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 "Document.h" 35 #include "FormDataBuilder.h" 36 #include "FormDataList.h" 37 #include "Frame.h" 38 #include "HTMLFormControlElement.h" 39 #include "HTMLFormElement.h" 40 #include "HTMLInputElement.h" 41 #include "HTMLNames.h" 42 #include "HTMLOptionElement.h" 43 #include "HTMLOptionsCollection.h" 44 #include "HTMLSelectElement.h" 45 #include "TextEncoding.h" 46 #include "WebFormElement.h" 47 48 using namespace WebCore; 49 50 namespace { 51 52 // Gets the encoding for the form. 53 void GetFormEncoding(const HTMLFormElement* form, TextEncoding* encoding) 54 { 55 String str(form->getAttribute(HTMLNames::accept_charsetAttr)); 56 str.replace(',', ' '); 57 Vector<String> charsets; 58 str.split(' ', charsets); 59 for (Vector<String>::const_iterator i(charsets.begin()); i != charsets.end(); ++i) { 60 *encoding = TextEncoding(*i); 61 if (encoding->isValid()) 62 return; 63 } 64 const Frame* frame = form->document()->frame(); 65 *encoding = frame ? TextEncoding(frame->loader()->encoding()) : Latin1Encoding(); 66 } 67 68 // Returns true if the submit request results in an HTTP URL. 69 bool IsHTTPFormSubmit(const HTMLFormElement* form) 70 { 71 String action(form->action()); 72 return form->document()->frame()->loader()->completeURL(action.isNull() ? "" : action).protocol() == "http"; 73 } 74 75 // If the form does not have an activated submit button, the first submit 76 // button is returned. 77 HTMLFormControlElement* GetButtonToActivate(HTMLFormElement* form) 78 { 79 HTMLFormControlElement* firstSubmitButton = 0; 80 for (Vector<HTMLFormControlElement*>::const_iterator i(form->formElements.begin()); i != form->formElements.end(); ++i) { 81 HTMLFormControlElement* formElement = *i; 82 if (formElement->isActivatedSubmit()) 83 // There's a button that is already activated for submit, return 0. 84 return 0; 85 if (!firstSubmitButton && formElement->isSuccessfulSubmitButton()) 86 firstSubmitButton = formElement; 87 } 88 return firstSubmitButton; 89 } 90 91 // Returns true if the selected state of all the options matches the default 92 // selected state. 93 bool IsSelectInDefaultState(const HTMLSelectElement* select) 94 { 95 const Vector<Element*>& listItems = select->listItems(); 96 if (select->multiple() || select->size() > 1) { 97 for (Vector<Element*>::const_iterator i(listItems.begin()); i != listItems.end(); ++i) { 98 if (!(*i)->hasLocalName(HTMLNames::optionTag)) 99 continue; 100 const HTMLOptionElement* optionElement = static_cast<const HTMLOptionElement*>(*i); 101 if (optionElement->selected() != optionElement->defaultSelected()) 102 return false; 103 } 104 return true; 105 } 106 107 // The select is rendered as a combobox (called menulist in WebKit). At 108 // least one item is selected, determine which one. 109 const HTMLOptionElement* initialSelected = 0; 110 for (Vector<Element*>::const_iterator i(listItems.begin()); i != listItems.end(); ++i) { 111 if (!(*i)->hasLocalName(HTMLNames::optionTag)) 112 continue; 113 const HTMLOptionElement* optionElement = static_cast<const HTMLOptionElement*>(*i); 114 if (optionElement->defaultSelected()) { 115 // The page specified the option to select. 116 initialSelected = optionElement; 117 break; 118 } 119 if (!initialSelected) 120 initialSelected = optionElement; 121 } 122 return initialSelected ? initialSelected->selected() : true; 123 } 124 125 // Returns true if the form element is in its default state, false otherwise. 126 // The default state is the state of the form element on initial load of the 127 // page, and varies depending upon the form element. For example, a checkbox is 128 // in its default state if the checked state matches the defaultChecked state. 129 bool IsInDefaultState(const HTMLFormControlElement* formElement) 130 { 131 if (formElement->hasTagName(HTMLNames::inputTag)) { 132 const HTMLInputElement* inputElement = static_cast<const HTMLInputElement*>(formElement); 133 if (inputElement->inputType() == HTMLInputElement::CHECKBOX || inputElement->inputType() == HTMLInputElement::RADIO) 134 return inputElement->checked() == inputElement->defaultChecked(); 135 } else if (formElement->hasTagName(HTMLNames::selectTag)) 136 return IsSelectInDefaultState(static_cast<const HTMLSelectElement*>(formElement)); 137 return true; 138 } 139 140 // If form has only one text input element, return true. If a valid input 141 // element is not found, return false. Additionally, the form data for all 142 // elements is added to enc_string and the encoding used is set in 143 // encoding_name. 144 bool HasSuitableTextElement(const HTMLFormElement* form, Vector<char>* encodedString, String* encodingName) 145 { 146 TextEncoding encoding; 147 GetFormEncoding(form, &encoding); 148 if (!encoding.isValid()) { 149 // Need a valid encoding to encode the form elements. 