diff options
| author | Karen Arutyunov <karen@codesynthesis.com> | 2023-12-01 20:12:40 +0300 |
|---|---|---|
| committer | Karen Arutyunov <karen@codesynthesis.com> | 2024-04-01 20:52:07 +0300 |
| commit | 982a13b902e3c7989e10ca2ba6604ce6465a7253 (patch) | |
| tree | f0e12f09e6a17c6db6df9ff6e0b0131481eca50c | |
| parent | 1a1828648f3c06580ffe7a9f78c557a9e73c5bcd (diff) | |
Add ReaderMgr test
| -rw-r--r-- | libxerces-c/tests/reader-mgr/ReaderMgrTest.cpp | 168 | ||||
| -rw-r--r-- | libxerces-c/tests/reader-mgr/buildfile | 8 | ||||
| -rw-r--r-- | libxerces-c/tests/reader-mgr/characters.ent | 297 | ||||
| -rw-r--r-- | libxerces-c/tests/reader-mgr/links.ent | 24 | ||||
| -rw-r--r-- | libxerces-c/tests/reader-mgr/personal.dtd | 17 | ||||
| -rw-r--r-- | libxerces-c/tests/reader-mgr/testscript | 8 |
6 files changed, 522 insertions, 0 deletions
diff --git a/libxerces-c/tests/reader-mgr/ReaderMgrTest.cpp b/libxerces-c/tests/reader-mgr/ReaderMgrTest.cpp new file mode 100644 index 0000000..fc7e328 --- /dev/null +++ b/libxerces-c/tests/reader-mgr/ReaderMgrTest.cpp @@ -0,0 +1,168 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/* + * $Id$ + * + */ + +/* + * This test verifies the fix of the CVE-2018-1311 issue (see + * https://issues.apache.org/jira/projects/XERCESC/issues/XERCESC-2188 for all + * the gory details). + */ + +// --------------------------------------------------------------------------- +// Includes +// --------------------------------------------------------------------------- +#include <xercesc/util/XMLUni.hpp> +#include <xercesc/util/Janitor.hpp> +#include <xercesc/util/XMLString.hpp> +#include <xercesc/util/PlatformUtils.hpp> +#include <xercesc/sax/InputSource.hpp> +#include <xercesc/framework/XMLEntityDecl.hpp> +#include <xercesc/framework/MemoryManager.hpp> +#include <xercesc/validators/DTD/DTDValidator.hpp> +#include <xercesc/internal/ReaderMgr.hpp> + +#if defined(XERCES_NEW_IOSTREAMS) +#include <iostream> +#else +#include <iostream.h> +#endif + +#include <set> +#include <memory> // unique_ptr +#include <string> +#include <cstddef> // size_t + +#undef NDEBUG +#include <cassert> + +XERCES_CPP_NAMESPACE_USE + +using namespace std; + +inline XERCES_STD_QUALIFIER ostream& operator<<(XERCES_STD_QUALIFIER ostream& os, const XMLCh* xmlStr) +{ + char* transcoded = XMLString::transcode(xmlStr); + os << transcoded; + XMLString::release(&transcoded); + return os; +} + +struct XMLStringDeleter +{ + void operator() (XMLCh* p) const {if (p != nullptr) XMLString::release(&p);} +}; + +using XMLChPtr = unique_ptr<XMLCh, XMLStringDeleter>; + +// --------------------------------------------------------------------------- +// Program entry point +// --------------------------------------------------------------------------- +int +main(int argc, char** argv) +{ + // Init the XML platform + try + { + XMLPlatformUtils::Initialize(); + } + catch(const XMLException& toCatch) + { + XERCES_STD_QUALIFIER cout << "Error during platform init! Message:\n" + << toCatch.getMessage() << XERCES_STD_QUALIFIER endl; + return 1; + } + + MemoryManager* const fMemoryManager = XMLPlatformUtils::fgMemoryManager; + + { + set<string> entity_names; + ReaderMgr fReaderMgr; + + for (int i (1); i != argc; ++i) + { + string s (argv[i]); + size_t n (s.find ('=')); + + assert (n != string::npos); + + string name (s, 0, n); + + XMLChPtr sysId (XMLString::transcode(string (s, n + 1).c_str ())); + + { + XMLChPtr gDTDStr (XMLString::transcode(name.c_str ())); + bool new_entity (entity_names.emplace (move (name)).second); + + InputSource* srcUsed=0; + Janitor<InputSource> janSrc(srcUsed); + + XMLReader* reader = + fReaderMgr.createReader + ( + sysId.get () + , XMLUni::fgEmptyString /* pubId */ + , false /* xmlDecl */ + , XMLReader::RefFrom_NonLiteral + , XMLReader::Type_General + , XMLReader::Source_External + , srcUsed + ); + + assert (reader != nullptr); + + janSrc.reset(srcUsed); + + DTDEntityDecl* declDTD = + new (fMemoryManager) DTDEntityDecl(gDTDStr.get (), false, fMemoryManager); + + assert (fReaderMgr.pushReaderAdoptEntity(reader, declDTD) == new_entity); + } + + { + InputSource* srcUsed=0; + Janitor<InputSource> janSrc(srcUsed); + + XMLReader* reader = + fReaderMgr.createReader + ( + sysId.get () + , XMLUni::fgEmptyString /* pubId */ + , false /* xmlDecl */ + , XMLReader::RefFrom_NonLiteral + , XMLReader::Type_General + , XMLReader::Source_External + , srcUsed + ); + + assert (reader != nullptr); + + janSrc.reset(srcUsed); + + assert (fReaderMgr.pushReader(reader, nullptr)); + } + } + } + + // And call the termination method + XMLPlatformUtils::Terminate(); + + return 0; +} diff --git a/libxerces-c/tests/reader-mgr/buildfile b/libxerces-c/tests/reader-mgr/buildfile new file mode 100644 index 0000000..dc2405c --- /dev/null +++ b/libxerces-c/tests/reader-mgr/buildfile @@ -0,0 +1,8 @@ +# file : tests/reader-mgr/buildfile +# license : Apache License 2.0; see accompanying LICENSE file + +import libs = libxerces-c%lib{xerces-c} + +./: exe{driver} file{*.dtd *.ent} + +exe{driver}: {hxx cxx}{*} $libs testscript diff --git a/libxerces-c/tests/reader-mgr/characters.ent b/libxerces-c/tests/reader-mgr/characters.ent new file mode 100644 index 0000000..d3780e5 --- /dev/null +++ b/libxerces-c/tests/reader-mgr/characters.ent @@ -0,0 +1,297 @@ +<?xml encoding='ISO-8859-1'?> + +<!-- CHARACTERS ENTITY --> + +<!-- Latin A --> +<!ENTITY nbsp " "> <!-- U+00A0 ISOnum - no-break space = non-breaking space --> +<!ENTITY iexcl "¡"> <!-- U+00A1 ISOnum - inverted exclamation mark --> +<!ENTITY cent "¢"> <!-- U+00A2 ISOnum - cent sign --> +<!ENTITY pound "£"> <!-- U+00A3 ISOnum - pound sign --> +<!ENTITY curren "¤"> <!-- U+00A4 ISOnum - currency sign --> +<!ENTITY yen "¥"> <!-- U+00A5 ISOnum - yen sign = yuan sign --> +<!ENTITY brvbar "¦"> <!-- U+00A6 ISOnum - broken bar = broken vertical bar --> +<!ENTITY sect "§"> <!-- U+00A7 ISOnum - section sign --> +<!ENTITY uml "¨"> <!-- U+00A8 ISOdia - diaeresis = spacing diaeresis --> +<!ENTITY copy "©"> <!-- U+00A9 ISOnum - copyright sign --> +<!ENTITY ordf "ª"> <!-- U+00AA ISOnum - feminine ordinal indicator --> +<!ENTITY laquo "«"> <!-- U+00AB ISOnum - left-pointing double angle quotation mark = left pointing guillemet --> +<!ENTITY not "¬"> <!-- U+00AC ISOnum - not sign --> +<!ENTITY shy "­"> <!-- U+00AD ISOnum - soft hyphen = discretionary hyphen --> +<!ENTITY reg "®"> <!-- U+00AE ISOnum - registered sign = registered trade mark sign --> +<!ENTITY macr "¯"> <!-- U+00AF ISOdia - macron = spacing macron = overline = APL overbar --> +<!ENTITY deg "°"> <!-- U+00B0 ISOnum - degree sign --> +<!ENTITY plusmn "±"> <!-- U+00B1 ISOnum - plus-minus sign = plus-or-minus sign --> +<!ENTITY sup2 "²"> <!