--- /dev/null
+/**
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package com.nexwave.nquindexer;
+
+import com.nexwave.nsidita.DirList;
+import com.nexwave.nsidita.DocFileInfo;
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.util.*;
+
+/**
+ * User: Kasun Gajasinghe, University of Moratuwa, http://kasunbg.blogspot.com
+ * Date: Feb 10, 2011
+ */
+
+public class IndexerMain {
+
+ // messages
+ private String txt_no_inputdir = "Input directory not found:";
+ private String txt_cannot_create_outputdir = "Cannot create output search directory.";
+ private String txt_no_files_found = "No html files found.";
+ private String txt_wrong_dita_basedir = "ERROR: Parser initialization failed. Wrong dita base dir";
+ private String txt_no_relative_files_found = "No relative html files calculated.";
+ private String txt_no_words_gathered = "No words have been indexed in";
+ private String txt_no_html_files = "No HTML Files found in";
+ private String txt_no_args = "No argument given: you must provide an htmlDir to the IndexerMain";
+
+ private static String txt_no_lang_specified ="Language of the content is not specified. Defaults to English.";
+
+ //working directories
+ private String searchdir = "search";
+ private File inputDir = null;
+ private String outputDir = null;
+ private String projectDir = null;
+
+ // ANT parameters
+ public String htmlDir = null;
+ public String indexerLanguage = "en";
+
+ //supported languages: add new additions to this. don't include country codes to the end such as en_US or en_UK,
+ // as stemmers doesn't find a difference between them.
+ private String[] supportedLanguages = {"en", "de", "fr", "zh", "ja", "ko"}; //currently extended support available for
+ // English, German, French and CJK (Chinese [zh], Japanese [ja], Korean [ko]) languages only.
+
+ // Indexing features: words to remove
+ private ArrayList<String> cleanUpStrings = null;
+ private ArrayList<String> cleanUpChars = null;
+
+ //Html extension
+ private String htmlExtension = "html";
+
+ // Constructors
+ public IndexerMain(String htmlDir, String indexerLanguage) {
+ super();
+ setHtmlDir(htmlDir);
+ setIndexerLanguage(indexerLanguage);
+ }
+
+ /**
+ * The content language defaults to English "en"
+ * @param htmlDir The directory where html files resides.
+ */
+ public IndexerMain(String htmlDir) {
+ super();
+ setHtmlDir(htmlDir);
+ setIndexerLanguage("en");
+ }
+
+ /**
+ * The setter for the "htmlDir" attribute (parameter of the task)
+ *
+ * @param htmlDir
+ */
+ public void setHtmlDir(String htmlDir) {
+ this.htmlDir = htmlDir;
+ }
+
+ /**
+ * Set the extension in which html files are generated
+ *
+ * @param htmlExtension The extension in which html files are generated
+ */
+ public void setHtmlextension(String htmlExtension) {
+ this.htmlExtension = htmlExtension;
+ //Trim the starting "."
+ if (this.htmlExtension.startsWith(".")) {
+ this.htmlExtension = this.htmlExtension.substring(1);
+ }
+ }
+
+ /**
+ * setter for "indexerLanguage" attribute from ANT
+ *
+ * @param indexerLanguage language for the search indexer. Used to differentiate which stemmer to be used.
+ */
+ public void setIndexerLanguage(String indexerLanguage) {
+ if (indexerLanguage != null && !"".equals(indexerLanguage)) {
+ int temp = indexerLanguage.indexOf('_');
+ if (temp != -1) {
+ indexerLanguage = indexerLanguage.substring(0, temp);
+ }
+ int i = 0;
+ for (; i < supportedLanguages.length; i++) {
+ if (indexerLanguage.equals(supportedLanguages[i])) {
+ this.indexerLanguage = supportedLanguages[i];
+ break;
+ }
+ }
+
+ //if not in supported language list,
+ if (i >= supportedLanguages.length) {
+// System.out.println("The given language, \""+indexerLanguage+"\", does not have extensive support for " +
+// "searching. Check documentation for details. ");
+ this.indexerLanguage = indexerLanguage;
+ }
+ } else {
+ this.indexerLanguage = "@@"; //fail-safe mechanism, This vm should not reach this point.
+ }
+ }
+
+ /**
+ * com.nexwave.nquindexer.IndexerMain
+ * The main class without Ant dependencies.
+ * This can be used as a standalone jar.
