				 */
+				if ((t->len = realloc(t->len,
+				     ++t->lenlen * sizeof(*t->len))) == NULL) {
+					fprintf(stderr, "break_test_"
+					        "callback: realloc: %s.\n",
+					        strerror(errno));
+					return 1;
+				}
+				t->len[t->lenlen - 1] = 0;
+			} else if (!strncmp(token, "\xC3\x97", 2)) { /* UTF-8 */
+				/*
+				 * '×' indicates a non-breakpoint, do nothing
+				 */
+			} else {
+				fprintf(stderr, "break_test_callback: "
+				        "Malformed delimiter '%s'.\n", token);
+				return 1;
+			}
+		} else {
+			/* add codepoint to cp-array */
+			if ((t->cp = realloc(t->cp, ++t->cplen *
+			                     sizeof(*t->cp))) == NULL) {
+				fprintf(stderr, "break_test_callback: "
+				        "realloc: %s.\n", strerror(errno));
+				return 1;
+			}
+			if (hextocp(token, strlen(token), &t->cp[t->cplen - 1])) {
+				return 1;
+			}
+			if (t->lenlen > 0) {
+				t->len[t->lenlen - 1]++;
+			}
+		}
+	}
+	if (t->len[t->lenlen - 1] == 0) {
+		/*
+		 * we allocated one more length than we needed because
+		 * the breakpoint was at the end
+		 */
+		t->lenlen--;
+	}
+
+	/* store comment */
+	if (((*test)[*testlen - 1].descr = strdup(comment)) == NULL) {
+		fprintf(stderr, "break_test_callback: strdup: %s.\n",
+		        strerror(errno));
+		return 1;
+	}
+
+	return 0;
+}
+
+void
+break_test_list_parse(char *fname, struct break_test **test,
+                        size_t *testlen)
+{
+	struct break_test_payload pl = {
+		.test = test,
+		.testlen = testlen,
+	};
+	*test = NULL;
+	*testlen = 0;
+
+	parse_file_with_callback(fname, break_test_callback, &pl);
+}
+
+void
+break_test_list_print(const struct break_test *test, size_t testlen,
+                        const char *identifier, const char *progname)
+{
+	size_t i, j;
+
+	printf("/* Automatically generated by %s */\n"
+	       "#include <stdint.h>\n#include <stddef.h>\n\n"
+	       "#include \"../gen/types.h\"\n\n", progname);
+
+	printf("static const struct break_test %s[] = {\n", identifier);
+	for (i = 0; i < testlen; i++) {
+		printf("\t{\n");
+
+		printf("\t\t.cp     = (uint_least32_t[]){");
+		for (j = 0; j < test[i].cplen; j++) {
+			printf(" UINT32_C(0x%06X)", test[i].cp[j]);
+			if (j + 1 < test[i].cplen) {
+				putchar(',');
+			}
+		}
+		printf(" },\n");
+		printf("\t\t.cplen  = %zu,\n", test[i].cplen);
+
+		printf("\t\t.len    = (size_t[]){");
+		for (j = 0; j < test[i].lenlen; j++) {
+			printf(" %zu", test[i].len[j]);
+			if (j + 1 < test[i].lenlen) {
+				putchar(',');
+			}
+		}
+		printf(" },\n");
+		printf("\t\t.lenlen = %zu,\n", test[i].lenlen);
+
+		printf("\t\t.descr  = \"%s\",\n", test[i].descr);
+
+		printf("\t},\n");
+	}
+	printf("};\n");
+}
+
+void
+break_test_list_free(struct break_test *test, size_t testlen)
+{
+	size_t i;
+
+	for (i = 0; i < testlen; i++) {
+		free(test[i].cp);
+		free(test[i].len);
+		free(test[i].descr);
+	}
+
+	free(test);
+}

libs/libgrapheme-2.0.2/gen/util.h

@@ -0,0 +1,60 @@
+/* See LICENSE file for copyright and license details. */
+#ifndef UTIL_H
+#define UTIL_H
+
+#include <stddef.h>
+#include <stdint.h>
+
+#include "types.h"
+
+#define LEN(x) (sizeof (x) / sizeof *(x))
+
+struct property_spec {
+	const char *enumname;
+	const char *file;
+	const char *ucdname;
+};
+
+struct properties {
+	int_least64_t property;
+};
+
+struct properties_compressed {
+	size_t *offset;
+	struct properties *data;
+	size_t datalen;
+};
+
+struct properties_major_minor {
+	size_t *major;
+	size_t *minor;
+	size_t minorlen;
+};
+
+int hextocp(const char *, size_t, uint_least32_t *cp);
+
+void parse_file_with_callback(const char *, int (*callback)(const char *,
+                              char **, size_t, char *, void *), void *payload);
+
+void properties_compress(const struct properties *, struct properties_compressed *comp);
+double properties_get_major_minor(const struct properties_compressed *,
+                                  struct properties_major_minor *);
+void properties_print_lookup_table(char *, size_t *, size_t);
+void properties_print_derived_lookup_table(char *, char *, size_t *, size_t,
+                                      int_least64_t (*get_value)(const struct properties *,
+                                      size_t), const void *);
+
+void properties_generate_break_property(const struct property_spec *,
+                                        uint_least8_t, uint_least8_t
+                                        (*handle_conflict)(uint_least32_t,
+                                        uint_least8_t, uint_least8_t),
+					uint_least8_t (*post_process)
+                                        (uint_least8_t), const char *,
+                                        const char *);
+
+void break_test_list_parse(char *, struct break_test **, size_t *);
+void break_test_list_print(const struct break_test *, size_t,
+                             const char *, const char *);
+void break_test_list_free(struct break_test *, size_t);
+
+#endif /* UTIL_H */

libs/libgrapheme-2.0.2/gen/word-test.c

@@ -0,0 +1,19 @@
+/* See LICENSE file for copyright and license details. */
+#include <stddef.h>
+
+#include "util.h"
+
+int
+main(int argc, char *argv[])
+{
+	struct break_test *test = NULL;
+	size_t testlen = 0;
+
+	(void)argc;
+
+	break_test_list_parse("data/WordBreakTest.txt", &test, &testlen);
+	break_test_list_print(test, testlen, "word_break_test", argv[0]);
+	break_test_list_free(test, testlen);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/gen/word.c

