diff options
Diffstat (limited to 'gpr/source/lib/expat_lib')
21 files changed, 7145 insertions, 0 deletions
diff --git a/gpr/source/lib/expat_lib/CMakeLists.txt b/gpr/source/lib/expat_lib/CMakeLists.txt new file mode 100644 index 0000000..a4c44f8 --- /dev/null +++ b/gpr/source/lib/expat_lib/CMakeLists.txt @@ -0,0 +1,21 @@ +# library +set( LIB_NAME expat_lib ) + +# get source files +file( GLOB SRC_FILES "*.c" ) + +# get include files +file( GLOB INC_FILES "*.h" ) + +# library +add_library( ${LIB_NAME} STATIC ${SRC_FILES} ${INC_FILES} ) + +# define compile time definitions +target_compile_definitions( ${LIB_NAME} PUBLIC XML_STATIC=1 ) + +SET(CMAKE_XCODE_ATTRIBUTE_CLANG_CXX_LIBRARY "libstdc++") + +target_link_libraries( ${LIB_NAME} ) + +# set the folder where to place the projects +set_target_properties( ${LIB_NAME} PROPERTIES FOLDER lib ) diff --git a/gpr/source/lib/expat_lib/amigaconfig.h b/gpr/source/lib/expat_lib/amigaconfig.h new file mode 100644 index 0000000..740f565 --- /dev/null +++ b/gpr/source/lib/expat_lib/amigaconfig.h @@ -0,0 +1,29 @@ +#ifndef AMIGACONFIG_H +#define AMIGACONFIG_H + +/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */ +#define BYTEORDER 4321 + +/* Define to 1 if you have the `bcopy' function. */ +#define HAVE_BCOPY 1 + +/* Define to 1 if you have the <check.h> header file. */ +#undef HAVE_CHECK_H + +/* Define to 1 if you have the <unistd.h> header file. */ +#define HAVE_UNISTD_H 1 + +/* whether byteorder is bigendian */ +#define WORDS_BIGENDIAN + +/* Define to specify how much context to retain around the current parse + point. */ +#define XML_CONTEXT_BYTES 1024 + +/* Define to make parameter entity parsing functionality available. */ +#define XML_DTD + +/* Define to make XML Namespaces functionality available. */ +#define XML_NS + +#endif /* AMIGACONFIG_H */ diff --git a/gpr/source/lib/expat_lib/ascii.h b/gpr/source/lib/expat_lib/ascii.h new file mode 100644 index 0000000..d10530b --- /dev/null +++ b/gpr/source/lib/expat_lib/ascii.h @@ -0,0 +1,92 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#define ASCII_A 0x41 +#define ASCII_B 0x42 +#define ASCII_C 0x43 +#define ASCII_D 0x44 +#define ASCII_E 0x45 +#define ASCII_F 0x46 +#define ASCII_G 0x47 +#define ASCII_H 0x48 +#define ASCII_I 0x49 +#define ASCII_J 0x4A +#define ASCII_K 0x4B +#define ASCII_L 0x4C +#define ASCII_M 0x4D +#define ASCII_N 0x4E +#define ASCII_O 0x4F +#define ASCII_P 0x50 +#define ASCII_Q 0x51 +#define ASCII_R 0x52 +#define ASCII_S 0x53 +#define ASCII_T 0x54 +#define ASCII_U 0x55 +#define ASCII_V 0x56 +#define ASCII_W 0x57 +#define ASCII_X 0x58 +#define ASCII_Y 0x59 +#define ASCII_Z 0x5A + +#define ASCII_a 0x61 +#define ASCII_b 0x62 +#define ASCII_c 0x63 +#define ASCII_d 0x64 +#define ASCII_e 0x65 +#define ASCII_f 0x66 +#define ASCII_g 0x67 +#define ASCII_h 0x68 +#define ASCII_i 0x69 +#define ASCII_j 0x6A +#define ASCII_k 0x6B +#define ASCII_l 0x6C +#define ASCII_m 0x6D +#define ASCII_n 0x6E +#define ASCII_o 0x6F +#define ASCII_p 0x70 +#define ASCII_q 0x71 +#define ASCII_r 0x72 +#define ASCII_s 0x73 +#define ASCII_t 0x74 +#define ASCII_u 0x75 +#define ASCII_v 0x76 +#define ASCII_w 0x77 +#define ASCII_x 0x78 +#define ASCII_y 0x79 +#define ASCII_z 0x7A + +#define ASCII_0 0x30 +#define ASCII_1 0x31 +#define ASCII_2 0x32 +#define ASCII_3 0x33 +#define ASCII_4 0x34 +#define ASCII_5 0x35 +#define ASCII_6 0x36 +#define ASCII_7 0x37 +#define ASCII_8 0x38 +#define ASCII_9 0x39 + +#define ASCII_TAB 0x09 +#define ASCII_SPACE 0x20 +#define ASCII_EXCL 0x21 +#define ASCII_QUOT 0x22 +#define ASCII_AMP 0x26 +#define ASCII_APOS 0x27 +#define ASCII_MINUS 0x2D +#define ASCII_PERIOD 0x2E +#define ASCII_COLON 0x3A +#define ASCII_SEMI 0x3B +#define ASCII_LT 0x3C +#define ASCII_EQUALS 0x3D +#define ASCII_GT 0x3E +#define ASCII_LSQB 0x5B +#define ASCII_RSQB 0x5D +#define ASCII_UNDERSCORE 0x5F +#define ASCII_LPAREN 0x28 +#define ASCII_RPAREN 0x29 +#define ASCII_FF 0x0C +#define ASCII_SLASH 0x2F +#define ASCII_HASH 0x23 +#define ASCII_PIPE 0x7C +#define ASCII_COMMA 0x2C diff --git a/gpr/source/lib/expat_lib/asciitab.h b/gpr/source/lib/expat_lib/asciitab.h new file mode 100644 index 0000000..79a15c2 --- /dev/null +++ b/gpr/source/lib/expat_lib/asciitab.h @@ -0,0 +1,36 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML, +/* 0x0C */ BT_NONXML, BT_CR, BT_NONXML, BT_NONXML, +/* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM, +/* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS, +/* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS, +/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, +/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, +/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, +/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI, +/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, +/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, +/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, +/* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB, +/* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT, +/* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, +/* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, +/* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, +/* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER, diff --git a/gpr/source/lib/expat_lib/expat.h b/gpr/source/lib/expat_lib/expat.h new file mode 100644 index 0000000..9a21680 --- /dev/null +++ b/gpr/source/lib/expat_lib/expat.h @@ -0,0 +1,1047 @@ +/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#ifndef Expat_INCLUDED +#define Expat_INCLUDED 1 + +#ifdef __VMS +/* 0 1 2 3 0 1 2 3 + 1234567890123456789012345678901 1234567890123456789012345678901 */ +#define XML_SetProcessingInstructionHandler XML_SetProcessingInstrHandler +#define XML_SetUnparsedEntityDeclHandler XML_SetUnparsedEntDeclHandler +#define XML_SetStartNamespaceDeclHandler XML_SetStartNamespcDeclHandler +#define XML_SetExternalEntityRefHandlerArg XML_SetExternalEntRefHandlerArg +#endif + +#include <stdlib.h> +#include "expat_external.h" + +#ifdef __cplusplus +extern "C" { +#endif + +struct XML_ParserStruct; +typedef struct XML_ParserStruct *XML_Parser; + +/* Should this be defined using stdbool.h when C99 is available? */ +typedef unsigned char XML_Bool; +#define XML_TRUE ((XML_Bool) 1) +#define XML_FALSE ((XML_Bool) 0) + +/* The XML_Status enum gives the possible return values for several + API functions. The preprocessor #defines are included so this + stanza can be added to code that still needs to support older + versions of Expat 1.95.x: + + #ifndef XML_STATUS_OK + #define XML_STATUS_OK 1 + #define XML_STATUS_ERROR 0 + #endif + + Otherwise, the #define hackery is quite ugly and would have been + dropped. +*/ +enum XML_Status { + XML_STATUS_ERROR = 0, +#define XML_STATUS_ERROR XML_STATUS_ERROR + XML_STATUS_OK = 1, +#define XML_STATUS_OK XML_STATUS_OK + XML_STATUS_SUSPENDED = 2 +#define XML_STATUS_SUSPENDED XML_STATUS_SUSPENDED +}; + +enum XML_Error { + XML_ERROR_NONE, + XML_ERROR_NO_MEMORY, + XML_ERROR_SYNTAX, + XML_ERROR_NO_ELEMENTS, + XML_ERROR_INVALID_TOKEN, + XML_ERROR_UNCLOSED_TOKEN, + XML_ERROR_PARTIAL_CHAR, + XML_ERROR_TAG_MISMATCH, + XML_ERROR_DUPLICATE_ATTRIBUTE, + XML_ERROR_JUNK_AFTER_DOC_ELEMENT, + XML_ERROR_PARAM_ENTITY_REF, + XML_ERROR_UNDEFINED_ENTITY, + XML_ERROR_RECURSIVE_ENTITY_REF, + XML_ERROR_ASYNC_ENTITY, + XML_ERROR_BAD_CHAR_REF, + XML_ERROR_BINARY_ENTITY_REF, + XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF, + XML_ERROR_MISPLACED_XML_PI, + XML_ERROR_UNKNOWN_ENCODING, + XML_ERROR_INCORRECT_ENCODING, + XML_ERROR_UNCLOSED_CDATA_SECTION, + XML_ERROR_EXTERNAL_ENTITY_HANDLING, + XML_ERROR_NOT_STANDALONE, + XML_ERROR_UNEXPECTED_STATE, + XML_ERROR_ENTITY_DECLARED_IN_PE, + XML_ERROR_FEATURE_REQUIRES_XML_DTD, + XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING, + /* Added in 1.95.7. */ + XML_ERROR_UNBOUND_PREFIX, + /* Added in 1.95.8. */ + XML_ERROR_UNDECLARING_PREFIX, + XML_ERROR_INCOMPLETE_PE, + XML_ERROR_XML_DECL, + XML_ERROR_TEXT_DECL, + XML_ERROR_PUBLICID, + XML_ERROR_SUSPENDED, + XML_ERROR_NOT_SUSPENDED, + XML_ERROR_ABORTED, + XML_ERROR_FINISHED, + XML_ERROR_SUSPEND_PE, + /* Added in 2.0. */ + XML_ERROR_RESERVED_PREFIX_XML, + XML_ERROR_RESERVED_PREFIX_XMLNS, + XML_ERROR_RESERVED_NAMESPACE_URI +}; + +enum XML_Content_Type { + XML_CTYPE_EMPTY = 1, + XML_CTYPE_ANY, + XML_CTYPE_MIXED, + XML_CTYPE_NAME, + XML_CTYPE_CHOICE, + XML_CTYPE_SEQ +}; + +enum XML_Content_Quant { + XML_CQUANT_NONE, + XML_CQUANT_OPT, + XML_CQUANT_REP, + XML_CQUANT_PLUS +}; + +/* If type == XML_CTYPE_EMPTY or XML_CTYPE_ANY, then quant will be + XML_CQUANT_NONE, and the other fields will be zero or NULL. + If type == XML_CTYPE_MIXED, then quant will be NONE or REP and + numchildren will contain number of elements that may be mixed in + and children point to an array of XML_Content cells that will be + all of XML_CTYPE_NAME type with no quantification. + + If type == XML_CTYPE_NAME, then the name points to the name, and + the numchildren field will be zero and children will be NULL. The + quant fields indicates any quantifiers placed on the name. + + CHOICE and SEQ will have name NULL, the number of children in + numchildren and children will point, recursively, to an array + of XML_Content cells. + + The EMPTY, ANY, and MIXED types will only occur at top level. +*/ + +typedef struct XML_cp XML_Content; + +struct XML_cp { + enum XML_Content_Type type; + enum XML_Content_Quant quant; + XML_Char * name; + unsigned int numchildren; + XML_Content * children; +}; + + +/* This is called for an element declaration. See above for + description of the model argument. It's the caller's responsibility + to free model when finished with it. +*/ +typedef void (XMLCALL *XML_ElementDeclHandler) (void *userData, + const XML_Char *name, + XML_Content *model); + +XMLPARSEAPI(void) +XML_SetElementDeclHandler(XML_Parser parser, + XML_ElementDeclHandler eldecl); + +/* The Attlist declaration handler is called for *each* attribute. So + a single Attlist declaration with multiple attributes declared will + generate multiple calls to this handler. The "default" parameter + may be NULL in the case of the "#IMPLIED" or "#REQUIRED" + keyword. The "isrequired" parameter will be true and the default + value will be NULL in the case of "#REQUIRED". If "isrequired" is + true and default is non-NULL, then this is a "#FIXED" default. +*/ +typedef void (XMLCALL *XML_AttlistDeclHandler) ( + void *userData, + const XML_Char *elname, + const XML_Char *attname, + const XML_Char *att_type, + const XML_Char *dflt, + int isrequired); + +XMLPARSEAPI(void) +XML_SetAttlistDeclHandler(XML_Parser parser, + XML_AttlistDeclHandler attdecl); + +/* The XML declaration handler is called for *both* XML declarations + and text declarations. The way to distinguish is that the version + parameter will be NULL for text declarations. The encoding + parameter may be NULL for XML declarations. The standalone + parameter will be -1, 0, or 1 indicating respectively that there + was no standalone parameter in the declaration, that it was given + as no, or that it was given as yes. +*/ +typedef void (XMLCALL *XML_XmlDeclHandler) (void *userData, + const XML_Char *version, + const XML_Char *encoding, + int standalone); + +XMLPARSEAPI(void) +XML_SetXmlDeclHandler(XML_Parser parser, + XML_XmlDeclHandler xmldecl); + + +typedef struct { + void *(*malloc_fcn)(size_t size); + void *(*realloc_fcn)(void *ptr, size_t size); + void (*free_fcn)(void *ptr); +} XML_Memory_Handling_Suite; + +/* Constructs a new parser; encoding is the encoding specified by the + external protocol or NULL if there is none specified. +*/ +XMLPARSEAPI(XML_Parser) +XML_ParserCreate(const XML_Char *encoding); + +/* Constructs a new parser and namespace processor. Element type + names and attribute names that belong to a namespace will be + expanded; unprefixed attribute names are never expanded; unprefixed + element type names are expanded only if there is a default + namespace. The expanded name is the concatenation of the namespace + URI, the namespace separator character, and the local part of the + name. If the namespace separator is '\0' then the namespace URI + and the local part will be concatenated without any separator. + It is a programming error to use the separator '\0' with namespace + triplets (see XML_SetReturnNSTriplet). +*/ +XMLPARSEAPI(XML_Parser) +XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); + + +/* Constructs a new parser using the memory management suite referred to + by memsuite. If memsuite is NULL, then use the standard library memory + suite. If namespaceSeparator is non-NULL it creates a parser with + namespace processing as described above. The character pointed at + will serve as the namespace separator. + + All further memory operations used for the created parser will come from + the given suite. +*/ +XMLPARSEAPI(XML_Parser) +XML_ParserCreate_MM(const XML_Char *encoding, + const XML_Memory_Handling_Suite *memsuite, + const XML_Char *namespaceSeparator); + +/* Prepare a parser object to be re-used. This is particularly + valuable when memory allocation overhead is disproportionatly high, + such as when a large number of small documnents need to be parsed. + All handlers are cleared from the parser, except for the + unknownEncodingHandler. The parser's external state is re-initialized + except for the values of ns and ns_triplets. + + Added in Expat 1.95.3. +*/ +XMLPARSEAPI(XML_Bool) +XML_ParserReset(XML_Parser parser, const XML_Char *encoding); + +/* atts is array of name/value pairs, terminated by 0; + names and values are 0 terminated. +*/ +typedef void (XMLCALL *XML_StartElementHandler) (void *userData, + const XML_Char *name, + const XML_Char **atts); + +typedef void (XMLCALL *XML_EndElementHandler) (void *userData, + const XML_Char *name); + + +/* s is not 0 terminated. */ +typedef void (XMLCALL *XML_CharacterDataHandler) (void *userData, + const XML_Char *s, + int len); + +/* target and data are 0 terminated */ +typedef void (XMLCALL *XML_ProcessingInstructionHandler) ( + void *userData, + const XML_Char *target, + const XML_Char *data); + +/* data is 0 terminated */ +typedef void (XMLCALL *XML_CommentHandler) (void *userData, + const XML_Char *data); + +typedef void (XMLCALL *XML_StartCdataSectionHandler) (void *userData); +typedef void (XMLCALL *XML_EndCdataSectionHandler) (void *userData); + +/* This is called for any characters in the XML document for which + there is no applicable handler. This includes both characters that + are part of markup which is of a kind that is not reported + (comments, markup declarations), or characters that are part of a + construct which could be reported but for which no handler has been + supplied. The characters are passed exactly as they were in the XML + document except that they will be encoded in UTF-8 or UTF-16. + Line boundaries are not normalized. Note that a byte order mark + character is not passed to the default handler. There are no + guarantees about how characters are divided between calls to the + default handler: for example, a comment might be split between + multiple calls. +*/ +typedef void (XMLCALL *XML_DefaultHandler) (void *userData, + const XML_Char *s, + int len); + +/* This is called for the start of the DOCTYPE declaration, before + any DTD or internal subset is parsed. +*/ +typedef void (XMLCALL *XML_StartDoctypeDeclHandler) ( + void *userData, + const XML_Char *doctypeName, + const XML_Char *sysid, + const XML_Char *pubid, + int has_internal_subset); + +/* This is called for the start of the DOCTYPE declaration when the + closing > is encountered, but after processing any external + subset. +*/ +typedef void (XMLCALL *XML_EndDoctypeDeclHandler)(void *userData); + +/* This is called for entity declarations. The is_parameter_entity + argument will be non-zero if the entity is a parameter entity, zero + otherwise. + + For internal entities (<!ENTITY foo "bar">), value will + be non-NULL and systemId, publicID, and notationName will be NULL. + The value string is NOT nul-terminated; the length is provided in + the value_length argument. Since it is legal to have zero-length + values, do not use this argument to test for internal entities. + + For external entities, value will be NULL and systemId will be + non-NULL. The publicId argument will be NULL unless a public + identifier was provided. The notationName argument will have a + non-NULL value only for unparsed entity declarations. + + Note that is_parameter_entity can't be changed to XML_Bool, since + that would break binary compatibility. +*/ +typedef void (XMLCALL *XML_EntityDeclHandler) ( + void *userData, + const XML_Char *entityName, + int is_parameter_entity, + const XML_Char *value, + int value_length, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId, + const XML_Char *notationName); + +XMLPARSEAPI(void) +XML_SetEntityDeclHandler(XML_Parser parser, + XML_EntityDeclHandler handler); + +/* OBSOLETE -- OBSOLETE -- OBSOLETE + This handler has been superceded by the EntityDeclHandler above. + It is provided here for backward compatibility. + + This is called for a declaration of an unparsed (NDATA) entity. + The base argument is whatever was set by XML_SetBase. The + entityName, systemId and notationName arguments will never be + NULL. The other arguments may be. +*/ +typedef void (XMLCALL *XML_UnparsedEntityDeclHandler) ( + void *userData, + const XML_Char *entityName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId, + const XML_Char *notationName); + +/* This is called for a declaration of notation. The base argument is + whatever was set by XML_SetBase. The notationName will never be + NULL. The other arguments can be. +*/ +typedef void (XMLCALL *XML_NotationDeclHandler) ( + void *userData, + const XML_Char *notationName, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); + +/* When namespace processing is enabled, these are called once for + each namespace declaration. The call to the start and end element + handlers occur between the calls to the start and end namespace + declaration handlers. For an xmlns attribute, prefix will be + NULL. For an xmlns="" attribute, uri will be NULL. +*/ +typedef void (XMLCALL *XML_StartNamespaceDeclHandler) ( + void *userData, + const XML_Char *prefix, + const XML_Char *uri); + +typedef void (XMLCALL *XML_EndNamespaceDeclHandler) ( + void *userData, + const XML_Char *prefix); + +/* This is called if the document is not standalone, that is, it has an + external subset or a reference to a parameter entity, but does not + have standalone="yes". If this handler returns XML_STATUS_ERROR, + then processing will not continue, and the parser will return a + XML_ERROR_NOT_STANDALONE error. + If parameter entity parsing is enabled, then in addition to the + conditions above this handler will only be called if the referenced + entity was actually read. +*/ +typedef int (XMLCALL *XML_NotStandaloneHandler) (void *userData); + +/* This is called for a reference to an external parsed general + entity. The referenced entity is not automatically parsed. The + application can parse it immediately or later using + XML_ExternalEntityParserCreate. + + The parser argument is the parser parsing the entity containing the + reference; it can be passed as the parser argument to + XML_ExternalEntityParserCreate. The systemId argument is the + system identifier as specified in the entity declaration; it will + not be NULL. + + The base argument is the system identifier that should be used as + the base for resolving systemId if systemId was relative; this is + set by XML_SetBase; it may be NULL. + + The publicId argument is the public identifier as specified in the + entity declaration, or NULL if none was specified; the whitespace + in the public identifier will have been normalized as required by + the XML spec. + + The context argument specifies the parsing context in the format + expected by the context argument to XML_ExternalEntityParserCreate; + context is valid only until the handler returns, so if the + referenced entity is to be parsed later, it must be copied. + context is NULL only when the entity is a parameter entity. + + The handler should return XML_STATUS_ERROR if processing should not + continue because of a fatal error in the handling of the external + entity. In this case the calling parser will return an + XML_ERROR_EXTERNAL_ENTITY_HANDLING error. + + Note that unlike other handlers the first argument is the parser, + not userData. +*/ +typedef int (XMLCALL *XML_ExternalEntityRefHandler) ( + XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); + +/* This is called in two situations: + 1) An entity reference is encountered for which no declaration + has been read *and* this is not an error. + 2) An internal entity reference is read, but not expanded, because + XML_SetDefaultHandler has been called. + Note: skipped parameter entities in declarations and skipped general + entities in attribute values cannot be reported, because + the event would be out of sync with the reporting of the + declarations or attribute values +*/ +typedef void (XMLCALL *XML_SkippedEntityHandler) ( + void *userData, + const XML_Char *entityName, + int is_parameter_entity); + +/* This structure is filled in by the XML_UnknownEncodingHandler to + provide information to the parser about encodings that are unknown + to the parser. + + The map[b] member gives information about byte sequences whose + first byte is b. + + If