v2.8.0 bump (#248)

* version 2.8.0 bump

* NEWS link

CMakeLists.txt

@@ -7,14 +7,14 @@ disallow_intree_builds()
 if (POLICY CMP0048)
   cmake_policy (SET CMP0048 NEW)
 endif ()
-project (utf8proc VERSION 2.6.1 LANGUAGES C)
+project (utf8proc VERSION 2.8.0 LANGUAGES C)
 
 # This is the ABI version number, which may differ from the
-# API version number (defined in utf8proc.h).
+# API version number (defined in utf8proc.h and above).
 # Be sure to also update these in Makefile and MANIFEST!
 set(SO_MAJOR 2)
-set(SO_MINOR 4)
-set(SO_PATCH 1)
+set(SO_MINOR 6)
+set(SO_PATCH 0)
 
 option(UTF8PROC_INSTALL "Enable installation of utf8proc" On)
 option(UTF8PROC_ENABLE_TESTING "Enable testing of utf8proc" Off)
@@ -68,7 +68,7 @@ endif()
 if(UTF8PROC_ENABLE_TESTING)
   enable_testing()
   file(MAKE_DIRECTORY data)
-  set(UNICODE_VERSION 13.0.0)
+  set(UNICODE_VERSION 15.0.0)
   file(DOWNLOAD https://www.unicode.org/Public/${UNICODE_VERSION}/ucd/NormalizationTest.txt ${CMAKE_BINARY_DIR}/data/NormalizationTest.txt SHOW_PROGRESS)
   file(DOWNLOAD https://www.unicode.org/Public/${UNICODE_VERSION}/ucd/auxiliary/GraphemeBreakTest.txt ${CMAKE_BINARY_DIR}/data/GraphemeBreakTest.txt SHOW_PROGRESS)
   add_executable(case test/tests.h test/tests.c utf8proc.h test/case.c)

Doxyfile

@@ -1,4 +1,4 @@
-# Doxyfile 1.8.18
+# Doxyfile 1.9.1
 
 # This file describes the settings to be used by the documentation system
 # doxygen (www.doxygen.org) for a project.
@@ -32,7 +32,7 @@ DOXYFILE_ENCODING      = UTF-8
 # title of most generated pages and in a few other places.
 # The default value is: My Project.
 
-PROJECT_NAME           = "utf8proc"
+PROJECT_NAME           = utf8proc
 
 # The PROJECT_NUMBER tag can be used to enter a project or revision number. This
 # could be handy for archiving the generated documentation or if some version
@@ -217,6 +217,14 @@ QT_AUTOBRIEF           = NO
 
 MULTILINE_CPP_IS_BRIEF = NO
 
+# By default Python docstrings are displayed as preformatted text and doxygen's
+# special commands cannot be used. By setting PYTHON_DOCSTRING to NO the
+# doxygen's special commands can be used and the contents of the docstring
+# documentation blocks is shown as doxygen documentation.
+# The default value is: YES.
+
+PYTHON_DOCSTRING       = YES
+
 # If the INHERIT_DOCS tag is set to YES then an undocumented member inherits the
 # documentation from any documented member that it re-implements.
 # The default value is: YES.
@@ -305,7 +313,10 @@ OPTIMIZE_OUTPUT_SLICE  = NO
 # Note: For files without extension you can use no_extension as a placeholder.
 #
 # Note that for custom extensions you also need to set FILE_PATTERNS otherwise
-# the files are not read by doxygen.
+# the files are not read by doxygen. When specifying no_extension you should add
+# * to the FILE_PATTERNS.
+#
+# Note see also the list of default file extension mappings.
 