@@ -0,0 +1,159 @@
+/* See LICENSE file for copyright and license details. */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "util.h"
+
+#define FILE_EMOJI "data/emoji-data.txt"
+#define FILE_WORD  "data/WordBreakProperty.txt"
+
+static const struct property_spec word_break_property[] = {
+	{
+		.enumname = "OTHER",
+		.file     = NULL,
+		.ucdname  = NULL,
+	},
+	{
+		.enumname = "ALETTER",
+		.file     = FILE_WORD,
+		.ucdname  = "ALetter",
+	},
+	{
+		.enumname = "BOTH_ALETTER_EXTPICT",
+		.file     = NULL,
+		.ucdname  = NULL,
+	},
+	{
+		.enumname = "CR",
+		.file     = FILE_WORD,
+		.ucdname  = "CR",
+	},
+	{
+		.enumname = "DOUBLE_QUOTE",
+		.file     = FILE_WORD,
+		.ucdname  = "Double_Quote",
+	},
+	{
+		.enumname = "EXTEND",
+		.file     = FILE_WORD,
+		.ucdname  = "Extend",
+	},
+	{
+		.enumname = "EXTENDED_PICTOGRAPHIC",
+		.file     = FILE_EMOJI,
+		.ucdname  = "Extended_Pictographic",
+	},
+	{
+		.enumname = "EXTENDNUMLET",
+		.file     = FILE_WORD,
+		.ucdname  = "ExtendNumLet",
+	},
+	{
+		.enumname = "FORMAT",
+		.file     = FILE_WORD,
+		.ucdname  = "Format",
+	},
+	{
+		.enumname = "HEBREW_LETTER",
+		.file     = FILE_WORD,
+		.ucdname  = "Hebrew_Letter",
+	},
+	{
+		.enumname = "KATAKANA",
+		.file     = FILE_WORD,
+		.ucdname  = "Katakana",
+	},
+	{
+		.enumname = "LF",
+		.file     = FILE_WORD,
+		.ucdname  = "LF",
+	},
+	{
+		.enumname = "MIDLETTER",
+		.file     = FILE_WORD,
+		.ucdname  = "MidLetter",
+	},
+	{
+		.enumname = "MIDNUM",
+		.file     = FILE_WORD,
+		.ucdname  = "MidNum",
+	},
+	{
+		.enumname = "MIDNUMLET",
+		.file     = FILE_WORD,
+		.ucdname  = "MidNumLet",
+	},
+	{
+		.enumname = "NEWLINE",
+		.file     = FILE_WORD,
+		.ucdname  = "Newline",
+	},
+	{
+		.enumname = "NUMERIC",
+		.file     = FILE_WORD,
+		.ucdname  = "Numeric",
+	},
+	{
+		.enumname = "REGIONAL_INDICATOR",
+		.file     = FILE_WORD,
+		.ucdname  = "Regional_Indicator",
+	},
+	{
+		.enumname = "SINGLE_QUOTE",
+		.file     = FILE_WORD,
+		.ucdname  = "Single_Quote",
+	},
+	{
+		.enumname = "WSEGSPACE",
+		.file     = FILE_WORD,
+		.ucdname  = "WSegSpace",
+	},
+	{
+		.enumname = "ZWJ",
+		.file     = FILE_WORD,
+		.ucdname  = "ZWJ",
+	},
+};
+
+static uint_least8_t
+handle_conflict(uint_least32_t cp, uint_least8_t prop1, uint_least8_t prop2)
+{
+	uint_least8_t result;
+
+	(void)cp;
+
+	if ((!strcmp(word_break_property[prop1].enumname, "ALETTER") &&
+	     !strcmp(word_break_property[prop2].enumname, "EXTENDED_PICTOGRAPHIC")) ||
+	    (!strcmp(word_break_property[prop1].enumname, "EXTENDED_PICTOGRAPHIC") &&
+	     !strcmp(word_break_property[prop2].enumname, "ALETTER"))) {
+		for (result = 0; result < LEN(word_break_property); result++) {
+			if (!strcmp(word_break_property[result].enumname,
+			            "BOTH_ALETTER_EXTPICT")) {
+				break;
+			}
+		}
+		if (result == LEN(word_break_property)) {
+			fprintf(stderr, "handle_conflict: Internal error.\n");
+			exit(1);
+		}
+	} else {
+		fprintf(stderr, "handle_conflict: Cannot handle conflict.\n");
+		exit(1);
+	}
+
+	return result;
+}
+
+int
+main(int argc, char *argv[])
+{
+	(void)argc;
+
+	properties_generate_break_property(word_break_property,
+	                                   LEN(word_break_property),
+	                                   handle_conflict, NULL, "word_break",
+	                                   argv[0]);
+
+	return 0;
+}

libs/libgrapheme-2.0.2/grapheme.h

@@ -0,0 +1,42 @@
+/* See LICENSE file for copyright and license details. */
+#ifndef GRAPHEME_H
+#define GRAPHEME_H
+
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+
+#define GRAPHEME_INVALID_CODEPOINT UINT32_C(0xFFFD)
+
+size_t grapheme_decode_utf8(const char *, size_t, uint_least32_t *);
+size_t grapheme_encode_utf8(uint_least32_t, char *, size_t);
+
+bool grapheme_is_character_break(uint_least32_t, uint_least32_t, uint_least16_t *);
+
+bool grapheme_is_lowercase(const uint_least32_t *, size_t, size_t *);
+bool grapheme_is_titlecase(const uint_least32_t *, size_t, size_t *);
+bool grapheme_is_uppercase(const uint_least32_t *, size_t, size_t *);
+
+bool grapheme_is_lowercase_utf8(const char *, size_t, size_t *);
+bool grapheme_is_titlecase_utf8(const char *, size_t, size_t *);
+bool grapheme_is_uppercase_utf8(const char *, size_t, size_t *);
+
+size_t grapheme_next_character_break(const uint_least32_t *, size_t);
+size_t grapheme_next_line_break(const uint_least32_t *, size_t);
+size_t grapheme_next_sentence_break(const uint_least32_t *, size_t);
+size_t grapheme_next_word_break(const uint_least32_t *, size_t);
+
+size_t grapheme_next_character_break_utf8(const char *, size_t);
+size_t grapheme_next_line_break_utf8(const char *, size_t);
+size_t grapheme_next_sentence_break_utf8(const char *, size_t);
+size_t grapheme_next_word_break_utf8(const char *, size_t);
+
+size_t grapheme_to_lowercase(const uint_least32_t *, size_t, uint_least32_t *, size_t);
+size_t grapheme_to_titlecase(const uint_least32_t *, size_t, uint_least32_t *, size_t);
+size_t grapheme_to_uppercase(const uint_least32_t *, size_t, uint_least32_t *, size_t);
+
+size_t grapheme_to_lowercase_utf8(const char *, size_t, char *, size_t);
+size_t grapheme_to_titlecase_utf8(const char *, size_t, char *, size_t);
+size_t grapheme_to_uppercase_utf8(const char *, size_t, char *, size_t);
+
+#endif /* GRAPHEME_H */

