Something went wrong. Try again.
Reactos
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436/* * parserInternals.c : Internal routines (and obsolete ones) needed for the * XML and HTML parsers. * * See Copyright for the status of this software. * * daniel@veillard.com */
#define IN_LIBXML#include "libxml.h"
#if defined(_WIN32)#define XML_DIR_SEP '\\'#else#define XML_DIR_SEP '/'#endif
#include <string.h>#include <ctype.h>#include <stdlib.h>
#include <libxml/xmlmemory.h>#include <libxml/tree.h>#include <libxml/parser.h>#include <libxml/parserInternals.h>#include <libxml/entities.h>#include <libxml/xmlerror.h>#include <libxml/encoding.h>#include <libxml/xmlIO.h>#include <libxml/uri.h>#include <libxml/dict.h>#include <libxml/xmlsave.h>#ifdef LIBXML_CATALOG_ENABLED#include <libxml/catalog.h>#endif#include <libxml/chvalid.h>
#define CUR(ctxt) ctxt->input->cur#define END(ctxt) ctxt->input->end
#include "private/buf.h"#include "private/enc.h"#include "private/error.h"#include "private/io.h"#include "private/parser.h"
/* * XML_MAX_AMPLIFICATION_DEFAULT is the default maximum allowed amplification * factor of serialized output after entity expansion. */#define XML_MAX_AMPLIFICATION_DEFAULT 5
/* * Various global defaults for parsing */
/** * xmlCheckVersion: * @version: the include version number * * check the compiled lib version against the include one. * This can warn or immediately kill the application */voidxmlCheckVersion(int version) { int myversion = LIBXML_VERSION;
xmlInitParser();
if ((myversion / 10000) != (version / 10000)) { xmlGenericError(xmlGenericErrorContext, "Fatal: program compiled against libxml %d using libxml %d\n", (version / 10000), (myversion / 10000)); fprintf(stderr, "Fatal: program compiled against libxml %d using libxml %d\n", (version / 10000), (myversion / 10000)); } if ((myversion / 100) < (version / 100)) { xmlGenericError(xmlGenericErrorContext, "Warning: program compiled against libxml %d using older %d\n", (version / 100), (myversion / 100)); }}
/************************************************************************ * * * Some factorized error routines * * * ************************************************************************/
/** * xmlErrMemory: * @ctxt: an XML parser context * @extra: extra information * * Handle a redefinition of attribute error */voidxmlErrMemory(xmlParserCtxtPtr ctxt, const char *extra){ if ((ctxt != NULL) && (ctxt->disableSAX != 0) && (ctxt->instate == XML_PARSER_EOF)) return; if (ctxt != NULL) { ctxt->errNo = XML_ERR_NO_MEMORY; ctxt->instate = XML_PARSER_EOF; ctxt->disableSAX = 1; } if (extra) __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, XML_ERR_NO_MEMORY, XML_ERR_FATAL, NULL, 0, extra, NULL, NULL, 0, 0, "Memory allocation failed : %s\n", extra); else __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, XML_ERR_NO_MEMORY, XML_ERR_FATAL, NULL, 0, NULL, NULL, NULL, 0, 0, "Memory allocation failed\n");}
/** * __xmlErrEncoding: * @ctxt: an XML parser context * @xmlerr: the error number * @msg: the error message * @str1: an string info * @str2: an string info * * Handle an encoding error */void__xmlErrEncoding(xmlParserCtxtPtr ctxt, xmlParserErrors xmlerr, const char *msg, const xmlChar * str1, const xmlChar * str2){ if ((ctxt != NULL) && (ctxt->disableSAX != 0) && (ctxt->instate == XML_PARSER_EOF)) return; if (ctxt != NULL) ctxt->errNo = xmlerr; __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, xmlerr, XML_ERR_FATAL, NULL, 0, (const char *) str1, (const char *) str2, NULL, 0, 0, msg, str1, str2); if (ctxt != NULL) { ctxt->wellFormed = 0; if (ctxt->recovery == 0) ctxt->disableSAX = 1; }}
/** * xmlErrInternal: * @ctxt: an XML parser context * @msg: the error message * @str: error information * * Handle an internal error */static void LIBXML_ATTR_FORMAT(2,0)xmlErrInternal(xmlParserCtxtPtr ctxt, const char *msg, const xmlChar * str){ if ((ctxt != NULL) && (ctxt->disableSAX != 0) && (ctxt->instate == XML_PARSER_EOF)) return; if (ctxt != NULL) ctxt->errNo = XML_ERR_INTERNAL_ERROR; __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, XML_ERR_INTERNAL_ERROR, XML_ERR_FATAL, NULL, 0, (const char *) str, NULL, NULL, 0, 0, msg, str); if (ctxt != NULL) { ctxt->wellFormed = 0; if (ctxt->recovery == 0) ctxt->disableSAX = 1; }}
/** * xmlFatalErr: * @ctxt: an XML parser context * @error: the error number * @info: extra information string * * Handle a fatal parser error, i.e. violating Well-Formedness constraints */voidxmlFatalErr(xmlParserCtxtPtr ctxt, xmlParserErrors error, const char *info){ const char *errmsg;
if ((ctxt != NULL) && (ctxt->disableSAX != 0) && (ctxt->instate == XML_PARSER_EOF)) return; switch (error) { case XML_ERR_INVALID_HEX_CHARREF: errmsg = "CharRef: invalid hexadecimal value"; break; case XML_ERR_INVALID_DEC_CHARREF: errmsg = "CharRef: invalid decimal value"; break; case XML_ERR_INVALID_CHARREF: errmsg = "CharRef: invalid value"; break; case XML_ERR_INTERNAL_ERROR: errmsg = "internal error"; break; case XML_ERR_PEREF_AT_EOF: errmsg = "PEReference at end of document"; break; case XML_ERR_PEREF_IN_PROLOG: errmsg = "PEReference in prolog"; break; case XML_ERR_PEREF_IN_EPILOG: errmsg = "PEReference in epilog"; break; case XML_ERR_PEREF_NO_NAME: errmsg = "PEReference: no name"; break; case XML_ERR_PEREF_SEMICOL_MISSING: errmsg = "PEReference: expecting ';'"; break; case XML_ERR_ENTITY_LOOP: errmsg = "Detected an entity reference loop"; break; case XML_ERR_ENTITY_NOT_STARTED: errmsg = "EntityValue: \" or ' expected"; break; case XML_ERR_ENTITY_PE_INTERNAL: errmsg = "PEReferences forbidden in internal subset"; break; case XML_ERR_ENTITY_NOT_FINISHED: errmsg = "EntityValue: \" or ' expected"; break; case XML_ERR_ATTRIBUTE_NOT_STARTED: errmsg = "AttValue: \" or ' expected"; break; case XML_ERR_LT_IN_ATTRIBUTE: errmsg = "Unescaped '<' not allowed in attributes values"; break; case XML_ERR_LITERAL_NOT_STARTED: errmsg = "SystemLiteral \" or ' expected"; break; case XML_ERR_LITERAL_NOT_FINISHED: errmsg = "Unfinished System or Public ID \" or ' expected"; break; case XML_ERR_MISPLACED_CDATA_END: errmsg = "Sequence ']]>' not allowed in content"; break; case XML_ERR_URI_REQUIRED: errmsg = "SYSTEM or PUBLIC, the URI is missing"; break; case XML_ERR_PUBID_REQUIRED: errmsg = "PUBLIC, the Public Identifier is missing"; break; case XML_ERR_HYPHEN_IN_COMMENT: errmsg = "Comment must not contain '--' (double-hyphen)"; break; case XML_ERR_PI_NOT_STARTED: errmsg = "xmlParsePI : no target name"; break; case XML_ERR_RESERVED_XML_NAME: errmsg = "Invalid PI name"; break; case XML_ERR_NOTATION_NOT_STARTED: errmsg = "NOTATION: Name expected here"; break; case XML_ERR_NOTATION_NOT_FINISHED: errmsg = "'>' required to close NOTATION declaration"; break; case XML_ERR_VALUE_REQUIRED: errmsg = "Entity value required"; break; case XML_ERR_URI_FRAGMENT: errmsg = "Fragment not allowed"; break; case XML_ERR_ATTLIST_NOT_STARTED: errmsg = "'(' required to start ATTLIST enumeration"; break; case XML_ERR_NMTOKEN_REQUIRED: errmsg = "NmToken expected in ATTLIST enumeration"; break; case XML_ERR_ATTLIST_NOT_FINISHED: errmsg = "')' required to finish ATTLIST enumeration"; break; case