150 // If the encoding isn't found webkit ends up replacing the params with 151 // empty strings. So, we don't try to do anything here. 152 return 0; 153 } 154 *encodingName = encoding.name(); 155 156 HTMLInputElement* textElement = 0; 157 for (Vector<HTMLFormControlElement*>::const_iterator i(form->formElements.begin()); i != form->formElements.end(); ++i) { 158 HTMLFormControlElement* formElement = *i; 159 if (formElement->disabled() || formElement->name().isNull()) 160 continue; 161 162 if (!IsInDefaultState(formElement) || formElement->hasTagName(HTMLNames::textareaTag)) 163 return 0; 164 165 bool isTextElement = false; 166 if (formElement->hasTagName(HTMLNames::inputTag)) { 167 switch (static_cast<const HTMLInputElement*>(formElement)->inputType()) { 168 case HTMLInputElement::TEXT: 169 case HTMLInputElement::ISINDEX: 170 isTextElement = true; 171 break; 172 case HTMLInputElement::PASSWORD: 173 // Don't store passwords! This is most likely an https anyway. 174 // Fall through. 175 case HTMLInputElement::FILE: 176 // Too big, don't try to index this. 177 return 0; 178 default: 179 // All other input types are indexable. 180 break; 181 } 182 } 183 184 FormDataList dataList(encoding); 185 if (!formElement->appendFormData(dataList, false)) 186 continue; 187 188 const Vector<FormDataList::Item>& itemList = dataList.list(); 189 if (isTextElement && !itemList.isEmpty()) { 190 if (textElement) { 191 // The auto-complete bar only knows how to fill in one value. 192 // This form has multiple fields; don't treat it as searchable. 193 return false; 194 } 195 textElement = static_cast<HTMLInputElement*>(formElement); 196 } 197 for (Vector<FormDataList::Item>::const_iterator j(itemList.begin()); j != itemList.end(); ++j) { 198 // Handle ISINDEX / <input name=isindex> specially, but only if it's 199 // the first entry. 200 if (!encodedString->isEmpty() || j->data() != "isindex") { 201 if (!encodedString->isEmpty()) 202 encodedString->append('&'); 203 FormDataBuilder::encodeStringAsFormData(*encodedString, j->data()); 204 encodedString->append('='); 205 } 206 ++j; 207 if (formElement == textElement) 208 encodedString->append("{searchTerms}", 13); 209 else 210 FormDataBuilder::encodeStringAsFormData(*encodedString, j->data()); 211 } 212 } 213 214 return textElement; 215 } 216 217 } // namespace 218 219 namespace WebKit { 220 221 WebSearchableFormData::WebSearchableFormData(const WebFormElement& form) 222 { 223 RefPtr<HTMLFormElement> formElement = form.operator PassRefPtr<HTMLFormElement>(); 224 const Frame* frame = formElement->document()->frame(); 225 if (!frame) 226 return; 227 228 // Only consider forms that GET data and the action targets an http page. 229 if (equalIgnoringCase(formElement->getAttribute(HTMLNames::methodAttr), "post") || !IsHTTPFormSubmit(formElement.get())) 230 return; 231 232 HTMLFormControlElement* firstSubmitButton = GetButtonToActivate(formElement.get()); 233 if (firstSubmitButton) { 234 // The form does not have an active submit button, make the first button 235 // active. We need to do this, otherwise the URL will not contain the 236 // name of the submit button. 237 firstSubmitButton->setActivatedSubmit(true); 238 } 239 Vector<char> encodedString; 240 String encoding; 241 bool hasElement = HasSuitableTextElement(formElement.get(), &encodedString, &encoding); 242 if (firstSubmitButton) 243 firstSubmitButton->setActivatedSubmit(false); 244 if (!hasElement) { 245 // Not a searchable form. 246 return; 247 } 248 249 String action(formElement->action()); 250 KURL url(frame->loader()->completeURL(action.isNull() ? "" : action)); 251 RefPtr<FormData> formData = FormData::create(encodedString); 252 url.setQuery(formData->flattenToString()); 253 m_url = url; 254 m_encoding = encoding; 255 } 256 257 } // namespace WebKit 258