map[b] is c where c is >= 0, then b by itself encodes the + Unicode scalar value c. + + If map[b] is -1, then the byte sequence is malformed. + + If map[b] is -n, where n >= 2, then b is the first byte of an + n-byte sequence that encodes a single Unicode scalar value. + + The data member will be passed as the first argument to the convert + function. + + The convert function is used to convert multibyte sequences; s will + point to a n-byte sequence where map[(unsigned char)*s] == -n. The + convert function must return the Unicode scalar value represented + by this byte sequence or -1 if the byte sequence is malformed. + + The convert function may be NULL if the encoding is a single-byte + encoding, that is if map[b] >= -1 for all bytes b. + + When the parser is finished with the encoding, then if release is + not NULL, it will call release passing it the data member; once + release has been called, the convert function will not be called + again. + + Expat places certain restrictions on the encodings that are supported + using this mechanism. + + 1. Every ASCII character that can appear in a well-formed XML document, + other than the characters + + $@\^`{}~ + + must be represented by a single byte, and that byte must be the + same byte that represents that character in ASCII. + + 2. No character may require more than 4 bytes to encode. + + 3. All characters encoded must have Unicode scalar values <= + 0xFFFF, (i.e., characters that would be encoded by surrogates in + UTF-16 are not allowed). Note that this restriction doesn't + apply to the built-in support for UTF-8 and UTF-16. + + 4. No Unicode character may be encoded by more than one distinct + sequence of bytes. +*/ +typedef struct { + int map[256]; + void *data; + int (XMLCALL *convert)(void *data, const char *s); + void (XMLCALL *release)(void *data); +} XML_Encoding; + +/* This is called for an encoding that is unknown to the parser. + + The encodingHandlerData argument is that which was passed as the + second argument to XML_SetUnknownEncodingHandler. + + The name argument gives the name of the encoding as specified in + the encoding declaration. + + If the callback can provide information about the encoding, it must + fill in the XML_Encoding structure, and return XML_STATUS_OK. + Otherwise it must return XML_STATUS_ERROR. + + If info does not describe a suitable encoding, then the parser will + return an XML_UNKNOWN_ENCODING error. +*/ +typedef int (XMLCALL *XML_UnknownEncodingHandler) ( + void *encodingHandlerData, + const XML_Char *name, + XML_Encoding *info); + +XMLPARSEAPI(void) +XML_SetElementHandler(XML_Parser parser, + XML_StartElementHandler start, + XML_EndElementHandler end); + +XMLPARSEAPI(void) +XML_SetStartElementHandler(XML_Parser parser, + XML_StartElementHandler handler); + +XMLPARSEAPI(void) +XML_SetEndElementHandler(XML_Parser parser, + XML_EndElementHandler handler); + +XMLPARSEAPI(void) +XML_SetCharacterDataHandler(XML_Parser parser, + XML_CharacterDataHandler handler); + +XMLPARSEAPI(void) +XML_SetProcessingInstructionHandler(XML_Parser parser, + XML_ProcessingInstructionHandler handler); +XMLPARSEAPI(void) +XML_SetCommentHandler(XML_Parser parser, + XML_CommentHandler handler); + +XMLPARSEAPI(void) +XML_SetCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start, + XML_EndCdataSectionHandler end); + +XMLPARSEAPI(void) +XML_SetStartCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start); + +XMLPARSEAPI(void) +XML_SetEndCdataSectionHandler(XML_Parser parser, + XML_EndCdataSectionHandler end); + +/* This sets the default handler and also inhibits expansion of + internal entities. These entity references will be passed to the + default handler, or to the skipped entity handler, if one is set. +*/ +XMLPARSEAPI(void) +XML_SetDefaultHandler(XML_Parser parser, + XML_DefaultHandler handler); + +/* This sets the default handler but does not inhibit expansion of + internal entities. The entity reference will not be passed to the + default handler. +*/ +XMLPARSEAPI(void) +XML_SetDefaultHandlerExpand(XML_Parser parser, + XML_DefaultHandler handler); + +XMLPARSEAPI(void) +XML_SetDoctypeDeclHandler(XML_Parser parser, + XML_StartDoctypeDeclHandler start, + XML_EndDoctypeDeclHandler end); + +XMLPARSEAPI(void) +XML_SetStartDoctypeDeclHandler(XML_Parser parser, + XML_StartDoctypeDeclHandler start); + +XMLPARSEAPI(void) +XML_SetEndDoctypeDeclHandler(XML_Parser parser, + XML_EndDoctypeDeclHandler end); + +XMLPARSEAPI(void) +XML_SetUnparsedEntityDeclHandler(XML_Parser parser, + XML_UnparsedEntityDeclHandler handler); + +XMLPARSEAPI(void) +XML_SetNotationDeclHandler(XML_Parser parser, + XML_NotationDeclHandler handler); + +XMLPARSEAPI(void) +XML_SetNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start, + XML_EndNamespaceDeclHandler end); + +XMLPARSEAPI(void) +XML_SetStartNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start); + +XMLPARSEAPI(void) +XML_SetEndNamespaceDeclHandler(XML_Parser parser, + XML_EndNamespaceDeclHandler end); + +XMLPARSEAPI(void) +XML_SetNotStandaloneHandler(XML_Parser parser, + XML_NotStandaloneHandler handler); + +XMLPARSEAPI(void) +XML_SetExternalEntityRefHandler(XML_Parser parser, + XML_ExternalEntityRefHandler handler); + +/* If a non-NULL value for arg is specified here, then it will be + passed as the first argument to the external entity ref handler + instead of the parser object. +*/ +XMLPARSEAPI(void) +XML_SetExternalEntityRefHandlerArg(XML_Parser parser, + void *arg); + +XMLPARSEAPI(void) +XML_SetSkippedEntityHandler(XML_Parser parser, + XML_SkippedEntityHandler handler); + +XMLPARSEAPI(void) +XML_SetUnknownEncodingHandler(XML_Parser parser, + XML_UnknownEncodingHandler handler, + void *encodingHandlerData); + +/* This can be called within a handler for a start element, end + element, processing instruction or character data. It causes the + corresponding markup to be passed to the default handler. +*/ +XMLPARSEAPI(void) +XML_DefaultCurrent(XML_Parser parser); + +/* If do_nst is non-zero, and namespace processing is in effect, and + a name has a prefix (i.e. an explicit namespace qualifier) then + that name is returned as a triplet in a single string separated by + the separator character specified when the parser was created: URI + + sep + local_name + sep + prefix. + + If do_nst is zero, then namespace information is returned in the + default manner (URI + sep + local_name) whether or not the name + has a prefix. + + Note: Calling XML_SetReturnNSTriplet after XML_Parse or + XML_ParseBuffer has no effect. +*/ + +XMLPARSEAPI(void) +XML_SetReturnNSTriplet(XML_Parser parser, int do_nst); + +/* This value is passed as the userData argument to callbacks. */ +XMLPARSEAPI(void) +XML_SetUserData(XML_Parser parser, void *userData); + +/* Returns the last value set by XML_SetUserData or NULL. */ +#define XML_GetUserData(parser) (*(void **)(parser)) + +/* This is equivalent to supplying an encoding argument to + XML_ParserCreate. On success XML_SetEncoding returns non-zero, + zero otherwise. + Note: Calling XML_SetEncoding after XML_Parse or XML_ParseBuffer + has no effect and returns XML_STATUS_ERROR. +*/ +XMLPARSEAPI(enum XML_Status) +XML_SetEncoding(XML_Parser parser, const XML_Char *encoding); + +/* If this function is called, then the parser will be passed as the + first argument to callbacks instead of userData. The userData will + still be accessible using XML_GetUserData. +*/ +XMLPARSEAPI(void) +XML_UseParserAsHandlerArg(XML_Parser parser); + +/* If useDTD == XML_TRUE is passed to this function, then the parser + will assume that there is an external subset, even if none is + specified in the document. In such a case the parser will call the + externalEntityRefHandler with a value of NULL for the systemId + argument (the publicId and context arguments will be NULL as well). + Note: For the purpose of checking WFC: Entity Declared, passing + useDTD == XML_TRUE will make the parser behave as if the document + had a DTD with an external subset. + Note: If this function is called, then this must be done before + the first call to XML_Parse or XML_ParseBuffer, since it will + have no effect after that. Returns + XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING. + Note: If the document does not have a DOCTYPE declaration at all, + then startDoctypeDeclHandler and endDoctypeDeclHandler will not + be called, despite an external subset being parsed. + Note: If XML_DTD is not defined when Expat is compiled, returns + XML_ERROR_FEATURE_REQUIRES_XML_DTD. +*/ +XMLPARSEAPI(enum XML_Error) +XML_UseForeignDTD(XML_Parser parser, XML_Bool useDTD); + + +/* Sets the base to be used for resolving relative URIs in system + identifiers in declarations. Resolving relative identifiers is + left to the application: this value will be passed through as the + base argument to the XML_ExternalEntityRefHandler, + XML_NotationDeclHandler and XML_UnparsedEntityDeclHandler. The base + argument will be copied. Returns XML_STATUS_ERROR if out of memory, + XML_STATUS_OK otherwise. +*/ +XMLPARSEAPI(enum XML_Status) +XML_SetBase(XML_Parser parser, const XML_Char *base); + +XMLPARSEAPI(const XML_Char *) +XML_GetBase(XML_Parser parser); + +/* Returns the number of the attribute/value pairs passed in last call + to the XML_StartElementHandler that were specified in the start-tag + rather than defaulted. Each attribute/value pair counts as 2; thus + this correspondds to an index into the atts array passed to the + XML_StartElementHandler. +*/ +XMLPARSEAPI(int) +XML_GetSpecifiedAttributeCount(XML_Parser parser); + +/* Returns the index of the ID attribute passed in the last call to + XML_StartElementHandler, or -1 if there is no ID attribute. Each + attribute/value pair counts as 2; thus this correspondds to an + index into the atts array passed to the XML_StartElementHandler. +*/ +XMLPARSEAPI(int) +XML_GetIdAttributeIndex(XML_Parser parser); + +#ifdef XML_ATTR_INFO +/* Source file byte offsets for the start and end of attribute names and values. + The value indices are exclusive of surrounding quotes; thus in a UTF-8 source + file an attribute value of "blah" will yield: + info->valueEnd - info->valueStart = 4 bytes. +*/ +typedef struct { + XML_Index nameStart; /* Offset to beginning of the attribute name. */ + XML_Index nameEnd; /* Offset after the attribute name's last byte. */ + XML_Index valueStart; /* Offset to beginning of the attribute value. */ + XML_Index valueEnd; /* Offset after the attribute value's last byte. */ +} XML_AttrInfo; + +/* Returns an array of XML_AttrInfo structures for the attribute/value pairs + passed in last call to the XML_StartElementHandler that were specified + in the start-tag rather than defaulted. Each attribute/value pair counts + as 1; thus the number of entries in the array is + XML_GetSpecifiedAttributeCount(parser) / 2. +*/ +XMLPARSEAPI(const XML_AttrInfo *) +XML_GetAttributeInfo(XML_Parser parser); +#endif + +/* Parses some input. Returns XML_STATUS_ERROR if a fatal error is + detected. The last call to XML_Parse must have isFinal true; len + may be zero for this call (or any other). + + Though the return values for these functions has always been + described as a Boolean value, the implementation, at least for the + 1.95.x series, has always returned exactly one of the XML_Status + values. +*/ +XMLPARSEAPI(enum XML_Status) +XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); + +XMLPARSEAPI(void *) +XML_GetBuffer(XML_Parser parser, int len); + +XMLPARSEAPI(enum XML_Status) +XML_ParseBuffer(XML_Parser parser, int len, int isFinal); + +/* Stops parsing, causing XML_Parse() or XML_ParseBuffer() to return. + Must be called from within a call-back handler, except when aborting + (resumable = 0) an already suspended parser. Some call-backs may + still follow because they would otherwise get lost. Examples: + - endElementHandler() for empty elements when stopped in + startElementHandler(), + - endNameSpaceDeclHandler() when stopped in endElementHandler(), + and possibly others. + + Can be called from most handlers, including DTD related call-backs, + except when parsing an external parameter entity and resumable != 0. + Returns XML_STATUS_OK when successful, XML_STATUS_ERROR otherwise. + Possible error codes: + - XML_ERROR_SUSPENDED: when suspending an already suspended parser. + - XML_ERROR_FINISHED: when the parser has already finished. + - XML_ERROR_SUSPEND_PE: when suspending while parsing an external PE. + + When resumable != 0 (true) then parsing is suspended, that is, + XML_Parse() and XML_ParseBuffer() return XML_STATUS_SUSPENDED. + Otherwise, parsing is aborted, that is, XML_Parse() and XML_ParseBuffer() + return XML_STATUS_ERROR with error code XML_ERROR_ABORTED. + + *Note*: + This will be applied to the current parser instance only, that is, if + there is a parent parser then it will continue parsing when the + externalEntityRefHandler() returns. It is up to the implementation of + the externalEntityRefHandler() to call XML_StopParser() on the parent + parser (recursively), if one wants to stop parsing altogether. + + When suspended, parsing can be resumed by calling XML_ResumeParser(). +*/ +XMLPARSEAPI(enum XML_Status) +XML_StopParser(XML_Parser parser, XML_Bool resumable); + +/* Resumes parsing after it has been suspended with XML_StopParser(). + Must not be called from within a handler call-back. Returns same + status codes as XML_Parse() or XML_ParseBuffer(). + Additional error code XML_ERROR_NOT_SUSPENDED possible. + + *Note*: + This must be called on the most deeply nested child parser instance + first, and on its parent parser only after the child parser has finished, + to be applied recursively until the document entity's parser is restarted. + That is, the parent parser will not resume by itself and it is up to the + application to call XML_ResumeParser() on it at the appropriate moment. +*/ +XMLPARSEAPI(enum XML_Status) +XML_ResumeParser(XML_Parser parser); + +enum XML_Parsing { + XML_INITIALIZED, + XML_PARSING, + XML_FINISHED, + XML_SUSPENDED +}; + +typedef struct { + enum XML_Parsing parsing; + XML_Bool finalBuffer; +} XML_ParsingStatus; + +/* Returns status of parser with respect to being initialized, parsing, + finished, or suspended and processing the final buffer. + XXX XML_Parse() and XML_ParseBuffer() should return XML_ParsingStatus, + XXX with XML_FINISHED_OK or XML_FINISHED_ERROR replacing XML_FINISHED +*/ +XMLPARSEAPI(void) +XML_GetParsingStatus(XML_Parser parser, XML_ParsingStatus *status); + +/* Creates an XML_Parser object that can parse an external general + entity; context is a '\0'-terminated string specifying the parse + context; encoding is a '\0'-terminated string giving the name of + the externally specified encoding, or NULL if there is no + externally specified encoding. The context string consists of a + sequence of tokens separated by formfeeds (\f); a token consisting + of a name specifies that the general entity of the name is open; a + token of the form prefix=uri specifies the namespace for a + particular prefix; a token of the form =uri specifies the default + namespace. This can be called at any point after the first call to + an ExternalEntityRefHandler so longer as the parser has not yet + been freed. The new parser is completely independent and may + safely be used in a separate thread. The handlers and userData are + initialized from the parser argument. Returns NULL if out of memory. + Otherwise returns a new XML_Parser object. +*/ +XMLPARSEAPI(XML_Parser) +XML_ExternalEntityParserCreate(XML_Parser parser, + const XML_Char *context, + const XML_Char *encoding); + +enum XML_ParamEntityParsing { + XML_PARAM_ENTITY_PARSING_NEVER, + XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE, + XML_PARAM_ENTITY_PARSING_ALWAYS +}; + +/* Controls parsing of parameter entities (including the external DTD + subset). If parsing of parameter entities is enabled, then + references to external parameter entities (including the external + DTD subset) will be passed to the handler set with + XML_SetExternalEntityRefHandler. The context passed will be 0. + + Unlike external general entities, external parameter entities can + only be parsed synchronously. If the external parameter entity is + to be parsed, it must be parsed during the call to the external + entity ref handler: the complete sequence of + XML_ExternalEntityParserCreate, XML_Parse/XML_ParseBuffer and + XML_ParserFree calls must be made during this call. After + XML_ExternalEntityParserCreate has been called to create the parser + for the external parameter entity (context must be 0 for this + call), it is illegal to make any calls on the old parser until + XML_ParserFree has been called on the newly created parser. + If the library has been compiled without support for parameter + entity parsing (ie without XML_DTD being defined), then + XML_SetParamEntityParsing will return 0 if parsing of parameter + entities is requested; otherwise it will return non-zero. + Note: If XML_SetParamEntityParsing is called after XML_Parse or + XML_ParseBuffer, then it has no effect and will always return 0. +*/ +XMLPARSEAPI(int) +XML_SetParamEntityParsing(XML_Parser parser, + enum XML_ParamEntityParsing parsing); + +/* Sets the hash salt to use for internal hash calculations. + Helps in preventing DoS attacks based on predicting hash + function behavior. This must be called before parsing is started. + Returns 1 if successful, 0 when called after parsing has started. +*/ +XMLPARSEAPI(int) +XML_SetHashSalt(XML_Parser parser, + unsigned long hash_salt); + +/* If XML_Parse or XML_ParseBuffer have returned XML_STATUS_ERROR, then + XML_GetErrorCode returns information about the error. +*/ +XMLPARSEAPI(enum XML_Error) +XML_GetErrorCode(XML_Parser parser); + +/* These functions return information about the current parse + location. They may be called from any callback called to report + some parse event; in this case the location is the location of the + first of the sequence of characters that generated the event. When + called from callbacks generated by declarations in the document + prologue, the location identified isn't as neatly defined, but will + be within the relevant markup. When called outside of the callback + functions, the position indicated will be just past the last parse + event (regardless of whether there was an associated callback). + + They may also be called after returning from a call to XML_Parse + or XML_ParseBuffer. If the return value is XML_STATUS_ERROR then + the location is the location of the character at which the error + was detected; otherwise the location is the location of the last + parse event, as described above. +*/ +XMLPARSEAPI(XML_Size) XML_GetCurrentLineNumber(XML_Parser parser); +XMLPARSEAPI(XML_Size) XML_GetCurrentColumnNumber(XML_Parser parser); +XMLPARSEAPI(XML_Index) XML_GetCurrentByteIndex(XML_Parser parser); + +/* Return the number of bytes in the current event. + Returns 0 if the event is in an internal entity. +*/ +XMLPARSEAPI(int) +XML_GetCurrentByteCount(XML_Parser parser); + +/* If XML_CONTEXT_BYTES is defined, returns the input buffer, sets + the integer pointed to by offset to the offset within this buffer + of the current parse position, and sets the integer pointed to by size + to the size of this buffer (the number of input bytes). Otherwise + returns a NULL pointer. Also returns a NULL pointer if a parse isn't + active. + + NOTE: The character pointer returned should not be used outside + the handler that makes the call. +*/ +XMLPARSEAPI(const char *) +XML_GetInputContext(XML_Parser parser, + int *offset, + int *size); + +/* For backwards compatibility with previous versions. */ +#define XML_GetErrorLineNumber XML_GetCurrentLineNumber +#define XML_GetErrorColumnNumber XML_GetCurrentColumnNumber +#define XML_GetErrorByteIndex XML_GetCurrentByteIndex + +/* Frees the content model passed to the element declaration handler */ +XMLPARSEAPI(void) +XML_FreeContentModel(XML_Parser parser, XML_Content *model); + +/* Exposing the memory handling functions used in Expat */ +XMLPARSEAPI(void *) +XML_MemMalloc(XML_Parser parser, size_t size); + +XMLPARSEAPI(void *) +XML_MemRealloc(XML_Parser parser, void *ptr, size_t size); + +XMLPARSEAPI(void) +XML_MemFree(XML_Parser parser, void *ptr); + +/* Frees memory used by the parser. */ +XMLPARSEAPI(void) +XML_ParserFree(XML_Parser parser); + +/* Returns a string describing the error. */ +XMLPARSEAPI(const XML_LChar *) +XML_ErrorString(enum XML_Error code); + +/* Return a string containing the version number of this expat */ +XMLPARSEAPI(const XML_LChar *) +XML_ExpatVersion(void); + +typedef struct { + int major; + int minor; + int micro; +} XML_Expat_Version; + +/* Return an XML_Expat_Version structure containing numeric version + number information for this version of expat. +*/ +XMLPARSEAPI(XML_Expat_Version) +XML_ExpatVersionInfo(void); + +/* Added in Expat 1.95.5. */ +enum XML_FeatureEnum { + XML_FEATURE_END = 0, + XML_FEATURE_UNICODE, + XML_FEATURE_UNICODE_WCHAR_T, + XML_FEATURE_DTD, + XML_FEATURE_CONTEXT_BYTES, + XML_FEATURE_MIN_SIZE, + XML_FEATURE_SIZEOF_XML_CHAR, + XML_FEATURE_SIZEOF_XML_LCHAR, + XML_FEATURE_NS, + XML_FEATURE_LARGE_SIZE, + XML_FEATURE_ATTR_INFO + /* Additional features must be added to the end of this enum. */ +}; + +typedef struct { + enum XML_FeatureEnum feature; + const XML_LChar *name; + long int value; +} XML_Feature; + +XMLPARSEAPI(const XML_Feature *) +XML_GetFeatureList(void); + + +/* Expat follows the GNU/Linux convention of odd number minor version for + beta/development releases and even number minor version for stable + releases. Micro is bumped with each release, and set to 0 with each + change to major or minor version. +*/ +#define XML_MAJOR_VERSION 2 +#define XML_MINOR_VERSION 1 +#define XML_MICRO_VERSION 0 + +#ifdef __cplusplus +} +#endif + +#endif /* not Expat_INCLUDED */ diff --git a/gpr/source/lib/expat_lib/expat_external.h b/gpr/source/lib/expat_lib/expat_external.h new file mode 100644 index 0000000..2c03284 --- /dev/null +++ b/gpr/source/lib/expat_lib/expat_external.h @@ -0,0 +1,115 @@ +/* Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#ifndef Expat_External_INCLUDED +#define Expat_External_INCLUDED 1 + +/* External API definitions */ + +#if defined(_MSC_EXTENSIONS) && !defined(__BEOS__) && !defined(__CYGWIN__) +#define XML_USE_MSC_EXTENSIONS 1 +#endif + +/* Expat tries very hard to make the API boundary very specifically + defined. There are two macros defined to control this boundary; + each of these can be defined before including this header to + achieve some different behavior, but doing so it not recommended or + tested frequently. + + XMLCALL - The calling convention to use for all calls across the + "library boundary." This will default to cdecl, and + try really hard to tell the compiler that's what we + want. + + XMLIMPORT - Whatever magic is needed to note that a function is + to be imported from a dynamically loaded library + (.dll, .so, or .sl, depending on your platform). + + The XMLCALL macro was added in Expat 1.95.7. The only one which is + expected to be directly useful in client code is XMLCALL. + + Note that on at least some Unix versions, the Expat library must be + compiled with the cdecl calling convention as the default since + system headers may assume the cdecl convention. +*/ +#ifndef XMLCALL +#if defined(_MSC_VER) +#define XMLCALL __cdecl +#elif defined(__GNUC__) && defined(__i386) && !defined(__INTEL_COMPILER) +#define XMLCALL __attribute__((cdecl)) +#else +/* For any platform which uses this definition and supports more than + one calling convention, we need to extend this definition to + declare the convention used on that platform, if it's possible to + do so. + + If this is the case for your platform, please file a bug report + with information on how to identify your platform via the C + pre-processor and how to specify the same calling convention as the + platform's malloc() implementation. +*/ +#define XMLCALL +#endif +#endif /* not defined XMLCALL */ + + +#if !defined(XML_STATIC) && !defined(XMLIMPORT) +#ifndef XML_BUILDING_EXPAT +/* using Expat from an application */ + +#ifdef XML_USE_MSC_EXTENSIONS +#define XMLIMPORT __declspec(dllimport) +#endif + +#endif +#endif /* not defined XML_STATIC */ + + +/* If we didn't define it above, define it away: */ +#ifndef XMLIMPORT +#define XMLIMPORT +#endif + + +#define XMLPARSEAPI(type) XMLIMPORT type XMLCALL + +#ifdef __cplusplus +extern "C" { +#endif + +#ifdef XML_UNICODE_WCHAR_T +#define XML_UNICODE +#endif + +#ifdef XML_UNICODE /* Information is UTF-16 encoded. */ +#ifdef XML_UNICODE_WCHAR_T +typedef wchar_t XML_Char; +typedef wchar_t XML_LChar; +#else +typedef unsigned short XML_Char; +typedef char XML_LChar; +#endif /* XML_UNICODE_WCHAR_T */ +#else /* Information is UTF-8 encoded. */ +typedef char XML_Char; +typedef char XML_LChar; +#endif /* XML_UNICODE */ + +#ifdef XML_LARGE_SIZE /* Use large integers for file/stream positions. */ +#if defined(XML_USE_MSC_EXTENSIONS) && _MSC_VER < 1400 +typedef __int64 XML_Index; +typedef unsigned __int64 XML_Size; +#else +typedef long long XML_Index; +typedef unsigned long long XML_Size; +#endif +#else +typedef long XML_Index; +typedef unsigned long XML_Size; +#endif /* XML_LARGE_SIZE */ + +#ifdef __cplusplus +} +#endif + +#endif /* not Expat_External_INCLUDED */ diff --git a/gpr/source/lib/expat_lib/iasciitab.h b/gpr/source/lib/expat_lib/iasciitab.h new file mode 100644 index 0000000..24a1d5c --- /dev/null +++ b/gpr/source/lib/expat_lib/iasciitab.h @@ -0,0 +1,37 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +/* Like asciitab.h, except that 0xD has code BT_S rather than BT_CR */ +/* 0x00 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x04 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x08 */ BT_NONXML, BT_S, BT_LF, BT_NONXML, +/* 0x0C */ BT_NONXML, BT_S, BT_NONXML, BT_NONXML, +/* 0x10 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x14 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x18 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x1C */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0x20 */ BT_S, BT_EXCL, BT_QUOT, BT_NUM, +/* 0x24 */ BT_OTHER, BT_PERCNT, BT_AMP, BT_APOS, +/* 0x28 */ BT_LPAR, BT_RPAR, BT_AST, BT_PLUS, +/* 0x2C */ BT_COMMA, BT_MINUS, BT_NAME, BT_SOL, +/* 0x30 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, +/* 0x34 */ BT_DIGIT, BT_DIGIT, BT_DIGIT, BT_DIGIT, +/* 0x38 */ BT_DIGIT, BT_DIGIT, BT_COLON, BT_SEMI, +/* 0x3C */ BT_LT, BT_EQUALS, BT_GT, BT_QUEST, +/* 0x40 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, +/* 0x44 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, +/* 0x48 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x4C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x50 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x54 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x58 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_LSQB, +/* 0x5C */ BT_OTHER, BT_RSQB, BT_OTHER, BT_NMSTRT, +/* 0x60 */ BT_OTHER, BT_HEX, BT_HEX, BT_HEX, +/* 0x64 */ BT_HEX, BT_HEX, BT_HEX, BT_NMSTRT, +/* 0x68 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x6C */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x70 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x74 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0x78 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, +/* 0x7C */ BT_VERBAR, BT_OTHER, BT_OTHER, BT_OTHER, diff --git a/gpr/source/lib/expat_lib/internal.h b/gpr/source/lib/expat_lib/internal.h new file mode 100644 index 0000000..9ee06af --- /dev/null +++ b/gpr/source/lib/expat_lib/internal.h @@ -0,0 +1,79 @@ +/* internal.h + + Internal definitions used by Expat. This is not needed to compile + client code. + + The following calling convention macros are defined for frequently + called functions: + + FASTCALL - Used for those internal functions that have a simple + body and a low number of arguments and local variables. + + PTRCALL - Used for functions called though function pointers. + + PTRFASTCALL - Like PTRCALL, but for low number of arguments. + + inline - Used for selected internal functions for which inlining + may improve performance on some platforms. + + Note: Use of these macros is based on judgement, not hard rules, + and therefore subject to change. +*/ + +#if defined(__GNUC__) && defined(__i386__) && !defined(__MINGW32__) +/* We'll use this version by default only where we know it helps. + + regparm() generates warnings on Solaris boxes. See SF bug #692878. + + Instability reported with egcs on a RedHat Linux 7.3. + Let's comment out: + #define FASTCALL __attribute__((stdcall, regparm(3))) + and let's try this: +*/ +#define FASTCALL __attribute__((regparm(3))) +#define PTRFASTCALL __attribute__((regparm(3))) +#endif + +#if defined(__GNUC__) && __GNUC__ >= 7 || defined(__clang__) && __clang_major__ >= 10 +#define FALL_THROUGH __attribute__ ((fallthrough)) +#else +#define FALL_THROUGH ((void)0) +#endif + +/* Using __fastcall seems to have an unexpected negative effect under + MS VC++, especially for function pointers, so we won't use it for + now on that platform. It may be reconsidered for a future release + if it can be made more effective. + Likely reason: __fastcall on Windows is like stdcall, therefore + the compiler cannot perform stack optimizations for call clusters. +*/ + +/* Make sure all of these are defined if they aren't already. */ + +#ifndef FASTCALL +#define FASTCALL +#endif + +#ifndef PTRCALL +#define PTRCALL +#endif + +#ifndef PTRFASTCALL +#define PTRFASTCALL +#endif + +#ifndef XML_MIN_SIZE +#if !defined(__cplusplus) && !defined(inline) +#ifdef __GNUC__ +#define inline __inline +#endif /* __GNUC__ */ +#endif +#endif /* XML_MIN_SIZE */ + +#ifdef __cplusplus +#define inline inline +#else +#ifndef inline +#define inline +#endif +#endif diff --git a/gpr/source/lib/expat_lib/latin1tab.h b/gpr/source/lib/expat_lib/latin1tab.h new file mode 100644 index 0000000..53c25d7 --- /dev/null +++ b/gpr/source/lib/expat_lib/latin1tab.h @@ -0,0 +1,36 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +/* 0x80 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x84 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x88 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x8C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x90 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x94 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x98 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0x9C */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xA0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xA4 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xA8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER, +/* 0xAC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xB0 */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xB4 */ BT_OTHER, BT_NMSTRT, BT_OTHER, BT_NAME, +/* 0xB8 */ BT_OTHER, BT_OTHER, BT_NMSTRT, BT_OTHER, +/* 0xBC */ BT_OTHER, BT_OTHER, BT_OTHER, BT_OTHER, +/* 0xC0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xC4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xC8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xCC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xD0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xD4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, +/* 0xD8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xDC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xE0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xE4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xE8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xEC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xF0 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xF4 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_OTHER, +/* 0xF8 */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, +/* 0xFC */ BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, BT_NMSTRT, diff --git a/gpr/source/lib/expat_lib/macconfig.h b/gpr/source/lib/expat_lib/macconfig.h new file mode 100644 index 0000000..3579cfc --- /dev/null +++ b/gpr/source/lib/expat_lib/macconfig.h @@ -0,0 +1,50 @@ +/*================================================================ +** Copyright 2000, Clark Cooper +** All rights reserved. +** +** This is free software. You are permitted to copy, distribute, or modify +** it under the terms of the MIT/X license (contained in the COPYING file +** with this distribution.) +** +*/ + +#ifndef MACCONFIG_H +#define MACCONFIG_H + + +/* 1234 = LIL_ENDIAN, 4321 = BIGENDIAN */ +#define BYTEORDER 4321 + +/* Define to 1 if you have the `bcopy' function. */ +#undef HAVE_BCOPY + +/* Define to 1 if you have a working `mmap' system call. */ +#undef HAVE_MMAP + +/* Define to 1 if you have the <unistd.h> header file. */ +#undef HAVE_UNISTD_H + +/* whether byteorder is bigendian */ +#define WORDS_BIGENDIAN + +/* Define to specify how much context to retain around the current parse + point. */ +#undef XML_CONTEXT_BYTES + +/* Define to make parameter entity parsing functionality available. */ +#define XML_DTD + +/* Define to make XML Namespaces functionality available. */ +#define XML_NS + +/* Define to empty if `const' does not conform to ANSI C. */ +#undef const + +/* Define to `long' if <sys/types.h> does not define. */ +#define off_t long + +/* Define to `unsigned' if <sys/types.h> does not define. */ +#undef size_t + + +#endif /* ifndef MACCONFIG_H */ diff --git a/gpr/source/lib/expat_lib/nametab.h b/gpr/source/lib/expat_lib/nametab.h new file mode 100644 index 0000000..b05e62c --- /dev/null +++ b/gpr/source/lib/expat_lib/nametab.h @@ -0,0 +1,150 @@ +static const unsigned namingBitmap[] = { +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +0x00000000, 0x04000000, 0x87FFFFFE, 0x07FFFFFE, +0x00000000, 0x00000000, 0xFF7FFFFF, 0xFF7FFFFF, +0xFFFFFFFF, 0x7FF3FFFF, 0xFFFFFDFE, 0x7FFFFFFF, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFE00F, 0xFC31FFFF, +0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF, +0xFFFFFFFF, 0xF80001FF, 0x00000003, 0x00000000, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0xFFFFD740, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD, +0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, +0xFFFF0003, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF, +0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE, +0x0000007F, 0x00000000, 0xFFFF0000, 0x000707FF, +0x00000000, 0x07FFFFFE, 0x000007FE, 0xFFFE0000, +0xFFFFFFFF, 0x7CFFFFFF, 0x002F7FFF, 0x00000060, +0xFFFFFFE0, 0x23FFFFFF, 0xFF000000, 0x00000003, +0xFFF99FE0, 0x03C5FDFF, 0xB0000000, 0x00030003, +0xFFF987E0, 0x036DFDFF, 0x5E000000, 0x001C0000, +0xFFFBAFE0, 0x23EDFDFF, 0x00000000, 0x00000001, +0xFFF99FE0, 0x23CDFDFF, 0xB0000000, 0x00000003, +0xD63DC7E0, 0x03BFC718, 0x00000000, 0x00000000, +0xFFFDDFE0, 0x03EFFDFF, 0x00000000, 0x00000003, +0xFFFDDFE0, 0x03EFFDFF, 0x40000000, 0x00000003, +0xFFFDDFE0, 0x03FFFDFF, 0x00000000, 0x00000003, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0xFFFFFFFE, 0x000D7FFF, 0x0000003F, 0x00000000, +0xFEF02596, 0x200D6CAE, 0x0000001F, 0x00000000, +0x00000000, 0x00000000, 0xFFFFFEFF, 0x000003FF, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0x00000000, 0xFFFFFFFF, 0xFFFF003F, 0x007FFFFF, +0x0007DAED, 0x50000000, 0x82315001, 0x002C62AB, +0x40000000, 0xF580C900, 0x00000007, 0x02010800, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +0x0FFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0x03FFFFFF, +0x3F3FFFFF, 0xFFFFFFFF, 0xAAFF3F3F, 0x3FFFFFFF, +0xFFFFFFFF, 0x5FDFFFFF, 0x0FCF1FDC, 0x1FDC1FFF, +0x00000000, 0x00004C40, 0x00000000, 0x00000000, +0x00000007, 0x00000000, 0x00000000, 0x00000000, +0x00000080, 0x000003FE, 0xFFFFFFFE, 0xFFFFFFFF, +0x001FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x07FFFFFF, +0xFFFFFFE0, 0x00001FFF, 0x00000000, 0x00000000, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +0xFFFFFFFF, 0x0000003F, 0x00000000, 0x00000000, +0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, +0xFFFFFFFF, 0x0000000F, 0x00000000, 0x00000000, +0x00000000, 0x07FF6000, 0x87FFFFFE, 0x07FFFFFE, +0x00000000, 0x00800000, 0xFF7FFFFF, 0xFF7FFFFF, +0x00FFFFFF, 0x00000000, 0xFFFF0000, 0xFFFFFFFF, +0xFFFFFFFF, 0xF80001FF, 0x00030003, 0x00000000, +0xFFFFFFFF, 0xFFFFFFFF, 0x0000003F, 0x00000003, +0xFFFFD7C0, 0xFFFFFFFB, 0x547F7FFF, 0x000FFFFD, +0xFFFFDFFE, 0xFFFFFFFF, 0xDFFEFFFF, 0xFFFFFFFF, +0xFFFF007B, 0xFFFFFFFF, 0xFFFF199F, 0x033FCFFF, +0x00000000, 0xFFFE0000, 0x027FFFFF, 0xFFFFFFFE, +0xFFFE007F, 0xBBFFFFFB, 0xFFFF0016, 0x000707FF, +0x00000000, 0x07FFFFFE, 0x0007FFFF, 0xFFFF03FF, +0xFFFFFFFF, 0x7CFFFFFF, 0xFFEF7FFF, 0x03FF3DFF, +0xFFFFFFEE, 0xF3FFFFFF, 0xFF1E3FFF, 0x0000FFCF, +0xFFF99FEE, 0xD3C5FDFF, 0xB080399F, 0x0003FFCF, +0xFFF987E4, 0xD36DFDFF, 0x5E003987, 0x001FFFC0, +0xFFFBAFEE, 0xF3EDFDFF, 0x00003BBF, 0x0000FFC1, +0xFFF99FEE, 0xF3CDFDFF, 0xB0C0398F, 0x0000FFC3, +0xD63DC7EC, 0xC3BFC718, 0x00803DC7, 0x0000FF80, +0xFFFDDFEE, 0xC3EFFDFF, 0x00603DDF, 0x0000FFC3, +0xFFFDDFEC, 0xC3EFFDFF, 0x40603DDF, 0x0000FFC3, +0xFFFDDFEC, 0xC3FFFDFF, 0x00803DCF, 0x0000FFC3, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0xFFFFFFFE, 0x07FF7FFF, 0x03FF7FFF, 0x00000000, +0xFEF02596, 0x3BFF6CAE, 0x03FF3F5F, 0x00000000, +0x03000000, 0xC2A003FF, 0xFFFFFEFF, 0xFFFE03FF, +0xFEBF0FDF, 0x02FE3FFF, 0x00000000, 0x00000000, +0x00000000, 0x00000000, 0x00000000, 0x00000000, +0x00000000, 0x00000000, 0x1FFF0000, 0x00000002, +0x000000A0, 0x003EFFFE, 0xFFFFFFFE, 0xFFFFFFFF, +0x661FFFFF, 0xFFFFFFFE, 0xFFFFFFFF, 0x77FFFFFF, +}; +static const unsigned char nmstrtPages[] = { +0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x00, +0x00, 0x09, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, +0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, +0x00, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x15, 0x16, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x17, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; +static const unsigned char namePages[] = { +0x19, 0x03, 0x1A, 0x1B, 0x1C, 0x1D, 0x1E, 0x00, +0x00, 0x1F, 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, +0x10, 0x11, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x12, 0x13, +0x26, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x27, 0x16, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x17, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, +0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x18, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, +}; diff --git a/gpr/source/lib/expat_lib/utf8tab.h b/gpr/source/lib/expat_lib/utf8tab.h new file mode 100644 index 0000000..7bb3e77 --- /dev/null +++ b/gpr/source/lib/expat_lib/utf8tab.h @@ -0,0 +1,37 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + + +/* 0x80 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x84 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x88 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x8C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x90 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x94 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x98 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0x9C */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xA0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xA4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xA8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xAC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xB0 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xB4 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xB8 */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xBC */ BT_TRAIL, BT_TRAIL, BT_TRAIL, BT_TRAIL, +/* 0xC0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xC4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xC8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xCC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xD0 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xD4 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xD8 */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xDC */ BT_LEAD2, BT_LEAD2, BT_LEAD2, BT_LEAD2, +/* 0xE0 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, +/* 0xE4 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, +/* 0xE8 */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, +/* 0xEC */ BT_LEAD3, BT_LEAD3, BT_LEAD3, BT_LEAD3, +/* 0xF0 */ BT_LEAD4, BT_LEAD4, BT_LEAD4, BT_LEAD4, +/* 0xF4 */ BT_LEAD4, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0xF8 */ BT_NONXML, BT_NONXML, BT_NONXML, BT_NONXML, +/* 0xFC */ BT_NONXML, BT_NONXML, BT_MALFORM, BT_MALFORM, diff --git a/gpr/source/lib/expat_lib/winconfig.h b/gpr/source/lib/expat_lib/winconfig.h new file mode 100644 index 0000000..c4e2646 --- /dev/null +++ b/gpr/source/lib/expat_lib/winconfig.h @@ -0,0 +1,27 @@ +/*================================================================ +** Copyright 2000, Clark Cooper +** All rights reserved. +** +** This is free software. You are permitted to copy, distribute, or modify +** it under the terms of the MIT/X license (contained in the COPYING file +** with this distribution.) +*/ + +#ifndef WINCONFIG_H +#define WINCONFIG_H + +#define WIN32_LEAN_AND_MEAN +#include <windows.h> +#undef WIN32_LEAN_AND_MEAN + +#include <memory.h> +#include <string.h> + +#define XML_NS 1 +#define XML_DTD 1 +#define XML_CONTEXT_BYTES 1024 + +/* we will assume all Windows platforms are little endian */ +#define BYTEORDER 1234 + +#endif /* ndef WINCONFIG_H */ diff --git a/gpr/source/lib/expat_lib/xmlparse.c b/gpr/source/lib/expat_lib/xmlparse.c new file mode 120000 index 0000000..0c018b0 --- /dev/null +++ b/gpr/source/lib/expat_lib/xmlparse.c @@ -0,0 +1 @@ +../../../../.git/annex/objects/4Z/7Q/SHA256E-s197456--49037b9f6b0e160aa4b2a73bfa43f4b2ba3aec69617db904fe3b5e34b7aa644c.c/SHA256E-s197456--49037b9f6b0e160aa4b2a73bfa43f4b2ba3aec69617db904fe3b5e34b7aa644c.c
