From 886e5076c8e81fd0cdfe82dbf4a80d19e778d594 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=B6rg=20Frings-F=C3=BCrst?= Date: Wed, 6 Aug 2014 18:24:22 +0200 Subject: Imported Upstream version 0.8.0.1 --- src/UriCommon.c | 531 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 531 insertions(+) create mode 100644 src/UriCommon.c (limited to 'src/UriCommon.c') diff --git a/src/UriCommon.c b/src/UriCommon.c new file mode 100644 index 0000000..c33a4ca --- /dev/null +++ b/src/UriCommon.c @@ -0,0 +1,531 @@ +/* + * uriparser - RFC 3986 URI parsing library + * + * Copyright (C) 2007, Weijia Song + * Copyright (C) 2007, Sebastian Pipping + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * * Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * * Neither the name of the nor the names of its + * contributors may be used to endorse or promote products + * derived from this software without specific prior written + * permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + * COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR + * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, + * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED + * OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +/* What encodings are enabled? */ +#include +#if (!defined(URI_PASS_ANSI) && !defined(URI_PASS_UNICODE)) +/* Include SELF twice */ +# ifdef URI_ENABLE_ANSI +# define URI_PASS_ANSI 1 +# include "UriCommon.c" +# undef URI_PASS_ANSI +# endif +# ifdef URI_ENABLE_UNICODE +# define URI_PASS_UNICODE 1 +# include "UriCommon.c" +# undef URI_PASS_UNICODE +# endif +#else +# ifdef URI_PASS_ANSI +# include +# else +# include +# include +# endif + + + +#ifndef URI_DOXYGEN +# include +# include "UriCommon.h" +#endif + + + +/*extern*/ const URI_CHAR * const URI_FUNC(SafeToPointTo) = _UT("X"); +/*extern*/ const URI_CHAR * const URI_FUNC(ConstPwd) = _UT("."); +/*extern*/ const URI_CHAR * const URI_FUNC(ConstParent) = _UT(".."); + + + +void URI_FUNC(ResetUri)(URI_TYPE(Uri) * uri) { + memset(uri, 0, sizeof(URI_TYPE(Uri))); +} + + + +/* Properly removes "." and ".." path segments */ +UriBool URI_FUNC(RemoveDotSegments)(URI_TYPE(Uri) * uri, + UriBool relative) { + if (uri == NULL) { + return URI_TRUE; + } + return URI_FUNC(RemoveDotSegmentsEx)(uri, relative, uri->owner); +} + + + +UriBool URI_FUNC(RemoveDotSegmentsEx)(URI_TYPE(Uri) * uri, + UriBool relative, UriBool pathOwned) { + URI_TYPE(PathSegment) * walker; + if ((uri == NULL) || (uri->pathHead == NULL)) { + return URI_TRUE; + } + + walker = uri->pathHead; + walker->reserved = NULL; /* Prev pointer */ + do { + UriBool removeSegment = URI_FALSE; + int len = (int)(walker->text.afterLast - walker->text.first); + switch (len) { + case 1: + if ((walker->text.first)[0] == _UT('.')) { + /* "." segment -> remove if not essential */ + URI_TYPE(PathSegment) * const prev = walker->reserved; + URI_TYPE(PathSegment) * const nextBackup = walker->next; + + /* Is this dot segment essential? */ + removeSegment = URI_TRUE; + if (relative && (walker == uri->pathHead) && (walker->next != NULL)) { + const URI_CHAR * ch = walker->next->text.first; + for (; ch < walker->next->text.afterLast; ch++) { + if (*ch == _UT(':')) { + removeSegment = URI_FALSE; + break; + } + } + } + + if (removeSegment) { + /* Last segment? */ + if (walker->next != NULL) { + /* Not last segment */ + walker->next->reserved = prev; + + if (prev == NULL) { + /* First but not last segment */ + uri->pathHead = walker->next; + } else { + /* Middle segment */ + prev->next = walker->next; + } + + if (pathOwned && (walker->text.first != walker->text.afterLast)) { + free((URI_CHAR *)walker->text.first); + } + free(walker); + } else { + /* Last segment */ + if (pathOwned && (walker->text.first != walker->text.afterLast)) { + free((URI_CHAR *)walker->text.first); + } + + if (prev == NULL) { + /* Last and first */ + if (URI_FUNC(IsHostSet)(uri)) { + /* Replace "." with empty segment to represent trailing slash */ + walker->text.first = URI_FUNC(SafeToPointTo); + walker->text.afterLast = URI_FUNC(SafeToPointTo); + } else { + free(walker); + + uri->pathHead = NULL; + uri->pathTail = NULL; + } + } else { + /* Last but not first, replace "." with empty segment to represent trailing slash */ + walker->text.first = URI_FUNC(SafeToPointTo); + walker->text.afterLast = URI_FUNC(SafeToPointTo); + } + } + + walker = nextBackup; + } + } + break; + + case 2: + if (((walker->text.first)[0] == _UT('.')) + && ((walker->text.first)[1] == _UT('.'))) { + /* Path ".." -> remove this and the previous segment */ + URI_TYPE(PathSegment) * const prev = walker->reserved; + URI_TYPE(PathSegment) * prevPrev; + URI_TYPE(PathSegment) * const nextBackup = walker->next; + + removeSegment = URI_TRUE; + if (relative) { + if (prev == NULL) { + removeSegment = URI_FALSE; + } else if ((prev != NULL) + && ((prev->text.afterLast - prev->text.first) == 2) + && ((prev->text.first)[0] == _UT('.')) + && ((prev->text.first)[1] == _UT('.'))) { + removeSegment = URI_FALSE; + } + } + + if (removeSegment) { + if (prev != NULL) { + /* Not first segment */ + prevPrev = prev->reserved; + if (prevPrev != NULL) { + /* Not even prev is the first one */ + prevPrev->next = walker->next; + if (walker->next != NULL) { + walker->next->reserved = prevPrev; + } else { + /* Last segment -> insert "" segment to represent trailing slash, update tail */ + URI_TYPE(PathSegment) * const segment = malloc(1 * sizeof(URI_TYPE(PathSegment))); + if (segment == NULL) { + if (pathOwned && (walker->text.first != walker->text.afterLast)) { + free((URI_CHAR *)walker->text.first); + } + free(walker); + + if (pathOwned && (prev->text.first != prev->text.afterLast)) { + free((URI_CHAR *)prev->text.first); + } + free(prev); + + return URI_FALSE; /* Raises malloc error */ + } + memset(segment, 0, sizeof(URI_TYPE(PathSegment))); + segment->text.first = URI_FUNC(SafeToPointTo); + segment->text.afterLast = URI_FUNC(SafeToPointTo); + prevPrev->next = segment; + uri->pathTail = segment; + } + + if (pathOwned && (walker->text.first != walker->text.afterLast)) { + free((URI_CHAR *)walker->text.first); + } + free(walker); + + if (pathOwned && (prev->text.first != prev->text.afterLast)) { + free((URI_CHAR *)prev->text.first); + } + free(prev); + + walker = nextBackup; + } else { + /* Prev is the first segment */ + if (walker->next != NULL) { + uri->pathHead = walker->next; + walker->next->reserved = NULL; + + if (pathOwned && (walker->text.first != walker->text.afterLast)) { + free((URI_CHAR *)walker->text.first); + } + free(walker); + } else { + /* Re-use segment for "" path segment to represent trailing slash, update tail */ + URI_TYPE(PathSegment) * const segment = walker; + if (pathOwned && (segment->text.first != segment->text.afterLast)) { + free((URI_CHAR *)segment->text.first); + } + segment->text.first = URI_FUNC(SafeToPointTo); + segment->text.afterLast = URI_FUNC(SafeToPointTo); + uri->pathHead = segment; + uri->pathTail = segment; + } + + if (pathOwned && (prev->text.first != prev->text.afterLast)) { + free((URI_CHAR *)prev->text.first); + } + free(prev); + + walker = nextBackup; + } + } else { + URI_TYPE(PathSegment) * const anotherNextBackup = walker->next; + /* First segment -> update head pointer */ + uri->pathHead = walker->next; + if (walker->next != NULL) { + walker->next->reserved = NULL; + } else { + /* Last segment -> update tail */ + uri->pathTail = NULL; + } + + if (pathOwned && (walker->text.first != walker->text.afterLast)) { + free((URI_CHAR *)walker->text.first); + } + free(walker); + + walker = anotherNextBackup; + } + } + } + break; + + } + + if (!removeSegment) { + if (walker->next != NULL) { + walker->next->reserved = walker; + } else { + /* Last segment -> update tail */ + uri->pathTail = walker; + } + walker = walker->next; + } + } while (walker != NULL); + + return URI_TRUE; +} + + + +/* Properly removes "." and ".." path segments */ +UriBool URI_FUNC(RemoveDotSegmentsAbsolute)(URI_TYPE(Uri) * uri) { + const UriBool ABSOLUTE = URI_FALSE; + return URI_FUNC(RemoveDotSegments)(uri, ABSOLUTE); +} + + + +unsigned char URI_FUNC(HexdigToInt)(URI_CHAR hexdig) { + switch (hexdig) { + case _UT('0'): + case _UT('1'): + case _UT('2'): + case _UT('3'): + case _UT('4'): + case _UT('5'): + case _UT('6'): + case _UT('7'): + case _UT('8'): + case _UT('9'): + return (unsigned char)(9 + hexdig - _UT('9')); + + case _UT('a'): + case _UT('b'): + case _UT('c'): + case _UT('d'): + case _UT('e'): + case _UT('f'): + return (unsigned char)(15 + hexdig - _UT('f')); + + case _UT('A'): + case _UT('B'): + case _UT('C'): + case _UT('D'): + case _UT('E'): + case _UT('F'): + return (unsigned char)(15 + hexdig - _UT('F')); + + default: + return 0; + } +} + + + +URI_CHAR URI_FUNC(HexToLetter)(unsigned int value) { + /* Uppercase recommended in section 2.1. of RFC 3986 * + * http://tools.ietf.org/html/rfc3986#section-2.1 */ + return URI_FUNC(HexToLetterEx)(value, URI_TRUE); +} + + + +URI_CHAR URI_FUNC(HexToLetterEx)(unsigned int value, UriBool uppercase) { + switch (value) { + case 0: return _UT('0'); + case 1: return _UT('1'); + case 2: return _UT('2'); + case 3: return _UT('3'); + case 4: return _UT('4'); + case 5: return _UT('5'); + case 6: return _UT('6'); + case 7: return _UT('7'); + case 8: return _UT('8'); + case 9: return _UT('9'); + + case 10: return (uppercase == URI_TRUE) ? _UT('A') : _UT('a'); + case 11: return (uppercase == URI_TRUE) ? _UT('B') : _UT('b'); + case 12: return (uppercase == URI_TRUE) ? _UT('C') : _UT('c'); + case 13: return (uppercase == URI_TRUE) ? _UT('D') : _UT('d'); + case 14: return (uppercase == URI_TRUE) ? _UT('E') : _UT('e'); + default: return (uppercase == URI_TRUE) ? _UT('F') : _UT('f'); + } +} + + + +/* Checks if a URI has the host component set. */ +UriBool URI_FUNC(IsHostSet)(const URI_TYPE(Uri) * uri) { + return (uri != NULL) + && ((uri->hostText.first != NULL) + || (uri->hostData.ip4 != NULL) + || (uri->hostData.ip6 != NULL) + || (uri->hostData.ipFuture.first != NULL) + ); +} + + + +/* Copies the path segment list from one URI to another. */ +UriBool URI_FUNC(CopyPath)(URI_TYPE(Uri) * dest, + const URI_TYPE(Uri) * source) { + if (source->pathHead == NULL) { + /* No path component */ + dest->pathHead = NULL; + dest->pathTail = NULL; + } else { + /* Copy list but not the text contained */ + URI_TYPE(PathSegment) * sourceWalker = source->pathHead; + URI_TYPE(PathSegment) * destPrev = NULL; + do { + URI_TYPE(PathSegment) * cur = malloc(sizeof(URI_TYPE(PathSegment))); + if (cur == NULL) { + /* Fix broken list */ + if (destPrev != NULL) { + destPrev->next = NULL; + } + return URI_FALSE; /* Raises malloc error */ + } + + /* From this functions usage we know that * + * the dest URI cannot be uri->owner */ + cur->text = sourceWalker->text; + if (destPrev == NULL) { + /* First segment ever */ + dest->pathHead = cur; + } else { + destPrev->next = cur; + } + destPrev = cur; + sourceWalker = sourceWalker->next; + } while (sourceWalker != NULL); + dest->pathTail = destPrev; + dest->pathTail->next = NULL; + } + + dest->absolutePath = source->absolutePath; + return URI_TRUE; +} + + + +/* Copies the authority part of an URI over to another. */ +UriBool URI_FUNC(CopyAuthority)(URI_TYPE(Uri) * dest, + const URI_TYPE(Uri) * source) { + /* From this functions usage we know that * + * the dest URI cannot be uri->owner */ + + /* Copy userInfo */ + dest->userInfo = source->userInfo; + + /* Copy hostText */ + dest->hostText = source->hostText; + + /* Copy hostData */ + if (source->hostData.ip4 != NULL) { + dest->hostData.ip4 = malloc(sizeof(UriIp4)); + if (dest->hostData.ip4 == NULL) { + return URI_FALSE; /* Raises malloc error */ + } + *(dest->hostData.ip4) = *(source->hostData.ip4); + dest->hostData.ip6 = NULL; + dest->hostData.ipFuture.first = NULL; + dest->hostData.ipFuture.afterLast = NULL; + } else if (source->hostData.ip6 != NULL) { + dest->hostData.ip4 = NULL; + dest->hostData.ip6 = malloc(sizeof(UriIp6)); + if (dest->hostData.ip6 == NULL) { + return URI_FALSE; /* Raises malloc error */ + } + *(dest->hostData.ip6) = *(source->hostData.ip6); + dest->hostData.ipFuture.first = NULL; + dest->hostData.ipFuture.afterLast = NULL; + } else { + dest->hostData.ip4 = NULL; + dest->hostData.ip6 = NULL; + dest->hostData.ipFuture = source->hostData.ipFuture; + } + + /* Copy portText */ + dest->portText = source->portText; + + return URI_TRUE; +} + + + +UriBool URI_FUNC(FixAmbiguity)(URI_TYPE(Uri) * uri) { + URI_TYPE(PathSegment) * segment; + + if ( /* Case 1: absolute path, empty first segment */ + (uri->absolutePath + && (uri->pathHead != NULL) + && (uri->pathHead->text.afterLast == uri->pathHead->text.first)) + + /* Case 2: relative path, empty first and second segment */ + || (!uri->absolutePath + && (uri->pathHead != NULL) + && (uri->pathHead->next != NULL) + && (uri->pathHead->text.afterLast == uri->pathHead->text.first) + && (uri->pathHead->next->text.afterLast == uri->pathHead->next->text.first))) { + /* NOOP */ + } else { + return URI_TRUE; + } + + segment = malloc(1 * sizeof(URI_TYPE(PathSegment))); + if (segment == NULL) { + return URI_FALSE; /* Raises malloc error */ + } + + /* Insert "." segment in front */ + segment->next = uri->pathHead; + segment->text.first = URI_FUNC(ConstPwd); + segment->text.afterLast = URI_FUNC(ConstPwd) + 1; + uri->pathHead = segment; + return URI_TRUE; +} + + + +void URI_FUNC(FixEmptyTrailSegment)(URI_TYPE(Uri) * uri) { + /* Fix path if only one empty segment */ + if (!uri->absolutePath + && !URI_FUNC(IsHostSet)(uri) + && (uri->pathHead != NULL) + && (uri->pathHead->next == NULL) + && (uri->pathHead->text.first == uri->pathHead->text.afterLast)) { + free(uri->pathHead); + uri->pathHead = NULL; + uri->pathTail = NULL; + } +} + + + +#endif -- cgit v1.2.3