-- U+00B2 ISOnum - superscript two = superscript digit two = squared --> +<!ENTITY sup3 "³"> <!-- U+00B3 ISOnum - superscript three = superscript digit three = cubed --> +<!ENTITY acute "´"> <!-- U+00B4 ISOdia - acute accent = spacing acute --> +<!ENTITY micro "µ"> <!-- U+00B5 ISOnum - micro sign --> +<!ENTITY para "¶"> <!-- U+00B6 ISOnum - pilcrow sign = paragraph sign --> +<!ENTITY middot "·"> <!-- U+00B7 ISOnum - middle dot = Georgian comma = Greek middle dot --> +<!ENTITY cedil "¸"> <!-- U+00B8 ISOdia - cedilla = spacing cedilla --> +<!ENTITY sup1 "¹"> <!-- U+00B9 ISOnum - superscript one = superscript digit one --> +<!ENTITY ordm "º"> <!-- U+00BA ISOnum - masculine ordinal indicator --> +<!ENTITY raquo "»"> <!-- U+00BB ISOnum - right-pointing double angle quotation mark = right pointing guillemet --> +<!ENTITY frac14 "¼"> <!-- U+00BC ISOnum - vulgar fraction one quarter = fraction one quarter --> +<!ENTITY frac12 "½"> <!-- U+00BD ISOnum - vulgar fraction one half = fraction one half --> +<!ENTITY frac34 "¾"> <!-- U+00BE ISOnum - vulgar fraction three quarters = fraction three quarters --> +<!ENTITY iquest "¿"> <!-- U+00BF ISOnum - inverted question mark = turned question mark --> +<!ENTITY Agrave "À"> <!-- U+00C0 ISOlat1 - latin capital letter A with grave = latin capital letter A grave --> +<!ENTITY Aacute "Á"> <!-- U+00C1 ISOlat1 - latin capital letter A with acute --> +<!ENTITY Acirc "Â"> <!-- U+00C2 ISOlat1 - latin capital letter A with circumflex --> +<!ENTITY Atilde "Ã"> <!-- U+00C3 ISOlat1 - latin capital letter A with tilde --> +<!ENTITY Auml "Ä"> <!-- U+00C4 ISOlat1 - latin capital letter A with diaeresis --> +<!ENTITY Aring "Å"> <!-- U+00C5 ISOlat1 - latin capital letter A with ring above = latin capital letter A ring --> +<!ENTITY AElig "Æ"> <!-- U+00C6 ISOlat1 - latin capital letter AE = latin capital ligature AE --> +<!ENTITY Ccedil "Ç"> <!-- U+00C7 ISOlat1 - latin capital letter C with cedilla --> +<!ENTITY Egrave "È"> <!-- U+00C8 ISOlat1 - latin capital letter E with grave --> +<!ENTITY Eacute "É"> <!-- U+00C9 ISOlat1 - latin capital letter E with acute --> +<!ENTITY Ecirc "Ê"> <!-- U+00CA ISOlat1 - latin capital letter E with circumflex --> +<!ENTITY Euml "Ë"> <!-- U+00CB ISOlat1 - latin capital letter E with diaeresis --> +<!ENTITY Igrave "Ì"> <!-- U+00CC ISOlat1 - latin capital letter I with grave --> +<!ENTITY Iacute "Í"> <!-- U+00CD ISOlat1 - latin capital letter I with acute --> +<!ENTITY Icirc "Î"> <!-- U+00CE ISOlat1 - latin capital letter I with circumflex --> +<!ENTITY Iuml "Ï"> <!-- U+00CF ISOlat1 - latin capital letter I with diaeresis --> +<!ENTITY ETH "Ð"> <!-- U+00D0 ISOlat1 - latin capital letter ETH --> +<!ENTITY Ntilde "Ñ"> <!-- U+00D1 ISOlat1 - latin capital letter N with tilde --> +<!ENTITY Ograve "Ò"> <!-- U+00D2 ISOlat1 - latin capital letter O with grave --> +<!ENTITY Oacute "Ó"> <!-- U+00D3 ISOlat1 - latin capital letter O with acute --> +<!ENTITY Ocirc "Ô"> <!-- U+00D4 ISOlat1 - latin capital letter O with circumflex --> +<!ENTITY Otilde "Õ"> <!-- U+00D5 ISOlat1 - latin capital letter O with tilde --> +<!ENTITY Ouml "Ö"> <!-- U+00D6 ISOlat1 - latin capital letter O with diaeresis --> +<!ENTITY times "×"> <!-- U+00D7 ISOnum - multiplication sign --> +<!ENTITY Oslash "Ø"> <!-- U+00D8 ISOlat1 - latin capital letter O with stroke = latin capital letter O slash --> +<!ENTITY Ugrave "Ù"> <!