/* __ __ _ ___\ \/ /_ __ __ _| |_ / _ \\ /| '_ \ / _` | __| | __// \| |_) | (_| | |_ \___/_/\_\ .__/ \__,_|\__| |_| XML parser Copyright (c) 1997-2000 Thai Open Source Software Center Ltd Copyright (c) 2000 Clark Cooper <[email protected]> Copyright (c) 2001-2003 Fred L. Drake, Jr. <[email protected]> Copyright (c) 2002 Greg Stein <[email protected]> Copyright (c) 2002-2016 Karl Waclawek <[email protected]> Copyright (c) 2005-2009 Steven Solie <[email protected]> Copyright (c) 2016-2024 Sebastian Pipping <[email protected]> Copyright (c) 2016 Pascal Cuoq <[email protected]> Copyright (c) 2016 Don Lewis <[email protected]> Copyright (c) 2017 Rhodri James <[email protected]> Copyright (c) 2017 Alexander Bluhm <[email protected]> Copyright (c) 2017 Benbuck Nason <[email protected]> Copyright (c) 2017 José Gutiérrez de la Concha <[email protected]> Copyright (c) 2019 David Loffredo <[email protected]> Copyright (c) 2021 Donghee Na <[email protected]> Copyright (c) 2022 Martin Ettl <[email protected]> Copyright (c) 2022 Sean McBride <[email protected]> Copyright (c) 2023 Hanno Böck <[email protected]> Licensed under the MIT license: Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions: The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. */ #include "expat_config.h" #include <stddef.h> #include <string.h> /* memcpy */ #include <stdbool.h> #ifdef _WIN32 # include "winconfig.h" #endif #include "expat_external.h" #include "internal.h" #include "xmltok.h" #include "nametab.h" #ifdef XML_DTD #define IGNORE_SECTION_TOK_VTABLE … #else #define IGNORE_SECTION_TOK_VTABLE … #endif #define VTABLE1 … #define VTABLE … #define UCS2_GET_NAMING(pages, hi, lo) … /* 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) … /* 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) … /* Detection of invalid UTF-8 sequences is based on Table 3.1B of Unicode 3.2: https://www.unicode.org/unicode/reports/tr28/ with the additional restriction of not allowing the Unicode code points 0xFFFF and 0xFFFE (sequences EF,BF,BF and EF,BF,BE). Implementation details: (A & 0x80) == 0 means A < 0x80 and (A & 0xC0) == 0xC0 means A > 0xBF */ #define UTF8_INVALID2(p) … #define UTF8_INVALID3(p) … #define UTF8_INVALID4(p) … static int PTRFASTCALL isNever(const ENCODING *enc, const char *p) { … } static int PTRFASTCALL utf8_isName2(const ENCODING *enc, const char *p) { … } static int PTRFASTCALL utf8_isName3(const ENCODING *enc, const char *p) { … } #define utf8_isName4 … static int PTRFASTCALL utf8_isNmstrt2(const ENCODING *enc, const char *p) { … } static int PTRFASTCALL utf8_isNmstrt3(const ENCODING *enc, const char *p) { … } #define utf8_isNmstrt4 … static int PTRFASTCALL utf8_isInvalid2(const ENCODING *enc, const char *p) { … } static int PTRFASTCALL utf8_isInvalid3(const ENCODING *enc, const char *p) { … } static int PTRFASTCALL utf8_isInvalid4(const ENCODING *enc, const char *p) { … } struct normal_encoding { … }; #define AS_NORMAL_ENCODING(enc) … #ifdef XML_MIN_SIZE #define STANDARD_VTABLE … #else #define STANDARD_VTABLE(E) … #endif #define NORMAL_VTABLE(E) … #define NULL_VTABLE … static int FASTCALL checkCharRefNumber(int result); #include "xmltok_impl.h" #include "ascii.h" #ifdef XML_MIN_SIZE #define sb_isNameMin … #define sb_isNmstrtMin … #endif #ifdef