1 /* 2 * Copyright (C) 2009 Google Inc. All rights reserved. 3 * 4 * Redistribution and use in source and binary forms, with or without 5 * modification, are permitted provided that the following conditions are 6 * met: 7 * 8 * * Redistributions of source code must retain the above copyright 9 * notice, this list of conditions and the following disclaimer. 10 * * Redistributions in binary form must reproduce the above 11 * copyright notice, this list of conditions and the following disclaimer 12 * in the documentation and/or other materials provided with the 13 * distribution. 14 * * Neither the name of Google Inc. nor the names of its 15 * contributors may be used to endorse or promote products derived from 16 * this software without specific prior written permission. 17 * 18 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 19 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 20 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR 21 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT 22 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 23 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT 24 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, 25 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY 26 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 27 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 28 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 29 */ 30 31 #include "config.h" 32 #include "WebSearchableFormData.h" 33 34 #include "HTMLNames.h" 35 #include "WebFormElement.h" 36 #include "WebInputElement.h" 37 #include "core/dom/Document.h" 38 #include "core/html/FormDataList.h" 39 #include "core/html/HTMLFormControlElement.h" 40 #include "core/html/HTMLFormElement.h" 41 #include "core/html/HTMLInputElement.h" 42 #include "core/html/HTMLOptionElement.h" 43 #include "core/html/HTMLOptionsCollection.h" 44 #include "core/html/HTMLSelectElement.h" 45 #include "core/html/HTMLTextAreaElement.h" 46 #include "core/loader/DocumentLoader.h" 47 #include "core/page/Frame.h" 48 #include "core/platform/network/FormDataBuilder.h" 49 #include "wtf/text/TextEncoding.h" 50 51 using namespace WebCore; 52 using namespace HTMLNames; 53 54 namespace { 55 56 // Gets the encoding for the form. 57 void GetFormEncoding(const HTMLFormElement* form, WTF::TextEncoding* encoding) 58 { 59 String str(form->getAttribute(HTMLNames::accept_charsetAttr)); 60 str.replace(',', ' '); 61 Vector<String> charsets; 62 str.split(' ', charsets); 63 for (Vector<String>::const_iterator i(charsets.begin()); i != charsets.end(); ++i) { 64 *encoding = WTF::TextEncoding(*i); 65 if (encoding->isValid()) 66 return; 67 } 68 if (!form->document()->loader()) 69 return; 70 *encoding = WTF::TextEncoding(form->document()->encoding()); 71 } 72 73 // Returns true if the submit request results in an HTTP URL. 74 bool IsHTTPFormSubmit(const HTMLFormElement* form) 75 { 76 // FIXME: This function is insane. This is an overly complicated way to get this information. 77 String action(form->action()); 78 // The isNull() check is trying to avoid completeURL returning KURL() when passed a null string. 79 return form->document()->completeURL(action.isNull() ? "" : action).protocolIs("http"); 80 } 81 82 // If the form does not have an activated submit button, the first submit 83 // button is returned. 84 HTMLFormControlElement* GetButtonToActivate(HTMLFormElement* form) 85 { 86 HTMLFormControlElement* firstSubmitButton = 0; 87 // FIXME: Consider refactoring this code so that we don't call form->associatedElements() twice. 88 for (Vector<FormAssociatedElement*>::const_iterator i(form->associatedElements().begin()); i != form->associatedElements().end(); ++i) { 89 if (!(*i)->isFormControlElement()) 90 continue; 91 HTMLFormControlElement* control = toHTMLFormControlElement(*i); 92 if (control->isActivatedSubmit()) { 93 // There's a button that is already activated for submit, return 0. 