url.cpp.svn-base

wince c++ 下 开发的 rss 阅读器源代码

/**
 *  url.cpp
 *
 *  Copyright (C) 2008  David Andrs <[e-mail]>
 *
 *  This program is free software: you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation, either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program.  If not, see <http://www.gnu.org/licenses/>.
 *
 */

#include <afxwin.h>
#include "url.h"
#include "../../share/helpers.h"
#include "../../share/str.h"
#include "../../regex/regex.h"
#include "../debug/Logger.h"
#include "HTMLFile.h"

#include <wininet.h>

#if defined PRSSR_APP

// Taken from afxint.h

static BOOL AFXAPI _ParseURLWorker(LPCTSTR pstrURL,
	LPURL_COMPONENTS lpComponents, DWORD& dwServiceType,
	INTERNET_PORT& nPort, DWORD dwFlags)
{
	// this function will return bogus stuff if lpComponents
	// isn't set up to copy the components

	ASSERT(lpComponents != NULL && pstrURL != NULL);
	if (lpComponents == NULL || pstrURL == NULL)
		return FALSE;
	ASSERT(lpComponents->dwHostNameLength == 0 ||
			lpComponents->lpszHostName != NULL);
	ASSERT(lpComponents->dwUrlPathLength == 0 ||
			lpComponents->lpszUrlPath != NULL);
	ASSERT(lpComponents->dwUserNameLength == 0 ||
			lpComponents->lpszUserName != NULL);
	ASSERT(lpComponents->dwPasswordLength == 0 ||
			lpComponents->lpszPassword != NULL);

	ASSERT(AfxIsValidAddress(lpComponents, sizeof(URL_COMPONENTS), TRUE));

	LPTSTR pstrCanonicalizedURL;
	TCHAR szCanonicalizedURL[INTERNET_MAX_URL_LENGTH];
	DWORD dwNeededLength = INTERNET_MAX_URL_LENGTH;
	BOOL bRetVal;
	BOOL bMustFree = FALSE;
	DWORD dwCanonicalizeFlags = dwFlags &
		(ICU_NO_ENCODE | ICU_DECODE | ICU_NO_META |
		ICU_ENCODE_SPACES_ONLY | ICU_BROWSER_MODE);
	DWORD dwCrackFlags = dwFlags & (ICU_ESCAPE | ICU_USERNAME);

	bRetVal = InternetCanonicalizeUrl(pstrURL, szCanonicalizedURL,
		&dwNeededLength, dwCanonicalizeFlags);

	if (!bRetVal)
	{
		if (::GetLastError() != ERROR_INSUFFICIENT_BUFFER)
			return FALSE;

		pstrCanonicalizedURL = new TCHAR[dwNeededLength];
		bMustFree = TRUE;
		bRetVal = InternetCanonicalizeUrl(pstrURL, pstrCanonicalizedURL,
			&dwNeededLength, dwCanonicalizeFlags);
		if (!bRetVal)
		{
			delete [] pstrCanonicalizedURL;
			return FALSE;
		}
	}
	else
		pstrCanonicalizedURL = szCanonicalizedURL;

	// now that it's safely canonicalized, crack it

	bRetVal = InternetCrackUrl(pstrCanonicalizedURL, 0,
						dwCrackFlags, lpComponents);
	if (bMustFree)
		delete [] pstrCanonicalizedURL;

	// convert to MFC-style service ID

	if (!bRetVal)
		dwServiceType = INET_SERVICE_UNK;
	else
	{
		nPort = lpComponents->nPort;
		switch (lpComponents->nScheme)
		{
		case INTERNET_SCHEME_FTP:
			dwServiceType = INET_SERVICE_FTP;
			break;

		case INTERNET_SCHEME_GOPHER:
			dwServiceType = INET_SERVICE_GOPHER;
			break;

		case INTERNET_SCHEME_HTTP:
			dwServiceType = INET_SERVICE_HTTP;
			break;

		case INTERNET_SCHEME_HTTPS:
			dwServiceType = INET_SERVICE_HTTPS;
			break;

		case INTERNET_SCHEME_FILE:
			dwServiceType = INET_SERVICE_FILE;
			break;

		case INTERNET_SCHEME_NEWS:
			dwServiceType = INET_SERVICE_NNTP;
			break;

		case INTERNET_SCHEME_MAILTO:
			dwServiceType = INET_SERVICE_MAILTO;
			break;

		default:
			dwServiceType = INET_SERVICE_UNK;
		}
	}

	return bRetVal;
}

BOOL AFXAPI ParseURL(LPCTSTR pstrURL, DWORD &dwServiceType, CString &strServer, CString &strObject, INTERNET_PORT &nPort) {
	dwServiceType = INET_SERVICE_UNK;