\ No newline at end of file diff --git a/gpr/source/lib/expat_lib/xmlrole.c b/gpr/source/lib/expat_lib/xmlrole.c new file mode 100644 index 0000000..44772e2 --- /dev/null +++ b/gpr/source/lib/expat_lib/xmlrole.c @@ -0,0 +1,1336 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include <stddef.h> + +#ifdef COMPILED_FROM_DSP +#include "winconfig.h" +#elif defined(MACOS_CLASSIC) +#include "macconfig.h" +#elif defined(__amigaos__) +#include "amigaconfig.h" +#elif defined(__WATCOMC__) +#include "watcomconfig.h" +#else +#ifdef HAVE_EXPAT_CONFIG_H +#include <expat_config.h> +#endif +#endif /* ndef COMPILED_FROM_DSP */ + +#include "expat_external.h" +#include "internal.h" +#include "xmlrole.h" +#include "ascii.h" + +/* Doesn't check: + + that ,| are not mixed in a model group + content of literals + +*/ + +static const char KW_ANY[] = { + ASCII_A, ASCII_N, ASCII_Y, '\0' }; +static const char KW_ATTLIST[] = { + ASCII_A, ASCII_T, ASCII_T, ASCII_L, ASCII_I, ASCII_S, ASCII_T, '\0' }; +static const char KW_CDATA[] = { + ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; +static const char KW_DOCTYPE[] = { + ASCII_D, ASCII_O, ASCII_C, ASCII_T, ASCII_Y, ASCII_P, ASCII_E, '\0' }; +static const char KW_ELEMENT[] = { + ASCII_E, ASCII_L, ASCII_E, ASCII_M, ASCII_E, ASCII_N, ASCII_T, '\0' }; +static const char KW_EMPTY[] = { + ASCII_E, ASCII_M, ASCII_P, ASCII_T, ASCII_Y, '\0' }; +static const char KW_ENTITIES[] = { + ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_I, ASCII_E, ASCII_S, + '\0' }; +static const char KW_ENTITY[] = { + ASCII_E, ASCII_N, ASCII_T, ASCII_I, ASCII_T, ASCII_Y, '\0' }; +static const char KW_FIXED[] = { + ASCII_F, ASCII_I, ASCII_X, ASCII_E, ASCII_D, '\0' }; +static const char KW_ID[] = { + ASCII_I, ASCII_D, '\0' }; +static const char KW_IDREF[] = { + ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, '\0' }; +static const char KW_IDREFS[] = { + ASCII_I, ASCII_D, ASCII_R, ASCII_E, ASCII_F, ASCII_S, '\0' }; +#ifdef XML_DTD +static const char KW_IGNORE[] = { + ASCII_I, ASCII_G, ASCII_N, ASCII_O, ASCII_R, ASCII_E, '\0' }; +#endif +static const char KW_IMPLIED[] = { + ASCII_I, ASCII_M, ASCII_P, ASCII_L, ASCII_I, ASCII_E, ASCII_D, '\0' }; +#ifdef XML_DTD +static const char KW_INCLUDE[] = { + ASCII_I, ASCII_N, ASCII_C, ASCII_L, ASCII_U, ASCII_D, ASCII_E, '\0' }; +#endif +static const char KW_NDATA[] = { + ASCII_N, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; +static const char KW_NMTOKEN[] = { + ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, '\0' }; +static const char KW_NMTOKENS[] = { + ASCII_N, ASCII_M, ASCII_T, ASCII_O, ASCII_K, ASCII_E, ASCII_N, ASCII_S, + '\0' }; +static const char KW_NOTATION[] = + { ASCII_N, ASCII_O, ASCII_T, ASCII_A, ASCII_T, ASCII_I, ASCII_O, ASCII_N, + '\0' }; +static const char KW_PCDATA[] = { + ASCII_P, ASCII_C, ASCII_D, ASCII_A, ASCII_T, ASCII_A, '\0' }; +static const char KW_PUBLIC[] = { + ASCII_P, ASCII_U, ASCII_B, ASCII_L, ASCII_I, ASCII_C, '\0' }; +static const char KW_REQUIRED[] = { + ASCII_R, ASCII_E, ASCII_Q, ASCII_U, ASCII_I, ASCII_R, ASCII_E, ASCII_D, + '\0' }; +static const char KW_SYSTEM[] = { + ASCII_S, ASCII_Y, ASCII_S, ASCII_T, ASCII_E, ASCII_M, '\0' }; + +#ifndef MIN_BYTES_PER_CHAR +#define MIN_BYTES_PER_CHAR(enc) ((enc)->minBytesPerChar) +#endif + +#ifdef XML_DTD +#define setTopLevel(state) \ + ((state)->handler = ((state)->documentEntity \ + ? internalSubset \ + : externalSubset1)) +#else /* not XML_DTD */ +#define setTopLevel(state) ((state)->handler = internalSubset) +#endif /* not XML_DTD */ + +typedef int PTRCALL PROLOG_HANDLER(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc); + +static PROLOG_HANDLER + prolog0, prolog1, prolog2, + doctype0, doctype1, doctype2, doctype3, doctype4, doctype5, + internalSubset, + entity0, entity1, entity2, entity3, entity4, entity5, entity6, + entity7, entity8, entity9, entity10, + notation0, notation1, notation2, notation3, notation4, + attlist0, attlist1, attlist2, attlist3, attlist4, attlist5, attlist6, + attlist7, attlist8, attlist9, + element0, element1, element2, element3, element4, element5, element6, + element7, +#ifdef XML_DTD + externalSubset0, externalSubset1, + condSect0, condSect1, condSect2, +#endif /* XML_DTD */ + declClose, + error; + +static int FASTCALL common(PROLOG_STATE *state, int tok); + +static int PTRCALL +prolog0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + state->handler = prolog1; + return XML_ROLE_NONE; + case XML_TOK_XML_DECL: + state->handler = prolog1; + return XML_ROLE_XML_DECL; + case XML_TOK_PI: + state->handler = prolog1; + return XML_ROLE_PI; + case XML_TOK_COMMENT: + state->handler = prolog1; + return XML_ROLE_COMMENT; + case XML_TOK_BOM: + return XML_ROLE_NONE; + case XML_TOK_DECL_OPEN: + if (!XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_DOCTYPE)) + break; + state->handler = doctype0; + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static int PTRCALL +prolog1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_PI: + return XML_ROLE_PI; + case XML_TOK_COMMENT: + return XML_ROLE_COMMENT; + case XML_TOK_BOM: + return XML_ROLE_NONE; + case XML_TOK_DECL_OPEN: + if (!XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_DOCTYPE)) + break; + state->handler = doctype0; + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static int PTRCALL +prolog2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_PI: + return XML_ROLE_PI; + case XML_TOK_COMMENT: + return XML_ROLE_COMMENT; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static int PTRCALL +doctype0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = doctype1; + return XML_ROLE_DOCTYPE_NAME; + } + return common(state, tok); +} + +static int PTRCALL +doctype1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = internalSubset; + return XML_ROLE_DOCTYPE_INTERNAL_SUBSET; + case XML_TOK_DECL_CLOSE: + state->handler = prolog2; + return XML_ROLE_DOCTYPE_CLOSE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = doctype3; + return XML_ROLE_DOCTYPE_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = doctype2; + return XML_ROLE_DOCTYPE_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +doctype2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_LITERAL: + state->handler = doctype3; + return XML_ROLE_DOCTYPE_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +doctype3(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_LITERAL: + state->handler = doctype4; + return XML_ROLE_DOCTYPE_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +doctype4(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = internalSubset; + return XML_ROLE_DOCTYPE_INTERNAL_SUBSET; + case XML_TOK_DECL_CLOSE: + state->handler = prolog2; + return XML_ROLE_DOCTYPE_CLOSE; + } + return common(state, tok); +} + +static int PTRCALL +doctype5(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_DECL_CLOSE: + state->handler = prolog2; + return XML_ROLE_DOCTYPE_CLOSE; + } + return common(state, tok); +} + +static int PTRCALL +internalSubset(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_DECL_OPEN: + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_ENTITY)) { + state->handler = entity0; + return XML_ROLE_ENTITY_NONE; + } + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_ATTLIST)) { + state->handler = attlist0; + return XML_ROLE_ATTLIST_NONE; + } + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_ELEMENT)) { + state->handler = element0; + return XML_ROLE_ELEMENT_NONE; + } + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_NOTATION)) { + state->handler = notation0; + return XML_ROLE_NOTATION_NONE; + } + break; + case XML_TOK_PI: + return XML_ROLE_PI; + case XML_TOK_COMMENT: + return XML_ROLE_COMMENT; + case XML_TOK_PARAM_ENTITY_REF: + return XML_ROLE_PARAM_ENTITY_REF; + case XML_TOK_CLOSE_BRACKET: + state->handler = doctype5; + return XML_ROLE_DOCTYPE_NONE; + case XML_TOK_NONE: + return XML_ROLE_NONE; + } + return common(state, tok); +} + +#ifdef XML_DTD + +static int PTRCALL +externalSubset0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + state->handler = externalSubset1; + if (tok == XML_TOK_XML_DECL) + return XML_ROLE_TEXT_DECL; + return externalSubset1(state, tok, ptr, end, enc); +} + +static int PTRCALL +externalSubset1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_COND_SECT_OPEN: + state->handler = condSect0; + return XML_ROLE_NONE; + case XML_TOK_COND_SECT_CLOSE: + if (state->includeLevel == 0) + break; + state->includeLevel -= 1; + return XML_ROLE_NONE; + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_CLOSE_BRACKET: + break; + case XML_TOK_NONE: + if (state->includeLevel) + break; + return XML_ROLE_NONE; + default: + return internalSubset(state, tok, ptr, end, enc); + } + return common(state, tok); +} + +#endif /* XML_DTD */ + +static int PTRCALL +entity0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_PERCENT: + state->handler = entity1; + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + state->handler = entity2; + return XML_ROLE_GENERAL_ENTITY_NAME; + } + return common(state, tok); +} + +static int PTRCALL +entity1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + state->handler = entity7; + return XML_ROLE_PARAM_ENTITY_NAME; + } + return common(state, tok); +} + +static int PTRCALL +entity2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = entity4; + return XML_ROLE_ENTITY_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = entity3; + return XML_ROLE_ENTITY_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_ENTITY_NONE; + return XML_ROLE_ENTITY_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +entity3(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity4; + return XML_ROLE_ENTITY_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity4(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity5; + return XML_ROLE_ENTITY_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity5(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_ENTITY_COMPLETE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_NDATA)) { + state->handler = entity6; + return XML_ROLE_ENTITY_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +entity6(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + state->handler = declClose; + state->role_none = XML_ROLE_ENTITY_NONE; + return XML_ROLE_ENTITY_NOTATION_NAME; + } + return common(state, tok); +} + +static int PTRCALL +entity7(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = entity9; + return XML_ROLE_ENTITY_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = entity8; + return XML_ROLE_ENTITY_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_ENTITY_NONE; + return XML_ROLE_ENTITY_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +entity8(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity9; + return XML_ROLE_ENTITY_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity9(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_LITERAL: + state->handler = entity10; + return XML_ROLE_ENTITY_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +entity10(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ENTITY_NONE; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_ENTITY_COMPLETE; + } + return common(state, tok); +} + +static int PTRCALL +notation0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_NAME: + state->handler = notation1; + return XML_ROLE_NOTATION_NAME; + } + return common(state, tok); +} + +static int PTRCALL +notation1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = notation3; + return XML_ROLE_NOTATION_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = notation2; + return XML_ROLE_NOTATION_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +notation2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_LITERAL: + state->handler = notation4; + return XML_ROLE_NOTATION_PUBLIC_ID; + } + return common(state, tok); +} + +static int PTRCALL +notation3(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_NOTATION_NONE; + return XML_ROLE_NOTATION_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +notation4(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NOTATION_NONE; + case XML_TOK_LITERAL: + state->handler = declClose; + state->role_none = XML_ROLE_NOTATION_NONE; + return XML_ROLE_NOTATION_SYSTEM_ID; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_NOTATION_NO_SYSTEM_ID; + } + return common(state, tok); +} + +static int PTRCALL +attlist0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = attlist1; + return XML_ROLE_ATTLIST_ELEMENT_NAME; + } + return common(state, tok); +} + +static int PTRCALL +attlist1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = attlist2; + return XML_ROLE_ATTRIBUTE_NAME; + } + return common(state, tok); +} + +static int PTRCALL +attlist2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + { + static const char * const types[] = { + KW_CDATA, + KW_ID, + KW_IDREF, + KW_IDREFS, + KW_ENTITY, + KW_ENTITIES, + KW_NMTOKEN, + KW_NMTOKENS, + }; + int i; + for (i = 0; i < (int)(sizeof(types)/sizeof(types[0])); i++) + if (XmlNameMatchesAscii(enc, ptr, end, types[i])) { + state->handler = attlist8; + return XML_ROLE_ATTRIBUTE_TYPE_CDATA + i; + } + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_NOTATION)) { + state->handler = attlist5; + return XML_ROLE_ATTLIST_NONE; + } + break; + case XML_TOK_OPEN_PAREN: + state->handler = attlist3; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +static int PTRCALL +attlist3(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NMTOKEN: + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = attlist4; + return XML_ROLE_ATTRIBUTE_ENUM_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +attlist4(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = attlist8; + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_OR: + state->handler = attlist3; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +static int PTRCALL +attlist5(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_OPEN_PAREN: + state->handler = attlist6; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +static int PTRCALL +attlist6(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_NAME: + state->handler = attlist7; + return XML_ROLE_ATTRIBUTE_NOTATION_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +attlist7(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = attlist8; + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_OR: + state->handler = attlist6; + return XML_ROLE_ATTLIST_NONE; + } + return common(state, tok); +} + +/* default value */ +static int PTRCALL +attlist8(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_POUND_NAME: + if (XmlNameMatchesAscii(enc, + ptr + MIN_BYTES_PER_CHAR(enc), + end, + KW_IMPLIED)) { + state->handler = attlist1; + return XML_ROLE_IMPLIED_ATTRIBUTE_VALUE; + } + if (XmlNameMatchesAscii(enc, + ptr + MIN_BYTES_PER_CHAR(enc), + end, + KW_REQUIRED)) { + state->handler = attlist1; + return XML_ROLE_REQUIRED_ATTRIBUTE_VALUE; + } + if (XmlNameMatchesAscii(enc, + ptr + MIN_BYTES_PER_CHAR(enc), + end, + KW_FIXED)) { + state->handler = attlist9; + return XML_ROLE_ATTLIST_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = attlist1; + return XML_ROLE_DEFAULT_ATTRIBUTE_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +attlist9(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ATTLIST_NONE; + case XML_TOK_LITERAL: + state->handler = attlist1; + return XML_ROLE_FIXED_ATTRIBUTE_VALUE; + } + return common(state, tok); +} + +static int PTRCALL +element0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element1; + return XML_ROLE_ELEMENT_NAME; + } + return common(state, tok); +} + +static int PTRCALL +element1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_EMPTY)) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_CONTENT_EMPTY; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_ANY)) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_CONTENT_ANY; + } + break; + case XML_TOK_OPEN_PAREN: + state->handler = element2; + state->level = 1; + return XML_ROLE_GROUP_OPEN; + } + return common(state, tok); +} + +static int PTRCALL +element2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_POUND_NAME: + if (XmlNameMatchesAscii(enc, + ptr + MIN_BYTES_PER_CHAR(enc), + end, + KW_PCDATA)) { + state->handler = element3; + return XML_ROLE_CONTENT_PCDATA; + } + break; + case XML_TOK_OPEN_PAREN: + state->level = 2; + state->handler = element6; + return XML_ROLE_GROUP_OPEN; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT; + case XML_TOK_NAME_QUESTION: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_OPT; + case XML_TOK_NAME_ASTERISK: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_REP; + case XML_TOK_NAME_PLUS: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_PLUS; + } + return common(state, tok); +} + +static int PTRCALL +element3(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_GROUP_CLOSE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_OR: + state->handler = element4; + return XML_ROLE_ELEMENT_NONE; + } + return common(state, tok); +} + +static int PTRCALL +element4(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element5; + return XML_ROLE_CONTENT_ELEMENT; + } + return common(state, tok); +} + +static int PTRCALL +element5(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_OR: + state->handler = element4; + return XML_ROLE_ELEMENT_NONE; + } + return common(state, tok); +} + +static int PTRCALL +element6(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_OPEN_PAREN: + state->level += 1; + return XML_ROLE_GROUP_OPEN; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT; + case XML_TOK_NAME_QUESTION: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_OPT; + case XML_TOK_NAME_ASTERISK: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_REP; + case XML_TOK_NAME_PLUS: + state->handler = element7; + return XML_ROLE_CONTENT_ELEMENT_PLUS; + } + return common(state, tok); +} + +static int PTRCALL +element7(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_ELEMENT_NONE; + case XML_TOK_CLOSE_PAREN: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_CLOSE_PAREN_QUESTION: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE_OPT; + case XML_TOK_CLOSE_PAREN_PLUS: + state->level -= 1; + if (state->level == 0) { + state->handler = declClose; + state->role_none = XML_ROLE_ELEMENT_NONE; + } + return XML_ROLE_GROUP_CLOSE_PLUS; + case XML_TOK_COMMA: + state->handler = element6; + return XML_ROLE_GROUP_SEQUENCE; + case XML_TOK_OR: + state->handler = element6; + return XML_ROLE_GROUP_CHOICE; + } + return common(state, tok); +} + +#ifdef XML_DTD + +static int PTRCALL +condSect0(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_INCLUDE)) { + state->handler = condSect1; + return XML_ROLE_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_IGNORE)) { + state->handler = condSect2; + return XML_ROLE_NONE; + } + break; + } + return common(state, tok); +} + +static int PTRCALL +condSect1(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = externalSubset1; + state->includeLevel += 1; + return XML_ROLE_NONE; + } + return common(state, tok); +} + +static int PTRCALL +condSect2(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return XML_ROLE_NONE; + case XML_TOK_OPEN_BRACKET: + state->handler = externalSubset1; + return XML_ROLE_IGNORE_SECT; + } + return common(state, tok); +} + +#endif /* XML_DTD */ + +static int PTRCALL +declClose(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_PROLOG_S: + return state->role_none; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return state->role_none; + } + return common(state, tok); +} + +static int PTRCALL +error(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + return XML_ROLE_NONE; +} + +static int FASTCALL +common(PROLOG_STATE *state, int tok) +{ +#ifdef XML_DTD + if (!state->documentEntity && tok == XML_TOK_PARAM_ENTITY_REF) + return XML_ROLE_INNER_PARAM_ENTITY_REF; +#endif + state->handler = error; + return XML_ROLE_ERROR; +} + +void +XmlPrologStateInit(PROLOG_STATE *state) +{ + state->handler = prolog0; +#ifdef XML_DTD + state->documentEntity = 1; + state->includeLevel = 0; + state->inEntityValue = 0; +#endif /* XML_DTD */ +} + +#ifdef XML_DTD + +void +XmlPrologStateInitExternalEntity(PROLOG_STATE *state) +{ + state->handler = externalSubset0; + state->documentEntity = 0; + state->includeLevel = 0; +} + +#endif /* XML_DTD */ diff --git a/gpr/source/lib/expat_lib/xmlrole.h b/gpr/source/lib/expat_lib/xmlrole.h new file mode 100644 index 0000000..4dd9f06 --- /dev/null +++ b/gpr/source/lib/expat_lib/xmlrole.h @@ -0,0 +1,114 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#ifndef XmlRole_INCLUDED +#define XmlRole_INCLUDED 1 + +#ifdef __VMS +/* 0 1 2 3 0 1 2 3 + 1234567890123456789012345678901 1234567890123456789012345678901 */ +#define XmlPrologStateInitExternalEntity XmlPrologStateInitExternalEnt +#endif + +#include "xmltok.h" + +#ifdef __cplusplus +extern "C" { +#endif + +enum { + XML_ROLE_ERROR = -1, + XML_ROLE_NONE = 0, + XML_ROLE_XML_DECL, + XML_ROLE_INSTANCE_START, + XML_ROLE_DOCTYPE_NONE, + XML_ROLE_DOCTYPE_NAME, + XML_ROLE_DOCTYPE_SYSTEM_ID, + XML_ROLE_DOCTYPE_PUBLIC_ID, + XML_ROLE_DOCTYPE_INTERNAL_SUBSET, + XML_ROLE_DOCTYPE_CLOSE, + XML_ROLE_GENERAL_ENTITY_NAME, + XML_ROLE_PARAM_ENTITY_NAME, + XML_ROLE_ENTITY_NONE, + XML_ROLE_ENTITY_VALUE, + XML_ROLE_ENTITY_SYSTEM_ID, + XML_ROLE_ENTITY_PUBLIC_ID, + XML_ROLE_ENTITY_COMPLETE, + XML_ROLE_ENTITY_NOTATION_NAME, + XML_ROLE_NOTATION_NONE, + XML_ROLE_NOTATION_NAME, + XML_ROLE_NOTATION_SYSTEM_ID, + XML_ROLE_NOTATION_NO_SYSTEM_ID, + XML_ROLE_NOTATION_PUBLIC_ID, + XML_ROLE_ATTRIBUTE_NAME, + XML_ROLE_ATTRIBUTE_TYPE_CDATA, + XML_ROLE_ATTRIBUTE_TYPE_ID, + XML_ROLE_ATTRIBUTE_TYPE_IDREF, + XML_ROLE_ATTRIBUTE_TYPE_IDREFS, + XML_ROLE_ATTRIBUTE_TYPE_ENTITY, + XML_ROLE_ATTRIBUTE_TYPE_ENTITIES, + XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN, + XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS, + XML_ROLE_ATTRIBUTE_ENUM_VALUE, + XML_ROLE_ATTRIBUTE_NOTATION_VALUE, + XML_ROLE_ATTLIST_NONE, + XML_ROLE_ATTLIST_ELEMENT_NAME, + XML_ROLE_IMPLIED_ATTRIBUTE_VALUE, + XML_ROLE_REQUIRED_ATTRIBUTE_VALUE, + XML_ROLE_DEFAULT_ATTRIBUTE_VALUE, + XML_ROLE_FIXED_ATTRIBUTE_VALUE, + XML_ROLE_ELEMENT_NONE, + XML_ROLE_ELEMENT_NAME, + XML_ROLE_CONTENT_ANY, + XML_ROLE_CONTENT_EMPTY, + XML_ROLE_CONTENT_PCDATA, + XML_ROLE_GROUP_OPEN, + XML_ROLE_GROUP_CLOSE, + XML_ROLE_GROUP_CLOSE_REP, + XML_ROLE_GROUP_CLOSE_OPT, + XML_ROLE_GROUP_CLOSE_PLUS, + XML_ROLE_GROUP_CHOICE, + XML_ROLE_GROUP_SEQUENCE, + XML_ROLE_CONTENT_ELEMENT, + XML_ROLE_CONTENT_ELEMENT_REP, + XML_ROLE_CONTENT_ELEMENT_OPT, + XML_ROLE_CONTENT_ELEMENT_PLUS, + XML_ROLE_PI, + XML_ROLE_COMMENT, +#ifdef XML_DTD + XML_ROLE_TEXT_DECL, + XML_ROLE_IGNORE_SECT, + XML_ROLE_INNER_PARAM_ENTITY_REF, +#endif /* XML_DTD */ + XML_ROLE_PARAM_ENTITY_REF +}; + +typedef struct prolog_state { + int (PTRCALL *handler) (struct prolog_state *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc); + unsigned level; + int role_none; +#ifdef XML_DTD + unsigned includeLevel; + int documentEntity; + int inEntityValue; +#endif /* XML_DTD */ +} PROLOG_STATE; + +void XmlPrologStateInit(PROLOG_STATE *); +#ifdef XML_DTD +void XmlPrologStateInitExternalEntity(PROLOG_STATE *); +#endif /* XML_DTD */ + +#define XmlTokenRole(state, tok, ptr, end, enc) \ + (((state)->handler)(state, tok, ptr, end, enc)) + +#ifdef __cplusplus +} +#endif + +#endif /* not XmlRole_INCLUDED */ diff --git a/gpr/source/lib/expat_lib/xmltok.c b/gpr/source/lib/expat_lib/xmltok.c new file mode 100644 index 0000000..c2e5e8c --- /dev/null +++ b/gpr/source/lib/expat_lib/xmltok.c @@ -0,0 +1,1664 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#include <stddef.h> + +#ifdef COMPILED_FROM_DSP +#include "winconfig.h" +#elif defined(MACOS_CLASSIC) +#include "macconfig.h" +#elif defined(__amigaos__) +#include "amigaconfig.h" +#elif defined(__WATCOMC__) +#include "watcomconfig.h" +#else +#ifdef HAVE_EXPAT_CONFIG_H +#include <expat_config.h> +#endif +#endif /* ndef COMPILED_FROM_DSP */ + +#include "expat_external.h" +#include "internal.h" +#include "xmltok.h" +#include "nametab.h" + +#ifdef XML_DTD +#define IGNORE_SECTION_TOK_VTABLE , PREFIX(ignoreSectionTok) +#else +#define IGNORE_SECTION_TOK_VTABLE /* as nothing */ +#endif + +#define VTABLE1 \ + { PREFIX(prologTok), PREFIX(contentTok), \ + PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE }, \ + { PREFIX(attributeValueTok), PREFIX(entityValueTok) }, \ + PREFIX(sameName), \ + PREFIX(nameMatchesAscii), \ + PREFIX(nameLength), \ + PREFIX(skipS), \ + PREFIX(getAtts), \ + PREFIX(charRefNumber), \ + PREFIX(predefinedEntityName), \ + PREFIX(updatePosition), \ + PREFIX(isPublicId) + +#define VTABLE VTABLE1, PREFIX(toUtf8), PREFIX(toUtf16) + +#define UCS2_GET_NAMING(pages, hi, lo) \ + (namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1 << ((lo) & 0x1F))) + +/* A 2 byte UTF-8 representation splits the characters 11 bits between + the bottom 5 and 6 bits of the bytes. We need 8 bits to index into + pages, 3 bits to add to that index and 5 bits to generate the mask. +*/ +#define UTF8_GET_NAMING2(pages, byte) \ + (namingBitmap[((pages)[(((byte)[0]) >> 2) & 7] << 3) \ + + ((((byte)[0]) & 3) << 1) \ + + ((((byte)[1]) >> 5) & 1)] \ + & (1 << (((byte)[1]) & 0x1F))) + +/* A 3 byte UTF-8 representation splits the characters 16 bits between + the bottom 4, 6 and 6 bits of the bytes. We need 8 bits to index + into pages, 3 bits to add to that index and 5 bits to generate the + mask. +*/ +#define UTF8_GET_NAMING3(pages, byte) \ + (namingBitmap[((pages)[((((byte)[0]) & 0xF) << 4) \ + + ((((byte)[1]) >> 2) & 0xF)] \ + << 3) \ + + ((((byte)[1]) & 3) << 1) \ + + ((((byte)[2]) >> 5) & 1)] \ + & (1 << (((byte)[2]) & 0x1F))) + +#define UTF8_GET_NAMING(pages, p, n) \ + ((n) == 2 \ + ? UTF8_GET_NAMING2(pages, (const unsigned char *)(p)) \ + : ((n) == 3 \ + ? UTF8_GET_NAMING3(pages, (const unsigned char *)(p)) \ + : 0)) + +/* Detection of invalid UTF-8 sequences is based on Table 3.1B + of Unicode 3.2: http://www.unicode.org/unicode/reports/tr28/ + with the additional restriction of not allowing the Unicode + code points 0xFFFF and 0xFFFE (sequences EF,BF,BF and EF,BF,BE). + Implementation details: + (A & 0x80) == 0 means A < 0x80 + and + (A & 0xC0) == 0xC0 means A > 0xBF +*/ + +#define UTF8_INVALID2(p) \ + ((*p) < 0xC2 || ((p)[1] & 0x80) == 0 || ((p)[1] & 0xC0) == 0xC0) + +#define UTF8_INVALID3(p) \ + (((p)[2] & 0x80) == 0 \ + || \ + ((*p) == 0xEF && (p)[1] == 0xBF \ + ? \ + (p)[2] > 0xBD \ + : \ + ((p)[2] & 0xC0) == 0xC0) \ + || \ + ((*p) == 0xE0 \ + ? \ + (p)[1] < 0xA0 || ((p)[1] & 0xC0) == 0xC0 \ + : \ + ((p)[1] & 0x80) == 0 \ + || \ + ((*p) == 0xED ? (p)[1] > 0x9F : ((p)[1] & 0xC0) == 0xC0))) + +#define UTF8_INVALID4(p) \ + (((p)[3] & 0x80) == 0 || ((p)[3] & 0xC0) == 0xC0 \ + || \ + ((p)[2] & 0x80) == 0 || ((p)[2] & 0xC0) == 0xC0 \ + || \ + ((*p) == 0xF0 \ + ? \ + (p)[1] < 0x90 || ((p)[1] & 0xC0) == 0xC0 \ + : \ + ((p)[1] & 0x80) == 0 \ + || \ + ((*p) == 0xF4 ? (p)[1] > 0x8F : ((p)[1] & 0xC0) == 0xC0))) + +static int PTRFASTCALL +isNever(const ENCODING *enc, const char *p) +{ + return 0; +} + +static int PTRFASTCALL +utf8_isName2(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING2(namePages, (const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isName3(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING3(namePages, (const unsigned char *)p); +} + +#define utf8_isName4 isNever + +static int PTRFASTCALL +utf8_isNmstrt2(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING2(nmstrtPages, (const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isNmstrt3(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING3(nmstrtPages, (const unsigned char *)p); +} + +#define utf8_isNmstrt4 isNever + +static int PTRFASTCALL +utf8_isInvalid2(const ENCODING *enc, const char *p) +{ + return UTF8_INVALID2((const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isInvalid3(const ENCODING *enc, const char *p) +{ + return UTF8_INVALID3((const unsigned char *)p); +} + +static int PTRFASTCALL +utf8_isInvalid4(const ENCODING *enc, const char *p) +{ + return UTF8_INVALID4((const unsigned char *)p); +} + +struct normal_encoding { + ENCODING enc; + unsigned char type[256]; +#ifdef XML_MIN_SIZE + int (PTRFASTCALL *byteType)(const ENCODING *, const char *); + int (PTRFASTCALL *isNameMin)(const ENCODING *, const char *); + int (PTRFASTCALL *isNmstrtMin)(const ENCODING *, const char *); + int (PTRFASTCALL *byteToAscii)(const ENCODING *, const char *); + int (PTRCALL *charMatches)(const ENCODING *, const char *, int); +#endif /* XML_MIN_SIZE */ + int (PTRFASTCALL *isName2)(const ENCODING *, const char *); + int (PTRFASTCALL *isName3)(const ENCODING *, const char *); + int (PTRFASTCALL *isName4)(const ENCODING *, const char *); + int (PTRFASTCALL *isNmstrt2)(const ENCODING *, const char *); + int (PTRFASTCALL *isNmstrt3)(const ENCODING *, const char *); + int (PTRFASTCALL *isNmstrt4)(const ENCODING *, const char *); + int (PTRFASTCALL *isInvalid2)(const ENCODING *, const char *); + int (PTRFASTCALL *isInvalid3)(const ENCODING *, const char *); + int (PTRFASTCALL *isInvalid4)(const ENCODING *, const char *); +}; + +#define AS_NORMAL_ENCODING(enc) ((const struct normal_encoding *) (enc)) + +#ifdef XML_MIN_SIZE + +#define STANDARD_VTABLE(E) \ + E ## byteType, \ + E ## isNameMin, \ + E ## isNmstrtMin, \ + E ## byteToAscii, \ + E ## charMatches, + +#else + +#define STANDARD_VTABLE(E) /* as nothing */ + +#endif + +#define NORMAL_VTABLE(E) \ + E ## isName2, \ + E ## isName3, \ + E ## isName4, \ + E ## isNmstrt2, \ + E ## isNmstrt3, \ + E ## isNmstrt4, \ + E ## isInvalid2, \ + E ## isInvalid3, \ + E ## isInvalid4 + +#define EMPTY_VTABLE \ + NULL, \ + NULL, \ + NULL, \ + NULL, \ + NULL, \ + NULL, \ + NULL, \ + NULL, \ + NULL + +static int FASTCALL checkCharRefNumber(int); + +#include "xmltok_impl.h" +#include "ascii.h" + +#ifdef XML_MIN_SIZE +#define sb_isNameMin isNever +#define sb_isNmstrtMin isNever +#endif + +#ifdef XML_MIN_SIZE +#define MINBPC(enc) ((enc)->minBytesPerChar) +#else +/* minimum bytes per character */ +#define MINBPC(enc) 1 +#endif + +#define SB_BYTE_TYPE(enc, p) \ + (((struct normal_encoding *)(enc))->type[(unsigned char)*(p)]) + +#ifdef XML_MIN_SIZE +static int PTRFASTCALL +sb_byteType(const ENCODING *enc, const char *p) +{ + return SB_BYTE_TYPE(enc, p); +} +#define BYTE_TYPE(enc, p) \ + (AS_NORMAL_ENCODING(enc)->byteType(enc, p)) +#else +#define BYTE_TYPE(enc, p) SB_BYTE_TYPE(enc, p) +#endif + +#ifdef XML_MIN_SIZE +#define BYTE_TO_ASCII(enc, p) \ + (AS_NORMAL_ENCODING(enc)->byteToAscii(enc, p)) +static int PTRFASTCALL +sb_byteToAscii(const ENCODING *enc, const char *p) +{ + return *p; +} +#else +#define BYTE_TO_ASCII(enc, p) (*(p)) +#endif + +#define IS_NAME_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isName ## n(enc, p)) +#define IS_NMSTRT_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isNmstrt ## n(enc, p)) +#define IS_INVALID_CHAR(enc, p, n) \ + (AS_NORMAL_ENCODING(enc)->isInvalid ## n(enc, p)) + +#ifdef XML_MIN_SIZE +#define IS_NAME_CHAR_MINBPC(enc, p) \ + (AS_NORMAL_ENCODING(enc)->isNameMin(enc, p)) +#define IS_NMSTRT_CHAR_MINBPC(enc, p) \ + (AS_NORMAL_ENCODING(enc)->isNmstrtMin(enc, p)) +#else +#define IS_NAME_CHAR_MINBPC(enc, p) (0) +#define IS_NMSTRT_CHAR_MINBPC(enc, p) (0) +#endif + +#ifdef XML_MIN_SIZE +#define CHAR_MATCHES(enc, p, c) \ + (AS_NORMAL_ENCODING(enc)->charMatches(enc, p, c)) +static int PTRCALL +sb_charMatches(const ENCODING *enc, const char *p, int c) +{ + return *p == c; +} +#else +/* c is an ASCII character */ +#define CHAR_MATCHES(enc, p, c) (*(p) == c) +#endif + +#define PREFIX(ident) normal_ ## ident +#define XML_TOK_IMPL_C +#include "xmltok_impl.c" +#undef XML_TOK_IMPL_C + +#undef MINBPC +#undef BYTE_TYPE +#undef BYTE_TO_ASCII +#undef CHAR_MATCHES +#undef IS_NAME_CHAR +#undef IS_NAME_CHAR_MINBPC +#undef IS_NMSTRT_CHAR +#undef IS_NMSTRT_CHAR_MINBPC +#undef IS_INVALID_CHAR + +enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */ + UTF8_cval1 = 0x00, + UTF8_cval2 = 0xc0, + UTF8_cval3 = 0xe0, + UTF8_cval4 = 0xf0 +}; + +static void PTRCALL +utf8_toUtf8(const ENCODING *enc, + const char **fromP, const char *fromLim, + char **toP, const char *toLim) +{ + char *to; + const char *from; + if (fromLim - *fromP > toLim - *toP) { + /* Avoid copying partial characters. */ + for (fromLim = *fromP + (toLim - *toP); fromLim > *fromP; fromLim--) + if (((unsigned char)fromLim[-1] & 0xc0) != 0x80) + break; + } + for (to = *toP, from = *fromP; from != fromLim; from++, to++) + *to = *from; + *fromP = from; + *toP = to; +} + +static void PTRCALL +utf8_toUtf16(const ENCODING *enc, + const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) +{ + unsigned short *to = *toP; + const char *from = *fromP; + while (from != fromLim && to != toLim) { + switch (((struct normal_encoding *)enc)->type[(unsigned char)*from]) { + case BT_LEAD2: + *to++ = (unsigned short)(((from[0] & 0x1f) << 6) | (from[1] & 0x3f)); + from += 2; + break; + case BT_LEAD3: + *to++ = (unsigned short)(((from[0] & 0xf) << 12) + | ((from[1] & 0x3f) << 6) | (from[2] & 0x3f)); + from += 3; + break; + case BT_LEAD4: + { + unsigned long n; + if (to + 1 == toLim) + goto after; + n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12) + | ((from[2] & 0x3f) << 6) | (from[3] & 0x3f); + n -= 0x10000; + to[0] = (unsigned short)((n >> 10) | 0xD800); + to[1] = (unsigned short)((n & 0x3FF) | 0xDC00); + to += 2; + from += 4; + } + break; + default: + *to++ = *from++; + break; + } + } +after: + *fromP = from; + *toP = to; +} + +#ifdef XML_NS +static const struct normal_encoding utf8_encoding_ns = { + { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, + { +#include "asciitab.h" +#include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) +}; +#endif + +static const struct normal_encoding utf8_encoding = { + { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) +}; + +#ifdef XML_NS + +static const struct normal_encoding internal_utf8_encoding_ns = { + { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, + { +#include "iasciitab.h" +#include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) +}; + +#endif + +static const struct normal_encoding internal_utf8_encoding = { + { VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0 }, + { +#define BT_COLON BT_NMSTRT +#include "iasciitab.h" +#undef BT_COLON +#include "utf8tab.h" + }, + STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_) +}; + +static void PTRCALL +latin1_toUtf8(const ENCODING *enc, + const char **fromP, const char *fromLim, + char **toP, const char *toLim) +{ + for (;;) { + unsigned char c; + if (*fromP == fromLim) + break; + c = (unsigned char)**fromP; + if (c & 0x80) { + if (toLim - *toP < 2) + break; + *(*toP)++ = (char)((c >> 6) | UTF8_cval2); + *(*toP)++ = (char)((c & 0x3f) | 0x80); + (*fromP)++; + } + else { + if (*toP == toLim) + break; + *(*toP)++ = *(*fromP)++; + } + } +} + +static void PTRCALL +latin1_toUtf16(const ENCODING *enc, + const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) +{ + while (*fromP != fromLim && *toP != toLim) + *(*toP)++ = (unsigned char)*(*fromP)++; +} + +#ifdef XML_NS + +static const struct normal_encoding latin1_encoding_ns = { + { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 }, + { +#include "asciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(sb_) EMPTY_VTABLE +}; + +#endif + +static const struct normal_encoding latin1_encoding = { + { VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0 }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(sb_) EMPTY_VTABLE +}; + +static void PTRCALL +ascii_toUtf8(const ENCODING *enc, + const char **fromP, const char *fromLim, + char **toP, const char *toLim) +{ + while (*fromP != fromLim && *toP != toLim) + *(*toP)++ = *(*fromP)++; +} + +#ifdef XML_NS + +static const struct normal_encoding ascii_encoding_ns = { + { VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 }, + { +#include "asciitab.h" +/* BT_NONXML == 0 */ + }, + STANDARD_VTABLE(sb_) EMPTY_VTABLE +}; + +#endif + +static const struct normal_encoding ascii_encoding = { + { VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0 }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +/* BT_NONXML == 0 */ + }, + STANDARD_VTABLE(sb_) EMPTY_VTABLE +}; + +static int PTRFASTCALL +unicode_byte_type(char hi, char lo) +{ + switch ((unsigned char)hi) { + case 0xD8: case 0xD9: case 0xDA: case 0xDB: + return BT_LEAD4; + case 0xDC: case 0xDD: case 0xDE: case 0xDF: + return BT_TRAIL; + case 0xFF: + switch ((unsigned char)lo) { + case 0xFF: + case 0xFE: + return BT_NONXML; + } + break; + } + return BT_NONASCII; +} + +#define DEFINE_UTF16_TO_UTF8(E) \ +static void PTRCALL \ +E ## toUtf8(const ENCODING *enc, \ + const char **fromP, const char *fromLim, \ + char **toP, const char *toLim) \ +{ \ + const char *from; \ + for (from = *fromP; from != fromLim; from += 2) { \ + int plane; \ + unsigned char lo2; \ + unsigned char lo = GET_LO(from); \ + unsigned char hi = GET_HI(from); \ + switch (hi) { \ + case 0: \ + if (lo < 0x80) { \ + if (*toP == toLim) { \ + *fromP = from; \ + return; \ + } \ + *(*toP)++ = lo; \ + break; \ + } \ + __attribute((fallthrough)); \ + /* fall through */ \ + case 0x1: case 0x2: case 0x3: \ + case 0x4: case 0x5: case 0x6: case 0x7: \ + if (toLim - *toP < 2) { \ + *fromP = from; \ + return; \ + } \ + *(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \ + *(*toP)++ = ((lo & 0x3f) | 0x80); \ + break; \ + default: \ + if (toLim - *toP < 3) { \ + *fromP = from; \ + return; \ + } \ + /* 16 bits divided 4, 6, 6 amongst 3 bytes */ \ + *(*toP)++ = ((hi >> 4) | UTF8_cval3); \ + *(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \ + *(*toP)++ = ((lo & 0x3f) | 0x80); \ + break; \ + case 0xD8: case 0xD9: case 0xDA: case 0xDB: \ + if (toLim - *toP < 4) { \ + *fromP = from; \ + return; \ + } \ + plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \ + *(*toP)++ = ((plane >> 2) | UTF8_cval4); \ + *(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \ + from += 2; \ + lo2 = GET_LO(from); \ + *(*toP)++ = (((lo & 0x3) << 4) \ + | ((GET_HI(from) & 0x3) << 2) \ + | (lo2 >> 6) \ + | 0x80); \ + *(*toP)++ = ((lo2 & 0x3f) | 0x80); \ + break; \ + } \ + } \ + *fromP = from; \ +} + +#define DEFINE_UTF16_TO_UTF16(E) \ +static void PTRCALL \ +E ## toUtf16(const ENCODING *enc, \ + const char **fromP, const char *fromLim, \ + unsigned short **toP, const unsigned short *toLim) \ +{ \ + /* Avoid copying first half only of surrogate */ \ + if (fromLim - *fromP > ((toLim - *toP) << 1) \ + && (GET_HI(fromLim - 2) & 0xF8) == 0xD8) \ + fromLim -= 2; \ + for (; *fromP != fromLim && *toP != toLim; *fromP += 2) \ + *(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \ +} + +#define SET2(ptr, ch) \ + (((ptr)[0] = ((ch) & 0xff)), ((ptr)[1] = ((ch) >> 8))) +#define GET_LO(ptr) ((unsigned char)(ptr)[0]) +#define GET_HI(ptr) ((unsigned char)(ptr)[1]) + +DEFINE_UTF16_TO_UTF8(little2_) +DEFINE_UTF16_TO_UTF16(little2_) + +#undef SET2 +#undef GET_LO +#undef GET_HI + +#define SET2(ptr, ch) \ + (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch) & 0xFF))) +#define GET_LO(ptr) ((unsigned char)(ptr)[1]) +#define GET_HI(ptr) ((unsigned char)(ptr)[0]) + +DEFINE_UTF16_TO_UTF8(big2_) +DEFINE_UTF16_TO_UTF16(big2_) + +#undef SET2 +#undef GET_LO +#undef GET_HI + +#define LITTLE2_BYTE_TYPE(enc, p) \ + ((p)[1] == 0 \ + ? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \ + : unicode_byte_type((p)[1], (p)[0])) +#define LITTLE2_BYTE_TO_ASCII(enc, p) ((p)[1] == 0 ? (p)[0] : -1) +#define LITTLE2_CHAR_MATCHES(enc, p, c) ((p)[1] == 0 && (p)[0] == c) +#define LITTLE2_IS_NAME_CHAR_MINBPC(enc, p) \ + UCS2_GET_NAMING(namePages, (unsigned char)p[1], (unsigned char)p[0]) +#define LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p) \ + UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[1], (unsigned char)p[0]) + +#ifdef XML_MIN_SIZE + +static int PTRFASTCALL +little2_byteType(const ENCODING *enc, const char *p) +{ + return LITTLE2_BYTE_TYPE(enc, p); +} + +static int PTRFASTCALL +little2_byteToAscii(const ENCODING *enc, const char *p) +{ + return LITTLE2_BYTE_TO_ASCII(enc, p); +} + +static int PTRCALL +little2_charMatches(const ENCODING *enc, const char *p, int c) +{ + return LITTLE2_CHAR_MATCHES(enc, p, c); +} + +static int PTRFASTCALL +little2_isNameMin(const ENCODING *enc, const char *p) +{ + return LITTLE2_IS_NAME_CHAR_MINBPC(enc, p); +} + +static int PTRFASTCALL +little2_isNmstrtMin(const ENCODING *enc, const char *p) +{ + return LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p); +} + +#undef VTABLE +#define VTABLE VTABLE1, little2_toUtf8, little2_toUtf16 + +#else /* not XML_MIN_SIZE */ + +#undef PREFIX +#define PREFIX(ident) little2_ ## ident +#define MINBPC(enc) 2 +/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ +#define BYTE_TYPE(enc, p) LITTLE2_BYTE_TYPE(enc, p) +#define BYTE_TO_ASCII(enc, p) LITTLE2_BYTE_TO_ASCII(enc, p) +#define CHAR_MATCHES(enc, p, c) LITTLE2_CHAR_MATCHES(enc, p, c) +#define IS_NAME_CHAR(enc, p, n) 0 +#define IS_NAME_CHAR_MINBPC(enc, p) LITTLE2_IS_NAME_CHAR_MINBPC(enc, p) +#define IS_NMSTRT_CHAR(enc, p, n) (0) +#define IS_NMSTRT_CHAR_MINBPC(enc, p) LITTLE2_IS_NMSTRT_CHAR_MINBPC(enc, p) + +#define XML_TOK_IMPL_C +#include "xmltok_impl.c" +#undef XML_TOK_IMPL_C + +#undef MINBPC +#undef BYTE_TYPE +#undef BYTE_TO_ASCII +#undef CHAR_MATCHES +#undef IS_NAME_CHAR +#undef IS_NAME_CHAR_MINBPC +#undef IS_NMSTRT_CHAR +#undef IS_NMSTRT_CHAR_MINBPC +#undef IS_INVALID_CHAR + +#endif /* not XML_MIN_SIZE */ + +#ifdef XML_NS + +static const struct normal_encoding little2_encoding_ns = { + { VTABLE, 2, 0, +#if BYTEORDER == 1234 + 1 +#else + 0 +#endif + }, + { +#include "asciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) EMPTY_VTABLE +}; + +#endif + +static const struct normal_encoding little2_encoding = { + { VTABLE, 2, 0, +#if BYTEORDER == 1234 + 1 +#else + 0 +#endif + }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) EMPTY_VTABLE +}; + +#if BYTEORDER != 4321 + +#ifdef XML_NS + +static const struct normal_encoding internal_little2_encoding_ns = { + { VTABLE, 2, 0, 1 }, + { +#include "iasciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) EMPTY_VTABLE +}; + +#endif + +static const struct normal_encoding internal_little2_encoding = { + { VTABLE, 2, 0, 1 }, + { +#define BT_COLON BT_NMSTRT +#include "iasciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) EMPTY_VTABLE +}; + +#endif + + +#define BIG2_BYTE_TYPE(enc, p) \ + ((p)[0] == 0 \ + ? ((struct normal_encoding *)(enc))->type[(unsigned char)(p)[1]] \ + : unicode_byte_type((p)[0], (p)[1])) +#define BIG2_BYTE_TO_ASCII(enc, p) ((p)[0] == 0 ? (p)[1] : -1) +#define BIG2_CHAR_MATCHES(enc, p, c) ((p)[0] == 0 && (p)[1] == c) +#define BIG2_IS_NAME_CHAR_MINBPC(enc, p) \ + UCS2_GET_NAMING(namePages, (unsigned char)p[0], (unsigned char)p[1]) +#define BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p) \ + UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[0], (unsigned char)p[1]) + +#ifdef XML_MIN_SIZE + +static int PTRFASTCALL +big2_byteType(const ENCODING *enc, const char *p) +{ + return BIG2_BYTE_TYPE(enc, p); +} + +static int PTRFASTCALL +big2_byteToAscii(const ENCODING *enc, const char *p) +{ + return BIG2_BYTE_TO_ASCII(enc, p); +} + +static int PTRCALL +big2_charMatches(const ENCODING *enc, const char *p, int c) +{ + return BIG2_CHAR_MATCHES(enc, p, c); +} + +static int PTRFASTCALL +big2_isNameMin(const ENCODING *enc, const char *p) +{ + return BIG2_IS_NAME_CHAR_MINBPC(enc, p); +} + +static int PTRFASTCALL +big2_isNmstrtMin(const ENCODING *enc, const char *p) +{ + return BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p); +} + +#undef VTABLE +#define VTABLE VTABLE1, big2_toUtf8, big2_toUtf16 + +#else /* not XML_MIN_SIZE */ + +#undef PREFIX +#define PREFIX(ident) big2_ ## ident +#define MINBPC(enc) 2 +/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ +#define BYTE_TYPE(enc, p) BIG2_BYTE_TYPE(enc, p) +#define BYTE_TO_ASCII(enc, p) BIG2_BYTE_TO_ASCII(enc, p) +#define CHAR_MATCHES(enc, p, c) BIG2_CHAR_MATCHES(enc, p, c) +#define IS_NAME_CHAR(enc, p, n) 0 +#define IS_NAME_CHAR_MINBPC(enc, p) BIG2_IS_NAME_CHAR_MINBPC(enc, p) +#define IS_NMSTRT_CHAR(enc, p, n) (0) +#define