+ *
+ * @param args need two parameters for this array. htmlDirectory indexerLanguage
+ * If only one parameter is there (htmlDir), indexerLanguage defaults to english
+ */
+ public static void main(String[] args) {
+
+ IndexerMain indexer;
+ if (args.length == 1) {
+ System.out.println(txt_no_lang_specified);
+ indexer = new IndexerMain(args[0]);
+ } else if (args.length >= 2) {
+
+ indexer = new IndexerMain(args[0], args[1]);
+ } else {
+ throw new ArrayIndexOutOfBoundsException("Please specify the parameters htmlDirectory and (optional) " +
+ "indexerLanguage");
+ }
+
+ indexer.execute();
+
+ }
+
+
+ /**
+ * Implementation of the execute function (Task interface)
+ */
+ public void execute() {
+ try {
+ //Use Xerces as the parser. Does not support Saxon6.5.5 parser
+ System.setProperty("org.xml.sax.driver", "org.apache.xerces.parsers.SAXParser");
+ System.setProperty("javax.xml.parsers.SAXParserFactory", "org.apache.xerces.jaxp.SAXParserFactoryImpl");
+// System.setProperty("org.xml.sax.driver", "com.icl.saxon.aelfred.SAXDriver");
+// System.setProperty("javax.xml.parsers.SAXParserFactory", "com.icl.saxon.aelfred.SAXParserFactoryImpl");
+ } catch (SecurityException se) {
+ System.out.println("[WARNING] Default parser is not set to Xerces. Make sure Saxon6.5.5 " +
+ "is not in your CLASSPATH.");
+ } catch (Exception e) {
+ System.out.println("[WARNING] Default parser is not set to Xerces. Make sure Saxon6.5.5 " +
+ "is not in your CLASSPATH");
+ }
+
+ ArrayList<DocFileInfo> filesDescription = null; // list of information about the topic files
+ ArrayList<File> htmlFiles = null; // topic files listed in the given directory
+ ArrayList<String> htmlFilesPathRel = null;
+ Map<String, String> tempDico = new HashMap<String, String>();
+ Iterator it;
+
+ //File name initialization
+ String htmlList = "htmlFileList.js";
+ String htmlInfoList = "htmlFileInfoList.js";
+ String indexName = ".js";
+
+ //timing
+ Date dateStart = new Date();
+
+ if (htmlDir == null) {
+ System.out.println(txt_no_args + ".");
+ return;
+ }
+ // Init input directory
+ inputDir = new File(htmlDir);
+
+ // Begin of init
+ // check if inputdir initialized
+ if (inputDir == null) {
+ DisplayHelp();
+ return;
+ }
+
+ // check if inputdir exists
+ if (!inputDir.exists()) {
+ System.out.println(txt_no_inputdir + " " + inputDir + ".");
+ return;
+ }
+
+ // check if outputdir defined
+ if (outputDir == null) {
+ //set the output directory: path= {inputDir}/search
+ outputDir = inputDir.getPath().concat(File.separator).concat(searchdir);
+ }
+
+ // check if outputdir exists
+ File tempfile = new File(outputDir);
+ if (!tempfile.exists()) {
+ boolean b = (new File(outputDir)).mkdir();
+ if (!b) {
+ System.out.println(txt_cannot_create_outputdir + " " + outputDir + ".");
+ return;
+ }
+ }
+
+ // check if projdir is defined
+ if (projectDir == null) {
+ projectDir = inputDir.getPath();
+ }
+ //end of init
+
+
+ // Get the list of all html files but the tocs, covers and indexes
+ DirList nsiDoc = new DirList(inputDir, "^.*\\." + htmlExtension + "?$", 1);
+ htmlFiles = nsiDoc.getListFiles();
+ // Check if found html files
+ if (htmlFiles.isEmpty()) {
+ System.out.println(txt_no_html_files + " " + inputDir + ".");
+ return;
+ }
+ // Get the list of all html files with relative paths
+ htmlFilesPathRel = nsiDoc.getListFilesRelTo(projectDir);
+
+ if (htmlFiles == null) {
+ System.out.println(txt_no_files_found);
+ return;
+ } else if (htmlFilesPathRel == null) {
+ System.out.println(txt_no_relative_files_found);
+ return;
+ }
+
+ // Create the list of the existing html files (index starts at 0)
+ WriteJSFiles.WriteHTMLList(outputDir.concat(File.separator).concat(htmlList), htmlFilesPathRel);
+
+ // Parse each html file to retrieve the words:
+ // ------------------------------------------
+
+ // Retrieve the clean-up properties for indexing
