12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561 |
- /**
- * uri.c: set of generic URI related routines
- *
- * Reference: RFCs 3986, 2732 and 2373
- *
- * See Copyright for the status of this software.
- *
- * daniel@veillard.com
- */
- #define IN_LIBXML
- #include "libxml.h"
- #include <limits.h>
- #include <string.h>
- #include <libxml/xmlmemory.h>
- #include <libxml/uri.h>
- #include <libxml/globals.h>
- #include <libxml/xmlerror.h>
- /**
- * MAX_URI_LENGTH:
- *
- * The definition of the URI regexp in the above RFC has no size limit
- * In practice they are usually relatively short except for the
- * data URI scheme as defined in RFC 2397. Even for data URI the usual
- * maximum size before hitting random practical limits is around 64 KB
- * and 4KB is usually a maximum admitted limit for proper operations.
- * The value below is more a security limit than anything else and
- * really should never be hit by 'normal' operations
- * Set to 1 MByte in 2012, this is only enforced on output
- */
- #define MAX_URI_LENGTH 1024 * 1024
- static void
- xmlURIErrMemory(const char *extra)
- {
- if (extra)
- __xmlRaiseError(NULL, NULL, NULL,
- NULL, NULL, XML_FROM_URI,
- 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,
- NULL, NULL, XML_FROM_URI,
- XML_ERR_NO_MEMORY, XML_ERR_FATAL, NULL, 0,
- NULL, NULL, NULL, 0, 0,
- "Memory allocation failed\n");
- }
- static void xmlCleanURI(xmlURIPtr uri);
- /*
- * Old rule from 2396 used in legacy handling code
- * alpha = lowalpha | upalpha
- */
- #define IS_ALPHA(x) (IS_LOWALPHA(x) || IS_UPALPHA(x))
- /*
- * lowalpha = "a" | "b" | "c" | "d" | "e" | "f" | "g" | "h" | "i" | "j" |
- * "k" | "l" | "m" | "n" | "o" | "p" | "q" | "r" | "s" | "t" |
- * "u" | "v" | "w" | "x" | "y" | "z"
- */
- #define IS_LOWALPHA(x) (((x) >= 'a') && ((x) <= 'z'))
- /*
- * upalpha = "A" | "B" | "C" | "D" | "E" | "F" | "G" | "H" | "I" | "J" |
- * "K" | "L" | "M" | "N" | "O" | "P" | "Q" | "R" | "S" | "T" |
- * "U" | "V" | "W" | "X" | "Y" | "Z"
- */
- #define IS_UPALPHA(x) (((x) >= 'A') && ((x) <= 'Z'))
- #ifdef IS_DIGIT
- #undef IS_DIGIT
- #endif
- /*
- * digit = "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9"
- */
- #define IS_DIGIT(x) (((x) >= '0') && ((x) <= '9'))
- /*
- * alphanum = alpha | digit
- */
- #define IS_ALPHANUM(x) (IS_ALPHA(x) || IS_DIGIT(x))
- /*
- * mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"
- */
- #define IS_MARK(x) (((x) == '-') || ((x) == '_') || ((x) == '.') || \
- ((x) == '!') || ((x) == '~') || ((x) == '*') || ((x) == '\'') || \
- ((x) == '(') || ((x) == ')'))
- /*
- * unwise = "{" | "}" | "|" | "\" | "^" | "`"
- */
- #define IS_UNWISE(p) \
- (((*(p) == '{')) || ((*(p) == '}')) || ((*(p) == '|')) || \
- ((*(p) == '\\')) || ((*(p) == '^')) || ((*(p) == '[')) || \
- ((*(p) == ']')) || ((*(p) == '`')))
- /*
- * reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | "$" | "," |
- * "[" | "]"
- */
- #define IS_RESERVED(x) (((x) == ';') || ((x) == '/') || ((x) == '?') || \
- ((x) == ':') || ((x) == '@') || ((x) == '&') || ((x) == '=') || \
- ((x) == '+') || ((x) == '$') || ((x) == ',') || ((x) == '[') || \
- ((x) == ']'))
- /*
- * unreserved = alphanum | mark
- */
- #define IS_UNRESERVED(x) (IS_ALPHANUM(x) || IS_MARK(x))
- /*
- * Skip to next pointer char, handle escaped sequences
- */
- #define NEXT(p) ((*p == '%')? p += 3 : p++)
- /*
- * Productions from the spec.
- *
- * authority = server | reg_name
- * reg_name = 1*( unreserved | escaped | "$" | "," |
- * ";" | ":" | "@" | "&" | "=" | "+" )
- *
- * path = [ abs_path | opaque_part ]
- */
- #define STRNDUP(s, n) (char *) xmlStrndup((const xmlChar *)(s), (n))
- /************************************************************************
- * *
- * RFC 3986 parser *
- * *
- ************************************************************************/
- #define ISA_DIGIT(p) ((*(p) >= '0') && (*(p) <= '9'))
- #define ISA_ALPHA(p) (((*(p) >= 'a') && (*(p) <= 'z')) || \
- ((*(p) >= 'A') && (*(p) <= 'Z')))
- #define ISA_HEXDIG(p) \
- (ISA_DIGIT(p) || ((*(p) >= 'a') && (*(p) <= 'f')) || \
- ((*(p) >= 'A') && (*(p) <= 'F')))
- /*
- * sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
- * / "*" / "+" / "," / ";" / "="
- */
- #define ISA_SUB_DELIM(p) \
- (((*(p) == '!')) || ((*(p) == '$')) || ((*(p) == '&')) || \
- ((*(p) == '(')) || ((*(p) == ')')) || ((*(p) == '*')) || \
- ((*(p) == '+')) || ((*(p) == ',')) || ((*(p) == ';')) || \
- ((*(p) == '=')) || ((*(p) == '\'')))
- /*
- * gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@"
- */
- #define ISA_GEN_DELIM(p) \
- (((*(p) == ':')) || ((*(p) == '/')) || ((*(p) == '?')) || \
- ((*(p) == '#')) || ((*(p) == '[')) || ((*(p) == ']')) || \
- ((*(p) == '@')))
- /*
- * reserved = gen-delims / sub-delims
- */
- #define ISA_RESERVED(p) (ISA_GEN_DELIM(p) || (ISA_SUB_DELIM(p)))
- /*
- * unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
- */
- #define ISA_UNRESERVED(p) \
- ((ISA_ALPHA(p)) || (ISA_DIGIT(p)) || ((*(p) == '-')) || \
- ((*(p) == '.')) || ((*(p) == '_')) || ((*(p) == '~')))
- /*
- * pct-encoded = "%" HEXDIG HEXDIG
- */
- #define ISA_PCT_ENCODED(p) \
- ((*(p) == '%') && (ISA_HEXDIG(p + 1)) && (ISA_HEXDIG(p + 2)))
- /*
- * pchar = unreserved / pct-encoded / sub-delims / ":" / "@"
- */
- #define ISA_PCHAR(p) \
- (ISA_UNRESERVED(p) || ISA_PCT_ENCODED(p) || ISA_SUB_DELIM(p) || \
- ((*(p) == ':')) || ((*(p) == '@')))
- /**
- * xmlParse3986Scheme:
- * @uri: pointer to an URI structure
- * @str: pointer to the string to analyze
- *
- * Parse an URI scheme
- *
- * ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986Scheme(xmlURIPtr uri, const char **str) {
- const char *cur;
- if (str == NULL)
- return(-1);
- cur = *str;
- if (!ISA_ALPHA(cur))
- return(2);
- cur++;
- while (ISA_ALPHA(cur) || ISA_DIGIT(cur) ||
- (*cur == '+') || (*cur == '-') || (*cur == '.')) cur++;
- if (uri != NULL) {
- if (uri->scheme != NULL) xmlFree(uri->scheme);
- uri->scheme = STRNDUP(*str, cur - *str);
- }
- *str = cur;
- return(0);
- }
- /**
- * xmlParse3986Fragment:
- * @uri: pointer to an URI structure
- * @str: pointer to the string to analyze
- *
- * Parse the query part of an URI
- *
- * fragment = *( pchar / "/" / "?" )
- * NOTE: the strict syntax as defined by 3986 does not allow '[' and ']'
- * in the fragment identifier but this is used very broadly for
- * xpointer scheme selection, so we are allowing it here to not break
- * for example all the DocBook processing chains.
