diff options
Diffstat (limited to 'Modules')
-rw-r--r-- | Modules/expat/Makefile.in | 158 | ||||
-rw-r--r-- | Modules/expat/ascii.h | 86 | ||||
-rw-r--r-- | Modules/expat/asciitab.h | 37 | ||||
-rw-r--r-- | Modules/expat/expat.h.in | 735 | ||||
-rw-r--r-- | Modules/expat/iasciitab.h | 38 | ||||
-rw-r--r-- | Modules/expat/latin1tab.h | 37 | ||||
-rw-r--r-- | Modules/expat/nametab.h | 150 | ||||
-rw-r--r-- | Modules/expat/utf8tab.h | 38 | ||||
-rw-r--r-- | Modules/expat/winconfig.h | 27 | ||||
-rw-r--r-- | Modules/expat/xmlparse.c | 4635 | ||||
-rw-r--r-- | Modules/expat/xmlrole.c | 1275 | ||||
-rw-r--r-- | Modules/expat/xmlrole.h | 100 | ||||
-rw-r--r-- | Modules/expat/xmltok.c | 1566 | ||||
-rw-r--r-- | Modules/expat/xmltok.h | 299 | ||||
-rw-r--r-- | Modules/expat/xmltok_impl.c | 1768 | ||||
-rw-r--r-- | Modules/expat/xmltok_impl.h | 46 | ||||
-rw-r--r-- | Modules/expat/xmltok_ns.c | 98 |
17 files changed, 11093 insertions, 0 deletions
diff --git a/Modules/expat/Makefile.in b/Modules/expat/Makefile.in new file mode 100644 index 0000000..9790739 --- /dev/null +++ b/Modules/expat/Makefile.in @@ -0,0 +1,158 @@ +################################################################ +# Process this file with top-level configure script to produce Makefile +# +# Copyright 2000 Clark Cooper +# +# This file is part of EXPAT. +# +# EXPAT is free software; you can redistribute it and/or modify it +# under the terms of the License (based on the MIT/X license) contained +# in the file COPYING that comes with this distribution. +# +# EXPAT IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +# SOFTWARE OR THE USE OR OTHER DEALINGS IN EXPAT. +# + + +SHELL = @SHELL@ + +srcdir = @srcdir@ +top_srcdir = @top_srcdir@ +VPATH = @srcdir@ +prefix = @prefix@ +exec_prefix = @exec_prefix@ + +bindir = @bindir@ +sbindir = @sbindir@ +libexecdir = @libexecdir@ +datadir = @datadir@ +sysconfdir = @sysconfdir@ +sharedstatedir = @sharedstatedir@ +localstatedir = @localstatedir@ +libdir = @libdir@ +infodir = @infodir@ +mandir = @mandir@ +includedir = @includedir@ +oldincludedir = /usr/include + +subdir = lib + +top_builddir = .. + +INSTALL = @INSTALL@ +INSTALL_PROGRAM = @INSTALL_PROGRAM@ +INSTALL_SCRIPT = @INSTALL_SCRIPT@ +INSTALL_DATA = @INSTALL_DATA@ + +host_alias = @host_alias@ +host_triplet = @host@ +AS = @AS@ +CC = @CC@ +DLLTOOL = @DLLTOOL@ +LIBTOOL = @LIBTOOL@ +LN_S = @LN_S@ +OBJDUMP = @OBJDUMP@ +PACKAGE = @PACKAGE@ +RANLIB = @RANLIB@ +VERSION = @VERSION@ + +LIBRARY = libexpat.la +SOURCES = xmlparse.c xmltok.c xmlrole.c +OBJECTS = $(SOURCES:.c=.o) +LTOBJECTS = $(SOURCES:.c=.lo) + +TEMPLATES = xmltok_impl.c xmltok_ns.c +APIHEADER = expat.h +HEADERS = ascii.h iasciitab.h utf8tab.h xmltok.h asciitab.h latin1tab.h \ + nametab.h xmldef.h xmlrole.h xmltok_impl.h + +mkinstalldirs = $(SHELL) $(top_srcdir)/conftools/mkinstalldirs +CONFIG_HEADER = ../config.h +CONFIG_CLEAN_FILES = + +INCLUDES = -I$(srcdir) -I. -I.. +DEFS = @DEFS@ -DPACKAGE='"$(PACKAGE)"' -DVERSION='"$(PACKAGE)_$(VERSION)"' + +CPPFLAGS = @CPPFLAGS@ +LDFLAGS = @LDFLAGS@ +LIBS = @LIBS@ +CFLAGS = @CFLAGS@ + +LIBREVISION = @LIBREVISION@ +LIBCURRENT = @LIBCURRENT@ +LIBAGE = @LIBAGE@ + +COMPILE = $(CC) $(DEFS) $(INCLUDES) $(CPPFLAGS) $(CFLAGS) +LTCOMPILE = $(LIBTOOL) --mode=compile $(CC) $(DEFS) $(INCLUDES) $(CPPFLAGS) $(CFLAGS) +CCLD = $(CC) +LINK = $(LIBTOOL) --mode=link $(CCLD) -version-info $(LIBCURRENT):$(LIBREVISION):$(LIBAGE) $(CFLAGS) $(LDFLAGS) -o $@ +DIST_COMMON = Makefile.in + + +DISTFILES = $(DIST_COMMON) $(SOURCES) $(TEMPLATES) $(APIHEADER) $(HEADERS) + +TAR = gtar +GZIP_ENV = --best + +all: $(LIBRARY) + +.SUFFIXES: .c .lo .o +.PHONY: all clean distclean maintainer-clean + +.c.o: + $(COMPILE) -c $< + +.c.lo: + $(LTCOMPILE) -c $< + +Makefile: $(srcdir)/Makefile.in $(top_builddir)/config.status + cd $(top_builddir) \ + && CONFIG_FILES=$(subdir)/$@ CONFIG_HEADERS= $(SHELL) ./config.status + +$(top_builddir)/config.status: $(top_builddir)/configure + cd $(top_builddir) && $(MAKE) config.status + +$(top_builddir)/config.h: $(top_builddir)/config.h.in + cd $(top_builddir) && $(MAKE) config.h + +clean: + rm -f $(LIBRARY) *.o *.lo *~ + rm -rf .libs _libs + +distclean: clean + rm -f Makefile + +maintainer-clean: distclean + +check: $(SUBDIRS) + @echo + @echo This package does not yet have a regression test. + @echo + +install: $(LIBRARY) $(APIHEADER) + $(mkinstalldirs) $(libdir) $(includedir) + $(LIBTOOL) --mode=install $(INSTALL) $(LIBRARY) $(libdir)/$(LIBRARY) + $(INSTALL_DATA) $(APIHEADER) $(includedir) + +uninstall: + $(LIBTOOL) --mode=uninstall rm -f $(libdir)/$(LIBRARY); + rm -f $(libdir)/$(APIHEADER) + +$(LIBRARY): $(LTOBJECTS) + $(LINK) -rpath $(libdir) $(LDFLAGS) $(LTOBJECTS) + +xmlparse.o \ +xmlparse.lo: xmlparse.c expat.h xmlrole.h xmltok.h $(top_builddir)/config.h + +xmlrole.o \ +xmlrole.lo: xmlrole.c ascii.h xmlrole.h $(top_builddir)/config.h + +xmltok.o \ +xmltok.lo: xmltok.c xmltok_impl.c xmltok_ns.c \ + ascii.h asciitab.h iasciitab.h latin1tab.h nametab.h utf8tab.h \ + xmltok.h xmltok_impl.h $(top_builddir)/config.h diff --git a/Modules/expat/ascii.h b/Modules/expat/ascii.h new file mode 100644 index 0000000..6376b1f --- /dev/null +++ b/Modules/expat/ascii.h @@ -0,0 +1,86 @@ +/* +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 diff --git a/Modules/expat/asciitab.h b/Modules/expat/asciitab.h new file mode 100644 index 0000000..eb445cc --- /dev/null +++ b/Modules/expat/asciitab.h @@ -0,0 +1,37 @@ +/* +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/Modules/expat/expat.h.in b/Modules/expat/expat.h.in new file mode 100644 index 0000000..7c928b1 --- /dev/null +++ b/Modules/expat/expat.h.in @@ -0,0 +1,735 @@ +/* +Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd +See the file COPYING for copying permission. +*/ + +#ifndef XmlParse_INCLUDED +#define XmlParse_INCLUDED 1 + +#include <stdlib.h> + +#ifndef XMLPARSEAPI +# if defined(__declspec) && !defined(__BEOS__) +# define XMLPARSEAPI(type) __declspec(dllimport) type __cdecl +# else +# define XMLPARSEAPI(type) type +# endif +#endif /* not defined XMLPARSEAPI */ + +#ifdef __cplusplus +extern "C" { +#endif + +typedef void *XML_Parser; + +/* Information is UTF-8 encoded. */ +typedef char XML_Char; +typedef char XML_LChar; + +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 (*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 (*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 (*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. When a namespace is not declared, +the name and prefix will be passed through without expansion. */ + +XMLPARSEAPI(XML_Parser) +XML_ParserCreateNS(const XML_Char *encoding, XML_Char namespaceSeparator); + + +/* Constructs a new parser using the memory management suit 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); + +/* atts is array of name/value pairs, terminated by 0; + names and values are 0 terminated. */ + +typedef void (*XML_StartElementHandler)(void *userData, + const XML_Char *name, + const XML_Char **atts); + +typedef void (*XML_EndElementHandler)(void *userData, + const XML_Char *name); + + +/* s is not 0 terminated. */ +typedef void (*XML_CharacterDataHandler)(void *userData, + const XML_Char *s, + int len); + +/* target and data are 0 terminated */ +typedef void (*XML_ProcessingInstructionHandler)(void *userData, + const XML_Char *target, + const XML_Char *data); + +/* data is 0 terminated */ +typedef void (*XML_CommentHandler)(void *userData, const XML_Char *data); + +typedef void (*XML_StartCdataSectionHandler)(void *userData); +typedef void (*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. 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 (*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 (*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 (*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 null 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. +*/ + +typedef void (*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 (*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 (*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 (*XML_StartNamespaceDeclHandler)(void *userData, + const XML_Char *prefix, + const XML_Char *uri); + +typedef void (*XML_EndNamespaceDeclHandler)(void *userData, + const XML_Char *prefix); + +/* This is called if the document is not standalone (it has an +external subset or a reference to a parameter entity, but does not +have standalone="yes"). If this handler returns 0, then processing +will not continue, and the parser will return a +XML_ERROR_NOT_STANDALONE error. */ + +typedef int (*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. +The handler should return 0 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 (*XML_ExternalEntityRefHandler)(XML_Parser parser, + const XML_Char *context, + const XML_Char *base, + const XML_Char *systemId, + const XML_Char *publicId); + +/* 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 (*convert)(void *data, const char *s); + void (*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 1. +Otherwise it must return 0. +If info does not describe a suitable encoding, +then the parser will return an XML_UNKNOWN_ENCODING error. */ + +typedef int (*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, XML_StartElementHandler); + +XMLPARSEAPI(void) +XML_SetEndElementHandler(XML_Parser, XML_EndElementHandler); + +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. The entity reference will be passed to the default +handler. */ + +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, void *arg); + +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 names + has a prefix. +*/ + +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. It must not be called after XML_Parse +or XML_ParseBuffer. */ + +XMLPARSEAPI(int) +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); + +/* 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 zero if out of memory, non-zero otherwise. */ + +XMLPARSEAPI(int) +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); + +/* Parses some input. Returns 0 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). */ +XMLPARSEAPI(int) +XML_Parse(XML_Parser parser, const char *s, int len, int isFinal); + +XMLPARSEAPI(void *) +XML_GetBuffer(XML_Parser parser, int len); + +XMLPARSEAPI(int) +XML_ParseBuffer(XML_Parser parser, int len, int isFinal); + +/* 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 0 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. */ + +XMLPARSEAPI(int) +XML_SetParamEntityParsing(XML_Parser parser, + enum XML_ParamEntityParsing parsing); + +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 +}; + +/* If XML_Parse or XML_ParseBuffer have returned 0, 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 when XML_Parse or XML_ParseBuffer return 0; +in this case the location is the location of the character at which +the error was detected. +They may also be called from any other callback called to report +some parse event; in this the location is the location of the first +of the sequence of characters that generated the event. */ + +XMLPARSEAPI(int) XML_GetCurrentLineNumber(XML_Parser parser); +XMLPARSEAPI(int) XML_GetCurrentColumnNumber(XML_Parser parser); +XMLPARSEAPI(long) 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 memory used by the parser. */ +XMLPARSEAPI(void) +XML_ParserFree(XML_Parser parser); + +/* Returns a string describing the error. */ +XMLPARSEAPI(const XML_LChar *) +XML_ErrorString(int 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); + +#define XML_MAJOR_VERSION @EXPAT_MAJOR_VERSION@ +#define XML_MINOR_VERSION @EXPAT_MINOR_VERSION@ +#define XML_MICRO_VERSION @EXPAT_EDIT@ + +#ifdef __cplusplus +} +#endif + +#endif /* not XmlParse_INCLUDED */ diff --git a/Modules/expat/iasciitab.h b/Modules/expat/iasciitab.h new file mode 100644 index 0000000..55dbc39 --- /dev/null +++ b/Modules/expat/iasciitab.h @@ -0,0 +1,38 @@ +/* +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/Modules/expat/latin1tab.h b/Modules/expat/latin1tab.h new file mode 100644 index 0000000..178b1d1 --- /dev/null +++ b/Modules/expat/latin1tab.h @@ -0,0 +1,37 @@ +/* +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/Modules/expat/nametab.h b/Modules/expat/nametab.h new file mode 100644 index 0000000..b05e62c --- /dev/null +++ b/Modules/expat/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/Modules/expat/utf8tab.h b/Modules/expat/utf8tab.h new file mode 100644 index 0000000..9e3b6b8 --- /dev/null +++ b/Modules/expat/utf8tab.h @@ -0,0 +1,38 @@ +/* +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/Modules/expat/winconfig.h b/Modules/expat/winconfig.h new file mode 100644 index 0000000..77b1ece --- /dev/null +++ b/Modules/expat/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_BYTE_ORDER 12 +#define XML_CONTEXT_BYTES 1024 + +#endif /* ndef WINCONFIG_H */ diff --git a/Modules/expat/xmlparse.c b/Modules/expat/xmlparse.c new file mode 100644 index 0000000..7c6a801 --- /dev/null +++ b/Modules/expat/xmlparse.c @@ -0,0 +1,4635 @@ +/* +Copyright (c) 1998, 1999, 2000 Thai Open Source Software Center Ltd +See the file COPYING for copying permission. +*/ + +#ifdef COMPILED_FROM_DSP +# include "winconfig.h" +# define XMLPARSEAPI(type) __declspec(dllexport) type __cdecl +# include "expat.h" +# undef XMLPARSEAPI +#else +#include <config.h> + +#ifdef __declspec +# define XMLPARSEAPI(type) __declspec(dllexport) type __cdecl +#endif + +#include "expat.h" + +#ifdef __declspec +# undef XMLPARSEAPI +#endif +#endif /* ndef COMPILED_FROM_DSP */ + +#include <stddef.h> +#include <string.h> + +#ifdef XML_UNICODE +#define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX +#define XmlConvert XmlUtf16Convert +#define XmlGetInternalEncoding XmlGetUtf16InternalEncoding +#define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS +#define XmlEncode XmlUtf16Encode +#define MUST_CONVERT(enc, s) (!(enc)->isUtf16 || (((unsigned long)s) & 1)) +typedef unsigned short ICHAR; +#else +#define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX +#define XmlConvert XmlUtf8Convert +#define XmlGetInternalEncoding XmlGetUtf8InternalEncoding +#define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS +#define XmlEncode XmlUtf8Encode +#define MUST_CONVERT(enc, s) (!(enc)->isUtf8) +typedef char ICHAR; +#endif + + +#ifndef XML_NS + +#define XmlInitEncodingNS XmlInitEncoding +#define XmlInitUnknownEncodingNS XmlInitUnknownEncoding +#undef XmlGetInternalEncodingNS +#define XmlGetInternalEncodingNS XmlGetInternalEncoding +#define XmlParseXmlDeclNS XmlParseXmlDecl + +#endif + +#ifdef XML_UNICODE_WCHAR_T +#define XML_T(x) L ## x +#else +#define XML_T(x) x +#endif + +/* Round up n to be a multiple of sz, where sz is a power of 2. */ +#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1)) + +#include "xmltok.h" +#include "xmlrole.h" + +typedef const XML_Char *KEY; + +typedef struct { + KEY name; +} NAMED; + +typedef struct { + NAMED **v; + size_t size; + size_t used; + size_t usedLim; + XML_Memory_Handling_Suite *mem; +} HASH_TABLE; + +typedef struct { + NAMED **p; + NAMED **end; +} HASH_TABLE_ITER; + +#define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */ +#define INIT_DATA_BUF_SIZE 1024 +#define INIT_ATTS_SIZE 16 +#define INIT_BLOCK_SIZE 1024 +#define INIT_BUFFER_SIZE 1024 + +#define EXPAND_SPARE 24 + +typedef struct binding { + struct prefix *prefix; + struct binding *nextTagBinding; + struct binding *prevPrefixBinding; + const struct attribute_id *attId; + XML_Char *uri; + int uriLen; + int uriAlloc; +} BINDING; + +typedef struct prefix { + const XML_Char *name; + BINDING *binding; +} PREFIX; + +typedef struct { + const XML_Char *str; + const XML_Char *localPart; + int uriLen; +} TAG_NAME; + +typedef struct tag { + struct tag *parent; + const char *rawName; + int rawNameLength; + TAG_NAME name; + char *buf; + char *bufEnd; + BINDING *bindings; +} TAG; + +typedef struct { + const XML_Char *name; + const XML_Char *textPtr; + int textLen; + const XML_Char *systemId; + const XML_Char *base; + const XML_Char *publicId; + const XML_Char *notation; + char open; + char is_param; +} ENTITY; + +typedef struct { + enum XML_Content_Type type; + enum XML_Content_Quant quant; + const XML_Char * name; + int firstchild; + int lastchild; + int childcnt; + int nextsib; +} CONTENT_SCAFFOLD; + +typedef struct block { + struct block *next; + int size; + XML_Char s[1]; +} BLOCK; + +typedef struct { + BLOCK *blocks; + BLOCK *freeBlocks; + const XML_Char *end; + XML_Char *ptr; + XML_Char *start; + XML_Memory_Handling_Suite *mem; +} STRING_POOL; + +/* The XML_Char before the name is used to determine whether +an attribute has been specified. */ +typedef struct attribute_id { + XML_Char *name; + PREFIX *prefix; + char maybeTokenized; + char xmlns; +} ATTRIBUTE_ID; + +typedef struct { + const ATTRIBUTE_ID *id; + char isCdata; + const XML_Char *value; +} DEFAULT_ATTRIBUTE; + +typedef struct { + const XML_Char *name; + PREFIX *prefix; + const ATTRIBUTE_ID *idAtt; + int nDefaultAtts; + int allocDefaultAtts; + DEFAULT_ATTRIBUTE *defaultAtts; +} ELEMENT_TYPE; + +typedef struct { + HASH_TABLE generalEntities; + HASH_TABLE elementTypes; + HASH_TABLE attributeIds; + HASH_TABLE prefixes; + STRING_POOL pool; + int complete; + int standalone; +#ifdef XML_DTD + HASH_TABLE paramEntities; +#endif /* XML_DTD */ + PREFIX defaultPrefix; + /* === scaffolding for building content model === */ + int in_eldecl; + CONTENT_SCAFFOLD *scaffold; + unsigned contentStringLen; + unsigned scaffSize; + unsigned scaffCount; + int scaffLevel; + int *scaffIndex; +} DTD; + +typedef struct open_internal_entity { + const char *internalEventPtr; + const char *internalEventEndPtr; + struct open_internal_entity *next; + ENTITY *entity; +} OPEN_INTERNAL_ENTITY; + +typedef enum XML_Error Processor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr); + +static Processor prologProcessor; +static Processor prologInitProcessor; +static Processor contentProcessor; +static Processor cdataSectionProcessor; +#ifdef XML_DTD +static Processor ignoreSectionProcessor; +#endif /* XML_DTD */ +static Processor epilogProcessor; +static Processor errorProcessor; +static Processor externalEntityInitProcessor; +static Processor externalEntityInitProcessor2; +static Processor externalEntityInitProcessor3; +static Processor externalEntityContentProcessor; + +static enum XML_Error +handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName); +static enum XML_Error +processXmlDecl(XML_Parser parser, int isGeneralTextEntity, const char *, const char *); +static enum XML_Error +initializeEncoding(XML_Parser parser); +static enum XML_Error +doProlog(XML_Parser parser, const ENCODING *enc, const char *s, + const char *end, int tok, const char *next, const char **nextPtr); +static enum XML_Error +processInternalParamEntity(XML_Parser parser, ENTITY *entity); +static enum XML_Error +doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc, + const char *start, const char *end, const char **endPtr); +static enum XML_Error +doCdataSection(XML_Parser parser, const ENCODING *, const char **startPtr, const char *end, const char **nextPtr); +#ifdef XML_DTD +static enum XML_Error +doIgnoreSection(XML_Parser parser, const ENCODING *, const char **startPtr, const char *end, const char **nextPtr); +#endif /* XML_DTD */ +static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *, const char *s, + TAG_NAME *tagNamePtr, BINDING **bindingsPtr); +static +int addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, const XML_Char *uri, BINDING **bindingsPtr); + +static int +defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, + int isCdata, int isId, const XML_Char *dfltValue, + XML_Parser parser); + +static enum XML_Error +storeAttributeValue(XML_Parser parser, const ENCODING *, int isCdata, const char *, const char *, + STRING_POOL *); +static enum XML_Error +appendAttributeValue(XML_Parser parser, const ENCODING *, int isCdata, const char *, const char *, + STRING_POOL *); +static ATTRIBUTE_ID * +getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const char *end); +static int setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *); +static enum XML_Error +storeEntityValue(XML_Parser parser, const ENCODING *enc, const char *start, const char *end); +static int +reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char *start, const char *end); +static int +reportComment(XML_Parser parser, const ENCODING *enc, const char *start, const char *end); +static void +reportDefault(XML_Parser parser, const ENCODING *enc, const char *start, const char *end); + +static const XML_Char *getContext(XML_Parser parser); +static int setContext(XML_Parser parser, const XML_Char *context); +static void normalizePublicId(XML_Char *s); +static int dtdInit(DTD *, XML_Parser parser); + +static void dtdDestroy(DTD *, XML_Parser parser); + +static int dtdCopy(DTD *newDtd, const DTD *oldDtd, XML_Parser parser); + +static int copyEntityTable(HASH_TABLE *, STRING_POOL *, const HASH_TABLE *, + XML_Parser parser); + +#ifdef XML_DTD +static void dtdSwap(DTD *, DTD *); +#endif /* XML_DTD */ + +static NAMED *lookup(HASH_TABLE *table, KEY name, size_t createSize); + +static void hashTableInit(HASH_TABLE *, XML_Memory_Handling_Suite *ms); + +static void hashTableDestroy(HASH_TABLE *); +static void hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *); +static NAMED *hashTableIterNext(HASH_TABLE_ITER *); +static void poolInit(STRING_POOL *, XML_Memory_Handling_Suite *ms); +static void poolClear(STRING_POOL *); +static void poolDestroy(STRING_POOL *); +static XML_Char *poolAppend(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end); +static XML_Char *poolStoreString(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end); + +static int poolGrow(STRING_POOL *pool); + +static int nextScaffoldPart(XML_Parser parser); +static XML_Content *build_model(XML_Parser parser); + +static const XML_Char *poolCopyString(STRING_POOL *pool, const XML_Char *s); +static const XML_Char *poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n); +static const XML_Char *poolAppendString(STRING_POOL *pool, const XML_Char *s); +static ELEMENT_TYPE * getElementType(XML_Parser Paraser, + const ENCODING *enc, + const char *ptr, + const char *end); + +#define poolStart(pool) ((pool)->start) +#define poolEnd(pool) ((pool)->ptr) +#define poolLength(pool) ((pool)->ptr - (pool)->start) +#define poolChop(pool) ((void)--(pool->ptr)) +#define poolLastChar(pool) (((pool)->ptr)[-1]) +#define poolDiscard(pool) ((pool)->ptr = (pool)->start) +#define poolFinish(pool) ((pool)->start = (pool)->ptr) +#define poolAppendChar(pool, c) \ + (((pool)->ptr == (pool)->end && !poolGrow(pool)) \ + ? 