+ RetrieveCleanUpProps();
+ // System.out.print("clean"+" " +cleanUpStrings);
+
+ //create a default handler
+ //SaxHTMLIndex spe = new SaxHTMLIndex (); // do not use clean-up props files
+ //SaxHTMLIndex spe = new SaxHTMLIndex (cleanUpStrings); // use clean-up props files
+ SaxHTMLIndex spe = new SaxHTMLIndex(cleanUpStrings, cleanUpChars); // use clean-up props files
+
+ if (spe.init(tempDico) == 0) {
+
+ //create a html file description list
+ filesDescription = new ArrayList<DocFileInfo>();
+
+ it = htmlFiles.iterator();
+
+ // parse each html files
+ while (it.hasNext()) {
+ File ftemp = (File) it.next();
+ //tempMap.put(key, value);
+ //The HTML file information are added in the list of FileInfoObject
+ DocFileInfo docFileInfoTemp = new DocFileInfo(spe.runExtractData(ftemp, this.indexerLanguage));
+
+ ftemp = docFileInfoTemp.getFullpath();
+ String stemp = ftemp.toString();
+ int i = stemp.indexOf(projectDir);
+ if (i != 0) {
+ System.out.println("the documentation root does not match with the documentation input!");
+ return;
+ }
+ int ad = 1;
+ if (stemp.equals(projectDir)) ad = 0;
+ stemp = stemp.substring(i + projectDir.length() + ad); //i is redundant (i==0 always)
+ ftemp = new File(stemp);
+ docFileInfoTemp.setFullpath(ftemp);
+
+ filesDescription.add(docFileInfoTemp);
+ }
+ /*remove empty strings from the map*/
+ if (tempDico.containsKey("")) {
+ tempDico.remove("");
+ }
+ // write the index files
+ if (tempDico.isEmpty()) {
+ System.out.println(txt_no_words_gathered + " " + inputDir + ".");
+ return;
+ }
+
+// WriteJSFiles.WriteIndex(outputDir.concat(File.separator).concat(indexName), tempDico);
+ WriteJSFiles.WriteIndex(outputDir.concat(File.separator).concat(indexName), tempDico, indexerLanguage);
+
+ // write the html list file with title and shortdesc
+ //create the list of the existing html files (index starts at 0)
+ WriteJSFiles.WriteHTMLInfoList(outputDir.concat(File.separator).concat(htmlInfoList), filesDescription);
+
+ //perf measurement
+ Date dateEnd = new Date();
+ long diff = dateEnd.getTime() - dateStart.getTime();
+ if (diff < 1000)
+ System.out.println("Delay = " + diff + " milliseconds");
+ else
+ System.out.println("Delay = " + diff / 1000 + " seconds");
+ } else {
+ System.out.println(txt_wrong_dita_basedir);
+ return;
+ }
+ }
+
+ /**
+ * Prints the usage information for this class to <code>System.out</code>.
+ */
+ private static void DisplayHelp() {
+ String lSep = System.getProperty("line.separator");
+ StringBuffer msg = new StringBuffer();
+ msg.append("USAGE:" + lSep);
+ msg.append(" java -classpath TesterIndexer inputDir outputDir projectDir" + lSep);
+ msg.append("with:" + lSep);
+ msg.append(" inputDir (mandatory) : specify the html files ' directory to index" + lSep);
+ msg.append(" outputDir (optional) : specify where to output the index files" + lSep);
+ msg.append(" projectDir (optional) : specify the root of the documentation directory" + lSep);
+ msg.append("Example:" + lSep);
+ msg.append(" java -classpath TesterIndexer /home/$USER/DITA/doc" + lSep);
+ msg.append("Example 2:" + lSep);
+ msg.append(" java -classpath TesterIndexer /home/$USER/DITA/doc/customer/concepts /home/$USER/temp/search /home/$USER/DITA/doc/" + lSep);
+ System.out.println(msg.toString());
+ }
+
+ private int RetrieveCleanUpProps() {
+
+ // Files for punctuation (only one for now)
+ String[] punctuationFiles = new String[]{"punctuation.props"};
+ FileInputStream input;
+ String tempStr;
+ File ftemp;
+ Collection c = new ArrayList<String>();
+
+ // Get the list of the props file containing the words to remove (not the punctuation)
+ DirList props = new DirList(inputDir, "^(?!(punctuation)).*\\.props$", 1);
+ ArrayList<File> wordsList = props.getListFiles();
+// System.out.println("props files:"+wordsList);
+ //TODO all properties are taken to a single arraylist. does it ok?.