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986Fragment(xmlURIPtr uri, const char **str)
- {
- const char *cur;
- if (str == NULL)
- return (-1);
- cur = *str;
- while ((ISA_PCHAR(cur)) || (*cur == '/') || (*cur == '?') ||
- (*cur == '[') || (*cur == ']') ||
- ((uri != NULL) && (uri->cleanup & 1) && (IS_UNWISE(cur))))
- NEXT(cur);
- if (uri != NULL) {
- if (uri->fragment != NULL)
- xmlFree(uri->fragment);
- if (uri->cleanup & 2)
- uri->fragment = STRNDUP(*str, cur - *str);
- else
- uri->fragment = xmlURIUnescapeString(*str, cur - *str, NULL);
- }
- *str = cur;
- return (0);
- }
- /**
- * xmlParse3986Query:
- * @uri: pointer to an URI structure
- * @str: pointer to the string to analyze
- *
- * Parse the query part of an URI
- *
- * query = *uric
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986Query(xmlURIPtr uri, const char **str)
- {
- const char *cur;
- if (str == NULL)
- return (-1);
- cur = *str;
- while ((ISA_PCHAR(cur)) || (*cur == '/') || (*cur == '?') ||
- ((uri != NULL) && (uri->cleanup & 1) && (IS_UNWISE(cur))))
- NEXT(cur);
- if (uri != NULL) {
- if (uri->query != NULL)
- xmlFree(uri->query);
- if (uri->cleanup & 2)
- uri->query = STRNDUP(*str, cur - *str);
- else
- uri->query = xmlURIUnescapeString(*str, cur - *str, NULL);
- /* Save the raw bytes of the query as well.
- * See: http://mail.gnome.org/archives/xml/2007-April/thread.html#00114
- */
- if (uri->query_raw != NULL)
- xmlFree (uri->query_raw);
- uri->query_raw = STRNDUP (*str, cur - *str);
- }
- *str = cur;
- return (0);
- }
- /**
- * xmlParse3986Port:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse a port part and fills in the appropriate fields
- * of the @uri structure
- *
- * port = *DIGIT
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986Port(xmlURIPtr uri, const char **str)
- {
- const char *cur = *str;
- int port = 0;
- if (ISA_DIGIT(cur)) {
- while (ISA_DIGIT(cur)) {
- int digit = *cur - '0';
- if (port > INT_MAX / 10)
- return(1);
- port *= 10;
- if (port > INT_MAX - digit)
- return(1);
- port += digit;
- cur++;
- }
- if (uri != NULL)
- uri->port = port;
- *str = cur;
- return(0);
- }
- return(1);
- }
- /**
- * xmlParse3986Userinfo:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an user information part and fills in the appropriate fields
- * of the @uri structure
- *
- * userinfo = *( unreserved / pct-encoded / sub-delims / ":" )
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986Userinfo(xmlURIPtr uri, const char **str)
- {
- const char *cur;
- cur = *str;
- while (ISA_UNRESERVED(cur) || ISA_PCT_ENCODED(cur) ||
- ISA_SUB_DELIM(cur) || (*cur == ':'))
- NEXT(cur);
- if (*cur == '@') {
- if (uri != NULL) {
- if (uri->user != NULL) xmlFree(uri->user);
- if (uri->cleanup & 2)
- uri->user = STRNDUP(*str, cur - *str);
- else
- uri->user = xmlURIUnescapeString(*str, cur - *str, NULL);
- }
- *str = cur;
- return(0);
- }
- return(1);
- }
- /**
- * xmlParse3986DecOctet:
- * @str: the string to analyze
- *
- * dec-octet = DIGIT ; 0-9
- * / %x31-39 DIGIT ; 10-99
- * / "1" 2DIGIT ; 100-199
- * / "2" %x30-34 DIGIT ; 200-249
- * / "25" %x30-35 ; 250-255
- *
- * Skip a dec-octet.
- *
- * Returns 0 if found and skipped, 1 otherwise
- */
- static int
- xmlParse3986DecOctet(const char **str) {
- const char *cur = *str;
- if (!(ISA_DIGIT(cur)))
- return(1);
- if (!ISA_DIGIT(cur+1))
- cur++;
- else if ((*cur != '0') && (ISA_DIGIT(cur + 1)) && (!ISA_DIGIT(cur+2)))
- cur += 2;
- else if ((*cur == '1') && (ISA_DIGIT(cur + 1)) && (ISA_DIGIT(cur + 2)))
- cur += 3;
- else if ((*cur == '2') && (*(cur + 1) >= '0') &&
- (*(cur + 1) <= '4') && (ISA_DIGIT(cur + 2)))
- cur += 3;
- else if ((*cur == '2') && (*(cur + 1) == '5') &&
- (*(cur + 2) >= '0') && (*(cur + 1) <= '5'))
- cur += 3;
- else
- return(1);
- *str = cur;
- return(0);
- }
- /**
- * xmlParse3986Host:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an host part and fills in the appropriate fields
- * of the @uri structure
- *
- * host = IP-literal / IPv4address / reg-name
- * IP-literal = "[" ( IPv6address / IPvFuture ) "]"
- * IPv4address = dec-octet "." dec-octet "." dec-octet "." dec-octet
- * reg-name = *( unreserved / pct-encoded / sub-delims )
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986Host(xmlURIPtr uri, const char **str)
- {
- const char *cur = *str;
- const char *host;
- host = cur;
- /*
- * IPv6 and future addressing scheme are enclosed between brackets
- */
- if (*cur == '[') {
- cur++;
- while ((*cur != ']') && (*cur != 0))
- cur++;
- if (*cur != ']')
- return(1);
- cur++;
- goto found;
- }
- /*
- * try to parse an IPv4
- */
- if (ISA_DIGIT(cur)) {
- if (xmlParse3986DecOctet(&cur) != 0)
- goto not_ipv4;
- if (*cur != '.')
- goto not_ipv4;
- cur++;
- if (xmlParse3986DecOctet(&cur) != 0)
- goto not_ipv4;
- if (*cur != '.')
- goto not_ipv4;
- if (xmlParse3986DecOctet(&cur) != 0)
- goto not_ipv4;
- if (*cur != '.')
- goto not_ipv4;
- if (xmlParse3986DecOctet(&cur) != 0)
- goto not_ipv4;
- goto found;
- not_ipv4:
- cur = *str;
- }
- /*
- * then this should be a hostname which can be empty
- */
- while (ISA_UNRESERVED(cur) || ISA_PCT_ENCODED(cur) || ISA_SUB_DELIM(cur))
- NEXT(cur);
- found:
- if (uri != NULL) {
- if (uri->authority != NULL) xmlFree(uri->authority);
- uri->authority = NULL;
- if (uri->server != NULL) xmlFree(uri->server);
- if (cur != host) {
- if (uri->cleanup & 2)
- uri->server = STRNDUP(host, cur - host);
- else
- uri->server = xmlURIUnescapeString(host, cur - host, NULL);
- } else
- uri->server = NULL;
- }
- *str = cur;
- return(0);
- }
- /**
- * xmlParse3986Authority:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an authority part and fills in the appropriate fields
- * of the @uri structure
- *
- * authority = [ userinfo "@" ] host [ ":" port ]
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986Authority(xmlURIPtr uri, const char **str)
- {
- const char *cur;
- int ret;
- cur = *str;
- /*
- * try to parse an userinfo and check for the trailing @
- */
- ret = xmlParse3986Userinfo(uri, &cur);
- if ((ret != 0) || (*cur != '@'))
- cur = *str;
- else
- cur++;
- ret = xmlParse3986Host(uri, &cur);
- if (ret != 0) return(ret);
- if (*cur == ':') {
- cur++;
- ret = xmlParse3986Port(uri, &cur);
- if (ret != 0) return(ret);
- }
- *str = cur;
- return(0);
- }
- /**
- * xmlParse3986Segment:
- * @str: the string to analyze
- * @forbid: an optional forbidden character
- * @empty: allow an empty segment
- *
- * Parse a segment and fills in the appropriate fields
- * of the @uri structure
- *
- * segment = *pchar
- * segment-nz = 1*pchar
- * segment-nz-nc = 1*( unreserved / pct-encoded / sub-delims / "@" )
- * ; non-zero-length segment without any colon ":"
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986Segment(const char **str, char forbid, int empty)
- {
- const char *cur;
- cur = *str;
- if (!ISA_PCHAR(cur)) {
- if (empty)
- return(0);
- return(1);
- }
- while (ISA_PCHAR(cur) && (*cur != forbid))
- NEXT(cur);
- *str = cur;
- return (0);
- }
- /**
- * xmlParse3986PathAbEmpty:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an path absolute or empty and fills in the appropriate fields
- * of the @uri structure
- *
- * path-abempty = *( "/" segment )
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986PathAbEmpty(xmlURIPtr uri, const char **str)
- {
- const char *cur;
- int ret;
- cur = *str;
- while (*cur == '/') {
- cur++;
- ret = xmlParse3986Segment(&cur, 0, 1);
- if (ret != 0) return(ret);
- }
- if (uri != NULL) {
- if (uri->path != NULL) xmlFree(uri->path);
- if (*str != cur) {
- if (uri->cleanup & 2)
- uri->path = STRNDUP(*str, cur - *str);
- else
- uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
- } else {
- uri->path = NULL;
- }
- }
- *str = cur;
- return (0);
- }
- /**
- * xmlParse3986PathAbsolute:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an path absolute and fills in the appropriate fields
- * of the @uri structure
- *
- * path-absolute = "/" [ segment-nz *( "/" segment ) ]
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986PathAbsolute(xmlURIPtr uri, const char **str)
- {
- const char *cur;
- int ret;
- cur = *str;
- if (*cur != '/')
- return(1);
- cur++;
- ret = xmlParse3986Segment(&cur, 0, 0);
- if (ret == 0) {
- while (*cur == '/') {
- cur++;
- ret = xmlParse3986Segment(&cur, 0, 1);
- if (ret != 0) return(ret);
- }
- }
- if (uri != NULL) {
- if (uri->path != NULL) xmlFree(uri->path);
- if (cur != *str) {
- if (uri->cleanup & 2)
- uri->path = STRNDUP(*str, cur - *str);
- else
- uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
- } else {
- uri->path = NULL;
- }
- }
- *str = cur;
- return (0);
- }
- /**
- * xmlParse3986PathRootless:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an path without root and fills in the appropriate fields
- * of the @uri structure
- *
- * path-rootless = segment-nz *( "/" segment )
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986PathRootless(xmlURIPtr uri, const char **str)
- {
- const char *cur;
- int ret;
- cur = *str;
- ret = xmlParse3986Segment(&cur, 0, 0);
- if (ret != 0) return(ret);
- while (*cur == '/') {
- cur++;
- ret = xmlParse3986Segment(&cur, 0, 1);
- if (ret != 0) return(ret);
- }
- if (uri != NULL) {
- if (uri->path != NULL) xmlFree(uri->path);
- if (cur != *str) {
- if (uri->cleanup & 2)
- uri->path = STRNDUP(*str, cur - *str);
- else
- uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
- } else {
- uri->path = NULL;
- }
- }
- *str = cur;
- return (0);
- }
- /**
- * xmlParse3986PathNoScheme:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an path which is not a scheme and fills in the appropriate fields
- * of the @uri structure
- *
- * path-noscheme = segment-nz-nc *( "/" segment )
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986PathNoScheme(xmlURIPtr uri, const char **str)
- {
- const char *cur;
- int ret;
- cur = *str;
- ret = xmlParse3986Segment(&cur, ':', 0);
- if (ret != 0) return(ret);
- while (*cur == '/') {
- cur++;
- ret = xmlParse3986Segment(&cur, 0, 1);
- if (ret != 0) return(ret);
- }
- if (uri != NULL) {
- if (uri->path != NULL) xmlFree(uri->path);
- if (cur != *str) {
- if (uri->cleanup & 2)
- uri->path = STRNDUP(*str, cur - *str);
- else
- uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
- } else {
- uri->path = NULL;
- }
- }
- *str = cur;
- return (0);
- }
- /**
- * xmlParse3986HierPart:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an hierarchical part and fills in the appropriate fields
- * of the @uri structure
- *
- * hier-part = "//" authority path-abempty
- * / path-absolute
- * / path-rootless
- * / path-empty
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986HierPart(xmlURIPtr uri, const char **str)
- {
- const char *cur;
- int ret;
- cur = *str;
- if ((*cur == '/') && (*(cur + 1) == '/')) {
- cur += 2;
- ret = xmlParse3986Authority(uri, &cur);
- if (ret != 0) return(ret);
- if (uri->server == NULL)
- uri->port = -1;
- ret = xmlParse3986PathAbEmpty(uri, &cur);
- if (ret != 0) return(ret);
- *str = cur;
- return(0);
- } else if (*cur == '/') {
- ret = xmlParse3986PathAbsolute(uri, &cur);
- if (ret != 0) return(ret);
- } else if (ISA_PCHAR(cur)) {
- ret = xmlParse3986PathRootless(uri, &cur);
- if (ret != 0) return(ret);
- } else {
- /* path-empty is effectively empty */
- if (uri != NULL) {
- if (uri->path != NULL) xmlFree(uri->path);
- uri->path = NULL;
- }
- }
- *str = cur;
- return (0);
- }
- /**
- * xmlParse3986RelativeRef:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an URI string and fills in the appropriate fields
- * of the @uri structure
- *
- * relative-ref = relative-part [ "?" query ] [ "#" fragment ]
- * relative-part = "//" authority path-abempty
- * / path-absolute
- * / path-noscheme
- * / path-empty
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986RelativeRef(xmlURIPtr uri, const char *str) {
- int ret;
- if ((*str == '/') && (*(str + 1) == '/')) {
- str += 2;
- ret = xmlParse3986Authority(uri, &str);
- if (ret != 0) return(ret);
- ret = xmlParse3986PathAbEmpty(uri, &str);
- if (ret != 0) return(ret);
- } else if (*str == '/') {
- ret = xmlParse3986PathAbsolute(uri, &str);
- if (ret != 0) return(ret);
- } else if (ISA_PCHAR(str)) {
- ret = xmlParse3986PathNoScheme(uri, &str);
- if (ret != 0) return(ret);
- } else {
- /* path-empty is effectively empty */
- if (uri != NULL) {
- if (uri->path != NULL) xmlFree(uri->path);
- uri->path = NULL;
- }
- }
- if (*str == '?') {
- str++;
- ret = xmlParse3986Query(uri, &str);
- if (ret != 0) return(ret);
- }
- if (*str == '#') {
- str++;
- ret = xmlParse3986Fragment(uri, &str);
- if (ret != 0) return(ret);
- }
- if (*str != 0) {
- xmlCleanURI(uri);
- return(1);
- }
- return(0);
- }
- /**
- * xmlParse3986URI:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an URI string and fills in the appropriate fields
- * of the @uri structure
- *
- * scheme ":" hier-part [ "?" query ] [ "#" fragment ]
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986URI(xmlURIPtr uri, const char *str) {
- int ret;
- ret = xmlParse3986Scheme(uri, &str);
- if (ret != 0) return(ret);
- if (*str != ':') {
- return(1);
- }
- str++;
- ret = xmlParse3986HierPart(uri, &str);
- if (ret != 0) return(ret);
- if (*str == '?') {
- str++;
- ret = xmlParse3986Query(uri, &str);
- if (ret != 0) return(ret);
- }
- if (*str == '#') {
- str++;
- ret = xmlParse3986Fragment(uri, &str);
- if (ret != 0) return(ret);
- }
- if (*str != 0) {
- xmlCleanURI(uri);
- return(1);
- }
- return(0);
- }
- /**
- * xmlParse3986URIReference:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an URI reference string and fills in the appropriate fields
- * of the @uri structure
- *
- * URI-reference = URI / relative-ref
- *
- * Returns 0 or the error code
- */
- static int
- xmlParse3986URIReference(xmlURIPtr uri, const char *str) {
- int ret;
- if (str == NULL)
- return(-1);
- xmlCleanURI(uri);
- /*
- * Try first to parse absolute refs, then fallback to relative if
- * it fails.
- */
- ret = xmlParse3986URI(uri, str);
- if (ret != 0) {
- xmlCleanURI(uri);
- ret = xmlParse3986RelativeRef(uri, str);
- if (ret != 0) {
- xmlCleanURI(uri);
- return(ret);
- }
- }
- return(0);
- }
- /**
- * xmlParseURI:
- * @str: the URI string to analyze
- *
- * Parse an URI based on RFC 3986
- *
- * URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
- *
- * Returns a newly built xmlURIPtr or NULL in case of error
- */
- xmlURIPtr
- xmlParseURI(const char *str) {
- xmlURIPtr uri;
- int ret;
- if (str == NULL)
- return(NULL);
- uri = xmlCreateURI();
- if (uri != NULL) {
- ret = xmlParse3986URIReference(uri, str);
- if (ret) {
- xmlFreeURI(uri);
- return(NULL);
- }
- }
- return(uri);
- }
- /**
- * xmlParseURIReference:
- * @uri: pointer to an URI structure
- * @str: the string to analyze
- *
- * Parse an URI reference string based on RFC 3986 and fills in the
- * appropriate fields of the @uri structure
- *
- * URI-reference = URI / relative-ref
- *
- * Returns 0 or the error code
- */
- int
- xmlParseURIReference(xmlURIPtr uri, const char *str) {
- return(xmlParse3986URIReference(uri, str));
- }
- /**
- * xmlParseURIRaw:
- * @str: the URI string to analyze
- * @raw: if 1 unescaping of URI pieces are disabled
- *
- * Parse an URI but allows to keep intact the original fragments.