94 return 0; 95 } 96 if (!firstSubmitButton && control->isSuccessfulSubmitButton()) 97 firstSubmitButton = control; 98 } 99 return firstSubmitButton; 100 } 101 102 // Returns true if the selected state of all the options matches the default 103 // selected state. 104 bool IsSelectInDefaultState(HTMLSelectElement* select) 105 { 106 const Vector<HTMLElement*>& listItems = select->listItems(); 107 if (select->multiple() || select->size() > 1) { 108 for (Vector<HTMLElement*>::const_iterator i(listItems.begin()); i != listItems.end(); ++i) { 109 if (!(*i)->hasLocalName(HTMLNames::optionTag)) 110 continue; 111 HTMLOptionElement* optionElement = toHTMLOptionElement(*i); 112 if (optionElement->selected() != optionElement->hasAttribute(selectedAttr)) 113 return false; 114 } 115 return true; 116 } 117 118 // The select is rendered as a combobox (called menulist in WebKit). At 119 // least one item is selected, determine which one. 120 HTMLOptionElement* initialSelected = 0; 121 for (Vector<HTMLElement*>::const_iterator i(listItems.begin()); i != listItems.end(); ++i) { 122 if (!(*i)->hasLocalName(HTMLNames::optionTag)) 123 continue; 124 HTMLOptionElement* optionElement = toHTMLOptionElement(*i); 125 if (optionElement->hasAttribute(selectedAttr)) { 126 // The page specified the option to select. 127 initialSelected = optionElement; 128 break; 129 } 130 if (!initialSelected) 131 initialSelected = optionElement; 132 } 133 return !initialSelected || initialSelected->selected(); 134 } 135 136 // Returns true if the form element is in its default state, false otherwise. 137 // The default state is the state of the form element on initial load of the 138 // page, and varies depending upon the form element. For example, a checkbox is 139 // in its default state if the checked state matches the state of the checked attribute. 140 bool IsInDefaultState(HTMLFormControlElement* formElement) 141 { 142 if (formElement->hasTagName(HTMLNames::inputTag)) { 143 const HTMLInputElement* inputElement = toHTMLInputElement(formElement); 144 if (inputElement->isCheckbox() || inputElement->isRadioButton()) 145 return inputElement->checked() == inputElement->hasAttribute(checkedAttr); 146 } else if (formElement->hasTagName(HTMLNames::selectTag)) { 147 return IsSelectInDefaultState(toHTMLSelectElement(formElement)); 148 } 149 return true; 150 } 151 152 // Look for a suitable search text field in a given HTMLFormElement 153 // Return nothing if one of those items are found: 154 // - A text area field 155 // - A file upload field 156 // - A Password field 157 // - More than one text field 158 HTMLInputElement* findSuitableSearchInputElement(const HTMLFormElement* form) 159 { 160 HTMLInputElement* textElement = 0; 161 // FIXME: Consider refactoring this code so that we don't call form->associatedElements() twice. 162 for (Vector<FormAssociatedElement*>::const_iterator i(form->associatedElements().begin()); i != form->associatedElements().end(); ++i) { 163 if (!(*i)->isFormControlElement()) 164 continue; 165 166 HTMLFormControlElement* control = toHTMLFormControlElement(*i); 167 168 if (control->isDisabledFormControl() || control->name().isNull()) 169 continue; 170 171 if (!IsInDefaultState(control) || isHTMLTextAreaElement(control)) 172 return 0; 173 174 if (control->hasTagName(HTMLNames::inputTag) && control->willValidate()) { 175 const HTMLInputElement* input = toHTMLInputElement(control); 176 177 // Return nothing if a file upload field or a password field are found. 178 if (input->isFileUpload() || input->isPasswordField()) 179 return 0; 180 181 if (input->isTextField()) { 182 if (textElement) { 183 // The auto-complete bar only knows how to fill in one value. 184 // This form has multiple fields; don't treat it as searchable. 