+ Properties enProps = new Properties();
+ String propsDir = inputDir.getPath().concat(File.separator).concat(searchdir);
+
+ // Init the lists which will contain the words and chars to remove
+ cleanUpStrings = new ArrayList<String>();
+ cleanUpChars = new ArrayList<String>();
+
+ try {
+ // Retrieve words to remove
+ for (File aWordsList : wordsList) {
+ ftemp = aWordsList;
+ if (ftemp.exists()) {
+ enProps.load(input = new FileInputStream(ftemp.getAbsolutePath()));
+ input.close();
+ c = enProps.values();
+ cleanUpStrings.addAll(c);
+ enProps.clear();
+ }
+ }
+
+ // Retrieve char to remove (punctuation for ex.)
+ for (String punctuationFile : punctuationFiles) {
+ tempStr = propsDir.concat(File.separator).concat(punctuationFile);
+ ftemp = new File(tempStr);
+ if (ftemp.exists()) {
+ enProps.load(input = new FileInputStream(tempStr));
+ input.close();
+ c = enProps.values();
+ cleanUpChars.addAll(c);
+ enProps.clear();
+ }
+ }
+ }
+ catch (IOException e) {
+ e.printStackTrace();
+ return 1;
+ }
+ return 0;
+ }
+
+}
+/*\r
package com.nexwave.nquindexer;\r
\r
import java.io.File;\r
import com.nexwave.nsidita.DirList;\r
import com.nexwave.nsidita.DocFileInfo;\r
\r
+*/\r
/**\r
* Indexer ant task.\r
* \r
* \r
* @author N. Quaine\r
* @author Kasun Gajasinghe <http://kasunbg.blogspot.com>\r
- */\r
+ *//*\r
+\r
public class IndexerTask extends Task {\r
\r
// messages\r
private String txt_no_relative_files_found= "No relative html files calculated.";\r
private String txt_no_words_gathered= "No words have been indexed in";\r
private String txt_no_html_files="No HTML Files found in";\r
- private String txt_no_args="No argument given: you must provide an htmldir to the IndexerTask";\r
+ private String txt_no_args="No argument given: you must provide an htmlDir to the IndexerTask";\r
\r
//working directories\r
private String searchdir = "search";\r
private String projectDir = null;\r
\r
// ANT parameters\r
- private String htmldir=null;\r
+ private String htmlDir=null;\r
public static String indexerLanguage="en";\r
\r
//supported languages: add new additions to this. don't include country codes to the end such as en_US or en_UK,\r
public IndexerTask() {\r
super();\r
}\r
- /** The setter for the "htmldir" attribute (parameter of the task)\r
+ */\r
+/** The setter for the "htmlDir" attribute (parameter of the task)\r
* @param htmldir\r
* @throws InterruptedException \r
- */\r
- public void setHtmldir(String htmldir) {\r
- this.htmldir = htmldir;\r
+ *//*\r
+\r
+ public void setHtmlDir(String htmlDir) {\r
+ this.htmlDir = htmlDir;\r
}\r
\r
- /**\r
+ */\r
+/**\r
* Set the extension in which html files are generated\r
* @param htmlExtension The extension in wich html files are generated\r
- */\r
+ *//*\r
+\r
public void setHtmlextension(String htmlExtension) {\r
this.htmlExtension = htmlExtension;\r
//Trim the starting "."\r
}\r
}\r
\r
- /**\r
+ */\r
+/**\r
* setter for "indexerLanguage" attribute from ANT\r
* @param indexerLanguage language for the search indexer. Used to differerentiate which stemmer to be used.\r
* @throws InterruptedException for ant\r
- */\r
+ *//*\r
+\r
public void setIndexerLanguage(String indexerLanguage){\r
if(indexerLanguage !=null && !"".equals(indexerLanguage)) {\r
int temp = indexerLanguage.indexOf('_');\r
} \r
}\r
\r
- /**\r
+ */\r
+/**\r
* Implementation of the execute function (Task interface)\r
- */\r
+ *//*\r
+\r
public void execute() throws BuildException {\r
try{\r
//Use Xerces as the parser. Does not support Saxon6.5.5 parser \r
//timing\r
Date dateStart = new Date();\r
\r
- if (htmldir == null) {\r
+ if (htmlDir == null) {\r
System.out.println(txt_no_args + ".");\r
return;\r
}\r
// Init input directory\r
- inputDir = new File(htmldir);\r
+ inputDir = new File(htmlDir);\r