XML_MIN_SIZE #define MINBPC … #else /* minimum bytes per character */ #define MINBPC … #endif #define SB_BYTE_TYPE(enc, p) … #ifdef XML_MIN_SIZE static int PTRFASTCALL sb_byteType(const ENCODING *enc, const char *p) { return SB_BYTE_TYPE(enc, p); } #define BYTE_TYPE … #else #define BYTE_TYPE … #endif #ifdef XML_MIN_SIZE #define BYTE_TO_ASCII … static int PTRFASTCALL sb_byteToAscii(const ENCODING *enc, const char *p) { UNUSED_P(enc); return *p; } #else #define BYTE_TO_ASCII … #endif #define IS_NAME_CHAR … #define IS_NMSTRT_CHAR … #ifdef XML_MIN_SIZE #define IS_INVALID_CHAR … #else #define IS_INVALID_CHAR … #endif #ifdef XML_MIN_SIZE #define IS_NAME_CHAR_MINBPC … #define IS_NMSTRT_CHAR_MINBPC … #else #define IS_NAME_CHAR_MINBPC … #define IS_NMSTRT_CHAR_MINBPC … #endif #ifdef XML_MIN_SIZE #define CHAR_MATCHES … static int PTRCALL sb_charMatches(const ENCODING *enc, const char *p, int c) { UNUSED_P(enc); return *p == c; } #else /* c is an ASCII character */ #define CHAR_MATCHES … #endif #define PREFIX … #define XML_TOK_IMPL_C #include "xmltok_impl.c" #undef XML_TOK_IMPL_C #undef MINBPC #undef BYTE_TYPE #undef BYTE_TO_ASCII #undef CHAR_MATCHES #undef IS_NAME_CHAR #undef IS_NAME_CHAR_MINBPC #undef IS_NMSTRT_CHAR #undef IS_NMSTRT_CHAR_MINBPC #undef IS_INVALID_CHAR enum { … }; void _INTERNAL_trim_to_complete_utf8_characters(const char *from, const char **fromLimRef) { … } static enum XML_Convert_Result PTRCALL utf8_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, char **toP, const char *toLim) { … } static enum XML_Convert_Result PTRCALL utf8_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, unsigned short **toP, const unsigned short *toLim) { … } #ifdef XML_NS static const struct normal_encoding utf8_encoding_ns = …; #endif static const struct normal_encoding utf8_encoding = …; #ifdef XML_NS static const struct normal_encoding internal_utf8_encoding_ns = …; #endif static const struct normal_encoding internal_utf8_encoding = …; static enum XML_Convert_Result PTRCALL latin1_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, char **toP, const char *toLim) { … } static enum XML_Convert_Result PTRCALL latin1_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, unsigned short **toP, const unsigned short *toLim) { … } #ifdef XML_NS static const struct normal_encoding latin1_encoding_ns = …; #endif static const struct normal_encoding latin1_encoding = …; static enum XML_Convert_Result PTRCALL ascii_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, char **toP, const char *toLim) { … } #ifdef XML_NS static const struct normal_encoding ascii_encoding_ns = …; #endif static const struct normal_encoding ascii_encoding = …; static int PTRFASTCALL unicode_byte_type(char hi, char lo) { … } #define DEFINE_UTF16_TO_UTF8(E) … #define DEFINE_UTF16_TO_UTF16(E) … #define GET_LO … #define GET_HI … DEFINE_UTF16_TO_UTF8(little2_) DEFINE_UTF16_TO_UTF16(little2_) #undef GET_LO #undef GET_HI #define GET_LO … #define GET_HI … DEFINE_UTF16_TO_UTF8(big2_) DEFINE_UTF16_TO_UTF16(big2_) #undef GET_LO #undef GET_HI #define LITTLE2_BYTE_TYPE(enc, p) … #define LITTLE2_BYTE_TO_ASCII(p) … #define LITTLE2_CHAR_MATCHES(p, c) … #define LITTLE2_IS_NAME_CHAR_MINBPC(p) … #define LITTLE2_IS_NMSTRT_CHAR_MINBPC(p) … #ifdef XML_MIN_SIZE static int PTRFASTCALL