 EXTENSION_MAPPING      =
 
@@ -439,6 +450,19 @@ TYPEDEF_HIDES_STRUCT   = NO
 
 LOOKUP_CACHE_SIZE      = 0
 
+# The NUM_PROC_THREADS specifies the number threads doxygen is allowed to use
+# during processing. When set to 0 doxygen will based this on the number of
+# cores available in the system. You can set it explicitly to a value larger
+# than 0 to get more control over the balance between CPU load and processing
+# speed. At this moment only the input processing can be done using multiple
+# threads. Since this is still an experimental feature the default is set to 1,
+# which efficively disables parallel processing. Please report any issues you
+# encounter. Generating dot graphs in parallel is controlled by the
+# DOT_NUM_THREADS setting.
+# Minimum value: 0, maximum value: 32, default value: 1.
+
+NUM_PROC_THREADS       = 1
+
 #---------------------------------------------------------------------------
 # Build related configuration options
 #---------------------------------------------------------------------------
@@ -502,6 +526,13 @@ EXTRACT_LOCAL_METHODS  = NO
 
 EXTRACT_ANON_NSPACES   = NO
 
+# If this flag is set to YES, the name of an unnamed parameter in a declaration
+# will be determined by the corresponding definition. By default unnamed
+# parameters remain unnamed in the output.
+# The default value is: YES.
+
+RESOLVE_UNNAMED_PARAMS = YES
+
 # If the HIDE_UNDOC_MEMBERS tag is set to YES, doxygen will hide all
 # undocumented members inside documented classes or files. If set to NO these
 # members will be included in the various overviews, but no documentation
@@ -539,11 +570,18 @@ HIDE_IN_BODY_DOCS      = NO
 
 INTERNAL_DOCS          = NO
 
-# If the CASE_SENSE_NAMES tag is set to NO then doxygen will only generate file
-# names in lower-case letters. If set to YES, upper-case letters are also
-# allowed. This is useful if you have classes or files whose names only differ
-# in case and if your file system supports case sensitive file names. Windows
-# (including Cygwin) ands Mac users are advised to set this option to NO.
+# With the correct setting of option CASE_SENSE_NAMES doxygen will better be
+# able to match the capabilities of the underlying filesystem. In case the
+# filesystem is case sensitive (i.e. it supports files in the same directory
+# whose names only differ in casing), the option must be set to YES to properly
+# deal with such files in case they appear in the input. For filesystems that
+# are not case sensitive the option should be be set to NO to properly deal with
+# output files written for symbols that only differ in casing, such as for two
+# classes, one named CLASS and the other named Class, and to also support
+# references to files without having to specify the exact matching casing. On
+# Windows (including Cygwin) and MacOS, users should typically set this option
+# to NO, whereas on Linux or other Unix flavors it should typically be set to
+# YES.
 # The default value is: system dependent.
 
 CASE_SENSE_NAMES       = NO
@@ -782,7 +820,10 @@ WARN_IF_DOC_ERROR      = YES
 WARN_NO_PARAMDOC       = NO
 
 # If the WARN_AS_ERROR tag is set to YES then doxygen will immediately stop when
-# a warning is encountered.
+# a warning is encountered. If the WARN_AS_ERROR tag is set to FAIL_ON_WARNINGS
+# then doxygen will continue running as if WARN_AS_ERROR tag is set to NO, but
+# at the end of the doxygen process doxygen will return with a non-zero status.
+# Possible values are: NO, YES and FAIL_ON_WARNINGS.
 # The default value is: NO.
 
 WARN_AS_ERROR          = NO
@@ -818,8 +859,8 @@ INPUT                  =
 # This tag can be used to specify the character encoding of the source files
 # that doxygen parses. Internally doxygen uses the UTF-8 encoding. Doxygen uses
 # libiconv (or the iconv built into libc) for the transcoding. See the libiconv
-# documentation (see: https://www.gnu.org/software/libiconv/) for the list of
-# possible encodings.
+# documentation (see:
+# https://www.gnu.org/software/libiconv/) for the list of possible encodings.
 # The default value is: UTF-8.
 