\r
// Begin of init\r
// check if inputdir initialized\r
\r
filesDescription.add(docFileInfoTemp);\r
}\r
- /*remove empty strings from the map*/\r
+ */\r
+/*remove empty strings from the map*//*\r
+\r
if (tempDico.containsKey("")) {\r
tempDico.remove("");\r
}\r
}\r
}\r
\r
- /**\r
+ */\r
+/**\r
* Prints the usage information for this class to <code>System.out</code>.\r
- */\r
+ *//*\r
+\r
private static void DisplayHelp() {\r
String lSep = System.getProperty("line.separator");\r
StringBuffer msg = new StringBuffer();\r
}\r
\r
}\r
+*/\r
+/*\r
package com.nexwave.nquindexer;\r
\r
+*/\r
/**\r
* For running tests with the indexertask.\r
* \r
* \r
* @author N. Quaine\r
* @author Kasun Gajasinghe\r
- */\r
+ *//*\r
+\r
public class TesterIndexer {\r
public static IndexerTask IT = null; \r
- /**\r
+ */\r
+/**\r
* @param args\r
* @throws InterruptedException \r
- */\r
+ *//*\r
+\r
public static void main(String[] args) throws InterruptedException {\r
if (args.length != 0) {\r
IT = new IndexerTask();\r
- IT.setHtmldir(args[0]);\r
+ IT.setHtmlDir(args[0]);\r
IT.setIndexerLanguage(args[1]);\r
IT.execute();\r
} else {\r
String dir = "../doc/content";\r
String lang = "en";\r
IT = new IndexerTask();\r
- IT.setHtmldir(dir);\r
+ IT.setHtmlDir(dir);\r
IT.setIndexerLanguage(lang);\r
IT.execute();\r
}\r
\r
}\r
\r
+*/\r
import java.util.TreeSet;\r
\r
import com.nexwave.nsidita.DocFileInfo;\r
+\r
/**\r
* Outputs the js files with:\r
* - the list of html files and their description\r
* - the words retrieved from the html files and their location\r
- * \r
- * @version 2.0 2010-08-13\r
- * \r
+ *\r
* @author N. Quaine\r
* @author Kasun Gajasinghe\r
+ * @version 2.0 2010-08-13\r
*/\r
public class WriteJSFiles {\r
- \r
- private static String txt_VM_encoding_not_supported = "This VM does not support the specified encoding.";\r
- private static String txt_indices_location = "The created index files are located in ";\r
- \r
- /** Create a javascript array listing the html files with their paths relative to the project root\r
- * @param fileO path and name of the file in which to output the list of html files \r
- * @param list of the html files, relative to the doc root directory \r
- */\r
- public static void WriteHTMLList (String fileO,ArrayList<String> list) {\r
- int i = 0;\r
- Iterator it;\r
- \r
- if (list == null) {\r
- return;\r
- }\r
- if (fileO == null) {\r
- return;\r
- }\r
- it = list.iterator ( ) ;\r
- \r
- try {\r
- // open a outputstream, here a file\r
- OutputStream fOut= new FileOutputStream(fileO);\r
- OutputStream bout= new BufferedOutputStream(fOut);\r
- OutputStreamWriter out = new OutputStreamWriter(bout, "UTF-8");\r
- \r
- /*fl : file list*/\r
- out.write("//List of files which are indexed.\n");\r
- out.write("fl = new Array();\n");\r
- String temp;\r
- while ( it.hasNext ( ) ) {\r
- temp = (String)it.next();\r
- //System.out.println("temp : "+File.separatorChar+" "+temp.replace(File.separatorChar, '/'));\r
- out.write("fl[\""+i+"\"]"+"= \""+temp.replace(File.separatorChar, '/')+"\";\n");\r
- i++;\r
- }\r
- \r
- out.flush(); // Don't forget to flush!\r
- out.close();\r
+\r
+ private static String txt_VM_encoding_not_supported = "This VM does not support the specified encoding.";\r
+ private static String txt_indices_location = "The created index files are located in ";\r
+\r
+ /**\r
+ * Create a javascript array listing the html files with their paths relative to the project root\r
+ *\r
+ * @param fileO path and name of the file in which to output the list of html files\r
+ * @param list of the html files, relative to the doc root directory\r
+ */\r
+ public static void WriteHTMLList(String fileO, ArrayList<String> list) {\r
+ int i = 0;\r
+ Iterator it;\r
+\r
