doxyindexer.cpp 10 KB
Newer Older
Dimitri van Heesch's avatar
Dimitri van Heesch committed
1 2
/******************************************************************************
 *
Dimitri van Heesch's avatar
Dimitri van Heesch committed
3
 * Copyright (C) 1997-2014 by Dimitri van Heesch.
Dimitri van Heesch's avatar
Dimitri van Heesch committed
4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377
 *
 * Permission to use, copy, modify, and distribute this software and its
 * documentation under the terms of the GNU General Public License is hereby 
 * granted. No representations are made about the suitability of this software 
 * for any purpose. It is provided "as is" without express or implied warranty.
 * See the GNU General Public License for more details.
 *
 * Documents produced by Doxygen are derivative works derived from the
 * input used in their production; they are not affected by this license.
 *
 */

// STL includes
#include <cstdio>
#include <cstdlib>
#include <iostream>
#include <string>
#include <algorithm>
#include <sstream>

// Qtools includes
#include <qregexp.h>
#include <qxml.h>
#include <qfile.h>
#include <qfileinfo.h>

// Xapian include
#include <xapian.h>

#if defined(_WIN32) && !defined(__CYGWIN__)
static char pathSep = '\\';
#else
static char pathSep = '/';
#endif

/** trims \a whitespace characters from the start and end of string \a str. */
static std::string trim(const std::string& str,
                        const std::string& whitespace = " \t")
{
  size_t strBegin = str.find_first_not_of(whitespace);
  if (strBegin == std::string::npos)
    return ""; // no content

  size_t strEnd = str.find_last_not_of(whitespace);
  int strRange = strEnd - strBegin + 1;

  return str.substr(strBegin, strRange);
}

/** trims \a whitespace from start and end and replace occurrences of 
 *  \a whitespace with \a fill.
 */
static std::string reduce(const std::string& str,
    const std::string& fill = " ",
    const std::string& whitespace = " \t")
{
  // trim first
  std::string result = trim(str, whitespace);

  // replace sub ranges
  size_t beginSpace = result.find_first_of(whitespace);
  while (beginSpace != std::string::npos)
  {
    size_t endSpace = result.find_first_not_of(whitespace, beginSpace);
    int range = endSpace - beginSpace;

    result.replace(beginSpace, range, fill);

    size_t newStart = beginSpace + fill.length();
    beginSpace = result.find_first_of(whitespace, newStart);
  }

  return result;
}

/** Adds all words in \a s to document \a doc with weight \a wfd */
static void addWords(const std::string &s,Xapian::Document &doc,int wfd)
{
  std::istringstream iss(s);
  std::istream_iterator<std::string> begin(iss),end,it;
  for (it=begin;it!=end;++it)
  {
    std::string word = *it;
    std::string lword = word;
    std::transform(lword.begin(), lword.end(), lword.begin(), ::tolower);
    doc.add_term(word,wfd);
    if (lword!=word)
    {
      doc.add_term(lword,wfd);
    }
  }
}

/** Adds all identifiers in \a s to document \a doc with weight \a wfd */
static void addIdentifiers(const std::string &s,Xapian::Document &doc,int wfd)
{
  QRegExp re("[A-Z_a-z][A-Z_a-z0-9]*");
  int i,l,p=0;
  QCString qs = s.c_str();
  while ((i=re.match(qs,p,&l))!=-1)
  {
    doc.add_term(qs.mid(p,i-p).data(),wfd);
    p=i+l;
  }
}

/** Replaces all occurrences of \a old with \a repl in string \a str */
static void replace_all(std::string& str, const std::string& old, const std::string& repl) 
{
  size_t pos = 0;
  while ((pos = str.find(old, pos)) != std::string::npos) 
  {
    str.replace(pos, old.length(), repl);
    pos += repl.length();
  }
}

/** Replaces all XML entities in \a s with their unescaped representation */
static std::string unescapeXmlEntities(const std::string &s)
{
  std::string result=s;
  replace_all(result,"&gt;",">");
  replace_all(result,"&lt;","<");
  replace_all(result,"&apos;","'");
  replace_all(result,"&quot;","\"");
  replace_all(result,"&amp;","&");
  return result;
}

/** This class is a wrapper around SAX style XML parser, which
 *  parses the file without first building a DOM tree in memory.
 */
class XMLContentHandler : public QXmlDefaultHandler
{
  public:
    /** Handler for parsing XML data */
    XMLContentHandler(const QString &path) 
      : m_db((path+"doxysearch.db").utf8().data(),Xapian::DB_CREATE_OR_OVERWRITE), 
        m_stemmer("english")
    {
      m_curFieldName = UnknownField;
      m_indexer.set_stemmer(m_stemmer);
      m_indexer.set_document(m_doc);
    }

    /** Free data handler */
   ~XMLContentHandler()
    {
      m_db.commit();
    }

  private:
    enum FieldNames
    {
      UnknownField = 0,
      TypeField    = 1,
      NameField    = 2,
      ArgsField    = 3,
      TagField     = 4,
      UrlField     = 5,
      KeywordField = 6,
      TextField    = 7
    };