 INPUT_ENCODING         = UTF-8
@@ -832,13 +873,15 @@ INPUT_ENCODING         = UTF-8
 # need to set EXTENSION_MAPPING for the extension otherwise the files are not
 # read by doxygen.
 #
+# Note the list of default checked file patterns might differ from the list of
+# default file extension mappings.
+#
 # If left blank the following patterns are tested:*.c, *.cc, *.cxx, *.cpp,
 # *.c++, *.java, *.ii, *.ixx, *.ipp, *.i++, *.inl, *.idl, *.ddl, *.odl, *.h,
 # *.hh, *.hxx, *.hpp, *.h++, *.cs, *.d, *.php, *.php4, *.php5, *.phtml, *.inc,
 # *.m, *.markdown, *.md, *.mm, *.dox (to be provided as doxygen C comment),
-# *.doc (to be provided as doxygen C comment), *.txt (to be provided as doxygen
-# C comment), *.py, *.pyw, *.f90, *.f95, *.f03, *.f08, *.f18, *.f, *.for, *.vhd,
-# *.vhdl, *.ucf, *.qsf and *.ice.
+# *.py, *.pyw, *.f90, *.f95, *.f03, *.f08, *.f18, *.f, *.for, *.vhd, *.vhdl,
+# *.ucf, *.qsf and *.ice.
 
 FILE_PATTERNS          =
 
@@ -1065,13 +1108,6 @@ VERBATIM_HEADERS       = YES
 
 ALPHABETICAL_INDEX     = YES
 
-# The COLS_IN_ALPHA_INDEX tag can be used to specify the number of columns in
-# which the alphabetical index list will be split.
-# Minimum value: 1, maximum value: 20, default value: 5.
-# This tag requires that the tag ALPHABETICAL_INDEX is set to YES.
-
-COLS_IN_ALPHA_INDEX    = 5
-
 # In case all classes in a project start with a common prefix, all classes will
 # be put under the same header in the alphabetical index. The IGNORE_PREFIX tag
 # can be used to specify a prefix (or a list of prefixes) that should be ignored
@@ -1242,10 +1278,11 @@ HTML_INDEX_NUM_ENTRIES = 100
 
 # If the GENERATE_DOCSET tag is set to YES, additional index files will be
 # generated that can be used as input for Apple's Xcode 3 integrated development
-# environment (see: https://developer.apple.com/xcode/), introduced with OSX
-# 10.5 (Leopard). To create a documentation set, doxygen will generate a
-# Makefile in the HTML output directory. Running make will produce the docset in
-# that directory and running make install will install the docset in
+# environment (see:
+# https://developer.apple.com/xcode/), introduced with OSX 10.5 (Leopard). To
+# create a documentation set, doxygen will generate a Makefile in the HTML
+# output directory. Running make will produce the docset in that directory and
+# running make install will install the docset in
 # ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find it at
 # startup. See https://developer.apple.com/library/archive/featuredarticles/Doxy
 # genXcode/_index.html for more information.
@@ -1287,8 +1324,8 @@ DOCSET_PUBLISHER_NAME  = Publisher
 # If the GENERATE_HTMLHELP tag is set to YES then doxygen generates three
 # additional HTML index files: index.hhp, index.hhc, and index.hhk. The
 # index.hhp is a project file that can be read by Microsoft's HTML Help Workshop
-# (see: https://www.microsoft.com/en-us/download/details.aspx?id=21138) on
-# Windows.
+# (see:
+# https://www.microsoft.com/en-us/download/details.aspx?id=21138) on Windows.
 #
 # The HTML Help Workshop contains a compiler that can convert all HTML output
 # generated by doxygen into a single compiled HTML file (.chm). Compiled HTML
@@ -1318,7 +1355,7 @@ CHM_FILE               =
 HHC_LOCATION           =
 
 # The GENERATE_CHI flag controls if a separate .chi index file is generated
-# (YES) or that it should be included in the master .chm file (NO).
+# (YES) or that it should be included in the main .chm file (NO).
 # The default value is: NO.
 # This tag requires that the tag GENERATE_HTMLHELP is set to YES.
 
@@ -1363,7 +1400,8 @@ QCH_FILE               =
 
 # The QHP_NAMESPACE tag specifies the namespace to use when generating Qt Help
 # Project output. For more information please see Qt Help Project / Namespace
-# (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#namespace).
+# (see:
+# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#namespace).
 # The default value is: org.doxygen.Project.
 # This tag requires that the tag GENERATE_QHP is set to YES.
 