- *
- * URI-reference = URI / relative-ref
- *
- * Returns a newly built xmlURIPtr or NULL in case of error
- */
- xmlURIPtr
- xmlParseURIRaw(const char *str, int raw) {
- xmlURIPtr uri;
- int ret;
- if (str == NULL)
- return(NULL);
- uri = xmlCreateURI();
- if (uri != NULL) {
- if (raw) {
- uri->cleanup |= 2;
- }
- ret = xmlParseURIReference(uri, str);
- if (ret) {
- xmlFreeURI(uri);
- return(NULL);
- }
- }
- return(uri);
- }
- /************************************************************************
- * *
- * Generic URI structure functions *
- * *
- ************************************************************************/
- /**
- * xmlCreateURI:
- *
- * Simply creates an empty xmlURI
- *
- * Returns the new structure or NULL in case of error
- */
- xmlURIPtr
- xmlCreateURI(void) {
- xmlURIPtr ret;
- ret = (xmlURIPtr) xmlMalloc(sizeof(xmlURI));
- if (ret == NULL) {
- xmlURIErrMemory("creating URI structure\n");
- return(NULL);
- }
- memset(ret, 0, sizeof(xmlURI));
- return(ret);
- }
- /**
- * xmlSaveUriRealloc:
- *
- * Function to handle properly a reallocation when saving an URI
- * Also imposes some limit on the length of an URI string output
- */
- static xmlChar *
- xmlSaveUriRealloc(xmlChar *ret, int *max) {
- xmlChar *temp;
- int tmp;
- if (*max > MAX_URI_LENGTH) {
- xmlURIErrMemory("reaching arbitrary MAX_URI_LENGTH limit\n");
- return(NULL);
- }
- tmp = *max * 2;
- temp = (xmlChar *) xmlRealloc(ret, (tmp + 1));
- if (temp == NULL) {
- xmlURIErrMemory("saving URI\n");
- return(NULL);
- }
- *max = tmp;
- return(temp);
- }
- /**
- * xmlSaveUri:
- * @uri: pointer to an xmlURI
- *
- * Save the URI as an escaped string
- *
- * Returns a new string (to be deallocated by caller)
- */
- xmlChar *
- xmlSaveUri(xmlURIPtr uri) {
- xmlChar *ret = NULL;
- xmlChar *temp;
- const char *p;
- int len;
- int max;
- if (uri == NULL) return(NULL);
- max = 80;
- ret = (xmlChar *) xmlMallocAtomic((max + 1) * sizeof(xmlChar));
- if (ret == NULL) {
- xmlURIErrMemory("saving URI\n");
- return(NULL);
- }
- len = 0;
- if (uri->scheme != NULL) {
- p = uri->scheme;
- while (*p != 0) {
- if (len >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = *p++;
- }
- if (len >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = ':';
- }
- if (uri->opaque != NULL) {
- p = uri->opaque;
- while (*p != 0) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- if (IS_RESERVED(*(p)) || IS_UNRESERVED(*(p)))
- ret[len++] = *p++;
- else {
- int val = *(unsigned char *)p++;
- int hi = val / 0x10, lo = val % 0x10;
- ret[len++] = '%';
- ret[len++] = hi + (hi > 9? 'A'-10 : '0');
- ret[len++] = lo + (lo > 9? 'A'-10 : '0');
- }
- }
- } else {
- if ((uri->server != NULL) || (uri->port == -1)) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = '/';
- ret[len++] = '/';
- if (uri->user != NULL) {
- p = uri->user;
- while (*p != 0) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- if ((IS_UNRESERVED(*(p))) ||
- ((*(p) == ';')) || ((*(p) == ':')) ||
- ((*(p) == '&')) || ((*(p) == '=')) ||
- ((*(p) == '+')) || ((*(p) == '$')) ||
- ((*(p) == ',')))
- ret[len++] = *p++;
- else {
- int val = *(unsigned char *)p++;
- int hi = val / 0x10, lo = val % 0x10;
- ret[len++] = '%';
- ret[len++] = hi + (hi > 9? 'A'-10 : '0');
- ret[len++] = lo + (lo > 9? 'A'-10 : '0');
- }
- }
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = '@';
- }
- if (uri->server != NULL) {
- p = uri->server;
- while (*p != 0) {
- if (len >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = *p++;
- }
- if (uri->port > 0) {
- if (len + 10 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- len += snprintf((char *) &ret[len], max - len, ":%d", uri->port);
- }
- }
- } else if (uri->authority != NULL) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = '/';
- ret[len++] = '/';
- p = uri->authority;
- while (*p != 0) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- if ((IS_UNRESERVED(*(p))) ||
- ((*(p) == '$')) || ((*(p) == ',')) || ((*(p) == ';')) ||
- ((*(p) == ':')) || ((*(p) == '@')) || ((*(p) == '&')) ||
- ((*(p) == '=')) || ((*(p) == '+')))
- ret[len++] = *p++;
- else {
- int val = *(unsigned char *)p++;
- int hi = val / 0x10, lo = val % 0x10;
- ret[len++] = '%';
- ret[len++] = hi + (hi > 9? 'A'-10 : '0');
- ret[len++] = lo + (lo > 9? 'A'-10 : '0');
- }
- }
- } else if (uri->scheme != NULL) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- }
- if (uri->path != NULL) {
- p = uri->path;
- /*
- * the colon in file:///d: should not be escaped or
- * Windows accesses fail later.
- */
- if ((uri->scheme != NULL) &&
- (p[0] == '/') &&
- (((p[1] >= 'a') && (p[1] <= 'z')) ||
- ((p[1] >= 'A') && (p[1] <= 'Z'))) &&
- (p[2] == ':') &&
- (xmlStrEqual(BAD_CAST uri->scheme, BAD_CAST "file"))) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = *p++;
- ret[len++] = *p++;
- ret[len++] = *p++;
- }
- while (*p != 0) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- if ((IS_UNRESERVED(*(p))) || ((*(p) == '/')) ||
- ((*(p) == ';')) || ((*(p) == '@')) || ((*(p) == '&')) ||
- ((*(p) == '=')) || ((*(p) == '+')) || ((*(p) == '$')) ||
- ((*(p) == ',')))
- ret[len++] = *p++;
- else {
- int val = *(unsigned char *)p++;
- int hi = val / 0x10, lo = val % 0x10;
- ret[len++] = '%';
- ret[len++] = hi + (hi > 9? 'A'-10 : '0');
- ret[len++] = lo + (lo > 9? 'A'-10 : '0');
- }
- }
- }
- if (uri->query_raw != NULL) {
- if (len + 1 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = '?';
- p = uri->query_raw;
- while (*p != 0) {
- if (len + 1 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = *p++;
- }
- } else if (uri->query != NULL) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = '?';
- p = uri->query;
- while (*p != 0) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- if ((IS_UNRESERVED(*(p))) || (IS_RESERVED(*(p))))
- ret[len++] = *p++;
- else {
- int val = *(unsigned char *)p++;
- int hi = val / 0x10, lo = val % 0x10;
- ret[len++] = '%';
- ret[len++] = hi + (hi > 9? 'A'-10 : '0');
- ret[len++] = lo + (lo > 9? 'A'-10 : '0');
- }
- }
- }
- }
- if (uri->fragment != NULL) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len++] = '#';
- p = uri->fragment;
- while (*p != 0) {
- if (len + 3 >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- if ((IS_UNRESERVED(*(p))) || (IS_RESERVED(*(p))))
- ret[len++] = *p++;
- else {
- int val = *(unsigned char *)p++;
- int hi = val / 0x10, lo = val % 0x10;
- ret[len++] = '%';
- ret[len++] = hi + (hi > 9? 'A'-10 : '0');
- ret[len++] = lo + (lo > 9? 'A'-10 : '0');
- }
- }
- }
- if (len >= max) {
- temp = xmlSaveUriRealloc(ret, &max);
- if (temp == NULL) goto mem_error;
- ret = temp;
- }
- ret[len] = 0;
- return(ret);
- mem_error:
- xmlFree(ret);
- return(NULL);
- }
- /**
- * xmlPrintURI:
- * @stream: a FILE* for the output
- * @uri: pointer to an xmlURI
- *
- * Prints the URI in the stream @stream.
- */
- void
- xmlPrintURI(FILE *stream, xmlURIPtr uri) {
- xmlChar *out;
- out = xmlSaveUri(uri);
- if (out != NULL) {
- fprintf(stream, "%s", (char *) out);
- xmlFree(out);
- }
- }
- /**
- * xmlCleanURI:
- * @uri: pointer to an xmlURI
- *
- * Make sure the xmlURI struct is free of content
- */
- static void
- xmlCleanURI(xmlURIPtr uri) {
- if (uri == NULL) return;
- if (uri->scheme != NULL) xmlFree(uri->scheme);
- uri->scheme = NULL;
- if (uri->server != NULL) xmlFree(uri->server);
- uri->server = NULL;
- if (uri->user != NULL) xmlFree(uri->user);
- uri->user = NULL;
- if (uri->path != NULL) xmlFree(uri->path);
- uri->path = NULL;
- if (uri->fragment != NULL) xmlFree(uri->fragment);
- uri->fragment = NULL;
- if (uri->opaque != NULL) xmlFree(uri->opaque);
- uri->opaque = NULL;
- if (uri->authority != NULL) xmlFree(uri->authority);
- uri->authority = NULL;
- if (uri->query != NULL) xmlFree(uri->query);
- uri->query = NULL;
- if (uri->query_raw != NULL) xmlFree(uri->query_raw);
- uri->query_raw = NULL;
- }
- /**
- * xmlFreeURI:
- * @uri: pointer to an xmlURI
- *
- * Free up the xmlURI struct
- */
- void
- xmlFreeURI(xmlURIPtr uri) {
- if (uri == NULL) return;
- if (uri->scheme != NULL) xmlFree(uri->scheme);
- if (uri->server != NULL) xmlFree(uri->server);
- if (uri->user != NULL) xmlFree(uri->user);
- if (uri->path != NULL) xmlFree(uri->path);
- if (uri->fragment != NULL) xmlFree(uri->fragment);
- if (uri->opaque != NULL) xmlFree(uri->opaque);
- if (uri->authority != NULL) xmlFree(uri->authority);
- if (uri->query != NULL) xmlFree(uri->query);
- if (uri->query_raw != NULL) xmlFree(uri->query_raw);
- xmlFree(uri);
- }
- /************************************************************************
- * *
- * Helper functions *
- * *
- ************************************************************************/
- /**
- * xmlNormalizeURIPath:
- * @path: pointer to the path string
- *
- * Applies the 5 normalization steps to a path string--that is, RFC 2396
- * Section 5.2, steps 6.c through 6.g.