XML_ERR_MIXED_NOT_STARTED: errmsg = "MixedContentDecl : '|' or ')*' expected"; break; case XML_ERR_PCDATA_REQUIRED: errmsg = "MixedContentDecl : '#PCDATA' expected"; break; case XML_ERR_ELEMCONTENT_NOT_STARTED: errmsg = "ContentDecl : Name or '(' expected"; break; case XML_ERR_ELEMCONTENT_NOT_FINISHED: errmsg = "ContentDecl : ',' '|' or ')' expected"; break; case XML_ERR_PEREF_IN_INT_SUBSET: errmsg = "PEReference: forbidden within markup decl in internal subset"; break; case XML_ERR_GT_REQUIRED: errmsg = "expected '>'"; break; case XML_ERR_CONDSEC_INVALID: errmsg = "XML conditional section '[' expected"; break; case XML_ERR_EXT_SUBSET_NOT_FINISHED: errmsg = "Content error in the external subset"; break; case XML_ERR_CONDSEC_INVALID_KEYWORD: errmsg = "conditional section INCLUDE or IGNORE keyword expected"; break; case XML_ERR_CONDSEC_NOT_FINISHED: errmsg = "XML conditional section not closed"; break; case XML_ERR_XMLDECL_NOT_STARTED: errmsg = "Text declaration '<?xml' required"; break; case XML_ERR_XMLDECL_NOT_FINISHED: errmsg = "parsing XML declaration: '?>' expected"; break; case XML_ERR_EXT_ENTITY_STANDALONE: errmsg = "external parsed entities cannot be standalone"; break; case XML_ERR_ENTITYREF_SEMICOL_MISSING: errmsg = "EntityRef: expecting ';'"; break; case XML_ERR_DOCTYPE_NOT_FINISHED: errmsg = "DOCTYPE improperly terminated"; break; case XML_ERR_LTSLASH_REQUIRED: errmsg = "EndTag: '</' not found"; break; case XML_ERR_EQUAL_REQUIRED: errmsg = "expected '='"; break; case XML_ERR_STRING_NOT_CLOSED: errmsg = "String not closed expecting \" or '"; break; case XML_ERR_STRING_NOT_STARTED: errmsg = "String not started expecting ' or \""; break; case XML_ERR_ENCODING_NAME: errmsg = "Invalid XML encoding name"; break; case XML_ERR_STANDALONE_VALUE: errmsg = "standalone accepts only 'yes' or 'no'"; break; case XML_ERR_DOCUMENT_EMPTY: errmsg = "Document is empty"; break; case XML_ERR_DOCUMENT_END: errmsg = "Extra content at the end of the document"; break; case XML_ERR_NOT_WELL_BALANCED: errmsg = "chunk is not well balanced"; break; case XML_ERR_EXTRA_CONTENT: errmsg = "extra content at the end of well balanced chunk"; break; case XML_ERR_VERSION_MISSING: errmsg = "Malformed declaration expecting version"; break; case XML_ERR_NAME_TOO_LONG: errmsg = "Name too long"; break; case XML_ERR_INVALID_ENCODING: errmsg = "Invalid bytes in character encoding"; break; case XML_IO_UNKNOWN: errmsg = "I/O error"; break;#if 0 case: errmsg = ""; break;#endif default: errmsg = "Unregistered error message"; } if (ctxt != NULL) ctxt->errNo = error; if (info == NULL) { __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL, NULL, 0, info, NULL, NULL, 0, 0, "%s\n", errmsg); } else { __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL, NULL, 0, info, NULL, NULL, 0, 0, "%s: %s\n", errmsg, info); } if (ctxt != NULL) { ctxt->wellFormed = 0; if (ctxt->recovery == 0) ctxt->disableSAX = 1; }}
/** * xmlErrEncodingInt: * @ctxt: an XML parser context * @error: the error number * @msg: the error message * @val: an integer value * * n encoding error */static void LIBXML_ATTR_FORMAT(3,0)xmlErrEncodingInt(xmlParserCtxtPtr ctxt, xmlParserErrors error, const char *msg, int val){ if ((ctxt != NULL) && (ctxt->disableSAX != 0) && (ctxt->instate == XML_PARSER_EOF)) return; if (ctxt != NULL) ctxt->errNo = error; __xmlRaiseError(NULL, NULL, NULL, ctxt, NULL, XML_FROM_PARSER, error, XML_ERR_FATAL, NULL, 0, NULL, NULL, NULL, val, 0, msg, val); if (ctxt != NULL) { ctxt->wellFormed = 0; if (ctxt->recovery == 0) ctxt->disableSAX = 1; }}
/** * xmlIsLetter: * @c: an unicode character (int) * * Check whether the character is allowed by the production * [84] Letter ::= BaseChar | Ideographic * * Returns 0 if not, non-zero otherwise */intxmlIsLetter(int c) { return(IS_BASECHAR(c) || IS_IDEOGRAPHIC(c));}
/************************************************************************ * * * Input handling functions for progressive parsing * * * ************************************************************************/
/* we need to keep enough input to show errors in context */#define LINE_LEN 80
/** * xmlHaltParser: * @ctxt: an XML parser context * * Blocks further parser processing don't override error * for internal use */voidxmlHaltParser(xmlParserCtxtPtr ctxt) { if (ctxt == NULL) return; ctxt->instate = XML_PARSER_EOF; ctxt->disableSAX = 1; while (ctxt->inputNr > 1) xmlFreeInputStream(inputPop(ctxt)); if (ctxt->input != NULL) { /* * in case there was a specific allocation deallocate before * overriding base */ if (ctxt->input->free != NULL) { ctxt->input->free((xmlChar *) ctxt->input->base); ctxt->input->free = NULL; } if (ctxt->input->buf != NULL) { xmlFreeParserInputBuffer(ctxt->input->buf); ctxt->input->buf = NULL; } ctxt->input->cur = BAD_CAST""; ctxt->input->length = 0; ctxt->input->base = ctxt->input->cur; ctxt->input->end = ctxt->input->cur; }}
/** * xmlParserInputRead: * @in: an XML parser input * @len: an indicative size for the lookahead * * DEPRECATED: This function was internal and is deprecated. * * Returns -1 as this is an error to use it. */intxmlParserInputRead(xmlParserInputPtr in ATTRIBUTE_UNUSED, int len ATTRIBUTE_UNUSED) { return(-1);}
/** * xmlParserGrow: * @ctxt: an XML parser context * * Grow the input buffer. * * Returns the number of bytes read or -1 in case of error. */intxmlParserGrow(xmlParserCtxtPtr ctxt) { xmlParserInputPtr in = ctxt->input; xmlParserInputBufferPtr buf = in->buf; ptrdiff_t curEnd = in->end - in->cur; ptrdiff_t curBase = in->cur - in->base; int ret;
if (buf == NULL) return(0); /* Don't grow push parser buffer. */ if ((ctxt->progressive) && (ctxt->inputNr <= 1)) return(0); /* Don't grow memory buffers. */ if ((buf->encoder == NULL) && (buf->readcallback == NULL)) return(0); if (buf->error != 0) return(-1);
if (((curEnd > XML_MAX_LOOKUP_LIMIT) || (curBase > XML_MAX_LOOKUP_LIMIT)) && ((ctxt->options & XML_PARSE_HUGE) == 0)) { xmlErrMemory(ctxt, "Huge input lookup"); xmlHaltParser(ctxt); return(-1); }
if (curEnd >= INPUT_CHUNK) return(0);
ret = xmlParserInputBufferGrow(buf, INPUT_CHUNK); xmlBufUpdateInput(buf->buffer, in, curBase);
if (ret < 0) { xmlFatalErr(ctxt, buf->error, NULL); /* Buffer contents may be lost in case of memory errors. */ if (buf->error == XML_ERR_NO_MEMORY) xmlHaltParser(ctxt); }
return(ret);}
/** * xmlParserInputGrow: * @in: an XML parser input * @len: an indicative size for the lookahead * * DEPRECATED: Don't use. * * This function increase the input for the parser. It tries to * preserve pointers to the input buffer, and keep already read data * * Returns the amount of char read, or -1 in case of error, 0 indicate the * end of this entity */intxmlParserInputGrow(xmlParserInputPtr in, int len) { int ret; size_t indx;
if ((in == NULL) || (len < 0)) return(-1); if (in->buf == NULL) return(-1); if (in->base == NULL) return(-1); if (in->cur == NULL) return(-1); if (in->buf->buffer == NULL) return(-1);
/* Don't grow memory buffers. */ if ((in->buf->encoder == NULL) && (in->buf->readcallback == NULL)) return(0);
indx = in->cur - in->base; if (xmlBufUse(in->buf->buffer) > (unsigned int) indx + INPUT_CHUNK) { return(0); } ret = xmlParserInputBufferGrow(in->buf, len);