IS_NMSTRT_CHAR_MINBPC(enc, p) BIG2_IS_NMSTRT_CHAR_MINBPC(enc, p) + +#define XML_TOK_IMPL_C +#include "xmltok_impl.c" +#undef XML_TOK_IMPL_C + +#undef MINBPC +#undef BYTE_TYPE +#undef BYTE_TO_ASCII +#undef CHAR_MATCHES +#undef IS_NAME_CHAR +#undef IS_NAME_CHAR_MINBPC +#undef IS_NMSTRT_CHAR +#undef IS_NMSTRT_CHAR_MINBPC +#undef IS_INVALID_CHAR + +#endif /* not XML_MIN_SIZE */ + +#ifdef XML_NS + +static const struct normal_encoding big2_encoding_ns = { + { VTABLE, 2, 0, +#if BYTEORDER == 4321 + 1 +#else + 0 +#endif + }, + { +#include "asciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) EMPTY_VTABLE +}; + +#endif + +static const struct normal_encoding big2_encoding = { + { VTABLE, 2, 0, +#if BYTEORDER == 4321 + 1 +#else + 0 +#endif + }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) EMPTY_VTABLE +}; + +#if BYTEORDER != 1234 + +#ifdef XML_NS + +static const struct normal_encoding internal_big2_encoding_ns = { + { VTABLE, 2, 0, 1 }, + { +#include "iasciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) EMPTY_VTABLE +}; + +#endif + +static const struct normal_encoding internal_big2_encoding = { + { VTABLE, 2, 0, 1 }, + { +#define BT_COLON BT_NMSTRT +#include "iasciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) EMPTY_VTABLE +}; + +#endif + +#undef PREFIX + +static int FASTCALL +streqci(const char *s1, const char *s2) +{ + for (;;) { + char c1 = *s1++; + char c2 = *s2++; + if (ASCII_a <= c1 && c1 <= ASCII_z) + c1 += ASCII_A - ASCII_a; + if (ASCII_a <= c2 && c2 <= ASCII_z) + c2 += ASCII_A - ASCII_a; + if (c1 != c2) + return 0; + if (!c1) + break; + } + return 1; +} + +static void PTRCALL +initUpdatePosition(const ENCODING *enc, const char *ptr, + const char *end, POSITION *pos) +{ + normal_updatePosition(&utf8_encoding.enc, ptr, end, pos); +} + +static int +toAscii(const ENCODING *enc, const char *ptr, const char *end) +{ + char buf[1]; + char *p = buf; + XmlUtf8Convert(enc, &ptr, end, &p, p + 1); + if (p == buf) + return -1; + else + return buf[0]; +} + +static int FASTCALL +isSpace(int c) +{ + switch (c) { + case 0x20: + case 0xD: + case 0xA: + case 0x9: + return 1; + } + return 0; +} + +/* Return 1 if there's just optional white space or there's an S + followed by name=val. +*/ +static int +parsePseudoAttribute(const ENCODING *enc, + const char *ptr, + const char *end, + const char **namePtr, + const char **nameEndPtr, + const char **valPtr, + const char **nextTokPtr) +{ + int c; + char open; + if (ptr == end) { + *namePtr = NULL; + return 1; + } + if (!isSpace(toAscii(enc, ptr, end))) { + *nextTokPtr = ptr; + return 0; + } + do { + ptr += enc->minBytesPerChar; + } while (isSpace(toAscii(enc, ptr, end))); + if (ptr == end) { + *namePtr = NULL; + return 1; + } + *namePtr = ptr; + for (;;) { + c = toAscii(enc, ptr, end); + if (c == -1) { + *nextTokPtr = ptr; + return 0; + } + if (c == ASCII_EQUALS) { + *nameEndPtr = ptr; + break; + } + if (isSpace(c)) { + *nameEndPtr = ptr; + do { + ptr += enc->minBytesPerChar; + } while (isSpace(c = toAscii(enc, ptr, end))); + if (c != ASCII_EQUALS) { + *nextTokPtr = ptr; + return 0; + } + break; + } + ptr += enc->minBytesPerChar; + } + if (ptr == *namePtr) { + *nextTokPtr = ptr; + return 0; + } + ptr += enc->minBytesPerChar; + c = toAscii(enc, ptr, end); + while (isSpace(c)) { + ptr += enc->minBytesPerChar; + c = toAscii(enc, ptr, end); + } + if (c != ASCII_QUOT && c != ASCII_APOS) { + *nextTokPtr = ptr; + return 0; + } + open = (char)c; + ptr += enc->minBytesPerChar; + *valPtr = ptr; + for (;; ptr += enc->minBytesPerChar) { + c = toAscii(enc, ptr, end); + if (c == open) + break; + if (!(ASCII_a <= c && c <= ASCII_z) + && !(ASCII_A <= c && c <= ASCII_Z) + && !(ASCII_0 <= c && c <= ASCII_9) + && c != ASCII_PERIOD + && c != ASCII_MINUS + && c != ASCII_UNDERSCORE) { + *nextTokPtr = ptr; + return 0; + } + } + *nextTokPtr = ptr + enc->minBytesPerChar; + return 1; +} + +static const char KW_version[] = { + ASCII_v, ASCII_e, ASCII_r, ASCII_s, ASCII_i, ASCII_o, ASCII_n, '\0' +}; + +static const char KW_encoding[] = { + ASCII_e, ASCII_n, ASCII_c, ASCII_o, ASCII_d, ASCII_i, ASCII_n, ASCII_g, '\0' +}; + +static const char KW_standalone[] = { + ASCII_s, ASCII_t, ASCII_a, ASCII_n, ASCII_d, ASCII_a, ASCII_l, ASCII_o, + ASCII_n, ASCII_e, '\0' +}; + +static const char KW_yes[] = { + ASCII_y, ASCII_e, ASCII_s, '\0' +}; + +static const char KW_no[] = { + ASCII_n, ASCII_o, '\0' +}; + +static int +doParseXmlDecl(const ENCODING *(*encodingFinder)(const ENCODING *, + const char *, + const char *), + int isGeneralTextEntity, + const ENCODING *enc, + const char *ptr, + const char *end, + const char **badPtr, + const char **versionPtr, + const char **versionEndPtr, + const char **encodingName, + const ENCODING **encoding, + int *standalone) +{ + const char *val = NULL; + const char *name = NULL; + const char *nameEnd = NULL; + ptr += 5 * enc->minBytesPerChar; + end -= 2 * enc->minBytesPerChar; + if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr) + || !name) { + *badPtr = ptr; + return 0; + } + if (!XmlNameMatchesAscii(enc, name, nameEnd, KW_version)) { + if (!isGeneralTextEntity) { + *badPtr = name; + return 0; + } + } + else { + if (versionPtr) + *versionPtr = val; + if (versionEndPtr) + *versionEndPtr = ptr; + if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { + *badPtr = ptr; + return 0; + } + if (!name) { + if (isGeneralTextEntity) { + /* a TextDecl must have an EncodingDecl */ + *badPtr = ptr; + return 0; + } + return 1; + } + } + if (XmlNameMatchesAscii(enc, name, nameEnd, KW_encoding)) { + int c = toAscii(enc, val, end); + if (!(ASCII_a <= c && c <= ASCII_z) && !(ASCII_A <= c && c <= ASCII_Z)) { + *badPtr = val; + return 0; + } + if (encodingName) + *encodingName = val; + if (encoding) + *encoding = encodingFinder(enc, val, ptr - enc->minBytesPerChar); + if (!parsePseudoAttribute(enc, ptr, end, &name, &nameEnd, &val, &ptr)) { + *badPtr = ptr; + return 0; + } + if (!name) + return 1; + } + if (!XmlNameMatchesAscii(enc, name, nameEnd, KW_standalone) + || isGeneralTextEntity) { + *badPtr = name; + return 0; + } + if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_yes)) { + if (standalone) + *standalone = 1; + } + else if (XmlNameMatchesAscii(enc, val, ptr - enc->minBytesPerChar, KW_no)) { + if (standalone) + *standalone = 0; + } + else { + *badPtr = val; + return 0; + } + while (isSpace(toAscii(enc, ptr, end))) + ptr += enc->minBytesPerChar; + if (ptr != end) { + *badPtr = ptr; + return 0; + } + return 1; +} + +static int FASTCALL +checkCharRefNumber(int result) +{ + switch (result >> 8) { + case 0xD8: case 0xD9: case 0xDA: case 0xDB: + case 0xDC: case 0xDD: case 0xDE: case 0xDF: + return -1; + case 0: + if (latin1_encoding.type[result] == BT_NONXML) + return -1; + break; + case 0xFF: + if (result == 0xFFFE || result == 0xFFFF) + return -1; + break; + } + return result; +} + +int FASTCALL +XmlUtf8Encode(int c, char *buf) +{ + enum { + /* minN is minimum legal resulting value for N byte sequence */ + min2 = 0x80, + min3 = 0x800, + min4 = 0x10000 + }; + + if (c < 0) + return 0; + if (c < min2) { + buf[0] = (char)(c | UTF8_cval1); + return 1; + } + if (c < min3) { + buf[0] = (char)((c >> 6) | UTF8_cval2); + buf[1] = (char)((c & 0x3f) | 0x80); + return 2; + } + if (c < min4) { + buf[0] = (char)((c >> 12) | UTF8_cval3); + buf[1] = (char)(((c >> 6) & 0x3f) | 0x80); + buf[2] = (char)((c & 0x3f) | 0x80); + return 3; + } + if (c < 0x110000) { + buf[0] = (char)((c >> 18) | UTF8_cval4); + buf[1] = (char)(((c >> 12) & 0x3f) | 0x80); + buf[2] = (char)(((c >> 6) & 0x3f) | 0x80); + buf[3] = (char)((c & 0x3f) | 0x80); + return 4; + } + return 0; +} + +int FASTCALL +XmlUtf16Encode(int charNum, unsigned short *buf) +{ + if (charNum < 0) + return 0; + if (charNum < 0x10000) { + buf[0] = (unsigned short)charNum; + return 1; + } + if (charNum < 0x110000) { + charNum -= 0x10000; + buf[0] = (unsigned short)((charNum >> 10) + 0xD800); + buf[1] = (unsigned short)((charNum & 0x3FF) + 0xDC00); + return 2; + } + return 0; +} + +struct unknown_encoding { + struct normal_encoding normal; + CONVERTER convert; + void *userData; + unsigned short utf16[256]; + char utf8[256][4]; +}; + +#define AS_UNKNOWN_ENCODING(enc) ((const struct unknown_encoding *) (enc)) + +int +XmlSizeOfUnknownEncoding(void) +{ + return sizeof(struct unknown_encoding); +} + +static int PTRFASTCALL +unknown_isName(const ENCODING *enc, const char *p) +{ + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + int c = uenc->convert(uenc->userData, p); + if (c & ~0xFFFF) + return 0; + return UCS2_GET_NAMING(namePages, c >> 8, c & 0xFF); +} + +static int PTRFASTCALL +unknown_isNmstrt(const ENCODING *enc, const char *p) +{ + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + int c = uenc->convert(uenc->userData, p); + if (c & ~0xFFFF) + return 0; + return UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xFF); +} + +static int PTRFASTCALL +unknown_isInvalid(const ENCODING *enc, const char *p) +{ + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + int c = uenc->convert(uenc->userData, p); + return (c & ~0xFFFF) || checkCharRefNumber(c) < 0; +} + +static void PTRCALL +unknown_toUtf8(const ENCODING *enc, + const char **fromP, const char *fromLim, + char **toP, const char *toLim) +{ + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + char buf[XML_UTF8_ENCODE_MAX]; + for (;;) { + const char *utf8; + int n; + if (*fromP == fromLim) + break; + utf8 = uenc->utf8[(unsigned char)**fromP]; + n = *utf8++; + if (n == 0) { + int c = uenc->convert(uenc->userData, *fromP); + n = XmlUtf8Encode(c, buf); + if (n > toLim - *toP) + break; + utf8 = buf; + *fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP] + - (BT_LEAD2 - 2)); + } + else { + if (n > toLim - *toP) + break; + (*fromP)++; + } + do { + *(*toP)++ = *utf8++; + } while (--n != 0); + } +} + +static void PTRCALL +unknown_toUtf16(const ENCODING *enc, + const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) +{ + const struct unknown_encoding *uenc = AS_UNKNOWN_ENCODING(enc); + while (*fromP != fromLim && *toP != toLim) { + unsigned short c = uenc->utf16[(unsigned char)**fromP]; + if (c == 0) { + c = (unsigned short) + uenc->convert(uenc->userData, *fromP); + *fromP += (AS_NORMAL_ENCODING(enc)->type[(unsigned char)**fromP] + - (BT_LEAD2 - 2)); + } + else + (*fromP)++; + *(*toP)++ = c; + } +} + +ENCODING * +XmlInitUnknownEncoding(void *mem, + int *table, + CONVERTER convert, + void *userData) +{ + int i; + struct unknown_encoding *e = (struct unknown_encoding *)mem; + for (i = 0; i < (int)sizeof(struct normal_encoding); i++) + ((char *)mem)[i] = ((char *)&latin1_encoding)[i]; + for (i = 0; i < 128; i++) + if (latin1_encoding.type[i] != BT_OTHER + && latin1_encoding.type[i] != BT_NONXML + && table[i] != i) + return 0; + for (i = 0; i < 256; i++) { + int c = table[i]; + if (c == -1) { + e->normal.type[i] = BT_MALFORM; + /* This shouldn't really get used. */ + e->utf16[i] = 0xFFFF; + e->utf8[i][0] = 1; + e->utf8[i][1] = 0; + } + else if (c < 0) { + if (c < -4) + return 0; + e->normal.type[i] = (unsigned char)(BT_LEAD2 - (c + 2)); + e->utf8[i][0] = 0; + e->utf16[i] = 0; + } + else if (c < 0x80) { + if (latin1_encoding.type[c] != BT_OTHER + && latin1_encoding.type[c] != BT_NONXML + && c != i) + return 0; + e->normal.type[i] = latin1_encoding.type[c]; + e->utf8[i][0] = 1; + e->utf8[i][1] = (char)c; + e->utf16[i] = (unsigned short)(c == 0 ? 0xFFFF : c); + } + else if (checkCharRefNumber(c) < 0) { + e->normal.type[i] = BT_NONXML; + /* This shouldn't really get used. */ + e->utf16[i] = 0xFFFF; + e->utf8[i][0] = 1; + e->utf8[i][1] = 0; + } + else { + if (c > 0xFFFF) + return 0; + if (UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xff)) + e->normal.type[i] = BT_NMSTRT; + else if (UCS2_GET_NAMING(namePages, c >> 8, c & 0xff)) + e->normal.type[i] = BT_NAME; + else + e->normal.type[i] = BT_OTHER; + e->utf8[i][0] = (char)XmlUtf8Encode(c, e->utf8[i] + 1); + e->utf16[i] = (unsigned short)c; + } + } + e->userData = userData; + e->convert = convert; + if (convert) { + e->normal.isName2 = unknown_isName; + e->normal.isName3 = unknown_isName; + e->normal.isName4 = unknown_isName; + e->normal.isNmstrt2 = unknown_isNmstrt; + e->normal.isNmstrt3 = unknown_isNmstrt; + e->normal.isNmstrt4 = unknown_isNmstrt; + e->normal.isInvalid2 = unknown_isInvalid; + e->normal.isInvalid3 = unknown_isInvalid; + e->normal.isInvalid4 = unknown_isInvalid; + } + e->normal.enc.utf8Convert = unknown_toUtf8; + e->normal.enc.utf16Convert = unknown_toUtf16; + return &(e->normal.enc); +} + +/* If this enumeration is changed, getEncodingIndex and encodings +must also be changed. */ +enum { + UNKNOWN_ENC = -1, + ISO_8859_1_ENC = 0, + US_ASCII_ENC, + UTF_8_ENC, + UTF_16_ENC, + UTF_16BE_ENC, + UTF_16LE_ENC, + /* must match encodingNames up to here */ + NO_ENC +}; + +static const char KW_ISO_8859_1[] = { + ASCII_I, ASCII_S, ASCII_O, ASCII_MINUS, ASCII_8, ASCII_8, ASCII_5, ASCII_9, + ASCII_MINUS, ASCII_1, '\0' +}; +static const char KW_US_ASCII[] = { + ASCII_U, ASCII_S, ASCII_MINUS, ASCII_A, ASCII_S, ASCII_C, ASCII_I, ASCII_I, + '\0' +}; +static const char KW_UTF_8[] = { + ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_8, '\0' +}; +static const char KW_UTF_16[] = { + ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, '\0' +}; +static const char KW_UTF_16BE[] = { + ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, ASCII_B, ASCII_E, + '\0' +}; +static const char KW_UTF_16LE[] = { + ASCII_U, ASCII_T, ASCII_F, ASCII_MINUS, ASCII_1, ASCII_6, ASCII_L, ASCII_E, + '\0' +}; + +static int FASTCALL +getEncodingIndex(const char *name) +{ + static const char * const encodingNames[] = { + KW_ISO_8859_1, + KW_US_ASCII, + KW_UTF_8, + KW_UTF_16, + KW_UTF_16BE, + KW_UTF_16LE, + }; + int i; + if (name == NULL) + return NO_ENC; + for (i = 0; i < (int)(sizeof(encodingNames)/sizeof(encodingNames[0])); i++) + if (streqci(name, encodingNames[i])) + return i; + return UNKNOWN_ENC; +} + +/* For binary compatibility, we store the index of the encoding + specified at initialization in the isUtf16 member. +*/ + +#define INIT_ENC_INDEX(enc) ((int)(enc)->initEnc.isUtf16) +#define SET_INIT_ENC_INDEX(enc, i) ((enc)->initEnc.isUtf16 = (char)i) + +/* This is what detects the encoding. encodingTable maps from + encoding indices to encodings; INIT_ENC_INDEX(enc) is the index of + the external (protocol) specified encoding; state is + XML_CONTENT_STATE if we're parsing an external text entity, and + XML_PROLOG_STATE otherwise. +*/ + + +static int +initScan(const ENCODING * const *encodingTable, + const INIT_ENCODING *enc, + int state, + const char *ptr, + const char *end, + const char **nextTokPtr) +{ + const ENCODING **encPtr; + + if (ptr == end) + return XML_TOK_NONE; + encPtr = enc->encPtr; + if (ptr + 1 == end) { + /* only a single byte available for auto-detection */ +#ifndef XML_DTD /* FIXME */ + /* a well-formed document entity must have more than one byte */ + if (state != XML_CONTENT_STATE) + return XML_TOK_PARTIAL; +#endif + /* so we're parsing an external text entity... */ + /* if UTF-16 was externally specified, then we need at least 2 bytes */ + switch (INIT_ENC_INDEX(enc)) { + case UTF_16_ENC: + case UTF_16LE_ENC: + case UTF_16BE_ENC: + return XML_TOK_PARTIAL; + } + switch ((unsigned char)*ptr) { + case 0xFE: + case 0xFF: + case 0xEF: /* possibly first byte of UTF-8 BOM */ + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC + && state == XML_CONTENT_STATE) + break; + __attribute((fallthrough)); + /* fall through */ + case 0x00: + case 0x3C: + return XML_TOK_PARTIAL; + } + } + else { + switch (((unsigned char)ptr[0] << 8) | (unsigned char)ptr[1]) { + case 0xFEFF: + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC + && state == XML_CONTENT_STATE) + break; + *nextTokPtr = ptr + 2; + *encPtr = encodingTable[UTF_16BE_ENC]; + return XML_TOK_BOM; + /* 00 3C is handled in the default case */ + case 0x3C00: + if ((INIT_ENC_INDEX(enc) == UTF_16BE_ENC + || INIT_ENC_INDEX(enc) == UTF_16_ENC) + && state == XML_CONTENT_STATE) + break; + *encPtr = encodingTable[UTF_16LE_ENC]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); + case 0xFFFE: + if (INIT_ENC_INDEX(enc) == ISO_8859_1_ENC + && state == XML_CONTENT_STATE) + break; + *nextTokPtr = ptr + 2; + *encPtr = encodingTable[UTF_16LE_ENC]; + return XML_TOK_BOM; + case 0xEFBB: + /* Maybe a UTF-8 BOM (EF BB BF) */ + /* If there's an explicitly specified (external) encoding + of ISO-8859-1 or some flavour of UTF-16 + and this is an external text entity, + don't look for the BOM, + because it might be a legal data. + */ + if (state == XML_CONTENT_STATE) { + int e = INIT_ENC_INDEX(enc); + if (e == ISO_8859_1_ENC || e == UTF_16BE_ENC + || e == UTF_16LE_ENC || e == UTF_16_ENC) + break; + } + if (ptr + 2 == end) + return XML_TOK_PARTIAL; + if ((unsigned char)ptr[2] == 0xBF) { + *nextTokPtr = ptr + 3; + *encPtr = encodingTable[UTF_8_ENC]; + return XML_TOK_BOM; + } + break; + default: + if (ptr[0] == '\0') { + /* 0 isn't a legal data character. Furthermore a document + entity can only start with ASCII characters. So the only + way this can fail to be big-endian UTF-16 if it it's an + external parsed general entity that's labelled as + UTF-16LE. + */ + if (state == XML_CONTENT_STATE && INIT_ENC_INDEX(enc) == UTF_16LE_ENC) + break; + *encPtr = encodingTable[UTF_16BE_ENC]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); + } + else if (ptr[1] == '\0') { + /* We could recover here in the case: + - parsing an external entity + - second byte is 0 + - no externally specified encoding + - no encoding declaration + by assuming UTF-16LE. But we don't, because this would mean when + presented just with a single byte, we couldn't reliably determine + whether we needed further bytes. + */ + if (state == XML_CONTENT_STATE) + break; + *encPtr = encodingTable[UTF_16LE_ENC]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); + } + break; + } + } + *encPtr = encodingTable[INIT_ENC_INDEX(enc)]; + return XmlTok(*encPtr, state, ptr, end, nextTokPtr); +} + + +#define NS(x) x +#define ns(x) x +#define XML_TOK_NS_C +#include "xmltok_ns.c" +#undef XML_TOK_NS_C +#undef NS +#undef ns + +#ifdef XML_NS + +#define NS(x) x ## NS +#define ns(x) x ## _ns + +#define XML_TOK_NS_C +#include "xmltok_ns.c" +#undef XML_TOK_NS_C + +#undef NS +#undef ns + +ENCODING * +XmlInitUnknownEncodingNS(void *mem, + int *table, + CONVERTER convert, + void *userData) +{ + ENCODING *enc = XmlInitUnknownEncoding(mem, table, convert, userData); + if (enc) + ((struct normal_encoding *)enc)->type[ASCII_COLON] = BT_COLON; + return enc; +} + +#endif /* XML_NS */ diff --git a/gpr/source/lib/expat_lib/xmltok.h b/gpr/source/lib/expat_lib/xmltok.h new file mode 100644 index 0000000..ca867aa --- /dev/null +++ b/gpr/source/lib/expat_lib/xmltok.h @@ -0,0 +1,316 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +#ifndef XmlTok_INCLUDED +#define XmlTok_INCLUDED 1 + +#ifdef __cplusplus +extern "C" { +#endif + +/* The following token may be returned by XmlContentTok */ +#define XML_TOK_TRAILING_RSQB -5 /* ] or ]] at the end of the scan; might be + start of illegal ]]> sequence */ +/* The following tokens may be returned by both XmlPrologTok and + XmlContentTok. +*/ +#define XML_TOK_NONE -4 /* The string to be scanned is empty */ +#define XML_TOK_TRAILING_CR -3 /* A CR at the end of the scan; + might be part of CRLF sequence */ +#define XML_TOK_PARTIAL_CHAR -2 /* only part of a multibyte sequence */ +#define XML_TOK_PARTIAL -1 /* only part of a token */ +#define XML_TOK_INVALID 0 + +/* The following tokens are returned by XmlContentTok; some are also + returned by XmlAttributeValueTok, XmlEntityTok, XmlCdataSectionTok. +*/ +#define XML_TOK_START_TAG_WITH_ATTS 1 +#define XML_TOK_START_TAG_NO_ATTS 2 +#define XML_TOK_EMPTY_ELEMENT_WITH_ATTS 3 /* empty element tag <e/> */ +#define XML_TOK_EMPTY_ELEMENT_NO_ATTS 4 +#define XML_TOK_END_TAG 5 +#define XML_TOK_DATA_CHARS 6 +#define XML_TOK_DATA_NEWLINE 7 +#define XML_TOK_CDATA_SECT_OPEN 8 +#define XML_TOK_ENTITY_REF 9 +#define XML_TOK_CHAR_REF 10 /* numeric character reference */ + +/* The following tokens may be returned by both XmlPrologTok and + XmlContentTok. +*/ +#define XML_TOK_PI 11 /* processing instruction */ +#define XML_TOK_XML_DECL 12 /* XML decl or text decl */ +#define XML_TOK_COMMENT 13 +#define XML_TOK_BOM 14 /* Byte order mark */ + +/* The following tokens are returned only by XmlPrologTok */ +#define XML_TOK_PROLOG_S 15 +#define XML_TOK_DECL_OPEN 16 /* <!foo */ +#define XML_TOK_DECL_CLOSE 17 /* > */ +#define XML_TOK_NAME 18 +#define XML_TOK_NMTOKEN 19 +#define XML_TOK_POUND_NAME 20 /* #name */ +#define XML_TOK_OR 21 /* | */ +#define XML_TOK_PERCENT 22 +#define XML_TOK_OPEN_PAREN 23 +#define XML_TOK_CLOSE_PAREN 24 +#define XML_TOK_OPEN_BRACKET 25 +#define XML_TOK_CLOSE_BRACKET 26 +#define XML_TOK_LITERAL 27 +#define XML_TOK_PARAM_ENTITY_REF 28 +#define XML_TOK_INSTANCE_START 29 + +/* The following occur only in element type declarations */ +#define XML_TOK_NAME_QUESTION 30 /* name? */ +#define XML_TOK_NAME_ASTERISK 31 /* name* */ +#define XML_TOK_NAME_PLUS 32 /* name+ */ +#define XML_TOK_COND_SECT_OPEN 33 /* <![ */ +#define XML_TOK_COND_SECT_CLOSE 34 /* ]]> */ +#define XML_TOK_CLOSE_PAREN_QUESTION 35 /* )? */ +#define XML_TOK_CLOSE_PAREN_ASTERISK 36 /* )* */ +#define XML_TOK_CLOSE_PAREN_PLUS 37 /* )+ */ +#define XML_TOK_COMMA 38 + +/* The following token is returned only by XmlAttributeValueTok */ +#define XML_TOK_ATTRIBUTE_VALUE_S 39 + +/* The following