- *
- * Normalization occurs directly on the string, no new allocation is done
- *
- * Returns 0 or an error code
- */
- int
- xmlNormalizeURIPath(char *path) {
- char *cur, *out;
- if (path == NULL)
- return(-1);
- /* Skip all initial "/" chars. We want to get to the beginning of the
- * first non-empty segment.
- */
- cur = path;
- while (cur[0] == '/')
- ++cur;
- if (cur[0] == '\0')
- return(0);
- /* Keep everything we've seen so far. */
- out = cur;
- /*
- * Analyze each segment in sequence for cases (c) and (d).
- */
- while (cur[0] != '\0') {
- /*
- * c) All occurrences of "./", where "." is a complete path segment,
- * are removed from the buffer string.
- */
- if ((cur[0] == '.') && (cur[1] == '/')) {
- cur += 2;
- /* '//' normalization should be done at this point too */
- while (cur[0] == '/')
- cur++;
- continue;
- }
- /*
- * d) If the buffer string ends with "." as a complete path segment,
- * that "." is removed.
- */
- if ((cur[0] == '.') && (cur[1] == '\0'))
- break;
- /* Otherwise keep the segment. */
- while (cur[0] != '/') {
- if (cur[0] == '\0')
- goto done_cd;
- (out++)[0] = (cur++)[0];
- }
- /* normalize // */
- while ((cur[0] == '/') && (cur[1] == '/'))
- cur++;
- (out++)[0] = (cur++)[0];
- }
- done_cd:
- out[0] = '\0';
- /* Reset to the beginning of the first segment for the next sequence. */
- cur = path;
- while (cur[0] == '/')
- ++cur;
- if (cur[0] == '\0')
- return(0);
- /*
- * Analyze each segment in sequence for cases (e) and (f).
- *
- * e) All occurrences of "<segment>/../", where <segment> is a
- * complete path segment not equal to "..", are removed from the
- * buffer string. Removal of these path segments is performed
- * iteratively, removing the leftmost matching pattern on each
- * iteration, until no matching pattern remains.
- *
- * f) If the buffer string ends with "<segment>/..", where <segment>
- * is a complete path segment not equal to "..", that
- * "<segment>/.." is removed.
- *
- * To satisfy the "iterative" clause in (e), we need to collapse the
- * string every time we find something that needs to be removed. Thus,
- * we don't need to keep two pointers into the string: we only need a
- * "current position" pointer.
- */
- while (1) {
- char *segp, *tmp;
- /* At the beginning of each iteration of this loop, "cur" points to
- * the first character of the segment we want to examine.
- */
- /* Find the end of the current segment. */
- segp = cur;
- while ((segp[0] != '/') && (segp[0] != '\0'))
- ++segp;
- /* If this is the last segment, we're done (we need at least two
- * segments to meet the criteria for the (e) and (f) cases).
- */
- if (segp[0] == '\0')
- break;
- /* If the first segment is "..", or if the next segment _isn't_ "..",
- * keep this segment and try the next one.
- */
- ++segp;
- if (((cur[0] == '.') && (cur[1] == '.') && (segp == cur+3))
- || ((segp[0] != '.') || (segp[1] != '.')
- || ((segp[2] != '/') && (segp[2] != '\0')))) {
- cur = segp;
- continue;
- }
- /* If we get here, remove this segment and the next one and back up
- * to the previous segment (if there is one), to implement the
- * "iteratively" clause. It's pretty much impossible to back up
- * while maintaining two pointers into the buffer, so just compact
- * the whole buffer now.
- */
- /* If this is the end of the buffer, we're done. */
- if (segp[2] == '\0') {
- cur[0] = '\0';
- break;
- }
- /* Valgrind complained, strcpy(cur, segp + 3); */
- /* string will overlap, do not use strcpy */
- tmp = cur;
- segp += 3;
- while ((*tmp++ = *segp++) != 0)
- ;
- /* If there are no previous segments, then keep going from here. */
- segp = cur;
- while ((segp > path) && ((--segp)[0] == '/'))
- ;
- if (segp == path)
- continue;
- /* "segp" is pointing to the end of a previous segment; find it's
- * start. We need to back up to the previous segment and start
- * over with that to handle things like "foo/bar/../..". If we
- * don't do this, then on the first pass we'll remove the "bar/..",
- * but be pointing at the second ".." so we won't realize we can also
- * remove the "foo/..".
- */
- cur = segp;
- while ((cur > path) && (cur[-1] != '/'))
- --cur;
- }
- out[0] = '\0';
- /*
- * g) If the resulting buffer string still begins with one or more
- * complete path segments of "..", then the reference is
- * considered to be in error. Implementations may handle this
- * error by retaining these components in the resolved path (i.e.,
- * treating them as part of the final URI), by removing them from
- * the resolved path (i.e., discarding relative levels above the
- * root), or by avoiding traversal of the reference.
- *
- * We discard them from the final path.
- */
- if (path[0] == '/') {
- cur = path;
- while ((cur[0] == '/') && (cur[1] == '.') && (cur[2] == '.')
- && ((cur[3] == '/') || (cur[3] == '\0')))
- cur += 3;
- if (cur != path) {
- out = path;
- while (cur[0] != '\0')
- (out++)[0] = (cur++)[0];
- out[0] = 0;
- }
- }
- return(0);
- }
- static int is_hex(char c) {
- if (((c >= '0') && (c <= '9')) ||
- ((c >= 'a') && (c <= 'f')) ||
- ((c >= 'A') && (c <= 'F')))
- return(1);
- return(0);
- }
- /**
- * xmlURIUnescapeString:
- * @str: the string to unescape
- * @len: the length in bytes to unescape (or <= 0 to indicate full string)
- * @target: optional destination buffer
- *
- * Unescaping routine, but does not check that the string is an URI. The
- * output is a direct unsigned char translation of %XX values (no encoding)
- * Note that the length of the result can only be smaller or same size as
- * the input string.
- *
- * Returns a copy of the string, but unescaped, will return NULL only in case
- * of error
- */
- char *
- xmlURIUnescapeString(const char *str, int len, char *target) {
- char *ret, *out;
- const char *in;
- if (str == NULL)
- return(NULL);
- if (len <= 0) len = strlen(str);
- if (len < 0) return(NULL);
- if (target == NULL) {
- ret = (char *) xmlMallocAtomic(len + 1);
- if (ret == NULL) {
- xmlURIErrMemory("unescaping URI value\n");
- return(NULL);
- }
- } else
- ret = target;
- in = str;
- out = ret;
- while(len > 0) {
- if ((len > 2) && (*in == '%') && (is_hex(in[1])) && (is_hex(in[2]))) {
- in++;
- if ((*in >= '0') && (*in <= '9'))
- *out = (*in - '0');
- else if ((*in >= 'a') && (*in <= 'f'))
- *out = (*in - 'a') + 10;
- else if ((*in >= 'A') && (*in <= 'F'))
- *out = (*in - 'A') + 10;
- in++;
- if ((*in >= '0') && (*in <= '9'))
- *out = *out * 16 + (*in - '0');
- else if ((*in >= 'a') && (*in <= 'f'))
- *out = *out * 16 + (*in - 'a') + 10;
- else if ((*in >= 'A') && (*in <= 'F'))
- *out = *out * 16 + (*in - 'A') + 10;
- in++;
- len -= 3;
- out++;
- } else {
- *out++ = *in++;
- len--;
- }
- }
- *out = 0;
- return(ret);
- }
- /**
- * xmlURIEscapeStr:
- * @str: string to escape
- * @list: exception list string of chars not to escape
- *
- * This routine escapes a string to hex, ignoring reserved characters (a-z)
- * and the characters in the exception list.
- *
- * Returns a new escaped string or NULL in case of error.