libs/libgrapheme-2.0.2/man/grapheme_decode_utf8.3

@@ -0,0 +1,100 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_DECODE_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_decode_utf8
+.Nd decode first codepoint in UTF-8-encoded string
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_decode_utf8 "const char *str" "size_t len" "uint_least32_t *cp"
+.Sh DESCRIPTION
+The
+.Fn grapheme_decode_utf8
+function decodes the first codepoint in the UTF-8-encoded string
+.Va str
+of length
+.Va len .
+If the UTF-8-sequence is invalid (overlong encoding, unexpected byte,
+string ends unexpectedly, empty string, etc.) the decoding is stopped
+at the last processed byte and the decoded codepoint set to
+.Dv GRAPHEME_INVALID_CODEPOINT .
+.Pp
+If
+.Va cp
+is not
+.Dv NULL
+the decoded codepoint is stored in the memory pointed to by
+.Va cp .
+.Pp
+Given NUL has a unique 1 byte representation, it is safe to operate on
+NUL-terminated strings by setting
+.Va len
+to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) and terminating when
+.Va cp
+is 0 (see
+.Sx EXAMPLES
+for an example).
+.Sh RETURN VALUES
+The
+.Fn grapheme_decode_utf8
+function returns the number of processed bytes and 0 if
+.Va str
+is
+.Dv NULL
+or
+.Va len
+is 0.
+If the string ends unexpectedly in a multibyte sequence, the desired
+length (that is larger than
+.Va len )
+is returned.
+.Sh EXAMPLES
+.Bd -literal
+/* cc (-static) -o example example.c -lgrapheme */
+#include <grapheme.h>
+#include <inttypes.h>
+#include <stdio.h>
+
+void
+print_cps(const char *str, size_t len)
+{
+	size_t ret, off;
+	uint_least32_t cp;
+
+	for (off = 0; off < len; off += ret) {
+		if ((ret = grapheme_decode_utf8(str + off,
+		                                len - off, &cp)) > (len - off)) {
+			/*
+			 * string ended unexpectedly in the middle of a
+			 * multibyte sequence and we have the choice
+			 * here to possibly expand str by ret - len + off
+			 * bytes to get a full sequence, but we just
+			 * bail out in this case.
+			 */
+			break;
+		}
+		printf("%"PRIxLEAST32"\\n", cp);
+	}
+}
+
+void
+print_cps_nul_terminated(const char *str)
+{
+	size_t ret, off;
+	uint_least32_t cp;
+
+	for (off = 0; (ret = grapheme_decode_utf8(str + off,
+	                                          SIZE_MAX, &cp)) > 0 &&
+	     cp != 0; off += ret) {
+		printf("%"PRIxLEAST32"\\n", cp);
+	}
+}
+.Ed
+.Sh SEE ALSO
+.Xr grapheme_encode_utf8 3 ,
+.Xr libgrapheme 7
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_decode_utf8.sh

@@ -0,0 +1,102 @@
+cat << EOF
+.Dd ${MAN_DATE}
+.Dt GRAPHEME_DECODE_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_decode_utf8
+.Nd decode first codepoint in UTF-8-encoded string
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_decode_utf8 "const char *str" "size_t len" "uint_least32_t *cp"
+.Sh DESCRIPTION
+The
+.Fn grapheme_decode_utf8
+function decodes the first codepoint in the UTF-8-encoded string
+.Va str
+of length
+.Va len .
+If the UTF-8-sequence is invalid (overlong encoding, unexpected byte,
+string ends unexpectedly, empty string, etc.) the decoding is stopped
+at the last processed byte and the decoded codepoint set to
+.Dv GRAPHEME_INVALID_CODEPOINT .
+.Pp
+If
+.Va cp
+is not
+.Dv NULL
+the decoded codepoint is stored in the memory pointed to by
+.Va cp .
+.Pp
+Given NUL has a unique 1 byte representation, it is safe to operate on
+NUL-terminated strings by setting
+.Va len
+to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) and terminating when
+.Va cp
+is 0 (see
+.Sx EXAMPLES
+for an example).
+.Sh RETURN VALUES
+The
+.Fn grapheme_decode_utf8
+function returns the number of processed bytes and 0 if
+.Va str
+is
+.Dv NULL
+or
+.Va len
+is 0.
+If the string ends unexpectedly in a multibyte sequence, the desired
+length (that is larger than
+.Va len )
+is returned.
+.Sh EXAMPLES
+.Bd -literal
+/* cc (-static) -o example example.c -lgrapheme */
+#include <grapheme.h>
+#include <inttypes.h>
+#include <stdio.h>
+
+void
+print_cps(const char *str, size_t len)
+{
+	size_t ret, off;
+	uint_least32_t cp;
+
+	for (off = 0; off < len; off += ret) {
+		if ((ret = grapheme_decode_utf8(str + off,
+		                                len - off, &cp)) > (len - off)) {
+			/*
+			 * string ended unexpectedly in the middle of a
+			 * multibyte sequence and we have the choice
+			 * here to possibly expand str by ret - len + off
+			 * bytes to get a full sequence, but we just
+			 * bail out in this case.
+			 */
+			break;
+		}
+		printf("%"PRIxLEAST32"\\\\n", cp);
+	}
+}
+
+void
+print_cps_nul_terminated(const char *str)
+{
+	size_t ret, off;
+	uint_least32_t cp;
+
+	for (off = 0; (ret = grapheme_decode_utf8(str + off,
+	                                          SIZE_MAX, &cp)) > 0 &&
+	     cp != 0; off += ret) {
+		printf("%"PRIxLEAST32"\\\\n", cp);
+	}
+}
+.Ed
+.Sh SEE ALSO
+.Xr grapheme_encode_utf8 3 ,
+.Xr libgrapheme 7
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de
+EOF

libs/libgrapheme-2.0.2/man/grapheme_encode_utf8.3

@@ -0,0 +1,101 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_ENCODE_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_encode_utf8
+.Nd encode codepoint into UTF-8 string
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_encode_utf8 "uint_least32_t cp" "char *str" "size_t len"
+.Sh DESCRIPTION
+The
+.Fn grapheme_encode_utf8
+function encodes the codepoint
+.Va cp
+into a UTF-8-string.
+If
+.Va str
+is not
+.Dv NULL
+and
+.Va len
+is large enough it writes the UTF-8-string to the memory pointed to by
+.Va str .
+Otherwise no data is written.
+.Sh RETURN VALUES
+The
+.Fn grapheme_encode_utf8
+function returns the length (in bytes) of the UTF-8-string resulting
+from encoding
+.Va cp ,
+even if
+.Va len
+is not large enough or
+.Va str
+is
+.Dv NULL .
+.Sh EXAMPLES
+.Bd -literal
+/* cc (-static) -o example example.c -lgrapheme */
+#include <grapheme.h>
+#include <stddef.h>
+#include <stdlib.h>
+
+size_t
+cps_to_utf8(const uint_least32_t *cp, size_t cplen, char *str, size_t len)
+{
+	size_t i, off, ret;
+
+	for (i = 0, off = 0; i < cplen; i++, off += ret) {
+		if ((ret = grapheme_encode_utf8(cp[i], str + off,
+		                                len - off)) > (len - off)) {
+			/* buffer too small */
+			break;
+		}
+	}
+
+	return off;
+}
+
+size_t
+cps_bytelen(const uint_least32_t *cp, size_t cplen)
+{
+	size_t i, len;
+
+	for (i = 0, len = 0; i < cplen; i++) {
+		len += grapheme_encode_utf8(cp[i], NULL, 0);
+	}
+
+	return len;
+}
+
+char *
+cps_to_utf8_alloc(const uint_least32_t *cp, size_t cplen)
+{
+	char *str;
+	size_t len, i, ret, off;
+
+	len = cps_bytelen(cp, cplen);
+
+	if (!(str = malloc(len))) {
+		return NULL;
+	}
+
+	for (i = 0, off = 0; i < cplen; i++, off += ret) {
+		if ((ret = grapheme_encode_utf8(cp[i], str + off,
+		                                len - off)) > (len - off)) {
+			/* buffer too small */
+			break;
+		}
+	}
+	str[off] = '\\0';
+
+	return str;
+}
+.Ed
+.Sh SEE ALSO
+.Xr grapheme_decode_utf8 3 ,
+.Xr libgrapheme 7
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_encode_utf8.sh