-- U+00D9 ISOlat1 - latin capital letter U with grave --> +<!ENTITY Uacute "Ú"> <!-- U+00DA ISOlat1 - latin capital letter U with acute --> +<!ENTITY Ucirc "Û"> <!-- U+00DB ISOlat1 - latin capital letter U with circumflex --> +<!ENTITY Uuml "Ü"> <!-- U+00DC ISOlat1 - latin capital letter U with diaeresis --> +<!ENTITY Yacute "Ý"> <!-- U+00DD ISOlat1 - latin capital letter Y with acute --> +<!ENTITY THORN "Þ"> <!-- U+00DE ISOlat1 - latin capital letter THORN --> +<!ENTITY szlig "ß"> <!-- U+00DF ISOlat1 - latin small letter sharp s = ess-zed --> +<!ENTITY agrave "à"> <!-- U+00E0 ISOlat1 - latin small letter a with grave = latin small letter a grave --> +<!ENTITY aacute "á"> <!-- U+00E1 ISOlat1 - latin small letter a with acute --> +<!ENTITY acirc "â"> <!-- U+00E2 ISOlat1 - latin small letter a with circumflex --> +<!ENTITY atilde "ã"> <!-- U+00E3 ISOlat1 - latin small letter a with tilde --> +<!ENTITY auml "ä"> <!-- U+00E4 ISOlat1 - latin small letter a with diaeresis --> +<!ENTITY aring "å"> <!-- U+00E5 ISOlat1 - latin small letter a with ring above = latin small letter a ring --> +<!ENTITY aelig "æ"> <!-- U+00E6 ISOlat1 - latin small letter ae = latin small ligature ae --> +<!ENTITY ccedil "ç"> <!-- U+00E7 ISOlat1 - latin small letter c with cedilla --> +<!ENTITY egrave "è"> <!-- U+00E8 ISOlat1 - latin small letter e with grave --> +<!ENTITY eacute "é"> <!-- U+00E9 ISOlat1 - latin small letter e with acute --> +<!ENTITY ecirc "ê"> <!-- U+00EA ISOlat1 - latin small letter e with circumflex --> +<!ENTITY euml "ë"> <!-- U+00EB ISOlat1 - latin small letter e with diaeresis --> +<!ENTITY igrave "ì"> <!-- U+00EC ISOlat1 - latin small letter i with grave --> +<!ENTITY iacute "í"> <!-- U+00ED ISOlat1 - latin small letter i with acute --> +<!ENTITY icirc "î"> <!-- U+00EE ISOlat1 - latin small letter i with circumflex --> +<!ENTITY iuml "ï"> <!-- U+00EF ISOlat1 - latin small letter i with diaeresis --> +<!ENTITY eth "ð"> <!-- U+00F0 ISOlat1 - latin small letter eth --> +<!ENTITY ntilde "ñ"> <!-- U+00F1 ISOlat1 - latin small letter n with tilde --> +<!ENTITY ograve "ò"> <!-- U+00F2 ISOlat1 - latin small letter o with grave --> +<!ENTITY oacute "ó"> <!-- U+00F3 ISOlat1 - latin small letter o with acute --> +<!ENTITY ocirc "ô"> <!-- U+00F4 ISOlat1 - latin small letter o with circumflex --> +<!ENTITY otilde "õ"> <!-- U+00F5 ISOlat1 - latin small letter o with tilde --> +<!ENTITY ouml "ö"> <!-- U+00F6 ISOlat1 - latin small letter o with diaeresis --> +<!ENTITY divide "÷"> <!-- U+00F7 ISOnum - division sign --> +<!ENTITY oslash "ø"> <!-- U+00F8 ISOlat1 - latin small letter o with stroke = latin small letter o slash --> +<!ENTITY ugrave "ù"> <!-- U+00F9 ISOlat1 - latin small letter u with grave --> +<!ENTITY uacute "ú"> <!-- U+00FA ISOlat1 - latin small letter u with acute --> +<!ENTITY ucirc "û"> <!-- U+00FB ISOlat1 - latin small letter u with circumflex --> +<!ENTITY uuml "ü"> <!-- U+00FC ISOlat1 - latin small letter u with diaeresis --> +<!ENTITY yacute "ý"> <!-- U+00FD ISOlat1 - latin small letter y with acute --> +<!ENTITY thorn "þ"> <!-- U+00FE ISOlat1 - latin small letter thorn --> +<!ENTITY yuml "ÿ"> <!-- U+00FF ISOlat1 - latin small letter y with diaeresis --> + + +<!-- C0 Controls and Basic Latin --> +<!ENTITY quot """> <!-- U+0022 ISOnum - quotation mark = APL quote --> +<!ENTITY amp "&"> <!