@@ -1371,8 +1409,8 @@ QHP_NAMESPACE          = org.doxygen.Project
 
 # The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating Qt
 # Help Project output. For more information please see Qt Help Project / Virtual
-# Folders (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#virtual-
-# folders).
+# Folders (see:
+# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#virtual-folders).
 # The default value is: doc.
 # This tag requires that the tag GENERATE_QHP is set to YES.
 
@@ -1380,16 +1418,16 @@ QHP_VIRTUAL_FOLDER     = doc
 
 # If the QHP_CUST_FILTER_NAME tag is set, it specifies the name of a custom
 # filter to add. For more information please see Qt Help Project / Custom
-# Filters (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-
-# filters).
+# Filters (see:
+# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-filters).
 # This tag requires that the tag GENERATE_QHP is set to YES.
 
 QHP_CUST_FILTER_NAME   =
 
 # The QHP_CUST_FILTER_ATTRS tag specifies the list of the attributes of the
 # custom filter to add. For more information please see Qt Help Project / Custom
-# Filters (see: https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-
-# filters).
+# Filters (see:
+# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-filters).
 # This tag requires that the tag GENERATE_QHP is set to YES.
 
 QHP_CUST_FILTER_ATTRS  =
@@ -1401,9 +1439,9 @@ QHP_CUST_FILTER_ATTRS  =
 
 QHP_SECT_FILTER_ATTRS  =
 
-# The QHG_LOCATION tag can be used to specify the location of Qt's
-# qhelpgenerator. If non-empty doxygen will try to run qhelpgenerator on the
-# generated .qhp file.
+# The QHG_LOCATION tag can be used to specify the location (absolute path
+# including file name) of Qt's qhelpgenerator. If non-empty doxygen will try to
+# run qhelpgenerator on the generated .qhp file.
 # This tag requires that the tag GENERATE_QHP is set to YES.
 
 QHG_LOCATION           =
@@ -1484,8 +1522,8 @@ EXT_LINKS_IN_WINDOW    = NO
 # tool (see https://github.com/dawbarton/pdf2svg) or inkscape (see
 # https://inkscape.org) to generate formulas as SVG images instead of PNGs for
 # the HTML output. These images will generally look nicer at scaled resolutions.
-# Possible values are: png The default and svg Looks nicer but requires the
-# pdf2svg tool.
+# Possible values are: png (the default) and svg (looks nicer but requires the
+# pdf2svg or inkscape tool).
 # The default value is: png.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
@@ -1530,7 +1568,7 @@ USE_MATHJAX            = NO
 
 # When MathJax is enabled you can set the default output format to be used for
 # the MathJax output. See the MathJax site (see:
-# http://docs.mathjax.org/en/latest/output.html) for more details.
+# http://docs.mathjax.org/en/v2.7-latest/output.html) for more details.
 # Possible values are: HTML-CSS (which is slower, but has the best
 # compatibility), NativeMML (i.e. MathML) and SVG.
 # The default value is: HTML-CSS.
@@ -1560,7 +1598,8 @@ MATHJAX_EXTENSIONS     =
 
 # The MATHJAX_CODEFILE tag can be used to specify a file with javascript pieces
 # of code that will be used on startup of the MathJax code. See the MathJax site
-# (see: http://docs.mathjax.org/en/latest/output.html) for more details. For an
+# (see:
+# http://docs.mathjax.org/en/v2.7-latest/output.html) for more details. For an
 # example see the documentation.
 # This tag requires that the tag USE_MATHJAX is set to YES.
 