+ if (list == null) {\r
+ return;\r
+ }\r
+ if (fileO == null) {\r
+ return;\r
+ }\r
+ it = list.iterator();\r
+\r
+ try {\r
+ // open a outputstream, here a file\r
+ OutputStream fOut = new FileOutputStream(fileO);\r
+ OutputStream bout = new BufferedOutputStream(fOut);\r
+ OutputStreamWriter out = new OutputStreamWriter(bout, "UTF-8");\r
+\r
+ /*fl : file list*/\r
+ out.write("//List of files which are indexed.\n");\r
+ out.write("fl = new Array();\n");\r
+ String temp;\r
+ while (it.hasNext()) {\r
+ temp = (String) it.next();\r
+ //System.out.println("temp : "+File.separatorChar+" "+temp.replace(File.separatorChar, '/'));\r
+ out.write("fl[\"" + i + "\"]" + "= \"" + temp.replace(File.separatorChar, '/') + "\";\n");\r
+ i++;\r
+ }\r
+\r
+ out.flush(); // Don't forget to flush!\r
+ out.close();\r
// System.out.println("the array of html is in " + fileO);\r
\r
- }\r
- catch (UnsupportedEncodingException e) {\r
- System.out.println(txt_VM_encoding_not_supported);\r
- }\r
- catch (IOException e) {\r
- System.out.println(e.getMessage()); \r
- }\r
- \r
- }\r
-\r
- /** Create a javascript array listing the html files with \r
- * their paths relative to project root, their titles and shortdescs\r
- * @param fileO path and name of the file in which to output the list of html files \r
- * @param list of the html files, relative to the doc root directory \r
- */\r
- public static void WriteHTMLInfoList (String fileO,ArrayList<DocFileInfo> list) {\r
- int i = 0;\r
- Iterator it = null;\r
- \r
- if (list == null) {\r
- return;\r
- }\r
- if (fileO == null) {\r
- return;\r
- }\r
- it = list.iterator ( ) ;\r
- try {\r
- // open a outputstream, here a file\r
- OutputStream fOut= new FileOutputStream(fileO);\r
- // open a buffer output stream\r
- OutputStream bout= new BufferedOutputStream(fOut);\r
- OutputStreamWriter out \r
- = new OutputStreamWriter(bout, "UTF-8");\r
- \r
- /*fil : file list*/\r
- out.write("fil = new Array();\n");\r
- \r
- DocFileInfo tempInfo;\r
- String tempPath;\r
- String tempTitle;\r
- String tempShortdesc;\r
- while ( it.hasNext ( ) ) {\r
- // Retrieve file information: path, title and shortdesc.\r
- tempInfo = (DocFileInfo)it.next();\r
- tempPath = tempInfo.getFullpath().toString().replace(File.separatorChar, '/');\r
- tempTitle = tempInfo.getTitle();\r
- tempShortdesc = tempInfo.getShortdesc();\r
- //Remove unwanted white char\r
- if (tempTitle != null ) {\r
- tempTitle = tempTitle.replaceAll("\\s+", " ");\r
- tempTitle = tempTitle.replaceAll("['�\"]", " ");\r
- }\r
- if (tempShortdesc != null ) {\r
- tempShortdesc = tempShortdesc.replaceAll("\\s+", " ");\r
- tempShortdesc = tempShortdesc.replaceAll("['�\"]", " ");\r
- }\r
- //System.out.println("temp : "+File.separatorChar+" "+tempShortdesc);\r
- out.write("fil[\""+i+"\"]"+"= \""+tempPath+"@@@"+tempTitle+"@@@"+tempShortdesc+"\";\n");\r
- i++;\r
- }\r
- \r
- out.flush(); // Don't forget to flush!\r
- out.close();\r
-\r
- }\r
- catch (UnsupportedEncodingException e) {\r
- System.out.println(txt_VM_encoding_not_supported);\r
- }\r
- catch (IOException e) {\r
- System.out.println(e.getMessage()); \r
- }\r
- \r
- }\r
-\r
- /** Create javascript index files alphabetically.\r
- * @param fileOutStr contains the path and the suffix of the index files to create. \r
- * The first letter of the key is added to the given suffix. For example: e.g. a.js, b.js etc... \r
- * @param indexMap its keys are the indexed words and\r
- * its values are the list of the files which contain the word. \r
- */\r
- public static void WriteIndex (String fileOutStr, Map<String, ?> indexMap) {\r
- OutputStreamWriter out;\r
- OutputStream bout;\r
- OutputStream fOut;\r
- String tstr; \r
- \r
- // check arguments\r
- if (indexMap == null || fileOutStr ==null) {\r