0 \ + : ((*((pool)->ptr)++ = c), 1)) + +typedef struct { + /* The first member must be userData so that the XML_GetUserData macro works. */ + void *m_userData; + void *m_handlerArg; + char *m_buffer; + XML_Memory_Handling_Suite m_mem; + /* first character to be parsed */ + const char *m_bufferPtr; + /* past last character to be parsed */ + char *m_bufferEnd; + /* allocated end of buffer */ + const char *m_bufferLim; + long m_parseEndByteIndex; + const char *m_parseEndPtr; + XML_Char *m_dataBuf; + XML_Char *m_dataBufEnd; + XML_StartElementHandler m_startElementHandler; + XML_EndElementHandler m_endElementHandler; + XML_CharacterDataHandler m_characterDataHandler; + XML_ProcessingInstructionHandler m_processingInstructionHandler; + XML_CommentHandler m_commentHandler; + XML_StartCdataSectionHandler m_startCdataSectionHandler; + XML_EndCdataSectionHandler m_endCdataSectionHandler; + XML_DefaultHandler m_defaultHandler; + XML_StartDoctypeDeclHandler m_startDoctypeDeclHandler; + XML_EndDoctypeDeclHandler m_endDoctypeDeclHandler; + XML_UnparsedEntityDeclHandler m_unparsedEntityDeclHandler; + XML_NotationDeclHandler m_notationDeclHandler; + XML_StartNamespaceDeclHandler m_startNamespaceDeclHandler; + XML_EndNamespaceDeclHandler m_endNamespaceDeclHandler; + XML_NotStandaloneHandler m_notStandaloneHandler; + XML_ExternalEntityRefHandler m_externalEntityRefHandler; + void *m_externalEntityRefHandlerArg; + XML_UnknownEncodingHandler m_unknownEncodingHandler; + XML_ElementDeclHandler m_elementDeclHandler; + XML_AttlistDeclHandler m_attlistDeclHandler; + XML_EntityDeclHandler m_entityDeclHandler; + XML_XmlDeclHandler m_xmlDeclHandler; + const ENCODING *m_encoding; + INIT_ENCODING m_initEncoding; + const ENCODING *m_internalEncoding; + const XML_Char *m_protocolEncodingName; + int m_ns; + int m_ns_triplets; + void *m_unknownEncodingMem; + void *m_unknownEncodingData; + void *m_unknownEncodingHandlerData; + void (*m_unknownEncodingRelease)(void *); + PROLOG_STATE m_prologState; + Processor *m_processor; + enum XML_Error m_errorCode; + const char *m_eventPtr; + const char *m_eventEndPtr; + const char *m_positionPtr; + OPEN_INTERNAL_ENTITY *m_openInternalEntities; + int m_defaultExpandInternalEntities; + int m_tagLevel; + ENTITY *m_declEntity; + const XML_Char *m_doctypeName; + const XML_Char *m_doctypeSysid; + const XML_Char *m_doctypePubid; + const XML_Char *m_declAttributeType; + const XML_Char *m_declNotationName; + const XML_Char *m_declNotationPublicId; + ELEMENT_TYPE *m_declElementType; + ATTRIBUTE_ID *m_declAttributeId; + char m_declAttributeIsCdata; + char m_declAttributeIsId; + DTD m_dtd; + const XML_Char *m_curBase; + TAG *m_tagStack; + TAG *m_freeTagList; + BINDING *m_inheritedBindings; + BINDING *m_freeBindingList; + int m_attsSize; + int m_nSpecifiedAtts; + int m_idAttIndex; + ATTRIBUTE *m_atts; + POSITION m_position; + STRING_POOL m_tempPool; + STRING_POOL m_temp2Pool; + char *m_groupConnector; + unsigned m_groupSize; + int m_hadExternalDoctype; + XML_Char m_namespaceSeparator; +#ifdef XML_DTD + enum XML_ParamEntityParsing m_paramEntityParsing; + XML_Parser m_parentParser; +#endif +} Parser; + +#define MALLOC(s) (((Parser *)parser)->m_mem.malloc_fcn((s))) +#define REALLOC(p,s) (((Parser *)parser)->m_mem.realloc_fcn((p),(s))) +#define FREE(p) (((Parser *)parser)->m_mem.free_fcn((p))) + +#define userData (((Parser *)parser)->m_userData) +#define handlerArg (((Parser *)parser)->m_handlerArg) +#define startElementHandler (((Parser *)parser)->m_startElementHandler) +#define endElementHandler (((Parser *)parser)->m_endElementHandler) +#define characterDataHandler (((Parser *)parser)->m_characterDataHandler) +#define processingInstructionHandler (((Parser *)parser)->m_processingInstructionHandler) +#define commentHandler (((Parser *)parser)->m_commentHandler) +#define startCdataSectionHandler (((Parser *)parser)->m_startCdataSectionHandler) +#define endCdataSectionHandler (((Parser *)parser)->m_endCdataSectionHandler) +#define defaultHandler (((Parser *)parser)->m_defaultHandler) +#define startDoctypeDeclHandler (((Parser *)parser)->m_startDoctypeDeclHandler) +#define endDoctypeDeclHandler (((Parser *)parser)->m_endDoctypeDeclHandler) +#define unparsedEntityDeclHandler (((Parser *)parser)->m_unparsedEntityDeclHandler) +#define notationDeclHandler (((Parser *)parser)->m_notationDeclHandler) +#define startNamespaceDeclHandler (((Parser *)parser)->m_startNamespaceDeclHandler) +#define endNamespaceDeclHandler (((Parser *)parser)->m_endNamespaceDeclHandler) +#define notStandaloneHandler (((Parser *)parser)->m_notStandaloneHandler) +#define externalEntityRefHandler (((Parser *)parser)->m_externalEntityRefHandler) +#define externalEntityRefHandlerArg (((Parser *)parser)->m_externalEntityRefHandlerArg) +#define internalEntityRefHandler (((Parser *)parser)->m_internalEntityRefHandler) +#define unknownEncodingHandler (((Parser *)parser)->m_unknownEncodingHandler) +#define elementDeclHandler (((Parser *)parser)->m_elementDeclHandler) +#define attlistDeclHandler (((Parser *)parser)->m_attlistDeclHandler) +#define entityDeclHandler (((Parser *)parser)->m_entityDeclHandler) +#define xmlDeclHandler (((Parser *)parser)->m_xmlDeclHandler) +#define encoding (((Parser *)parser)->m_encoding) +#define initEncoding (((Parser *)parser)->m_initEncoding) +#define internalEncoding (((Parser *)parser)->m_internalEncoding) +#define unknownEncodingMem (((Parser *)parser)->m_unknownEncodingMem) +#define unknownEncodingData (((Parser *)parser)->m_unknownEncodingData) +#define unknownEncodingHandlerData \ + (((Parser *)parser)->m_unknownEncodingHandlerData) +#define unknownEncodingRelease (((Parser *)parser)->m_unknownEncodingRelease) +#define protocolEncodingName (((Parser *)parser)->m_protocolEncodingName) +#define ns (((Parser *)parser)->m_ns) +#define ns_triplets (((Parser *)parser)->m_ns_triplets) +#define prologState (((Parser *)parser)->m_prologState) +#define processor (((Parser *)parser)->m_processor) +#define errorCode (((Parser *)parser)->m_errorCode) +#define eventPtr (((Parser *)parser)->m_eventPtr) +#define eventEndPtr (((Parser *)parser)->m_eventEndPtr) +#define positionPtr (((Parser *)parser)->m_positionPtr) +#define position (((Parser *)parser)->m_position) +#define openInternalEntities (((Parser *)parser)->m_openInternalEntities) +#define defaultExpandInternalEntities (((Parser *)parser)->m_defaultExpandInternalEntities) +#define tagLevel (((Parser *)parser)->m_tagLevel) +#define buffer (((Parser *)parser)->m_buffer) +#define bufferPtr (((Parser *)parser)->m_bufferPtr) +#define bufferEnd (((Parser *)parser)->m_bufferEnd) +#define parseEndByteIndex (((Parser *)parser)->m_parseEndByteIndex) +#define parseEndPtr (((Parser *)parser)->m_parseEndPtr) +#define bufferLim (((Parser *)parser)->m_bufferLim) +#define dataBuf (((Parser *)parser)->m_dataBuf) +#define dataBufEnd (((Parser *)parser)->m_dataBufEnd) +#define dtd (((Parser *)parser)->m_dtd) +#define curBase (((Parser *)parser)->m_curBase) +#define declEntity (((Parser *)parser)->m_declEntity) +#define doctypeName (((Parser *)parser)->m_doctypeName) +#define doctypeSysid (((Parser *)parser)->m_doctypeSysid) +#define doctypePubid (((Parser *)parser)->m_doctypePubid) +#define declAttributeType (((Parser *)parser)->m_declAttributeType) +#define declNotationName (((Parser *)parser)->m_declNotationName) +#define declNotationPublicId (((Parser *)parser)->m_declNotationPublicId) +#define declElementType (((Parser *)parser)->m_declElementType) +#define declAttributeId (((Parser *)parser)->m_declAttributeId) +#define declAttributeIsCdata (((Parser *)parser)->m_declAttributeIsCdata) +#define declAttributeIsId (((Parser *)parser)->m_declAttributeIsId) +#define freeTagList (((Parser *)parser)->m_freeTagList) +#define freeBindingList (((Parser *)parser)->m_freeBindingList) +#define inheritedBindings (((Parser *)parser)->m_inheritedBindings) +#define tagStack (((Parser *)parser)->m_tagStack) +#define atts (((Parser *)parser)->m_atts) +#define attsSize (((Parser *)parser)->m_attsSize) +#define nSpecifiedAtts (((Parser *)parser)->m_nSpecifiedAtts) +#define idAttIndex (((Parser *)parser)->m_idAttIndex) +#define tempPool (((Parser *)parser)->m_tempPool) +#define temp2Pool (((Parser *)parser)->m_temp2Pool) +#define groupConnector (((Parser *)parser)->m_groupConnector) +#define groupSize (((Parser *)parser)->m_groupSize) +#define hadExternalDoctype (((Parser *)parser)->m_hadExternalDoctype) +#define namespaceSeparator (((Parser *)parser)->m_namespaceSeparator) +#ifdef XML_DTD +#define parentParser (((Parser *)parser)->m_parentParser) +#define paramEntityParsing (((Parser *)parser)->m_paramEntityParsing) +#endif /* XML_DTD */ + +#ifdef COMPILED_FROM_DSP +BOOL WINAPI DllMain(HINSTANCE h, DWORD r, LPVOID p) { + return TRUE; +} +#endif /* def COMPILED_FROM_DSP */ + +#ifdef _MSC_VER +#ifdef _DEBUG +Parser *asParser(XML_Parser parser) +{ + return parser; +} +#endif +#endif + +XML_Parser XML_ParserCreate(const XML_Char *encodingName) +{ + return XML_ParserCreate_MM(encodingName, NULL, NULL); +} + +XML_Parser XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep) +{ + XML_Char tmp[2]; + *tmp = nsSep; + return XML_ParserCreate_MM(encodingName, NULL, tmp); +} + +XML_Parser +XML_ParserCreate_MM(const XML_Char *encodingName, + const XML_Memory_Handling_Suite *memsuite, + const XML_Char *nameSep) { + + XML_Parser parser; + static + const XML_Char implicitContext[] = { + XML_T('x'), XML_T('m'), XML_T('l'), XML_T('='), + XML_T('h'), XML_T('t'), XML_T('t'), XML_T('p'), XML_T(':'), + XML_T('/'), XML_T('/'), XML_T('w'), XML_T('w'), XML_T('w'), + XML_T('.'), XML_T('w'), XML_T('3'), + XML_T('.'), XML_T('o'), XML_T('r'), XML_T('g'), + XML_T('/'), XML_T('X'), XML_T('M'), XML_T('L'), + XML_T('/'), XML_T('1'), XML_T('9'), XML_T('9'), XML_T('8'), + XML_T('/'), XML_T('n'), XML_T('a'), XML_T('m'), XML_T('e'), + XML_T('s'), XML_T('p'), XML_T('a'), XML_T('c'), XML_T('e'), + XML_T('\0') + }; + + + if (memsuite) { + XML_Memory_Handling_Suite *mtemp; + parser = memsuite->malloc_fcn(sizeof(Parser)); + mtemp = &(((Parser *) parser)->m_mem); + mtemp->malloc_fcn = memsuite->malloc_fcn; + mtemp->realloc_fcn = memsuite->realloc_fcn; + mtemp->free_fcn = memsuite->free_fcn; + } + else { + XML_Memory_Handling_Suite *mtemp; + parser = malloc(sizeof(Parser)); + mtemp = &(((Parser *) parser)->m_mem); + mtemp->malloc_fcn = malloc; + mtemp->realloc_fcn = realloc; + mtemp->free_fcn = free; + } + + if (!parser) + return parser; + processor = prologInitProcessor; + XmlPrologStateInit(&prologState); + userData = 0; + handlerArg = 0; + startElementHandler = 0; + endElementHandler = 0; + characterDataHandler = 0; + processingInstructionHandler = 0; + commentHandler = 0; + startCdataSectionHandler = 0; + endCdataSectionHandler = 0; + defaultHandler = 0; + startDoctypeDeclHandler = 0; + endDoctypeDeclHandler = 0; + unparsedEntityDeclHandler = 0; + notationDeclHandler = 0; + startNamespaceDeclHandler = 0; + endNamespaceDeclHandler = 0; + notStandaloneHandler = 0; + externalEntityRefHandler = 0; + externalEntityRefHandlerArg = parser; + unknownEncodingHandler = 0; + elementDeclHandler = 0; + attlistDeclHandler = 0; + entityDeclHandler = 0; + xmlDeclHandler = 0; + buffer = 0; + bufferPtr = 0; + bufferEnd = 0; + parseEndByteIndex = 0; + parseEndPtr = 0; + bufferLim = 0; + declElementType = 0; + declAttributeId = 0; + declEntity = 0; + doctypeName = 0; + doctypeSysid = 0; + doctypePubid = 0; + declAttributeType = 0; + declNotationName = 0; + declNotationPublicId = 0; + memset(&position, 0, sizeof(POSITION)); + errorCode = XML_ERROR_NONE; + eventPtr = 0; + eventEndPtr = 0; + positionPtr = 0; + openInternalEntities = 0; + tagLevel = 0; + tagStack = 0; + freeTagList = 0; + freeBindingList = 0; + inheritedBindings = 0; + attsSize = INIT_ATTS_SIZE; + atts = MALLOC(attsSize * sizeof(ATTRIBUTE)); + nSpecifiedAtts = 0; + dataBuf = MALLOC(INIT_DATA_BUF_SIZE * sizeof(XML_Char)); + groupSize = 0; + groupConnector = 0; + hadExternalDoctype = 0; + unknownEncodingMem = 0; + unknownEncodingRelease = 0; + unknownEncodingData = 0; + unknownEncodingHandlerData = 0; + namespaceSeparator = '!'; +#ifdef XML_DTD + parentParser = 0; + paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; +#endif + ns = 0; + ns_triplets = 0; + poolInit(&tempPool, &(((Parser *) parser)->m_mem)); + poolInit(&temp2Pool, &(((Parser *) parser)->m_mem)); + protocolEncodingName = encodingName ? poolCopyString(&tempPool, encodingName) : 0; + curBase = 0; + if (!dtdInit(&dtd, parser) || !atts || !dataBuf + || (encodingName && !protocolEncodingName)) { + XML_ParserFree(parser); + return 0; + } + dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE; + + if (nameSep) { + XmlInitEncodingNS(&initEncoding, &encoding, 0); + ns = 1; + internalEncoding = XmlGetInternalEncodingNS(); + namespaceSeparator = *nameSep; + + if (! setContext(parser, implicitContext)) { + XML_ParserFree(parser); + return 0; + } + } + else { + XmlInitEncoding(&initEncoding, &encoding, 0); + internalEncoding = XmlGetInternalEncoding(); + } + + return parser; +} /* End XML_ParserCreate_MM */ + +int XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName) +{ + if (!encodingName) + protocolEncodingName = 0; + else { + protocolEncodingName = poolCopyString(&tempPool, encodingName); + if (!protocolEncodingName) + return 0; + } + return 1; +} + +XML_Parser XML_ExternalEntityParserCreate(XML_Parser oldParser, + const XML_Char *context, + const XML_Char *encodingName) +{ + XML_Parser parser = oldParser; + DTD *oldDtd = &dtd; + XML_StartElementHandler oldStartElementHandler = startElementHandler; + XML_EndElementHandler oldEndElementHandler = endElementHandler; + XML_CharacterDataHandler oldCharacterDataHandler = characterDataHandler; + XML_ProcessingInstructionHandler oldProcessingInstructionHandler = processingInstructionHandler; + XML_CommentHandler oldCommentHandler = commentHandler; + XML_StartCdataSectionHandler oldStartCdataSectionHandler = startCdataSectionHandler; + XML_EndCdataSectionHandler oldEndCdataSectionHandler = endCdataSectionHandler; + XML_DefaultHandler oldDefaultHandler = defaultHandler; + XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler = unparsedEntityDeclHandler; + XML_NotationDeclHandler oldNotationDeclHandler = notationDeclHandler; + XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler = startNamespaceDeclHandler; + XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler = endNamespaceDeclHandler; + XML_NotStandaloneHandler oldNotStandaloneHandler = notStandaloneHandler; + XML_ExternalEntityRefHandler oldExternalEntityRefHandler = externalEntityRefHandler; + XML_UnknownEncodingHandler oldUnknownEncodingHandler = unknownEncodingHandler; + XML_ElementDeclHandler oldElementDeclHandler = elementDeclHandler; + XML_AttlistDeclHandler oldAttlistDeclHandler = attlistDeclHandler; + XML_EntityDeclHandler oldEntityDeclHandler = entityDeclHandler; + XML_XmlDeclHandler oldXmlDeclHandler = xmlDeclHandler; + ELEMENT_TYPE * oldDeclElementType = declElementType; + + void *oldUserData = userData; + void *oldHandlerArg = handlerArg; + int oldDefaultExpandInternalEntities = defaultExpandInternalEntities; + void *oldExternalEntityRefHandlerArg = externalEntityRefHandlerArg; +#ifdef XML_DTD + int oldParamEntityParsing = paramEntityParsing; +#endif + int oldns_triplets = ns_triplets; + + if (ns) { + XML_Char tmp[2]; + + *tmp = namespaceSeparator; + parser = XML_ParserCreate_MM(encodingName, &((Parser *)parser)->m_mem, + tmp); + } + else { + parser = XML_ParserCreate_MM(encodingName, &((Parser *)parser)->m_mem, + NULL); + } + + if (!parser) + return 0; + + startElementHandler = oldStartElementHandler; + endElementHandler = oldEndElementHandler; + characterDataHandler = oldCharacterDataHandler; + processingInstructionHandler = oldProcessingInstructionHandler; + commentHandler = oldCommentHandler; + startCdataSectionHandler = oldStartCdataSectionHandler; + endCdataSectionHandler = oldEndCdataSectionHandler; + defaultHandler = oldDefaultHandler; + unparsedEntityDeclHandler = oldUnparsedEntityDeclHandler; + notationDeclHandler = oldNotationDeclHandler; + startNamespaceDeclHandler = oldStartNamespaceDeclHandler; + endNamespaceDeclHandler = oldEndNamespaceDeclHandler; + notStandaloneHandler = oldNotStandaloneHandler; + externalEntityRefHandler = oldExternalEntityRefHandler; + unknownEncodingHandler = oldUnknownEncodingHandler; + elementDeclHandler = oldElementDeclHandler; + attlistDeclHandler = oldAttlistDeclHandler; + entityDeclHandler = oldEntityDeclHandler; + xmlDeclHandler = oldXmlDeclHandler; + declElementType = oldDeclElementType; + userData = oldUserData; + if (oldUserData == oldHandlerArg) + handlerArg = userData; + else + handlerArg = parser; + if (oldExternalEntityRefHandlerArg != oldParser) + externalEntityRefHandlerArg = oldExternalEntityRefHandlerArg; + defaultExpandInternalEntities = oldDefaultExpandInternalEntities; + ns_triplets = oldns_triplets; +#ifdef XML_DTD + paramEntityParsing = oldParamEntityParsing; + if (context) { +#endif /* XML_DTD */ + if (!dtdCopy(&dtd, oldDtd, parser) || !setContext(parser, context)) { + XML_ParserFree(parser); + return 0; + } + processor = externalEntityInitProcessor; +#ifdef XML_DTD + } + else { + dtdSwap(&dtd, oldDtd); + parentParser = oldParser; + XmlPrologStateInitExternalEntity(&prologState); + dtd.complete = 1; + hadExternalDoctype = 1; + } +#endif /* XML_DTD */ + return parser; +} + +static +void destroyBindings(BINDING *bindings, XML_Parser parser) +{ + for (;;) { + BINDING *b = bindings; + if (!b) + break; + bindings = b->nextTagBinding; + FREE(b->uri); + FREE(b); + } +} + +void