@@ -1607,7 +1646,8 @@ SERVER_BASED_SEARCH    = NO
 #
 # Doxygen ships with an example indexer (doxyindexer) and search engine
 # (doxysearch.cgi) which are based on the open source search engine library
-# Xapian (see: https://xapian.org/).
+# Xapian (see:
+# https://xapian.org/).
 #
 # See the section "External Indexing and Searching" for details.
 # The default value is: NO.
@@ -1620,8 +1660,9 @@ EXTERNAL_SEARCH        = NO
 #
 # Doxygen ships with an example indexer (doxyindexer) and search engine
 # (doxysearch.cgi) which are based on the open source search engine library
-# Xapian (see: https://xapian.org/). See the section "External Indexing and
-# Searching" for details.
+# Xapian (see:
+# https://xapian.org/). See the section "External Indexing and Searching" for
+# details.
 # This tag requires that the tag SEARCHENGINE is set to YES.
 
 SEARCHENGINE_URL       =
@@ -1785,9 +1826,11 @@ LATEX_EXTRA_FILES      =
 
 PDF_HYPERLINKS         = YES
 
-# If the USE_PDFLATEX tag is set to YES, doxygen will use pdflatex to generate
-# the PDF file directly from the LaTeX files. Set this option to YES, to get a
-# higher quality PDF documentation.
+# If the USE_PDFLATEX tag is set to YES, doxygen will use the engine as
+# specified with LATEX_CMD_NAME to generate the PDF file directly from the LaTeX
+# files. Set this option to YES, to get a higher quality PDF documentation.
+#
+# See also section LATEX_CMD_NAME for selecting the engine.
 # The default value is: YES.
 # This tag requires that the tag GENERATE_LATEX is set to YES.
 
@@ -2298,10 +2341,32 @@ UML_LOOK               = NO
 # but if the number exceeds 15, the total amount of fields shown is limited to
 # 10.
 # Minimum value: 0, maximum value: 100, default value: 10.
-# This tag requires that the tag HAVE_DOT is set to YES.
+# This tag requires that the tag UML_LOOK is set to YES.
 
 UML_LIMIT_NUM_FIELDS   = 10
 
+# If the DOT_UML_DETAILS tag is set to NO, doxygen will show attributes and
+# methods without types and arguments in the UML graphs. If the DOT_UML_DETAILS
+# tag is set to YES, doxygen will add type and arguments for attributes and
+# methods in the UML graphs. If the DOT_UML_DETAILS tag is set to NONE, doxygen
+# will not generate fields with class member information in the UML graphs. The
+# class diagrams will look similar to the default class diagrams but using UML
+# notation for the relationships.
+# Possible values are: NO, YES and NONE.
+# The default value is: NO.
+# This tag requires that the tag UML_LOOK is set to YES.
+
+DOT_UML_DETAILS        = NO
+
+# The DOT_WRAP_THRESHOLD tag can be used to set the maximum number of characters
+# to display on a single line. If the actual line length exceeds this threshold
+# significantly it will wrapped across multiple lines. Some heuristics are apply
+# to avoid ugly line breaks.
+# Minimum value: 0, maximum value: 1000, default value: 17.
+# This tag requires that the tag HAVE_DOT is set to YES.
+
+DOT_WRAP_THRESHOLD     = 17
+
 # If the TEMPLATE_RELATIONS tag is set to YES then the inheritance and
 # collaboration graphs will show the relations between templates and their
 # instances.
@@ -2491,9 +2556,11 @@ DOT_MULTI_TARGETS      = NO
 
 GENERATE_LEGEND        = YES
 
-# If the DOT_CLEANUP tag is set to YES, doxygen will remove the intermediate dot
+# If the DOT_CLEANUP tag is set to YES, doxygen will remove the intermediate
 # files that are used to generate the various graphs.
+#
+# Note: This setting is not only used for dot files but also for msc and
+# plantuml temporary files.
 # The default value is: YES.
-# This tag requires that the tag HAVE_DOT is set to YES.
 