- return;\r
- }\r
-\r
- // Collect the key of the index map\r
- TreeSet<String> sortedKeys = new TreeSet<String>();\r
- sortedKeys.addAll(indexMap.keySet());\r
- Iterator keyIt = sortedKeys.iterator();\r
- tstr = (String)keyIt.next();\r
- \r
- File fileOut= new File(fileOutStr);\r
+ }\r
+ catch (UnsupportedEncodingException e) {\r
+ System.out.println(txt_VM_encoding_not_supported);\r
+ }\r
+ catch (IOException e) {\r
+ System.out.println(e.getMessage());\r
+ }\r
+\r
+ }\r
+\r
+ /**\r
+ * Create a javascript array listing the html files with\r
+ * their paths relative to project root, their titles and shortdescs\r
+ *\r
+ * @param fileO path and name of the file in which to output the list of html files\r
+ * @param list of the html files, relative to the doc root directory\r
+ */\r
+ public static void WriteHTMLInfoList(String fileO, ArrayList<DocFileInfo> list) {\r
+ int i = 0;\r
+ Iterator it = null;\r
+\r
+ if (list == null) {\r
+ return;\r
+ }\r
+ if (fileO == null) {\r
+ return;\r
+ }\r
+ it = list.iterator();\r
+ try {\r
+ // open a outputstream, here a file\r
+ OutputStream fOut = new FileOutputStream(fileO);\r
+ // open a buffer output stream\r
+ OutputStream bout = new BufferedOutputStream(fOut);\r
+ OutputStreamWriter out\r
+ = new OutputStreamWriter(bout, "UTF-8");\r
+\r
+ /*fil : file list*/\r
+ out.write("fil = new Array();\n");\r
+\r
+ DocFileInfo tempInfo;\r
+ String tempPath;\r
+ String tempTitle;\r
+ String tempShortdesc;\r
+ while (it.hasNext()) {\r
+ // Retrieve file information: path, title and shortdesc.\r
+ tempInfo = (DocFileInfo) it.next();\r
+ tempPath = tempInfo.getFullpath().toString().replace(File.separatorChar, '/');\r
+ tempTitle = tempInfo.getTitle();\r
+ tempShortdesc = tempInfo.getShortdesc();\r
+ //Remove unwanted white char\r
+ if (tempTitle != null) {\r
+ tempTitle = tempTitle.replaceAll("\\s+", " ");\r
+ tempTitle = tempTitle.replaceAll("['�\"]", " ");\r
+ }\r
+ if (tempShortdesc != null) {\r
+ tempShortdesc = tempShortdesc.replaceAll("\\s+", " ");\r
+ tempShortdesc = tempShortdesc.replaceAll("['�\"]", " ");\r
+ }\r
+ //System.out.println("temp : "+File.separatorChar+" "+tempShortdesc);\r
+ out.write("fil[\"" + i + "\"]" + "= \"" + tempPath + "@@@" + tempTitle + "@@@" + tempShortdesc + "\";\n");\r
+ i++;\r
+ }\r
+\r
+ out.flush(); // Don't forget to flush!\r
+ out.close();\r
+\r
+ }\r
+ catch (UnsupportedEncodingException e) {\r
+ System.out.println(txt_VM_encoding_not_supported);\r
+ }\r
+ catch (IOException e) {\r
+ System.out.println(e.getMessage());\r
+ }\r
+\r
+ }\r
+\r
+ /**\r
+ * Create javascript index files alphabetically.\r
+ *\r
+ * @param fileOutStr contains the path and the suffix of the index files to create.\r
+ * The first letter of the key is added to the given suffix. For example: e.g. a.js, b.js etc...\r
+ * @param indexMap its keys are the indexed words and\r
+ * its values are the list of the files which contain the word.\r
+ * @param indexerLanguage The language of the content that gets indexed\r
+ */\r
+ public static void WriteIndex(String fileOutStr, Map<String, ?> indexMap, String indexerLanguage) {\r
+ OutputStreamWriter out;\r
+ OutputStream bout;\r
+ OutputStream fOut;\r
+ String tstr;\r
+\r
+ // check arguments\r
+ if (indexMap == null || fileOutStr == null) {\r
+ return;\r
+ }\r
+\r
+ // Collect the key of the index map\r
+ TreeSet<String> sortedKeys = new TreeSet<String>();\r
+ sortedKeys.addAll(indexMap.keySet());\r
+ Iterator keyIt = sortedKeys.iterator();\r
+ tstr = (String) keyIt.next();\r
+\r
+ File fileOut = new File(fileOutStr);\r
+\r
+ /* Writes the index to Three JS files, namely: index-1.js, index-2.js, index-3.js\r
+ * Index will be distributed evenly in these three files.\r
+ * tstr is the current key\r