	ASSERT(pstrURL != NULL);
	if (pstrURL == NULL)
		return FALSE;

	URL_COMPONENTS urlComponents;
	memset(&urlComponents, 0, sizeof(URL_COMPONENTS));
	urlComponents.dwStructSize = sizeof(URL_COMPONENTS);

	urlComponents.dwHostNameLength = INTERNET_MAX_URL_LENGTH;
	urlComponents.lpszHostName = strServer.GetBuffer(INTERNET_MAX_URL_LENGTH+1);
	urlComponents.dwUrlPathLength = INTERNET_MAX_URL_LENGTH;
	urlComponents.lpszUrlPath = strObject.GetBuffer(INTERNET_MAX_URL_LENGTH+1);

	BOOL bRetVal = _ParseURLWorker(pstrURL, &urlComponents, dwServiceType, nPort, ICU_BROWSER_MODE);

	strServer.ReleaseBuffer();
	strObject.ReleaseBuffer();
	return bRetVal;
}

////

CString SanitizeUrl(const CString &url) {
	int nPos = url.Find(_T("://"));
	if (nPos != -1) {
		int nEndPos = url.Find(_T("/"), nPos + 3);

		CString sServer;
		if (nEndPos != -1)
			sServer = url.Mid(nPos + 3, nEndPos - nPos - 3);
		else
			sServer = url.Mid(nPos + 3);
		sServer.MakeLower();

		return url.Left(nPos + 3) + sServer + url.Mid(nEndPos);
	}
	else
		return url;
}

//
//
//
CString GetURLFilePath(const CString &strObject) {
	CString strObj;
	int qmarkPos = strObject.Find('?');
	if (qmarkPos != -1)
		strObj = strObject.Left(qmarkPos);
	else
		strObj = strObject;

	int slashPos = strObj.ReverseFind('/');
	CString strPath = strObj.Left(slashPos + 1);
//	if (strPath.GetLength() > 0 && strPath.GetAt(strPath.GetLength() - 1) != '/')
//		strPath += '/';

	return strPath;
}

CString GetUrlFileName(const CString &strUrl) {
	CString strObj;
	int qmarkPos = strUrl.Find('?');
	if (qmarkPos != -1)
		strObj = strUrl.Left(qmarkPos);
	else
		strObj = strUrl;

	int slashPos = strObj.ReverseFind('/');
	CString strPath = strObj.Mid(slashPos + 1);

	return strPath;
}

/*BOOL ParseURL(const CString &url, CString &strServer, CString &strObject) {
	LOG1(5, "ParseURL('%S')", url);

	DWORD dwServiceType;
	INTERNET_PORT nPort;

	AfxParseURL(url, dwServiceType, strServer, strObject, nPort);

	return TRUE;
}
*/

//
// Translates url to file path (<root>/<sever>/<object>)
//
CString UrlToFileName(const CString &url, BOOL addHTMLExt/* = FALSE*/) {
	LOG1(5, "UrlToFileName('%S')", url);

	if (url.Left(7).CompareNoCase(_T("file://")) == 0) {
		CString fileName = url.Mid(7);
		fileName.Replace('/', '\\');
		return fileName;
	}

	DWORD serviceType;
	INTERNET_PORT port;
	CString strServer, strObject;
	ParseURL(url, serviceType, strServer, strObject, port);

	// remove #text
	int hashPos = strObject.ReverseFind('#');
	CString strHash;
	if (hashPos != -1) {
		strHash = strObject.Right(strObject.GetLength() - hashPos);
		strObject = strObject.Left(hashPos);
	}

	CString strPath = GetURLFilePath(strObject);
	CString strFileName = strObject.Right(strObject.GetLength() - strPath.GetLength());