@@ -0,0 +1,103 @@
+cat << EOF
+.Dd ${MAN_DATE}
+.Dt GRAPHEME_ENCODE_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_encode_utf8
+.Nd encode codepoint into UTF-8 string
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_encode_utf8 "uint_least32_t cp" "char *str" "size_t len"
+.Sh DESCRIPTION
+The
+.Fn grapheme_encode_utf8
+function encodes the codepoint
+.Va cp
+into a UTF-8-string.
+If
+.Va str
+is not
+.Dv NULL
+and
+.Va len
+is large enough it writes the UTF-8-string to the memory pointed to by
+.Va str .
+Otherwise no data is written.
+.Sh RETURN VALUES
+The
+.Fn grapheme_encode_utf8
+function returns the length (in bytes) of the UTF-8-string resulting
+from encoding
+.Va cp ,
+even if
+.Va len
+is not large enough or
+.Va str
+is
+.Dv NULL .
+.Sh EXAMPLES
+.Bd -literal
+/* cc (-static) -o example example.c -lgrapheme */
+#include <grapheme.h>
+#include <stddef.h>
+#include <stdlib.h>
+
+size_t
+cps_to_utf8(const uint_least32_t *cp, size_t cplen, char *str, size_t len)
+{
+	size_t i, off, ret;
+
+	for (i = 0, off = 0; i < cplen; i++, off += ret) {
+		if ((ret = grapheme_encode_utf8(cp[i], str + off,
+		                                len - off)) > (len - off)) {
+			/* buffer too small */
+			break;
+		}
+	}
+
+	return off;
+}
+
+size_t
+cps_bytelen(const uint_least32_t *cp, size_t cplen)
+{
+	size_t i, len;
+
+	for (i = 0, len = 0; i < cplen; i++) {
+		len += grapheme_encode_utf8(cp[i], NULL, 0);
+	}
+
+	return len;
+}
+
+char *
+cps_to_utf8_alloc(const uint_least32_t *cp, size_t cplen)
+{
+	char *str;
+	size_t len, i, ret, off;
+
+	len = cps_bytelen(cp, cplen);
+
+	if (!(str = malloc(len))) {
+		return NULL;
+	}
+
+	for (i = 0, off = 0; i < cplen; i++, off += ret) {
+		if ((ret = grapheme_encode_utf8(cp[i], str + off,
+		                                len - off)) > (len - off)) {
+			/* buffer too small */
+			break;
+		}
+	}
+	str[off] = '\\\\0';
+
+	return str;
+}
+.Ed
+.Sh SEE ALSO
+.Xr grapheme_decode_utf8 3 ,
+.Xr libgrapheme 7
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de
+EOF

libs/libgrapheme-2.0.2/man/grapheme_is_character_break.3

@@ -0,0 +1,81 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_IS_CHARACTER_BREAK 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_is_character_break
+.Nd test for a grapheme cluster break between two codepoints
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_is_character_break "uint_least32_t cp1" "uint_least32_t cp2" "uint_least16_t *state"
+.Sh DESCRIPTION
+The
+.Fn grapheme_is_character_break
+function determines if there is a grapheme cluster break (see
+.Xr libgrapheme 7 )
+between the two codepoints
+.Va cp1
+and
+.Va cp2 .
+By specification this decision depends on a
+.Va state
+that can at most be completely reset after detecting a break and must
+be reset every time one deviates from sequential processing.
+.Pp
+If
+.Va state
+is
+.Dv NULL
+.Fn grapheme_is_character_break
+behaves as if it was called with a fully reset state.
+.Sh RETURN VALUES
+The
+.Fn grapheme_is_character_break
+function returns
+.Va true
+if there is a grapheme cluster break between the codepoints
+.Va cp1
+and
+.Va cp2
+and
+.Va false
+if there is not.
+.Sh EXAMPLES
+.Bd -literal
+/* cc (-static) -o example example.c -lgrapheme */
+#include <grapheme.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+int
+main(void)
+{
+	uint_least16_t state = 0;
+	uint_least32_t s1[] = ..., s2[] = ...; /* two input arrays */
+	size_t i;
+
+	for (i = 0; i + 1 < sizeof(s1) / sizeof(*s1); i++) {
+		if (grapheme_is_character_break(s[i], s[i + 1], &state)) {
+			printf("break in s1 at offset %zu\n", i);
+		}
+	}
+	memset(&state, 0, sizeof(state)); /* reset state */
+	for (i = 0; i + 1 < sizeof(s2) / sizeof(*s2); i++) {
+		if (grapheme_is_character_break(s[i], s[i + 1], &state)) {
+			printf("break in s2 at offset %zu\n", i);
+		}
+	}
+
+	return 0;
+}
+.Ed
+.Sh SEE ALSO
+.Xr grapheme_next_character_break 3 ,
+.Xr grapheme_next_character_break_utf8 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_is_character_break
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_is_character_break.sh

@@ -0,0 +1,83 @@
+cat << EOF
+.Dd ${MAN_DATE}
+.Dt GRAPHEME_IS_CHARACTER_BREAK 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_is_character_break
+.Nd test for a grapheme cluster break between two codepoints
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_is_character_break "uint_least32_t cp1" "uint_least32_t cp2" "uint_least16_t *state"
+.Sh DESCRIPTION
+The
+.Fn grapheme_is_character_break
+function determines if there is a grapheme cluster break (see
+.Xr libgrapheme 7 )
+between the two codepoints
+.Va cp1
+and
+.Va cp2 .
+By specification this decision depends on a
+.Va state
+that can at most be completely reset after detecting a break and must
+be reset every time one deviates from sequential processing.
+.Pp
+If
+.Va state
+is
+.Dv NULL
+.Fn grapheme_is_character_break
+behaves as if it was called with a fully reset state.
+.Sh RETURN VALUES
+The
+.Fn grapheme_is_character_break
+function returns
+.Va true
+if there is a grapheme cluster break between the codepoints
+.Va cp1
+and
+.Va cp2
+and
+.Va false
+if there is not.
+.Sh EXAMPLES
+.Bd -literal
+/* cc (-static) -o example example.c -lgrapheme */
+#include <grapheme.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+int
+main(void)
+{
+	uint_least16_t state = 0;
+	uint_least32_t s1[] = ..., s2[] = ...; /* two input arrays */
+	size_t i;
+
+	for (i = 0; i + 1 < sizeof(s1) / sizeof(*s1); i++) {
+		if (grapheme_is_character_break(s[i], s[i + 1], &state)) {
+			printf("break in s1 at offset %zu\n", i);
+		}
+	}
+	memset(&state, 0, sizeof(state)); /* reset state */
+	for (i = 0; i + 1 < sizeof(s2) / sizeof(*s2); i++) {
+		if (grapheme_is_character_break(s[i], s[i + 1], &state)) {
+			printf("break in s2 at offset %zu\n", i);
+		}
+	}
+
+	return 0;
+}
+.Ed
+.Sh SEE ALSO
+.Xr grapheme_next_character_break 3 ,
+.Xr grapheme_next_character_break_utf8 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_is_character_break
+is compliant with the Unicode ${UNICODE_VERSION} specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de
+EOF

