pcre2: Version 10.44 (#4478) (#4678)

* update(pcre2): Version 10.44 (#4478)

* update(pcre2): Add new file to VS project files (version 10.44) (#4478)

* fix(RegEx): Use generic pcre2 function names (without suffix _8).

* update(pcre2): Fix configuration (define PCRE2_STATIC) (#4478)

Foundation/CMakeLists.txt

@@ -42,6 +42,7 @@ else()
 	POCO_SOURCES(SRCS pcre2
 		src/pcre2_auto_possess.c
 		src/pcre2_chartables.c
+		src/pcre2_chkdint.c
 		src/pcre2_compile.c
 		src/pcre2_config.c
 		src/pcre2_context.c

Foundation/Foundation_vs160.vcxproj

@@ -1047,6 +1047,7 @@
     <ClCompile Include="src\PatternFormatter.cpp" />
     <ClCompile Include="src\pcre2_auto_possess.c" />
     <ClCompile Include="src\pcre2_chartables.c" />
+    <ClCompile Include="src\pcre2_chkdint.c" />
     <ClCompile Include="src\pcre2_compile.c" />
     <ClCompile Include="src\pcre2_config.c" />
     <ClCompile Include="src\pcre2_context.c" />

Foundation/Foundation_vs160.vcxproj.filters

@@ -846,6 +846,9 @@
     <ClCompile Include="src\pcre2_chartables.c">
       <Filter>RegularExpression\PCRE2 Source Files</Filter>
     </ClCompile>
+    <ClCompile Include="src\pcre2_chkdint.c">
+      <Filter>RegularExpression\PCRE2 Source Files</Filter>
+    </ClCompile>
     <ClCompile Include="src\pcre2_compile.c">
       <Filter>RegularExpression\PCRE2 Source Files</Filter>
     </ClCompile>

Foundation/Foundation_vs170.vcxproj

@@ -1509,6 +1509,7 @@
     <ClCompile Include="src\PatternFormatter.cpp" />
     <ClCompile Include="src\pcre2_auto_possess.c" />
     <ClCompile Include="src\pcre2_chartables.c" />
+    <ClCompile Include="src\pcre2_chkdint.c" />
     <ClCompile Include="src\pcre2_compile.c" />
     <ClCompile Include="src\pcre2_config.c" />
     <ClCompile Include="src\pcre2_context.c" />

Foundation/Foundation_vs170.vcxproj.filters

@@ -846,6 +846,9 @@
     <ClCompile Include="src\pcre2_chartables.c">
       <Filter>RegularExpression\PCRE2 Source Files</Filter>
     </ClCompile>
+    <ClCompile Include="src\pcre2_chkdint.c">
+      <Filter>RegularExpression\PCRE2 Source Files</Filter>
+    </ClCompile>
     <ClCompile Include="src\pcre2_compile.c">
       <Filter>RegularExpression\PCRE2 Source Files</Filter>
     </ClCompile>

Foundation/Makefile

@@ -35,7 +35,7 @@ objects = ArchiveStrategy Ascii ASCIIEncoding AsyncChannel AsyncNotificationCent
 zlib_objects = adler32 compress crc32 deflate \
 	infback inffast inflate inftrees trees zutil
 
-pcre_objects = pcre2_auto_possess pcre2_chartables pcre2_compile pcre2_config \
+pcre_objects = pcre2_auto_possess pcre2_chartables pcre2_chkdint pcre2_compile pcre2_config \
 	pcre2_context pcre2_convert pcre2_dfa_match pcre2_error pcre2_extuni \
 	pcre2_find_bracket pcre2_jit_compile pcre2_maketables pcre2_match \
 	pcre2_match_data pcre2_newline pcre2_ord2utf pcre2_pattern_info \