in->base = xmlBufContent(in->buf->buffer); if (in->base == NULL) { in->base = BAD_CAST ""; in->cur = in->base; in->end = in->base; return(-1); } in->cur = in->base + indx; in->end = xmlBufEnd(in->buf->buffer);
return(ret);}
/** * xmlParserShrink: * @ctxt: an XML parser context * * Shrink the input buffer. */voidxmlParserShrink(xmlParserCtxtPtr ctxt) { xmlParserInputPtr in = ctxt->input; xmlParserInputBufferPtr buf = in->buf; size_t used;
if (buf == NULL) return; /* Don't shrink pull parser memory buffers. */ if (((ctxt->progressive == 0) || (ctxt->inputNr > 1)) && (buf->encoder == NULL) && (buf->readcallback == NULL)) return;
used = in->cur - in->base; /* * Do not shrink on large buffers whose only a tiny fraction * was consumed */ if (used > INPUT_CHUNK) { size_t res = xmlBufShrink(buf->buffer, used - LINE_LEN);
if (res > 0) { used -= res; if ((res > ULONG_MAX) || (in->consumed > ULONG_MAX - (unsigned long)res)) in->consumed = ULONG_MAX; else in->consumed += res; } }
xmlBufUpdateInput(buf->buffer, in, used);}
/** * xmlParserInputShrink: * @in: an XML parser input * * DEPRECATED: Don't use. * * This function removes used input for the parser. */voidxmlParserInputShrink(xmlParserInputPtr in) { size_t used; size_t ret;
if (in == NULL) return; if (in->buf == NULL) return; if (in->base == NULL) return; if (in->cur == NULL) return; if (in->buf->buffer == NULL) return;
used = in->cur - in->base; /* * Do not shrink on large buffers whose only a tiny fraction * was consumed */ if (used > INPUT_CHUNK) { ret = xmlBufShrink(in->buf->buffer, used - LINE_LEN); if (ret > 0) { used -= ret; if ((ret > ULONG_MAX) || (in->consumed > ULONG_MAX - (unsigned long)ret)) in->consumed = ULONG_MAX; else in->consumed += ret; } }
if (xmlBufUse(in->buf->buffer) <= INPUT_CHUNK) { xmlParserInputBufferRead(in->buf, 2 * INPUT_CHUNK); }
in->base = xmlBufContent(in->buf->buffer); if (in->base == NULL) { /* TODO: raise error */ in->base = BAD_CAST ""; in->cur = in->base; in->end = in->base; return; } in->cur = in->base + used; in->end = xmlBufEnd(in->buf->buffer);}
/************************************************************************ * * * UTF8 character input and related functions * * * ************************************************************************/
/** * xmlNextChar: * @ctxt: the XML parser context * * DEPRECATED: Internal function, do not use. * * Skip to the next char input char. */
voidxmlNextChar(xmlParserCtxtPtr ctxt){ const unsigned char *cur; size_t avail; int c;
if ((ctxt == NULL) || (ctxt->instate == XML_PARSER_EOF) || (ctxt->input == NULL)) return;
avail = ctxt->input->end - ctxt->input->cur;
if (avail < INPUT_CHUNK) { xmlParserGrow(ctxt); if ((ctxt->instate == XML_PARSER_EOF) || (ctxt->input->cur >= ctxt->input->end)) return; avail = ctxt->input->end - ctxt->input->cur; }
cur = ctxt->input->cur; c = *cur;
if (c < 0x80) { if (c == '\n') { ctxt->input->cur++; ctxt->input->line++; ctxt->input->col = 1; } else if (c == '\r') { /* * 2.11 End-of-Line Handling * the literal two-character sequence "#xD#xA" or a standalone * literal #xD, an XML processor must pass to the application * the single character #xA. */ ctxt->input->cur += ((cur[1] == '\n') ? 2 : 1); ctxt->input->line++; ctxt->input->col = 1; return; } else { ctxt->input->cur++; ctxt->input->col++; } } else { ctxt->input->col++;
if ((avail < 2) || (cur[1] & 0xc0) != 0x80) goto encoding_error;
if (c < 0xe0) { /* 2-byte code */ if (c < 0xc2) goto encoding_error; ctxt->input->cur += 2; } else { unsigned int val = (c << 8) | cur[1];
if ((avail < 3) || (cur[2] & 0xc0) != 0x80) goto encoding_error;
if (c < 0xf0) { /* 3-byte code */ if ((val < 0xe0a0) || ((val >= 0xeda0) && (val < 0xee00))) goto encoding_error; ctxt->input->cur += 3; } else { if ((avail < 4) || ((cur[3] & 0xc0) != 0x80)) goto encoding_error;
/* 4-byte code */ if ((val < 0xf090) || (val >= 0xf490)) goto encoding_error; ctxt->input->cur += 4; } } }
return;
encoding_error: /* Only report the first error */ if ((ctxt->input->flags & XML_INPUT_ENCODING_ERROR) == 0) { if ((ctxt == NULL) || (ctxt->input == NULL) || (ctxt->input->end - ctxt->input->cur < 4)) { __xmlErrEncoding(ctxt, XML_ERR_INVALID_CHAR, "Input is not proper UTF-8, indicate encoding !\n", NULL, NULL); } else { char buffer[150];
snprintf(buffer, 149, "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n", ctxt->input->cur[0], ctxt->input->cur[1], ctxt->input->cur[2], ctxt->input->cur[3]); __xmlErrEncoding(ctxt, XML_ERR_INVALID_CHAR, "Input is not proper UTF-8, indicate encoding !\n%s", BAD_CAST buffer, NULL); } ctxt->input->flags |= XML_INPUT_ENCODING_ERROR; } ctxt->input->cur++; return;}
/** * xmlCurrentChar: * @ctxt: the XML parser context * @len: pointer to the length of the char read * * DEPRECATED: Internal function, do not use. * * The current char value, if using UTF-8 this may actually span multiple * bytes in the input buffer. Implement the end of line normalization: * 2.11 End-of-Line Handling * Wherever an external parsed entity or the literal entity value * of an internal parsed entity contains either the literal two-character * sequence "#xD#xA" or a standalone literal #xD, an XML processor * must pass to the application the single character #xA. * This behavior can conveniently be produced by normalizing all * line breaks to #xA on input, before parsing.) * * Returns the current char value and its length */
intxmlCurrentChar(xmlParserCtxtPtr ctxt, int *len) { const unsigned char *cur; size_t avail; int c;
if ((ctxt == NULL) || (len == NULL) || (ctxt->input == NULL)) return(0); if (ctxt->instate == XML_PARSER_EOF) return(0);
avail = ctxt->input->end - ctxt->input->cur;
if (avail < INPUT_CHUNK) { xmlParserGrow(ctxt); if (ctxt->instate == XML_PARSER_EOF) return(0); avail = ctxt->input->end - ctxt->input->cur; }
cur = ctxt->input->cur; c = *cur;
if (c < 0x80) { /* 1-byte code */ if (c < 0x20) { /* * 2.11 End-of-Line Handling * the literal two-character sequence "#xD#xA" or a standalone * literal #xD, an XML processor must pass to the application * the single character #xA. */ if (c == '\r') { /* * TODO: This function shouldn't change the 'cur' pointer * as side effect, but the NEXTL macro in parser.c relies * on this behavior when incrementing line numbers. */ if (cur[1] == '\n') ctxt->input->cur++; *len = 1; c = '\n'; } else if (c == 0) { if (ctxt->input->cur >= ctxt->input->end) { *len = 0; } else { *len = 1; /* * TODO: Null bytes should be handled by callers, * but this can be tricky. */ xmlErrEncodingInt(ctxt, XML_ERR_INVALID_CHAR, "Char 0x0 out of allowed range\n", c); } } else { *len = 1; } } else { *len = 1; }
return(c); } else { int val;
if (avail < 2) goto incomplete_sequence; if ((cur[1] & 0xc0) != 0x80) goto encoding_error;
if (c < 0xe0) { /* 2-byte code */ if (c < 0xc2) goto encoding_error; val = (c & 0x1f) << 6; val |= cur[1] & 0x3f; *len = 2; } else { if (avail < 3) goto incomplete_sequence; if ((cur[2] & 0xc0) != 0x80) goto encoding_error;