little2_byteType(const ENCODING *enc, const char *p) { return LITTLE2_BYTE_TYPE(enc, p); } static int PTRFASTCALL little2_byteToAscii(const ENCODING *enc, const char *p) { UNUSED_P(enc); return LITTLE2_BYTE_TO_ASCII(p); } static int PTRCALL little2_charMatches(const ENCODING *enc, const char *p, int c) { UNUSED_P(enc); return LITTLE2_CHAR_MATCHES(p, c); } static int PTRFASTCALL little2_isNameMin(const ENCODING *enc, const char *p) { UNUSED_P(enc); return LITTLE2_IS_NAME_CHAR_MINBPC(p); } static int PTRFASTCALL little2_isNmstrtMin(const ENCODING *enc, const char *p) { UNUSED_P(enc); return LITTLE2_IS_NMSTRT_CHAR_MINBPC(p); } # undef VTABLE #define VTABLE … #else /* not XML_MIN_SIZE */ # undef PREFIX #define PREFIX … #define MINBPC … /* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ #define BYTE_TYPE … #define BYTE_TO_ASCII … #define CHAR_MATCHES … #define IS_NAME_CHAR … #define IS_NAME_CHAR_MINBPC … #define IS_NMSTRT_CHAR … #define IS_NMSTRT_CHAR_MINBPC … #define XML_TOK_IMPL_C # include "xmltok_impl.c" # undef XML_TOK_IMPL_C # undef MINBPC # undef BYTE_TYPE # undef BYTE_TO_ASCII # undef CHAR_MATCHES # undef IS_NAME_CHAR # undef IS_NAME_CHAR_MINBPC # undef IS_NMSTRT_CHAR # undef IS_NMSTRT_CHAR_MINBPC # undef IS_INVALID_CHAR #endif /* not XML_MIN_SIZE */ #ifdef XML_NS static const struct normal_encoding little2_encoding_ns = …; #endif static const struct normal_encoding little2_encoding = …; #if BYTEORDER != 4321 # ifdef XML_NS static const struct normal_encoding internal_little2_encoding_ns = …; # endif static const struct normal_encoding internal_little2_encoding = …; #endif #define BIG2_BYTE_TYPE(enc, p) … #define BIG2_BYTE_TO_ASCII(p) … #define BIG2_CHAR_MATCHES(p, c) … #define BIG2_IS_NAME_CHAR_MINBPC(p) … #define BIG2_IS_NMSTRT_CHAR_MINBPC(p) … #ifdef XML_MIN_SIZE static int PTRFASTCALL big2_byteType(const ENCODING *enc, const char *p) { return BIG2_BYTE_TYPE(enc, p); } static int PTRFASTCALL big2_byteToAscii(const ENCODING *enc, const char *p) { UNUSED_P(enc); return BIG2_BYTE_TO_ASCII(p); } static int PTRCALL big2_charMatches(const ENCODING *enc, const char *p, int c) { UNUSED_P(enc); return BIG2_CHAR_MATCHES(p, c); } static int PTRFASTCALL big2_isNameMin(const ENCODING *enc, const char *p) { UNUSED_P(enc); return BIG2_IS_NAME_CHAR_MINBPC(p); } static int PTRFASTCALL big2_isNmstrtMin(const ENCODING *enc, const char *p) { UNUSED_P(enc); return BIG2_IS_NMSTRT_CHAR_MINBPC(p); } # undef VTABLE #define VTABLE … #else /* not XML_MIN_SIZE */ # undef PREFIX #define PREFIX … #define MINBPC … /* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */ #define BYTE_TYPE … #define BYTE_TO_ASCII … #define CHAR_MATCHES … #define IS_NAME_CHAR … #define IS_NAME_CHAR_MINBPC … #define IS_NMSTRT_CHAR … #define IS_NMSTRT_CHAR_MINBPC … #define XML_TOK_IMPL_C # include "xmltok_impl.c" # undef XML_TOK_IMPL_C # undef MINBPC # undef BYTE_TYPE # undef BYTE_TO_ASCII # undef CHAR_MATCHES # undef IS_NAME_CHAR # undef IS_NAME_CHAR_MINBPC # undef IS_NMSTRT_CHAR # undef IS_NMSTRT_CHAR_MINBPC # undef IS_INVALID_CHAR #endif /* not XML_MIN_SIZE */ #ifdef XML_NS static const struct normal_encoding big2_encoding_ns = …; #endif static const struct normal_encoding big2_encoding = …; #if BYTEORDER != 1234 # ifdef XML_NS static const struct normal_encoding