XML_ParserFree(XML_Parser parser) +{ + for (;;) { + TAG *p; + if (tagStack == 0) { + if (freeTagList == 0) + break; + tagStack = freeTagList; + freeTagList = 0; + } + p = tagStack; + tagStack = tagStack->parent; + FREE(p->buf); + destroyBindings(p->bindings, parser); + FREE(p); + } + destroyBindings(freeBindingList, parser); + destroyBindings(inheritedBindings, parser); + poolDestroy(&tempPool); + poolDestroy(&temp2Pool); +#ifdef XML_DTD + if (parentParser) { + if (hadExternalDoctype) + dtd.complete = 0; + dtdSwap(&dtd, &((Parser *)parentParser)->m_dtd); + } +#endif /* XML_DTD */ + dtdDestroy(&dtd, parser); + FREE((void *)atts); + if (groupConnector) + FREE(groupConnector); + if (buffer) + FREE(buffer); + FREE(dataBuf); + if (unknownEncodingMem) + FREE(unknownEncodingMem); + if (unknownEncodingRelease) + unknownEncodingRelease(unknownEncodingData); + FREE(parser); +} + +void XML_UseParserAsHandlerArg(XML_Parser parser) +{ + handlerArg = parser; +} + +void +XML_SetReturnNSTriplet(XML_Parser parser, int do_nst) { + ns_triplets = do_nst; +} + +void XML_SetUserData(XML_Parser parser, void *p) +{ + if (handlerArg == userData) + handlerArg = userData = p; + else + userData = p; +} + +int XML_SetBase(XML_Parser parser, const XML_Char *p) +{ + if (p) { + p = poolCopyString(&dtd.pool, p); + if (!p) + return 0; + curBase = p; + } + else + curBase = 0; + return 1; +} + +const XML_Char *XML_GetBase(XML_Parser parser) +{ + return curBase; +} + +int XML_GetSpecifiedAttributeCount(XML_Parser parser) +{ + return nSpecifiedAtts; +} + +int XML_GetIdAttributeIndex(XML_Parser parser) +{ + return idAttIndex; +} + +void XML_SetElementHandler(XML_Parser parser, + XML_StartElementHandler start, + XML_EndElementHandler end) +{ + startElementHandler = start; + endElementHandler = end; +} + +void XML_SetStartElementHandler(XML_Parser parser, + XML_StartElementHandler start) { + startElementHandler = start; +} + +void XML_SetEndElementHandler(XML_Parser parser, + XML_EndElementHandler end) { + endElementHandler = end; +} + +void XML_SetCharacterDataHandler(XML_Parser parser, + XML_CharacterDataHandler handler) +{ + characterDataHandler = handler; +} + +void XML_SetProcessingInstructionHandler(XML_Parser parser, + XML_ProcessingInstructionHandler handler) +{ + processingInstructionHandler = handler; +} + +void XML_SetCommentHandler(XML_Parser parser, + XML_CommentHandler handler) +{ + commentHandler = handler; +} + +void XML_SetCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start, + XML_EndCdataSectionHandler end) +{ + startCdataSectionHandler = start; + endCdataSectionHandler = end; +} + +void XML_SetStartCdataSectionHandler(XML_Parser parser, + XML_StartCdataSectionHandler start) { + startCdataSectionHandler = start; +} + +void XML_SetEndCdataSectionHandler(XML_Parser parser, + XML_EndCdataSectionHandler end) { + endCdataSectionHandler = end; +} + +void XML_SetDefaultHandler(XML_Parser parser, + XML_DefaultHandler handler) +{ + defaultHandler = handler; + defaultExpandInternalEntities = 0; +} + +void XML_SetDefaultHandlerExpand(XML_Parser parser, + XML_DefaultHandler handler) +{ + defaultHandler = handler; + defaultExpandInternalEntities = 1; +} + +void XML_SetDoctypeDeclHandler(XML_Parser parser, + XML_StartDoctypeDeclHandler start, + XML_EndDoctypeDeclHandler end) +{ + startDoctypeDeclHandler = start; + endDoctypeDeclHandler = end; +} + +void XML_SetStartDoctypeDeclHandler(XML_Parser parser, + XML_StartDoctypeDeclHandler start) { + startDoctypeDeclHandler = start; +} + +void XML_SetEndDoctypeDeclHandler(XML_Parser parser, + XML_EndDoctypeDeclHandler end) { + endDoctypeDeclHandler = end; +} + +void XML_SetUnparsedEntityDeclHandler(XML_Parser parser, + XML_UnparsedEntityDeclHandler handler) +{ + unparsedEntityDeclHandler = handler; +} + +void XML_SetNotationDeclHandler(XML_Parser parser, + XML_NotationDeclHandler handler) +{ + notationDeclHandler = handler; +} + +void XML_SetNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start, + XML_EndNamespaceDeclHandler end) +{ + startNamespaceDeclHandler = start; + endNamespaceDeclHandler = end; +} + +void XML_SetStartNamespaceDeclHandler(XML_Parser parser, + XML_StartNamespaceDeclHandler start) { + startNamespaceDeclHandler = start; +} + +void XML_SetEndNamespaceDeclHandler(XML_Parser parser, + XML_EndNamespaceDeclHandler end) { + endNamespaceDeclHandler = end; +} + + +void XML_SetNotStandaloneHandler(XML_Parser parser, + XML_NotStandaloneHandler handler) +{ + notStandaloneHandler = handler; +} + +void XML_SetExternalEntityRefHandler(XML_Parser parser, + XML_ExternalEntityRefHandler handler) +{ + externalEntityRefHandler = handler; +} + +void XML_SetExternalEntityRefHandlerArg(XML_Parser parser, void *arg) +{ + if (arg) + externalEntityRefHandlerArg = arg; + else + externalEntityRefHandlerArg = parser; +} + +void XML_SetUnknownEncodingHandler(XML_Parser parser, + XML_UnknownEncodingHandler handler, + void *data) +{ + unknownEncodingHandler = handler; + unknownEncodingHandlerData = data; +} + +void XML_SetElementDeclHandler(XML_Parser parser, + XML_ElementDeclHandler eldecl) +{ + elementDeclHandler = eldecl; +} + +void XML_SetAttlistDeclHandler(XML_Parser parser, + XML_AttlistDeclHandler attdecl) +{ + attlistDeclHandler = attdecl; +} + +void XML_SetEntityDeclHandler(XML_Parser parser, + XML_EntityDeclHandler handler) +{ + entityDeclHandler = handler; +} + +void XML_SetXmlDeclHandler(XML_Parser parser, + XML_XmlDeclHandler handler) { + xmlDeclHandler = handler; +} + +int XML_SetParamEntityParsing(XML_Parser parser, + enum XML_ParamEntityParsing parsing) +{ +#ifdef XML_DTD + paramEntityParsing = parsing; + return 1; +#else + return parsing == XML_PARAM_ENTITY_PARSING_NEVER; +#endif +} + +int XML_Parse(XML_Parser parser, const char *s, int len, int isFinal) +{ + if (len == 0) { + if (!isFinal) + return 1; + positionPtr = bufferPtr; + errorCode = processor(parser, bufferPtr, parseEndPtr = bufferEnd, 0); + if (errorCode == XML_ERROR_NONE) + return 1; + eventEndPtr = eventPtr; + processor = errorProcessor; + return 0; + } +#ifndef XML_CONTEXT_BYTES + else if (bufferPtr == bufferEnd) { + const char *end; + int nLeftOver; + parseEndByteIndex += len; + positionPtr = s; + if (isFinal) { + errorCode = processor(parser, s, parseEndPtr = s + len, 0); + if (errorCode == XML_ERROR_NONE) + return 1; + eventEndPtr = eventPtr; + processor = errorProcessor; + return 0; + } + errorCode = processor(parser, s, parseEndPtr = s + len, &end); + if (errorCode != XML_ERROR_NONE) { + eventEndPtr = eventPtr; + processor = errorProcessor; + return 0; + } + XmlUpdatePosition(encoding, positionPtr, end, &position); + nLeftOver = s + len - end; + if (nLeftOver) { + if (buffer == 0 || nLeftOver > bufferLim - buffer) { + /* FIXME avoid integer overflow */ + buffer = buffer == 0 ? MALLOC(len * 2) : REALLOC(buffer, len * 2); + /* FIXME storage leak if realloc fails */ + if (!buffer) { + errorCode = XML_ERROR_NO_MEMORY; + eventPtr = eventEndPtr = 0; + processor = errorProcessor; + return 0; + } + bufferLim = buffer + len * 2; + } + memcpy(buffer, end, nLeftOver); + bufferPtr = buffer; + bufferEnd = buffer + nLeftOver; + } + return 1; + } +#endif /* not defined XML_CONTEXT_BYTES */ + else { + memcpy(XML_GetBuffer(parser, len), s, len); + return XML_ParseBuffer(parser, len, isFinal); + } +} + +int XML_ParseBuffer(XML_Parser parser, int len, int isFinal) +{ + const char *start = bufferPtr; + positionPtr = start; + bufferEnd += len; + parseEndByteIndex += len; + errorCode = processor(parser, start, parseEndPtr = bufferEnd, + isFinal ? (const char **)0 : &bufferPtr); + if (errorCode == XML_ERROR_NONE) { + if (!isFinal) + XmlUpdatePosition(encoding, positionPtr, bufferPtr, &position); + return 1; + } + else { + eventEndPtr = eventPtr; + processor = errorProcessor; + return 0; + } +} + +void *XML_GetBuffer(XML_Parser parser, int len) +{ + if (len > bufferLim - bufferEnd) { + /* FIXME avoid integer overflow */ + int neededSize = len + (bufferEnd - bufferPtr); +#ifdef XML_CONTEXT_BYTES + int keep = bufferPtr - buffer; + + if (keep > XML_CONTEXT_BYTES) + keep = XML_CONTEXT_BYTES; + neededSize += keep; +#endif /* defined XML_CONTEXT_BYTES */ + if (neededSize <= bufferLim - buffer) { +#ifdef XML_CONTEXT_BYTES + if (keep < bufferPtr - buffer) { + int offset = (bufferPtr - buffer) - keep; + memmove(buffer, &buffer[offset], bufferEnd - bufferPtr + keep); + bufferEnd -= offset; + bufferPtr -= offset; + } +#else + memmove(buffer, bufferPtr, bufferEnd - bufferPtr); + bufferEnd = buffer + (bufferEnd - bufferPtr); + bufferPtr = buffer; +#endif /* not defined XML_CONTEXT_BYTES */ + } + else { + char *newBuf; + int bufferSize = bufferLim - bufferPtr; + if (bufferSize == 0) + bufferSize = INIT_BUFFER_SIZE; + do { + bufferSize *= 2; + } while (bufferSize < neededSize); + newBuf = MALLOC(bufferSize); + if (newBuf == 0) { + errorCode = XML_ERROR_NO_MEMORY; + return 0; + } + bufferLim = newBuf + bufferSize; +#ifdef XML_CONTEXT_BYTES + if (bufferPtr) { + int keep = bufferPtr - buffer; + if (keep > XML_CONTEXT_BYTES) + keep = XML_CONTEXT_BYTES; + memcpy(newBuf, &bufferPtr[-keep], bufferEnd - bufferPtr + keep); + FREE(buffer); + buffer = newBuf; + bufferEnd = buffer + (bufferEnd - bufferPtr) + keep; + bufferPtr = buffer + keep; + } + else { + bufferEnd = newBuf + (bufferEnd - bufferPtr); + bufferPtr = buffer = newBuf; + } +#else + if (bufferPtr) { + memcpy(newBuf, bufferPtr, bufferEnd - bufferPtr); + FREE(buffer); + } + bufferEnd = newBuf + (bufferEnd - bufferPtr); + bufferPtr = buffer = newBuf; +#endif /* not defined XML_CONTEXT_BYTES */ + } + } + return bufferEnd; +} + +enum XML_Error XML_GetErrorCode(XML_Parser parser) +{ + return errorCode; +} + +long XML_GetCurrentByteIndex(XML_Parser parser) +{ + if (eventPtr) + return parseEndByteIndex - (parseEndPtr - eventPtr); + return -1; +} + +int XML_GetCurrentByteCount(XML_Parser parser) +{ + if (eventEndPtr && eventPtr) + return eventEndPtr - eventPtr; + return 0; +} + +const char * XML_GetInputContext(XML_Parser parser, int *offset, int *size) +{ +#ifdef XML_CONTEXT_BYTES + if (eventPtr && buffer) { + *offset = eventPtr - buffer; + *size = bufferEnd - buffer; + return buffer; + } +#endif /* defined XML_CONTEXT_BYTES */ + return (char *) 0; +} + +int XML_GetCurrentLineNumber(XML_Parser parser) +{ + if (eventPtr) { + XmlUpdatePosition(encoding, positionPtr, eventPtr, &position); + positionPtr = eventPtr; + } + return position.lineNumber + 1; +} + +int XML_GetCurrentColumnNumber(XML_Parser parser) +{ + if (eventPtr) { + XmlUpdatePosition(encoding, positionPtr, eventPtr, &position); + positionPtr = eventPtr; + } + return position.columnNumber; +} + +void XML_DefaultCurrent(XML_Parser parser) +{ + if (defaultHandler) { + if (openInternalEntities) + reportDefault(parser, + internalEncoding, + openInternalEntities->internalEventPtr, + openInternalEntities->internalEventEndPtr); + else + reportDefault(parser, encoding, eventPtr, eventEndPtr); + } +} + +const XML_LChar *XML_ErrorString(int code) +{ + static const XML_LChar *message[] = { + 0, + XML_T("out of memory"), + XML_T("syntax error"), + XML_T("no element found"), + XML_T("not well-formed (invalid token)"), + XML_T("unclosed token"), + XML_T("unclosed token"), + XML_T("mismatched tag"), + XML_T("duplicate attribute"), + XML_T("junk after document element"), + XML_T("illegal parameter entity reference"), + XML_T("undefined entity"), + XML_T("recursive entity reference"), + XML_T("asynchronous entity"), + XML_T("reference to invalid character number"), + XML_T("reference to binary entity"), + XML_T("reference to external entity in attribute"), + XML_T("xml processing instruction not at start of external entity"), + XML_T("unknown encoding"), + XML_T("encoding specified in XML declaration is incorrect"), + XML_T("unclosed CDATA section"), + XML_T("error in processing external entity reference"), + XML_T("document is not standalone"), + XML_T("unexpected parser state - please send a bug report") + }; + if (code > 0 && code < sizeof(message)/sizeof(message[0])) + return message[code]; + return 0; +} + +const XML_LChar * +XML_ExpatVersion(void) { + return VERSION; +} + +XML_Expat_Version +XML_ExpatVersionInfo(void) { + XML_Expat_Version version; + + version.major = XML_MAJOR_VERSION; + version.minor = XML_MINOR_VERSION; + version.micro = XML_MICRO_VERSION; + + return version; +} + +static +enum XML_Error contentProcessor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + return doContent(parser, 0, encoding, start, end, endPtr); +} + +static +enum XML_Error externalEntityInitProcessor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + enum XML_Error result = initializeEncoding(parser); + if (result != XML_ERROR_NONE) + return result; + processor = externalEntityInitProcessor2; + return externalEntityInitProcessor2(parser, start, end, endPtr); +} + +static +enum XML_Error externalEntityInitProcessor2(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + const char *next; + int tok = XmlContentTok(encoding, start, end, &next); + switch (tok) { + case XML_TOK_BOM: + start = next; + break; + case XML_TOK_PARTIAL: + if (endPtr) { + *endPtr = start; + return XML_ERROR_NONE; + } + eventPtr = start; + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (endPtr) { + *endPtr = start; + return XML_ERROR_NONE; + } + eventPtr = start; + return XML_ERROR_PARTIAL_CHAR; + } + processor = externalEntityInitProcessor3; + return externalEntityInitProcessor3(parser, start, end, endPtr); +} + +static +enum XML_Error externalEntityInitProcessor3(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + const char *next; + int tok = XmlContentTok(encoding, start, end, &next); + switch (tok) { + case XML_TOK_XML_DECL: + { + enum XML_Error result = processXmlDecl(parser, 1, start, next); + if (result != XML_ERROR_NONE) + return result; + start = next; + } + break; + case XML_TOK_PARTIAL: + if (endPtr) { + *endPtr = start; + return XML_ERROR_NONE; + } + eventPtr = start; + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (endPtr) { + *endPtr = start; + return XML_ERROR_NONE; + } + eventPtr = start; + return XML_ERROR_PARTIAL_CHAR; + } + processor = externalEntityContentProcessor; + tagLevel = 1; + return doContent(parser, 1, encoding, start, end, endPtr); +} + +static +enum XML_Error externalEntityContentProcessor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + return doContent(parser, 1, encoding, start, end, endPtr); +} + +static enum XML_Error +doContent(XML_Parser parser, + int startTagLevel, + const ENCODING *enc, + const char *s, + const char *end, + const char **nextPtr) +{ + const char **eventPP; + const char **eventEndPP; + if (enc == encoding) { + eventPP = &eventPtr; + eventEndPP = &eventEndPtr; + } + else { + eventPP = &(openInternalEntities->internalEventPtr); + eventEndPP = &(openInternalEntities->internalEventEndPtr); + } + *eventPP = s; + for (;;) { + const char *next = s; /* XmlContentTok doesn't always set the last arg */ + int tok = XmlContentTok(enc, s, end, &next); + *eventEndPP = next; + switch (tok) { + case XML_TOK_TRAILING_CR: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + *eventEndPP = end; + if (characterDataHandler) { + XML_Char c = 0xA; + characterDataHandler(handlerArg, &c, 1); + } + else if (defaultHandler) + reportDefault(parser, enc, s, end); + if (startTagLevel == 0) + return XML_ERROR_NO_ELEMENTS; + if (tagLevel != startTagLevel) + return XML_ERROR_ASYNC_ENTITY; + return XML_ERROR_NONE; + case XML_TOK_NONE: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + if (startTagLevel > 0) { + if (tagLevel != startTagLevel) + return XML_ERROR_ASYNC_ENTITY; + return XML_ERROR_NONE; + } + return XML_ERROR_NO_ELEMENTS; + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_ENTITY_REF: + { + const XML_Char *name; + ENTITY *entity; + XML_Char ch = XmlPredefinedEntityName(enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (ch) { + if (characterDataHandler) + characterDataHandler(handlerArg, &ch, 1); + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + name = poolStoreString(&dtd.pool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(&dtd.generalEntities, name, 0); + poolDiscard(&dtd.pool); + if (!entity) { + if (dtd.complete || dtd.standalone) + return XML_ERROR_UNDEFINED_ENTITY; + if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + if (entity->open) + return XML_ERROR_RECURSIVE_ENTITY_REF; + if (entity->notation) + return XML_ERROR_BINARY_ENTITY_REF; + if (entity) { + if (entity->textPtr) { + enum XML_Error result; + OPEN_INTERNAL_ENTITY openEntity; + if (defaultHandler && !defaultExpandInternalEntities) { + reportDefault(parser, enc, s, next); + break; + } + entity->open = 1; + openEntity.next = openInternalEntities; + openInternalEntities = &openEntity; + openEntity.entity = entity; + openEntity.internalEventPtr = 0; + openEntity.internalEventEndPtr = 0; + result = doContent(parser, + tagLevel, + internalEncoding, + (char *)entity->textPtr, + (char *)(entity->textPtr + entity->textLen), + 0); + entity->open = 0; + openInternalEntities = openEntity.next; + if (result) + return result; + } + else if (externalEntityRefHandler) { + const XML_Char *context; + entity->open = 1; + context = getContext(parser); + entity->open = 0; + if (!context) + return XML_ERROR_NO_MEMORY; + if (!externalEntityRefHandler(externalEntityRefHandlerArg, + context, + entity->base, + entity->systemId, + entity->publicId)) + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + poolDiscard(&tempPool); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + } + break; + } + case XML_TOK_START_TAG_WITH_ATTS: + if (!startElementHandler) { + enum XML_Error result = storeAtts(parser, enc, s, 0, 0); + if (result) + return result; + } + /* fall through */ + case XML_TOK_START_TAG_NO_ATTS: + { + TAG *tag; + if (freeTagList) { + tag = freeTagList; + freeTagList = freeTagList->parent; + } + else { + tag = MALLOC(sizeof(TAG)); + if (!tag) + return XML_ERROR_NO_MEMORY; + tag->buf = MALLOC(INIT_TAG_BUF_SIZE); + if (!tag->buf) + return XML_ERROR_NO_MEMORY; + tag->bufEnd = tag->buf + INIT_TAG_BUF_SIZE; + } + tag->bindings = 0; + tag->parent = tagStack; + tagStack = tag; + tag->name.localPart = 0; + tag->rawName = s + enc->minBytesPerChar; + tag->rawNameLength = XmlNameLength(enc, tag->rawName); + if (nextPtr) { + /* Need to guarantee that: + tag->buf + ROUND_UP(tag->rawNameLength, sizeof(XML_Char)) <= tag->bufEnd - sizeof(XML_Char) */ + if (tag->rawNameLength + (int)(sizeof(XML_Char) - 1) + (int)sizeof(XML_Char) > tag->bufEnd - tag->buf) { + int bufSize = tag->rawNameLength * 4; + bufSize = ROUND_UP(bufSize, sizeof(XML_Char)); + tag->buf = REALLOC(tag->buf, bufSize); + if (!tag->buf) + return XML_ERROR_NO_MEMORY; + tag->bufEnd = tag->buf + bufSize; + } + memcpy(tag->buf, tag->rawName, tag->rawNameLength); + tag->rawName = tag->buf; + } + ++tagLevel; + if (startElementHandler) { + enum XML_Error result; + XML_Char *toPtr; + for (;;) { + const char *rawNameEnd = tag->rawName + tag->rawNameLength; + const char *fromPtr = tag->rawName; + int bufSize; + if (nextPtr) + toPtr = (XML_Char *)(tag->buf + ROUND_UP(tag->rawNameLength, sizeof(XML_Char))); + else + toPtr = (XML_Char *)tag->buf; + tag->name.str = toPtr; + XmlConvert(enc, + &fromPtr, rawNameEnd, + (ICHAR **)&toPtr, (ICHAR *)tag->bufEnd - 1); + if (fromPtr == rawNameEnd) + break; + bufSize = (tag->bufEnd - tag->buf) << 1; + tag->buf = REALLOC(tag->buf, bufSize); + if (!tag->buf) + return XML_ERROR_NO_MEMORY; + tag->bufEnd = tag->buf + bufSize; + if (nextPtr) + tag->rawName = tag->buf; + } + *toPtr = XML_T('\0'); + result = storeAtts(parser, enc, s, &(tag->name), &(tag->bindings)); + if (result) + return result; + startElementHandler(handlerArg, tag->name.str, (const XML_Char **)atts); + poolClear(&tempPool); + } + else { + tag->name.str = 0; + if (defaultHandler) + reportDefault(parser, enc, s, next); + } + break; + } + case XML_TOK_EMPTY_ELEMENT_WITH_ATTS: + if (!startElementHandler) { + enum XML_Error result = storeAtts(parser, enc, s, 0, 0); + if (result) + return result; + } + /* fall through */ + case XML_TOK_EMPTY_ELEMENT_NO_ATTS: + if (startElementHandler || endElementHandler) { + const char *rawName = s + enc->minBytesPerChar; + enum XML_Error result; + BINDING *bindings = 0; + TAG_NAME name; + name.str = poolStoreString(&tempPool, enc, rawName, + rawName + XmlNameLength(enc, rawName)); + if (!name.str) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + result = storeAtts(parser, enc, s, &name, &bindings); + if (result) + return result; + poolFinish(&tempPool); + if (startElementHandler) + startElementHandler(handlerArg, name.str, (const XML_Char **)atts); + if (endElementHandler) { + if (startElementHandler) + *eventPP = *eventEndPP; + endElementHandler(handlerArg, name.str); + } + poolClear(&tempPool); + while (bindings) { + BINDING *b = bindings; + if (endNamespaceDeclHandler) + endNamespaceDeclHandler(handlerArg, b->prefix->name); + bindings = bindings->nextTagBinding; + b->nextTagBinding = freeBindingList; + freeBindingList = b; + b->prefix->binding = b->prevPrefixBinding; + } + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + if (tagLevel == 0) + return epilogProcessor(parser, next, end, nextPtr); + break; + case XML_TOK_END_TAG: + if (tagLevel == startTagLevel) + return XML_ERROR_ASYNC_ENTITY; + else { + int len; + const char *rawName; + TAG *tag = tagStack; + tagStack = tag->parent; + tag->parent = freeTagList; + freeTagList = tag; + rawName = s + enc->minBytesPerChar*2; + len = XmlNameLength(enc, rawName); + if (len != tag->rawNameLength + || memcmp(tag->rawName, rawName, len) != 0) { + *eventPP = rawName; + return XML_ERROR_TAG_MISMATCH; + } + --tagLevel; + if (endElementHandler && tag->name.str) { + if (tag->name.localPart) { + XML_Char *to = (XML_Char *)tag->name.str + tag->name.uriLen; + const XML_Char *from = tag->name.localPart; + while ((*to++ = *from++) != 0) + ; + } + endElementHandler(handlerArg, tag->name.str); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + while (tag->bindings) { + BINDING *b = tag->bindings; + if (endNamespaceDeclHandler) + endNamespaceDeclHandler(handlerArg, b->prefix->name); + tag->bindings = tag->bindings->nextTagBinding; + b->nextTagBinding = freeBindingList; + freeBindingList = b; + b->prefix->binding = b->prevPrefixBinding; + } + if (tagLevel == 0) + return epilogProcessor(parser, next, end, nextPtr); + } + break; + case XML_TOK_CHAR_REF: + { + int n = XmlCharRefNumber(enc, s); + if (n < 0) + return XML_ERROR_BAD_CHAR_REF; + if (characterDataHandler) { + XML_Char buf[XML_ENCODE_MAX]; + characterDataHandler(handlerArg, buf, XmlEncode(n, (ICHAR *)buf)); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + } + break; + case XML_TOK_XML_DECL: + return XML_ERROR_MISPLACED_XML_PI; + case XML_TOK_DATA_NEWLINE: + if (characterDataHandler) { + XML_Char c = 0xA; + characterDataHandler(handlerArg, &c, 1); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + case XML_TOK_CDATA_SECT_OPEN: + { + enum XML_Error result; + if (startCdataSectionHandler) + startCdataSectionHandler(handlerArg); +#if 0 + /* Suppose you doing a transformation on a document that involves + changing only the character data. You set up a defaultHandler + and a characterDataHandler. The defaultHandler simply copies + characters through. The characterDataHandler does the transformation + and writes the characters out escaping them as necessary. This case + will fail to work if we leave out the following two lines (because & + and < inside CDATA sections will be incorrectly escaped). + + However, now we have a start/endCdataSectionHandler, so it seems + easier to let the user deal with this. */ + + else if (characterDataHandler) + characterDataHandler(handlerArg, dataBuf, 0); +#endif + else if (defaultHandler) + reportDefault(parser, enc, s, next); + result = doCdataSection(parser, enc, &next, end, nextPtr); + if (!next) { + processor = cdataSectionProcessor; + return result; + } + } + break; + case XML_TOK_TRAILING_RSQB: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + if (characterDataHandler) { + if (MUST_CONVERT(enc, s)) { + ICHAR *dataPtr = (ICHAR *)dataBuf; + XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); + characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf); + } + else + characterDataHandler(handlerArg, + (XML_Char *)s, + (XML_Char *)end - (XML_Char *)s); + } + else if (defaultHandler) + reportDefault(parser, enc, s, end); + if (startTagLevel == 0) { + *eventPP = end; + return XML_ERROR_NO_ELEMENTS; + } + if (tagLevel != startTagLevel) { + *eventPP = end; + return XML_ERROR_ASYNC_ENTITY; + } + return XML_ERROR_NONE; + case XML_TOK_DATA_CHARS: + if (characterDataHandler) { + if (MUST_CONVERT(enc, s)) { + for (;;) { + ICHAR *dataPtr = (ICHAR *)dataBuf; + XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); + *eventEndPP = s; + characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf); + if (s == next) + break; + *eventPP = s; + } + } + else + characterDataHandler(handlerArg, + (XML_Char *)s, + (XML_Char *)next - (XML_Char *)s); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + case XML_TOK_PI: + if (!reportProcessingInstruction(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_COMMENT: + if (!reportComment(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + break; + default: + if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + } + *eventPP = s = next; + } + /* not reached */ +} + +/* If tagNamePtr is non-null, build a real list of attributes, +otherwise just check the attributes for well-formedness. */ + +static enum XML_Error storeAtts(XML_Parser parser, const ENCODING *enc, + const char *attStr, TAG_NAME *tagNamePtr, + BINDING **bindingsPtr) +{ + ELEMENT_TYPE *elementType = 0; + int nDefaultAtts = 0; + const XML_Char **appAtts; /* the attribute list to pass to the application */ + int attIndex = 0; + int i; + int n; + int nPrefixes = 0; + BINDING *binding; + const XML_Char *localPart; + + /* lookup the element type name */ + if (tagNamePtr) { + elementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, tagNamePtr->str,0); + if (!elementType) { + tagNamePtr->str = poolCopyString(&dtd.pool, tagNamePtr->str); + if (!tagNamePtr->str) + return XML_ERROR_NO_MEMORY; + elementType = (ELEMENT_TYPE *)lookup(&dtd.elementTypes, tagNamePtr->str, sizeof(ELEMENT_TYPE)); + if (!elementType) + return XML_ERROR_NO_MEMORY; + if (ns && !setElementTypePrefix(parser, elementType)) + return XML_ERROR_NO_MEMORY; + } + nDefaultAtts = elementType->nDefaultAtts; + } + /* get the attributes from the tokenizer */ + n = XmlGetAttributes(enc, attStr, attsSize, atts); + if (n + nDefaultAtts > attsSize) { + int oldAttsSize = attsSize; + attsSize = n + nDefaultAtts + INIT_ATTS_SIZE; + atts = REALLOC((void *)atts, attsSize * sizeof(ATTRIBUTE)); + if (!atts) + return XML_ERROR_NO_MEMORY; + if (n > oldAttsSize) + XmlGetAttributes(enc, attStr, n, atts); + } + appAtts = (const XML_Char **)atts; + for (i = 0; i < n; i++) { + /* add the name and value to the attribute list */ + ATTRIBUTE_ID *attId = getAttributeId(parser, enc, atts[i].name, + atts[i].name + + XmlNameLength(enc, atts[i].name)); + if (!attId) + return XML_ERROR_NO_MEMORY; + /* detect duplicate attributes */ + if ((attId->name)[-1]) { + if (enc == encoding) + eventPtr = atts[i].name; + return XML_ERROR_DUPLICATE_ATTRIBUTE; + } + (attId->name)[-1] = 1; + appAtts[attIndex++] = attId->name; + if (!atts[i].normalized) { + enum XML_Error result; + int isCdata = 1; + + /* figure out whether declared as other than CDATA */ + if (attId->maybeTokenized) { + int j; + for (j = 0; j < nDefaultAtts; j++) { + if (attId == elementType->defaultAtts[j].id) { + isCdata = elementType->defaultAtts[j].isCdata; + break; + } + } + } + + /* normalize the attribute value */ + result = storeAttributeValue(parser, enc, isCdata, + atts[i].valuePtr, atts[i].valueEnd, + &tempPool); + if (result) + return result; + if (tagNamePtr) { + appAtts[attIndex] = poolStart(&tempPool); + poolFinish(&tempPool); + } + else + poolDiscard(&tempPool); + } + else if (tagNamePtr) { + /* the value did not need normalizing */ + appAtts[attIndex] = poolStoreString(&tempPool, enc, atts[i].valuePtr, atts[i].valueEnd); + if (appAtts[attIndex] == 0) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + } + /* handle prefixed attribute names */ + if (attId->prefix && tagNamePtr) { + if (attId->xmlns) { + /* deal with namespace declarations here */ + if (!addBinding(parser, attId->prefix, attId, appAtts[attIndex], bindingsPtr)) + return XML_ERROR_NO_MEMORY; + --attIndex; + } + else { + /* deal with other prefixed names later */ + attIndex++; + nPrefixes++; + (attId->name)[-1] = 2; + } + } + else + attIndex++; + } + if (tagNamePtr) { + int j; + nSpecifiedAtts = attIndex; + if (elementType->idAtt && (elementType->idAtt->name)[-1]) { + for (i = 0; i < attIndex; i += 2) + if (appAtts[i] == elementType->idAtt->name) { + idAttIndex = i; + break; + } + } + else + idAttIndex = -1; + /* do attribute defaulting */ + for (j = 0; j < nDefaultAtts; j++) { + const DEFAULT_ATTRIBUTE *da = elementType->defaultAtts + j; + if (!(da->id->name)[-1] && da->value) { + if (da->id->prefix) { + if (da->id->xmlns) { + if (!addBinding(parser, da->id->prefix, da->id, da->value, bindingsPtr)) + return XML_ERROR_NO_MEMORY; + } + else { + (da->id->name)[-1] = 2; + nPrefixes++; + appAtts[attIndex++] = da->id->name; + appAtts[attIndex++] = da->value; + } + } + else { + (da->id->name)[-1] = 1; + appAtts[attIndex++] = da->id->name; + appAtts[attIndex++] = da->value; + } + } + } + appAtts[attIndex] = 0; + } + i = 0; + if (nPrefixes) { + /* expand prefixed attribute names */ + for (; i < attIndex; i += 2) { + if (appAtts[i][-1] == 2) { + ATTRIBUTE_ID *id; + ((XML_Char *)(appAtts[i]))[-1] = 0; + id = (ATTRIBUTE_ID *)lookup(&dtd.attributeIds, appAtts[i], 0); + if (id->prefix->binding) { + int j; + const BINDING *b = id->prefix->binding; + const XML_Char *s = appAtts[i]; + for (j = 0; j < b->uriLen; j++) { + if (!poolAppendChar(&tempPool, b->uri[j])) + return XML_ERROR_NO_MEMORY; + } + while (*s++ != ':') + ; + do { + if (!poolAppendChar(&tempPool, *s)) + return XML_ERROR_NO_MEMORY; + } while (*s++); + if (ns_triplets) { + tempPool.ptr[-1] = namespaceSeparator; + s = b->prefix->name; + do { + if (!poolAppendChar(&tempPool, *s)) + return XML_ERROR_NO_MEMORY; + } while (*s++); + } + + appAtts[i] = poolStart(&tempPool); + poolFinish(&tempPool); + } + if (!--nPrefixes) + break; + } + else + ((XML_Char *)(appAtts[i]))[-1] = 0; + } + } + /* clear the flags that say whether attributes were specified */ + for (; i < attIndex; i += 2) + ((XML_Char *)(appAtts[i]))[-1] = 0; + if (!tagNamePtr) + return XML_ERROR_NONE; + for (binding = *bindingsPtr; binding; binding = binding->nextTagBinding) + binding->attId->name[-1] = 0; + /* expand the element type name */ + if (elementType->prefix) { + binding = elementType->prefix->binding; + if (!binding) + return XML_ERROR_NONE; + localPart = tagNamePtr->str; + while (*localPart++ != XML_T(':')) + ; + } + else if (dtd.defaultPrefix.binding) { + binding = dtd.defaultPrefix.binding; + localPart = tagNamePtr->str; + } + else + return XML_ERROR_NONE; + tagNamePtr->localPart = localPart; + tagNamePtr->uriLen = binding->uriLen; + for (i = 0; localPart[i++];) + ; + n = i + binding->uriLen; + if (n > binding->uriAlloc) { + TAG *p; + XML_Char *uri = MALLOC((n + EXPAND_SPARE) * sizeof(XML_Char)); + if (!uri) + return XML_ERROR_NO_MEMORY; + binding->uriAlloc = n + EXPAND_SPARE; + memcpy(uri, binding->uri, binding->uriLen * sizeof(XML_Char)); + for (p = tagStack; p; p = p->parent) + if (p->name.str == binding->uri) + p->name.str = uri; + FREE(binding->uri); + binding->uri = uri; + } + memcpy(binding->uri + binding->uriLen, localPart, i * sizeof(XML_Char)); + tagNamePtr->str = binding->uri; + return XML_ERROR_NONE; +} + +static +int addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId, const XML_Char *uri, BINDING **bindingsPtr) +{ + BINDING *b; + int len; + for (len = 0; uri[len]; len++) + ; + if (namespaceSeparator) + len++; + if (freeBindingList) { + b = freeBindingList; + if (len > b->uriAlloc) { + b->uri = REALLOC(b->uri, sizeof(XML_Char) * (len + EXPAND_SPARE)); + if (!b->uri) + return 0; + b->uriAlloc = len + EXPAND_SPARE; + } + freeBindingList = b->nextTagBinding; + } + else { + b = MALLOC(sizeof(BINDING)); + if (!b) + return 0; + b->uri = MALLOC(sizeof(XML_Char) * (len + EXPAND_SPARE)); + if (!b->uri) { + FREE(b); + return 0; + } + b->uriAlloc = len + EXPAND_SPARE; + } + b->uriLen = len; + memcpy(b->uri, uri, len * sizeof(XML_Char)); + if (namespaceSeparator) + b->uri[len - 1] = namespaceSeparator; + b->prefix = prefix; + b->attId = attId; + b->prevPrefixBinding = prefix->binding; + if (*uri == XML_T('\0') && prefix == &dtd.defaultPrefix) + prefix->binding = 0; + else + prefix->binding = b; + b->nextTagBinding = *bindingsPtr; + *bindingsPtr = b; + if (startNamespaceDeclHandler) + startNamespaceDeclHandler(handlerArg, prefix->name, + prefix->binding ? uri : 0); + return 1; +} + +/* The idea here is to avoid using stack for each CDATA section when +the whole file is parsed with one call. */ + +static +enum XML_Error cdataSectionProcessor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + enum XML_Error result = doCdataSection(parser, encoding, &start, end, endPtr); + if (start) { + processor = contentProcessor; + return contentProcessor(parser, start, end, endPtr); + } + return result; +} + +/* startPtr gets set to non-null is the section is closed, and to null if +the section is not yet closed. */ + +static +enum XML_Error doCdataSection(XML_Parser parser, + const ENCODING *enc, + const char **startPtr, + const char *end, + const char **nextPtr) +{ + const char *s = *startPtr; + const char **eventPP; + const char **eventEndPP; + if (enc == encoding) { + eventPP = &eventPtr; + *eventPP = s; + eventEndPP = &eventEndPtr; + } + else { + eventPP = &(openInternalEntities->internalEventPtr); + eventEndPP = &(openInternalEntities->internalEventEndPtr); + } + *eventPP = s; + *startPtr = 0; + for (;;) { + const char *next; + int tok = XmlCdataSectionTok(enc, s, end, &next); + *eventEndPP = next; + switch (tok) { + case XML_TOK_CDATA_SECT_CLOSE: + if (endCdataSectionHandler) + endCdataSectionHandler(handlerArg); +#if 0 + /* see comment under XML_TOK_CDATA_SECT_OPEN */ + else if (characterDataHandler) + characterDataHandler(handlerArg, dataBuf, 0); +#endif + else if (defaultHandler) + reportDefault(parser, enc, s, next); + *startPtr = next; + return XML_ERROR_NONE; + case XML_TOK_DATA_NEWLINE: + if (characterDataHandler) { + XML_Char c = 0xA; + characterDataHandler(handlerArg, &c, 1); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + case XML_TOK_DATA_CHARS: + if (characterDataHandler) { + if (MUST_CONVERT(enc, s)) { + for (;;) { + ICHAR *dataPtr = (ICHAR *)dataBuf; + XmlConvert(enc, &s, next, &dataPtr, (ICHAR *)dataBufEnd); + *eventEndPP = next; + characterDataHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf); + if (s == next) + break; + *eventPP = s; + } + } + else + characterDataHandler(handlerArg, + (XML_Char *)s, + (XML_Char *)next - (XML_Char *)s); + } + else if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_PARTIAL: + case XML_TOK_NONE: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_CDATA_SECTION; + default: + *eventPP = next; + return XML_ERROR_UNEXPECTED_STATE; + } + *eventPP = s = next; + } + /* not reached */ +} + +#ifdef XML_DTD + +/* The idea here is to avoid using stack for each IGNORE section when +the whole file is parsed with one call. */ + +static +enum XML_Error ignoreSectionProcessor(XML_Parser parser, + const char *start, + const char *end, + const char **endPtr) +{ + enum XML_Error result = doIgnoreSection(parser, encoding, &start, end, endPtr); + if (start) { + processor = prologProcessor; + return prologProcessor(parser, start, end, endPtr); + } + return result; +} + +/* startPtr gets set to non-null is the section is closed, and to null if +the section is not yet closed. */ + +static +enum XML_Error doIgnoreSection(XML_Parser parser, + const ENCODING *enc, + const char **startPtr, + const char *end, + const char **nextPtr) +{ + const char *next; + int tok; + const char *s = *startPtr; + const char **eventPP; + const char **eventEndPP; + if (enc == encoding) { + eventPP = &eventPtr; + *eventPP = s; + eventEndPP = &eventEndPtr; + } + else { + eventPP = &(openInternalEntities->internalEventPtr); + eventEndPP = &(openInternalEntities->internalEventEndPtr); + } + *eventPP = s; + *startPtr = 0; + tok = XmlIgnoreSectionTok(enc, s, end, &next); + *eventEndPP = next; + switch (tok) { + case XML_TOK_IGNORE_SECT: + if (defaultHandler) + reportDefault(parser, enc, s, next); + *startPtr = next; + return XML_ERROR_NONE; + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_PARTIAL: + case XML_TOK_NONE: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_SYNTAX; /* XML_ERROR_UNCLOSED_IGNORE_SECTION */ + default: + *eventPP = next; + return XML_ERROR_UNEXPECTED_STATE; + } + /* not reached */ +} + +#endif /* XML_DTD */ + +static enum XML_Error +initializeEncoding(XML_Parser parser) +{ + const char *s; +#ifdef XML_UNICODE + char encodingBuf[128]; + if (!protocolEncodingName) + s = 0; + else { + int i; + for (i = 0; protocolEncodingName[i]; i++) { + if (i == sizeof(encodingBuf) - 1 + || (protocolEncodingName[i] & ~0x7f) != 0) { + encodingBuf[0] = '\0'; + break; + } + encodingBuf[i] = (char)protocolEncodingName[i]; + } + encodingBuf[i] = '\0'; + s = encodingBuf; + } +#else + s = protocolEncodingName; +#endif + if ((ns ? XmlInitEncodingNS : XmlInitEncoding)(&initEncoding, &encoding, s)) + return XML_ERROR_NONE; + return handleUnknownEncoding(parser, protocolEncodingName); +} + +static enum XML_Error +processXmlDecl(XML_Parser parser, int isGeneralTextEntity, + const char *s, const char *next) +{ + const char *encodingName = 0; + const char *storedEncName = 0; + const ENCODING *newEncoding = 0; + const char *version = 0; + const char *versionend; + const char *storedversion = 0; + int standalone = -1; + if (!