 DOT_CLEANUP            = YES

LICENSE.md

@@ -7,7 +7,7 @@ whose copyright and license statements are reproduced below, all new
 work on the utf8proc library is licensed under the [MIT "expat"
 license](http://opensource.org/licenses/MIT):
 
-*Copyright © 2014-2019 by Steven G. Johnson, Jiahao Chen, Tony Kelman, Jonas Fonseca, and other contributors listed in the git history.*
+*Copyright © 2014-2021 by Steven G. Johnson, Jiahao Chen, Tony Kelman, Jonas Fonseca, and other contributors listed in the git history.*
 
 Permission is hereby granted, free of charge, to any person obtaining a
 copy of this software and associated documentation files (the "Software"),

MANIFEST

@@ -2,8 +2,8 @@ include/
 include/utf8proc.h
 lib/
 lib/libutf8proc.a
-lib/libutf8proc.so -> libutf8proc.so.2.4.1
-lib/libutf8proc.so.2 -> libutf8proc.so.2.4.1
-lib/libutf8proc.so.2.4.1
+lib/libutf8proc.so -> libutf8proc.so.2.6.0
+lib/libutf8proc.so.2 -> libutf8proc.so.2.6.0
+lib/libutf8proc.so.2.6.0
 lib/pkgconfig/
 lib/pkgconfig/libutf8proc.pc

Makefile

@@ -23,8 +23,8 @@ SOFLAG = -Wl,-soname
 # The API version number is defined in utf8proc.h.
 # Be sure to also update these ABI versions in MANIFEST and CMakeLists.txt!
 MAJOR=2
-MINOR=4
-PATCH=1
+MINOR=6
+PATCH=0
 
 OS := $(shell uname)
 ifeq ($(OS),Darwin) # MacOS X
@@ -78,7 +78,7 @@ utf8proc.o: utf8proc.h utf8proc.c utf8proc_data.c
 
 libutf8proc.a: utf8proc.o
 	rm -f libutf8proc.a
-	$(AR) rs libutf8proc.a utf8proc.o
+	$(AR) crs libutf8proc.a utf8proc.o
 
 libutf8proc.so.$(MAJOR).$(MINOR).$(PATCH): utf8proc.o
 	$(CC) $(LDFLAGS) $(LDFLAG_SHARED) -o $@ $(SOFLAG) -Wl,libutf8proc.so.$(MAJOR) utf8proc.o

NEWS.md

@@ -1,5 +1,23 @@
 # utf8proc release history #
 
+## Version 2.8.0 ##
+
+2022-10-30
+
+ - Unicode 15 support ([#247]).
+
+## Version 2.7.0 ##
+
+2021-12-16
+
+ - Unicode 14 support ([#233]).
+
+ - Support `GNUInstallDirs` in CMake build ([#159]).
+
+ - `cmake` build now installs `pkg-config` file ([#224]).
+
+ - Various build and portability improvements.
+
 ## Version 2.6.1 ##
 
 2020-12-15
@@ -409,8 +427,12 @@ Release of version 1.0.1
 [#152]: https://github.com/JuliaStrings/utf8proc/issues/152
 [#154]: https://github.com/JuliaStrings/utf8proc/issues/154
 [#156]: https://github.com/JuliaStrings/utf8proc/issues/156
+[#159]: https://github.com/JuliaStrings/utf8proc/issues/159
 [#167]: https://github.com/JuliaStrings/utf8proc/issues/167
 [#173]: https://github.com/JuliaStrings/utf8proc/issues/173
 [#179]: https://github.com/JuliaStrings/utf8proc/issues/179
 [#196]: https://github.com/JuliaStrings/utf8proc/issues/196
 [#205]: https://github.com/JuliaStrings/utf8proc/issues/205
+[#224]: https://github.com/JuliaStrings/utf8proc/issues/224
+[#233]: https://github.com/JuliaStrings/utf8proc/issues/233
+[#247]: https://github.com/JuliaStrings/utf8proc/issues/247

README.md

@@ -38,9 +38,8 @@ For compilation of the C library, run `make`.  You can also install the library
 Alternatively, you can compile with `cmake`, e.g. by
 ```sh
 mkdir build
-cd build
-cmake ..
-make
+cmake -S . -B build
+cmake --build build
 ```
 
 ### Using other compilers
@@ -60,7 +59,7 @@ The C library is found in this directory after successful compilation
 and is named `libutf8proc.a` (for the static library) and
 `libutf8proc.so` (for the dynamic library).
 