token is returned only by XmlCdataSectionTok */ +#define XML_TOK_CDATA_SECT_CLOSE 40 + +/* With namespace processing this is returned by XmlPrologTok for a + name with a colon. +*/ +#define XML_TOK_PREFIXED_NAME 41 + +#ifdef XML_DTD +#define XML_TOK_IGNORE_SECT 42 +#endif /* XML_DTD */ + +#ifdef XML_DTD +#define XML_N_STATES 4 +#else /* not XML_DTD */ +#define XML_N_STATES 3 +#endif /* not XML_DTD */ + +#define XML_PROLOG_STATE 0 +#define XML_CONTENT_STATE 1 +#define XML_CDATA_SECTION_STATE 2 +#ifdef XML_DTD +#define XML_IGNORE_SECTION_STATE 3 +#endif /* XML_DTD */ + +#define XML_N_LITERAL_TYPES 2 +#define XML_ATTRIBUTE_VALUE_LITERAL 0 +#define XML_ENTITY_VALUE_LITERAL 1 + +/* The size of the buffer passed to XmlUtf8Encode must be at least this. */ +#define XML_UTF8_ENCODE_MAX 4 +/* The size of the buffer passed to XmlUtf16Encode must be at least this. */ +#define XML_UTF16_ENCODE_MAX 2 + +typedef struct position { + /* first line and first column are 0 not 1 */ + XML_Size lineNumber; + XML_Size columnNumber; +} POSITION; + +typedef struct { + const char *name; + const char *valuePtr; + const char *valueEnd; + char normalized; +} ATTRIBUTE; + +struct encoding; +typedef struct encoding ENCODING; + +typedef int (PTRCALL *SCANNER)(const ENCODING *, + const char *, + const char *, + const char **); + +struct encoding { + SCANNER scanners[XML_N_STATES]; + SCANNER literalScanners[XML_N_LITERAL_TYPES]; + int (PTRCALL *sameName)(const ENCODING *, + const char *, + const char *); + int (PTRCALL *nameMatchesAscii)(const ENCODING *, + const char *, + const char *, + const char *); + int (PTRFASTCALL *nameLength)(const ENCODING *, const char *); + const char *(PTRFASTCALL *skipS)(const ENCODING *, const char *); + int (PTRCALL *getAtts)(const ENCODING *enc, + const char *ptr, + int attsMax, + ATTRIBUTE *atts); + int (PTRFASTCALL *charRefNumber)(const ENCODING *enc, const char *ptr); + int (PTRCALL *predefinedEntityName)(const ENCODING *, + const char *, + const char *); + void (PTRCALL *updatePosition)(const ENCODING *, + const char *ptr, + const char *end, + POSITION *); + int (PTRCALL *isPublicId)(const ENCODING *enc, + const char *ptr, + const char *end, + const char **badPtr); + void (PTRCALL *utf8Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, + char **toP, + const char *toLim); + void (PTRCALL *utf16Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, + unsigned short **toP, + const unsigned short *toLim); + int minBytesPerChar; + char isUtf8; + char isUtf16; +}; + +/* Scan the string starting at ptr until the end of the next complete + token, but do not scan past eptr. Return an integer giving the + type of token. + + Return XML_TOK_NONE when ptr == eptr; nextTokPtr will not be set. + + Return XML_TOK_PARTIAL when the string does not contain a complete + token; nextTokPtr will not be set. + + Return XML_TOK_INVALID when the string does not start a valid + token; nextTokPtr will be set to point to the character which made + the token invalid. + + Otherwise the string starts with a valid token; nextTokPtr will be + set to point to the character following the end of that token. + + Each data character counts as a single token, but adjacent data + characters may be returned together. Similarly for characters in + the prolog outside literals, comments and processing instructions. +*/ + + +#define XmlTok(enc, state, ptr, end, nextTokPtr) \ + (((enc)->scanners[state])(enc, ptr, end, nextTokPtr)) + +#define XmlPrologTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_PROLOG_STATE, ptr, end, nextTokPtr) + +#define XmlContentTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_CONTENT_STATE, ptr, end, nextTokPtr) + +#define XmlCdataSectionTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_CDATA_SECTION_STATE, ptr, end, nextTokPtr) + +#ifdef XML_DTD + +#define XmlIgnoreSectionTok(enc, ptr, end, nextTokPtr) \ + XmlTok(enc, XML_IGNORE_SECTION_STATE, ptr, end, nextTokPtr) + +#endif /* XML_DTD */ + +/* This is used for performing a 2nd-level tokenization on the content + of a literal that has already been returned by XmlTok. +*/ +#define XmlLiteralTok(enc, literalType, ptr, end, nextTokPtr) \ + (((enc)->literalScanners[literalType])(enc, ptr, end, nextTokPtr)) + +#define XmlAttributeValueTok(enc, ptr, end, nextTokPtr) \ + XmlLiteralTok(enc, XML_ATTRIBUTE_VALUE_LITERAL, ptr, end, nextTokPtr) + +#define XmlEntityValueTok(enc, ptr, end, nextTokPtr) \ + XmlLiteralTok(enc, XML_ENTITY_VALUE_LITERAL, ptr, end, nextTokPtr) + +#define XmlSameName(enc, ptr1, ptr2) (((enc)->sameName)(enc, ptr1, ptr2)) + +#define XmlNameMatchesAscii(enc, ptr1, end1, ptr2) \ + (((enc)->nameMatchesAscii)(enc, ptr1, end1, ptr2)) + +#define XmlNameLength(enc, ptr) \ + (((enc)->nameLength)(enc, ptr)) + +#define XmlSkipS(enc, ptr) \ + (((enc)->skipS)(enc, ptr)) + +#define XmlGetAttributes(enc, ptr, attsMax, atts) \ + (((enc)->getAtts)(enc, ptr, attsMax, atts)) + +#define XmlCharRefNumber(enc, ptr) \ + (((enc)->charRefNumber)(enc, ptr)) + +#define XmlPredefinedEntityName(enc, ptr, end) \ + (((enc)->predefinedEntityName)(enc, ptr, end)) + +#define XmlUpdatePosition(enc, ptr, end, pos) \ + (((enc)->updatePosition)(enc, ptr, end, pos)) + +#define XmlIsPublicId(enc, ptr, end, badPtr) \ + (((enc)->isPublicId)(enc, ptr, end, badPtr)) + +#define XmlUtf8Convert(enc, fromP, fromLim, toP, toLim) \ + (((enc)->utf8Convert)(enc, fromP, fromLim, toP, toLim)) + +#define XmlUtf16Convert(enc, fromP, fromLim, toP, toLim) \ + (((enc)->utf16Convert)(enc, fromP, fromLim, toP, toLim)) + +typedef struct { + ENCODING initEnc; + const ENCODING **encPtr; +} INIT_ENCODING; + +int XmlParseXmlDecl(int isGeneralTextEntity, + const ENCODING *enc, + const char *ptr, + const char *end, + const char **badPtr, + const char **versionPtr, + const char **versionEndPtr, + const char **encodingNamePtr, + const ENCODING **namedEncodingPtr, + int *standalonePtr); + +int XmlInitEncoding(INIT_ENCODING *, const ENCODING **, const char *name); +const ENCODING *XmlGetUtf8InternalEncoding(void); +const ENCODING *XmlGetUtf16InternalEncoding(void); +int FASTCALL XmlUtf8Encode(int charNumber, char *buf); +int FASTCALL XmlUtf16Encode(int charNumber, unsigned short *buf); +int XmlSizeOfUnknownEncoding(void); + + +typedef int (XMLCALL *CONVERTER) (void *userData, const char *p); + +ENCODING * +XmlInitUnknownEncoding(void *mem, + int *table, + CONVERTER convert, + void *userData); + +int XmlParseXmlDeclNS(int isGeneralTextEntity, + const ENCODING *enc, + const char *ptr, + const char *end, + const char **badPtr, + const char **versionPtr, + const char **versionEndPtr, + const char **encodingNamePtr, + const ENCODING **namedEncodingPtr, + int *standalonePtr); + +int XmlInitEncodingNS(INIT_ENCODING *, const ENCODING **, const char *name); +const ENCODING *XmlGetUtf8InternalEncodingNS(void); +const ENCODING *XmlGetUtf16InternalEncodingNS(void); +ENCODING * +XmlInitUnknownEncodingNS(void *mem, + int *table, + CONVERTER convert, + void *userData); +#ifdef __cplusplus +} +#endif + +#endif /* not XmlTok_INCLUDED */ diff --git a/gpr/source/lib/expat_lib/xmltok_impl.c b/gpr/source/lib/expat_lib/xmltok_impl.c new file mode 100644 index 0000000..41679ea --- /dev/null +++ b/gpr/source/lib/expat_lib/xmltok_impl.c @@ -0,0 +1,1797 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +/* This file is included! */ +#ifdef XML_TOK_IMPL_C + +#ifndef IS_INVALID_CHAR +#define IS_INVALID_CHAR(enc, ptr, n) (0) +#endif + +#define INVALID_LEAD_CASE(n, ptr, nextTokPtr) \ + case BT_LEAD ## n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_INVALID_CHAR(enc, ptr, n)) { \ + *(nextTokPtr) = (ptr); \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; + +#define INVALID_CASES(ptr, nextTokPtr) \ + INVALID_LEAD_CASE(2, ptr, nextTokPtr) \ + INVALID_LEAD_CASE(3, ptr, nextTokPtr) \ + INVALID_LEAD_CASE(4, ptr, nextTokPtr) \ + case BT_NONXML: \ + case BT_MALFORM: \ + case BT_TRAIL: \ + *(nextTokPtr) = (ptr); \ + return XML_TOK_INVALID; + +#define CHECK_NAME_CASE(n, enc, ptr, end, nextTokPtr) \ + case BT_LEAD ## n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (!IS_NAME_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; + +#define CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) \ + case BT_NONASCII: \ + if (!IS_NAME_CHAR_MINBPC(enc, ptr)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + __attribute((fallthrough)); \ + case BT_NMSTRT: \ + case BT_HEX: \ + case BT_DIGIT: \ + case BT_NAME: \ + case BT_MINUS: \ + ptr += MINBPC(enc); \ + break; \ + CHECK_NAME_CASE(2, enc, ptr, end, nextTokPtr) \ + CHECK_NAME_CASE(3, enc, ptr, end, nextTokPtr) \ + CHECK_NAME_CASE(4, enc, ptr, end, nextTokPtr) + +#define CHECK_NMSTRT_CASE(n, enc, ptr, end, nextTokPtr) \ + case BT_LEAD ## n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (!IS_NMSTRT_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + ptr += n; \ + break; + +#define CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) \ + case BT_NONASCII: \ + if (!IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; \ + } \ + __attribute((fallthrough)); \ + case BT_NMSTRT: \ + case BT_HEX: \ + ptr += MINBPC(enc); \ + break; \ + CHECK_NMSTRT_CASE(2, enc, ptr, end, nextTokPtr) \ + CHECK_NMSTRT_CASE(3, enc, ptr, end, nextTokPtr) \ + CHECK_NMSTRT_CASE(4, enc, ptr, end, nextTokPtr) + +#ifndef PREFIX +#define PREFIX(ident) ident +#endif + +/* ptr points to character following "<!-" */ + +static int PTRCALL +PREFIX(scanComment)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr != end) { + if (!CHAR_MATCHES(enc, ptr, ASCII_MINUS)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + ptr += MINBPC(enc); + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + INVALID_CASES(ptr, nextTokPtr) + case BT_MINUS: + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_MINUS)) { + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_COMMENT; + } + break; + default: + ptr += MINBPC(enc); + break; + } + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "<!" */ + +static int PTRCALL +PREFIX(scanDecl)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + case BT_MINUS: + return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_LSQB: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_COND_SECT_OPEN; + case BT_NMSTRT: + case BT_HEX: + ptr += MINBPC(enc); + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_PERCNT: + if (ptr + MINBPC(enc) == end) + return XML_TOK_PARTIAL; + /* don't allow <!ENTITY% foo "whatever"> */ + switch (BYTE_TYPE(enc, ptr + MINBPC(enc))) { + case BT_S: case BT_CR: case BT_LF: case BT_PERCNT: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + FALL_THROUGH; + /* fall through */ + case BT_S: case BT_CR: case BT_LF: + *nextTokPtr = ptr; + return XML_TOK_DECL_OPEN; + case BT_NMSTRT: + case BT_HEX: + ptr += MINBPC(enc); + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(checkPiTarget)(const ENCODING *enc, const char *ptr, + const char *end, int *tokPtr) +{ + int upper = 0; + *tokPtr = XML_TOK_PI; + if (end - ptr != MINBPC(enc)*3) + return 1; + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_x: + break; + case ASCII_X: + upper = 1; + break; + default: + return 1; + } + ptr += MINBPC(enc); + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_m: + break; + case ASCII_M: + upper = 1; + break; + default: + return 1; + } + ptr += MINBPC(enc); + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_l: + break; + case ASCII_L: + upper = 1; + break; + default: + return 1; + } + if (upper) + return 0; + *tokPtr = XML_TOK_XML_DECL; + return 1; +} + +/* ptr points to character following "<?" */ + +static int PTRCALL +PREFIX(scanPi)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + int tok; + const char *target = ptr; + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_S: case BT_CR: case BT_LF: + if (!PREFIX(checkPiTarget)(enc, target, ptr, &tok)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + ptr += MINBPC(enc); + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + INVALID_CASES(ptr, nextTokPtr) + case BT_QUEST: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr + MINBPC(enc); + return tok; + } + break; + default: + ptr += MINBPC(enc); + break; + } + } + return XML_TOK_PARTIAL; + case BT_QUEST: + if (!PREFIX(checkPiTarget)(enc, target, ptr, &tok)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr + MINBPC(enc); + return tok; + } + FALL_THROUGH; + /* fall through */ + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(scanCdataSection)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + static const char CDATA_LSQB[] = { ASCII_C, ASCII_D, ASCII_A, + ASCII_T, ASCII_A, ASCII_LSQB }; + int i; + /* CDATA[ */ + if (end - ptr < 6 * MINBPC(enc)) + return XML_TOK_PARTIAL; + for (i = 0; i < 6; i++, ptr += MINBPC(enc)) { + if (!CHAR_MATCHES(enc, ptr, CDATA_LSQB[i])) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + *nextTokPtr = ptr; + return XML_TOK_CDATA_SECT_OPEN; +} + +static int PTRCALL +PREFIX(cdataSectionTok)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_NONE; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + if (n == 0) + return XML_TOK_PARTIAL; + end = ptr + n; + } + } + switch (BYTE_TYPE(enc, ptr)) { + case BT_RSQB: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB)) + break; + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + ptr -= MINBPC(enc); + break; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CDATA_SECT_CLOSE; + case BT_CR: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + case BT_LF: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + INVALID_CASES(ptr, nextTokPtr) + default: + ptr += MINBPC(enc); + break; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: \ + if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_DATA_CHARS; \ + } \ + ptr += n; \ + break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_NONXML: + case BT_MALFORM: + case BT_TRAIL: + case BT_CR: + case BT_LF: + case BT_RSQB: + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +/* ptr points to character following "</" */ + +static int PTRCALL +PREFIX(scanEndTag)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_S: case BT_CR: case BT_LF: + for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: case BT_CR: case BT_LF: + break; + case BT_GT: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_END_TAG; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +#ifdef XML_NS + case BT_COLON: + /* no need to check qname syntax here, + since end-tag must match exactly */ + ptr += MINBPC(enc); + break; +#endif + case BT_GT: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_END_TAG; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "&#X" */ + +static int PTRCALL +PREFIX(scanHexCharRef)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + case BT_HEX: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + case BT_HEX: + break; + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CHAR_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "&#" */ + +static int PTRCALL +PREFIX(scanCharRef)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + if (ptr != end) { + if (CHAR_MATCHES(enc, ptr, ASCII_x)) + return PREFIX(scanHexCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + for (ptr += MINBPC(enc); ptr != end; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + break; + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CHAR_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "&" */ + +static int PTRCALL +PREFIX(scanRef)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_NUM: + return PREFIX(scanCharRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_ENTITY_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following first character of attribute name */ + +static int PTRCALL +PREFIX(scanAtts)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ +#ifdef XML_NS + int hadColon = 0; +#endif + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) +#ifdef XML_NS + case BT_COLON: + if (hadColon) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + hadColon = 1; + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + break; +#endif + case BT_S: case BT_CR: case BT_LF: + for (;;) { + int t; + + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + t = BYTE_TYPE(enc, ptr); + if (t == BT_EQUALS) + break; + switch (t) { + case BT_S: + case BT_LF: + case BT_CR: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + FALL_THROUGH; + /* fall through */ + case BT_EQUALS: + { + int open; +#ifdef XML_NS + hadColon = 0; +#endif + for (;;) { + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + open = BYTE_TYPE(enc, ptr); + if (open == BT_QUOT || open == BT_APOS) + break; + switch (open) { + case BT_S: + case BT_LF: + case BT_CR: + break; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + ptr += MINBPC(enc); + /* in attribute value */ + for (;;) { + int t; + if (ptr == end) + return XML_TOK_PARTIAL; + t = BYTE_TYPE(enc, ptr); + if (t == open) + break; + switch (t) { + INVALID_CASES(ptr, nextTokPtr) + case BT_AMP: + { + int tok = PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, &ptr); + if (tok <= 0) { + if (tok == XML_TOK_INVALID) + *nextTokPtr = ptr; + return tok; + } + break; + } + case BT_LT: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + default: + ptr += MINBPC(enc); + break; + } + } + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: + case BT_CR: + case BT_LF: + break; + case BT_SOL: + goto sol; + case BT_GT: + goto gt; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + /* ptr points to closing quote */ + for (;;) { + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_S: case BT_CR: case BT_LF: + continue; + case BT_GT: + gt: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_START_TAG_WITH_ATTS; + case BT_SOL: + sol: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_EMPTY_ELEMENT_WITH_ATTS; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + break; + } + break; + } + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +/* ptr points to character following "<" */ + +static int PTRCALL +PREFIX(scanLt)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ +#ifdef XML_NS + int hadColon; +#endif + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_EXCL: + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + case BT_MINUS: + return PREFIX(scanComment)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_LSQB: + return PREFIX(scanCdataSection)(enc, ptr + MINBPC(enc), + end, nextTokPtr); + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + case BT_QUEST: + return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_SOL: + return PREFIX(scanEndTag)(enc, ptr + MINBPC(enc), end, nextTokPtr); + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } +#ifdef XML_NS + hadColon = 0; +#endif + /* we have a start-tag */ + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) +#ifdef XML_NS + case BT_COLON: + if (hadColon) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + hadColon = 1; + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + break; +#endif + case BT_S: case BT_CR: case BT_LF: + { + ptr += MINBPC(enc); + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_GT: + goto gt; + case BT_SOL: + goto sol; + case BT_S: case BT_CR: case BT_LF: + ptr += MINBPC(enc); + continue; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + return PREFIX(scanAtts)(enc, ptr, end, nextTokPtr); + } + return XML_TOK_PARTIAL; + } + case BT_GT: + gt: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_START_TAG_NO_ATTS; + case BT_SOL: + sol: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_EMPTY_ELEMENT_NO_ATTS; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(contentTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_NONE; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + if (n == 0) + return XML_TOK_PARTIAL; + end = ptr + n; + } + } + switch (BYTE_TYPE(enc, ptr)) { + case BT_LT: + return PREFIX(scanLt)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_AMP: + return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_CR: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_TRAILING_CR; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + case BT_LF: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + case BT_RSQB: + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_TRAILING_RSQB; + if (!CHAR_MATCHES(enc, ptr, ASCII_RSQB)) + break; + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_TRAILING_RSQB; + if (!CHAR_MATCHES(enc, ptr, ASCII_GT)) { + ptr -= MINBPC(enc); + break; + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + INVALID_CASES(ptr, nextTokPtr) + default: + ptr += MINBPC(enc); + break; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: \ + if (end - ptr < n || IS_INVALID_CHAR(enc, ptr, n)) { \ + *nextTokPtr = ptr; \ + return XML_TOK_DATA_CHARS; \ + } \ + ptr += n; \ + break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_RSQB: + if (ptr + MINBPC(enc) != end) { + if (!CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_RSQB)) { + ptr += MINBPC(enc); + break; + } + if (ptr + 2*MINBPC(enc) != end) { + if (!CHAR_MATCHES(enc, ptr + 2*MINBPC(enc), ASCII_GT)) { + ptr += MINBPC(enc); + break; + } + *nextTokPtr = ptr + 2*MINBPC(enc); + return XML_TOK_INVALID; + } + } + FALL_THROUGH; + /* fall through */ + case BT_AMP: + case BT_LT: + case BT_NONXML: + case BT_MALFORM: + case BT_TRAIL: + case BT_CR: + case BT_LF: + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +/* ptr points to character following "%" */ + +static int PTRCALL +PREFIX(scanPercent)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + case BT_S: case BT_LF: case BT_CR: case