if (c < 0xf0) { /* 3-byte code */ val = (c & 0xf) << 12; val |= (cur[1] & 0x3f) << 6; val |= cur[2] & 0x3f; if ((val < 0x800) || ((val >= 0xd800) && (val < 0xe000))) goto encoding_error; *len = 3; } else { if (avail < 4) goto incomplete_sequence; if ((cur[3] & 0xc0) != 0x80) goto encoding_error;
/* 4-byte code */ val = (c & 0x0f) << 18; val |= (cur[1] & 0x3f) << 12; val |= (cur[2] & 0x3f) << 6; val |= cur[3] & 0x3f; if ((val < 0x10000) || (val >= 0x110000)) goto encoding_error; *len = 4; } }
return(val); }
encoding_error: /* Only report the first error */ if ((ctxt->input->flags & XML_INPUT_ENCODING_ERROR) == 0) { if (ctxt->input->end - ctxt->input->cur < 4) { __xmlErrEncoding(ctxt, XML_ERR_INVALID_CHAR, "Input is not proper UTF-8, indicate encoding !\n", NULL, NULL); } else { char buffer[150];
snprintf(&buffer[0], 149, "Bytes: 0x%02X 0x%02X 0x%02X 0x%02X\n", ctxt->input->cur[0], ctxt->input->cur[1], ctxt->input->cur[2], ctxt->input->cur[3]); __xmlErrEncoding(ctxt, XML_ERR_INVALID_CHAR, "Input is not proper UTF-8, indicate encoding !\n%s", BAD_CAST buffer, NULL); } ctxt->input->flags |= XML_INPUT_ENCODING_ERROR; } *len = 1; return(0xFFFD); /* U+FFFD Replacement Character */
incomplete_sequence: /* * An encoding problem may arise from a truncated input buffer * splitting a character in the middle. In that case do not raise * an error but return 0. This should only happen when push parsing * char data. */ *len = 0; return(0);}
/** * xmlStringCurrentChar: * @ctxt: the XML parser context * @cur: pointer to the beginning of the char * @len: pointer to the length of the char read * * DEPRECATED: Internal function, do not use. * * The current char value, if using UTF-8 this may actually span multiple * bytes in the input buffer. * * Returns the current char value and its length */
intxmlStringCurrentChar(xmlParserCtxtPtr ctxt ATTRIBUTE_UNUSED, const xmlChar *cur, int *len) { int c;
if ((cur == NULL) || (len == NULL)) return(0);
/* cur is zero-terminated, so we can lie about its length. */ *len = 4; c = xmlGetUTF8Char(cur, len);
return((c < 0) ? 0 : c);}
/** * xmlCopyCharMultiByte: * @out: pointer to an array of xmlChar * @val: the char value * * append the char value in the array * * Returns the number of xmlChar written */intxmlCopyCharMultiByte(xmlChar *out, int val) { if ((out == NULL) || (val < 0)) return(0); /* * We are supposed to handle UTF8, check it's valid * From rfc2044: encoding of the Unicode values on UTF-8: * * UCS-4 range (hex.) UTF-8 octet sequence (binary) * 0000 0000-0000 007F 0xxxxxxx * 0000 0080-0000 07FF 110xxxxx 10xxxxxx * 0000 0800-0000 FFFF 1110xxxx 10xxxxxx 10xxxxxx */ if (val >= 0x80) { xmlChar *savedout = out; int bits; if (val < 0x800) { *out++= (val >> 6) | 0xC0; bits= 0; } else if (val < 0x10000) { *out++= (val >> 12) | 0xE0; bits= 6;} else if (val < 0x110000) { *out++= (val >> 18) | 0xF0; bits= 12; } else { xmlErrEncodingInt(NULL, XML_ERR_INVALID_CHAR, "Internal error, xmlCopyCharMultiByte 0x%X out of bound\n", val); return(0); } for ( ; bits >= 0; bits-= 6) *out++= ((val >> bits) & 0x3F) | 0x80 ; return (out - savedout); } *out = val; return 1;}
/** * xmlCopyChar: * @len: Ignored, compatibility * @out: pointer to an array of xmlChar * @val: the char value * * append the char value in the array * * Returns the number of xmlChar written */
intxmlCopyChar(int len ATTRIBUTE_UNUSED, xmlChar *out, int val) { if ((out == NULL) || (val < 0)) return(0); /* the len parameter is ignored */ if (val >= 0x80) { return(xmlCopyCharMultiByte (out, val)); } *out = val; return 1;}
/************************************************************************ * * * Commodity functions to switch encodings * * * ************************************************************************/
static xmlCharEncodingHandlerPtrxmlDetectEBCDIC(xmlParserInputPtr input) { xmlChar out[200]; xmlCharEncodingHandlerPtr handler; int inlen, outlen, res, i;
/* * To detect the EBCDIC code page, we convert the first 200 bytes * to EBCDIC-US and try to find the encoding declaration. */ handler = xmlGetCharEncodingHandler(XML_CHAR_ENCODING_EBCDIC); if (handler == NULL) return(NULL); outlen = sizeof(out) - 1; inlen = input->end - input->cur; res = xmlEncInputChunk(handler, out, &outlen, input->cur, &inlen); if (res < 0) return(handler); out[outlen] = 0;
for (i = 0; i < outlen; i++) { if (out[i] == '>') break; if ((out[i] == 'e') && (xmlStrncmp(out + i, BAD_CAST "encoding", 8) == 0)) { int start, cur, quote;
i += 8; while (IS_BLANK_CH(out[i])) i += 1; if (out[i++] != '=') break; while (IS_BLANK_CH(out[i])) i += 1; quote = out[i++]; if ((quote != '\'') && (quote != '"')) break; start = i; cur = out[i]; while (((cur >= 'a') && (cur <= 'z')) || ((cur >= 'A') && (cur <= 'Z')) || ((cur >= '0') && (cur <= '9')) || (cur == '.') || (cur == '_') || (cur == '-')) cur = out[++i]; if (cur != quote) break; out[i] = 0; xmlCharEncCloseFunc(handler); return(xmlFindCharEncodingHandler((char *) out + start)); } }
/* * ICU handlers are stateful, so we have to recreate them. */ xmlCharEncCloseFunc(handler); return(xmlGetCharEncodingHandler(XML_CHAR_ENCODING_EBCDIC));}
/** * xmlSwitchEncoding: * @ctxt: the parser context * @enc: the encoding value (number) * * Use encoding specified by enum to decode input data. * * This function can be used to enforce the encoding of chunks passed * to xmlParseChunk. * * Returns 0 in case of success, -1 otherwise */intxmlSwitchEncoding(xmlParserCtxtPtr ctxt, xmlCharEncoding enc){ xmlCharEncodingHandlerPtr handler = NULL; int check = 1; int ret;
if ((ctxt == NULL) || (ctxt->input == NULL)) return(-1);
switch (enc) { case XML_CHAR_ENCODING_NONE: case XML_CHAR_ENCODING_UTF8: case XML_CHAR_ENCODING_ASCII: check = 0; break; case XML_CHAR_ENCODING_EBCDIC: handler = xmlDetectEBCDIC(ctxt->input); break; default: handler = xmlGetCharEncodingHandler(enc); break; }
if ((check) && (handler == NULL)) { const char *name = xmlGetCharEncodingName(enc);
__xmlErrEncoding(ctxt, XML_ERR_UNSUPPORTED_ENCODING, "encoding not supported: %s\n", BAD_CAST (name ? name : "<null>"), NULL); /* * TODO: We could recover from errors in external entities * if we didn't stop the parser. But most callers of this * function don't check the return value. */ xmlStopParser(ctxt); return(-1); }
ret = xmlSwitchInputEncoding(ctxt, ctxt->input, handler);
if ((ret >= 0) && (enc == XML_CHAR_ENCODING_NONE)) { ctxt->input->flags &= ~XML_INPUT_HAS_ENCODING; }
return(ret);}
/** * xmlSwitchInputEncoding: * @ctxt: the parser context * @input: the input stream * @handler: the encoding handler * * DEPRECATED: Internal function, don't use. * * Use encoding handler to decode input data. * * Returns 0 in case of success, -1 otherwise */intxmlSwitchInputEncoding(xmlParserCtxtPtr ctxt, xmlParserInputPtr input, xmlCharEncodingHandlerPtr handler){ int nbchars; xmlParserInputBufferPtr in;
if ((input == NULL) || (input->buf == NULL)) { xmlCharEncCloseFunc(handler); return (-1); } in = input->buf;
input->flags |= XML_INPUT_HAS_ENCODING;
/* * UTF-8 requires no encoding handler. */ if ((handler != NULL) && (xmlStrcasecmp(BAD_CAST handler->name, BAD_CAST "UTF-8") == 0)) { xmlCharEncCloseFunc(handler); handler = NULL; }
if (in->encoder == handler) return (0);