(ns + ? XmlParseXmlDeclNS + : XmlParseXmlDecl)(isGeneralTextEntity, + encoding, + s, + next, + &eventPtr, + &version, + &versionend, + &encodingName, + &newEncoding, + &standalone)) + return XML_ERROR_SYNTAX; + if (!isGeneralTextEntity && standalone == 1) { + dtd.standalone = 1; +#ifdef XML_DTD + if (paramEntityParsing == XML_PARAM_ENTITY_PARSING_UNLESS_STANDALONE) + paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER; +#endif /* XML_DTD */ + } + if (xmlDeclHandler) { + if (encodingName) { + storedEncName = poolStoreString(&temp2Pool, + encoding, + encodingName, + encodingName + + XmlNameLength(encoding, encodingName)); + if (! storedEncName) + return XML_ERROR_NO_MEMORY; + poolFinish(&temp2Pool); + } + if (version) { + storedversion = poolStoreString(&temp2Pool, + encoding, + version, + versionend - encoding->minBytesPerChar); + if (! storedversion) + return XML_ERROR_NO_MEMORY; + } + xmlDeclHandler(handlerArg, storedversion, storedEncName, standalone); + } + else if (defaultHandler) + reportDefault(parser, encoding, s, next); + if (!protocolEncodingName) { + if (newEncoding) { + if (newEncoding->minBytesPerChar != encoding->minBytesPerChar) { + eventPtr = encodingName; + return XML_ERROR_INCORRECT_ENCODING; + } + encoding = newEncoding; + } + else if (encodingName) { + enum XML_Error result; + if (! storedEncName) { + storedEncName = poolStoreString(&temp2Pool, + encoding, + encodingName, + encodingName + + XmlNameLength(encoding, encodingName)); + if (! storedEncName) + return XML_ERROR_NO_MEMORY; + } + result = handleUnknownEncoding(parser, storedEncName); + poolClear(&tempPool); + if (result == XML_ERROR_UNKNOWN_ENCODING) + eventPtr = encodingName; + return result; + } + } + + if (storedEncName || storedversion) + poolClear(&temp2Pool); + + return XML_ERROR_NONE; +} + +static enum XML_Error +handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName) +{ + if (unknownEncodingHandler) { + XML_Encoding info; + int i; + for (i = 0; i < 256; i++) + info.map[i] = -1; + info.convert = 0; + info.data = 0; + info.release = 0; + if (unknownEncodingHandler(unknownEncodingHandlerData, encodingName, &info)) { + ENCODING *enc; + unknownEncodingMem = MALLOC(XmlSizeOfUnknownEncoding()); + if (!unknownEncodingMem) { + if (info.release) + info.release(info.data); + return XML_ERROR_NO_MEMORY; + } + enc = (ns + ? XmlInitUnknownEncodingNS + : XmlInitUnknownEncoding)(unknownEncodingMem, + info.map, + info.convert, + info.data); + if (enc) { + unknownEncodingData = info.data; + unknownEncodingRelease = info.release; + encoding = enc; + return XML_ERROR_NONE; + } + } + if (info.release) + info.release(info.data); + } + return XML_ERROR_UNKNOWN_ENCODING; +} + +static enum XML_Error +prologInitProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + enum XML_Error result = initializeEncoding(parser); + if (result != XML_ERROR_NONE) + return result; + processor = prologProcessor; + return prologProcessor(parser, s, end, nextPtr); +} + +static enum XML_Error +prologProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + const char *next; + int tok = XmlPrologTok(encoding, s, end, &next); + return doProlog(parser, encoding, s, end, tok, next, nextPtr); +} + +static enum XML_Error +doProlog(XML_Parser parser, + const ENCODING *enc, + const char *s, + const char *end, + int tok, + const char *next, + const char **nextPtr) +{ +#ifdef XML_DTD + static const XML_Char externalSubsetName[] = { '#' , '\0' }; +#endif /* XML_DTD */ + + const char **eventPP; + const char **eventEndPP; + enum XML_Content_Quant quant; + + if (enc == encoding) { + eventPP = &eventPtr; + eventEndPP = &eventEndPtr; + } + else { + eventPP = &(openInternalEntities->internalEventPtr); + eventEndPP = &(openInternalEntities->internalEventEndPtr); + } + for (;;) { + int role; + *eventPP = s; + *eventEndPP = next; + if (tok <= 0) { + if (nextPtr != 0 && tok != XML_TOK_INVALID) { + *nextPtr = s; + return XML_ERROR_NONE; + } + switch (tok) { + case XML_TOK_INVALID: + *eventPP = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + return XML_ERROR_PARTIAL_CHAR; + case XML_TOK_NONE: +#ifdef XML_DTD + if (enc != encoding) + return XML_ERROR_NONE; + if (parentParser) { + if (XmlTokenRole(&prologState, XML_TOK_NONE, end, end, enc) + == XML_ROLE_ERROR) + return XML_ERROR_SYNTAX; + hadExternalDoctype = 0; + return XML_ERROR_NONE; + } +#endif /* XML_DTD */ + return XML_ERROR_NO_ELEMENTS; + default: + tok = -tok; + next = end; + break; + } + } + role = XmlTokenRole(&prologState, tok, s, next, enc); + switch (role) { + case XML_ROLE_XML_DECL: + { + enum XML_Error result = processXmlDecl(parser, 0, s, next); + if (result != XML_ERROR_NONE) + return result; + enc = encoding; + } + break; + case XML_ROLE_DOCTYPE_NAME: + if (startDoctypeDeclHandler) { + doctypeName = poolStoreString(&tempPool, enc, s, next); + if (! doctypeName) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + doctypeSysid = 0; + doctypePubid = 0; + } + break; + case XML_ROLE_DOCTYPE_INTERNAL_SUBSET: + if (startDoctypeDeclHandler) { + startDoctypeDeclHandler(handlerArg, doctypeName, doctypeSysid, + doctypePubid, 1); + doctypeName = 0; + poolClear(&tempPool); + } + break; +#ifdef XML_DTD + case XML_ROLE_TEXT_DECL: + { + enum XML_Error result = processXmlDecl(parser, 1, s, next); + if (result != XML_ERROR_NONE) + return result; + enc = encoding; + } + break; +#endif /* XML_DTD */ + case XML_ROLE_DOCTYPE_PUBLIC_ID: + if (startDoctypeDeclHandler) { + doctypePubid = poolStoreString(&tempPool, enc, s + 1, next - 1); + if (! doctypePubid) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + } +#ifdef XML_DTD + declEntity = (ENTITY *)lookup(&dtd.paramEntities, + externalSubsetName, + sizeof(ENTITY)); + if (!declEntity) + return XML_ERROR_NO_MEMORY; +#endif /* XML_DTD */ + /* fall through */ + case XML_ROLE_ENTITY_PUBLIC_ID: + if (!XmlIsPublicId(enc, s, next, eventPP)) + return XML_ERROR_SYNTAX; + if (declEntity) { + XML_Char *tem = poolStoreString(&dtd.pool, + enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!tem) + return XML_ERROR_NO_MEMORY; + normalizePublicId(tem); + declEntity->publicId = tem; + poolFinish(&dtd.pool); + } + break; + case XML_ROLE_DOCTYPE_CLOSE: + if (doctypeName) { + startDoctypeDeclHandler(handlerArg, doctypeName, + doctypeSysid, doctypePubid, 0); + poolClear(&tempPool); + } + if (dtd.complete && hadExternalDoctype) { + dtd.complete = 0; +#ifdef XML_DTD + if (paramEntityParsing && externalEntityRefHandler) { + ENTITY *entity = (ENTITY *)lookup(&dtd.paramEntities, + externalSubsetName, + 0); + if (!externalEntityRefHandler(externalEntityRefHandlerArg, + 0, + entity->base, + entity->systemId, + entity->publicId)) + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + } +#endif /* XML_DTD */ + if (!dtd.complete + && !dtd.standalone + && notStandaloneHandler + && !notStandaloneHandler(handlerArg)) + return XML_ERROR_NOT_STANDALONE; + } + if (endDoctypeDeclHandler) + endDoctypeDeclHandler(handlerArg); + break; + case XML_ROLE_INSTANCE_START: + processor = contentProcessor; + return contentProcessor(parser, s, end, nextPtr); + case XML_ROLE_ATTLIST_ELEMENT_NAME: + declElementType = getElementType(parser, enc, s, next); + if (!declElementType) + return XML_ERROR_NO_MEMORY; + break; + case XML_ROLE_ATTRIBUTE_NAME: + declAttributeId = getAttributeId(parser, enc, s, next); + if (!declAttributeId) + return XML_ERROR_NO_MEMORY; + declAttributeIsCdata = 0; + declAttributeType = 0; + declAttributeIsId = 0; + break; + case XML_ROLE_ATTRIBUTE_TYPE_CDATA: + declAttributeIsCdata = 1; + declAttributeType = "CDATA"; + break; + case XML_ROLE_ATTRIBUTE_TYPE_ID: + declAttributeIsId = 1; + declAttributeType = "ID"; + break; + case XML_ROLE_ATTRIBUTE_TYPE_IDREF: + declAttributeType = "IDREF"; + break; + case XML_ROLE_ATTRIBUTE_TYPE_IDREFS: + declAttributeType = "IDREFS"; + break; + case XML_ROLE_ATTRIBUTE_TYPE_ENTITY: + declAttributeType = "ENTITY"; + break; + case XML_ROLE_ATTRIBUTE_TYPE_ENTITIES: + declAttributeType = "ENTITIES"; + break; + case XML_ROLE_ATTRIBUTE_TYPE_NMTOKEN: + declAttributeType = "NMTOKEN"; + break; + case XML_ROLE_ATTRIBUTE_TYPE_NMTOKENS: + declAttributeType = "NMTOKENS"; + break; + + case XML_ROLE_ATTRIBUTE_ENUM_VALUE: + case XML_ROLE_ATTRIBUTE_NOTATION_VALUE: + if (attlistDeclHandler) + { + char *prefix; + if (declAttributeType) { + prefix = "|"; + } + else { + prefix = (role == XML_ROLE_ATTRIBUTE_NOTATION_VALUE + ? "NOTATION(" + : "("); + } + if (! poolAppendString(&tempPool, prefix)) + return XML_ERROR_NO_MEMORY; + if (! poolAppend(&tempPool, enc, s, next)) + return XML_ERROR_NO_MEMORY; + declAttributeType = tempPool.start; + } + break; + case XML_ROLE_IMPLIED_ATTRIBUTE_VALUE: + case XML_ROLE_REQUIRED_ATTRIBUTE_VALUE: + if (dtd.complete + && !defineAttribute(declElementType, declAttributeId, + declAttributeIsCdata, declAttributeIsId, 0, + parser)) + return XML_ERROR_NO_MEMORY; + if (attlistDeclHandler && declAttributeType) { + if (*declAttributeType == '(' + || (*declAttributeType == 'N' && declAttributeType[1] == 'O')) { + /* Enumerated or Notation type */ + if (! poolAppendChar(&tempPool, ')') + || ! poolAppendChar(&tempPool, '\0')) + return XML_ERROR_NO_MEMORY; + declAttributeType = tempPool.start; + poolFinish(&tempPool); + } + *eventEndPP = s; + attlistDeclHandler(handlerArg, declElementType->name, + declAttributeId->name, declAttributeType, + 0, role == XML_ROLE_REQUIRED_ATTRIBUTE_VALUE); + poolClear(&tempPool); + } + break; + case XML_ROLE_DEFAULT_ATTRIBUTE_VALUE: + case XML_ROLE_FIXED_ATTRIBUTE_VALUE: + { + const XML_Char *attVal; + enum XML_Error result + = storeAttributeValue(parser, enc, declAttributeIsCdata, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar, + &dtd.pool); + if (result) + return result; + attVal = poolStart(&dtd.pool); + poolFinish(&dtd.pool); + if (dtd.complete + /* ID attributes aren't allowed to have a default */ + && !defineAttribute(declElementType, declAttributeId, declAttributeIsCdata, 0, attVal, parser)) + return XML_ERROR_NO_MEMORY; + if (attlistDeclHandler && declAttributeType) { + if (*declAttributeType == '(' + || (*declAttributeType == 'N' && declAttributeType[1] == 'O')) { + /* Enumerated or Notation type */ + if (! poolAppendChar(&tempPool, ')') + || ! poolAppendChar(&tempPool, '\0')) + return XML_ERROR_NO_MEMORY; + declAttributeType = tempPool.start; + poolFinish(&tempPool); + } + *eventEndPP = s; + attlistDeclHandler(handlerArg, declElementType->name, + declAttributeId->name, declAttributeType, + attVal, + role == XML_ROLE_FIXED_ATTRIBUTE_VALUE); + poolClear(&tempPool); + } + break; + } + case XML_ROLE_ENTITY_VALUE: + { + enum XML_Error result = storeEntityValue(parser, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (declEntity) { + declEntity->textPtr = poolStart(&dtd.pool); + declEntity->textLen = poolLength(&dtd.pool); + poolFinish(&dtd.pool); + if (entityDeclHandler) { + *eventEndPP = s; + entityDeclHandler(handlerArg, + declEntity->name, + declEntity->is_param, + declEntity->textPtr, + declEntity->textLen, + curBase, 0, 0, 0); + } + } + else + poolDiscard(&dtd.pool); + if (result != XML_ERROR_NONE) + return result; + } + break; + case XML_ROLE_DOCTYPE_SYSTEM_ID: + if (startDoctypeDeclHandler) { + doctypeSysid = poolStoreString(&tempPool, enc, s + 1, next - 1); + if (! doctypeSysid) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + } + if (!dtd.standalone +#ifdef XML_DTD + && !paramEntityParsing +#endif /* XML_DTD */ + && notStandaloneHandler + && !notStandaloneHandler(handlerArg)) + return XML_ERROR_NOT_STANDALONE; + hadExternalDoctype = 1; +#ifndef XML_DTD + break; +#else /* XML_DTD */ + if (!declEntity) { + declEntity = (ENTITY *)lookup(&dtd.paramEntities, + externalSubsetName, + sizeof(ENTITY)); + declEntity->publicId = 0; + if (!declEntity) + return XML_ERROR_NO_MEMORY; + } + /* fall through */ +#endif /* XML_DTD */ + case XML_ROLE_ENTITY_SYSTEM_ID: + if (declEntity) { + declEntity->systemId = poolStoreString(&dtd.pool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!declEntity->systemId) + return XML_ERROR_NO_MEMORY; + declEntity->base = curBase; + poolFinish(&dtd.pool); + } + break; + case XML_ROLE_ENTITY_COMPLETE: + if (declEntity && entityDeclHandler) { + *eventEndPP = s; + entityDeclHandler(handlerArg, + declEntity->name, + 0,0,0, + declEntity->base, + declEntity->systemId, + declEntity->publicId, + 0); + } + break; + case XML_ROLE_ENTITY_NOTATION_NAME: + if (declEntity) { + declEntity->notation = poolStoreString(&dtd.pool, enc, s, next); + if (!declEntity->notation) + return XML_ERROR_NO_MEMORY; + poolFinish(&dtd.pool); + if (unparsedEntityDeclHandler) { + *eventEndPP = s; + unparsedEntityDeclHandler(handlerArg, + declEntity->name, + declEntity->base, + declEntity->systemId, + declEntity->publicId, + declEntity->notation); + } + else if (entityDeclHandler) { + *eventEndPP = s; + entityDeclHandler(handlerArg, + declEntity->name, + 0,0,0, + declEntity->base, + declEntity->systemId, + declEntity->publicId, + declEntity->notation); + } + } + break; + case XML_ROLE_GENERAL_ENTITY_NAME: + { + const XML_Char *name; + if (XmlPredefinedEntityName(enc, s, next)) { + declEntity = 0; + break; + } + name = poolStoreString(&dtd.pool, enc, s, next); + if (!name) + return XML_ERROR_NO_MEMORY; + if (dtd.complete) { + declEntity = (ENTITY *)lookup(&dtd.generalEntities, name, sizeof(ENTITY)); + if (!declEntity) + return XML_ERROR_NO_MEMORY; + if (declEntity->name != name) { + poolDiscard(&dtd.pool); + declEntity = 0; + } + else { + poolFinish(&dtd.pool); + declEntity->publicId = 0; + declEntity->is_param = 0; + } + } + else { + poolDiscard(&dtd.pool); + declEntity = 0; + } + } + break; + case XML_ROLE_PARAM_ENTITY_NAME: +#ifdef XML_DTD + if (dtd.complete) { + const XML_Char *name = poolStoreString(&dtd.pool, enc, s, next); + if (!name) + return XML_ERROR_NO_MEMORY; + declEntity = (ENTITY *)lookup(&dtd.paramEntities, + name, sizeof(ENTITY)); + if (!declEntity) + return XML_ERROR_NO_MEMORY; + if (declEntity->name != name) { + poolDiscard(&dtd.pool); + declEntity = 0; + } + else { + poolFinish(&dtd.pool); + declEntity->publicId = 0; + declEntity->is_param = 1; + } + } +#else /* not XML_DTD */ + declEntity = 0; +#endif /* not XML_DTD */ + break; + case XML_ROLE_NOTATION_NAME: + declNotationPublicId = 0; + declNotationName = 0; + if (notationDeclHandler) { + declNotationName = poolStoreString(&tempPool, enc, s, next); + if (!declNotationName) + return XML_ERROR_NO_MEMORY; + poolFinish(&tempPool); + } + break; + case XML_ROLE_NOTATION_PUBLIC_ID: + if (!XmlIsPublicId(enc, s, next, eventPP)) + return XML_ERROR_SYNTAX; + if (declNotationName) { + XML_Char *tem = poolStoreString(&tempPool, + enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!tem) + return XML_ERROR_NO_MEMORY; + normalizePublicId(tem); + declNotationPublicId = tem; + poolFinish(&tempPool); + } + break; + case XML_ROLE_NOTATION_SYSTEM_ID: + if (declNotationName && notationDeclHandler) { + const XML_Char *systemId + = poolStoreString(&tempPool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!systemId) + return XML_ERROR_NO_MEMORY; + *eventEndPP = s; + notationDeclHandler(handlerArg, + declNotationName, + curBase, + systemId, + declNotationPublicId); + } + poolClear(&tempPool); + break; + case XML_ROLE_NOTATION_NO_SYSTEM_ID: + if (declNotationPublicId && notationDeclHandler) { + *eventEndPP = s; + notationDeclHandler(handlerArg, + declNotationName, + curBase, + 0, + declNotationPublicId); + } + poolClear(&tempPool); + break; + case XML_ROLE_ERROR: + switch (tok) { + case XML_TOK_PARAM_ENTITY_REF: + return XML_ERROR_PARAM_ENTITY_REF; + case XML_TOK_XML_DECL: + return XML_ERROR_MISPLACED_XML_PI; + default: + return XML_ERROR_SYNTAX; + } +#ifdef XML_DTD + case XML_ROLE_IGNORE_SECT: + { + enum XML_Error result; + if (defaultHandler) + reportDefault(parser, enc, s, next); + result = doIgnoreSection(parser, enc, &next, end, nextPtr); + if (!next) { + processor = ignoreSectionProcessor; + return result; + } + } + break; +#endif /* XML_DTD */ + case XML_ROLE_GROUP_OPEN: + if (prologState.level >= groupSize) { + if (groupSize) { + groupConnector = REALLOC(groupConnector, groupSize *= 2); + if (dtd.scaffIndex) + dtd.scaffIndex = REALLOC(dtd.scaffIndex, groupSize * sizeof(int)); + } + else + groupConnector = MALLOC(groupSize = 32); + if (!groupConnector) + return XML_ERROR_NO_MEMORY; + } + groupConnector[prologState.level] = 0; + if (dtd.in_eldecl) { + int myindex = nextScaffoldPart(parser); + if (myindex < 0) + return XML_ERROR_NO_MEMORY; + dtd.scaffIndex[dtd.scaffLevel] = myindex; + dtd.scaffLevel++; + dtd.scaffold[myindex].type = XML_CTYPE_SEQ; + } + break; + case XML_ROLE_GROUP_SEQUENCE: + if (groupConnector[prologState.level] == '|') + return XML_ERROR_SYNTAX; + groupConnector[prologState.level] = ','; + break; + case XML_ROLE_GROUP_CHOICE: + if (groupConnector[prologState.level] == ',') + return XML_ERROR_SYNTAX; + if (dtd.in_eldecl + && ! groupConnector[prologState.level] + && dtd.scaffold[dtd.scaffIndex[dtd.scaffLevel - 1]].type != XML_CTYPE_MIXED + ) { + dtd.scaffold[dtd.scaffIndex[dtd.scaffLevel - 1]].type = XML_CTYPE_CHOICE; + } + groupConnector[prologState.level] = '|'; + break; + case XML_ROLE_PARAM_ENTITY_REF: +#ifdef XML_DTD + case XML_ROLE_INNER_PARAM_ENTITY_REF: + if (paramEntityParsing + && (dtd.complete || role == XML_ROLE_INNER_PARAM_ENTITY_REF)) { + const XML_Char *name; + ENTITY *entity; + name = poolStoreString(&dtd.pool, enc, + s + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(&dtd.paramEntities, name, 0); + poolDiscard(&dtd.pool); + if (!entity) { + /* FIXME what to do if !dtd.complete? */ + return XML_ERROR_UNDEFINED_ENTITY; + } + if (entity->open) + return XML_ERROR_RECURSIVE_ENTITY_REF; + if (entity->textPtr) { + enum XML_Error result; + result = processInternalParamEntity(parser, entity); + if (result != XML_ERROR_NONE) + return result; + break; + } + if (role == XML_ROLE_INNER_PARAM_ENTITY_REF) + return XML_ERROR_PARAM_ENTITY_REF; + if (externalEntityRefHandler) { + dtd.complete = 0; + entity->open = 1; + if (!externalEntityRefHandler(externalEntityRefHandlerArg, + 0, + entity->base, + entity->systemId, + entity->publicId)) { + entity->open = 0; + return XML_ERROR_EXTERNAL_ENTITY_HANDLING; + } + entity->open = 0; + if (dtd.complete) + break; + } + } +#endif /* XML_DTD */ + if (!dtd.standalone + && notStandaloneHandler + && !notStandaloneHandler(handlerArg)) + return XML_ERROR_NOT_STANDALONE; + dtd.complete = 0; + if (defaultHandler) + reportDefault(parser, enc, s, next); + break; + + /* Element declaration stuff */ + + case XML_ROLE_ELEMENT_NAME: + if (elementDeclHandler) { + declElementType = getElementType(parser, enc, s, next); + if (! declElementType) + return XML_ERROR_NO_MEMORY; + dtd.scaffLevel = 0; + dtd.scaffCount = 0; + dtd.in_eldecl = 1; + } + break; + + case XML_ROLE_CONTENT_ANY: + case XML_ROLE_CONTENT_EMPTY: + if (dtd.in_eldecl) { + if (elementDeclHandler) { + XML_Content * content = (XML_Content *) MALLOC(sizeof(XML_Content)); + if (! content) + return XML_ERROR_NO_MEMORY; + content->quant = XML_CQUANT_NONE; + content->name = 0; + content->numchildren = 0; + content->children = 0; + content->type = ((role == XML_ROLE_CONTENT_ANY) ? + XML_CTYPE_ANY : + XML_CTYPE_EMPTY); + *eventEndPP = s; + elementDeclHandler(handlerArg, declElementType->name, content); + } + dtd.in_eldecl = 0; + } + break; + + case XML_ROLE_CONTENT_PCDATA: + if (dtd.in_eldecl) { + dtd.scaffold[dtd.scaffIndex[dtd.scaffLevel - 1]].type = XML_CTYPE_MIXED; + } + break; + + case XML_ROLE_CONTENT_ELEMENT: + quant = XML_CQUANT_NONE; + goto elementContent; + case XML_ROLE_CONTENT_ELEMENT_OPT: + quant = XML_CQUANT_OPT; + goto elementContent; + case XML_ROLE_CONTENT_ELEMENT_REP: + quant = XML_CQUANT_REP; + goto elementContent; + case XML_ROLE_CONTENT_ELEMENT_PLUS: + quant = XML_CQUANT_PLUS; + elementContent: + if (dtd.in_eldecl) + { + ELEMENT_TYPE *el; + const char *nxt = quant == XML_CQUANT_NONE ? next : next - 1; + int myindex = nextScaffoldPart(parser); + if (myindex < 0) + return XML_ERROR_NO_MEMORY; + dtd.scaffold[myindex].type = XML_CTYPE_NAME; + dtd.scaffold[myindex].quant = quant; + el = getElementType(parser, enc, s, nxt); + if (! el) + return XML_ERROR_NO_MEMORY; + dtd.scaffold[myindex].name = el->name; + dtd.contentStringLen += nxt - s + 1; + } + break; + + case XML_ROLE_GROUP_CLOSE: + quant = XML_CQUANT_NONE; + goto closeGroup; + case XML_ROLE_GROUP_CLOSE_OPT: + quant = XML_CQUANT_OPT; + goto closeGroup; + case XML_ROLE_GROUP_CLOSE_REP: + quant = XML_CQUANT_REP; + goto closeGroup; + case XML_ROLE_GROUP_CLOSE_PLUS: + quant = XML_CQUANT_PLUS; + closeGroup: + if (dtd.in_eldecl) { + dtd.scaffLevel--; + dtd.scaffold[dtd.scaffIndex[dtd.scaffLevel]].quant = quant; + if (dtd.scaffLevel == 0) { + if (elementDeclHandler) { + XML_Content *model = build_model(parser); + if (! model) + return XML_ERROR_NO_MEMORY; + *eventEndPP = s; + elementDeclHandler(handlerArg, declElementType->name, model); + } + dtd.in_eldecl = 0; + dtd.contentStringLen = 0; + } + } + break; + /* End element declaration stuff */ + + case XML_ROLE_NONE: + switch (tok) { + case XML_TOK_PI: + if (!reportProcessingInstruction(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_COMMENT: + if (!reportComment(parser, enc, s, next)) + return XML_ERROR_NO_MEMORY; + break; + } + break; + } + if (defaultHandler) { + switch (tok) { + case XML_TOK_PI: + case XML_TOK_COMMENT: + case XML_TOK_BOM: + case XML_TOK_XML_DECL: +#ifdef XML_DTD + case XML_TOK_IGNORE_SECT: +#endif /* XML_DTD */ + case XML_TOK_PARAM_ENTITY_REF: + break; + default: +#ifdef XML_DTD + if (role != XML_ROLE_IGNORE_SECT) +#endif /* XML_DTD */ + reportDefault(parser, enc, s, next); + } + } + s = next; + tok = XmlPrologTok(enc, s, end, &next); + } + /* not reached */ +} + +static +enum XML_Error epilogProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + processor = epilogProcessor; + eventPtr = s; + for (;;) { + const char *next; + int tok = XmlPrologTok(encoding, s, end, &next); + eventEndPtr = next; + switch (tok) { + case -XML_TOK_PROLOG_S: + if (defaultHandler) { + eventEndPtr = end; + reportDefault(parser, encoding, s, end); + } + /* fall through */ + case XML_TOK_NONE: + if (nextPtr) + *nextPtr = end; + return XML_ERROR_NONE; + case XML_TOK_PROLOG_S: + if (defaultHandler) + reportDefault(parser, encoding, s, next); + break; + case XML_TOK_PI: + if (!reportProcessingInstruction(parser, encoding, s, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_COMMENT: + if (!reportComment(parser, encoding, s, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_INVALID: + eventPtr = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_UNCLOSED_TOKEN; + case XML_TOK_PARTIAL_CHAR: + if (nextPtr) { + *nextPtr = s; + return XML_ERROR_NONE; + } + return XML_ERROR_PARTIAL_CHAR; + default: + return XML_ERROR_JUNK_AFTER_DOC_ELEMENT; + } + eventPtr = s = next; + } +} + +#ifdef XML_DTD + +static enum XML_Error +processInternalParamEntity(XML_Parser parser, ENTITY *entity) +{ + const char *s, *end, *next; + int tok; + enum XML_Error result; + OPEN_INTERNAL_ENTITY openEntity; + entity->open = 1; + openEntity.next = openInternalEntities; + openInternalEntities = &openEntity; + openEntity.entity = entity; + openEntity.internalEventPtr = 0; + openEntity.internalEventEndPtr = 0; + s = (char *)entity->textPtr; + end = (char *)(entity->textPtr + entity->textLen); + tok = XmlPrologTok(internalEncoding, s, end, &next); + result = doProlog(parser, internalEncoding, s, end, tok, next, 0); + entity->open = 0; + openInternalEntities = openEntity.next; + return result; +} + +#endif /* XML_DTD */ + +static +enum XML_Error errorProcessor(XML_Parser parser, + const char *s, + const char *end, + const char **nextPtr) +{ + return errorCode; +} + +static enum XML_Error +storeAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata, + const char *ptr, const char *end, + STRING_POOL *pool) +{ + enum XML_Error result = appendAttributeValue(parser, enc, isCdata, ptr, end, pool); + if (result) + return result; + if (!isCdata && poolLength(pool) && poolLastChar(pool) == 0x20) + poolChop(pool); + if (!poolAppendChar(pool, XML_T('\0'))) + return XML_ERROR_NO_MEMORY; + return XML_ERROR_NONE; +} + +static enum XML_Error +appendAttributeValue(XML_Parser parser, const ENCODING *enc, int isCdata, + const char *ptr, const char *end, + STRING_POOL *pool) +{ + for (;;) { + const char *next; + int tok = XmlAttributeValueTok(enc, ptr, end, &next); + switch (tok) { + case XML_TOK_NONE: + return XML_ERROR_NONE; + case XML_TOK_INVALID: + if (enc == encoding) + eventPtr = next; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_PARTIAL: + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_CHAR_REF: + { + XML_Char buf[XML_ENCODE_MAX]; + int i; + int n = XmlCharRefNumber(enc, ptr); + if (n < 0) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_BAD_CHAR_REF; + } + if (!isCdata + && n == 0x20 /* space */ + && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) + break; + n = XmlEncode(n, (ICHAR *)buf); + if (!n) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_BAD_CHAR_REF; + } + for (i = 0; i < n; i++) { + if (!poolAppendChar(pool, buf[i])) + return XML_ERROR_NO_MEMORY; + } + } + break; + case XML_TOK_DATA_CHARS: + if (!poolAppend(pool, enc, ptr, next)) + return XML_ERROR_NO_MEMORY; + break; + break; + case XML_TOK_TRAILING_CR: + next = ptr + enc->minBytesPerChar; + /* fall through */ + case XML_TOK_ATTRIBUTE_VALUE_S: + case XML_TOK_DATA_NEWLINE: + if (!isCdata && (poolLength(pool) == 0 || poolLastChar(pool) == 0x20)) + break; + if (!poolAppendChar(pool, 0x20)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_ENTITY_REF: + { + const XML_Char *name; + ENTITY *entity; + XML_Char ch = XmlPredefinedEntityName(enc, + ptr + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (ch) { + if (!poolAppendChar(pool, ch)) + return XML_ERROR_NO_MEMORY; + break; + } + name = poolStoreString(&temp2Pool, enc, + ptr + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(&dtd.generalEntities, name, 0); + poolDiscard(&temp2Pool); + if (!entity) { + if (dtd.complete) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_UNDEFINED_ENTITY; + } + } + else if (entity->open) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_RECURSIVE_ENTITY_REF; + } + else if (entity->notation) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_BINARY_ENTITY_REF; + } + else if (!entity->textPtr) { + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF; + } + else { + enum XML_Error result; + const XML_Char *textEnd = entity->textPtr + entity->textLen; + entity->open = 1; + result = appendAttributeValue(parser, internalEncoding, isCdata, (char *)entity->textPtr, (char *)textEnd, pool); + entity->open = 0; + if (result) + return result; + } + } + break; + default: + if (enc == encoding) + eventPtr = ptr; + return XML_ERROR_UNEXPECTED_STATE; + } + ptr = next; + } + /* not reached */ +} + +static +enum XML_Error storeEntityValue(XML_Parser parser, + const ENCODING *enc, + const char *entityTextPtr, + const char *entityTextEnd) +{ + STRING_POOL *pool = &(dtd.pool); + for (;;) { + const char *next; + int tok = XmlEntityValueTok(enc, entityTextPtr, entityTextEnd, &next); + switch (tok) { + case XML_TOK_PARAM_ENTITY_REF: +#ifdef XML_DTD + if (parentParser || enc != encoding) { + enum XML_Error result; + const XML_Char *name; + ENTITY *entity; + name = poolStoreString(&tempPool, enc, + entityTextPtr + enc->minBytesPerChar, + next - enc->minBytesPerChar); + if (!name) + return XML_ERROR_NO_MEMORY; + entity = (ENTITY *)lookup(&dtd.paramEntities, name, 0); + poolDiscard(&tempPool); + if (!entity) { + if (enc == encoding) + eventPtr = entityTextPtr; + return XML_ERROR_UNDEFINED_ENTITY; + } + if (entity->open) { + if (enc == encoding) + eventPtr = entityTextPtr; + return XML_ERROR_RECURSIVE_ENTITY_REF; + } + if (entity->systemId) { + if (enc == encoding) + eventPtr = entityTextPtr; + return XML_ERROR_PARAM_ENTITY_REF; + } + entity->open = 1; + result = storeEntityValue(parser, + internalEncoding, + (char *)entity->textPtr, + (char *)(entity->textPtr + entity->textLen)); + entity->open = 0; + if (result) + return result; + break; + } +#endif /* XML_DTD */ + eventPtr = entityTextPtr; + return XML_ERROR_SYNTAX; + case XML_TOK_NONE: + return XML_ERROR_NONE; + case XML_TOK_ENTITY_REF: + case XML_TOK_DATA_CHARS: + if (!poolAppend(pool, enc, entityTextPtr, next)) + return XML_ERROR_NO_MEMORY; + break; + case XML_TOK_TRAILING_CR: + next = entityTextPtr + enc->minBytesPerChar; + /* fall through */ + case XML_TOK_DATA_NEWLINE: + if (pool->end == pool->ptr && !poolGrow(pool)) + return XML_ERROR_NO_MEMORY; + *(pool->ptr)++ = 0xA; + break; + case XML_TOK_CHAR_REF: + { + XML_Char buf[XML_ENCODE_MAX]; + int i; + int n = XmlCharRefNumber(enc, entityTextPtr); + if (n < 0) { + if (enc == encoding) + eventPtr = entityTextPtr; + return XML_ERROR_BAD_CHAR_REF; + } + n = XmlEncode(n, (ICHAR *)buf); + if (!n) { + if (enc == encoding) + eventPtr = entityTextPtr; + return XML_ERROR_BAD_CHAR_REF; + } + for (i = 0; i < n; i++) { + if (pool->end == pool->ptr && !poolGrow(pool)) + return XML_ERROR_NO_MEMORY; + *(pool->ptr)++ = buf[i]; + } + } + break; + case XML_TOK_PARTIAL: + if (enc == encoding) + eventPtr = entityTextPtr; + return XML_ERROR_INVALID_TOKEN; + case XML_TOK_INVALID: + if (enc == encoding) + eventPtr = next; + return XML_ERROR_INVALID_TOKEN; + default: + if (enc == encoding) + eventPtr = entityTextPtr; + return XML_ERROR_UNEXPECTED_STATE; + } + entityTextPtr = next; + } + /* not reached */ +} + +static void +normalizeLines(XML_Char *s) +{ + XML_Char *p; + for (;; s++) { + if (*s == XML_T('\0')) + return; + if (*s == 0xD) + break; + } + p = s; + do { + if (*s == 0xD) { + *p++ = 0xA; + if (*++s == 0xA) + s++; + } + else + *p++ = *s++; + } while (*s); + *p = XML_T('\0'); +} + +static int +reportProcessingInstruction(XML_Parser parser, const ENCODING *enc, const char *start, const char *end) +{ + const XML_Char *target; + XML_Char *data; + const char *tem; + if (!processingInstructionHandler) { + if (defaultHandler) + reportDefault(parser, enc, start, end); + return 1; + } + start += enc->minBytesPerChar * 2; + tem = start + XmlNameLength(enc, start); + target = poolStoreString(&tempPool, enc, start, tem); + if (!target) + return 0; + poolFinish(&tempPool); + data = poolStoreString(&tempPool, enc, + XmlSkipS(enc, tem), + end - enc->minBytesPerChar*2); + if (!data) + return 0; + normalizeLines(data); + processingInstructionHandler(handlerArg, target, data); + poolClear(&tempPool); + return 1; +} + +static int +reportComment(XML_Parser parser, const ENCODING *enc, const char *start, const char *end) +{ + XML_Char *data; + if (!commentHandler) { + if (defaultHandler) + reportDefault(parser, enc, start, end); + return 1; + } + data = poolStoreString(&tempPool, + enc, + start + enc->minBytesPerChar * 4, + end - enc->minBytesPerChar * 3); + if (!data) + return 0; + normalizeLines(data); + commentHandler(handlerArg, data); + poolClear(&tempPool); + return 1; +} + +static void +reportDefault(XML_Parser parser, const ENCODING *enc, const char *s, const char *end) +{ + if (MUST_CONVERT(enc, s)) { + const char **eventPP; + const char **eventEndPP; + if (enc == encoding) { + eventPP = &eventPtr; + eventEndPP = &eventEndPtr; + } + else { + eventPP = &(openInternalEntities->internalEventPtr); + eventEndPP = &(openInternalEntities->internalEventEndPtr); + } + do { + ICHAR *dataPtr = (ICHAR *)dataBuf; + XmlConvert(enc, &s, end, &dataPtr, (ICHAR *)dataBufEnd); + *eventEndPP = s; + defaultHandler(handlerArg, dataBuf, dataPtr - (ICHAR *)dataBuf); + *eventPP = s; + } while (s != end); + } + else + defaultHandler(handlerArg, (XML_Char *)s, (XML_Char *)end - (XML_Char *)s); +} + + +static int +defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *attId, int isCdata, + int isId, const XML_Char *value, XML_Parser parser) +{ + DEFAULT_ATTRIBUTE *att; + if (value || isId) { + /* The handling of default attributes gets messed up if we have + a default which duplicates a non-default. */ + int i; + for (i = 0; i < type->nDefaultAtts; i++) + if (attId == type->defaultAtts[i].id) + return 1; + if (isId && !type->idAtt && !attId->xmlns) + type->idAtt = attId; + } + if (type->nDefaultAtts == type->allocDefaultAtts) { + if (type->allocDefaultAtts == 0) { + type->allocDefaultAtts = 8; + type->defaultAtts = MALLOC(type->allocDefaultAtts*sizeof(DEFAULT_ATTRIBUTE)); + } + else { + type->allocDefaultAtts *= 2; + type->defaultAtts = REALLOC(type->defaultAtts, + type->allocDefaultAtts*sizeof(DEFAULT_ATTRIBUTE)); + } + if (!type->defaultAtts) + return 0; + } + att = type->defaultAtts + type->nDefaultAtts; + att->id = attId; + att->value = value; + att->isCdata = isCdata; + if (!isCdata) + attId->maybeTokenized = 1; + type->nDefaultAtts += 1; + return 1; +} + +static int setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *elementType) +{ + const XML_Char *name; + for (name = elementType->name; *name; name++) { + if (*name == XML_T(':')) { + PREFIX *prefix; + const XML_Char *s; + for (s = elementType->name; s != name; s++) { + if (!poolAppendChar(&dtd.pool, *s)) + return 0; + } + if (!poolAppendChar(&dtd.pool, XML_T('\0'))) + return 0; + prefix = (PREFIX *)lookup(&dtd.prefixes, poolStart(&dtd.pool), sizeof(PREFIX)); + if (!prefix) + return 0; + if (prefix->name == poolStart(&dtd.pool)) + poolFinish(&dtd.pool); + else + poolDiscard(&dtd.pool); + elementType->prefix = prefix; + + } + } + return 1; +} + +static ATTRIBUTE_ID * +getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start, const char *end) +{ + ATTRIBUTE_ID *id; + const XML_Char *name; + if (!poolAppendChar(&dtd.pool, XML_T('\0'))) + return 0; + name = poolStoreString(&dtd.pool, enc, start, end); + if (!name) + return 0; + ++name; + id = (ATTRIBUTE_ID *)lookup(&dtd.attributeIds, name, sizeof(ATTRIBUTE_ID)); + if (!id) + return 0; + if (id->name != name) + poolDiscard(&dtd.pool); + else { + poolFinish(&dtd.pool); + if (!ns) + ; + else if (name[0] == 'x' + && name[1] == 'm' + && name[2] == 'l' + && name[3] == 'n' + && name[4] == 's' + && (name[5] == XML_T('\0') || name[5] == XML_T(':'))) { + if (name[5] == '\0') + id->prefix = &dtd.defaultPrefix; + else + id->prefix = (PREFIX *)lookup(&dtd.prefixes, name + 6, sizeof(PREFIX)); + id->xmlns = 1; + } + else { + int i; + for (i = 0; name[i]; i++) { + if (name[i] == XML_T(':')) { + int j; + for (j = 0; j < i; j++) { + if (!poolAppendChar(&dtd.pool, name[j])) + return 0; + } + if (!poolAppendChar(&dtd.pool, XML_T('\0'))) + return 0; + id->prefix = (PREFIX *)lookup(&dtd.prefixes, poolStart(&dtd.pool), sizeof(PREFIX)); + if (id->prefix->name == poolStart(&dtd.pool)) + poolFinish(&dtd.pool); + else + poolDiscard(&dtd.pool); + break; + } + } + } + } + return id; +} + +#define CONTEXT_SEP XML_T('\f') + +static +const XML_Char *getContext(XML_Parser parser) +{ + HASH_TABLE_ITER iter; + int needSep = 0; + + if (dtd.defaultPrefix.binding) { + int i; + int len; + if (!poolAppendChar(&tempPool, XML_T('='))) + return 0; + len = dtd.defaultPrefix.binding->uriLen; + if (namespaceSeparator != XML_T('\0')) + len--; + for (i = 0; i < len; i++) + if (!poolAppendChar(&tempPool, dtd.defaultPrefix.binding->uri[i])) + return 0; + needSep = 1; + } + + hashTableIterInit(&iter, &(dtd.prefixes)); + for (;;) { + int i; + int len; + const XML_Char *s; + PREFIX *prefix = (PREFIX *)hashTableIterNext(&iter); + if (!prefix) + break; + if (!prefix->binding) + continue; + if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP)) + return 0; + for (s = prefix->name; *s; s++) + if (!poolAppendChar(&tempPool, *s)) + return 0; + if (!poolAppendChar(&tempPool, XML_T('='))) + return 0; + len = prefix->binding->uriLen; + if (namespaceSeparator != XML_T('\0')) + len--; + for (i = 0; i < len; i++) + if (!poolAppendChar(&tempPool, prefix->binding->uri[i])) + return 0; + needSep = 1; + } + + + hashTableIterInit(&iter, &(dtd.generalEntities)); + for (;;) { + const XML_Char *s; + ENTITY *e = (ENTITY *)hashTableIterNext(&iter); + if (!e) + break; + if (!e->open) + continue; + if (needSep && !poolAppendChar(&tempPool, CONTEXT_SEP)) + return 0; + for (s = e->name; *s; s++) + if (!poolAppendChar(&tempPool, *s)) + return 0; + needSep = 1; + } + + if (!poolAppendChar(&tempPool, XML_T('\0'))) + return 0; + return tempPool.start; +} + +static +int setContext(XML_Parser parser, const XML_Char *context) +{ + const XML_Char *s = context; + + while (*context != XML_T('\0')) { + if (*s == CONTEXT_SEP || *s == XML_T('\0')) { + ENTITY *e; + if (!poolAppendChar(&tempPool, XML_T('\0'))) + return 0; + e = (ENTITY *)lookup(&dtd.generalEntities, poolStart(&tempPool), 0); + if (e) + e->open = 1; + if (*s != XML_T('\0')) + s++; + context = s; + poolDiscard(&tempPool); + } + else if (*s == '=') { + PREFIX *prefix; + if (poolLength(&tempPool) == 0) + prefix = &dtd.defaultPrefix; + else { + if (!poolAppendChar(&tempPool, XML_T('\0'))) + return 0; + prefix = (PREFIX *)lookup(&dtd.prefixes, poolStart(&tempPool), sizeof(PREFIX)); + if (!prefix) + return 0; + if (prefix->name == poolStart(&tempPool)) { + prefix->name = poolCopyString(&dtd.pool, prefix->name); + if (!prefix->name) + return 0; + } + poolDiscard(&tempPool); + } + for (context = s + 1; *context != CONTEXT_SEP && *context != XML_T('\0'); context++) + if (!poolAppendChar(&tempPool, *context)) + return 0; + if (!poolAppendChar(&tempPool, XML_T('\0'))) + return 0; + if (!addBinding(parser, prefix, 0, poolStart(&tempPool), &inheritedBindings)) + return 0; + poolDiscard(&tempPool); + if (*context != XML_T('\0')) + ++context; + s = context; + } + else { + if (!poolAppendChar(&tempPool, *s)) + return 0; + s++; + } + } + return 1; +} + + +static +void normalizePublicId(XML_Char *publicId) +{ + XML_Char *p = publicId; + XML_Char *s; + for (s = publicId; *s; s++) { + switch (*s) { + case 0x20: + case 0xD: + case 0xA: + if (p != publicId && p[-1] != 0x20) + *p++ = 0x20; + break; + default: + *p++ = *s; + } + } + if (p != publicId && p[-1] == 0x20) + --p; + *p = XML_T('\0'); +} + +static int dtdInit(DTD *p, XML_Parser parser) +{ + XML_Memory_Handling_Suite *ms = &((Parser *) parser)->m_mem; + poolInit(&(p->pool), ms); + hashTableInit(&(p->generalEntities), ms); + hashTableInit(&(p->elementTypes), ms); + hashTableInit(&(p->attributeIds), ms); + hashTableInit(&(p->prefixes), ms); + p->complete = 1; + p->standalone = 0; +#ifdef XML_DTD + hashTableInit(&(p->paramEntities), ms); +#endif /* XML_DTD */ + p->defaultPrefix.name = 0; + p->defaultPrefix.binding = 0; + + p->in_eldecl = 0; + p->scaffIndex = 0; + p->scaffLevel = 0; + p->scaffold = 0; + p->contentStringLen = 0; + p->scaffSize = 0; + p->scaffCount = 0; + + return 1; +} + +#ifdef XML_DTD + +static void dtdSwap(DTD *p1, DTD *p2) +{ + DTD tem; + memcpy(&tem, p1, sizeof(DTD)); + memcpy(p1, p2, sizeof(DTD)); + memcpy(p2, &tem, sizeof(DTD)); +} + +#endif /* XML_DTD */ + +static void dtdDestroy(DTD *p, XML_Parser parser) +{ + HASH_TABLE_ITER iter; + hashTableIterInit(&iter, &(p->elementTypes)); + for (;;) { + ELEMENT_TYPE *e = (ELEMENT_TYPE *)hashTableIterNext(&iter); + if (!e) + break; + if (e->allocDefaultAtts != 0) + FREE(e->defaultAtts); + } + hashTableDestroy(&(p->generalEntities)); +#ifdef XML_DTD + hashTableDestroy(&(p->paramEntities)); +#endif /* XML_DTD */ + hashTableDestroy(&(p->elementTypes)); + hashTableDestroy(&(p->attributeIds)); + hashTableDestroy(&(p->prefixes)); + poolDestroy(&(p->pool)); + if (p->scaffIndex) + FREE(p->scaffIndex); + if (p->scaffold) + FREE(p->scaffold); +} + +/* Do a deep copy of the DTD. Return 0 for out of memory; non-zero otherwise. +The new DTD has already been initialized. */ + +static int dtdCopy(DTD *newDtd, const DTD *oldDtd, XML_Parser parser) +{ + HASH_TABLE_ITER iter; + + /* Copy the prefix table. */ + + hashTableIterInit(&iter, &(oldDtd->prefixes)); + for (;;) { + const XML_Char *name; + const PREFIX *oldP = (PREFIX *)hashTableIterNext(&iter); + if (!oldP) + break; + name = poolCopyString(&(newDtd->pool), oldP->name); + if (!name) + return 0; + if (!lookup(&(newDtd->prefixes), name, sizeof(PREFIX))) + return 0; + } + + hashTableIterInit(&iter, &(oldDtd->attributeIds)); + + /* Copy the attribute id table. */ + + for (;;) { + ATTRIBUTE_ID *newA; + const XML_Char *name; + const ATTRIBUTE_ID *oldA = (ATTRIBUTE_ID *)hashTableIterNext(&iter); + + if (!oldA) + break; + /* Remember to allocate the scratch byte before the name. */ + if (!poolAppendChar(&(newDtd->pool), XML_T('\0'))) + return 0; + name = poolCopyString(&(newDtd->pool), oldA->name); + if (!name) + return 0; + ++name; + newA = (ATTRIBUTE_ID *)lookup(&(newDtd->attributeIds), name, sizeof(ATTRIBUTE_ID)); + if (!newA) + return 0; + newA->maybeTokenized = oldA->maybeTokenized; + if (oldA->prefix) { + newA->xmlns = oldA->xmlns; + if (oldA->prefix == &oldDtd->defaultPrefix) + newA->prefix = &newDtd->defaultPrefix; + else + newA->prefix = (PREFIX *)lookup(&(newDtd->prefixes), oldA->prefix->name, 0); + } + } + + /* Copy the element type table. */ + + hashTableIterInit(&iter, &(oldDtd->elementTypes)); + + for (;;) { + int i; + ELEMENT_TYPE *newE; + const XML_Char *name; + const ELEMENT_TYPE *oldE = (ELEMENT_TYPE *)hashTableIterNext(&iter); + if (!oldE) + break; + name = poolCopyString(&(newDtd->pool), oldE->name); + if (!name) + return 0; + newE = (ELEMENT_TYPE *)lookup(&(newDtd->elementTypes), name, sizeof(ELEMENT_TYPE)); + if (!newE) + return 0; + if (oldE->nDefaultAtts) { + newE->defaultAtts = (DEFAULT_ATTRIBUTE *)MALLOC(oldE->nDefaultAtts * sizeof(DEFAULT_ATTRIBUTE)); + if (!newE->defaultAtts) + return 0; + } + if (oldE->idAtt) + newE->idAtt = (ATTRIBUTE_ID *)lookup(&(newDtd->attributeIds), oldE->idAtt->name, 0); + newE->allocDefaultAtts = newE->nDefaultAtts = oldE->nDefaultAtts; + if (oldE->prefix) + newE->prefix = (PREFIX *)lookup(&(newDtd->prefixes), oldE->prefix->name, 0); + for (i = 0; i < newE->nDefaultAtts; i++) { + newE->defaultAtts[i].id = (ATTRIBUTE_ID *)lookup(&(newDtd->attributeIds), oldE->defaultAtts[i].id->name, 0); + newE->defaultAtts[i].isCdata = oldE->defaultAtts[i].isCdata; + if (oldE->defaultAtts[i].value) { + newE->defaultAtts[i].value = poolCopyString(&(newDtd->pool), oldE->defaultAtts[i].value); + if (!newE->defaultAtts[i].value) + return 0; + } + else + newE->defaultAtts[i].value = 0; + } + } + + /* Copy the entity tables. */ + if (!copyEntityTable(&(newDtd->generalEntities), + &(newDtd->pool), + &(oldDtd->generalEntities), parser)) + return 0; + +#ifdef XML_DTD + if (!copyEntityTable(&(newDtd->paramEntities), + &(newDtd->pool), + &(oldDtd->paramEntities), parser)) + return 0; +#endif /* XML_DTD */ + + newDtd->complete = oldDtd->complete; + newDtd->standalone = oldDtd->standalone; + + /* Don't want deep copying for scaffolding */ + newDtd->in_eldecl = oldDtd->in_eldecl; + newDtd->scaffold = oldDtd->scaffold; + newDtd->contentStringLen = oldDtd->contentStringLen; + newDtd->scaffSize = oldDtd->scaffSize; + newDtd->scaffLevel = oldDtd->scaffLevel; + newDtd->scaffIndex = oldDtd->scaffIndex; + + return 1; +} /* End dtdCopy */ + +static int copyEntityTable(HASH_TABLE *newTable, + STRING_POOL *newPool, + const HASH_TABLE *oldTable, + XML_Parser parser) +{ + HASH_TABLE_ITER iter; + const XML_Char *cachedOldBase = 0; + const XML_Char *cachedNewBase = 0; + + hashTableIterInit(&iter, oldTable); + + for (;;) { + ENTITY *newE; + const XML_Char *name; + const ENTITY *oldE = (ENTITY *)hashTableIterNext(&iter); + if (!oldE) + break; + name = poolCopyString(newPool, oldE->name); + if (!name) + return 0; + newE = (ENTITY *)lookup(newTable, name, sizeof(ENTITY)); + if (!newE) + return 0; + if (oldE->systemId) { + const XML_Char *tem = poolCopyString(newPool, oldE->systemId); + if (!tem) + return 0; + newE->systemId = tem; + if (oldE->base) { + if (oldE->base == cachedOldBase) + newE->base = cachedNewBase; + else { + cachedOldBase = oldE->base; + tem = poolCopyString(newPool, cachedOldBase); + if (!tem) + return 0; + cachedNewBase = newE->base = tem; + } + } + } + else { + const XML_Char *tem = poolCopyStringN(newPool, oldE->textPtr, oldE->textLen); + if (!tem) + return 0; + newE->textPtr = tem; + newE->textLen = oldE->textLen; + } + if (oldE->notation) { + const XML_Char *tem = poolCopyString(newPool, oldE->notation); + if (!tem) + return 0; + newE->notation = tem; + } + } + return 1; +} + +#define INIT_SIZE 64 + +static +int keyeq(KEY s1, KEY s2) +{ + for (; *s1 == *s2; s1++, s2++) + if (*s1 == 0) + return 1; + return 0; +} + +static +unsigned long hash(KEY s) +{ + unsigned long h = 0; + while (*s) + h = (h << 5) + h + (unsigned char)*s++; + return h; +} + +static +NAMED *lookup(HASH_TABLE *table, KEY name, size_t createSize) +{ + size_t i; + if (table->size == 0) { + size_t tsize; + + if (!createSize) + return 0; + tsize = INIT_SIZE * sizeof(NAMED *); + table->v = table->mem->malloc_fcn(tsize); + if (!table->v) + return 0; + memset(table->v, 0, tsize); + table->size = INIT_SIZE; + table->usedLim = INIT_SIZE / 2; + i = hash(name) & (table->size - 1); + } + else { + unsigned long h = hash(name); + for (i = h & (table->size - 1); + table->v[i]; + i == 0 ? i = table->size - 1 : --i) { + if (keyeq(name, table->v[i]->name)) + return table->v[i]; + } + if (!createSize) + return 0; + if (table->used == table->usedLim) { + /* check for overflow */ + size_t newSize = table->size * 2; + size_t tsize = newSize * sizeof(NAMED *); + NAMED **newV = table->mem->malloc_fcn(tsize); + if (!newV) + return 0; + memset(newV, 0, tsize); + for (i = 0; i < table->size; i++) + if (table->v[i]) { + size_t j; + for (j = hash(table->v[i]->name) & (newSize - 1); + newV[j]; + j == 0 ? j = newSize - 1 : --j) + ; + newV[j] = table->v[i]; + } + table->mem->free_fcn(table->v); + table->v = newV; + table->size = newSize; + table->usedLim = newSize/2; + for (i = h & (table->size - 1); + table->v[i]; + i == 0 ? i = table->size - 1 : --i) + ; + } + } + table->v[i] = table->mem->malloc_fcn(createSize); + if (!table->v[i]) + return 0; + memset(table->v[i], 0, createSize); + table->v[i]->name = name; + (table->used)++; + return table->v[i]; +} + +static +void hashTableDestroy(HASH_TABLE *table) +{ + size_t i; + for (i = 0; i < table->size; i++) { + NAMED *p = table->v[i]; + if (p) + table->mem->free_fcn(p); + } + if (table->v) + table->mem->free_fcn(table->v); +} + +static +void hashTableInit(HASH_TABLE *p, XML_Memory_Handling_Suite *ms) +{ + p->size = 0; + p->usedLim = 0; + p->used = 0; + p->v = 0; + p->mem = ms; +} + +static +void hashTableIterInit(HASH_TABLE_ITER *iter, const HASH_TABLE *table) +{ + iter->p = table->v; + iter->end = iter->p + table->size; +} + +static +NAMED *hashTableIterNext(HASH_TABLE_ITER *iter) +{ + while (iter->p != iter->end) { + NAMED *tem = *(iter->p)++; + if (tem) + return tem; + } + return 0; +} + + +static +void poolInit(STRING_POOL *pool, XML_Memory_Handling_Suite *ms) +{ + pool->blocks = 0; + pool->freeBlocks = 0; + pool->start = 0; + pool->ptr = 0; + pool->end = 0; + pool->mem = ms; +} + +static +void poolClear(STRING_POOL *pool) +{ + if (!pool->freeBlocks) + pool->freeBlocks = pool->blocks; + else { + BLOCK *p = pool->blocks; + while (p) { + BLOCK *tem = p->next; + p->next = pool->freeBlocks; + pool->freeBlocks = p; + p = tem; + } + } + pool->blocks = 0; + pool->start = 0; + pool->ptr = 0; + pool->end = 0; +} + +static +void poolDestroy(STRING_POOL *pool) +{ + BLOCK *p = pool->blocks; + while (p) { + BLOCK *tem = p->next; + pool->mem->free_fcn(p); + p = tem; + } + pool->blocks = 0; + p = pool->freeBlocks; + while (p) { + BLOCK *tem = p->next; + pool->mem->free_fcn(p); + p = tem; + } + pool->freeBlocks = 0; + pool->ptr = 0; + pool->start = 0; + pool->end = 0; +} + +static +XML_Char *poolAppend(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end) +{ + if (!pool->ptr && !poolGrow(pool)) + return 0; + for (;;) { + XmlConvert(enc, &ptr, end, (ICHAR **)&(pool->ptr), (ICHAR *)pool->end); + if (ptr == end) + break; + if (!poolGrow(pool)) + return 0; + } + return pool->start; +} + +static const XML_Char *poolCopyString(STRING_POOL *pool, const XML_Char *s) +{ + do { + if (!poolAppendChar(pool, *s)) + return 0; + } while (*s++); + s = pool->start; + poolFinish(pool); + return s; +} + +static const XML_Char *poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n) +{ + if (!pool->ptr && !poolGrow(pool)) + return 0; + for (; n > 0; --n, s++) { + if (!poolAppendChar(pool, *s)) + return 0; + + } + s = pool->start; + poolFinish(pool); + return s; +} + +static +const XML_Char *poolAppendString(STRING_POOL *pool, const XML_Char *s) +{ + while (*s) { + if (!poolAppendChar(pool, *s)) + return 0; + s++; + } + return pool->start; +} /* End poolAppendString */ + +static +XML_Char *poolStoreString(STRING_POOL *pool, const ENCODING *enc, + const char *ptr, const char *end) +{ + if (!poolAppend(pool, enc, ptr, end)) + return 0; + if (pool->ptr == pool->end && !poolGrow(pool)) + return 0; + *(pool->ptr)++ = 0; + return pool->start; +} + +static +int poolGrow(STRING_POOL *pool) +{ + if (pool->freeBlocks) { + if (pool->start == 0) { + pool->blocks = pool->freeBlocks; + pool->freeBlocks = pool->freeBlocks->next; + pool->blocks->next = 0; + pool->start = pool->blocks->s; + pool->end = pool->start + pool->blocks->size; + pool->ptr = pool->start; + return 1; + } + if (pool->end - pool->start < pool->freeBlocks->size) { + BLOCK *tem = pool->freeBlocks->next; + pool->freeBlocks->next = pool->blocks; + pool->blocks = pool->freeBlocks; + pool->freeBlocks = tem; + memcpy(pool->blocks->s, pool->start, (pool->end - pool->start) * sizeof(XML_Char)); + pool->ptr = pool->blocks->s + (pool->ptr - pool->start); + pool->start = pool->blocks->s; + pool->end = pool->start + pool->blocks->size; + return 1; + } + } + if (pool->blocks && pool->start == pool->blocks->s) { + int blockSize = (pool->end - pool->start)*2; + pool->blocks = pool->mem->realloc_fcn(pool->blocks, offsetof(BLOCK, s) + blockSize * sizeof(XML_Char)); + if (!pool->blocks) + return 0; + pool->blocks->size = blockSize; + pool->ptr = pool->blocks->s + (pool->ptr - pool->start); + pool->start = pool->blocks->s; + pool->end = pool->start + blockSize; + } + else { + BLOCK *tem; + int blockSize = pool->end - pool->start; + if (blockSize < INIT_BLOCK_SIZE) + blockSize = INIT_BLOCK_SIZE; + else + blockSize *= 2; + tem = pool->mem->malloc_fcn(offsetof(BLOCK, s) + blockSize * sizeof(XML_Char)); + if (!tem) + return 0; + tem->size = blockSize; + tem->next = pool->blocks; + pool->blocks = tem; + if (pool->ptr != pool->start) + memcpy(tem->s, pool->start, (pool->ptr - pool->start) * sizeof(XML_Char)); + pool->ptr = tem->s + (pool->ptr - pool->start); + pool->start = tem->s; + pool->end = tem->s + blockSize; + } + return 1; +} + +static int +nextScaffoldPart(XML_Parser parser) +{ + CONTENT_SCAFFOLD * me; + int next; + + if (! dtd.scaffIndex) { + dtd.scaffIndex = MALLOC(groupSize * sizeof(int)); + if (! dtd.scaffIndex) + return -1; + dtd.scaffIndex[0] = 0; + } + + if (dtd.scaffCount >= dtd.scaffSize) { + if (dtd.scaffold) { + dtd.scaffSize *= 2; + dtd.scaffold = (CONTENT_SCAFFOLD *) REALLOC(dtd.scaffold, + dtd.scaffSize * sizeof(CONTENT_SCAFFOLD)); + } + else { + dtd.scaffSize = 32; + dtd.scaffold = (CONTENT_SCAFFOLD *) MALLOC(dtd.scaffSize * sizeof(CONTENT_SCAFFOLD)); + } + if (! dtd.scaffold) + return -1; + } + next = dtd.scaffCount++; + me = &dtd.scaffold[next]; + if (dtd.scaffLevel) { + CONTENT_SCAFFOLD *parent = &dtd.scaffold[dtd.scaffIndex[dtd.scaffLevel - 1]]; + if (parent->lastchild) { + dtd.scaffold[parent->lastchild].nextsib = next; + } + if (! parent->childcnt) + parent->firstchild = next; + parent->lastchild = next; + parent->childcnt++; + } + me->firstchild = me->lastchild = me->childcnt = me->nextsib = 0; + return next; +} /* End nextScaffoldPart */ + +static void +build_node (XML_Parser parser, + int src_node, + XML_Content *dest, + XML_Content **contpos, + char **strpos) +{ + dest->type = dtd.scaffold[src_node].type; + dest->quant = dtd.scaffold[src_node].quant; + if (dest->type == XML_CTYPE_NAME) { + const char *src; + dest->name = *strpos; + src = dtd.scaffold[src_node].name; + for (;;) { + *(*strpos)++ = *src; + if (! *src) + break; + src++; + } + dest->numchildren = 0; + dest->children = 0; + } + else { + unsigned int i; + int cn; + dest->numchildren = dtd.scaffold[src_node].childcnt; + dest->children = *contpos; + *contpos += dest->numchildren; + for (i = 0, cn = dtd.scaffold[src_node].firstchild; + i < dest->numchildren; + i++, cn = dtd.scaffold[cn].nextsib) { + build_node(parser, cn, &(dest->children[i]), contpos, strpos); + } + dest->name = 0; + } +} /* End build_node */ + +static XML_Content * +build_model (XML_Parser parser) +{ + XML_Content *ret; + XML_Content *cpos; + char * str; + int allocsize = dtd.scaffCount * sizeof(XML_Content) + dtd.contentStringLen; + + ret = MALLOC(allocsize); + if (! ret) + return 0; + + str = (char *) (&ret[dtd.scaffCount]); + cpos = &ret[1]; + + build_node(parser, 0, ret, &cpos, &str); + return ret; +} /* End build_model */ + +static ELEMENT_TYPE * +getElementType(XML_Parser parser, + const ENCODING *enc, + const char *ptr, + const char *end) +{ + const XML_Char *name = poolStoreString(&dtd.pool, enc, ptr, end); + ELEMENT_TYPE *ret; + + if (! name) + return 0; + ret = (ELEMENT_TYPE *) lookup(&dtd.elementTypes, name, sizeof(ELEMENT_TYPE)); + if (! ret) + return 0; + if (ret->name != name) + poolDiscard(&dtd.pool); + else { + poolFinish(&dtd.pool); + if (!setElementTypePrefix(parser, ret)) + return 0; + } + return ret; +} /* End getElementType */ diff --git a/Modules/expat/xmlrole.c b/Modules/expat/xmlrole.c new file mode 100644 index 0000000..20a1444 --- /dev/null +++ b/Modules/expat/xmlrole.c @@ -0,0 +1,1275 @@ +/* +Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd +See the file COPYING for copying permission. +*/ + +static char RCSId[] + = "$Header$"; + +#ifdef COMPILED_FROM_DSP +# include "winconfig.h" +#else +# include <config.h> +#endif /* ndef COMPILED_FROM_DSP */ + +#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' }; +static const char KW_IGNORE[] = { ASCII_I, ASCII_G, ASCII_N, ASCII_O, ASCII_R, ASCII_E, '\0' }; +static const char KW_IMPLIED[] = { ASCII_I, ASCII_M, ASCII_P, ASCII_L, ASCII_I, ASCII_E, ASCII_D, '\0' }; +static const char KW_INCLUDE[] = { ASCII_I, ASCII_N, ASCII_C, ASCII_L, ASCII_U, ASCII_D, ASCII_E, '\0' }; +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 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, + 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 common(PROLOG_STATE *state, int tok); + +static +int 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_NONE; + case XML_TOK_COMMENT: + state->handler = prolog1; + 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_NONE; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static +int 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: + case XML_TOK_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_NONE; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static +int 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: + case XML_TOK_COMMENT: + return XML_ROLE_NONE; + case XML_TOK_INSTANCE_START: + state->handler = error; + return XML_ROLE_INSTANCE_START; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = doctype1; + return XML_ROLE_DOCTYPE_NAME; + } + return common(state, tok); +} + +static +int 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_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_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = doctype2; + return XML_ROLE_NONE; + } + break; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_LITERAL: + state->handler = doctype3; + return XML_ROLE_DOCTYPE_PUBLIC_ID; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_LITERAL: + state->handler = doctype4; + return XML_ROLE_DOCTYPE_SYSTEM_ID; + } + return common(state, tok); +} + +static +int 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_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 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_NONE; + case XML_TOK_DECL_CLOSE: + state->handler = prolog2; + return XML_ROLE_DOCTYPE_CLOSE; + } + return common(state, tok); +} + +static +int 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_NONE; + } + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_ATTLIST)) { + state->handler = attlist0; + return XML_ROLE_NONE; + } + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_ELEMENT)) { + state->handler = element0; + return XML_ROLE_NONE; + } + if (XmlNameMatchesAscii(enc, + ptr + 2 * MIN_BYTES_PER_CHAR(enc), + end, + KW_NOTATION)) { + state->handler = notation0; + return XML_ROLE_NONE; + } + break; + case XML_TOK_PI: + case XML_TOK_COMMENT: + return XML_ROLE_NONE; + case XML_TOK_PARAM_ENTITY_REF: + return XML_ROLE_PARAM_ENTITY_REF; + case XML_TOK_CLOSE_BRACKET: + state->handler = doctype5; + return XML_ROLE_NONE; + } + return common(state, tok); +} + +#ifdef XML_DTD + +static +int 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 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 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_NONE; + case XML_TOK_PERCENT: + state->handler = entity1; + return XML_ROLE_NONE; + case XML_TOK_NAME: + state->handler = entity2; + return XML_ROLE_GENERAL_ENTITY_NAME; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + state->handler = entity7; + return XML_ROLE_PARAM_ENTITY_NAME; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = entity4; + return XML_ROLE_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = entity3; + return XML_ROLE_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = declClose; + return XML_ROLE_ENTITY_VALUE; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_LITERAL: + state->handler = entity4; + return XML_ROLE_ENTITY_PUBLIC_ID; + } + return common(state, tok); +} + + +static +int 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_NONE; + case XML_TOK_LITERAL: + state->handler = entity5; + return XML_ROLE_ENTITY_SYSTEM_ID; + } + return common(state, tok); +} + +static +int 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_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_NONE; + } + break; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + state->handler = declClose; + return XML_ROLE_ENTITY_NOTATION_NAME; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = entity9; + return XML_ROLE_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = entity8; + return XML_ROLE_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = declClose; + return XML_ROLE_ENTITY_VALUE; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_LITERAL: + state->handler = entity9; + return XML_ROLE_ENTITY_PUBLIC_ID; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_LITERAL: + state->handler = declClose; + return XML_ROLE_ENTITY_SYSTEM_ID; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + state->handler = notation1; + return XML_ROLE_NOTATION_NAME; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_SYSTEM)) { + state->handler = notation3; + return XML_ROLE_NONE; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_PUBLIC)) { + state->handler = notation2; + return XML_ROLE_NONE; + } + break; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_LITERAL: + state->handler = notation4; + return XML_ROLE_NOTATION_PUBLIC_ID; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_LITERAL: + state->handler = declClose; + return XML_ROLE_NOTATION_SYSTEM_ID; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_LITERAL: + state->handler = declClose; + 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 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_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 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_NONE; + case XML_TOK_DECL_CLOSE: + setTopLevel(state); + return XML_ROLE_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = attlist2; + return XML_ROLE_ATTRIBUTE_NAME; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + { + static const char *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_NONE; + } + break; + case XML_TOK_OPEN_PAREN: + state->handler = attlist3; + return XML_ROLE_NONE; + } + return common(state, tok); +} + +static +int 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_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 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_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = attlist8; + return XML_ROLE_NONE; + case XML_TOK_OR: + state->handler = attlist3; + return XML_ROLE_NONE; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_OPEN_PAREN: + state->handler = attlist6; + return XML_ROLE_NONE; + } + return common(state, tok); +} + + +static +int 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_NONE; + case XML_TOK_NAME: + state->handler = attlist7; + return XML_ROLE_ATTRIBUTE_NOTATION_VALUE; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = attlist8; + return XML_ROLE_NONE; + case XML_TOK_OR: + state->handler = attlist6; + return XML_ROLE_NONE; + } + return common(state, tok); +} + +/* default value */ +static +int 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_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_NONE; + } + break; + case XML_TOK_LITERAL: + state->handler = attlist1; + return XML_ROLE_DEFAULT_ATTRIBUTE_VALUE; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_LITERAL: + state->handler = attlist1; + return XML_ROLE_FIXED_ATTRIBUTE_VALUE; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element1; + return XML_ROLE_ELEMENT_NAME; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + if (XmlNameMatchesAscii(enc, ptr, end, KW_EMPTY)) { + state->handler = declClose; + return XML_ROLE_CONTENT_EMPTY; + } + if (XmlNameMatchesAscii(enc, ptr, end, KW_ANY)) { + state->handler = declClose; + 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 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_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 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_NONE; + case XML_TOK_CLOSE_PAREN: + state->handler = declClose; + return XML_ROLE_GROUP_CLOSE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->handler = declClose; + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_OR: + state->handler = element4; + return XML_ROLE_NONE; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_NAME: + case XML_TOK_PREFIXED_NAME: + state->handler = element5; + return XML_ROLE_CONTENT_ELEMENT; + } + return common(state, tok); +} + +static +int 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_NONE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->handler = declClose; + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_OR: + state->handler = element4; + return