Foundation/src/RegularExpression.cpp

@@ -29,34 +29,34 @@ namespace
 	class MatchData
 	{
 	public:
-		MatchData(pcre2_code_8* code):
-			_match(pcre2_match_data_create_from_pattern_8(reinterpret_cast<pcre2_code_8*>(code), nullptr))
+		MatchData(pcre2_code* code):
+			_match(pcre2_match_data_create_from_pattern(reinterpret_cast<pcre2_code*>(code), nullptr))
 		{
 			if (!_match) throw Poco::RegularExpressionException("cannot create match data");
 		}
 
 		~MatchData()
 		{
-			if (_match) pcre2_match_data_free_8(_match);
+			if (_match) pcre2_match_data_free(_match);
 		}
 
 		std::uint32_t count() const
 		{
-			return pcre2_get_ovector_count_8(_match);
+			return pcre2_get_ovector_count(_match);
 		}
 
 		const PCRE2_SIZE* data() const
 		{
-			return pcre2_get_ovector_pointer_8(_match);
+			return pcre2_get_ovector_pointer(_match);
 		}
 
-		operator pcre2_match_data_8*()
+		operator pcre2_match_data*()
 		{
 			return _match;
 		}
 
 	private:
-		pcre2_match_data_8* _match;
+		pcre2_match_data* _match;
 	};
 }
 
@@ -72,57 +72,57 @@ RegularExpression::RegularExpression(const std::string& pattern, int options, bo
 	unsigned nameEntrySize;
 	unsigned char* nameTable;
 
-	pcre2_compile_context_8* context = pcre2_compile_context_create_8(nullptr);
+	pcre2_compile_context* context = pcre2_compile_context_create(nullptr);
 	if (!context) throw Poco::RegularExpressionException("cannot create compile context");
 
 	if (options & RE_NEWLINE_LF)
-		pcre2_set_newline_8(context, PCRE2_NEWLINE_LF);
+		pcre2_set_newline(context, PCRE2_NEWLINE_LF);
 	else if (options & RE_NEWLINE_CRLF)
-		pcre2_set_newline_8(context, PCRE2_NEWLINE_CRLF);
+		pcre2_set_newline(context, PCRE2_NEWLINE_CRLF);
 	else if (options & RE_NEWLINE_ANY)
-		pcre2_set_newline_8(context, PCRE2_NEWLINE_ANY);
+		pcre2_set_newline(context, PCRE2_NEWLINE_ANY);
 	else if (options & RE_NEWLINE_ANYCRLF)
-		pcre2_set_newline_8(context, PCRE2_NEWLINE_ANYCRLF);
+		pcre2_set_newline(context, PCRE2_NEWLINE_ANYCRLF);
 	else // default RE_NEWLINE_CR
-		pcre2_set_newline_8(context, PCRE2_NEWLINE_CR);
+		pcre2_set_newline(context, PCRE2_NEWLINE_CR);
 
-	_pcre = pcre2_compile_8(reinterpret_cast<const PCRE2_SPTR>(pattern.c_str()), pattern.length(), compileOptions(options), &errorCode, &errorOffset, context);
-	pcre2_compile_context_free_8(context);
+	_pcre = pcre2_compile(reinterpret_cast<const PCRE2_SPTR>(pattern.c_str()), pattern.length(), compileOptions(options), &errorCode, &errorOffset, context);
+	pcre2_compile_context_free(context);
 
 	if (!_pcre)
 	{
 		PCRE2_UCHAR buffer[256];
-		pcre2_get_error_message_8(errorCode, buffer, sizeof(buffer));
+		pcre2_get_error_message(errorCode, buffer, sizeof(buffer));
 		std::ostringstream msg;
 		msg << reinterpret_cast<char*>(buffer) << " (at offset " << errorOffset << ")";
 		throw RegularExpressionException(msg.str());
 	}
 