libs/libgrapheme-2.0.2/man/grapheme_is_lowercase.3

@@ -0,0 +1,51 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_IS_LOWERCASE 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_is_lowercase
+.Nd check if codepoint array is lowercase
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_is_lowercase "const uint_least32_t *str" "size_t len" "size_t *caselen"
+.Sh DESCRIPTION
+The
+.Fn grapheme_is_lowercase
+function checks if the codepoint array
+.Va str
+is lowercase and writes the length of the matching lowercase-sequence to the integer pointed to by
+.Va caselen ,
+unless
+.Va caselen
+is set to
+.Dv NULL .
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the codepoint array
+.Va src
+is interpreted to be NUL-terminated and processing stops when a
+NUL-byte is encountered.
+.Pp
+For UTF-8-encoded input data
+.Xr grapheme_is_lowercase_utf8 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_is_lowercase
+function returns
+.Dv true
+if the codepoint array
+.Va str
+is lowercase, otherwise
+.Dv false .
+.Sh SEE ALSO
+.Xr grapheme_is_lowercase_utf8 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_is_lowercase
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_is_lowercase.sh

@@ -0,0 +1,3 @@
+ENCODING="codepoint" \
+CASE="lowercase" \
+	$SH man/template/is_case.sh

libs/libgrapheme-2.0.2/man/grapheme_is_lowercase_utf8.3

@@ -0,0 +1,51 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_IS_LOWERCASE_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_is_lowercase_utf8
+.Nd check if UTF-8-encoded string is lowercase
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_is_lowercase_utf8 "const char *str" "size_t len" "size_t *caselen"
+.Sh DESCRIPTION
+The
+.Fn grapheme_is_lowercase_utf8
+function checks if the UTF-8-encoded string
+.Va str
+is lowercase and writes the length of the matching lowercase-sequence to the integer pointed to by
+.Va caselen ,
+unless
+.Va caselen
+is set to
+.Dv NULL .
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the UTF-8-encoded string
+.Va src
+is interpreted to be NUL-terminated and processing stops when a
+NUL-byte is encountered.
+.Pp
+For non-UTF-8 input data
+.Xr grapheme_is_lowercase 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_is_lowercase_utf8
+function returns
+.Dv true
+if the UTF-8-encoded string
+.Va str
+is lowercase, otherwise
+.Dv false .
+.Sh SEE ALSO
+.Xr grapheme_is_lowercase 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_is_lowercase_utf8
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_is_lowercase_utf8.sh

@@ -0,0 +1,3 @@
+ENCODING="utf8" \
+CASE="lowercase" \
+	$SH man/template/is_case.sh

libs/libgrapheme-2.0.2/man/grapheme_is_titlecase.3

@@ -0,0 +1,51 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_IS_TITLECASE 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_is_titlecase
+.Nd check if codepoint array is titlecase
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_is_titlecase "const uint_least32_t *str" "size_t len" "size_t *caselen"
+.Sh DESCRIPTION
+The
+.Fn grapheme_is_titlecase
+function checks if the codepoint array
+.Va str
+is titlecase and writes the length of the matching titlecase-sequence to the integer pointed to by
+.Va caselen ,
+unless
+.Va caselen
+is set to
+.Dv NULL .
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the codepoint array
+.Va src
+is interpreted to be NUL-terminated and processing stops when a
+NUL-byte is encountered.
+.Pp
+For UTF-8-encoded input data
+.Xr grapheme_is_titlecase_utf8 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_is_titlecase
+function returns
+.Dv true
+if the codepoint array
+.Va str
+is titlecase, otherwise
+.Dv false .
+.Sh SEE ALSO
+.Xr grapheme_is_titlecase_utf8 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_is_titlecase
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_is_titlecase.sh

@@ -0,0 +1,3 @@
+ENCODING="codepoint" \
+CASE="titlecase" \
+	$SH man/template/is_case.sh

libs/libgrapheme-2.0.2/man/grapheme_is_titlecase_utf8.3

@@ -0,0 +1,51 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_IS_TITLECASE_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_is_titlecase_utf8
+.Nd check if UTF-8-encoded string is titlecase
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_is_titlecase_utf8 "const char *str" "size_t len" "size_t *caselen"
+.Sh DESCRIPTION
+The
+.Fn grapheme_is_titlecase_utf8
+function checks if the UTF-8-encoded string
+.Va str
+is titlecase and writes the length of the matching titlecase-sequence to the integer pointed to by
+.Va caselen ,
+unless
+.Va caselen
+is set to
+.Dv NULL .
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the UTF-8-encoded string
+.Va src
+is interpreted to be NUL-terminated and processing stops when a
+NUL-byte is encountered.
+.Pp
+For non-UTF-8 input data
+.Xr grapheme_is_titlecase 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_is_titlecase_utf8
+function returns
+.Dv true
+if the UTF-8-encoded string
+.Va str
+is titlecase, otherwise
+.Dv false .
+.Sh SEE ALSO
+.Xr grapheme_is_titlecase 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_is_titlecase_utf8
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_is_titlecase_utf8.sh

@@ -0,0 +1,3 @@
+ENCODING="utf8" \
+CASE="titlecase" \
+	$SH man/template/is_case.sh

libs/libgrapheme-2.0.2/man/grapheme_is_uppercase.3

@@ -0,0 +1,51 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_IS_UPPERCASE 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_is_uppercase
+.Nd check if codepoint array is uppercase
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_is_uppercase "const uint_least32_t *str" "size_t len" "size_t *caselen"
+.Sh DESCRIPTION
+The
+.Fn grapheme_is_uppercase
+function checks if the codepoint array
+.Va str
+is uppercase and writes the length of the matching uppercase-sequence to the integer pointed to by
+.Va caselen ,
+unless
+.Va caselen
+is set to
+.Dv NULL .
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the codepoint array
+.Va src
+is interpreted to be NUL-terminated and processing stops when a
+NUL-byte is encountered.
+.Pp
+For UTF-8-encoded input data
+.Xr grapheme_is_uppercase_utf8 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_is_uppercase
+function returns
+.Dv true
+if the codepoint array
+.Va str
+is uppercase, otherwise
+.Dv false .
+.Sh SEE ALSO
+.Xr grapheme_is_uppercase_utf8 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_is_uppercase
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_is_uppercase.sh