-- U+0026 ISOnum - ampersand --> +<!ENTITY lt "<"> <!-- U+003C ISOnum - less-than sign --> +<!ENTITY gt ">"> <!-- U+003E ISOnum - greater-than sign --> + +<!-- Latin Extended-A --> +<!ENTITY OElig "Œ"> <!-- U+0152 ISOlat2 - latin capital ligature OE --> +<!ENTITY oelig "œ"> <!-- U+0153 ISOlat2 - latin small ligature oe --> + +<!-- ligature is a misnomer, this is a separate character in some languages --> +<!ENTITY Scaron "Š"> <!-- U+0160 ISOlat2 - latin capital letter S with caron --> +<!ENTITY scaron "š"> <!-- U+0161 ISOlat2 - latin small letter s with caron --> +<!ENTITY Yuml "Ÿ"> <!-- U+0178 ISOlat2 - latin capital letter Y with diaeresis --> + +<!-- Spacing Modifier Letters --> +<!ENTITY circ "ˆ" > <!-- U+02C6 ISOpub - modifier letter circumflex accent --> +<!ENTITY tilde "˜" > <!-- U+02DC ISOdia - small tilde --> + +<!-- General Punctuation --> +<!ENTITY ensp " "> <!-- U+2002 ISOpub - en space --> +<!ENTITY emsp " "> <!-- U+2003 ISOpub - em space --> +<!ENTITY thinsp " "> <!-- U+2009 ISOpub - thin space --> +<!ENTITY zwnj "‌"> <!-- U+200C RFC 2070 - zero width non-joiner --> +<!ENTITY zwj "‍"> <!-- U+200D RFC 2070 - zero width joiner --> +<!ENTITY lrm "‎"> <!-- U+200E RFC 2070 - left-to-right mark --> +<!ENTITY rlm "‏"> <!-- U+200F RFC 2070 - right-to-left mark --> +<!ENTITY ndash "–"> <!-- U+2013 ISOpub - en dash --> +<!ENTITY mdash "—"> <!-- U+2014 ISOpub - em dash --> +<!ENTITY lsquo "‘"> <!-- U+2018 ISOnum - left single quotation mark --> +<!ENTITY rsquo "’"> <!-- U+2019 ISOnum - right single quotation mark --> +<!ENTITY sbquo "‚"> <!-- U+201A NEW - single low-9 quotation mark --> +<!ENTITY ldquo "“"> <!-- U+201C ISOnum - left double quotation mark --> +<!ENTITY rdquo "”"> <!-- U+201D ISOnum - right double quotation mark, --> +<!ENTITY bdquo "„"> <!-- U+201E NEW - double low-9 quotation mark --> +<!ENTITY dagger "†"> <!-- U+2020 ISOpub - dagger --> +<!ENTITY Dagger "‡"> <!-- U+2021 ISOpub - double dagger --> +<!ENTITY permil "‰"> <!-- U+2030 ISOtech - per mille sign --> +<!ENTITY lsaquo "‹"> <!-- U+2039 ISO prop. - single left-pointing angle quotation mark --> + +<!-- lsaquo is proposed but not yet ISO standardized --> +<!ENTITY rsaquo "›"> <!-- U+203A ISO prop. - single right-pointing angle quotation mark --> + +<!-- rsaquo is proposed but not yet ISO standardized --> +<!ENTITY euro "€"> <!-- U+20AC NEW - euro sign --> + +<!-- Latin Extended-B --> +<!ENTITY fnof "ƒ"> <!-- U+0192 ISOtech - latin small f with hook = function = florin --> + +<!-- Greek --> +<!ENTITY Alpha "Α"> <!-- U+0391 - greek capital letter alpha --> +<!ENTITY Beta "Β"> <!-- U+0392 - greek capital letter beta --> +<!ENTITY Gamma "Γ"> <!-- U+0393 ISOgrk3 - greek capital letter gamma --> +<!ENTITY Delta "Δ"> <!-- U+0394 ISOgrk3 - greek capital letter delta --> +<!ENTITY Epsilon "Ε"> <!-- U+0395 - greek capital letter epsilon --> +<!ENTITY Zeta "Ζ"> <!-- U+0396 - greek capital letter zeta --> +<!ENTITY Eta "Η"> <!-- U+0397 - greek capital letter eta --> +<!ENTITY Theta "Θ"> <!-- U+0398 ISOgrk3 - greek capital letter theta --> +<!ENTITY Iota "Ι"> <!-- U+0399 - greek capital letter iota --> +<!ENTITY Kappa "Κ"> <!-- U+039A - greek capital letter kappa --> +<!ENTITY Lambda "Λ"> <!-- U+039B ISOgrk3 - greek capital letter lambda --> +<!ENTITY Mu "Μ"> <!-- U+039C - greek capital letter mu --> +<!ENTITY Nu "Ν"> <!-- U+039D - greek capital letter nu --> +<!ENTITY Xi "Ξ"> <!