- */
- xmlChar *
- xmlURIEscapeStr(const xmlChar *str, const xmlChar *list) {
- xmlChar *ret, ch;
- xmlChar *temp;
- const xmlChar *in;
- int len, out;
- if (str == NULL)
- return(NULL);
- if (str[0] == 0)
- return(xmlStrdup(str));
- len = xmlStrlen(str);
- if (!(len > 0)) return(NULL);
- len += 20;
- ret = (xmlChar *) xmlMallocAtomic(len);
- if (ret == NULL) {
- xmlURIErrMemory("escaping URI value\n");
- return(NULL);
- }
- in = (const xmlChar *) str;
- out = 0;
- while(*in != 0) {
- if (len - out <= 3) {
- temp = xmlSaveUriRealloc(ret, &len);
- if (temp == NULL) {
- xmlURIErrMemory("escaping URI value\n");
- xmlFree(ret);
- return(NULL);
- }
- ret = temp;
- }
- ch = *in;
- if ((ch != '@') && (!IS_UNRESERVED(ch)) && (!xmlStrchr(list, ch))) {
- unsigned char val;
- ret[out++] = '%';
- val = ch >> 4;
- if (val <= 9)
- ret[out++] = '0' + val;
- else
- ret[out++] = 'A' + val - 0xA;
- val = ch & 0xF;
- if (val <= 9)
- ret[out++] = '0' + val;
- else
- ret[out++] = 'A' + val - 0xA;
- in++;
- } else {
- ret[out++] = *in++;
- }
- }
- ret[out] = 0;
- return(ret);
- }
- /**
- * xmlURIEscape:
- * @str: the string of the URI to escape
- *
- * Escaping routine, does not do validity checks !
- * It will try to escape the chars needing this, but this is heuristic
- * based it's impossible to be sure.
- *
- * Returns an copy of the string, but escaped
- *
- * 25 May 2001
- * Uses xmlParseURI and xmlURIEscapeStr to try to escape correctly
- * according to RFC2396.
- * - Carl Douglas
- */
- xmlChar *
- xmlURIEscape(const xmlChar * str)
- {
- xmlChar *ret, *segment = NULL;
- xmlURIPtr uri;
- int ret2;
- if (str == NULL)
- return (NULL);
- uri = xmlCreateURI();
- if (uri != NULL) {
- /*
- * Allow escaping errors in the unescaped form
- */
- uri->cleanup = 1;
- ret2 = xmlParseURIReference(uri, (const char *)str);
- if (ret2) {
- xmlFreeURI(uri);
- return (NULL);
- }
- }
- if (!uri)
- return NULL;
- ret = NULL;
- #define NULLCHK(p) if(!p) { \
- xmlURIErrMemory("escaping URI value\n"); \
- xmlFreeURI(uri); \
- xmlFree(ret); \
- return NULL; } \
- if (uri->scheme) {
- segment = xmlURIEscapeStr(BAD_CAST uri->scheme, BAD_CAST "+-.");
- NULLCHK(segment)
- ret = xmlStrcat(ret, segment);
- ret = xmlStrcat(ret, BAD_CAST ":");
- xmlFree(segment);
- }
- if (uri->authority) {
- segment =
- xmlURIEscapeStr(BAD_CAST uri->authority, BAD_CAST "/?;:@");
- NULLCHK(segment)
- ret = xmlStrcat(ret, BAD_CAST "//");
- ret = xmlStrcat(ret, segment);
- xmlFree(segment);
- }
- if (uri->user) {
- segment = xmlURIEscapeStr(BAD_CAST uri->user, BAD_CAST ";:&=+$,");
- NULLCHK(segment)
- ret = xmlStrcat(ret,BAD_CAST "//");
- ret = xmlStrcat(ret, segment);
- ret = xmlStrcat(ret, BAD_CAST "@");
- xmlFree(segment);
- }
- if (uri->server) {
- segment = xmlURIEscapeStr(BAD_CAST uri->server, BAD_CAST "/?;:@");
- NULLCHK(segment)
- if (uri->user == NULL)
- ret = xmlStrcat(ret, BAD_CAST "//");
- ret = xmlStrcat(ret, segment);
- xmlFree(segment);
- }
- if (uri->port) {
- xmlChar port[10];
- snprintf((char *) port, 10, "%d", uri->port);
- ret = xmlStrcat(ret, BAD_CAST ":");
- ret = xmlStrcat(ret, port);
- }
- if (uri->path) {
- segment =
- xmlURIEscapeStr(BAD_CAST uri->path, BAD_CAST ":@&=+$,/?;");
- NULLCHK(segment)
- ret = xmlStrcat(ret, segment);
- xmlFree(segment);
- }
- if (uri->query_raw) {
- ret = xmlStrcat(ret, BAD_CAST "?");
- ret = xmlStrcat(ret, BAD_CAST uri->query_raw);
- }
- else if (uri->query) {
- segment =
- xmlURIEscapeStr(BAD_CAST uri->query, BAD_CAST ";/?:@&=+,$");
- NULLCHK(segment)
- ret = xmlStrcat(ret, BAD_CAST "?");
- ret = xmlStrcat(ret, segment);
- xmlFree(segment);
- }
- if (uri->opaque) {
- segment = xmlURIEscapeStr(BAD_CAST uri->opaque, BAD_CAST "");
- NULLCHK(segment)
- ret = xmlStrcat(ret, segment);
- xmlFree(segment);
- }
- if (uri->fragment) {
- segment = xmlURIEscapeStr(BAD_CAST uri->fragment, BAD_CAST "#");
- NULLCHK(segment)
- ret = xmlStrcat(ret, BAD_CAST "#");
- ret = xmlStrcat(ret, segment);
- xmlFree(segment);
- }
- xmlFreeURI(uri);
- #undef NULLCHK
- return (ret);
- }
- /************************************************************************
- * *
- * Public functions *
- * *
- ************************************************************************/
- /**
- * xmlBuildURI:
- * @URI: the URI instance found in the document
- * @base: the base value
- *
- * Computes he final URI of the reference done by checking that
- * the given URI is valid, and building the final URI using the
- * base URI. This is processed according to section 5.2 of the
- * RFC 2396
- *
- * 5.2. Resolving Relative References to Absolute Form
- *
- * Returns a new URI string (to be freed by the caller) or NULL in case
- * of error.
- */
- xmlChar *
- xmlBuildURI(const xmlChar *URI, const xmlChar *base) {
- xmlChar *val = NULL;
- int ret, len, indx, cur, out;
- xmlURIPtr ref = NULL;
- xmlURIPtr bas = NULL;
- xmlURIPtr res = NULL;
- /*
- * 1) The URI reference is parsed into the potential four components and
- * fragment identifier, as described in Section 4.3.
- *
- * NOTE that a completely empty URI is treated by modern browsers
- * as a reference to "." rather than as a synonym for the current
- * URI. Should we do that here?
- */
- if (URI == NULL)
- ret = -1;
- else {
- if (*URI) {
- ref = xmlCreateURI();
- if (ref == NULL)
- goto done;
- ret = xmlParseURIReference(ref, (const char *) URI);
- }
- else
- ret = 0;
- }
- if (ret != 0)
- goto done;
- if ((ref != NULL) && (ref->scheme != NULL)) {
- /*
- * The URI is absolute don't modify.
- */
- val = xmlStrdup(URI);
- goto done;
- }
- if (base == NULL)
- ret = -1;
- else {
- bas = xmlCreateURI();
- if (bas == NULL)
- goto done;
- ret = xmlParseURIReference(bas, (const char *) base);
- }
- if (ret != 0) {
- if (ref)
- val = xmlSaveUri(ref);
- goto done;
- }
- if (ref == NULL) {
- /*
- * the base fragment must be ignored
- */
- if (bas->fragment != NULL) {
- xmlFree(bas->fragment);
- bas->fragment = NULL;
- }
- val = xmlSaveUri(bas);
- goto done;
- }
- /*
- * 2) If the path component is empty and the scheme, authority, and
- * query components are undefined, then it is a reference to the
- * current document and we are done. Otherwise, the reference URI's
- * query and fragment components are defined as found (or not found)
- * within the URI reference and not inherited from the base URI.
- *
- * NOTE that in modern browsers, the parsing differs from the above
- * in the following aspect: the query component is allowed to be
- * defined while still treating this as a reference to the current
- * document.
- */
- res = xmlCreateURI();
- if (res == NULL)
- goto done;
- if ((ref->scheme == NULL) && (ref->path == NULL) &&
- ((ref->authority == NULL) && (ref->server == NULL))) {
- if (bas->scheme != NULL)
- res->scheme = xmlMemStrdup(bas->scheme);
- if (bas->authority != NULL)
- res->authority = xmlMemStrdup(bas->authority);
- else if ((bas->server != NULL) || (bas->port == -1)) {
- if (bas->server != NULL)
- res->server = xmlMemStrdup(bas->server);
- if (bas->user != NULL)
- res->user = xmlMemStrdup(bas->user);
- res->port = bas->port;
- }
- if (bas->path != NULL)
- res->path = xmlMemStrdup(bas->path);
- if (ref->query_raw != NULL)
- res->query_raw = xmlMemStrdup (ref->query_raw);
- else if (ref->query != NULL)
- res->query = xmlMemStrdup(ref->query);
- else if (bas->query_raw != NULL)
- res->query_raw = xmlMemStrdup(bas->query_raw);
- else if (bas->query != NULL)
- res->query = xmlMemStrdup(bas->query);
- if (ref->fragment != NULL)
- res->fragment = xmlMemStrdup(ref->fragment);
- goto step_7;
- }
- /*
- * 3) If the scheme component is defined, indicating that the reference
- * starts with a scheme name, then the reference is interpreted as an
- * absolute URI and we are done. Otherwise, the reference URI's
- * scheme is inherited from the base URI's scheme component.