if (in->encoder != NULL) { /* * Switching encodings during parsing is a really bad idea, * but Chromium can switch between ISO-8859-1 and UTF-16 before * separate calls to xmlParseChunk. * * TODO: We should check whether the "raw" input buffer is empty and * convert the old content using the old encoder. */
xmlCharEncCloseFunc(in->encoder); in->encoder = handler; return (0); }
in->encoder = handler;
/* * Is there already some content down the pipe to convert ? */ if (xmlBufIsEmpty(in->buffer) == 0) { size_t processed;
/* * Shrink the current input buffer. * Move it as the raw buffer and create a new input buffer */ processed = input->cur - input->base; xmlBufShrink(in->buffer, processed); input->consumed += processed; in->raw = in->buffer; in->buffer = xmlBufCreate(); in->rawconsumed = processed;
nbchars = xmlCharEncInput(in); xmlBufResetInput(in->buffer, input); if (nbchars < 0) { /* TODO: This could be an out of memory or an encoding error. */ xmlErrInternal(ctxt, "switching encoding: encoder error\n", NULL); xmlHaltParser(ctxt); return (-1); } } return (0);}
/** * xmlSwitchToEncoding: * @ctxt: the parser context * @handler: the encoding handler * * Use encoding handler to decode input data. * * This function can be used to enforce the encoding of chunks passed * to xmlParseChunk. * * Returns 0 in case of success, -1 otherwise */intxmlSwitchToEncoding(xmlParserCtxtPtr ctxt, xmlCharEncodingHandlerPtr handler){ if (ctxt == NULL) return(-1); return(xmlSwitchInputEncoding(ctxt, ctxt->input, handler));}
/** * xmlDetectEncoding: * @ctxt: the parser context * * Handle optional BOM, detect and switch to encoding. * * Assumes that there are at least four bytes in the input buffer. */voidxmlDetectEncoding(xmlParserCtxtPtr ctxt) { const xmlChar *in; xmlCharEncoding enc; int bomSize; int autoFlag = 0;
if (xmlParserGrow(ctxt) < 0) return; in = ctxt->input->cur; if (ctxt->input->end - in < 4) return;
if (ctxt->input->flags & XML_INPUT_HAS_ENCODING) { /* * If the encoding was already set, only skip the BOM which was * possibly decoded to UTF-8. */ if ((in[0] == 0xEF) && (in[1] == 0xBB) && (in[2] == 0xBF)) { ctxt->input->cur += 3; }
return; }
enc = XML_CHAR_ENCODING_NONE; bomSize = 0;
switch (in[0]) { case 0x00: if ((in[1] == 0x00) && (in[2] == 0x00) && (in[3] == 0x3C)) { enc = XML_CHAR_ENCODING_UCS4BE; autoFlag = XML_INPUT_AUTO_OTHER; } else if ((in[1] == 0x3C) && (in[2] == 0x00) && (in[3] == 0x3F)) { enc = XML_CHAR_ENCODING_UTF16BE; autoFlag = XML_INPUT_AUTO_UTF16BE; } break;
case 0x3C: if (in[1] == 0x00) { if ((in[2] == 0x00) && (in[3] == 0x00)) { enc = XML_CHAR_ENCODING_UCS4LE; autoFlag = XML_INPUT_AUTO_OTHER; } else if ((in[2] == 0x3F) && (in[3] == 0x00)) { enc = XML_CHAR_ENCODING_UTF16LE; autoFlag = XML_INPUT_AUTO_UTF16LE; } } break;
case 0x4C: if ((in[1] == 0x6F) && (in[2] == 0xA7) && (in[3] == 0x94)) { enc = XML_CHAR_ENCODING_EBCDIC; autoFlag = XML_INPUT_AUTO_OTHER; } break;
case 0xEF: if ((in[1] == 0xBB) && (in[2] == 0xBF)) { enc = XML_CHAR_ENCODING_UTF8; autoFlag = XML_INPUT_AUTO_UTF8; bomSize = 3; } break;
case 0xFE: if (in[1] == 0xFF) { enc = XML_CHAR_ENCODING_UTF16BE; autoFlag = XML_INPUT_AUTO_UTF16BE; bomSize = 2; } break;
case 0xFF: if (in[1] == 0xFE) { enc = XML_CHAR_ENCODING_UTF16LE; autoFlag = XML_INPUT_AUTO_UTF16LE; bomSize = 2; } break; }
if (bomSize > 0) { ctxt->input->cur += bomSize; }
if (enc != XML_CHAR_ENCODING_NONE) { ctxt->input->flags |= autoFlag; xmlSwitchEncoding(ctxt, enc); }}
/** * xmlSetDeclaredEncoding: * @ctxt: the parser context * @encoding: declared encoding * * Set the encoding from a declaration in the document. * * If no encoding was set yet, switch the encoding. Otherwise, only warn * about encoding mismatches. * * Takes ownership of 'encoding'. */voidxmlSetDeclaredEncoding(xmlParserCtxtPtr ctxt, xmlChar *encoding) { if (ctxt->encoding != NULL) xmlFree((xmlChar *) ctxt->encoding); ctxt->encoding = encoding;
if (((ctxt->input->flags & XML_INPUT_HAS_ENCODING) == 0) && ((ctxt->options & XML_PARSE_IGNORE_ENC) == 0)) { xmlCharEncodingHandlerPtr handler;
handler = xmlFindCharEncodingHandler((const char *) encoding); if (handler == NULL) { __xmlErrEncoding(ctxt, XML_ERR_UNSUPPORTED_ENCODING, "Unsupported encoding: %s\n", encoding, NULL); return; }
xmlSwitchToEncoding(ctxt, handler); ctxt->input->flags |= XML_INPUT_USES_ENC_DECL; } else if (ctxt->input->flags & XML_INPUT_AUTO_ENCODING) { static const char *allowedUTF8[] = { "UTF-8", "UTF8", NULL }; static const char *allowedUTF16LE[] = { "UTF-16", "UTF-16LE", "UTF16", NULL }; static const char *allowedUTF16BE[] = { "UTF-16", "UTF-16BE", "UTF16", NULL }; const char **allowed = NULL; const char *autoEnc = NULL;
switch (ctxt->input->flags & XML_INPUT_AUTO_ENCODING) { case XML_INPUT_AUTO_UTF8: allowed = allowedUTF8; autoEnc = "UTF-8"; break; case XML_INPUT_AUTO_UTF16LE: allowed = allowedUTF16LE; autoEnc = "UTF-16LE"; break; case XML_INPUT_AUTO_UTF16BE: allowed = allowedUTF16BE; autoEnc = "UTF-16BE"; break; }
if (allowed != NULL) { const char **p; int match = 0;
for (p = allowed; *p != NULL; p++) { if (xmlStrcasecmp(encoding, BAD_CAST *p) == 0) { match = 1; break; } }
if (match == 0) { xmlWarningMsg(ctxt, XML_WAR_ENCODING_MISMATCH, "Encoding '%s' doesn't match " "auto-detected '%s'\n", encoding, BAD_CAST autoEnc); } } }}
/** * xmlGetActualEncoding: * @ctxt: the parser context * * Returns the actual used to parse the document. This can differ from * the declared encoding. */const xmlChar *xmlGetActualEncoding(xmlParserCtxtPtr ctxt) { const xmlChar *encoding = NULL;
if ((ctxt->input->flags & XML_INPUT_USES_ENC_DECL) || (ctxt->input->flags & XML_INPUT_AUTO_ENCODING)) { /* Preserve encoding exactly */ encoding = ctxt->encoding; } else if ((ctxt->input->buf) && (ctxt->input->buf->encoder)) { encoding = BAD_CAST ctxt->input->buf->encoder->name; } else if (ctxt->input->flags & XML_INPUT_HAS_ENCODING) { encoding = BAD_CAST "UTF-8"; }
return(encoding);}
/************************************************************************ * * * Commodity functions to handle entities processing * * * ************************************************************************/
/** * xmlFreeInputStream: * @input: an xmlParserInputPtr * * Free up an input stream. */voidxmlFreeInputStream(xmlParserInputPtr input) { if (input == NULL) return;
if (input->filename != NULL) xmlFree((char *) input->filename); if (input->directory != NULL) xmlFree((char *) input->directory); if (input->version != NULL) xmlFree((char *) input->version); if ((input->free != NULL) && (input->base != NULL)) input->free((xmlChar *) input->base); if (input->buf != NULL) xmlFreeParserInputBuffer(input->buf); xmlFree(input);}
/** * xmlNewInputStream: * @ctxt: an XML parser context * * Create a new input stream structure. * * Returns the new input stream or NULL */xmlParserInputPtrxmlNewInputStream(xmlParserCtxtPtr ctxt) { xmlParserInputPtr input;
input = (xmlParserInputPtr) xmlMalloc(sizeof(xmlParserInput)); if (input == NULL) { xmlErrMemory(ctxt, "couldn't allocate a new input stream\n"); return(NULL); } memset(input, 0, sizeof(xmlParserInput)); input->line = 1; input->col = 1;