    /** Handler for a start tag. Called for <doc> and <field> tags */
    bool startElement(const QString &, const QString &,
        const QString &name, const QXmlAttributes &attrib)
    {
      m_data="";
      if (name=="field")
      {
        QString fieldName = attrib.value("name");
        if      (fieldName=="type")     m_curFieldName=TypeField;
        else if (fieldName=="name")     m_curFieldName=NameField;
        else if (fieldName=="args")     m_curFieldName=ArgsField;
        else if (fieldName=="tag")      m_curFieldName=TagField;
        else if (fieldName=="url")      m_curFieldName=UrlField;
        else if (fieldName=="keywords") m_curFieldName=KeywordField;
        else if (fieldName=="text")     m_curFieldName=TextField;
        else m_curFieldName=UnknownField;
      }
      return TRUE;
    }

    /** Handler for an end tag. Called for </doc> and </field> tags */
    bool endElement(const QString &, const QString &, const QString &name)
    {
      if (name=="doc") // </doc>
      {
        std::string term = m_doc.get_value(NameField);
        std::string partTerm;
        size_t pos = term.rfind("::");
        if (pos!=std::string::npos)
        {
          partTerm = term.substr(pos+2);
        }
        if (m_doc.get_value(TypeField)=="class" || 
            m_doc.get_value(TypeField)=="file" || 
            m_doc.get_value(TypeField)=="namespace") // containers get highest prio
        {
          m_doc.add_term(term,1000);
          if (!partTerm.empty())
          {
            m_doc.add_term(partTerm,500);
          }
        }
        else // members and others get lower prio
        {
          m_doc.add_term(m_doc.get_value(NameField),100);
          if (!partTerm.empty())
          {
            m_doc.add_term(partTerm,50);
          }
        }
        m_db.add_document(m_doc);
        m_doc.clear_values();
        m_doc.clear_terms();
      }
      else if (name=="field" && m_curFieldName!=UnknownField) // </field>
      {
        // strip whitespace from m_data
        m_data = reduce(m_data);
        // replace XML entities
        m_data = unescapeXmlEntities(m_data);
        // add data to the document
        m_doc.add_value(m_curFieldName,m_data); 
        switch (m_curFieldName)
        {
          case TypeField:    
          case NameField:    
          case TagField:     
          case UrlField:     
            // meta data that is not searchable
            break;
          case KeywordField: 
            addWords(m_data,m_doc,50);
            break;
          case ArgsField:    
            addIdentifiers(m_data,m_doc,10);
            break;
          case TextField:    
            addWords(m_data,m_doc,2);
            break;
          default:
            break;
        }
        m_data="";
        m_curFieldName=UnknownField;
      }
      // reset m_data
      return TRUE;
    }

    /** Handler for inline text */
    bool characters(const QString& ch) 
    {
      m_data += ch.utf8();
      return TRUE;
    }

    // internal state
    Xapian::WritableDatabase m_db;
    Xapian::Document m_doc;
    Xapian::TermGenerator m_indexer;
    Xapian::Stem m_stemmer;
    std::string m_data;
    FieldNames m_curFieldName;
};

/** Class for handling error during XML parsing */
class XMLErrorHandler : public QXmlErrorHandler
{
  public:
    virtual ~XMLErrorHandler() {}
    bool warning( const QXmlParseException & )
    {
      return FALSE;
    }
    bool error( const QXmlParseException & )
    {
      return FALSE;
    }
    bool fatalError( const QXmlParseException &exception )
    {
      std::cerr << "Fatal error at line " << exception.lineNumber() 
                << " column " << exception.columnNumber() << ": "
                << exception.message().utf8() << std::endl;
      return FALSE;
    }
    QString errorString() { return ""; }

  private:
    QString errorMsg;
};

static void usage(const char *name)
{
  std::cerr << "Usage: " << name << " [-o output_dir] searchdata.xml [searchdata2.xml ...]" << std::endl;
  exit(1);
}

/** main function to index data */
int main(int argc,const char **argv)
{
  if (argc<2)
  {
    usage(argv[0]);
  }
  QString outputDir;
  for (int i=1;i<argc;i++)
  {
    if (std::string(argv[i])=="-o")
    {
      if (i>=argc-1)
      {
        std::cerr << "Error: missing parameter for -o option" << std::endl;
        usage(argv[0]);
      }
      else
      {
        i++;
        outputDir=argv[i];
        QFileInfo fi(outputDir);
        if (!fi.exists() || !fi.isDir())
        {
          std::cerr << "Error: specified output directory does not exist!" << std::endl;
          usage(argv[0]);
        }
      }
    }
    else if (std::string(argv[i])=="-h" || std::string(argv[i])=="--help")
    {
      usage(argv[0]);
    }
  }

  try
  {
    if (!outputDir.isEmpty() && outputDir.at(outputDir.length()-1)!=pathSep)
    {
      outputDir+=pathSep;
    }
    XMLContentHandler handler(outputDir);
    XMLErrorHandler errorHandler;
    for (int i=1;i<argc;i++)
    {
      if (std::string(argv[i])=="-o")
      {
        i++;
      }
      else
      {
        QString xmlFileName = argv[i];
        std::cout << "Processing " << xmlFileName.utf8() << "..." << std::endl;
        QFile xmlFile(xmlFileName);
        QXmlInputSource source(xmlFile);
        QXmlSimpleReader reader;
        reader.setContentHandler(&handler);
        reader.setErrorHandler(&errorHandler);
        reader.parse(source);
      }
    }
  }
  catch(const Xapian::Error &e) 
  {
    std::cerr << "Caught exception: " << e.get_description() << std::endl;
  }
  catch(...)
  {
    std::cerr << "Caught an unknown exception" << std::endl;
  }

  return 0;
}