- */
- if (ref->scheme != NULL) {
- val = xmlSaveUri(ref);
- goto done;
- }
- if (bas->scheme != NULL)
- res->scheme = xmlMemStrdup(bas->scheme);
- if (ref->query_raw != NULL)
- res->query_raw = xmlMemStrdup(ref->query_raw);
- else if (ref->query != NULL)
- res->query = xmlMemStrdup(ref->query);
- if (ref->fragment != NULL)
- res->fragment = xmlMemStrdup(ref->fragment);
- /*
- * 4) If the authority component is defined, then the reference is a
- * network-path and we skip to step 7. Otherwise, the reference
- * URI's authority is inherited from the base URI's authority
- * component, which will also be undefined if the URI scheme does not
- * use an authority component.
- */
- if ((ref->authority != NULL) || (ref->server != NULL)) {
- if (ref->authority != NULL)
- res->authority = xmlMemStrdup(ref->authority);
- else {
- res->server = xmlMemStrdup(ref->server);
- if (ref->user != NULL)
- res->user = xmlMemStrdup(ref->user);
- res->port = ref->port;
- }
- if (ref->path != NULL)
- res->path = xmlMemStrdup(ref->path);
- goto step_7;
- }
- if (bas->authority != NULL)
- res->authority = xmlMemStrdup(bas->authority);
- else if ((bas->server != NULL) || (bas->port == -1)) {
- if (bas->server != NULL)
- res->server = xmlMemStrdup(bas->server);
- if (bas->user != NULL)
- res->user = xmlMemStrdup(bas->user);
- res->port = bas->port;
- }
- /*
- * 5) If the path component begins with a slash character ("/"), then
- * the reference is an absolute-path and we skip to step 7.
- */
- if ((ref->path != NULL) && (ref->path[0] == '/')) {
- res->path = xmlMemStrdup(ref->path);
- goto step_7;
- }
- /*
- * 6) If this step is reached, then we are resolving a relative-path
- * reference. The relative path needs to be merged with the base
- * URI's path. Although there are many ways to do this, we will
- * describe a simple method using a separate string buffer.
- *
- * Allocate a buffer large enough for the result string.
- */
- len = 2; /* extra / and 0 */
- if (ref->path != NULL)
- len += strlen(ref->path);
- if (bas->path != NULL)
- len += strlen(bas->path);
- res->path = (char *) xmlMallocAtomic(len);
- if (res->path == NULL) {
- xmlURIErrMemory("resolving URI against base\n");
- goto done;
- }
- res->path[0] = 0;
- /*
- * a) All but the last segment of the base URI's path component is
- * copied to the buffer. In other words, any characters after the
- * last (right-most) slash character, if any, are excluded.
- */
- cur = 0;
- out = 0;
- if (bas->path != NULL) {
- while (bas->path[cur] != 0) {
- while ((bas->path[cur] != 0) && (bas->path[cur] != '/'))
- cur++;
- if (bas->path[cur] == 0)
- break;
- cur++;
- while (out < cur) {
- res->path[out] = bas->path[out];
- out++;
- }
- }
- }
- res->path[out] = 0;
- /*
- * b) The reference's path component is appended to the buffer
- * string.
- */
- if (ref->path != NULL && ref->path[0] != 0) {
- indx = 0;
- /*
- * Ensure the path includes a '/'
- */
- if ((out == 0) && (bas->server != NULL))
- res->path[out++] = '/';
- while (ref->path[indx] != 0) {
- res->path[out++] = ref->path[indx++];
- }
- }
- res->path[out] = 0;
- /*
- * Steps c) to h) are really path normalization steps
- */
- xmlNormalizeURIPath(res->path);
- step_7:
- /*
- * 7) The resulting URI components, including any inherited from the
- * base URI, are recombined to give the absolute form of the URI
- * reference.
- */
- val = xmlSaveUri(res);
- done:
- if (ref != NULL)
- xmlFreeURI(ref);
- if (bas != NULL)
- xmlFreeURI(bas);
- if (res != NULL)
- xmlFreeURI(res);
- return(val);
- }
- /**
- * xmlBuildRelativeURI:
- * @URI: the URI reference under consideration
- * @base: the base value
- *
- * Expresses the URI of the reference in terms relative to the
- * base. Some examples of this operation include:
- * base = "http://site1.com/docs/book1.html"
- * URI input URI returned
- * docs/pic1.gif pic1.gif
- * docs/img/pic1.gif img/pic1.gif
- * img/pic1.gif ../img/pic1.gif
- * http://site1.com/docs/pic1.gif pic1.gif
- * http://site2.com/docs/pic1.gif http://site2.com/docs/pic1.gif
- *
- * base = "docs/book1.html"
- * URI input URI returned
- * docs/pic1.gif pic1.gif
- * docs/img/pic1.gif img/pic1.gif
- * img/pic1.gif ../img/pic1.gif
- * http://site1.com/docs/pic1.gif http://site1.com/docs/pic1.gif
- *
- *
- * Note: if the URI reference is really weird or complicated, it may be
- * worthwhile to first convert it into a "nice" one by calling
- * xmlBuildURI (using 'base') before calling this routine,
- * since this routine (for reasonable efficiency) assumes URI has
- * already been through some validation.
- *
- * Returns a new URI string (to be freed by the caller) or NULL in case
- * error.
- */
- xmlChar *
- xmlBuildRelativeURI (const xmlChar * URI, const xmlChar * base)
- {
- xmlChar *val = NULL;
- int ret;
- int ix;
- int nbslash = 0;
- int len;
- xmlURIPtr ref = NULL;
- xmlURIPtr bas = NULL;
- xmlChar *bptr, *uptr, *vptr;
- int remove_path = 0;
- if ((URI == NULL) || (*URI == 0))
- return NULL;
- /*
- * First parse URI into a standard form
- */
- ref = xmlCreateURI ();
- if (ref == NULL)
- return NULL;
- /* If URI not already in "relative" form */
- if (URI[0] != '.') {
- ret = xmlParseURIReference (ref, (const char *) URI);
- if (ret != 0)
- goto done; /* Error in URI, return NULL */
- } else
- ref->path = (char *)xmlStrdup(URI);
- /*
- * Next parse base into the same standard form
- */
- if ((base == NULL) || (*base == 0)) {
- val = xmlStrdup (URI);
- goto done;
- }
- bas = xmlCreateURI ();
- if (bas == NULL)
- goto done;
- if (base[0] != '.') {
- ret = xmlParseURIReference (bas, (const char *) base);
- if (ret != 0)
- goto done; /* Error in base, return NULL */
- } else
- bas->path = (char *)xmlStrdup(base);
- /*
- * If the scheme / server on the URI differs from the base,
- * just return the URI
- */
- if ((ref->scheme != NULL) &&
- ((bas->scheme == NULL) ||
- (xmlStrcmp ((xmlChar *)bas->scheme, (xmlChar *)ref->scheme)) ||
- (xmlStrcmp ((xmlChar *)bas->server, (xmlChar *)ref->server)))) {
- val = xmlStrdup (URI);
- goto done;
- }
- if (xmlStrEqual((xmlChar *)bas->path, (xmlChar *)ref->path)) {
- val = xmlStrdup(BAD_CAST "");
- goto done;
- }
- if (bas->path == NULL) {
- val = xmlStrdup((xmlChar *)ref->path);
- goto done;
- }
- if (ref->path == NULL) {
- ref->path = (char *) "/";
- remove_path = 1;
- }
- /*
- * At this point (at last!) we can compare the two paths
- *
- * First we take care of the special case where either of the
- * two path components may be missing (bug 316224)
- */
- bptr = (xmlChar *)bas->path;
- {
- xmlChar *rptr = (xmlChar *) ref->path;
- int pos = 0;
- /*
- * Next we compare the two strings and find where they first differ
- */
- if ((*rptr == '.') && (rptr[1] == '/'))
- rptr += 2;
- if ((*bptr == '.') && (bptr[1] == '/'))
- bptr += 2;
- else if ((*bptr == '/') && (*rptr != '/'))
- bptr++;
- while ((bptr[pos] == rptr[pos]) && (bptr[pos] != 0))
- pos++;
- if (bptr[pos] == rptr[pos]) {
- val = xmlStrdup(BAD_CAST "");
- goto done; /* (I can't imagine why anyone would do this) */
- }
- /*
- * In URI, "back up" to the last '/' encountered. This will be the
- * beginning of the "unique" suffix of URI
- */
- ix = pos;
- for (; ix > 0; ix--) {
- if (rptr[ix - 1] == '/')
- break;
- }
- uptr = (xmlChar *)&rptr[ix];
- /*
- * In base, count the number of '/' from the differing point
- */
- for (; bptr[ix] != 0; ix++) {
- if (bptr[ix] == '/')
- nbslash++;
- }
- /*
- * e.g: URI="foo/" base="foo/bar" -> "./"
- */
- if (nbslash == 0 && !uptr[0]) {
- val = xmlStrdup(BAD_CAST "./");
- goto done;
- }
- len = xmlStrlen (uptr) + 1;
- }
- if (nbslash == 0) {
- if (uptr != NULL)
- /* exception characters from xmlSaveUri */
- val = xmlURIEscapeStr(uptr, BAD_CAST "/;&=+$,");
- goto done;
- }
- /*
- * Allocate just enough space for the returned string -
- * length of the remainder of the URI, plus enough space
- * for the "../" groups, plus one for the terminator
- */
- val = (xmlChar *) xmlMalloc (len + 3 * nbslash);
- if (val == NULL) {
- xmlURIErrMemory("building relative URI\n");
- goto done;
- }
- vptr = val;
- /*
- * Put in as many "../" as needed
- */
- for (; nbslash>0; nbslash--) {
- *vptr++ = '.';
- *vptr++ = '.';
- *vptr++ = '/';
- }
- /*
- * Finish up with the end of the URI
- */
- if (uptr != NULL) {
- if ((vptr > val) && (len > 0) &&
- (uptr[0] == '/') && (vptr[-1] == '/')) {
- memcpy (vptr, uptr + 1, len - 1);
- vptr[len - 2] = 0;
- } else {
- memcpy (vptr, uptr, len);
- vptr[len - 1] = 0;
- }
- } else {
- vptr[len - 1] = 0;
- }
- /* escape the freshly-built path */
- vptr = val;
- /* exception characters from xmlSaveUri */
- val = xmlURIEscapeStr(vptr, BAD_CAST "/;&=+$,");
- xmlFree(vptr);
- done:
- /*
- * Free the working variables
- */
- if (remove_path != 0)
- ref->path = NULL;
- if (ref != NULL)
- xmlFreeURI (ref);
- if (bas != NULL)
- xmlFreeURI (bas);
- return val;
- }
- /**
- * xmlCanonicPath:
- * @path: the resource locator in a filesystem notation
- *
- * Constructs a canonic path from the specified path.