/* * If the context is NULL the id cannot be initialized, but that * should not happen while parsing which is the situation where * the id is actually needed. */ if (ctxt != NULL) { if (input->id >= INT_MAX) { xmlErrMemory(ctxt, "Input ID overflow\n"); return(NULL); } input->id = ctxt->input_id++; }
return(input);}
/** * xmlNewIOInputStream: * @ctxt: an XML parser context * @input: an I/O Input * @enc: the charset encoding if known * * Create a new input stream structure encapsulating the @input into * a stream suitable for the parser. * * Returns the new input stream or NULL */xmlParserInputPtrxmlNewIOInputStream(xmlParserCtxtPtr ctxt, xmlParserInputBufferPtr input, xmlCharEncoding enc) { xmlParserInputPtr inputStream;
if (input == NULL) return(NULL); if (xmlParserDebugEntities) xmlGenericError(xmlGenericErrorContext, "new input from I/O\n"); inputStream = xmlNewInputStream(ctxt); if (inputStream == NULL) { return(NULL); } inputStream->filename = NULL; inputStream->buf = input; xmlBufResetInput(inputStream->buf->buffer, inputStream);
if (enc != XML_CHAR_ENCODING_NONE) { xmlSwitchEncoding(ctxt, enc); }
return(inputStream);}
/** * xmlNewEntityInputStream: * @ctxt: an XML parser context * @entity: an Entity pointer * * DEPRECATED: Internal function, do not use. * * Create a new input stream based on an xmlEntityPtr * * Returns the new input stream or NULL */xmlParserInputPtrxmlNewEntityInputStream(xmlParserCtxtPtr ctxt, xmlEntityPtr entity) { xmlParserInputPtr input;
if (entity == NULL) { xmlErrInternal(ctxt, "xmlNewEntityInputStream entity = NULL\n", NULL); return(NULL); } if (xmlParserDebugEntities) xmlGenericError(xmlGenericErrorContext, "new input from entity: %s\n", entity->name); if (entity->content == NULL) { switch (entity->etype) { case XML_EXTERNAL_GENERAL_UNPARSED_ENTITY: xmlErrInternal(ctxt, "Cannot parse entity %s\n", entity->name); break; case XML_EXTERNAL_GENERAL_PARSED_ENTITY: case XML_EXTERNAL_PARAMETER_ENTITY: input = xmlLoadExternalEntity((char *) entity->URI, (char *) entity->ExternalID, ctxt); if (input != NULL) input->entity = entity; return(input); case XML_INTERNAL_GENERAL_ENTITY: xmlErrInternal(ctxt, "Internal entity %s without content !\n", entity->name); break; case XML_INTERNAL_PARAMETER_ENTITY: xmlErrInternal(ctxt, "Internal parameter entity %s without content !\n", entity->name); break; case XML_INTERNAL_PREDEFINED_ENTITY: xmlErrInternal(ctxt, "Predefined entity %s without content !\n", entity->name); break; } return(NULL); } input = xmlNewInputStream(ctxt); if (input == NULL) { return(NULL); } if (entity->URI != NULL) input->filename = (char *) xmlStrdup((xmlChar *) entity->URI); input->base = entity->content; if (entity->length == 0) entity->length = xmlStrlen(entity->content); input->cur = entity->content; input->length = entity->length; input->end = &entity->content[input->length]; input->entity = entity; return(input);}
/** * xmlNewStringInputStream: * @ctxt: an XML parser context * @buffer: an memory buffer * * Create a new input stream based on a memory buffer. * Returns the new input stream */xmlParserInputPtrxmlNewStringInputStream(xmlParserCtxtPtr ctxt, const xmlChar *buffer) { xmlParserInputPtr input; xmlParserInputBufferPtr buf;
if (buffer == NULL) { xmlErrInternal(ctxt, "xmlNewStringInputStream string = NULL\n", NULL); return(NULL); } if (xmlParserDebugEntities) xmlGenericError(xmlGenericErrorContext, "new fixed input: %.30s\n", buffer); buf = xmlParserInputBufferCreateString(buffer); if (buf == NULL) { xmlErrMemory(ctxt, NULL); return(NULL); } input = xmlNewInputStream(ctxt); if (input == NULL) { xmlErrMemory(ctxt, "couldn't allocate a new input stream\n"); xmlFreeParserInputBuffer(buf); return(NULL); } input->buf = buf; xmlBufResetInput(input->buf->buffer, input); return(input);}
/** * xmlNewInputFromFile: * @ctxt: an XML parser context * @filename: the filename to use as entity * * Create a new input stream based on a file or an URL. * * Returns the new input stream or NULL in case of error */xmlParserInputPtrxmlNewInputFromFile(xmlParserCtxtPtr ctxt, const char *filename) { xmlParserInputBufferPtr buf; xmlParserInputPtr inputStream; char *directory = NULL; xmlChar *URI = NULL;
if (xmlParserDebugEntities) xmlGenericError(xmlGenericErrorContext, "new input from file: %s\n", filename); if (ctxt == NULL) return(NULL); buf = xmlParserInputBufferCreateFilename(filename, XML_CHAR_ENCODING_NONE); if (buf == NULL) { if (filename == NULL) __xmlLoaderErr(ctxt, "failed to load external entity: NULL filename \n", NULL); else __xmlLoaderErr(ctxt, "failed to load external entity \"%s\"\n", (const char *) filename); return(NULL); }
inputStream = xmlNewInputStream(ctxt); if (inputStream == NULL) { xmlFreeParserInputBuffer(buf); return(NULL); }
inputStream->buf = buf; inputStream = xmlCheckHTTPInput(ctxt, inputStream); if (inputStream == NULL) return(NULL);
if (inputStream->filename == NULL) URI = xmlStrdup((xmlChar *) filename); else URI = xmlStrdup((xmlChar *) inputStream->filename); directory = xmlParserGetDirectory((const char *) URI); if (inputStream->filename != NULL) xmlFree((char *)inputStream->filename); inputStream->filename = (char *) xmlCanonicPath((const xmlChar *) URI); if (URI != NULL) xmlFree((char *) URI); inputStream->directory = directory;
xmlBufResetInput(inputStream->buf->buffer, inputStream); if ((ctxt->directory == NULL) && (directory != NULL)) ctxt->directory = (char *) xmlStrdup((const xmlChar *) directory); return(inputStream);}
/************************************************************************ * * * Commodity functions to handle parser contexts * * * ************************************************************************/
/** * xmlInitSAXParserCtxt: * @ctxt: XML parser context * @sax: SAX handlert * @userData: user data * * Initialize a SAX parser context * * Returns 0 in case of success and -1 in case of error */
static intxmlInitSAXParserCtxt(xmlParserCtxtPtr ctxt, const xmlSAXHandler *sax, void *userData){ xmlParserInputPtr input;
if(ctxt==NULL) { xmlErrInternal(NULL, "Got NULL parser context\n", NULL); return(-1); }
xmlInitParser();
if (ctxt->dict == NULL) ctxt->dict = xmlDictCreate(); if (ctxt->dict == NULL) { xmlErrMemory(NULL, "cannot initialize parser context\n"); return(-1); } xmlDictSetLimit(ctxt->dict, XML_MAX_DICTIONARY_LIMIT);
if (ctxt->sax == NULL) ctxt->sax = (xmlSAXHandler *) xmlMalloc(sizeof(xmlSAXHandler)); if (ctxt->sax == NULL) { xmlErrMemory(NULL, "cannot initialize parser context\n"); return(-1); } if (sax == NULL) { memset(ctxt->sax, 0, sizeof(xmlSAXHandler)); xmlSAXVersion(ctxt->sax, 2); ctxt->userData = ctxt; } else { if (sax->initialized == XML_SAX2_MAGIC) { memcpy(ctxt->sax, sax, sizeof(xmlSAXHandler)); } else { memset(ctxt->sax, 0, sizeof(xmlSAXHandler)); memcpy(ctxt->sax, sax, sizeof(xmlSAXHandlerV1)); } ctxt->userData = userData ? userData : ctxt; }
ctxt->maxatts = 0; ctxt->atts = NULL; /* Allocate the Input stack */ if (ctxt->inputTab == NULL) { ctxt->inputTab = (xmlParserInputPtr *) xmlMalloc(5 * sizeof(xmlParserInputPtr)); ctxt->inputMax = 5; } if (ctxt->inputTab == NULL) { xmlErrMemory(NULL, "cannot initialize parser context\n"); ctxt->inputNr = 0; ctxt->inputMax = 0; ctxt->input = NULL; return(-1); } while ((input = inputPop(ctxt)) != NULL) { /* Non consuming */ xmlFreeInputStream(input); } ctxt->inputNr = 0; ctxt->input = NULL;