@@ -0,0 +1,3 @@
+ENCODING="codepoint" \
+CASE="uppercase" \
+	$SH man/template/is_case.sh

libs/libgrapheme-2.0.2/man/grapheme_is_uppercase_utf8.3

@@ -0,0 +1,51 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_IS_LOWERCASE_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_is_lowercase_utf8
+.Nd check if UTF-8-encoded string is lowercase
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_is_lowercase_utf8 "const char *str" "size_t len" "size_t *caselen"
+.Sh DESCRIPTION
+The
+.Fn grapheme_is_lowercase_utf8
+function checks if the UTF-8-encoded string
+.Va str
+is lowercase and writes the length of the matching lowercase-sequence to the integer pointed to by
+.Va caselen ,
+unless
+.Va caselen
+is set to
+.Dv NULL .
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the UTF-8-encoded string
+.Va src
+is interpreted to be NUL-terminated and processing stops when a
+NUL-byte is encountered.
+.Pp
+For non-UTF-8 input data
+.Xr grapheme_is_lowercase 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_is_lowercase_utf8
+function returns
+.Dv true
+if the UTF-8-encoded string
+.Va str
+is lowercase, otherwise
+.Dv false .
+.Sh SEE ALSO
+.Xr grapheme_is_lowercase 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_is_lowercase_utf8
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_is_uppercase_utf8.sh

@@ -0,0 +1,3 @@
+ENCODING="utf8" \
+CASE="lowercase" \
+	$SH man/template/is_case.sh

libs/libgrapheme-2.0.2/man/grapheme_next_character_break.3

@@ -0,0 +1,56 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_NEXT_CHARACTER_BREAK 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_next_character_break
+.Nd determine codepoint-offset to next grapheme cluster break
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_next_character_break "const uint_least32_t *str" "size_t len"
+.Sh DESCRIPTION
+The
+.Fn grapheme_next_character_break
+function computes the offset (in codepoints) to the next grapheme cluster
+break (see
+.Xr libgrapheme 7 )
+in the codepoint array
+.Va str
+of length
+.Va len .
+If a grapheme cluster begins at
+.Va str
+this offset is equal to the length of said grapheme cluster.
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the string
+.Va str
+is interpreted to be NUL-terminated and processing stops when
+a codepoint with the value 0 is encountered.
+.Pp
+For UTF-8-encoded input
+data
+.Xr grapheme_next_character_break_utf8 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_next_character_break
+function returns the offset (in codepoints) to the next grapheme cluster
+break in
+.Va str
+or 0 if
+.Va str
+is
+.Dv NULL .
+.Sh SEE ALSO
+.Xr grapheme_is_character_break 3 ,
+.Xr grapheme_next_character_break_utf8 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_next_character_break
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_next_character_break.sh

@@ -0,0 +1,4 @@
+ENCODING="codepoint" \
+TYPE="character" \
+REALTYPE="grapheme cluster" \
+	$SH man/template/next_break.sh

libs/libgrapheme-2.0.2/man/grapheme_next_character_break_utf8.3

@@ -0,0 +1,94 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_NEXT_CHARACTER_BREAK_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_next_character_break_utf8
+.Nd determine byte-offset to next grapheme cluster break
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_next_character_break_utf8 "const char *str" "size_t len"
+.Sh DESCRIPTION
+The
+.Fn grapheme_next_character_break_utf8
+function computes the offset (in bytes) to the next grapheme cluster
+break (see
+.Xr libgrapheme 7 )
+in the UTF-8-encoded string
+.Va str
+of length
+.Va len .
+If a grapheme cluster begins at
+.Va str
+this offset is equal to the length of said grapheme cluster.
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the string
+.Va str
+is interpreted to be NUL-terminated and processing stops when
+a NUL-byte is encountered.
+.Pp
+For non-UTF-8 input
+data
+.Xr grapheme_is_character_break 3 and
+.Xr grapheme_next_character_break 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_next_character_break_utf8
+function returns the offset (in bytes) to the next grapheme cluster
+break in
+.Va str
+or 0 if
+.Va str
+is
+.Dv NULL .
+.Sh EXAMPLES
+.Bd -literal
+/* cc (-static) -o example example.c -lgrapheme */
+#include <grapheme.h>
+#include <stdint.h>
+#include <stdio.h>
+
+int
+main(void)
+{
+	/* UTF-8 encoded input */
+	char *s = "T\\xC3\\xABst \\xF0\\x9F\\x91\\xA8\\xE2\\x80\\x8D\\xF0"
+	          "\\x9F\\x91\\xA9\\xE2\\x80\\x8D\\xF0\\x9F\\x91\\xA6 \\xF0"
+	          "\\x9F\\x87\\xBA\\xF0\\x9F\\x87\\xB8 \\xE0\\xA4\\xA8\\xE0"
+	          "\\xA5\\x80 \\xE0\\xAE\\xA8\\xE0\\xAE\\xBF!";
+	size_t ret, len, off;
+
+	printf("Input: \\"%s\\"\\n", s);
+
+	/* print each grapheme cluster with byte-length */
+	printf("grapheme clusters in NUL-delimited input:\\n");
+	for (off = 0; s[off] != '\\0'; off += ret) {
+		ret = grapheme_next_character_break_utf8(s + off, SIZE_MAX);
+		printf("%2zu bytes | %.*s\\n", ret, (int)ret, s + off);
+	}
+	printf("\\n");
+
+	/* do the same, but this time string is length-delimited */
+	len = 17;
+	printf("grapheme clusters in input delimited to %zu bytes:\\n", len);
+	for (off = 0; off < len; off += ret) {
+		ret = grapheme_next_character_break_utf8(s + off, len - off);
+		printf("%2zu bytes | %.*s\\n", ret, (int)ret, s + off);
+	}
+
+	return 0;
+}
+.Ed
+.Sh SEE ALSO
+.Xr grapheme_next_character_break 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_next_character_break_utf8
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_next_character_break_utf8.sh

@@ -0,0 +1,4 @@
+ENCODING="utf8" \
+TYPE="character" \
+REALTYPE="grapheme cluster" \
+	$SH man/template/next_break.sh

libs/libgrapheme-2.0.2/man/grapheme_next_line_break.3

@@ -0,0 +1,52 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_NEXT_LINE_BREAK 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_next_line_break
+.Nd determine codepoint-offset to next possible line break
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_next_line_break "const uint_least32_t *str" "size_t len"
+.Sh DESCRIPTION
+The
+.Fn grapheme_next_line_break
+function computes the offset (in codepoints) to the next possible line
+break (see
+.Xr libgrapheme 7 )
+in the codepoint array
+.Va str
+of length
+.Va len .
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the string
+.Va str
+is interpreted to be NUL-terminated and processing stops when
+a codepoint with the value 0 is encountered.
+.Pp
+For UTF-8-encoded input
+data
+.Xr grapheme_next_line_break_utf8 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_next_line_break
+function returns the offset (in codepoints) to the next possible line
+break in
+.Va str
+or 0 if
+.Va str
+is
+.Dv NULL .
+.Sh SEE ALSO
+.Xr grapheme_next_line_break_utf8 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_next_line_break
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_next_line_break.sh