+ * keyIt is the iterator of the key set\r
+ * */\r
+ int indexSize = sortedKeys.size();\r
+ for (int i = 1; i <= 3; i++) {\r
+ try {\r
+ // open a outputstream, here a file\r
+ fOut = new FileOutputStream(fileOut.getParent() + File.separator + "index-" + i + fileOut.getName());\r
+ bout = new BufferedOutputStream(fOut);\r
+ out = new OutputStreamWriter(bout, "UTF-8");\r
+\r
+ try {\r
+ /* Populate a javascript hashmap:\r
+ The key is a word to look for in the index,\r
+ The value is the numbers of the files in which the word exists.\r
+ Example: w["key"]="file1,file2,file3";*/\r
+ int count = 0;\r
+ if (i == 1)\r
+ out.write("var indexerLanguage=\"" + indexerLanguage + "\";\n");\r
+ out.write("//Auto generated index for searching.\n");\r
+ while (keyIt.hasNext()) { //&& (tempLetter == tstr.charAt(0))\r
+ out.write("w[\"" + tstr + "\"]" + "=\"" + indexMap.get(tstr) + "\";\n");\r
+ tstr = (String) keyIt.next();\r
+ count++;\r
+ if (indexSize / count < 3) {\r
+ break;\r
+ }\r
+ }\r
+ out.write("\n");\r
+ out.flush(); // Don't forget to flush!\r
+ out.close();\r
+ }\r
+ catch (UnsupportedEncodingException e) {\r
+ System.out.println(txt_VM_encoding_not_supported);\r
+ }\r
+ }\r
+ catch (IOException e) {\r
+ System.out.println(e.getMessage());\r
+ }\r
+ }\r
+ System.out.println(txt_indices_location + fileOutStr);\r
+ }\r
+\r
+\r
+ /**\r
+ * Create javascript index files alphabetically.\r
+ *\r
+ * @deprecated replaced by WriteIndex(String fileOutStr, Map<String, ?> indexMap, String indexerLanguage) { \r
+ *\r
+ * @param fileOutStr contains the path and the suffix of the index files to create.\r
+ * The first letter of the key is added to the given suffix. For example: e.g. a.js, b.js etc...\r
+ * @param indexMap its keys are the indexed words and\r
+ * its values are the list of the files which contain the word.\r
+ */\r
+\r
+\r
+ public static void WriteIndex(String fileOutStr, Map<String, ?> indexMap) {\r
+ OutputStreamWriter out;\r
+ OutputStream bout;\r
+ OutputStream fOut;\r
+ String tstr;\r
+\r
+ // check arguments\r
+ if (indexMap == null || fileOutStr == null) {\r
+ return;\r
+ }\r
+\r
+ // Collect the key of the index map\r
+ TreeSet<String> sortedKeys = new TreeSet<String>();\r
+ sortedKeys.addAll(indexMap.keySet());\r
+ Iterator keyIt = sortedKeys.iterator();\r
+ tstr = (String) keyIt.next();\r
+\r
+ File fileOut = new File(fileOutStr);\r
\r
/* Writes the index to Three JS files, namely: index-1.js, index-2.js, index-3.js\r
* Index will be distributed evenly in these three files. \r
* tstr is the current key\r
* keyIt is the iterator of the key set\r
* */\r
- int indexSize = sortedKeys.size(); \r
+ int indexSize = sortedKeys.size();\r
for (int i = 1; i <= 3; i++) {\r
try {\r
// open a outputstream, here a file\r
The value is the numbers of the files in which the word exists.\r
Example: w["key"]="file1,file2,file3";*/\r
int count = 0;\r
- if(i==1)\r
- out.write("var indexerLanguage=\""+IndexerTask.indexerLanguage+"\";\n");\r
+// if (i == 1)\r
+// out.write("var indexerLanguage=\"" + IndexerTask.indexerLanguage + "\";\n");\r
out.write("//Auto generated index for searching.\n");\r
while (keyIt.hasNext()) { //&& (tempLetter == tstr.charAt(0)) \r
out.write("w[\"" + tstr + "\"]" + "=\"" + indexMap.get(tstr) + "\";\n");\r
tstr = (String) keyIt.next();\r
count++;\r
- if (indexSize / count < 3){\r
+ if (indexSize / count < 3) {\r
break;\r
}\r
- } \r
+ }\r
out.write("\n");\r
out.flush(); // Don't forget to flush!\r
out.close();\r
catch (IOException e) {\r
System.out.println(e.getMessage());\r
}\r
- } \r
- System.out.println(txt_indices_location + fileOutStr);\r
- }\r
+ }\r
+ System.out.println(txt_indices_location + fileOutStr);\r
+ }\r
}\r
projects / docbook-dsssl / commitdiff