ctxt->version = NULL; ctxt->encoding = NULL; ctxt->standalone = -1; ctxt->hasExternalSubset = 0; ctxt->hasPErefs = 0; ctxt->html = 0; ctxt->external = 0; ctxt->instate = XML_PARSER_START; ctxt->token = 0; ctxt->directory = NULL;
/* Allocate the Node stack */ if (ctxt->nodeTab == NULL) { ctxt->nodeTab = (xmlNodePtr *) xmlMalloc(10 * sizeof(xmlNodePtr)); ctxt->nodeMax = 10; } if (ctxt->nodeTab == NULL) { xmlErrMemory(NULL, "cannot initialize parser context\n"); ctxt->nodeNr = 0; ctxt->nodeMax = 0; ctxt->node = NULL; ctxt->inputNr = 0; ctxt->inputMax = 0; ctxt->input = NULL; return(-1); } ctxt->nodeNr = 0; ctxt->node = NULL;
/* Allocate the Name stack */ if (ctxt->nameTab == NULL) { ctxt->nameTab = (const xmlChar **) xmlMalloc(10 * sizeof(xmlChar *)); ctxt->nameMax = 10; } if (ctxt->nameTab == NULL) { xmlErrMemory(NULL, "cannot initialize parser context\n"); ctxt->nodeNr = 0; ctxt->nodeMax = 0; ctxt->node = NULL; ctxt->inputNr = 0; ctxt->inputMax = 0; ctxt->input = NULL; ctxt->nameNr = 0; ctxt->nameMax = 0; ctxt->name = NULL; return(-1); } ctxt->nameNr = 0; ctxt->name = NULL;
/* Allocate the space stack */ if (ctxt->spaceTab == NULL) { ctxt->spaceTab = (int *) xmlMalloc(10 * sizeof(int)); ctxt->spaceMax = 10; } if (ctxt->spaceTab == NULL) { xmlErrMemory(NULL, "cannot initialize parser context\n"); ctxt->nodeNr = 0; ctxt->nodeMax = 0; ctxt->node = NULL; ctxt->inputNr = 0; ctxt->inputMax = 0; ctxt->input = NULL; ctxt->nameNr = 0; ctxt->nameMax = 0; ctxt->name = NULL; ctxt->spaceNr = 0; ctxt->spaceMax = 0; ctxt->space = NULL; return(-1); } ctxt->spaceNr = 1; ctxt->spaceMax = 10; ctxt->spaceTab[0] = -1; ctxt->space = &ctxt->spaceTab[0]; ctxt->myDoc = NULL; ctxt->wellFormed = 1; ctxt->nsWellFormed = 1; ctxt->valid = 1; ctxt->loadsubset = xmlLoadExtDtdDefaultValue; if (ctxt->loadsubset) { ctxt->options |= XML_PARSE_DTDLOAD; } ctxt->validate = xmlDoValidityCheckingDefaultValue; ctxt->pedantic = xmlPedanticParserDefaultValue; if (ctxt->pedantic) { ctxt->options |= XML_PARSE_PEDANTIC; } ctxt->linenumbers = xmlLineNumbersDefaultValue; ctxt->keepBlanks = xmlKeepBlanksDefaultValue; if (ctxt->keepBlanks == 0) { ctxt->sax->ignorableWhitespace = xmlSAX2IgnorableWhitespace; ctxt->options |= XML_PARSE_NOBLANKS; }
ctxt->vctxt.flags = XML_VCTXT_USE_PCTXT; ctxt->vctxt.userData = ctxt; ctxt->vctxt.error = xmlParserValidityError; ctxt->vctxt.warning = xmlParserValidityWarning; if (ctxt->validate) { if (xmlGetWarningsDefaultValue == 0) ctxt->vctxt.warning = NULL; else ctxt->vctxt.warning = xmlParserValidityWarning; ctxt->vctxt.nodeMax = 0; ctxt->options |= XML_PARSE_DTDVALID; } ctxt->replaceEntities = xmlSubstituteEntitiesDefaultValue; if (ctxt->replaceEntities) { ctxt->options |= XML_PARSE_NOENT; } ctxt->record_info = 0; ctxt->checkIndex = 0; ctxt->inSubset = 0; ctxt->errNo = XML_ERR_OK; ctxt->depth = 0; ctxt->catalogs = NULL; ctxt->sizeentities = 0; ctxt->sizeentcopy = 0; ctxt->input_id = 1; ctxt->maxAmpl = XML_MAX_AMPLIFICATION_DEFAULT; xmlInitNodeInfoSeq(&ctxt->node_seq);
if (ctxt->nsdb == NULL) { ctxt->nsdb = xmlParserNsCreate(); if (ctxt->nsdb == NULL) { xmlErrMemory(ctxt, NULL); return(-1); } }
return(0);}
/** * xmlInitParserCtxt: * @ctxt: an XML parser context * * DEPRECATED: Internal function which will be made private in a future * version. * * Initialize a parser context * * Returns 0 in case of success and -1 in case of error */
intxmlInitParserCtxt(xmlParserCtxtPtr ctxt){ return(xmlInitSAXParserCtxt(ctxt, NULL, NULL));}
/** * xmlFreeParserCtxt: * @ctxt: an XML parser context * * Free all the memory used by a parser context. However the parsed * document in ctxt->myDoc is not freed. */
voidxmlFreeParserCtxt(xmlParserCtxtPtr ctxt){ xmlParserInputPtr input;
if (ctxt == NULL) return;
while ((input = inputPop(ctxt)) != NULL) { /* Non consuming */ xmlFreeInputStream(input); } if (ctxt->spaceTab != NULL) xmlFree(ctxt->spaceTab); if (ctxt->nameTab != NULL) xmlFree((xmlChar * *)ctxt->nameTab); if (ctxt->nodeTab != NULL) xmlFree(ctxt->nodeTab); if (ctxt->nodeInfoTab != NULL) xmlFree(ctxt->nodeInfoTab); if (ctxt->inputTab != NULL) xmlFree(ctxt->inputTab); if (ctxt->version != NULL) xmlFree((char *) ctxt->version); if (ctxt->encoding != NULL) xmlFree((char *) ctxt->encoding); if (ctxt->extSubURI != NULL) xmlFree((char *) ctxt->extSubURI); if (ctxt->extSubSystem != NULL) xmlFree((char *) ctxt->extSubSystem);#ifdef LIBXML_SAX1_ENABLED if ((ctxt->sax != NULL) && (ctxt->sax != (xmlSAXHandlerPtr) &xmlDefaultSAXHandler))#else if (ctxt->sax != NULL)#endif /* LIBXML_SAX1_ENABLED */ xmlFree(ctxt->sax); if (ctxt->directory != NULL) xmlFree((char *) ctxt->directory); if (ctxt->vctxt.nodeTab != NULL) xmlFree(ctxt->vctxt.nodeTab); if (ctxt->atts != NULL) xmlFree((xmlChar * *)ctxt->atts); if (ctxt->dict != NULL) xmlDictFree(ctxt->dict); if (ctxt->nsTab != NULL) xmlFree(ctxt->nsTab); if (ctxt->nsdb != NULL) xmlParserNsFree(ctxt->nsdb); if (ctxt->attrHash != NULL) xmlFree(ctxt->attrHash); if (ctxt->pushTab != NULL) xmlFree(ctxt->pushTab); if (ctxt->attallocs != NULL) xmlFree(ctxt->attallocs); if (ctxt->attsDefault != NULL) xmlHashFree(ctxt->attsDefault, xmlHashDefaultDeallocator); if (ctxt->attsSpecial != NULL) xmlHashFree(ctxt->attsSpecial, NULL); if (ctxt->freeElems != NULL) { xmlNodePtr cur, next;
cur = ctxt->freeElems; while (cur != NULL) { next = cur->next; xmlFree(cur); cur = next; } } if (ctxt->freeAttrs != NULL) { xmlAttrPtr cur, next;
cur = ctxt->freeAttrs; while (cur != NULL) { next = cur->next; xmlFree(cur); cur = next; } } /* * cleanup the error strings */ if (ctxt->lastError.message != NULL) xmlFree(ctxt->lastError.message); if (ctxt->lastError.file != NULL) xmlFree(ctxt->lastError.file); if (ctxt->lastError.str1 != NULL) xmlFree(ctxt->lastError.str1); if (ctxt->lastError.str2 != NULL) xmlFree(ctxt->lastError.str2); if (ctxt->lastError.str3 != NULL) xmlFree(ctxt->lastError.str3);
#ifdef LIBXML_CATALOG_ENABLED if (ctxt->catalogs != NULL) xmlCatalogFreeLocal(ctxt->catalogs);#endif xmlFree(ctxt);}
/** * xmlNewParserCtxt: * * Allocate and initialize a new parser context. * * Returns the xmlParserCtxtPtr or NULL */
xmlParserCtxtPtrxmlNewParserCtxt(void){ return(xmlNewSAXParserCtxt(NULL, NULL));}
/** * xmlNewSAXParserCtxt: * @sax: SAX handler * @userData: user data * * Allocate and initialize a new SAX parser context. If userData is NULL, * the parser context will be passed as user data. * * Returns the xmlParserCtxtPtr or NULL if memory allocation failed. */
xmlParserCtxtPtrxmlNewSAXParserCtxt(const xmlSAXHandler *sax, void *userData){ xmlParserCtxtPtr ctxt;
ctxt = (xmlParserCtxtPtr) xmlMalloc(sizeof(xmlParserCtxt)); if (ctxt == NULL) { xmlErrMemory(NULL, "cannot allocate parser context\n"); return(NULL); } memset(ctxt, 0, sizeof(xmlParserCtxt)); if (xmlInitSAXParserCtxt(ctxt, sax, userData) < 0) { xmlFreeParserCtxt(ctxt); return(NULL); } return(ctxt);}
/************************************************************************ * * * Handling of node information * * * ************************************************************************/