-- U+039E ISOgrk3 - greek capital letter xi --> +<!ENTITY Omicron "Ο"> <!-- U+039F - greek capital letter omicron --> +<!ENTITY Pi "Π"> <!-- U+03A0 ISOgrk3 - greek capital letter pi --> +<!ENTITY Rho "Ρ"> <!-- U+03A1 - greek capital letter rho --> +<!ENTITY Sigma "Σ"> <!-- U+03A3 ISOgrk3 - greek capital letter sigma --> +<!ENTITY Tau "Τ"> <!-- U+03A4 - greek capital letter tau --> +<!ENTITY Upsilon "Υ"> <!-- U+03A5 ISOgrk3 - greek capital letter upsilon --> +<!ENTITY Phi "Φ"> <!-- U+03A6 ISOgrk3 - greek capital letter phi --> +<!ENTITY Chi "Χ"> <!-- U+03A7 - greek capital letter chi --> +<!ENTITY Psi "Ψ"> <!-- U+03A8 ISOgrk3 - greek capital letter psi --> +<!ENTITY Omega "Ω"> <!-- U+03A9 ISOgrk3 - greek capital letter omega --> +<!ENTITY alpha "α"> <!-- U+03B1 ISOgrk3 - greek small letter alpha --> +<!ENTITY beta "β"> <!-- U+03B2 ISOgrk3 - greek small letter beta --> +<!ENTITY gamma "γ"> <!-- U+03B3 ISOgrk3 - greek small letter gamma --> +<!ENTITY delta "δ"> <!-- U+03B4 ISOgrk3 - greek small letter delta --> +<!ENTITY epsilon "ε"> <!-- U+03B5 ISOgrk3 - greek small letter epsilon --> +<!ENTITY zeta "ζ"> <!-- U+03B6 ISOgrk3 - greek small letter zeta --> +<!ENTITY eta "η"> <!-- U+03B7 ISOgrk3 - greek small letter eta --> +<!ENTITY theta "θ"> <!-- U+03B8 ISOgrk3 - greek small letter theta --> +<!ENTITY iota "ι"> <!-- U+03B9 ISOgrk3 - greek small letter iota --> +<!ENTITY kappa "κ"> <!-- U+03BA ISOgrk3 - greek small letter kappa --> +<!ENTITY lambda "λ"> <!-- U+03BB ISOgrk3 - greek small letter lambda --> +<!ENTITY mu "μ"> <!-- U+03BC ISOgrk3 - greek small letter mu --> +<!ENTITY nu "ν"> <!-- U+03BD ISOgrk3 - greek small letter nu --> +<!ENTITY xi "ξ"> <!-- U+03BE ISOgrk3 - greek small letter xi --> +<!ENTITY omicron "ο"> <!-- U+03BF NEW - greek small letter omicron --> +<!ENTITY pi "π"> <!-- U+03C0 ISOgrk3 - greek small letter pi --> +<!ENTITY rho "ρ"> <!-- U+03C1 ISOgrk3 - greek small letter rho --> +<!ENTITY sigmaf "ς"> <!-- U+03C2 ISOgrk3 - greek small letter final sigma --> +<!ENTITY sigma "σ"> <!-- U+03C3 ISOgrk3 - greek small letter sigma --> +<!ENTITY tau "τ"> <!-- U+03C4 ISOgrk3 - greek small letter tau --> +<!ENTITY upsilon "υ"> <!-- U+03C5 ISOgrk3 - greek small letter upsilon --> +<!ENTITY phi "φ"> <!-- U+03C6 ISOgrk3 - greek small letter phi --> +<!ENTITY chi "χ"> <!-- U+03C7 ISOgrk3 - greek small letter chi --> +<!ENTITY psi "ψ"> <!-- U+03C8 ISOgrk3 - greek small letter psi --> +<!ENTITY omega "ω"> <!-- U+03C9 ISOgrk3 - greek small letter omega --> +<!ENTITY thetasym "ϑ"> <!-- U+03D1 NEW - greek small letter theta symbol --> +<!ENTITY upsih "ϒ"> <!-- U+03D2 NEW - greek upsilon with hook symbol --> +<!ENTITY piv "ϖ"> <!-- U+03D6 ISOgrk3 - greek pi symbol --> + +<!-- General Punctuation --> +<!ENTITY bull "•"> <!-- U+2022 ISOpub - bullet = black small circle --> +<!ENTITY hellip "…"> <!-- U+2026 ISOpub - horizontal ellipsis = three dot leader --> +<!ENTITY prime "′"> <!-- U+2032 ISOtech - prime = minutes = feet --> +<!ENTITY Prime "″"> <!-- U+2033 ISOtech - double prime = seconds = inches --> +<!ENTITY oline "‾"> <!-- U+203E NEW - overline = spacing overscore --> +<!ENTITY frasl "⁄"> <!-- U+2044 NEW - fraction slash --> + +<!-- Letterlike Symbols --> +<!ENTITY weierp "℘"> <!-- U+2118 ISOamso - script capital P = power set = Weierstrass p --> +<!ENTITY image "ℑ"> <!