XML_ROLE_NONE; + } + return common(state, tok); +} + +static +int 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_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 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_NONE; + case XML_TOK_CLOSE_PAREN: + state->level -= 1; + if (state->level == 0) + state->handler = declClose; + return XML_ROLE_GROUP_CLOSE; + case XML_TOK_CLOSE_PAREN_ASTERISK: + state->level -= 1; + if (state->level == 0) + state->handler = declClose; + return XML_ROLE_GROUP_CLOSE_REP; + case XML_TOK_CLOSE_PAREN_QUESTION: + state->level -= 1; + if (state->level == 0) + state->handler = declClose; + return XML_ROLE_GROUP_CLOSE_OPT; + case XML_TOK_CLOSE_PAREN_PLUS: + state->level -= 1; + if (state->level == 0) + state->handler = declClose; + 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 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 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 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 declClose(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_CLOSE: + setTopLevel(state); + return XML_ROLE_NONE; + } + return common(state, tok); +} + +#if 0 + +static +int ignore(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + switch (tok) { + case XML_TOK_DECL_CLOSE: + state->handler = internalSubset; + return 0; + default: + return XML_ROLE_NONE; + } + return common(state, tok); +} +#endif + +static +int error(PROLOG_STATE *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc) +{ + return XML_ROLE_NONE; +} + +static +int 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; +#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/Modules/expat/xmlrole.h b/Modules/expat/xmlrole.h new file mode 100644 index 0000000..db3ebc8 --- /dev/null +++ b/Modules/expat/xmlrole.h @@ -0,0 +1,100 @@ +/* +Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd +See the file COPYING for copying permission. +*/ + +#ifndef XmlRole_INCLUDED +#define XmlRole_INCLUDED 1 + +#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_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_VALUE, + XML_ROLE_ENTITY_SYSTEM_ID, + XML_ROLE_ENTITY_PUBLIC_ID, + XML_ROLE_ENTITY_COMPLETE, + XML_ROLE_ENTITY_NOTATION_NAME, + 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_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_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, +#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 (*handler)(struct prolog_state *state, + int tok, + const char *ptr, + const char *end, + const ENCODING *enc); + unsigned level; +#ifdef XML_DTD + unsigned includeLevel; + int documentEntity; +#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/Modules/expat/xmltok.c b/Modules/expat/xmltok.c new file mode 100644 index 0000000..8a4a363 --- /dev/null +++ b/Modules/expat/xmltok.c @@ -0,0 +1,1566 @@ +/* +Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd +See the file COPYING for copying permission. +*/ + +#ifdef COMPILED_FROM_DSP +# include "winconfig.h" +#else +# include <config.h> +#endif /* ndef COMPILED_FROM_DSP */ + +#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)) + +#define UTF8_INVALID3(p) \ + ((*p) == 0xED \ + ? (((p)[1] & 0x20) != 0) \ + : ((*p) == 0xEF \ + ? ((p)[1] == 0xBF && ((p)[2] == 0xBF || (p)[2] == 0xBE)) \ + : 0)) + +#define UTF8_INVALID4(p) ((*p) == 0xF4 && ((p)[1] & 0x30) != 0) + +static +int isNever(const ENCODING *enc, const char *p) +{ + return 0; +} + +static +int utf8_isName2(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING2(namePages, (const unsigned char *)p); +} + +static +int utf8_isName3(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING3(namePages, (const unsigned char *)p); +} + +#define utf8_isName4 isNever + +static +int utf8_isNmstrt2(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING2(nmstrtPages, (const unsigned char *)p); +} + +static +int utf8_isNmstrt3(const ENCODING *enc, const char *p) +{ + return UTF8_GET_NAMING3(nmstrtPages, (const unsigned char *)p); +} + +#define utf8_isNmstrt4 isNever + +#define utf8_isInvalid2 isNever + +static +int utf8_isInvalid3(const ENCODING *enc, const char *p) +{ + return UTF8_INVALID3((const unsigned char *)p); +} + +static +int 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 (*byteType)(const ENCODING *, const char *); + int (*isNameMin)(const ENCODING *, const char *); + int (*isNmstrtMin)(const ENCODING *, const char *); + int (*byteToAscii)(const ENCODING *, const char *); + int (*charMatches)(const ENCODING *, const char *, int); +#endif /* XML_MIN_SIZE */ + int (*isName2)(const ENCODING *, const char *); + int (*isName3)(const ENCODING *, const char *); + int (*isName4)(const ENCODING *, const char *); + int (*isNmstrt2)(const ENCODING *, const char *); + int (*isNmstrt3)(const ENCODING *, const char *); + int (*isNmstrt4)(const ENCODING *, const char *); + int (*isInvalid2)(const ENCODING *, const char *); + int (*isInvalid3)(const ENCODING *, const char *); + int (*isInvalid4)(const ENCODING *, const char *); +}; + +#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 + +static int 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 sb_byteType(const ENCODING *enc, const char *p) +{ + return SB_BYTE_TYPE(enc, p); +} +#define BYTE_TYPE(enc, p) \ + (((const struct 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) \ + (((const struct normal_encoding *)(enc))->byteToAscii(enc, p)) +static +int 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) \ + (((const struct normal_encoding *)(enc))->isName ## n(enc, p)) +#define IS_NMSTRT_CHAR(enc, p, n) \ + (((const struct normal_encoding *)(enc))->isNmstrt ## n(enc, p)) +#define IS_INVALID_CHAR(enc, p, n) \ + (((const struct normal_encoding *)(enc))->isInvalid ## n(enc, p)) + +#ifdef XML_MIN_SIZE +#define IS_NAME_CHAR_MINBPC(enc, p) \ + (((const struct normal_encoding *)(enc))->isNameMin(enc, p)) +#define IS_NMSTRT_CHAR_MINBPC(enc, p) \ + (((const struct 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) \ + (((const struct normal_encoding *)(enc))->charMatches(enc, p, c)) +static +int 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 +#include "xmltok_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 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 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++ = ((from[0] & 0x1f) << 6) | (from[1] & 0x3f); + from += 2; + break; + case BT_LEAD3: + *to++ = ((from[0] & 0xf) << 12) | ((from[1] & 0x3f) << 6) | (from[2] & 0x3f); + from += 3; + break; + case BT_LEAD4: + { + unsigned long n; + if (to + 1 == toLim) + break; + 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; + } + } + *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 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)++ = ((c >> 6) | UTF8_cval2); + *(*toP)++ = ((c & 0x3f) | 0x80); + (*fromP)++; + } + else { + if (*toP == toLim) + break; + *(*toP)++ = *(*fromP)++; + } + } +} + +static +void 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_) +}; + +#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_) +}; + +static +void 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_) +}; + +#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_) +}; + +static int 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 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; \ + } \ + /* 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 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 little2_byteType(const ENCODING *enc, const char *p) +{ + return LITTLE2_BYTE_TYPE(enc, p); +} + +static +int little2_byteToAscii(const ENCODING *enc, const char *p) +{ + return LITTLE2_BYTE_TO_ASCII(enc, p); +} + +static +int little2_charMatches(const ENCODING *enc, const char *p, int c) +{ + return LITTLE2_CHAR_MATCHES(enc, p, c); +} + +static +int little2_isNameMin(const ENCODING *enc, const char *p) +{ + return LITTLE2_IS_NAME_CHAR_MINBPC(enc, p); +} + +static +int 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) + +#include "xmltok_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 XML_BYTE_ORDER == 12 + 1 +#else + 0 +#endif + }, + { +#include "asciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) +}; + +#endif + +static const struct normal_encoding little2_encoding = { + { VTABLE, 2, 0, +#if XML_BYTE_ORDER == 12 + 1 +#else + 0 +#endif + }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(little2_) +}; + +#if XML_BYTE_ORDER != 21 + +#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_) +}; + +#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_) +}; + +#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 big2_byteType(const ENCODING *enc, const char *p) +{ + return BIG2_BYTE_TYPE(enc, p); +} + +static +int big2_byteToAscii(const ENCODING *enc, const char *p) +{ + return BIG2_BYTE_TO_ASCII(enc, p); +} + +static +int big2_charMatches(const ENCODING *enc, const char *p, int c) +{ + return BIG2_CHAR_MATCHES(enc, p, c); +} + +static +int big2_isNameMin(const ENCODING *enc, const char *p) +{ + return BIG2_IS_NAME_CHAR_MINBPC(enc, p); +} + +static +int 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) + +#include "xmltok_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 XML_BYTE_ORDER == 21 + 1 +#else + 0 +#endif + }, + { +#include "asciitab.h" +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) +}; + +#endif + +static const struct normal_encoding big2_encoding = { + { VTABLE, 2, 0, +#if XML_BYTE_ORDER == 21 + 1 +#else + 0 +#endif + }, + { +#define BT_COLON BT_NMSTRT +#include "asciitab.h" +#undef BT_COLON +#include "latin1tab.h" + }, + STANDARD_VTABLE(big2_) +}; + +#if XML_BYTE_ORDER != 12 + +#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_) +}; + +#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_) +}; + +#endif + +#undef PREFIX + +static +int 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 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 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 = 0; + 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 = 0; + 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 = 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 = 0; + const char *name = 0; + const char *nameEnd = 0; + 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 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 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] = (c | UTF8_cval1); + return 1; + } + if (c < min3) { + buf[0] = ((c >> 6) | UTF8_cval2); + buf[1] = ((c & 0x3f) | 0x80); + return 2; + } + if (c < min4) { + buf[0] = ((c >> 12) | UTF8_cval3); + buf[1] = (((c >> 6) & 0x3f) | 0x80); + buf[2] = ((c & 0x3f) | 0x80); + return 3; + } + if (c < 0x110000) { + buf[0] = ((c >> 18) | UTF8_cval4); + buf[1] = (((c >> 12) & 0x3f) | 0x80); + buf[2] = (((c >> 6) & 0x3f) | 0x80); + buf[3] = ((c & 0x3f) | 0x80); + return 4; + } + return 0; +} + +int XmlUtf16Encode(int charNum, unsigned short *buf) +{ + if (charNum < 0) + return 0; + if (charNum < 0x10000) { + buf[0] = charNum; + return 1; + } + if (charNum < 0x110000) { + charNum -= 0x10000; + buf[0] = (charNum >> 10) + 0xD800; + buf[1] = (charNum & 0x3FF) + 0xDC00; + return 2; + } + return 0; +} + +struct unknown_encoding { + struct normal_encoding normal; + int (*convert)(void *userData, const char *p); + void *userData; + unsigned short utf16[256]; + char utf8[256][4]; +}; + +int XmlSizeOfUnknownEncoding(void) +{ + return sizeof(struct unknown_encoding); +} + +static +int unknown_isName(const ENCODING *enc, const char *p) +{ + int c = ((const struct unknown_encoding *)enc) + ->convert(((const struct unknown_encoding *)enc)->userData, p); + if (c & ~0xFFFF) + return 0; + return UCS2_GET_NAMING(namePages, c >> 8, c & 0xFF); +} + +static +int unknown_isNmstrt(const ENCODING *enc, const char *p) +{ + int c = ((const struct unknown_encoding *)enc) + ->convert(((const struct unknown_encoding *)enc)->userData, p); + if (c & ~0xFFFF) + return 0; + return UCS2_GET_NAMING(nmstrtPages, c >> 8, c & 0xFF); +} + +static +int unknown_isInvalid(const ENCODING *enc, const char *p) +{ + int c = ((const struct unknown_encoding *)enc) + ->convert(((const struct unknown_encoding *)enc)->userData, p); + return (c & ~0xFFFF) || checkCharRefNumber(c) < 0; +} + +static +void unknown_toUtf8(const ENCODING *enc, + const char **fromP, const char *fromLim, + char **toP, const char *toLim) +{ + char buf[XML_UTF8_ENCODE_MAX]; + for (;;) { + const char *utf8; + int n; + if (*fromP == fromLim) + break; + utf8 = ((const struct unknown_encoding *)enc)->utf8[(unsigned char)**fromP]; + n = *utf8++; + if (n == 0) { + int c = ((const struct unknown_encoding *)enc) + ->convert(((const struct unknown_encoding *)enc)->userData, *fromP); + n = XmlUtf8Encode(c, buf); + if (n > toLim - *toP) + break; + utf8 = buf; + *fromP += ((const struct 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 unknown_toUtf16(const ENCODING *enc, + const char **fromP, const char *fromLim, + unsigned short **toP, const unsigned short *toLim) +{ + while (*fromP != fromLim && *toP != toLim) { + unsigned short c + = ((const struct unknown_encoding *)enc)->utf16[(unsigned char)**fromP]; + if (c == 0) { + c = (unsigned short)((const struct unknown_encoding *)enc) + ->convert(((const struct unknown_encoding *)enc)->userData, *fromP); + *fromP += ((const struct normal_encoding *)enc)->type[(unsigned char)**fromP] + - (BT_LEAD2 - 2); + } + else + (*fromP)++; + *(*toP)++ = c; + } +} + +ENCODING * +XmlInitUnknownEncoding(void *mem, + int *table, + int (*convert)(void *userData, const char *p), + void *userData) +{ + int i; + struct unknown_encoding *e = 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] = 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] = 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] = 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 getEncodingIndex(const char *name) +{ + static const char *encodingNames[] = { + KW_ISO_8859_1, + KW_US_ASCII, + KW_UTF_8, + KW_UTF_16, + KW_UTF_16BE, + KW_UTF_16LE, + }; + int i; + if (name == 0) + 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 **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; + /* 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 +#include "xmltok_ns.c" +#undef NS +#undef ns + +#ifdef XML_NS + +#define NS(x) x ## NS +#define ns(x) x ## _ns + +#include "xmltok_ns.c" + +#undef NS +#undef ns + +ENCODING * +XmlInitUnknownEncodingNS(void *mem, + int *table, + int (*convert)(void *userData, const char *p), + 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/Modules/expat/xmltok.h b/Modules/expat/xmltok.h new file mode 100644 index 0000000..8b02324 --- /dev/null +++ b/Modules/expat/xmltok.h @@ -0,0 +1,299 @@ +/* +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 */ + unsigned long lineNumber; + unsigned long columnNumber; +} POSITION; + +typedef struct { + const char *name; + const char *valuePtr; + const char *valueEnd; + char normalized; +} ATTRIBUTE; + +struct encoding; +typedef struct encoding ENCODING; + +struct encoding { + int (*scanners[XML_N_STATES])(const ENCODING *, + const char *, + const char *, + const char **); + int (*literalScanners[XML_N_LITERAL_TYPES])(const ENCODING *, + const char *, + const char *, + const char **); + int (*sameName)(const ENCODING *, + const char *, const char *); + int (*nameMatchesAscii)(const ENCODING *, + const char *, const char *, const char *); + int (*nameLength)(const ENCODING *, const char *); + const char *(*skipS)(const ENCODING *, const char *); + int (*getAtts)(const ENCODING *enc, const char *ptr, + int attsMax, ATTRIBUTE *atts); + int (*charRefNumber)(const ENCODING *enc, const char *ptr); + int (*predefinedEntityName)(const ENCODING *, const char *, const char *); + void (*updatePosition)(const ENCODING *, + const char *ptr, + const char *end, + POSITION *); + int (*isPublicId)(const ENCODING *enc, const char *ptr, const char *end, + const char **badPtr); + void (*utf8Convert)(const ENCODING *enc, + const char **fromP, + const char *fromLim, + char **toP, + const char *toLim); + void (*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 XmlUtf8Encode(int charNumber, char *buf); +int XmlUtf16Encode(int charNumber, unsigned short *buf); + +int XmlSizeOfUnknownEncoding(void); +ENCODING * +XmlInitUnknownEncoding(void *mem, + int *table, + int (*conv)(void *userData, const char *p), + 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, + int (*conv)(void *userData, const char *p), + void *userData); +#ifdef __cplusplus +} +#endif + +#endif /* not XmlTok_INCLUDED */ diff --git a/Modules/expat/xmltok_impl.c b/Modules/expat/xmltok_impl.c new file mode 100644 index 0000000..36d2065 --- /dev/null +++ b/Modules/expat/xmltok_impl.c @@ -0,0 +1,1768 @@ +/* +Copyright (c) 1998, 1999 Thai Open Source Software Center Ltd +See the file COPYING for copying permission. +*/ + +#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; \ + } \ + 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; \ + } \ + 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 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 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 */ + 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 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 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 */ + default: + *nextTokPtr = ptr; + return XML_TOK_INVALID; + } + } + return XML_TOK_PARTIAL; +} + + +static +int 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 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 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 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 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 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 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 */ + 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 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 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 */ + 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 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 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 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 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) + return -XML_TOK_PROLOG_S; + /* 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 */ + 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 */ + 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 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 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 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 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; + 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 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 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 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 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) LEAD_CASE(3) 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 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 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 ptr - start; + } + } +} + +static +const char *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 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 = (unsigned)-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 = (unsigned)-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 diff --git a/Modules/expat/xmltok_impl.h b/Modules/expat/xmltok_impl.h new file mode 100644 index 0000000..da0ea60 --- /dev/null +++ b/Modules/expat/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/Modules/expat/xmltok_ns.c b/Modules/expat/xmltok_ns.c new file mode 100644 index 0000000..2185973 --- /dev/null +++ b/Modules/expat/xmltok_ns.c @@ -0,0 +1,98 @@ +const ENCODING *NS(XmlGetUtf8InternalEncoding)(void) +{ + return &ns(internal_utf8_encoding).enc; +} + +const ENCODING *NS(XmlGetUtf16InternalEncoding)(void) +{ +#if XML_BYTE_ORDER == 12 + return &ns(internal_little2_encoding).enc; +#elif XML_BYTE_ORDER == 21 + 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 *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 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 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); +} |