/** * xmlClearParserCtxt: * @ctxt: an XML parser context * * Clear (release owned resources) and reinitialize a parser context */
voidxmlClearParserCtxt(xmlParserCtxtPtr ctxt){ if (ctxt==NULL) return; xmlClearNodeInfoSeq(&ctxt->node_seq); xmlCtxtReset(ctxt);}
/** * xmlParserFindNodeInfo: * @ctx: an XML parser context * @node: an XML node within the tree * * DEPRECATED: Don't use. * * Find the parser node info struct for a given node * * Returns an xmlParserNodeInfo block pointer or NULL */const xmlParserNodeInfo *xmlParserFindNodeInfo(const xmlParserCtxtPtr ctx, const xmlNodePtr node){ unsigned long pos;
if ((ctx == NULL) || (node == NULL)) return (NULL); /* Find position where node should be at */ pos = xmlParserFindNodeInfoIndex(&ctx->node_seq, node); if (pos < ctx->node_seq.length && ctx->node_seq.buffer[pos].node == node) return &ctx->node_seq.buffer[pos]; else return NULL;}
/** * xmlInitNodeInfoSeq: * @seq: a node info sequence pointer * * DEPRECATED: Don't use. * * -- Initialize (set to initial state) node info sequence */voidxmlInitNodeInfoSeq(xmlParserNodeInfoSeqPtr seq){ if (seq == NULL) return; seq->length = 0; seq->maximum = 0; seq->buffer = NULL;}
/** * xmlClearNodeInfoSeq: * @seq: a node info sequence pointer * * DEPRECATED: Don't use. * * -- Clear (release memory and reinitialize) node * info sequence */voidxmlClearNodeInfoSeq(xmlParserNodeInfoSeqPtr seq){ if (seq == NULL) return; if (seq->buffer != NULL) xmlFree(seq->buffer); xmlInitNodeInfoSeq(seq);}
/** * xmlParserFindNodeInfoIndex: * @seq: a node info sequence pointer * @node: an XML node pointer * * DEPRECATED: Don't use. * * xmlParserFindNodeInfoIndex : Find the index that the info record for * the given node is or should be at in a sorted sequence * * Returns a long indicating the position of the record */unsigned longxmlParserFindNodeInfoIndex(const xmlParserNodeInfoSeqPtr seq, const xmlNodePtr node){ unsigned long upper, lower, middle; int found = 0;
if ((seq == NULL) || (node == NULL)) return ((unsigned long) -1);
/* Do a binary search for the key */ lower = 1; upper = seq->length; middle = 0; while (lower <= upper && !found) { middle = lower + (upper - lower) / 2; if (node == seq->buffer[middle - 1].node) found = 1; else if (node < seq->buffer[middle - 1].node) upper = middle - 1; else lower = middle + 1; }
/* Return position */ if (middle == 0 || seq->buffer[middle - 1].node < node) return middle; else return middle - 1;}
/** * xmlParserAddNodeInfo: * @ctxt: an XML parser context * @info: a node info sequence pointer * * DEPRECATED: Don't use. * * Insert node info record into the sorted sequence */voidxmlParserAddNodeInfo(xmlParserCtxtPtr ctxt, const xmlParserNodeInfoPtr info){ unsigned long pos;
if ((ctxt == NULL) || (info == NULL)) return;
/* Find pos and check to see if node is already in the sequence */ pos = xmlParserFindNodeInfoIndex(&ctxt->node_seq, (xmlNodePtr) info->node);
if ((pos < ctxt->node_seq.length) && (ctxt->node_seq.buffer != NULL) && (ctxt->node_seq.buffer[pos].node == info->node)) { ctxt->node_seq.buffer[pos] = *info; }
/* Otherwise, we need to add new node to buffer */ else { if ((ctxt->node_seq.length + 1 > ctxt->node_seq.maximum) || (ctxt->node_seq.buffer == NULL)) { xmlParserNodeInfo *tmp_buffer; unsigned int byte_size;
if (ctxt->node_seq.maximum == 0) ctxt->node_seq.maximum = 2; byte_size = (sizeof(*ctxt->node_seq.buffer) * (2 * ctxt->node_seq.maximum));
if (ctxt->node_seq.buffer == NULL) tmp_buffer = (xmlParserNodeInfo *) xmlMalloc(byte_size); else tmp_buffer = (xmlParserNodeInfo *) xmlRealloc(ctxt->node_seq.buffer, byte_size);
if (tmp_buffer == NULL) { xmlErrMemory(ctxt, "failed to allocate buffer\n"); return; } ctxt->node_seq.buffer = tmp_buffer; ctxt->node_seq.maximum *= 2; }
/* If position is not at end, move elements out of the way */ if (pos != ctxt->node_seq.length) { unsigned long i;
for (i = ctxt->node_seq.length; i > pos; i--) ctxt->node_seq.buffer[i] = ctxt->node_seq.buffer[i - 1]; }
/* Copy element and increase length */ ctxt->node_seq.buffer[pos] = *info; ctxt->node_seq.length++; }}
/************************************************************************ * * * Defaults settings * * * ************************************************************************//** * xmlPedanticParserDefault: * @val: int 0 or 1 * * DEPRECATED: Use the modern options API with XML_PARSE_PEDANTIC. * * Set and return the previous value for enabling pedantic warnings. * * Returns the last value for 0 for no substitution, 1 for substitution. */
intxmlPedanticParserDefault(int val) { int old = xmlPedanticParserDefaultValue;
xmlPedanticParserDefaultValue = val; return(old);}
/** * xmlLineNumbersDefault: * @val: int 0 or 1 * * DEPRECATED: The modern options API always enables line numbers. * * Set and return the previous value for enabling line numbers in elements * contents. This may break on old application and is turned off by default. * * Returns the last value for 0 for no substitution, 1 for substitution. */
intxmlLineNumbersDefault(int val) { int old = xmlLineNumbersDefaultValue;
xmlLineNumbersDefaultValue = val; return(old);}
/** * xmlSubstituteEntitiesDefault: * @val: int 0 or 1 * * DEPRECATED: Use the modern options API with XML_PARSE_NOENT. * * Set and return the previous value for default entity support. * Initially the parser always keep entity references instead of substituting * entity values in the output. This function has to be used to change the * default parser behavior * SAX::substituteEntities() has to be used for changing that on a file by * file basis. * * Returns the last value for 0 for no substitution, 1 for substitution. */
intxmlSubstituteEntitiesDefault(int val) { int old = xmlSubstituteEntitiesDefaultValue;
xmlSubstituteEntitiesDefaultValue = val; return(old);}
/** * xmlKeepBlanksDefault: * @val: int 0 or 1 * * DEPRECATED: Use the modern options API with XML_PARSE_NOBLANKS. * * Set and return the previous value for default blanks text nodes support. * The 1.x version of the parser used an heuristic to try to detect * ignorable white spaces. As a result the SAX callback was generating * xmlSAX2IgnorableWhitespace() callbacks instead of characters() one, and when * using the DOM output text nodes containing those blanks were not generated. * The 2.x and later version will switch to the XML standard way and * ignorableWhitespace() are only generated when running the parser in * validating mode and when the current element doesn't allow CDATA or * mixed content. * This function is provided as a way to force the standard behavior * on 1.X libs and to switch back to the old mode for compatibility when * running 1.X client code on 2.X . Upgrade of 1.X code should be done * by using xmlIsBlankNode() commodity function to detect the "empty" * nodes generated. * This value also affect autogeneration of indentation when saving code * if blanks sections are kept, indentation is not generated. * * Returns the last value for 0 for no substitution, 1 for substitution. */
intxmlKeepBlanksDefault(int val) { int old = xmlKeepBlanksDefaultValue;
xmlKeepBlanksDefaultValue = val;#ifdef LIBXML_OUTPUT_ENABLED if (!val) xmlIndentTreeOutput = 1;#endif return(old);}