@@ -0,0 +1,4 @@
+ENCODING="codepoint" \
+TYPE="line" \
+REALTYPE="possible line" \
+	$SH man/template/next_break.sh

libs/libgrapheme-2.0.2/man/grapheme_next_line_break_utf8.3

@@ -0,0 +1,90 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_NEXT_LINE_BREAK_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_next_line_break_utf8
+.Nd determine byte-offset to next possible line break
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_next_line_break_utf8 "const char *str" "size_t len"
+.Sh DESCRIPTION
+The
+.Fn grapheme_next_line_break_utf8
+function computes the offset (in bytes) to the next possible line
+break (see
+.Xr libgrapheme 7 )
+in the UTF-8-encoded string
+.Va str
+of length
+.Va len .
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the string
+.Va str
+is interpreted to be NUL-terminated and processing stops when
+a NUL-byte is encountered.
+.Pp
+For non-UTF-8 input
+data
+.Xr grapheme_next_line_break 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_next_line_break_utf8
+function returns the offset (in bytes) to the next possible line
+break in
+.Va str
+or 0 if
+.Va str
+is
+.Dv NULL .
+.Sh EXAMPLES
+.Bd -literal
+/* cc (-static) -o example example.c -lgrapheme */
+#include <grapheme.h>
+#include <stdint.h>
+#include <stdio.h>
+
+int
+main(void)
+{
+	/* UTF-8 encoded input */
+	char *s = "T\\xC3\\xABst \\xF0\\x9F\\x91\\xA8\\xE2\\x80\\x8D\\xF0"
+	          "\\x9F\\x91\\xA9\\xE2\\x80\\x8D\\xF0\\x9F\\x91\\xA6 \\xF0"
+	          "\\x9F\\x87\\xBA\\xF0\\x9F\\x87\\xB8 \\xE0\\xA4\\xA8\\xE0"
+	          "\\xA5\\x80 \\xE0\\xAE\\xA8\\xE0\\xAE\\xBF!";
+	size_t ret, len, off;
+
+	printf("Input: \\"%s\\"\\n", s);
+
+	/* print each possible line with byte-length */
+	printf("possible lines in NUL-delimited input:\\n");
+	for (off = 0; s[off] != '\\0'; off += ret) {
+		ret = grapheme_next_line_break_utf8(s + off, SIZE_MAX);
+		printf("%2zu bytes | %.*s\\n", ret, (int)ret, s + off);
+	}
+	printf("\\n");
+
+	/* do the same, but this time string is length-delimited */
+	len = 17;
+	printf("possible lines in input delimited to %zu bytes:\\n", len);
+	for (off = 0; off < len; off += ret) {
+		ret = grapheme_next_line_break_utf8(s + off, len - off);
+		printf("%2zu bytes | %.*s\\n", ret, (int)ret, s + off);
+	}
+
+	return 0;
+}
+.Ed
+.Sh SEE ALSO
+.Xr grapheme_next_line_break 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_next_line_break_utf8
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_next_line_break_utf8.sh

@@ -0,0 +1,4 @@
+ENCODING="utf8" \
+TYPE="line" \
+REALTYPE="possible line" \
+	$SH man/template/next_break.sh

libs/libgrapheme-2.0.2/man/grapheme_next_sentence_break.3

@@ -0,0 +1,55 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_NEXT_SENTENCE_BREAK 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_next_sentence_break
+.Nd determine codepoint-offset to next sentence break
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_next_sentence_break "const uint_least32_t *str" "size_t len"
+.Sh DESCRIPTION
+The
+.Fn grapheme_next_sentence_break
+function computes the offset (in codepoints) to the next sentence
+break (see
+.Xr libgrapheme 7 )
+in the codepoint array
+.Va str
+of length
+.Va len .
+If a sentence begins at
+.Va str
+this offset is equal to the length of said sentence.
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the string
+.Va str
+is interpreted to be NUL-terminated and processing stops when
+a codepoint with the value 0 is encountered.
+.Pp
+For UTF-8-encoded input
+data
+.Xr grapheme_next_sentence_break_utf8 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_next_sentence_break
+function returns the offset (in codepoints) to the next sentence
+break in
+.Va str
+or 0 if
+.Va str
+is
+.Dv NULL .
+.Sh SEE ALSO
+.Xr grapheme_next_sentence_break_utf8 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_next_sentence_break
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_next_sentence_break.sh

@@ -0,0 +1,4 @@
+ENCODING="codepoint" \
+TYPE="sentence" \
+REALTYPE="sentence" \
+	$SH man/template/next_break.sh

libs/libgrapheme-2.0.2/man/grapheme_next_sentence_break_utf8.3

@@ -0,0 +1,93 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_NEXT_SENTENCE_BREAK_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_next_sentence_break_utf8
+.Nd determine byte-offset to next sentence break
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_next_sentence_break_utf8 "const char *str" "size_t len"
+.Sh DESCRIPTION
+The
+.Fn grapheme_next_sentence_break_utf8
+function computes the offset (in bytes) to the next sentence
+break (see
+.Xr libgrapheme 7 )
+in the UTF-8-encoded string
+.Va str
+of length
+.Va len .
+If a sentence begins at
+.Va str
+this offset is equal to the length of said sentence.
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the string
+.Va str
+is interpreted to be NUL-terminated and processing stops when
+a NUL-byte is encountered.
+.Pp
+For non-UTF-8 input
+data
+.Xr grapheme_next_sentence_break 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_next_sentence_break_utf8
+function returns the offset (in bytes) to the next sentence
+break in
+.Va str
+or 0 if
+.Va str
+is
+.Dv NULL .
+.Sh EXAMPLES
+.Bd -literal
+/* cc (-static) -o example example.c -lgrapheme */
+#include <grapheme.h>
+#include <stdint.h>
+#include <stdio.h>
+
+int
+main(void)
+{
+	/* UTF-8 encoded input */
+	char *s = "T\\xC3\\xABst \\xF0\\x9F\\x91\\xA8\\xE2\\x80\\x8D\\xF0"
+	          "\\x9F\\x91\\xA9\\xE2\\x80\\x8D\\xF0\\x9F\\x91\\xA6 \\xF0"
+	          "\\x9F\\x87\\xBA\\xF0\\x9F\\x87\\xB8 \\xE0\\xA4\\xA8\\xE0"
+	          "\\xA5\\x80 \\xE0\\xAE\\xA8\\xE0\\xAE\\xBF!";
+	size_t ret, len, off;
+
+	printf("Input: \\"%s\\"\\n", s);
+
+	/* print each sentence with byte-length */
+	printf("sentences in NUL-delimited input:\\n");
+	for (off = 0; s[off] != '\\0'; off += ret) {
+		ret = grapheme_next_sentence_break_utf8(s + off, SIZE_MAX);
+		printf("%2zu bytes | %.*s\\n", ret, (int)ret, s + off);
+	}
+	printf("\\n");
+
+	/* do the same, but this time string is length-delimited */
+	len = 17;
+	printf("sentences in input delimited to %zu bytes:\\n", len);
+	for (off = 0; off < len; off += ret) {
+		ret = grapheme_next_sentence_break_utf8(s + off, len - off);
+		printf("%2zu bytes | %.*s\\n", ret, (int)ret, s + off);
+	}
+
+	return 0;
+}
+.Ed
+.Sh SEE ALSO
+.Xr grapheme_next_sentence_break 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_next_sentence_break_utf8
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_next_sentence_break_utf8.sh