	// get params
	int qmPos = strFileName.ReverseFind('?');
	CString strPars;
	if (qmPos != -1) {
		strPars = strFileName.Right(strFileName.GetLength() - qmPos);
		strFileName = strFileName.Left(qmPos);
	}

	int dotPos = strFileName.ReverseFind('.');
	CString strExt;
	if (dotPos != -1) {
		strExt = strFileName.Right(strFileName.GetLength() - dotPos);
		strFileName = strFileName.Left(dotPos);
	}

	if (strFileName.GetLength() == 0) {
		strFileName = _T("index");
		strExt = _T(".html");
	}

	// add html extension to files, which have none (to open in Pocket IE successfully)
	if (addHTMLExt) {
		if (strExt.CompareNoCase(_T(".html")) != 0 && strExt.CompareNoCase(_T(".htm")) != 0)
			strExt = _T(".html");		// add html one
	}

	//
	strPars.Replace('?', '_');
	strPars.Replace(',', '_');
	strPars.Remove('/');
	strPars.Remove('\\');

//	strFileName += strHash;

	strPath.Replace('/', '\\');

	CString strFileNamePath;
	strFileNamePath.Format(_T("%s%s%s%s%s"), strServer, strPath, strFileName, strPars, strExt);

	strFileNamePath.Remove('&');
	strFileNamePath.Remove('=');
	strFileNamePath.Remove('%');
	strFileNamePath.Remove('\'');
	strFileNamePath.Remove('"');
	strFileNamePath.Remove(';');
	strFileNamePath.Remove(':');

	// truncate the file name to MAX_PATH (limit for filenames), because some URLs are longer than MAX_PATH
	strFileNamePath = strFileNamePath.Left(MAX_PATH - 10);

	return strFileNamePath;
}


CString MakeAbsoluteUrl(const CString &url, const CString &strServer, const CString &strPath) {
	LOG1(5, "MakeAbsoluteUrl('%S')", url);

	CString strAbsUrl;

	if (url.Left(7).CompareNoCase(_T("http://")) == 0 ||
		url.Left(8).CompareNoCase(_T("https://")) == 0 ||
		url.Left(7).CompareNoCase(_T("file://")) == 0) {
		// absolute link
		strAbsUrl = url;
	}
	else {
		// relative link
		if (url.GetLength() > 0 && url.GetAt(0) == '/')
			strAbsUrl.Format(_T("http://%s%s"), strServer, url);
		else
			strAbsUrl.Format(_T("http://%s%s%s"), strServer, strPath, url);
	}

	return strAbsUrl;
}


//
// Creates url for offline browsing in form (file://<url>)
// Keeps #part
//
CString MakeOfflineUrl(const CString &strRootDir, const CString &strFileName) {
	LOG0(5, "MakeOfflineUrl()");

	CString strOfflineUrl;
	strOfflineUrl.Format(_T("file://localhost%s/%s"), strRootDir, strFileName);
	strOfflineUrl.Replace('\\', '/');

	return strOfflineUrl;
}

CString MakeOfflineUrl(const CString &strFileName) {
	LOG0(5, "MakeOfflineUrl()");

	CString strOfflineUrl;
	strOfflineUrl.Format(_T("file://localhost%s"), strFileName);
	strOfflineUrl.Replace('\\', '/');

	return strOfflineUrl;
}

/*
//
// Create file url from object (#part is removed)
// For caching purposes
//
CString MakeOnlineFile(const CString &strObject, const CString &strServer, const CString &strActivePath) {
	LOG0(5, "MakeOnlineFile()");

	CString strAbsUrl;
	if (strObject.Left(7).Compare(_T("file://")) == 0)
		strAbsUrl = strObject;
	else
		strAbsUrl = MakeAbsoluteUrl(strObject, strServer, strActivePath);

	CString strObjectFileName;
	int hashPos = strAbsUrl.ReverseFind('#');
	if (hashPos != -1)
		strObjectFileName = strAbsUrl.Left(hashPos);
	else
		strObjectFileName = strAbsUrl;

	return strObjectFileName;
}
*/


//
// Rewrite URL
//
CString RewriteUrl(const CString &sUrl, CArray<CRewriteRule *, CRewriteRule *> &rules) {
	LOG1(5, "RewriteUrl('%S', )", sUrl);

	CString newUrl = sUrl;
	char *url = WCharToChar(sUrl, CP_ACP);

	BOOL found = FALSE;
	for (int i = 0; i < rules.GetSize() && !found; i++) {