BT_PERCNT: + *nextTokPtr = ptr; + return XML_TOK_PERCENT; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_SEMI: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_PARAM_ENTITY_REF; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(scanPoundName)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NMSTRT_CASES(enc, ptr, end, nextTokPtr) + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_CR: case BT_LF: case BT_S: + case BT_RPAR: case BT_GT: case BT_PERCNT: case BT_VERBAR: + *nextTokPtr = ptr; + return XML_TOK_POUND_NAME; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return -XML_TOK_POUND_NAME; +} + +static int PTRCALL +PREFIX(scanLit)(int open, const ENCODING *enc, + const char *ptr, const char *end, + const char **nextTokPtr) +{ + while (ptr != end) { + int t = BYTE_TYPE(enc, ptr); + switch (t) { + INVALID_CASES(ptr, nextTokPtr) + case BT_QUOT: + case BT_APOS: + ptr += MINBPC(enc); + if (t != open) + break; + if (ptr == end) + return -XML_TOK_LITERAL; + *nextTokPtr = ptr; + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: case BT_CR: case BT_LF: + case BT_GT: case BT_PERCNT: case BT_LSQB: + return XML_TOK_LITERAL; + default: + return XML_TOK_INVALID; + } + default: + ptr += MINBPC(enc); + break; + } + } + return XML_TOK_PARTIAL; +} + +static int PTRCALL +PREFIX(prologTok)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + int tok; + if (ptr == end) + return XML_TOK_NONE; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + if (n == 0) + return XML_TOK_PARTIAL; + end = ptr + n; + } + } + switch (BYTE_TYPE(enc, ptr)) { + case BT_QUOT: + return PREFIX(scanLit)(BT_QUOT, enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_APOS: + return PREFIX(scanLit)(BT_APOS, enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_LT: + { + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_PARTIAL; + switch (BYTE_TYPE(enc, ptr)) { + case BT_EXCL: + return PREFIX(scanDecl)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_QUEST: + return PREFIX(scanPi)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_NMSTRT: + case BT_HEX: + case BT_NONASCII: + case BT_LEAD2: + case BT_LEAD3: + case BT_LEAD4: + *nextTokPtr = ptr - MINBPC(enc); + return XML_TOK_INSTANCE_START; + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + case BT_CR: + if (ptr + MINBPC(enc) == end) { + *nextTokPtr = end; + /* indicate that this might be part of a CR/LF pair */ + return -XML_TOK_PROLOG_S; + } + FALL_THROUGH; + /* fall through */ + case BT_S: case BT_LF: + for (;;) { + ptr += MINBPC(enc); + if (ptr == end) + break; + switch (BYTE_TYPE(enc, ptr)) { + case BT_S: case BT_LF: + break; + case BT_CR: + /* don't split CR/LF pair */ + if (ptr + MINBPC(enc) != end) + break; + FALL_THROUGH; + /* fall through */ + default: + *nextTokPtr = ptr; + return XML_TOK_PROLOG_S; + } + } + *nextTokPtr = ptr; + return XML_TOK_PROLOG_S; + case BT_PERCNT: + return PREFIX(scanPercent)(enc, ptr + MINBPC(enc), end, nextTokPtr); + case BT_COMMA: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_COMMA; + case BT_LSQB: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_OPEN_BRACKET; + case BT_RSQB: + ptr += MINBPC(enc); + if (ptr == end) + return -XML_TOK_CLOSE_BRACKET; + if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) { + if (ptr + MINBPC(enc) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_GT)) { + *nextTokPtr = ptr + 2*MINBPC(enc); + return XML_TOK_COND_SECT_CLOSE; + } + } + *nextTokPtr = ptr; + return XML_TOK_CLOSE_BRACKET; + case BT_LPAR: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_OPEN_PAREN; + case BT_RPAR: + ptr += MINBPC(enc); + if (ptr == end) + return -XML_TOK_CLOSE_PAREN; + switch (BYTE_TYPE(enc, ptr)) { + case BT_AST: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CLOSE_PAREN_ASTERISK; + case BT_QUEST: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CLOSE_PAREN_QUESTION; + case BT_PLUS: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_CLOSE_PAREN_PLUS; + case BT_CR: case BT_LF: case BT_S: + case BT_GT: case BT_COMMA: case BT_VERBAR: + case BT_RPAR: + *nextTokPtr = ptr; + return XML_TOK_CLOSE_PAREN; + } + *nextTokPtr = ptr; + return XML_TOK_INVALID; + case BT_VERBAR: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_OR; + case BT_GT: + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DECL_CLOSE; + case BT_NUM: + return PREFIX(scanPoundName)(enc, ptr + MINBPC(enc), end, nextTokPtr); +#define LEAD_CASE(n) \ + case BT_LEAD ## n: \ + if (end - ptr < n) \ + return XML_TOK_PARTIAL_CHAR; \ + if (IS_NMSTRT_CHAR(enc, ptr, n)) { \ + ptr += n; \ + tok = XML_TOK_NAME; \ + break; \ + } \ + if (IS_NAME_CHAR(enc, ptr, n)) { \ + ptr += n; \ + tok = XML_TOK_NMTOKEN; \ + break; \ + } \ + *nextTokPtr = ptr; \ + return XML_TOK_INVALID; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_NMSTRT: + case BT_HEX: + tok = XML_TOK_NAME; + ptr += MINBPC(enc); + break; + case BT_DIGIT: + case BT_NAME: + case BT_MINUS: +#ifdef XML_NS + case BT_COLON: +#endif + tok = XML_TOK_NMTOKEN; + ptr += MINBPC(enc); + break; + case BT_NONASCII: + if (IS_NMSTRT_CHAR_MINBPC(enc, ptr)) { + ptr += MINBPC(enc); + tok = XML_TOK_NAME; + break; + } + if (IS_NAME_CHAR_MINBPC(enc, ptr)) { + ptr += MINBPC(enc); + tok = XML_TOK_NMTOKEN; + break; + } + FALL_THROUGH; + /* fall through */ + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + case BT_GT: case BT_RPAR: case BT_COMMA: + case BT_VERBAR: case BT_LSQB: case BT_PERCNT: + case BT_S: case BT_CR: case BT_LF: + *nextTokPtr = ptr; + return tok; +#ifdef XML_NS + case BT_COLON: + ptr += MINBPC(enc); + switch (tok) { + case XML_TOK_NAME: + if (ptr == end) + return XML_TOK_PARTIAL; + tok = XML_TOK_PREFIXED_NAME; + switch (BYTE_TYPE(enc, ptr)) { + CHECK_NAME_CASES(enc, ptr, end, nextTokPtr) + default: + tok = XML_TOK_NMTOKEN; + break; + } + break; + case XML_TOK_PREFIXED_NAME: + tok = XML_TOK_NMTOKEN; + break; + } + break; +#endif + case BT_PLUS: + if (tok == XML_TOK_NMTOKEN) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_NAME_PLUS; + case BT_AST: + if (tok == XML_TOK_NMTOKEN) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_NAME_ASTERISK; + case BT_QUEST: + if (tok == XML_TOK_NMTOKEN) { + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_NAME_QUESTION; + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return -tok; +} + +static int PTRCALL +PREFIX(attributeValueTok)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + const char *start; + if (ptr == end) + return XML_TOK_NONE; + start = ptr; + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: ptr += n; break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_AMP: + if (ptr == start) + return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_LT: + /* this is for inside entity references */ + *nextTokPtr = ptr; + return XML_TOK_INVALID; + case BT_LF: + if (ptr == start) { + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_CR: + if (ptr == start) { + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_TRAILING_CR; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_S: + if (ptr == start) { + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_ATTRIBUTE_VALUE_S; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +static int PTRCALL +PREFIX(entityValueTok)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + const char *start; + if (ptr == end) + return XML_TOK_NONE; + start = ptr; + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: ptr += n; break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_AMP: + if (ptr == start) + return PREFIX(scanRef)(enc, ptr + MINBPC(enc), end, nextTokPtr); + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_PERCNT: + if (ptr == start) { + int tok = PREFIX(scanPercent)(enc, ptr + MINBPC(enc), + end, nextTokPtr); + return (tok == XML_TOK_PERCENT) ? XML_TOK_INVALID : tok; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_LF: + if (ptr == start) { + *nextTokPtr = ptr + MINBPC(enc); + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + case BT_CR: + if (ptr == start) { + ptr += MINBPC(enc); + if (ptr == end) + return XML_TOK_TRAILING_CR; + if (BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + *nextTokPtr = ptr; + return XML_TOK_DATA_NEWLINE; + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; + default: + ptr += MINBPC(enc); + break; + } + } + *nextTokPtr = ptr; + return XML_TOK_DATA_CHARS; +} + +#ifdef XML_DTD + +static int PTRCALL +PREFIX(ignoreSectionTok)(const ENCODING *enc, const char *ptr, + const char *end, const char **nextTokPtr) +{ + int level = 0; + if (MINBPC(enc) > 1) { + size_t n = end - ptr; + if (n & (MINBPC(enc) - 1)) { + n &= ~(MINBPC(enc) - 1); + end = ptr + n; + } + } + while (ptr != end) { + switch (BYTE_TYPE(enc, ptr)) { + INVALID_CASES(ptr, nextTokPtr) + case BT_LT: + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_EXCL)) { + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_LSQB)) { + ++level; + ptr += MINBPC(enc); + } + } + break; + case BT_RSQB: + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_RSQB)) { + if ((ptr += MINBPC(enc)) == end) + return XML_TOK_PARTIAL; + if (CHAR_MATCHES(enc, ptr, ASCII_GT)) { + ptr += MINBPC(enc); + if (level == 0) { + *nextTokPtr = ptr; + return XML_TOK_IGNORE_SECT; + } + --level; + } + } + break; + default: + ptr += MINBPC(enc); + break; + } + } + return XML_TOK_PARTIAL; +} + +#endif /* XML_DTD */ + +static int PTRCALL +PREFIX(isPublicId)(const ENCODING *enc, const char *ptr, const char *end, + const char **badPtr) +{ + ptr += MINBPC(enc); + end -= MINBPC(enc); + for (; ptr != end; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_DIGIT: + case BT_HEX: + case BT_MINUS: + case BT_APOS: + case BT_LPAR: + case BT_RPAR: + case BT_PLUS: + case BT_COMMA: + case BT_SOL: + case BT_EQUALS: + case BT_QUEST: + case BT_CR: + case BT_LF: + case BT_SEMI: + case BT_EXCL: + case BT_AST: + case BT_PERCNT: + case BT_NUM: +#ifdef XML_NS + case BT_COLON: +#endif + break; + case BT_S: + if (CHAR_MATCHES(enc, ptr, ASCII_TAB)) { + *badPtr = ptr; + return 0; + } + break; + case BT_NAME: + case BT_NMSTRT: + if (!(BYTE_TO_ASCII(enc, ptr) & ~0x7f)) + break; + FALL_THROUGH; + default: + switch (BYTE_TO_ASCII(enc, ptr)) { + case 0x24: /* $ */ + case 0x40: /* @ */ + break; + default: + *badPtr = ptr; + return 0; + } + break; + } + } + return 1; +} + +/* This must only be called for a well-formed start-tag or empty + element tag. Returns the number of attributes. Pointers to the + first attsMax attributes are stored in atts. +*/ + +static int PTRCALL +PREFIX(getAtts)(const ENCODING *enc, const char *ptr, + int attsMax, ATTRIBUTE *atts) +{ + enum { other, inName, inValue } state = inName; + int nAtts = 0; + int open = 0; /* defined when state == inValue; + initialization just to shut up compilers */ + + for (ptr += MINBPC(enc);; ptr += MINBPC(enc)) { + switch (BYTE_TYPE(enc, ptr)) { +#define START_NAME \ + if (state == other) { \ + if (nAtts < attsMax) { \ + atts[nAtts].name = ptr; \ + atts[nAtts].normalized = 1; \ + } \ + state = inName; \ + } +#define LEAD_CASE(n) \ + case BT_LEAD ## n: START_NAME ptr += (n - MINBPC(enc)); break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_NONASCII: + case BT_NMSTRT: + case BT_HEX: + START_NAME + break; +#undef START_NAME + case BT_QUOT: + if (state != inValue) { + if (nAtts < attsMax) + atts[nAtts].valuePtr = ptr + MINBPC(enc); + state = inValue; + open = BT_QUOT; + } + else if (open == BT_QUOT) { + state = other; + if (nAtts < attsMax) + atts[nAtts].valueEnd = ptr; + nAtts++; + } + break; + case BT_APOS: + if (state != inValue) { + if (nAtts < attsMax) + atts[nAtts].valuePtr = ptr + MINBPC(enc); + state = inValue; + open = BT_APOS; + } + else if (open == BT_APOS) { + state = other; + if (nAtts < attsMax) + atts[nAtts].valueEnd = ptr; + nAtts++; + } + break; + case BT_AMP: + if (nAtts < attsMax) + atts[nAtts].normalized = 0; + break; + case BT_S: + if (state == inName) + state = other; + else if (state == inValue + && nAtts < attsMax + && atts[nAtts].normalized + && (ptr == atts[nAtts].valuePtr + || BYTE_TO_ASCII(enc, ptr) != ASCII_SPACE + || BYTE_TO_ASCII(enc, ptr + MINBPC(enc)) == ASCII_SPACE + || BYTE_TYPE(enc, ptr + MINBPC(enc)) == open)) + atts[nAtts].normalized = 0; + break; + case BT_CR: case BT_LF: + /* This case ensures that the first attribute name is counted + Apart from that we could just change state on the quote. */ + if (state == inName) + state = other; + else if (state == inValue && nAtts < attsMax) + atts[nAtts].normalized = 0; + break; + case BT_GT: + case BT_SOL: + if (state != inValue) + return nAtts; + break; + default: + break; + } + } + /* not reached */ +} + +static int PTRFASTCALL +PREFIX(charRefNumber)(const ENCODING *enc, const char *ptr) +{ + int result = 0; + /* skip &# */ + ptr += 2*MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_x)) { + for (ptr += MINBPC(enc); + !CHAR_MATCHES(enc, ptr, ASCII_SEMI); + ptr += MINBPC(enc)) { + int c = BYTE_TO_ASCII(enc, ptr); + switch (c) { + case ASCII_0: case ASCII_1: case ASCII_2: case ASCII_3: case ASCII_4: + case ASCII_5: case ASCII_6: case ASCII_7: case ASCII_8: case ASCII_9: + result <<= 4; + result |= (c - ASCII_0); + break; + case ASCII_A: case ASCII_B: case ASCII_C: + case ASCII_D: case ASCII_E: case ASCII_F: + result <<= 4; + result += 10 + (c - ASCII_A); + break; + case ASCII_a: case ASCII_b: case ASCII_c: + case ASCII_d: case ASCII_e: case ASCII_f: + result <<= 4; + result += 10 + (c - ASCII_a); + break; + } + if (result >= 0x110000) + return -1; + } + } + else { + for (; !CHAR_MATCHES(enc, ptr, ASCII_SEMI); ptr += MINBPC(enc)) { + int c = BYTE_TO_ASCII(enc, ptr); + result *= 10; + result += (c - ASCII_0); + if (result >= 0x110000) + return -1; + } + } + return checkCharRefNumber(result); +} + +static int PTRCALL +PREFIX(predefinedEntityName)(const ENCODING *enc, const char *ptr, + const char *end) +{ + switch ((end - ptr)/MINBPC(enc)) { + case 2: + if (CHAR_MATCHES(enc, ptr + MINBPC(enc), ASCII_t)) { + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_l: + return ASCII_LT; + case ASCII_g: + return ASCII_GT; + } + } + break; + case 3: + if (CHAR_MATCHES(enc, ptr, ASCII_a)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_m)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_p)) + return ASCII_AMP; + } + } + break; + case 4: + switch (BYTE_TO_ASCII(enc, ptr)) { + case ASCII_q: + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_u)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_o)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_t)) + return ASCII_QUOT; + } + } + break; + case ASCII_a: + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_p)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_o)) { + ptr += MINBPC(enc); + if (CHAR_MATCHES(enc, ptr, ASCII_s)) + return ASCII_APOS; + } + } + break; + } + } + return 0; +} + +static int PTRCALL +PREFIX(sameName)(const ENCODING *enc, const char *ptr1, const char *ptr2) +{ + for (;;) { + switch (BYTE_TYPE(enc, ptr1)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: \ + if (*ptr1++ != *ptr2++) \ + return 0; + LEAD_CASE(4) + FALL_THROUGH; + LEAD_CASE(3) + FALL_THROUGH; + LEAD_CASE(2) +#undef LEAD_CASE + /* fall through */ + if (*ptr1++ != *ptr2++) + return 0; + break; + case BT_NONASCII: + case BT_NMSTRT: +#ifdef XML_NS + case BT_COLON: +#endif + case BT_HEX: + case BT_DIGIT: + case BT_NAME: + case BT_MINUS: + if (*ptr2++ != *ptr1++) + return 0; + if (MINBPC(enc) > 1) { + if (*ptr2++ != *ptr1++) + return 0; + if (MINBPC(enc) > 2) { + if (*ptr2++ != *ptr1++) + return 0; + if (MINBPC(enc) > 3) { + if (*ptr2++ != *ptr1++) + return 0; + } + } + } + break; + default: + if (MINBPC(enc) == 1 && *ptr1 == *ptr2) + return 1; + switch (BYTE_TYPE(enc, ptr2)) { + case BT_LEAD2: + case BT_LEAD3: + case BT_LEAD4: + case BT_NONASCII: + case BT_NMSTRT: +#ifdef XML_NS + case BT_COLON: +#endif + case BT_HEX: + case BT_DIGIT: + case BT_NAME: + case BT_MINUS: + return 0; + default: + return 1; + } + } + } + /* not reached */ +} + +static int PTRCALL +PREFIX(nameMatchesAscii)(const ENCODING *enc, const char *ptr1, + const char *end1, const char *ptr2) +{ + for (; *ptr2; ptr1 += MINBPC(enc), ptr2++) { + if (ptr1 == end1) + return 0; + if (!CHAR_MATCHES(enc, ptr1, *ptr2)) + return 0; + } + return ptr1 == end1; +} + +static int PTRFASTCALL +PREFIX(nameLength)(const ENCODING *enc, const char *ptr) +{ + const char *start = ptr; + for (;;) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: ptr += n; break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_NONASCII: + case BT_NMSTRT: +#ifdef XML_NS + case BT_COLON: +#endif + case BT_HEX: + case BT_DIGIT: + case BT_NAME: + case BT_MINUS: + ptr += MINBPC(enc); + break; + default: + return (int)(ptr - start); + } + } +} + +static const char * PTRFASTCALL +PREFIX(skipS)(const ENCODING *enc, const char *ptr) +{ + for (;;) { + switch (BYTE_TYPE(enc, ptr)) { + case BT_LF: + case BT_CR: + case BT_S: + ptr += MINBPC(enc); + break; + default: + return ptr; + } + } +} + +static void PTRCALL +PREFIX(updatePosition)(const ENCODING *enc, + const char *ptr, + const char *end, + POSITION *pos) +{ + while (ptr < end) { + switch (BYTE_TYPE(enc, ptr)) { +#define LEAD_CASE(n) \ + case BT_LEAD ## n: \ + ptr += n; \ + break; + LEAD_CASE(2) LEAD_CASE(3) LEAD_CASE(4) +#undef LEAD_CASE + case BT_LF: + pos->columnNumber = (XML_Size)-1; + pos->lineNumber++; + ptr += MINBPC(enc); + break; + case BT_CR: + pos->lineNumber++; + ptr += MINBPC(enc); + if (ptr != end && BYTE_TYPE(enc, ptr) == BT_LF) + ptr += MINBPC(enc); + pos->columnNumber = (XML_Size)-1; + break; + default: + ptr += MINBPC(enc); + break; + } + pos->columnNumber++; + } +} + +#undef DO_LEAD_CASE +#undef MULTIBYTE_CASES +#undef INVALID_CASES +#undef CHECK_NAME_CASE +#undef CHECK_NAME_CASES +#undef CHECK_NMSTRT_CASE +#undef CHECK_NMSTRT_CASES + +#endif /* XML_TOK_IMPL_C */ diff --git a/gpr/source/lib/expat_lib/xmltok_impl.h b/gpr/source/lib/expat_lib/xmltok_impl.h new file mode 100644 index 0000000..da0ea60 --- /dev/null +++ b/gpr/source/lib/expat_lib/xmltok_impl.h @@ -0,0 +1,46 @@ +/* +Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd +See the file COPYING for copying permission. +*/ + +enum { + BT_NONXML, + BT_MALFORM, + BT_LT, + BT_AMP, + BT_RSQB, + BT_LEAD2, + BT_LEAD3, + BT_LEAD4, + BT_TRAIL, + BT_CR, + BT_LF, + BT_GT, + BT_QUOT, + BT_APOS, + BT_EQUALS, + BT_QUEST, + BT_EXCL, + BT_SOL, + BT_SEMI, + BT_NUM, + BT_LSQB, + BT_S, + BT_NMSTRT, + BT_COLON, + BT_HEX, + BT_DIGIT, + BT_NAME, + BT_MINUS, + BT_OTHER, /* known not to be a name or name start character */ + BT_NONASCII, /* might be a name or name start character */ + BT_PERCNT, + BT_LPAR, + BT_RPAR, + BT_AST, + BT_PLUS, + BT_COMMA, + BT_VERBAR +}; + +#include <stddef.h> diff --git a/gpr/source/lib/expat_lib/xmltok_ns.c b/gpr/source/lib/expat_lib/xmltok_ns.c new file mode 100644 index 0000000..c3b88fd --- /dev/null +++ b/gpr/source/lib/expat_lib/xmltok_ns.c @@ -0,0 +1,115 @@ +/* Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd + See the file COPYING for copying permission. +*/ + +/* This file is included! */ +#ifdef XML_TOK_NS_C + +const ENCODING * +NS(XmlGetUtf8InternalEncoding)(void) +{ + return &ns(internal_utf8_encoding).enc; +} + +const ENCODING * +NS(XmlGetUtf16InternalEncoding)(void) +{ +#if BYTEORDER == 1234 + return &ns(internal_little2_encoding).enc; +#elif BYTEORDER == 4321 + return &ns(internal_big2_encoding).enc; +#else + const short n = 1; + return (*(const char *)&n + ? &ns(internal_little2_encoding).enc + : &ns(internal_big2_encoding).enc); +#endif +} + +static const ENCODING * const NS(encodings)[] = { + &ns(latin1_encoding).enc, + &ns(ascii_encoding).enc, + &ns(utf8_encoding).enc, + &ns(big2_encoding).enc, + &ns(big2_encoding).enc, + &ns(little2_encoding).enc, + &ns(utf8_encoding).enc /* NO_ENC */ +}; + +static int PTRCALL +NS(initScanProlog)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + return initScan(NS(encodings), (const INIT_ENCODING *)enc, + XML_PROLOG_STATE, ptr, end, nextTokPtr); +} + +static int PTRCALL +NS(initScanContent)(const ENCODING *enc, const char *ptr, const char *end, + const char **nextTokPtr) +{ + return initScan(NS(encodings), (const INIT_ENCODING *)enc, + XML_CONTENT_STATE, ptr, end, nextTokPtr); +} + +int +NS(XmlInitEncoding)(INIT_ENCODING *p, const ENCODING **encPtr, + const char *name) +{ + int i = getEncodingIndex(name); + if (i == UNKNOWN_ENC) + return 0; + SET_INIT_ENC_INDEX(p, i); + p->initEnc.scanners[XML_PROLOG_STATE] = NS(initScanProlog); + p->initEnc.scanners[XML_CONTENT_STATE] = NS(initScanContent); + p->initEnc.updatePosition = initUpdatePosition; + p->encPtr = encPtr; + *encPtr = &(p->initEnc); + return 1; +} + +static const ENCODING * +NS(findEncoding)(const ENCODING *enc, const char *ptr, const char *end) +{ +#define ENCODING_MAX 128 + char buf[ENCODING_MAX]; + char *p = buf; + int i; + XmlUtf8Convert(enc, &ptr, end, &p, p + ENCODING_MAX - 1); + if (ptr != end) + return 0; + *p = 0; + if (streqci(buf, KW_UTF_16) && enc->minBytesPerChar == 2) + return enc; + i = getEncodingIndex(buf); + if (i == UNKNOWN_ENC) + return 0; + return NS(encodings)[i]; +} + +int +NS(XmlParseXmlDecl)(int isGeneralTextEntity, + const ENCODING *enc, + const char *ptr, + const char *end, + const char **badPtr, + const char **versionPtr, + const char **versionEndPtr, + const char **encodingName, + const ENCODING **encoding, + int *standalone) +{ + return doParseXmlDecl(NS(findEncoding), + isGeneralTextEntity, + enc, + ptr, + end, + badPtr, + versionPtr, + versionEndPtr, + encodingName, + encoding, + standalone); +} + +#endif /* XML_TOK_NS_C */ |