@@ -0,0 +1,4 @@
+ENCODING="utf8" \
+TYPE="sentence" \
+REALTYPE="sentence" \
+	$SH man/template/next_break.sh

libs/libgrapheme-2.0.2/man/grapheme_next_word_break.3

@@ -0,0 +1,55 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_NEXT_WORD_BREAK 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_next_word_break
+.Nd determine codepoint-offset to next word break
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_next_word_break "const uint_least32_t *str" "size_t len"
+.Sh DESCRIPTION
+The
+.Fn grapheme_next_word_break
+function computes the offset (in codepoints) to the next word
+break (see
+.Xr libgrapheme 7 )
+in the codepoint array
+.Va str
+of length
+.Va len .
+If a word begins at
+.Va str
+this offset is equal to the length of said word.
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the string
+.Va str
+is interpreted to be NUL-terminated and processing stops when
+a codepoint with the value 0 is encountered.
+.Pp
+For UTF-8-encoded input
+data
+.Xr grapheme_next_word_break_utf8 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_next_word_break
+function returns the offset (in codepoints) to the next word
+break in
+.Va str
+or 0 if
+.Va str
+is
+.Dv NULL .
+.Sh SEE ALSO
+.Xr grapheme_next_word_break_utf8 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_next_word_break
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_next_word_break.sh

@@ -0,0 +1,4 @@
+ENCODING="codepoint" \
+TYPE="word" \
+REALTYPE="word" \
+	$SH man/template/next_break.sh

libs/libgrapheme-2.0.2/man/grapheme_next_word_break_utf8.3

@@ -0,0 +1,93 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_NEXT_WORD_BREAK_UTF8 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_next_word_break_utf8
+.Nd determine byte-offset to next word break
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_next_word_break_utf8 "const char *str" "size_t len"
+.Sh DESCRIPTION
+The
+.Fn grapheme_next_word_break_utf8
+function computes the offset (in bytes) to the next word
+break (see
+.Xr libgrapheme 7 )
+in the UTF-8-encoded string
+.Va str
+of length
+.Va len .
+If a word begins at
+.Va str
+this offset is equal to the length of said word.
+.Pp
+If
+.Va len
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the string
+.Va str
+is interpreted to be NUL-terminated and processing stops when
+a NUL-byte is encountered.
+.Pp
+For non-UTF-8 input
+data
+.Xr grapheme_next_word_break 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_next_word_break_utf8
+function returns the offset (in bytes) to the next word
+break in
+.Va str
+or 0 if
+.Va str
+is
+.Dv NULL .
+.Sh EXAMPLES
+.Bd -literal
+/* cc (-static) -o example example.c -lgrapheme */
+#include <grapheme.h>
+#include <stdint.h>
+#include <stdio.h>
+
+int
+main(void)
+{
+	/* UTF-8 encoded input */
+	char *s = "T\\xC3\\xABst \\xF0\\x9F\\x91\\xA8\\xE2\\x80\\x8D\\xF0"
+	          "\\x9F\\x91\\xA9\\xE2\\x80\\x8D\\xF0\\x9F\\x91\\xA6 \\xF0"
+	          "\\x9F\\x87\\xBA\\xF0\\x9F\\x87\\xB8 \\xE0\\xA4\\xA8\\xE0"
+	          "\\xA5\\x80 \\xE0\\xAE\\xA8\\xE0\\xAE\\xBF!";
+	size_t ret, len, off;
+
+	printf("Input: \\"%s\\"\\n", s);
+
+	/* print each word with byte-length */
+	printf("words in NUL-delimited input:\\n");
+	for (off = 0; s[off] != '\\0'; off += ret) {
+		ret = grapheme_next_word_break_utf8(s + off, SIZE_MAX);
+		printf("%2zu bytes | %.*s\\n", ret, (int)ret, s + off);
+	}
+	printf("\\n");
+
+	/* do the same, but this time string is length-delimited */
+	len = 17;
+	printf("words in input delimited to %zu bytes:\\n", len);
+	for (off = 0; off < len; off += ret) {
+		ret = grapheme_next_word_break_utf8(s + off, len - off);
+		printf("%2zu bytes | %.*s\\n", ret, (int)ret, s + off);
+	}
+
+	return 0;
+}
+.Ed
+.Sh SEE ALSO
+.Xr grapheme_next_word_break 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_next_word_break_utf8
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_next_word_break_utf8.sh

@@ -0,0 +1,4 @@
+ENCODING="utf8" \
+TYPE="word" \
+REALTYPE="word" \
+	$SH man/template/next_break.sh

libs/libgrapheme-2.0.2/man/grapheme_to_lowercase.3

@@ -0,0 +1,56 @@
+.Dd 2022-10-06
+.Dt GRAPHEME_TO_LOWERCASE 3
+.Os suckless.org
+.Sh NAME
+.Nm grapheme_to_lowercase
+.Nd convert codepoint array to lowercase
+.Sh SYNOPSIS
+.In grapheme.h
+.Ft size_t
+.Fn grapheme_to_lowercase "const uint_least32_t *src" "size_t srclen" "uint_least32_t *dest" "size_t destlen"
+.Sh DESCRIPTION
+The
+.Fn grapheme_to_lowercase
+function converts the codepoint array
+.Va str
+to lowercase and writes the result to
+.Va dest
+up to
+.Va destlen ,
+unless
+.Va dest
+is set to
+.Dv NULL .
+.Pp
+If
+.Va srclen
+is set to
+.Dv SIZE_MAX
+(stdint.h is already included by grapheme.h) the codepoint array
+.Va src
+is interpreted to be NUL-terminated and processing stops when a
+NUL-byte is encountered.
+.Pp
+For UTF-8-encoded input data
+.Xr grapheme_to_lowercase_utf8 3
+can be used instead.
+.Sh RETURN VALUES
+The
+.Fn grapheme_to_lowercase
+function returns the number of codepoints in the array resulting
+from converting
+.Va src
+to lowercase, even if
+.Va destlen
+is not large enough or
+.Va dest
+is
+.Dv NULL .
+.Sh SEE ALSO
+.Xr grapheme_to_lowercase_utf8 3 ,
+.Xr libgrapheme 7
+.Sh STANDARDS
+.Fn grapheme_to_lowercase
+is compliant with the Unicode 15.0.0 specification.
+.Sh AUTHORS
+.An Laslo Hunhold Aq Mt dev@frign.de

libs/libgrapheme-2.0.2/man/grapheme_to_lowercase.sh

@@ -0,0 +1,3 @@
+ENCODING="codepoint" \
+CASE="lowercase" \
+	$SH man/template/to_case.sh