internal_big2_encoding_ns = {{VTABLE, 2, 0, 1}, { # include "iasciitab.h" # include "latin1tab.h" }, STANDARD_VTABLE(big2_) NULL_VTABLE}; # endif static const struct normal_encoding internal_big2_encoding = {{VTABLE, 2, 0, 1}, { #define BT_COLON … # include "iasciitab.h" # undef BT_COLON # include "latin1tab.h" }, STANDARD_VTABLE(big2_) NULL_VTABLE}; #endif #undef PREFIX static int FASTCALL streqci(const char *s1, const char *s2) { … } static void PTRCALL initUpdatePosition(const ENCODING *enc, const char *ptr, const char *end, POSITION *pos) { … } static int toAscii(const ENCODING *enc, const char *ptr, const char *end) { … } static int FASTCALL isSpace(int c) { … } /* 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) { … } static const char KW_version[] = …; static const char KW_encoding[] = …; static const char KW_standalone[] = …; static const char KW_yes[] = …; static const char KW_no[] = …; 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) { … } static int FASTCALL checkCharRefNumber(int result) { … } int FASTCALL XmlUtf8Encode(int c, char *buf) { … } int FASTCALL XmlUtf16Encode(int charNum, unsigned short *buf) { … } struct unknown_encoding { … }; #define AS_UNKNOWN_ENCODING(enc) … int XmlSizeOfUnknownEncoding(void) { … } static int PTRFASTCALL unknown_isName(const ENCODING *enc, const char *p) { … } static int PTRFASTCALL unknown_isNmstrt(const ENCODING *enc, const char *p) { … } static int PTRFASTCALL unknown_isInvalid(const ENCODING *enc, const char *p) { … } static enum XML_Convert_Result PTRCALL unknown_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim, char **toP, const char *toLim) { … } static enum XML_Convert_Result PTRCALL unknown_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim, unsigned short **toP, const unsigned short *toLim) { … } ENCODING * XmlInitUnknownEncoding(void *mem, int *table, CONVERTER convert, void *userData) { … } /* If this enumeration is changed, getEncodingIndex and encodings must also be changed. */ enum { … }; static const char KW_ISO_8859_1[] = …; static const char KW_US_ASCII[] = …; static const char KW_UTF_8[] = …; static const char KW_UTF_16[] = …; static const char KW_UTF_16BE[] = …; static const char KW_UTF_16LE[] = …; static int FASTCALL getEncodingIndex(const char *name) { … } /* For binary compatibility, we store the index of the encoding specified at initialization in the isUtf16 member. */ #define INIT_ENC_INDEX(enc) … #define SET_INIT_ENC_INDEX(enc, i) … /* This is what detects the encoding. encodingTable maps from encoding indices to encodings; INIT_ENC_INDEX(enc) is the index of the external (protocol) specified encoding; state is XML_CONTENT_STATE if we're parsing an external text entity, and XML_PROLOG_STATE otherwise. */ static int initScan(const ENCODING *const *encodingTable, const INIT_ENCODING *enc, int state, const char *ptr, const char *end, const char **nextTokPtr) { … } #define NS … #define ns … #define XML_TOK_NS_C #include "xmltok_ns.c" #undef XML_TOK_NS_C #undef NS #undef ns #ifdef XML_NS #define NS … #define ns … #define XML_TOK_NS_C # include "xmltok_ns.c" # undef XML_TOK_NS_C # undef NS # undef ns ENCODING * XmlInitUnknownEncodingNS(void *mem, int *table, CONVERTER convert, void *userData) { … } #endif /* XML_NS */
Codebase Browser
cpython