From 6d05f3e01a26fa416c9d0150163db20abac4b4ef Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=B6rg=20Frings-F=C3=BCrst?= Date: Wed, 21 Mar 2018 22:11:05 +0100 Subject: New upstream version 0.8.5 --- doc/Mainpage.txt | 343 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 343 insertions(+) create mode 100644 doc/Mainpage.txt (limited to 'doc/Mainpage.txt') diff --git a/doc/Mainpage.txt b/doc/Mainpage.txt new file mode 100644 index 0000000..3a80e30 --- /dev/null +++ b/doc/Mainpage.txt @@ -0,0 +1,343 @@ +/** + * @mainpage + * + * @section SEC_TOC Table of Contents + * - Introduction + * - Algorithms and Examples + * - Parsing URIs (from string to object) + * - Recomposing URIs (from object back to string) + * - Resolving References + * - Creating References + * - Filenames and URIs + * - Normalizing URIs + * - Working with query strings + * - Ansi and Unicode + * - Autoconf Check + * + * + * @section intro Introduction + * Welcome to the short uriparser integration tutorial. + * It is intended to answer upcoming questions and to shed light + * where function prototypes alone are not enough. + * Please drop me a line if you need further assistance and I will + * see what I can do for you. Good luck with uriparser! + * + * + * @subsection parsing Parsing URIs (from string to object) + * Parsing a URI with uriparser looks like this: + * + * @code + * UriParserStateA state; + * UriUriA uri; + * + * state.uri = &uri; + * if (uriParseUriA(&state, "file:///home/user/song.mp3") != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * uriFreeUriMembersA(&uri); + * ... + * } + * ... + * uriFreeUriMembersA(&uri); + * @endcode + * + * While the URI object (::UriUriA) holds information about the recogized + * parts of the given URI string, the parser state object (::UriParserStateA) + * keeps error code and position. This information does not belong to + * the URI itself, which is why there are two seperate objects. + * + * You can reuse parser state objects for parsing several URIs like this: + * + * @code + * UriParserStateA state; + * UriUriA uriOne; + * UriUriA uriTwo; + * + * state.uri = &uriOne; + * if (uriParseUriA(&state, "file:///home/user/one") != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * uriFreeUriMembersA(&uriOne); + * ... + * } + * ... + * state.uri = &uriTwo; + * if (uriParseUriA(&state, "file:///home/user/two") != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * uriFreeUriMembersA(&uriOne); + * uriFreeUriMembersA(&uriTwo); + * ... + * } + * ... + * uriFreeUriMembersA(&uriOne); + * uriFreeUriMembersA(&uriTwo); + * @endcode + * + * + * @subsection recomposition Recomposing URIs (from object back to string) + * According to RFC 3986 + * glueing parts of a URI together to form a string is called recomposition. + * Before we can recompose a URI object we have to know how much + * space the resulting string will take: + * + * @code + * UriUriA uri; + * char * uriString; + * int charsRequired; + * ... + * if (uriToStringCharsRequiredA(&uri, &charsRequired) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * ... + * } + * charsRequired++; + * @endcode + * + * Now we can tell uriToStringA() to write the string to a given buffer: + * + * @code + * uriString = malloc(charsRequired * sizeof(char)); + * if (uriString == NULL) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * ... + * } + * if (uriToStringA(uriString, &uri, charsRequired, NULL) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * ... + * } + * @endcode + * + * @remarks + * Incrementing charsRequired by 1 is required since + * uriToStringCharsRequiredA() returns the length of the string + * as strlen() does, but uriToStringA() works with the number + * of maximum characters to be written including the + * zero-terminator. + * + * + * @subsection resolution Resolving References + * Reference Resolution + * is the process of turning a (relative) URI reference into an absolute URI by applying a