-	pcre2_pattern_info_8(reinterpret_cast<pcre2_code_8*>(_pcre), PCRE2_INFO_NAMECOUNT, &nameCount);
-	pcre2_pattern_info_8(reinterpret_cast<pcre2_code_8*>(_pcre), PCRE2_INFO_NAMEENTRYSIZE, &nameEntrySize);
-	pcre2_pattern_info_8(reinterpret_cast<pcre2_code_8*>(_pcre), PCRE2_INFO_NAMETABLE, &nameTable);
+	pcre2_pattern_info(reinterpret_cast<pcre2_code*>(_pcre), PCRE2_INFO_NAMECOUNT, &nameCount);
+	pcre2_pattern_info(reinterpret_cast<pcre2_code*>(_pcre), PCRE2_INFO_NAMEENTRYSIZE, &nameEntrySize);
+	pcre2_pattern_info(reinterpret_cast<pcre2_code*>(_pcre), PCRE2_INFO_NAMETABLE, &nameTable);
 
 	for (int i = 0; i < nameCount; i++)
 	{
 		unsigned char* group = nameTable + 2 + (nameEntrySize * i);
-		int n = pcre2_substring_number_from_name_8(reinterpret_cast<pcre2_code_8*>(_pcre), group);
+		int n = pcre2_substring_number_from_name(reinterpret_cast<pcre2_code*>(_pcre), group);
 		_groups[n] = std::string(reinterpret_cast<char*>(group));
 	}
 }
 
 
 RegularExpression::~RegularExpression()
 {
-	if (_pcre) pcre2_code_free_8(reinterpret_cast<pcre2_code_8*>(_pcre));
+	if (_pcre) pcre2_code_free(reinterpret_cast<pcre2_code*>(_pcre));
 }
 
 
 int RegularExpression::match(const std::string& subject, std::string::size_type offset, Match& mtch, int options) const
 {
 	poco_assert (offset <= subject.length());
 
-	MatchData matchData(reinterpret_cast<pcre2_code_8*>(_pcre));
-	int rc = pcre2_match_8(reinterpret_cast<pcre2_code_8*>(_pcre), reinterpret_cast<const PCRE2_SPTR>(subject.c_str()), subject.size(), offset, matchOptions(options), matchData, nullptr);
+	MatchData matchData(reinterpret_cast<pcre2_code*>(_pcre));
+	int rc = pcre2_match(reinterpret_cast<pcre2_code*>(_pcre), reinterpret_cast<const PCRE2_SPTR>(subject.c_str()), subject.size(), offset, matchOptions(options), matchData, nullptr);
 	if (rc == PCRE2_ERROR_NOMATCH)
 	{
 		mtch.offset = std::string::npos;
@@ -140,7 +140,7 @@ int RegularExpression::match(const std::string& subject, std::string::size_type
 	else if (rc < 0)
 	{
 		PCRE2_UCHAR buffer[256];
-		pcre2_get_error_message_8(rc, buffer, sizeof(buffer));
+		pcre2_get_error_message(rc, buffer, sizeof(buffer));
 		throw RegularExpressionException(std::string(reinterpret_cast<char*>(buffer)));
 	}
 	const PCRE2_SIZE* ovec = matchData.data();
@@ -156,8 +156,8 @@ int RegularExpression::match(const std::string& subject, std::string::size_type
 
 	matches.clear();
 
-	MatchData matchData(reinterpret_cast<pcre2_code_8*>(_pcre));
-	int rc = pcre2_match_8(reinterpret_cast<pcre2_code_8*>(_pcre), reinterpret_cast<const PCRE2_SPTR>(subject.c_str()), subject.size(), offset, options & 0xFFFF, matchData, nullptr);
+	MatchData matchData(reinterpret_cast<pcre2_code*>(_pcre));
+	int rc = pcre2_match(reinterpret_cast<pcre2_code*>(_pcre), reinterpret_cast<const PCRE2_SPTR>(subject.c_str()), subject.size(), offset, options & 0xFFFF, matchData, nullptr);
 	if (rc == PCRE2_ERROR_NOMATCH)
 	{
 		return 0;
@@ -173,7 +173,7 @@ int RegularExpression::match(const std::string& subject, std::string::size_type
 	else if (rc < 0)
 	{
 		PCRE2_UCHAR buffer[256];
-		pcre2_get_error_message_8(rc, buffer, sizeof(buffer));
+		pcre2_get_error_message(rc, buffer, sizeof(buffer));
 		throw RegularExpressionException(std::string(reinterpret_cast<char*>(buffer)));
 	}
 	matches.reserve(rc);
@@ -279,8 +279,8 @@ std::string::size_type RegularExpression::substOne(std::string& subject, std::st
 {
 	if (offset >= subject.length()) return std::string::npos;
 