-- U+2111 ISOamso - blackletter capital I = imaginary part --> +<!ENTITY real "ℜ"> <!-- U+211C ISOamso - blackletter capital R = real part symbol --> +<!ENTITY trade "™"> <!-- U+2122 ISOnum - trade mark sign --> +<!ENTITY alefsym "ℵ"> <!-- U+2135 NEW - alef symbol = first transfinite cardinal --> + +<!-- Arrows --> +<!ENTITY larr "←"> <!-- U+2190 ISOnum - leftwards arrow --> +<!ENTITY uarr "↑"> <!-- U+2191 ISOnum - upwards arrow --> +<!ENTITY rarr "→"> <!-- U+2192 ISOnum - rightwards arrow --> +<!ENTITY darr "↓"> <!-- U+2193 ISOnum - downwards arrow --> +<!ENTITY harr "↔"> <!-- U+2194 ISOamsa - left right arrow --> +<!ENTITY crarr "↵"> <!-- U+21B5 NEW - downwards arrow with corner leftwards = carriage return --> +<!ENTITY lArr "⇐"> <!-- U+21D0 ISOtech - leftwards double arrow --> +<!ENTITY uArr "⇑"> <!-- U+21D1 ISOamsa - upwards double arrow --> +<!ENTITY rArr "⇒"> <!-- U+21D2 ISOtech - rightwards double arrow --> +<!ENTITY dArr "⇓"> <!-- U+21D3 ISOamsa - downwards double arrow --> +<!ENTITY hArr "⇔"> <!-- U+21D4 ISOamsa - left right double arrow --> + +<!-- Mathematical Operators --> +<!ENTITY forall "∀"> <!-- U+2200 ISOtech - for all --> +<!ENTITY part "∂"> <!-- U+2202 ISOtech - partial differential --> +<!ENTITY exist "∃"> <!-- U+2203 ISOtech - there exists --> +<!ENTITY empty "∅"> <!-- U+2205 ISOamso - empty set = null set = diameter --> +<!ENTITY nabla "∇"> <!-- U+2207 ISOtech - nabla = backward difference --> +<!ENTITY isin "∈"> <!-- U+2208 ISOtech - element of --> +<!ENTITY notin "∉"> <!-- U+2209 ISOtech - not an element of --> +<!ENTITY ni "∋"> <!-- U+220B ISOtech - contains as member --> +<!ENTITY prod "∏"> <!-- U+220F ISOamsb - n-ary product = product sign --> +<!ENTITY sum "∑"> <!-- U+2211 ISOamsb - n-ary sumation --> +<!ENTITY minus "−"> <!-- U+2212 ISOtech - minus sign --> +<!ENTITY lowast "∗"> <!-- U+2217 ISOtech - asterisk operator --> +<!ENTITY radic "√"> <!-- U+221A ISOtech - square root = radical sign --> +<!ENTITY prop "∝"> <!-- U+221D ISOtech - proportional to --> +<!ENTITY infin "∞"> <!-- U+221E ISOtech - infinity --> +<!ENTITY ang "∠"> <!-- U+2220 ISOamso - angle --> +<!ENTITY and "∧"> <!-- U+2227 ISOtech - logical and = wedge --> +<!ENTITY or "∨"> <!-- U+2228 ISOtech - logical or = vee --> +<!ENTITY cap "∩"> <!-- U+2229 ISOtech - intersection = cap --> +<!ENTITY cup "∪"> <!-- U+222A ISOtech - union = cup --> +<!ENTITY int "∫"> <!-- U+222B ISOtech - integral --> +<!ENTITY there4 "∴"> <!-- U+2234 ISOtech - therefore --> +<!ENTITY sim "∼"> <!-- U+223C ISOtech - tilde operator = varies with = similar to --> +<!ENTITY cong "≅"> <!-- U+2245 ISOtech - approximately equal to --> +<!ENTITY asymp "≈"> <!-- U+2248 ISOamsr - almost equal to = asymptotic to --> +<!ENTITY ne "≠"> <!-- U+2260 ISOtech - not equal to --> +<!ENTITY equiv "≡"> <!-- U+2261 ISOtech - identical to --> +<!ENTITY le "≤"> <!-- U+2264 ISOtech - less-than or equal to --> +<!ENTITY ge "≥"> <!-- U+2265 ISOtech - greater-than or equal to --> +<!ENTITY sub "⊂"> <!-- U+2282 ISOtech - subset of --> +<!ENTITY sup "⊃"> <!-- U+2283 ISOtech - superset of --> +<!ENTITY nsub "⊄"> <!-- U+2284 ISOamsn - not a subset of --> +<!ENTITY sube "⊆"> <!-- U+2286 ISOtech - subset of or equal to --> +<!ENTITY supe "⊇"> <!-- U+2287 ISOtech - superset of or equal to --> +<!ENTITY oplus "⊕"> <!-- U+2295 ISOamsb - circled plus = direct sum --> +<!ENTITY otimes "⊗"> <!