-The Unicode version supported is 13.0.0.
+The Unicode version supported is 15.0.0.
 
 For Unicode normalizations, the following options are used:
 

data/Makefile

@@ -22,7 +22,7 @@ CharWidths.txt: charwidths.jl EastAsianWidth.txt
 	$(JULIA) charwidths.jl > $@
 
 # Unicode data version (must also update utf8proc_unicode_version function)
-UNICODE_VERSION=13.0.0
+UNICODE_VERSION=15.0.0
 
 UnicodeData.txt:
 	$(CURL) $(CURLFLAGS) -o $@ https://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/UnicodeData.txt

test/fuzzer.c

@@ -5,10 +5,13 @@ int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
 {
     if(size < 1) return 0;
 
+    /* Avoid timeout with long inputs */
+    if(size > (64 * 1024)) return 0;
+
     if(data[size-1] != '\0') return 0;
 
     const uint8_t* ptr = data;
-    utf8proc_int32_t c = 0;
+    utf8proc_int32_t c = 0, c_prev = 0, state = 0;
     utf8proc_option_t options;
     utf8proc_ssize_t ret, bytes = 0;
     size_t len = strlen((const char*)data);
@@ -31,6 +34,11 @@ int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         utf8proc_category(c);
         utf8proc_category_string(c);
         utf8proc_codepoint_valid(c);
+        
+        utf8proc_grapheme_break(c_prev, c);
+        utf8proc_grapheme_break_stateful(c_prev, c, &state);
+        
+        c_prev = c;
     }
     
     utf8proc_int32_t *copy = size >= 4 ? NULL : malloc(size);
@@ -54,7 +62,11 @@ int LLVMFuzzerTestOneInput(const uint8_t* data, size_t size)
         options = UTF8PROC_STRIPCC;
         memcpy(copy, data, size);
         utf8proc_normalize_utf32(copy, size, options);
-        
+
+        options = UTF8PROC_LUMP;
+        memcpy(copy, data, size);
+        utf8proc_normalize_utf32(copy, size, options);
+
         options = 0;
         memcpy(copy, data, size);
         utf8proc_normalize_utf32(copy, size, options);

utf8proc.c

@@ -1,6 +1,6 @@
 /* -*- mode: c; c-basic-offset: 2; tab-width: 2; indent-tabs-mode: nil -*- */
 /*
- *  Copyright (c) 2014-2019 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
+ *  Copyright (c) 2014-2021 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
  *  Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
  *
  *  Permission is hereby granted, free of charge, to any person obtaining a
@@ -101,7 +101,7 @@ UTF8PROC_DLLEXPORT const char *utf8proc_version(void) {
 }
 
 UTF8PROC_DLLEXPORT const char *utf8proc_unicode_version(void) {
-  return "13.0.0";
+  return "15.0.0";
 }
 
 UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode) {
@@ -410,7 +410,7 @@ UTF8PROC_DLLEXPORT int utf8proc_charwidth(utf8proc_int32_t c) {
 }
 
 UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t c) {
-  return utf8proc_get_property(c)->category;
+  return (utf8proc_category_t) utf8proc_get_property(c)->category;
 }
 
 UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t c) {

utf8proc.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2014-2019 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
+ * Copyright (c) 2014-2021 Steven G. Johnson, Jiahao Chen, Peter Colberg, Tony Kelman, Scott P. Jones, and other contributors.
  * Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
@@ -71,9 +71,9 @@
 /** The MAJOR version number (increased when backwards API compatibility is broken). */
 #define UTF8PROC_VERSION_MAJOR 2
 /** The MINOR version number (increased when new functionality is added in a backwards-compatible manner). */
-#define UTF8PROC_VERSION_MINOR 6
+#define UTF8PROC_VERSION_MINOR 8
 /** The PATCH version (increased for fixes that do not change the API). */
-#define UTF8PROC_VERSION_PATCH 1
+#define UTF8PROC_VERSION_PATCH 0
 /** @} */
 
 #include <stdlib.h>