base + * URI to it. In code it looks like this: + * + * @code + * UriUriA absoluteDest; + * UriUriA relativeSource; + * UriUriA absoluteBase; + * ... + * /COMMENT_HACK* relativeSource holds "../TWO" now *COMMENT_HACK/ + * /COMMENT_HACK* absoluteBase holds "file:///one/two/three" now *COMMENT_HACK/ + * if (uriAddBaseUriA(&absoluteDest, &relativeSource, &absoluteBase) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * uriFreeUriMembersA(&absoluteDest); + * ... + * } + * /COMMENT_HACK* absoluteDest holds "file:///one/TWO" now *COMMENT_HACK/ + * ... + * uriFreeUriMembersA(&absoluteDest); + * @endcode + * + * @remarks + * uriAddBaseUriA() does not normalize the resulting URI. + * Usually you might want to pass it through uriNormalizeSyntaxA() after. + * + * + * @subsection shortening Creating References + * Reference Creation is the inverse process of Reference Resolution: A common base URI + * is "substracted" from an absolute URI to make a (relative) reference. + * If the base URI is not common the remaining URI will still be absolute, i.e. will + * carry a scheme + * + * @code + * UriUriA dest; + * UriUriA absoluteSource; + * UriUriA absoluteBase; + * ... + * /COMMENT_HACK* absoluteSource holds "file:///one/TWO" now *COMMENT_HACK/ + * /COMMENT_HACK* absoluteBase holds "file:///one/two/three" now *COMMENT_HACK/ + * if (uriRemoveBaseUriA(&dest, &absoluteSource, &absoluteBase, URI_FALSE) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * uriFreeUriMembersA(&dest); + * ... + * } + * /COMMENT_HACK* dest holds "../TWO" now *COMMENT_HACK/ + * ... + * uriFreeUriMembersA(&dest); + * @endcode + * + * The fourth parameter is the domain root mode. With URI_FALSE as above this will produce + * URIs relative to the base URI. With URI_TRUE the resulting URI will be relative to the + * domain root instead, e.g. "/one/TWO" in this case. + * + * + * @subsection filenames Filenames and URIs + * Converting filenames to and from URIs works on strings directly, + * i.e. without creating an URI object. + * + * @code + * const char * const absFilename = "E:\\Documents and Settings"; + * const int bytesNeeded = 8 + 3 * strlen(absFilename) + 1; + * char * absUri = malloc(bytesNeeded * sizeof(char)); + * if (uriWindowsFilenameToUriStringA(absFilename, absUri) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * free(absUri); + * ... + * } + * /COMMENT_HACK* absUri is "file:///E:/Documents%20and%20Settings" now *COMMENT_HACK/ + * ... + * free(absUri); + * @endcode + * + * Conversion works .. + * - for relative or absolute values, + * - in both directions (filenames <--> URIs) and + * - with Unix and Windows filenames. + * + * All you have to do is to choose the right function for the task and allocate + * the required space (in characters) for the target buffer. + * Let me present you an overview: + * + * - Filename --> URI + * - uriUnixFilenameToUriStringA()\n + * Space required: [7 +] 3 * len(filename) + 1 + * - uriWindowsFilenameToUriStringA()\n + * Space required: [8 +] 3 * len(filename) + 1 + * - URI --> filename + * - uriUriStringToUnixFilenameA()\n + * Space required: len(uriString) + 1 [- 7] + * - uriUriStringToWindowsFilenameA()\n + * Space required: len(uriString) + 1 [- 8] + * + * + * @subsection normalization Normalizing URIs + * Sometimes we come accross unnecessarily long URIs like "http://example.org/one/two/../../one". + * The algorithm we can use to shorten this URI down to "http://example.org/one" is called + * Syntax-Based Normalization. + * Note that normalizing a URI does more than just "stripping dot segments". Please have a look at + * Section 6.2.2 of RFC 3986 + * for the full description. + * + * As we asked uriToStringCharsRequiredA() for the required space when converting + * a URI object back to a sring, we can ask uriNormalizeSyntaxMaskRequiredA() for + * the parts of a URI that require normalization and then pass this normalization + * mask to uriNormalizeSyntaxExA(): + * + * @code + * const unsigned int dirtyParts = uriNormalizeSyntaxMaskRequiredA(&uri); + * if (uriNormalizeSyntaxExA(&uri, dirtyParts) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * ... + * } + * @endcode + * + * If you don't want to normalize all parts of the URI you can pass a custom + * mask as well: + * + * @code + * const unsigned int normMask = URI_NORMALIZE_SCHEME | URI_NORMALIZE_USER_INFO; + * if (uriNormalizeSyntaxExA(&uri, normMask) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * ... + * } + * @endcode + * + * Please see ::UriNormalizationMaskEnum for the complete set of flags. + * + * On the other hand calling plain uriNormalizeSyntaxA() (without the "Ex") + * saves you thinking about single parts, as it queries uriNormalizeSyntaxMaskRequiredA() + * internally: + * + * @code + * if (uriNormalizeSyntaxA(&uri) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * ... + * } + * @endcode + * + * + * @section querystrings Working with query strings + * RFC 3986 + * itself does not understand the query part of a URI as a list of key/value pairs. + * But HTML 2.0 does and defines a media type application/x-www-form-urlencoded + * in in section 8.2.1 + * of RFC 1866. + * uriparser allows you to dissect (or parse) a query string into unescaped key/value pairs + * and back. + * + * To dissect the query part of a just-parsed URI you could write code like this: + * + * @code + * UriUriA uri; + * UriQueryListA * queryList; + * int itemCount; + * ... + * if (uriDissectQueryMallocA(&queryList, &itemCount, uri.query.first, + * uri.query.afterLast) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * ... + * } + * ... + * uriFreeQueryListA(queryList); + * @endcode + * + * @remarks + * - NULL in the value member means there was no '=' in the item text as with "?abc&def". + * - An empty string in the value member means there was '=' in the item as with "?abc=&def". + * + * + * To compose a query string from a query list you could write code like this: + * + * @code + * int charsRequired; + * int charsWritten; + * char * queryString; + * ... + * if (uriComposeQueryCharsRequiredA(queryList, &charsRequired) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * ... + * } + * queryString = malloc((charsRequired + 1) * sizeof(char)); + * if (queryString == NULL) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * ... + * } + * if (uriComposeQueryA(queryString, queryList, charsRequired + 1, &charsWritten) != URI_SUCCESS) { + * /COMMENT_HACK* Failure *COMMENT_HACK/ + * ... + * } + * ... + * free(queryString); + * @endcode + * + * + * @section chartypes Ansi and Unicode + * uriparser comes with two versions of every structure and function: + * one handling Ansi text (char *) and one working with Unicode text (wchar_t *), + * for instance + * - uriParseUriA() for Ansi and + * - uriParseUriW() for Unicode. + * + * This tutorial only shows the usage of the Ansi editions but + * their Unicode counterparts work in the very same way. + * + * + * @section autoconf Autoconf Check + * You can use the code below to make ./configure test for presence + * of uriparser 0.6.4 or later. + * + *
URIPARSER_MISSING="Please install uriparser 0.6.4 or later.
+ *   On a Debian-based system enter 'sudo apt-get install liburiparser-dev'."
+ *AC_CHECK_LIB(uriparser, uriParseUriA,, AC_MSG_ERROR(${URIPARSER_MISSING}))
+ *AC_CHECK_HEADER(uriparser/Uri.h,, AC_MSG_ERROR(${URIPARSER_MISSING}))
+ *
+ *URIPARSER_TOO_OLD="uriparser 0.6.4 or later is required, your copy is too old."
+ *AC_COMPILE_IFELSE([
+ *\#include 
+ *\#if (defined(URI_VER_MAJOR) && defined(URI_VER_MINOR) && defined(URI_VER_RELEASE) \\
+ *&& ((URI_VER_MAJOR > 0) \\
+ *|| ((URI_VER_MAJOR == 0) && (URI_VER_MINOR > 6)) \\
+ *|| ((URI_VER_MAJOR == 0) && (URI_VER_MINOR == 6) && (URI_VER_RELEASE >= 4)) \\
+ *))
+ */* FINE */
+ *\#else
+ *\# error uriparser not recent enough
+ *\#endif
+ *],,AC_MSG_ERROR(${URIPARSER_TOO_OLD}))
+ */ -- cgit v1.2.3