-- U+2297 ISOamsb - circled times = vector product --> +<!ENTITY perp "⊥"> <!-- U+22A5 ISOtech - up tack = orthogonal to = perpendicular --> +<!ENTITY sdot "⋅"> <!-- U+22C5 ISOamsb - dot operator --> + +<!-- Miscellaneous Technical --> +<!ENTITY lceil "⌈"> <!-- U+2308 ISOamsc - left ceiling = apl upstile --> +<!ENTITY rceil "⌉"> <!-- U+2309 ISOamsc - right ceiling --> +<!ENTITY lfloor "⌊"> <!-- U+230A ISOamsc - left floor = apl downstile --> +<!ENTITY rfloor "⌋"> <!-- U+230B ISOamsc - right floor --> +<!ENTITY lang "〈"> <!-- U+2329 ISOtech - left-pointing angle bracket = bra --> +<!ENTITY rang "〉"> <!-- U+232A ISOtech - right-pointing angle bracket = ket --> + +<!-- Geometric Shapes --> +<!ENTITY loz "◊"> <!-- U+25CA ISOpub - lozenge --> + +<!-- Miscellaneous Symbols --> +<!ENTITY spades "♠"> <!-- U+2660 ISOpub - black spade suit --> +<!ENTITY clubs "♣"> <!-- U+2663 ISOpub - black club suit = shamrock --> +<!ENTITY hearts "♥"> <!-- U+2665 ISOpub - black heart suit = valentine --> +<!ENTITY diams "♦"> <!-- U+2666 ISOpub - black diamond suit --> + +<!-- CVS $Revision$ $Date$ --> + +<!-- Portions (C) International Organization for Standardization 1986 + Permission to copy in any form is granted for use with + conforming SGML systems and applications as defined in + ISO 8879, provided this notice is included in all copies. --> diff --git a/libxerces-c/tests/reader-mgr/links.ent b/libxerces-c/tests/reader-mgr/links.ent new file mode 100644 index 0000000..a8f9fd4 --- /dev/null +++ b/libxerces-c/tests/reader-mgr/links.ent @@ -0,0 +1,24 @@ +<?xml encoding='ISO-8859-1'?> + +<!-- LINKS ENTITY --> +<!ENTITY % links "link|anchor|jump|img|resource-ref|human-resource-ref"> + +<!ELEMENT anchor EMPTY> +<!ATTLIST anchor name NMTOKEN #REQUIRED> + +<!ELEMENT img EMPTY> +<!ATTLIST img src CDATA #REQUIRED + alt CDATA #REQUIRED> + +<!ELEMENT link (#PCDATA|img)*> +<!ATTLIST link idref NMTOKEN #IMPLIED + anchor CDATA #IMPLIED> + +<!ELEMENT jump (#PCDATA|img)*> +<!ATTLIST jump href CDATA #REQUIRED> + +<!-- cross-reference resource elements --> +<!ELEMENT resource-ref EMPTY> +<!ATTLIST resource-ref idref CDATA #REQUIRED> +<!ELEMENT human-resource-ref EMPTY> +<!ATTLIST human-resource-ref idref CDATA #REQUIRED>
\ No newline at end of file diff --git a/libxerces-c/tests/reader-mgr/personal.dtd b/libxerces-c/tests/reader-mgr/personal.dtd new file mode 100644 index 0000000..e636266 --- /dev/null +++ b/libxerces-c/tests/reader-mgr/personal.dtd @@ -0,0 +1,17 @@ +<?xml encoding="ISO-8859-1"?> + +<!-- @version: --> + +<!ELEMENT personnel (person)+> +<!ELEMENT person (name,email*,url*,link?)> +<!ATTLIST person id ID #REQUIRED> +<!ELEMENT family (#PCDATA)> +<!ELEMENT given (#PCDATA)> +<!ELEMENT name (#PCDATA|family|given)*> +<!ELEMENT email (#PCDATA)> +<!ELEMENT url EMPTY> +<!ATTLIST url href CDATA #REQUIRED> +<!ELEMENT link EMPTY> +<!ATTLIST link + manager IDREF #IMPLIED + subordinates IDREFS #IMPLIED> diff --git a/libxerces-c/tests/reader-mgr/testscript b/libxerces-c/tests/reader-mgr/testscript new file mode 100644 index 0000000..09bb7cc --- /dev/null +++ b/libxerces-c/tests/reader-mgr/testscript @@ -0,0 +1,8 @@ +# file : tests/reader-mgr/testscript +# license : Apache License 2.0; see accompanying LICENSE file + +: basics +: +$* "personal=$src_base/personal.dtd" \ + "links=$src_base/links.ent" \ + "characters=$src_base/characters.ent" |