-	MatchData matchData(reinterpret_cast<pcre2_code_8*>(_pcre));
-	int rc = pcre2_match_8(reinterpret_cast<pcre2_code_8*>(_pcre), reinterpret_cast<const PCRE2_SPTR>(subject.c_str()), subject.size(), offset, matchOptions(options), matchData, nullptr);
+	MatchData matchData(reinterpret_cast<pcre2_code*>(_pcre));
+	int rc = pcre2_match(reinterpret_cast<pcre2_code*>(_pcre), reinterpret_cast<const PCRE2_SPTR>(subject.c_str()), subject.size(), offset, matchOptions(options), matchData, nullptr);
 	if (rc == PCRE2_ERROR_NOMATCH)
 	{
 		return std::string::npos;
@@ -296,7 +296,7 @@ std::string::size_type RegularExpression::substOne(std::string& subject, std::st
 	else if (rc < 0)
 	{
 		PCRE2_UCHAR buffer[256];
-		pcre2_get_error_message_8(rc, buffer, sizeof(buffer));
+		pcre2_get_error_message(rc, buffer, sizeof(buffer));
 		throw RegularExpressionException(std::string(reinterpret_cast<char*>(buffer)));
 	}
 	const PCRE2_SIZE* ovec = matchData.data();

Foundation/src/Unicode.cpp

@@ -29,7 +29,7 @@ void Unicode::properties(int ch, CharacterProperties& props)
 {
 	if (ch > UCP_MAX_CODEPOINT) ch = 0;
 	const ucd_record* ucd = GET_UCD(ch);
-	props.category = static_cast<CharacterCategory>(PRIV(ucp_gentype_8)[ucd->chartype]);
+	props.category = static_cast<CharacterCategory>(PRIV(ucp_gentype)[ucd->chartype]);
 	props.type     = static_cast<CharacterType>(ucd->chartype);
 	props.script   = static_cast<Script>(ucd->script);
 }

Foundation/src/pcre2.h

@@ -5,7 +5,7 @@
 /* This is the public header file for the PCRE library, second API, to be
 #included by applications that call PCRE2 functions.
 
-           Copyright (c) 2016-2021 University of Cambridge
+           Copyright (c) 2016-2024 University of Cambridge
 
 -----------------------------------------------------------------------------
 Redistribution and use in source and binary forms, with or without
@@ -42,9 +42,9 @@ POSSIBILITY OF SUCH DAMAGE.
 /* The current PCRE version information. */
 
 #define PCRE2_MAJOR           10
-#define PCRE2_MINOR           42
-#define PCRE2_PRERELEASE
-#define PCRE2_DATE            2022-12-11
+#define PCRE2_MINOR           44
+#define PCRE2_PRERELEASE      
+#define PCRE2_DATE            2024-06-07
 