185 return 0; 186 } 187 textElement = toHTMLInputElement(control); 188 } 189 } 190 } 191 return textElement; 192 } 193 194 // Build a search string based on a given HTMLFormElement and HTMLInputElement 195 // 196 // Search string output example from www.google.com: 197 // "hl=en&source=hp&biw=1085&bih=854&q={searchTerms}&btnG=Google+Search&aq=f&aqi=&aql=&oq=" 198 // 199 // Return false if the provided HTMLInputElement is not found in the form 200 bool buildSearchString(const HTMLFormElement* form, Vector<char>* encodedString, WTF::TextEncoding* encoding, const HTMLInputElement* textElement) 201 { 202 bool isElementFound = false; 203 204 // FIXME: Consider refactoring this code so that we don't call form->associatedElements() twice. 205 for (Vector<FormAssociatedElement*>::const_iterator i(form->associatedElements().begin()); i != form->associatedElements().end(); ++i) { 206 if (!(*i)->isFormControlElement()) 207 continue; 208 209 HTMLFormControlElement* control = toHTMLFormControlElement(*i); 210 211 if (control->isDisabledFormControl() || control->name().isNull()) 212 continue; 213 214 FormDataList dataList(*encoding); 215 if (!control->appendFormData(dataList, false)) 216 continue; 217 218 const Vector<FormDataList::Item>& items = dataList.items(); 219 220 for (Vector<FormDataList::Item>::const_iterator j(items.begin()); j != items.end(); ++j) { 221 // Handle ISINDEX / <input name=isindex> specially, but only if it's 222 // the first entry. 223 if (!encodedString->isEmpty() || j->data() != "isindex") { 224 if (!encodedString->isEmpty()) 225 encodedString->append('&'); 226 FormDataBuilder::encodeStringAsFormData(*encodedString, j->data()); 227 encodedString->append('='); 228 } 229 ++j; 230 if (control == textElement) { 231 encodedString->append("{searchTerms}", 13); 232 isElementFound = true; 233 } else 234 FormDataBuilder::encodeStringAsFormData(*encodedString, j->data()); 235 } 236 } 237 return isElementFound; 238 } 239 } // namespace 240 241 namespace WebKit { 242 243 WebSearchableFormData::WebSearchableFormData(const WebFormElement& form, const WebInputElement& selectedInputElement) 244 { 245 RefPtr<HTMLFormElement> formElement = form.operator PassRefPtr<HTMLFormElement>(); 246 HTMLInputElement* inputElement = selectedInputElement.operator PassRefPtr<HTMLInputElement>().get(); 247 248 // Only consider forms that GET data. 249 // Allow HTTPS only when an input element is provided. 250 if (equalIgnoringCase(formElement->getAttribute(methodAttr), "post") 251 || (!IsHTTPFormSubmit(formElement.get()) && !inputElement)) 252 return; 253 254 Vector<char> encodedString; 255 WTF::TextEncoding encoding; 256 257 GetFormEncoding(formElement.get(), &encoding); 258 if (!encoding.isValid()) { 259 // Need a valid encoding to encode the form elements. 260 // If the encoding isn't found webkit ends up replacing the params with 261 // empty strings. So, we don't try to do anything here. 262 return; 263 } 264 265 // Look for a suitable search text field in the form when a 266 // selectedInputElement is not provided. 267 if (!inputElement) { 268 inputElement = findSuitableSearchInputElement(formElement.get()); 269 270 // Return if no suitable text element has been found. 271 if (!inputElement) 272 return; 273 } 274 275 HTMLFormControlElement* firstSubmitButton = GetButtonToActivate(formElement.get()); 276 if (firstSubmitButton) { 277 // The form does not have an active submit button, make the first button 278 // active. We need to do this, otherwise the URL will not contain the 279 // name of the submit button. 280 firstSubmitButton->setActivatedSubmit(true); 281 } 282 283 bool isValidSearchString = buildSearchString(formElement.get(), &encodedString, &encoding, inputElement); 284 285 if (firstSubmitButton) 286 firstSubmitButton->setActivatedSubmit(false); 287 288 // Return if the search string is not valid. 289 if (!isValidSearchString) 290 return; 291 292 String action(formElement->action()); 293 KURL url(formElement->document()->completeURL(action.isNull() ? "" : action)); 294 RefPtr<FormData> formData = FormData::create(encodedString); 295 url.setQuery(formData->flattenToString()); 296 m_url = url; 297 m_encoding = String(encoding.name()); 298 } 299 300 } // namespace WebKit 301