- *
- * Returns a new canonic path, or a duplicate of the path parameter if the
- * construction fails. The caller is responsible for freeing the memory occupied
- * by the returned string. If there is insufficient memory available, or the
- * argument is NULL, the function returns NULL.
- */
- #define IS_WINDOWS_PATH(p) \
- ((p != NULL) && \
- (((p[0] >= 'a') && (p[0] <= 'z')) || \
- ((p[0] >= 'A') && (p[0] <= 'Z'))) && \
- (p[1] == ':') && ((p[2] == '/') || (p[2] == '\\')))
- xmlChar *
- xmlCanonicPath(const xmlChar *path)
- {
- /*
- * For Windows implementations, additional work needs to be done to
- * replace backslashes in pathnames with "forward slashes"
- */
- #if defined(_WIN32) && !defined(__CYGWIN__)
- int len = 0;
- char *p = NULL;
- #endif
- xmlURIPtr uri;
- xmlChar *ret;
- const xmlChar *absuri;
- if (path == NULL)
- return(NULL);
- #if defined(_WIN32)
- /*
- * We must not change the backslashes to slashes if the the path
- * starts with \\?\
- * Those paths can be up to 32k characters long.
- * Was added specifically for OpenOffice, those paths can't be converted
- * to URIs anyway.
- */
- if ((path[0] == '\\') && (path[1] == '\\') && (path[2] == '?') &&
- (path[3] == '\\') )
- return xmlStrdup((const xmlChar *) path);
- #endif
- /* sanitize filename starting with // so it can be used as URI */
- if ((path[0] == '/') && (path[1] == '/') && (path[2] != '/'))
- path++;
- if ((uri = xmlParseURI((const char *) path)) != NULL) {
- xmlFreeURI(uri);
- return xmlStrdup(path);
- }
- /* Check if this is an "absolute uri" */
- absuri = xmlStrstr(path, BAD_CAST "://");
- if (absuri != NULL) {
- int l, j;
- unsigned char c;
- xmlChar *escURI;
- /*
- * this looks like an URI where some parts have not been
- * escaped leading to a parsing problem. Check that the first
- * part matches a protocol.
- */
- l = absuri - path;
- /* Bypass if first part (part before the '://') is > 20 chars */
- if ((l <= 0) || (l > 20))
- goto path_processing;
- /* Bypass if any non-alpha characters are present in first part */
- for (j = 0;j < l;j++) {
- c = path[j];
- if (!(((c >= 'a') && (c <= 'z')) || ((c >= 'A') && (c <= 'Z'))))
- goto path_processing;
- }
- /* Escape all except the characters specified in the supplied path */
- escURI = xmlURIEscapeStr(path, BAD_CAST ":/?_.#&;=");
- if (escURI != NULL) {
- /* Try parsing the escaped path */
- uri = xmlParseURI((const char *) escURI);
- /* If successful, return the escaped string */
- if (uri != NULL) {
- xmlFreeURI(uri);
- return escURI;
- }
- xmlFree(escURI);
- }
- }
- path_processing:
- /* For Windows implementations, replace backslashes with 'forward slashes' */
- #if defined(_WIN32) && !defined(__CYGWIN__)
- /*
- * Create a URI structure
- */
- uri = xmlCreateURI();
- if (uri == NULL) { /* Guard against 'out of memory' */
- return(NULL);
- }
- len = xmlStrlen(path);
- if ((len > 2) && IS_WINDOWS_PATH(path)) {
- /* make the scheme 'file' */
- uri->scheme = (char *) xmlStrdup(BAD_CAST "file");
- /* allocate space for leading '/' + path + string terminator */
- uri->path = xmlMallocAtomic(len + 2);
- if (uri->path == NULL) {
- xmlFreeURI(uri); /* Guard against 'out of memory' */
- return(NULL);
- }
- /* Put in leading '/' plus path */
- uri->path[0] = '/';
- p = uri->path + 1;
- strncpy(p, (char *) path, len + 1);
- } else {
- uri->path = (char *) xmlStrdup(path);
- if (uri->path == NULL) {
- xmlFreeURI(uri);
- return(NULL);
- }
- p = uri->path;
- }
- /* Now change all occurrences of '\' to '/' */
- while (*p != '\0') {
- if (*p == '\\')
- *p = '/';
- p++;
- }
- if (uri->scheme == NULL) {
- ret = xmlStrdup((const xmlChar *) uri->path);
- } else {
- ret = xmlSaveUri(uri);
- }
- xmlFreeURI(uri);
- #else
- ret = xmlStrdup((const xmlChar *) path);
- #endif
- return(ret);
- }
- /**
- * xmlPathToURI:
- * @path: the resource locator in a filesystem notation
- *
- * Constructs an URI expressing the existing path
- *
- * Returns a new URI, or a duplicate of the path parameter if the
- * construction fails. The caller is responsible for freeing the memory
- * occupied by the returned string. If there is insufficient memory available,
- * or the argument is NULL, the function returns NULL.
- */
- xmlChar *
- xmlPathToURI(const xmlChar *path)
- {
- xmlURIPtr uri;
- xmlURI temp;
- xmlChar *ret, *cal;
- if (path == NULL)
- return(NULL);
- if ((uri = xmlParseURI((const char *) path)) != NULL) {
- xmlFreeURI(uri);
- return xmlStrdup(path);
- }
- cal = xmlCanonicPath(path);
- if (cal == NULL)
- return(NULL);
- #if defined(_WIN32) && !defined(__CYGWIN__)
- /* xmlCanonicPath can return an URI on Windows (is that the intended behaviour?)
- If 'cal' is a valid URI already then we are done here, as continuing would make
- it invalid. */
- if ((uri = xmlParseURI((const char *) cal)) != NULL) {
- xmlFreeURI(uri);
- return cal;
- }
- /* 'cal' can contain a relative path with backslashes. If that is processed
- by xmlSaveURI, they will be escaped and the external entity loader machinery
- will fail. So convert them to slashes. Misuse 'ret' for walking. */
- ret = cal;
- while (*ret != '\0') {
- if (*ret == '\\')
- *ret = '/';
- ret++;
- }
- #endif
- memset(&temp, 0, sizeof(temp));
- temp.path = (char *) cal;
- ret = xmlSaveUri(&temp);
- xmlFree(cal);
- return(ret);
- }
- #define bottom_uri
- #include "elfgcchack.h"
|