 /* When an application links to a PCRE DLL in Windows, the symbols that are
 imported have to be identified as such. When building PCRE2, the appropriate
@@ -153,6 +153,12 @@ D   is inspected during pcre2_dfa_match() execution
 #define PCRE2_EXTRA_ESCAPED_CR_IS_LF         0x00000010u  /* C */
 #define PCRE2_EXTRA_ALT_BSUX                 0x00000020u  /* C */
 #define PCRE2_EXTRA_ALLOW_LOOKAROUND_BSK     0x00000040u  /* C */
+#define PCRE2_EXTRA_CASELESS_RESTRICT        0x00000080u  /* C */
+#define PCRE2_EXTRA_ASCII_BSD                0x00000100u  /* C */
+#define PCRE2_EXTRA_ASCII_BSS                0x00000200u  /* C */
+#define PCRE2_EXTRA_ASCII_BSW                0x00000400u  /* C */
+#define PCRE2_EXTRA_ASCII_POSIX              0x00000800u  /* C */
+#define PCRE2_EXTRA_ASCII_DIGIT              0x00001000u  /* C */
 
 /* These are for pcre2_jit_compile(). */
 
@@ -180,11 +186,12 @@ pcre2_jit_match() ignores the latter since it bypasses all sanity checks). */
 #define PCRE2_SUBSTITUTE_UNSET_EMPTY      0x00000400u  /* pcre2_substitute() only */
 #define PCRE2_SUBSTITUTE_UNKNOWN_UNSET    0x00000800u  /* pcre2_substitute() only */
 #define PCRE2_SUBSTITUTE_OVERFLOW_LENGTH  0x00001000u  /* pcre2_substitute() only */
-#define PCRE2_NO_JIT                      0x00002000u  /* Not for pcre2_dfa_match() */
+#define PCRE2_NO_JIT                      0x00002000u  /* not for pcre2_dfa_match() */
 #define PCRE2_COPY_MATCHED_SUBJECT        0x00004000u
 #define PCRE2_SUBSTITUTE_LITERAL          0x00008000u  /* pcre2_substitute() only */
 #define PCRE2_SUBSTITUTE_MATCHED          0x00010000u  /* pcre2_substitute() only */
 #define PCRE2_SUBSTITUTE_REPLACEMENT_ONLY 0x00020000u  /* pcre2_substitute() only */
+#define PCRE2_DISABLE_RECURSELOOP_CHECK   0x00040000u  /* not for pcre2_dfa_match() or pcre2_jit_match() */
 
 /* Options for pcre2_pattern_convert(). */
 
@@ -399,6 +406,7 @@ released, the numbers must not be changed. */
 #define PCRE2_ERROR_CONVERT_SYNTAX    (-64)
 #define PCRE2_ERROR_INTERNAL_DUPMATCH (-65)
 #define PCRE2_ERROR_DFA_UINVALID_UTF  (-66)
+#define PCRE2_ERROR_INVALIDOFFSET     (-67)
 
 
 /* Request types for pcre2_pattern_info() */
@@ -575,7 +583,7 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION pcre2_config(uint32_t, void *);
 PCRE2_EXP_DECL pcre2_general_context *PCRE2_CALL_CONVENTION \
   pcre2_general_context_copy(pcre2_general_context *); \
 PCRE2_EXP_DECL pcre2_general_context *PCRE2_CALL_CONVENTION \
-  pcre2_general_context_create(void *(*)(PCRE2_SIZE, void *), \
+  pcre2_general_context_create(void *(*)(size_t, void *), \
     void (*)(void *, void *), void *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_general_context_free(pcre2_general_context *);
@@ -595,6 +603,10 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_set_compile_extra_options(pcre2_compile_context *, uint32_t); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_set_max_pattern_length(pcre2_compile_context *, PCRE2_SIZE); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_max_pattern_compiled_length(pcre2_compile_context *, PCRE2_SIZE); \
+PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
+  pcre2_set_max_varlookbehind(pcre2_compile_context *, uint32_t); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_set_newline(pcre2_compile_context *, uint32_t); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
@@ -628,7 +640,7 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_set_recursion_limit(pcre2_match_context *, uint32_t); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_set_recursion_memory_management(pcre2_match_context *, \
-    void *(*)(PCRE2_SIZE, void *), void (*)(void *, void *), void *);
+    void *(*)(size_t, void *), void (*)(void *, void *), void *);
 
 #define PCRE2_CONVERT_CONTEXT_FUNCTIONS \
 PCRE2_EXP_DECL pcre2_convert_context *PCRE2_CALL_CONVENTION \
@@ -687,6 +699,8 @@ PCRE2_EXP_DECL PCRE2_SPTR PCRE2_CALL_CONVENTION \
   pcre2_get_mark(pcre2_match_data *); \
 PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
   pcre2_get_match_data_size(pcre2_match_data *); \
+PCRE2_EXP_DECL PCRE2_SIZE PCRE2_CALL_CONVENTION \
+  pcre2_get_match_data_heapframes_size(pcre2_match_data *); \
 PCRE2_EXP_DECL uint32_t PCRE2_CALL_CONVENTION \
   pcre2_get_ovector_count(pcre2_match_data *); \
 PCRE2_EXP_DECL PCRE2_SIZE *PCRE2_CALL_CONVENTION \
@@ -722,7 +736,7 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_substring_number_from_name(const pcre2_code *, PCRE2_SPTR); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
-  pcre2_substring_list_free(PCRE2_SPTR *); \
+  pcre2_substring_list_free(PCRE2_UCHAR **); \
 PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
   pcre2_substring_list_get(pcre2_match_data *, PCRE2_UCHAR ***, PCRE2_SIZE **);
 
@@ -771,7 +785,7 @@ PCRE2_EXP_DECL int PCRE2_CALL_CONVENTION \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_jit_free_unused_memory(pcre2_general_context *); \
 PCRE2_EXP_DECL pcre2_jit_stack *PCRE2_CALL_CONVENTION \
-  pcre2_jit_stack_create(PCRE2_SIZE, PCRE2_SIZE, pcre2_general_context *); \
+  pcre2_jit_stack_create(size_t, size_t, pcre2_general_context *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
   pcre2_jit_stack_assign(pcre2_match_context *, pcre2_jit_callback, void *); \
 PCRE2_EXP_DECL void PCRE2_CALL_CONVENTION \
@@ -851,6 +865,7 @@ pcre2_compile are called by application code. */
 #define pcre2_general_context_free            PCRE2_SUFFIX(pcre2_general_context_free_)
 #define pcre2_get_error_message               PCRE2_SUFFIX(pcre2_get_error_message_)
 #define pcre2_get_mark                        PCRE2_SUFFIX(pcre2_get_mark_)
+#define pcre2_get_match_data_heapframes_size  PCRE2_SUFFIX(pcre2_get_match_data_heapframes_size_)
 #define pcre2_get_match_data_size             PCRE2_SUFFIX(pcre2_get_match_data_size_)
 #define pcre2_get_ovector_pointer             PCRE2_SUFFIX(pcre2_get_ovector_pointer_)
 #define pcre2_get_ovector_count               PCRE2_SUFFIX(pcre2_get_ovector_count_)
@@ -886,7 +901,9 @@ pcre2_compile are called by application code. */
 #define pcre2_set_glob_separator              PCRE2_SUFFIX(pcre2_set_glob_separator_)
 #define pcre2_set_heap_limit                  PCRE2_SUFFIX(pcre2_set_heap_limit_)
 #define pcre2_set_match_limit                 PCRE2_SUFFIX(pcre2_set_match_limit_)
+#define pcre2_set_max_varlookbehind           PCRE2_SUFFIX(pcre2_set_max_varlookbehind_)
 #define pcre2_set_max_pattern_length          PCRE2_SUFFIX(pcre2_set_max_pattern_length_)
+#define pcre2_set_max_pattern_compiled_length PCRE2_SUFFIX(pcre2_set_max_pattern_compiled_length_)
 #define pcre2_set_newline                     PCRE2_SUFFIX(pcre2_set_newline_)
 #define pcre2_set_parens_nest_limit           PCRE2_SUFFIX(pcre2_set_parens_nest_limit_)
 #define pcre2_set_offset_limit                PCRE2_SUFFIX(pcre2_set_offset_limit_)